diff options
1598 files changed, 43125 insertions, 16954 deletions
diff --git a/Documentation/ABI/stable/sysfs-driver-mlxreg-io b/Documentation/ABI/stable/sysfs-driver-mlxreg-io index 9b642669cb16..169fe08a649b 100644 --- a/Documentation/ABI/stable/sysfs-driver-mlxreg-io +++ b/Documentation/ABI/stable/sysfs-driver-mlxreg-io @@ -24,7 +24,7 @@ What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/ cpld3_version Date: November 2018 -KernelVersion: 4.21 +KernelVersion: 5.0 Contact: Vadim Pasternak <vadimpmellanox.com> Description: These files show with which CPLD versions have been burned on LED board. @@ -35,7 +35,7 @@ What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/ jtag_enable Date: November 2018 -KernelVersion: 4.21 +KernelVersion: 5.0 Contact: Vadim Pasternak <vadimpmellanox.com> Description: These files enable and disable the access to the JTAG domain. By default access to the JTAG domain is disabled. @@ -105,7 +105,7 @@ What: /sys/devices/platform/mlxplat/mlxreg-io/hwmon/hwmon*/ reset_voltmon_upgrade_fail Date: November 2018 -KernelVersion: 4.21 +KernelVersion: 5.0 Contact: Vadim Pasternak <vadimpmellanox.com> Description: These files show the system reset cause, as following: ComEx power fail, reset from ComEx, system platform reset, reset diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index b799bcf67d7b..bcf2cd519d1e 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -461,6 +461,11 @@ possible to determine what the correct size should be. This option provides an override for these situations. + carrier_timeout= + [NET] Specifies amount of time (in seconds) that + the kernel should wait for a network carrier. By default + it waits 120 seconds. + ca_keys= [KEYS] This parameter identifies a specific key(s) on the system trusted keyring to be used for certificate trust validation. @@ -1696,12 +1701,11 @@ By default, super page will be supported if Intel IOMMU has the capability. With this option, super page will not be supported. - sm_off [Default Off] - By default, scalable mode will be supported if the + sm_on [Default Off] + By default, scalable mode will be disabled even if the hardware advertises that it has support for the scalable mode translation. With this option set, scalable mode - will not be used even on hardware which claims to support - it. + will be used on hardware which claims to support it. tboot_noforce [Default Off] Do not force the Intel IOMMU enabled under tboot. By default, tboot will force Intel IOMMU on, which diff --git a/Documentation/devicetree/bindings/Makefile b/Documentation/devicetree/bindings/Makefile index 6e5cef0ed6fb..50daa0b3b032 100644 --- a/Documentation/devicetree/bindings/Makefile +++ b/Documentation/devicetree/bindings/Makefile @@ -17,7 +17,11 @@ extra-y += $(DT_TMP_SCHEMA) quiet_cmd_mk_schema = SCHEMA $@ cmd_mk_schema = $(DT_MK_SCHEMA) $(DT_MK_SCHEMA_FLAGS) -o $@ $(filter-out FORCE, $^) -DT_DOCS = $(shell cd $(srctree)/$(src) && find * -name '*.yaml') +DT_DOCS = $(shell \ + cd $(srctree)/$(src) && \ + find * \( -name '*.yaml' ! -name $(DT_TMP_SCHEMA) \) \ + ) + DT_SCHEMA_FILES ?= $(addprefix $(src)/,$(DT_DOCS)) extra-y += $(patsubst $(src)/%.yaml,%.example.dts, $(DT_SCHEMA_FILES)) diff --git a/Documentation/devicetree/bindings/net/dsa/mt7530.txt b/Documentation/devicetree/bindings/net/dsa/mt7530.txt index aa3527f71fdc..47aa205ee0bd 100644 --- a/Documentation/devicetree/bindings/net/dsa/mt7530.txt +++ b/Documentation/devicetree/bindings/net/dsa/mt7530.txt @@ -3,12 +3,16 @@ Mediatek MT7530 Ethernet switch Required properties: -- compatible: Must be compatible = "mediatek,mt7530"; +- compatible: may be compatible = "mediatek,mt7530" + or compatible = "mediatek,mt7621" - #address-cells: Must be 1. - #size-cells: Must be 0. - mediatek,mcm: Boolean; if defined, indicates that either MT7530 is the part on multi-chip module belong to MT7623A has or the remotely standalone chip as the function MT7623N reference board provided for. + +If compatible mediatek,mt7530 is set then the following properties are required + - core-supply: Phandle to the regulator node necessary for the core power. - io-supply: Phandle to the regulator node necessary for the I/O power. See Documentation/devicetree/bindings/regulator/mt6323-regulator.txt diff --git a/Documentation/devicetree/bindings/net/macb.txt b/Documentation/devicetree/bindings/net/macb.txt index 3e17ac1d5d58..174f292d8a3e 100644 --- a/Documentation/devicetree/bindings/net/macb.txt +++ b/Documentation/devicetree/bindings/net/macb.txt @@ -3,8 +3,8 @@ Required properties: - compatible: Should be "cdns,[<chip>-]{macb|gem}" Use "cdns,at91rm9200-emac" Atmel at91rm9200 SoC. - Use "cdns,at91sam9260-macb" for Atmel at91sam9 SoCs or the 10/100Mbit IP - available on sama5d3 SoCs. + Use "cdns,at91sam9260-macb" for Atmel at91sam9 SoCs. + Use "cdns,sam9x60-macb" for Microchip sam9x60 SoC. Use "cdns,np4-macb" for NP4 SoC devices. Use "cdns,at32ap7000-macb" for other 10/100 usage or use the generic form: "cdns,macb". Use "cdns,pc302-gem" for Picochip picoXcell pc302 and later devices based on diff --git a/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt b/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt index bedcfd5a52cd..691f886cfc4a 100644 --- a/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt +++ b/Documentation/devicetree/bindings/net/marvell-armada-370-neta.txt @@ -19,7 +19,7 @@ Optional properties: "marvell,armada-370-neta" and 9800B for others. - clock-names: List of names corresponding to clocks property; shall be "core" for core clock and "bus" for the optional bus clock. - +- phys: comphy for the ethernet port, see ../phy/phy-bindings.txt Optional properties (valid only for Armada XP/38x): diff --git a/Documentation/devicetree/bindings/net/nixge.txt b/Documentation/devicetree/bindings/net/nixge.txt index e55af7f0881a..85d7240a9b20 100644 --- a/Documentation/devicetree/bindings/net/nixge.txt +++ b/Documentation/devicetree/bindings/net/nixge.txt @@ -1,17 +1,53 @@ * NI XGE Ethernet controller Required properties: -- compatible: Should be "ni,xge-enet-2.00" -- reg: Address and length of the register set for the device +- compatible: Should be "ni,xge-enet-3.00", but can be "ni,xge-enet-2.00" for + older device trees with DMA engines co-located in the address map, + with the one reg entry to describe the whole device. +- reg: Address and length of the register set for the device. It contains the + information of registers in the same order as described by reg-names. +- reg-names: Should contain the reg names + "dma": DMA engine control and status region + "ctrl": MDIO and PHY control and status region - interrupts: Should contain tx and rx interrupt - interrupt-names: Should be "rx" and "tx" - phy-mode: See ethernet.txt file in the same directory. -- phy-handle: See ethernet.txt file in the same directory. - nvmem-cells: Phandle of nvmem cell containing the MAC address - nvmem-cell-names: Should be "address" +Optional properties: +- mdio subnode to indicate presence of MDIO controller +- fixed-link : Assume a fixed link. See fixed-link.txt in the same directory. + Use instead of phy-handle. +- phy-handle: See ethernet.txt file in the same directory. + Examples (10G generic PHY): nixge0: ethernet@40000000 { + compatible = "ni,xge-enet-3.00"; + reg = <0x40000000 0x4000 + 0x41002000 0x2000>; + reg-names = "dma", "ctrl"; + + nvmem-cells = <ð1_addr>; + nvmem-cell-names = "address"; + + interrupts = <0 29 IRQ_TYPE_LEVEL_HIGH>, <0 30 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "rx", "tx"; + interrupt-parent = <&intc>; + + phy-mode = "xgmii"; + phy-handle = <ðernet_phy1>; + + mdio { + ethernet_phy1: ethernet-phy@4 { + compatible = "ethernet-phy-ieee802.3-c45"; + reg = <4>; + }; + }; + }; + +Examples (10G generic PHY, no MDIO): + nixge0: ethernet@40000000 { compatible = "ni,xge-enet-2.00"; reg = <0x40000000 0x6000>; @@ -24,9 +60,33 @@ Examples (10G generic PHY): phy-mode = "xgmii"; phy-handle = <ðernet_phy1>; + }; + +Examples (1G generic fixed-link + MDIO): + nixge0: ethernet@40000000 { + compatible = "ni,xge-enet-2.00"; + reg = <0x40000000 0x6000>; - ethernet_phy1: ethernet-phy@4 { - compatible = "ethernet-phy-ieee802.3-c45"; - reg = <4>; + nvmem-cells = <ð1_addr>; + nvmem-cell-names = "address"; + + interrupts = <0 29 IRQ_TYPE_LEVEL_HIGH>, <0 30 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "rx", "tx"; + interrupt-parent = <&intc>; + + phy-mode = "xgmii"; + + fixed-link { + speed = <1000>; + pause; + link-gpios = <&gpio0 63 GPIO_ACTIVE_HIGH>; + }; + + mdio { + ethernet_phy1: ethernet-phy@4 { + compatible = "ethernet-phy-ieee802.3-c22"; + reg = <4>; + }; }; + }; diff --git a/Documentation/devicetree/bindings/phy/phy-armada38x-comphy.txt b/Documentation/devicetree/bindings/phy/phy-armada38x-comphy.txt new file mode 100644 index 000000000000..ad49e5c01334 --- /dev/null +++ b/Documentation/devicetree/bindings/phy/phy-armada38x-comphy.txt @@ -0,0 +1,40 @@ +mvebu armada 38x comphy driver +------------------------------ + +This comphy controller can be found on Marvell Armada 38x. It provides a +number of shared PHYs used by various interfaces (network, sata, usb, +PCIe...). + +Required properties: + +- compatible: should be "marvell,armada-380-comphy" +- reg: should contain the comphy register location and length. +- #address-cells: should be 1. +- #size-cells: should be 0. + +A sub-node is required for each comphy lane provided by the comphy. + +Required properties (child nodes): + +- reg: comphy lane number. +- #phy-cells : from the generic phy bindings, must be 1. Defines the + input port to use for a given comphy lane. + +Example: + + comphy: phy@18300 { + compatible = "marvell,armada-380-comphy"; + reg = <0x18300 0x100>; + #address-cells = <1>; + #size-cells = <0>; + + cpm_comphy0: phy@0 { + reg = <0>; + #phy-cells = <1>; + }; + + cpm_comphy1: phy@1 { + reg = <1>; + #phy-cells = <1>; + }; + }; diff --git a/Documentation/devicetree/bindings/ptp/ptp-qoriq.txt b/Documentation/devicetree/bindings/ptp/ptp-qoriq.txt index 8e7f8551d190..454c937076a2 100644 --- a/Documentation/devicetree/bindings/ptp/ptp-qoriq.txt +++ b/Documentation/devicetree/bindings/ptp/ptp-qoriq.txt @@ -19,6 +19,9 @@ Clock Properties: - fsl,max-adj Maximum frequency adjustment in parts per billion. - fsl,extts-fifo The presence of this property indicates hardware support for the external trigger stamp FIFO. + - little-endian The presence of this property indicates the 1588 timer + IP block is little-endian mode. The default endian mode + is big-endian. These properties set the operational parameters for the PTP clock. You must choose these carefully for the clock to work right. diff --git a/Documentation/devicetree/bindings/serio/olpc,ap-sp.txt b/Documentation/devicetree/bindings/serio/olpc,ap-sp.txt index 36603419d6f8..0e72183f52bc 100644 --- a/Documentation/devicetree/bindings/serio/olpc,ap-sp.txt +++ b/Documentation/devicetree/bindings/serio/olpc,ap-sp.txt @@ -4,14 +4,10 @@ Required properties: - compatible : "olpc,ap-sp" - reg : base address and length of SoC's WTM registers - interrupts : SP-AP interrupt -- clocks : phandle + clock-specifier for the clock that drives the WTM -- clock-names: should be "sp" Example: ap-sp@d4290000 { compatible = "olpc,ap-sp"; reg = <0xd4290000 0x1000>; interrupts = <40>; - clocks = <&soc_clocks MMP2_CLK_SP>; - clock-names = "sp"; } diff --git a/Documentation/driver-api/80211/mac80211.rst b/Documentation/driver-api/80211/mac80211.rst index 85a8335e80b6..eab40bcf3987 100644 --- a/Documentation/driver-api/80211/mac80211.rst +++ b/Documentation/driver-api/80211/mac80211.rst @@ -126,6 +126,9 @@ functions/definitions :functions: ieee80211_rx_status .. kernel-doc:: include/net/mac80211.h + :functions: mac80211_rx_encoding_flags + +.. kernel-doc:: include/net/mac80211.h :functions: mac80211_rx_flags .. kernel-doc:: include/net/mac80211.h diff --git a/Documentation/networking/device_drivers/freescale/dpaa2/dpio-driver.rst b/Documentation/networking/device_drivers/freescale/dpaa2/dpio-driver.rst index a188466b6698..5045df990a4c 100644 --- a/Documentation/networking/device_drivers/freescale/dpaa2/dpio-driver.rst +++ b/Documentation/networking/device_drivers/freescale/dpaa2/dpio-driver.rst @@ -27,11 +27,12 @@ Driver Overview The DPIO driver is bound to DPIO objects discovered on the fsl-mc bus and provides services that: - A) allow other drivers, such as the Ethernet driver, to enqueue and dequeue + + A. allow other drivers, such as the Ethernet driver, to enqueue and dequeue frames for their respective objects - B) allow drivers to register callbacks for data availability notifications + B. allow drivers to register callbacks for data availability notifications when data becomes available on a queue or channel - C) allow drivers to manage hardware buffer pools + C. allow drivers to manage hardware buffer pools The Linux DPIO driver consists of 3 primary components-- DPIO object driver-- fsl-mc driver that manages the DPIO object @@ -140,11 +141,10 @@ QBman portal interface (qbman-portal.c) The qbman-portal component provides APIs to do the low level hardware bit twiddling for operations such as: - -initializing Qman software portals - - -building and sending portal commands - -portal interrupt configuration and processing + - initializing Qman software portals + - building and sending portal commands + - portal interrupt configuration and processing The qbman-portal APIs are not public to other drivers, and are only used by dpio-service. diff --git a/Documentation/networking/device_drivers/intel/e100.rst b/Documentation/networking/device_drivers/intel/e100.rst index 5e2839b4ec92..2b9f4887beda 100644 --- a/Documentation/networking/device_drivers/intel/e100.rst +++ b/Documentation/networking/device_drivers/intel/e100.rst @@ -1,5 +1,6 @@ .. SPDX-License-Identifier: GPL-2.0+ +============================================================== Linux* Base Driver for the Intel(R) PRO/100 Family of Adapters ============================================================== diff --git a/Documentation/networking/device_drivers/intel/e1000.rst b/Documentation/networking/device_drivers/intel/e1000.rst index 6379d4d20771..956560b6e745 100644 --- a/Documentation/networking/device_drivers/intel/e1000.rst +++ b/Documentation/networking/device_drivers/intel/e1000.rst @@ -1,5 +1,6 @@ .. SPDX-License-Identifier: GPL-2.0+ +=========================================================== Linux* Base Driver for Intel(R) Ethernet Network Connection =========================================================== diff --git a/Documentation/networking/device_drivers/intel/e1000e.rst b/Documentation/networking/device_drivers/intel/e1000e.rst index 33554e5416c5..01999f05509c 100644 --- a/Documentation/networking/device_drivers/intel/e1000e.rst +++ b/Documentation/networking/device_drivers/intel/e1000e.rst @@ -1,5 +1,6 @@ .. SPDX-License-Identifier: GPL-2.0+ +====================================================== Linux* Driver for Intel(R) Ethernet Network Connection ====================================================== diff --git a/Documentation/networking/device_drivers/intel/fm10k.rst b/Documentation/networking/device_drivers/intel/fm10k.rst index bf5e5942f28d..ac3269e34f55 100644 --- a/Documentation/networking/device_drivers/intel/fm10k.rst +++ b/Documentation/networking/device_drivers/intel/fm10k.rst @@ -1,5 +1,6 @@ .. SPDX-License-Identifier: GPL-2.0+ +============================================================== Linux* Base Driver for Intel(R) Ethernet Multi-host Controller ============================================================== diff --git a/Documentation/networking/device_drivers/intel/i40e.rst b/Documentation/networking/device_drivers/intel/i40e.rst index 0cc16c525d10..848fd388fa6e 100644 --- a/Documentation/networking/device_drivers/intel/i40e.rst +++ b/Documentation/networking/device_drivers/intel/i40e.rst @@ -1,5 +1,6 @@ .. SPDX-License-Identifier: GPL-2.0+ +================================================================== Linux* Base Driver for the Intel(R) Ethernet Controller 700 Series ================================================================== diff --git a/Documentation/networking/device_drivers/intel/iavf.rst b/Documentation/networking/device_drivers/intel/iavf.rst index f8b42b64eb28..2d0c3baa1752 100644 --- a/Documentation/networking/device_drivers/intel/iavf.rst +++ b/Documentation/networking/device_drivers/intel/iavf.rst @@ -1,5 +1,6 @@ .. SPDX-License-Identifier: GPL-2.0+ +================================================================== Linux* Base Driver for Intel(R) Ethernet Adaptive Virtual Function ================================================================== diff --git a/Documentation/networking/device_drivers/intel/ice.rst b/Documentation/networking/device_drivers/intel/ice.rst index 4d118b827bbb..c220aa2711c6 100644 --- a/Documentation/networking/device_drivers/intel/ice.rst +++ b/Documentation/networking/device_drivers/intel/ice.rst @@ -1,5 +1,6 @@ .. SPDX-License-Identifier: GPL-2.0+ +=================================================================== Linux* Base Driver for the Intel(R) Ethernet Connection E800 Series =================================================================== diff --git a/Documentation/networking/device_drivers/intel/igb.rst b/Documentation/networking/device_drivers/intel/igb.rst index e87a4a72ea2d..fc8cfaa5dcfa 100644 --- a/Documentation/networking/device_drivers/intel/igb.rst +++ b/Documentation/networking/device_drivers/intel/igb.rst @@ -1,5 +1,6 @@ .. SPDX-License-Identifier: GPL-2.0+ +=========================================================== Linux* Base Driver for Intel(R) Ethernet Network Connection =========================================================== diff --git a/Documentation/networking/device_drivers/intel/igbvf.rst b/Documentation/networking/device_drivers/intel/igbvf.rst index a8a9ffa4f8d3..9cddabe8108e 100644 --- a/Documentation/networking/device_drivers/intel/igbvf.rst +++ b/Documentation/networking/device_drivers/intel/igbvf.rst @@ -1,5 +1,6 @@ .. SPDX-License-Identifier: GPL-2.0+ +============================================================ Linux* Base Virtual Function Driver for Intel(R) 1G Ethernet ============================================================ diff --git a/Documentation/networking/device_drivers/intel/ixgb.rst b/Documentation/networking/device_drivers/intel/ixgb.rst index 8bd80e27843d..945018207a92 100644 --- a/Documentation/networking/device_drivers/intel/ixgb.rst +++ b/Documentation/networking/device_drivers/intel/ixgb.rst @@ -1,5 +1,6 @@ .. SPDX-License-Identifier: GPL-2.0+ +===================================================================== Linux Base Driver for 10 Gigabit Intel(R) Ethernet Network Connection ===================================================================== diff --git a/Documentation/networking/device_drivers/intel/ixgbe.rst b/Documentation/networking/device_drivers/intel/ixgbe.rst index 86d887a63606..c7d25483fedb 100644 --- a/Documentation/networking/device_drivers/intel/ixgbe.rst +++ b/Documentation/networking/device_drivers/intel/ixgbe.rst @@ -1,5 +1,6 @@ .. SPDX-License-Identifier: GPL-2.0+ +============================================================================= Linux* Base Driver for the Intel(R) Ethernet 10 Gigabit PCI Express Adapters ============================================================================= diff --git a/Documentation/networking/device_drivers/intel/ixgbevf.rst b/Documentation/networking/device_drivers/intel/ixgbevf.rst index 56cde6366c2f..5d4977360157 100644 --- a/Documentation/networking/device_drivers/intel/ixgbevf.rst +++ b/Documentation/networking/device_drivers/intel/ixgbevf.rst @@ -1,5 +1,6 @@ .. SPDX-License-Identifier: GPL-2.0+ +============================================================= Linux* Base Virtual Function Driver for Intel(R) 10G Ethernet ============================================================= diff --git a/Documentation/networking/device_drivers/stmicro/stmmac.txt b/Documentation/networking/device_drivers/stmicro/stmmac.txt index 2bb07078f535..1ae979fd90d2 100644 --- a/Documentation/networking/device_drivers/stmicro/stmmac.txt +++ b/Documentation/networking/device_drivers/stmicro/stmmac.txt @@ -267,7 +267,7 @@ static struct fixed_phy_status stmmac0_fixed_phy_status = { During the board's device_init we can configure the first MAC for fixed_link by calling: - fixed_phy_add(PHY_POLL, 1, &stmmac0_fixed_phy_status, -1); + fixed_phy_add(PHY_POLL, 1, &stmmac0_fixed_phy_status); and the second one, with a real PHY device attached to the bus, by using the stmmac_mdio_bus_data structure (to provide the id, the reset procedure etc). diff --git a/Documentation/networking/devlink-health.txt b/Documentation/networking/devlink-health.txt new file mode 100644 index 000000000000..1db3fbea0831 --- /dev/null +++ b/Documentation/networking/devlink-health.txt @@ -0,0 +1,86 @@ +The health mechanism is targeted for Real Time Alerting, in order to know when +something bad had happened to a PCI device +- Provide alert debug information +- Self healing +- If problem needs vendor support, provide a way to gather all needed debugging + information. + +The main idea is to unify and centralize driver health reports in the +generic devlink instance and allow the user to set different +attributes of the health reporting and recovery procedures. + +The devlink health reporter: +Device driver creates a "health reporter" per each error/health type. +Error/Health type can be a known/generic (eg pci error, fw error, rx/tx error) +or unknown (driver specific). +For each registered health reporter a driver can issue error/health reports +asynchronously. All health reports handling is done by devlink. +Device driver can provide specific callbacks for each "health reporter", e.g. + - Recovery procedures + - Diagnostics and object dump procedures + - OOB initial parameters +Different parts of the driver can register different types of health reporters +with different handlers. + +Once an error is reported, devlink health will do the following actions: + * A log is being send to the kernel trace events buffer + * Health status and statistics are being updated for the reporter instance + * Object dump is being taken and saved at the reporter instance (as long as + there is no other dump which is already stored) + * Auto recovery attempt is being done. Depends on: + - Auto-recovery configuration + - Grace period vs. time passed since last recover + +The user interface: +User can access/change each reporter's parameters and driver specific callbacks +via devlink, e.g per error type (per health reporter) + - Configure reporter's generic parameters (like: disable/enable auto recovery) + - Invoke recovery procedure + - Run diagnostics + - Object dump + +The devlink health interface (via netlink): +DEVLINK_CMD_HEALTH_REPORTER_GET + Retrieves status and configuration info per DEV and reporter. +DEVLINK_CMD_HEALTH_REPORTER_SET + Allows reporter-related configuration setting. +DEVLINK_CMD_HEALTH_REPORTER_RECOVER + Triggers a reporter's recovery procedure. +DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE + Retrieves diagnostics data from a reporter on a device. +DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET + Retrieves the last stored dump. Devlink health + saves a single dump. If an dump is not already stored by the devlink + for this reporter, devlink generates a new dump. + dump output is defined by the reporter. +DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR + Clears the last saved dump file for the specified reporter. + + + netlink + +--------------------------+ + | | + | + | + | | | + +--------------------------+ + |request for ops + |(diagnose, + mlx5_core devlink |recover, + |dump) ++--------+ +--------------------------+ +| | | reporter| | +| | | +---------v----------+ | +| | ops execution | | | | +| <----------------------------------+ | | +| | | | | | +| | | + ^------------------+ | +| | | | request for ops | +| | | | (recover, dump) | +| | | | | +| | | +-+------------------+ | +| | health report | | health handler | | +| +-------------------------------> | | +| | | +--------------------+ | +| | health reporter create | | +| +----------------------------> | ++--------+ +--------------------------+ diff --git a/Documentation/networking/devlink-info-versions.rst b/Documentation/networking/devlink-info-versions.rst new file mode 100644 index 000000000000..c79ad8593383 --- /dev/null +++ b/Documentation/networking/devlink-info-versions.rst @@ -0,0 +1,43 @@ +.. SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +===================== +Devlink info versions +===================== + +board.id +======== + +Unique identifier of the board design. + +board.rev +========= + +Board design revision. + +board.manufacture +================= + +An identifier of the company or the facility which produced the part. + +fw.mgmt +======= + +Control unit firmware version. This firmware is responsible for house +keeping tasks, PHY control etc. but not the packet-by-packet data path +operation. + +fw.app +====== + +Data path microcode controlling high-speed packet processing. + +fw.undi +======= + +UNDI software, may include the UEFI driver, firmware or both. + +fw.ncsi +======= + +Version of the software responsible for supporting/handling the +Network Controller Sideband Interface. diff --git a/Documentation/networking/devlink-params-mlxsw.txt b/Documentation/networking/devlink-params-mlxsw.txt index 2c5c67a920c9..c63ea9fc7009 100644 --- a/Documentation/networking/devlink-params-mlxsw.txt +++ b/Documentation/networking/devlink-params-mlxsw.txt @@ -1,2 +1,10 @@ fw_load_policy [DEVICE, GENERIC] Configuration mode: driverinit + +acl_region_rehash_interval [DEVICE, DRIVER-SPECIFIC] + Sets an interval for periodic ACL region rehashes. + The value is in milliseconds, minimal value is "3000". + Value "0" disables the periodic work. + The first rehash will be run right after value is set. + Type: u32 + Configuration mode: runtime diff --git a/Documentation/networking/filter.txt b/Documentation/networking/filter.txt index 01603bc2eff1..b5e060edfc38 100644 --- a/Documentation/networking/filter.txt +++ b/Documentation/networking/filter.txt @@ -464,10 +464,11 @@ breakpoints: 0 1 JIT compiler ------------ -The Linux kernel has a built-in BPF JIT compiler for x86_64, SPARC, PowerPC, -ARM, ARM64, MIPS and s390 and can be enabled through CONFIG_BPF_JIT. The JIT -compiler is transparently invoked for each attached filter from user space -or for internal kernel users if it has been previously enabled by root: +The Linux kernel has a built-in BPF JIT compiler for x86_64, SPARC, +PowerPC, ARM, ARM64, MIPS, RISC-V and s390 and can be enabled through +CONFIG_BPF_JIT. The JIT compiler is transparently invoked for each +attached filter from user space or for internal kernel users if it has +been previously enabled by root: echo 1 > /proc/sys/net/core/bpf_jit_enable @@ -603,9 +604,10 @@ got from bpf_prog_create(), and 'ctx' the given context (e.g. skb pointer). All constraints and restrictions from bpf_check_classic() apply before a conversion to the new layout is being done behind the scenes! -Currently, the classic BPF format is being used for JITing on most 32-bit -architectures, whereas x86-64, aarch64, s390x, powerpc64, sparc64, arm32 perform -JIT compilation from eBPF instruction set. +Currently, the classic BPF format is being used for JITing on most +32-bit architectures, whereas x86-64, aarch64, s390x, powerpc64, +sparc64, arm32, riscv (RV64G) perform JIT compilation from eBPF +instruction set. Some core changes of the new internal format: diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index f1627ca2a0ea..9a32451cd201 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -24,6 +24,7 @@ Contents: device_drivers/intel/i40e device_drivers/intel/iavf device_drivers/intel/ice + devlink-info-versions kapi z8530book msg_zerocopy diff --git a/Documentation/networking/operstates.txt b/Documentation/networking/operstates.txt index 355c6d8ef8ad..b203d1334822 100644 --- a/Documentation/networking/operstates.txt +++ b/Documentation/networking/operstates.txt @@ -22,8 +22,9 @@ and changeable from userspace under certain rules. 2. Querying from userspace Both admin and operational state can be queried via the netlink -operation RTM_GETLINK. It is also possible to subscribe to RTMGRP_LINK -to be notified of updates. This is important for setting from userspace. +operation RTM_GETLINK. It is also possible to subscribe to RTNLGRP_LINK +to be notified of updates while the interface is admin up. This is +important for setting from userspace. These values contain interface state: @@ -101,8 +102,9 @@ because some driver controlled protocol establishment has to complete. Corresponding functions are netif_dormant_on() to set the flag, netif_dormant_off() to clear it and netif_dormant() to query. -On device allocation, networking core sets the flags equivalent to -netif_carrier_ok() and !netif_dormant(). +On device allocation, both flags __LINK_STATE_NOCARRIER and +__LINK_STATE_DORMANT are cleared, so the effective state is equivalent +to netif_carrier_ok() and !netif_dormant(). Whenever the driver CHANGES one of these flags, a workqueue event is @@ -133,11 +135,11 @@ netif_carrier_ok() && !netif_dormant() is set by the driver. Afterwards, the userspace application can set IFLA_OPERSTATE to IF_OPER_DORMANT or IF_OPER_UP as long as the driver does not set netif_carrier_off() or netif_dormant_on(). Changes made by userspace -are multicasted on the netlink group RTMGRP_LINK. +are multicasted on the netlink group RTNLGRP_LINK. So basically a 802.1X supplicant interacts with the kernel like this: --subscribe to RTMGRP_LINK +-subscribe to RTNLGRP_LINK -set IFLA_LINKMODE to 1 via RTM_SETLINK -query RTM_GETLINK once to get initial state -if initial flags are not (IFF_LOWER_UP && !IFF_DORMANT), wait until diff --git a/Documentation/networking/snmp_counter.rst b/Documentation/networking/snmp_counter.rst index c5642f430d2e..52b026be028f 100644 --- a/Documentation/networking/snmp_counter.rst +++ b/Documentation/networking/snmp_counter.rst @@ -367,16 +367,19 @@ to the accept queue. TCP Fast Open ============= * TcpEstabResets + Defined in `RFC1213 tcpEstabResets`_. .. _RFC1213 tcpEstabResets: https://tools.ietf.org/html/rfc1213#page-48 * TcpAttemptFails + Defined in `RFC1213 tcpAttemptFails`_. .. _RFC1213 tcpAttemptFails: https://tools.ietf.org/html/rfc1213#page-48 * TcpOutRsts + Defined in `RFC1213 tcpOutRsts`_. The RFC says this counter indicates the 'segments sent containing the RST flag', but in linux kernel, this couner indicates the segments kerenl tried to send. The sending @@ -384,6 +387,30 @@ process might be failed due to some errors (e.g. memory alloc failed). .. _RFC1213 tcpOutRsts: https://tools.ietf.org/html/rfc1213#page-52 +* TcpExtTCPSpuriousRtxHostQueues + +When the TCP stack wants to retransmit a packet, and finds that packet +is not lost in the network, but the packet is not sent yet, the TCP +stack would give up the retransmission and update this counter. It +might happen if a packet stays too long time in a qdisc or driver +queue. + +* TcpEstabResets + +The socket receives a RST packet in Establish or CloseWait state. + +* TcpExtTCPKeepAlive + +This counter indicates many keepalive packets were sent. The keepalive +won't be enabled by default. A userspace program could enable it by +setting the SO_KEEPALIVE socket option. + +* TcpExtTCPSpuriousRTOs + +The spurious retransmission timeout detected by the `F-RTO`_ +algorithm. + +.. _F-RTO: https://tools.ietf.org/html/rfc5682 TCP Fast Path ============ @@ -609,6 +636,29 @@ packet yet, the sender would know packet 4 is out of order. The TCP stack of kernel will increase TcpExtTCPSACKReorder for both of the above scenarios. +* TcpExtTCPSlowStartRetrans + +The TCP stack wants to retransmit a packet and the congestion control +state is 'Loss'. + +* TcpExtTCPFastRetrans + +The TCP stack wants to retransmit a packet and the congestion control +state is not 'Loss'. + +* TcpExtTCPLostRetransmit + +A SACK points out that a retransmission packet is lost again. + +* TcpExtTCPRetransFail + +The TCP stack tries to deliver a retransmission packet to lower layers +but the lower layers return an error. + +* TcpExtTCPSynRetrans + +The TCP stack retransmits a SYN packet. + DSACK ===== The DSACK is defined in `RFC2883`_. The receiver uses DSACK to report @@ -790,8 +840,9 @@ unacknowledged number (more strict than `RFC 5961 section 5.2`_). .. _RFC 5961 section 5.2: https://tools.ietf.org/html/rfc5961#page-11 TCP receive window -================= +================== * TcpExtTCPWantZeroWindowAdv + Depending on current memory usage, the TCP stack tries to set receive window to zero. But the receive window might still be a no-zero value. For example, if the previous window size is 10, and the TCP @@ -799,14 +850,16 @@ stack receives 3 bytes, the current window size would be 7 even if the window size calculated by the memory usage is zero. * TcpExtTCPToZeroWindowAdv + The TCP receive window is set to zero from a no-zero value. * TcpExtTCPFromZeroWindowAdv + The TCP receive window is set to no-zero value from zero. Delayed ACK -========== +=========== The TCP Delayed ACK is a technique which is used for reducing the packet count in the network. For more details, please refer the `Delayed ACK wiki`_ @@ -814,10 +867,12 @@ packet count in the network. For more details, please refer the .. _Delayed ACK wiki: https://en.wikipedia.org/wiki/TCP_delayed_acknowledgment * TcpExtDelayedACKs + A delayed ACK timer expires. The TCP stack will send a pure ACK packet and exit the delayed ACK mode. * TcpExtDelayedACKLocked + A delayed ACK timer expires, but the TCP stack can't send an ACK immediately due to the socket is locked by a userspace program. The TCP stack will send a pure ACK later (after the userspace program @@ -826,24 +881,147 @@ TCP stack will also update TcpExtDelayedACKs and exit the delayed ACK mode. * TcpExtDelayedACKLost + It will be updated when the TCP stack receives a packet which has been ACKed. A Delayed ACK loss might cause this issue, but it would also be triggered by other reasons, such as a packet is duplicated in the network. Tail Loss Probe (TLP) -=================== +===================== TLP is an algorithm which is used to detect TCP packet loss. For more details, please refer the `TLP paper`_. .. _TLP paper: https://tools.ietf.org/html/draft-dukkipati-tcpm-tcp-loss-probe-01 * TcpExtTCPLossProbes + A TLP probe packet is sent. * TcpExtTCPLossProbeRecovery + A packet loss is detected and recovered by TLP. +TCP Fast Open +============= +TCP Fast Open is a technology which allows data transfer before the +3-way handshake complete. Please refer the `TCP Fast Open wiki`_ for a +general description. + +.. _TCP Fast Open wiki: https://en.wikipedia.org/wiki/TCP_Fast_Open + +* TcpExtTCPFastOpenActive + +When the TCP stack receives an ACK packet in the SYN-SENT status, and +the ACK packet acknowledges the data in the SYN packet, the TCP stack +understand the TFO cookie is accepted by the other side, then it +updates this counter. + +* TcpExtTCPFastOpenActiveFail + +This counter indicates that the TCP stack initiated a TCP Fast Open, +but it failed. This counter would be updated in three scenarios: (1) +the other side doesn't acknowledge the data in the SYN packet. (2) The +SYN packet which has the TFO cookie is timeout at least once. (3) +after the 3-way handshake, the retransmission timeout happens +net.ipv4.tcp_retries1 times, because some middle-boxes may black-hole +fast open after the handshake. + +* TcpExtTCPFastOpenPassive + +This counter indicates how many times the TCP stack accepts the fast +open request. + +* TcpExtTCPFastOpenPassiveFail + +This counter indicates how many times the TCP stack rejects the fast +open request. It is caused by either the TFO cookie is invalid or the +TCP stack finds an error during the socket creating process. + +* TcpExtTCPFastOpenListenOverflow + +When the pending fast open request number is larger than +fastopenq->max_qlen, the TCP stack will reject the fast open request +and update this counter. When this counter is updated, the TCP stack +won't update TcpExtTCPFastOpenPassive or +TcpExtTCPFastOpenPassiveFail. The fastopenq->max_qlen is set by the +TCP_FASTOPEN socket operation and it could not be larger than +net.core.somaxconn. For example: + +setsockopt(sfd, SOL_TCP, TCP_FASTOPEN, &qlen, sizeof(qlen)); + +* TcpExtTCPFastOpenCookieReqd + +This counter indicates how many times a client wants to request a TFO +cookie. + +SYN cookies +=========== +SYN cookies are used to mitigate SYN flood, for details, please refer +the `SYN cookies wiki`_. + +.. _SYN cookies wiki: https://en.wikipedia.org/wiki/SYN_cookies + +* TcpExtSyncookiesSent + +It indicates how many SYN cookies are sent. + +* TcpExtSyncookiesRecv + +How many reply packets of the SYN cookies the TCP stack receives. + +* TcpExtSyncookiesFailed + +The MSS decoded from the SYN cookie is invalid. When this counter is +updated, the received packet won't be treated as a SYN cookie and the +TcpExtSyncookiesRecv counter wont be updated. + +Challenge ACK +============= +For details of challenge ACK, please refer the explaination of +TcpExtTCPACKSkippedChallenge. + +* TcpExtTCPChallengeACK + +The number of challenge acks sent. + +* TcpExtTCPSYNChallenge + +The number of challenge acks sent in response to SYN packets. After +updates this counter, the TCP stack might send a challenge ACK and +update the TcpExtTCPChallengeACK counter, or it might also skip to +send the challenge and update the TcpExtTCPACKSkippedChallenge. + +prune +===== +When a socket is under memory pressure, the TCP stack will try to +reclaim memory from the receiving queue and out of order queue. One of +the reclaiming method is 'collapse', which means allocate a big sbk, +copy the contiguous skbs to the single big skb, and free these +contiguous skbs. + +* TcpExtPruneCalled + +The TCP stack tries to reclaim memory for a socket. After updates this +counter, the TCP stack will try to collapse the out of order queue and +the receiving queue. If the memory is still not enough, the TCP stack +will try to discard packets from the out of order queue (and update the +TcpExtOfoPruned counter) + +* TcpExtOfoPruned + +The TCP stack tries to discard packet on the out of order queue. + +* TcpExtRcvPruned + +After 'collapse' and discard packets from the out of order queue, if +the actually used memory is still larger than the max allowed memory, +this counter will be updated. It means the 'prune' fails. + +* TcpExtTCPRcvCollapsed + +This counter indicates how many skbs are freed during 'collapse'. + examples ======== diff --git a/Documentation/networking/timestamping.txt b/Documentation/networking/timestamping.txt index 9d1432e0aaa8..bbdaf8990031 100644 --- a/Documentation/networking/timestamping.txt +++ b/Documentation/networking/timestamping.txt @@ -6,11 +6,21 @@ The interfaces for receiving network packages timestamps are: * SO_TIMESTAMP Generates a timestamp for each incoming packet in (not necessarily monotonic) system time. Reports the timestamp via recvmsg() in a - control message as struct timeval (usec resolution). + control message in usec resolution. + SO_TIMESTAMP is defined as SO_TIMESTAMP_NEW or SO_TIMESTAMP_OLD + based on the architecture type and time_t representation of libc. + Control message format is in struct __kernel_old_timeval for + SO_TIMESTAMP_OLD and in struct __kernel_sock_timeval for + SO_TIMESTAMP_NEW options respectively. * SO_TIMESTAMPNS Same timestamping mechanism as SO_TIMESTAMP, but reports the - timestamp as struct timespec (nsec resolution). + timestamp as struct timespec in nsec resolution. + SO_TIMESTAMPNS is defined as SO_TIMESTAMPNS_NEW or SO_TIMESTAMPNS_OLD + based on the architecture type and time_t representation of libc. + Control message format is in struct timespec for SO_TIMESTAMPNS_OLD + and in struct __kernel_timespec for SO_TIMESTAMPNS_NEW options + respectively. * IP_MULTICAST_LOOP + SO_TIMESTAMP[NS] Only for multicast:approximate transmit timestamp obtained by @@ -22,7 +32,7 @@ The interfaces for receiving network packages timestamps are: timestamps for stream sockets. -1.1 SO_TIMESTAMP: +1.1 SO_TIMESTAMP (also SO_TIMESTAMP_OLD and SO_TIMESTAMP_NEW): This socket option enables timestamping of datagrams on the reception path. Because the destination socket, if any, is not known early in @@ -31,15 +41,25 @@ same is true for all early receive timestamp options. For interface details, see `man 7 socket`. +Always use SO_TIMESTAMP_NEW timestamp to always get timestamp in +struct __kernel_sock_timeval format. -1.2 SO_TIMESTAMPNS: +SO_TIMESTAMP_OLD returns incorrect timestamps after the year 2038 +on 32 bit machines. + +1.2 SO_TIMESTAMPNS (also SO_TIMESTAMPNS_OLD and SO_TIMESTAMPNS_NEW): This option is identical to SO_TIMESTAMP except for the returned data type. Its struct timespec allows for higher resolution (ns) timestamps than the timeval of SO_TIMESTAMP (ms). +Always use SO_TIMESTAMPNS_NEW timestamp to always get timestamp in +struct __kernel_timespec format. + +SO_TIMESTAMPNS_OLD returns incorrect timestamps after the year 2038 +on 32 bit machines. -1.3 SO_TIMESTAMPING: +1.3 SO_TIMESTAMPING (also SO_TIMESTAMPING_OLD and SO_TIMESTAMPING_NEW): Supports multiple types of timestamp requests. As a result, this socket option takes a bitmap of flags, not a boolean. In @@ -323,10 +343,23 @@ SO_TIMESTAMP and SO_TIMESTAMPNS records can be retrieved. These timestamps are returned in a control message with cmsg_level SOL_SOCKET, cmsg_type SCM_TIMESTAMPING, and payload of type +For SO_TIMESTAMPING_OLD: + struct scm_timestamping { struct timespec ts[3]; }; +For SO_TIMESTAMPING_NEW: + +struct scm_timestamping64 { + struct __kernel_timespec ts[3]; + +Always use SO_TIMESTAMPING_NEW timestamp to always get timestamp in +struct scm_timestamping64 format. + +SO_TIMESTAMPING_OLD returns incorrect timestamps after the year 2038 +on 32 bit machines. + The structure can return up to three timestamps. This is a legacy feature. At least one field is non-zero at any time. Most timestamps are passed in ts[0]. Hardware timestamps are passed in ts[2]. diff --git a/Documentation/sysctl/fs.txt b/Documentation/sysctl/fs.txt index 819caf8ca05f..ebc679bcb2dc 100644 --- a/Documentation/sysctl/fs.txt +++ b/Documentation/sysctl/fs.txt @@ -56,26 +56,34 @@ of any kernel data structures. dentry-state: -From linux/fs/dentry.c: +From linux/include/linux/dcache.h: -------------------------------------------------------------- -struct { +struct dentry_stat_t dentry_stat { int nr_dentry; int nr_unused; int age_limit; /* age in seconds */ int want_pages; /* pages requested by system */ - int dummy[2]; -} dentry_stat = {0, 0, 45, 0,}; --------------------------------------------------------------- - -Dentries are dynamically allocated and deallocated, and -nr_dentry seems to be 0 all the time. Hence it's safe to -assume that only nr_unused, age_limit and want_pages are -used. Nr_unused seems to be exactly what its name says. + int nr_negative; /* # of unused negative dentries */ + int dummy; /* Reserved for future use */ +}; +-------------------------------------------------------------- + +Dentries are dynamically allocated and deallocated. + +nr_dentry shows the total number of dentries allocated (active ++ unused). nr_unused shows the number of dentries that are not +actively used, but are saved in the LRU list for future reuse. + Age_limit is the age in seconds after which dcache entries can be reclaimed when memory is short and want_pages is nonzero when shrink_dcache_pages() has been called and the dcache isn't pruned yet. +nr_negative shows the number of unused dentries that are also +negative dentries which do not map to any files. Instead, +they help speeding up rejection of non-existing files provided +by the users. + ============================================================== dquot-max & dquot-nr: diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt index bc0680706870..2ae91d3873bb 100644 --- a/Documentation/sysctl/net.txt +++ b/Documentation/sysctl/net.txt @@ -52,6 +52,7 @@ two flavors of JITs, the newer eBPF JIT currently supported on: - sparc64 - mips64 - s390x + - riscv And the older cBPF JIT supported on the following archs: - mips diff --git a/Documentation/x86/resctrl_ui.txt b/Documentation/x86/resctrl_ui.txt index e8e8d14d3c4e..c1f95b59e14d 100644 --- a/Documentation/x86/resctrl_ui.txt +++ b/Documentation/x86/resctrl_ui.txt @@ -9,7 +9,7 @@ Fenghua Yu <fenghua.yu@intel.com> Tony Luck <tony.luck@intel.com> Vikas Shivappa <vikas.shivappa@intel.com> -This feature is enabled by the CONFIG_X86_RESCTRL and the x86 /proc/cpuinfo +This feature is enabled by the CONFIG_X86_CPU_RESCTRL and the x86 /proc/cpuinfo flag bits: RDT (Resource Director Technology) Allocation - "rdt_a" CAT (Cache Allocation Technology) - "cat_l3", "cat_l2" diff --git a/MAINTAINERS b/MAINTAINERS index ecbc22ec2699..8c8f509844c5 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2848,6 +2848,9 @@ F: include/uapi/linux/if_bonding.h BPF (Safe dynamic programs and tools) M: Alexei Starovoitov <ast@kernel.org> M: Daniel Borkmann <daniel@iogearbox.net> +R: Martin KaFai Lau <kafai@fb.com> +R: Song Liu <songliubraving@fb.com> +R: Yonghong Song <yhs@fb.com> L: netdev@vger.kernel.org L: linux-kernel@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git @@ -2873,6 +2876,8 @@ F: samples/bpf/ F: tools/bpf/ F: tools/lib/bpf/ F: tools/testing/selftests/bpf/ +K: bpf +N: bpf BPF JIT for ARM M: Shubham Bansal <illusionist.neo@gmail.com> @@ -2907,6 +2912,12 @@ L: netdev@vger.kernel.org S: Maintained F: arch/powerpc/net/ +BPF JIT for RISC-V (RV64G) +M: Björn Töpel <bjorn.topel@gmail.com> +L: netdev@vger.kernel.org +S: Maintained +F: arch/riscv/net/ + BPF JIT for S390 M: Martin Schwidefsky <schwidefsky@de.ibm.com> M: Heiko Carstens <heiko.carstens@de.ibm.com> @@ -4123,7 +4134,7 @@ S: Maintained F: drivers/media/dvb-frontends/cxd2820r* CXGB3 ETHERNET DRIVER (CXGB3) -M: Arjun Vynipadath <arjun@chelsio.com> +M: Vishal Kulkarni <vishal@chelsio.com> L: netdev@vger.kernel.org W: http://www.chelsio.com S: Supported @@ -4152,7 +4163,7 @@ S: Supported F: drivers/crypto/chelsio CXGB4 ETHERNET DRIVER (CXGB4) -M: Arjun Vynipadath <arjun@chelsio.com> +M: Vishal Kulkarni <vishal@chelsio.com> L: netdev@vger.kernel.org W: http://www.chelsio.com S: Supported @@ -5181,7 +5192,7 @@ DRM DRIVERS FOR XEN M: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com> T: git git://anongit.freedesktop.org/drm/drm-misc L: dri-devel@lists.freedesktop.org -L: xen-devel@lists.xen.org +L: xen-devel@lists.xenproject.org (moderated for non-subscribers) S: Supported F: drivers/gpu/drm/xen/ F: Documentation/gpu/xen-front.rst @@ -6093,6 +6104,7 @@ FREESCALE QORIQ PTP CLOCK DRIVER M: Yangbo Lu <yangbo.lu@nxp.com> L: netdev@vger.kernel.org S: Maintained +F: drivers/net/ethernet/freescale/enetc/enetc_ptp.c F: drivers/ptp/ptp_qoriq.c F: drivers/ptp/ptp_qoriq_debugfs.c F: include/linux/fsl/ptp_qoriq.h @@ -6153,7 +6165,7 @@ FREESCALE SOC SOUND DRIVERS M: Timur Tabi <timur@kernel.org> M: Nicolin Chen <nicoleotsuka@gmail.com> M: Xiubo Li <Xiubo.Lee@gmail.com> -R: Fabio Estevam <fabio.estevam@nxp.com> +R: Fabio Estevam <festevam@gmail.com> L: alsa-devel@alsa-project.org (moderated for non-subscribers) L: linuxppc-dev@lists.ozlabs.org S: Maintained @@ -10901,7 +10913,7 @@ F: include/linux/nvmem-consumer.h F: include/linux/nvmem-provider.h NXP SGTL5000 DRIVER -M: Fabio Estevam <fabio.estevam@nxp.com> +M: Fabio Estevam <festevam@gmail.com> L: alsa-devel@alsa-project.org (moderated for non-subscribers) S: Maintained F: Documentation/devicetree/bindings/sound/sgtl5000.txt @@ -11315,10 +11327,12 @@ F: include/dt-bindings/ OPENCORES I2C BUS DRIVER M: Peter Korsgaard <peter@korsgaard.com> +M: Andrew Lunn <andrew@lunn.ch> L: linux-i2c@vger.kernel.org S: Maintained F: Documentation/i2c/busses/i2c-ocores F: drivers/i2c/busses/i2c-ocores.c +F: include/linux/platform_data/i2c-ocores.h OPENRISC ARCHITECTURE M: Jonas Bonn <jonas@southpole.se> @@ -12884,6 +12898,13 @@ F: Documentation/devicetree/bindings/net/dsa/realtek-smi.txt F: drivers/net/dsa/realtek-smi* F: drivers/net/dsa/rtl83* +REDPINE WIRELESS DRIVER +M: Amitkumar Karwar <amitkarwar@gmail.com> +M: Siva Rebbagondla <siva8118@gmail.com> +L: linux-wireless@vger.kernel.org +S: Maintained +F: drivers/net/wireless/rsi/ + REGISTER MAP ABSTRACTION M: Mark Brown <broonie@kernel.org> L: linux-kernel@vger.kernel.org @@ -13712,6 +13733,15 @@ L: netdev@vger.kernel.org S: Supported F: drivers/net/ethernet/sfc/ +SFF/SFP/SFP+ MODULE SUPPORT +M: Russell King <linux@armlinux.org.uk> +L: netdev@vger.kernel.org +S: Maintained +F: drivers/net/phy/phylink.c +F: drivers/net/phy/sfp* +F: include/linux/phylink.h +F: include/linux/sfp.h + SGI GRU DRIVER M: Dimitri Sivanich <sivanich@sgi.com> S: Maintained @@ -13733,6 +13763,7 @@ F: drivers/misc/sgi-xp/ SHARED MEMORY COMMUNICATIONS (SMC) SOCKETS M: Ursula Braun <ubraun@linux.ibm.com> +M: Karsten Graul <kgraul@linux.ibm.com> L: linux-s390@vger.kernel.org W: http://www.ibm.com/developerworks/linux/linux390/ S: Supported @@ -16657,6 +16688,15 @@ S: Maintained F: drivers/platform/x86/ F: drivers/platform/olpc/ +X86 PLATFORM DRIVERS - ARCH +R: Darren Hart <dvhart@infradead.org> +R: Andy Shevchenko <andy@infradead.org> +L: platform-driver-x86@vger.kernel.org +L: x86@kernel.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/core +S: Maintained +F: arch/x86/platform + X86 VDSO M: Andy Lutomirski <luto@kernel.org> L: linux-kernel@vger.kernel.org @@ -16689,6 +16729,24 @@ T: git git://linuxtv.org/media_tree.git S: Maintained F: drivers/media/tuners/tuner-xc2028.* +XDP (eXpress Data Path) +M: Alexei Starovoitov <ast@kernel.org> +M: Daniel Borkmann <daniel@iogearbox.net> +M: David S. Miller <davem@davemloft.net> +M: Jakub Kicinski <jakub.kicinski@netronome.com> +M: Jesper Dangaard Brouer <hawk@kernel.org> +M: John Fastabend <john.fastabend@gmail.com> +L: netdev@vger.kernel.org +L: xdp-newbies@vger.kernel.org +S: Supported +F: net/core/xdp.c +F: include/net/xdp.h +F: kernel/bpf/devmap.c +F: kernel/bpf/cpumap.c +F: include/trace/events/xdp.h +K: xdp +N: xdp + XDP SOCKETS (AF_XDP) M: Björn Töpel <bjorn.topel@intel.com> M: Magnus Karlsson <magnus.karlsson@intel.com> @@ -2,7 +2,7 @@ VERSION = 5 PATCHLEVEL = 0 SUBLEVEL = 0 -EXTRAVERSION = -rc3 +EXTRAVERSION = -rc6 NAME = Shy Crocodile # *DOCUMENTATION* diff --git a/arch/alpha/include/asm/irq.h b/arch/alpha/include/asm/irq.h index 4d17cacd1462..432402c8e47f 100644 --- a/arch/alpha/include/asm/irq.h +++ b/arch/alpha/include/asm/irq.h @@ -56,15 +56,15 @@ #elif defined(CONFIG_ALPHA_DP264) || \ defined(CONFIG_ALPHA_LYNX) || \ - defined(CONFIG_ALPHA_SHARK) || \ - defined(CONFIG_ALPHA_EIGER) + defined(CONFIG_ALPHA_SHARK) # define NR_IRQS 64 #elif defined(CONFIG_ALPHA_TITAN) #define NR_IRQS 80 #elif defined(CONFIG_ALPHA_RAWHIDE) || \ - defined(CONFIG_ALPHA_TAKARA) + defined(CONFIG_ALPHA_TAKARA) || \ + defined(CONFIG_ALPHA_EIGER) # define NR_IRQS 128 #elif defined(CONFIG_ALPHA_WILDFIRE) diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index b1c9b542c021..0d0fddb7e738 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -3,6 +3,7 @@ #define _UAPI_ASM_SOCKET_H #include <asm/sockios.h> +#include <asm/bitsperlong.h> /* For setsockopt(2) */ /* @@ -30,8 +31,8 @@ #define SO_RCVBUFFORCE 0x100b #define SO_RCVLOWAT 0x1010 #define SO_SNDLOWAT 0x1011 -#define SO_RCVTIMEO 0x1012 -#define SO_SNDTIMEO 0x1013 +#define SO_RCVTIMEO_OLD 0x1012 +#define SO_SNDTIMEO_OLD 0x1013 #define SO_ACCEPTCONN 0x1014 #define SO_PROTOCOL 0x1028 #define SO_DOMAIN 0x1029 @@ -51,13 +52,9 @@ #define SO_GET_FILTER SO_ATTACH_FILTER #define SO_PEERNAME 28 -#define SO_TIMESTAMP 29 -#define SCM_TIMESTAMP SO_TIMESTAMP #define SO_PEERSEC 30 #define SO_PASSSEC 34 -#define SO_TIMESTAMPNS 35 -#define SCM_TIMESTAMPNS SO_TIMESTAMPNS /* Security levels - as per NRL IPv6 - don't actually do anything */ #define SO_SECURITY_AUTHENTICATION 19 @@ -66,9 +63,6 @@ #define SO_MARK 36 -#define SO_TIMESTAMPING 37 -#define SCM_TIMESTAMPING SO_TIMESTAMPING - #define SO_RXQ_OVFL 40 #define SO_WIFI_STATUS 41 @@ -117,4 +111,39 @@ #define SO_BINDTOIFINDEX 62 +#define SO_TIMESTAMP_OLD 29 +#define SO_TIMESTAMPNS_OLD 35 +#define SO_TIMESTAMPING_OLD 37 + +#define SO_TIMESTAMP_NEW 63 +#define SO_TIMESTAMPNS_NEW 64 +#define SO_TIMESTAMPING_NEW 65 + +#define SO_RCVTIMEO_NEW 66 +#define SO_SNDTIMEO_NEW 67 + +#if !defined(__KERNEL__) + +#if __BITS_PER_LONG == 64 +#define SO_TIMESTAMP SO_TIMESTAMP_OLD +#define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD +#define SO_TIMESTAMPING SO_TIMESTAMPING_OLD + +#define SO_RCVTIMEO SO_RCVTIMEO_OLD +#define SO_SNDTIMEO SO_SNDTIMEO_OLD +#else +#define SO_TIMESTAMP (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMP_OLD : SO_TIMESTAMP_NEW) +#define SO_TIMESTAMPNS (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPNS_OLD : SO_TIMESTAMPNS_NEW) +#define SO_TIMESTAMPING (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPING_OLD : SO_TIMESTAMPING_NEW) + +#define SO_RCVTIMEO (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_RCVTIMEO_OLD : SO_RCVTIMEO_NEW) +#define SO_SNDTIMEO (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_SNDTIMEO_OLD : SO_SNDTIMEO_NEW) +#endif + +#define SCM_TIMESTAMP SO_TIMESTAMP +#define SCM_TIMESTAMPNS SO_TIMESTAMPNS +#define SCM_TIMESTAMPING SO_TIMESTAMPING + +#endif + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index d73dc473fbb9..188fc9256baf 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -78,7 +78,7 @@ __load_new_mm_context(struct mm_struct *next_mm) /* Macro for exception fixup code to access integer registers. */ #define dpf_reg(r) \ (((unsigned long *)regs)[(r) <= 8 ? (r) : (r) <= 15 ? (r)-16 : \ - (r) <= 18 ? (r)+8 : (r)-10]) + (r) <= 18 ? (r)+10 : (r)-10]) asmlinkage void do_page_fault(unsigned long address, unsigned long mmcsr, diff --git a/arch/arm/boot/dts/am335x-shc.dts b/arch/arm/boot/dts/am335x-shc.dts index d0fd68873689..5b250060f6dd 100644 --- a/arch/arm/boot/dts/am335x-shc.dts +++ b/arch/arm/boot/dts/am335x-shc.dts @@ -215,7 +215,7 @@ pinctrl-names = "default"; pinctrl-0 = <&mmc1_pins>; bus-width = <0x4>; - cd-gpios = <&gpio0 6 GPIO_ACTIVE_HIGH>; + cd-gpios = <&gpio0 6 GPIO_ACTIVE_LOW>; cd-inverted; max-frequency = <26000000>; vmmc-supply = <&vmmcsd_fixed>; diff --git a/arch/arm/boot/dts/armada-388-clearfog.dtsi b/arch/arm/boot/dts/armada-388-clearfog.dtsi index 1b0d0680c8b6..0d81600ca247 100644 --- a/arch/arm/boot/dts/armada-388-clearfog.dtsi +++ b/arch/arm/boot/dts/armada-388-clearfog.dtsi @@ -93,6 +93,7 @@ bm,pool-long = <2>; bm,pool-short = <1>; buffer-manager = <&bm>; + phys = <&comphy1 1>; phy-mode = "sgmii"; status = "okay"; }; @@ -103,6 +104,7 @@ bm,pool-short = <1>; buffer-manager = <&bm>; managed = "in-band-status"; + phys = <&comphy5 2>; phy-mode = "sgmii"; sfp = <&sfp>; status = "okay"; diff --git a/arch/arm/boot/dts/armada-38x.dtsi b/arch/arm/boot/dts/armada-38x.dtsi index 929459c42760..7b2e2bd6479b 100644 --- a/arch/arm/boot/dts/armada-38x.dtsi +++ b/arch/arm/boot/dts/armada-38x.dtsi @@ -335,6 +335,43 @@ #clock-cells = <1>; }; + comphy: phy@18300 { + compatible = "marvell,armada-380-comphy"; + reg = <0x18300 0x100>; + #address-cells = <1>; + #size-cells = <0>; + + comphy0: phy@0 { + reg = <0>; + #phy-cells = <1>; + }; + + comphy1: phy@1 { + reg = <1>; + #phy-cells = <1>; + }; + + comphy2: phy@2 { + reg = <2>; + #phy-cells = <1>; + }; + + comphy3: phy@3 { + reg = <3>; + #phy-cells = <1>; + }; + + comphy4: phy@4 { + reg = <4>; + #phy-cells = <1>; + }; + + comphy5: phy@5 { + reg = <5>; + #phy-cells = <1>; + }; + }; + coreclk: mvebu-sar@18600 { compatible = "marvell,armada-380-core-clock"; reg = <0x18600 0x04>; diff --git a/arch/arm/boot/dts/da850.dtsi b/arch/arm/boot/dts/da850.dtsi index 47aa53ba6b92..559659b399d0 100644 --- a/arch/arm/boot/dts/da850.dtsi +++ b/arch/arm/boot/dts/da850.dtsi @@ -476,7 +476,7 @@ clocksource: timer@20000 { compatible = "ti,da830-timer"; reg = <0x20000 0x1000>; - interrupts = <12>, <13>; + interrupts = <21>, <22>; interrupt-names = "tint12", "tint34"; clocks = <&pll0_auxclk>; }; diff --git a/arch/arm/boot/dts/imx6q-pistachio.dts b/arch/arm/boot/dts/imx6q-pistachio.dts index 5edf858c8b86..a31b17eaf51c 100644 --- a/arch/arm/boot/dts/imx6q-pistachio.dts +++ b/arch/arm/boot/dts/imx6q-pistachio.dts @@ -103,7 +103,7 @@ power { label = "Power Button"; gpios = <&gpio2 12 GPIO_ACTIVE_LOW>; - gpio-key,wakeup; + wakeup-source; linux,code = <KEY_POWER>; }; }; diff --git a/arch/arm/boot/dts/imx6sll-evk.dts b/arch/arm/boot/dts/imx6sll-evk.dts index d8163705363e..4a31a415f88e 100644 --- a/arch/arm/boot/dts/imx6sll-evk.dts +++ b/arch/arm/boot/dts/imx6sll-evk.dts @@ -309,7 +309,7 @@ pinctrl-2 = <&pinctrl_usdhc3_200mhz>; cd-gpios = <&gpio3 22 GPIO_ACTIVE_LOW>; keep-power-in-suspend; - enable-sdio-wakeup; + wakeup-source; vmmc-supply = <®_sd3_vmmc>; status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6sx.dtsi b/arch/arm/boot/dts/imx6sx.dtsi index 272ff6133ec1..d1375d3650fd 100644 --- a/arch/arm/boot/dts/imx6sx.dtsi +++ b/arch/arm/boot/dts/imx6sx.dtsi @@ -467,7 +467,7 @@ }; gpt: gpt@2098000 { - compatible = "fsl,imx6sx-gpt", "fsl,imx31-gpt"; + compatible = "fsl,imx6sx-gpt", "fsl,imx6dl-gpt"; reg = <0x02098000 0x4000>; interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX6SX_CLK_GPT_BUS>, diff --git a/arch/arm/boot/dts/meson.dtsi b/arch/arm/boot/dts/meson.dtsi index e4645f612712..2ab74860d962 100644 --- a/arch/arm/boot/dts/meson.dtsi +++ b/arch/arm/boot/dts/meson.dtsi @@ -274,7 +274,7 @@ compatible = "amlogic,meson6-dwmac", "snps,dwmac"; reg = <0xc9410000 0x10000 0xc1108108 0x4>; - interrupts = <GIC_SPI 8 IRQ_TYPE_EDGE_RISING>; + interrupts = <GIC_SPI 8 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "macirq"; status = "disabled"; }; diff --git a/arch/arm/boot/dts/meson8b-ec100.dts b/arch/arm/boot/dts/meson8b-ec100.dts index 0872f6e3abf5..d50fc2f60fa3 100644 --- a/arch/arm/boot/dts/meson8b-ec100.dts +++ b/arch/arm/boot/dts/meson8b-ec100.dts @@ -205,8 +205,7 @@ cap-sd-highspeed; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vcc_3v3>; }; diff --git a/arch/arm/boot/dts/meson8b-odroidc1.dts b/arch/arm/boot/dts/meson8b-odroidc1.dts index 58669abda259..0f0a46ddf3ff 100644 --- a/arch/arm/boot/dts/meson8b-odroidc1.dts +++ b/arch/arm/boot/dts/meson8b-odroidc1.dts @@ -221,7 +221,6 @@ /* Realtek RTL8211F (0x001cc916) */ eth_phy: ethernet-phy@0 { reg = <0>; - eee-broken-1000t; interrupt-parent = <&gpio_intc>; /* GPIOH_3 */ interrupts = <17 IRQ_TYPE_LEVEL_LOW>; @@ -273,8 +272,7 @@ cap-sd-highspeed; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&tflash_vdd>; vqmmc-supply = <&tf_io>; diff --git a/arch/arm/boot/dts/meson8m2-mxiii-plus.dts b/arch/arm/boot/dts/meson8m2-mxiii-plus.dts index f5853610b20b..6ac02beb5fa7 100644 --- a/arch/arm/boot/dts/meson8m2-mxiii-plus.dts +++ b/arch/arm/boot/dts/meson8m2-mxiii-plus.dts @@ -206,8 +206,7 @@ cap-sd-highspeed; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vcc_3v3>; }; diff --git a/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi b/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi index ddc7a7bb33c0..f57acf8f66b9 100644 --- a/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi +++ b/arch/arm/boot/dts/motorola-cpcap-mapphone.dtsi @@ -105,7 +105,7 @@ interrupts-extended = < &cpcap 15 0 &cpcap 14 0 &cpcap 28 0 &cpcap 19 0 &cpcap 18 0 &cpcap 17 0 &cpcap 16 0 &cpcap 49 0 - &cpcap 48 1 + &cpcap 48 0 >; interrupt-names = "id_ground", "id_float", "se0conn", "vbusvld", diff --git a/arch/arm/boot/dts/omap3-gta04.dtsi b/arch/arm/boot/dts/omap3-gta04.dtsi index e53d32691308..93b420934e8e 100644 --- a/arch/arm/boot/dts/omap3-gta04.dtsi +++ b/arch/arm/boot/dts/omap3-gta04.dtsi @@ -714,11 +714,7 @@ vdda-supply = <&vdac>; - #address-cells = <1>; - #size-cells = <0>; - port { - reg = <0>; venc_out: endpoint { remote-endpoint = <&opa_in>; ti,channels = <1>; diff --git a/arch/arm/boot/dts/omap3-n900.dts b/arch/arm/boot/dts/omap3-n900.dts index 182a53991c90..826920e6b878 100644 --- a/arch/arm/boot/dts/omap3-n900.dts +++ b/arch/arm/boot/dts/omap3-n900.dts @@ -814,7 +814,7 @@ /* For debugging, it is often good idea to remove this GPIO. It means you can remove back cover (to reboot by removing battery) and still use the MMC card. */ - cd-gpios = <&gpio6 0 GPIO_ACTIVE_HIGH>; /* 160 */ + cd-gpios = <&gpio6 0 GPIO_ACTIVE_LOW>; /* 160 */ }; /* most boards use vaux3, only some old versions use vmmc2 instead */ diff --git a/arch/arm/boot/dts/omap3-n950-n9.dtsi b/arch/arm/boot/dts/omap3-n950-n9.dtsi index 0d9b85317529..e142e6c70a59 100644 --- a/arch/arm/boot/dts/omap3-n950-n9.dtsi +++ b/arch/arm/boot/dts/omap3-n950-n9.dtsi @@ -370,6 +370,19 @@ compatible = "ti,omap2-onenand"; reg = <0 0 0x20000>; /* CS0, offset 0, IO size 128K */ + /* + * These timings are based on CONFIG_OMAP_GPMC_DEBUG=y reported + * bootloader set values when booted with v4.19 using both N950 + * and N9 devices (OneNAND Manufacturer: Samsung): + * + * gpmc cs0 before gpmc_cs_program_settings: + * cs0 GPMC_CS_CONFIG1: 0xfd001202 + * cs0 GPMC_CS_CONFIG2: 0x00181800 + * cs0 GPMC_CS_CONFIG3: 0x00030300 + * cs0 GPMC_CS_CONFIG4: 0x18001804 + * cs0 GPMC_CS_CONFIG5: 0x03171d1d + * cs0 GPMC_CS_CONFIG6: 0x97080000 + */ gpmc,sync-read; gpmc,sync-write; gpmc,burst-length = <16>; @@ -379,26 +392,27 @@ gpmc,device-width = <2>; gpmc,mux-add-data = <2>; gpmc,cs-on-ns = <0>; - gpmc,cs-rd-off-ns = <87>; - gpmc,cs-wr-off-ns = <87>; + gpmc,cs-rd-off-ns = <122>; + gpmc,cs-wr-off-ns = <122>; gpmc,adv-on-ns = <0>; - gpmc,adv-rd-off-ns = <10>; - gpmc,adv-wr-off-ns = <10>; - gpmc,oe-on-ns = <15>; - gpmc,oe-off-ns = <87>; + gpmc,adv-rd-off-ns = <15>; + gpmc,adv-wr-off-ns = <15>; + gpmc,oe-on-ns = <20>; + gpmc,oe-off-ns = <122>; gpmc,we-on-ns = <0>; - gpmc,we-off-ns = <87>; - gpmc,rd-cycle-ns = <112>; - gpmc,wr-cycle-ns = <112>; - gpmc,access-ns = <81>; + gpmc,we-off-ns = <122>; + gpmc,rd-cycle-ns = <148>; + gpmc,wr-cycle-ns = <148>; + gpmc,access-ns = <117>; gpmc,page-burst-access-ns = <15>; gpmc,bus-turnaround-ns = <0>; gpmc,cycle2cycle-delay-ns = <0>; gpmc,wait-monitoring-ns = <0>; - gpmc,clk-activation-ns = <5>; - gpmc,wr-data-mux-bus-ns = <30>; - gpmc,wr-access-ns = <81>; - gpmc,sync-clk-ps = <15000>; + gpmc,clk-activation-ns = <10>; + gpmc,wr-data-mux-bus-ns = <40>; + gpmc,wr-access-ns = <117>; + + gpmc,sync-clk-ps = <15000>; /* TBC; Where this value came? */ /* * MTD partition table corresponding to Nokia's MeeGo 1.2 diff --git a/arch/arm/boot/dts/omap5-l4.dtsi b/arch/arm/boot/dts/omap5-l4.dtsi index 9c7e309d9c2c..0960348002ad 100644 --- a/arch/arm/boot/dts/omap5-l4.dtsi +++ b/arch/arm/boot/dts/omap5-l4.dtsi @@ -1046,8 +1046,6 @@ <SYSC_IDLE_SMART>, <SYSC_IDLE_SMART_WKUP>; ti,syss-mask = <1>; - ti,no-reset-on-init; - ti,no-idle-on-init; /* Domains (V, P, C): core, core_pwrdm, l4per_clkdm */ clocks = <&l4per_clkctrl OMAP5_UART3_CLKCTRL 0>; clock-names = "fck"; diff --git a/arch/arm/boot/dts/r8a7743.dtsi b/arch/arm/boot/dts/r8a7743.dtsi index 3cc33f7ff7fe..3adc158a40bb 100644 --- a/arch/arm/boot/dts/r8a7743.dtsi +++ b/arch/arm/boot/dts/r8a7743.dtsi @@ -1681,15 +1681,12 @@ du: display@feb00000 { compatible = "renesas,du-r8a7743"; - reg = <0 0xfeb00000 0 0x40000>, - <0 0xfeb90000 0 0x1c>; - reg-names = "du", "lvds.0"; + reg = <0 0xfeb00000 0 0x40000>; interrupts = <GIC_SPI 256 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 268 IRQ_TYPE_LEVEL_HIGH>; clocks = <&cpg CPG_MOD 724>, - <&cpg CPG_MOD 723>, - <&cpg CPG_MOD 726>; - clock-names = "du.0", "du.1", "lvds.0"; + <&cpg CPG_MOD 723>; + clock-names = "du.0", "du.1"; status = "disabled"; ports { @@ -1704,6 +1701,33 @@ port@1 { reg = <1>; du_out_lvds0: endpoint { + remote-endpoint = <&lvds0_in>; + }; + }; + }; + }; + + lvds0: lvds@feb90000 { + compatible = "renesas,r8a7743-lvds"; + reg = <0 0xfeb90000 0 0x1c>; + clocks = <&cpg CPG_MOD 726>; + power-domains = <&sysc R8A7743_PD_ALWAYS_ON>; + resets = <&cpg 726>; + status = "disabled"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + lvds0_in: endpoint { + remote-endpoint = <&du_out_lvds0>; + }; + }; + port@1 { + reg = <1>; + lvds0_out: endpoint { }; }; }; diff --git a/arch/arm/boot/dts/sun6i-a31.dtsi b/arch/arm/boot/dts/sun6i-a31.dtsi index 353d90f99b40..13304b8c5139 100644 --- a/arch/arm/boot/dts/sun6i-a31.dtsi +++ b/arch/arm/boot/dts/sun6i-a31.dtsi @@ -216,6 +216,7 @@ #clock-cells = <0>; compatible = "fixed-clock"; clock-frequency = <24000000>; + clock-output-names = "osc24M"; }; osc32k: clk-32k { diff --git a/arch/arm/boot/dts/sun8i-h3-beelink-x2.dts b/arch/arm/boot/dts/sun8i-h3-beelink-x2.dts index 5d23667dc2d2..25540b7694d5 100644 --- a/arch/arm/boot/dts/sun8i-h3-beelink-x2.dts +++ b/arch/arm/boot/dts/sun8i-h3-beelink-x2.dts @@ -53,7 +53,7 @@ aliases { serial0 = &uart0; - /* ethernet0 is the H3 emac, defined in sun8i-h3.dtsi */ + ethernet0 = &emac; ethernet1 = &sdiowifi; }; diff --git a/arch/arm/boot/dts/vf610-bk4.dts b/arch/arm/boot/dts/vf610-bk4.dts index 689c8930dce3..b08d561d6748 100644 --- a/arch/arm/boot/dts/vf610-bk4.dts +++ b/arch/arm/boot/dts/vf610-bk4.dts @@ -110,11 +110,11 @@ bus-num = <3>; status = "okay"; spi-slave; + #address-cells = <0>; - slave@0 { + slave { compatible = "lwn,bk4"; spi-max-frequency = <30000000>; - reg = <0>; }; }; diff --git a/arch/arm/mach-cns3xxx/pcie.c b/arch/arm/mach-cns3xxx/pcie.c index 318394ed5c7a..95a11d5b3587 100644 --- a/arch/arm/mach-cns3xxx/pcie.c +++ b/arch/arm/mach-cns3xxx/pcie.c @@ -83,7 +83,7 @@ static void __iomem *cns3xxx_pci_map_bus(struct pci_bus *bus, } else /* remote PCI bus */ base = cnspci->cfg1_regs + ((busno & 0xf) << 20); - return base + (where & 0xffc) + (devfn << 12); + return base + where + (devfn << 12); } static int cns3xxx_pci_read_config(struct pci_bus *bus, unsigned int devfn, @@ -93,7 +93,7 @@ static int cns3xxx_pci_read_config(struct pci_bus *bus, unsigned int devfn, u32 mask = (0x1ull << (size * 8)) - 1; int shift = (where % 4) * 8; - ret = pci_generic_config_read32(bus, devfn, where, size, val); + ret = pci_generic_config_read(bus, devfn, where, size, val); if (ret == PCIBIOS_SUCCESSFUL && !bus->number && !devfn && (where & 0xffc) == PCI_CLASS_REVISION) diff --git a/arch/arm/mach-iop32x/n2100.c b/arch/arm/mach-iop32x/n2100.c index 3b73813c6b04..23e8c93515d4 100644 --- a/arch/arm/mach-iop32x/n2100.c +++ b/arch/arm/mach-iop32x/n2100.c @@ -75,8 +75,7 @@ void __init n2100_map_io(void) /* * N2100 PCI. */ -static int __init -n2100_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) +static int n2100_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) { int irq; diff --git a/arch/arm/mach-tango/pm.c b/arch/arm/mach-tango/pm.c index 028e50c6383f..a32c3b631484 100644 --- a/arch/arm/mach-tango/pm.c +++ b/arch/arm/mach-tango/pm.c @@ -3,6 +3,7 @@ #include <linux/suspend.h> #include <asm/suspend.h> #include "smc.h" +#include "pm.h" static int tango_pm_powerdown(unsigned long arg) { @@ -24,10 +25,7 @@ static const struct platform_suspend_ops tango_pm_ops = { .valid = suspend_valid_only_mem, }; -static int __init tango_pm_init(void) +void __init tango_pm_init(void) { suspend_set_ops(&tango_pm_ops); - return 0; } - -late_initcall(tango_pm_init); diff --git a/arch/arm/mach-tango/pm.h b/arch/arm/mach-tango/pm.h new file mode 100644 index 000000000000..35ea705a0ee2 --- /dev/null +++ b/arch/arm/mach-tango/pm.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifdef CONFIG_SUSPEND +void __init tango_pm_init(void); +#else +#define tango_pm_init NULL +#endif diff --git a/arch/arm/mach-tango/setup.c b/arch/arm/mach-tango/setup.c index 677dd7b5efd9..824f90737b04 100644 --- a/arch/arm/mach-tango/setup.c +++ b/arch/arm/mach-tango/setup.c @@ -2,6 +2,7 @@ #include <asm/mach/arch.h> #include <asm/hardware/cache-l2x0.h> #include "smc.h" +#include "pm.h" static void tango_l2c_write(unsigned long val, unsigned int reg) { @@ -15,4 +16,5 @@ DT_MACHINE_START(TANGO_DT, "Sigma Tango DT") .dt_compat = tango_dt_compat, .l2c_aux_mask = ~0, .l2c_write_sec = tango_l2c_write, + .init_late = tango_pm_init, MACHINE_END diff --git a/arch/arm/plat-pxa/ssp.c b/arch/arm/plat-pxa/ssp.c index ed36dcab80f1..f51919974183 100644 --- a/arch/arm/plat-pxa/ssp.c +++ b/arch/arm/plat-pxa/ssp.c @@ -190,8 +190,6 @@ static int pxa_ssp_remove(struct platform_device *pdev) if (ssp == NULL) return -ENODEV; - iounmap(ssp->mmio_base); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); release_mem_region(res->start, resource_size(res)); @@ -201,7 +199,6 @@ static int pxa_ssp_remove(struct platform_device *pdev) list_del(&ssp->node); mutex_unlock(&ssp_lock); - kfree(ssp); return 0; } diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c index cb44aa290e73..e1d44b903dfc 100644 --- a/arch/arm/xen/mm.c +++ b/arch/arm/xen/mm.c @@ -7,7 +7,6 @@ #include <linux/of_address.h> #include <linux/slab.h> #include <linux/types.h> -#include <linux/dma-mapping.h> #include <linux/vmalloc.h> #include <linux/swiotlb.h> diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts b/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts index b0c64f75792c..8974b5a1d3b1 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64-orangepi-win.dts @@ -188,6 +188,7 @@ reg = <0x3a3>; interrupt-parent = <&r_intc>; interrupts = <0 IRQ_TYPE_LEVEL_LOW>; + x-powers,drive-vbus-en; /* set N_VBUSEN as output pin */ }; }; diff --git a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi index 837a03dee875..2abb335145a6 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi +++ b/arch/arm64/boot/dts/allwinner/sun50i-a64.dtsi @@ -390,7 +390,7 @@ }; video-codec@1c0e000 { - compatible = "allwinner,sun50i-h5-video-engine"; + compatible = "allwinner,sun50i-a64-video-engine"; reg = <0x01c0e000 0x1000>; clocks = <&ccu CLK_BUS_VE>, <&ccu CLK_VE>, <&ccu CLK_DRAM_VE>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi index e14e0ce7e89f..016641a41694 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gx-p23x-q20x.dtsi @@ -187,8 +187,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_boot>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts index 8cd50b75171d..ade2ee09ae96 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-nanopi-k2.dts @@ -305,8 +305,7 @@ max-frequency = <200000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddio_ao3v3>; vqmmc-supply = <&vddio_tf>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts index 4cf7f6e80c6a..25105ac96d55 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-nexbox-a95x.dts @@ -238,8 +238,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_card>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts index 2e1cd5e3a246..1cc9dc68ef00 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-odroidc2.dts @@ -258,8 +258,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&tflash_vdd>; vqmmc-supply = <&tf_io>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi index ce862266b9aa..0be0f2a5d2fe 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-p20x.dtsi @@ -196,8 +196,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_card>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi index 93a4acf2c46c..ad4d50bd9d77 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-vega-s95.dtsi @@ -154,8 +154,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vcc_3v3>; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek.dtsi index ec09bb5792b7..2d2db783c44c 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb-wetek.dtsi @@ -211,8 +211,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vcc_3v3>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts index f1c410e2da2b..796baea7a0bf 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-hwacom-amazetv.dts @@ -131,8 +131,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_card>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts index db293440e4ca..255cede7b447 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-libretech-cc.dts @@ -238,8 +238,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vcc_3v3>; vqmmc-supply = <&vcc_card>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts index 6739697be1de..9cbdb85fb591 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-nexbox-a95x.dts @@ -183,8 +183,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_card>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi index a1b31013ab6e..bc811a2faf42 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxl-s905x-p212.dtsi @@ -137,8 +137,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_boot>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts index 3c3a667a8df8..3f086ed7de05 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxm-khadas-vim2.dts @@ -356,8 +356,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_boot>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts index f7a1cffab4a8..8acfd40090d2 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxm-nexbox-a1.dts @@ -147,8 +147,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_boot>; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts b/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts index 7212dc4531e4..7fa20a8ede17 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts +++ b/arch/arm64/boot/dts/amlogic/meson-gxm-rbox-pro.dts @@ -170,8 +170,7 @@ max-frequency = <100000000>; disable-wp; - cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_HIGH>; - cd-inverted; + cd-gpios = <&gpio CARD_6 GPIO_ACTIVE_LOW>; vmmc-supply = <&vddao_3v3>; vqmmc-supply = <&vddio_boot>; diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi index 99b7495455a6..838e32cc14c9 100644 --- a/arch/arm64/boot/dts/qcom/msm8996.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi @@ -404,7 +404,7 @@ }; intc: interrupt-controller@9bc0000 { - compatible = "arm,gic-v3"; + compatible = "qcom,msm8996-gic-v3", "arm,gic-v3"; #interrupt-cells = <3>; interrupt-controller; #redistributor-regions = <1>; diff --git a/arch/arm64/boot/dts/renesas/r8a774a1.dtsi b/arch/arm64/boot/dts/renesas/r8a774a1.dtsi index 20745a8528c5..719ed9d9067d 100644 --- a/arch/arm64/boot/dts/renesas/r8a774a1.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a774a1.dtsi @@ -1011,6 +1011,9 @@ <&cpg CPG_CORE R8A774A1_CLK_S3D1>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; + dmas = <&dmac1 0x13>, <&dmac1 0x12>, + <&dmac2 0x13>, <&dmac2 0x12>; + dma-names = "tx", "rx", "tx", "rx"; power-domains = <&sysc R8A774A1_PD_ALWAYS_ON>; resets = <&cpg 310>; status = "disabled"; diff --git a/arch/arm64/boot/dts/renesas/r8a7796.dtsi b/arch/arm64/boot/dts/renesas/r8a7796.dtsi index afedbf5728ec..0648d12778ed 100644 --- a/arch/arm64/boot/dts/renesas/r8a7796.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a7796.dtsi @@ -1262,6 +1262,9 @@ <&cpg CPG_CORE R8A7796_CLK_S3D1>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; + dmas = <&dmac1 0x13>, <&dmac1 0x12>, + <&dmac2 0x13>, <&dmac2 0x12>; + dma-names = "tx", "rx", "tx", "rx"; power-domains = <&sysc R8A7796_PD_ALWAYS_ON>; resets = <&cpg 310>; status = "disabled"; diff --git a/arch/arm64/boot/dts/renesas/r8a77965.dtsi b/arch/arm64/boot/dts/renesas/r8a77965.dtsi index 6dc9b1fef830..4b3730f640ef 100644 --- a/arch/arm64/boot/dts/renesas/r8a77965.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a77965.dtsi @@ -1068,6 +1068,9 @@ <&cpg CPG_CORE R8A77965_CLK_S3D1>, <&scif_clk>; clock-names = "fck", "brg_int", "scif_clk"; + dmas = <&dmac1 0x13>, <&dmac1 0x12>, + <&dmac2 0x13>, <&dmac2 0x12>; + dma-names = "tx", "rx", "tx", "rx"; power-domains = <&sysc R8A77965_PD_ALWAYS_ON>; resets = <&cpg 310>; status = "disabled"; diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index 29cdc99688f3..9859e1178e6b 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -299,8 +299,10 @@ int swsusp_arch_suspend(void) dcache_clean_range(__idmap_text_start, __idmap_text_end); /* Clean kvm setup code to PoC? */ - if (el2_reset_needed()) + if (el2_reset_needed()) { dcache_clean_range(__hyp_idmap_text_start, __hyp_idmap_text_end); + dcache_clean_range(__hyp_text_start, __hyp_text_end); + } /* make the crash dump kernel image protected again */ crash_post_resume(); diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S index e1261fbaa374..17f325ba831e 100644 --- a/arch/arm64/kernel/hyp-stub.S +++ b/arch/arm64/kernel/hyp-stub.S @@ -28,6 +28,8 @@ #include <asm/virt.h> .text + .pushsection .hyp.text, "ax" + .align 11 ENTRY(__hyp_stub_vectors) diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c index ba6b41790fcd..b09b6f75f759 100644 --- a/arch/arm64/kernel/kaslr.c +++ b/arch/arm64/kernel/kaslr.c @@ -88,6 +88,7 @@ u64 __init kaslr_early_init(u64 dt_phys) * we end up running with module randomization disabled. */ module_alloc_base = (u64)_etext - MODULES_VSIZE; + __flush_dcache_area(&module_alloc_base, sizeof(module_alloc_base)); /* * Try to map the FDT early. If this fails, we simply bail, diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c index f2c211a6229b..58871333737a 100644 --- a/arch/arm64/kernel/machine_kexec_file.c +++ b/arch/arm64/kernel/machine_kexec_file.c @@ -120,10 +120,12 @@ static int create_dtb(struct kimage *image, { void *buf; size_t buf_size; + size_t cmdline_len; int ret; + cmdline_len = cmdline ? strlen(cmdline) : 0; buf_size = fdt_totalsize(initial_boot_params) - + strlen(cmdline) + DTB_EXTRA_SPACE; + + cmdline_len + DTB_EXTRA_SPACE; for (;;) { buf = vmalloc(buf_size); diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c index 2a5b338b2542..f17afb99890c 100644 --- a/arch/arm64/kernel/probes/kprobes.c +++ b/arch/arm64/kernel/probes/kprobes.c @@ -478,13 +478,13 @@ bool arch_within_kprobe_blacklist(unsigned long addr) addr < (unsigned long)__entry_text_end) || (addr >= (unsigned long)__idmap_text_start && addr < (unsigned long)__idmap_text_end) || + (addr >= (unsigned long)__hyp_text_start && + addr < (unsigned long)__hyp_text_end) || !!search_exception_tables(addr)) return true; if (!is_kernel_in_hyp_mode()) { - if ((addr >= (unsigned long)__hyp_text_start && - addr < (unsigned long)__hyp_text_end) || - (addr >= (unsigned long)__hyp_idmap_text_start && + if ((addr >= (unsigned long)__hyp_idmap_text_start && addr < (unsigned long)__hyp_idmap_text_end)) return true; } diff --git a/arch/arm64/mm/dump.c b/arch/arm64/mm/dump.c index fcb1f2a6d7c6..99bb8facb5cb 100644 --- a/arch/arm64/mm/dump.c +++ b/arch/arm64/mm/dump.c @@ -286,74 +286,73 @@ static void note_page(struct pg_state *st, unsigned long addr, unsigned level, } -static void walk_pte(struct pg_state *st, pmd_t *pmdp, unsigned long start) +static void walk_pte(struct pg_state *st, pmd_t *pmdp, unsigned long start, + unsigned long end) { - pte_t *ptep = pte_offset_kernel(pmdp, 0UL); - unsigned long addr; - unsigned i; + unsigned long addr = start; + pte_t *ptep = pte_offset_kernel(pmdp, start); - for (i = 0; i < PTRS_PER_PTE; i++, ptep++) { - addr = start + i * PAGE_SIZE; + do { note_page(st, addr, 4, READ_ONCE(pte_val(*ptep))); - } + } while (ptep++, addr += PAGE_SIZE, addr != end); } -static void walk_pmd(struct pg_state *st, pud_t *pudp, unsigned long start) +static void walk_pmd(struct pg_state *st, pud_t *pudp, unsigned long start, + unsigned long end) { - pmd_t *pmdp = pmd_offset(pudp, 0UL); - unsigned long addr; - unsigned i; + unsigned long next, addr = start; + pmd_t *pmdp = pmd_offset(pudp, start); - for (i = 0; i < PTRS_PER_PMD; i++, pmdp++) { + do { pmd_t pmd = READ_ONCE(*pmdp); + next = pmd_addr_end(addr, end); - addr = start + i * PMD_SIZE; if (pmd_none(pmd) || pmd_sect(pmd)) { note_page(st, addr, 3, pmd_val(pmd)); } else { BUG_ON(pmd_bad(pmd)); - walk_pte(st, pmdp, addr); + walk_pte(st, pmdp, addr, next); } - } + } while (pmdp++, addr = next, addr != end); } -static void walk_pud(struct pg_state *st, pgd_t *pgdp, unsigned long start) +static void walk_pud(struct pg_state *st, pgd_t *pgdp, unsigned long start, + unsigned long end) { - pud_t *pudp = pud_offset(pgdp, 0UL); - unsigned long addr; - unsigned i; + unsigned long next, addr = start; + pud_t *pudp = pud_offset(pgdp, start); - for (i = 0; i < PTRS_PER_PUD; i++, pudp++) { + do { pud_t pud = READ_ONCE(*pudp); + next = pud_addr_end(addr, end); - addr = start + i * PUD_SIZE; if (pud_none(pud) || pud_sect(pud)) { note_page(st, addr, 2, pud_val(pud)); } else { BUG_ON(pud_bad(pud)); - walk_pmd(st, pudp, addr); + walk_pmd(st, pudp, addr, next); } - } + } while (pudp++, addr = next, addr != end); } static void walk_pgd(struct pg_state *st, struct mm_struct *mm, unsigned long start) { - pgd_t *pgdp = pgd_offset(mm, 0UL); - unsigned i; - unsigned long addr; + unsigned long end = (start < TASK_SIZE_64) ? TASK_SIZE_64 : 0; + unsigned long next, addr = start; + pgd_t *pgdp = pgd_offset(mm, start); - for (i = 0; i < PTRS_PER_PGD; i++, pgdp++) { + do { pgd_t pgd = READ_ONCE(*pgdp); + next = pgd_addr_end(addr, end); - addr = start + i * PGDIR_SIZE; if (pgd_none(pgd)) { note_page(st, addr, 1, pgd_val(pgd)); } else { BUG_ON(pgd_bad(pgd)); - walk_pud(st, pgdp, addr); + walk_pud(st, pgdp, addr, next); } - } + } while (pgdp++, addr = next, addr != end); } void ptdump_walk_pgd(struct seq_file *m, struct ptdump_info *info) diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c index 30695a868107..5c9073bace83 100644 --- a/arch/arm64/mm/flush.c +++ b/arch/arm64/mm/flush.c @@ -33,7 +33,11 @@ void sync_icache_aliases(void *kaddr, unsigned long len) __clean_dcache_area_pou(kaddr, len); __flush_icache_all(); } else { - flush_icache_range(addr, addr + len); + /* + * Don't issue kick_all_cpus_sync() after I-cache invalidation + * for user mappings. + */ + __flush_icache_range(addr, addr + len); } } diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild index 33a2c94fed0d..63b4a1705182 100644 --- a/arch/c6x/include/asm/Kbuild +++ b/arch/c6x/include/asm/Kbuild @@ -30,6 +30,7 @@ generic-y += pgalloc.h generic-y += preempt.h generic-y += segment.h generic-y += serial.h +generic-y += shmparam.h generic-y += tlbflush.h generic-y += topology.h generic-y += trace_clock.h diff --git a/arch/c6x/include/uapi/asm/Kbuild b/arch/c6x/include/uapi/asm/Kbuild index 6c6f6301012e..0febf1a07c30 100644 --- a/arch/c6x/include/uapi/asm/Kbuild +++ b/arch/c6x/include/uapi/asm/Kbuild @@ -1,5 +1,4 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += kvm_para.h -generic-y += shmparam.h generic-y += ucontext.h diff --git a/arch/h8300/include/asm/Kbuild b/arch/h8300/include/asm/Kbuild index cd400d353d18..961c1dc064e1 100644 --- a/arch/h8300/include/asm/Kbuild +++ b/arch/h8300/include/asm/Kbuild @@ -40,6 +40,7 @@ generic-y += preempt.h generic-y += scatterlist.h generic-y += sections.h generic-y += serial.h +generic-y += shmparam.h generic-y += sizes.h generic-y += spinlock.h generic-y += timex.h diff --git a/arch/h8300/include/uapi/asm/Kbuild b/arch/h8300/include/uapi/asm/Kbuild index 6c6f6301012e..0febf1a07c30 100644 --- a/arch/h8300/include/uapi/asm/Kbuild +++ b/arch/h8300/include/uapi/asm/Kbuild @@ -1,5 +1,4 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += kvm_para.h -generic-y += shmparam.h generic-y += ucontext.h diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild index 47c4da3d64a4..b25fd42aa0f4 100644 --- a/arch/hexagon/include/asm/Kbuild +++ b/arch/hexagon/include/asm/Kbuild @@ -30,6 +30,7 @@ generic-y += rwsem.h generic-y += sections.h generic-y += segment.h generic-y += serial.h +generic-y += shmparam.h generic-y += sizes.h generic-y += topology.h generic-y += trace_clock.h diff --git a/arch/hexagon/include/uapi/asm/Kbuild b/arch/hexagon/include/uapi/asm/Kbuild index 61d955c1747a..c1b06dcf6cf8 100644 --- a/arch/hexagon/include/uapi/asm/Kbuild +++ b/arch/hexagon/include/uapi/asm/Kbuild @@ -1,4 +1,3 @@ include include/uapi/asm-generic/Kbuild.asm -generic-y += shmparam.h generic-y += ucontext.h diff --git a/arch/ia64/include/uapi/asm/Kbuild b/arch/ia64/include/uapi/asm/Kbuild index 5b819e53c397..b71c5f787783 100644 --- a/arch/ia64/include/uapi/asm/Kbuild +++ b/arch/ia64/include/uapi/asm/Kbuild @@ -2,3 +2,4 @@ include include/uapi/asm-generic/Kbuild.asm generated-y += unistd_64.h generic-y += kvm_para.h +generic-y += socket.h diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h deleted file mode 100644 index ba0d245f9576..000000000000 --- a/arch/ia64/include/uapi/asm/socket.h +++ /dev/null @@ -1,122 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#ifndef _ASM_IA64_SOCKET_H -#define _ASM_IA64_SOCKET_H - -/* - * Socket related defines. - * - * Based on <asm-i386/socket.h>. - * - * Modified 1998-2000 - * David Mosberger-Tang <davidm@hpl.hp.com>, Hewlett-Packard Co - */ - -#include <asm/sockios.h> - -/* For setsockopt(2) */ -#define SOL_SOCKET 1 - -#define SO_DEBUG 1 -#define SO_REUSEADDR 2 -#define SO_TYPE 3 -#define SO_ERROR 4 -#define SO_DONTROUTE 5 -#define SO_BROADCAST 6 -#define SO_SNDBUF 7 -#define SO_RCVBUF 8 -#define SO_SNDBUFFORCE 32 -#define SO_RCVBUFFORCE 33 -#define SO_KEEPALIVE 9 -#define SO_OOBINLINE 10 -#define SO_NO_CHECK 11 -#define SO_PRIORITY 12 -#define SO_LINGER 13 -#define SO_BSDCOMPAT 14 -#define SO_REUSEPORT 15 -#define SO_PASSCRED 16 -#define SO_PEERCRED 17 -#define SO_RCVLOWAT 18 -#define SO_SNDLOWAT 19 -#define SO_RCVTIMEO 20 -#define SO_SNDTIMEO 21 - -/* Security levels - as per NRL IPv6 - don't actually do anything */ -#define SO_SECURITY_AUTHENTICATION 22 -#define SO_SECURITY_ENCRYPTION_TRANSPORT 23 -#define SO_SECURITY_ENCRYPTION_NETWORK 24 - -#define SO_BINDTODEVICE 25 - -/* Socket filtering */ -#define SO_ATTACH_FILTER 26 -#define SO_DETACH_FILTER 27 -#define SO_GET_FILTER SO_ATTACH_FILTER - -#define SO_PEERNAME 28 -#define SO_TIMESTAMP 29 -#define SCM_TIMESTAMP SO_TIMESTAMP - -#define SO_ACCEPTCONN 30 - -#define SO_PEERSEC 31 -#define SO_PASSSEC 34 -#define SO_TIMESTAMPNS 35 -#define SCM_TIMESTAMPNS SO_TIMESTAMPNS - -#define SO_MARK 36 - -#define SO_TIMESTAMPING 37 -#define SCM_TIMESTAMPING SO_TIMESTAMPING - -#define SO_PROTOCOL 38 -#define SO_DOMAIN 39 - -#define SO_RXQ_OVFL 40 - -#define SO_WIFI_STATUS 41 -#define SCM_WIFI_STATUS SO_WIFI_STATUS -#define SO_PEEK_OFF 42 - -/* Instruct lower device to use last 4-bytes of skb data as FCS */ -#define SO_NOFCS 43 - -#define SO_LOCK_FILTER 44 - -#define SO_SELECT_ERR_QUEUE 45 - -#define SO_BUSY_POLL 46 - -#define SO_MAX_PACING_RATE 47 - -#define SO_BPF_EXTENSIONS 48 - -#define SO_INCOMING_CPU 49 - -#define SO_ATTACH_BPF 50 -#define SO_DETACH_BPF SO_DETACH_FILTER - -#define SO_ATTACH_REUSEPORT_CBPF 51 -#define SO_ATTACH_REUSEPORT_EBPF 52 - -#define SO_CNX_ADVICE 53 - -#define SCM_TIMESTAMPING_OPT_STATS 54 - -#define SO_MEMINFO 55 - -#define SO_INCOMING_NAPI_ID 56 - -#define SO_COOKIE 57 - -#define SCM_TIMESTAMPING_PKTINFO 58 - -#define SO_PEERGROUPS 59 - -#define SO_ZEROCOPY 60 - -#define SO_TXTIME 61 -#define SCM_TXTIME SO_TXTIME - -#define SO_BINDTOIFINDEX 62 - -#endif /* _ASM_IA64_SOCKET_H */ diff --git a/arch/m68k/coldfire/m5272.c b/arch/m68k/coldfire/m5272.c index ad1185c68df7..6b3ab583c698 100644 --- a/arch/m68k/coldfire/m5272.c +++ b/arch/m68k/coldfire/m5272.c @@ -127,7 +127,7 @@ static struct fixed_phy_status nettel_fixed_phy_status __initdata = { static int __init init_BSP(void) { m5272_uarts_init(); - fixed_phy_add(PHY_POLL, 0, &nettel_fixed_phy_status, -1); + fixed_phy_add(PHY_POLL, 0, &nettel_fixed_phy_status); return 0; } diff --git a/arch/m68k/emu/nfblock.c b/arch/m68k/emu/nfblock.c index 38049357d6d3..40712e49381b 100644 --- a/arch/m68k/emu/nfblock.c +++ b/arch/m68k/emu/nfblock.c @@ -155,18 +155,22 @@ out: static int __init nfhd_init(void) { u32 blocks, bsize; + int ret; int i; nfhd_id = nf_get_id("XHDI"); if (!nfhd_id) return -ENODEV; - major_num = register_blkdev(major_num, "nfhd"); - if (major_num <= 0) { + ret = register_blkdev(major_num, "nfhd"); + if (ret < 0) { pr_warn("nfhd: unable to get major number\n"); - return major_num; + return ret; } + if (!major_num) + major_num = ret; + for (i = NFHD_DEV_OFFSET; i < 24; i++) { if (nfhd_get_capacity(i, 0, &blocks, &bsize)) continue; diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild index 9f1dd26903e3..95f8f631c4df 100644 --- a/arch/m68k/include/asm/Kbuild +++ b/arch/m68k/include/asm/Kbuild @@ -20,6 +20,7 @@ generic-y += mm-arch-hooks.h generic-y += percpu.h generic-y += preempt.h generic-y += sections.h +generic-y += shmparam.h generic-y += spinlock.h generic-y += topology.h generic-y += trace_clock.h diff --git a/arch/m68k/include/uapi/asm/Kbuild b/arch/m68k/include/uapi/asm/Kbuild index b8b3525271fa..960bf1e4be53 100644 --- a/arch/m68k/include/uapi/asm/Kbuild +++ b/arch/m68k/include/uapi/asm/Kbuild @@ -2,4 +2,3 @@ include include/uapi/asm-generic/Kbuild.asm generated-y += unistd_32.h generic-y += kvm_para.h -generic-y += shmparam.h diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild index 9c7d1d25bf3d..791cc8d54d0a 100644 --- a/arch/microblaze/include/asm/Kbuild +++ b/arch/microblaze/include/asm/Kbuild @@ -26,6 +26,7 @@ generic-y += parport.h generic-y += percpu.h generic-y += preempt.h generic-y += serial.h +generic-y += shmparam.h generic-y += syscalls.h generic-y += topology.h generic-y += trace_clock.h diff --git a/arch/microblaze/include/uapi/asm/Kbuild b/arch/microblaze/include/uapi/asm/Kbuild index 28823e3db825..97823ec46e97 100644 --- a/arch/microblaze/include/uapi/asm/Kbuild +++ b/arch/microblaze/include/uapi/asm/Kbuild @@ -2,5 +2,4 @@ include include/uapi/asm-generic/Kbuild.asm generated-y += unistd_32.h generic-y += kvm_para.h -generic-y += shmparam.h generic-y += ucontext.h diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 0d14f51d0002..a84c24d894aa 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -1403,6 +1403,21 @@ config LOONGSON3_ENHANCEMENT please say 'N' here. If you want a high-performance kernel to run on new Loongson 3 machines only, please say 'Y' here. +config CPU_LOONGSON3_WORKAROUNDS + bool "Old Loongson 3 LLSC Workarounds" + default y if SMP + depends on CPU_LOONGSON3 + help + Loongson 3 processors have the llsc issues which require workarounds. + Without workarounds the system may hang unexpectedly. + + Newer Loongson 3 will fix these issues and no workarounds are needed. + The workarounds have no significant side effect on them but may + decrease the performance of the system so this option should be + disabled unless the kernel is intended to be run on old systems. + + If unsure, please say Y. + config CPU_LOONGSON2E bool "Loongson 2E" depends on SYS_HAS_CPU_LOONGSON2E diff --git a/arch/mips/ar7/platform.c b/arch/mips/ar7/platform.c index f09262e0a72f..10ff07b7721e 100644 --- a/arch/mips/ar7/platform.c +++ b/arch/mips/ar7/platform.c @@ -683,7 +683,7 @@ static int __init ar7_register_devices(void) if (ar7_has_high_cpmac()) { res = fixed_phy_add(PHY_POLL, cpmac_high.id, - &fixed_phy_status, -1); + &fixed_phy_status); if (!res) { cpmac_get_mac(1, cpmac_high_data.dev_addr); @@ -696,7 +696,7 @@ static int __init ar7_register_devices(void) } else cpmac_low_data.phy_mask = 0xffffffff; - res = fixed_phy_add(PHY_POLL, cpmac_low.id, &fixed_phy_status, -1); + res = fixed_phy_add(PHY_POLL, cpmac_low.id, &fixed_phy_status); if (!res) { cpmac_get_mac(0, cpmac_low_data.dev_addr); res = platform_device_register(&cpmac_low); diff --git a/arch/mips/bcm47xx/setup.c b/arch/mips/bcm47xx/setup.c index fe3773539eff..82627c264964 100644 --- a/arch/mips/bcm47xx/setup.c +++ b/arch/mips/bcm47xx/setup.c @@ -274,7 +274,7 @@ static int __init bcm47xx_register_bus_complete(void) bcm47xx_leds_register(); bcm47xx_workarounds(); - fixed_phy_add(PHY_POLL, 0, &bcm47xx_fixed_phy_status, -1); + fixed_phy_add(PHY_POLL, 0, &bcm47xx_fixed_phy_status); return 0; } device_initcall(bcm47xx_register_bus_complete); diff --git a/arch/mips/boot/dts/ingenic/ci20.dts b/arch/mips/boot/dts/ingenic/ci20.dts index 50cff3cbcc6d..4f7b1fa31cf5 100644 --- a/arch/mips/boot/dts/ingenic/ci20.dts +++ b/arch/mips/boot/dts/ingenic/ci20.dts @@ -76,7 +76,7 @@ status = "okay"; pinctrl-names = "default"; - pinctrl-0 = <&pins_uart2>; + pinctrl-0 = <&pins_uart3>; }; &uart4 { @@ -196,9 +196,9 @@ bias-disable; }; - pins_uart2: uart2 { - function = "uart2"; - groups = "uart2-data", "uart2-hwflow"; + pins_uart3: uart3 { + function = "uart3"; + groups = "uart3-data", "uart3-hwflow"; bias-disable; }; diff --git a/arch/mips/boot/dts/ingenic/jz4740.dtsi b/arch/mips/boot/dts/ingenic/jz4740.dtsi index 6fb16fd24035..2beb78a62b7d 100644 --- a/arch/mips/boot/dts/ingenic/jz4740.dtsi +++ b/arch/mips/boot/dts/ingenic/jz4740.dtsi @@ -161,7 +161,7 @@ #dma-cells = <2>; interrupt-parent = <&intc>; - interrupts = <29>; + interrupts = <20>; clocks = <&cgu JZ4740_CLK_DMA>; diff --git a/arch/mips/boot/dts/xilfpga/nexys4ddr.dts b/arch/mips/boot/dts/xilfpga/nexys4ddr.dts index 2152b7ba65fb..cc8dbea0911f 100644 --- a/arch/mips/boot/dts/xilfpga/nexys4ddr.dts +++ b/arch/mips/boot/dts/xilfpga/nexys4ddr.dts @@ -90,11 +90,11 @@ interrupts = <0>; }; - axi_i2c: i2c@10A00000 { + axi_i2c: i2c@10a00000 { compatible = "xlnx,xps-iic-2.00.a"; interrupt-parent = <&axi_intc>; interrupts = <4>; - reg = < 0x10A00000 0x10000 >; + reg = < 0x10a00000 0x10000 >; clocks = <&ext>; xlnx,clk-freq = <0x5f5e100>; xlnx,family = "Artix7"; @@ -106,9 +106,9 @@ #address-cells = <1>; #size-cells = <0>; - ad7420@4B { + ad7420@4b { compatible = "adi,adt7420"; - reg = <0x4B>; + reg = <0x4b>; }; } ; }; diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h index 43fcd35e2957..94096299fc56 100644 --- a/arch/mips/include/asm/atomic.h +++ b/arch/mips/include/asm/atomic.h @@ -58,6 +58,7 @@ static __inline__ void atomic_##op(int i, atomic_t * v) \ if (kernel_uses_llsc) { \ int temp; \ \ + loongson_llsc_mb(); \ __asm__ __volatile__( \ " .set push \n" \ " .set "MIPS_ISA_LEVEL" \n" \ @@ -85,6 +86,7 @@ static __inline__ int atomic_##op##_return_relaxed(int i, atomic_t * v) \ if (kernel_uses_llsc) { \ int temp; \ \ + loongson_llsc_mb(); \ __asm__ __volatile__( \ " .set push \n" \ " .set "MIPS_ISA_LEVEL" \n" \ @@ -118,6 +120,7 @@ static __inline__ int atomic_fetch_##op##_relaxed(int i, atomic_t * v) \ if (kernel_uses_llsc) { \ int temp; \ \ + loongson_llsc_mb(); \ __asm__ __volatile__( \ " .set push \n" \ " .set "MIPS_ISA_LEVEL" \n" \ @@ -256,6 +259,7 @@ static __inline__ void atomic64_##op(long i, atomic64_t * v) \ if (kernel_uses_llsc) { \ long temp; \ \ + loongson_llsc_mb(); \ __asm__ __volatile__( \ " .set push \n" \ " .set "MIPS_ISA_LEVEL" \n" \ @@ -283,6 +287,7 @@ static __inline__ long atomic64_##op##_return_relaxed(long i, atomic64_t * v) \ if (kernel_uses_llsc) { \ long temp; \ \ + loongson_llsc_mb(); \ __asm__ __volatile__( \ " .set push \n" \ " .set "MIPS_ISA_LEVEL" \n" \ @@ -316,6 +321,7 @@ static __inline__ long atomic64_fetch_##op##_relaxed(long i, atomic64_t * v) \ if (kernel_uses_llsc) { \ long temp; \ \ + loongson_llsc_mb(); \ __asm__ __volatile__( \ " .set push \n" \ " .set "MIPS_ISA_LEVEL" \n" \ diff --git a/arch/mips/include/asm/barrier.h b/arch/mips/include/asm/barrier.h index a5eb1bb199a7..b7f6ac5e513c 100644 --- a/arch/mips/include/asm/barrier.h +++ b/arch/mips/include/asm/barrier.h @@ -222,6 +222,42 @@ #define __smp_mb__before_atomic() __smp_mb__before_llsc() #define __smp_mb__after_atomic() smp_llsc_mb() +/* + * Some Loongson 3 CPUs have a bug wherein execution of a memory access (load, + * store or pref) in between an ll & sc can cause the sc instruction to + * erroneously succeed, breaking atomicity. Whilst it's unusual to write code + * containing such sequences, this bug bites harder than we might otherwise + * expect due to reordering & speculation: + * + * 1) A memory access appearing prior to the ll in program order may actually + * be executed after the ll - this is the reordering case. + * + * In order to avoid this we need to place a memory barrier (ie. a sync + * instruction) prior to every ll instruction, in between it & any earlier + * memory access instructions. Many of these cases are already covered by + * smp_mb__before_llsc() but for the remaining cases, typically ones in + * which multiple CPUs may operate on a memory location but ordering is not + * usually guaranteed, we use loongson_llsc_mb() below. + * + * This reordering case is fixed by 3A R2 CPUs, ie. 3A2000 models and later. + * + * 2) If a conditional branch exists between an ll & sc with a target outside + * of the ll-sc loop, for example an exit upon value mismatch in cmpxchg() + * or similar, then misprediction of the branch may allow speculative + * execution of memory accesses from outside of the ll-sc loop. + * + * In order to avoid this we need a memory barrier (ie. a sync instruction) + * at each affected branch target, for which we also use loongson_llsc_mb() + * defined below. + * + * This case affects all current Loongson 3 CPUs. + */ +#ifdef CONFIG_CPU_LOONGSON3_WORKAROUNDS /* Loongson-3's LLSC workaround */ +#define loongson_llsc_mb() __asm__ __volatile__(__WEAK_LLSC_MB : : :"memory") +#else +#define loongson_llsc_mb() do { } while (0) +#endif + #include <asm-generic/barrier.h> #endif /* __ASM_BARRIER_H */ diff --git a/arch/mips/include/asm/bitops.h b/arch/mips/include/asm/bitops.h index c4675957b21b..830c93a010c3 100644 --- a/arch/mips/include/asm/bitops.h +++ b/arch/mips/include/asm/bitops.h @@ -69,6 +69,7 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *addr) : "ir" (1UL << bit), GCC_OFF_SMALL_ASM() (*m)); #if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) } else if (kernel_uses_llsc && __builtin_constant_p(bit)) { + loongson_llsc_mb(); do { __asm__ __volatile__( " " __LL "%0, %1 # set_bit \n" @@ -79,6 +80,7 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *addr) } while (unlikely(!temp)); #endif /* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */ } else if (kernel_uses_llsc) { + loongson_llsc_mb(); do { __asm__ __volatile__( " .set push \n" @@ -123,6 +125,7 @@ static inline void clear_bit(unsigned long nr, volatile unsigned long *addr) : "ir" (~(1UL << bit))); #if defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) } else if (kernel_uses_llsc && __builtin_constant_p(bit)) { + loongson_llsc_mb(); do { __asm__ __volatile__( " " __LL "%0, %1 # clear_bit \n" @@ -133,6 +136,7 @@ static inline void clear_bit(unsigned long nr, volatile unsigned long *addr) } while (unlikely(!temp)); #endif /* CONFIG_CPU_MIPSR2 || CONFIG_CPU_MIPSR6 */ } else if (kernel_uses_llsc) { + loongson_llsc_mb(); do { __asm__ __volatile__( " .set push \n" @@ -193,6 +197,7 @@ static inline void change_bit(unsigned long nr, volatile unsigned long *addr) unsigned long *m = ((unsigned long *) addr) + (nr >> SZLONG_LOG); unsigned long temp; + loongson_llsc_mb(); do { __asm__ __volatile__( " .set push \n" diff --git a/arch/mips/include/asm/futex.h b/arch/mips/include/asm/futex.h index c14d798f3888..b83b0397462d 100644 --- a/arch/mips/include/asm/futex.h +++ b/arch/mips/include/asm/futex.h @@ -50,6 +50,7 @@ "i" (-EFAULT) \ : "memory"); \ } else if (cpu_has_llsc) { \ + loongson_llsc_mb(); \ __asm__ __volatile__( \ " .set push \n" \ " .set noat \n" \ @@ -163,6 +164,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, "i" (-EFAULT) : "memory"); } else if (cpu_has_llsc) { + loongson_llsc_mb(); __asm__ __volatile__( "# futex_atomic_cmpxchg_inatomic \n" " .set push \n" @@ -192,6 +194,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, : GCC_OFF_SMALL_ASM() (*uaddr), "Jr" (oldval), "Jr" (newval), "i" (-EFAULT) : "memory"); + loongson_llsc_mb(); } else return -ENOSYS; diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h index 57933fc8fd98..910851c62db3 100644 --- a/arch/mips/include/asm/pgtable.h +++ b/arch/mips/include/asm/pgtable.h @@ -228,6 +228,7 @@ static inline void set_pte(pte_t *ptep, pte_t pteval) : [buddy] "+m" (buddy->pte), [tmp] "=&r" (tmp) : [global] "r" (page_global)); } else if (kernel_uses_llsc) { + loongson_llsc_mb(); __asm__ __volatile__ ( " .set push \n" " .set "MIPS_ISA_ARCH_LEVEL" \n" @@ -242,6 +243,7 @@ static inline void set_pte(pte_t *ptep, pte_t pteval) " .set pop \n" : [buddy] "+m" (buddy->pte), [tmp] "=&r" (tmp) : [global] "r" (page_global)); + loongson_llsc_mb(); } #else /* !CONFIG_SMP */ if (pte_none(*buddy)) diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 73e25e35d803..eb9f33f8a8b3 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -11,6 +11,7 @@ #define _UAPI_ASM_SOCKET_H #include <asm/sockios.h> +#include <asm/bitsperlong.h> /* * For setsockopt(2) @@ -38,8 +39,8 @@ #define SO_RCVBUF 0x1002 /* Receive buffer. */ #define SO_SNDLOWAT 0x1003 /* send low-water mark */ #define SO_RCVLOWAT 0x1004 /* receive low-water mark */ -#define SO_SNDTIMEO 0x1005 /* send timeout */ -#define SO_RCVTIMEO 0x1006 /* receive timeout */ +#define SO_SNDTIMEO_OLD 0x1005 /* send timeout */ +#define SO_RCVTIMEO_OLD 0x1006 /* receive timeout */ #define SO_ACCEPTCONN 0x1009 #define SO_PROTOCOL 0x1028 /* protocol type */ #define SO_DOMAIN 0x1029 /* domain/socket family */ @@ -65,21 +66,14 @@ #define SO_GET_FILTER SO_ATTACH_FILTER #define SO_PEERNAME 28 -#define SO_TIMESTAMP 29 -#define SCM_TIMESTAMP SO_TIMESTAMP #define SO_PEERSEC 30 #define SO_SNDBUFFORCE 31 #define SO_RCVBUFFORCE 33 #define SO_PASSSEC 34 -#define SO_TIMESTAMPNS 35 -#define SCM_TIMESTAMPNS SO_TIMESTAMPNS #define SO_MARK 36 -#define SO_TIMESTAMPING 37 -#define SCM_TIMESTAMPING SO_TIMESTAMPING - #define SO_RXQ_OVFL 40 #define SO_WIFI_STATUS 41 @@ -128,4 +122,39 @@ #define SO_BINDTOIFINDEX 62 +#define SO_TIMESTAMP_OLD 29 +#define SO_TIMESTAMPNS_OLD 35 +#define SO_TIMESTAMPING_OLD 37 + +#define SO_TIMESTAMP_NEW 63 +#define SO_TIMESTAMPNS_NEW 64 +#define SO_TIMESTAMPING_NEW 65 + +#define SO_RCVTIMEO_NEW 66 +#define SO_SNDTIMEO_NEW 67 + +#if !defined(__KERNEL__) + +#if __BITS_PER_LONG == 64 +#define SO_TIMESTAMP SO_TIMESTAMP_OLD +#define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD +#define SO_TIMESTAMPING SO_TIMESTAMPING_OLD + +#define SO_RCVTIMEO SO_RCVTIMEO_OLD +#define SO_SNDTIMEO SO_SNDTIMEO_OLD +#else +#define SO_TIMESTAMP (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMP_OLD : SO_TIMESTAMP_NEW) +#define SO_TIMESTAMPNS (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPNS_OLD : SO_TIMESTAMPNS_NEW) +#define SO_TIMESTAMPING (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPING_OLD : SO_TIMESTAMPING_NEW) + +#define SO_RCVTIMEO (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_RCVTIMEO_OLD : SO_RCVTIMEO_NEW) +#define SO_SNDTIMEO (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_SNDTIMEO_OLD : SO_SNDTIMEO_NEW) +#endif + +#define SCM_TIMESTAMP SO_TIMESTAMP +#define SCM_TIMESTAMPNS SO_TIMESTAMPNS +#define SCM_TIMESTAMPING SO_TIMESTAMPING + +#endif + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/mips/kernel/mips-cm.c b/arch/mips/kernel/mips-cm.c index 8f5bd04f320a..7f3f136572de 100644 --- a/arch/mips/kernel/mips-cm.c +++ b/arch/mips/kernel/mips-cm.c @@ -457,5 +457,5 @@ void mips_cm_error_report(void) } /* reprime cause register */ - write_gcr_error_cause(0); + write_gcr_error_cause(cm_error); } diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index 6829a064aac8..339870ed92f7 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -371,7 +371,7 @@ static inline int is_sp_move_ins(union mips_instruction *ip, int *frame_size) static int get_frame_info(struct mips_frame_info *info) { bool is_mmips = IS_ENABLED(CONFIG_CPU_MICROMIPS); - union mips_instruction insn, *ip, *ip_end; + union mips_instruction insn, *ip; const unsigned int max_insns = 128; unsigned int last_insn_size = 0; unsigned int i; @@ -384,10 +384,9 @@ static int get_frame_info(struct mips_frame_info *info) if (!ip) goto err; - ip_end = (void *)ip + info->func_size; - - for (i = 0; i < max_insns && ip < ip_end; i++) { + for (i = 0; i < max_insns; i++) { ip = (void *)ip + last_insn_size; + if (is_mmips && mm_insn_16bit(ip->halfword[0])) { insn.word = ip->halfword[0] << 16; last_insn_size = 2; diff --git a/arch/mips/loongson64/Platform b/arch/mips/loongson64/Platform index 0fce4608aa88..c1a4d4dc4665 100644 --- a/arch/mips/loongson64/Platform +++ b/arch/mips/loongson64/Platform @@ -23,6 +23,29 @@ ifdef CONFIG_CPU_LOONGSON2F_WORKAROUNDS endif cflags-$(CONFIG_CPU_LOONGSON3) += -Wa,--trap + +# +# Some versions of binutils, not currently mainline as of 2019/02/04, support +# an -mfix-loongson3-llsc flag which emits a sync prior to each ll instruction +# to work around a CPU bug (see loongson_llsc_mb() in asm/barrier.h for a +# description). +# +# We disable this in order to prevent the assembler meddling with the +# instruction that labels refer to, ie. if we label an ll instruction: +# +# 1: ll v0, 0(a0) +# +# ...then with the assembler fix applied the label may actually point at a sync +# instruction inserted by the assembler, and if we were using the label in an +# exception table the table would no longer contain the address of the ll +# instruction. +# +# Avoid this by explicitly disabling that assembler behaviour. If upstream +# binutils does not merge support for the flag then we can revisit & remove +# this later - for now it ensures vendor toolchains don't cause problems. +# +cflags-$(CONFIG_CPU_LOONGSON3) += $(call as-option,-Wa$(comma)-mno-fix-loongson3-llsc,) + # # binutils from v2.25 on and gcc starting from v4.9.0 treat -march=loongson3a # as MIPS64 R2; older versions as just R1. This leaves the possibility open diff --git a/arch/mips/loongson64/common/reset.c b/arch/mips/loongson64/common/reset.c index a60715e11306..b26892ce871c 100644 --- a/arch/mips/loongson64/common/reset.c +++ b/arch/mips/loongson64/common/reset.c @@ -59,7 +59,12 @@ static void loongson_poweroff(void) { #ifndef CONFIG_LEFI_FIRMWARE_INTERFACE mach_prepare_shutdown(); - unreachable(); + + /* + * It needs a wait loop here, but mips/kernel/reset.c already calls + * a generic delay loop, machine_hang(), so simply return. + */ + return; #else void (*fw_poweroff)(void) = (void *)loongson_sysconf.poweroff_addr; diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c index 37b1cb246332..65b6e85447b1 100644 --- a/arch/mips/mm/tlbex.c +++ b/arch/mips/mm/tlbex.c @@ -932,6 +932,8 @@ build_get_pgd_vmalloc64(u32 **p, struct uasm_label **l, struct uasm_reloc **r, * to mimic that here by taking a load/istream page * fault. */ + if (IS_ENABLED(CONFIG_CPU_LOONGSON3_WORKAROUNDS)) + uasm_i_sync(p, 0); UASM_i_LA(p, ptr, (unsigned long)tlb_do_page_fault_0); uasm_i_jr(p, ptr); @@ -1646,6 +1648,8 @@ static void iPTE_LW(u32 **p, unsigned int pte, unsigned int ptr) { #ifdef CONFIG_SMP + if (IS_ENABLED(CONFIG_CPU_LOONGSON3_WORKAROUNDS)) + uasm_i_sync(p, 0); # ifdef CONFIG_PHYS_ADDR_T_64BIT if (cpu_has_64bits) uasm_i_lld(p, pte, 0, ptr); @@ -2259,6 +2263,8 @@ static void build_r4000_tlb_load_handler(void) #endif uasm_l_nopage_tlbl(&l, p); + if (IS_ENABLED(CONFIG_CPU_LOONGSON3_WORKAROUNDS)) + uasm_i_sync(&p, 0); build_restore_work_registers(&p); #ifdef CONFIG_CPU_MICROMIPS if ((unsigned long)tlb_do_page_fault_0 & 1) { @@ -2313,6 +2319,8 @@ static void build_r4000_tlb_store_handler(void) #endif uasm_l_nopage_tlbs(&l, p); + if (IS_ENABLED(CONFIG_CPU_LOONGSON3_WORKAROUNDS)) + uasm_i_sync(&p, 0); build_restore_work_registers(&p); #ifdef CONFIG_CPU_MICROMIPS if ((unsigned long)tlb_do_page_fault_1 & 1) { @@ -2368,6 +2376,8 @@ static void build_r4000_tlb_modify_handler(void) #endif uasm_l_nopage_tlbm(&l, p); + if (IS_ENABLED(CONFIG_CPU_LOONGSON3_WORKAROUNDS)) + uasm_i_sync(&p, 0); build_restore_work_registers(&p); #ifdef CONFIG_CPU_MICROMIPS if ((unsigned long)tlb_do_page_fault_1 & 1) { diff --git a/arch/mips/pci/pci-octeon.c b/arch/mips/pci/pci-octeon.c index 5017d5843c5a..fc29b85cfa92 100644 --- a/arch/mips/pci/pci-octeon.c +++ b/arch/mips/pci/pci-octeon.c @@ -568,6 +568,11 @@ static int __init octeon_pci_setup(void) if (octeon_has_feature(OCTEON_FEATURE_PCIE)) return 0; + if (!octeon_is_pci_host()) { + pr_notice("Not in host mode, PCI Controller not initialized\n"); + return 0; + } + /* Point pcibios_map_irq() to the PCI version of it */ octeon_pcibios_map_irq = octeon_pci_pcibios_map_irq; @@ -579,11 +584,6 @@ static int __init octeon_pci_setup(void) else octeon_dma_bar_type = OCTEON_DMA_BAR_TYPE_BIG; - if (!octeon_is_pci_host()) { - pr_notice("Not in host mode, PCI Controller not initialized\n"); - return 0; - } - /* PCI I/O and PCI MEM values */ set_io_port_base(OCTEON_PCI_IOSPACE_BASE); ioport_resource.start = 0; diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile index f6fd340e39c2..0ede4deb8181 100644 --- a/arch/mips/vdso/Makefile +++ b/arch/mips/vdso/Makefile @@ -8,6 +8,7 @@ ccflags-vdso := \ $(filter -E%,$(KBUILD_CFLAGS)) \ $(filter -mmicromips,$(KBUILD_CFLAGS)) \ $(filter -march=%,$(KBUILD_CFLAGS)) \ + $(filter -m%-float,$(KBUILD_CFLAGS)) \ -D__VDSO__ ifdef CONFIG_CC_IS_CLANG @@ -129,7 +130,7 @@ $(obj)/%-o32.o: $(src)/%.c FORCE $(call cmd,force_checksrc) $(call if_changed_rule,cc_o_c) -$(obj)/vdso-o32.lds: KBUILD_CPPFLAGS := -mabi=32 +$(obj)/vdso-o32.lds: KBUILD_CPPFLAGS := $(ccflags-vdso) -mabi=32 $(obj)/vdso-o32.lds: $(src)/vdso.lds.S FORCE $(call if_changed_dep,cpp_lds_S) @@ -169,7 +170,7 @@ $(obj)/%-n32.o: $(src)/%.c FORCE $(call cmd,force_checksrc) $(call if_changed_rule,cc_o_c) -$(obj)/vdso-n32.lds: KBUILD_CPPFLAGS := -mabi=n32 +$(obj)/vdso-n32.lds: KBUILD_CPPFLAGS := $(ccflags-vdso) -mabi=n32 $(obj)/vdso-n32.lds: $(src)/vdso.lds.S FORCE $(call if_changed_dep,cpp_lds_S) diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild index eb87cd8327c8..1f04844b6b82 100644 --- a/arch/openrisc/include/asm/Kbuild +++ b/arch/openrisc/include/asm/Kbuild @@ -34,6 +34,7 @@ generic-y += qrwlock_types.h generic-y += qrwlock.h generic-y += sections.h generic-y += segment.h +generic-y += shmparam.h generic-y += string.h generic-y += switch_to.h generic-y += topology.h diff --git a/arch/openrisc/include/uapi/asm/Kbuild b/arch/openrisc/include/uapi/asm/Kbuild index 6c6f6301012e..0febf1a07c30 100644 --- a/arch/openrisc/include/uapi/asm/Kbuild +++ b/arch/openrisc/include/uapi/asm/Kbuild @@ -1,5 +1,4 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += kvm_para.h -generic-y += shmparam.h generic-y += ucontext.h diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index 52bed5976cbe..16e428f03526 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -3,6 +3,7 @@ #define _UAPI_ASM_SOCKET_H #include <asm/sockios.h> +#include <asm/bitsperlong.h> /* For setsockopt(2) */ #define SOL_SOCKET 0xffff @@ -21,8 +22,8 @@ #define SO_RCVBUFFORCE 0x100b #define SO_SNDLOWAT 0x1003 #define SO_RCVLOWAT 0x1004 -#define SO_SNDTIMEO 0x1005 -#define SO_RCVTIMEO 0x1006 +#define SO_SNDTIMEO_OLD 0x1005 +#define SO_RCVTIMEO_OLD 0x1006 #define SO_ERROR 0x1007 #define SO_TYPE 0x1008 #define SO_PROTOCOL 0x1028 @@ -34,10 +35,6 @@ #define SO_BSDCOMPAT 0x400e #define SO_PASSCRED 0x4010 #define SO_PEERCRED 0x4011 -#define SO_TIMESTAMP 0x4012 -#define SCM_TIMESTAMP SO_TIMESTAMP -#define SO_TIMESTAMPNS 0x4013 -#define SCM_TIMESTAMPNS SO_TIMESTAMPNS /* Security levels - as per NRL IPv6 - don't actually do anything */ #define SO_SECURITY_AUTHENTICATION 0x4016 @@ -58,9 +55,6 @@ #define SO_MARK 0x401f -#define SO_TIMESTAMPING 0x4020 -#define SCM_TIMESTAMPING SO_TIMESTAMPING - #define SO_RXQ_OVFL 0x4021 #define SO_WIFI_STATUS 0x4022 @@ -109,4 +103,38 @@ #define SO_BINDTOIFINDEX 0x4037 +#define SO_TIMESTAMP_OLD 0x4012 +#define SO_TIMESTAMPNS_OLD 0x4013 +#define SO_TIMESTAMPING_OLD 0x4020 + +#define SO_TIMESTAMP_NEW 0x4038 +#define SO_TIMESTAMPNS_NEW 0x4039 +#define SO_TIMESTAMPING_NEW 0x403A + +#define SO_RCVTIMEO_NEW 0x4040 +#define SO_SNDTIMEO_NEW 0x4041 + +#if !defined(__KERNEL__) + +#if __BITS_PER_LONG == 64 +#define SO_TIMESTAMP SO_TIMESTAMP_OLD +#define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD +#define SO_TIMESTAMPING SO_TIMESTAMPING_OLD +#define SO_RCVTIMEO SO_RCVTIMEO_OLD +#define SO_SNDTIMEO SO_SNDTIMEO_OLD +#else +#define SO_TIMESTAMP (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMP_OLD : SO_TIMESTAMP_NEW) +#define SO_TIMESTAMPNS (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPNS_OLD : SO_TIMESTAMPNS_NEW) +#define SO_TIMESTAMPING (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPING_OLD : SO_TIMESTAMPING_NEW) + +#define SO_RCVTIMEO (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_RCVTIMEO_OLD : SO_RCVTIMEO_NEW) +#define SO_SNDTIMEO (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_SNDTIMEO_OLD : SO_SNDTIMEO_NEW) +#endif + +#define SCM_TIMESTAMP SO_TIMESTAMP +#define SCM_TIMESTAMPNS SO_TIMESTAMPNS +#define SCM_TIMESTAMPING SO_TIMESTAMPING + +#endif + #endif /* _UAPI_ASM_SOCKET_H */ diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 2e6ada28da64..c9bfe526ca9d 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -1258,21 +1258,13 @@ extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, #define pmd_move_must_withdraw pmd_move_must_withdraw struct spinlock; -static inline int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl, - struct spinlock *old_pmd_ptl, - struct vm_area_struct *vma) -{ - if (radix_enabled()) - return false; - /* - * Archs like ppc64 use pgtable to store per pmd - * specific information. So when we switch the pmd, - * we should also withdraw and deposit the pgtable - */ - return true; -} - - +extern int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl, + struct spinlock *old_pmd_ptl, + struct vm_area_struct *vma); +/* + * Hash translation mode use the deposited table to store hash pte + * slot information. + */ #define arch_needs_pgtable_deposit arch_needs_pgtable_deposit static inline bool arch_needs_pgtable_deposit(void) { diff --git a/arch/powerpc/include/uapi/asm/socket.h b/arch/powerpc/include/uapi/asm/socket.h index 94de465e0920..12aa0c43e775 100644 --- a/arch/powerpc/include/uapi/asm/socket.h +++ b/arch/powerpc/include/uapi/asm/socket.h @@ -11,8 +11,8 @@ #define SO_RCVLOWAT 16 #define SO_SNDLOWAT 17 -#define SO_RCVTIMEO 18 -#define SO_SNDTIMEO 19 +#define SO_RCVTIMEO_OLD 18 +#define SO_SNDTIMEO_OLD 19 #define SO_PASSCRED 20 #define SO_PEERCRED 21 diff --git a/arch/powerpc/mm/pgtable-book3s64.c b/arch/powerpc/mm/pgtable-book3s64.c index f3c31f5e1026..ecd31569a120 100644 --- a/arch/powerpc/mm/pgtable-book3s64.c +++ b/arch/powerpc/mm/pgtable-book3s64.c @@ -400,3 +400,25 @@ void arch_report_meminfo(struct seq_file *m) atomic_long_read(&direct_pages_count[MMU_PAGE_1G]) << 20); } #endif /* CONFIG_PROC_FS */ + +/* + * For hash translation mode, we use the deposited table to store hash slot + * information and they are stored at PTRS_PER_PMD offset from related pmd + * location. Hence a pmd move requires deposit and withdraw. + * + * For radix translation with split pmd ptl, we store the deposited table in the + * pmd page. Hence if we have different pmd page we need to withdraw during pmd + * move. + * + * With hash we use deposited table always irrespective of anon or not. + * With radix we use deposited table only for anonymous mapping. + */ +int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl, + struct spinlock *old_pmd_ptl, + struct vm_area_struct *vma) +{ + if (radix_enabled()) + return (new_pmd_ptl != old_pmd_ptl) && vma_is_anonymous(vma); + + return true; +} diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 15bba765fa79..4194d3cfb60c 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -1185,6 +1185,7 @@ skip_codegen_passes: bpf_flush_icache(bpf_hdr, (u8 *)bpf_hdr + (bpf_hdr->pages * PAGE_SIZE)); if (!fp->is_func || extra_pass) { + bpf_prog_fill_jited_linfo(fp, addrs); out_addrs: kfree(addrs); kfree(jit_data); diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index 7d6457ab5d34..bba281b1fe1b 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -43,6 +43,7 @@ static int drc_pmem_bind(struct papr_scm_priv *p) { unsigned long ret[PLPAR_HCALL_BUFSIZE]; uint64_t rc, token; + uint64_t saved = 0; /* * When the hypervisor cannot map all the requested memory in a single @@ -56,6 +57,8 @@ static int drc_pmem_bind(struct papr_scm_priv *p) rc = plpar_hcall(H_SCM_BIND_MEM, ret, p->drc_index, 0, p->blocks, BIND_ANY_ADDR, token); token = ret[0]; + if (!saved) + saved = ret[1]; cond_resched(); } while (rc == H_BUSY); @@ -64,7 +67,7 @@ static int drc_pmem_bind(struct papr_scm_priv *p) return -ENXIO; } - p->bound_addr = ret[1]; + p->bound_addr = saved; dev_dbg(&p->pdev->dev, "bound drc %x to %pR\n", p->drc_index, &p->res); diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index feeeaa60697c..bd149905a5b5 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -49,6 +49,7 @@ config RISCV select RISCV_TIMER select GENERIC_IRQ_MULTI_HANDLER select ARCH_HAS_PTE_SPECIAL + select HAVE_EBPF_JIT if 64BIT config MMU def_bool y @@ -103,7 +104,7 @@ choice prompt "Base ISA" default ARCH_RV64I help - This selects the base ISA that this kernel will traget and must match + This selects the base ISA that this kernel will target and must match the target platform. config ARCH_RV32I diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index 4b594f2e4f7e..c6342e638ef7 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -77,7 +77,7 @@ KBUILD_IMAGE := $(boot)/Image.gz head-y := arch/riscv/kernel/head.o -core-y += arch/riscv/kernel/ arch/riscv/mm/ +core-y += arch/riscv/kernel/ arch/riscv/mm/ arch/riscv/net/ libs-y += arch/riscv/lib/ diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index f399659d3b8d..2fd3461e50ab 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -13,8 +13,6 @@ CONFIG_BLK_DEV_INITRD=y CONFIG_EXPERT=y CONFIG_BPF_SYSCALL=y CONFIG_SMP=y -CONFIG_PCI=y -CONFIG_PCIE_XILINX=y CONFIG_MODULES=y CONFIG_MODULE_UNLOAD=y CONFIG_NET=y @@ -28,6 +26,10 @@ CONFIG_IP_PNP_DHCP=y CONFIG_IP_PNP_BOOTP=y CONFIG_IP_PNP_RARP=y CONFIG_NETLINK_DIAG=y +CONFIG_PCI=y +CONFIG_PCIEPORTBUS=y +CONFIG_PCI_HOST_GENERIC=y +CONFIG_PCIE_XILINX=y CONFIG_DEVTMPFS=y CONFIG_BLK_DEV_LOOP=y CONFIG_VIRTIO_BLK=y @@ -63,7 +65,6 @@ CONFIG_USB_STORAGE=y CONFIG_USB_UAS=y CONFIG_VIRTIO_MMIO=y CONFIG_SIFIVE_PLIC=y -CONFIG_RAS=y CONFIG_EXT4_FS=y CONFIG_EXT4_FS_POSIX_ACL=y CONFIG_AUTOFS4_FS=y @@ -77,5 +78,6 @@ CONFIG_NFS_V4_1=y CONFIG_NFS_V4_2=y CONFIG_ROOT_NFS=y CONFIG_CRYPTO_USER_API_HASH=y +CONFIG_CRYPTO_DEV_VIRTIO=y CONFIG_PRINTK_TIME=y # CONFIG_RCU_TRACE is not set diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h index 06cfbb3aacbb..2a546a52f02a 100644 --- a/arch/riscv/include/asm/page.h +++ b/arch/riscv/include/asm/page.h @@ -80,7 +80,7 @@ typedef struct page *pgtable_t; #define __pgd(x) ((pgd_t) { (x) }) #define __pgprot(x) ((pgprot_t) { (x) }) -#ifdef CONFIG_64BITS +#ifdef CONFIG_64BIT #define PTE_FMT "%016lx" #else #define PTE_FMT "%08lx" diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h index 2fa2942be221..470755cb7558 100644 --- a/arch/riscv/include/asm/pgtable-bits.h +++ b/arch/riscv/include/asm/pgtable-bits.h @@ -35,6 +35,12 @@ #define _PAGE_SPECIAL _PAGE_SOFT #define _PAGE_TABLE _PAGE_PRESENT +/* + * _PAGE_PROT_NONE is set on not-present pages (and ignored by the hardware) to + * distinguish them from swapped out pages + */ +#define _PAGE_PROT_NONE _PAGE_READ + #define _PAGE_PFN_SHIFT 10 /* Set of bits to preserve across pte_modify() */ diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h index 16301966d65b..a8179a8c1491 100644 --- a/arch/riscv/include/asm/pgtable.h +++ b/arch/riscv/include/asm/pgtable.h @@ -44,7 +44,7 @@ /* Page protection bits */ #define _PAGE_BASE (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_USER) -#define PAGE_NONE __pgprot(0) +#define PAGE_NONE __pgprot(_PAGE_PROT_NONE) #define PAGE_READ __pgprot(_PAGE_BASE | _PAGE_READ) #define PAGE_WRITE __pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_WRITE) #define PAGE_EXEC __pgprot(_PAGE_BASE | _PAGE_EXEC) @@ -98,7 +98,7 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; static inline int pmd_present(pmd_t pmd) { - return (pmd_val(pmd) & _PAGE_PRESENT); + return (pmd_val(pmd) & (_PAGE_PRESENT | _PAGE_PROT_NONE)); } static inline int pmd_none(pmd_t pmd) @@ -178,7 +178,7 @@ static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long addr) static inline int pte_present(pte_t pte) { - return (pte_val(pte) & _PAGE_PRESENT); + return (pte_val(pte) & (_PAGE_PRESENT | _PAGE_PROT_NONE)); } static inline int pte_none(pte_t pte) @@ -380,7 +380,7 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma, * * Format of swap PTE: * bit 0: _PAGE_PRESENT (zero) - * bit 1: reserved for future use (zero) + * bit 1: _PAGE_PROT_NONE (zero) * bits 2 to 6: swap type * bits 7 to XLEN-1: swap offset */ diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h index 0531f49af5c3..ce70bceb8872 100644 --- a/arch/riscv/include/asm/processor.h +++ b/arch/riscv/include/asm/processor.h @@ -22,7 +22,7 @@ * This decides where the kernel will search for a free chunk of vm * space during mmap's. */ -#define TASK_UNMAPPED_BASE PAGE_ALIGN(TASK_SIZE >> 1) +#define TASK_UNMAPPED_BASE PAGE_ALIGN(TASK_SIZE / 3) #define STACK_TOP TASK_SIZE #define STACK_TOP_MAX STACK_TOP diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c index 6a92a2fe198e..dac98348c6a3 100644 --- a/arch/riscv/kernel/asm-offsets.c +++ b/arch/riscv/kernel/asm-offsets.c @@ -39,6 +39,7 @@ void asm_offsets(void) OFFSET(TASK_STACK, task_struct, stack); OFFSET(TASK_TI, task_struct, thread_info); OFFSET(TASK_TI_FLAGS, task_struct, thread_info.flags); + OFFSET(TASK_TI_PREEMPT_COUNT, task_struct, thread_info.preempt_count); OFFSET(TASK_TI_KERNEL_SP, task_struct, thread_info.kernel_sp); OFFSET(TASK_TI_USER_SP, task_struct, thread_info.user_sp); OFFSET(TASK_TI_CPU, task_struct, thread_info.cpu); diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S index 355166f57205..fd9b57c8b4ce 100644 --- a/arch/riscv/kernel/entry.S +++ b/arch/riscv/kernel/entry.S @@ -144,6 +144,10 @@ _save_context: REG_L x2, PT_SP(sp) .endm +#if !IS_ENABLED(CONFIG_PREEMPT) +.set resume_kernel, restore_all +#endif + ENTRY(handle_exception) SAVE_ALL @@ -228,7 +232,7 @@ ret_from_exception: REG_L s0, PT_SSTATUS(sp) csrc sstatus, SR_SIE andi s0, s0, SR_SPP - bnez s0, restore_all + bnez s0, resume_kernel resume_userspace: /* Interrupts must be disabled here so flags are checked atomically */ @@ -250,6 +254,18 @@ restore_all: RESTORE_ALL sret +#if IS_ENABLED(CONFIG_PREEMPT) +resume_kernel: + REG_L s0, TASK_TI_PREEMPT_COUNT(tp) + bnez s0, restore_all +need_resched: + REG_L s0, TASK_TI_FLAGS(tp) + andi s0, s0, _TIF_NEED_RESCHED + beqz s0, restore_all + call preempt_schedule_irq + j need_resched +#endif + work_pending: /* Enter slow path for supplementary processing */ la ra, ret_from_exception diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index 6e079e94b638..77564310235f 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -181,7 +181,7 @@ static void __init setup_bootmem(void) BUG_ON(mem_size == 0); set_max_mapnr(PFN_DOWN(mem_size)); - max_low_pfn = memblock_end_of_DRAM(); + max_low_pfn = PFN_DOWN(memblock_end_of_DRAM()); #ifdef CONFIG_BLK_DEV_INITRD setup_initrd(); diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c index fc185ecabb0a..18cda0e8cf94 100644 --- a/arch/riscv/kernel/smpboot.c +++ b/arch/riscv/kernel/smpboot.c @@ -57,15 +57,12 @@ void __init setup_smp(void) while ((dn = of_find_node_by_type(dn, "cpu"))) { hart = riscv_of_processor_hartid(dn); - if (hart < 0) { - of_node_put(dn); + if (hart < 0) continue; - } if (hart == cpuid_to_hartid_map(0)) { BUG_ON(found_boot_cpu); found_boot_cpu = 1; - of_node_put(dn); continue; } @@ -73,7 +70,6 @@ void __init setup_smp(void) set_cpu_possible(cpuid, true); set_cpu_present(cpuid, true); cpuid++; - of_node_put(dn); } BUG_ON(!found_boot_cpu); diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S index 1e1395d63dab..65df1dfdc303 100644 --- a/arch/riscv/kernel/vmlinux.lds.S +++ b/arch/riscv/kernel/vmlinux.lds.S @@ -18,8 +18,6 @@ #include <asm/cache.h> #include <asm/thread_info.h> -#define MAX_BYTES_PER_LONG 0x10 - OUTPUT_ARCH(riscv) ENTRY(_start) @@ -76,6 +74,8 @@ SECTIONS *(.sbss*) } + BSS_SECTION(PAGE_SIZE, PAGE_SIZE, 0) + EXCEPTION_TABLE(0x10) NOTES @@ -83,10 +83,6 @@ SECTIONS *(.rel.dyn*) } - BSS_SECTION(MAX_BYTES_PER_LONG, - MAX_BYTES_PER_LONG, - MAX_BYTES_PER_LONG) - _end = .; STABS_DEBUG diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 1d9bfaff60bc..658ebf645f42 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -28,7 +28,8 @@ static void __init zone_sizes_init(void) unsigned long max_zone_pfns[MAX_NR_ZONES] = { 0, }; #ifdef CONFIG_ZONE_DMA32 - max_zone_pfns[ZONE_DMA32] = PFN_DOWN(min(4UL * SZ_1G, max_low_pfn)); + max_zone_pfns[ZONE_DMA32] = PFN_DOWN(min(4UL * SZ_1G, + (unsigned long) PFN_PHYS(max_low_pfn))); #endif max_zone_pfns[ZONE_NORMAL] = max_low_pfn; diff --git a/arch/riscv/net/Makefile b/arch/riscv/net/Makefile new file mode 100644 index 000000000000..a132220cc582 --- /dev/null +++ b/arch/riscv/net/Makefile @@ -0,0 +1 @@ +obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o diff --git a/arch/riscv/net/bpf_jit_comp.c b/arch/riscv/net/bpf_jit_comp.c new file mode 100644 index 000000000000..80b12aa5e10d --- /dev/null +++ b/arch/riscv/net/bpf_jit_comp.c @@ -0,0 +1,1602 @@ +// SPDX-License-Identifier: GPL-2.0 +/* BPF JIT compiler for RV64G + * + * Copyright(c) 2019 Björn Töpel <bjorn.topel@gmail.com> + * + */ + +#include <linux/bpf.h> +#include <linux/filter.h> +#include <asm/cacheflush.h> + +enum { + RV_REG_ZERO = 0, /* The constant value 0 */ + RV_REG_RA = 1, /* Return address */ + RV_REG_SP = 2, /* Stack pointer */ + RV_REG_GP = 3, /* Global pointer */ + RV_REG_TP = 4, /* Thread pointer */ + RV_REG_T0 = 5, /* Temporaries */ + RV_REG_T1 = 6, + RV_REG_T2 = 7, + RV_REG_FP = 8, + RV_REG_S1 = 9, /* Saved registers */ + RV_REG_A0 = 10, /* Function argument/return values */ + RV_REG_A1 = 11, /* Function arguments */ + RV_REG_A2 = 12, + RV_REG_A3 = 13, + RV_REG_A4 = 14, + RV_REG_A5 = 15, + RV_REG_A6 = 16, + RV_REG_A7 = 17, + RV_REG_S2 = 18, /* Saved registers */ + RV_REG_S3 = 19, + RV_REG_S4 = 20, + RV_REG_S5 = 21, + RV_REG_S6 = 22, + RV_REG_S7 = 23, + RV_REG_S8 = 24, + RV_REG_S9 = 25, + RV_REG_S10 = 26, + RV_REG_S11 = 27, + RV_REG_T3 = 28, /* Temporaries */ + RV_REG_T4 = 29, + RV_REG_T5 = 30, + RV_REG_T6 = 31, +}; + +#define RV_REG_TCC RV_REG_A6 +#define RV_REG_TCC_SAVED RV_REG_S6 /* Store A6 in S6 if program do calls */ + +static const int regmap[] = { + [BPF_REG_0] = RV_REG_A5, + [BPF_REG_1] = RV_REG_A0, + [BPF_REG_2] = RV_REG_A1, + [BPF_REG_3] = RV_REG_A2, + [BPF_REG_4] = RV_REG_A3, + [BPF_REG_5] = RV_REG_A4, + [BPF_REG_6] = RV_REG_S1, + [BPF_REG_7] = RV_REG_S2, + [BPF_REG_8] = RV_REG_S3, + [BPF_REG_9] = RV_REG_S4, + [BPF_REG_FP] = RV_REG_S5, + [BPF_REG_AX] = RV_REG_T0, +}; + +enum { + RV_CTX_F_SEEN_TAIL_CALL = 0, + RV_CTX_F_SEEN_CALL = RV_REG_RA, + RV_CTX_F_SEEN_S1 = RV_REG_S1, + RV_CTX_F_SEEN_S2 = RV_REG_S2, + RV_CTX_F_SEEN_S3 = RV_REG_S3, + RV_CTX_F_SEEN_S4 = RV_REG_S4, + RV_CTX_F_SEEN_S5 = RV_REG_S5, + RV_CTX_F_SEEN_S6 = RV_REG_S6, +}; + +struct rv_jit_context { + struct bpf_prog *prog; + u32 *insns; /* RV insns */ + int ninsns; + int epilogue_offset; + int *offset; /* BPF to RV */ + unsigned long flags; + int stack_size; +}; + +struct rv_jit_data { + struct bpf_binary_header *header; + u8 *image; + struct rv_jit_context ctx; +}; + +static u8 bpf_to_rv_reg(int bpf_reg, struct rv_jit_context *ctx) +{ + u8 reg = regmap[bpf_reg]; + + switch (reg) { + case RV_CTX_F_SEEN_S1: + case RV_CTX_F_SEEN_S2: + case RV_CTX_F_SEEN_S3: + case RV_CTX_F_SEEN_S4: + case RV_CTX_F_SEEN_S5: + case RV_CTX_F_SEEN_S6: + __set_bit(reg, &ctx->flags); + } + return reg; +}; + +static bool seen_reg(int reg, struct rv_jit_context *ctx) +{ + switch (reg) { + case RV_CTX_F_SEEN_CALL: + case RV_CTX_F_SEEN_S1: + case RV_CTX_F_SEEN_S2: + case RV_CTX_F_SEEN_S3: + case RV_CTX_F_SEEN_S4: + case RV_CTX_F_SEEN_S5: + case RV_CTX_F_SEEN_S6: + return test_bit(reg, &ctx->flags); + } + return false; +} + +static void mark_call(struct rv_jit_context *ctx) +{ + __set_bit(RV_CTX_F_SEEN_CALL, &ctx->flags); +} + +static bool seen_call(struct rv_jit_context *ctx) +{ + return test_bit(RV_CTX_F_SEEN_CALL, &ctx->flags); +} + +static void mark_tail_call(struct rv_jit_context *ctx) +{ + __set_bit(RV_CTX_F_SEEN_TAIL_CALL, &ctx->flags); +} + +static bool seen_tail_call(struct rv_jit_context *ctx) +{ + return test_bit(RV_CTX_F_SEEN_TAIL_CALL, &ctx->flags); +} + +static u8 rv_tail_call_reg(struct rv_jit_context *ctx) +{ + mark_tail_call(ctx); + + if (seen_call(ctx)) { + __set_bit(RV_CTX_F_SEEN_S6, &ctx->flags); + return RV_REG_S6; + } + return RV_REG_A6; +} + +static void emit(const u32 insn, struct rv_jit_context *ctx) +{ + if (ctx->insns) + ctx->insns[ctx->ninsns] = insn; + + ctx->ninsns++; +} + +static u32 rv_r_insn(u8 funct7, u8 rs2, u8 rs1, u8 funct3, u8 rd, u8 opcode) +{ + return (funct7 << 25) | (rs2 << 20) | (rs1 << 15) | (funct3 << 12) | + (rd << 7) | opcode; +} + +static u32 rv_i_insn(u16 imm11_0, u8 rs1, u8 funct3, u8 rd, u8 opcode) +{ + return (imm11_0 << 20) | (rs1 << 15) | (funct3 << 12) | (rd << 7) | + opcode; +} + +static u32 rv_s_insn(u16 imm11_0, u8 rs2, u8 rs1, u8 funct3, u8 opcode) +{ + u8 imm11_5 = imm11_0 >> 5, imm4_0 = imm11_0 & 0x1f; + + return (imm11_5 << 25) | (rs2 << 20) | (rs1 << 15) | (funct3 << 12) | + (imm4_0 << 7) | opcode; +} + +static u32 rv_sb_insn(u16 imm12_1, u8 rs2, u8 rs1, u8 funct3, u8 opcode) +{ + u8 imm12 = ((imm12_1 & 0x800) >> 5) | ((imm12_1 & 0x3f0) >> 4); + u8 imm4_1 = ((imm12_1 & 0xf) << 1) | ((imm12_1 & 0x400) >> 10); + + return (imm12 << 25) | (rs2 << 20) | (rs1 << 15) | (funct3 << 12) | + (imm4_1 << 7) | opcode; +} + +static u32 rv_u_insn(u32 imm31_12, u8 rd, u8 opcode) +{ + return (imm31_12 << 12) | (rd << 7) | opcode; +} + +static u32 rv_uj_insn(u32 imm20_1, u8 rd, u8 opcode) +{ + u32 imm; + + imm = (imm20_1 & 0x80000) | ((imm20_1 & 0x3ff) << 9) | + ((imm20_1 & 0x400) >> 2) | ((imm20_1 & 0x7f800) >> 11); + + return (imm << 12) | (rd << 7) | opcode; +} + +static u32 rv_amo_insn(u8 funct5, u8 aq, u8 rl, u8 rs2, u8 rs1, + u8 funct3, u8 rd, u8 opcode) +{ + u8 funct7 = (funct5 << 2) | (aq << 1) | rl; + + return rv_r_insn(funct7, rs2, rs1, funct3, rd, opcode); +} + +static u32 rv_addiw(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 0, rd, 0x1b); +} + +static u32 rv_addi(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 0, rd, 0x13); +} + +static u32 rv_addw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 0, rd, 0x3b); +} + +static u32 rv_add(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 0, rd, 0x33); +} + +static u32 rv_subw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0x20, rs2, rs1, 0, rd, 0x3b); +} + +static u32 rv_sub(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0x20, rs2, rs1, 0, rd, 0x33); +} + +static u32 rv_and(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 7, rd, 0x33); +} + +static u32 rv_or(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 6, rd, 0x33); +} + +static u32 rv_xor(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 4, rd, 0x33); +} + +static u32 rv_mulw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 0, rd, 0x3b); +} + +static u32 rv_mul(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 0, rd, 0x33); +} + +static u32 rv_divuw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 5, rd, 0x3b); +} + +static u32 rv_divu(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 5, rd, 0x33); +} + +static u32 rv_remuw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 7, rd, 0x3b); +} + +static u32 rv_remu(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 7, rd, 0x33); +} + +static u32 rv_sllw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 1, rd, 0x3b); +} + +static u32 rv_sll(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 1, rd, 0x33); +} + +static u32 rv_srlw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 5, rd, 0x3b); +} + +static u32 rv_srl(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 5, rd, 0x33); +} + +static u32 rv_sraw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0x20, rs2, rs1, 5, rd, 0x3b); +} + +static u32 rv_sra(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0x20, rs2, rs1, 5, rd, 0x33); +} + +static u32 rv_lui(u8 rd, u32 imm31_12) +{ + return rv_u_insn(imm31_12, rd, 0x37); +} + +static u32 rv_slli(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 1, rd, 0x13); +} + +static u32 rv_andi(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 7, rd, 0x13); +} + +static u32 rv_ori(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 6, rd, 0x13); +} + +static u32 rv_xori(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 4, rd, 0x13); +} + +static u32 rv_slliw(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 1, rd, 0x1b); +} + +static u32 rv_srliw(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 5, rd, 0x1b); +} + +static u32 rv_srli(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 5, rd, 0x13); +} + +static u32 rv_sraiw(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(0x400 | imm11_0, rs1, 5, rd, 0x1b); +} + +static u32 rv_srai(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(0x400 | imm11_0, rs1, 5, rd, 0x13); +} + +static u32 rv_jal(u8 rd, u32 imm20_1) +{ + return rv_uj_insn(imm20_1, rd, 0x6f); +} + +static u32 rv_jalr(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 0, rd, 0x67); +} + +static u32 rv_beq(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_sb_insn(imm12_1, rs2, rs1, 0, 0x63); +} + +static u32 rv_bltu(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_sb_insn(imm12_1, rs2, rs1, 6, 0x63); +} + +static u32 rv_bgeu(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_sb_insn(imm12_1, rs2, rs1, 7, 0x63); +} + +static u32 rv_bne(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_sb_insn(imm12_1, rs2, rs1, 1, 0x63); +} + +static u32 rv_blt(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_sb_insn(imm12_1, rs2, rs1, 4, 0x63); +} + +static u32 rv_bge(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_sb_insn(imm12_1, rs2, rs1, 5, 0x63); +} + +static u32 rv_sb(u8 rs1, u16 imm11_0, u8 rs2) +{ + return rv_s_insn(imm11_0, rs2, rs1, 0, 0x23); +} + +static u32 rv_sh(u8 rs1, u16 imm11_0, u8 rs2) +{ + return rv_s_insn(imm11_0, rs2, rs1, 1, 0x23); +} + +static u32 rv_sw(u8 rs1, u16 imm11_0, u8 rs2) +{ + return rv_s_insn(imm11_0, rs2, rs1, 2, 0x23); +} + +static u32 rv_sd(u8 rs1, u16 imm11_0, u8 rs2) +{ + return rv_s_insn(imm11_0, rs2, rs1, 3, 0x23); +} + +static u32 rv_lbu(u8 rd, u16 imm11_0, u8 rs1) +{ + return rv_i_insn(imm11_0, rs1, 4, rd, 0x03); +} + +static u32 rv_lhu(u8 rd, u16 imm11_0, u8 rs1) +{ + return rv_i_insn(imm11_0, rs1, 5, rd, 0x03); +} + +static u32 rv_lwu(u8 rd, u16 imm11_0, u8 rs1) +{ + return rv_i_insn(imm11_0, rs1, 6, rd, 0x03); +} + +static u32 rv_ld(u8 rd, u16 imm11_0, u8 rs1) +{ + return rv_i_insn(imm11_0, rs1, 3, rd, 0x03); +} + +static u32 rv_amoadd_w(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl) +{ + return rv_amo_insn(0, aq, rl, rs2, rs1, 2, rd, 0x2f); +} + +static u32 rv_amoadd_d(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl) +{ + return rv_amo_insn(0, aq, rl, rs2, rs1, 3, rd, 0x2f); +} + +static bool is_12b_int(s64 val) +{ + return -(1 << 11) <= val && val < (1 << 11); +} + +static bool is_13b_int(s64 val) +{ + return -(1 << 12) <= val && val < (1 << 12); +} + +static bool is_21b_int(s64 val) +{ + return -(1L << 20) <= val && val < (1L << 20); +} + +static bool is_32b_int(s64 val) +{ + return -(1L << 31) <= val && val < (1L << 31); +} + +static int is_12b_check(int off, int insn) +{ + if (!is_12b_int(off)) { + pr_err("bpf-jit: insn=%d offset=%d not supported yet!\n", + insn, (int)off); + return -1; + } + return 0; +} + +static int is_13b_check(int off, int insn) +{ + if (!is_13b_int(off)) { + pr_err("bpf-jit: insn=%d offset=%d not supported yet!\n", + insn, (int)off); + return -1; + } + return 0; +} + +static int is_21b_check(int off, int insn) +{ + if (!is_21b_int(off)) { + pr_err("bpf-jit: insn=%d offset=%d not supported yet!\n", + insn, (int)off); + return -1; + } + return 0; +} + +static void emit_imm(u8 rd, s64 val, struct rv_jit_context *ctx) +{ + /* Note that the immediate from the add is sign-extended, + * which means that we need to compensate this by adding 2^12, + * when the 12th bit is set. A simpler way of doing this, and + * getting rid of the check, is to just add 2**11 before the + * shift. The "Loading a 32-Bit constant" example from the + * "Computer Organization and Design, RISC-V edition" book by + * Patterson/Hennessy highlights this fact. + * + * This also means that we need to process LSB to MSB. + */ + s64 upper = (val + (1 << 11)) >> 12, lower = val & 0xfff; + int shift; + + if (is_32b_int(val)) { + if (upper) + emit(rv_lui(rd, upper), ctx); + + if (!upper) { + emit(rv_addi(rd, RV_REG_ZERO, lower), ctx); + return; + } + + emit(rv_addiw(rd, rd, lower), ctx); + return; + } + + shift = __ffs(upper); + upper >>= shift; + shift += 12; + + emit_imm(rd, upper, ctx); + + emit(rv_slli(rd, rd, shift), ctx); + if (lower) + emit(rv_addi(rd, rd, lower), ctx); +} + +static int rv_offset(int bpf_to, int bpf_from, struct rv_jit_context *ctx) +{ + int from = ctx->offset[bpf_from] - 1, to = ctx->offset[bpf_to]; + + return (to - from) << 2; +} + +static int epilogue_offset(struct rv_jit_context *ctx) +{ + int to = ctx->epilogue_offset, from = ctx->ninsns; + + return (to - from) << 2; +} + +static void __build_epilogue(u8 reg, struct rv_jit_context *ctx) +{ + int stack_adjust = ctx->stack_size, store_offset = stack_adjust - 8; + + if (seen_reg(RV_REG_RA, ctx)) { + emit(rv_ld(RV_REG_RA, store_offset, RV_REG_SP), ctx); + store_offset -= 8; + } + emit(rv_ld(RV_REG_FP, store_offset, RV_REG_SP), ctx); + store_offset -= 8; + if (seen_reg(RV_REG_S1, ctx)) { + emit(rv_ld(RV_REG_S1, store_offset, RV_REG_SP), ctx); + store_offset -= 8; + } + if (seen_reg(RV_REG_S2, ctx)) { + emit(rv_ld(RV_REG_S2, store_offset, RV_REG_SP), ctx); + store_offset -= 8; + } + if (seen_reg(RV_REG_S3, ctx)) { + emit(rv_ld(RV_REG_S3, store_offset, RV_REG_SP), ctx); + store_offset -= 8; + } + if (seen_reg(RV_REG_S4, ctx)) { + emit(rv_ld(RV_REG_S4, store_offset, RV_REG_SP), ctx); + store_offset -= 8; + } + if (seen_reg(RV_REG_S5, ctx)) { + emit(rv_ld(RV_REG_S5, store_offset, RV_REG_SP), ctx); + store_offset -= 8; + } + if (seen_reg(RV_REG_S6, ctx)) { + emit(rv_ld(RV_REG_S6, store_offset, RV_REG_SP), ctx); + store_offset -= 8; + } + + emit(rv_addi(RV_REG_SP, RV_REG_SP, stack_adjust), ctx); + /* Set return value. */ + emit(rv_addi(RV_REG_A0, RV_REG_A5, 0), ctx); + emit(rv_jalr(RV_REG_ZERO, reg, 0), ctx); +} + +static void emit_zext_32(u8 reg, struct rv_jit_context *ctx) +{ + emit(rv_slli(reg, reg, 32), ctx); + emit(rv_srli(reg, reg, 32), ctx); +} + +static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx) +{ + int tc_ninsn, off, start_insn = ctx->ninsns; + u8 tcc = rv_tail_call_reg(ctx); + + /* a0: &ctx + * a1: &array + * a2: index + * + * if (index >= array->map.max_entries) + * goto out; + */ + tc_ninsn = insn ? ctx->offset[insn] - ctx->offset[insn - 1] : + ctx->offset[0]; + emit_zext_32(RV_REG_A2, ctx); + + off = offsetof(struct bpf_array, map.max_entries); + if (is_12b_check(off, insn)) + return -1; + emit(rv_lwu(RV_REG_T1, off, RV_REG_A1), ctx); + off = (tc_ninsn - (ctx->ninsns - start_insn)) << 2; + if (is_13b_check(off, insn)) + return -1; + emit(rv_bgeu(RV_REG_A2, RV_REG_T1, off >> 1), ctx); + + /* if (--TCC < 0) + * goto out; + */ + emit(rv_addi(RV_REG_T1, tcc, -1), ctx); + off = (tc_ninsn - (ctx->ninsns - start_insn)) << 2; + if (is_13b_check(off, insn)) + return -1; + emit(rv_blt(RV_REG_T1, RV_REG_ZERO, off >> 1), ctx); + + /* prog = array->ptrs[index]; + * if (!prog) + * goto out; + */ + emit(rv_slli(RV_REG_T2, RV_REG_A2, 3), ctx); + emit(rv_add(RV_REG_T2, RV_REG_T2, RV_REG_A1), ctx); + off = offsetof(struct bpf_array, ptrs); + if (is_12b_check(off, insn)) + return -1; + emit(rv_ld(RV_REG_T2, off, RV_REG_T2), ctx); + off = (tc_ninsn - (ctx->ninsns - start_insn)) << 2; + if (is_13b_check(off, insn)) + return -1; + emit(rv_beq(RV_REG_T2, RV_REG_ZERO, off >> 1), ctx); + + /* goto *(prog->bpf_func + 4); */ + off = offsetof(struct bpf_prog, bpf_func); + if (is_12b_check(off, insn)) + return -1; + emit(rv_ld(RV_REG_T3, off, RV_REG_T2), ctx); + emit(rv_addi(RV_REG_T3, RV_REG_T3, 4), ctx); + emit(rv_addi(RV_REG_TCC, RV_REG_T1, 0), ctx); + __build_epilogue(RV_REG_T3, ctx); + return 0; +} + +static void init_regs(u8 *rd, u8 *rs, const struct bpf_insn *insn, + struct rv_jit_context *ctx) +{ + u8 code = insn->code; + + switch (code) { + case BPF_JMP | BPF_JA: + case BPF_JMP | BPF_CALL: + case BPF_JMP | BPF_EXIT: + case BPF_JMP | BPF_TAIL_CALL: + break; + default: + *rd = bpf_to_rv_reg(insn->dst_reg, ctx); + } + + if (code & (BPF_ALU | BPF_X) || code & (BPF_ALU64 | BPF_X) || + code & (BPF_JMP | BPF_X) || code & (BPF_JMP32 | BPF_X) || + code & BPF_LDX || code & BPF_STX) + *rs = bpf_to_rv_reg(insn->src_reg, ctx); +} + +static int rv_offset_check(int *rvoff, s16 off, int insn, + struct rv_jit_context *ctx) +{ + *rvoff = rv_offset(insn + off, insn, ctx); + return is_13b_check(*rvoff, insn); +} + +static void emit_zext_32_rd_rs(u8 *rd, u8 *rs, struct rv_jit_context *ctx) +{ + emit(rv_addi(RV_REG_T2, *rd, 0), ctx); + emit_zext_32(RV_REG_T2, ctx); + emit(rv_addi(RV_REG_T1, *rs, 0), ctx); + emit_zext_32(RV_REG_T1, ctx); + *rd = RV_REG_T2; + *rs = RV_REG_T1; +} + +static void emit_sext_32_rd_rs(u8 *rd, u8 *rs, struct rv_jit_context *ctx) +{ + emit(rv_addiw(RV_REG_T2, *rd, 0), ctx); + emit(rv_addiw(RV_REG_T1, *rs, 0), ctx); + *rd = RV_REG_T2; + *rs = RV_REG_T1; +} + +static void emit_zext_32_rd_t1(u8 *rd, struct rv_jit_context *ctx) +{ + emit(rv_addi(RV_REG_T2, *rd, 0), ctx); + emit_zext_32(RV_REG_T2, ctx); + emit_zext_32(RV_REG_T1, ctx); + *rd = RV_REG_T2; +} + +static void emit_sext_32_rd(u8 *rd, struct rv_jit_context *ctx) +{ + emit(rv_addiw(RV_REG_T2, *rd, 0), ctx); + *rd = RV_REG_T2; +} + +static int emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, + bool extra_pass) +{ + bool is64 = BPF_CLASS(insn->code) == BPF_ALU64 || + BPF_CLASS(insn->code) == BPF_JMP; + int rvoff, i = insn - ctx->prog->insnsi; + u8 rd = -1, rs = -1, code = insn->code; + s16 off = insn->off; + s32 imm = insn->imm; + + init_regs(&rd, &rs, insn, ctx); + + switch (code) { + /* dst = src */ + case BPF_ALU | BPF_MOV | BPF_X: + case BPF_ALU64 | BPF_MOV | BPF_X: + emit(is64 ? rv_addi(rd, rs, 0) : rv_addiw(rd, rs, 0), ctx); + if (!is64) + emit_zext_32(rd, ctx); + break; + + /* dst = dst OP src */ + case BPF_ALU | BPF_ADD | BPF_X: + case BPF_ALU64 | BPF_ADD | BPF_X: + emit(is64 ? rv_add(rd, rd, rs) : rv_addw(rd, rd, rs), ctx); + break; + case BPF_ALU | BPF_SUB | BPF_X: + case BPF_ALU64 | BPF_SUB | BPF_X: + emit(is64 ? rv_sub(rd, rd, rs) : rv_subw(rd, rd, rs), ctx); + break; + case BPF_ALU | BPF_AND | BPF_X: + case BPF_ALU64 | BPF_AND | BPF_X: + emit(rv_and(rd, rd, rs), ctx); + break; + case BPF_ALU | BPF_OR | BPF_X: + case BPF_ALU64 | BPF_OR | BPF_X: + emit(rv_or(rd, rd, rs), ctx); + break; + case BPF_ALU | BPF_XOR | BPF_X: + case BPF_ALU64 | BPF_XOR | BPF_X: + emit(rv_xor(rd, rd, rs), ctx); + break; + case BPF_ALU | BPF_MUL | BPF_X: + case BPF_ALU64 | BPF_MUL | BPF_X: + emit(is64 ? rv_mul(rd, rd, rs) : rv_mulw(rd, rd, rs), ctx); + if (!is64) + emit_zext_32(rd, ctx); + break; + case BPF_ALU | BPF_DIV | BPF_X: + case BPF_ALU64 | BPF_DIV | BPF_X: + emit(is64 ? rv_divu(rd, rd, rs) : rv_divuw(rd, rd, rs), ctx); + if (!is64) + emit_zext_32(rd, ctx); + break; + case BPF_ALU | BPF_MOD | BPF_X: + case BPF_ALU64 | BPF_MOD | BPF_X: + emit(is64 ? rv_remu(rd, rd, rs) : rv_remuw(rd, rd, rs), ctx); + if (!is64) + emit_zext_32(rd, ctx); + break; + case BPF_ALU | BPF_LSH | BPF_X: + case BPF_ALU64 | BPF_LSH | BPF_X: + emit(is64 ? rv_sll(rd, rd, rs) : rv_sllw(rd, rd, rs), ctx); + break; + case BPF_ALU | BPF_RSH | BPF_X: + case BPF_ALU64 | BPF_RSH | BPF_X: + emit(is64 ? rv_srl(rd, rd, rs) : rv_srlw(rd, rd, rs), ctx); + break; + case BPF_ALU | BPF_ARSH | BPF_X: + case BPF_ALU64 | BPF_ARSH | BPF_X: + emit(is64 ? rv_sra(rd, rd, rs) : rv_sraw(rd, rd, rs), ctx); + break; + + /* dst = -dst */ + case BPF_ALU | BPF_NEG: + case BPF_ALU64 | BPF_NEG: + emit(is64 ? rv_sub(rd, RV_REG_ZERO, rd) : + rv_subw(rd, RV_REG_ZERO, rd), ctx); + break; + + /* dst = BSWAP##imm(dst) */ + case BPF_ALU | BPF_END | BPF_FROM_LE: + { + int shift = 64 - imm; + + emit(rv_slli(rd, rd, shift), ctx); + emit(rv_srli(rd, rd, shift), ctx); + break; + } + case BPF_ALU | BPF_END | BPF_FROM_BE: + emit(rv_addi(RV_REG_T2, RV_REG_ZERO, 0), ctx); + + emit(rv_andi(RV_REG_T1, rd, 0xff), ctx); + emit(rv_add(RV_REG_T2, RV_REG_T2, RV_REG_T1), ctx); + emit(rv_slli(RV_REG_T2, RV_REG_T2, 8), ctx); + emit(rv_srli(rd, rd, 8), ctx); + if (imm == 16) + goto out_be; + + emit(rv_andi(RV_REG_T1, rd, 0xff), ctx); + emit(rv_add(RV_REG_T2, RV_REG_T2, RV_REG_T1), ctx); + emit(rv_slli(RV_REG_T2, RV_REG_T2, 8), ctx); + emit(rv_srli(rd, rd, 8), ctx); + + emit(rv_andi(RV_REG_T1, rd, 0xff), ctx); + emit(rv_add(RV_REG_T2, RV_REG_T2, RV_REG_T1), ctx); + emit(rv_slli(RV_REG_T2, RV_REG_T2, 8), ctx); + emit(rv_srli(rd, rd, 8), ctx); + if (imm == 32) + goto out_be; + + emit(rv_andi(RV_REG_T1, rd, 0xff), ctx); + emit(rv_add(RV_REG_T2, RV_REG_T2, RV_REG_T1), ctx); + emit(rv_slli(RV_REG_T2, RV_REG_T2, 8), ctx); + emit(rv_srli(rd, rd, 8), ctx); + + emit(rv_andi(RV_REG_T1, rd, 0xff), ctx); + emit(rv_add(RV_REG_T2, RV_REG_T2, RV_REG_T1), ctx); + emit(rv_slli(RV_REG_T2, RV_REG_T2, 8), ctx); + emit(rv_srli(rd, rd, 8), ctx); + + emit(rv_andi(RV_REG_T1, rd, 0xff), ctx); + emit(rv_add(RV_REG_T2, RV_REG_T2, RV_REG_T1), ctx); + emit(rv_slli(RV_REG_T2, RV_REG_T2, 8), ctx); + emit(rv_srli(rd, rd, 8), ctx); + + emit(rv_andi(RV_REG_T1, rd, 0xff), ctx); + emit(rv_add(RV_REG_T2, RV_REG_T2, RV_REG_T1), ctx); + emit(rv_slli(RV_REG_T2, RV_REG_T2, 8), ctx); + emit(rv_srli(rd, rd, 8), ctx); +out_be: + emit(rv_andi(RV_REG_T1, rd, 0xff), ctx); + emit(rv_add(RV_REG_T2, RV_REG_T2, RV_REG_T1), ctx); + + emit(rv_addi(rd, RV_REG_T2, 0), ctx); + break; + + /* dst = imm */ + case BPF_ALU | BPF_MOV | BPF_K: + case BPF_ALU64 | BPF_MOV | BPF_K: + emit_imm(rd, imm, ctx); + if (!is64) + emit_zext_32(rd, ctx); + break; + + /* dst = dst OP imm */ + case BPF_ALU | BPF_ADD | BPF_K: + case BPF_ALU64 | BPF_ADD | BPF_K: + if (is_12b_int(imm)) { + emit(is64 ? rv_addi(rd, rd, imm) : + rv_addiw(rd, rd, imm), ctx); + } else { + emit_imm(RV_REG_T1, imm, ctx); + emit(is64 ? rv_add(rd, rd, RV_REG_T1) : + rv_addw(rd, rd, RV_REG_T1), ctx); + } + if (!is64) + emit_zext_32(rd, ctx); + break; + case BPF_ALU | BPF_SUB | BPF_K: + case BPF_ALU64 | BPF_SUB | BPF_K: + if (is_12b_int(-imm)) { + emit(is64 ? rv_addi(rd, rd, -imm) : + rv_addiw(rd, rd, -imm), ctx); + } else { + emit_imm(RV_REG_T1, imm, ctx); + emit(is64 ? rv_sub(rd, rd, RV_REG_T1) : + rv_subw(rd, rd, RV_REG_T1), ctx); + } + if (!is64) + emit_zext_32(rd, ctx); + break; + case BPF_ALU | BPF_AND | BPF_K: + case BPF_ALU64 | BPF_AND | BPF_K: + if (is_12b_int(imm)) { + emit(rv_andi(rd, rd, imm), ctx); + } else { + emit_imm(RV_REG_T1, imm, ctx); + emit(rv_and(rd, rd, RV_REG_T1), ctx); + } + if (!is64) + emit_zext_32(rd, ctx); + break; + case BPF_ALU | BPF_OR | BPF_K: + case BPF_ALU64 | BPF_OR | BPF_K: + if (is_12b_int(imm)) { + emit(rv_ori(rd, rd, imm), ctx); + } else { + emit_imm(RV_REG_T1, imm, ctx); + emit(rv_or(rd, rd, RV_REG_T1), ctx); + } + if (!is64) + emit_zext_32(rd, ctx); + break; + case BPF_ALU | BPF_XOR | BPF_K: + case BPF_ALU64 | BPF_XOR | BPF_K: + if (is_12b_int(imm)) { + emit(rv_xori(rd, rd, imm), ctx); + } else { + emit_imm(RV_REG_T1, imm, ctx); + emit(rv_xor(rd, rd, RV_REG_T1), ctx); + } + if (!is64) + emit_zext_32(rd, ctx); + break; + case BPF_ALU | BPF_MUL | BPF_K: + case BPF_ALU64 | BPF_MUL | BPF_K: + emit_imm(RV_REG_T1, imm, ctx); + emit(is64 ? rv_mul(rd, rd, RV_REG_T1) : + rv_mulw(rd, rd, RV_REG_T1), ctx); + if (!is64) + emit_zext_32(rd, ctx); + break; + case BPF_ALU | BPF_DIV | BPF_K: + case BPF_ALU64 | BPF_DIV | BPF_K: + emit_imm(RV_REG_T1, imm, ctx); + emit(is64 ? rv_divu(rd, rd, RV_REG_T1) : + rv_divuw(rd, rd, RV_REG_T1), ctx); + if (!is64) + emit_zext_32(rd, ctx); + break; + case BPF_ALU | BPF_MOD | BPF_K: + case BPF_ALU64 | BPF_MOD | BPF_K: + emit_imm(RV_REG_T1, imm, ctx); + emit(is64 ? rv_remu(rd, rd, RV_REG_T1) : + rv_remuw(rd, rd, RV_REG_T1), ctx); + if (!is64) + emit_zext_32(rd, ctx); + break; + case BPF_ALU | BPF_LSH | BPF_K: + case BPF_ALU64 | BPF_LSH | BPF_K: + emit(is64 ? rv_slli(rd, rd, imm) : rv_slliw(rd, rd, imm), ctx); + break; + case BPF_ALU | BPF_RSH | BPF_K: + case BPF_ALU64 | BPF_RSH | BPF_K: + emit(is64 ? rv_srli(rd, rd, imm) : rv_srliw(rd, rd, imm), ctx); + break; + case BPF_ALU | BPF_ARSH | BPF_K: + case BPF_ALU64 | BPF_ARSH | BPF_K: + emit(is64 ? rv_srai(rd, rd, imm) : rv_sraiw(rd, rd, imm), ctx); + break; + + /* JUMP off */ + case BPF_JMP | BPF_JA: + rvoff = rv_offset(i + off, i, ctx); + if (!is_21b_int(rvoff)) { + pr_err("bpf-jit: insn=%d offset=%d not supported yet!\n", + i, rvoff); + return -1; + } + + emit(rv_jal(RV_REG_ZERO, rvoff >> 1), ctx); + break; + + /* IF (dst COND src) JUMP off */ + case BPF_JMP | BPF_JEQ | BPF_X: + case BPF_JMP32 | BPF_JEQ | BPF_X: + if (rv_offset_check(&rvoff, off, i, ctx)) + return -1; + if (!is64) + emit_zext_32_rd_rs(&rd, &rs, ctx); + emit(rv_beq(rd, rs, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JGT | BPF_X: + case BPF_JMP32 | BPF_JGT | BPF_X: + if (rv_offset_check(&rvoff, off, i, ctx)) + return -1; + if (!is64) + emit_zext_32_rd_rs(&rd, &rs, ctx); + emit(rv_bltu(rs, rd, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JLT | BPF_X: + case BPF_JMP32 | BPF_JLT | BPF_X: + if (rv_offset_check(&rvoff, off, i, ctx)) + return -1; + if (!is64) + emit_zext_32_rd_rs(&rd, &rs, ctx); + emit(rv_bltu(rd, rs, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JGE | BPF_X: + case BPF_JMP32 | BPF_JGE | BPF_X: + if (rv_offset_check(&rvoff, off, i, ctx)) + return -1; + if (!is64) + emit_zext_32_rd_rs(&rd, &rs, ctx); + emit(rv_bgeu(rd, rs, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JLE | BPF_X: + case BPF_JMP32 | BPF_JLE | BPF_X: + if (rv_offset_check(&rvoff, off, i, ctx)) + return -1; + if (!is64) + emit_zext_32_rd_rs(&rd, &rs, ctx); + emit(rv_bgeu(rs, rd, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JNE | BPF_X: + case BPF_JMP32 | BPF_JNE | BPF_X: + if (rv_offset_check(&rvoff, off, i, ctx)) + return -1; + if (!is64) + emit_zext_32_rd_rs(&rd, &rs, ctx); + emit(rv_bne(rd, rs, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JSGT | BPF_X: + case BPF_JMP32 | BPF_JSGT | BPF_X: + if (rv_offset_check(&rvoff, off, i, ctx)) + return -1; + if (!is64) + emit_sext_32_rd_rs(&rd, &rs, ctx); + emit(rv_blt(rs, rd, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JSLT | BPF_X: + case BPF_JMP32 | BPF_JSLT | BPF_X: + if (rv_offset_check(&rvoff, off, i, ctx)) + return -1; + if (!is64) + emit_sext_32_rd_rs(&rd, &rs, ctx); + emit(rv_blt(rd, rs, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JSGE | BPF_X: + case BPF_JMP32 | BPF_JSGE | BPF_X: + if (rv_offset_check(&rvoff, off, i, ctx)) + return -1; + if (!is64) + emit_sext_32_rd_rs(&rd, &rs, ctx); + emit(rv_bge(rd, rs, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JSLE | BPF_X: + case BPF_JMP32 | BPF_JSLE | BPF_X: + if (rv_offset_check(&rvoff, off, i, ctx)) + return -1; + if (!is64) + emit_sext_32_rd_rs(&rd, &rs, ctx); + emit(rv_bge(rs, rd, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JSET | BPF_X: + case BPF_JMP32 | BPF_JSET | BPF_X: + if (rv_offset_check(&rvoff, off, i, ctx)) + return -1; + if (!is64) + emit_zext_32_rd_rs(&rd, &rs, ctx); + emit(rv_and(RV_REG_T1, rd, rs), ctx); + emit(rv_bne(RV_REG_T1, RV_REG_ZERO, rvoff >> 1), ctx); + break; + + /* IF (dst COND imm) JUMP off */ + case BPF_JMP | BPF_JEQ | BPF_K: + case BPF_JMP32 | BPF_JEQ | BPF_K: + if (rv_offset_check(&rvoff, off, i, ctx)) + return -1; + emit_imm(RV_REG_T1, imm, ctx); + if (!is64) + emit_zext_32_rd_t1(&rd, ctx); + emit(rv_beq(rd, RV_REG_T1, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP32 | BPF_JGT | BPF_K: + if (rv_offset_check(&rvoff, off, i, ctx)) + return -1; + emit_imm(RV_REG_T1, imm, ctx); + if (!is64) + emit_zext_32_rd_t1(&rd, ctx); + emit(rv_bltu(RV_REG_T1, rd, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JLT | BPF_K: + case BPF_JMP32 | BPF_JLT | BPF_K: + if (rv_offset_check(&rvoff, off, i, ctx)) + return -1; + emit_imm(RV_REG_T1, imm, ctx); + if (!is64) + emit_zext_32_rd_t1(&rd, ctx); + emit(rv_bltu(rd, RV_REG_T1, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JGE | BPF_K: + case BPF_JMP32 | BPF_JGE | BPF_K: + if (rv_offset_check(&rvoff, off, i, ctx)) + return -1; + emit_imm(RV_REG_T1, imm, ctx); + if (!is64) + emit_zext_32_rd_t1(&rd, ctx); + emit(rv_bgeu(rd, RV_REG_T1, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JLE | BPF_K: + case BPF_JMP32 | BPF_JLE | BPF_K: + if (rv_offset_check(&rvoff, off, i, ctx)) + return -1; + emit_imm(RV_REG_T1, imm, ctx); + if (!is64) + emit_zext_32_rd_t1(&rd, ctx); + emit(rv_bgeu(RV_REG_T1, rd, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JNE | BPF_K: + case BPF_JMP32 | BPF_JNE | BPF_K: + if (rv_offset_check(&rvoff, off, i, ctx)) + return -1; + emit_imm(RV_REG_T1, imm, ctx); + if (!is64) + emit_zext_32_rd_t1(&rd, ctx); + emit(rv_bne(rd, RV_REG_T1, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JSGT | BPF_K: + case BPF_JMP32 | BPF_JSGT | BPF_K: + if (rv_offset_check(&rvoff, off, i, ctx)) + return -1; + emit_imm(RV_REG_T1, imm, ctx); + if (!is64) + emit_sext_32_rd(&rd, ctx); + emit(rv_blt(RV_REG_T1, rd, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JSLT | BPF_K: + case BPF_JMP32 | BPF_JSLT | BPF_K: + if (rv_offset_check(&rvoff, off, i, ctx)) + return -1; + emit_imm(RV_REG_T1, imm, ctx); + if (!is64) + emit_sext_32_rd(&rd, ctx); + emit(rv_blt(rd, RV_REG_T1, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JSGE | BPF_K: + case BPF_JMP32 | BPF_JSGE | BPF_K: + if (rv_offset_check(&rvoff, off, i, ctx)) + return -1; + emit_imm(RV_REG_T1, imm, ctx); + if (!is64) + emit_sext_32_rd(&rd, ctx); + emit(rv_bge(rd, RV_REG_T1, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JSLE | BPF_K: + case BPF_JMP32 | BPF_JSLE | BPF_K: + if (rv_offset_check(&rvoff, off, i, ctx)) + return -1; + emit_imm(RV_REG_T1, imm, ctx); + if (!is64) + emit_sext_32_rd(&rd, ctx); + emit(rv_bge(RV_REG_T1, rd, rvoff >> 1), ctx); + break; + case BPF_JMP | BPF_JSET | BPF_K: + case BPF_JMP32 | BPF_JSET | BPF_K: + if (rv_offset_check(&rvoff, off, i, ctx)) + return -1; + emit_imm(RV_REG_T1, imm, ctx); + if (!is64) + emit_zext_32_rd_t1(&rd, ctx); + emit(rv_and(RV_REG_T1, rd, RV_REG_T1), ctx); + emit(rv_bne(RV_REG_T1, RV_REG_ZERO, rvoff >> 1), ctx); + break; + + /* function call */ + case BPF_JMP | BPF_CALL: + { + bool fixed; + int i, ret; + u64 addr; + + mark_call(ctx); + ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass, &addr, + &fixed); + if (ret < 0) + return ret; + if (fixed) { + emit_imm(RV_REG_T1, addr, ctx); + } else { + i = ctx->ninsns; + emit_imm(RV_REG_T1, addr, ctx); + for (i = ctx->ninsns - i; i < 8; i++) { + /* nop */ + emit(rv_addi(RV_REG_ZERO, RV_REG_ZERO, 0), + ctx); + } + } + emit(rv_jalr(RV_REG_RA, RV_REG_T1, 0), ctx); + rd = bpf_to_rv_reg(BPF_REG_0, ctx); + emit(rv_addi(rd, RV_REG_A0, 0), ctx); + break; + } + /* tail call */ + case BPF_JMP | BPF_TAIL_CALL: + if (emit_bpf_tail_call(i, ctx)) + return -1; + break; + + /* function return */ + case BPF_JMP | BPF_EXIT: + if (i == ctx->prog->len - 1) + break; + + rvoff = epilogue_offset(ctx); + if (is_21b_check(rvoff, i)) + return -1; + emit(rv_jal(RV_REG_ZERO, rvoff >> 1), ctx); + break; + + /* dst = imm64 */ + case BPF_LD | BPF_IMM | BPF_DW: + { + struct bpf_insn insn1 = insn[1]; + u64 imm64; + + imm64 = (u64)insn1.imm << 32 | (u32)imm; + emit_imm(rd, imm64, ctx); + return 1; + } + + /* LDX: dst = *(size *)(src + off) */ + case BPF_LDX | BPF_MEM | BPF_B: + if (is_12b_int(off)) { + emit(rv_lbu(rd, off, rs), ctx); + break; + } + + emit_imm(RV_REG_T1, off, ctx); + emit(rv_add(RV_REG_T1, RV_REG_T1, rs), ctx); + emit(rv_lbu(rd, 0, RV_REG_T1), ctx); + break; + case BPF_LDX | BPF_MEM | BPF_H: + if (is_12b_int(off)) { + emit(rv_lhu(rd, off, rs), ctx); + break; + } + + emit_imm(RV_REG_T1, off, ctx); + emit(rv_add(RV_REG_T1, RV_REG_T1, rs), ctx); + emit(rv_lhu(rd, 0, RV_REG_T1), ctx); + break; + case BPF_LDX | BPF_MEM | BPF_W: + if (is_12b_int(off)) { + emit(rv_lwu(rd, off, rs), ctx); + break; + } + + emit_imm(RV_REG_T1, off, ctx); + emit(rv_add(RV_REG_T1, RV_REG_T1, rs), ctx); + emit(rv_lwu(rd, 0, RV_REG_T1), ctx); + break; + case BPF_LDX | BPF_MEM | BPF_DW: + if (is_12b_int(off)) { + emit(rv_ld(rd, off, rs), ctx); + break; + } + + emit_imm(RV_REG_T1, off, ctx); + emit(rv_add(RV_REG_T1, RV_REG_T1, rs), ctx); + emit(rv_ld(rd, 0, RV_REG_T1), ctx); + break; + + /* ST: *(size *)(dst + off) = imm */ + case BPF_ST | BPF_MEM | BPF_B: + emit_imm(RV_REG_T1, imm, ctx); + if (is_12b_int(off)) { + emit(rv_sb(rd, off, RV_REG_T1), ctx); + break; + } + + emit_imm(RV_REG_T2, off, ctx); + emit(rv_add(RV_REG_T2, RV_REG_T2, rd), ctx); + emit(rv_sb(RV_REG_T2, 0, RV_REG_T1), ctx); + break; + + case BPF_ST | BPF_MEM | BPF_H: + emit_imm(RV_REG_T1, imm, ctx); + if (is_12b_int(off)) { + emit(rv_sh(rd, off, RV_REG_T1), ctx); + break; + } + + emit_imm(RV_REG_T2, off, ctx); + emit(rv_add(RV_REG_T2, RV_REG_T2, rd), ctx); + emit(rv_sh(RV_REG_T2, 0, RV_REG_T1), ctx); + break; + case BPF_ST | BPF_MEM | BPF_W: + emit_imm(RV_REG_T1, imm, ctx); + if (is_12b_int(off)) { + emit(rv_sw(rd, off, RV_REG_T1), ctx); + break; + } + + emit_imm(RV_REG_T2, off, ctx); + emit(rv_add(RV_REG_T2, RV_REG_T2, rd), ctx); + emit(rv_sw(RV_REG_T2, 0, RV_REG_T1), ctx); + break; + case BPF_ST | BPF_MEM | BPF_DW: + emit_imm(RV_REG_T1, imm, ctx); + if (is_12b_int(off)) { + emit(rv_sd(rd, off, RV_REG_T1), ctx); + break; + } + + emit_imm(RV_REG_T2, off, ctx); + emit(rv_add(RV_REG_T2, RV_REG_T2, rd), ctx); + emit(rv_sd(RV_REG_T2, 0, RV_REG_T1), ctx); + break; + + /* STX: *(size *)(dst + off) = src */ + case BPF_STX | BPF_MEM | BPF_B: + if (is_12b_int(off)) { + emit(rv_sb(rd, off, rs), ctx); + break; + } + + emit_imm(RV_REG_T1, off, ctx); + emit(rv_add(RV_REG_T1, RV_REG_T1, rd), ctx); + emit(rv_sb(RV_REG_T1, 0, rs), ctx); + break; + case BPF_STX | BPF_MEM | BPF_H: + if (is_12b_int(off)) { + emit(rv_sh(rd, off, rs), ctx); + break; + } + + emit_imm(RV_REG_T1, off, ctx); + emit(rv_add(RV_REG_T1, RV_REG_T1, rd), ctx); + emit(rv_sh(RV_REG_T1, 0, rs), ctx); + break; + case BPF_STX | BPF_MEM | BPF_W: + if (is_12b_int(off)) { + emit(rv_sw(rd, off, rs), ctx); + break; + } + + emit_imm(RV_REG_T1, off, ctx); + emit(rv_add(RV_REG_T1, RV_REG_T1, rd), ctx); + emit(rv_sw(RV_REG_T1, 0, rs), ctx); + break; + case BPF_STX | BPF_MEM | BPF_DW: + if (is_12b_int(off)) { + emit(rv_sd(rd, off, rs), ctx); + break; + } + + emit_imm(RV_REG_T1, off, ctx); + emit(rv_add(RV_REG_T1, RV_REG_T1, rd), ctx); + emit(rv_sd(RV_REG_T1, 0, rs), ctx); + break; + /* STX XADD: lock *(u32 *)(dst + off) += src */ + case BPF_STX | BPF_XADD | BPF_W: + /* STX XADD: lock *(u64 *)(dst + off) += src */ + case BPF_STX | BPF_XADD | BPF_DW: + if (off) { + if (is_12b_int(off)) { + emit(rv_addi(RV_REG_T1, rd, off), ctx); + } else { + emit_imm(RV_REG_T1, off, ctx); + emit(rv_add(RV_REG_T1, RV_REG_T1, rd), ctx); + } + + rd = RV_REG_T1; + } + + emit(BPF_SIZE(code) == BPF_W ? + rv_amoadd_w(RV_REG_ZERO, rs, rd, 0, 0) : + rv_amoadd_d(RV_REG_ZERO, rs, rd, 0, 0), ctx); + break; + default: + pr_err("bpf-jit: unknown opcode %02x\n", code); + return -EINVAL; + } + + return 0; +} + +static void build_prologue(struct rv_jit_context *ctx) +{ + int stack_adjust = 0, store_offset, bpf_stack_adjust; + + if (seen_reg(RV_REG_RA, ctx)) + stack_adjust += 8; + stack_adjust += 8; /* RV_REG_FP */ + if (seen_reg(RV_REG_S1, ctx)) + stack_adjust += 8; + if (seen_reg(RV_REG_S2, ctx)) + stack_adjust += 8; + if (seen_reg(RV_REG_S3, ctx)) + stack_adjust += 8; + if (seen_reg(RV_REG_S4, ctx)) + stack_adjust += 8; + if (seen_reg(RV_REG_S5, ctx)) + stack_adjust += 8; + if (seen_reg(RV_REG_S6, ctx)) + stack_adjust += 8; + + stack_adjust = round_up(stack_adjust, 16); + bpf_stack_adjust = round_up(ctx->prog->aux->stack_depth, 16); + stack_adjust += bpf_stack_adjust; + + store_offset = stack_adjust - 8; + + /* First instruction is always setting the tail-call-counter + * (TCC) register. This instruction is skipped for tail calls. + */ + emit(rv_addi(RV_REG_TCC, RV_REG_ZERO, MAX_TAIL_CALL_CNT), ctx); + + emit(rv_addi(RV_REG_SP, RV_REG_SP, -stack_adjust), ctx); + + if (seen_reg(RV_REG_RA, ctx)) { + emit(rv_sd(RV_REG_SP, store_offset, RV_REG_RA), ctx); + store_offset -= 8; + } + emit(rv_sd(RV_REG_SP, store_offset, RV_REG_FP), ctx); + store_offset -= 8; + if (seen_reg(RV_REG_S1, ctx)) { + emit(rv_sd(RV_REG_SP, store_offset, RV_REG_S1), ctx); + store_offset -= 8; + } + if (seen_reg(RV_REG_S2, ctx)) { + emit(rv_sd(RV_REG_SP, store_offset, RV_REG_S2), ctx); + store_offset -= 8; + } + if (seen_reg(RV_REG_S3, ctx)) { + emit(rv_sd(RV_REG_SP, store_offset, RV_REG_S3), ctx); + store_offset -= 8; + } + if (seen_reg(RV_REG_S4, ctx)) { + emit(rv_sd(RV_REG_SP, store_offset, RV_REG_S4), ctx); + store_offset -= 8; + } + if (seen_reg(RV_REG_S5, ctx)) { + emit(rv_sd(RV_REG_SP, store_offset, RV_REG_S5), ctx); + store_offset -= 8; + } + if (seen_reg(RV_REG_S6, ctx)) { + emit(rv_sd(RV_REG_SP, store_offset, RV_REG_S6), ctx); + store_offset -= 8; + } + + emit(rv_addi(RV_REG_FP, RV_REG_SP, stack_adjust), ctx); + + if (bpf_stack_adjust) + emit(rv_addi(RV_REG_S5, RV_REG_SP, bpf_stack_adjust), ctx); + + /* Program contains calls and tail calls, so RV_REG_TCC need + * to be saved across calls. + */ + if (seen_tail_call(ctx) && seen_call(ctx)) + emit(rv_addi(RV_REG_TCC_SAVED, RV_REG_TCC, 0), ctx); + + ctx->stack_size = stack_adjust; +} + +static void build_epilogue(struct rv_jit_context *ctx) +{ + __build_epilogue(RV_REG_RA, ctx); +} + +static int build_body(struct rv_jit_context *ctx, bool extra_pass) +{ + const struct bpf_prog *prog = ctx->prog; + int i; + + for (i = 0; i < prog->len; i++) { + const struct bpf_insn *insn = &prog->insnsi[i]; + int ret; + + ret = emit_insn(insn, ctx, extra_pass); + if (ret > 0) { + i++; + if (ctx->insns == NULL) + ctx->offset[i] = ctx->ninsns; + continue; + } + if (ctx->insns == NULL) + ctx->offset[i] = ctx->ninsns; + if (ret) + return ret; + } + return 0; +} + +static void bpf_fill_ill_insns(void *area, unsigned int size) +{ + memset(area, 0, size); +} + +static void bpf_flush_icache(void *start, void *end) +{ + flush_icache_range((unsigned long)start, (unsigned long)end); +} + +struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) +{ + bool tmp_blinded = false, extra_pass = false; + struct bpf_prog *tmp, *orig_prog = prog; + struct rv_jit_data *jit_data; + struct rv_jit_context *ctx; + unsigned int image_size; + + if (!prog->jit_requested) + return orig_prog; + + tmp = bpf_jit_blind_constants(prog); + if (IS_ERR(tmp)) + return orig_prog; + if (tmp != prog) { + tmp_blinded = true; + prog = tmp; + } + + jit_data = prog->aux->jit_data; + if (!jit_data) { + jit_data = kzalloc(sizeof(*jit_data), GFP_KERNEL); + if (!jit_data) { + prog = orig_prog; + goto out; + } + prog->aux->jit_data = jit_data; + } + + ctx = &jit_data->ctx; + + if (ctx->offset) { + extra_pass = true; + image_size = sizeof(u32) * ctx->ninsns; + goto skip_init_ctx; + } + + ctx->prog = prog; + ctx->offset = kcalloc(prog->len, sizeof(int), GFP_KERNEL); + if (!ctx->offset) { + prog = orig_prog; + goto out_offset; + } + + /* First pass generates the ctx->offset, but does not emit an image. */ + if (build_body(ctx, extra_pass)) { + prog = orig_prog; + goto out_offset; + } + build_prologue(ctx); + ctx->epilogue_offset = ctx->ninsns; + build_epilogue(ctx); + + /* Allocate image, now that we know the size. */ + image_size = sizeof(u32) * ctx->ninsns; + jit_data->header = bpf_jit_binary_alloc(image_size, &jit_data->image, + sizeof(u32), + bpf_fill_ill_insns); + if (!jit_data->header) { + prog = orig_prog; + goto out_offset; + } + + /* Second, real pass, that acutally emits the image. */ + ctx->insns = (u32 *)jit_data->image; +skip_init_ctx: + ctx->ninsns = 0; + + build_prologue(ctx); + if (build_body(ctx, extra_pass)) { + bpf_jit_binary_free(jit_data->header); + prog = orig_prog; + goto out_offset; + } + build_epilogue(ctx); + + if (bpf_jit_enable > 1) + bpf_jit_dump(prog->len, image_size, 2, ctx->insns); + + prog->bpf_func = (void *)ctx->insns; + prog->jited = 1; + prog->jited_len = image_size; + + bpf_flush_icache(jit_data->header, ctx->insns + ctx->ninsns); + + if (!prog->is_func || extra_pass) { +out_offset: + kfree(ctx->offset); + kfree(jit_data); + prog->aux->jit_data = NULL; + } +out: + if (tmp_blinded) + bpf_jit_prog_release_other(prog, prog == orig_prog ? + tmp : orig_prog); + return prog; +} diff --git a/arch/s390/include/asm/pnet.h b/arch/s390/include/asm/pnet.h index 6e278584f8f1..5739276b458d 100644 --- a/arch/s390/include/asm/pnet.h +++ b/arch/s390/include/asm/pnet.h @@ -11,13 +11,5 @@ #include <linux/device.h> #include <linux/types.h> -#define PNETIDS_LEN 64 /* Total utility string length in bytes - * to cover up to 4 PNETIDs of 16 bytes - * for up to 4 device ports - */ -#define MAX_PNETID_LEN 16 /* Max.length of a single port PNETID */ -#define MAX_PNETID_PORTS (PNETIDS_LEN / MAX_PNETID_LEN) - /* Max. # of ports with a PNETID */ - int pnet_id_by_dev_port(struct device *dev, unsigned short port, u8 *pnetid); #endif /* _ASM_S390_PNET_H */ diff --git a/arch/s390/include/uapi/asm/Kbuild b/arch/s390/include/uapi/asm/Kbuild index da3e0d48abbc..6b0f30b14642 100644 --- a/arch/s390/include/uapi/asm/Kbuild +++ b/arch/s390/include/uapi/asm/Kbuild @@ -3,3 +3,4 @@ include include/uapi/asm-generic/Kbuild.asm generated-y += unistd_32.h generated-y += unistd_64.h +generic-y += socket.h diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h deleted file mode 100644 index 49c971587087..000000000000 --- a/arch/s390/include/uapi/asm/socket.h +++ /dev/null @@ -1,119 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* - * S390 version - * - * Derived from "include/asm-i386/socket.h" - */ - -#ifndef _ASM_SOCKET_H -#define _ASM_SOCKET_H - -#include <asm/sockios.h> - -/* For setsockopt(2) */ -#define SOL_SOCKET 1 - -#define SO_DEBUG 1 -#define SO_REUSEADDR 2 -#define SO_TYPE 3 -#define SO_ERROR 4 -#define SO_DONTROUTE 5 -#define SO_BROADCAST 6 -#define SO_SNDBUF 7 -#define SO_RCVBUF 8 -#define SO_SNDBUFFORCE 32 -#define SO_RCVBUFFORCE 33 -#define SO_KEEPALIVE 9 -#define SO_OOBINLINE 10 -#define SO_NO_CHECK 11 -#define SO_PRIORITY 12 -#define SO_LINGER 13 -#define SO_BSDCOMPAT 14 -#define SO_REUSEPORT 15 -#define SO_PASSCRED 16 -#define SO_PEERCRED 17 -#define SO_RCVLOWAT 18 -#define SO_SNDLOWAT 19 -#define SO_RCVTIMEO 20 -#define SO_SNDTIMEO 21 - -/* Security levels - as per NRL IPv6 - don't actually do anything */ -#define SO_SECURITY_AUTHENTICATION 22 -#define SO_SECURITY_ENCRYPTION_TRANSPORT 23 -#define SO_SECURITY_ENCRYPTION_NETWORK 24 - -#define SO_BINDTODEVICE 25 - -/* Socket filtering */ -#define SO_ATTACH_FILTER 26 -#define SO_DETACH_FILTER 27 -#define SO_GET_FILTER SO_ATTACH_FILTER - -#define SO_PEERNAME 28 -#define SO_TIMESTAMP 29 -#define SCM_TIMESTAMP SO_TIMESTAMP - -#define SO_ACCEPTCONN 30 - -#define SO_PEERSEC 31 -#define SO_PASSSEC 34 -#define SO_TIMESTAMPNS 35 -#define SCM_TIMESTAMPNS SO_TIMESTAMPNS - -#define SO_MARK 36 - -#define SO_TIMESTAMPING 37 -#define SCM_TIMESTAMPING SO_TIMESTAMPING - -#define SO_PROTOCOL 38 -#define SO_DOMAIN 39 - -#define SO_RXQ_OVFL 40 - -#define SO_WIFI_STATUS 41 -#define SCM_WIFI_STATUS SO_WIFI_STATUS -#define SO_PEEK_OFF 42 - -/* Instruct lower device to use last 4-bytes of skb data as FCS */ -#define SO_NOFCS 43 - -#define SO_LOCK_FILTER 44 - -#define SO_SELECT_ERR_QUEUE 45 - -#define SO_BUSY_POLL 46 - -#define SO_MAX_PACING_RATE 47 - -#define SO_BPF_EXTENSIONS 48 - -#define SO_INCOMING_CPU 49 - -#define SO_ATTACH_BPF 50 -#define SO_DETACH_BPF SO_DETACH_FILTER - -#define SO_ATTACH_REUSEPORT_CBPF 51 -#define SO_ATTACH_REUSEPORT_EBPF 52 - -#define SO_CNX_ADVICE 53 - -#define SCM_TIMESTAMPING_OPT_STATS 54 - -#define SO_MEMINFO 55 - -#define SO_INCOMING_NAPI_ID 56 - -#define SO_COOKIE 57 - -#define SCM_TIMESTAMPING_PKTINFO 58 - -#define SO_PEERGROUPS 59 - -#define SO_ZEROCOPY 60 - -#define SO_TXTIME 61 -#define SCM_TXTIME SO_TXTIME - -#define SO_BINDTOIFINDEX 62 - -#endif /* _ASM_SOCKET_H */ diff --git a/arch/s390/kernel/swsusp.S b/arch/s390/kernel/swsusp.S index 537f97fde37f..b6796e616812 100644 --- a/arch/s390/kernel/swsusp.S +++ b/arch/s390/kernel/swsusp.S @@ -30,10 +30,10 @@ .section .text ENTRY(swsusp_arch_suspend) lg %r1,__LC_NODAT_STACK - aghi %r1,-STACK_FRAME_OVERHEAD stmg %r6,%r15,__SF_GPRS(%r1) + aghi %r1,-STACK_FRAME_OVERHEAD stg %r15,__SF_BACKCHAIN(%r1) - lgr %r1,%r15 + lgr %r15,%r1 /* Store FPU registers */ brasl %r14,save_fpu_regs diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index ce9defdff62a..51dd0267d014 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -1154,7 +1154,7 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i mask = 0x7000; /* jnz */ if (BPF_CLASS(insn->code) == BPF_JMP32) { /* llilf %w1,imm (load zero extend imm) */ - EMIT6_IMM(0xc0010000, REG_W1, imm); + EMIT6_IMM(0xc00f0000, REG_W1, imm); /* nr %w1,%dst */ EMIT2(0x1400, REG_W1, dst_reg); } else { @@ -1216,6 +1216,7 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i REG_W1, dst_reg, src_reg); goto branch_oc; branch_ks: + is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32; /* lgfi %w1,imm (load sign extend imm) */ EMIT6_IMM(0xc0010000, REG_W1, imm); /* crj or cgrj %dst,%w1,mask,off */ @@ -1223,6 +1224,7 @@ branch_ks: dst_reg, REG_W1, i, off, mask); break; branch_ku: + is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32; /* lgfi %w1,imm (load sign extend imm) */ EMIT6_IMM(0xc0010000, REG_W1, imm); /* clrj or clgrj %dst,%w1,mask,off */ @@ -1230,11 +1232,13 @@ branch_ku: dst_reg, REG_W1, i, off, mask); break; branch_xs: + is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32; /* crj or cgrj %dst,%src,mask,off */ EMIT6_PCREL(0xec000000, (is_jmp32 ? 0x0076 : 0x0064), dst_reg, src_reg, i, off, mask); break; branch_xu: + is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32; /* clrj or clgrj %dst,%src,mask,off */ EMIT6_PCREL(0xec000000, (is_jmp32 ? 0x0077 : 0x0065), dst_reg, src_reg, i, off, mask); diff --git a/arch/s390/net/pnet.c b/arch/s390/net/pnet.c index e22f1b10a6c7..9ecdbdf59781 100644 --- a/arch/s390/net/pnet.c +++ b/arch/s390/net/pnet.c @@ -13,6 +13,14 @@ #include <asm/ccwdev.h> #include <asm/pnet.h> +#define PNETIDS_LEN 64 /* Total utility string length in bytes + * to cover up to 4 PNETIDs of 16 bytes + * for up to 4 device ports + */ +#define MAX_PNETID_LEN 16 /* Max.length of a single port PNETID */ +#define MAX_PNETID_PORTS (PNETIDS_LEN / MAX_PNETID_LEN) + /* Max. # of ports with a PNETID */ + /* * Get the PNETIDs from a device. * s390 hardware supports the definition of a so-called Physical Network diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index a966d7bfac57..4266a4de3160 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -382,7 +382,9 @@ static void zpci_irq_handler(struct airq_struct *airq) if (ai == -1UL) break; inc_irq_stat(IRQIO_MSI); + airq_iv_lock(aibv, ai); generic_handle_irq(airq_iv_get_data(aibv, ai)); + airq_iv_unlock(aibv, ai); } } } @@ -408,7 +410,7 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) zdev->aisb = aisb; /* Create adapter interrupt vector */ - zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA); + zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA | AIRQ_IV_BITLOCK); if (!zdev->aibv) return -ENOMEM; diff --git a/arch/sparc/include/uapi/asm/posix_types.h b/arch/sparc/include/uapi/asm/posix_types.h index fec499d6efb7..f139e0048628 100644 --- a/arch/sparc/include/uapi/asm/posix_types.h +++ b/arch/sparc/include/uapi/asm/posix_types.h @@ -19,6 +19,16 @@ typedef unsigned short __kernel_old_gid_t; typedef int __kernel_suseconds_t; #define __kernel_suseconds_t __kernel_suseconds_t +typedef long __kernel_long_t; +typedef unsigned long __kernel_ulong_t; +#define __kernel_long_t __kernel_long_t + +struct __kernel_old_timeval { + __kernel_long_t tv_sec; + __kernel_suseconds_t tv_usec; +}; +#define __kernel_old_timeval __kernel_old_timeval + #else /* sparc 32 bit */ diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index bbdb81594dd4..88fe4f978aca 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -3,6 +3,7 @@ #define _ASM_SOCKET_H #include <asm/sockios.h> +#include <asm/bitsperlong.h> /* For setsockopt(2) */ #define SOL_SOCKET 0xffff @@ -20,8 +21,8 @@ #define SO_BSDCOMPAT 0x0400 #define SO_RCVLOWAT 0x0800 #define SO_SNDLOWAT 0x1000 -#define SO_RCVTIMEO 0x2000 -#define SO_SNDTIMEO 0x4000 +#define SO_RCVTIMEO_OLD 0x2000 +#define SO_SNDTIMEO_OLD 0x4000 #define SO_ACCEPTCONN 0x8000 #define SO_SNDBUF 0x1001 @@ -33,7 +34,6 @@ #define SO_PROTOCOL 0x1028 #define SO_DOMAIN 0x1029 - /* Linux specific, keep the same. */ #define SO_NO_CHECK 0x000b #define SO_PRIORITY 0x000c @@ -45,19 +45,12 @@ #define SO_GET_FILTER SO_ATTACH_FILTER #define SO_PEERNAME 0x001c -#define SO_TIMESTAMP 0x001d -#define SCM_TIMESTAMP SO_TIMESTAMP #define SO_PEERSEC 0x001e #define SO_PASSSEC 0x001f -#define SO_TIMESTAMPNS 0x0021 -#define SCM_TIMESTAMPNS SO_TIMESTAMPNS #define SO_MARK 0x0022 -#define SO_TIMESTAMPING 0x0023 -#define SCM_TIMESTAMPING SO_TIMESTAMPING - #define SO_RXQ_OVFL 0x0024 #define SO_WIFI_STATUS 0x0025 @@ -111,4 +104,40 @@ #define SO_SECURITY_ENCRYPTION_TRANSPORT 0x5002 #define SO_SECURITY_ENCRYPTION_NETWORK 0x5004 +#define SO_TIMESTAMP_OLD 0x001d +#define SO_TIMESTAMPNS_OLD 0x0021 +#define SO_TIMESTAMPING_OLD 0x0023 + +#define SO_TIMESTAMP_NEW 0x0046 +#define SO_TIMESTAMPNS_NEW 0x0042 +#define SO_TIMESTAMPING_NEW 0x0043 + +#define SO_RCVTIMEO_NEW 0x0044 +#define SO_SNDTIMEO_NEW 0x0045 + +#if !defined(__KERNEL__) + + +#if __BITS_PER_LONG == 64 +#define SO_TIMESTAMP SO_TIMESTAMP_OLD +#define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD +#define SO_TIMESTAMPING SO_TIMESTAMPING_OLD + +#define SO_RCVTIMEO SO_RCVTIMEO_OLD +#define SO_SNDTIMEO SO_SNDTIMEO_OLD +#else +#define SO_TIMESTAMP (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMP_OLD : SO_TIMESTAMP_NEW) +#define SO_TIMESTAMPNS (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPNS_OLD : SO_TIMESTAMPNS_NEW) +#define SO_TIMESTAMPING (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPING_OLD : SO_TIMESTAMPING_NEW) + +#define SO_RCVTIMEO (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_RCVTIMEO_OLD : SO_RCVTIMEO_NEW) +#define SO_SNDTIMEO (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_SNDTIMEO_OLD : SO_SNDTIMEO_NEW) +#endif + +#define SCM_TIMESTAMP SO_TIMESTAMP +#define SCM_TIMESTAMPNS SO_TIMESTAMPNS +#define SCM_TIMESTAMPING SO_TIMESTAMPING + +#endif + #endif /* _ASM_SOCKET_H */ diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild index 1372553dc0a9..1d1544b6ca74 100644 --- a/arch/unicore32/include/asm/Kbuild +++ b/arch/unicore32/include/asm/Kbuild @@ -28,6 +28,7 @@ generic-y += preempt.h generic-y += sections.h generic-y += segment.h generic-y += serial.h +generic-y += shmparam.h generic-y += sizes.h generic-y += syscalls.h generic-y += topology.h diff --git a/arch/unicore32/include/uapi/asm/Kbuild b/arch/unicore32/include/uapi/asm/Kbuild index 6c6f6301012e..0febf1a07c30 100644 --- a/arch/unicore32/include/uapi/asm/Kbuild +++ b/arch/unicore32/include/uapi/asm/Kbuild @@ -1,5 +1,4 @@ include include/uapi/asm-generic/Kbuild.asm generic-y += kvm_para.h -generic-y += shmparam.h generic-y += ucontext.h diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 4b4a7f32b68e..68261430fe6e 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -198,7 +198,7 @@ config X86 select IRQ_FORCED_THREADING select NEED_SG_DMA_LENGTH select PCI_DOMAINS if PCI - select PCI_LOCKLESS_CONFIG + select PCI_LOCKLESS_CONFIG if PCI select PERF_EVENTS select RTC_LIB select RTC_MC146818_LIB @@ -446,12 +446,12 @@ config RETPOLINE branches. Requires a compiler with -mindirect-branch=thunk-extern support for full protection. The kernel may run slower. -config X86_RESCTRL - bool "Resource Control support" +config X86_CPU_RESCTRL + bool "x86 CPU resource control support" depends on X86 && (CPU_SUP_INTEL || CPU_SUP_AMD) select KERNFS help - Enable Resource Control support. + Enable x86 CPU resource control support. Provide support for the allocation and monitoring of system resources usage by the CPU. diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index 64037895b085..f62e347862cc 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -600,6 +600,16 @@ ENTRY(trampoline_32bit_src) leal TRAMPOLINE_32BIT_PGTABLE_OFFSET(%ecx), %eax movl %eax, %cr3 3: + /* Set EFER.LME=1 as a precaution in case hypervsior pulls the rug */ + pushl %ecx + pushl %edx + movl $MSR_EFER, %ecx + rdmsr + btsl $_EFER_LME, %eax + wrmsr + popl %edx + popl %ecx + /* Enable PAE and LA57 (if required) paging modes */ movl $X86_CR4_PAE, %eax cmpl $0, %edx diff --git a/arch/x86/boot/compressed/pgtable.h b/arch/x86/boot/compressed/pgtable.h index 91f75638f6e6..6ff7e81b5628 100644 --- a/arch/x86/boot/compressed/pgtable.h +++ b/arch/x86/boot/compressed/pgtable.h @@ -6,7 +6,7 @@ #define TRAMPOLINE_32BIT_PGTABLE_OFFSET 0 #define TRAMPOLINE_32BIT_CODE_OFFSET PAGE_SIZE -#define TRAMPOLINE_32BIT_CODE_SIZE 0x60 +#define TRAMPOLINE_32BIT_CODE_SIZE 0x70 #define TRAMPOLINE_32BIT_STACK_END TRAMPOLINE_32BIT_SIZE diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 8eaf8952c408..39913770a44d 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -361,7 +361,8 @@ ENTRY(entry_INT80_compat) /* Need to switch before accessing the thread stack. */ SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi - movq %rsp, %rdi + /* In the Xen PV case we already run on the thread stack. */ + ALTERNATIVE "movq %rsp, %rdi", "jmp .Lint80_keep_stack", X86_FEATURE_XENPV movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp pushq 6*8(%rdi) /* regs->ss */ @@ -370,8 +371,9 @@ ENTRY(entry_INT80_compat) pushq 3*8(%rdi) /* regs->cs */ pushq 2*8(%rdi) /* regs->ip */ pushq 1*8(%rdi) /* regs->orig_ax */ - pushq (%rdi) /* pt_regs->di */ +.Lint80_keep_stack: + pushq %rsi /* pt_regs->si */ xorl %esi, %esi /* nospec si */ pushq %rdx /* pt_regs->dx */ diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 40e12cfc87f6..daafb893449b 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3559,6 +3559,14 @@ static void free_excl_cntrs(int cpu) static void intel_pmu_cpu_dying(int cpu) { + fini_debug_store_on_cpu(cpu); + + if (x86_pmu.counter_freezing) + disable_counter_freeze(); +} + +static void intel_pmu_cpu_dead(int cpu) +{ struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); struct intel_shared_regs *pc; @@ -3570,11 +3578,6 @@ static void intel_pmu_cpu_dying(int cpu) } free_excl_cntrs(cpu); - - fini_debug_store_on_cpu(cpu); - - if (x86_pmu.counter_freezing) - disable_counter_freeze(); } static void intel_pmu_sched_task(struct perf_event_context *ctx, @@ -3663,6 +3666,7 @@ static __initconst const struct x86_pmu core_pmu = { .cpu_prepare = intel_pmu_cpu_prepare, .cpu_starting = intel_pmu_cpu_starting, .cpu_dying = intel_pmu_cpu_dying, + .cpu_dead = intel_pmu_cpu_dead, }; static struct attribute *intel_pmu_attrs[]; @@ -3703,6 +3707,8 @@ static __initconst const struct x86_pmu intel_pmu = { .cpu_prepare = intel_pmu_cpu_prepare, .cpu_starting = intel_pmu_cpu_starting, .cpu_dying = intel_pmu_cpu_dying, + .cpu_dead = intel_pmu_cpu_dead, + .guest_get_msrs = intel_guest_get_msrs, .sched_task = intel_pmu_sched_task, }; diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index c07bee31abe8..b10e04387f38 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -1222,6 +1222,8 @@ static struct pci_driver snbep_uncore_pci_driver = { .id_table = snbep_uncore_pci_ids, }; +#define NODE_ID_MASK 0x7 + /* * build pci bus to socket mapping */ @@ -1243,7 +1245,7 @@ static int snbep_pci2phy_map_init(int devid, int nodeid_loc, int idmap_loc, bool err = pci_read_config_dword(ubox_dev, nodeid_loc, &config); if (err) break; - nodeid = config; + nodeid = config & NODE_ID_MASK; /* get the Node ID mapping */ err = pci_read_config_dword(ubox_dev, idmap_loc, &config); if (err) diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 0dd6b0f4000e..d9a9993af882 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -6,7 +6,7 @@ * "Big Core" Processors (Branded as Core, Xeon, etc...) * * The "_X" parts are generally the EP and EX Xeons, or the - * "Extreme" ones, like Broadwell-E. + * "Extreme" ones, like Broadwell-E, or Atom microserver. * * While adding a new CPUID for a new microarchitecture, add a new * group to keep logically sorted out in chronological order. Within @@ -71,6 +71,7 @@ #define INTEL_FAM6_ATOM_GOLDMONT 0x5C /* Apollo Lake */ #define INTEL_FAM6_ATOM_GOLDMONT_X 0x5F /* Denverton */ #define INTEL_FAM6_ATOM_GOLDMONT_PLUS 0x7A /* Gemini Lake */ +#define INTEL_FAM6_ATOM_TREMONT_X 0x86 /* Jacobsville */ /* Xeon Phi */ diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h index 0ca50611e8ce..19d18fae6ec6 100644 --- a/arch/x86/include/asm/mmu_context.h +++ b/arch/x86/include/asm/mmu_context.h @@ -178,6 +178,10 @@ static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next) void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk); +/* + * Init a new mm. Used on mm copies, like at fork() + * and on mm's that are brand-new, like at execve(). + */ static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm) { @@ -228,8 +232,22 @@ do { \ } while (0) #endif +static inline void arch_dup_pkeys(struct mm_struct *oldmm, + struct mm_struct *mm) +{ +#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS + if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) + return; + + /* Duplicate the oldmm pkey state in mm: */ + mm->context.pkey_allocation_map = oldmm->context.pkey_allocation_map; + mm->context.execute_only_pkey = oldmm->context.execute_only_pkey; +#endif +} + static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) { + arch_dup_pkeys(oldmm, mm); paravirt_arch_dup_mmap(oldmm, mm); return ldt_dup_context(oldmm, mm); } diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index 8f657286d599..0ce558a8150d 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -7,7 +7,11 @@ #endif #ifdef CONFIG_KASAN +#ifdef CONFIG_KASAN_EXTRA +#define KASAN_STACK_ORDER 2 +#else #define KASAN_STACK_ORDER 1 +#endif #else #define KASAN_STACK_ORDER 0 #endif diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 40616e805292..2779ace16d23 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -1065,7 +1065,7 @@ static inline void native_set_pte_at(struct mm_struct *mm, unsigned long addr, static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd) { - native_set_pmd(pmdp, pmd); + set_pmd(pmdp, pmd); } static inline void set_pud_at(struct mm_struct *mm, unsigned long addr, diff --git a/arch/x86/include/asm/resctrl_sched.h b/arch/x86/include/asm/resctrl_sched.h index 40ebddde6ac2..f6b7fe2833cc 100644 --- a/arch/x86/include/asm/resctrl_sched.h +++ b/arch/x86/include/asm/resctrl_sched.h @@ -2,7 +2,7 @@ #ifndef _ASM_X86_RESCTRL_SCHED_H #define _ASM_X86_RESCTRL_SCHED_H -#ifdef CONFIG_X86_RESCTRL +#ifdef CONFIG_X86_CPU_RESCTRL #include <linux/sched.h> #include <linux/jump_label.h> @@ -88,6 +88,6 @@ static inline void resctrl_sched_in(void) static inline void resctrl_sched_in(void) {} -#endif /* CONFIG_X86_RESCTRL */ +#endif /* CONFIG_X86_CPU_RESCTRL */ #endif /* _ASM_X86_RESCTRL_SCHED_H */ diff --git a/arch/x86/include/uapi/asm/Kbuild b/arch/x86/include/uapi/asm/Kbuild index f6648e9928b3..efe701b7c6ce 100644 --- a/arch/x86/include/uapi/asm/Kbuild +++ b/arch/x86/include/uapi/asm/Kbuild @@ -3,3 +3,4 @@ include include/uapi/asm-generic/Kbuild.asm generated-y += unistd_32.h generated-y += unistd_64.h generated-y += unistd_x32.h +generic-y += socket.h diff --git a/arch/x86/include/uapi/asm/socket.h b/arch/x86/include/uapi/asm/socket.h deleted file mode 100644 index 6b71384b9d8b..000000000000 --- a/arch/x86/include/uapi/asm/socket.h +++ /dev/null @@ -1 +0,0 @@ -#include <asm-generic/socket.h> diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index b6fa0869f7aa..cfd24f9f7614 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -39,7 +39,7 @@ obj-$(CONFIG_CPU_SUP_UMC_32) += umc.o obj-$(CONFIG_X86_MCE) += mce/ obj-$(CONFIG_MTRR) += mtrr/ obj-$(CONFIG_MICROCODE) += microcode/ -obj-$(CONFIG_X86_RESCTRL) += resctrl/ +obj-$(CONFIG_X86_CPU_RESCTRL) += resctrl/ obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 1de0f4170178..01874d54f4fd 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -71,7 +71,7 @@ void __init check_bugs(void) * identify_boot_cpu() initialized SMT support information, let the * core code know. */ - cpu_smt_check_topology_early(); + cpu_smt_check_topology(); if (!IS_ENABLED(CONFIG_SMP)) { pr_info("CPU: "); diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 672c7225cb1b..6ce290c506d9 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -784,6 +784,7 @@ static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, quirk_no_way_out(i, m, regs); if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) { + m->bank = i; mce_read_aux(m, i); *msg = tmp; return 1; diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 51adde0a0f1a..e1f3ba19ba54 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -855,7 +855,7 @@ load_microcode_amd(bool save, u8 family, const u8 *data, size_t size) if (!p) { return ret; } else { - if (boot_cpu_data.microcode == p->patch_id) + if (boot_cpu_data.microcode >= p->patch_id) return ret; ret = UCODE_NEW; diff --git a/arch/x86/kernel/cpu/resctrl/Makefile b/arch/x86/kernel/cpu/resctrl/Makefile index 1cabe6fd8e11..4a06c37b9cf1 100644 --- a/arch/x86/kernel/cpu/resctrl/Makefile +++ b/arch/x86/kernel/cpu/resctrl/Makefile @@ -1,4 +1,4 @@ # SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_X86_RESCTRL) += core.o rdtgroup.o monitor.o -obj-$(CONFIG_X86_RESCTRL) += ctrlmondata.o pseudo_lock.o +obj-$(CONFIG_X86_CPU_RESCTRL) += core.o rdtgroup.o monitor.o +obj-$(CONFIG_X86_CPU_RESCTRL) += ctrlmondata.o pseudo_lock.o CFLAGS_pseudo_lock.o = -I$(src) diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index c8b07d8ea5a2..17ffc869cab8 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -470,6 +470,7 @@ int crash_load_segments(struct kimage *image) kbuf.memsz = kbuf.bufsz; kbuf.buf_align = ELF_CORE_HEADER_ALIGN; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; ret = kexec_add_buffer(&kbuf); if (ret) { vfree((void *)image->arch.elf_headers); diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index b0acb22e5a46..dfd3aca82c61 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -21,10 +21,6 @@ #define HPET_MASK CLOCKSOURCE_MASK(32) -/* FSEC = 10^-15 - NSEC = 10^-9 */ -#define FSEC_PER_NSEC 1000000L - #define HPET_DEV_USED_BIT 2 #define HPET_DEV_USED (1 << HPET_DEV_USED_BIT) #define HPET_DEV_VALID 0x8 diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index 278cd07228dd..53917a3ebf94 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -167,6 +167,9 @@ setup_efi_state(struct boot_params *params, unsigned long params_load_addr, struct efi_info *current_ei = &boot_params.efi_info; struct efi_info *ei = ¶ms->efi_info; + if (!efi_enabled(EFI_RUNTIME_SERVICES)) + return 0; + if (!current_ei->efi_memmap_size) return 0; @@ -434,6 +437,7 @@ static void *bzImage64_load(struct kimage *image, char *kernel, kbuf.memsz = PAGE_ALIGN(header->init_size); kbuf.buf_align = header->kernel_alignment; kbuf.buf_min = MIN_KERNEL_LOAD_ADDR; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; ret = kexec_add_buffer(&kbuf); if (ret) goto out_free_params; @@ -448,6 +452,7 @@ static void *bzImage64_load(struct kimage *image, char *kernel, kbuf.bufsz = kbuf.memsz = initrd_len; kbuf.buf_align = PAGE_SIZE; kbuf.buf_min = MIN_INITRD_LOAD_ADDR; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; ret = kexec_add_buffer(&kbuf); if (ret) goto out_free_params; diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index e9f777bfed40..3fae23834069 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -297,15 +297,16 @@ static int __init tsc_setup(char *str) __setup("tsc=", tsc_setup); -#define MAX_RETRIES 5 -#define SMI_TRESHOLD 50000 +#define MAX_RETRIES 5 +#define TSC_DEFAULT_THRESHOLD 0x20000 /* - * Read TSC and the reference counters. Take care of SMI disturbance + * Read TSC and the reference counters. Take care of any disturbances */ static u64 tsc_read_refs(u64 *p, int hpet) { u64 t1, t2; + u64 thresh = tsc_khz ? tsc_khz >> 5 : TSC_DEFAULT_THRESHOLD; int i; for (i = 0; i < MAX_RETRIES; i++) { @@ -315,7 +316,7 @@ static u64 tsc_read_refs(u64 *p, int hpet) else *p = acpi_pm_read_early(); t2 = get_cycles(); - if ((t2 - t1) < SMI_TRESHOLD) + if ((t2 - t1) < thresh) return t2; } return ULLONG_MAX; @@ -703,15 +704,15 @@ static unsigned long pit_hpet_ptimer_calibrate_cpu(void) * zero. In each wait loop iteration we read the TSC and check * the delta to the previous read. We keep track of the min * and max values of that delta. The delta is mostly defined - * by the IO time of the PIT access, so we can detect when a - * SMI/SMM disturbance happened between the two reads. If the + * by the IO time of the PIT access, so we can detect when + * any disturbance happened between the two reads. If the * maximum time is significantly larger than the minimum time, * then we discard the result and have another try. * * 2) Reference counter. If available we use the HPET or the * PMTIMER as a reference to check the sanity of that value. * We use separate TSC readouts and check inside of the - * reference read for a SMI/SMM disturbance. We dicard + * reference read for any possible disturbance. We dicard * disturbed values here as well. We do that around the PIT * calibration delay loop as we have to wait for a certain * amount of time anyway. @@ -744,7 +745,7 @@ static unsigned long pit_hpet_ptimer_calibrate_cpu(void) if (ref1 == ref2) continue; - /* Check, whether the sampling was disturbed by an SMI */ + /* Check, whether the sampling was disturbed */ if (tsc1 == ULLONG_MAX || tsc2 == ULLONG_MAX) continue; @@ -1268,7 +1269,7 @@ static DECLARE_DELAYED_WORK(tsc_irqwork, tsc_refine_calibration_work); */ static void tsc_refine_calibration_work(struct work_struct *work) { - static u64 tsc_start = -1, ref_start; + static u64 tsc_start = ULLONG_MAX, ref_start; static int hpet; u64 tsc_stop, ref_stop, delta; unsigned long freq; @@ -1283,14 +1284,15 @@ static void tsc_refine_calibration_work(struct work_struct *work) * delayed the first time we expire. So set the workqueue * again once we know timers are working. */ - if (tsc_start == -1) { + if (tsc_start == ULLONG_MAX) { +restart: /* * Only set hpet once, to avoid mixing hardware * if the hpet becomes enabled later. */ hpet = is_hpet_enabled(); - schedule_delayed_work(&tsc_irqwork, HZ); tsc_start = tsc_read_refs(&ref_start, hpet); + schedule_delayed_work(&tsc_irqwork, HZ); return; } @@ -1300,9 +1302,9 @@ static void tsc_refine_calibration_work(struct work_struct *work) if (ref_start == ref_stop) goto out; - /* Check, whether the sampling was disturbed by an SMI */ - if (tsc_start == ULLONG_MAX || tsc_stop == ULLONG_MAX) - goto out; + /* Check, whether the sampling was disturbed */ + if (tsc_stop == ULLONG_MAX) + goto restart; delta = tsc_stop - tsc_start; delta *= 1000000LL; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 8ff20523661b..d8ea4ebd79e7 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -211,6 +211,7 @@ static void free_nested(struct kvm_vcpu *vcpu) if (!vmx->nested.vmxon && !vmx->nested.smm.vmxon) return; + hrtimer_cancel(&vmx->nested.preemption_timer); vmx->nested.vmxon = false; vmx->nested.smm.vmxon = false; free_vpid(vmx->nested.vpid02); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 4341175339f3..95d618045001 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -26,6 +26,7 @@ #include <linux/mod_devicetable.h> #include <linux/mm.h> #include <linux/sched.h> +#include <linux/sched/smt.h> #include <linux/slab.h> #include <linux/tboot.h> #include <linux/trace_events.h> @@ -6823,7 +6824,7 @@ static int vmx_vm_init(struct kvm *kvm) * Warn upon starting the first VM in a potentially * insecure environment. */ - if (cpu_smt_control == CPU_SMT_ENABLED) + if (sched_smt_active()) pr_warn_once(L1TF_MSG_SMT); if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_NEVER) pr_warn_once(L1TF_MSG_L1D); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 3d27206f6c01..e67ecf25e690 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5116,6 +5116,13 @@ int kvm_read_guest_virt(struct kvm_vcpu *vcpu, { u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + /* + * FIXME: this should call handle_emulation_failure if X86EMUL_IO_NEEDED + * is returned, but our callers are not ready for that and they blindly + * call kvm_inject_page_fault. Ensure that they at least do not leak + * uninitialized kernel stack memory into cr2 and error code. + */ + memset(exception, 0, sizeof(*exception)); return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access, exception); } diff --git a/arch/x86/lib/iomem.c b/arch/x86/lib/iomem.c index 66894675f3c8..df50451d94ef 100644 --- a/arch/x86/lib/iomem.c +++ b/arch/x86/lib/iomem.c @@ -2,8 +2,11 @@ #include <linux/module.h> #include <linux/io.h> +#define movs(type,to,from) \ + asm volatile("movs" type:"=&D" (to), "=&S" (from):"0" (to), "1" (from):"memory") + /* Originally from i386/string.h */ -static __always_inline void __iomem_memcpy(void *to, const void *from, size_t n) +static __always_inline void rep_movs(void *to, const void *from, size_t n) { unsigned long d0, d1, d2; asm volatile("rep ; movsl\n\t" @@ -21,13 +24,37 @@ static __always_inline void __iomem_memcpy(void *to, const void *from, size_t n) void memcpy_fromio(void *to, const volatile void __iomem *from, size_t n) { - __iomem_memcpy(to, (const void *)from, n); + if (unlikely(!n)) + return; + + /* Align any unaligned source IO */ + if (unlikely(1 & (unsigned long)from)) { + movs("b", to, from); + n--; + } + if (n > 1 && unlikely(2 & (unsigned long)from)) { + movs("w", to, from); + n-=2; + } + rep_movs(to, (const void *)from, n); } EXPORT_SYMBOL(memcpy_fromio); void memcpy_toio(volatile void __iomem *to, const void *from, size_t n) { - __iomem_memcpy((void *)to, (const void *) from, n); + if (unlikely(!n)) + return; + + /* Align any unaligned destination IO */ + if (unlikely(1 & (unsigned long)to)) { + movs("b", to, from); + n--; + } + if (n > 1 && unlikely(2 & (unsigned long)to)) { + movs("w", to, from); + n-=2; + } + rep_movs((void *)to, (const void *) from, n); } EXPORT_SYMBOL(memcpy_toio); diff --git a/arch/x86/lib/kaslr.c b/arch/x86/lib/kaslr.c index 79778ab200e4..a53665116458 100644 --- a/arch/x86/lib/kaslr.c +++ b/arch/x86/lib/kaslr.c @@ -36,8 +36,8 @@ static inline u16 i8254(void) u16 status, timer; do { - outb(I8254_PORT_CONTROL, - I8254_CMD_READBACK | I8254_SELECT_COUNTER0); + outb(I8254_CMD_READBACK | I8254_SELECT_COUNTER0, + I8254_PORT_CONTROL); status = inb(I8254_PORT_COUNTER0); timer = inb(I8254_PORT_COUNTER0); timer |= inb(I8254_PORT_COUNTER0) << 8; diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 2ff25ad33233..9d5c75f02295 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -595,7 +595,7 @@ static void show_ldttss(const struct desc_ptr *gdt, const char *name, u16 index) return; } - addr = desc.base0 | (desc.base1 << 16) | (desc.base2 << 24); + addr = desc.base0 | (desc.base1 << 16) | ((unsigned long)desc.base2 << 24); #ifdef CONFIG_X86_64 addr |= ((u64)desc.base3 << 32); #endif diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c index a19ef1a416ff..4aa9b1480866 100644 --- a/arch/x86/mm/mem_encrypt_identity.c +++ b/arch/x86/mm/mem_encrypt_identity.c @@ -158,8 +158,8 @@ static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd) pmd = pmd_offset(pud, ppd->vaddr); if (pmd_none(*pmd)) { pte = ppd->pgtable_area; - memset(pte, 0, sizeof(pte) * PTRS_PER_PTE); - ppd->pgtable_area += sizeof(pte) * PTRS_PER_PTE; + memset(pte, 0, sizeof(*pte) * PTRS_PER_PTE); + ppd->pgtable_area += sizeof(*pte) * PTRS_PER_PTE; set_pmd(pmd, __pmd(PMD_FLAGS | __pa(pte))); } diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 4f8972311a77..14e6119838a6 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -230,6 +230,29 @@ static bool __cpa_pfn_in_highmap(unsigned long pfn) #endif +/* + * See set_mce_nospec(). + * + * Machine check recovery code needs to change cache mode of poisoned pages to + * UC to avoid speculative access logging another error. But passing the + * address of the 1:1 mapping to set_memory_uc() is a fine way to encourage a + * speculative access. So we cheat and flip the top bit of the address. This + * works fine for the code that updates the page tables. But at the end of the + * process we need to flush the TLB and cache and the non-canonical address + * causes a #GP fault when used by the INVLPG and CLFLUSH instructions. + * + * But in the common case we already have a canonical address. This code + * will fix the top bit if needed and is a no-op otherwise. + */ +static inline unsigned long fix_addr(unsigned long addr) +{ +#ifdef CONFIG_X86_64 + return (long)(addr << 1) >> 1; +#else + return addr; +#endif +} + static unsigned long __cpa_addr(struct cpa_data *cpa, unsigned long idx) { if (cpa->flags & CPA_PAGES_ARRAY) { @@ -313,7 +336,7 @@ void __cpa_flush_tlb(void *data) unsigned int i; for (i = 0; i < cpa->numpages; i++) - __flush_tlb_one_kernel(__cpa_addr(cpa, i)); + __flush_tlb_one_kernel(fix_addr(__cpa_addr(cpa, i))); } static void cpa_flush(struct cpa_data *data, int cache) @@ -347,7 +370,7 @@ static void cpa_flush(struct cpa_data *data, int cache) * Only flush present addresses: */ if (pte && (pte_val(*pte) & _PAGE_PRESENT)) - clflush_cache_range_opt((void *)addr, PAGE_SIZE); + clflush_cache_range_opt((void *)fix_addr(addr), PAGE_SIZE); } mb(); } @@ -1627,29 +1650,6 @@ out: return ret; } -/* - * Machine check recovery code needs to change cache mode of poisoned - * pages to UC to avoid speculative access logging another error. But - * passing the address of the 1:1 mapping to set_memory_uc() is a fine - * way to encourage a speculative access. So we cheat and flip the top - * bit of the address. This works fine for the code that updates the - * page tables. But at the end of the process we need to flush the cache - * and the non-canonical address causes a #GP fault when used by the - * CLFLUSH instruction. - * - * But in the common case we already have a canonical address. This code - * will fix the top bit if needed and is a no-op otherwise. - */ -static inline unsigned long make_addr_canonical_again(unsigned long addr) -{ -#ifdef CONFIG_X86_64 - return (long)(addr << 1) >> 1; -#else - return addr; -#endif -} - - static int change_page_attr_set_clr(unsigned long *addr, int numpages, pgprot_t mask_set, pgprot_t mask_clr, int force_split, int in_flag, diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index 20a0756f27ef..ce91682770cb 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -164,7 +164,7 @@ config XTENSA_FAKE_NMI If unsure, say N. config XTENSA_UNALIGNED_USER - bool "Unaligned memory access in use space" + bool "Unaligned memory access in user space" help The Xtensa architecture currently does not handle unaligned memory accesses in hardware but through an exception handler. @@ -451,7 +451,7 @@ config USE_OF help Include support for flattened device tree machine descriptions. -config BUILTIN_DTB +config BUILTIN_DTB_SOURCE string "DTB to build into the kernel image" depends on OF diff --git a/arch/xtensa/boot/dts/Makefile b/arch/xtensa/boot/dts/Makefile index f8052ba5aea8..0b8d00cdae7c 100644 --- a/arch/xtensa/boot/dts/Makefile +++ b/arch/xtensa/boot/dts/Makefile @@ -7,9 +7,9 @@ # # -BUILTIN_DTB := $(patsubst "%",%,$(CONFIG_BUILTIN_DTB)).dtb.o -ifneq ($(CONFIG_BUILTIN_DTB),"") -obj-$(CONFIG_OF) += $(BUILTIN_DTB) +BUILTIN_DTB_SOURCE := $(patsubst "%",%,$(CONFIG_BUILTIN_DTB_SOURCE)).dtb.o +ifneq ($(CONFIG_BUILTIN_DTB_SOURCE),"") +obj-$(CONFIG_OF) += $(BUILTIN_DTB_SOURCE) endif # for CONFIG_OF_ALL_DTBS test diff --git a/arch/xtensa/configs/audio_kc705_defconfig b/arch/xtensa/configs/audio_kc705_defconfig index 2bf964df37ba..f378e56f9ce6 100644 --- a/arch/xtensa/configs/audio_kc705_defconfig +++ b/arch/xtensa/configs/audio_kc705_defconfig @@ -34,7 +34,7 @@ CONFIG_XTENSA_PLATFORM_XTFPGA=y CONFIG_CMDLINE_BOOL=y CONFIG_CMDLINE="earlycon=uart8250,mmio32native,0xfd050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=0x38000000@0" CONFIG_USE_OF=y -CONFIG_BUILTIN_DTB="kc705" +CONFIG_BUILTIN_DTB_SOURCE="kc705" # CONFIG_COMPACTION is not set # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_PM=y diff --git a/arch/xtensa/configs/cadence_csp_defconfig b/arch/xtensa/configs/cadence_csp_defconfig index 3221b7053fa3..62f32a902568 100644 --- a/arch/xtensa/configs/cadence_csp_defconfig +++ b/arch/xtensa/configs/cadence_csp_defconfig @@ -38,7 +38,7 @@ CONFIG_HIGHMEM=y # CONFIG_PCI is not set CONFIG_XTENSA_PLATFORM_XTFPGA=y CONFIG_USE_OF=y -CONFIG_BUILTIN_DTB="csp" +CONFIG_BUILTIN_DTB_SOURCE="csp" # CONFIG_COMPACTION is not set CONFIG_XTFPGA_LCD=y # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set diff --git a/arch/xtensa/configs/generic_kc705_defconfig b/arch/xtensa/configs/generic_kc705_defconfig index 985fa8546e4e..8bebe07f1060 100644 --- a/arch/xtensa/configs/generic_kc705_defconfig +++ b/arch/xtensa/configs/generic_kc705_defconfig @@ -33,7 +33,7 @@ CONFIG_XTENSA_PLATFORM_XTFPGA=y CONFIG_CMDLINE_BOOL=y CONFIG_CMDLINE="earlycon=uart8250,mmio32native,0xfd050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=0x38000000@0" CONFIG_USE_OF=y -CONFIG_BUILTIN_DTB="kc705" +CONFIG_BUILTIN_DTB_SOURCE="kc705" # CONFIG_COMPACTION is not set # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_NET=y diff --git a/arch/xtensa/configs/nommu_kc705_defconfig b/arch/xtensa/configs/nommu_kc705_defconfig index f3fc4f970ca8..933ab2adf434 100644 --- a/arch/xtensa/configs/nommu_kc705_defconfig +++ b/arch/xtensa/configs/nommu_kc705_defconfig @@ -39,7 +39,7 @@ CONFIG_XTENSA_PLATFORM_XTFPGA=y CONFIG_CMDLINE_BOOL=y CONFIG_CMDLINE="earlycon=uart8250,mmio32native,0x9d050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=256M@0x60000000" CONFIG_USE_OF=y -CONFIG_BUILTIN_DTB="kc705_nommu" +CONFIG_BUILTIN_DTB_SOURCE="kc705_nommu" CONFIG_BINFMT_FLAT=y CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/xtensa/configs/smp_lx200_defconfig b/arch/xtensa/configs/smp_lx200_defconfig index 11fed6c06a7c..e29c5b179a5b 100644 --- a/arch/xtensa/configs/smp_lx200_defconfig +++ b/arch/xtensa/configs/smp_lx200_defconfig @@ -33,11 +33,12 @@ CONFIG_SMP=y CONFIG_HOTPLUG_CPU=y # CONFIG_INITIALIZE_XTENSA_MMU_INSIDE_VMLINUX is not set # CONFIG_PCI is not set +CONFIG_VECTORS_OFFSET=0x00002000 CONFIG_XTENSA_PLATFORM_XTFPGA=y CONFIG_CMDLINE_BOOL=y CONFIG_CMDLINE="earlycon=uart8250,mmio32native,0xfd050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=96M@0" CONFIG_USE_OF=y -CONFIG_BUILTIN_DTB="lx200mx" +CONFIG_BUILTIN_DTB_SOURCE="lx200mx" # CONFIG_COMPACTION is not set # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set CONFIG_NET=y diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild index e255683cd520..809f39ce08c0 100644 --- a/arch/xtensa/include/asm/Kbuild +++ b/arch/xtensa/include/asm/Kbuild @@ -25,6 +25,7 @@ generic-y += percpu.h generic-y += preempt.h generic-y += rwsem.h generic-y += sections.h +generic-y += socket.h generic-y += topology.h generic-y += trace_clock.h generic-y += vga.h diff --git a/arch/xtensa/include/uapi/asm/Kbuild b/arch/xtensa/include/uapi/asm/Kbuild index 960bf1e4be53..6b43e5049ff7 100644 --- a/arch/xtensa/include/uapi/asm/Kbuild +++ b/arch/xtensa/include/uapi/asm/Kbuild @@ -2,3 +2,4 @@ include include/uapi/asm-generic/Kbuild.asm generated-y += unistd_32.h generic-y += kvm_para.h +generic-y += socket.h diff --git a/arch/xtensa/include/uapi/asm/socket.h b/arch/xtensa/include/uapi/asm/socket.h deleted file mode 100644 index b434217783d0..000000000000 --- a/arch/xtensa/include/uapi/asm/socket.h +++ /dev/null @@ -1,124 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* - * include/asm-xtensa/socket.h - * - * Copied from i386. - * - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - */ - -#ifndef _XTENSA_SOCKET_H -#define _XTENSA_SOCKET_H - -#include <asm/sockios.h> - -/* For setsockoptions(2) */ -#define SOL_SOCKET 1 - -#define SO_DEBUG 1 -#define SO_REUSEADDR 2 -#define SO_TYPE 3 -#define SO_ERROR 4 -#define SO_DONTROUTE 5 -#define SO_BROADCAST 6 -#define SO_SNDBUF 7 -#define SO_RCVBUF 8 -#define SO_SNDBUFFORCE 32 -#define SO_RCVBUFFORCE 33 -#define SO_KEEPALIVE 9 -#define SO_OOBINLINE 10 -#define SO_NO_CHECK 11 -#define SO_PRIORITY 12 -#define SO_LINGER 13 -#define SO_BSDCOMPAT 14 -#define SO_REUSEPORT 15 -#define SO_PASSCRED 16 -#define SO_PEERCRED 17 -#define SO_RCVLOWAT 18 -#define SO_SNDLOWAT 19 -#define SO_RCVTIMEO 20 -#define SO_SNDTIMEO 21 - -/* Security levels - as per NRL IPv6 - don't actually do anything */ - -#define SO_SECURITY_AUTHENTICATION 22 -#define SO_SECURITY_ENCRYPTION_TRANSPORT 23 -#define SO_SECURITY_ENCRYPTION_NETWORK 24 - -#define SO_BINDTODEVICE 25 - -/* Socket filtering */ - -#define SO_ATTACH_FILTER 26 -#define SO_DETACH_FILTER 27 -#define SO_GET_FILTER SO_ATTACH_FILTER - -#define SO_PEERNAME 28 -#define SO_TIMESTAMP 29 -#define SCM_TIMESTAMP SO_TIMESTAMP - -#define SO_ACCEPTCONN 30 -#define SO_PEERSEC 31 -#define SO_PASSSEC 34 -#define SO_TIMESTAMPNS 35 -#define SCM_TIMESTAMPNS SO_TIMESTAMPNS - -#define SO_MARK 36 - -#define SO_TIMESTAMPING 37 -#define SCM_TIMESTAMPING SO_TIMESTAMPING - -#define SO_PROTOCOL 38 -#define SO_DOMAIN 39 - -#define SO_RXQ_OVFL 40 - -#define SO_WIFI_STATUS 41 -#define SCM_WIFI_STATUS SO_WIFI_STATUS -#define SO_PEEK_OFF 42 - -/* Instruct lower device to use last 4-bytes of skb data as FCS */ -#define SO_NOFCS 43 - -#define SO_LOCK_FILTER 44 - -#define SO_SELECT_ERR_QUEUE 45 - -#define SO_BUSY_POLL 46 - -#define SO_MAX_PACING_RATE 47 - -#define SO_BPF_EXTENSIONS 48 - -#define SO_INCOMING_CPU 49 - -#define SO_ATTACH_BPF 50 -#define SO_DETACH_BPF SO_DETACH_FILTER - -#define SO_ATTACH_REUSEPORT_CBPF 51 -#define SO_ATTACH_REUSEPORT_EBPF 52 - -#define SO_CNX_ADVICE 53 - -#define SCM_TIMESTAMPING_OPT_STATS 54 - -#define SO_MEMINFO 55 - -#define SO_INCOMING_NAPI_ID 56 - -#define SO_COOKIE 57 - -#define SCM_TIMESTAMPING_PKTINFO 58 - -#define SO_PEERGROUPS 59 - -#define SO_ZEROCOPY 60 - -#define SO_TXTIME 61 -#define SCM_TXTIME SO_TXTIME - -#define SO_BINDTOIFINDEX 62 - -#endif /* _XTENSA_SOCKET_H */ diff --git a/arch/xtensa/kernel/head.S b/arch/xtensa/kernel/head.S index da08e75100ab..7f009719304e 100644 --- a/arch/xtensa/kernel/head.S +++ b/arch/xtensa/kernel/head.S @@ -276,12 +276,13 @@ should_never_return: movi a2, cpu_start_ccount 1: + memw l32i a3, a2, 0 beqi a3, 0, 1b movi a3, 0 s32i a3, a2, 0 - memw 1: + memw l32i a3, a2, 0 beqi a3, 0, 1b wsr a3, ccount @@ -317,11 +318,13 @@ ENTRY(cpu_restart) rsr a0, prid neg a2, a0 movi a3, cpu_start_id + memw s32i a2, a3, 0 #if XCHAL_DCACHE_IS_WRITEBACK dhwbi a3, 0 #endif 1: + memw l32i a2, a3, 0 dhi a3, 0 bne a2, a0, 1b diff --git a/arch/xtensa/kernel/smp.c b/arch/xtensa/kernel/smp.c index 932d64689bac..be1f280c322c 100644 --- a/arch/xtensa/kernel/smp.c +++ b/arch/xtensa/kernel/smp.c @@ -83,7 +83,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus) { unsigned i; - for (i = 0; i < max_cpus; ++i) + for_each_possible_cpu(i) set_cpu_present(i, true); } @@ -96,6 +96,11 @@ void __init smp_init_cpus(void) pr_info("%s: Core Count = %d\n", __func__, ncpus); pr_info("%s: Core Id = %d\n", __func__, core_id); + if (ncpus > NR_CPUS) { + ncpus = NR_CPUS; + pr_info("%s: limiting core count by %d\n", __func__, ncpus); + } + for (i = 0; i < ncpus; ++i) set_cpu_possible(i, true); } @@ -195,9 +200,11 @@ static int boot_secondary(unsigned int cpu, struct task_struct *ts) int i; #ifdef CONFIG_HOTPLUG_CPU - cpu_start_id = cpu; - system_flush_invalidate_dcache_range( - (unsigned long)&cpu_start_id, sizeof(cpu_start_id)); + WRITE_ONCE(cpu_start_id, cpu); + /* Pairs with the third memw in the cpu_restart */ + mb(); + system_flush_invalidate_dcache_range((unsigned long)&cpu_start_id, + sizeof(cpu_start_id)); #endif smp_call_function_single(0, mx_cpu_start, (void *)cpu, 1); @@ -206,18 +213,21 @@ static int boot_secondary(unsigned int cpu, struct task_struct *ts) ccount = get_ccount(); while (!ccount); - cpu_start_ccount = ccount; + WRITE_ONCE(cpu_start_ccount, ccount); - while (time_before(jiffies, timeout)) { + do { + /* + * Pairs with the first two memws in the + * .Lboot_secondary. + */ mb(); - if (!cpu_start_ccount) - break; - } + ccount = READ_ONCE(cpu_start_ccount); + } while (ccount && time_before(jiffies, timeout)); - if (cpu_start_ccount) { + if (ccount) { smp_call_function_single(0, mx_cpu_stop, - (void *)cpu, 1); - cpu_start_ccount = 0; + (void *)cpu, 1); + WRITE_ONCE(cpu_start_ccount, 0); return -EIO; } } @@ -237,6 +247,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle) pr_debug("%s: Calling wakeup_secondary(cpu:%d, idle:%p, sp: %08lx)\n", __func__, cpu, idle, start_info.stack); + init_completion(&cpu_running); ret = boot_secondary(cpu, idle); if (ret == 0) { wait_for_completion_timeout(&cpu_running, @@ -298,8 +309,10 @@ void __cpu_die(unsigned int cpu) unsigned long timeout = jiffies + msecs_to_jiffies(1000); while (time_before(jiffies, timeout)) { system_invalidate_dcache_range((unsigned long)&cpu_start_id, - sizeof(cpu_start_id)); - if (cpu_start_id == -cpu) { + sizeof(cpu_start_id)); + /* Pairs with the second memw in the cpu_restart */ + mb(); + if (READ_ONCE(cpu_start_id) == -cpu) { platform_cpu_kill(cpu); return; } diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c index fd524a54d2ab..378186b5eb40 100644 --- a/arch/xtensa/kernel/time.c +++ b/arch/xtensa/kernel/time.c @@ -89,7 +89,7 @@ static int ccount_timer_shutdown(struct clock_event_device *evt) container_of(evt, struct ccount_timer, evt); if (timer->irq_enabled) { - disable_irq(evt->irq); + disable_irq_nosync(evt->irq); timer->irq_enabled = 0; } return 0; diff --git a/block/blk-core.c b/block/blk-core.c index 1ccec27d20c3..6b78ec56a4f2 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -462,6 +462,10 @@ static void blk_rq_timed_out_timer(struct timer_list *t) kblockd_schedule_work(&q->timeout_work); } +static void blk_timeout_work(struct work_struct *work) +{ +} + /** * blk_alloc_queue_node - allocate a request queue * @gfp_mask: memory allocation flags @@ -505,7 +509,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) timer_setup(&q->backing_dev_info->laptop_mode_wb_timer, laptop_mode_timer_fn, 0); timer_setup(&q->timeout, blk_rq_timed_out_timer, 0); - INIT_WORK(&q->timeout_work, NULL); + INIT_WORK(&q->timeout_work, blk_timeout_work); INIT_LIST_HEAD(&q->icq_list); #ifdef CONFIG_BLK_CGROUP INIT_LIST_HEAD(&q->blkg_list); @@ -1083,18 +1087,7 @@ blk_qc_t generic_make_request(struct bio *bio) /* Create a fresh bio_list for all subordinate requests */ bio_list_on_stack[1] = bio_list_on_stack[0]; bio_list_init(&bio_list_on_stack[0]); - - /* - * Since we're recursing into make_request here, ensure - * that we mark this bio as already having entered the queue. - * If not, and the queue is going away, we can get stuck - * forever on waiting for the queue reference to drop. But - * that will never happen, as we're already holding a - * reference to it. - */ - bio_set_flag(bio, BIO_QUEUE_ENTERED); ret = q->make_request_fn(q, bio); - bio_clear_flag(bio, BIO_QUEUE_ENTERED); /* sort new bios into those for a lower level * and those for the same level diff --git a/block/blk-flush.c b/block/blk-flush.c index a3fc7191c694..6e0f2d97fc6d 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -335,7 +335,7 @@ static void mq_flush_data_end_io(struct request *rq, blk_status_t error) blk_flush_complete_seq(rq, fq, REQ_FSEQ_DATA, error); spin_unlock_irqrestore(&fq->mq_flush_lock, flags); - blk_mq_run_hw_queue(hctx, true); + blk_mq_sched_restart(hctx); } /** diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c index fc714ef402a6..2620baa1f699 100644 --- a/block/blk-iolatency.c +++ b/block/blk-iolatency.c @@ -72,6 +72,7 @@ #include <linux/sched/loadavg.h> #include <linux/sched/signal.h> #include <trace/events/block.h> +#include <linux/blk-mq.h> #include "blk-rq-qos.h" #include "blk-stat.h" @@ -591,6 +592,7 @@ static void blkcg_iolatency_done_bio(struct rq_qos *rqos, struct bio *bio) u64 now = ktime_to_ns(ktime_get()); bool issue_as_root = bio_issue_as_root_blkg(bio); bool enabled = false; + int inflight = 0; blkg = bio->bi_blkg; if (!blkg || !bio_flagged(bio, BIO_TRACKED)) @@ -601,6 +603,9 @@ static void blkcg_iolatency_done_bio(struct rq_qos *rqos, struct bio *bio) return; enabled = blk_iolatency_enabled(iolat->blkiolat); + if (!enabled) + return; + while (blkg && blkg->parent) { iolat = blkg_to_lat(blkg); if (!iolat) { @@ -609,8 +614,9 @@ static void blkcg_iolatency_done_bio(struct rq_qos *rqos, struct bio *bio) } rqw = &iolat->rq_wait; - atomic_dec(&rqw->inflight); - if (!enabled || iolat->min_lat_nsec == 0) + inflight = atomic_dec_return(&rqw->inflight); + WARN_ON_ONCE(inflight < 0); + if (iolat->min_lat_nsec == 0) goto next; iolatency_record_time(iolat, &bio->bi_issue, now, issue_as_root); @@ -754,10 +760,13 @@ int blk_iolatency_init(struct request_queue *q) return 0; } -static void iolatency_set_min_lat_nsec(struct blkcg_gq *blkg, u64 val) +/* + * return 1 for enabling iolatency, return -1 for disabling iolatency, otherwise + * return 0. + */ +static int iolatency_set_min_lat_nsec(struct blkcg_gq *blkg, u64 val) { struct iolatency_grp *iolat = blkg_to_lat(blkg); - struct blk_iolatency *blkiolat = iolat->blkiolat; u64 oldval = iolat->min_lat_nsec; iolat->min_lat_nsec = val; @@ -766,9 +775,10 @@ static void iolatency_set_min_lat_nsec(struct blkcg_gq *blkg, u64 val) BLKIOLATENCY_MAX_WIN_SIZE); if (!oldval && val) - atomic_inc(&blkiolat->enabled); + return 1; if (oldval && !val) - atomic_dec(&blkiolat->enabled); + return -1; + return 0; } static void iolatency_clear_scaling(struct blkcg_gq *blkg) @@ -800,6 +810,7 @@ static ssize_t iolatency_set_limit(struct kernfs_open_file *of, char *buf, u64 lat_val = 0; u64 oldval; int ret; + int enable = 0; ret = blkg_conf_prep(blkcg, &blkcg_policy_iolatency, buf, &ctx); if (ret) @@ -834,7 +845,12 @@ static ssize_t iolatency_set_limit(struct kernfs_open_file *of, char *buf, blkg = ctx.blkg; oldval = iolat->min_lat_nsec; - iolatency_set_min_lat_nsec(blkg, lat_val); + enable = iolatency_set_min_lat_nsec(blkg, lat_val); + if (enable) { + WARN_ON_ONCE(!blk_get_queue(blkg->q)); + blkg_get(blkg); + } + if (oldval != iolat->min_lat_nsec) { iolatency_clear_scaling(blkg); } @@ -842,6 +858,24 @@ static ssize_t iolatency_set_limit(struct kernfs_open_file *of, char *buf, ret = 0; out: blkg_conf_finish(&ctx); + if (ret == 0 && enable) { + struct iolatency_grp *tmp = blkg_to_lat(blkg); + struct blk_iolatency *blkiolat = tmp->blkiolat; + + blk_mq_freeze_queue(blkg->q); + + if (enable == 1) + atomic_inc(&blkiolat->enabled); + else if (enable == -1) + atomic_dec(&blkiolat->enabled); + else + WARN_ON_ONCE(1); + + blk_mq_unfreeze_queue(blkg->q); + + blkg_put(blkg); + blk_put_queue(blkg->q); + } return ret ?: nbytes; } @@ -977,8 +1011,14 @@ static void iolatency_pd_offline(struct blkg_policy_data *pd) { struct iolatency_grp *iolat = pd_to_lat(pd); struct blkcg_gq *blkg = lat_to_blkg(iolat); + struct blk_iolatency *blkiolat = iolat->blkiolat; + int ret; - iolatency_set_min_lat_nsec(blkg, 0); + ret = iolatency_set_min_lat_nsec(blkg, 0); + if (ret == 1) + atomic_inc(&blkiolat->enabled); + if (ret == -1) + atomic_dec(&blkiolat->enabled); iolatency_clear_scaling(blkg); } diff --git a/block/blk-merge.c b/block/blk-merge.c index d79a22f111d1..71e9ac03f621 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -272,6 +272,16 @@ void blk_queue_split(struct request_queue *q, struct bio **bio) /* there isn't chance to merge the splitted bio */ split->bi_opf |= REQ_NOMERGE; + /* + * Since we're recursing into make_request here, ensure + * that we mark this bio as already having entered the queue. + * If not, and the queue is going away, we can get stuck + * forever on waiting for the queue reference to drop. But + * that will never happen, as we're already holding a + * reference to it. + */ + bio_set_flag(*bio, BIO_QUEUE_ENTERED); + bio_chain(split, *bio); trace_block_split(q, split, (*bio)->bi_iter.bi_sector); generic_make_request(*bio); diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index f8120832ca7b..7921573aebbc 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -839,6 +839,9 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_ctx_attrs[] = { static bool debugfs_create_files(struct dentry *parent, void *data, const struct blk_mq_debugfs_attr *attr) { + if (IS_ERR_OR_NULL(parent)) + return false; + d_inode(parent)->i_private = data; for (; attr->name; attr++) { diff --git a/block/blk-mq.c b/block/blk-mq.c index 8f5b533764ca..9437a5eb07cf 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -737,12 +737,20 @@ static void blk_mq_requeue_work(struct work_struct *work) spin_unlock_irq(&q->requeue_lock); list_for_each_entry_safe(rq, next, &rq_list, queuelist) { - if (!(rq->rq_flags & RQF_SOFTBARRIER)) + if (!(rq->rq_flags & (RQF_SOFTBARRIER | RQF_DONTPREP))) continue; rq->rq_flags &= ~RQF_SOFTBARRIER; list_del_init(&rq->queuelist); - blk_mq_sched_insert_request(rq, true, false, false); + /* + * If RQF_DONTPREP, rq has contained some driver specific + * data, so insert it to hctx dispatch list to avoid any + * merge. + */ + if (rq->rq_flags & RQF_DONTPREP) + blk_mq_request_bypass_insert(rq, false); + else + blk_mq_sched_insert_request(rq, true, false, false); } while (!list_empty(&rq_list)) { diff --git a/block/blk-mq.h b/block/blk-mq.h index d943d46b0785..d0b3dd54ef8d 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -36,7 +36,6 @@ struct blk_mq_ctx { struct kobject kobj; } ____cacheline_aligned_in_smp; -void blk_mq_freeze_queue(struct request_queue *q); void blk_mq_free_queue(struct request_queue *q); int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr); void blk_mq_wake_waiters(struct request_queue *q); diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index 5c093ce01bcd..147f6c7ea59c 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -1029,6 +1029,9 @@ void __init acpi_early_init(void) acpi_permanent_mmap = true; + /* Initialize debug output. Linux does not use ACPICA defaults */ + acpi_dbg_level = ACPI_LV_INFO | ACPI_LV_REPAIR; + #ifdef CONFIG_X86 /* * If the machine falls into the DMI check table, diff --git a/drivers/android/binder.c b/drivers/android/binder.c index cdfc87629efb..4d2b2ad1ee0e 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -5854,9 +5854,10 @@ static int __init init_binder_device(const char *name) static int __init binder_init(void) { int ret; - char *device_name, *device_names, *device_tmp; + char *device_name, *device_tmp; struct binder_device *device; struct hlist_node *tmp; + char *device_names = NULL; ret = binder_alloc_shrinker_init(); if (ret) @@ -5898,23 +5899,29 @@ static int __init binder_init(void) &transaction_log_fops); } - /* - * Copy the module_parameter string, because we don't want to - * tokenize it in-place. - */ - device_names = kstrdup(binder_devices_param, GFP_KERNEL); - if (!device_names) { - ret = -ENOMEM; - goto err_alloc_device_names_failed; - } + if (strcmp(binder_devices_param, "") != 0) { + /* + * Copy the module_parameter string, because we don't want to + * tokenize it in-place. + */ + device_names = kstrdup(binder_devices_param, GFP_KERNEL); + if (!device_names) { + ret = -ENOMEM; + goto err_alloc_device_names_failed; + } - device_tmp = device_names; - while ((device_name = strsep(&device_tmp, ","))) { - ret = init_binder_device(device_name); - if (ret) - goto err_init_binder_device_failed; + device_tmp = device_names; + while ((device_name = strsep(&device_tmp, ","))) { + ret = init_binder_device(device_name); + if (ret) + goto err_init_binder_device_failed; + } } + ret = init_binderfs(); + if (ret) + goto err_init_binder_device_failed; + return ret; err_init_binder_device_failed: diff --git a/drivers/android/binder_internal.h b/drivers/android/binder_internal.h index 7fb97f503ef2..045b3e42d98b 100644 --- a/drivers/android/binder_internal.h +++ b/drivers/android/binder_internal.h @@ -46,4 +46,13 @@ static inline bool is_binderfs_device(const struct inode *inode) } #endif +#ifdef CONFIG_ANDROID_BINDERFS +extern int __init init_binderfs(void); +#else +static inline int __init init_binderfs(void) +{ + return 0; +} +#endif + #endif /* _LINUX_BINDER_INTERNAL_H */ diff --git a/drivers/android/binderfs.c b/drivers/android/binderfs.c index 6a2185eb66c5..e773f45d19d9 100644 --- a/drivers/android/binderfs.c +++ b/drivers/android/binderfs.c @@ -395,6 +395,11 @@ static int binderfs_binder_ctl_create(struct super_block *sb) struct inode *inode = NULL; struct dentry *root = sb->s_root; struct binderfs_info *info = sb->s_fs_info; +#if defined(CONFIG_IPC_NS) + bool use_reserve = (info->ipc_ns == &init_ipc_ns); +#else + bool use_reserve = true; +#endif device = kzalloc(sizeof(*device), GFP_KERNEL); if (!device) @@ -413,7 +418,10 @@ static int binderfs_binder_ctl_create(struct super_block *sb) /* Reserve a new minor number for the new device. */ mutex_lock(&binderfs_minors_mutex); - minor = ida_alloc_max(&binderfs_minors, BINDERFS_MAX_MINOR, GFP_KERNEL); + minor = ida_alloc_max(&binderfs_minors, + use_reserve ? BINDERFS_MAX_MINOR : + BINDERFS_MAX_MINOR_CAPPED, + GFP_KERNEL); mutex_unlock(&binderfs_minors_mutex); if (minor < 0) { ret = minor; @@ -542,7 +550,7 @@ static struct file_system_type binder_fs_type = { .fs_flags = FS_USERNS_MOUNT, }; -static int __init init_binderfs(void) +int __init init_binderfs(void) { int ret; @@ -560,5 +568,3 @@ static int __init init_binderfs(void) return ret; } - -device_initcall(init_binderfs); diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index b8c3f9e6af89..adf28788cab5 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -4554,6 +4554,7 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { { "SAMSUNG MZMPC128HBFU-000MV", "CXM14M1Q", ATA_HORKAGE_NOLPM, }, { "SAMSUNG SSD PM830 mSATA *", "CXM13D1Q", ATA_HORKAGE_NOLPM, }, { "SAMSUNG MZ7TD256HAFV-000L9", NULL, ATA_HORKAGE_NOLPM, }, + { "SAMSUNG MZ7TE512HMHP-000L1", "EXT06L0Q", ATA_HORKAGE_NOLPM, }, /* devices that don't properly handle queued TRIM commands */ { "Micron_M500IT_*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c index cf78fa6d470d..a7359535caf5 100644 --- a/drivers/base/cacheinfo.c +++ b/drivers/base/cacheinfo.c @@ -79,8 +79,7 @@ static void cache_size(struct cacheinfo *this_leaf, struct device_node *np) ct_idx = get_cacheinfo_idx(this_leaf->type); propname = cache_type_info[ct_idx].size_prop; - if (of_property_read_u32(np, propname, &this_leaf->size)) - this_leaf->size = 0; + of_property_read_u32(np, propname, &this_leaf->size); } /* not cache_line_size() because that's a macro in include/linux/cache.h */ @@ -114,8 +113,7 @@ static void cache_nr_sets(struct cacheinfo *this_leaf, struct device_node *np) ct_idx = get_cacheinfo_idx(this_leaf->type); propname = cache_type_info[ct_idx].nr_sets_prop; - if (of_property_read_u32(np, propname, &this_leaf->number_of_sets)) - this_leaf->number_of_sets = 0; + of_property_read_u32(np, propname, &this_leaf->number_of_sets); } static void cache_associativity(struct cacheinfo *this_leaf) diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c index 457be03b744d..0ea2139c50d8 100644 --- a/drivers/base/power/runtime.c +++ b/drivers/base/power/runtime.c @@ -130,7 +130,7 @@ u64 pm_runtime_autosuspend_expiration(struct device *dev) { int autosuspend_delay; u64 last_busy, expires = 0; - u64 now = ktime_to_ns(ktime_get()); + u64 now = ktime_get_mono_fast_ns(); if (!dev->power.use_autosuspend) goto out; @@ -909,7 +909,7 @@ static enum hrtimer_restart pm_suspend_timer_fn(struct hrtimer *timer) * If 'expires' is after the current time, we've been called * too early. */ - if (expires > 0 && expires < ktime_to_ns(ktime_get())) { + if (expires > 0 && expires < ktime_get_mono_fast_ns()) { dev->power.timer_expires = 0; rpm_suspend(dev, dev->power.timer_autosuspends ? (RPM_ASYNC | RPM_AUTO) : RPM_ASYNC); @@ -928,7 +928,7 @@ static enum hrtimer_restart pm_suspend_timer_fn(struct hrtimer *timer) int pm_schedule_suspend(struct device *dev, unsigned int delay) { unsigned long flags; - ktime_t expires; + u64 expires; int retval; spin_lock_irqsave(&dev->power.lock, flags); @@ -945,8 +945,8 @@ int pm_schedule_suspend(struct device *dev, unsigned int delay) /* Other scheduled or pending requests need to be canceled. */ pm_runtime_cancel_pending(dev); - expires = ktime_add(ktime_get(), ms_to_ktime(delay)); - dev->power.timer_expires = ktime_to_ns(expires); + expires = ktime_get_mono_fast_ns() + (u64)delay * NSEC_PER_MSEC; + dev->power.timer_expires = expires; dev->power.timer_autosuspends = 0; hrtimer_start(&dev->power.suspend_timer, expires, HRTIMER_MODE_ABS); diff --git a/drivers/bcma/bcma_private.h b/drivers/bcma/bcma_private.h index a4aac370f21f..6eded32d1aac 100644 --- a/drivers/bcma/bcma_private.h +++ b/drivers/bcma/bcma_private.h @@ -10,13 +10,13 @@ #include <linux/delay.h> #define bcma_err(bus, fmt, ...) \ - pr_err("bus%d: " fmt, (bus)->num, ##__VA_ARGS__) + dev_err((bus)->dev, "bus%d: " fmt, (bus)->num, ##__VA_ARGS__) #define bcma_warn(bus, fmt, ...) \ - pr_warn("bus%d: " fmt, (bus)->num, ##__VA_ARGS__) + dev_warn((bus)->dev, "bus%d: " fmt, (bus)->num, ##__VA_ARGS__) #define bcma_info(bus, fmt, ...) \ - pr_info("bus%d: " fmt, (bus)->num, ##__VA_ARGS__) + dev_info((bus)->dev, "bus%d: " fmt, (bus)->num, ##__VA_ARGS__) #define bcma_debug(bus, fmt, ...) \ - pr_debug("bus%d: " fmt, (bus)->num, ##__VA_ARGS__) + dev_dbg((bus)->dev, "bus%d: " fmt, (bus)->num, ##__VA_ARGS__) struct bcma_bus; @@ -33,7 +33,6 @@ int __init bcma_bus_early_register(struct bcma_bus *bus); int bcma_bus_suspend(struct bcma_bus *bus); int bcma_bus_resume(struct bcma_bus *bus); #endif -struct device *bcma_bus_get_host_dev(struct bcma_bus *bus); /* scan.c */ void bcma_detect_chip(struct bcma_bus *bus); diff --git a/drivers/bcma/driver_gpio.c b/drivers/bcma/driver_gpio.c index 2c0ffb77d738..a5df3d111334 100644 --- a/drivers/bcma/driver_gpio.c +++ b/drivers/bcma/driver_gpio.c @@ -183,7 +183,7 @@ int bcma_gpio_init(struct bcma_drv_cc *cc) chip->direction_input = bcma_gpio_direction_input; chip->direction_output = bcma_gpio_direction_output; chip->owner = THIS_MODULE; - chip->parent = bcma_bus_get_host_dev(bus); + chip->parent = bus->dev; #if IS_BUILTIN(CONFIG_OF) chip->of_node = cc->core->dev.of_node; #endif diff --git a/drivers/bcma/host_pci.c b/drivers/bcma/host_pci.c index 63410ecfe640..f52239feb4cb 100644 --- a/drivers/bcma/host_pci.c +++ b/drivers/bcma/host_pci.c @@ -196,6 +196,8 @@ static int bcma_host_pci_probe(struct pci_dev *dev, goto err_pci_release_regions; } + bus->dev = &dev->dev; + /* Map MMIO */ err = -ENOMEM; bus->mmio = pci_iomap(dev, 0, ~0UL); diff --git a/drivers/bcma/host_soc.c b/drivers/bcma/host_soc.c index 2dce34789329..c8073b509a2b 100644 --- a/drivers/bcma/host_soc.c +++ b/drivers/bcma/host_soc.c @@ -179,7 +179,6 @@ int __init bcma_host_soc_register(struct bcma_soc *soc) /* Host specific */ bus->hosttype = BCMA_HOSTTYPE_SOC; bus->ops = &bcma_host_soc_ops; - bus->host_pdev = NULL; /* Initialize struct, detect chip */ bcma_init_bus(bus); @@ -213,6 +212,8 @@ static int bcma_host_soc_probe(struct platform_device *pdev) if (!bus) return -ENOMEM; + bus->dev = dev; + /* Map MMIO */ bus->mmio = of_iomap(np, 0); if (!bus->mmio) @@ -221,7 +222,6 @@ static int bcma_host_soc_probe(struct platform_device *pdev) /* Host specific */ bus->hosttype = BCMA_HOSTTYPE_SOC; bus->ops = &bcma_host_soc_ops; - bus->host_pdev = pdev; /* Initialize struct, detect chip */ bcma_init_bus(bus); diff --git a/drivers/bcma/main.c b/drivers/bcma/main.c index fc1f4acdd189..6535614a7dc1 100644 --- a/drivers/bcma/main.c +++ b/drivers/bcma/main.c @@ -223,8 +223,8 @@ unsigned int bcma_core_irq(struct bcma_device *core, int num) mips_irq = bcma_core_mips_irq(core); return mips_irq <= 4 ? mips_irq + 2 : 0; } - if (bus->host_pdev) - return bcma_of_get_irq(&bus->host_pdev->dev, core, num); + if (bus->dev) + return bcma_of_get_irq(bus->dev, core, num); return 0; case BCMA_HOSTTYPE_SDIO: return 0; @@ -239,18 +239,18 @@ void bcma_prepare_core(struct bcma_bus *bus, struct bcma_device *core) core->dev.release = bcma_release_core_dev; core->dev.bus = &bcma_bus_type; dev_set_name(&core->dev, "bcma%d:%d", bus->num, core->core_index); - core->dev.parent = bcma_bus_get_host_dev(bus); - if (core->dev.parent) - bcma_of_fill_device(core->dev.parent, core); + core->dev.parent = bus->dev; + if (bus->dev) + bcma_of_fill_device(bus->dev, core); switch (bus->hosttype) { case BCMA_HOSTTYPE_PCI: - core->dma_dev = &bus->host_pci->dev; + core->dma_dev = bus->dev; core->irq = bus->host_pci->irq; break; case BCMA_HOSTTYPE_SOC: - if (IS_ENABLED(CONFIG_OF) && bus->host_pdev) { - core->dma_dev = &bus->host_pdev->dev; + if (IS_ENABLED(CONFIG_OF) && bus->dev) { + core->dma_dev = bus->dev; } else { core->dev.dma_mask = &core->dev.coherent_dma_mask; core->dma_dev = &core->dev; @@ -261,28 +261,6 @@ void bcma_prepare_core(struct bcma_bus *bus, struct bcma_device *core) } } -struct device *bcma_bus_get_host_dev(struct bcma_bus *bus) -{ - switch (bus->hosttype) { - case BCMA_HOSTTYPE_PCI: - if (bus->host_pci) - return &bus->host_pci->dev; - else - return NULL; - case BCMA_HOSTTYPE_SOC: - if (bus->host_pdev) - return &bus->host_pdev->dev; - else - return NULL; - case BCMA_HOSTTYPE_SDIO: - if (bus->host_sdio) - return &bus->host_sdio->dev; - else - return NULL; - } - return NULL; -} - void bcma_init_bus(struct bcma_bus *bus) { mutex_lock(&bcma_buses_mutex); @@ -402,7 +380,6 @@ int bcma_bus_register(struct bcma_bus *bus) { int err; struct bcma_device *core; - struct device *dev; /* Scan for devices (cores) */ err = bcma_bus_scan(bus); @@ -425,10 +402,8 @@ int bcma_bus_register(struct bcma_bus *bus) bcma_core_pci_early_init(&bus->drv_pci[0]); } - dev = bcma_bus_get_host_dev(bus); - if (dev) { - of_platform_default_populate(dev->of_node, NULL, dev); - } + if (bus->dev) + of_platform_default_populate(bus->dev->of_node, NULL, bus->dev); /* Cores providing flash access go before SPROM init */ list_for_each_entry(core, &bus->cores, list) { diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 6f2856c6d0f2..55481b40df9a 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -4075,7 +4075,7 @@ static unsigned int floppy_check_events(struct gendisk *disk, if (time_after(jiffies, UDRS->last_checked + UDP->checkfreq)) { if (lock_fdc(drive)) - return -EINTR; + return 0; poll_drive(false, 0); process_fd_request(); } diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index 6ccdbedb02f3..d2477a5058ac 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -1513,9 +1513,19 @@ static int clk_fetch_parent_index(struct clk_core *core, if (!parent) return -EINVAL; - for (i = 0; i < core->num_parents; i++) - if (clk_core_get_parent_by_index(core, i) == parent) + for (i = 0; i < core->num_parents; i++) { + if (core->parents[i] == parent) + return i; + + if (core->parents[i]) + continue; + + /* Fallback to comparing globally unique names */ + if (!strcmp(parent->name, core->parent_names[i])) { + core->parents[i] = parent; return i; + } + } return -EINVAL; } diff --git a/drivers/clk/imx/clk-frac-pll.c b/drivers/clk/imx/clk-frac-pll.c index 0026c3969b1e..76b9eb15604e 100644 --- a/drivers/clk/imx/clk-frac-pll.c +++ b/drivers/clk/imx/clk-frac-pll.c @@ -155,13 +155,14 @@ static int clk_pll_set_rate(struct clk_hw *hw, unsigned long rate, { struct clk_frac_pll *pll = to_clk_frac_pll(hw); u32 val, divfi, divff; - u64 temp64 = parent_rate; + u64 temp64; int ret; parent_rate *= 8; rate *= 2; divfi = rate / parent_rate; - temp64 *= rate - divfi; + temp64 = parent_rate * divfi; + temp64 = rate - temp64; temp64 *= PLL_FRAC_DENOM; do_div(temp64, parent_rate); divff = temp64; diff --git a/drivers/clk/mmp/clk-of-mmp2.c b/drivers/clk/mmp/clk-of-mmp2.c index 61fefc046ec5..d083b860f083 100644 --- a/drivers/clk/mmp/clk-of-mmp2.c +++ b/drivers/clk/mmp/clk-of-mmp2.c @@ -53,7 +53,6 @@ #define APMU_DISP1 0x110 #define APMU_CCIC0 0x50 #define APMU_CCIC1 0xf4 -#define APMU_SP 0x68 #define MPMU_UART_PLL 0x14 struct mmp2_clk_unit { @@ -210,8 +209,6 @@ static struct mmp_clk_mix_config ccic1_mix_config = { .reg_info = DEFINE_MIX_REG_INFO(4, 16, 2, 6, 32), }; -static DEFINE_SPINLOCK(sp_lock); - static struct mmp_param_mux_clk apmu_mux_clks[] = { {MMP2_CLK_DISP0_MUX, "disp0_mux", disp_parent_names, ARRAY_SIZE(disp_parent_names), CLK_SET_RATE_PARENT, APMU_DISP0, 6, 2, 0, &disp0_lock}, {MMP2_CLK_DISP1_MUX, "disp1_mux", disp_parent_names, ARRAY_SIZE(disp_parent_names), CLK_SET_RATE_PARENT, APMU_DISP1, 6, 2, 0, &disp1_lock}, @@ -242,7 +239,6 @@ static struct mmp_param_gate_clk apmu_gate_clks[] = { {MMP2_CLK_CCIC1, "ccic1_clk", "ccic1_mix_clk", CLK_SET_RATE_PARENT, APMU_CCIC1, 0x1b, 0x1b, 0x0, 0, &ccic1_lock}, {MMP2_CLK_CCIC1_PHY, "ccic1_phy_clk", "ccic1_mix_clk", CLK_SET_RATE_PARENT, APMU_CCIC1, 0x24, 0x24, 0x0, 0, &ccic1_lock}, {MMP2_CLK_CCIC1_SPHY, "ccic1_sphy_clk", "ccic1_sphy_div", CLK_SET_RATE_PARENT, APMU_CCIC1, 0x300, 0x300, 0x0, 0, &ccic1_lock}, - {MMP2_CLK_SP, "sp_clk", NULL, CLK_SET_RATE_PARENT, APMU_SP, 0x1b, 0x1b, 0x0, 0, &sp_lock}, }; static void mmp2_axi_periph_clk_init(struct mmp2_clk_unit *pxa_unit) diff --git a/drivers/clk/qcom/gcc-sdm845.c b/drivers/clk/qcom/gcc-sdm845.c index c782e62dd98b..58fa5c247af1 100644 --- a/drivers/clk/qcom/gcc-sdm845.c +++ b/drivers/clk/qcom/gcc-sdm845.c @@ -115,8 +115,8 @@ static const char * const gcc_parent_names_6[] = { "core_bi_pll_test_se", }; -static const char * const gcc_parent_names_7[] = { - "bi_tcxo", +static const char * const gcc_parent_names_7_ao[] = { + "bi_tcxo_ao", "gpll0", "gpll0_out_even", "core_bi_pll_test_se", @@ -128,6 +128,12 @@ static const char * const gcc_parent_names_8[] = { "core_bi_pll_test_se", }; +static const char * const gcc_parent_names_8_ao[] = { + "bi_tcxo_ao", + "gpll0", + "core_bi_pll_test_se", +}; + static const struct parent_map gcc_parent_map_10[] = { { P_BI_TCXO, 0 }, { P_GPLL0_OUT_MAIN, 1 }, @@ -210,7 +216,7 @@ static struct clk_rcg2 gcc_cpuss_ahb_clk_src = { .freq_tbl = ftbl_gcc_cpuss_ahb_clk_src, .clkr.hw.init = &(struct clk_init_data){ .name = "gcc_cpuss_ahb_clk_src", - .parent_names = gcc_parent_names_7, + .parent_names = gcc_parent_names_7_ao, .num_parents = 4, .ops = &clk_rcg2_ops, }, @@ -229,7 +235,7 @@ static struct clk_rcg2 gcc_cpuss_rbcpr_clk_src = { .freq_tbl = ftbl_gcc_cpuss_rbcpr_clk_src, .clkr.hw.init = &(struct clk_init_data){ .name = "gcc_cpuss_rbcpr_clk_src", - .parent_names = gcc_parent_names_8, + .parent_names = gcc_parent_names_8_ao, .num_parents = 3, .ops = &clk_rcg2_ops, }, diff --git a/drivers/clk/ti/divider.c b/drivers/clk/ti/divider.c index 8d77090ad94a..0241450f3eb3 100644 --- a/drivers/clk/ti/divider.c +++ b/drivers/clk/ti/divider.c @@ -403,8 +403,10 @@ int ti_clk_parse_divider_data(int *div_table, int num_dividers, int max_div, num_dividers = i; tmp = kcalloc(valid_div + 1, sizeof(*tmp), GFP_KERNEL); - if (!tmp) + if (!tmp) { + *table = ERR_PTR(-ENOMEM); return -ENOMEM; + } valid_div = 0; *width = 0; @@ -439,6 +441,7 @@ struct clk_hw *ti_clk_build_component_div(struct ti_clk_divider *setup) { struct clk_omap_divider *div; struct clk_omap_reg *reg; + int ret; if (!setup) return NULL; @@ -458,6 +461,12 @@ struct clk_hw *ti_clk_build_component_div(struct ti_clk_divider *setup) div->flags |= CLK_DIVIDER_POWER_OF_TWO; div->table = _get_div_table_from_setup(setup, &div->width); + if (IS_ERR(div->table)) { + ret = PTR_ERR(div->table); + kfree(div); + return ERR_PTR(ret); + } + div->shift = setup->bit_shift; div->latch = -EINVAL; diff --git a/drivers/cpuidle/poll_state.c b/drivers/cpuidle/poll_state.c index b17d153e724f..23a1b27579a5 100644 --- a/drivers/cpuidle/poll_state.c +++ b/drivers/cpuidle/poll_state.c @@ -21,7 +21,7 @@ static int __cpuidle poll_idle(struct cpuidle_device *dev, local_irq_enable(); if (!current_set_polling_and_test()) { unsigned int loop_count = 0; - u64 limit = TICK_USEC; + u64 limit = TICK_NSEC; int i; for (i = 1; i < drv->state_count; i++) { diff --git a/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c b/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c index fe070d75c842..4c97478d44bd 100644 --- a/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c +++ b/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c @@ -537,6 +537,8 @@ static void process_response_list(struct nitrox_cmdq *cmdq) struct nitrox_device *ndev = cmdq->ndev; struct nitrox_softreq *sr; int req_completed = 0, err = 0, budget; + completion_t callback; + void *cb_arg; /* check all pending requests */ budget = atomic_read(&cmdq->pending_count); @@ -564,13 +566,13 @@ static void process_response_list(struct nitrox_cmdq *cmdq) smp_mb__after_atomic(); /* remove from response list */ response_list_del(sr, cmdq); - /* ORH error code */ err = READ_ONCE(*sr->resp.orh) & 0xff; - - if (sr->callback) - sr->callback(sr->cb_arg, err); + callback = sr->callback; + cb_arg = sr->cb_arg; softreq_destroy(sr); + if (callback) + callback(cb_arg, err); req_completed++; } diff --git a/drivers/crypto/ccree/cc_driver.c b/drivers/crypto/ccree/cc_driver.c index 8ada308d72ee..b0125ad65825 100644 --- a/drivers/crypto/ccree/cc_driver.c +++ b/drivers/crypto/ccree/cc_driver.c @@ -380,7 +380,7 @@ static int init_cc_resources(struct platform_device *plat_dev) rc = cc_ivgen_init(new_drvdata); if (rc) { dev_err(dev, "cc_ivgen_init failed\n"); - goto post_power_mgr_err; + goto post_buf_mgr_err; } /* Allocate crypto algs */ @@ -403,6 +403,9 @@ static int init_cc_resources(struct platform_device *plat_dev) goto post_hash_err; } + /* All set, we can allow autosuspend */ + cc_pm_go(new_drvdata); + /* If we got here and FIPS mode is enabled * it means all FIPS test passed, so let TEE * know we're good. @@ -417,8 +420,6 @@ post_cipher_err: cc_cipher_free(new_drvdata); post_ivgen_err: cc_ivgen_fini(new_drvdata); -post_power_mgr_err: - cc_pm_fini(new_drvdata); post_buf_mgr_err: cc_buffer_mgr_fini(new_drvdata); post_req_mgr_err: diff --git a/drivers/crypto/ccree/cc_pm.c b/drivers/crypto/ccree/cc_pm.c index d990f472e89f..6ff7e75ad90e 100644 --- a/drivers/crypto/ccree/cc_pm.c +++ b/drivers/crypto/ccree/cc_pm.c @@ -100,20 +100,19 @@ int cc_pm_put_suspend(struct device *dev) int cc_pm_init(struct cc_drvdata *drvdata) { - int rc = 0; struct device *dev = drvdata_to_dev(drvdata); /* must be before the enabling to avoid resdundent suspending */ pm_runtime_set_autosuspend_delay(dev, CC_SUSPEND_TIMEOUT); pm_runtime_use_autosuspend(dev); /* activate the PM module */ - rc = pm_runtime_set_active(dev); - if (rc) - return rc; - /* enable the PM module*/ - pm_runtime_enable(dev); + return pm_runtime_set_active(dev); +} - return rc; +/* enable the PM module*/ +void cc_pm_go(struct cc_drvdata *drvdata) +{ + pm_runtime_enable(drvdata_to_dev(drvdata)); } void cc_pm_fini(struct cc_drvdata *drvdata) diff --git a/drivers/crypto/ccree/cc_pm.h b/drivers/crypto/ccree/cc_pm.h index 020a5403c58b..f62624357020 100644 --- a/drivers/crypto/ccree/cc_pm.h +++ b/drivers/crypto/ccree/cc_pm.h @@ -16,6 +16,7 @@ extern const struct dev_pm_ops ccree_pm; int cc_pm_init(struct cc_drvdata *drvdata); +void cc_pm_go(struct cc_drvdata *drvdata); void cc_pm_fini(struct cc_drvdata *drvdata); int cc_pm_suspend(struct device *dev); int cc_pm_resume(struct device *dev); @@ -29,6 +30,8 @@ static inline int cc_pm_init(struct cc_drvdata *drvdata) return 0; } +static void cc_pm_go(struct cc_drvdata *drvdata) {} + static inline void cc_pm_fini(struct cc_drvdata *drvdata) {} static inline int cc_pm_suspend(struct device *dev) diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c index 4e557684f792..fe69dccfa0c0 100644 --- a/drivers/dma/at_xdmac.c +++ b/drivers/dma/at_xdmac.c @@ -203,6 +203,7 @@ struct at_xdmac_chan { u32 save_cim; u32 save_cnda; u32 save_cndc; + u32 irq_status; unsigned long status; struct tasklet_struct tasklet; struct dma_slave_config sconfig; @@ -1580,8 +1581,8 @@ static void at_xdmac_tasklet(unsigned long data) struct at_xdmac_desc *desc; u32 error_mask; - dev_dbg(chan2dev(&atchan->chan), "%s: status=0x%08lx\n", - __func__, atchan->status); + dev_dbg(chan2dev(&atchan->chan), "%s: status=0x%08x\n", + __func__, atchan->irq_status); error_mask = AT_XDMAC_CIS_RBEIS | AT_XDMAC_CIS_WBEIS @@ -1589,15 +1590,15 @@ static void at_xdmac_tasklet(unsigned long data) if (at_xdmac_chan_is_cyclic(atchan)) { at_xdmac_handle_cyclic(atchan); - } else if ((atchan->status & AT_XDMAC_CIS_LIS) - || (atchan->status & error_mask)) { + } else if ((atchan->irq_status & AT_XDMAC_CIS_LIS) + || (atchan->irq_status & error_mask)) { struct dma_async_tx_descriptor *txd; - if (atchan->status & AT_XDMAC_CIS_RBEIS) + if (atchan->irq_status & AT_XDMAC_CIS_RBEIS) dev_err(chan2dev(&atchan->chan), "read bus error!!!"); - if (atchan->status & AT_XDMAC_CIS_WBEIS) + if (atchan->irq_status & AT_XDMAC_CIS_WBEIS) dev_err(chan2dev(&atchan->chan), "write bus error!!!"); - if (atchan->status & AT_XDMAC_CIS_ROIS) + if (atchan->irq_status & AT_XDMAC_CIS_ROIS) dev_err(chan2dev(&atchan->chan), "request overflow error!!!"); spin_lock(&atchan->lock); @@ -1652,7 +1653,7 @@ static irqreturn_t at_xdmac_interrupt(int irq, void *dev_id) atchan = &atxdmac->chan[i]; chan_imr = at_xdmac_chan_read(atchan, AT_XDMAC_CIM); chan_status = at_xdmac_chan_read(atchan, AT_XDMAC_CIS); - atchan->status = chan_status & chan_imr; + atchan->irq_status = chan_status & chan_imr; dev_vdbg(atxdmac->dma.dev, "%s: chan%d: imr=0x%x, status=0x%x\n", __func__, i, chan_imr, chan_status); @@ -1666,7 +1667,7 @@ static irqreturn_t at_xdmac_interrupt(int irq, void *dev_id) at_xdmac_chan_read(atchan, AT_XDMAC_CDA), at_xdmac_chan_read(atchan, AT_XDMAC_CUBC)); - if (atchan->status & (AT_XDMAC_CIS_RBEIS | AT_XDMAC_CIS_WBEIS)) + if (atchan->irq_status & (AT_XDMAC_CIS_RBEIS | AT_XDMAC_CIS_WBEIS)) at_xdmac_write(atxdmac, AT_XDMAC_GD, atchan->mask); tasklet_schedule(&atchan->tasklet); diff --git a/drivers/dma/bcm2835-dma.c b/drivers/dma/bcm2835-dma.c index 1a44c8086d77..ae10f5614f95 100644 --- a/drivers/dma/bcm2835-dma.c +++ b/drivers/dma/bcm2835-dma.c @@ -406,38 +406,32 @@ static void bcm2835_dma_fill_cb_chain_with_sg( } } -static int bcm2835_dma_abort(void __iomem *chan_base) +static int bcm2835_dma_abort(struct bcm2835_chan *c) { - unsigned long cs; + void __iomem *chan_base = c->chan_base; long int timeout = 10000; - cs = readl(chan_base + BCM2835_DMA_CS); - if (!(cs & BCM2835_DMA_ACTIVE)) + /* + * A zero control block address means the channel is idle. + * (The ACTIVE flag in the CS register is not a reliable indicator.) + */ + if (!readl(chan_base + BCM2835_DMA_ADDR)) return 0; /* Write 0 to the active bit - Pause the DMA */ writel(0, chan_base + BCM2835_DMA_CS); /* Wait for any current AXI transfer to complete */ - while ((cs & BCM2835_DMA_ISPAUSED) && --timeout) { + while ((readl(chan_base + BCM2835_DMA_CS) & + BCM2835_DMA_WAITING_FOR_WRITES) && --timeout) cpu_relax(); - cs = readl(chan_base + BCM2835_DMA_CS); - } - /* We'll un-pause when we set of our next DMA */ + /* Peripheral might be stuck and fail to signal AXI write responses */ if (!timeout) - return -ETIMEDOUT; - - if (!(cs & BCM2835_DMA_ACTIVE)) - return 0; - - /* Terminate the control block chain */ - writel(0, chan_base + BCM2835_DMA_NEXTCB); - - /* Abort the whole DMA */ - writel(BCM2835_DMA_ABORT | BCM2835_DMA_ACTIVE, - chan_base + BCM2835_DMA_CS); + dev_err(c->vc.chan.device->dev, + "failed to complete outstanding writes\n"); + writel(BCM2835_DMA_RESET, chan_base + BCM2835_DMA_CS); return 0; } @@ -476,8 +470,15 @@ static irqreturn_t bcm2835_dma_callback(int irq, void *data) spin_lock_irqsave(&c->vc.lock, flags); - /* Acknowledge interrupt */ - writel(BCM2835_DMA_INT, c->chan_base + BCM2835_DMA_CS); + /* + * Clear the INT flag to receive further interrupts. Keep the channel + * active in case the descriptor is cyclic or in case the client has + * already terminated the descriptor and issued a new one. (May happen + * if this IRQ handler is threaded.) If the channel is finished, it + * will remain idle despite the ACTIVE flag being set. + */ + writel(BCM2835_DMA_INT | BCM2835_DMA_ACTIVE, + c->chan_base + BCM2835_DMA_CS); d = c->desc; @@ -485,11 +486,7 @@ static irqreturn_t bcm2835_dma_callback(int irq, void *data) if (d->cyclic) { /* call the cyclic callback */ vchan_cyclic_callback(&d->vd); - - /* Keep the DMA engine running */ - writel(BCM2835_DMA_ACTIVE, - c->chan_base + BCM2835_DMA_CS); - } else { + } else if (!readl(c->chan_base + BCM2835_DMA_ADDR)) { vchan_cookie_complete(&c->desc->vd); bcm2835_dma_start_desc(c); } @@ -779,7 +776,6 @@ static int bcm2835_dma_terminate_all(struct dma_chan *chan) struct bcm2835_chan *c = to_bcm2835_dma_chan(chan); struct bcm2835_dmadev *d = to_bcm2835_dma_dev(c->vc.chan.device); unsigned long flags; - int timeout = 10000; LIST_HEAD(head); spin_lock_irqsave(&c->vc.lock, flags); @@ -789,27 +785,11 @@ static int bcm2835_dma_terminate_all(struct dma_chan *chan) list_del_init(&c->node); spin_unlock(&d->lock); - /* - * Stop DMA activity: we assume the callback will not be called - * after bcm_dma_abort() returns (even if it does, it will see - * c->desc is NULL and exit.) - */ + /* stop DMA activity */ if (c->desc) { vchan_terminate_vdesc(&c->desc->vd); c->desc = NULL; - bcm2835_dma_abort(c->chan_base); - - /* Wait for stopping */ - while (--timeout) { - if (!(readl(c->chan_base + BCM2835_DMA_CS) & - BCM2835_DMA_ACTIVE)) - break; - - cpu_relax(); - } - - if (!timeout) - dev_err(d->ddev.dev, "DMA transfer could not be terminated\n"); + bcm2835_dma_abort(c); } vchan_get_all_descriptors(&c->vc, &head); diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c index 2eea4ef72915..6511928b4cdf 100644 --- a/drivers/dma/dmatest.c +++ b/drivers/dma/dmatest.c @@ -711,11 +711,9 @@ static int dmatest_func(void *data) srcs[i] = um->addr[i] + src_off; ret = dma_mapping_error(dev->dev, um->addr[i]); if (ret) { - dmaengine_unmap_put(um); result("src mapping error", total_tests, src_off, dst_off, len, ret); - failed_tests++; - continue; + goto error_unmap_continue; } um->to_cnt++; } @@ -730,11 +728,9 @@ static int dmatest_func(void *data) DMA_BIDIRECTIONAL); ret = dma_mapping_error(dev->dev, dsts[i]); if (ret) { - dmaengine_unmap_put(um); result("dst mapping error", total_tests, src_off, dst_off, len, ret); - failed_tests++; - continue; + goto error_unmap_continue; } um->bidi_cnt++; } @@ -762,12 +758,10 @@ static int dmatest_func(void *data) } if (!tx) { - dmaengine_unmap_put(um); result("prep error", total_tests, src_off, dst_off, len, ret); msleep(100); - failed_tests++; - continue; + goto error_unmap_continue; } done->done = false; @@ -776,12 +770,10 @@ static int dmatest_func(void *data) cookie = tx->tx_submit(tx); if (dma_submit_error(cookie)) { - dmaengine_unmap_put(um); result("submit error", total_tests, src_off, dst_off, len, ret); msleep(100); - failed_tests++; - continue; + goto error_unmap_continue; } dma_async_issue_pending(chan); @@ -790,22 +782,20 @@ static int dmatest_func(void *data) status = dma_async_is_tx_complete(chan, cookie, NULL, NULL); - dmaengine_unmap_put(um); - if (!done->done) { result("test timed out", total_tests, src_off, dst_off, len, 0); - failed_tests++; - continue; + goto error_unmap_continue; } else if (status != DMA_COMPLETE) { result(status == DMA_ERROR ? "completion error status" : "completion busy status", total_tests, src_off, dst_off, len, ret); - failed_tests++; - continue; + goto error_unmap_continue; } + dmaengine_unmap_put(um); + if (params->noverify) { verbose_result("test passed", total_tests, src_off, dst_off, len, 0); @@ -846,6 +836,12 @@ static int dmatest_func(void *data) verbose_result("test passed", total_tests, src_off, dst_off, len, 0); } + + continue; + +error_unmap_continue: + dmaengine_unmap_put(um); + failed_tests++; } ktime = ktime_sub(ktime_get(), ktime); ktime = ktime_sub(ktime, comparetime); diff --git a/drivers/dma/imx-dma.c b/drivers/dma/imx-dma.c index c2fff3f6c9ca..4a09af3cd546 100644 --- a/drivers/dma/imx-dma.c +++ b/drivers/dma/imx-dma.c @@ -618,7 +618,7 @@ static void imxdma_tasklet(unsigned long data) { struct imxdma_channel *imxdmac = (void *)data; struct imxdma_engine *imxdma = imxdmac->imxdma; - struct imxdma_desc *desc; + struct imxdma_desc *desc, *next_desc; unsigned long flags; spin_lock_irqsave(&imxdma->lock, flags); @@ -648,10 +648,10 @@ static void imxdma_tasklet(unsigned long data) list_move_tail(imxdmac->ld_active.next, &imxdmac->ld_free); if (!list_empty(&imxdmac->ld_queue)) { - desc = list_first_entry(&imxdmac->ld_queue, struct imxdma_desc, - node); + next_desc = list_first_entry(&imxdmac->ld_queue, + struct imxdma_desc, node); list_move_tail(imxdmac->ld_queue.next, &imxdmac->ld_active); - if (imxdma_xfer_desc(desc) < 0) + if (imxdma_xfer_desc(next_desc) < 0) dev_warn(imxdma->dev, "%s: channel: %d couldn't xfer desc\n", __func__, imxdmac->channel); } diff --git a/drivers/edac/altera_edac.h b/drivers/edac/altera_edac.h index 4213cb0bb2a7..f8664bac9fa8 100644 --- a/drivers/edac/altera_edac.h +++ b/drivers/edac/altera_edac.h @@ -295,8 +295,8 @@ struct altr_sdram_mc_data { #define S10_SYSMGR_ECC_INTSTAT_DERR_OFST 0xA0 /* Sticky registers for Uncorrected Errors */ -#define S10_SYSMGR_UE_VAL_OFST 0x120 -#define S10_SYSMGR_UE_ADDR_OFST 0x124 +#define S10_SYSMGR_UE_VAL_OFST 0x220 +#define S10_SYSMGR_UE_ADDR_OFST 0x224 #define S10_DDR0_IRQ_MASK BIT(16) diff --git a/drivers/firmware/arm_scmi/bus.c b/drivers/firmware/arm_scmi/bus.c index 472c88ae1c0f..92f843eaf1e0 100644 --- a/drivers/firmware/arm_scmi/bus.c +++ b/drivers/firmware/arm_scmi/bus.c @@ -119,6 +119,11 @@ void scmi_driver_unregister(struct scmi_driver *driver) } EXPORT_SYMBOL_GPL(scmi_driver_unregister); +static void scmi_device_release(struct device *dev) +{ + kfree(to_scmi_dev(dev)); +} + struct scmi_device * scmi_device_create(struct device_node *np, struct device *parent, int protocol) { @@ -138,6 +143,7 @@ scmi_device_create(struct device_node *np, struct device *parent, int protocol) scmi_dev->dev.parent = parent; scmi_dev->dev.of_node = np; scmi_dev->dev.bus = &scmi_bus_type; + scmi_dev->dev.release = scmi_device_release; dev_set_name(&scmi_dev->dev, "scmi_dev.%d", id); retval = device_register(&scmi_dev->dev); @@ -156,9 +162,8 @@ free_mem: void scmi_device_destroy(struct scmi_device *scmi_dev) { scmi_handle_put(scmi_dev->handle); - device_unregister(&scmi_dev->dev); ida_simple_remove(&scmi_bus_id, scmi_dev->id); - kfree(scmi_dev); + device_unregister(&scmi_dev->dev); } void scmi_set_handle(struct scmi_device *scmi_dev) diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c index 23ea1ed409d1..352bd2473162 100644 --- a/drivers/firmware/efi/arm-runtime.c +++ b/drivers/firmware/efi/arm-runtime.c @@ -37,8 +37,9 @@ extern u64 efi_system_table; static struct ptdump_info efi_ptdump_info = { .mm = &efi_mm, .markers = (struct addr_marker[]){ - { 0, "UEFI runtime start" }, - { DEFAULT_MAP_WINDOW_64, "UEFI runtime end" } + { 0, "UEFI runtime start" }, + { DEFAULT_MAP_WINDOW_64, "UEFI runtime end" }, + { -1, NULL } }, .base_addr = 0, }; diff --git a/drivers/fpga/stratix10-soc.c b/drivers/fpga/stratix10-soc.c index a1a09e04fab8..13851b3d1c56 100644 --- a/drivers/fpga/stratix10-soc.c +++ b/drivers/fpga/stratix10-soc.c @@ -508,14 +508,11 @@ static int __init s10_init(void) return -ENODEV; np = of_find_matching_node(fw_np, s10_of_match); - if (!np) { - of_node_put(fw_np); + if (!np) return -ENODEV; - } of_node_put(np); ret = of_platform_populate(fw_np, s10_of_match, NULL, NULL); - of_node_put(fw_np); if (ret) return ret; diff --git a/drivers/gpio/gpio-altera-a10sr.c b/drivers/gpio/gpio-altera-a10sr.c index 6b11f1314248..7f9e0304b510 100644 --- a/drivers/gpio/gpio-altera-a10sr.c +++ b/drivers/gpio/gpio-altera-a10sr.c @@ -66,8 +66,10 @@ static int altr_a10sr_gpio_direction_input(struct gpio_chip *gc, static int altr_a10sr_gpio_direction_output(struct gpio_chip *gc, unsigned int nr, int value) { - if (nr <= (ALTR_A10SR_OUT_VALID_RANGE_HI - ALTR_A10SR_LED_VALID_SHIFT)) + if (nr <= (ALTR_A10SR_OUT_VALID_RANGE_HI - ALTR_A10SR_LED_VALID_SHIFT)) { + altr_a10sr_gpio_set(gc, nr, value); return 0; + } return -EINVAL; } diff --git a/drivers/gpio/gpio-eic-sprd.c b/drivers/gpio/gpio-eic-sprd.c index e0d6a0a7bc69..e41223c05f6e 100644 --- a/drivers/gpio/gpio-eic-sprd.c +++ b/drivers/gpio/gpio-eic-sprd.c @@ -180,7 +180,18 @@ static void sprd_eic_free(struct gpio_chip *chip, unsigned int offset) static int sprd_eic_get(struct gpio_chip *chip, unsigned int offset) { - return sprd_eic_read(chip, offset, SPRD_EIC_DBNC_DATA); + struct sprd_eic *sprd_eic = gpiochip_get_data(chip); + + switch (sprd_eic->type) { + case SPRD_EIC_DEBOUNCE: + return sprd_eic_read(chip, offset, SPRD_EIC_DBNC_DATA); + case SPRD_EIC_ASYNC: + return sprd_eic_read(chip, offset, SPRD_EIC_ASYNC_DATA); + case SPRD_EIC_SYNC: + return sprd_eic_read(chip, offset, SPRD_EIC_SYNC_DATA); + default: + return -ENOTSUPP; + } } static int sprd_eic_direction_input(struct gpio_chip *chip, unsigned int offset) @@ -368,6 +379,7 @@ static int sprd_eic_irq_set_type(struct irq_data *data, unsigned int flow_type) irq_set_handler_locked(data, handle_edge_irq); break; case IRQ_TYPE_EDGE_BOTH: + sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTMODE, 0); sprd_eic_update(chip, offset, SPRD_EIC_ASYNC_INTBOTH, 1); irq_set_handler_locked(data, handle_edge_irq); break; diff --git a/drivers/gpio/gpio-pcf857x.c b/drivers/gpio/gpio-pcf857x.c index adf72dda25a2..68a35b65925a 100644 --- a/drivers/gpio/gpio-pcf857x.c +++ b/drivers/gpio/gpio-pcf857x.c @@ -84,6 +84,7 @@ MODULE_DEVICE_TABLE(of, pcf857x_of_table); */ struct pcf857x { struct gpio_chip chip; + struct irq_chip irqchip; struct i2c_client *client; struct mutex lock; /* protect 'out' */ unsigned out; /* software latch */ @@ -252,18 +253,6 @@ static void pcf857x_irq_bus_sync_unlock(struct irq_data *data) mutex_unlock(&gpio->lock); } -static struct irq_chip pcf857x_irq_chip = { - .name = "pcf857x", - .irq_enable = pcf857x_irq_enable, - .irq_disable = pcf857x_irq_disable, - .irq_ack = noop, - .irq_mask = noop, - .irq_unmask = noop, - .irq_set_wake = pcf857x_irq_set_wake, - .irq_bus_lock = pcf857x_irq_bus_lock, - .irq_bus_sync_unlock = pcf857x_irq_bus_sync_unlock, -}; - /*-------------------------------------------------------------------------*/ static int pcf857x_probe(struct i2c_client *client, @@ -376,8 +365,17 @@ static int pcf857x_probe(struct i2c_client *client, /* Enable irqchip if we have an interrupt */ if (client->irq) { + gpio->irqchip.name = "pcf857x", + gpio->irqchip.irq_enable = pcf857x_irq_enable, + gpio->irqchip.irq_disable = pcf857x_irq_disable, + gpio->irqchip.irq_ack = noop, + gpio->irqchip.irq_mask = noop, + gpio->irqchip.irq_unmask = noop, + gpio->irqchip.irq_set_wake = pcf857x_irq_set_wake, + gpio->irqchip.irq_bus_lock = pcf857x_irq_bus_lock, + gpio->irqchip.irq_bus_sync_unlock = pcf857x_irq_bus_sync_unlock, status = gpiochip_irqchip_add_nested(&gpio->chip, - &pcf857x_irq_chip, + &gpio->irqchip, 0, handle_level_irq, IRQ_TYPE_NONE); if (status) { @@ -392,7 +390,7 @@ static int pcf857x_probe(struct i2c_client *client, if (status) goto fail; - gpiochip_set_nested_irqchip(&gpio->chip, &pcf857x_irq_chip, + gpiochip_set_nested_irqchip(&gpio->chip, &gpio->irqchip, client->irq); gpio->irq_parent = client->irq; } diff --git a/drivers/gpio/gpio-vf610.c b/drivers/gpio/gpio-vf610.c index 1b79ebcfce3e..541fa6ac399d 100644 --- a/drivers/gpio/gpio-vf610.c +++ b/drivers/gpio/gpio-vf610.c @@ -253,6 +253,7 @@ static int vf610_gpio_probe(struct platform_device *pdev) struct vf610_gpio_port *port; struct resource *iores; struct gpio_chip *gc; + int i; int ret; port = devm_kzalloc(&pdev->dev, sizeof(*port), GFP_KERNEL); @@ -319,6 +320,10 @@ static int vf610_gpio_probe(struct platform_device *pdev) if (ret < 0) return ret; + /* Mask all GPIO interrupts */ + for (i = 0; i < gc->ngpio; i++) + vf610_gpio_writel(0, port->base + PORT_PCR(i)); + /* Clear the interrupt status register for all GPIO's */ vf610_gpio_writel(~0, port->base + PORT_ISFR); diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 1651d7f0a303..d1adfdf50fb3 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -828,7 +828,14 @@ static irqreturn_t lineevent_irq_thread(int irq, void *p) /* Do not leak kernel stack to userspace */ memset(&ge, 0, sizeof(ge)); - ge.timestamp = le->timestamp; + /* + * We may be running from a nested threaded interrupt in which case + * we didn't get the timestamp from lineevent_irq_handler(). + */ + if (!le->timestamp) + ge.timestamp = ktime_get_real_ns(); + else + ge.timestamp = le->timestamp; if (le->eflags & GPIOEVENT_REQUEST_RISING_EDGE && le->eflags & GPIOEVENT_REQUEST_FALLING_EDGE) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c index 6896dec97fc7..0ed41a9d2d77 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c @@ -1686,7 +1686,8 @@ static umode_t hwmon_attributes_visible(struct kobject *kobj, effective_mode &= ~S_IWUSR; if ((adev->flags & AMD_IS_APU) && - (attr == &sensor_dev_attr_power1_cap_max.dev_attr.attr || + (attr == &sensor_dev_attr_power1_average.dev_attr.attr || + attr == &sensor_dev_attr_power1_cap_max.dev_attr.attr || attr == &sensor_dev_attr_power1_cap_min.dev_attr.attr|| attr == &sensor_dev_attr_power1_cap.dev_attr.attr)) return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c index 71913a18d142..a38e0fb4a6fe 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c @@ -38,6 +38,7 @@ #include "amdgpu_gem.h" #include <drm/amdgpu_drm.h> #include <linux/dma-buf.h> +#include <linux/dma-fence-array.h> /** * amdgpu_gem_prime_get_sg_table - &drm_driver.gem_prime_get_sg_table @@ -187,6 +188,48 @@ error: return ERR_PTR(ret); } +static int +__reservation_object_make_exclusive(struct reservation_object *obj) +{ + struct dma_fence **fences; + unsigned int count; + int r; + + if (!reservation_object_get_list(obj)) /* no shared fences to convert */ + return 0; + + r = reservation_object_get_fences_rcu(obj, NULL, &count, &fences); + if (r) + return r; + + if (count == 0) { + /* Now that was unexpected. */ + } else if (count == 1) { + reservation_object_add_excl_fence(obj, fences[0]); + dma_fence_put(fences[0]); + kfree(fences); + } else { + struct dma_fence_array *array; + + array = dma_fence_array_create(count, fences, + dma_fence_context_alloc(1), 0, + false); + if (!array) + goto err_fences_put; + + reservation_object_add_excl_fence(obj, &array->base); + dma_fence_put(&array->base); + } + + return 0; + +err_fences_put: + while (count--) + dma_fence_put(fences[count]); + kfree(fences); + return -ENOMEM; +} + /** * amdgpu_gem_map_attach - &dma_buf_ops.attach implementation * @dma_buf: Shared DMA buffer @@ -218,16 +261,16 @@ static int amdgpu_gem_map_attach(struct dma_buf *dma_buf, if (attach->dev->driver != adev->dev->driver) { /* - * Wait for all shared fences to complete before we switch to future - * use of exclusive fence on this prime shared bo. + * We only create shared fences for internal use, but importers + * of the dmabuf rely on exclusive fences for implicitly + * tracking write hazards. As any of the current fences may + * correspond to a write, we need to convert all existing + * fences on the reservation object into a single exclusive + * fence. */ - r = reservation_object_wait_timeout_rcu(bo->tbo.resv, - true, false, - MAX_SCHEDULE_TIMEOUT); - if (unlikely(r < 0)) { - DRM_DEBUG_PRIME("Fence wait failed: %li\n", r); + r = __reservation_object_make_exclusive(bo->tbo.resv); + if (r) goto error_unreserve; - } } /* pin buffer into GTT */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 8fab0d637ee5..3a9b48b227ac 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -90,8 +90,10 @@ static int psp_sw_fini(void *handle) adev->psp.sos_fw = NULL; release_firmware(adev->psp.asd_fw); adev->psp.asd_fw = NULL; - release_firmware(adev->psp.ta_fw); - adev->psp.ta_fw = NULL; + if (adev->psp.ta_fw) { + release_firmware(adev->psp.ta_fw); + adev->psp.ta_fw = NULL; + } return 0; } @@ -435,6 +437,9 @@ static int psp_xgmi_initialize(struct psp_context *psp) struct ta_xgmi_shared_memory *xgmi_cmd; int ret; + if (!psp->adev->psp.ta_fw) + return -ENOENT; + if (!psp->xgmi_context.initialized) { ret = psp_xgmi_init_shared_buf(psp); if (ret) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index d2ea5ce2cefb..7c108e687683 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -3363,14 +3363,15 @@ void amdgpu_vm_get_task_info(struct amdgpu_device *adev, unsigned int pasid, struct amdgpu_task_info *task_info) { struct amdgpu_vm *vm; + unsigned long flags; - spin_lock(&adev->vm_manager.pasid_lock); + spin_lock_irqsave(&adev->vm_manager.pasid_lock, flags); vm = idr_find(&adev->vm_manager.pasid_idr, pasid); if (vm) *task_info = vm->task_info; - spin_unlock(&adev->vm_manager.pasid_lock); + spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, flags); } /** diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c index 4cd31a276dcd..186db182f924 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c @@ -93,7 +93,20 @@ static void nbio_v7_4_enable_doorbell_aperture(struct amdgpu_device *adev, static void nbio_v7_4_enable_doorbell_selfring_aperture(struct amdgpu_device *adev, bool enable) { + u32 tmp = 0; + if (enable) { + tmp = REG_SET_FIELD(tmp, DOORBELL_SELFRING_GPA_APER_CNTL, DOORBELL_SELFRING_GPA_APER_EN, 1) | + REG_SET_FIELD(tmp, DOORBELL_SELFRING_GPA_APER_CNTL, DOORBELL_SELFRING_GPA_APER_MODE, 1) | + REG_SET_FIELD(tmp, DOORBELL_SELFRING_GPA_APER_CNTL, DOORBELL_SELFRING_GPA_APER_SIZE, 0); + + WREG32_SOC15(NBIO, 0, mmDOORBELL_SELFRING_GPA_APER_BASE_LOW, + lower_32_bits(adev->doorbell.base)); + WREG32_SOC15(NBIO, 0, mmDOORBELL_SELFRING_GPA_APER_BASE_HIGH, + upper_32_bits(adev->doorbell.base)); + } + + WREG32_SOC15(NBIO, 0, mmDOORBELL_SELFRING_GPA_APER_CNTL, tmp); } static void nbio_v7_4_ih_doorbell_range(struct amdgpu_device *adev, diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c index 0c6e7f9b143f..189fcb004579 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v11_0.c @@ -152,18 +152,22 @@ static int psp_v11_0_init_microcode(struct psp_context *psp) snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ta.bin", chip_name); err = request_firmware(&adev->psp.ta_fw, fw_name, adev->dev); - if (err) - goto out2; - - err = amdgpu_ucode_validate(adev->psp.ta_fw); - if (err) - goto out2; - - ta_hdr = (const struct ta_firmware_header_v1_0 *)adev->psp.ta_fw->data; - adev->psp.ta_xgmi_ucode_version = le32_to_cpu(ta_hdr->ta_xgmi_ucode_version); - adev->psp.ta_xgmi_ucode_size = le32_to_cpu(ta_hdr->ta_xgmi_size_bytes); - adev->psp.ta_xgmi_start_addr = (uint8_t *)ta_hdr + - le32_to_cpu(ta_hdr->header.ucode_array_offset_bytes); + if (err) { + release_firmware(adev->psp.ta_fw); + adev->psp.ta_fw = NULL; + dev_info(adev->dev, + "psp v11.0: Failed to load firmware \"%s\"\n", fw_name); + } else { + err = amdgpu_ucode_validate(adev->psp.ta_fw); + if (err) + goto out2; + + ta_hdr = (const struct ta_firmware_header_v1_0 *)adev->psp.ta_fw->data; + adev->psp.ta_xgmi_ucode_version = le32_to_cpu(ta_hdr->ta_xgmi_ucode_version); + adev->psp.ta_xgmi_ucode_size = le32_to_cpu(ta_hdr->ta_xgmi_size_bytes); + adev->psp.ta_xgmi_start_addr = (uint8_t *)ta_hdr + + le32_to_cpu(ta_hdr->header.ucode_array_offset_bytes); + } return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.c b/drivers/gpu/drm/amd/amdgpu/soc15.c index 8849b74078d6..9b639974c70c 100644 --- a/drivers/gpu/drm/amd/amdgpu/soc15.c +++ b/drivers/gpu/drm/amd/amdgpu/soc15.c @@ -729,11 +729,13 @@ static int soc15_common_early_init(void *handle) case CHIP_RAVEN: adev->asic_funcs = &soc15_asic_funcs; if (adev->rev_id >= 0x8) - adev->external_rev_id = adev->rev_id + 0x81; + adev->external_rev_id = adev->rev_id + 0x79; else if (adev->pdev->device == 0x15d8) adev->external_rev_id = adev->rev_id + 0x41; + else if (adev->rev_id == 1) + adev->external_rev_id = adev->rev_id + 0x20; else - adev->external_rev_id = 0x1; + adev->external_rev_id = adev->rev_id + 0x01; if (adev->rev_id >= 0x8) { adev->cg_flags = AMD_CG_SUPPORT_GFX_MGCG | diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c index 5d85ff341385..2e7c44955f43 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c @@ -863,7 +863,7 @@ static int kfd_fill_mem_info_for_cpu(int numa_node_id, int *avail_size, return 0; } -#if CONFIG_X86_64 +#ifdef CONFIG_X86_64 static int kfd_fill_iolink_info_for_cpu(int numa_node_id, int *avail_size, uint32_t *num_entries, struct crat_subtype_iolink *sub_type_hdr) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index f4fa40c387d3..0b392bfca284 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -4082,7 +4082,8 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm, } if (connector_type == DRM_MODE_CONNECTOR_HDMIA || - connector_type == DRM_MODE_CONNECTOR_DisplayPort) { + connector_type == DRM_MODE_CONNECTOR_DisplayPort || + connector_type == DRM_MODE_CONNECTOR_eDP) { drm_connector_attach_vrr_capable_property( &aconnector->base); } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c index 9a7ac58eb18e..ddd75a4d8ba5 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c @@ -671,6 +671,25 @@ static ssize_t dp_phy_test_pattern_debugfs_write(struct file *f, const char __us return bytes_from_user; } +/* + * Returns the min and max vrr vfreq through the connector's debugfs file. + * Example usage: cat /sys/kernel/debug/dri/0/DP-1/vrr_range + */ +static int vrr_range_show(struct seq_file *m, void *data) +{ + struct drm_connector *connector = m->private; + struct amdgpu_dm_connector *aconnector = to_amdgpu_dm_connector(connector); + + if (connector->status != connector_status_connected) + return -ENODEV; + + seq_printf(m, "Min: %u\n", (unsigned int)aconnector->min_vfreq); + seq_printf(m, "Max: %u\n", (unsigned int)aconnector->max_vfreq); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(vrr_range); + static const struct file_operations dp_link_settings_debugfs_fops = { .owner = THIS_MODULE, .read = dp_link_settings_read, @@ -697,7 +716,8 @@ static const struct { } dp_debugfs_entries[] = { {"link_settings", &dp_link_settings_debugfs_fops}, {"phy_settings", &dp_phy_settings_debugfs_fop}, - {"test_pattern", &dp_phy_test_pattern_fops} + {"test_pattern", &dp_phy_test_pattern_fops}, + {"vrr_range", &vrr_range_fops} }; int connector_debugfs_init(struct amdgpu_dm_connector *connector) diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clk_mgr.c index afd287f08bc9..19801bdba0d2 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clk_mgr.c @@ -591,7 +591,15 @@ static void dce11_pplib_apply_display_requirements( dc, context->bw.dce.sclk_khz); - pp_display_cfg->min_dcfclock_khz = pp_display_cfg->min_engine_clock_khz; + /* + * As workaround for >4x4K lightup set dcfclock to min_engine_clock value. + * This is not required for less than 5 displays, + * thus don't request decfclk in dc to avoid impact + * on power saving. + * + */ + pp_display_cfg->min_dcfclock_khz = (context->stream_count > 4)? + pp_display_cfg->min_engine_clock_khz : 0; pp_display_cfg->min_engine_clock_deep_sleep_khz = context->bw.dce.sclk_deep_sleep_khz; diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c index f95c5f50eb0f..5273de3c5b98 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c @@ -1033,6 +1033,7 @@ static int smu10_get_clock_by_type_with_latency(struct pp_hwmgr *hwmgr, break; case amd_pp_dpp_clock: pclk_vol_table = pinfo->vdd_dep_on_dppclk; + break; default: return -EINVAL; } diff --git a/drivers/gpu/drm/drm_lease.c b/drivers/gpu/drm/drm_lease.c index 99cba8ea5d82..5df1256618cc 100644 --- a/drivers/gpu/drm/drm_lease.c +++ b/drivers/gpu/drm/drm_lease.c @@ -528,7 +528,8 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev, object_count = cl->object_count; - object_ids = memdup_user(u64_to_user_ptr(cl->object_ids), object_count * sizeof(__u32)); + object_ids = memdup_user(u64_to_user_ptr(cl->object_ids), + array_size(object_count, sizeof(__u32))); if (IS_ERR(object_ids)) return PTR_ERR(object_ids); diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c index 24a750436559..f91e02c87fd8 100644 --- a/drivers/gpu/drm/drm_modes.c +++ b/drivers/gpu/drm/drm_modes.c @@ -758,7 +758,7 @@ int drm_mode_hsync(const struct drm_display_mode *mode) if (mode->hsync) return mode->hsync; - if (mode->htotal < 0) + if (mode->htotal <= 0) return 0; calc_val = (mode->clock * 1000) / mode->htotal; /* hsync in Hz */ diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 216f52b744a6..c882ea94172c 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -1824,6 +1824,16 @@ i915_gem_sw_finish_ioctl(struct drm_device *dev, void *data, return 0; } +static inline bool +__vma_matches(struct vm_area_struct *vma, struct file *filp, + unsigned long addr, unsigned long size) +{ + if (vma->vm_file != filp) + return false; + + return vma->vm_start == addr && (vma->vm_end - vma->vm_start) == size; +} + /** * i915_gem_mmap_ioctl - Maps the contents of an object, returning the address * it is mapped to. @@ -1882,7 +1892,7 @@ i915_gem_mmap_ioctl(struct drm_device *dev, void *data, return -EINTR; } vma = find_vma(mm, addr); - if (vma) + if (vma && __vma_matches(vma, obj->base.filp, addr, args->size)) vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags)); else diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c index d6c8f8fdfda5..017fc602a10e 100644 --- a/drivers/gpu/drm/i915/i915_pmu.c +++ b/drivers/gpu/drm/i915/i915_pmu.c @@ -594,7 +594,8 @@ static void i915_pmu_enable(struct perf_event *event) * Update the bitmask of enabled events and increment * the event reference counter. */ - GEM_BUG_ON(bit >= I915_PMU_MASK_BITS); + BUILD_BUG_ON(ARRAY_SIZE(i915->pmu.enable_count) != I915_PMU_MASK_BITS); + GEM_BUG_ON(bit >= ARRAY_SIZE(i915->pmu.enable_count)); GEM_BUG_ON(i915->pmu.enable_count[bit] == ~0); i915->pmu.enable |= BIT_ULL(bit); i915->pmu.enable_count[bit]++; @@ -615,11 +616,16 @@ static void i915_pmu_enable(struct perf_event *event) engine = intel_engine_lookup_user(i915, engine_event_class(event), engine_event_instance(event)); - GEM_BUG_ON(!engine); - engine->pmu.enable |= BIT(sample); - GEM_BUG_ON(sample >= I915_PMU_SAMPLE_BITS); + BUILD_BUG_ON(ARRAY_SIZE(engine->pmu.enable_count) != + I915_ENGINE_SAMPLE_COUNT); + BUILD_BUG_ON(ARRAY_SIZE(engine->pmu.sample) != + I915_ENGINE_SAMPLE_COUNT); + GEM_BUG_ON(sample >= ARRAY_SIZE(engine->pmu.enable_count)); + GEM_BUG_ON(sample >= ARRAY_SIZE(engine->pmu.sample)); GEM_BUG_ON(engine->pmu.enable_count[sample] == ~0); + + engine->pmu.enable |= BIT(sample); engine->pmu.enable_count[sample]++; } @@ -649,9 +655,11 @@ static void i915_pmu_disable(struct perf_event *event) engine = intel_engine_lookup_user(i915, engine_event_class(event), engine_event_instance(event)); - GEM_BUG_ON(!engine); - GEM_BUG_ON(sample >= I915_PMU_SAMPLE_BITS); + + GEM_BUG_ON(sample >= ARRAY_SIZE(engine->pmu.enable_count)); + GEM_BUG_ON(sample >= ARRAY_SIZE(engine->pmu.sample)); GEM_BUG_ON(engine->pmu.enable_count[sample] == 0); + /* * Decrement the reference count and clear the enabled * bitmask when the last listener on an event goes away. @@ -660,7 +668,7 @@ static void i915_pmu_disable(struct perf_event *event) engine->pmu.enable &= ~BIT(sample); } - GEM_BUG_ON(bit >= I915_PMU_MASK_BITS); + GEM_BUG_ON(bit >= ARRAY_SIZE(i915->pmu.enable_count)); GEM_BUG_ON(i915->pmu.enable_count[bit] == 0); /* * Decrement the reference count and clear the enabled diff --git a/drivers/gpu/drm/i915/i915_pmu.h b/drivers/gpu/drm/i915/i915_pmu.h index 7f164ca3db12..b3728c5f13e7 100644 --- a/drivers/gpu/drm/i915/i915_pmu.h +++ b/drivers/gpu/drm/i915/i915_pmu.h @@ -31,6 +31,8 @@ enum { ((1 << I915_PMU_SAMPLE_BITS) + \ (I915_PMU_LAST + 1 - __I915_PMU_OTHER(0))) +#define I915_ENGINE_SAMPLE_COUNT (I915_SAMPLE_SEMA + 1) + struct i915_pmu_sample { u64 cur; }; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 0a7d60509ca7..067054cf4a86 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -1790,7 +1790,7 @@ enum i915_power_well_id { #define _CNL_PORT_TX_C_LN0_OFFSET 0x162C40 #define _CNL_PORT_TX_D_LN0_OFFSET 0x162E40 #define _CNL_PORT_TX_F_LN0_OFFSET 0x162840 -#define _CNL_PORT_TX_DW_GRP(port, dw) (_PICK((port), \ +#define _CNL_PORT_TX_DW_GRP(dw, port) (_PICK((port), \ _CNL_PORT_TX_AE_GRP_OFFSET, \ _CNL_PORT_TX_B_GRP_OFFSET, \ _CNL_PORT_TX_B_GRP_OFFSET, \ @@ -1798,7 +1798,7 @@ enum i915_power_well_id { _CNL_PORT_TX_AE_GRP_OFFSET, \ _CNL_PORT_TX_F_GRP_OFFSET) + \ 4 * (dw)) -#define _CNL_PORT_TX_DW_LN0(port, dw) (_PICK((port), \ +#define _CNL_PORT_TX_DW_LN0(dw, port) (_PICK((port), \ _CNL_PORT_TX_AE_LN0_OFFSET, \ _CNL_PORT_TX_B_LN0_OFFSET, \ _CNL_PORT_TX_B_LN0_OFFSET, \ @@ -1834,9 +1834,9 @@ enum i915_power_well_id { #define _CNL_PORT_TX_DW4_LN0_AE 0x162450 #define _CNL_PORT_TX_DW4_LN1_AE 0x1624D0 -#define CNL_PORT_TX_DW4_GRP(port) _MMIO(_CNL_PORT_TX_DW_GRP((port), 4)) -#define CNL_PORT_TX_DW4_LN0(port) _MMIO(_CNL_PORT_TX_DW_LN0((port), 4)) -#define CNL_PORT_TX_DW4_LN(port, ln) _MMIO(_CNL_PORT_TX_DW_LN0((port), 4) + \ +#define CNL_PORT_TX_DW4_GRP(port) _MMIO(_CNL_PORT_TX_DW_GRP(4, (port))) +#define CNL_PORT_TX_DW4_LN0(port) _MMIO(_CNL_PORT_TX_DW_LN0(4, (port))) +#define CNL_PORT_TX_DW4_LN(port, ln) _MMIO(_CNL_PORT_TX_DW_LN0(4, (port)) + \ ((ln) * (_CNL_PORT_TX_DW4_LN1_AE - \ _CNL_PORT_TX_DW4_LN0_AE))) #define ICL_PORT_TX_DW4_AUX(port) _MMIO(_ICL_PORT_TX_DW_AUX(4, port)) @@ -1864,8 +1864,12 @@ enum i915_power_well_id { #define RTERM_SELECT(x) ((x) << 3) #define RTERM_SELECT_MASK (0x7 << 3) -#define CNL_PORT_TX_DW7_GRP(port) _MMIO(_CNL_PORT_TX_DW_GRP((port), 7)) -#define CNL_PORT_TX_DW7_LN0(port) _MMIO(_CNL_PORT_TX_DW_LN0((port), 7)) +#define CNL_PORT_TX_DW7_GRP(port) _MMIO(_CNL_PORT_TX_DW_GRP(7, (port))) +#define CNL_PORT_TX_DW7_LN0(port) _MMIO(_CNL_PORT_TX_DW_LN0(7, (port))) +#define ICL_PORT_TX_DW7_AUX(port) _MMIO(_ICL_PORT_TX_DW_AUX(7, port)) +#define ICL_PORT_TX_DW7_GRP(port) _MMIO(_ICL_PORT_TX_DW_GRP(7, port)) +#define ICL_PORT_TX_DW7_LN0(port) _MMIO(_ICL_PORT_TX_DW_LN(7, 0, port)) +#define ICL_PORT_TX_DW7_LN(port, ln) _MMIO(_ICL_PORT_TX_DW_LN(7, ln, port)) #define N_SCALAR(x) ((x) << 24) #define N_SCALAR_MASK (0x7F << 24) diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index f3e1d6a0b7dd..7edce1b7b348 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -494,103 +494,58 @@ static const struct cnl_ddi_buf_trans cnl_ddi_translations_edp_1_05V[] = { { 0x2, 0x7F, 0x3F, 0x00, 0x00 }, /* 400 400 0.0 */ }; -struct icl_combo_phy_ddi_buf_trans { - u32 dw2_swing_select; - u32 dw2_swing_scalar; - u32 dw4_scaling; -}; - -/* Voltage Swing Programming for VccIO 0.85V for DP */ -static const struct icl_combo_phy_ddi_buf_trans icl_combo_phy_ddi_translations_dp_hdmi_0_85V[] = { - /* Voltage mV db */ - { 0x2, 0x98, 0x0018 }, /* 400 0.0 */ - { 0x2, 0x98, 0x3015 }, /* 400 3.5 */ - { 0x2, 0x98, 0x6012 }, /* 400 6.0 */ - { 0x2, 0x98, 0x900F }, /* 400 9.5 */ - { 0xB, 0x70, 0x0018 }, /* 600 0.0 */ - { 0xB, 0x70, 0x3015 }, /* 600 3.5 */ - { 0xB, 0x70, 0x6012 }, /* 600 6.0 */ - { 0x5, 0x00, 0x0018 }, /* 800 0.0 */ - { 0x5, 0x00, 0x3015 }, /* 800 3.5 */ - { 0x6, 0x98, 0x0018 }, /* 1200 0.0 */ -}; - -/* FIXME - After table is updated in Bspec */ -/* Voltage Swing Programming for VccIO 0.85V for eDP */ -static const struct icl_combo_phy_ddi_buf_trans icl_combo_phy_ddi_translations_edp_0_85V[] = { - /* Voltage mV db */ - { 0x0, 0x00, 0x00 }, /* 200 0.0 */ - { 0x0, 0x00, 0x00 }, /* 200 1.5 */ - { 0x0, 0x00, 0x00 }, /* 200 4.0 */ - { 0x0, 0x00, 0x00 }, /* 200 6.0 */ - { 0x0, 0x00, 0x00 }, /* 250 0.0 */ - { 0x0, 0x00, 0x00 }, /* 250 1.5 */ - { 0x0, 0x00, 0x00 }, /* 250 4.0 */ - { 0x0, 0x00, 0x00 }, /* 300 0.0 */ - { 0x0, 0x00, 0x00 }, /* 300 1.5 */ - { 0x0, 0x00, 0x00 }, /* 350 0.0 */ -}; - -/* Voltage Swing Programming for VccIO 0.95V for DP */ -static const struct icl_combo_phy_ddi_buf_trans icl_combo_phy_ddi_translations_dp_hdmi_0_95V[] = { - /* Voltage mV db */ - { 0x2, 0x98, 0x0018 }, /* 400 0.0 */ - { 0x2, 0x98, 0x3015 }, /* 400 3.5 */ - { 0x2, 0x98, 0x6012 }, /* 400 6.0 */ - { 0x2, 0x98, 0x900F }, /* 400 9.5 */ - { 0x4, 0x98, 0x0018 }, /* 600 0.0 */ - { 0x4, 0x98, 0x3015 }, /* 600 3.5 */ - { 0x4, 0x98, 0x6012 }, /* 600 6.0 */ - { 0x5, 0x76, 0x0018 }, /* 800 0.0 */ - { 0x5, 0x76, 0x3015 }, /* 800 3.5 */ - { 0x6, 0x98, 0x0018 }, /* 1200 0.0 */ +/* icl_combo_phy_ddi_translations */ +static const struct cnl_ddi_buf_trans icl_combo_phy_ddi_translations_dp_hbr2[] = { + /* NT mV Trans mV db */ + { 0xA, 0x35, 0x3F, 0x00, 0x00 }, /* 350 350 0.0 */ + { 0xA, 0x4F, 0x37, 0x00, 0x08 }, /* 350 500 3.1 */ + { 0xC, 0x71, 0x2F, 0x00, 0x10 }, /* 350 700 6.0 */ + { 0x6, 0x7F, 0x2B, 0x00, 0x14 }, /* 350 900 8.2 */ + { 0xA, 0x4C, 0x3F, 0x00, 0x00 }, /* 500 500 0.0 */ + { 0xC, 0x73, 0x34, 0x00, 0x0B }, /* 500 700 2.9 */ + { 0x6, 0x7F, 0x2F, 0x00, 0x10 }, /* 500 900 5.1 */ + { 0xC, 0x6C, 0x3C, 0x00, 0x03 }, /* 650 700 0.6 */ + { 0x6, 0x7F, 0x35, 0x00, 0x0A }, /* 600 900 3.5 */ + { 0x6, 0x7F, 0x3F, 0x00, 0x00 }, /* 900 900 0.0 */ }; -/* FIXME - After table is updated in Bspec */ -/* Voltage Swing Programming for VccIO 0.95V for eDP */ -static const struct icl_combo_phy_ddi_buf_trans icl_combo_phy_ddi_translations_edp_0_95V[] = { - /* Voltage mV db */ - { 0x0, 0x00, 0x00 }, /* 200 0.0 */ - { 0x0, 0x00, 0x00 }, /* 200 1.5 */ - { 0x0, 0x00, 0x00 }, /* 200 4.0 */ - { 0x0, 0x00, 0x00 }, /* 200 6.0 */ - { 0x0, 0x00, 0x00 }, /* 250 0.0 */ - { 0x0, 0x00, 0x00 }, /* 250 1.5 */ - { 0x0, 0x00, 0x00 }, /* 250 4.0 */ - { 0x0, 0x00, 0x00 }, /* 300 0.0 */ - { 0x0, 0x00, 0x00 }, /* 300 1.5 */ - { 0x0, 0x00, 0x00 }, /* 350 0.0 */ +static const struct cnl_ddi_buf_trans icl_combo_phy_ddi_translations_edp_hbr2[] = { + /* NT mV Trans mV db */ + { 0x0, 0x7F, 0x3F, 0x00, 0x00 }, /* 200 200 0.0 */ + { 0x8, 0x7F, 0x38, 0x00, 0x07 }, /* 200 250 1.9 */ + { 0x1, 0x7F, 0x33, 0x00, 0x0C }, /* 200 300 3.5 */ + { 0x9, 0x7F, 0x31, 0x00, 0x0E }, /* 200 350 4.9 */ + { 0x8, 0x7F, 0x3F, 0x00, 0x00 }, /* 250 250 0.0 */ + { 0x1, 0x7F, 0x38, 0x00, 0x07 }, /* 250 300 1.6 */ + { 0x9, 0x7F, 0x35, 0x00, 0x0A }, /* 250 350 2.9 */ + { 0x1, 0x7F, 0x3F, 0x00, 0x00 }, /* 300 300 0.0 */ + { 0x9, 0x7F, 0x38, 0x00, 0x07 }, /* 300 350 1.3 */ + { 0x9, 0x7F, 0x3F, 0x00, 0x00 }, /* 350 350 0.0 */ }; -/* Voltage Swing Programming for VccIO 1.05V for DP */ -static const struct icl_combo_phy_ddi_buf_trans icl_combo_phy_ddi_translations_dp_hdmi_1_05V[] = { - /* Voltage mV db */ - { 0x2, 0x98, 0x0018 }, /* 400 0.0 */ - { 0x2, 0x98, 0x3015 }, /* 400 3.5 */ - { 0x2, 0x98, 0x6012 }, /* 400 6.0 */ - { 0x2, 0x98, 0x900F }, /* 400 9.5 */ - { 0x4, 0x98, 0x0018 }, /* 600 0.0 */ - { 0x4, 0x98, 0x3015 }, /* 600 3.5 */ - { 0x4, 0x98, 0x6012 }, /* 600 6.0 */ - { 0x5, 0x71, 0x0018 }, /* 800 0.0 */ - { 0x5, 0x71, 0x3015 }, /* 800 3.5 */ - { 0x6, 0x98, 0x0018 }, /* 1200 0.0 */ +static const struct cnl_ddi_buf_trans icl_combo_phy_ddi_translations_edp_hbr3[] = { + /* NT mV Trans mV db */ + { 0xA, 0x35, 0x3F, 0x00, 0x00 }, /* 350 350 0.0 */ + { 0xA, 0x4F, 0x37, 0x00, 0x08 }, /* 350 500 3.1 */ + { 0xC, 0x71, 0x2F, 0x00, 0x10 }, /* 350 700 6.0 */ + { 0x6, 0x7F, 0x2B, 0x00, 0x14 }, /* 350 900 8.2 */ + { 0xA, 0x4C, 0x3F, 0x00, 0x00 }, /* 500 500 0.0 */ + { 0xC, 0x73, 0x34, 0x00, 0x0B }, /* 500 700 2.9 */ + { 0x6, 0x7F, 0x2F, 0x00, 0x10 }, /* 500 900 5.1 */ + { 0xC, 0x6C, 0x3C, 0x00, 0x03 }, /* 650 700 0.6 */ + { 0x6, 0x7F, 0x35, 0x00, 0x0A }, /* 600 900 3.5 */ + { 0x6, 0x7F, 0x3F, 0x00, 0x00 }, /* 900 900 0.0 */ }; -/* FIXME - After table is updated in Bspec */ -/* Voltage Swing Programming for VccIO 1.05V for eDP */ -static const struct icl_combo_phy_ddi_buf_trans icl_combo_phy_ddi_translations_edp_1_05V[] = { - /* Voltage mV db */ - { 0x0, 0x00, 0x00 }, /* 200 0.0 */ - { 0x0, 0x00, 0x00 }, /* 200 1.5 */ - { 0x0, 0x00, 0x00 }, /* 200 4.0 */ - { 0x0, 0x00, 0x00 }, /* 200 6.0 */ - { 0x0, 0x00, 0x00 }, /* 250 0.0 */ - { 0x0, 0x00, 0x00 }, /* 250 1.5 */ - { 0x0, 0x00, 0x00 }, /* 250 4.0 */ - { 0x0, 0x00, 0x00 }, /* 300 0.0 */ - { 0x0, 0x00, 0x00 }, /* 300 1.5 */ - { 0x0, 0x00, 0x00 }, /* 350 0.0 */ +static const struct cnl_ddi_buf_trans icl_combo_phy_ddi_translations_hdmi[] = { + /* NT mV Trans mV db */ + { 0xA, 0x60, 0x3F, 0x00, 0x00 }, /* 450 450 0.0 */ + { 0xB, 0x73, 0x36, 0x00, 0x09 }, /* 450 650 3.2 */ + { 0x6, 0x7F, 0x31, 0x00, 0x0E }, /* 450 850 5.5 */ + { 0xB, 0x73, 0x3F, 0x00, 0x00 }, /* 650 650 0.0 ALS */ + { 0x6, 0x7F, 0x37, 0x00, 0x08 }, /* 650 850 2.3 */ + { 0x6, 0x7F, 0x3F, 0x00, 0x00 }, /* 850 850 0.0 */ + { 0x6, 0x7F, 0x35, 0x00, 0x0A }, /* 600 850 3.0 */ }; struct icl_mg_phy_ddi_buf_trans { @@ -871,43 +826,23 @@ cnl_get_buf_trans_edp(struct drm_i915_private *dev_priv, int *n_entries) } } -static const struct icl_combo_phy_ddi_buf_trans * +static const struct cnl_ddi_buf_trans * icl_get_combo_buf_trans(struct drm_i915_private *dev_priv, enum port port, - int type, int *n_entries) + int type, int rate, int *n_entries) { - u32 voltage = I915_READ(ICL_PORT_COMP_DW3(port)) & VOLTAGE_INFO_MASK; - - if (type == INTEL_OUTPUT_EDP && dev_priv->vbt.edp.low_vswing) { - switch (voltage) { - case VOLTAGE_INFO_0_85V: - *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_edp_0_85V); - return icl_combo_phy_ddi_translations_edp_0_85V; - case VOLTAGE_INFO_0_95V: - *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_edp_0_95V); - return icl_combo_phy_ddi_translations_edp_0_95V; - case VOLTAGE_INFO_1_05V: - *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_edp_1_05V); - return icl_combo_phy_ddi_translations_edp_1_05V; - default: - MISSING_CASE(voltage); - return NULL; - } - } else { - switch (voltage) { - case VOLTAGE_INFO_0_85V: - *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_dp_hdmi_0_85V); - return icl_combo_phy_ddi_translations_dp_hdmi_0_85V; - case VOLTAGE_INFO_0_95V: - *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_dp_hdmi_0_95V); - return icl_combo_phy_ddi_translations_dp_hdmi_0_95V; - case VOLTAGE_INFO_1_05V: - *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_dp_hdmi_1_05V); - return icl_combo_phy_ddi_translations_dp_hdmi_1_05V; - default: - MISSING_CASE(voltage); - return NULL; - } + if (type == INTEL_OUTPUT_HDMI) { + *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_hdmi); + return icl_combo_phy_ddi_translations_hdmi; + } else if (rate > 540000 && type == INTEL_OUTPUT_EDP) { + *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_edp_hbr3); + return icl_combo_phy_ddi_translations_edp_hbr3; + } else if (type == INTEL_OUTPUT_EDP && dev_priv->vbt.edp.low_vswing) { + *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_edp_hbr2); + return icl_combo_phy_ddi_translations_edp_hbr2; } + + *n_entries = ARRAY_SIZE(icl_combo_phy_ddi_translations_dp_hbr2); + return icl_combo_phy_ddi_translations_dp_hbr2; } static int intel_ddi_hdmi_level(struct drm_i915_private *dev_priv, enum port port) @@ -918,8 +853,8 @@ static int intel_ddi_hdmi_level(struct drm_i915_private *dev_priv, enum port por if (IS_ICELAKE(dev_priv)) { if (intel_port_is_combophy(dev_priv, port)) - icl_get_combo_buf_trans(dev_priv, port, - INTEL_OUTPUT_HDMI, &n_entries); + icl_get_combo_buf_trans(dev_priv, port, INTEL_OUTPUT_HDMI, + 0, &n_entries); else n_entries = ARRAY_SIZE(icl_mg_phy_ddi_translations); default_entry = n_entries - 1; @@ -1086,7 +1021,7 @@ static uint32_t icl_pll_to_ddi_pll_sel(struct intel_encoder *encoder, return DDI_CLK_SEL_TBT_810; default: MISSING_CASE(clock); - break; + return DDI_CLK_SEL_NONE; } case DPLL_ID_ICL_MGPLL1: case DPLL_ID_ICL_MGPLL2: @@ -2275,13 +2210,14 @@ static void bxt_ddi_vswing_sequence(struct intel_encoder *encoder, u8 intel_ddi_dp_voltage_max(struct intel_encoder *encoder) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); + struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base); enum port port = encoder->port; int n_entries; if (IS_ICELAKE(dev_priv)) { if (intel_port_is_combophy(dev_priv, port)) icl_get_combo_buf_trans(dev_priv, port, encoder->type, - &n_entries); + intel_dp->link_rate, &n_entries); else n_entries = ARRAY_SIZE(icl_mg_phy_ddi_translations); } else if (IS_CANNONLAKE(dev_priv)) { @@ -2462,14 +2398,15 @@ static void cnl_ddi_vswing_sequence(struct intel_encoder *encoder, } static void icl_ddi_combo_vswing_program(struct drm_i915_private *dev_priv, - u32 level, enum port port, int type) + u32 level, enum port port, int type, + int rate) { - const struct icl_combo_phy_ddi_buf_trans *ddi_translations = NULL; + const struct cnl_ddi_buf_trans *ddi_translations = NULL; u32 n_entries, val; int ln; ddi_translations = icl_get_combo_buf_trans(dev_priv, port, type, - &n_entries); + rate, &n_entries); if (!ddi_translations) return; @@ -2478,34 +2415,23 @@ static void icl_ddi_combo_vswing_program(struct drm_i915_private *dev_priv, level = n_entries - 1; } - /* Set PORT_TX_DW5 Rterm Sel to 110b. */ + /* Set PORT_TX_DW5 */ val = I915_READ(ICL_PORT_TX_DW5_LN0(port)); - val &= ~RTERM_SELECT_MASK; + val &= ~(SCALING_MODE_SEL_MASK | RTERM_SELECT_MASK | + TAP2_DISABLE | TAP3_DISABLE); + val |= SCALING_MODE_SEL(0x2); val |= RTERM_SELECT(0x6); - I915_WRITE(ICL_PORT_TX_DW5_GRP(port), val); - - /* Program PORT_TX_DW5 */ - val = I915_READ(ICL_PORT_TX_DW5_LN0(port)); - /* Set DisableTap2 and DisableTap3 if MIPI DSI - * Clear DisableTap2 and DisableTap3 for all other Ports - */ - if (type == INTEL_OUTPUT_DSI) { - val |= TAP2_DISABLE; - val |= TAP3_DISABLE; - } else { - val &= ~TAP2_DISABLE; - val &= ~TAP3_DISABLE; - } + val |= TAP3_DISABLE; I915_WRITE(ICL_PORT_TX_DW5_GRP(port), val); /* Program PORT_TX_DW2 */ val = I915_READ(ICL_PORT_TX_DW2_LN0(port)); val &= ~(SWING_SEL_LOWER_MASK | SWING_SEL_UPPER_MASK | RCOMP_SCALAR_MASK); - val |= SWING_SEL_UPPER(ddi_translations[level].dw2_swing_select); - val |= SWING_SEL_LOWER(ddi_translations[level].dw2_swing_select); + val |= SWING_SEL_UPPER(ddi_translations[level].dw2_swing_sel); + val |= SWING_SEL_LOWER(ddi_translations[level].dw2_swing_sel); /* Program Rcomp scalar for every table entry */ - val |= RCOMP_SCALAR(ddi_translations[level].dw2_swing_scalar); + val |= RCOMP_SCALAR(0x98); I915_WRITE(ICL_PORT_TX_DW2_GRP(port), val); /* Program PORT_TX_DW4 */ @@ -2514,9 +2440,17 @@ static void icl_ddi_combo_vswing_program(struct drm_i915_private *dev_priv, val = I915_READ(ICL_PORT_TX_DW4_LN(port, ln)); val &= ~(POST_CURSOR_1_MASK | POST_CURSOR_2_MASK | CURSOR_COEFF_MASK); - val |= ddi_translations[level].dw4_scaling; + val |= POST_CURSOR_1(ddi_translations[level].dw4_post_cursor_1); + val |= POST_CURSOR_2(ddi_translations[level].dw4_post_cursor_2); + val |= CURSOR_COEFF(ddi_translations[level].dw4_cursor_coeff); I915_WRITE(ICL_PORT_TX_DW4_LN(port, ln), val); } + + /* Program PORT_TX_DW7 */ + val = I915_READ(ICL_PORT_TX_DW7_LN0(port)); + val &= ~N_SCALAR_MASK; + val |= N_SCALAR(ddi_translations[level].dw7_n_scalar); + I915_WRITE(ICL_PORT_TX_DW7_GRP(port), val); } static void icl_combo_phy_ddi_vswing_sequence(struct intel_encoder *encoder, @@ -2581,7 +2515,7 @@ static void icl_combo_phy_ddi_vswing_sequence(struct intel_encoder *encoder, I915_WRITE(ICL_PORT_TX_DW5_GRP(port), val); /* 5. Program swing and de-emphasis */ - icl_ddi_combo_vswing_program(dev_priv, level, port, type); + icl_ddi_combo_vswing_program(dev_priv, level, port, type, rate); /* 6. Set training enable to trigger update */ val = I915_READ(ICL_PORT_TX_DW5_LN0(port)); diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 3da9c0f9e948..248128126422 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -15415,16 +15415,45 @@ static void intel_sanitize_crtc(struct intel_crtc *crtc, } } +static bool has_bogus_dpll_config(const struct intel_crtc_state *crtc_state) +{ + struct drm_i915_private *dev_priv = to_i915(crtc_state->base.crtc->dev); + + /* + * Some SNB BIOSen (eg. ASUS K53SV) are known to misprogram + * the hardware when a high res displays plugged in. DPLL P + * divider is zero, and the pipe timings are bonkers. We'll + * try to disable everything in that case. + * + * FIXME would be nice to be able to sanitize this state + * without several WARNs, but for now let's take the easy + * road. + */ + return IS_GEN6(dev_priv) && + crtc_state->base.active && + crtc_state->shared_dpll && + crtc_state->port_clock == 0; +} + static void intel_sanitize_encoder(struct intel_encoder *encoder) { struct drm_i915_private *dev_priv = to_i915(encoder->base.dev); struct intel_connector *connector; + struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc); + struct intel_crtc_state *crtc_state = crtc ? + to_intel_crtc_state(crtc->base.state) : NULL; /* We need to check both for a crtc link (meaning that the * encoder is active and trying to read from a pipe) and the * pipe itself being active. */ - bool has_active_crtc = encoder->base.crtc && - to_intel_crtc(encoder->base.crtc)->active; + bool has_active_crtc = crtc_state && + crtc_state->base.active; + + if (crtc_state && has_bogus_dpll_config(crtc_state)) { + DRM_DEBUG_KMS("BIOS has misprogrammed the hardware. Disabling pipe %c\n", + pipe_name(crtc->pipe)); + has_active_crtc = false; + } connector = intel_encoder_find_connector(encoder); if (connector && !has_active_crtc) { @@ -15435,16 +15464,25 @@ static void intel_sanitize_encoder(struct intel_encoder *encoder) /* Connector is active, but has no active pipe. This is * fallout from our resume register restoring. Disable * the encoder manually again. */ - if (encoder->base.crtc) { - struct drm_crtc_state *crtc_state = encoder->base.crtc->state; + if (crtc_state) { + struct drm_encoder *best_encoder; DRM_DEBUG_KMS("[ENCODER:%d:%s] manually disabled\n", encoder->base.base.id, encoder->base.name); + + /* avoid oopsing in case the hooks consult best_encoder */ + best_encoder = connector->base.state->best_encoder; + connector->base.state->best_encoder = &encoder->base; + if (encoder->disable) - encoder->disable(encoder, to_intel_crtc_state(crtc_state), connector->base.state); + encoder->disable(encoder, crtc_state, + connector->base.state); if (encoder->post_disable) - encoder->post_disable(encoder, to_intel_crtc_state(crtc_state), connector->base.state); + encoder->post_disable(encoder, crtc_state, + connector->base.state); + + connector->base.state->best_encoder = best_encoder; } encoder->base.crtc = NULL; diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index fdd2cbc56fa3..22a74608c6e4 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -304,9 +304,11 @@ static int cnl_max_source_rate(struct intel_dp *intel_dp) static int icl_max_source_rate(struct intel_dp *intel_dp) { struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp); + struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev); enum port port = dig_port->base.port; - if (port == PORT_B) + if (intel_port_is_combophy(dev_priv, port) && + !intel_dp_is_edp(intel_dp)) return 540000; return 810000; diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index f94a04b4ad87..e9ddeaf05a14 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -209,6 +209,16 @@ struct intel_fbdev { unsigned long vma_flags; async_cookie_t cookie; int preferred_bpp; + + /* Whether or not fbdev hpd processing is temporarily suspended */ + bool hpd_suspended : 1; + /* Set when a hotplug was received while HPD processing was + * suspended + */ + bool hpd_waiting : 1; + + /* Protects hpd_suspended */ + struct mutex hpd_lock; }; struct intel_encoder { diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c index fb5bb5b32a60..7f365ac0b549 100644 --- a/drivers/gpu/drm/i915/intel_fbdev.c +++ b/drivers/gpu/drm/i915/intel_fbdev.c @@ -679,6 +679,7 @@ int intel_fbdev_init(struct drm_device *dev) if (ifbdev == NULL) return -ENOMEM; + mutex_init(&ifbdev->hpd_lock); drm_fb_helper_prepare(dev, &ifbdev->helper, &intel_fb_helper_funcs); if (!intel_fbdev_init_bios(dev, ifbdev)) @@ -752,6 +753,26 @@ void intel_fbdev_fini(struct drm_i915_private *dev_priv) intel_fbdev_destroy(ifbdev); } +/* Suspends/resumes fbdev processing of incoming HPD events. When resuming HPD + * processing, fbdev will perform a full connector reprobe if a hotplug event + * was received while HPD was suspended. + */ +static void intel_fbdev_hpd_set_suspend(struct intel_fbdev *ifbdev, int state) +{ + bool send_hpd = false; + + mutex_lock(&ifbdev->hpd_lock); + ifbdev->hpd_suspended = state == FBINFO_STATE_SUSPENDED; + send_hpd = !ifbdev->hpd_suspended && ifbdev->hpd_waiting; + ifbdev->hpd_waiting = false; + mutex_unlock(&ifbdev->hpd_lock); + + if (send_hpd) { + DRM_DEBUG_KMS("Handling delayed fbcon HPD event\n"); + drm_fb_helper_hotplug_event(&ifbdev->helper); + } +} + void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous) { struct drm_i915_private *dev_priv = to_i915(dev); @@ -773,6 +794,7 @@ void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous */ if (state != FBINFO_STATE_RUNNING) flush_work(&dev_priv->fbdev_suspend_work); + console_lock(); } else { /* @@ -800,17 +822,26 @@ void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous drm_fb_helper_set_suspend(&ifbdev->helper, state); console_unlock(); + + intel_fbdev_hpd_set_suspend(ifbdev, state); } void intel_fbdev_output_poll_changed(struct drm_device *dev) { struct intel_fbdev *ifbdev = to_i915(dev)->fbdev; + bool send_hpd; if (!ifbdev) return; intel_fbdev_sync(ifbdev); - if (ifbdev->vma || ifbdev->helper.deferred_setup) + + mutex_lock(&ifbdev->hpd_lock); + send_hpd = !ifbdev->hpd_suspended; + ifbdev->hpd_waiting = true; + mutex_unlock(&ifbdev->hpd_lock); + + if (send_hpd && (ifbdev->vma || ifbdev->helper.deferred_setup)) drm_fb_helper_hotplug_event(&ifbdev->helper); } diff --git a/drivers/gpu/drm/i915/intel_opregion.c b/drivers/gpu/drm/i915/intel_opregion.c index b8f106d9ecf8..3ac20153705a 100644 --- a/drivers/gpu/drm/i915/intel_opregion.c +++ b/drivers/gpu/drm/i915/intel_opregion.c @@ -55,7 +55,12 @@ struct opregion_header { u8 signature[16]; u32 size; - u32 opregion_ver; + struct { + u8 rsvd; + u8 revision; + u8 minor; + u8 major; + } __packed over; u8 bios_ver[32]; u8 vbios_ver[16]; u8 driver_ver[16]; @@ -119,7 +124,8 @@ struct opregion_asle { u64 fdss; u32 fdsp; u32 stat; - u64 rvda; /* Physical address of raw vbt data */ + u64 rvda; /* Physical (2.0) or relative from opregion (2.1+) + * address of raw VBT data. */ u32 rvds; /* Size of raw vbt data */ u8 rsvd[58]; } __packed; @@ -925,6 +931,11 @@ int intel_opregion_setup(struct drm_i915_private *dev_priv) opregion->header = base; opregion->lid_state = base + ACPI_CLID; + DRM_DEBUG_DRIVER("ACPI OpRegion version %u.%u.%u\n", + opregion->header->over.major, + opregion->header->over.minor, + opregion->header->over.revision); + mboxes = opregion->header->mboxes; if (mboxes & MBOX_ACPI) { DRM_DEBUG_DRIVER("Public ACPI methods supported\n"); @@ -953,11 +964,26 @@ int intel_opregion_setup(struct drm_i915_private *dev_priv) if (dmi_check_system(intel_no_opregion_vbt)) goto out; - if (opregion->header->opregion_ver >= 2 && opregion->asle && + if (opregion->header->over.major >= 2 && opregion->asle && opregion->asle->rvda && opregion->asle->rvds) { - opregion->rvda = memremap(opregion->asle->rvda, - opregion->asle->rvds, + resource_size_t rvda = opregion->asle->rvda; + + /* + * opregion 2.0: rvda is the physical VBT address. + * + * opregion 2.1+: rvda is unsigned, relative offset from + * opregion base, and should never point within opregion. + */ + if (opregion->header->over.major > 2 || + opregion->header->over.minor >= 1) { + WARN_ON(rvda < OPREGION_SIZE); + + rvda += asls; + } + + opregion->rvda = memremap(rvda, opregion->asle->rvds, MEMREMAP_WB); + vbt = opregion->rvda; vbt_size = opregion->asle->rvds; if (intel_bios_is_valid_vbt(vbt, vbt_size)) { @@ -967,6 +993,8 @@ int intel_opregion_setup(struct drm_i915_private *dev_priv) goto out; } else { DRM_DEBUG_KMS("Invalid VBT in ACPI OpRegion (RVDA)\n"); + memunmap(opregion->rvda); + opregion->rvda = NULL; } } diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index 72edaa7ff411..a1a7cc29fdd1 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -415,16 +415,17 @@ struct intel_engine_cs { /** * @enable_count: Reference count for the enabled samplers. * - * Index number corresponds to the bit number from @enable. + * Index number corresponds to @enum drm_i915_pmu_engine_sample. */ - unsigned int enable_count[I915_PMU_SAMPLE_BITS]; + unsigned int enable_count[I915_ENGINE_SAMPLE_COUNT]; /** * @sample: Counter values for sampling events. * * Our internal timer stores the current counters in this field. + * + * Index number corresponds to @enum drm_i915_pmu_engine_sample. */ -#define I915_ENGINE_SAMPLE_MAX (I915_SAMPLE_SEMA + 1) - struct i915_pmu_sample sample[I915_ENGINE_SAMPLE_MAX]; + struct i915_pmu_sample sample[I915_ENGINE_SAMPLE_COUNT]; } pmu; /* diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c index d2e003d8f3db..5170a0f5fe7b 100644 --- a/drivers/gpu/drm/i915/intel_sprite.c +++ b/drivers/gpu/drm/i915/intel_sprite.c @@ -494,7 +494,7 @@ skl_program_plane(struct intel_plane *plane, keymax = (key->max_value & 0xffffff) | PLANE_KEYMAX_ALPHA(alpha); - keymsk = key->channel_mask & 0x3ffffff; + keymsk = key->channel_mask & 0x7ffffff; if (alpha < 0xff) keymsk |= PLANE_KEYMSK_ALPHA_ENABLE; diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c index 2c5bbe317353..e31e263cf86b 100644 --- a/drivers/gpu/drm/imx/imx-ldb.c +++ b/drivers/gpu/drm/imx/imx-ldb.c @@ -643,8 +643,10 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data) int bus_format; ret = of_property_read_u32(child, "reg", &i); - if (ret || i < 0 || i > 1) - return -EINVAL; + if (ret || i < 0 || i > 1) { + ret = -EINVAL; + goto free_child; + } if (!of_device_is_available(child)) continue; @@ -657,7 +659,6 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data) channel = &imx_ldb->channel[i]; channel->ldb = imx_ldb; channel->chno = i; - channel->child = child; /* * The output port is port@4 with an external 4-port mux or @@ -667,13 +668,13 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data) imx_ldb->lvds_mux ? 4 : 2, 0, &channel->panel, &channel->bridge); if (ret && ret != -ENODEV) - return ret; + goto free_child; /* panel ddc only if there is no bridge */ if (!channel->bridge) { ret = imx_ldb_panel_ddc(dev, channel, child); if (ret) - return ret; + goto free_child; } bus_format = of_get_bus_format(dev, child); @@ -689,18 +690,26 @@ static int imx_ldb_bind(struct device *dev, struct device *master, void *data) if (bus_format < 0) { dev_err(dev, "could not determine data mapping: %d\n", bus_format); - return bus_format; + ret = bus_format; + goto free_child; } channel->bus_format = bus_format; + channel->child = child; ret = imx_ldb_register(drm, channel); - if (ret) - return ret; + if (ret) { + channel->child = NULL; + goto free_child; + } } dev_set_drvdata(dev, imx_ldb); return 0; + +free_child: + of_node_put(child); + return ret; } static void imx_ldb_unbind(struct device *dev, struct device *master, diff --git a/drivers/gpu/drm/imx/ipuv3-plane.c b/drivers/gpu/drm/imx/ipuv3-plane.c index c390924de93d..21e964f6ab5c 100644 --- a/drivers/gpu/drm/imx/ipuv3-plane.c +++ b/drivers/gpu/drm/imx/ipuv3-plane.c @@ -370,9 +370,9 @@ static int ipu_plane_atomic_check(struct drm_plane *plane, if (ret) return ret; - /* CRTC should be enabled */ + /* nothing to check when disabling or disabled */ if (!crtc_state->enable) - return -EINVAL; + return 0; switch (plane->type) { case DRM_PLANE_TYPE_PRIMARY: diff --git a/drivers/gpu/drm/omapdrm/dss/dsi.c b/drivers/gpu/drm/omapdrm/dss/dsi.c index 00a9c2ab9e6c..64fb788b6647 100644 --- a/drivers/gpu/drm/omapdrm/dss/dsi.c +++ b/drivers/gpu/drm/omapdrm/dss/dsi.c @@ -1406,7 +1406,7 @@ static void dsi_pll_disable(struct dss_pll *pll) static int dsi_dump_dsi_clocks(struct seq_file *s, void *p) { - struct dsi_data *dsi = p; + struct dsi_data *dsi = s->private; struct dss_pll_clock_info *cinfo = &dsi->pll.cinfo; enum dss_clk_source dispc_clk_src, dsi_clk_src; int dsi_module = dsi->module_id; @@ -1467,7 +1467,7 @@ static int dsi_dump_dsi_clocks(struct seq_file *s, void *p) #ifdef CONFIG_OMAP2_DSS_COLLECT_IRQ_STATS static int dsi_dump_dsi_irqs(struct seq_file *s, void *p) { - struct dsi_data *dsi = p; + struct dsi_data *dsi = s->private; unsigned long flags; struct dsi_irq_stats stats; @@ -1558,7 +1558,7 @@ static int dsi_dump_dsi_irqs(struct seq_file *s, void *p) static int dsi_dump_dsi_regs(struct seq_file *s, void *p) { - struct dsi_data *dsi = p; + struct dsi_data *dsi = s->private; if (dsi_runtime_get(dsi)) return 0; @@ -4751,6 +4751,17 @@ static int dsi_set_config(struct omap_dss_device *dssdev, dsi->vm.flags |= DISPLAY_FLAGS_HSYNC_HIGH; dsi->vm.flags &= ~DISPLAY_FLAGS_VSYNC_LOW; dsi->vm.flags |= DISPLAY_FLAGS_VSYNC_HIGH; + /* + * HACK: These flags should be handled through the omap_dss_device bus + * flags, but this will only be possible when the DSI encoder will be + * converted to the omapdrm-managed encoder model. + */ + dsi->vm.flags &= ~DISPLAY_FLAGS_PIXDATA_NEGEDGE; + dsi->vm.flags |= DISPLAY_FLAGS_PIXDATA_POSEDGE; + dsi->vm.flags &= ~DISPLAY_FLAGS_DE_LOW; + dsi->vm.flags |= DISPLAY_FLAGS_DE_HIGH; + dsi->vm.flags &= ~DISPLAY_FLAGS_SYNC_POSEDGE; + dsi->vm.flags |= DISPLAY_FLAGS_SYNC_NEGEDGE; dss_mgr_set_timings(&dsi->output, &dsi->vm); @@ -5083,15 +5094,15 @@ static int dsi_bind(struct device *dev, struct device *master, void *data) snprintf(name, sizeof(name), "dsi%u_regs", dsi->module_id + 1); dsi->debugfs.regs = dss_debugfs_create_file(dss, name, - dsi_dump_dsi_regs, &dsi); + dsi_dump_dsi_regs, dsi); #ifdef CONFIG_OMAP2_DSS_COLLECT_IRQ_STATS snprintf(name, sizeof(name), "dsi%u_irqs", dsi->module_id + 1); dsi->debugfs.irqs = dss_debugfs_create_file(dss, name, - dsi_dump_dsi_irqs, &dsi); + dsi_dump_dsi_irqs, dsi); #endif snprintf(name, sizeof(name), "dsi%u_clks", dsi->module_id + 1); dsi->debugfs.clks = dss_debugfs_create_file(dss, name, - dsi_dump_dsi_clocks, &dsi); + dsi_dump_dsi_clocks, dsi); return 0; } @@ -5104,8 +5115,6 @@ static void dsi_unbind(struct device *dev, struct device *master, void *data) dss_debugfs_remove_file(dsi->debugfs.irqs); dss_debugfs_remove_file(dsi->debugfs.regs); - of_platform_depopulate(dev); - WARN_ON(dsi->scp_clk_refcount > 0); dss_pll_unregister(&dsi->pll); @@ -5457,6 +5466,8 @@ static int dsi_remove(struct platform_device *pdev) dsi_uninit_output(dsi); + of_platform_depopulate(&pdev->dev); + pm_runtime_disable(&pdev->dev); if (dsi->vdds_dsi_reg != NULL && dsi->vdds_dsi_enabled) { diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c index d587779a80b4..a97294ac96d5 100644 --- a/drivers/gpu/drm/radeon/ci_dpm.c +++ b/drivers/gpu/drm/radeon/ci_dpm.c @@ -5676,7 +5676,7 @@ int ci_dpm_init(struct radeon_device *rdev) u16 data_offset, size; u8 frev, crev; struct ci_power_info *pi; - enum pci_bus_speed speed_cap; + enum pci_bus_speed speed_cap = PCI_SPEED_UNKNOWN; struct pci_dev *root = rdev->pdev->bus->self; int ret; @@ -5685,7 +5685,8 @@ int ci_dpm_init(struct radeon_device *rdev) return -ENOMEM; rdev->pm.dpm.priv = pi; - speed_cap = pcie_get_speed_cap(root); + if (!pci_is_root_bus(rdev->pdev->bus)) + speed_cap = pcie_get_speed_cap(root); if (speed_cap == PCI_SPEED_UNKNOWN) { pi->sys_pcie_mask = 0; } else { diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c index 8fb60b3af015..0a785ef0ab66 100644 --- a/drivers/gpu/drm/radeon/si_dpm.c +++ b/drivers/gpu/drm/radeon/si_dpm.c @@ -6899,7 +6899,7 @@ int si_dpm_init(struct radeon_device *rdev) struct ni_power_info *ni_pi; struct si_power_info *si_pi; struct atom_clock_dividers dividers; - enum pci_bus_speed speed_cap; + enum pci_bus_speed speed_cap = PCI_SPEED_UNKNOWN; struct pci_dev *root = rdev->pdev->bus->self; int ret; @@ -6911,7 +6911,8 @@ int si_dpm_init(struct radeon_device *rdev) eg_pi = &ni_pi->eg; pi = &eg_pi->rv7xx; - speed_cap = pcie_get_speed_cap(root); + if (!pci_is_root_bus(rdev->pdev->bus)) + speed_cap = pcie_get_speed_cap(root); if (speed_cap == PCI_SPEED_UNKNOWN) { si_pi->sys_pcie_mask = 0; } else { diff --git a/drivers/gpu/drm/rockchip/rockchip_rgb.c b/drivers/gpu/drm/rockchip/rockchip_rgb.c index 37f93022a106..c0351abf83a3 100644 --- a/drivers/gpu/drm/rockchip/rockchip_rgb.c +++ b/drivers/gpu/drm/rockchip/rockchip_rgb.c @@ -1,17 +1,8 @@ -//SPDX-License-Identifier: GPL-2.0+ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) Fuzhou Rockchip Electronics Co.Ltd * Author: * Sandy Huang <hjc@rock-chips.com> - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #include <drm/drmP.h> diff --git a/drivers/gpu/drm/rockchip/rockchip_rgb.h b/drivers/gpu/drm/rockchip/rockchip_rgb.h index 38b52e63b2b0..27b9635124bc 100644 --- a/drivers/gpu/drm/rockchip/rockchip_rgb.h +++ b/drivers/gpu/drm/rockchip/rockchip_rgb.h @@ -1,17 +1,8 @@ -//SPDX-License-Identifier: GPL-2.0+ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) Fuzhou Rockchip Electronics Co.Ltd * Author: * Sandy Huang <hjc@rock-chips.com> - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #ifdef CONFIG_ROCKCHIP_RGB diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index 4463d3826ecb..e2942c9a11a7 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -440,13 +440,10 @@ struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity) while ((entity->dependency = sched->ops->dependency(sched_job, entity))) { + trace_drm_sched_job_wait_dep(sched_job, entity->dependency); - if (drm_sched_entity_add_dependency_cb(entity)) { - - trace_drm_sched_job_wait_dep(sched_job, - entity->dependency); + if (drm_sched_entity_add_dependency_cb(entity)) return NULL; - } } /* skip jobs from entity that marked guilty */ diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c index 0420f5c978b9..cf45d0f940f9 100644 --- a/drivers/gpu/drm/sun4i/sun4i_tcon.c +++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c @@ -761,6 +761,7 @@ static int sun4i_tcon_init_clocks(struct device *dev, return PTR_ERR(tcon->sclk0); } } + clk_prepare_enable(tcon->sclk0); if (tcon->quirks->has_channel_1) { tcon->sclk1 = devm_clk_get(dev, "tcon-ch1"); @@ -775,6 +776,7 @@ static int sun4i_tcon_init_clocks(struct device *dev, static void sun4i_tcon_free_clocks(struct sun4i_tcon *tcon) { + clk_disable_unprepare(tcon->sclk0); clk_disable_unprepare(tcon->clk); } diff --git a/drivers/gpu/drm/vkms/vkms_crc.c b/drivers/gpu/drm/vkms/vkms_crc.c index 9d9e8146db90..d7b409a3c0f8 100644 --- a/drivers/gpu/drm/vkms/vkms_crc.c +++ b/drivers/gpu/drm/vkms/vkms_crc.c @@ -1,4 +1,5 @@ -// SPDX-License-Identifier: GPL-2.0 +// SPDX-License-Identifier: GPL-2.0+ + #include "vkms_drv.h" #include <linux/crc32.h> #include <drm/drm_atomic.h> diff --git a/drivers/gpu/drm/vkms/vkms_crtc.c b/drivers/gpu/drm/vkms/vkms_crtc.c index 177bbcb38306..eb56ee893761 100644 --- a/drivers/gpu/drm/vkms/vkms_crtc.c +++ b/drivers/gpu/drm/vkms/vkms_crtc.c @@ -1,10 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ +// SPDX-License-Identifier: GPL-2.0+ #include "vkms_drv.h" #include <drm/drm_atomic_helper.h> diff --git a/drivers/gpu/drm/vkms/vkms_drv.c b/drivers/gpu/drm/vkms/vkms_drv.c index 83087877565c..7dcbecb5fac2 100644 --- a/drivers/gpu/drm/vkms/vkms_drv.c +++ b/drivers/gpu/drm/vkms/vkms_drv.c @@ -1,9 +1,4 @@ -/* - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ +// SPDX-License-Identifier: GPL-2.0+ /** * DOC: vkms (Virtual Kernel Modesetting) diff --git a/drivers/gpu/drm/vkms/vkms_drv.h b/drivers/gpu/drm/vkms/vkms_drv.h index e4469cd3d254..81f1cfbeb936 100644 --- a/drivers/gpu/drm/vkms/vkms_drv.h +++ b/drivers/gpu/drm/vkms/vkms_drv.h @@ -1,3 +1,5 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + #ifndef _VKMS_DRV_H_ #define _VKMS_DRV_H_ diff --git a/drivers/gpu/drm/vkms/vkms_gem.c b/drivers/gpu/drm/vkms/vkms_gem.c index 80311daed47a..138b0bb325cf 100644 --- a/drivers/gpu/drm/vkms/vkms_gem.c +++ b/drivers/gpu/drm/vkms/vkms_gem.c @@ -1,10 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ +// SPDX-License-Identifier: GPL-2.0+ #include <linux/shmem_fs.h> diff --git a/drivers/gpu/drm/vkms/vkms_output.c b/drivers/gpu/drm/vkms/vkms_output.c index 271a0eb9042c..4173e4f48334 100644 --- a/drivers/gpu/drm/vkms/vkms_output.c +++ b/drivers/gpu/drm/vkms/vkms_output.c @@ -1,10 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ +// SPDX-License-Identifier: GPL-2.0+ #include "vkms_drv.h" #include <drm/drm_crtc_helper.h> diff --git a/drivers/gpu/drm/vkms/vkms_plane.c b/drivers/gpu/drm/vkms/vkms_plane.c index 418817600ad1..0e67d2d42f0c 100644 --- a/drivers/gpu/drm/vkms/vkms_plane.c +++ b/drivers/gpu/drm/vkms/vkms_plane.c @@ -1,10 +1,4 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ +// SPDX-License-Identifier: GPL-2.0+ #include "vkms_drv.h" #include <drm/drm_plane_helper.h> diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 25afb1d594e3..7ef5dcb06104 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -26,6 +26,7 @@ **************************************************************************/ #include <linux/module.h> #include <linux/console.h> +#include <linux/dma-mapping.h> #include <drm/drmP.h> #include "vmwgfx_drv.h" @@ -34,7 +35,6 @@ #include <drm/ttm/ttm_placement.h> #include <drm/ttm/ttm_bo_driver.h> #include <drm/ttm/ttm_module.h> -#include <linux/intel-iommu.h> #define VMWGFX_DRIVER_DESC "Linux drm driver for VMware graphics devices" #define VMWGFX_CHIP_SVGAII 0 @@ -546,6 +546,21 @@ static void vmw_get_initial_size(struct vmw_private *dev_priv) } /** + * vmw_assume_iommu - Figure out whether coherent dma-remapping might be + * taking place. + * @dev: Pointer to the struct drm_device. + * + * Return: true if iommu present, false otherwise. + */ +static bool vmw_assume_iommu(struct drm_device *dev) +{ + const struct dma_map_ops *ops = get_dma_ops(dev->dev); + + return !dma_is_direct(ops) && ops && + ops->map_page != dma_direct_map_page; +} + +/** * vmw_dma_select_mode - Determine how DMA mappings should be set up for this * system. * @@ -565,55 +580,27 @@ static int vmw_dma_select_mode(struct vmw_private *dev_priv) [vmw_dma_alloc_coherent] = "Using coherent TTM pages.", [vmw_dma_map_populate] = "Keeping DMA mappings.", [vmw_dma_map_bind] = "Giving up DMA mappings early."}; -#ifdef CONFIG_X86 - const struct dma_map_ops *dma_ops = get_dma_ops(dev_priv->dev->dev); -#ifdef CONFIG_INTEL_IOMMU - if (intel_iommu_enabled) { + if (vmw_force_coherent) + dev_priv->map_mode = vmw_dma_alloc_coherent; + else if (vmw_assume_iommu(dev_priv->dev)) dev_priv->map_mode = vmw_dma_map_populate; - goto out_fixup; - } -#endif - - if (!(vmw_force_iommu || vmw_force_coherent)) { + else if (!vmw_force_iommu) dev_priv->map_mode = vmw_dma_phys; - DRM_INFO("DMA map mode: %s\n", names[dev_priv->map_mode]); - return 0; - } - - dev_priv->map_mode = vmw_dma_map_populate; - - if (dma_ops && dma_ops->sync_single_for_cpu) + else if (IS_ENABLED(CONFIG_SWIOTLB) && swiotlb_nr_tbl()) dev_priv->map_mode = vmw_dma_alloc_coherent; -#ifdef CONFIG_SWIOTLB - if (swiotlb_nr_tbl() == 0) + else dev_priv->map_mode = vmw_dma_map_populate; -#endif -#ifdef CONFIG_INTEL_IOMMU -out_fixup: -#endif - if (dev_priv->map_mode == vmw_dma_map_populate && - vmw_restrict_iommu) + if (dev_priv->map_mode == vmw_dma_map_populate && vmw_restrict_iommu) dev_priv->map_mode = vmw_dma_map_bind; - if (vmw_force_coherent) - dev_priv->map_mode = vmw_dma_alloc_coherent; - -#if !defined(CONFIG_SWIOTLB) && !defined(CONFIG_INTEL_IOMMU) - /* - * No coherent page pool - */ - if (dev_priv->map_mode == vmw_dma_alloc_coherent) + /* No TTM coherent page pool? FIXME: Ask TTM instead! */ + if (!(IS_ENABLED(CONFIG_SWIOTLB) || IS_ENABLED(CONFIG_INTEL_IOMMU)) && + (dev_priv->map_mode == vmw_dma_alloc_coherent)) return -EINVAL; -#endif - -#else /* CONFIG_X86 */ - dev_priv->map_mode = vmw_dma_map_populate; -#endif /* CONFIG_X86 */ DRM_INFO("DMA map mode: %s\n", names[dev_priv->map_mode]); - return 0; } @@ -625,24 +612,20 @@ out_fixup: * With 32-bit we can only handle 32 bit PFNs. Optionally set that * restriction also for 64-bit systems. */ -#ifdef CONFIG_INTEL_IOMMU static int vmw_dma_masks(struct vmw_private *dev_priv) { struct drm_device *dev = dev_priv->dev; + int ret = 0; - if (intel_iommu_enabled && + ret = dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(64)); + if (dev_priv->map_mode != vmw_dma_phys && (sizeof(unsigned long) == 4 || vmw_restrict_dma_mask)) { DRM_INFO("Restricting DMA addresses to 44 bits.\n"); - return dma_set_mask(dev->dev, DMA_BIT_MASK(44)); + return dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(44)); } - return 0; -} -#else -static int vmw_dma_masks(struct vmw_private *dev_priv) -{ - return 0; + + return ret; } -#endif static int vmw_driver_load(struct drm_device *dev, unsigned long chipset) { diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index f2d13a72c05d..88b8178d4687 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -3570,7 +3570,7 @@ int vmw_execbuf_fence_commands(struct drm_file *file_priv, *p_fence = NULL; } - return 0; + return ret; } /** diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index b351fb5214d3..ed2f67822f45 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -1646,7 +1646,7 @@ static int vmw_kms_check_topology(struct drm_device *dev, struct drm_connector_state *conn_state; struct vmw_connector_state *vmw_conn_state; - if (!du->pref_active) { + if (!du->pref_active && new_crtc_state->enable) { ret = -EINVAL; goto clean; } @@ -2554,8 +2554,8 @@ void vmw_kms_helper_validation_finish(struct vmw_private *dev_priv, user_fence_rep) { struct vmw_fence_obj *fence = NULL; - uint32_t handle; - int ret; + uint32_t handle = 0; + int ret = 0; if (file_priv || user_fence_rep || vmw_validation_has_bos(ctx) || out_fence) diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c index 474b00e19697..0a7d4395d427 100644 --- a/drivers/gpu/ipu-v3/ipu-common.c +++ b/drivers/gpu/ipu-v3/ipu-common.c @@ -898,8 +898,8 @@ static struct ipu_devtype ipu_type_imx51 = { .cpmem_ofs = 0x1f000000, .srm_ofs = 0x1f040000, .tpm_ofs = 0x1f060000, - .csi0_ofs = 0x1f030000, - .csi1_ofs = 0x1f038000, + .csi0_ofs = 0x1e030000, + .csi1_ofs = 0x1e038000, .ic_ofs = 0x1e020000, .disp0_ofs = 0x1e040000, .disp1_ofs = 0x1e048000, @@ -914,8 +914,8 @@ static struct ipu_devtype ipu_type_imx53 = { .cpmem_ofs = 0x07000000, .srm_ofs = 0x07040000, .tpm_ofs = 0x07060000, - .csi0_ofs = 0x07030000, - .csi1_ofs = 0x07038000, + .csi0_ofs = 0x06030000, + .csi1_ofs = 0x06038000, .ic_ofs = 0x06020000, .disp0_ofs = 0x06040000, .disp1_ofs = 0x06048000, diff --git a/drivers/gpu/ipu-v3/ipu-pre.c b/drivers/gpu/ipu-v3/ipu-pre.c index 2f8db9d62551..4a28f3fbb0a2 100644 --- a/drivers/gpu/ipu-v3/ipu-pre.c +++ b/drivers/gpu/ipu-v3/ipu-pre.c @@ -106,6 +106,7 @@ struct ipu_pre { void *buffer_virt; bool in_use; unsigned int safe_window_end; + unsigned int last_bufaddr; }; static DEFINE_MUTEX(ipu_pre_list_mutex); @@ -185,6 +186,7 @@ void ipu_pre_configure(struct ipu_pre *pre, unsigned int width, writel(bufaddr, pre->regs + IPU_PRE_CUR_BUF); writel(bufaddr, pre->regs + IPU_PRE_NEXT_BUF); + pre->last_bufaddr = bufaddr; val = IPU_PRE_PREF_ENG_CTRL_INPUT_PIXEL_FORMAT(0) | IPU_PRE_PREF_ENG_CTRL_INPUT_ACTIVE_BPP(active_bpp) | @@ -242,7 +244,11 @@ void ipu_pre_update(struct ipu_pre *pre, unsigned int bufaddr) unsigned short current_yblock; u32 val; + if (bufaddr == pre->last_bufaddr) + return; + writel(bufaddr, pre->regs + IPU_PRE_NEXT_BUF); + pre->last_bufaddr = bufaddr; do { if (time_after(jiffies, timeout)) { diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c index c530476edba6..ac9fda1b5a72 100644 --- a/drivers/hid/hid-debug.c +++ b/drivers/hid/hid-debug.c @@ -30,6 +30,7 @@ #include <linux/debugfs.h> #include <linux/seq_file.h> +#include <linux/kfifo.h> #include <linux/sched/signal.h> #include <linux/export.h> #include <linux/slab.h> @@ -661,17 +662,12 @@ EXPORT_SYMBOL_GPL(hid_dump_device); /* enqueue string to 'events' ring buffer */ void hid_debug_event(struct hid_device *hdev, char *buf) { - unsigned i; struct hid_debug_list *list; unsigned long flags; spin_lock_irqsave(&hdev->debug_list_lock, flags); - list_for_each_entry(list, &hdev->debug_list, node) { - for (i = 0; buf[i]; i++) - list->hid_debug_buf[(list->tail + i) % HID_DEBUG_BUFSIZE] = - buf[i]; - list->tail = (list->tail + i) % HID_DEBUG_BUFSIZE; - } + list_for_each_entry(list, &hdev->debug_list, node) + kfifo_in(&list->hid_debug_fifo, buf, strlen(buf)); spin_unlock_irqrestore(&hdev->debug_list_lock, flags); wake_up_interruptible(&hdev->debug_wait); @@ -722,8 +718,7 @@ void hid_dump_input(struct hid_device *hdev, struct hid_usage *usage, __s32 valu hid_debug_event(hdev, buf); kfree(buf); - wake_up_interruptible(&hdev->debug_wait); - + wake_up_interruptible(&hdev->debug_wait); } EXPORT_SYMBOL_GPL(hid_dump_input); @@ -1083,8 +1078,8 @@ static int hid_debug_events_open(struct inode *inode, struct file *file) goto out; } - if (!(list->hid_debug_buf = kzalloc(HID_DEBUG_BUFSIZE, GFP_KERNEL))) { - err = -ENOMEM; + err = kfifo_alloc(&list->hid_debug_fifo, HID_DEBUG_FIFOSIZE, GFP_KERNEL); + if (err) { kfree(list); goto out; } @@ -1104,77 +1099,57 @@ static ssize_t hid_debug_events_read(struct file *file, char __user *buffer, size_t count, loff_t *ppos) { struct hid_debug_list *list = file->private_data; - int ret = 0, len; + int ret = 0, copied; DECLARE_WAITQUEUE(wait, current); mutex_lock(&list->read_mutex); - while (ret == 0) { - if (list->head == list->tail) { - add_wait_queue(&list->hdev->debug_wait, &wait); - set_current_state(TASK_INTERRUPTIBLE); - - while (list->head == list->tail) { - if (file->f_flags & O_NONBLOCK) { - ret = -EAGAIN; - break; - } - if (signal_pending(current)) { - ret = -ERESTARTSYS; - break; - } + if (kfifo_is_empty(&list->hid_debug_fifo)) { + add_wait_queue(&list->hdev->debug_wait, &wait); + set_current_state(TASK_INTERRUPTIBLE); + + while (kfifo_is_empty(&list->hid_debug_fifo)) { + if (file->f_flags & O_NONBLOCK) { + ret = -EAGAIN; + break; + } - if (!list->hdev || !list->hdev->debug) { - ret = -EIO; - set_current_state(TASK_RUNNING); - goto out; - } + if (signal_pending(current)) { + ret = -ERESTARTSYS; + break; + } - /* allow O_NONBLOCK from other threads */ - mutex_unlock(&list->read_mutex); - schedule(); - mutex_lock(&list->read_mutex); - set_current_state(TASK_INTERRUPTIBLE); + /* if list->hdev is NULL we cannot remove_wait_queue(). + * if list->hdev->debug is 0 then hid_debug_unregister() + * was already called and list->hdev is being destroyed. + * if we add remove_wait_queue() here we can hit a race. + */ + if (!list->hdev || !list->hdev->debug) { + ret = -EIO; + set_current_state(TASK_RUNNING); + goto out; } - set_current_state(TASK_RUNNING); - remove_wait_queue(&list->hdev->debug_wait, &wait); + /* allow O_NONBLOCK from other threads */ + mutex_unlock(&list->read_mutex); + schedule(); + mutex_lock(&list->read_mutex); + set_current_state(TASK_INTERRUPTIBLE); } - if (ret) - goto out; + __set_current_state(TASK_RUNNING); + remove_wait_queue(&list->hdev->debug_wait, &wait); - /* pass the ringbuffer contents to userspace */ -copy_rest: - if (list->tail == list->head) + if (ret) goto out; - if (list->tail > list->head) { - len = list->tail - list->head; - if (len > count) - len = count; - - if (copy_to_user(buffer + ret, &list->hid_debug_buf[list->head], len)) { - ret = -EFAULT; - goto out; - } - ret += len; - list->head += len; - } else { - len = HID_DEBUG_BUFSIZE - list->head; - if (len > count) - len = count; - - if (copy_to_user(buffer, &list->hid_debug_buf[list->head], len)) { - ret = -EFAULT; - goto out; - } - list->head = 0; - ret += len; - count -= len; - if (count > 0) - goto copy_rest; - } - } + + /* pass the fifo content to userspace, locking is not needed with only + * one concurrent reader and one concurrent writer + */ + ret = kfifo_to_user(&list->hid_debug_fifo, buffer, count, &copied); + if (ret) + goto out; + ret = copied; out: mutex_unlock(&list->read_mutex); return ret; @@ -1185,7 +1160,7 @@ static __poll_t hid_debug_events_poll(struct file *file, poll_table *wait) struct hid_debug_list *list = file->private_data; poll_wait(file, &list->hdev->debug_wait, wait); - if (list->head != list->tail) + if (!kfifo_is_empty(&list->hid_debug_fifo)) return EPOLLIN | EPOLLRDNORM; if (!list->hdev->debug) return EPOLLERR | EPOLLHUP; @@ -1200,7 +1175,7 @@ static int hid_debug_events_release(struct inode *inode, struct file *file) spin_lock_irqsave(&list->hdev->debug_list_lock, flags); list_del(&list->node); spin_unlock_irqrestore(&list->hdev->debug_list_lock, flags); - kfree(list->hid_debug_buf); + kfifo_free(&list->hid_debug_fifo); kfree(list); return 0; @@ -1246,4 +1221,3 @@ void hid_debug_exit(void) { debugfs_remove_recursive(hid_debug_root); } - diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c index 4adec4ab7d06..59ee01f3d022 100644 --- a/drivers/hwmon/nct6775.c +++ b/drivers/hwmon/nct6775.c @@ -3594,7 +3594,8 @@ nct6775_check_fan_inputs(struct nct6775_data *data) fan5pin |= cr1b & BIT(5); fan5pin |= creb & BIT(5); - fan6pin = creb & BIT(3); + fan6pin = !dsw_en && (cr2d & BIT(1)); + fan6pin |= creb & BIT(3); pwm5pin |= cr2d & BIT(7); pwm5pin |= (creb & BIT(4)) && !(cr2a & BIT(0)); diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c index b1086bfb0465..cd9c65f3d404 100644 --- a/drivers/i2c/busses/i2c-omap.c +++ b/drivers/i2c/busses/i2c-omap.c @@ -1500,8 +1500,7 @@ static int omap_i2c_remove(struct platform_device *pdev) return 0; } -#ifdef CONFIG_PM -static int omap_i2c_runtime_suspend(struct device *dev) +static int __maybe_unused omap_i2c_runtime_suspend(struct device *dev) { struct omap_i2c_dev *omap = dev_get_drvdata(dev); @@ -1527,7 +1526,7 @@ static int omap_i2c_runtime_suspend(struct device *dev) return 0; } -static int omap_i2c_runtime_resume(struct device *dev) +static int __maybe_unused omap_i2c_runtime_resume(struct device *dev) { struct omap_i2c_dev *omap = dev_get_drvdata(dev); @@ -1542,20 +1541,18 @@ static int omap_i2c_runtime_resume(struct device *dev) } static const struct dev_pm_ops omap_i2c_pm_ops = { + SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, + pm_runtime_force_resume) SET_RUNTIME_PM_OPS(omap_i2c_runtime_suspend, omap_i2c_runtime_resume, NULL) }; -#define OMAP_I2C_PM_OPS (&omap_i2c_pm_ops) -#else -#define OMAP_I2C_PM_OPS NULL -#endif /* CONFIG_PM */ static struct platform_driver omap_i2c_driver = { .probe = omap_i2c_probe, .remove = omap_i2c_remove, .driver = { .name = "omap_i2c", - .pm = OMAP_I2C_PM_OPS, + .pm = &omap_i2c_pm_ops, .of_match_table = of_match_ptr(omap_i2c_of_match), }, }; diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c index c39f89d2deba..2dc628d4f1ae 100644 --- a/drivers/i3c/master.c +++ b/drivers/i3c/master.c @@ -1828,7 +1828,7 @@ int i3c_master_add_i3c_dev_locked(struct i3c_master_controller *master, ret = i3c_master_retrieve_dev_info(newdev); if (ret) - goto err_free_dev; + goto err_detach_dev; olddev = i3c_master_search_i3c_dev_duplicate(newdev); if (olddev) { diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c index f8c00b94817f..bb03079fbade 100644 --- a/drivers/i3c/master/dw-i3c-master.c +++ b/drivers/i3c/master/dw-i3c-master.c @@ -419,12 +419,9 @@ static void dw_i3c_master_enqueue_xfer(struct dw_i3c_master *master, spin_unlock_irqrestore(&master->xferqueue.lock, flags); } -static void dw_i3c_master_dequeue_xfer(struct dw_i3c_master *master, - struct dw_i3c_xfer *xfer) +static void dw_i3c_master_dequeue_xfer_locked(struct dw_i3c_master *master, + struct dw_i3c_xfer *xfer) { - unsigned long flags; - - spin_lock_irqsave(&master->xferqueue.lock, flags); if (master->xferqueue.cur == xfer) { u32 status; @@ -439,6 +436,15 @@ static void dw_i3c_master_dequeue_xfer(struct dw_i3c_master *master, } else { list_del_init(&xfer->node); } +} + +static void dw_i3c_master_dequeue_xfer(struct dw_i3c_master *master, + struct dw_i3c_xfer *xfer) +{ + unsigned long flags; + + spin_lock_irqsave(&master->xferqueue.lock, flags); + dw_i3c_master_dequeue_xfer_locked(master, xfer); spin_unlock_irqrestore(&master->xferqueue.lock, flags); } @@ -494,7 +500,7 @@ static void dw_i3c_master_end_xfer_locked(struct dw_i3c_master *master, u32 isr) complete(&xfer->comp); if (ret < 0) { - dw_i3c_master_dequeue_xfer(master, xfer); + dw_i3c_master_dequeue_xfer_locked(master, xfer); writel(readl(master->regs + DEVICE_CTRL) | DEV_CTRL_RESUME, master->regs + DEVICE_CTRL); } diff --git a/drivers/ide/ide-atapi.c b/drivers/ide/ide-atapi.c index da58020a144e..33a28cde126c 100644 --- a/drivers/ide/ide-atapi.c +++ b/drivers/ide/ide-atapi.c @@ -235,21 +235,28 @@ EXPORT_SYMBOL_GPL(ide_prep_sense); int ide_queue_sense_rq(ide_drive_t *drive, void *special) { - struct request *sense_rq = drive->sense_rq; + ide_hwif_t *hwif = drive->hwif; + struct request *sense_rq; + unsigned long flags; + + spin_lock_irqsave(&hwif->lock, flags); /* deferred failure from ide_prep_sense() */ if (!drive->sense_rq_armed) { printk(KERN_WARNING PFX "%s: error queuing a sense request\n", drive->name); + spin_unlock_irqrestore(&hwif->lock, flags); return -ENOMEM; } + sense_rq = drive->sense_rq; ide_req(sense_rq)->special = special; drive->sense_rq_armed = false; drive->hwif->rq = NULL; ide_insert_request_head(drive, sense_rq); + spin_unlock_irqrestore(&hwif->lock, flags); return 0; } EXPORT_SYMBOL_GPL(ide_queue_sense_rq); diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c index 8445b484ae69..b137f27a34d5 100644 --- a/drivers/ide/ide-io.c +++ b/drivers/ide/ide-io.c @@ -68,8 +68,10 @@ int ide_end_rq(ide_drive_t *drive, struct request *rq, blk_status_t error, } if (!blk_update_request(rq, error, nr_bytes)) { - if (rq == drive->sense_rq) + if (rq == drive->sense_rq) { drive->sense_rq = NULL; + drive->sense_rq_active = false; + } __blk_mq_end_request(rq, error); return 0; @@ -451,16 +453,11 @@ void ide_requeue_and_plug(ide_drive_t *drive, struct request *rq) blk_mq_delay_run_hw_queue(q->queue_hw_ctx[0], 3); } -/* - * Issue a new request to a device. - */ -blk_status_t ide_queue_rq(struct blk_mq_hw_ctx *hctx, - const struct blk_mq_queue_data *bd) +blk_status_t ide_issue_rq(ide_drive_t *drive, struct request *rq, + bool local_requeue) { - ide_drive_t *drive = hctx->queue->queuedata; - ide_hwif_t *hwif = drive->hwif; + ide_hwif_t *hwif = drive->hwif; struct ide_host *host = hwif->host; - struct request *rq = bd->rq; ide_startstop_t startstop; if (!blk_rq_is_passthrough(rq) && !(rq->rq_flags & RQF_DONTPREP)) { @@ -474,8 +471,6 @@ blk_status_t ide_queue_rq(struct blk_mq_hw_ctx *hctx, if (ide_lock_host(host, hwif)) return BLK_STS_DEV_RESOURCE; - blk_mq_start_request(rq); - spin_lock_irq(&hwif->lock); if (!ide_lock_port(hwif)) { @@ -511,18 +506,6 @@ repeat: drive->dev_flags &= ~(IDE_DFLAG_SLEEPING | IDE_DFLAG_PARKED); /* - * we know that the queue isn't empty, but this can happen - * if ->prep_rq() decides to kill a request - */ - if (!rq) { - rq = bd->rq; - if (!rq) { - ide_unlock_port(hwif); - goto out; - } - } - - /* * Sanity: don't accept a request that isn't a PM request * if we are currently power managed. This is very important as * blk_stop_queue() doesn't prevent the blk_fetch_request() @@ -560,9 +543,12 @@ repeat: } } else { plug_device: + if (local_requeue) + list_add(&rq->queuelist, &drive->rq_list); spin_unlock_irq(&hwif->lock); ide_unlock_host(host); - ide_requeue_and_plug(drive, rq); + if (!local_requeue) + ide_requeue_and_plug(drive, rq); return BLK_STS_OK; } @@ -573,6 +559,26 @@ out: return BLK_STS_OK; } +/* + * Issue a new request to a device. + */ +blk_status_t ide_queue_rq(struct blk_mq_hw_ctx *hctx, + const struct blk_mq_queue_data *bd) +{ + ide_drive_t *drive = hctx->queue->queuedata; + ide_hwif_t *hwif = drive->hwif; + + spin_lock_irq(&hwif->lock); + if (drive->sense_rq_active) { + spin_unlock_irq(&hwif->lock); + return BLK_STS_DEV_RESOURCE; + } + spin_unlock_irq(&hwif->lock); + + blk_mq_start_request(bd->rq); + return ide_issue_rq(drive, bd->rq, false); +} + static int drive_is_ready(ide_drive_t *drive) { ide_hwif_t *hwif = drive->hwif; @@ -893,13 +899,8 @@ EXPORT_SYMBOL_GPL(ide_pad_transfer); void ide_insert_request_head(ide_drive_t *drive, struct request *rq) { - ide_hwif_t *hwif = drive->hwif; - unsigned long flags; - - spin_lock_irqsave(&hwif->lock, flags); + drive->sense_rq_active = true; list_add_tail(&rq->queuelist, &drive->rq_list); - spin_unlock_irqrestore(&hwif->lock, flags); - kblockd_schedule_work(&drive->rq_work); } EXPORT_SYMBOL_GPL(ide_insert_request_head); diff --git a/drivers/ide/ide-park.c b/drivers/ide/ide-park.c index 102aa3bc3e7f..8af7af6001eb 100644 --- a/drivers/ide/ide-park.c +++ b/drivers/ide/ide-park.c @@ -54,7 +54,9 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout) scsi_req(rq)->cmd[0] = REQ_UNPARK_HEADS; scsi_req(rq)->cmd_len = 1; ide_req(rq)->type = ATA_PRIV_MISC; + spin_lock_irq(&hwif->lock); ide_insert_request_head(drive, rq); + spin_unlock_irq(&hwif->lock); out: return; diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c index 63627be0811a..5aeaca24a28f 100644 --- a/drivers/ide/ide-probe.c +++ b/drivers/ide/ide-probe.c @@ -1159,18 +1159,27 @@ static void drive_rq_insert_work(struct work_struct *work) ide_drive_t *drive = container_of(work, ide_drive_t, rq_work); ide_hwif_t *hwif = drive->hwif; struct request *rq; + blk_status_t ret; LIST_HEAD(list); - spin_lock_irq(&hwif->lock); - if (!list_empty(&drive->rq_list)) - list_splice_init(&drive->rq_list, &list); - spin_unlock_irq(&hwif->lock); + blk_mq_quiesce_queue(drive->queue); - while (!list_empty(&list)) { - rq = list_first_entry(&list, struct request, queuelist); + ret = BLK_STS_OK; + spin_lock_irq(&hwif->lock); + while (!list_empty(&drive->rq_list)) { + rq = list_first_entry(&drive->rq_list, struct request, queuelist); list_del_init(&rq->queuelist); - blk_execute_rq_nowait(drive->queue, rq->rq_disk, rq, true, NULL); + + spin_unlock_irq(&hwif->lock); + ret = ide_issue_rq(drive, rq, true); + spin_lock_irq(&hwif->lock); } + spin_unlock_irq(&hwif->lock); + + blk_mq_unquiesce_queue(drive->queue); + + if (ret != BLK_STS_OK) + kblockd_schedule_work(&drive->rq_work); } static const u8 ide_hwif_to_major[] = diff --git a/drivers/iio/adc/axp288_adc.c b/drivers/iio/adc/axp288_adc.c index 031d568b4972..4e339cfd0c54 100644 --- a/drivers/iio/adc/axp288_adc.c +++ b/drivers/iio/adc/axp288_adc.c @@ -27,9 +27,18 @@ #include <linux/iio/machine.h> #include <linux/iio/driver.h> -#define AXP288_ADC_EN_MASK 0xF1 -#define AXP288_ADC_TS_PIN_GPADC 0xF2 -#define AXP288_ADC_TS_PIN_ON 0xF3 +/* + * This mask enables all ADCs except for the battery temp-sensor (TS), that is + * left as-is to avoid breaking charging on devices without a temp-sensor. + */ +#define AXP288_ADC_EN_MASK 0xF0 +#define AXP288_ADC_TS_ENABLE 0x01 + +#define AXP288_ADC_TS_CURRENT_ON_OFF_MASK GENMASK(1, 0) +#define AXP288_ADC_TS_CURRENT_OFF (0 << 0) +#define AXP288_ADC_TS_CURRENT_ON_WHEN_CHARGING (1 << 0) +#define AXP288_ADC_TS_CURRENT_ON_ONDEMAND (2 << 0) +#define AXP288_ADC_TS_CURRENT_ON (3 << 0) enum axp288_adc_id { AXP288_ADC_TS, @@ -44,6 +53,7 @@ enum axp288_adc_id { struct axp288_adc_info { int irq; struct regmap *regmap; + bool ts_enabled; }; static const struct iio_chan_spec axp288_adc_channels[] = { @@ -115,21 +125,33 @@ static int axp288_adc_read_channel(int *val, unsigned long address, return IIO_VAL_INT; } -static int axp288_adc_set_ts(struct regmap *regmap, unsigned int mode, - unsigned long address) +/* + * The current-source used for the battery temp-sensor (TS) is shared + * with the GPADC. For proper fuel-gauge and charger operation the TS + * current-source needs to be permanently on. But to read the GPADC we + * need to temporary switch the TS current-source to ondemand, so that + * the GPADC can use it, otherwise we will always read an all 0 value. + */ +static int axp288_adc_set_ts(struct axp288_adc_info *info, + unsigned int mode, unsigned long address) { int ret; - /* channels other than GPADC do not need to switch TS pin */ + /* No need to switch the current-source if the TS pin is disabled */ + if (!info->ts_enabled) + return 0; + + /* Channels other than GPADC do not need the current source */ if (address != AXP288_GP_ADC_H) return 0; - ret = regmap_write(regmap, AXP288_ADC_TS_PIN_CTRL, mode); + ret = regmap_update_bits(info->regmap, AXP288_ADC_TS_PIN_CTRL, + AXP288_ADC_TS_CURRENT_ON_OFF_MASK, mode); if (ret) return ret; /* When switching to the GPADC pin give things some time to settle */ - if (mode == AXP288_ADC_TS_PIN_GPADC) + if (mode == AXP288_ADC_TS_CURRENT_ON_ONDEMAND) usleep_range(6000, 10000); return 0; @@ -145,14 +167,14 @@ static int axp288_adc_read_raw(struct iio_dev *indio_dev, mutex_lock(&indio_dev->mlock); switch (mask) { case IIO_CHAN_INFO_RAW: - if (axp288_adc_set_ts(info->regmap, AXP288_ADC_TS_PIN_GPADC, + if (axp288_adc_set_ts(info, AXP288_ADC_TS_CURRENT_ON_ONDEMAND, chan->address)) { dev_err(&indio_dev->dev, "GPADC mode\n"); ret = -EINVAL; break; } ret = axp288_adc_read_channel(val, chan->address, info->regmap); - if (axp288_adc_set_ts(info->regmap, AXP288_ADC_TS_PIN_ON, + if (axp288_adc_set_ts(info, AXP288_ADC_TS_CURRENT_ON, chan->address)) dev_err(&indio_dev->dev, "TS pin restore\n"); break; @@ -164,13 +186,35 @@ static int axp288_adc_read_raw(struct iio_dev *indio_dev, return ret; } -static int axp288_adc_set_state(struct regmap *regmap) +static int axp288_adc_initialize(struct axp288_adc_info *info) { - /* ADC should be always enabled for internal FG to function */ - if (regmap_write(regmap, AXP288_ADC_TS_PIN_CTRL, AXP288_ADC_TS_PIN_ON)) - return -EIO; + int ret, adc_enable_val; + + /* + * Determine if the TS pin is enabled and set the TS current-source + * accordingly. + */ + ret = regmap_read(info->regmap, AXP20X_ADC_EN1, &adc_enable_val); + if (ret) + return ret; + + if (adc_enable_val & AXP288_ADC_TS_ENABLE) { + info->ts_enabled = true; + ret = regmap_update_bits(info->regmap, AXP288_ADC_TS_PIN_CTRL, + AXP288_ADC_TS_CURRENT_ON_OFF_MASK, + AXP288_ADC_TS_CURRENT_ON); + } else { + info->ts_enabled = false; + ret = regmap_update_bits(info->regmap, AXP288_ADC_TS_PIN_CTRL, + AXP288_ADC_TS_CURRENT_ON_OFF_MASK, + AXP288_ADC_TS_CURRENT_OFF); + } + if (ret) + return ret; - return regmap_write(regmap, AXP20X_ADC_EN1, AXP288_ADC_EN_MASK); + /* Turn on the ADC for all channels except TS, leave TS as is */ + return regmap_update_bits(info->regmap, AXP20X_ADC_EN1, + AXP288_ADC_EN_MASK, AXP288_ADC_EN_MASK); } static const struct iio_info axp288_adc_iio_info = { @@ -200,7 +244,7 @@ static int axp288_adc_probe(struct platform_device *pdev) * Set ADC to enabled state at all time, including system suspend. * otherwise internal fuel gauge functionality may be affected. */ - ret = axp288_adc_set_state(axp20x->regmap); + ret = axp288_adc_initialize(info); if (ret) { dev_err(&pdev->dev, "unable to enable ADC device\n"); return ret; diff --git a/drivers/iio/adc/ti-ads8688.c b/drivers/iio/adc/ti-ads8688.c index 184d686ebd99..8b4568edd5cb 100644 --- a/drivers/iio/adc/ti-ads8688.c +++ b/drivers/iio/adc/ti-ads8688.c @@ -41,6 +41,7 @@ #define ADS8688_VREF_MV 4096 #define ADS8688_REALBITS 16 +#define ADS8688_MAX_CHANNELS 8 /* * enum ads8688_range - ADS8688 reference voltage range @@ -385,7 +386,7 @@ static irqreturn_t ads8688_trigger_handler(int irq, void *p) { struct iio_poll_func *pf = p; struct iio_dev *indio_dev = pf->indio_dev; - u16 buffer[8]; + u16 buffer[ADS8688_MAX_CHANNELS + sizeof(s64)/sizeof(u16)]; int i, j = 0; for (i = 0; i < indio_dev->masklength; i++) { diff --git a/drivers/iio/chemical/atlas-ph-sensor.c b/drivers/iio/chemical/atlas-ph-sensor.c index a406ad31b096..3a20cb5d9bff 100644 --- a/drivers/iio/chemical/atlas-ph-sensor.c +++ b/drivers/iio/chemical/atlas-ph-sensor.c @@ -444,9 +444,8 @@ static int atlas_read_raw(struct iio_dev *indio_dev, case IIO_CHAN_INFO_SCALE: switch (chan->type) { case IIO_TEMP: - *val = 1; /* 0.01 */ - *val2 = 100; - break; + *val = 10; + return IIO_VAL_INT; case IIO_PH: *val = 1; /* 0.001 */ *val2 = 1000; @@ -477,7 +476,7 @@ static int atlas_write_raw(struct iio_dev *indio_dev, int val, int val2, long mask) { struct atlas_data *data = iio_priv(indio_dev); - __be32 reg = cpu_to_be32(val); + __be32 reg = cpu_to_be32(val / 10); if (val2 != 0 || val < 0 || val > 20000) return -EINVAL; diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h index 3cd830d52967..616734313f0c 100644 --- a/drivers/infiniband/core/core_priv.h +++ b/drivers/infiniband/core/core_priv.h @@ -267,7 +267,6 @@ static inline int ib_mad_enforce_security(struct ib_mad_agent_private *map, #endif struct ib_device *ib_device_get_by_index(u32 ifindex); -void ib_device_put(struct ib_device *device); /* RDMA device netlink */ void nldev_init(void); void nldev_exit(void); diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c index 8872453e26c0..238ec42778ef 100644 --- a/drivers/infiniband/core/device.c +++ b/drivers/infiniband/core/device.c @@ -156,19 +156,26 @@ struct ib_device *ib_device_get_by_index(u32 index) down_read(&lists_rwsem); device = __ib_device_get_by_index(index); if (device) { - /* Do not return a device if unregistration has started. */ - if (!refcount_inc_not_zero(&device->refcount)) + if (!ib_device_try_get(device)) device = NULL; } up_read(&lists_rwsem); return device; } +/** + * ib_device_put - Release IB device reference + * @device: device whose reference to be released + * + * ib_device_put() releases reference to the IB device to allow it to be + * unregistered and eventually free. + */ void ib_device_put(struct ib_device *device) { if (refcount_dec_and_test(&device->refcount)) complete(&device->unreg_completion); } +EXPORT_SYMBOL(ib_device_put); static struct ib_device *__ib_device_get_by_name(const char *name) { @@ -303,7 +310,6 @@ struct ib_device *ib_alloc_device(size_t size) rwlock_init(&device->client_data_lock); INIT_LIST_HEAD(&device->client_data_list); INIT_LIST_HEAD(&device->port_list); - refcount_set(&device->refcount, 1); init_completion(&device->unreg_completion); return device; @@ -620,6 +626,7 @@ int ib_register_device(struct ib_device *device, const char *name, goto cg_cleanup; } + refcount_set(&device->refcount, 1); device->reg_state = IB_DEV_REGISTERED; list_for_each_entry(client, &client_list, list) diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c index a4ec43093cb3..acb882f279cb 100644 --- a/drivers/infiniband/core/umem_odp.c +++ b/drivers/infiniband/core/umem_odp.c @@ -352,6 +352,8 @@ struct ib_umem_odp *ib_alloc_odp_umem(struct ib_ucontext_per_mm *per_mm, umem->writable = 1; umem->is_odp = 1; odp_data->per_mm = per_mm; + umem->owning_mm = per_mm->mm; + mmgrab(umem->owning_mm); mutex_init(&odp_data->umem_mutex); init_completion(&odp_data->notifier_completion); @@ -384,6 +386,7 @@ struct ib_umem_odp *ib_alloc_odp_umem(struct ib_ucontext_per_mm *per_mm, out_page_list: vfree(odp_data->page_list); out_odp_data: + mmdrop(umem->owning_mm); kfree(odp_data); return ERR_PTR(ret); } diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 2890a77339e1..5f366838b7ff 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -204,6 +204,9 @@ void ib_uverbs_release_file(struct kref *ref) if (atomic_dec_and_test(&file->device->refcount)) ib_uverbs_comp_dev(file->device); + if (file->async_file) + kref_put(&file->async_file->ref, + ib_uverbs_release_async_event_file); put_device(&file->device->dev); kfree(file); } @@ -964,11 +967,19 @@ void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile) /* Get an arbitrary mm pointer that hasn't been cleaned yet */ mutex_lock(&ufile->umap_lock); - if (!list_empty(&ufile->umaps)) { - mm = list_first_entry(&ufile->umaps, - struct rdma_umap_priv, list) - ->vma->vm_mm; - mmget(mm); + while (!list_empty(&ufile->umaps)) { + int ret; + + priv = list_first_entry(&ufile->umaps, + struct rdma_umap_priv, list); + mm = priv->vma->vm_mm; + ret = mmget_not_zero(mm); + if (!ret) { + list_del_init(&priv->list); + mm = NULL; + continue; + } + break; } mutex_unlock(&ufile->umap_lock); if (!mm) @@ -1096,10 +1107,6 @@ static int ib_uverbs_close(struct inode *inode, struct file *filp) list_del_init(&file->list); mutex_unlock(&file->device->lists_mutex); - if (file->async_file) - kref_put(&file->async_file->ref, - ib_uverbs_release_async_event_file); - kref_put(&file->ref, ib_uverbs_release_file); return 0; diff --git a/drivers/infiniband/core/uverbs_std_types_device.c b/drivers/infiniband/core/uverbs_std_types_device.c index 5030ec480370..2a3f2f01028d 100644 --- a/drivers/infiniband/core/uverbs_std_types_device.c +++ b/drivers/infiniband/core/uverbs_std_types_device.c @@ -168,12 +168,18 @@ void copy_port_attr_to_resp(struct ib_port_attr *attr, static int UVERBS_HANDLER(UVERBS_METHOD_QUERY_PORT)( struct uverbs_attr_bundle *attrs) { - struct ib_device *ib_dev = attrs->ufile->device->ib_dev; + struct ib_device *ib_dev; struct ib_port_attr attr = {}; struct ib_uverbs_query_port_resp_ex resp = {}; + struct ib_ucontext *ucontext; int ret; u8 port_num; + ucontext = ib_uverbs_get_ucontext(attrs); + if (IS_ERR(ucontext)) + return PTR_ERR(ucontext); + ib_dev = ucontext->device; + /* FIXME: Extend the UAPI_DEF_OBJ_NEEDS_FN stuff.. */ if (!ib_dev->ops.query_port) return -EOPNOTSUPP; diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c index c22ebc774a6a..f9a7e9d29c8b 100644 --- a/drivers/infiniband/hw/hfi1/file_ops.c +++ b/drivers/infiniband/hw/hfi1/file_ops.c @@ -488,7 +488,7 @@ static int hfi1_file_mmap(struct file *fp, struct vm_area_struct *vma) vmf = 1; break; case STATUS: - if (flags & (unsigned long)(VM_WRITE | VM_EXEC)) { + if (flags & VM_WRITE) { ret = -EPERM; goto done; } diff --git a/drivers/infiniband/hw/hfi1/ud.c b/drivers/infiniband/hw/hfi1/ud.c index 88242fe95eaa..bf96067876c9 100644 --- a/drivers/infiniband/hw/hfi1/ud.c +++ b/drivers/infiniband/hw/hfi1/ud.c @@ -987,7 +987,6 @@ void hfi1_ud_rcv(struct hfi1_packet *packet) opcode == IB_OPCODE_UD_SEND_ONLY_WITH_IMMEDIATE) { wc.ex.imm_data = packet->ohdr->u.ud.imm_data; wc.wc_flags = IB_WC_WITH_IMM; - tlen -= sizeof(u32); } else if (opcode == IB_OPCODE_UD_SEND_ONLY) { wc.ex.imm_data = 0; wc.wc_flags = 0; diff --git a/drivers/infiniband/hw/hns/hns_roce_srq.c b/drivers/infiniband/hw/hns/hns_roce_srq.c index 960b1946c365..12deacf442cf 100644 --- a/drivers/infiniband/hw/hns/hns_roce_srq.c +++ b/drivers/infiniband/hw/hns/hns_roce_srq.c @@ -210,6 +210,7 @@ struct ib_srq *hns_roce_create_srq(struct ib_pd *pd, struct ib_udata *udata) { struct hns_roce_dev *hr_dev = to_hr_dev(pd->device); + struct hns_roce_ib_create_srq_resp resp = {}; struct hns_roce_srq *srq; int srq_desc_size; int srq_buf_size; @@ -378,16 +379,21 @@ struct ib_srq *hns_roce_create_srq(struct ib_pd *pd, srq->event = hns_roce_ib_srq_event; srq->ibsrq.ext.xrc.srq_num = srq->srqn; + resp.srqn = srq->srqn; if (udata) { - if (ib_copy_to_udata(udata, &srq->srqn, sizeof(__u32))) { + if (ib_copy_to_udata(udata, &resp, + min(udata->outlen, sizeof(resp)))) { ret = -EFAULT; - goto err_wrid; + goto err_srqc_alloc; } } return &srq->ibsrq; +err_srqc_alloc: + hns_roce_srq_free(hr_dev, srq); + err_wrid: kvfree(srq->wrid); diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c index 25439da8976c..936ee1314bcd 100644 --- a/drivers/infiniband/hw/mlx4/mad.c +++ b/drivers/infiniband/hw/mlx4/mad.c @@ -1411,7 +1411,7 @@ int mlx4_ib_send_to_wire(struct mlx4_ib_dev *dev, int slave, u8 port, sqp_mad = (struct mlx4_mad_snd_buf *) (sqp->tx_ring[wire_tx_ix].buf.addr); if (sqp->tx_ring[wire_tx_ix].ah) - rdma_destroy_ah(sqp->tx_ring[wire_tx_ix].ah, 0); + mlx4_ib_destroy_ah(sqp->tx_ring[wire_tx_ix].ah, 0); sqp->tx_ring[wire_tx_ix].ah = ah; ib_dma_sync_single_for_cpu(&dev->ib_dev, sqp->tx_ring[wire_tx_ix].buf.map, @@ -1902,7 +1902,7 @@ static void mlx4_ib_sqp_comp_worker(struct work_struct *work) if (wc.status == IB_WC_SUCCESS) { switch (wc.opcode) { case IB_WC_SEND: - rdma_destroy_ah(sqp->tx_ring[wc.wr_id & + mlx4_ib_destroy_ah(sqp->tx_ring[wc.wr_id & (MLX4_NUM_TUNNEL_BUFS - 1)].ah, 0); sqp->tx_ring[wc.wr_id & (MLX4_NUM_TUNNEL_BUFS - 1)].ah = NULL; @@ -1931,7 +1931,7 @@ static void mlx4_ib_sqp_comp_worker(struct work_struct *work) " status = %d, wrid = 0x%llx\n", ctx->slave, wc.status, wc.wr_id); if (!MLX4_TUN_IS_RECV(wc.wr_id)) { - rdma_destroy_ah(sqp->tx_ring[wc.wr_id & + mlx4_ib_destroy_ah(sqp->tx_ring[wc.wr_id & (MLX4_NUM_TUNNEL_BUFS - 1)].ah, 0); sqp->tx_ring[wc.wr_id & (MLX4_NUM_TUNNEL_BUFS - 1)].ah = NULL; diff --git a/drivers/infiniband/hw/mlx5/cmd.c b/drivers/infiniband/hw/mlx5/cmd.c index 356bccc715ee..6bcc63aaa50b 100644 --- a/drivers/infiniband/hw/mlx5/cmd.c +++ b/drivers/infiniband/hw/mlx5/cmd.c @@ -345,3 +345,40 @@ int mlx5_cmd_alloc_q_counter(struct mlx5_core_dev *dev, u16 *counter_id, counter_set_id); return err; } + +int mlx5_cmd_mad_ifc(struct mlx5_core_dev *dev, const void *inb, void *outb, + u16 opmod, u8 port) +{ + int outlen = MLX5_ST_SZ_BYTES(mad_ifc_out); + int inlen = MLX5_ST_SZ_BYTES(mad_ifc_in); + int err = -ENOMEM; + void *data; + void *resp; + u32 *out; + u32 *in; + + in = kzalloc(inlen, GFP_KERNEL); + out = kzalloc(outlen, GFP_KERNEL); + if (!in || !out) + goto out; + + MLX5_SET(mad_ifc_in, in, opcode, MLX5_CMD_OP_MAD_IFC); + MLX5_SET(mad_ifc_in, in, op_mod, opmod); + MLX5_SET(mad_ifc_in, in, port, port); + + data = MLX5_ADDR_OF(mad_ifc_in, in, mad); + memcpy(data, inb, MLX5_FLD_SZ_BYTES(mad_ifc_in, mad)); + + err = mlx5_cmd_exec(dev, in, inlen, out, outlen); + if (err) + goto out; + + resp = MLX5_ADDR_OF(mad_ifc_out, out, response_mad_packet); + memcpy(outb, resp, + MLX5_FLD_SZ_BYTES(mad_ifc_out, response_mad_packet)); + +out: + kfree(out); + kfree(in); + return err; +} diff --git a/drivers/infiniband/hw/mlx5/cmd.h b/drivers/infiniband/hw/mlx5/cmd.h index 1e76dc67a369..923a7b93f507 100644 --- a/drivers/infiniband/hw/mlx5/cmd.h +++ b/drivers/infiniband/hw/mlx5/cmd.h @@ -63,4 +63,6 @@ int mlx5_cmd_xrcd_alloc(struct mlx5_core_dev *dev, u32 *xrcdn, u16 uid); int mlx5_cmd_xrcd_dealloc(struct mlx5_core_dev *dev, u32 xrcdn, u16 uid); int mlx5_cmd_alloc_q_counter(struct mlx5_core_dev *dev, u16 *counter_id, u16 uid); +int mlx5_cmd_mad_ifc(struct mlx5_core_dev *dev, const void *inb, void *outb, + u16 opmod, u8 port); #endif /* MLX5_IB_CMD_H */ diff --git a/drivers/infiniband/hw/mlx5/flow.c b/drivers/infiniband/hw/mlx5/flow.c index e8a1e4498e3f..798591a18484 100644 --- a/drivers/infiniband/hw/mlx5/flow.c +++ b/drivers/infiniband/hw/mlx5/flow.c @@ -630,8 +630,7 @@ const struct uapi_definition mlx5_ib_flow_defs[] = { UAPI_DEF_IS_OBJ_SUPPORTED(flow_is_supported)), UAPI_DEF_CHAIN_OBJ_TREE( UVERBS_OBJECT_FLOW, - &mlx5_ib_fs, - UAPI_DEF_IS_OBJ_SUPPORTED(flow_is_supported)), + &mlx5_ib_fs), UAPI_DEF_CHAIN_OBJ_TREE(UVERBS_OBJECT_FLOW_ACTION, &mlx5_ib_flow_actions), {}, diff --git a/drivers/infiniband/hw/mlx5/ib_rep.c b/drivers/infiniband/hw/mlx5/ib_rep.c index 46a9ddc8ca56..4700cffb5a00 100644 --- a/drivers/infiniband/hw/mlx5/ib_rep.c +++ b/drivers/infiniband/hw/mlx5/ib_rep.c @@ -3,10 +3,11 @@ * Copyright (c) 2018 Mellanox Technologies. All rights reserved. */ +#include <linux/mlx5/vport.h> #include "ib_rep.h" #include "srq.h" -static const struct mlx5_ib_profile rep_profile = { +static const struct mlx5_ib_profile vf_rep_profile = { STAGE_CREATE(MLX5_IB_STAGE_INIT, mlx5_ib_stage_init_init, mlx5_ib_stage_init_cleanup), @@ -46,30 +47,16 @@ static const struct mlx5_ib_profile rep_profile = { }; static int -mlx5_ib_nic_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) -{ - struct mlx5_ib_dev *ibdev; - - ibdev = mlx5_ib_rep_to_dev(rep); - if (!__mlx5_ib_add(ibdev, ibdev->profile)) - return -EINVAL; - return 0; -} - -static void -mlx5_ib_nic_rep_unload(struct mlx5_eswitch_rep *rep) -{ - struct mlx5_ib_dev *ibdev; - - ibdev = mlx5_ib_rep_to_dev(rep); - __mlx5_ib_remove(ibdev, ibdev->profile, MLX5_IB_STAGE_MAX); -} - -static int mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) { + const struct mlx5_ib_profile *profile; struct mlx5_ib_dev *ibdev; + if (rep->vport == MLX5_VPORT_UPLINK) + profile = &uplink_rep_profile; + else + profile = &vf_rep_profile; + ibdev = (struct mlx5_ib_dev *)ib_alloc_device(sizeof(*ibdev)); if (!ibdev) return -ENOMEM; @@ -78,7 +65,7 @@ mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) ibdev->mdev = dev; ibdev->num_ports = max(MLX5_CAP_GEN(dev, num_ports), MLX5_CAP_GEN(dev, num_vhca_ports)); - if (!__mlx5_ib_add(ibdev, &rep_profile)) + if (!__mlx5_ib_add(ibdev, profile)) return -EINVAL; rep->rep_if[REP_IB].priv = ibdev; @@ -105,53 +92,23 @@ static void *mlx5_ib_vport_get_proto_dev(struct mlx5_eswitch_rep *rep) return mlx5_ib_rep_to_dev(rep); } -static void mlx5_ib_rep_register_vf_vports(struct mlx5_ib_dev *dev) -{ - struct mlx5_eswitch *esw = dev->mdev->priv.eswitch; - int total_vfs = MLX5_TOTAL_VPORTS(dev->mdev); - int vport; - - for (vport = 1; vport < total_vfs; vport++) { - struct mlx5_eswitch_rep_if rep_if = {}; - - rep_if.load = mlx5_ib_vport_rep_load; - rep_if.unload = mlx5_ib_vport_rep_unload; - rep_if.get_proto_dev = mlx5_ib_vport_get_proto_dev; - mlx5_eswitch_register_vport_rep(esw, vport, &rep_if, REP_IB); - } -} - -static void mlx5_ib_rep_unregister_vf_vports(struct mlx5_ib_dev *dev) +void mlx5_ib_register_vport_reps(struct mlx5_core_dev *mdev) { - struct mlx5_eswitch *esw = dev->mdev->priv.eswitch; - int total_vfs = MLX5_TOTAL_VPORTS(dev->mdev); - int vport; - - for (vport = 1; vport < total_vfs; vport++) - mlx5_eswitch_unregister_vport_rep(esw, vport, REP_IB); -} - -void mlx5_ib_register_vport_reps(struct mlx5_ib_dev *dev) -{ - struct mlx5_eswitch *esw = dev->mdev->priv.eswitch; + struct mlx5_eswitch *esw = mdev->priv.eswitch; struct mlx5_eswitch_rep_if rep_if = {}; - rep_if.load = mlx5_ib_nic_rep_load; - rep_if.unload = mlx5_ib_nic_rep_unload; + rep_if.load = mlx5_ib_vport_rep_load; + rep_if.unload = mlx5_ib_vport_rep_unload; rep_if.get_proto_dev = mlx5_ib_vport_get_proto_dev; - rep_if.priv = dev; - - mlx5_eswitch_register_vport_rep(esw, 0, &rep_if, REP_IB); - mlx5_ib_rep_register_vf_vports(dev); + mlx5_eswitch_register_vport_reps(esw, &rep_if, REP_IB); } -void mlx5_ib_unregister_vport_reps(struct mlx5_ib_dev *dev) +void mlx5_ib_unregister_vport_reps(struct mlx5_core_dev *mdev) { - struct mlx5_eswitch *esw = dev->mdev->priv.eswitch; + struct mlx5_eswitch *esw = mdev->priv.eswitch; - mlx5_ib_rep_unregister_vf_vports(dev); /* VFs vports */ - mlx5_eswitch_unregister_vport_rep(esw, 0, REP_IB); /* UPLINK PF*/ + mlx5_eswitch_unregister_vport_reps(esw, REP_IB); } u8 mlx5_ib_eswitch_mode(struct mlx5_eswitch *esw) diff --git a/drivers/infiniband/hw/mlx5/ib_rep.h b/drivers/infiniband/hw/mlx5/ib_rep.h index 2ba73636a2fb..798d41e61fb4 100644 --- a/drivers/infiniband/hw/mlx5/ib_rep.h +++ b/drivers/infiniband/hw/mlx5/ib_rep.h @@ -10,14 +10,16 @@ #include "mlx5_ib.h" #ifdef CONFIG_MLX5_ESWITCH +extern const struct mlx5_ib_profile uplink_rep_profile; + u8 mlx5_ib_eswitch_mode(struct mlx5_eswitch *esw); struct mlx5_ib_dev *mlx5_ib_get_rep_ibdev(struct mlx5_eswitch *esw, int vport_index); struct mlx5_ib_dev *mlx5_ib_get_uplink_ibdev(struct mlx5_eswitch *esw); struct mlx5_eswitch_rep *mlx5_ib_vport_rep(struct mlx5_eswitch *esw, int vport_index); -void mlx5_ib_register_vport_reps(struct mlx5_ib_dev *dev); -void mlx5_ib_unregister_vport_reps(struct mlx5_ib_dev *dev); +void mlx5_ib_register_vport_reps(struct mlx5_core_dev *mdev); +void mlx5_ib_unregister_vport_reps(struct mlx5_core_dev *mdev); int create_flow_rule_vport_sq(struct mlx5_ib_dev *dev, struct mlx5_ib_sq *sq); struct net_device *mlx5_ib_get_rep_netdev(struct mlx5_eswitch *esw, @@ -48,8 +50,8 @@ struct mlx5_eswitch_rep *mlx5_ib_vport_rep(struct mlx5_eswitch *esw, return NULL; } -static inline void mlx5_ib_register_vport_reps(struct mlx5_ib_dev *dev) {} -static inline void mlx5_ib_unregister_vport_reps(struct mlx5_ib_dev *dev) {} +static inline void mlx5_ib_register_vport_reps(struct mlx5_core_dev *mdev) {} +static inline void mlx5_ib_unregister_vport_reps(struct mlx5_core_dev *mdev) {} static inline int create_flow_rule_vport_sq(struct mlx5_ib_dev *dev, struct mlx5_ib_sq *sq) { diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c index 558638468edb..6c529e6f3a01 100644 --- a/drivers/infiniband/hw/mlx5/mad.c +++ b/drivers/infiniband/hw/mlx5/mad.c @@ -36,6 +36,7 @@ #include <rdma/ib_smi.h> #include <rdma/ib_pma.h> #include "mlx5_ib.h" +#include "cmd.h" enum { MLX5_IB_VENDOR_CLASS1 = 0x9, @@ -51,9 +52,10 @@ static bool can_do_mad_ifc(struct mlx5_ib_dev *dev, u8 port_num, return dev->mdev->port_caps[port_num - 1].has_smi; } -int mlx5_MAD_IFC(struct mlx5_ib_dev *dev, int ignore_mkey, int ignore_bkey, - u8 port, const struct ib_wc *in_wc, const struct ib_grh *in_grh, - const void *in_mad, void *response_mad) +static int mlx5_MAD_IFC(struct mlx5_ib_dev *dev, int ignore_mkey, + int ignore_bkey, u8 port, const struct ib_wc *in_wc, + const struct ib_grh *in_grh, const void *in_mad, + void *response_mad) { u8 op_modifier = 0; @@ -68,7 +70,8 @@ int mlx5_MAD_IFC(struct mlx5_ib_dev *dev, int ignore_mkey, int ignore_bkey, if (ignore_bkey || !in_wc) op_modifier |= 0x2; - return mlx5_core_mad_ifc(dev->mdev, in_mad, response_mad, op_modifier, port); + return mlx5_cmd_mad_ifc(dev->mdev, in_mad, response_mad, op_modifier, + port); } static int process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 94fe253d4956..581ae11e2fc9 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -331,8 +331,8 @@ out: spin_unlock(&port->mp.mpi_lock); } -static int translate_eth_proto_oper(u32 eth_proto_oper, u8 *active_speed, - u8 *active_width) +static int translate_eth_legacy_proto_oper(u32 eth_proto_oper, u8 *active_speed, + u8 *active_width) { switch (eth_proto_oper) { case MLX5E_PROT_MASK(MLX5E_1000BASE_CX_SGMII): @@ -389,10 +389,66 @@ static int translate_eth_proto_oper(u32 eth_proto_oper, u8 *active_speed, return 0; } +static int translate_eth_ext_proto_oper(u32 eth_proto_oper, u8 *active_speed, + u8 *active_width) +{ + switch (eth_proto_oper) { + case MLX5E_PROT_MASK(MLX5E_SGMII_100M): + case MLX5E_PROT_MASK(MLX5E_1000BASE_X_SGMII): + *active_width = IB_WIDTH_1X; + *active_speed = IB_SPEED_SDR; + break; + case MLX5E_PROT_MASK(MLX5E_5GBASE_R): + *active_width = IB_WIDTH_1X; + *active_speed = IB_SPEED_DDR; + break; + case MLX5E_PROT_MASK(MLX5E_10GBASE_XFI_XAUI_1): + *active_width = IB_WIDTH_1X; + *active_speed = IB_SPEED_QDR; + break; + case MLX5E_PROT_MASK(MLX5E_40GBASE_XLAUI_4_XLPPI_4): + *active_width = IB_WIDTH_4X; + *active_speed = IB_SPEED_QDR; + break; + case MLX5E_PROT_MASK(MLX5E_25GAUI_1_25GBASE_CR_KR): + *active_width = IB_WIDTH_1X; + *active_speed = IB_SPEED_EDR; + break; + case MLX5E_PROT_MASK(MLX5E_50GAUI_2_LAUI_2_50GBASE_CR2_KR2): + case MLX5E_PROT_MASK(MLX5E_50GAUI_1_LAUI_1_50GBASE_CR_KR): + *active_width = IB_WIDTH_1X; + *active_speed = IB_SPEED_HDR; + break; + case MLX5E_PROT_MASK(MLX5E_100GAUI_2_100GBASE_CR2_KR2): + *active_width = IB_WIDTH_2X; + *active_speed = IB_SPEED_HDR; + break; + case MLX5E_PROT_MASK(MLX5E_200GAUI_4_200GBASE_CR4_KR4): + *active_width = IB_WIDTH_4X; + *active_speed = IB_SPEED_HDR; + break; + default: + return -EINVAL; + } + + return 0; +} + +static int translate_eth_proto_oper(u32 eth_proto_oper, u8 *active_speed, + u8 *active_width, bool ext) +{ + return ext ? + translate_eth_ext_proto_oper(eth_proto_oper, active_speed, + active_width) : + translate_eth_legacy_proto_oper(eth_proto_oper, active_speed, + active_width); +} + static int mlx5_query_port_roce(struct ib_device *device, u8 port_num, struct ib_port_attr *props) { struct mlx5_ib_dev *dev = to_mdev(device); + u32 out[MLX5_ST_SZ_DW(ptys_reg)] = {0}; struct mlx5_core_dev *mdev; struct net_device *ndev, *upper; enum ib_mtu ndev_ib_mtu; @@ -400,6 +456,7 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num, u16 qkey_viol_cntr; u32 eth_prot_oper; u8 mdev_port_num; + bool ext; int err; mdev = mlx5_ib_get_native_port_mdev(dev, port_num, &mdev_port_num); @@ -416,16 +473,18 @@ static int mlx5_query_port_roce(struct ib_device *device, u8 port_num, /* Possible bad flows are checked before filling out props so in case * of an error it will still be zeroed out. */ - err = mlx5_query_port_eth_proto_oper(mdev, ð_prot_oper, - mdev_port_num); + err = mlx5_query_port_ptys(mdev, out, sizeof(out), MLX5_PTYS_EN, + mdev_port_num); if (err) goto out; + ext = MLX5_CAP_PCAM_FEATURE(dev->mdev, ptys_extended_ethernet); + eth_prot_oper = MLX5_GET_ETH_PROTO(ptys_reg, out, ext, eth_proto_oper); props->active_width = IB_WIDTH_4X; props->active_speed = IB_SPEED_QDR; translate_eth_proto_oper(eth_prot_oper, &props->active_speed, - &props->active_width); + &props->active_width, ext); props->port_cap_flags |= IB_PORT_CM_SUP; props->ip_gids = true; @@ -6386,7 +6445,7 @@ static const struct mlx5_ib_profile pf_profile = { mlx5_ib_stage_delay_drop_cleanup), }; -static const struct mlx5_ib_profile nic_rep_profile = { +const struct mlx5_ib_profile uplink_rep_profile = { STAGE_CREATE(MLX5_IB_STAGE_INIT, mlx5_ib_stage_init_init, mlx5_ib_stage_init_cleanup), @@ -6479,6 +6538,12 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev) printk_once(KERN_INFO "%s", mlx5_version); + if (MLX5_ESWITCH_MANAGER(mdev) && + mlx5_ib_eswitch_mode(mdev->priv.eswitch) == SRIOV_OFFLOADS) { + mlx5_ib_register_vport_reps(mdev); + return mdev; + } + port_type_cap = MLX5_CAP_GEN(mdev, port_type); ll = mlx5_port_type_cap_to_rdma_ll(port_type_cap); @@ -6493,14 +6558,6 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev) dev->num_ports = max(MLX5_CAP_GEN(mdev, num_ports), MLX5_CAP_GEN(mdev, num_vhca_ports)); - if (MLX5_ESWITCH_MANAGER(mdev) && - mlx5_ib_eswitch_mode(mdev->priv.eswitch) == SRIOV_OFFLOADS) { - dev->rep = mlx5_ib_vport_rep(mdev->priv.eswitch, 0); - dev->profile = &nic_rep_profile; - mlx5_ib_register_vport_reps(dev); - return dev; - } - return __mlx5_ib_add(dev, &pf_profile); } @@ -6509,6 +6566,11 @@ static void mlx5_ib_remove(struct mlx5_core_dev *mdev, void *context) struct mlx5_ib_multiport_info *mpi; struct mlx5_ib_dev *dev; + if (MLX5_ESWITCH_MANAGER(mdev) && context == mdev) { + mlx5_ib_unregister_vport_reps(mdev); + return; + } + if (mlx5_core_is_mp_slave(mdev)) { mpi = context; mutex_lock(&mlx5_ib_multiport_mutex); @@ -6520,10 +6582,7 @@ static void mlx5_ib_remove(struct mlx5_core_dev *mdev, void *context) } dev = context; - if (dev->profile == &nic_rep_profile) - mlx5_ib_unregister_vport_reps(dev); - else - __mlx5_ib_remove(dev, dev->profile, MLX5_IB_STAGE_MAX); + __mlx5_ib_remove(dev, dev->profile, MLX5_IB_STAGE_MAX); ib_dealloc_device((struct ib_device *)dev); } diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index b06d3b1efea8..eedba0d2ec4b 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -587,6 +587,7 @@ struct mlx5_ib_mr { struct mlx5_ib_mr *parent; atomic_t num_leaf_free; wait_queue_head_t q_leaf_free; + struct mlx5_async_work cb_work; }; struct mlx5_ib_mw { @@ -944,6 +945,7 @@ struct mlx5_ib_dev { struct mlx5_memic memic; u16 devx_whitelist_uid; struct mlx5_srq_table srq_table; + struct mlx5_async_ctx async_ctx; }; static inline struct mlx5_ib_cq *to_mibcq(struct mlx5_core_cq *mcq) @@ -1038,9 +1040,6 @@ void mlx5_ib_db_unmap_user(struct mlx5_ib_ucontext *context, struct mlx5_db *db) void __mlx5_ib_cq_clean(struct mlx5_ib_cq *cq, u32 qpn, struct mlx5_ib_srq *srq); void mlx5_ib_cq_clean(struct mlx5_ib_cq *cq, u32 qpn, struct mlx5_ib_srq *srq); void mlx5_ib_free_srq_wqe(struct mlx5_ib_srq *srq, int wqe_index); -int mlx5_MAD_IFC(struct mlx5_ib_dev *dev, int ignore_mkey, int ignore_bkey, - u8 port, const struct ib_wc *in_wc, const struct ib_grh *in_grh, - const void *in_mad, void *response_mad); struct ib_ah *mlx5_ib_create_ah(struct ib_pd *pd, struct rdma_ah_attr *ah_attr, u32 flags, struct ib_udata *udata); int mlx5_ib_query_ah(struct ib_ah *ibah, struct rdma_ah_attr *ah_attr); diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c index fd6ea1f75085..bf2b6ea23851 100644 --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@ -123,9 +123,10 @@ static void update_odp_mr(struct mlx5_ib_mr *mr) } #endif -static void reg_mr_callback(int status, void *context) +static void reg_mr_callback(int status, struct mlx5_async_work *context) { - struct mlx5_ib_mr *mr = context; + struct mlx5_ib_mr *mr = + container_of(context, struct mlx5_ib_mr, cb_work); struct mlx5_ib_dev *dev = mr->dev; struct mlx5_mr_cache *cache = &dev->cache; int c = order2idx(dev, mr->order); @@ -216,9 +217,9 @@ static int add_keys(struct mlx5_ib_dev *dev, int c, int num) ent->pending++; spin_unlock_irq(&ent->lock); err = mlx5_core_create_mkey_cb(dev->mdev, &mr->mmkey, - in, inlen, + &dev->async_ctx, in, inlen, mr->out, sizeof(mr->out), - reg_mr_callback, mr); + reg_mr_callback, &mr->cb_work); if (err) { spin_lock_irq(&ent->lock); ent->pending--; @@ -679,6 +680,7 @@ int mlx5_mr_cache_init(struct mlx5_ib_dev *dev) return -ENOMEM; } + mlx5_cmd_init_async_ctx(dev->mdev, &dev->async_ctx); timer_setup(&dev->delay_timer, delay_time_func, 0); for (i = 0; i < MAX_MR_CACHE_ENTRIES; i++) { ent = &cache->ent[i]; @@ -725,33 +727,6 @@ int mlx5_mr_cache_init(struct mlx5_ib_dev *dev) return 0; } -static void wait_for_async_commands(struct mlx5_ib_dev *dev) -{ - struct mlx5_mr_cache *cache = &dev->cache; - struct mlx5_cache_ent *ent; - int total = 0; - int i; - int j; - - for (i = 0; i < MAX_MR_CACHE_ENTRIES; i++) { - ent = &cache->ent[i]; - for (j = 0 ; j < 1000; j++) { - if (!ent->pending) - break; - msleep(50); - } - } - for (i = 0; i < MAX_MR_CACHE_ENTRIES; i++) { - ent = &cache->ent[i]; - total += ent->pending; - } - - if (total) - mlx5_ib_warn(dev, "aborted while there are %d pending mr requests\n", total); - else - mlx5_ib_warn(dev, "done with all pending requests\n"); -} - int mlx5_mr_cache_cleanup(struct mlx5_ib_dev *dev) { int i; @@ -763,12 +738,12 @@ int mlx5_mr_cache_cleanup(struct mlx5_ib_dev *dev) flush_workqueue(dev->cache.wq); mlx5_mr_cache_debugfs_cleanup(dev); + mlx5_cmd_cleanup_async_ctx(&dev->async_ctx); for (i = 0; i < MAX_MR_CACHE_ENTRIES; i++) clean_keys(dev, i); destroy_workqueue(dev->cache.wq); - wait_for_async_commands(dev); del_timer_sync(&dev->delay_timer); return 0; diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index 01e0f6200631..4ee32964e1dd 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -1595,10 +1595,12 @@ static void mlx5_ib_prefetch_mr_work(struct work_struct *work) struct prefetch_mr_work *w = container_of(work, struct prefetch_mr_work, work); - if (w->dev->ib_dev.reg_state == IB_DEV_REGISTERED) + if (ib_device_try_get(&w->dev->ib_dev)) { mlx5_ib_prefetch_sg_list(w->dev, w->pf_flags, w->sg_list, w->num_sge); - + ib_device_put(&w->dev->ib_dev); + } + put_device(&w->dev->ib_dev.dev); kfree(w); } @@ -1617,15 +1619,13 @@ int mlx5_ib_advise_mr_prefetch(struct ib_pd *pd, return mlx5_ib_prefetch_sg_list(dev, pf_flags, sg_list, num_sge); - if (dev->ib_dev.reg_state != IB_DEV_REGISTERED) - return -ENODEV; - work = kvzalloc(struct_size(work, sg_list, num_sge), GFP_KERNEL); if (!work) return -ENOMEM; memcpy(work->sg_list, sg_list, num_sge * sizeof(struct ib_sge)); + get_device(&dev->ib_dev.dev); work->dev = dev; work->pf_flags = pf_flags; work->num_sge = num_sge; diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index dd2ae640bc84..7db778d96ef5 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -1912,14 +1912,16 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd, } if (!check_flags_mask(ucmd.flags, + MLX5_QP_FLAG_ALLOW_SCATTER_CQE | + MLX5_QP_FLAG_BFREG_INDEX | + MLX5_QP_FLAG_PACKET_BASED_CREDIT_MODE | + MLX5_QP_FLAG_SCATTER_CQE | MLX5_QP_FLAG_SIGNATURE | - MLX5_QP_FLAG_SCATTER_CQE | - MLX5_QP_FLAG_TUNNEL_OFFLOADS | - MLX5_QP_FLAG_BFREG_INDEX | - MLX5_QP_FLAG_TYPE_DCT | - MLX5_QP_FLAG_TYPE_DCI | - MLX5_QP_FLAG_ALLOW_SCATTER_CQE | - MLX5_QP_FLAG_PACKET_BASED_CREDIT_MODE)) + MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_MC | + MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_UC | + MLX5_QP_FLAG_TUNNEL_OFFLOADS | + MLX5_QP_FLAG_TYPE_DCI | + MLX5_QP_FLAG_TYPE_DCT)) return -EINVAL; err = get_qp_user_index(to_mucontext(pd->uobject->context), diff --git a/drivers/infiniband/hw/qib/qib_ud.c b/drivers/infiniband/hw/qib/qib_ud.c index 868da0ece7ba..445ea19a2ec8 100644 --- a/drivers/infiniband/hw/qib/qib_ud.c +++ b/drivers/infiniband/hw/qib/qib_ud.c @@ -512,7 +512,6 @@ void qib_ud_rcv(struct qib_ibport *ibp, struct ib_header *hdr, opcode == IB_OPCODE_UD_SEND_ONLY_WITH_IMMEDIATE) { wc.ex.imm_data = ohdr->u.ud.imm_data; wc.wc_flags = IB_WC_WITH_IMM; - tlen -= sizeof(u32); } else if (opcode == IB_OPCODE_UD_SEND_ONLY) { wc.ex.imm_data = 0; wc.wc_flags = 0; diff --git a/drivers/infiniband/sw/rdmavt/qp.c b/drivers/infiniband/sw/rdmavt/qp.c index a1bd8cfc2c25..c6cc3e4ab71d 100644 --- a/drivers/infiniband/sw/rdmavt/qp.c +++ b/drivers/infiniband/sw/rdmavt/qp.c @@ -2910,6 +2910,8 @@ send: goto op_err; if (!ret) goto rnr_nak; + if (wqe->length > qp->r_len) + goto inv_err; break; case IB_WR_RDMA_WRITE_WITH_IMM: @@ -3078,7 +3080,10 @@ op_err: goto err; inv_err: - send_status = IB_WC_REM_INV_REQ_ERR; + send_status = + sqp->ibqp.qp_type == IB_QPT_RC ? + IB_WC_REM_INV_REQ_ERR : + IB_WC_SUCCESS; wc.status = IB_WC_LOC_QP_OP_ERR; goto err; diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h index 1da119d901a9..73e808c1e6ad 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib.h +++ b/drivers/infiniband/ulp/ipoib/ipoib.h @@ -248,7 +248,6 @@ struct ipoib_cm_tx { struct list_head list; struct net_device *dev; struct ipoib_neigh *neigh; - struct ipoib_path *path; struct ipoib_tx_buf *tx_ring; unsigned int tx_head; unsigned int tx_tail; diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index 0428e01e8f69..aa9dcfc36cd3 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -1312,7 +1312,6 @@ struct ipoib_cm_tx *ipoib_cm_create_tx(struct net_device *dev, struct ipoib_path neigh->cm = tx; tx->neigh = neigh; - tx->path = path; tx->dev = dev; list_add(&tx->list, &priv->cm.start_list); set_bit(IPOIB_FLAG_INITIALIZED, &tx->flags); @@ -1371,7 +1370,7 @@ static void ipoib_cm_tx_start(struct work_struct *work) neigh->daddr + QPN_AND_OPTIONS_OFFSET); goto free_neigh; } - memcpy(&pathrec, &p->path->pathrec, sizeof(pathrec)); + memcpy(&pathrec, &path->pathrec, sizeof(pathrec)); spin_unlock_irqrestore(&priv->lock, flags); netif_tx_unlock_bh(dev); diff --git a/drivers/input/serio/olpc_apsp.c b/drivers/input/serio/olpc_apsp.c index bae08226e3d9..a7cfab3db9ee 100644 --- a/drivers/input/serio/olpc_apsp.c +++ b/drivers/input/serio/olpc_apsp.c @@ -23,7 +23,6 @@ #include <linux/of.h> #include <linux/slab.h> #include <linux/delay.h> -#include <linux/clk.h> /* * The OLPC XO-1.75 and XO-4 laptops do not have a hardware PS/2 controller. @@ -75,7 +74,6 @@ struct olpc_apsp { struct serio *kbio; struct serio *padio; void __iomem *base; - struct clk *clk; int open_count; int irq; }; @@ -148,17 +146,11 @@ static int olpc_apsp_open(struct serio *port) struct olpc_apsp *priv = port->port_data; unsigned int tmp; unsigned long l; - int error; if (priv->open_count++ == 0) { - error = clk_prepare_enable(priv->clk); - if (error) - return error; - l = readl(priv->base + COMMAND_FIFO_STATUS); if (!(l & CMD_STS_MASK)) { dev_err(priv->dev, "SP cannot accept commands.\n"); - clk_disable_unprepare(priv->clk); return -EIO; } @@ -179,8 +171,6 @@ static void olpc_apsp_close(struct serio *port) /* Disable interrupt 0 */ tmp = readl(priv->base + PJ_INTERRUPT_MASK); writel(tmp | INT_0, priv->base + PJ_INTERRUPT_MASK); - - clk_disable_unprepare(priv->clk); } } @@ -208,10 +198,6 @@ static int olpc_apsp_probe(struct platform_device *pdev) if (priv->irq < 0) return priv->irq; - priv->clk = devm_clk_get(&pdev->dev, "sp"); - if (IS_ERR(priv->clk)) - return PTR_ERR(priv->clk); - /* KEYBOARD */ kb_serio = kzalloc(sizeof(struct serio), GFP_KERNEL); if (!kb_serio) diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index 87ba23a75b38..2a7b78bb98b4 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -1991,16 +1991,13 @@ static void do_attach(struct iommu_dev_data *dev_data, static void do_detach(struct iommu_dev_data *dev_data) { + struct protection_domain *domain = dev_data->domain; struct amd_iommu *iommu; u16 alias; iommu = amd_iommu_rlookup_table[dev_data->devid]; alias = dev_data->alias; - /* decrease reference counters */ - dev_data->domain->dev_iommu[iommu->index] -= 1; - dev_data->domain->dev_cnt -= 1; - /* Update data structures */ dev_data->domain = NULL; list_del(&dev_data->list); @@ -2010,6 +2007,16 @@ static void do_detach(struct iommu_dev_data *dev_data) /* Flush the DTE entry */ device_flush_dte(dev_data); + + /* Flush IOTLB */ + domain_flush_tlb_pde(domain); + + /* Wait for the flushes to finish */ + domain_flush_complete(domain); + + /* decrease reference counters - needs to happen after the flushes */ + domain->dev_iommu[iommu->index] -= 1; + domain->dev_cnt -= 1; } /* @@ -2617,13 +2624,13 @@ out_unmap: bus_addr = address + s->dma_address + (j << PAGE_SHIFT); iommu_unmap_page(domain, bus_addr, PAGE_SIZE); - if (--mapped_pages) + if (--mapped_pages == 0) goto out_free_iova; } } out_free_iova: - free_iova_fast(&dma_dom->iovad, address, npages); + free_iova_fast(&dma_dom->iovad, address >> PAGE_SHIFT, npages); out_err: return 0; diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 2bd9ac285c0d..78188bf7e90d 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -363,7 +363,7 @@ static int dmar_map_gfx = 1; static int dmar_forcedac; static int intel_iommu_strict; static int intel_iommu_superpage = 1; -static int intel_iommu_sm = 1; +static int intel_iommu_sm; static int iommu_identity_mapping; #define IDENTMAP_ALL 1 @@ -456,9 +456,9 @@ static int __init intel_iommu_setup(char *str) } else if (!strncmp(str, "sp_off", 6)) { pr_info("Disable supported super page\n"); intel_iommu_superpage = 0; - } else if (!strncmp(str, "sm_off", 6)) { - pr_info("Intel-IOMMU: disable scalable mode support\n"); - intel_iommu_sm = 0; + } else if (!strncmp(str, "sm_on", 5)) { + pr_info("Intel-IOMMU: scalable mode supported\n"); + intel_iommu_sm = 1; } else if (!strncmp(str, "tboot_noforce", 13)) { printk(KERN_INFO "Intel-IOMMU: not forcing on after tboot. This could expose security risk for tboot\n"); @@ -5294,7 +5294,7 @@ static void intel_iommu_put_resv_regions(struct device *dev, struct iommu_resv_region *entry, *next; list_for_each_entry_safe(entry, next, head, list) { - if (entry->type == IOMMU_RESV_RESERVED) + if (entry->type == IOMMU_RESV_MSI) kfree(entry); } } diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c index 730f7dabcf37..7e0df67bd3e9 100644 --- a/drivers/iommu/mtk_iommu_v1.c +++ b/drivers/iommu/mtk_iommu_v1.c @@ -441,6 +441,10 @@ static int mtk_iommu_add_device(struct device *dev) iommu_spec.args_count = count; mtk_iommu_create_mapping(dev, &iommu_spec); + + /* dev->iommu_fwspec might have changed */ + fwspec = dev_iommu_fwspec_get(dev); + of_node_put(iommu_spec.np); } diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index db20e992a40f..c3aba3fc818d 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -97,9 +97,14 @@ struct its_device; * The ITS structure - contains most of the infrastructure, with the * top-level MSI domain, the command queue, the collections, and the * list of devices writing to it. + * + * dev_alloc_lock has to be taken for device allocations, while the + * spinlock must be taken to parse data structures such as the device + * list. */ struct its_node { raw_spinlock_t lock; + struct mutex dev_alloc_lock; struct list_head entry; void __iomem *base; phys_addr_t phys_base; @@ -156,6 +161,7 @@ struct its_device { void *itt; u32 nr_ites; u32 device_id; + bool shared; }; static struct { @@ -1580,6 +1586,9 @@ static unsigned long *its_lpi_alloc(int nr_irqs, u32 *base, int *nr_ids) nr_irqs /= 2; } while (nr_irqs > 0); + if (!nr_irqs) + err = -ENOSPC; + if (err) goto out; @@ -2059,6 +2068,29 @@ static int __init allocate_lpi_tables(void) return 0; } +static u64 its_clear_vpend_valid(void __iomem *vlpi_base) +{ + u32 count = 1000000; /* 1s! */ + bool clean; + u64 val; + + val = gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER); + val &= ~GICR_VPENDBASER_Valid; + gits_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER); + + do { + val = gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER); + clean = !(val & GICR_VPENDBASER_Dirty); + if (!clean) { + count--; + cpu_relax(); + udelay(1); + } + } while (!clean && count); + + return val; +} + static void its_cpu_init_lpis(void) { void __iomem *rbase = gic_data_rdist_rd_base(); @@ -2144,6 +2176,30 @@ static void its_cpu_init_lpis(void) val |= GICR_CTLR_ENABLE_LPIS; writel_relaxed(val, rbase + GICR_CTLR); + if (gic_rdists->has_vlpis) { + void __iomem *vlpi_base = gic_data_rdist_vlpi_base(); + + /* + * It's possible for CPU to receive VLPIs before it is + * sheduled as a vPE, especially for the first CPU, and the + * VLPI with INTID larger than 2^(IDbits+1) will be considered + * as out of range and dropped by GIC. + * So we initialize IDbits to known value to avoid VLPI drop. + */ + val = (LPI_NRBITS - 1) & GICR_VPROPBASER_IDBITS_MASK; + pr_debug("GICv4: CPU%d: Init IDbits to 0x%llx for GICR_VPROPBASER\n", + smp_processor_id(), val); + gits_write_vpropbaser(val, vlpi_base + GICR_VPROPBASER); + + /* + * Also clear Valid bit of GICR_VPENDBASER, in case some + * ancient programming gets left in and has possibility of + * corrupting memory. + */ + val = its_clear_vpend_valid(vlpi_base); + WARN_ON(val & GICR_VPENDBASER_Dirty); + } + /* Make sure the GIC has seen the above */ dsb(sy); out: @@ -2399,13 +2455,14 @@ static void its_free_device(struct its_device *its_dev) kfree(its_dev); } -static int its_alloc_device_irq(struct its_device *dev, irq_hw_number_t *hwirq) +static int its_alloc_device_irq(struct its_device *dev, int nvecs, irq_hw_number_t *hwirq) { int idx; - idx = find_first_zero_bit(dev->event_map.lpi_map, - dev->event_map.nr_lpis); - if (idx == dev->event_map.nr_lpis) + idx = bitmap_find_free_region(dev->event_map.lpi_map, + dev->event_map.nr_lpis, + get_count_order(nvecs)); + if (idx < 0) return -ENOSPC; *hwirq = dev->event_map.lpi_base + idx; @@ -2421,6 +2478,7 @@ static int its_msi_prepare(struct irq_domain *domain, struct device *dev, struct its_device *its_dev; struct msi_domain_info *msi_info; u32 dev_id; + int err = 0; /* * We ignore "dev" entierely, and rely on the dev_id that has @@ -2443,6 +2501,7 @@ static int its_msi_prepare(struct irq_domain *domain, struct device *dev, return -EINVAL; } + mutex_lock(&its->dev_alloc_lock); its_dev = its_find_device(its, dev_id); if (its_dev) { /* @@ -2450,18 +2509,22 @@ static int its_msi_prepare(struct irq_domain *domain, struct device *dev, * another alias (PCI bridge of some sort). No need to * create the device. */ + its_dev->shared = true; pr_debug("Reusing ITT for devID %x\n", dev_id); goto out; } its_dev = its_create_device(its, dev_id, nvec, true); - if (!its_dev) - return -ENOMEM; + if (!its_dev) { + err = -ENOMEM; + goto out; + } pr_debug("ITT %d entries, %d bits\n", nvec, ilog2(nvec)); out: + mutex_unlock(&its->dev_alloc_lock); info->scratchpad[0].ptr = its_dev; - return 0; + return err; } static struct msi_domain_ops its_msi_domain_ops = { @@ -2501,21 +2564,21 @@ static int its_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, int err; int i; - for (i = 0; i < nr_irqs; i++) { - err = its_alloc_device_irq(its_dev, &hwirq); - if (err) - return err; + err = its_alloc_device_irq(its_dev, nr_irqs, &hwirq); + if (err) + return err; - err = its_irq_gic_domain_alloc(domain, virq + i, hwirq); + for (i = 0; i < nr_irqs; i++) { + err = its_irq_gic_domain_alloc(domain, virq + i, hwirq + i); if (err) return err; irq_domain_set_hwirq_and_chip(domain, virq + i, - hwirq, &its_irq_chip, its_dev); + hwirq + i, &its_irq_chip, its_dev); irqd_set_single_target(irq_desc_get_irq_data(irq_to_desc(virq + i))); pr_debug("ID:%d pID:%d vID:%d\n", - (int)(hwirq - its_dev->event_map.lpi_base), - (int) hwirq, virq + i); + (int)(hwirq + i - its_dev->event_map.lpi_base), + (int)(hwirq + i), virq + i); } return 0; @@ -2565,6 +2628,7 @@ static void its_irq_domain_free(struct irq_domain *domain, unsigned int virq, { struct irq_data *d = irq_domain_get_irq_data(domain, virq); struct its_device *its_dev = irq_data_get_irq_chip_data(d); + struct its_node *its = its_dev->its; int i; for (i = 0; i < nr_irqs; i++) { @@ -2579,8 +2643,14 @@ static void its_irq_domain_free(struct irq_domain *domain, unsigned int virq, irq_domain_reset_irq_data(data); } - /* If all interrupts have been freed, start mopping the floor */ - if (bitmap_empty(its_dev->event_map.lpi_map, + mutex_lock(&its->dev_alloc_lock); + + /* + * If all interrupts have been freed, start mopping the + * floor. This is conditionned on the device not being shared. + */ + if (!its_dev->shared && + bitmap_empty(its_dev->event_map.lpi_map, its_dev->event_map.nr_lpis)) { its_lpi_free(its_dev->event_map.lpi_map, its_dev->event_map.lpi_base, @@ -2592,6 +2662,8 @@ static void its_irq_domain_free(struct irq_domain *domain, unsigned int virq, its_free_device(its_dev); } + mutex_unlock(&its->dev_alloc_lock); + irq_domain_free_irqs_parent(domain, virq, nr_irqs); } @@ -2754,26 +2826,11 @@ static void its_vpe_schedule(struct its_vpe *vpe) static void its_vpe_deschedule(struct its_vpe *vpe) { void __iomem *vlpi_base = gic_data_rdist_vlpi_base(); - u32 count = 1000000; /* 1s! */ - bool clean; u64 val; - /* We're being scheduled out */ - val = gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER); - val &= ~GICR_VPENDBASER_Valid; - gits_write_vpendbaser(val, vlpi_base + GICR_VPENDBASER); - - do { - val = gits_read_vpendbaser(vlpi_base + GICR_VPENDBASER); - clean = !(val & GICR_VPENDBASER_Dirty); - if (!clean) { - count--; - cpu_relax(); - udelay(1); - } - } while (!clean && count); + val = its_clear_vpend_valid(vlpi_base); - if (unlikely(!clean && !count)) { + if (unlikely(val & GICR_VPENDBASER_Dirty)) { pr_err_ratelimited("ITS virtual pending table not cleaning\n"); vpe->idai = false; vpe->pending_last = true; @@ -3516,6 +3573,7 @@ static int __init its_probe_one(struct resource *res, } raw_spin_lock_init(&its->lock); + mutex_init(&its->dev_alloc_lock); INIT_LIST_HEAD(&its->entry); INIT_LIST_HEAD(&its->its_device_list); typer = gic_read_typer(its_base + GITS_TYPER); diff --git a/drivers/irqchip/irq-gic-v3-mbi.c b/drivers/irqchip/irq-gic-v3-mbi.c index ad70e7c416e3..fbfa7ff6deb1 100644 --- a/drivers/irqchip/irq-gic-v3-mbi.c +++ b/drivers/irqchip/irq-gic-v3-mbi.c @@ -24,7 +24,7 @@ struct mbi_range { unsigned long *bm; }; -static struct mutex mbi_lock; +static DEFINE_MUTEX(mbi_lock); static phys_addr_t mbi_phys_base; static struct mbi_range *mbi_ranges; static unsigned int mbi_range_nr; diff --git a/drivers/irqchip/irq-madera.c b/drivers/irqchip/irq-madera.c index e9256dee1a45..8b81271c823c 100644 --- a/drivers/irqchip/irq-madera.c +++ b/drivers/irqchip/irq-madera.c @@ -7,7 +7,6 @@ */ #include <linux/module.h> -#include <linux/gpio.h> #include <linux/interrupt.h> #include <linux/irq.h> #include <linux/irqdomain.h> @@ -16,7 +15,6 @@ #include <linux/slab.h> #include <linux/of.h> #include <linux/of_device.h> -#include <linux/of_gpio.h> #include <linux/of_irq.h> #include <linux/irqchip/irq-madera.h> #include <linux/mfd/madera/core.h> diff --git a/drivers/irqchip/irq-mmp.c b/drivers/irqchip/irq-mmp.c index 25f32e1d7764..3496b61a312a 100644 --- a/drivers/irqchip/irq-mmp.c +++ b/drivers/irqchip/irq-mmp.c @@ -34,6 +34,9 @@ #define SEL_INT_PENDING (1 << 6) #define SEL_INT_NUM_MASK 0x3f +#define MMP2_ICU_INT_ROUTE_PJ4_IRQ (1 << 5) +#define MMP2_ICU_INT_ROUTE_PJ4_FIQ (1 << 6) + struct icu_chip_data { int nr_irqs; unsigned int virq_base; @@ -190,7 +193,8 @@ static const struct mmp_intc_conf mmp_conf = { static const struct mmp_intc_conf mmp2_conf = { .conf_enable = 0x20, .conf_disable = 0x0, - .conf_mask = 0x7f, + .conf_mask = MMP2_ICU_INT_ROUTE_PJ4_IRQ | + MMP2_ICU_INT_ROUTE_PJ4_FIQ, }; static void __exception_irq_entry mmp_handle_irq(struct pt_regs *regs) diff --git a/drivers/irqchip/irq-stm32-exti.c b/drivers/irqchip/irq-stm32-exti.c index 6edfd4bfa169..a93296b9b45d 100644 --- a/drivers/irqchip/irq-stm32-exti.c +++ b/drivers/irqchip/irq-stm32-exti.c @@ -822,6 +822,7 @@ out_unmap: static const struct irq_domain_ops stm32_exti_h_domain_ops = { .alloc = stm32_exti_h_domain_alloc, .free = irq_domain_free_irqs_common, + .xlate = irq_domain_xlate_twocell, }; static int diff --git a/drivers/irqchip/irq-xtensa-mx.c b/drivers/irqchip/irq-xtensa-mx.c index 5385f5768345..27933338f7b3 100644 --- a/drivers/irqchip/irq-xtensa-mx.c +++ b/drivers/irqchip/irq-xtensa-mx.c @@ -71,14 +71,17 @@ static void xtensa_mx_irq_mask(struct irq_data *d) unsigned int mask = 1u << d->hwirq; if (mask & (XCHAL_INTTYPE_MASK_EXTERN_EDGE | - XCHAL_INTTYPE_MASK_EXTERN_LEVEL)) { - set_er(1u << (xtensa_get_ext_irq_no(d->hwirq) - - HW_IRQ_MX_BASE), MIENG); - } else { - mask = __this_cpu_read(cached_irq_mask) & ~mask; - __this_cpu_write(cached_irq_mask, mask); - xtensa_set_sr(mask, intenable); + XCHAL_INTTYPE_MASK_EXTERN_LEVEL)) { + unsigned int ext_irq = xtensa_get_ext_irq_no(d->hwirq); + + if (ext_irq >= HW_IRQ_MX_BASE) { + set_er(1u << (ext_irq - HW_IRQ_MX_BASE), MIENG); + return; + } } + mask = __this_cpu_read(cached_irq_mask) & ~mask; + __this_cpu_write(cached_irq_mask, mask); + xtensa_set_sr(mask, intenable); } static void xtensa_mx_irq_unmask(struct irq_data *d) @@ -86,14 +89,17 @@ static void xtensa_mx_irq_unmask(struct irq_data *d) unsigned int mask = 1u << d->hwirq; if (mask & (XCHAL_INTTYPE_MASK_EXTERN_EDGE | - XCHAL_INTTYPE_MASK_EXTERN_LEVEL)) { - set_er(1u << (xtensa_get_ext_irq_no(d->hwirq) - - HW_IRQ_MX_BASE), MIENGSET); - } else { - mask |= __this_cpu_read(cached_irq_mask); - __this_cpu_write(cached_irq_mask, mask); - xtensa_set_sr(mask, intenable); + XCHAL_INTTYPE_MASK_EXTERN_LEVEL)) { + unsigned int ext_irq = xtensa_get_ext_irq_no(d->hwirq); + + if (ext_irq >= HW_IRQ_MX_BASE) { + set_er(1u << (ext_irq - HW_IRQ_MX_BASE), MIENGSET); + return; + } } + mask |= __this_cpu_read(cached_irq_mask); + __this_cpu_write(cached_irq_mask, mask); + xtensa_set_sr(mask, intenable); } static void xtensa_mx_irq_enable(struct irq_data *d) @@ -113,7 +119,11 @@ static void xtensa_mx_irq_ack(struct irq_data *d) static int xtensa_mx_irq_retrigger(struct irq_data *d) { - xtensa_set_sr(1 << d->hwirq, intset); + unsigned int mask = 1u << d->hwirq; + + if (WARN_ON(mask & ~XCHAL_INTTYPE_MASK_SOFTWARE)) + return 0; + xtensa_set_sr(mask, intset); return 1; } diff --git a/drivers/irqchip/irq-xtensa-pic.c b/drivers/irqchip/irq-xtensa-pic.c index c200234dd2c9..ab12328be5ee 100644 --- a/drivers/irqchip/irq-xtensa-pic.c +++ b/drivers/irqchip/irq-xtensa-pic.c @@ -70,7 +70,11 @@ static void xtensa_irq_ack(struct irq_data *d) static int xtensa_irq_retrigger(struct irq_data *d) { - xtensa_set_sr(1 << d->hwirq, intset); + unsigned int mask = 1u << d->hwirq; + + if (WARN_ON(mask & ~XCHAL_INTTYPE_MASK_SOFTWARE)) + return 0; + xtensa_set_sr(mask, intset); return 1; } diff --git a/drivers/isdn/gigaset/ser-gigaset.c b/drivers/isdn/gigaset/ser-gigaset.c index ab0b63a4d045..e1de8b1a1001 100644 --- a/drivers/isdn/gigaset/ser-gigaset.c +++ b/drivers/isdn/gigaset/ser-gigaset.c @@ -633,7 +633,7 @@ gigaset_tty_ioctl(struct tty_struct *tty, struct file *file, flush_send_queue(cs); break; } - /* Pass through */ + /* fall through */ default: /* pass through to underlying serial device */ diff --git a/drivers/isdn/hisax/hfc_pci.c b/drivers/isdn/hisax/hfc_pci.c index 81dd465afcf4..71a8312592d6 100644 --- a/drivers/isdn/hisax/hfc_pci.c +++ b/drivers/isdn/hisax/hfc_pci.c @@ -656,7 +656,7 @@ hfcpci_fill_fifo(struct BCState *bcs) schedule_event(bcs, B_ACKPENDING); } - dev_kfree_skb_any(bcs->tx_skb); + dev_consume_skb_any(bcs->tx_skb); bcs->tx_skb = skb_dequeue(&bcs->squeue); /* fetch next data */ } test_and_clear_bit(BC_FLG_BUSY, &bcs->Flag); diff --git a/drivers/isdn/i4l/isdn_tty.c b/drivers/isdn/i4l/isdn_tty.c index dc1cded716c1..43700fc19a31 100644 --- a/drivers/isdn/i4l/isdn_tty.c +++ b/drivers/isdn/i4l/isdn_tty.c @@ -3642,7 +3642,7 @@ isdn_tty_edit_at(const char *p, int count, modem_info *info) break; } else m->mdmcmdl = 0; - /* Fall through, check for 'A' */ + /* Fall through - check for 'A' */ case 0: if (c == 'A') { m->mdmcmd[m->mdmcmdl] = c; diff --git a/drivers/isdn/i4l/isdn_v110.c b/drivers/isdn/i4l/isdn_v110.c index 2a5f6668756c..d11fe76f138f 100644 --- a/drivers/isdn/i4l/isdn_v110.c +++ b/drivers/isdn/i4l/isdn_v110.c @@ -354,7 +354,7 @@ EncodeMatrix(unsigned char *buf, int len, unsigned char *m, int mlen) printk(KERN_WARNING "isdn_v110 (EncodeMatrix): buffer full!\n"); return line; } - /* else: fall through */ + /* fall through */ case 128: m[line] = 128; /* leftmost -> set byte to 1000000 */ mbit = 64; /* current bit in the matrix line */ diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c index 15d3ca37669a..4ab8b1b6608f 100644 --- a/drivers/isdn/mISDN/socket.c +++ b/drivers/isdn/mISDN/socket.c @@ -103,7 +103,7 @@ mISDN_ctrl(struct mISDNchannel *ch, u_int cmd, void *arg) static inline void mISDN_sock_cmsg(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) { - struct timeval tv; + struct __kernel_old_timeval tv; if (_pms(sk)->cmask & MISDN_TIME_STAMP) { skb_get_timestamp(skb, &tv); diff --git a/drivers/isdn/mISDN/timerdev.c b/drivers/isdn/mISDN/timerdev.c index 211ed6cffd10..578978711887 100644 --- a/drivers/isdn/mISDN/timerdev.c +++ b/drivers/isdn/mISDN/timerdev.c @@ -170,8 +170,8 @@ dev_expire_timer(struct timer_list *t) spin_lock_irqsave(&timer->dev->lock, flags); if (timer->id >= 0) list_move_tail(&timer->list, &timer->dev->expired); - spin_unlock_irqrestore(&timer->dev->lock, flags); wake_up_interruptible(&timer->dev->wait); + spin_unlock_irqrestore(&timer->dev->lock, flags); } static int diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 47d4e0d30bf0..dd538e6b2748 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -932,7 +932,7 @@ static int dm_crypt_integrity_io_alloc(struct dm_crypt_io *io, struct bio *bio) if (IS_ERR(bip)) return PTR_ERR(bip); - tag_len = io->cc->on_disk_tag_size * bio_sectors(bio); + tag_len = io->cc->on_disk_tag_size * (bio_sectors(bio) >> io->cc->sector_shift); bip->bip_iter.bi_size = tag_len; bip->bip_iter.bi_sector = io->cc->start + io->sector; diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index 4eb5f8c56535..a20531e5f3b4 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -131,7 +131,7 @@ static void rq_end_stats(struct mapped_device *md, struct request *orig) static void rq_completed(struct mapped_device *md) { /* nudge anyone waiting on suspend queue */ - if (unlikely(waitqueue_active(&md->wait))) + if (unlikely(wq_has_sleeper(&md->wait))) wake_up(&md->wait); /* diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index ca8af21bf644..e83b63608262 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -257,6 +257,7 @@ struct pool { spinlock_t lock; struct bio_list deferred_flush_bios; + struct bio_list deferred_flush_completions; struct list_head prepared_mappings; struct list_head prepared_discards; struct list_head prepared_discards_pt2; @@ -956,6 +957,39 @@ static void process_prepared_mapping_fail(struct dm_thin_new_mapping *m) mempool_free(m, &m->tc->pool->mapping_pool); } +static void complete_overwrite_bio(struct thin_c *tc, struct bio *bio) +{ + struct pool *pool = tc->pool; + unsigned long flags; + + /* + * If the bio has the REQ_FUA flag set we must commit the metadata + * before signaling its completion. + */ + if (!bio_triggers_commit(tc, bio)) { + bio_endio(bio); + return; + } + + /* + * Complete bio with an error if earlier I/O caused changes to the + * metadata that can't be committed, e.g, due to I/O errors on the + * metadata device. + */ + if (dm_thin_aborted_changes(tc->td)) { + bio_io_error(bio); + return; + } + + /* + * Batch together any bios that trigger commits and then issue a + * single commit for them in process_deferred_bios(). + */ + spin_lock_irqsave(&pool->lock, flags); + bio_list_add(&pool->deferred_flush_completions, bio); + spin_unlock_irqrestore(&pool->lock, flags); +} + static void process_prepared_mapping(struct dm_thin_new_mapping *m) { struct thin_c *tc = m->tc; @@ -988,7 +1022,7 @@ static void process_prepared_mapping(struct dm_thin_new_mapping *m) */ if (bio) { inc_remap_and_issue_cell(tc, m->cell, m->data_block); - bio_endio(bio); + complete_overwrite_bio(tc, bio); } else { inc_all_io_entry(tc->pool, m->cell->holder); remap_and_issue(tc, m->cell->holder, m->data_block); @@ -2317,7 +2351,7 @@ static void process_deferred_bios(struct pool *pool) { unsigned long flags; struct bio *bio; - struct bio_list bios; + struct bio_list bios, bio_completions; struct thin_c *tc; tc = get_first_thin(pool); @@ -2328,26 +2362,36 @@ static void process_deferred_bios(struct pool *pool) } /* - * If there are any deferred flush bios, we must commit - * the metadata before issuing them. + * If there are any deferred flush bios, we must commit the metadata + * before issuing them or signaling their completion. */ bio_list_init(&bios); + bio_list_init(&bio_completions); + spin_lock_irqsave(&pool->lock, flags); bio_list_merge(&bios, &pool->deferred_flush_bios); bio_list_init(&pool->deferred_flush_bios); + + bio_list_merge(&bio_completions, &pool->deferred_flush_completions); + bio_list_init(&pool->deferred_flush_completions); spin_unlock_irqrestore(&pool->lock, flags); - if (bio_list_empty(&bios) && + if (bio_list_empty(&bios) && bio_list_empty(&bio_completions) && !(dm_pool_changed_this_transaction(pool->pmd) && need_commit_due_to_time(pool))) return; if (commit(pool)) { + bio_list_merge(&bios, &bio_completions); + while ((bio = bio_list_pop(&bios))) bio_io_error(bio); return; } pool->last_commit_jiffies = jiffies; + while ((bio = bio_list_pop(&bio_completions))) + bio_endio(bio); + while ((bio = bio_list_pop(&bios))) generic_make_request(bio); } @@ -2954,6 +2998,7 @@ static struct pool *pool_create(struct mapped_device *pool_md, INIT_DELAYED_WORK(&pool->no_space_timeout, do_no_space_timeout); spin_lock_init(&pool->lock); bio_list_init(&pool->deferred_flush_bios); + bio_list_init(&pool->deferred_flush_completions); INIT_LIST_HEAD(&pool->prepared_mappings); INIT_LIST_HEAD(&pool->prepared_discards); INIT_LIST_HEAD(&pool->prepared_discards_pt2); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 2b53c3841b53..515e6af9bed2 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -699,7 +699,7 @@ static void end_io_acct(struct dm_io *io) true, duration, &io->stats_aux); /* nudge anyone waiting on suspend queue */ - if (unlikely(waitqueue_active(&md->wait))) + if (unlikely(wq_has_sleeper(&md->wait))) wake_up(&md->wait); } @@ -1336,7 +1336,11 @@ static int clone_bio(struct dm_target_io *tio, struct bio *bio, return r; } - bio_trim(clone, sector - clone->bi_iter.bi_sector, len); + bio_advance(clone, to_bytes(sector - clone->bi_iter.bi_sector)); + clone->bi_iter.bi_size = to_bytes(len); + + if (bio_integrity(bio)) + bio_integrity_trim(clone); return 0; } diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 1d54109071cc..fa47249fa3e4 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1863,6 +1863,20 @@ static void end_sync_read(struct bio *bio) reschedule_retry(r1_bio); } +static void abort_sync_write(struct mddev *mddev, struct r1bio *r1_bio) +{ + sector_t sync_blocks = 0; + sector_t s = r1_bio->sector; + long sectors_to_go = r1_bio->sectors; + + /* make sure these bits don't get cleared. */ + do { + md_bitmap_end_sync(mddev->bitmap, s, &sync_blocks, 1); + s += sync_blocks; + sectors_to_go -= sync_blocks; + } while (sectors_to_go > 0); +} + static void end_sync_write(struct bio *bio) { int uptodate = !bio->bi_status; @@ -1874,15 +1888,7 @@ static void end_sync_write(struct bio *bio) struct md_rdev *rdev = conf->mirrors[find_bio_disk(r1_bio, bio)].rdev; if (!uptodate) { - sector_t sync_blocks = 0; - sector_t s = r1_bio->sector; - long sectors_to_go = r1_bio->sectors; - /* make sure these bits doesn't get cleared. */ - do { - md_bitmap_end_sync(mddev->bitmap, s, &sync_blocks, 1); - s += sync_blocks; - sectors_to_go -= sync_blocks; - } while (sectors_to_go > 0); + abort_sync_write(mddev, r1_bio); set_bit(WriteErrorSeen, &rdev->flags); if (!test_and_set_bit(WantReplacement, &rdev->flags)) set_bit(MD_RECOVERY_NEEDED, & @@ -2172,8 +2178,10 @@ static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio) (i == r1_bio->read_disk || !test_bit(MD_RECOVERY_SYNC, &mddev->recovery)))) continue; - if (test_bit(Faulty, &conf->mirrors[i].rdev->flags)) + if (test_bit(Faulty, &conf->mirrors[i].rdev->flags)) { + abort_sync_write(mddev, r1_bio); continue; + } bio_set_op_attrs(wbio, REQ_OP_WRITE, 0); if (test_bit(FailFast, &conf->mirrors[i].rdev->flags)) diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index ec3a5ef7fee0..cbbe6b6535be 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -1935,12 +1935,14 @@ out: } static struct stripe_head * -r5c_recovery_alloc_stripe(struct r5conf *conf, - sector_t stripe_sect) +r5c_recovery_alloc_stripe( + struct r5conf *conf, + sector_t stripe_sect, + int noblock) { struct stripe_head *sh; - sh = raid5_get_active_stripe(conf, stripe_sect, 0, 1, 0); + sh = raid5_get_active_stripe(conf, stripe_sect, 0, noblock, 0); if (!sh) return NULL; /* no more stripe available */ @@ -2150,7 +2152,7 @@ r5c_recovery_analyze_meta_block(struct r5l_log *log, stripe_sect); if (!sh) { - sh = r5c_recovery_alloc_stripe(conf, stripe_sect); + sh = r5c_recovery_alloc_stripe(conf, stripe_sect, 1); /* * cannot get stripe from raid5_get_active_stripe * try replay some stripes @@ -2159,20 +2161,29 @@ r5c_recovery_analyze_meta_block(struct r5l_log *log, r5c_recovery_replay_stripes( cached_stripe_list, ctx); sh = r5c_recovery_alloc_stripe( - conf, stripe_sect); + conf, stripe_sect, 1); } if (!sh) { + int new_size = conf->min_nr_stripes * 2; pr_debug("md/raid:%s: Increasing stripe cache size to %d to recovery data on journal.\n", mdname(mddev), - conf->min_nr_stripes * 2); - raid5_set_cache_size(mddev, - conf->min_nr_stripes * 2); - sh = r5c_recovery_alloc_stripe(conf, - stripe_sect); + new_size); + ret = raid5_set_cache_size(mddev, new_size); + if (conf->min_nr_stripes <= new_size / 2) { + pr_err("md/raid:%s: Cannot increase cache size, ret=%d, new_size=%d, min_nr_stripes=%d, max_nr_stripes=%d\n", + mdname(mddev), + ret, + new_size, + conf->min_nr_stripes, + conf->max_nr_stripes); + return -ENOMEM; + } + sh = r5c_recovery_alloc_stripe( + conf, stripe_sect, 0); } if (!sh) { pr_err("md/raid:%s: Cannot get enough stripes due to memory pressure. Recovery failed.\n", - mdname(mddev)); + mdname(mddev)); return -ENOMEM; } list_add_tail(&sh->lru, cached_stripe_list); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 4990f0319f6c..cecea901ab8c 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -6369,6 +6369,7 @@ raid5_show_stripe_cache_size(struct mddev *mddev, char *page) int raid5_set_cache_size(struct mddev *mddev, int size) { + int result = 0; struct r5conf *conf = mddev->private; if (size <= 16 || size > 32768) @@ -6385,11 +6386,14 @@ raid5_set_cache_size(struct mddev *mddev, int size) mutex_lock(&conf->cache_size_mutex); while (size > conf->max_nr_stripes) - if (!grow_one_stripe(conf, GFP_KERNEL)) + if (!grow_one_stripe(conf, GFP_KERNEL)) { + conf->min_nr_stripes = conf->max_nr_stripes; + result = -ENOMEM; break; + } mutex_unlock(&conf->cache_size_mutex); - return 0; + return result; } EXPORT_SYMBOL(raid5_set_cache_size); diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig index f461460a2aeb..76f9909cf396 100644 --- a/drivers/mfd/Kconfig +++ b/drivers/mfd/Kconfig @@ -1419,7 +1419,7 @@ config MFD_TPS65217 config MFD_TPS68470 bool "TI TPS68470 Power Management / LED chips" - depends on ACPI && I2C=y + depends on ACPI && PCI && I2C=y select MFD_CORE select REGMAP_I2C select I2C_DESIGNWARE_PLATFORM diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c index 1fc8ea0f519b..ca4c9cc218a2 100644 --- a/drivers/misc/mei/client.c +++ b/drivers/misc/mei/client.c @@ -401,8 +401,11 @@ static void mei_io_list_flush_cl(struct list_head *head, struct mei_cl_cb *cb, *next; list_for_each_entry_safe(cb, next, head, list) { - if (cl == cb->cl) + if (cl == cb->cl) { list_del_init(&cb->list); + if (cb->fop_type == MEI_FOP_READ) + mei_io_cb_free(cb); + } } } diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h index 23739a60517f..bb1ee9834a02 100644 --- a/drivers/misc/mei/hw-me-regs.h +++ b/drivers/misc/mei/hw-me-regs.h @@ -139,6 +139,8 @@ #define MEI_DEV_ID_CNP_H 0xA360 /* Cannon Point H */ #define MEI_DEV_ID_CNP_H_4 0xA364 /* Cannon Point H 4 (iTouch) */ +#define MEI_DEV_ID_ICP_LP 0x34E0 /* Ice Lake Point LP */ + /* * MEI HW Section */ diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c index e89497f858ae..3ab946ad3257 100644 --- a/drivers/misc/mei/pci-me.c +++ b/drivers/misc/mei/pci-me.c @@ -105,6 +105,8 @@ static const struct pci_device_id mei_me_pci_tbl[] = { {MEI_PCI_DEVICE(MEI_DEV_ID_CNP_H, MEI_ME_PCH12_CFG)}, {MEI_PCI_DEVICE(MEI_DEV_ID_CNP_H_4, MEI_ME_PCH8_CFG)}, + {MEI_PCI_DEVICE(MEI_DEV_ID_ICP_LP, MEI_ME_PCH12_CFG)}, + /* required last entry */ {0, } }; diff --git a/drivers/misc/mic/vop/vop_main.c b/drivers/misc/mic/vop/vop_main.c index 2bfa3a903bf9..744757f541be 100644 --- a/drivers/misc/mic/vop/vop_main.c +++ b/drivers/misc/mic/vop/vop_main.c @@ -47,7 +47,8 @@ * @dc: Virtio device control * @vpdev: VOP device which is the parent for this virtio device * @vr: Buffer for accessing the VRING - * @used: Buffer for used + * @used_virt: Virtual address of used ring + * @used: DMA address of used ring * @used_size: Size of the used buffer * @reset_done: Track whether VOP reset is complete * @virtio_cookie: Cookie returned upon requesting a interrupt @@ -61,6 +62,7 @@ struct _vop_vdev { struct mic_device_ctrl __iomem *dc; struct vop_device *vpdev; void __iomem *vr[VOP_MAX_VRINGS]; + void *used_virt[VOP_MAX_VRINGS]; dma_addr_t used[VOP_MAX_VRINGS]; int used_size[VOP_MAX_VRINGS]; struct completion reset_done; @@ -260,12 +262,12 @@ static bool vop_notify(struct virtqueue *vq) static void vop_del_vq(struct virtqueue *vq, int n) { struct _vop_vdev *vdev = to_vopvdev(vq->vdev); - struct vring *vr = (struct vring *)(vq + 1); struct vop_device *vpdev = vdev->vpdev; dma_unmap_single(&vpdev->dev, vdev->used[n], vdev->used_size[n], DMA_BIDIRECTIONAL); - free_pages((unsigned long)vr->used, get_order(vdev->used_size[n])); + free_pages((unsigned long)vdev->used_virt[n], + get_order(vdev->used_size[n])); vring_del_virtqueue(vq); vpdev->hw_ops->iounmap(vpdev, vdev->vr[n]); vdev->vr[n] = NULL; @@ -283,6 +285,26 @@ static void vop_del_vqs(struct virtio_device *dev) vop_del_vq(vq, idx++); } +static struct virtqueue *vop_new_virtqueue(unsigned int index, + unsigned int num, + struct virtio_device *vdev, + bool context, + void *pages, + bool (*notify)(struct virtqueue *vq), + void (*callback)(struct virtqueue *vq), + const char *name, + void *used) +{ + bool weak_barriers = false; + struct vring vring; + + vring_init(&vring, num, pages, MIC_VIRTIO_RING_ALIGN); + vring.used = used; + + return __vring_new_virtqueue(index, vring, vdev, weak_barriers, context, + notify, callback, name); +} + /* * This routine will assign vring's allocated in host/io memory. Code in * virtio_ring.c however continues to access this io memory as if it were local @@ -302,7 +324,6 @@ static struct virtqueue *vop_find_vq(struct virtio_device *dev, struct _mic_vring_info __iomem *info; void *used; int vr_size, _vr_size, err, magic; - struct vring *vr; u8 type = ioread8(&vdev->desc->type); if (index >= ioread8(&vdev->desc->num_vq)) @@ -322,17 +343,7 @@ static struct virtqueue *vop_find_vq(struct virtio_device *dev, return ERR_PTR(-ENOMEM); vdev->vr[index] = va; memset_io(va, 0x0, _vr_size); - vq = vring_new_virtqueue( - index, - le16_to_cpu(config.num), MIC_VIRTIO_RING_ALIGN, - dev, - false, - ctx, - (void __force *)va, vop_notify, callback, name); - if (!vq) { - err = -ENOMEM; - goto unmap; - } + info = va + _vr_size; magic = ioread32(&info->magic); @@ -341,18 +352,27 @@ static struct virtqueue *vop_find_vq(struct virtio_device *dev, goto unmap; } - /* Allocate and reassign used ring now */ vdev->used_size[index] = PAGE_ALIGN(sizeof(__u16) * 3 + sizeof(struct vring_used_elem) * le16_to_cpu(config.num)); used = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, get_order(vdev->used_size[index])); + vdev->used_virt[index] = used; if (!used) { err = -ENOMEM; dev_err(_vop_dev(vdev), "%s %d err %d\n", __func__, __LINE__, err); - goto del_vq; + goto unmap; + } + + vq = vop_new_virtqueue(index, le16_to_cpu(config.num), dev, ctx, + (void __force *)va, vop_notify, callback, + name, used); + if (!vq) { + err = -ENOMEM; + goto free_used; } + vdev->used[index] = dma_map_single(&vpdev->dev, used, vdev->used_size[index], DMA_BIDIRECTIONAL); @@ -360,26 +380,17 @@ static struct virtqueue *vop_find_vq(struct virtio_device *dev, err = -ENOMEM; dev_err(_vop_dev(vdev), "%s %d err %d\n", __func__, __LINE__, err); - goto free_used; + goto del_vq; } writeq(vdev->used[index], &vqconfig->used_address); - /* - * To reassign the used ring here we are directly accessing - * struct vring_virtqueue which is a private data structure - * in virtio_ring.c. At the minimum, a BUILD_BUG_ON() in - * vring_new_virtqueue() would ensure that - * (&vq->vring == (struct vring *) (&vq->vq + 1)); - */ - vr = (struct vring *)(vq + 1); - vr->used = used; vq->priv = vdev; return vq; +del_vq: + vring_del_virtqueue(vq); free_used: free_pages((unsigned long)used, get_order(vdev->used_size[index])); -del_vq: - vring_del_virtqueue(vq); unmap: vpdev->hw_ops->iounmap(vpdev, vdev->vr[index]); return ERR_PTR(err); @@ -581,6 +592,8 @@ static int _vop_remove_device(struct mic_device_desc __iomem *d, int ret = -1; if (ioread8(&dc->config_change) == MIC_VIRTIO_PARAM_DEV_REMOVE) { + struct device *dev = get_device(&vdev->vdev.dev); + dev_dbg(&vpdev->dev, "%s %d config_change %d type %d vdev %p\n", __func__, __LINE__, @@ -592,7 +605,7 @@ static int _vop_remove_device(struct mic_device_desc __iomem *d, iowrite8(-1, &dc->h2c_vdev_db); if (status & VIRTIO_CONFIG_S_DRIVER_OK) wait_for_completion(&vdev->reset_done); - put_device(&vdev->vdev.dev); + put_device(dev); iowrite8(1, &dc->guest_ack); dev_dbg(&vpdev->dev, "%s %d guest_ack %d\n", __func__, __LINE__, ioread8(&dc->guest_ack)); diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index aef1185f383d..14f3fdb8c6bb 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -2112,7 +2112,7 @@ static void mmc_blk_mq_req_done(struct mmc_request *mrq) if (waiting) wake_up(&mq->wait); else - kblockd_schedule_work(&mq->complete_work); + queue_work(mq->card->complete_wq, &mq->complete_work); return; } @@ -2924,6 +2924,13 @@ static int mmc_blk_probe(struct mmc_card *card) mmc_fixup_device(card, mmc_blk_fixups); + card->complete_wq = alloc_workqueue("mmc_complete", + WQ_MEM_RECLAIM | WQ_HIGHPRI, 0); + if (unlikely(!card->complete_wq)) { + pr_err("Failed to create mmc completion workqueue"); + return -ENOMEM; + } + md = mmc_blk_alloc(card); if (IS_ERR(md)) return PTR_ERR(md); @@ -2987,6 +2994,7 @@ static void mmc_blk_remove(struct mmc_card *card) pm_runtime_put_noidle(&card->dev); mmc_blk_remove_req(md); dev_set_drvdata(&card->dev, NULL); + destroy_workqueue(card->complete_wq); } static int _mmc_blk_suspend(struct mmc_card *card) diff --git a/drivers/mmc/host/bcm2835.c b/drivers/mmc/host/bcm2835.c index 50293529d6de..c9e7aa50bb0a 100644 --- a/drivers/mmc/host/bcm2835.c +++ b/drivers/mmc/host/bcm2835.c @@ -1431,6 +1431,8 @@ static int bcm2835_probe(struct platform_device *pdev) err: dev_dbg(dev, "%s -> err %d\n", __func__, ret); + if (host->dma_chan_rxtx) + dma_release_channel(host->dma_chan_rxtx); mmc_free_host(mmc); return ret; diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c index f19ec60bcbdc..2eba507790e4 100644 --- a/drivers/mmc/host/meson-gx-mmc.c +++ b/drivers/mmc/host/meson-gx-mmc.c @@ -1338,7 +1338,8 @@ static int meson_mmc_probe(struct platform_device *pdev) host->regs + SD_EMMC_IRQ_EN); ret = request_threaded_irq(host->irq, meson_mmc_irq, - meson_mmc_irq_thread, IRQF_SHARED, NULL, host); + meson_mmc_irq_thread, IRQF_SHARED, + dev_name(&pdev->dev), host); if (ret) goto err_init_clk; diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c index 8afeaf81ae66..833ef0590af8 100644 --- a/drivers/mmc/host/mtk-sd.c +++ b/drivers/mmc/host/mtk-sd.c @@ -846,7 +846,7 @@ static void msdc_set_mclk(struct msdc_host *host, unsigned char timing, u32 hz) if (timing == MMC_TIMING_MMC_HS400 && host->dev_comp->hs400_tune) - sdr_set_field(host->base + PAD_CMD_TUNE, + sdr_set_field(host->base + tune_reg, MSDC_PAD_TUNE_CMDRRDLY, host->hs400_cmd_int_delay); dev_dbg(host->dev, "sclk: %d, timing: %d\n", host->mmc->actual_clock, diff --git a/drivers/mmc/host/sunxi-mmc.c b/drivers/mmc/host/sunxi-mmc.c index 279e326e397e..70fadc976795 100644 --- a/drivers/mmc/host/sunxi-mmc.c +++ b/drivers/mmc/host/sunxi-mmc.c @@ -1399,13 +1399,37 @@ static int sunxi_mmc_probe(struct platform_device *pdev) mmc->caps |= MMC_CAP_MMC_HIGHSPEED | MMC_CAP_SD_HIGHSPEED | MMC_CAP_ERASE | MMC_CAP_SDIO_IRQ; - if (host->cfg->clk_delays || host->use_new_timings) + /* + * Some H5 devices do not have signal traces precise enough to + * use HS DDR mode for their eMMC chips. + * + * We still enable HS DDR modes for all the other controller + * variants that support them. + */ + if ((host->cfg->clk_delays || host->use_new_timings) && + !of_device_is_compatible(pdev->dev.of_node, + "allwinner,sun50i-h5-emmc")) mmc->caps |= MMC_CAP_1_8V_DDR | MMC_CAP_3_3V_DDR; ret = mmc_of_parse(mmc); if (ret) goto error_free_dma; + /* + * If we don't support delay chains in the SoC, we can't use any + * of the higher speed modes. Mask them out in case the device + * tree specifies the properties for them, which gets added to + * the caps by mmc_of_parse() above. + */ + if (!(host->cfg->clk_delays || host->use_new_timings)) { + mmc->caps &= ~(MMC_CAP_3_3V_DDR | MMC_CAP_1_8V_DDR | + MMC_CAP_1_2V_DDR | MMC_CAP_UHS); + mmc->caps2 &= ~MMC_CAP2_HS200; + } + + /* TODO: This driver doesn't support HS400 mode yet */ + mmc->caps2 &= ~MMC_CAP2_HS400; + ret = sunxi_mmc_init_host(host); if (ret) goto error_free_dma; diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c index 60104e1079c5..37f174ccbcec 100644 --- a/drivers/mtd/mtdpart.c +++ b/drivers/mtd/mtdpart.c @@ -480,6 +480,10 @@ static struct mtd_part *allocate_partition(struct mtd_info *parent, /* let's register it anyway to preserve ordering */ slave->offset = 0; slave->mtd.size = 0; + + /* Initialize ->erasesize to make add_mtd_device() happy. */ + slave->mtd.erasesize = parent->erasesize; + printk(KERN_ERR"mtd: partition \"%s\" is out of reach -- disabled\n", part->name); goto out_register; @@ -632,7 +636,6 @@ err_remove_part: mutex_unlock(&mtd_partitions_mutex); free_partition(new); - pr_info("%s:%i\n", __func__, __LINE__); return ret; } diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c b/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c index bd4cfac6b5aa..a4768df5083f 100644 --- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c +++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c @@ -155,9 +155,10 @@ int gpmi_init(struct gpmi_nand_data *this) /* * Reset BCH here, too. We got failures otherwise :( - * See later BCH reset for explanation of MX23 handling + * See later BCH reset for explanation of MX23 and MX28 handling */ - ret = gpmi_reset_block(r->bch_regs, GPMI_IS_MX23(this)); + ret = gpmi_reset_block(r->bch_regs, + GPMI_IS_MX23(this) || GPMI_IS_MX28(this)); if (ret) goto err_out; @@ -263,12 +264,10 @@ int bch_set_geometry(struct gpmi_nand_data *this) /* * Due to erratum #2847 of the MX23, the BCH cannot be soft reset on this * chip, otherwise it will lock up. So we skip resetting BCH on the MX23. - * On the other hand, the MX28 needs the reset, because one case has been - * seen where the BCH produced ECC errors constantly after 10000 - * consecutive reboots. The latter case has not been seen on the MX23 - * yet, still we don't know if it could happen there as well. + * and MX28. */ - ret = gpmi_reset_block(r->bch_regs, GPMI_IS_MX23(this)); + ret = gpmi_reset_block(r->bch_regs, + GPMI_IS_MX23(this) || GPMI_IS_MX28(this)); if (ret) goto err_out; diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index cca4b24d2ffa..839494ac457c 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -410,6 +410,7 @@ static int nand_check_wp(struct nand_chip *chip) /** * nand_fill_oob - [INTERN] Transfer client buffer to oob + * @chip: NAND chip object * @oob: oob data buffer * @len: oob data write length * @ops: oob ops structure diff --git a/drivers/mtd/nand/raw/nand_bbt.c b/drivers/mtd/nand/raw/nand_bbt.c index 1b722fe9213c..19a2b563acdf 100644 --- a/drivers/mtd/nand/raw/nand_bbt.c +++ b/drivers/mtd/nand/raw/nand_bbt.c @@ -158,7 +158,7 @@ static u32 add_marker_len(struct nand_bbt_descr *td) /** * read_bbt - [GENERIC] Read the bad block table starting from page - * @chip: NAND chip object + * @this: NAND chip object * @buf: temporary buffer * @page: the starting page * @num: the number of bbt descriptors to read diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c index 479c2f2cf17f..fa87ae28cdfe 100644 --- a/drivers/mtd/nand/spi/core.c +++ b/drivers/mtd/nand/spi/core.c @@ -304,24 +304,30 @@ static int spinand_write_to_cache_op(struct spinand_device *spinand, struct nand_device *nand = spinand_to_nand(spinand); struct mtd_info *mtd = nanddev_to_mtd(nand); struct nand_page_io_req adjreq = *req; - unsigned int nbytes = 0; - void *buf = NULL; + void *buf = spinand->databuf; + unsigned int nbytes; u16 column = 0; int ret; - memset(spinand->databuf, 0xff, - nanddev_page_size(nand) + - nanddev_per_page_oobsize(nand)); + /* + * Looks like PROGRAM LOAD (AKA write cache) does not necessarily reset + * the cache content to 0xFF (depends on vendor implementation), so we + * must fill the page cache entirely even if we only want to program + * the data portion of the page, otherwise we might corrupt the BBM or + * user data previously programmed in OOB area. + */ + nbytes = nanddev_page_size(nand) + nanddev_per_page_oobsize(nand); + memset(spinand->databuf, 0xff, nbytes); + adjreq.dataoffs = 0; + adjreq.datalen = nanddev_page_size(nand); + adjreq.databuf.out = spinand->databuf; + adjreq.ooblen = nanddev_per_page_oobsize(nand); + adjreq.ooboffs = 0; + adjreq.oobbuf.out = spinand->oobbuf; - if (req->datalen) { + if (req->datalen) memcpy(spinand->databuf + req->dataoffs, req->databuf.out, req->datalen); - adjreq.dataoffs = 0; - adjreq.datalen = nanddev_page_size(nand); - adjreq.databuf.out = spinand->databuf; - nbytes = adjreq.datalen; - buf = spinand->databuf; - } if (req->ooblen) { if (req->mode == MTD_OPS_AUTO_OOB) @@ -332,14 +338,6 @@ static int spinand_write_to_cache_op(struct spinand_device *spinand, else memcpy(spinand->oobbuf + req->ooboffs, req->oobbuf.out, req->ooblen); - - adjreq.ooblen = nanddev_per_page_oobsize(nand); - adjreq.ooboffs = 0; - nbytes += nanddev_per_page_oobsize(nand); - if (!buf) { - buf = spinand->oobbuf; - column = nanddev_page_size(nand); - } } spinand_cache_op_adjust_colum(spinand, &adjreq, &column); @@ -370,8 +368,8 @@ static int spinand_write_to_cache_op(struct spinand_device *spinand, /* * We need to use the RANDOM LOAD CACHE operation if there's - * more than one iteration, because the LOAD operation resets - * the cache to 0xff. + * more than one iteration, because the LOAD operation might + * reset the cache to 0xff. */ if (nbytes) { column = op.addr.val; @@ -1018,11 +1016,11 @@ static int spinand_init(struct spinand_device *spinand) for (i = 0; i < nand->memorg.ntargets; i++) { ret = spinand_select_target(spinand, i); if (ret) - goto err_free_bufs; + goto err_manuf_cleanup; ret = spinand_lock_block(spinand, BL_ALL_UNLOCKED); if (ret) - goto err_free_bufs; + goto err_manuf_cleanup; } ret = nanddev_init(nand, &spinand_ops, THIS_MODULE); diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index edb1c023a753..6210757772ed 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -145,13 +145,16 @@ config MACVTAP To compile this driver as a module, choose M here: the module will be called macvtap. +config IPVLAN_L3S + depends on NETFILTER + depends on IPVLAN + def_bool y + select NET_L3_MASTER_DEV config IPVLAN tristate "IP-VLAN support" depends on INET depends on IPV6 || !IPV6 - depends on NETFILTER - select NET_L3_MASTER_DEV ---help--- This allows one to create virtual devices off of a main interface and packets will be delivered based on the dest L3 (IPv6/IPv4 addr) @@ -197,9 +200,9 @@ config VXLAN config GENEVE tristate "Generic Network Virtualization Encapsulation" - depends on INET && NET_UDP_TUNNEL + depends on INET depends on IPV6 || !IPV6 - select NET_IP_TUNNEL + select NET_UDP_TUNNEL select GRO_CELLS ---help--- This allows one to create geneve virtual interfaces that provide diff --git a/drivers/net/appletalk/cops.c b/drivers/net/appletalk/cops.c index f90bb723985f..b3c63d2f16aa 100644 --- a/drivers/net/appletalk/cops.c +++ b/drivers/net/appletalk/cops.c @@ -301,7 +301,7 @@ static int __init cops_probe1(struct net_device *dev, int ioaddr) dev->irq = cops_irq(ioaddr, board); if (dev->irq) break; - /* No IRQ found on this port, fallthrough */ + /* fall through - Once no IRQ found on this port. */ case 1: retval = -EINVAL; goto err_out; diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 4d5d01cb8141..da1fc17295d9 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -1375,6 +1375,7 @@ static int bond_option_slaves_set(struct bonding *bond, sscanf(newval->string, "%16s", command); /* IFNAMSIZ*/ ifname = command + 1; if ((strlen(command) <= 1) || + (command[0] != '+' && command[0] != '-') || !dev_valid_name(ifname)) goto err_no_cmd; @@ -1398,6 +1399,7 @@ static int bond_option_slaves_set(struct bonding *bond, break; default: + /* should not run here. */ goto err_no_cmd; } diff --git a/drivers/net/caif/caif_serial.c b/drivers/net/caif/caif_serial.c index a0f954f36c09..44e6c7b1b222 100644 --- a/drivers/net/caif/caif_serial.c +++ b/drivers/net/caif/caif_serial.c @@ -257,10 +257,7 @@ static int handle_tx(struct ser_device *ser) if (skb->len == 0) { struct sk_buff *tmp = skb_dequeue(&ser->head); WARN_ON(tmp != skb); - if (in_interrupt()) - dev_kfree_skb_irq(skb); - else - kfree_skb(skb); + dev_consume_skb_any(skb); } } /* Send flow off if queue is empty */ diff --git a/drivers/net/caif/caif_spi.c b/drivers/net/caif/caif_spi.c index d28a1398c091..7608bc3e00df 100644 --- a/drivers/net/caif/caif_spi.c +++ b/drivers/net/caif/caif_spi.c @@ -73,35 +73,37 @@ MODULE_PARM_DESC(spi_down_tail_align, "SPI downlink tail alignment."); #define LOW_WATER_MARK 100 #define HIGH_WATER_MARK (LOW_WATER_MARK*5) -#ifdef CONFIG_UML +#ifndef CONFIG_HAS_DMA /* * We sometimes use UML for debugging, but it cannot handle * dma_alloc_coherent so we have to wrap it. */ -static inline void *dma_alloc(dma_addr_t *daddr) +static inline void *dma_alloc(struct cfspi *cfspi, dma_addr_t *daddr) { return kmalloc(SPI_DMA_BUF_LEN, GFP_KERNEL); } -static inline void dma_free(void *cpu_addr, dma_addr_t handle) +static inline void dma_free(struct cfspi *cfspi, void *cpu_addr, + dma_addr_t handle) { kfree(cpu_addr); } #else -static inline void *dma_alloc(dma_addr_t *daddr) +static inline void *dma_alloc(struct cfspi *cfspi, dma_addr_t *daddr) { - return dma_alloc_coherent(NULL, SPI_DMA_BUF_LEN, daddr, + return dma_alloc_coherent(&cfspi->pdev->dev, SPI_DMA_BUF_LEN, daddr, GFP_KERNEL); } -static inline void dma_free(void *cpu_addr, dma_addr_t handle) +static inline void dma_free(struct cfspi *cfspi, void *cpu_addr, + dma_addr_t handle) { - dma_free_coherent(NULL, SPI_DMA_BUF_LEN, cpu_addr, handle); + dma_free_coherent(&cfspi->pdev->dev, SPI_DMA_BUF_LEN, cpu_addr, handle); } -#endif /* CONFIG_UML */ +#endif /* CONFIG_HAS_DMA */ #ifdef CONFIG_DEBUG_FS @@ -610,13 +612,13 @@ static int cfspi_init(struct net_device *dev) } /* Allocate DMA buffers. */ - cfspi->xfer.va_tx[0] = dma_alloc(&cfspi->xfer.pa_tx[0]); + cfspi->xfer.va_tx[0] = dma_alloc(cfspi, &cfspi->xfer.pa_tx[0]); if (!cfspi->xfer.va_tx[0]) { res = -ENODEV; goto err_dma_alloc_tx_0; } - cfspi->xfer.va_rx = dma_alloc(&cfspi->xfer.pa_rx); + cfspi->xfer.va_rx = dma_alloc(cfspi, &cfspi->xfer.pa_rx); if (!cfspi->xfer.va_rx) { res = -ENODEV; @@ -665,9 +667,9 @@ static int cfspi_init(struct net_device *dev) return 0; err_create_wq: - dma_free(cfspi->xfer.va_rx, cfspi->xfer.pa_rx); + dma_free(cfspi, cfspi->xfer.va_rx, cfspi->xfer.pa_rx); err_dma_alloc_rx: - dma_free(cfspi->xfer.va_tx[0], cfspi->xfer.pa_tx[0]); + dma_free(cfspi, cfspi->xfer.va_tx[0], cfspi->xfer.pa_tx[0]); err_dma_alloc_tx_0: return res; } @@ -683,8 +685,8 @@ static void cfspi_uninit(struct net_device *dev) cfspi->ndev = NULL; /* Free DMA buffers. */ - dma_free(cfspi->xfer.va_rx, cfspi->xfer.pa_rx); - dma_free(cfspi->xfer.va_tx[0], cfspi->xfer.pa_tx[0]); + dma_free(cfspi, cfspi->xfer.va_rx, cfspi->xfer.pa_rx); + dma_free(cfspi, cfspi->xfer.va_tx[0], cfspi->xfer.pa_tx[0]); set_bit(SPI_TERMINATE, &cfspi->state); wake_up_interruptible(&cfspi->wait); destroy_workqueue(cfspi->wq); diff --git a/drivers/net/dsa/b53/b53_srab.c b/drivers/net/dsa/b53/b53_srab.c index 90f514252987..d9c56a779c08 100644 --- a/drivers/net/dsa/b53/b53_srab.c +++ b/drivers/net/dsa/b53/b53_srab.c @@ -511,9 +511,6 @@ static void b53_srab_prepare_irq(struct platform_device *pdev) /* Clear all pending interrupts */ writel(0xffffffff, priv->regs + B53_SRAB_INTR); - if (dev->pdata && dev->pdata->chip_id != BCM58XX_DEVICE_ID) - return; - for (i = 0; i < B53_N_PORTS; i++) { port = &priv->port_intrs[i]; diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 361fbde76654..98696a88fa1c 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -690,7 +690,7 @@ static int bcm_sf2_sw_suspend(struct dsa_switch *ds) * port, the other ones have already been disabled during * bcm_sf2_sw_setup */ - for (port = 0; port < DSA_MAX_PORTS; port++) { + for (port = 0; port < ds->num_ports; port++) { if (dsa_is_user_port(ds, port) || dsa_is_cpu_port(ds, port)) bcm_sf2_port_disable(ds, port, NULL); } @@ -894,12 +894,44 @@ static const struct b53_io_ops bcm_sf2_io_ops = { .write64 = bcm_sf2_core_write64, }; +static void bcm_sf2_sw_get_strings(struct dsa_switch *ds, int port, + u32 stringset, uint8_t *data) +{ + int cnt = b53_get_sset_count(ds, port, stringset); + + b53_get_strings(ds, port, stringset, data); + bcm_sf2_cfp_get_strings(ds, port, stringset, + data + cnt * ETH_GSTRING_LEN); +} + +static void bcm_sf2_sw_get_ethtool_stats(struct dsa_switch *ds, int port, + uint64_t *data) +{ + int cnt = b53_get_sset_count(ds, port, ETH_SS_STATS); + + b53_get_ethtool_stats(ds, port, data); + bcm_sf2_cfp_get_ethtool_stats(ds, port, data + cnt); +} + +static int bcm_sf2_sw_get_sset_count(struct dsa_switch *ds, int port, + int sset) +{ + int cnt = b53_get_sset_count(ds, port, sset); + + if (cnt < 0) + return cnt; + + cnt += bcm_sf2_cfp_get_sset_count(ds, port, sset); + + return cnt; +} + static const struct dsa_switch_ops bcm_sf2_ops = { .get_tag_protocol = b53_get_tag_protocol, .setup = bcm_sf2_sw_setup, - .get_strings = b53_get_strings, - .get_ethtool_stats = b53_get_ethtool_stats, - .get_sset_count = b53_get_sset_count, + .get_strings = bcm_sf2_sw_get_strings, + .get_ethtool_stats = bcm_sf2_sw_get_ethtool_stats, + .get_sset_count = bcm_sf2_sw_get_sset_count, .get_ethtool_phy_stats = b53_get_ethtool_phy_stats, .get_phy_flags = bcm_sf2_sw_get_phy_flags, .phylink_validate = bcm_sf2_sw_validate, @@ -1062,7 +1094,6 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev) dev_set_drvdata(&pdev->dev, priv); spin_lock_init(&priv->indir_lock); - mutex_init(&priv->stats_mutex); mutex_init(&priv->cfp.lock); INIT_LIST_HEAD(&priv->cfp.rules_list); diff --git a/drivers/net/dsa/bcm_sf2.h b/drivers/net/dsa/bcm_sf2.h index faaef320ec48..eb3655bea467 100644 --- a/drivers/net/dsa/bcm_sf2.h +++ b/drivers/net/dsa/bcm_sf2.h @@ -87,9 +87,6 @@ struct bcm_sf2_priv { /* Backing b53_device */ struct b53_device *dev; - /* Mutex protecting access to the MIB counters */ - struct mutex stats_mutex; - struct bcm_sf2_hw_params hw_params; struct bcm_sf2_port_status port_sts[DSA_MAX_PORTS]; @@ -216,5 +213,10 @@ int bcm_sf2_set_rxnfc(struct dsa_switch *ds, int port, int bcm_sf2_cfp_rst(struct bcm_sf2_priv *priv); void bcm_sf2_cfp_exit(struct dsa_switch *ds); int bcm_sf2_cfp_resume(struct dsa_switch *ds); +void bcm_sf2_cfp_get_strings(struct dsa_switch *ds, int port, + u32 stringset, uint8_t *data); +void bcm_sf2_cfp_get_ethtool_stats(struct dsa_switch *ds, int port, + uint64_t *data); +int bcm_sf2_cfp_get_sset_count(struct dsa_switch *ds, int port, int sset); #endif /* __BCM_SF2_H */ diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c index e14663ab6dbc..e6234d209787 100644 --- a/drivers/net/dsa/bcm_sf2_cfp.c +++ b/drivers/net/dsa/bcm_sf2_cfp.c @@ -16,6 +16,7 @@ #include <linux/netdevice.h> #include <net/dsa.h> #include <linux/bitmap.h> +#include <net/flow_offload.h> #include "bcm_sf2.h" #include "bcm_sf2_regs.h" @@ -212,6 +213,7 @@ static inline unsigned int bcm_sf2_cfp_rule_size(struct bcm_sf2_priv *priv) static int bcm_sf2_cfp_act_pol_set(struct bcm_sf2_priv *priv, unsigned int rule_index, + int src_port, unsigned int port_num, unsigned int queue_num, bool fwd_map_change) @@ -229,6 +231,10 @@ static int bcm_sf2_cfp_act_pol_set(struct bcm_sf2_priv *priv, else reg = 0; + /* Enable looping back to the original port */ + if (src_port == port_num) + reg |= LOOP_BK_EN; + core_writel(priv, reg, CORE_ACT_POL_DATA0); /* Set classification ID that needs to be put in Broadcom tag */ @@ -257,7 +263,8 @@ static int bcm_sf2_cfp_act_pol_set(struct bcm_sf2_priv *priv, } static void bcm_sf2_cfp_slice_ipv4(struct bcm_sf2_priv *priv, - struct ethtool_tcpip4_spec *v4_spec, + struct flow_dissector_key_ipv4_addrs *addrs, + struct flow_dissector_key_ports *ports, unsigned int slice_num, bool mask) { @@ -278,7 +285,7 @@ static void bcm_sf2_cfp_slice_ipv4(struct bcm_sf2_priv *priv, * UDF_n_A6 [23:8] * UDF_n_A5 [7:0] */ - reg = be16_to_cpu(v4_spec->pdst) >> 8; + reg = be16_to_cpu(ports->dst) >> 8; if (mask) offset = CORE_CFP_MASK_PORT(3); else @@ -289,9 +296,9 @@ static void bcm_sf2_cfp_slice_ipv4(struct bcm_sf2_priv *priv, * UDF_n_A4 [23:8] * UDF_n_A3 [7:0] */ - reg = (be16_to_cpu(v4_spec->pdst) & 0xff) << 24 | - (u32)be16_to_cpu(v4_spec->psrc) << 8 | - (be32_to_cpu(v4_spec->ip4dst) & 0x0000ff00) >> 8; + reg = (be16_to_cpu(ports->dst) & 0xff) << 24 | + (u32)be16_to_cpu(ports->src) << 8 | + (be32_to_cpu(addrs->dst) & 0x0000ff00) >> 8; if (mask) offset = CORE_CFP_MASK_PORT(2); else @@ -302,9 +309,9 @@ static void bcm_sf2_cfp_slice_ipv4(struct bcm_sf2_priv *priv, * UDF_n_A2 [23:8] * UDF_n_A1 [7:0] */ - reg = (u32)(be32_to_cpu(v4_spec->ip4dst) & 0xff) << 24 | - (u32)(be32_to_cpu(v4_spec->ip4dst) >> 16) << 8 | - (be32_to_cpu(v4_spec->ip4src) & 0x0000ff00) >> 8; + reg = (u32)(be32_to_cpu(addrs->dst) & 0xff) << 24 | + (u32)(be32_to_cpu(addrs->dst) >> 16) << 8 | + (be32_to_cpu(addrs->src) & 0x0000ff00) >> 8; if (mask) offset = CORE_CFP_MASK_PORT(1); else @@ -317,8 +324,8 @@ static void bcm_sf2_cfp_slice_ipv4(struct bcm_sf2_priv *priv, * Slice ID [3:2] * Slice valid [1:0] */ - reg = (u32)(be32_to_cpu(v4_spec->ip4src) & 0xff) << 24 | - (u32)(be32_to_cpu(v4_spec->ip4src) >> 16) << 8 | + reg = (u32)(be32_to_cpu(addrs->src) & 0xff) << 24 | + (u32)(be32_to_cpu(addrs->src) >> 16) << 8 | SLICE_NUM(slice_num) | SLICE_VALID; if (mask) offset = CORE_CFP_MASK_PORT(0); @@ -332,9 +339,13 @@ static int bcm_sf2_cfp_ipv4_rule_set(struct bcm_sf2_priv *priv, int port, unsigned int queue_num, struct ethtool_rx_flow_spec *fs) { - struct ethtool_tcpip4_spec *v4_spec, *v4_m_spec; + struct ethtool_rx_flow_spec_input input = {}; const struct cfp_udf_layout *layout; unsigned int slice_num, rule_index; + struct ethtool_rx_flow_rule *flow; + struct flow_match_ipv4_addrs ipv4; + struct flow_match_ports ports; + struct flow_match_ip ip; u8 ip_proto, ip_frag; u8 num_udf; u32 reg; @@ -343,13 +354,9 @@ static int bcm_sf2_cfp_ipv4_rule_set(struct bcm_sf2_priv *priv, int port, switch (fs->flow_type & ~FLOW_EXT) { case TCP_V4_FLOW: ip_proto = IPPROTO_TCP; - v4_spec = &fs->h_u.tcp_ip4_spec; - v4_m_spec = &fs->m_u.tcp_ip4_spec; break; case UDP_V4_FLOW: ip_proto = IPPROTO_UDP; - v4_spec = &fs->h_u.udp_ip4_spec; - v4_m_spec = &fs->m_u.udp_ip4_spec; break; default: return -EINVAL; @@ -367,11 +374,22 @@ static int bcm_sf2_cfp_ipv4_rule_set(struct bcm_sf2_priv *priv, int port, if (rule_index > bcm_sf2_cfp_rule_size(priv)) return -ENOSPC; + input.fs = fs; + flow = ethtool_rx_flow_rule_create(&input); + if (IS_ERR(flow)) + return PTR_ERR(flow); + + flow_rule_match_ipv4_addrs(flow->rule, &ipv4); + flow_rule_match_ports(flow->rule, &ports); + flow_rule_match_ip(flow->rule, &ip); + layout = &udf_tcpip4_layout; /* We only use one UDF slice for now */ slice_num = bcm_sf2_get_slice_number(layout, 0); - if (slice_num == UDF_NUM_SLICES) - return -EINVAL; + if (slice_num == UDF_NUM_SLICES) { + ret = -EINVAL; + goto out_err_flow_rule; + } num_udf = bcm_sf2_get_num_udf_slices(layout->udfs[slice_num].slices); @@ -398,7 +416,7 @@ static int bcm_sf2_cfp_ipv4_rule_set(struct bcm_sf2_priv *priv, int port, * Reserved [1] * UDF_Valid[8] [0] */ - core_writel(priv, v4_spec->tos << IPTOS_SHIFT | + core_writel(priv, ip.key->tos << IPTOS_SHIFT | ip_proto << IPPROTO_SHIFT | ip_frag << IP_FRAG_SHIFT | udf_upper_bits(num_udf), CORE_CFP_DATA_PORT(6)); @@ -417,8 +435,8 @@ static int bcm_sf2_cfp_ipv4_rule_set(struct bcm_sf2_priv *priv, int port, core_writel(priv, udf_lower_bits(num_udf) << 24, CORE_CFP_MASK_PORT(5)); /* Program the match and the mask */ - bcm_sf2_cfp_slice_ipv4(priv, v4_spec, slice_num, false); - bcm_sf2_cfp_slice_ipv4(priv, v4_m_spec, SLICE_NUM_MASK, true); + bcm_sf2_cfp_slice_ipv4(priv, ipv4.key, ports.key, slice_num, false); + bcm_sf2_cfp_slice_ipv4(priv, ipv4.mask, ports.mask, SLICE_NUM_MASK, true); /* Insert into TCAM now */ bcm_sf2_cfp_rule_addr_set(priv, rule_index); @@ -426,14 +444,14 @@ static int bcm_sf2_cfp_ipv4_rule_set(struct bcm_sf2_priv *priv, int port, ret = bcm_sf2_cfp_op(priv, OP_SEL_WRITE | TCAM_SEL); if (ret) { pr_err("TCAM entry at addr %d failed\n", rule_index); - return ret; + goto out_err_flow_rule; } /* Insert into Action and policer RAMs now */ - ret = bcm_sf2_cfp_act_pol_set(priv, rule_index, port_num, + ret = bcm_sf2_cfp_act_pol_set(priv, rule_index, port, port_num, queue_num, true); if (ret) - return ret; + goto out_err_flow_rule; /* Turn on CFP for this rule now */ reg = core_readl(priv, CORE_CFP_CTL_REG); @@ -446,6 +464,10 @@ static int bcm_sf2_cfp_ipv4_rule_set(struct bcm_sf2_priv *priv, int port, fs->location = rule_index; return 0; + +out_err_flow_rule: + ethtool_rx_flow_rule_destroy(flow); + return ret; } static void bcm_sf2_cfp_slice_ipv6(struct bcm_sf2_priv *priv, @@ -581,9 +603,12 @@ static int bcm_sf2_cfp_ipv6_rule_set(struct bcm_sf2_priv *priv, int port, unsigned int queue_num, struct ethtool_rx_flow_spec *fs) { - struct ethtool_tcpip6_spec *v6_spec, *v6_m_spec; + struct ethtool_rx_flow_spec_input input = {}; unsigned int slice_num, rule_index[2]; const struct cfp_udf_layout *layout; + struct ethtool_rx_flow_rule *flow; + struct flow_match_ipv6_addrs ipv6; + struct flow_match_ports ports; u8 ip_proto, ip_frag; int ret = 0; u8 num_udf; @@ -592,13 +617,9 @@ static int bcm_sf2_cfp_ipv6_rule_set(struct bcm_sf2_priv *priv, int port, switch (fs->flow_type & ~FLOW_EXT) { case TCP_V6_FLOW: ip_proto = IPPROTO_TCP; - v6_spec = &fs->h_u.tcp_ip6_spec; - v6_m_spec = &fs->m_u.tcp_ip6_spec; break; case UDP_V6_FLOW: ip_proto = IPPROTO_UDP; - v6_spec = &fs->h_u.udp_ip6_spec; - v6_m_spec = &fs->m_u.udp_ip6_spec; break; default: return -EINVAL; @@ -645,6 +666,15 @@ static int bcm_sf2_cfp_ipv6_rule_set(struct bcm_sf2_priv *priv, int port, goto out_err; } + input.fs = fs; + flow = ethtool_rx_flow_rule_create(&input); + if (IS_ERR(flow)) { + ret = PTR_ERR(flow); + goto out_err; + } + flow_rule_match_ipv6_addrs(flow->rule, &ipv6); + flow_rule_match_ports(flow->rule, &ports); + /* Apply the UDF layout for this filter */ bcm_sf2_cfp_udf_set(priv, layout, slice_num); @@ -688,10 +718,10 @@ static int bcm_sf2_cfp_ipv6_rule_set(struct bcm_sf2_priv *priv, int port, core_writel(priv, udf_lower_bits(num_udf) << 24, CORE_CFP_MASK_PORT(5)); /* Slice the IPv6 source address and port */ - bcm_sf2_cfp_slice_ipv6(priv, v6_spec->ip6src, v6_spec->psrc, - slice_num, false); - bcm_sf2_cfp_slice_ipv6(priv, v6_m_spec->ip6src, v6_m_spec->psrc, - SLICE_NUM_MASK, true); + bcm_sf2_cfp_slice_ipv6(priv, ipv6.key->src.in6_u.u6_addr32, + ports.key->src, slice_num, false); + bcm_sf2_cfp_slice_ipv6(priv, ipv6.mask->src.in6_u.u6_addr32, + ports.mask->src, SLICE_NUM_MASK, true); /* Insert into TCAM now because we need to insert a second rule */ bcm_sf2_cfp_rule_addr_set(priv, rule_index[0]); @@ -699,20 +729,20 @@ static int bcm_sf2_cfp_ipv6_rule_set(struct bcm_sf2_priv *priv, int port, ret = bcm_sf2_cfp_op(priv, OP_SEL_WRITE | TCAM_SEL); if (ret) { pr_err("TCAM entry at addr %d failed\n", rule_index[0]); - goto out_err; + goto out_err_flow_rule; } /* Insert into Action and policer RAMs now */ - ret = bcm_sf2_cfp_act_pol_set(priv, rule_index[0], port_num, + ret = bcm_sf2_cfp_act_pol_set(priv, rule_index[0], port, port_num, queue_num, false); if (ret) - goto out_err; + goto out_err_flow_rule; /* Now deal with the second slice to chain this rule */ slice_num = bcm_sf2_get_slice_number(layout, slice_num + 1); if (slice_num == UDF_NUM_SLICES) { ret = -EINVAL; - goto out_err; + goto out_err_flow_rule; } num_udf = bcm_sf2_get_num_udf_slices(layout->udfs[slice_num].slices); @@ -748,10 +778,10 @@ static int bcm_sf2_cfp_ipv6_rule_set(struct bcm_sf2_priv *priv, int port, /* Mask all */ core_writel(priv, 0, CORE_CFP_MASK_PORT(5)); - bcm_sf2_cfp_slice_ipv6(priv, v6_spec->ip6dst, v6_spec->pdst, slice_num, - false); - bcm_sf2_cfp_slice_ipv6(priv, v6_m_spec->ip6dst, v6_m_spec->pdst, - SLICE_NUM_MASK, true); + bcm_sf2_cfp_slice_ipv6(priv, ipv6.key->dst.in6_u.u6_addr32, + ports.key->dst, slice_num, false); + bcm_sf2_cfp_slice_ipv6(priv, ipv6.mask->dst.in6_u.u6_addr32, + ports.key->dst, SLICE_NUM_MASK, true); /* Insert into TCAM now */ bcm_sf2_cfp_rule_addr_set(priv, rule_index[1]); @@ -759,16 +789,16 @@ static int bcm_sf2_cfp_ipv6_rule_set(struct bcm_sf2_priv *priv, int port, ret = bcm_sf2_cfp_op(priv, OP_SEL_WRITE | TCAM_SEL); if (ret) { pr_err("TCAM entry at addr %d failed\n", rule_index[1]); - goto out_err; + goto out_err_flow_rule; } /* Insert into Action and policer RAMs now, set chain ID to * the one we are chained to */ - ret = bcm_sf2_cfp_act_pol_set(priv, rule_index[1], port_num, + ret = bcm_sf2_cfp_act_pol_set(priv, rule_index[1], port, port_num, queue_num, true); if (ret) - goto out_err; + goto out_err_flow_rule; /* Turn on CFP for this rule now */ reg = core_readl(priv, CORE_CFP_CTL_REG); @@ -784,6 +814,8 @@ static int bcm_sf2_cfp_ipv6_rule_set(struct bcm_sf2_priv *priv, int port, return ret; +out_err_flow_rule: + ethtool_rx_flow_rule_destroy(flow); out_err: clear_bit(rule_index[1], priv->cfp.used); return ret; @@ -1169,3 +1201,91 @@ int bcm_sf2_cfp_resume(struct dsa_switch *ds) return ret; } + +static const struct bcm_sf2_cfp_stat { + unsigned int offset; + unsigned int ram_loc; + const char *name; +} bcm_sf2_cfp_stats[] = { + { + .offset = CORE_STAT_GREEN_CNTR, + .ram_loc = GREEN_STAT_RAM, + .name = "Green" + }, + { + .offset = CORE_STAT_YELLOW_CNTR, + .ram_loc = YELLOW_STAT_RAM, + .name = "Yellow" + }, + { + .offset = CORE_STAT_RED_CNTR, + .ram_loc = RED_STAT_RAM, + .name = "Red" + }, +}; + +void bcm_sf2_cfp_get_strings(struct dsa_switch *ds, int port, + u32 stringset, uint8_t *data) +{ + struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); + unsigned int s = ARRAY_SIZE(bcm_sf2_cfp_stats); + char buf[ETH_GSTRING_LEN]; + unsigned int i, j, iter; + + if (stringset != ETH_SS_STATS) + return; + + for (i = 1; i < priv->num_cfp_rules; i++) { + for (j = 0; j < s; j++) { + snprintf(buf, sizeof(buf), + "CFP%03d_%sCntr", + i, bcm_sf2_cfp_stats[j].name); + iter = (i - 1) * s + j; + strlcpy(data + iter * ETH_GSTRING_LEN, + buf, ETH_GSTRING_LEN); + } + } +} + +void bcm_sf2_cfp_get_ethtool_stats(struct dsa_switch *ds, int port, + uint64_t *data) +{ + struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); + unsigned int s = ARRAY_SIZE(bcm_sf2_cfp_stats); + const struct bcm_sf2_cfp_stat *stat; + unsigned int i, j, iter; + struct cfp_rule *rule; + int ret; + + mutex_lock(&priv->cfp.lock); + for (i = 1; i < priv->num_cfp_rules; i++) { + rule = bcm_sf2_cfp_rule_find(priv, port, i); + if (!rule) + continue; + + for (j = 0; j < s; j++) { + stat = &bcm_sf2_cfp_stats[j]; + + bcm_sf2_cfp_rule_addr_set(priv, i); + ret = bcm_sf2_cfp_op(priv, stat->ram_loc | OP_SEL_READ); + if (ret) + continue; + + iter = (i - 1) * s + j; + data[iter] = core_readl(priv, stat->offset); + } + + } + mutex_unlock(&priv->cfp.lock); +} + +int bcm_sf2_cfp_get_sset_count(struct dsa_switch *ds, int port, int sset) +{ + struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); + + if (sset != ETH_SS_STATS) + return 0; + + /* 3 counters per CFP rules */ + return (priv->num_cfp_rules - 1) * ARRAY_SIZE(bcm_sf2_cfp_stats); +} diff --git a/drivers/net/dsa/bcm_sf2_regs.h b/drivers/net/dsa/bcm_sf2_regs.h index 0a1e530d52b7..67f056206f37 100644 --- a/drivers/net/dsa/bcm_sf2_regs.h +++ b/drivers/net/dsa/bcm_sf2_regs.h @@ -400,6 +400,10 @@ enum bcm_sf2_reg_offs { #define CORE_RATE_METER6 0x281e0 #define CIR_REF_CNT_MASK 0x7ffff +#define CORE_STAT_GREEN_CNTR 0x28200 +#define CORE_STAT_YELLOW_CNTR 0x28210 +#define CORE_STAT_RED_CNTR 0x28220 + #define CORE_CFP_CTL_REG 0x28400 #define CFP_EN_MAP_MASK 0x1ff diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c index 816f34d64736..17482ae09aa5 100644 --- a/drivers/net/dsa/dsa_loop.c +++ b/drivers/net/dsa/dsa_loop.c @@ -343,7 +343,7 @@ static int __init dsa_loop_init(void) unsigned int i; for (i = 0; i < NUM_FIXED_PHYS; i++) - phydevs[i] = fixed_phy_register(PHY_POLL, &status, -1, NULL); + phydevs[i] = fixed_phy_register(PHY_POLL, &status, NULL); return mdio_driver_register(&dsa_loop_drv); } diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index 89ed059bb576..674d77e1b029 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -397,6 +397,7 @@ static void ksz9477_port_stp_state_set(struct dsa_switch *ds, int port, struct ksz_port *p = &dev->ports[port]; u8 data; int member = -1; + int forward = dev->member; ksz_pread8(dev, port, P_STP_CTRL, &data); data &= ~(PORT_TX_ENABLE | PORT_RX_ENABLE | PORT_LEARN_DISABLE); @@ -464,10 +465,10 @@ static void ksz9477_port_stp_state_set(struct dsa_switch *ds, int port, } /* When topology has changed the function ksz_update_port_member - * should be called to modify port forwarding behavior. However - * as the offload_fwd_mark indication cannot be reported here - * the switch forwarding function is not enabled. + * should be called to modify port forwarding behavior. */ + if (forward != dev->member) + ksz_update_port_member(dev, port); } static void ksz9477_flush_dyn_mac_table(struct ksz_device *dev, int port) diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index a8a2c728afba..c2b61500f958 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -621,17 +621,19 @@ static void mt7530_adjust_link(struct dsa_switch *ds, int port, struct mt7530_priv *priv = ds->priv; if (phy_is_pseudo_fixed_link(phydev)) { - dev_dbg(priv->dev, "phy-mode for master device = %x\n", - phydev->interface); - - /* Setup TX circuit incluing relevant PAD and driving */ - mt7530_pad_clk_setup(ds, phydev->interface); - - /* Setup RX circuit, relevant PAD and driving on the host - * which must be placed after the setup on the device side is - * all finished. - */ - mt7623_pad_clk_setup(ds); + if (priv->id == ID_MT7530) { + dev_dbg(priv->dev, "phy-mode for master device = %x\n", + phydev->interface); + + /* Setup TX circuit incluing relevant PAD and driving */ + mt7530_pad_clk_setup(ds, phydev->interface); + + /* Setup RX circuit, relevant PAD and driving on the + * host which must be placed after the setup on the + * device side is all finished. + */ + mt7623_pad_clk_setup(ds); + } } else { u16 lcl_adv = 0, rmt_adv = 0; u8 flowctrl; @@ -687,6 +689,10 @@ mt7530_cpu_port_enable(struct mt7530_priv *priv, /* Unknown unicast frame fordwarding to the cpu port */ mt7530_set(priv, MT7530_MFC, UNU_FFP(BIT(port))); + /* Set CPU port number */ + if (priv->id == ID_MT7621) + mt7530_rmw(priv, MT7530_MFC, CPU_MASK, CPU_EN | CPU_PORT(port)); + /* CPU port gets connected to all user ports of * the switch */ @@ -1219,24 +1225,27 @@ mt7530_setup(struct dsa_switch *ds) * as two netdev instances. */ dn = ds->ports[MT7530_CPU_PORT].master->dev.of_node->parent; - priv->ethernet = syscon_node_to_regmap(dn); - if (IS_ERR(priv->ethernet)) - return PTR_ERR(priv->ethernet); - regulator_set_voltage(priv->core_pwr, 1000000, 1000000); - ret = regulator_enable(priv->core_pwr); - if (ret < 0) { - dev_err(priv->dev, - "Failed to enable core power: %d\n", ret); - return ret; - } + if (priv->id == ID_MT7530) { + priv->ethernet = syscon_node_to_regmap(dn); + if (IS_ERR(priv->ethernet)) + return PTR_ERR(priv->ethernet); + + regulator_set_voltage(priv->core_pwr, 1000000, 1000000); + ret = regulator_enable(priv->core_pwr); + if (ret < 0) { + dev_err(priv->dev, + "Failed to enable core power: %d\n", ret); + return ret; + } - regulator_set_voltage(priv->io_pwr, 3300000, 3300000); - ret = regulator_enable(priv->io_pwr); - if (ret < 0) { - dev_err(priv->dev, "Failed to enable io pwr: %d\n", - ret); - return ret; + regulator_set_voltage(priv->io_pwr, 3300000, 3300000); + ret = regulator_enable(priv->io_pwr); + if (ret < 0) { + dev_err(priv->dev, "Failed to enable io pwr: %d\n", + ret); + return ret; + } } /* Reset whole chip through gpio pin or memory-mapped registers for @@ -1326,6 +1335,13 @@ static const struct dsa_switch_ops mt7530_switch_ops = { .port_vlan_del = mt7530_port_vlan_del, }; +static const struct of_device_id mt7530_of_match[] = { + { .compatible = "mediatek,mt7621", .data = (void *)ID_MT7621, }, + { .compatible = "mediatek,mt7530", .data = (void *)ID_MT7530, }, + { /* sentinel */ }, +}; +MODULE_DEVICE_TABLE(of, mt7530_of_match); + static int mt7530_probe(struct mdio_device *mdiodev) { @@ -1356,13 +1372,21 @@ mt7530_probe(struct mdio_device *mdiodev) } } - priv->core_pwr = devm_regulator_get(&mdiodev->dev, "core"); - if (IS_ERR(priv->core_pwr)) - return PTR_ERR(priv->core_pwr); + /* Get the hardware identifier from the devicetree node. + * We will need it for some of the clock and regulator setup. + */ + priv->id = (unsigned int)(unsigned long) + of_device_get_match_data(&mdiodev->dev); - priv->io_pwr = devm_regulator_get(&mdiodev->dev, "io"); - if (IS_ERR(priv->io_pwr)) - return PTR_ERR(priv->io_pwr); + if (priv->id == ID_MT7530) { + priv->core_pwr = devm_regulator_get(&mdiodev->dev, "core"); + if (IS_ERR(priv->core_pwr)) + return PTR_ERR(priv->core_pwr); + + priv->io_pwr = devm_regulator_get(&mdiodev->dev, "io"); + if (IS_ERR(priv->io_pwr)) + return PTR_ERR(priv->io_pwr); + } /* Not MCM that indicates switch works as the remote standalone * integrated circuit so the GPIO pin would be used to complete @@ -1408,12 +1432,6 @@ mt7530_remove(struct mdio_device *mdiodev) mutex_destroy(&priv->reg_mutex); } -static const struct of_device_id mt7530_of_match[] = { - { .compatible = "mediatek,mt7530" }, - { /* sentinel */ }, -}; -MODULE_DEVICE_TABLE(of, mt7530_of_match); - static struct mdio_driver mt7530_mdio_driver = { .probe = mt7530_probe, .remove = mt7530_remove, diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h index d9b407a22a58..a95ed958df5b 100644 --- a/drivers/net/dsa/mt7530.h +++ b/drivers/net/dsa/mt7530.h @@ -19,6 +19,11 @@ #define MT7530_NUM_FDB_RECORDS 2048 #define MT7530_ALL_MEMBERS 0xff +enum { + ID_MT7530 = 0, + ID_MT7621 = 1, +}; + #define NUM_TRGMII_CTRL 5 #define TRGMII_BASE(x) (0x10000 + (x)) @@ -36,6 +41,9 @@ #define UNM_FFP(x) (((x) & 0xff) << 16) #define UNU_FFP(x) (((x) & 0xff) << 8) #define UNU_FFP_MASK UNU_FFP(~0) +#define CPU_EN BIT(7) +#define CPU_PORT(x) ((x) << 4) +#define CPU_MASK (0xf << 4) /* Registers for address table access */ #define MT7530_ATA1 0x74 @@ -430,6 +438,7 @@ struct mt7530_priv { struct regulator *core_pwr; struct regulator *io_pwr; struct gpio_desc *reset; + unsigned int id; bool mcm; struct mt7530_port ports[MT7530_NUM_PORTS]; diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 8dca2c949e73..32e7af5caa69 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -261,6 +261,7 @@ static irqreturn_t mv88e6xxx_g1_irq_thread_work(struct mv88e6xxx_chip *chip) unsigned int sub_irq; unsigned int n; u16 reg; + u16 ctl1; int err; mutex_lock(&chip->reg_lock); @@ -270,13 +271,28 @@ static irqreturn_t mv88e6xxx_g1_irq_thread_work(struct mv88e6xxx_chip *chip) if (err) goto out; - for (n = 0; n < chip->g1_irq.nirqs; ++n) { - if (reg & (1 << n)) { - sub_irq = irq_find_mapping(chip->g1_irq.domain, n); - handle_nested_irq(sub_irq); - ++nhandled; + do { + for (n = 0; n < chip->g1_irq.nirqs; ++n) { + if (reg & (1 << n)) { + sub_irq = irq_find_mapping(chip->g1_irq.domain, + n); + handle_nested_irq(sub_irq); + ++nhandled; + } } - } + + mutex_lock(&chip->reg_lock); + err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_CTL1, &ctl1); + if (err) + goto unlock; + err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_STS, ®); +unlock: + mutex_unlock(&chip->reg_lock); + if (err) + goto out; + ctl1 &= GENMASK(chip->g1_irq.nirqs, 0); + } while (reg & ctl1); + out: return (nhandled > 0 ? IRQ_HANDLED : IRQ_NONE); } @@ -647,8 +663,10 @@ static void mv88e6390_phylink_validate(struct mv88e6xxx_chip *chip, int port, unsigned long *mask, struct phylink_link_state *state) { - if (port >= 9) + if (port >= 9) { phylink_set(mask, 2500baseX_Full); + phylink_set(mask, 2500baseT_Full); + } /* No ethtool bits for 200Mbps */ phylink_set(mask, 1000baseT_Full); @@ -4764,6 +4782,21 @@ static const void *pdata_device_get_match_data(struct device *dev) return NULL; } +/* There is no suspend to RAM support at DSA level yet, the switch configuration + * would be lost after a power cycle so prevent it to be suspended. + */ +static int __maybe_unused mv88e6xxx_suspend(struct device *dev) +{ + return -EOPNOTSUPP; +} + +static int __maybe_unused mv88e6xxx_resume(struct device *dev) +{ + return 0; +} + +static SIMPLE_DEV_PM_OPS(mv88e6xxx_pm_ops, mv88e6xxx_suspend, mv88e6xxx_resume); + static int mv88e6xxx_probe(struct mdio_device *mdiodev) { struct dsa_mv88e6xxx_pdata *pdata = mdiodev->dev.platform_data; @@ -4948,6 +4981,7 @@ static struct mdio_driver mv88e6xxx_driver = { .mdiodrv.driver = { .name = "mv88e6085", .of_match_table = mv88e6xxx_of_match, + .pm = &mv88e6xxx_pm_ops, }, }; diff --git a/drivers/net/dsa/mv88e6xxx/global1_atu.c b/drivers/net/dsa/mv88e6xxx/global1_atu.c index 5200e4bdce93..ea243840ee0f 100644 --- a/drivers/net/dsa/mv88e6xxx/global1_atu.c +++ b/drivers/net/dsa/mv88e6xxx/global1_atu.c @@ -314,6 +314,7 @@ static irqreturn_t mv88e6xxx_g1_atu_prob_irq_thread_fn(int irq, void *dev_id) { struct mv88e6xxx_chip *chip = dev_id; struct mv88e6xxx_atu_entry entry; + int spid; int err; u16 val; @@ -336,6 +337,8 @@ static irqreturn_t mv88e6xxx_g1_atu_prob_irq_thread_fn(int irq, void *dev_id) if (err) goto out; + spid = entry.state; + if (val & MV88E6XXX_G1_ATU_OP_AGE_OUT_VIOLATION) { dev_err_ratelimited(chip->dev, "ATU age out violation for %pM\n", @@ -344,23 +347,23 @@ static irqreturn_t mv88e6xxx_g1_atu_prob_irq_thread_fn(int irq, void *dev_id) if (val & MV88E6XXX_G1_ATU_OP_MEMBER_VIOLATION) { dev_err_ratelimited(chip->dev, - "ATU member violation for %pM portvec %x\n", - entry.mac, entry.portvec); - chip->ports[entry.portvec].atu_member_violation++; + "ATU member violation for %pM portvec %x spid %d\n", + entry.mac, entry.portvec, spid); + chip->ports[spid].atu_member_violation++; } if (val & MV88E6XXX_G1_ATU_OP_MISS_VIOLATION) { dev_err_ratelimited(chip->dev, - "ATU miss violation for %pM portvec %x\n", - entry.mac, entry.portvec); - chip->ports[entry.portvec].atu_miss_violation++; + "ATU miss violation for %pM portvec %x spid %d\n", + entry.mac, entry.portvec, spid); + chip->ports[spid].atu_miss_violation++; } if (val & MV88E6XXX_G1_ATU_OP_FULL_VIOLATION) { dev_err_ratelimited(chip->dev, - "ATU full violation for %pM portvec %x\n", - entry.mac, entry.portvec); - chip->ports[entry.portvec].atu_full_violation++; + "ATU full violation for %pM portvec %x spid %d\n", + entry.mac, entry.portvec, spid); + chip->ports[spid].atu_full_violation++; } mutex_unlock(&chip->reg_lock); diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c index 2caa8c8b4b55..1bfc5ff8d81d 100644 --- a/drivers/net/dsa/mv88e6xxx/serdes.c +++ b/drivers/net/dsa/mv88e6xxx/serdes.c @@ -664,7 +664,7 @@ int mv88e6390_serdes_irq_setup(struct mv88e6xxx_chip *chip, int port) if (port < 9) return 0; - return mv88e6390_serdes_irq_setup(chip, port); + return mv88e6390x_serdes_irq_setup(chip, port); } void mv88e6390x_serdes_irq_free(struct mv88e6xxx_chip *chip, int port) diff --git a/drivers/net/ethernet/3com/3c515.c b/drivers/net/ethernet/3com/3c515.c index b648e3f95c01..808abb6b3671 100644 --- a/drivers/net/ethernet/3com/3c515.c +++ b/drivers/net/ethernet/3com/3c515.c @@ -1177,7 +1177,7 @@ static irqreturn_t corkscrew_interrupt(int irq, void *dev_id) if (inl(ioaddr + DownListPtr) == isa_virt_to_bus(&lp->tx_ring[entry])) break; /* It still hasn't been processed. */ if (lp->tx_skbuff[entry]) { - dev_kfree_skb_irq(lp->tx_skbuff[entry]); + dev_consume_skb_irq(lp->tx_skbuff[entry]); lp->tx_skbuff[entry] = NULL; } dirty_tx++; @@ -1192,7 +1192,7 @@ static irqreturn_t corkscrew_interrupt(int irq, void *dev_id) #ifdef VORTEX_BUS_MASTER if (status & DMADone) { outw(0x1000, ioaddr + Wn7_MasterStatus); /* Ack the event. */ - dev_kfree_skb_irq(lp->tx_skb); /* Release the transferred buffer */ + dev_consume_skb_irq(lp->tx_skb); /* Release the transferred buffer */ netif_wake_queue(dev); } #endif diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c index 40f421dbdf57..147051404194 100644 --- a/drivers/net/ethernet/3com/3c59x.c +++ b/drivers/net/ethernet/3com/3c59x.c @@ -2307,7 +2307,7 @@ _vortex_interrupt(int irq, struct net_device *dev) dma_unmap_single(vp->gendev, vp->tx_skb_dma, (vp->tx_skb->len + 3) & ~3, DMA_TO_DEVICE); pkts_compl++; bytes_compl += vp->tx_skb->len; - dev_kfree_skb_irq(vp->tx_skb); /* Release the transferred buffer */ + dev_consume_skb_irq(vp->tx_skb); /* Release the transferred buffer */ if (ioread16(ioaddr + TxFree) > 1536) { /* * AKPM: FIXME: I don't think we need this. If the queue was stopped due to @@ -2449,7 +2449,7 @@ _boomerang_interrupt(int irq, struct net_device *dev) #endif pkts_compl++; bytes_compl += skb->len; - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); vp->tx_skbuff[entry] = NULL; } else { pr_debug("boomerang_interrupt: no skb!\n"); diff --git a/drivers/net/ethernet/adaptec/starfire.c b/drivers/net/ethernet/adaptec/starfire.c index 097467f44b0d..816540e6beac 100644 --- a/drivers/net/ethernet/adaptec/starfire.c +++ b/drivers/net/ethernet/adaptec/starfire.c @@ -1390,7 +1390,7 @@ static irqreturn_t intr_handler(int irq, void *dev_instance) } } - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); } np->tx_done_q[np->tx_done].status = 0; np->tx_done = (np->tx_done + 1) % DONE_Q_SIZE; diff --git a/drivers/net/ethernet/alteon/acenic.c b/drivers/net/ethernet/alteon/acenic.c index 4f11f98347ed..1827ef1f6d55 100644 --- a/drivers/net/ethernet/alteon/acenic.c +++ b/drivers/net/ethernet/alteon/acenic.c @@ -2059,7 +2059,7 @@ static inline void ace_tx_int(struct net_device *dev, if (skb) { dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); info->skb = NULL; } diff --git a/drivers/net/ethernet/altera/altera_msgdma.c b/drivers/net/ethernet/altera/altera_msgdma.c index 0fb986ba3290..0ae723f75341 100644 --- a/drivers/net/ethernet/altera/altera_msgdma.c +++ b/drivers/net/ethernet/altera/altera_msgdma.c @@ -145,7 +145,8 @@ u32 msgdma_tx_completions(struct altera_tse_private *priv) & 0xffff; if (inuse) { /* Tx FIFO is not empty */ - ready = priv->tx_prod - priv->tx_cons - inuse - 1; + ready = max_t(int, + priv->tx_prod - priv->tx_cons - inuse - 1, 0); } else { /* Check for buffered last packet */ status = csrrd32(priv->tx_dma_csr, msgdma_csroffs(status)); diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index a70bb1bb90e7..a6eacf2099c3 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -2663,11 +2663,6 @@ static int ena_restore_device(struct ena_adapter *adapter) goto err_device_destroy; } - clear_bit(ENA_FLAG_ONGOING_RESET, &adapter->flags); - /* Make sure we don't have a race with AENQ Links state handler */ - if (test_bit(ENA_FLAG_LINK_UP, &adapter->flags)) - netif_carrier_on(adapter->netdev); - rc = ena_enable_msix_and_set_admin_interrupts(adapter, adapter->num_queues); if (rc) { @@ -2684,6 +2679,11 @@ static int ena_restore_device(struct ena_adapter *adapter) } set_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags); + + clear_bit(ENA_FLAG_ONGOING_RESET, &adapter->flags); + if (test_bit(ENA_FLAG_LINK_UP, &adapter->flags)) + netif_carrier_on(adapter->netdev); + mod_timer(&adapter->timer_service, round_jiffies(jiffies + HZ)); dev_err(&pdev->dev, "Device reset completed successfully, Driver info: %s\n", diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h index dc8b6173d8d8..63870072cbbd 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.h +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h @@ -45,7 +45,7 @@ #define DRV_MODULE_VER_MAJOR 2 #define DRV_MODULE_VER_MINOR 0 -#define DRV_MODULE_VER_SUBMINOR 2 +#define DRV_MODULE_VER_SUBMINOR 3 #define DRV_MODULE_NAME "ena" #ifndef DRV_MODULE_VERSION diff --git a/drivers/net/ethernet/amd/amd8111e.c b/drivers/net/ethernet/amd/amd8111e.c index b9632928496e..145fe71fd155 100644 --- a/drivers/net/ethernet/amd/amd8111e.c +++ b/drivers/net/ethernet/amd/amd8111e.c @@ -666,7 +666,7 @@ static int amd8111e_tx(struct net_device *dev) pci_unmap_single(lp->pci_dev, lp->tx_dma_addr[tx_index], lp->tx_skbuff[tx_index]->len, PCI_DMA_TODEVICE); - dev_kfree_skb_irq (lp->tx_skbuff[tx_index]); + dev_consume_skb_irq(lp->tx_skbuff[tx_index]); lp->tx_skbuff[tx_index] = NULL; lp->tx_dma_addr[tx_index] = 0; } diff --git a/drivers/net/ethernet/amd/au1000_eth.c b/drivers/net/ethernet/amd/au1000_eth.c index e833d1b3fe18..e5073aeea06a 100644 --- a/drivers/net/ethernet/amd/au1000_eth.c +++ b/drivers/net/ethernet/amd/au1000_eth.c @@ -1167,7 +1167,7 @@ static int au1000_probe(struct platform_device *pdev) /* Allocate the data buffers * Snooping works fine with eth on all au1xxx */ - aup->vaddr = (u32)dma_alloc_attrs(NULL, MAX_BUF_SIZE * + aup->vaddr = (u32)dma_alloc_attrs(&pdev->dev, MAX_BUF_SIZE * (NUM_TX_BUFFS + NUM_RX_BUFFS), &aup->dma_addr, 0, DMA_ATTR_NON_CONSISTENT); @@ -1349,7 +1349,7 @@ err_remap3: err_remap2: iounmap(aup->mac); err_remap1: - dma_free_attrs(NULL, MAX_BUF_SIZE * (NUM_TX_BUFFS + NUM_RX_BUFFS), + dma_free_attrs(&pdev->dev, MAX_BUF_SIZE * (NUM_TX_BUFFS + NUM_RX_BUFFS), (void *)aup->vaddr, aup->dma_addr, DMA_ATTR_NON_CONSISTENT); err_vaddr: @@ -1383,7 +1383,7 @@ static int au1000_remove(struct platform_device *pdev) if (aup->tx_db_inuse[i]) au1000_ReleaseDB(aup, aup->tx_db_inuse[i]); - dma_free_attrs(NULL, MAX_BUF_SIZE * (NUM_TX_BUFFS + NUM_RX_BUFFS), + dma_free_attrs(&pdev->dev, MAX_BUF_SIZE * (NUM_TX_BUFFS + NUM_RX_BUFFS), (void *)aup->vaddr, aup->dma_addr, DMA_ATTR_NON_CONSISTENT); diff --git a/drivers/net/ethernet/amd/lance.c b/drivers/net/ethernet/amd/lance.c index b56d84c7df46..f90b454b1642 100644 --- a/drivers/net/ethernet/amd/lance.c +++ b/drivers/net/ethernet/amd/lance.c @@ -1084,7 +1084,7 @@ static irqreturn_t lance_interrupt(int irq, void *dev_id) /* We must free the original skb if it's not a data-only copy in the bounce buffer. */ if (lp->tx_skbuff[entry]) { - dev_kfree_skb_irq(lp->tx_skbuff[entry]); + dev_consume_skb_irq(lp->tx_skbuff[entry]); lp->tx_skbuff[entry] = NULL; } dirty_tx++; diff --git a/drivers/net/ethernet/amd/ni65.c b/drivers/net/ethernet/amd/ni65.c index 8931ce6bab7b..87ff5d6d1b22 100644 --- a/drivers/net/ethernet/amd/ni65.c +++ b/drivers/net/ethernet/amd/ni65.c @@ -1028,7 +1028,7 @@ static void ni65_xmit_intr(struct net_device *dev,int csr0) #ifdef XMT_VIA_SKB if(p->tmd_skb[p->tmdlast]) { - dev_kfree_skb_irq(p->tmd_skb[p->tmdlast]); + dev_consume_skb_irq(p->tmd_skb[p->tmdlast]); p->tmd_skb[p->tmdlast] = NULL; } #endif diff --git a/drivers/net/ethernet/apple/bmac.c b/drivers/net/ethernet/apple/bmac.c index 6a8e2567f2bd..4d3855ceb500 100644 --- a/drivers/net/ethernet/apple/bmac.c +++ b/drivers/net/ethernet/apple/bmac.c @@ -777,7 +777,7 @@ static irqreturn_t bmac_txdma_intr(int irq, void *dev_id) if (bp->tx_bufs[bp->tx_empty]) { ++dev->stats.tx_packets; - dev_kfree_skb_irq(bp->tx_bufs[bp->tx_empty]); + dev_consume_skb_irq(bp->tx_bufs[bp->tx_empty]); } bp->tx_bufs[bp->tx_empty] = NULL; bp->tx_fullup = 0; diff --git a/drivers/net/ethernet/apple/mace.c b/drivers/net/ethernet/apple/mace.c index 68b9ee489489..4d9819d2894d 100644 --- a/drivers/net/ethernet/apple/mace.c +++ b/drivers/net/ethernet/apple/mace.c @@ -764,7 +764,7 @@ static irqreturn_t mace_interrupt(int irq, void *dev_id) dev->stats.tx_bytes += mp->tx_bufs[i]->len; ++dev->stats.tx_packets; } - dev_kfree_skb_irq(mp->tx_bufs[i]); + dev_consume_skb_irq(mp->tx_bufs[i]); --mp->tx_active; if (++i >= N_TX_RING) i = 0; diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c index 4406325fdd9f..ff3d68532f5f 100644 --- a/drivers/net/ethernet/arc/emac_main.c +++ b/drivers/net/ethernet/arc/emac_main.c @@ -148,7 +148,7 @@ static void arc_emac_tx_clean(struct net_device *ndev) dma_unmap_len(tx_buff, len), DMA_TO_DEVICE); /* return the sk_buff to system */ - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); txbd->data = 0; txbd->info = 0; diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c index 3a3b35b5df67..0f1eb1981469 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c @@ -1833,10 +1833,10 @@ rrs_checked: atl1c_clean_rrd(rrd_ring, rrs, rfd_num); if (rrs->word3 & (RRS_RX_ERR_SUM | RRS_802_3_LEN_ERR)) { atl1c_clean_rfd(rfd_ring, rrs, rfd_num); - if (netif_msg_rx_err(adapter)) - dev_warn(&pdev->dev, - "wrong packet! rrs word3 is %x\n", - rrs->word3); + if (netif_msg_rx_err(adapter)) + dev_warn(&pdev->dev, + "wrong packet! rrs word3 is %x\n", + rrs->word3); continue; } diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c index 3164aad29bcf..9dfe6a9431e6 100644 --- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c +++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c @@ -1259,7 +1259,7 @@ static bool atl1e_clean_tx_irq(struct atl1e_adapter *adapter) } if (tx_buffer->skb) { - dev_kfree_skb_irq(tx_buffer->skb); + dev_consume_skb_irq(tx_buffer->skb); tx_buffer->skb = NULL; } diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c index 63edc5706c09..9e07b469066a 100644 --- a/drivers/net/ethernet/atheros/atlx/atl1.c +++ b/drivers/net/ethernet/atheros/atlx/atl1.c @@ -2088,7 +2088,7 @@ static int atl1_intr_tx(struct atl1_adapter *adapter) } if (buffer_info->skb) { - dev_kfree_skb_irq(buffer_info->skb); + dev_consume_skb_irq(buffer_info->skb); buffer_info->skb = NULL; } diff --git a/drivers/net/ethernet/atheros/atlx/atl2.c b/drivers/net/ethernet/atheros/atlx/atl2.c index c44e95255aa1..a7337a6d507d 100644 --- a/drivers/net/ethernet/atheros/atlx/atl2.c +++ b/drivers/net/ethernet/atheros/atlx/atl2.c @@ -2946,7 +2946,7 @@ static int atl2_validate_option(int *value, struct atl2_option *opt) if (*value == ent->i) { if (ent->str[0] != '\0') printk(KERN_INFO "%s\n", ent->str); - return 0; + return 0; } } break; diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c index f44808959ff3..97ab0dd25552 100644 --- a/drivers/net/ethernet/broadcom/b44.c +++ b/drivers/net/ethernet/broadcom/b44.c @@ -638,7 +638,7 @@ static void b44_tx(struct b44 *bp) bytes_compl += skb->len; pkts_compl++; - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); } netdev_completed_queue(bp->dev, pkts_compl, bytes_compl); @@ -1012,7 +1012,7 @@ static netdev_tx_t b44_start_xmit(struct sk_buff *skb, struct net_device *dev) } skb_copy_from_linear_data(skb, skb_put(bounce_skb, len), len); - dev_kfree_skb_any(skb); + dev_consume_skb_any(skb); skb = bounce_skb; } diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index f9521d0274b7..28c9b0bdf2f6 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -520,7 +520,6 @@ static void bcm_sysport_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) { struct bcm_sysport_priv *priv = netdev_priv(dev); - u32 reg; wol->supported = WAKE_MAGIC | WAKE_MAGICSECURE | WAKE_FILTER; wol->wolopts = priv->wolopts; @@ -528,11 +527,7 @@ static void bcm_sysport_get_wol(struct net_device *dev, if (!(priv->wolopts & WAKE_MAGICSECURE)) return; - /* Return the programmed SecureOn password */ - reg = umac_readl(priv, UMAC_PSW_MS); - put_unaligned_be16(reg, &wol->sopass[0]); - reg = umac_readl(priv, UMAC_PSW_LS); - put_unaligned_be32(reg, &wol->sopass[2]); + memcpy(wol->sopass, priv->sopass, sizeof(priv->sopass)); } static int bcm_sysport_set_wol(struct net_device *dev, @@ -548,13 +543,8 @@ static int bcm_sysport_set_wol(struct net_device *dev, if (wol->wolopts & ~supported) return -EINVAL; - /* Program the SecureOn password */ - if (wol->wolopts & WAKE_MAGICSECURE) { - umac_writel(priv, get_unaligned_be16(&wol->sopass[0]), - UMAC_PSW_MS); - umac_writel(priv, get_unaligned_be32(&wol->sopass[2]), - UMAC_PSW_LS); - } + if (wol->wolopts & WAKE_MAGICSECURE) + memcpy(priv->sopass, wol->sopass, sizeof(priv->sopass)); /* Flag the device and relevant IRQ as wakeup capable */ if (wol->wolopts) { @@ -2649,13 +2639,18 @@ static int bcm_sysport_suspend_to_wol(struct bcm_sysport_priv *priv) unsigned int index, i = 0; u32 reg; - /* Password has already been programmed */ reg = umac_readl(priv, UMAC_MPD_CTRL); if (priv->wolopts & (WAKE_MAGIC | WAKE_MAGICSECURE)) reg |= MPD_EN; reg &= ~PSW_EN; - if (priv->wolopts & WAKE_MAGICSECURE) + if (priv->wolopts & WAKE_MAGICSECURE) { + /* Program the SecureOn password */ + umac_writel(priv, get_unaligned_be16(&priv->sopass[0]), + UMAC_PSW_MS); + umac_writel(priv, get_unaligned_be32(&priv->sopass[2]), + UMAC_PSW_LS); reg |= PSW_EN; + } umac_writel(priv, reg, UMAC_MPD_CTRL); if (priv->wolopts & WAKE_FILTER) { diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h index 0887e6356649..0b192fea9c5d 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.h +++ b/drivers/net/ethernet/broadcom/bcmsysport.h @@ -12,6 +12,7 @@ #define __BCM_SYSPORT_H #include <linux/bitmap.h> +#include <linux/ethtool.h> #include <linux/if_vlan.h> #include <linux/net_dim.h> @@ -778,6 +779,7 @@ struct bcm_sysport_priv { unsigned int crc_fwd:1; u16 rev; u32 wolopts; + u8 sopass[SOPASS_MAX]; unsigned int wol_irq_disabled:1; /* MIB related fields */ diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index 2d3a44c40221..4632dd5dbad1 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -1446,7 +1446,7 @@ int bgmac_phy_connect_direct(struct bgmac *bgmac) struct phy_device *phy_dev; int err; - phy_dev = fixed_phy_register(PHY_POLL, &fphy_status, -1, NULL); + phy_dev = fixed_phy_register(PHY_POLL, &fphy_status, NULL); if (!phy_dev || IS_ERR(phy_dev)) { dev_err(bgmac->dev, "Failed to register fixed PHY device\n"); return -ENODEV; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c index 8e0a317b31f7..a9bdc21873d3 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c @@ -1654,13 +1654,9 @@ static int bnx2x_vf_mbx_macvlan_list(struct bnx2x *bp, { int i, j; struct bnx2x_vf_mac_vlan_filters *fl = NULL; - size_t fsz; - fsz = tlv->n_mac_vlan_filters * - sizeof(struct bnx2x_vf_mac_vlan_filter) + - sizeof(struct bnx2x_vf_mac_vlan_filters); - - fl = kzalloc(fsz, GFP_KERNEL); + fl = kzalloc(struct_size(fl, filters, tlv->n_mac_vlan_filters), + GFP_KERNEL); if (!fl) return -ENOMEM; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 6a512871176b..92d73453a318 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -4973,12 +4973,18 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp) struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring; struct bnxt_ring_struct *ring = &cpr->cp_ring_struct; u32 map_idx = ring->map_idx; + unsigned int vector; + vector = bp->irq_tbl[map_idx].vector; + disable_irq_nosync(vector); rc = hwrm_ring_alloc_send_msg(bp, ring, type, map_idx); - if (rc) + if (rc) { + enable_irq(vector); goto err_out; + } bnxt_set_db(bp, &cpr->cp_db, type, map_idx, ring->fw_ring_id); bnxt_db_nq(bp, &cpr->cp_db, cpr->cp_raw_cons); + enable_irq(vector); bp->grp_info[i].cp_fw_ring_id = ring->fw_ring_id; if (!i) { @@ -9981,8 +9987,11 @@ static int bnxt_get_phys_port_name(struct net_device *dev, char *buf, return 0; } -int bnxt_port_attr_get(struct bnxt *bp, struct switchdev_attr *attr) +int bnxt_get_port_parent_id(struct net_device *dev, + struct netdev_phys_item_id *ppid) { + struct bnxt *bp = netdev_priv(dev); + if (bp->eswitch_mode != DEVLINK_ESWITCH_MODE_SWITCHDEV) return -EOPNOTSUPP; @@ -9990,27 +9999,12 @@ int bnxt_port_attr_get(struct bnxt *bp, struct switchdev_attr *attr) if (!BNXT_PF(bp)) return -EOPNOTSUPP; - switch (attr->id) { - case SWITCHDEV_ATTR_ID_PORT_PARENT_ID: - attr->u.ppid.id_len = sizeof(bp->switch_id); - memcpy(attr->u.ppid.id, bp->switch_id, attr->u.ppid.id_len); - break; - default: - return -EOPNOTSUPP; - } - return 0; -} + ppid->id_len = sizeof(bp->switch_id); + memcpy(ppid->id, bp->switch_id, ppid->id_len); -static int bnxt_swdev_port_attr_get(struct net_device *dev, - struct switchdev_attr *attr) -{ - return bnxt_port_attr_get(netdev_priv(dev), attr); + return 0; } -static const struct switchdev_ops bnxt_switchdev_ops = { - .switchdev_port_attr_get = bnxt_swdev_port_attr_get -}; - static const struct net_device_ops bnxt_netdev_ops = { .ndo_open = bnxt_open, .ndo_start_xmit = bnxt_start_xmit, @@ -10042,6 +10036,7 @@ static const struct net_device_ops bnxt_netdev_ops = { .ndo_bpf = bnxt_xdp, .ndo_bridge_getlink = bnxt_bridge_getlink, .ndo_bridge_setlink = bnxt_bridge_setlink, + .ndo_get_port_parent_id = bnxt_get_port_parent_id, .ndo_get_phys_port_name = bnxt_get_phys_port_name }; @@ -10400,7 +10395,6 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) dev->netdev_ops = &bnxt_netdev_ops; dev->watchdog_timeo = BNXT_TX_TIMEOUT; dev->ethtool_ops = &bnxt_ethtool_ops; - SWITCHDEV_SET_OPS(dev, &bnxt_switchdev_ops); pci_set_drvdata(pdev, dev); rc = bnxt_alloc_hwrm_resources(bp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index a451796deefe..17554d4be651 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -22,7 +22,6 @@ #include <linux/rhashtable.h> #include <net/devlink.h> #include <net/dst_metadata.h> -#include <net/switchdev.h> #include <net/xdp.h> #include <linux/net_dim.h> @@ -1609,6 +1608,7 @@ struct bnxt { /* devlink interface and vf-rep structs */ struct devlink *dl; + struct devlink_port dl_port; enum devlink_eswitch_mode eswitch_mode; struct bnxt_vf_rep **vf_reps; /* array of vf-rep ptrs */ u16 *cfa_code_map; /* cfa_code -> vf_idx map */ @@ -1794,7 +1794,8 @@ int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs, int bnxt_setup_mq_tc(struct net_device *dev, u8 tc); int bnxt_get_max_rings(struct bnxt *, int *, int *, bool); int bnxt_restore_pf_fw_resources(struct bnxt *bp); -int bnxt_port_attr_get(struct bnxt *bp, struct switchdev_attr *attr); +int bnxt_get_port_parent_id(struct net_device *dev, + struct netdev_phys_item_id *ppid); void bnxt_dim_work(struct work_struct *work); int bnxt_hwrm_set_ring_coal(struct bnxt *bp, struct bnxt_napi *bnapi); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index 7f56032e44ac..e1feb97bcd81 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -188,6 +188,9 @@ static const struct devlink_param bnxt_dl_params[] = { NULL), }; +static const struct devlink_param bnxt_dl_port_params[] = { +}; + int bnxt_dl_register(struct bnxt *bp) { struct devlink *dl; @@ -225,8 +228,29 @@ int bnxt_dl_register(struct bnxt *bp) goto err_dl_unreg; } + rc = devlink_port_register(dl, &bp->dl_port, bp->pf.port_id); + if (rc) { + netdev_err(bp->dev, "devlink_port_register failed"); + goto err_dl_param_unreg; + } + devlink_port_type_eth_set(&bp->dl_port, bp->dev); + + rc = devlink_port_params_register(&bp->dl_port, bnxt_dl_port_params, + ARRAY_SIZE(bnxt_dl_port_params)); + if (rc) { + netdev_err(bp->dev, "devlink_port_params_register failed"); + goto err_dl_port_unreg; + } + + devlink_params_publish(dl); + return 0; +err_dl_port_unreg: + devlink_port_unregister(&bp->dl_port); +err_dl_param_unreg: + devlink_params_unregister(dl, bnxt_dl_params, + ARRAY_SIZE(bnxt_dl_params)); err_dl_unreg: devlink_unregister(dl); err_dl_free: @@ -242,6 +266,9 @@ void bnxt_dl_unregister(struct bnxt *bp) if (!dl) return; + devlink_port_params_unregister(&bp->dl_port, bnxt_dl_port_params, + ARRAY_SIZE(bnxt_dl_port_params)); + devlink_port_unregister(&bp->dl_port); devlink_params_unregister(dl, bnxt_dl_params, ARRAY_SIZE(bnxt_dl_params)); devlink_unregister(dl); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c index c683b5e96b1d..61a3457ed71b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c @@ -45,7 +45,7 @@ static u16 bnxt_flow_get_dst_fid(struct bnxt *pf_bp, struct net_device *dev) struct bnxt *bp; /* check if dev belongs to the same switch */ - if (!switchdev_port_same_parent_id(pf_bp->dev, dev)) { + if (!netdev_port_same_parent_id(pf_bp->dev, dev)) { netdev_info(pf_bp->dev, "dev(ifindex=%d) not on same switch", dev->ifindex); return BNXT_FID_INVALID; @@ -61,9 +61,9 @@ static u16 bnxt_flow_get_dst_fid(struct bnxt *pf_bp, struct net_device *dev) static int bnxt_tc_parse_redir(struct bnxt *bp, struct bnxt_tc_actions *actions, - const struct tc_action *tc_act) + const struct flow_action_entry *act) { - struct net_device *dev = tcf_mirred_dev(tc_act); + struct net_device *dev = act->dev; if (!dev) { netdev_info(bp->dev, "no dev in mirred action"); @@ -77,16 +77,16 @@ static int bnxt_tc_parse_redir(struct bnxt *bp, static int bnxt_tc_parse_vlan(struct bnxt *bp, struct bnxt_tc_actions *actions, - const struct tc_action *tc_act) + const struct flow_action_entry *act) { - switch (tcf_vlan_action(tc_act)) { - case TCA_VLAN_ACT_POP: + switch (act->id) { + case FLOW_ACTION_VLAN_POP: actions->flags |= BNXT_TC_ACTION_FLAG_POP_VLAN; break; - case TCA_VLAN_ACT_PUSH: + case FLOW_ACTION_VLAN_PUSH: actions->flags |= BNXT_TC_ACTION_FLAG_PUSH_VLAN; - actions->push_vlan_tci = htons(tcf_vlan_push_vid(tc_act)); - actions->push_vlan_tpid = tcf_vlan_push_proto(tc_act); + actions->push_vlan_tci = htons(act->vlan.vid); + actions->push_vlan_tpid = act->vlan.proto; break; default: return -EOPNOTSUPP; @@ -96,10 +96,10 @@ static int bnxt_tc_parse_vlan(struct bnxt *bp, static int bnxt_tc_parse_tunnel_set(struct bnxt *bp, struct bnxt_tc_actions *actions, - const struct tc_action *tc_act) + const struct flow_action_entry *act) { - struct ip_tunnel_info *tun_info = tcf_tunnel_info(tc_act); - struct ip_tunnel_key *tun_key = &tun_info->key; + const struct ip_tunnel_info *tun_info = act->tunnel; + const struct ip_tunnel_key *tun_key = &tun_info->key; if (ip_tunnel_info_af(tun_info) != AF_INET) { netdev_info(bp->dev, "only IPv4 tunnel-encap is supported"); @@ -113,51 +113,43 @@ static int bnxt_tc_parse_tunnel_set(struct bnxt *bp, static int bnxt_tc_parse_actions(struct bnxt *bp, struct bnxt_tc_actions *actions, - struct tcf_exts *tc_exts) + struct flow_action *flow_action) { - const struct tc_action *tc_act; + struct flow_action_entry *act; int i, rc; - if (!tcf_exts_has_actions(tc_exts)) { + if (!flow_action_has_entries(flow_action)) { netdev_info(bp->dev, "no actions"); return -EINVAL; } - tcf_exts_for_each_action(i, tc_act, tc_exts) { - /* Drop action */ - if (is_tcf_gact_shot(tc_act)) { + flow_action_for_each(i, act, flow_action) { + switch (act->id) { + case FLOW_ACTION_DROP: actions->flags |= BNXT_TC_ACTION_FLAG_DROP; return 0; /* don't bother with other actions */ - } - - /* Redirect action */ - if (is_tcf_mirred_egress_redirect(tc_act)) { - rc = bnxt_tc_parse_redir(bp, actions, tc_act); + case FLOW_ACTION_REDIRECT: + rc = bnxt_tc_parse_redir(bp, actions, act); if (rc) return rc; - continue; - } - - /* Push/pop VLAN */ - if (is_tcf_vlan(tc_act)) { - rc = bnxt_tc_parse_vlan(bp, actions, tc_act); + break; + case FLOW_ACTION_VLAN_POP: + case FLOW_ACTION_VLAN_PUSH: + case FLOW_ACTION_VLAN_MANGLE: + rc = bnxt_tc_parse_vlan(bp, actions, act); if (rc) return rc; - continue; - } - - /* Tunnel encap */ - if (is_tcf_tunnel_set(tc_act)) { - rc = bnxt_tc_parse_tunnel_set(bp, actions, tc_act); + break; + case FLOW_ACTION_TUNNEL_ENCAP: + rc = bnxt_tc_parse_tunnel_set(bp, actions, act); if (rc) return rc; - continue; - } - - /* Tunnel decap */ - if (is_tcf_tunnel_release(tc_act)) { + break; + case FLOW_ACTION_TUNNEL_DECAP: actions->flags |= BNXT_TC_ACTION_FLAG_TUNNEL_DECAP; - continue; + break; + default: + break; } } @@ -177,18 +169,12 @@ static int bnxt_tc_parse_actions(struct bnxt *bp, return 0; } -#define GET_KEY(flow_cmd, key_type) \ - skb_flow_dissector_target((flow_cmd)->dissector, key_type,\ - (flow_cmd)->key) -#define GET_MASK(flow_cmd, key_type) \ - skb_flow_dissector_target((flow_cmd)->dissector, key_type,\ - (flow_cmd)->mask) - static int bnxt_tc_parse_flow(struct bnxt *bp, struct tc_cls_flower_offload *tc_flow_cmd, struct bnxt_tc_flow *flow) { - struct flow_dissector *dissector = tc_flow_cmd->dissector; + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(tc_flow_cmd); + struct flow_dissector *dissector = rule->match.dissector; /* KEY_CONTROL and KEY_BASIC are needed for forming a meaningful key */ if ((dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_CONTROL)) == 0 || @@ -198,143 +184,123 @@ static int bnxt_tc_parse_flow(struct bnxt *bp, return -EOPNOTSUPP; } - if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_BASIC)) { - struct flow_dissector_key_basic *key = - GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_BASIC); - struct flow_dissector_key_basic *mask = - GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_BASIC); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_match_basic match; - flow->l2_key.ether_type = key->n_proto; - flow->l2_mask.ether_type = mask->n_proto; + flow_rule_match_basic(rule, &match); + flow->l2_key.ether_type = match.key->n_proto; + flow->l2_mask.ether_type = match.mask->n_proto; - if (key->n_proto == htons(ETH_P_IP) || - key->n_proto == htons(ETH_P_IPV6)) { - flow->l4_key.ip_proto = key->ip_proto; - flow->l4_mask.ip_proto = mask->ip_proto; + if (match.key->n_proto == htons(ETH_P_IP) || + match.key->n_proto == htons(ETH_P_IPV6)) { + flow->l4_key.ip_proto = match.key->ip_proto; + flow->l4_mask.ip_proto = match.mask->ip_proto; } } - if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { - struct flow_dissector_key_eth_addrs *key = - GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ETH_ADDRS); - struct flow_dissector_key_eth_addrs *mask = - GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_ETH_ADDRS); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { + struct flow_match_eth_addrs match; + flow_rule_match_eth_addrs(rule, &match); flow->flags |= BNXT_TC_FLOW_FLAGS_ETH_ADDRS; - ether_addr_copy(flow->l2_key.dmac, key->dst); - ether_addr_copy(flow->l2_mask.dmac, mask->dst); - ether_addr_copy(flow->l2_key.smac, key->src); - ether_addr_copy(flow->l2_mask.smac, mask->src); + ether_addr_copy(flow->l2_key.dmac, match.key->dst); + ether_addr_copy(flow->l2_mask.dmac, match.mask->dst); + ether_addr_copy(flow->l2_key.smac, match.key->src); + ether_addr_copy(flow->l2_mask.smac, match.mask->src); } - if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_VLAN)) { - struct flow_dissector_key_vlan *key = - GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_VLAN); - struct flow_dissector_key_vlan *mask = - GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_VLAN); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_match_vlan match; + flow_rule_match_vlan(rule, &match); flow->l2_key.inner_vlan_tci = - cpu_to_be16(VLAN_TCI(key->vlan_id, key->vlan_priority)); + cpu_to_be16(VLAN_TCI(match.key->vlan_id, + match.key->vlan_priority)); flow->l2_mask.inner_vlan_tci = - cpu_to_be16((VLAN_TCI(mask->vlan_id, mask->vlan_priority))); + cpu_to_be16((VLAN_TCI(match.mask->vlan_id, + match.mask->vlan_priority))); flow->l2_key.inner_vlan_tpid = htons(ETH_P_8021Q); flow->l2_mask.inner_vlan_tpid = htons(0xffff); flow->l2_key.num_vlans = 1; } - if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) { - struct flow_dissector_key_ipv4_addrs *key = - GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_IPV4_ADDRS); - struct flow_dissector_key_ipv4_addrs *mask = - GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_IPV4_ADDRS); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) { + struct flow_match_ipv4_addrs match; + flow_rule_match_ipv4_addrs(rule, &match); flow->flags |= BNXT_TC_FLOW_FLAGS_IPV4_ADDRS; - flow->l3_key.ipv4.daddr.s_addr = key->dst; - flow->l3_mask.ipv4.daddr.s_addr = mask->dst; - flow->l3_key.ipv4.saddr.s_addr = key->src; - flow->l3_mask.ipv4.saddr.s_addr = mask->src; - } else if (dissector_uses_key(dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { - struct flow_dissector_key_ipv6_addrs *key = - GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_IPV6_ADDRS); - struct flow_dissector_key_ipv6_addrs *mask = - GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_IPV6_ADDRS); - + flow->l3_key.ipv4.daddr.s_addr = match.key->dst; + flow->l3_mask.ipv4.daddr.s_addr = match.mask->dst; + flow->l3_key.ipv4.saddr.s_addr = match.key->src; + flow->l3_mask.ipv4.saddr.s_addr = match.mask->src; + } else if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { + struct flow_match_ipv6_addrs match; + + flow_rule_match_ipv6_addrs(rule, &match); flow->flags |= BNXT_TC_FLOW_FLAGS_IPV6_ADDRS; - flow->l3_key.ipv6.daddr = key->dst; - flow->l3_mask.ipv6.daddr = mask->dst; - flow->l3_key.ipv6.saddr = key->src; - flow->l3_mask.ipv6.saddr = mask->src; + flow->l3_key.ipv6.daddr = match.key->dst; + flow->l3_mask.ipv6.daddr = match.mask->dst; + flow->l3_key.ipv6.saddr = match.key->src; + flow->l3_mask.ipv6.saddr = match.mask->src; } - if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_PORTS)) { - struct flow_dissector_key_ports *key = - GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_PORTS); - struct flow_dissector_key_ports *mask = - GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_PORTS); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) { + struct flow_match_ports match; + flow_rule_match_ports(rule, &match); flow->flags |= BNXT_TC_FLOW_FLAGS_PORTS; - flow->l4_key.ports.dport = key->dst; - flow->l4_mask.ports.dport = mask->dst; - flow->l4_key.ports.sport = key->src; - flow->l4_mask.ports.sport = mask->src; + flow->l4_key.ports.dport = match.key->dst; + flow->l4_mask.ports.dport = match.mask->dst; + flow->l4_key.ports.sport = match.key->src; + flow->l4_mask.ports.sport = match.mask->src; } - if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ICMP)) { - struct flow_dissector_key_icmp *key = - GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ICMP); - struct flow_dissector_key_icmp *mask = - GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_ICMP); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ICMP)) { + struct flow_match_icmp match; + flow_rule_match_icmp(rule, &match); flow->flags |= BNXT_TC_FLOW_FLAGS_ICMP; - flow->l4_key.icmp.type = key->type; - flow->l4_key.icmp.code = key->code; - flow->l4_mask.icmp.type = mask->type; - flow->l4_mask.icmp.code = mask->code; + flow->l4_key.icmp.type = match.key->type; + flow->l4_key.icmp.code = match.key->code; + flow->l4_mask.icmp.type = match.mask->type; + flow->l4_mask.icmp.code = match.mask->code; } - if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) { - struct flow_dissector_key_ipv4_addrs *key = - GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS); - struct flow_dissector_key_ipv4_addrs *mask = - GET_MASK(tc_flow_cmd, - FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) { + struct flow_match_ipv4_addrs match; + flow_rule_match_enc_ipv4_addrs(rule, &match); flow->flags |= BNXT_TC_FLOW_FLAGS_TUNL_IPV4_ADDRS; - flow->tun_key.u.ipv4.dst = key->dst; - flow->tun_mask.u.ipv4.dst = mask->dst; - flow->tun_key.u.ipv4.src = key->src; - flow->tun_mask.u.ipv4.src = mask->src; - } else if (dissector_uses_key(dissector, + flow->tun_key.u.ipv4.dst = match.key->dst; + flow->tun_mask.u.ipv4.dst = match.mask->dst; + flow->tun_key.u.ipv4.src = match.key->src; + flow->tun_mask.u.ipv4.src = match.mask->src; + } else if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS)) { return -EOPNOTSUPP; } - if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) { - struct flow_dissector_key_keyid *key = - GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_KEYID); - struct flow_dissector_key_keyid *mask = - GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_KEYID); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID)) { + struct flow_match_enc_keyid match; + flow_rule_match_enc_keyid(rule, &match); flow->flags |= BNXT_TC_FLOW_FLAGS_TUNL_ID; - flow->tun_key.tun_id = key32_to_tunnel_id(key->keyid); - flow->tun_mask.tun_id = key32_to_tunnel_id(mask->keyid); + flow->tun_key.tun_id = key32_to_tunnel_id(match.key->keyid); + flow->tun_mask.tun_id = key32_to_tunnel_id(match.mask->keyid); } - if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ENC_PORTS)) { - struct flow_dissector_key_ports *key = - GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_PORTS); - struct flow_dissector_key_ports *mask = - GET_MASK(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_PORTS); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_PORTS)) { + struct flow_match_ports match; + flow_rule_match_enc_ports(rule, &match); flow->flags |= BNXT_TC_FLOW_FLAGS_TUNL_PORTS; - flow->tun_key.tp_dst = key->dst; - flow->tun_mask.tp_dst = mask->dst; - flow->tun_key.tp_src = key->src; - flow->tun_mask.tp_src = mask->src; + flow->tun_key.tp_dst = match.key->dst; + flow->tun_mask.tp_dst = match.mask->dst; + flow->tun_key.tp_src = match.key->src; + flow->tun_mask.tp_src = match.mask->src; } - return bnxt_tc_parse_actions(bp, &flow->actions, tc_flow_cmd->exts); + return bnxt_tc_parse_actions(bp, &flow->actions, &rule->action); } static int bnxt_hwrm_cfa_flow_free(struct bnxt *bp, @@ -1422,8 +1388,8 @@ static int bnxt_tc_get_flow_stats(struct bnxt *bp, lastused = flow->lastused; spin_unlock(&flow->stats_lock); - tcf_exts_stats_update(tc_flow_cmd->exts, stats.bytes, stats.packets, - lastused); + flow_stats_update(&tc_flow_cmd->stats, stats.bytes, stats.packets, + lastused); return 0; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c index 9a25c05aa571..2bdd2da9aac7 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c @@ -237,21 +237,17 @@ static void bnxt_vf_rep_get_drvinfo(struct net_device *dev, strlcpy(info->version, DRV_MODULE_VERSION, sizeof(info->version)); } -static int bnxt_vf_rep_port_attr_get(struct net_device *dev, - struct switchdev_attr *attr) +static int bnxt_vf_rep_get_port_parent_id(struct net_device *dev, + struct netdev_phys_item_id *ppid) { struct bnxt_vf_rep *vf_rep = netdev_priv(dev); /* as only PORT_PARENT_ID is supported currently use common code * between PF and VF-rep for now. */ - return bnxt_port_attr_get(vf_rep->bp, attr); + return bnxt_get_port_parent_id(vf_rep->bp->dev, ppid); } -static const struct switchdev_ops bnxt_vf_rep_switchdev_ops = { - .switchdev_port_attr_get = bnxt_vf_rep_port_attr_get -}; - static const struct ethtool_ops bnxt_vf_rep_ethtool_ops = { .get_drvinfo = bnxt_vf_rep_get_drvinfo }; @@ -262,6 +258,7 @@ static const struct net_device_ops bnxt_vf_rep_netdev_ops = { .ndo_start_xmit = bnxt_vf_rep_xmit, .ndo_get_stats64 = bnxt_vf_rep_get_stats64, .ndo_setup_tc = bnxt_vf_rep_setup_tc, + .ndo_get_port_parent_id = bnxt_vf_rep_get_port_parent_id, .ndo_get_phys_port_name = bnxt_vf_rep_get_phys_port_name }; @@ -392,7 +389,6 @@ static void bnxt_vf_rep_netdev_init(struct bnxt *bp, struct bnxt_vf_rep *vf_rep, dev->netdev_ops = &bnxt_vf_rep_netdev_ops; dev->ethtool_ops = &bnxt_vf_rep_ethtool_ops; - SWITCHDEV_SET_OPS(dev, &bnxt_vf_rep_switchdev_ops); /* Just inherit all the featues of the parent PF as the VF-R * uses the RX/TX rings of the parent PF */ diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index aceb9b7b55bd..51880d83131a 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -525,7 +525,7 @@ static int bcmgenet_mii_pd_init(struct bcmgenet_priv *priv) .asym_pause = 0, }; - phydev = fixed_phy_register(PHY_POLL, &fphy_status, -1, NULL); + phydev = fixed_phy_register(PHY_POLL, &fphy_status, NULL); if (!phydev || IS_ERR(phydev)) { dev_err(kdev, "failed to register fixed PHY device\n"); return -ENODEV; diff --git a/drivers/net/ethernet/broadcom/sb1250-mac.c b/drivers/net/ethernet/broadcom/sb1250-mac.c index 5db9f4158e62..134ae2862efa 100644 --- a/drivers/net/ethernet/broadcom/sb1250-mac.c +++ b/drivers/net/ethernet/broadcom/sb1250-mac.c @@ -1288,7 +1288,7 @@ static void sbdma_tx_process(struct sbmac_softc *sc, struct sbmacdma *d, * for transmits, we just free buffers. */ - dev_kfree_skb_irq(sb); + dev_consume_skb_irq(sb); /* * .. and advance to the next buffer. diff --git a/drivers/net/ethernet/brocade/bna/bfa_ioc.c b/drivers/net/ethernet/brocade/bna/bfa_ioc.c index cbc9175d74c5..84741d288ffa 100644 --- a/drivers/net/ethernet/brocade/bna/bfa_ioc.c +++ b/drivers/net/ethernet/brocade/bna/bfa_ioc.c @@ -743,7 +743,7 @@ bfa_iocpf_sm_hwinit(struct bfa_iocpf *iocpf, enum iocpf_event event) case IOCPF_E_TIMEOUT: bfa_nw_ioc_hw_sem_release(ioc); - bfa_ioc_pf_failed(ioc); + bfa_ioc_pf_failed(ioc); bfa_fsm_set_state(iocpf, bfa_iocpf_sm_initfail_sync); break; diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index 3d45f4c92cf6..9bbaad9f3d63 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -643,6 +643,7 @@ #define MACB_CAPS_JUMBO 0x00000020 #define MACB_CAPS_GEM_HAS_PTP 0x00000040 #define MACB_CAPS_BD_RD_PREFETCH 0x00000080 +#define MACB_CAPS_NEEDS_RSTONUBR 0x00000100 #define MACB_CAPS_FIFO_MODE 0x10000000 #define MACB_CAPS_GIGABIT_MODE_AVAILABLE 0x20000000 #define MACB_CAPS_SG_DISABLED 0x40000000 @@ -1214,6 +1215,8 @@ struct macb { int rx_bd_rd_prefetch; int tx_bd_rd_prefetch; + + u32 rx_intr_mask; }; #ifdef CONFIG_MACB_USE_HWSTAMP diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 66cc7927061a..f2915f2fe21a 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -56,8 +56,7 @@ /* level of occupied TX descriptors under which we wake up TX process */ #define MACB_TX_WAKEUP_THRESH(bp) (3 * (bp)->tx_ring_size / 4) -#define MACB_RX_INT_FLAGS (MACB_BIT(RCOMP) | MACB_BIT(RXUBR) \ - | MACB_BIT(ISR_ROVR)) +#define MACB_RX_INT_FLAGS (MACB_BIT(RCOMP) | MACB_BIT(ISR_ROVR)) #define MACB_TX_ERR_FLAGS (MACB_BIT(ISR_TUND) \ | MACB_BIT(ISR_RLE) \ | MACB_BIT(TXERR)) @@ -1270,7 +1269,7 @@ static int macb_poll(struct napi_struct *napi, int budget) queue_writel(queue, ISR, MACB_BIT(RCOMP)); napi_reschedule(napi); } else { - queue_writel(queue, IER, MACB_RX_INT_FLAGS); + queue_writel(queue, IER, bp->rx_intr_mask); } } @@ -1288,7 +1287,7 @@ static void macb_hresp_error_task(unsigned long data) u32 ctrl; for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) { - queue_writel(queue, IDR, MACB_RX_INT_FLAGS | + queue_writel(queue, IDR, bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP)); } @@ -1318,7 +1317,7 @@ static void macb_hresp_error_task(unsigned long data) /* Enable interrupts */ queue_writel(queue, IER, - MACB_RX_INT_FLAGS | + bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP)); } @@ -1372,14 +1371,14 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id) (unsigned int)(queue - bp->queues), (unsigned long)status); - if (status & MACB_RX_INT_FLAGS) { + if (status & bp->rx_intr_mask) { /* There's no point taking any more interrupts * until we have processed the buffers. The * scheduling call may fail if the poll routine * is already scheduled, so disable interrupts * now. */ - queue_writel(queue, IDR, MACB_RX_INT_FLAGS); + queue_writel(queue, IDR, bp->rx_intr_mask); if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE) queue_writel(queue, ISR, MACB_BIT(RCOMP)); @@ -1412,8 +1411,9 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id) /* There is a hardware issue under heavy load where DMA can * stop, this causes endless "used buffer descriptor read" * interrupts but it can be cleared by re-enabling RX. See - * the at91 manual, section 41.3.1 or the Zynq manual - * section 16.7.4 for details. + * the at91rm9200 manual, section 41.3.1 or the Zynq manual + * section 16.7.4 for details. RXUBR is only enabled for + * these two versions. */ if (status & MACB_BIT(RXUBR)) { ctrl = macb_readl(bp, NCR); @@ -1734,7 +1734,7 @@ static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *ndev) if (!nskb) return -ENOMEM; - dev_kfree_skb_any(*skb); + dev_consume_skb_any(*skb); *skb = nskb; } @@ -2259,7 +2259,7 @@ static void macb_init_hw(struct macb *bp) /* Enable interrupts */ queue_writel(queue, IER, - MACB_RX_INT_FLAGS | + bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP)); } @@ -3673,9 +3673,9 @@ static netdev_tx_t at91ether_start_xmit(struct sk_buff *skb, /* Store packet information (to free when Tx completed) */ lp->skb = skb; lp->skb_length = skb->len; - lp->skb_physaddr = dma_map_single(NULL, skb->data, skb->len, - DMA_TO_DEVICE); - if (dma_mapping_error(NULL, lp->skb_physaddr)) { + lp->skb_physaddr = dma_map_single(&lp->pdev->dev, skb->data, + skb->len, DMA_TO_DEVICE); + if (dma_mapping_error(&lp->pdev->dev, lp->skb_physaddr)) { dev_kfree_skb_any(skb); dev->stats.tx_dropped++; netdev_err(dev, "%s: DMA mapping error\n", __func__); @@ -3763,9 +3763,9 @@ static irqreturn_t at91ether_interrupt(int irq, void *dev_id) dev->stats.tx_errors++; if (lp->skb) { - dev_kfree_skb_irq(lp->skb); + dev_consume_skb_irq(lp->skb); lp->skb = NULL; - dma_unmap_single(NULL, lp->skb_physaddr, + dma_unmap_single(&lp->pdev->dev, lp->skb_physaddr, lp->skb_length, DMA_TO_DEVICE); dev->stats.tx_packets++; dev->stats.tx_bytes += lp->skb_length; @@ -3907,6 +3907,7 @@ static const struct macb_config sama5d4_config = { }; static const struct macb_config emac_config = { + .caps = MACB_CAPS_NEEDS_RSTONUBR, .clk_init = at91ether_clk_init, .init = at91ether_init, }; @@ -3928,7 +3929,8 @@ static const struct macb_config zynqmp_config = { }; static const struct macb_config zynq_config = { - .caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_NO_GIGABIT_HALF, + .caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_NO_GIGABIT_HALF | + MACB_CAPS_NEEDS_RSTONUBR, .dma_burst_length = 16, .clk_init = macb_clk_init, .init = macb_init, @@ -3941,6 +3943,7 @@ static const struct of_device_id macb_dt_ids[] = { { .compatible = "cdns,np4-macb", .data = &np4_config }, { .compatible = "cdns,pc302-gem", .data = &pc302gem_config }, { .compatible = "cdns,gem", .data = &pc302gem_config }, + { .compatible = "cdns,sam9x60-macb", .data = &at91sam9260_config }, { .compatible = "atmel,sama5d2-gem", .data = &sama5d2_config }, { .compatible = "atmel,sama5d3-gem", .data = &sama5d3_config }, { .compatible = "atmel,sama5d3-macb", .data = &sama5d3macb_config }, @@ -4083,6 +4086,10 @@ static int macb_probe(struct platform_device *pdev) macb_dma_desc_get_size(bp); } + bp->rx_intr_mask = MACB_RX_INT_FLAGS; + if (bp->caps & MACB_CAPS_NEEDS_RSTONUBR) + bp->rx_intr_mask |= MACB_BIT(RXUBR); + mac = of_get_mac_address(np); if (mac) { ether_addr_copy(bp->dev->dev_addr, mac); diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig index 5f03199a3acf..05f4a3b21e29 100644 --- a/drivers/net/ethernet/cavium/Kconfig +++ b/drivers/net/ethernet/cavium/Kconfig @@ -54,7 +54,6 @@ config CAVIUM_PTP tristate "Cavium PTP coprocessor as PTP clock" depends on 64BIT && PCI imply PTP_1588_CLOCK - default y ---help--- This driver adds support for the Precision Time Protocol Clocks and Timestamping coprocessor (PTP) found on Cavium processors. diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c index 825a28e5b544..e21bf3724611 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_core.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c @@ -661,7 +661,8 @@ liquidio_push_packet(u32 octeon_id __attribute__((unused)), (((rh->r_dh.encap_on) && (rh->r_dh.csum_verified & CNNIC_TUN_CSUM_VERIFIED)) || (!(rh->r_dh.encap_on) && - (rh->r_dh.csum_verified & CNNIC_CSUM_VERIFIED)))) + ((rh->r_dh.csum_verified & CNNIC_CSUM_VERIFIED) == + CNNIC_CSUM_VERIFIED)))) /* checksum has already been verified */ skb->ip_summed = CHECKSUM_UNNECESSARY; else diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index 3d24133e5e49..e97e6754ee09 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -21,7 +21,6 @@ #include <linux/firmware.h> #include <net/vxlan.h> #include <linux/kthread.h> -#include <net/switchdev.h> #include "liquidio_common.h" #include "octeon_droq.h" #include "octeon_iq.h" @@ -3184,7 +3183,8 @@ static const struct devlink_ops liquidio_devlink_ops = { }; static int -lio_pf_switchdev_attr_get(struct net_device *dev, struct switchdev_attr *attr) +liquidio_get_port_parent_id(struct net_device *dev, + struct netdev_phys_item_id *ppid) { struct lio *lio = GET_LIO(dev); struct octeon_device *oct = lio->oct_dev; @@ -3192,24 +3192,12 @@ lio_pf_switchdev_attr_get(struct net_device *dev, struct switchdev_attr *attr) if (oct->eswitch_mode != DEVLINK_ESWITCH_MODE_SWITCHDEV) return -EOPNOTSUPP; - switch (attr->id) { - case SWITCHDEV_ATTR_ID_PORT_PARENT_ID: - attr->u.ppid.id_len = ETH_ALEN; - ether_addr_copy(attr->u.ppid.id, - (void *)&lio->linfo.hw_addr + 2); - break; - - default: - return -EOPNOTSUPP; - } + ppid->id_len = ETH_ALEN; + ether_addr_copy(ppid->id, (void *)&lio->linfo.hw_addr + 2); return 0; } -static const struct switchdev_ops lio_pf_switchdev_ops = { - .switchdev_port_attr_get = lio_pf_switchdev_attr_get, -}; - static int liquidio_get_vf_stats(struct net_device *netdev, int vfidx, struct ifla_vf_stats *vf_stats) { @@ -3259,6 +3247,7 @@ static const struct net_device_ops lionetdevops = { .ndo_set_vf_trust = liquidio_set_vf_trust, .ndo_set_vf_link_state = liquidio_set_vf_link_state, .ndo_get_vf_stats = liquidio_get_vf_stats, + .ndo_get_port_parent_id = liquidio_get_port_parent_id, }; /** \brief Entry point for the liquidio module @@ -3534,7 +3523,6 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) * netdev tasks. */ netdev->netdev_ops = &lionetdevops; - SWITCHDEV_SET_OPS(netdev, &lio_pf_switchdev_ops); retval = netif_set_real_num_rx_queues(netdev, num_oqueues); if (retval) { diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c index de61060721c4..f3f2e71431ac 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c @@ -25,7 +25,6 @@ #include "octeon_nic.h" #include "octeon_main.h" #include "octeon_network.h" -#include <net/switchdev.h> #include "lio_vf_rep.h" static int lio_vf_rep_open(struct net_device *ndev); @@ -38,6 +37,8 @@ static int lio_vf_rep_phys_port_name(struct net_device *dev, static void lio_vf_rep_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats64); static int lio_vf_rep_change_mtu(struct net_device *ndev, int new_mtu); +static int lio_vf_get_port_parent_id(struct net_device *dev, + struct netdev_phys_item_id *ppid); static const struct net_device_ops lio_vf_rep_ndev_ops = { .ndo_open = lio_vf_rep_open, @@ -47,6 +48,7 @@ static const struct net_device_ops lio_vf_rep_ndev_ops = { .ndo_get_phys_port_name = lio_vf_rep_phys_port_name, .ndo_get_stats64 = lio_vf_rep_get_stats64, .ndo_change_mtu = lio_vf_rep_change_mtu, + .ndo_get_port_parent_id = lio_vf_get_port_parent_id, }; static int @@ -443,31 +445,19 @@ xmit_failed: return NETDEV_TX_OK; } -static int -lio_vf_rep_attr_get(struct net_device *dev, struct switchdev_attr *attr) +static int lio_vf_get_port_parent_id(struct net_device *dev, + struct netdev_phys_item_id *ppid) { struct lio_vf_rep_desc *vf_rep = netdev_priv(dev); struct net_device *parent_ndev = vf_rep->parent_ndev; struct lio *lio = GET_LIO(parent_ndev); - switch (attr->id) { - case SWITCHDEV_ATTR_ID_PORT_PARENT_ID: - attr->u.ppid.id_len = ETH_ALEN; - ether_addr_copy(attr->u.ppid.id, - (void *)&lio->linfo.hw_addr + 2); - break; - - default: - return -EOPNOTSUPP; - } + ppid->id_len = ETH_ALEN; + ether_addr_copy(ppid->id, (void *)&lio->linfo.hw_addr + 2); return 0; } -static const struct switchdev_ops lio_vf_rep_switchdev_ops = { - .switchdev_port_attr_get = lio_vf_rep_attr_get, -}; - static void lio_vf_rep_fetch_stats(struct work_struct *work) { @@ -524,7 +514,6 @@ lio_vf_rep_create(struct octeon_device *oct) ndev->min_mtu = LIO_MIN_MTU_SIZE; ndev->max_mtu = LIO_MAX_MTU_SIZE; ndev->netdev_ops = &lio_vf_rep_ndev_ops; - SWITCHDEV_SET_OPS(ndev, &lio_vf_rep_switchdev_ops); vf_rep = netdev_priv(ndev); memset(vf_rep, 0, sizeof(*vf_rep)); diff --git a/drivers/net/ethernet/chelsio/cxgb/sge.c b/drivers/net/ethernet/chelsio/cxgb/sge.c index 30de26ef3da4..47b5c8e2104b 100644 --- a/drivers/net/ethernet/chelsio/cxgb/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb/sge.c @@ -585,8 +585,7 @@ static int alloc_rx_resources(struct sge *sge, struct sge_params *p) sizeof(struct cpl_rx_data) + sge->freelQ[!sge->jumbo_fl].dma_offset; - size = (16 * 1024) - - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + size = (16 * 1024) - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); sge->freelQ[sge->jumbo_fl].rx_buffer_size = size; diff --git a/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c b/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c index 5701272aa7f7..ce28820c57c9 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c +++ b/drivers/net/ethernet/chelsio/cxgb4/clip_tbl.c @@ -289,8 +289,7 @@ struct clip_tbl *t4_init_clip_tbl(unsigned int clipt_start, if (clipt_size < CLIPT_MIN_HASH_BUCKETS) return NULL; - ctbl = kvzalloc(sizeof(*ctbl) + - clipt_size*sizeof(struct list_head), GFP_KERNEL); + ctbl = kvzalloc(struct_size(ctbl, hash_list, clipt_size), GFP_KERNEL); if (!ctbl) return NULL; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index 2d1ca920601e..b7b0eb104430 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -568,7 +568,7 @@ struct sge_rspq; struct port_info { struct adapter *adapter; u16 viid; - s16 xact_addr_filt; /* index of exact MAC address filter */ + int xact_addr_filt; /* index of exact MAC address filter */ u16 rss_size; /* size of VI's RSS table slice */ s8 mdio_addr; enum fw_port_type port_type; @@ -617,6 +617,7 @@ enum { /* adapter flags */ FW_OFLD_CONN = (1 << 9), ROOT_NO_RELAXED_ORDERING = (1 << 10), SHUTTING_DOWN = (1 << 11), + SGE_DBQ_TIMER = (1 << 12), }; enum { @@ -756,6 +757,8 @@ struct sge_eth_txq { /* state for an SGE Ethernet Tx queue */ #ifdef CONFIG_CHELSIO_T4_DCB u8 dcb_prio; /* DCB Priority bound to queue */ #endif + u8 dbqt; /* SGE Doorbell Queue Timer in use */ + unsigned int dbqtimerix; /* SGE Doorbell Queue Timer Index */ unsigned long tso; /* # of TSO requests */ unsigned long tx_cso; /* # of Tx checksum offloads */ unsigned long vlan_ins; /* # of Tx VLAN insertions */ @@ -816,6 +819,8 @@ struct sge { u16 nqs_per_uld; /* # of Rx queues per ULD */ u16 timer_val[SGE_NTIMERS]; u8 counter_val[SGE_NCOUNTERS]; + u16 dbqtimer_tick; + u16 dbqtimer_val[SGE_NDBQTIMERS]; u32 fl_pg_order; /* large page allocation size */ u32 stat_len; /* length of status page at ring end */ u32 pktshift; /* padding between CPL & packet data */ @@ -860,6 +865,7 @@ struct doorbell_stats { struct hash_mac_addr { struct list_head list; u8 addr[ETH_ALEN]; + unsigned int iface_mac; }; struct uld_msix_bmap { @@ -1401,7 +1407,7 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq, rspq_flush_handler_t flush_handler, int cong); int t4_sge_alloc_eth_txq(struct adapter *adap, struct sge_eth_txq *txq, struct net_device *dev, struct netdev_queue *netdevq, - unsigned int iqid); + unsigned int iqid, u8 dbqt); int t4_sge_alloc_ctrl_txq(struct adapter *adap, struct sge_ctrl_txq *txq, struct net_device *dev, unsigned int iqid, unsigned int cmplqid); @@ -1414,6 +1420,8 @@ irqreturn_t t4_sge_intr_msix(int irq, void *cookie); int t4_sge_init(struct adapter *adap); void t4_sge_start(struct adapter *adap); void t4_sge_stop(struct adapter *adap); +int t4_sge_eth_txq_egress_update(struct adapter *adap, struct sge_eth_txq *q, + int maxreclaim); void cxgb4_set_ethtool_ops(struct net_device *netdev); int cxgb4_write_rss(const struct port_info *pi, const u16 *queues); enum cpl_tx_tnl_lso_type cxgb_encap_offload_supported(struct sk_buff *skb); @@ -1820,6 +1828,8 @@ int t4_ctrl_eq_free(struct adapter *adap, unsigned int mbox, unsigned int pf, int t4_ofld_eq_free(struct adapter *adap, unsigned int mbox, unsigned int pf, unsigned int vf, unsigned int eqid); int t4_sge_ctxt_flush(struct adapter *adap, unsigned int mbox, int ctxt_type); +int t4_read_sge_dbqtimers(struct adapter *adap, unsigned int ndbqtimers, + u16 *dbqtimers); void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl); int t4_update_port_info(struct port_info *pi); int t4_get_link_params(struct port_info *pi, unsigned int *link_okp, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c index 796043544fc3..65b8dc706c1d 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c @@ -932,11 +932,190 @@ static int get_adaptive_rx_setting(struct net_device *dev) return q->rspq.adaptive_rx; } -static int set_coalesce(struct net_device *dev, struct ethtool_coalesce *c) +/* Return the current global Adapter SGE Doorbell Queue Timer Tick for all + * Ethernet TX Queues. + */ +static int get_dbqtimer_tick(struct net_device *dev) +{ + struct port_info *pi = netdev_priv(dev); + struct adapter *adap = pi->adapter; + + if (!(adap->flags & SGE_DBQ_TIMER)) + return 0; + + return adap->sge.dbqtimer_tick; +} + +/* Return the SGE Doorbell Queue Timer Value for the Ethernet TX Queues + * associated with a Network Device. + */ +static int get_dbqtimer(struct net_device *dev) +{ + struct port_info *pi = netdev_priv(dev); + struct adapter *adap = pi->adapter; + struct sge_eth_txq *txq; + + txq = &adap->sge.ethtxq[pi->first_qset]; + + if (!(adap->flags & SGE_DBQ_TIMER)) + return 0; + + /* all of the TX Queues use the same Timer Index */ + return adap->sge.dbqtimer_val[txq->dbqtimerix]; +} + +/* Set the global Adapter SGE Doorbell Queue Timer Tick for all Ethernet TX + * Queues. This is the fundamental "Tick" that sets the scale of values which + * can be used. Individual Ethernet TX Queues index into a relatively small + * array of Tick Multipliers. Changing the base Tick will thus change all of + * the resulting Timer Values associated with those multipliers for all + * Ethernet TX Queues. + */ +static int set_dbqtimer_tick(struct net_device *dev, int usecs) +{ + struct port_info *pi = netdev_priv(dev); + struct adapter *adap = pi->adapter; + struct sge *s = &adap->sge; + u32 param, val; + int ret; + + if (!(adap->flags & SGE_DBQ_TIMER)) + return 0; + + /* return early if it's the same Timer Tick we're already using */ + if (s->dbqtimer_tick == usecs) + return 0; + + /* attempt to set the new Timer Tick value */ + param = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) | + FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_DBQ_TIMERTICK)); + val = usecs; + ret = t4_set_params(adap, adap->mbox, adap->pf, 0, 1, ¶m, &val); + if (ret) + return ret; + s->dbqtimer_tick = usecs; + + /* if successful, reread resulting dependent Timer values */ + ret = t4_read_sge_dbqtimers(adap, ARRAY_SIZE(s->dbqtimer_val), + s->dbqtimer_val); + return ret; +} + +/* Set the SGE Doorbell Queue Timer Value for the Ethernet TX Queues + * associated with a Network Device. There is a relatively small array of + * possible Timer Values so we need to pick the closest value available. + */ +static int set_dbqtimer(struct net_device *dev, int usecs) +{ + int qix, timerix, min_timerix, delta, min_delta; + struct port_info *pi = netdev_priv(dev); + struct adapter *adap = pi->adapter; + struct sge *s = &adap->sge; + struct sge_eth_txq *txq; + u32 param, val; + int ret; + + if (!(adap->flags & SGE_DBQ_TIMER)) + return 0; + + /* Find the SGE Doorbell Timer Value that's closest to the requested + * value. + */ + min_delta = INT_MAX; + min_timerix = 0; + for (timerix = 0; timerix < ARRAY_SIZE(s->dbqtimer_val); timerix++) { + delta = s->dbqtimer_val[timerix] - usecs; + if (delta < 0) + delta = -delta; + if (delta < min_delta) { + min_delta = delta; + min_timerix = timerix; + } + } + + /* Return early if it's the same Timer Index we're already using. + * We use the same Timer Index for all of the TX Queues for an + * interface so it's only necessary to check the first one. + */ + txq = &s->ethtxq[pi->first_qset]; + if (txq->dbqtimerix == min_timerix) + return 0; + + for (qix = 0; qix < pi->nqsets; qix++, txq++) { + if (adap->flags & FULL_INIT_DONE) { + param = + (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DMAQ) | + FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DMAQ_EQ_TIMERIX) | + FW_PARAMS_PARAM_YZ_V(txq->q.cntxt_id)); + val = min_timerix; + ret = t4_set_params(adap, adap->mbox, adap->pf, 0, + 1, ¶m, &val); + if (ret) + return ret; + } + txq->dbqtimerix = min_timerix; + } + return 0; +} + +/* Set the global Adapter SGE Doorbell Queue Timer Tick for all Ethernet TX + * Queues and the Timer Value for the Ethernet TX Queues associated with a + * Network Device. Since changing the global Tick changes all of the + * available Timer Values, we need to do this first before selecting the + * resulting closest Timer Value. Moreover, since the Tick is global, + * changing it affects the Timer Values for all Network Devices on the + * adapter. So, before changing the Tick, we grab all of the current Timer + * Values for other Network Devices on this Adapter and then attempt to select + * new Timer Values which are close to the old values ... + */ +static int set_dbqtimer_tickval(struct net_device *dev, + int tick_usecs, int timer_usecs) +{ + struct port_info *pi = netdev_priv(dev); + struct adapter *adap = pi->adapter; + int timer[MAX_NPORTS]; + unsigned int port; + int ret; + + /* Grab the other adapter Network Interface current timers and fill in + * the new one for this Network Interface. + */ + for_each_port(adap, port) + if (port == pi->port_id) + timer[port] = timer_usecs; + else + timer[port] = get_dbqtimer(adap->port[port]); + + /* Change the global Tick first ... */ + ret = set_dbqtimer_tick(dev, tick_usecs); + if (ret) + return ret; + + /* ... and then set all of the Network Interface Timer Values ... */ + for_each_port(adap, port) { + ret = set_dbqtimer(adap->port[port], timer[port]); + if (ret) + return ret; + } + + return 0; +} + +static int set_coalesce(struct net_device *dev, + struct ethtool_coalesce *coalesce) { - set_adaptive_rx_setting(dev, c->use_adaptive_rx_coalesce); - return set_rx_intr_params(dev, c->rx_coalesce_usecs, - c->rx_max_coalesced_frames); + int ret; + + set_adaptive_rx_setting(dev, coalesce->use_adaptive_rx_coalesce); + + ret = set_rx_intr_params(dev, coalesce->rx_coalesce_usecs, + coalesce->rx_max_coalesced_frames); + if (ret) + return ret; + + return set_dbqtimer_tickval(dev, + coalesce->tx_coalesce_usecs_irq, + coalesce->tx_coalesce_usecs); } static int get_coalesce(struct net_device *dev, struct ethtool_coalesce *c) @@ -949,6 +1128,8 @@ static int get_coalesce(struct net_device *dev, struct ethtool_coalesce *c) c->rx_max_coalesced_frames = (rq->intr_params & QINTR_CNT_EN_F) ? adap->sge.counter_val[rq->pktcnt_idx] : 0; c->use_adaptive_rx_coalesce = get_adaptive_rx_setting(dev); + c->tx_coalesce_usecs_irq = get_dbqtimer_tick(dev); + c->tx_coalesce_usecs = get_dbqtimer(dev); return 0; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 73fc2479b4f4..bcbac247a73d 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -433,6 +433,60 @@ static int set_rxmode(struct net_device *dev, int mtu, bool sleep_ok) } /** + * cxgb4_change_mac - Update match filter for a MAC address. + * @pi: the port_info + * @viid: the VI id + * @tcam_idx: TCAM index of existing filter for old value of MAC address, + * or -1 + * @addr: the new MAC address value + * @persist: whether a new MAC allocation should be persistent + * @add_smt: if true also add the address to the HW SMT + * + * Modifies an MPS filter and sets it to the new MAC address if + * @tcam_idx >= 0, or adds the MAC address to a new filter if + * @tcam_idx < 0. In the latter case the address is added persistently + * if @persist is %true. + * Addresses are programmed to hash region, if tcam runs out of entries. + * + */ +static int cxgb4_change_mac(struct port_info *pi, unsigned int viid, + int *tcam_idx, const u8 *addr, bool persist, + u8 *smt_idx) +{ + struct adapter *adapter = pi->adapter; + struct hash_mac_addr *entry, *new_entry; + int ret; + + ret = t4_change_mac(adapter, adapter->mbox, viid, + *tcam_idx, addr, persist, smt_idx); + /* We ran out of TCAM entries. try programming hash region. */ + if (ret == -ENOMEM) { + /* If the MAC address to be updated is in the hash addr + * list, update it from the list + */ + list_for_each_entry(entry, &adapter->mac_hlist, list) { + if (entry->iface_mac) { + ether_addr_copy(entry->addr, addr); + goto set_hash; + } + } + new_entry = kzalloc(sizeof(*new_entry), GFP_KERNEL); + if (!new_entry) + return -ENOMEM; + ether_addr_copy(new_entry->addr, addr); + new_entry->iface_mac = true; + list_add_tail(&new_entry->list, &adapter->mac_hlist); +set_hash: + ret = cxgb4_set_addr_hash(pi); + } else if (ret >= 0) { + *tcam_idx = ret; + ret = 0; + } + + return ret; +} + +/* * link_start - enable a port * @dev: the port to enable * @@ -450,15 +504,9 @@ static int link_start(struct net_device *dev) */ ret = t4_set_rxmode(pi->adapter, mb, pi->viid, dev->mtu, -1, -1, -1, !!(dev->features & NETIF_F_HW_VLAN_CTAG_RX), true); - if (ret == 0) { - ret = t4_change_mac(pi->adapter, mb, pi->viid, - pi->xact_addr_filt, dev->dev_addr, true, - &pi->smt_idx); - if (ret >= 0) { - pi->xact_addr_filt = ret; - ret = 0; - } - } + if (ret == 0) + ret = cxgb4_change_mac(pi, pi->viid, &pi->xact_addr_filt, + dev->dev_addr, true, &pi->smt_idx); if (ret == 0) ret = t4_link_l1cfg(pi->adapter, mb, pi->tx_chan, &pi->link_cfg); @@ -527,7 +575,7 @@ static int fwevtq_handler(struct sge_rspq *q, const __be64 *rsp, struct sge_eth_txq *eq; eq = container_of(txq, struct sge_eth_txq, q); - netif_tx_wake_queue(eq->txq); + t4_sge_eth_txq_egress_update(q->adap, eq, -1); } else { struct sge_uld_txq *oq; @@ -885,10 +933,13 @@ static int setup_sge_queues(struct adapter *adap) q->rspq.idx = j; memset(&q->stats, 0, sizeof(q->stats)); } - for (j = 0; j < pi->nqsets; j++, t++) { + + q = &s->ethrxq[pi->first_qset]; + for (j = 0; j < pi->nqsets; j++, t++, q++) { err = t4_sge_alloc_eth_txq(adap, t, dev, netdev_get_tx_queue(dev, j), - s->fw_evtq.cntxt_id); + q->rspq.cntxt_id, + !!(adap->flags & SGE_DBQ_TIMER)); if (err) goto freeout; } @@ -910,7 +961,7 @@ static int setup_sge_queues(struct adapter *adap) if (!is_t4(adap->params.chip)) { err = t4_sge_alloc_eth_txq(adap, &s->ptptxq, adap->port[0], netdev_get_tx_queue(adap->port[0], 0) - , s->fw_evtq.cntxt_id); + , s->fw_evtq.cntxt_id, false); if (err) goto freeout; } @@ -2839,9 +2890,8 @@ static int cxgb_set_mac_addr(struct net_device *dev, void *p) if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; - ret = t4_change_mac(pi->adapter, pi->adapter->pf, pi->viid, - pi->xact_addr_filt, addr->sa_data, true, - &pi->smt_idx); + ret = cxgb4_change_mac(pi, pi->viid, &pi->xact_addr_filt, + addr->sa_data, true, &pi->smt_idx); if (ret < 0) return ret; @@ -4278,6 +4328,24 @@ static int adap_init0(struct adapter *adap) if (ret < 0) goto bye; + /* Grab the SGE Doorbell Queue Timer values. If successful, that + * indicates that the Firmware and Hardware support this. + */ + params[0] = (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) | + FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_DBQ_TIMERTICK)); + ret = t4_query_params(adap, adap->mbox, adap->pf, 0, + 1, params, val); + + if (!ret) { + adap->sge.dbqtimer_tick = val[0]; + ret = t4_read_sge_dbqtimers(adap, + ARRAY_SIZE(adap->sge.dbqtimer_val), + adap->sge.dbqtimer_val); + } + + if (!ret) + adap->flags |= SGE_DBQ_TIMER; + if (is_bypass_device(adap->pdev->device)) adap->params.bypass = 1; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c index c116f96956fe..82a8d1970060 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c @@ -83,28 +83,23 @@ static void cxgb4_process_flow_match(struct net_device *dev, struct tc_cls_flower_offload *cls, struct ch_filter_specification *fs) { + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(cls); u16 addr_type = 0; - if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_CONTROL)) { - struct flow_dissector_key_control *key = - skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_CONTROL, - cls->key); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) { + struct flow_match_control match; - addr_type = key->addr_type; + flow_rule_match_control(rule, &match); + addr_type = match.key->addr_type; } - if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_BASIC)) { - struct flow_dissector_key_basic *key = - skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_BASIC, - cls->key); - struct flow_dissector_key_basic *mask = - skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_BASIC, - cls->mask); - u16 ethtype_key = ntohs(key->n_proto); - u16 ethtype_mask = ntohs(mask->n_proto); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_match_basic match; + u16 ethtype_key, ethtype_mask; + + flow_rule_match_basic(rule, &match); + ethtype_key = ntohs(match.key->n_proto); + ethtype_mask = ntohs(match.mask->n_proto); if (ethtype_key == ETH_P_ALL) { ethtype_key = 0; @@ -116,115 +111,89 @@ static void cxgb4_process_flow_match(struct net_device *dev, fs->val.ethtype = ethtype_key; fs->mask.ethtype = ethtype_mask; - fs->val.proto = key->ip_proto; - fs->mask.proto = mask->ip_proto; + fs->val.proto = match.key->ip_proto; + fs->mask.proto = match.mask->ip_proto; } if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { - struct flow_dissector_key_ipv4_addrs *key = - skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS, - cls->key); - struct flow_dissector_key_ipv4_addrs *mask = - skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS, - cls->mask); + struct flow_match_ipv4_addrs match; + + flow_rule_match_ipv4_addrs(rule, &match); fs->type = 0; - memcpy(&fs->val.lip[0], &key->dst, sizeof(key->dst)); - memcpy(&fs->val.fip[0], &key->src, sizeof(key->src)); - memcpy(&fs->mask.lip[0], &mask->dst, sizeof(mask->dst)); - memcpy(&fs->mask.fip[0], &mask->src, sizeof(mask->src)); + memcpy(&fs->val.lip[0], &match.key->dst, sizeof(match.key->dst)); + memcpy(&fs->val.fip[0], &match.key->src, sizeof(match.key->src)); + memcpy(&fs->mask.lip[0], &match.mask->dst, sizeof(match.mask->dst)); + memcpy(&fs->mask.fip[0], &match.mask->src, sizeof(match.mask->src)); /* also initialize nat_lip/fip to same values */ - memcpy(&fs->nat_lip[0], &key->dst, sizeof(key->dst)); - memcpy(&fs->nat_fip[0], &key->src, sizeof(key->src)); - + memcpy(&fs->nat_lip[0], &match.key->dst, sizeof(match.key->dst)); + memcpy(&fs->nat_fip[0], &match.key->src, sizeof(match.key->src)); } if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { - struct flow_dissector_key_ipv6_addrs *key = - skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS, - cls->key); - struct flow_dissector_key_ipv6_addrs *mask = - skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS, - cls->mask); + struct flow_match_ipv6_addrs match; + flow_rule_match_ipv6_addrs(rule, &match); fs->type = 1; - memcpy(&fs->val.lip[0], key->dst.s6_addr, sizeof(key->dst)); - memcpy(&fs->val.fip[0], key->src.s6_addr, sizeof(key->src)); - memcpy(&fs->mask.lip[0], mask->dst.s6_addr, sizeof(mask->dst)); - memcpy(&fs->mask.fip[0], mask->src.s6_addr, sizeof(mask->src)); + memcpy(&fs->val.lip[0], match.key->dst.s6_addr, + sizeof(match.key->dst)); + memcpy(&fs->val.fip[0], match.key->src.s6_addr, + sizeof(match.key->src)); + memcpy(&fs->mask.lip[0], match.mask->dst.s6_addr, + sizeof(match.mask->dst)); + memcpy(&fs->mask.fip[0], match.mask->src.s6_addr, + sizeof(match.mask->src)); /* also initialize nat_lip/fip to same values */ - memcpy(&fs->nat_lip[0], key->dst.s6_addr, sizeof(key->dst)); - memcpy(&fs->nat_fip[0], key->src.s6_addr, sizeof(key->src)); + memcpy(&fs->nat_lip[0], match.key->dst.s6_addr, + sizeof(match.key->dst)); + memcpy(&fs->nat_fip[0], match.key->src.s6_addr, + sizeof(match.key->src)); } - if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_PORTS)) { - struct flow_dissector_key_ports *key, *mask; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) { + struct flow_match_ports match; - key = skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_PORTS, - cls->key); - mask = skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_PORTS, - cls->mask); - fs->val.lport = cpu_to_be16(key->dst); - fs->mask.lport = cpu_to_be16(mask->dst); - fs->val.fport = cpu_to_be16(key->src); - fs->mask.fport = cpu_to_be16(mask->src); + flow_rule_match_ports(rule, &match); + fs->val.lport = cpu_to_be16(match.key->dst); + fs->mask.lport = cpu_to_be16(match.mask->dst); + fs->val.fport = cpu_to_be16(match.key->src); + fs->mask.fport = cpu_to_be16(match.mask->src); /* also initialize nat_lport/fport to same values */ - fs->nat_lport = cpu_to_be16(key->dst); - fs->nat_fport = cpu_to_be16(key->src); + fs->nat_lport = cpu_to_be16(match.key->dst); + fs->nat_fport = cpu_to_be16(match.key->src); } - if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_IP)) { - struct flow_dissector_key_ip *key, *mask; - - key = skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_IP, - cls->key); - mask = skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_IP, - cls->mask); - fs->val.tos = key->tos; - fs->mask.tos = mask->tos; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IP)) { + struct flow_match_ip match; + + flow_rule_match_ip(rule, &match); + fs->val.tos = match.key->tos; + fs->mask.tos = match.mask->tos; } - if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) { - struct flow_dissector_key_keyid *key, *mask; - - key = skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_ENC_KEYID, - cls->key); - mask = skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_ENC_KEYID, - cls->mask); - fs->val.vni = be32_to_cpu(key->keyid); - fs->mask.vni = be32_to_cpu(mask->keyid); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID)) { + struct flow_match_enc_keyid match; + + flow_rule_match_enc_keyid(rule, &match); + fs->val.vni = be32_to_cpu(match.key->keyid); + fs->mask.vni = be32_to_cpu(match.mask->keyid); if (fs->mask.vni) { fs->val.encap_vld = 1; fs->mask.encap_vld = 1; } } - if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_VLAN)) { - struct flow_dissector_key_vlan *key, *mask; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_match_vlan match; u16 vlan_tci, vlan_tci_mask; - key = skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_VLAN, - cls->key); - mask = skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_VLAN, - cls->mask); - vlan_tci = key->vlan_id | (key->vlan_priority << - VLAN_PRIO_SHIFT); - vlan_tci_mask = mask->vlan_id | (mask->vlan_priority << - VLAN_PRIO_SHIFT); + flow_rule_match_vlan(rule, &match); + vlan_tci = match.key->vlan_id | (match.key->vlan_priority << + VLAN_PRIO_SHIFT); + vlan_tci_mask = match.mask->vlan_id | (match.mask->vlan_priority << + VLAN_PRIO_SHIFT); fs->val.ivlan = vlan_tci; fs->mask.ivlan = vlan_tci_mask; @@ -255,10 +224,12 @@ static void cxgb4_process_flow_match(struct net_device *dev, static int cxgb4_validate_flow_match(struct net_device *dev, struct tc_cls_flower_offload *cls) { + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(cls); + struct flow_dissector *dissector = rule->match.dissector; u16 ethtype_mask = 0; u16 ethtype_key = 0; - if (cls->dissector->used_keys & + if (dissector->used_keys & ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | BIT(FLOW_DISSECTOR_KEY_BASIC) | BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | @@ -268,36 +239,29 @@ static int cxgb4_validate_flow_match(struct net_device *dev, BIT(FLOW_DISSECTOR_KEY_VLAN) | BIT(FLOW_DISSECTOR_KEY_IP))) { netdev_warn(dev, "Unsupported key used: 0x%x\n", - cls->dissector->used_keys); + dissector->used_keys); return -EOPNOTSUPP; } - if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_BASIC)) { - struct flow_dissector_key_basic *key = - skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_BASIC, - cls->key); - struct flow_dissector_key_basic *mask = - skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_BASIC, - cls->mask); - ethtype_key = ntohs(key->n_proto); - ethtype_mask = ntohs(mask->n_proto); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_match_basic match; + + flow_rule_match_basic(rule, &match); + ethtype_key = ntohs(match.key->n_proto); + ethtype_mask = ntohs(match.mask->n_proto); } - if (dissector_uses_key(cls->dissector, FLOW_DISSECTOR_KEY_IP)) { + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IP)) { u16 eth_ip_type = ethtype_key & ethtype_mask; - struct flow_dissector_key_ip *mask; + struct flow_match_ip match; if (eth_ip_type != ETH_P_IP && eth_ip_type != ETH_P_IPV6) { netdev_err(dev, "IP Key supported only with IPv4/v6"); return -EINVAL; } - mask = skb_flow_dissector_target(cls->dissector, - FLOW_DISSECTOR_KEY_IP, - cls->mask); - if (mask->ttl) { + flow_rule_match_ip(rule, &match); + if (match.mask->ttl) { netdev_warn(dev, "ttl match unsupported for offload"); return -EOPNOTSUPP; } @@ -328,7 +292,7 @@ static void process_pedit_field(struct ch_filter_specification *fs, u32 val, u32 mask, u32 offset, u8 htype) { switch (htype) { - case TCA_PEDIT_KEY_EX_HDR_TYPE_ETH: + case FLOW_ACT_MANGLE_HDR_TYPE_ETH: switch (offset) { case PEDIT_ETH_DMAC_31_0: fs->newdmac = 1; @@ -346,7 +310,7 @@ static void process_pedit_field(struct ch_filter_specification *fs, u32 val, offload_pedit(fs, val, mask, ETH_SMAC_47_16); } break; - case TCA_PEDIT_KEY_EX_HDR_TYPE_IP4: + case FLOW_ACT_MANGLE_HDR_TYPE_IP4: switch (offset) { case PEDIT_IP4_SRC: offload_pedit(fs, val, mask, IP4_SRC); @@ -356,7 +320,7 @@ static void process_pedit_field(struct ch_filter_specification *fs, u32 val, } fs->nat_mode = NAT_MODE_ALL; break; - case TCA_PEDIT_KEY_EX_HDR_TYPE_IP6: + case FLOW_ACT_MANGLE_HDR_TYPE_IP6: switch (offset) { case PEDIT_IP6_SRC_31_0: offload_pedit(fs, val, mask, IP6_SRC_31_0); @@ -384,7 +348,7 @@ static void process_pedit_field(struct ch_filter_specification *fs, u32 val, } fs->nat_mode = NAT_MODE_ALL; break; - case TCA_PEDIT_KEY_EX_HDR_TYPE_TCP: + case FLOW_ACT_MANGLE_HDR_TYPE_TCP: switch (offset) { case PEDIT_TCP_SPORT_DPORT: if (~mask & PEDIT_TCP_UDP_SPORT_MASK) @@ -397,7 +361,7 @@ static void process_pedit_field(struct ch_filter_specification *fs, u32 val, } fs->nat_mode = NAT_MODE_ALL; break; - case TCA_PEDIT_KEY_EX_HDR_TYPE_UDP: + case FLOW_ACT_MANGLE_HDR_TYPE_UDP: switch (offset) { case PEDIT_UDP_SPORT_DPORT: if (~mask & PEDIT_TCP_UDP_SPORT_MASK) @@ -416,56 +380,63 @@ static void cxgb4_process_flow_actions(struct net_device *in, struct tc_cls_flower_offload *cls, struct ch_filter_specification *fs) { - const struct tc_action *a; + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(cls); + struct flow_action_entry *act; int i; - tcf_exts_for_each_action(i, a, cls->exts) { - if (is_tcf_gact_ok(a)) { + flow_action_for_each(i, act, &rule->action) { + switch (act->id) { + case FLOW_ACTION_ACCEPT: fs->action = FILTER_PASS; - } else if (is_tcf_gact_shot(a)) { + break; + case FLOW_ACTION_DROP: fs->action = FILTER_DROP; - } else if (is_tcf_mirred_egress_redirect(a)) { - struct net_device *out = tcf_mirred_dev(a); + break; + case FLOW_ACTION_REDIRECT: { + struct net_device *out = act->dev; struct port_info *pi = netdev_priv(out); fs->action = FILTER_SWITCH; fs->eport = pi->port_id; - } else if (is_tcf_vlan(a)) { - u32 vlan_action = tcf_vlan_action(a); - u8 prio = tcf_vlan_push_prio(a); - u16 vid = tcf_vlan_push_vid(a); + } + break; + case FLOW_ACTION_VLAN_POP: + case FLOW_ACTION_VLAN_PUSH: + case FLOW_ACTION_VLAN_MANGLE: { + u8 prio = act->vlan.prio; + u16 vid = act->vlan.vid; u16 vlan_tci = (prio << VLAN_PRIO_SHIFT) | vid; - - switch (vlan_action) { - case TCA_VLAN_ACT_POP: + switch (act->id) { + case FLOW_ACTION_VLAN_POP: fs->newvlan |= VLAN_REMOVE; break; - case TCA_VLAN_ACT_PUSH: + case FLOW_ACTION_VLAN_PUSH: fs->newvlan |= VLAN_INSERT; fs->vlan = vlan_tci; break; - case TCA_VLAN_ACT_MODIFY: + case FLOW_ACTION_VLAN_MANGLE: fs->newvlan |= VLAN_REWRITE; fs->vlan = vlan_tci; break; default: break; } - } else if (is_tcf_pedit(a)) { + } + break; + case FLOW_ACTION_MANGLE: { u32 mask, val, offset; - int nkeys, i; u8 htype; - nkeys = tcf_pedit_nkeys(a); - for (i = 0; i < nkeys; i++) { - htype = tcf_pedit_htype(a, i); - mask = tcf_pedit_mask(a, i); - val = tcf_pedit_val(a, i); - offset = tcf_pedit_offset(a, i); + htype = act->mangle.htype; + mask = act->mangle.mask; + val = act->mangle.val; + offset = act->mangle.offset; - process_pedit_field(fs, val, mask, offset, - htype); + process_pedit_field(fs, val, mask, offset, htype); } + break; + default: + break; } } } @@ -484,101 +455,89 @@ static bool valid_l4_mask(u32 mask) } static bool valid_pedit_action(struct net_device *dev, - const struct tc_action *a) + const struct flow_action_entry *act) { u32 mask, offset; - u8 cmd, htype; - int nkeys, i; - - nkeys = tcf_pedit_nkeys(a); - for (i = 0; i < nkeys; i++) { - htype = tcf_pedit_htype(a, i); - cmd = tcf_pedit_cmd(a, i); - mask = tcf_pedit_mask(a, i); - offset = tcf_pedit_offset(a, i); - - if (cmd != TCA_PEDIT_KEY_EX_CMD_SET) { - netdev_err(dev, "%s: Unsupported pedit cmd\n", + u8 htype; + + htype = act->mangle.htype; + mask = act->mangle.mask; + offset = act->mangle.offset; + + switch (htype) { + case FLOW_ACT_MANGLE_HDR_TYPE_ETH: + switch (offset) { + case PEDIT_ETH_DMAC_31_0: + case PEDIT_ETH_DMAC_47_32_SMAC_15_0: + case PEDIT_ETH_SMAC_47_16: + break; + default: + netdev_err(dev, "%s: Unsupported pedit field\n", __func__); return false; } - - switch (htype) { - case TCA_PEDIT_KEY_EX_HDR_TYPE_ETH: - switch (offset) { - case PEDIT_ETH_DMAC_31_0: - case PEDIT_ETH_DMAC_47_32_SMAC_15_0: - case PEDIT_ETH_SMAC_47_16: - break; - default: - netdev_err(dev, "%s: Unsupported pedit field\n", - __func__); - return false; - } - break; - case TCA_PEDIT_KEY_EX_HDR_TYPE_IP4: - switch (offset) { - case PEDIT_IP4_SRC: - case PEDIT_IP4_DST: - break; - default: - netdev_err(dev, "%s: Unsupported pedit field\n", - __func__); - return false; - } + break; + case FLOW_ACT_MANGLE_HDR_TYPE_IP4: + switch (offset) { + case PEDIT_IP4_SRC: + case PEDIT_IP4_DST: break; - case TCA_PEDIT_KEY_EX_HDR_TYPE_IP6: - switch (offset) { - case PEDIT_IP6_SRC_31_0: - case PEDIT_IP6_SRC_63_32: - case PEDIT_IP6_SRC_95_64: - case PEDIT_IP6_SRC_127_96: - case PEDIT_IP6_DST_31_0: - case PEDIT_IP6_DST_63_32: - case PEDIT_IP6_DST_95_64: - case PEDIT_IP6_DST_127_96: - break; - default: - netdev_err(dev, "%s: Unsupported pedit field\n", - __func__); - return false; - } + default: + netdev_err(dev, "%s: Unsupported pedit field\n", + __func__); + return false; + } + break; + case FLOW_ACT_MANGLE_HDR_TYPE_IP6: + switch (offset) { + case PEDIT_IP6_SRC_31_0: + case PEDIT_IP6_SRC_63_32: + case PEDIT_IP6_SRC_95_64: + case PEDIT_IP6_SRC_127_96: + case PEDIT_IP6_DST_31_0: + case PEDIT_IP6_DST_63_32: + case PEDIT_IP6_DST_95_64: + case PEDIT_IP6_DST_127_96: break; - case TCA_PEDIT_KEY_EX_HDR_TYPE_TCP: - switch (offset) { - case PEDIT_TCP_SPORT_DPORT: - if (!valid_l4_mask(~mask)) { - netdev_err(dev, "%s: Unsupported mask for TCP L4 ports\n", - __func__); - return false; - } - break; - default: - netdev_err(dev, "%s: Unsupported pedit field\n", + default: + netdev_err(dev, "%s: Unsupported pedit field\n", + __func__); + return false; + } + break; + case FLOW_ACT_MANGLE_HDR_TYPE_TCP: + switch (offset) { + case PEDIT_TCP_SPORT_DPORT: + if (!valid_l4_mask(~mask)) { + netdev_err(dev, "%s: Unsupported mask for TCP L4 ports\n", __func__); return false; } break; - case TCA_PEDIT_KEY_EX_HDR_TYPE_UDP: - switch (offset) { - case PEDIT_UDP_SPORT_DPORT: - if (!valid_l4_mask(~mask)) { - netdev_err(dev, "%s: Unsupported mask for UDP L4 ports\n", - __func__); - return false; - } - break; - default: - netdev_err(dev, "%s: Unsupported pedit field\n", + default: + netdev_err(dev, "%s: Unsupported pedit field\n", + __func__); + return false; + } + break; + case FLOW_ACT_MANGLE_HDR_TYPE_UDP: + switch (offset) { + case PEDIT_UDP_SPORT_DPORT: + if (!valid_l4_mask(~mask)) { + netdev_err(dev, "%s: Unsupported mask for UDP L4 ports\n", __func__); return false; } break; default: - netdev_err(dev, "%s: Unsupported pedit type\n", + netdev_err(dev, "%s: Unsupported pedit field\n", __func__); return false; } + break; + default: + netdev_err(dev, "%s: Unsupported pedit type\n", __func__); + return false; } return true; } @@ -586,24 +545,26 @@ static bool valid_pedit_action(struct net_device *dev, static int cxgb4_validate_flow_actions(struct net_device *dev, struct tc_cls_flower_offload *cls) { - const struct tc_action *a; + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(cls); + struct flow_action_entry *act; bool act_redir = false; bool act_pedit = false; bool act_vlan = false; int i; - tcf_exts_for_each_action(i, a, cls->exts) { - if (is_tcf_gact_ok(a)) { - /* Do nothing */ - } else if (is_tcf_gact_shot(a)) { + flow_action_for_each(i, act, &rule->action) { + switch (act->id) { + case FLOW_ACTION_ACCEPT: + case FLOW_ACTION_DROP: /* Do nothing */ - } else if (is_tcf_mirred_egress_redirect(a)) { + break; + case FLOW_ACTION_REDIRECT: { struct adapter *adap = netdev2adap(dev); struct net_device *n_dev, *target_dev; unsigned int i; bool found = false; - target_dev = tcf_mirred_dev(a); + target_dev = act->dev; for_each_port(adap, i) { n_dev = adap->port[i]; if (target_dev == n_dev) { @@ -621,15 +582,18 @@ static int cxgb4_validate_flow_actions(struct net_device *dev, return -EINVAL; } act_redir = true; - } else if (is_tcf_vlan(a)) { - u16 proto = be16_to_cpu(tcf_vlan_push_proto(a)); - u32 vlan_action = tcf_vlan_action(a); + } + break; + case FLOW_ACTION_VLAN_POP: + case FLOW_ACTION_VLAN_PUSH: + case FLOW_ACTION_VLAN_MANGLE: { + u16 proto = be16_to_cpu(act->vlan.proto); - switch (vlan_action) { - case TCA_VLAN_ACT_POP: + switch (act->id) { + case FLOW_ACTION_VLAN_POP: break; - case TCA_VLAN_ACT_PUSH: - case TCA_VLAN_ACT_MODIFY: + case FLOW_ACTION_VLAN_PUSH: + case FLOW_ACTION_VLAN_MANGLE: if (proto != ETH_P_8021Q) { netdev_err(dev, "%s: Unsupported vlan proto\n", __func__); @@ -642,13 +606,17 @@ static int cxgb4_validate_flow_actions(struct net_device *dev, return -EOPNOTSUPP; } act_vlan = true; - } else if (is_tcf_pedit(a)) { - bool pedit_valid = valid_pedit_action(dev, a); + } + break; + case FLOW_ACTION_MANGLE: { + bool pedit_valid = valid_pedit_action(dev, act); if (!pedit_valid) return -EOPNOTSUPP; act_pedit = true; - } else { + } + break; + default: netdev_err(dev, "%s: Unsupported action\n", __func__); return -EOPNOTSUPP; } @@ -843,9 +811,9 @@ int cxgb4_tc_flower_stats(struct net_device *dev, if (ofld_stats->packet_count != packets) { if (ofld_stats->prev_packet_count != packets) ofld_stats->last_used = jiffies; - tcf_exts_stats_update(cls->exts, bytes - ofld_stats->byte_count, - packets - ofld_stats->packet_count, - ofld_stats->last_used); + flow_stats_update(&cls->stats, bytes - ofld_stats->byte_count, + packets - ofld_stats->packet_count, + ofld_stats->last_used); ofld_stats->packet_count = packets; ofld_stats->byte_count = bytes; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c index c7d2b4dc7568..02fc63fa7f25 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c @@ -444,8 +444,7 @@ struct cxgb4_tc_u32_table *cxgb4_init_tc_u32(struct adapter *adap) if (!max_tids) return NULL; - t = kvzalloc(sizeof(*t) + - (max_tids * sizeof(struct cxgb4_link)), GFP_KERNEL); + t = kvzalloc(struct_size(t, table, max_tids), GFP_KERNEL); if (!t) return NULL; diff --git a/drivers/net/ethernet/chelsio/cxgb4/sched.c b/drivers/net/ethernet/chelsio/cxgb4/sched.c index 52edb688942b..ba6c153ee45c 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sched.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sched.c @@ -478,7 +478,7 @@ struct sched_table *t4_init_sched(unsigned int sched_size) struct sched_table *s; unsigned int i; - s = kvzalloc(sizeof(*s) + sched_size * sizeof(struct sched_class), GFP_KERNEL); + s = kvzalloc(struct_size(s, tab, sched_size), GFP_KERNEL); if (!s) return NULL; diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index fc0bc6458e84..f18493fb32aa 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -80,9 +80,10 @@ * Max number of Tx descriptors we clean up at a time. Should be modest as * freeing skbs isn't cheap and it happens while holding locks. We just need * to free packets faster than they arrive, we eventually catch up and keep - * the amortized cost reasonable. Must be >= 2 * TXQ_STOP_THRES. + * the amortized cost reasonable. Must be >= 2 * TXQ_STOP_THRES. It should + * also match the CIDX Flush Threshold. */ -#define MAX_TX_RECLAIM 16 +#define MAX_TX_RECLAIM 32 /* * Max number of Rx buffers we replenish at a time. Again keep this modest, @@ -401,31 +402,52 @@ static inline int reclaimable(const struct sge_txq *q) } /** - * cxgb4_reclaim_completed_tx - reclaims completed Tx descriptors + * reclaim_completed_tx - reclaims completed TX Descriptors * @adap: the adapter * @q: the Tx queue to reclaim completed descriptors from + * @maxreclaim: the maximum number of TX Descriptors to reclaim or -1 * @unmap: whether the buffers should be unmapped for DMA * - * Reclaims Tx descriptors that the SGE has indicated it has processed, - * and frees the associated buffers if possible. Called with the Tx - * queue locked. + * Reclaims Tx Descriptors that the SGE has indicated it has processed, + * and frees the associated buffers if possible. If @max == -1, then + * we'll use a defaiult maximum. Called with the TX Queue locked. */ -inline void cxgb4_reclaim_completed_tx(struct adapter *adap, struct sge_txq *q, - bool unmap) +static inline int reclaim_completed_tx(struct adapter *adap, struct sge_txq *q, + int maxreclaim, bool unmap) { - int avail = reclaimable(q); + int reclaim = reclaimable(q); - if (avail) { + if (reclaim) { /* * Limit the amount of clean up work we do at a time to keep * the Tx lock hold time O(1). */ - if (avail > MAX_TX_RECLAIM) - avail = MAX_TX_RECLAIM; + if (maxreclaim < 0) + maxreclaim = MAX_TX_RECLAIM; + if (reclaim > maxreclaim) + reclaim = maxreclaim; - free_tx_desc(adap, q, avail, unmap); - q->in_use -= avail; + free_tx_desc(adap, q, reclaim, unmap); + q->in_use -= reclaim; } + + return reclaim; +} + +/** + * cxgb4_reclaim_completed_tx - reclaims completed Tx descriptors + * @adap: the adapter + * @q: the Tx queue to reclaim completed descriptors from + * @unmap: whether the buffers should be unmapped for DMA + * + * Reclaims Tx descriptors that the SGE has indicated it has processed, + * and frees the associated buffers if possible. Called with the Tx + * queue locked. + */ +void cxgb4_reclaim_completed_tx(struct adapter *adap, struct sge_txq *q, + bool unmap) +{ + (void)reclaim_completed_tx(adap, q, -1, unmap); } EXPORT_SYMBOL(cxgb4_reclaim_completed_tx); @@ -1288,6 +1310,44 @@ static inline void t6_fill_tnl_lso(struct sk_buff *skb, } /** + * t4_sge_eth_txq_egress_update - handle Ethernet TX Queue update + * @adap: the adapter + * @eq: the Ethernet TX Queue + * @maxreclaim: the maximum number of TX Descriptors to reclaim or -1 + * + * We're typically called here to update the state of an Ethernet TX + * Queue with respect to the hardware's progress in consuming the TX + * Work Requests that we've put on that Egress Queue. This happens + * when we get Egress Queue Update messages and also prophylactically + * in regular timer-based Ethernet TX Queue maintenance. + */ +int t4_sge_eth_txq_egress_update(struct adapter *adap, struct sge_eth_txq *eq, + int maxreclaim) +{ + struct sge_txq *q = &eq->q; + unsigned int reclaimed; + + if (!q->in_use || !__netif_tx_trylock(eq->txq)) + return 0; + + /* Reclaim pending completed TX Descriptors. */ + reclaimed = reclaim_completed_tx(adap, &eq->q, maxreclaim, true); + + /* If the TX Queue is currently stopped and there's now more than half + * the queue available, restart it. Otherwise bail out since the rest + * of what we want do here is with the possibility of shipping any + * currently buffered Coalesced TX Work Request. + */ + if (netif_tx_queue_stopped(eq->txq) && txq_avail(q) > (q->size / 2)) { + netif_tx_wake_queue(eq->txq); + eq->q.restarts++; + } + + __netif_tx_unlock(eq->txq); + return reclaimed; +} + +/** * cxgb4_eth_xmit - add a packet to an Ethernet Tx queue * @skb: the packet * @dev: the egress net device @@ -1357,7 +1417,7 @@ out_free: dev_kfree_skb_any(skb); } skb_tx_timestamp(skb); - cxgb4_reclaim_completed_tx(adap, &q->q, true); + reclaim_completed_tx(adap, &q->q, -1, true); cntrl = TXPKT_L4CSUM_DIS_F | TXPKT_IPCSUM_DIS_F; #ifdef CONFIG_CHELSIO_T4_FCOE @@ -1400,8 +1460,25 @@ out_free: dev_kfree_skb_any(skb); wr_mid = FW_WR_LEN16_V(DIV_ROUND_UP(flits, 2)); if (unlikely(credits < ETHTXQ_STOP_THRES)) { + /* After we're done injecting the Work Request for this + * packet, we'll be below our "stop threshold" so stop the TX + * Queue now and schedule a request for an SGE Egress Queue + * Update message. The queue will get started later on when + * the firmware processes this Work Request and sends us an + * Egress Queue Status Update message indicating that space + * has opened up. + */ eth_txq_stop(q); - wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F; + + /* If we're using the SGE Doorbell Queue Timer facility, we + * don't need to ask the Firmware to send us Egress Queue CIDX + * Updates: the Hardware will do this automatically. And + * since we send the Ingress Queue CIDX Updates to the + * corresponding Ethernet Response Queue, we'll get them very + * quickly. + */ + if (!q->dbqt) + wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F; } wr = (void *)&q->q.desc[q->q.pidx]; @@ -1671,7 +1748,7 @@ static netdev_tx_t cxgb4_vf_eth_xmit(struct sk_buff *skb, /* Take this opportunity to reclaim any TX Descriptors whose DMA * transfers have completed. */ - cxgb4_reclaim_completed_tx(adapter, &txq->q, true); + reclaim_completed_tx(adapter, &txq->q, -1, true); /* Calculate the number of flits and TX Descriptors we're going to * need along with how many TX Descriptors will be left over after @@ -1715,7 +1792,16 @@ static netdev_tx_t cxgb4_vf_eth_xmit(struct sk_buff *skb, * has opened up. */ eth_txq_stop(txq); - wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F; + + /* If we're using the SGE Doorbell Queue Timer facility, we + * don't need to ask the Firmware to send us Egress Queue CIDX + * Updates: the Hardware will do this automatically. And + * since we send the Ingress Queue CIDX Updates to the + * corresponding Ethernet Response Queue, we'll get them very + * quickly. + */ + if (!txq->dbqt) + wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F; } /* Start filling in our Work Request. Note that we do _not_ handle @@ -2794,6 +2880,74 @@ static int t4_tx_hststamp(struct adapter *adapter, struct sk_buff *skb, } /** + * t4_tx_completion_handler - handle CPL_SGE_EGR_UPDATE messages + * @rspq: Ethernet RX Response Queue associated with Ethernet TX Queue + * @rsp: Response Entry pointer into Response Queue + * @gl: Gather List pointer + * + * For adapters which support the SGE Doorbell Queue Timer facility, + * we configure the Ethernet TX Queues to send CIDX Updates to the + * Associated Ethernet RX Response Queue with CPL_SGE_EGR_UPDATE + * messages. This adds a small load to PCIe Link RX bandwidth and, + * potentially, higher CPU Interrupt load, but allows us to respond + * much more quickly to the CIDX Updates. This is important for + * Upper Layer Software which isn't willing to have a large amount + * of TX Data outstanding before receiving DMA Completions. + */ +static void t4_tx_completion_handler(struct sge_rspq *rspq, + const __be64 *rsp, + const struct pkt_gl *gl) +{ + u8 opcode = ((const struct rss_header *)rsp)->opcode; + struct port_info *pi = netdev_priv(rspq->netdev); + struct adapter *adapter = rspq->adap; + struct sge *s = &adapter->sge; + struct sge_eth_txq *txq; + + /* skip RSS header */ + rsp++; + + /* FW can send EGR_UPDATEs encapsulated in a CPL_FW4_MSG. + */ + if (unlikely(opcode == CPL_FW4_MSG && + ((const struct cpl_fw4_msg *)rsp)->type == + FW_TYPE_RSSCPL)) { + rsp++; + opcode = ((const struct rss_header *)rsp)->opcode; + rsp++; + } + + if (unlikely(opcode != CPL_SGE_EGR_UPDATE)) { + pr_info("%s: unexpected FW4/CPL %#x on Rx queue\n", + __func__, opcode); + return; + } + + txq = &s->ethtxq[pi->first_qset + rspq->idx]; + + /* We've got the Hardware Consumer Index Update in the Egress Update + * message. If we're using the SGE Doorbell Queue Timer mechanism, + * these Egress Update messages will be our sole CIDX Updates we get + * since we don't want to chew up PCIe bandwidth for both Ingress + * Messages and Status Page writes. However, The code which manages + * reclaiming successfully DMA'ed TX Work Requests uses the CIDX value + * stored in the Status Page at the end of the TX Queue. It's easiest + * to simply copy the CIDX Update value from the Egress Update message + * to the Status Page. Also note that no Endian issues need to be + * considered here since both are Big Endian and we're just copying + * bytes consistently ... + */ + if (txq->dbqt) { + struct cpl_sge_egr_update *egr; + + egr = (struct cpl_sge_egr_update *)rsp; + WRITE_ONCE(txq->q.stat->cidx, egr->cidx); + } + + t4_sge_eth_txq_egress_update(adapter, txq, -1); +} + +/** * t4_ethrx_handler - process an ingress ethernet packet * @q: the response queue that received the packet * @rsp: the response queue descriptor holding the RX_PKT message @@ -2816,6 +2970,15 @@ int t4_ethrx_handler(struct sge_rspq *q, const __be64 *rsp, struct port_info *pi; int ret = 0; + /* If we're looking at TX Queue CIDX Update, handle that separately + * and return. + */ + if (unlikely((*(u8 *)rsp == CPL_FW4_MSG) || + (*(u8 *)rsp == CPL_SGE_EGR_UPDATE))) { + t4_tx_completion_handler(q, rsp, si); + return 0; + } + if (unlikely(*(u8 *)rsp == cpl_trace_pkt)) return handle_trace_pkt(q->adap, si); @@ -3289,10 +3452,10 @@ done: static void sge_tx_timer_cb(struct timer_list *t) { - unsigned long m; - unsigned int i, budget; struct adapter *adap = from_timer(adap, t, sge.tx_timer); struct sge *s = &adap->sge; + unsigned long m, period; + unsigned int i, budget; for (i = 0; i < BITS_TO_LONGS(s->egr_sz); i++) for (m = s->txq_maperr[i]; m; m &= m - 1) { @@ -3320,29 +3483,29 @@ static void sge_tx_timer_cb(struct timer_list *t) budget = MAX_TIMER_TX_RECLAIM; i = s->ethtxq_rover; do { - struct sge_eth_txq *q = &s->ethtxq[i]; - - if (q->q.in_use && - time_after_eq(jiffies, q->txq->trans_start + HZ / 100) && - __netif_tx_trylock(q->txq)) { - int avail = reclaimable(&q->q); - - if (avail) { - if (avail > budget) - avail = budget; - - free_tx_desc(adap, &q->q, avail, true); - q->q.in_use -= avail; - budget -= avail; - } - __netif_tx_unlock(q->txq); - } + budget -= t4_sge_eth_txq_egress_update(adap, &s->ethtxq[i], + budget); + if (!budget) + break; if (++i >= s->ethqsets) i = 0; - } while (budget && i != s->ethtxq_rover); + } while (i != s->ethtxq_rover); s->ethtxq_rover = i; - mod_timer(&s->tx_timer, jiffies + (budget ? TX_QCHECK_PERIOD : 2)); + + if (budget == 0) { + /* If we found too many reclaimable packets schedule a timer + * in the near future to continue where we left off. + */ + period = 2; + } else { + /* We reclaimed all reclaimable TX Descriptors, so reschedule + * at the normal period. + */ + period = TX_QCHECK_PERIOD; + } + + mod_timer(&s->tx_timer, jiffies + period); } /** @@ -3421,7 +3584,8 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq, : FW_IQ_IQTYPE_OFLD)); if (fl) { - enum chip_type chip = CHELSIO_CHIP_VERSION(adap->params.chip); + unsigned int chip_ver = + CHELSIO_CHIP_VERSION(adap->params.chip); /* Allocate the ring for the hardware free list (with space * for its status page) along with the associated software @@ -3459,10 +3623,10 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq, * the smaller 64-byte value there). */ c.fl0dcaen_to_fl0cidxfthresh = - htons(FW_IQ_CMD_FL0FBMIN_V(chip <= CHELSIO_T5 ? + htons(FW_IQ_CMD_FL0FBMIN_V(chip_ver <= CHELSIO_T5 ? FETCHBURSTMIN_128B_X : - FETCHBURSTMIN_64B_X) | - FW_IQ_CMD_FL0FBMAX_V((chip <= CHELSIO_T5) ? + FETCHBURSTMIN_64B_T6_X) | + FW_IQ_CMD_FL0FBMAX_V((chip_ver <= CHELSIO_T5) ? FETCHBURSTMAX_512B_X : FETCHBURSTMAX_256B_X)); c.fl0size = htons(flsz); @@ -3584,14 +3748,24 @@ static void init_txq(struct adapter *adap, struct sge_txq *q, unsigned int id) adap->sge.egr_map[id - adap->sge.egr_start] = q; } +/** + * t4_sge_alloc_eth_txq - allocate an Ethernet TX Queue + * @adap: the adapter + * @txq: the SGE Ethernet TX Queue to initialize + * @dev: the Linux Network Device + * @netdevq: the corresponding Linux TX Queue + * @iqid: the Ingress Queue to which to deliver CIDX Update messages + * @dbqt: whether this TX Queue will use the SGE Doorbell Queue Timers + */ int t4_sge_alloc_eth_txq(struct adapter *adap, struct sge_eth_txq *txq, struct net_device *dev, struct netdev_queue *netdevq, - unsigned int iqid) + unsigned int iqid, u8 dbqt) { - int ret, nentries; - struct fw_eq_eth_cmd c; - struct sge *s = &adap->sge; + unsigned int chip_ver = CHELSIO_CHIP_VERSION(adap->params.chip); struct port_info *pi = netdev_priv(dev); + struct sge *s = &adap->sge; + struct fw_eq_eth_cmd c; + int ret, nentries; /* Add status entries */ nentries = txq->q.size + s->stat_len / sizeof(struct tx_desc); @@ -3610,19 +3784,47 @@ int t4_sge_alloc_eth_txq(struct adapter *adap, struct sge_eth_txq *txq, FW_EQ_ETH_CMD_VFN_V(0)); c.alloc_to_len16 = htonl(FW_EQ_ETH_CMD_ALLOC_F | FW_EQ_ETH_CMD_EQSTART_F | FW_LEN16(c)); - c.viid_pkd = htonl(FW_EQ_ETH_CMD_AUTOEQUEQE_F | - FW_EQ_ETH_CMD_VIID_V(pi->viid)); + + /* For TX Ethernet Queues using the SGE Doorbell Queue Timer + * mechanism, we use Ingress Queue messages for Hardware Consumer + * Index Updates on the TX Queue. Otherwise we have the Hardware + * write the CIDX Updates into the Status Page at the end of the + * TX Queue. + */ + c.autoequiqe_to_viid = htonl((dbqt + ? FW_EQ_ETH_CMD_AUTOEQUIQE_F + : FW_EQ_ETH_CMD_AUTOEQUEQE_F) | + FW_EQ_ETH_CMD_VIID_V(pi->viid)); + c.fetchszm_to_iqid = - htonl(FW_EQ_ETH_CMD_HOSTFCMODE_V(HOSTFCMODE_STATUS_PAGE_X) | + htonl(FW_EQ_ETH_CMD_HOSTFCMODE_V(dbqt + ? HOSTFCMODE_INGRESS_QUEUE_X + : HOSTFCMODE_STATUS_PAGE_X) | FW_EQ_ETH_CMD_PCIECHN_V(pi->tx_chan) | FW_EQ_ETH_CMD_FETCHRO_F | FW_EQ_ETH_CMD_IQID_V(iqid)); + + /* Note that the CIDX Flush Threshold should match MAX_TX_RECLAIM. */ c.dcaen_to_eqsize = - htonl(FW_EQ_ETH_CMD_FBMIN_V(FETCHBURSTMIN_64B_X) | + htonl(FW_EQ_ETH_CMD_FBMIN_V(chip_ver <= CHELSIO_T5 + ? FETCHBURSTMIN_64B_X + : FETCHBURSTMIN_64B_T6_X) | FW_EQ_ETH_CMD_FBMAX_V(FETCHBURSTMAX_512B_X) | FW_EQ_ETH_CMD_CIDXFTHRESH_V(CIDXFLUSHTHRESH_32_X) | FW_EQ_ETH_CMD_EQSIZE_V(nentries)); + c.eqaddr = cpu_to_be64(txq->q.phys_addr); + /* If we're using the SGE Doorbell Queue Timer mechanism, pass in the + * currently configured Timer Index. THis can be changed later via an + * ethtool -C tx-usecs {Timer Val} command. Note that the SGE + * Doorbell Queue mode is currently automatically enabled in the + * Firmware by setting either AUTOEQUEQE or AUTOEQUIQE ... + */ + if (dbqt) + c.timeren_timerix = + cpu_to_be32(FW_EQ_ETH_CMD_TIMEREN_F | + FW_EQ_ETH_CMD_TIMERIX_V(txq->dbqtimerix)); + ret = t4_wr_mbox(adap, adap->mbox, &c, sizeof(c), &c); if (ret) { kfree(txq->q.sdesc); @@ -3639,6 +3841,8 @@ int t4_sge_alloc_eth_txq(struct adapter *adap, struct sge_eth_txq *txq, txq->txq = netdevq; txq->tso = txq->tx_cso = txq->vlan_ins = 0; txq->mapping_err = 0; + txq->dbqt = dbqt; + return 0; } @@ -3646,10 +3850,11 @@ int t4_sge_alloc_ctrl_txq(struct adapter *adap, struct sge_ctrl_txq *txq, struct net_device *dev, unsigned int iqid, unsigned int cmplqid) { - int ret, nentries; - struct fw_eq_ctrl_cmd c; - struct sge *s = &adap->sge; + unsigned int chip_ver = CHELSIO_CHIP_VERSION(adap->params.chip); struct port_info *pi = netdev_priv(dev); + struct sge *s = &adap->sge; + struct fw_eq_ctrl_cmd c; + int ret, nentries; /* Add status entries */ nentries = txq->q.size + s->stat_len / sizeof(struct tx_desc); @@ -3673,7 +3878,9 @@ int t4_sge_alloc_ctrl_txq(struct adapter *adap, struct sge_ctrl_txq *txq, FW_EQ_CTRL_CMD_PCIECHN_V(pi->tx_chan) | FW_EQ_CTRL_CMD_FETCHRO_F | FW_EQ_CTRL_CMD_IQID_V(iqid)); c.dcaen_to_eqsize = - htonl(FW_EQ_CTRL_CMD_FBMIN_V(FETCHBURSTMIN_64B_X) | + htonl(FW_EQ_CTRL_CMD_FBMIN_V(chip_ver <= CHELSIO_T5 + ? FETCHBURSTMIN_64B_X + : FETCHBURSTMIN_64B_T6_X) | FW_EQ_CTRL_CMD_FBMAX_V(FETCHBURSTMAX_512B_X) | FW_EQ_CTRL_CMD_CIDXFTHRESH_V(CIDXFLUSHTHRESH_32_X) | FW_EQ_CTRL_CMD_EQSIZE_V(nentries)); @@ -3713,6 +3920,7 @@ int t4_sge_alloc_uld_txq(struct adapter *adap, struct sge_uld_txq *txq, struct net_device *dev, unsigned int iqid, unsigned int uld_type) { + unsigned int chip_ver = CHELSIO_CHIP_VERSION(adap->params.chip); int ret, nentries; struct fw_eq_ofld_cmd c; struct sge *s = &adap->sge; @@ -3743,7 +3951,9 @@ int t4_sge_alloc_uld_txq(struct adapter *adap, struct sge_uld_txq *txq, FW_EQ_OFLD_CMD_PCIECHN_V(pi->tx_chan) | FW_EQ_OFLD_CMD_FETCHRO_F | FW_EQ_OFLD_CMD_IQID_V(iqid)); c.dcaen_to_eqsize = - htonl(FW_EQ_OFLD_CMD_FBMIN_V(FETCHBURSTMIN_64B_X) | + htonl(FW_EQ_OFLD_CMD_FBMIN_V(chip_ver <= CHELSIO_T5 + ? FETCHBURSTMIN_64B_X + : FETCHBURSTMIN_64B_T6_X) | FW_EQ_OFLD_CMD_FBMAX_V(FETCHBURSTMAX_512B_X) | FW_EQ_OFLD_CMD_CIDXFTHRESH_V(CIDXFLUSHTHRESH_32_X) | FW_EQ_OFLD_CMD_EQSIZE_V(nentries)); diff --git a/drivers/net/ethernet/chelsio/cxgb4/smt.c b/drivers/net/ethernet/chelsio/cxgb4/smt.c index 7b2207a2a130..eaf1fb74689c 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/smt.c +++ b/drivers/net/ethernet/chelsio/cxgb4/smt.c @@ -47,8 +47,7 @@ struct smt_data *t4_init_smt(void) smt_size = SMT_SIZE; - s = kvzalloc(sizeof(*s) + smt_size * sizeof(struct smt_entry), - GFP_KERNEL); + s = kvzalloc(struct_size(s, smtab, smt_size), GFP_KERNEL); if (!s) return NULL; s->smt_size = smt_size; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index c5e5466ee38b..27af347be4af 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -6713,6 +6713,47 @@ int t4_sge_ctxt_flush(struct adapter *adap, unsigned int mbox, int ctxt_type) } /** + * t4_read_sge_dbqtimers - reag SGE Doorbell Queue Timer values + * @adap - the adapter + * @ndbqtimers: size of the provided SGE Doorbell Queue Timer table + * @dbqtimers: SGE Doorbell Queue Timer table + * + * Reads the SGE Doorbell Queue Timer values into the provided table. + * Returns 0 on success (Firmware and Hardware support this feature), + * an error on failure. + */ +int t4_read_sge_dbqtimers(struct adapter *adap, unsigned int ndbqtimers, + u16 *dbqtimers) +{ + int ret, dbqtimerix; + + ret = 0; + dbqtimerix = 0; + while (dbqtimerix < ndbqtimers) { + int nparams, param; + u32 params[7], vals[7]; + + nparams = ndbqtimers - dbqtimerix; + if (nparams > ARRAY_SIZE(params)) + nparams = ARRAY_SIZE(params); + + for (param = 0; param < nparams; param++) + params[param] = + (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) | + FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_DBQ_TIMER) | + FW_PARAMS_PARAM_Y_V(dbqtimerix + param)); + ret = t4_query_params(adap, adap->mbox, adap->pf, 0, + nparams, params, vals); + if (ret) + break; + + for (param = 0; param < nparams; param++) + dbqtimers[dbqtimerix++] = vals[param]; + } + return ret; +} + +/** * t4_fw_hello - establish communication with FW * @adap: the adapter * @mbox: mailbox to use for the FW command diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h index 361d5032c288..002fc62ea726 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h @@ -91,6 +91,7 @@ enum { SGE_CTXT_SIZE = 24, /* size of SGE context */ SGE_NTIMERS = 6, /* # of interrupt holdoff timer values */ SGE_NCOUNTERS = 4, /* # of interrupt packet counter values */ + SGE_NDBQTIMERS = 8, /* # of Doorbell Queue Timer values */ SGE_MAX_IQ_SIZE = 65520, SGE_TIMER_RSTRT_CNTR = 6, /* restart RX packet threshold counter */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h index bf7325f6d553..0c5373462ced 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h @@ -218,6 +218,7 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN CH_PCI_ID_TABLE_FENTRY(0x6088), /* Custom T62100-CR */ CH_PCI_ID_TABLE_FENTRY(0x6089), /* Custom T62100-KR */ CH_PCI_ID_TABLE_FENTRY(0x608a), /* Custom T62100-CR */ + CH_PCI_ID_TABLE_FENTRY(0x608b), /* Custom T6225-CR */ CH_PCI_DEVICE_ID_TABLE_DEFINE_END; #endif /* __T4_PCI_ID_TBL_H__ */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_values.h b/drivers/net/ethernet/chelsio/cxgb4/t4_values.h index f6558cbfc54e..eb1aa82149db 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_values.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_values.h @@ -71,12 +71,18 @@ #define FETCHBURSTMIN_64B_X 2 #define FETCHBURSTMIN_128B_X 3 +/* T6 and later use a single-bit encoding for FetchBurstMin */ +#define FETCHBURSTMIN_64B_T6_X 0 +#define FETCHBURSTMIN_128B_T6_X 1 + #define FETCHBURSTMAX_256B_X 2 #define FETCHBURSTMAX_512B_X 3 +#define HOSTFCMODE_INGRESS_QUEUE_X 1 #define HOSTFCMODE_STATUS_PAGE_X 2 #define CIDXFLUSHTHRESH_32_X 5 +#define CIDXFLUSHTHRESH_128_X 7 #define UPDATEDELIVERY_INTERRUPT_X 1 diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h index 1d9b3e1e5f94..631f1663f4e0 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h @@ -1254,6 +1254,8 @@ enum fw_params_param_dev { FW_PARAMS_PARAM_DEV_RDMA_WRITE_WITH_IMM = 0x21, FW_PARAMS_PARAM_DEV_RI_WRITE_CMPL_WR = 0x24, FW_PARAMS_PARAM_DEV_OPAQUE_VIID_SMT_EXTN = 0x27, + FW_PARAMS_PARAM_DEV_DBQ_TIMER = 0x29, + FW_PARAMS_PARAM_DEV_DBQ_TIMERTICK = 0x2A, }; /* @@ -1322,6 +1324,7 @@ enum fw_params_param_dmaq { FW_PARAMS_PARAM_DMAQ_EQ_CMPLIQID_CTRL = 0x11, FW_PARAMS_PARAM_DMAQ_EQ_SCHEDCLASS_ETH = 0x12, FW_PARAMS_PARAM_DMAQ_EQ_DCBPRIO_ETH = 0x13, + FW_PARAMS_PARAM_DMAQ_EQ_TIMERIX = 0x15, FW_PARAMS_PARAM_DMAQ_CONM_CTXT = 0x20, }; @@ -1751,8 +1754,8 @@ struct fw_eq_eth_cmd { __be32 fetchszm_to_iqid; __be32 dcaen_to_eqsize; __be64 eqaddr; - __be32 viid_pkd; - __be32 r8_lo; + __be32 autoequiqe_to_viid; + __be32 timeren_timerix; __be64 r9; }; @@ -1847,6 +1850,10 @@ struct fw_eq_eth_cmd { #define FW_EQ_ETH_CMD_EQSIZE_S 0 #define FW_EQ_ETH_CMD_EQSIZE_V(x) ((x) << FW_EQ_ETH_CMD_EQSIZE_S) +#define FW_EQ_ETH_CMD_AUTOEQUIQE_S 31 +#define FW_EQ_ETH_CMD_AUTOEQUIQE_V(x) ((x) << FW_EQ_ETH_CMD_AUTOEQUIQE_S) +#define FW_EQ_ETH_CMD_AUTOEQUIQE_F FW_EQ_ETH_CMD_AUTOEQUIQE_V(1U) + #define FW_EQ_ETH_CMD_AUTOEQUEQE_S 30 #define FW_EQ_ETH_CMD_AUTOEQUEQE_V(x) ((x) << FW_EQ_ETH_CMD_AUTOEQUEQE_S) #define FW_EQ_ETH_CMD_AUTOEQUEQE_F FW_EQ_ETH_CMD_AUTOEQUEQE_V(1U) @@ -1854,6 +1861,19 @@ struct fw_eq_eth_cmd { #define FW_EQ_ETH_CMD_VIID_S 16 #define FW_EQ_ETH_CMD_VIID_V(x) ((x) << FW_EQ_ETH_CMD_VIID_S) +#define FW_EQ_ETH_CMD_TIMEREN_S 3 +#define FW_EQ_ETH_CMD_TIMEREN_M 0x1 +#define FW_EQ_ETH_CMD_TIMEREN_V(x) ((x) << FW_EQ_ETH_CMD_TIMEREN_S) +#define FW_EQ_ETH_CMD_TIMEREN_G(x) \ + (((x) >> FW_EQ_ETH_CMD_TIMEREN_S) & FW_EQ_ETH_CMD_TIMEREN_M) +#define FW_EQ_ETH_CMD_TIMEREN_F FW_EQ_ETH_CMD_TIMEREN_V(1U) + +#define FW_EQ_ETH_CMD_TIMERIX_S 0 +#define FW_EQ_ETH_CMD_TIMERIX_M 0x7 +#define FW_EQ_ETH_CMD_TIMERIX_V(x) ((x) << FW_EQ_ETH_CMD_TIMERIX_S) +#define FW_EQ_ETH_CMD_TIMERIX_G(x) \ + (((x) >> FW_EQ_ETH_CMD_TIMERIX_S) & FW_EQ_ETH_CMD_TIMERIX_M) + struct fw_eq_ctrl_cmd { __be32 op_to_vfn; __be32 alloc_to_len16; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h index a844296135b4..9125ddd89dd1 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h @@ -36,8 +36,8 @@ #define __T4FW_VERSION_H__ #define T4FW_VERSION_MAJOR 0x01 -#define T4FW_VERSION_MINOR 0x14 -#define T4FW_VERSION_MICRO 0x08 +#define T4FW_VERSION_MINOR 0x16 +#define T4FW_VERSION_MICRO 0x09 #define T4FW_VERSION_BUILD 0x00 #define T4FW_MIN_VERSION_MAJOR 0x01 @@ -45,8 +45,8 @@ #define T4FW_MIN_VERSION_MICRO 0x00 #define T5FW_VERSION_MAJOR 0x01 -#define T5FW_VERSION_MINOR 0x14 -#define T5FW_VERSION_MICRO 0x08 +#define T5FW_VERSION_MINOR 0x16 +#define T5FW_VERSION_MICRO 0x09 #define T5FW_VERSION_BUILD 0x00 #define T5FW_MIN_VERSION_MAJOR 0x00 @@ -54,8 +54,8 @@ #define T5FW_MIN_VERSION_MICRO 0x00 #define T6FW_VERSION_MAJOR 0x01 -#define T6FW_VERSION_MINOR 0x14 -#define T6FW_VERSION_MICRO 0x08 +#define T6FW_VERSION_MINOR 0x16 +#define T6FW_VERSION_MICRO 0x09 #define T6FW_VERSION_BUILD 0x00 #define T6FW_MIN_VERSION_MAJOR 0x00 diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/adapter.h b/drivers/net/ethernet/chelsio/cxgb4vf/adapter.h index 5883f09e3804..26f48a14d2f9 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/adapter.h +++ b/drivers/net/ethernet/chelsio/cxgb4vf/adapter.h @@ -94,7 +94,7 @@ struct port_info { struct adapter *adapter; /* our adapter */ u32 vlan_id; /* vlan id for VST */ u16 viid; /* virtual interface ID */ - s16 xact_addr_filt; /* index of our MAC address filter */ + int xact_addr_filt; /* index of our MAC address filter */ u16 rss_size; /* size of VI's RSS table slice */ u8 pidx; /* index into adapter port[] */ s8 mdio_addr; @@ -352,6 +352,7 @@ struct sge { struct hash_mac_addr { struct list_head list; u8 addr[ETH_ALEN]; + unsigned int iface_mac; }; struct mbox_list { diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index 2fab87e86561..3300b69a42b3 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -236,6 +236,73 @@ void t4vf_os_portmod_changed(struct adapter *adapter, int pidx) "inserted\n", dev->name, pi->mod_type); } +static int cxgb4vf_set_addr_hash(struct port_info *pi) +{ + struct adapter *adapter = pi->adapter; + u64 vec = 0; + bool ucast = false; + struct hash_mac_addr *entry; + + /* Calculate the hash vector for the updated list and program it */ + list_for_each_entry(entry, &adapter->mac_hlist, list) { + ucast |= is_unicast_ether_addr(entry->addr); + vec |= (1ULL << hash_mac_addr(entry->addr)); + } + return t4vf_set_addr_hash(adapter, pi->viid, ucast, vec, false); +} + +/** + * cxgb4vf_change_mac - Update match filter for a MAC address. + * @pi: the port_info + * @viid: the VI id + * @tcam_idx: TCAM index of existing filter for old value of MAC address, + * or -1 + * @addr: the new MAC address value + * @persist: whether a new MAC allocation should be persistent + * @add_smt: if true also add the address to the HW SMT + * + * Modifies an MPS filter and sets it to the new MAC address if + * @tcam_idx >= 0, or adds the MAC address to a new filter if + * @tcam_idx < 0. In the latter case the address is added persistently + * if @persist is %true. + * Addresses are programmed to hash region, if tcam runs out of entries. + * + */ +static int cxgb4vf_change_mac(struct port_info *pi, unsigned int viid, + int *tcam_idx, const u8 *addr, bool persistent) +{ + struct hash_mac_addr *new_entry, *entry; + struct adapter *adapter = pi->adapter; + int ret; + + ret = t4vf_change_mac(adapter, viid, *tcam_idx, addr, persistent); + /* We ran out of TCAM entries. try programming hash region. */ + if (ret == -ENOMEM) { + /* If the MAC address to be updated is in the hash addr + * list, update it from the list + */ + list_for_each_entry(entry, &adapter->mac_hlist, list) { + if (entry->iface_mac) { + ether_addr_copy(entry->addr, addr); + goto set_hash; + } + } + new_entry = kzalloc(sizeof(*new_entry), GFP_KERNEL); + if (!new_entry) + return -ENOMEM; + ether_addr_copy(new_entry->addr, addr); + new_entry->iface_mac = true; + list_add_tail(&new_entry->list, &adapter->mac_hlist); +set_hash: + ret = cxgb4vf_set_addr_hash(pi); + } else if (ret >= 0) { + *tcam_idx = ret; + ret = 0; + } + + return ret; +} + /* * Net device operations. * ====================== @@ -259,14 +326,10 @@ static int link_start(struct net_device *dev) */ ret = t4vf_set_rxmode(pi->adapter, pi->viid, dev->mtu, -1, -1, -1, 1, true); - if (ret == 0) { - ret = t4vf_change_mac(pi->adapter, pi->viid, - pi->xact_addr_filt, dev->dev_addr, true); - if (ret >= 0) { - pi->xact_addr_filt = ret; - ret = 0; - } - } + if (ret == 0) + ret = cxgb4vf_change_mac(pi, pi->viid, + &pi->xact_addr_filt, + dev->dev_addr, true); /* * We don't need to actually "start the link" itself since the @@ -791,6 +854,13 @@ static int cxgb4vf_open(struct net_device *dev) return err; } + /* It's possible that the basic port information could have + * changed since we first read it. + */ + err = t4vf_update_port_info(pi); + if (err < 0) + return err; + /* * Note that this interface is up and start everything up ... */ @@ -863,21 +933,6 @@ static struct net_device_stats *cxgb4vf_get_stats(struct net_device *dev) return ns; } -static inline int cxgb4vf_set_addr_hash(struct port_info *pi) -{ - struct adapter *adapter = pi->adapter; - u64 vec = 0; - bool ucast = false; - struct hash_mac_addr *entry; - - /* Calculate the hash vector for the updated list and program it */ - list_for_each_entry(entry, &adapter->mac_hlist, list) { - ucast |= is_unicast_ether_addr(entry->addr); - vec |= (1ULL << hash_mac_addr(entry->addr)); - } - return t4vf_set_addr_hash(adapter, pi->viid, ucast, vec, false); -} - static int cxgb4vf_mac_sync(struct net_device *netdev, const u8 *mac_addr) { struct port_info *pi = netdev_priv(netdev); @@ -1159,13 +1214,12 @@ static int cxgb4vf_set_mac_addr(struct net_device *dev, void *_addr) if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; - ret = t4vf_change_mac(pi->adapter, pi->viid, pi->xact_addr_filt, - addr->sa_data, true); + ret = cxgb4vf_change_mac(pi, pi->viid, &pi->xact_addr_filt, + addr->sa_data, true); if (ret < 0) return ret; memcpy(dev->dev_addr, addr->sa_data, dev->addr_len); - pi->xact_addr_filt = ret; return 0; } @@ -1354,7 +1408,7 @@ static void fw_caps_to_lmm(enum fw_port_type port_type, case FW_PORT_TYPE_CR4_QSFP: SET_LMM(FIBRE); FW_CAPS_TO_LMM(SPEED_1G, 1000baseT_Full); - FW_CAPS_TO_LMM(SPEED_10G, 10000baseSR_Full); + FW_CAPS_TO_LMM(SPEED_10G, 10000baseKR_Full); FW_CAPS_TO_LMM(SPEED_40G, 40000baseSR4_Full); FW_CAPS_TO_LMM(SPEED_25G, 25000baseCR_Full); FW_CAPS_TO_LMM(SPEED_50G, 50000baseCR2_Full); @@ -1365,6 +1419,13 @@ static void fw_caps_to_lmm(enum fw_port_type port_type, break; } + if (fw_caps & FW_PORT_CAP32_FEC_V(FW_PORT_CAP32_FEC_M)) { + FW_CAPS_TO_LMM(FEC_RS, FEC_RS); + FW_CAPS_TO_LMM(FEC_BASER_RS, FEC_BASER); + } else { + SET_LMM(FEC_NONE); + } + FW_CAPS_TO_LMM(ANEG, Autoneg); FW_CAPS_TO_LMM(802_3_PAUSE, Pause); FW_CAPS_TO_LMM(802_3_ASM_DIR, Asym_Pause); diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c index 1d534f0baa69..11d2ba0a2bf5 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c @@ -2268,7 +2268,7 @@ int t4vf_sge_alloc_rxq(struct adapter *adapter, struct sge_rspq *rspq, cmd.iqaddr = cpu_to_be64(rspq->phys_addr); if (fl) { - enum chip_type chip = + unsigned int chip_ver = CHELSIO_CHIP_VERSION(adapter->params.chip); /* * Allocate the ring for the hardware free list (with space @@ -2319,10 +2319,10 @@ int t4vf_sge_alloc_rxq(struct adapter *adapter, struct sge_rspq *rspq, */ cmd.fl0dcaen_to_fl0cidxfthresh = cpu_to_be16( - FW_IQ_CMD_FL0FBMIN_V(chip <= CHELSIO_T5 ? - FETCHBURSTMIN_128B_X : - FETCHBURSTMIN_64B_X) | - FW_IQ_CMD_FL0FBMAX_V((chip <= CHELSIO_T5) ? + FW_IQ_CMD_FL0FBMIN_V(chip_ver <= CHELSIO_T5 + ? FETCHBURSTMIN_128B_X + : FETCHBURSTMIN_64B_T6_X) | + FW_IQ_CMD_FL0FBMAX_V((chip_ver <= CHELSIO_T5) ? FETCHBURSTMAX_512B_X : FETCHBURSTMAX_256B_X)); cmd.fl0size = cpu_to_be16(flsz); @@ -2411,10 +2411,11 @@ int t4vf_sge_alloc_eth_txq(struct adapter *adapter, struct sge_eth_txq *txq, struct net_device *dev, struct netdev_queue *devq, unsigned int iqid) { + unsigned int chip_ver = CHELSIO_CHIP_VERSION(adapter->params.chip); + struct port_info *pi = netdev_priv(dev); + struct fw_eq_eth_cmd cmd, rpl; struct sge *s = &adapter->sge; int ret, nentries; - struct fw_eq_eth_cmd cmd, rpl; - struct port_info *pi = netdev_priv(dev); /* * Calculate the size of the hardware TX Queue (including the Status @@ -2448,17 +2449,19 @@ int t4vf_sge_alloc_eth_txq(struct adapter *adapter, struct sge_eth_txq *txq, cmd.alloc_to_len16 = cpu_to_be32(FW_EQ_ETH_CMD_ALLOC_F | FW_EQ_ETH_CMD_EQSTART_F | FW_LEN16(cmd)); - cmd.viid_pkd = cpu_to_be32(FW_EQ_ETH_CMD_AUTOEQUEQE_F | - FW_EQ_ETH_CMD_VIID_V(pi->viid)); + cmd.autoequiqe_to_viid = cpu_to_be32(FW_EQ_ETH_CMD_AUTOEQUEQE_F | + FW_EQ_ETH_CMD_VIID_V(pi->viid)); cmd.fetchszm_to_iqid = cpu_to_be32(FW_EQ_ETH_CMD_HOSTFCMODE_V(SGE_HOSTFCMODE_STPG) | FW_EQ_ETH_CMD_PCIECHN_V(pi->port_id) | FW_EQ_ETH_CMD_IQID_V(iqid)); cmd.dcaen_to_eqsize = - cpu_to_be32(FW_EQ_ETH_CMD_FBMIN_V(SGE_FETCHBURSTMIN_64B) | - FW_EQ_ETH_CMD_FBMAX_V(SGE_FETCHBURSTMAX_512B) | + cpu_to_be32(FW_EQ_ETH_CMD_FBMIN_V(chip_ver <= CHELSIO_T5 + ? FETCHBURSTMIN_64B_X + : FETCHBURSTMIN_64B_T6_X) | + FW_EQ_ETH_CMD_FBMAX_V(FETCHBURSTMAX_512B_X) | FW_EQ_ETH_CMD_CIDXFTHRESH_V( - SGE_CIDXFLUSHTHRESH_32) | + CIDXFLUSHTHRESH_32_X) | FW_EQ_ETH_CMD_EQSIZE_V(nentries)); cmd.eqaddr = cpu_to_be64(txq->q.phys_addr); diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index 60641e202534..9a7f70db20c7 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -1434,7 +1434,8 @@ static void enic_rq_indicate_buf(struct vnic_rq *rq, * csum is correct or is zero. */ if ((netdev->features & NETIF_F_RXCSUM) && !csum_not_calc && - tcp_udp_csum_ok && ipv4_csum_ok && outer_csum_ok) { + tcp_udp_csum_ok && outer_csum_ok && + (ipv4_csum_ok || ipv6)) { skb->ip_summed = CHECKSUM_UNNECESSARY; skb->csum_level = encap; } diff --git a/drivers/net/ethernet/dec/tulip/de2104x.c b/drivers/net/ethernet/dec/tulip/de2104x.c index 13430f75496c..f1a2da15dd0a 100644 --- a/drivers/net/ethernet/dec/tulip/de2104x.c +++ b/drivers/net/ethernet/dec/tulip/de2104x.c @@ -585,7 +585,7 @@ static void de_tx (struct de_private *de) netif_dbg(de, tx_done, de->dev, "tx done, slot %d\n", tx_tail); } - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); } next: diff --git a/drivers/net/ethernet/dec/tulip/eeprom.c b/drivers/net/ethernet/dec/tulip/eeprom.c index 1812f4916917..ba0a69b363f8 100644 --- a/drivers/net/ethernet/dec/tulip/eeprom.c +++ b/drivers/net/ethernet/dec/tulip/eeprom.c @@ -224,9 +224,7 @@ subsequent_board: return; } - mtable = kmalloc(sizeof(struct mediatable) + - count * sizeof(struct medialeaf), - GFP_KERNEL); + mtable = kmalloc(struct_size(mtable, mleaf, count), GFP_KERNEL); if (mtable == NULL) return; /* Horrible, impossible failure. */ last_mediatable = tp->mtable = mtable; diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c index d8d423f22c4f..cfcdfee718b0 100644 --- a/drivers/net/ethernet/dlink/dl2k.c +++ b/drivers/net/ethernet/dlink/dl2k.c @@ -843,9 +843,9 @@ rio_free_tx (struct net_device *dev, int irq) desc_to_dma(&np->tx_ring[entry]), skb->len, PCI_DMA_TODEVICE); if (irq) - dev_kfree_skb_irq (skb); + dev_consume_skb_irq(skb); else - dev_kfree_skb (skb); + dev_kfree_skb(skb); np->tx_skbuff[entry] = NULL; entry = (entry + 1) % TX_RING_SIZE; diff --git a/drivers/net/ethernet/dlink/sundance.c b/drivers/net/ethernet/dlink/sundance.c index 1a27176381fb..4a37a69764ce 100644 --- a/drivers/net/ethernet/dlink/sundance.c +++ b/drivers/net/ethernet/dlink/sundance.c @@ -1193,7 +1193,6 @@ static irqreturn_t intr_handler(int irq, void *dev_instance) int handled = 0; int i; - do { int intr_status = ioread16(ioaddr + IntrStatus); iowrite16(intr_status, ioaddr + IntrStatus); @@ -1286,7 +1285,7 @@ static irqreturn_t intr_handler(int irq, void *dev_instance) dma_unmap_single(&np->pci_dev->dev, le32_to_cpu(np->tx_ring[entry].frag[0].addr), skb->len, DMA_TO_DEVICE); - dev_kfree_skb_irq (np->tx_skbuff[entry]); + dev_consume_skb_irq(np->tx_skbuff[entry]); np->tx_skbuff[entry] = NULL; np->tx_ring[entry].frag[0].addr = 0; np->tx_ring[entry].frag[0].length = 0; @@ -1305,7 +1304,7 @@ static irqreturn_t intr_handler(int irq, void *dev_instance) dma_unmap_single(&np->pci_dev->dev, le32_to_cpu(np->tx_ring[entry].frag[0].addr), skb->len, DMA_TO_DEVICE); - dev_kfree_skb_irq (np->tx_skbuff[entry]); + dev_consume_skb_irq(np->tx_skbuff[entry]); np->tx_skbuff[entry] = NULL; np->tx_ring[entry].frag[0].addr = 0; np->tx_ring[entry].frag[0].length = 0; diff --git a/drivers/net/ethernet/fealnx.c b/drivers/net/ethernet/fealnx.c index ae55da60ed0e..c24fd56a2c71 100644 --- a/drivers/net/ethernet/fealnx.c +++ b/drivers/net/ethernet/fealnx.c @@ -1531,7 +1531,7 @@ static irqreturn_t intr_handler(int irq, void *dev_instance) /* Free the original skb. */ pci_unmap_single(np->pci_dev, np->cur_tx->buffer, np->cur_tx->skbuff->len, PCI_DMA_TODEVICE); - dev_kfree_skb_irq(np->cur_tx->skbuff); + dev_consume_skb_irq(np->cur_tx->skbuff); np->cur_tx->skbuff = NULL; --np->really_tx_count; if (np->cur_tx->control & TXLD) { diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c index 62497119c85f..bdee441bc3b7 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c @@ -501,7 +501,7 @@ static int dpaa_get_ts_info(struct net_device *net_dev, struct device_node *mac_node = dev->of_node; struct device_node *fman_node = NULL, *ptp_node = NULL; struct platform_device *ptp_dev = NULL; - struct qoriq_ptp *ptp = NULL; + struct ptp_qoriq *ptp = NULL; info->phc_index = -1; diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 04925c731f0b..87777b09f5e0 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -86,16 +86,16 @@ static void free_rx_fd(struct dpaa2_eth_priv *priv, for (i = 1; i < DPAA2_ETH_MAX_SG_ENTRIES; i++) { addr = dpaa2_sg_get_addr(&sgt[i]); sg_vaddr = dpaa2_iova_to_virt(priv->iommu_domain, addr); - dma_unmap_single(dev, addr, DPAA2_ETH_RX_BUF_SIZE, - DMA_BIDIRECTIONAL); + dma_unmap_page(dev, addr, DPAA2_ETH_RX_BUF_SIZE, + DMA_BIDIRECTIONAL); - skb_free_frag(sg_vaddr); + free_pages((unsigned long)sg_vaddr, 0); if (dpaa2_sg_is_final(&sgt[i])) break; } free_buf: - skb_free_frag(vaddr); + free_pages((unsigned long)vaddr, 0); } /* Build a linear skb based on a single-buffer frame descriptor */ @@ -109,7 +109,7 @@ static struct sk_buff *build_linear_skb(struct dpaa2_eth_channel *ch, ch->buf_count--; - skb = build_skb(fd_vaddr, DPAA2_ETH_SKB_SIZE); + skb = build_skb(fd_vaddr, DPAA2_ETH_RX_BUF_RAW_SIZE); if (unlikely(!skb)) return NULL; @@ -144,19 +144,19 @@ static struct sk_buff *build_frag_skb(struct dpaa2_eth_priv *priv, /* Get the address and length from the S/G entry */ sg_addr = dpaa2_sg_get_addr(sge); sg_vaddr = dpaa2_iova_to_virt(priv->iommu_domain, sg_addr); - dma_unmap_single(dev, sg_addr, DPAA2_ETH_RX_BUF_SIZE, - DMA_BIDIRECTIONAL); + dma_unmap_page(dev, sg_addr, DPAA2_ETH_RX_BUF_SIZE, + DMA_BIDIRECTIONAL); sg_length = dpaa2_sg_get_len(sge); if (i == 0) { /* We build the skb around the first data buffer */ - skb = build_skb(sg_vaddr, DPAA2_ETH_SKB_SIZE); + skb = build_skb(sg_vaddr, DPAA2_ETH_RX_BUF_RAW_SIZE); if (unlikely(!skb)) { /* Free the first SG entry now, since we already * unmapped it and obtained the virtual address */ - skb_free_frag(sg_vaddr); + free_pages((unsigned long)sg_vaddr, 0); /* We still need to subtract the buffers used * by this FD from our software counter @@ -211,9 +211,9 @@ static void free_bufs(struct dpaa2_eth_priv *priv, u64 *buf_array, int count) for (i = 0; i < count; i++) { vaddr = dpaa2_iova_to_virt(priv->iommu_domain, buf_array[i]); - dma_unmap_single(dev, buf_array[i], DPAA2_ETH_RX_BUF_SIZE, - DMA_BIDIRECTIONAL); - skb_free_frag(vaddr); + dma_unmap_page(dev, buf_array[i], DPAA2_ETH_RX_BUF_SIZE, + DMA_BIDIRECTIONAL); + free_pages((unsigned long)vaddr, 0); } } @@ -264,9 +264,7 @@ static int xdp_enqueue(struct dpaa2_eth_priv *priv, struct dpaa2_fd *fd, fq = &priv->fq[queue_id]; for (i = 0; i < DPAA2_ETH_ENQUEUE_RETRIES; i++) { - err = dpaa2_io_service_enqueue_qd(fq->channel->dpio, - priv->tx_qdid, 0, - fq->tx_qdbin, fd); + err = priv->enqueue(priv, fq, fd, 0); if (err != -EBUSY) break; } @@ -378,16 +376,16 @@ static void dpaa2_eth_rx(struct dpaa2_eth_priv *priv, return; } - dma_unmap_single(dev, addr, DPAA2_ETH_RX_BUF_SIZE, - DMA_BIDIRECTIONAL); + dma_unmap_page(dev, addr, DPAA2_ETH_RX_BUF_SIZE, + DMA_BIDIRECTIONAL); skb = build_linear_skb(ch, fd, vaddr); } else if (fd_format == dpaa2_fd_sg) { WARN_ON(priv->xdp_prog); - dma_unmap_single(dev, addr, DPAA2_ETH_RX_BUF_SIZE, - DMA_BIDIRECTIONAL); + dma_unmap_page(dev, addr, DPAA2_ETH_RX_BUF_SIZE, + DMA_BIDIRECTIONAL); skb = build_frag_skb(priv, ch, buf_data); - skb_free_frag(vaddr); + free_pages((unsigned long)vaddr, 0); percpu_extras->rx_sg_frames++; percpu_extras->rx_sg_bytes += dpaa2_fd_get_len(fd); } else { @@ -657,7 +655,7 @@ static int build_single_fd(struct dpaa2_eth_priv *priv, * dpaa2_eth_tx(). */ static void free_tx_fd(const struct dpaa2_eth_priv *priv, - const struct dpaa2_fd *fd) + const struct dpaa2_fd *fd, bool in_napi) { struct device *dev = priv->net_dev->dev.parent; dma_addr_t fd_addr; @@ -712,7 +710,7 @@ static void free_tx_fd(const struct dpaa2_eth_priv *priv, skb_free_frag(skbh); /* Move on with skb release */ - dev_kfree_skb(skb); + napi_consume_skb(skb, in_napi); } static netdev_tx_t dpaa2_eth_tx(struct sk_buff *skb, struct net_device *net_dev) @@ -785,9 +783,7 @@ static netdev_tx_t dpaa2_eth_tx(struct sk_buff *skb, struct net_device *net_dev) queue_mapping = skb_get_queue_mapping(skb); fq = &priv->fq[queue_mapping]; for (i = 0; i < DPAA2_ETH_ENQUEUE_RETRIES; i++) { - err = dpaa2_io_service_enqueue_qd(fq->channel->dpio, - priv->tx_qdid, 0, - fq->tx_qdbin, &fd); + err = priv->enqueue(priv, fq, &fd, 0); if (err != -EBUSY) break; } @@ -795,7 +791,7 @@ static netdev_tx_t dpaa2_eth_tx(struct sk_buff *skb, struct net_device *net_dev) if (unlikely(err < 0)) { percpu_stats->tx_errors++; /* Clean up everything, including freeing the skb */ - free_tx_fd(priv, &fd); + free_tx_fd(priv, &fd, false); } else { fd_len = dpaa2_fd_get_len(&fd); percpu_stats->tx_packets++; @@ -837,7 +833,7 @@ static void dpaa2_eth_tx_conf(struct dpaa2_eth_priv *priv, /* Check frame errors in the FD field */ fd_errors = dpaa2_fd_get_ctrl(fd) & DPAA2_FD_TX_ERR_MASK; - free_tx_fd(priv, fd); + free_tx_fd(priv, fd, true); if (likely(!fd_errors)) return; @@ -903,7 +899,7 @@ static int add_bufs(struct dpaa2_eth_priv *priv, { struct device *dev = priv->net_dev->dev.parent; u64 buf_array[DPAA2_ETH_BUFS_PER_CMD]; - void *buf; + struct page *page; dma_addr_t addr; int i, err; @@ -911,14 +907,16 @@ static int add_bufs(struct dpaa2_eth_priv *priv, /* Allocate buffer visible to WRIOP + skb shared info + * alignment padding */ - buf = napi_alloc_frag(dpaa2_eth_buf_raw_size(priv)); - if (unlikely(!buf)) + /* allocate one page for each Rx buffer. WRIOP sees + * the entire page except for a tailroom reserved for + * skb shared info + */ + page = dev_alloc_pages(0); + if (!page) goto err_alloc; - buf = PTR_ALIGN(buf, priv->rx_buf_align); - - addr = dma_map_single(dev, buf, DPAA2_ETH_RX_BUF_SIZE, - DMA_BIDIRECTIONAL); + addr = dma_map_page(dev, page, 0, DPAA2_ETH_RX_BUF_SIZE, + DMA_BIDIRECTIONAL); if (unlikely(dma_mapping_error(dev, addr))) goto err_map; @@ -926,7 +924,7 @@ static int add_bufs(struct dpaa2_eth_priv *priv, /* tracing point */ trace_dpaa2_eth_buf_seed(priv->net_dev, - buf, dpaa2_eth_buf_raw_size(priv), + page, DPAA2_ETH_RX_BUF_RAW_SIZE, addr, DPAA2_ETH_RX_BUF_SIZE, bpid); } @@ -948,7 +946,7 @@ release_bufs: return i; err_map: - skb_free_frag(buf); + __free_pages(page, 0); err_alloc: /* If we managed to allocate at least some buffers, * release them to hardware @@ -2134,6 +2132,7 @@ static int set_buffer_layout(struct dpaa2_eth_priv *priv) { struct device *dev = priv->net_dev->dev.parent; struct dpni_buffer_layout buf_layout = {0}; + u16 rx_buf_align; int err; /* We need to check for WRIOP version 1.0.0, but depending on the MC @@ -2142,9 +2141,9 @@ static int set_buffer_layout(struct dpaa2_eth_priv *priv) */ if (priv->dpni_attrs.wriop_version == DPAA2_WRIOP_VERSION(0, 0, 0) || priv->dpni_attrs.wriop_version == DPAA2_WRIOP_VERSION(1, 0, 0)) - priv->rx_buf_align = DPAA2_ETH_RX_BUF_ALIGN_REV1; + rx_buf_align = DPAA2_ETH_RX_BUF_ALIGN_REV1; else - priv->rx_buf_align = DPAA2_ETH_RX_BUF_ALIGN; + rx_buf_align = DPAA2_ETH_RX_BUF_ALIGN; /* tx buffer */ buf_layout.private_data_size = DPAA2_ETH_SWA_SIZE; @@ -2184,7 +2183,7 @@ static int set_buffer_layout(struct dpaa2_eth_priv *priv) /* rx buffer */ buf_layout.pass_frame_status = true; buf_layout.pass_parser_result = true; - buf_layout.data_align = priv->rx_buf_align; + buf_layout.data_align = rx_buf_align; buf_layout.data_head_room = dpaa2_eth_rx_head_room(priv); buf_layout.private_data_size = 0; buf_layout.options = DPNI_BUF_LAYOUT_OPT_PARSER_RESULT | @@ -2202,6 +2201,36 @@ static int set_buffer_layout(struct dpaa2_eth_priv *priv) return 0; } +#define DPNI_ENQUEUE_FQID_VER_MAJOR 7 +#define DPNI_ENQUEUE_FQID_VER_MINOR 9 + +static inline int dpaa2_eth_enqueue_qd(struct dpaa2_eth_priv *priv, + struct dpaa2_eth_fq *fq, + struct dpaa2_fd *fd, u8 prio) +{ + return dpaa2_io_service_enqueue_qd(fq->channel->dpio, + priv->tx_qdid, prio, + fq->tx_qdbin, fd); +} + +static inline int dpaa2_eth_enqueue_fq(struct dpaa2_eth_priv *priv, + struct dpaa2_eth_fq *fq, + struct dpaa2_fd *fd, + u8 prio __always_unused) +{ + return dpaa2_io_service_enqueue_fq(fq->channel->dpio, + fq->tx_fqid, fd); +} + +static void set_enqueue_mode(struct dpaa2_eth_priv *priv) +{ + if (dpaa2_eth_cmp_dpni_ver(priv, DPNI_ENQUEUE_FQID_VER_MAJOR, + DPNI_ENQUEUE_FQID_VER_MINOR) < 0) + priv->enqueue = dpaa2_eth_enqueue_qd; + else + priv->enqueue = dpaa2_eth_enqueue_fq; +} + /* Configure the DPNI object this interface is associated with */ static int setup_dpni(struct fsl_mc_device *ls_dev) { @@ -2255,6 +2284,8 @@ static int setup_dpni(struct fsl_mc_device *ls_dev) if (err) goto close; + set_enqueue_mode(priv); + priv->cls_rules = devm_kzalloc(dev, sizeof(struct dpaa2_eth_cls_rule) * dpaa2_eth_fs_count(priv), GFP_KERNEL); if (!priv->cls_rules) @@ -2339,6 +2370,7 @@ static int setup_tx_flow(struct dpaa2_eth_priv *priv, } fq->tx_qdbin = qid.qdbin; + fq->tx_fqid = qid.fqid; err = dpni_get_queue(priv->mc_io, 0, priv->mc_token, DPNI_QUEUE_TX_CONFIRM, 0, fq->flowid, diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h index 31fe486ec25f..9510928b7cca 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h @@ -53,7 +53,8 @@ */ #define DPAA2_ETH_MAX_FRAMES_PER_QUEUE (DPAA2_ETH_TAILDROP_THRESH / 64) #define DPAA2_ETH_NUM_BUFS (DPAA2_ETH_MAX_FRAMES_PER_QUEUE + 256) -#define DPAA2_ETH_REFILL_THRESH DPAA2_ETH_MAX_FRAMES_PER_QUEUE +#define DPAA2_ETH_REFILL_THRESH \ + (DPAA2_ETH_NUM_BUFS - DPAA2_ETH_BUFS_PER_CMD) /* Maximum number of buffers that can be acquired/released through a single * QBMan command @@ -63,9 +64,11 @@ /* Hardware requires alignment for ingress/egress buffer addresses */ #define DPAA2_ETH_TX_BUF_ALIGN 64 -#define DPAA2_ETH_RX_BUF_SIZE 2048 -#define DPAA2_ETH_SKB_SIZE \ - (DPAA2_ETH_RX_BUF_SIZE + SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) +#define DPAA2_ETH_RX_BUF_RAW_SIZE PAGE_SIZE +#define DPAA2_ETH_RX_BUF_TAILROOM \ + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) +#define DPAA2_ETH_RX_BUF_SIZE \ + (DPAA2_ETH_RX_BUF_RAW_SIZE - DPAA2_ETH_RX_BUF_TAILROOM) /* Hardware annotation area in RX/TX buffers */ #define DPAA2_ETH_RX_HWA_SIZE 64 @@ -274,6 +277,7 @@ struct dpaa2_eth_priv; struct dpaa2_eth_fq { u32 fqid; u32 tx_qdbin; + u32 tx_fqid; u16 flowid; int target_cpu; u32 dq_frames; @@ -326,6 +330,9 @@ struct dpaa2_eth_priv { u8 num_fqs; struct dpaa2_eth_fq fq[DPAA2_ETH_MAX_QUEUES]; + int (*enqueue)(struct dpaa2_eth_priv *priv, + struct dpaa2_eth_fq *fq, + struct dpaa2_fd *fd, u8 prio); u8 num_channels; struct dpaa2_eth_channel *channel[DPAA2_ETH_MAX_DPCONS]; @@ -343,7 +350,6 @@ struct dpaa2_eth_priv { bool rx_tstamp; /* Rx timestamping enabled */ u16 tx_qdid; - u16 rx_buf_align; struct fsl_mc_io *mc_io; /* Cores which have an affine DPIO/DPCON. * This is the cpu set on which Rx and Tx conf frames are processed @@ -418,15 +424,6 @@ enum dpaa2_eth_rx_dist { DPAA2_ETH_RX_DIST_CLS }; -/* Hardware only sees DPAA2_ETH_RX_BUF_SIZE, but the skb built around - * the buffer also needs space for its shared info struct, and we need - * to allocate enough to accommodate hardware alignment restrictions - */ -static inline unsigned int dpaa2_eth_buf_raw_size(struct dpaa2_eth_priv *priv) -{ - return DPAA2_ETH_SKB_SIZE + priv->rx_buf_align; -} - static inline unsigned int dpaa2_eth_needed_headroom(struct dpaa2_eth_priv *priv, struct sk_buff *skb) @@ -451,8 +448,7 @@ unsigned int dpaa2_eth_needed_headroom(struct dpaa2_eth_priv *priv, */ static inline unsigned int dpaa2_eth_rx_head_room(struct dpaa2_eth_priv *priv) { - return priv->tx_data_offset + DPAA2_ETH_TX_BUF_ALIGN - - DPAA2_ETH_RX_HWA_SIZE; + return priv->tx_data_offset - DPAA2_ETH_RX_HWA_SIZE; } int dpaa2_eth_set_hash(struct net_device *net_dev, u64 flags); diff --git a/drivers/net/ethernet/freescale/enetc/Kconfig b/drivers/net/ethernet/freescale/enetc/Kconfig index f9dd26fbfc83..8429f5c1d810 100644 --- a/drivers/net/ethernet/freescale/enetc/Kconfig +++ b/drivers/net/ethernet/freescale/enetc/Kconfig @@ -17,3 +17,15 @@ config FSL_ENETC_VF virtual function (VF) devices enabled by the ENETC PF driver. If compiled as module (M), the module name is fsl-enetc-vf. + +config FSL_ENETC_PTP_CLOCK + tristate "ENETC PTP clock driver" + depends on PTP_1588_CLOCK_QORIQ && (FSL_ENETC || FSL_ENETC_VF) + default y + help + This driver adds support for using the ENETC 1588 timer + as a PTP clock. This clock is only useful if your PTP + programs are getting hardware time stamps on the PTP Ethernet + packets using the SO_TIMESTAMPING API. + + If compiled as module (M), the module name is fsl-enetc-ptp. diff --git a/drivers/net/ethernet/freescale/enetc/Makefile b/drivers/net/ethernet/freescale/enetc/Makefile index 9529b01872ca..697660294dbc 100644 --- a/drivers/net/ethernet/freescale/enetc/Makefile +++ b/drivers/net/ethernet/freescale/enetc/Makefile @@ -13,3 +13,6 @@ fsl-enetc-vf-$(CONFIG_FSL_ENETC_VF) += enetc.o enetc_cbdr.o \ enetc_ethtool.o fsl-enetc-vf-objs := enetc_vf.o $(fsl-enetc-vf-y) endif + +obj-$(CONFIG_FSL_ENETC_PTP_CLOCK) += fsl-enetc-ptp.o +fsl-enetc-ptp-$(CONFIG_FSL_ENETC_PTP_CLOCK) += enetc_ptp.o diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h index efa0b1a5ef4f..df8eb8882d92 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h +++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h @@ -4,8 +4,9 @@ #include <linux/bitops.h> /* ENETC device IDs */ -#define ENETC_DEV_ID_PF 0xe100 -#define ENETC_DEV_ID_VF 0xef00 +#define ENETC_DEV_ID_PF 0xe100 +#define ENETC_DEV_ID_VF 0xef00 +#define ENETC_DEV_ID_PTP 0xee02 /* ENETC register block BAR */ #define ENETC_BAR_REGS 0 diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ptp.c b/drivers/net/ethernet/freescale/enetc/enetc_ptp.c new file mode 100644 index 000000000000..dc2f58a7c9e5 --- /dev/null +++ b/drivers/net/ethernet/freescale/enetc/enetc_ptp.c @@ -0,0 +1,144 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) +/* Copyright 2019 NXP */ + +#include <linux/module.h> +#include <linux/of.h> +#include <linux/fsl/ptp_qoriq.h> + +#include "enetc.h" + +static struct ptp_clock_info enetc_ptp_caps = { + .owner = THIS_MODULE, + .name = "ENETC PTP clock", + .max_adj = 512000, + .n_alarm = 0, + .n_ext_ts = 2, + .n_per_out = 0, + .n_pins = 0, + .pps = 1, + .adjfine = ptp_qoriq_adjfine, + .adjtime = ptp_qoriq_adjtime, + .gettime64 = ptp_qoriq_gettime, + .settime64 = ptp_qoriq_settime, + .enable = ptp_qoriq_enable, +}; + +static int enetc_ptp_probe(struct pci_dev *pdev, + const struct pci_device_id *ent) +{ + struct ptp_qoriq *ptp_qoriq; + void __iomem *base; + int err, len, n; + + if (pdev->dev.of_node && !of_device_is_available(pdev->dev.of_node)) { + dev_info(&pdev->dev, "device is disabled, skipping\n"); + return -ENODEV; + } + + err = pci_enable_device_mem(pdev); + if (err) { + dev_err(&pdev->dev, "device enable failed\n"); + return err; + } + + /* set up for high or low dma */ + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); + if (err) { + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (err) { + dev_err(&pdev->dev, + "DMA configuration failed: 0x%x\n", err); + goto err_dma; + } + } + + err = pci_request_mem_regions(pdev, KBUILD_MODNAME); + if (err) { + dev_err(&pdev->dev, "pci_request_regions failed err=%d\n", err); + goto err_pci_mem_reg; + } + + pci_set_master(pdev); + + ptp_qoriq = kzalloc(sizeof(*ptp_qoriq), GFP_KERNEL); + if (!ptp_qoriq) { + err = -ENOMEM; + goto err_alloc_ptp; + } + + len = pci_resource_len(pdev, ENETC_BAR_REGS); + + base = ioremap(pci_resource_start(pdev, ENETC_BAR_REGS), len); + if (!base) { + err = -ENXIO; + dev_err(&pdev->dev, "ioremap() failed\n"); + goto err_ioremap; + } + + /* Allocate 1 interrupt */ + n = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSIX); + if (n != 1) { + err = -EPERM; + goto err_irq; + } + + ptp_qoriq->irq = pci_irq_vector(pdev, 0); + + err = request_irq(ptp_qoriq->irq, ptp_qoriq_isr, 0, DRIVER, ptp_qoriq); + if (err) { + dev_err(&pdev->dev, "request_irq() failed!\n"); + goto err_irq; + } + + ptp_qoriq->dev = &pdev->dev; + + err = ptp_qoriq_init(ptp_qoriq, base, enetc_ptp_caps); + if (err) + goto err_no_clock; + + pci_set_drvdata(pdev, ptp_qoriq); + + return 0; + +err_no_clock: + free_irq(ptp_qoriq->irq, ptp_qoriq); +err_irq: + iounmap(base); +err_ioremap: + kfree(ptp_qoriq); +err_alloc_ptp: + pci_release_mem_regions(pdev); +err_pci_mem_reg: +err_dma: + pci_disable_device(pdev); + + return err; +} + +static void enetc_ptp_remove(struct pci_dev *pdev) +{ + struct ptp_qoriq *ptp_qoriq = pci_get_drvdata(pdev); + + ptp_qoriq_free(ptp_qoriq); + kfree(ptp_qoriq); + + pci_release_mem_regions(pdev); + pci_disable_device(pdev); +} + +static const struct pci_device_id enetc_ptp_id_table[] = { + { PCI_DEVICE(PCI_VENDOR_ID_FREESCALE, ENETC_DEV_ID_PTP) }, + { 0, } /* End of table. */ +}; +MODULE_DEVICE_TABLE(pci, enetc_ptp_id_table); + +static struct pci_driver enetc_ptp_driver = { + .name = KBUILD_MODNAME, + .id_table = enetc_ptp_id_table, + .probe = enetc_ptp_probe, + .remove = enetc_ptp_remove, +}; +module_pci_driver(enetc_ptp_driver); + +MODULE_DESCRIPTION("ENETC PTP clock driver"); +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 2370dc204202..697c2427f2b7 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -2098,6 +2098,7 @@ static int fec_enet_get_regs_len(struct net_device *ndev) #if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \ defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM) || \ defined(CONFIG_ARM64) || defined(CONFIG_COMPILE_TEST) +static __u32 fec_enet_register_version = 2; static u32 fec_enet_register_offset[] = { FEC_IEVENT, FEC_IMASK, FEC_R_DES_ACTIVE_0, FEC_X_DES_ACTIVE_0, FEC_ECNTRL, FEC_MII_DATA, FEC_MII_SPEED, FEC_MIB_CTRLSTAT, FEC_R_CNTRL, @@ -2128,6 +2129,7 @@ static u32 fec_enet_register_offset[] = { IEEE_R_FDXFC, IEEE_R_OCTETS_OK }; #else +static __u32 fec_enet_register_version = 1; static u32 fec_enet_register_offset[] = { FEC_ECNTRL, FEC_IEVENT, FEC_IMASK, FEC_IVEC, FEC_R_DES_ACTIVE_0, FEC_R_DES_ACTIVE_1, FEC_R_DES_ACTIVE_2, FEC_X_DES_ACTIVE_0, @@ -2149,6 +2151,8 @@ static void fec_enet_get_regs(struct net_device *ndev, u32 *buf = (u32 *)regbuf; u32 i, off; + regs->version = fec_enet_register_version; + memset(buf, 0, regs->len); for (i = 0; i < ARRAY_SIZE(fec_enet_register_offset); i++) { diff --git a/drivers/net/ethernet/freescale/fec_mpc52xx.c b/drivers/net/ethernet/freescale/fec_mpc52xx.c index b90bab72efdb..c1968b3ecec8 100644 --- a/drivers/net/ethernet/freescale/fec_mpc52xx.c +++ b/drivers/net/ethernet/freescale/fec_mpc52xx.c @@ -369,7 +369,7 @@ static irqreturn_t mpc52xx_fec_tx_interrupt(int irq, void *dev_id) dma_unmap_single(dev->dev.parent, bd->skb_pa, skb->len, DMA_TO_DEVICE); - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); } spin_unlock(&priv->lock); diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c index 241325c35cb4..27ed995f439a 100644 --- a/drivers/net/ethernet/freescale/gianfar_ethtool.c +++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c @@ -1492,7 +1492,7 @@ static int gfar_get_ts_info(struct net_device *dev, struct gfar_private *priv = netdev_priv(dev); struct platform_device *ptp_dev; struct device_node *ptp_node; - struct qoriq_ptp *ptp = NULL; + struct ptp_qoriq *ptp = NULL; info->phc_index = -1; diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c index c3d539e209ed..eb3e65e8868f 100644 --- a/drivers/net/ethernet/freescale/ucc_geth.c +++ b/drivers/net/ethernet/freescale/ucc_geth.c @@ -1879,6 +1879,8 @@ static void ucc_geth_free_tx(struct ucc_geth_private *ugeth) u16 i, j; u8 __iomem *bd; + netdev_reset_queue(ugeth->ndev); + ug_info = ugeth->ug_info; uf_info = &ug_info->uf_info; diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c index 3b9e74be5fbd..b8155f5e71b4 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c @@ -3081,6 +3081,7 @@ int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset) dsaf_dev = dev_get_drvdata(&pdev->dev); if (!dsaf_dev) { dev_err(&pdev->dev, "dsaf_dev is NULL\n"); + put_device(&pdev->dev); return -ENODEV; } @@ -3088,6 +3089,7 @@ int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset) if (AE_IS_VER1(dsaf_dev->dsaf_ver)) { dev_err(dsaf_dev->dev, "%s v1 chip doesn't support RoCE!\n", dsaf_dev->ae_dev.name); + put_device(&pdev->dev); return -ENODEV; } diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 5b33238c6680..60e7d7ae3787 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -2418,6 +2418,8 @@ static int hns_nic_dev_probe(struct platform_device *pdev) out_notify_fail: (void)cancel_work_sync(&priv->service_task); out_read_prop_fail: + /* safe for ACPI FW */ + of_node_put(to_of_node(priv->fwnode)); free_netdev(ndev); return ret; } @@ -2447,6 +2449,9 @@ static int hns_nic_dev_remove(struct platform_device *pdev) set_bit(NIC_STATE_REMOVING, &priv->state); (void)cancel_work_sync(&priv->service_task); + /* safe for ACPI FW */ + of_node_put(to_of_node(priv->fwnode)); + free_netdev(ndev); return 0; } diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c index 8e9b95871d30..ce15d2350db9 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c @@ -1157,16 +1157,18 @@ static int hns_get_regs_len(struct net_device *net_dev) */ static int hns_nic_nway_reset(struct net_device *netdev) { - int ret = 0; struct phy_device *phy = netdev->phydev; - if (netif_running(netdev)) { - /* if autoneg is disabled, don't restart auto-negotiation */ - if (phy && phy->autoneg == AUTONEG_ENABLE) - ret = genphy_restart_aneg(phy); - } + if (!netif_running(netdev)) + return 0; - return ret; + if (!phy) + return -EOPNOTSUPP; + + if (phy->autoneg != AUTONEG_ENABLE) + return -EINVAL; + + return genphy_restart_aneg(phy); } static u32 diff --git a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h index 691d12174902..53089cd980d9 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h +++ b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h @@ -40,6 +40,8 @@ enum HCLGE_MBX_OPCODE { HCLGE_MBX_SET_ALIVE, /* (VF -> PF) set alive state */ HCLGE_MBX_SET_MTU, /* (VF -> PF) set mtu */ HCLGE_MBX_GET_QID_IN_PF, /* (VF -> PF) get queue id in pf */ + HCLGE_MBX_LINK_STAT_MODE, /* (PF -> VF) link mode has changed */ + HCLGE_MBX_GET_LINK_MODE, /* (VF -> PF) get the link mode of pf */ }; /* below are per-VF mac-vlan subcodes */ @@ -60,7 +62,7 @@ enum hclge_mbx_vlan_cfg_subcode { }; #define HCLGE_MBX_MAX_MSG_SIZE 16 -#define HCLGE_MBX_MAX_RESP_DATA_SIZE 8 +#define HCLGE_MBX_MAX_RESP_DATA_SIZE 16 #define HCLGE_MBX_RING_MAP_BASIC_MSG_NUM 3 #define HCLGE_MBX_RING_NODE_VARIABLE_NUM 3 diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.c b/drivers/net/ethernet/hisilicon/hns3/hnae3.c index 781e5dee3c70..50011aafbae4 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.c +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.c @@ -238,7 +238,7 @@ EXPORT_SYMBOL(hnae3_unregister_ae_algo); * @ae_dev: the AE device * NOTE: the duplicated name will not be checked */ -void hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev) +int hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev) { const struct pci_device_id *id; struct hnae3_ae_algo *ae_algo; @@ -259,6 +259,7 @@ void hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev) if (!ae_dev->ops) { dev_err(&ae_dev->pdev->dev, "ae_dev ops are null\n"); + ret = -EOPNOTSUPP; goto out_err; } @@ -285,8 +286,15 @@ void hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev) ret); } + mutex_unlock(&hnae3_common_lock); + + return 0; + out_err: + list_del(&ae_dev->node); mutex_unlock(&hnae3_common_lock); + + return ret; } EXPORT_SYMBOL(hnae3_register_ae_dev); diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index 585800e634e6..10f1cc2ba157 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -461,9 +461,11 @@ struct hnae3_ae_ops { bool (*get_hw_reset_stat)(struct hnae3_handle *handle); bool (*ae_dev_resetting)(struct hnae3_handle *handle); unsigned long (*ae_dev_reset_cnt)(struct hnae3_handle *handle); - int (*set_gro_en)(struct hnae3_handle *handle, int enable); + int (*set_gro_en)(struct hnae3_handle *handle, bool enable); u16 (*get_global_queue_id)(struct hnae3_handle *handle, u16 queue_id); void (*set_timer_task)(struct hnae3_handle *handle, bool enable); + int (*mac_connect_phy)(struct hnae3_handle *handle); + void (*mac_disconnect_phy)(struct hnae3_handle *handle); }; struct hnae3_dcb_ops { @@ -587,7 +589,7 @@ struct hnae3_handle { #define hnae3_get_bit(origin, shift) \ hnae3_get_field((origin), (0x1 << (shift)), (shift)) -void hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev); +int hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev); void hnae3_unregister_ae_dev(struct hnae3_ae_dev *ae_dev); void hnae3_unregister_ae_algo(struct hnae3_ae_algo *ae_algo); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 4b38c37eef8f..40b17223ee41 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -655,11 +655,7 @@ static int hns3_set_tso(struct sk_buff *skb, u32 *paylen, static int hns3_get_l4_protocol(struct sk_buff *skb, u8 *ol4_proto, u8 *il4_proto) { - union { - struct iphdr *v4; - struct ipv6hdr *v6; - unsigned char *hdr; - } l3; + union l3_hdr_info l3; unsigned char *l4_hdr; unsigned char *exthdr; u8 l4_proto_tmp; @@ -712,17 +708,8 @@ static void hns3_set_l2l3l4_len(struct sk_buff *skb, u8 ol4_proto, u8 il4_proto, u32 *type_cs_vlan_tso, u32 *ol_type_vlan_len_msec) { - union { - struct iphdr *v4; - struct ipv6hdr *v6; - unsigned char *hdr; - } l3; - union { - struct tcphdr *tcp; - struct udphdr *udp; - struct gre_base_hdr *gre; - unsigned char *hdr; - } l4; + union l3_hdr_info l3; + union l4_hdr_info l4; unsigned char *l2_hdr; u8 l4_proto = ol4_proto; u32 ol2_len; @@ -821,12 +808,7 @@ static void hns3_set_l2l3l4_len(struct sk_buff *skb, u8 ol4_proto, static bool hns3_tunnel_csum_bug(struct sk_buff *skb) { #define IANA_VXLAN_PORT 4789 - union { - struct tcphdr *tcp; - struct udphdr *udp; - struct gre_base_hdr *gre; - unsigned char *hdr; - } l4; + union l4_hdr_info l4; l4.hdr = skb_transport_header(skb); @@ -842,11 +824,7 @@ static int hns3_set_l3l4_type_csum(struct sk_buff *skb, u8 ol4_proto, u8 il4_proto, u32 *type_cs_vlan_tso, u32 *ol_type_vlan_len_msec) { - union { - struct iphdr *v4; - struct ipv6hdr *v6; - unsigned char *hdr; - } l3; + union l3_hdr_info l3; u32 l4_proto = ol4_proto; l3.hdr = skb_network_header(skb); @@ -1371,6 +1349,7 @@ static int hns3_nic_set_features(struct net_device *netdev, netdev_features_t changed = netdev->features ^ features; struct hns3_nic_priv *priv = netdev_priv(netdev); struct hnae3_handle *h = priv->ae_handle; + bool enable; int ret; if (changed & (NETIF_F_TSO | NETIF_F_TSO6)) { @@ -1381,38 +1360,29 @@ static int hns3_nic_set_features(struct net_device *netdev, } if (changed & (NETIF_F_GRO_HW) && h->ae_algo->ops->set_gro_en) { - if (features & NETIF_F_GRO_HW) - ret = h->ae_algo->ops->set_gro_en(h, true); - else - ret = h->ae_algo->ops->set_gro_en(h, false); + enable = !!(features & NETIF_F_GRO_HW); + ret = h->ae_algo->ops->set_gro_en(h, enable); if (ret) return ret; } if ((changed & NETIF_F_HW_VLAN_CTAG_FILTER) && h->ae_algo->ops->enable_vlan_filter) { - if (features & NETIF_F_HW_VLAN_CTAG_FILTER) - h->ae_algo->ops->enable_vlan_filter(h, true); - else - h->ae_algo->ops->enable_vlan_filter(h, false); + enable = !!(features & NETIF_F_HW_VLAN_CTAG_FILTER); + h->ae_algo->ops->enable_vlan_filter(h, enable); } if ((changed & NETIF_F_HW_VLAN_CTAG_RX) && h->ae_algo->ops->enable_hw_strip_rxvtag) { - if (features & NETIF_F_HW_VLAN_CTAG_RX) - ret = h->ae_algo->ops->enable_hw_strip_rxvtag(h, true); - else - ret = h->ae_algo->ops->enable_hw_strip_rxvtag(h, false); - + enable = !!(features & NETIF_F_HW_VLAN_CTAG_RX); + ret = h->ae_algo->ops->enable_hw_strip_rxvtag(h, enable); if (ret) return ret; } if ((changed & NETIF_F_NTUPLE) && h->ae_algo->ops->enable_fd) { - if (features & NETIF_F_NTUPLE) - h->ae_algo->ops->enable_fd(h, true); - else - h->ae_algo->ops->enable_fd(h, false); + enable = !!(features & NETIF_F_NTUPLE); + h->ae_algo->ops->enable_fd(h, enable); } netdev->features = features; @@ -1774,9 +1744,13 @@ static int hns3_probe(struct pci_dev *pdev, const struct pci_device_id *ent) hns3_get_dev_capability(pdev, ae_dev); pci_set_drvdata(pdev, ae_dev); - hnae3_register_ae_dev(ae_dev); + ret = hnae3_register_ae_dev(ae_dev); + if (ret) { + devm_kfree(&pdev->dev, ae_dev); + pci_set_drvdata(pdev, NULL); + } - return 0; + return ret; } /* hns3_remove - Device removal routine @@ -1955,8 +1929,7 @@ static void hns3_set_default_feature(struct net_device *netdev) NETIF_F_GSO_UDP_TUNNEL_CSUM | NETIF_F_SCTP_CRC; if (pdev->revision >= 0x21) { - netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER | - NETIF_F_GRO_HW; + netdev->hw_features |= NETIF_F_GRO_HW; netdev->features |= NETIF_F_GRO_HW; if (!(h->flags & HNAE3_SUPPORT_VF)) { @@ -2795,7 +2768,7 @@ static bool hns3_get_new_int_gl(struct hns3_enet_ring_group *ring_group) u32 time_passed_ms; u16 new_int_gl; - if (!ring_group->coal.int_gl || !tqp_vector->last_jiffies) + if (!tqp_vector->last_jiffies) return false; if (ring_group->total_packets == 0) { @@ -2898,7 +2871,7 @@ static void hns3_update_new_int_gl(struct hns3_enet_tqp_vector *tqp_vector) } if (tx_group->coal.gl_adapt_enable) { - tx_update = hns3_get_new_int_gl(&tqp_vector->tx_group); + tx_update = hns3_get_new_int_gl(tx_group); if (tx_update) hns3_set_vector_coalesce_tx_gl(tqp_vector, tx_group->coal.int_gl); @@ -3201,12 +3174,12 @@ static void hns3_clear_ring_group(struct hns3_enet_ring_group *group) group->count = 0; } -static int hns3_nic_uninit_vector_data(struct hns3_nic_priv *priv) +static void hns3_nic_uninit_vector_data(struct hns3_nic_priv *priv) { struct hnae3_ring_chain_node vector_ring_chain; struct hnae3_handle *h = priv->ae_handle; struct hns3_enet_tqp_vector *tqp_vector; - int i, ret; + int i; for (i = 0; i < priv->vector_num; i++) { tqp_vector = &priv->tqp_vector[i]; @@ -3214,15 +3187,10 @@ static int hns3_nic_uninit_vector_data(struct hns3_nic_priv *priv) if (!tqp_vector->rx_group.ring && !tqp_vector->tx_group.ring) continue; - ret = hns3_get_vector_ring_chain(tqp_vector, - &vector_ring_chain); - if (ret) - return ret; + hns3_get_vector_ring_chain(tqp_vector, &vector_ring_chain); - ret = h->ae_algo->ops->unmap_ring_from_vector(h, + h->ae_algo->ops->unmap_ring_from_vector(h, tqp_vector->vector_irq, &vector_ring_chain); - if (ret) - return ret; hns3_free_vector_ring_chain(tqp_vector, &vector_ring_chain); @@ -3238,8 +3206,6 @@ static int hns3_nic_uninit_vector_data(struct hns3_nic_priv *priv) hns3_clear_ring_group(&tqp_vector->tx_group); netif_napi_del(&priv->tqp_vector[i].napi); } - - return 0; } static int hns3_nic_dealloc_vector_data(struct hns3_nic_priv *priv) @@ -3549,6 +3515,25 @@ static int hns3_init_mac_addr(struct net_device *netdev, bool init) return ret; } +static int hns3_init_phy(struct net_device *netdev) +{ + struct hnae3_handle *h = hns3_get_handle(netdev); + int ret = 0; + + if (h->ae_algo->ops->mac_connect_phy) + ret = h->ae_algo->ops->mac_connect_phy(h); + + return ret; +} + +static void hns3_uninit_phy(struct net_device *netdev) +{ + struct hnae3_handle *h = hns3_get_handle(netdev); + + if (h->ae_algo->ops->mac_disconnect_phy) + h->ae_algo->ops->mac_disconnect_phy(h); +} + static int hns3_restore_fd_rules(struct net_device *netdev) { struct hnae3_handle *h = hns3_get_handle(netdev); @@ -3658,6 +3643,10 @@ static int hns3_client_init(struct hnae3_handle *handle) goto out_init_ring_data; } + ret = hns3_init_phy(netdev); + if (ret) + goto out_init_phy; + ret = register_netdev(netdev); if (ret) { dev_err(priv->dev, "probe register netdev fail!\n"); @@ -3682,8 +3671,11 @@ static int hns3_client_init(struct hnae3_handle *handle) return ret; out_reg_netdev_fail: + hns3_uninit_phy(netdev); +out_init_phy: + hns3_uninit_all_ring(priv); out_init_ring_data: - (void)hns3_nic_uninit_vector_data(priv); + hns3_nic_uninit_vector_data(priv); out_init_vector_data: hns3_nic_dealloc_vector_data(priv); out_alloc_vector_data: @@ -3716,9 +3708,9 @@ static void hns3_client_uninit(struct hnae3_handle *handle, bool reset) hns3_force_clear_all_rx_ring(handle); - ret = hns3_nic_uninit_vector_data(priv); - if (ret) - netdev_err(netdev, "uninit vector error\n"); + hns3_uninit_phy(netdev); + + hns3_nic_uninit_vector_data(priv); ret = hns3_nic_dealloc_vector_data(priv); if (ret) @@ -4111,11 +4103,7 @@ static int hns3_reset_notify_uninit_enet(struct hnae3_handle *handle) hns3_force_clear_all_rx_ring(handle); - ret = hns3_nic_uninit_vector_data(priv); - if (ret) { - netdev_err(netdev, "uninit vector error\n"); - return ret; - } + hns3_nic_uninit_vector_data(priv); hns3_store_coal(priv); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h index f3d248626ab3..71ff8f4d6c18 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h @@ -574,6 +574,7 @@ union l3_hdr_info { union l4_hdr_info { struct tcphdr *tcp; struct udphdr *udp; + struct gre_base_hdr *gre; unsigned char *hdr; }; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index ed73f7fc9171..63f5f56bda94 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -805,7 +805,7 @@ static int hns3_set_ringparam(struct net_device *ndev, old_desc_num, new_desc_num); if (if_running) - dev_close(ndev); + ndev->netdev_ops->ndo_stop(ndev); ret = hns3_uninit_all_ring(priv); if (ret) @@ -822,7 +822,7 @@ static int hns3_set_ringparam(struct net_device *ndev, } if (if_running) - ret = dev_open(ndev, NULL); + ret = ndev->netdev_ops->ndo_open(ndev); return ret; } @@ -1115,6 +1115,8 @@ static const struct ethtool_ops hns3vf_ethtool_ops = { .get_channels = hns3_get_channels, .get_coalesce = hns3_get_coalesce, .set_coalesce = hns3_set_coalesce, + .get_regs_len = hns3_get_regs_len, + .get_regs = hns3_get_regs, .get_link = hns3_get_link, }; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c index 81dbe1b6abb0..1dddfcba41a9 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c @@ -186,6 +186,38 @@ static bool hclge_is_special_opcode(u16 opcode) return false; } +static int hclge_cmd_check_retval(struct hclge_hw *hw, struct hclge_desc *desc, + int num, int ntc) +{ + u16 opcode, desc_ret; + int handle; + int retval; + + opcode = le16_to_cpu(desc[0].opcode); + for (handle = 0; handle < num; handle++) { + desc[handle] = hw->cmq.csq.desc[ntc]; + ntc++; + if (ntc >= hw->cmq.csq.desc_num) + ntc = 0; + } + if (likely(!hclge_is_special_opcode(opcode))) + desc_ret = le16_to_cpu(desc[num - 1].retval); + else + desc_ret = le16_to_cpu(desc[0].retval); + + if (desc_ret == HCLGE_CMD_EXEC_SUCCESS) + retval = 0; + else if (desc_ret == HCLGE_CMD_NO_AUTH) + retval = -EPERM; + else if (desc_ret == HCLGE_CMD_NOT_SUPPORTED) + retval = -EOPNOTSUPP; + else + retval = -EIO; + hw->cmq.last_status = desc_ret; + + return retval; +} + /** * hclge_cmd_send - send command to command queue * @hw: pointer to the hw struct @@ -203,7 +235,6 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num) u32 timeout = 0; int handle = 0; int retval = 0; - u16 opcode, desc_ret; int ntc; spin_lock_bh(&hw->cmq.csq.lock); @@ -219,12 +250,11 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num) * which will be use for hardware to write back */ ntc = hw->cmq.csq.next_to_use; - opcode = le16_to_cpu(desc[0].opcode); while (handle < num) { desc_to_use = &hw->cmq.csq.desc[hw->cmq.csq.next_to_use]; *desc_to_use = desc[handle]; (hw->cmq.csq.next_to_use)++; - if (hw->cmq.csq.next_to_use == hw->cmq.csq.desc_num) + if (hw->cmq.csq.next_to_use >= hw->cmq.csq.desc_num) hw->cmq.csq.next_to_use = 0; handle++; } @@ -250,31 +280,7 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num) if (!complete) { retval = -EAGAIN; } else { - handle = 0; - while (handle < num) { - /* Get the result of hardware write back */ - desc_to_use = &hw->cmq.csq.desc[ntc]; - desc[handle] = *desc_to_use; - - if (likely(!hclge_is_special_opcode(opcode))) - desc_ret = le16_to_cpu(desc[handle].retval); - else - desc_ret = le16_to_cpu(desc[0].retval); - - if (desc_ret == HCLGE_CMD_EXEC_SUCCESS) - retval = 0; - else if (desc_ret == HCLGE_CMD_NO_AUTH) - retval = -EPERM; - else if (desc_ret == HCLGE_CMD_NOT_SUPPORTED) - retval = -EOPNOTSUPP; - else - retval = -EIO; - hw->cmq.last_status = desc_ret; - ntc++; - handle++; - if (ntc == hw->cmq.csq.desc_num) - ntc = 0; - } + retval = hclge_cmd_check_retval(hw, desc, num, ntc); } /* Clean the command send queue */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h index e26a25128693..ac2cd219a9fb 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h @@ -312,16 +312,16 @@ struct hclge_ctrl_vector_chain_cmd { u8 rsv; }; -#define HCLGE_TC_NUM 8 +#define HCLGE_MAX_TC_NUM 8 #define HCLGE_TC0_PRI_BUF_EN_B 15 /* Bit 15 indicate enable or not */ #define HCLGE_BUF_UNIT_S 7 /* Buf size is united by 128 bytes */ struct hclge_tx_buff_alloc_cmd { - __le16 tx_pkt_buff[HCLGE_TC_NUM]; + __le16 tx_pkt_buff[HCLGE_MAX_TC_NUM]; u8 tx_buff_rsv[8]; }; struct hclge_rx_priv_buff_cmd { - __le16 buf_num[HCLGE_TC_NUM]; + __le16 buf_num[HCLGE_MAX_TC_NUM]; __le16 shared_buf; u8 rsv[6]; }; @@ -367,7 +367,6 @@ struct hclge_priv_buf { u32 enable; /* Enable TC private buffer or not */ }; -#define HCLGE_MAX_TC_NUM 8 struct hclge_shared_buf { struct hclge_waterline self; struct hclge_tc_thrd tc_thrd[HCLGE_MAX_TC_NUM]; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c index 961aedb0e20f..1161361a973b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c @@ -93,13 +93,11 @@ static int hclge_dcb_common_validate(struct hclge_dev *hdev, u8 num_tc, } } - for (i = 0; i < hdev->num_alloc_vport; i++) { - if (num_tc > hdev->vport[i].alloc_tqps) { - dev_err(&hdev->pdev->dev, - "allocated tqp(%u) checking failed, %u > tqp(%u)\n", - i, num_tc, hdev->vport[i].alloc_tqps); - return -EINVAL; - } + if (num_tc > hdev->vport[0].alloc_tqps) { + dev_err(&hdev->pdev->dev, + "allocated tqp checking failed, %u > tqp(%u)\n", + num_tc, hdev->vport[0].alloc_tqps); + return -EINVAL; } return 0; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c index 26d80504c730..1192cf6f2321 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c @@ -691,7 +691,7 @@ static void hclge_dbg_dump_qos_buf_cfg(struct hclge_dev *hdev) dev_info(&hdev->pdev->dev, "dump qos buf cfg\n"); tx_buf_cmd = (struct hclge_tx_buff_alloc_cmd *)desc[0].data; - for (i = 0; i < HCLGE_TC_NUM; i++) + for (i = 0; i < HCLGE_MAX_TC_NUM; i++) dev_info(&hdev->pdev->dev, "tx_packet_buf_tc_%d: 0x%x\n", i, tx_buf_cmd->tx_pkt_buff[i]); @@ -703,7 +703,7 @@ static void hclge_dbg_dump_qos_buf_cfg(struct hclge_dev *hdev) dev_info(&hdev->pdev->dev, "\n"); rx_buf_cmd = (struct hclge_rx_priv_buff_cmd *)desc[0].data; - for (i = 0; i < HCLGE_TC_NUM; i++) + for (i = 0; i < HCLGE_MAX_TC_NUM; i++) dev_info(&hdev->pdev->dev, "rx_packet_buf_tc_%d: 0x%x\n", i, rx_buf_cmd->buf_num[i]); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index ae8336c18264..75ec3094bbf9 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -295,6 +295,14 @@ static const struct hclge_mac_mgr_tbl_entry_cmd hclge_mgr_table[] = { }, }; +static const u8 hclge_hash_key[] = { + 0x6D, 0x5A, 0x56, 0xDA, 0x25, 0x5B, 0x0E, 0xC2, + 0x41, 0x67, 0x25, 0x3D, 0x43, 0xA3, 0x8F, 0xB0, + 0xD0, 0xCA, 0x2B, 0xCB, 0xAE, 0x7B, 0x30, 0xB4, + 0x77, 0xCB, 0x2D, 0xA3, 0x80, 0x30, 0xF2, 0x0C, + 0x6A, 0x42, 0xB7, 0x3B, 0xBE, 0xAC, 0x01, 0xFA +}; + static int hclge_mac_update_stats_defective(struct hclge_dev *hdev) { #define HCLGE_MAC_CMD_NUM 21 @@ -343,6 +351,8 @@ static int hclge_mac_update_stats_complete(struct hclge_dev *hdev, u32 desc_num) int ret; desc = kcalloc(desc_num, sizeof(struct hclge_desc), GFP_KERNEL); + if (!desc) + return -ENOMEM; hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_STATS_MAC_ALL, true); ret = hclge_cmd_send(&hdev->hw, desc, desc_num); if (ret) { @@ -999,6 +1009,9 @@ static int hclge_configure(struct hclge_dev *hdev) hdev->tm_info.hw_pfc_map = 0; hdev->wanted_umv_size = cfg.umv_space; + if (hnae3_dev_fd_supported(hdev)) + hdev->fd_en = true; + ret = hclge_parse_speed(cfg.default_speed, &hdev->hw.mac.speed); if (ret) { dev_err(&hdev->pdev->dev, "Get wrong speed ret=%d.\n", ret); @@ -1318,7 +1331,7 @@ static int hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev, req = (struct hclge_tx_buff_alloc_cmd *)desc.data; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_TX_BUFF_ALLOC, 0); - for (i = 0; i < HCLGE_TC_NUM; i++) { + for (i = 0; i < HCLGE_MAX_TC_NUM; i++) { u32 buf_size = buf_alloc->priv_buf[i].tx_buf_size; req->tx_pkt_buff[i] = @@ -1493,13 +1506,14 @@ static int hclge_tx_buffer_calc(struct hclge_dev *hdev, for (i = 0; i < HCLGE_MAX_TC_NUM; i++) { struct hclge_priv_buf *priv = &buf_alloc->priv_buf[i]; - if (total_size < hdev->tx_buf_size) - return -ENOMEM; + if (hdev->hw_tc_map & BIT(i)) { + if (total_size < hdev->tx_buf_size) + return -ENOMEM; - if (hdev->hw_tc_map & BIT(i)) priv->tx_buf_size = hdev->tx_buf_size; - else + } else { priv->tx_buf_size = 0; + } total_size -= priv->tx_buf_size; } @@ -1507,66 +1521,15 @@ static int hclge_tx_buffer_calc(struct hclge_dev *hdev, return 0; } -/* hclge_rx_buffer_calc: calculate the rx private buffer size for all TCs - * @hdev: pointer to struct hclge_dev - * @buf_alloc: pointer to buffer calculation data - * @return: 0: calculate sucessful, negative: fail - */ -static int hclge_rx_buffer_calc(struct hclge_dev *hdev, - struct hclge_pkt_buf_alloc *buf_alloc) +static bool hclge_rx_buf_calc_all(struct hclge_dev *hdev, bool max, + struct hclge_pkt_buf_alloc *buf_alloc) { - u32 rx_all = hdev->pkt_buf_size, aligned_mps; - int no_pfc_priv_num, pfc_priv_num; - struct hclge_priv_buf *priv; + u32 rx_all = hdev->pkt_buf_size - hclge_get_tx_buff_alloced(buf_alloc); + u32 aligned_mps = round_up(hdev->mps, HCLGE_BUF_SIZE_UNIT); int i; - aligned_mps = round_up(hdev->mps, HCLGE_BUF_SIZE_UNIT); - rx_all -= hclge_get_tx_buff_alloced(buf_alloc); - - /* When DCB is not supported, rx private - * buffer is not allocated. - */ - if (!hnae3_dev_dcb_supported(hdev)) { - if (!hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all)) - return -ENOMEM; - - return 0; - } - - /* step 1, try to alloc private buffer for all enabled tc */ - for (i = 0; i < HCLGE_MAX_TC_NUM; i++) { - priv = &buf_alloc->priv_buf[i]; - if (hdev->hw_tc_map & BIT(i)) { - priv->enable = 1; - if (hdev->tm_info.hw_pfc_map & BIT(i)) { - priv->wl.low = aligned_mps; - priv->wl.high = - roundup(priv->wl.low + aligned_mps, - HCLGE_BUF_SIZE_UNIT); - priv->buf_size = priv->wl.high + - hdev->dv_buf_size; - } else { - priv->wl.low = 0; - priv->wl.high = 2 * aligned_mps; - priv->buf_size = priv->wl.high + - hdev->dv_buf_size; - } - } else { - priv->enable = 0; - priv->wl.low = 0; - priv->wl.high = 0; - priv->buf_size = 0; - } - } - - if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all)) - return 0; - - /* step 2, try to decrease the buffer size of - * no pfc TC's private buffer - */ for (i = 0; i < HCLGE_MAX_TC_NUM; i++) { - priv = &buf_alloc->priv_buf[i]; + struct hclge_priv_buf *priv = &buf_alloc->priv_buf[i]; priv->enable = 0; priv->wl.low = 0; @@ -1579,28 +1542,30 @@ static int hclge_rx_buffer_calc(struct hclge_dev *hdev, priv->enable = 1; if (hdev->tm_info.hw_pfc_map & BIT(i)) { - priv->wl.low = 256; - priv->wl.high = priv->wl.low + aligned_mps; - priv->buf_size = priv->wl.high + hdev->dv_buf_size; + priv->wl.low = max ? aligned_mps : 256; + priv->wl.high = roundup(priv->wl.low + aligned_mps, + HCLGE_BUF_SIZE_UNIT); } else { priv->wl.low = 0; - priv->wl.high = aligned_mps; - priv->buf_size = priv->wl.high + hdev->dv_buf_size; + priv->wl.high = max ? (aligned_mps * 2) : aligned_mps; } + + priv->buf_size = priv->wl.high + hdev->dv_buf_size; } - if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all)) - return 0; + return hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all); +} - /* step 3, try to reduce the number of pfc disabled TCs, - * which have private buffer - */ - /* get the total no pfc enable TC number, which have private buffer */ - no_pfc_priv_num = hclge_get_no_pfc_priv_num(hdev, buf_alloc); +static bool hclge_drop_nopfc_buf_till_fit(struct hclge_dev *hdev, + struct hclge_pkt_buf_alloc *buf_alloc) +{ + u32 rx_all = hdev->pkt_buf_size - hclge_get_tx_buff_alloced(buf_alloc); + int no_pfc_priv_num = hclge_get_no_pfc_priv_num(hdev, buf_alloc); + int i; /* let the last to be cleared first */ for (i = HCLGE_MAX_TC_NUM - 1; i >= 0; i--) { - priv = &buf_alloc->priv_buf[i]; + struct hclge_priv_buf *priv = &buf_alloc->priv_buf[i]; if (hdev->hw_tc_map & BIT(i) && !(hdev->tm_info.hw_pfc_map & BIT(i))) { @@ -1617,17 +1582,19 @@ static int hclge_rx_buffer_calc(struct hclge_dev *hdev, break; } - if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all)) - return 0; + return hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all); +} - /* step 4, try to reduce the number of pfc enabled TCs - * which have private buffer. - */ - pfc_priv_num = hclge_get_pfc_priv_num(hdev, buf_alloc); +static bool hclge_drop_pfc_buf_till_fit(struct hclge_dev *hdev, + struct hclge_pkt_buf_alloc *buf_alloc) +{ + u32 rx_all = hdev->pkt_buf_size - hclge_get_tx_buff_alloced(buf_alloc); + int pfc_priv_num = hclge_get_pfc_priv_num(hdev, buf_alloc); + int i; /* let the last to be cleared first */ for (i = HCLGE_MAX_TC_NUM - 1; i >= 0; i--) { - priv = &buf_alloc->priv_buf[i]; + struct hclge_priv_buf *priv = &buf_alloc->priv_buf[i]; if (hdev->hw_tc_map & BIT(i) && hdev->tm_info.hw_pfc_map & BIT(i)) { @@ -1643,7 +1610,40 @@ static int hclge_rx_buffer_calc(struct hclge_dev *hdev, pfc_priv_num == 0) break; } - if (hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all)) + + return hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all); +} + +/* hclge_rx_buffer_calc: calculate the rx private buffer size for all TCs + * @hdev: pointer to struct hclge_dev + * @buf_alloc: pointer to buffer calculation data + * @return: 0: calculate sucessful, negative: fail + */ +static int hclge_rx_buffer_calc(struct hclge_dev *hdev, + struct hclge_pkt_buf_alloc *buf_alloc) +{ + /* When DCB is not supported, rx private buffer is not allocated. */ + if (!hnae3_dev_dcb_supported(hdev)) { + u32 rx_all = hdev->pkt_buf_size; + + rx_all -= hclge_get_tx_buff_alloced(buf_alloc); + if (!hclge_is_rx_buf_ok(hdev, buf_alloc, rx_all)) + return -ENOMEM; + + return 0; + } + + if (hclge_rx_buf_calc_all(hdev, true, buf_alloc)) + return 0; + + /* try to decrease the buffer size */ + if (hclge_rx_buf_calc_all(hdev, false, buf_alloc)) + return 0; + + if (hclge_drop_nopfc_buf_till_fit(hdev, buf_alloc)) + return 0; + + if (hclge_drop_pfc_buf_till_fit(hdev, buf_alloc)) return 0; return -ENOMEM; @@ -2599,7 +2599,7 @@ static int hclge_set_vf_rst(struct hclge_dev *hdev, int func_id, bool reset) return hclge_cmd_send(&hdev->hw, &desc, 1); } -int hclge_set_all_vf_rst(struct hclge_dev *hdev, bool reset) +static int hclge_set_all_vf_rst(struct hclge_dev *hdev, bool reset) { int i; @@ -3652,8 +3652,11 @@ void hclge_rss_indir_init_cfg(struct hclge_dev *hdev) static void hclge_rss_init_cfg(struct hclge_dev *hdev) { + int i, rss_algo = HCLGE_RSS_HASH_ALGO_TOEPLITZ; struct hclge_vport *vport = hdev->vport; - int i; + + if (hdev->pdev->revision >= 0x21) + rss_algo = HCLGE_RSS_HASH_ALGO_SIMPLE; for (i = 0; i < hdev->num_vmdq_vport + 1; i++) { vport[i].rss_tuple_sets.ipv4_tcp_en = @@ -3673,9 +3676,10 @@ static void hclge_rss_init_cfg(struct hclge_dev *hdev) vport[i].rss_tuple_sets.ipv6_fragment_en = HCLGE_RSS_INPUT_TUPLE_OTHER; - vport[i].rss_algo = HCLGE_RSS_HASH_ALGO_TOEPLITZ; + vport[i].rss_algo = rss_algo; - netdev_rss_key_fill(vport[i].rss_hash_key, HCLGE_RSS_KEY_SIZE); + memcpy(vport[i].rss_hash_key, hclge_hash_key, + HCLGE_RSS_KEY_SIZE); } hclge_rss_indir_init_cfg(hdev); @@ -3961,7 +3965,6 @@ static int hclge_init_fd_config(struct hclge_dev *hdev) return -EOPNOTSUPP; } - hdev->fd_cfg.fd_en = true; hdev->fd_cfg.proto_support = TCP_V4_FLOW | UDP_V4_FLOW | SCTP_V4_FLOW | TCP_V6_FLOW | UDP_V6_FLOW | SCTP_V6_FLOW | IPV4_USER_FLOW | IPV6_USER_FLOW; @@ -4719,7 +4722,7 @@ static int hclge_add_fd_entry(struct hnae3_handle *handle, if (!hnae3_dev_fd_supported(hdev)) return -EOPNOTSUPP; - if (!hdev->fd_cfg.fd_en) { + if (!hdev->fd_en) { dev_warn(&hdev->pdev->dev, "Please enable flow director first\n"); return -EOPNOTSUPP; @@ -4872,7 +4875,7 @@ static int hclge_restore_fd_entries(struct hnae3_handle *handle) return 0; /* if fd is disabled, should not restore it when reset */ - if (!hdev->fd_cfg.fd_en) + if (!hdev->fd_en) return 0; hlist_for_each_entry_safe(rule, node, &hdev->fd_rule_list, rule_node) { @@ -5158,7 +5161,7 @@ static void hclge_enable_fd(struct hnae3_handle *handle, bool enable) struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_dev *hdev = vport->back; - hdev->fd_cfg.fd_en = enable; + hdev->fd_en = enable; if (!enable) hclge_del_all_fd_entries(handle, false); else @@ -5584,13 +5587,19 @@ static bool hclge_is_all_function_id_zero(struct hclge_desc *desc) } static void hclge_prepare_mac_addr(struct hclge_mac_vlan_tbl_entry_cmd *new_req, - const u8 *addr) + const u8 *addr, bool is_mc) { const unsigned char *mac_addr = addr; u32 high_val = mac_addr[2] << 16 | (mac_addr[3] << 24) | (mac_addr[0]) | (mac_addr[1] << 8); u32 low_val = mac_addr[4] | (mac_addr[5] << 8); + hnae3_set_bit(new_req->flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1); + if (is_mc) { + hnae3_set_bit(new_req->entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 1); + hnae3_set_bit(new_req->mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 1); + } + new_req->mac_addr_hi32 = cpu_to_le32(high_val); new_req->mac_addr_lo16 = cpu_to_le16(low_val & 0xffff); } @@ -5821,9 +5830,12 @@ static void hclge_update_umv_space(struct hclge_vport *vport, bool is_free) if (is_free) { if (vport->used_umv_num > hdev->priv_umv_size) hdev->share_umv_size++; - vport->used_umv_num--; + + if (vport->used_umv_num > 0) + vport->used_umv_num--; } else { - if (vport->used_umv_num >= hdev->priv_umv_size) + if (vport->used_umv_num >= hdev->priv_umv_size && + hdev->share_umv_size > 0) hdev->share_umv_size--; vport->used_umv_num++; } @@ -5861,14 +5873,13 @@ int hclge_add_uc_addr_common(struct hclge_vport *vport, } memset(&req, 0, sizeof(req)); - hnae3_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1); hnae3_set_field(egress_port, HCLGE_MAC_EPORT_VFID_M, HCLGE_MAC_EPORT_VFID_S, vport->vport_id); req.egress_port = cpu_to_le16(egress_port); - hclge_prepare_mac_addr(&req, addr); + hclge_prepare_mac_addr(&req, addr, false); /* Lookup the mac address in the mac_vlan table, and add * it if the entry is inexistent. Repeated unicast entry @@ -5926,9 +5937,8 @@ int hclge_rm_uc_addr_common(struct hclge_vport *vport, } memset(&req, 0, sizeof(req)); - hnae3_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1); hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0); - hclge_prepare_mac_addr(&req, addr); + hclge_prepare_mac_addr(&req, addr, false); ret = hclge_remove_mac_vlan_tbl(vport, &req); if (!ret) hclge_update_umv_space(vport, true); @@ -5960,11 +5970,8 @@ int hclge_add_mc_addr_common(struct hclge_vport *vport, return -EINVAL; } memset(&req, 0, sizeof(req)); - hnae3_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1); hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0); - hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 1); - hnae3_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 1); - hclge_prepare_mac_addr(&req, addr); + hclge_prepare_mac_addr(&req, addr, true); status = hclge_lookup_mac_vlan_tbl(vport, &req, desc, true); if (!status) { /* This mac addr exist, update VFID for it */ @@ -6010,11 +6017,8 @@ int hclge_rm_mc_addr_common(struct hclge_vport *vport, } memset(&req, 0, sizeof(req)); - hnae3_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1); hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0); - hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 1); - hnae3_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 1); - hclge_prepare_mac_addr(&req, addr); + hclge_prepare_mac_addr(&req, addr, true); status = hclge_lookup_mac_vlan_tbl(vport, &req, desc, true); if (!status) { /* This mac addr exist, remove this handle's VFID for it */ @@ -7050,16 +7054,6 @@ static void hclge_get_mdix_mode(struct hnae3_handle *handle, *tp_mdix = ETH_TP_MDI; } -static int hclge_init_instance_hw(struct hclge_dev *hdev) -{ - return hclge_mac_connect_phy(hdev); -} - -static void hclge_uninit_instance_hw(struct hclge_dev *hdev) -{ - hclge_mac_disconnect_phy(hdev); -} - static int hclge_init_client_instance(struct hnae3_client *client, struct hnae3_ae_dev *ae_dev) { @@ -7079,13 +7073,6 @@ static int hclge_init_client_instance(struct hnae3_client *client, if (ret) goto clear_nic; - ret = hclge_init_instance_hw(hdev); - if (ret) { - client->ops->uninit_instance(&vport->nic, - 0); - goto clear_nic; - } - hnae3_set_client_init_flag(client, ae_dev, 1); if (hdev->roce_client && @@ -7170,7 +7157,6 @@ static void hclge_uninit_client_instance(struct hnae3_client *client, if (client->type == HNAE3_CLIENT_ROCE) return; if (hdev->nic_client && client->ops->uninit_instance) { - hclge_uninit_instance_hw(hdev); client->ops->uninit_instance(&vport->nic, 0); hdev->nic_client = NULL; vport->nic.client = NULL; @@ -7389,7 +7375,7 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) ret = hclge_init_umv_space(hdev); if (ret) { dev_err(&pdev->dev, "umv space init error, ret=%d.\n", ret); - goto err_msi_irq_uninit; + goto err_mdiobus_unreg; } ret = hclge_mac_init(hdev); @@ -7991,7 +7977,7 @@ static void hclge_get_link_mode(struct hnae3_handle *handle, } } -static int hclge_gro_en(struct hnae3_handle *handle, int enable) +static int hclge_gro_en(struct hnae3_handle *handle, bool enable) { struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_dev *hdev = vport->back; @@ -8076,6 +8062,8 @@ static const struct hnae3_ae_ops hclge_ops = { .set_gro_en = hclge_gro_en, .get_global_queue_id = hclge_covert_handle_qid_global, .set_timer_task = hclge_set_timer_task, + .mac_connect_phy = hclge_mac_connect_phy, + .mac_disconnect_phy = hclge_mac_disconnect_phy, }; static struct hnae3_ae_algo ae_algo = { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index 2c413c63c6c9..c939f4a7f5f0 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -583,7 +583,6 @@ struct hclge_fd_key_cfg { struct hclge_fd_cfg { u8 fd_mode; - u8 fd_en; u16 max_key_length; u32 proto_support; u32 rule_num[2]; /* rule entry number */ @@ -758,6 +757,7 @@ struct hclge_dev { struct hclge_fd_cfg fd_cfg; struct hlist_head fd_rule_list; u16 hclge_fd_rule_num; + u8 fd_en; u16 wanted_umv_size; /* max available unicast mac vlan space */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index 3603034aa45c..7e4a104582d6 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -319,10 +319,14 @@ static int hclge_get_vf_tcinfo(struct hclge_vport *vport, struct hclge_mbx_vf_to_pf_cmd *mbx_req, bool gen_resp) { - struct hclge_dev *hdev = vport->back; - int ret; + struct hnae3_knic_private_info *kinfo = &vport->nic.kinfo; + u8 vf_tc_map = 0; + int i, ret; - ret = hclge_gen_resp_to_vf(vport, mbx_req, 0, &hdev->hw_tc_map, + for (i = 0; i < kinfo->num_tc; i++) + vf_tc_map |= BIT(i); + + ret = hclge_gen_resp_to_vf(vport, mbx_req, 0, &vf_tc_map, sizeof(u8)); return ret; @@ -351,16 +355,19 @@ static int hclge_get_link_info(struct hclge_vport *vport, { struct hclge_dev *hdev = vport->back; u16 link_status; - u8 msg_data[8]; + u8 msg_data[10]; + u16 media_type; u8 dest_vfid; u16 duplex; /* mac.link can only be 0 or 1 */ link_status = (u16)hdev->hw.mac.link; duplex = hdev->hw.mac.duplex; + media_type = hdev->hw.mac.media_type; memcpy(&msg_data[0], &link_status, sizeof(u16)); memcpy(&msg_data[2], &hdev->hw.mac.speed, sizeof(u32)); memcpy(&msg_data[6], &duplex, sizeof(u16)); + memcpy(&msg_data[8], &media_type, sizeof(u16)); dest_vfid = mbx_req->mbx_src_vfid; /* send this requested info to VF */ @@ -368,6 +375,29 @@ static int hclge_get_link_info(struct hclge_vport *vport, HCLGE_MBX_LINK_STAT_CHANGE, dest_vfid); } +static void hclge_get_link_mode(struct hclge_vport *vport, + struct hclge_mbx_vf_to_pf_cmd *mbx_req) +{ +#define HCLGE_SUPPORTED 1 + struct hclge_dev *hdev = vport->back; + unsigned long advertising; + unsigned long supported; + unsigned long send_data; + u8 msg_data[10]; + u8 dest_vfid; + + advertising = hdev->hw.mac.advertising[0]; + supported = hdev->hw.mac.supported[0]; + dest_vfid = mbx_req->mbx_src_vfid; + msg_data[0] = mbx_req->msg[2]; + + send_data = msg_data[0] == HCLGE_SUPPORTED ? supported : advertising; + + memcpy(&msg_data[2], &send_data, sizeof(unsigned long)); + hclge_send_mbx_msg(vport, msg_data, sizeof(msg_data), + HCLGE_MBX_LINK_STAT_MODE, dest_vfid); +} + static void hclge_mbx_reset_vf_queue(struct hclge_vport *vport, struct hclge_mbx_vf_to_pf_cmd *mbx_req) { @@ -552,6 +582,9 @@ void hclge_mbx_handler(struct hclge_dev *hdev) "PF failed(%d) to get qid for VF\n", ret); break; + case HCLGE_MBX_GET_LINK_MODE: + hclge_get_link_mode(vport, req); + break; default: dev_err(&hdev->pdev->dev, "un-supported mailbox message, code = %d\n", diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c index dabb8437f8dc..84f28785ba28 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c @@ -195,8 +195,10 @@ static void hclge_mac_adjust_link(struct net_device *netdev) netdev_err(netdev, "failed to configure flow control.\n"); } -int hclge_mac_connect_phy(struct hclge_dev *hdev) +int hclge_mac_connect_phy(struct hnae3_handle *handle) { + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; struct net_device *netdev = hdev->vport[0].nic.netdev; struct phy_device *phydev = hdev->hw.mac.phydev; __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; @@ -229,8 +231,10 @@ int hclge_mac_connect_phy(struct hclge_dev *hdev) return 0; } -void hclge_mac_disconnect_phy(struct hclge_dev *hdev) +void hclge_mac_disconnect_phy(struct hnae3_handle *handle) { + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; struct phy_device *phydev = hdev->hw.mac.phydev; if (!phydev) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h index 5fbf7dddb5d9..ef095d9c566f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h @@ -5,8 +5,8 @@ #define __HCLGE_MDIO_H int hclge_mac_mdio_config(struct hclge_dev *hdev); -int hclge_mac_connect_phy(struct hclge_dev *hdev); -void hclge_mac_disconnect_phy(struct hclge_dev *hdev); +int hclge_mac_connect_phy(struct hnae3_handle *handle); +void hclge_mac_disconnect_phy(struct hnae3_handle *handle); void hclge_mac_start_phy(struct hclge_dev *hdev); void hclge_mac_stop_phy(struct hclge_dev *hdev); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index 9f4069fb786b..aafc69f4bfdd 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -520,8 +520,14 @@ static void hclge_tm_vport_tc_info_update(struct hclge_vport *vport) u16 max_rss_size; u8 i; - vport->bw_limit = hdev->tm_info.pg_info[0].bw_limit; - kinfo->num_tc = min_t(u16, vport->alloc_tqps, hdev->tm_info.num_tc); + /* TC configuration is shared by PF/VF in one port, only allow + * one tc for VF for simplicity. VF's vport_id is non zero. + */ + kinfo->num_tc = vport->vport_id ? 1 : + min_t(u16, vport->alloc_tqps, hdev->tm_info.num_tc); + vport->qs_offset = (vport->vport_id ? hdev->tm_info.num_tc : 0) + + (vport->vport_id ? (vport->vport_id - 1) : 0); + max_rss_size = min_t(u16, hdev->rss_size_max, vport->alloc_tqps / kinfo->num_tc); @@ -538,12 +544,12 @@ static void hclge_tm_vport_tc_info_update(struct hclge_vport *vport) } kinfo->num_tqps = kinfo->num_tc * kinfo->rss_size; - vport->qs_offset = hdev->tm_info.num_tc * vport->vport_id; vport->dwrr = 100; /* 100 percent as init */ vport->alloc_rss_size = kinfo->rss_size; + vport->bw_limit = hdev->tm_info.pg_info[0].bw_limit; for (i = 0; i < HNAE3_MAX_TC; i++) { - if (hdev->hw_tc_map & BIT(i)) { + if (hdev->hw_tc_map & BIT(i) && i < kinfo->num_tc) { kinfo->tc_info[i].enable = true; kinfo->tc_info[i].tqp_offset = i * kinfo->rss_size; kinfo->tc_info[i].tqp_count = kinfo->rss_size; @@ -766,13 +772,17 @@ static int hclge_tm_pri_q_qs_cfg(struct hclge_dev *hdev) if (hdev->tx_sch_mode == HCLGE_FLAG_TC_BASE_SCH_MODE) { /* Cfg qs -> pri mapping, one by one mapping */ - for (k = 0; k < hdev->num_alloc_vport; k++) - for (i = 0; i < hdev->tm_info.num_tc; i++) { + for (k = 0; k < hdev->num_alloc_vport; k++) { + struct hnae3_knic_private_info *kinfo = + &vport[k].nic.kinfo; + + for (i = 0; i < kinfo->num_tc; i++) { ret = hclge_tm_qs_to_pri_map_cfg( hdev, vport[k].qs_offset + i, i); if (ret) return ret; } + } } else if (hdev->tx_sch_mode == HCLGE_FLAG_VNET_BASE_SCH_MODE) { /* Cfg qs -> pri mapping, qs = tc, pri = vf, 8 qs -> 1 pri */ for (k = 0; k < hdev->num_alloc_vport; k++) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index fc99a0c70164..4a897cfb573b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -21,6 +21,14 @@ static const struct pci_device_id ae_algovf_pci_tbl[] = { {0, } }; +static const u8 hclgevf_hash_key[] = { + 0x6D, 0x5A, 0x56, 0xDA, 0x25, 0x5B, 0x0E, 0xC2, + 0x41, 0x67, 0x25, 0x3D, 0x43, 0xA3, 0x8F, 0xB0, + 0xD0, 0xCA, 0x2B, 0xCB, 0xAE, 0x7B, 0x30, 0xB4, + 0x77, 0xCB, 0x2D, 0xA3, 0x80, 0x30, 0xF2, 0x0C, + 0x6A, 0x42, 0xB7, 0x3B, 0xBE, 0xAC, 0x01, 0xFA +}; + MODULE_DEVICE_TABLE(pci, ae_algovf_pci_tbl); static const u32 cmdq_reg_addr_list[] = {HCLGEVF_CMDQ_TX_ADDR_L_REG, @@ -78,7 +86,12 @@ static const u32 tqp_intr_reg_addr_list[] = {HCLGEVF_TQP_INTR_CTRL_REG, static inline struct hclgevf_dev *hclgevf_ae_get_hdev( struct hnae3_handle *handle) { - return container_of(handle, struct hclgevf_dev, nic); + if (!handle->client) + return container_of(handle, struct hclgevf_dev, nic); + else if (handle->client->type == HNAE3_CLIENT_ROCE) + return container_of(handle, struct hclgevf_dev, roce); + else + return container_of(handle, struct hclgevf_dev, nic); } static int hclgevf_tqps_update_stats(struct hnae3_handle *handle) @@ -368,6 +381,21 @@ void hclgevf_update_link_status(struct hclgevf_dev *hdev, int link_state) } } +void hclgevf_update_link_mode(struct hclgevf_dev *hdev) +{ +#define HCLGEVF_ADVERTISING 0 +#define HCLGEVF_SUPPORTED 1 + u8 send_msg; + u8 resp_msg; + + send_msg = HCLGEVF_ADVERTISING; + hclgevf_send_mbx_msg(hdev, HCLGE_MBX_GET_LINK_MODE, 0, &send_msg, + sizeof(u8), false, &resp_msg, sizeof(u8)); + send_msg = HCLGEVF_SUPPORTED; + hclgevf_send_mbx_msg(hdev, HCLGE_MBX_GET_LINK_MODE, 0, &send_msg, + sizeof(u8), false, &resp_msg, sizeof(u8)); +} + static int hclgevf_set_handle_info(struct hclgevf_dev *hdev) { struct hnae3_handle *nic = &hdev->nic; @@ -1611,6 +1639,10 @@ static void hclgevf_keep_alive_task(struct work_struct *work) int ret; hdev = container_of(work, struct hclgevf_dev, keep_alive_task); + + if (test_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state)) + return; + ret = hclgevf_send_mbx_msg(hdev, HCLGE_MBX_KEEP_ALIVE, 0, NULL, 0, false, &respmsg, sizeof(u8)); if (ret) @@ -1629,6 +1661,8 @@ static void hclgevf_service_task(struct work_struct *work) */ hclgevf_request_link_info(hdev); + hclgevf_update_link_mode(hdev); + hclgevf_deferred_task_schedule(hdev); clear_bit(HCLGEVF_STATE_SERVICE_SCHED, &hdev->state); @@ -1709,8 +1743,6 @@ static int hclgevf_configure(struct hclgevf_dev *hdev) { int ret; - hdev->hw.mac.media_type = HNAE3_MEDIA_TYPE_NONE; - /* get queue configuration from PF */ ret = hclgevf_get_queue_info(hdev); if (ret) @@ -1789,9 +1821,9 @@ static int hclgevf_rss_init_hw(struct hclgevf_dev *hdev) rss_cfg->rss_size = hdev->rss_size_max; if (hdev->pdev->revision >= 0x21) { - rss_cfg->hash_algo = HCLGEVF_RSS_HASH_ALGO_TOEPLITZ; - netdev_rss_key_fill(rss_cfg->rss_hash_key, - HCLGEVF_RSS_KEY_SIZE); + rss_cfg->hash_algo = HCLGEVF_RSS_HASH_ALGO_SIMPLE; + memcpy(rss_cfg->rss_hash_key, hclgevf_hash_key, + HCLGEVF_RSS_KEY_SIZE); ret = hclgevf_set_rss_algo_key(hdev, rss_cfg->hash_algo, rss_cfg->rss_hash_key); @@ -1863,6 +1895,8 @@ static int hclgevf_ae_start(struct hnae3_handle *handle) hclgevf_request_link_info(hdev); + hclgevf_update_link_mode(hdev); + clear_bit(HCLGEVF_STATE_DOWN, &hdev->state); return 0; @@ -2533,7 +2567,7 @@ void hclgevf_update_speed_duplex(struct hclgevf_dev *hdev, u32 speed, hdev->hw.mac.duplex = duplex; } -static int hclgevf_gro_en(struct hnae3_handle *handle, int enable) +static int hclgevf_gro_en(struct hnae3_handle *handle, bool enable) { struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); @@ -2569,6 +2603,16 @@ static unsigned long hclgevf_ae_dev_reset_cnt(struct hnae3_handle *handle) return hdev->reset_count; } +static void hclgevf_get_link_mode(struct hnae3_handle *handle, + unsigned long *supported, + unsigned long *advertising) +{ + struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); + + *supported = hdev->hw.mac.supported; + *advertising = hdev->hw.mac.advertising; +} + #define MAX_SEPARATE_NUM 4 #define SEPARATOR_VALUE 0xFFFFFFFF #define REG_NUM_PER_LINE 4 @@ -2687,6 +2731,7 @@ static const struct hnae3_ae_ops hclgevf_ops = { .set_mtu = hclgevf_set_mtu, .get_global_queue_id = hclgevf_get_qid_global, .set_timer_task = hclgevf_set_timer_task, + .get_link_mode = hclgevf_get_link_mode, }; static struct hnae3_ae_algo ae_algovf = { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h index 787bc06944e5..eba1118a766d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h @@ -145,6 +145,8 @@ struct hclgevf_mac { int link; u8 duplex; u32 speed; + u64 supported; + u64 advertising; }; struct hclgevf_hw { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c index 84653f58b2d1..7dc3c9f79169 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c @@ -197,6 +197,7 @@ void hclgevf_mbx_handler(struct hclgevf_dev *hdev) break; case HCLGE_MBX_LINK_STAT_CHANGE: case HCLGE_MBX_ASSERTING_RESET: + case HCLGE_MBX_LINK_STAT_MODE: /* set this mbx event as pending. This is required as we * might loose interrupt event when mbx task is busy * handling. This shall be cleared when mbx task just @@ -247,6 +248,7 @@ void hclgevf_mbx_async_handler(struct hclgevf_dev *hdev) u8 duplex; u32 speed; u32 tail; + u8 idx; /* we can safely clear it now as we are at start of the async message * processing @@ -270,12 +272,22 @@ void hclgevf_mbx_async_handler(struct hclgevf_dev *hdev) link_status = le16_to_cpu(msg_q[1]); memcpy(&speed, &msg_q[2], sizeof(speed)); duplex = (u8)le16_to_cpu(msg_q[4]); + hdev->hw.mac.media_type = (u8)le16_to_cpu(msg_q[5]); /* update upper layer with new link link status */ hclgevf_update_link_status(hdev, link_status); hclgevf_update_speed_duplex(hdev, speed, duplex); break; + case HCLGE_MBX_LINK_STAT_MODE: + idx = (u8)le16_to_cpu(msg_q[1]); + if (idx) + memcpy(&hdev->hw.mac.supported, &msg_q[2], + sizeof(unsigned long)); + else + memcpy(&hdev->hw.mac.advertising, &msg_q[2], + sizeof(unsigned long)); + break; case HCLGE_MBX_ASSERTING_RESET: /* PF has asserted reset hence VF should go in pending * state and poll for the hardware reset status till it diff --git a/drivers/net/ethernet/hisilicon/hns_mdio.c b/drivers/net/ethernet/hisilicon/hns_mdio.c index 017e08452d8c..baf5cc251f32 100644 --- a/drivers/net/ethernet/hisilicon/hns_mdio.c +++ b/drivers/net/ethernet/hisilicon/hns_mdio.c @@ -321,7 +321,7 @@ static int hns_mdio_read(struct mii_bus *bus, int phy_id, int regnum) } hns_mdio_cmd_write(mdio_dev, is_c45, - MDIO_C45_WRITE_ADDR, phy_id, devad); + MDIO_C45_READ, phy_id, devad); } /* Step 5: waitting for MDIO_COMMAND_REG 's mdio_start==0,*/ diff --git a/drivers/net/ethernet/i825xx/82596.c b/drivers/net/ethernet/i825xx/82596.c index d719668a6684..92929750f832 100644 --- a/drivers/net/ethernet/i825xx/82596.c +++ b/drivers/net/ethernet/i825xx/82596.c @@ -1310,7 +1310,7 @@ static irqreturn_t i596_interrupt(int irq, void *dev_id) dev->stats.tx_aborted_errors++; } - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); tx_cmd->cmd.command = 0; /* Mark free */ break; diff --git a/drivers/net/ethernet/i825xx/lib82596.c b/drivers/net/ethernet/i825xx/lib82596.c index 2f7ae118217f..1274ad24d6af 100644 --- a/drivers/net/ethernet/i825xx/lib82596.c +++ b/drivers/net/ethernet/i825xx/lib82596.c @@ -1194,7 +1194,7 @@ static irqreturn_t i596_interrupt(int irq, void *dev_id) dma_unmap_single(dev->dev.parent, tx_cmd->dma_addr, skb->len, DMA_TO_DEVICE); - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); tx_cmd->cmd.command = 0; /* Mark free */ break; diff --git a/drivers/net/ethernet/ibm/emac/Kconfig b/drivers/net/ethernet/ibm/emac/Kconfig index 90d49191beb3..eacf7e141fdc 100644 --- a/drivers/net/ethernet/ibm/emac/Kconfig +++ b/drivers/net/ethernet/ibm/emac/Kconfig @@ -28,18 +28,6 @@ config IBM_EMAC_RX_COPY_THRESHOLD depends on IBM_EMAC default "256" -config IBM_EMAC_RX_SKB_HEADROOM - int "Additional RX skb headroom (bytes)" - depends on IBM_EMAC - default "0" - help - Additional receive skb headroom. Note, that driver - will always reserve at least 2 bytes to make IP header - aligned, so usually there is no need to add any additional - headroom. - - If unsure, set to 0. - config IBM_EMAC_DEBUG bool "Debugging" depends on IBM_EMAC diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c index 209255495bc9..3c2a5759844a 100644 --- a/drivers/net/ethernet/ibm/emac/core.c +++ b/drivers/net/ethernet/ibm/emac/core.c @@ -1071,7 +1071,9 @@ static int emac_resize_rx_ring(struct emac_instance *dev, int new_mtu) /* Second pass, allocate new skbs */ for (i = 0; i < NUM_RX_BUFF; ++i) { - struct sk_buff *skb = alloc_skb(rx_skb_size, GFP_ATOMIC); + struct sk_buff *skb; + + skb = netdev_alloc_skb_ip_align(dev->ndev, rx_skb_size); if (!skb) { ret = -ENOMEM; goto oom; @@ -1080,10 +1082,10 @@ static int emac_resize_rx_ring(struct emac_instance *dev, int new_mtu) BUG_ON(!dev->rx_skb[i]); dev_kfree_skb(dev->rx_skb[i]); - skb_reserve(skb, EMAC_RX_SKB_HEADROOM + 2); dev->rx_desc[i].data_ptr = - dma_map_single(&dev->ofdev->dev, skb->data - 2, rx_sync_size, - DMA_FROM_DEVICE) + 2; + dma_map_single(&dev->ofdev->dev, skb->data - NET_IP_ALIGN, + rx_sync_size, DMA_FROM_DEVICE) + + NET_IP_ALIGN; dev->rx_skb[i] = skb; } skip: @@ -1174,20 +1176,18 @@ static void emac_clean_rx_ring(struct emac_instance *dev) } } -static inline int emac_alloc_rx_skb(struct emac_instance *dev, int slot, - gfp_t flags) +static int +__emac_prepare_rx_skb(struct sk_buff *skb, struct emac_instance *dev, int slot) { - struct sk_buff *skb = alloc_skb(dev->rx_skb_size, flags); if (unlikely(!skb)) return -ENOMEM; dev->rx_skb[slot] = skb; dev->rx_desc[slot].data_len = 0; - skb_reserve(skb, EMAC_RX_SKB_HEADROOM + 2); dev->rx_desc[slot].data_ptr = - dma_map_single(&dev->ofdev->dev, skb->data - 2, dev->rx_sync_size, - DMA_FROM_DEVICE) + 2; + dma_map_single(&dev->ofdev->dev, skb->data - NET_IP_ALIGN, + dev->rx_sync_size, DMA_FROM_DEVICE) + NET_IP_ALIGN; wmb(); dev->rx_desc[slot].ctrl = MAL_RX_CTRL_EMPTY | (slot == (NUM_RX_BUFF - 1) ? MAL_RX_CTRL_WRAP : 0); @@ -1195,6 +1195,27 @@ static inline int emac_alloc_rx_skb(struct emac_instance *dev, int slot, return 0; } +static int +emac_alloc_rx_skb(struct emac_instance *dev, int slot) +{ + struct sk_buff *skb; + + skb = __netdev_alloc_skb_ip_align(dev->ndev, dev->rx_skb_size, + GFP_KERNEL); + + return __emac_prepare_rx_skb(skb, dev, slot); +} + +static int +emac_alloc_rx_skb_napi(struct emac_instance *dev, int slot) +{ + struct sk_buff *skb; + + skb = napi_alloc_skb(&dev->mal->napi, dev->rx_skb_size); + + return __emac_prepare_rx_skb(skb, dev, slot); +} + static void emac_print_link_status(struct emac_instance *dev) { if (netif_carrier_ok(dev->ndev)) @@ -1225,7 +1246,7 @@ static int emac_open(struct net_device *ndev) /* Allocate RX ring */ for (i = 0; i < NUM_RX_BUFF; ++i) - if (emac_alloc_rx_skb(dev, i, GFP_KERNEL)) { + if (emac_alloc_rx_skb(dev, i)) { printk(KERN_ERR "%s: failed to allocate RX ring\n", ndev->name); goto oom; @@ -1660,8 +1681,9 @@ static inline void emac_recycle_rx_skb(struct emac_instance *dev, int slot, DBG2(dev, "recycle %d %d" NL, slot, len); if (len) - dma_map_single(&dev->ofdev->dev, skb->data - 2, - EMAC_DMA_ALIGN(len + 2), DMA_FROM_DEVICE); + dma_map_single(&dev->ofdev->dev, skb->data - NET_IP_ALIGN, + SKB_DATA_ALIGN(len + NET_IP_ALIGN), + DMA_FROM_DEVICE); dev->rx_desc[slot].data_len = 0; wmb(); @@ -1713,7 +1735,7 @@ static inline int emac_rx_sg_append(struct emac_instance *dev, int slot) int len = dev->rx_desc[slot].data_len; int tot_len = dev->rx_sg_skb->len + len; - if (unlikely(tot_len + 2 > dev->rx_skb_size)) { + if (unlikely(tot_len + NET_IP_ALIGN > dev->rx_skb_size)) { ++dev->estats.rx_dropped_mtu; dev_kfree_skb(dev->rx_sg_skb); dev->rx_sg_skb = NULL; @@ -1769,16 +1791,18 @@ static int emac_poll_rx(void *param, int budget) } if (len && len < EMAC_RX_COPY_THRESH) { - struct sk_buff *copy_skb = - alloc_skb(len + EMAC_RX_SKB_HEADROOM + 2, GFP_ATOMIC); + struct sk_buff *copy_skb; + + copy_skb = napi_alloc_skb(&dev->mal->napi, len); if (unlikely(!copy_skb)) goto oom; - skb_reserve(copy_skb, EMAC_RX_SKB_HEADROOM + 2); - memcpy(copy_skb->data - 2, skb->data - 2, len + 2); + memcpy(copy_skb->data - NET_IP_ALIGN, + skb->data - NET_IP_ALIGN, + len + NET_IP_ALIGN); emac_recycle_rx_skb(dev, slot, len); skb = copy_skb; - } else if (unlikely(emac_alloc_rx_skb(dev, slot, GFP_ATOMIC))) + } else if (unlikely(emac_alloc_rx_skb_napi(dev, slot))) goto oom; skb_put(skb, len); @@ -1799,7 +1823,7 @@ static int emac_poll_rx(void *param, int budget) sg: if (ctrl & MAL_RX_CTRL_FIRST) { BUG_ON(dev->rx_sg_skb); - if (unlikely(emac_alloc_rx_skb(dev, slot, GFP_ATOMIC))) { + if (unlikely(emac_alloc_rx_skb_napi(dev, slot))) { DBG(dev, "rx OOM %d" NL, slot); ++dev->estats.rx_dropped_oom; emac_recycle_rx_skb(dev, slot, 0); diff --git a/drivers/net/ethernet/ibm/emac/core.h b/drivers/net/ethernet/ibm/emac/core.h index 84caa4a3fc52..187689cd8212 100644 --- a/drivers/net/ethernet/ibm/emac/core.h +++ b/drivers/net/ethernet/ibm/emac/core.h @@ -68,22 +68,18 @@ static inline int emac_rx_size(int mtu) return mal_rx_size(ETH_DATA_LEN + EMAC_MTU_OVERHEAD); } -#define EMAC_DMA_ALIGN(x) ALIGN((x), dma_get_cache_alignment()) - -#define EMAC_RX_SKB_HEADROOM \ - EMAC_DMA_ALIGN(CONFIG_IBM_EMAC_RX_SKB_HEADROOM) - /* Size of RX skb for the given MTU */ static inline int emac_rx_skb_size(int mtu) { int size = max(mtu + EMAC_MTU_OVERHEAD, emac_rx_size(mtu)); - return EMAC_DMA_ALIGN(size + 2) + EMAC_RX_SKB_HEADROOM; + + return SKB_DATA_ALIGN(size + NET_IP_ALIGN) + NET_SKB_PAD; } /* RX DMA sync size */ static inline int emac_rx_sync_size(int mtu) { - return EMAC_DMA_ALIGN(emac_rx_size(mtu) + 2); + return SKB_DATA_ALIGN(emac_rx_size(mtu) + NET_IP_ALIGN); } /* Driver statistcs is split into two parts to make it more cache friendly: diff --git a/drivers/net/ethernet/intel/e1000e/80003es2lan.c b/drivers/net/ethernet/intel/e1000e/80003es2lan.c index 257bd59bc9c6..f86d55657959 100644 --- a/drivers/net/ethernet/intel/e1000e/80003es2lan.c +++ b/drivers/net/ethernet/intel/e1000e/80003es2lan.c @@ -696,11 +696,16 @@ static s32 e1000_reset_hw_80003es2lan(struct e1000_hw *hw) ret_val = e1000_read_kmrn_reg_80003es2lan(hw, E1000_KMRNCTRLSTA_INBAND_PARAM, &kum_reg_data); - if (ret_val) - return ret_val; - kum_reg_data |= E1000_KMRNCTRLSTA_IBIST_DISABLE; - e1000_write_kmrn_reg_80003es2lan(hw, E1000_KMRNCTRLSTA_INBAND_PARAM, - kum_reg_data); + if (!ret_val) { + kum_reg_data |= E1000_KMRNCTRLSTA_IBIST_DISABLE; + ret_val = e1000_write_kmrn_reg_80003es2lan(hw, + E1000_KMRNCTRLSTA_INBAND_PARAM, + kum_reg_data); + if (ret_val) + e_dbg("Error disabling far-end loopback\n"); + } else { + e_dbg("Error disabling far-end loopback\n"); + } ret_val = e1000e_get_auto_rd_done(hw); if (ret_val) @@ -754,11 +759,19 @@ static s32 e1000_init_hw_80003es2lan(struct e1000_hw *hw) return ret_val; /* Disable IBIST slave mode (far-end loopback) */ - e1000_read_kmrn_reg_80003es2lan(hw, E1000_KMRNCTRLSTA_INBAND_PARAM, - &kum_reg_data); - kum_reg_data |= E1000_KMRNCTRLSTA_IBIST_DISABLE; - e1000_write_kmrn_reg_80003es2lan(hw, E1000_KMRNCTRLSTA_INBAND_PARAM, - kum_reg_data); + ret_val = + e1000_read_kmrn_reg_80003es2lan(hw, E1000_KMRNCTRLSTA_INBAND_PARAM, + &kum_reg_data); + if (!ret_val) { + kum_reg_data |= E1000_KMRNCTRLSTA_IBIST_DISABLE; + ret_val = e1000_write_kmrn_reg_80003es2lan(hw, + E1000_KMRNCTRLSTA_INBAND_PARAM, + kum_reg_data); + if (ret_val) + e_dbg("Error disabling far-end loopback\n"); + } else { + e_dbg("Error disabling far-end loopback\n"); + } /* Set the transmit descriptor write-back policy */ reg_data = er32(TXDCTL(0)); diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 189f231075c2..736fa51878f8 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -5309,8 +5309,13 @@ static void e1000_watchdog_task(struct work_struct *work) /* 8000ES2LAN requires a Rx packet buffer work-around * on link down event; reset the controller to flush * the Rx packet buffer. + * + * If the link is lost the controller stops DMA, but + * if there is queued Tx work it cannot be done. So + * reset the controller to flush the Tx packet buffers. */ - if (adapter->flags & FLAG_RX_NEEDS_RESTART) + if ((adapter->flags & FLAG_RX_NEEDS_RESTART) || + e1000_desc_unused(tx_ring) + 1 < tx_ring->count) adapter->flags |= FLAG_RESTART_NOW; else pm_schedule_suspend(netdev->dev.parent, @@ -5333,14 +5338,6 @@ link_up: adapter->gotc_old = adapter->stats.gotc; spin_unlock(&adapter->stats64_lock); - /* If the link is lost the controller stops DMA, but - * if there is queued Tx work it cannot be done. So - * reset the controller to flush the Tx packet buffers. - */ - if (!netif_carrier_ok(netdev) && - (e1000_desc_unused(tx_ring) + 1 < tx_ring->count)) - adapter->flags |= FLAG_RESTART_NOW; - /* If reset is necessary, do it outside of interrupt context. */ if (adapter->flags & FLAG_RESTART_NOW) { schedule_work(&adapter->reset_task); @@ -7351,6 +7348,8 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) e1000_print_device_info(adapter); + dev_pm_set_driver_flags(&pdev->dev, DPM_FLAG_NEVER_SKIP); + if (pci_dev_run_wake(pdev)) pm_runtime_put_noidle(&pdev->dev); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index 6fd15a734324..5a0419421511 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -1603,14 +1603,12 @@ static int fm10k_alloc_q_vector(struct fm10k_intfc *interface, { struct fm10k_q_vector *q_vector; struct fm10k_ring *ring; - int ring_count, size; + int ring_count; ring_count = txr_count + rxr_count; - size = sizeof(struct fm10k_q_vector) + - (sizeof(struct fm10k_ring) * ring_count); /* allocate q_vector and rings */ - q_vector = kzalloc(size, GFP_KERNEL); + q_vector = kzalloc(struct_size(q_vector, ring, ring_count), GFP_KERNEL); if (!q_vector) return -ENOMEM; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c index 8f0a99b6a537..cb4d02629b86 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c @@ -1148,7 +1148,7 @@ static void fm10k_iov_update_stats_pf(struct fm10k_hw *hw, * @results: Pointer array to message, results[0] is pointer to message * @mbx: Pointer to mailbox information structure * - * This function is a default handler for MSI-X requests from the VF. The + * This function is a default handler for MSI-X requests from the VF. The * assumption is that in this case it is acceptable to just directly * hand off the message from the VF to the underlying shared code. **/ diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 5c6731b97059..5e74a5127849 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -7169,11 +7169,13 @@ static int i40e_parse_cls_flower(struct i40e_vsi *vsi, struct tc_cls_flower_offload *f, struct i40e_cloud_filter *filter) { + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f); + struct flow_dissector *dissector = rule->match.dissector; u16 n_proto_mask = 0, n_proto_key = 0, addr_type = 0; struct i40e_pf *pf = vsi->back; u8 field_flags = 0; - if (f->dissector->used_keys & + if (dissector->used_keys & ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | BIT(FLOW_DISSECTOR_KEY_BASIC) | BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | @@ -7183,143 +7185,109 @@ static int i40e_parse_cls_flower(struct i40e_vsi *vsi, BIT(FLOW_DISSECTOR_KEY_PORTS) | BIT(FLOW_DISSECTOR_KEY_ENC_KEYID))) { dev_err(&pf->pdev->dev, "Unsupported key used: 0x%x\n", - f->dissector->used_keys); + dissector->used_keys); return -EOPNOTSUPP; } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) { - struct flow_dissector_key_keyid *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_KEYID, - f->key); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID)) { + struct flow_match_enc_keyid match; - struct flow_dissector_key_keyid *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_KEYID, - f->mask); - - if (mask->keyid != 0) + flow_rule_match_enc_keyid(rule, &match); + if (match.mask->keyid != 0) field_flags |= I40E_CLOUD_FIELD_TEN_ID; - filter->tenant_id = be32_to_cpu(key->keyid); + filter->tenant_id = be32_to_cpu(match.key->keyid); } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) { - struct flow_dissector_key_basic *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_BASIC, - f->key); - - struct flow_dissector_key_basic *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_BASIC, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_match_basic match; - n_proto_key = ntohs(key->n_proto); - n_proto_mask = ntohs(mask->n_proto); + flow_rule_match_basic(rule, &match); + n_proto_key = ntohs(match.key->n_proto); + n_proto_mask = ntohs(match.mask->n_proto); if (n_proto_key == ETH_P_ALL) { n_proto_key = 0; n_proto_mask = 0; } filter->n_proto = n_proto_key & n_proto_mask; - filter->ip_proto = key->ip_proto; + filter->ip_proto = match.key->ip_proto; } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { - struct flow_dissector_key_eth_addrs *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ETH_ADDRS, - f->key); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { + struct flow_match_eth_addrs match; - struct flow_dissector_key_eth_addrs *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ETH_ADDRS, - f->mask); + flow_rule_match_eth_addrs(rule, &match); /* use is_broadcast and is_zero to check for all 0xf or 0 */ - if (!is_zero_ether_addr(mask->dst)) { - if (is_broadcast_ether_addr(mask->dst)) { + if (!is_zero_ether_addr(match.mask->dst)) { + if (is_broadcast_ether_addr(match.mask->dst)) { field_flags |= I40E_CLOUD_FIELD_OMAC; } else { dev_err(&pf->pdev->dev, "Bad ether dest mask %pM\n", - mask->dst); + match.mask->dst); return I40E_ERR_CONFIG; } } - if (!is_zero_ether_addr(mask->src)) { - if (is_broadcast_ether_addr(mask->src)) { + if (!is_zero_ether_addr(match.mask->src)) { + if (is_broadcast_ether_addr(match.mask->src)) { field_flags |= I40E_CLOUD_FIELD_IMAC; } else { dev_err(&pf->pdev->dev, "Bad ether src mask %pM\n", - mask->src); + match.mask->src); return I40E_ERR_CONFIG; } } - ether_addr_copy(filter->dst_mac, key->dst); - ether_addr_copy(filter->src_mac, key->src); + ether_addr_copy(filter->dst_mac, match.key->dst); + ether_addr_copy(filter->src_mac, match.key->src); } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) { - struct flow_dissector_key_vlan *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_VLAN, - f->key); - struct flow_dissector_key_vlan *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_VLAN, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_match_vlan match; - if (mask->vlan_id) { - if (mask->vlan_id == VLAN_VID_MASK) { + flow_rule_match_vlan(rule, &match); + if (match.mask->vlan_id) { + if (match.mask->vlan_id == VLAN_VID_MASK) { field_flags |= I40E_CLOUD_FIELD_IVLAN; } else { dev_err(&pf->pdev->dev, "Bad vlan mask 0x%04x\n", - mask->vlan_id); + match.mask->vlan_id); return I40E_ERR_CONFIG; } } - filter->vlan_id = cpu_to_be16(key->vlan_id); + filter->vlan_id = cpu_to_be16(match.key->vlan_id); } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) { - struct flow_dissector_key_control *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_CONTROL, - f->key); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) { + struct flow_match_control match; - addr_type = key->addr_type; + flow_rule_match_control(rule, &match); + addr_type = match.key->addr_type; } if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { - struct flow_dissector_key_ipv4_addrs *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS, - f->key); - struct flow_dissector_key_ipv4_addrs *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS, - f->mask); - - if (mask->dst) { - if (mask->dst == cpu_to_be32(0xffffffff)) { + struct flow_match_ipv4_addrs match; + + flow_rule_match_ipv4_addrs(rule, &match); + if (match.mask->dst) { + if (match.mask->dst == cpu_to_be32(0xffffffff)) { field_flags |= I40E_CLOUD_FIELD_IIP; } else { dev_err(&pf->pdev->dev, "Bad ip dst mask %pI4b\n", - &mask->dst); + &match.mask->dst); return I40E_ERR_CONFIG; } } - if (mask->src) { - if (mask->src == cpu_to_be32(0xffffffff)) { + if (match.mask->src) { + if (match.mask->src == cpu_to_be32(0xffffffff)) { field_flags |= I40E_CLOUD_FIELD_IIP; } else { dev_err(&pf->pdev->dev, "Bad ip src mask %pI4b\n", - &mask->src); + &match.mask->src); return I40E_ERR_CONFIG; } } @@ -7328,70 +7296,60 @@ static int i40e_parse_cls_flower(struct i40e_vsi *vsi, dev_err(&pf->pdev->dev, "Tenant id not allowed for ip filter\n"); return I40E_ERR_CONFIG; } - filter->dst_ipv4 = key->dst; - filter->src_ipv4 = key->src; + filter->dst_ipv4 = match.key->dst; + filter->src_ipv4 = match.key->src; } if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { - struct flow_dissector_key_ipv6_addrs *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS, - f->key); - struct flow_dissector_key_ipv6_addrs *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS, - f->mask); + struct flow_match_ipv6_addrs match; + + flow_rule_match_ipv6_addrs(rule, &match); /* src and dest IPV6 address should not be LOOPBACK * (0:0:0:0:0:0:0:1), which can be represented as ::1 */ - if (ipv6_addr_loopback(&key->dst) || - ipv6_addr_loopback(&key->src)) { + if (ipv6_addr_loopback(&match.key->dst) || + ipv6_addr_loopback(&match.key->src)) { dev_err(&pf->pdev->dev, "Bad ipv6, addr is LOOPBACK\n"); return I40E_ERR_CONFIG; } - if (!ipv6_addr_any(&mask->dst) || !ipv6_addr_any(&mask->src)) + if (!ipv6_addr_any(&match.mask->dst) || + !ipv6_addr_any(&match.mask->src)) field_flags |= I40E_CLOUD_FIELD_IIP; - memcpy(&filter->src_ipv6, &key->src.s6_addr32, + memcpy(&filter->src_ipv6, &match.key->src.s6_addr32, sizeof(filter->src_ipv6)); - memcpy(&filter->dst_ipv6, &key->dst.s6_addr32, + memcpy(&filter->dst_ipv6, &match.key->dst.s6_addr32, sizeof(filter->dst_ipv6)); } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) { - struct flow_dissector_key_ports *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_PORTS, - f->key); - struct flow_dissector_key_ports *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_PORTS, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) { + struct flow_match_ports match; - if (mask->src) { - if (mask->src == cpu_to_be16(0xffff)) { + flow_rule_match_ports(rule, &match); + if (match.mask->src) { + if (match.mask->src == cpu_to_be16(0xffff)) { field_flags |= I40E_CLOUD_FIELD_IIP; } else { dev_err(&pf->pdev->dev, "Bad src port mask 0x%04x\n", - be16_to_cpu(mask->src)); + be16_to_cpu(match.mask->src)); return I40E_ERR_CONFIG; } } - if (mask->dst) { - if (mask->dst == cpu_to_be16(0xffff)) { + if (match.mask->dst) { + if (match.mask->dst == cpu_to_be16(0xffff)) { field_flags |= I40E_CLOUD_FIELD_IIP; } else { dev_err(&pf->pdev->dev, "Bad dst port mask 0x%04x\n", - be16_to_cpu(mask->dst)); + be16_to_cpu(match.mask->dst)); return I40E_ERR_CONFIG; } } - filter->dst_port = key->dst; - filter->src_port = key->src; + filter->dst_port = match.key->dst; + filter->src_port = match.key->src; switch (filter->ip_proto) { case IPPROTO_TCP: @@ -12170,9 +12128,6 @@ static int i40e_xdp(struct net_device *dev, case XDP_QUERY_PROG: xdp->prog_id = vsi->xdp_prog ? vsi->xdp_prog->aux->id : 0; return 0; - case XDP_QUERY_XSK_UMEM: - return i40e_xsk_umem_query(vsi, &xdp->xsk.umem, - xdp->xsk.queue_id); case XDP_SETUP_XSK_UMEM: return i40e_xsk_umem_setup(vsi, xdp->xsk.umem, xdp->xsk.queue_id); diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 96d849460d9b..e190a2c2b9ff 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -155,34 +155,6 @@ static int i40e_xsk_umem_disable(struct i40e_vsi *vsi, u16 qid) } /** - * i40e_xsk_umem_query - Queries a certain ring/qid for its UMEM - * @vsi: Current VSI - * @umem: UMEM associated to the ring, if any - * @qid: Rx ring to associate UMEM to - * - * This function will store, if any, the UMEM associated to certain ring. - * - * Returns 0 on success, <0 on failure - **/ -int i40e_xsk_umem_query(struct i40e_vsi *vsi, struct xdp_umem **umem, - u16 qid) -{ - struct net_device *netdev = vsi->netdev; - struct xdp_umem *queried_umem; - - if (vsi->type != I40E_VSI_MAIN) - return -EINVAL; - - queried_umem = xdp_get_umem_from_qid(netdev, qid); - - if (!queried_umem) - return -EINVAL; - - *umem = queried_umem; - return 0; -} - -/** * i40e_xsk_umem_setup - Enable/disassociate a UMEM to/from a ring/qid * @vsi: Current VSI * @umem: UMEM to enable/associate to a ring, or NULL to disable diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.h b/drivers/net/ethernet/intel/i40e/i40e_xsk.h index 9038c5d5cf08..8cc0a2e7d9a2 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.h +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.h @@ -10,8 +10,6 @@ struct zero_copy_allocator; int i40e_queue_pair_disable(struct i40e_vsi *vsi, int queue_pair); int i40e_queue_pair_enable(struct i40e_vsi *vsi, int queue_pair); -int i40e_xsk_umem_query(struct i40e_vsi *vsi, struct xdp_umem **umem, - u16 qid); int i40e_xsk_umem_setup(struct i40e_vsi *vsi, struct xdp_umem *umem, u16 qid); void i40e_zca_free(struct zero_copy_allocator *alloc, unsigned long handle); diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 9f2b7b7adf6b..4569d69a2b55 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -2439,6 +2439,8 @@ static int iavf_parse_cls_flower(struct iavf_adapter *adapter, struct tc_cls_flower_offload *f, struct iavf_cloud_filter *filter) { + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f); + struct flow_dissector *dissector = rule->match.dissector; u16 n_proto_mask = 0; u16 n_proto_key = 0; u8 field_flags = 0; @@ -2447,7 +2449,7 @@ static int iavf_parse_cls_flower(struct iavf_adapter *adapter, int i = 0; struct virtchnl_filter *vf = &filter->f; - if (f->dissector->used_keys & + if (dissector->used_keys & ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | BIT(FLOW_DISSECTOR_KEY_BASIC) | BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | @@ -2457,32 +2459,24 @@ static int iavf_parse_cls_flower(struct iavf_adapter *adapter, BIT(FLOW_DISSECTOR_KEY_PORTS) | BIT(FLOW_DISSECTOR_KEY_ENC_KEYID))) { dev_err(&adapter->pdev->dev, "Unsupported key used: 0x%x\n", - f->dissector->used_keys); + dissector->used_keys); return -EOPNOTSUPP; } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) { - struct flow_dissector_key_keyid *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_KEYID, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID)) { + struct flow_match_enc_keyid match; - if (mask->keyid != 0) + flow_rule_match_enc_keyid(rule, &match); + if (match.mask->keyid != 0) field_flags |= IAVF_CLOUD_FIELD_TEN_ID; } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) { - struct flow_dissector_key_basic *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_BASIC, - f->key); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_match_basic match; - struct flow_dissector_key_basic *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_BASIC, - f->mask); - n_proto_key = ntohs(key->n_proto); - n_proto_mask = ntohs(mask->n_proto); + flow_rule_match_basic(rule, &match); + n_proto_key = ntohs(match.key->n_proto); + n_proto_mask = ntohs(match.mask->n_proto); if (n_proto_key == ETH_P_ALL) { n_proto_key = 0; @@ -2496,122 +2490,103 @@ static int iavf_parse_cls_flower(struct iavf_adapter *adapter, vf->flow_type = VIRTCHNL_TCP_V6_FLOW; } - if (key->ip_proto != IPPROTO_TCP) { + if (match.key->ip_proto != IPPROTO_TCP) { dev_info(&adapter->pdev->dev, "Only TCP transport is supported\n"); return -EINVAL; } } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { - struct flow_dissector_key_eth_addrs *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ETH_ADDRS, - f->key); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { + struct flow_match_eth_addrs match; + + flow_rule_match_eth_addrs(rule, &match); - struct flow_dissector_key_eth_addrs *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ETH_ADDRS, - f->mask); /* use is_broadcast and is_zero to check for all 0xf or 0 */ - if (!is_zero_ether_addr(mask->dst)) { - if (is_broadcast_ether_addr(mask->dst)) { + if (!is_zero_ether_addr(match.mask->dst)) { + if (is_broadcast_ether_addr(match.mask->dst)) { field_flags |= IAVF_CLOUD_FIELD_OMAC; } else { dev_err(&adapter->pdev->dev, "Bad ether dest mask %pM\n", - mask->dst); + match.mask->dst); return I40E_ERR_CONFIG; } } - if (!is_zero_ether_addr(mask->src)) { - if (is_broadcast_ether_addr(mask->src)) { + if (!is_zero_ether_addr(match.mask->src)) { + if (is_broadcast_ether_addr(match.mask->src)) { field_flags |= IAVF_CLOUD_FIELD_IMAC; } else { dev_err(&adapter->pdev->dev, "Bad ether src mask %pM\n", - mask->src); + match.mask->src); return I40E_ERR_CONFIG; } } - if (!is_zero_ether_addr(key->dst)) - if (is_valid_ether_addr(key->dst) || - is_multicast_ether_addr(key->dst)) { + if (!is_zero_ether_addr(match.key->dst)) + if (is_valid_ether_addr(match.key->dst) || + is_multicast_ether_addr(match.key->dst)) { /* set the mask if a valid dst_mac address */ for (i = 0; i < ETH_ALEN; i++) vf->mask.tcp_spec.dst_mac[i] |= 0xff; ether_addr_copy(vf->data.tcp_spec.dst_mac, - key->dst); + match.key->dst); } - if (!is_zero_ether_addr(key->src)) - if (is_valid_ether_addr(key->src) || - is_multicast_ether_addr(key->src)) { + if (!is_zero_ether_addr(match.key->src)) + if (is_valid_ether_addr(match.key->src) || + is_multicast_ether_addr(match.key->src)) { /* set the mask if a valid dst_mac address */ for (i = 0; i < ETH_ALEN; i++) vf->mask.tcp_spec.src_mac[i] |= 0xff; ether_addr_copy(vf->data.tcp_spec.src_mac, - key->src); + match.key->src); } } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) { - struct flow_dissector_key_vlan *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_VLAN, - f->key); - struct flow_dissector_key_vlan *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_VLAN, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_match_vlan match; - if (mask->vlan_id) { - if (mask->vlan_id == VLAN_VID_MASK) { + flow_rule_match_vlan(rule, &match); + if (match.mask->vlan_id) { + if (match.mask->vlan_id == VLAN_VID_MASK) { field_flags |= IAVF_CLOUD_FIELD_IVLAN; } else { dev_err(&adapter->pdev->dev, "Bad vlan mask %u\n", - mask->vlan_id); + match.mask->vlan_id); return I40E_ERR_CONFIG; } } vf->mask.tcp_spec.vlan_id |= cpu_to_be16(0xffff); - vf->data.tcp_spec.vlan_id = cpu_to_be16(key->vlan_id); + vf->data.tcp_spec.vlan_id = cpu_to_be16(match.key->vlan_id); } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) { - struct flow_dissector_key_control *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_CONTROL, - f->key); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) { + struct flow_match_control match; - addr_type = key->addr_type; + flow_rule_match_control(rule, &match); + addr_type = match.key->addr_type; } if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { - struct flow_dissector_key_ipv4_addrs *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS, - f->key); - struct flow_dissector_key_ipv4_addrs *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS, - f->mask); - - if (mask->dst) { - if (mask->dst == cpu_to_be32(0xffffffff)) { + struct flow_match_ipv4_addrs match; + + flow_rule_match_ipv4_addrs(rule, &match); + if (match.mask->dst) { + if (match.mask->dst == cpu_to_be32(0xffffffff)) { field_flags |= IAVF_CLOUD_FIELD_IIP; } else { dev_err(&adapter->pdev->dev, "Bad ip dst mask 0x%08x\n", - be32_to_cpu(mask->dst)); + be32_to_cpu(match.mask->dst)); return I40E_ERR_CONFIG; } } - if (mask->src) { - if (mask->src == cpu_to_be32(0xffffffff)) { + if (match.mask->src) { + if (match.mask->src == cpu_to_be32(0xffffffff)) { field_flags |= IAVF_CLOUD_FIELD_IIP; } else { dev_err(&adapter->pdev->dev, "Bad ip src mask 0x%08x\n", - be32_to_cpu(mask->dst)); + be32_to_cpu(match.mask->dst)); return I40E_ERR_CONFIG; } } @@ -2620,28 +2595,23 @@ static int iavf_parse_cls_flower(struct iavf_adapter *adapter, dev_info(&adapter->pdev->dev, "Tenant id not allowed for ip filter\n"); return I40E_ERR_CONFIG; } - if (key->dst) { + if (match.key->dst) { vf->mask.tcp_spec.dst_ip[0] |= cpu_to_be32(0xffffffff); - vf->data.tcp_spec.dst_ip[0] = key->dst; + vf->data.tcp_spec.dst_ip[0] = match.key->dst; } - if (key->src) { + if (match.key->src) { vf->mask.tcp_spec.src_ip[0] |= cpu_to_be32(0xffffffff); - vf->data.tcp_spec.src_ip[0] = key->src; + vf->data.tcp_spec.src_ip[0] = match.key->src; } } if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { - struct flow_dissector_key_ipv6_addrs *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS, - f->key); - struct flow_dissector_key_ipv6_addrs *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS, - f->mask); + struct flow_match_ipv6_addrs match; + + flow_rule_match_ipv6_addrs(rule, &match); /* validate mask, make sure it is not IPV6_ADDR_ANY */ - if (ipv6_addr_any(&mask->dst)) { + if (ipv6_addr_any(&match.mask->dst)) { dev_err(&adapter->pdev->dev, "Bad ipv6 dst mask 0x%02x\n", IPV6_ADDR_ANY); return I40E_ERR_CONFIG; @@ -2650,61 +2620,56 @@ static int iavf_parse_cls_flower(struct iavf_adapter *adapter, /* src and dest IPv6 address should not be LOOPBACK * (0:0:0:0:0:0:0:1) which can be represented as ::1 */ - if (ipv6_addr_loopback(&key->dst) || - ipv6_addr_loopback(&key->src)) { + if (ipv6_addr_loopback(&match.key->dst) || + ipv6_addr_loopback(&match.key->src)) { dev_err(&adapter->pdev->dev, "ipv6 addr should not be loopback\n"); return I40E_ERR_CONFIG; } - if (!ipv6_addr_any(&mask->dst) || !ipv6_addr_any(&mask->src)) + if (!ipv6_addr_any(&match.mask->dst) || + !ipv6_addr_any(&match.mask->src)) field_flags |= IAVF_CLOUD_FIELD_IIP; for (i = 0; i < 4; i++) vf->mask.tcp_spec.dst_ip[i] |= cpu_to_be32(0xffffffff); - memcpy(&vf->data.tcp_spec.dst_ip, &key->dst.s6_addr32, + memcpy(&vf->data.tcp_spec.dst_ip, &match.key->dst.s6_addr32, sizeof(vf->data.tcp_spec.dst_ip)); for (i = 0; i < 4; i++) vf->mask.tcp_spec.src_ip[i] |= cpu_to_be32(0xffffffff); - memcpy(&vf->data.tcp_spec.src_ip, &key->src.s6_addr32, + memcpy(&vf->data.tcp_spec.src_ip, &match.key->src.s6_addr32, sizeof(vf->data.tcp_spec.src_ip)); } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) { - struct flow_dissector_key_ports *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_PORTS, - f->key); - struct flow_dissector_key_ports *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_PORTS, - f->mask); - - if (mask->src) { - if (mask->src == cpu_to_be16(0xffff)) { + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) { + struct flow_match_ports match; + + flow_rule_match_ports(rule, &match); + if (match.mask->src) { + if (match.mask->src == cpu_to_be16(0xffff)) { field_flags |= IAVF_CLOUD_FIELD_IIP; } else { dev_err(&adapter->pdev->dev, "Bad src port mask %u\n", - be16_to_cpu(mask->src)); + be16_to_cpu(match.mask->src)); return I40E_ERR_CONFIG; } } - if (mask->dst) { - if (mask->dst == cpu_to_be16(0xffff)) { + if (match.mask->dst) { + if (match.mask->dst == cpu_to_be16(0xffff)) { field_flags |= IAVF_CLOUD_FIELD_IIP; } else { dev_err(&adapter->pdev->dev, "Bad dst port mask %u\n", - be16_to_cpu(mask->dst)); + be16_to_cpu(match.mask->dst)); return I40E_ERR_CONFIG; } } - if (key->dst) { + if (match.key->dst) { vf->mask.tcp_spec.dst_port |= cpu_to_be16(0xffff); - vf->data.tcp_spec.dst_port = key->dst; + vf->data.tcp_spec.dst_port = match.key->dst; } - if (key->src) { + if (match.key->src) { vf->mask.tcp_spec.src_port |= cpu_to_be16(0xffff); - vf->data.tcp_spec.src_port = key->src; + vf->data.tcp_spec.src_port = match.key->src; } } vf->field_flags = field_flags; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index dfa357b1a9d6..69b230c53fed 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -39,7 +39,7 @@ #include "igb.h" #define MAJ 5 -#define MIN 4 +#define MIN 6 #define BUILD 0 #define DRV_VERSION __stringify(MAJ) "." __stringify(MIN) "." \ __stringify(BUILD) "-k" @@ -1189,15 +1189,15 @@ static int igb_alloc_q_vector(struct igb_adapter *adapter, { struct igb_q_vector *q_vector; struct igb_ring *ring; - int ring_count, size; + int ring_count; + size_t size; /* igb only supports 1 Tx and/or 1 Rx queue per vector */ if (txr_count > 1 || rxr_count > 1) return -ENOMEM; ring_count = txr_count + rxr_count; - size = sizeof(struct igb_q_vector) + - (sizeof(struct igb_ring) * ring_count); + size = struct_size(q_vector, ring, ring_count); /* allocate q_vector and rings */ q_vector = adapter->q_vector[v_idx]; @@ -2581,9 +2581,11 @@ static int igb_parse_cls_flower(struct igb_adapter *adapter, int traffic_class, struct igb_nfc_filter *input) { + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f); + struct flow_dissector *dissector = rule->match.dissector; struct netlink_ext_ack *extack = f->common.extack; - if (f->dissector->used_keys & + if (dissector->used_keys & ~(BIT(FLOW_DISSECTOR_KEY_BASIC) | BIT(FLOW_DISSECTOR_KEY_CONTROL) | BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | @@ -2593,78 +2595,60 @@ static int igb_parse_cls_flower(struct igb_adapter *adapter, return -EOPNOTSUPP; } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { - struct flow_dissector_key_eth_addrs *key, *mask; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { + struct flow_match_eth_addrs match; - key = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ETH_ADDRS, - f->key); - mask = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ETH_ADDRS, - f->mask); - - if (!is_zero_ether_addr(mask->dst)) { - if (!is_broadcast_ether_addr(mask->dst)) { + flow_rule_match_eth_addrs(rule, &match); + if (!is_zero_ether_addr(match.mask->dst)) { + if (!is_broadcast_ether_addr(match.mask->dst)) { NL_SET_ERR_MSG_MOD(extack, "Only full masks are supported for destination MAC address"); return -EINVAL; } input->filter.match_flags |= IGB_FILTER_FLAG_DST_MAC_ADDR; - ether_addr_copy(input->filter.dst_addr, key->dst); + ether_addr_copy(input->filter.dst_addr, match.key->dst); } - if (!is_zero_ether_addr(mask->src)) { - if (!is_broadcast_ether_addr(mask->src)) { + if (!is_zero_ether_addr(match.mask->src)) { + if (!is_broadcast_ether_addr(match.mask->src)) { NL_SET_ERR_MSG_MOD(extack, "Only full masks are supported for source MAC address"); return -EINVAL; } input->filter.match_flags |= IGB_FILTER_FLAG_SRC_MAC_ADDR; - ether_addr_copy(input->filter.src_addr, key->src); + ether_addr_copy(input->filter.src_addr, match.key->src); } } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) { - struct flow_dissector_key_basic *key, *mask; - - key = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_BASIC, - f->key); - mask = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_BASIC, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_match_basic match; - if (mask->n_proto) { - if (mask->n_proto != ETHER_TYPE_FULL_MASK) { + flow_rule_match_basic(rule, &match); + if (match.mask->n_proto) { + if (match.mask->n_proto != ETHER_TYPE_FULL_MASK) { NL_SET_ERR_MSG_MOD(extack, "Only full mask is supported for EtherType filter"); return -EINVAL; } input->filter.match_flags |= IGB_FILTER_FLAG_ETHER_TYPE; - input->filter.etype = key->n_proto; + input->filter.etype = match.key->n_proto; } } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) { - struct flow_dissector_key_vlan *key, *mask; - - key = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_VLAN, - f->key); - mask = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_VLAN, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_match_vlan match; - if (mask->vlan_priority) { - if (mask->vlan_priority != VLAN_PRIO_FULL_MASK) { + flow_rule_match_vlan(rule, &match); + if (match.mask->vlan_priority) { + if (match.mask->vlan_priority != VLAN_PRIO_FULL_MASK) { NL_SET_ERR_MSG_MOD(extack, "Only full mask is supported for VLAN priority"); return -EINVAL; } input->filter.match_flags |= IGB_FILTER_FLAG_VLAN_TCI; - input->filter.vlan_tci = key->vlan_priority; + input->filter.vlan_tci = match.key->vlan_priority; } } diff --git a/drivers/net/ethernet/intel/igc/Makefile b/drivers/net/ethernet/intel/igc/Makefile index 4387f6ba8e67..88c6f88baac5 100644 --- a/drivers/net/ethernet/intel/igc/Makefile +++ b/drivers/net/ethernet/intel/igc/Makefile @@ -7,4 +7,5 @@ obj-$(CONFIG_IGC) += igc.o -igc-objs := igc_main.o igc_mac.o igc_i225.o igc_base.o igc_nvm.o igc_phy.o +igc-objs := igc_main.o igc_mac.o igc_i225.o igc_base.o igc_nvm.o igc_phy.o \ +igc_ethtool.o diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index b1039dd3dd13..80faccc34cda 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -13,19 +13,43 @@ #include "igc_hw.h" -/* main */ +/* forward declaration */ +void igc_set_ethtool_ops(struct net_device *); + +struct igc_adapter; +struct igc_ring; + +void igc_up(struct igc_adapter *adapter); +void igc_down(struct igc_adapter *adapter); +int igc_setup_tx_resources(struct igc_ring *ring); +int igc_setup_rx_resources(struct igc_ring *ring); +void igc_free_tx_resources(struct igc_ring *ring); +void igc_free_rx_resources(struct igc_ring *ring); +unsigned int igc_get_max_rss_queues(struct igc_adapter *adapter); +void igc_set_flag_queue_pairs(struct igc_adapter *adapter, + const u32 max_rss_queues); +int igc_reinit_queues(struct igc_adapter *adapter); +bool igc_has_link(struct igc_adapter *adapter); +void igc_reset(struct igc_adapter *adapter); +int igc_set_spd_dplx(struct igc_adapter *adapter, u32 spd, u8 dplx); + extern char igc_driver_name[]; extern char igc_driver_version[]; +#define IGC_REGS_LEN 740 +#define IGC_RETA_SIZE 128 + /* Interrupt defines */ #define IGC_START_ITR 648 /* ~6000 ints/sec */ #define IGC_FLAG_HAS_MSI BIT(0) -#define IGC_FLAG_QUEUE_PAIRS BIT(4) +#define IGC_FLAG_QUEUE_PAIRS BIT(3) +#define IGC_FLAG_DMAC BIT(4) #define IGC_FLAG_NEED_LINK_UPDATE BIT(9) #define IGC_FLAG_MEDIA_RESET BIT(10) #define IGC_FLAG_MAS_ENABLE BIT(12) #define IGC_FLAG_HAS_MSIX BIT(13) #define IGC_FLAG_VLAN_PROMISC BIT(15) +#define IGC_FLAG_RX_LEGACY BIT(16) #define IGC_START_ITR 648 /* ~6000 ints/sec */ #define IGC_4K_ITR 980 @@ -60,6 +84,7 @@ extern char igc_driver_version[]; #define IGC_RXBUFFER_2048 2048 #define IGC_RXBUFFER_3072 3072 +#define AUTO_ALL_MODES 0 #define IGC_RX_HDR_LEN IGC_RXBUFFER_256 /* RX and TX descriptor control thresholds. @@ -340,6 +365,8 @@ struct igc_adapter { struct igc_mac_addr *mac_table; + u8 rss_indir_tbl[IGC_RETA_SIZE]; + unsigned long link_check_timeout; struct igc_info ei; }; @@ -418,6 +445,9 @@ static inline s32 igc_read_phy_reg(struct igc_hw *hw, u32 offset, u16 *data) return 0; } +/* forward declaration */ +void igc_reinit_locked(struct igc_adapter *); + #define igc_rx_pg_size(_ring) (PAGE_SIZE << igc_rx_pg_order(_ring)) #define IGC_TXD_DCMD (IGC_ADVTXD_DCMD_EOP | IGC_ADVTXD_DCMD_RS) diff --git a/drivers/net/ethernet/intel/igc/igc_base.c b/drivers/net/ethernet/intel/igc/igc_base.c index df40af759542..51a8b8769c67 100644 --- a/drivers/net/ethernet/intel/igc/igc_base.c +++ b/drivers/net/ethernet/intel/igc/igc_base.c @@ -54,22 +54,6 @@ out: } /** - * igc_check_for_link_base - Check for link - * @hw: pointer to the HW structure - * - * If sgmii is enabled, then use the pcs register to determine link, otherwise - * use the generic interface for determining link. - */ -static s32 igc_check_for_link_base(struct igc_hw *hw) -{ - s32 ret_val = 0; - - ret_val = igc_check_for_copper_link(hw); - - return ret_val; -} - -/** * igc_reset_hw_base - Reset hardware * @hw: pointer to the HW structure * @@ -124,22 +108,6 @@ static s32 igc_reset_hw_base(struct igc_hw *hw) } /** - * igc_get_phy_id_base - Retrieve PHY addr and id - * @hw: pointer to the HW structure - * - * Retrieves the PHY address and ID for both PHY's which do and do not use - * sgmi interface. - */ -static s32 igc_get_phy_id_base(struct igc_hw *hw) -{ - s32 ret_val = 0; - - ret_val = igc_get_phy_id(hw); - - return ret_val; -} - -/** * igc_init_nvm_params_base - Init NVM func ptrs. * @hw: pointer to the HW structure */ @@ -163,6 +131,7 @@ static s32 igc_init_nvm_params_base(struct igc_hw *hw) if (size > 15) size = 15; + nvm->type = igc_nvm_eeprom_spi; nvm->word_size = BIT(size); nvm->opcode_bits = 8; nvm->delay_usec = 1; @@ -261,11 +230,11 @@ static s32 igc_init_phy_params_base(struct igc_hw *hw) goto out; } - ret_val = igc_get_phy_id_base(hw); + ret_val = igc_get_phy_id(hw); if (ret_val) return ret_val; - igc_check_for_link_base(hw); + igc_check_for_copper_link(hw); /* Verify phy id and set remaining function pointers */ switch (phy->id) { @@ -350,26 +319,6 @@ static void igc_release_phy_base(struct igc_hw *hw) } /** - * igc_get_link_up_info_base - Get link speed/duplex info - * @hw: pointer to the HW structure - * @speed: stores the current speed - * @duplex: stores the current duplex - * - * This is a wrapper function, if using the serial gigabit media independent - * interface, use PCS to retrieve the link speed and duplex information. - * Otherwise, use the generic function to get the link speed and duplex info. - */ -static s32 igc_get_link_up_info_base(struct igc_hw *hw, u16 *speed, - u16 *duplex) -{ - s32 ret_val; - - ret_val = igc_get_speed_and_duplex_copper(hw, speed, duplex); - - return ret_val; -} - -/** * igc_init_hw_base - Initialize hardware * @hw: pointer to the HW structure * @@ -408,19 +357,6 @@ static s32 igc_init_hw_base(struct igc_hw *hw) } /** - * igc_read_mac_addr_base - Read device MAC address - * @hw: pointer to the HW structure - */ -static s32 igc_read_mac_addr_base(struct igc_hw *hw) -{ - s32 ret_val = 0; - - ret_val = igc_read_mac_addr(hw); - - return ret_val; -} - -/** * igc_power_down_phy_copper_base - Remove link during PHY power down * @hw: pointer to the HW structure * @@ -512,10 +448,10 @@ void igc_rx_fifo_flush_base(struct igc_hw *hw) static struct igc_mac_operations igc_mac_ops_base = { .init_hw = igc_init_hw_base, - .check_for_link = igc_check_for_link_base, + .check_for_link = igc_check_for_copper_link, .rar_set = igc_rar_set, - .read_mac_addr = igc_read_mac_addr_base, - .get_speed_and_duplex = igc_get_link_up_info_base, + .read_mac_addr = igc_read_mac_addr, + .get_speed_and_duplex = igc_get_speed_and_duplex_copper, }; static const struct igc_phy_operations igc_phy_ops_base = { diff --git a/drivers/net/ethernet/intel/igc/igc_base.h b/drivers/net/ethernet/intel/igc/igc_base.h index 35588fa7b8c5..76d4991d7284 100644 --- a/drivers/net/ethernet/intel/igc/igc_base.h +++ b/drivers/net/ethernet/intel/igc/igc_base.h @@ -36,28 +36,6 @@ union igc_adv_tx_desc { #define IGC_RAR_ENTRIES 16 -struct igc_adv_data_desc { - __le64 buffer_addr; /* Address of the descriptor's data buffer */ - union { - u32 data; - struct { - u32 datalen:16; /* Data buffer length */ - u32 rsvd:4; - u32 dtyp:4; /* Descriptor type */ - u32 dcmd:8; /* Descriptor command */ - } config; - } lower; - union { - u32 data; - struct { - u32 status:4; /* Descriptor status */ - u32 idx:4; - u32 popts:6; /* Packet Options */ - u32 paylen:18; /* Payload length */ - } options; - } upper; -}; - /* Receive Descriptor - Advanced */ union igc_adv_rx_desc { struct { @@ -90,9 +68,6 @@ union igc_adv_rx_desc { } wb; /* writeback */ }; -/* Adv Transmit Descriptor Config Masks */ -#define IGC_ADVTXD_PAYLEN_SHIFT 14 /* Adv desc PAYLEN shift */ - /* Additional Transmit Descriptor Control definitions */ #define IGC_TXDCTL_QUEUE_ENABLE 0x02000000 /* Ena specific Tx Queue */ diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h index 8740754ea1fd..7d1bdcd1225a 100644 --- a/drivers/net/ethernet/intel/igc/igc_defines.h +++ b/drivers/net/ethernet/intel/igc/igc_defines.h @@ -4,6 +4,10 @@ #ifndef _IGC_DEFINES_H_ #define _IGC_DEFINES_H_ +/* Number of Transmit and Receive Descriptors must be a multiple of 8 */ +#define REQ_TX_DESCRIPTOR_MULTIPLE 8 +#define REQ_RX_DESCRIPTOR_MULTIPLE 8 + #define IGC_CTRL_EXT_DRV_LOAD 0x10000000 /* Drv loaded bit for FW */ /* PCI Bus Info */ diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c new file mode 100644 index 000000000000..eff37a6c0afa --- /dev/null +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -0,0 +1,1032 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018 Intel Corporation */ + +/* ethtool support for igc */ +#include <linux/pm_runtime.h> + +#include "igc.h" + +static const char igc_priv_flags_strings[][ETH_GSTRING_LEN] = { +#define IGC_PRIV_FLAGS_LEGACY_RX BIT(0) + "legacy-rx", +}; + +#define IGC_PRIV_FLAGS_STR_LEN ARRAY_SIZE(igc_priv_flags_strings) + +static void igc_get_drvinfo(struct net_device *netdev, + struct ethtool_drvinfo *drvinfo) +{ + struct igc_adapter *adapter = netdev_priv(netdev); + + strlcpy(drvinfo->driver, igc_driver_name, sizeof(drvinfo->driver)); + strlcpy(drvinfo->version, igc_driver_version, sizeof(drvinfo->version)); + + /* add fw_version here */ + strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), + sizeof(drvinfo->bus_info)); + + drvinfo->n_priv_flags = IGC_PRIV_FLAGS_STR_LEN; +} + +static int igc_get_regs_len(struct net_device *netdev) +{ + return IGC_REGS_LEN * sizeof(u32); +} + +static void igc_get_regs(struct net_device *netdev, + struct ethtool_regs *regs, void *p) +{ + struct igc_adapter *adapter = netdev_priv(netdev); + struct igc_hw *hw = &adapter->hw; + u32 *regs_buff = p; + u8 i; + + memset(p, 0, IGC_REGS_LEN * sizeof(u32)); + + regs->version = (1u << 24) | (hw->revision_id << 16) | hw->device_id; + + /* General Registers */ + regs_buff[0] = rd32(IGC_CTRL); + regs_buff[1] = rd32(IGC_STATUS); + regs_buff[2] = rd32(IGC_CTRL_EXT); + regs_buff[3] = rd32(IGC_MDIC); + regs_buff[4] = rd32(IGC_CONNSW); + + /* NVM Register */ + regs_buff[5] = rd32(IGC_EECD); + + /* Interrupt */ + /* Reading EICS for EICR because they read the + * same but EICS does not clear on read + */ + regs_buff[6] = rd32(IGC_EICS); + regs_buff[7] = rd32(IGC_EICS); + regs_buff[8] = rd32(IGC_EIMS); + regs_buff[9] = rd32(IGC_EIMC); + regs_buff[10] = rd32(IGC_EIAC); + regs_buff[11] = rd32(IGC_EIAM); + /* Reading ICS for ICR because they read the + * same but ICS does not clear on read + */ + regs_buff[12] = rd32(IGC_ICS); + regs_buff[13] = rd32(IGC_ICS); + regs_buff[14] = rd32(IGC_IMS); + regs_buff[15] = rd32(IGC_IMC); + regs_buff[16] = rd32(IGC_IAC); + regs_buff[17] = rd32(IGC_IAM); + + /* Flow Control */ + regs_buff[18] = rd32(IGC_FCAL); + regs_buff[19] = rd32(IGC_FCAH); + regs_buff[20] = rd32(IGC_FCTTV); + regs_buff[21] = rd32(IGC_FCRTL); + regs_buff[22] = rd32(IGC_FCRTH); + regs_buff[23] = rd32(IGC_FCRTV); + + /* Receive */ + regs_buff[24] = rd32(IGC_RCTL); + regs_buff[25] = rd32(IGC_RXCSUM); + regs_buff[26] = rd32(IGC_RLPML); + regs_buff[27] = rd32(IGC_RFCTL); + + /* Transmit */ + regs_buff[28] = rd32(IGC_TCTL); + regs_buff[29] = rd32(IGC_TIPG); + + /* Wake Up */ + + /* MAC */ + + /* Statistics */ + regs_buff[30] = adapter->stats.crcerrs; + regs_buff[31] = adapter->stats.algnerrc; + regs_buff[32] = adapter->stats.symerrs; + regs_buff[33] = adapter->stats.rxerrc; + regs_buff[34] = adapter->stats.mpc; + regs_buff[35] = adapter->stats.scc; + regs_buff[36] = adapter->stats.ecol; + regs_buff[37] = adapter->stats.mcc; + regs_buff[38] = adapter->stats.latecol; + regs_buff[39] = adapter->stats.colc; + regs_buff[40] = adapter->stats.dc; + regs_buff[41] = adapter->stats.tncrs; + regs_buff[42] = adapter->stats.sec; + regs_buff[43] = adapter->stats.htdpmc; + regs_buff[44] = adapter->stats.rlec; + regs_buff[45] = adapter->stats.xonrxc; + regs_buff[46] = adapter->stats.xontxc; + regs_buff[47] = adapter->stats.xoffrxc; + regs_buff[48] = adapter->stats.xofftxc; + regs_buff[49] = adapter->stats.fcruc; + regs_buff[50] = adapter->stats.prc64; + regs_buff[51] = adapter->stats.prc127; + regs_buff[52] = adapter->stats.prc255; + regs_buff[53] = adapter->stats.prc511; + regs_buff[54] = adapter->stats.prc1023; + regs_buff[55] = adapter->stats.prc1522; + regs_buff[56] = adapter->stats.gprc; + regs_buff[57] = adapter->stats.bprc; + regs_buff[58] = adapter->stats.mprc; + regs_buff[59] = adapter->stats.gptc; + regs_buff[60] = adapter->stats.gorc; + regs_buff[61] = adapter->stats.gotc; + regs_buff[62] = adapter->stats.rnbc; + regs_buff[63] = adapter->stats.ruc; + regs_buff[64] = adapter->stats.rfc; + regs_buff[65] = adapter->stats.roc; + regs_buff[66] = adapter->stats.rjc; + regs_buff[67] = adapter->stats.mgprc; + regs_buff[68] = adapter->stats.mgpdc; + regs_buff[69] = adapter->stats.mgptc; + regs_buff[70] = adapter->stats.tor; + regs_buff[71] = adapter->stats.tot; + regs_buff[72] = adapter->stats.tpr; + regs_buff[73] = adapter->stats.tpt; + regs_buff[74] = adapter->stats.ptc64; + regs_buff[75] = adapter->stats.ptc127; + regs_buff[76] = adapter->stats.ptc255; + regs_buff[77] = adapter->stats.ptc511; + regs_buff[78] = adapter->stats.ptc1023; + regs_buff[79] = adapter->stats.ptc1522; + regs_buff[80] = adapter->stats.mptc; + regs_buff[81] = adapter->stats.bptc; + regs_buff[82] = adapter->stats.tsctc; + regs_buff[83] = adapter->stats.iac; + regs_buff[84] = adapter->stats.rpthc; + regs_buff[85] = adapter->stats.hgptc; + regs_buff[86] = adapter->stats.hgorc; + regs_buff[87] = adapter->stats.hgotc; + regs_buff[88] = adapter->stats.lenerrs; + regs_buff[89] = adapter->stats.scvpc; + regs_buff[90] = adapter->stats.hrmpc; + + for (i = 0; i < 4; i++) + regs_buff[91 + i] = rd32(IGC_SRRCTL(i)); + for (i = 0; i < 4; i++) + regs_buff[95 + i] = rd32(IGC_PSRTYPE(i)); + for (i = 0; i < 4; i++) + regs_buff[99 + i] = rd32(IGC_RDBAL(i)); + for (i = 0; i < 4; i++) + regs_buff[103 + i] = rd32(IGC_RDBAH(i)); + for (i = 0; i < 4; i++) + regs_buff[107 + i] = rd32(IGC_RDLEN(i)); + for (i = 0; i < 4; i++) + regs_buff[111 + i] = rd32(IGC_RDH(i)); + for (i = 0; i < 4; i++) + regs_buff[115 + i] = rd32(IGC_RDT(i)); + for (i = 0; i < 4; i++) + regs_buff[119 + i] = rd32(IGC_RXDCTL(i)); + + for (i = 0; i < 10; i++) + regs_buff[123 + i] = rd32(IGC_EITR(i)); + for (i = 0; i < 16; i++) + regs_buff[139 + i] = rd32(IGC_RAL(i)); + for (i = 0; i < 16; i++) + regs_buff[145 + i] = rd32(IGC_RAH(i)); + + for (i = 0; i < 4; i++) + regs_buff[149 + i] = rd32(IGC_TDBAL(i)); + for (i = 0; i < 4; i++) + regs_buff[152 + i] = rd32(IGC_TDBAH(i)); + for (i = 0; i < 4; i++) + regs_buff[156 + i] = rd32(IGC_TDLEN(i)); + for (i = 0; i < 4; i++) + regs_buff[160 + i] = rd32(IGC_TDH(i)); + for (i = 0; i < 4; i++) + regs_buff[164 + i] = rd32(IGC_TDT(i)); + for (i = 0; i < 4; i++) + regs_buff[168 + i] = rd32(IGC_TXDCTL(i)); +} + +static u32 igc_get_msglevel(struct net_device *netdev) +{ + struct igc_adapter *adapter = netdev_priv(netdev); + + return adapter->msg_enable; +} + +static void igc_set_msglevel(struct net_device *netdev, u32 data) +{ + struct igc_adapter *adapter = netdev_priv(netdev); + + adapter->msg_enable = data; +} + +static int igc_nway_reset(struct net_device *netdev) +{ + struct igc_adapter *adapter = netdev_priv(netdev); + + if (netif_running(netdev)) + igc_reinit_locked(adapter); + return 0; +} + +static u32 igc_get_link(struct net_device *netdev) +{ + struct igc_adapter *adapter = netdev_priv(netdev); + struct igc_mac_info *mac = &adapter->hw.mac; + + /* If the link is not reported up to netdev, interrupts are disabled, + * and so the physical link state may have changed since we last + * looked. Set get_link_status to make sure that the true link + * state is interrogated, rather than pulling a cached and possibly + * stale link state from the driver. + */ + if (!netif_carrier_ok(netdev)) + mac->get_link_status = 1; + + return igc_has_link(adapter); +} + +static int igc_get_eeprom_len(struct net_device *netdev) +{ + struct igc_adapter *adapter = netdev_priv(netdev); + + return adapter->hw.nvm.word_size * 2; +} + +static int igc_get_eeprom(struct net_device *netdev, + struct ethtool_eeprom *eeprom, u8 *bytes) +{ + struct igc_adapter *adapter = netdev_priv(netdev); + struct igc_hw *hw = &adapter->hw; + int first_word, last_word; + u16 *eeprom_buff; + int ret_val = 0; + u16 i; + + if (eeprom->len == 0) + return -EINVAL; + + eeprom->magic = hw->vendor_id | (hw->device_id << 16); + + first_word = eeprom->offset >> 1; + last_word = (eeprom->offset + eeprom->len - 1) >> 1; + + eeprom_buff = kmalloc_array(last_word - first_word + 1, sizeof(u16), + GFP_KERNEL); + if (!eeprom_buff) + return -ENOMEM; + + if (hw->nvm.type == igc_nvm_eeprom_spi) { + ret_val = hw->nvm.ops.read(hw, first_word, + last_word - first_word + 1, + eeprom_buff); + } else { + for (i = 0; i < last_word - first_word + 1; i++) { + ret_val = hw->nvm.ops.read(hw, first_word + i, 1, + &eeprom_buff[i]); + if (ret_val) + break; + } + } + + /* Device's eeprom is always little-endian, word addressable */ + for (i = 0; i < last_word - first_word + 1; i++) + le16_to_cpus(&eeprom_buff[i]); + + memcpy(bytes, (u8 *)eeprom_buff + (eeprom->offset & 1), + eeprom->len); + kfree(eeprom_buff); + + return ret_val; +} + +static int igc_set_eeprom(struct net_device *netdev, + struct ethtool_eeprom *eeprom, u8 *bytes) +{ + struct igc_adapter *adapter = netdev_priv(netdev); + struct igc_hw *hw = &adapter->hw; + int max_len, first_word, last_word, ret_val = 0; + u16 *eeprom_buff; + void *ptr; + u16 i; + + if (eeprom->len == 0) + return -EOPNOTSUPP; + + if (hw->mac.type >= igc_i225 && + !igc_get_flash_presence_i225(hw)) { + return -EOPNOTSUPP; + } + + if (eeprom->magic != (hw->vendor_id | (hw->device_id << 16))) + return -EFAULT; + + max_len = hw->nvm.word_size * 2; + + first_word = eeprom->offset >> 1; + last_word = (eeprom->offset + eeprom->len - 1) >> 1; + eeprom_buff = kmalloc(max_len, GFP_KERNEL); + if (!eeprom_buff) + return -ENOMEM; + + ptr = (void *)eeprom_buff; + + if (eeprom->offset & 1) { + /* need read/modify/write of first changed EEPROM word + * only the second byte of the word is being modified + */ + ret_val = hw->nvm.ops.read(hw, first_word, 1, + &eeprom_buff[0]); + ptr++; + } + if (((eeprom->offset + eeprom->len) & 1) && ret_val == 0) { + /* need read/modify/write of last changed EEPROM word + * only the first byte of the word is being modified + */ + ret_val = hw->nvm.ops.read(hw, last_word, 1, + &eeprom_buff[last_word - first_word]); + } + + /* Device's eeprom is always little-endian, word addressable */ + for (i = 0; i < last_word - first_word + 1; i++) + le16_to_cpus(&eeprom_buff[i]); + + memcpy(ptr, bytes, eeprom->len); + + for (i = 0; i < last_word - first_word + 1; i++) + eeprom_buff[i] = cpu_to_le16(eeprom_buff[i]); + + ret_val = hw->nvm.ops.write(hw, first_word, + last_word - first_word + 1, eeprom_buff); + + /* Update the checksum if nvm write succeeded */ + if (ret_val == 0) + hw->nvm.ops.update(hw); + + /* check if need: igc_set_fw_version(adapter); */ + kfree(eeprom_buff); + return ret_val; +} + +static void igc_get_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring) +{ + struct igc_adapter *adapter = netdev_priv(netdev); + + ring->rx_max_pending = IGC_MAX_RXD; + ring->tx_max_pending = IGC_MAX_TXD; + ring->rx_pending = adapter->rx_ring_count; + ring->tx_pending = adapter->tx_ring_count; +} + +static int igc_set_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring) +{ + struct igc_adapter *adapter = netdev_priv(netdev); + struct igc_ring *temp_ring; + u16 new_rx_count, new_tx_count; + int i, err = 0; + + if (ring->rx_mini_pending || ring->rx_jumbo_pending) + return -EINVAL; + + new_rx_count = min_t(u32, ring->rx_pending, IGC_MAX_RXD); + new_rx_count = max_t(u16, new_rx_count, IGC_MIN_RXD); + new_rx_count = ALIGN(new_rx_count, REQ_RX_DESCRIPTOR_MULTIPLE); + + new_tx_count = min_t(u32, ring->tx_pending, IGC_MAX_TXD); + new_tx_count = max_t(u16, new_tx_count, IGC_MIN_TXD); + new_tx_count = ALIGN(new_tx_count, REQ_TX_DESCRIPTOR_MULTIPLE); + + if (new_tx_count == adapter->tx_ring_count && + new_rx_count == adapter->rx_ring_count) { + /* nothing to do */ + return 0; + } + + while (test_and_set_bit(__IGC_RESETTING, &adapter->state)) + usleep_range(1000, 2000); + + if (!netif_running(adapter->netdev)) { + for (i = 0; i < adapter->num_tx_queues; i++) + adapter->tx_ring[i]->count = new_tx_count; + for (i = 0; i < adapter->num_rx_queues; i++) + adapter->rx_ring[i]->count = new_rx_count; + adapter->tx_ring_count = new_tx_count; + adapter->rx_ring_count = new_rx_count; + goto clear_reset; + } + + if (adapter->num_tx_queues > adapter->num_rx_queues) + temp_ring = vmalloc(array_size(sizeof(struct igc_ring), + adapter->num_tx_queues)); + else + temp_ring = vmalloc(array_size(sizeof(struct igc_ring), + adapter->num_rx_queues)); + + if (!temp_ring) { + err = -ENOMEM; + goto clear_reset; + } + + igc_down(adapter); + + /* We can't just free everything and then setup again, + * because the ISRs in MSI-X mode get passed pointers + * to the Tx and Rx ring structs. + */ + if (new_tx_count != adapter->tx_ring_count) { + for (i = 0; i < adapter->num_tx_queues; i++) { + memcpy(&temp_ring[i], adapter->tx_ring[i], + sizeof(struct igc_ring)); + + temp_ring[i].count = new_tx_count; + err = igc_setup_tx_resources(&temp_ring[i]); + if (err) { + while (i) { + i--; + igc_free_tx_resources(&temp_ring[i]); + } + goto err_setup; + } + } + + for (i = 0; i < adapter->num_tx_queues; i++) { + igc_free_tx_resources(adapter->tx_ring[i]); + + memcpy(adapter->tx_ring[i], &temp_ring[i], + sizeof(struct igc_ring)); + } + + adapter->tx_ring_count = new_tx_count; + } + + if (new_rx_count != adapter->rx_ring_count) { + for (i = 0; i < adapter->num_rx_queues; i++) { + memcpy(&temp_ring[i], adapter->rx_ring[i], + sizeof(struct igc_ring)); + + temp_ring[i].count = new_rx_count; + err = igc_setup_rx_resources(&temp_ring[i]); + if (err) { + while (i) { + i--; + igc_free_rx_resources(&temp_ring[i]); + } + goto err_setup; + } + } + + for (i = 0; i < adapter->num_rx_queues; i++) { + igc_free_rx_resources(adapter->rx_ring[i]); + + memcpy(adapter->rx_ring[i], &temp_ring[i], + sizeof(struct igc_ring)); + } + + adapter->rx_ring_count = new_rx_count; + } +err_setup: + igc_up(adapter); + vfree(temp_ring); +clear_reset: + clear_bit(__IGC_RESETTING, &adapter->state); + return err; +} + +static void igc_get_pauseparam(struct net_device *netdev, + struct ethtool_pauseparam *pause) +{ + struct igc_adapter *adapter = netdev_priv(netdev); + struct igc_hw *hw = &adapter->hw; + + pause->autoneg = + (adapter->fc_autoneg ? AUTONEG_ENABLE : AUTONEG_DISABLE); + + if (hw->fc.current_mode == igc_fc_rx_pause) { + pause->rx_pause = 1; + } else if (hw->fc.current_mode == igc_fc_tx_pause) { + pause->tx_pause = 1; + } else if (hw->fc.current_mode == igc_fc_full) { + pause->rx_pause = 1; + pause->tx_pause = 1; + } +} + +static int igc_set_pauseparam(struct net_device *netdev, + struct ethtool_pauseparam *pause) +{ + struct igc_adapter *adapter = netdev_priv(netdev); + struct igc_hw *hw = &adapter->hw; + int retval = 0; + + adapter->fc_autoneg = pause->autoneg; + + while (test_and_set_bit(__IGC_RESETTING, &adapter->state)) + usleep_range(1000, 2000); + + if (adapter->fc_autoneg == AUTONEG_ENABLE) { + hw->fc.requested_mode = igc_fc_default; + if (netif_running(adapter->netdev)) { + igc_down(adapter); + igc_up(adapter); + } else { + igc_reset(adapter); + } + } else { + if (pause->rx_pause && pause->tx_pause) + hw->fc.requested_mode = igc_fc_full; + else if (pause->rx_pause && !pause->tx_pause) + hw->fc.requested_mode = igc_fc_rx_pause; + else if (!pause->rx_pause && pause->tx_pause) + hw->fc.requested_mode = igc_fc_tx_pause; + else if (!pause->rx_pause && !pause->tx_pause) + hw->fc.requested_mode = igc_fc_none; + + hw->fc.current_mode = hw->fc.requested_mode; + + retval = ((hw->phy.media_type == igc_media_type_copper) ? + igc_force_mac_fc(hw) : igc_setup_link(hw)); + } + + clear_bit(__IGC_RESETTING, &adapter->state); + return retval; +} + +static int igc_get_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec) +{ + struct igc_adapter *adapter = netdev_priv(netdev); + + if (adapter->rx_itr_setting <= 3) + ec->rx_coalesce_usecs = adapter->rx_itr_setting; + else + ec->rx_coalesce_usecs = adapter->rx_itr_setting >> 2; + + if (!(adapter->flags & IGC_FLAG_QUEUE_PAIRS)) { + if (adapter->tx_itr_setting <= 3) + ec->tx_coalesce_usecs = adapter->tx_itr_setting; + else + ec->tx_coalesce_usecs = adapter->tx_itr_setting >> 2; + } + + return 0; +} + +static int igc_set_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec) +{ + struct igc_adapter *adapter = netdev_priv(netdev); + int i; + + if (ec->rx_max_coalesced_frames || + ec->rx_coalesce_usecs_irq || + ec->rx_max_coalesced_frames_irq || + ec->tx_max_coalesced_frames || + ec->tx_coalesce_usecs_irq || + ec->stats_block_coalesce_usecs || + ec->use_adaptive_rx_coalesce || + ec->use_adaptive_tx_coalesce || + ec->pkt_rate_low || + ec->rx_coalesce_usecs_low || + ec->rx_max_coalesced_frames_low || + ec->tx_coalesce_usecs_low || + ec->tx_max_coalesced_frames_low || + ec->pkt_rate_high || + ec->rx_coalesce_usecs_high || + ec->rx_max_coalesced_frames_high || + ec->tx_coalesce_usecs_high || + ec->tx_max_coalesced_frames_high || + ec->rate_sample_interval) + return -ENOTSUPP; + + if (ec->rx_coalesce_usecs > IGC_MAX_ITR_USECS || + (ec->rx_coalesce_usecs > 3 && + ec->rx_coalesce_usecs < IGC_MIN_ITR_USECS) || + ec->rx_coalesce_usecs == 2) + return -EINVAL; + + if (ec->tx_coalesce_usecs > IGC_MAX_ITR_USECS || + (ec->tx_coalesce_usecs > 3 && + ec->tx_coalesce_usecs < IGC_MIN_ITR_USECS) || + ec->tx_coalesce_usecs == 2) + return -EINVAL; + + if ((adapter->flags & IGC_FLAG_QUEUE_PAIRS) && ec->tx_coalesce_usecs) + return -EINVAL; + + /* If ITR is disabled, disable DMAC */ + if (ec->rx_coalesce_usecs == 0) { + if (adapter->flags & IGC_FLAG_DMAC) + adapter->flags &= ~IGC_FLAG_DMAC; + } + + /* convert to rate of irq's per second */ + if (ec->rx_coalesce_usecs && ec->rx_coalesce_usecs <= 3) + adapter->rx_itr_setting = ec->rx_coalesce_usecs; + else + adapter->rx_itr_setting = ec->rx_coalesce_usecs << 2; + + /* convert to rate of irq's per second */ + if (adapter->flags & IGC_FLAG_QUEUE_PAIRS) + adapter->tx_itr_setting = adapter->rx_itr_setting; + else if (ec->tx_coalesce_usecs && ec->tx_coalesce_usecs <= 3) + adapter->tx_itr_setting = ec->tx_coalesce_usecs; + else + adapter->tx_itr_setting = ec->tx_coalesce_usecs << 2; + + for (i = 0; i < adapter->num_q_vectors; i++) { + struct igc_q_vector *q_vector = adapter->q_vector[i]; + + q_vector->tx.work_limit = adapter->tx_work_limit; + if (q_vector->rx.ring) + q_vector->itr_val = adapter->rx_itr_setting; + else + q_vector->itr_val = adapter->tx_itr_setting; + if (q_vector->itr_val && q_vector->itr_val <= 3) + q_vector->itr_val = IGC_START_ITR; + q_vector->set_itr = 1; + } + + return 0; +} + +void igc_write_rss_indir_tbl(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + u32 reg = IGC_RETA(0); + u32 shift = 0; + int i = 0; + + while (i < IGC_RETA_SIZE) { + u32 val = 0; + int j; + + for (j = 3; j >= 0; j--) { + val <<= 8; + val |= adapter->rss_indir_tbl[i + j]; + } + + wr32(reg, val << shift); + reg += 4; + i += 4; + } +} + +static u32 igc_get_rxfh_indir_size(struct net_device *netdev) +{ + return IGC_RETA_SIZE; +} + +static int igc_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, + u8 *hfunc) +{ + struct igc_adapter *adapter = netdev_priv(netdev); + int i; + + if (hfunc) + *hfunc = ETH_RSS_HASH_TOP; + if (!indir) + return 0; + for (i = 0; i < IGC_RETA_SIZE; i++) + indir[i] = adapter->rss_indir_tbl[i]; + + return 0; +} + +static int igc_set_rxfh(struct net_device *netdev, const u32 *indir, + const u8 *key, const u8 hfunc) +{ + struct igc_adapter *adapter = netdev_priv(netdev); + u32 num_queues; + int i; + + /* We do not allow change in unsupported parameters */ + if (key || + (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)) + return -EOPNOTSUPP; + if (!indir) + return 0; + + num_queues = adapter->rss_queues; + + /* Verify user input. */ + for (i = 0; i < IGC_RETA_SIZE; i++) + if (indir[i] >= num_queues) + return -EINVAL; + + for (i = 0; i < IGC_RETA_SIZE; i++) + adapter->rss_indir_tbl[i] = indir[i]; + + igc_write_rss_indir_tbl(adapter); + + return 0; +} + +static unsigned int igc_max_channels(struct igc_adapter *adapter) +{ + return igc_get_max_rss_queues(adapter); +} + +static void igc_get_channels(struct net_device *netdev, + struct ethtool_channels *ch) +{ + struct igc_adapter *adapter = netdev_priv(netdev); + + /* Report maximum channels */ + ch->max_combined = igc_max_channels(adapter); + + /* Report info for other vector */ + if (adapter->flags & IGC_FLAG_HAS_MSIX) { + ch->max_other = NON_Q_VECTORS; + ch->other_count = NON_Q_VECTORS; + } + + ch->combined_count = adapter->rss_queues; +} + +static int igc_set_channels(struct net_device *netdev, + struct ethtool_channels *ch) +{ + struct igc_adapter *adapter = netdev_priv(netdev); + unsigned int count = ch->combined_count; + unsigned int max_combined = 0; + + /* Verify they are not requesting separate vectors */ + if (!count || ch->rx_count || ch->tx_count) + return -EINVAL; + + /* Verify other_count is valid and has not been changed */ + if (ch->other_count != NON_Q_VECTORS) + return -EINVAL; + + /* Verify the number of channels doesn't exceed hw limits */ + max_combined = igc_max_channels(adapter); + if (count > max_combined) + return -EINVAL; + + if (count != adapter->rss_queues) { + adapter->rss_queues = count; + igc_set_flag_queue_pairs(adapter, max_combined); + + /* Hardware has to reinitialize queues and interrupts to + * match the new configuration. + */ + return igc_reinit_queues(adapter); + } + + return 0; +} + +static u32 igc_get_priv_flags(struct net_device *netdev) +{ + struct igc_adapter *adapter = netdev_priv(netdev); + u32 priv_flags = 0; + + if (adapter->flags & IGC_FLAG_RX_LEGACY) + priv_flags |= IGC_PRIV_FLAGS_LEGACY_RX; + + return priv_flags; +} + +static int igc_set_priv_flags(struct net_device *netdev, u32 priv_flags) +{ + struct igc_adapter *adapter = netdev_priv(netdev); + unsigned int flags = adapter->flags; + + flags &= ~IGC_FLAG_RX_LEGACY; + if (priv_flags & IGC_PRIV_FLAGS_LEGACY_RX) + flags |= IGC_FLAG_RX_LEGACY; + + if (flags != adapter->flags) { + adapter->flags = flags; + + /* reset interface to repopulate queues */ + if (netif_running(netdev)) + igc_reinit_locked(adapter); + } + + return 0; +} + +static int igc_ethtool_begin(struct net_device *netdev) +{ + struct igc_adapter *adapter = netdev_priv(netdev); + + pm_runtime_get_sync(&adapter->pdev->dev); + return 0; +} + +static void igc_ethtool_complete(struct net_device *netdev) +{ + struct igc_adapter *adapter = netdev_priv(netdev); + + pm_runtime_put(&adapter->pdev->dev); +} + +static int igc_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) +{ + struct igc_adapter *adapter = netdev_priv(netdev); + struct igc_hw *hw = &adapter->hw; + u32 status; + u32 speed; + + ethtool_link_ksettings_zero_link_mode(cmd, supported); + ethtool_link_ksettings_zero_link_mode(cmd, advertising); + + /* supported link modes */ + ethtool_link_ksettings_add_link_mode(cmd, supported, 10baseT_Half); + ethtool_link_ksettings_add_link_mode(cmd, supported, 10baseT_Full); + ethtool_link_ksettings_add_link_mode(cmd, supported, 100baseT_Half); + ethtool_link_ksettings_add_link_mode(cmd, supported, 100baseT_Full); + ethtool_link_ksettings_add_link_mode(cmd, supported, 1000baseT_Full); + ethtool_link_ksettings_add_link_mode(cmd, supported, 2500baseT_Full); + + /* twisted pair */ + cmd->base.port = PORT_TP; + cmd->base.phy_address = hw->phy.addr; + + /* advertising link modes */ + ethtool_link_ksettings_add_link_mode(cmd, advertising, 10baseT_Half); + ethtool_link_ksettings_add_link_mode(cmd, advertising, 10baseT_Full); + ethtool_link_ksettings_add_link_mode(cmd, advertising, 100baseT_Half); + ethtool_link_ksettings_add_link_mode(cmd, advertising, 100baseT_Full); + ethtool_link_ksettings_add_link_mode(cmd, advertising, 1000baseT_Full); + ethtool_link_ksettings_add_link_mode(cmd, advertising, 2500baseT_Full); + + /* set autoneg settings */ + if (hw->mac.autoneg == 1) { + ethtool_link_ksettings_add_link_mode(cmd, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + Autoneg); + } + + switch (hw->fc.requested_mode) { + case igc_fc_full: + ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause); + break; + case igc_fc_rx_pause: + ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + Asym_Pause); + break; + case igc_fc_tx_pause: + ethtool_link_ksettings_add_link_mode(cmd, advertising, + Asym_Pause); + break; + default: + ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + Asym_Pause); + } + + status = rd32(IGC_STATUS); + + if (status & IGC_STATUS_LU) { + if (status & IGC_STATUS_SPEED_1000) { + /* For I225, STATUS will indicate 1G speed in both + * 1 Gbps and 2.5 Gbps link modes. + * An additional bit is used + * to differentiate between 1 Gbps and 2.5 Gbps. + */ + if (hw->mac.type == igc_i225 && + (status & IGC_STATUS_SPEED_2500)) { + speed = SPEED_2500; + hw_dbg("2500 Mbs, "); + } else { + speed = SPEED_1000; + hw_dbg("1000 Mbs, "); + } + } else if (status & IGC_STATUS_SPEED_100) { + speed = SPEED_100; + hw_dbg("100 Mbs, "); + } else { + speed = SPEED_10; + hw_dbg("10 Mbs, "); + } + if ((status & IGC_STATUS_FD) || + hw->phy.media_type != igc_media_type_copper) + cmd->base.duplex = DUPLEX_FULL; + else + cmd->base.duplex = DUPLEX_HALF; + } else { + speed = SPEED_UNKNOWN; + cmd->base.duplex = DUPLEX_UNKNOWN; + } + cmd->base.speed = speed; + if (hw->mac.autoneg) + cmd->base.autoneg = AUTONEG_ENABLE; + else + cmd->base.autoneg = AUTONEG_DISABLE; + + /* MDI-X => 2; MDI =>1; Invalid =>0 */ + if (hw->phy.media_type == igc_media_type_copper) + cmd->base.eth_tp_mdix = hw->phy.is_mdix ? ETH_TP_MDI_X : + ETH_TP_MDI; + else + cmd->base.eth_tp_mdix = ETH_TP_MDI_INVALID; + + if (hw->phy.mdix == AUTO_ALL_MODES) + cmd->base.eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO; + else + cmd->base.eth_tp_mdix_ctrl = hw->phy.mdix; + + return 0; +} + +static int igc_set_link_ksettings(struct net_device *netdev, + const struct ethtool_link_ksettings *cmd) +{ + struct igc_adapter *adapter = netdev_priv(netdev); + struct igc_hw *hw = &adapter->hw; + u32 advertising; + + /* When adapter in resetting mode, autoneg/speed/duplex + * cannot be changed + */ + if (igc_check_reset_block(hw)) { + dev_err(&adapter->pdev->dev, + "Cannot change link characteristics when reset is active.\n"); + return -EINVAL; + } + + /* MDI setting is only allowed when autoneg enabled because + * some hardware doesn't allow MDI setting when speed or + * duplex is forced. + */ + if (cmd->base.eth_tp_mdix_ctrl) { + if (cmd->base.eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO && + cmd->base.autoneg != AUTONEG_ENABLE) { + dev_err(&adapter->pdev->dev, "forcing MDI/MDI-X state is not supported when link speed and/or duplex are forced\n"); + return -EINVAL; + } + } + + while (test_and_set_bit(__IGC_RESETTING, &adapter->state)) + usleep_range(1000, 2000); + + ethtool_convert_link_mode_to_legacy_u32(&advertising, + cmd->link_modes.advertising); + + if (cmd->base.autoneg == AUTONEG_ENABLE) { + hw->mac.autoneg = 1; + hw->phy.autoneg_advertised = advertising; + if (adapter->fc_autoneg) + hw->fc.requested_mode = igc_fc_default; + } else { + /* calling this overrides forced MDI setting */ + dev_info(&adapter->pdev->dev, + "Force mode currently not supported\n"); + } + + /* MDI-X => 2; MDI => 1; Auto => 3 */ + if (cmd->base.eth_tp_mdix_ctrl) { + /* fix up the value for auto (3 => 0) as zero is mapped + * internally to auto + */ + if (cmd->base.eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO) + hw->phy.mdix = AUTO_ALL_MODES; + else + hw->phy.mdix = cmd->base.eth_tp_mdix_ctrl; + } + + /* reset the link */ + if (netif_running(adapter->netdev)) { + igc_down(adapter); + igc_up(adapter); + } else { + igc_reset(adapter); + } + + clear_bit(__IGC_RESETTING, &adapter->state); + + return 0; +} + +static const struct ethtool_ops igc_ethtool_ops = { + .get_drvinfo = igc_get_drvinfo, + .get_regs_len = igc_get_regs_len, + .get_regs = igc_get_regs, + .get_msglevel = igc_get_msglevel, + .set_msglevel = igc_set_msglevel, + .nway_reset = igc_nway_reset, + .get_link = igc_get_link, + .get_eeprom_len = igc_get_eeprom_len, + .get_eeprom = igc_get_eeprom, + .set_eeprom = igc_set_eeprom, + .get_ringparam = igc_get_ringparam, + .set_ringparam = igc_set_ringparam, + .get_pauseparam = igc_get_pauseparam, + .set_pauseparam = igc_set_pauseparam, + .get_coalesce = igc_get_coalesce, + .set_coalesce = igc_set_coalesce, + .get_rxfh_indir_size = igc_get_rxfh_indir_size, + .get_rxfh = igc_get_rxfh, + .set_rxfh = igc_set_rxfh, + .get_channels = igc_get_channels, + .set_channels = igc_set_channels, + .get_priv_flags = igc_get_priv_flags, + .set_priv_flags = igc_set_priv_flags, + .begin = igc_ethtool_begin, + .complete = igc_ethtool_complete, + .get_link_ksettings = igc_get_link_ksettings, + .set_link_ksettings = igc_set_link_ksettings, +}; + +void igc_set_ethtool_ops(struct net_device *netdev) +{ + netdev->ethtool_ops = &igc_ethtool_ops; +} diff --git a/drivers/net/ethernet/intel/igc/igc_hw.h b/drivers/net/ethernet/intel/igc/igc_hw.h index c50414f48f0d..7c88b7bd4799 100644 --- a/drivers/net/ethernet/intel/igc/igc_hw.h +++ b/drivers/net/ethernet/intel/igc/igc_hw.h @@ -55,6 +55,7 @@ enum igc_media_type { enum igc_nvm_type { igc_nvm_unknown = 0, + igc_nvm_eeprom_spi, igc_nvm_flash_hw, igc_nvm_invm, }; diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index f20183037fb2..87a11879bf2d 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -12,6 +12,8 @@ #define DRV_VERSION "0.0.1-k" #define DRV_SUMMARY "Intel(R) 2.5G Ethernet Linux Driver" +#define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK) + static int debug = -1; MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); @@ -66,7 +68,7 @@ enum latency_range { latency_invalid = 255 }; -static void igc_reset(struct igc_adapter *adapter) +void igc_reset(struct igc_adapter *adapter) { struct pci_dev *pdev = adapter->pdev; struct igc_hw *hw = &adapter->hw; @@ -150,7 +152,7 @@ static void igc_get_hw_control(struct igc_adapter *adapter) * * Free all transmit software resources */ -static void igc_free_tx_resources(struct igc_ring *tx_ring) +void igc_free_tx_resources(struct igc_ring *tx_ring) { igc_clean_tx_ring(tx_ring); @@ -261,7 +263,7 @@ static void igc_clean_all_tx_rings(struct igc_adapter *adapter) * * Return 0 on success, negative on failure */ -static int igc_setup_tx_resources(struct igc_ring *tx_ring) +int igc_setup_tx_resources(struct igc_ring *tx_ring) { struct device *dev = tx_ring->dev; int size = 0; @@ -381,7 +383,7 @@ static void igc_clean_all_rx_rings(struct igc_adapter *adapter) * * Free all receive software resources */ -static void igc_free_rx_resources(struct igc_ring *rx_ring) +void igc_free_rx_resources(struct igc_ring *rx_ring) { igc_clean_rx_ring(rx_ring); @@ -418,7 +420,7 @@ static void igc_free_all_rx_resources(struct igc_adapter *adapter) * * Returns 0 on success, negative on failure */ -static int igc_setup_rx_resources(struct igc_ring *rx_ring) +int igc_setup_rx_resources(struct igc_ring *rx_ring) { struct device *dev = rx_ring->dev; int size, desc_len; @@ -1703,7 +1705,7 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget) * igc_up - Open the interface and prepare it to handle traffic * @adapter: board private structure */ -static void igc_up(struct igc_adapter *adapter) +void igc_up(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; int i = 0; @@ -1748,7 +1750,7 @@ static void igc_nfc_filter_exit(struct igc_adapter *adapter) * igc_down - Close the interface * @adapter: board private structure */ -static void igc_down(struct igc_adapter *adapter) +void igc_down(struct igc_adapter *adapter) { struct net_device *netdev = adapter->netdev; struct igc_hw *hw = &adapter->hw; @@ -1810,7 +1812,7 @@ static void igc_down(struct igc_adapter *adapter) igc_clean_all_rx_rings(adapter); } -static void igc_reinit_locked(struct igc_adapter *adapter) +void igc_reinit_locked(struct igc_adapter *adapter) { WARN_ON(in_interrupt()); while (test_and_set_bit(__IGC_RESETTING, &adapter->state)) @@ -1922,7 +1924,7 @@ static void igc_configure(struct igc_adapter *adapter) /** * igc_rar_set_index - Sync RAL[index] and RAH[index] registers with MAC table - * @adapter: Pointer to adapter structure + * @adapter: address of board private structure * @index: Index of the RAR entry which need to be synced with MAC table */ static void igc_rar_set_index(struct igc_adapter *adapter, u32 index) @@ -2298,7 +2300,7 @@ static void igc_update_phy_info(struct timer_list *t) * igc_has_link - check shared code for link and determine up/down * @adapter: pointer to driver private info */ -static bool igc_has_link(struct igc_adapter *adapter) +bool igc_has_link(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; bool link_active = false; @@ -2956,22 +2958,21 @@ static int igc_alloc_q_vector(struct igc_adapter *adapter, { struct igc_q_vector *q_vector; struct igc_ring *ring; - int ring_count, size; + int ring_count; /* igc only supports 1 Tx and/or 1 Rx queue per vector */ if (txr_count > 1 || rxr_count > 1) return -ENOMEM; ring_count = txr_count + rxr_count; - size = sizeof(struct igc_q_vector) + - (sizeof(struct igc_ring) * ring_count); /* allocate q_vector and rings */ q_vector = adapter->q_vector[v_idx]; if (!q_vector) - q_vector = kzalloc(size, GFP_KERNEL); + q_vector = kzalloc(struct_size(q_vector, ring, ring_count), + GFP_KERNEL); else - memset(q_vector, 0, size); + memset(q_vector, 0, struct_size(q_vector, ring, ring_count)); if (!q_vector) return -ENOMEM; @@ -3501,6 +3502,57 @@ u32 igc_rd32(struct igc_hw *hw, u32 reg) return value; } +int igc_set_spd_dplx(struct igc_adapter *adapter, u32 spd, u8 dplx) +{ + struct pci_dev *pdev = adapter->pdev; + struct igc_mac_info *mac = &adapter->hw.mac; + + mac->autoneg = 0; + + /* Make sure dplx is at most 1 bit and lsb of speed is not set + * for the switch() below to work + */ + if ((spd & 1) || (dplx & ~1)) + goto err_inval; + + switch (spd + dplx) { + case SPEED_10 + DUPLEX_HALF: + mac->forced_speed_duplex = ADVERTISE_10_HALF; + break; + case SPEED_10 + DUPLEX_FULL: + mac->forced_speed_duplex = ADVERTISE_10_FULL; + break; + case SPEED_100 + DUPLEX_HALF: + mac->forced_speed_duplex = ADVERTISE_100_HALF; + break; + case SPEED_100 + DUPLEX_FULL: + mac->forced_speed_duplex = ADVERTISE_100_FULL; + break; + case SPEED_1000 + DUPLEX_FULL: + mac->autoneg = 1; + adapter->hw.phy.autoneg_advertised = ADVERTISE_1000_FULL; + break; + case SPEED_1000 + DUPLEX_HALF: /* not supported */ + goto err_inval; + case SPEED_2500 + DUPLEX_FULL: + mac->autoneg = 1; + adapter->hw.phy.autoneg_advertised = ADVERTISE_2500_FULL; + break; + case SPEED_2500 + DUPLEX_HALF: /* not supported */ + default: + goto err_inval; + } + + /* clear MDI, MDI(-X) override is only allowed when autoneg enabled */ + adapter->hw.phy.mdix = AUTO_ALL_MODES; + + return 0; + +err_inval: + dev_err(&pdev->dev, "Unsupported Speed/Duplex configuration\n"); + return -EINVAL; +} + /** * igc_probe - Device Initialization Routine * @pdev: PCI device information struct @@ -3568,7 +3620,7 @@ static int igc_probe(struct pci_dev *pdev, hw = &adapter->hw; hw->back = adapter; adapter->port_num = hw->bus.func; - adapter->msg_enable = GENMASK(debug - 1, 0); + adapter->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE); err = pci_save_state(pdev); if (err) @@ -3584,7 +3636,7 @@ static int igc_probe(struct pci_dev *pdev, hw->hw_addr = adapter->io_addr; netdev->netdev_ops = &igc_netdev_ops; - + igc_set_ethtool_ops(netdev); netdev->watchdog_timeo = 5 * HZ; netdev->mem_start = pci_resource_start(pdev, 0); @@ -3744,8 +3796,8 @@ static struct pci_driver igc_driver = { .remove = igc_remove, }; -static void igc_set_flag_queue_pairs(struct igc_adapter *adapter, - const u32 max_rss_queues) +void igc_set_flag_queue_pairs(struct igc_adapter *adapter, + const u32 max_rss_queues) { /* Determine if we need to pair queues. */ /* If rss_queues > half of max_rss_queues, pair the queues in @@ -3757,7 +3809,7 @@ static void igc_set_flag_queue_pairs(struct igc_adapter *adapter, adapter->flags &= ~IGC_FLAG_QUEUE_PAIRS; } -static unsigned int igc_get_max_rss_queues(struct igc_adapter *adapter) +unsigned int igc_get_max_rss_queues(struct igc_adapter *adapter) { unsigned int max_rss_queues; @@ -3837,6 +3889,32 @@ static int igc_sw_init(struct igc_adapter *adapter) } /** + * igc_reinit_queues - return error + * @adapter: pointer to adapter structure + */ +int igc_reinit_queues(struct igc_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + struct pci_dev *pdev = adapter->pdev; + int err = 0; + + if (netif_running(netdev)) + igc_close(netdev); + + igc_reset_interrupt_capability(adapter); + + if (igc_init_interrupt_scheme(adapter, true)) { + dev_err(&pdev->dev, "Unable to allocate memory for queues\n"); + return -ENOMEM; + } + + if (netif_running(netdev)) + err = igc_open(netdev); + + return err; +} + +/** * igc_get_hw_dev - return device * @hw: pointer to hardware structure * diff --git a/drivers/net/ethernet/intel/igc/igc_phy.c b/drivers/net/ethernet/intel/igc/igc_phy.c index 38e43e6fc1c7..4c8f96a9a148 100644 --- a/drivers/net/ethernet/intel/igc/igc_phy.c +++ b/drivers/net/ethernet/intel/igc/igc_phy.c @@ -152,7 +152,6 @@ void igc_power_down_phy_copper(struct igc_hw *hw) s32 igc_check_downshift(struct igc_hw *hw) { struct igc_phy_info *phy = &hw->phy; - u16 phy_data, offset, mask; s32 ret_val; switch (phy->type) { @@ -161,15 +160,8 @@ s32 igc_check_downshift(struct igc_hw *hw) /* speed downshift not supported */ phy->speed_downgraded = false; ret_val = 0; - goto out; } - ret_val = phy->ops.read_reg(hw, offset, &phy_data); - - if (!ret_val) - phy->speed_downgraded = (phy_data & mask) ? true : false; - -out: return ret_val; } diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h index a1bd3216c906..5afe7a8d3faf 100644 --- a/drivers/net/ethernet/intel/igc/igc_regs.h +++ b/drivers/net/ethernet/intel/igc/igc_regs.h @@ -80,6 +80,9 @@ /* MSI-X Table Register Descriptions */ #define IGC_PBACL 0x05B68 /* MSIx PBA Clear - R/W 1 to clear */ +/* Redirection Table - RW Array */ +#define IGC_RETA(_i) (0x05C00 + ((_i) * 4)) + /* Receive Register Descriptions */ #define IGC_RCTL 0x00100 /* Rx Control - RW */ #define IGC_SRRCTL(_n) (0x0C00C + ((_n) * 0x40)) @@ -188,7 +191,6 @@ #define IGC_HGOTCL 0x04130 /* Host Good Octets Transmit Count Low */ #define IGC_HGOTCH 0x04134 /* Host Good Octets Transmit Count High */ #define IGC_LENERRS 0x04138 /* Length Errors Count */ -#define IGC_SCVPC 0x04228 /* SerDes/SGMII Code Violation Pkt Count */ #define IGC_HRMPC 0x0A018 /* Header Redirection Missed Packet Count */ /* Management registers */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c index 1e49716f52bc..109f8de5a1c2 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c @@ -1048,7 +1048,7 @@ mac_reset_top: * clear the multicast table. Also reset num_rar_entries to 128, * since we modify this value when programming the SAN MAC address. */ - hw->mac.num_rar_entries = 128; + hw->mac.num_rar_entries = IXGBE_82599_RAR_ENTRIES; hw->mac.ops.init_rx_addrs(hw); /* Store the permanent SAN mac address */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c index 62e6499e4146..cc3196ae5aea 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c @@ -836,12 +836,10 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter, struct ixgbe_ring *ring; int node = NUMA_NO_NODE; int cpu = -1; - int ring_count, size; + int ring_count; u8 tcs = adapter->hw_tcs; ring_count = txr_count + rxr_count + xdp_count; - size = sizeof(struct ixgbe_q_vector) + - (sizeof(struct ixgbe_ring) * ring_count); /* customize cpu for Flow Director mapping */ if ((tcs <= 1) && !(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) { @@ -855,9 +853,11 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter, } /* allocate q_vector and rings */ - q_vector = kzalloc_node(size, GFP_KERNEL, node); + q_vector = kzalloc_node(struct_size(q_vector, ring, ring_count), + GFP_KERNEL, node); if (!q_vector) - q_vector = kzalloc(size, GFP_KERNEL); + q_vector = kzalloc(struct_size(q_vector, ring, ring_count), + GFP_KERNEL); if (!q_vector) return -ENOMEM; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index b53087a980ef..38c430b94ae3 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -10280,9 +10280,6 @@ static int ixgbe_xdp(struct net_device *dev, struct netdev_bpf *xdp) xdp->prog_id = adapter->xdp_prog ? adapter->xdp_prog->aux->id : 0; return 0; - case XDP_QUERY_XSK_UMEM: - return ixgbe_xsk_umem_query(adapter, &xdp->xsk.umem, - xdp->xsk.queue_id); case XDP_SETUP_XSK_UMEM: return ixgbe_xsk_umem_setup(adapter, xdp->xsk.umem, xdp->xsk.queue_id); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h index 53d4089f5644..d93a690aff74 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h @@ -30,8 +30,6 @@ void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring); struct xdp_umem *ixgbe_xsk_umem(struct ixgbe_adapter *adapter, struct ixgbe_ring *ring); -int ixgbe_xsk_umem_query(struct ixgbe_adapter *adapter, struct xdp_umem **umem, - u16 qid); int ixgbe_xsk_umem_setup(struct ixgbe_adapter *adapter, struct xdp_umem *umem, u16 qid); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c index 65c3e2c979d4..98870707b51a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -174,23 +174,6 @@ static int ixgbe_xsk_umem_disable(struct ixgbe_adapter *adapter, u16 qid) return 0; } -int ixgbe_xsk_umem_query(struct ixgbe_adapter *adapter, struct xdp_umem **umem, - u16 qid) -{ - if (qid >= adapter->num_rx_queues) - return -EINVAL; - - if (adapter->xsk_umems) { - if (qid >= adapter->num_xsk_umems) - return -EINVAL; - *umem = adapter->xsk_umems[qid]; - return 0; - } - - *umem = NULL; - return 0; -} - int ixgbe_xsk_umem_setup(struct ixgbe_adapter *adapter, struct xdp_umem *umem, u16 qid) { diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c index 32ac9045cdae..f9bb890733b5 100644 --- a/drivers/net/ethernet/lantiq_etop.c +++ b/drivers/net/ethernet/lantiq_etop.c @@ -112,10 +112,12 @@ struct ltq_etop_priv { static int ltq_etop_alloc_skb(struct ltq_etop_chan *ch) { + struct ltq_etop_priv *priv = netdev_priv(ch->netdev); + ch->skb[ch->dma.desc] = netdev_alloc_skb(ch->netdev, MAX_DMA_DATA_LEN); if (!ch->skb[ch->dma.desc]) return -ENOMEM; - ch->dma.desc_base[ch->dma.desc].addr = dma_map_single(NULL, + ch->dma.desc_base[ch->dma.desc].addr = dma_map_single(&priv->pdev->dev, ch->skb[ch->dma.desc]->data, MAX_DMA_DATA_LEN, DMA_FROM_DEVICE); ch->dma.desc_base[ch->dma.desc].addr = @@ -487,7 +489,7 @@ ltq_etop_tx(struct sk_buff *skb, struct net_device *dev) netif_trans_update(dev); spin_lock_irqsave(&priv->lock, flags); - desc->addr = ((unsigned int) dma_map_single(NULL, skb->data, len, + desc->addr = ((unsigned int) dma_map_single(&priv->pdev->dev, skb->data, len, DMA_TO_DEVICE)) - byte_offset; wmb(); desc->ctl = LTQ_DMA_OWN | LTQ_DMA_SOP | LTQ_DMA_EOP | diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 9d4568eb2297..d134d3538f9b 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -27,6 +27,7 @@ #include <linux/of_irq.h> #include <linux/of_mdio.h> #include <linux/of_net.h> +#include <linux/phy/phy.h> #include <linux/phy.h> #include <linux/phylink.h> #include <linux/platform_device.h> @@ -436,6 +437,7 @@ struct mvneta_port { struct device_node *dn; unsigned int tx_csum_limit; struct phylink *phylink; + struct phy *comphy; struct mvneta_bm *bm_priv; struct mvneta_bm_pool *pool_long; @@ -3151,6 +3153,8 @@ static void mvneta_start_dev(struct mvneta_port *pp) { int cpu; + WARN_ON(phy_power_on(pp->comphy)); + mvneta_max_rx_size_set(pp, pp->pkt_size); mvneta_txq_max_tx_size_set(pp, pp->pkt_size); @@ -3213,6 +3217,8 @@ static void mvneta_stop_dev(struct mvneta_port *pp) mvneta_tx_reset(pp); mvneta_rx_reset(pp); + + WARN_ON(phy_power_off(pp->comphy)); } static void mvneta_percpu_enable(void *arg) @@ -3338,6 +3344,7 @@ static int mvneta_set_mac_addr(struct net_device *dev, void *addr) static void mvneta_validate(struct net_device *ndev, unsigned long *supported, struct phylink_link_state *state) { + struct mvneta_port *pp = netdev_priv(ndev); __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; /* We only support QSGMII, SGMII, 802.3z and RGMII modes */ @@ -3358,8 +3365,13 @@ static void mvneta_validate(struct net_device *ndev, unsigned long *supported, phylink_set(mask, Pause); /* Half-duplex at speeds higher than 100Mbit is unsupported */ - phylink_set(mask, 1000baseT_Full); - phylink_set(mask, 1000baseX_Full); + if (pp->comphy || state->interface != PHY_INTERFACE_MODE_2500BASEX) { + phylink_set(mask, 1000baseT_Full); + phylink_set(mask, 1000baseX_Full); + } + if (pp->comphy || state->interface == PHY_INTERFACE_MODE_2500BASEX) { + phylink_set(mask, 2500baseX_Full); + } if (!phy_interface_mode_is_8023z(state->interface)) { /* 10M and 100M are only supported in non-802.3z mode */ @@ -3373,6 +3385,11 @@ static void mvneta_validate(struct net_device *ndev, unsigned long *supported, __ETHTOOL_LINK_MODE_MASK_NBITS); bitmap_and(state->advertising, state->advertising, mask, __ETHTOOL_LINK_MODE_MASK_NBITS); + + /* We can only operate at 2500BaseX or 1000BaseX. If requested + * to advertise both, only report advertising at 2500BaseX. + */ + phylink_helper_basex_speed(state); } static int mvneta_mac_link_state(struct net_device *ndev, @@ -3384,7 +3401,9 @@ static int mvneta_mac_link_state(struct net_device *ndev, gmac_stat = mvreg_read(pp, MVNETA_GMAC_STATUS); if (gmac_stat & MVNETA_GMAC_SPEED_1000) - state->speed = SPEED_1000; + state->speed = + state->interface == PHY_INTERFACE_MODE_2500BASEX ? + SPEED_2500 : SPEED_1000; else if (gmac_stat & MVNETA_GMAC_SPEED_100) state->speed = SPEED_100; else @@ -3499,12 +3518,20 @@ static void mvneta_mac_config(struct net_device *ndev, unsigned int mode, MVNETA_GMAC_FORCE_LINK_DOWN); } + /* When at 2.5G, the link partner can send frames with shortened * preambles. */ if (state->speed == SPEED_2500) new_ctrl4 |= MVNETA_GMAC4_SHORT_PREAMBLE_ENABLE; + if (pp->comphy && + (state->interface == PHY_INTERFACE_MODE_SGMII || + state->interface == PHY_INTERFACE_MODE_1000BASEX || + state->interface == PHY_INTERFACE_MODE_2500BASEX)) + WARN_ON(phy_set_mode_ext(pp->comphy, PHY_MODE_ETHERNET, + state->interface)); + if (new_ctrl0 != gmac_ctrl0) mvreg_write(pp, MVNETA_GMAC_CTRL_0, new_ctrl0); if (new_ctrl2 != gmac_ctrl2) @@ -4404,7 +4431,7 @@ static int mvneta_port_power_up(struct mvneta_port *pp, int phy_mode) if (phy_mode == PHY_INTERFACE_MODE_QSGMII) mvreg_write(pp, MVNETA_SERDES_CFG, MVNETA_QSGMII_SERDES_PROTO); else if (phy_mode == PHY_INTERFACE_MODE_SGMII || - phy_mode == PHY_INTERFACE_MODE_1000BASEX) + phy_interface_mode_is_8023z(phy_mode)) mvreg_write(pp, MVNETA_SERDES_CFG, MVNETA_SGMII_SERDES_PROTO); else if (!phy_interface_mode_is_rgmii(phy_mode)) return -EINVAL; @@ -4421,6 +4448,7 @@ static int mvneta_probe(struct platform_device *pdev) struct mvneta_port *pp; struct net_device *dev; struct phylink *phylink; + struct phy *comphy; const char *dt_mac_addr; char hw_mac_addr[ETH_ALEN]; const char *mac_from; @@ -4446,6 +4474,14 @@ static int mvneta_probe(struct platform_device *pdev) goto err_free_irq; } + comphy = devm_of_phy_get(&pdev->dev, dn, NULL); + if (comphy == ERR_PTR(-EPROBE_DEFER)) { + err = -EPROBE_DEFER; + goto err_free_irq; + } else if (IS_ERR(comphy)) { + comphy = NULL; + } + phylink = phylink_create(dev, pdev->dev.fwnode, phy_mode, &mvneta_phylink_ops); if (IS_ERR(phylink)) { @@ -4462,6 +4498,7 @@ static int mvneta_probe(struct platform_device *pdev) pp = netdev_priv(dev); spin_lock_init(&pp->lock); pp->phylink = phylink; + pp->comphy = comphy; pp->phy_interface = phy_mode; pp->dn = dn; diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h index 398328f10743..96e3f0669032 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h @@ -402,8 +402,8 @@ #define MVPP2_GMAC_STATUS0_GMII_SPEED BIT(1) #define MVPP2_GMAC_STATUS0_MII_SPEED BIT(2) #define MVPP2_GMAC_STATUS0_FULL_DUPLEX BIT(3) -#define MVPP2_GMAC_STATUS0_RX_PAUSE BIT(6) -#define MVPP2_GMAC_STATUS0_TX_PAUSE BIT(7) +#define MVPP2_GMAC_STATUS0_RX_PAUSE BIT(4) +#define MVPP2_GMAC_STATUS0_TX_PAUSE BIT(5) #define MVPP2_GMAC_STATUS0_AN_COMPLETE BIT(11) #define MVPP2_GMAC_PORT_FIFO_CFG_1_REG 0x1c #define MVPP2_GMAC_TX_FIFO_MIN_TH_OFFS 6 diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 16066c2d5b3a..191d9ce85b7e 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -965,6 +965,11 @@ mvpp2_shared_interrupt_mask_unmask(struct mvpp2_port *port, bool mask) } /* Port configuration routines */ +static bool mvpp2_is_xlg(phy_interface_t interface) +{ + return interface == PHY_INTERFACE_MODE_10GKR || + interface == PHY_INTERFACE_MODE_XAUI; +} static void mvpp22_gop_init_rgmii(struct mvpp2_port *port) { @@ -1090,9 +1095,8 @@ static void mvpp22_gop_unmask_irq(struct mvpp2_port *port) u32 val; if (phy_interface_mode_is_rgmii(port->phy_interface) || - port->phy_interface == PHY_INTERFACE_MODE_SGMII || - port->phy_interface == PHY_INTERFACE_MODE_1000BASEX || - port->phy_interface == PHY_INTERFACE_MODE_2500BASEX) { + phy_interface_mode_is_8023z(port->phy_interface) || + port->phy_interface == PHY_INTERFACE_MODE_SGMII) { /* Enable the GMAC link status irq for this port */ val = readl(port->base + MVPP22_GMAC_INT_SUM_MASK); val |= MVPP22_GMAC_INT_SUM_MASK_LINK_STAT; @@ -1102,7 +1106,7 @@ static void mvpp22_gop_unmask_irq(struct mvpp2_port *port) if (port->gop_id == 0) { /* Enable the XLG/GIG irqs for this port */ val = readl(port->base + MVPP22_XLG_EXT_INT_MASK); - if (port->phy_interface == PHY_INTERFACE_MODE_10GKR) + if (mvpp2_is_xlg(port->phy_interface)) val |= MVPP22_XLG_EXT_INT_MASK_XLG; else val |= MVPP22_XLG_EXT_INT_MASK_GIG; @@ -1122,9 +1126,8 @@ static void mvpp22_gop_mask_irq(struct mvpp2_port *port) } if (phy_interface_mode_is_rgmii(port->phy_interface) || - port->phy_interface == PHY_INTERFACE_MODE_SGMII || - port->phy_interface == PHY_INTERFACE_MODE_1000BASEX || - port->phy_interface == PHY_INTERFACE_MODE_2500BASEX) { + phy_interface_mode_is_8023z(port->phy_interface) || + port->phy_interface == PHY_INTERFACE_MODE_SGMII) { val = readl(port->base + MVPP22_GMAC_INT_SUM_MASK); val &= ~MVPP22_GMAC_INT_SUM_MASK_LINK_STAT; writel(val, port->base + MVPP22_GMAC_INT_SUM_MASK); @@ -1135,10 +1138,10 @@ static void mvpp22_gop_setup_irq(struct mvpp2_port *port) { u32 val; - if (phy_interface_mode_is_rgmii(port->phy_interface) || - port->phy_interface == PHY_INTERFACE_MODE_SGMII || - port->phy_interface == PHY_INTERFACE_MODE_1000BASEX || - port->phy_interface == PHY_INTERFACE_MODE_2500BASEX) { + if (port->phylink || + phy_interface_mode_is_rgmii(port->phy_interface) || + phy_interface_mode_is_8023z(port->phy_interface) || + port->phy_interface == PHY_INTERFACE_MODE_SGMII) { val = readl(port->base + MVPP22_GMAC_INT_MASK); val |= MVPP22_GMAC_INT_MASK_LINK_STAT; writel(val, port->base + MVPP22_GMAC_INT_MASK); @@ -1183,9 +1186,7 @@ static void mvpp2_port_enable(struct mvpp2_port *port) u32 val; /* Only GOP port 0 has an XLG MAC */ - if (port->gop_id == 0 && - (port->phy_interface == PHY_INTERFACE_MODE_XAUI || - port->phy_interface == PHY_INTERFACE_MODE_10GKR)) { + if (port->gop_id == 0 && mvpp2_is_xlg(port->phy_interface)) { val = readl(port->base + MVPP22_XLG_CTRL0_REG); val |= MVPP22_XLG_CTRL0_PORT_EN | MVPP22_XLG_CTRL0_MAC_RESET_DIS; @@ -1204,9 +1205,7 @@ static void mvpp2_port_disable(struct mvpp2_port *port) u32 val; /* Only GOP port 0 has an XLG MAC */ - if (port->gop_id == 0 && - (port->phy_interface == PHY_INTERFACE_MODE_XAUI || - port->phy_interface == PHY_INTERFACE_MODE_10GKR)) { + if (port->gop_id == 0 && mvpp2_is_xlg(port->phy_interface)) { val = readl(port->base + MVPP22_XLG_CTRL0_REG); val &= ~MVPP22_XLG_CTRL0_PORT_EN; writel(val, port->base + MVPP22_XLG_CTRL0_REG); @@ -1244,9 +1243,8 @@ static void mvpp2_port_loopback_set(struct mvpp2_port *port, else val &= ~MVPP2_GMAC_GMII_LB_EN_MASK; - if (port->phy_interface == PHY_INTERFACE_MODE_SGMII || - port->phy_interface == PHY_INTERFACE_MODE_1000BASEX || - port->phy_interface == PHY_INTERFACE_MODE_2500BASEX) + if (phy_interface_mode_is_8023z(port->phy_interface) || + port->phy_interface == PHY_INTERFACE_MODE_SGMII) val |= MVPP2_GMAC_PCS_LB_EN_MASK; else val &= ~MVPP2_GMAC_PCS_LB_EN_MASK; @@ -1380,13 +1378,9 @@ static void mvpp2_port_reset(struct mvpp2_port *port) for (i = 0; i < ARRAY_SIZE(mvpp2_ethtool_regs); i++) mvpp2_read_count(port, &mvpp2_ethtool_regs[i]); - val = readl(port->base + MVPP2_GMAC_CTRL_2_REG) & - ~MVPP2_GMAC_PORT_RESET_MASK; + val = readl(port->base + MVPP2_GMAC_CTRL_2_REG) | + MVPP2_GMAC_PORT_RESET_MASK; writel(val, port->base + MVPP2_GMAC_CTRL_2_REG); - - while (readl(port->base + MVPP2_GMAC_CTRL_2_REG) & - MVPP2_GMAC_PORT_RESET_MASK) - continue; } /* Change maximum receive size of the port */ @@ -2462,8 +2456,7 @@ static irqreturn_t mvpp2_link_status_isr(int irq, void *dev_id) mvpp22_gop_mask_irq(port); - if (port->gop_id == 0 && - port->phy_interface == PHY_INTERFACE_MODE_10GKR) { + if (port->gop_id == 0 && mvpp2_is_xlg(port->phy_interface)) { val = readl(port->base + MVPP22_XLG_INT_STAT); if (val & MVPP22_XLG_INT_STAT_LINK) { event = true; @@ -2472,9 +2465,8 @@ static irqreturn_t mvpp2_link_status_isr(int irq, void *dev_id) link = true; } } else if (phy_interface_mode_is_rgmii(port->phy_interface) || - port->phy_interface == PHY_INTERFACE_MODE_SGMII || - port->phy_interface == PHY_INTERFACE_MODE_1000BASEX || - port->phy_interface == PHY_INTERFACE_MODE_2500BASEX) { + phy_interface_mode_is_8023z(port->phy_interface) || + port->phy_interface == PHY_INTERFACE_MODE_SGMII) { val = readl(port->base + MVPP22_GMAC_INT_STAT); if (val & MVPP22_GMAC_INT_STAT_LINK) { event = true; @@ -3154,8 +3146,7 @@ static void mvpp22_mode_reconfigure(struct mvpp2_port *port) ctrl3 = readl(port->base + MVPP22_XLG_CTRL3_REG); ctrl3 &= ~MVPP22_XLG_CTRL3_MACMODESELECT_MASK; - if (port->phy_interface == PHY_INTERFACE_MODE_XAUI || - port->phy_interface == PHY_INTERFACE_MODE_10GKR) + if (mvpp2_is_xlg(port->phy_interface)) ctrl3 |= MVPP22_XLG_CTRL3_MACMODESELECT_10G; else ctrl3 |= MVPP22_XLG_CTRL3_MACMODESELECT_GMAC; @@ -3163,9 +3154,7 @@ static void mvpp22_mode_reconfigure(struct mvpp2_port *port) writel(ctrl3, port->base + MVPP22_XLG_CTRL3_REG); } - if (port->gop_id == 0 && - (port->phy_interface == PHY_INTERFACE_MODE_XAUI || - port->phy_interface == PHY_INTERFACE_MODE_10GKR)) + if (port->gop_id == 0 && mvpp2_is_xlg(port->phy_interface)) mvpp2_xlg_max_rx_size_set(port); else mvpp2_gmac_max_rx_size_set(port); @@ -4505,17 +4494,12 @@ static int mvpp2_phylink_mac_link_state(struct net_device *dev, static void mvpp2_mac_an_restart(struct net_device *dev) { struct mvpp2_port *port = netdev_priv(dev); - u32 val; + u32 val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG); - if (port->phy_interface != PHY_INTERFACE_MODE_SGMII) - return; - - val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG); - /* The RESTART_AN bit is cleared by the h/w after restarting the AN - * process. - */ - val |= MVPP2_GMAC_IN_BAND_RESTART_AN | MVPP2_GMAC_IN_BAND_AUTONEG; - writel(val, port->base + MVPP2_GMAC_AUTONEG_CONFIG); + writel(val | MVPP2_GMAC_IN_BAND_RESTART_AN, + port->base + MVPP2_GMAC_AUTONEG_CONFIG); + writel(val & ~MVPP2_GMAC_IN_BAND_RESTART_AN, + port->base + MVPP2_GMAC_AUTONEG_CONFIG); } static void mvpp2_xlg_config(struct mvpp2_port *port, unsigned int mode, @@ -4528,8 +4512,13 @@ static void mvpp2_xlg_config(struct mvpp2_port *port, unsigned int mode, if (state->pause & MLO_PAUSE_TX) ctrl0 |= MVPP22_XLG_CTRL0_TX_FLOW_CTRL_EN; + else + ctrl0 &= ~MVPP22_XLG_CTRL0_TX_FLOW_CTRL_EN; + if (state->pause & MLO_PAUSE_RX) ctrl0 |= MVPP22_XLG_CTRL0_RX_FLOW_CTRL_EN; + else + ctrl0 &= ~MVPP22_XLG_CTRL0_RX_FLOW_CTRL_EN; ctrl4 &= ~MVPP22_XLG_CTRL4_MACMODSELECT_GMAC; ctrl4 |= MVPP22_XLG_CTRL4_FWD_FC | MVPP22_XLG_CTRL4_FWD_PFC | @@ -4542,122 +4531,172 @@ static void mvpp2_xlg_config(struct mvpp2_port *port, unsigned int mode, static void mvpp2_gmac_config(struct mvpp2_port *port, unsigned int mode, const struct phylink_link_state *state) { - u32 an, ctrl0, ctrl2, ctrl4; - - an = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG); - ctrl0 = readl(port->base + MVPP2_GMAC_CTRL_0_REG); - ctrl2 = readl(port->base + MVPP2_GMAC_CTRL_2_REG); - ctrl4 = readl(port->base + MVPP22_GMAC_CTRL_4_REG); - - /* Force link down */ - an &= ~MVPP2_GMAC_FORCE_LINK_PASS; - an |= MVPP2_GMAC_FORCE_LINK_DOWN; - writel(an, port->base + MVPP2_GMAC_AUTONEG_CONFIG); + u32 old_an, an; + u32 old_ctrl0, ctrl0; + u32 old_ctrl2, ctrl2; + u32 old_ctrl4, ctrl4; - /* Set the GMAC in a reset state */ - ctrl2 |= MVPP2_GMAC_PORT_RESET_MASK; - writel(ctrl2, port->base + MVPP2_GMAC_CTRL_2_REG); + old_an = an = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG); + old_ctrl0 = ctrl0 = readl(port->base + MVPP2_GMAC_CTRL_0_REG); + old_ctrl2 = ctrl2 = readl(port->base + MVPP2_GMAC_CTRL_2_REG); + old_ctrl4 = ctrl4 = readl(port->base + MVPP22_GMAC_CTRL_4_REG); an &= ~(MVPP2_GMAC_CONFIG_MII_SPEED | MVPP2_GMAC_CONFIG_GMII_SPEED | MVPP2_GMAC_AN_SPEED_EN | MVPP2_GMAC_FC_ADV_EN | MVPP2_GMAC_FC_ADV_ASM_EN | MVPP2_GMAC_FLOW_CTRL_AUTONEG | MVPP2_GMAC_CONFIG_FULL_DUPLEX | MVPP2_GMAC_AN_DUPLEX_EN | - MVPP2_GMAC_FORCE_LINK_DOWN); + MVPP2_GMAC_IN_BAND_AUTONEG | MVPP2_GMAC_IN_BAND_AUTONEG_BYPASS); ctrl0 &= ~MVPP2_GMAC_PORT_TYPE_MASK; - ctrl2 &= ~(MVPP2_GMAC_PORT_RESET_MASK | MVPP2_GMAC_PCS_ENABLE_MASK); - - if (state->interface == PHY_INTERFACE_MODE_1000BASEX || - state->interface == PHY_INTERFACE_MODE_2500BASEX) { - /* 1000BaseX and 2500BaseX ports cannot negotiate speed nor can - * they negotiate duplex: they are always operating with a fixed - * speed of 1000/2500Mbps in full duplex, so force 1000/2500 - * speed and full duplex here. - */ - ctrl0 |= MVPP2_GMAC_PORT_TYPE_MASK; - an |= MVPP2_GMAC_CONFIG_GMII_SPEED | - MVPP2_GMAC_CONFIG_FULL_DUPLEX; - } else if (!phy_interface_mode_is_rgmii(state->interface)) { - an |= MVPP2_GMAC_AN_SPEED_EN | MVPP2_GMAC_FLOW_CTRL_AUTONEG; + ctrl2 &= ~(MVPP2_GMAC_INBAND_AN_MASK | MVPP2_GMAC_PORT_RESET_MASK | + MVPP2_GMAC_PCS_ENABLE_MASK); + ctrl4 &= ~(MVPP22_CTRL4_RX_FC_EN | MVPP22_CTRL4_TX_FC_EN); + + /* Configure port type */ + if (phy_interface_mode_is_8023z(state->interface)) { + ctrl2 |= MVPP2_GMAC_PCS_ENABLE_MASK; + ctrl4 &= ~MVPP22_CTRL4_EXT_PIN_GMII_SEL; + ctrl4 |= MVPP22_CTRL4_SYNC_BYPASS_DIS | + MVPP22_CTRL4_DP_CLK_SEL | + MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE; + } else if (state->interface == PHY_INTERFACE_MODE_SGMII) { + ctrl2 |= MVPP2_GMAC_PCS_ENABLE_MASK | MVPP2_GMAC_INBAND_AN_MASK; + ctrl4 &= ~MVPP22_CTRL4_EXT_PIN_GMII_SEL; + ctrl4 |= MVPP22_CTRL4_SYNC_BYPASS_DIS | + MVPP22_CTRL4_DP_CLK_SEL | + MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE; + } else if (phy_interface_mode_is_rgmii(state->interface)) { + ctrl4 &= ~MVPP22_CTRL4_DP_CLK_SEL; + ctrl4 |= MVPP22_CTRL4_EXT_PIN_GMII_SEL | + MVPP22_CTRL4_SYNC_BYPASS_DIS | + MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE; } - if (state->duplex) - an |= MVPP2_GMAC_CONFIG_FULL_DUPLEX; + /* Configure advertisement bits */ if (phylink_test(state->advertising, Pause)) an |= MVPP2_GMAC_FC_ADV_EN; if (phylink_test(state->advertising, Asym_Pause)) an |= MVPP2_GMAC_FC_ADV_ASM_EN; - if (state->interface == PHY_INTERFACE_MODE_SGMII || - state->interface == PHY_INTERFACE_MODE_1000BASEX || - state->interface == PHY_INTERFACE_MODE_2500BASEX) { - an |= MVPP2_GMAC_IN_BAND_AUTONEG; - ctrl2 |= MVPP2_GMAC_INBAND_AN_MASK | MVPP2_GMAC_PCS_ENABLE_MASK; + /* Configure negotiation style */ + if (!phylink_autoneg_inband(mode)) { + /* Phy or fixed speed - no in-band AN */ + if (state->duplex) + an |= MVPP2_GMAC_CONFIG_FULL_DUPLEX; - ctrl4 &= ~(MVPP22_CTRL4_EXT_PIN_GMII_SEL | - MVPP22_CTRL4_RX_FC_EN | MVPP22_CTRL4_TX_FC_EN); - ctrl4 |= MVPP22_CTRL4_SYNC_BYPASS_DIS | - MVPP22_CTRL4_DP_CLK_SEL | - MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE; + if (state->speed == SPEED_1000 || state->speed == SPEED_2500) + an |= MVPP2_GMAC_CONFIG_GMII_SPEED; + else if (state->speed == SPEED_100) + an |= MVPP2_GMAC_CONFIG_MII_SPEED; if (state->pause & MLO_PAUSE_TX) ctrl4 |= MVPP22_CTRL4_TX_FC_EN; if (state->pause & MLO_PAUSE_RX) ctrl4 |= MVPP22_CTRL4_RX_FC_EN; - } else if (phy_interface_mode_is_rgmii(state->interface)) { - an |= MVPP2_GMAC_IN_BAND_AUTONEG_BYPASS; + } else if (state->interface == PHY_INTERFACE_MODE_SGMII) { + /* SGMII in-band mode receives the speed and duplex from + * the PHY. Flow control information is not received. */ + an &= ~(MVPP2_GMAC_FORCE_LINK_DOWN | MVPP2_GMAC_FORCE_LINK_PASS); + an |= MVPP2_GMAC_IN_BAND_AUTONEG | + MVPP2_GMAC_AN_SPEED_EN | + MVPP2_GMAC_AN_DUPLEX_EN; - if (state->speed == SPEED_1000) - an |= MVPP2_GMAC_CONFIG_GMII_SPEED; - else if (state->speed == SPEED_100) - an |= MVPP2_GMAC_CONFIG_MII_SPEED; + if (state->pause & MLO_PAUSE_TX) + ctrl4 |= MVPP22_CTRL4_TX_FC_EN; + if (state->pause & MLO_PAUSE_RX) + ctrl4 |= MVPP22_CTRL4_RX_FC_EN; + } else if (phy_interface_mode_is_8023z(state->interface)) { + /* 1000BaseX and 2500BaseX ports cannot negotiate speed nor can + * they negotiate duplex: they are always operating with a fixed + * speed of 1000/2500Mbps in full duplex, so force 1000/2500 + * speed and full duplex here. + */ + ctrl0 |= MVPP2_GMAC_PORT_TYPE_MASK; + an &= ~(MVPP2_GMAC_FORCE_LINK_DOWN | MVPP2_GMAC_FORCE_LINK_PASS); + an |= MVPP2_GMAC_IN_BAND_AUTONEG | + MVPP2_GMAC_CONFIG_GMII_SPEED | + MVPP2_GMAC_CONFIG_FULL_DUPLEX; - ctrl4 &= ~MVPP22_CTRL4_DP_CLK_SEL; - ctrl4 |= MVPP22_CTRL4_EXT_PIN_GMII_SEL | - MVPP22_CTRL4_SYNC_BYPASS_DIS | - MVPP22_CTRL4_QSGMII_BYPASS_ACTIVE; + if (state->pause & MLO_PAUSE_AN && state->an_enabled) { + an |= MVPP2_GMAC_FLOW_CTRL_AUTONEG; + } else { + if (state->pause & MLO_PAUSE_TX) + ctrl4 |= MVPP22_CTRL4_TX_FC_EN; + if (state->pause & MLO_PAUSE_RX) + ctrl4 |= MVPP22_CTRL4_RX_FC_EN; + } } - writel(ctrl0, port->base + MVPP2_GMAC_CTRL_0_REG); - writel(ctrl2, port->base + MVPP2_GMAC_CTRL_2_REG); - writel(ctrl4, port->base + MVPP22_GMAC_CTRL_4_REG); - writel(an, port->base + MVPP2_GMAC_AUTONEG_CONFIG); + if ((old_ctrl0 ^ ctrl0) & MVPP2_GMAC_PORT_TYPE_MASK || + (old_ctrl2 ^ ctrl2) & MVPP2_GMAC_INBAND_AN_MASK || + (old_an ^ an) & MVPP2_GMAC_IN_BAND_AUTONEG) { + /* Force link down */ + old_an &= ~MVPP2_GMAC_FORCE_LINK_PASS; + old_an |= MVPP2_GMAC_FORCE_LINK_DOWN; + writel(old_an, port->base + MVPP2_GMAC_AUTONEG_CONFIG); + + /* Set the GMAC in a reset state - do this in a way that + * ensures we clear it below. + */ + old_ctrl2 |= MVPP2_GMAC_PORT_RESET_MASK; + writel(old_ctrl2, port->base + MVPP2_GMAC_CTRL_2_REG); + } + + if (old_ctrl0 != ctrl0) + writel(ctrl0, port->base + MVPP2_GMAC_CTRL_0_REG); + if (old_ctrl2 != ctrl2) + writel(ctrl2, port->base + MVPP2_GMAC_CTRL_2_REG); + if (old_ctrl4 != ctrl4) + writel(ctrl4, port->base + MVPP22_GMAC_CTRL_4_REG); + if (old_an != an) + writel(an, port->base + MVPP2_GMAC_AUTONEG_CONFIG); + + if (old_ctrl2 & MVPP2_GMAC_PORT_RESET_MASK) { + while (readl(port->base + MVPP2_GMAC_CTRL_2_REG) & + MVPP2_GMAC_PORT_RESET_MASK) + continue; + } } static void mvpp2_mac_config(struct net_device *dev, unsigned int mode, const struct phylink_link_state *state) { struct mvpp2_port *port = netdev_priv(dev); + bool change_interface = port->phy_interface != state->interface; /* Check for invalid configuration */ - if (state->interface == PHY_INTERFACE_MODE_10GKR && port->gop_id != 0) { + if (mvpp2_is_xlg(state->interface) && port->gop_id != 0) { netdev_err(dev, "Invalid mode on %s\n", dev->name); return; } /* Make sure the port is disabled when reconfiguring the mode */ mvpp2_port_disable(port); + if (change_interface) { + mvpp22_gop_mask_irq(port); - if (port->priv->hw_version == MVPP22 && - port->phy_interface != state->interface) { - port->phy_interface = state->interface; + if (port->priv->hw_version == MVPP22) { + port->phy_interface = state->interface; - /* Reconfigure the serdes lanes */ - phy_power_off(port->comphy); - mvpp22_mode_reconfigure(port); + /* Reconfigure the serdes lanes */ + phy_power_off(port->comphy); + mvpp22_mode_reconfigure(port); + } } /* mac (re)configuration */ - if (state->interface == PHY_INTERFACE_MODE_10GKR) + if (mvpp2_is_xlg(state->interface)) mvpp2_xlg_config(port, mode, state); else if (phy_interface_mode_is_rgmii(state->interface) || - state->interface == PHY_INTERFACE_MODE_SGMII || - state->interface == PHY_INTERFACE_MODE_1000BASEX || - state->interface == PHY_INTERFACE_MODE_2500BASEX) + phy_interface_mode_is_8023z(state->interface) || + state->interface == PHY_INTERFACE_MODE_SGMII) mvpp2_gmac_config(port, mode, state); if (port->priv->hw_version == MVPP21 && port->flags & MVPP2_F_LOOPBACK) mvpp2_port_loopback_set(port, state); + if (change_interface) + mvpp22_gop_unmask_irq(port); + mvpp2_port_enable(port); } @@ -4667,12 +4706,10 @@ static void mvpp2_mac_link_up(struct net_device *dev, unsigned int mode, struct mvpp2_port *port = netdev_priv(dev); u32 val; - if (!phylink_autoneg_inband(mode) && - interface != PHY_INTERFACE_MODE_10GKR) { + if (!phylink_autoneg_inband(mode) && !mvpp2_is_xlg(interface)) { val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG); val &= ~MVPP2_GMAC_FORCE_LINK_DOWN; - if (phy_interface_mode_is_rgmii(interface)) - val |= MVPP2_GMAC_FORCE_LINK_PASS; + val |= MVPP2_GMAC_FORCE_LINK_PASS; writel(val, port->base + MVPP2_GMAC_AUTONEG_CONFIG); } @@ -4689,8 +4726,7 @@ static void mvpp2_mac_link_down(struct net_device *dev, unsigned int mode, struct mvpp2_port *port = netdev_priv(dev); u32 val; - if (!phylink_autoneg_inband(mode) && - interface != PHY_INTERFACE_MODE_10GKR) { + if (!phylink_autoneg_inband(mode) && !mvpp2_is_xlg(interface)) { val = readl(port->base + MVPP2_GMAC_AUTONEG_CONFIG); val &= ~MVPP2_GMAC_FORCE_LINK_PASS; val |= MVPP2_GMAC_FORCE_LINK_DOWN; diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c index f8a6d6e3cb7a..35f2142aac5e 100644 --- a/drivers/net/ethernet/marvell/pxa168_eth.c +++ b/drivers/net/ethernet/marvell/pxa168_eth.c @@ -201,6 +201,7 @@ struct tx_desc { }; struct pxa168_eth_private { + struct platform_device *pdev; int port_num; /* User Ethernet port number */ int phy_addr; int phy_speed; @@ -331,7 +332,7 @@ static void rxq_refill(struct net_device *dev) used_rx_desc = pep->rx_used_desc_q; p_used_rx_desc = &pep->p_rx_desc_area[used_rx_desc]; size = skb_end_pointer(skb) - skb->data; - p_used_rx_desc->buf_ptr = dma_map_single(NULL, + p_used_rx_desc->buf_ptr = dma_map_single(&pep->pdev->dev, skb->data, size, DMA_FROM_DEVICE); @@ -743,7 +744,7 @@ static int txq_reclaim(struct net_device *dev, int force) netdev_err(dev, "Error in TX\n"); dev->stats.tx_errors++; } - dma_unmap_single(NULL, addr, count, DMA_TO_DEVICE); + dma_unmap_single(&pep->pdev->dev, addr, count, DMA_TO_DEVICE); if (skb) dev_kfree_skb_irq(skb); released++; @@ -805,7 +806,7 @@ static int rxq_process(struct net_device *dev, int budget) if (rx_next_curr_desc == rx_used_desc) pep->rx_resource_err = 1; pep->rx_desc_count--; - dma_unmap_single(NULL, rx_desc->buf_ptr, + dma_unmap_single(&pep->pdev->dev, rx_desc->buf_ptr, rx_desc->buf_size, DMA_FROM_DEVICE); received_packets++; @@ -1274,7 +1275,8 @@ pxa168_eth_start_xmit(struct sk_buff *skb, struct net_device *dev) length = skb->len; pep->tx_skb[tx_index] = skb; desc->byte_cnt = length; - desc->buf_ptr = dma_map_single(NULL, skb->data, length, DMA_TO_DEVICE); + desc->buf_ptr = dma_map_single(&pep->pdev->dev, skb->data, length, + DMA_TO_DEVICE); skb_tx_timestamp(skb); @@ -1528,6 +1530,7 @@ static int pxa168_eth_probe(struct platform_device *pdev) if (err) goto err_free_mdio; + pep->pdev = pdev; SET_NETDEV_DEV(dev, &pdev->dev); pxa168_init_hw(pep); err = register_netdev(dev); diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c index 04fd1f135011..654ac534b10e 100644 --- a/drivers/net/ethernet/marvell/skge.c +++ b/drivers/net/ethernet/marvell/skge.c @@ -152,8 +152,10 @@ static void skge_get_regs(struct net_device *dev, struct ethtool_regs *regs, memset(p, 0, regs->len); memcpy_fromio(p, io, B3_RAM_ADDR); - memcpy_fromio(p + B3_RI_WTO_R1, io + B3_RI_WTO_R1, - regs->len - B3_RI_WTO_R1); + if (regs->len > B3_RI_WTO_R1) { + memcpy_fromio(p + B3_RI_WTO_R1, io + B3_RI_WTO_R1, + regs->len - B3_RI_WTO_R1); + } } /* Wake on Lan only supported on Yukon chips with rev 1 or above */ diff --git a/drivers/net/ethernet/mediatek/Kconfig b/drivers/net/ethernet/mediatek/Kconfig index f9149d2a4694..43656f961891 100644 --- a/drivers/net/ethernet/mediatek/Kconfig +++ b/drivers/net/ethernet/mediatek/Kconfig @@ -1,6 +1,6 @@ config NET_VENDOR_MEDIATEK bool "MediaTek ethernet driver" - depends on ARCH_MEDIATEK + depends on ARCH_MEDIATEK || SOC_MT7621 ---help--- If you have a Mediatek SoC with ethernet, say Y. diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 49f926b7a91c..94d4663e3933 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -1745,6 +1745,22 @@ static irqreturn_t mtk_handle_irq_tx(int irq, void *_eth) return IRQ_HANDLED; } +static irqreturn_t mtk_handle_irq(int irq, void *_eth) +{ + struct mtk_eth *eth = _eth; + + if (mtk_r32(eth, MTK_PDMA_INT_MASK) & MTK_RX_DONE_INT) { + if (mtk_r32(eth, MTK_PDMA_INT_STATUS) & MTK_RX_DONE_INT) + mtk_handle_irq_rx(irq, _eth); + } + if (mtk_r32(eth, MTK_QDMA_INT_MASK) & MTK_TX_DONE_INT) { + if (mtk_r32(eth, MTK_QMTK_INT_STATUS) & MTK_TX_DONE_INT) + mtk_handle_irq_tx(irq, _eth); + } + + return IRQ_HANDLED; +} + #ifdef CONFIG_NET_POLL_CONTROLLER static void mtk_poll_controller(struct net_device *dev) { @@ -2485,7 +2501,10 @@ static int mtk_probe(struct platform_device *pdev) } for (i = 0; i < 3; i++) { - eth->irq[i] = platform_get_irq(pdev, i); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_SHARED_INT) && i > 0) + eth->irq[i] = eth->irq[0]; + else + eth->irq[i] = platform_get_irq(pdev, i); if (eth->irq[i] < 0) { dev_err(&pdev->dev, "no IRQ%d resource found\n", i); return -ENXIO; @@ -2528,13 +2547,21 @@ static int mtk_probe(struct platform_device *pdev) goto err_deinit_hw; } - err = devm_request_irq(eth->dev, eth->irq[1], mtk_handle_irq_tx, 0, - dev_name(eth->dev), eth); - if (err) - goto err_free_dev; + if (MTK_HAS_CAPS(eth->soc->caps, MTK_SHARED_INT)) { + err = devm_request_irq(eth->dev, eth->irq[0], + mtk_handle_irq, 0, + dev_name(eth->dev), eth); + } else { + err = devm_request_irq(eth->dev, eth->irq[1], + mtk_handle_irq_tx, 0, + dev_name(eth->dev), eth); + if (err) + goto err_free_dev; - err = devm_request_irq(eth->dev, eth->irq[2], mtk_handle_irq_rx, 0, - dev_name(eth->dev), eth); + err = devm_request_irq(eth->dev, eth->irq[2], + mtk_handle_irq_rx, 0, + dev_name(eth->dev), eth); + } if (err) goto err_free_dev; @@ -2607,6 +2634,12 @@ static const struct mtk_soc_data mt2701_data = { .required_pctl = true, }; +static const struct mtk_soc_data mt7621_data = { + .caps = MTK_SHARED_INT, + .required_clks = MT7621_CLKS_BITMAP, + .required_pctl = false, +}; + static const struct mtk_soc_data mt7622_data = { .caps = MTK_DUAL_GMAC_SHARED_SGMII | MTK_GMAC1_ESW | MTK_HWLRO, .required_clks = MT7622_CLKS_BITMAP, @@ -2621,6 +2654,7 @@ static const struct mtk_soc_data mt7623_data = { const struct of_device_id of_mtk_match[] = { { .compatible = "mediatek,mt2701-eth", .data = &mt2701_data}, + { .compatible = "mediatek,mt7621-eth", .data = &mt7621_data}, { .compatible = "mediatek,mt7622-eth", .data = &mt7622_data}, { .compatible = "mediatek,mt7623-eth", .data = &mt7623_data}, {}, diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index 46819297fc3e..f7501997cea0 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -363,6 +363,7 @@ #define ETHSYS_CHIPID4_7 0x4 #define MT7623_ETH 7623 #define MT7622_ETH 7622 +#define MT7621_ETH 7621 /* ethernet subsystem config register */ #define ETHSYS_SYSCFG0 0x14 @@ -488,6 +489,8 @@ enum mtk_clks_map { BIT(MTK_CLK_SGMII_CDR_FB) | \ BIT(MTK_CLK_SGMII_CK) | \ BIT(MTK_CLK_ETH2PLL)) +#define MT7621_CLKS_BITMAP (0) + enum mtk_dev_state { MTK_HW_INIT, MTK_RESETTING @@ -567,6 +570,7 @@ struct mtk_rx_ring { #define MTK_DUAL_GMAC_SHARED_SGMII (BIT(11) | MTK_GMAC1_SGMII | \ MTK_GMAC2_SGMII) #define MTK_HWLRO BIT(12) +#define MTK_SHARED_INT BIT(13) #define MTK_HAS_CAPS(caps, _x) (((caps) & (_x)) == (_x)) /* struct mtk_eth_data - This is the structure holding all differences diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 9a0881cb7f51..6c01314e87b0 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -617,6 +617,8 @@ static int get_fixed_ipv6_csum(__wsum hw_checksum, struct sk_buff *skb, } #endif +#define short_frame(size) ((size) <= ETH_ZLEN + ETH_FCS_LEN) + /* We reach this function only after checking that any of * the (IPv4 | IPv6) bits are set in cqe->status. */ @@ -624,9 +626,20 @@ static int check_csum(struct mlx4_cqe *cqe, struct sk_buff *skb, void *va, netdev_features_t dev_features) { __wsum hw_checksum = 0; + void *hdr; + + /* CQE csum doesn't cover padding octets in short ethernet + * frames. And the pad field is appended prior to calculating + * and appending the FCS field. + * + * Detecting these padded frames requires to verify and parse + * IP headers, so we simply force all those small frames to skip + * checksum complete. + */ + if (short_frame(skb->len)) + return -EINVAL; - void *hdr = (u8 *)va + sizeof(struct ethhdr); - + hdr = (u8 *)va + sizeof(struct ethhdr); hw_checksum = csum_unfold((__force __sum16)cqe->checksum); if (cqe->vlan_my_qpn & cpu_to_be32(MLX4_CQE_CVLAN_PRESENT_MASK) && @@ -819,6 +832,11 @@ xdp_drop_no_cnt: skb_record_rx_queue(skb, cq_ring); if (likely(dev->features & NETIF_F_RXCSUM)) { + /* TODO: For IP non TCP/UDP packets when csum complete is + * not an option (not supported or any other reason) we can + * actually check cqe IPOK status bit and report + * CHECKSUM_UNNECESSARY rather than CHECKSUM_NONE + */ if ((cqe->status & cpu_to_be16(MLX4_CQE_STATUS_TCP | MLX4_CQE_STATUS_UDP)) && (cqe->status & cpu_to_be16(MLX4_CQE_STATUS_IPOK)) && diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index bdb8dd161923..1f6e16d5ea6b 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -3981,6 +3981,7 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id) if (ret) goto err_params_unregister; + devlink_params_publish(devlink); pci_save_state(pdev); return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 9de9abacf7f6..82d636baaa4e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -13,7 +13,7 @@ obj-$(CONFIG_MLX5_CORE) += mlx5_core.o # mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ health.o mcg.o cq.o alloc.o qp.o port.o mr.o pd.o \ - mad.o transobj.o vport.o sriov.o fs_cmd.o fs_core.o \ + transobj.o vport.o sriov.o fs_cmd.o fs_core.o \ fs_counters.o rl.o lag.o dev.o events.o wq.o lib/gid.o \ lib/devcom.o diag/fs_tracepoint.o diag/fw_tracer.o @@ -22,7 +22,7 @@ mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ # mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \ en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \ - en_selftest.o en/port.o en/monitor_stats.o + en_selftest.o en/port.o en/monitor_stats.o en/reporter_tx.o # # Netdev extra @@ -35,7 +35,7 @@ mlx5_core-$(CONFIG_MLX5_ESWITCH) += en_rep.o en_tc.o en/tc_tun.o # # Core extra # -mlx5_core-$(CONFIG_MLX5_ESWITCH) += eswitch.o eswitch_offloads.o +mlx5_core-$(CONFIG_MLX5_ESWITCH) += eswitch.o eswitch_offloads.o ecpf.o mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o mlx5_core-$(CONFIG_VXLAN) += lib/vxlan.o mlx5_core-$(CONFIG_PTP_1588_CLOCK) += lib/clock.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 3e0fa8a8077b..be48c6440251 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -316,6 +316,7 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op, case MLX5_CMD_OP_DESTROY_GENERAL_OBJECT: case MLX5_CMD_OP_DEALLOC_MEMIC: case MLX5_CMD_OP_PAGE_FAULT_RESUME: + case MLX5_CMD_OP_QUERY_HOST_PARAMS: return MLX5_CMD_STAT_OK; case MLX5_CMD_OP_QUERY_HCA_CAP: @@ -627,6 +628,7 @@ const char *mlx5_command_str(int command) MLX5_COMMAND_STR_CASE(QUERY_MODIFY_HEADER_CONTEXT); MLX5_COMMAND_STR_CASE(ALLOC_MEMIC); MLX5_COMMAND_STR_CASE(DEALLOC_MEMIC); + MLX5_COMMAND_STR_CASE(QUERY_HOST_PARAMS); default: return "unknown command opcode"; } } @@ -1583,6 +1585,24 @@ no_trig: spin_unlock_irqrestore(&dev->cmd.alloc_lock, flags); } +void mlx5_cmd_flush(struct mlx5_core_dev *dev) +{ + struct mlx5_cmd *cmd = &dev->cmd; + int i; + + for (i = 0; i < cmd->max_reg_cmds; i++) + while (down_trylock(&cmd->sem)) + mlx5_cmd_trigger_completions(dev); + + while (down_trylock(&cmd->pages_sem)) + mlx5_cmd_trigger_completions(dev); + + /* Unlock cmdif */ + up(&cmd->pages_sem); + for (i = 0; i < cmd->max_reg_cmds; i++) + up(&cmd->sem); +} + static int status_to_err(u8 status) { return status ? -1 : 0; /* TBD more meaningful codes */ @@ -1711,12 +1731,57 @@ int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, } EXPORT_SYMBOL(mlx5_cmd_exec); -int mlx5_cmd_exec_cb(struct mlx5_core_dev *dev, void *in, int in_size, - void *out, int out_size, mlx5_cmd_cbk_t callback, - void *context) +void mlx5_cmd_init_async_ctx(struct mlx5_core_dev *dev, + struct mlx5_async_ctx *ctx) +{ + ctx->dev = dev; + /* Starts at 1 to avoid doing wake_up if we are not cleaning up */ + atomic_set(&ctx->num_inflight, 1); + init_waitqueue_head(&ctx->wait); +} +EXPORT_SYMBOL(mlx5_cmd_init_async_ctx); + +/** + * mlx5_cmd_cleanup_async_ctx - Clean up an async_ctx + * @ctx: The ctx to clean + * + * Upon return all callbacks given to mlx5_cmd_exec_cb() have been called. The + * caller must ensure that mlx5_cmd_exec_cb() is not called during or after + * the call mlx5_cleanup_async_ctx(). + */ +void mlx5_cmd_cleanup_async_ctx(struct mlx5_async_ctx *ctx) +{ + atomic_dec(&ctx->num_inflight); + wait_event(ctx->wait, atomic_read(&ctx->num_inflight) == 0); +} +EXPORT_SYMBOL(mlx5_cmd_cleanup_async_ctx); + +static void mlx5_cmd_exec_cb_handler(int status, void *_work) +{ + struct mlx5_async_work *work = _work; + struct mlx5_async_ctx *ctx = work->ctx; + + work->user_callback(status, work); + if (atomic_dec_and_test(&ctx->num_inflight)) + wake_up(&ctx->wait); +} + +int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size, + void *out, int out_size, mlx5_async_cbk_t callback, + struct mlx5_async_work *work) { - return cmd_exec(dev, in, in_size, out, out_size, callback, context, - false); + int ret; + + work->ctx = ctx; + work->user_callback = callback; + if (WARN_ON(!atomic_inc_not_zero(&ctx->num_inflight))) + return -EIO; + ret = cmd_exec(ctx->dev, in, in_size, out, out_size, + mlx5_cmd_exec_cb_handler, work, false); + if (ret && atomic_dec_and_test(&ctx->num_inflight)) + wake_up(&ctx->wait); + + return ret; } EXPORT_SYMBOL(mlx5_cmd_exec_cb); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c new file mode 100644 index 000000000000..4746f2d28fb6 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c @@ -0,0 +1,112 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2019 Mellanox Technologies. */ + +#include "ecpf.h" + +bool mlx5_read_embedded_cpu(struct mlx5_core_dev *dev) +{ + return (ioread32be(&dev->iseg->initializing) >> MLX5_ECPU_BIT_NUM) & 1; +} + +static int mlx5_peer_pf_enable_hca(struct mlx5_core_dev *dev) +{ + u32 out[MLX5_ST_SZ_DW(enable_hca_out)] = {}; + u32 in[MLX5_ST_SZ_DW(enable_hca_in)] = {}; + + MLX5_SET(enable_hca_in, in, opcode, MLX5_CMD_OP_ENABLE_HCA); + MLX5_SET(enable_hca_in, in, function_id, 0); + MLX5_SET(enable_hca_in, in, embedded_cpu_function, 0); + return mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out)); +} + +static int mlx5_peer_pf_disable_hca(struct mlx5_core_dev *dev) +{ + u32 out[MLX5_ST_SZ_DW(disable_hca_out)] = {}; + u32 in[MLX5_ST_SZ_DW(disable_hca_in)] = {}; + + MLX5_SET(disable_hca_in, in, opcode, MLX5_CMD_OP_DISABLE_HCA); + MLX5_SET(disable_hca_in, in, function_id, 0); + MLX5_SET(enable_hca_in, in, embedded_cpu_function, 0); + return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); +} + +static int mlx5_peer_pf_init(struct mlx5_core_dev *dev) +{ + int err; + + err = mlx5_peer_pf_enable_hca(dev); + if (err) + mlx5_core_err(dev, "Failed to enable peer PF HCA err(%d)\n", + err); + + return err; +} + +static void mlx5_peer_pf_cleanup(struct mlx5_core_dev *dev) +{ + int err; + + err = mlx5_peer_pf_disable_hca(dev); + if (err) { + mlx5_core_err(dev, "Failed to disable peer PF HCA err(%d)\n", + err); + return; + } + + err = mlx5_wait_for_pages(dev, &dev->priv.peer_pf_pages); + if (err) + mlx5_core_warn(dev, "Timeout reclaiming peer PF pages err(%d)\n", + err); +} + +int mlx5_ec_init(struct mlx5_core_dev *dev) +{ + int err = 0; + + if (!mlx5_core_is_ecpf(dev)) + return 0; + + /* ECPF shall enable HCA for peer PF in the same way a PF + * does this for its VFs. + */ + err = mlx5_peer_pf_init(dev); + if (err) + return err; + + return 0; +} + +void mlx5_ec_cleanup(struct mlx5_core_dev *dev) +{ + if (!mlx5_core_is_ecpf(dev)) + return; + + mlx5_peer_pf_cleanup(dev); +} + +static int mlx5_query_host_params_context(struct mlx5_core_dev *dev, + u32 *out, int outlen) +{ + u32 in[MLX5_ST_SZ_DW(query_host_params_in)] = {}; + + MLX5_SET(query_host_params_in, in, opcode, + MLX5_CMD_OP_QUERY_HOST_PARAMS); + + return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen); +} + +int mlx5_query_host_params_num_vfs(struct mlx5_core_dev *dev, int *num_vf) +{ + u32 out[MLX5_ST_SZ_DW(query_host_params_out)] = {}; + int err; + + err = mlx5_query_host_params_context(dev, out, sizeof(out)); + if (err) + return err; + + *num_vf = MLX5_GET(query_host_params_out, out, + host_params_context.host_num_of_vfs); + mlx5_core_dbg(dev, "host_num_of_vfs %d\n", *num_vf); + + return 0; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.h b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.h new file mode 100644 index 000000000000..346372df218f --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2019 Mellanox Technologies. */ + +#ifndef __MLX5_ECPF_H__ +#define __MLX5_ECPF_H__ + +#include <linux/mlx5/driver.h> +#include "mlx5_core.h" + +#ifdef CONFIG_MLX5_ESWITCH + +enum { + MLX5_ECPU_BIT_NUM = 23, +}; + +bool mlx5_read_embedded_cpu(struct mlx5_core_dev *dev); +int mlx5_ec_init(struct mlx5_core_dev *dev); +void mlx5_ec_cleanup(struct mlx5_core_dev *dev); +int mlx5_query_host_params_num_vfs(struct mlx5_core_dev *dev, int *num_vf); + +#else /* CONFIG_MLX5_ESWITCH */ + +static inline bool +mlx5_read_embedded_cpu(struct mlx5_core_dev *dev) { return false; } +static inline int mlx5_ec_init(struct mlx5_core_dev *dev) { return 0; } +static inline void mlx5_ec_cleanup(struct mlx5_core_dev *dev) {} +static inline int +mlx5_query_host_params_num_vfs(struct mlx5_core_dev *dev, int *num_vf) +{ return -EOPNOTSUPP; } + +#endif /* CONFIG_MLX5_ESWITCH */ + +#endif /* __MLX5_ECPF_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 6dd74ef69389..e9acfa9aa069 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -387,10 +387,7 @@ struct mlx5e_txqsq { struct mlx5e_channel *channel; int txq_ix; u32 rate_limit; - struct mlx5e_txqsq_recover { - struct work_struct recover_work; - u64 last_recover; - } recover; + struct work_struct recover_work; } ____cacheline_aligned_in_smp; struct mlx5e_dma_info { @@ -658,6 +655,7 @@ struct mlx5e_channel_stats { enum { MLX5E_STATE_OPENED, MLX5E_STATE_DESTROYING, + MLX5E_STATE_XDP_TX_ENABLED, }; struct mlx5e_rqt { @@ -683,6 +681,13 @@ struct mlx5e_rss_params { u8 hfunc; }; +struct mlx5e_modify_sq_param { + int curr_state; + int next_state; + int rl_update; + int rl_index; +}; + struct mlx5e_priv { /* priv data path fields - start */ struct mlx5e_txqsq *txq2sq[MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC]; @@ -738,6 +743,7 @@ struct mlx5e_priv { #ifdef CONFIG_MLX5_EN_TLS struct mlx5e_tls *tls; #endif + struct devlink_health_reporter *tx_reporter; }; struct mlx5e_profile { @@ -868,6 +874,11 @@ void mlx5e_set_rq_type(struct mlx5_core_dev *mdev, struct mlx5e_params *params); void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev, struct mlx5e_params *params); +int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn, + struct mlx5e_modify_sq_param *p); +void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq); +void mlx5e_tx_disable_queue(struct netdev_queue *txq); + static inline bool mlx5e_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev) { return (MLX5_CAP_ETH(mdev, tunnel_stateless_gre) && diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c index 4a37713023be..122927f3a600 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c @@ -63,66 +63,168 @@ static const u32 mlx5e_link_speed[MLX5E_LINK_MODES_NUMBER] = { [MLX5E_50GBASE_KR2] = 50000, }; -u32 mlx5e_port_ptys2speed(u32 eth_proto_oper) +static const u32 mlx5e_ext_link_speed[MLX5E_EXT_LINK_MODES_NUMBER] = { + [MLX5E_SGMII_100M] = 100, + [MLX5E_1000BASE_X_SGMII] = 1000, + [MLX5E_5GBASE_R] = 5000, + [MLX5E_10GBASE_XFI_XAUI_1] = 10000, + [MLX5E_40GBASE_XLAUI_4_XLPPI_4] = 40000, + [MLX5E_25GAUI_1_25GBASE_CR_KR] = 25000, + [MLX5E_50GAUI_2_LAUI_2_50GBASE_CR2_KR2] = 50000, + [MLX5E_50GAUI_1_LAUI_1_50GBASE_CR_KR] = 50000, + [MLX5E_CAUI_4_100GBASE_CR4_KR4] = 100000, + [MLX5E_200GAUI_4_200GBASE_CR4_KR4] = 200000, + [MLX5E_400GAUI_8] = 400000, +}; + +static void mlx5e_port_get_speed_arr(struct mlx5_core_dev *mdev, + const u32 **arr, u32 *size) +{ + bool ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet); + + *size = ext ? ARRAY_SIZE(mlx5e_ext_link_speed) : + ARRAY_SIZE(mlx5e_link_speed); + *arr = ext ? mlx5e_ext_link_speed : mlx5e_link_speed; +} + +int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, bool ext, + struct mlx5e_port_eth_proto *eproto) +{ + u32 out[MLX5_ST_SZ_DW(ptys_reg)]; + int err; + + if (!eproto) + return -EINVAL; + + if (ext != MLX5_CAP_PCAM_FEATURE(dev, ptys_extended_ethernet)) + return -EOPNOTSUPP; + + err = mlx5_query_port_ptys(dev, out, sizeof(out), MLX5_PTYS_EN, port); + if (err) + return err; + + eproto->cap = MLX5_GET_ETH_PROTO(ptys_reg, out, ext, + eth_proto_capability); + eproto->admin = MLX5_GET_ETH_PROTO(ptys_reg, out, ext, eth_proto_admin); + eproto->oper = MLX5_GET_ETH_PROTO(ptys_reg, out, ext, eth_proto_oper); + return 0; +} + +void mlx5_port_query_eth_autoneg(struct mlx5_core_dev *dev, u8 *an_status, + u8 *an_disable_cap, u8 *an_disable_admin) +{ + u32 out[MLX5_ST_SZ_DW(ptys_reg)]; + + *an_status = 0; + *an_disable_cap = 0; + *an_disable_admin = 0; + + if (mlx5_query_port_ptys(dev, out, sizeof(out), MLX5_PTYS_EN, 1)) + return; + + *an_status = MLX5_GET(ptys_reg, out, an_status); + *an_disable_cap = MLX5_GET(ptys_reg, out, an_disable_cap); + *an_disable_admin = MLX5_GET(ptys_reg, out, an_disable_admin); +} + +int mlx5_port_set_eth_ptys(struct mlx5_core_dev *dev, bool an_disable, + u32 proto_admin, bool ext) +{ + u32 out[MLX5_ST_SZ_DW(ptys_reg)]; + u32 in[MLX5_ST_SZ_DW(ptys_reg)]; + u8 an_disable_admin; + u8 an_disable_cap; + u8 an_status; + + mlx5_port_query_eth_autoneg(dev, &an_status, &an_disable_cap, + &an_disable_admin); + if (!an_disable_cap && an_disable) + return -EPERM; + + memset(in, 0, sizeof(in)); + + MLX5_SET(ptys_reg, in, local_port, 1); + MLX5_SET(ptys_reg, in, an_disable_admin, an_disable); + MLX5_SET(ptys_reg, in, proto_mask, MLX5_PTYS_EN); + if (ext) + MLX5_SET(ptys_reg, in, ext_eth_proto_admin, proto_admin); + else + MLX5_SET(ptys_reg, in, eth_proto_admin, proto_admin); + + return mlx5_core_access_reg(dev, in, sizeof(in), out, + sizeof(out), MLX5_REG_PTYS, 0, 1); +} + +u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper) { unsigned long temp = eth_proto_oper; + const u32 *table; u32 speed = 0; + u32 max_size; int i; - i = find_first_bit(&temp, MLX5E_LINK_MODES_NUMBER); - if (i < MLX5E_LINK_MODES_NUMBER) - speed = mlx5e_link_speed[i]; - + mlx5e_port_get_speed_arr(mdev, &table, &max_size); + i = find_first_bit(&temp, max_size); + if (i < max_size) + speed = table[i]; return speed; } int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed) { - u32 out[MLX5_ST_SZ_DW(ptys_reg)] = {}; - u32 eth_proto_oper; + struct mlx5e_port_eth_proto eproto; + bool ext; int err; - err = mlx5_query_port_ptys(mdev, out, sizeof(out), MLX5_PTYS_EN, 1); + ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet); + err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto); if (err) - return err; + goto out; - eth_proto_oper = MLX5_GET(ptys_reg, out, eth_proto_oper); - *speed = mlx5e_port_ptys2speed(eth_proto_oper); + *speed = mlx5e_port_ptys2speed(mdev, eproto.oper); if (!(*speed)) err = -EINVAL; +out: return err; } int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed) { + struct mlx5e_port_eth_proto eproto; u32 max_speed = 0; - u32 proto_cap; + const u32 *table; + u32 max_size; + bool ext; int err; int i; - err = mlx5_query_port_proto_cap(mdev, &proto_cap, MLX5_PTYS_EN); + ext = MLX5_CAP_PCAM_FEATURE(mdev, ptys_extended_ethernet); + err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto); if (err) return err; - for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i) - if (proto_cap & MLX5E_PROT_MASK(i)) - max_speed = max(max_speed, mlx5e_link_speed[i]); + mlx5e_port_get_speed_arr(mdev, &table, &max_size); + for (i = 0; i < max_size; ++i) + if (eproto.cap & MLX5E_PROT_MASK(i)) + max_speed = max(max_speed, table[i]); *speed = max_speed; return 0; } -u32 mlx5e_port_speed2linkmodes(u32 speed) +u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed) { u32 link_modes = 0; + const u32 *table; + u32 max_size; int i; - for (i = 0; i < MLX5E_LINK_MODES_NUMBER; ++i) { - if (mlx5e_link_speed[i] == speed) + mlx5e_port_get_speed_arr(mdev, &table, &max_size); + for (i = 0; i < max_size; ++i) { + if (table[i] == speed) link_modes |= MLX5E_PROT_MASK(i); } - return link_modes; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h index cd2160b8c9bf..70f536ec51c4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h @@ -36,10 +36,22 @@ #include <linux/mlx5/driver.h> #include "en.h" -u32 mlx5e_port_ptys2speed(u32 eth_proto_oper); +struct mlx5e_port_eth_proto { + u32 cap; + u32 admin; + u32 oper; +}; + +int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, bool ext, + struct mlx5e_port_eth_proto *eproto); +void mlx5_port_query_eth_autoneg(struct mlx5_core_dev *dev, u8 *an_status, + u8 *an_disable_cap, u8 *an_disable_admin); +int mlx5_port_set_eth_ptys(struct mlx5_core_dev *dev, bool an_disable, + u32 proto_admin, bool ext); +u32 mlx5e_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper); int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed); int mlx5e_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed); -u32 mlx5e_port_speed2linkmodes(u32 speed); +u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed); int mlx5e_port_query_pbmc(struct mlx5_core_dev *mdev, void *out); int mlx5e_port_set_pbmc(struct mlx5_core_dev *mdev, void *in); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h new file mode 100644 index 000000000000..e78e92753d73 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2019 Mellanox Technologies. */ + +#ifndef __MLX5E_EN_REPORTER_H +#define __MLX5E_EN_REPORTER_H + +#include <linux/mlx5/driver.h> +#include "en.h" + +int mlx5e_tx_reporter_create(struct mlx5e_priv *priv); +void mlx5e_tx_reporter_destroy(struct mlx5e_priv *priv); +void mlx5e_tx_reporter_err_cqe(struct mlx5e_txqsq *sq); +int mlx5e_tx_reporter_timeout(struct mlx5e_txqsq *sq); + +#endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c new file mode 100644 index 000000000000..0aebfb377cf0 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -0,0 +1,297 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2019 Mellanox Technologies. */ + +#include <net/devlink.h> +#include "reporter.h" +#include "lib/eq.h" + +#define MLX5E_TX_REPORTER_PER_SQ_MAX_LEN 256 + +struct mlx5e_tx_err_ctx { + int (*recover)(struct mlx5e_txqsq *sq); + struct mlx5e_txqsq *sq; +}; + +static int mlx5e_wait_for_sq_flush(struct mlx5e_txqsq *sq) +{ + unsigned long exp_time = jiffies + msecs_to_jiffies(2000); + + while (time_before(jiffies, exp_time)) { + if (sq->cc == sq->pc) + return 0; + + msleep(20); + } + + netdev_err(sq->channel->netdev, + "Wait for SQ 0x%x flush timeout (sq cc = 0x%x, sq pc = 0x%x)\n", + sq->sqn, sq->cc, sq->pc); + + return -ETIMEDOUT; +} + +static void mlx5e_reset_txqsq_cc_pc(struct mlx5e_txqsq *sq) +{ + WARN_ONCE(sq->cc != sq->pc, + "SQ 0x%x: cc (0x%x) != pc (0x%x)\n", + sq->sqn, sq->cc, sq->pc); + sq->cc = 0; + sq->dma_fifo_cc = 0; + sq->pc = 0; +} + +static int mlx5e_sq_to_ready(struct mlx5e_txqsq *sq, int curr_state) +{ + struct mlx5_core_dev *mdev = sq->channel->mdev; + struct net_device *dev = sq->channel->netdev; + struct mlx5e_modify_sq_param msp = {0}; + int err; + + msp.curr_state = curr_state; + msp.next_state = MLX5_SQC_STATE_RST; + + err = mlx5e_modify_sq(mdev, sq->sqn, &msp); + if (err) { + netdev_err(dev, "Failed to move sq 0x%x to reset\n", sq->sqn); + return err; + } + + memset(&msp, 0, sizeof(msp)); + msp.curr_state = MLX5_SQC_STATE_RST; + msp.next_state = MLX5_SQC_STATE_RDY; + + err = mlx5e_modify_sq(mdev, sq->sqn, &msp); + if (err) { + netdev_err(dev, "Failed to move sq 0x%x to ready\n", sq->sqn); + return err; + } + + return 0; +} + +static int mlx5e_tx_reporter_err_cqe_recover(struct mlx5e_txqsq *sq) +{ + struct mlx5_core_dev *mdev = sq->channel->mdev; + struct net_device *dev = sq->channel->netdev; + u8 state; + int err; + + if (!test_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) + return 0; + + err = mlx5_core_query_sq_state(mdev, sq->sqn, &state); + if (err) { + netdev_err(dev, "Failed to query SQ 0x%x state. err = %d\n", + sq->sqn, err); + return err; + } + + if (state != MLX5_SQC_STATE_ERR) { + netdev_err(dev, "SQ 0x%x not in ERROR state\n", sq->sqn); + return -EINVAL; + } + + mlx5e_tx_disable_queue(sq->txq); + + err = mlx5e_wait_for_sq_flush(sq); + if (err) + return err; + + /* At this point, no new packets will arrive from the stack as TXQ is + * marked with QUEUE_STATE_DRV_XOFF. In addition, NAPI cleared all + * pending WQEs. SQ can safely reset the SQ. + */ + + err = mlx5e_sq_to_ready(sq, state); + if (err) + return err; + + mlx5e_reset_txqsq_cc_pc(sq); + sq->stats->recover++; + mlx5e_activate_txqsq(sq); + + return 0; +} + +void mlx5e_tx_reporter_err_cqe(struct mlx5e_txqsq *sq) +{ + char err_str[MLX5E_TX_REPORTER_PER_SQ_MAX_LEN]; + struct mlx5e_tx_err_ctx err_ctx = {0}; + + err_ctx.sq = sq; + err_ctx.recover = mlx5e_tx_reporter_err_cqe_recover; + sprintf(err_str, "ERR CQE on SQ: 0x%x", sq->sqn); + + devlink_health_report(sq->channel->priv->tx_reporter, err_str, + &err_ctx); +} + +static int mlx5e_tx_reporter_timeout_recover(struct mlx5e_txqsq *sq) +{ + struct mlx5_eq_comp *eq = sq->cq.mcq.eq; + u32 eqe_count; + int ret; + + netdev_err(sq->channel->netdev, "EQ 0x%x: Cons = 0x%x, irqn = 0x%x\n", + eq->core.eqn, eq->core.cons_index, eq->core.irqn); + + eqe_count = mlx5_eq_poll_irq_disabled(eq); + ret = eqe_count ? true : false; + if (!eqe_count) { + clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); + return ret; + } + + netdev_err(sq->channel->netdev, "Recover %d eqes on EQ 0x%x\n", + eqe_count, eq->core.eqn); + sq->channel->stats->eq_rearm++; + return ret; +} + +int mlx5e_tx_reporter_timeout(struct mlx5e_txqsq *sq) +{ + char err_str[MLX5E_TX_REPORTER_PER_SQ_MAX_LEN]; + struct mlx5e_tx_err_ctx err_ctx; + + err_ctx.sq = sq; + err_ctx.recover = mlx5e_tx_reporter_timeout_recover; + sprintf(err_str, + "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x, usecs since last trans: %u\n", + sq->channel->ix, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc, + jiffies_to_usecs(jiffies - sq->txq->trans_start)); + + return devlink_health_report(sq->channel->priv->tx_reporter, err_str, + &err_ctx); +} + +/* state lock cannot be grabbed within this function. + * It can cause a dead lock or a read-after-free. + */ +int mlx5e_tx_reporter_recover_from_ctx(struct mlx5e_tx_err_ctx *err_ctx) +{ + return err_ctx->recover(err_ctx->sq); +} + +static int mlx5e_tx_reporter_recover_all(struct mlx5e_priv *priv) +{ + int err; + + rtnl_lock(); + mutex_lock(&priv->state_lock); + mlx5e_close_locked(priv->netdev); + err = mlx5e_open_locked(priv->netdev); + mutex_unlock(&priv->state_lock); + rtnl_unlock(); + + return err; +} + +static int mlx5e_tx_reporter_recover(struct devlink_health_reporter *reporter, + void *context) +{ + struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter); + struct mlx5e_tx_err_ctx *err_ctx = context; + + return err_ctx ? mlx5e_tx_reporter_recover_from_ctx(err_ctx) : + mlx5e_tx_reporter_recover_all(priv); +} + +static int +mlx5e_tx_reporter_build_diagnose_output(struct devlink_fmsg *fmsg, + u32 sqn, u8 state, bool stopped) +{ + int err; + + err = devlink_fmsg_obj_nest_start(fmsg); + if (err) + return err; + + err = devlink_fmsg_u32_pair_put(fmsg, "sqn", sqn); + if (err) + return err; + + err = devlink_fmsg_u8_pair_put(fmsg, "HW state", state); + if (err) + return err; + + err = devlink_fmsg_bool_pair_put(fmsg, "stopped", stopped); + if (err) + return err; + + err = devlink_fmsg_obj_nest_end(fmsg); + if (err) + return err; + + return 0; +} + +static int mlx5e_tx_reporter_diagnose(struct devlink_health_reporter *reporter, + struct devlink_fmsg *fmsg) +{ + struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter); + int i, err = 0; + + mutex_lock(&priv->state_lock); + + if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) + goto unlock; + + err = devlink_fmsg_arr_pair_nest_start(fmsg, "SQs"); + if (err) + goto unlock; + + for (i = 0; i < priv->channels.num * priv->channels.params.num_tc; + i++) { + struct mlx5e_txqsq *sq = priv->txq2sq[i]; + u8 state; + + err = mlx5_core_query_sq_state(priv->mdev, sq->sqn, &state); + if (err) + break; + + err = mlx5e_tx_reporter_build_diagnose_output(fmsg, sq->sqn, + state, + netif_xmit_stopped(sq->txq)); + if (err) + break; + } + err = devlink_fmsg_arr_pair_nest_end(fmsg); + if (err) + goto unlock; + +unlock: + mutex_unlock(&priv->state_lock); + return err; +} + +static const struct devlink_health_reporter_ops mlx5_tx_reporter_ops = { + .name = "tx", + .recover = mlx5e_tx_reporter_recover, + .diagnose = mlx5e_tx_reporter_diagnose, +}; + +#define MLX5_REPORTER_TX_GRACEFUL_PERIOD 500 + +int mlx5e_tx_reporter_create(struct mlx5e_priv *priv) +{ + struct mlx5_core_dev *mdev = priv->mdev; + struct devlink *devlink = priv_to_devlink(mdev); + + priv->tx_reporter = + devlink_health_reporter_create(devlink, &mlx5_tx_reporter_ops, + MLX5_REPORTER_TX_GRACEFUL_PERIOD, + true, priv); + if (IS_ERR_OR_NULL(priv->tx_reporter)) + netdev_warn(priv->netdev, + "Failed to create tx reporter, err = %ld\n", + PTR_ERR(priv->tx_reporter)); + return PTR_ERR_OR_ZERO(priv->tx_reporter); +} + +void mlx5e_tx_reporter_destroy(struct mlx5e_priv *priv) +{ + if (IS_ERR_OR_NULL(priv->tx_reporter)) + return; + + devlink_health_reporter_destroy(priv->tx_reporter); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index 046948ead152..bdcc5e79328d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -25,7 +25,7 @@ static int get_route_and_out_devs(struct mlx5e_priv *priv, /* if the egress device isn't on the same HW e-switch or * it's a LAG device, use the uplink */ - if (!switchdev_port_same_parent_id(priv->netdev, dev) || + if (!netdev_port_same_parent_id(priv->netdev, dev) || dst_is_lag_dev) { *route_dev = uplink_dev; *out_dev = *route_dev; @@ -256,6 +256,7 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, e->m_neigh.family = n->ops->family; memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len); e->out_dev = out_dev; + e->route_dev = route_dev; /* It's important to add the neigh to the hash table before checking * the neigh validity state. So if we'll get a notification, in case the @@ -369,6 +370,7 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, e->m_neigh.family = n->ops->family; memcpy(&e->m_neigh.dst_ip, n->primary_key, n->tbl->key_len); e->out_dev = out_dev; + e->route_dev = route_dev; /* It's importent to add the neigh to the hash table before checking * the neigh validity state. So if we'll get a notification, in case the @@ -496,25 +498,21 @@ static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv, void *headers_c, void *headers_v) { + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f); struct netlink_ext_ack *extack = f->common.extack; - struct flow_dissector_key_ports *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_PORTS, - f->key); - struct flow_dissector_key_ports *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_PORTS, - f->mask); void *misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters); void *misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters); + struct flow_match_ports enc_ports; + + flow_rule_match_enc_ports(rule, &enc_ports); /* Full udp dst port must be given */ - if (!dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_PORTS) || - memchr_inv(&mask->dst, 0xff, sizeof(mask->dst))) { + if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_PORTS) || + memchr_inv(&enc_ports.mask->dst, 0xff, sizeof(enc_ports.mask->dst))) { NL_SET_ERR_MSG_MOD(extack, "VXLAN decap filter must include enc_dst_port condition"); netdev_warn(priv->netdev, @@ -523,12 +521,12 @@ static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv, } /* udp dst port must be knonwn as a VXLAN port */ - if (!mlx5_vxlan_lookup_port(priv->mdev->vxlan, be16_to_cpu(key->dst))) { + if (!mlx5_vxlan_lookup_port(priv->mdev->vxlan, be16_to_cpu(enc_ports.key->dst))) { NL_SET_ERR_MSG_MOD(extack, "Matched UDP port is not registered as a VXLAN port"); netdev_warn(priv->netdev, "UDP port %d is not registered as a VXLAN port\n", - be16_to_cpu(key->dst)); + be16_to_cpu(enc_ports.key->dst)); return -EOPNOTSUPP; } @@ -536,26 +534,26 @@ static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv, MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ip_protocol); MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol, IPPROTO_UDP); - MLX5_SET(fte_match_set_lyr_2_4, headers_c, udp_dport, ntohs(mask->dst)); - MLX5_SET(fte_match_set_lyr_2_4, headers_v, udp_dport, ntohs(key->dst)); + MLX5_SET(fte_match_set_lyr_2_4, headers_c, udp_dport, + ntohs(enc_ports.mask->dst)); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, udp_dport, + ntohs(enc_ports.key->dst)); - MLX5_SET(fte_match_set_lyr_2_4, headers_c, udp_sport, ntohs(mask->src)); - MLX5_SET(fte_match_set_lyr_2_4, headers_v, udp_sport, ntohs(key->src)); + MLX5_SET(fte_match_set_lyr_2_4, headers_c, udp_sport, + ntohs(enc_ports.mask->src)); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, udp_sport, + ntohs(enc_ports.key->src)); /* match on VNI */ - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) { - struct flow_dissector_key_keyid *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_KEYID, - f->key); - struct flow_dissector_key_keyid *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_KEYID, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID)) { + struct flow_match_enc_keyid enc_keyid; + + flow_rule_match_enc_keyid(rule, &enc_keyid); + MLX5_SET(fte_match_set_misc, misc_c, vxlan_vni, - be32_to_cpu(mask->keyid)); + be32_to_cpu(enc_keyid.mask->keyid)); MLX5_SET(fte_match_set_misc, misc_v, vxlan_vni, - be32_to_cpu(key->keyid)); + be32_to_cpu(enc_keyid.key->keyid)); } return 0; } @@ -570,6 +568,7 @@ static int mlx5e_tc_tun_parse_gretap(struct mlx5e_priv *priv, misc_parameters); void *misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters); + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f); if (!MLX5_CAP_ESW(priv->mdev, nvgre_encap_decap)) { NL_SET_ERR_MSG_MOD(f->common.extack, @@ -587,21 +586,14 @@ static int mlx5e_tc_tun_parse_gretap(struct mlx5e_priv *priv, MLX5_SET(fte_match_set_misc, misc_v, gre_protocol, ETH_P_TEB); /* gre key */ - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) { - struct flow_dissector_key_keyid *mask = NULL; - struct flow_dissector_key_keyid *key = NULL; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID)) { + struct flow_match_enc_keyid enc_keyid; - mask = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_KEYID, - f->mask); + flow_rule_match_enc_keyid(rule, &enc_keyid); MLX5_SET(fte_match_set_misc, misc_c, - gre_key.key, be32_to_cpu(mask->keyid)); - - key = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_KEYID, - f->key); + gre_key.key, be32_to_cpu(enc_keyid.mask->keyid)); MLX5_SET(fte_match_set_misc, misc_v, - gre_key.key, be32_to_cpu(key->keyid)); + gre_key.key, be32_to_cpu(enc_keyid.key->keyid)); } return 0; @@ -612,16 +604,18 @@ int mlx5e_tc_tun_parse(struct net_device *filter_dev, struct mlx5_flow_spec *spec, struct tc_cls_flower_offload *f, void *headers_c, - void *headers_v) + void *headers_v, u8 *match_level) { int tunnel_type; int err = 0; tunnel_type = mlx5e_tc_tun_get_type(filter_dev); if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_VXLAN) { + *match_level = MLX5_MATCH_L4; err = mlx5e_tc_tun_parse_vxlan(priv, spec, f, headers_c, headers_v); } else if (tunnel_type == MLX5E_TC_TUNNEL_TYPE_GRETAP) { + *match_level = MLX5_MATCH_L3; err = mlx5e_tc_tun_parse_gretap(priv, spec, f, headers_c, headers_v); } else { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h index 706ce7bf15e7..b63f15de899d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h @@ -39,6 +39,6 @@ int mlx5e_tc_tun_parse(struct net_device *filter_dev, struct mlx5_flow_spec *spec, struct tc_cls_flower_offload *f, void *headers_c, - void *headers_v); + void *headers_v, u8 *match_level); #endif //__MLX5_EN_TC_TUNNEL_H__ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index 3740177eed09..03b2a9f9c589 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -365,7 +365,8 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, int sq_num; int i; - if (unlikely(!test_bit(MLX5E_STATE_OPENED, &priv->state))) + /* this flag is sufficient, no need to test internal sq state */ + if (unlikely(!mlx5e_xdp_tx_is_enabled(priv))) return -ENETDOWN; if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) @@ -378,9 +379,6 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, sq = &priv->channels.c[sq_num]->xdpsq; - if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state))) - return -ENETDOWN; - for (i = 0; i < n; i++) { struct xdp_frame *xdpf = frames[i]; struct mlx5e_xdp_info xdpi; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h index 3a67cb3cd179..ee27a7c8cd87 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h @@ -50,6 +50,23 @@ void mlx5e_xdp_rx_poll_complete(struct mlx5e_rq *rq); int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags); +static inline void mlx5e_xdp_tx_enable(struct mlx5e_priv *priv) +{ + set_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state); +} + +static inline void mlx5e_xdp_tx_disable(struct mlx5e_priv *priv) +{ + clear_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state); + /* let other device's napi(s) see our new state */ + synchronize_rcu(); +} + +static inline bool mlx5e_xdp_tx_is_enabled(struct mlx5e_priv *priv) +{ + return test_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state); +} + static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq) { if (sq->doorbell_cseg) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 3bbccead2f63..3cd73254d020 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -354,9 +354,6 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv, new_channels.params = priv->channels.params; new_channels.params.num_channels = count; - if (!netif_is_rxfh_configured(priv->netdev)) - mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt, - MLX5E_INDIR_RQT_SIZE, count); if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { priv->channels.params = new_channels.params; @@ -372,6 +369,10 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv, if (arfs_enabled) mlx5e_arfs_disable(priv); + if (!netif_is_rxfh_configured(priv->netdev)) + mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt, + MLX5E_INDIR_RQT_SIZE, count); + /* Switch to new channels, set new parameters and close old ones */ mlx5e_switch_priv_channels(priv, &new_channels, NULL); @@ -695,13 +696,14 @@ static void get_speed_duplex(struct net_device *netdev, u32 eth_proto_oper, struct ethtool_link_ksettings *link_ksettings) { + struct mlx5e_priv *priv = netdev_priv(netdev); u32 speed = SPEED_UNKNOWN; u8 duplex = DUPLEX_UNKNOWN; if (!netif_carrier_ok(netdev)) goto out; - speed = mlx5e_port_ptys2speed(eth_proto_oper); + speed = mlx5e_port_ptys2speed(priv->mdev, eth_proto_oper); if (!speed) { speed = SPEED_UNKNOWN; goto out; @@ -885,7 +887,7 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv, const struct ethtool_link_ksettings *link_ksettings) { struct mlx5_core_dev *mdev = priv->mdev; - u32 eth_proto_cap, eth_proto_admin; + struct mlx5e_port_eth_proto eproto; bool an_changes = false; u8 an_disable_admin; u8 an_disable_cap; @@ -899,16 +901,16 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv, link_modes = link_ksettings->base.autoneg == AUTONEG_ENABLE ? mlx5e_ethtool2ptys_adver_link(link_ksettings->link_modes.advertising) : - mlx5e_port_speed2linkmodes(speed); + mlx5e_port_speed2linkmodes(mdev, speed); - err = mlx5_query_port_proto_cap(mdev, ð_proto_cap, MLX5_PTYS_EN); + err = mlx5_port_query_eth_proto(mdev, 1, false, &eproto); if (err) { - netdev_err(priv->netdev, "%s: query port eth proto cap failed: %d\n", + netdev_err(priv->netdev, "%s: query port eth proto failed: %d\n", __func__, err); goto out; } - link_modes = link_modes & eth_proto_cap; + link_modes = link_modes & eproto.cap; if (!link_modes) { netdev_err(priv->netdev, "%s: Not supported link mode(s) requested", __func__); @@ -916,24 +918,17 @@ int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv, goto out; } - err = mlx5_query_port_proto_admin(mdev, ð_proto_admin, MLX5_PTYS_EN); - if (err) { - netdev_err(priv->netdev, "%s: query port eth proto admin failed: %d\n", - __func__, err); - goto out; - } - - mlx5_query_port_autoneg(mdev, MLX5_PTYS_EN, &an_status, - &an_disable_cap, &an_disable_admin); + mlx5_port_query_eth_autoneg(mdev, &an_status, &an_disable_cap, + &an_disable_admin); an_disable = link_ksettings->base.autoneg == AUTONEG_DISABLE; an_changes = ((!an_disable && an_disable_admin) || (an_disable && !an_disable_admin)); - if (!an_changes && link_modes == eth_proto_admin) + if (!an_changes && link_modes == eproto.admin) goto out; - mlx5_set_port_ptys(mdev, an_disable, link_modes, MLX5_PTYS_EN); + mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, false); mlx5_toggle_port_link(mdev); out: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 17b6babbed8a..83510ca0bcd8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -51,6 +51,7 @@ #include "en/xdp.h" #include "lib/eq.h" #include "en/monitor_stats.h" +#include "en/reporter.h" struct mlx5e_rq_param { u32 rqc[MLX5_ST_SZ_DW(rqc)]; @@ -949,7 +950,7 @@ static int mlx5e_open_rq(struct mlx5e_channel *c, if (params->rx_dim_enabled) __set_bit(MLX5E_RQ_STATE_AM, &c->rq.state); - if (params->pflags & MLX5E_PFLAG_RX_NO_CSUM_COMPLETE) + if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_NO_CSUM_COMPLETE)) __set_bit(MLX5E_RQ_STATE_NO_CSUM_COMPLETE, &c->rq.state); return 0; @@ -1159,7 +1160,7 @@ static int mlx5e_alloc_txqsq_db(struct mlx5e_txqsq *sq, int numa) return 0; } -static void mlx5e_sq_recover(struct work_struct *work); +static void mlx5e_tx_err_cqe_work(struct work_struct *recover_work); static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, int txq_ix, struct mlx5e_params *params, @@ -1181,7 +1182,7 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, sq->uar_map = mdev->mlx5e_res.bfreg.map; sq->min_inline_mode = params->tx_min_inline_mode; sq->stats = &c->priv->channel_stats[c->ix].sq[tc]; - INIT_WORK(&sq->recover.recover_work, mlx5e_sq_recover); + INIT_WORK(&sq->recover_work, mlx5e_tx_err_cqe_work); if (MLX5_IPSEC_DEV(c->priv->mdev)) set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state); if (mlx5_accel_is_tls_device(c->priv->mdev)) @@ -1269,15 +1270,8 @@ static int mlx5e_create_sq(struct mlx5_core_dev *mdev, return err; } -struct mlx5e_modify_sq_param { - int curr_state; - int next_state; - bool rl_update; - int rl_index; -}; - -static int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn, - struct mlx5e_modify_sq_param *p) +int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn, + struct mlx5e_modify_sq_param *p) { void *in; void *sqc; @@ -1375,17 +1369,7 @@ err_free_txqsq: return err; } -static void mlx5e_reset_txqsq_cc_pc(struct mlx5e_txqsq *sq) -{ - WARN_ONCE(sq->cc != sq->pc, - "SQ 0x%x: cc (0x%x) != pc (0x%x)\n", - sq->sqn, sq->cc, sq->pc); - sq->cc = 0; - sq->dma_fifo_cc = 0; - sq->pc = 0; -} - -static void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq) +void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq) { sq->txq = netdev_get_tx_queue(sq->channel->netdev, sq->txq_ix); clear_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state); @@ -1394,7 +1378,7 @@ static void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq) netif_tx_start_queue(sq->txq); } -static inline void netif_tx_disable_queue(struct netdev_queue *txq) +void mlx5e_tx_disable_queue(struct netdev_queue *txq) { __netif_tx_lock_bh(txq); netif_tx_stop_queue(txq); @@ -1410,7 +1394,7 @@ static void mlx5e_deactivate_txqsq(struct mlx5e_txqsq *sq) /* prevent netif_tx_wake_queue */ napi_synchronize(&c->napi); - netif_tx_disable_queue(sq->txq); + mlx5e_tx_disable_queue(sq->txq); /* last doorbell out, godspeed .. */ if (mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, 1)) { @@ -1430,6 +1414,7 @@ static void mlx5e_close_txqsq(struct mlx5e_txqsq *sq) struct mlx5_rate_limit rl = {0}; cancel_work_sync(&sq->dim.work); + cancel_work_sync(&sq->recover_work); mlx5e_destroy_sq(mdev, sq->sqn); if (sq->rate_limit) { rl.rate = sq->rate_limit; @@ -1439,105 +1424,12 @@ static void mlx5e_close_txqsq(struct mlx5e_txqsq *sq) mlx5e_free_txqsq(sq); } -static int mlx5e_wait_for_sq_flush(struct mlx5e_txqsq *sq) -{ - unsigned long exp_time = jiffies + msecs_to_jiffies(2000); - - while (time_before(jiffies, exp_time)) { - if (sq->cc == sq->pc) - return 0; - - msleep(20); - } - - netdev_err(sq->channel->netdev, - "Wait for SQ 0x%x flush timeout (sq cc = 0x%x, sq pc = 0x%x)\n", - sq->sqn, sq->cc, sq->pc); - - return -ETIMEDOUT; -} - -static int mlx5e_sq_to_ready(struct mlx5e_txqsq *sq, int curr_state) -{ - struct mlx5_core_dev *mdev = sq->channel->mdev; - struct net_device *dev = sq->channel->netdev; - struct mlx5e_modify_sq_param msp = {0}; - int err; - - msp.curr_state = curr_state; - msp.next_state = MLX5_SQC_STATE_RST; - - err = mlx5e_modify_sq(mdev, sq->sqn, &msp); - if (err) { - netdev_err(dev, "Failed to move sq 0x%x to reset\n", sq->sqn); - return err; - } - - memset(&msp, 0, sizeof(msp)); - msp.curr_state = MLX5_SQC_STATE_RST; - msp.next_state = MLX5_SQC_STATE_RDY; - - err = mlx5e_modify_sq(mdev, sq->sqn, &msp); - if (err) { - netdev_err(dev, "Failed to move sq 0x%x to ready\n", sq->sqn); - return err; - } - - return 0; -} - -static void mlx5e_sq_recover(struct work_struct *work) +static void mlx5e_tx_err_cqe_work(struct work_struct *recover_work) { - struct mlx5e_txqsq_recover *recover = - container_of(work, struct mlx5e_txqsq_recover, - recover_work); - struct mlx5e_txqsq *sq = container_of(recover, struct mlx5e_txqsq, - recover); - struct mlx5_core_dev *mdev = sq->channel->mdev; - struct net_device *dev = sq->channel->netdev; - u8 state; - int err; - - err = mlx5_core_query_sq_state(mdev, sq->sqn, &state); - if (err) { - netdev_err(dev, "Failed to query SQ 0x%x state. err = %d\n", - sq->sqn, err); - return; - } - - if (state != MLX5_RQC_STATE_ERR) { - netdev_err(dev, "SQ 0x%x not in ERROR state\n", sq->sqn); - return; - } - - netif_tx_disable_queue(sq->txq); - - if (mlx5e_wait_for_sq_flush(sq)) - return; - - /* If the interval between two consecutive recovers per SQ is too - * short, don't recover to avoid infinite loop of ERR_CQE -> recover. - * If we reached this state, there is probably a bug that needs to be - * fixed. let's keep the queue close and let tx timeout cleanup. - */ - if (jiffies_to_msecs(jiffies - recover->last_recover) < - MLX5E_SQ_RECOVER_MIN_INTERVAL) { - netdev_err(dev, "Recover SQ 0x%x canceled, too many error CQEs\n", - sq->sqn); - return; - } - - /* At this point, no new packets will arrive from the stack as TXQ is - * marked with QUEUE_STATE_DRV_XOFF. In addition, NAPI cleared all - * pending WQEs. SQ can safely reset the SQ. - */ - if (mlx5e_sq_to_ready(sq, state)) - return; + struct mlx5e_txqsq *sq = container_of(recover_work, struct mlx5e_txqsq, + recover_work); - mlx5e_reset_txqsq_cc_pc(sq); - sq->stats->recover++; - recover->last_recover = jiffies; - mlx5e_activate_txqsq(sq); + mlx5e_tx_reporter_err_cqe(sq); } static int mlx5e_open_icosq(struct mlx5e_channel *c, @@ -2967,6 +2859,7 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv) mlx5e_build_tx2sq_maps(priv); mlx5e_activate_channels(&priv->channels); + mlx5e_xdp_tx_enable(priv); netif_tx_start_all_queues(priv->netdev); if (mlx5e_is_vport_rep(priv)) @@ -2988,6 +2881,7 @@ void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv) */ netif_tx_stop_all_queues(priv->netdev); netif_tx_disable(priv->netdev); + mlx5e_xdp_tx_disable(priv); mlx5e_deactivate_channels(&priv->channels); } @@ -3236,6 +3130,7 @@ static void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv) { int tc; + mlx5e_tx_reporter_destroy(priv); for (tc = 0; tc < priv->profile->max_tc; tc++) mlx5e_destroy_tis(priv->mdev, priv->tisn[tc]); } @@ -4223,31 +4118,13 @@ netdev_features_t mlx5e_features_check(struct sk_buff *skb, return features; } -static bool mlx5e_tx_timeout_eq_recover(struct net_device *dev, - struct mlx5e_txqsq *sq) -{ - struct mlx5_eq_comp *eq = sq->cq.mcq.eq; - u32 eqe_count; - - netdev_err(dev, "EQ 0x%x: Cons = 0x%x, irqn = 0x%x\n", - eq->core.eqn, eq->core.cons_index, eq->core.irqn); - - eqe_count = mlx5_eq_poll_irq_disabled(eq); - if (!eqe_count) - return false; - - netdev_err(dev, "Recover %d eqes on EQ 0x%x\n", eqe_count, eq->core.eqn); - sq->channel->stats->eq_rearm++; - return true; -} - static void mlx5e_tx_timeout_work(struct work_struct *work) { struct mlx5e_priv *priv = container_of(work, struct mlx5e_priv, tx_timeout_work); - struct net_device *dev = priv->netdev; - bool reopen_channels = false; - int i, err; + bool report_failed = false; + int err; + int i; rtnl_lock(); mutex_lock(&priv->state_lock); @@ -4256,31 +4133,22 @@ static void mlx5e_tx_timeout_work(struct work_struct *work) goto unlock; for (i = 0; i < priv->channels.num * priv->channels.params.num_tc; i++) { - struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, i); + struct netdev_queue *dev_queue = + netdev_get_tx_queue(priv->netdev, i); struct mlx5e_txqsq *sq = priv->txq2sq[i]; if (!netif_xmit_stopped(dev_queue)) continue; - netdev_err(dev, - "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x, usecs since last trans: %u\n", - i, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc, - jiffies_to_usecs(jiffies - dev_queue->trans_start)); - - /* If we recover a lost interrupt, most likely TX timeout will - * be resolved, skip reopening channels - */ - if (!mlx5e_tx_timeout_eq_recover(dev, sq)) { - clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); - reopen_channels = true; - } + if (mlx5e_tx_reporter_timeout(sq)) + report_failed = true; } - if (!reopen_channels) + if (!report_failed) goto unlock; - mlx5e_close_locked(dev); - err = mlx5e_open_locked(dev); + mlx5e_close_locked(priv->netdev); + err = mlx5e_open_locked(priv->netdev); if (err) netdev_err(priv->netdev, "mlx5e_open_locked failed recovering from a tx_timeout, err(%d).\n", @@ -4296,6 +4164,12 @@ static void mlx5e_tx_timeout(struct net_device *dev) struct mlx5e_priv *priv = netdev_priv(dev); netdev_err(dev, "TX timeout detected\n"); + + if (IS_ERR_OR_NULL(priv->tx_reporter)) { + netdev_err_once(priv->netdev, "tx timeout will not be handled, no valid tx reporter\n"); + return; + } + queue_work(priv->wq, &priv->tx_timeout_work); } @@ -4953,6 +4827,7 @@ static int mlx5e_init_nic_tx(struct mlx5e_priv *priv) #ifdef CONFIG_MLX5_CORE_EN_DCB mlx5e_dcbnl_initialize(priv); #endif + mlx5e_tx_reporter_create(priv); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index edb34b397c53..287d48e5b073 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -153,7 +153,7 @@ static void mlx5e_rep_update_hw_counters(struct mlx5e_priv *priv) struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_eswitch_rep *rep = rpriv->rep; - if (rep->vport == FDB_UPLINK_VPORT) + if (rep->vport == MLX5_VPORT_UPLINK) mlx5e_uplink_rep_update_hw_counters(priv); else mlx5e_vf_rep_update_hw_counters(priv); @@ -381,7 +381,8 @@ static const struct ethtool_ops mlx5e_uplink_rep_ethtool_ops = { .set_pauseparam = mlx5e_uplink_rep_set_pauseparam, }; -static int mlx5e_attr_get(struct net_device *dev, struct switchdev_attr *attr) +static int mlx5e_rep_get_port_parent_id(struct net_device *dev, + struct netdev_phys_item_id *ppid) { struct mlx5e_priv *priv = netdev_priv(dev); struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; @@ -398,20 +399,14 @@ static int mlx5e_attr_get(struct net_device *dev, struct switchdev_attr *attr) uplink_priv = netdev_priv(uplink_dev); } - switch (attr->id) { - case SWITCHDEV_ATTR_ID_PORT_PARENT_ID: - attr->u.ppid.id_len = ETH_ALEN; - if (uplink_upper && mlx5_lag_is_sriov(uplink_priv->mdev)) { - ether_addr_copy(attr->u.ppid.id, uplink_upper->dev_addr); - } else { - struct mlx5e_rep_priv *rpriv = priv->ppriv; - struct mlx5_eswitch_rep *rep = rpriv->rep; + ppid->id_len = ETH_ALEN; + if (uplink_upper && mlx5_lag_is_sriov(uplink_priv->mdev)) { + ether_addr_copy(ppid->id, uplink_upper->dev_addr); + } else { + struct mlx5e_rep_priv *rpriv = priv->ppriv; + struct mlx5_eswitch_rep *rep = rpriv->rep; - ether_addr_copy(attr->u.ppid.id, rep->hw_id); - } - break; - default: - return -EOPNOTSUPP; + ether_addr_copy(ppid->id, rep->hw_id); } return 0; @@ -584,6 +579,10 @@ static void mlx5e_rep_update_flows(struct mlx5e_priv *priv, if (neigh_connected && !(e->flags & MLX5_ENCAP_ENTRY_VALID)) { ether_addr_copy(e->h_dest, ha); ether_addr_copy(eth->h_dest, ha); + /* Update the encap source mac, in case that we delete + * the flows when encap source mac changed. + */ + ether_addr_copy(eth->h_source, e->route_dev->dev_addr); mlx5e_tc_encap_flows_add(priv, e); } @@ -1084,7 +1083,8 @@ static int mlx5e_vf_rep_open(struct net_device *dev) if (!mlx5_modify_vport_admin_state(priv->mdev, MLX5_VPORT_STATE_OP_MOD_ESW_VPORT, - rep->vport, MLX5_VPORT_ADMIN_STATE_UP)) + rep->vport, 1, + MLX5_VPORT_ADMIN_STATE_UP)) netif_carrier_on(dev); unlock: @@ -1102,7 +1102,8 @@ static int mlx5e_vf_rep_close(struct net_device *dev) mutex_lock(&priv->state_lock); mlx5_modify_vport_admin_state(priv->mdev, MLX5_VPORT_STATE_OP_MOD_ESW_VPORT, - rep->vport, MLX5_VPORT_ADMIN_STATE_DOWN); + rep->vport, 1, + MLX5_VPORT_ADMIN_STATE_DOWN); ret = mlx5e_close_locked(dev); mutex_unlock(&priv->state_lock); return ret; @@ -1114,9 +1115,17 @@ static int mlx5e_rep_get_phys_port_name(struct net_device *dev, struct mlx5e_priv *priv = netdev_priv(dev); struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_eswitch_rep *rep = rpriv->rep; - int ret; + int ret, pf_num; + + ret = mlx5_lag_get_pf_num(priv->mdev, &pf_num); + if (ret) + return ret; + + if (rep->vport == MLX5_VPORT_UPLINK) + ret = snprintf(buf, len, "p%d", pf_num); + else + ret = snprintf(buf, len, "pf%dvf%d", pf_num, rep->vport - 1); - ret = snprintf(buf, len, "%d", rep->vport - 1); if (ret >= len) return -EOPNOTSUPP; @@ -1199,7 +1208,7 @@ bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv) return false; rep = rpriv->rep; - return (rep->vport == FDB_UPLINK_VPORT); + return (rep->vport == MLX5_VPORT_UPLINK); } static bool mlx5e_rep_has_offload_stats(const struct net_device *dev, int attr_id) @@ -1264,9 +1273,17 @@ static int mlx5e_uplink_rep_set_mac(struct net_device *netdev, void *addr) return 0; } -static const struct switchdev_ops mlx5e_rep_switchdev_ops = { - .switchdev_port_attr_get = mlx5e_attr_get, -}; +static int mlx5e_uplink_rep_set_vf_vlan(struct net_device *dev, int vf, u16 vlan, u8 qos, + __be16 vlan_proto) +{ + netdev_warn_once(dev, "legacy vf vlan setting isn't supported in switchdev mode\n"); + + if (vlan != 0) + return -EOPNOTSUPP; + + /* allow setting 0-vid for compatibility with libvirt */ + return 0; +} static const struct net_device_ops mlx5e_netdev_ops_vf_rep = { .ndo_open = mlx5e_vf_rep_open, @@ -1278,6 +1295,7 @@ static const struct net_device_ops mlx5e_netdev_ops_vf_rep = { .ndo_has_offload_stats = mlx5e_rep_has_offload_stats, .ndo_get_offload_stats = mlx5e_rep_get_offload_stats, .ndo_change_mtu = mlx5e_vf_rep_change_mtu, + .ndo_get_port_parent_id = mlx5e_rep_get_port_parent_id, }; static const struct net_device_ops mlx5e_netdev_ops_uplink_rep = { @@ -1298,6 +1316,8 @@ static const struct net_device_ops mlx5e_netdev_ops_uplink_rep = { .ndo_set_vf_rate = mlx5e_set_vf_rate, .ndo_get_vf_config = mlx5e_get_vf_config, .ndo_get_vf_stats = mlx5e_get_vf_stats, + .ndo_set_vf_vlan = mlx5e_uplink_rep_set_vf_vlan, + .ndo_get_port_parent_id = mlx5e_rep_get_port_parent_id, }; bool mlx5e_eswitch_rep(struct net_device *netdev) @@ -1326,7 +1346,7 @@ static void mlx5e_build_rep_params(struct net_device *netdev) params->sw_mtu = netdev->mtu; /* SQ */ - if (rep->vport == FDB_UPLINK_VPORT) + if (rep->vport == MLX5_VPORT_UPLINK) params->log_sq_size = MLX5E_PARAMS_DEFAULT_LOG_SQ_SIZE; else params->log_sq_size = MLX5E_REP_PARAMS_DEF_LOG_SQ_SIZE; @@ -1353,7 +1373,7 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev) struct mlx5_eswitch_rep *rep = rpriv->rep; struct mlx5_core_dev *mdev = priv->mdev; - if (rep->vport == FDB_UPLINK_VPORT) { + if (rep->vport == MLX5_VPORT_UPLINK) { SET_NETDEV_DEV(netdev, &priv->mdev->pdev->dev); netdev->netdev_ops = &mlx5e_netdev_ops_uplink_rep; /* we want a persistent mac for the uplink rep */ @@ -1372,8 +1392,6 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev) netdev->watchdog_timeo = 15 * HZ; - netdev->switchdev_ops = &mlx5e_rep_switchdev_ops; - netdev->features |= NETIF_F_HW_TC | NETIF_F_NETNS_LOCAL; netdev->hw_features |= NETIF_F_HW_TC; @@ -1385,7 +1403,7 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev) netdev->hw_features |= NETIF_F_TSO6; netdev->hw_features |= NETIF_F_RXCSUM; - if (rep->vport != FDB_UPLINK_VPORT) + if (rep->vport != MLX5_VPORT_UPLINK) netdev->features |= NETIF_F_VLAN_CHALLENGED; netdev->features |= netdev->hw_features; @@ -1538,7 +1556,7 @@ static int mlx5e_init_rep_tx(struct mlx5e_priv *priv) return err; } - if (rpriv->rep->vport == FDB_UPLINK_VPORT) { + if (rpriv->rep->vport == MLX5_VPORT_UPLINK) { uplink_priv = &rpriv->uplink_priv; /* init shared tc flow table */ @@ -1574,7 +1592,7 @@ static void mlx5e_cleanup_rep_tx(struct mlx5e_priv *priv) for (tc = 0; tc < priv->profile->max_tc; tc++) mlx5e_destroy_tis(priv->mdev, priv->tisn[tc]); - if (rpriv->rep->vport == FDB_UPLINK_VPORT) { + if (rpriv->rep->vport == MLX5_VPORT_UPLINK) { /* clean indirect TC block notifications */ unregister_netdevice_notifier(&rpriv->uplink_priv.netdevice_nb); mlx5e_rep_indr_clean_block_privs(rpriv); @@ -1693,7 +1711,7 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) rpriv->rep = rep; nch = mlx5e_get_max_num_channels(dev); - profile = (rep->vport == FDB_UPLINK_VPORT) ? &mlx5e_uplink_rep_profile : &mlx5e_vf_rep_profile; + profile = (rep->vport == MLX5_VPORT_UPLINK) ? &mlx5e_uplink_rep_profile : &mlx5e_vf_rep_profile; netdev = mlx5e_create_netdev(dev, profile, nch, rpriv); if (!netdev) { pr_warn("Failed to create representor netdev for vport %d\n", @@ -1706,7 +1724,7 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) rep->rep_if[REP_ETH].priv = rpriv; INIT_LIST_HEAD(&rpriv->vport_sqs_list); - if (rep->vport == FDB_UPLINK_VPORT) { + if (rep->vport == MLX5_VPORT_UPLINK) { err = mlx5e_create_mdev_resources(dev); if (err) goto err_destroy_netdev; @@ -1742,7 +1760,7 @@ err_detach_netdev: mlx5e_detach_netdev(netdev_priv(netdev)); err_destroy_mdev_resources: - if (rep->vport == FDB_UPLINK_VPORT) + if (rep->vport == MLX5_VPORT_UPLINK) mlx5e_destroy_mdev_resources(dev); err_destroy_netdev: @@ -1762,7 +1780,7 @@ mlx5e_vport_rep_unload(struct mlx5_eswitch_rep *rep) unregister_netdev(netdev); mlx5e_rep_neigh_cleanup(rpriv); mlx5e_detach_netdev(priv); - if (rep->vport == FDB_UPLINK_VPORT) + if (rep->vport == MLX5_VPORT_UPLINK) mlx5e_destroy_mdev_resources(priv->mdev); mlx5e_destroy_netdev(priv); kfree(ppriv); /* mlx5e_rep_priv */ @@ -1780,25 +1798,18 @@ static void *mlx5e_vport_rep_get_proto_dev(struct mlx5_eswitch_rep *rep) void mlx5e_rep_register_vport_reps(struct mlx5_core_dev *mdev) { struct mlx5_eswitch *esw = mdev->priv.eswitch; - int total_vfs = MLX5_TOTAL_VPORTS(mdev); - int vport; + struct mlx5_eswitch_rep_if rep_if = {}; - for (vport = 0; vport < total_vfs; vport++) { - struct mlx5_eswitch_rep_if rep_if = {}; + rep_if.load = mlx5e_vport_rep_load; + rep_if.unload = mlx5e_vport_rep_unload; + rep_if.get_proto_dev = mlx5e_vport_rep_get_proto_dev; - rep_if.load = mlx5e_vport_rep_load; - rep_if.unload = mlx5e_vport_rep_unload; - rep_if.get_proto_dev = mlx5e_vport_rep_get_proto_dev; - mlx5_eswitch_register_vport_rep(esw, vport, &rep_if, REP_ETH); - } + mlx5_eswitch_register_vport_reps(esw, &rep_if, REP_ETH); } void mlx5e_rep_unregister_vport_reps(struct mlx5_core_dev *mdev) { struct mlx5_eswitch *esw = mdev->priv.eswitch; - int total_vfs = MLX5_TOTAL_VPORTS(mdev); - int vport; - for (vport = total_vfs - 1; vport >= 0; vport--) - mlx5_eswitch_unregister_vport_rep(esw, vport, REP_ETH); + mlx5_eswitch_unregister_vport_reps(esw, REP_ETH); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h index edd722824697..36eafc877e6b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h @@ -148,6 +148,7 @@ struct mlx5e_encap_entry { unsigned char h_dest[ETH_ALEN]; /* destination eth addr */ struct net_device *out_dev; + struct net_device *route_dev; int tunnel_type; int tunnel_hlen; int reformat_type; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 74159d39dd66..05892fc4e03f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -38,7 +38,6 @@ #include <linux/mlx5/fs.h> #include <linux/mlx5/device.h> #include <linux/rhashtable.h> -#include <net/switchdev.h> #include <net/tc_act/tc_mirred.h> #include <net/tc_act/tc_vlan.h> #include <net/tc_act/tc_tunnel_key.h> @@ -128,6 +127,7 @@ struct mlx5e_tc_flow_parse_attr { struct net_device *filter_dev; struct mlx5_flow_spec spec; int num_mod_hdr_actions; + int max_mod_hdr_actions; void *mod_hdr_actions; int mirred_ifindex[MLX5_MAX_FLOW_FWD_VPORTS]; }; @@ -1302,101 +1302,89 @@ static void mlx5e_tc_del_flow(struct mlx5e_priv *priv, static int parse_tunnel_attr(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec, struct tc_cls_flower_offload *f, - struct net_device *filter_dev) + struct net_device *filter_dev, u8 *match_level) { struct netlink_ext_ack *extack = f->common.extack; void *headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, outer_headers); void *headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, outer_headers); - - struct flow_dissector_key_control *enc_control = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_CONTROL, - f->key); - int err = 0; + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f); + struct flow_match_control enc_control; + int err; err = mlx5e_tc_tun_parse(filter_dev, priv, spec, f, - headers_c, headers_v); + headers_c, headers_v, match_level); if (err) { NL_SET_ERR_MSG_MOD(extack, "failed to parse tunnel attributes"); return err; } - if (enc_control->addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { - struct flow_dissector_key_ipv4_addrs *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, - f->key); - struct flow_dissector_key_ipv4_addrs *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, - f->mask); + flow_rule_match_enc_control(rule, &enc_control); + + if (enc_control.key->addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { + struct flow_match_ipv4_addrs match; + + flow_rule_match_enc_ipv4_addrs(rule, &match); MLX5_SET(fte_match_set_lyr_2_4, headers_c, src_ipv4_src_ipv6.ipv4_layout.ipv4, - ntohl(mask->src)); + ntohl(match.mask->src)); MLX5_SET(fte_match_set_lyr_2_4, headers_v, src_ipv4_src_ipv6.ipv4_layout.ipv4, - ntohl(key->src)); + ntohl(match.key->src)); MLX5_SET(fte_match_set_lyr_2_4, headers_c, dst_ipv4_dst_ipv6.ipv4_layout.ipv4, - ntohl(mask->dst)); + ntohl(match.mask->dst)); MLX5_SET(fte_match_set_lyr_2_4, headers_v, dst_ipv4_dst_ipv6.ipv4_layout.ipv4, - ntohl(key->dst)); + ntohl(match.key->dst)); MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ethertype); MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype, ETH_P_IP); - } else if (enc_control->addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { - struct flow_dissector_key_ipv6_addrs *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS, - f->key); - struct flow_dissector_key_ipv6_addrs *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS, - f->mask); + } else if (enc_control.key->addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { + struct flow_match_ipv6_addrs match; + flow_rule_match_enc_ipv6_addrs(rule, &match); memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c, src_ipv4_src_ipv6.ipv6_layout.ipv6), - &mask->src, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6)); + &match.mask->src, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6)); memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, src_ipv4_src_ipv6.ipv6_layout.ipv6), - &key->src, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6)); + &match.key->src, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6)); memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c, dst_ipv4_dst_ipv6.ipv6_layout.ipv6), - &mask->dst, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6)); + &match.mask->dst, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6)); memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, dst_ipv4_dst_ipv6.ipv6_layout.ipv6), - &key->dst, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6)); + &match.key->dst, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6)); MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ethertype); MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype, ETH_P_IPV6); } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_IP)) { - struct flow_dissector_key_ip *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_IP, - f->key); - struct flow_dissector_key_ip *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_IP, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IP)) { + struct flow_match_ip match; - MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_ecn, mask->tos & 0x3); - MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_ecn, key->tos & 0x3); + flow_rule_match_enc_ip(rule, &match); + MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_ecn, + match.mask->tos & 0x3); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_ecn, + match.key->tos & 0x3); - MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_dscp, mask->tos >> 2); - MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_dscp, key->tos >> 2); + MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_dscp, + match.mask->tos >> 2); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_dscp, + match.key->tos >> 2); - MLX5_SET(fte_match_set_lyr_2_4, headers_c, ttl_hoplimit, mask->ttl); - MLX5_SET(fte_match_set_lyr_2_4, headers_v, ttl_hoplimit, key->ttl); + MLX5_SET(fte_match_set_lyr_2_4, headers_c, ttl_hoplimit, + match.mask->ttl); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, ttl_hoplimit, + match.key->ttl); - if (mask->ttl && + if (match.mask->ttl && !MLX5_CAP_ESW_FLOWTABLE_FDB (priv->mdev, ft_field_support.outer_ipv4_ttl)) { @@ -1426,7 +1414,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_flow_spec *spec, struct tc_cls_flower_offload *f, struct net_device *filter_dev, - u8 *match_level) + u8 *match_level, u8 *tunnel_match_level) { struct netlink_ext_ack *extack = f->common.extack; void *headers_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, @@ -1437,12 +1425,14 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, misc_parameters); void *misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters); + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f); + struct flow_dissector *dissector = rule->match.dissector; u16 addr_type = 0; u8 ip_proto = 0; *match_level = MLX5_MATCH_NONE; - if (f->dissector->used_keys & + if (dissector->used_keys & ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | BIT(FLOW_DISSECTOR_KEY_BASIC) | BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | @@ -1461,23 +1451,21 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, BIT(FLOW_DISSECTOR_KEY_ENC_IP))) { NL_SET_ERR_MSG_MOD(extack, "Unsupported key"); netdev_warn(priv->netdev, "Unsupported key used: 0x%x\n", - f->dissector->used_keys); + dissector->used_keys); return -EOPNOTSUPP; } - if ((dissector_uses_key(f->dissector, - FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) || - dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID) || - dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_PORTS)) && - dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL)) { - struct flow_dissector_key_control *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_CONTROL, - f->key); - switch (key->addr_type) { + if ((flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) || + flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID) || + flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_PORTS)) && + flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_CONTROL)) { + struct flow_match_control match; + + flow_rule_match_enc_control(rule, &match); + switch (match.key->addr_type) { case FLOW_DISSECTOR_KEY_IPV4_ADDRS: case FLOW_DISSECTOR_KEY_IPV6_ADDRS: - if (parse_tunnel_attr(priv, spec, f, filter_dev)) + if (parse_tunnel_attr(priv, spec, f, filter_dev, tunnel_match_level)) return -EOPNOTSUPP; break; default: @@ -1493,35 +1481,27 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, inner_headers); } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) { - struct flow_dissector_key_basic *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_BASIC, - f->key); - struct flow_dissector_key_basic *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_BASIC, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_match_basic match; + + flow_rule_match_basic(rule, &match); MLX5_SET(fte_match_set_lyr_2_4, headers_c, ethertype, - ntohs(mask->n_proto)); + ntohs(match.mask->n_proto)); MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype, - ntohs(key->n_proto)); + ntohs(match.key->n_proto)); - if (mask->n_proto) + if (match.mask->n_proto) *match_level = MLX5_MATCH_L2; } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) { - struct flow_dissector_key_vlan *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_VLAN, - f->key); - struct flow_dissector_key_vlan *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_VLAN, - f->mask); - if (mask->vlan_id || mask->vlan_priority || mask->vlan_tpid) { - if (key->vlan_tpid == htons(ETH_P_8021AD)) { + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_match_vlan match; + + flow_rule_match_vlan(rule, &match); + if (match.mask->vlan_id || + match.mask->vlan_priority || + match.mask->vlan_tpid) { + if (match.key->vlan_tpid == htons(ETH_P_8021AD)) { MLX5_SET(fte_match_set_lyr_2_4, headers_c, svlan_tag, 1); MLX5_SET(fte_match_set_lyr_2_4, headers_v, @@ -1533,11 +1513,15 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, cvlan_tag, 1); } - MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_vid, mask->vlan_id); - MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_vid, key->vlan_id); + MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_vid, + match.mask->vlan_id); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_vid, + match.key->vlan_id); - MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_prio, mask->vlan_priority); - MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_prio, key->vlan_priority); + MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_prio, + match.mask->vlan_priority); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_prio, + match.key->vlan_priority); *match_level = MLX5_MATCH_L2; } @@ -1547,17 +1531,14 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, *match_level = MLX5_MATCH_L2; } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CVLAN)) { - struct flow_dissector_key_vlan *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_CVLAN, - f->key); - struct flow_dissector_key_vlan *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_CVLAN, - f->mask); - if (mask->vlan_id || mask->vlan_priority || mask->vlan_tpid) { - if (key->vlan_tpid == htons(ETH_P_8021AD)) { + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CVLAN)) { + struct flow_match_vlan match; + + flow_rule_match_vlan(rule, &match); + if (match.mask->vlan_id || + match.mask->vlan_priority || + match.mask->vlan_tpid) { + if (match.key->vlan_tpid == htons(ETH_P_8021AD)) { MLX5_SET(fte_match_set_misc, misc_c, outer_second_svlan_tag, 1); MLX5_SET(fte_match_set_misc, misc_v, @@ -1570,69 +1551,58 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, } MLX5_SET(fte_match_set_misc, misc_c, outer_second_vid, - mask->vlan_id); + match.mask->vlan_id); MLX5_SET(fte_match_set_misc, misc_v, outer_second_vid, - key->vlan_id); + match.key->vlan_id); MLX5_SET(fte_match_set_misc, misc_c, outer_second_prio, - mask->vlan_priority); + match.mask->vlan_priority); MLX5_SET(fte_match_set_misc, misc_v, outer_second_prio, - key->vlan_priority); + match.key->vlan_priority); *match_level = MLX5_MATCH_L2; } } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { - struct flow_dissector_key_eth_addrs *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ETH_ADDRS, - f->key); - struct flow_dissector_key_eth_addrs *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ETH_ADDRS, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { + struct flow_match_eth_addrs match; + flow_rule_match_eth_addrs(rule, &match); ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c, dmac_47_16), - mask->dst); + match.mask->dst); ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, dmac_47_16), - key->dst); + match.key->dst); ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c, smac_47_16), - mask->src); + match.mask->src); ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, smac_47_16), - key->src); + match.key->src); - if (!is_zero_ether_addr(mask->src) || !is_zero_ether_addr(mask->dst)) + if (!is_zero_ether_addr(match.mask->src) || + !is_zero_ether_addr(match.mask->dst)) *match_level = MLX5_MATCH_L2; } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) { - struct flow_dissector_key_control *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_CONTROL, - f->key); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) { + struct flow_match_control match; - struct flow_dissector_key_control *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_CONTROL, - f->mask); - addr_type = key->addr_type; + flow_rule_match_control(rule, &match); + addr_type = match.key->addr_type; /* the HW doesn't support frag first/later */ - if (mask->flags & FLOW_DIS_FIRST_FRAG) + if (match.mask->flags & FLOW_DIS_FIRST_FRAG) return -EOPNOTSUPP; - if (mask->flags & FLOW_DIS_IS_FRAGMENT) { + if (match.mask->flags & FLOW_DIS_IS_FRAGMENT) { MLX5_SET(fte_match_set_lyr_2_4, headers_c, frag, 1); MLX5_SET(fte_match_set_lyr_2_4, headers_v, frag, - key->flags & FLOW_DIS_IS_FRAGMENT); + match.key->flags & FLOW_DIS_IS_FRAGMENT); /* the HW doesn't need L3 inline to match on frag=no */ - if (!(key->flags & FLOW_DIS_IS_FRAGMENT)) + if (!(match.key->flags & FLOW_DIS_IS_FRAGMENT)) *match_level = MLX5_MATCH_L2; /* *** L2 attributes parsing up to here *** */ else @@ -1640,102 +1610,85 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, } } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) { - struct flow_dissector_key_basic *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_BASIC, - f->key); - struct flow_dissector_key_basic *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_BASIC, - f->mask); - ip_proto = key->ip_proto; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_match_basic match; + + flow_rule_match_basic(rule, &match); + ip_proto = match.key->ip_proto; MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_protocol, - mask->ip_proto); + match.mask->ip_proto); MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol, - key->ip_proto); + match.key->ip_proto); - if (mask->ip_proto) + if (match.mask->ip_proto) *match_level = MLX5_MATCH_L3; } if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { - struct flow_dissector_key_ipv4_addrs *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS, - f->key); - struct flow_dissector_key_ipv4_addrs *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS, - f->mask); + struct flow_match_ipv4_addrs match; + flow_rule_match_ipv4_addrs(rule, &match); memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c, src_ipv4_src_ipv6.ipv4_layout.ipv4), - &mask->src, sizeof(mask->src)); + &match.mask->src, sizeof(match.mask->src)); memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, src_ipv4_src_ipv6.ipv4_layout.ipv4), - &key->src, sizeof(key->src)); + &match.key->src, sizeof(match.key->src)); memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c, dst_ipv4_dst_ipv6.ipv4_layout.ipv4), - &mask->dst, sizeof(mask->dst)); + &match.mask->dst, sizeof(match.mask->dst)); memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, dst_ipv4_dst_ipv6.ipv4_layout.ipv4), - &key->dst, sizeof(key->dst)); + &match.key->dst, sizeof(match.key->dst)); - if (mask->src || mask->dst) + if (match.mask->src || match.mask->dst) *match_level = MLX5_MATCH_L3; } if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { - struct flow_dissector_key_ipv6_addrs *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS, - f->key); - struct flow_dissector_key_ipv6_addrs *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS, - f->mask); + struct flow_match_ipv6_addrs match; + flow_rule_match_ipv6_addrs(rule, &match); memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c, src_ipv4_src_ipv6.ipv6_layout.ipv6), - &mask->src, sizeof(mask->src)); + &match.mask->src, sizeof(match.mask->src)); memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, src_ipv4_src_ipv6.ipv6_layout.ipv6), - &key->src, sizeof(key->src)); + &match.key->src, sizeof(match.key->src)); memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_c, dst_ipv4_dst_ipv6.ipv6_layout.ipv6), - &mask->dst, sizeof(mask->dst)); + &match.mask->dst, sizeof(match.mask->dst)); memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, headers_v, dst_ipv4_dst_ipv6.ipv6_layout.ipv6), - &key->dst, sizeof(key->dst)); + &match.key->dst, sizeof(match.key->dst)); - if (ipv6_addr_type(&mask->src) != IPV6_ADDR_ANY || - ipv6_addr_type(&mask->dst) != IPV6_ADDR_ANY) + if (ipv6_addr_type(&match.mask->src) != IPV6_ADDR_ANY || + ipv6_addr_type(&match.mask->dst) != IPV6_ADDR_ANY) *match_level = MLX5_MATCH_L3; } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_IP)) { - struct flow_dissector_key_ip *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IP, - f->key); - struct flow_dissector_key_ip *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IP, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IP)) { + struct flow_match_ip match; - MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_ecn, mask->tos & 0x3); - MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_ecn, key->tos & 0x3); + flow_rule_match_ip(rule, &match); + MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_ecn, + match.mask->tos & 0x3); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_ecn, + match.key->tos & 0x3); - MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_dscp, mask->tos >> 2); - MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_dscp, key->tos >> 2); + MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_dscp, + match.mask->tos >> 2); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_dscp, + match.key->tos >> 2); - MLX5_SET(fte_match_set_lyr_2_4, headers_c, ttl_hoplimit, mask->ttl); - MLX5_SET(fte_match_set_lyr_2_4, headers_v, ttl_hoplimit, key->ttl); + MLX5_SET(fte_match_set_lyr_2_4, headers_c, ttl_hoplimit, + match.mask->ttl); + MLX5_SET(fte_match_set_lyr_2_4, headers_v, ttl_hoplimit, + match.key->ttl); - if (mask->ttl && + if (match.mask->ttl && !MLX5_CAP_ESW_FLOWTABLE_FDB(priv->mdev, ft_field_support.outer_ipv4_ttl)) { NL_SET_ERR_MSG_MOD(extack, @@ -1743,44 +1696,39 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, return -EOPNOTSUPP; } - if (mask->tos || mask->ttl) + if (match.mask->tos || match.mask->ttl) *match_level = MLX5_MATCH_L3; } /* *** L3 attributes parsing up to here *** */ - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) { - struct flow_dissector_key_ports *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_PORTS, - f->key); - struct flow_dissector_key_ports *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_PORTS, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) { + struct flow_match_ports match; + + flow_rule_match_ports(rule, &match); switch (ip_proto) { case IPPROTO_TCP: MLX5_SET(fte_match_set_lyr_2_4, headers_c, - tcp_sport, ntohs(mask->src)); + tcp_sport, ntohs(match.mask->src)); MLX5_SET(fte_match_set_lyr_2_4, headers_v, - tcp_sport, ntohs(key->src)); + tcp_sport, ntohs(match.key->src)); MLX5_SET(fte_match_set_lyr_2_4, headers_c, - tcp_dport, ntohs(mask->dst)); + tcp_dport, ntohs(match.mask->dst)); MLX5_SET(fte_match_set_lyr_2_4, headers_v, - tcp_dport, ntohs(key->dst)); + tcp_dport, ntohs(match.key->dst)); break; case IPPROTO_UDP: MLX5_SET(fte_match_set_lyr_2_4, headers_c, - udp_sport, ntohs(mask->src)); + udp_sport, ntohs(match.mask->src)); MLX5_SET(fte_match_set_lyr_2_4, headers_v, - udp_sport, ntohs(key->src)); + udp_sport, ntohs(match.key->src)); MLX5_SET(fte_match_set_lyr_2_4, headers_c, - udp_dport, ntohs(mask->dst)); + udp_dport, ntohs(match.mask->dst)); MLX5_SET(fte_match_set_lyr_2_4, headers_v, - udp_dport, ntohs(key->dst)); + udp_dport, ntohs(match.key->dst)); break; default: NL_SET_ERR_MSG_MOD(extack, @@ -1790,26 +1738,20 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, return -EINVAL; } - if (mask->src || mask->dst) + if (match.mask->src || match.mask->dst) *match_level = MLX5_MATCH_L4; } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_TCP)) { - struct flow_dissector_key_tcp *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_TCP, - f->key); - struct flow_dissector_key_tcp *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_TCP, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_TCP)) { + struct flow_match_tcp match; + flow_rule_match_tcp(rule, &match); MLX5_SET(fte_match_set_lyr_2_4, headers_c, tcp_flags, - ntohs(mask->flags)); + ntohs(match.mask->flags)); MLX5_SET(fte_match_set_lyr_2_4, headers_v, tcp_flags, - ntohs(key->flags)); + ntohs(match.key->flags)); - if (mask->flags) + if (match.mask->flags) *match_level = MLX5_MATCH_L4; } @@ -1826,15 +1768,15 @@ static int parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_core_dev *dev = priv->mdev; struct mlx5_eswitch *esw = dev->priv.eswitch; struct mlx5e_rep_priv *rpriv = priv->ppriv; + u8 match_level, tunnel_match_level = MLX5_MATCH_NONE; struct mlx5_eswitch_rep *rep; - u8 match_level; int err; - err = __parse_cls_flower(priv, spec, f, filter_dev, &match_level); + err = __parse_cls_flower(priv, spec, f, filter_dev, &match_level, &tunnel_match_level); if (!err && (flow->flags & MLX5E_TC_FLOW_ESWITCH)) { rep = rpriv->rep; - if (rep->vport != FDB_UPLINK_VPORT && + if (rep->vport != MLX5_VPORT_UPLINK && (esw->offloads.inline_mode != MLX5_INLINE_MODE_NONE && esw->offloads.inline_mode < match_level)) { NL_SET_ERR_MSG_MOD(extack, @@ -1846,10 +1788,12 @@ static int parse_cls_flower(struct mlx5e_priv *priv, } } - if (flow->flags & MLX5E_TC_FLOW_ESWITCH) + if (flow->flags & MLX5E_TC_FLOW_ESWITCH) { flow->esw_attr->match_level = match_level; - else + flow->esw_attr->tunnel_match_level = tunnel_match_level; + } else { flow->nic_attr->match_level = match_level; + } return err; } @@ -1862,27 +1806,32 @@ struct pedit_headers { struct udphdr udp; }; +struct pedit_headers_action { + struct pedit_headers vals; + struct pedit_headers masks; + u32 pedits; +}; + static int pedit_header_offsets[] = { - [TCA_PEDIT_KEY_EX_HDR_TYPE_ETH] = offsetof(struct pedit_headers, eth), - [TCA_PEDIT_KEY_EX_HDR_TYPE_IP4] = offsetof(struct pedit_headers, ip4), - [TCA_PEDIT_KEY_EX_HDR_TYPE_IP6] = offsetof(struct pedit_headers, ip6), - [TCA_PEDIT_KEY_EX_HDR_TYPE_TCP] = offsetof(struct pedit_headers, tcp), - [TCA_PEDIT_KEY_EX_HDR_TYPE_UDP] = offsetof(struct pedit_headers, udp), + [FLOW_ACT_MANGLE_HDR_TYPE_ETH] = offsetof(struct pedit_headers, eth), + [FLOW_ACT_MANGLE_HDR_TYPE_IP4] = offsetof(struct pedit_headers, ip4), + [FLOW_ACT_MANGLE_HDR_TYPE_IP6] = offsetof(struct pedit_headers, ip6), + [FLOW_ACT_MANGLE_HDR_TYPE_TCP] = offsetof(struct pedit_headers, tcp), + [FLOW_ACT_MANGLE_HDR_TYPE_UDP] = offsetof(struct pedit_headers, udp), }; #define pedit_header(_ph, _htype) ((void *)(_ph) + pedit_header_offsets[_htype]) static int set_pedit_val(u8 hdr_type, u32 mask, u32 val, u32 offset, - struct pedit_headers *masks, - struct pedit_headers *vals) + struct pedit_headers_action *hdrs) { u32 *curr_pmask, *curr_pval; - if (hdr_type >= __PEDIT_HDR_TYPE_MAX) + if (hdr_type >= 2) goto out_err; - curr_pmask = (u32 *)(pedit_header(masks, hdr_type) + offset); - curr_pval = (u32 *)(pedit_header(vals, hdr_type) + offset); + curr_pmask = (u32 *)(pedit_header(&hdrs->masks, hdr_type) + offset); + curr_pval = (u32 *)(pedit_header(&hdrs->vals, hdr_type) + offset); if (*curr_pmask & mask) /* disallow acting twice on the same location */ goto out_err; @@ -1934,12 +1883,11 @@ static struct mlx5_fields fields[] = { OFFLOAD(UDP_DPORT, 2, udp.dest, 0), }; -/* On input attr->num_mod_hdr_actions tells how many HW actions can be parsed at - * max from the SW pedit action. On success, it says how many HW actions were - * actually parsed. +/* On input attr->max_mod_hdr_actions tells how many HW actions can be parsed at + * max from the SW pedit action. On success, attr->num_mod_hdr_actions + * says how many HW actions were actually parsed. */ -static int offload_pedit_fields(struct pedit_headers *masks, - struct pedit_headers *vals, +static int offload_pedit_fields(struct pedit_headers_action *hdrs, struct mlx5e_tc_flow_parse_attr *parse_attr, struct netlink_ext_ack *extack) { @@ -1954,15 +1902,17 @@ static int offload_pedit_fields(struct pedit_headers *masks, __be16 mask_be16; void *action; - set_masks = &masks[TCA_PEDIT_KEY_EX_CMD_SET]; - add_masks = &masks[TCA_PEDIT_KEY_EX_CMD_ADD]; - set_vals = &vals[TCA_PEDIT_KEY_EX_CMD_SET]; - add_vals = &vals[TCA_PEDIT_KEY_EX_CMD_ADD]; + set_masks = &hdrs[0].masks; + add_masks = &hdrs[1].masks; + set_vals = &hdrs[0].vals; + add_vals = &hdrs[1].vals; action_size = MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto); - action = parse_attr->mod_hdr_actions; - max_actions = parse_attr->num_mod_hdr_actions; - nactions = 0; + action = parse_attr->mod_hdr_actions + + parse_attr->num_mod_hdr_actions * action_size; + + max_actions = parse_attr->max_mod_hdr_actions; + nactions = parse_attr->num_mod_hdr_actions; for (i = 0; i < ARRAY_SIZE(fields); i++) { f = &fields[i]; @@ -2053,12 +2003,14 @@ static int offload_pedit_fields(struct pedit_headers *masks, } static int alloc_mod_hdr_actions(struct mlx5e_priv *priv, - const struct tc_action *a, int namespace, + struct pedit_headers_action *hdrs, + int namespace, struct mlx5e_tc_flow_parse_attr *parse_attr) { int nkeys, action_size, max_actions; - nkeys = tcf_pedit_nkeys(a); + nkeys = hdrs[TCA_PEDIT_KEY_EX_CMD_SET].pedits + + hdrs[TCA_PEDIT_KEY_EX_CMD_ADD].pedits; action_size = MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto); if (namespace == MLX5_FLOW_NAMESPACE_FDB) /* FDB offloading */ @@ -2073,62 +2025,67 @@ static int alloc_mod_hdr_actions(struct mlx5e_priv *priv, if (!parse_attr->mod_hdr_actions) return -ENOMEM; - parse_attr->num_mod_hdr_actions = max_actions; + parse_attr->max_mod_hdr_actions = max_actions; return 0; } static const struct pedit_headers zero_masks = {}; static int parse_tc_pedit_action(struct mlx5e_priv *priv, - const struct tc_action *a, int namespace, + const struct flow_action_entry *act, int namespace, struct mlx5e_tc_flow_parse_attr *parse_attr, + struct pedit_headers_action *hdrs, struct netlink_ext_ack *extack) { - struct pedit_headers masks[__PEDIT_CMD_MAX], vals[__PEDIT_CMD_MAX], *cmd_masks; - int nkeys, i, err = -EOPNOTSUPP; + u8 cmd = (act->id == FLOW_ACTION_MANGLE) ? 0 : 1; + int err = -EOPNOTSUPP; u32 mask, val, offset; - u8 cmd, htype; + u8 htype; - nkeys = tcf_pedit_nkeys(a); + htype = act->mangle.htype; + err = -EOPNOTSUPP; /* can't be all optimistic */ - memset(masks, 0, sizeof(struct pedit_headers) * __PEDIT_CMD_MAX); - memset(vals, 0, sizeof(struct pedit_headers) * __PEDIT_CMD_MAX); + if (htype == FLOW_ACT_MANGLE_UNSPEC) { + NL_SET_ERR_MSG_MOD(extack, "legacy pedit isn't offloaded"); + goto out_err; + } - for (i = 0; i < nkeys; i++) { - htype = tcf_pedit_htype(a, i); - cmd = tcf_pedit_cmd(a, i); - err = -EOPNOTSUPP; /* can't be all optimistic */ + mask = act->mangle.mask; + val = act->mangle.val; + offset = act->mangle.offset; - if (htype == TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK) { - NL_SET_ERR_MSG_MOD(extack, - "legacy pedit isn't offloaded"); - goto out_err; - } + err = set_pedit_val(htype, ~mask, val, offset, &hdrs[cmd]); + if (err) + goto out_err; - if (cmd != TCA_PEDIT_KEY_EX_CMD_SET && cmd != TCA_PEDIT_KEY_EX_CMD_ADD) { - NL_SET_ERR_MSG_MOD(extack, "pedit cmd isn't offloaded"); - goto out_err; - } + hdrs[cmd].pedits++; - mask = tcf_pedit_mask(a, i); - val = tcf_pedit_val(a, i); - offset = tcf_pedit_offset(a, i); + return 0; +out_err: + return err; +} + +static int alloc_tc_pedit_action(struct mlx5e_priv *priv, int namespace, + struct mlx5e_tc_flow_parse_attr *parse_attr, + struct pedit_headers_action *hdrs, + struct netlink_ext_ack *extack) +{ + struct pedit_headers *cmd_masks; + int err; + u8 cmd; - err = set_pedit_val(htype, ~mask, val, offset, &masks[cmd], &vals[cmd]); + if (!parse_attr->mod_hdr_actions) { + err = alloc_mod_hdr_actions(priv, hdrs, namespace, parse_attr); if (err) goto out_err; } - err = alloc_mod_hdr_actions(priv, a, namespace, parse_attr); - if (err) - goto out_err; - - err = offload_pedit_fields(masks, vals, parse_attr, extack); + err = offload_pedit_fields(hdrs, parse_attr, extack); if (err < 0) goto out_dealloc_parsed_actions; for (cmd = 0; cmd < __PEDIT_CMD_MAX; cmd++) { - cmd_masks = &masks[cmd]; + cmd_masks = &hdrs[cmd].masks; if (memcmp(cmd_masks, &zero_masks, sizeof(zero_masks))) { NL_SET_ERR_MSG_MOD(extack, "attempt to offload an unsupported field"); @@ -2178,17 +2135,22 @@ static bool csum_offload_supported(struct mlx5e_priv *priv, } static bool modify_header_match_supported(struct mlx5_flow_spec *spec, - struct tcf_exts *exts, + struct flow_action *flow_action, + u32 actions, struct netlink_ext_ack *extack) { - const struct tc_action *a; + const struct flow_action_entry *act; bool modify_ip_header; u8 htype, ip_proto; void *headers_v; u16 ethertype; - int nkeys, i; + int i; + + if (actions & MLX5_FLOW_CONTEXT_ACTION_DECAP) + headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, inner_headers); + else + headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, outer_headers); - headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, outer_headers); ethertype = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ethertype); /* for non-IP we only re-write MACs, so we're okay */ @@ -2196,20 +2158,16 @@ static bool modify_header_match_supported(struct mlx5_flow_spec *spec, goto out_ok; modify_ip_header = false; - tcf_exts_for_each_action(i, a, exts) { - int k; - - if (!is_tcf_pedit(a)) + flow_action_for_each(i, act, flow_action) { + if (act->id != FLOW_ACTION_MANGLE && + act->id != FLOW_ACTION_ADD) continue; - nkeys = tcf_pedit_nkeys(a); - for (k = 0; k < nkeys; k++) { - htype = tcf_pedit_htype(a, k); - if (htype == TCA_PEDIT_KEY_EX_HDR_TYPE_IP4 || - htype == TCA_PEDIT_KEY_EX_HDR_TYPE_IP6) { - modify_ip_header = true; - break; - } + htype = act->mangle.htype; + if (htype == FLOW_ACT_MANGLE_HDR_TYPE_IP4 || + htype == FLOW_ACT_MANGLE_HDR_TYPE_IP6) { + modify_ip_header = true; + break; } } @@ -2227,7 +2185,7 @@ out_ok: } static bool actions_match_supported(struct mlx5e_priv *priv, - struct tcf_exts *exts, + struct flow_action *flow_action, struct mlx5e_tc_flow_parse_attr *parse_attr, struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack) @@ -2244,7 +2202,8 @@ static bool actions_match_supported(struct mlx5e_priv *priv, return false; if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) - return modify_header_match_supported(&parse_attr->spec, exts, + return modify_header_match_supported(&parse_attr->spec, + flow_action, actions, extack); return true; @@ -2264,52 +2223,50 @@ static bool same_hw_devs(struct mlx5e_priv *priv, struct mlx5e_priv *peer_priv) return (fsystem_guid == psystem_guid); } -static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, +static int parse_tc_nic_actions(struct mlx5e_priv *priv, + struct flow_action *flow_action, struct mlx5e_tc_flow_parse_attr *parse_attr, struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack) { struct mlx5_nic_flow_attr *attr = flow->nic_attr; - const struct tc_action *a; + struct pedit_headers_action hdrs[2] = {}; + const struct flow_action_entry *act; u32 action = 0; int err, i; - if (!tcf_exts_has_actions(exts)) + if (!flow_action_has_entries(flow_action)) return -EINVAL; attr->flow_tag = MLX5_FS_DEFAULT_FLOW_TAG; - tcf_exts_for_each_action(i, a, exts) { - if (is_tcf_gact_shot(a)) { + flow_action_for_each(i, act, flow_action) { + switch (act->id) { + case FLOW_ACTION_DROP: action |= MLX5_FLOW_CONTEXT_ACTION_DROP; if (MLX5_CAP_FLOWTABLE(priv->mdev, flow_table_properties_nic_receive.flow_counter)) action |= MLX5_FLOW_CONTEXT_ACTION_COUNT; - continue; - } - - if (is_tcf_pedit(a)) { - err = parse_tc_pedit_action(priv, a, MLX5_FLOW_NAMESPACE_KERNEL, - parse_attr, extack); + break; + case FLOW_ACTION_MANGLE: + case FLOW_ACTION_ADD: + err = parse_tc_pedit_action(priv, act, MLX5_FLOW_NAMESPACE_KERNEL, + parse_attr, hdrs, extack); if (err) return err; action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR | MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; - continue; - } - - if (is_tcf_csum(a)) { + break; + case FLOW_ACTION_CSUM: if (csum_offload_supported(priv, action, - tcf_csum_update_flags(a), + act->csum_flags, extack)) - continue; + break; return -EOPNOTSUPP; - } - - if (is_tcf_mirred_egress_redirect(a)) { - struct net_device *peer_dev = tcf_mirred_dev(a); + case FLOW_ACTION_REDIRECT: { + struct net_device *peer_dev = act->dev; if (priv->netdev->netdev_ops == peer_dev->netdev_ops && same_hw_devs(priv, netdev_priv(peer_dev))) { @@ -2324,11 +2281,10 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, peer_dev->name); return -EINVAL; } - continue; - } - - if (is_tcf_skbedit_mark(a)) { - u32 mark = tcf_skbedit_mark(a); + } + break; + case FLOW_ACTION_MARK: { + u32 mark = act->mark; if (mark & ~MLX5E_TC_FLOW_ID_MASK) { NL_SET_ERR_MSG_MOD(extack, @@ -2338,14 +2294,23 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, attr->flow_tag = mark; action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; - continue; + } + break; + default: + return -EINVAL; } + } - return -EINVAL; + if (hdrs[TCA_PEDIT_KEY_EX_CMD_SET].pedits || + hdrs[TCA_PEDIT_KEY_EX_CMD_ADD].pedits) { + err = alloc_tc_pedit_action(priv, MLX5_FLOW_NAMESPACE_KERNEL, + parse_attr, hdrs, extack); + if (err) + return err; } attr->action = action; - if (!actions_match_supported(priv, exts, parse_attr, flow, extack)) + if (!actions_match_supported(priv, flow_action, parse_attr, flow, extack)) return -EOPNOTSUPP; return 0; @@ -2450,7 +2415,7 @@ out_err: } static int parse_tc_vlan_action(struct mlx5e_priv *priv, - const struct tc_action *a, + const struct flow_action_entry *act, struct mlx5_esw_flow_attr *attr, u32 *action) { @@ -2459,7 +2424,8 @@ static int parse_tc_vlan_action(struct mlx5e_priv *priv, if (vlan_idx >= MLX5_FS_VLAN_DEPTH) return -EOPNOTSUPP; - if (tcf_vlan_action(a) == TCA_VLAN_ACT_POP) { + switch (act->id) { + case FLOW_ACTION_VLAN_POP: if (vlan_idx) { if (!mlx5_eswitch_vlan_actions_supported(priv->mdev, MLX5_FS_VLAN_DEPTH)) @@ -2469,10 +2435,11 @@ static int parse_tc_vlan_action(struct mlx5e_priv *priv, } else { *action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP; } - } else if (tcf_vlan_action(a) == TCA_VLAN_ACT_PUSH) { - attr->vlan_vid[vlan_idx] = tcf_vlan_push_vid(a); - attr->vlan_prio[vlan_idx] = tcf_vlan_push_prio(a); - attr->vlan_proto[vlan_idx] = tcf_vlan_push_proto(a); + break; + case FLOW_ACTION_VLAN_PUSH: + attr->vlan_vid[vlan_idx] = act->vlan.vid; + attr->vlan_prio[vlan_idx] = act->vlan.prio; + attr->vlan_proto[vlan_idx] = act->vlan.proto; if (!attr->vlan_proto[vlan_idx]) attr->vlan_proto[vlan_idx] = htons(ETH_P_8021Q); @@ -2484,13 +2451,15 @@ static int parse_tc_vlan_action(struct mlx5e_priv *priv, *action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2; } else { if (!mlx5_eswitch_vlan_actions_supported(priv->mdev, 1) && - (tcf_vlan_push_proto(a) != htons(ETH_P_8021Q) || - tcf_vlan_push_prio(a))) + (act->vlan.proto != htons(ETH_P_8021Q) || + act->vlan.prio)) return -EOPNOTSUPP; *action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH; } - } else { /* action is TCA_VLAN_ACT_MODIFY */ + break; + default: + /* action is FLOW_ACT_VLAN_MANGLE */ return -EOPNOTSUPP; } @@ -2499,58 +2468,56 @@ static int parse_tc_vlan_action(struct mlx5e_priv *priv, return 0; } -static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, +static int parse_tc_fdb_actions(struct mlx5e_priv *priv, + struct flow_action *flow_action, struct mlx5e_tc_flow_parse_attr *parse_attr, struct mlx5e_tc_flow *flow, struct netlink_ext_ack *extack) { + struct pedit_headers_action hdrs[2] = {}; struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5_esw_flow_attr *attr = flow->esw_attr; struct mlx5e_rep_priv *rpriv = priv->ppriv; - struct ip_tunnel_info *info = NULL; - const struct tc_action *a; + const struct ip_tunnel_info *info = NULL; + const struct flow_action_entry *act; bool encap = false; u32 action = 0; int err, i; - if (!tcf_exts_has_actions(exts)) + if (!flow_action_has_entries(flow_action)) return -EINVAL; attr->in_rep = rpriv->rep; attr->in_mdev = priv->mdev; - tcf_exts_for_each_action(i, a, exts) { - if (is_tcf_gact_shot(a)) { + flow_action_for_each(i, act, flow_action) { + switch (act->id) { + case FLOW_ACTION_DROP: action |= MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT; - continue; - } - - if (is_tcf_pedit(a)) { - err = parse_tc_pedit_action(priv, a, MLX5_FLOW_NAMESPACE_FDB, - parse_attr, extack); + break; + case FLOW_ACTION_MANGLE: + case FLOW_ACTION_ADD: + err = parse_tc_pedit_action(priv, act, MLX5_FLOW_NAMESPACE_FDB, + parse_attr, hdrs, extack); if (err) return err; action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; attr->split_count = attr->out_count; - continue; - } - - if (is_tcf_csum(a)) { + break; + case FLOW_ACTION_CSUM: if (csum_offload_supported(priv, action, - tcf_csum_update_flags(a), - extack)) - continue; + act->csum_flags, extack)) + break; return -EOPNOTSUPP; - } - - if (is_tcf_mirred_egress_redirect(a) || is_tcf_mirred_egress_mirror(a)) { + case FLOW_ACTION_REDIRECT: + case FLOW_ACTION_MIRRED: { struct mlx5e_priv *out_priv; struct net_device *out_dev; - out_dev = tcf_mirred_dev(a); + out_dev = act->dev; if (!out_dev) { /* out_dev is NULL when filters with * non-existing mirred device are replayed to @@ -2569,8 +2536,8 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_COUNT; - if (switchdev_port_same_parent_id(priv->netdev, - out_dev) || + if (netdev_port_same_parent_id(priv->netdev, + out_dev) || is_merged_eswitch_dev(priv, out_dev)) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct net_device *uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH); @@ -2615,35 +2582,29 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, priv->netdev->name, out_dev->name); return -EINVAL; } - continue; - } - - if (is_tcf_tunnel_set(a)) { - info = tcf_tunnel_info(a); + } + break; + case FLOW_ACTION_TUNNEL_ENCAP: + info = act->tunnel; if (info) encap = true; else return -EOPNOTSUPP; - continue; - } - - if (is_tcf_vlan(a)) { - err = parse_tc_vlan_action(priv, a, attr, &action); + break; + case FLOW_ACTION_VLAN_PUSH: + case FLOW_ACTION_VLAN_POP: + err = parse_tc_vlan_action(priv, act, attr, &action); if (err) return err; attr->split_count = attr->out_count; - continue; - } - - if (is_tcf_tunnel_release(a)) { + break; + case FLOW_ACTION_TUNNEL_DECAP: action |= MLX5_FLOW_CONTEXT_ACTION_DECAP; - continue; - } - - if (is_tcf_gact_goto_chain(a)) { - u32 dest_chain = tcf_gact_goto_chain_index(a); + break; + case FLOW_ACTION_GOTO: { + u32 dest_chain = act->chain_index; u32 max_chain = mlx5_eswitch_get_chain_range(esw); if (dest_chain <= attr->chain) { @@ -2656,15 +2617,23 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, } action |= MLX5_FLOW_CONTEXT_ACTION_COUNT; attr->dest_chain = dest_chain; - - continue; + break; + } + default: + return -EINVAL; } + } - return -EINVAL; + if (hdrs[TCA_PEDIT_KEY_EX_CMD_SET].pedits || + hdrs[TCA_PEDIT_KEY_EX_CMD_ADD].pedits) { + err = alloc_tc_pedit_action(priv, MLX5_FLOW_NAMESPACE_KERNEL, + parse_attr, hdrs, extack); + if (err) + return err; } attr->action = action; - if (!actions_match_supported(priv, exts, parse_attr, flow, extack)) + if (!actions_match_supported(priv, flow_action, parse_attr, flow, extack)) return -EOPNOTSUPP; if (attr->dest_chain) { @@ -2724,7 +2693,7 @@ static struct rhashtable *get_tc_ht(struct mlx5e_priv *priv, int flags) static bool is_peer_flow_needed(struct mlx5e_tc_flow *flow) { struct mlx5_esw_flow_attr *attr = flow->esw_attr; - bool is_rep_ingress = attr->in_rep->vport != FDB_UPLINK_VPORT && + bool is_rep_ingress = attr->in_rep->vport != MLX5_VPORT_UPLINK && flow->flags & MLX5E_TC_FLOW_INGRESS; bool act_is_encap = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT); @@ -2775,6 +2744,7 @@ __mlx5e_add_fdb_flow(struct mlx5e_priv *priv, struct mlx5_eswitch_rep *in_rep, struct mlx5_core_dev *in_mdev) { + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f); struct netlink_ext_ack *extack = f->common.extack; struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5e_tc_flow_parse_attr *parse_attr; @@ -2796,7 +2766,7 @@ __mlx5e_add_fdb_flow(struct mlx5e_priv *priv, flow->esw_attr->chain = f->common.chain_index; flow->esw_attr->prio = TC_H_MAJ(f->common.prio) >> 16; - err = parse_tc_fdb_actions(priv, f->exts, parse_attr, flow, extack); + err = parse_tc_fdb_actions(priv, &rule->action, parse_attr, flow, extack); if (err) goto err_free; @@ -2846,7 +2816,7 @@ static int mlx5e_tc_add_fdb_peer_flow(struct tc_cls_flower_offload *f, * original flow and packets redirected from uplink use the * peer mdev. */ - if (flow->esw_attr->in_rep->vport == FDB_UPLINK_VPORT) + if (flow->esw_attr->in_rep->vport == MLX5_VPORT_UPLINK) in_mdev = peer_priv->mdev; else in_mdev = priv->mdev; @@ -2912,6 +2882,7 @@ mlx5e_add_nic_flow(struct mlx5e_priv *priv, struct net_device *filter_dev, struct mlx5e_tc_flow **__flow) { + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f); struct netlink_ext_ack *extack = f->common.extack; struct mlx5e_tc_flow_parse_attr *parse_attr; struct mlx5e_tc_flow *flow; @@ -2934,7 +2905,7 @@ mlx5e_add_nic_flow(struct mlx5e_priv *priv, if (err) goto err_free; - err = parse_tc_nic_actions(priv, f->exts, parse_attr, flow, extack); + err = parse_tc_nic_actions(priv, &rule->action, parse_attr, flow, extack); if (err) goto err_free; @@ -3092,7 +3063,7 @@ int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv, mlx5_devcom_release_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS); out: - tcf_exts_stats_update(f->exts, bytes, packets, lastuse); + flow_stats_update(&f->stats, bytes, packets, lastuse); return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 598ad7e4d5c9..c1334a8ac8f3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -387,8 +387,14 @@ netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, num_wqebbs = DIV_ROUND_UP(ds_cnt, MLX5_SEND_WQEBB_NUM_DS); contig_wqebbs_room = mlx5_wq_cyc_get_contig_wqebbs(wq, pi); if (unlikely(contig_wqebbs_room < num_wqebbs)) { +#ifdef CONFIG_MLX5_EN_IPSEC + struct mlx5_wqe_eth_seg cur_eth = wqe->eth; +#endif mlx5e_fill_sq_frag_edge(sq, wq, pi, contig_wqebbs_room); mlx5e_sq_fetch_wqe(sq, &wqe, &pi); +#ifdef CONFIG_MLX5_EN_IPSEC + wqe->eth = cur_eth; +#endif } /* fill wqe */ @@ -513,8 +519,9 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget) &sq->state)) { mlx5e_dump_error_cqe(sq, (struct mlx5_err_cqe *)cqe); - queue_work(cq->channel->priv->wq, - &sq->recover.recover_work); + if (!IS_ERR_OR_NULL(cq->channel->priv->tx_reporter)) + queue_work(cq->channel->priv->wq, + &sq->recover_work); } stats->cqe_err++; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index ee04aab65a9f..bb6e5b5d9681 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -34,6 +34,7 @@ #include <linux/notifier.h> #include <linux/module.h> #include <linux/mlx5/driver.h> +#include <linux/mlx5/vport.h> #include <linux/mlx5/eq.h> #include <linux/mlx5/cmd.h> #ifdef CONFIG_RFS_ACCEL @@ -114,11 +115,11 @@ static struct mlx5_core_cq *mlx5_eq_cq_get(struct mlx5_eq *eq, u32 cqn) struct mlx5_cq_table *table = &eq->cq_table; struct mlx5_core_cq *cq = NULL; - spin_lock(&table->lock); + rcu_read_lock(); cq = radix_tree_lookup(&table->tree, cqn); if (likely(cq)) mlx5_cq_hold(cq); - spin_unlock(&table->lock); + rcu_read_unlock(); return cq; } @@ -371,9 +372,9 @@ int mlx5_eq_add_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq) struct mlx5_cq_table *table = &eq->cq_table; int err; - spin_lock_irq(&table->lock); + spin_lock(&table->lock); err = radix_tree_insert(&table->tree, cq->cqn, cq); - spin_unlock_irq(&table->lock); + spin_unlock(&table->lock); return err; } @@ -383,9 +384,9 @@ int mlx5_eq_del_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq) struct mlx5_cq_table *table = &eq->cq_table; struct mlx5_core_cq *tmp; - spin_lock_irq(&table->lock); + spin_lock(&table->lock); tmp = radix_tree_delete(&table->tree, cq->cqn); - spin_unlock_irq(&table->lock); + spin_unlock(&table->lock); if (!tmp) { mlx5_core_warn(eq->dev, "cq 0x%x not found in eq 0x%x tree\n", eq->eqn, cq->cqn); @@ -530,6 +531,9 @@ static u64 gather_async_events_mask(struct mlx5_core_dev *dev) if (MLX5_CAP_GEN(dev, max_num_of_monitor_counters)) async_event_mask |= (1ull << MLX5_EVENT_TYPE_MONITOR_COUNTER); + if (mlx5_core_is_ecpf_esw_manager(dev)) + async_event_mask |= (1ull << MLX5_EVENT_TYPE_HOST_PARAMS_CHANGE); + return async_event_mask; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index a44ea7b85614..e18af31336e6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -39,8 +39,7 @@ #include "lib/eq.h" #include "eswitch.h" #include "fs_core.h" - -#define UPLINK_VPORT 0xFFFF +#include "ecpf.h" enum { MLX5_ACTION_NONE = 0, @@ -52,7 +51,7 @@ enum { struct vport_addr { struct l2addr_node node; u8 action; - u32 vport; + u16 vport; struct mlx5_flow_handle *flow_rule; bool mpfs; /* UC MAC was added to MPFs */ /* A flag indicating that mac was added due to mc promiscuous vport */ @@ -70,6 +69,28 @@ enum { MC_ADDR_CHANGE | \ PROMISC_CHANGE) +/* The vport getter/iterator are only valid after esw->total_vports + * and vport->vport are initialized in mlx5_eswitch_init. + */ +#define mlx5_esw_for_all_vports(esw, i, vport) \ + for ((i) = MLX5_VPORT_PF; \ + (vport) = &(esw)->vports[i], \ + (i) < (esw)->total_vports; (i)++) + +#define mlx5_esw_for_each_vf_vport(esw, i, vport, nvfs) \ + for ((i) = MLX5_VPORT_FIRST_VF; \ + (vport) = &(esw)->vports[i], \ + (i) <= (nvfs); (i)++) + +static struct mlx5_vport *mlx5_eswitch_get_vport(struct mlx5_eswitch *esw, + u16 vport_num) +{ + u16 idx = mlx5_eswitch_vport_num_to_index(esw, vport_num); + + WARN_ON(vport_num > esw->total_vports - 1); + return &esw->vports[idx]; +} + static int arm_vport_context_events_cmd(struct mlx5_core_dev *dev, u16 vport, u32 events_mask) { @@ -115,7 +136,7 @@ static int modify_esw_vport_context_cmd(struct mlx5_core_dev *dev, u16 vport, return mlx5_cmd_exec(dev, in, inlen, out, sizeof(out)); } -static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u32 vport, +static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u16 vport, u16 vlan, u8 qos, u8 set_flags) { u32 in[MLX5_ST_SZ_DW(modify_esw_vport_context_in)] = {0}; @@ -152,7 +173,7 @@ static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u32 vport, /* E-Switch FDB */ static struct mlx5_flow_handle * -__esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule, +__esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u16 vport, bool rx_rule, u8 mac_c[ETH_ALEN], u8 mac_v[ETH_ALEN]) { int match_header = (is_zero_ether_addr(mac_c) ? 0 : @@ -188,7 +209,7 @@ __esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule, misc_parameters); mc_misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters); - MLX5_SET(fte_match_set_misc, mv_misc, source_port, UPLINK_VPORT); + MLX5_SET(fte_match_set_misc, mv_misc, source_port, MLX5_VPORT_UPLINK); MLX5_SET_TO_ONES(fte_match_set_misc, mc_misc, source_port); } @@ -215,7 +236,7 @@ __esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u32 vport, bool rx_rule, } static struct mlx5_flow_handle * -esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u8 mac[ETH_ALEN], u32 vport) +esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u8 mac[ETH_ALEN], u16 vport) { u8 mac_c[ETH_ALEN]; @@ -224,7 +245,7 @@ esw_fdb_set_vport_rule(struct mlx5_eswitch *esw, u8 mac[ETH_ALEN], u32 vport) } static struct mlx5_flow_handle * -esw_fdb_set_vport_allmulti_rule(struct mlx5_eswitch *esw, u32 vport) +esw_fdb_set_vport_allmulti_rule(struct mlx5_eswitch *esw, u16 vport) { u8 mac_c[ETH_ALEN]; u8 mac_v[ETH_ALEN]; @@ -237,7 +258,7 @@ esw_fdb_set_vport_allmulti_rule(struct mlx5_eswitch *esw, u32 vport) } static struct mlx5_flow_handle * -esw_fdb_set_vport_promisc_rule(struct mlx5_eswitch *esw, u32 vport) +esw_fdb_set_vport_promisc_rule(struct mlx5_eswitch *esw, u16 vport) { u8 mac_c[ETH_ALEN]; u8 mac_v[ETH_ALEN]; @@ -377,19 +398,19 @@ typedef int (*vport_addr_action)(struct mlx5_eswitch *esw, static int esw_add_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) { u8 *mac = vaddr->node.addr; - u32 vport = vaddr->vport; + u16 vport = vaddr->vport; int err; - /* Skip mlx5_mpfs_add_mac for PFs, - * it is already done by the PF netdev in mlx5e_execute_l2_action + /* Skip mlx5_mpfs_add_mac for eswitch_managers, + * it is already done by its netdev in mlx5e_execute_l2_action */ - if (!vport) + if (esw->manager_vport == vport) goto fdb_add; err = mlx5_mpfs_add_mac(esw->dev, mac); if (err) { esw_warn(esw->dev, - "Failed to add L2 table mac(%pM) for vport(%d), err(%d)\n", + "Failed to add L2 table mac(%pM) for vport(0x%x), err(%d)\n", mac, vport, err); return err; } @@ -409,13 +430,13 @@ fdb_add: static int esw_del_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) { u8 *mac = vaddr->node.addr; - u32 vport = vaddr->vport; + u16 vport = vaddr->vport; int err = 0; - /* Skip mlx5_mpfs_del_mac for PFs, - * it is already done by the PF netdev in mlx5e_execute_l2_action + /* Skip mlx5_mpfs_del_mac for eswitch managerss, + * it is already done by its netdev in mlx5e_execute_l2_action */ - if (!vport || !vaddr->mpfs) + if (!vaddr->mpfs || esw->manager_vport == vport) goto fdb_del; err = mlx5_mpfs_del_mac(esw->dev, mac); @@ -438,17 +459,18 @@ static void update_allmulti_vports(struct mlx5_eswitch *esw, struct esw_mc_addr *esw_mc) { u8 *mac = vaddr->node.addr; - u32 vport_idx = 0; + struct mlx5_vport *vport; + u16 i, vport_num; - for (vport_idx = 0; vport_idx < esw->total_vports; vport_idx++) { - struct mlx5_vport *vport = &esw->vports[vport_idx]; + mlx5_esw_for_all_vports(esw, i, vport) { struct hlist_head *vport_hash = vport->mc_list; struct vport_addr *iter_vaddr = l2addr_hash_find(vport_hash, mac, struct vport_addr); + vport_num = vport->vport; if (IS_ERR_OR_NULL(vport->allmulti_rule) || - vaddr->vport == vport_idx) + vaddr->vport == vport_num) continue; switch (vaddr->action) { case MLX5_ACTION_ADD: @@ -460,14 +482,14 @@ static void update_allmulti_vports(struct mlx5_eswitch *esw, if (!iter_vaddr) { esw_warn(esw->dev, "ALL-MULTI: Failed to add MAC(%pM) to vport[%d] DB\n", - mac, vport_idx); + mac, vport_num); continue; } - iter_vaddr->vport = vport_idx; + iter_vaddr->vport = vport_num; iter_vaddr->flow_rule = esw_fdb_set_vport_rule(esw, mac, - vport_idx); + vport_num); iter_vaddr->mc_promisc = true; break; case MLX5_ACTION_DEL: @@ -485,7 +507,7 @@ static int esw_add_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) struct hlist_head *hash = esw->mc_table; struct esw_mc_addr *esw_mc; u8 *mac = vaddr->node.addr; - u32 vport = vaddr->vport; + u16 vport = vaddr->vport; if (!esw->fdb_table.legacy.fdb) return 0; @@ -499,7 +521,7 @@ static int esw_add_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) return -ENOMEM; esw_mc->uplink_rule = /* Forward MC MAC to Uplink */ - esw_fdb_set_vport_rule(esw, mac, UPLINK_VPORT); + esw_fdb_set_vport_rule(esw, mac, MLX5_VPORT_UPLINK); /* Add this multicast mac to all the mc promiscuous vports */ update_allmulti_vports(esw, vaddr, esw_mc); @@ -525,7 +547,7 @@ static int esw_del_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) struct hlist_head *hash = esw->mc_table; struct esw_mc_addr *esw_mc; u8 *mac = vaddr->node.addr; - u32 vport = vaddr->vport; + u16 vport = vaddr->vport; if (!esw->fdb_table.legacy.fdb) return 0; @@ -564,9 +586,9 @@ static int esw_del_mc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr) /* Apply vport UC/MC list to HW l2 table and FDB table */ static void esw_apply_vport_addr_list(struct mlx5_eswitch *esw, - u32 vport_num, int list_type) + u16 vport_num, int list_type) { - struct mlx5_vport *vport = &esw->vports[vport_num]; + struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num); bool is_uc = list_type == MLX5_NVPRT_LIST_TYPE_UC; vport_addr_action vport_addr_add; vport_addr_action vport_addr_del; @@ -599,9 +621,9 @@ static void esw_apply_vport_addr_list(struct mlx5_eswitch *esw, /* Sync vport UC/MC list from vport context */ static void esw_update_vport_addr_list(struct mlx5_eswitch *esw, - u32 vport_num, int list_type) + u16 vport_num, int list_type) { - struct mlx5_vport *vport = &esw->vports[vport_num]; + struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num); bool is_uc = list_type == MLX5_NVPRT_LIST_TYPE_UC; u8 (*mac_list)[ETH_ALEN]; struct l2addr_node *node; @@ -686,9 +708,9 @@ out: /* Sync vport UC/MC list from vport context * Must be called after esw_update_vport_addr_list */ -static void esw_update_vport_mc_promisc(struct mlx5_eswitch *esw, u32 vport_num) +static void esw_update_vport_mc_promisc(struct mlx5_eswitch *esw, u16 vport_num) { - struct mlx5_vport *vport = &esw->vports[vport_num]; + struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num); struct l2addr_node *node; struct vport_addr *addr; struct hlist_head *hash; @@ -721,11 +743,11 @@ static void esw_update_vport_mc_promisc(struct mlx5_eswitch *esw, u32 vport_num) } /* Apply vport rx mode to HW FDB table */ -static void esw_apply_vport_rx_mode(struct mlx5_eswitch *esw, u32 vport_num, +static void esw_apply_vport_rx_mode(struct mlx5_eswitch *esw, u16 vport_num, bool promisc, bool mc_promisc) { + struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num); struct esw_mc_addr *allmulti_addr = &esw->mc_promisc; - struct mlx5_vport *vport = &esw->vports[vport_num]; if (IS_ERR_OR_NULL(vport->allmulti_rule) != mc_promisc) goto promisc; @@ -736,7 +758,7 @@ static void esw_apply_vport_rx_mode(struct mlx5_eswitch *esw, u32 vport_num, if (!allmulti_addr->uplink_rule) allmulti_addr->uplink_rule = esw_fdb_set_vport_allmulti_rule(esw, - UPLINK_VPORT); + MLX5_VPORT_UPLINK); allmulti_addr->refcnt++; } else if (vport->allmulti_rule) { mlx5_del_flow_rules(vport->allmulti_rule); @@ -764,9 +786,9 @@ promisc: } /* Sync vport rx mode from vport context */ -static void esw_update_vport_rx_mode(struct mlx5_eswitch *esw, u32 vport_num) +static void esw_update_vport_rx_mode(struct mlx5_eswitch *esw, u16 vport_num) { - struct mlx5_vport *vport = &esw->vports[vport_num]; + struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num); int promisc_all = 0; int promisc_uc = 0; int promisc_mc = 0; @@ -1134,13 +1156,6 @@ static int esw_vport_ingress_config(struct mlx5_eswitch *esw, int err = 0; u8 *smac_v; - if (vport->info.spoofchk && !is_valid_ether_addr(vport->info.mac)) { - mlx5_core_warn(esw->dev, - "vport[%d] configure ingress rules failed, illegal mac with spoofchk\n", - vport->vport); - return -EPERM; - } - esw_vport_cleanup_ingress_rules(esw, vport); if (!vport->info.vlan && !vport->info.qos && !vport->info.spoofchk) { @@ -1350,8 +1365,8 @@ static void esw_destroy_tsar(struct mlx5_eswitch *esw) static int esw_vport_enable_qos(struct mlx5_eswitch *esw, int vport_num, u32 initial_max_rate, u32 initial_bw_share) { + struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num); u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0}; - struct mlx5_vport *vport = &esw->vports[vport_num]; struct mlx5_core_dev *dev = esw->dev; void *vport_elem; int err = 0; @@ -1390,7 +1405,7 @@ static int esw_vport_enable_qos(struct mlx5_eswitch *esw, int vport_num, static void esw_vport_disable_qos(struct mlx5_eswitch *esw, int vport_num) { - struct mlx5_vport *vport = &esw->vports[vport_num]; + struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num); int err = 0; if (!vport->qos.enabled) @@ -1409,8 +1424,8 @@ static void esw_vport_disable_qos(struct mlx5_eswitch *esw, int vport_num) static int esw_vport_qos_config(struct mlx5_eswitch *esw, int vport_num, u32 max_rate, u32 bw_share) { + struct mlx5_vport *vport = mlx5_eswitch_get_vport(esw, vport_num); u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0}; - struct mlx5_vport *vport = &esw->vports[vport_num]; struct mlx5_core_dev *dev = esw->dev; void *vport_elem; u32 bitmask = 0; @@ -1466,15 +1481,22 @@ static void esw_apply_vport_conf(struct mlx5_eswitch *esw, { int vport_num = vport->vport; - if (!vport_num) + if (esw->manager_vport == vport_num) return; mlx5_modify_vport_admin_state(esw->dev, MLX5_VPORT_STATE_OP_MOD_ESW_VPORT, - vport_num, + vport_num, 1, vport->info.link_state); - mlx5_modify_nic_vport_mac_address(esw->dev, vport_num, vport->info.mac); - mlx5_modify_nic_vport_node_guid(esw->dev, vport_num, vport->info.node_guid); + + /* Host PF has its own mac/guid. */ + if (vport_num) { + mlx5_modify_nic_vport_mac_address(esw->dev, vport_num, + vport->info.mac); + mlx5_modify_nic_vport_node_guid(esw->dev, vport_num, + vport->info.node_guid); + } + modify_esw_vport_cvlan(esw->dev, vport_num, vport->info.vlan, vport->info.qos, (vport->info.vlan || vport->info.qos)); @@ -1520,10 +1542,10 @@ static void esw_vport_destroy_drop_counters(struct mlx5_vport *vport) mlx5_fc_destroy(dev, vport->egress.drop_counter); } -static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num, +static void esw_enable_vport(struct mlx5_eswitch *esw, struct mlx5_vport *vport, int enable_events) { - struct mlx5_vport *vport = &esw->vports[vport_num]; + u16 vport_num = vport->vport; mutex_lock(&esw->state_lock); WARN_ON(vport->enabled); @@ -1546,8 +1568,11 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num, vport->enabled_events = enable_events; vport->enabled = true; - /* only PF is trusted by default */ - if (!vport_num) + /* Esw manager is trusted by default. Host PF (vport 0) is trusted as well + * in smartNIC as it's a vport group manager. + */ + if (esw->manager_vport == vport_num || + (!vport_num && mlx5_core_is_ecpf(esw->dev))) vport->info.trusted = true; esw_vport_change_handle_locked(vport); @@ -1557,9 +1582,10 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, int vport_num, mutex_unlock(&esw->state_lock); } -static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num) +static void esw_disable_vport(struct mlx5_eswitch *esw, + struct mlx5_vport *vport) { - struct mlx5_vport *vport = &esw->vports[vport_num]; + u16 vport_num = vport->vport; if (!vport->enabled) return; @@ -1580,10 +1606,10 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num) esw_vport_change_handle_locked(vport); vport->enabled_events = 0; esw_vport_disable_qos(esw, vport_num); - if (vport_num && esw->mode == SRIOV_LEGACY) { + if (esw->mode == SRIOV_LEGACY) { mlx5_modify_vport_admin_state(esw->dev, MLX5_VPORT_STATE_OP_MOD_ESW_VPORT, - vport_num, + vport_num, 1, MLX5_VPORT_ADMIN_STATE_DOWN); esw_vport_disable_egress_acl(esw, vport); esw_vport_disable_ingress_acl(esw, vport); @@ -1602,7 +1628,7 @@ static int eswitch_vport_event(struct notifier_block *nb, u16 vport_num; vport_num = be16_to_cpu(eqe->data.vport_change.vport_num); - vport = &esw->vports[vport_num]; + vport = mlx5_eswitch_get_vport(esw, vport_num); if (vport->enabled) queue_work(esw->work_queue, &vport->vport_change_handler); @@ -1614,6 +1640,8 @@ static int eswitch_vport_event(struct notifier_block *nb, int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) { + int vf_nvports = 0, total_nvports = 0; + struct mlx5_vport *vport; int err; int i, enabled_events; @@ -1631,6 +1659,18 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) esw_info(esw->dev, "E-Switch enable SRIOV: nvfs(%d) mode (%d)\n", nvfs, mode); + if (mode == SRIOV_OFFLOADS) { + if (mlx5_core_is_ecpf_esw_manager(esw->dev)) { + err = mlx5_query_host_params_num_vfs(esw->dev, &vf_nvports); + if (err) + return err; + total_nvports = esw->total_vports; + } else { + vf_nvports = nvfs; + total_nvports = nvfs + MLX5_SPECIAL_VPORTS(esw->dev); + } + } + esw->mode = mode; mlx5_lag_update(esw->dev); @@ -1640,7 +1680,7 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) } else { mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH); mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB); - err = esw_offloads_init(esw, nvfs + 1); + err = esw_offloads_init(esw, vf_nvports, total_nvports); } if (err) @@ -1655,8 +1695,20 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) * 2. FDB/Eswitch is programmed by user space tools */ enabled_events = (mode == SRIOV_LEGACY) ? SRIOV_VPORT_EVENTS : 0; - for (i = 0; i <= nvfs; i++) - esw_enable_vport(esw, i, enabled_events); + + /* Enable PF vport */ + vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF); + esw_enable_vport(esw, vport, enabled_events); + + /* Enable ECPF vports */ + if (mlx5_ecpf_vport_exists(esw->dev)) { + vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF); + esw_enable_vport(esw, vport, enabled_events); + } + + /* Enable VF vports */ + mlx5_esw_for_each_vf_vport(esw, i, vport, nvfs) + esw_enable_vport(esw, vport, enabled_events); if (mode == SRIOV_LEGACY) { MLX5_NB_INIT(&esw->nb, eswitch_vport_event, NIC_VPORT_CHANGE); @@ -1681,8 +1733,8 @@ abort: void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw) { struct esw_mc_addr *mc_promisc; + struct mlx5_vport *vport; int old_mode; - int nvports; int i; if (!ESW_ALLOWED(esw) || esw->mode == SRIOV_NONE) @@ -1692,13 +1744,12 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw) esw->enabled_vports, esw->mode); mc_promisc = &esw->mc_promisc; - nvports = esw->enabled_vports; if (esw->mode == SRIOV_LEGACY) mlx5_eq_notifier_unregister(esw->dev, &esw->nb); - for (i = 0; i < esw->total_vports; i++) - esw_disable_vport(esw, i); + mlx5_esw_for_all_vports(esw, i, vport) + esw_disable_vport(esw, vport); if (mc_promisc && mc_promisc->uplink_rule) mlx5_del_flow_rules(mc_promisc->uplink_rule); @@ -1708,7 +1759,7 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw) if (esw->mode == SRIOV_LEGACY) esw_destroy_legacy_fdb_table(esw); else if (esw->mode == SRIOV_OFFLOADS) - esw_offloads_cleanup(esw, nvports); + esw_offloads_cleanup(esw); old_mode = esw->mode; esw->mode = SRIOV_NONE; @@ -1725,10 +1776,10 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) { int total_vports = MLX5_TOTAL_VPORTS(dev); struct mlx5_eswitch *esw; - int vport_num; - int err; + struct mlx5_vport *vport; + int err, i; - if (!MLX5_ESWITCH_MANAGER(dev)) + if (!MLX5_VPORT_MANAGER(dev)) return 0; esw_info(dev, @@ -1742,6 +1793,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) return -ENOMEM; esw->dev = dev; + esw->manager_vport = mlx5_eswitch_manager_vport(dev); esw->work_queue = create_singlethread_workqueue("mlx5_esw_wq"); if (!esw->work_queue) { @@ -1756,6 +1808,8 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) goto abort; } + esw->total_vports = total_vports; + err = esw_offloads_init_reps(esw); if (err) goto abort; @@ -1764,17 +1818,14 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) hash_init(esw->offloads.mod_hdr_tbl); mutex_init(&esw->state_lock); - for (vport_num = 0; vport_num < total_vports; vport_num++) { - struct mlx5_vport *vport = &esw->vports[vport_num]; - - vport->vport = vport_num; + mlx5_esw_for_all_vports(esw, i, vport) { + vport->vport = mlx5_eswitch_index_to_vport_num(esw, i); vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO; vport->dev = dev; INIT_WORK(&vport->vport_change_handler, esw_vport_change_handler); } - esw->total_vports = total_vports; esw->enabled_vports = 0; esw->mode = SRIOV_NONE; esw->offloads.inline_mode = MLX5_INLINE_MODE_NONE; @@ -1797,7 +1848,7 @@ abort: void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) { - if (!esw || !MLX5_ESWITCH_MANAGER(esw->dev)) + if (!esw || !MLX5_VPORT_MANAGER(esw->dev)) return; esw_info(esw->dev, "cleanup\n"); @@ -1827,13 +1878,10 @@ int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw, mutex_lock(&esw->state_lock); evport = &esw->vports[vport]; - if (evport->info.spoofchk && !is_valid_ether_addr(mac)) { + if (evport->info.spoofchk && !is_valid_ether_addr(mac)) mlx5_core_warn(esw->dev, - "MAC invalidation is not allowed when spoofchk is on, vport(%d)\n", + "Set invalid MAC while spoofchk is on, vport(%d)\n", vport); - err = -EPERM; - goto unlock; - } err = mlx5_modify_nic_vport_mac_address(esw->dev, vport, mac); if (err) { @@ -1876,7 +1924,7 @@ int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw, err = mlx5_modify_vport_admin_state(esw->dev, MLX5_VPORT_STATE_OP_MOD_ESW_VPORT, - vport, link_state); + vport, 1, link_state); if (err) { mlx5_core_warn(esw->dev, "Failed to set vport %d link state, err = %d", @@ -1979,6 +2027,10 @@ int mlx5_eswitch_set_vport_spoofchk(struct mlx5_eswitch *esw, evport = &esw->vports[vport]; pschk = evport->info.spoofchk; evport->info.spoofchk = spoofchk; + if (pschk && !is_valid_ether_addr(evport->info.mac)) + mlx5_core_warn(esw->dev, + "Spoofchk in set while MAC is invalid, vport(%d)\n", + evport->vport); if (evport->enabled && esw->mode == SRIOV_LEGACY) err = esw_vport_ingress_config(esw, evport); if (err) @@ -2015,8 +2067,7 @@ static u32 calculate_vports_min_rate_divider(struct mlx5_eswitch *esw) u32 max_guarantee = 0; int i; - for (i = 0; i < esw->total_vports; i++) { - evport = &esw->vports[i]; + mlx5_esw_for_all_vports(esw, i, evport) { if (!evport->enabled || evport->info.min_rate < max_guarantee) continue; max_guarantee = evport->info.min_rate; @@ -2035,8 +2086,7 @@ static int normalize_vports_min_rate(struct mlx5_eswitch *esw, u32 divider) int err; int i; - for (i = 0; i < esw->total_vports; i++) { - evport = &esw->vports[i]; + mlx5_esw_for_all_vports(esw, i, evport) { if (!evport->enabled) continue; vport_min_rate = evport->info.min_rate; @@ -2051,7 +2101,7 @@ static int normalize_vports_min_rate(struct mlx5_eswitch *esw, u32 divider) if (bw_share == evport->qos.bw_share) continue; - err = esw_vport_qos_config(esw, i, vport_max_rate, + err = esw_vport_qos_config(esw, evport->vport, vport_max_rate, bw_share); if (!err) evport->qos.bw_share = bw_share; @@ -2134,7 +2184,7 @@ static int mlx5_eswitch_query_vport_drop_stats(struct mlx5_core_dev *dev, !MLX5_CAP_GEN(dev, transmit_discard_vport_down)) return 0; - err = mlx5_query_vport_down_stats(dev, vport_idx, + err = mlx5_query_vport_down_stats(dev, vport_idx, 1, &rx_discard_vport_down, &tx_discard_vport_down); if (err) @@ -2171,8 +2221,7 @@ int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw, MLX5_CMD_OP_QUERY_VPORT_COUNTER); MLX5_SET(query_vport_counter_in, in, op_mod, 0); MLX5_SET(query_vport_counter_in, in, vport_number, vport); - if (vport) - MLX5_SET(query_vport_counter_in, in, other_vport, 1); + MLX5_SET(query_vport_counter_in, in, other_vport, 1); memset(out, 0, outlen); err = mlx5_cmd_exec(esw->dev, in, sizeof(in), out, outlen); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 9c89eea9b2c3..af5581a57e56 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -38,6 +38,7 @@ #include <net/devlink.h> #include <linux/mlx5/device.h> #include <linux/mlx5/eswitch.h> +#include <linux/mlx5/vport.h> #include <linux/mlx5/fs.h> #include "lib/mpfs.h" @@ -49,8 +50,6 @@ #define MLX5_MAX_MC_PER_VPORT(dev) \ (1 << MLX5_CAP_GEN(dev, log_max_current_mc_list)) -#define FDB_UPLINK_VPORT 0xffff - #define MLX5_MIN_BW_SHARE 1 #define MLX5_RATE_TO_BW_SHARE(rate, divider, limit) \ @@ -183,6 +182,16 @@ struct esw_mc_addr { /* SRIOV only */ u32 refcnt; }; +struct mlx5_host_work { + struct work_struct work; + struct mlx5_eswitch *esw; +}; + +struct mlx5_host_info { + struct mlx5_nb nb; + u16 num_vfs; +}; + struct mlx5_eswitch { struct mlx5_core_dev *dev; struct mlx5_nb nb; @@ -206,10 +215,13 @@ struct mlx5_eswitch { struct mlx5_esw_offload offloads; int mode; int nvports; + u16 manager_vport; + struct mlx5_host_info host_info; }; -void esw_offloads_cleanup(struct mlx5_eswitch *esw, int nvports); -int esw_offloads_init(struct mlx5_eswitch *esw, int nvports); +void esw_offloads_cleanup(struct mlx5_eswitch *esw); +int esw_offloads_init(struct mlx5_eswitch *esw, int vf_nvports, + int total_nvports); void esw_offloads_cleanup_reps(struct mlx5_eswitch *esw); int esw_offloads_init_reps(struct mlx5_eswitch *esw); @@ -312,6 +324,7 @@ struct mlx5_esw_flow_attr { } dests[MLX5_MAX_FLOW_FWD_VPORTS]; u32 mod_hdr_id; u8 match_level; + u8 tunnel_match_level; struct mlx5_fc *counter; u32 chain; u16 prio; @@ -364,6 +377,53 @@ bool mlx5_esw_lag_prereq(struct mlx5_core_dev *dev0, #define esw_debug(dev, format, ...) \ mlx5_core_dbg_mask(dev, MLX5_DEBUG_ESWITCH_MASK, format, ##__VA_ARGS__) + +/* The returned number is valid only when the dev is eswitch manager. */ +static inline u16 mlx5_eswitch_manager_vport(struct mlx5_core_dev *dev) +{ + return mlx5_core_is_ecpf_esw_manager(dev) ? + MLX5_VPORT_ECPF : MLX5_VPORT_PF; +} + +static inline int mlx5_eswitch_uplink_idx(struct mlx5_eswitch *esw) +{ + /* Uplink always locate at the last element of the array.*/ + return esw->total_vports - 1; +} + +static inline int mlx5_eswitch_ecpf_idx(struct mlx5_eswitch *esw) +{ + return esw->total_vports - 2; +} + +static inline int mlx5_eswitch_vport_num_to_index(struct mlx5_eswitch *esw, + u16 vport_num) +{ + if (vport_num == MLX5_VPORT_ECPF) { + if (!mlx5_ecpf_vport_exists(esw->dev)) + esw_warn(esw->dev, "ECPF vport doesn't exist!\n"); + return mlx5_eswitch_ecpf_idx(esw); + } + + if (vport_num == MLX5_VPORT_UPLINK) + return mlx5_eswitch_uplink_idx(esw); + + return vport_num; +} + +static inline int mlx5_eswitch_index_to_vport_num(struct mlx5_eswitch *esw, + int index) +{ + if (index == mlx5_eswitch_ecpf_idx(esw) && + mlx5_ecpf_vport_exists(esw->dev)) + return MLX5_VPORT_ECPF; + + if (index == mlx5_eswitch_uplink_idx(esw)) + return MLX5_VPORT_UPLINK; + + return index; +} + #else /* CONFIG_MLX5_ESWITCH */ /* eswitch API stubs */ static inline int mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 53065b6ae593..f2260391be5b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -40,15 +40,59 @@ #include "en.h" #include "fs_core.h" #include "lib/devcom.h" +#include "ecpf.h" +#include "lib/eq.h" enum { FDB_FAST_PATH = 0, FDB_SLOW_PATH }; +/* There are two match-all miss flows, one for unicast dst mac and + * one for multicast. + */ +#define MLX5_ESW_MISS_FLOWS (2) + #define fdb_prio_table(esw, chain, prio, level) \ (esw)->fdb_table.offloads.fdb_prio[(chain)][(prio)][(level)] +#define UPLINK_REP_INDEX 0 + +/* The rep getter/iterator are only valid after esw->total_vports + * and vport->vport are initialized in mlx5_eswitch_init. + */ +#define mlx5_esw_for_all_reps(esw, i, rep) \ + for ((i) = MLX5_VPORT_PF; \ + (rep) = &(esw)->offloads.vport_reps[i], \ + (i) < (esw)->total_vports; (i)++) + +#define mlx5_esw_for_each_vf_rep(esw, i, rep, nvfs) \ + for ((i) = MLX5_VPORT_FIRST_VF; \ + (rep) = &(esw)->offloads.vport_reps[i], \ + (i) <= (nvfs); (i)++) + +#define mlx5_esw_for_each_vf_rep_reverse(esw, i, rep, nvfs) \ + for ((i) = (nvfs); \ + (rep) = &(esw)->offloads.vport_reps[i], \ + (i) >= MLX5_VPORT_FIRST_VF; (i)--) + +#define mlx5_esw_for_each_vf_vport(esw, vport, nvfs) \ + for ((vport) = MLX5_VPORT_FIRST_VF; \ + (vport) <= (nvfs); (vport)++) + +#define mlx5_esw_for_each_vf_vport_reverse(esw, vport, nvfs) \ + for ((vport) = (nvfs); \ + (vport) >= MLX5_VPORT_FIRST_VF; (vport)--) + +static struct mlx5_eswitch_rep *mlx5_eswitch_get_rep(struct mlx5_eswitch *esw, + u16 vport_num) +{ + u16 idx = mlx5_eswitch_vport_num_to_index(esw, vport_num); + + WARN_ON(idx > esw->total_vports - 1); + return &esw->offloads.vport_reps[idx]; +} + static struct mlx5_flow_table * esw_get_prio_table(struct mlx5_eswitch *esw, u32 chain, u16 prio, int level); static void @@ -160,14 +204,15 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_eswitch_owner_vhca_id); - if (attr->match_level == MLX5_MATCH_NONE) - spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS; - else - spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS | - MLX5_MATCH_MISC_PARAMETERS; - - if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DECAP) - spec->match_criteria_enable |= MLX5_MATCH_INNER_HEADERS; + spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS; + if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DECAP) { + if (attr->tunnel_match_level != MLX5_MATCH_NONE) + spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS; + if (attr->match_level != MLX5_MATCH_NONE) + spec->match_criteria_enable |= MLX5_MATCH_INNER_HEADERS; + } else if (attr->match_level != MLX5_MATCH_NONE) { + spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS; + } if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) flow_act.modify_id = attr->mod_hdr_id; @@ -318,7 +363,7 @@ static int esw_set_global_vlan_pop(struct mlx5_eswitch *esw, u8 val) esw_debug(esw->dev, "%s applying global %s policy\n", __func__, val ? "pop" : "none"); for (vf_vport = 1; vf_vport < esw->enabled_vports; vf_vport++) { rep = &esw->offloads.vport_reps[vf_vport]; - if (!rep->rep_if[REP_ETH].valid) + if (rep->rep_if[REP_ETH].state != REP_LOADED) continue; err = __mlx5_eswitch_set_vport_vlan(esw, rep->vport, 0, 0, val); @@ -359,15 +404,15 @@ static int esw_add_vlan_action_check(struct mlx5_esw_flow_attr *attr, in_rep = attr->in_rep; out_rep = attr->dests[0].rep; - if (push && in_rep->vport == FDB_UPLINK_VPORT) + if (push && in_rep->vport == MLX5_VPORT_UPLINK) goto out_notsupp; - if (pop && out_rep->vport == FDB_UPLINK_VPORT) + if (pop && out_rep->vport == MLX5_VPORT_UPLINK) goto out_notsupp; /* vport has vlan push configured, can't offload VF --> wire rules w.o it */ if (!push && !pop && fwd) - if (in_rep->vlan && out_rep->vport == FDB_UPLINK_VPORT) + if (in_rep->vlan && out_rep->vport == MLX5_VPORT_UPLINK) goto out_notsupp; /* protects against (1) setting rules with different vlans to push and @@ -409,7 +454,7 @@ int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw, if (!push && !pop && fwd) { /* tracks VF --> wire rules without vlan push action */ - if (attr->dests[0].rep->vport == FDB_UPLINK_VPORT) { + if (attr->dests[0].rep->vport == MLX5_VPORT_UPLINK) { vport->vlan_refcount++; attr->vlan_handled = true; } @@ -469,7 +514,7 @@ int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw, if (!push && !pop && fwd) { /* tracks VF --> wire rules without vlan push action */ - if (attr->dests[0].rep->vport == FDB_UPLINK_VPORT) + if (attr->dests[0].rep->vport == MLX5_VPORT_UPLINK) vport->vlan_refcount--; return 0; @@ -516,7 +561,8 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw, int vport, u32 sqn misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters); MLX5_SET(fte_match_set_misc, misc, source_sqn, sqn); - MLX5_SET(fte_match_set_misc, misc, source_port, 0x0); /* source vport is 0 */ + /* source vport is the esw manager */ + MLX5_SET(fte_match_set_misc, misc, source_port, esw->manager_vport); misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters); MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_sqn); @@ -561,7 +607,7 @@ static void peer_miss_rules_setup(struct mlx5_core_dev *peer_dev, source_eswitch_owner_vhca_id); dest->type = MLX5_FLOW_DESTINATION_TYPE_VPORT; - dest->vport.num = 0; + dest->vport.num = peer_dev->priv.eswitch->manager_vport; dest->vport.vhca_id = MLX5_CAP_GEN(peer_dev, vhca_id); dest->vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID; } @@ -595,14 +641,35 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters); - for (i = 1; i < nvports; i++) { + if (mlx5_core_is_ecpf_esw_manager(esw->dev)) { + MLX5_SET(fte_match_set_misc, misc, source_port, MLX5_VPORT_PF); + flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb, + spec, &flow_act, &dest, 1); + if (IS_ERR(flow)) { + err = PTR_ERR(flow); + goto add_pf_flow_err; + } + flows[MLX5_VPORT_PF] = flow; + } + + if (mlx5_ecpf_vport_exists(esw->dev)) { + MLX5_SET(fte_match_set_misc, misc, source_port, MLX5_VPORT_ECPF); + flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb, + spec, &flow_act, &dest, 1); + if (IS_ERR(flow)) { + err = PTR_ERR(flow); + goto add_ecpf_flow_err; + } + flows[mlx5_eswitch_ecpf_idx(esw)] = flow; + } + + mlx5_esw_for_each_vf_vport(esw, i, mlx5_core_max_vfs(esw->dev)) { MLX5_SET(fte_match_set_misc, misc, source_port, i); flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb, spec, &flow_act, &dest, 1); if (IS_ERR(flow)) { err = PTR_ERR(flow); - esw_warn(esw->dev, "FDB: Failed to add peer miss flow rule err %d\n", err); - goto add_flow_err; + goto add_vf_flow_err; } flows[i] = flow; } @@ -612,9 +679,18 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw, kvfree(spec); return 0; -add_flow_err: - for (i--; i > 0; i--) +add_vf_flow_err: + nvports = --i; + mlx5_esw_for_each_vf_vport_reverse(esw, i, nvports) mlx5_del_flow_rules(flows[i]); + + if (mlx5_ecpf_vport_exists(esw->dev)) + mlx5_del_flow_rules(flows[mlx5_eswitch_ecpf_idx(esw)]); +add_ecpf_flow_err: + if (mlx5_core_is_ecpf_esw_manager(esw->dev)) + mlx5_del_flow_rules(flows[MLX5_VPORT_PF]); +add_pf_flow_err: + esw_warn(esw->dev, "FDB: Failed to add peer miss flow rule err %d\n", err); kvfree(flows); alloc_flows_err: kvfree(spec); @@ -628,9 +704,15 @@ static void esw_del_fdb_peer_miss_rules(struct mlx5_eswitch *esw) flows = esw->fdb_table.offloads.peer_miss_rules; - for (i = 1; i < esw->total_vports; i++) + mlx5_esw_for_each_vf_vport_reverse(esw, i, mlx5_core_max_vfs(esw->dev)) mlx5_del_flow_rules(flows[i]); + if (mlx5_ecpf_vport_exists(esw->dev)) + mlx5_del_flow_rules(flows[mlx5_eswitch_ecpf_idx(esw)]); + + if (mlx5_core_is_ecpf_esw_manager(esw->dev)) + mlx5_del_flow_rules(flows[MLX5_VPORT_PF]); + kvfree(flows); } @@ -660,7 +742,7 @@ static int esw_add_fdb_miss_rule(struct mlx5_eswitch *esw) dmac_c[0] = 0x01; dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT; - dest.vport.num = 0; + dest.vport.num = esw->manager_vport; flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; flow_rule = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb, spec, @@ -904,8 +986,8 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports) esw->fdb_table.offloads.fdb_left[i] = ESW_POOLS[i] <= fdb_max ? ESW_SIZE / ESW_POOLS[i] : 0; - table_size = nvports * MAX_SQ_NVPORTS + MAX_PF_SQ + 2 + - esw->total_vports; + table_size = nvports * MAX_SQ_NVPORTS + MAX_PF_SQ + + MLX5_ESW_MISS_FLOWS + esw->total_vports; /* create the slow path fdb with encap set, so further table instances * can be created at run time while VFs are probed if the FW allows that. @@ -999,7 +1081,8 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports) dmac[0] = 0x01; MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix); - MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, ix + 2); + MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, + ix + MLX5_ESW_MISS_FLOWS); g = mlx5_create_flow_group(fdb, flow_group_in); if (IS_ERR(g)) { @@ -1048,7 +1131,7 @@ static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw) esw_destroy_offloads_fast_fdb_tables(esw); } -static int esw_create_offloads_table(struct mlx5_eswitch *esw) +static int esw_create_offloads_table(struct mlx5_eswitch *esw, int nvports) { struct mlx5_flow_table_attr ft_attr = {}; struct mlx5_core_dev *dev = esw->dev; @@ -1062,7 +1145,7 @@ static int esw_create_offloads_table(struct mlx5_eswitch *esw) return -EOPNOTSUPP; } - ft_attr.max_fte = dev->priv.sriov.num_vfs + 2; + ft_attr.max_fte = nvports + MLX5_ESW_MISS_FLOWS; ft_offloads = mlx5_create_flow_table(ns, &ft_attr); if (IS_ERR(ft_offloads)) { @@ -1082,16 +1165,15 @@ static void esw_destroy_offloads_table(struct mlx5_eswitch *esw) mlx5_destroy_flow_table(offloads->ft_offloads); } -static int esw_create_vport_rx_group(struct mlx5_eswitch *esw) +static int esw_create_vport_rx_group(struct mlx5_eswitch *esw, int nvports) { int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); struct mlx5_flow_group *g; - struct mlx5_priv *priv = &esw->dev->priv; u32 *flow_group_in; void *match_criteria, *misc; int err = 0; - int nvports = priv->sriov.num_vfs + 2; + nvports = nvports + MLX5_ESW_MISS_FLOWS; flow_group_in = kvzalloc(inlen, GFP_KERNEL); if (!flow_group_in) return -ENOMEM; @@ -1168,7 +1250,8 @@ static int esw_offloads_start(struct mlx5_eswitch *esw, { int err, err1, num_vfs = esw->dev->priv.sriov.num_vfs; - if (esw->mode != SRIOV_LEGACY) { + if (esw->mode != SRIOV_LEGACY && + !mlx5_core_is_ecpf_esw_manager(esw->dev)) { NL_SET_ERR_MSG_MOD(extack, "Can't set offloads mode, SRIOV legacy not enabled"); return -EINVAL; @@ -1206,9 +1289,8 @@ int esw_offloads_init_reps(struct mlx5_eswitch *esw) { int total_vfs = MLX5_TOTAL_VPORTS(esw->dev); struct mlx5_core_dev *dev = esw->dev; - struct mlx5_esw_offload *offloads; struct mlx5_eswitch_rep *rep; - u8 hw_id[ETH_ALEN]; + u8 hw_id[ETH_ALEN], rep_type; int vport; esw->offloads.vport_reps = kcalloc(total_vfs, @@ -1217,75 +1299,203 @@ int esw_offloads_init_reps(struct mlx5_eswitch *esw) if (!esw->offloads.vport_reps) return -ENOMEM; - offloads = &esw->offloads; mlx5_query_nic_vport_mac_address(dev, 0, hw_id); - for (vport = 0; vport < total_vfs; vport++) { - rep = &offloads->vport_reps[vport]; - - rep->vport = vport; + mlx5_esw_for_all_reps(esw, vport, rep) { + rep->vport = mlx5_eswitch_index_to_vport_num(esw, vport); ether_addr_copy(rep->hw_id, hw_id); - } - offloads->vport_reps[0].vport = FDB_UPLINK_VPORT; + for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) + rep->rep_if[rep_type].state = REP_UNREGISTERED; + } return 0; } -static void esw_offloads_unload_reps_type(struct mlx5_eswitch *esw, int nvports, - u8 rep_type) +static void __esw_offloads_unload_rep(struct mlx5_eswitch *esw, + struct mlx5_eswitch_rep *rep, u8 rep_type) +{ + if (rep->rep_if[rep_type].state != REP_LOADED) + return; + + rep->rep_if[rep_type].unload(rep); + rep->rep_if[rep_type].state = REP_REGISTERED; +} + +static void __unload_reps_special_vport(struct mlx5_eswitch *esw, u8 rep_type) { struct mlx5_eswitch_rep *rep; - int vport; - for (vport = nvports - 1; vport >= 0; vport--) { - rep = &esw->offloads.vport_reps[vport]; - if (!rep->rep_if[rep_type].valid) - continue; + if (mlx5_ecpf_vport_exists(esw->dev)) { + rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_ECPF); + __esw_offloads_unload_rep(esw, rep, rep_type); + } - rep->rep_if[rep_type].unload(rep); + if (mlx5_core_is_ecpf_esw_manager(esw->dev)) { + rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_PF); + __esw_offloads_unload_rep(esw, rep, rep_type); } + + rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK); + __esw_offloads_unload_rep(esw, rep, rep_type); } -static void esw_offloads_unload_reps(struct mlx5_eswitch *esw, int nvports) +static void __unload_reps_vf_vport(struct mlx5_eswitch *esw, int nvports, + u8 rep_type) +{ + struct mlx5_eswitch_rep *rep; + int i; + + mlx5_esw_for_each_vf_rep_reverse(esw, i, rep, nvports) + __esw_offloads_unload_rep(esw, rep, rep_type); +} + +static void esw_offloads_unload_vf_reps(struct mlx5_eswitch *esw, int nvports) +{ + u8 rep_type = NUM_REP_TYPES; + + while (rep_type-- > 0) + __unload_reps_vf_vport(esw, nvports, rep_type); +} + +static void __unload_reps_all_vport(struct mlx5_eswitch *esw, int nvports, + u8 rep_type) +{ + __unload_reps_vf_vport(esw, nvports, rep_type); + + /* Special vports must be the last to unload. */ + __unload_reps_special_vport(esw, rep_type); +} + +static void esw_offloads_unload_all_reps(struct mlx5_eswitch *esw, int nvports) { u8 rep_type = NUM_REP_TYPES; while (rep_type-- > 0) - esw_offloads_unload_reps_type(esw, nvports, rep_type); + __unload_reps_all_vport(esw, nvports, rep_type); +} + +static int __esw_offloads_load_rep(struct mlx5_eswitch *esw, + struct mlx5_eswitch_rep *rep, u8 rep_type) +{ + int err = 0; + + if (rep->rep_if[rep_type].state != REP_REGISTERED) + return 0; + + err = rep->rep_if[rep_type].load(esw->dev, rep); + if (err) + return err; + + rep->rep_if[rep_type].state = REP_LOADED; + + return 0; } -static int esw_offloads_load_reps_type(struct mlx5_eswitch *esw, int nvports, - u8 rep_type) +static int __load_reps_special_vport(struct mlx5_eswitch *esw, u8 rep_type) { struct mlx5_eswitch_rep *rep; - int vport; int err; - for (vport = 0; vport < nvports; vport++) { - rep = &esw->offloads.vport_reps[vport]; - if (!rep->rep_if[rep_type].valid) - continue; + rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK); + err = __esw_offloads_load_rep(esw, rep, rep_type); + if (err) + return err; - err = rep->rep_if[rep_type].load(esw->dev, rep); + if (mlx5_core_is_ecpf_esw_manager(esw->dev)) { + rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_PF); + err = __esw_offloads_load_rep(esw, rep, rep_type); if (err) - goto err_reps; + goto err_pf; + } + + if (mlx5_ecpf_vport_exists(esw->dev)) { + rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_ECPF); + err = __esw_offloads_load_rep(esw, rep, rep_type); + if (err) + goto err_ecpf; + } + + return 0; + +err_ecpf: + if (mlx5_core_is_ecpf_esw_manager(esw->dev)) { + rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_PF); + __esw_offloads_unload_rep(esw, rep, rep_type); + } + +err_pf: + rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK); + __esw_offloads_unload_rep(esw, rep, rep_type); + return err; +} + +static int __load_reps_vf_vport(struct mlx5_eswitch *esw, int nvports, + u8 rep_type) +{ + struct mlx5_eswitch_rep *rep; + int err, i; + + mlx5_esw_for_each_vf_rep(esw, i, rep, nvports) { + err = __esw_offloads_load_rep(esw, rep, rep_type); + if (err) + goto err_vf; } return 0; +err_vf: + __unload_reps_vf_vport(esw, --i, rep_type); + return err; +} + +static int esw_offloads_load_vf_reps(struct mlx5_eswitch *esw, int nvports) +{ + u8 rep_type = 0; + int err; + + for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) { + err = __load_reps_vf_vport(esw, nvports, rep_type); + if (err) + goto err_reps; + } + + return err; + err_reps: - esw_offloads_unload_reps_type(esw, vport, rep_type); + while (rep_type-- > 0) + __unload_reps_vf_vport(esw, nvports, rep_type); + return err; +} + +static int __load_reps_all_vport(struct mlx5_eswitch *esw, int nvports, + u8 rep_type) +{ + int err; + + /* Special vports must be loaded first. */ + err = __load_reps_special_vport(esw, rep_type); + if (err) + return err; + + err = __load_reps_vf_vport(esw, nvports, rep_type); + if (err) + goto err_vfs; + + return 0; + +err_vfs: + __unload_reps_special_vport(esw, rep_type); return err; } -static int esw_offloads_load_reps(struct mlx5_eswitch *esw, int nvports) +static int esw_offloads_load_all_reps(struct mlx5_eswitch *esw, int nvports) { u8 rep_type = 0; int err; for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) { - err = esw_offloads_load_reps_type(esw, nvports, rep_type); + err = __load_reps_all_vport(esw, nvports, rep_type); if (err) goto err_reps; } @@ -1294,7 +1504,7 @@ static int esw_offloads_load_reps(struct mlx5_eswitch *esw, int nvports) err_reps: while (rep_type-- > 0) - esw_offloads_unload_reps_type(esw, nvports, rep_type); + __unload_reps_all_vport(esw, nvports, rep_type); return err; } @@ -1397,7 +1607,7 @@ static void esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw) mlx5_devcom_unregister_component(devcom, MLX5_DEVCOM_ESW_OFFLOADS); } -int esw_offloads_init(struct mlx5_eswitch *esw, int nvports) +static int esw_offloads_steering_init(struct mlx5_eswitch *esw, int nvports) { int err; @@ -1407,24 +1617,16 @@ int esw_offloads_init(struct mlx5_eswitch *esw, int nvports) if (err) return err; - err = esw_create_offloads_table(esw); + err = esw_create_offloads_table(esw, nvports); if (err) goto create_ft_err; - err = esw_create_vport_rx_group(esw); + err = esw_create_vport_rx_group(esw, nvports); if (err) goto create_fg_err; - err = esw_offloads_load_reps(esw, nvports); - if (err) - goto err_reps; - - esw_offloads_devcom_init(esw); return 0; -err_reps: - esw_destroy_vport_rx_group(esw); - create_fg_err: esw_destroy_offloads_table(esw); @@ -1434,6 +1636,95 @@ create_ft_err: return err; } +static void esw_offloads_steering_cleanup(struct mlx5_eswitch *esw) +{ + esw_destroy_vport_rx_group(esw); + esw_destroy_offloads_table(esw); + esw_destroy_offloads_fdb_tables(esw); +} + +static void esw_host_params_event_handler(struct work_struct *work) +{ + struct mlx5_host_work *host_work; + struct mlx5_eswitch *esw; + int err, num_vf = 0; + + host_work = container_of(work, struct mlx5_host_work, work); + esw = host_work->esw; + + err = mlx5_query_host_params_num_vfs(esw->dev, &num_vf); + if (err || num_vf == esw->host_info.num_vfs) + goto out; + + /* Number of VFs can only change from "0 to x" or "x to 0". */ + if (esw->host_info.num_vfs > 0) { + esw_offloads_unload_vf_reps(esw, esw->host_info.num_vfs); + } else { + err = esw_offloads_load_vf_reps(esw, num_vf); + + if (err) + goto out; + } + + esw->host_info.num_vfs = num_vf; + +out: + kfree(host_work); +} + +static int esw_host_params_event(struct notifier_block *nb, + unsigned long type, void *data) +{ + struct mlx5_host_work *host_work; + struct mlx5_host_info *host_info; + struct mlx5_eswitch *esw; + + host_work = kzalloc(sizeof(*host_work), GFP_ATOMIC); + if (!host_work) + return NOTIFY_DONE; + + host_info = mlx5_nb_cof(nb, struct mlx5_host_info, nb); + esw = container_of(host_info, struct mlx5_eswitch, host_info); + + host_work->esw = esw; + + INIT_WORK(&host_work->work, esw_host_params_event_handler); + queue_work(esw->work_queue, &host_work->work); + + return NOTIFY_OK; +} + +int esw_offloads_init(struct mlx5_eswitch *esw, int vf_nvports, + int total_nvports) +{ + int err; + + mutex_init(&esw->fdb_table.offloads.fdb_prio_lock); + + err = esw_offloads_steering_init(esw, total_nvports); + if (err) + return err; + + err = esw_offloads_load_all_reps(esw, vf_nvports); + if (err) + goto err_reps; + + esw_offloads_devcom_init(esw); + + if (mlx5_core_is_ecpf_esw_manager(esw->dev)) { + MLX5_NB_INIT(&esw->host_info.nb, esw_host_params_event, + HOST_PARAMS_CHANGE); + mlx5_eq_notifier_register(esw->dev, &esw->host_info.nb); + esw->host_info.num_vfs = vf_nvports; + } + + return 0; + +err_reps: + esw_offloads_steering_cleanup(esw); + return err; +} + static int esw_offloads_stop(struct mlx5_eswitch *esw, struct netlink_ext_ack *extack) { @@ -1453,13 +1744,21 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw, return err; } -void esw_offloads_cleanup(struct mlx5_eswitch *esw, int nvports) +void esw_offloads_cleanup(struct mlx5_eswitch *esw) { + u16 num_vfs; + + if (mlx5_core_is_ecpf_esw_manager(esw->dev)) { + mlx5_eq_notifier_unregister(esw->dev, &esw->host_info.nb); + flush_workqueue(esw->work_queue); + num_vfs = esw->host_info.num_vfs; + } else { + num_vfs = esw->dev->priv.sriov.num_vfs; + } + esw_offloads_devcom_cleanup(esw); - esw_offloads_unload_reps(esw, nvports); - esw_destroy_vport_rx_group(esw); - esw_destroy_offloads_table(esw); - esw_destroy_offloads_fdb_tables(esw); + esw_offloads_unload_all_reps(esw, num_vfs); + esw_offloads_steering_cleanup(esw); } static int esw_mode_from_devlink(u16 mode, u16 *mlx5_mode) @@ -1548,7 +1847,8 @@ static int mlx5_devlink_eswitch_check(struct devlink *devlink) if(!MLX5_ESWITCH_MANAGER(dev)) return -EPERM; - if (dev->priv.eswitch->mode == SRIOV_NONE) + if (dev->priv.eswitch->mode == SRIOV_NONE && + !mlx5_core_is_ecpf_esw_manager(dev)) return -EOPNOTSUPP; return 0; @@ -1760,47 +2060,45 @@ int mlx5_devlink_eswitch_encap_mode_get(struct devlink *devlink, u8 *encap) return 0; } -void mlx5_eswitch_register_vport_rep(struct mlx5_eswitch *esw, - int vport_index, - struct mlx5_eswitch_rep_if *__rep_if, - u8 rep_type) +void mlx5_eswitch_register_vport_reps(struct mlx5_eswitch *esw, + struct mlx5_eswitch_rep_if *__rep_if, + u8 rep_type) { - struct mlx5_esw_offload *offloads = &esw->offloads; struct mlx5_eswitch_rep_if *rep_if; + struct mlx5_eswitch_rep *rep; + int i; - rep_if = &offloads->vport_reps[vport_index].rep_if[rep_type]; - - rep_if->load = __rep_if->load; - rep_if->unload = __rep_if->unload; - rep_if->get_proto_dev = __rep_if->get_proto_dev; - rep_if->priv = __rep_if->priv; + mlx5_esw_for_all_reps(esw, i, rep) { + rep_if = &rep->rep_if[rep_type]; + rep_if->load = __rep_if->load; + rep_if->unload = __rep_if->unload; + rep_if->get_proto_dev = __rep_if->get_proto_dev; + rep_if->priv = __rep_if->priv; - rep_if->valid = true; + rep_if->state = REP_REGISTERED; + } } -EXPORT_SYMBOL(mlx5_eswitch_register_vport_rep); +EXPORT_SYMBOL(mlx5_eswitch_register_vport_reps); -void mlx5_eswitch_unregister_vport_rep(struct mlx5_eswitch *esw, - int vport_index, u8 rep_type) +void mlx5_eswitch_unregister_vport_reps(struct mlx5_eswitch *esw, u8 rep_type) { - struct mlx5_esw_offload *offloads = &esw->offloads; + u16 max_vf = mlx5_core_max_vfs(esw->dev); struct mlx5_eswitch_rep *rep; + int i; - rep = &offloads->vport_reps[vport_index]; - - if (esw->mode == SRIOV_OFFLOADS && esw->vports[vport_index].enabled) - rep->rep_if[rep_type].unload(rep); + if (esw->mode == SRIOV_OFFLOADS) + __unload_reps_all_vport(esw, max_vf, rep_type); - rep->rep_if[rep_type].valid = false; + mlx5_esw_for_all_reps(esw, i, rep) + rep->rep_if[rep_type].state = REP_UNREGISTERED; } -EXPORT_SYMBOL(mlx5_eswitch_unregister_vport_rep); +EXPORT_SYMBOL(mlx5_eswitch_unregister_vport_reps); void *mlx5_eswitch_get_uplink_priv(struct mlx5_eswitch *esw, u8 rep_type) { -#define UPLINK_REP_INDEX 0 - struct mlx5_esw_offload *offloads = &esw->offloads; struct mlx5_eswitch_rep *rep; - rep = &offloads->vport_reps[UPLINK_REP_INDEX]; + rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK); return rep->rep_if[rep_type].priv; } @@ -1808,15 +2106,11 @@ void *mlx5_eswitch_get_proto_dev(struct mlx5_eswitch *esw, int vport, u8 rep_type) { - struct mlx5_esw_offload *offloads = &esw->offloads; struct mlx5_eswitch_rep *rep; - if (vport == FDB_UPLINK_VPORT) - vport = UPLINK_REP_INDEX; - - rep = &offloads->vport_reps[vport]; + rep = mlx5_eswitch_get_rep(esw, vport); - if (rep->rep_if[rep_type].valid && + if (rep->rep_if[rep_type].state == REP_LOADED && rep->rep_if[rep_type].get_proto_dev) return rep->rep_if[rep_type].get_proto_dev(rep); return NULL; @@ -1825,13 +2119,13 @@ EXPORT_SYMBOL(mlx5_eswitch_get_proto_dev); void *mlx5_eswitch_uplink_get_proto_dev(struct mlx5_eswitch *esw, u8 rep_type) { - return mlx5_eswitch_get_proto_dev(esw, UPLINK_REP_INDEX, rep_type); + return mlx5_eswitch_get_proto_dev(esw, MLX5_VPORT_UPLINK, rep_type); } EXPORT_SYMBOL(mlx5_eswitch_uplink_get_proto_dev); struct mlx5_eswitch_rep *mlx5_eswitch_vport_rep(struct mlx5_eswitch *esw, int vport) { - return &esw->offloads.vport_reps[vport]; + return mlx5_eswitch_get_rep(esw, vport); } EXPORT_SYMBOL(mlx5_eswitch_vport_rep); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c index fbc42b7252a9..5d5864e8df3c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/events.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c @@ -103,6 +103,8 @@ static const char *eqe_type_str(u8 type) return "MLX5_EVENT_TYPE_STALL_EVENT"; case MLX5_EVENT_TYPE_CMD: return "MLX5_EVENT_TYPE_CMD"; + case MLX5_EVENT_TYPE_HOST_PARAMS_CHANGE: + return "MLX5_EVENT_TYPE_HOST_PARAMS_CHANGE"; case MLX5_EVENT_TYPE_PAGE_REQUEST: return "MLX5_EVENT_TYPE_PAGE_REQUEST"; case MLX5_EVENT_TYPE_PAGE_FAULT: @@ -211,11 +213,10 @@ static int port_module(struct notifier_block *nb, unsigned long type, void *data enum port_module_event_status_type module_status; enum port_module_event_error_type error_type; struct mlx5_eqe_port_module *module_event_eqe; - const char *status_str, *error_str; + const char *status_str; u8 module_num; module_event_eqe = &eqe->data.port_module; - module_num = module_event_eqe->module; module_status = module_event_eqe->module_status & PORT_MODULE_EVENT_MODULE_STATUS_MASK; error_type = module_event_eqe->error_type & @@ -223,25 +224,27 @@ static int port_module(struct notifier_block *nb, unsigned long type, void *data if (module_status < MLX5_MODULE_STATUS_NUM) events->pme_stats.status_counters[module_status]++; - status_str = mlx5_pme_status_to_string(module_status); - if (module_status == MLX5_MODULE_STATUS_ERROR) { + if (module_status == MLX5_MODULE_STATUS_ERROR) if (error_type < MLX5_MODULE_EVENT_ERROR_NUM) events->pme_stats.error_counters[error_type]++; - error_str = mlx5_pme_error_to_string(error_type); - } if (!printk_ratelimit()) return NOTIFY_OK; - if (module_status == MLX5_MODULE_STATUS_ERROR) + module_num = module_event_eqe->module; + status_str = mlx5_pme_status_to_string(module_status); + if (module_status == MLX5_MODULE_STATUS_ERROR) { + const char *error_str = mlx5_pme_error_to_string(error_type); + mlx5_core_err(events->dev, "Port module event[error]: module %u, %s, %s\n", module_num, status_str, error_str); - else + } else { mlx5_core_info(events->dev, "Port module event: module %u, %s\n", module_num, status_str); + } return NOTIFY_OK; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index b2df7c3749fb..f2cfa012315e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -32,6 +32,7 @@ #include <linux/mutex.h> #include <linux/mlx5/driver.h> +#include <linux/mlx5/vport.h> #include <linux/mlx5/eswitch.h> #include "mlx5_core.h" @@ -619,7 +620,8 @@ static struct mlx5_flow_group *alloc_flow_group(struct mlx5_flow_steering *steer if (ret) { kmem_cache_free(steering->fgs_cache, fg); return ERR_PTR(ret); -} + } + ida_init(&fg->fte_allocator); fg->mask.match_criteria_enable = match_criteria_enable; memcpy(&fg->mask.match_criteria, match_criteria, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 196c07383082..cb9fa3430c53 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -103,7 +103,7 @@ void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force) mlx5_core_err(dev, "start\n"); if (pci_channel_offline(dev->pdev) || in_fatal(dev) || force) { dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR; - mlx5_cmd_trigger_completions(dev); + mlx5_cmd_flush(dev); } mlx5_notifier_call_chain(dev->priv.events, MLX5_DEV_EVENT_SYS_ERROR, (void *)1); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c index 3a6baed722d8..04c5aca7f8c5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c @@ -343,6 +343,11 @@ static void mlx5_do_bond(struct mlx5_lag *ldev) roce_lag = !mlx5_sriov_is_enabled(dev0) && !mlx5_sriov_is_enabled(dev1); +#ifdef CONFIG_MLX5_ESWITCH + roce_lag &= dev0->priv.eswitch->mode == SRIOV_NONE && + dev1->priv.eswitch->mode == SRIOV_NONE; +#endif + if (roce_lag) mlx5_lag_remove_ib_devices(ldev); @@ -616,6 +621,27 @@ void mlx5_lag_add(struct mlx5_core_dev *dev, struct net_device *netdev) } } +int mlx5_lag_get_pf_num(struct mlx5_core_dev *dev, int *pf_num) +{ + struct mlx5_lag *ldev; + int n; + + ldev = mlx5_lag_dev_get(dev); + if (!ldev) { + mlx5_core_warn(dev, "no lag device, can't get pf num\n"); + return -EINVAL; + } + + for (n = 0; n < MLX5_MAX_PORTS; n++) + if (ldev->pf[n].dev == dev) { + *pf_num = n; + return 0; + } + + mlx5_core_warn(dev, "wasn't able to locate pf in the lag device\n"); + return -EINVAL; +} + /* Must be called with intf_mutex held */ void mlx5_lag_remove(struct mlx5_core_dev *dev) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mad.c b/drivers/net/ethernet/mellanox/mlx5/core/mad.c deleted file mode 100644 index 3a3b0005fd2b..000000000000 --- a/drivers/net/ethernet/mellanox/mlx5/core/mad.c +++ /dev/null @@ -1,75 +0,0 @@ -/* - * Copyright (c) 2013-2015, Mellanox Technologies. All rights reserved. - * - * This software is available to you under a choice of one of two - * licenses. You may choose to be licensed under the terms of the GNU - * General Public License (GPL) Version 2, available from the file - * COPYING in the main directory of this source tree, or the - * OpenIB.org BSD license below: - * - * Redistribution and use in source and binary forms, with or - * without modification, are permitted provided that the following - * conditions are met: - * - * - Redistributions of source code must retain the above - * copyright notice, this list of conditions and the following - * disclaimer. - * - * - Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following - * disclaimer in the documentation and/or other materials - * provided with the distribution. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, - * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF - * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND - * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS - * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN - * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN - * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE - * SOFTWARE. - */ - -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/mlx5/driver.h> -#include <linux/mlx5/cmd.h> -#include "mlx5_core.h" - -int mlx5_core_mad_ifc(struct mlx5_core_dev *dev, const void *inb, void *outb, - u16 opmod, u8 port) -{ - int outlen = MLX5_ST_SZ_BYTES(mad_ifc_out); - int inlen = MLX5_ST_SZ_BYTES(mad_ifc_in); - int err = -ENOMEM; - void *data; - void *resp; - u32 *out; - u32 *in; - - in = kzalloc(inlen, GFP_KERNEL); - out = kzalloc(outlen, GFP_KERNEL); - if (!in || !out) - goto out; - - MLX5_SET(mad_ifc_in, in, opcode, MLX5_CMD_OP_MAD_IFC); - MLX5_SET(mad_ifc_in, in, op_mod, opmod); - MLX5_SET(mad_ifc_in, in, port, port); - - data = MLX5_ADDR_OF(mad_ifc_in, in, mad); - memcpy(data, inb, MLX5_FLD_SZ_BYTES(mad_ifc_in, mad)); - - err = mlx5_cmd_exec(dev, in, inlen, out, outlen); - if (err) - goto out; - - resp = MLX5_ADDR_OF(mad_ifc_out, out, response_mad_packet); - memcpy(outb, resp, - MLX5_FLD_SZ_BYTES(mad_ifc_out, response_mad_packet)); - -out: - kfree(out); - kfree(in); - return err; -} -EXPORT_SYMBOL_GPL(mlx5_core_mad_ifc); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index be81b319b0dc..40d591c8e76c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -65,6 +65,7 @@ #include "lib/vxlan.h" #include "lib/devcom.h" #include "diag/fw_tracer.h" +#include "ecpf.h" MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>"); MODULE_DESCRIPTION("Mellanox 5th generation network adapters (ConnectX series) core driver"); @@ -459,6 +460,50 @@ static int handle_hca_cap_atomic(struct mlx5_core_dev *dev) return err; } +static int handle_hca_cap_odp(struct mlx5_core_dev *dev) +{ + void *set_hca_cap; + void *set_ctx; + int set_sz; + int err; + + if (!MLX5_CAP_GEN(dev, pg)) + return 0; + + err = mlx5_core_get_caps(dev, MLX5_CAP_ODP); + if (err) + return err; + + if (!(MLX5_CAP_ODP_MAX(dev, ud_odp_caps.srq_receive) || + MLX5_CAP_ODP_MAX(dev, rc_odp_caps.srq_receive) || + MLX5_CAP_ODP_MAX(dev, xrc_odp_caps.srq_receive))) + return 0; + + set_sz = MLX5_ST_SZ_BYTES(set_hca_cap_in); + set_ctx = kzalloc(set_sz, GFP_KERNEL); + if (!set_ctx) + return -ENOMEM; + + set_hca_cap = MLX5_ADDR_OF(set_hca_cap_in, set_ctx, capability); + memcpy(set_hca_cap, dev->caps.hca_cur[MLX5_CAP_ODP], + MLX5_ST_SZ_BYTES(odp_cap)); + + /* set ODP SRQ support for RC/UD and XRC transports */ + MLX5_SET(odp_cap, set_hca_cap, ud_odp_caps.srq_receive, + MLX5_CAP_ODP_MAX(dev, ud_odp_caps.srq_receive)); + + MLX5_SET(odp_cap, set_hca_cap, rc_odp_caps.srq_receive, + MLX5_CAP_ODP_MAX(dev, rc_odp_caps.srq_receive)); + + MLX5_SET(odp_cap, set_hca_cap, xrc_odp_caps.srq_receive, + MLX5_CAP_ODP_MAX(dev, xrc_odp_caps.srq_receive)); + + err = set_caps(dev, set_ctx, set_sz, MLX5_SET_HCA_CAP_OP_MOD_ODP); + + kfree(set_ctx); + return err; +} + static int handle_hca_cap(struct mlx5_core_dev *dev) { void *set_ctx = NULL; @@ -567,6 +612,8 @@ int mlx5_core_enable_hca(struct mlx5_core_dev *dev, u16 func_id) MLX5_SET(enable_hca_in, in, opcode, MLX5_CMD_OP_ENABLE_HCA); MLX5_SET(enable_hca_in, in, function_id, func_id); + MLX5_SET(enable_hca_in, in, embedded_cpu_function, + dev->caps.embedded_cpu); return mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out)); } @@ -577,6 +624,8 @@ int mlx5_core_disable_hca(struct mlx5_core_dev *dev, u16 func_id) MLX5_SET(disable_hca_in, in, opcode, MLX5_CMD_OP_DISABLE_HCA); MLX5_SET(disable_hca_in, in, function_id, func_id); + MLX5_SET(enable_hca_in, in, embedded_cpu_function, + dev->caps.embedded_cpu); return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); } @@ -693,6 +742,11 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct mlx5_priv *priv) goto err_clr_master; } + if (pci_enable_atomic_ops_to_root(pdev, PCI_EXP_DEVCAP2_ATOMIC_COMP32) && + pci_enable_atomic_ops_to_root(pdev, PCI_EXP_DEVCAP2_ATOMIC_COMP64) && + pci_enable_atomic_ops_to_root(pdev, PCI_EXP_DEVCAP2_ATOMIC_COMP128)) + mlx5_core_dbg(dev, "Enabling pci atomics failed\n"); + dev->iseg_base = pci_resource_start(dev->pdev, 0); dev->iseg = ioremap(dev->iseg_base, sizeof(*dev->iseg)); if (!dev->iseg) { @@ -849,6 +903,7 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, struct pci_dev *pdev = dev->pdev; int err; + dev->caps.embedded_cpu = mlx5_read_embedded_cpu(dev); mutex_lock(&dev->intf_state_mutex); if (test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) { dev_warn(&dev->pdev->dev, "%s: interface is up, NOP\n", @@ -926,6 +981,12 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, goto reclaim_boot_pages; } + err = handle_hca_cap_odp(dev); + if (err) { + dev_err(&pdev->dev, "handle_hca_cap_odp failed\n"); + goto reclaim_boot_pages; + } + err = mlx5_satisfy_startup_pages(dev, 0); if (err) { dev_err(&pdev->dev, "failed to allocate init pages\n"); @@ -1014,6 +1075,12 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, goto err_sriov; } + err = mlx5_ec_init(dev); + if (err) { + dev_err(&pdev->dev, "Failed to init embedded CPU\n"); + goto err_ec; + } + if (mlx5_device_registered(dev)) { mlx5_attach_device(dev); } else { @@ -1031,6 +1098,9 @@ out: return 0; err_reg_dev: + mlx5_ec_cleanup(dev); + +err_ec: mlx5_sriov_detach(dev); err_sriov: @@ -1105,6 +1175,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, if (mlx5_device_registered(dev)) mlx5_detach_device(dev); + mlx5_ec_cleanup(dev); mlx5_sriov_detach(dev); mlx5_cleanup_fs(dev); mlx5_accel_ipsec_cleanup(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index c68dcea5985b..9529cf9623e3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -121,11 +121,12 @@ int mlx5_modify_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy, u32 modify_bitmask); int mlx5_destroy_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy, u32 element_id); -int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev); +int mlx5_wait_for_pages(struct mlx5_core_dev *dev, int *pages); u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev, struct ptp_system_timestamp *sts); void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev); +void mlx5_cmd_flush(struct mlx5_core_dev *dev); int mlx5_cq_debugfs_init(struct mlx5_core_dev *dev); void mlx5_cq_debugfs_cleanup(struct mlx5_core_dev *dev); @@ -187,6 +188,8 @@ static inline int mlx5_lag_is_lacp_owner(struct mlx5_core_dev *dev) MLX5_CAP_GEN(dev, lag_master); } +int mlx5_lag_get_pf_num(struct mlx5_core_dev *dev, int *pf_num); + void mlx5_reload_interface(struct mlx5_core_dev *mdev, int protocol); void mlx5_lag_update(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c index 0670165afd5f..ea744d8466ea 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c @@ -51,9 +51,10 @@ void mlx5_cleanup_mkey_table(struct mlx5_core_dev *dev) int mlx5_core_create_mkey_cb(struct mlx5_core_dev *dev, struct mlx5_core_mkey *mkey, - u32 *in, int inlen, - u32 *out, int outlen, - mlx5_cmd_cbk_t callback, void *context) + struct mlx5_async_ctx *async_ctx, u32 *in, + int inlen, u32 *out, int outlen, + mlx5_async_cbk_t callback, + struct mlx5_async_work *context) { struct mlx5_mkey_table *table = &dev->priv.mkey_table; u32 lout[MLX5_ST_SZ_DW(create_mkey_out)] = {0}; @@ -71,7 +72,7 @@ int mlx5_core_create_mkey_cb(struct mlx5_core_dev *dev, MLX5_SET(mkc, mkc, mkey_7_0, key); if (callback) - return mlx5_cmd_exec_cb(dev, in, inlen, out, outlen, + return mlx5_cmd_exec_cb(async_ctx, in, inlen, out, outlen, callback, context); err = mlx5_cmd_exec(dev, in, inlen, lout, sizeof(lout)); @@ -105,7 +106,7 @@ int mlx5_core_create_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mkey *mkey, u32 *in, int inlen) { - return mlx5_core_create_mkey_cb(dev, mkey, in, inlen, + return mlx5_core_create_mkey_cb(dev, mkey, NULL, in, inlen, NULL, 0, NULL, NULL); } EXPORT_SYMBOL(mlx5_core_create_mkey); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index a83b517b0714..41025387ff2c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -48,6 +48,7 @@ enum { struct mlx5_pages_req { struct mlx5_core_dev *dev; u16 func_id; + u8 ec_function; s32 npages; struct work_struct work; }; @@ -143,6 +144,7 @@ static int mlx5_cmd_query_pages(struct mlx5_core_dev *dev, u16 *func_id, MLX5_SET(query_pages_in, in, op_mod, boot ? MLX5_QUERY_PAGES_IN_OP_MOD_BOOT_PAGES : MLX5_QUERY_PAGES_IN_OP_MOD_INIT_PAGES); + MLX5_SET(query_pages_in, in, embedded_cpu_function, mlx5_core_is_ecpf(dev)); err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); if (err) @@ -253,7 +255,8 @@ err_mapping: return err; } -static void page_notify_fail(struct mlx5_core_dev *dev, u16 func_id) +static void page_notify_fail(struct mlx5_core_dev *dev, u16 func_id, + bool ec_function) { u32 out[MLX5_ST_SZ_DW(manage_pages_out)] = {0}; u32 in[MLX5_ST_SZ_DW(manage_pages_in)] = {0}; @@ -262,6 +265,7 @@ static void page_notify_fail(struct mlx5_core_dev *dev, u16 func_id) MLX5_SET(manage_pages_in, in, opcode, MLX5_CMD_OP_MANAGE_PAGES); MLX5_SET(manage_pages_in, in, op_mod, MLX5_PAGES_CANT_GIVE); MLX5_SET(manage_pages_in, in, function_id, func_id); + MLX5_SET(manage_pages_in, in, embedded_cpu_function, ec_function); err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); if (err) @@ -270,7 +274,7 @@ static void page_notify_fail(struct mlx5_core_dev *dev, u16 func_id) } static int give_pages(struct mlx5_core_dev *dev, u16 func_id, int npages, - int notify_fail) + int notify_fail, bool ec_function) { u32 out[MLX5_ST_SZ_DW(manage_pages_out)] = {0}; int inlen = MLX5_ST_SZ_BYTES(manage_pages_in); @@ -305,6 +309,7 @@ retry: MLX5_SET(manage_pages_in, in, op_mod, MLX5_PAGES_GIVE); MLX5_SET(manage_pages_in, in, function_id, func_id); MLX5_SET(manage_pages_in, in, input_num_entries, npages); + MLX5_SET(manage_pages_in, in, embedded_cpu_function, ec_function); err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out)); if (err) { @@ -316,8 +321,11 @@ retry: dev->priv.fw_pages += npages; if (func_id) dev->priv.vfs_pages += npages; + else if (mlx5_core_is_ecpf(dev) && !ec_function) + dev->priv.peer_pf_pages += npages; - mlx5_core_dbg(dev, "err %d\n", err); + mlx5_core_dbg(dev, "npages %d, ec_function %d, func_id 0x%x, err %d\n", + npages, ec_function, func_id, err); kvfree(in); return 0; @@ -328,7 +336,7 @@ out_4k: out_free: kvfree(in); if (notify_fail) - page_notify_fail(dev, func_id); + page_notify_fail(dev, func_id, ec_function); return err; } @@ -364,7 +372,7 @@ static int reclaim_pages_cmd(struct mlx5_core_dev *dev, } static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages, - int *nclaimed) + int *nclaimed, bool ec_function) { int outlen = MLX5_ST_SZ_BYTES(manage_pages_out); u32 in[MLX5_ST_SZ_DW(manage_pages_in)] = {0}; @@ -385,6 +393,7 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages, MLX5_SET(manage_pages_in, in, op_mod, MLX5_PAGES_TAKE); MLX5_SET(manage_pages_in, in, function_id, func_id); MLX5_SET(manage_pages_in, in, input_num_entries, npages); + MLX5_SET(manage_pages_in, in, embedded_cpu_function, ec_function); mlx5_core_dbg(dev, "npages %d, outlen %d\n", npages, outlen); err = reclaim_pages_cmd(dev, in, sizeof(in), out, outlen); @@ -410,6 +419,8 @@ static int reclaim_pages(struct mlx5_core_dev *dev, u32 func_id, int npages, dev->priv.fw_pages -= num_claimed; if (func_id) dev->priv.vfs_pages -= num_claimed; + else if (mlx5_core_is_ecpf(dev) && !ec_function) + dev->priv.peer_pf_pages -= num_claimed; out_free: kvfree(out); @@ -423,9 +434,10 @@ static void pages_work_handler(struct work_struct *work) int err = 0; if (req->npages < 0) - err = reclaim_pages(dev, req->func_id, -1 * req->npages, NULL); + err = reclaim_pages(dev, req->func_id, -1 * req->npages, NULL, + req->ec_function); else if (req->npages > 0) - err = give_pages(dev, req->func_id, req->npages, 1); + err = give_pages(dev, req->func_id, req->npages, 1, req->ec_function); if (err) mlx5_core_warn(dev, "%s fail %d\n", @@ -434,6 +446,10 @@ static void pages_work_handler(struct work_struct *work) kfree(req); } +enum { + EC_FUNCTION_MASK = 0x8000, +}; + static int req_pages_handler(struct notifier_block *nb, unsigned long type, void *data) { @@ -441,6 +457,7 @@ static int req_pages_handler(struct notifier_block *nb, struct mlx5_core_dev *dev; struct mlx5_priv *priv; struct mlx5_eqe *eqe; + bool ec_function; u16 func_id; s32 npages; @@ -450,6 +467,7 @@ static int req_pages_handler(struct notifier_block *nb, func_id = be16_to_cpu(eqe->data.req_pages.func_id); npages = be32_to_cpu(eqe->data.req_pages.num_pages); + ec_function = be16_to_cpu(eqe->data.req_pages.ec_function) & EC_FUNCTION_MASK; mlx5_core_dbg(dev, "page request for func 0x%x, npages %d\n", func_id, npages); req = kzalloc(sizeof(*req), GFP_ATOMIC); @@ -461,6 +479,7 @@ static int req_pages_handler(struct notifier_block *nb, req->dev = dev; req->func_id = func_id; req->npages = npages; + req->ec_function = ec_function; INIT_WORK(&req->work, pages_work_handler); queue_work(dev->priv.pg_wq, &req->work); return NOTIFY_OK; @@ -479,7 +498,7 @@ int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot) mlx5_core_dbg(dev, "requested %d %s pages for func_id 0x%x\n", npages, boot ? "boot" : "init", func_id); - return give_pages(dev, func_id, npages, 0); + return give_pages(dev, func_id, npages, 0, mlx5_core_is_ecpf(dev)); } enum { @@ -513,7 +532,7 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev) fwp = rb_entry(p, struct fw_page, rb_node); err = reclaim_pages(dev, fwp->func_id, optimal_reclaimed_pages(), - &nclaimed); + &nclaimed, mlx5_core_is_ecpf(dev)); if (err) { mlx5_core_warn(dev, "failed reclaiming pages (%d)\n", @@ -535,6 +554,9 @@ int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev) WARN(dev->priv.vfs_pages, "VFs FW pages counter is %d after reclaiming all pages\n", dev->priv.vfs_pages); + WARN(dev->priv.peer_pf_pages, + "Peer PF FW pages counter is %d after reclaiming all pages\n", + dev->priv.peer_pf_pages); return 0; } @@ -567,10 +589,10 @@ void mlx5_pagealloc_stop(struct mlx5_core_dev *dev) flush_workqueue(dev->priv.pg_wq); } -int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev) +int mlx5_wait_for_pages(struct mlx5_core_dev *dev, int *pages) { unsigned long end = jiffies + msecs_to_jiffies(MAX_RECLAIM_VFS_PAGES_TIME_MSECS); - int prev_vfs_pages = dev->priv.vfs_pages; + int prev_pages = *pages; /* In case of internal error we will free the pages manually later */ if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) { @@ -578,16 +600,16 @@ int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev) return 0; } - mlx5_core_dbg(dev, "Waiting for %d pages from %s\n", prev_vfs_pages, + mlx5_core_dbg(dev, "Waiting for %d pages from %s\n", prev_pages, dev->priv.name); - while (dev->priv.vfs_pages) { + while (*pages) { if (time_after(jiffies, end)) { - mlx5_core_warn(dev, "aborting while there are %d pending pages\n", dev->priv.vfs_pages); + mlx5_core_warn(dev, "aborting while there are %d pending pages\n", *pages); return -ETIMEDOUT; } - if (dev->priv.vfs_pages < prev_vfs_pages) { + if (*pages < prev_pages) { end = jiffies + msecs_to_jiffies(MAX_RECLAIM_VFS_PAGES_TIME_MSECS); - prev_vfs_pages = dev->priv.vfs_pages; + prev_pages = *pages; } msleep(50); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index 2b82f35f4c35..b81542820528 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -30,10 +30,7 @@ * SOFTWARE. */ -#include <linux/module.h> -#include <linux/mlx5/driver.h> #include <linux/mlx5/port.h> -#include <linux/mlx5/cmd.h> #include "mlx5_core.h" int mlx5_core_access_reg(struct mlx5_core_dev *dev, void *data_in, @@ -157,44 +154,6 @@ int mlx5_set_port_beacon(struct mlx5_core_dev *dev, u16 beacon_duration) sizeof(out), MLX5_REG_MLCR, 0, 1); } -int mlx5_query_port_proto_cap(struct mlx5_core_dev *dev, - u32 *proto_cap, int proto_mask) -{ - u32 out[MLX5_ST_SZ_DW(ptys_reg)]; - int err; - - err = mlx5_query_port_ptys(dev, out, sizeof(out), proto_mask, 1); - if (err) - return err; - - if (proto_mask == MLX5_PTYS_EN) - *proto_cap = MLX5_GET(ptys_reg, out, eth_proto_capability); - else - *proto_cap = MLX5_GET(ptys_reg, out, ib_proto_capability); - - return 0; -} -EXPORT_SYMBOL_GPL(mlx5_query_port_proto_cap); - -int mlx5_query_port_proto_admin(struct mlx5_core_dev *dev, - u32 *proto_admin, int proto_mask) -{ - u32 out[MLX5_ST_SZ_DW(ptys_reg)]; - int err; - - err = mlx5_query_port_ptys(dev, out, sizeof(out), proto_mask, 1); - if (err) - return err; - - if (proto_mask == MLX5_PTYS_EN) - *proto_admin = MLX5_GET(ptys_reg, out, eth_proto_admin); - else - *proto_admin = MLX5_GET(ptys_reg, out, ib_proto_admin); - - return 0; -} -EXPORT_SYMBOL_GPL(mlx5_query_port_proto_admin); - int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev, u8 *link_width_oper, u8 local_port) { @@ -211,23 +170,6 @@ int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev, } EXPORT_SYMBOL_GPL(mlx5_query_port_link_width_oper); -int mlx5_query_port_eth_proto_oper(struct mlx5_core_dev *dev, - u32 *proto_oper, u8 local_port) -{ - u32 out[MLX5_ST_SZ_DW(ptys_reg)]; - int err; - - err = mlx5_query_port_ptys(dev, out, sizeof(out), MLX5_PTYS_EN, - local_port); - if (err) - return err; - - *proto_oper = MLX5_GET(ptys_reg, out, eth_proto_oper); - - return 0; -} -EXPORT_SYMBOL(mlx5_query_port_eth_proto_oper); - int mlx5_query_port_ib_proto_oper(struct mlx5_core_dev *dev, u8 *proto_oper, u8 local_port) { @@ -245,35 +187,6 @@ int mlx5_query_port_ib_proto_oper(struct mlx5_core_dev *dev, } EXPORT_SYMBOL(mlx5_query_port_ib_proto_oper); -int mlx5_set_port_ptys(struct mlx5_core_dev *dev, bool an_disable, - u32 proto_admin, int proto_mask) -{ - u32 out[MLX5_ST_SZ_DW(ptys_reg)]; - u32 in[MLX5_ST_SZ_DW(ptys_reg)]; - u8 an_disable_admin; - u8 an_disable_cap; - u8 an_status; - - mlx5_query_port_autoneg(dev, proto_mask, &an_status, - &an_disable_cap, &an_disable_admin); - if (!an_disable_cap && an_disable) - return -EPERM; - - memset(in, 0, sizeof(in)); - - MLX5_SET(ptys_reg, in, local_port, 1); - MLX5_SET(ptys_reg, in, an_disable_admin, an_disable); - MLX5_SET(ptys_reg, in, proto_mask, proto_mask); - if (proto_mask == MLX5_PTYS_EN) - MLX5_SET(ptys_reg, in, eth_proto_admin, proto_admin); - else - MLX5_SET(ptys_reg, in, ib_proto_admin, proto_admin); - - return mlx5_core_access_reg(dev, in, sizeof(in), out, - sizeof(out), MLX5_REG_PTYS, 0, 1); -} -EXPORT_SYMBOL_GPL(mlx5_set_port_ptys); - /* This function should be used after setting a port register only */ void mlx5_toggle_port_link(struct mlx5_core_dev *dev) { @@ -606,25 +519,6 @@ int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx, u8 *pfc_en_rx) } EXPORT_SYMBOL_GPL(mlx5_query_port_pfc); -void mlx5_query_port_autoneg(struct mlx5_core_dev *dev, int proto_mask, - u8 *an_status, - u8 *an_disable_cap, u8 *an_disable_admin) -{ - u32 out[MLX5_ST_SZ_DW(ptys_reg)]; - - *an_status = 0; - *an_disable_cap = 0; - *an_disable_admin = 0; - - if (mlx5_query_port_ptys(dev, out, sizeof(out), proto_mask, 1)) - return; - - *an_status = MLX5_GET(ptys_reg, out, an_status); - *an_disable_cap = MLX5_GET(ptys_reg, out, an_disable_cap); - *an_disable_admin = MLX5_GET(ptys_reg, out, an_disable_admin); -} -EXPORT_SYMBOL_GPL(mlx5_query_port_autoneg); - int mlx5_max_tc(struct mlx5_core_dev *mdev) { u8 num_tc = MLX5_CAP_GEN(mdev, max_tc) ? : 8; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c index 388f205a497f..370ca94b6775 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c @@ -44,14 +44,15 @@ static struct mlx5_core_rsc_common * mlx5_get_rsc(struct mlx5_qp_table *table, u32 rsn) { struct mlx5_core_rsc_common *common; + unsigned long flags; - spin_lock(&table->lock); + spin_lock_irqsave(&table->lock, flags); common = radix_tree_lookup(&table->tree, rsn); if (common) atomic_inc(&common->refcount); - spin_unlock(&table->lock); + spin_unlock_irqrestore(&table->lock, flags); return common; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c index 6e178030d8fb..7b23fa8d2d60 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c @@ -147,7 +147,7 @@ out: if (MLX5_ESWITCH_MANAGER(dev)) mlx5_eswitch_disable_sriov(dev->priv.eswitch); - if (mlx5_wait_for_vf_pages(dev)) + if (mlx5_wait_for_pages(dev, &dev->priv.vfs_pages)) mlx5_core_warn(dev, "timeout reclaiming VFs pages\n"); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index 9b150ce9d315..ef95feca9961 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -64,7 +64,7 @@ u8 mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport) } int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod, - u16 vport, u8 state) + u16 vport, u8 other_vport, u8 state) { u32 in[MLX5_ST_SZ_DW(modify_vport_state_in)] = {0}; u32 out[MLX5_ST_SZ_DW(modify_vport_state_out)] = {0}; @@ -73,8 +73,7 @@ int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod, MLX5_CMD_OP_MODIFY_VPORT_STATE); MLX5_SET(modify_vport_state_in, in, op_mod, opmod); MLX5_SET(modify_vport_state_in, in, vport_number, vport); - if (vport) - MLX5_SET(modify_vport_state_in, in, other_vport, 1); + MLX5_SET(modify_vport_state_in, in, other_vport, other_vport); MLX5_SET(modify_vport_state_in, in, admin_state, state); return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); @@ -255,7 +254,7 @@ int mlx5_modify_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 mtu) EXPORT_SYMBOL_GPL(mlx5_modify_nic_vport_mtu); int mlx5_query_nic_vport_mac_list(struct mlx5_core_dev *dev, - u32 vport, + u16 vport, enum mlx5_list_type list_type, u8 addr_list[][ETH_ALEN], int *list_size) @@ -373,7 +372,7 @@ int mlx5_modify_nic_vport_mac_list(struct mlx5_core_dev *dev, EXPORT_SYMBOL_GPL(mlx5_modify_nic_vport_mac_list); int mlx5_query_nic_vport_vlans(struct mlx5_core_dev *dev, - u32 vport, + u16 vport, u16 vlans[], int *size) { @@ -526,7 +525,7 @@ int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid) EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_node_guid); int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev, - u32 vport, u64 node_guid) + u16 vport, u64 node_guid) { int inlen = MLX5_ST_SZ_BYTES(modify_nic_vport_context_in); void *nic_vport_context; @@ -827,7 +826,7 @@ int mlx5_query_hca_vport_node_guid(struct mlx5_core_dev *dev, EXPORT_SYMBOL_GPL(mlx5_query_hca_vport_node_guid); int mlx5_query_nic_vport_promisc(struct mlx5_core_dev *mdev, - u32 vport, + u16 vport, int *promisc_uc, int *promisc_mc, int *promisc_all) @@ -1057,7 +1056,7 @@ free: EXPORT_SYMBOL_GPL(mlx5_core_query_vport_counter); int mlx5_query_vport_down_stats(struct mlx5_core_dev *mdev, u16 vport, - u64 *rx_discard_vport_down, + u8 other_vport, u64 *rx_discard_vport_down, u64 *tx_discard_vport_down) { u32 out[MLX5_ST_SZ_DW(query_vnic_env_out)] = {0}; @@ -1068,8 +1067,7 @@ int mlx5_query_vport_down_stats(struct mlx5_core_dev *mdev, u16 vport, MLX5_CMD_OP_QUERY_VNIC_ENV); MLX5_SET(query_vnic_env_in, in, op_mod, 0); MLX5_SET(query_vnic_env_in, in, vport_number, vport); - if (vport) - MLX5_SET(query_vnic_env_in, in, other_vport, 1); + MLX5_SET(query_vnic_env_in, in, other_vport, other_vport); err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); if (err) diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile index bbf45f10c208..a01d15546e37 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Makefile +++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_MLXSW_CORE) += mlxsw_core.o mlxsw_core-objs := core.o core_acl_flex_keys.o \ - core_acl_flex_actions.o + core_acl_flex_actions.o core_env.o mlxsw_core-$(CONFIG_MLXSW_CORE_HWMON) += core_hwmon.o mlxsw_core-$(CONFIG_MLXSW_CORE_THERMAL) += core_thermal.o obj-$(CONFIG_MLXSW_PCI) += mlxsw_pci.o diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index ddedf8ab5b64..b505d3858235 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -1062,6 +1062,9 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, goto err_driver_init; } + if (mlxsw_driver->params_register && !reload) + devlink_params_publish(devlink); + return 0; err_driver_init: @@ -1131,6 +1134,8 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core, return; } + if (mlxsw_core->driver->params_unregister && !reload) + devlink_params_unpublish(devlink); if (mlxsw_core->driver->fini) mlxsw_core->driver->fini(mlxsw_core); mlxsw_thermal_fini(mlxsw_core->thermal); @@ -1460,13 +1465,17 @@ static int mlxsw_reg_trans_wait(struct mlxsw_reg_trans *trans) if (trans->retries) dev_warn(mlxsw_core->bus_info->dev, "EMAD retries (%d/%d) (tid=%llx)\n", trans->retries, MLXSW_EMAD_MAX_RETRY, trans->tid); - if (err) + if (err) { dev_err(mlxsw_core->bus_info->dev, "EMAD reg access failed (tid=%llx,reg_id=%x(%s),type=%s,status=%x(%s))\n", trans->tid, trans->reg->id, mlxsw_reg_id_str(trans->reg->id), mlxsw_core_reg_access_type_str(trans->type), trans->emad_status, mlxsw_emad_op_tlv_status_str(trans->emad_status)); + trace_devlink_hwerr(priv_to_devlink(mlxsw_core), + trans->emad_status, + mlxsw_emad_op_tlv_status_str(trans->emad_status)); + } list_del(&trans->bulk_list); kfree_rcu(trans, rcu); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h index 4e114f35ee0d..cd0c6aa0dff9 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core.h @@ -344,6 +344,7 @@ struct mlxsw_bus_info { struct mlxsw_fw_rev fw_rev; u8 vsd[MLXSW_CMD_BOARDINFO_VSD_LEN]; u8 psid[MLXSW_CMD_BOARDINFO_PSID_LEN]; + u8 low_frequency; }; struct mlxsw_hwmon; @@ -394,4 +395,9 @@ static inline void mlxsw_thermal_fini(struct mlxsw_thermal *thermal) #endif +enum mlxsw_devlink_param_id { + MLXSW_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX, + MLXSW_DEVLINK_PARAM_ID_ACL_REGION_REHASH_INTERVAL, +}; + #endif diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.c b/drivers/net/ethernet/mellanox/mlxsw/core_env.c new file mode 100644 index 000000000000..160d6cd164f4 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.c @@ -0,0 +1,117 @@ +// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 +/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */ + +#include <linux/kernel.h> +#include <linux/err.h> + +#include "core.h" +#include "core_env.h" +#include "item.h" +#include "reg.h" + +static int mlxsw_env_validate_cable_ident(struct mlxsw_core *core, int id, + bool *qsfp) +{ + char eeprom_tmp[MLXSW_REG_MCIA_EEPROM_SIZE]; + char mcia_pl[MLXSW_REG_MCIA_LEN]; + u8 ident; + int err; + + mlxsw_reg_mcia_pack(mcia_pl, id, 0, MLXSW_REG_MCIA_PAGE0_LO_OFF, 0, 1, + MLXSW_REG_MCIA_I2C_ADDR_LOW); + err = mlxsw_reg_query(core, MLXSW_REG(mcia), mcia_pl); + if (err) + return err; + mlxsw_reg_mcia_eeprom_memcpy_from(mcia_pl, eeprom_tmp); + ident = eeprom_tmp[0]; + switch (ident) { + case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_SFP: + *qsfp = false; + break; + case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP: /* fall-through */ + case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_PLUS: /* fall-through */ + case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP28: /* fall-through */ + case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_DD: + *qsfp = true; + break; + default: + return -EINVAL; + } + + return 0; +} + +int mlxsw_env_module_temp_thresholds_get(struct mlxsw_core *core, int module, + int off, int *temp) +{ + char eeprom_tmp[MLXSW_REG_MCIA_EEPROM_SIZE]; + union { + u8 buf[MLXSW_REG_MCIA_TH_ITEM_SIZE]; + u16 temp; + } temp_thresh; + char mcia_pl[MLXSW_REG_MCIA_LEN] = {0}; + char mtbr_pl[MLXSW_REG_MTBR_LEN] = {0}; + u16 module_temp; + bool qsfp; + int err; + + mlxsw_reg_mtbr_pack(mtbr_pl, MLXSW_REG_MTBR_BASE_MODULE_INDEX + module, + 1); + err = mlxsw_reg_query(core, MLXSW_REG(mtbr), mtbr_pl); + if (err) + return err; + + /* Don't read temperature thresholds for module with no valid info. */ + mlxsw_reg_mtbr_temp_unpack(mtbr_pl, 0, &module_temp, NULL); + switch (module_temp) { + case MLXSW_REG_MTBR_BAD_SENS_INFO: /* fall-through */ + case MLXSW_REG_MTBR_NO_CONN: /* fall-through */ + case MLXSW_REG_MTBR_NO_TEMP_SENS: /* fall-through */ + case MLXSW_REG_MTBR_INDEX_NA: + *temp = 0; + return 0; + default: + /* Do not consider thresholds for zero temperature. */ + if (!MLXSW_REG_MTMP_TEMP_TO_MC(module_temp)) { + *temp = 0; + return 0; + } + break; + } + + /* Read Free Side Device Temperature Thresholds from page 03h + * (MSB at lower byte address). + * Bytes: + * 128-129 - Temp High Alarm (SFP_TEMP_HIGH_ALARM); + * 130-131 - Temp Low Alarm (SFP_TEMP_LOW_ALARM); + * 132-133 - Temp High Warning (SFP_TEMP_HIGH_WARN); + * 134-135 - Temp Low Warning (SFP_TEMP_LOW_WARN); + */ + + /* Validate module identifier value. */ + err = mlxsw_env_validate_cable_ident(core, module, &qsfp); + if (err) + return err; + + if (qsfp) + mlxsw_reg_mcia_pack(mcia_pl, module, 0, + MLXSW_REG_MCIA_TH_PAGE_NUM, + MLXSW_REG_MCIA_TH_PAGE_OFF + off, + MLXSW_REG_MCIA_TH_ITEM_SIZE, + MLXSW_REG_MCIA_I2C_ADDR_LOW); + else + mlxsw_reg_mcia_pack(mcia_pl, module, 0, + MLXSW_REG_MCIA_PAGE0_LO, + off, MLXSW_REG_MCIA_TH_ITEM_SIZE, + MLXSW_REG_MCIA_I2C_ADDR_HIGH); + + err = mlxsw_reg_query(core, MLXSW_REG(mcia), mcia_pl); + if (err) + return err; + + mlxsw_reg_mcia_eeprom_memcpy_from(mcia_pl, eeprom_tmp); + memcpy(temp_thresh.buf, eeprom_tmp, MLXSW_REG_MCIA_TH_ITEM_SIZE); + *temp = temp_thresh.temp * 1000; + + return 0; +} diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_env.h b/drivers/net/ethernet/mellanox/mlxsw/core_env.h new file mode 100644 index 000000000000..6dbdf63f3ee1 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxsw/core_env.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */ +/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */ + +#ifndef _MLXSW_CORE_ENV_H +#define _MLXSW_CORE_ENV_H + +int mlxsw_env_module_temp_thresholds_get(struct mlxsw_core *core, int module, + int off, int *temp); + +#endif diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c index e04e8162aa14..6956bbebe2f1 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c @@ -7,8 +7,10 @@ #include <linux/sysfs.h> #include <linux/hwmon.h> #include <linux/err.h> +#include <linux/sfp.h> #include "core.h" +#include "core_env.h" #define MLXSW_HWMON_TEMP_SENSOR_MAX_COUNT 127 #define MLXSW_HWMON_ATTR_COUNT (MLXSW_HWMON_TEMP_SENSOR_MAX_COUNT * 4 + \ @@ -30,6 +32,7 @@ struct mlxsw_hwmon { struct attribute *attrs[MLXSW_HWMON_ATTR_COUNT + 1]; struct mlxsw_hwmon_attr hwmon_attrs[MLXSW_HWMON_ATTR_COUNT]; unsigned int attrs_count; + u8 sensor_count; }; static ssize_t mlxsw_hwmon_temp_show(struct device *dev, @@ -121,6 +124,27 @@ static ssize_t mlxsw_hwmon_fan_rpm_show(struct device *dev, return sprintf(buf, "%u\n", mlxsw_reg_mfsm_rpm_get(mfsm_pl)); } +static ssize_t mlxsw_hwmon_fan_fault_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct mlxsw_hwmon_attr *mlwsw_hwmon_attr = + container_of(attr, struct mlxsw_hwmon_attr, dev_attr); + struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon; + char fore_pl[MLXSW_REG_FORE_LEN]; + bool fault; + int err; + + err = mlxsw_reg_query(mlxsw_hwmon->core, MLXSW_REG(fore), fore_pl); + if (err) { + dev_err(mlxsw_hwmon->bus_info->dev, "Failed to query fan\n"); + return err; + } + mlxsw_reg_fore_unpack(fore_pl, mlwsw_hwmon_attr->type_index, &fault); + + return sprintf(buf, "%u\n", fault); +} + static ssize_t mlxsw_hwmon_pwm_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -167,12 +191,160 @@ static ssize_t mlxsw_hwmon_pwm_store(struct device *dev, return len; } +static ssize_t mlxsw_hwmon_module_temp_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct mlxsw_hwmon_attr *mlwsw_hwmon_attr = + container_of(attr, struct mlxsw_hwmon_attr, dev_attr); + struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon; + char mtbr_pl[MLXSW_REG_MTBR_LEN] = {0}; + u16 temp; + u8 module; + int err; + + module = mlwsw_hwmon_attr->type_index - mlxsw_hwmon->sensor_count; + mlxsw_reg_mtbr_pack(mtbr_pl, MLXSW_REG_MTBR_BASE_MODULE_INDEX + module, + 1); + err = mlxsw_reg_query(mlxsw_hwmon->core, MLXSW_REG(mtbr), mtbr_pl); + if (err) { + dev_err(dev, "Failed to query module temperature sensor\n"); + return err; + } + + mlxsw_reg_mtbr_temp_unpack(mtbr_pl, 0, &temp, NULL); + /* Update status and temperature cache. */ + switch (temp) { + case MLXSW_REG_MTBR_NO_CONN: /* fall-through */ + case MLXSW_REG_MTBR_NO_TEMP_SENS: /* fall-through */ + case MLXSW_REG_MTBR_INDEX_NA: + temp = 0; + break; + case MLXSW_REG_MTBR_BAD_SENS_INFO: + /* Untrusted cable is connected. Reading temperature from its + * sensor is faulty. + */ + temp = 0; + break; + default: + temp = MLXSW_REG_MTMP_TEMP_TO_MC(temp); + break; + } + + return sprintf(buf, "%u\n", temp); +} + +static ssize_t mlxsw_hwmon_module_temp_fault_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct mlxsw_hwmon_attr *mlwsw_hwmon_attr = + container_of(attr, struct mlxsw_hwmon_attr, dev_attr); + struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon; + char mtbr_pl[MLXSW_REG_MTBR_LEN] = {0}; + u8 module, fault; + u16 temp; + int err; + + module = mlwsw_hwmon_attr->type_index - mlxsw_hwmon->sensor_count; + mlxsw_reg_mtbr_pack(mtbr_pl, MLXSW_REG_MTBR_BASE_MODULE_INDEX + module, + 1); + err = mlxsw_reg_query(mlxsw_hwmon->core, MLXSW_REG(mtbr), mtbr_pl); + if (err) { + dev_err(dev, "Failed to query module temperature sensor\n"); + return err; + } + + mlxsw_reg_mtbr_temp_unpack(mtbr_pl, 0, &temp, NULL); + + /* Update status and temperature cache. */ + switch (temp) { + case MLXSW_REG_MTBR_BAD_SENS_INFO: + /* Untrusted cable is connected. Reading temperature from its + * sensor is faulty. + */ + fault = 1; + break; + case MLXSW_REG_MTBR_NO_CONN: /* fall-through */ + case MLXSW_REG_MTBR_NO_TEMP_SENS: /* fall-through */ + case MLXSW_REG_MTBR_INDEX_NA: + default: + fault = 0; + break; + } + + return sprintf(buf, "%u\n", fault); +} + +static ssize_t +mlxsw_hwmon_module_temp_critical_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct mlxsw_hwmon_attr *mlwsw_hwmon_attr = + container_of(attr, struct mlxsw_hwmon_attr, dev_attr); + struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon; + int temp; + u8 module; + int err; + + module = mlwsw_hwmon_attr->type_index - mlxsw_hwmon->sensor_count; + err = mlxsw_env_module_temp_thresholds_get(mlxsw_hwmon->core, module, + SFP_TEMP_HIGH_WARN, &temp); + if (err) { + dev_err(dev, "Failed to query module temperature thresholds\n"); + return err; + } + + return sprintf(buf, "%u\n", temp); +} + +static ssize_t +mlxsw_hwmon_module_temp_emergency_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct mlxsw_hwmon_attr *mlwsw_hwmon_attr = + container_of(attr, struct mlxsw_hwmon_attr, dev_attr); + struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon; + u8 module; + int temp; + int err; + + module = mlwsw_hwmon_attr->type_index - mlxsw_hwmon->sensor_count; + err = mlxsw_env_module_temp_thresholds_get(mlxsw_hwmon->core, module, + SFP_TEMP_HIGH_ALARM, &temp); + if (err) { + dev_err(dev, "Failed to query module temperature thresholds\n"); + return err; + } + + return sprintf(buf, "%u\n", temp); +} + +static ssize_t +mlxsw_hwmon_module_temp_label_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct mlxsw_hwmon_attr *mlwsw_hwmon_attr = + container_of(attr, struct mlxsw_hwmon_attr, dev_attr); + + return sprintf(buf, "front panel %03u\n", + mlwsw_hwmon_attr->type_index); +} + enum mlxsw_hwmon_attr_type { MLXSW_HWMON_ATTR_TYPE_TEMP, MLXSW_HWMON_ATTR_TYPE_TEMP_MAX, MLXSW_HWMON_ATTR_TYPE_TEMP_RST, MLXSW_HWMON_ATTR_TYPE_FAN_RPM, + MLXSW_HWMON_ATTR_TYPE_FAN_FAULT, MLXSW_HWMON_ATTR_TYPE_PWM, + MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE, + MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_FAULT, + MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_CRIT, + MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_EMERG, + MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_LABEL, }; static void mlxsw_hwmon_attr_add(struct mlxsw_hwmon *mlxsw_hwmon, @@ -209,6 +381,12 @@ static void mlxsw_hwmon_attr_add(struct mlxsw_hwmon *mlxsw_hwmon, snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name), "fan%u_input", num + 1); break; + case MLXSW_HWMON_ATTR_TYPE_FAN_FAULT: + mlxsw_hwmon_attr->dev_attr.show = mlxsw_hwmon_fan_fault_show; + mlxsw_hwmon_attr->dev_attr.attr.mode = 0444; + snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name), + "fan%u_fault", num + 1); + break; case MLXSW_HWMON_ATTR_TYPE_PWM: mlxsw_hwmon_attr->dev_attr.show = mlxsw_hwmon_pwm_show; mlxsw_hwmon_attr->dev_attr.store = mlxsw_hwmon_pwm_store; @@ -216,6 +394,40 @@ static void mlxsw_hwmon_attr_add(struct mlxsw_hwmon *mlxsw_hwmon, snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name), "pwm%u", num + 1); break; + case MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE: + mlxsw_hwmon_attr->dev_attr.show = mlxsw_hwmon_module_temp_show; + mlxsw_hwmon_attr->dev_attr.attr.mode = 0444; + snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name), + "temp%u_input", num + 1); + break; + case MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_FAULT: + mlxsw_hwmon_attr->dev_attr.show = + mlxsw_hwmon_module_temp_fault_show; + mlxsw_hwmon_attr->dev_attr.attr.mode = 0444; + snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name), + "temp%u_fault", num + 1); + break; + case MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_CRIT: + mlxsw_hwmon_attr->dev_attr.show = + mlxsw_hwmon_module_temp_critical_show; + mlxsw_hwmon_attr->dev_attr.attr.mode = 0444; + snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name), + "temp%u_crit", num + 1); + break; + case MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_EMERG: + mlxsw_hwmon_attr->dev_attr.show = + mlxsw_hwmon_module_temp_emergency_show; + mlxsw_hwmon_attr->dev_attr.attr.mode = 0444; + snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name), + "temp%u_emergency", num + 1); + break; + case MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_LABEL: + mlxsw_hwmon_attr->dev_attr.show = + mlxsw_hwmon_module_temp_label_show; + mlxsw_hwmon_attr->dev_attr.attr.mode = 0444; + snprintf(mlxsw_hwmon_attr->name, sizeof(mlxsw_hwmon_attr->name), + "temp%u_label", num + 1); + break; default: WARN_ON(1); } @@ -233,7 +445,6 @@ static int mlxsw_hwmon_temp_init(struct mlxsw_hwmon *mlxsw_hwmon) { char mtcap_pl[MLXSW_REG_MTCAP_LEN] = {0}; char mtmp_pl[MLXSW_REG_MTMP_LEN]; - u8 sensor_count; int i; int err; @@ -242,8 +453,8 @@ static int mlxsw_hwmon_temp_init(struct mlxsw_hwmon *mlxsw_hwmon) dev_err(mlxsw_hwmon->bus_info->dev, "Failed to get number of temp sensors\n"); return err; } - sensor_count = mlxsw_reg_mtcap_sensor_count_get(mtcap_pl); - for (i = 0; i < sensor_count; i++) { + mlxsw_hwmon->sensor_count = mlxsw_reg_mtcap_sensor_count_get(mtcap_pl); + for (i = 0; i < mlxsw_hwmon->sensor_count; i++) { mlxsw_reg_mtmp_pack(mtmp_pl, i, true, true); err = mlxsw_reg_write(mlxsw_hwmon->core, MLXSW_REG(mtmp), mtmp_pl); @@ -280,10 +491,14 @@ static int mlxsw_hwmon_fans_init(struct mlxsw_hwmon *mlxsw_hwmon) mlxsw_reg_mfcr_unpack(mfcr_pl, &freq, &tacho_active, &pwm_active); num = 0; for (type_index = 0; type_index < MLXSW_MFCR_TACHOS_MAX; type_index++) { - if (tacho_active & BIT(type_index)) + if (tacho_active & BIT(type_index)) { mlxsw_hwmon_attr_add(mlxsw_hwmon, MLXSW_HWMON_ATTR_TYPE_FAN_RPM, + type_index, num); + mlxsw_hwmon_attr_add(mlxsw_hwmon, + MLXSW_HWMON_ATTR_TYPE_FAN_FAULT, type_index, num++); + } } num = 0; for (type_index = 0; type_index < MLXSW_MFCR_PWMS_MAX; type_index++) { @@ -295,6 +510,53 @@ static int mlxsw_hwmon_fans_init(struct mlxsw_hwmon *mlxsw_hwmon) return 0; } +static int mlxsw_hwmon_module_init(struct mlxsw_hwmon *mlxsw_hwmon) +{ + unsigned int module_count = mlxsw_core_max_ports(mlxsw_hwmon->core); + char pmlp_pl[MLXSW_REG_PMLP_LEN] = {0}; + int i, index; + u8 width; + int err; + + /* Add extra attributes for module temperature. Sensor index is + * assigned to sensor_count value, while all indexed before + * sensor_count are already utilized by the sensors connected through + * mtmp register by mlxsw_hwmon_temp_init(). + */ + index = mlxsw_hwmon->sensor_count; + for (i = 1; i < module_count; i++) { + mlxsw_reg_pmlp_pack(pmlp_pl, i); + err = mlxsw_reg_query(mlxsw_hwmon->core, MLXSW_REG(pmlp), + pmlp_pl); + if (err) { + dev_err(mlxsw_hwmon->bus_info->dev, "Failed to read module index %d\n", + i); + return err; + } + width = mlxsw_reg_pmlp_width_get(pmlp_pl); + if (!width) + continue; + mlxsw_hwmon_attr_add(mlxsw_hwmon, + MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE, index, + index); + mlxsw_hwmon_attr_add(mlxsw_hwmon, + MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_FAULT, + index, index); + mlxsw_hwmon_attr_add(mlxsw_hwmon, + MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_CRIT, + index, index); + mlxsw_hwmon_attr_add(mlxsw_hwmon, + MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_EMERG, + index, index); + mlxsw_hwmon_attr_add(mlxsw_hwmon, + MLXSW_HWMON_ATTR_TYPE_TEMP_MODULE_LABEL, + index, index); + index++; + } + + return 0; +} + int mlxsw_hwmon_init(struct mlxsw_core *mlxsw_core, const struct mlxsw_bus_info *mlxsw_bus_info, struct mlxsw_hwmon **p_hwmon) @@ -317,6 +579,10 @@ int mlxsw_hwmon_init(struct mlxsw_core *mlxsw_core, if (err) goto err_fans_init; + err = mlxsw_hwmon_module_init(mlxsw_hwmon); + if (err) + goto err_temp_module_init; + mlxsw_hwmon->groups[0] = &mlxsw_hwmon->group; mlxsw_hwmon->group.attrs = mlxsw_hwmon->attrs; @@ -333,6 +599,7 @@ int mlxsw_hwmon_init(struct mlxsw_core *mlxsw_core, return 0; err_hwmon_register: +err_temp_module_init: err_fans_init: err_temp_init: kfree(mlxsw_hwmon); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c index 61f897b40f82..0b85c7252f9e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c @@ -9,11 +9,20 @@ #include <linux/sysfs.h> #include <linux/thermal.h> #include <linux/err.h> +#include <linux/sfp.h> #include "core.h" +#include "core_env.h" #define MLXSW_THERMAL_POLL_INT 1000 /* ms */ -#define MLXSW_THERMAL_MAX_TEMP 110000 /* 110C */ +#define MLXSW_THERMAL_SLOW_POLL_INT 20000 /* ms */ +#define MLXSW_THERMAL_ASIC_TEMP_NORM 75000 /* 75C */ +#define MLXSW_THERMAL_ASIC_TEMP_HIGH 85000 /* 85C */ +#define MLXSW_THERMAL_ASIC_TEMP_HOT 105000 /* 105C */ +#define MLXSW_THERMAL_ASIC_TEMP_CRIT 110000 /* 110C */ +#define MLXSW_THERMAL_HYSTERESIS_TEMP 5000 /* 5C */ +#define MLXSW_THERMAL_MODULE_TEMP_SHIFT (MLXSW_THERMAL_HYSTERESIS_TEMP * 2) +#define MLXSW_THERMAL_ZONE_MAX_NAME 16 #define MLXSW_THERMAL_MAX_STATE 10 #define MLXSW_THERMAL_MAX_DUTY 255 /* Minimum and maximum fan allowed speed in percent: from 20% to 100%. Values @@ -26,9 +35,22 @@ #define MLXSW_THERMAL_SPEED_MAX (MLXSW_THERMAL_MAX_STATE * 2) #define MLXSW_THERMAL_SPEED_MIN_LEVEL 2 /* 20% */ +/* External cooling devices, allowed for binding to mlxsw thermal zones. */ +static char * const mlxsw_thermal_external_allowed_cdev[] = { + "mlxreg_fan", +}; + +enum mlxsw_thermal_trips { + MLXSW_THERMAL_TEMP_TRIP_NORM, + MLXSW_THERMAL_TEMP_TRIP_HIGH, + MLXSW_THERMAL_TEMP_TRIP_HOT, + MLXSW_THERMAL_TEMP_TRIP_CRIT, +}; + struct mlxsw_thermal_trip { int type; int temp; + int hyst; int min_state; int max_state; }; @@ -36,32 +58,29 @@ struct mlxsw_thermal_trip { static const struct mlxsw_thermal_trip default_thermal_trips[] = { { /* In range - 0-40% PWM */ .type = THERMAL_TRIP_ACTIVE, - .temp = 75000, + .temp = MLXSW_THERMAL_ASIC_TEMP_NORM, + .hyst = MLXSW_THERMAL_HYSTERESIS_TEMP, .min_state = 0, .max_state = (4 * MLXSW_THERMAL_MAX_STATE) / 10, }, - { /* High - 40-100% PWM */ - .type = THERMAL_TRIP_ACTIVE, - .temp = 80000, - .min_state = (4 * MLXSW_THERMAL_MAX_STATE) / 10, - .max_state = MLXSW_THERMAL_MAX_STATE, - }, { - /* Very high - 100% PWM */ + /* In range - 40-100% PWM */ .type = THERMAL_TRIP_ACTIVE, - .temp = 85000, - .min_state = MLXSW_THERMAL_MAX_STATE, + .temp = MLXSW_THERMAL_ASIC_TEMP_HIGH, + .hyst = MLXSW_THERMAL_HYSTERESIS_TEMP, + .min_state = (4 * MLXSW_THERMAL_MAX_STATE) / 10, .max_state = MLXSW_THERMAL_MAX_STATE, }, { /* Warning */ .type = THERMAL_TRIP_HOT, - .temp = 105000, + .temp = MLXSW_THERMAL_ASIC_TEMP_HOT, + .hyst = MLXSW_THERMAL_HYSTERESIS_TEMP, .min_state = MLXSW_THERMAL_MAX_STATE, .max_state = MLXSW_THERMAL_MAX_STATE, }, { /* Critical - soft poweroff */ .type = THERMAL_TRIP_CRITICAL, - .temp = MLXSW_THERMAL_MAX_TEMP, + .temp = MLXSW_THERMAL_ASIC_TEMP_CRIT, .min_state = MLXSW_THERMAL_MAX_STATE, .max_state = MLXSW_THERMAL_MAX_STATE, } @@ -72,14 +91,27 @@ static const struct mlxsw_thermal_trip default_thermal_trips[] = { /* Make sure all trips are writable */ #define MLXSW_THERMAL_TRIP_MASK (BIT(MLXSW_THERMAL_NUM_TRIPS) - 1) +struct mlxsw_thermal; + +struct mlxsw_thermal_module { + struct mlxsw_thermal *parent; + struct thermal_zone_device *tzdev; + struct mlxsw_thermal_trip trips[MLXSW_THERMAL_NUM_TRIPS]; + enum thermal_device_mode mode; + int module; +}; + struct mlxsw_thermal { struct mlxsw_core *core; const struct mlxsw_bus_info *bus_info; struct thermal_zone_device *tzdev; + int polling_delay; struct thermal_cooling_device *cdevs[MLXSW_MFCR_PWMS_MAX]; u8 cooling_levels[MLXSW_THERMAL_MAX_STATE + 1]; struct mlxsw_thermal_trip trips[MLXSW_THERMAL_NUM_TRIPS]; enum thermal_device_mode mode; + struct mlxsw_thermal_module *tz_module_arr; + unsigned int tz_module_num; }; static inline u8 mlxsw_state_to_duty(int state) @@ -103,9 +135,67 @@ static int mlxsw_get_cooling_device_idx(struct mlxsw_thermal *thermal, if (thermal->cdevs[i] == cdev) return i; + /* Allow mlxsw thermal zone binding to an external cooling device */ + for (i = 0; i < ARRAY_SIZE(mlxsw_thermal_external_allowed_cdev); i++) { + if (strnstr(cdev->type, mlxsw_thermal_external_allowed_cdev[i], + sizeof(cdev->type))) + return 0; + } + return -ENODEV; } +static void +mlxsw_thermal_module_trips_reset(struct mlxsw_thermal_module *tz) +{ + tz->trips[MLXSW_THERMAL_TEMP_TRIP_NORM].temp = 0; + tz->trips[MLXSW_THERMAL_TEMP_TRIP_HIGH].temp = 0; + tz->trips[MLXSW_THERMAL_TEMP_TRIP_HOT].temp = 0; + tz->trips[MLXSW_THERMAL_TEMP_TRIP_CRIT].temp = 0; +} + +static int +mlxsw_thermal_module_trips_update(struct device *dev, struct mlxsw_core *core, + struct mlxsw_thermal_module *tz) +{ + int crit_temp, emerg_temp; + int err; + + err = mlxsw_env_module_temp_thresholds_get(core, tz->module, + SFP_TEMP_HIGH_WARN, + &crit_temp); + if (err) + return err; + + err = mlxsw_env_module_temp_thresholds_get(core, tz->module, + SFP_TEMP_HIGH_ALARM, + &emerg_temp); + if (err) + return err; + + /* According to the system thermal requirements, the thermal zones are + * defined with four trip points. The critical and emergency + * temperature thresholds, provided by QSFP module are set as "active" + * and "hot" trip points, "normal" and "critical" trip points are + * derived from "active" and "hot" by subtracting or adding double + * hysteresis value. + */ + if (crit_temp >= MLXSW_THERMAL_MODULE_TEMP_SHIFT) + tz->trips[MLXSW_THERMAL_TEMP_TRIP_NORM].temp = crit_temp - + MLXSW_THERMAL_MODULE_TEMP_SHIFT; + else + tz->trips[MLXSW_THERMAL_TEMP_TRIP_NORM].temp = crit_temp; + tz->trips[MLXSW_THERMAL_TEMP_TRIP_HIGH].temp = crit_temp; + tz->trips[MLXSW_THERMAL_TEMP_TRIP_HOT].temp = emerg_temp; + if (emerg_temp > crit_temp) + tz->trips[MLXSW_THERMAL_TEMP_TRIP_CRIT].temp = emerg_temp + + MLXSW_THERMAL_MODULE_TEMP_SHIFT; + else + tz->trips[MLXSW_THERMAL_TEMP_TRIP_CRIT].temp = emerg_temp; + + return 0; +} + static int mlxsw_thermal_bind(struct thermal_zone_device *tzdev, struct thermal_cooling_device *cdev) { @@ -172,7 +262,7 @@ static int mlxsw_thermal_set_mode(struct thermal_zone_device *tzdev, mutex_lock(&tzdev->lock); if (mode == THERMAL_DEVICE_ENABLED) - tzdev->polling_delay = MLXSW_THERMAL_POLL_INT; + tzdev->polling_delay = thermal->polling_delay; else tzdev->polling_delay = 0; @@ -237,13 +327,31 @@ static int mlxsw_thermal_set_trip_temp(struct thermal_zone_device *tzdev, struct mlxsw_thermal *thermal = tzdev->devdata; if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS || - temp > MLXSW_THERMAL_MAX_TEMP) + temp > MLXSW_THERMAL_ASIC_TEMP_CRIT) return -EINVAL; thermal->trips[trip].temp = temp; return 0; } +static int mlxsw_thermal_get_trip_hyst(struct thermal_zone_device *tzdev, + int trip, int *p_hyst) +{ + struct mlxsw_thermal *thermal = tzdev->devdata; + + *p_hyst = thermal->trips[trip].hyst; + return 0; +} + +static int mlxsw_thermal_set_trip_hyst(struct thermal_zone_device *tzdev, + int trip, int hyst) +{ + struct mlxsw_thermal *thermal = tzdev->devdata; + + thermal->trips[trip].hyst = hyst; + return 0; +} + static struct thermal_zone_device_ops mlxsw_thermal_ops = { .bind = mlxsw_thermal_bind, .unbind = mlxsw_thermal_unbind, @@ -253,6 +361,206 @@ static struct thermal_zone_device_ops mlxsw_thermal_ops = { .get_trip_type = mlxsw_thermal_get_trip_type, .get_trip_temp = mlxsw_thermal_get_trip_temp, .set_trip_temp = mlxsw_thermal_set_trip_temp, + .get_trip_hyst = mlxsw_thermal_get_trip_hyst, + .set_trip_hyst = mlxsw_thermal_set_trip_hyst, +}; + +static int mlxsw_thermal_module_bind(struct thermal_zone_device *tzdev, + struct thermal_cooling_device *cdev) +{ + struct mlxsw_thermal_module *tz = tzdev->devdata; + struct mlxsw_thermal *thermal = tz->parent; + int i, j, err; + + /* If the cooling device is one of ours bind it */ + if (mlxsw_get_cooling_device_idx(thermal, cdev) < 0) + return 0; + + for (i = 0; i < MLXSW_THERMAL_NUM_TRIPS; i++) { + const struct mlxsw_thermal_trip *trip = &tz->trips[i]; + + err = thermal_zone_bind_cooling_device(tzdev, i, cdev, + trip->max_state, + trip->min_state, + THERMAL_WEIGHT_DEFAULT); + if (err < 0) + goto err_bind_cooling_device; + } + return 0; + +err_bind_cooling_device: + for (j = i - 1; j >= 0; j--) + thermal_zone_unbind_cooling_device(tzdev, j, cdev); + return err; +} + +static int mlxsw_thermal_module_unbind(struct thermal_zone_device *tzdev, + struct thermal_cooling_device *cdev) +{ + struct mlxsw_thermal_module *tz = tzdev->devdata; + struct mlxsw_thermal *thermal = tz->parent; + int i; + int err; + + /* If the cooling device is one of ours unbind it */ + if (mlxsw_get_cooling_device_idx(thermal, cdev) < 0) + return 0; + + for (i = 0; i < MLXSW_THERMAL_NUM_TRIPS; i++) { + err = thermal_zone_unbind_cooling_device(tzdev, i, cdev); + WARN_ON(err); + } + return err; +} + +static int mlxsw_thermal_module_mode_get(struct thermal_zone_device *tzdev, + enum thermal_device_mode *mode) +{ + struct mlxsw_thermal_module *tz = tzdev->devdata; + + *mode = tz->mode; + + return 0; +} + +static int mlxsw_thermal_module_mode_set(struct thermal_zone_device *tzdev, + enum thermal_device_mode mode) +{ + struct mlxsw_thermal_module *tz = tzdev->devdata; + struct mlxsw_thermal *thermal = tz->parent; + + mutex_lock(&tzdev->lock); + + if (mode == THERMAL_DEVICE_ENABLED) + tzdev->polling_delay = thermal->polling_delay; + else + tzdev->polling_delay = 0; + + mutex_unlock(&tzdev->lock); + + tz->mode = mode; + thermal_zone_device_update(tzdev, THERMAL_EVENT_UNSPECIFIED); + + return 0; +} + +static int mlxsw_thermal_module_temp_get(struct thermal_zone_device *tzdev, + int *p_temp) +{ + struct mlxsw_thermal_module *tz = tzdev->devdata; + struct mlxsw_thermal *thermal = tz->parent; + struct device *dev = thermal->bus_info->dev; + char mtbr_pl[MLXSW_REG_MTBR_LEN]; + u16 temp; + int err; + + /* Read module temperature. */ + mlxsw_reg_mtbr_pack(mtbr_pl, MLXSW_REG_MTBR_BASE_MODULE_INDEX + + tz->module, 1); + err = mlxsw_reg_query(thermal->core, MLXSW_REG(mtbr), mtbr_pl); + if (err) + return err; + + mlxsw_reg_mtbr_temp_unpack(mtbr_pl, 0, &temp, NULL); + /* Update temperature. */ + switch (temp) { + case MLXSW_REG_MTBR_NO_CONN: /* fall-through */ + case MLXSW_REG_MTBR_NO_TEMP_SENS: /* fall-through */ + case MLXSW_REG_MTBR_INDEX_NA: /* fall-through */ + case MLXSW_REG_MTBR_BAD_SENS_INFO: + temp = 0; + break; + default: + temp = MLXSW_REG_MTMP_TEMP_TO_MC(temp); + /* Reset all trip point. */ + mlxsw_thermal_module_trips_reset(tz); + /* Update trip points. */ + err = mlxsw_thermal_module_trips_update(dev, thermal->core, + tz); + if (err) + return err; + break; + } + + *p_temp = (int) temp; + return 0; +} + +static int +mlxsw_thermal_module_trip_type_get(struct thermal_zone_device *tzdev, int trip, + enum thermal_trip_type *p_type) +{ + struct mlxsw_thermal_module *tz = tzdev->devdata; + + if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS) + return -EINVAL; + + *p_type = tz->trips[trip].type; + return 0; +} + +static int +mlxsw_thermal_module_trip_temp_get(struct thermal_zone_device *tzdev, + int trip, int *p_temp) +{ + struct mlxsw_thermal_module *tz = tzdev->devdata; + + if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS) + return -EINVAL; + + *p_temp = tz->trips[trip].temp; + return 0; +} + +static int +mlxsw_thermal_module_trip_temp_set(struct thermal_zone_device *tzdev, + int trip, int temp) +{ + struct mlxsw_thermal_module *tz = tzdev->devdata; + + if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS || + temp > tz->trips[MLXSW_THERMAL_TEMP_TRIP_CRIT].temp) + return -EINVAL; + + tz->trips[trip].temp = temp; + return 0; +} + +static int +mlxsw_thermal_module_trip_hyst_get(struct thermal_zone_device *tzdev, int trip, + int *p_hyst) +{ + struct mlxsw_thermal_module *tz = tzdev->devdata; + + *p_hyst = tz->trips[trip].hyst; + return 0; +} + +static int +mlxsw_thermal_module_trip_hyst_set(struct thermal_zone_device *tzdev, int trip, + int hyst) +{ + struct mlxsw_thermal_module *tz = tzdev->devdata; + + tz->trips[trip].hyst = hyst; + return 0; +} + +static struct thermal_zone_params mlxsw_thermal_module_params = { + .governor_name = "user_space", +}; + +static struct thermal_zone_device_ops mlxsw_thermal_module_ops = { + .bind = mlxsw_thermal_module_bind, + .unbind = mlxsw_thermal_module_unbind, + .get_mode = mlxsw_thermal_module_mode_get, + .set_mode = mlxsw_thermal_module_mode_set, + .get_temp = mlxsw_thermal_module_temp_get, + .get_trip_type = mlxsw_thermal_module_trip_type_get, + .get_trip_temp = mlxsw_thermal_module_trip_temp_get, + .set_trip_temp = mlxsw_thermal_module_trip_temp_set, + .get_trip_hyst = mlxsw_thermal_module_trip_hyst_get, + .set_trip_hyst = mlxsw_thermal_module_trip_hyst_set, }; static int mlxsw_thermal_get_max_state(struct thermal_cooling_device *cdev, @@ -355,6 +663,123 @@ static const struct thermal_cooling_device_ops mlxsw_cooling_ops = { .set_cur_state = mlxsw_thermal_set_cur_state, }; +static int +mlxsw_thermal_module_tz_init(struct mlxsw_thermal_module *module_tz) +{ + char tz_name[MLXSW_THERMAL_ZONE_MAX_NAME]; + int err; + + snprintf(tz_name, sizeof(tz_name), "mlxsw-module%d", + module_tz->module + 1); + module_tz->tzdev = thermal_zone_device_register(tz_name, + MLXSW_THERMAL_NUM_TRIPS, + MLXSW_THERMAL_TRIP_MASK, + module_tz, + &mlxsw_thermal_module_ops, + &mlxsw_thermal_module_params, + 0, 0); + if (IS_ERR(module_tz->tzdev)) { + err = PTR_ERR(module_tz->tzdev); + return err; + } + + return 0; +} + +static void mlxsw_thermal_module_tz_fini(struct thermal_zone_device *tzdev) +{ + thermal_zone_device_unregister(tzdev); +} + +static int +mlxsw_thermal_module_init(struct device *dev, struct mlxsw_core *core, + struct mlxsw_thermal *thermal, u8 local_port) +{ + struct mlxsw_thermal_module *module_tz; + char pmlp_pl[MLXSW_REG_PMLP_LEN]; + u8 width, module; + int err; + + mlxsw_reg_pmlp_pack(pmlp_pl, local_port); + err = mlxsw_reg_query(core, MLXSW_REG(pmlp), pmlp_pl); + if (err) + return err; + + width = mlxsw_reg_pmlp_width_get(pmlp_pl); + if (!width) + return 0; + + module = mlxsw_reg_pmlp_module_get(pmlp_pl, 0); + module_tz = &thermal->tz_module_arr[module]; + module_tz->module = module; + module_tz->parent = thermal; + memcpy(module_tz->trips, default_thermal_trips, + sizeof(thermal->trips)); + /* Initialize all trip point. */ + mlxsw_thermal_module_trips_reset(module_tz); + /* Update trip point according to the module data. */ + err = mlxsw_thermal_module_trips_update(dev, core, module_tz); + if (err) + return err; + + thermal->tz_module_num++; + + return 0; +} + +static void mlxsw_thermal_module_fini(struct mlxsw_thermal_module *module_tz) +{ + if (module_tz && module_tz->tzdev) { + mlxsw_thermal_module_tz_fini(module_tz->tzdev); + module_tz->tzdev = NULL; + } +} + +static int +mlxsw_thermal_modules_init(struct device *dev, struct mlxsw_core *core, + struct mlxsw_thermal *thermal) +{ + unsigned int module_count = mlxsw_core_max_ports(core); + int i, err; + + thermal->tz_module_arr = kcalloc(module_count, + sizeof(*thermal->tz_module_arr), + GFP_KERNEL); + if (!thermal->tz_module_arr) + return -ENOMEM; + + for (i = 1; i < module_count; i++) { + err = mlxsw_thermal_module_init(dev, core, thermal, i); + if (err) + goto err_unreg_tz_module_arr; + } + + for (i = 0; i < thermal->tz_module_num; i++) { + err = mlxsw_thermal_module_tz_init(&thermal->tz_module_arr[i]); + if (err) + goto err_unreg_tz_module_arr; + } + + return 0; + +err_unreg_tz_module_arr: + for (i = module_count - 1; i >= 0; i--) + mlxsw_thermal_module_fini(&thermal->tz_module_arr[i]); + kfree(thermal->tz_module_arr); + return err; +} + +static void +mlxsw_thermal_modules_fini(struct mlxsw_thermal *thermal) +{ + unsigned int module_count = mlxsw_core_max_ports(thermal->core); + int i; + + for (i = module_count - 1; i >= 0; i--) + mlxsw_thermal_module_fini(&thermal->tz_module_arr[i]); + kfree(thermal->tz_module_arr); +} + int mlxsw_thermal_init(struct mlxsw_core *core, const struct mlxsw_bus_info *bus_info, struct mlxsw_thermal **p_thermal) @@ -407,8 +832,9 @@ int mlxsw_thermal_init(struct mlxsw_core *core, if (pwm_active & BIT(i)) { struct thermal_cooling_device *cdev; - cdev = thermal_cooling_device_register("Fan", thermal, - &mlxsw_cooling_ops); + cdev = thermal_cooling_device_register("mlxsw_fan", + thermal, + &mlxsw_cooling_ops); if (IS_ERR(cdev)) { err = PTR_ERR(cdev); dev_err(dev, "Failed to register cooling device\n"); @@ -423,22 +849,36 @@ int mlxsw_thermal_init(struct mlxsw_core *core, thermal->cooling_levels[i] = max(MLXSW_THERMAL_SPEED_MIN_LEVEL, i); + thermal->polling_delay = bus_info->low_frequency ? + MLXSW_THERMAL_SLOW_POLL_INT : + MLXSW_THERMAL_POLL_INT; + thermal->tzdev = thermal_zone_device_register("mlxsw", MLXSW_THERMAL_NUM_TRIPS, MLXSW_THERMAL_TRIP_MASK, thermal, &mlxsw_thermal_ops, NULL, 0, - MLXSW_THERMAL_POLL_INT); + thermal->polling_delay); if (IS_ERR(thermal->tzdev)) { err = PTR_ERR(thermal->tzdev); dev_err(dev, "Failed to register thermal zone\n"); goto err_unreg_cdevs; } + err = mlxsw_thermal_modules_init(dev, core, thermal); + if (err) + goto err_unreg_tzdev; + thermal->mode = THERMAL_DEVICE_ENABLED; *p_thermal = thermal; return 0; + +err_unreg_tzdev: + if (thermal->tzdev) { + thermal_zone_device_unregister(thermal->tzdev); + thermal->tzdev = NULL; + } err_unreg_cdevs: for (i = 0; i < MLXSW_MFCR_PWMS_MAX; i++) if (thermal->cdevs[i]) @@ -452,6 +892,7 @@ void mlxsw_thermal_fini(struct mlxsw_thermal *thermal) { int i; + mlxsw_thermal_modules_fini(thermal); if (thermal->tzdev) { thermal_zone_device_unregister(thermal->tzdev); thermal->tzdev = NULL; diff --git a/drivers/net/ethernet/mellanox/mlxsw/i2c.c b/drivers/net/ethernet/mellanox/mlxsw/i2c.c index 798bd5aca384..a87ca6b6580d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/i2c.c +++ b/drivers/net/ethernet/mellanox/mlxsw/i2c.c @@ -503,6 +503,7 @@ static int mlxsw_i2c_probe(struct i2c_client *client, mlxsw_i2c->bus_info.device_kind = id->name; mlxsw_i2c->bus_info.device_name = client->name; mlxsw_i2c->bus_info.dev = &client->dev; + mlxsw_i2c->bus_info.low_frequency = true; mlxsw_i2c->dev = &client->dev; err = mlxsw_core_bus_device_register(&mlxsw_i2c->bus_info, diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 5f8066ab7d40..cbd0193ec3f6 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -2199,6 +2199,14 @@ MLXSW_ITEM32(reg, pagt, size, 0x00, 0, 8); */ MLXSW_ITEM32(reg, pagt, acl_group_id, 0x08, 0, 16); +/* reg_pagt_multi + * Multi-ACL + * 0 - This ACL is the last ACL in the multi-ACL + * 1 - This ACL is part of a multi-ACL + * Access: RW + */ +MLXSW_ITEM32_INDEXED(reg, pagt, multi, 0x30, 31, 1, 0x04, 0x00, false); + /* reg_pagt_acl_id * ACL identifier * Access: RW @@ -2212,12 +2220,13 @@ static inline void mlxsw_reg_pagt_pack(char *payload, u16 acl_group_id) } static inline void mlxsw_reg_pagt_acl_id_pack(char *payload, int index, - u16 acl_id) + u16 acl_id, bool multi) { u8 size = mlxsw_reg_pagt_size_get(payload); if (index >= size) mlxsw_reg_pagt_size_set(payload, index + 1); + mlxsw_reg_pagt_multi_set(payload, index, multi); mlxsw_reg_pagt_acl_id_set(payload, index, acl_id); } @@ -7866,6 +7875,35 @@ static inline void mlxsw_reg_mfsl_unpack(char *payload, u8 tacho, *p_tach_max = mlxsw_reg_mfsl_tach_max_get(payload); } +/* FORE - Fan Out of Range Event Register + * -------------------------------------- + * This register reports the status of the controlled fans compared to the + * range defined by the MFSL register. + */ +#define MLXSW_REG_FORE_ID 0x9007 +#define MLXSW_REG_FORE_LEN 0x0C + +MLXSW_REG_DEFINE(fore, MLXSW_REG_FORE_ID, MLXSW_REG_FORE_LEN); + +/* fan_under_limit + * Fan speed is below the low limit defined in MFSL register. Each bit relates + * to a single tachometer and indicates the specific tachometer reading is + * below the threshold. + * Access: RO + */ +MLXSW_ITEM32(reg, fore, fan_under_limit, 0x00, 16, 10); + +static inline void mlxsw_reg_fore_unpack(char *payload, u8 tacho, + bool *fault) +{ + u16 limit; + + if (fault) { + limit = mlxsw_reg_fore_fan_under_limit_get(payload); + *fault = limit & BIT(tacho); + } +} + /* MTCAP - Management Temperature Capabilities * ------------------------------------------- * This register exposes the capabilities of the device and @@ -7992,6 +8030,80 @@ static inline void mlxsw_reg_mtmp_unpack(char *payload, unsigned int *p_temp, mlxsw_reg_mtmp_sensor_name_memcpy_from(payload, sensor_name); } +/* MTBR - Management Temperature Bulk Register + * ------------------------------------------- + * This register is used for bulk temperature reading. + */ +#define MLXSW_REG_MTBR_ID 0x900F +#define MLXSW_REG_MTBR_BASE_LEN 0x10 /* base length, without records */ +#define MLXSW_REG_MTBR_REC_LEN 0x04 /* record length */ +#define MLXSW_REG_MTBR_REC_MAX_COUNT 47 /* firmware limitation */ +#define MLXSW_REG_MTBR_LEN (MLXSW_REG_MTBR_BASE_LEN + \ + MLXSW_REG_MTBR_REC_LEN * \ + MLXSW_REG_MTBR_REC_MAX_COUNT) + +MLXSW_REG_DEFINE(mtbr, MLXSW_REG_MTBR_ID, MLXSW_REG_MTBR_LEN); + +/* reg_mtbr_base_sensor_index + * Base sensors index to access (0 - ASIC sensor, 1-63 - ambient sensors, + * 64-127 are mapped to the SFP+/QSFP modules sequentially). + * Access: Index + */ +MLXSW_ITEM32(reg, mtbr, base_sensor_index, 0x00, 0, 7); + +/* reg_mtbr_num_rec + * Request: Number of records to read + * Response: Number of records read + * See above description for more details. + * Range 1..255 + * Access: RW + */ +MLXSW_ITEM32(reg, mtbr, num_rec, 0x04, 0, 8); + +/* reg_mtbr_rec_max_temp + * The highest measured temperature from the sensor. + * When the bit mte is cleared, the field max_temperature is reserved. + * Access: RO + */ +MLXSW_ITEM32_INDEXED(reg, mtbr, rec_max_temp, MLXSW_REG_MTBR_BASE_LEN, 16, + 16, MLXSW_REG_MTBR_REC_LEN, 0x00, false); + +/* reg_mtbr_rec_temp + * Temperature reading from the sensor. Reading is in 0..125 Celsius + * degrees units. + * Access: RO + */ +MLXSW_ITEM32_INDEXED(reg, mtbr, rec_temp, MLXSW_REG_MTBR_BASE_LEN, 0, 16, + MLXSW_REG_MTBR_REC_LEN, 0x00, false); + +static inline void mlxsw_reg_mtbr_pack(char *payload, u8 base_sensor_index, + u8 num_rec) +{ + MLXSW_REG_ZERO(mtbr, payload); + mlxsw_reg_mtbr_base_sensor_index_set(payload, base_sensor_index); + mlxsw_reg_mtbr_num_rec_set(payload, num_rec); +} + +/* Error codes from temperatute reading */ +enum mlxsw_reg_mtbr_temp_status { + MLXSW_REG_MTBR_NO_CONN = 0x8000, + MLXSW_REG_MTBR_NO_TEMP_SENS = 0x8001, + MLXSW_REG_MTBR_INDEX_NA = 0x8002, + MLXSW_REG_MTBR_BAD_SENS_INFO = 0x8003, +}; + +/* Base index for reading modules temperature */ +#define MLXSW_REG_MTBR_BASE_MODULE_INDEX 64 + +static inline void mlxsw_reg_mtbr_temp_unpack(char *payload, int rec_ind, + u16 *p_temp, u16 *p_max_temp) +{ + if (p_temp) + *p_temp = mlxsw_reg_mtbr_rec_temp_get(payload, rec_ind); + if (p_max_temp) + *p_max_temp = mlxsw_reg_mtbr_rec_max_temp_get(payload, rec_ind); +} + /* MCIA - Management Cable Info Access * ----------------------------------- * MCIA register is used to access the SFP+ and QSFP connector's EPROM. @@ -8046,13 +8158,41 @@ MLXSW_ITEM32(reg, mcia, device_address, 0x04, 0, 16); */ MLXSW_ITEM32(reg, mcia, size, 0x08, 0, 16); -#define MLXSW_SP_REG_MCIA_EEPROM_SIZE 48 +#define MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH 256 +#define MLXSW_REG_MCIA_EEPROM_SIZE 48 +#define MLXSW_REG_MCIA_I2C_ADDR_LOW 0x50 +#define MLXSW_REG_MCIA_I2C_ADDR_HIGH 0x51 +#define MLXSW_REG_MCIA_PAGE0_LO_OFF 0xa0 +#define MLXSW_REG_MCIA_TH_ITEM_SIZE 2 +#define MLXSW_REG_MCIA_TH_PAGE_NUM 3 +#define MLXSW_REG_MCIA_PAGE0_LO 0 +#define MLXSW_REG_MCIA_TH_PAGE_OFF 0x80 + +enum mlxsw_reg_mcia_eeprom_module_info_rev_id { + MLXSW_REG_MCIA_EEPROM_MODULE_INFO_REV_ID_UNSPC = 0x00, + MLXSW_REG_MCIA_EEPROM_MODULE_INFO_REV_ID_8436 = 0x01, + MLXSW_REG_MCIA_EEPROM_MODULE_INFO_REV_ID_8636 = 0x03, +}; + +enum mlxsw_reg_mcia_eeprom_module_info_id { + MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_SFP = 0x03, + MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP = 0x0C, + MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_PLUS = 0x0D, + MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP28 = 0x11, + MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_DD = 0x18, +}; + +enum mlxsw_reg_mcia_eeprom_module_info { + MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID, + MLXSW_REG_MCIA_EEPROM_MODULE_INFO_REV_ID, + MLXSW_REG_MCIA_EEPROM_MODULE_INFO_SIZE, +}; /* reg_mcia_eeprom * Bytes to read/write. * Access: RW */ -MLXSW_ITEM_BUF(reg, mcia, eeprom, 0x10, MLXSW_SP_REG_MCIA_EEPROM_SIZE); +MLXSW_ITEM_BUF(reg, mcia, eeprom, 0x10, MLXSW_REG_MCIA_EEPROM_SIZE); static inline void mlxsw_reg_mcia_pack(char *payload, u8 module, u8 lock, u8 page_number, u16 device_addr, @@ -9740,8 +9880,10 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = { MLXSW_REG(mfsc), MLXSW_REG(mfsm), MLXSW_REG(mfsl), + MLXSW_REG(fore), MLXSW_REG(mtcap), MLXSW_REG(mtmp), + MLXSW_REG(mtbr), MLXSW_REG(mcia), MLXSW_REG(mpat), MLXSW_REG(mpar), diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index a88169738b4a..abac923a8d04 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -1700,6 +1700,18 @@ static int mlxsw_sp_set_features(struct net_device *dev, mlxsw_sp_feature_hw_tc); } +static int mlxsw_sp_port_get_port_parent_id(struct net_device *dev, + struct netdev_phys_item_id *ppid) +{ + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + + ppid->id_len = sizeof(mlxsw_sp->base_mac); + memcpy(&ppid->id, &mlxsw_sp->base_mac, ppid->id_len); + + return 0; +} + static const struct net_device_ops mlxsw_sp_port_netdev_ops = { .ndo_open = mlxsw_sp_port_open, .ndo_stop = mlxsw_sp_port_stop, @@ -1715,6 +1727,7 @@ static const struct net_device_ops mlxsw_sp_port_netdev_ops = { .ndo_vlan_rx_kill_vid = mlxsw_sp_port_kill_vid, .ndo_get_phys_port_name = mlxsw_sp_port_get_phys_port_name, .ndo_set_features = mlxsw_sp_set_features, + .ndo_get_port_parent_id = mlxsw_sp_port_get_port_parent_id, }; static void mlxsw_sp_port_get_drvinfo(struct net_device *dev, @@ -2710,23 +2723,23 @@ static int mlxsw_sp_query_module_eeprom(struct mlxsw_sp_port *mlxsw_sp_port, unsigned int *p_read_size) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; - char eeprom_tmp[MLXSW_SP_REG_MCIA_EEPROM_SIZE]; + char eeprom_tmp[MLXSW_REG_MCIA_EEPROM_SIZE]; char mcia_pl[MLXSW_REG_MCIA_LEN]; u16 i2c_addr; int status; int err; - size = min_t(u16, size, MLXSW_SP_REG_MCIA_EEPROM_SIZE); + size = min_t(u16, size, MLXSW_REG_MCIA_EEPROM_SIZE); - if (offset < MLXSW_SP_EEPROM_PAGE_LENGTH && - offset + size > MLXSW_SP_EEPROM_PAGE_LENGTH) + if (offset < MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH && + offset + size > MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH) /* Cross pages read, read until offset 256 in low page */ - size = MLXSW_SP_EEPROM_PAGE_LENGTH - offset; + size = MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH - offset; - i2c_addr = MLXSW_SP_I2C_ADDR_LOW; - if (offset >= MLXSW_SP_EEPROM_PAGE_LENGTH) { - i2c_addr = MLXSW_SP_I2C_ADDR_HIGH; - offset -= MLXSW_SP_EEPROM_PAGE_LENGTH; + i2c_addr = MLXSW_REG_MCIA_I2C_ADDR_LOW; + if (offset >= MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH) { + i2c_addr = MLXSW_REG_MCIA_I2C_ADDR_HIGH; + offset -= MLXSW_REG_MCIA_EEPROM_PAGE_LENGTH; } mlxsw_reg_mcia_pack(mcia_pl, mlxsw_sp_port->mapping.module, @@ -2747,55 +2760,37 @@ static int mlxsw_sp_query_module_eeprom(struct mlxsw_sp_port *mlxsw_sp_port, return 0; } -enum mlxsw_sp_eeprom_module_info_rev_id { - MLXSW_SP_EEPROM_MODULE_INFO_REV_ID_UNSPC = 0x00, - MLXSW_SP_EEPROM_MODULE_INFO_REV_ID_8436 = 0x01, - MLXSW_SP_EEPROM_MODULE_INFO_REV_ID_8636 = 0x03, -}; - -enum mlxsw_sp_eeprom_module_info_id { - MLXSW_SP_EEPROM_MODULE_INFO_ID_SFP = 0x03, - MLXSW_SP_EEPROM_MODULE_INFO_ID_QSFP = 0x0C, - MLXSW_SP_EEPROM_MODULE_INFO_ID_QSFP_PLUS = 0x0D, - MLXSW_SP_EEPROM_MODULE_INFO_ID_QSFP28 = 0x11, -}; - -enum mlxsw_sp_eeprom_module_info { - MLXSW_SP_EEPROM_MODULE_INFO_ID, - MLXSW_SP_EEPROM_MODULE_INFO_REV_ID, - MLXSW_SP_EEPROM_MODULE_INFO_SIZE, -}; - static int mlxsw_sp_get_module_info(struct net_device *netdev, struct ethtool_modinfo *modinfo) { struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(netdev); - u8 module_info[MLXSW_SP_EEPROM_MODULE_INFO_SIZE]; + u8 module_info[MLXSW_REG_MCIA_EEPROM_MODULE_INFO_SIZE]; + u16 offset = MLXSW_REG_MCIA_EEPROM_MODULE_INFO_SIZE; u8 module_rev_id, module_id; unsigned int read_size; int err; - err = mlxsw_sp_query_module_eeprom(mlxsw_sp_port, 0, - MLXSW_SP_EEPROM_MODULE_INFO_SIZE, + err = mlxsw_sp_query_module_eeprom(mlxsw_sp_port, 0, offset, module_info, &read_size); if (err) return err; - if (read_size < MLXSW_SP_EEPROM_MODULE_INFO_SIZE) + if (read_size < offset) return -EIO; - module_rev_id = module_info[MLXSW_SP_EEPROM_MODULE_INFO_REV_ID]; - module_id = module_info[MLXSW_SP_EEPROM_MODULE_INFO_ID]; + module_rev_id = module_info[MLXSW_REG_MCIA_EEPROM_MODULE_INFO_REV_ID]; + module_id = module_info[MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID]; switch (module_id) { - case MLXSW_SP_EEPROM_MODULE_INFO_ID_QSFP: + case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP: modinfo->type = ETH_MODULE_SFF_8436; modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN; break; - case MLXSW_SP_EEPROM_MODULE_INFO_ID_QSFP_PLUS: - case MLXSW_SP_EEPROM_MODULE_INFO_ID_QSFP28: - if (module_id == MLXSW_SP_EEPROM_MODULE_INFO_ID_QSFP28 || - module_rev_id >= MLXSW_SP_EEPROM_MODULE_INFO_REV_ID_8636) { + case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP_PLUS: /* fall-through */ + case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP28: + if (module_id == MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_QSFP28 || + module_rev_id >= + MLXSW_REG_MCIA_EEPROM_MODULE_INFO_REV_ID_8636) { modinfo->type = ETH_MODULE_SFF_8636; modinfo->eeprom_len = ETH_MODULE_SFF_8636_LEN; } else { @@ -2803,7 +2798,7 @@ static int mlxsw_sp_get_module_info(struct net_device *netdev, modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN; } break; - case MLXSW_SP_EEPROM_MODULE_INFO_ID_SFP: + case MLXSW_REG_MCIA_EEPROM_MODULE_INFO_ID_SFP: modinfo->type = ETH_MODULE_SFF_8472; modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN; break; @@ -4400,6 +4395,71 @@ static void mlxsw_sp_params_unregister(struct mlxsw_core *mlxsw_core) ARRAY_SIZE(mlxsw_sp_devlink_params)); } +static int +mlxsw_sp_params_acl_region_rehash_intrvl_get(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct mlxsw_core *mlxsw_core = devlink_priv(devlink); + struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); + + ctx->val.vu32 = mlxsw_sp_acl_region_rehash_intrvl_get(mlxsw_sp); + return 0; +} + +static int +mlxsw_sp_params_acl_region_rehash_intrvl_set(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct mlxsw_core *mlxsw_core = devlink_priv(devlink); + struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); + + return mlxsw_sp_acl_region_rehash_intrvl_set(mlxsw_sp, ctx->val.vu32); +} + +static const struct devlink_param mlxsw_sp2_devlink_params[] = { + DEVLINK_PARAM_DRIVER(MLXSW_DEVLINK_PARAM_ID_ACL_REGION_REHASH_INTERVAL, + "acl_region_rehash_interval", + DEVLINK_PARAM_TYPE_U32, + BIT(DEVLINK_PARAM_CMODE_RUNTIME), + mlxsw_sp_params_acl_region_rehash_intrvl_get, + mlxsw_sp_params_acl_region_rehash_intrvl_set, + NULL), +}; + +static int mlxsw_sp2_params_register(struct mlxsw_core *mlxsw_core) +{ + struct devlink *devlink = priv_to_devlink(mlxsw_core); + union devlink_param_value value; + int err; + + err = mlxsw_sp_params_register(mlxsw_core); + if (err) + return err; + + err = devlink_params_register(devlink, mlxsw_sp2_devlink_params, + ARRAY_SIZE(mlxsw_sp2_devlink_params)); + if (err) + goto err_devlink_params_register; + + value.vu32 = 0; + devlink_param_driverinit_value_set(devlink, + MLXSW_DEVLINK_PARAM_ID_ACL_REGION_REHASH_INTERVAL, + value); + return 0; + +err_devlink_params_register: + mlxsw_sp_params_unregister(mlxsw_core); + return err; +} + +static void mlxsw_sp2_params_unregister(struct mlxsw_core *mlxsw_core) +{ + devlink_params_unregister(priv_to_devlink(mlxsw_core), + mlxsw_sp2_devlink_params, + ARRAY_SIZE(mlxsw_sp2_devlink_params)); + mlxsw_sp_params_unregister(mlxsw_core); +} + static struct mlxsw_driver mlxsw_sp1_driver = { .kind = mlxsw_sp1_driver_name, .priv_size = sizeof(struct mlxsw_sp), @@ -4448,8 +4508,8 @@ static struct mlxsw_driver mlxsw_sp2_driver = { .sb_occ_tc_port_bind_get = mlxsw_sp_sb_occ_tc_port_bind_get, .txhdr_construct = mlxsw_sp_txhdr_construct, .resources_register = mlxsw_sp2_resources_register, - .params_register = mlxsw_sp_params_register, - .params_unregister = mlxsw_sp_params_unregister, + .params_register = mlxsw_sp2_params_register, + .params_unregister = mlxsw_sp2_params_unregister, .txhdr_len = MLXSW_TXHDR_LEN, .profile = &mlxsw_sp2_config_profile, .res_query_enabled = true, @@ -4693,9 +4753,6 @@ static int mlxsw_sp_port_lag_join(struct mlxsw_sp_port *mlxsw_sp_port, err = mlxsw_sp_lag_col_port_add(mlxsw_sp_port, lag_id, port_index); if (err) goto err_col_port_add; - err = mlxsw_sp_lag_col_port_enable(mlxsw_sp_port, lag_id); - if (err) - goto err_col_port_enable; mlxsw_core_lag_mapping_set(mlxsw_sp->core, lag_id, port_index, mlxsw_sp_port->local_port); @@ -4709,8 +4766,6 @@ static int mlxsw_sp_port_lag_join(struct mlxsw_sp_port *mlxsw_sp_port, return 0; -err_col_port_enable: - mlxsw_sp_lag_col_port_remove(mlxsw_sp_port, lag_id); err_col_port_add: if (!lag->ref_count) mlxsw_sp_lag_destroy(mlxsw_sp, lag_id); @@ -4729,7 +4784,6 @@ static void mlxsw_sp_port_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port, lag = mlxsw_sp_lag_get(mlxsw_sp, lag_id); WARN_ON(lag->ref_count == 0); - mlxsw_sp_lag_col_port_disable(mlxsw_sp_port, lag_id); mlxsw_sp_lag_col_port_remove(mlxsw_sp_port, lag_id); /* Any VLANs configured on the port are no longer valid */ @@ -4774,21 +4828,56 @@ static int mlxsw_sp_lag_dist_port_remove(struct mlxsw_sp_port *mlxsw_sp_port, return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sldr), sldr_pl); } -static int mlxsw_sp_port_lag_tx_en_set(struct mlxsw_sp_port *mlxsw_sp_port, - bool lag_tx_enabled) +static int +mlxsw_sp_port_lag_col_dist_enable(struct mlxsw_sp_port *mlxsw_sp_port) { - if (lag_tx_enabled) - return mlxsw_sp_lag_dist_port_add(mlxsw_sp_port, - mlxsw_sp_port->lag_id); - else - return mlxsw_sp_lag_dist_port_remove(mlxsw_sp_port, - mlxsw_sp_port->lag_id); + int err; + + err = mlxsw_sp_lag_col_port_enable(mlxsw_sp_port, + mlxsw_sp_port->lag_id); + if (err) + return err; + + err = mlxsw_sp_lag_dist_port_add(mlxsw_sp_port, mlxsw_sp_port->lag_id); + if (err) + goto err_dist_port_add; + + return 0; + +err_dist_port_add: + mlxsw_sp_lag_col_port_disable(mlxsw_sp_port, mlxsw_sp_port->lag_id); + return err; +} + +static int +mlxsw_sp_port_lag_col_dist_disable(struct mlxsw_sp_port *mlxsw_sp_port) +{ + int err; + + err = mlxsw_sp_lag_dist_port_remove(mlxsw_sp_port, + mlxsw_sp_port->lag_id); + if (err) + return err; + + err = mlxsw_sp_lag_col_port_disable(mlxsw_sp_port, + mlxsw_sp_port->lag_id); + if (err) + goto err_col_port_disable; + + return 0; + +err_col_port_disable: + mlxsw_sp_lag_dist_port_add(mlxsw_sp_port, mlxsw_sp_port->lag_id); + return err; } static int mlxsw_sp_port_lag_changed(struct mlxsw_sp_port *mlxsw_sp_port, struct netdev_lag_lower_state_info *info) { - return mlxsw_sp_port_lag_tx_en_set(mlxsw_sp_port, info->tx_enabled); + if (info->tx_enabled) + return mlxsw_sp_port_lag_col_dist_enable(mlxsw_sp_port); + else + return mlxsw_sp_port_lag_col_dist_disable(mlxsw_sp_port); } static int mlxsw_sp_port_stp_set(struct mlxsw_sp_port *mlxsw_sp_port, @@ -5011,8 +5100,7 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev, err = mlxsw_sp_port_lag_join(mlxsw_sp_port, upper_dev); } else { - mlxsw_sp_port_lag_tx_en_set(mlxsw_sp_port, - false); + mlxsw_sp_port_lag_col_dist_disable(mlxsw_sp_port); mlxsw_sp_port_lag_leave(mlxsw_sp_port, upper_dev); } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 4fe0996c7cdd..ceebc91f4f1d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -690,6 +690,8 @@ struct mlxsw_sp_fid *mlxsw_sp_acl_dummy_fid(struct mlxsw_sp *mlxsw_sp); int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp); void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp); +u32 mlxsw_sp_acl_region_rehash_intrvl_get(struct mlxsw_sp *mlxsw_sp); +int mlxsw_sp_acl_region_rehash_intrvl_set(struct mlxsw_sp *mlxsw_sp, u32 val); /* spectrum_acl_tcam.c */ struct mlxsw_sp_acl_tcam; @@ -704,10 +706,13 @@ struct mlxsw_sp_acl_tcam_ops { size_t region_priv_size; int (*region_init)(struct mlxsw_sp *mlxsw_sp, void *region_priv, void *tcam_priv, - struct mlxsw_sp_acl_tcam_region *region); + struct mlxsw_sp_acl_tcam_region *region, + void *hints_priv); void (*region_fini)(struct mlxsw_sp *mlxsw_sp, void *region_priv); int (*region_associate)(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_tcam_region *region); + void * (*region_rehash_hints_get)(void *region_priv); + void (*region_rehash_hints_put)(void *hints_priv); size_t chunk_priv_size; void (*chunk_init)(void *region_priv, void *chunk_priv, unsigned int priority); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c index 6e444525713f..3a636f753607 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c @@ -112,7 +112,8 @@ mlxsw_sp1_acl_ctcam_region_catchall_del(struct mlxsw_sp *mlxsw_sp, static int mlxsw_sp1_acl_tcam_region_init(struct mlxsw_sp *mlxsw_sp, void *region_priv, void *tcam_priv, - struct mlxsw_sp_acl_tcam_region *_region) + struct mlxsw_sp_acl_tcam_region *_region, + void *hints_priv) { struct mlxsw_sp1_acl_tcam_region *region = region_priv; int err; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c index d380b3403960..6c66a0f1b79e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c @@ -139,7 +139,8 @@ static void mlxsw_sp2_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp, void *priv) static int mlxsw_sp2_acl_tcam_region_init(struct mlxsw_sp *mlxsw_sp, void *region_priv, void *tcam_priv, - struct mlxsw_sp_acl_tcam_region *_region) + struct mlxsw_sp_acl_tcam_region *_region, + void *hints_priv) { struct mlxsw_sp2_acl_tcam_region *region = region_priv; struct mlxsw_sp2_acl_tcam *tcam = tcam_priv; @@ -147,7 +148,8 @@ mlxsw_sp2_acl_tcam_region_init(struct mlxsw_sp *mlxsw_sp, void *region_priv, region->region = _region; return mlxsw_sp_acl_atcam_region_init(mlxsw_sp, &tcam->atcam, - ®ion->aregion, _region, + ®ion->aregion, + _region, hints_priv, &mlxsw_sp2_acl_ctcam_region_ops); } @@ -166,6 +168,18 @@ mlxsw_sp2_acl_tcam_region_associate(struct mlxsw_sp *mlxsw_sp, return mlxsw_sp_acl_atcam_region_associate(mlxsw_sp, region->id); } +static void *mlxsw_sp2_acl_tcam_region_rehash_hints_get(void *region_priv) +{ + struct mlxsw_sp2_acl_tcam_region *region = region_priv; + + return mlxsw_sp_acl_atcam_rehash_hints_get(®ion->aregion); +} + +static void mlxsw_sp2_acl_tcam_region_rehash_hints_put(void *hints_priv) +{ + mlxsw_sp_acl_atcam_rehash_hints_put(hints_priv); +} + static void mlxsw_sp2_acl_tcam_chunk_init(void *region_priv, void *chunk_priv, unsigned int priority) { @@ -243,6 +257,8 @@ const struct mlxsw_sp_acl_tcam_ops mlxsw_sp2_acl_tcam_ops = { .region_init = mlxsw_sp2_acl_tcam_region_init, .region_fini = mlxsw_sp2_acl_tcam_region_fini, .region_associate = mlxsw_sp2_acl_tcam_region_associate, + .region_rehash_hints_get = mlxsw_sp2_acl_tcam_region_rehash_hints_get, + .region_rehash_hints_put = mlxsw_sp2_acl_tcam_region_rehash_hints_put, .chunk_priv_size = sizeof(struct mlxsw_sp2_acl_tcam_chunk), .chunk_init = mlxsw_sp2_acl_tcam_chunk_init, .chunk_fini = mlxsw_sp2_acl_tcam_chunk_fini, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c index a69e3462b65e..a146a44634e9 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c @@ -588,7 +588,7 @@ int mlxsw_sp_acl_rulei_act_vlan(struct mlxsw_sp *mlxsw_sp, { u8 ethertype; - if (action == TCA_VLAN_ACT_MODIFY) { + if (action == FLOW_ACTION_VLAN_MANGLE) { switch (proto) { case ETH_P_8021Q: ethertype = 0; @@ -640,7 +640,7 @@ mlxsw_sp_acl_rule_create(struct mlxsw_sp *mlxsw_sp, int err; mlxsw_sp_acl_ruleset_ref_inc(ruleset); - rule = kzalloc(sizeof(*rule) + ops->rule_priv_size(mlxsw_sp), + rule = kzalloc(sizeof(*rule) + ops->rule_priv_size, GFP_KERNEL); if (!rule) { err = -ENOMEM; @@ -912,3 +912,19 @@ void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp) mlxsw_afk_destroy(acl->afk); kfree(acl); } + +u32 mlxsw_sp_acl_region_rehash_intrvl_get(struct mlxsw_sp *mlxsw_sp) +{ + struct mlxsw_sp_acl *acl = mlxsw_sp->acl; + + return mlxsw_sp_acl_tcam_vregion_rehash_intrvl_get(mlxsw_sp, + &acl->tcam); +} + +int mlxsw_sp_acl_region_rehash_intrvl_set(struct mlxsw_sp *mlxsw_sp, u32 val) +{ + struct mlxsw_sp_acl *acl = mlxsw_sp->acl; + + return mlxsw_sp_acl_tcam_vregion_rehash_intrvl_set(mlxsw_sp, + &acl->tcam, val); +} diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c index 40dc76a5c412..ded4cf658680 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c @@ -7,6 +7,8 @@ #include <linux/gfp.h> #include <linux/refcount.h> #include <linux/rhashtable.h> +#define CREATE_TRACE_POINTS +#include <trace/events/mlxsw.h> #include "reg.h" #include "core.h" @@ -316,6 +318,7 @@ mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_atcam *atcam, struct mlxsw_sp_acl_atcam_region *aregion, struct mlxsw_sp_acl_tcam_region *region, + void *hints_priv, const struct mlxsw_sp_acl_ctcam_region_ops *ops) { int err; @@ -332,7 +335,7 @@ mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp, err = aregion->ops->init(aregion); if (err) goto err_ops_init; - err = mlxsw_sp_acl_erp_region_init(aregion); + err = mlxsw_sp_acl_erp_region_init(aregion, hints_priv); if (err) goto err_erp_region_init; err = mlxsw_sp_acl_ctcam_region_init(mlxsw_sp, &aregion->cregion, @@ -390,8 +393,7 @@ mlxsw_sp_acl_atcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp, if (err) return err; - lkey_id = aregion->ops->lkey_id_get(aregion, aentry->ht_key.enc_key, - erp_id); + lkey_id = aregion->ops->lkey_id_get(aregion, aentry->enc_key, erp_id); if (IS_ERR(lkey_id)) return PTR_ERR(lkey_id); aentry->lkey_id = lkey_id; @@ -399,7 +401,7 @@ mlxsw_sp_acl_atcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp, kvdl_index = mlxsw_afa_block_first_kvdl_index(rulei->act_block); mlxsw_reg_ptce3_pack(ptce3_pl, true, MLXSW_REG_PTCE3_OP_WRITE_WRITE, priority, region->tcam_region_info, - aentry->ht_key.enc_key, erp_id, + aentry->enc_key, erp_id, aentry->delta_info.start, aentry->delta_info.mask, aentry->delta_info.value, @@ -424,12 +426,11 @@ mlxsw_sp_acl_atcam_region_entry_remove(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_atcam_lkey_id *lkey_id = aentry->lkey_id; struct mlxsw_sp_acl_tcam_region *region = aregion->region; u8 erp_id = mlxsw_sp_acl_erp_mask_erp_id(aentry->erp_mask); - char *enc_key = aentry->ht_key.enc_key; char ptce3_pl[MLXSW_REG_PTCE3_LEN]; mlxsw_reg_ptce3_pack(ptce3_pl, false, MLXSW_REG_PTCE3_OP_WRITE_WRITE, 0, region->tcam_region_info, - enc_key, erp_id, + aentry->enc_key, erp_id, aentry->delta_info.start, aentry->delta_info.mask, aentry->delta_info.value, @@ -458,7 +459,7 @@ mlxsw_sp_acl_atcam_region_entry_action_replace(struct mlxsw_sp *mlxsw_sp, kvdl_index = mlxsw_afa_block_first_kvdl_index(rulei->act_block); mlxsw_reg_ptce3_pack(ptce3_pl, true, MLXSW_REG_PTCE3_OP_WRITE_UPDATE, priority, region->tcam_region_info, - aentry->ht_key.enc_key, erp_id, + aentry->enc_key, erp_id, aentry->delta_info.start, aentry->delta_info.mask, aentry->delta_info.value, @@ -481,15 +482,15 @@ __mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp, int err; mlxsw_afk_encode(afk, region->key_info, &rulei->values, - aentry->full_enc_key, mask); + aentry->ht_key.full_enc_key, mask); erp_mask = mlxsw_sp_acl_erp_mask_get(aregion, mask, false); if (IS_ERR(erp_mask)) return PTR_ERR(erp_mask); aentry->erp_mask = erp_mask; aentry->ht_key.erp_id = mlxsw_sp_acl_erp_mask_erp_id(erp_mask); - memcpy(aentry->ht_key.enc_key, aentry->full_enc_key, - sizeof(aentry->ht_key.enc_key)); + memcpy(aentry->enc_key, aentry->ht_key.full_enc_key, + sizeof(aentry->enc_key)); /* Compute all needed delta information and clear the delta bits * from the encrypted key. @@ -498,8 +499,9 @@ __mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp, aentry->delta_info.start = mlxsw_sp_acl_erp_delta_start(delta); aentry->delta_info.mask = mlxsw_sp_acl_erp_delta_mask(delta); aentry->delta_info.value = - mlxsw_sp_acl_erp_delta_value(delta, aentry->full_enc_key); - mlxsw_sp_acl_erp_delta_clear(delta, aentry->ht_key.enc_key); + mlxsw_sp_acl_erp_delta_value(delta, + aentry->ht_key.full_enc_key); + mlxsw_sp_acl_erp_delta_clear(delta, aentry->enc_key); /* Add rule to the list of A-TCAM rules, assuming this * rule is intended to A-TCAM. In case this rule does @@ -579,6 +581,7 @@ int mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp, /* It is possible we failed to add the rule to the A-TCAM due to * exceeded number of masks. Try to spill into C-TCAM. */ + trace_mlxsw_sp_acl_atcam_entry_add_ctcam_spill(mlxsw_sp, aregion); err = mlxsw_sp_acl_ctcam_entry_add(mlxsw_sp, &aregion->cregion, &achunk->cchunk, &aentry->centry, rulei, true); @@ -632,3 +635,14 @@ void mlxsw_sp_acl_atcam_fini(struct mlxsw_sp *mlxsw_sp, { mlxsw_sp_acl_erps_fini(mlxsw_sp, atcam); } + +void * +mlxsw_sp_acl_atcam_rehash_hints_get(struct mlxsw_sp_acl_atcam_region *aregion) +{ + return mlxsw_sp_acl_erp_rehash_hints_get(aregion); +} + +void mlxsw_sp_acl_atcam_rehash_hints_put(void *hints_priv) +{ + mlxsw_sp_acl_erp_rehash_hints_put(hints_priv); +} diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c index f5c381dcb015..9545b572747e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c @@ -133,7 +133,7 @@ mlxsw_sp_acl_bf_key_encode(struct mlxsw_sp_acl_atcam_region *aregion, memcpy(chunk + MLXSW_BLOOM_CHUNK_PAD_BYTES, &erp_region_id, sizeof(erp_region_id)); memcpy(chunk + MLXSW_BLOOM_CHUNK_KEY_OFFSET, - &aentry->ht_key.enc_key[chunk_key_offsets[chunk_index]], + &aentry->enc_key[chunk_key_offsets[chunk_index]], MLXSW_BLOOM_CHUNK_KEY_BYTES); chunk += MLXSW_BLOOM_KEY_CHUNK_BYTES; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c index 2941967e1cc5..e935c36638d9 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c @@ -1200,6 +1200,32 @@ mlxsw_sp_acl_erp_delta_fill(const struct mlxsw_sp_acl_erp_key *parent_key, return 0; } +static bool mlxsw_sp_acl_erp_delta_check(void *priv, const void *parent_obj, + const void *obj) +{ + const struct mlxsw_sp_acl_erp_key *parent_key = parent_obj; + const struct mlxsw_sp_acl_erp_key *key = obj; + u16 delta_start; + u8 delta_mask; + int err; + + err = mlxsw_sp_acl_erp_delta_fill(parent_key, key, + &delta_start, &delta_mask); + return err ? false : true; +} + +static int mlxsw_sp_acl_erp_hints_obj_cmp(const void *obj1, const void *obj2) +{ + const struct mlxsw_sp_acl_erp_key *key1 = obj1; + const struct mlxsw_sp_acl_erp_key *key2 = obj2; + + /* For hints purposes, two objects are considered equal + * in case the masks are the same. Does not matter what + * the "ctcam" value is. + */ + return memcmp(key1->mask, key2->mask, sizeof(key1->mask)); +} + static void *mlxsw_sp_acl_erp_delta_create(void *priv, void *parent_obj, void *obj) { @@ -1254,12 +1280,17 @@ static void mlxsw_sp_acl_erp_delta_destroy(void *priv, void *delta_priv) kfree(delta); } -static void *mlxsw_sp_acl_erp_root_create(void *priv, void *obj) +static void *mlxsw_sp_acl_erp_root_create(void *priv, void *obj, + unsigned int root_id) { struct mlxsw_sp_acl_atcam_region *aregion = priv; struct mlxsw_sp_acl_erp_table *erp_table = aregion->erp_table; struct mlxsw_sp_acl_erp_key *key = obj; + if (!key->ctcam && + root_id != OBJAGG_OBJ_ROOT_ID_INVALID && + root_id >= MLXSW_SP_ACL_ERP_MAX_PER_REGION) + return ERR_PTR(-ENOBUFS); return erp_table->ops->erp_create(erp_table, key); } @@ -1273,6 +1304,8 @@ static void mlxsw_sp_acl_erp_root_destroy(void *priv, void *root_priv) static const struct objagg_ops mlxsw_sp_acl_erp_objagg_ops = { .obj_size = sizeof(struct mlxsw_sp_acl_erp_key), + .delta_check = mlxsw_sp_acl_erp_delta_check, + .hints_obj_cmp = mlxsw_sp_acl_erp_hints_obj_cmp, .delta_create = mlxsw_sp_acl_erp_delta_create, .delta_destroy = mlxsw_sp_acl_erp_delta_destroy, .root_create = mlxsw_sp_acl_erp_root_create, @@ -1280,7 +1313,8 @@ static const struct objagg_ops mlxsw_sp_acl_erp_objagg_ops = { }; static struct mlxsw_sp_acl_erp_table * -mlxsw_sp_acl_erp_table_create(struct mlxsw_sp_acl_atcam_region *aregion) +mlxsw_sp_acl_erp_table_create(struct mlxsw_sp_acl_atcam_region *aregion, + struct objagg_hints *hints) { struct mlxsw_sp_acl_erp_table *erp_table; int err; @@ -1290,7 +1324,7 @@ mlxsw_sp_acl_erp_table_create(struct mlxsw_sp_acl_atcam_region *aregion) return ERR_PTR(-ENOMEM); erp_table->objagg = objagg_create(&mlxsw_sp_acl_erp_objagg_ops, - aregion); + hints, aregion); if (IS_ERR(erp_table->objagg)) { err = PTR_ERR(erp_table->objagg); goto err_objagg_create; @@ -1337,12 +1371,88 @@ mlxsw_sp_acl_erp_region_param_init(struct mlxsw_sp_acl_atcam_region *aregion) return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pererp), pererp_pl); } -int mlxsw_sp_acl_erp_region_init(struct mlxsw_sp_acl_atcam_region *aregion) +static int +mlxsw_sp_acl_erp_hints_check(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_atcam_region *aregion, + struct objagg_hints *hints, bool *p_rehash_needed) +{ + struct objagg *objagg = aregion->erp_table->objagg; + const struct objagg_stats *ostats; + const struct objagg_stats *hstats; + int err; + + *p_rehash_needed = false; + + ostats = objagg_stats_get(objagg); + if (IS_ERR(ostats)) { + dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to get ERP stats\n"); + return PTR_ERR(ostats); + } + + hstats = objagg_hints_stats_get(hints); + if (IS_ERR(hstats)) { + dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to get ERP hints stats\n"); + err = PTR_ERR(hstats); + goto err_hints_stats_get; + } + + /* Very basic criterion for now. */ + if (hstats->root_count < ostats->root_count) + *p_rehash_needed = true; + + err = 0; + + objagg_stats_put(hstats); +err_hints_stats_get: + objagg_stats_put(ostats); + return err; +} + +void * +mlxsw_sp_acl_erp_rehash_hints_get(struct mlxsw_sp_acl_atcam_region *aregion) +{ + struct mlxsw_sp *mlxsw_sp = aregion->region->mlxsw_sp; + struct objagg_hints *hints; + bool rehash_needed; + int err; + + hints = objagg_hints_get(aregion->erp_table->objagg, + OBJAGG_OPT_ALGO_SIMPLE_GREEDY); + if (IS_ERR(hints)) { + dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Failed to create ERP hints\n"); + return ERR_CAST(hints); + } + err = mlxsw_sp_acl_erp_hints_check(mlxsw_sp, aregion, hints, + &rehash_needed); + if (err) + goto errout; + + if (!rehash_needed) { + err = -EAGAIN; + goto errout; + } + return hints; + +errout: + objagg_hints_put(hints); + return ERR_PTR(err); +} + +void mlxsw_sp_acl_erp_rehash_hints_put(void *hints_priv) +{ + struct objagg_hints *hints = hints_priv; + + objagg_hints_put(hints); +} + +int mlxsw_sp_acl_erp_region_init(struct mlxsw_sp_acl_atcam_region *aregion, + void *hints_priv) { struct mlxsw_sp_acl_erp_table *erp_table; + struct objagg_hints *hints = hints_priv; int err; - erp_table = mlxsw_sp_acl_erp_table_create(aregion); + erp_table = mlxsw_sp_acl_erp_table_create(aregion, hints); if (IS_ERR(erp_table)) return PTR_ERR(erp_table); aregion->erp_table = erp_table; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c index 11456e1f236f..7e225a86e3a8 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c @@ -8,6 +8,7 @@ #include <linux/list.h> #include <linux/rhashtable.h> #include <linux/netdevice.h> +#include <trace/events/mlxsw.h> #include "reg.h" #include "core.h" @@ -23,6 +24,9 @@ size_t mlxsw_sp_acl_tcam_priv_size(struct mlxsw_sp *mlxsw_sp) return ops->priv_size; } +#define MLXSW_SP_ACL_TCAM_VREGION_REHASH_INTRVL_DFLT 5000 /* ms */ +#define MLXSW_SP_ACL_TCAM_VREGION_REHASH_INTRVL_MIN 3000 /* ms */ + int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_tcam *tcam) { @@ -33,6 +37,10 @@ int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, size_t alloc_size; int err; + tcam->vregion_rehash_intrvl = + MLXSW_SP_ACL_TCAM_VREGION_REHASH_INTRVL_DFLT; + INIT_LIST_HEAD(&tcam->vregion_list); + max_tcam_regions = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_TCAM_REGIONS); max_regions = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_REGIONS); @@ -153,9 +161,9 @@ struct mlxsw_sp_acl_tcam_pattern { struct mlxsw_sp_acl_tcam_group { struct mlxsw_sp_acl_tcam *tcam; u16 id; - struct list_head region_list; + struct list_head vregion_list; unsigned int region_count; - struct rhashtable chunk_ht; + struct rhashtable vchunk_ht; struct mlxsw_sp_acl_tcam_group_ops *ops; const struct mlxsw_sp_acl_tcam_pattern *patterns; unsigned int patterns_count; @@ -163,40 +171,77 @@ struct mlxsw_sp_acl_tcam_group { struct mlxsw_afk_element_usage tmplt_elusage; }; -struct mlxsw_sp_acl_tcam_chunk { - struct list_head list; /* Member of a TCAM region */ - struct rhash_head ht_node; /* Member of a chunk HT */ - unsigned int priority; /* Priority within the region and group */ +struct mlxsw_sp_acl_tcam_vregion { + struct mlxsw_sp_acl_tcam_region *region; + struct mlxsw_sp_acl_tcam_region *region2; /* Used during migration */ + struct list_head list; /* Member of a TCAM group */ + struct list_head tlist; /* Member of a TCAM */ + struct list_head vchunk_list; /* List of vchunks under this vregion */ struct mlxsw_sp_acl_tcam_group *group; + struct mlxsw_afk_key_info *key_info; + struct mlxsw_sp_acl_tcam *tcam; + struct delayed_work rehash_dw; + struct mlxsw_sp *mlxsw_sp; + bool failed_rollback; /* Indicates failed rollback during migration */ +}; + +struct mlxsw_sp_acl_tcam_vchunk; + +struct mlxsw_sp_acl_tcam_chunk { + struct mlxsw_sp_acl_tcam_vchunk *vchunk; struct mlxsw_sp_acl_tcam_region *region; - unsigned int ref_count; unsigned long priv[0]; /* priv has to be always the last item */ }; +struct mlxsw_sp_acl_tcam_vchunk { + struct mlxsw_sp_acl_tcam_chunk *chunk; + struct mlxsw_sp_acl_tcam_chunk *chunk2; /* Used during migration */ + struct list_head list; /* Member of a TCAM vregion */ + struct rhash_head ht_node; /* Member of a chunk HT */ + struct list_head ventry_list; + unsigned int priority; /* Priority within the vregion and group */ + struct mlxsw_sp_acl_tcam_group *group; + struct mlxsw_sp_acl_tcam_vregion *vregion; + unsigned int ref_count; +}; + struct mlxsw_sp_acl_tcam_entry { + struct mlxsw_sp_acl_tcam_ventry *ventry; struct mlxsw_sp_acl_tcam_chunk *chunk; unsigned long priv[0]; /* priv has to be always the last item */ }; -static const struct rhashtable_params mlxsw_sp_acl_tcam_chunk_ht_params = { +struct mlxsw_sp_acl_tcam_ventry { + struct mlxsw_sp_acl_tcam_entry *entry; + struct list_head list; /* Member of a TCAM vchunk */ + struct mlxsw_sp_acl_tcam_vchunk *vchunk; + struct mlxsw_sp_acl_rule_info *rulei; +}; + +static const struct rhashtable_params mlxsw_sp_acl_tcam_vchunk_ht_params = { .key_len = sizeof(unsigned int), - .key_offset = offsetof(struct mlxsw_sp_acl_tcam_chunk, priority), - .head_offset = offsetof(struct mlxsw_sp_acl_tcam_chunk, ht_node), + .key_offset = offsetof(struct mlxsw_sp_acl_tcam_vchunk, priority), + .head_offset = offsetof(struct mlxsw_sp_acl_tcam_vchunk, ht_node), .automatic_shrinking = true, }; static int mlxsw_sp_acl_tcam_group_update(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_tcam_group *group) { - struct mlxsw_sp_acl_tcam_region *region; + struct mlxsw_sp_acl_tcam_vregion *vregion; char pagt_pl[MLXSW_REG_PAGT_LEN]; int acl_index = 0; mlxsw_reg_pagt_pack(pagt_pl, group->id); - list_for_each_entry(region, &group->region_list, list) - mlxsw_reg_pagt_acl_id_pack(pagt_pl, acl_index++, region->id); + list_for_each_entry(vregion, &group->vregion_list, list) { + if (vregion->region2) + mlxsw_reg_pagt_acl_id_pack(pagt_pl, acl_index++, + vregion->region2->id, true); + mlxsw_reg_pagt_acl_id_pack(pagt_pl, acl_index++, + vregion->region->id, false); + } mlxsw_reg_pagt_size_set(pagt_pl, acl_index); return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pagt), pagt_pl); } @@ -219,13 +264,13 @@ mlxsw_sp_acl_tcam_group_add(struct mlxsw_sp *mlxsw_sp, memcpy(&group->tmplt_elusage, tmplt_elusage, sizeof(group->tmplt_elusage)); } - INIT_LIST_HEAD(&group->region_list); + INIT_LIST_HEAD(&group->vregion_list); err = mlxsw_sp_acl_tcam_group_id_get(tcam, &group->id); if (err) return err; - err = rhashtable_init(&group->chunk_ht, - &mlxsw_sp_acl_tcam_chunk_ht_params); + err = rhashtable_init(&group->vchunk_ht, + &mlxsw_sp_acl_tcam_vchunk_ht_params); if (err) goto err_rhashtable_init; @@ -241,9 +286,9 @@ static void mlxsw_sp_acl_tcam_group_del(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_acl_tcam *tcam = group->tcam; - rhashtable_destroy(&group->chunk_ht); + rhashtable_destroy(&group->vchunk_ht); mlxsw_sp_acl_tcam_group_id_put(tcam, group->id); - WARN_ON(!list_empty(&group->region_list)); + WARN_ON(!list_empty(&group->vregion_list)); } static int @@ -283,140 +328,153 @@ mlxsw_sp_acl_tcam_group_id(struct mlxsw_sp_acl_tcam_group *group) } static unsigned int -mlxsw_sp_acl_tcam_region_prio(struct mlxsw_sp_acl_tcam_region *region) +mlxsw_sp_acl_tcam_vregion_prio(struct mlxsw_sp_acl_tcam_vregion *vregion) { - struct mlxsw_sp_acl_tcam_chunk *chunk; + struct mlxsw_sp_acl_tcam_vchunk *vchunk; - if (list_empty(®ion->chunk_list)) + if (list_empty(&vregion->vchunk_list)) return 0; - /* As a priority of a region, return priority of the first chunk */ - chunk = list_first_entry(®ion->chunk_list, typeof(*chunk), list); - return chunk->priority; + /* As a priority of a vregion, return priority of the first vchunk */ + vchunk = list_first_entry(&vregion->vchunk_list, + typeof(*vchunk), list); + return vchunk->priority; } static unsigned int -mlxsw_sp_acl_tcam_region_max_prio(struct mlxsw_sp_acl_tcam_region *region) +mlxsw_sp_acl_tcam_vregion_max_prio(struct mlxsw_sp_acl_tcam_vregion *vregion) { - struct mlxsw_sp_acl_tcam_chunk *chunk; + struct mlxsw_sp_acl_tcam_vchunk *vchunk; - if (list_empty(®ion->chunk_list)) + if (list_empty(&vregion->vchunk_list)) return 0; - chunk = list_last_entry(®ion->chunk_list, typeof(*chunk), list); - return chunk->priority; + vchunk = list_last_entry(&vregion->vchunk_list, + typeof(*vchunk), list); + return vchunk->priority; } -static void -mlxsw_sp_acl_tcam_group_list_add(struct mlxsw_sp_acl_tcam_group *group, - struct mlxsw_sp_acl_tcam_region *region) +static int +mlxsw_sp_acl_tcam_group_region_attach(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_region *region) { - struct mlxsw_sp_acl_tcam_region *region2; - struct list_head *pos; + struct mlxsw_sp_acl_tcam_group *group = region->vregion->group; + int err; + + if (group->region_count == group->tcam->max_group_size) + return -ENOBUFS; + + err = mlxsw_sp_acl_tcam_group_update(mlxsw_sp, group); + if (err) + return err; - /* Position the region inside the list according to priority */ - list_for_each(pos, &group->region_list) { - region2 = list_entry(pos, typeof(*region2), list); - if (mlxsw_sp_acl_tcam_region_prio(region2) > - mlxsw_sp_acl_tcam_region_prio(region)) - break; - } - list_add_tail(®ion->list, pos); group->region_count++; + return 0; } static void -mlxsw_sp_acl_tcam_group_list_del(struct mlxsw_sp_acl_tcam_group *group, - struct mlxsw_sp_acl_tcam_region *region) +mlxsw_sp_acl_tcam_group_region_detach(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_region *region) { + struct mlxsw_sp_acl_tcam_group *group = region->vregion->group; + group->region_count--; - list_del(®ion->list); + mlxsw_sp_acl_tcam_group_update(mlxsw_sp, group); } static int -mlxsw_sp_acl_tcam_group_region_attach(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam_group *group, - struct mlxsw_sp_acl_tcam_region *region) +mlxsw_sp_acl_tcam_group_vregion_attach(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_group *group, + struct mlxsw_sp_acl_tcam_vregion *vregion) { + struct mlxsw_sp_acl_tcam_vregion *vregion2; + struct list_head *pos; int err; - if (group->region_count == group->tcam->max_group_size) - return -ENOBUFS; - - mlxsw_sp_acl_tcam_group_list_add(group, region); + /* Position the vregion inside the list according to priority */ + list_for_each(pos, &group->vregion_list) { + vregion2 = list_entry(pos, typeof(*vregion2), list); + if (mlxsw_sp_acl_tcam_vregion_prio(vregion2) > + mlxsw_sp_acl_tcam_vregion_prio(vregion)) + break; + } + list_add_tail(&vregion->list, pos); + vregion->group = group; - err = mlxsw_sp_acl_tcam_group_update(mlxsw_sp, group); + err = mlxsw_sp_acl_tcam_group_region_attach(mlxsw_sp, vregion->region); if (err) - goto err_group_update; - region->group = group; + goto err_region_attach; return 0; -err_group_update: - mlxsw_sp_acl_tcam_group_list_del(group, region); - mlxsw_sp_acl_tcam_group_update(mlxsw_sp, group); +err_region_attach: + list_del(&vregion->list); return err; } static void -mlxsw_sp_acl_tcam_group_region_detach(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam_region *region) +mlxsw_sp_acl_tcam_group_vregion_detach(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_vregion *vregion) { - struct mlxsw_sp_acl_tcam_group *group = region->group; - - mlxsw_sp_acl_tcam_group_list_del(group, region); - mlxsw_sp_acl_tcam_group_update(mlxsw_sp, group); + list_del(&vregion->list); + if (vregion->region2) + mlxsw_sp_acl_tcam_group_region_detach(mlxsw_sp, + vregion->region2); + mlxsw_sp_acl_tcam_group_region_detach(mlxsw_sp, vregion->region); } -static struct mlxsw_sp_acl_tcam_region * -mlxsw_sp_acl_tcam_group_region_find(struct mlxsw_sp_acl_tcam_group *group, - unsigned int priority, - struct mlxsw_afk_element_usage *elusage, - bool *p_need_split) +static struct mlxsw_sp_acl_tcam_vregion * +mlxsw_sp_acl_tcam_group_vregion_find(struct mlxsw_sp_acl_tcam_group *group, + unsigned int priority, + struct mlxsw_afk_element_usage *elusage, + bool *p_need_split) { - struct mlxsw_sp_acl_tcam_region *region, *region2; + struct mlxsw_sp_acl_tcam_vregion *vregion, *vregion2; struct list_head *pos; bool issubset; - list_for_each(pos, &group->region_list) { - region = list_entry(pos, typeof(*region), list); + list_for_each(pos, &group->vregion_list) { + vregion = list_entry(pos, typeof(*vregion), list); /* First, check if the requested priority does not rather belong - * under some of the next regions. + * under some of the next vregions. */ - if (pos->next != &group->region_list) { /* not last */ - region2 = list_entry(pos->next, typeof(*region2), list); - if (priority >= mlxsw_sp_acl_tcam_region_prio(region2)) + if (pos->next != &group->vregion_list) { /* not last */ + vregion2 = list_entry(pos->next, typeof(*vregion2), + list); + if (priority >= + mlxsw_sp_acl_tcam_vregion_prio(vregion2)) continue; } - issubset = mlxsw_afk_key_info_subset(region->key_info, elusage); + issubset = mlxsw_afk_key_info_subset(vregion->key_info, + elusage); /* If requested element usage would not fit and the priority - * is lower than the currently inspected region we cannot - * use this region, so return NULL to indicate new region has + * is lower than the currently inspected vregion we cannot + * use this region, so return NULL to indicate new vregion has * to be created. */ if (!issubset && - priority < mlxsw_sp_acl_tcam_region_prio(region)) + priority < mlxsw_sp_acl_tcam_vregion_prio(vregion)) return NULL; /* If requested element usage would not fit and the priority - * is higher than the currently inspected region we cannot - * use this region. There is still some hope that the next - * region would be the fit. So let it be processed and + * is higher than the currently inspected vregion we cannot + * use this vregion. There is still some hope that the next + * vregion would be the fit. So let it be processed and * eventually break at the check right above this. */ if (!issubset && - priority > mlxsw_sp_acl_tcam_region_max_prio(region)) + priority > mlxsw_sp_acl_tcam_vregion_max_prio(vregion)) continue; - /* Indicate if the region needs to be split in order to add + /* Indicate if the vregion needs to be split in order to add * the requested priority. Split is needed when requested - * element usage won't fit into the found region. + * element usage won't fit into the found vregion. */ *p_need_split = !issubset; - return region; + return vregion; } - return NULL; /* New region has to be created. */ + return NULL; /* New vregion has to be created. */ } static void @@ -511,24 +569,19 @@ mlxsw_sp_acl_tcam_region_disable(struct mlxsw_sp *mlxsw_sp, static struct mlxsw_sp_acl_tcam_region * mlxsw_sp_acl_tcam_region_create(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_tcam *tcam, - struct mlxsw_afk_element_usage *elusage) + struct mlxsw_sp_acl_tcam_vregion *vregion, + void *hints_priv) { const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; - struct mlxsw_afk *afk = mlxsw_sp_acl_afk(mlxsw_sp->acl); struct mlxsw_sp_acl_tcam_region *region; int err; region = kzalloc(sizeof(*region) + ops->region_priv_size, GFP_KERNEL); if (!region) return ERR_PTR(-ENOMEM); - INIT_LIST_HEAD(®ion->chunk_list); region->mlxsw_sp = mlxsw_sp; - - region->key_info = mlxsw_afk_key_info_get(afk, elusage); - if (IS_ERR(region->key_info)) { - err = PTR_ERR(region->key_info); - goto err_key_info_get; - } + region->vregion = vregion; + region->key_info = vregion->key_info; err = mlxsw_sp_acl_tcam_region_id_get(tcam, ®ion->id); if (err) @@ -547,7 +600,8 @@ mlxsw_sp_acl_tcam_region_create(struct mlxsw_sp *mlxsw_sp, if (err) goto err_tcam_region_enable; - err = ops->region_init(mlxsw_sp, region->priv, tcam->priv, region); + err = ops->region_init(mlxsw_sp, region->priv, tcam->priv, + region, hints_priv); if (err) goto err_tcam_region_init; @@ -561,8 +615,6 @@ err_tcam_region_alloc: err_tcam_region_associate: mlxsw_sp_acl_tcam_region_id_put(tcam, region->id); err_region_id_get: - mlxsw_afk_key_info_put(region->key_info); -err_key_info_get: kfree(region); return ERR_PTR(err); } @@ -576,217 +628,372 @@ mlxsw_sp_acl_tcam_region_destroy(struct mlxsw_sp *mlxsw_sp, ops->region_fini(mlxsw_sp, region->priv); mlxsw_sp_acl_tcam_region_disable(mlxsw_sp, region); mlxsw_sp_acl_tcam_region_free(mlxsw_sp, region); - mlxsw_sp_acl_tcam_region_id_put(region->group->tcam, region->id); - mlxsw_afk_key_info_put(region->key_info); + mlxsw_sp_acl_tcam_region_id_put(region->vregion->group->tcam, + region->id); kfree(region); } +static void +mlxsw_sp_acl_tcam_vregion_rehash_work_schedule(struct mlxsw_sp_acl_tcam_vregion *vregion) +{ + unsigned long interval = vregion->tcam->vregion_rehash_intrvl; + + if (!interval) + return; + mlxsw_core_schedule_dw(&vregion->rehash_dw, + msecs_to_jiffies(interval)); +} + static int -mlxsw_sp_acl_tcam_chunk_assoc(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam_group *group, - unsigned int priority, - struct mlxsw_afk_element_usage *elusage, - struct mlxsw_sp_acl_tcam_chunk *chunk) +mlxsw_sp_acl_tcam_vregion_rehash(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_vregion *vregion); + +static void mlxsw_sp_acl_tcam_vregion_rehash_work(struct work_struct *work) { - struct mlxsw_sp_acl_tcam_region *region; - bool region_created = false; + struct mlxsw_sp_acl_tcam_vregion *vregion = + container_of(work, struct mlxsw_sp_acl_tcam_vregion, + rehash_dw.work); + + /* TODO: Take rtnl lock here as the rest of the code counts on it + * now. Later, this should be replaced by per-vregion lock. + */ + rtnl_lock(); + mlxsw_sp_acl_tcam_vregion_rehash(vregion->mlxsw_sp, vregion); + rtnl_unlock(); + mlxsw_sp_acl_tcam_vregion_rehash_work_schedule(vregion); +} + +static struct mlxsw_sp_acl_tcam_vregion * +mlxsw_sp_acl_tcam_vregion_create(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam *tcam, + struct mlxsw_afk_element_usage *elusage) +{ + const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; + struct mlxsw_afk *afk = mlxsw_sp_acl_afk(mlxsw_sp->acl); + struct mlxsw_sp_acl_tcam_vregion *vregion; + int err; + + vregion = kzalloc(sizeof(*vregion), GFP_KERNEL); + if (!vregion) + return ERR_PTR(-ENOMEM); + INIT_LIST_HEAD(&vregion->vchunk_list); + vregion->tcam = tcam; + vregion->mlxsw_sp = mlxsw_sp; + + vregion->key_info = mlxsw_afk_key_info_get(afk, elusage); + if (IS_ERR(vregion->key_info)) { + err = PTR_ERR(vregion->key_info); + goto err_key_info_get; + } + + vregion->region = mlxsw_sp_acl_tcam_region_create(mlxsw_sp, tcam, + vregion, NULL); + if (IS_ERR(vregion->region)) { + err = PTR_ERR(vregion->region); + goto err_region_create; + } + + list_add_tail(&vregion->tlist, &tcam->vregion_list); + + if (ops->region_rehash_hints_get) { + /* Create the delayed work for vregion periodic rehash */ + INIT_DELAYED_WORK(&vregion->rehash_dw, + mlxsw_sp_acl_tcam_vregion_rehash_work); + mlxsw_sp_acl_tcam_vregion_rehash_work_schedule(vregion); + } + + return vregion; + +err_region_create: + mlxsw_afk_key_info_put(vregion->key_info); +err_key_info_get: + kfree(vregion); + return ERR_PTR(err); +} + +static void +mlxsw_sp_acl_tcam_vregion_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_vregion *vregion) +{ + const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; + + if (ops->region_rehash_hints_get) + cancel_delayed_work_sync(&vregion->rehash_dw); + list_del(&vregion->tlist); + if (vregion->region2) + mlxsw_sp_acl_tcam_region_destroy(mlxsw_sp, vregion->region2); + mlxsw_sp_acl_tcam_region_destroy(mlxsw_sp, vregion->region); + mlxsw_afk_key_info_put(vregion->key_info); + kfree(vregion); +} + +u32 mlxsw_sp_acl_tcam_vregion_rehash_intrvl_get(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam *tcam) +{ + const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; + u32 vregion_rehash_intrvl; + + if (WARN_ON(!ops->region_rehash_hints_get)) + return 0; + vregion_rehash_intrvl = tcam->vregion_rehash_intrvl; + return vregion_rehash_intrvl; +} + +int mlxsw_sp_acl_tcam_vregion_rehash_intrvl_set(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam *tcam, + u32 val) +{ + const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; + struct mlxsw_sp_acl_tcam_vregion *vregion; + + if (val < MLXSW_SP_ACL_TCAM_VREGION_REHASH_INTRVL_MIN && val) + return -EINVAL; + if (WARN_ON(!ops->region_rehash_hints_get)) + return -EOPNOTSUPP; + tcam->vregion_rehash_intrvl = val; + rtnl_lock(); + list_for_each_entry(vregion, &tcam->vregion_list, tlist) { + if (val) + mlxsw_core_schedule_dw(&vregion->rehash_dw, 0); + else + cancel_delayed_work_sync(&vregion->rehash_dw); + } + rtnl_unlock(); + return 0; +} + +static int +mlxsw_sp_acl_tcam_vchunk_assoc(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_group *group, + unsigned int priority, + struct mlxsw_afk_element_usage *elusage, + struct mlxsw_sp_acl_tcam_vchunk *vchunk) +{ + struct mlxsw_sp_acl_tcam_vregion *vregion; + bool vregion_created = false; bool need_split; int err; - region = mlxsw_sp_acl_tcam_group_region_find(group, priority, elusage, - &need_split); - if (region && need_split) { - /* According to priority, the chunk should belong to an - * existing region. However, this chunk needs elements - * that region does not contain. We need to split the existing - * region into two and create a new region for this chunk + vregion = mlxsw_sp_acl_tcam_group_vregion_find(group, priority, elusage, + &need_split); + if (vregion && need_split) { + /* According to priority, the vchunk should belong to an + * existing vregion. However, this vchunk needs elements + * that vregion does not contain. We need to split the existing + * vregion into two and create a new vregion for this vchunk * in between. This is not supported now. */ return -EOPNOTSUPP; } - if (!region) { - struct mlxsw_afk_element_usage region_elusage; + if (!vregion) { + struct mlxsw_afk_element_usage vregion_elusage; mlxsw_sp_acl_tcam_group_use_patterns(group, elusage, - ®ion_elusage); - region = mlxsw_sp_acl_tcam_region_create(mlxsw_sp, group->tcam, - ®ion_elusage); - if (IS_ERR(region)) - return PTR_ERR(region); - region_created = true; + &vregion_elusage); + vregion = mlxsw_sp_acl_tcam_vregion_create(mlxsw_sp, + group->tcam, + &vregion_elusage); + if (IS_ERR(vregion)) + return PTR_ERR(vregion); + vregion_created = true; } - chunk->region = region; - list_add_tail(&chunk->list, ®ion->chunk_list); + vchunk->vregion = vregion; + list_add_tail(&vchunk->list, &vregion->vchunk_list); - if (!region_created) + if (!vregion_created) return 0; - err = mlxsw_sp_acl_tcam_group_region_attach(mlxsw_sp, group, region); + err = mlxsw_sp_acl_tcam_group_vregion_attach(mlxsw_sp, group, vregion); if (err) - goto err_group_region_attach; + goto err_group_vregion_attach; return 0; -err_group_region_attach: - mlxsw_sp_acl_tcam_region_destroy(mlxsw_sp, region); +err_group_vregion_attach: + mlxsw_sp_acl_tcam_vregion_destroy(mlxsw_sp, vregion); return err; } static void -mlxsw_sp_acl_tcam_chunk_deassoc(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam_chunk *chunk) +mlxsw_sp_acl_tcam_vchunk_deassoc(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_vchunk *vchunk) { - struct mlxsw_sp_acl_tcam_region *region = chunk->region; + struct mlxsw_sp_acl_tcam_vregion *vregion = vchunk->vregion; - list_del(&chunk->list); - if (list_empty(®ion->chunk_list)) { - mlxsw_sp_acl_tcam_group_region_detach(mlxsw_sp, region); - mlxsw_sp_acl_tcam_region_destroy(mlxsw_sp, region); + list_del(&vchunk->list); + if (list_empty(&vregion->vchunk_list)) { + mlxsw_sp_acl_tcam_group_vregion_detach(mlxsw_sp, vregion); + mlxsw_sp_acl_tcam_vregion_destroy(mlxsw_sp, vregion); } } static struct mlxsw_sp_acl_tcam_chunk * mlxsw_sp_acl_tcam_chunk_create(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam_group *group, - unsigned int priority, - struct mlxsw_afk_element_usage *elusage) + struct mlxsw_sp_acl_tcam_vchunk *vchunk, + struct mlxsw_sp_acl_tcam_region *region) { const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; struct mlxsw_sp_acl_tcam_chunk *chunk; + + chunk = kzalloc(sizeof(*chunk) + ops->chunk_priv_size, GFP_KERNEL); + if (!chunk) + return ERR_PTR(-ENOMEM); + chunk->vchunk = vchunk; + chunk->region = region; + + ops->chunk_init(region->priv, chunk->priv, vchunk->priority); + return chunk; +} + +static void +mlxsw_sp_acl_tcam_chunk_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_chunk *chunk) +{ + const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; + + ops->chunk_fini(chunk->priv); + kfree(chunk); +} + +static struct mlxsw_sp_acl_tcam_vchunk * +mlxsw_sp_acl_tcam_vchunk_create(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_group *group, + unsigned int priority, + struct mlxsw_afk_element_usage *elusage) +{ + struct mlxsw_sp_acl_tcam_vchunk *vchunk; int err; if (priority == MLXSW_SP_ACL_TCAM_CATCHALL_PRIO) return ERR_PTR(-EINVAL); - chunk = kzalloc(sizeof(*chunk) + ops->chunk_priv_size, GFP_KERNEL); - if (!chunk) + vchunk = kzalloc(sizeof(*vchunk), GFP_KERNEL); + if (!vchunk) return ERR_PTR(-ENOMEM); - chunk->priority = priority; - chunk->group = group; - chunk->ref_count = 1; + INIT_LIST_HEAD(&vchunk->ventry_list); + vchunk->priority = priority; + vchunk->group = group; + vchunk->ref_count = 1; - err = mlxsw_sp_acl_tcam_chunk_assoc(mlxsw_sp, group, priority, - elusage, chunk); + err = mlxsw_sp_acl_tcam_vchunk_assoc(mlxsw_sp, group, priority, + elusage, vchunk); if (err) - goto err_chunk_assoc; + goto err_vchunk_assoc; - ops->chunk_init(chunk->region->priv, chunk->priv, priority); - - err = rhashtable_insert_fast(&group->chunk_ht, &chunk->ht_node, - mlxsw_sp_acl_tcam_chunk_ht_params); + err = rhashtable_insert_fast(&group->vchunk_ht, &vchunk->ht_node, + mlxsw_sp_acl_tcam_vchunk_ht_params); if (err) goto err_rhashtable_insert; - return chunk; + vchunk->chunk = mlxsw_sp_acl_tcam_chunk_create(mlxsw_sp, vchunk, + vchunk->vregion->region); + if (IS_ERR(vchunk->chunk)) { + err = PTR_ERR(vchunk->chunk); + goto err_chunk_create; + } + + return vchunk; +err_chunk_create: + rhashtable_remove_fast(&group->vchunk_ht, &vchunk->ht_node, + mlxsw_sp_acl_tcam_vchunk_ht_params); err_rhashtable_insert: - ops->chunk_fini(chunk->priv); - mlxsw_sp_acl_tcam_chunk_deassoc(mlxsw_sp, chunk); -err_chunk_assoc: - kfree(chunk); + mlxsw_sp_acl_tcam_vchunk_deassoc(mlxsw_sp, vchunk); +err_vchunk_assoc: + kfree(vchunk); return ERR_PTR(err); } static void -mlxsw_sp_acl_tcam_chunk_destroy(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam_chunk *chunk) +mlxsw_sp_acl_tcam_vchunk_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_vchunk *vchunk) { - const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; - struct mlxsw_sp_acl_tcam_group *group = chunk->group; - - rhashtable_remove_fast(&group->chunk_ht, &chunk->ht_node, - mlxsw_sp_acl_tcam_chunk_ht_params); - ops->chunk_fini(chunk->priv); - mlxsw_sp_acl_tcam_chunk_deassoc(mlxsw_sp, chunk); - kfree(chunk); + struct mlxsw_sp_acl_tcam_group *group = vchunk->group; + + if (vchunk->chunk2) + mlxsw_sp_acl_tcam_chunk_destroy(mlxsw_sp, vchunk->chunk2); + mlxsw_sp_acl_tcam_chunk_destroy(mlxsw_sp, vchunk->chunk); + rhashtable_remove_fast(&group->vchunk_ht, &vchunk->ht_node, + mlxsw_sp_acl_tcam_vchunk_ht_params); + mlxsw_sp_acl_tcam_vchunk_deassoc(mlxsw_sp, vchunk); + kfree(vchunk); } -static struct mlxsw_sp_acl_tcam_chunk * -mlxsw_sp_acl_tcam_chunk_get(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam_group *group, - unsigned int priority, - struct mlxsw_afk_element_usage *elusage) +static struct mlxsw_sp_acl_tcam_vchunk * +mlxsw_sp_acl_tcam_vchunk_get(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_group *group, + unsigned int priority, + struct mlxsw_afk_element_usage *elusage) { - struct mlxsw_sp_acl_tcam_chunk *chunk; + struct mlxsw_sp_acl_tcam_vchunk *vchunk; - chunk = rhashtable_lookup_fast(&group->chunk_ht, &priority, - mlxsw_sp_acl_tcam_chunk_ht_params); - if (chunk) { - if (WARN_ON(!mlxsw_afk_key_info_subset(chunk->region->key_info, + vchunk = rhashtable_lookup_fast(&group->vchunk_ht, &priority, + mlxsw_sp_acl_tcam_vchunk_ht_params); + if (vchunk) { + if (WARN_ON(!mlxsw_afk_key_info_subset(vchunk->vregion->key_info, elusage))) return ERR_PTR(-EINVAL); - chunk->ref_count++; - return chunk; + vchunk->ref_count++; + return vchunk; } - return mlxsw_sp_acl_tcam_chunk_create(mlxsw_sp, group, - priority, elusage); + return mlxsw_sp_acl_tcam_vchunk_create(mlxsw_sp, group, + priority, elusage); } -static void mlxsw_sp_acl_tcam_chunk_put(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam_chunk *chunk) +static void +mlxsw_sp_acl_tcam_vchunk_put(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_vchunk *vchunk) { - if (--chunk->ref_count) + if (--vchunk->ref_count) return; - mlxsw_sp_acl_tcam_chunk_destroy(mlxsw_sp, chunk); + mlxsw_sp_acl_tcam_vchunk_destroy(mlxsw_sp, vchunk); } -static size_t mlxsw_sp_acl_tcam_entry_priv_size(struct mlxsw_sp *mlxsw_sp) -{ - const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; - - return ops->entry_priv_size; -} - -static int mlxsw_sp_acl_tcam_entry_add(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam_group *group, - struct mlxsw_sp_acl_tcam_entry *entry, - struct mlxsw_sp_acl_rule_info *rulei) +static struct mlxsw_sp_acl_tcam_entry * +mlxsw_sp_acl_tcam_entry_create(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_ventry *ventry, + struct mlxsw_sp_acl_tcam_chunk *chunk) { const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; - struct mlxsw_sp_acl_tcam_chunk *chunk; - struct mlxsw_sp_acl_tcam_region *region; + struct mlxsw_sp_acl_tcam_entry *entry; int err; - chunk = mlxsw_sp_acl_tcam_chunk_get(mlxsw_sp, group, rulei->priority, - &rulei->values.elusage); - if (IS_ERR(chunk)) - return PTR_ERR(chunk); - - region = chunk->region; + entry = kzalloc(sizeof(*entry) + ops->entry_priv_size, GFP_KERNEL); + if (!entry) + return ERR_PTR(-ENOMEM); + entry->ventry = ventry; + entry->chunk = chunk; - err = ops->entry_add(mlxsw_sp, region->priv, chunk->priv, - entry->priv, rulei); + err = ops->entry_add(mlxsw_sp, chunk->region->priv, chunk->priv, + entry->priv, ventry->rulei); if (err) goto err_entry_add; - entry->chunk = chunk; - return 0; + return entry; err_entry_add: - mlxsw_sp_acl_tcam_chunk_put(mlxsw_sp, chunk); - return err; + kfree(entry); + return ERR_PTR(err); } -static void mlxsw_sp_acl_tcam_entry_del(struct mlxsw_sp *mlxsw_sp, - struct mlxsw_sp_acl_tcam_entry *entry) +static void mlxsw_sp_acl_tcam_entry_destroy(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_entry *entry) { const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; - struct mlxsw_sp_acl_tcam_chunk *chunk = entry->chunk; - struct mlxsw_sp_acl_tcam_region *region = chunk->region; - ops->entry_del(mlxsw_sp, region->priv, chunk->priv, entry->priv); - mlxsw_sp_acl_tcam_chunk_put(mlxsw_sp, chunk); + ops->entry_del(mlxsw_sp, entry->chunk->region->priv, + entry->chunk->priv, entry->priv); + kfree(entry); } static int mlxsw_sp_acl_tcam_entry_action_replace(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_region *region, struct mlxsw_sp_acl_tcam_entry *entry, struct mlxsw_sp_acl_rule_info *rulei) { const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; - struct mlxsw_sp_acl_tcam_chunk *chunk = entry->chunk; - struct mlxsw_sp_acl_tcam_region *region = chunk->region; return ops->entry_action_replace(mlxsw_sp, region->priv, entry->priv, rulei); @@ -798,13 +1005,249 @@ mlxsw_sp_acl_tcam_entry_activity_get(struct mlxsw_sp *mlxsw_sp, bool *activity) { const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; - struct mlxsw_sp_acl_tcam_chunk *chunk = entry->chunk; - struct mlxsw_sp_acl_tcam_region *region = chunk->region; - return ops->entry_activity_get(mlxsw_sp, region->priv, + return ops->entry_activity_get(mlxsw_sp, entry->chunk->region->priv, entry->priv, activity); } +static int mlxsw_sp_acl_tcam_ventry_add(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_group *group, + struct mlxsw_sp_acl_tcam_ventry *ventry, + struct mlxsw_sp_acl_rule_info *rulei) +{ + struct mlxsw_sp_acl_tcam_vchunk *vchunk; + int err; + + vchunk = mlxsw_sp_acl_tcam_vchunk_get(mlxsw_sp, group, rulei->priority, + &rulei->values.elusage); + if (IS_ERR(vchunk)) + return PTR_ERR(vchunk); + + ventry->vchunk = vchunk; + ventry->rulei = rulei; + ventry->entry = mlxsw_sp_acl_tcam_entry_create(mlxsw_sp, ventry, + vchunk->chunk); + if (IS_ERR(ventry->entry)) { + err = PTR_ERR(ventry->entry); + goto err_entry_create; + } + + list_add_tail(&ventry->list, &vchunk->ventry_list); + + return 0; + +err_entry_create: + mlxsw_sp_acl_tcam_vchunk_put(mlxsw_sp, vchunk); + return err; +} + +static void mlxsw_sp_acl_tcam_ventry_del(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_ventry *ventry) +{ + struct mlxsw_sp_acl_tcam_vchunk *vchunk = ventry->vchunk; + + list_del(&ventry->list); + mlxsw_sp_acl_tcam_entry_destroy(mlxsw_sp, ventry->entry); + mlxsw_sp_acl_tcam_vchunk_put(mlxsw_sp, vchunk); +} + +static int +mlxsw_sp_acl_tcam_ventry_action_replace(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_ventry *ventry, + struct mlxsw_sp_acl_rule_info *rulei) +{ + struct mlxsw_sp_acl_tcam_vchunk *vchunk = ventry->vchunk; + + return mlxsw_sp_acl_tcam_entry_action_replace(mlxsw_sp, + vchunk->vregion->region, + ventry->entry, rulei); +} + +static int +mlxsw_sp_acl_tcam_ventry_activity_get(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_ventry *ventry, + bool *activity) +{ + return mlxsw_sp_acl_tcam_entry_activity_get(mlxsw_sp, + ventry->entry, activity); +} + +static int +mlxsw_sp_acl_tcam_ventry_migrate(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_ventry *ventry, + struct mlxsw_sp_acl_tcam_chunk *chunk2) +{ + struct mlxsw_sp_acl_tcam_entry *entry2; + + entry2 = mlxsw_sp_acl_tcam_entry_create(mlxsw_sp, ventry, chunk2); + if (IS_ERR(entry2)) + return PTR_ERR(entry2); + mlxsw_sp_acl_tcam_entry_destroy(mlxsw_sp, ventry->entry); + ventry->entry = entry2; + return 0; +} + +static int +mlxsw_sp_acl_tcam_vchunk_migrate_one(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_vchunk *vchunk, + struct mlxsw_sp_acl_tcam_region *region, + bool this_is_rollback) +{ + struct mlxsw_sp_acl_tcam_ventry *ventry; + struct mlxsw_sp_acl_tcam_chunk *chunk2; + int err; + int err2; + + chunk2 = mlxsw_sp_acl_tcam_chunk_create(mlxsw_sp, vchunk, region); + if (IS_ERR(chunk2)) { + if (this_is_rollback) + vchunk->vregion->failed_rollback = true; + return PTR_ERR(chunk2); + } + vchunk->chunk2 = chunk2; + list_for_each_entry(ventry, &vchunk->ventry_list, list) { + err = mlxsw_sp_acl_tcam_ventry_migrate(mlxsw_sp, ventry, + vchunk->chunk2); + if (err) { + if (this_is_rollback) { + vchunk->vregion->failed_rollback = true; + return err; + } + goto rollback; + } + } + mlxsw_sp_acl_tcam_chunk_destroy(mlxsw_sp, vchunk->chunk); + vchunk->chunk = chunk2; + vchunk->chunk2 = NULL; + return 0; + +rollback: + /* Migrate the entries back to the original chunk. If some entry + * migration fails, there's no good way how to proceed. Set the + * vregion with "failed_rollback" flag. + */ + list_for_each_entry_continue_reverse(ventry, &vchunk->ventry_list, + list) { + err2 = mlxsw_sp_acl_tcam_ventry_migrate(mlxsw_sp, ventry, + vchunk->chunk); + if (err2) { + vchunk->vregion->failed_rollback = true; + goto err_rollback; + } + } + + mlxsw_sp_acl_tcam_chunk_destroy(mlxsw_sp, vchunk->chunk2); + vchunk->chunk2 = NULL; + +err_rollback: + return err; +} + +static int +mlxsw_sp_acl_tcam_vchunk_migrate_all(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_vregion *vregion) +{ + struct mlxsw_sp_acl_tcam_vchunk *vchunk; + int err; + + list_for_each_entry(vchunk, &vregion->vchunk_list, list) { + err = mlxsw_sp_acl_tcam_vchunk_migrate_one(mlxsw_sp, vchunk, + vregion->region2, + false); + if (err) + goto rollback; + } + return 0; + +rollback: + list_for_each_entry_continue_reverse(vchunk, &vregion->vchunk_list, + list) { + mlxsw_sp_acl_tcam_vchunk_migrate_one(mlxsw_sp, vchunk, + vregion->region, true); + } + return err; +} + +static int +mlxsw_sp_acl_tcam_vregion_migrate(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_vregion *vregion, + void *hints_priv) +{ + struct mlxsw_sp_acl_tcam_region *region2, *unused_region; + int err; + + trace_mlxsw_sp_acl_tcam_vregion_migrate(mlxsw_sp, vregion); + + region2 = mlxsw_sp_acl_tcam_region_create(mlxsw_sp, vregion->tcam, + vregion, hints_priv); + if (IS_ERR(region2)) + return PTR_ERR(region2); + + vregion->region2 = region2; + err = mlxsw_sp_acl_tcam_group_region_attach(mlxsw_sp, region2); + if (err) + goto err_group_region_attach; + + err = mlxsw_sp_acl_tcam_vchunk_migrate_all(mlxsw_sp, vregion); + if (!vregion->failed_rollback) { + if (!err) { + /* In case of successful migration, region2 is used and + * the original is unused. + */ + unused_region = vregion->region; + vregion->region = vregion->region2; + } else { + /* In case of failure during migration, the original + * region is still used. + */ + unused_region = vregion->region2; + } + vregion->region2 = NULL; + mlxsw_sp_acl_tcam_group_region_detach(mlxsw_sp, unused_region); + mlxsw_sp_acl_tcam_region_destroy(mlxsw_sp, unused_region); + } + return err; + +err_group_region_attach: + vregion->region2 = NULL; + mlxsw_sp_acl_tcam_region_destroy(mlxsw_sp, region2); + return err; +} + +static int +mlxsw_sp_acl_tcam_vregion_rehash(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam_vregion *vregion) +{ + const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops; + void *hints_priv; + int err; + + trace_mlxsw_sp_acl_tcam_vregion_rehash(mlxsw_sp, vregion); + if (vregion->failed_rollback) + return -EBUSY; + + hints_priv = ops->region_rehash_hints_get(vregion->region->priv); + if (IS_ERR(hints_priv)) { + err = PTR_ERR(hints_priv); + if (err != -EAGAIN) + dev_err(mlxsw_sp->bus_info->dev, "Failed get rehash hints\n"); + return err; + } + + err = mlxsw_sp_acl_tcam_vregion_migrate(mlxsw_sp, vregion, hints_priv); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Failed to migrate vregion\n"); + if (vregion->failed_rollback) { + trace_mlxsw_sp_acl_tcam_vregion_rehash_dis(mlxsw_sp, + vregion); + dev_err(mlxsw_sp->bus_info->dev, "Failed to rollback during vregion migration fail\n"); + } + } + + ops->region_rehash_hints_put(hints_priv); + return err; +} + static const enum mlxsw_afk_element mlxsw_sp_acl_tcam_pattern_ipv4[] = { MLXSW_AFK_ELEMENT_SRC_SYS_PORT, MLXSW_AFK_ELEMENT_DMAC_32_47, @@ -859,7 +1302,7 @@ struct mlxsw_sp_acl_tcam_flower_ruleset { }; struct mlxsw_sp_acl_tcam_flower_rule { - struct mlxsw_sp_acl_tcam_entry entry; + struct mlxsw_sp_acl_tcam_ventry ventry; }; static int @@ -917,12 +1360,6 @@ mlxsw_sp_acl_tcam_flower_ruleset_group_id(void *ruleset_priv) return mlxsw_sp_acl_tcam_group_id(&ruleset->group); } -static size_t mlxsw_sp_acl_tcam_flower_rule_priv_size(struct mlxsw_sp *mlxsw_sp) -{ - return sizeof(struct mlxsw_sp_acl_tcam_flower_rule) + - mlxsw_sp_acl_tcam_entry_priv_size(mlxsw_sp); -} - static int mlxsw_sp_acl_tcam_flower_rule_add(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv, void *rule_priv, @@ -931,8 +1368,8 @@ mlxsw_sp_acl_tcam_flower_rule_add(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_tcam_flower_ruleset *ruleset = ruleset_priv; struct mlxsw_sp_acl_tcam_flower_rule *rule = rule_priv; - return mlxsw_sp_acl_tcam_entry_add(mlxsw_sp, &ruleset->group, - &rule->entry, rulei); + return mlxsw_sp_acl_tcam_ventry_add(mlxsw_sp, &ruleset->group, + &rule->ventry, rulei); } static void @@ -940,7 +1377,7 @@ mlxsw_sp_acl_tcam_flower_rule_del(struct mlxsw_sp *mlxsw_sp, void *rule_priv) { struct mlxsw_sp_acl_tcam_flower_rule *rule = rule_priv; - mlxsw_sp_acl_tcam_entry_del(mlxsw_sp, &rule->entry); + mlxsw_sp_acl_tcam_ventry_del(mlxsw_sp, &rule->ventry); } static int @@ -957,8 +1394,8 @@ mlxsw_sp_acl_tcam_flower_rule_activity_get(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_acl_tcam_flower_rule *rule = rule_priv; - return mlxsw_sp_acl_tcam_entry_activity_get(mlxsw_sp, &rule->entry, - activity); + return mlxsw_sp_acl_tcam_ventry_activity_get(mlxsw_sp, &rule->ventry, + activity); } static const struct mlxsw_sp_acl_profile_ops mlxsw_sp_acl_tcam_flower_ops = { @@ -968,7 +1405,7 @@ static const struct mlxsw_sp_acl_profile_ops mlxsw_sp_acl_tcam_flower_ops = { .ruleset_bind = mlxsw_sp_acl_tcam_flower_ruleset_bind, .ruleset_unbind = mlxsw_sp_acl_tcam_flower_ruleset_unbind, .ruleset_group_id = mlxsw_sp_acl_tcam_flower_ruleset_group_id, - .rule_priv_size = mlxsw_sp_acl_tcam_flower_rule_priv_size, + .rule_priv_size = sizeof(struct mlxsw_sp_acl_tcam_flower_rule), .rule_add = mlxsw_sp_acl_tcam_flower_rule_add, .rule_del = mlxsw_sp_acl_tcam_flower_rule_del, .rule_action_replace = mlxsw_sp_acl_tcam_flower_rule_action_replace, @@ -976,12 +1413,12 @@ static const struct mlxsw_sp_acl_profile_ops mlxsw_sp_acl_tcam_flower_ops = { }; struct mlxsw_sp_acl_tcam_mr_ruleset { - struct mlxsw_sp_acl_tcam_chunk *chunk; + struct mlxsw_sp_acl_tcam_vchunk *vchunk; struct mlxsw_sp_acl_tcam_group group; }; struct mlxsw_sp_acl_tcam_mr_rule { - struct mlxsw_sp_acl_tcam_entry entry; + struct mlxsw_sp_acl_tcam_ventry ventry; }; static int @@ -1006,10 +1443,11 @@ mlxsw_sp_acl_tcam_mr_ruleset_add(struct mlxsw_sp *mlxsw_sp, * specific ACL Group ID which must exist in HW before multicast router * is initialized. */ - ruleset->chunk = mlxsw_sp_acl_tcam_chunk_get(mlxsw_sp, &ruleset->group, - 1, tmplt_elusage); - if (IS_ERR(ruleset->chunk)) { - err = PTR_ERR(ruleset->chunk); + ruleset->vchunk = mlxsw_sp_acl_tcam_vchunk_get(mlxsw_sp, + &ruleset->group, 1, + tmplt_elusage); + if (IS_ERR(ruleset->vchunk)) { + err = PTR_ERR(ruleset->vchunk); goto err_chunk_get; } @@ -1025,7 +1463,7 @@ mlxsw_sp_acl_tcam_mr_ruleset_del(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv) { struct mlxsw_sp_acl_tcam_mr_ruleset *ruleset = ruleset_priv; - mlxsw_sp_acl_tcam_chunk_put(mlxsw_sp, ruleset->chunk); + mlxsw_sp_acl_tcam_vchunk_put(mlxsw_sp, ruleset->vchunk); mlxsw_sp_acl_tcam_group_del(mlxsw_sp, &ruleset->group); } @@ -1054,12 +1492,6 @@ mlxsw_sp_acl_tcam_mr_ruleset_group_id(void *ruleset_priv) return mlxsw_sp_acl_tcam_group_id(&ruleset->group); } -static size_t mlxsw_sp_acl_tcam_mr_rule_priv_size(struct mlxsw_sp *mlxsw_sp) -{ - return sizeof(struct mlxsw_sp_acl_tcam_mr_rule) + - mlxsw_sp_acl_tcam_entry_priv_size(mlxsw_sp); -} - static int mlxsw_sp_acl_tcam_mr_rule_add(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv, void *rule_priv, @@ -1068,8 +1500,8 @@ mlxsw_sp_acl_tcam_mr_rule_add(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv, struct mlxsw_sp_acl_tcam_mr_ruleset *ruleset = ruleset_priv; struct mlxsw_sp_acl_tcam_mr_rule *rule = rule_priv; - return mlxsw_sp_acl_tcam_entry_add(mlxsw_sp, &ruleset->group, - &rule->entry, rulei); + return mlxsw_sp_acl_tcam_ventry_add(mlxsw_sp, &ruleset->group, + &rule->ventry, rulei); } static void @@ -1077,7 +1509,7 @@ mlxsw_sp_acl_tcam_mr_rule_del(struct mlxsw_sp *mlxsw_sp, void *rule_priv) { struct mlxsw_sp_acl_tcam_mr_rule *rule = rule_priv; - mlxsw_sp_acl_tcam_entry_del(mlxsw_sp, &rule->entry); + mlxsw_sp_acl_tcam_ventry_del(mlxsw_sp, &rule->ventry); } static int @@ -1087,8 +1519,8 @@ mlxsw_sp_acl_tcam_mr_rule_action_replace(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_acl_tcam_mr_rule *rule = rule_priv; - return mlxsw_sp_acl_tcam_entry_action_replace(mlxsw_sp, &rule->entry, - rulei); + return mlxsw_sp_acl_tcam_ventry_action_replace(mlxsw_sp, &rule->ventry, + rulei); } static int @@ -1097,8 +1529,8 @@ mlxsw_sp_acl_tcam_mr_rule_activity_get(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_acl_tcam_mr_rule *rule = rule_priv; - return mlxsw_sp_acl_tcam_entry_activity_get(mlxsw_sp, &rule->entry, - activity); + return mlxsw_sp_acl_tcam_ventry_activity_get(mlxsw_sp, &rule->ventry, + activity); } static const struct mlxsw_sp_acl_profile_ops mlxsw_sp_acl_tcam_mr_ops = { @@ -1108,7 +1540,7 @@ static const struct mlxsw_sp_acl_profile_ops mlxsw_sp_acl_tcam_mr_ops = { .ruleset_bind = mlxsw_sp_acl_tcam_mr_ruleset_bind, .ruleset_unbind = mlxsw_sp_acl_tcam_mr_ruleset_unbind, .ruleset_group_id = mlxsw_sp_acl_tcam_mr_ruleset_group_id, - .rule_priv_size = mlxsw_sp_acl_tcam_mr_rule_priv_size, + .rule_priv_size = sizeof(struct mlxsw_sp_acl_tcam_mr_rule), .rule_add = mlxsw_sp_acl_tcam_mr_rule_add, .rule_del = mlxsw_sp_acl_tcam_mr_rule_del, .rule_action_replace = mlxsw_sp_acl_tcam_mr_rule_action_replace, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h index 10512b7c6d50..96bd42a9fbc3 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h @@ -17,6 +17,8 @@ struct mlxsw_sp_acl_tcam { unsigned long *used_groups; /* bit array */ unsigned int max_groups; unsigned int max_group_size; + struct list_head vregion_list; + u32 vregion_rehash_intrvl; /* ms */ unsigned long priv[0]; /* priv has to be always the last item */ }; @@ -26,6 +28,11 @@ int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_tcam *tcam); void mlxsw_sp_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_tcam *tcam); +u32 mlxsw_sp_acl_tcam_vregion_rehash_intrvl_get(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam *tcam); +int mlxsw_sp_acl_tcam_vregion_rehash_intrvl_set(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_acl_tcam *tcam, + u32 val); int mlxsw_sp_acl_tcam_priority_get(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_rule_info *rulei, u32 *priority, bool fillup_priority); @@ -43,7 +50,7 @@ struct mlxsw_sp_acl_profile_ops { struct mlxsw_sp_port *mlxsw_sp_port, bool ingress); u16 (*ruleset_group_id)(void *ruleset_priv); - size_t (*rule_priv_size)(struct mlxsw_sp *mlxsw_sp); + size_t rule_priv_size; int (*rule_add)(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv, void *rule_priv, struct mlxsw_sp_acl_rule_info *rulei); @@ -67,11 +74,10 @@ mlxsw_sp_acl_tcam_profile_ops(struct mlxsw_sp *mlxsw_sp, (MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN * BITS_PER_BYTE) struct mlxsw_sp_acl_tcam_group; +struct mlxsw_sp_acl_tcam_vregion; struct mlxsw_sp_acl_tcam_region { - struct list_head list; /* Member of a TCAM group */ - struct list_head chunk_list; /* List of chunks under this region */ - struct mlxsw_sp_acl_tcam_group *group; + struct mlxsw_sp_acl_tcam_vregion *vregion; enum mlxsw_reg_ptar_key_type key_type; u16 id; /* ACL ID and region ID - they are same */ char tcam_region_info[MLXSW_REG_PXXX_TCAM_REGION_INFO_LEN]; @@ -161,9 +167,9 @@ struct mlxsw_sp_acl_atcam_region { }; struct mlxsw_sp_acl_atcam_entry_ht_key { - char enc_key[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; /* Encoded key, - * minus delta bits. - */ + char full_enc_key[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; /* Encoded + * key. + */ u8 erp_id; }; @@ -175,7 +181,9 @@ struct mlxsw_sp_acl_atcam_entry { struct rhash_head ht_node; struct list_head list; /* Member in entries_list */ struct mlxsw_sp_acl_atcam_entry_ht_key ht_key; - char full_enc_key[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; /* Encoded key */ + char enc_key[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; /* Encoded key, + * minus delta bits. + */ struct { u16 start; u8 mask; @@ -205,6 +213,7 @@ mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_atcam *atcam, struct mlxsw_sp_acl_atcam_region *aregion, struct mlxsw_sp_acl_tcam_region *region, + void *hints_priv, const struct mlxsw_sp_acl_ctcam_region_ops *ops); void mlxsw_sp_acl_atcam_region_fini(struct mlxsw_sp_acl_atcam_region *aregion); void mlxsw_sp_acl_atcam_chunk_init(struct mlxsw_sp_acl_atcam_region *aregion, @@ -228,6 +237,9 @@ int mlxsw_sp_acl_atcam_init(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_atcam *atcam); void mlxsw_sp_acl_atcam_fini(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_atcam *atcam); +void * +mlxsw_sp_acl_atcam_rehash_hints_get(struct mlxsw_sp_acl_atcam_region *aregion); +void mlxsw_sp_acl_atcam_rehash_hints_put(void *hints_priv); struct mlxsw_sp_acl_erp_delta; @@ -258,7 +270,11 @@ void mlxsw_sp_acl_erp_bf_remove(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_atcam_region *aregion, struct mlxsw_sp_acl_erp_mask *erp_mask, struct mlxsw_sp_acl_atcam_entry *aentry); -int mlxsw_sp_acl_erp_region_init(struct mlxsw_sp_acl_atcam_region *aregion); +void * +mlxsw_sp_acl_erp_rehash_hints_get(struct mlxsw_sp_acl_atcam_region *aregion); +void mlxsw_sp_acl_erp_rehash_hints_put(void *hints_priv); +int mlxsw_sp_acl_erp_region_init(struct mlxsw_sp_acl_atcam_region *aregion, + void *hints_priv); void mlxsw_sp_acl_erp_region_fini(struct mlxsw_sp_acl_atcam_region *aregion); int mlxsw_sp_acl_erps_init(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_atcam *atcam); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c index 12c61e0cc570..80066f437a65 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c @@ -713,6 +713,7 @@ int mlxsw_sp_sb_pool_get(struct mlxsw_core *mlxsw_core, pool_info->pool_type = (enum devlink_sb_pool_type) dir; pool_info->size = mlxsw_sp_cells_bytes(mlxsw_sp, pr->size); pool_info->threshold_type = (enum devlink_sb_threshold_type) pr->mode; + pool_info->cell_size = mlxsw_sp->sb->cell_size; return 0; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c index ff072358d950..15f804453cd6 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c @@ -17,13 +17,13 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_block *block, struct mlxsw_sp_acl_rule_info *rulei, - struct tcf_exts *exts, + struct flow_action *flow_action, struct netlink_ext_ack *extack) { - const struct tc_action *a; + const struct flow_action_entry *act; int err, i; - if (!tcf_exts_has_actions(exts)) + if (!flow_action_has_entries(flow_action)) return 0; /* Count action is inserted first */ @@ -31,27 +31,31 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, if (err) return err; - tcf_exts_for_each_action(i, a, exts) { - if (is_tcf_gact_ok(a)) { + flow_action_for_each(i, act, flow_action) { + switch (act->id) { + case FLOW_ACTION_ACCEPT: err = mlxsw_sp_acl_rulei_act_terminate(rulei); if (err) { NL_SET_ERR_MSG_MOD(extack, "Cannot append terminate action"); return err; } - } else if (is_tcf_gact_shot(a)) { + break; + case FLOW_ACTION_DROP: err = mlxsw_sp_acl_rulei_act_drop(rulei); if (err) { NL_SET_ERR_MSG_MOD(extack, "Cannot append drop action"); return err; } - } else if (is_tcf_gact_trap(a)) { + break; + case FLOW_ACTION_TRAP: err = mlxsw_sp_acl_rulei_act_trap(rulei); if (err) { NL_SET_ERR_MSG_MOD(extack, "Cannot append trap action"); return err; } - } else if (is_tcf_gact_goto_chain(a)) { - u32 chain_index = tcf_gact_goto_chain_index(a); + break; + case FLOW_ACTION_GOTO: { + u32 chain_index = act->chain_index; struct mlxsw_sp_acl_ruleset *ruleset; u16 group_id; @@ -67,7 +71,9 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, NL_SET_ERR_MSG_MOD(extack, "Cannot append jump action"); return err; } - } else if (is_tcf_mirred_egress_redirect(a)) { + } + break; + case FLOW_ACTION_REDIRECT: { struct net_device *out_dev; struct mlxsw_sp_fid *fid; u16 fid_index; @@ -79,29 +85,33 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, if (err) return err; - out_dev = tcf_mirred_dev(a); + out_dev = act->dev; err = mlxsw_sp_acl_rulei_act_fwd(mlxsw_sp, rulei, out_dev, extack); if (err) return err; - } else if (is_tcf_mirred_egress_mirror(a)) { - struct net_device *out_dev = tcf_mirred_dev(a); + } + break; + case FLOW_ACTION_MIRRED: { + struct net_device *out_dev = act->dev; err = mlxsw_sp_acl_rulei_act_mirror(mlxsw_sp, rulei, block, out_dev, extack); if (err) return err; - } else if (is_tcf_vlan(a)) { - u16 proto = be16_to_cpu(tcf_vlan_push_proto(a)); - u32 action = tcf_vlan_action(a); - u8 prio = tcf_vlan_push_prio(a); - u16 vid = tcf_vlan_push_vid(a); + } + break; + case FLOW_ACTION_VLAN_MANGLE: { + u16 proto = be16_to_cpu(act->vlan.proto); + u8 prio = act->vlan.prio; + u16 vid = act->vlan.vid; return mlxsw_sp_acl_rulei_act_vlan(mlxsw_sp, rulei, - action, vid, + act->id, vid, proto, prio, extack); - } else { + } + default: NL_SET_ERR_MSG_MOD(extack, "Unsupported action"); dev_err(mlxsw_sp->bus_info->dev, "Unsupported action\n"); return -EOPNOTSUPP; @@ -113,59 +123,49 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, static void mlxsw_sp_flower_parse_ipv4(struct mlxsw_sp_acl_rule_info *rulei, struct tc_cls_flower_offload *f) { - struct flow_dissector_key_ipv4_addrs *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS, - f->key); - struct flow_dissector_key_ipv4_addrs *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS, - f->mask); + struct flow_match_ipv4_addrs match; + + flow_rule_match_ipv4_addrs(f->rule, &match); mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_0_31, - (char *) &key->src, - (char *) &mask->src, 4); + (char *) &match.key->src, + (char *) &match.mask->src, 4); mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_0_31, - (char *) &key->dst, - (char *) &mask->dst, 4); + (char *) &match.key->dst, + (char *) &match.mask->dst, 4); } static void mlxsw_sp_flower_parse_ipv6(struct mlxsw_sp_acl_rule_info *rulei, struct tc_cls_flower_offload *f) { - struct flow_dissector_key_ipv6_addrs *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS, - f->key); - struct flow_dissector_key_ipv6_addrs *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS, - f->mask); + struct flow_match_ipv6_addrs match; + + flow_rule_match_ipv6_addrs(f->rule, &match); mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_96_127, - &key->src.s6_addr[0x0], - &mask->src.s6_addr[0x0], 4); + &match.key->src.s6_addr[0x0], + &match.mask->src.s6_addr[0x0], 4); mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_64_95, - &key->src.s6_addr[0x4], - &mask->src.s6_addr[0x4], 4); + &match.key->src.s6_addr[0x4], + &match.mask->src.s6_addr[0x4], 4); mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_32_63, - &key->src.s6_addr[0x8], - &mask->src.s6_addr[0x8], 4); + &match.key->src.s6_addr[0x8], + &match.mask->src.s6_addr[0x8], 4); mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_0_31, - &key->src.s6_addr[0xC], - &mask->src.s6_addr[0xC], 4); + &match.key->src.s6_addr[0xC], + &match.mask->src.s6_addr[0xC], 4); mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_96_127, - &key->dst.s6_addr[0x0], - &mask->dst.s6_addr[0x0], 4); + &match.key->dst.s6_addr[0x0], + &match.mask->dst.s6_addr[0x0], 4); mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_64_95, - &key->dst.s6_addr[0x4], - &mask->dst.s6_addr[0x4], 4); + &match.key->dst.s6_addr[0x4], + &match.mask->dst.s6_addr[0x4], 4); mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_32_63, - &key->dst.s6_addr[0x8], - &mask->dst.s6_addr[0x8], 4); + &match.key->dst.s6_addr[0x8], + &match.mask->dst.s6_addr[0x8], 4); mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_0_31, - &key->dst.s6_addr[0xC], - &mask->dst.s6_addr[0xC], 4); + &match.key->dst.s6_addr[0xC], + &match.mask->dst.s6_addr[0xC], 4); } static int mlxsw_sp_flower_parse_ports(struct mlxsw_sp *mlxsw_sp, @@ -173,9 +173,10 @@ static int mlxsw_sp_flower_parse_ports(struct mlxsw_sp *mlxsw_sp, struct tc_cls_flower_offload *f, u8 ip_proto) { - struct flow_dissector_key_ports *key, *mask; + const struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f); + struct flow_match_ports match; - if (!dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) + if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) return 0; if (ip_proto != IPPROTO_TCP && ip_proto != IPPROTO_UDP) { @@ -184,16 +185,13 @@ static int mlxsw_sp_flower_parse_ports(struct mlxsw_sp *mlxsw_sp, return -EINVAL; } - key = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_PORTS, - f->key); - mask = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_PORTS, - f->mask); + flow_rule_match_ports(rule, &match); mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_DST_L4_PORT, - ntohs(key->dst), ntohs(mask->dst)); + ntohs(match.key->dst), + ntohs(match.mask->dst)); mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_SRC_L4_PORT, - ntohs(key->src), ntohs(mask->src)); + ntohs(match.key->src), + ntohs(match.mask->src)); return 0; } @@ -202,9 +200,10 @@ static int mlxsw_sp_flower_parse_tcp(struct mlxsw_sp *mlxsw_sp, struct tc_cls_flower_offload *f, u8 ip_proto) { - struct flow_dissector_key_tcp *key, *mask; + const struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f); + struct flow_match_tcp match; - if (!dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_TCP)) + if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_TCP)) return 0; if (ip_proto != IPPROTO_TCP) { @@ -213,14 +212,11 @@ static int mlxsw_sp_flower_parse_tcp(struct mlxsw_sp *mlxsw_sp, return -EINVAL; } - key = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_TCP, - f->key); - mask = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_TCP, - f->mask); + flow_rule_match_tcp(rule, &match); + mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_TCP_FLAGS, - ntohs(key->flags), ntohs(mask->flags)); + ntohs(match.key->flags), + ntohs(match.mask->flags)); return 0; } @@ -229,9 +225,10 @@ static int mlxsw_sp_flower_parse_ip(struct mlxsw_sp *mlxsw_sp, struct tc_cls_flower_offload *f, u16 n_proto) { - struct flow_dissector_key_ip *key, *mask; + const struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f); + struct flow_match_ip match; - if (!dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_IP)) + if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IP)) return 0; if (n_proto != ETH_P_IP && n_proto != ETH_P_IPV6) { @@ -240,20 +237,18 @@ static int mlxsw_sp_flower_parse_ip(struct mlxsw_sp *mlxsw_sp, return -EINVAL; } - key = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IP, - f->key); - mask = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IP, - f->mask); + flow_rule_match_ip(rule, &match); + mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_IP_TTL_, - key->ttl, mask->ttl); + match.key->ttl, match.mask->ttl); mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_IP_ECN, - key->tos & 0x3, mask->tos & 0x3); + match.key->tos & 0x3, + match.mask->tos & 0x3); mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_IP_DSCP, - key->tos >> 6, mask->tos >> 6); + match.key->tos >> 6, + match.mask->tos >> 6); return 0; } @@ -263,13 +258,15 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_rule_info *rulei, struct tc_cls_flower_offload *f) { + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f); + struct flow_dissector *dissector = rule->match.dissector; u16 n_proto_mask = 0; u16 n_proto_key = 0; u16 addr_type = 0; u8 ip_proto = 0; int err; - if (f->dissector->used_keys & + if (dissector->used_keys & ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | BIT(FLOW_DISSECTOR_KEY_BASIC) | BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | @@ -286,25 +283,19 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_acl_rulei_priority(rulei, f->common.prio); - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) { - struct flow_dissector_key_control *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_CONTROL, - f->key); - addr_type = key->addr_type; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) { + struct flow_match_control match; + + flow_rule_match_control(rule, &match); + addr_type = match.key->addr_type; } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) { - struct flow_dissector_key_basic *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_BASIC, - f->key); - struct flow_dissector_key_basic *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_BASIC, - f->mask); - n_proto_key = ntohs(key->n_proto); - n_proto_mask = ntohs(mask->n_proto); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_match_basic match; + + flow_rule_match_basic(rule, &match); + n_proto_key = ntohs(match.key->n_proto); + n_proto_mask = ntohs(match.mask->n_proto); if (n_proto_key == ETH_P_ALL) { n_proto_key = 0; @@ -314,60 +305,53 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp, MLXSW_AFK_ELEMENT_ETHERTYPE, n_proto_key, n_proto_mask); - ip_proto = key->ip_proto; + ip_proto = match.key->ip_proto; mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_IP_PROTO, - key->ip_proto, mask->ip_proto); + match.key->ip_proto, + match.mask->ip_proto); } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { - struct flow_dissector_key_eth_addrs *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ETH_ADDRS, - f->key); - struct flow_dissector_key_eth_addrs *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ETH_ADDRS, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { + struct flow_match_eth_addrs match; + flow_rule_match_eth_addrs(rule, &match); mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DMAC_32_47, - key->dst, mask->dst, 2); + match.key->dst, + match.mask->dst, 2); mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DMAC_0_31, - key->dst + 2, mask->dst + 2, 4); + match.key->dst + 2, + match.mask->dst + 2, 4); mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SMAC_32_47, - key->src, mask->src, 2); + match.key->src, + match.mask->src, 2); mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SMAC_0_31, - key->src + 2, mask->src + 2, 4); + match.key->src + 2, + match.mask->src + 2, 4); } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) { - struct flow_dissector_key_vlan *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_VLAN, - f->key); - struct flow_dissector_key_vlan *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_VLAN, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_match_vlan match; + flow_rule_match_vlan(rule, &match); if (mlxsw_sp_acl_block_is_egress_bound(block)) { NL_SET_ERR_MSG_MOD(f->common.extack, "vlan_id key is not supported on egress"); return -EOPNOTSUPP; } - if (mask->vlan_id != 0) + if (match.mask->vlan_id != 0) mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_VID, - key->vlan_id, - mask->vlan_id); - if (mask->vlan_priority != 0) + match.key->vlan_id, + match.mask->vlan_id); + if (match.mask->vlan_priority != 0) mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_PCP, - key->vlan_priority, - mask->vlan_priority); + match.key->vlan_priority, + match.mask->vlan_priority); } if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) @@ -387,7 +371,8 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp, if (err) return err; - return mlxsw_sp_flower_parse_actions(mlxsw_sp, block, rulei, f->exts, + return mlxsw_sp_flower_parse_actions(mlxsw_sp, block, rulei, + &f->rule->action, f->common.extack); } @@ -486,7 +471,7 @@ int mlxsw_sp_flower_stats(struct mlxsw_sp *mlxsw_sp, if (err) goto err_rule_get_stats; - tcf_exts_stats_update(f->exts, bytes, packets, lastuse); + flow_stats_update(&f->stats, bytes, packets, lastuse); mlxsw_sp_acl_ruleset_put(mlxsw_sp, ruleset); return 0; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 230e1f6e192b..52fed8c7bf1e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -364,6 +364,7 @@ enum mlxsw_sp_fib_entry_type { MLXSW_SP_FIB_ENTRY_TYPE_REMOTE, MLXSW_SP_FIB_ENTRY_TYPE_LOCAL, MLXSW_SP_FIB_ENTRY_TYPE_TRAP, + MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE, /* This is a special case of local delivery, where a packet should be * decapsulated on reception. Note that there is no corresponding ENCAP, @@ -3813,13 +3814,11 @@ mlxsw_sp_nexthop4_group_create(struct mlxsw_sp *mlxsw_sp, struct fib_info *fi) struct mlxsw_sp_nexthop_group *nh_grp; struct mlxsw_sp_nexthop *nh; struct fib_nh *fib_nh; - size_t alloc_size; int i; int err; - alloc_size = sizeof(*nh_grp) + - fi->fib_nhs * sizeof(struct mlxsw_sp_nexthop); - nh_grp = kzalloc(alloc_size, GFP_KERNEL); + nh_grp = kzalloc(struct_size(nh_grp, nexthops, fi->fib_nhs), + GFP_KERNEL); if (!nh_grp) return ERR_PTR(-ENOMEM); nh_grp->priv = fi; @@ -3928,6 +3927,7 @@ mlxsw_sp_fib_entry_should_offload(const struct mlxsw_sp_fib_entry *fib_entry) return !!nh_group->adj_index_valid; case MLXSW_SP_FIB_ENTRY_TYPE_LOCAL: return !!nh_group->nh_rif; + case MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE: case MLXSW_SP_FIB_ENTRY_TYPE_IPIP_DECAP: case MLXSW_SP_FIB_ENTRY_TYPE_NVE_DECAP: return true; @@ -3963,6 +3963,7 @@ mlxsw_sp_fib4_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry) int i; if (fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_LOCAL || + fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE || fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_IPIP_DECAP || fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_NVE_DECAP) { nh_grp->nexthops->key.fib_nh->nh_flags |= RTNH_F_OFFLOAD; @@ -4004,7 +4005,8 @@ mlxsw_sp_fib6_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry) fib6_entry = container_of(fib_entry, struct mlxsw_sp_fib6_entry, common); - if (fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_LOCAL) { + if (fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_LOCAL || + fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE) { list_first_entry(&fib6_entry->rt6_list, struct mlxsw_sp_rt6, list)->rt->fib6_nh.nh_flags |= RTNH_F_OFFLOAD; return; @@ -4172,6 +4174,19 @@ static int mlxsw_sp_fib_entry_op_trap(struct mlxsw_sp *mlxsw_sp, return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); } +static int mlxsw_sp_fib_entry_op_blackhole(struct mlxsw_sp *mlxsw_sp, + struct mlxsw_sp_fib_entry *fib_entry, + enum mlxsw_reg_ralue_op op) +{ + enum mlxsw_reg_ralue_trap_action trap_action; + char ralue_pl[MLXSW_REG_RALUE_LEN]; + + trap_action = MLXSW_REG_RALUE_TRAP_ACTION_DISCARD_ERROR; + mlxsw_sp_fib_entry_ralue_pack(ralue_pl, fib_entry, op); + mlxsw_reg_ralue_act_local_pack(ralue_pl, trap_action, 0, 0); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralue), ralue_pl); +} + static int mlxsw_sp_fib_entry_op_ipip_decap(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_entry *fib_entry, @@ -4211,6 +4226,8 @@ static int __mlxsw_sp_fib_entry_op(struct mlxsw_sp *mlxsw_sp, return mlxsw_sp_fib_entry_op_local(mlxsw_sp, fib_entry, op); case MLXSW_SP_FIB_ENTRY_TYPE_TRAP: return mlxsw_sp_fib_entry_op_trap(mlxsw_sp, fib_entry, op); + case MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE: + return mlxsw_sp_fib_entry_op_blackhole(mlxsw_sp, fib_entry, op); case MLXSW_SP_FIB_ENTRY_TYPE_IPIP_DECAP: return mlxsw_sp_fib_entry_op_ipip_decap(mlxsw_sp, fib_entry, op); @@ -4279,8 +4296,10 @@ mlxsw_sp_fib4_entry_type_set(struct mlxsw_sp *mlxsw_sp, case RTN_BROADCAST: fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_TRAP; return 0; + case RTN_BLACKHOLE: + fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE; + return 0; case RTN_UNREACHABLE: /* fall through */ - case RTN_BLACKHOLE: /* fall through */ case RTN_PROHIBIT: /* Packets hitting these routes need to be trapped, but * can do so with a lower priority than packets directed @@ -5045,13 +5064,11 @@ mlxsw_sp_nexthop6_group_create(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop_group *nh_grp; struct mlxsw_sp_rt6 *mlxsw_sp_rt6; struct mlxsw_sp_nexthop *nh; - size_t alloc_size; int i = 0; int err; - alloc_size = sizeof(*nh_grp) + - fib6_entry->nrt6 * sizeof(struct mlxsw_sp_nexthop); - nh_grp = kzalloc(alloc_size, GFP_KERNEL); + nh_grp = kzalloc(struct_size(nh_grp, nexthops, fib6_entry->nrt6), + GFP_KERNEL); if (!nh_grp) return ERR_PTR(-ENOMEM); INIT_LIST_HEAD(&nh_grp->fib_list); @@ -5229,6 +5246,8 @@ static void mlxsw_sp_fib6_entry_type_set(struct mlxsw_sp *mlxsw_sp, */ if (rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_TRAP; + else if (rt->fib6_type == RTN_BLACKHOLE) + fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_BLACKHOLE; else if (rt->fib6_flags & RTF_REJECT) fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL; else if (mlxsw_sp_rt6_is_gateway(mlxsw_sp, rt)) @@ -6123,7 +6142,7 @@ static int mlxsw_sp_router_rif_disable(struct mlxsw_sp *mlxsw_sp, u16 rif) mlxsw_reg_ritr_rif_pack(ritr_pl, rif); err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl); - if (WARN_ON_ONCE(err)) + if (err) return err; mlxsw_reg_ritr_enable_set(ritr_pl, false); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index a4a9fe992193..1f492b7dbea8 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -431,35 +431,10 @@ static void mlxsw_sp_bridge_vlan_put(struct mlxsw_sp_bridge_vlan *bridge_vlan) mlxsw_sp_bridge_vlan_destroy(bridge_vlan); } -static void mlxsw_sp_port_bridge_flags_get(struct mlxsw_sp_bridge *bridge, - struct net_device *dev, - unsigned long *brport_flags) -{ - struct mlxsw_sp_bridge_port *bridge_port; - - bridge_port = mlxsw_sp_bridge_port_find(bridge, dev); - if (WARN_ON(!bridge_port)) - return; - - memcpy(brport_flags, &bridge_port->flags, sizeof(*brport_flags)); -} - static int mlxsw_sp_port_attr_get(struct net_device *dev, struct switchdev_attr *attr) { - struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; - switch (attr->id) { - case SWITCHDEV_ATTR_ID_PORT_PARENT_ID: - attr->u.ppid.id_len = sizeof(mlxsw_sp->base_mac); - memcpy(&attr->u.ppid.id, &mlxsw_sp->base_mac, - attr->u.ppid.id_len); - break; - case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS: - mlxsw_sp_port_bridge_flags_get(mlxsw_sp->bridge, attr->orig_dev, - &attr->u.brport_flags); - break; case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT: attr->u.brport_flags_support = BR_LEARNING | BR_FLOOD | BR_MCAST_FLOOD; diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c index 2d4f213e154d..533fe6235b7c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c +++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c @@ -11,7 +11,6 @@ #include <linux/device.h> #include <linux/skbuff.h> #include <linux/if_vlan.h> -#include <net/switchdev.h> #include "pci.h" #include "core.h" @@ -390,6 +389,18 @@ static int mlxsw_sx_port_get_phys_port_name(struct net_device *dev, char *name, name, len); } +static int mlxsw_sx_port_get_port_parent_id(struct net_device *dev, + struct netdev_phys_item_id *ppid) +{ + struct mlxsw_sx_port *mlxsw_sx_port = netdev_priv(dev); + struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx; + + ppid->id_len = sizeof(mlxsw_sx->hw_id); + memcpy(&ppid->id, &mlxsw_sx->hw_id, ppid->id_len); + + return 0; +} + static const struct net_device_ops mlxsw_sx_port_netdev_ops = { .ndo_open = mlxsw_sx_port_open, .ndo_stop = mlxsw_sx_port_stop, @@ -397,6 +408,7 @@ static const struct net_device_ops mlxsw_sx_port_netdev_ops = { .ndo_change_mtu = mlxsw_sx_port_change_mtu, .ndo_get_stats64 = mlxsw_sx_port_get_stats64, .ndo_get_phys_port_name = mlxsw_sx_port_get_phys_port_name, + .ndo_get_port_parent_id = mlxsw_sx_port_get_port_parent_id, }; static void mlxsw_sx_port_get_drvinfo(struct net_device *dev, @@ -901,28 +913,6 @@ static const struct ethtool_ops mlxsw_sx_port_ethtool_ops = { .set_link_ksettings = mlxsw_sx_port_set_link_ksettings, }; -static int mlxsw_sx_port_attr_get(struct net_device *dev, - struct switchdev_attr *attr) -{ - struct mlxsw_sx_port *mlxsw_sx_port = netdev_priv(dev); - struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx; - - switch (attr->id) { - case SWITCHDEV_ATTR_ID_PORT_PARENT_ID: - attr->u.ppid.id_len = sizeof(mlxsw_sx->hw_id); - memcpy(&attr->u.ppid.id, &mlxsw_sx->hw_id, attr->u.ppid.id_len); - break; - default: - return -EOPNOTSUPP; - } - - return 0; -} - -static const struct switchdev_ops mlxsw_sx_port_switchdev_ops = { - .switchdev_port_attr_get = mlxsw_sx_port_attr_get, -}; - static int mlxsw_sx_hw_id_get(struct mlxsw_sx *mlxsw_sx) { char spad_pl[MLXSW_REG_SPAD_LEN] = {0}; @@ -1034,7 +1024,6 @@ static int __mlxsw_sx_port_eth_create(struct mlxsw_sx *mlxsw_sx, u8 local_port, dev->netdev_ops = &mlxsw_sx_port_netdev_ops; dev->ethtool_ops = &mlxsw_sx_port_ethtool_ops; - dev->switchdev_ops = &mlxsw_sx_port_switchdev_ops; err = mlxsw_sx_port_dev_addr_get(mlxsw_sx_port); if (err) { diff --git a/drivers/net/ethernet/micrel/ks8695net.c b/drivers/net/ethernet/micrel/ks8695net.c index b881f5d4a7f9..6006d47707cb 100644 --- a/drivers/net/ethernet/micrel/ks8695net.c +++ b/drivers/net/ethernet/micrel/ks8695net.c @@ -391,7 +391,7 @@ ks8695_tx_irq(int irq, void *dev_id) ksp->tx_buffers[buff_n].dma_ptr, ksp->tx_buffers[buff_n].length, DMA_TO_DEVICE); - dev_kfree_skb_irq(ksp->tx_buffers[buff_n].skb); + dev_consume_skb_irq(ksp->tx_buffers[buff_n].skb); ksp->tx_buffers[buff_n].skb = NULL; ksp->tx_ring_used--; } diff --git a/drivers/net/ethernet/moxa/moxart_ether.c b/drivers/net/ethernet/moxa/moxart_ether.c index b34055ac476f..e1651756bf9d 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.c +++ b/drivers/net/ethernet/moxa/moxart_ether.c @@ -81,11 +81,13 @@ static void moxart_mac_free_memory(struct net_device *ndev) priv->rx_buf_size, DMA_FROM_DEVICE); if (priv->tx_desc_base) - dma_free_coherent(NULL, TX_REG_DESC_SIZE * TX_DESC_NUM, + dma_free_coherent(&priv->pdev->dev, + TX_REG_DESC_SIZE * TX_DESC_NUM, priv->tx_desc_base, priv->tx_base); if (priv->rx_desc_base) - dma_free_coherent(NULL, RX_REG_DESC_SIZE * RX_DESC_NUM, + dma_free_coherent(&priv->pdev->dev, + RX_REG_DESC_SIZE * RX_DESC_NUM, priv->rx_desc_base, priv->rx_base); kfree(priv->tx_buf_base); @@ -298,7 +300,7 @@ static void moxart_tx_finished(struct net_device *ndev) ndev->stats.tx_packets++; ndev->stats.tx_bytes += priv->tx_skb[tx_tail]->len; - dev_kfree_skb_irq(priv->tx_skb[tx_tail]); + dev_consume_skb_irq(priv->tx_skb[tx_tail]); priv->tx_skb[tx_tail] = NULL; tx_tail = TX_NEXT(tx_tail); @@ -476,6 +478,7 @@ static int moxart_mac_probe(struct platform_device *pdev) priv = netdev_priv(ndev); priv->ndev = ndev; + priv->pdev = pdev; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); ndev->base_addr = res->start; @@ -491,7 +494,7 @@ static int moxart_mac_probe(struct platform_device *pdev) priv->tx_buf_size = TX_BUF_SIZE; priv->rx_buf_size = RX_BUF_SIZE; - priv->tx_desc_base = dma_alloc_coherent(NULL, TX_REG_DESC_SIZE * + priv->tx_desc_base = dma_alloc_coherent(&pdev->dev, TX_REG_DESC_SIZE * TX_DESC_NUM, &priv->tx_base, GFP_DMA | GFP_KERNEL); if (!priv->tx_desc_base) { @@ -499,7 +502,7 @@ static int moxart_mac_probe(struct platform_device *pdev) goto init_fail; } - priv->rx_desc_base = dma_alloc_coherent(NULL, RX_REG_DESC_SIZE * + priv->rx_desc_base = dma_alloc_coherent(&pdev->dev, RX_REG_DESC_SIZE * RX_DESC_NUM, &priv->rx_base, GFP_DMA | GFP_KERNEL); if (!priv->rx_desc_base) { diff --git a/drivers/net/ethernet/moxa/moxart_ether.h b/drivers/net/ethernet/moxa/moxart_ether.h index bee608b547d1..bf4c3029cd0c 100644 --- a/drivers/net/ethernet/moxa/moxart_ether.h +++ b/drivers/net/ethernet/moxa/moxart_ether.h @@ -292,6 +292,7 @@ #define LINK_STATUS 0x4 struct moxart_mac_priv_t { + struct platform_device *pdev; void __iomem *base; unsigned int reg_maccr; unsigned int reg_imr; diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index c6a575eb0ff5..195306d05bcd 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -916,6 +916,18 @@ static int ocelot_set_features(struct net_device *dev, return 0; } +static int ocelot_get_port_parent_id(struct net_device *dev, + struct netdev_phys_item_id *ppid) +{ + struct ocelot_port *ocelot_port = netdev_priv(dev); + struct ocelot *ocelot = ocelot_port->ocelot; + + ppid->id_len = sizeof(ocelot->base_mac); + memcpy(&ppid->id, &ocelot->base_mac, ppid->id_len); + + return 0; +} + static const struct net_device_ops ocelot_port_netdev_ops = { .ndo_open = ocelot_port_open, .ndo_stop = ocelot_port_stop, @@ -930,6 +942,7 @@ static const struct net_device_ops ocelot_port_netdev_ops = { .ndo_vlan_rx_add_vid = ocelot_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = ocelot_vlan_rx_kill_vid, .ndo_set_features = ocelot_set_features, + .ndo_get_port_parent_id = ocelot_get_port_parent_id, }; static void ocelot_get_strings(struct net_device *netdev, u32 sset, u8 *data) @@ -1013,25 +1026,6 @@ static const struct ethtool_ops ocelot_ethtool_ops = { .set_link_ksettings = phy_ethtool_set_link_ksettings, }; -static int ocelot_port_attr_get(struct net_device *dev, - struct switchdev_attr *attr) -{ - struct ocelot_port *ocelot_port = netdev_priv(dev); - struct ocelot *ocelot = ocelot_port->ocelot; - - switch (attr->id) { - case SWITCHDEV_ATTR_ID_PORT_PARENT_ID: - attr->u.ppid.id_len = sizeof(ocelot->base_mac); - memcpy(&attr->u.ppid.id, &ocelot->base_mac, - attr->u.ppid.id_len); - break; - default: - return -EOPNOTSUPP; - } - - return 0; -} - static int ocelot_port_attr_stp_state_set(struct ocelot_port *ocelot_port, struct switchdev_trans *trans, u8 state) @@ -1331,7 +1325,6 @@ static int ocelot_port_obj_del(struct net_device *dev, } static const struct switchdev_ops ocelot_port_switchdev_ops = { - .switchdev_port_attr_get = ocelot_port_attr_get, .switchdev_port_attr_set = ocelot_port_attr_set, }; diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index 19ce0e605096..e0340f778d8f 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -1408,7 +1408,7 @@ myri10ge_tx_done(struct myri10ge_slice_state *ss, int mcp_index) if (skb) { ss->stats.tx_bytes += skb->len; ss->stats.tx_packets++; - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); if (len) pci_unmap_single(pdev, dma_unmap_addr(&tx->info[idx], diff --git a/drivers/net/ethernet/natsemi/natsemi.c b/drivers/net/ethernet/natsemi/natsemi.c index b9a1a9f999ea..1a2634cbbb69 100644 --- a/drivers/net/ethernet/natsemi/natsemi.c +++ b/drivers/net/ethernet/natsemi/natsemi.c @@ -2173,7 +2173,7 @@ static void netdev_tx_done(struct net_device *dev) np->tx_skbuff[entry]->len, PCI_DMA_TODEVICE); /* Free the original skb. */ - dev_kfree_skb_irq(np->tx_skbuff[entry]); + dev_consume_skb_irq(np->tx_skbuff[entry]); np->tx_skbuff[entry] = NULL; } if (netif_queue_stopped(dev) && diff --git a/drivers/net/ethernet/natsemi/ns83820.c b/drivers/net/ethernet/natsemi/ns83820.c index 958fced4dacf..000009e18ff8 100644 --- a/drivers/net/ethernet/natsemi/ns83820.c +++ b/drivers/net/ethernet/natsemi/ns83820.c @@ -1003,7 +1003,7 @@ static void do_tx_done(struct net_device *ndev) addr, len, PCI_DMA_TODEVICE); - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); atomic_dec(&dev->nr_tx_skbs); } else pci_unmap_page(dev->pci_dev, diff --git a/drivers/net/ethernet/natsemi/sonic.c b/drivers/net/ethernet/natsemi/sonic.c index c805dcbebd02..aaec00912ea0 100644 --- a/drivers/net/ethernet/natsemi/sonic.c +++ b/drivers/net/ethernet/natsemi/sonic.c @@ -328,7 +328,7 @@ static irqreturn_t sonic_interrupt(int irq, void *dev_id) } /* We must free the original skb */ - dev_kfree_skb_irq(lp->tx_skb[entry]); + dev_consume_skb_irq(lp->tx_skb[entry]); lp->tx_skb[entry] = NULL; /* and unmap DMA buffer */ dma_unmap_single(lp->device, lp->tx_laddr[entry], lp->tx_len[entry], DMA_TO_DEVICE); diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c index 82be90075695..feda9644289d 100644 --- a/drivers/net/ethernet/neterion/s2io.c +++ b/drivers/net/ethernet/neterion/s2io.c @@ -3055,7 +3055,7 @@ static void tx_intr_handler(struct fifo_info *fifo_data) /* Updating the statistics block */ swstats->mem_freed += skb->truesize; - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); get_info.offset++; if (get_info.offset == get_info.fifo_len + 1) diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c index 0da7393b2ef3..b877acec5cde 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-main.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c @@ -114,7 +114,7 @@ static inline void VXGE_COMPLETE_VPATH_TX(struct vxge_fifo *fifo) /* free SKBs */ for (temp = completed; temp != skb_ptr; temp++) - dev_kfree_skb_irq(*temp); + dev_consume_skb_irq(*temp); } while (more); } diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c index aa3a2098a583..4d9d3806908e 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c @@ -1967,6 +1967,9 @@ static int neg_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) */ static int __shl_imm64(struct nfp_prog *nfp_prog, u8 dst, u8 shift_amt) { + if (!shift_amt) + return 0; + if (shift_amt < 32) { emit_shf(nfp_prog, reg_both(dst + 1), reg_a(dst + 1), SHF_OP_NONE, reg_b(dst), SHF_SC_R_DSHF, @@ -2079,6 +2082,9 @@ static int shl_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) */ static int __shr_imm64(struct nfp_prog *nfp_prog, u8 dst, u8 shift_amt) { + if (!shift_amt) + return 0; + if (shift_amt < 32) { emit_shf(nfp_prog, reg_both(dst), reg_a(dst + 1), SHF_OP_NONE, reg_b(dst), SHF_SC_R_DSHF, shift_amt); @@ -2180,6 +2186,9 @@ static int shr_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) */ static int __ashr_imm64(struct nfp_prog *nfp_prog, u8 dst, u8 shift_amt) { + if (!shift_amt) + return 0; + if (shift_amt < 32) { emit_shf(nfp_prog, reg_both(dst), reg_a(dst + 1), SHF_OP_NONE, reg_b(dst), SHF_SC_R_DSHF, shift_amt); @@ -2388,10 +2397,13 @@ static int neg_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) static int __ashr_imm(struct nfp_prog *nfp_prog, u8 dst, u8 shift_amt) { - /* Set signedness bit (MSB of result). */ - emit_alu(nfp_prog, reg_none(), reg_a(dst), ALU_OP_OR, reg_imm(0)); - emit_shf(nfp_prog, reg_both(dst), reg_none(), SHF_OP_ASHR, reg_b(dst), - SHF_SC_R_SHF, shift_amt); + if (shift_amt) { + /* Set signedness bit (MSB of result). */ + emit_alu(nfp_prog, reg_none(), reg_a(dst), ALU_OP_OR, + reg_imm(0)); + emit_shf(nfp_prog, reg_both(dst), reg_none(), SHF_OP_ASHR, + reg_b(dst), SHF_SC_R_SHF, shift_amt); + } wrp_immed(nfp_prog, reg_both(dst + 1), 0); return 0; @@ -2429,18 +2441,75 @@ static int ashr_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) return __ashr_imm(nfp_prog, dst, insn->imm); } +static int __shr_imm(struct nfp_prog *nfp_prog, u8 dst, u8 shift_amt) +{ + if (shift_amt) + emit_shf(nfp_prog, reg_both(dst), reg_none(), SHF_OP_NONE, + reg_b(dst), SHF_SC_R_SHF, shift_amt); + wrp_immed(nfp_prog, reg_both(dst + 1), 0); + return 0; +} + +static int shr_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +{ + const struct bpf_insn *insn = &meta->insn; + u8 dst = insn->dst_reg * 2; + + return __shr_imm(nfp_prog, dst, insn->imm); +} + +static int shr_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +{ + const struct bpf_insn *insn = &meta->insn; + u64 umin, umax; + u8 dst, src; + + dst = insn->dst_reg * 2; + umin = meta->umin_src; + umax = meta->umax_src; + if (umin == umax) + return __shr_imm(nfp_prog, dst, umin); + + src = insn->src_reg * 2; + emit_alu(nfp_prog, reg_none(), reg_a(src), ALU_OP_OR, reg_imm(0)); + emit_shf_indir(nfp_prog, reg_both(dst), reg_none(), SHF_OP_NONE, + reg_b(dst), SHF_SC_R_SHF); + wrp_immed(nfp_prog, reg_both(dst + 1), 0); + return 0; +} + +static int __shl_imm(struct nfp_prog *nfp_prog, u8 dst, u8 shift_amt) +{ + if (shift_amt) + emit_shf(nfp_prog, reg_both(dst), reg_none(), SHF_OP_NONE, + reg_b(dst), SHF_SC_L_SHF, shift_amt); + wrp_immed(nfp_prog, reg_both(dst + 1), 0); + return 0; +} + static int shl_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { const struct bpf_insn *insn = &meta->insn; + u8 dst = insn->dst_reg * 2; - if (!insn->imm) - return 1; /* TODO: zero shift means indirect */ + return __shl_imm(nfp_prog, dst, insn->imm); +} - emit_shf(nfp_prog, reg_both(insn->dst_reg * 2), - reg_none(), SHF_OP_NONE, reg_b(insn->dst_reg * 2), - SHF_SC_L_SHF, insn->imm); - wrp_immed(nfp_prog, reg_both(insn->dst_reg * 2 + 1), 0); +static int shl_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +{ + const struct bpf_insn *insn = &meta->insn; + u64 umin, umax; + u8 dst, src; + dst = insn->dst_reg * 2; + umin = meta->umin_src; + umax = meta->umax_src; + if (umin == umax) + return __shl_imm(nfp_prog, dst, umin); + + src = insn->src_reg * 2; + shl_reg64_lt32_low(nfp_prog, dst, src); + wrp_immed(nfp_prog, reg_both(dst + 1), 0); return 0; } @@ -3350,7 +3419,10 @@ static const instr_cb_t instr_cb[256] = { [BPF_ALU | BPF_DIV | BPF_X] = div_reg, [BPF_ALU | BPF_DIV | BPF_K] = div_imm, [BPF_ALU | BPF_NEG] = neg_reg, + [BPF_ALU | BPF_LSH | BPF_X] = shl_reg, [BPF_ALU | BPF_LSH | BPF_K] = shl_imm, + [BPF_ALU | BPF_RSH | BPF_X] = shr_reg, + [BPF_ALU | BPF_RSH | BPF_K] = shr_imm, [BPF_ALU | BPF_ARSH | BPF_X] = ashr_reg, [BPF_ALU | BPF_ARSH | BPF_K] = ashr_imm, [BPF_ALU | BPF_END | BPF_X] = end_reg32, diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c index dccae0319204..275de9f4c61c 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c @@ -465,7 +465,7 @@ static int nfp_bpf_init(struct nfp_app *app) app->ctrl_mtu = nfp_bpf_ctrl_cmsg_mtu(bpf); } - bpf->bpf_dev = bpf_offload_dev_create(&nfp_bpf_dev_ops); + bpf->bpf_dev = bpf_offload_dev_create(&nfp_bpf_dev_ops, bpf); err = PTR_ERR_OR_ZERO(bpf->bpf_dev); if (err) goto err_free_neutral_maps; diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c index 55c7dbf8b421..15dce97650a5 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c @@ -185,8 +185,6 @@ static void nfp_prog_free(struct nfp_prog *nfp_prog) static int nfp_bpf_verifier_prep(struct bpf_prog *prog) { - struct nfp_net *nn = netdev_priv(prog->aux->offload->netdev); - struct nfp_app *app = nn->app; struct nfp_prog *nfp_prog; int ret; @@ -197,7 +195,7 @@ static int nfp_bpf_verifier_prep(struct bpf_prog *prog) INIT_LIST_HEAD(&nfp_prog->insns); nfp_prog->type = prog->type; - nfp_prog->bpf = app->priv; + nfp_prog->bpf = bpf_offload_dev_priv(prog->aux->offload->offdev); ret = nfp_prog_prepare(nfp_prog, prog->insnsi, prog->len); if (ret) diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c index 8d54b36afee8..eeda4ed98333 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/action.c +++ b/drivers/net/ethernet/netronome/nfp/flower/action.c @@ -3,7 +3,6 @@ #include <linux/bitfield.h> #include <net/pkt_cls.h> -#include <net/switchdev.h> #include <net/tc_act/tc_csum.h> #include <net/tc_act/tc_gact.h> #include <net/tc_act/tc_mirred.h> @@ -37,7 +36,7 @@ static void nfp_fl_pop_vlan(struct nfp_fl_pop_vlan *pop_vlan) static void nfp_fl_push_vlan(struct nfp_fl_push_vlan *push_vlan, - const struct tc_action *action) + const struct flow_action_entry *act) { size_t act_size = sizeof(struct nfp_fl_push_vlan); u16 tmp_push_vlan_tci; @@ -45,17 +44,17 @@ nfp_fl_push_vlan(struct nfp_fl_push_vlan *push_vlan, push_vlan->head.jump_id = NFP_FL_ACTION_OPCODE_PUSH_VLAN; push_vlan->head.len_lw = act_size >> NFP_FL_LW_SIZ; push_vlan->reserved = 0; - push_vlan->vlan_tpid = tcf_vlan_push_proto(action); + push_vlan->vlan_tpid = act->vlan.proto; tmp_push_vlan_tci = - FIELD_PREP(NFP_FL_PUSH_VLAN_PRIO, tcf_vlan_push_prio(action)) | - FIELD_PREP(NFP_FL_PUSH_VLAN_VID, tcf_vlan_push_vid(action)) | + FIELD_PREP(NFP_FL_PUSH_VLAN_PRIO, act->vlan.prio) | + FIELD_PREP(NFP_FL_PUSH_VLAN_VID, act->vlan.vid) | NFP_FL_PUSH_VLAN_CFI; push_vlan->vlan_tci = cpu_to_be16(tmp_push_vlan_tci); } static int -nfp_fl_pre_lag(struct nfp_app *app, const struct tc_action *action, +nfp_fl_pre_lag(struct nfp_app *app, const struct flow_action_entry *act, struct nfp_fl_payload *nfp_flow, int act_len) { size_t act_size = sizeof(struct nfp_fl_pre_lag); @@ -63,7 +62,7 @@ nfp_fl_pre_lag(struct nfp_app *app, const struct tc_action *action, struct net_device *out_dev; int err; - out_dev = tcf_mirred_dev(action); + out_dev = act->dev; if (!out_dev || !netif_is_lag_master(out_dev)) return 0; @@ -92,7 +91,8 @@ nfp_fl_pre_lag(struct nfp_app *app, const struct tc_action *action, static int nfp_fl_output(struct nfp_app *app, struct nfp_fl_output *output, - const struct tc_action *action, struct nfp_fl_payload *nfp_flow, + const struct flow_action_entry *act, + struct nfp_fl_payload *nfp_flow, bool last, struct net_device *in_dev, enum nfp_flower_tun_type tun_type, int *tun_out_cnt) { @@ -104,7 +104,7 @@ nfp_fl_output(struct nfp_app *app, struct nfp_fl_output *output, output->head.jump_id = NFP_FL_ACTION_OPCODE_OUTPUT; output->head.len_lw = act_size >> NFP_FL_LW_SIZ; - out_dev = tcf_mirred_dev(action); + out_dev = act->dev; if (!out_dev) return -EOPNOTSUPP; @@ -137,7 +137,7 @@ nfp_fl_output(struct nfp_app *app, struct nfp_fl_output *output, if (nfp_netdev_is_nfp_repr(in_dev)) { /* Confirm ingress and egress are on same device. */ - if (!switchdev_port_same_parent_id(in_dev, out_dev)) + if (!netdev_port_same_parent_id(in_dev, out_dev)) return -EOPNOTSUPP; } @@ -155,9 +155,9 @@ nfp_fl_output(struct nfp_app *app, struct nfp_fl_output *output, static enum nfp_flower_tun_type nfp_fl_get_tun_from_act_l4_port(struct nfp_app *app, - const struct tc_action *action) + const struct flow_action_entry *act) { - struct ip_tunnel_info *tun = tcf_tunnel_info(action); + const struct ip_tunnel_info *tun = act->tunnel; struct nfp_flower_priv *priv = app->priv; switch (tun->key.tp_dst) { @@ -195,9 +195,9 @@ static struct nfp_fl_pre_tunnel *nfp_fl_pre_tunnel(char *act_data, int act_len) static int nfp_fl_push_geneve_options(struct nfp_fl_payload *nfp_fl, int *list_len, - const struct tc_action *action) + const struct flow_action_entry *act) { - struct ip_tunnel_info *ip_tun = tcf_tunnel_info(action); + struct ip_tunnel_info *ip_tun = (struct ip_tunnel_info *)act->tunnel; int opt_len, opt_cnt, act_start, tot_push_len; u8 *src = ip_tunnel_info_opts(ip_tun); @@ -259,13 +259,13 @@ nfp_fl_push_geneve_options(struct nfp_fl_payload *nfp_fl, int *list_len, static int nfp_fl_set_ipv4_udp_tun(struct nfp_app *app, struct nfp_fl_set_ipv4_udp_tun *set_tun, - const struct tc_action *action, + const struct flow_action_entry *act, struct nfp_fl_pre_tunnel *pre_tun, enum nfp_flower_tun_type tun_type, struct net_device *netdev) { size_t act_size = sizeof(struct nfp_fl_set_ipv4_udp_tun); - struct ip_tunnel_info *ip_tun = tcf_tunnel_info(action); + const struct ip_tunnel_info *ip_tun = act->tunnel; struct nfp_flower_priv *priv = app->priv; u32 tmp_set_ip_tun_type_index = 0; /* Currently support one pre-tunnel so index is always 0. */ @@ -345,7 +345,7 @@ static void nfp_fl_set_helper32(u32 value, u32 mask, u8 *p_exact, u8 *p_mask) } static int -nfp_fl_set_eth(const struct tc_action *action, int idx, u32 off, +nfp_fl_set_eth(const struct flow_action_entry *act, u32 off, struct nfp_fl_set_eth *set_eth) { u32 exact, mask; @@ -353,8 +353,8 @@ nfp_fl_set_eth(const struct tc_action *action, int idx, u32 off, if (off + 4 > ETH_ALEN * 2) return -EOPNOTSUPP; - mask = ~tcf_pedit_mask(action, idx); - exact = tcf_pedit_val(action, idx); + mask = ~act->mangle.mask; + exact = act->mangle.val; if (exact & ~mask) return -EOPNOTSUPP; @@ -376,7 +376,7 @@ struct ipv4_ttl_word { }; static int -nfp_fl_set_ip4(const struct tc_action *action, int idx, u32 off, +nfp_fl_set_ip4(const struct flow_action_entry *act, u32 off, struct nfp_fl_set_ip4_addrs *set_ip_addr, struct nfp_fl_set_ip4_ttl_tos *set_ip_ttl_tos) { @@ -387,8 +387,8 @@ nfp_fl_set_ip4(const struct tc_action *action, int idx, u32 off, __be32 exact, mask; /* We are expecting tcf_pedit to return a big endian value */ - mask = (__force __be32)~tcf_pedit_mask(action, idx); - exact = (__force __be32)tcf_pedit_val(action, idx); + mask = (__force __be32)~act->mangle.mask; + exact = (__force __be32)act->mangle.val; if (exact & ~mask) return -EOPNOTSUPP; @@ -505,7 +505,7 @@ nfp_fl_set_ip6_hop_limit_flow_label(u32 off, __be32 exact, __be32 mask, } static int -nfp_fl_set_ip6(const struct tc_action *action, int idx, u32 off, +nfp_fl_set_ip6(const struct flow_action_entry *act, u32 off, struct nfp_fl_set_ipv6_addr *ip_dst, struct nfp_fl_set_ipv6_addr *ip_src, struct nfp_fl_set_ipv6_tc_hl_fl *ip_hl_fl) @@ -515,8 +515,8 @@ nfp_fl_set_ip6(const struct tc_action *action, int idx, u32 off, u8 word; /* We are expecting tcf_pedit to return a big endian value */ - mask = (__force __be32)~tcf_pedit_mask(action, idx); - exact = (__force __be32)tcf_pedit_val(action, idx); + mask = (__force __be32)~act->mangle.mask; + exact = (__force __be32)act->mangle.val; if (exact & ~mask) return -EOPNOTSUPP; @@ -541,7 +541,7 @@ nfp_fl_set_ip6(const struct tc_action *action, int idx, u32 off, } static int -nfp_fl_set_tport(const struct tc_action *action, int idx, u32 off, +nfp_fl_set_tport(const struct flow_action_entry *act, u32 off, struct nfp_fl_set_tport *set_tport, int opcode) { u32 exact, mask; @@ -549,8 +549,8 @@ nfp_fl_set_tport(const struct tc_action *action, int idx, u32 off, if (off) return -EOPNOTSUPP; - mask = ~tcf_pedit_mask(action, idx); - exact = tcf_pedit_val(action, idx); + mask = ~act->mangle.mask; + exact = act->mangle.val; if (exact & ~mask) return -EOPNOTSUPP; @@ -584,20 +584,22 @@ static u32 nfp_fl_csum_l4_to_flag(u8 ip_proto) } static int -nfp_fl_pedit(const struct tc_action *action, struct tc_cls_flower_offload *flow, +nfp_fl_pedit(const struct flow_action_entry *act, + struct tc_cls_flower_offload *flow, char *nfp_action, int *a_len, u32 *csum_updated) { + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow); struct nfp_fl_set_ipv6_addr set_ip6_dst, set_ip6_src; struct nfp_fl_set_ipv6_tc_hl_fl set_ip6_tc_hl_fl; struct nfp_fl_set_ip4_ttl_tos set_ip_ttl_tos; struct nfp_fl_set_ip4_addrs set_ip_addr; + enum flow_action_mangle_base htype; struct nfp_fl_set_tport set_tport; struct nfp_fl_set_eth set_eth; - enum pedit_header_type htype; - int idx, nkeys, err; size_t act_size = 0; - u32 offset, cmd; u8 ip_proto = 0; + u32 offset; + int err; memset(&set_ip6_tc_hl_fl, 0, sizeof(set_ip6_tc_hl_fl)); memset(&set_ip_ttl_tos, 0, sizeof(set_ip_ttl_tos)); @@ -606,50 +608,41 @@ nfp_fl_pedit(const struct tc_action *action, struct tc_cls_flower_offload *flow, memset(&set_ip_addr, 0, sizeof(set_ip_addr)); memset(&set_tport, 0, sizeof(set_tport)); memset(&set_eth, 0, sizeof(set_eth)); - nkeys = tcf_pedit_nkeys(action); - - for (idx = 0; idx < nkeys; idx++) { - cmd = tcf_pedit_cmd(action, idx); - htype = tcf_pedit_htype(action, idx); - offset = tcf_pedit_offset(action, idx); - if (cmd != TCA_PEDIT_KEY_EX_CMD_SET) - return -EOPNOTSUPP; + htype = act->mangle.htype; + offset = act->mangle.offset; - switch (htype) { - case TCA_PEDIT_KEY_EX_HDR_TYPE_ETH: - err = nfp_fl_set_eth(action, idx, offset, &set_eth); - break; - case TCA_PEDIT_KEY_EX_HDR_TYPE_IP4: - err = nfp_fl_set_ip4(action, idx, offset, &set_ip_addr, - &set_ip_ttl_tos); - break; - case TCA_PEDIT_KEY_EX_HDR_TYPE_IP6: - err = nfp_fl_set_ip6(action, idx, offset, &set_ip6_dst, - &set_ip6_src, &set_ip6_tc_hl_fl); - break; - case TCA_PEDIT_KEY_EX_HDR_TYPE_TCP: - err = nfp_fl_set_tport(action, idx, offset, &set_tport, - NFP_FL_ACTION_OPCODE_SET_TCP); - break; - case TCA_PEDIT_KEY_EX_HDR_TYPE_UDP: - err = nfp_fl_set_tport(action, idx, offset, &set_tport, - NFP_FL_ACTION_OPCODE_SET_UDP); - break; - default: - return -EOPNOTSUPP; - } - if (err) - return err; + switch (htype) { + case TCA_PEDIT_KEY_EX_HDR_TYPE_ETH: + err = nfp_fl_set_eth(act, offset, &set_eth); + break; + case TCA_PEDIT_KEY_EX_HDR_TYPE_IP4: + err = nfp_fl_set_ip4(act, offset, &set_ip_addr, + &set_ip_ttl_tos); + break; + case TCA_PEDIT_KEY_EX_HDR_TYPE_IP6: + err = nfp_fl_set_ip6(act, offset, &set_ip6_dst, + &set_ip6_src, &set_ip6_tc_hl_fl); + break; + case TCA_PEDIT_KEY_EX_HDR_TYPE_TCP: + err = nfp_fl_set_tport(act, offset, &set_tport, + NFP_FL_ACTION_OPCODE_SET_TCP); + break; + case TCA_PEDIT_KEY_EX_HDR_TYPE_UDP: + err = nfp_fl_set_tport(act, offset, &set_tport, + NFP_FL_ACTION_OPCODE_SET_UDP); + break; + default: + return -EOPNOTSUPP; } + if (err) + return err; - if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_BASIC)) { - struct flow_dissector_key_basic *basic; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_match_basic match; - basic = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_BASIC, - flow->key); - ip_proto = basic->ip_proto; + flow_rule_match_basic(rule, &match); + ip_proto = match.key->ip_proto; } if (set_eth.head.len_lw) { @@ -733,7 +726,7 @@ nfp_fl_pedit(const struct tc_action *action, struct tc_cls_flower_offload *flow, } static int -nfp_flower_output_action(struct nfp_app *app, const struct tc_action *a, +nfp_flower_output_action(struct nfp_app *app, const struct flow_action_entry *act, struct nfp_fl_payload *nfp_fl, int *a_len, struct net_device *netdev, bool last, enum nfp_flower_tun_type *tun_type, int *tun_out_cnt, @@ -753,7 +746,7 @@ nfp_flower_output_action(struct nfp_app *app, const struct tc_action *a, return -EOPNOTSUPP; output = (struct nfp_fl_output *)&nfp_fl->action_data[*a_len]; - err = nfp_fl_output(app, output, a, nfp_fl, last, netdev, *tun_type, + err = nfp_fl_output(app, output, act, nfp_fl, last, netdev, *tun_type, tun_out_cnt); if (err) return err; @@ -764,7 +757,7 @@ nfp_flower_output_action(struct nfp_app *app, const struct tc_action *a, /* nfp_fl_pre_lag returns -err or size of prelag action added. * This will be 0 if it is not egressing to a lag dev. */ - prelag_size = nfp_fl_pre_lag(app, a, nfp_fl, *a_len); + prelag_size = nfp_fl_pre_lag(app, act, nfp_fl, *a_len); if (prelag_size < 0) return prelag_size; else if (prelag_size > 0 && (!last || *out_cnt)) @@ -778,7 +771,7 @@ nfp_flower_output_action(struct nfp_app *app, const struct tc_action *a, } static int -nfp_flower_loop_action(struct nfp_app *app, const struct tc_action *a, +nfp_flower_loop_action(struct nfp_app *app, const struct flow_action_entry *act, struct tc_cls_flower_offload *flow, struct nfp_fl_payload *nfp_fl, int *a_len, struct net_device *netdev, @@ -791,23 +784,25 @@ nfp_flower_loop_action(struct nfp_app *app, const struct tc_action *a, struct nfp_fl_pop_vlan *pop_v; int err; - if (is_tcf_gact_shot(a)) { + switch (act->id) { + case FLOW_ACTION_DROP: nfp_fl->meta.shortcut = cpu_to_be32(NFP_FL_SC_ACT_DROP); - } else if (is_tcf_mirred_egress_redirect(a)) { - err = nfp_flower_output_action(app, a, nfp_fl, a_len, netdev, + break; + case FLOW_ACTION_REDIRECT: + err = nfp_flower_output_action(app, act, nfp_fl, a_len, netdev, true, tun_type, tun_out_cnt, out_cnt, csum_updated); if (err) return err; - - } else if (is_tcf_mirred_egress_mirror(a)) { - err = nfp_flower_output_action(app, a, nfp_fl, a_len, netdev, + break; + case FLOW_ACTION_MIRRED: + err = nfp_flower_output_action(app, act, nfp_fl, a_len, netdev, false, tun_type, tun_out_cnt, out_cnt, csum_updated); if (err) return err; - - } else if (is_tcf_vlan(a) && tcf_vlan_action(a) == TCA_VLAN_ACT_POP) { + break; + case FLOW_ACTION_VLAN_POP: if (*a_len + sizeof(struct nfp_fl_pop_vlan) > NFP_FL_MAX_A_SIZ) return -EOPNOTSUPP; @@ -816,19 +811,21 @@ nfp_flower_loop_action(struct nfp_app *app, const struct tc_action *a, nfp_fl_pop_vlan(pop_v); *a_len += sizeof(struct nfp_fl_pop_vlan); - } else if (is_tcf_vlan(a) && tcf_vlan_action(a) == TCA_VLAN_ACT_PUSH) { + break; + case FLOW_ACTION_VLAN_PUSH: if (*a_len + sizeof(struct nfp_fl_push_vlan) > NFP_FL_MAX_A_SIZ) return -EOPNOTSUPP; psh_v = (struct nfp_fl_push_vlan *)&nfp_fl->action_data[*a_len]; nfp_fl->meta.shortcut = cpu_to_be32(NFP_FL_SC_ACT_NULL); - nfp_fl_push_vlan(psh_v, a); + nfp_fl_push_vlan(psh_v, act); *a_len += sizeof(struct nfp_fl_push_vlan); - } else if (is_tcf_tunnel_set(a)) { - struct ip_tunnel_info *ip_tun = tcf_tunnel_info(a); + break; + case FLOW_ACTION_TUNNEL_ENCAP: { + const struct ip_tunnel_info *ip_tun = act->tunnel; - *tun_type = nfp_fl_get_tun_from_act_l4_port(app, a); + *tun_type = nfp_fl_get_tun_from_act_l4_port(app, act); if (*tun_type == NFP_FL_TUNNEL_NONE) return -EOPNOTSUPP; @@ -847,32 +844,36 @@ nfp_flower_loop_action(struct nfp_app *app, const struct tc_action *a, nfp_fl->meta.shortcut = cpu_to_be32(NFP_FL_SC_ACT_NULL); *a_len += sizeof(struct nfp_fl_pre_tunnel); - err = nfp_fl_push_geneve_options(nfp_fl, a_len, a); + err = nfp_fl_push_geneve_options(nfp_fl, a_len, act); if (err) return err; set_tun = (void *)&nfp_fl->action_data[*a_len]; - err = nfp_fl_set_ipv4_udp_tun(app, set_tun, a, pre_tun, + err = nfp_fl_set_ipv4_udp_tun(app, set_tun, act, pre_tun, *tun_type, netdev); if (err) return err; *a_len += sizeof(struct nfp_fl_set_ipv4_udp_tun); - } else if (is_tcf_tunnel_release(a)) { + } + break; + case FLOW_ACTION_TUNNEL_DECAP: /* Tunnel decap is handled by default so accept action. */ return 0; - } else if (is_tcf_pedit(a)) { - if (nfp_fl_pedit(a, flow, &nfp_fl->action_data[*a_len], + case FLOW_ACTION_MANGLE: + if (nfp_fl_pedit(act, flow, &nfp_fl->action_data[*a_len], a_len, csum_updated)) return -EOPNOTSUPP; - } else if (is_tcf_csum(a)) { + break; + case FLOW_ACTION_CSUM: /* csum action requests recalc of something we have not fixed */ - if (tcf_csum_update_flags(a) & ~*csum_updated) + if (act->csum_flags & ~*csum_updated) return -EOPNOTSUPP; /* If we will correctly fix the csum we can remove it from the * csum update list. Which will later be used to check support. */ - *csum_updated &= ~tcf_csum_update_flags(a); - } else { + *csum_updated &= ~act->csum_flags; + break; + default: /* Currently we do not handle any other actions. */ return -EOPNOTSUPP; } @@ -887,7 +888,7 @@ int nfp_flower_compile_action(struct nfp_app *app, { int act_len, act_cnt, err, tun_out_cnt, out_cnt, i; enum nfp_flower_tun_type tun_type; - const struct tc_action *a; + struct flow_action_entry *act; u32 csum_updated = 0; memset(nfp_flow->action_data, 0, NFP_FL_MAX_A_SIZ); @@ -898,8 +899,8 @@ int nfp_flower_compile_action(struct nfp_app *app, tun_out_cnt = 0; out_cnt = 0; - tcf_exts_for_each_action(i, a, flow->exts) { - err = nfp_flower_loop_action(app, a, flow, nfp_flow, &act_len, + flow_action_for_each(i, act, &flow->rule->action) { + err = nfp_flower_loop_action(app, act, flow, nfp_flow, &act_len, netdev, &tun_type, &tun_out_cnt, &out_cnt, &csum_updated); if (err) diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.c b/drivers/net/ethernet/netronome/nfp/flower/cmsg.c index 56b22ea32474..cf9e1118ee8f 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.c +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.c @@ -45,11 +45,9 @@ nfp_flower_cmsg_mac_repr_start(struct nfp_app *app, unsigned int num_ports) { struct nfp_flower_cmsg_mac_repr *msg; struct sk_buff *skb; - unsigned int size; - size = sizeof(*msg) + num_ports * sizeof(msg->ports[0]); - skb = nfp_flower_cmsg_alloc(app, size, NFP_FLOWER_CMSG_TYPE_MAC_REPR, - GFP_KERNEL); + skb = nfp_flower_cmsg_alloc(app, struct_size(msg, ports, num_ports), + NFP_FLOWER_CMSG_TYPE_MAC_REPR, GFP_KERNEL); if (!skb) return NULL; diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c index c04a0d6b0184..e03c8ef2c28c 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/match.c +++ b/drivers/net/ethernet/netronome/nfp/flower/match.c @@ -8,31 +8,41 @@ #include "main.h" static void -nfp_flower_compile_meta_tci(struct nfp_flower_meta_tci *frame, - struct tc_cls_flower_offload *flow, u8 key_type, - bool mask_version) +nfp_flower_compile_meta_tci(struct nfp_flower_meta_tci *ext, + struct nfp_flower_meta_tci *msk, + struct tc_cls_flower_offload *flow, u8 key_type) { - struct fl_flow_key *target = mask_version ? flow->mask : flow->key; - struct flow_dissector_key_vlan *flow_vlan; + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow); u16 tmp_tci; - memset(frame, 0, sizeof(struct nfp_flower_meta_tci)); + memset(ext, 0, sizeof(struct nfp_flower_meta_tci)); + memset(msk, 0, sizeof(struct nfp_flower_meta_tci)); + /* Populate the metadata frame. */ - frame->nfp_flow_key_layer = key_type; - frame->mask_id = ~0; + ext->nfp_flow_key_layer = key_type; + ext->mask_id = ~0; + + msk->nfp_flow_key_layer = key_type; + msk->mask_id = ~0; - if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_VLAN)) { - flow_vlan = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_VLAN, - target); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_match_vlan match; + + flow_rule_match_vlan(rule, &match); /* Populate the tci field. */ - if (flow_vlan->vlan_id || flow_vlan->vlan_priority) { + if (match.key->vlan_id || match.key->vlan_priority) { tmp_tci = FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO, - flow_vlan->vlan_priority) | + match.key->vlan_priority) | FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID, - flow_vlan->vlan_id) | + match.key->vlan_id) | NFP_FLOWER_MASK_VLAN_CFI; - frame->tci = cpu_to_be16(tmp_tci); + ext->tci = cpu_to_be16(tmp_tci); + tmp_tci = FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO, + match.mask->vlan_priority) | + FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID, + match.mask->vlan_id) | + NFP_FLOWER_MASK_VLAN_CFI; + msk->tci = cpu_to_be16(tmp_tci); } } } @@ -64,231 +74,249 @@ nfp_flower_compile_port(struct nfp_flower_in_port *frame, u32 cmsg_port, } static void -nfp_flower_compile_mac(struct nfp_flower_mac_mpls *frame, - struct tc_cls_flower_offload *flow, - bool mask_version) +nfp_flower_compile_mac(struct nfp_flower_mac_mpls *ext, + struct nfp_flower_mac_mpls *msk, + struct tc_cls_flower_offload *flow) { - struct fl_flow_key *target = mask_version ? flow->mask : flow->key; - struct flow_dissector_key_eth_addrs *addr; + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow); + + memset(ext, 0, sizeof(struct nfp_flower_mac_mpls)); + memset(msk, 0, sizeof(struct nfp_flower_mac_mpls)); - memset(frame, 0, sizeof(struct nfp_flower_mac_mpls)); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { + struct flow_match_eth_addrs match; - if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { - addr = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_ETH_ADDRS, - target); + flow_rule_match_eth_addrs(rule, &match); /* Populate mac frame. */ - ether_addr_copy(frame->mac_dst, &addr->dst[0]); - ether_addr_copy(frame->mac_src, &addr->src[0]); + ether_addr_copy(ext->mac_dst, &match.key->dst[0]); + ether_addr_copy(ext->mac_src, &match.key->src[0]); + ether_addr_copy(msk->mac_dst, &match.mask->dst[0]); + ether_addr_copy(msk->mac_src, &match.mask->src[0]); } - if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_MPLS)) { - struct flow_dissector_key_mpls *mpls; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_MPLS)) { + struct flow_match_mpls match; u32 t_mpls; - mpls = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_MPLS, - target); - - t_mpls = FIELD_PREP(NFP_FLOWER_MASK_MPLS_LB, mpls->mpls_label) | - FIELD_PREP(NFP_FLOWER_MASK_MPLS_TC, mpls->mpls_tc) | - FIELD_PREP(NFP_FLOWER_MASK_MPLS_BOS, mpls->mpls_bos) | + flow_rule_match_mpls(rule, &match); + t_mpls = FIELD_PREP(NFP_FLOWER_MASK_MPLS_LB, match.key->mpls_label) | + FIELD_PREP(NFP_FLOWER_MASK_MPLS_TC, match.key->mpls_tc) | + FIELD_PREP(NFP_FLOWER_MASK_MPLS_BOS, match.key->mpls_bos) | NFP_FLOWER_MASK_MPLS_Q; - - frame->mpls_lse = cpu_to_be32(t_mpls); - } else if (dissector_uses_key(flow->dissector, - FLOW_DISSECTOR_KEY_BASIC)) { + ext->mpls_lse = cpu_to_be32(t_mpls); + t_mpls = FIELD_PREP(NFP_FLOWER_MASK_MPLS_LB, match.mask->mpls_label) | + FIELD_PREP(NFP_FLOWER_MASK_MPLS_TC, match.mask->mpls_tc) | + FIELD_PREP(NFP_FLOWER_MASK_MPLS_BOS, match.mask->mpls_bos) | + NFP_FLOWER_MASK_MPLS_Q; + msk->mpls_lse = cpu_to_be32(t_mpls); + } else if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) { /* Check for mpls ether type and set NFP_FLOWER_MASK_MPLS_Q * bit, which indicates an mpls ether type but without any * mpls fields. */ - struct flow_dissector_key_basic *key_basic; - - key_basic = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_BASIC, - flow->key); - if (key_basic->n_proto == cpu_to_be16(ETH_P_MPLS_UC) || - key_basic->n_proto == cpu_to_be16(ETH_P_MPLS_MC)) - frame->mpls_lse = cpu_to_be32(NFP_FLOWER_MASK_MPLS_Q); + struct flow_match_basic match; + + flow_rule_match_basic(rule, &match); + if (match.key->n_proto == cpu_to_be16(ETH_P_MPLS_UC) || + match.key->n_proto == cpu_to_be16(ETH_P_MPLS_MC)) { + ext->mpls_lse = cpu_to_be32(NFP_FLOWER_MASK_MPLS_Q); + msk->mpls_lse = cpu_to_be32(NFP_FLOWER_MASK_MPLS_Q); + } } } static void -nfp_flower_compile_tport(struct nfp_flower_tp_ports *frame, - struct tc_cls_flower_offload *flow, - bool mask_version) +nfp_flower_compile_tport(struct nfp_flower_tp_ports *ext, + struct nfp_flower_tp_ports *msk, + struct tc_cls_flower_offload *flow) { - struct fl_flow_key *target = mask_version ? flow->mask : flow->key; - struct flow_dissector_key_ports *tp; + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow); + + memset(ext, 0, sizeof(struct nfp_flower_tp_ports)); + memset(msk, 0, sizeof(struct nfp_flower_tp_ports)); - memset(frame, 0, sizeof(struct nfp_flower_tp_ports)); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) { + struct flow_match_ports match; - if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_PORTS)) { - tp = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_PORTS, - target); - frame->port_src = tp->src; - frame->port_dst = tp->dst; + flow_rule_match_ports(rule, &match); + ext->port_src = match.key->src; + ext->port_dst = match.key->dst; + msk->port_src = match.mask->src; + msk->port_dst = match.mask->dst; } } static void -nfp_flower_compile_ip_ext(struct nfp_flower_ip_ext *frame, - struct tc_cls_flower_offload *flow, - bool mask_version) +nfp_flower_compile_ip_ext(struct nfp_flower_ip_ext *ext, + struct nfp_flower_ip_ext *msk, + struct tc_cls_flower_offload *flow) { - struct fl_flow_key *target = mask_version ? flow->mask : flow->key; + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow); - if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_BASIC)) { - struct flow_dissector_key_basic *basic; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_match_basic match; - basic = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_BASIC, - target); - frame->proto = basic->ip_proto; + flow_rule_match_basic(rule, &match); + ext->proto = match.key->ip_proto; + msk->proto = match.mask->ip_proto; } - if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_IP)) { - struct flow_dissector_key_ip *flow_ip; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IP)) { + struct flow_match_ip match; - flow_ip = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_IP, - target); - frame->tos = flow_ip->tos; - frame->ttl = flow_ip->ttl; + flow_rule_match_ip(rule, &match); + ext->tos = match.key->tos; + ext->ttl = match.key->ttl; + msk->tos = match.mask->tos; + msk->ttl = match.mask->ttl; } - if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_TCP)) { - struct flow_dissector_key_tcp *tcp; - u32 tcp_flags; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_TCP)) { + u16 tcp_flags, tcp_flags_mask; + struct flow_match_tcp match; - tcp = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_TCP, target); - tcp_flags = be16_to_cpu(tcp->flags); + flow_rule_match_tcp(rule, &match); + tcp_flags = be16_to_cpu(match.key->flags); + tcp_flags_mask = be16_to_cpu(match.mask->flags); if (tcp_flags & TCPHDR_FIN) - frame->flags |= NFP_FL_TCP_FLAG_FIN; + ext->flags |= NFP_FL_TCP_FLAG_FIN; + if (tcp_flags_mask & TCPHDR_FIN) + msk->flags |= NFP_FL_TCP_FLAG_FIN; + if (tcp_flags & TCPHDR_SYN) - frame->flags |= NFP_FL_TCP_FLAG_SYN; + ext->flags |= NFP_FL_TCP_FLAG_SYN; + if (tcp_flags_mask & TCPHDR_SYN) + msk->flags |= NFP_FL_TCP_FLAG_SYN; + if (tcp_flags & TCPHDR_RST) - frame->flags |= NFP_FL_TCP_FLAG_RST; + ext->flags |= NFP_FL_TCP_FLAG_RST; + if (tcp_flags_mask & TCPHDR_RST) + msk->flags |= NFP_FL_TCP_FLAG_RST; + if (tcp_flags & TCPHDR_PSH) - frame->flags |= NFP_FL_TCP_FLAG_PSH; + ext->flags |= NFP_FL_TCP_FLAG_PSH; + if (tcp_flags_mask & TCPHDR_PSH) + msk->flags |= NFP_FL_TCP_FLAG_PSH; + if (tcp_flags & TCPHDR_URG) - frame->flags |= NFP_FL_TCP_FLAG_URG; + ext->flags |= NFP_FL_TCP_FLAG_URG; + if (tcp_flags_mask & TCPHDR_URG) + msk->flags |= NFP_FL_TCP_FLAG_URG; } - if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_CONTROL)) { - struct flow_dissector_key_control *key; - - key = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_CONTROL, - target); - if (key->flags & FLOW_DIS_IS_FRAGMENT) - frame->flags |= NFP_FL_IP_FRAGMENTED; - if (key->flags & FLOW_DIS_FIRST_FRAG) - frame->flags |= NFP_FL_IP_FRAG_FIRST; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) { + struct flow_match_control match; + + flow_rule_match_control(rule, &match); + if (match.key->flags & FLOW_DIS_IS_FRAGMENT) + ext->flags |= NFP_FL_IP_FRAGMENTED; + if (match.mask->flags & FLOW_DIS_IS_FRAGMENT) + msk->flags |= NFP_FL_IP_FRAGMENTED; + if (match.key->flags & FLOW_DIS_FIRST_FRAG) + ext->flags |= NFP_FL_IP_FRAG_FIRST; + if (match.mask->flags & FLOW_DIS_FIRST_FRAG) + msk->flags |= NFP_FL_IP_FRAG_FIRST; } } static void -nfp_flower_compile_ipv4(struct nfp_flower_ipv4 *frame, - struct tc_cls_flower_offload *flow, - bool mask_version) +nfp_flower_compile_ipv4(struct nfp_flower_ipv4 *ext, + struct nfp_flower_ipv4 *msk, + struct tc_cls_flower_offload *flow) { - struct fl_flow_key *target = mask_version ? flow->mask : flow->key; - struct flow_dissector_key_ipv4_addrs *addr; - - memset(frame, 0, sizeof(struct nfp_flower_ipv4)); - - if (dissector_uses_key(flow->dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS)) { - addr = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS, - target); - frame->ipv4_src = addr->src; - frame->ipv4_dst = addr->dst; + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow); + struct flow_match_ipv4_addrs match; + + memset(ext, 0, sizeof(struct nfp_flower_ipv4)); + memset(msk, 0, sizeof(struct nfp_flower_ipv4)); + + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) { + flow_rule_match_ipv4_addrs(rule, &match); + ext->ipv4_src = match.key->src; + ext->ipv4_dst = match.key->dst; + msk->ipv4_src = match.mask->src; + msk->ipv4_dst = match.mask->dst; } - nfp_flower_compile_ip_ext(&frame->ip_ext, flow, mask_version); + nfp_flower_compile_ip_ext(&ext->ip_ext, &msk->ip_ext, flow); } static void -nfp_flower_compile_ipv6(struct nfp_flower_ipv6 *frame, - struct tc_cls_flower_offload *flow, - bool mask_version) +nfp_flower_compile_ipv6(struct nfp_flower_ipv6 *ext, + struct nfp_flower_ipv6 *msk, + struct tc_cls_flower_offload *flow) { - struct fl_flow_key *target = mask_version ? flow->mask : flow->key; - struct flow_dissector_key_ipv6_addrs *addr; - - memset(frame, 0, sizeof(struct nfp_flower_ipv6)); - - if (dissector_uses_key(flow->dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { - addr = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS, - target); - frame->ipv6_src = addr->src; - frame->ipv6_dst = addr->dst; + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow); + + memset(ext, 0, sizeof(struct nfp_flower_ipv6)); + memset(msk, 0, sizeof(struct nfp_flower_ipv6)); + + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { + struct flow_match_ipv6_addrs match; + + flow_rule_match_ipv6_addrs(rule, &match); + ext->ipv6_src = match.key->src; + ext->ipv6_dst = match.key->dst; + msk->ipv6_src = match.mask->src; + msk->ipv6_dst = match.mask->dst; } - nfp_flower_compile_ip_ext(&frame->ip_ext, flow, mask_version); + nfp_flower_compile_ip_ext(&ext->ip_ext, &msk->ip_ext, flow); } static int -nfp_flower_compile_geneve_opt(void *key_buf, struct tc_cls_flower_offload *flow, - bool mask_version) +nfp_flower_compile_geneve_opt(void *ext, void *msk, + struct tc_cls_flower_offload *flow) { - struct fl_flow_key *target = mask_version ? flow->mask : flow->key; - struct flow_dissector_key_enc_opts *opts; + struct flow_match_enc_opts match; - opts = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_ENC_OPTS, - target); - memcpy(key_buf, opts->data, opts->len); + flow_rule_match_enc_opts(flow->rule, &match); + memcpy(ext, match.key->data, match.key->len); + memcpy(msk, match.mask->data, match.mask->len); return 0; } static void -nfp_flower_compile_ipv4_udp_tun(struct nfp_flower_ipv4_udp_tun *frame, - struct tc_cls_flower_offload *flow, - bool mask_version) +nfp_flower_compile_ipv4_udp_tun(struct nfp_flower_ipv4_udp_tun *ext, + struct nfp_flower_ipv4_udp_tun *msk, + struct tc_cls_flower_offload *flow) { - struct fl_flow_key *target = mask_version ? flow->mask : flow->key; - struct flow_dissector_key_ipv4_addrs *tun_ips; - struct flow_dissector_key_keyid *vni; - struct flow_dissector_key_ip *ip; + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow); - memset(frame, 0, sizeof(struct nfp_flower_ipv4_udp_tun)); + memset(ext, 0, sizeof(struct nfp_flower_ipv4_udp_tun)); + memset(msk, 0, sizeof(struct nfp_flower_ipv4_udp_tun)); - if (dissector_uses_key(flow->dissector, - FLOW_DISSECTOR_KEY_ENC_KEYID)) { + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID)) { + struct flow_match_enc_keyid match; u32 temp_vni; - vni = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_ENC_KEYID, - target); - temp_vni = be32_to_cpu(vni->keyid) << NFP_FL_TUN_VNI_OFFSET; - frame->tun_id = cpu_to_be32(temp_vni); + flow_rule_match_enc_keyid(rule, &match); + temp_vni = be32_to_cpu(match.key->keyid) << NFP_FL_TUN_VNI_OFFSET; + ext->tun_id = cpu_to_be32(temp_vni); + temp_vni = be32_to_cpu(match.mask->keyid) << NFP_FL_TUN_VNI_OFFSET; + msk->tun_id = cpu_to_be32(temp_vni); } - if (dissector_uses_key(flow->dissector, - FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) { - tun_ips = - skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, - target); - frame->ip_src = tun_ips->src; - frame->ip_dst = tun_ips->dst; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) { + struct flow_match_ipv4_addrs match; + + flow_rule_match_enc_ipv4_addrs(rule, &match); + ext->ip_src = match.key->src; + ext->ip_dst = match.key->dst; + msk->ip_src = match.mask->src; + msk->ip_dst = match.mask->dst; } - if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_ENC_IP)) { - ip = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_ENC_IP, - target); - frame->tos = ip->tos; - frame->ttl = ip->ttl; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IP)) { + struct flow_match_ip match; + + flow_rule_match_enc_ip(rule, &match); + ext->tos = match.key->tos; + ext->ttl = match.key->ttl; + msk->tos = match.mask->tos; + msk->ttl = match.mask->ttl; } } @@ -313,12 +341,9 @@ int nfp_flower_compile_flow_match(struct nfp_app *app, ext = nfp_flow->unmasked_data; msk = nfp_flow->mask_data; - /* Populate Exact Metadata. */ nfp_flower_compile_meta_tci((struct nfp_flower_meta_tci *)ext, - flow, key_ls->key_layer, false); - /* Populate Mask Metadata. */ - nfp_flower_compile_meta_tci((struct nfp_flower_meta_tci *)msk, - flow, key_ls->key_layer, true); + (struct nfp_flower_meta_tci *)msk, + flow, key_ls->key_layer); ext += sizeof(struct nfp_flower_meta_tci); msk += sizeof(struct nfp_flower_meta_tci); @@ -348,45 +373,33 @@ int nfp_flower_compile_flow_match(struct nfp_app *app, msk += sizeof(struct nfp_flower_in_port); if (NFP_FLOWER_LAYER_MAC & key_ls->key_layer) { - /* Populate Exact MAC Data. */ nfp_flower_compile_mac((struct nfp_flower_mac_mpls *)ext, - flow, false); - /* Populate Mask MAC Data. */ - nfp_flower_compile_mac((struct nfp_flower_mac_mpls *)msk, - flow, true); + (struct nfp_flower_mac_mpls *)msk, + flow); ext += sizeof(struct nfp_flower_mac_mpls); msk += sizeof(struct nfp_flower_mac_mpls); } if (NFP_FLOWER_LAYER_TP & key_ls->key_layer) { - /* Populate Exact TP Data. */ nfp_flower_compile_tport((struct nfp_flower_tp_ports *)ext, - flow, false); - /* Populate Mask TP Data. */ - nfp_flower_compile_tport((struct nfp_flower_tp_ports *)msk, - flow, true); + (struct nfp_flower_tp_ports *)msk, + flow); ext += sizeof(struct nfp_flower_tp_ports); msk += sizeof(struct nfp_flower_tp_ports); } if (NFP_FLOWER_LAYER_IPV4 & key_ls->key_layer) { - /* Populate Exact IPv4 Data. */ nfp_flower_compile_ipv4((struct nfp_flower_ipv4 *)ext, - flow, false); - /* Populate Mask IPv4 Data. */ - nfp_flower_compile_ipv4((struct nfp_flower_ipv4 *)msk, - flow, true); + (struct nfp_flower_ipv4 *)msk, + flow); ext += sizeof(struct nfp_flower_ipv4); msk += sizeof(struct nfp_flower_ipv4); } if (NFP_FLOWER_LAYER_IPV6 & key_ls->key_layer) { - /* Populate Exact IPv4 Data. */ nfp_flower_compile_ipv6((struct nfp_flower_ipv6 *)ext, - flow, false); - /* Populate Mask IPv4 Data. */ - nfp_flower_compile_ipv6((struct nfp_flower_ipv6 *)msk, - flow, true); + (struct nfp_flower_ipv6 *)msk, + flow); ext += sizeof(struct nfp_flower_ipv6); msk += sizeof(struct nfp_flower_ipv6); } @@ -395,10 +408,7 @@ int nfp_flower_compile_flow_match(struct nfp_app *app, key_ls->key_layer_two & NFP_FLOWER_LAYER2_GENEVE) { __be32 tun_dst; - /* Populate Exact VXLAN Data. */ - nfp_flower_compile_ipv4_udp_tun((void *)ext, flow, false); - /* Populate Mask VXLAN Data. */ - nfp_flower_compile_ipv4_udp_tun((void *)msk, flow, true); + nfp_flower_compile_ipv4_udp_tun((void *)ext, (void *)msk, flow); tun_dst = ((struct nfp_flower_ipv4_udp_tun *)ext)->ip_dst; ext += sizeof(struct nfp_flower_ipv4_udp_tun); msk += sizeof(struct nfp_flower_ipv4_udp_tun); @@ -410,11 +420,7 @@ int nfp_flower_compile_flow_match(struct nfp_app *app, nfp_tunnel_add_ipv4_off(app, tun_dst); if (key_ls->key_layer_two & NFP_FLOWER_LAYER2_GENEVE_OP) { - err = nfp_flower_compile_geneve_opt(ext, flow, false); - if (err) - return err; - - err = nfp_flower_compile_geneve_opt(msk, flow, true); + err = nfp_flower_compile_geneve_opt(ext, msk, flow); if (err) return err; } diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index 2cdbf29ecbe7..450d7296fd57 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -102,23 +102,22 @@ nfp_flower_xmit_flow(struct nfp_app *app, struct nfp_fl_payload *nfp_flow, static bool nfp_flower_check_higher_than_mac(struct tc_cls_flower_offload *f) { - return dissector_uses_key(f->dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS) || - dissector_uses_key(f->dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS) || - dissector_uses_key(f->dissector, - FLOW_DISSECTOR_KEY_PORTS) || - dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ICMP); + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f); + + return flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS) || + flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS) || + flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS) || + flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ICMP); } static int -nfp_flower_calc_opt_layer(struct flow_dissector_key_enc_opts *enc_opts, +nfp_flower_calc_opt_layer(struct flow_match_enc_opts *enc_opts, u32 *key_layer_two, int *key_size) { - if (enc_opts->len > NFP_FL_MAX_GENEVE_OPT_KEY) + if (enc_opts->key->len > NFP_FL_MAX_GENEVE_OPT_KEY) return -EOPNOTSUPP; - if (enc_opts->len > 0) { + if (enc_opts->key->len > 0) { *key_layer_two |= NFP_FLOWER_LAYER2_GENEVE_OP; *key_size += sizeof(struct nfp_flower_geneve_options); } @@ -133,20 +132,21 @@ nfp_flower_calculate_key_layers(struct nfp_app *app, struct tc_cls_flower_offload *flow, enum nfp_flower_tun_type *tun_type) { - struct flow_dissector_key_basic *mask_basic = NULL; - struct flow_dissector_key_basic *key_basic = NULL; + struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow); + struct flow_dissector *dissector = rule->match.dissector; + struct flow_match_basic basic = { NULL, NULL}; struct nfp_flower_priv *priv = app->priv; u32 key_layer_two; u8 key_layer; int key_size; int err; - if (flow->dissector->used_keys & ~NFP_FLOWER_WHITELIST_DISSECTOR) + if (dissector->used_keys & ~NFP_FLOWER_WHITELIST_DISSECTOR) return -EOPNOTSUPP; /* If any tun dissector is used then the required set must be used. */ - if (flow->dissector->used_keys & NFP_FLOWER_WHITELIST_TUN_DISSECTOR && - (flow->dissector->used_keys & NFP_FLOWER_WHITELIST_TUN_DISSECTOR_R) + if (dissector->used_keys & NFP_FLOWER_WHITELIST_TUN_DISSECTOR && + (dissector->used_keys & NFP_FLOWER_WHITELIST_TUN_DISSECTOR_R) != NFP_FLOWER_WHITELIST_TUN_DISSECTOR_R) return -EOPNOTSUPP; @@ -155,76 +155,52 @@ nfp_flower_calculate_key_layers(struct nfp_app *app, key_size = sizeof(struct nfp_flower_meta_tci) + sizeof(struct nfp_flower_in_port); - if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS) || - dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_MPLS)) { + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS) || + flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_MPLS)) { key_layer |= NFP_FLOWER_LAYER_MAC; key_size += sizeof(struct nfp_flower_mac_mpls); } - if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_VLAN)) { - struct flow_dissector_key_vlan *flow_vlan; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_match_vlan vlan; - flow_vlan = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_VLAN, - flow->mask); + flow_rule_match_vlan(rule, &vlan); if (!(priv->flower_ext_feats & NFP_FL_FEATS_VLAN_PCP) && - flow_vlan->vlan_priority) + vlan.key->vlan_priority) return -EOPNOTSUPP; } - if (dissector_uses_key(flow->dissector, - FLOW_DISSECTOR_KEY_ENC_CONTROL)) { - struct flow_dissector_key_ipv4_addrs *mask_ipv4 = NULL; - struct flow_dissector_key_ports *mask_enc_ports = NULL; - struct flow_dissector_key_enc_opts *enc_op = NULL; - struct flow_dissector_key_ports *enc_ports = NULL; - struct flow_dissector_key_control *mask_enc_ctl = - skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_ENC_CONTROL, - flow->mask); - struct flow_dissector_key_control *enc_ctl = - skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_ENC_CONTROL, - flow->key); - - if (mask_enc_ctl->addr_type != 0xffff || - enc_ctl->addr_type != FLOW_DISSECTOR_KEY_IPV4_ADDRS) + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_CONTROL)) { + struct flow_match_enc_opts enc_op = { NULL, NULL }; + struct flow_match_ipv4_addrs ipv4_addrs; + struct flow_match_control enc_ctl; + struct flow_match_ports enc_ports; + + flow_rule_match_enc_control(rule, &enc_ctl); + + if (enc_ctl.mask->addr_type != 0xffff || + enc_ctl.key->addr_type != FLOW_DISSECTOR_KEY_IPV4_ADDRS) return -EOPNOTSUPP; /* These fields are already verified as used. */ - mask_ipv4 = - skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, - flow->mask); - if (mask_ipv4->dst != cpu_to_be32(~0)) + flow_rule_match_enc_ipv4_addrs(rule, &ipv4_addrs); + if (ipv4_addrs.mask->dst != cpu_to_be32(~0)) return -EOPNOTSUPP; - mask_enc_ports = - skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_ENC_PORTS, - flow->mask); - enc_ports = - skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_ENC_PORTS, - flow->key); - - if (mask_enc_ports->dst != cpu_to_be16(~0)) + flow_rule_match_enc_ports(rule, &enc_ports); + if (enc_ports.mask->dst != cpu_to_be16(~0)) return -EOPNOTSUPP; - if (dissector_uses_key(flow->dissector, - FLOW_DISSECTOR_KEY_ENC_OPTS)) { - enc_op = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_ENC_OPTS, - flow->key); - } + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_OPTS)) + flow_rule_match_enc_opts(rule, &enc_op); - switch (enc_ports->dst) { + switch (enc_ports.key->dst) { case htons(NFP_FL_VXLAN_PORT): *tun_type = NFP_FL_TUNNEL_VXLAN; key_layer |= NFP_FLOWER_LAYER_VXLAN; key_size += sizeof(struct nfp_flower_ipv4_udp_tun); - if (enc_op) + if (enc_op.key) return -EOPNOTSUPP; break; case htons(NFP_FL_GENEVE_PORT): @@ -236,11 +212,11 @@ nfp_flower_calculate_key_layers(struct nfp_app *app, key_layer_two |= NFP_FLOWER_LAYER2_GENEVE; key_size += sizeof(struct nfp_flower_ipv4_udp_tun); - if (!enc_op) + if (!enc_op.key) break; if (!(priv->flower_ext_feats & NFP_FL_FEATS_GENEVE_OPT)) return -EOPNOTSUPP; - err = nfp_flower_calc_opt_layer(enc_op, &key_layer_two, + err = nfp_flower_calc_opt_layer(&enc_op, &key_layer_two, &key_size); if (err) return err; @@ -254,19 +230,12 @@ nfp_flower_calculate_key_layers(struct nfp_app *app, return -EOPNOTSUPP; } - if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_BASIC)) { - mask_basic = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_BASIC, - flow->mask); - - key_basic = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_BASIC, - flow->key); - } + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) + flow_rule_match_basic(rule, &basic); - if (mask_basic && mask_basic->n_proto) { + if (basic.mask && basic.mask->n_proto) { /* Ethernet type is present in the key. */ - switch (key_basic->n_proto) { + switch (basic.key->n_proto) { case cpu_to_be16(ETH_P_IP): key_layer |= NFP_FLOWER_LAYER_IPV4; key_size += sizeof(struct nfp_flower_ipv4); @@ -305,9 +274,9 @@ nfp_flower_calculate_key_layers(struct nfp_app *app, } } - if (mask_basic && mask_basic->ip_proto) { + if (basic.mask && basic.mask->ip_proto) { /* Ethernet type is present in the key. */ - switch (key_basic->ip_proto) { + switch (basic.key->ip_proto) { case IPPROTO_TCP: case IPPROTO_UDP: case IPPROTO_SCTP: @@ -324,14 +293,12 @@ nfp_flower_calculate_key_layers(struct nfp_app *app, } } - if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_TCP)) { - struct flow_dissector_key_tcp *tcp; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_TCP)) { + struct flow_match_tcp tcp; u32 tcp_flags; - tcp = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_TCP, - flow->key); - tcp_flags = be16_to_cpu(tcp->flags); + flow_rule_match_tcp(rule, &tcp); + tcp_flags = be16_to_cpu(tcp.key->flags); if (tcp_flags & ~NFP_FLOWER_SUPPORTED_TCPFLAGS) return -EOPNOTSUPP; @@ -347,12 +314,12 @@ nfp_flower_calculate_key_layers(struct nfp_app *app, * space, thus we need to ensure we include a IPv4/IPv6 key * layer if we have not done so already. */ - if (!key_basic) + if (!basic.key) return -EOPNOTSUPP; if (!(key_layer & NFP_FLOWER_LAYER_IPV4) && !(key_layer & NFP_FLOWER_LAYER_IPV6)) { - switch (key_basic->n_proto) { + switch (basic.key->n_proto) { case cpu_to_be16(ETH_P_IP): key_layer |= NFP_FLOWER_LAYER_IPV4; key_size += sizeof(struct nfp_flower_ipv4); @@ -369,14 +336,11 @@ nfp_flower_calculate_key_layers(struct nfp_app *app, } } - if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_CONTROL)) { - struct flow_dissector_key_control *key_ctl; - - key_ctl = skb_flow_dissector_target(flow->dissector, - FLOW_DISSECTOR_KEY_CONTROL, - flow->key); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) { + struct flow_match_control ctl; - if (key_ctl->flags & ~NFP_FLOWER_SUPPORTED_CTLFLAGS) + flow_rule_match_control(rule, &ctl); + if (ctl.key->flags & ~NFP_FLOWER_SUPPORTED_CTLFLAGS) return -EOPNOTSUPP; } @@ -589,9 +553,8 @@ nfp_flower_get_stats(struct nfp_app *app, struct net_device *netdev, ctx_id = be32_to_cpu(nfp_flow->meta.host_ctx_id); spin_lock_bh(&priv->stats_lock); - tcf_exts_stats_update(flow->exts, priv->stats[ctx_id].bytes, - priv->stats[ctx_id].pkts, - priv->stats[ctx_id].used); + flow_stats_update(&flow->stats, priv->stats[ctx_id].bytes, + priv->stats[ctx_id].pkts, priv->stats[ctx_id].used); priv->stats[ctx_id].pkts = 0; priv->stats[ctx_id].bytes = 0; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c index 808647ec3573..db2da99f6aa7 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_devlink.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_devlink.c @@ -4,6 +4,7 @@ #include <linux/rtnetlink.h> #include <net/devlink.h> +#include "nfpcore/nfp.h" #include "nfpcore/nfp_nsp.h" #include "nfp_app.h" #include "nfp_main.h" @@ -171,6 +172,173 @@ static int nfp_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, return ret; } +static const struct nfp_devlink_versions_simple { + const char *key; + const char *hwinfo; +} nfp_devlink_versions_hwinfo[] = { + { DEVLINK_INFO_VERSION_GENERIC_BOARD_ID, "assembly.partno", }, + { DEVLINK_INFO_VERSION_GENERIC_BOARD_REV, "assembly.revision", }, + { DEVLINK_INFO_VERSION_GENERIC_BOARD_MANUFACTURE, "assembly.vendor", }, + { "board.model", /* code name */ "assembly.model", }, +}; + +static int +nfp_devlink_versions_get_hwinfo(struct nfp_pf *pf, struct devlink_info_req *req) +{ + unsigned int i; + int err; + + for (i = 0; i < ARRAY_SIZE(nfp_devlink_versions_hwinfo); i++) { + const struct nfp_devlink_versions_simple *info; + const char *val; + + info = &nfp_devlink_versions_hwinfo[i]; + + val = nfp_hwinfo_lookup(pf->hwinfo, info->hwinfo); + if (!val) + continue; + + err = devlink_info_version_fixed_put(req, info->key, val); + if (err) + return err; + } + + return 0; +} + +static const struct nfp_devlink_versions { + enum nfp_nsp_versions id; + const char *key; +} nfp_devlink_versions_nsp[] = { + { NFP_VERSIONS_BUNDLE, "fw.bundle_id", }, + { NFP_VERSIONS_BSP, DEVLINK_INFO_VERSION_GENERIC_FW_MGMT, }, + { NFP_VERSIONS_CPLD, "fw.cpld", }, + { NFP_VERSIONS_APP, DEVLINK_INFO_VERSION_GENERIC_FW_APP, }, + { NFP_VERSIONS_UNDI, DEVLINK_INFO_VERSION_GENERIC_FW_UNDI, }, + { NFP_VERSIONS_NCSI, DEVLINK_INFO_VERSION_GENERIC_FW_NCSI, }, + { NFP_VERSIONS_CFGR, "chip.init", }, +}; + +static int +nfp_devlink_versions_get_nsp(struct devlink_info_req *req, bool flash, + const u8 *buf, unsigned int size) +{ + unsigned int i; + int err; + + for (i = 0; i < ARRAY_SIZE(nfp_devlink_versions_nsp); i++) { + const struct nfp_devlink_versions *info; + const char *version; + + info = &nfp_devlink_versions_nsp[i]; + + version = nfp_nsp_versions_get(info->id, flash, buf, size); + if (IS_ERR(version)) { + if (PTR_ERR(version) == -ENOENT) + continue; + else + return PTR_ERR(version); + } + + if (flash) + err = devlink_info_version_stored_put(req, info->key, + version); + else + err = devlink_info_version_running_put(req, info->key, + version); + if (err) + return err; + } + + return 0; +} + +static int +nfp_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req, + struct netlink_ext_ack *extack) +{ + struct nfp_pf *pf = devlink_priv(devlink); + const char *sn, *vendor, *part; + struct nfp_nsp *nsp; + char *buf = NULL; + int err; + + err = devlink_info_driver_name_put(req, "nfp"); + if (err) + return err; + + vendor = nfp_hwinfo_lookup(pf->hwinfo, "assembly.vendor"); + part = nfp_hwinfo_lookup(pf->hwinfo, "assembly.partno"); + sn = nfp_hwinfo_lookup(pf->hwinfo, "assembly.serial"); + if (vendor && part && sn) { + char *buf; + + buf = kmalloc(strlen(vendor) + strlen(part) + strlen(sn) + 1, + GFP_KERNEL); + if (!buf) + return -ENOMEM; + + buf[0] = '\0'; + strcat(buf, vendor); + strcat(buf, part); + strcat(buf, sn); + + err = devlink_info_serial_number_put(req, buf); + kfree(buf); + if (err) + return err; + } + + nsp = nfp_nsp_open(pf->cpp); + if (IS_ERR(nsp)) { + NL_SET_ERR_MSG_MOD(extack, "can't access NSP"); + return PTR_ERR(nsp); + } + + if (nfp_nsp_has_versions(nsp)) { + buf = kzalloc(NFP_NSP_VERSION_BUFSZ, GFP_KERNEL); + if (!buf) { + err = -ENOMEM; + goto err_close_nsp; + } + + err = nfp_nsp_versions(nsp, buf, NFP_NSP_VERSION_BUFSZ); + if (err) + goto err_free_buf; + + err = nfp_devlink_versions_get_nsp(req, false, + buf, NFP_NSP_VERSION_BUFSZ); + if (err) + goto err_free_buf; + + err = nfp_devlink_versions_get_nsp(req, true, + buf, NFP_NSP_VERSION_BUFSZ); + if (err) + goto err_free_buf; + + kfree(buf); + } + + nfp_nsp_close(nsp); + + return nfp_devlink_versions_get_hwinfo(pf, req); + +err_free_buf: + kfree(buf); +err_close_nsp: + nfp_nsp_close(nsp); + return err; +} + +static int +nfp_devlink_flash_update(struct devlink *devlink, const char *path, + const char *component, struct netlink_ext_ack *extack) +{ + if (component) + return -EOPNOTSUPP; + return nfp_flash_update_common(devlink_priv(devlink), path, extack); +} + const struct devlink_ops nfp_devlink_ops = { .port_split = nfp_devlink_port_split, .port_unsplit = nfp_devlink_port_unsplit, @@ -178,6 +346,8 @@ const struct devlink_ops nfp_devlink_ops = { .sb_pool_set = nfp_devlink_sb_pool_set, .eswitch_mode_get = nfp_devlink_eswitch_mode_get, .eswitch_mode_set = nfp_devlink_eswitch_mode_set, + .info_get = nfp_devlink_info_get, + .flash_update = nfp_devlink_flash_update, }; int nfp_devlink_port_register(struct nfp_app *app, struct nfp_port *port) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.c b/drivers/net/ethernet/netronome/nfp/nfp_main.c index 6c10e8d119e4..f4c8776e42b6 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_main.c @@ -300,6 +300,47 @@ static int nfp_pcie_sriov_configure(struct pci_dev *pdev, int num_vfs) return nfp_pcie_sriov_enable(pdev, num_vfs); } +int nfp_flash_update_common(struct nfp_pf *pf, const char *path, + struct netlink_ext_ack *extack) +{ + struct device *dev = &pf->pdev->dev; + const struct firmware *fw; + struct nfp_nsp *nsp; + int err; + + nsp = nfp_nsp_open(pf->cpp); + if (IS_ERR(nsp)) { + err = PTR_ERR(nsp); + if (extack) + NL_SET_ERR_MSG_MOD(extack, "can't access NSP"); + else + dev_err(dev, "Failed to access the NSP: %d\n", err); + return err; + } + + err = request_firmware_direct(&fw, path, dev); + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "unable to read flash file from disk"); + goto exit_close_nsp; + } + + dev_info(dev, "Please be patient while writing flash image: %s\n", + path); + + err = nfp_nsp_write_flash(nsp, fw); + if (err < 0) + goto exit_release_fw; + dev_info(dev, "Finished writing flash image\n"); + err = 0; + +exit_release_fw: + release_firmware(fw); +exit_close_nsp: + nfp_nsp_close(nsp); + return err; +} + static const struct firmware * nfp_net_fw_request(struct pci_dev *pdev, struct nfp_pf *pf, const char *name) { diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.h b/drivers/net/ethernet/netronome/nfp/nfp_main.h index a3613a2e0aa5..b7211f200d22 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_main.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_main.h @@ -164,6 +164,8 @@ nfp_pf_map_rtsym(struct nfp_pf *pf, const char *name, const char *sym_fmt, unsigned int min_size, struct nfp_cpp_area **area); int nfp_mbox_cmd(struct nfp_pf *pf, u32 cmd, void *in_data, u64 in_length, void *out_data, u64 out_length); +int nfp_flash_update_common(struct nfp_pf *pf, const char *path, + struct netlink_ext_ack *extack); enum nfp_dump_diag { NFP_DUMP_NSP_DIAG = 0, diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 7d2d4241498f..776f6c07701b 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -36,7 +36,6 @@ #include <linux/vmalloc.h> #include <linux/ktime.h> -#include <net/switchdev.h> #include <net/vxlan.h> #include "nfpcore/nfp_nsp.h" @@ -3531,6 +3530,7 @@ const struct net_device_ops nfp_net_netdev_ops = { .ndo_udp_tunnel_add = nfp_net_add_vxlan_port, .ndo_udp_tunnel_del = nfp_net_del_vxlan_port, .ndo_bpf = nfp_net_xdp, + .ndo_get_port_parent_id = nfp_port_get_port_parent_id, }; /** @@ -3815,8 +3815,6 @@ static void nfp_net_netdev_init(struct nfp_net *nn) netdev->netdev_ops = &nfp_net_netdev_ops; netdev->watchdog_timeo = msecs_to_jiffies(5 * 1000); - SWITCHDEV_SET_OPS(netdev, &nfp_port_switchdev_ops); - /* MTU range: 68 - hw-specific max */ netdev->min_mtu = ETH_MIN_MTU; netdev->max_mtu = nn->max_mtu; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index cb9c512abc76..8f189149efc5 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -1237,11 +1237,8 @@ static int nfp_net_set_channels(struct net_device *netdev, static int nfp_net_flash_device(struct net_device *netdev, struct ethtool_flash *flash) { - const struct firmware *fw; struct nfp_app *app; - struct nfp_nsp *nsp; - struct device *dev; - int err; + int ret; if (flash->region != ETHTOOL_FLASH_ALL_REGIONS) return -EOPNOTSUPP; @@ -1250,39 +1247,13 @@ nfp_net_flash_device(struct net_device *netdev, struct ethtool_flash *flash) if (!app) return -EOPNOTSUPP; - dev = &app->pdev->dev; - - nsp = nfp_nsp_open(app->cpp); - if (IS_ERR(nsp)) { - err = PTR_ERR(nsp); - dev_err(dev, "Failed to access the NSP: %d\n", err); - return err; - } - - err = request_firmware_direct(&fw, flash->data, dev); - if (err) - goto exit_close_nsp; - - dev_info(dev, "Please be patient while writing flash image: %s\n", - flash->data); dev_hold(netdev); rtnl_unlock(); - - err = nfp_nsp_write_flash(nsp, fw); - if (err < 0) { - dev_err(dev, "Flash write failed: %d\n", err); - goto exit_rtnl_lock; - } - dev_info(dev, "Finished writing flash image\n"); - -exit_rtnl_lock: + ret = nfp_flash_update_common(app->pf, flash->data, NULL); rtnl_lock(); dev_put(netdev); - release_firmware(fw); -exit_close_nsp: - nfp_nsp_close(nsp); - return err; + return ret; } static const struct ethtool_ops nfp_net_ethtool_ops = { diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c index 69d7aebda09b..62839807e21e 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c @@ -5,7 +5,6 @@ #include <linux/io-64-nonatomic-hi-lo.h> #include <linux/lockdep.h> #include <net/dst_metadata.h> -#include <net/switchdev.h> #include "nfpcore/nfp_cpp.h" #include "nfpcore/nfp_nsp.h" @@ -273,6 +272,7 @@ const struct net_device_ops nfp_repr_netdev_ops = { .ndo_fix_features = nfp_repr_fix_features, .ndo_set_features = nfp_port_set_features, .ndo_set_mac_address = eth_mac_addr, + .ndo_get_port_parent_id = nfp_port_get_port_parent_id, }; void @@ -336,8 +336,6 @@ int nfp_repr_init(struct nfp_app *app, struct net_device *netdev, netdev->max_mtu = pf_netdev->max_mtu; - SWITCHDEV_SET_OPS(netdev, &nfp_port_switchdev_ops); - /* Set features the lower device can support with representors */ if (repr_cap & NFP_NET_CFG_CTRL_LIVE_ADDR) netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_port.c b/drivers/net/ethernet/netronome/nfp/nfp_port.c index 86bc149ca231..7e90880fa46b 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_port.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_port.c @@ -31,34 +31,22 @@ struct nfp_port *nfp_port_from_netdev(struct net_device *netdev) return NULL; } -static int -nfp_port_attr_get(struct net_device *netdev, struct switchdev_attr *attr) +int nfp_port_get_port_parent_id(struct net_device *netdev, + struct netdev_phys_item_id *ppid) { struct nfp_port *port; + const u8 *serial; port = nfp_port_from_netdev(netdev); if (!port) return -EOPNOTSUPP; - switch (attr->id) { - case SWITCHDEV_ATTR_ID_PORT_PARENT_ID: { - const u8 *serial; - /* N.B: attr->u.ppid.id is binary data */ - attr->u.ppid.id_len = nfp_cpp_serial(port->app->cpp, &serial); - memcpy(&attr->u.ppid.id, serial, attr->u.ppid.id_len); - break; - } - default: - return -EOPNOTSUPP; - } + ppid->id_len = nfp_cpp_serial(port->app->cpp, &serial); + memcpy(&ppid->id, serial, ppid->id_len); return 0; } -const struct switchdev_ops nfp_port_switchdev_ops = { - .switchdev_port_attr_get = nfp_port_attr_get, -}; - int nfp_port_setup_tc(struct net_device *netdev, enum tc_setup_type type, void *type_data) { diff --git a/drivers/net/ethernet/netronome/nfp/nfp_port.h b/drivers/net/ethernet/netronome/nfp/nfp_port.h index b2479a2a49e5..90ae053f5c07 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_port.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_port.h @@ -7,6 +7,7 @@ #include <net/devlink.h> struct net_device; +struct netdev_phys_item_id; struct nfp_app; struct nfp_pf; struct nfp_port; @@ -90,7 +91,6 @@ struct nfp_port { }; extern const struct ethtool_ops nfp_port_ethtool_ops; -extern const struct switchdev_ops nfp_port_switchdev_ops; __printf(2, 3) u8 *nfp_pr_et(u8 *data, const char *fmt, ...); @@ -106,6 +106,8 @@ int nfp_port_set_features(struct net_device *netdev, netdev_features_t features); struct nfp_port *nfp_port_from_netdev(struct net_device *netdev); +int nfp_port_get_port_parent_id(struct net_device *netdev, + struct netdev_phys_item_id *ppid); struct nfp_port * nfp_port_from_id(struct nfp_pf *pf, enum nfp_port_type type, unsigned int id); struct nfp_eth_table_port *__nfp_port_get_eth_port(struct nfp_port *port); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_shared_buf.c b/drivers/net/ethernet/netronome/nfp/nfp_shared_buf.c index 814360ed3a20..ea2e3f829aba 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_shared_buf.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_shared_buf.c @@ -48,6 +48,7 @@ int nfp_shared_buf_pool_get(struct nfp_pf *pf, unsigned int sb, u16 pool_index, pool_info->pool_type = le32_to_cpu(get_data.pool_type); pool_info->threshold_type = le32_to_cpu(get_data.threshold_type); pool_info->size = le32_to_cpu(get_data.size) * unit_size; + pool_info->cell_size = unit_size; return 0; } diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c index ce1577bbbd2a..a9d53df0070c 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c @@ -7,6 +7,7 @@ * Jason McMullan <jason.mcmullan@netronome.com> */ +#include <asm/unaligned.h> #include <linux/bitfield.h> #include <linux/delay.h> #include <linux/firmware.h> @@ -62,6 +63,16 @@ #define NFP_HWINFO_LOOKUP_SIZE GENMASK(11, 0) +#define NFP_VERSIONS_SIZE GENMASK(11, 0) +#define NFP_VERSIONS_CNT_OFF 0 +#define NFP_VERSIONS_BSP_OFF 2 +#define NFP_VERSIONS_CPLD_OFF 6 +#define NFP_VERSIONS_APP_OFF 10 +#define NFP_VERSIONS_BUNDLE_OFF 14 +#define NFP_VERSIONS_UNDI_OFF 18 +#define NFP_VERSIONS_NCSI_OFF 22 +#define NFP_VERSIONS_CFGR_OFF 26 + enum nfp_nsp_cmd { SPCODE_NOOP = 0, /* No operation */ SPCODE_SOFT_RESET = 1, /* Soft reset the NFP */ @@ -77,6 +88,7 @@ enum nfp_nsp_cmd { SPCODE_NSP_IDENTIFY = 13, /* Read NSP version */ SPCODE_FW_STORED = 16, /* If no FW loaded, load flash app FW */ SPCODE_HWINFO_LOOKUP = 17, /* Lookup HWinfo with overwrites etc. */ + SPCODE_VERSIONS = 21, /* Report FW versions */ }; static const struct { @@ -711,3 +723,52 @@ int nfp_nsp_hwinfo_lookup(struct nfp_nsp *state, void *buf, unsigned int size) return 0; } + +int nfp_nsp_versions(struct nfp_nsp *state, void *buf, unsigned int size) +{ + struct nfp_nsp_command_buf_arg versions = { + { + .code = SPCODE_VERSIONS, + .option = min_t(u32, size, NFP_VERSIONS_SIZE), + }, + .out_buf = buf, + .out_size = min_t(u32, size, NFP_VERSIONS_SIZE), + }; + + return nfp_nsp_command_buf(state, &versions); +} + +const char *nfp_nsp_versions_get(enum nfp_nsp_versions id, bool flash, + const u8 *buf, unsigned int size) +{ + static const u32 id2off[] = { + [NFP_VERSIONS_BSP] = NFP_VERSIONS_BSP_OFF, + [NFP_VERSIONS_CPLD] = NFP_VERSIONS_CPLD_OFF, + [NFP_VERSIONS_APP] = NFP_VERSIONS_APP_OFF, + [NFP_VERSIONS_BUNDLE] = NFP_VERSIONS_BUNDLE_OFF, + [NFP_VERSIONS_UNDI] = NFP_VERSIONS_UNDI_OFF, + [NFP_VERSIONS_NCSI] = NFP_VERSIONS_NCSI_OFF, + [NFP_VERSIONS_CFGR] = NFP_VERSIONS_CFGR_OFF, + }; + unsigned int field, buf_field_cnt, buf_off; + + if (id >= ARRAY_SIZE(id2off) || !id2off[id]) + return ERR_PTR(-EINVAL); + + field = id * 2 + flash; + + buf_field_cnt = get_unaligned_le16(buf); + if (buf_field_cnt <= field) + return ERR_PTR(-ENOENT); + + buf_off = get_unaligned_le16(buf + id2off[id] + flash * 2); + if (!buf_off) + return ERR_PTR(-ENOENT); + + if (buf_off >= size) + return ERR_PTR(-EINVAL); + if (strnlen(&buf[buf_off], size - buf_off) == size - buf_off) + return ERR_PTR(-EINVAL); + + return (const char *)&buf[buf_off]; +} diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h index ff33ac54097a..246e213f1514 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h @@ -38,6 +38,11 @@ static inline bool nfp_nsp_has_hwinfo_lookup(struct nfp_nsp *state) return nfp_nsp_get_abi_ver_minor(state) > 24; } +static inline bool nfp_nsp_has_versions(struct nfp_nsp *state) +{ + return nfp_nsp_get_abi_ver_minor(state) > 27; +} + enum nfp_eth_interface { NFP_INTERFACE_NONE = 0, NFP_INTERFACE_SFP = 1, @@ -208,4 +213,19 @@ enum nfp_nsp_sensor_id { int nfp_hwmon_read_sensor(struct nfp_cpp *cpp, enum nfp_nsp_sensor_id id, long *val); +#define NFP_NSP_VERSION_BUFSZ 1024 /* reasonable size, not in the ABI */ + +enum nfp_nsp_versions { + NFP_VERSIONS_BSP, + NFP_VERSIONS_CPLD, + NFP_VERSIONS_APP, + NFP_VERSIONS_BUNDLE, + NFP_VERSIONS_UNDI, + NFP_VERSIONS_NCSI, + NFP_VERSIONS_CFGR, +}; + +int nfp_nsp_versions(struct nfp_nsp *state, void *buf, unsigned int size); +const char *nfp_nsp_versions_get(enum nfp_nsp_versions id, bool flash, + const u8 *buf, unsigned int size); #endif diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c index 802c9224bb32..f6f028fa5db9 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp_eth.c @@ -269,8 +269,7 @@ __nfp_eth_read_ports(struct nfp_cpp *cpp, struct nfp_nsp *nsp) goto err; } - table = kzalloc(sizeof(*table) + - sizeof(struct nfp_eth_table_port) * cnt, GFP_KERNEL); + table = kzalloc(struct_size(table, ports, cnt), GFP_KERNEL); if (!table) goto err; diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c index 1e408d1a9b5f..96f7a9818294 100644 --- a/drivers/net/ethernet/ni/nixge.c +++ b/drivers/net/ethernet/ni/nixge.c @@ -105,6 +105,12 @@ #define NIXGE_MAX_JUMBO_FRAME_SIZE \ (NIXGE_JUMBO_MTU + NIXGE_HDR_SIZE + NIXGE_TRL_SIZE) +enum nixge_version { + NIXGE_V2, + NIXGE_V3, + NIXGE_VERSION_COUNT +}; + struct nixge_hw_dma_bd { u32 next_lo; u32 next_hi; @@ -1225,11 +1231,60 @@ static void *nixge_get_nvmem_address(struct device *dev) return mac; } +/* Match table for of_platform binding */ +static const struct of_device_id nixge_dt_ids[] = { + { .compatible = "ni,xge-enet-2.00", .data = (void *)NIXGE_V2 }, + { .compatible = "ni,xge-enet-3.00", .data = (void *)NIXGE_V3 }, + {}, +}; +MODULE_DEVICE_TABLE(of, nixge_dt_ids); + +static int nixge_of_get_resources(struct platform_device *pdev) +{ + const struct of_device_id *of_id; + enum nixge_version version; + struct resource *ctrlres; + struct resource *dmares; + struct net_device *ndev; + struct nixge_priv *priv; + + ndev = platform_get_drvdata(pdev); + priv = netdev_priv(ndev); + of_id = of_match_node(nixge_dt_ids, pdev->dev.of_node); + if (!of_id) + return -ENODEV; + + version = (enum nixge_version)of_id->data; + if (version <= NIXGE_V2) + dmares = platform_get_resource(pdev, IORESOURCE_MEM, 0); + else + dmares = platform_get_resource_byname(pdev, IORESOURCE_MEM, + "dma"); + + priv->dma_regs = devm_ioremap_resource(&pdev->dev, dmares); + if (IS_ERR(priv->dma_regs)) { + netdev_err(ndev, "failed to map dma regs\n"); + return PTR_ERR(priv->dma_regs); + } + if (version <= NIXGE_V2) { + priv->ctrl_regs = priv->dma_regs + NIXGE_REG_CTRL_OFFSET; + } else { + ctrlres = platform_get_resource_byname(pdev, IORESOURCE_MEM, + "ctrl"); + priv->ctrl_regs = devm_ioremap_resource(&pdev->dev, ctrlres); + } + if (IS_ERR(priv->ctrl_regs)) { + netdev_err(ndev, "failed to map ctrl regs\n"); + return PTR_ERR(priv->ctrl_regs); + } + return 0; +} + static int nixge_probe(struct platform_device *pdev) { + struct device_node *mn, *phy_node; struct nixge_priv *priv; struct net_device *ndev; - struct resource *dmares; const u8 *mac_addr; int err; @@ -1261,14 +1316,9 @@ static int nixge_probe(struct platform_device *pdev) priv->dev = &pdev->dev; netif_napi_add(ndev, &priv->napi, nixge_poll, NAPI_POLL_WEIGHT); - - dmares = platform_get_resource(pdev, IORESOURCE_MEM, 0); - priv->dma_regs = devm_ioremap_resource(&pdev->dev, dmares); - if (IS_ERR(priv->dma_regs)) { - netdev_err(ndev, "failed to map dma regs\n"); - return PTR_ERR(priv->dma_regs); - } - priv->ctrl_regs = priv->dma_regs + NIXGE_REG_CTRL_OFFSET; + err = nixge_of_get_resources(pdev); + if (err) + return err; __nixge_hw_set_mac_address(ndev); priv->tx_irq = platform_get_irq_byname(pdev, "tx"); @@ -1286,10 +1336,14 @@ static int nixge_probe(struct platform_device *pdev) priv->coalesce_count_rx = XAXIDMA_DFT_RX_THRESHOLD; priv->coalesce_count_tx = XAXIDMA_DFT_TX_THRESHOLD; - err = nixge_mdio_setup(priv, pdev->dev.of_node); - if (err) { - netdev_err(ndev, "error registering mdio bus"); - goto free_netdev; + mn = of_get_child_by_name(pdev->dev.of_node, "mdio"); + if (mn) { + err = nixge_mdio_setup(priv, mn); + of_node_put(mn); + if (err) { + netdev_err(ndev, "error registering mdio bus"); + goto free_netdev; + } } priv->phy_mode = of_get_phy_mode(pdev->dev.of_node); @@ -1299,23 +1353,33 @@ static int nixge_probe(struct platform_device *pdev) goto unregister_mdio; } - priv->phy_node = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0); - if (!priv->phy_node) { - netdev_err(ndev, "not find \"phy-handle\" property\n"); - err = -EINVAL; - goto unregister_mdio; + phy_node = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0); + if (!phy_node && of_phy_is_fixed_link(pdev->dev.of_node)) { + err = of_phy_register_fixed_link(pdev->dev.of_node); + if (err < 0) { + netdev_err(ndev, "broken fixed-link specification\n"); + goto unregister_mdio; + } + phy_node = of_node_get(pdev->dev.of_node); } + priv->phy_node = phy_node; err = register_netdev(priv->ndev); if (err) { netdev_err(ndev, "register_netdev() error (%i)\n", err); - goto unregister_mdio; + goto free_phy; } return 0; +free_phy: + if (of_phy_is_fixed_link(pdev->dev.of_node)) + of_phy_deregister_fixed_link(pdev->dev.of_node); + of_node_put(phy_node); + unregister_mdio: - mdiobus_unregister(priv->mii_bus); + if (priv->mii_bus) + mdiobus_unregister(priv->mii_bus); free_netdev: free_netdev(ndev); @@ -1330,20 +1394,18 @@ static int nixge_remove(struct platform_device *pdev) unregister_netdev(ndev); - mdiobus_unregister(priv->mii_bus); + if (of_phy_is_fixed_link(pdev->dev.of_node)) + of_phy_deregister_fixed_link(pdev->dev.of_node); + of_node_put(priv->phy_node); + + if (priv->mii_bus) + mdiobus_unregister(priv->mii_bus); free_netdev(ndev); return 0; } -/* Match table for of_platform binding */ -static const struct of_device_id nixge_dt_ids[] = { - { .compatible = "ni,xge-enet-2.00", }, - {}, -}; -MODULE_DEVICE_TABLE(of, nixge_dt_ids); - static struct platform_driver nixge_driver = { .probe = nixge_probe, .remove = nixge_remove, diff --git a/drivers/net/ethernet/nuvoton/w90p910_ether.c b/drivers/net/ethernet/nuvoton/w90p910_ether.c index c662c6f5bee3..67bf02b0763a 100644 --- a/drivers/net/ethernet/nuvoton/w90p910_ether.c +++ b/drivers/net/ethernet/nuvoton/w90p910_ether.c @@ -630,7 +630,7 @@ static int w90p910_ether_start_xmit(struct sk_buff *skb, struct net_device *dev) if (!(w90p910_send_frame(dev, skb->data, skb->len))) { ether->skb = skb; - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); return 0; } return -EAGAIN; diff --git a/drivers/net/ethernet/packetengines/hamachi.c b/drivers/net/ethernet/packetengines/hamachi.c index c9529c29a0a7..eee883a2aa8d 100644 --- a/drivers/net/ethernet/packetengines/hamachi.c +++ b/drivers/net/ethernet/packetengines/hamachi.c @@ -1337,7 +1337,7 @@ static irqreturn_t hamachi_interrupt(int irq, void *dev_instance) leXX_to_cpu(hmp->tx_ring[entry].addr), skb->len, PCI_DMA_TODEVICE); - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); hmp->tx_skbuff[entry] = NULL; } hmp->tx_ring[entry].status_n_length = 0; diff --git a/drivers/net/ethernet/packetengines/yellowfin.c b/drivers/net/ethernet/packetengines/yellowfin.c index 54224d1822e3..6f8d6584f809 100644 --- a/drivers/net/ethernet/packetengines/yellowfin.c +++ b/drivers/net/ethernet/packetengines/yellowfin.c @@ -925,7 +925,7 @@ static irqreturn_t yellowfin_interrupt(int irq, void *dev_instance) /* Free the original skb. */ pci_unmap_single(yp->pci_dev, le32_to_cpu(yp->tx_ring[entry].addr), skb->len, PCI_DMA_TODEVICE); - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); yp->tx_skbuff[entry] = NULL; } if (yp->tx_full && @@ -983,7 +983,7 @@ static irqreturn_t yellowfin_interrupt(int irq, void *dev_instance) pci_unmap_single(yp->pci_dev, yp->tx_ring[entry<<1].addr, skb->len, PCI_DMA_TODEVICE); - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); yp->tx_skbuff[entry] = 0; /* Mark status as empty. */ yp->tx_status[entry].tx_errs = 0; diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h index 3b0955d34716..2d21c94f19c2 100644 --- a/drivers/net/ethernet/qlogic/qed/qed.h +++ b/drivers/net/ethernet/qlogic/qed/qed.h @@ -53,7 +53,7 @@ extern const struct qed_common_ops qed_common_ops_pass; #define QED_MAJOR_VERSION 8 -#define QED_MINOR_VERSION 33 +#define QED_MINOR_VERSION 37 #define QED_REVISION_VERSION 0 #define QED_ENGINEERING_VERSION 20 diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c index 35c9f484eb9f..e61d1d905415 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c +++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c @@ -2135,12 +2135,12 @@ int qed_cxt_set_pf_params(struct qed_hwfn *p_hwfn, u32 rdma_tasks) struct qed_eth_pf_params *p_params = &p_hwfn->pf_params.eth_pf_params; - if (!p_params->num_vf_cons) - p_params->num_vf_cons = - ETH_PF_PARAMS_VF_CONS_DEFAULT; - qed_cxt_set_proto_cid_count(p_hwfn, PROTOCOLID_ETH, - p_params->num_cons, - p_params->num_vf_cons); + if (!p_params->num_vf_cons) + p_params->num_vf_cons = + ETH_PF_PARAMS_VF_CONS_DEFAULT; + qed_cxt_set_proto_cid_count(p_hwfn, PROTOCOLID_ETH, + p_params->num_cons, + p_params->num_vf_cons); p_hwfn->p_cxt_mngr->arfs_count = p_params->num_arfs_filters; break; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index b17003d9066c..e2cbd77646a2 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -795,19 +795,19 @@ static void qed_init_qm_pq(struct qed_hwfn *p_hwfn, /* get pq index according to PQ_FLAGS */ static u16 *qed_init_qm_get_idx_from_flags(struct qed_hwfn *p_hwfn, - u32 pq_flags) + unsigned long pq_flags) { struct qed_qm_info *qm_info = &p_hwfn->qm_info; /* Can't have multiple flags set here */ - if (bitmap_weight((unsigned long *)&pq_flags, + if (bitmap_weight(&pq_flags, sizeof(pq_flags) * BITS_PER_BYTE) > 1) { - DP_ERR(p_hwfn, "requested multiple pq flags 0x%x\n", pq_flags); + DP_ERR(p_hwfn, "requested multiple pq flags 0x%lx\n", pq_flags); goto err; } if (!(qed_get_pq_flags(p_hwfn) & pq_flags)) { - DP_ERR(p_hwfn, "pq flag 0x%x is not set\n", pq_flags); + DP_ERR(p_hwfn, "pq flag 0x%lx is not set\n", pq_flags); goto err; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h index 417121e74ee9..37edaa847512 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h @@ -12796,6 +12796,7 @@ struct public_drv_mb { #define FW_MB_PARAM_GET_PF_RDMA_BOTH 0x3 /* get MFW feature support response */ +#define FW_MB_PARAM_FEATURE_SUPPORT_SMARTLINQ 0x00000001 #define FW_MB_PARAM_FEATURE_SUPPORT_EEE 0x00000002 #define FW_MB_PARAM_FEATURE_SUPPORT_VLINK 0x00010000 diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 67c02ea93906..58be1c4c6668 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -609,6 +609,10 @@ qed_sp_update_accept_mode(struct qed_hwfn *p_hwfn, (!!(accept_filter & QED_ACCEPT_MCAST_MATCHED) && !!(accept_filter & QED_ACCEPT_MCAST_UNMATCHED))); + SET_FIELD(state, ETH_VPORT_TX_MODE_UCAST_ACCEPT_ALL, + (!!(accept_filter & QED_ACCEPT_UCAST_MATCHED) && + !!(accept_filter & QED_ACCEPT_UCAST_UNMATCHED))); + SET_FIELD(state, ETH_VPORT_TX_MODE_BCAST_ACCEPT_ALL, !!(accept_filter & QED_ACCEPT_BCAST)); @@ -744,6 +748,11 @@ int qed_sp_vport_update(struct qed_hwfn *p_hwfn, return rc; } + if (p_params->update_ctl_frame_check) { + p_cmn->ctl_frame_mac_check_en = p_params->mac_chk_en; + p_cmn->ctl_frame_ethtype_check_en = p_params->ethtype_chk_en; + } + /* Update mcast bins for VFs, PF doesn't use this functionality */ qed_sp_update_mcast_bin(p_hwfn, p_ramrod, p_params); @@ -2207,7 +2216,7 @@ static int qed_fill_eth_dev_info(struct qed_dev *cdev, u16 num_queues = 0; /* Since the feature controls only queue-zones, - * make sure we have the contexts [rx, tx, xdp] to + * make sure we have the contexts [rx, xdp, tcs] to * match. */ for_each_hwfn(cdev, i) { @@ -2217,7 +2226,8 @@ static int qed_fill_eth_dev_info(struct qed_dev *cdev, u16 cids; cids = hwfn->pf_params.eth_pf_params.num_cons; - num_queues += min_t(u16, l2_queues, cids / 3); + cids /= (2 + info->num_tc); + num_queues += min_t(u16, l2_queues, cids); } /* queues might theoretically be >256, but interrupts' @@ -2688,7 +2698,8 @@ static int qed_configure_filter_rx_mode(struct qed_dev *cdev, if (type == QED_FILTER_RX_MODE_TYPE_PROMISC) { accept_flags.rx_accept_filter |= QED_ACCEPT_UCAST_UNMATCHED | QED_ACCEPT_MCAST_UNMATCHED; - accept_flags.tx_accept_filter |= QED_ACCEPT_MCAST_UNMATCHED; + accept_flags.tx_accept_filter |= QED_ACCEPT_UCAST_UNMATCHED | + QED_ACCEPT_MCAST_UNMATCHED; } else if (type == QED_FILTER_RX_MODE_TYPE_MULTI_PROMISC) { accept_flags.rx_accept_filter |= QED_ACCEPT_MCAST_UNMATCHED; accept_flags.tx_accept_filter |= QED_ACCEPT_MCAST_UNMATCHED; @@ -2860,7 +2871,8 @@ static int qed_get_coalesce(struct qed_dev *cdev, u16 *coal, void *handle) p_hwfn = p_cid->p_owner; rc = qed_get_queue_coalesce(p_hwfn, coal, handle); if (rc) - DP_NOTICE(p_hwfn, "Unable to read queue coalescing\n"); + DP_VERBOSE(cdev, QED_MSG_DEBUG, + "Unable to read queue coalescing\n"); return rc; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.h b/drivers/net/ethernet/qlogic/qed/qed_l2.h index 8d80f1095d17..7127d5aaac42 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.h +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.h @@ -219,6 +219,9 @@ struct qed_sp_vport_update_params { struct qed_rss_params *rss_params; struct qed_filter_accept_flags accept_flags; struct qed_sge_tpa_params *sge_tpa_params; + u8 update_ctl_frame_check; + u8 mac_chk_en; + u8 ethtype_chk_en; }; int qed_sp_vport_update(struct qed_hwfn *p_hwfn, diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index d9237c65a838..b5f419b71287 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -2451,19 +2451,24 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb, { struct qed_ll2_tx_pkt_info pkt; const skb_frag_t *frag; + u8 flags = 0, nr_frags; int rc = -EINVAL, i; dma_addr_t mapping; u16 vlan = 0; - u8 flags = 0; if (unlikely(skb->ip_summed != CHECKSUM_NONE)) { DP_INFO(cdev, "Cannot transmit a checksummed packet\n"); return -EINVAL; } - if (1 + skb_shinfo(skb)->nr_frags > CORE_LL2_TX_MAX_BDS_PER_PACKET) { + /* Cache number of fragments from SKB since SKB may be freed by + * the completion routine after calling qed_ll2_prepare_tx_packet() + */ + nr_frags = skb_shinfo(skb)->nr_frags; + + if (1 + nr_frags > CORE_LL2_TX_MAX_BDS_PER_PACKET) { DP_ERR(cdev, "Cannot transmit a packet with %d fragments\n", - 1 + skb_shinfo(skb)->nr_frags); + 1 + nr_frags); return -EINVAL; } @@ -2485,7 +2490,7 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb, } memset(&pkt, 0, sizeof(pkt)); - pkt.num_of_bds = 1 + skb_shinfo(skb)->nr_frags; + pkt.num_of_bds = 1 + nr_frags; pkt.vlan = vlan; pkt.bd_flags = flags; pkt.tx_dest = QED_LL2_TX_DEST_NW; @@ -2496,12 +2501,17 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb, test_bit(QED_LL2_XMIT_FLAGS_FIP_DISCOVERY, &xmit_flags)) pkt.remove_stag = true; + /* qed_ll2_prepare_tx_packet() may actually send the packet if + * there are no fragments in the skb and subsequently the completion + * routine may run and free the SKB, so no dereferencing the SKB + * beyond this point unless skb has any fragments. + */ rc = qed_ll2_prepare_tx_packet(&cdev->hwfns[0], cdev->ll2->handle, &pkt, 1); if (rc) goto err; - for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + for (i = 0; i < nr_frags; i++) { frag = &skb_shinfo(skb)->frags[i]; mapping = skb_frag_dma_map(&cdev->pdev->dev, frag, 0, diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index b47352643fb5..f164d4acebcb 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -281,6 +281,8 @@ int qed_fill_dev_info(struct qed_dev *cdev, if (hw_info->b_wol_support == QED_WOL_SUPPORT_PME) dev_info->wol_support = true; + dev_info->smart_an = qed_mcp_is_smart_an_supported(p_hwfn); + dev_info->abs_pf_id = QED_LEADING_HWFN(cdev)->abs_pf_id; } else { qed_vf_get_fw_version(&cdev->hwfns[0], &dev_info->fw_major, diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index bb8541847aa5..cc27fd60d689 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -3654,6 +3654,12 @@ void qed_mcp_resc_lock_default_init(struct qed_resc_lock_params *p_lock, } } +bool qed_mcp_is_smart_an_supported(struct qed_hwfn *p_hwfn) +{ + return !!(p_hwfn->mcp_info->capabilities & + FW_MB_PARAM_FEATURE_SUPPORT_SMARTLINQ); +} + int qed_mcp_get_capabilities(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) { u32 mcp_resp; diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h index 6e1d72a669ae..2799e6741765 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h @@ -1148,6 +1148,16 @@ void qed_mcp_resc_lock_default_init(struct qed_resc_lock_params *p_lock, struct qed_resc_unlock_params *p_unlock, enum qed_resc_lock resource, bool b_is_permanent); + +/** + * @brief - Return whether management firmware support smart AN + * + * @param p_hwfn + * + * @return bool - true if feature is supported. + */ +bool qed_mcp_is_smart_an_supported(struct qed_hwfn *p_hwfn); + /** * @brief Learn of supported MFW features; To be done during early init * diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp.h b/drivers/net/ethernet/qlogic/qed/qed_sp.h index 4179c9013fc6..96ab77ae6af5 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_sp.h @@ -382,6 +382,7 @@ void qed_consq_setup(struct qed_hwfn *p_hwfn); * @param p_hwfn */ void qed_consq_free(struct qed_hwfn *p_hwfn); +int qed_spq_pend_post(struct qed_hwfn *p_hwfn); /** * @file diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c index 888274fa208b..5a495fda9e9d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c @@ -604,6 +604,9 @@ int qed_sp_pf_update_stag(struct qed_hwfn *p_hwfn) p_ent->ramrod.pf_update.update_mf_vlan_flag = true; p_ent->ramrod.pf_update.mf_vlan = cpu_to_le16(p_hwfn->hw_info.ovlan); + if (test_bit(QED_MF_UFP_SPECIFIC, &p_hwfn->cdev->mf_bits)) + p_ent->ramrod.pf_update.mf_vlan |= + cpu_to_le16(((u16)p_hwfn->ufp_info.tc << 13)); return qed_spq_post(p_hwfn, p_ent, NULL); } diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c index 3e0f7c46bb1b..79b311b86f66 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_spq.c +++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c @@ -397,6 +397,11 @@ int qed_eq_completion(struct qed_hwfn *p_hwfn, void *cookie) qed_eq_prod_update(p_hwfn, qed_chain_get_prod_idx(p_chain)); + /* Attempt to post pending requests */ + spin_lock_bh(&p_hwfn->p_spq->lock); + rc = qed_spq_pend_post(p_hwfn); + spin_unlock_bh(&p_hwfn->p_spq->lock); + return rc; } @@ -767,7 +772,7 @@ static int qed_spq_post_list(struct qed_hwfn *p_hwfn, return 0; } -static int qed_spq_pend_post(struct qed_hwfn *p_hwfn) +int qed_spq_pend_post(struct qed_hwfn *p_hwfn) { struct qed_spq *p_spq = p_hwfn->p_spq; struct qed_spq_entry *p_ent = NULL; @@ -927,7 +932,6 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn, struct qed_spq_entry *p_ent = NULL; struct qed_spq_entry *tmp; struct qed_spq_entry *found = NULL; - int rc; if (!p_hwfn) return -EINVAL; @@ -985,12 +989,7 @@ int qed_spq_completion(struct qed_hwfn *p_hwfn, */ qed_spq_return_entry(p_hwfn, found); - /* Attempt to post pending requests */ - spin_lock_bh(&p_spq->lock); - rc = qed_spq_pend_post(p_hwfn); - spin_unlock_bh(&p_spq->lock); - - return rc; + return 0; } int qed_consq_alloc(struct qed_hwfn *p_hwfn) diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c index 71e28be58102..9faaa6df78ed 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c @@ -1969,7 +1969,9 @@ static void qed_iov_vf_mbx_start_vport(struct qed_hwfn *p_hwfn, params.vport_id = vf->vport_id; params.max_buffers_per_cqe = start->max_buffers_per_cqe; params.mtu = vf->mtu; - params.check_mac = true; + + /* Non trusted VFs should enable control frame filtering */ + params.check_mac = !vf->p_vf_info.is_trusted_configured; rc = qed_sp_eth_vport_start(p_hwfn, ¶ms); if (rc) { @@ -5137,6 +5139,9 @@ static void qed_iov_handle_trust_change(struct qed_hwfn *hwfn) params.opaque_fid = vf->opaque_fid; params.vport_id = vf->vport_id; + params.update_ctl_frame_check = 1; + params.mac_chk_en = !vf_info->is_trusted_configured; + if (vf_info->rx_accept_mode & mask) { flags->update_rx_mode_config = 1; flags->rx_accept_filter = vf_info->rx_accept_mode; @@ -5154,7 +5159,8 @@ static void qed_iov_handle_trust_change(struct qed_hwfn *hwfn) } if (flags->update_rx_mode_config || - flags->update_tx_mode_config) + flags->update_tx_mode_config || + params.update_ctl_frame_check) qed_sp_vport_update(hwfn, ¶ms, QED_SPQ_MODE_EBLOCK, NULL); } diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c index b6cccf44bf40..5dda547772c1 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_vf.c +++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c @@ -261,6 +261,7 @@ static int qed_vf_pf_acquire(struct qed_hwfn *p_hwfn) struct pfvf_acquire_resp_tlv *resp = &p_iov->pf2vf_reply->acquire_resp; struct pf_vf_pfdev_info *pfdev_info = &resp->pfdev_info; struct vf_pf_resc_request *p_resc; + u8 retry_cnt = VF_ACQUIRE_THRESH; bool resources_acquired = false; struct vfpf_acquire_tlv *req; int rc = 0, attempts = 0; @@ -314,6 +315,15 @@ static int qed_vf_pf_acquire(struct qed_hwfn *p_hwfn) /* send acquire request */ rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp)); + + /* Re-try acquire in case of vf-pf hw channel timeout */ + if (retry_cnt && rc == -EBUSY) { + DP_VERBOSE(p_hwfn, QED_MSG_IOV, + "VF retrying to acquire due to VPC timeout\n"); + retry_cnt--; + continue; + } + if (rc) goto exit; diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index 843416404aeb..63a78162cfaf 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -56,7 +56,7 @@ #include <net/tc_act/tc_gact.h> #define QEDE_MAJOR_VERSION 8 -#define QEDE_MINOR_VERSION 33 +#define QEDE_MINOR_VERSION 37 #define QEDE_REVISION_VERSION 0 #define QEDE_ENGINEERING_VERSION 20 #define DRV_MODULE_VERSION __stringify(QEDE_MAJOR_VERSION) "." \ @@ -497,6 +497,9 @@ struct qede_reload_args { /* Datapath functions definition */ netdev_tx_t qede_start_xmit(struct sk_buff *skb, struct net_device *ndev); +u16 qede_select_queue(struct net_device *dev, struct sk_buff *skb, + struct net_device *sb_dev, + select_queue_fallback_t fallback); netdev_features_t qede_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features); diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c index 16331c6c6fa7..c6238083e898 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c @@ -186,11 +186,13 @@ static const struct { enum { QEDE_PRI_FLAG_CMT, + QEDE_PRI_FLAG_SMART_AN_SUPPORT, /* MFW supports SmartAN */ QEDE_PRI_FLAG_LEN, }; static const char qede_private_arr[QEDE_PRI_FLAG_LEN][ETH_GSTRING_LEN] = { "Coupled-Function", + "SmartAN capable", }; enum qede_ethtool_tests { @@ -404,8 +406,15 @@ static int qede_get_sset_count(struct net_device *dev, int stringset) static u32 qede_get_priv_flags(struct net_device *dev) { struct qede_dev *edev = netdev_priv(dev); + u32 flags = 0; - return (!!(edev->dev_info.common.num_hwfns > 1)) << QEDE_PRI_FLAG_CMT; + if (edev->dev_info.common.num_hwfns > 1) + flags |= BIT(QEDE_PRI_FLAG_CMT); + + if (edev->dev_info.common.smart_an) + flags |= BIT(QEDE_PRI_FLAG_SMART_AN_SUPPORT); + + return flags; } struct qede_link_mode_mapping { diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c index b16ce7d93caf..add922b93d2c 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_filter.c +++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c @@ -1665,198 +1665,6 @@ static int qede_set_v6_tuple_to_profile(struct qede_dev *edev, return 0; } -static int qede_flow_spec_to_tuple_ipv4_common(struct qede_dev *edev, - struct qede_arfs_tuple *t, - struct ethtool_rx_flow_spec *fs) -{ - if ((fs->h_u.tcp_ip4_spec.ip4src & - fs->m_u.tcp_ip4_spec.ip4src) != fs->h_u.tcp_ip4_spec.ip4src) { - DP_INFO(edev, "Don't support IP-masks\n"); - return -EOPNOTSUPP; - } - - if ((fs->h_u.tcp_ip4_spec.ip4dst & - fs->m_u.tcp_ip4_spec.ip4dst) != fs->h_u.tcp_ip4_spec.ip4dst) { - DP_INFO(edev, "Don't support IP-masks\n"); - return -EOPNOTSUPP; - } - - if ((fs->h_u.tcp_ip4_spec.psrc & - fs->m_u.tcp_ip4_spec.psrc) != fs->h_u.tcp_ip4_spec.psrc) { - DP_INFO(edev, "Don't support port-masks\n"); - return -EOPNOTSUPP; - } - - if ((fs->h_u.tcp_ip4_spec.pdst & - fs->m_u.tcp_ip4_spec.pdst) != fs->h_u.tcp_ip4_spec.pdst) { - DP_INFO(edev, "Don't support port-masks\n"); - return -EOPNOTSUPP; - } - - if (fs->h_u.tcp_ip4_spec.tos) { - DP_INFO(edev, "Don't support tos\n"); - return -EOPNOTSUPP; - } - - t->eth_proto = htons(ETH_P_IP); - t->src_ipv4 = fs->h_u.tcp_ip4_spec.ip4src; - t->dst_ipv4 = fs->h_u.tcp_ip4_spec.ip4dst; - t->src_port = fs->h_u.tcp_ip4_spec.psrc; - t->dst_port = fs->h_u.tcp_ip4_spec.pdst; - - return qede_set_v4_tuple_to_profile(edev, t); -} - -static int qede_flow_spec_to_tuple_tcpv4(struct qede_dev *edev, - struct qede_arfs_tuple *t, - struct ethtool_rx_flow_spec *fs) -{ - t->ip_proto = IPPROTO_TCP; - - if (qede_flow_spec_to_tuple_ipv4_common(edev, t, fs)) - return -EINVAL; - - return 0; -} - -static int qede_flow_spec_to_tuple_udpv4(struct qede_dev *edev, - struct qede_arfs_tuple *t, - struct ethtool_rx_flow_spec *fs) -{ - t->ip_proto = IPPROTO_UDP; - - if (qede_flow_spec_to_tuple_ipv4_common(edev, t, fs)) - return -EINVAL; - - return 0; -} - -static int qede_flow_spec_to_tuple_ipv6_common(struct qede_dev *edev, - struct qede_arfs_tuple *t, - struct ethtool_rx_flow_spec *fs) -{ - struct in6_addr zero_addr; - - memset(&zero_addr, 0, sizeof(zero_addr)); - - if ((fs->h_u.tcp_ip6_spec.psrc & - fs->m_u.tcp_ip6_spec.psrc) != fs->h_u.tcp_ip6_spec.psrc) { - DP_INFO(edev, "Don't support port-masks\n"); - return -EOPNOTSUPP; - } - - if ((fs->h_u.tcp_ip6_spec.pdst & - fs->m_u.tcp_ip6_spec.pdst) != fs->h_u.tcp_ip6_spec.pdst) { - DP_INFO(edev, "Don't support port-masks\n"); - return -EOPNOTSUPP; - } - - if (fs->h_u.tcp_ip6_spec.tclass) { - DP_INFO(edev, "Don't support tclass\n"); - return -EOPNOTSUPP; - } - - t->eth_proto = htons(ETH_P_IPV6); - memcpy(&t->src_ipv6, &fs->h_u.tcp_ip6_spec.ip6src, - sizeof(struct in6_addr)); - memcpy(&t->dst_ipv6, &fs->h_u.tcp_ip6_spec.ip6dst, - sizeof(struct in6_addr)); - t->src_port = fs->h_u.tcp_ip6_spec.psrc; - t->dst_port = fs->h_u.tcp_ip6_spec.pdst; - - return qede_set_v6_tuple_to_profile(edev, t, &zero_addr); -} - -static int qede_flow_spec_to_tuple_tcpv6(struct qede_dev *edev, - struct qede_arfs_tuple *t, - struct ethtool_rx_flow_spec *fs) -{ - t->ip_proto = IPPROTO_TCP; - - if (qede_flow_spec_to_tuple_ipv6_common(edev, t, fs)) - return -EINVAL; - - return 0; -} - -static int qede_flow_spec_to_tuple_udpv6(struct qede_dev *edev, - struct qede_arfs_tuple *t, - struct ethtool_rx_flow_spec *fs) -{ - t->ip_proto = IPPROTO_UDP; - - if (qede_flow_spec_to_tuple_ipv6_common(edev, t, fs)) - return -EINVAL; - - return 0; -} - -static int qede_flow_spec_to_tuple(struct qede_dev *edev, - struct qede_arfs_tuple *t, - struct ethtool_rx_flow_spec *fs) -{ - memset(t, 0, sizeof(*t)); - - if (qede_flow_spec_validate_unused(edev, fs)) - return -EOPNOTSUPP; - - switch ((fs->flow_type & ~FLOW_EXT)) { - case TCP_V4_FLOW: - return qede_flow_spec_to_tuple_tcpv4(edev, t, fs); - case UDP_V4_FLOW: - return qede_flow_spec_to_tuple_udpv4(edev, t, fs); - case TCP_V6_FLOW: - return qede_flow_spec_to_tuple_tcpv6(edev, t, fs); - case UDP_V6_FLOW: - return qede_flow_spec_to_tuple_udpv6(edev, t, fs); - default: - DP_VERBOSE(edev, NETIF_MSG_IFUP, - "Can't support flow of type %08x\n", fs->flow_type); - return -EOPNOTSUPP; - } - - return 0; -} - -static int qede_flow_spec_validate(struct qede_dev *edev, - struct ethtool_rx_flow_spec *fs, - struct qede_arfs_tuple *t) -{ - if (fs->location >= QEDE_RFS_MAX_FLTR) { - DP_INFO(edev, "Location out-of-bounds\n"); - return -EINVAL; - } - - /* Check location isn't already in use */ - if (test_bit(fs->location, edev->arfs->arfs_fltr_bmap)) { - DP_INFO(edev, "Location already in use\n"); - return -EINVAL; - } - - /* Check if the filtering-mode could support the filter */ - if (edev->arfs->filter_count && - edev->arfs->mode != t->mode) { - DP_INFO(edev, - "flow_spec would require filtering mode %08x, but %08x is configured\n", - t->mode, edev->arfs->filter_count); - return -EINVAL; - } - - /* If drop requested then no need to validate other data */ - if (fs->ring_cookie == RX_CLS_FLOW_DISC) - return 0; - - if (ethtool_get_flow_spec_ring_vf(fs->ring_cookie)) - return 0; - - if (fs->ring_cookie >= QEDE_RSS_COUNT(edev)) { - DP_INFO(edev, "Queue out-of-bounds\n"); - return -EINVAL; - } - - return 0; -} - /* Must be called while qede lock is held */ static struct qede_arfs_fltr_node * qede_flow_find_fltr(struct qede_dev *edev, struct qede_arfs_tuple *t) @@ -1896,72 +1704,6 @@ static void qede_flow_set_destination(struct qede_dev *edev, "Configuring N-tuple for VF 0x%02x\n", n->vfid - 1); } -int qede_add_cls_rule(struct qede_dev *edev, struct ethtool_rxnfc *info) -{ - struct ethtool_rx_flow_spec *fsp = &info->fs; - struct qede_arfs_fltr_node *n; - struct qede_arfs_tuple t; - int min_hlen, rc; - - __qede_lock(edev); - - if (!edev->arfs) { - rc = -EPERM; - goto unlock; - } - - /* Translate the flow specification into something fittign our DB */ - rc = qede_flow_spec_to_tuple(edev, &t, fsp); - if (rc) - goto unlock; - - /* Make sure location is valid and filter isn't already set */ - rc = qede_flow_spec_validate(edev, fsp, &t); - if (rc) - goto unlock; - - if (qede_flow_find_fltr(edev, &t)) { - rc = -EINVAL; - goto unlock; - } - - n = kzalloc(sizeof(*n), GFP_KERNEL); - if (!n) { - rc = -ENOMEM; - goto unlock; - } - - min_hlen = qede_flow_get_min_header_size(&t); - n->data = kzalloc(min_hlen, GFP_KERNEL); - if (!n->data) { - kfree(n); - rc = -ENOMEM; - goto unlock; - } - - n->sw_id = fsp->location; - set_bit(n->sw_id, edev->arfs->arfs_fltr_bmap); - n->buf_len = min_hlen; - - memcpy(&n->tuple, &t, sizeof(n->tuple)); - - qede_flow_set_destination(edev, n, fsp); - - /* Build a minimal header according to the flow */ - n->tuple.build_hdr(&n->tuple, n->data); - - rc = qede_enqueue_fltr_and_config_searcher(edev, n, 0); - if (rc) - goto unlock; - - qede_configure_arfs_fltr(edev, n, n->rxq_id, true); - rc = qede_poll_arfs_filter_config(edev, n); -unlock: - __qede_unlock(edev); - - return rc; -} - int qede_delete_flow_filter(struct qede_dev *edev, u64 cookie) { struct qede_arfs_fltr_node *fltr = NULL; @@ -2004,190 +1746,172 @@ unlock: } static int qede_parse_actions(struct qede_dev *edev, - struct tcf_exts *exts) + struct flow_action *flow_action) { - int rc = -EINVAL, num_act = 0, i; - const struct tc_action *a; - bool is_drop = false; + const struct flow_action_entry *act; + int i; - if (!tcf_exts_has_actions(exts)) { - DP_NOTICE(edev, "No tc actions received\n"); - return rc; + if (!flow_action_has_entries(flow_action)) { + DP_NOTICE(edev, "No actions received\n"); + return -EINVAL; } - tcf_exts_for_each_action(i, a, exts) { - num_act++; + flow_action_for_each(i, act, flow_action) { + switch (act->id) { + case FLOW_ACTION_DROP: + break; + case FLOW_ACTION_QUEUE: + if (act->queue.vf) + break; - if (is_tcf_gact_shot(a)) - is_drop = true; + if (act->queue.index >= QEDE_RSS_COUNT(edev)) { + DP_INFO(edev, "Queue out-of-bounds\n"); + return -EINVAL; + } + break; + default: + return -EINVAL; + } } - if (num_act == 1 && is_drop) - return 0; - - return rc; + return 0; } static int -qede_tc_parse_ports(struct qede_dev *edev, - struct tc_cls_flower_offload *f, - struct qede_arfs_tuple *t) -{ - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) { - struct flow_dissector_key_ports *key, *mask; - - key = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_PORTS, - f->key); - mask = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_PORTS, - f->mask); - - if ((key->src && mask->src != U16_MAX) || - (key->dst && mask->dst != U16_MAX)) { +qede_flow_parse_ports(struct qede_dev *edev, struct flow_rule *rule, + struct qede_arfs_tuple *t) +{ + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) { + struct flow_match_ports match; + + flow_rule_match_ports(rule, &match); + if ((match.key->src && match.mask->src != U16_MAX) || + (match.key->dst && match.mask->dst != U16_MAX)) { DP_NOTICE(edev, "Do not support ports masks\n"); return -EINVAL; } - t->src_port = key->src; - t->dst_port = key->dst; + t->src_port = match.key->src; + t->dst_port = match.key->dst; } return 0; } static int -qede_tc_parse_v6_common(struct qede_dev *edev, - struct tc_cls_flower_offload *f, - struct qede_arfs_tuple *t) +qede_flow_parse_v6_common(struct qede_dev *edev, struct flow_rule *rule, + struct qede_arfs_tuple *t) { struct in6_addr zero_addr, addr; memset(&zero_addr, 0, sizeof(addr)); memset(&addr, 0xff, sizeof(addr)); - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { - struct flow_dissector_key_ipv6_addrs *key, *mask; - - key = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS, - f->key); - mask = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { + struct flow_match_ipv6_addrs match; - if ((memcmp(&key->src, &zero_addr, sizeof(addr)) && - memcmp(&mask->src, &addr, sizeof(addr))) || - (memcmp(&key->dst, &zero_addr, sizeof(addr)) && - memcmp(&mask->dst, &addr, sizeof(addr)))) { + flow_rule_match_ipv6_addrs(rule, &match); + if ((memcmp(&match.key->src, &zero_addr, sizeof(addr)) && + memcmp(&match.mask->src, &addr, sizeof(addr))) || + (memcmp(&match.key->dst, &zero_addr, sizeof(addr)) && + memcmp(&match.mask->dst, &addr, sizeof(addr)))) { DP_NOTICE(edev, "Do not support IPv6 address prefix/mask\n"); return -EINVAL; } - memcpy(&t->src_ipv6, &key->src, sizeof(addr)); - memcpy(&t->dst_ipv6, &key->dst, sizeof(addr)); + memcpy(&t->src_ipv6, &match.key->src, sizeof(addr)); + memcpy(&t->dst_ipv6, &match.key->dst, sizeof(addr)); } - if (qede_tc_parse_ports(edev, f, t)) + if (qede_flow_parse_ports(edev, rule, t)) return -EINVAL; return qede_set_v6_tuple_to_profile(edev, t, &zero_addr); } static int -qede_tc_parse_v4_common(struct qede_dev *edev, - struct tc_cls_flower_offload *f, +qede_flow_parse_v4_common(struct qede_dev *edev, struct flow_rule *rule, struct qede_arfs_tuple *t) { - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) { - struct flow_dissector_key_ipv4_addrs *key, *mask; - - key = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS, - f->key); - mask = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) { + struct flow_match_ipv4_addrs match; - if ((key->src && mask->src != U32_MAX) || - (key->dst && mask->dst != U32_MAX)) { + flow_rule_match_ipv4_addrs(rule, &match); + if ((match.key->src && match.mask->src != U32_MAX) || + (match.key->dst && match.mask->dst != U32_MAX)) { DP_NOTICE(edev, "Do not support ipv4 prefix/masks\n"); return -EINVAL; } - t->src_ipv4 = key->src; - t->dst_ipv4 = key->dst; + t->src_ipv4 = match.key->src; + t->dst_ipv4 = match.key->dst; } - if (qede_tc_parse_ports(edev, f, t)) + if (qede_flow_parse_ports(edev, rule, t)) return -EINVAL; return qede_set_v4_tuple_to_profile(edev, t); } static int -qede_tc_parse_tcp_v6(struct qede_dev *edev, - struct tc_cls_flower_offload *f, +qede_flow_parse_tcp_v6(struct qede_dev *edev, struct flow_rule *rule, struct qede_arfs_tuple *tuple) { tuple->ip_proto = IPPROTO_TCP; tuple->eth_proto = htons(ETH_P_IPV6); - return qede_tc_parse_v6_common(edev, f, tuple); + return qede_flow_parse_v6_common(edev, rule, tuple); } static int -qede_tc_parse_tcp_v4(struct qede_dev *edev, - struct tc_cls_flower_offload *f, +qede_flow_parse_tcp_v4(struct qede_dev *edev, struct flow_rule *rule, struct qede_arfs_tuple *tuple) { tuple->ip_proto = IPPROTO_TCP; tuple->eth_proto = htons(ETH_P_IP); - return qede_tc_parse_v4_common(edev, f, tuple); + return qede_flow_parse_v4_common(edev, rule, tuple); } static int -qede_tc_parse_udp_v6(struct qede_dev *edev, - struct tc_cls_flower_offload *f, +qede_flow_parse_udp_v6(struct qede_dev *edev, struct flow_rule *rule, struct qede_arfs_tuple *tuple) { tuple->ip_proto = IPPROTO_UDP; tuple->eth_proto = htons(ETH_P_IPV6); - return qede_tc_parse_v6_common(edev, f, tuple); + return qede_flow_parse_v6_common(edev, rule, tuple); } static int -qede_tc_parse_udp_v4(struct qede_dev *edev, - struct tc_cls_flower_offload *f, +qede_flow_parse_udp_v4(struct qede_dev *edev, struct flow_rule *rule, struct qede_arfs_tuple *tuple) { tuple->ip_proto = IPPROTO_UDP; tuple->eth_proto = htons(ETH_P_IP); - return qede_tc_parse_v4_common(edev, f, tuple); + return qede_flow_parse_v4_common(edev, rule, tuple); } static int -qede_parse_flower_attr(struct qede_dev *edev, __be16 proto, - struct tc_cls_flower_offload *f, - struct qede_arfs_tuple *tuple) +qede_parse_flow_attr(struct qede_dev *edev, __be16 proto, + struct flow_rule *rule, struct qede_arfs_tuple *tuple) { + struct flow_dissector *dissector = rule->match.dissector; int rc = -EINVAL; u8 ip_proto = 0; memset(tuple, 0, sizeof(*tuple)); - if (f->dissector->used_keys & + if (dissector->used_keys & ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | BIT(FLOW_DISSECTOR_KEY_BASIC) | BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | BIT(FLOW_DISSECTOR_KEY_PORTS))) { DP_NOTICE(edev, "Unsupported key set:0x%x\n", - f->dissector->used_keys); + dissector->used_keys); return -EOPNOTSUPP; } @@ -2197,25 +1921,23 @@ qede_parse_flower_attr(struct qede_dev *edev, __be16 proto, return -EPROTONOSUPPORT; } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) { - struct flow_dissector_key_basic *key; + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_match_basic match; - key = skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_BASIC, - f->key); - ip_proto = key->ip_proto; + flow_rule_match_basic(rule, &match); + ip_proto = match.key->ip_proto; } if (ip_proto == IPPROTO_TCP && proto == htons(ETH_P_IP)) - rc = qede_tc_parse_tcp_v4(edev, f, tuple); + rc = qede_flow_parse_tcp_v4(edev, rule, tuple); else if (ip_proto == IPPROTO_TCP && proto == htons(ETH_P_IPV6)) - rc = qede_tc_parse_tcp_v6(edev, f, tuple); + rc = qede_flow_parse_tcp_v6(edev, rule, tuple); else if (ip_proto == IPPROTO_UDP && proto == htons(ETH_P_IP)) - rc = qede_tc_parse_udp_v4(edev, f, tuple); + rc = qede_flow_parse_udp_v4(edev, rule, tuple); else if (ip_proto == IPPROTO_UDP && proto == htons(ETH_P_IPV6)) - rc = qede_tc_parse_udp_v6(edev, f, tuple); + rc = qede_flow_parse_udp_v6(edev, rule, tuple); else - DP_NOTICE(edev, "Invalid tc protocol request\n"); + DP_NOTICE(edev, "Invalid protocol request\n"); return rc; } @@ -2235,7 +1957,7 @@ int qede_add_tc_flower_fltr(struct qede_dev *edev, __be16 proto, } /* parse flower attribute and prepare filter */ - if (qede_parse_flower_attr(edev, proto, f, &t)) + if (qede_parse_flow_attr(edev, proto, f->rule, &t)) goto unlock; /* Validate profile mode and number of filters */ @@ -2248,7 +1970,7 @@ int qede_add_tc_flower_fltr(struct qede_dev *edev, __be16 proto, } /* parse tc actions and get the vf_id */ - if (qede_parse_actions(edev, f->exts)) + if (qede_parse_actions(edev, &f->rule->action)) goto unlock; if (qede_flow_find_fltr(edev, &t)) { @@ -2290,3 +2012,141 @@ unlock: __qede_unlock(edev); return rc; } + +static int qede_flow_spec_validate(struct qede_dev *edev, + struct flow_action *flow_action, + struct qede_arfs_tuple *t, + __u32 location) +{ + if (location >= QEDE_RFS_MAX_FLTR) { + DP_INFO(edev, "Location out-of-bounds\n"); + return -EINVAL; + } + + /* Check location isn't already in use */ + if (test_bit(location, edev->arfs->arfs_fltr_bmap)) { + DP_INFO(edev, "Location already in use\n"); + return -EINVAL; + } + + /* Check if the filtering-mode could support the filter */ + if (edev->arfs->filter_count && + edev->arfs->mode != t->mode) { + DP_INFO(edev, + "flow_spec would require filtering mode %08x, but %08x is configured\n", + t->mode, edev->arfs->filter_count); + return -EINVAL; + } + + if (qede_parse_actions(edev, flow_action)) + return -EINVAL; + + return 0; +} + +static int qede_flow_spec_to_rule(struct qede_dev *edev, + struct qede_arfs_tuple *t, + struct ethtool_rx_flow_spec *fs) +{ + struct ethtool_rx_flow_spec_input input = {}; + struct ethtool_rx_flow_rule *flow; + __be16 proto; + int err = 0; + + if (qede_flow_spec_validate_unused(edev, fs)) + return -EOPNOTSUPP; + + switch ((fs->flow_type & ~FLOW_EXT)) { + case TCP_V4_FLOW: + case UDP_V4_FLOW: + proto = htons(ETH_P_IP); + break; + case TCP_V6_FLOW: + case UDP_V6_FLOW: + proto = htons(ETH_P_IPV6); + break; + default: + DP_VERBOSE(edev, NETIF_MSG_IFUP, + "Can't support flow of type %08x\n", fs->flow_type); + return -EOPNOTSUPP; + } + + input.fs = fs; + flow = ethtool_rx_flow_rule_create(&input); + if (IS_ERR(flow)) + return PTR_ERR(flow); + + if (qede_parse_flow_attr(edev, proto, flow->rule, t)) { + err = -EINVAL; + goto err_out; + } + + /* Make sure location is valid and filter isn't already set */ + err = qede_flow_spec_validate(edev, &flow->rule->action, t, + fs->location); +err_out: + ethtool_rx_flow_rule_destroy(flow); + return err; + +} + +int qede_add_cls_rule(struct qede_dev *edev, struct ethtool_rxnfc *info) +{ + struct ethtool_rx_flow_spec *fsp = &info->fs; + struct qede_arfs_fltr_node *n; + struct qede_arfs_tuple t; + int min_hlen, rc; + + __qede_lock(edev); + + if (!edev->arfs) { + rc = -EPERM; + goto unlock; + } + + /* Translate the flow specification into something fittign our DB */ + rc = qede_flow_spec_to_rule(edev, &t, fsp); + if (rc) + goto unlock; + + if (qede_flow_find_fltr(edev, &t)) { + rc = -EINVAL; + goto unlock; + } + + n = kzalloc(sizeof(*n), GFP_KERNEL); + if (!n) { + rc = -ENOMEM; + goto unlock; + } + + min_hlen = qede_flow_get_min_header_size(&t); + n->data = kzalloc(min_hlen, GFP_KERNEL); + if (!n->data) { + kfree(n); + rc = -ENOMEM; + goto unlock; + } + + n->sw_id = fsp->location; + set_bit(n->sw_id, edev->arfs->arfs_fltr_bmap); + n->buf_len = min_hlen; + + memcpy(&n->tuple, &t, sizeof(n->tuple)); + + qede_flow_set_destination(edev, n, fsp); + + /* Build a minimal header according to the flow */ + n->tuple.build_hdr(&n->tuple, n->data); + + rc = qede_enqueue_fltr_and_config_searcher(edev, n, 0); + if (rc) + goto unlock; + + qede_configure_arfs_fltr(edev, n, n->rxq_id, true); + rc = qede_poll_arfs_filter_config(edev, n); +unlock: + __qede_unlock(edev); + + return rc; +} diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c index bdf816fe5a16..31b046e24565 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_fp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c @@ -1695,6 +1695,19 @@ netdev_tx_t qede_start_xmit(struct sk_buff *skb, struct net_device *ndev) return NETDEV_TX_OK; } +u16 qede_select_queue(struct net_device *dev, struct sk_buff *skb, + struct net_device *sb_dev, + select_queue_fallback_t fallback) +{ + struct qede_dev *edev = netdev_priv(dev); + int total_txq; + + total_txq = QEDE_TSS_COUNT(edev) * edev->dev_info.num_tc; + + return QEDE_TSS_COUNT(edev) ? + fallback(dev, skb, NULL) % total_txq : 0; +} + /* 8B udp header + 8B base tunnel header + 32B option length */ #define QEDE_MAX_TUN_HDR_LEN 48 diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 6b4d96635238..02a97c659e29 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -621,6 +621,7 @@ static const struct net_device_ops qede_netdev_ops = { .ndo_open = qede_open, .ndo_stop = qede_close, .ndo_start_xmit = qede_start_xmit, + .ndo_select_queue = qede_select_queue, .ndo_set_rx_mode = qede_set_rx_mode, .ndo_set_mac_address = qede_set_mac_addr, .ndo_validate_addr = eth_validate_addr, @@ -656,6 +657,7 @@ static const struct net_device_ops qede_netdev_vf_ops = { .ndo_open = qede_open, .ndo_stop = qede_close, .ndo_start_xmit = qede_start_xmit, + .ndo_select_queue = qede_select_queue, .ndo_set_rx_mode = qede_set_rx_mode, .ndo_set_mac_address = qede_set_mac_addr, .ndo_validate_addr = eth_validate_addr, @@ -674,6 +676,7 @@ static const struct net_device_ops qede_netdev_vf_xdp_ops = { .ndo_open = qede_open, .ndo_stop = qede_close, .ndo_start_xmit = qede_start_xmit, + .ndo_select_queue = qede_select_queue, .ndo_set_rx_mode = qede_set_rx_mode, .ndo_set_mac_address = qede_set_mac_addr, .ndo_validate_addr = eth_validate_addr, diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c b/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c index 5edbd532127d..a6886cc5654c 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c +++ b/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c @@ -249,8 +249,8 @@ static void ql_update_stats(struct ql_adapter *qdev) spin_lock(&qdev->stats_lock); if (ql_sem_spinlock(qdev, qdev->xg_sem_mask)) { - netif_err(qdev, drv, qdev->ndev, - "Couldn't get xgmac sem.\n"); + netif_err(qdev, drv, qdev->ndev, + "Couldn't get xgmac sem.\n"); goto quit; } /* diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c index 059ba9429e51..096515c27263 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c +++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c @@ -1159,10 +1159,10 @@ static void ql_update_lbq(struct ql_adapter *qdev, struct rx_ring *rx_ring) map = lbq_desc->p.pg_chunk.map + lbq_desc->p.pg_chunk.offset; - dma_unmap_addr_set(lbq_desc, mapaddr, map); + dma_unmap_addr_set(lbq_desc, mapaddr, map); dma_unmap_len_set(lbq_desc, maplen, rx_ring->lbq_buf_size); - *lbq_desc->addr = cpu_to_le64(map); + *lbq_desc->addr = cpu_to_le64(map); pci_dma_sync_single_for_device(qdev->pdev, map, rx_ring->lbq_buf_size, diff --git a/drivers/net/ethernet/qualcomm/emac/emac-mac.c b/drivers/net/ethernet/qualcomm/emac/emac-mac.c index 8d790313ee3d..20d2400ad300 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac-mac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac-mac.c @@ -1204,7 +1204,7 @@ void emac_mac_tx_process(struct emac_adapter *adpt, struct emac_tx_queue *tx_q) if (tpbuf->skb) { pkts_compl++; bytes_compl += tpbuf->skb->len; - dev_kfree_skb_irq(tpbuf->skb); + dev_consume_skb_irq(tpbuf->skb); tpbuf->skb = NULL; } diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c index 44f6e4873aad..4f910c4f67b0 100644 --- a/drivers/net/ethernet/realtek/8139cp.c +++ b/drivers/net/ethernet/realtek/8139cp.c @@ -691,7 +691,7 @@ static void cp_tx (struct cp_private *cp) } bytes_compl += skb->len; pkts_compl++; - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); } cp->tx_skb[tx_tail] = NULL; diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 3e650bd9e94b..10bab1f7150a 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -1288,11 +1288,13 @@ static u8 rtl8168d_efuse_read(struct rtl8169_private *tp, int reg_addr) static void rtl_ack_events(struct rtl8169_private *tp, u16 bits) { RTL_W16(tp, IntrStatus, bits); + mmiowb(); } static void rtl_irq_disable(struct rtl8169_private *tp) { RTL_W16(tp, IntrMask, 0); + mmiowb(); } #define RTL_EVENT_NAPI_RX (RxOK | RxErr) @@ -1371,41 +1373,6 @@ static void rtl_link_chg_patch(struct rtl8169_private *tp) #define WAKE_ANY (WAKE_PHY | WAKE_MAGIC | WAKE_UCAST | WAKE_BCAST | WAKE_MCAST) -static u32 __rtl8169_get_wol(struct rtl8169_private *tp) -{ - u8 options; - u32 wolopts = 0; - - options = RTL_R8(tp, Config1); - if (!(options & PMEnable)) - return 0; - - options = RTL_R8(tp, Config3); - if (options & LinkUp) - wolopts |= WAKE_PHY; - switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_34 ... RTL_GIGA_MAC_VER_38: - case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51: - if (rtl_eri_read(tp, 0xdc, ERIAR_EXGMAC) & MagicPacket_v2) - wolopts |= WAKE_MAGIC; - break; - default: - if (options & MagicPacket) - wolopts |= WAKE_MAGIC; - break; - } - - options = RTL_R8(tp, Config5); - if (options & UWF) - wolopts |= WAKE_UCAST; - if (options & BWF) - wolopts |= WAKE_BCAST; - if (options & MWF) - wolopts |= WAKE_MCAST; - - return wolopts; -} - static void rtl8169_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) { struct rtl8169_private *tp = netdev_priv(dev); @@ -4282,17 +4249,6 @@ static void rtl_wol_suspend_quirk(struct rtl8169_private *tp) } } -static bool rtl_wol_pll_power_down(struct rtl8169_private *tp) -{ - if (!__rtl8169_get_wol(tp)) - return false; - - phy_speed_down(tp->phydev, false); - rtl_wol_suspend_quirk(tp); - - return true; -} - static void r8168_pll_power_down(struct rtl8169_private *tp) { if (r8168_check_dash(tp)) @@ -4302,8 +4258,11 @@ static void r8168_pll_power_down(struct rtl8169_private *tp) tp->mac_version == RTL_GIGA_MAC_VER_33) rtl_ephy_write(tp, 0x19, 0xff64); - if (rtl_wol_pll_power_down(tp)) + if (device_may_wakeup(tp_to_dev(tp))) { + phy_speed_down(tp->phydev, false); + rtl_wol_suspend_quirk(tp); return; + } switch (tp->mac_version) { case RTL_GIGA_MAC_VER_25 ... RTL_GIGA_MAC_VER_33: @@ -6235,7 +6194,6 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, struct device *d = tp_to_dev(tp); dma_addr_t mapping; u32 opts[2], len; - bool stop_queue; int frags; if (unlikely(!rtl_tx_slots_avail(tp, skb_shinfo(skb)->nr_frags))) { @@ -6277,6 +6235,8 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, txd->opts2 = cpu_to_le32(opts[1]); + netdev_sent_queue(dev, skb->len); + skb_tx_timestamp(skb); /* Force memory writes to complete before releasing descriptor */ @@ -6289,14 +6249,16 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, tp->cur_tx += frags + 1; - stop_queue = !rtl_tx_slots_avail(tp, MAX_SKB_FRAGS); - if (unlikely(stop_queue)) - netif_stop_queue(dev); + RTL_W8(tp, TxPoll, NPQ); - if (__netdev_sent_queue(dev, skb->len, skb->xmit_more)) - RTL_W8(tp, TxPoll, NPQ); + mmiowb(); - if (unlikely(stop_queue)) { + if (!rtl_tx_slots_avail(tp, MAX_SKB_FRAGS)) { + /* Avoid wrongly optimistic queue wake-up: rtl_tx thread must + * not miss a ring update when it notices a stopped queue. + */ + smp_wmb(); + netif_stop_queue(dev); /* Sync with rtl_tx: * - publish queue status and cur_tx ring index (write barrier) * - refresh dirty_tx ring index (read barrier). @@ -6635,7 +6597,9 @@ static int rtl8169_poll(struct napi_struct *napi, int budget) if (work_done < budget) { napi_complete_done(napi, work_done); + rtl_irq_enable(tp); + mmiowb(); } return work_done; @@ -7153,6 +7117,30 @@ static int rtl_alloc_irq(struct rtl8169_private *tp) return pci_alloc_irq_vectors(tp->pci_dev, 1, 1, flags); } +static void rtl_read_mac_address(struct rtl8169_private *tp, + u8 mac_addr[ETH_ALEN]) +{ + u32 value; + + /* Get MAC address */ + switch (tp->mac_version) { + case RTL_GIGA_MAC_VER_35 ... RTL_GIGA_MAC_VER_38: + case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51: + value = rtl_eri_read(tp, 0xe0, ERIAR_EXGMAC); + mac_addr[0] = (value >> 0) & 0xff; + mac_addr[1] = (value >> 8) & 0xff; + mac_addr[2] = (value >> 16) & 0xff; + mac_addr[3] = (value >> 24) & 0xff; + + value = rtl_eri_read(tp, 0xe4, ERIAR_EXGMAC); + mac_addr[4] = (value >> 0) & 0xff; + mac_addr[5] = (value >> 8) & 0xff; + break; + default: + break; + } +} + DECLARE_RTL_COND(rtl_link_list_ready_cond) { return RTL_R8(tp, MCU) & LINK_LIST_RDY; @@ -7344,6 +7332,8 @@ static int rtl_get_ether_clk(struct rtl8169_private *tp) static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) { const struct rtl_cfg_info *cfg = rtl_cfg_infos + ent->driver_data; + /* align to u16 for is_valid_ether_addr() */ + u8 mac_addr[ETH_ALEN] __aligned(2) = {}; struct rtl8169_private *tp; struct net_device *dev; int chipset, region, i; @@ -7441,27 +7431,19 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) return rc; } - tp->saved_wolopts = __rtl8169_get_wol(tp); - mutex_init(&tp->wk.mutex); INIT_WORK(&tp->wk.work, rtl_task); u64_stats_init(&tp->rx_stats.syncp); u64_stats_init(&tp->tx_stats.syncp); - /* Get MAC address */ - switch (tp->mac_version) { - u8 mac_addr[ETH_ALEN] __aligned(4); - case RTL_GIGA_MAC_VER_35 ... RTL_GIGA_MAC_VER_38: - case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51: - *(u32 *)&mac_addr[0] = rtl_eri_read(tp, 0xe0, ERIAR_EXGMAC); - *(u16 *)&mac_addr[4] = rtl_eri_read(tp, 0xe4, ERIAR_EXGMAC); + /* get MAC address */ + rc = eth_platform_get_mac_address(&pdev->dev, mac_addr); + if (rc) + rtl_read_mac_address(tp, mac_addr); + + if (is_valid_ether_addr(mac_addr)) + rtl_rar_set(tp, mac_addr); - if (is_valid_ether_addr(mac_addr)) - rtl_rar_set(tp, mac_addr); - break; - default: - break; - } for (i = 0; i < ETH_ALEN; i++) dev->dev_addr[i] = RTL_R8(tp, MAC0 + i); diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index f27a0dc8c563..339b2eae2100 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -555,7 +555,7 @@ static int sh_eth_soft_reset_gether(struct net_device *ndev) sh_eth_write(ndev, 0, RDFFR); /* Reset HW CRC register */ - if (mdp->cd->hw_checksum) + if (mdp->cd->csmr) sh_eth_write(ndev, 0, CSMR); /* Select MII mode */ @@ -619,7 +619,8 @@ static struct sh_eth_cpu_data r7s72100_data = { .no_trimd = 1, .no_ade = 1, .xdfar_rw = 1, - .hw_checksum = 1, + .csmr = 1, + .rx_csum = 1, .tsu = 1, .no_tx_cntrs = 1, }; @@ -668,7 +669,8 @@ static struct sh_eth_cpu_data r8a7740_data = { .no_trimd = 1, .no_ade = 1, .xdfar_rw = 1, - .hw_checksum = 1, + .csmr = 1, + .rx_csum = 1, .tsu = 1, .select_mii = 1, .magic = 1, @@ -793,7 +795,8 @@ static struct sh_eth_cpu_data r8a77980_data = { .no_trimd = 1, .no_ade = 1, .xdfar_rw = 1, - .hw_checksum = 1, + .csmr = 1, + .rx_csum = 1, .select_mii = 1, .magic = 1, .cexcr = 1, @@ -1045,7 +1048,8 @@ static struct sh_eth_cpu_data sh7734_data = { .no_ade = 1, .xdfar_rw = 1, .tsu = 1, - .hw_checksum = 1, + .csmr = 1, + .rx_csum = 1, .select_mii = 1, .magic = 1, .cexcr = 1, @@ -1088,6 +1092,7 @@ static struct sh_eth_cpu_data sh7763_data = { .irq_flags = IRQF_SHARED, .magic = 1, .cexcr = 1, + .rx_csum = 1, .dual_port = 1, }; @@ -1532,8 +1537,9 @@ static int sh_eth_dev_init(struct net_device *ndev) mdp->irq_enabled = true; sh_eth_write(ndev, mdp->cd->eesipr_value, EESIPR); - /* PAUSE Prohibition */ + /* EMAC Mode: PAUSE prohibition; Duplex; RX Checksum; TX; RX */ sh_eth_write(ndev, ECMR_ZPF | (mdp->duplex ? ECMR_DM : 0) | + (ndev->features & NETIF_F_RXCSUM ? ECMR_RCSC : 0) | ECMR_TE | ECMR_RE, ECMR); if (mdp->cd->set_rate) @@ -1592,6 +1598,19 @@ static void sh_eth_dev_exit(struct net_device *ndev) update_mac_address(ndev); } +static void sh_eth_rx_csum(struct sk_buff *skb) +{ + u8 *hw_csum; + + /* The hardware checksum is 2 bytes appended to packet data */ + if (unlikely(skb->len < sizeof(__sum16))) + return; + hw_csum = skb_tail_pointer(skb) - sizeof(__sum16); + skb->csum = csum_unfold((__force __sum16)get_unaligned_le16(hw_csum)); + skb->ip_summed = CHECKSUM_COMPLETE; + skb_trim(skb, skb->len - sizeof(__sum16)); +} + /* Packet receive function */ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota) { @@ -1633,7 +1652,7 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota) * the RFS bits are from bit 25 to bit 16. So, the * driver needs right shifting by 16. */ - if (mdp->cd->hw_checksum) + if (mdp->cd->csmr) desc_status >>= 16; skb = mdp->rx_skbuff[entry]; @@ -1666,6 +1685,8 @@ static int sh_eth_rx(struct net_device *ndev, u32 intr_status, int *quota) DMA_FROM_DEVICE); skb_put(skb, pkt_len); skb->protocol = eth_type_trans(skb, ndev); + if (ndev->features & NETIF_F_RXCSUM) + sh_eth_rx_csum(skb); netif_receive_skb(skb); ndev->stats.rx_packets++; ndev->stats.rx_bytes += pkt_len; @@ -2173,7 +2194,7 @@ static size_t __sh_eth_get_regs(struct net_device *ndev, u32 *buf) add_reg(MAFCR); if (cd->rtrate) add_reg(RTRATE); - if (cd->hw_checksum) + if (cd->csmr) add_reg(CSMR); if (cd->select_mii) add_reg(RMII_MII); @@ -2921,6 +2942,39 @@ static void sh_eth_set_rx_mode(struct net_device *ndev) spin_unlock_irqrestore(&mdp->lock, flags); } +static void sh_eth_set_rx_csum(struct net_device *ndev, bool enable) +{ + struct sh_eth_private *mdp = netdev_priv(ndev); + unsigned long flags; + + spin_lock_irqsave(&mdp->lock, flags); + + /* Disable TX and RX */ + sh_eth_rcv_snd_disable(ndev); + + /* Modify RX Checksum setting */ + sh_eth_modify(ndev, ECMR, ECMR_RCSC, enable ? ECMR_RCSC : 0); + + /* Enable TX and RX */ + sh_eth_rcv_snd_enable(ndev); + + spin_unlock_irqrestore(&mdp->lock, flags); +} + +static int sh_eth_set_features(struct net_device *ndev, + netdev_features_t features) +{ + netdev_features_t changed = ndev->features ^ features; + struct sh_eth_private *mdp = netdev_priv(ndev); + + if (changed & NETIF_F_RXCSUM && mdp->cd->rx_csum) + sh_eth_set_rx_csum(ndev, features & NETIF_F_RXCSUM); + + ndev->features = features; + + return 0; +} + static int sh_eth_get_vtag_index(struct sh_eth_private *mdp) { if (!mdp->port) @@ -3102,6 +3156,7 @@ static const struct net_device_ops sh_eth_netdev_ops = { .ndo_change_mtu = sh_eth_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, + .ndo_set_features = sh_eth_set_features, }; static const struct net_device_ops sh_eth_netdev_ops_tsu = { @@ -3117,6 +3172,7 @@ static const struct net_device_ops sh_eth_netdev_ops_tsu = { .ndo_change_mtu = sh_eth_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, + .ndo_set_features = sh_eth_set_features, }; #ifdef CONFIG_OF @@ -3245,6 +3301,11 @@ static int sh_eth_drv_probe(struct platform_device *pdev) ndev->max_mtu = 2000 - (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN); ndev->min_mtu = ETH_MIN_MTU; + if (mdp->cd->rx_csum) { + ndev->features = NETIF_F_RXCSUM; + ndev->hw_features = NETIF_F_RXCSUM; + } + /* set function */ if (mdp->cd->tsu) ndev->netdev_ops = &sh_eth_netdev_ops_tsu; @@ -3294,7 +3355,7 @@ static int sh_eth_drv_probe(struct platform_device *pdev) goto out_release; } mdp->port = port; - ndev->features = NETIF_F_HW_VLAN_CTAG_FILTER; + ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; /* Need to init only the first port of the two sharing a TSU */ if (port == 0) { diff --git a/drivers/net/ethernet/renesas/sh_eth.h b/drivers/net/ethernet/renesas/sh_eth.h index 0c18650bbfe6..850726301e1c 100644 --- a/drivers/net/ethernet/renesas/sh_eth.h +++ b/drivers/net/ethernet/renesas/sh_eth.h @@ -499,7 +499,8 @@ struct sh_eth_cpu_data { unsigned no_ade:1; /* E-DMAC DOES NOT have ADE bit in EESR */ unsigned no_xdfar:1; /* E-DMAC DOES NOT have RDFAR/TDFAR */ unsigned xdfar_rw:1; /* E-DMAC has writeable RDFAR/TDFAR */ - unsigned hw_checksum:1; /* E-DMAC has CSMR */ + unsigned csmr:1; /* E-DMAC has CSMR */ + unsigned rx_csum:1; /* EtherC has ECMR.RCSC */ unsigned select_mii:1; /* EtherC has RMII_MII (MII select register) */ unsigned rmiimode:1; /* EtherC has RMIIMODE register */ unsigned rtrate:1; /* EtherC has RTRATE register */ diff --git a/drivers/net/ethernet/rocker/rocker.h b/drivers/net/ethernet/rocker/rocker.h index 748fb12260a6..2b2e1c4f0dc3 100644 --- a/drivers/net/ethernet/rocker/rocker.h +++ b/drivers/net/ethernet/rocker/rocker.h @@ -109,8 +109,6 @@ struct rocker_world_ops { int (*port_attr_bridge_flags_set)(struct rocker_port *rocker_port, unsigned long brport_flags, struct switchdev_trans *trans); - int (*port_attr_bridge_flags_get)(const struct rocker_port *rocker_port, - unsigned long *p_brport_flags); int (*port_attr_bridge_flags_support_get)(const struct rocker_port * rocker_port, unsigned long * diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c index 62a205eba9f7..5ce8d5aba603 100644 --- a/drivers/net/ethernet/rocker/rocker_main.c +++ b/drivers/net/ethernet/rocker/rocker_main.c @@ -1583,17 +1583,6 @@ rocker_world_port_attr_bridge_flags_set(struct rocker_port *rocker_port, } static int -rocker_world_port_attr_bridge_flags_get(const struct rocker_port *rocker_port, - unsigned long *p_brport_flags) -{ - struct rocker_world_ops *wops = rocker_port->rocker->wops; - - if (!wops->port_attr_bridge_flags_get) - return -EOPNOTSUPP; - return wops->port_attr_bridge_flags_get(rocker_port, p_brport_flags); -} - -static int rocker_world_port_attr_bridge_flags_support_get(const struct rocker_port * rocker_port, unsigned long * @@ -2026,6 +2015,18 @@ static void rocker_port_neigh_destroy(struct net_device *dev, err); } +static int rocker_port_get_port_parent_id(struct net_device *dev, + struct netdev_phys_item_id *ppid) +{ + const struct rocker_port *rocker_port = netdev_priv(dev); + const struct rocker *rocker = rocker_port->rocker; + + ppid->id_len = sizeof(rocker->hw.id); + memcpy(&ppid->id, &rocker->hw.id, ppid->id_len); + + return 0; +} + static const struct net_device_ops rocker_port_netdev_ops = { .ndo_open = rocker_port_open, .ndo_stop = rocker_port_stop, @@ -2035,6 +2036,7 @@ static const struct net_device_ops rocker_port_netdev_ops = { .ndo_get_phys_port_name = rocker_port_get_phys_port_name, .ndo_change_proto_down = rocker_port_change_proto_down, .ndo_neigh_destroy = rocker_port_neigh_destroy, + .ndo_get_port_parent_id = rocker_port_get_port_parent_id, }; /******************** @@ -2045,18 +2047,9 @@ static int rocker_port_attr_get(struct net_device *dev, struct switchdev_attr *attr) { const struct rocker_port *rocker_port = netdev_priv(dev); - const struct rocker *rocker = rocker_port->rocker; int err = 0; switch (attr->id) { - case SWITCHDEV_ATTR_ID_PORT_PARENT_ID: - attr->u.ppid.id_len = sizeof(rocker->hw.id); - memcpy(&attr->u.ppid.id, &rocker->hw.id, attr->u.ppid.id_len); - break; - case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS: - err = rocker_world_port_attr_bridge_flags_get(rocker_port, - &attr->u.brport_flags); - break; case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT: err = rocker_world_port_attr_bridge_flags_support_get(rocker_port, &attr->u.brport_flags_support); diff --git a/drivers/net/ethernet/rocker/rocker_ofdpa.c b/drivers/net/ethernet/rocker/rocker_ofdpa.c index bea7895930f6..fa296a7c255d 100644 --- a/drivers/net/ethernet/rocker/rocker_ofdpa.c +++ b/drivers/net/ethernet/rocker/rocker_ofdpa.c @@ -2512,16 +2512,6 @@ static int ofdpa_port_attr_bridge_flags_set(struct rocker_port *rocker_port, } static int -ofdpa_port_attr_bridge_flags_get(const struct rocker_port *rocker_port, - unsigned long *p_brport_flags) -{ - const struct ofdpa_port *ofdpa_port = rocker_port->wpriv; - - *p_brport_flags = ofdpa_port->brport_flags; - return 0; -} - -static int ofdpa_port_attr_bridge_flags_support_get(const struct rocker_port * rocker_port, unsigned long * @@ -2823,7 +2813,6 @@ struct rocker_world_ops rocker_ofdpa_ops = { .port_stop = ofdpa_port_stop, .port_attr_stp_state_set = ofdpa_port_attr_stp_state_set, .port_attr_bridge_flags_set = ofdpa_port_attr_bridge_flags_set, - .port_attr_bridge_flags_get = ofdpa_port_attr_bridge_flags_get, .port_attr_bridge_flags_support_get = ofdpa_port_attr_bridge_flags_support_get, .port_attr_bridge_ageing_time_set = ofdpa_port_attr_bridge_ageing_time_set, .port_obj_vlan_add = ofdpa_port_obj_vlan_add, diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index 6062e99fa69b..e888b479c596 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -6046,6 +6046,8 @@ static const struct efx_ef10_nvram_type_info efx_ef10_nvram_types[] = { { NVRAM_PARTITION_TYPE_DYNCONFIG_DEFAULTS, 0, 0, "sfc_dynamic_cfg_dflt" }, { NVRAM_PARTITION_TYPE_ROMCONFIG_DEFAULTS, 0, 0, "sfc_exp_rom_cfg_dflt" }, { NVRAM_PARTITION_TYPE_STATUS, 0, 0, "sfc_status" }, + { NVRAM_PARTITION_TYPE_BUNDLE, 0, 0, "sfc_bundle" }, + { NVRAM_PARTITION_TYPE_BUNDLE_METADATA, 0, 0, "sfc_bundle_metadata" }, }; #define EF10_NVRAM_PARTITION_COUNT ARRAY_SIZE(efx_ef10_nvram_types) @@ -6123,7 +6125,7 @@ static int efx_ef10_mtd_probe_partition(struct efx_nic *efx, static int efx_ef10_mtd_probe(struct efx_nic *efx) { MCDI_DECLARE_BUF(outbuf, MC_CMD_NVRAM_PARTITIONS_OUT_LENMAX); - DECLARE_BITMAP(found, EF10_NVRAM_PARTITION_COUNT); + DECLARE_BITMAP(found, EF10_NVRAM_PARTITION_COUNT) = { 0 }; struct efx_mcdi_mtd_partition *parts; size_t outlen, n_parts_total, i, n_parts; unsigned int type; diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 3643015a55cf..bc655ffc9e02 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -915,7 +915,7 @@ rollback: void efx_schedule_slow_fill(struct efx_rx_queue *rx_queue) { - mod_timer(&rx_queue->slow_fill, jiffies + msecs_to_jiffies(100)); + mod_timer(&rx_queue->slow_fill, jiffies + msecs_to_jiffies(10)); } static bool efx_default_channel_want_txqs(struct efx_channel *channel) diff --git a/drivers/net/ethernet/sfc/mcdi_pcol.h b/drivers/net/ethernet/sfc/mcdi_pcol.h index 3839eec783ea..20a5523bf9f3 100644 --- a/drivers/net/ethernet/sfc/mcdi_pcol.h +++ b/drivers/net/ethernet/sfc/mcdi_pcol.h @@ -6784,6 +6784,14 @@ * subset of the information stored in this partition. */ #define NVRAM_PARTITION_TYPE_FRU_INFORMATION 0x1d00 +/* enum: Bundle image partition */ +#define NVRAM_PARTITION_TYPE_BUNDLE 0x1e00 +/* enum: Bundle metadata partition that holds additional information related to + * a bundle update in TLV format + */ +#define NVRAM_PARTITION_TYPE_BUNDLE_METADATA 0x1e01 +/* enum: Bundle update non-volatile log output partition */ +#define NVRAM_PARTITION_TYPE_BUNDLE_LOG 0x1e02 /* enum: Start of reserved value range (firmware may use for any purpose) */ #define NVRAM_PARTITION_TYPE_RESERVED_VALUES_MIN 0xff00 /* enum: End of reserved value range (firmware may use for any purpose) */ diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c index 396ff01298cd..8702ab44d80b 100644 --- a/drivers/net/ethernet/sfc/rx.c +++ b/drivers/net/ethernet/sfc/rx.c @@ -360,8 +360,7 @@ void efx_fast_push_rx_descriptors(struct efx_rx_queue *rx_queue, bool atomic) rc = efx_init_rx_buffers(rx_queue, atomic); if (unlikely(rc)) { /* Ensure that we don't leave the rx queue empty */ - if (rx_queue->added_count == rx_queue->removed_count) - efx_schedule_slow_fill(rx_queue); + efx_schedule_slow_fill(rx_queue); goto out; } } while ((space -= batch_size) >= batch_size); diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index 22eb059086f7..06c8f282263f 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -471,7 +471,7 @@ static int efx_tx_tso_fallback(struct efx_tx_queue *tx_queue, if (IS_ERR(segments)) return PTR_ERR(segments); - dev_kfree_skb_any(skb); + dev_consume_skb_any(skb); skb = segments; while (skb) { diff --git a/drivers/net/ethernet/sgi/ioc3-eth.c b/drivers/net/ethernet/sgi/ioc3-eth.c index 3140999642ba..358e66b81926 100644 --- a/drivers/net/ethernet/sgi/ioc3-eth.c +++ b/drivers/net/ethernet/sgi/ioc3-eth.c @@ -666,7 +666,7 @@ static inline void ioc3_tx(struct net_device *dev) packets++; skb = ip->tx_skbs[o_entry]; bytes += skb->len; - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); ip->tx_skbs[o_entry] = NULL; o_entry = (o_entry + 1) & 127; /* Next */ diff --git a/drivers/net/ethernet/sgi/meth.c b/drivers/net/ethernet/sgi/meth.c index 0e1b7e960b98..f1271402ca21 100644 --- a/drivers/net/ethernet/sgi/meth.c +++ b/drivers/net/ethernet/sgi/meth.c @@ -68,6 +68,8 @@ module_param(timeout, int, 0); * packets in and out, so there is place for a packet */ struct meth_private { + struct platform_device *pdev; + /* in-memory copy of MAC Control register */ u64 mac_ctrl; @@ -211,8 +213,8 @@ static void meth_check_link(struct net_device *dev) static int meth_init_tx_ring(struct meth_private *priv) { /* Init TX ring */ - priv->tx_ring = dma_alloc_coherent(NULL, TX_RING_BUFFER_SIZE, - &priv->tx_ring_dma, GFP_ATOMIC); + priv->tx_ring = dma_alloc_coherent(&priv->pdev->dev, + TX_RING_BUFFER_SIZE, &priv->tx_ring_dma, GFP_ATOMIC); if (!priv->tx_ring) return -ENOMEM; @@ -236,7 +238,7 @@ static int meth_init_rx_ring(struct meth_private *priv) priv->rx_ring[i]=(rx_packet*)(priv->rx_skbs[i]->head); /* I'll need to re-sync it after each RX */ priv->rx_ring_dmas[i] = - dma_map_single(NULL, priv->rx_ring[i], + dma_map_single(&priv->pdev->dev, priv->rx_ring[i], METH_RX_BUFF_SIZE, DMA_FROM_DEVICE); mace->eth.rx_fifo = priv->rx_ring_dmas[i]; } @@ -253,7 +255,7 @@ static void meth_free_tx_ring(struct meth_private *priv) dev_kfree_skb(priv->tx_skbs[i]); priv->tx_skbs[i] = NULL; } - dma_free_coherent(NULL, TX_RING_BUFFER_SIZE, priv->tx_ring, + dma_free_coherent(&priv->pdev->dev, TX_RING_BUFFER_SIZE, priv->tx_ring, priv->tx_ring_dma); } @@ -263,7 +265,7 @@ static void meth_free_rx_ring(struct meth_private *priv) int i; for (i = 0; i < RX_RING_ENTRIES; i++) { - dma_unmap_single(NULL, priv->rx_ring_dmas[i], + dma_unmap_single(&priv->pdev->dev, priv->rx_ring_dmas[i], METH_RX_BUFF_SIZE, DMA_FROM_DEVICE); priv->rx_ring[i] = 0; priv->rx_ring_dmas[i] = 0; @@ -393,7 +395,8 @@ static void meth_rx(struct net_device* dev, unsigned long int_status) fifo_rptr = (fifo_rptr - 1) & 0x0f; } while (priv->rx_write != fifo_rptr) { - dma_unmap_single(NULL, priv->rx_ring_dmas[priv->rx_write], + dma_unmap_single(&priv->pdev->dev, + priv->rx_ring_dmas[priv->rx_write], METH_RX_BUFF_SIZE, DMA_FROM_DEVICE); status = priv->rx_ring[priv->rx_write]->status.raw; #if MFE_DEBUG @@ -454,7 +457,8 @@ static void meth_rx(struct net_device* dev, unsigned long int_status) priv->rx_ring[priv->rx_write] = (rx_packet*)skb->head; priv->rx_ring[priv->rx_write]->status.raw = 0; priv->rx_ring_dmas[priv->rx_write] = - dma_map_single(NULL, priv->rx_ring[priv->rx_write], + dma_map_single(&priv->pdev->dev, + priv->rx_ring[priv->rx_write], METH_RX_BUFF_SIZE, DMA_FROM_DEVICE); mace->eth.rx_fifo = priv->rx_ring_dmas[priv->rx_write]; ADVANCE_RX_PTR(priv->rx_write); @@ -521,7 +525,7 @@ static void meth_tx_cleanup(struct net_device* dev, unsigned long int_status) DPRINTK("RPTR points us here, but packet not done?\n"); break; } - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); priv->tx_skbs[priv->tx_read] = NULL; priv->tx_ring[priv->tx_read].header.raw = 0; priv->tx_read = (priv->tx_read+1)&(TX_RING_ENTRIES-1); @@ -637,7 +641,7 @@ static void meth_tx_1page_prepare(struct meth_private *priv, } /* first page */ - catbuf = dma_map_single(NULL, buffer_data, buffer_len, + catbuf = dma_map_single(&priv->pdev->dev, buffer_data, buffer_len, DMA_TO_DEVICE); desc->data.cat_buf[0].form.start_addr = catbuf >> 3; desc->data.cat_buf[0].form.len = buffer_len - 1; @@ -663,12 +667,12 @@ static void meth_tx_2page_prepare(struct meth_private *priv, } /* first page */ - catbuf1 = dma_map_single(NULL, buffer1_data, buffer1_len, + catbuf1 = dma_map_single(&priv->pdev->dev, buffer1_data, buffer1_len, DMA_TO_DEVICE); desc->data.cat_buf[0].form.start_addr = catbuf1 >> 3; desc->data.cat_buf[0].form.len = buffer1_len - 1; /* second page */ - catbuf2 = dma_map_single(NULL, buffer2_data, buffer2_len, + catbuf2 = dma_map_single(&priv->pdev->dev, buffer2_data, buffer2_len, DMA_TO_DEVICE); desc->data.cat_buf[1].form.start_addr = catbuf2 >> 3; desc->data.cat_buf[1].form.len = buffer2_len - 1; @@ -840,6 +844,7 @@ static int meth_probe(struct platform_device *pdev) memcpy(dev->dev_addr, o2meth_eaddr, ETH_ALEN); priv = netdev_priv(dev); + priv->pdev = pdev; spin_lock_init(&priv->meth_lock); SET_NETDEV_DEV(dev, &pdev->dev); diff --git a/drivers/net/ethernet/sis/sis190.c b/drivers/net/ethernet/sis/sis190.c index 808cf9816673..5b351beb78cb 100644 --- a/drivers/net/ethernet/sis/sis190.c +++ b/drivers/net/ethernet/sis/sis190.c @@ -714,7 +714,7 @@ static void sis190_tx_interrupt(struct net_device *dev, sis190_unmap_tx_skb(tp->pci_dev, skb, txd); tp->Tx_skbuff[entry] = NULL; - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); } if (tp->dirty_tx != dirty_tx) { diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c index 4bb89f74742c..6073387511f8 100644 --- a/drivers/net/ethernet/sis/sis900.c +++ b/drivers/net/ethernet/sis/sis900.c @@ -1927,7 +1927,7 @@ static void sis900_finish_xmit (struct net_device *net_dev) pci_unmap_single(sis_priv->pci_dev, sis_priv->tx_ring[entry].bufptr, skb->len, PCI_DMA_TODEVICE); - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); sis_priv->tx_skbuff[entry] = NULL; sis_priv->tx_ring[entry].bufptr = 0; sis_priv->tx_ring[entry].cmdsts = 0; diff --git a/drivers/net/ethernet/smsc/epic100.c b/drivers/net/ethernet/smsc/epic100.c index 15c62c160953..be47d864f8b9 100644 --- a/drivers/net/ethernet/smsc/epic100.c +++ b/drivers/net/ethernet/smsc/epic100.c @@ -1037,7 +1037,7 @@ static void epic_tx(struct net_device *dev, struct epic_private *ep) skb = ep->tx_skbuff[entry]; pci_unmap_single(ep->pci_dev, ep->tx_ring[entry].bufaddr, skb->len, PCI_DMA_TODEVICE); - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); ep->tx_skbuff[entry] = NULL; } diff --git a/drivers/net/ethernet/smsc/smc911x.c b/drivers/net/ethernet/smsc/smc911x.c index 8355dfbb8ec3..b550e624500d 100644 --- a/drivers/net/ethernet/smsc/smc911x.c +++ b/drivers/net/ethernet/smsc/smc911x.c @@ -1188,7 +1188,7 @@ smc911x_tx_dma_irq(void *data) DBG(SMC_DEBUG_TX | SMC_DEBUG_DMA, dev, "TX DMA irq handler\n"); BUG_ON(skb == NULL); - dma_unmap_single(NULL, tx_dmabuf, tx_dmalen, DMA_TO_DEVICE); + dma_unmap_single(lp->dev, tx_dmabuf, tx_dmalen, DMA_TO_DEVICE); netif_trans_update(dev); dev_kfree_skb_irq(skb); lp->current_tx_skb = NULL; @@ -1219,7 +1219,7 @@ smc911x_rx_dma_irq(void *data) DBG(SMC_DEBUG_FUNC, dev, "--> %s\n", __func__); DBG(SMC_DEBUG_RX | SMC_DEBUG_DMA, dev, "RX DMA irq handler\n"); - dma_unmap_single(NULL, rx_dmabuf, rx_dmalen, DMA_FROM_DEVICE); + dma_unmap_single(lp->dev, rx_dmabuf, rx_dmalen, DMA_FROM_DEVICE); BUG_ON(skb == NULL); lp->current_rx_skb = NULL; PRINT_PKT(skb->data, skb->len); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c index 7b923362ee55..3b174eae77c1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c @@ -1342,8 +1342,10 @@ static int rk_gmac_powerup(struct rk_priv_data *bsp_priv) } ret = phy_power_on(bsp_priv, true); - if (ret) + if (ret) { + gmac_clk_enable(bsp_priv, false); return ret; + } pm_runtime_enable(dev); pm_runtime_get_sync(dev); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c index 20299f6f65fc..90045fffd393 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c @@ -268,7 +268,7 @@ static int dwmac4_wrback_get_rx_timestamp_status(void *desc, void *next_desc, int ret = -EINVAL; /* Get the status from normal w/b descriptor */ - if (likely(p->des3 & TDES3_RS1V)) { + if (likely(le32_to_cpu(p->des3) & RDES3_RDES1_VALID)) { if (likely(le32_to_cpu(p->des1) & RDES1_TIMESTAMP_AVAILABLE)) { int i = 0; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index d1f61c25d82b..5d85742a2be0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -721,8 +721,11 @@ static u32 stmmac_usec2riwt(u32 usec, struct stmmac_priv *priv) { unsigned long clk = clk_get_rate(priv->plat->stmmac_clk); - if (!clk) - return 0; + if (!clk) { + clk = priv->plat->clk_ref_rate; + if (!clk) + return 0; + } return (usec * (clk / 1000000)) / 256; } @@ -731,8 +734,11 @@ static u32 stmmac_riwt2usec(u32 riwt, struct stmmac_priv *priv) { unsigned long clk = clk_get_rate(priv->plat->stmmac_clk); - if (!clk) - return 0; + if (!clk) { + clk = priv->plat->clk_ref_rate; + if (!clk) + return 0; + } return (riwt * 256) / (clk / 1000000); } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 517555bcfa44..f12dd59c85cf 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -597,12 +597,13 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: /* PTP v1, UDP, any kind of event packet */ config.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT; - /* take time stamp for all event messages */ - if (xmac) - snap_type_sel = PTP_GMAC4_TCR_SNAPTYPSEL_1; - else - snap_type_sel = PTP_TCR_SNAPTYPSEL_1; - + /* 'xmac' hardware can support Sync, Pdelay_Req and + * Pdelay_resp by setting bit14 and bits17/16 to 01 + * This leaves Delay_Req timestamps out. + * Enable all events *and* general purpose message + * timestamping + */ + snap_type_sel = PTP_TCR_SNAPTYPSEL_1; ptp_over_ipv4_udp = PTP_TCR_TSIPV4ENA; ptp_over_ipv6_udp = PTP_TCR_TSIPV6ENA; break; @@ -633,10 +634,7 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) config.rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT; ptp_v2 = PTP_TCR_TSVER2ENA; /* take time stamp for all event messages */ - if (xmac) - snap_type_sel = PTP_GMAC4_TCR_SNAPTYPSEL_1; - else - snap_type_sel = PTP_TCR_SNAPTYPSEL_1; + snap_type_sel = PTP_TCR_SNAPTYPSEL_1; ptp_over_ipv4_udp = PTP_TCR_TSIPV4ENA; ptp_over_ipv6_udp = PTP_TCR_TSIPV6ENA; @@ -669,12 +667,7 @@ static int stmmac_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) /* PTP v2/802.AS1 any layer, any kind of event packet */ config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; ptp_v2 = PTP_TCR_TSVER2ENA; - /* take time stamp for all event messages */ - if (xmac) - snap_type_sel = PTP_GMAC4_TCR_SNAPTYPSEL_1; - else - snap_type_sel = PTP_TCR_SNAPTYPSEL_1; - + snap_type_sel = PTP_TCR_SNAPTYPSEL_1; ptp_over_ipv4_udp = PTP_TCR_TSIPV4ENA; ptp_over_ipv6_udp = PTP_TCR_TSIPV6ENA; ptp_over_ethernet = PTP_TCR_TSIPENA; @@ -3046,10 +3039,22 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) tx_q = &priv->tx_queue[queue]; + if (priv->tx_path_in_lpi_mode) + stmmac_disable_eee_mode(priv); + /* Manage oversized TCP frames for GMAC4 device */ if (skb_is_gso(skb) && priv->tso) { - if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) + if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) { + /* + * There is no way to determine the number of TSO + * capable Queues. Let's use always the Queue 0 + * because if TSO is supported then at least this + * one will be capable. + */ + skb_set_queue_mapping(skb, 0); + return stmmac_tso_xmit(skb, dev); + } } if (unlikely(stmmac_tx_avail(priv, queue) < nfrags + 1)) { @@ -3064,9 +3069,6 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_BUSY; } - if (priv->tx_path_in_lpi_mode) - stmmac_disable_eee_mode(priv); - entry = tx_q->cur_tx; first_entry = entry; WARN_ON(tx_q->tx_skbuff[first_entry]); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h index ecccf895fd7e..e852821289cf 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h @@ -59,9 +59,14 @@ #define PTP_TCR_TSEVNTENA BIT(14) /* Enable Snapshot for Messages Relevant to Master */ #define PTP_TCR_TSMSTRENA BIT(15) -/* Select PTP packets for Taking Snapshots */ +/* Select PTP packets for Taking Snapshots + * On gmac4 specifically: + * Enable SYNC, Pdelay_Req, Pdelay_Resp when TSEVNTENA is enabled. + * or + * Enable SYNC, Follow_Up, Delay_Req, Delay_Resp, Pdelay_Req, Pdelay_Resp, + * Pdelay_Resp_Follow_Up if TSEVNTENA is disabled + */ #define PTP_TCR_SNAPTYPSEL_1 BIT(16) -#define PTP_GMAC4_TCR_SNAPTYPSEL_1 GENMASK(17, 16) /* Enable MAC address for PTP Frame Filtering */ #define PTP_TCR_TSENMACADDR BIT(18) diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c index 7ec4eb74fe21..6fc05c106afc 100644 --- a/drivers/net/ethernet/sun/cassini.c +++ b/drivers/net/ethernet/sun/cassini.c @@ -1898,7 +1898,7 @@ static inline void cas_tx_ringN(struct cas *cp, int ring, int limit) cp->net_stats[ring].tx_packets++; cp->net_stats[ring].tx_bytes += skb->len; spin_unlock(&cp->stat_lock[ring]); - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); } cp->tx_old[ring] = entry; diff --git a/drivers/net/ethernet/sun/sunbmac.c b/drivers/net/ethernet/sun/sunbmac.c index 720b7ac77f3b..e9b757b03b56 100644 --- a/drivers/net/ethernet/sun/sunbmac.c +++ b/drivers/net/ethernet/sun/sunbmac.c @@ -781,7 +781,7 @@ static void bigmac_tx(struct bigmac *bp) DTX(("skb(%p) ", skb)); bp->tx_skbs[elem] = NULL; - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); elem = NEXT_TX(elem); } diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c index ff641cf30a4e..d007dfeba5c3 100644 --- a/drivers/net/ethernet/sun/sunhme.c +++ b/drivers/net/ethernet/sun/sunhme.c @@ -1962,7 +1962,7 @@ static void happy_meal_tx(struct happy_meal *hp) this = &txbase[elem]; } - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); dev->stats.tx_packets++; } hp->tx_old = elem; diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c index dc966ddb6d81..b24c11187017 100644 --- a/drivers/net/ethernet/tehuti/tehuti.c +++ b/drivers/net/ethernet/tehuti/tehuti.c @@ -1739,7 +1739,7 @@ static void bdx_tx_cleanup(struct bdx_priv *priv) tx_level -= db->rptr->len; /* '-' koz len is negative */ /* now should come skb pointer - free it */ - dev_kfree_skb_irq(db->rptr->addr.skb); + dev_consume_skb_irq(db->rptr->addr.skb); bdx_tx_db_inc_rptr(db); } diff --git a/drivers/net/ethernet/ti/cpmac.c b/drivers/net/ethernet/ti/cpmac.c index 810dfc7de1f9..e2d47b24a869 100644 --- a/drivers/net/ethernet/ti/cpmac.c +++ b/drivers/net/ethernet/ti/cpmac.c @@ -608,7 +608,7 @@ static void cpmac_end_xmit(struct net_device *dev, int queue) netdev_dbg(dev, "sent 0x%p, len=%d\n", desc->skb, desc->skb->len); - dev_kfree_skb_irq(desc->skb); + dev_consume_skb_irq(desc->skb); desc->skb = NULL; if (__netif_subqueue_stopped(dev, queue)) netif_wake_subqueue(dev, queue); diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c index 82412691ee66..27f6cf140845 100644 --- a/drivers/net/ethernet/via/via-velocity.c +++ b/drivers/net/ethernet/via/via-velocity.c @@ -1740,7 +1740,7 @@ static void velocity_free_tx_buf(struct velocity_info *vptr, dma_unmap_single(vptr->dev, tdinfo->skb_dma[i], le16_to_cpu(pktlen), DMA_TO_DEVICE); } - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); tdinfo->skb = NULL; } diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c index 15bb058db392..44efffbe7970 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_main.c +++ b/drivers/net/ethernet/xilinx/ll_temac_main.c @@ -630,7 +630,7 @@ static void temac_start_xmit_done(struct net_device *ndev) dma_unmap_single(ndev->dev.parent, cur_p->phys, cur_p->len, DMA_TO_DEVICE); if (cur_p->app4) - dev_kfree_skb_irq((struct sk_buff *)cur_p->app4); + dev_consume_skb_irq((struct sk_buff *)cur_p->app4); cur_p->app0 = 0; cur_p->app1 = 0; cur_p->app2 = 0; diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 0789d8af7d72..ec7e7ec24ff9 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -595,7 +595,7 @@ static void axienet_start_xmit_done(struct net_device *ndev) (cur_p->cntrl & XAXIDMA_BD_CTRL_LENGTH_MASK), DMA_TO_DEVICE); if (cur_p->app4) - dev_kfree_skb_irq((struct sk_buff *)cur_p->app4); + dev_consume_skb_irq((struct sk_buff *)cur_p->app4); /*cur_p->phys = 0;*/ cur_p->app0 = 0; cur_p->app1 = 0; diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c index 639e3e99af46..b03a417d0073 100644 --- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c +++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c @@ -581,7 +581,7 @@ static void xemaclite_tx_handler(struct net_device *dev) return; dev->stats.tx_bytes += lp->deferred_skb->len; - dev_kfree_skb_irq(lp->deferred_skb); + dev_consume_skb_irq(lp->deferred_skb); lp->deferred_skb = NULL; netif_trans_update(dev); /* prevent tx timeout */ netif_wake_queue(dev); diff --git a/drivers/net/ethernet/xscale/ixp4xx_eth.c b/drivers/net/ethernet/xscale/ixp4xx_eth.c index aee55c03def0..ed6623a9801e 100644 --- a/drivers/net/ethernet/xscale/ixp4xx_eth.c +++ b/drivers/net/ethernet/xscale/ixp4xx_eth.c @@ -139,7 +139,7 @@ #ifdef __ARMEB__ typedef struct sk_buff buffer_t; #define free_buffer dev_kfree_skb -#define free_buffer_irq dev_kfree_skb_irq +#define free_buffer_irq dev_consume_skb_irq #else typedef void buffer_t; #define free_buffer kfree diff --git a/drivers/net/fddi/defxx.c b/drivers/net/fddi/defxx.c index 38ac8ef41f5f..56b7791911bf 100644 --- a/drivers/net/fddi/defxx.c +++ b/drivers/net/fddi/defxx.c @@ -3512,7 +3512,7 @@ static int dfx_xmt_done(DFX_board_t *bp) bp->descr_block_virt->xmt_data[comp].long_1, p_xmt_drv_descr->p_skb->len, DMA_TO_DEVICE); - dev_kfree_skb_irq(p_xmt_drv_descr->p_skb); + dev_consume_skb_irq(p_xmt_drv_descr->p_skb); /* * Move to start of next packet by updating completion index diff --git a/drivers/net/fddi/skfp/pcmplc.c b/drivers/net/fddi/skfp/pcmplc.c index 6ef44c480bd5..f29f5a6a45ab 100644 --- a/drivers/net/fddi/skfp/pcmplc.c +++ b/drivers/net/fddi/skfp/pcmplc.c @@ -851,6 +851,7 @@ static void pcm_fsm(struct s_smc *smc, struct s_phy *phy, int cmd) case ACTIONS(PC5_SIGNAL) : ACTIONS_DONE() ; + /* fall through */ case PC5_SIGNAL : if ((cmd != PC_SIGNAL) && (cmd != PC_TIMEOUT_LCT)) break ; diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 58bbba8582b0..3377ac66a347 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -1512,9 +1512,13 @@ static void geneve_link_config(struct net_device *dev, } #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: { - struct rt6_info *rt = rt6_lookup(geneve->net, - &info->key.u.ipv6.dst, NULL, 0, - NULL, 0); + struct rt6_info *rt; + + if (!__in6_dev_get(dev)) + break; + + rt = rt6_lookup(geneve->net, &info->key.u.ipv6.dst, NULL, 0, + NULL, 0); if (rt && rt->dst.dev) ldev_mtu = rt->dst.dev->mtu - GENEVE_IPV6_HLEN; diff --git a/drivers/net/ieee802154/mcr20a.c b/drivers/net/ieee802154/mcr20a.c index 44de81e5f140..c589f5ae75bb 100644 --- a/drivers/net/ieee802154/mcr20a.c +++ b/drivers/net/ieee802154/mcr20a.c @@ -905,9 +905,9 @@ mcr20a_irq_clean_complete(void *context) } break; case (DAR_IRQSTS1_RXIRQ | DAR_IRQSTS1_SEQIRQ): - /* rx is starting */ - dev_dbg(printdev(lp), "RX is starting\n"); - mcr20a_handle_rx(lp); + /* rx is starting */ + dev_dbg(printdev(lp), "RX is starting\n"); + mcr20a_handle_rx(lp); break; case (DAR_IRQSTS1_RXIRQ | DAR_IRQSTS1_TXIRQ | DAR_IRQSTS1_SEQIRQ): if (lp->is_tx) { diff --git a/drivers/net/ipvlan/Makefile b/drivers/net/ipvlan/Makefile index 8a2c64dc9641..3ee95367a994 100644 --- a/drivers/net/ipvlan/Makefile +++ b/drivers/net/ipvlan/Makefile @@ -5,4 +5,5 @@ obj-$(CONFIG_IPVLAN) += ipvlan.o obj-$(CONFIG_IPVTAP) += ipvtap.o -ipvlan-objs := ipvlan_core.o ipvlan_main.o +ipvlan-objs-$(CONFIG_IPVLAN_L3S) += ipvlan_l3s.o +ipvlan-objs := ipvlan_core.o ipvlan_main.o $(ipvlan-objs-y) diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h index adb826f55e60..b906d2f6bd04 100644 --- a/drivers/net/ipvlan/ipvlan.h +++ b/drivers/net/ipvlan/ipvlan.h @@ -165,10 +165,9 @@ struct ipvl_addr *ipvlan_find_addr(const struct ipvl_dev *ipvlan, const void *iaddr, bool is_v6); bool ipvlan_addr_busy(struct ipvl_port *port, void *iaddr, bool is_v6); void ipvlan_ht_addr_del(struct ipvl_addr *addr); -struct sk_buff *ipvlan_l3_rcv(struct net_device *dev, struct sk_buff *skb, - u16 proto); -unsigned int ipvlan_nf_input(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state); +struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port, void *lyr3h, + int addr_type, bool use_dest); +void *ipvlan_get_L3_hdr(struct ipvl_port *port, struct sk_buff *skb, int *type); void ipvlan_count_rx(const struct ipvl_dev *ipvlan, unsigned int len, bool success, bool mcast); int ipvlan_link_new(struct net *src_net, struct net_device *dev, @@ -177,6 +176,36 @@ int ipvlan_link_new(struct net *src_net, struct net_device *dev, void ipvlan_link_delete(struct net_device *dev, struct list_head *head); void ipvlan_link_setup(struct net_device *dev); int ipvlan_link_register(struct rtnl_link_ops *ops); +#ifdef CONFIG_IPVLAN_L3S +int ipvlan_l3s_register(struct ipvl_port *port); +void ipvlan_l3s_unregister(struct ipvl_port *port); +void ipvlan_migrate_l3s_hook(struct net *oldnet, struct net *newnet); +int ipvlan_l3s_init(void); +void ipvlan_l3s_cleanup(void); +#else +static inline int ipvlan_l3s_register(struct ipvl_port *port) +{ + return -ENOTSUPP; +} + +static inline void ipvlan_l3s_unregister(struct ipvl_port *port) +{ +} + +static inline void ipvlan_migrate_l3s_hook(struct net *oldnet, + struct net *newnet) +{ +} + +static inline int ipvlan_l3s_init(void) +{ + return 0; +} + +static inline void ipvlan_l3s_cleanup(void) +{ +} +#endif /* CONFIG_IPVLAN_L3S */ static inline bool netif_is_ipvlan_port(const struct net_device *dev) { diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c index 1a8132eb2a3e..e0f5bc82b10c 100644 --- a/drivers/net/ipvlan/ipvlan_core.c +++ b/drivers/net/ipvlan/ipvlan_core.c @@ -138,7 +138,7 @@ bool ipvlan_addr_busy(struct ipvl_port *port, void *iaddr, bool is_v6) return ret; } -static void *ipvlan_get_L3_hdr(struct ipvl_port *port, struct sk_buff *skb, int *type) +void *ipvlan_get_L3_hdr(struct ipvl_port *port, struct sk_buff *skb, int *type) { void *lyr3h = NULL; @@ -355,9 +355,8 @@ out: return ret; } -static struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port, - void *lyr3h, int addr_type, - bool use_dest) +struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port, void *lyr3h, + int addr_type, bool use_dest) { struct ipvl_addr *addr = NULL; @@ -647,7 +646,9 @@ int ipvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev) case IPVLAN_MODE_L2: return ipvlan_xmit_mode_l2(skb, dev); case IPVLAN_MODE_L3: +#ifdef CONFIG_IPVLAN_L3S case IPVLAN_MODE_L3S: +#endif return ipvlan_xmit_mode_l3(skb, dev); } @@ -743,8 +744,10 @@ rx_handler_result_t ipvlan_handle_frame(struct sk_buff **pskb) return ipvlan_handle_mode_l2(pskb, port); case IPVLAN_MODE_L3: return ipvlan_handle_mode_l3(pskb, port); +#ifdef CONFIG_IPVLAN_L3S case IPVLAN_MODE_L3S: return RX_HANDLER_PASS; +#endif } /* Should not reach here */ @@ -753,97 +756,3 @@ rx_handler_result_t ipvlan_handle_frame(struct sk_buff **pskb) kfree_skb(skb); return RX_HANDLER_CONSUMED; } - -static struct ipvl_addr *ipvlan_skb_to_addr(struct sk_buff *skb, - struct net_device *dev) -{ - struct ipvl_addr *addr = NULL; - struct ipvl_port *port; - void *lyr3h; - int addr_type; - - if (!dev || !netif_is_ipvlan_port(dev)) - goto out; - - port = ipvlan_port_get_rcu(dev); - if (!port || port->mode != IPVLAN_MODE_L3S) - goto out; - - lyr3h = ipvlan_get_L3_hdr(port, skb, &addr_type); - if (!lyr3h) - goto out; - - addr = ipvlan_addr_lookup(port, lyr3h, addr_type, true); -out: - return addr; -} - -struct sk_buff *ipvlan_l3_rcv(struct net_device *dev, struct sk_buff *skb, - u16 proto) -{ - struct ipvl_addr *addr; - struct net_device *sdev; - - addr = ipvlan_skb_to_addr(skb, dev); - if (!addr) - goto out; - - sdev = addr->master->dev; - switch (proto) { - case AF_INET: - { - int err; - struct iphdr *ip4h = ip_hdr(skb); - - err = ip_route_input_noref(skb, ip4h->daddr, ip4h->saddr, - ip4h->tos, sdev); - if (unlikely(err)) - goto out; - break; - } -#if IS_ENABLED(CONFIG_IPV6) - case AF_INET6: - { - struct dst_entry *dst; - struct ipv6hdr *ip6h = ipv6_hdr(skb); - int flags = RT6_LOOKUP_F_HAS_SADDR; - struct flowi6 fl6 = { - .flowi6_iif = sdev->ifindex, - .daddr = ip6h->daddr, - .saddr = ip6h->saddr, - .flowlabel = ip6_flowinfo(ip6h), - .flowi6_mark = skb->mark, - .flowi6_proto = ip6h->nexthdr, - }; - - skb_dst_drop(skb); - dst = ip6_route_input_lookup(dev_net(sdev), sdev, &fl6, - skb, flags); - skb_dst_set(skb, dst); - break; - } -#endif - default: - break; - } - -out: - return skb; -} - -unsigned int ipvlan_nf_input(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - struct ipvl_addr *addr; - unsigned int len; - - addr = ipvlan_skb_to_addr(skb, skb->dev); - if (!addr) - goto out; - - skb->dev = addr->master->dev; - len = skb->len + ETH_HLEN; - ipvlan_count_rx(addr->master, len, true, false); -out: - return NF_ACCEPT; -} diff --git a/drivers/net/ipvlan/ipvlan_l3s.c b/drivers/net/ipvlan/ipvlan_l3s.c new file mode 100644 index 000000000000..d17480a911a3 --- /dev/null +++ b/drivers/net/ipvlan/ipvlan_l3s.c @@ -0,0 +1,227 @@ +/* Copyright (c) 2014 Mahesh Bandewar <maheshb@google.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 of + * the License, or (at your option) any later version. + */ + +#include "ipvlan.h" + +static unsigned int ipvlan_netid __read_mostly; + +struct ipvlan_netns { + unsigned int ipvl_nf_hook_refcnt; +}; + +static struct ipvl_addr *ipvlan_skb_to_addr(struct sk_buff *skb, + struct net_device *dev) +{ + struct ipvl_addr *addr = NULL; + struct ipvl_port *port; + int addr_type; + void *lyr3h; + + if (!dev || !netif_is_ipvlan_port(dev)) + goto out; + + port = ipvlan_port_get_rcu(dev); + if (!port || port->mode != IPVLAN_MODE_L3S) + goto out; + + lyr3h = ipvlan_get_L3_hdr(port, skb, &addr_type); + if (!lyr3h) + goto out; + + addr = ipvlan_addr_lookup(port, lyr3h, addr_type, true); +out: + return addr; +} + +static struct sk_buff *ipvlan_l3_rcv(struct net_device *dev, + struct sk_buff *skb, u16 proto) +{ + struct ipvl_addr *addr; + struct net_device *sdev; + + addr = ipvlan_skb_to_addr(skb, dev); + if (!addr) + goto out; + + sdev = addr->master->dev; + switch (proto) { + case AF_INET: + { + struct iphdr *ip4h = ip_hdr(skb); + int err; + + err = ip_route_input_noref(skb, ip4h->daddr, ip4h->saddr, + ip4h->tos, sdev); + if (unlikely(err)) + goto out; + break; + } +#if IS_ENABLED(CONFIG_IPV6) + case AF_INET6: + { + struct dst_entry *dst; + struct ipv6hdr *ip6h = ipv6_hdr(skb); + int flags = RT6_LOOKUP_F_HAS_SADDR; + struct flowi6 fl6 = { + .flowi6_iif = sdev->ifindex, + .daddr = ip6h->daddr, + .saddr = ip6h->saddr, + .flowlabel = ip6_flowinfo(ip6h), + .flowi6_mark = skb->mark, + .flowi6_proto = ip6h->nexthdr, + }; + + skb_dst_drop(skb); + dst = ip6_route_input_lookup(dev_net(sdev), sdev, &fl6, + skb, flags); + skb_dst_set(skb, dst); + break; + } +#endif + default: + break; + } +out: + return skb; +} + +static const struct l3mdev_ops ipvl_l3mdev_ops = { + .l3mdev_l3_rcv = ipvlan_l3_rcv, +}; + +static unsigned int ipvlan_nf_input(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct ipvl_addr *addr; + unsigned int len; + + addr = ipvlan_skb_to_addr(skb, skb->dev); + if (!addr) + goto out; + + skb->dev = addr->master->dev; + len = skb->len + ETH_HLEN; + ipvlan_count_rx(addr->master, len, true, false); +out: + return NF_ACCEPT; +} + +static const struct nf_hook_ops ipvl_nfops[] = { + { + .hook = ipvlan_nf_input, + .pf = NFPROTO_IPV4, + .hooknum = NF_INET_LOCAL_IN, + .priority = INT_MAX, + }, +#if IS_ENABLED(CONFIG_IPV6) + { + .hook = ipvlan_nf_input, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_LOCAL_IN, + .priority = INT_MAX, + }, +#endif +}; + +static int ipvlan_register_nf_hook(struct net *net) +{ + struct ipvlan_netns *vnet = net_generic(net, ipvlan_netid); + int err = 0; + + if (!vnet->ipvl_nf_hook_refcnt) { + err = nf_register_net_hooks(net, ipvl_nfops, + ARRAY_SIZE(ipvl_nfops)); + if (!err) + vnet->ipvl_nf_hook_refcnt = 1; + } else { + vnet->ipvl_nf_hook_refcnt++; + } + + return err; +} + +static void ipvlan_unregister_nf_hook(struct net *net) +{ + struct ipvlan_netns *vnet = net_generic(net, ipvlan_netid); + + if (WARN_ON(!vnet->ipvl_nf_hook_refcnt)) + return; + + vnet->ipvl_nf_hook_refcnt--; + if (!vnet->ipvl_nf_hook_refcnt) + nf_unregister_net_hooks(net, ipvl_nfops, + ARRAY_SIZE(ipvl_nfops)); +} + +void ipvlan_migrate_l3s_hook(struct net *oldnet, struct net *newnet) +{ + struct ipvlan_netns *old_vnet; + + ASSERT_RTNL(); + + old_vnet = net_generic(oldnet, ipvlan_netid); + if (!old_vnet->ipvl_nf_hook_refcnt) + return; + + ipvlan_register_nf_hook(newnet); + ipvlan_unregister_nf_hook(oldnet); +} + +static void ipvlan_ns_exit(struct net *net) +{ + struct ipvlan_netns *vnet = net_generic(net, ipvlan_netid); + + if (WARN_ON_ONCE(vnet->ipvl_nf_hook_refcnt)) { + vnet->ipvl_nf_hook_refcnt = 0; + nf_unregister_net_hooks(net, ipvl_nfops, + ARRAY_SIZE(ipvl_nfops)); + } +} + +static struct pernet_operations ipvlan_net_ops = { + .id = &ipvlan_netid, + .size = sizeof(struct ipvlan_netns), + .exit = ipvlan_ns_exit, +}; + +int ipvlan_l3s_init(void) +{ + return register_pernet_subsys(&ipvlan_net_ops); +} + +void ipvlan_l3s_cleanup(void) +{ + unregister_pernet_subsys(&ipvlan_net_ops); +} + +int ipvlan_l3s_register(struct ipvl_port *port) +{ + struct net_device *dev = port->dev; + int ret; + + ASSERT_RTNL(); + + ret = ipvlan_register_nf_hook(read_pnet(&port->pnet)); + if (!ret) { + dev->l3mdev_ops = &ipvl_l3mdev_ops; + dev->priv_flags |= IFF_L3MDEV_RX_HANDLER; + } + + return ret; +} + +void ipvlan_l3s_unregister(struct ipvl_port *port) +{ + struct net_device *dev = port->dev; + + ASSERT_RTNL(); + + dev->priv_flags &= ~IFF_L3MDEV_RX_HANDLER; + ipvlan_unregister_nf_hook(read_pnet(&port->pnet)); + dev->l3mdev_ops = NULL; +} diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c index 19bdde60680c..8ec73d973079 100644 --- a/drivers/net/ipvlan/ipvlan_main.c +++ b/drivers/net/ipvlan/ipvlan_main.c @@ -9,73 +9,10 @@ #include "ipvlan.h" -static unsigned int ipvlan_netid __read_mostly; - -struct ipvlan_netns { - unsigned int ipvl_nf_hook_refcnt; -}; - -static const struct nf_hook_ops ipvl_nfops[] = { - { - .hook = ipvlan_nf_input, - .pf = NFPROTO_IPV4, - .hooknum = NF_INET_LOCAL_IN, - .priority = INT_MAX, - }, -#if IS_ENABLED(CONFIG_IPV6) - { - .hook = ipvlan_nf_input, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_LOCAL_IN, - .priority = INT_MAX, - }, -#endif -}; - -static const struct l3mdev_ops ipvl_l3mdev_ops = { - .l3mdev_l3_rcv = ipvlan_l3_rcv, -}; - -static void ipvlan_adjust_mtu(struct ipvl_dev *ipvlan, struct net_device *dev) -{ - ipvlan->dev->mtu = dev->mtu; -} - -static int ipvlan_register_nf_hook(struct net *net) -{ - struct ipvlan_netns *vnet = net_generic(net, ipvlan_netid); - int err = 0; - - if (!vnet->ipvl_nf_hook_refcnt) { - err = nf_register_net_hooks(net, ipvl_nfops, - ARRAY_SIZE(ipvl_nfops)); - if (!err) - vnet->ipvl_nf_hook_refcnt = 1; - } else { - vnet->ipvl_nf_hook_refcnt++; - } - - return err; -} - -static void ipvlan_unregister_nf_hook(struct net *net) -{ - struct ipvlan_netns *vnet = net_generic(net, ipvlan_netid); - - if (WARN_ON(!vnet->ipvl_nf_hook_refcnt)) - return; - - vnet->ipvl_nf_hook_refcnt--; - if (!vnet->ipvl_nf_hook_refcnt) - nf_unregister_net_hooks(net, ipvl_nfops, - ARRAY_SIZE(ipvl_nfops)); -} - static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval, struct netlink_ext_ack *extack) { struct ipvl_dev *ipvlan; - struct net_device *mdev = port->dev; unsigned int flags; int err; @@ -97,17 +34,12 @@ static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval, } if (nval == IPVLAN_MODE_L3S) { /* New mode is L3S */ - err = ipvlan_register_nf_hook(read_pnet(&port->pnet)); - if (!err) { - mdev->l3mdev_ops = &ipvl_l3mdev_ops; - mdev->priv_flags |= IFF_L3MDEV_MASTER; - } else + err = ipvlan_l3s_register(port); + if (err) goto fail; } else if (port->mode == IPVLAN_MODE_L3S) { /* Old mode was L3S */ - mdev->priv_flags &= ~IFF_L3MDEV_MASTER; - ipvlan_unregister_nf_hook(read_pnet(&port->pnet)); - mdev->l3mdev_ops = NULL; + ipvlan_l3s_unregister(port); } port->mode = nval; } @@ -166,11 +98,8 @@ static void ipvlan_port_destroy(struct net_device *dev) struct ipvl_port *port = ipvlan_port_get_rtnl(dev); struct sk_buff *skb; - if (port->mode == IPVLAN_MODE_L3S) { - dev->priv_flags &= ~IFF_L3MDEV_MASTER; - ipvlan_unregister_nf_hook(dev_net(dev)); - dev->l3mdev_ops = NULL; - } + if (port->mode == IPVLAN_MODE_L3S) + ipvlan_l3s_unregister(port); netdev_rx_handler_unregister(dev); cancel_work_sync(&port->wq); while ((skb = __skb_dequeue(&port->backlog)) != NULL) { @@ -446,6 +375,11 @@ static const struct header_ops ipvlan_header_ops = { .cache_update = eth_header_cache_update, }; +static void ipvlan_adjust_mtu(struct ipvl_dev *ipvlan, struct net_device *dev) +{ + ipvlan->dev->mtu = dev->mtu; +} + static bool netif_is_ipvlan(const struct net_device *dev) { /* both ipvlan and ipvtap devices use the same netdev_ops */ @@ -781,7 +715,6 @@ static int ipvlan_device_event(struct notifier_block *unused, case NETDEV_REGISTER: { struct net *oldnet, *newnet = dev_net(dev); - struct ipvlan_netns *old_vnet; oldnet = read_pnet(&port->pnet); if (net_eq(newnet, oldnet)) @@ -789,12 +722,7 @@ static int ipvlan_device_event(struct notifier_block *unused, write_pnet(&port->pnet, newnet); - old_vnet = net_generic(oldnet, ipvlan_netid); - if (!old_vnet->ipvl_nf_hook_refcnt) - break; - - ipvlan_register_nf_hook(newnet); - ipvlan_unregister_nf_hook(oldnet); + ipvlan_migrate_l3s_hook(oldnet, newnet); break; } case NETDEV_UNREGISTER: @@ -1068,23 +996,6 @@ static struct notifier_block ipvlan_addr6_vtor_notifier_block __read_mostly = { }; #endif -static void ipvlan_ns_exit(struct net *net) -{ - struct ipvlan_netns *vnet = net_generic(net, ipvlan_netid); - - if (WARN_ON_ONCE(vnet->ipvl_nf_hook_refcnt)) { - vnet->ipvl_nf_hook_refcnt = 0; - nf_unregister_net_hooks(net, ipvl_nfops, - ARRAY_SIZE(ipvl_nfops)); - } -} - -static struct pernet_operations ipvlan_net_ops = { - .id = &ipvlan_netid, - .size = sizeof(struct ipvlan_netns), - .exit = ipvlan_ns_exit, -}; - static int __init ipvlan_init_module(void) { int err; @@ -1099,13 +1010,13 @@ static int __init ipvlan_init_module(void) register_inetaddr_notifier(&ipvlan_addr4_notifier_block); register_inetaddr_validator_notifier(&ipvlan_addr4_vtor_notifier_block); - err = register_pernet_subsys(&ipvlan_net_ops); + err = ipvlan_l3s_init(); if (err < 0) goto error; err = ipvlan_link_register(&ipvlan_link_ops); if (err < 0) { - unregister_pernet_subsys(&ipvlan_net_ops); + ipvlan_l3s_cleanup(); goto error; } @@ -1126,7 +1037,7 @@ error: static void __exit ipvlan_cleanup_module(void) { rtnl_link_unregister(&ipvlan_link_ops); - unregister_pernet_subsys(&ipvlan_net_ops); + ipvlan_l3s_cleanup(); unregister_netdevice_notifier(&ipvlan_notifier_block); unregister_inetaddr_notifier(&ipvlan_addr4_notifier_block); unregister_inetaddr_validator_notifier( diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index cf22a79af66b..26e53832b095 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -119,8 +119,6 @@ static struct macvlan_port *macvlan_port_get_rtnl(const struct net_device *dev) return rtnl_dereference(dev->rx_handler_data); } -#define macvlan_port_exists(dev) (dev->priv_flags & IFF_MACVLAN_PORT) - static struct macvlan_dev *macvlan_hash_lookup(const struct macvlan_port *port, const unsigned char *addr) { @@ -1378,7 +1376,7 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev, if (!tb[IFLA_ADDRESS]) eth_hw_addr_random(dev); - if (!macvlan_port_exists(lowerdev)) { + if (!netif_is_macvlan_port(lowerdev)) { err = macvlan_port_create(lowerdev); if (err < 0) return err; @@ -1638,7 +1636,7 @@ static int macvlan_device_event(struct notifier_block *unused, struct macvlan_port *port; LIST_HEAD(list_kill); - if (!macvlan_port_exists(dev)) + if (!netif_is_macvlan_port(dev)) return NOTIFY_DONE; port = macvlan_port_get_rtnl(dev); diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c index 172b271c8bd2..f92c43453ec6 100644 --- a/drivers/net/netdevsim/bpf.c +++ b/drivers/net/netdevsim/bpf.c @@ -248,7 +248,7 @@ static int nsim_bpf_create_prog(struct netdevsim *ns, struct bpf_prog *prog) static int nsim_bpf_verifier_prep(struct bpf_prog *prog) { - struct netdevsim *ns = netdev_priv(prog->aux->offload->netdev); + struct netdevsim *ns = bpf_offload_dev_priv(prog->aux->offload->offdev); if (!ns->bpf_bind_accept) return -EOPNOTSUPP; @@ -589,7 +589,8 @@ int nsim_bpf_init(struct netdevsim *ns) if (IS_ERR_OR_NULL(ns->sdev->ddir_bpf_bound_progs)) return -ENOMEM; - ns->sdev->bpf_dev = bpf_offload_dev_create(&nsim_bpf_dev_ops); + ns->sdev->bpf_dev = bpf_offload_dev_create(&nsim_bpf_dev_ops, + ns); err = PTR_ERR_OR_ZERO(ns->sdev->bpf_dev); if (err) return err; diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index 8d8e2b3f263e..75a50b59cb8f 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -22,7 +22,6 @@ #include <net/netlink.h> #include <net/pkt_cls.h> #include <net/rtnetlink.h> -#include <net/switchdev.h> #include "netdevsim.h" @@ -148,26 +147,16 @@ static struct device_type nsim_dev_type = { .release = nsim_dev_release, }; -static int -nsim_port_attr_get(struct net_device *dev, struct switchdev_attr *attr) +static int nsim_get_port_parent_id(struct net_device *dev, + struct netdev_phys_item_id *ppid) { struct netdevsim *ns = netdev_priv(dev); - switch (attr->id) { - case SWITCHDEV_ATTR_ID_PORT_PARENT_ID: - attr->u.ppid.id_len = sizeof(ns->sdev->switch_id); - memcpy(&attr->u.ppid.id, &ns->sdev->switch_id, - attr->u.ppid.id_len); - return 0; - default: - return -EOPNOTSUPP; - } + ppid->id_len = sizeof(ns->sdev->switch_id); + memcpy(&ppid->id, &ns->sdev->switch_id, ppid->id_len); + return 0; } -static const struct switchdev_ops nsim_switchdev_ops = { - .switchdev_port_attr_get = nsim_port_attr_get, -}; - static int nsim_init(struct net_device *dev) { char sdev_ddir_name[10], sdev_link_name[32]; @@ -214,7 +203,6 @@ static int nsim_init(struct net_device *dev) goto err_bpf_uninit; SET_NETDEV_DEV(dev, &ns->dev); - SWITCHDEV_SET_OPS(dev, &nsim_switchdev_ops); err = nsim_devlink_setup(ns); if (err) @@ -493,6 +481,7 @@ static const struct net_device_ops nsim_netdev_ops = { .ndo_setup_tc = nsim_setup_tc, .ndo_set_features = nsim_set_features, .ndo_bpf = nsim_bpf, + .ndo_get_port_parent_id = nsim_get_port_parent_id, }; static void nsim_setup(struct net_device *dev) diff --git a/drivers/net/phy/aquantia.c b/drivers/net/phy/aquantia.c index 0578fe75d3b6..0f772a47a18e 100644 --- a/drivers/net/phy/aquantia.c +++ b/drivers/net/phy/aquantia.c @@ -10,19 +10,59 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/delay.h> -#include <linux/mii.h> -#include <linux/ethtool.h> #include <linux/phy.h> -#include <linux/mdio.h> #define PHY_ID_AQ1202 0x03a1b445 #define PHY_ID_AQ2104 0x03a1b460 #define PHY_ID_AQR105 0x03a1b4a2 #define PHY_ID_AQR106 0x03a1b4d0 #define PHY_ID_AQR107 0x03a1b4e0 +#define PHY_ID_AQCS109 0x03a1b5c2 #define PHY_ID_AQR405 0x03a1b4b0 -static int aquantia_config_aneg(struct phy_device *phydev) +#define MDIO_AN_TX_VEND_STATUS1 0xc800 +#define MDIO_AN_TX_VEND_STATUS1_10BASET (0x0 << 1) +#define MDIO_AN_TX_VEND_STATUS1_100BASETX (0x1 << 1) +#define MDIO_AN_TX_VEND_STATUS1_1000BASET (0x2 << 1) +#define MDIO_AN_TX_VEND_STATUS1_10GBASET (0x3 << 1) +#define MDIO_AN_TX_VEND_STATUS1_2500BASET (0x4 << 1) +#define MDIO_AN_TX_VEND_STATUS1_5000BASET (0x5 << 1) +#define MDIO_AN_TX_VEND_STATUS1_RATE_MASK (0x7 << 1) +#define MDIO_AN_TX_VEND_STATUS1_FULL_DUPLEX BIT(0) + +#define MDIO_AN_TX_VEND_INT_STATUS2 0xcc01 + +#define MDIO_AN_TX_VEND_INT_MASK2 0xd401 +#define MDIO_AN_TX_VEND_INT_MASK2_LINK BIT(0) + +/* Vendor specific 1, MDIO_MMD_VEND1 */ +#define VEND1_GLOBAL_INT_STD_STATUS 0xfc00 +#define VEND1_GLOBAL_INT_VEND_STATUS 0xfc01 + +#define VEND1_GLOBAL_INT_STD_MASK 0xff00 +#define VEND1_GLOBAL_INT_STD_MASK_PMA1 BIT(15) +#define VEND1_GLOBAL_INT_STD_MASK_PMA2 BIT(14) +#define VEND1_GLOBAL_INT_STD_MASK_PCS1 BIT(13) +#define VEND1_GLOBAL_INT_STD_MASK_PCS2 BIT(12) +#define VEND1_GLOBAL_INT_STD_MASK_PCS3 BIT(11) +#define VEND1_GLOBAL_INT_STD_MASK_PHY_XS1 BIT(10) +#define VEND1_GLOBAL_INT_STD_MASK_PHY_XS2 BIT(9) +#define VEND1_GLOBAL_INT_STD_MASK_AN1 BIT(8) +#define VEND1_GLOBAL_INT_STD_MASK_AN2 BIT(7) +#define VEND1_GLOBAL_INT_STD_MASK_GBE BIT(6) +#define VEND1_GLOBAL_INT_STD_MASK_ALL BIT(0) + +#define VEND1_GLOBAL_INT_VEND_MASK 0xff01 +#define VEND1_GLOBAL_INT_VEND_MASK_PMA BIT(15) +#define VEND1_GLOBAL_INT_VEND_MASK_PCS BIT(14) +#define VEND1_GLOBAL_INT_VEND_MASK_PHY_XS BIT(13) +#define VEND1_GLOBAL_INT_VEND_MASK_AN BIT(12) +#define VEND1_GLOBAL_INT_VEND_MASK_GBE BIT(11) +#define VEND1_GLOBAL_INT_VEND_MASK_GLOBAL1 BIT(2) +#define VEND1_GLOBAL_INT_VEND_MASK_GLOBAL2 BIT(1) +#define VEND1_GLOBAL_INT_VEND_MASK_GLOBAL3 BIT(0) + +static int aqr_config_aneg(struct phy_device *phydev) { linkmode_copy(phydev->supported, phy_10gbit_features); linkmode_copy(phydev->advertising, phydev->supported); @@ -30,44 +70,55 @@ static int aquantia_config_aneg(struct phy_device *phydev) return 0; } -static int aquantia_config_intr(struct phy_device *phydev) +static int aqr_config_intr(struct phy_device *phydev) { int err; if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { - err = phy_write_mmd(phydev, MDIO_MMD_AN, 0xd401, 1); + err = phy_write_mmd(phydev, MDIO_MMD_AN, + MDIO_AN_TX_VEND_INT_MASK2, + MDIO_AN_TX_VEND_INT_MASK2_LINK); if (err < 0) return err; - err = phy_write_mmd(phydev, MDIO_MMD_VEND1, 0xff00, 1); + err = phy_write_mmd(phydev, MDIO_MMD_VEND1, + VEND1_GLOBAL_INT_STD_MASK, + VEND1_GLOBAL_INT_STD_MASK_ALL); if (err < 0) return err; - err = phy_write_mmd(phydev, MDIO_MMD_VEND1, 0xff01, 0x1001); + err = phy_write_mmd(phydev, MDIO_MMD_VEND1, + VEND1_GLOBAL_INT_VEND_MASK, + VEND1_GLOBAL_INT_VEND_MASK_GLOBAL3 | + VEND1_GLOBAL_INT_VEND_MASK_AN); } else { - err = phy_write_mmd(phydev, MDIO_MMD_AN, 0xd401, 0); + err = phy_write_mmd(phydev, MDIO_MMD_AN, + MDIO_AN_TX_VEND_INT_MASK2, 0); if (err < 0) return err; - err = phy_write_mmd(phydev, MDIO_MMD_VEND1, 0xff00, 0); + err = phy_write_mmd(phydev, MDIO_MMD_VEND1, + VEND1_GLOBAL_INT_STD_MASK, 0); if (err < 0) return err; - err = phy_write_mmd(phydev, MDIO_MMD_VEND1, 0xff01, 0); + err = phy_write_mmd(phydev, MDIO_MMD_VEND1, + VEND1_GLOBAL_INT_VEND_MASK, 0); } return err; } -static int aquantia_ack_interrupt(struct phy_device *phydev) +static int aqr_ack_interrupt(struct phy_device *phydev) { int reg; - reg = phy_read_mmd(phydev, MDIO_MMD_AN, 0xcc01); + reg = phy_read_mmd(phydev, MDIO_MMD_AN, + MDIO_AN_TX_VEND_INT_STATUS2); return (reg < 0) ? reg : 0; } -static int aquantia_read_status(struct phy_device *phydev) +static int aqr_read_status(struct phy_device *phydev) { int reg; @@ -78,21 +129,20 @@ static int aquantia_read_status(struct phy_device *phydev) else phydev->link = 0; - reg = phy_read_mmd(phydev, MDIO_MMD_AN, 0xc800); + reg = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_TX_VEND_STATUS1); mdelay(10); - reg = phy_read_mmd(phydev, MDIO_MMD_AN, 0xc800); + reg = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_TX_VEND_STATUS1); - switch (reg) { - case 0x9: + switch (reg & MDIO_AN_TX_VEND_STATUS1_RATE_MASK) { + case MDIO_AN_TX_VEND_STATUS1_2500BASET: phydev->speed = SPEED_2500; break; - case 0x5: + case MDIO_AN_TX_VEND_STATUS1_1000BASET: phydev->speed = SPEED_1000; break; - case 0x3: + case MDIO_AN_TX_VEND_STATUS1_100BASETX: phydev->speed = SPEED_100; break; - case 0x7: default: phydev->speed = SPEED_10000; break; @@ -102,88 +152,93 @@ static int aquantia_read_status(struct phy_device *phydev) return 0; } -static struct phy_driver aquantia_driver[] = { +static struct phy_driver aqr_driver[] = { { - .phy_id = PHY_ID_AQ1202, - .phy_id_mask = 0xfffffff0, + PHY_ID_MATCH_MODEL(PHY_ID_AQ1202), .name = "Aquantia AQ1202", .features = PHY_10GBIT_FULL_FEATURES, .aneg_done = genphy_c45_aneg_done, - .config_aneg = aquantia_config_aneg, - .config_intr = aquantia_config_intr, - .ack_interrupt = aquantia_ack_interrupt, - .read_status = aquantia_read_status, + .config_aneg = aqr_config_aneg, + .config_intr = aqr_config_intr, + .ack_interrupt = aqr_ack_interrupt, + .read_status = aqr_read_status, }, { - .phy_id = PHY_ID_AQ2104, - .phy_id_mask = 0xfffffff0, + PHY_ID_MATCH_MODEL(PHY_ID_AQ2104), .name = "Aquantia AQ2104", .features = PHY_10GBIT_FULL_FEATURES, .aneg_done = genphy_c45_aneg_done, - .config_aneg = aquantia_config_aneg, - .config_intr = aquantia_config_intr, - .ack_interrupt = aquantia_ack_interrupt, - .read_status = aquantia_read_status, + .config_aneg = aqr_config_aneg, + .config_intr = aqr_config_intr, + .ack_interrupt = aqr_ack_interrupt, + .read_status = aqr_read_status, }, { - .phy_id = PHY_ID_AQR105, - .phy_id_mask = 0xfffffff0, + PHY_ID_MATCH_MODEL(PHY_ID_AQR105), .name = "Aquantia AQR105", .features = PHY_10GBIT_FULL_FEATURES, .aneg_done = genphy_c45_aneg_done, - .config_aneg = aquantia_config_aneg, - .config_intr = aquantia_config_intr, - .ack_interrupt = aquantia_ack_interrupt, - .read_status = aquantia_read_status, + .config_aneg = aqr_config_aneg, + .config_intr = aqr_config_intr, + .ack_interrupt = aqr_ack_interrupt, + .read_status = aqr_read_status, }, { - .phy_id = PHY_ID_AQR106, - .phy_id_mask = 0xfffffff0, + PHY_ID_MATCH_MODEL(PHY_ID_AQR106), .name = "Aquantia AQR106", .features = PHY_10GBIT_FULL_FEATURES, .aneg_done = genphy_c45_aneg_done, - .config_aneg = aquantia_config_aneg, - .config_intr = aquantia_config_intr, - .ack_interrupt = aquantia_ack_interrupt, - .read_status = aquantia_read_status, + .config_aneg = aqr_config_aneg, + .config_intr = aqr_config_intr, + .ack_interrupt = aqr_ack_interrupt, + .read_status = aqr_read_status, }, { - .phy_id = PHY_ID_AQR107, - .phy_id_mask = 0xfffffff0, + PHY_ID_MATCH_MODEL(PHY_ID_AQR107), .name = "Aquantia AQR107", .features = PHY_10GBIT_FULL_FEATURES, .aneg_done = genphy_c45_aneg_done, - .config_aneg = aquantia_config_aneg, - .config_intr = aquantia_config_intr, - .ack_interrupt = aquantia_ack_interrupt, - .read_status = aquantia_read_status, + .config_aneg = aqr_config_aneg, + .config_intr = aqr_config_intr, + .ack_interrupt = aqr_ack_interrupt, + .read_status = aqr_read_status, }, { - .phy_id = PHY_ID_AQR405, - .phy_id_mask = 0xfffffff0, + PHY_ID_MATCH_MODEL(PHY_ID_AQCS109), + .name = "Aquantia AQCS109", + .features = PHY_10GBIT_FULL_FEATURES, + .aneg_done = genphy_c45_aneg_done, + .config_aneg = aqr_config_aneg, + .config_intr = aqr_config_intr, + .ack_interrupt = aqr_ack_interrupt, + .read_status = aqr_read_status, +}, +{ + PHY_ID_MATCH_MODEL(PHY_ID_AQR405), .name = "Aquantia AQR405", .features = PHY_10GBIT_FULL_FEATURES, .aneg_done = genphy_c45_aneg_done, - .config_aneg = aquantia_config_aneg, - .config_intr = aquantia_config_intr, - .ack_interrupt = aquantia_ack_interrupt, - .read_status = aquantia_read_status, + .config_aneg = aqr_config_aneg, + .config_intr = aqr_config_intr, + .ack_interrupt = aqr_ack_interrupt, + .read_status = aqr_read_status, }, }; -module_phy_driver(aquantia_driver); +module_phy_driver(aqr_driver); -static struct mdio_device_id __maybe_unused aquantia_tbl[] = { - { PHY_ID_AQ1202, 0xfffffff0 }, - { PHY_ID_AQ2104, 0xfffffff0 }, - { PHY_ID_AQR105, 0xfffffff0 }, - { PHY_ID_AQR106, 0xfffffff0 }, - { PHY_ID_AQR107, 0xfffffff0 }, - { PHY_ID_AQR405, 0xfffffff0 }, +static struct mdio_device_id __maybe_unused aqr_tbl[] = { + { PHY_ID_MATCH_MODEL(PHY_ID_AQ1202) }, + { PHY_ID_MATCH_MODEL(PHY_ID_AQ2104) }, + { PHY_ID_MATCH_MODEL(PHY_ID_AQR105) }, + { PHY_ID_MATCH_MODEL(PHY_ID_AQR106) }, + { PHY_ID_MATCH_MODEL(PHY_ID_AQR107) }, + { PHY_ID_MATCH_MODEL(PHY_ID_AQCS109) }, + { PHY_ID_MATCH_MODEL(PHY_ID_AQR405) }, { } }; -MODULE_DEVICE_TABLE(mdio, aquantia_tbl); +MODULE_DEVICE_TABLE(mdio, aqr_tbl); MODULE_DESCRIPTION("Aquantia PHY driver"); MODULE_AUTHOR("Shaohui Xie <Shaohui.Xie@freescale.com>"); diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c index 25ef483bcc24..2fe2ebaf62d1 100644 --- a/drivers/net/phy/dp83640.c +++ b/drivers/net/phy/dp83640.c @@ -885,14 +885,14 @@ static void decode_txts(struct dp83640_private *dp83640, struct phy_txts *phy_txts) { struct skb_shared_hwtstamps shhwtstamps; + struct dp83640_skb_info *skb_info; struct sk_buff *skb; - u64 ns; u8 overflow; + u64 ns; /* We must already have the skb that triggered this. */ - +again: skb = skb_dequeue(&dp83640->tx_queue); - if (!skb) { pr_debug("have timestamp but tx_queue empty\n"); return; @@ -907,6 +907,11 @@ static void decode_txts(struct dp83640_private *dp83640, } return; } + skb_info = (struct dp83640_skb_info *)skb->cb; + if (time_after(jiffies, skb_info->tmo)) { + kfree_skb(skb); + goto again; + } ns = phy2txts(phy_txts); memset(&shhwtstamps, 0, sizeof(shhwtstamps)); @@ -1459,6 +1464,7 @@ static bool dp83640_rxtstamp(struct phy_device *phydev, static void dp83640_txtstamp(struct phy_device *phydev, struct sk_buff *skb, int type) { + struct dp83640_skb_info *skb_info = (struct dp83640_skb_info *)skb->cb; struct dp83640_private *dp83640 = phydev->priv; switch (dp83640->hwts_tx_en) { @@ -1471,6 +1477,7 @@ static void dp83640_txtstamp(struct phy_device *phydev, /* fall through */ case HWTSTAMP_TX_ON: skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; + skb_info->tmo = jiffies + SKB_TIMESTAMP_TIMEOUT; skb_queue_tail(&dp83640->tx_queue, skb); break; diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c index 8a8d9f606b3e..fc09c5c1a4de 100644 --- a/drivers/net/phy/dp83867.c +++ b/drivers/net/phy/dp83867.c @@ -127,17 +127,13 @@ static int dp83867_config_port_mirroring(struct phy_device *phydev) { struct dp83867_private *dp83867 = (struct dp83867_private *)phydev->priv; - u16 val; - - val = phy_read_mmd(phydev, DP83867_DEVADDR, DP83867_CFG4); if (dp83867->port_mirroring == DP83867_PORT_MIRROING_EN) - val |= DP83867_CFG4_PORT_MIRROR_EN; + phy_set_bits_mmd(phydev, DP83867_DEVADDR, DP83867_CFG4, + DP83867_CFG4_PORT_MIRROR_EN); else - val &= ~DP83867_CFG4_PORT_MIRROR_EN; - - phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_CFG4, val); - + phy_clear_bits_mmd(phydev, DP83867_DEVADDR, DP83867_CFG4, + DP83867_CFG4_PORT_MIRROR_EN); return 0; } @@ -222,11 +218,9 @@ static int dp83867_config_init(struct phy_device *phydev) } /* RX_DV/RX_CTRL strapped in mode 1 or mode 2 workaround */ - if (dp83867->rxctrl_strap_quirk) { - val = phy_read_mmd(phydev, DP83867_DEVADDR, DP83867_CFG4); - val &= ~BIT(7); - phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_CFG4, val); - } + if (dp83867->rxctrl_strap_quirk) + phy_clear_bits_mmd(phydev, DP83867_DEVADDR, DP83867_CFG4, + BIT(7)); if (phy_interface_is_rgmii(phydev)) { val = phy_read(phydev, MII_DP83867_PHYCTRL); @@ -275,17 +269,11 @@ static int dp83867_config_init(struct phy_device *phydev) phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_RGMIIDCTL, delay); - if (dp83867->io_impedance >= 0) { - val = phy_read_mmd(phydev, DP83867_DEVADDR, - DP83867_IO_MUX_CFG); - - val &= ~DP83867_IO_MUX_CFG_IO_IMPEDANCE_CTRL; - val |= dp83867->io_impedance & - DP83867_IO_MUX_CFG_IO_IMPEDANCE_CTRL; - - phy_write_mmd(phydev, DP83867_DEVADDR, - DP83867_IO_MUX_CFG, val); - } + if (dp83867->io_impedance >= 0) + phy_modify_mmd(phydev, DP83867_DEVADDR, DP83867_IO_MUX_CFG, + DP83867_IO_MUX_CFG_IO_IMPEDANCE_CTRL, + dp83867->io_impedance & + DP83867_IO_MUX_CFG_IO_IMPEDANCE_CTRL); } /* Enable Interrupt output INT_OE in CFG3 register */ @@ -299,12 +287,11 @@ static int dp83867_config_init(struct phy_device *phydev) dp83867_config_port_mirroring(phydev); /* Clock output selection if muxing property is set */ - if (dp83867->clk_output_sel != DP83867_CLK_O_SEL_REF_CLK) { - val = phy_read_mmd(phydev, DP83867_DEVADDR, DP83867_IO_MUX_CFG); - val &= ~DP83867_IO_MUX_CFG_CLK_O_SEL_MASK; - val |= (dp83867->clk_output_sel << DP83867_IO_MUX_CFG_CLK_O_SEL_SHIFT); - phy_write_mmd(phydev, DP83867_DEVADDR, DP83867_IO_MUX_CFG, val); - } + if (dp83867->clk_output_sel != DP83867_CLK_O_SEL_REF_CLK) + phy_modify_mmd(phydev, DP83867_DEVADDR, DP83867_IO_MUX_CFG, + DP83867_IO_MUX_CFG_CLK_O_SEL_MASK, + dp83867->clk_output_sel << + DP83867_IO_MUX_CFG_CLK_O_SEL_SHIFT); return 0; } diff --git a/drivers/net/phy/dp83tc811.c b/drivers/net/phy/dp83tc811.c index da13356999e5..e9704af1d239 100644 --- a/drivers/net/phy/dp83tc811.c +++ b/drivers/net/phy/dp83tc811.c @@ -144,11 +144,8 @@ static int dp83811_set_wol(struct phy_device *phydev, phy_write_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG, value); } else { - value = phy_read_mmd(phydev, DP83811_DEVADDR, - MII_DP83811_WOL_CFG); - value &= ~DP83811_WOL_EN; - phy_write_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG, - value); + phy_clear_bits_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG, + DP83811_WOL_EN); } return 0; @@ -328,14 +325,10 @@ static int dp83811_suspend(struct phy_device *phydev) static int dp83811_resume(struct phy_device *phydev) { - int value; - genphy_resume(phydev); - value = phy_read_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG); - - phy_write_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG, value | - DP83811_WOL_CLR_INDICATION); + phy_set_bits_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG, + DP83811_WOL_CLR_INDICATION); return 0; } diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c index 47a8cb574c45..b0d1368c3400 100644 --- a/drivers/net/phy/fixed_phy.c +++ b/drivers/net/phy/fixed_phy.c @@ -18,7 +18,7 @@ #include <linux/err.h> #include <linux/slab.h> #include <linux/of.h> -#include <linux/gpio.h> +#include <linux/gpio/consumer.h> #include <linux/seqlock.h> #include <linux/idr.h> #include <linux/netdevice.h> @@ -38,7 +38,7 @@ struct fixed_phy { bool no_carrier; int (*link_update)(struct net_device *, struct fixed_phy_status *); struct list_head node; - int link_gpio; + struct gpio_desc *link_gpiod; }; static struct platform_device *pdev; @@ -67,8 +67,8 @@ EXPORT_SYMBOL_GPL(fixed_phy_change_carrier); static void fixed_phy_update(struct fixed_phy *fp) { - if (!fp->no_carrier && gpio_is_valid(fp->link_gpio)) - fp->status.link = !!gpio_get_value_cansleep(fp->link_gpio); + if (!fp->no_carrier && fp->link_gpiod) + fp->status.link = !!gpiod_get_value_cansleep(fp->link_gpiod); } static int fixed_mdio_read(struct mii_bus *bus, int phy_addr, int reg_num) @@ -85,11 +85,11 @@ static int fixed_mdio_read(struct mii_bus *bus, int phy_addr, int reg_num) s = read_seqcount_begin(&fp->seqcount); fp->status.link = !fp->no_carrier; /* Issue callback if user registered it. */ - if (fp->link_update) { + if (fp->link_update) fp->link_update(fp->phydev->attached_dev, &fp->status); - fixed_phy_update(fp); - } + /* Check the GPIO for change in status */ + fixed_phy_update(fp); state = fp->status; } while (read_seqcount_retry(&fp->seqcount, s)); @@ -133,9 +133,9 @@ int fixed_phy_set_link_update(struct phy_device *phydev, } EXPORT_SYMBOL_GPL(fixed_phy_set_link_update); -int fixed_phy_add(unsigned int irq, int phy_addr, - struct fixed_phy_status *status, - int link_gpio) +static int fixed_phy_add_gpiod(unsigned int irq, int phy_addr, + struct fixed_phy_status *status, + struct gpio_desc *gpiod) { int ret; struct fixed_mdio_bus *fmb = &platform_fmb; @@ -156,24 +156,19 @@ int fixed_phy_add(unsigned int irq, int phy_addr, fp->addr = phy_addr; fp->status = *status; - fp->link_gpio = link_gpio; - - if (gpio_is_valid(fp->link_gpio)) { - ret = gpio_request_one(fp->link_gpio, GPIOF_DIR_IN, - "fixed-link-gpio-link"); - if (ret) - goto err_regs; - } + fp->link_gpiod = gpiod; fixed_phy_update(fp); list_add_tail(&fp->node, &fmb->phys); return 0; +} -err_regs: - kfree(fp); - return ret; +int fixed_phy_add(unsigned int irq, int phy_addr, + struct fixed_phy_status *status) { + + return fixed_phy_add_gpiod(irq, phy_addr, status, NULL); } EXPORT_SYMBOL_GPL(fixed_phy_add); @@ -187,8 +182,8 @@ static void fixed_phy_del(int phy_addr) list_for_each_entry_safe(fp, tmp, &fmb->phys, node) { if (fp->addr == phy_addr) { list_del(&fp->node); - if (gpio_is_valid(fp->link_gpio)) - gpio_free(fp->link_gpio); + if (fp->link_gpiod) + gpiod_put(fp->link_gpiod); kfree(fp); ida_simple_remove(&phy_fixed_ida, phy_addr); return; @@ -196,10 +191,48 @@ static void fixed_phy_del(int phy_addr) } } -struct phy_device *fixed_phy_register(unsigned int irq, - struct fixed_phy_status *status, - int link_gpio, - struct device_node *np) +#ifdef CONFIG_OF_GPIO +static struct gpio_desc *fixed_phy_get_gpiod(struct device_node *np) +{ + struct device_node *fixed_link_node; + struct gpio_desc *gpiod; + + if (!np) + return NULL; + + fixed_link_node = of_get_child_by_name(np, "fixed-link"); + if (!fixed_link_node) + return NULL; + + /* + * As the fixed link is just a device tree node without any + * Linux device associated with it, we simply have obtain + * the GPIO descriptor from the device tree like this. + */ + gpiod = gpiod_get_from_of_node(fixed_link_node, "link-gpios", 0, + GPIOD_IN, "mdio"); + of_node_put(fixed_link_node); + if (IS_ERR(gpiod)) { + if (PTR_ERR(gpiod) == -EPROBE_DEFER) + return gpiod; + pr_err("error getting GPIO for fixed link %pOF, proceed without\n", + fixed_link_node); + gpiod = NULL; + } + + return gpiod; +} +#else +static struct gpio_desc *fixed_phy_get_gpiod(struct device_node *np) +{ + return NULL; +} +#endif + +static struct phy_device *__fixed_phy_register(unsigned int irq, + struct fixed_phy_status *status, + struct device_node *np, + struct gpio_desc *gpiod) { struct fixed_mdio_bus *fmb = &platform_fmb; struct phy_device *phy; @@ -209,12 +242,19 @@ struct phy_device *fixed_phy_register(unsigned int irq, if (!fmb->mii_bus || fmb->mii_bus->state != MDIOBUS_REGISTERED) return ERR_PTR(-EPROBE_DEFER); + /* Check if we have a GPIO associated with this fixed phy */ + if (!gpiod) { + gpiod = fixed_phy_get_gpiod(np); + if (IS_ERR(gpiod)) + return ERR_CAST(gpiod); + } + /* Get the next available PHY address, up to PHY_MAX_ADDR */ phy_addr = ida_simple_get(&phy_fixed_ida, 0, PHY_MAX_ADDR, GFP_KERNEL); if (phy_addr < 0) return ERR_PTR(phy_addr); - ret = fixed_phy_add(irq, phy_addr, status, link_gpio); + ret = fixed_phy_add_gpiod(irq, phy_addr, status, gpiod); if (ret < 0) { ida_simple_remove(&phy_fixed_ida, phy_addr); return ERR_PTR(ret); @@ -270,8 +310,24 @@ struct phy_device *fixed_phy_register(unsigned int irq, return phy; } + +struct phy_device *fixed_phy_register(unsigned int irq, + struct fixed_phy_status *status, + struct device_node *np) +{ + return __fixed_phy_register(irq, status, np, NULL); +} EXPORT_SYMBOL_GPL(fixed_phy_register); +struct phy_device * +fixed_phy_register_with_gpiod(unsigned int irq, + struct fixed_phy_status *status, + struct gpio_desc *gpiod) +{ + return __fixed_phy_register(irq, status, NULL, gpiod); +} +EXPORT_SYMBOL_GPL(fixed_phy_register_with_gpiod); + void fixed_phy_unregister(struct phy_device *phy) { phy_device_remove(phy); diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 90f44ba8aca7..3ccba37bd6dd 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -842,7 +842,6 @@ static int m88e1510_config_init(struct phy_device *phydev) /* SGMII-to-Copper mode initialization */ if (phydev->interface == PHY_INTERFACE_MODE_SGMII) { - /* Select page 18 */ err = marvell_set_page(phydev, 18); if (err < 0) @@ -865,21 +864,6 @@ static int m88e1510_config_init(struct phy_device *phydev) err = marvell_set_page(phydev, MII_MARVELL_COPPER_PAGE); if (err < 0) return err; - - /* There appears to be a bug in the 88e1512 when used in - * SGMII to copper mode, where the AN advertisement register - * clears the pause bits each time a negotiation occurs. - * This means we can never be truely sure what was advertised, - * so disable Pause support. - */ - linkmode_clear_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, - phydev->supported); - linkmode_clear_bit(ETHTOOL_LINK_MODE_Pause_BIT, - phydev->supported); - linkmode_clear_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, - phydev->advertising); - linkmode_clear_bit(ETHTOOL_LINK_MODE_Pause_BIT, - phydev->advertising); } return m88e1318_config_init(phydev); diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c index 38cfc923a88a..f9e0a2fc0277 100644 --- a/drivers/net/phy/marvell10g.c +++ b/drivers/net/phy/marvell10g.c @@ -58,24 +58,6 @@ struct mv3310_priv { char *hwmon_name; }; -static int mv3310_modify(struct phy_device *phydev, int devad, u16 reg, - u16 mask, u16 bits) -{ - int old, val, ret; - - old = phy_read_mmd(phydev, devad, reg); - if (old < 0) - return old; - - val = (old & ~mask) | (bits & mask); - if (val == old) - return 0; - - ret = phy_write_mmd(phydev, devad, reg, val); - - return ret < 0 ? ret : 1; -} - #ifdef CONFIG_HWMON static umode_t mv3310_hwmon_is_visible(const void *data, enum hwmon_sensor_types type, @@ -159,10 +141,9 @@ static int mv3310_hwmon_config(struct phy_device *phydev, bool enable) return ret; val = enable ? MV_V2_TEMP_CTRL_SAMPLE : MV_V2_TEMP_CTRL_DISABLE; - ret = mv3310_modify(phydev, MDIO_MMD_VEND2, MV_V2_TEMP_CTRL, - MV_V2_TEMP_CTRL_MASK, val); - return ret < 0 ? ret : 0; + return phy_modify_mmd(phydev, MDIO_MMD_VEND2, MV_V2_TEMP_CTRL, + MV_V2_TEMP_CTRL_MASK, val); } static void mv3310_hwmon_disable(void *data) @@ -252,8 +233,7 @@ static int mv3310_resume(struct phy_device *phydev) static int mv3310_config_init(struct phy_device *phydev) { - __ETHTOOL_DECLARE_LINK_MODE_MASK(supported) = { 0, }; - int val; + int ret, val; /* Check that the PHY interface type is compatible */ if (phydev->interface != PHY_INTERFACE_MODE_SGMII && @@ -262,83 +242,19 @@ static int mv3310_config_init(struct phy_device *phydev) phydev->interface != PHY_INTERFACE_MODE_10GKR) return -ENODEV; - __set_bit(ETHTOOL_LINK_MODE_Pause_BIT, supported); - __set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, supported); - if (phydev->c45_ids.devices_in_package & MDIO_DEVS_AN) { val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_STAT1); if (val < 0) return val; if (val & MDIO_AN_STAT1_ABLE) - __set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, supported); - } - - val = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_STAT2); - if (val < 0) - return val; - - /* Ethtool does not support the WAN mode bits */ - if (val & (MDIO_PMA_STAT2_10GBSR | MDIO_PMA_STAT2_10GBLR | - MDIO_PMA_STAT2_10GBER | MDIO_PMA_STAT2_10GBLX4 | - MDIO_PMA_STAT2_10GBSW | MDIO_PMA_STAT2_10GBLW | - MDIO_PMA_STAT2_10GBEW)) - __set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, supported); - if (val & MDIO_PMA_STAT2_10GBSR) - __set_bit(ETHTOOL_LINK_MODE_10000baseSR_Full_BIT, supported); - if (val & MDIO_PMA_STAT2_10GBLR) - __set_bit(ETHTOOL_LINK_MODE_10000baseLR_Full_BIT, supported); - if (val & MDIO_PMA_STAT2_10GBER) - __set_bit(ETHTOOL_LINK_MODE_10000baseER_Full_BIT, supported); - - if (val & MDIO_PMA_STAT2_EXTABLE) { - val = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_EXTABLE); - if (val < 0) - return val; - - if (val & (MDIO_PMA_EXTABLE_10GBT | MDIO_PMA_EXTABLE_1000BT | - MDIO_PMA_EXTABLE_100BTX | MDIO_PMA_EXTABLE_10BT)) - __set_bit(ETHTOOL_LINK_MODE_TP_BIT, supported); - if (val & MDIO_PMA_EXTABLE_10GBLRM) - __set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, supported); - if (val & (MDIO_PMA_EXTABLE_10GBKX4 | MDIO_PMA_EXTABLE_10GBKR | - MDIO_PMA_EXTABLE_1000BKX)) - __set_bit(ETHTOOL_LINK_MODE_Backplane_BIT, supported); - if (val & MDIO_PMA_EXTABLE_10GBLRM) - __set_bit(ETHTOOL_LINK_MODE_10000baseLRM_Full_BIT, - supported); - if (val & MDIO_PMA_EXTABLE_10GBT) - __set_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT, - supported); - if (val & MDIO_PMA_EXTABLE_10GBKX4) - __set_bit(ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT, - supported); - if (val & MDIO_PMA_EXTABLE_10GBKR) - __set_bit(ETHTOOL_LINK_MODE_10000baseKR_Full_BIT, - supported); - if (val & MDIO_PMA_EXTABLE_1000BT) - __set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, - supported); - if (val & MDIO_PMA_EXTABLE_1000BKX) - __set_bit(ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, - supported); - if (val & MDIO_PMA_EXTABLE_100BTX) { - __set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, - supported); - __set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, - supported); - } - if (val & MDIO_PMA_EXTABLE_10BT) { - __set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, - supported); - __set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, - supported); - } + __set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, + phydev->supported); } - linkmode_copy(phydev->supported, supported); - linkmode_and(phydev->advertising, phydev->advertising, - phydev->supported); + ret = genphy_c45_pma_read_abilities(phydev); + if (ret) + return ret; return 0; } @@ -360,39 +276,32 @@ static int mv3310_config_aneg(struct phy_device *phydev) return genphy_c45_an_disable_aneg(phydev); } - linkmode_and(phydev->advertising, phydev->advertising, - phydev->supported); - - ret = mv3310_modify(phydev, MDIO_MMD_AN, MDIO_AN_ADVERTISE, - ADVERTISE_ALL | ADVERTISE_100BASE4 | - ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM, - linkmode_adv_to_mii_adv_t(phydev->advertising)); + ret = genphy_c45_an_config_aneg(phydev); if (ret < 0) return ret; if (ret > 0) changed = true; + /* Clause 45 has no standardized support for 1000BaseT, therefore + * use vendor registers for this mode. + */ reg = linkmode_adv_to_mii_ctrl1000_t(phydev->advertising); - ret = mv3310_modify(phydev, MDIO_MMD_AN, MV_AN_CTRL1000, - ADVERTISE_1000FULL | ADVERTISE_1000HALF, reg); + ret = phy_modify_mmd_changed(phydev, MDIO_MMD_AN, MV_AN_CTRL1000, + ADVERTISE_1000FULL | ADVERTISE_1000HALF, reg); if (ret < 0) return ret; if (ret > 0) changed = true; - /* 10G control register */ - if (linkmode_test_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT, - phydev->advertising)) - reg = MDIO_AN_10GBT_CTRL_ADV10G; - else - reg = 0; + if (!changed) { + /* Configure and restart aneg if it wasn't set before */ + ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_CTRL1); + if (ret < 0) + return ret; - ret = mv3310_modify(phydev, MDIO_MMD_AN, MDIO_AN_10GBT_CTRL, - MDIO_AN_10GBT_CTRL_ADV10G, reg); - if (ret < 0) - return ret; - if (ret > 0) - changed = true; + if (!(ret & MDIO_AN_CTRL1_ENABLE)) + changed = 1; + } if (changed) ret = genphy_c45_restart_aneg(phydev); @@ -446,16 +355,8 @@ static int mv3310_read_10gbr_status(struct phy_device *phydev) static int mv3310_read_status(struct phy_device *phydev) { - u32 mmd_mask = phydev->c45_ids.devices_in_package; int val; - /* The vendor devads do not report link status. Avoid the PHYXS - * instance as there are three, and its status depends on the MAC - * being appropriately configured for the negotiated speed. - */ - mmd_mask &= ~(BIT(MDIO_MMD_VEND1) | BIT(MDIO_MMD_VEND2) | - BIT(MDIO_MMD_PHYXS)); - phydev->speed = SPEED_UNKNOWN; phydev->duplex = DUPLEX_UNKNOWN; linkmode_zero(phydev->lp_advertising); @@ -471,12 +372,10 @@ static int mv3310_read_status(struct phy_device *phydev) if (val & MDIO_STAT1_LSTATUS) return mv3310_read_10gbr_status(phydev); - val = genphy_c45_read_link(phydev, mmd_mask); + val = genphy_c45_read_link(phydev); if (val < 0) return val; - phydev->link = val > 0 ? 1 : 0; - val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_STAT1); if (val < 0) return val; diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c index 03af927fa5ad..e17672bd180e 100644 --- a/drivers/net/phy/phy-c45.c +++ b/drivers/net/phy/phy-c45.c @@ -47,6 +47,16 @@ int genphy_c45_pma_setup_forced(struct phy_device *phydev) /* Assume 1000base-T */ ctrl2 |= MDIO_PMA_CTRL2_1000BT; break; + case SPEED_2500: + ctrl1 |= MDIO_CTRL1_SPEED2_5G; + /* Assume 2.5Gbase-T */ + ctrl2 |= MDIO_PMA_CTRL2_2_5GBT; + break; + case SPEED_5000: + ctrl1 |= MDIO_CTRL1_SPEED5G; + /* Assume 5Gbase-T */ + ctrl2 |= MDIO_PMA_CTRL2_5GBT; + break; case SPEED_10000: ctrl1 |= MDIO_CTRL1_SPEED10G; /* Assume 10Gbase-T */ @@ -65,6 +75,50 @@ int genphy_c45_pma_setup_forced(struct phy_device *phydev) EXPORT_SYMBOL_GPL(genphy_c45_pma_setup_forced); /** + * genphy_c45_an_config_aneg - configure advertisement registers + * @phydev: target phy_device struct + * + * Configure advertisement registers based on modes set in phydev->advertising + * + * Returns negative errno code on failure, 0 if advertisement didn't change, + * or 1 if advertised modes changed. + */ +int genphy_c45_an_config_aneg(struct phy_device *phydev) +{ + int changed = 0, ret; + u32 adv; + + linkmode_and(phydev->advertising, phydev->advertising, + phydev->supported); + + adv = linkmode_adv_to_mii_adv_t(phydev->advertising); + + ret = phy_modify_mmd(phydev, MDIO_MMD_AN, MDIO_AN_ADVERTISE, + ADVERTISE_ALL | ADVERTISE_100BASE4 | + ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM, + adv); + if (ret < 0) + return ret; + if (ret > 0) + changed = 1; + + adv = linkmode_adv_to_mii_10gbt_adv_t(phydev->advertising); + + ret = phy_modify_mmd(phydev, MDIO_MMD_AN, MDIO_AN_10GBT_CTRL, + MDIO_AN_10GBT_CTRL_ADV10G | + MDIO_AN_10GBT_CTRL_ADV5G | + MDIO_AN_10GBT_CTRL_ADV2_5G, + adv); + if (ret < 0) + return ret; + if (ret > 0) + changed = 1; + + return changed; +} +EXPORT_SYMBOL_GPL(genphy_c45_an_config_aneg); + +/** * genphy_c45_an_disable_aneg - disable auto-negotiation * @phydev: target phy_device struct * @@ -75,15 +129,9 @@ EXPORT_SYMBOL_GPL(genphy_c45_pma_setup_forced); */ int genphy_c45_an_disable_aneg(struct phy_device *phydev) { - int val; - val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_CTRL1); - if (val < 0) - return val; - - val &= ~(MDIO_AN_CTRL1_ENABLE | MDIO_AN_CTRL1_RESTART); - - return phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_CTRL1, val); + return phy_clear_bits_mmd(phydev, MDIO_MMD_AN, MDIO_CTRL1, + MDIO_AN_CTRL1_ENABLE | MDIO_AN_CTRL1_RESTART); } EXPORT_SYMBOL_GPL(genphy_c45_an_disable_aneg); @@ -97,15 +145,8 @@ EXPORT_SYMBOL_GPL(genphy_c45_an_disable_aneg); */ int genphy_c45_restart_aneg(struct phy_device *phydev) { - int val; - - val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_CTRL1); - if (val < 0) - return val; - - val |= MDIO_AN_CTRL1_ENABLE | MDIO_AN_CTRL1_RESTART; - - return phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_CTRL1, val); + return phy_set_bits_mmd(phydev, MDIO_MMD_AN, MDIO_CTRL1, + MDIO_AN_CTRL1_ENABLE | MDIO_AN_CTRL1_RESTART); } EXPORT_SYMBOL_GPL(genphy_c45_restart_aneg); @@ -131,25 +172,40 @@ EXPORT_SYMBOL_GPL(genphy_c45_aneg_done); /** * genphy_c45_read_link - read the overall link status from the MMDs * @phydev: target phy_device struct - * @mmd_mask: MMDs to read status from * * Read the link status from the specified MMDs, and if they all indicate - * that the link is up, return positive. If an error is encountered, + * that the link is up, set phydev->link to 1. If an error is encountered, * a negative errno will be returned, otherwise zero. */ -int genphy_c45_read_link(struct phy_device *phydev, u32 mmd_mask) +int genphy_c45_read_link(struct phy_device *phydev) { + u32 mmd_mask = phydev->c45_ids.devices_in_package; int val, devad; bool link = true; - while (mmd_mask) { + /* The vendor devads and C22EXT do not report link status. Avoid the + * PHYXS instance as its status may depend on the MAC being + * appropriately configured for the negotiated speed. + */ + mmd_mask &= ~(MDIO_DEVS_VEND1 | MDIO_DEVS_VEND2 | MDIO_DEVS_C22EXT | + MDIO_DEVS_PHYXS); + + while (mmd_mask && link) { devad = __ffs(mmd_mask); mmd_mask &= ~BIT(devad); /* The link state is latched low so that momentary link - * drops can be detected. Do not double-read the status - * register if the link is down. + * drops can be detected. Do not double-read the status + * in polling mode to detect such short link drops. */ + if (!phy_polling_mode(phydev)) { + val = phy_read_mmd(phydev, devad, MDIO_STAT1); + if (val < 0) + return val; + else if (val & MDIO_STAT1_LSTATUS) + continue; + } + val = phy_read_mmd(phydev, devad, MDIO_STAT1); if (val < 0) return val; @@ -158,7 +214,9 @@ int genphy_c45_read_link(struct phy_device *phydev, u32 mmd_mask) link = false; } - return link; + phydev->link = link; + + return 0; } EXPORT_SYMBOL_GPL(genphy_c45_read_link); @@ -190,6 +248,12 @@ int genphy_c45_read_lpa(struct phy_device *phydev) if (val < 0) return val; + if (val & MDIO_AN_10GBT_STAT_LP2_5G) + linkmode_set_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT, + phydev->lp_advertising); + if (val & MDIO_AN_10GBT_STAT_LP5G) + linkmode_set_bit(ETHTOOL_LINK_MODE_5000baseT_Full_BIT, + phydev->lp_advertising); if (val & MDIO_AN_10GBT_STAT_LP10G) linkmode_set_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT, phydev->lp_advertising); @@ -220,6 +284,12 @@ int genphy_c45_read_pma(struct phy_device *phydev) case MDIO_PMA_CTRL1_SPEED1000: phydev->speed = SPEED_1000; break; + case MDIO_CTRL1_SPEED2_5G: + phydev->speed = SPEED_2500; + break; + case MDIO_CTRL1_SPEED5G: + phydev->speed = SPEED_5000; + break; case MDIO_CTRL1_SPEED10G: phydev->speed = SPEED_10000; break; @@ -267,6 +337,95 @@ int genphy_c45_read_mdix(struct phy_device *phydev) } EXPORT_SYMBOL_GPL(genphy_c45_read_mdix); +/** + * genphy_c45_pma_read_abilities - read supported link modes from PMA + * @phydev: target phy_device struct + * + * Read the supported link modes from the PMA Status 2 (1.8) register. If bit + * 1.8.9 is set, the list of supported modes is build using the values in the + * PMA Extended Abilities (1.11) register, indicating 1000BASET an 10G related + * modes. If bit 1.11.14 is set, then the list is also extended with the modes + * in the 2.5G/5G PMA Extended register (1.21), indicating if 2.5GBASET and + * 5GBASET are supported. + */ +int genphy_c45_pma_read_abilities(struct phy_device *phydev) +{ + int val; + + val = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_STAT2); + if (val < 0) + return val; + + linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseSR_Full_BIT, + phydev->supported, + val & MDIO_PMA_STAT2_10GBSR); + + linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseLR_Full_BIT, + phydev->supported, + val & MDIO_PMA_STAT2_10GBLR); + + linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseER_Full_BIT, + phydev->supported, + val & MDIO_PMA_STAT2_10GBER); + + if (val & MDIO_PMA_STAT2_EXTABLE) { + val = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, MDIO_PMA_EXTABLE); + if (val < 0) + return val; + + linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseLRM_Full_BIT, + phydev->supported, + val & MDIO_PMA_EXTABLE_10GBLRM); + linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT, + phydev->supported, + val & MDIO_PMA_EXTABLE_10GBT); + linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT, + phydev->supported, + val & MDIO_PMA_EXTABLE_10GBKX4); + linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseKR_Full_BIT, + phydev->supported, + val & MDIO_PMA_EXTABLE_10GBKR); + linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, + phydev->supported, + val & MDIO_PMA_EXTABLE_1000BT); + linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, + phydev->supported, + val & MDIO_PMA_EXTABLE_1000BKX); + + linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, + phydev->supported, + val & MDIO_PMA_EXTABLE_100BTX); + linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, + phydev->supported, + val & MDIO_PMA_EXTABLE_100BTX); + + linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, + phydev->supported, + val & MDIO_PMA_EXTABLE_10BT); + linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, + phydev->supported, + val & MDIO_PMA_EXTABLE_10BT); + + if (val & MDIO_PMA_EXTABLE_NBT) { + val = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, + MDIO_PMA_NG_EXTABLE); + if (val < 0) + return val; + + linkmode_mod_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT, + phydev->supported, + val & MDIO_PMA_NG_EXTABLE_2_5GBT); + + linkmode_mod_bit(ETHTOOL_LINK_MODE_5000baseT_Full_BIT, + phydev->supported, + val & MDIO_PMA_NG_EXTABLE_5GBT); + } + } + + return 0; +} +EXPORT_SYMBOL_GPL(genphy_c45_pma_read_abilities); + /* The gen10g_* functions are the old Clause 45 stub */ int gen10g_config_aneg(struct phy_device *phydev) @@ -277,21 +436,11 @@ EXPORT_SYMBOL_GPL(gen10g_config_aneg); int gen10g_read_status(struct phy_device *phydev) { - u32 mmd_mask = phydev->c45_ids.devices_in_package; - int ret; - /* For now just lie and say it's 10G all the time */ phydev->speed = SPEED_10000; phydev->duplex = DUPLEX_FULL; - /* Avoid reading the vendor MMDs */ - mmd_mask &= ~(BIT(MDIO_MMD_VEND1) | BIT(MDIO_MMD_VEND2)); - - ret = genphy_c45_read_link(phydev, mmd_mask); - - phydev->link = ret > 0 ? 1 : 0; - - return 0; + return genphy_c45_read_link(phydev); } EXPORT_SYMBOL_GPL(gen10g_read_status); diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c index 909b3344babf..5016cd5fd7c7 100644 --- a/drivers/net/phy/phy-core.c +++ b/drivers/net/phy/phy-core.c @@ -4,6 +4,7 @@ */ #include <linux/export.h> #include <linux/phy.h> +#include <linux/of.h> const char *phy_speed_to_str(int speed) { @@ -338,6 +339,77 @@ size_t phy_speeds(unsigned int *speeds, size_t size, return count; } +static int __set_phy_supported(struct phy_device *phydev, u32 max_speed) +{ + const struct phy_setting *p; + int i; + + for (i = 0, p = settings; i < ARRAY_SIZE(settings); i++, p++) { + if (p->speed > max_speed) + linkmode_clear_bit(p->bit, phydev->supported); + else + break; + } + + return 0; +} + +int phy_set_max_speed(struct phy_device *phydev, u32 max_speed) +{ + int err; + + err = __set_phy_supported(phydev, max_speed); + if (err) + return err; + + linkmode_copy(phydev->advertising, phydev->supported); + + return 0; +} +EXPORT_SYMBOL(phy_set_max_speed); + +void of_set_phy_supported(struct phy_device *phydev) +{ + struct device_node *node = phydev->mdio.dev.of_node; + u32 max_speed; + + if (!IS_ENABLED(CONFIG_OF_MDIO)) + return; + + if (!node) + return; + + if (!of_property_read_u32(node, "max-speed", &max_speed)) + __set_phy_supported(phydev, max_speed); +} + +void of_set_phy_eee_broken(struct phy_device *phydev) +{ + struct device_node *node = phydev->mdio.dev.of_node; + u32 broken = 0; + + if (!IS_ENABLED(CONFIG_OF_MDIO)) + return; + + if (!node) + return; + + if (of_property_read_bool(node, "eee-broken-100tx")) + broken |= MDIO_EEE_100TX; + if (of_property_read_bool(node, "eee-broken-1000t")) + broken |= MDIO_EEE_1000T; + if (of_property_read_bool(node, "eee-broken-10gt")) + broken |= MDIO_EEE_10GT; + if (of_property_read_bool(node, "eee-broken-1000kx")) + broken |= MDIO_EEE_1000KX; + if (of_property_read_bool(node, "eee-broken-10gkx4")) + broken |= MDIO_EEE_10GKX4; + if (of_property_read_bool(node, "eee-broken-10gkr")) + broken |= MDIO_EEE_10GKR; + + phydev->eee_broken_modes = broken; +} + /** * phy_resolve_aneg_linkmode - resolve the advertisements into phy settings * @phydev: The phy_device struct @@ -349,45 +421,16 @@ size_t phy_speeds(unsigned int *speeds, size_t size, void phy_resolve_aneg_linkmode(struct phy_device *phydev) { __ETHTOOL_DECLARE_LINK_MODE_MASK(common); + int i; linkmode_and(common, phydev->lp_advertising, phydev->advertising); - if (linkmode_test_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT, common)) { - phydev->speed = SPEED_10000; - phydev->duplex = DUPLEX_FULL; - } else if (linkmode_test_bit(ETHTOOL_LINK_MODE_5000baseT_Full_BIT, - common)) { - phydev->speed = SPEED_5000; - phydev->duplex = DUPLEX_FULL; - } else if (linkmode_test_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT, - common)) { - phydev->speed = SPEED_2500; - phydev->duplex = DUPLEX_FULL; - } else if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, - common)) { - phydev->speed = SPEED_1000; - phydev->duplex = DUPLEX_FULL; - } else if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, - common)) { - phydev->speed = SPEED_1000; - phydev->duplex = DUPLEX_HALF; - } else if (linkmode_test_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, - common)) { - phydev->speed = SPEED_100; - phydev->duplex = DUPLEX_FULL; - } else if (linkmode_test_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, - common)) { - phydev->speed = SPEED_100; - phydev->duplex = DUPLEX_HALF; - } else if (linkmode_test_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, - common)) { - phydev->speed = SPEED_10; - phydev->duplex = DUPLEX_FULL; - } else if (linkmode_test_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, - common)) { - phydev->speed = SPEED_10; - phydev->duplex = DUPLEX_HALF; - } + for (i = 0; i < ARRAY_SIZE(settings); i++) + if (test_bit(settings[i].bit, common)) { + phydev->speed = settings[i].speed; + phydev->duplex = settings[i].duplex; + break; + } if (phydev->duplex == DUPLEX_FULL) { phydev->pause = linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, @@ -414,15 +457,15 @@ static void mmd_phy_indirect(struct mii_bus *bus, int phy_addr, int devad, } /** - * phy_read_mmd - Convenience function for reading a register + * __phy_read_mmd - Convenience function for reading a register * from an MMD on a given PHY. * @phydev: The phy_device struct * @devad: The MMD to read from (0..31) * @regnum: The register on the MMD to read (0..65535) * - * Same rules as for phy_read(); + * Same rules as for __phy_read(); */ -int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum) +int __phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum) { int val; @@ -434,33 +477,52 @@ int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum) } else if (phydev->is_c45) { u32 addr = MII_ADDR_C45 | (devad << 16) | (regnum & 0xffff); - val = mdiobus_read(phydev->mdio.bus, phydev->mdio.addr, addr); + val = __mdiobus_read(phydev->mdio.bus, phydev->mdio.addr, addr); } else { struct mii_bus *bus = phydev->mdio.bus; int phy_addr = phydev->mdio.addr; - mutex_lock(&bus->mdio_lock); mmd_phy_indirect(bus, phy_addr, devad, regnum); /* Read the content of the MMD's selected register */ val = __mdiobus_read(bus, phy_addr, MII_MMD_DATA); - mutex_unlock(&bus->mdio_lock); } return val; } +EXPORT_SYMBOL(__phy_read_mmd); + +/** + * phy_read_mmd - Convenience function for reading a register + * from an MMD on a given PHY. + * @phydev: The phy_device struct + * @devad: The MMD to read from + * @regnum: The register on the MMD to read + * + * Same rules as for phy_read(); + */ +int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum) +{ + int ret; + + mutex_lock(&phydev->mdio.bus->mdio_lock); + ret = __phy_read_mmd(phydev, devad, regnum); + mutex_unlock(&phydev->mdio.bus->mdio_lock); + + return ret; +} EXPORT_SYMBOL(phy_read_mmd); /** - * phy_write_mmd - Convenience function for writing a register + * __phy_write_mmd - Convenience function for writing a register * on an MMD on a given PHY. * @phydev: The phy_device struct * @devad: The MMD to read from * @regnum: The register on the MMD to read * @val: value to write to @regnum * - * Same rules as for phy_write(); + * Same rules as for __phy_write(); */ -int phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val) +int __phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val) { int ret; @@ -472,27 +534,47 @@ int phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val) } else if (phydev->is_c45) { u32 addr = MII_ADDR_C45 | (devad << 16) | (regnum & 0xffff); - ret = mdiobus_write(phydev->mdio.bus, phydev->mdio.addr, - addr, val); + ret = __mdiobus_write(phydev->mdio.bus, phydev->mdio.addr, + addr, val); } else { struct mii_bus *bus = phydev->mdio.bus; int phy_addr = phydev->mdio.addr; - mutex_lock(&bus->mdio_lock); mmd_phy_indirect(bus, phy_addr, devad, regnum); /* Write the data into MMD's selected register */ __mdiobus_write(bus, phy_addr, MII_MMD_DATA, val); - mutex_unlock(&bus->mdio_lock); ret = 0; } return ret; } +EXPORT_SYMBOL(__phy_write_mmd); + +/** + * phy_write_mmd - Convenience function for writing a register + * on an MMD on a given PHY. + * @phydev: The phy_device struct + * @devad: The MMD to read from + * @regnum: The register on the MMD to read + * @val: value to write to @regnum + * + * Same rules as for phy_write(); + */ +int phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val) +{ + int ret; + + mutex_lock(&phydev->mdio.bus->mdio_lock); + ret = __phy_write_mmd(phydev, devad, regnum, val); + mutex_unlock(&phydev->mdio.bus->mdio_lock); + + return ret; +} EXPORT_SYMBOL(phy_write_mmd); /** - * __phy_modify() - Convenience function for modifying a PHY register + * __phy_modify_changed() - Convenience function for modifying a PHY register * @phydev: a pointer to a &struct phy_device * @regnum: register number * @mask: bit mask of bits to clear @@ -500,16 +582,69 @@ EXPORT_SYMBOL(phy_write_mmd); * * Unlocked helper function which allows a PHY register to be modified as * new register value = (old register value & ~mask) | set + * + * Returns negative errno, 0 if there was no change, and 1 in case of change */ -int __phy_modify(struct phy_device *phydev, u32 regnum, u16 mask, u16 set) +int __phy_modify_changed(struct phy_device *phydev, u32 regnum, u16 mask, + u16 set) { - int ret; + int new, ret; ret = __phy_read(phydev, regnum); if (ret < 0) return ret; - ret = __phy_write(phydev, regnum, (ret & ~mask) | set); + new = (ret & ~mask) | set; + if (new == ret) + return 0; + + ret = __phy_write(phydev, regnum, new); + + return ret < 0 ? ret : 1; +} +EXPORT_SYMBOL_GPL(__phy_modify_changed); + +/** + * phy_modify_changed - Function for modifying a PHY register + * @phydev: the phy_device struct + * @regnum: register number to modify + * @mask: bit mask of bits to clear + * @set: new value of bits set in mask to write to @regnum + * + * NOTE: MUST NOT be called from interrupt context, + * because the bus read/write functions may wait for an interrupt + * to conclude the operation. + * + * Returns negative errno, 0 if there was no change, and 1 in case of change + */ +int phy_modify_changed(struct phy_device *phydev, u32 regnum, u16 mask, u16 set) +{ + int ret; + + mutex_lock(&phydev->mdio.bus->mdio_lock); + ret = __phy_modify_changed(phydev, regnum, mask, set); + mutex_unlock(&phydev->mdio.bus->mdio_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(phy_modify_changed); + +/** + * __phy_modify - Convenience function for modifying a PHY register + * @phydev: the phy_device struct + * @regnum: register number to modify + * @mask: bit mask of bits to clear + * @set: new value of bits set in mask to write to @regnum + * + * NOTE: MUST NOT be called from interrupt context, + * because the bus read/write functions may wait for an interrupt + * to conclude the operation. + */ +int __phy_modify(struct phy_device *phydev, u32 regnum, u16 mask, u16 set) +{ + int ret; + + ret = __phy_modify_changed(phydev, regnum, mask, set); return ret < 0 ? ret : 0; } @@ -538,6 +673,113 @@ int phy_modify(struct phy_device *phydev, u32 regnum, u16 mask, u16 set) } EXPORT_SYMBOL_GPL(phy_modify); +/** + * __phy_modify_mmd_changed - Function for modifying a register on MMD + * @phydev: the phy_device struct + * @devad: the MMD containing register to modify + * @regnum: register number to modify + * @mask: bit mask of bits to clear + * @set: new value of bits set in mask to write to @regnum + * + * Unlocked helper function which allows a MMD register to be modified as + * new register value = (old register value & ~mask) | set + * + * Returns negative errno, 0 if there was no change, and 1 in case of change + */ +int __phy_modify_mmd_changed(struct phy_device *phydev, int devad, u32 regnum, + u16 mask, u16 set) +{ + int new, ret; + + ret = __phy_read_mmd(phydev, devad, regnum); + if (ret < 0) + return ret; + + new = (ret & ~mask) | set; + if (new == ret) + return 0; + + ret = __phy_write_mmd(phydev, devad, regnum, new); + + return ret < 0 ? ret : 1; +} +EXPORT_SYMBOL_GPL(__phy_modify_mmd_changed); + +/** + * phy_modify_mmd_changed - Function for modifying a register on MMD + * @phydev: the phy_device struct + * @devad: the MMD containing register to modify + * @regnum: register number to modify + * @mask: bit mask of bits to clear + * @set: new value of bits set in mask to write to @regnum + * + * NOTE: MUST NOT be called from interrupt context, + * because the bus read/write functions may wait for an interrupt + * to conclude the operation. + * + * Returns negative errno, 0 if there was no change, and 1 in case of change + */ +int phy_modify_mmd_changed(struct phy_device *phydev, int devad, u32 regnum, + u16 mask, u16 set) +{ + int ret; + + mutex_lock(&phydev->mdio.bus->mdio_lock); + ret = __phy_modify_mmd_changed(phydev, devad, regnum, mask, set); + mutex_unlock(&phydev->mdio.bus->mdio_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(phy_modify_mmd_changed); + +/** + * __phy_modify_mmd - Convenience function for modifying a register on MMD + * @phydev: the phy_device struct + * @devad: the MMD containing register to modify + * @regnum: register number to modify + * @mask: bit mask of bits to clear + * @set: new value of bits set in mask to write to @regnum + * + * NOTE: MUST NOT be called from interrupt context, + * because the bus read/write functions may wait for an interrupt + * to conclude the operation. + */ +int __phy_modify_mmd(struct phy_device *phydev, int devad, u32 regnum, + u16 mask, u16 set) +{ + int ret; + + ret = __phy_modify_mmd_changed(phydev, devad, regnum, mask, set); + + return ret < 0 ? ret : 0; +} +EXPORT_SYMBOL_GPL(__phy_modify_mmd); + +/** + * phy_modify_mmd - Convenience function for modifying a register on MMD + * @phydev: the phy_device struct + * @devad: the MMD containing register to modify + * @regnum: register number to modify + * @mask: bit mask of bits to clear + * @set: new value of bits set in mask to write to @regnum + * + * NOTE: MUST NOT be called from interrupt context, + * because the bus read/write functions may wait for an interrupt + * to conclude the operation. + */ +int phy_modify_mmd(struct phy_device *phydev, int devad, u32 regnum, + u16 mask, u16 set) +{ + int ret; + + mutex_lock(&phydev->mdio.bus->mdio_lock); + ret = __phy_modify_mmd(phydev, devad, regnum, mask, set); + mutex_unlock(&phydev->mdio.bus->mdio_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(phy_modify_mmd); + static int __phy_read_page(struct phy_device *phydev) { return phydev->drv->read_page(phydev); diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index d12aa512b7f5..69dc64a4dbf8 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -543,7 +543,7 @@ int phy_start_aneg(struct phy_device *phydev) if (err < 0) goto out_unlock; - if (__phy_is_started(phydev)) { + if (phy_is_started(phydev)) { if (phydev->autoneg == AUTONEG_ENABLE) { err = phy_check_link_status(phydev); } else { @@ -699,7 +699,7 @@ void phy_stop_machine(struct phy_device *phydev) cancel_delayed_work_sync(&phydev->state_queue); mutex_lock(&phydev->lock); - if (__phy_is_started(phydev)) + if (phy_is_started(phydev)) phydev->state = PHY_UP; mutex_unlock(&phydev->lock); } @@ -752,9 +752,6 @@ static irqreturn_t phy_interrupt(int irq, void *phy_dat) { struct phy_device *phydev = phy_dat; - if (!phy_is_started(phydev)) - return IRQ_NONE; /* It can't be ours. */ - if (phydev->drv->did_interrupt && !phydev->drv->did_interrupt(phydev)) return IRQ_NONE; @@ -813,15 +810,14 @@ EXPORT_SYMBOL(phy_request_interrupt); */ void phy_stop(struct phy_device *phydev) { - mutex_lock(&phydev->lock); - - if (!__phy_is_started(phydev)) { + if (!phy_is_started(phydev)) { WARN(1, "called from state %s\n", phy_state_to_str(phydev->state)); - mutex_unlock(&phydev->lock); return; } + mutex_lock(&phydev->lock); + if (phy_interrupt_is_valid(phydev)) phy_disable_interrupts(phydev); @@ -961,8 +957,10 @@ void phy_state_machine(struct work_struct *work) * state machine would be pointless and possibly error prone when * called from phy_disconnect() synchronously. */ + mutex_lock(&phydev->lock); if (phy_polling_mode(phydev) && phy_is_started(phydev)) phy_queue_state_machine(phydev, PHY_STATE_TIME); + mutex_unlock(&phydev->lock); } /** @@ -1060,17 +1058,12 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable) if (!phy_check_valid(phydev->speed, phydev->duplex, common)) goto eee_exit_err; - if (clk_stop_enable) { + if (clk_stop_enable) /* Configure the PHY to stop receiving xMII * clock while it is signaling LPI. */ - int val = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1); - if (val < 0) - return val; - - val |= MDIO_PCS_CTRL1_CLKSTOP_EN; - phy_write_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1, val); - } + phy_set_bits_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1, + MDIO_PCS_CTRL1_CLKSTOP_EN); return 0; /* EEE supported */ } diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 891e0178b97f..7e71124bb20e 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -30,7 +30,6 @@ #include <linux/mdio.h> #include <linux/io.h> #include <linux/uaccess.h> -#include <linux/of.h> MODULE_DESCRIPTION("PHY library"); MODULE_AUTHOR("Andy Fleming"); @@ -676,13 +675,16 @@ static int get_phy_c45_devs_in_pkg(struct mii_bus *bus, int addr, int dev_addr, phy_reg = mdiobus_read(bus, addr, reg_addr); if (phy_reg < 0) return -EIO; - *devices_in_package = (phy_reg & 0xffff) << 16; + *devices_in_package = phy_reg << 16; reg_addr = MII_ADDR_C45 | dev_addr << 16 | MDIO_DEVS1; phy_reg = mdiobus_read(bus, addr, reg_addr); if (phy_reg < 0) return -EIO; - *devices_in_package |= (phy_reg & 0xffff); + *devices_in_package |= phy_reg; + + /* Bit 0 doesn't represent a device, it indicates c22 regs presence */ + *devices_in_package &= ~BIT(0); return 0; } @@ -743,13 +745,13 @@ static int get_phy_c45_ids(struct mii_bus *bus, int addr, u32 *phy_id, phy_reg = mdiobus_read(bus, addr, reg_addr); if (phy_reg < 0) return -EIO; - c45_ids->device_ids[i] = (phy_reg & 0xffff) << 16; + c45_ids->device_ids[i] = phy_reg << 16; reg_addr = MII_ADDR_C45 | i << 16 | MII_PHYSID2; phy_reg = mdiobus_read(bus, addr, reg_addr); if (phy_reg < 0) return -EIO; - c45_ids->device_ids[i] |= (phy_reg & 0xffff); + c45_ids->device_ids[i] |= phy_reg; } *phy_id = 0; return 0; @@ -786,14 +788,14 @@ static int get_phy_id(struct mii_bus *bus, int addr, u32 *phy_id, return (phy_reg == -EIO || phy_reg == -ENODEV) ? -ENODEV : -EIO; } - *phy_id = (phy_reg & 0xffff) << 16; + *phy_id = phy_reg << 16; /* Grab the bits from PHYIR2, and put them in the lower half */ phy_reg = mdiobus_read(bus, addr, MII_PHYSID2); if (phy_reg < 0) return -EIO; - *phy_id |= (phy_reg & 0xffff); + *phy_id |= phy_reg; return 0; } @@ -1513,7 +1515,7 @@ EXPORT_SYMBOL(phy_reset_after_clk_enable); static int genphy_config_advert(struct phy_device *phydev) { u32 advertise; - int oldadv, adv, bmsr; + int bmsr, adv; int err, changed = 0; /* Only allow advertising what this PHY supports */ @@ -1526,22 +1528,14 @@ static int genphy_config_advert(struct phy_device *phydev) phydev->advertising); /* Setup standard advertisement */ - adv = phy_read(phydev, MII_ADVERTISE); - if (adv < 0) - return adv; - - oldadv = adv; - adv &= ~(ADVERTISE_ALL | ADVERTISE_100BASE4 | ADVERTISE_PAUSE_CAP | - ADVERTISE_PAUSE_ASYM); - adv |= ethtool_adv_to_mii_adv_t(advertise); - - if (adv != oldadv) { - err = phy_write(phydev, MII_ADVERTISE, adv); - - if (err < 0) - return err; + err = phy_modify_changed(phydev, MII_ADVERTISE, + ADVERTISE_ALL | ADVERTISE_100BASE4 | + ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM, + ethtool_adv_to_mii_adv_t(advertise)); + if (err < 0) + return err; + if (err > 0) changed = 1; - } bmsr = phy_read(phydev, MII_BMSR); if (bmsr < 0) @@ -1555,25 +1549,20 @@ static int genphy_config_advert(struct phy_device *phydev) return changed; /* Configure gigabit if it's supported */ - adv = phy_read(phydev, MII_CTRL1000); - if (adv < 0) - return adv; - - oldadv = adv; - adv &= ~(ADVERTISE_1000FULL | ADVERTISE_1000HALF); - + adv = 0; if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, phydev->supported) || linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, phydev->supported)) - adv |= ethtool_adv_to_mii_ctrl1000_t(advertise); + adv = ethtool_adv_to_mii_ctrl1000_t(advertise); - if (adv != oldadv) - changed = 1; - - err = phy_write(phydev, MII_CTRL1000, adv); + err = phy_modify_changed(phydev, MII_CTRL1000, + ADVERTISE_1000FULL | ADVERTISE_1000HALF, + adv); if (err < 0) return err; + if (err > 0) + changed = 1; return changed; } @@ -1588,31 +1577,16 @@ static int genphy_config_advert(struct phy_device *phydev) */ static int genphy_config_eee_advert(struct phy_device *phydev) { - int broken = phydev->eee_broken_modes; - int old_adv, adv; + int err; /* Nothing to disable */ - if (!broken) - return 0; - - /* If the following call fails, we assume that EEE is not - * supported by the phy. If we read 0, EEE is not advertised - * In both case, we don't need to continue - */ - adv = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV); - if (adv <= 0) - return 0; - - old_adv = adv; - adv &= ~broken; - - /* Advertising remains unchanged with the broken mask */ - if (old_adv == adv) + if (!phydev->eee_broken_modes) return 0; - phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV, adv); - - return 1; + err = phy_modify_mmd_changed(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV, + phydev->eee_broken_modes, 0); + /* If the call failed, we assume that EEE is not supported */ + return err < 0 ? 0 : err; } /** @@ -1729,10 +1703,19 @@ int genphy_update_link(struct phy_device *phydev) { int status; - /* Do a fake read */ - status = phy_read(phydev, MII_BMSR); - if (status < 0) - return status; + /* The link state is latched low so that momentary link + * drops can be detected. Do not double-read the status + * in polling mode to detect such short link drops. + */ + if (!phy_polling_mode(phydev)) { + status = phy_read(phydev, MII_BMSR); + if (status < 0) { + return status; + } else if (status & BMSR_LSTATUS) { + phydev->link = 1; + return 0; + } + } /* Read link and autonegotiation status */ status = phy_read(phydev, MII_BMSR); @@ -1763,8 +1746,6 @@ int genphy_read_status(struct phy_device *phydev) int err; int lpa; int lpagb = 0; - int common_adv; - int common_adv_gb = 0; /* Update the link, but return if there was an error */ err = genphy_update_link(phydev); @@ -1796,7 +1777,6 @@ int genphy_read_status(struct phy_device *phydev) mii_stat1000_mod_linkmode_lpa_t(phydev->lp_advertising, lpagb); - common_adv_gb = lpagb & adv << 2; } lpa = phy_read(phydev, MII_LPA); @@ -1809,31 +1789,12 @@ int genphy_read_status(struct phy_device *phydev) if (adv < 0) return adv; - common_adv = lpa & adv; - phydev->speed = SPEED_10; phydev->duplex = DUPLEX_HALF; phydev->pause = 0; phydev->asym_pause = 0; - if (common_adv_gb & (LPA_1000FULL | LPA_1000HALF)) { - phydev->speed = SPEED_1000; - - if (common_adv_gb & LPA_1000FULL) - phydev->duplex = DUPLEX_FULL; - } else if (common_adv & (LPA_100FULL | LPA_100HALF)) { - phydev->speed = SPEED_100; - - if (common_adv & LPA_100FULL) - phydev->duplex = DUPLEX_FULL; - } else - if (common_adv & LPA_10FULL) - phydev->duplex = DUPLEX_FULL; - - if (phydev->duplex == DUPLEX_FULL) { - phydev->pause = lpa & LPA_PAUSE_CAP ? 1 : 0; - phydev->asym_pause = lpa & LPA_PAUSE_ASYM ? 1 : 0; - } + phy_resolve_aneg_linkmode(phydev); } else { int bmcr = phy_read(phydev, MII_BMCR); @@ -1965,44 +1926,6 @@ int genphy_loopback(struct phy_device *phydev, bool enable) } EXPORT_SYMBOL(genphy_loopback); -static int __set_phy_supported(struct phy_device *phydev, u32 max_speed) -{ - switch (max_speed) { - case SPEED_10: - linkmode_clear_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, - phydev->supported); - linkmode_clear_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, - phydev->supported); - /* fall through */ - case SPEED_100: - linkmode_clear_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, - phydev->supported); - linkmode_clear_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, - phydev->supported); - break; - case SPEED_1000: - break; - default: - return -ENOTSUPP; - } - - return 0; -} - -int phy_set_max_speed(struct phy_device *phydev, u32 max_speed) -{ - int err; - - err = __set_phy_supported(phydev, max_speed); - if (err) - return err; - - linkmode_copy(phydev->advertising, phydev->supported); - - return 0; -} -EXPORT_SYMBOL(phy_set_max_speed); - /** * phy_remove_link_mode - Remove a supported link mode * @phydev: phy_device structure to remove link mode from @@ -2133,48 +2056,6 @@ bool phy_validate_pause(struct phy_device *phydev, } EXPORT_SYMBOL(phy_validate_pause); -static void of_set_phy_supported(struct phy_device *phydev) -{ - struct device_node *node = phydev->mdio.dev.of_node; - u32 max_speed; - - if (!IS_ENABLED(CONFIG_OF_MDIO)) - return; - - if (!node) - return; - - if (!of_property_read_u32(node, "max-speed", &max_speed)) - __set_phy_supported(phydev, max_speed); -} - -static void of_set_phy_eee_broken(struct phy_device *phydev) -{ - struct device_node *node = phydev->mdio.dev.of_node; - u32 broken = 0; - - if (!IS_ENABLED(CONFIG_OF_MDIO)) - return; - - if (!node) - return; - - if (of_property_read_bool(node, "eee-broken-100tx")) - broken |= MDIO_EEE_100TX; - if (of_property_read_bool(node, "eee-broken-1000t")) - broken |= MDIO_EEE_1000T; - if (of_property_read_bool(node, "eee-broken-10gt")) - broken |= MDIO_EEE_10GT; - if (of_property_read_bool(node, "eee-broken-1000kx")) - broken |= MDIO_EEE_1000KX; - if (of_property_read_bool(node, "eee-broken-10gkx4")) - broken |= MDIO_EEE_10GKX4; - if (of_property_read_bool(node, "eee-broken-10gkr")) - broken |= MDIO_EEE_10GKR; - - phydev->eee_broken_modes = broken; -} - static bool phy_drv_supports_irq(struct phy_driver *phydrv) { return phydrv->config_intr && phydrv->ack_interrupt; @@ -2208,11 +2089,30 @@ static int phy_probe(struct device *dev) mutex_lock(&phydev->lock); + if (phydev->drv->probe) { + /* Deassert the reset signal */ + phy_device_reset(phydev, 0); + + err = phydev->drv->probe(phydev); + if (err) { + /* Assert the reset signal */ + phy_device_reset(phydev, 1); + goto out; + } + } + /* Start out supporting everything. Eventually, * a controller will attach, and may modify one * or both of these values */ - linkmode_copy(phydev->supported, phydrv->features); + if (phydrv->features) { + linkmode_copy(phydev->supported, phydrv->features); + } else { + err = phydrv->get_features(phydev); + if (err) + goto out; + } + of_set_phy_supported(phydev); linkmode_copy(phydev->advertising, phydev->supported); @@ -2232,20 +2132,8 @@ static int phy_probe(struct device *dev) * (e.g. hardware erratum) where the driver wants to set only one * of these bits. */ - if (test_bit(ETHTOOL_LINK_MODE_Pause_BIT, phydrv->features) || - test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, phydrv->features)) { - linkmode_clear_bit(ETHTOOL_LINK_MODE_Pause_BIT, - phydev->supported); - linkmode_clear_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, - phydev->supported); - if (test_bit(ETHTOOL_LINK_MODE_Pause_BIT, phydrv->features)) - linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, - phydev->supported); - if (test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, - phydrv->features)) - linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, - phydev->supported); - } else { + if (!test_bit(ETHTOOL_LINK_MODE_Pause_BIT, phydev->supported) && + !test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, phydev->supported)) { linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, phydev->supported); linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, @@ -2255,17 +2143,7 @@ static int phy_probe(struct device *dev) /* Set the state to READY by default */ phydev->state = PHY_READY; - if (phydev->drv->probe) { - /* Deassert the reset signal */ - phy_device_reset(phydev, 0); - - err = phydev->drv->probe(phydev); - if (err) { - /* Assert the reset signal */ - phy_device_reset(phydev, 1); - } - } - +out: mutex_unlock(&phydev->lock); return err; @@ -2301,7 +2179,11 @@ int phy_driver_register(struct phy_driver *new_driver, struct module *owner) { int retval; - if (WARN_ON(!new_driver->features)) { + /* Either the features are hard coded, or dynamically + * determine. It cannot be both or neither + */ + if (WARN_ON((!new_driver->features && !new_driver->get_features) || + (new_driver->features && new_driver->get_features))) { pr_err("%s: Driver features are missing\n", new_driver->name); return -EINVAL; } diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 2e21ce42e388..59d175a5ba54 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -302,6 +302,13 @@ static void phylink_mac_config(struct phylink *pl, pl->ops->mac_config(pl->netdev, pl->link_an_mode, state); } +static void phylink_mac_config_up(struct phylink *pl, + const struct phylink_link_state *state) +{ + if (state->link) + phylink_mac_config(pl, state); +} + static void phylink_mac_an_restart(struct phylink *pl) { if (pl->link_config.an_enabled && @@ -401,12 +408,12 @@ static void phylink_resolve(struct work_struct *w) case MLO_AN_PHY: link_state = pl->phy_state; phylink_resolve_flow(pl, &link_state); - phylink_mac_config(pl, &link_state); + phylink_mac_config_up(pl, &link_state); break; case MLO_AN_FIXED: phylink_get_fixed_state(pl, &link_state); - phylink_mac_config(pl, &link_state); + phylink_mac_config_up(pl, &link_state); break; case MLO_AN_INBAND: @@ -471,6 +478,17 @@ static void phylink_run_resolve(struct phylink *pl) queue_work(system_power_efficient_wq, &pl->resolve); } +static void phylink_run_resolve_and_disable(struct phylink *pl, int bit) +{ + unsigned long state = pl->phylink_disable_state; + + set_bit(bit, &pl->phylink_disable_state); + if (state == 0) { + queue_work(system_power_efficient_wq, &pl->resolve); + flush_work(&pl->resolve); + } +} + static void phylink_fixed_poll(struct timer_list *t) { struct phylink *pl = container_of(t, struct phylink, link_poll); @@ -920,9 +938,7 @@ void phylink_stop(struct phylink *pl) if (pl->link_an_mode == MLO_AN_FIXED && !IS_ERR(pl->link_gpio)) del_timer_sync(&pl->link_poll); - set_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state); - queue_work(system_power_efficient_wq, &pl->resolve); - flush_work(&pl->resolve); + phylink_run_resolve_and_disable(pl, PHYLINK_DISABLE_STOPPED); } EXPORT_SYMBOL_GPL(phylink_stop); @@ -1265,6 +1281,24 @@ int phylink_get_eee_err(struct phylink *pl) EXPORT_SYMBOL_GPL(phylink_get_eee_err); /** + * phylink_init_eee() - init and check the EEE features + * @pl: a pointer to a &struct phylink returned from phylink_create() + * @clk_stop_enable: allow PHY to stop receive clock + * + * Must be called either with RTNL held or within mac_link_up() + */ +int phylink_init_eee(struct phylink *pl, bool clk_stop_enable) +{ + int ret = -EOPNOTSUPP; + + if (pl->phydev) + ret = phy_init_eee(pl->phydev, clk_stop_enable); + + return ret; +} +EXPORT_SYMBOL_GPL(phylink_init_eee); + +/** * phylink_ethtool_get_eee() - read the energy efficient ethernet parameters * @pl: a pointer to a &struct phylink returned from phylink_create() * @eee: a pointer to a &struct ethtool_eee for the read parameters @@ -1628,9 +1662,7 @@ static void phylink_sfp_link_down(void *upstream) ASSERT_RTNL(); - set_bit(PHYLINK_DISABLE_LINK, &pl->phylink_disable_state); - queue_work(system_power_efficient_wq, &pl->resolve); - flush_work(&pl->resolve); + phylink_run_resolve_and_disable(pl, PHYLINK_DISABLE_LINK); } static void phylink_sfp_link_up(void *upstream) diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index 75543f9370f3..d8c4b9ae0fa4 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -273,6 +273,15 @@ static struct phy_driver realtek_drvs[] = { .read_page = rtl821x_read_page, .write_page = rtl821x_write_page, }, { + PHY_ID_MATCH_EXACT(0x001cc800), + .name = "Generic Realtek PHY", + .features = PHY_GBIT_FEATURES, + .config_init = genphy_config_init, + .suspend = genphy_suspend, + .resume = genphy_resume, + .read_page = rtl821x_read_page, + .write_page = rtl821x_write_page, + }, { PHY_ID_MATCH_EXACT(0x001cc961), .name = "RTL8366RB Gigabit Ethernet", .features = PHY_GBIT_FEATURES, diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c index ad9db652874d..fef701bfad62 100644 --- a/drivers/net/phy/sfp-bus.c +++ b/drivers/net/phy/sfp-bus.c @@ -347,6 +347,7 @@ static int sfp_register_bus(struct sfp_bus *bus) return ret; } } + bus->socket_ops->attach(bus->sfp); if (bus->started) bus->socket_ops->start(bus->sfp); bus->netdev->sfp_bus = bus; @@ -362,6 +363,7 @@ static void sfp_unregister_bus(struct sfp_bus *bus) if (bus->registered) { if (bus->started) bus->socket_ops->stop(bus->sfp); + bus->socket_ops->detach(bus->sfp); if (bus->phydev && ops && ops->disconnect_phy) ops->disconnect_phy(bus->upstream); } diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index 298ab7546929..d4635c2178d1 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -185,6 +185,7 @@ struct sfp { struct gpio_desc *gpio[GPIO_MAX]; + bool attached; unsigned int state; struct delayed_work poll; struct delayed_work timeout; @@ -1476,7 +1477,7 @@ static void sfp_sm_event(struct sfp *sfp, unsigned int event) */ switch (sfp->sm_mod_state) { default: - if (event == SFP_E_INSERT) { + if (event == SFP_E_INSERT && sfp->attached) { sfp_module_tx_disable(sfp); sfp_sm_ins_next(sfp, SFP_MOD_PROBE, T_PROBE_INIT); } @@ -1608,6 +1609,19 @@ static void sfp_sm_event(struct sfp *sfp, unsigned int event) mutex_unlock(&sfp->sm_mutex); } +static void sfp_attach(struct sfp *sfp) +{ + sfp->attached = true; + if (sfp->state & SFP_F_PRESENT) + sfp_sm_event(sfp, SFP_E_INSERT); +} + +static void sfp_detach(struct sfp *sfp) +{ + sfp->attached = false; + sfp_sm_event(sfp, SFP_E_REMOVE); +} + static void sfp_start(struct sfp *sfp) { sfp_sm_event(sfp, SFP_E_DEV_UP); @@ -1668,6 +1682,8 @@ static int sfp_module_eeprom(struct sfp *sfp, struct ethtool_eeprom *ee, } static const struct sfp_socket_ops sfp_module_ops = { + .attach = sfp_attach, + .detach = sfp_detach, .start = sfp_start, .stop = sfp_stop, .module_info = sfp_module_info, @@ -1835,10 +1851,6 @@ static int sfp_probe(struct platform_device *pdev) dev_info(sfp->dev, "Host maximum power %u.%uW\n", sfp->max_power_mW / 1000, (sfp->max_power_mW / 100) % 10); - sfp->sfp_bus = sfp_register_socket(sfp->dev, sfp, &sfp_module_ops); - if (!sfp->sfp_bus) - return -ENOMEM; - /* Get the initial state, and always signal TX disable, * since the network interface will not be up. */ @@ -1849,10 +1861,6 @@ static int sfp_probe(struct platform_device *pdev) sfp->state |= SFP_F_RATE_SELECT; sfp_set_state(sfp, sfp->state); sfp_module_tx_disable(sfp); - rtnl_lock(); - if (sfp->state & SFP_F_PRESENT) - sfp_sm_event(sfp, SFP_E_INSERT); - rtnl_unlock(); for (i = 0; i < GPIO_MAX; i++) { if (gpio_flags[i] != GPIOD_IN || !sfp->gpio[i]) @@ -1885,6 +1893,10 @@ static int sfp_probe(struct platform_device *pdev) dev_warn(sfp->dev, "No tx_disable pin: SFP modules will always be emitting.\n"); + sfp->sfp_bus = sfp_register_socket(sfp->dev, sfp, &sfp_module_ops); + if (!sfp->sfp_bus) + return -ENOMEM; + return 0; } diff --git a/drivers/net/phy/sfp.h b/drivers/net/phy/sfp.h index 31b0acf337e2..64f54b0bbd8c 100644 --- a/drivers/net/phy/sfp.h +++ b/drivers/net/phy/sfp.h @@ -7,6 +7,8 @@ struct sfp; struct sfp_socket_ops { + void (*attach)(struct sfp *sfp); + void (*detach)(struct sfp *sfp); void (*start)(struct sfp *sfp); void (*stop)(struct sfp *sfp); int (*module_info)(struct sfp *sfp, struct ethtool_modinfo *modinfo); diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index afd9d25d1992..958f1cf67282 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -256,17 +256,6 @@ static void __team_option_inst_mark_removed_port(struct team *team, } } -static bool __team_option_inst_tmp_find(const struct list_head *opts, - const struct team_option_inst *needle) -{ - struct team_option_inst *opt_inst; - - list_for_each_entry(opt_inst, opts, tmp_list) - if (opt_inst == needle) - return true; - return false; -} - static int __team_options_register(struct team *team, const struct team_option *option, size_t option_count) @@ -2460,7 +2449,6 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info) int err = 0; int i; struct nlattr *nl_option; - LIST_HEAD(opt_inst_list); rtnl_lock(); @@ -2480,6 +2468,7 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info) struct nlattr *opt_attrs[TEAM_ATTR_OPTION_MAX + 1]; struct nlattr *attr; struct nlattr *attr_data; + LIST_HEAD(opt_inst_list); enum team_option_type opt_type; int opt_port_ifindex = 0; /* != 0 for per-port options */ u32 opt_array_index = 0; @@ -2584,23 +2573,17 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info) if (err) goto team_put; opt_inst->changed = true; - - /* dumb/evil user-space can send us duplicate opt, - * keep only the last one - */ - if (__team_option_inst_tmp_find(&opt_inst_list, - opt_inst)) - continue; - list_add(&opt_inst->tmp_list, &opt_inst_list); } if (!opt_found) { err = -ENOENT; goto team_put; } - } - err = team_nl_send_event_options_get(team, &opt_inst_list); + err = team_nl_send_event_options_get(team, &opt_inst_list); + if (err) + break; + } team_put: team_nl_team_put(team); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 18656c4094b3..fed298c0cb39 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -866,8 +866,6 @@ static int tun_attach(struct tun_struct *tun, struct file *file, if (rtnl_dereference(tun->xdp_prog)) sock_set_flag(&tfile->sk, SOCK_XDP); - tun_set_real_num_queues(tun); - /* device is allowed to go away first, so no need to hold extra * refcnt. */ @@ -879,6 +877,7 @@ static int tun_attach(struct tun_struct *tun, struct file *file, rcu_assign_pointer(tfile->tun, tun); rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile); tun->numqueues++; + tun_set_real_num_queues(tun); out: return err; } diff --git a/drivers/net/usb/cdc-phonet.c b/drivers/net/usb/cdc-phonet.c index 78b16eb9e58c..63aaae487995 100644 --- a/drivers/net/usb/cdc-phonet.c +++ b/drivers/net/usb/cdc-phonet.c @@ -361,8 +361,8 @@ static int usbpn_probe(struct usb_interface *intf, const struct usb_device_id *i else return -EINVAL; - dev = alloc_netdev(sizeof(*pnd) + sizeof(pnd->urbs[0]) * rxq_size, - ifname, NET_NAME_UNKNOWN, usbpn_setup); + dev = alloc_netdev(struct_size(pnd, urbs, rxq_size), ifname, + NET_NAME_UNKNOWN, usbpn_setup); if (!dev) return -ENOMEM; diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index e96bc0c6140f..3d92ea6fcc02 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -2051,8 +2051,7 @@ static struct phy_device *lan7801_phy_init(struct lan78xx_net *dev) phydev = phy_find_first(dev->mdiobus); if (!phydev) { netdev_dbg(dev->net, "PHY Not Found!! Registering Fixed PHY\n"); - phydev = fixed_phy_register(PHY_POLL, &fphy_status, -1, - NULL); + phydev = fixed_phy_register(PHY_POLL, &fphy_status, NULL); if (IS_ERR(phydev)) { netdev_err(dev->net, "No PHY/fixed_PHY found\n"); return NULL; diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c index f4247b275e09..63e44e746ccc 100644 --- a/drivers/net/usb/pegasus.c +++ b/drivers/net/usb/pegasus.c @@ -1011,6 +1011,7 @@ static int pegasus_ioctl(struct net_device *net, struct ifreq *rq, int cmd) switch (cmd) { case SIOCDEVPRIVATE: data[0] = pegasus->phy; + /* fall through */ case SIOCDEVPRIVATE + 1: read_mii_word(pegasus, data[0], data[1] & 0x1f, &data[3]); res = 0; diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c index 3f145e4c6c08..59dbdbb5feff 100644 --- a/drivers/net/usb/rtl8150.c +++ b/drivers/net/usb/rtl8150.c @@ -847,6 +847,7 @@ static int rtl8150_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) switch (cmd) { case SIOCDEVPRIVATE: data[0] = dev->phy; + /* fall through */ case SIOCDEVPRIVATE + 1: read_mii_word(dev, dev->phy, (data[1] & 0x1f), &data[3]); break; diff --git a/drivers/net/veth.c b/drivers/net/veth.c index f412ea1cef18..fbf890ebbeae 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -540,8 +540,10 @@ static struct sk_buff *veth_xdp_rcv_one(struct veth_rq *rq, goto xdp_xmit; default: bpf_warn_invalid_xdp_action(act); + /* fall through */ case XDP_ABORTED: trace_xdp_exception(rq->dev, xdp_prog, act); + /* fall through */ case XDP_DROP: goto err_xdp; } @@ -661,8 +663,10 @@ static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq, struct sk_buff *skb, goto xdp_xmit; default: bpf_warn_invalid_xdp_action(act); + /* fall through */ case XDP_ABORTED: trace_xdp_exception(rq->dev, xdp_prog, act); + /* fall through */ case XDP_DROP: goto drop; } diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 2a0edd4653e3..7eb38ea9ba56 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -57,6 +57,8 @@ module_param(napi_tx, bool, 0644); #define VIRTIO_XDP_TX BIT(0) #define VIRTIO_XDP_REDIR BIT(1) +#define VIRTIO_XDP_FLAG BIT(0) + /* RX packet size EWMA. The average packet size is used to determine the packet * buffer size when refilling RX rings. As the entire RX ring may be refilled * at once, the weight is chosen so that the EWMA will be insensitive to short- @@ -252,6 +254,21 @@ struct padded_vnet_hdr { char padding[4]; }; +static bool is_xdp_frame(void *ptr) +{ + return (unsigned long)ptr & VIRTIO_XDP_FLAG; +} + +static void *xdp_to_ptr(struct xdp_frame *ptr) +{ + return (void *)((unsigned long)ptr | VIRTIO_XDP_FLAG); +} + +static struct xdp_frame *ptr_to_xdp(void *ptr) +{ + return (struct xdp_frame *)((unsigned long)ptr & ~VIRTIO_XDP_FLAG); +} + /* Converting between virtqueue no. and kernel tx/rx queue no. * 0:rx0 1:tx0 2:rx1 3:tx1 ... 2N:rxN 2N+1:txN 2N+2:cvq */ @@ -462,7 +479,8 @@ static int __virtnet_xdp_xmit_one(struct virtnet_info *vi, sg_init_one(sq->sg, xdpf->data, xdpf->len); - err = virtqueue_add_outbuf(sq->vq, sq->sg, 1, xdpf, GFP_ATOMIC); + err = virtqueue_add_outbuf(sq->vq, sq->sg, 1, xdp_to_ptr(xdpf), + GFP_ATOMIC); if (unlikely(err)) return -ENOSPC; /* Caller handle free/refcnt */ @@ -482,36 +500,47 @@ static int virtnet_xdp_xmit(struct net_device *dev, { struct virtnet_info *vi = netdev_priv(dev); struct receive_queue *rq = vi->rq; - struct xdp_frame *xdpf_sent; struct bpf_prog *xdp_prog; struct send_queue *sq; unsigned int len; + int packets = 0; + int bytes = 0; int drops = 0; int kicks = 0; int ret, err; + void *ptr; int i; - sq = virtnet_xdp_sq(vi); - - if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) { - ret = -EINVAL; - drops = n; - goto out; - } - /* Only allow ndo_xdp_xmit if XDP is loaded on dev, as this * indicate XDP resources have been successfully allocated. */ xdp_prog = rcu_dereference(rq->xdp_prog); - if (!xdp_prog) { - ret = -ENXIO; + if (!xdp_prog) + return -ENXIO; + + sq = virtnet_xdp_sq(vi); + + if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) { + ret = -EINVAL; drops = n; goto out; } /* Free up any pending old buffers before queueing new ones. */ - while ((xdpf_sent = virtqueue_get_buf(sq->vq, &len)) != NULL) - xdp_return_frame(xdpf_sent); + while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) { + if (likely(is_xdp_frame(ptr))) { + struct xdp_frame *frame = ptr_to_xdp(ptr); + + bytes += frame->len; + xdp_return_frame(frame); + } else { + struct sk_buff *skb = ptr; + + bytes += skb->len; + napi_consume_skb(skb, false); + } + packets++; + } for (i = 0; i < n; i++) { struct xdp_frame *xdpf = frames[i]; @@ -530,6 +559,8 @@ static int virtnet_xdp_xmit(struct net_device *dev, } out: u64_stats_update_begin(&sq->stats.syncp); + sq->stats.bytes += bytes; + sq->stats.packets += packets; sq->stats.xdp_tx += n; sq->stats.xdp_tx_drops += drops; sq->stats.kicks += kicks; @@ -1333,18 +1364,26 @@ static int virtnet_receive(struct receive_queue *rq, int budget, static void free_old_xmit_skbs(struct send_queue *sq, bool in_napi) { - struct sk_buff *skb; unsigned int len; unsigned int packets = 0; unsigned int bytes = 0; + void *ptr; - while ((skb = virtqueue_get_buf(sq->vq, &len)) != NULL) { - pr_debug("Sent skb %p\n", skb); + while ((ptr = virtqueue_get_buf(sq->vq, &len)) != NULL) { + if (likely(!is_xdp_frame(ptr))) { + struct sk_buff *skb = ptr; - bytes += skb->len; - packets++; + pr_debug("Sent skb %p\n", skb); + + bytes += skb->len; + napi_consume_skb(skb, in_napi); + } else { + struct xdp_frame *frame = ptr_to_xdp(ptr); - napi_consume_skb(skb, in_napi); + bytes += frame->len; + xdp_return_frame(frame); + } + packets++; } /* Avoid overhead when no packets have been processed @@ -1359,6 +1398,16 @@ static void free_old_xmit_skbs(struct send_queue *sq, bool in_napi) u64_stats_update_end(&sq->stats.syncp); } +static bool is_xdp_raw_buffer_queue(struct virtnet_info *vi, int q) +{ + if (q < (vi->curr_queue_pairs - vi->xdp_queue_pairs)) + return false; + else if (q < vi->curr_queue_pairs) + return true; + else + return false; +} + static void virtnet_poll_cleantx(struct receive_queue *rq) { struct virtnet_info *vi = rq->vq->vdev->priv; @@ -1366,7 +1415,7 @@ static void virtnet_poll_cleantx(struct receive_queue *rq) struct send_queue *sq = &vi->sq[index]; struct netdev_queue *txq = netdev_get_tx_queue(vi->dev, index); - if (!sq->napi.weight) + if (!sq->napi.weight || is_xdp_raw_buffer_queue(vi, index)) return; if (__netif_tx_trylock(txq)) { @@ -1443,8 +1492,16 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget) { struct send_queue *sq = container_of(napi, struct send_queue, napi); struct virtnet_info *vi = sq->vq->vdev->priv; - struct netdev_queue *txq = netdev_get_tx_queue(vi->dev, vq2txq(sq->vq)); + unsigned int index = vq2txq(sq->vq); + struct netdev_queue *txq; + if (unlikely(is_xdp_raw_buffer_queue(vi, index))) { + /* We don't need to enable cb for XDP */ + napi_complete_done(napi, 0); + return 0; + } + + txq = netdev_get_tx_queue(vi->dev, index); __netif_tx_lock(txq, raw_smp_processor_id()); free_old_xmit_skbs(sq, true); __netif_tx_unlock(txq); @@ -2396,6 +2453,10 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, return -ENOMEM; } + old_prog = rtnl_dereference(vi->rq[0].xdp_prog); + if (!prog && !old_prog) + return 0; + if (prog) { prog = bpf_prog_add(prog, vi->max_queue_pairs - 1); if (IS_ERR(prog)) @@ -2403,36 +2464,62 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, } /* Make sure NAPI is not using any XDP TX queues for RX. */ - if (netif_running(dev)) - for (i = 0; i < vi->max_queue_pairs; i++) + if (netif_running(dev)) { + for (i = 0; i < vi->max_queue_pairs; i++) { napi_disable(&vi->rq[i].napi); + virtnet_napi_tx_disable(&vi->sq[i].napi); + } + } + + if (!prog) { + for (i = 0; i < vi->max_queue_pairs; i++) { + rcu_assign_pointer(vi->rq[i].xdp_prog, prog); + if (i == 0) + virtnet_restore_guest_offloads(vi); + } + synchronize_net(); + } - netif_set_real_num_rx_queues(dev, curr_qp + xdp_qp); err = _virtnet_set_queues(vi, curr_qp + xdp_qp); if (err) goto err; + netif_set_real_num_rx_queues(dev, curr_qp + xdp_qp); vi->xdp_queue_pairs = xdp_qp; - for (i = 0; i < vi->max_queue_pairs; i++) { - old_prog = rtnl_dereference(vi->rq[i].xdp_prog); - rcu_assign_pointer(vi->rq[i].xdp_prog, prog); - if (i == 0) { - if (!old_prog) + if (prog) { + for (i = 0; i < vi->max_queue_pairs; i++) { + rcu_assign_pointer(vi->rq[i].xdp_prog, prog); + if (i == 0 && !old_prog) virtnet_clear_guest_offloads(vi); - if (!prog) - virtnet_restore_guest_offloads(vi); } + } + + for (i = 0; i < vi->max_queue_pairs; i++) { if (old_prog) bpf_prog_put(old_prog); - if (netif_running(dev)) + if (netif_running(dev)) { virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi); + virtnet_napi_tx_enable(vi, vi->sq[i].vq, + &vi->sq[i].napi); + } } return 0; err: - for (i = 0; i < vi->max_queue_pairs; i++) - virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi); + if (!prog) { + virtnet_clear_guest_offloads(vi); + for (i = 0; i < vi->max_queue_pairs; i++) + rcu_assign_pointer(vi->rq[i].xdp_prog, old_prog); + } + + if (netif_running(dev)) { + for (i = 0; i < vi->max_queue_pairs; i++) { + virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi); + virtnet_napi_tx_enable(vi, vi->sq[i].vq, + &vi->sq[i].napi); + } + } if (prog) bpf_prog_sub(prog, vi->max_queue_pairs - 1); return err; @@ -2614,16 +2701,6 @@ static void free_receive_page_frags(struct virtnet_info *vi) put_page(vi->rq[i].alloc_frag.page); } -static bool is_xdp_raw_buffer_queue(struct virtnet_info *vi, int q) -{ - if (q < (vi->curr_queue_pairs - vi->xdp_queue_pairs)) - return false; - else if (q < vi->curr_queue_pairs) - return true; - else - return false; -} - static void free_unused_bufs(struct virtnet_info *vi) { void *buf; @@ -2632,10 +2709,10 @@ static void free_unused_bufs(struct virtnet_info *vi) for (i = 0; i < vi->max_queue_pairs; i++) { struct virtqueue *vq = vi->sq[i].vq; while ((buf = virtqueue_detach_unused_buf(vq)) != NULL) { - if (!is_xdp_raw_buffer_queue(vi, i)) + if (!is_xdp_frame(buf)) dev_kfree_skb(buf); else - put_page(virt_to_head_page(buf)); + xdp_return_frame(ptr_to_xdp(buf)); } } diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index ef45c3c925be..33edc78e818d 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -869,6 +869,14 @@ static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f, call_rcu(&f->rcu, vxlan_fdb_free); } +static void vxlan_dst_free(struct rcu_head *head) +{ + struct vxlan_rdst *rd = container_of(head, struct vxlan_rdst, rcu); + + dst_cache_destroy(&rd->dst_cache); + kfree(rd); +} + static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan, union vxlan_addr *ip, __u16 state, __u16 flags, @@ -941,8 +949,10 @@ static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan, err_notify: if ((flags & NLM_F_REPLACE) && rc) *rd = oldrd; - else if ((flags & NLM_F_APPEND) && rc) + else if ((flags & NLM_F_APPEND) && rc) { list_del_rcu(&rd->list); + call_rcu(&rd->rcu, vxlan_dst_free); + } return err; } @@ -1013,14 +1023,6 @@ static int vxlan_fdb_update(struct vxlan_dev *vxlan, } } -static void vxlan_dst_free(struct rcu_head *head) -{ - struct vxlan_rdst *rd = container_of(head, struct vxlan_rdst, rcu); - - dst_cache_destroy(&rd->dst_cache); - kfree(rd); -} - static void vxlan_fdb_dst_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f, struct vxlan_rdst *rd, bool swdev_notify) { @@ -2291,7 +2293,7 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, struct pcpu_sw_netstats *tx_stats, *rx_stats; union vxlan_addr loopback; union vxlan_addr *remote_ip = &dst_vxlan->default_dst.remote_ip; - struct net_device *dev = skb->dev; + struct net_device *dev; int len = skb->len; tx_stats = this_cpu_ptr(src_vxlan->dev->tstats); @@ -2311,9 +2313,15 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, #endif } + rcu_read_lock(); + dev = skb->dev; + if (unlikely(!(dev->flags & IFF_UP))) { + kfree_skb(skb); + goto drop; + } + if (dst_vxlan->cfg.flags & VXLAN_F_LEARN) - vxlan_snoop(skb->dev, &loopback, eth_hdr(skb)->h_source, 0, - vni); + vxlan_snoop(dev, &loopback, eth_hdr(skb)->h_source, 0, vni); u64_stats_update_begin(&tx_stats->syncp); tx_stats->tx_packets++; @@ -2326,8 +2334,10 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, rx_stats->rx_bytes += len; u64_stats_update_end(&rx_stats->syncp); } else { +drop: dev->stats.rx_dropped++; } + rcu_read_unlock(); } static int encap_bypass_if_local(struct sk_buff *skb, struct net_device *dev, diff --git a/drivers/net/wan/dscc4.c b/drivers/net/wan/dscc4.c index d5dc823f781e..fa78d2b14136 100644 --- a/drivers/net/wan/dscc4.c +++ b/drivers/net/wan/dscc4.c @@ -1575,7 +1575,7 @@ try: dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; } - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); dpriv->tx_skbuff[cur] = NULL; ++dpriv->tx_dirty; } else { diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c index 66d889d54e58..a08f04c3f644 100644 --- a/drivers/net/wan/fsl_ucc_hdlc.c +++ b/drivers/net/wan/fsl_ucc_hdlc.c @@ -482,7 +482,7 @@ static int hdlc_tx_done(struct ucc_hdlc_private *priv) memset(priv->tx_buffer + (be32_to_cpu(bd->buf) - priv->dma_tx_addr), 0, skb->len); - dev_kfree_skb_irq(skb); + dev_consume_skb_irq(skb); priv->tx_skbuff[priv->skb_dirtytx] = NULL; priv->skb_dirtytx = diff --git a/drivers/net/wan/wanxl.c b/drivers/net/wan/wanxl.c index d573a57bc301..459ce52a0a4d 100644 --- a/drivers/net/wan/wanxl.c +++ b/drivers/net/wan/wanxl.c @@ -565,7 +565,7 @@ static int wanxl_pci_init_one(struct pci_dev *pdev, u32 plx_phy; /* PLX PCI base address */ u32 mem_phy; /* memory PCI base addr */ u8 __iomem *mem; /* memory virtual base addr */ - int i, ports, alloc_size; + int i, ports; #ifndef MODULE pr_info_once("%s\n", version); @@ -601,8 +601,7 @@ static int wanxl_pci_init_one(struct pci_dev *pdev, default: ports = 4; } - alloc_size = sizeof(struct card) + ports * sizeof(struct port); - card = kzalloc(alloc_size, GFP_KERNEL); + card = kzalloc(struct_size(card, ports, ports), GFP_KERNEL); if (card == NULL) { pci_release_regions(pdev); pci_disable_device(pdev); diff --git a/drivers/net/wimax/i2400m/rx.c b/drivers/net/wimax/i2400m/rx.c index 0b602951ff6b..d28b96d06919 100644 --- a/drivers/net/wimax/i2400m/rx.c +++ b/drivers/net/wimax/i2400m/rx.c @@ -1260,8 +1260,8 @@ int i2400m_rx(struct i2400m *i2400m, struct sk_buff *skb) goto error_msg_hdr_check; result = -EIO; num_pls = le16_to_cpu(msg_hdr->num_pls); - pl_itr = sizeof(*msg_hdr) + /* Check payload descriptor(s) */ - num_pls * sizeof(msg_hdr->pld[0]); + /* Check payload descriptor(s) */ + pl_itr = struct_size(msg_hdr, pld, num_pls); pl_itr = ALIGN(pl_itr, I2400M_PL_ALIGN); if (pl_itr > skb_len) { /* got all the payload descriptors? */ dev_err(dev, "RX: HW BUG? message too short (%u bytes) for " diff --git a/drivers/net/wimax/i2400m/usb.c b/drivers/net/wimax/i2400m/usb.c index f8eb66ef2944..73842a830645 100644 --- a/drivers/net/wimax/i2400m/usb.c +++ b/drivers/net/wimax/i2400m/usb.c @@ -210,6 +210,7 @@ retry: msleep(10); /* give the device some time */ goto retry; } + /* fall through */ case -EINVAL: /* while removing driver */ case -ENODEV: /* dev disconnect ... */ case -ENOENT: /* just ignore it */ diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c index 399b501f3c3c..e8891f5fc83a 100644 --- a/drivers/net/wireless/ath/ath10k/core.c +++ b/drivers/net/wireless/ath/ath10k/core.c @@ -548,7 +548,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = { { .id = WCN3990_HW_1_0_DEV_VERSION, .dev_id = 0, - .bus = ATH10K_BUS_PCI, + .bus = ATH10K_BUS_SNOC, .name = "wcn3990 hw1.0", .continuous_frag_desc = true, .tx_chain_mask = 0x7, diff --git a/drivers/net/wireless/ath/ath10k/wmi.h b/drivers/net/wireless/ath/ath10k/wmi.h index 2034ccc7cc72..021eb30d1fb7 100644 --- a/drivers/net/wireless/ath/ath10k/wmi.h +++ b/drivers/net/wireless/ath/ath10k/wmi.h @@ -1986,7 +1986,7 @@ static inline const char *ath10k_wmi_phymode_str(enum wmi_phy_mode mode) /* no default handler to allow compiler to check that the * enum is fully handled */ - }; + } return "<unknown>"; } diff --git a/drivers/net/wireless/ath/ath6kl/init.c b/drivers/net/wireless/ath/ath6kl/init.c index 54132af70094..aa1c71a76ef7 100644 --- a/drivers/net/wireless/ath/ath6kl/init.c +++ b/drivers/net/wireless/ath/ath6kl/init.c @@ -1140,7 +1140,7 @@ static int ath6kl_fetch_fw_apin(struct ath6kl *ar, const char *name) len -= ie_len; data += ie_len; - }; + } ret = 0; out: diff --git a/drivers/net/wireless/broadcom/b43/debugfs.c b/drivers/net/wireless/broadcom/b43/debugfs.c index 77046384dd80..976c8ec4e992 100644 --- a/drivers/net/wireless/broadcom/b43/debugfs.c +++ b/drivers/net/wireless/broadcom/b43/debugfs.c @@ -668,15 +668,13 @@ static void b43_remove_dynamic_debug(struct b43_wldev *dev) static void b43_add_dynamic_debug(struct b43_wldev *dev) { struct b43_dfsentry *e = dev->dfsentry; - struct dentry *d; -#define add_dyn_dbg(name, id, initstate) do { \ - e->dyn_debug[id] = (initstate); \ - d = debugfs_create_bool(name, 0600, e->subdir, \ - &(e->dyn_debug[id])); \ - if (!IS_ERR(d)) \ - e->dyn_debug_dentries[id] = d; \ - } while (0) +#define add_dyn_dbg(name, id, initstate) do { \ + e->dyn_debug[id] = (initstate); \ + e->dyn_debug_dentries[id] = \ + debugfs_create_bool(name, 0600, e->subdir, \ + &(e->dyn_debug[id])); \ + } while (0) add_dyn_dbg("debug_xmitpower", B43_DBG_XMITPOWER, false); add_dyn_dbg("debug_dmaoverflow", B43_DBG_DMAOVERFLOW, false); @@ -718,19 +716,6 @@ void b43_debugfs_add_device(struct b43_wldev *dev) snprintf(devdir, sizeof(devdir), "%s", wiphy_name(dev->wl->hw->wiphy)); e->subdir = debugfs_create_dir(devdir, rootdir); - if (!e->subdir || IS_ERR(e->subdir)) { - if (e->subdir == ERR_PTR(-ENODEV)) { - b43dbg(dev->wl, "DebugFS (CONFIG_DEBUG_FS) not " - "enabled in kernel config\n"); - } else { - b43err(dev->wl, "debugfs: cannot create %s directory\n", - devdir); - } - dev->dfsentry = NULL; - kfree(log->log); - kfree(e); - return; - } e->mmio16read_next = 0xFFFF; /* invalid address */ e->mmio32read_next = 0xFFFF; /* invalid address */ @@ -741,13 +726,10 @@ void b43_debugfs_add_device(struct b43_wldev *dev) #define ADD_FILE(name, mode) \ do { \ - struct dentry *d; \ - d = debugfs_create_file(__stringify(name), \ + e->file_##name.dentry = \ + debugfs_create_file(__stringify(name), \ mode, e->subdir, dev, \ &fops_##name.fops); \ - e->file_##name.dentry = NULL; \ - if (!IS_ERR(d)) \ - e->file_##name.dentry = d; \ } while (0) @@ -818,8 +800,6 @@ void b43_debugfs_log_txstat(struct b43_wldev *dev, void b43_debugfs_init(void) { rootdir = debugfs_create_dir(KBUILD_MODNAME, NULL); - if (IS_ERR(rootdir)) - rootdir = NULL; } void b43_debugfs_exit(void) diff --git a/drivers/net/wireless/broadcom/b43legacy/debugfs.c b/drivers/net/wireless/broadcom/b43legacy/debugfs.c index 82ef56ed7ca1..8150adee3e34 100644 --- a/drivers/net/wireless/broadcom/b43legacy/debugfs.c +++ b/drivers/net/wireless/broadcom/b43legacy/debugfs.c @@ -361,15 +361,13 @@ static void b43legacy_remove_dynamic_debug(struct b43legacy_wldev *dev) static void b43legacy_add_dynamic_debug(struct b43legacy_wldev *dev) { struct b43legacy_dfsentry *e = dev->dfsentry; - struct dentry *d; -#define add_dyn_dbg(name, id, initstate) do { \ - e->dyn_debug[id] = (initstate); \ - d = debugfs_create_bool(name, 0600, e->subdir, \ - &(e->dyn_debug[id])); \ - if (!IS_ERR(d)) \ - e->dyn_debug_dentries[id] = d; \ - } while (0) +#define add_dyn_dbg(name, id, initstate) do { \ + e->dyn_debug[id] = (initstate); \ + e->dyn_debug_dentries[id] = \ + debugfs_create_bool(name, 0600, e->subdir, \ + &(e->dyn_debug[id])); \ + } while (0) add_dyn_dbg("debug_xmitpower", B43legacy_DBG_XMITPOWER, false); add_dyn_dbg("debug_dmaoverflow", B43legacy_DBG_DMAOVERFLOW, false); @@ -408,29 +406,14 @@ void b43legacy_debugfs_add_device(struct b43legacy_wldev *dev) snprintf(devdir, sizeof(devdir), "%s", wiphy_name(dev->wl->hw->wiphy)); e->subdir = debugfs_create_dir(devdir, rootdir); - if (!e->subdir || IS_ERR(e->subdir)) { - if (e->subdir == ERR_PTR(-ENODEV)) { - b43legacydbg(dev->wl, "DebugFS (CONFIG_DEBUG_FS) not " - "enabled in kernel config\n"); - } else { - b43legacyerr(dev->wl, "debugfs: cannot create %s directory\n", - devdir); - } - dev->dfsentry = NULL; - kfree(log->log); - kfree(e); - return; - } #define ADD_FILE(name, mode) \ do { \ - struct dentry *d; \ - d = debugfs_create_file(__stringify(name), \ + e->file_##name.dentry = \ + debugfs_create_file(__stringify(name), \ mode, e->subdir, dev, \ &fops_##name.fops); \ e->file_##name.dentry = NULL; \ - if (!IS_ERR(d)) \ - e->file_##name.dentry = d; \ } while (0) @@ -492,8 +475,6 @@ void b43legacy_debugfs_log_txstat(struct b43legacy_wldev *dev, void b43legacy_debugfs_init(void) { rootdir = debugfs_create_dir(KBUILD_MODNAME, NULL); - if (IS_ERR(rootdir)) - rootdir = NULL; } void b43legacy_debugfs_exit(void) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/Makefile b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/Makefile index 22fd95a736a8..f7cf3e5f4849 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/Makefile +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/Makefile @@ -16,8 +16,8 @@ # CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. ccflags-y += \ - -Idrivers/net/wireless/broadcom/brcm80211/brcmfmac \ - -Idrivers/net/wireless/broadcom/brcm80211/include + -I $(srctree)/$(src) \ + -I $(srctree)/$(src)/../include obj-$(CONFIG_BRCMFMAC) += brcmfmac.o brcmfmac-objs += \ diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c index d64bf233b12c..ec129864cc9c 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c @@ -315,7 +315,7 @@ static int brcmf_sdiod_skbuff_read(struct brcmf_sdio_dev *sdiodev, /* bail out as things are really fishy here */ WARN(1, "invalid sdio function number: %d\n", func->num); err = -ENOMEDIUM; - }; + } if (err == -ENOMEDIUM) brcmf_sdiod_change_state(sdiodev, BRCMF_SDIOD_NOMEDIUM); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c index 1f1e95a15a17..0ce1d8174e6d 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/common.c @@ -149,7 +149,7 @@ static int brcmf_c_process_clm_blob(struct brcmf_if *ifp) return err; } - err = request_firmware(&clm, clm_name, bus->dev); + err = firmware_request_nowarn(&clm, clm_name, bus->dev); if (err) { brcmf_info("no clm_blob available (err=%d), device may have limited channels available\n", err); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/dmi.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/dmi.c index 51d76ac45075..7535cb0d4ac0 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/dmi.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/dmi.c @@ -43,6 +43,10 @@ static const struct brcmf_dmi_data meegopad_t08_data = { BRCM_CC_43340_CHIP_ID, 2, "meegopad-t08" }; +static const struct brcmf_dmi_data pov_tab_p1006w_data = { + BRCM_CC_43340_CHIP_ID, 2, "pov-tab-p1006w-data" +}; + static const struct dmi_system_id dmi_platform_data[] = { { /* Match for the GPDwin which unfortunately uses somewhat @@ -81,6 +85,17 @@ static const struct dmi_system_id dmi_platform_data[] = { }, .driver_data = (void *)&meegopad_t08_data, }, + { + /* Point of View TAB-P1006W-232 */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Insyde"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "BayTrail"), + /* Note 105b is Foxcon's USB/PCI vendor id */ + DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "105B"), + DMI_EXACT_MATCH(DMI_BOARD_NAME, "0E57"), + }, + .driver_data = (void *)&pov_tab_p1006w_data, + }, {} }; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pno.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pno.c index ffa243e2e2d0..37b403877228 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pno.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/pno.c @@ -496,6 +496,11 @@ int brcmf_pno_stop_sched_scan(struct brcmf_if *ifp, u64 reqid) brcmf_dbg(TRACE, "reqid=%llu\n", reqid); pi = ifp_to_pno(ifp); + + /* No PNO request */ + if (!pi->n_reqs) + return 0; + err = brcmf_pno_remove_request(pi, reqid); if (err) return err; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c index a4308c6e72d7..76cfaf6999c8 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/usb.c @@ -1550,6 +1550,10 @@ void brcmf_usb_exit(void) void brcmf_usb_register(void) { + int ret; + brcmf_dbg(USB, "Enter\n"); - usb_register(&brcmf_usbdrvr); + ret = usb_register(&brcmf_usbdrvr); + if (ret) + brcmf_err("usb_register failed %d\n", ret); } diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/Makefile b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/Makefile index ed83f33aceb7..482d7737764d 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/Makefile +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/Makefile @@ -16,9 +16,9 @@ # CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. ccflags-y := \ - -Idrivers/net/wireless/broadcom/brcm80211/brcmsmac \ - -Idrivers/net/wireless/broadcom/brcm80211/brcmsmac/phy \ - -Idrivers/net/wireless/broadcom/brcm80211/include + -I $(srctree)/$(src) \ + -I $(srctree)/$(src)/phy \ + -I $(srctree)/$(src)/../include brcmsmac-y := \ mac80211_if.o \ diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/debug.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/debug.c index 3bd54f125776..6d776ef6ff54 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/debug.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/debug.c @@ -37,27 +37,18 @@ static struct dentry *root_folder; void brcms_debugfs_init(void) { root_folder = debugfs_create_dir(KBUILD_MODNAME, NULL); - if (IS_ERR(root_folder)) - root_folder = NULL; } void brcms_debugfs_exit(void) { - if (!root_folder) - return; - debugfs_remove_recursive(root_folder); root_folder = NULL; } -int brcms_debugfs_attach(struct brcms_pub *drvr) +void brcms_debugfs_attach(struct brcms_pub *drvr) { - if (!root_folder) - return -ENODEV; - drvr->dbgfs_dir = debugfs_create_dir( dev_name(&drvr->wlc->hw->d11core->dev), root_folder); - return PTR_ERR_OR_ZERO(drvr->dbgfs_dir); } void brcms_debugfs_detach(struct brcms_pub *drvr) @@ -195,7 +186,7 @@ static const struct file_operations brcms_debugfs_def_ops = { .llseek = seq_lseek }; -static int +static void brcms_debugfs_add_entry(struct brcms_pub *drvr, const char *fn, int (*read_fn)(struct seq_file *seq, void *data)) { @@ -203,27 +194,18 @@ brcms_debugfs_add_entry(struct brcms_pub *drvr, const char *fn, struct dentry *dentry = drvr->dbgfs_dir; struct brcms_debugfs_entry *entry; - if (IS_ERR_OR_NULL(dentry)) - return -ENOENT; - entry = devm_kzalloc(dev, sizeof(*entry), GFP_KERNEL); if (!entry) - return -ENOMEM; + return; entry->read = read_fn; entry->drvr = drvr; - dentry = debugfs_create_file(fn, 0444, dentry, entry, - &brcms_debugfs_def_ops); - - return PTR_ERR_OR_ZERO(dentry); + debugfs_create_file(fn, 0444, dentry, entry, &brcms_debugfs_def_ops); } void brcms_debugfs_create_files(struct brcms_pub *drvr) { - if (IS_ERR_OR_NULL(drvr->dbgfs_dir)) - return; - brcms_debugfs_add_entry(drvr, "hardware", brcms_debugfs_hardware_read); brcms_debugfs_add_entry(drvr, "macstat", brcms_debugfs_macstat_read); } diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/debug.h b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/debug.h index 822781cf15d4..56898e6d789d 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/debug.h +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/debug.h @@ -68,7 +68,7 @@ void __brcms_dbg(struct device *dev, u32 level, const char *func, struct brcms_pub; void brcms_debugfs_init(void); void brcms_debugfs_exit(void); -int brcms_debugfs_attach(struct brcms_pub *drvr); +void brcms_debugfs_attach(struct brcms_pub *drvr); void brcms_debugfs_detach(struct brcms_pub *drvr); struct dentry *brcms_debugfs_get_devdir(struct brcms_pub *drvr); void brcms_debugfs_create_files(struct brcms_pub *drvr); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c index e78a93a45741..c6e107f41948 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c @@ -1199,8 +1199,6 @@ wlc_lcnphy_rx_iq_est(struct brcms_phy *pi, { int wait_count = 0; bool result = true; - u8 phybw40; - phybw40 = CHSPEC_IS40(pi->radio_chanspec); mod_phy_reg(pi, 0x6da, (0x1 << 5), (1) << 5); @@ -3082,7 +3080,7 @@ static void wlc_lcnphy_tx_pwr_ctrl_init(struct brcms_phy_pub *ppi) u8 bbmult; struct phytbl_info tab; s32 a1, b0, b1; - s32 tssi, pwr, maxtargetpwr, mintargetpwr; + s32 tssi, pwr, mintargetpwr; bool suspend; struct brcms_phy *pi = container_of(ppi, struct brcms_phy, pubpi_ro); @@ -3119,7 +3117,6 @@ static void wlc_lcnphy_tx_pwr_ctrl_init(struct brcms_phy_pub *ppi) b0 = pi->txpa_2g[0]; b1 = pi->txpa_2g[1]; a1 = pi->txpa_2g[2]; - maxtargetpwr = wlc_lcnphy_tssi2dbm(10, a1, b0, b1); mintargetpwr = wlc_lcnphy_tssi2dbm(125, a1, b0, b1); tab.tbl_id = LCNPHY_TBL_ID_TXPWRCTL; @@ -4212,7 +4209,7 @@ static void wlc_lcnphy_periodic_cal(struct brcms_phy *pi) s8 index; struct phytbl_info tab; s32 a1, b0, b1; - s32 tssi, pwr, maxtargetpwr, mintargetpwr; + s32 tssi, pwr, mintargetpwr; struct brcms_phy_lcnphy *pi_lcn = pi->u.pi_lcnphy; pi->phy_lastcal = pi->sh->now; @@ -4249,7 +4246,6 @@ static void wlc_lcnphy_periodic_cal(struct brcms_phy *pi) b0 = pi->txpa_2g[0]; b1 = pi->txpa_2g[1]; a1 = pi->txpa_2g[2]; - maxtargetpwr = wlc_lcnphy_tssi2dbm(10, a1, b0, b1); mintargetpwr = wlc_lcnphy_tssi2dbm(125, a1, b0, b1); tab.tbl_id = LCNPHY_TBL_ID_TXPWRCTL; @@ -4622,13 +4618,10 @@ static void wlc_lcnphy_radio_init(struct brcms_phy *pi) static void wlc_lcnphy_tbl_init(struct brcms_phy *pi) { uint idx; - u8 phybw40; struct phytbl_info tab; const struct phytbl_info *tb; u32 val; - phybw40 = CHSPEC_IS40(pi->radio_chanspec); - for (idx = 0; idx < dot11lcnphytbl_info_sz_rev0; idx++) wlc_lcnphy_write_table(pi, &dot11lcnphytbl_info_rev0[idx]); @@ -4831,9 +4824,7 @@ static void wlc_lcnphy_baseband_init(struct brcms_phy *pi) void wlc_phy_init_lcnphy(struct brcms_phy *pi) { - u8 phybw40; struct brcms_phy_lcnphy *pi_lcn = pi->u.pi_lcnphy; - phybw40 = CHSPEC_IS40(pi->radio_chanspec); pi_lcn->lcnphy_cal_counter = 0; pi_lcn->lcnphy_cal_temper = pi_lcn->lcnphy_rawtempsense; diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmutil/Makefile b/drivers/net/wireless/broadcom/brcm80211/brcmutil/Makefile index 256c91f9ac4b..bb02c6220a88 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmutil/Makefile +++ b/drivers/net/wireless/broadcom/brcm80211/brcmutil/Makefile @@ -15,9 +15,7 @@ # OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN # CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. -ccflags-y := \ - -Idrivers/net/wireless/broadcom/brcm80211/brcmutil \ - -Idrivers/net/wireless/broadcom/brcm80211/include +ccflags-y := -I $(srctree)/$(src)/../include obj-$(CONFIG_BRCMUTIL) += brcmutil.o brcmutil-objs = utils.o d11.o diff --git a/drivers/net/wireless/intel/iwlegacy/3945-mac.c b/drivers/net/wireless/intel/iwlegacy/3945-mac.c index 57e3b6cca234..271977f7fbb0 100644 --- a/drivers/net/wireless/intel/iwlegacy/3945-mac.c +++ b/drivers/net/wireless/intel/iwlegacy/3945-mac.c @@ -3756,10 +3756,7 @@ il3945_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (err) goto out_remove_sysfs; - err = il_dbgfs_register(il, DRV_NAME); - if (err) - IL_ERR("failed to create debugfs files. Ignoring error: %d\n", - err); + il_dbgfs_register(il, DRV_NAME); /* Start monitoring the killswitch */ queue_delayed_work(il->workqueue, &il->_3945.rfkill_poll, 2 * HZ); diff --git a/drivers/net/wireless/intel/iwlegacy/4965-mac.c b/drivers/net/wireless/intel/iwlegacy/4965-mac.c index 6b4488a178a7..94222ae464ae 100644 --- a/drivers/net/wireless/intel/iwlegacy/4965-mac.c +++ b/drivers/net/wireless/intel/iwlegacy/4965-mac.c @@ -4988,10 +4988,7 @@ il4965_ucode_callback(const struct firmware *ucode_raw, void *context) if (err) goto out_unbind; - err = il_dbgfs_register(il, DRV_NAME); - if (err) - IL_ERR("failed to create debugfs files. Ignoring error: %d\n", - err); + il_dbgfs_register(il, DRV_NAME); err = sysfs_create_group(&il->pci_dev->dev.kobj, &il_attribute_group); if (err) { diff --git a/drivers/net/wireless/intel/iwlegacy/common.h b/drivers/net/wireless/intel/iwlegacy/common.h index dc6a74a05983..b079c64ca014 100644 --- a/drivers/net/wireless/intel/iwlegacy/common.h +++ b/drivers/net/wireless/intel/iwlegacy/common.h @@ -2974,13 +2974,11 @@ il_print_hex_dump(struct il_priv *il, int level, const void *p, u32 len) #endif /* CONFIG_IWLEGACY_DEBUG */ #ifdef CONFIG_IWLEGACY_DEBUGFS -int il_dbgfs_register(struct il_priv *il, const char *name); +void il_dbgfs_register(struct il_priv *il, const char *name); void il_dbgfs_unregister(struct il_priv *il); #else -static inline int -il_dbgfs_register(struct il_priv *il, const char *name) +static inline void il_dbgfs_register(struct il_priv *il, const char *name) { - return 0; } static inline void diff --git a/drivers/net/wireless/intel/iwlegacy/debug.c b/drivers/net/wireless/intel/iwlegacy/debug.c index d76073def677..fa211412e0ac 100644 --- a/drivers/net/wireless/intel/iwlegacy/debug.c +++ b/drivers/net/wireless/intel/iwlegacy/debug.c @@ -128,23 +128,12 @@ EXPORT_SYMBOL(il_update_stats); /* create and remove of files */ #define DEBUGFS_ADD_FILE(name, parent, mode) do { \ - if (!debugfs_create_file(#name, mode, parent, il, \ - &il_dbgfs_##name##_ops)) \ - goto err; \ + debugfs_create_file(#name, mode, parent, il, \ + &il_dbgfs_##name##_ops); \ } while (0) #define DEBUGFS_ADD_BOOL(name, parent, ptr) do { \ - struct dentry *__tmp; \ - __tmp = debugfs_create_bool(#name, 0600, parent, ptr); \ - if (IS_ERR(__tmp) || !__tmp) \ - goto err; \ -} while (0) - -#define DEBUGFS_ADD_X32(name, parent, ptr) do { \ - struct dentry *__tmp; \ - __tmp = debugfs_create_x32(#name, 0600, parent, ptr); \ - if (IS_ERR(__tmp) || !__tmp) \ - goto err; \ + debugfs_create_bool(#name, 0600, parent, ptr); \ } while (0) /* file operation */ @@ -1341,27 +1330,18 @@ DEBUGFS_WRITE_FILE_OPS(wd_timeout); * Create the debugfs files and directories * */ -int +void il_dbgfs_register(struct il_priv *il, const char *name) { struct dentry *phyd = il->hw->wiphy->debugfsdir; struct dentry *dir_drv, *dir_data, *dir_rf, *dir_debug; dir_drv = debugfs_create_dir(name, phyd); - if (!dir_drv) - return -ENOMEM; - il->debugfs_dir = dir_drv; dir_data = debugfs_create_dir("data", dir_drv); - if (!dir_data) - goto err; dir_rf = debugfs_create_dir("rf", dir_drv); - if (!dir_rf) - goto err; dir_debug = debugfs_create_dir("debug", dir_drv); - if (!dir_debug) - goto err; DEBUGFS_ADD_FILE(nvm, dir_data, 0400); DEBUGFS_ADD_FILE(sram, dir_data, 0600); @@ -1399,12 +1379,6 @@ il_dbgfs_register(struct il_priv *il, const char *name) DEBUGFS_ADD_BOOL(disable_chain_noise, dir_rf, &il->disable_chain_noise_cal); DEBUGFS_ADD_BOOL(disable_tx_power, dir_rf, &il->disable_tx_power_cal); - return 0; - -err: - IL_ERR("Can't create the debugfs directory\n"); - il_dbgfs_unregister(il); - return -ENOMEM; } EXPORT_SYMBOL(il_dbgfs_register); diff --git a/drivers/net/wireless/intel/iwlwifi/Kconfig b/drivers/net/wireless/intel/iwlwifi/Kconfig index 491ca3c8b43c..83d5bceea08f 100644 --- a/drivers/net/wireless/intel/iwlwifi/Kconfig +++ b/drivers/net/wireless/intel/iwlwifi/Kconfig @@ -1,6 +1,6 @@ config IWLWIFI tristate "Intel Wireless WiFi Next Gen AGN - Wireless-N/Advanced-N/Ultimate-N (iwlwifi) " - depends on PCI && HAS_IOMEM + depends on PCI && HAS_IOMEM && CFG80211 select FW_LOADER ---help--- Select to build the driver supporting the: @@ -47,6 +47,7 @@ if IWLWIFI config IWLWIFI_LEDS bool depends on LEDS_CLASS=y || LEDS_CLASS=IWLWIFI + depends on IWLMVM || IWLDVM select LEDS_TRIGGERS select MAC80211_LEDS default y diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c index 7e65073834b7..eb93711d474b 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c @@ -83,6 +83,7 @@ #define IWL_22000_HR_A0_FW_PRE "iwlwifi-QuQnj-a0-hr-a0-" #define IWL_22000_SU_Z0_FW_PRE "iwlwifi-su-z0-" #define IWL_QU_B_JF_B_FW_PRE "iwlwifi-Qu-b0-jf-b0-" +#define IWL_CC_A_FW_PRE "iwlwifi-cc-a0-" #define IWL_22000_HR_MODULE_FIRMWARE(api) \ IWL_22000_HR_FW_PRE __stringify(api) ".ucode" @@ -104,6 +105,8 @@ IWL_22000_SU_Z0_FW_PRE __stringify(api) ".ucode" #define IWL_QU_B_JF_B_MODULE_FIRMWARE(api) \ IWL_QU_B_JF_B_FW_PRE __stringify(api) ".ucode" +#define IWL_CC_A_MODULE_FIRMWARE(api) \ + IWL_CC_A_FW_PRE __stringify(api) ".ucode" static const struct iwl_base_params iwl_22000_base_params = { .eeprom_size = OTP_LOW_IMAGE_SIZE_32K, @@ -195,8 +198,8 @@ const struct iwl_cfg iwl22000_2ac_cfg_jf = { IWL_DEVICE_22500, }; -const struct iwl_cfg iwl22000_2ax_cfg_hr = { - .name = "Intel(R) Dual Band Wireless AX 22000", +const struct iwl_cfg iwl22560_2ax_cfg_hr = { + .name = "Intel(R) Wireless-AX 22560", .fw_name_pre = IWL_22000_QU_B_HR_B_FW_PRE, IWL_DEVICE_22500, /* @@ -207,6 +210,42 @@ const struct iwl_cfg iwl22000_2ax_cfg_hr = { .max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT, }; +const struct iwl_cfg iwl22260_2ax_cfg = { + .name = "Intel(R) Wireless-AX 22260", + .fw_name_pre = IWL_CC_A_FW_PRE, + IWL_DEVICE_22500, + /* + * This device doesn't support receiving BlockAck with a large bitmap + * so we need to restrict the size of transmitted aggregation to the + * HT size; mac80211 would otherwise pick the HE max (256) by default. + */ + .max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT, +}; + +const struct iwl_cfg killer1650x_2ax_cfg = { + .name = "Killer(R) Wireless-AX 1650x Wireless Network Adapter (22260NGW)", + .fw_name_pre = IWL_CC_A_FW_PRE, + IWL_DEVICE_22500, + /* + * This device doesn't support receiving BlockAck with a large bitmap + * so we need to restrict the size of transmitted aggregation to the + * HT size; mac80211 would otherwise pick the HE max (256) by default. + */ + .max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT, +}; + +const struct iwl_cfg killer1650w_2ax_cfg = { + .name = "Killer(R) Wireless-AX 1650w Wireless Network Adapter (22260D2W)", + .fw_name_pre = IWL_CC_A_FW_PRE, + IWL_DEVICE_22500, + /* + * This device doesn't support receiving BlockAck with a large bitmap + * so we need to restrict the size of transmitted aggregation to the + * HT size; mac80211 would otherwise pick the HE max (256) by default. + */ + .max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT, +}; + /* * All JF radio modules are part of the 9000 series, but the MAC part * looks more like 22000. That's why this device is here, but called @@ -230,6 +269,12 @@ const struct iwl_cfg iwl9560_2ac_cfg_qu_b0_jf_b0 = { IWL_DEVICE_22500, }; +const struct iwl_cfg iwl9560_2ac_160_cfg_qu_b0_jf_b0 = { + .name = "Intel(R) Wireless-AC 9560 160MHz", + .fw_name_pre = IWL_QU_B_JF_B_FW_PRE, + IWL_DEVICE_22500, +}; + const struct iwl_cfg killer1550i_2ac_cfg_qu_b0_jf_b0 = { .name = "Killer (R) Wireless-AC 1550i Wireless Network Adapter (9560NGW)", .fw_name_pre = IWL_QU_B_JF_B_FW_PRE, @@ -242,6 +287,30 @@ const struct iwl_cfg killer1550s_2ac_cfg_qu_b0_jf_b0 = { IWL_DEVICE_22500, }; +const struct iwl_cfg killer1650s_2ax_cfg_qu_b0_hr_b0 = { + .name = "Killer(R) Wireless-AX 1650i Wireless Network Adapter (22560NGW)", + .fw_name_pre = IWL_22000_QU_B_HR_B_FW_PRE, + IWL_DEVICE_22500, + /* + * This device doesn't support receiving BlockAck with a large bitmap + * so we need to restrict the size of transmitted aggregation to the + * HT size; mac80211 would otherwise pick the HE max (256) by default. + */ + .max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT, +}; + +const struct iwl_cfg killer1650i_2ax_cfg_qu_b0_hr_b0 = { + .name = "Killer(R) Wireless-AX 1650s Wireless Network Adapter (22560D2W)", + .fw_name_pre = IWL_22000_QU_B_HR_B_FW_PRE, + IWL_DEVICE_22500, + /* + * This device doesn't support receiving BlockAck with a large bitmap + * so we need to restrict the size of transmitted aggregation to the + * HT size; mac80211 would otherwise pick the HE max (256) by default. + */ + .max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT, +}; + const struct iwl_cfg iwl22000_2ax_cfg_jf = { .name = "Intel(R) Dual Band Wireless AX 22000", .fw_name_pre = IWL_QU_B_JF_B_FW_PRE, @@ -324,3 +393,4 @@ MODULE_FIRMWARE(IWL_22000_JF_B0_QNJ_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_22000_HR_A0_QNJ_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_22000_SU_Z0_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX)); MODULE_FIRMWARE(IWL_QU_B_JF_B_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX)); +MODULE_FIRMWARE(IWL_CC_A_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX)); diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c index f2114137c13f..113bcf7735a0 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c @@ -73,21 +73,12 @@ #define IWL9000_SMEM_OFFSET 0x400000 #define IWL9000_SMEM_LEN 0x68000 -#define IWL9000A_FW_PRE "iwlwifi-9000-pu-a0-jf-a0-" -#define IWL9000B_FW_PRE "iwlwifi-9000-pu-b0-jf-b0-" -#define IWL9000RFB_FW_PRE "iwlwifi-9000-pu-a0-jf-b0-" -#define IWL9260A_FW_PRE "iwlwifi-9260-th-a0-jf-a0-" -#define IWL9260B_FW_PRE "iwlwifi-9260-th-b0-jf-b0-" -#define IWL9000A_MODULE_FIRMWARE(api) \ - IWL9000A_FW_PRE __stringify(api) ".ucode" -#define IWL9000B_MODULE_FIRMWARE(api) \ - IWL9000B_FW_PRE __stringify(api) ".ucode" -#define IWL9000RFB_MODULE_FIRMWARE(api) \ - IWL9000RFB_FW_PRE __stringify(api) ".ucode" -#define IWL9260A_MODULE_FIRMWARE(api) \ - IWL9260A_FW_PRE __stringify(api) ".ucode" -#define IWL9260B_MODULE_FIRMWARE(api) \ - IWL9260B_FW_PRE __stringify(api) ".ucode" +#define IWL9000_FW_PRE "iwlwifi-9000-pu-b0-jf-b0-" +#define IWL9260_FW_PRE "iwlwifi-9260-th-b0-jf-b0-" +#define IWL9000_MODULE_FIRMWARE(api) \ + IWL9000_FW_PRE __stringify(api) ".ucode" +#define IWL9260_MODULE_FIRMWARE(api) \ + IWL9260_FW_PRE __stringify(api) ".ucode" static const struct iwl_base_params iwl9000_base_params = { .eeprom_size = OTP_LOW_IMAGE_SIZE_32K, @@ -162,81 +153,87 @@ static const struct iwl_tt_params iwl9000_tt_params = { const struct iwl_cfg iwl9160_2ac_cfg = { .name = "Intel(R) Dual Band Wireless AC 9160", - .fw_name_pre = IWL9260A_FW_PRE, - .fw_name_pre_b_or_c_step = IWL9260B_FW_PRE, + .fw_name_pre = IWL9260_FW_PRE, IWL_DEVICE_9000, }; const struct iwl_cfg iwl9260_2ac_cfg = { .name = "Intel(R) Dual Band Wireless AC 9260", - .fw_name_pre = IWL9260A_FW_PRE, - .fw_name_pre_b_or_c_step = IWL9260B_FW_PRE, + .fw_name_pre = IWL9260_FW_PRE, + IWL_DEVICE_9000, +}; + +const struct iwl_cfg iwl9260_2ac_160_cfg = { + .name = "Intel(R) Wireless-AC 9260 160MHz", + .fw_name_pre = IWL9260_FW_PRE, IWL_DEVICE_9000, }; const struct iwl_cfg iwl9260_killer_2ac_cfg = { .name = "Killer (R) Wireless-AC 1550 Wireless Network Adapter (9260NGW)", - .fw_name_pre = IWL9260A_FW_PRE, - .fw_name_pre_b_or_c_step = IWL9260B_FW_PRE, + .fw_name_pre = IWL9260_FW_PRE, IWL_DEVICE_9000, }; const struct iwl_cfg iwl9270_2ac_cfg = { .name = "Intel(R) Dual Band Wireless AC 9270", - .fw_name_pre = IWL9260A_FW_PRE, - .fw_name_pre_b_or_c_step = IWL9260B_FW_PRE, + .fw_name_pre = IWL9260_FW_PRE, IWL_DEVICE_9000, }; const struct iwl_cfg iwl9460_2ac_cfg = { .name = "Intel(R) Dual Band Wireless AC 9460", - .fw_name_pre = IWL9260A_FW_PRE, - .fw_name_pre_b_or_c_step = IWL9260B_FW_PRE, + .fw_name_pre = IWL9260_FW_PRE, IWL_DEVICE_9000, }; const struct iwl_cfg iwl9460_2ac_cfg_soc = { .name = "Intel(R) Dual Band Wireless AC 9460", - .fw_name_pre = IWL9000A_FW_PRE, - .fw_name_pre_b_or_c_step = IWL9000B_FW_PRE, - .fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE, + .fw_name_pre = IWL9000_FW_PRE, IWL_DEVICE_9000, .integrated = true, .soc_latency = 5000, }; const struct iwl_cfg iwl9461_2ac_cfg_soc = { - .name = "Intel(R) Dual Band Wireless AC 9461", - .fw_name_pre = IWL9000A_FW_PRE, - .fw_name_pre_b_or_c_step = IWL9000B_FW_PRE, - .fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE, - IWL_DEVICE_9000, - .integrated = true, - .soc_latency = 5000, + .name = "Intel(R) Dual Band Wireless AC 9461", + .fw_name_pre = IWL9000_FW_PRE, + IWL_DEVICE_9000, + .integrated = true, + .soc_latency = 5000, }; const struct iwl_cfg iwl9462_2ac_cfg_soc = { - .name = "Intel(R) Dual Band Wireless AC 9462", - .fw_name_pre = IWL9000A_FW_PRE, - .fw_name_pre_b_or_c_step = IWL9000B_FW_PRE, - .fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE, - IWL_DEVICE_9000, - .integrated = true, - .soc_latency = 5000, + .name = "Intel(R) Dual Band Wireless AC 9462", + .fw_name_pre = IWL9000_FW_PRE, + IWL_DEVICE_9000, + .integrated = true, + .soc_latency = 5000, }; const struct iwl_cfg iwl9560_2ac_cfg = { .name = "Intel(R) Dual Band Wireless AC 9560", - .fw_name_pre = IWL9260A_FW_PRE, - .fw_name_pre_b_or_c_step = IWL9260B_FW_PRE, + .fw_name_pre = IWL9260_FW_PRE, + IWL_DEVICE_9000, +}; + +const struct iwl_cfg iwl9560_2ac_160_cfg = { + .name = "Intel(R) Wireless-AC 9560 160MHz", + .fw_name_pre = IWL9260_FW_PRE, IWL_DEVICE_9000, }; const struct iwl_cfg iwl9560_2ac_cfg_soc = { .name = "Intel(R) Dual Band Wireless AC 9560", - .fw_name_pre = IWL9000A_FW_PRE, - .fw_name_pre_b_or_c_step = IWL9000B_FW_PRE, - .fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE, + .fw_name_pre = IWL9000_FW_PRE, + IWL_DEVICE_9000, + .integrated = true, + .soc_latency = 5000, +}; + +const struct iwl_cfg iwl9560_2ac_160_cfg_soc = { + .name = "Intel(R) Wireless-AC 9560 160MHz", + .fw_name_pre = IWL9000_FW_PRE, IWL_DEVICE_9000, .integrated = true, .soc_latency = 5000, @@ -244,9 +241,7 @@ const struct iwl_cfg iwl9560_2ac_cfg_soc = { const struct iwl_cfg iwl9560_killer_2ac_cfg_soc = { .name = "Killer (R) Wireless-AC 1550i Wireless Network Adapter (9560NGW)", - .fw_name_pre = IWL9000A_FW_PRE, - .fw_name_pre_b_or_c_step = IWL9000B_FW_PRE, - .fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE, + .fw_name_pre = IWL9000_FW_PRE, IWL_DEVICE_9000, .integrated = true, .soc_latency = 5000, @@ -254,9 +249,7 @@ const struct iwl_cfg iwl9560_killer_2ac_cfg_soc = { const struct iwl_cfg iwl9560_killer_s_2ac_cfg_soc = { .name = "Killer (R) Wireless-AC 1550s Wireless Network Adapter (9560NGW)", - .fw_name_pre = IWL9000A_FW_PRE, - .fw_name_pre_b_or_c_step = IWL9000B_FW_PRE, - .fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE, + .fw_name_pre = IWL9000_FW_PRE, IWL_DEVICE_9000, .integrated = true, .soc_latency = 5000, @@ -264,9 +257,7 @@ const struct iwl_cfg iwl9560_killer_s_2ac_cfg_soc = { const struct iwl_cfg iwl9460_2ac_cfg_shared_clk = { .name = "Intel(R) Dual Band Wireless AC 9460", - .fw_name_pre = IWL9000A_FW_PRE, - .fw_name_pre_b_or_c_step = IWL9000B_FW_PRE, - .fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE, + .fw_name_pre = IWL9000_FW_PRE, IWL_DEVICE_9000, .integrated = true, .soc_latency = 5000, @@ -275,9 +266,7 @@ const struct iwl_cfg iwl9460_2ac_cfg_shared_clk = { const struct iwl_cfg iwl9461_2ac_cfg_shared_clk = { .name = "Intel(R) Dual Band Wireless AC 9461", - .fw_name_pre = IWL9000A_FW_PRE, - .fw_name_pre_b_or_c_step = IWL9000B_FW_PRE, - .fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE, + .fw_name_pre = IWL9000_FW_PRE, IWL_DEVICE_9000, .integrated = true, .soc_latency = 5000, @@ -286,9 +275,7 @@ const struct iwl_cfg iwl9461_2ac_cfg_shared_clk = { const struct iwl_cfg iwl9462_2ac_cfg_shared_clk = { .name = "Intel(R) Dual Band Wireless AC 9462", - .fw_name_pre = IWL9000A_FW_PRE, - .fw_name_pre_b_or_c_step = IWL9000B_FW_PRE, - .fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE, + .fw_name_pre = IWL9000_FW_PRE, IWL_DEVICE_9000, .integrated = true, .soc_latency = 5000, @@ -297,9 +284,16 @@ const struct iwl_cfg iwl9462_2ac_cfg_shared_clk = { const struct iwl_cfg iwl9560_2ac_cfg_shared_clk = { .name = "Intel(R) Dual Band Wireless AC 9560", - .fw_name_pre = IWL9000A_FW_PRE, - .fw_name_pre_b_or_c_step = IWL9000B_FW_PRE, - .fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE, + .fw_name_pre = IWL9000_FW_PRE, + IWL_DEVICE_9000, + .integrated = true, + .soc_latency = 5000, + .extra_phy_cfg_flags = FW_PHY_CFG_SHARED_CLK +}; + +const struct iwl_cfg iwl9560_2ac_160_cfg_shared_clk = { + .name = "Intel(R) Wireless-AC 9560 160MHz", + .fw_name_pre = IWL9000_FW_PRE, IWL_DEVICE_9000, .integrated = true, .soc_latency = 5000, @@ -308,9 +302,7 @@ const struct iwl_cfg iwl9560_2ac_cfg_shared_clk = { const struct iwl_cfg iwl9560_killer_2ac_cfg_shared_clk = { .name = "Killer (R) Wireless-AC 1550i Wireless Network Adapter (9560NGW)", - .fw_name_pre = IWL9000A_FW_PRE, - .fw_name_pre_b_or_c_step = IWL9000B_FW_PRE, - .fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE, + .fw_name_pre = IWL9000_FW_PRE, IWL_DEVICE_9000, .integrated = true, .soc_latency = 5000, @@ -319,17 +311,12 @@ const struct iwl_cfg iwl9560_killer_2ac_cfg_shared_clk = { const struct iwl_cfg iwl9560_killer_s_2ac_cfg_shared_clk = { .name = "Killer (R) Wireless-AC 1550s Wireless Network Adapter (9560NGW)", - .fw_name_pre = IWL9000A_FW_PRE, - .fw_name_pre_b_or_c_step = IWL9000B_FW_PRE, - .fw_name_pre_rf_next_step = IWL9000RFB_FW_PRE, + .fw_name_pre = IWL9000_FW_PRE, IWL_DEVICE_9000, .integrated = true, .soc_latency = 5000, .extra_phy_cfg_flags = FW_PHY_CFG_SHARED_CLK }; -MODULE_FIRMWARE(IWL9000A_MODULE_FIRMWARE(IWL9000_UCODE_API_MAX)); -MODULE_FIRMWARE(IWL9000B_MODULE_FIRMWARE(IWL9000_UCODE_API_MAX)); -MODULE_FIRMWARE(IWL9000RFB_MODULE_FIRMWARE(IWL9000_UCODE_API_MAX)); -MODULE_FIRMWARE(IWL9260A_MODULE_FIRMWARE(IWL9000_UCODE_API_MAX)); -MODULE_FIRMWARE(IWL9260B_MODULE_FIRMWARE(IWL9000_UCODE_API_MAX)); +MODULE_FIRMWARE(IWL9000_MODULE_FIRMWARE(IWL9000_UCODE_API_MAX)); +MODULE_FIRMWARE(IWL9260_MODULE_FIRMWARE(IWL9000_UCODE_API_MAX)); diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/Makefile b/drivers/net/wireless/intel/iwlwifi/dvm/Makefile index 702d42b2d452..0486b17d7c41 100644 --- a/drivers/net/wireless/intel/iwlwifi/dvm/Makefile +++ b/drivers/net/wireless/intel/iwlwifi/dvm/Makefile @@ -11,4 +11,4 @@ iwldvm-objs += rxon.o devices.o iwldvm-$(CONFIG_IWLWIFI_LEDS) += led.o iwldvm-$(CONFIG_IWLWIFI_DEBUGFS) += debugfs.o -ccflags-y += -I$(src)/../ +ccflags-y += -I $(srctree)/$(src)/../ diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/dvm/mac80211.c index 49b71dbf8490..54b759cec8b3 100644 --- a/drivers/net/wireless/intel/iwlwifi/dvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/dvm/mac80211.c @@ -1,6 +1,7 @@ /****************************************************************************** * * Copyright(c) 2003 - 2014 Intel Corporation. All rights reserved. + * Copyright (C) 2018 Intel Corporation * * Portions of this file are derived from the ipw3945 project, as well * as portions of the ieee80211 subsystem header files. @@ -710,24 +711,6 @@ static int iwlagn_mac_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, return ret; } -static inline bool iwl_enable_rx_ampdu(const struct iwl_cfg *cfg) -{ - if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_RXAGG) - return false; - return true; -} - -static inline bool iwl_enable_tx_ampdu(const struct iwl_cfg *cfg) -{ - if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_TXAGG) - return false; - if (iwlwifi_mod_params.disable_11n & IWL_ENABLE_HT_TXAGG) - return true; - - /* disabled by default */ - return false; -} - static int iwlagn_mac_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_ampdu_params *params) @@ -752,7 +735,7 @@ static int iwlagn_mac_ampdu_action(struct ieee80211_hw *hw, switch (action) { case IEEE80211_AMPDU_RX_START: - if (!iwl_enable_rx_ampdu(priv->cfg)) + if (!iwl_enable_rx_ampdu()) break; IWL_DEBUG_HT(priv, "start Rx\n"); ret = iwl_sta_rx_agg_start(priv, sta, tid, *ssn); @@ -764,7 +747,7 @@ static int iwlagn_mac_ampdu_action(struct ieee80211_hw *hw, case IEEE80211_AMPDU_TX_START: if (!priv->trans->ops->txq_enable) break; - if (!iwl_enable_tx_ampdu(priv->cfg)) + if (!iwl_enable_tx_ampdu()) break; IWL_DEBUG_HT(priv, "start Tx\n"); ret = iwlagn_tx_agg_start(priv, vif, sta, tid, ssn); diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/main.c b/drivers/net/wireless/intel/iwlwifi/dvm/main.c index c219bca5cff4..bd3c3b921d4c 100644 --- a/drivers/net/wireless/intel/iwlwifi/dvm/main.c +++ b/drivers/net/wireless/intel/iwlwifi/dvm/main.c @@ -1054,7 +1054,7 @@ static void iwl_bg_restart(struct work_struct *data) ieee80211_restart_hw(priv->hw); else IWL_ERR(priv, - "Cannot request restart before registrating with mac80211\n"); + "Cannot request restart before registering with mac80211\n"); } else { WARN_ON(1); } diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/tt.c b/drivers/net/wireless/intel/iwlwifi/dvm/tt.c index 4de2727ac63e..a156dcf5b7d9 100644 --- a/drivers/net/wireless/intel/iwlwifi/dvm/tt.c +++ b/drivers/net/wireless/intel/iwlwifi/dvm/tt.c @@ -1,6 +1,7 @@ /****************************************************************************** * * Copyright(c) 2007 - 2014 Intel Corporation. All rights reserved. + * Copyright (C) 2018 Intel Corporation * * Portions of this file are derived from the ipw3945 project, as well * as portions of the ieee80211 subsystem header files. @@ -325,9 +326,9 @@ static void iwl_legacy_tt_handler(struct iwl_priv *priv, s32 temp, bool force) iwl_prepare_ct_kill_task(priv); tt->state = old_state; } - } else if (old_state == IWL_TI_CT_KILL && - tt->state != IWL_TI_CT_KILL) + } else if (old_state == IWL_TI_CT_KILL) { iwl_perform_ct_kill_task(priv, false); + } IWL_DEBUG_TEMP(priv, "Temperature state changed %u\n", tt->state); IWL_DEBUG_TEMP(priv, "Power Index change to %u\n", diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h index 8b4922bbe139..0290b333d860 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h @@ -77,7 +77,8 @@ * @DATA_PATH_GROUP: data path group, uses command IDs from * &enum iwl_data_path_subcmd_ids * @NAN_GROUP: NAN group, uses command IDs from &enum iwl_nan_subcmd_ids - * @TOF_GROUP: TOF group, uses command IDs from &enum iwl_tof_subcmd_ids + * @LOCATION_GROUP: location group, uses command IDs from + * &enum iwl_location_subcmd_ids * @PROT_OFFLOAD_GROUP: protocol offload group, uses command IDs from * &enum iwl_prot_offload_subcmd_ids * @REGULATORY_AND_NVM_GROUP: regulatory/NVM group, uses command IDs from @@ -92,7 +93,7 @@ enum iwl_mvm_command_groups { PHY_OPS_GROUP = 0x4, DATA_PATH_GROUP = 0x5, NAN_GROUP = 0x7, - TOF_GROUP = 0x8, + LOCATION_GROUP = 0x8, PROT_OFFLOAD_GROUP = 0xb, REGULATORY_AND_NVM_GROUP = 0xc, DEBUG_GROUP = 0xf, @@ -353,16 +354,6 @@ enum iwl_legacy_cmds { PHY_DB_CMD = 0x6c, /** - * @TOF_CMD: &struct iwl_tof_config_cmd - */ - TOF_CMD = 0x10, - - /** - * @TOF_NOTIFICATION: &struct iwl_tof_gen_resp_cmd - */ - TOF_NOTIFICATION = 0x11, - - /** * @POWER_TABLE_CMD: &struct iwl_device_power_cmd */ POWER_TABLE_CMD = 0x77, @@ -415,7 +406,11 @@ enum iwl_legacy_cmds { TX_ANT_CONFIGURATION_CMD = 0x98, /** - * @STATISTICS_CMD: &struct iwl_statistics_cmd + * @STATISTICS_CMD: + * one of &struct iwl_statistics_cmd, + * &struct iwl_notif_statistics_v11, + * &struct iwl_notif_statistics_v10, + * &struct iwl_notif_statistics */ STATISTICS_CMD = 0x9c, @@ -423,7 +418,7 @@ enum iwl_legacy_cmds { * @STATISTICS_NOTIFICATION: * one of &struct iwl_notif_statistics_v10, * &struct iwl_notif_statistics_v11, - * &struct iwl_notif_statistics_cdb + * &struct iwl_notif_statistics */ STATISTICS_NOTIFICATION = 0x9d, diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/d3.h b/drivers/net/wireless/intel/iwlwifi/fw/api/d3.h index 6fae02fa4cad..86ea0784e1a3 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/d3.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/d3.h @@ -224,8 +224,18 @@ struct iwl_wowlan_pattern { #define IWL_WOWLAN_MAX_PATTERNS 20 +/** + * struct iwl_wowlan_patterns_cmd - WoWLAN wakeup patterns + */ struct iwl_wowlan_patterns_cmd { + /** + * @n_patterns: number of patterns + */ __le32 n_patterns; + + /** + * @patterns: the patterns, array length in @n_patterns + */ struct iwl_wowlan_pattern patterns[]; } __packed; /* WOWLAN_PATTERN_ARRAY_API_S_VER_1 */ diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h b/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h index fdc54a5dc9de..93c06e6c1ced 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h @@ -105,6 +105,12 @@ enum iwl_data_path_subcmd_ids { HE_AIR_SNIFFER_CONFIG_CMD = 0x13, /** + * @CHEST_COLLECTOR_FILTER_CONFIG_CMD: Configure the CSI + * matrix collection, uses &struct iwl_channel_estimation_cfg + */ + CHEST_COLLECTOR_FILTER_CONFIG_CMD = 0x14, + + /** * @RX_NO_DATA_NOTIF: &struct iwl_rx_no_data */ RX_NO_DATA_NOTIF = 0xF5, @@ -156,4 +162,53 @@ struct iwl_mu_group_mgmt_notif { __le32 user_position[4]; } __packed; /* MU_GROUP_MNG_NTFY_API_S_VER_1 */ +enum iwl_channel_estimation_flags { + IWL_CHANNEL_ESTIMATION_ENABLE = BIT(0), + IWL_CHANNEL_ESTIMATION_TIMER = BIT(1), + IWL_CHANNEL_ESTIMATION_COUNTER = BIT(2), +}; + +/** + * struct iwl_channel_estimation_cfg - channel estimation reporting config + */ +struct iwl_channel_estimation_cfg { + /** + * @flags: flags, see &enum iwl_channel_estimation_flags + */ + __le32 flags; + /** + * @timer: if enabled via flags, automatically disable after this many + * microseconds + */ + __le32 timer; + /** + * @count: if enabled via flags, automatically disable after this many + * frames with channel estimation matrix were captured + */ + __le32 count; + /** + * @rate_n_flags_mask: only try to record the channel estimation matrix + * if the rate_n_flags value for the received frame (let's call + * that rx_rnf) matches the mask/value given here like this: + * (rx_rnf & rate_n_flags_mask) == rate_n_flags_val. + */ + __le32 rate_n_flags_mask; + /** + * @rate_n_flags_val: see @rate_n_flags_mask + */ + __le32 rate_n_flags_val; + /** + * @reserved: reserved (for alignment) + */ + __le32 reserved; + /** + * @frame_types: bitmap of frame types to capture, the received frame's + * subtype|type takes 6 bits in the frame and the corresponding bit + * in this field must be set to 1 to capture channel estimation for + * that frame type. Set to all-ones to enable capturing for all + * frame types. + */ + __le64 frame_types; +} __packed; /* CHEST_COLLECTOR_FILTER_CMD_API_S_VER_1 */ + #endif /* __iwl_fw_api_datapath_h__ */ diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h b/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h index dc1fa377087a..988584973aba 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h @@ -335,29 +335,11 @@ struct iwl_dbg_mem_access_rsp { __le32 data[]; } __packed; /* DEBUG_(U|L)MAC_RD_WR_RSP_API_S_VER_1 */ -#define CONT_REC_COMMAND_SIZE 80 -#define ENABLE_CONT_RECORDING 0x15 -#define DISABLE_CONT_RECORDING 0x16 +#define LDBG_CFG_COMMAND_SIZE 80 #define BUFFER_ALLOCATION 0x27 #define START_DEBUG_RECORDING 0x29 #define STOP_DEBUG_RECORDING 0x2A -/* - * struct iwl_continuous_record_mode - recording mode - */ -struct iwl_continuous_record_mode { - __le16 enable_recording; -} __packed; - -/* - * struct iwl_continuous_record_cmd - enable/disable continuous recording - */ -struct iwl_continuous_record_cmd { - struct iwl_continuous_record_mode record_mode; - u8 pad[CONT_REC_COMMAND_SIZE - - sizeof(struct iwl_continuous_record_mode)]; -} __packed; - /* maximum fragments to be allocated per target of allocationId */ #define IWL_BUFFER_LOCATION_MAX_FRAGS 2 @@ -385,4 +367,17 @@ struct iwl_buffer_allocation_cmd { struct iwl_fragment_data fragments[IWL_BUFFER_LOCATION_MAX_FRAGS]; } __packed; /* BUFFER_ALLOCATION_CMD_API_S_VER_1 */ +/** + * struct iwl_ldbg_config_cmd - LDBG config command + * @type: configuration type + * @pad: reserved space for type-dependent data + */ +struct iwl_ldbg_config_cmd { + __le32 type; + union { + u8 pad[LDBG_CFG_COMMAND_SIZE - sizeof(__le32)]; + struct iwl_buffer_allocation_cmd buffer_allocation; + }; /* LDBG_CFG_BODY_API_U_VER_2 (partially) */ +} __packed; /* LDBG_CFG_CMD_API_S_VER_2 */ + #endif /* __iwl_fw_api_debug_h__ */ diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/location.h b/drivers/net/wireless/intel/iwlwifi/fw/api/location.h new file mode 100644 index 000000000000..6da91ec0df55 --- /dev/null +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/location.h @@ -0,0 +1,711 @@ +/****************************************************************************** + * + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * Copyright(c) 2015 - 2017 Intel Deutschland GmbH + * Copyright (C) 2018 Intel Corporation + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * The full GNU General Public License is included in this distribution + * in the file called COPYING. + * + * Contact Information: + * Intel Linux Wireless <linuxwifi@intel.com> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + * + * BSD LICENSE + * + * Copyright(c) 2015 - 2017 Intel Deutschland GmbH + * Copyright (C) 2018 Intel Corporation + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * + *****************************************************************************/ +#ifndef __iwl_fw_api_location_h__ +#define __iwl_fw_api_location_h__ + +/** + * enum iwl_location_subcmd_ids - location group command IDs + */ +enum iwl_location_subcmd_ids { + /** + * @TOF_RANGE_REQ_CMD: TOF ranging request, + * uses &struct iwl_tof_range_req_cmd + */ + TOF_RANGE_REQ_CMD = 0x0, + /** + * @TOF_CONFIG_CMD: TOF configuration, uses &struct iwl_tof_config_cmd + */ + TOF_CONFIG_CMD = 0x1, + /** + * @TOF_RANGE_ABORT_CMD: abort ongoing ranging, uses + * &struct iwl_tof_range_abort_cmd + */ + TOF_RANGE_ABORT_CMD = 0x2, + /** + * @TOF_RANGE_REQ_EXT_CMD: TOF extended ranging config, + * uses &struct iwl_tof_range_request_ext_cmd + */ + TOF_RANGE_REQ_EXT_CMD = 0x3, + /** + * @TOF_RESPONDER_CONFIG_CMD: FTM responder configuration, + * uses &struct iwl_tof_responder_config_cmd + */ + TOF_RESPONDER_CONFIG_CMD = 0x4, + /** + * @TOF_RESPONDER_DYN_CONFIG_CMD: FTM dynamic configuration, + * uses &struct iwl_tof_responder_dyn_config_cmd + */ + TOF_RESPONDER_DYN_CONFIG_CMD = 0x5, + /** + * @CSI_HEADER_NOTIFICATION: CSI header + */ + CSI_HEADER_NOTIFICATION = 0xFA, + /** + * @CSI_CHUNKS_NOTIFICATION: CSI chunk, + * uses &struct iwl_csi_chunk_notification + */ + CSI_CHUNKS_NOTIFICATION = 0xFB, + /** + * @TOF_LC_NOTIF: used for LCI/civic location, contains just + * the action frame + */ + TOF_LC_NOTIF = 0xFC, + /** + * @TOF_RESPONDER_STATS: FTM responder statistics notification, + * uses &struct iwl_ftm_responder_stats + */ + TOF_RESPONDER_STATS = 0xFD, + /** + * @TOF_MCSI_DEBUG_NOTIF: MCSI debug notification, uses + * &struct iwl_tof_mcsi_notif + */ + TOF_MCSI_DEBUG_NOTIF = 0xFE, + /** + * @TOF_RANGE_RESPONSE_NOTIF: ranging response, using + * &struct iwl_tof_range_rsp_ntfy + */ + TOF_RANGE_RESPONSE_NOTIF = 0xFF, +}; + +/** + * struct iwl_tof_config_cmd - ToF configuration + * @tof_disabled: indicates if ToF is disabled (or not) + * @one_sided_disabled: indicates if one-sided is disabled (or not) + * @is_debug_mode: indiciates if debug mode is active + * @is_buf_required: indicates if channel estimation buffer is required + */ +struct iwl_tof_config_cmd { + u8 tof_disabled; + u8 one_sided_disabled; + u8 is_debug_mode; + u8 is_buf_required; +} __packed; + +/** + * enum iwl_tof_bandwidth - values for iwl_tof_range_req_ap_entry.bandwidth + * @IWL_TOF_BW_20_LEGACY: 20 MHz non-HT + * @IWL_TOF_BW_20_HT: 20 MHz HT + * @IWL_TOF_BW_40: 40 MHz + * @IWL_TOF_BW_80: 80 MHz + * @IWL_TOF_BW_160: 160 MHz + */ +enum iwl_tof_bandwidth { + IWL_TOF_BW_20_LEGACY, + IWL_TOF_BW_20_HT, + IWL_TOF_BW_40, + IWL_TOF_BW_80, + IWL_TOF_BW_160, +}; /* LOCAT_BW_TYPE_E */ + +/* + * enum iwl_tof_algo_type - Algorithym type for range measurement request + */ +enum iwl_tof_algo_type { + IWL_TOF_ALGO_TYPE_MAX_LIKE = 0, + IWL_TOF_ALGO_TYPE_LINEAR_REG = 1, + IWL_TOF_ALGO_TYPE_FFT = 2, + + /* Keep last */ + IWL_TOF_ALGO_TYPE_INVALID, +}; /* ALGO_TYPE_E */ + +/* + * enum iwl_tof_mcsi_ntfy - Enable/Disable MCSI notifications + */ +enum iwl_tof_mcsi_enable { + IWL_TOF_MCSI_DISABLED = 0, + IWL_TOF_MCSI_ENABLED = 1, +}; /* MCSI_ENABLE_E */ + +/** + * enum iwl_tof_responder_cmd_valid_field - valid fields in the responder cfg + * @IWL_TOF_RESPONDER_CMD_VALID_CHAN_INFO: channel info is valid + * @IWL_TOF_RESPONDER_CMD_VALID_TOA_OFFSET: ToA offset is valid + * @IWL_TOF_RESPONDER_CMD_VALID_COMMON_CALIB: common calibration mode is valid + * @IWL_TOF_RESPONDER_CMD_VALID_SPECIFIC_CALIB: spefici calibration mode is + * valid + * @IWL_TOF_RESPONDER_CMD_VALID_BSSID: BSSID is valid + * @IWL_TOF_RESPONDER_CMD_VALID_TX_ANT: TX antenna is valid + * @IWL_TOF_RESPONDER_CMD_VALID_ALGO_TYPE: algorithm type is valid + * @IWL_TOF_RESPONDER_CMD_VALID_NON_ASAP_SUPPORT: non-ASAP support is valid + * @IWL_TOF_RESPONDER_CMD_VALID_STATISTICS_REPORT_SUPPORT: statistics report + * support is valid + * @IWL_TOF_RESPONDER_CMD_VALID_MCSI_NOTIF_SUPPORT: MCSI notification support + * is valid + * @IWL_TOF_RESPONDER_CMD_VALID_FAST_ALGO_SUPPORT: fast algorithm support + * is valid + * @IWL_TOF_RESPONDER_CMD_VALID_RETRY_ON_ALGO_FAIL: retry on algorithm failure + * is valid + * @IWL_TOF_RESPONDER_CMD_VALID_STA_ID: station ID is valid + */ +enum iwl_tof_responder_cmd_valid_field { + IWL_TOF_RESPONDER_CMD_VALID_CHAN_INFO = BIT(0), + IWL_TOF_RESPONDER_CMD_VALID_TOA_OFFSET = BIT(1), + IWL_TOF_RESPONDER_CMD_VALID_COMMON_CALIB = BIT(2), + IWL_TOF_RESPONDER_CMD_VALID_SPECIFIC_CALIB = BIT(3), + IWL_TOF_RESPONDER_CMD_VALID_BSSID = BIT(4), + IWL_TOF_RESPONDER_CMD_VALID_TX_ANT = BIT(5), + IWL_TOF_RESPONDER_CMD_VALID_ALGO_TYPE = BIT(6), + IWL_TOF_RESPONDER_CMD_VALID_NON_ASAP_SUPPORT = BIT(7), + IWL_TOF_RESPONDER_CMD_VALID_STATISTICS_REPORT_SUPPORT = BIT(8), + IWL_TOF_RESPONDER_CMD_VALID_MCSI_NOTIF_SUPPORT = BIT(9), + IWL_TOF_RESPONDER_CMD_VALID_FAST_ALGO_SUPPORT = BIT(10), + IWL_TOF_RESPONDER_CMD_VALID_RETRY_ON_ALGO_FAIL = BIT(11), + IWL_TOF_RESPONDER_CMD_VALID_STA_ID = BIT(12), +}; + +/** + * enum iwl_tof_responder_cfg_flags - responder configuration flags + * @IWL_TOF_RESPONDER_FLAGS_NON_ASAP_SUPPORT: non-ASAP support + * @IWL_TOF_RESPONDER_FLAGS_REPORT_STATISTICS: report statistics + * @IWL_TOF_RESPONDER_FLAGS_REPORT_MCSI: report MCSI + * @IWL_TOF_RESPONDER_FLAGS_ALGO_TYPE: algorithm type + * @IWL_TOF_RESPONDER_FLAGS_TOA_OFFSET_MODE: ToA offset mode + * @IWL_TOF_RESPONDER_FLAGS_COMMON_CALIB_MODE: common calibration mode + * @IWL_TOF_RESPONDER_FLAGS_SPECIFIC_CALIB_MODE: specific calibration mode + * @IWL_TOF_RESPONDER_FLAGS_FAST_ALGO_SUPPORT: fast algorithm support + * @IWL_TOF_RESPONDER_FLAGS_RETRY_ON_ALGO_FAIL: retry on algorithm fail + * @IWL_TOF_RESPONDER_FLAGS_FTM_TX_ANT: TX antenna mask + */ +enum iwl_tof_responder_cfg_flags { + IWL_TOF_RESPONDER_FLAGS_NON_ASAP_SUPPORT = BIT(0), + IWL_TOF_RESPONDER_FLAGS_REPORT_STATISTICS = BIT(1), + IWL_TOF_RESPONDER_FLAGS_REPORT_MCSI = BIT(2), + IWL_TOF_RESPONDER_FLAGS_ALGO_TYPE = BIT(3) | BIT(4) | BIT(5), + IWL_TOF_RESPONDER_FLAGS_TOA_OFFSET_MODE = BIT(6), + IWL_TOF_RESPONDER_FLAGS_COMMON_CALIB_MODE = BIT(7), + IWL_TOF_RESPONDER_FLAGS_SPECIFIC_CALIB_MODE = BIT(8), + IWL_TOF_RESPONDER_FLAGS_FAST_ALGO_SUPPORT = BIT(9), + IWL_TOF_RESPONDER_FLAGS_RETRY_ON_ALGO_FAIL = BIT(10), + IWL_TOF_RESPONDER_FLAGS_FTM_TX_ANT = RATE_MCS_ANT_ABC_MSK, +}; + +/** + * struct iwl_tof_responder_config_cmd - ToF AP mode (for debug) + * @cmd_valid_fields: &iwl_tof_responder_cmd_valid_field + * @responder_cfg_flags: &iwl_tof_responder_cfg_flags + * @bandwidth: current AP Bandwidth: &enum iwl_tof_bandwidth + * @rate: current AP rate + * @channel_num: current AP Channel + * @ctrl_ch_position: coding of the control channel position relative to + * the center frequency, see iwl_mvm_get_ctrl_pos() + * @sta_id: index of the AP STA when in AP mode + * @reserved1: reserved + * @toa_offset: Artificial addition [pSec] for the ToA - to be used for debug + * purposes, simulating station movement by adding various values + * to this field + * @common_calib: XVT: common calibration value + * @specific_calib: XVT: specific calibration value + * @bssid: Current AP BSSID + * @reserved2: reserved + */ +struct iwl_tof_responder_config_cmd { + __le32 cmd_valid_fields; + __le32 responder_cfg_flags; + u8 bandwidth; + u8 rate; + u8 channel_num; + u8 ctrl_ch_position; + u8 sta_id; + u8 reserved1; + __le16 toa_offset; + __le16 common_calib; + __le16 specific_calib; + u8 bssid[ETH_ALEN]; + __le16 reserved2; +} __packed; /* TOF_RESPONDER_CONFIG_CMD_API_S_VER_6 */ + +#define IWL_LCI_CIVIC_IE_MAX_SIZE 400 + +/** + * struct iwl_tof_responder_dyn_config_cmd - Dynamic responder settings + * @lci_len: The length of the 1st (LCI) part in the @lci_civic buffer + * @civic_len: The length of the 2nd (CIVIC) part in the @lci_civic buffer + * @lci_civic: The LCI/CIVIC buffer. LCI data (if exists) comes first, then, if + * needed, 0-padding such that the next part is dword-aligned, then CIVIC + * data (if exists) follows, and then 0-padding again to complete a + * 4-multiple long buffer. + */ +struct iwl_tof_responder_dyn_config_cmd { + __le32 lci_len; + __le32 civic_len; + u8 lci_civic[]; +} __packed; /* TOF_RESPONDER_DYN_CONFIG_CMD_API_S_VER_2 */ + +/** + * struct iwl_tof_range_request_ext_cmd - extended range req for WLS + * @tsf_timer_offset_msec: the recommended time offset (mSec) from the AP's TSF + * @reserved: reserved + * @min_delta_ftm: Minimal time between two consecutive measurements, + * in units of 100us. 0 means no preference by station + * @ftm_format_and_bw20M: FTM Channel Spacing/Format for 20MHz: recommended + * value be sent to the AP + * @ftm_format_and_bw40M: FTM Channel Spacing/Format for 40MHz: recommended + * value to be sent to the AP + * @ftm_format_and_bw80M: FTM Channel Spacing/Format for 80MHz: recommended + * value to be sent to the AP + */ +struct iwl_tof_range_req_ext_cmd { + __le16 tsf_timer_offset_msec; + __le16 reserved; + u8 min_delta_ftm; + u8 ftm_format_and_bw20M; + u8 ftm_format_and_bw40M; + u8 ftm_format_and_bw80M; +} __packed; + +/** + * enum iwl_tof_location_query - values for query bitmap + * @IWL_TOF_LOC_LCI: query LCI + * @IWL_TOF_LOC_CIVIC: query civic + */ +enum iwl_tof_location_query { + IWL_TOF_LOC_LCI = 0x01, + IWL_TOF_LOC_CIVIC = 0x02, +}; + + /** + * struct iwl_tof_range_req_ap_entry - AP configuration parameters + * @channel_num: Current AP Channel + * @bandwidth: Current AP Bandwidth. One of iwl_tof_bandwidth. + * @tsf_delta_direction: TSF relatively to the subject AP + * @ctrl_ch_position: Coding of the control channel position relative to the + * center frequency, see iwl_mvm_get_ctrl_pos(). + * @bssid: AP's BSSID + * @measure_type: Measurement type: 0 - two sided, 1 - One sided + * @num_of_bursts: Recommended value to be sent to the AP. 2s Exponent of the + * number of measurement iterations (min 2^0 = 1, max 2^14) + * @burst_period: Recommended value to be sent to the AP. Measurement + * periodicity In units of 100ms. ignored if num_of_bursts = 0 + * @samples_per_burst: 2-sided: the number of FTMs pairs in single Burst (1-31); + * 1-sided: how many rts/cts pairs should be used per burst. + * @retries_per_sample: Max number of retries that the LMAC should send + * in case of no replies by the AP. + * @tsf_delta: TSF Delta in units of microseconds. + * The difference between the AP TSF and the device local clock. + * @location_req: Location Request Bit[0] LCI should be sent in the FTMR; + * Bit[1] Civic should be sent in the FTMR + * @asap_mode: 0 - non asap mode, 1 - asap mode (not relevant for one sided) + * @enable_dyn_ack: Enable Dynamic ACK BW. + * 0: Initiator interact with regular AP; + * 1: Initiator interact with Responder machine: need to send the + * Initiator Acks with HT 40MHz / 80MHz, since the Responder should + * use it for its ch est measurement (this flag will be set when we + * configure the opposite machine to be Responder). + * @rssi: Last received value + * legal values: -128-0 (0x7f). above 0x0 indicating an invalid value. + * @algo_type: &enum iwl_tof_algo_type + * @notify_mcsi: &enum iwl_tof_mcsi_ntfy. + * @reserved: For alignment and future use + */ +struct iwl_tof_range_req_ap_entry { + u8 channel_num; + u8 bandwidth; + u8 tsf_delta_direction; + u8 ctrl_ch_position; + u8 bssid[ETH_ALEN]; + u8 measure_type; + u8 num_of_bursts; + __le16 burst_period; + u8 samples_per_burst; + u8 retries_per_sample; + __le32 tsf_delta; + u8 location_req; + u8 asap_mode; + u8 enable_dyn_ack; + s8 rssi; + u8 algo_type; + u8 notify_mcsi; + __le16 reserved; +} __packed; /* LOCATION_RANGE_REQ_AP_ENTRY_CMD_API_S_VER_3 */ + +/** + * enum iwl_tof_response_mode + * @IWL_MVM_TOF_RESPONSE_ASAP: report each AP measurement separately as soon as + * possible (not supported for this release) + * @IWL_MVM_TOF_RESPONSE_TIMEOUT: report all AP measurements as a batch upon + * timeout expiration + * @IWL_MVM_TOF_RESPONSE_COMPLETE: report all AP measurements as a batch at the + * earlier of: measurements completion / timeout + * expiration. + */ +enum iwl_tof_response_mode { + IWL_MVM_TOF_RESPONSE_ASAP, + IWL_MVM_TOF_RESPONSE_TIMEOUT, + IWL_MVM_TOF_RESPONSE_COMPLETE, +}; + +/** + * enum iwl_tof_initiator_flags + * + * @IWL_TOF_INITIATOR_FLAGS_FAST_ALGO_DISABLED: disable fast algo, meaning run + * the algo on ant A+B, instead of only one of them. + * @IWL_TOF_INITIATOR_FLAGS_RX_CHAIN_SEL_A: open RX antenna A for FTMs RX + * @IWL_TOF_INITIATOR_FLAGS_RX_CHAIN_SEL_B: open RX antenna B for FTMs RX + * @IWL_TOF_INITIATOR_FLAGS_RX_CHAIN_SEL_C: open RX antenna C for FTMs RX + * @IWL_TOF_INITIATOR_FLAGS_TX_CHAIN_SEL_A: use antenna A fo TX ACKs during FTM + * @IWL_TOF_INITIATOR_FLAGS_TX_CHAIN_SEL_B: use antenna B fo TX ACKs during FTM + * @IWL_TOF_INITIATOR_FLAGS_TX_CHAIN_SEL_C: use antenna C fo TX ACKs during FTM + * @IWL_TOF_INITIATOR_FLAGS_MINDELTA_NO_PREF: no preference for minDeltaFTM + */ +enum iwl_tof_initiator_flags { + IWL_TOF_INITIATOR_FLAGS_FAST_ALGO_DISABLED = BIT(0), + IWL_TOF_INITIATOR_FLAGS_RX_CHAIN_SEL_A = BIT(1), + IWL_TOF_INITIATOR_FLAGS_RX_CHAIN_SEL_B = BIT(2), + IWL_TOF_INITIATOR_FLAGS_RX_CHAIN_SEL_C = BIT(3), + IWL_TOF_INITIATOR_FLAGS_TX_CHAIN_SEL_A = BIT(4), + IWL_TOF_INITIATOR_FLAGS_TX_CHAIN_SEL_B = BIT(5), + IWL_TOF_INITIATOR_FLAGS_TX_CHAIN_SEL_C = BIT(6), + IWL_TOF_INITIATOR_FLAGS_MINDELTA_NO_PREF = BIT(7), +}; /* LOCATION_RANGE_REQ_CMD_API_S_VER_5 */ + +#define IWL_MVM_TOF_MAX_APS 5 +#define IWL_MVM_TOF_MAX_TWO_SIDED_APS 5 + +/** + * struct iwl_tof_range_req_cmd - start measurement cmd + * @initiator_flags: see flags @ iwl_tof_initiator_flags + * @request_id: A Token incremented per request. The same Token will be + * sent back in the range response + * @initiator: 0- NW initiated, 1 - Client Initiated + * @one_sided_los_disable: '0'- run ML-Algo for both ToF/OneSided, + * '1' - run ML-Algo for ToF only + * @req_timeout: Requested timeout of the response in units of 100ms. + * This is equivalent to the session time configured to the + * LMAC in Initiator Request + * @report_policy: Supported partially for this release: For current release - + * the range report will be uploaded as a batch when ready or + * when the session is done (successfully / partially). + * one of iwl_tof_response_mode. + * @reserved0: reserved + * @num_of_ap: Number of APs to measure (error if > IWL_MVM_TOF_MAX_APS) + * @macaddr_random: '0' Use default source MAC address (i.e. p2_p), + * '1' Use MAC Address randomization according to the below + * @range_req_bssid: ranging request BSSID + * @macaddr_template: MAC address template to use for non-randomized bits + * @macaddr_mask: Bits set to 0 shall be copied from the MAC address template. + * Bits set to 1 shall be randomized by the UMAC + * @ftm_rx_chains: Rx chain to open to receive Responder's FTMs (XVT) + * @ftm_tx_chains: Tx chain to send the ack to the Responder FTM (XVT) + * @common_calib: The common calib value to inject to this measurement calc + * @specific_calib: The specific calib value to inject to this measurement calc + * @ap: per-AP request data + */ +struct iwl_tof_range_req_cmd { + __le32 initiator_flags; + u8 request_id; + u8 initiator; + u8 one_sided_los_disable; + u8 req_timeout; + u8 report_policy; + u8 reserved0; + u8 num_of_ap; + u8 macaddr_random; + u8 range_req_bssid[ETH_ALEN]; + u8 macaddr_template[ETH_ALEN]; + u8 macaddr_mask[ETH_ALEN]; + u8 ftm_rx_chains; + u8 ftm_tx_chains; + __le16 common_calib; + __le16 specific_calib; + struct iwl_tof_range_req_ap_entry ap[IWL_MVM_TOF_MAX_APS]; +} __packed; +/* LOCATION_RANGE_REQ_CMD_API_S_VER_5 */ + +/* + * enum iwl_tof_range_request_status - status of the sent request + * @IWL_TOF_RANGE_REQUEST_STATUS_SUCCESSFUL - FW successfully received the + * request + * @IWL_TOF_RANGE_REQUEST_STATUS_BUSY - FW is busy with a previous request, the + * sent request will not be handled + */ +enum iwl_tof_range_request_status { + IWL_TOF_RANGE_REQUEST_STATUS_SUCCESS, + IWL_TOF_RANGE_REQUEST_STATUS_BUSY, +}; + +/** + * enum iwl_tof_entry_status + * + * @IWL_TOF_ENTRY_SUCCESS: successful measurement. + * @IWL_TOF_ENTRY_GENERAL_FAILURE: General failure. + * @IWL_TOF_ENTRY_NO_RESPONSE: Responder didn't reply to the request. + * @IWL_TOF_ENTRY_REQUEST_REJECTED: Responder rejected the request. + * @IWL_TOF_ENTRY_NOT_SCHEDULED: Time event was scheduled but not called yet. + * @IWL_TOF_ENTRY_TIMING_MEASURE_TIMEOUT: Time event triggered but no + * measurement was completed. + * @IWL_TOF_ENTRY_TARGET_DIFF_CH_CANNOT_CHANGE: No range due inability to switch + * from the primary channel. + * @IWL_TOF_ENTRY_RANGE_NOT_SUPPORTED: Device doesn't support FTM. + * @IWL_TOF_ENTRY_REQUEST_ABORT_UNKNOWN_REASON: Request aborted due to unknown + * reason. + * @IWL_TOF_ENTRY_LOCATION_INVALID_T1_T4_TIME_STAMP: Failure due to invalid + * T1/T4. + * @IWL_TOF_ENTRY_11MC_PROTOCOL_FAILURE: Failure due to invalid FTM frame + * structure. + * @IWL_TOF_ENTRY_REQUEST_CANNOT_SCHED: Request cannot be scheduled. + * @IWL_TOF_ENTRY_RESPONDER_CANNOT_COLABORATE: Responder cannot serve the + * initiator for some period, period supplied in @refusal_period. + * @IWL_TOF_ENTRY_BAD_REQUEST_ARGS: Bad request arguments. + * @IWL_TOF_ENTRY_WIFI_NOT_ENABLED: Wifi not enabled. + * @IWL_TOF_ENTRY_RESPONDER_OVERRIDE_PARAMS: Responder override the original + * parameters within the current session. + */ +enum iwl_tof_entry_status { + IWL_TOF_ENTRY_SUCCESS = 0, + IWL_TOF_ENTRY_GENERAL_FAILURE = 1, + IWL_TOF_ENTRY_NO_RESPONSE = 2, + IWL_TOF_ENTRY_REQUEST_REJECTED = 3, + IWL_TOF_ENTRY_NOT_SCHEDULED = 4, + IWL_TOF_ENTRY_TIMING_MEASURE_TIMEOUT = 5, + IWL_TOF_ENTRY_TARGET_DIFF_CH_CANNOT_CHANGE = 6, + IWL_TOF_ENTRY_RANGE_NOT_SUPPORTED = 7, + IWL_TOF_ENTRY_REQUEST_ABORT_UNKNOWN_REASON = 8, + IWL_TOF_ENTRY_LOCATION_INVALID_T1_T4_TIME_STAMP = 9, + IWL_TOF_ENTRY_11MC_PROTOCOL_FAILURE = 10, + IWL_TOF_ENTRY_REQUEST_CANNOT_SCHED = 11, + IWL_TOF_ENTRY_RESPONDER_CANNOT_COLABORATE = 12, + IWL_TOF_ENTRY_BAD_REQUEST_ARGS = 13, + IWL_TOF_ENTRY_WIFI_NOT_ENABLED = 14, + IWL_TOF_ENTRY_RESPONDER_OVERRIDE_PARAMS = 15, +}; /* LOCATION_RANGE_RSP_AP_ENTRY_NTFY_API_S_VER_2 */ + +/** + * struct iwl_tof_range_rsp_ap_entry_ntfy - AP parameters (response) + * @bssid: BSSID of the AP + * @measure_status: current APs measurement status, one of + * &enum iwl_tof_entry_status. + * @measure_bw: Current AP Bandwidth: 0 20MHz, 1 40MHz, 2 80MHz + * @rtt: The Round Trip Time that took for the last measurement for + * current AP [pSec] + * @rtt_variance: The Variance of the RTT values measured for current AP + * @rtt_spread: The Difference between the maximum and the minimum RTT + * values measured for current AP in the current session [pSec] + * @rssi: RSSI as uploaded in the Channel Estimation notification + * @rssi_spread: The Difference between the maximum and the minimum RSSI values + * measured for current AP in the current session + * @reserved: reserved + * @refusal_period: refusal period in case of + * @IWL_TOF_ENTRY_RESPONDER_CANNOT_COLABORATE [sec] + * @range: Measured range [cm] + * @range_variance: Measured range variance [cm] + * @timestamp: The GP2 Clock [usec] where Channel Estimation notification was + * uploaded by the LMAC + * @t2t3_initiator: as calculated from the algo in the initiator + * @t1t4_responder: as calculated from the algo in the responder + * @common_calib: Calib val that was used in for this AP measurement + * @specific_calib: val that was used in for this AP measurement + * @papd_calib_output: The result of the tof papd calibration that was injected + * into the algorithm. + */ +struct iwl_tof_range_rsp_ap_entry_ntfy { + u8 bssid[ETH_ALEN]; + u8 measure_status; + u8 measure_bw; + __le32 rtt; + __le32 rtt_variance; + __le32 rtt_spread; + s8 rssi; + u8 rssi_spread; + u8 reserved; + u8 refusal_period; + __le32 range; + __le32 range_variance; + __le32 timestamp; + __le32 t2t3_initiator; + __le32 t1t4_responder; + __le16 common_calib; + __le16 specific_calib; + __le32 papd_calib_output; +} __packed; /* LOCATION_RANGE_RSP_AP_ETRY_NTFY_API_S_VER_3 */ + +/** + * enum iwl_tof_response_status - tof response status + * + * @IWL_TOF_RESPONSE_SUCCESS: successful range. + * @IWL_TOF_RESPONSE_TIMEOUT: request aborted due to timeout expiration. + * partial result of ranges done so far is included in the response. + * @IWL_TOF_RESPONSE_ABORTED: Measurement aborted by command. + * @IWL_TOF_RESPONSE_FAILED: Measurement request command failed. + */ +enum iwl_tof_response_status { + IWL_TOF_RESPONSE_SUCCESS = 0, + IWL_TOF_RESPONSE_TIMEOUT = 1, + IWL_TOF_RESPONSE_ABORTED = 4, + IWL_TOF_RESPONSE_FAILED = 5, +}; /* LOCATION_RNG_RSP_STATUS */ + +/** + * struct iwl_tof_range_rsp_ntfy - ranging response notification + * @request_id: A Token ID of the corresponding Range request + * @request_status: status of current measurement session, one of + * &enum iwl_tof_response_status. + * @last_in_batch: reprot policy (when not all responses are uploaded at once) + * @num_of_aps: Number of APs to measure (error if > IWL_MVM_TOF_MAX_APS) + * @ap: per-AP data + */ +struct iwl_tof_range_rsp_ntfy { + u8 request_id; + u8 request_status; + u8 last_in_batch; + u8 num_of_aps; + struct iwl_tof_range_rsp_ap_entry_ntfy ap[IWL_MVM_TOF_MAX_APS]; +} __packed; + +#define IWL_MVM_TOF_MCSI_BUF_SIZE (245) +/** + * struct iwl_tof_mcsi_notif - used for debug + * @token: token ID for the current session + * @role: '0' - initiator, '1' - responder + * @reserved: reserved + * @initiator_bssid: initiator machine + * @responder_bssid: responder machine + * @mcsi_buffer: debug data + */ +struct iwl_tof_mcsi_notif { + u8 token; + u8 role; + __le16 reserved; + u8 initiator_bssid[ETH_ALEN]; + u8 responder_bssid[ETH_ALEN]; + u8 mcsi_buffer[IWL_MVM_TOF_MCSI_BUF_SIZE * 4]; +} __packed; + +/** + * struct iwl_tof_range_abort_cmd + * @request_id: corresponds to a range request + * @reserved: reserved + */ +struct iwl_tof_range_abort_cmd { + u8 request_id; + u8 reserved[3]; +} __packed; + +enum ftm_responder_stats_flags { + FTM_RESP_STAT_NON_ASAP_STARTED = BIT(0), + FTM_RESP_STAT_NON_ASAP_IN_WIN = BIT(1), + FTM_RESP_STAT_NON_ASAP_OUT_WIN = BIT(2), + FTM_RESP_STAT_TRIGGER_DUP = BIT(3), + FTM_RESP_STAT_DUP = BIT(4), + FTM_RESP_STAT_DUP_IN_WIN = BIT(5), + FTM_RESP_STAT_DUP_OUT_WIN = BIT(6), + FTM_RESP_STAT_SCHED_SUCCESS = BIT(7), + FTM_RESP_STAT_ASAP_REQ = BIT(8), + FTM_RESP_STAT_NON_ASAP_REQ = BIT(9), + FTM_RESP_STAT_ASAP_RESP = BIT(10), + FTM_RESP_STAT_NON_ASAP_RESP = BIT(11), + FTM_RESP_STAT_FAIL_INITIATOR_INACTIVE = BIT(12), + FTM_RESP_STAT_FAIL_INITIATOR_OUT_WIN = BIT(13), + FTM_RESP_STAT_FAIL_INITIATOR_RETRY_LIM = BIT(14), + FTM_RESP_STAT_FAIL_NEXT_SERVED = BIT(15), + FTM_RESP_STAT_FAIL_TRIGGER_ERR = BIT(16), + FTM_RESP_STAT_FAIL_GC = BIT(17), + FTM_RESP_STAT_SUCCESS = BIT(18), + FTM_RESP_STAT_INTEL_IE = BIT(19), + FTM_RESP_STAT_INITIATOR_ACTIVE = BIT(20), + FTM_RESP_STAT_MEASUREMENTS_AVAILABLE = BIT(21), + FTM_RESP_STAT_TRIGGER_UNKNOWN = BIT(22), + FTM_RESP_STAT_PROCESS_FAIL = BIT(23), + FTM_RESP_STAT_ACK = BIT(24), + FTM_RESP_STAT_NACK = BIT(25), + FTM_RESP_STAT_INVALID_INITIATOR_ID = BIT(26), + FTM_RESP_STAT_TIMER_MIN_DELTA = BIT(27), + FTM_RESP_STAT_INITIATOR_REMOVED = BIT(28), + FTM_RESP_STAT_INITIATOR_ADDED = BIT(29), + FTM_RESP_STAT_ERR_LIST_FULL = BIT(30), + FTM_RESP_STAT_INITIATOR_SCHED_NOW = BIT(31), +}; /* RESP_IND_E */ + +/** + * struct iwl_ftm_responder_stats - FTM responder statistics + * @addr: initiator address + * @success_ftm: number of successful ftm frames + * @ftm_per_burst: num of FTM frames that were received + * @flags: &enum ftm_responder_stats_flags + * @duration: actual duration of FTM + * @allocated_duration: time that was allocated for this FTM session + * @bw: FTM request bandwidth + * @rate: FTM request rate + * @reserved: for alingment and future use + */ +struct iwl_ftm_responder_stats { + u8 addr[ETH_ALEN]; + u8 success_ftm; + u8 ftm_per_burst; + __le32 flags; + __le32 duration; + __le32 allocated_duration; + u8 bw; + u8 rate; + __le16 reserved; +} __packed; /* TOF_RESPONDER_STATISTICS_NTFY_S_VER_2 */ + +#define IWL_CSI_CHUNK_CTL_NUM_MASK 0x3 +#define IWL_CSI_CHUNK_CTL_IDX_MASK 0xc + +struct iwl_csi_chunk_notification { + __le32 token; + __le16 seq; + __le16 ctl; + __le32 size; + u8 data[]; +} __packed; /* CSI_CHUNKS_HDR_NTFY_API_S_VER_1 */ + +#endif /* __iwl_fw_api_location_h__ */ diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/phy-ctxt.h b/drivers/net/wireless/intel/iwlwifi/fw/api/phy-ctxt.h index 45f61c6af14e..b833b80ea3d6 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/phy-ctxt.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/phy-ctxt.h @@ -8,6 +8,7 @@ * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH * Copyright(c) 2016 - 2017 Intel Deutschland GmbH + * Copyright(c) 2018 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -30,6 +31,7 @@ * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH * Copyright(c) 2016 - 2017 Intel Deutschland GmbH + * Copyright(c) 2018 Intel Corporation * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -95,17 +97,36 @@ #define PHY_VHT_CTRL_POS_4_ABOVE (0x7) /* + * struct iwl_fw_channel_info_v1 - channel information + * * @band: PHY_BAND_* * @channel: channel number * @width: PHY_[VHT|LEGACY]_CHANNEL_* * @ctrl channel: PHY_[VHT|LEGACY]_CTRL_* */ -struct iwl_fw_channel_info { +struct iwl_fw_channel_info_v1 { u8 band; u8 channel; u8 width; u8 ctrl_pos; -} __packed; +} __packed; /* CHANNEL_CONFIG_API_S_VER_1 */ + +/* + * struct iwl_fw_channel_info - channel information + * + * @channel: channel number + * @band: PHY_BAND_* + * @width: PHY_[VHT|LEGACY]_CHANNEL_* + * @ctrl channel: PHY_[VHT|LEGACY]_CTRL_* + * @reserved: for future use and alignment + */ +struct iwl_fw_channel_info { + __le32 channel; + u8 band; + u8 width; + u8 ctrl_pos; + u8 reserved; +} __packed; /*CHANNEL_CONFIG_API_S_VER_2 */ #define PHY_RX_CHAIN_DRIVER_FORCE_POS (0) #define PHY_RX_CHAIN_DRIVER_FORCE_MSK \ @@ -134,6 +155,22 @@ struct iwl_fw_channel_info { /* TODO: complete missing documentation */ /** + * struct iwl_phy_context_cmd_tail - tail of iwl_phy_ctx_cmd for alignment with + * various channel structures. + * + * @txchain_info: ??? + * @rxchain_info: ??? + * @acquisition_data: ??? + * @dsp_cfg_flags: set to 0 + */ +struct iwl_phy_context_cmd_tail { + __le32 txchain_info; + __le32 rxchain_info; + __le32 acquisition_data; + __le32 dsp_cfg_flags; +} __packed; + +/** * struct iwl_phy_context_cmd - config of the PHY context * ( PHY_CONTEXT_CMD = 0x8 ) * @id_and_color: ID and color of the relevant Binding @@ -142,10 +179,7 @@ struct iwl_fw_channel_info { * other value means apply new params after X usecs * @tx_param_color: ??? * @ci: channel info - * @txchain_info: ??? - * @rxchain_info: ??? - * @acquisition_data: ??? - * @dsp_cfg_flags: set to 0 + * @tail: command tail */ struct iwl_phy_context_cmd { /* COMMON_INDEX_HDR_API_S_VER_1 */ @@ -155,10 +189,7 @@ struct iwl_phy_context_cmd { __le32 apply_time; __le32 tx_param_color; struct iwl_fw_channel_info ci; - __le32 txchain_info; - __le32 rxchain_info; - __le32 acquisition_data; - __le32 dsp_cfg_flags; + struct iwl_phy_context_cmd_tail tail; } __packed; /* PHY_CONTEXT_CMD_API_VER_1 */ #endif /* __iwl_fw_api_phy_ctxt_h__ */ diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h b/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h index 0791a854fc8f..6e8224ce8906 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h @@ -209,8 +209,6 @@ enum iwl_rx_phy_flags { * @RX_MPDU_RES_STATUS_CSUM_OK: checksum found no errors * @RX_MPDU_RES_STATUS_STA_ID_MSK: station ID mask * @RX_MDPU_RES_STATUS_STA_ID_SHIFT: station ID bit shift - * @RX_MPDU_RES_STATUS_FILTERING_MSK: filter status - * @RX_MPDU_RES_STATUS2_FILTERING_MSK: filter status 2 */ enum iwl_mvm_rx_status { RX_MPDU_RES_STATUS_CRC_OK = BIT(0), @@ -238,8 +236,6 @@ enum iwl_mvm_rx_status { RX_MPDU_RES_STATUS_CSUM_OK = BIT(17), RX_MDPU_RES_STATUS_STA_ID_SHIFT = 24, RX_MPDU_RES_STATUS_STA_ID_MSK = 0x1f << RX_MDPU_RES_STATUS_STA_ID_SHIFT, - RX_MPDU_RES_STATUS_FILTERING_MSK = (0xc00000), - RX_MPDU_RES_STATUS2_FILTERING_MSK = (0xc0000000), }; /* 9000 series API */ @@ -337,6 +333,8 @@ enum iwl_rx_mpdu_phy_info { IWL_RX_MPDU_PHY_AMPDU = BIT(5), IWL_RX_MPDU_PHY_AMPDU_TOGGLE = BIT(6), IWL_RX_MPDU_PHY_SHORT_PREAMBLE = BIT(7), + /* short preamble is only for CCK, for non-CCK overridden by this */ + IWL_RX_MPDU_PHY_NCCK_ADDTL_NTFY = BIT(7), IWL_RX_MPDU_PHY_TSF_OVERLOAD = BIT(8), }; @@ -723,6 +721,9 @@ struct iwl_rx_mpdu_desc { #define RX_NO_DATA_FRAME_TIME_POS 0 #define RX_NO_DATA_FRAME_TIME_MSK (0xfffff << RX_NO_DATA_FRAME_TIME_POS) +#define RX_NO_DATA_RX_VEC0_HE_NSTS_MSK 0x03800000 +#define RX_NO_DATA_RX_VEC0_VHT_NSTS_MSK 0x38000000 + /** * struct iwl_rx_no_data - RX no data descriptor * @info: 7:0 frame type, 15:8 RX error type @@ -743,7 +744,7 @@ struct iwl_rx_no_data { __le32 fr_time; __le32 rate; __le32 phy_info[2]; - __le32 rx_vec[3]; + __le32 rx_vec[2]; } __packed; /* RX_NO_DATA_NTFY_API_S_VER_1 */ /** diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/stats.h b/drivers/net/wireless/intel/iwlwifi/fw/api/stats.h index 53cb622aa9ab..318843138490 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/stats.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/stats.h @@ -8,6 +8,7 @@ * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH * Copyright(c) 2016 - 2017 Intel Deutschland GmbH + * Copyright (C) 2018 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -29,6 +30,7 @@ * * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH + * Copyright (C) 2018 Intel Corporation * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -363,14 +365,7 @@ struct mvm_statistics_general_v8 { u8 reserved[4 - (NUM_MAC_INDEX % 4)]; } __packed; /* STATISTICS_GENERAL_API_S_VER_8 */ -struct mvm_statistics_general_cdb_v9 { - struct mvm_statistics_general_common_v19 common; - __le32 beacon_counter[NUM_MAC_INDEX_CDB]; - u8 beacon_average_energy[NUM_MAC_INDEX_CDB]; - u8 reserved[4 - (NUM_MAC_INDEX_CDB % 4)]; -} __packed; /* STATISTICS_GENERAL_API_S_VER_9 */ - -struct mvm_statistics_general_cdb { +struct mvm_statistics_general { struct mvm_statistics_general_common common; __le32 beacon_counter[MAC_INDEX_AUX]; u8 beacon_average_energy[MAC_INDEX_AUX]; @@ -435,11 +430,11 @@ struct iwl_notif_statistics_v11 { struct mvm_statistics_load_v1 load_stats; } __packed; /* STATISTICS_NTFY_API_S_VER_11 */ -struct iwl_notif_statistics_cdb { +struct iwl_notif_statistics { __le32 flag; struct mvm_statistics_rx rx; struct mvm_statistics_tx tx; - struct mvm_statistics_general_cdb general; + struct mvm_statistics_general general; struct mvm_statistics_load load_stats; } __packed; /* STATISTICS_NTFY_API_S_VER_13 */ diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/tdls.h b/drivers/net/wireless/intel/iwlwifi/fw/api/tdls.h index 7c6c2462d0e8..b089285ac466 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/tdls.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/tdls.h @@ -8,6 +8,7 @@ * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH * Copyright(c) 2016 - 2017 Intel Deutschland GmbH + * Copyright(c) 2018 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -30,6 +31,7 @@ * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH * Copyright(c) 2016 - 2017 Intel Deutschland GmbH + * Copyright(c) 2018 Intel Corporation * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -111,6 +113,17 @@ struct iwl_tdls_channel_switch_frame { } __packed; /* TDLS_STA_CHANNEL_SWITCH_FRAME_API_S_VER_1 */ /** + * struct iwl_tdls_channel_switch_cmd_tail - tail of iwl_tdls_channel_switch_cmd + * + * @timing: timing related data for command + * @frame: channel-switch request/response template, depending to switch_type + */ +struct iwl_tdls_channel_switch_cmd_tail { + struct iwl_tdls_channel_switch_timing timing; + struct iwl_tdls_channel_switch_frame frame; +} __packed; + +/** * struct iwl_tdls_channel_switch_cmd - TDLS channel switch command * * The command is sent to initiate a channel switch and also in response to @@ -119,15 +132,13 @@ struct iwl_tdls_channel_switch_frame { * @switch_type: see &enum iwl_tdls_channel_switch_type * @peer_sta_id: station id of TDLS peer * @ci: channel we switch to - * @timing: timing related data for command - * @frame: channel-switch request/response template, depending to switch_type + * @tail: command tail */ struct iwl_tdls_channel_switch_cmd { u8 switch_type; __le32 peer_sta_id; struct iwl_fw_channel_info ci; - struct iwl_tdls_channel_switch_timing timing; - struct iwl_tdls_channel_switch_frame frame; + struct iwl_tdls_channel_switch_cmd_tail tail; } __packed; /* TDLS_STA_CHANNEL_SWITCH_CMD_API_S_VER_1 */ /** diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/time-event.h b/drivers/net/wireless/intel/iwlwifi/fw/api/time-event.h index f824bebceb06..4621ef93a2cf 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/time-event.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/time-event.h @@ -8,6 +8,7 @@ * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH * Copyright(c) 2016 - 2017 Intel Deutschland GmbH + * Copyright(c) 2018 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -30,6 +31,7 @@ * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH * Copyright(c) 2016 - 2017 Intel Deutschland GmbH + * Copyright(c) 2018 Intel Corporation * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -318,6 +320,25 @@ struct iwl_time_event_notif { } __packed; /* MAC_TIME_EVENT_NTFY_API_S_VER_1 */ /* + * struct iwl_hs20_roc_req_tail - tail of iwl_hs20_roc_req + * + * @node_addr: Our MAC Address + * @reserved: reserved for alignment + * @apply_time: GP2 value to start (should always be the current GP2 value) + * @apply_time_max_delay: Maximum apply time delay value in TU. Defines max + * time by which start of the event is allowed to be postponed. + * @duration: event duration in TU To calculate event duration: + * timeEventDuration = min(duration, remainingQuota) + */ +struct iwl_hs20_roc_req_tail { + u8 node_addr[ETH_ALEN]; + __le16 reserved; + __le32 apply_time; + __le32 apply_time_max_delay; + __le32 duration; +} __packed; + +/* * Aux ROC command * * Command requests the firmware to create a time event for a certain duration @@ -336,13 +357,6 @@ struct iwl_time_event_notif { * @sta_id_and_color: station id and color, resumed during "Remain On Channel" * activity. * @channel_info: channel info - * @node_addr: Our MAC Address - * @reserved: reserved for alignment - * @apply_time: GP2 value to start (should always be the current GP2 value) - * @apply_time_max_delay: Maximum apply time delay value in TU. Defines max - * time by which start of the event is allowed to be postponed. - * @duration: event duration in TU To calculate event duration: - * timeEventDuration = min(duration, remainingQuota) */ struct iwl_hs20_roc_req { /* COMMON_INDEX_HDR_API_S_VER_1 hdr */ @@ -351,11 +365,7 @@ struct iwl_hs20_roc_req { __le32 event_unique_id; __le32 sta_id_and_color; struct iwl_fw_channel_info channel_info; - u8 node_addr[ETH_ALEN]; - __le16 reserved; - __le32 apply_time; - __le32 apply_time_max_delay; - __le32 duration; + struct iwl_hs20_roc_req_tail tail; } __packed; /* HOT_SPOT_CMD_API_S_VER_1 */ /* diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/tof.h b/drivers/net/wireless/intel/iwlwifi/fw/api/tof.h deleted file mode 100644 index 7328a1606146..000000000000 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/tof.h +++ /dev/null @@ -1,393 +0,0 @@ -/****************************************************************************** - * - * This file is provided under a dual BSD/GPLv2 license. When using or - * redistributing this file, you may do so under either license. - * - * GPL LICENSE SUMMARY - * - * Copyright(c) 2015 - 2017 Intel Deutschland GmbH - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of version 2 of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * The full GNU General Public License is included in this distribution - * in the file called COPYING. - * - * Contact Information: - * Intel Linux Wireless <linuxwifi@intel.com> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - * BSD LICENSE - * - * Copyright(c) 2015 - 2017 Intel Deutschland GmbH - * All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in - * the documentation and/or other materials provided with the - * distribution. - * * Neither the name Intel Corporation nor the names of its - * contributors may be used to endorse or promote products derived - * from this software without specific prior written permission. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - * - *****************************************************************************/ -#ifndef __iwl_fw_api_tof_h__ -#define __iwl_fw_api_tof_h__ - -/* ToF sub-group command IDs */ -enum iwl_mvm_tof_sub_grp_ids { - TOF_RANGE_REQ_CMD = 0x1, - TOF_CONFIG_CMD = 0x2, - TOF_RANGE_ABORT_CMD = 0x3, - TOF_RANGE_REQ_EXT_CMD = 0x4, - TOF_RESPONDER_CONFIG_CMD = 0x5, - TOF_NW_INITIATED_RES_SEND_CMD = 0x6, - TOF_NEIGHBOR_REPORT_REQ_CMD = 0x7, - TOF_NEIGHBOR_REPORT_RSP_NOTIF = 0xFC, - TOF_NW_INITIATED_REQ_RCVD_NOTIF = 0xFD, - TOF_RANGE_RESPONSE_NOTIF = 0xFE, - TOF_MCSI_DEBUG_NOTIF = 0xFB, -}; - -/** - * struct iwl_tof_config_cmd - ToF configuration - * @tof_disabled: 0 enabled, 1 - disabled - * @one_sided_disabled: 0 enabled, 1 - disabled - * @is_debug_mode: 1 debug mode, 0 - otherwise - * @is_buf_required: 1 channel estimation buffer required, 0 - otherwise - */ -struct iwl_tof_config_cmd { - __le32 sub_grp_cmd_id; - u8 tof_disabled; - u8 one_sided_disabled; - u8 is_debug_mode; - u8 is_buf_required; -} __packed; - -/** - * struct iwl_tof_responder_config_cmd - ToF AP mode (for debug) - * @burst_period: future use: (currently hard coded in the LMAC) - * The interval between two sequential bursts. - * @min_delta_ftm: future use: (currently hard coded in the LMAC) - * The minimum delay between two sequential FTM Responses - * in the same burst. - * @burst_duration: future use: (currently hard coded in the LMAC) - * The total time for all FTMs handshake in the same burst. - * Affect the time events duration in the LMAC. - * @num_of_burst_exp: future use: (currently hard coded in the LMAC) - * The number of bursts for the current ToF request. Affect - * the number of events allocations in the current iteration. - * @get_ch_est: for xVT only, NA for driver - * @abort_responder: when set to '1' - Responder will terminate its activity - * (all other fields in the command are ignored) - * @recv_sta_req_params: 1 - Responder will ignore the other Responder's - * params and use the recomended Initiator params. - * 0 - otherwise - * @channel_num: current AP Channel - * @bandwidth: current AP Bandwidth: 0 20MHz, 1 40MHz, 2 80MHz - * @rate: current AP rate - * @ctrl_ch_position: coding of the control channel position relative to - * the center frequency: - * - * 40 MHz - * 0 below center, 1 above center - * - * 80 MHz - * bits [0..1] - * * 0 the near 20MHz to the center, - * * 1 the far 20MHz to the center - * bit[2] - * as above 40MHz - * @ftm_per_burst: FTMs per Burst - * @ftm_resp_ts_avail: '0' - we don't measure over the Initial FTM Response, - * '1' - we measure over the Initial FTM Response - * @asap_mode: ASAP / Non ASAP mode for the current WLS station - * @sta_id: index of the AP STA when in AP mode - * @tsf_timer_offset_msecs: The dictated time offset (mSec) from the AP's TSF - * @toa_offset: Artificial addition [0.1nsec] for the ToA - to be used for debug - * purposes, simulating station movement by adding various values - * to this field - * @bssid: Current AP BSSID - */ -struct iwl_tof_responder_config_cmd { - __le32 sub_grp_cmd_id; - __le16 burst_period; - u8 min_delta_ftm; - u8 burst_duration; - u8 num_of_burst_exp; - u8 get_ch_est; - u8 abort_responder; - u8 recv_sta_req_params; - u8 channel_num; - u8 bandwidth; - u8 rate; - u8 ctrl_ch_position; - u8 ftm_per_burst; - u8 ftm_resp_ts_avail; - u8 asap_mode; - u8 sta_id; - __le16 tsf_timer_offset_msecs; - __le16 toa_offset; - u8 bssid[ETH_ALEN]; -} __packed; - -/** - * struct iwl_tof_range_request_ext_cmd - extended range req for WLS - * @tsf_timer_offset_msec: the recommended time offset (mSec) from the AP's TSF - * @reserved: reserved - * @min_delta_ftm: Minimal time between two consecutive measurements, - * in units of 100us. 0 means no preference by station - * @ftm_format_and_bw20M: FTM Channel Spacing/Format for 20MHz: recommended - * value be sent to the AP - * @ftm_format_and_bw40M: FTM Channel Spacing/Format for 40MHz: recommended - * value to be sent to the AP - * @ftm_format_and_bw80M: FTM Channel Spacing/Format for 80MHz: recommended - * value to be sent to the AP - */ -struct iwl_tof_range_req_ext_cmd { - __le32 sub_grp_cmd_id; - __le16 tsf_timer_offset_msec; - __le16 reserved; - u8 min_delta_ftm; - u8 ftm_format_and_bw20M; - u8 ftm_format_and_bw40M; - u8 ftm_format_and_bw80M; -} __packed; - -#define IWL_MVM_TOF_MAX_APS 21 - -/** - * struct iwl_tof_range_req_ap_entry - AP configuration parameters - * @channel_num: Current AP Channel - * @bandwidth: Current AP Bandwidth: 0 20MHz, 1 40MHz, 2 80MHz - * @tsf_delta_direction: TSF relatively to the subject AP - * @ctrl_ch_position: Coding of the control channel position relative to the - * center frequency. - * 40MHz 0 below center, 1 above center - * 80MHz bits [0..1]: 0 the near 20MHz to the center, - * 1 the far 20MHz to the center - * bit[2] as above 40MHz - * @bssid: AP's bss id - * @measure_type: Measurement type: 0 - two sided, 1 - One sided - * @num_of_bursts: Recommended value to be sent to the AP. 2s Exponent of the - * number of measurement iterations (min 2^0 = 1, max 2^14) - * @burst_period: Recommended value to be sent to the AP. Measurement - * periodicity In units of 100ms. ignored if num_of_bursts = 0 - * @samples_per_burst: 2-sided: the number of FTMs pairs in single Burst (1-31) - * 1-sided: how many rts/cts pairs should be used per burst. - * @retries_per_sample: Max number of retries that the LMAC should send - * in case of no replies by the AP. - * @tsf_delta: TSF Delta in units of microseconds. - * The difference between the AP TSF and the device local clock. - * @location_req: Location Request Bit[0] LCI should be sent in the FTMR - * Bit[1] Civic should be sent in the FTMR - * @asap_mode: 0 - non asap mode, 1 - asap mode (not relevant for one sided) - * @enable_dyn_ack: Enable Dynamic ACK BW. - * 0 Initiator interact with regular AP - * 1 Initiator interact with Responder machine: need to send the - * Initiator Acks with HT 40MHz / 80MHz, since the Responder should - * use it for its ch est measurement (this flag will be set when we - * configure the opposite machine to be Responder). - * @rssi: Last received value - * leagal values: -128-0 (0x7f). above 0x0 indicating an invalid value. - */ -struct iwl_tof_range_req_ap_entry { - u8 channel_num; - u8 bandwidth; - u8 tsf_delta_direction; - u8 ctrl_ch_position; - u8 bssid[ETH_ALEN]; - u8 measure_type; - u8 num_of_bursts; - __le16 burst_period; - u8 samples_per_burst; - u8 retries_per_sample; - __le32 tsf_delta; - u8 location_req; - u8 asap_mode; - u8 enable_dyn_ack; - s8 rssi; -} __packed; - -/** - * enum iwl_tof_response_mode - * @IWL_MVM_TOF_RESPOSE_ASAP: report each AP measurement separately as soon as - * possible (not supported for this release) - * @IWL_MVM_TOF_RESPOSE_TIMEOUT: report all AP measurements as a batch upon - * timeout expiration - * @IWL_MVM_TOF_RESPOSE_COMPLETE: report all AP measurements as a batch at the - * earlier of: measurements completion / timeout - * expiration. - */ -enum iwl_tof_response_mode { - IWL_MVM_TOF_RESPOSE_ASAP = 1, - IWL_MVM_TOF_RESPOSE_TIMEOUT, - IWL_MVM_TOF_RESPOSE_COMPLETE, -}; - -/** - * struct iwl_tof_range_req_cmd - start measurement cmd - * @request_id: A Token incremented per request. The same Token will be - * sent back in the range response - * @initiator: 0- NW initiated, 1 - Client Initiated - * @one_sided_los_disable: '0'- run ML-Algo for both ToF/OneSided, - * '1' - run ML-Algo for ToF only - * @req_timeout: Requested timeout of the response in units of 100ms. - * This is equivalent to the session time configured to the - * LMAC in Initiator Request - * @report_policy: Supported partially for this release: For current release - - * the range report will be uploaded as a batch when ready or - * when the session is done (successfully / partially). - * one of iwl_tof_response_mode. - * @num_of_ap: Number of APs to measure (error if > IWL_MVM_TOF_MAX_APS) - * @macaddr_random: '0' Use default source MAC address (i.e. p2_p), - * '1' Use MAC Address randomization according to the below - * @macaddr_mask: Bits set to 0 shall be copied from the MAC address template. - * Bits set to 1 shall be randomized by the UMAC - * @ap: per-AP request data - */ -struct iwl_tof_range_req_cmd { - __le32 sub_grp_cmd_id; - u8 request_id; - u8 initiator; - u8 one_sided_los_disable; - u8 req_timeout; - u8 report_policy; - u8 los_det_disable; - u8 num_of_ap; - u8 macaddr_random; - u8 macaddr_template[ETH_ALEN]; - u8 macaddr_mask[ETH_ALEN]; - struct iwl_tof_range_req_ap_entry ap[IWL_MVM_TOF_MAX_APS]; -} __packed; - -/** - * struct iwl_tof_gen_resp_cmd - generic ToF response - */ -struct iwl_tof_gen_resp_cmd { - __le32 sub_grp_cmd_id; - u8 data[]; -} __packed; - -/** - * struct iwl_tof_range_rsp_ap_entry_ntfy - AP parameters (response) - * @bssid: BSSID of the AP - * @measure_status: current APs measurement status, one of - * &enum iwl_tof_entry_status. - * @measure_bw: Current AP Bandwidth: 0 20MHz, 1 40MHz, 2 80MHz - * @rtt: The Round Trip Time that took for the last measurement for - * current AP [nSec] - * @rtt_variance: The Variance of the RTT values measured for current AP - * @rtt_spread: The Difference between the maximum and the minimum RTT - * values measured for current AP in the current session [nsec] - * @rssi: RSSI as uploaded in the Channel Estimation notification - * @rssi_spread: The Difference between the maximum and the minimum RSSI values - * measured for current AP in the current session - * @reserved: reserved - * @range: Measured range [cm] - * @range_variance: Measured range variance [cm] - * @timestamp: The GP2 Clock [usec] where Channel Estimation notification was - * uploaded by the LMAC - */ -struct iwl_tof_range_rsp_ap_entry_ntfy { - u8 bssid[ETH_ALEN]; - u8 measure_status; - u8 measure_bw; - __le32 rtt; - __le32 rtt_variance; - __le32 rtt_spread; - s8 rssi; - u8 rssi_spread; - __le16 reserved; - __le32 range; - __le32 range_variance; - __le32 timestamp; -} __packed; - -/** - * struct iwl_tof_range_rsp_ntfy - - * @request_id: A Token ID of the corresponding Range request - * @request_status: status of current measurement session - * @last_in_batch: reprot policy (when not all responses are uploaded at once) - * @num_of_aps: Number of APs to measure (error if > IWL_MVM_TOF_MAX_APS) - * @ap: per-AP data - */ -struct iwl_tof_range_rsp_ntfy { - u8 request_id; - u8 request_status; - u8 last_in_batch; - u8 num_of_aps; - struct iwl_tof_range_rsp_ap_entry_ntfy ap[IWL_MVM_TOF_MAX_APS]; -} __packed; - -#define IWL_MVM_TOF_MCSI_BUF_SIZE (245) -/** - * struct iwl_tof_mcsi_notif - used for debug - * @token: token ID for the current session - * @role: '0' - initiator, '1' - responder - * @reserved: reserved - * @initiator_bssid: initiator machine - * @responder_bssid: responder machine - * @mcsi_buffer: debug data - */ -struct iwl_tof_mcsi_notif { - u8 token; - u8 role; - __le16 reserved; - u8 initiator_bssid[ETH_ALEN]; - u8 responder_bssid[ETH_ALEN]; - u8 mcsi_buffer[IWL_MVM_TOF_MCSI_BUF_SIZE * 4]; -} __packed; - -/** - * struct iwl_tof_neighbor_report_notif - * @bssid: BSSID of the AP which sent the report - * @request_token: same token as the corresponding request - * @status: - * @report_ie_len: the length of the response frame starting from the Element ID - * @data: the IEs - */ -struct iwl_tof_neighbor_report { - u8 bssid[ETH_ALEN]; - u8 request_token; - u8 status; - __le16 report_ie_len; - u8 data[]; -} __packed; - -/** - * struct iwl_tof_range_abort_cmd - * @request_id: corresponds to a range request - * @reserved: reserved - */ -struct iwl_tof_range_abort_cmd { - __le32 sub_grp_cmd_id; - u8 request_id; - u8 reserved[3]; -} __packed; - -#endif diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c index 2a19b178c5e8..22efd94da6d3 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c @@ -469,6 +469,93 @@ static const struct iwl_prph_range iwl_prph_dump_addr_9000[] = { { .start = 0x00a02400, .end = 0x00a02758 }, }; +static const struct iwl_prph_range iwl_prph_dump_addr_22000[] = { + { .start = 0x00a00000, .end = 0x00a00000 }, + { .start = 0x00a0000c, .end = 0x00a00024 }, + { .start = 0x00a0002c, .end = 0x00a00034 }, + { .start = 0x00a0003c, .end = 0x00a0003c }, + { .start = 0x00a00410, .end = 0x00a00418 }, + { .start = 0x00a00420, .end = 0x00a00420 }, + { .start = 0x00a00428, .end = 0x00a00428 }, + { .start = 0x00a00430, .end = 0x00a0043c }, + { .start = 0x00a00444, .end = 0x00a00444 }, + { .start = 0x00a00840, .end = 0x00a00840 }, + { .start = 0x00a00850, .end = 0x00a00858 }, + { .start = 0x00a01004, .end = 0x00a01008 }, + { .start = 0x00a01010, .end = 0x00a01010 }, + { .start = 0x00a01018, .end = 0x00a01018 }, + { .start = 0x00a01024, .end = 0x00a01024 }, + { .start = 0x00a0102c, .end = 0x00a01034 }, + { .start = 0x00a0103c, .end = 0x00a01040 }, + { .start = 0x00a01048, .end = 0x00a01050 }, + { .start = 0x00a01058, .end = 0x00a01058 }, + { .start = 0x00a01060, .end = 0x00a01070 }, + { .start = 0x00a0108c, .end = 0x00a0108c }, + { .start = 0x00a01c20, .end = 0x00a01c28 }, + { .start = 0x00a01d10, .end = 0x00a01d10 }, + { .start = 0x00a01e28, .end = 0x00a01e2c }, + { .start = 0x00a01e60, .end = 0x00a01e60 }, + { .start = 0x00a01e80, .end = 0x00a01e80 }, + { .start = 0x00a01ea0, .end = 0x00a01ea0 }, + { .start = 0x00a02000, .end = 0x00a0201c }, + { .start = 0x00a02024, .end = 0x00a02024 }, + { .start = 0x00a02040, .end = 0x00a02048 }, + { .start = 0x00a020c0, .end = 0x00a020e0 }, + { .start = 0x00a02400, .end = 0x00a02404 }, + { .start = 0x00a0240c, .end = 0x00a02414 }, + { .start = 0x00a0241c, .end = 0x00a0243c }, + { .start = 0x00a02448, .end = 0x00a024bc }, + { .start = 0x00a024c4, .end = 0x00a024cc }, + { .start = 0x00a02508, .end = 0x00a02508 }, + { .start = 0x00a02510, .end = 0x00a02514 }, + { .start = 0x00a0251c, .end = 0x00a0251c }, + { .start = 0x00a0252c, .end = 0x00a0255c }, + { .start = 0x00a02564, .end = 0x00a025a0 }, + { .start = 0x00a025a8, .end = 0x00a025b4 }, + { .start = 0x00a025c0, .end = 0x00a025c0 }, + { .start = 0x00a025e8, .end = 0x00a025f4 }, + { .start = 0x00a02c08, .end = 0x00a02c18 }, + { .start = 0x00a02c2c, .end = 0x00a02c38 }, + { .start = 0x00a02c68, .end = 0x00a02c78 }, + { .start = 0x00a03000, .end = 0x00a03000 }, + { .start = 0x00a03010, .end = 0x00a03014 }, + { .start = 0x00a0301c, .end = 0x00a0302c }, + { .start = 0x00a03034, .end = 0x00a03038 }, + { .start = 0x00a03040, .end = 0x00a03044 }, + { .start = 0x00a03060, .end = 0x00a03068 }, + { .start = 0x00a03070, .end = 0x00a03070 }, + { .start = 0x00a0307c, .end = 0x00a03084 }, + { .start = 0x00a0308c, .end = 0x00a03090 }, + { .start = 0x00a03098, .end = 0x00a03098 }, + { .start = 0x00a030a0, .end = 0x00a030a0 }, + { .start = 0x00a030a8, .end = 0x00a030b4 }, + { .start = 0x00a030bc, .end = 0x00a030c0 }, + { .start = 0x00a030c8, .end = 0x00a030f4 }, + { .start = 0x00a03100, .end = 0x00a0312c }, + { .start = 0x00a03c00, .end = 0x00a03c5c }, + { .start = 0x00a04400, .end = 0x00a04454 }, + { .start = 0x00a04460, .end = 0x00a04474 }, + { .start = 0x00a044c0, .end = 0x00a044ec }, + { .start = 0x00a04500, .end = 0x00a04504 }, + { .start = 0x00a04510, .end = 0x00a04538 }, + { .start = 0x00a04540, .end = 0x00a04548 }, + { .start = 0x00a04560, .end = 0x00a04560 }, + { .start = 0x00a04570, .end = 0x00a0457c }, + { .start = 0x00a04590, .end = 0x00a04590 }, + { .start = 0x00a04598, .end = 0x00a04598 }, + { .start = 0x00a045c0, .end = 0x00a045f4 }, + { .start = 0x00a0c000, .end = 0x00a0c018 }, + { .start = 0x00a0c020, .end = 0x00a0c028 }, + { .start = 0x00a0c038, .end = 0x00a0c094 }, + { .start = 0x00a0c0c0, .end = 0x00a0c104 }, + { .start = 0x00a0c10c, .end = 0x00a0c118 }, + { .start = 0x00a0c150, .end = 0x00a0c174 }, + { .start = 0x00a0c17c, .end = 0x00a0c188 }, + { .start = 0x00a0c190, .end = 0x00a0c198 }, + { .start = 0x00a0c1a0, .end = 0x00a0c1a8 }, + { .start = 0x00a0c1b0, .end = 0x00a0c1b8 }, +}; + static void iwl_read_prph_block(struct iwl_trans *trans, u32 start, u32 len_bytes, __le32 *data) { @@ -478,15 +565,20 @@ static void iwl_read_prph_block(struct iwl_trans *trans, u32 start, *data++ = cpu_to_le32(iwl_read_prph_no_grab(trans, start + i)); } -static void iwl_dump_prph(struct iwl_trans *trans, - struct iwl_fw_error_dump_data **data, +static void iwl_dump_prph(struct iwl_fw_runtime *fwrt, const struct iwl_prph_range *iwl_prph_dump_addr, - u32 range_len) + u32 range_len, void *ptr) { struct iwl_fw_error_dump_prph *prph; + struct iwl_trans *trans = fwrt->trans; + struct iwl_fw_error_dump_data **data = + (struct iwl_fw_error_dump_data **)ptr; unsigned long flags; u32 i; + if (!data) + return; + IWL_DEBUG_INFO(trans, "WRT PRPH dump\n"); if (!iwl_trans_grab_nic_access(trans, &flags)) @@ -552,37 +644,47 @@ static struct scatterlist *alloc_sgtable(int size) return table; } -static int iwl_fw_get_prph_len(struct iwl_fw_runtime *fwrt) +static void iwl_fw_get_prph_len(struct iwl_fw_runtime *fwrt, + const struct iwl_prph_range *iwl_prph_dump_addr, + u32 range_len, void *ptr) { - u32 prph_len = 0; - int i; + u32 *prph_len = (u32 *)ptr; + int i, num_bytes_in_chunk; + + if (!prph_len) + return; - for (i = 0; i < ARRAY_SIZE(iwl_prph_dump_addr_comm); - i++) { + for (i = 0; i < range_len; i++) { /* The range includes both boundaries */ - int num_bytes_in_chunk = - iwl_prph_dump_addr_comm[i].end - - iwl_prph_dump_addr_comm[i].start + 4; + num_bytes_in_chunk = + iwl_prph_dump_addr[i].end - + iwl_prph_dump_addr[i].start + 4; - prph_len += sizeof(struct iwl_fw_error_dump_data) + + *prph_len += sizeof(struct iwl_fw_error_dump_data) + sizeof(struct iwl_fw_error_dump_prph) + num_bytes_in_chunk; } +} - if (fwrt->trans->cfg->mq_rx_supported) { - for (i = 0; i < - ARRAY_SIZE(iwl_prph_dump_addr_9000); i++) { - /* The range includes both boundaries */ - int num_bytes_in_chunk = - iwl_prph_dump_addr_9000[i].end - - iwl_prph_dump_addr_9000[i].start + 4; - - prph_len += sizeof(struct iwl_fw_error_dump_data) + - sizeof(struct iwl_fw_error_dump_prph) + - num_bytes_in_chunk; +static void iwl_fw_prph_handler(struct iwl_fw_runtime *fwrt, void *ptr, + void (*handler)(struct iwl_fw_runtime *, + const struct iwl_prph_range *, + u32, void *)) +{ + u32 range_len; + + if (fwrt->trans->cfg->device_family >= IWL_DEVICE_FAMILY_22000) { + range_len = ARRAY_SIZE(iwl_prph_dump_addr_22000); + handler(fwrt, iwl_prph_dump_addr_22000, range_len, ptr); + } else { + range_len = ARRAY_SIZE(iwl_prph_dump_addr_comm); + handler(fwrt, iwl_prph_dump_addr_comm, range_len, ptr); + + if (fwrt->trans->cfg->mq_rx_supported) { + range_len = ARRAY_SIZE(iwl_prph_dump_addr_9000); + handler(fwrt, iwl_prph_dump_addr_9000, range_len, ptr); } } - return prph_len; } static void iwl_fw_dump_mem(struct iwl_fw_runtime *fwrt, @@ -646,6 +748,9 @@ static int iwl_fw_rxf_len(struct iwl_fw_runtime *fwrt, ADD_LEN(fifo_len, mem_cfg->rxfifo2_size, hdr_len); /* Count RXF1 sizes */ + if (WARN_ON(mem_cfg->num_lmacs > MAX_NUM_LMAC)) + mem_cfg->num_lmacs = MAX_NUM_LMAC; + for (i = 0; i < mem_cfg->num_lmacs; i++) ADD_LEN(fifo_len, mem_cfg->lmac[i].rxfifo1_size, hdr_len); @@ -664,6 +769,9 @@ static int iwl_fw_txf_len(struct iwl_fw_runtime *fwrt, goto dump_internal_txf; /* Count TXF sizes */ + if (WARN_ON(mem_cfg->num_lmacs > MAX_NUM_LMAC)) + mem_cfg->num_lmacs = MAX_NUM_LMAC; + for (i = 0; i < mem_cfg->num_lmacs; i++) { int j; @@ -733,6 +841,8 @@ _iwl_fw_error_dump(struct iwl_fw_runtime *fwrt, if (!fwrt->trans->cfg->dccm_offset || !fwrt->trans->cfg->dccm_len) { const struct fw_img *img; + if (fwrt->cur_fw_img >= IWL_UCODE_TYPE_MAX) + return NULL; img = &fwrt->fw->img[fwrt->cur_fw_img]; sram_ofs = img->sec[IWL_UCODE_SECTION_DATA].offset; sram_len = img->sec[IWL_UCODE_SECTION_DATA].len; @@ -747,9 +857,9 @@ _iwl_fw_error_dump(struct iwl_fw_runtime *fwrt, fifo_len += iwl_fw_txf_len(fwrt, mem_cfg); /* Make room for PRPH registers */ - if (!fwrt->trans->cfg->gen2 && - iwl_fw_dbg_type_on(fwrt, IWL_FW_ERROR_DUMP_PRPH)) - prph_len += iwl_fw_get_prph_len(fwrt); + if (iwl_fw_dbg_type_on(fwrt, IWL_FW_ERROR_DUMP_PRPH)) + iwl_fw_prph_handler(fwrt, &prph_len, + iwl_fw_get_prph_len); if (fwrt->trans->cfg->device_family == IWL_DEVICE_FAMILY_7000 && iwl_fw_dbg_type_on(fwrt, IWL_FW_ERROR_DUMP_RADIO_REG)) @@ -828,7 +938,13 @@ _iwl_fw_error_dump(struct iwl_fw_runtime *fwrt, sizeof(dump_info->dev_human_readable) - 1); strncpy(dump_info->bus_human_readable, fwrt->dev->bus->name, sizeof(dump_info->bus_human_readable) - 1); - dump_info->rt_status = cpu_to_le32(fwrt->dump.rt_status); + dump_info->num_of_lmacs = fwrt->smem_cfg.num_lmacs; + dump_info->lmac_err_id[0] = + cpu_to_le32(fwrt->dump.lmac_err_id[0]); + if (fwrt->smem_cfg.num_lmacs > 1) + dump_info->lmac_err_id[1] = + cpu_to_le32(fwrt->dump.lmac_err_id[1]); + dump_info->umac_err_id = cpu_to_le32(fwrt->dump.umac_err_id); dump_data = iwl_fw_error_next_data(dump_data); } @@ -935,16 +1051,8 @@ _iwl_fw_error_dump(struct iwl_fw_runtime *fwrt, if (iwl_fw_dbg_is_paging_enabled(fwrt)) iwl_dump_paging(fwrt, &dump_data); - if (prph_len) { - iwl_dump_prph(fwrt->trans, &dump_data, - iwl_prph_dump_addr_comm, - ARRAY_SIZE(iwl_prph_dump_addr_comm)); - - if (fwrt->trans->cfg->mq_rx_supported) - iwl_dump_prph(fwrt->trans, &dump_data, - iwl_prph_dump_addr_9000, - ARRAY_SIZE(iwl_prph_dump_addr_9000)); - } + if (prph_len) + iwl_fw_prph_handler(fwrt, &dump_data, iwl_dump_prph); out: dump_file->file_len = cpu_to_le32(file_len); @@ -1108,13 +1216,13 @@ static void iwl_fw_ini_dump_trigger(struct iwl_fw_runtime *fwrt, iwl_dump_prph_ini(fwrt->trans, data, reg); break; case IWL_FW_INI_REGION_DRAM_BUFFER: - *dump_mask |= IWL_FW_ERROR_DUMP_FW_MONITOR; + *dump_mask |= BIT(IWL_FW_ERROR_DUMP_FW_MONITOR); break; case IWL_FW_INI_REGION_PAGING: if (iwl_fw_dbg_is_paging_enabled(fwrt)) iwl_dump_paging(fwrt, data); else - *dump_mask |= IWL_FW_ERROR_DUMP_PAGING; + *dump_mask |= BIT(IWL_FW_ERROR_DUMP_PAGING); break; case IWL_FW_INI_REGION_TXF: iwl_fw_dump_txf(fwrt, data); @@ -1146,10 +1254,6 @@ _iwl_fw_error_ini_dump(struct iwl_fw_runtime *fwrt, if (id == FW_DBG_TRIGGER_FW_ASSERT) id = IWL_FW_TRIGGER_ID_FW_ASSERT; - else if (id == FW_DBG_TRIGGER_USER) - id = IWL_FW_TRIGGER_ID_USER_TRIGGER; - else if (id < FW_DBG_TRIGGER_MAX) - return NULL; if (WARN_ON(id >= ARRAY_SIZE(fwrt->dump.active_trigs))) return NULL; @@ -1385,7 +1489,7 @@ int iwl_fw_dbg_collect(struct iwl_fw_runtime *fwrt, if (WARN_ON(!fwrt->dump.active_trigs[id].active)) return -EINVAL; - delay = le32_to_cpu(fwrt->dump.active_trigs[id].conf->ignore_consec); + delay = le32_to_cpu(fwrt->dump.active_trigs[id].conf->dump_delay); occur = le32_to_cpu(fwrt->dump.active_trigs[id].conf->occurrences); if (!occur) return 0; @@ -1570,27 +1674,29 @@ iwl_fw_dbg_buffer_allocation(struct iwl_fw_runtime *fwrt, struct iwl_fw_ini_allocation_tlv *alloc) { struct iwl_trans *trans = fwrt->trans; - struct iwl_continuous_record_cmd cont_rec = {}; - struct iwl_buffer_allocation_cmd *cmd = (void *)&cont_rec.pad[0]; + struct iwl_ldbg_config_cmd ldbg_cmd = { + .type = cpu_to_le32(BUFFER_ALLOCATION), + }; + struct iwl_buffer_allocation_cmd *cmd = &ldbg_cmd.buffer_allocation; struct iwl_host_cmd hcmd = { .id = LDBG_CONFIG_CMD, .flags = CMD_ASYNC, - .data[0] = &cont_rec, - .len[0] = sizeof(cont_rec), + .data[0] = &ldbg_cmd, + .len[0] = sizeof(ldbg_cmd), }; void *virtual_addr = NULL; u32 size = le32_to_cpu(alloc->size); dma_addr_t phys_addr; - cont_rec.record_mode.enable_recording = cpu_to_le16(BUFFER_ALLOCATION); - if (!trans->num_blocks && le32_to_cpu(alloc->buffer_location) != IWL_FW_INI_LOCATION_DRAM_PATH) return; - virtual_addr = dma_alloc_coherent(fwrt->trans->dev, size, - &phys_addr, GFP_KERNEL); + virtual_addr = + dma_alloc_coherent(fwrt->trans->dev, size, &phys_addr, + GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO | + __GFP_COMP); /* TODO: alloc fragments if needed */ if (!virtual_addr) diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h index 6aabbdd72326..330229d2a61d 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h @@ -102,7 +102,10 @@ static inline void iwl_fw_free_dump_desc(struct iwl_fw_runtime *fwrt) if (fwrt->dump.desc != &iwl_dump_desc_assert) kfree(fwrt->dump.desc); fwrt->dump.desc = NULL; - fwrt->dump.rt_status = 0; + fwrt->dump.lmac_err_id[0] = 0; + if (fwrt->smem_cfg.num_lmacs > 1) + fwrt->dump.lmac_err_id[1] = 0; + fwrt->dump.umac_err_id = 0; } void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt); @@ -266,20 +269,20 @@ _iwl_fw_dbg_trigger_simple_stop(struct iwl_fw_runtime *fwrt, iwl_fw_dbg_get_trigger((fwrt)->fw,\ (trig))) -static int iwl_fw_dbg_start_stop_hcmd(struct iwl_fw_runtime *fwrt, bool start) +static inline int +iwl_fw_dbg_start_stop_hcmd(struct iwl_fw_runtime *fwrt, bool start) { - struct iwl_continuous_record_cmd cont_rec = {}; + struct iwl_ldbg_config_cmd cmd = { + .type = start ? cpu_to_le32(START_DEBUG_RECORDING) : + cpu_to_le32(STOP_DEBUG_RECORDING), + }; struct iwl_host_cmd hcmd = { .id = LDBG_CONFIG_CMD, .flags = CMD_ASYNC, - .data[0] = &cont_rec, - .len[0] = sizeof(cont_rec), + .data[0] = &cmd, + .len[0] = sizeof(cmd), }; - cont_rec.record_mode.enable_recording = start ? - cpu_to_le16(START_DEBUG_RECORDING) : - cpu_to_le16(STOP_DEBUG_RECORDING); - return iwl_trans_send_cmd(fwrt->trans, &hcmd); } @@ -378,6 +381,7 @@ static inline bool iwl_fw_dbg_is_paging_enabled(struct iwl_fw_runtime *fwrt) { return iwl_fw_dbg_type_on(fwrt, IWL_FW_ERROR_DUMP_PAGING) && !fwrt->trans->cfg->gen2 && + fwrt->cur_fw_img < IWL_UCODE_TYPE_MAX && fwrt->fw->img[fwrt->cur_fw_img].paging_mem_size && fwrt->fw_paging_db[0].fw_paging_block; } diff --git a/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h b/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h index 65faecf552cd..c02425a1e64f 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h @@ -180,6 +180,8 @@ enum iwl_fw_error_dump_family { IWL_FW_ERROR_DUMP_FAMILY_8 = 8, }; +#define MAX_NUM_LMAC 2 + /** * struct iwl_fw_error_dump_info - info on the device / firmware * @device_family: the family of the device (7 / 8) @@ -187,7 +189,10 @@ enum iwl_fw_error_dump_family { * @fw_human_readable: human readable FW version * @dev_human_readable: name of the device * @bus_human_readable: name of the bus used - * @rt_status: the error_id/rt_status that that triggered the latest dump + * @num_of_lmacs: the number of lmacs + * @lmac_err_id: the lmac 0/1 error_id/rt_status that triggered the latest dump + * if the dump collection was not initiated by an assert, the value is 0 + * @umac_err_id: the umac error_id/rt_status that triggered the latest dump * if the dump collection was not initiated by an assert, the value is 0 */ struct iwl_fw_error_dump_info { @@ -196,7 +201,9 @@ struct iwl_fw_error_dump_info { u8 fw_human_readable[FW_VER_HUMAN_READABLE_SZ]; u8 dev_human_readable[64]; u8 bus_human_readable[8]; - __le32 rt_status; + u8 num_of_lmacs; + __le32 umac_err_id; + __le32 lmac_err_id[MAX_NUM_LMAC]; } __packed; /** diff --git a/drivers/net/wireless/intel/iwlwifi/fw/file.h b/drivers/net/wireless/intel/iwlwifi/fw/file.h index 81f557c0b58d..e8b00b795cbb 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/file.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/file.h @@ -303,7 +303,6 @@ typedef unsigned int __bitwise iwl_ucode_tlv_capa_t; * @IWL_UCODE_TLV_CAPA_LAR_SUPPORT: supports Location Aware Regulatory * @IWL_UCODE_TLV_CAPA_UMAC_SCAN: supports UMAC scan. * @IWL_UCODE_TLV_CAPA_BEAMFORMER: supports Beamformer - * @IWL_UCODE_TLV_CAPA_TOF_SUPPORT: supports Time of Flight (802.11mc FTM) * @IWL_UCODE_TLV_CAPA_TDLS_SUPPORT: support basic TDLS functionality * @IWL_UCODE_TLV_CAPA_TXPOWER_INSERTION_SUPPORT: supports insertion of current * tx power value into TPC Report action frame and Link Measurement Report @@ -334,6 +333,8 @@ typedef unsigned int __bitwise iwl_ucode_tlv_capa_t; * @IWL_UCODE_TLV_CAPA_TLC_OFFLOAD: firmware implements rate scaling algorithm * @IWL_UCODE_TLV_CAPA_DYNAMIC_QUOTA: firmware implements quota related * @IWL_UCODE_TLV_CAPA_COEX_SCHEMA_2: firmware implements Coex Schema 2 + * @IWL_UCODE_TLV_CAPA_ULTRA_HB_CHANNELS: firmware supports ultra high band + * (6 GHz). * @IWL_UCODE_TLV_CAPA_EXTENDED_DTS_MEASURE: extended DTS measurement * @IWL_UCODE_TLV_CAPA_SHORT_PM_TIMEOUTS: supports short PM timeouts * @IWL_UCODE_TLV_CAPA_BT_MPLUT_SUPPORT: supports bt-coex Multi-priority LUT @@ -357,10 +358,13 @@ typedef unsigned int __bitwise iwl_ucode_tlv_capa_t; * @IWL_UCODE_TLV_CAPA_TX_POWER_ACK: reduced TX power API has larger * command size (command version 4) that supports toggling ACK TX * power reduction. - * @IWL_UCODE_TLV_CAPA_MLME_OFFLOAD: supports MLME offload * @IWL_UCODE_TLV_CAPA_D3_DEBUG: supports debug recording during D3 * @IWL_UCODE_TLV_CAPA_MCC_UPDATE_11AX_SUPPORT: MCC response support 11ax * capability. + * @IWL_UCODE_TLV_CAPA_CSI_REPORTING: firmware is capable of being configured + * to report the CSI information with (certain) RX frames + * + * @IWL_UCODE_TLV_CAPA_MLME_OFFLOAD: supports MLME offload * * @NUM_IWL_UCODE_TLV_CAPA: number of bits used */ @@ -369,7 +373,6 @@ enum iwl_ucode_tlv_capa { IWL_UCODE_TLV_CAPA_LAR_SUPPORT = (__force iwl_ucode_tlv_capa_t)1, IWL_UCODE_TLV_CAPA_UMAC_SCAN = (__force iwl_ucode_tlv_capa_t)2, IWL_UCODE_TLV_CAPA_BEAMFORMER = (__force iwl_ucode_tlv_capa_t)3, - IWL_UCODE_TLV_CAPA_TOF_SUPPORT = (__force iwl_ucode_tlv_capa_t)5, IWL_UCODE_TLV_CAPA_TDLS_SUPPORT = (__force iwl_ucode_tlv_capa_t)6, IWL_UCODE_TLV_CAPA_TXPOWER_INSERTION_SUPPORT = (__force iwl_ucode_tlv_capa_t)8, IWL_UCODE_TLV_CAPA_DS_PARAM_SET_IE_SUPPORT = (__force iwl_ucode_tlv_capa_t)9, @@ -394,6 +397,7 @@ enum iwl_ucode_tlv_capa { IWL_UCODE_TLV_CAPA_TLC_OFFLOAD = (__force iwl_ucode_tlv_capa_t)43, IWL_UCODE_TLV_CAPA_DYNAMIC_QUOTA = (__force iwl_ucode_tlv_capa_t)44, IWL_UCODE_TLV_CAPA_COEX_SCHEMA_2 = (__force iwl_ucode_tlv_capa_t)45, + IWL_UCODE_TLV_CAPA_ULTRA_HB_CHANNELS = (__force iwl_ucode_tlv_capa_t)48, IWL_UCODE_TLV_CAPA_EXTENDED_DTS_MEASURE = (__force iwl_ucode_tlv_capa_t)64, IWL_UCODE_TLV_CAPA_SHORT_PM_TIMEOUTS = (__force iwl_ucode_tlv_capa_t)65, IWL_UCODE_TLV_CAPA_BT_MPLUT_SUPPORT = (__force iwl_ucode_tlv_capa_t)67, @@ -412,6 +416,8 @@ enum iwl_ucode_tlv_capa { IWL_UCODE_TLV_CAPA_D3_DEBUG = (__force iwl_ucode_tlv_capa_t)87, IWL_UCODE_TLV_CAPA_LED_CMD_SUPPORT = (__force iwl_ucode_tlv_capa_t)88, IWL_UCODE_TLV_CAPA_MCC_UPDATE_11AX_SUPPORT = (__force iwl_ucode_tlv_capa_t)89, + IWL_UCODE_TLV_CAPA_CSI_REPORTING = (__force iwl_ucode_tlv_capa_t)90, + IWL_UCODE_TLV_CAPA_MLME_OFFLOAD = (__force iwl_ucode_tlv_capa_t)96, NUM_IWL_UCODE_TLV_CAPA diff --git a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h index 4f7090f88cb0..a0fcbb28114b 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h @@ -142,7 +142,8 @@ struct iwl_fw_runtime { u32 *d3_debug_data; struct iwl_fw_ini_active_regs active_regs[IWL_FW_INI_MAX_REGION_ID]; struct iwl_fw_ini_active_triggers active_trigs[IWL_FW_TRIGGER_ID_NUM]; - u32 rt_status; + u32 lmac_err_id[MAX_NUM_LMAC]; + u32 umac_err_id; } dump; #ifdef CONFIG_IWLWIFI_DEBUGFS struct { diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h index 91861a9cbe57..ff942532fac3 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h @@ -335,10 +335,6 @@ struct iwl_csr_params { * @fw_name_pre: Firmware filename prefix. The api version and extension * (.ucode) will be added to filename before loading from disk. The * filename is constructed as fw_name_pre<api>.ucode. - * @fw_name_pre_b_or_c_step: same as @fw_name_pre, only for b or c steps - * (if supported) - * @fw_name_pre_rf_next_step: same as @fw_name_pre_b_or_c_step, only for rf - * next step. Supported only in integrated solutions. * @ucode_api_max: Highest version of uCode API supported by driver. * @ucode_api_min: Lowest version of uCode API supported by driver. * @max_inst_size: The maximal length of the fw inst section (only DVM) @@ -392,8 +388,6 @@ struct iwl_cfg { /* params specific to an individual device within a device family */ const char *name; const char *fw_name_pre; - const char *fw_name_pre_b_or_c_step; - const char *fw_name_pre_rf_next_step; /* params not likely to change within a device family */ const struct iwl_base_params *base_params; /* params likely to change within a device family */ @@ -551,29 +545,40 @@ extern const struct iwl_cfg iwl8275_2ac_cfg; extern const struct iwl_cfg iwl4165_2ac_cfg; extern const struct iwl_cfg iwl9160_2ac_cfg; extern const struct iwl_cfg iwl9260_2ac_cfg; +extern const struct iwl_cfg iwl9260_2ac_160_cfg; extern const struct iwl_cfg iwl9260_killer_2ac_cfg; extern const struct iwl_cfg iwl9270_2ac_cfg; extern const struct iwl_cfg iwl9460_2ac_cfg; extern const struct iwl_cfg iwl9560_2ac_cfg; +extern const struct iwl_cfg iwl9560_2ac_160_cfg; extern const struct iwl_cfg iwl9460_2ac_cfg_soc; extern const struct iwl_cfg iwl9461_2ac_cfg_soc; extern const struct iwl_cfg iwl9462_2ac_cfg_soc; extern const struct iwl_cfg iwl9560_2ac_cfg_soc; +extern const struct iwl_cfg iwl9560_2ac_160_cfg_soc; extern const struct iwl_cfg iwl9560_killer_2ac_cfg_soc; extern const struct iwl_cfg iwl9560_killer_s_2ac_cfg_soc; extern const struct iwl_cfg iwl9460_2ac_cfg_shared_clk; extern const struct iwl_cfg iwl9461_2ac_cfg_shared_clk; extern const struct iwl_cfg iwl9462_2ac_cfg_shared_clk; extern const struct iwl_cfg iwl9560_2ac_cfg_shared_clk; +extern const struct iwl_cfg iwl9560_2ac_160_cfg_shared_clk; extern const struct iwl_cfg iwl9560_killer_2ac_cfg_shared_clk; extern const struct iwl_cfg iwl9560_killer_s_2ac_cfg_shared_clk; extern const struct iwl_cfg iwl22000_2ac_cfg_hr; extern const struct iwl_cfg iwl22000_2ac_cfg_hr_cdb; extern const struct iwl_cfg iwl22000_2ac_cfg_jf; +extern const struct iwl_cfg iwl22560_2ax_cfg_hr; extern const struct iwl_cfg iwl22000_2ax_cfg_hr; +extern const struct iwl_cfg iwl22260_2ax_cfg; +extern const struct iwl_cfg killer1650s_2ax_cfg_qu_b0_hr_b0; +extern const struct iwl_cfg killer1650i_2ax_cfg_qu_b0_hr_b0; +extern const struct iwl_cfg killer1650x_2ax_cfg; +extern const struct iwl_cfg killer1650w_2ax_cfg; extern const struct iwl_cfg iwl9461_2ac_cfg_qu_b0_jf_b0; extern const struct iwl_cfg iwl9462_2ac_cfg_qu_b0_jf_b0; extern const struct iwl_cfg iwl9560_2ac_cfg_qu_b0_jf_b0; +extern const struct iwl_cfg iwl9560_2ac_160_cfg_qu_b0_jf_b0; extern const struct iwl_cfg killer1550i_2ac_cfg_qu_b0_jf_b0; extern const struct iwl_cfg killer1550s_2ac_cfg_qu_b0_jf_b0; extern const struct iwl_cfg iwl22000_2ax_cfg_jf; diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h index caa5806acd81..42af421bbc3c 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h @@ -325,6 +325,7 @@ enum { #define CSR_HW_REV_TYPE_7265D (0x0000210) #define CSR_HW_REV_TYPE_NONE (0x00001F0) #define CSR_HW_REV_TYPE_QNJ (0x0000360) +#define CSR_HW_REV_TYPE_QNJ_B0 (0x0000364) #define CSR_HW_REV_TYPE_HR_CDB (0x0000340) /* RF_ID value */ diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c index bf1be985f36b..2efa1dfe9b4c 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c @@ -210,18 +210,15 @@ static int iwl_request_firmware(struct iwl_drv *drv, bool first) { const struct iwl_cfg *cfg = drv->trans->cfg; char tag[8]; - const char *fw_pre_name; if (drv->trans->cfg->device_family == IWL_DEVICE_FAMILY_9000 && - (CSR_HW_REV_STEP(drv->trans->hw_rev) == SILICON_B_STEP || - CSR_HW_REV_STEP(drv->trans->hw_rev) == SILICON_C_STEP)) - fw_pre_name = cfg->fw_name_pre_b_or_c_step; - else if (drv->trans->cfg->integrated && - CSR_HW_RFID_STEP(drv->trans->hw_rf_id) == SILICON_B_STEP && - cfg->fw_name_pre_rf_next_step) - fw_pre_name = cfg->fw_name_pre_rf_next_step; - else - fw_pre_name = cfg->fw_name_pre; + (CSR_HW_REV_STEP(drv->trans->hw_rev) != SILICON_B_STEP && + CSR_HW_REV_STEP(drv->trans->hw_rev) != SILICON_C_STEP)) { + IWL_ERR(drv, + "Only HW steps B and C are currently supported (0x%0x)\n", + drv->trans->hw_rev); + return -EINVAL; + } if (first) { drv->fw_index = cfg->ucode_api_max; @@ -235,15 +232,13 @@ static int iwl_request_firmware(struct iwl_drv *drv, bool first) IWL_ERR(drv, "no suitable firmware found!\n"); if (cfg->ucode_api_min == cfg->ucode_api_max) { - IWL_ERR(drv, "%s%d is required\n", fw_pre_name, + IWL_ERR(drv, "%s%d is required\n", cfg->fw_name_pre, cfg->ucode_api_max); } else { IWL_ERR(drv, "minimum version required: %s%d\n", - fw_pre_name, - cfg->ucode_api_min); + cfg->fw_name_pre, cfg->ucode_api_min); IWL_ERR(drv, "maximum version supported: %s%d\n", - fw_pre_name, - cfg->ucode_api_max); + cfg->fw_name_pre, cfg->ucode_api_max); } IWL_ERR(drv, @@ -252,7 +247,7 @@ static int iwl_request_firmware(struct iwl_drv *drv, bool first) } snprintf(drv->firmware_name, sizeof(drv->firmware_name), "%s%s.ucode", - fw_pre_name, tag); + cfg->fw_name_pre, tag); IWL_DEBUG_INFO(drv, "attempting to load firmware '%s'\n", drv->firmware_name); diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-io.c b/drivers/net/wireless/intel/iwlwifi/iwl-io.c index 4f10914f6048..ffd1e649bfa0 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-io.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-io.c @@ -1,10 +1,13 @@ /****************************************************************************** * + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * * Copyright(c) 2003 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2015 - 2016 Intel Deutschland GmbH * - * Portions of this file are derived from the ipw3945 project. - * * This program is free software; you can redistribute it and/or modify it * under the terms of version 2 of the GNU General Public License as * published by the Free Software Foundation. @@ -15,12 +18,44 @@ * more details. * * The full GNU General Public License is included in this distribution in the - * file called LICENSE. + * file called COPYING. * * Contact Information: * Intel Linux Wireless <linuxwifi@intel.com> * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 * + * BSD LICENSE + * + * Copyright(c) 2003 - 2014 Intel Corporation. All rights reserved. + * Copyright(c) 2015 - 2016 Intel Deutschland GmbH + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * *****************************************************************************/ #include <linux/delay.h> #include <linux/device.h> diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-io.h b/drivers/net/wireless/intel/iwlwifi/iwl-io.h index 38085850a2d3..61477e58352d 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-io.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-io.h @@ -1,8 +1,9 @@ /****************************************************************************** * - * Copyright(c) 2003 - 2014 Intel Corporation. All rights reserved. + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. * - * Portions of this file are derived from the ipw3945 project. + * GPL LICENSE SUMMARY * * This program is free software; you can redistribute it and/or modify it * under the terms of version 2 of the GNU General Public License as @@ -14,14 +15,43 @@ * more details. * * The full GNU General Public License is included in this distribution in the - * file called LICENSE. + * file called COPYING. * * Contact Information: * Intel Linux Wireless <linuxwifi@intel.com> * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 * + * BSD LICENSE + * + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * *****************************************************************************/ - #ifndef __iwl_io_h__ #define __iwl_io_h__ diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h b/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h index 73b1c46f1158..0cae2ef9b9df 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h @@ -152,4 +152,22 @@ struct iwl_mod_params { bool enable_ini; }; +static inline bool iwl_enable_rx_ampdu(void) +{ + if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_RXAGG) + return false; + return true; +} + +static inline bool iwl_enable_tx_ampdu(void) +{ + if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_TXAGG) + return false; + if (iwlwifi_mod_params.disable_11n & IWL_ENABLE_HT_TXAGG) + return true; + + /* enabled by default */ + return true; +} + #endif /* #__iwl_modparams_h__ */ diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c index d9afedc3d1d9..484ef4556953 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c @@ -569,8 +569,7 @@ static struct ieee80211_sband_iftype_data iwl_he_capa[] = { .has_he = true, .he_cap_elem = { .mac_cap_info[0] = - IEEE80211_HE_MAC_CAP0_HTC_HE | - IEEE80211_HE_MAC_CAP0_TWT_RES, + IEEE80211_HE_MAC_CAP0_HTC_HE, .mac_cap_info[1] = IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US | IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8, @@ -1196,14 +1195,12 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg, regd_to_copy = sizeof(struct ieee80211_regdomain) + valid_rules * sizeof(struct ieee80211_reg_rule); - copy_rd = kzalloc(regd_to_copy, GFP_KERNEL); + copy_rd = kmemdup(regd, regd_to_copy, GFP_KERNEL); if (!copy_rd) { copy_rd = ERR_PTR(-ENOMEM); goto out; } - memcpy(copy_rd, regd, regd_to_copy); - out: kfree(regdb_ptrs); kfree(regd); diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-prph.h b/drivers/net/wireless/intel/iwlwifi/iwl-prph.h index 9d89b7d7f9fa..3aaa5f06461c 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-prph.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-prph.h @@ -358,12 +358,12 @@ /* FW monitor */ #define MON_BUFF_SAMPLE_CTL (0xa03c00) -#define MON_BUFF_BASE_ADDR (0xa03c3c) +#define MON_BUFF_BASE_ADDR (0xa03c1c) #define MON_BUFF_END_ADDR (0xa03c40) #define MON_BUFF_WRPTR (0xa03c44) #define MON_BUFF_CYCLE_CNT (0xa03c48) /* FW monitor family 8000 and on */ -#define MON_BUFF_BASE_ADDR_VER2 (0xa03c3c) +#define MON_BUFF_BASE_ADDR_VER2 (0xa03c1c) #define MON_BUFF_END_ADDR_VER2 (0xa03c20) #define MON_BUFF_WRPTR_VER2 (0xa03c24) #define MON_BUFF_CYCLE_CNT_VER2 (0xa03c28) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/Makefile b/drivers/net/wireless/intel/iwlwifi/mvm/Makefile index 9ffd21918b5a..30cbd981efbd 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/Makefile +++ b/drivers/net/wireless/intel/iwlwifi/mvm/Makefile @@ -7,7 +7,6 @@ iwlmvm-y += power.o coex.o iwlmvm-y += tt.o offloading.o tdls.o iwlmvm-$(CONFIG_IWLWIFI_DEBUGFS) += debugfs.o debugfs-vif.o iwlmvm-$(CONFIG_IWLWIFI_LEDS) += led.o -iwlmvm-y += tof.o iwlmvm-$(CONFIG_PM) += d3.o -ccflags-y += -I$(src)/../ +ccflags-y += -I $(srctree)/$(src)/../ diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c index 01b5338201d6..36ed7d6fc971 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c @@ -2125,7 +2125,6 @@ static int iwl_mvm_d3_test_open(struct inode *inode, struct file *file) file->private_data = inode->i_private; - ieee80211_stop_queues(mvm->hw); synchronize_net(); mvm->trans->system_pm_mode = IWL_PLAT_PM_MODE_D3; @@ -2140,10 +2139,9 @@ static int iwl_mvm_d3_test_open(struct inode *inode, struct file *file) rtnl_unlock(); if (err > 0) err = -EINVAL; - if (err) { - ieee80211_wake_queues(mvm->hw); + if (err) return err; - } + mvm->d3_test_active = true; mvm->keep_vif = NULL; return 0; @@ -2223,8 +2221,6 @@ static int iwl_mvm_d3_test_release(struct inode *inode, struct file *file) mvm->hw, IEEE80211_IFACE_ITER_NORMAL, iwl_mvm_d3_test_disconn_work_iter, mvm->keep_vif); - ieee80211_wake_queues(mvm->hw); - return 0; } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c index 33b0af24a537..2453ceabf00d 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs-vif.c @@ -60,7 +60,6 @@ * *****************************************************************************/ #include "mvm.h" -#include "fw/api/tof.h" #include "debugfs.h" static void iwl_dbgfs_update_pm(struct iwl_mvm *mvm, @@ -523,753 +522,30 @@ static ssize_t iwl_dbgfs_os_device_timediff_read(struct file *file, return simple_read_from_buffer(user_buf, count, ppos, buf, pos); } -static ssize_t iwl_dbgfs_tof_enable_write(struct ieee80211_vif *vif, - char *buf, - size_t count, loff_t *ppos) -{ - struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); - struct iwl_mvm *mvm = mvmvif->mvm; - u32 value; - int ret = -EINVAL; - char *data; - - mutex_lock(&mvm->mutex); - - data = iwl_dbgfs_is_match("tof_disabled=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0) - mvm->tof_data.tof_cfg.tof_disabled = value; - goto out; - } - - data = iwl_dbgfs_is_match("one_sided_disabled=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0) - mvm->tof_data.tof_cfg.one_sided_disabled = value; - goto out; - } - - data = iwl_dbgfs_is_match("is_debug_mode=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0) - mvm->tof_data.tof_cfg.is_debug_mode = value; - goto out; - } - - data = iwl_dbgfs_is_match("is_buf=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0) - mvm->tof_data.tof_cfg.is_buf_required = value; - goto out; - } - - data = iwl_dbgfs_is_match("send_tof_cfg=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0 && value) { - ret = iwl_mvm_tof_config_cmd(mvm); - goto out; - } - } - -out: - mutex_unlock(&mvm->mutex); - - return ret ?: count; -} - -static ssize_t iwl_dbgfs_tof_enable_read(struct file *file, - char __user *user_buf, - size_t count, loff_t *ppos) -{ - struct ieee80211_vif *vif = file->private_data; - struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); - struct iwl_mvm *mvm = mvmvif->mvm; - char buf[256]; - int pos = 0; - const size_t bufsz = sizeof(buf); - struct iwl_tof_config_cmd *cmd; - - cmd = &mvm->tof_data.tof_cfg; - - mutex_lock(&mvm->mutex); - - pos += scnprintf(buf + pos, bufsz - pos, "tof_disabled = %d\n", - cmd->tof_disabled); - pos += scnprintf(buf + pos, bufsz - pos, "one_sided_disabled = %d\n", - cmd->one_sided_disabled); - pos += scnprintf(buf + pos, bufsz - pos, "is_debug_mode = %d\n", - cmd->is_debug_mode); - pos += scnprintf(buf + pos, bufsz - pos, "is_buf_required = %d\n", - cmd->is_buf_required); - - mutex_unlock(&mvm->mutex); - - return simple_read_from_buffer(user_buf, count, ppos, buf, pos); -} - -static ssize_t iwl_dbgfs_tof_responder_params_write(struct ieee80211_vif *vif, - char *buf, - size_t count, loff_t *ppos) -{ - struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); - struct iwl_mvm *mvm = mvmvif->mvm; - u32 value; - int ret = 0; - char *data; - - mutex_lock(&mvm->mutex); - - data = iwl_dbgfs_is_match("burst_period=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (!ret) - mvm->tof_data.responder_cfg.burst_period = - cpu_to_le16(value); - goto out; - } - - data = iwl_dbgfs_is_match("min_delta_ftm=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0) - mvm->tof_data.responder_cfg.min_delta_ftm = value; - goto out; - } - - data = iwl_dbgfs_is_match("burst_duration=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0) - mvm->tof_data.responder_cfg.burst_duration = value; - goto out; - } - - data = iwl_dbgfs_is_match("num_of_burst_exp=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0) - mvm->tof_data.responder_cfg.num_of_burst_exp = value; - goto out; - } - - data = iwl_dbgfs_is_match("abort_responder=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0) - mvm->tof_data.responder_cfg.abort_responder = value; - goto out; - } - - data = iwl_dbgfs_is_match("get_ch_est=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0) - mvm->tof_data.responder_cfg.get_ch_est = value; - goto out; - } - - data = iwl_dbgfs_is_match("recv_sta_req_params=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0) - mvm->tof_data.responder_cfg.recv_sta_req_params = value; - goto out; - } - - data = iwl_dbgfs_is_match("channel_num=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0) - mvm->tof_data.responder_cfg.channel_num = value; - goto out; - } - - data = iwl_dbgfs_is_match("bandwidth=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0) - mvm->tof_data.responder_cfg.bandwidth = value; - goto out; - } - - data = iwl_dbgfs_is_match("rate=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0) - mvm->tof_data.responder_cfg.rate = value; - goto out; - } - - data = iwl_dbgfs_is_match("bssid=", buf); - if (data) { - u8 *mac = mvm->tof_data.responder_cfg.bssid; - - if (!mac_pton(data, mac)) { - ret = -EINVAL; - goto out; - } - } - - data = iwl_dbgfs_is_match("tsf_timer_offset_msecs=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0) - mvm->tof_data.responder_cfg.tsf_timer_offset_msecs = - cpu_to_le16(value); - goto out; - } - - data = iwl_dbgfs_is_match("toa_offset=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0) - mvm->tof_data.responder_cfg.toa_offset = - cpu_to_le16(value); - goto out; - } - - data = iwl_dbgfs_is_match("center_freq=", buf); - if (data) { - struct iwl_tof_responder_config_cmd *cmd = - &mvm->tof_data.responder_cfg; - - ret = kstrtou32(data, 10, &value); - if (ret == 0 && value) { - enum nl80211_band band = (cmd->channel_num <= 14) ? - NL80211_BAND_2GHZ : - NL80211_BAND_5GHZ; - struct ieee80211_channel chn = { - .band = band, - .center_freq = ieee80211_channel_to_frequency( - cmd->channel_num, band), - }; - struct cfg80211_chan_def chandef = { - .chan = &chn, - .center_freq1 = - ieee80211_channel_to_frequency(value, - band), - }; - - cmd->ctrl_ch_position = iwl_mvm_get_ctrl_pos(&chandef); - } - goto out; - } - - data = iwl_dbgfs_is_match("ftm_per_burst=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0) - mvm->tof_data.responder_cfg.ftm_per_burst = value; - goto out; - } - - data = iwl_dbgfs_is_match("ftm_resp_ts_avail=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0) - mvm->tof_data.responder_cfg.ftm_resp_ts_avail = value; - goto out; - } - - data = iwl_dbgfs_is_match("asap_mode=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0) - mvm->tof_data.responder_cfg.asap_mode = value; - goto out; - } - - data = iwl_dbgfs_is_match("send_responder_cfg=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0 && value) { - ret = iwl_mvm_tof_responder_cmd(mvm, vif); - goto out; - } - } - -out: - mutex_unlock(&mvm->mutex); - - return ret ?: count; -} - -static ssize_t iwl_dbgfs_tof_responder_params_read(struct file *file, - char __user *user_buf, - size_t count, loff_t *ppos) -{ - struct ieee80211_vif *vif = file->private_data; - struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); - struct iwl_mvm *mvm = mvmvif->mvm; - char buf[256]; - int pos = 0; - const size_t bufsz = sizeof(buf); - struct iwl_tof_responder_config_cmd *cmd; - - cmd = &mvm->tof_data.responder_cfg; - - mutex_lock(&mvm->mutex); - - pos += scnprintf(buf + pos, bufsz - pos, "burst_period = %d\n", - le16_to_cpu(cmd->burst_period)); - pos += scnprintf(buf + pos, bufsz - pos, "burst_duration = %d\n", - cmd->burst_duration); - pos += scnprintf(buf + pos, bufsz - pos, "bandwidth = %d\n", - cmd->bandwidth); - pos += scnprintf(buf + pos, bufsz - pos, "channel_num = %d\n", - cmd->channel_num); - pos += scnprintf(buf + pos, bufsz - pos, "ctrl_ch_position = 0x%x\n", - cmd->ctrl_ch_position); - pos += scnprintf(buf + pos, bufsz - pos, "bssid = %pM\n", - cmd->bssid); - pos += scnprintf(buf + pos, bufsz - pos, "min_delta_ftm = %d\n", - cmd->min_delta_ftm); - pos += scnprintf(buf + pos, bufsz - pos, "num_of_burst_exp = %d\n", - cmd->num_of_burst_exp); - pos += scnprintf(buf + pos, bufsz - pos, "rate = %d\n", cmd->rate); - pos += scnprintf(buf + pos, bufsz - pos, "abort_responder = %d\n", - cmd->abort_responder); - pos += scnprintf(buf + pos, bufsz - pos, "get_ch_est = %d\n", - cmd->get_ch_est); - pos += scnprintf(buf + pos, bufsz - pos, "recv_sta_req_params = %d\n", - cmd->recv_sta_req_params); - pos += scnprintf(buf + pos, bufsz - pos, "ftm_per_burst = %d\n", - cmd->ftm_per_burst); - pos += scnprintf(buf + pos, bufsz - pos, "ftm_resp_ts_avail = %d\n", - cmd->ftm_resp_ts_avail); - pos += scnprintf(buf + pos, bufsz - pos, "asap_mode = %d\n", - cmd->asap_mode); - pos += scnprintf(buf + pos, bufsz - pos, - "tsf_timer_offset_msecs = %d\n", - le16_to_cpu(cmd->tsf_timer_offset_msecs)); - pos += scnprintf(buf + pos, bufsz - pos, "toa_offset = %d\n", - le16_to_cpu(cmd->toa_offset)); - - mutex_unlock(&mvm->mutex); - - return simple_read_from_buffer(user_buf, count, ppos, buf, pos); -} - -static ssize_t iwl_dbgfs_tof_range_request_write(struct ieee80211_vif *vif, - char *buf, size_t count, - loff_t *ppos) -{ - struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); - struct iwl_mvm *mvm = mvmvif->mvm; - u32 value; - int ret = 0; - char *data; - - mutex_lock(&mvm->mutex); - - data = iwl_dbgfs_is_match("request_id=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0) - mvm->tof_data.range_req.request_id = value; - goto out; - } - - data = iwl_dbgfs_is_match("initiator=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0) - mvm->tof_data.range_req.initiator = value; - goto out; - } - - data = iwl_dbgfs_is_match("one_sided_los_disable=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0) - mvm->tof_data.range_req.one_sided_los_disable = value; - goto out; - } - - data = iwl_dbgfs_is_match("req_timeout=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0) - mvm->tof_data.range_req.req_timeout = value; - goto out; - } - - data = iwl_dbgfs_is_match("report_policy=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0) - mvm->tof_data.range_req.report_policy = value; - goto out; - } - - data = iwl_dbgfs_is_match("macaddr_random=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0) - mvm->tof_data.range_req.macaddr_random = value; - goto out; - } - - data = iwl_dbgfs_is_match("num_of_ap=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0) - mvm->tof_data.range_req.num_of_ap = value; - goto out; - } - - data = iwl_dbgfs_is_match("macaddr_template=", buf); - if (data) { - u8 mac[ETH_ALEN]; - - if (!mac_pton(data, mac)) { - ret = -EINVAL; - goto out; - } - memcpy(mvm->tof_data.range_req.macaddr_template, mac, ETH_ALEN); - goto out; - } - - data = iwl_dbgfs_is_match("macaddr_mask=", buf); - if (data) { - u8 mac[ETH_ALEN]; - - if (!mac_pton(data, mac)) { - ret = -EINVAL; - goto out; - } - memcpy(mvm->tof_data.range_req.macaddr_mask, mac, ETH_ALEN); - goto out; - } - - data = iwl_dbgfs_is_match("ap=", buf); - if (data) { - struct iwl_tof_range_req_ap_entry ap = {}; - int size = sizeof(struct iwl_tof_range_req_ap_entry); - u16 burst_period; - u8 *mac = ap.bssid; - unsigned int i; - - if (sscanf(data, "%u %hhd %hhd %hhd" - "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx" - "%hhd %hhd %hd" - "%hhd %hhd %d" - "%hhx %hhd %hhd %hhd", - &i, &ap.channel_num, &ap.bandwidth, - &ap.ctrl_ch_position, - mac, mac + 1, mac + 2, mac + 3, mac + 4, mac + 5, - &ap.measure_type, &ap.num_of_bursts, - &burst_period, - &ap.samples_per_burst, &ap.retries_per_sample, - &ap.tsf_delta, &ap.location_req, &ap.asap_mode, - &ap.enable_dyn_ack, &ap.rssi) != 20) { - ret = -EINVAL; - goto out; - } - if (i >= IWL_MVM_TOF_MAX_APS) { - IWL_ERR(mvm, "Invalid AP index %d\n", i); - ret = -EINVAL; - goto out; - } - - ap.burst_period = cpu_to_le16(burst_period); - - memcpy(&mvm->tof_data.range_req.ap[i], &ap, size); - goto out; - } - - data = iwl_dbgfs_is_match("send_range_request=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0 && value) - ret = iwl_mvm_tof_range_request_cmd(mvm, vif); - goto out; - } - - ret = -EINVAL; -out: - mutex_unlock(&mvm->mutex); - return ret ?: count; -} - -static ssize_t iwl_dbgfs_tof_range_request_read(struct file *file, - char __user *user_buf, - size_t count, loff_t *ppos) -{ - struct ieee80211_vif *vif = file->private_data; - struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); - struct iwl_mvm *mvm = mvmvif->mvm; - char buf[512]; - int pos = 0; - const size_t bufsz = sizeof(buf); - struct iwl_tof_range_req_cmd *cmd; - int i; - - cmd = &mvm->tof_data.range_req; - - mutex_lock(&mvm->mutex); - - pos += scnprintf(buf + pos, bufsz - pos, "request_id= %d\n", - cmd->request_id); - pos += scnprintf(buf + pos, bufsz - pos, "initiator= %d\n", - cmd->initiator); - pos += scnprintf(buf + pos, bufsz - pos, "one_sided_los_disable = %d\n", - cmd->one_sided_los_disable); - pos += scnprintf(buf + pos, bufsz - pos, "req_timeout= %d\n", - cmd->req_timeout); - pos += scnprintf(buf + pos, bufsz - pos, "report_policy= %d\n", - cmd->report_policy); - pos += scnprintf(buf + pos, bufsz - pos, "macaddr_random= %d\n", - cmd->macaddr_random); - pos += scnprintf(buf + pos, bufsz - pos, "macaddr_template= %pM\n", - cmd->macaddr_template); - pos += scnprintf(buf + pos, bufsz - pos, "macaddr_mask= %pM\n", - cmd->macaddr_mask); - pos += scnprintf(buf + pos, bufsz - pos, "num_of_ap= %d\n", - cmd->num_of_ap); - for (i = 0; i < cmd->num_of_ap; i++) { - struct iwl_tof_range_req_ap_entry *ap = &cmd->ap[i]; - - pos += scnprintf(buf + pos, bufsz - pos, - "ap %.2d: channel_num=%hhd bw=%hhd" - " control=%hhd bssid=%pM type=%hhd" - " num_of_bursts=%hhd burst_period=%hd ftm=%hhd" - " retries=%hhd tsf_delta=%d" - " tsf_delta_direction=%hhd location_req=0x%hhx " - " asap=%hhd enable=%hhd rssi=%hhd\n", - i, ap->channel_num, ap->bandwidth, - ap->ctrl_ch_position, ap->bssid, - ap->measure_type, ap->num_of_bursts, - ap->burst_period, ap->samples_per_burst, - ap->retries_per_sample, ap->tsf_delta, - ap->tsf_delta_direction, - ap->location_req, ap->asap_mode, - ap->enable_dyn_ack, ap->rssi); - } - - mutex_unlock(&mvm->mutex); - - return simple_read_from_buffer(user_buf, count, ppos, buf, pos); -} - -static ssize_t iwl_dbgfs_tof_range_req_ext_write(struct ieee80211_vif *vif, - char *buf, - size_t count, loff_t *ppos) -{ - struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); - struct iwl_mvm *mvm = mvmvif->mvm; - u32 value; - int ret = 0; - char *data; - - mutex_lock(&mvm->mutex); - - data = iwl_dbgfs_is_match("tsf_timer_offset_msec=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0) - mvm->tof_data.range_req_ext.tsf_timer_offset_msec = - cpu_to_le16(value); - goto out; - } - - data = iwl_dbgfs_is_match("min_delta_ftm=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0) - mvm->tof_data.range_req_ext.min_delta_ftm = value; - goto out; - } - - data = iwl_dbgfs_is_match("ftm_format_and_bw20M=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0) - mvm->tof_data.range_req_ext.ftm_format_and_bw20M = - value; - goto out; - } - - data = iwl_dbgfs_is_match("ftm_format_and_bw40M=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0) - mvm->tof_data.range_req_ext.ftm_format_and_bw40M = - value; - goto out; - } - - data = iwl_dbgfs_is_match("ftm_format_and_bw80M=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0) - mvm->tof_data.range_req_ext.ftm_format_and_bw80M = - value; - goto out; - } - - data = iwl_dbgfs_is_match("send_range_req_ext=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0 && value) - ret = iwl_mvm_tof_range_request_ext_cmd(mvm, vif); - goto out; - } - - ret = -EINVAL; -out: - mutex_unlock(&mvm->mutex); - return ret ?: count; -} - -static ssize_t iwl_dbgfs_tof_range_req_ext_read(struct file *file, - char __user *user_buf, - size_t count, loff_t *ppos) -{ - struct ieee80211_vif *vif = file->private_data; - struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); - struct iwl_mvm *mvm = mvmvif->mvm; - char buf[256]; - int pos = 0; - const size_t bufsz = sizeof(buf); - struct iwl_tof_range_req_ext_cmd *cmd; - - cmd = &mvm->tof_data.range_req_ext; - - mutex_lock(&mvm->mutex); - - pos += scnprintf(buf + pos, bufsz - pos, - "tsf_timer_offset_msec = %hd\n", - cmd->tsf_timer_offset_msec); - pos += scnprintf(buf + pos, bufsz - pos, "min_delta_ftm = %hhd\n", - cmd->min_delta_ftm); - pos += scnprintf(buf + pos, bufsz - pos, - "ftm_format_and_bw20M = %hhd\n", - cmd->ftm_format_and_bw20M); - pos += scnprintf(buf + pos, bufsz - pos, - "ftm_format_and_bw40M = %hhd\n", - cmd->ftm_format_and_bw40M); - pos += scnprintf(buf + pos, bufsz - pos, - "ftm_format_and_bw80M = %hhd\n", - cmd->ftm_format_and_bw80M); - - mutex_unlock(&mvm->mutex); - return simple_read_from_buffer(user_buf, count, ppos, buf, pos); -} - -static ssize_t iwl_dbgfs_tof_range_abort_write(struct ieee80211_vif *vif, - char *buf, - size_t count, loff_t *ppos) -{ - struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); - struct iwl_mvm *mvm = mvmvif->mvm; - u32 value; - int abort_id, ret = 0; - char *data; - - mutex_lock(&mvm->mutex); - - data = iwl_dbgfs_is_match("abort_id=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0) - mvm->tof_data.last_abort_id = value; - goto out; - } - - data = iwl_dbgfs_is_match("send_range_abort=", buf); - if (data) { - ret = kstrtou32(data, 10, &value); - if (ret == 0 && value) { - abort_id = mvm->tof_data.last_abort_id; - ret = iwl_mvm_tof_range_abort_cmd(mvm, abort_id); - goto out; - } - } - -out: - mutex_unlock(&mvm->mutex); - return ret ?: count; -} - -static ssize_t iwl_dbgfs_tof_range_abort_read(struct file *file, - char __user *user_buf, - size_t count, loff_t *ppos) -{ - struct ieee80211_vif *vif = file->private_data; - struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); - struct iwl_mvm *mvm = mvmvif->mvm; - char buf[32]; - int pos = 0; - const size_t bufsz = sizeof(buf); - int last_abort_id; - - mutex_lock(&mvm->mutex); - last_abort_id = mvm->tof_data.last_abort_id; - mutex_unlock(&mvm->mutex); - - pos += scnprintf(buf + pos, bufsz - pos, "last_abort_id = %d\n", - last_abort_id); - return simple_read_from_buffer(user_buf, count, ppos, buf, pos); -} - -static ssize_t iwl_dbgfs_tof_range_response_read(struct file *file, - char __user *user_buf, - size_t count, loff_t *ppos) +static ssize_t iwl_dbgfs_low_latency_write(struct ieee80211_vif *vif, char *buf, + size_t count, loff_t *ppos) { - struct ieee80211_vif *vif = file->private_data; struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); struct iwl_mvm *mvm = mvmvif->mvm; - char *buf; - int pos = 0; - const size_t bufsz = sizeof(struct iwl_tof_range_rsp_ntfy) + 256; - struct iwl_tof_range_rsp_ntfy *cmd; - int i, ret; + u8 value; + int ret; - buf = kzalloc(bufsz, GFP_KERNEL); - if (!buf) - return -ENOMEM; + ret = kstrtou8(buf, 0, &value); + if (ret) + return ret; + if (value > 1) + return -EINVAL; mutex_lock(&mvm->mutex); - cmd = &mvm->tof_data.range_resp; - - pos += scnprintf(buf + pos, bufsz - pos, "request_id = %d\n", - cmd->request_id); - pos += scnprintf(buf + pos, bufsz - pos, "status = %d\n", - cmd->request_status); - pos += scnprintf(buf + pos, bufsz - pos, "last_in_batch = %d\n", - cmd->last_in_batch); - pos += scnprintf(buf + pos, bufsz - pos, "num_of_aps = %d\n", - cmd->num_of_aps); - for (i = 0; i < cmd->num_of_aps; i++) { - struct iwl_tof_range_rsp_ap_entry_ntfy *ap = &cmd->ap[i]; - - pos += scnprintf(buf + pos, bufsz - pos, - "ap %.2d: bssid=%pM status=%hhd bw=%hhd" - " rtt=%d rtt_var=%d rtt_spread=%d" - " rssi=%hhd rssi_spread=%hhd" - " range=%d range_var=%d" - " time_stamp=%d\n", - i, ap->bssid, ap->measure_status, - ap->measure_bw, - ap->rtt, ap->rtt_variance, ap->rtt_spread, - ap->rssi, ap->rssi_spread, ap->range, - ap->range_variance, ap->timestamp); - } + iwl_mvm_update_low_latency(mvm, vif, value, LOW_LATENCY_DEBUGFS); mutex_unlock(&mvm->mutex); - ret = simple_read_from_buffer(user_buf, count, ppos, buf, pos); - kfree(buf); - return ret; + return count; } -static ssize_t iwl_dbgfs_low_latency_write(struct ieee80211_vif *vif, char *buf, - size_t count, loff_t *ppos) +static ssize_t +iwl_dbgfs_low_latency_force_write(struct ieee80211_vif *vif, char *buf, + size_t count, loff_t *ppos) { struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); struct iwl_mvm *mvm = mvmvif->mvm; @@ -1279,13 +555,24 @@ static ssize_t iwl_dbgfs_low_latency_write(struct ieee80211_vif *vif, char *buf, ret = kstrtou8(buf, 0, &value); if (ret) return ret; - if (value > 1) + + if (value > NUM_LOW_LATENCY_FORCE) return -EINVAL; mutex_lock(&mvm->mutex); - iwl_mvm_update_low_latency(mvm, vif, value, LOW_LATENCY_DEBUGFS); + if (value == LOW_LATENCY_FORCE_UNSET) { + iwl_mvm_update_low_latency(mvm, vif, false, + LOW_LATENCY_DEBUGFS_FORCE); + iwl_mvm_update_low_latency(mvm, vif, false, + LOW_LATENCY_DEBUGFS_FORCE_ENABLE); + } else { + iwl_mvm_update_low_latency(mvm, vif, + value == LOW_LATENCY_FORCE_ON, + LOW_LATENCY_DEBUGFS_FORCE); + iwl_mvm_update_low_latency(mvm, vif, true, + LOW_LATENCY_DEBUGFS_FORCE_ENABLE); + } mutex_unlock(&mvm->mutex); - return count; } @@ -1295,15 +582,25 @@ static ssize_t iwl_dbgfs_low_latency_read(struct file *file, { struct ieee80211_vif *vif = file->private_data; struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); - char buf[30] = {}; + char format[] = "traffic=%d\ndbgfs=%d\nvcmd=%d\nvif_type=%d\n" + "dbgfs_force_enable=%d\ndbgfs_force=%d\nactual=%d\n"; + + /* + * all values in format are boolean so the size of format is enough + * for holding the result string + */ + char buf[sizeof(format) + 1] = {}; int len; - len = scnprintf(buf, sizeof(buf) - 1, - "traffic=%d\ndbgfs=%d\nvcmd=%d\nvif_type=%d\n", + len = scnprintf(buf, sizeof(buf) - 1, format, !!(mvmvif->low_latency & LOW_LATENCY_TRAFFIC), !!(mvmvif->low_latency & LOW_LATENCY_DEBUGFS), !!(mvmvif->low_latency & LOW_LATENCY_VCMD), - !!(mvmvif->low_latency & LOW_LATENCY_VIF_TYPE)); + !!(mvmvif->low_latency & LOW_LATENCY_VIF_TYPE), + !!(mvmvif->low_latency & + LOW_LATENCY_DEBUGFS_FORCE_ENABLE), + !!(mvmvif->low_latency & LOW_LATENCY_DEBUGFS_FORCE), + !!(mvmvif->low_latency_actual)); return simple_read_from_buffer(user_buf, count, ppos, buf, len); } @@ -1456,14 +753,9 @@ MVM_DEBUGFS_READ_FILE_OPS(tx_pwr_lmt); MVM_DEBUGFS_READ_WRITE_FILE_OPS(pm_params, 32); MVM_DEBUGFS_READ_WRITE_FILE_OPS(bf_params, 256); MVM_DEBUGFS_READ_WRITE_FILE_OPS(low_latency, 10); +MVM_DEBUGFS_WRITE_FILE_OPS(low_latency_force, 10); MVM_DEBUGFS_READ_WRITE_FILE_OPS(uapsd_misbehaving, 20); MVM_DEBUGFS_READ_WRITE_FILE_OPS(rx_phyinfo, 10); -MVM_DEBUGFS_READ_WRITE_FILE_OPS(tof_enable, 32); -MVM_DEBUGFS_READ_WRITE_FILE_OPS(tof_range_request, 512); -MVM_DEBUGFS_READ_WRITE_FILE_OPS(tof_range_req_ext, 32); -MVM_DEBUGFS_READ_WRITE_FILE_OPS(tof_range_abort, 32); -MVM_DEBUGFS_READ_FILE_OPS(tof_range_response); -MVM_DEBUGFS_READ_WRITE_FILE_OPS(tof_responder_params, 32); MVM_DEBUGFS_READ_WRITE_FILE_OPS(quota_min, 32); MVM_DEBUGFS_READ_FILE_OPS(os_device_timediff); @@ -1497,6 +789,7 @@ void iwl_mvm_vif_dbgfs_register(struct iwl_mvm *mvm, struct ieee80211_vif *vif) MVM_DEBUGFS_ADD_FILE_VIF(tx_pwr_lmt, mvmvif->dbgfs_dir, 0400); MVM_DEBUGFS_ADD_FILE_VIF(mac_params, mvmvif->dbgfs_dir, 0400); MVM_DEBUGFS_ADD_FILE_VIF(low_latency, mvmvif->dbgfs_dir, 0600); + MVM_DEBUGFS_ADD_FILE_VIF(low_latency_force, mvmvif->dbgfs_dir, 0600); MVM_DEBUGFS_ADD_FILE_VIF(uapsd_misbehaving, mvmvif->dbgfs_dir, 0600); MVM_DEBUGFS_ADD_FILE_VIF(rx_phyinfo, mvmvif->dbgfs_dir, 0600); MVM_DEBUGFS_ADD_FILE_VIF(quota_min, mvmvif->dbgfs_dir, 0600); @@ -1506,24 +799,6 @@ void iwl_mvm_vif_dbgfs_register(struct iwl_mvm *mvm, struct ieee80211_vif *vif) mvmvif == mvm->bf_allowed_vif) MVM_DEBUGFS_ADD_FILE_VIF(bf_params, mvmvif->dbgfs_dir, 0600); - if (fw_has_capa(&mvm->fw->ucode_capa, IWL_UCODE_TLV_CAPA_TOF_SUPPORT) && - !vif->p2p && (vif->type != NL80211_IFTYPE_P2P_DEVICE)) { - if (IWL_MVM_TOF_IS_RESPONDER && vif->type == NL80211_IFTYPE_AP) - MVM_DEBUGFS_ADD_FILE_VIF(tof_responder_params, - mvmvif->dbgfs_dir, 0600); - - MVM_DEBUGFS_ADD_FILE_VIF(tof_range_request, mvmvif->dbgfs_dir, - 0600); - MVM_DEBUGFS_ADD_FILE_VIF(tof_range_req_ext, mvmvif->dbgfs_dir, - 0600); - MVM_DEBUGFS_ADD_FILE_VIF(tof_enable, mvmvif->dbgfs_dir, - 0600); - MVM_DEBUGFS_ADD_FILE_VIF(tof_range_abort, mvmvif->dbgfs_dir, - 0600); - MVM_DEBUGFS_ADD_FILE_VIF(tof_range_response, mvmvif->dbgfs_dir, - 0400); - } - /* * Create symlink for convenience pointing to interface specific * debugfs entries for the driver. For example, under diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c index 52c361a6124c..e136475a34f6 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c @@ -69,6 +69,7 @@ #include "sta.h" #include "iwl-io.h" #include "debugfs.h" +#include "iwl-modparams.h" #include "fw/error-dump.h" static ssize_t iwl_dbgfs_ctdp_budget_read(struct file *file, @@ -1206,47 +1207,6 @@ static ssize_t iwl_dbgfs_fw_dbg_conf_read(struct file *file, return simple_read_from_buffer(user_buf, count, ppos, buf, pos); } -/* - * Enable / Disable continuous recording. - * Cause the FW to start continuous recording, by sending the relevant hcmd. - * Enable: input of every integer larger than 0, ENABLE_CONT_RECORDING. - * Disable: for 0 as input, DISABLE_CONT_RECORDING. - */ -static ssize_t iwl_dbgfs_cont_recording_write(struct iwl_mvm *mvm, - char *buf, size_t count, - loff_t *ppos) -{ - struct iwl_trans *trans = mvm->trans; - const struct iwl_fw_dbg_dest_tlv_v1 *dest = trans->dbg_dest_tlv; - struct iwl_continuous_record_cmd cont_rec = {}; - int ret, rec_mode; - - if (!iwl_mvm_firmware_running(mvm)) - return -EIO; - - if (!dest) - return -EOPNOTSUPP; - - if (dest->monitor_mode != SMEM_MODE || - trans->cfg->device_family < IWL_DEVICE_FAMILY_8000) - return -EOPNOTSUPP; - - ret = kstrtoint(buf, 0, &rec_mode); - if (ret) - return ret; - - cont_rec.record_mode.enable_recording = rec_mode ? - cpu_to_le16(ENABLE_CONT_RECORDING) : - cpu_to_le16(DISABLE_CONT_RECORDING); - - mutex_lock(&mvm->mutex); - ret = iwl_mvm_send_cmd_pdu(mvm, LDBG_CONFIG_CMD, 0, - sizeof(cont_rec), &cont_rec); - mutex_unlock(&mvm->mutex); - - return ret ?: count; -} - static ssize_t iwl_dbgfs_fw_dbg_conf_write(struct iwl_mvm *mvm, char *buf, size_t count, loff_t *ppos) @@ -1722,11 +1682,33 @@ iwl_dbgfs_send_echo_cmd_write(struct iwl_mvm *mvm, char *buf, return ret ?: count; } +struct iwl_mvm_sniffer_apply { + struct iwl_mvm *mvm; + u16 aid; +}; + +static bool iwl_mvm_sniffer_apply(struct iwl_notif_wait_data *notif_data, + struct iwl_rx_packet *pkt, void *data) +{ + struct iwl_mvm_sniffer_apply *apply = data; + + apply->mvm->cur_aid = cpu_to_le16(apply->aid); + + return true; +} + static ssize_t iwl_dbgfs_he_sniffer_params_write(struct iwl_mvm *mvm, char *buf, - size_t count, loff_t *ppos) + size_t count, loff_t *ppos) { + struct iwl_notification_wait wait; struct iwl_he_monitor_cmd he_mon_cmd = {}; + struct iwl_mvm_sniffer_apply apply = { + .mvm = mvm, + }; + u16 wait_cmds[] = { + iwl_cmd_id(HE_AIR_SNIFFER_CONFIG_CMD, DATA_PATH_GROUP, 0), + }; u32 aid; int ret; @@ -1742,10 +1724,30 @@ iwl_dbgfs_he_sniffer_params_write(struct iwl_mvm *mvm, char *buf, he_mon_cmd.aid = cpu_to_le16(aid); + apply.aid = aid; + mutex_lock(&mvm->mutex); + + /* + * Use the notification waiter to get our function triggered + * in sequence with other RX. This ensures that frames we get + * on the RX queue _before_ the new configuration is applied + * still have mvm->cur_aid pointing to the old AID, and that + * frames on the RX queue _after_ the firmware processed the + * new configuration (and sent the response, synchronously) + * get mvm->cur_aid correctly set to the new AID. + */ + iwl_init_notification_wait(&mvm->notif_wait, &wait, + wait_cmds, ARRAY_SIZE(wait_cmds), + iwl_mvm_sniffer_apply, &apply); + ret = iwl_mvm_send_cmd_pdu(mvm, iwl_cmd_id(HE_AIR_SNIFFER_CONFIG_CMD, DATA_PATH_GROUP, 0), 0, sizeof(he_mon_cmd), &he_mon_cmd); + + /* no need to really wait, we already did anyway */ + iwl_remove_notification(&mvm->notif_wait, &wait); + mutex_unlock(&mvm->mutex); return ret ?: count; @@ -1800,7 +1802,6 @@ MVM_DEBUGFS_READ_WRITE_FILE_OPS(scan_ant_rxchain, 8); MVM_DEBUGFS_READ_WRITE_FILE_OPS(d0i3_refs, 8); MVM_DEBUGFS_READ_WRITE_FILE_OPS(fw_dbg_conf, 8); MVM_DEBUGFS_WRITE_FILE_OPS(fw_dbg_collect, 64); -MVM_DEBUGFS_WRITE_FILE_OPS(cont_recording, 8); MVM_DEBUGFS_WRITE_FILE_OPS(max_amsdu_len, 8); MVM_DEBUGFS_WRITE_FILE_OPS(indirection_tbl, (IWL_RSS_INDIRECTION_TABLE_SIZE * 2)); @@ -2004,7 +2005,6 @@ int iwl_mvm_dbgfs_register(struct iwl_mvm *mvm, struct dentry *dbgfs_dir) MVM_DEBUGFS_ADD_FILE(fw_dbg_collect, mvm->debugfs_dir, 0200); MVM_DEBUGFS_ADD_FILE(max_amsdu_len, mvm->debugfs_dir, 0200); MVM_DEBUGFS_ADD_FILE(send_echo_cmd, mvm->debugfs_dir, 0200); - MVM_DEBUGFS_ADD_FILE(cont_recording, mvm->debugfs_dir, 0200); MVM_DEBUGFS_ADD_FILE(indirection_tbl, mvm->debugfs_dir, 0200); MVM_DEBUGFS_ADD_FILE(inject_packet, mvm->debugfs_dir, 0200); #ifdef CONFIG_ACPI @@ -2071,6 +2071,9 @@ int iwl_mvm_dbgfs_register(struct iwl_mvm *mvm, struct dentry *dbgfs_dir) if (!debugfs_create_blob("nvm_phy_sku", 0400, mvm->debugfs_dir, &mvm->nvm_phy_sku_blob)) goto err; + if (!debugfs_create_blob("nvm_reg", S_IRUSR, + mvm->debugfs_dir, &mvm->nvm_reg_blob)) + goto err; debugfs_create_file("mem", 0600, dbgfs_dir, mvm, &iwl_dbgfs_mem_ops); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw-api.h b/drivers/net/wireless/intel/iwlwifi/mvm/fw-api.h index 143c7fcaea41..e3eb812e0248 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw-api.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw-api.h @@ -8,6 +8,7 @@ * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH * Copyright(c) 2016 - 2017 Intel Deutschland GmbH + * Copyright (C) 2018 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -30,6 +31,7 @@ * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH * Copyright(c) 2016 - 2017 Intel Deutschland GmbH + * Copyright (C) 2018 Intel Corporation * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -89,7 +91,7 @@ #include "fw/api/sf.h" #include "fw/api/sta.h" #include "fw/api/stats.h" -#include "fw/api/tof.h" +#include "fw/api/location.h" #include "fw/api/tx.h" #endif /* __fw_api_h__ */ diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c index 0d6c313b6669..d3dc9d276e0f 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c @@ -293,9 +293,9 @@ static int iwl_mvm_load_ucode_wait_alive(struct iwl_mvm *mvm, enum iwl_ucode_type ucode_type) { struct iwl_notification_wait alive_wait; - struct iwl_mvm_alive_data alive_data; + struct iwl_mvm_alive_data alive_data = {}; const struct fw_img *fw; - int ret, i; + int ret; enum iwl_ucode_type old_type = mvm->fwrt.cur_fw_img; static const u16 alive_cmd[] = { MVM_ALIVE }; @@ -373,9 +373,6 @@ static int iwl_mvm_load_ucode_wait_alive(struct iwl_mvm *mvm, mvm->queue_info[IWL_MVM_DQA_CMD_QUEUE].tid_bitmap = BIT(IWL_MAX_TID_COUNT + 2); - for (i = 0; i < IEEE80211_MAX_QUEUES; i++) - atomic_set(&mvm->mac80211_queue_stop_count[i], 0); - set_bit(IWL_MVM_STATUS_FIRMWARE_RUNNING, &mvm->status); #ifdef CONFIG_IWLWIFI_DEBUGFS iwl_fw_set_dbg_rec_on(&mvm->fwrt); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c index 7779951a9533..7cfdd07d8736 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c @@ -97,11 +97,6 @@ struct iwl_mvm_mac_iface_iterator_data { bool found_vif; }; -struct iwl_mvm_hw_queues_iface_iterator_data { - struct ieee80211_vif *exclude_vif; - unsigned long used_hw_queues; -}; - static void iwl_mvm_mac_tsf_id_iter(void *_data, u8 *mac, struct ieee80211_vif *vif) { @@ -208,61 +203,6 @@ static void iwl_mvm_mac_tsf_id_iter(void *_data, u8 *mac, data->preferred_tsf = NUM_TSF_IDS; } -/* - * Get the mask of the queues used by the vif - */ -u32 iwl_mvm_mac_get_queues_mask(struct ieee80211_vif *vif) -{ - u32 qmask = 0, ac; - - if (vif->type == NL80211_IFTYPE_P2P_DEVICE) - return BIT(IWL_MVM_OFFCHANNEL_QUEUE); - - for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { - if (vif->hw_queue[ac] != IEEE80211_INVAL_HW_QUEUE) - qmask |= BIT(vif->hw_queue[ac]); - } - - if (vif->type == NL80211_IFTYPE_AP || - vif->type == NL80211_IFTYPE_ADHOC) - qmask |= BIT(vif->cab_queue); - - return qmask; -} - -static void iwl_mvm_iface_hw_queues_iter(void *_data, u8 *mac, - struct ieee80211_vif *vif) -{ - struct iwl_mvm_hw_queues_iface_iterator_data *data = _data; - - /* exclude the given vif */ - if (vif == data->exclude_vif) - return; - - data->used_hw_queues |= iwl_mvm_mac_get_queues_mask(vif); -} - -unsigned long iwl_mvm_get_used_hw_queues(struct iwl_mvm *mvm, - struct ieee80211_vif *exclude_vif) -{ - struct iwl_mvm_hw_queues_iface_iterator_data data = { - .exclude_vif = exclude_vif, - .used_hw_queues = - BIT(IWL_MVM_OFFCHANNEL_QUEUE) | - BIT(mvm->aux_queue) | - BIT(IWL_MVM_DQA_GCAST_QUEUE), - }; - - lockdep_assert_held(&mvm->mutex); - - /* mark all VIF used hw queues */ - ieee80211_iterate_active_interfaces_atomic( - mvm->hw, IEEE80211_IFACE_ITER_RESUME_ALL, - iwl_mvm_iface_hw_queues_iter, &data); - - return data.used_hw_queues; -} - static void iwl_mvm_mac_iface_iterator(void *_data, u8 *mac, struct ieee80211_vif *vif) { @@ -360,8 +300,6 @@ int iwl_mvm_mac_ctxt_init(struct iwl_mvm *mvm, struct ieee80211_vif *vif) mvm->hw, IEEE80211_IFACE_ITER_RESUME_ALL, iwl_mvm_mac_iface_iterator, &data); - used_hw_queues = iwl_mvm_get_used_hw_queues(mvm, vif); - /* * In the case we're getting here during resume, it's similar to * firmware restart, and with RESUME_ALL the iterator will find @@ -416,9 +354,6 @@ int iwl_mvm_mac_ctxt_init(struct iwl_mvm *mvm, struct ieee80211_vif *vif) * the ones here - no real limit */ queue_limit = IEEE80211_MAX_QUEUES; - BUILD_BUG_ON(IEEE80211_MAX_QUEUES > - BITS_PER_BYTE * - sizeof(mvm->hw_queue_to_mac80211[0])); /* * Find available queues, and allocate them to the ACs. When in @@ -446,9 +381,6 @@ int iwl_mvm_mac_ctxt_init(struct iwl_mvm *mvm, struct ieee80211_vif *vif) * queue value (when queue is enabled). */ mvmvif->cab_queue = IWL_MVM_DQA_GCAST_QUEUE; - vif->cab_queue = IWL_MVM_DQA_GCAST_QUEUE; - } else { - vif->cab_queue = IEEE80211_INVAL_HW_QUEUE; } mvmvif->bcast_sta.sta_id = IWL_MVM_INVALID_STA; @@ -462,8 +394,6 @@ int iwl_mvm_mac_ctxt_init(struct iwl_mvm *mvm, struct ieee80211_vif *vif) exit_fail: memset(mvmvif, 0, sizeof(struct iwl_mvm_vif)); - memset(vif->hw_queue, IEEE80211_INVAL_HW_QUEUE, sizeof(vif->hw_queue)); - vif->cab_queue = IEEE80211_INVAL_HW_QUEUE; return ret; } @@ -778,27 +708,9 @@ static int iwl_mvm_mac_ctxt_cmd_sta(struct iwl_mvm *mvm, if (vif->bss_conf.assoc && vif->bss_conf.he_support && !iwlwifi_mod_params.disable_11ax) { - struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); - u8 sta_id = mvmvif->ap_sta_id; - cmd.filter_flags |= cpu_to_le32(MAC_FILTER_IN_11AX); - if (sta_id != IWL_MVM_INVALID_STA) { - struct ieee80211_sta *sta; - - sta = rcu_dereference_protected(mvm->fw_id_to_mac_id[sta_id], - lockdep_is_held(&mvm->mutex)); - - /* - * TODO: we should check the ext cap IE but it is - * unclear why the spec requires two bits (one in HE - * cap IE, and one in the ext cap IE). In the meantime - * rely on the HE cap IE only. - */ - if (sta && (sta->he_cap.he_cap_elem.mac_cap_info[0] & - IEEE80211_HE_MAC_CAP0_TWT_RES)) - ctxt_sta->data_policy |= - cpu_to_le32(TWT_SUPPORTED); - } + if (vif->bss_conf.twt_requester) + ctxt_sta->data_policy |= cpu_to_le32(TWT_SUPPORTED); } @@ -881,8 +793,6 @@ static int iwl_mvm_mac_ctxt_cmd_p2p_device(struct iwl_mvm *mvm, iwl_mvm_mac_ctxt_cmd_common(mvm, vif, &cmd, NULL, action); - cmd.protection_flags |= cpu_to_le32(MAC_PROT_FLG_TGG_PROTECT); - /* Override the filter flags to accept only probe requests */ cmd.filter_flags = cpu_to_le32(MAC_FILTER_IN_PROBE_REQUEST); @@ -1203,7 +1113,7 @@ static void iwl_mvm_mac_ctxt_cmd_fill_ap(struct iwl_mvm *mvm, if (!fw_has_api(&mvm->fw->ucode_capa, IWL_UCODE_TLV_API_STA_TYPE)) - ctxt_ap->mcast_qid = cpu_to_le32(vif->cab_queue); + ctxt_ap->mcast_qid = cpu_to_le32(mvmvif->cab_queue); /* * Only set the beacon time when the MAC is being added, when we @@ -1435,7 +1345,7 @@ void iwl_mvm_rx_beacon_notif(struct iwl_mvm *mvm, agg_status = iwl_mvm_get_agg_status(mvm, beacon_notify_hdr); status = le16_to_cpu(agg_status->status) & TX_STATUS_MSK; IWL_DEBUG_RX(mvm, - "beacon status %#x retries:%d tsf:0x%16llX gp2:0x%X rate:%d\n", + "beacon status %#x retries:%d tsf:0x%016llX gp2:0x%X rate:%d\n", status, beacon_notify_hdr->failure_frame, le64_to_cpu(beacon->tsf), mvm->ap_last_beacon_gp2, @@ -1472,35 +1382,48 @@ void iwl_mvm_rx_beacon_notif(struct iwl_mvm *mvm, } } -static void iwl_mvm_beacon_loss_iterator(void *_data, u8 *mac, - struct ieee80211_vif *vif) +void iwl_mvm_rx_missed_beacons_notif(struct iwl_mvm *mvm, + struct iwl_rx_cmd_buffer *rxb) { - struct iwl_missed_beacons_notif *missed_beacons = _data; - struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); - struct iwl_mvm *mvm = mvmvif->mvm; + struct iwl_rx_packet *pkt = rxb_addr(rxb); + struct iwl_missed_beacons_notif *mb = (void *)pkt->data; struct iwl_fw_dbg_trigger_missed_bcon *bcon_trig; struct iwl_fw_dbg_trigger_tlv *trigger; u32 stop_trig_missed_bcon, stop_trig_missed_bcon_since_rx; u32 rx_missed_bcon, rx_missed_bcon_since_rx; + struct ieee80211_vif *vif; + u32 id = le32_to_cpu(mb->mac_id); - if (mvmvif->id != (u16)le32_to_cpu(missed_beacons->mac_id)) - return; + IWL_DEBUG_INFO(mvm, + "missed bcn mac_id=%u, consecutive=%u (%u, %u, %u)\n", + le32_to_cpu(mb->mac_id), + le32_to_cpu(mb->consec_missed_beacons), + le32_to_cpu(mb->consec_missed_beacons_since_last_rx), + le32_to_cpu(mb->num_recvd_beacons), + le32_to_cpu(mb->num_expected_beacons)); + + rcu_read_lock(); + + vif = iwl_mvm_rcu_dereference_vif_id(mvm, id, true); + if (!vif) + goto out; - rx_missed_bcon = le32_to_cpu(missed_beacons->consec_missed_beacons); + rx_missed_bcon = le32_to_cpu(mb->consec_missed_beacons); rx_missed_bcon_since_rx = - le32_to_cpu(missed_beacons->consec_missed_beacons_since_last_rx); + le32_to_cpu(mb->consec_missed_beacons_since_last_rx); /* * TODO: the threshold should be adjusted based on latency conditions, * and/or in case of a CS flow on one of the other AP vifs. */ - if (le32_to_cpu(missed_beacons->consec_missed_beacons_since_last_rx) > - IWL_MVM_MISSED_BEACONS_THRESHOLD) + if (rx_missed_bcon > IWL_MVM_MISSED_BEACONS_THRESHOLD_LONG) + iwl_mvm_connection_loss(mvm, vif, "missed beacons"); + else if (rx_missed_bcon_since_rx > IWL_MVM_MISSED_BEACONS_THRESHOLD) ieee80211_beacon_loss(vif); trigger = iwl_fw_dbg_trigger_on(&mvm->fwrt, ieee80211_vif_to_wdev(vif), FW_DBG_TRIGGER_MISSED_BEACONS); if (!trigger) - return; + goto out; bcon_trig = (void *)trigger->data; stop_trig_missed_bcon = le32_to_cpu(bcon_trig->stop_consec_missed_bcon); @@ -1512,28 +1435,11 @@ static void iwl_mvm_beacon_loss_iterator(void *_data, u8 *mac, if (rx_missed_bcon_since_rx >= stop_trig_missed_bcon_since_rx || rx_missed_bcon >= stop_trig_missed_bcon) iwl_fw_dbg_collect_trig(&mvm->fwrt, trigger, NULL); -} - -void iwl_mvm_rx_missed_beacons_notif(struct iwl_mvm *mvm, - struct iwl_rx_cmd_buffer *rxb) -{ - struct iwl_rx_packet *pkt = rxb_addr(rxb); - struct iwl_missed_beacons_notif *mb = (void *)pkt->data; - - IWL_DEBUG_INFO(mvm, - "missed bcn mac_id=%u, consecutive=%u (%u, %u, %u)\n", - le32_to_cpu(mb->mac_id), - le32_to_cpu(mb->consec_missed_beacons), - le32_to_cpu(mb->consec_missed_beacons_since_last_rx), - le32_to_cpu(mb->num_recvd_beacons), - le32_to_cpu(mb->num_expected_beacons)); - - ieee80211_iterate_active_interfaces_atomic(mvm->hw, - IEEE80211_IFACE_ITER_NORMAL, - iwl_mvm_beacon_loss_iterator, - mb); iwl_fw_dbg_apply_point(&mvm->fwrt, IWL_FW_INI_APPLY_MISSED_BEACONS); + +out: + rcu_read_unlock(); } void iwl_mvm_rx_stored_beacon_notif(struct iwl_mvm *mvm, @@ -1575,16 +1481,29 @@ void iwl_mvm_rx_stored_beacon_notif(struct iwl_mvm *mvm, ieee80211_rx_napi(mvm->hw, NULL, skb, NULL); } -static void iwl_mvm_probe_resp_data_iter(void *_data, u8 *mac, - struct ieee80211_vif *vif) +void iwl_mvm_probe_resp_data_notif(struct iwl_mvm *mvm, + struct iwl_rx_cmd_buffer *rxb) { - struct iwl_probe_resp_data_notif *notif = _data; - struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); + struct iwl_rx_packet *pkt = rxb_addr(rxb); + struct iwl_probe_resp_data_notif *notif = (void *)pkt->data; struct iwl_probe_resp_data *old_data, *new_data; + int len = iwl_rx_packet_payload_len(pkt); + u32 id = le32_to_cpu(notif->mac_id); + struct ieee80211_vif *vif; + struct iwl_mvm_vif *mvmvif; - if (mvmvif->id != (u16)le32_to_cpu(notif->mac_id)) + if (WARN_ON_ONCE(len < sizeof(*notif))) return; + IWL_DEBUG_INFO(mvm, "Probe response data notif: noa %d, csa %d\n", + notif->noa_active, notif->csa_counter); + + vif = iwl_mvm_rcu_dereference_vif_id(mvm, id, false); + if (!vif) + return; + + mvmvif = iwl_mvm_vif_from_mac80211(vif); + new_data = kzalloc(sizeof(*new_data), GFP_KERNEL); if (!new_data) return; @@ -1615,25 +1534,6 @@ static void iwl_mvm_probe_resp_data_iter(void *_data, u8 *mac, ieee80211_csa_set_counter(vif, notif->csa_counter); } -void iwl_mvm_probe_resp_data_notif(struct iwl_mvm *mvm, - struct iwl_rx_cmd_buffer *rxb) -{ - struct iwl_rx_packet *pkt = rxb_addr(rxb); - struct iwl_probe_resp_data_notif *notif = (void *)pkt->data; - int len = iwl_rx_packet_payload_len(pkt); - - if (WARN_ON_ONCE(len < sizeof(*notif))) - return; - - IWL_DEBUG_INFO(mvm, "Probe response data notif: noa %d, csa %d\n", - notif->noa_active, notif->csa_counter); - - ieee80211_iterate_active_interfaces(mvm->hw, - IEEE80211_IFACE_ITER_ACTIVE, - iwl_mvm_probe_resp_data_iter, - notif); -} - void iwl_mvm_channel_switch_noa_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb) { diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 97dc464379d2..c9effd7f0ef8 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -395,6 +395,21 @@ int iwl_mvm_init_fw_regd(struct iwl_mvm *mvm) return ret; } +const static u8 he_if_types_ext_capa_sta[] = { + [0] = WLAN_EXT_CAPA1_EXT_CHANNEL_SWITCHING, + [7] = WLAN_EXT_CAPA8_OPMODE_NOTIF, + [9] = WLAN_EXT_CAPA10_TWT_REQUESTER_SUPPORT, +}; + +const static struct wiphy_iftype_ext_capab he_iftypes_ext_capa[] = { + { + .iftype = NL80211_IFTYPE_STATION, + .extended_capabilities = he_if_types_ext_capa_sta, + .extended_capabilities_mask = he_if_types_ext_capa_sta, + .extended_capabilities_len = sizeof(he_if_types_ext_capa_sta), + }, +}; + int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm) { struct ieee80211_hw *hw = mvm->hw; @@ -410,7 +425,6 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm) ieee80211_hw_set(hw, SIGNAL_DBM); ieee80211_hw_set(hw, SPECTRUM_MGMT); ieee80211_hw_set(hw, REPORTS_TX_ACK_STATUS); - ieee80211_hw_set(hw, QUEUE_CONTROL); ieee80211_hw_set(hw, WANT_MONITOR_VIF); ieee80211_hw_set(hw, SUPPORTS_PS); ieee80211_hw_set(hw, SUPPORTS_DYNAMIC_PS); @@ -424,6 +438,10 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm) ieee80211_hw_set(hw, NEEDS_UNIQUE_STA_ADDR); ieee80211_hw_set(hw, DEAUTH_NEED_MGD_TX_PREP); ieee80211_hw_set(hw, SUPPORTS_VHT_EXT_NSS_BW); + ieee80211_hw_set(hw, BUFF_MMPDU_TXQ); + ieee80211_hw_set(hw, STA_MMPDU_TXQ); + ieee80211_hw_set(hw, TX_AMSDU); + ieee80211_hw_set(hw, TX_FRAG_LIST); if (iwl_mvm_has_tlc_offload(mvm)) { ieee80211_hw_set(hw, TX_AMPDU_SETUP_IN_HW); @@ -469,6 +487,7 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm) hw->uapsd_queues = IWL_MVM_UAPSD_QUEUES; hw->uapsd_max_sp_len = IWL_UAPSD_MAX_SP; + hw->max_tx_fragments = mvm->trans->max_skb_frags; BUILD_BUG_ON(ARRAY_SIZE(mvm->ciphers) < ARRAY_SIZE(mvm_ciphers) + 6); memcpy(mvm->ciphers, mvm_ciphers, sizeof(mvm_ciphers)); @@ -534,6 +553,7 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm) hw->sta_data_size = sizeof(struct iwl_mvm_sta); hw->vif_data_size = sizeof(struct iwl_mvm_vif); hw->chanctx_data_size = sizeof(u16); + hw->txq_data_size = sizeof(struct iwl_mvm_txq); hw->wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION) | BIT(NL80211_IFTYPE_P2P_CLIENT) | @@ -673,6 +693,13 @@ int iwl_mvm_mac_setup_register(struct iwl_mvm *mvm) NL80211_EXT_FEATURE_OCE_PROBE_REQ_HIGH_TX_RATE); } + if (mvm->nvm_data->sku_cap_11ax_enable && + !iwlwifi_mod_params.disable_11ax) { + hw->wiphy->iftype_ext_capab = he_iftypes_ext_capa; + hw->wiphy->num_iftype_ext_capab = + ARRAY_SIZE(he_iftypes_ext_capa); + } + mvm->rts_threshold = IEEE80211_MAX_RTS_THRESHOLD; #ifdef CONFIG_PM_SLEEP @@ -776,7 +803,6 @@ static bool iwl_mvm_defer_tx(struct iwl_mvm *mvm, goto out; __skb_queue_tail(&mvm->d0i3_tx, skb); - ieee80211_stop_queues(mvm->hw); /* trigger wakeup */ iwl_mvm_ref(mvm, IWL_MVM_REF_TX); @@ -796,13 +822,15 @@ static void iwl_mvm_mac_tx(struct ieee80211_hw *hw, struct ieee80211_sta *sta = control->sta; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct ieee80211_hdr *hdr = (void *)skb->data; + bool offchannel = IEEE80211_SKB_CB(skb)->flags & + IEEE80211_TX_CTL_TX_OFFCHAN; if (iwl_mvm_is_radio_killed(mvm)) { IWL_DEBUG_DROP(mvm, "Dropping - RF/CT KILL\n"); goto drop; } - if (info->hw_queue == IWL_MVM_OFFCHANNEL_QUEUE && + if (offchannel && !test_bit(IWL_MVM_STATUS_ROC_RUNNING, &mvm->status) && !test_bit(IWL_MVM_STATUS_ROC_AUX_RUNNING, &mvm->status)) goto drop; @@ -815,8 +843,8 @@ static void iwl_mvm_mac_tx(struct ieee80211_hw *hw, sta = NULL; /* If there is no sta, and it's not offchannel - send through AP */ - if (info->control.vif->type == NL80211_IFTYPE_STATION && - info->hw_queue != IWL_MVM_OFFCHANNEL_QUEUE && !sta) { + if (!sta && info->control.vif->type == NL80211_IFTYPE_STATION && + !offchannel) { struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(info->control.vif); u8 ap_sta_id = READ_ONCE(mvmvif->ap_sta_id); @@ -844,22 +872,95 @@ static void iwl_mvm_mac_tx(struct ieee80211_hw *hw, ieee80211_free_txskb(hw, skb); } -static inline bool iwl_enable_rx_ampdu(const struct iwl_cfg *cfg) +void iwl_mvm_mac_itxq_xmit(struct ieee80211_hw *hw, struct ieee80211_txq *txq) { - if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_RXAGG) - return false; - return true; + struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw); + struct iwl_mvm_txq *mvmtxq = iwl_mvm_txq_from_mac80211(txq); + struct sk_buff *skb = NULL; + + /* + * No need for threads to be pending here, they can leave the first + * taker all the work. + * + * mvmtxq->tx_request logic: + * + * If 0, no one is currently TXing, set to 1 to indicate current thread + * will now start TX and other threads should quit. + * + * If 1, another thread is currently TXing, set to 2 to indicate to + * that thread that there was another request. Since that request may + * have raced with the check whether the queue is empty, the TXing + * thread should check the queue's status one more time before leaving. + * This check is done in order to not leave any TX hanging in the queue + * until the next TX invocation (which may not even happen). + * + * If 2, another thread is currently TXing, and it will already double + * check the queue, so do nothing. + */ + if (atomic_fetch_add_unless(&mvmtxq->tx_request, 1, 2)) + return; + + rcu_read_lock(); + do { + while (likely(!mvmtxq->stopped && + (mvm->trans->system_pm_mode == + IWL_PLAT_PM_MODE_DISABLED))) { + skb = ieee80211_tx_dequeue(hw, txq); + + if (!skb) + break; + + if (!txq->sta) + iwl_mvm_tx_skb_non_sta(mvm, skb); + else + iwl_mvm_tx_skb(mvm, skb, txq->sta); + } + } while (atomic_dec_return(&mvmtxq->tx_request)); + rcu_read_unlock(); } -static inline bool iwl_enable_tx_ampdu(const struct iwl_cfg *cfg) +static void iwl_mvm_mac_wake_tx_queue(struct ieee80211_hw *hw, + struct ieee80211_txq *txq) { - if (iwlwifi_mod_params.disable_11n & IWL_DISABLE_HT_TXAGG) - return false; - if (iwlwifi_mod_params.disable_11n & IWL_ENABLE_HT_TXAGG) - return true; + struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw); + struct iwl_mvm_txq *mvmtxq = iwl_mvm_txq_from_mac80211(txq); - /* enabled by default */ - return true; + /* + * Please note that racing is handled very carefully here: + * mvmtxq->txq_id is updated during allocation, and mvmtxq->list is + * deleted afterwards. + * This means that if: + * mvmtxq->txq_id != INVALID_QUEUE && list_empty(&mvmtxq->list): + * queue is allocated and we can TX. + * mvmtxq->txq_id != INVALID_QUEUE && !list_empty(&mvmtxq->list): + * a race, should defer the frame. + * mvmtxq->txq_id == INVALID_QUEUE && list_empty(&mvmtxq->list): + * need to allocate the queue and defer the frame. + * mvmtxq->txq_id == INVALID_QUEUE && !list_empty(&mvmtxq->list): + * queue is already scheduled for allocation, no need to allocate, + * should defer the frame. + */ + + /* If the queue is allocated TX and return. */ + if (!txq->sta || mvmtxq->txq_id != IWL_MVM_INVALID_QUEUE) { + /* + * Check that list is empty to avoid a race where txq_id is + * already updated, but the queue allocation work wasn't + * finished + */ + if (unlikely(txq->sta && !list_empty(&mvmtxq->list))) + return; + + iwl_mvm_mac_itxq_xmit(hw, txq); + return; + } + + /* The list is being deleted only after the queue is fully allocated. */ + if (!list_empty(&mvmtxq->list)) + return; + + list_add_tail(&mvmtxq->list, &mvm->add_stream_txqs); + schedule_work(&mvm->add_stream_wk); } #define CHECK_BA_TRIGGER(_mvm, _trig, _tid_bm, _tid, _fmt...) \ @@ -974,7 +1075,7 @@ static int iwl_mvm_mac_ampdu_action(struct ieee80211_hw *hw, mvmvif = iwl_mvm_vif_from_mac80211(vif); cancel_delayed_work(&mvmvif->uapsd_nonagg_detected_wk); } - if (!iwl_enable_rx_ampdu(mvm->cfg)) { + if (!iwl_enable_rx_ampdu()) { ret = -EINVAL; break; } @@ -986,7 +1087,7 @@ static int iwl_mvm_mac_ampdu_action(struct ieee80211_hw *hw, timeout); break; case IEEE80211_AMPDU_TX_START: - if (!iwl_enable_tx_ampdu(mvm->cfg)) { + if (!iwl_enable_tx_ampdu()) { ret = -EINVAL; break; } @@ -1066,6 +1167,8 @@ static void iwl_mvm_restart_cleanup(struct iwl_mvm *mvm) iwl_mvm_stop_device(mvm); + mvm->cur_aid = 0; + mvm->scan_status = 0; mvm->ps_disabled = false; mvm->calibrating = false; @@ -1085,7 +1188,6 @@ static void iwl_mvm_restart_cleanup(struct iwl_mvm *mvm) iwl_mvm_reset_phy_ctxts(mvm); memset(mvm->fw_key_table, 0, sizeof(mvm->fw_key_table)); - memset(mvm->sta_deferred_frames, 0, sizeof(mvm->sta_deferred_frames)); memset(&mvm->last_bt_notif, 0, sizeof(mvm->last_bt_notif)); memset(&mvm->last_bt_ci_cmd, 0, sizeof(mvm->last_bt_ci_cmd)); @@ -1391,6 +1493,8 @@ static int iwl_mvm_mac_add_interface(struct ieee80211_hw *hw, if (ret) goto out_unlock; + rcu_assign_pointer(mvm->vif_id_to_mac[mvmvif->id], vif); + /* Counting number of interfaces is needed for legacy PM */ if (vif->type != NL80211_IFTYPE_P2P_DEVICE) mvm->vif_count++; @@ -1582,6 +1686,8 @@ static void iwl_mvm_mac_remove_interface(struct ieee80211_hw *hw, iwl_mvm_power_update_mac(mvm); iwl_mvm_mac_ctxt_remove(mvm, vif); + RCU_INIT_POINTER(mvm->vif_id_to_mac[mvmvif->id], NULL); + if (vif->type == NL80211_IFTYPE_MONITOR) mvm->monitor_on = false; @@ -2146,6 +2252,12 @@ static void iwl_mvm_bss_info_changed_station(struct iwl_mvm *mvm, iwl_mvm_mac_ctxt_recalc_tsf_id(mvm, vif); } + /* Update MU EDCA params */ + if (changes & BSS_CHANGED_QOS && mvmvif->associated && + bss_conf->assoc && vif->bss_conf.he_support && + !iwlwifi_mod_params.disable_11ax) + iwl_mvm_cfg_he_sta(mvm, vif, mvmvif->ap_sta_id); + /* * If we're not associated yet, take the (new) BSSID before associating * so the firmware knows. If we're already associated, then use the old @@ -2672,7 +2784,7 @@ static void __iwl_mvm_mac_sta_notify(struct ieee80211_hw *hw, return; spin_lock_bh(&mvmsta->lock); - for (tid = 0; tid < IWL_MAX_TID_COUNT; tid++) { + for (tid = 0; tid < ARRAY_SIZE(mvmsta->tid_data); tid++) { struct iwl_mvm_tid_data *tid_data = &mvmsta->tid_data[tid]; if (tid_data->txq_id == IWL_MVM_INVALID_QUEUE) @@ -2861,32 +2973,6 @@ iwl_mvm_tdls_check_trigger(struct iwl_mvm *mvm, peer_addr, action); } -static void iwl_mvm_purge_deferred_tx_frames(struct iwl_mvm *mvm, - struct iwl_mvm_sta *mvm_sta) -{ - struct iwl_mvm_tid_data *tid_data; - struct sk_buff *skb; - int i; - - spin_lock_bh(&mvm_sta->lock); - for (i = 0; i <= IWL_MAX_TID_COUNT; i++) { - tid_data = &mvm_sta->tid_data[i]; - - while ((skb = __skb_dequeue(&tid_data->deferred_tx_frames))) { - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - - /* - * The first deferred frame should've stopped the MAC - * queues, so we should never get a second deferred - * frame for the RA/TID. - */ - iwl_mvm_start_mac_queues(mvm, BIT(info->hw_queue)); - ieee80211_free_txskb(mvm->hw, skb); - } - } - spin_unlock_bh(&mvm_sta->lock); -} - static int iwl_mvm_mac_sta_state(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, @@ -2920,7 +3006,6 @@ static int iwl_mvm_mac_sta_state(struct ieee80211_hw *hw, */ if (old_state == IEEE80211_STA_NONE && new_state == IEEE80211_STA_NOTEXIST) { - iwl_mvm_purge_deferred_tx_frames(mvm, mvm_sta); flush_work(&mvm->add_stream_wk); /* @@ -2967,6 +3052,8 @@ static int iwl_mvm_mac_sta_state(struct ieee80211_hw *hw, iwl_mvm_tdls_check_trigger(mvm, vif, sta->addr, NL80211_TDLS_SETUP); } + + sta->max_rc_amsdu_len = 1; } else if (old_state == IEEE80211_STA_NONE && new_state == IEEE80211_STA_AUTH) { /* @@ -3036,6 +3123,16 @@ static int iwl_mvm_mac_sta_state(struct ieee80211_hw *hw, iwl_mvm_tdls_check_trigger(mvm, vif, sta->addr, NL80211_TDLS_DISABLE_LINK); } + + /* Remove STA key if this is an AP using WEP */ + if (vif->type == NL80211_IFTYPE_AP && mvmvif->ap_wep_key) { + int rm_ret = iwl_mvm_remove_sta_key(mvm, vif, sta, + mvmvif->ap_wep_key); + + if (!ret) + ret = rm_ret; + } + } else { ret = -EIO; } @@ -3431,14 +3528,20 @@ static int iwl_mvm_send_aux_roc_cmd(struct iwl_mvm *mvm, .id_and_color = cpu_to_le32(FW_CMD_ID_AND_COLOR(MAC_INDEX_AUX, 0)), .sta_id_and_color = cpu_to_le32(mvm->aux_sta.sta_id), - /* Set the channel info data */ - .channel_info.band = (channel->band == NL80211_BAND_2GHZ) ? - PHY_BAND_24 : PHY_BAND_5, - .channel_info.channel = channel->hw_value, - .channel_info.width = PHY_VHT_CHANNEL_MODE20, - /* Set the time and duration */ - .apply_time = cpu_to_le32(iwl_read_prph(mvm->trans, time_reg)), - }; + }; + struct iwl_hs20_roc_req_tail *tail = iwl_mvm_chan_info_cmd_tail(mvm, + &aux_roc_req.channel_info); + u16 len = sizeof(aux_roc_req) - iwl_mvm_chan_info_padding(mvm); + + /* Set the channel info data */ + iwl_mvm_set_chan_info(mvm, &aux_roc_req.channel_info, channel->hw_value, + (channel->band == NL80211_BAND_2GHZ) ? + PHY_BAND_24 : PHY_BAND_5, + PHY_VHT_CHANNEL_MODE20, + 0); + + /* Set the time and duration */ + tail->apply_time = cpu_to_le32(iwl_read_prph(mvm->trans, time_reg)); delay = AUX_ROC_MIN_DELAY; req_dur = MSEC_TO_TU(duration); @@ -3463,15 +3566,15 @@ static int iwl_mvm_send_aux_roc_cmd(struct iwl_mvm *mvm, } } - aux_roc_req.duration = cpu_to_le32(req_dur); - aux_roc_req.apply_time_max_delay = cpu_to_le32(delay); + tail->duration = cpu_to_le32(req_dur); + tail->apply_time_max_delay = cpu_to_le32(delay); IWL_DEBUG_TE(mvm, "ROC: Requesting to remain on channel %u for %ums (requested = %ums, max_delay = %ums, dtim_interval = %ums)\n", channel->hw_value, req_dur, duration, delay, dtim_interval); /* Set the node address */ - memcpy(aux_roc_req.node_addr, vif->addr, ETH_ALEN); + memcpy(tail->node_addr, vif->addr, ETH_ALEN); lockdep_assert_held(&mvm->mutex); @@ -3502,7 +3605,7 @@ static int iwl_mvm_send_aux_roc_cmd(struct iwl_mvm *mvm, ARRAY_SIZE(time_event_response), iwl_mvm_rx_aux_roc, te_data); - res = iwl_mvm_send_cmd_pdu(mvm, HOT_SPOT_CMD, 0, sizeof(aux_roc_req), + res = iwl_mvm_send_cmd_pdu(mvm, HOT_SPOT_CMD, 0, len, &aux_roc_req); if (res) { @@ -4656,8 +4759,35 @@ static void iwl_mvm_sync_rx_queues(struct ieee80211_hw *hw) mutex_unlock(&mvm->mutex); } +static bool iwl_mvm_can_hw_csum(struct sk_buff *skb) +{ + u8 protocol = ip_hdr(skb)->protocol; + + if (!IS_ENABLED(CONFIG_INET)) + return false; + + return protocol == IPPROTO_TCP || protocol == IPPROTO_UDP; +} + +static bool iwl_mvm_mac_can_aggregate(struct ieee80211_hw *hw, + struct sk_buff *head, + struct sk_buff *skb) +{ + struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw); + + /* For now don't aggregate IPv6 in AMSDU */ + if (skb->protocol != htons(ETH_P_IP)) + return false; + + if (!iwl_mvm_is_csum_supported(mvm)) + return true; + + return iwl_mvm_can_hw_csum(skb) == iwl_mvm_can_hw_csum(head); +} + const struct ieee80211_ops iwl_mvm_hw_ops = { .tx = iwl_mvm_mac_tx, + .wake_tx_queue = iwl_mvm_mac_wake_tx_queue, .ampdu_action = iwl_mvm_mac_ampdu_action, .start = iwl_mvm_mac_start, .reconfig_complete = iwl_mvm_mac_reconfig_complete, @@ -4731,6 +4861,7 @@ const struct ieee80211_ops iwl_mvm_hw_ops = { #endif .get_survey = iwl_mvm_mac_get_survey, .sta_statistics = iwl_mvm_mac_sta_statistics, + .can_aggregate_in_amsdu = iwl_mvm_mac_can_aggregate, #ifdef CONFIG_IWLWIFI_DEBUGFS .sta_add_debugfs = iwl_mvm_sta_add_debugfs, #endif diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h index 1aa690e081ff..12e9ecc3ee27 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h @@ -83,7 +83,6 @@ #include "sta.h" #include "fw-api.h" #include "constants.h" -#include "tof.h" #include "fw/runtime.h" #include "fw/dbg.h" #include "fw/acpi.h" @@ -95,6 +94,8 @@ /* RSSI offset for WkP */ #define IWL_RSSI_OFFSET 50 #define IWL_MVM_MISSED_BEACONS_THRESHOLD 8 +#define IWL_MVM_MISSED_BEACONS_THRESHOLD_LONG 16 + /* A TimeUnit is 1024 microsecond */ #define MSEC_TO_TU(_msec) (_msec*1000/1024) @@ -299,17 +300,38 @@ enum iwl_bt_force_ant_mode { }; /** + * struct iwl_mvm_low_latency_force - low latency force mode set by debugfs + * @LOW_LATENCY_FORCE_UNSET: unset force mode + * @LOW_LATENCY_FORCE_ON: for low latency on + * @LOW_LATENCY_FORCE_OFF: for low latency off + * @NUM_LOW_LATENCY_FORCE: max num of modes + */ +enum iwl_mvm_low_latency_force { + LOW_LATENCY_FORCE_UNSET, + LOW_LATENCY_FORCE_ON, + LOW_LATENCY_FORCE_OFF, + NUM_LOW_LATENCY_FORCE +}; + +/** * struct iwl_mvm_low_latency_cause - low latency set causes * @LOW_LATENCY_TRAFFIC: indicates low latency traffic was detected * @LOW_LATENCY_DEBUGFS: low latency mode set from debugfs * @LOW_LATENCY_VCMD: low latency mode set from vendor command * @LOW_LATENCY_VIF_TYPE: low latency mode set because of vif type (ap) +* @LOW_LATENCY_DEBUGFS_FORCE_ENABLE: indicate that force mode is enabled +* the actual set/unset is done with LOW_LATENCY_DEBUGFS_FORCE +* @LOW_LATENCY_DEBUGFS_FORCE: low latency force mode from debugfs +* set this with LOW_LATENCY_DEBUGFS_FORCE_ENABLE flag +* in low_latency. */ enum iwl_mvm_low_latency_cause { LOW_LATENCY_TRAFFIC = BIT(0), LOW_LATENCY_DEBUGFS = BIT(1), LOW_LATENCY_VCMD = BIT(2), LOW_LATENCY_VIF_TYPE = BIT(3), + LOW_LATENCY_DEBUGFS_FORCE_ENABLE = BIT(4), + LOW_LATENCY_DEBUGFS_FORCE = BIT(5), }; /** @@ -360,8 +382,10 @@ struct iwl_probe_resp_data { * @pm_enabled - Indicate if MAC power management is allowed * @monitor_active: indicates that monitor context is configured, and that the * interface should get quota etc. - * @low_latency: indicates low latency is set, see - * enum &iwl_mvm_low_latency_cause for causes. + * @low_latency: bit flags for low latency + * see enum &iwl_mvm_low_latency_cause for causes. + * @low_latency_actual: boolean, indicates low latency is set, + * as a result from low_latency bit flags and takes force into account. * @ps_disabled: indicates that this interface requires PS to be disabled * @queue_params: QoS params for this MAC * @bcast_sta: station used for broadcast packets. Used by the following @@ -393,7 +417,8 @@ struct iwl_mvm_vif { bool ap_ibss_active; bool pm_enabled; bool monitor_active; - u8 low_latency; + u8 low_latency: 6; + u8 low_latency_actual: 1; bool ps_disabled; struct iwl_mvm_vif_bf_data bf_data; @@ -778,6 +803,39 @@ struct iwl_mvm_geo_profile { u8 values[ACPI_GEO_TABLE_SIZE]; }; +struct iwl_mvm_txq { + struct list_head list; + u16 txq_id; + atomic_t tx_request; + bool stopped; +}; + +static inline struct iwl_mvm_txq * +iwl_mvm_txq_from_mac80211(struct ieee80211_txq *txq) +{ + return (void *)txq->drv_priv; +} + +static inline struct iwl_mvm_txq * +iwl_mvm_txq_from_tid(struct ieee80211_sta *sta, u8 tid) +{ + if (tid == IWL_MAX_TID_COUNT) + tid = IEEE80211_NUM_TIDS; + + return (void *)sta->txq[tid]->drv_priv; +} + +/** + * struct iwl_mvm_tvqm_txq_info - maps TVQM hw queue to tid + * + * @sta_id: sta id + * @txq_tid: txq tid + */ +struct iwl_mvm_tvqm_txq_info { + u8 sta_id; + u8 txq_tid; +}; + struct iwl_mvm_dqa_txq_info { u8 ra_sta_id; /* The RA this queue is mapped to, if exists */ bool reserved; /* Is this the TXQ reserved for a STA */ @@ -843,13 +901,13 @@ struct iwl_mvm { u64 on_time_scan; } radio_stats, accu_radio_stats; - u16 hw_queue_to_mac80211[IWL_MAX_TVQM_QUEUES]; - - struct iwl_mvm_dqa_txq_info queue_info[IWL_MAX_HW_QUEUES]; + struct list_head add_stream_txqs; + union { + struct iwl_mvm_dqa_txq_info queue_info[IWL_MAX_HW_QUEUES]; + struct iwl_mvm_tvqm_txq_info tvqm_info[IWL_MAX_TVQM_QUEUES]; + }; struct work_struct add_stream_wk; /* To add streams to queues */ - atomic_t mac80211_queue_stop_count[IEEE80211_MAX_QUEUES]; - const char *nvm_file_name; struct iwl_nvm_data *nvm_data; /* NVM sections */ @@ -863,7 +921,6 @@ struct iwl_mvm { /* data related to data path */ struct iwl_rx_phy_info last_phy_info; struct ieee80211_sta __rcu *fw_id_to_mac_id[IWL_MVM_STATION_COUNT]; - unsigned long sta_deferred_frames[BITS_TO_LONGS(IWL_MVM_STATION_COUNT)]; u8 rx_ba_sessions; /* configured by mac80211 */ @@ -932,6 +989,7 @@ struct iwl_mvm { struct debugfs_blob_wrapper nvm_calib_blob; struct debugfs_blob_wrapper nvm_prod_blob; struct debugfs_blob_wrapper nvm_phy_sku_blob; + struct debugfs_blob_wrapper nvm_reg_blob; struct iwl_mvm_frame_stats drv_rx_stats; spinlock_t drv_stats_lock; @@ -955,6 +1013,7 @@ struct iwl_mvm { u8 refs[IWL_MVM_REF_COUNT]; u8 vif_count; + struct ieee80211_vif __rcu *vif_id_to_mac[NUM_MAC_INDEX_DRIVER]; /* -1 for always, 0 for never, >0 for that many times */ s8 fw_restart; @@ -1090,7 +1149,6 @@ struct iwl_mvm { u32 ciphers[IWL_MVM_NUM_CIPHERS]; struct ieee80211_cipher_scheme cs[IWL_UCODE_MAX_CS]; - struct iwl_mvm_tof_data tof_data; struct ieee80211_vif *nan_vif; #define IWL_MAX_BAID 32 @@ -1106,6 +1164,10 @@ struct iwl_mvm { /* does a monitor vif exist (only one can exist hence bool) */ bool monitor_on; + + /* sniffer data to include in radiotap */ + __le16 cur_aid; + #ifdef CONFIG_ACPI struct iwl_mvm_sar_profile sar_profiles[ACPI_SAR_PROFILE_NUM]; struct iwl_mvm_geo_profile geo_profiles[ACPI_NUM_GEO_PROFILES]; @@ -1150,7 +1212,6 @@ enum iwl_mvm_init_status { IWL_MVM_INIT_STATUS_THERMAL_INIT_COMPLETE = BIT(0), IWL_MVM_INIT_STATUS_LEDS_INIT_COMPLETE = BIT(1), IWL_MVM_INIT_STATUS_REG_HW_INIT_COMPLETE = BIT(2), - IWL_MVM_INIT_STATUS_TOF_INIT_COMPLETE = BIT(3), }; static inline bool iwl_mvm_is_radio_killed(struct iwl_mvm *mvm) @@ -1207,6 +1268,19 @@ iwl_mvm_sta_from_staid_protected(struct iwl_mvm *mvm, u8 sta_id) return iwl_mvm_sta_from_mac80211(sta); } +static inline struct ieee80211_vif * +iwl_mvm_rcu_dereference_vif_id(struct iwl_mvm *mvm, u8 vif_id, bool rcu) +{ + if (WARN_ON(vif_id >= ARRAY_SIZE(mvm->vif_id_to_mac))) + return NULL; + + if (rcu) + return rcu_dereference(mvm->vif_id_to_mac[vif_id]); + + return rcu_dereference_protected(mvm->vif_id_to_mac[vif_id], + lockdep_is_held(&mvm->mutex)); +} + static inline bool iwl_mvm_is_d0i3_supported(struct iwl_mvm *mvm) { return !iwlwifi_mod_params.d0i3_disable && @@ -1470,6 +1544,11 @@ void iwl_mvm_set_tx_cmd(struct iwl_mvm *mvm, struct sk_buff *skb, void iwl_mvm_set_tx_cmd_rate(struct iwl_mvm *mvm, struct iwl_tx_cmd *tx_cmd, struct ieee80211_tx_info *info, struct ieee80211_sta *sta, __le16 fc); +void iwl_mvm_mac_itxq_xmit(struct ieee80211_hw *hw, struct ieee80211_txq *txq); +unsigned int iwl_mvm_max_amsdu_size(struct iwl_mvm *mvm, + struct ieee80211_sta *sta, + unsigned int tid); + #ifdef CONFIG_IWLWIFI_DEBUG const char *iwl_mvm_get_tx_fail_reason(u32 status); #else @@ -1599,7 +1678,6 @@ int iwl_mvm_mac_ctxt_add(struct iwl_mvm *mvm, struct ieee80211_vif *vif); int iwl_mvm_mac_ctxt_changed(struct iwl_mvm *mvm, struct ieee80211_vif *vif, bool force_assoc_off, const u8 *bssid_override); int iwl_mvm_mac_ctxt_remove(struct iwl_mvm *mvm, struct ieee80211_vif *vif); -u32 iwl_mvm_mac_get_queues_mask(struct ieee80211_vif *vif); int iwl_mvm_mac_ctxt_beacon_changed(struct iwl_mvm *mvm, struct ieee80211_vif *vif); void iwl_mvm_rx_beacon_notif(struct iwl_mvm *mvm, @@ -1615,8 +1693,6 @@ void iwl_mvm_window_status_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb); void iwl_mvm_mac_ctxt_recalc_tsf_id(struct iwl_mvm *mvm, struct ieee80211_vif *vif); -unsigned long iwl_mvm_get_used_hw_queues(struct iwl_mvm *mvm, - struct ieee80211_vif *exclude_vif); void iwl_mvm_probe_resp_data_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb); void iwl_mvm_channel_switch_noa_notif(struct iwl_mvm *mvm, @@ -1870,17 +1946,43 @@ static inline bool iwl_mvm_vif_low_latency(struct iwl_mvm_vif *mvmvif) * binding, so this has no real impact. For now, just return * the current desired low-latency state. */ - return mvmvif->low_latency; + return mvmvif->low_latency_actual; } static inline void iwl_mvm_vif_set_low_latency(struct iwl_mvm_vif *mvmvif, bool set, enum iwl_mvm_low_latency_cause cause) { + u8 new_state; + if (set) mvmvif->low_latency |= cause; else mvmvif->low_latency &= ~cause; + + /* + * if LOW_LATENCY_DEBUGFS_FORCE_ENABLE is enabled no changes are + * allowed to actual mode. + */ + if (mvmvif->low_latency & LOW_LATENCY_DEBUGFS_FORCE_ENABLE && + cause != LOW_LATENCY_DEBUGFS_FORCE_ENABLE) + return; + + if (cause == LOW_LATENCY_DEBUGFS_FORCE_ENABLE && set) + /* + * We enter force state + */ + new_state = !!(mvmvif->low_latency & + LOW_LATENCY_DEBUGFS_FORCE); + else + /* + * Check if any other one set low latency + */ + new_state = !!(mvmvif->low_latency & + ~(LOW_LATENCY_DEBUGFS_FORCE_ENABLE | + LOW_LATENCY_DEBUGFS_FORCE)); + + mvmvif->low_latency_actual = new_state; } /* Return a bitmask with all the hw supported queues, except for the @@ -1895,6 +1997,16 @@ static inline u32 iwl_mvm_flushable_queues(struct iwl_mvm *mvm) static inline void iwl_mvm_stop_device(struct iwl_mvm *mvm) { lockdep_assert_held(&mvm->mutex); + /* If IWL_MVM_STATUS_HW_RESTART_REQUESTED bit is set then we received + * an assert. Since we failed to bring the interface up, mac80211 + * will not attempt to reconfig the device, + * which handles the dump collection in assert flow, + * so trigger dump collection here. + */ + if (test_and_clear_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED, + &mvm->status)) + iwl_fw_dbg_collect_desc(&mvm->fwrt, &iwl_dump_desc_assert, + false, 0); /* calling this function without using dump_start/end since at this * point we already hold the op mode mutex */ @@ -1906,10 +2018,6 @@ static inline void iwl_mvm_stop_device(struct iwl_mvm *mvm) iwl_trans_stop_device(mvm->trans); } -/* Stop/start all mac queues in a given bitmap */ -void iwl_mvm_start_mac_queues(struct iwl_mvm *mvm, unsigned long mq); -void iwl_mvm_stop_mac_queues(struct iwl_mvm *mvm, unsigned long mq); - /* Re-configure the SCD for a queue that has already been configured */ int iwl_mvm_reconfig_scd(struct iwl_mvm *mvm, int queue, int fifo, int sta_id, int tid, int frame_limit, u16 ssn); @@ -2015,4 +2123,59 @@ void iwl_mvm_sta_add_debugfs(struct ieee80211_hw *hw, struct dentry *dir); #endif +/* Channel info utils */ +static inline bool iwl_mvm_has_ultra_hb_channel(struct iwl_mvm *mvm) +{ + return fw_has_capa(&mvm->fw->ucode_capa, + IWL_UCODE_TLV_CAPA_ULTRA_HB_CHANNELS); +} + +static inline void *iwl_mvm_chan_info_cmd_tail(struct iwl_mvm *mvm, + struct iwl_fw_channel_info *ci) +{ + return (u8 *)ci + (iwl_mvm_has_ultra_hb_channel(mvm) ? + sizeof(struct iwl_fw_channel_info) : + sizeof(struct iwl_fw_channel_info_v1)); +} + +static inline size_t iwl_mvm_chan_info_padding(struct iwl_mvm *mvm) +{ + return iwl_mvm_has_ultra_hb_channel(mvm) ? 0 : + sizeof(struct iwl_fw_channel_info) - + sizeof(struct iwl_fw_channel_info_v1); +} + +static inline void iwl_mvm_set_chan_info(struct iwl_mvm *mvm, + struct iwl_fw_channel_info *ci, + u32 chan, u8 band, u8 width, + u8 ctrl_pos) +{ + if (iwl_mvm_has_ultra_hb_channel(mvm)) { + ci->channel = cpu_to_le32(chan); + ci->band = band; + ci->width = width; + ci->ctrl_pos = ctrl_pos; + } else { + struct iwl_fw_channel_info_v1 *ci_v1 = + (struct iwl_fw_channel_info_v1 *)ci; + + ci_v1->channel = chan; + ci_v1->band = band; + ci_v1->width = width; + ci_v1->ctrl_pos = ctrl_pos; + } +} + +static inline void +iwl_mvm_set_chan_info_chandef(struct iwl_mvm *mvm, + struct iwl_fw_channel_info *ci, + struct cfg80211_chan_def *chandef) +{ + iwl_mvm_set_chan_info(mvm, ci, chandef->chan->hw_value, + (chandef->chan->band == NL80211_BAND_2GHZ ? + PHY_BAND_24 : PHY_BAND_5), + iwl_mvm_get_channel_width(chandef), + iwl_mvm_get_ctrl_pos(chandef)); +} + #endif /* __IWL_MVM_H__ */ diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c index 6fc5cc1f2b5b..7bdbd010ae6b 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/nvm.c @@ -179,7 +179,7 @@ static int iwl_nvm_read_chunk(struct iwl_mvm *mvm, u16 section, IWL_DEBUG_EEPROM(mvm->trans->dev, "NVM access command failed with status %d (device: %s)\n", ret, mvm->cfg->name); - ret = -EIO; + ret = -ENODATA; } goto exit; } @@ -380,8 +380,12 @@ int iwl_nvm_init(struct iwl_mvm *mvm) /* we override the constness for initial read */ ret = iwl_nvm_read_section(mvm, section, nvm_buffer, size_read); - if (ret < 0) + if (ret == -ENODATA) { + ret = 0; continue; + } + if (ret < 0) + break; size_read += ret; temp = kmemdup(nvm_buffer, ret, GFP_KERNEL); if (!temp) { @@ -412,6 +416,11 @@ int iwl_nvm_init(struct iwl_mvm *mvm) mvm->nvm_phy_sku_blob.data = temp; mvm->nvm_phy_sku_blob.size = ret; break; + case NVM_SECTION_TYPE_REGULATORY_SDP: + case NVM_SECTION_TYPE_REGULATORY: + mvm->nvm_reg_blob.data = temp; + mvm->nvm_reg_blob.size = ret; + break; default: if (section == mvm->cfg->nvm_hw_section_num) { mvm->nvm_hw_blob.data = temp; @@ -454,7 +463,7 @@ int iwl_nvm_init(struct iwl_mvm *mvm) IWL_DEBUG_EEPROM(mvm->trans->dev, "nvm version = %x\n", mvm->nvm_data->nvm_version); - return 0; + return ret < 0 ? ret : 0; } struct iwl_mcc_update_resp * diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c index 30c5127034a0..5e4f8b767d10 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c @@ -301,8 +301,6 @@ static const struct iwl_rx_handlers iwl_mvm_rx_handlers[] = { RX_HANDLER_ASYNC_LOCKED), RX_HANDLER(MFUART_LOAD_NOTIFICATION, iwl_mvm_rx_mfuart_notif, RX_HANDLER_SYNC), - RX_HANDLER(TOF_NOTIFICATION, iwl_mvm_tof_resp_handler, - RX_HANDLER_ASYNC_LOCKED), RX_HANDLER_GRP(DEBUG_GROUP, MFU_ASSERT_DUMP_NTF, iwl_mvm_mfu_assert_dump_notif, RX_HANDLER_SYNC), RX_HANDLER_GRP(PROT_OFFLOAD_GROUP, STORED_BEACON_NTF, @@ -329,8 +327,6 @@ static const struct iwl_hcmd_names iwl_mvm_legacy_names[] = { HCMD_NAME(SCAN_REQ_UMAC), HCMD_NAME(SCAN_ABORT_UMAC), HCMD_NAME(SCAN_COMPLETE_UMAC), - HCMD_NAME(TOF_CMD), - HCMD_NAME(TOF_NOTIFICATION), HCMD_NAME(BA_WINDOW_STATUS_NOTIFICATION_ID), HCMD_NAME(ADD_STA_KEY), HCMD_NAME(ADD_STA), @@ -449,6 +445,7 @@ static const struct iwl_hcmd_names iwl_mvm_data_path_names[] = { HCMD_NAME(TRIGGER_RX_QUEUES_NOTIF_CMD), HCMD_NAME(STA_HE_CTXT_CMD), HCMD_NAME(RFH_QUEUE_CONFIG_CMD), + HCMD_NAME(CHEST_COLLECTOR_FILTER_CONFIG_CMD), HCMD_NAME(STA_PM_NOTIF), HCMD_NAME(MU_GROUP_MGMT_NOTIF), HCMD_NAME(RX_QUEUES_NOTIFICATION), @@ -464,6 +461,22 @@ static const struct iwl_hcmd_names iwl_mvm_debug_names[] = { /* Please keep this array *SORTED* by hex value. * Access is done through binary search */ +static const struct iwl_hcmd_names iwl_mvm_location_names[] = { + HCMD_NAME(TOF_RANGE_REQ_CMD), + HCMD_NAME(TOF_CONFIG_CMD), + HCMD_NAME(TOF_RANGE_ABORT_CMD), + HCMD_NAME(TOF_RANGE_REQ_EXT_CMD), + HCMD_NAME(TOF_RESPONDER_CONFIG_CMD), + HCMD_NAME(TOF_RESPONDER_DYN_CONFIG_CMD), + HCMD_NAME(TOF_LC_NOTIF), + HCMD_NAME(TOF_RESPONDER_STATS), + HCMD_NAME(TOF_MCSI_DEBUG_NOTIF), + HCMD_NAME(TOF_RANGE_RESPONSE_NOTIF), +}; + +/* Please keep this array *SORTED* by hex value. + * Access is done through binary search + */ static const struct iwl_hcmd_names iwl_mvm_prot_offload_names[] = { HCMD_NAME(STORED_BEACON_NTF), }; @@ -483,6 +496,7 @@ static const struct iwl_hcmd_arr iwl_mvm_groups[] = { [MAC_CONF_GROUP] = HCMD_ARR(iwl_mvm_mac_conf_names), [PHY_OPS_GROUP] = HCMD_ARR(iwl_mvm_phy_names), [DATA_PATH_GROUP] = HCMD_ARR(iwl_mvm_data_path_names), + [LOCATION_GROUP] = HCMD_ARR(iwl_mvm_location_names), [PROT_OFFLOAD_GROUP] = HCMD_ARR(iwl_mvm_prot_offload_names), [REGULATORY_AND_NVM_GROUP] = HCMD_ARR(iwl_mvm_regulatory_and_nvm_names), @@ -685,6 +699,7 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg, INIT_DELAYED_WORK(&mvm->tdls_cs.dwork, iwl_mvm_tdls_ch_switch_work); INIT_DELAYED_WORK(&mvm->scan_timeout_dwork, iwl_mvm_scan_timeout_wk); INIT_WORK(&mvm->add_stream_wk, iwl_mvm_add_new_dqa_stream_wk); + INIT_LIST_HEAD(&mvm->add_stream_txqs); spin_lock_init(&mvm->d0i3_tx_lock); spin_lock_init(&mvm->refs_lock); @@ -736,6 +751,9 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg, trans_cfg.rx_buf_size = rb_size_default; } + BUILD_BUG_ON(sizeof(struct iwl_ldbg_config_cmd) != + LDBG_CFG_COMMAND_SIZE); + trans->wide_cmd_header = true; trans_cfg.bc_table_dword = mvm->trans->cfg->device_family < IWL_DEVICE_FAMILY_22560; @@ -842,8 +860,6 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg, if (iwl_mvm_is_d0i3_supported(mvm)) iwl_trans_unref(mvm->trans); - iwl_mvm_tof_init(mvm); - iwl_mvm_toggle_tx_ant(mvm, &mvm->mgmt_last_antenna_idx); return op_mode; @@ -909,8 +925,6 @@ static void iwl_op_mode_mvm_stop(struct iwl_op_mode *op_mode) cancel_delayed_work_sync(&mvm->tcm.work); - iwl_mvm_tof_clean(mvm); - iwl_fw_runtime_free(&mvm->fwrt); mutex_destroy(&mvm->mutex); mutex_destroy(&mvm->d0i3_suspend_mutex); @@ -1079,24 +1093,6 @@ static void iwl_mvm_rx_mq(struct iwl_op_mode *op_mode, iwl_mvm_rx_common(mvm, rxb, pkt); } -void iwl_mvm_stop_mac_queues(struct iwl_mvm *mvm, unsigned long mq) -{ - int q; - - if (WARN_ON_ONCE(!mq)) - return; - - for_each_set_bit(q, &mq, IEEE80211_MAX_QUEUES) { - if (atomic_inc_return(&mvm->mac80211_queue_stop_count[q]) > 1) { - IWL_DEBUG_TX_QUEUES(mvm, - "mac80211 %d already stopped\n", q); - continue; - } - - ieee80211_stop_queue(mvm->hw, q); - } -} - static void iwl_mvm_async_cb(struct iwl_op_mode *op_mode, const struct iwl_device_cmd *cmd) { @@ -1109,38 +1105,66 @@ static void iwl_mvm_async_cb(struct iwl_op_mode *op_mode, iwl_trans_block_txq_ptrs(mvm->trans, false); } -static void iwl_mvm_stop_sw_queue(struct iwl_op_mode *op_mode, int hw_queue) +static void iwl_mvm_queue_state_change(struct iwl_op_mode *op_mode, + int hw_queue, bool start) { struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode); - unsigned long mq = mvm->hw_queue_to_mac80211[hw_queue]; + struct ieee80211_sta *sta; + struct ieee80211_txq *txq; + struct iwl_mvm_txq *mvmtxq; + int i; + unsigned long tid_bitmap; + struct iwl_mvm_sta *mvmsta; + u8 sta_id; - iwl_mvm_stop_mac_queues(mvm, mq); -} + sta_id = iwl_mvm_has_new_tx_api(mvm) ? + mvm->tvqm_info[hw_queue].sta_id : + mvm->queue_info[hw_queue].ra_sta_id; -void iwl_mvm_start_mac_queues(struct iwl_mvm *mvm, unsigned long mq) -{ - int q; - - if (WARN_ON_ONCE(!mq)) + if (WARN_ON_ONCE(sta_id >= ARRAY_SIZE(mvm->fw_id_to_mac_id))) return; - for_each_set_bit(q, &mq, IEEE80211_MAX_QUEUES) { - if (atomic_dec_return(&mvm->mac80211_queue_stop_count[q]) > 0) { - IWL_DEBUG_TX_QUEUES(mvm, - "mac80211 %d still stopped\n", q); - continue; - } + rcu_read_lock(); + + sta = rcu_dereference(mvm->fw_id_to_mac_id[sta_id]); + if (IS_ERR_OR_NULL(sta)) + goto out; + mvmsta = iwl_mvm_sta_from_mac80211(sta); - ieee80211_wake_queue(mvm->hw, q); + if (iwl_mvm_has_new_tx_api(mvm)) { + int tid = mvm->tvqm_info[hw_queue].txq_tid; + + tid_bitmap = BIT(tid); + } else { + tid_bitmap = mvm->queue_info[hw_queue].tid_bitmap; } + + for_each_set_bit(i, &tid_bitmap, IWL_MAX_TID_COUNT + 1) { + int tid = i; + + if (tid == IWL_MAX_TID_COUNT) + tid = IEEE80211_NUM_TIDS; + + txq = sta->txq[tid]; + mvmtxq = iwl_mvm_txq_from_mac80211(txq); + mvmtxq->stopped = !start; + + if (start && mvmsta->sta_state != IEEE80211_STA_NOTEXIST) + iwl_mvm_mac_itxq_xmit(mvm->hw, txq); + } + +out: + rcu_read_unlock(); } -static void iwl_mvm_wake_sw_queue(struct iwl_op_mode *op_mode, int hw_queue) +static void iwl_mvm_stop_sw_queue(struct iwl_op_mode *op_mode, int hw_queue) { - struct iwl_mvm *mvm = IWL_OP_MODE_GET_MVM(op_mode); - unsigned long mq = mvm->hw_queue_to_mac80211[hw_queue]; + iwl_mvm_queue_state_change(op_mode, hw_queue, false); +} - iwl_mvm_start_mac_queues(mvm, mq); +static void iwl_mvm_wake_sw_queue(struct iwl_op_mode *op_mode, int hw_queue) +{ + iwl_mvm_queue_state_change(op_mode, hw_queue, true); } static void iwl_mvm_set_rfkill_state(struct iwl_mvm *mvm) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c index 7f5434b34d0d..f369173db11c 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c @@ -143,14 +143,11 @@ static void iwl_mvm_phy_ctxt_cmd_data(struct iwl_mvm *mvm, u8 chains_static, u8 chains_dynamic) { u8 active_cnt, idle_cnt; + struct iwl_phy_context_cmd_tail *tail = + iwl_mvm_chan_info_cmd_tail(mvm, &cmd->ci); /* Set the channel info data */ - cmd->ci.band = (chandef->chan->band == NL80211_BAND_2GHZ ? - PHY_BAND_24 : PHY_BAND_5); - - cmd->ci.channel = chandef->chan->hw_value; - cmd->ci.width = iwl_mvm_get_channel_width(chandef); - cmd->ci.ctrl_pos = iwl_mvm_get_ctrl_pos(chandef); + iwl_mvm_set_chan_info_chandef(mvm, &cmd->ci, chandef); /* Set rx the chains */ idle_cnt = chains_static; @@ -168,17 +165,17 @@ static void iwl_mvm_phy_ctxt_cmd_data(struct iwl_mvm *mvm, active_cnt = 2; } - cmd->rxchain_info = cpu_to_le32(iwl_mvm_get_valid_rx_ant(mvm) << + tail->rxchain_info = cpu_to_le32(iwl_mvm_get_valid_rx_ant(mvm) << PHY_RX_CHAIN_VALID_POS); - cmd->rxchain_info |= cpu_to_le32(idle_cnt << PHY_RX_CHAIN_CNT_POS); - cmd->rxchain_info |= cpu_to_le32(active_cnt << + tail->rxchain_info |= cpu_to_le32(idle_cnt << PHY_RX_CHAIN_CNT_POS); + tail->rxchain_info |= cpu_to_le32(active_cnt << PHY_RX_CHAIN_MIMO_CNT_POS); #ifdef CONFIG_IWLWIFI_DEBUGFS if (unlikely(mvm->dbgfs_rx_phyinfo)) - cmd->rxchain_info = cpu_to_le32(mvm->dbgfs_rx_phyinfo); + tail->rxchain_info = cpu_to_le32(mvm->dbgfs_rx_phyinfo); #endif - cmd->txchain_info = cpu_to_le32(iwl_mvm_get_valid_tx_ant(mvm)); + tail->txchain_info = cpu_to_le32(iwl_mvm_get_valid_tx_ant(mvm)); } /* @@ -195,6 +192,7 @@ static int iwl_mvm_phy_ctxt_apply(struct iwl_mvm *mvm, { struct iwl_phy_context_cmd cmd; int ret; + u16 len = sizeof(cmd) - iwl_mvm_chan_info_padding(mvm); /* Set the command header fields */ iwl_mvm_phy_ctxt_cmd_hdr(ctxt, &cmd, action, apply_time); @@ -203,9 +201,7 @@ static int iwl_mvm_phy_ctxt_apply(struct iwl_mvm *mvm, iwl_mvm_phy_ctxt_cmd_data(mvm, &cmd, chandef, chains_static, chains_dynamic); - ret = iwl_mvm_send_cmd_pdu(mvm, PHY_CONTEXT_CMD, 0, - sizeof(struct iwl_phy_context_cmd), - &cmd); + ret = iwl_mvm_send_cmd_pdu(mvm, PHY_CONTEXT_CMD, 0, len, &cmd); if (ret) IWL_ERR(mvm, "PHY ctxt cmd error. ret=%d\n", ret); return ret; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c index dabbc04853ac..a28283ff7295 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c @@ -149,14 +149,9 @@ static u16 rs_fw_set_config_flags(struct iwl_mvm *mvm, if (he_cap && he_cap->has_he && (he_cap->he_cap_elem.phy_cap_info[3] & - IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_MASK)) { + IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_MASK)) flags |= IWL_TLC_MNG_CFG_FLAGS_HE_DCM_NSS_1_MSK; - if (he_cap->he_cap_elem.phy_cap_info[3] & - IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_2) - flags |= IWL_TLC_MNG_CFG_FLAGS_HE_DCM_NSS_2_MSK; - } - return flags; } @@ -320,12 +315,26 @@ void iwl_mvm_tlc_update_notif(struct iwl_mvm *mvm, if (flags & IWL_TLC_NOTIF_FLAG_AMSDU) { u16 size = le32_to_cpu(notif->amsdu_size); + int i; if (WARN_ON(sta->max_amsdu_len < size)) goto out; mvmsta->amsdu_enabled = le32_to_cpu(notif->amsdu_enabled); mvmsta->max_amsdu_len = size; + sta->max_rc_amsdu_len = mvmsta->max_amsdu_len; + + for (i = 0; i < IWL_MAX_TID_COUNT; i++) { + if (mvmsta->amsdu_enabled & BIT(i)) + sta->max_tid_amsdu_len[i] = + iwl_mvm_max_amsdu_size(mvm, sta, i); + else + /* + * Not so elegant, but this will effectively + * prevent AMSDU on this TID + */ + sta->max_tid_amsdu_len[i] = 1; + } IWL_DEBUG_RATE(mvm, "AMSDU update. AMSDU size: %d, AMSDU selected size: %d, AMSDU TID bitmap 0x%X\n", diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c index 089972280daa..09866f50857a 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c @@ -1744,6 +1744,7 @@ static void rs_set_amsdu_len(struct iwl_mvm *mvm, struct ieee80211_sta *sta, enum rs_action scale_action) { struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); + int i; /* * In case TLC offload is not active amsdu_enabled is either 0xFFFF @@ -1757,6 +1758,19 @@ static void rs_set_amsdu_len(struct iwl_mvm *mvm, struct ieee80211_sta *sta, mvmsta->amsdu_enabled = 0xFFFF; mvmsta->max_amsdu_len = sta->max_amsdu_len; + sta->max_rc_amsdu_len = mvmsta->max_amsdu_len; + + for (i = 0; i < IWL_MAX_TID_COUNT; i++) { + if (mvmsta->amsdu_enabled) + sta->max_tid_amsdu_len[i] = + iwl_mvm_max_amsdu_size(mvm, sta, i); + else + /* + * Not so elegant, but this will effectively + * prevent AMSDU on this TID + */ + sta->max_tid_amsdu_len[i] = 1; + } } /* @@ -3332,12 +3346,12 @@ static void rs_fill_rates_for_column(struct iwl_mvm *mvm, /* Building the rate table is non trivial. When we're in MIMO2/VHT/80Mhz/SGI * column the rate table should look like this: * - * rate[0] 0x400D019 VHT | ANT: AB BW: 80Mhz MCS: 9 NSS: 2 SGI - * rate[1] 0x400D019 VHT | ANT: AB BW: 80Mhz MCS: 9 NSS: 2 SGI - * rate[2] 0x400D018 VHT | ANT: AB BW: 80Mhz MCS: 8 NSS: 2 SGI - * rate[3] 0x400D018 VHT | ANT: AB BW: 80Mhz MCS: 8 NSS: 2 SGI - * rate[4] 0x400D017 VHT | ANT: AB BW: 80Mhz MCS: 7 NSS: 2 SGI - * rate[5] 0x400D017 VHT | ANT: AB BW: 80Mhz MCS: 7 NSS: 2 SGI + * rate[0] 0x400F019 VHT | ANT: AB BW: 80Mhz MCS: 9 NSS: 2 SGI + * rate[1] 0x400F019 VHT | ANT: AB BW: 80Mhz MCS: 9 NSS: 2 SGI + * rate[2] 0x400F018 VHT | ANT: AB BW: 80Mhz MCS: 8 NSS: 2 SGI + * rate[3] 0x400F018 VHT | ANT: AB BW: 80Mhz MCS: 8 NSS: 2 SGI + * rate[4] 0x400F017 VHT | ANT: AB BW: 80Mhz MCS: 7 NSS: 2 SGI + * rate[5] 0x400F017 VHT | ANT: AB BW: 80Mhz MCS: 7 NSS: 2 SGI * rate[6] 0x4005007 VHT | ANT: A BW: 80Mhz MCS: 7 NSS: 1 NGI * rate[7] 0x4009006 VHT | ANT: B BW: 80Mhz MCS: 6 NSS: 1 NGI * rate[8] 0x4005005 VHT | ANT: A BW: 80Mhz MCS: 5 NSS: 1 NGI diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c index 6653a238f32e..235ab26ca429 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c @@ -599,8 +599,8 @@ static void iwl_mvm_stat_iterator(void *_data, u8 *mac, * data copied into the "data" struct, but rather the data from * the notification directly. */ - if (iwl_mvm_is_cdb_supported(mvm)) { - struct mvm_statistics_general_cdb *general = + if (iwl_mvm_has_new_rx_stats_api(mvm)) { + struct mvm_statistics_general *general = data->general; mvmvif->beacon_stats.num_beacons = @@ -723,7 +723,7 @@ void iwl_mvm_handle_rx_statistics(struct iwl_mvm *mvm, else expected_size = sizeof(struct iwl_notif_statistics_v10); } else { - expected_size = sizeof(struct iwl_notif_statistics_cdb); + expected_size = sizeof(struct iwl_notif_statistics); } if (WARN_ONCE(iwl_rx_packet_payload_len(pkt) != expected_size, @@ -753,7 +753,7 @@ void iwl_mvm_handle_rx_statistics(struct iwl_mvm *mvm, flags = stats->flag; } else { - struct iwl_notif_statistics_cdb *stats = (void *)&pkt->data; + struct iwl_notif_statistics *stats = (void *)&pkt->data; data.mac_id = stats->rx.general.mac_id; data.beacon_filter_average_energy = @@ -792,7 +792,7 @@ void iwl_mvm_handle_rx_statistics(struct iwl_mvm *mvm, bytes = (void *)&v11->load_stats.byte_count; air_time = (void *)&v11->load_stats.air_time; } else { - struct iwl_notif_statistics_cdb *stats = (void *)&pkt->data; + struct iwl_notif_statistics *stats = (void *)&pkt->data; energy = (void *)&stats->load_stats.avg_energy; bytes = (void *)&stats->load_stats.byte_count; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c index 7bd8676508f5..2c56f73d688e 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c @@ -192,27 +192,48 @@ static void iwl_mvm_create_skb(struct sk_buff *skb, struct ieee80211_hdr *hdr, } } +static void iwl_mvm_add_rtap_sniffer_config(struct iwl_mvm *mvm, + struct sk_buff *skb) +{ + struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb); + struct ieee80211_vendor_radiotap *radiotap; + int size = sizeof(*radiotap) + sizeof(__le16); + + if (!mvm->cur_aid) + return; + + radiotap = skb_put(skb, size); + radiotap->align = 1; + /* Intel OUI */ + radiotap->oui[0] = 0xf6; + radiotap->oui[1] = 0x54; + radiotap->oui[2] = 0x25; + /* radiotap sniffer config sub-namespace */ + radiotap->subns = 1; + radiotap->present = 0x1; + radiotap->len = size - sizeof(*radiotap); + radiotap->pad = 0; + + /* fill the data now */ + memcpy(radiotap->data, &mvm->cur_aid, sizeof(mvm->cur_aid)); + + rx_status->flag |= RX_FLAG_RADIOTAP_VENDOR_DATA; +} + /* iwl_mvm_pass_packet_to_mac80211 - passes the packet for mac80211 */ static void iwl_mvm_pass_packet_to_mac80211(struct iwl_mvm *mvm, struct napi_struct *napi, struct sk_buff *skb, int queue, - struct ieee80211_sta *sta) + struct ieee80211_sta *sta, + bool csi) { struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb); if (!(rx_status->flag & RX_FLAG_NO_PSDU) && - iwl_mvm_check_pn(mvm, skb, queue, sta)) { + iwl_mvm_check_pn(mvm, skb, queue, sta)) kfree_skb(skb); - } else { - unsigned int radiotap_len = 0; - - if (rx_status->flag & RX_FLAG_RADIOTAP_HE) - radiotap_len += sizeof(struct ieee80211_radiotap_he); - if (rx_status->flag & RX_FLAG_RADIOTAP_HE_MU) - radiotap_len += sizeof(struct ieee80211_radiotap_he_mu); - __skb_push(skb, radiotap_len); + else ieee80211_rx_napi(mvm->hw, sta, skb, napi); - } } static void iwl_mvm_get_signal_strength(struct iwl_mvm *mvm, @@ -473,7 +494,7 @@ static void iwl_mvm_release_frames(struct iwl_mvm *mvm, while ((skb = __skb_dequeue(skb_list))) { iwl_mvm_pass_packet_to_mac80211(mvm, napi, skb, reorder_buf->queue, - sta); + sta, false); reorder_buf->num_stored--; } } @@ -666,6 +687,8 @@ static bool iwl_mvm_reorder(struct iwl_mvm *mvm, * This also covers the case of receiving a Block Ack Request * outside a BA session; we'll pass it to mac80211 and that * then sends a delBA action frame. + * This also covers pure monitor mode, in which case we won't + * have any BA sessions. */ if (baid == IWL_RX_REORDER_DATA_INVALID_BAID) return false; @@ -1158,14 +1181,12 @@ static void iwl_mvm_rx_he(struct iwl_mvm *mvm, struct sk_buff *skb, /* temporarily hide the radiotap data */ __skb_pull(skb, radiotap_len); - if (phy_data->info_type == IWL_RX_PHY_INFO_TYPE_HE_SU) { - /* report the AMPDU-EOF bit on single frames */ - if (!queue && !(phy_info & IWL_RX_MPDU_PHY_AMPDU)) { - rx_status->flag |= RX_FLAG_AMPDU_DETAILS; - rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT_KNOWN; - if (phy_data->d0 & cpu_to_le32(IWL_RX_PHY_DATA0_HE_DELIM_EOF)) - rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT; - } + /* report the AMPDU-EOF bit on single frames */ + if (!queue && !(phy_info & IWL_RX_MPDU_PHY_AMPDU)) { + rx_status->flag |= RX_FLAG_AMPDU_DETAILS; + rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT_KNOWN; + if (phy_data->d0 & cpu_to_le32(IWL_RX_PHY_DATA0_HE_DELIM_EOF)) + rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT; } if (phy_info & IWL_RX_MPDU_PHY_TSF_OVERLOAD) @@ -1178,9 +1199,7 @@ static void iwl_mvm_rx_he(struct iwl_mvm *mvm, struct sk_buff *skb, bool toggle_bit = phy_info & IWL_RX_MPDU_PHY_AMPDU_TOGGLE; /* toggle is switched whenever new aggregation starts */ - if (toggle_bit != mvm->ampdu_toggle && - (he_type == RATE_MCS_HE_TYPE_MU || - he_type == RATE_MCS_HE_TYPE_SU)) { + if (toggle_bit != mvm->ampdu_toggle) { rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT_KNOWN; if (phy_data->d0 & cpu_to_le32(IWL_RX_PHY_DATA0_HE_DELIM_EOF)) rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT; @@ -1314,6 +1333,7 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi, .d4 = desc->phy_data4, .info_type = IWL_RX_PHY_INFO_TYPE_NONE, }; + bool csi = false; if (unlikely(test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status))) return; @@ -1412,7 +1432,8 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi, rx_status->flag |= RX_FLAG_FAILED_FCS_CRC; } /* set the preamble flag if appropriate */ - if (phy_info & IWL_RX_MPDU_PHY_SHORT_PREAMBLE) + if (rate_n_flags & RATE_MCS_CCK_MSK && + phy_info & IWL_RX_MPDU_PHY_SHORT_PREAMBLE) rx_status->enc_flags |= RX_ENC_FLAG_SHORTPRE; if (likely(!(phy_info & IWL_RX_MPDU_PHY_TSF_OVERLOAD))) { @@ -1441,14 +1462,23 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi, bool toggle_bit = phy_info & IWL_RX_MPDU_PHY_AMPDU_TOGGLE; rx_status->flag |= RX_FLAG_AMPDU_DETAILS; - rx_status->ampdu_reference = mvm->ampdu_ref; - /* toggle is switched whenever new aggregation starts */ + /* + * Toggle is switched whenever new aggregation starts. Make + * sure ampdu_reference is never 0 so we can later use it to + * see if the frame was really part of an A-MPDU or not. + */ if (toggle_bit != mvm->ampdu_toggle) { mvm->ampdu_ref++; + if (mvm->ampdu_ref == 0) + mvm->ampdu_ref++; mvm->ampdu_toggle = toggle_bit; } + rx_status->ampdu_reference = mvm->ampdu_ref; } + if (unlikely(mvm->monitor_on)) + iwl_mvm_add_rtap_sniffer_config(mvm, skb); + rcu_read_lock(); if (desc->status & cpu_to_le16(IWL_RX_MPDU_STATUS_SRC_STA_FOUND)) { @@ -1602,7 +1632,8 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi, iwl_mvm_create_skb(skb, hdr, len, crypt_len, rxb); if (!iwl_mvm_reorder(mvm, napi, queue, sta, skb, desc)) - iwl_mvm_pass_packet_to_mac80211(mvm, napi, skb, queue, sta); + iwl_mvm_pass_packet_to_mac80211(mvm, napi, skb, queue, + sta, csi); out: rcu_read_unlock(); } @@ -1705,15 +1736,24 @@ void iwl_mvm_rx_monitor_ndp(struct iwl_mvm *mvm, struct napi_struct *napi, } else if (rate_n_flags & RATE_MCS_VHT_MSK) { u8 stbc = (rate_n_flags & RATE_MCS_STBC_MSK) >> RATE_MCS_STBC_POS; - rx_status->nss = - ((rate_n_flags & RATE_VHT_MCS_NSS_MSK) >> - RATE_VHT_MCS_NSS_POS) + 1; rx_status->rate_idx = rate_n_flags & RATE_VHT_MCS_RATE_CODE_MSK; rx_status->encoding = RX_ENC_VHT; rx_status->enc_flags |= stbc << RX_ENC_FLAG_STBC_SHIFT; if (rate_n_flags & RATE_MCS_BF_MSK) rx_status->enc_flags |= RX_ENC_FLAG_BF; - } else if (!(rate_n_flags & RATE_MCS_HE_MSK)) { + /* + * take the nss from the rx_vec since the rate_n_flags has + * only 2 bits for the nss which gives a max of 4 ss but + * there may be up to 8 spatial streams + */ + rx_status->nss = + le32_get_bits(desc->rx_vec[0], + RX_NO_DATA_RX_VEC0_VHT_NSTS_MSK) + 1; + } else if (rate_n_flags & RATE_MCS_HE_MSK) { + rx_status->nss = + le32_get_bits(desc->rx_vec[0], + RX_NO_DATA_RX_VEC0_HE_NSTS_MSK) + 1; + } else { int rate = iwl_mvm_legacy_rate_to_mac80211_idx(rate_n_flags, rx_status->band); @@ -1726,7 +1766,7 @@ void iwl_mvm_rx_monitor_ndp(struct iwl_mvm *mvm, struct napi_struct *napi, rx_status->rate_idx = rate; } - iwl_mvm_pass_packet_to_mac80211(mvm, napi, skb, queue, sta); + iwl_mvm_pass_packet_to_mac80211(mvm, napi, skb, queue, sta, false); out: rcu_read_unlock(); } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sf.c b/drivers/net/wireless/intel/iwlwifi/mvm/sf.c index d1d76bb9a750..9da0dae78510 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sf.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sf.c @@ -7,6 +7,7 @@ * * Copyright(c) 2013 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH + * Copyright (C) 2018 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -28,6 +29,7 @@ * * Copyright(c) 2013 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH + * Copyright (C) 2018 Intel Corporation * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -64,7 +66,7 @@ struct iwl_mvm_active_iface_iterator_data { struct ieee80211_vif *ignore_vif; u8 sta_vif_ap_sta_id; enum iwl_sf_state sta_vif_state; - int num_active_macs; + u32 num_active_macs; }; /* diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c index e28009832da0..c5a01470a3bc 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c @@ -356,24 +356,16 @@ static int iwl_mvm_invalidate_sta_queue(struct iwl_mvm *mvm, int queue, return ret; } -static int iwl_mvm_disable_txq(struct iwl_mvm *mvm, int queue, - int mac80211_queue, u8 tid, u8 flags) +static int iwl_mvm_disable_txq(struct iwl_mvm *mvm, struct ieee80211_sta *sta, + int queue, u8 tid, u8 flags) { struct iwl_scd_txq_cfg_cmd cmd = { .scd_queue = queue, .action = SCD_CFG_DISABLE_QUEUE, }; - bool remove_mac_queue = mac80211_queue != IEEE80211_INVAL_HW_QUEUE; int ret; - if (WARN_ON(remove_mac_queue && mac80211_queue >= IEEE80211_MAX_QUEUES)) - return -EINVAL; - if (iwl_mvm_has_new_tx_api(mvm)) { - if (remove_mac_queue) - mvm->hw_queue_to_mac80211[queue] &= - ~BIT(mac80211_queue); - iwl_trans_txq_free(mvm->trans, queue); return 0; @@ -384,36 +376,15 @@ static int iwl_mvm_disable_txq(struct iwl_mvm *mvm, int queue, mvm->queue_info[queue].tid_bitmap &= ~BIT(tid); - /* - * If there is another TID with the same AC - don't remove the MAC queue - * from the mapping - */ - if (tid < IWL_MAX_TID_COUNT) { - unsigned long tid_bitmap = - mvm->queue_info[queue].tid_bitmap; - int ac = tid_to_mac80211_ac[tid]; - int i; - - for_each_set_bit(i, &tid_bitmap, IWL_MAX_TID_COUNT) { - if (tid_to_mac80211_ac[i] == ac) - remove_mac_queue = false; - } - } - - if (remove_mac_queue) - mvm->hw_queue_to_mac80211[queue] &= - ~BIT(mac80211_queue); - cmd.action = mvm->queue_info[queue].tid_bitmap ? SCD_CFG_ENABLE_QUEUE : SCD_CFG_DISABLE_QUEUE; if (cmd.action == SCD_CFG_DISABLE_QUEUE) mvm->queue_info[queue].status = IWL_MVM_QUEUE_FREE; IWL_DEBUG_TX_QUEUES(mvm, - "Disabling TXQ #%d tids=0x%x (mac80211 map:0x%x)\n", + "Disabling TXQ #%d tids=0x%x\n", queue, - mvm->queue_info[queue].tid_bitmap, - mvm->hw_queue_to_mac80211[queue]); + mvm->queue_info[queue].tid_bitmap); /* If the queue is still enabled - nothing left to do in this func */ if (cmd.action == SCD_CFG_ENABLE_QUEUE) @@ -423,15 +394,19 @@ static int iwl_mvm_disable_txq(struct iwl_mvm *mvm, int queue, cmd.tid = mvm->queue_info[queue].txq_tid; /* Make sure queue info is correct even though we overwrite it */ - WARN(mvm->queue_info[queue].tid_bitmap || - mvm->hw_queue_to_mac80211[queue], - "TXQ #%d info out-of-sync - mac map=0x%x, tids=0x%x\n", - queue, mvm->hw_queue_to_mac80211[queue], - mvm->queue_info[queue].tid_bitmap); + WARN(mvm->queue_info[queue].tid_bitmap, + "TXQ #%d info out-of-sync - tids=0x%x\n", + queue, mvm->queue_info[queue].tid_bitmap); /* If we are here - the queue is freed and we can zero out these vals */ mvm->queue_info[queue].tid_bitmap = 0; - mvm->hw_queue_to_mac80211[queue] = 0; + + if (sta) { + struct iwl_mvm_txq *mvmtxq = + iwl_mvm_txq_from_tid(sta, tid); + + mvmtxq->txq_id = IWL_MVM_INVALID_QUEUE; + } /* Regardless if this is a reserved TXQ for a STA - mark it as false */ mvm->queue_info[queue].reserved = false; @@ -517,9 +492,14 @@ static int iwl_mvm_remove_sta_queue_marking(struct iwl_mvm *mvm, int queue) spin_lock_bh(&mvmsta->lock); /* Unmap MAC queues and TIDs from this queue */ for_each_set_bit(tid, &tid_bitmap, IWL_MAX_TID_COUNT + 1) { + struct iwl_mvm_txq *mvmtxq = + iwl_mvm_txq_from_tid(sta, tid); + if (mvmsta->tid_data[tid].state == IWL_AGG_ON) disable_agg_tids |= BIT(tid); mvmsta->tid_data[tid].txq_id = IWL_MVM_INVALID_QUEUE; + + mvmtxq->txq_id = IWL_MVM_INVALID_QUEUE; } mvmsta->tfd_queue_msk &= ~BIT(queue); /* Don't use this queue anymore */ @@ -541,10 +521,11 @@ static int iwl_mvm_remove_sta_queue_marking(struct iwl_mvm *mvm, int queue) } static int iwl_mvm_free_inactive_queue(struct iwl_mvm *mvm, int queue, + struct ieee80211_sta *old_sta, u8 new_sta_id) { struct iwl_mvm_sta *mvmsta; - u8 txq_curr_ac, sta_id, tid; + u8 sta_id, tid; unsigned long disable_agg_tids = 0; bool same_sta; int ret; @@ -554,7 +535,6 @@ static int iwl_mvm_free_inactive_queue(struct iwl_mvm *mvm, int queue, if (WARN_ON(iwl_mvm_has_new_tx_api(mvm))) return -EINVAL; - txq_curr_ac = mvm->queue_info[queue].mac80211_ac; sta_id = mvm->queue_info[queue].ra_sta_id; tid = mvm->queue_info[queue].txq_tid; @@ -570,9 +550,7 @@ static int iwl_mvm_free_inactive_queue(struct iwl_mvm *mvm, int queue, iwl_mvm_invalidate_sta_queue(mvm, queue, disable_agg_tids, false); - ret = iwl_mvm_disable_txq(mvm, queue, - mvmsta->vif->hw_queue[txq_curr_ac], - tid, 0); + ret = iwl_mvm_disable_txq(mvm, old_sta, queue, tid, 0); if (ret) { IWL_ERR(mvm, "Failed to free inactive queue %d (ret=%d)\n", @@ -662,16 +640,15 @@ static int iwl_mvm_get_shared_queue(struct iwl_mvm *mvm, * in such a case, otherwise - if no redirection required - it does nothing, * unless the %force param is true. */ -static int iwl_mvm_scd_queue_redirect(struct iwl_mvm *mvm, int queue, int tid, - int ac, int ssn, unsigned int wdg_timeout, - bool force) +static int iwl_mvm_redirect_queue(struct iwl_mvm *mvm, int queue, int tid, + int ac, int ssn, unsigned int wdg_timeout, + bool force, struct iwl_mvm_txq *txq) { struct iwl_scd_txq_cfg_cmd cmd = { .scd_queue = queue, .action = SCD_CFG_DISABLE_QUEUE, }; bool shared_queue; - unsigned long mq; int ret; if (WARN_ON(iwl_mvm_has_new_tx_api(mvm))) @@ -695,14 +672,14 @@ static int iwl_mvm_scd_queue_redirect(struct iwl_mvm *mvm, int queue, int tid, cmd.sta_id = mvm->queue_info[queue].ra_sta_id; cmd.tx_fifo = iwl_mvm_ac_to_tx_fifo[mvm->queue_info[queue].mac80211_ac]; cmd.tid = mvm->queue_info[queue].txq_tid; - mq = mvm->hw_queue_to_mac80211[queue]; shared_queue = hweight16(mvm->queue_info[queue].tid_bitmap) > 1; IWL_DEBUG_TX_QUEUES(mvm, "Redirecting TXQ #%d to FIFO #%d\n", queue, iwl_mvm_ac_to_tx_fifo[ac]); - /* Stop MAC queues and wait for this queue to empty */ - iwl_mvm_stop_mac_queues(mvm, mq); + /* Stop the queue and wait for it to empty */ + txq->stopped = true; + ret = iwl_trans_wait_tx_queues_empty(mvm->trans, BIT(queue)); if (ret) { IWL_ERR(mvm, "Error draining queue %d before reconfig\n", @@ -743,8 +720,8 @@ static int iwl_mvm_scd_queue_redirect(struct iwl_mvm *mvm, int queue, int tid, iwl_trans_txq_set_shared_mode(mvm->trans, queue, true); out: - /* Continue using the MAC queues */ - iwl_mvm_start_mac_queues(mvm, mq); + /* Continue using the queue */ + txq->stopped = false; return ret; } @@ -769,7 +746,7 @@ static int iwl_mvm_find_free_queue(struct iwl_mvm *mvm, u8 sta_id, return -ENOSPC; } -static int iwl_mvm_tvqm_enable_txq(struct iwl_mvm *mvm, int mac80211_queue, +static int iwl_mvm_tvqm_enable_txq(struct iwl_mvm *mvm, u8 sta_id, u8 tid, unsigned int timeout) { int queue, size = IWL_DEFAULT_QUEUE_SIZE; @@ -792,10 +769,7 @@ static int iwl_mvm_tvqm_enable_txq(struct iwl_mvm *mvm, int mac80211_queue, IWL_DEBUG_TX_QUEUES(mvm, "Enabling TXQ #%d for sta %d tid %d\n", queue, sta_id, tid); - mvm->hw_queue_to_mac80211[queue] |= BIT(mac80211_queue); - IWL_DEBUG_TX_QUEUES(mvm, - "Enabling TXQ #%d (mac80211 map:0x%x)\n", - queue, mvm->hw_queue_to_mac80211[queue]); + IWL_DEBUG_TX_QUEUES(mvm, "Enabling TXQ #%d\n", queue); return queue; } @@ -805,9 +779,10 @@ static int iwl_mvm_sta_alloc_queue_tvqm(struct iwl_mvm *mvm, int tid) { struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); + struct iwl_mvm_txq *mvmtxq = + iwl_mvm_txq_from_tid(sta, tid); unsigned int wdg_timeout = iwl_mvm_get_wd_timeout(mvm, mvmsta->vif, false, false); - u8 mac_queue = mvmsta->vif->hw_queue[ac]; int queue = -1; lockdep_assert_held(&mvm->mutex); @@ -815,11 +790,16 @@ static int iwl_mvm_sta_alloc_queue_tvqm(struct iwl_mvm *mvm, IWL_DEBUG_TX_QUEUES(mvm, "Allocating queue for sta %d on tid %d\n", mvmsta->sta_id, tid); - queue = iwl_mvm_tvqm_enable_txq(mvm, mac_queue, mvmsta->sta_id, tid, - wdg_timeout); + queue = iwl_mvm_tvqm_enable_txq(mvm, mvmsta->sta_id, tid, wdg_timeout); if (queue < 0) return queue; + if (sta) { + mvmtxq->txq_id = queue; + mvm->tvqm_info[queue].txq_tid = tid; + mvm->tvqm_info[queue].sta_id = mvmsta->sta_id; + } + IWL_DEBUG_TX_QUEUES(mvm, "Allocated queue is %d\n", queue); spin_lock_bh(&mvmsta->lock); @@ -829,8 +809,9 @@ static int iwl_mvm_sta_alloc_queue_tvqm(struct iwl_mvm *mvm, return 0; } -static bool iwl_mvm_update_txq_mapping(struct iwl_mvm *mvm, int queue, - int mac80211_queue, u8 sta_id, u8 tid) +static bool iwl_mvm_update_txq_mapping(struct iwl_mvm *mvm, + struct ieee80211_sta *sta, + int queue, u8 sta_id, u8 tid) { bool enable_queue = true; @@ -845,14 +826,6 @@ static bool iwl_mvm_update_txq_mapping(struct iwl_mvm *mvm, int queue, if (mvm->queue_info[queue].tid_bitmap) enable_queue = false; - if (mac80211_queue != IEEE80211_INVAL_HW_QUEUE) { - WARN(mac80211_queue >= - BITS_PER_BYTE * sizeof(mvm->hw_queue_to_mac80211[0]), - "cannot track mac80211 queue %d (queue %d, sta %d, tid %d)\n", - mac80211_queue, queue, sta_id, tid); - mvm->hw_queue_to_mac80211[queue] |= BIT(mac80211_queue); - } - mvm->queue_info[queue].tid_bitmap |= BIT(tid); mvm->queue_info[queue].ra_sta_id = sta_id; @@ -866,16 +839,22 @@ static bool iwl_mvm_update_txq_mapping(struct iwl_mvm *mvm, int queue, mvm->queue_info[queue].txq_tid = tid; } + if (sta) { + struct iwl_mvm_txq *mvmtxq = + iwl_mvm_txq_from_tid(sta, tid); + + mvmtxq->txq_id = queue; + } + IWL_DEBUG_TX_QUEUES(mvm, - "Enabling TXQ #%d tids=0x%x (mac80211 map:0x%x)\n", - queue, mvm->queue_info[queue].tid_bitmap, - mvm->hw_queue_to_mac80211[queue]); + "Enabling TXQ #%d tids=0x%x\n", + queue, mvm->queue_info[queue].tid_bitmap); return enable_queue; } -static bool iwl_mvm_enable_txq(struct iwl_mvm *mvm, int queue, - int mac80211_queue, u16 ssn, +static bool iwl_mvm_enable_txq(struct iwl_mvm *mvm, struct ieee80211_sta *sta, + int queue, u16 ssn, const struct iwl_trans_txq_scd_cfg *cfg, unsigned int wdg_timeout) { @@ -895,8 +874,7 @@ static bool iwl_mvm_enable_txq(struct iwl_mvm *mvm, int queue, return false; /* Send the enabling command if we need to */ - if (!iwl_mvm_update_txq_mapping(mvm, queue, mac80211_queue, - cfg->sta_id, cfg->tid)) + if (!iwl_mvm_update_txq_mapping(mvm, sta, queue, cfg->sta_id, cfg->tid)) return false; inc_ssn = iwl_trans_txq_enable_cfg(mvm->trans, queue, ssn, @@ -989,9 +967,10 @@ static void iwl_mvm_unshare_queue(struct iwl_mvm *mvm, int queue) ssn = IEEE80211_SEQ_TO_SN(mvmsta->tid_data[tid].seq_number); - ret = iwl_mvm_scd_queue_redirect(mvm, queue, tid, - tid_to_mac80211_ac[tid], ssn, - wdg_timeout, true); + ret = iwl_mvm_redirect_queue(mvm, queue, tid, + tid_to_mac80211_ac[tid], ssn, + wdg_timeout, true, + iwl_mvm_txq_from_tid(sta, tid)); if (ret) { IWL_ERR(mvm, "Failed to redirect TXQ %d\n", queue); return; @@ -1068,11 +1047,9 @@ static bool iwl_mvm_remove_inactive_tids(struct iwl_mvm *mvm, * Remove the ones that did. */ for_each_set_bit(tid, &tid_bitmap, IWL_MAX_TID_COUNT + 1) { - int mac_queue = mvmsta->vif->hw_queue[tid_to_mac80211_ac[tid]]; u16 tid_bitmap; mvmsta->tid_data[tid].txq_id = IWL_MVM_INVALID_QUEUE; - mvm->hw_queue_to_mac80211[queue] &= ~BIT(mac_queue); mvm->queue_info[queue].tid_bitmap &= ~BIT(tid); tid_bitmap = mvm->queue_info[queue].tid_bitmap; @@ -1105,10 +1082,6 @@ static bool iwl_mvm_remove_inactive_tids(struct iwl_mvm *mvm, * sure all TIDs have existing corresponding mac queues enabled */ tid_bitmap = mvm->queue_info[queue].tid_bitmap; - for_each_set_bit(tid, &tid_bitmap, IWL_MAX_TID_COUNT + 1) { - mvm->hw_queue_to_mac80211[queue] |= - BIT(mvmsta->vif->hw_queue[tid_to_mac80211_ac[tid]]); - } /* If the queue is marked as shared - "unshare" it */ if (hweight16(mvm->queue_info[queue].tid_bitmap) == 1 && @@ -1136,6 +1109,7 @@ static int iwl_mvm_inactivity_check(struct iwl_mvm *mvm, u8 alloc_for_sta) unsigned long unshare_queues = 0; unsigned long changetid_queues = 0; int i, ret, free_queue = -ENOSPC; + struct ieee80211_sta *queue_owner = NULL; lockdep_assert_held(&mvm->mutex); @@ -1201,13 +1175,14 @@ static int iwl_mvm_inactivity_check(struct iwl_mvm *mvm, u8 alloc_for_sta) inactive_tid_bitmap, &unshare_queues, &changetid_queues); - if (ret >= 0 && free_queue < 0) + if (ret >= 0 && free_queue < 0) { + queue_owner = sta; free_queue = ret; + } /* only unlock sta lock - we still need the queue info lock */ spin_unlock_bh(&mvmsta->lock); } - rcu_read_unlock(); /* Reconfigure queues requiring reconfiguation */ for_each_set_bit(i, &unshare_queues, IWL_MAX_HW_QUEUES) @@ -1216,18 +1191,21 @@ static int iwl_mvm_inactivity_check(struct iwl_mvm *mvm, u8 alloc_for_sta) iwl_mvm_change_queue_tid(mvm, i); if (free_queue >= 0 && alloc_for_sta != IWL_MVM_INVALID_STA) { - ret = iwl_mvm_free_inactive_queue(mvm, free_queue, + ret = iwl_mvm_free_inactive_queue(mvm, free_queue, queue_owner, alloc_for_sta); - if (ret) + if (ret) { + rcu_read_unlock(); return ret; + } } + rcu_read_unlock(); + return free_queue; } static int iwl_mvm_sta_alloc_queue(struct iwl_mvm *mvm, - struct ieee80211_sta *sta, u8 ac, int tid, - struct ieee80211_hdr *hdr) + struct ieee80211_sta *sta, u8 ac, int tid) { struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); struct iwl_trans_txq_scd_cfg cfg = { @@ -1238,7 +1216,6 @@ static int iwl_mvm_sta_alloc_queue(struct iwl_mvm *mvm, }; unsigned int wdg_timeout = iwl_mvm_get_wd_timeout(mvm, mvmsta->vif, false, false); - u8 mac_queue = mvmsta->vif->hw_queue[ac]; int queue = -1; unsigned long disable_agg_tids = 0; enum iwl_mvm_agg_state queue_state; @@ -1257,12 +1234,7 @@ static int iwl_mvm_sta_alloc_queue(struct iwl_mvm *mvm, ssn = IEEE80211_SEQ_TO_SN(mvmsta->tid_data[tid].seq_number); spin_unlock_bh(&mvmsta->lock); - /* - * Non-QoS, QoS NDP and MGMT frames should go to a MGMT queue, if one - * exists - */ - if (!ieee80211_is_data_qos(hdr->frame_control) || - ieee80211_is_qos_nullfunc(hdr->frame_control)) { + if (tid == IWL_MAX_TID_COUNT) { queue = iwl_mvm_find_free_queue(mvm, mvmsta->sta_id, IWL_MVM_DQA_MIN_MGMT_QUEUE, IWL_MVM_DQA_MAX_MGMT_QUEUE); @@ -1341,8 +1313,7 @@ static int iwl_mvm_sta_alloc_queue(struct iwl_mvm *mvm, } } - inc_ssn = iwl_mvm_enable_txq(mvm, queue, mac_queue, - ssn, &cfg, wdg_timeout); + inc_ssn = iwl_mvm_enable_txq(mvm, sta, queue, ssn, &cfg, wdg_timeout); /* * Mark queue as shared in transport if shared @@ -1384,8 +1355,9 @@ static int iwl_mvm_sta_alloc_queue(struct iwl_mvm *mvm, } } else { /* Redirect queue, if needed */ - ret = iwl_mvm_scd_queue_redirect(mvm, queue, tid, ac, ssn, - wdg_timeout, false); + ret = iwl_mvm_redirect_queue(mvm, queue, tid, ac, ssn, + wdg_timeout, false, + iwl_mvm_txq_from_tid(sta, tid)); if (ret) goto out_err; } @@ -1393,7 +1365,7 @@ static int iwl_mvm_sta_alloc_queue(struct iwl_mvm *mvm, return 0; out_err: - iwl_mvm_disable_txq(mvm, queue, mac_queue, tid, 0); + iwl_mvm_disable_txq(mvm, sta, queue, tid, 0); return ret; } @@ -1406,87 +1378,32 @@ static inline u8 iwl_mvm_tid_to_ac_queue(int tid) return tid_to_mac80211_ac[tid]; } -static void iwl_mvm_tx_deferred_stream(struct iwl_mvm *mvm, - struct ieee80211_sta *sta, int tid) -{ - struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); - struct iwl_mvm_tid_data *tid_data = &mvmsta->tid_data[tid]; - struct sk_buff *skb; - struct ieee80211_hdr *hdr; - struct sk_buff_head deferred_tx; - u8 mac_queue; - bool no_queue = false; /* Marks if there is a problem with the queue */ - u8 ac; - - lockdep_assert_held(&mvm->mutex); - - skb = skb_peek(&tid_data->deferred_tx_frames); - if (!skb) - return; - hdr = (void *)skb->data; - - ac = iwl_mvm_tid_to_ac_queue(tid); - mac_queue = IEEE80211_SKB_CB(skb)->hw_queue; - - if (tid_data->txq_id == IWL_MVM_INVALID_QUEUE && - iwl_mvm_sta_alloc_queue(mvm, sta, ac, tid, hdr)) { - IWL_ERR(mvm, - "Can't alloc TXQ for sta %d tid %d - dropping frame\n", - mvmsta->sta_id, tid); - - /* - * Mark queue as problematic so later the deferred traffic is - * freed, as we can do nothing with it - */ - no_queue = true; - } - - __skb_queue_head_init(&deferred_tx); - - /* Disable bottom-halves when entering TX path */ - local_bh_disable(); - spin_lock(&mvmsta->lock); - skb_queue_splice_init(&tid_data->deferred_tx_frames, &deferred_tx); - mvmsta->deferred_traffic_tid_map &= ~BIT(tid); - spin_unlock(&mvmsta->lock); - - while ((skb = __skb_dequeue(&deferred_tx))) - if (no_queue || iwl_mvm_tx_skb(mvm, skb, sta)) - ieee80211_free_txskb(mvm->hw, skb); - local_bh_enable(); - - /* Wake queue */ - iwl_mvm_start_mac_queues(mvm, BIT(mac_queue)); -} - void iwl_mvm_add_new_dqa_stream_wk(struct work_struct *wk) { struct iwl_mvm *mvm = container_of(wk, struct iwl_mvm, add_stream_wk); - struct ieee80211_sta *sta; - struct iwl_mvm_sta *mvmsta; - unsigned long deferred_tid_traffic; - int sta_id, tid; mutex_lock(&mvm->mutex); iwl_mvm_inactivity_check(mvm, IWL_MVM_INVALID_STA); - /* Go over all stations with deferred traffic */ - for_each_set_bit(sta_id, mvm->sta_deferred_frames, - IWL_MVM_STATION_COUNT) { - clear_bit(sta_id, mvm->sta_deferred_frames); - sta = rcu_dereference_protected(mvm->fw_id_to_mac_id[sta_id], - lockdep_is_held(&mvm->mutex)); - if (IS_ERR_OR_NULL(sta)) - continue; + while (!list_empty(&mvm->add_stream_txqs)) { + struct iwl_mvm_txq *mvmtxq; + struct ieee80211_txq *txq; + u8 tid; - mvmsta = iwl_mvm_sta_from_mac80211(sta); - deferred_tid_traffic = mvmsta->deferred_traffic_tid_map; + mvmtxq = list_first_entry(&mvm->add_stream_txqs, + struct iwl_mvm_txq, list); + + txq = container_of((void *)mvmtxq, struct ieee80211_txq, + drv_priv); + tid = txq->tid; + if (tid == IEEE80211_NUM_TIDS) + tid = IWL_MAX_TID_COUNT; - for_each_set_bit(tid, &deferred_tid_traffic, - IWL_MAX_TID_COUNT + 1) - iwl_mvm_tx_deferred_stream(mvm, sta, tid); + iwl_mvm_sta_alloc_queue(mvm, txq->sta, txq->ac, tid); + list_del_init(&mvmtxq->list); + iwl_mvm_mac_itxq_xmit(mvm->hw, txq); } mutex_unlock(&mvm->mutex); @@ -1542,10 +1459,11 @@ static int iwl_mvm_reserve_sta_stream(struct iwl_mvm *mvm, * Note that re-enabling aggregations isn't done in this function. */ static void iwl_mvm_realloc_queues_after_restart(struct iwl_mvm *mvm, - struct iwl_mvm_sta *mvm_sta) + struct ieee80211_sta *sta) { - unsigned int wdg_timeout = - iwl_mvm_get_wd_timeout(mvm, mvm_sta->vif, false, false); + struct iwl_mvm_sta *mvm_sta = iwl_mvm_sta_from_mac80211(sta); + unsigned int wdg = + iwl_mvm_get_wd_timeout(mvm, mvm_sta->vif, false, false); int i; struct iwl_trans_txq_scd_cfg cfg = { .sta_id = mvm_sta->sta_id, @@ -1561,23 +1479,18 @@ static void iwl_mvm_realloc_queues_after_restart(struct iwl_mvm *mvm, struct iwl_mvm_tid_data *tid_data = &mvm_sta->tid_data[i]; int txq_id = tid_data->txq_id; int ac; - u8 mac_queue; if (txq_id == IWL_MVM_INVALID_QUEUE) continue; - skb_queue_head_init(&tid_data->deferred_tx_frames); - ac = tid_to_mac80211_ac[i]; - mac_queue = mvm_sta->vif->hw_queue[ac]; if (iwl_mvm_has_new_tx_api(mvm)) { IWL_DEBUG_TX_QUEUES(mvm, "Re-mapping sta %d tid %d\n", mvm_sta->sta_id, i); - txq_id = iwl_mvm_tvqm_enable_txq(mvm, mac_queue, - mvm_sta->sta_id, - i, wdg_timeout); + txq_id = iwl_mvm_tvqm_enable_txq(mvm, mvm_sta->sta_id, + i, wdg); tid_data->txq_id = txq_id; /* @@ -1600,8 +1513,7 @@ static void iwl_mvm_realloc_queues_after_restart(struct iwl_mvm *mvm, "Re-mapping sta %d tid %d to queue %d\n", mvm_sta->sta_id, i, txq_id); - iwl_mvm_enable_txq(mvm, txq_id, mac_queue, seq, &cfg, - wdg_timeout); + iwl_mvm_enable_txq(mvm, sta, txq_id, seq, &cfg, wdg); mvm->queue_info[txq_id].status = IWL_MVM_QUEUE_READY; } } @@ -1691,7 +1603,7 @@ int iwl_mvm_add_sta(struct iwl_mvm *mvm, if (ret) goto err; - iwl_mvm_realloc_queues_after_restart(mvm, mvm_sta); + iwl_mvm_realloc_queues_after_restart(mvm, sta); sta_update = true; sta_flags = iwl_mvm_has_new_tx_api(mvm) ? 0 : STA_MODIFY_QUEUES; goto update_fw; @@ -1724,9 +1636,17 @@ int iwl_mvm_add_sta(struct iwl_mvm *mvm, * frames until the queue is allocated */ mvm_sta->tid_data[i].txq_id = IWL_MVM_INVALID_QUEUE; - skb_queue_head_init(&mvm_sta->tid_data[i].deferred_tx_frames); } - mvm_sta->deferred_traffic_tid_map = 0; + + for (i = 0; i < ARRAY_SIZE(sta->txq); i++) { + struct iwl_mvm_txq *mvmtxq = + iwl_mvm_txq_from_mac80211(sta->txq[i]); + + mvmtxq->txq_id = IWL_MVM_INVALID_QUEUE; + INIT_LIST_HEAD(&mvmtxq->list); + atomic_set(&mvmtxq->tx_request, 0); + } + mvm_sta->agg_tids = 0; if (iwl_mvm_has_new_rx_api(mvm) && @@ -1861,9 +1781,9 @@ static int iwl_mvm_rm_sta_common(struct iwl_mvm *mvm, u8 sta_id) static void iwl_mvm_disable_sta_queues(struct iwl_mvm *mvm, struct ieee80211_vif *vif, - struct iwl_mvm_sta *mvm_sta) + struct ieee80211_sta *sta) { - int ac; + struct iwl_mvm_sta *mvm_sta = iwl_mvm_sta_from_mac80211(sta); int i; lockdep_assert_held(&mvm->mutex); @@ -1872,11 +1792,17 @@ static void iwl_mvm_disable_sta_queues(struct iwl_mvm *mvm, if (mvm_sta->tid_data[i].txq_id == IWL_MVM_INVALID_QUEUE) continue; - ac = iwl_mvm_tid_to_ac_queue(i); - iwl_mvm_disable_txq(mvm, mvm_sta->tid_data[i].txq_id, - vif->hw_queue[ac], i, 0); + iwl_mvm_disable_txq(mvm, sta, mvm_sta->tid_data[i].txq_id, i, + 0); mvm_sta->tid_data[i].txq_id = IWL_MVM_INVALID_QUEUE; } + + for (i = 0; i < ARRAY_SIZE(sta->txq); i++) { + struct iwl_mvm_txq *mvmtxq = + iwl_mvm_txq_from_mac80211(sta->txq[i]); + + mvmtxq->txq_id = IWL_MVM_INVALID_QUEUE; + } } int iwl_mvm_wait_sta_queues_empty(struct iwl_mvm *mvm, @@ -1938,7 +1864,7 @@ int iwl_mvm_rm_sta(struct iwl_mvm *mvm, ret = iwl_mvm_drain_sta(mvm, mvm_sta, false); - iwl_mvm_disable_sta_queues(mvm, vif, mvm_sta); + iwl_mvm_disable_sta_queues(mvm, vif, sta); /* If there is a TXQ still marked as reserved - free it */ if (mvm_sta->reserved_queue != IEEE80211_INVAL_HW_QUEUE) { @@ -2044,7 +1970,7 @@ static void iwl_mvm_enable_aux_snif_queue(struct iwl_mvm *mvm, u16 *queue, if (iwl_mvm_has_new_tx_api(mvm)) { int tvqm_queue = - iwl_mvm_tvqm_enable_txq(mvm, *queue, sta_id, + iwl_mvm_tvqm_enable_txq(mvm, sta_id, IWL_MAX_TID_COUNT, wdg_timeout); *queue = tvqm_queue; @@ -2057,7 +1983,7 @@ static void iwl_mvm_enable_aux_snif_queue(struct iwl_mvm *mvm, u16 *queue, .frame_limit = IWL_FRAME_LIMIT, }; - iwl_mvm_enable_txq(mvm, *queue, *queue, 0, &cfg, wdg_timeout); + iwl_mvm_enable_txq(mvm, NULL, *queue, 0, &cfg, wdg_timeout); } } @@ -2135,8 +2061,7 @@ int iwl_mvm_rm_snif_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif) lockdep_assert_held(&mvm->mutex); - iwl_mvm_disable_txq(mvm, mvm->snif_queue, mvm->snif_queue, - IWL_MAX_TID_COUNT, 0); + iwl_mvm_disable_txq(mvm, NULL, mvm->snif_queue, IWL_MAX_TID_COUNT, 0); ret = iwl_mvm_rm_sta_common(mvm, mvm->snif_sta.sta_id); if (ret) IWL_WARN(mvm, "Failed sending remove station\n"); @@ -2195,8 +2120,7 @@ int iwl_mvm_send_add_bcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif) bsta->tfd_queue_msk |= BIT(queue); - iwl_mvm_enable_txq(mvm, queue, vif->hw_queue[0], 0, - &cfg, wdg_timeout); + iwl_mvm_enable_txq(mvm, NULL, queue, 0, &cfg, wdg_timeout); } if (vif->type == NL80211_IFTYPE_ADHOC) @@ -2215,8 +2139,7 @@ int iwl_mvm_send_add_bcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif) * to firmware so enable queue here - after the station was added */ if (iwl_mvm_has_new_tx_api(mvm)) { - queue = iwl_mvm_tvqm_enable_txq(mvm, vif->hw_queue[0], - bsta->sta_id, + queue = iwl_mvm_tvqm_enable_txq(mvm, bsta->sta_id, IWL_MAX_TID_COUNT, wdg_timeout); @@ -2254,7 +2177,7 @@ static void iwl_mvm_free_bcast_sta_queues(struct iwl_mvm *mvm, return; } - iwl_mvm_disable_txq(mvm, queue, vif->hw_queue[0], IWL_MAX_TID_COUNT, 0); + iwl_mvm_disable_txq(mvm, NULL, queue, IWL_MAX_TID_COUNT, 0); if (iwl_mvm_has_new_tx_api(mvm)) return; @@ -2377,10 +2300,8 @@ int iwl_mvm_add_mcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif) * Note that this is done here as we want to avoid making DQA * changes in mac80211 layer. */ - if (vif->type == NL80211_IFTYPE_ADHOC) { - vif->cab_queue = IWL_MVM_DQA_GCAST_QUEUE; - mvmvif->cab_queue = vif->cab_queue; - } + if (vif->type == NL80211_IFTYPE_ADHOC) + mvmvif->cab_queue = IWL_MVM_DQA_GCAST_QUEUE; /* * While in previous FWs we had to exclude cab queue from TFD queue @@ -2388,9 +2309,9 @@ int iwl_mvm_add_mcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif) */ if (!iwl_mvm_has_new_tx_api(mvm) && fw_has_api(&mvm->fw->ucode_capa, IWL_UCODE_TLV_API_STA_TYPE)) { - iwl_mvm_enable_txq(mvm, vif->cab_queue, vif->cab_queue, 0, - &cfg, timeout); - msta->tfd_queue_msk |= BIT(vif->cab_queue); + iwl_mvm_enable_txq(mvm, NULL, mvmvif->cab_queue, 0, &cfg, + timeout); + msta->tfd_queue_msk |= BIT(mvmvif->cab_queue); } ret = iwl_mvm_add_int_sta_common(mvm, msta, maddr, mvmvif->id, mvmvif->color); @@ -2407,15 +2328,14 @@ int iwl_mvm_add_mcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif) * tfd_queue_mask. */ if (iwl_mvm_has_new_tx_api(mvm)) { - int queue = iwl_mvm_tvqm_enable_txq(mvm, vif->cab_queue, - msta->sta_id, + int queue = iwl_mvm_tvqm_enable_txq(mvm, msta->sta_id, 0, timeout); mvmvif->cab_queue = queue; } else if (!fw_has_api(&mvm->fw->ucode_capa, IWL_UCODE_TLV_API_STA_TYPE)) - iwl_mvm_enable_txq(mvm, vif->cab_queue, vif->cab_queue, 0, - &cfg, timeout); + iwl_mvm_enable_txq(mvm, NULL, mvmvif->cab_queue, 0, &cfg, + timeout); if (mvmvif->ap_wep_key) { u8 key_offset = iwl_mvm_set_fw_key_idx(mvm); @@ -2446,8 +2366,7 @@ int iwl_mvm_rm_mcast_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif) iwl_mvm_flush_sta(mvm, &mvmvif->mcast_sta, true, 0); - iwl_mvm_disable_txq(mvm, mvmvif->cab_queue, vif->cab_queue, - 0, 0); + iwl_mvm_disable_txq(mvm, NULL, mvmvif->cab_queue, 0, 0); ret = iwl_mvm_rm_sta_common(mvm, mvmvif->mcast_sta.sta_id); if (ret) @@ -2781,7 +2700,7 @@ int iwl_mvm_sta_tx_agg_start(struct iwl_mvm *mvm, struct ieee80211_vif *vif, struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); struct iwl_mvm_tid_data *tid_data; u16 normalized_ssn; - int txq_id; + u16 txq_id; int ret; if (WARN_ON_ONCE(tid >= IWL_MAX_TID_COUNT)) @@ -2823,17 +2742,24 @@ int iwl_mvm_sta_tx_agg_start(struct iwl_mvm *mvm, struct ieee80211_vif *vif, */ txq_id = mvmsta->tid_data[tid].txq_id; if (txq_id == IWL_MVM_INVALID_QUEUE) { - txq_id = iwl_mvm_find_free_queue(mvm, mvmsta->sta_id, - IWL_MVM_DQA_MIN_DATA_QUEUE, - IWL_MVM_DQA_MAX_DATA_QUEUE); - if (txq_id < 0) { - ret = txq_id; + ret = iwl_mvm_find_free_queue(mvm, mvmsta->sta_id, + IWL_MVM_DQA_MIN_DATA_QUEUE, + IWL_MVM_DQA_MAX_DATA_QUEUE); + if (ret < 0) { IWL_ERR(mvm, "Failed to allocate agg queue\n"); goto out; } + txq_id = ret; + /* TXQ hasn't yet been enabled, so mark it only as reserved */ mvm->queue_info[txq_id].status = IWL_MVM_QUEUE_RESERVED; + } else if (WARN_ON(txq_id >= IWL_MAX_HW_QUEUES)) { + ret = -ENXIO; + IWL_ERR(mvm, "tid_id %d out of range (0, %d)!\n", + tid, IWL_MAX_HW_QUEUES - 1); + goto out; + } else if (unlikely(mvm->queue_info[txq_id].status == IWL_MVM_QUEUE_SHARED)) { ret = -ENXIO; @@ -2976,8 +2902,7 @@ int iwl_mvm_sta_tx_agg_oper(struct iwl_mvm *mvm, struct ieee80211_vif *vif, } if (alloc_queue) - iwl_mvm_enable_txq(mvm, queue, - vif->hw_queue[tid_to_mac80211_ac[tid]], ssn, + iwl_mvm_enable_txq(mvm, sta, queue, ssn, &cfg, wdg_timeout); /* Send ADD_STA command to enable aggs only if the queue isn't shared */ diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h index d52cd888f77d..0614296244b3 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h @@ -297,7 +297,6 @@ enum iwl_mvm_agg_state { /** * struct iwl_mvm_tid_data - holds the states for each RA / TID - * @deferred_tx_frames: deferred TX frames for this RA/TID * @seq_number: the next WiFi sequence number to use * @next_reclaimed: the WiFi sequence number of the next packet to be acked. * This is basically (last acked packet++). @@ -318,7 +317,6 @@ enum iwl_mvm_agg_state { * tpt_meas_start */ struct iwl_mvm_tid_data { - struct sk_buff_head deferred_tx_frames; u16 seq_number; u16 next_reclaimed; /* The rest is Tx AGG related */ @@ -427,8 +425,6 @@ struct iwl_mvm_sta { struct iwl_mvm_key_pn __rcu *ptk_pn[4]; struct iwl_mvm_rxq_dup_data *dup_data; - u16 deferred_traffic_tid_map; - u8 reserved_queue; /* Temporary, until the new TLC will control the Tx protection */ diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tdls.c b/drivers/net/wireless/intel/iwlwifi/mvm/tdls.c index e02f4eb20359..859aa5a4e6b5 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tdls.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tdls.c @@ -399,6 +399,9 @@ iwl_mvm_tdls_config_channel_switch(struct iwl_mvm *mvm, struct ieee80211_tx_info *info; struct ieee80211_hdr *hdr; struct iwl_tdls_channel_switch_cmd cmd = {0}; + struct iwl_tdls_channel_switch_cmd_tail *tail = + iwl_mvm_chan_info_cmd_tail(mvm, &cmd.ci); + u16 len = sizeof(cmd) - iwl_mvm_chan_info_padding(mvm); int ret; lockdep_assert_held(&mvm->mutex); @@ -414,9 +417,9 @@ iwl_mvm_tdls_config_channel_switch(struct iwl_mvm *mvm, } cmd.switch_type = type; - cmd.timing.frame_timestamp = cpu_to_le32(timestamp); - cmd.timing.switch_time = cpu_to_le32(switch_time); - cmd.timing.switch_timeout = cpu_to_le32(switch_timeout); + tail->timing.frame_timestamp = cpu_to_le32(timestamp); + tail->timing.switch_time = cpu_to_le32(switch_time); + tail->timing.switch_timeout = cpu_to_le32(switch_timeout); rcu_read_lock(); sta = ieee80211_find_sta(vif, peer); @@ -448,21 +451,16 @@ iwl_mvm_tdls_config_channel_switch(struct iwl_mvm *mvm, } } - if (chandef) { - cmd.ci.band = (chandef->chan->band == NL80211_BAND_2GHZ ? - PHY_BAND_24 : PHY_BAND_5); - cmd.ci.channel = chandef->chan->hw_value; - cmd.ci.width = iwl_mvm_get_channel_width(chandef); - cmd.ci.ctrl_pos = iwl_mvm_get_ctrl_pos(chandef); - } + if (chandef) + iwl_mvm_set_chan_info_chandef(mvm, &cmd.ci, chandef); /* keep quota calculation simple for now - 50% of DTIM for TDLS */ - cmd.timing.max_offchan_duration = + tail->timing.max_offchan_duration = cpu_to_le32(TU_TO_US(vif->bss_conf.dtim_period * vif->bss_conf.beacon_int) / 2); /* Switch time is the first element in the switch-timing IE. */ - cmd.frame.switch_time_offset = cpu_to_le32(ch_sw_tm_ie + 2); + tail->frame.switch_time_offset = cpu_to_le32(ch_sw_tm_ie + 2); info = IEEE80211_SKB_CB(skb); hdr = (void *)skb->data; @@ -472,20 +470,19 @@ iwl_mvm_tdls_config_channel_switch(struct iwl_mvm *mvm, ret = -EINVAL; goto out; } - iwl_mvm_set_tx_cmd_ccmp(info, &cmd.frame.tx_cmd); + iwl_mvm_set_tx_cmd_ccmp(info, &tail->frame.tx_cmd); } - iwl_mvm_set_tx_cmd(mvm, skb, &cmd.frame.tx_cmd, info, + iwl_mvm_set_tx_cmd(mvm, skb, &tail->frame.tx_cmd, info, mvmsta->sta_id); - iwl_mvm_set_tx_cmd_rate(mvm, &cmd.frame.tx_cmd, info, sta, + iwl_mvm_set_tx_cmd_rate(mvm, &tail->frame.tx_cmd, info, sta, hdr->frame_control); rcu_read_unlock(); - memcpy(cmd.frame.data, skb->data, skb->len); + memcpy(tail->frame.data, skb->data, skb->len); - ret = iwl_mvm_send_cmd_pdu(mvm, TDLS_CHANNEL_SWITCH_CMD, 0, - sizeof(cmd), &cmd); + ret = iwl_mvm_send_cmd_pdu(mvm, TDLS_CHANNEL_SWITCH_CMD, 0, len, &cmd); if (ret) { IWL_ERR(mvm, "Failed to send TDLS_CHANNEL_SWITCH cmd: %d\n", ret); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c index e1a6f4e22253..5b34100e9099 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c @@ -334,6 +334,7 @@ static void iwl_mvm_te_handle_notif(struct iwl_mvm *mvm, switch (te_data->vif->type) { case NL80211_IFTYPE_P2P_DEVICE: ieee80211_remain_on_channel_expired(mvm->hw); + set_bit(IWL_MVM_STATUS_NEED_FLUSH_P2P, &mvm->status); iwl_mvm_roc_finished(mvm); break; case NL80211_IFTYPE_STATION: @@ -686,6 +687,8 @@ static void iwl_mvm_remove_aux_roc_te(struct iwl_mvm *mvm, struct iwl_mvm_time_event_data *te_data) { struct iwl_hs20_roc_req aux_cmd = {}; + u16 len = sizeof(aux_cmd) - iwl_mvm_chan_info_padding(mvm); + u32 uid; int ret; @@ -699,7 +702,7 @@ static void iwl_mvm_remove_aux_roc_te(struct iwl_mvm *mvm, IWL_DEBUG_TE(mvm, "Removing BSS AUX ROC TE 0x%x\n", le32_to_cpu(aux_cmd.event_unique_id)); ret = iwl_mvm_send_cmd_pdu(mvm, HOT_SPOT_CMD, 0, - sizeof(aux_cmd), &aux_cmd); + len, &aux_cmd); if (WARN_ON(ret)) return; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tof.c b/drivers/net/wireless/intel/iwlwifi/mvm/tof.c deleted file mode 100644 index 01e0a999063b..000000000000 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tof.c +++ /dev/null @@ -1,305 +0,0 @@ -/****************************************************************************** - * - * This file is provided under a dual BSD/GPLv2 license. When using or - * redistributing this file, you may do so under either license. - * - * GPL LICENSE SUMMARY - * - * Copyright(c) 2015 Intel Deutschland GmbH - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of version 2 of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * The full GNU General Public License is included in this distribution - * in the file called COPYING. - * - * Contact Information: - * Intel Linux Wireless <linuxwifi@intel.com> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - * BSD LICENSE - * - * Copyright(c) 2015 Intel Deutschland GmbH - * All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in - * the documentation and/or other materials provided with the - * distribution. - * * Neither the name Intel Corporation nor the names of its - * contributors may be used to endorse or promote products derived - * from this software without specific prior written permission. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - * - *****************************************************************************/ -#include "mvm.h" -#include "fw/api/tof.h" - -#define IWL_MVM_TOF_RANGE_REQ_MAX_ID 256 - -void iwl_mvm_tof_init(struct iwl_mvm *mvm) -{ - struct iwl_mvm_tof_data *tof_data = &mvm->tof_data; - - if (!fw_has_capa(&mvm->fw->ucode_capa, IWL_UCODE_TLV_CAPA_TOF_SUPPORT)) - return; - - memset(tof_data, 0, sizeof(*tof_data)); - - tof_data->tof_cfg.sub_grp_cmd_id = cpu_to_le32(TOF_CONFIG_CMD); - -#ifdef CONFIG_IWLWIFI_DEBUGFS - if (IWL_MVM_TOF_IS_RESPONDER) { - tof_data->responder_cfg.sub_grp_cmd_id = - cpu_to_le32(TOF_RESPONDER_CONFIG_CMD); - tof_data->responder_cfg.sta_id = IWL_MVM_INVALID_STA; - } -#endif - - tof_data->range_req.sub_grp_cmd_id = cpu_to_le32(TOF_RANGE_REQ_CMD); - tof_data->range_req.req_timeout = 1; - tof_data->range_req.initiator = 1; - tof_data->range_req.report_policy = 3; - - tof_data->range_req_ext.sub_grp_cmd_id = - cpu_to_le32(TOF_RANGE_REQ_EXT_CMD); - - mvm->tof_data.active_range_request = IWL_MVM_TOF_RANGE_REQ_MAX_ID; - mvm->init_status |= IWL_MVM_INIT_STATUS_TOF_INIT_COMPLETE; -} - -void iwl_mvm_tof_clean(struct iwl_mvm *mvm) -{ - struct iwl_mvm_tof_data *tof_data = &mvm->tof_data; - - if (!fw_has_capa(&mvm->fw->ucode_capa, - IWL_UCODE_TLV_CAPA_TOF_SUPPORT) || - !(mvm->init_status & IWL_MVM_INIT_STATUS_TOF_INIT_COMPLETE)) - return; - - memset(tof_data, 0, sizeof(*tof_data)); - mvm->tof_data.active_range_request = IWL_MVM_TOF_RANGE_REQ_MAX_ID; - mvm->init_status &= ~IWL_MVM_INIT_STATUS_TOF_INIT_COMPLETE; -} - -static void iwl_tof_iterator(void *_data, u8 *mac, - struct ieee80211_vif *vif) -{ - bool *enabled = _data; - - /* non bss vif exists */ - if (ieee80211_vif_type_p2p(vif) != NL80211_IFTYPE_STATION) - *enabled = false; -} - -int iwl_mvm_tof_config_cmd(struct iwl_mvm *mvm) -{ - struct iwl_tof_config_cmd *cmd = &mvm->tof_data.tof_cfg; - bool enabled; - - lockdep_assert_held(&mvm->mutex); - - if (!fw_has_capa(&mvm->fw->ucode_capa, IWL_UCODE_TLV_CAPA_TOF_SUPPORT)) - return -EINVAL; - - ieee80211_iterate_active_interfaces_atomic(mvm->hw, - IEEE80211_IFACE_ITER_NORMAL, - iwl_tof_iterator, &enabled); - if (!enabled) { - IWL_DEBUG_INFO(mvm, "ToF is not supported (non bss vif)\n"); - return -EINVAL; - } - - mvm->tof_data.active_range_request = IWL_MVM_TOF_RANGE_REQ_MAX_ID; - return iwl_mvm_send_cmd_pdu(mvm, iwl_cmd_id(TOF_CMD, - IWL_ALWAYS_LONG_GROUP, 0), - 0, sizeof(*cmd), cmd); -} - -int iwl_mvm_tof_range_abort_cmd(struct iwl_mvm *mvm, u8 id) -{ - struct iwl_tof_range_abort_cmd cmd = { - .sub_grp_cmd_id = cpu_to_le32(TOF_RANGE_ABORT_CMD), - .request_id = id, - }; - - lockdep_assert_held(&mvm->mutex); - - if (!fw_has_capa(&mvm->fw->ucode_capa, IWL_UCODE_TLV_CAPA_TOF_SUPPORT)) - return -EINVAL; - - if (id != mvm->tof_data.active_range_request) { - IWL_ERR(mvm, "Invalid range request id %d (active %d)\n", - id, mvm->tof_data.active_range_request); - return -EINVAL; - } - - /* after abort is sent there's no active request anymore */ - mvm->tof_data.active_range_request = IWL_MVM_TOF_RANGE_REQ_MAX_ID; - - return iwl_mvm_send_cmd_pdu(mvm, iwl_cmd_id(TOF_CMD, - IWL_ALWAYS_LONG_GROUP, 0), - 0, sizeof(cmd), &cmd); -} - -#ifdef CONFIG_IWLWIFI_DEBUGFS -int iwl_mvm_tof_responder_cmd(struct iwl_mvm *mvm, - struct ieee80211_vif *vif) -{ - struct iwl_tof_responder_config_cmd *cmd = &mvm->tof_data.responder_cfg; - struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); - - lockdep_assert_held(&mvm->mutex); - - if (!fw_has_capa(&mvm->fw->ucode_capa, IWL_UCODE_TLV_CAPA_TOF_SUPPORT)) - return -EINVAL; - - if (vif->p2p || vif->type != NL80211_IFTYPE_AP || - !mvmvif->ap_ibss_active) { - IWL_ERR(mvm, "Cannot start responder, not in AP mode\n"); - return -EIO; - } - - cmd->sta_id = mvmvif->bcast_sta.sta_id; - memcpy(cmd->bssid, vif->addr, ETH_ALEN); - return iwl_mvm_send_cmd_pdu(mvm, iwl_cmd_id(TOF_CMD, - IWL_ALWAYS_LONG_GROUP, 0), - 0, sizeof(*cmd), cmd); -} -#endif - -int iwl_mvm_tof_range_request_cmd(struct iwl_mvm *mvm, - struct ieee80211_vif *vif) -{ - struct iwl_host_cmd cmd = { - .id = iwl_cmd_id(TOF_CMD, IWL_ALWAYS_LONG_GROUP, 0), - .len = { sizeof(mvm->tof_data.range_req), }, - /* no copy because of the command size */ - .dataflags = { IWL_HCMD_DFL_NOCOPY, }, - }; - - lockdep_assert_held(&mvm->mutex); - - if (!fw_has_capa(&mvm->fw->ucode_capa, IWL_UCODE_TLV_CAPA_TOF_SUPPORT)) - return -EINVAL; - - if (ieee80211_vif_type_p2p(vif) != NL80211_IFTYPE_STATION) { - IWL_ERR(mvm, "Cannot send range request, not STA mode\n"); - return -EIO; - } - - /* nesting of range requests is not supported in FW */ - if (mvm->tof_data.active_range_request != - IWL_MVM_TOF_RANGE_REQ_MAX_ID) { - IWL_ERR(mvm, "Cannot send range req, already active req %d\n", - mvm->tof_data.active_range_request); - return -EIO; - } - - mvm->tof_data.active_range_request = mvm->tof_data.range_req.request_id; - - cmd.data[0] = &mvm->tof_data.range_req; - return iwl_mvm_send_cmd(mvm, &cmd); -} - -int iwl_mvm_tof_range_request_ext_cmd(struct iwl_mvm *mvm, - struct ieee80211_vif *vif) -{ - lockdep_assert_held(&mvm->mutex); - - if (!fw_has_capa(&mvm->fw->ucode_capa, IWL_UCODE_TLV_CAPA_TOF_SUPPORT)) - return -EINVAL; - - if (ieee80211_vif_type_p2p(vif) != NL80211_IFTYPE_STATION) { - IWL_ERR(mvm, "Cannot send ext range req, not in STA mode\n"); - return -EIO; - } - - return iwl_mvm_send_cmd_pdu(mvm, iwl_cmd_id(TOF_CMD, - IWL_ALWAYS_LONG_GROUP, 0), - 0, sizeof(mvm->tof_data.range_req_ext), - &mvm->tof_data.range_req_ext); -} - -static int iwl_mvm_tof_range_resp(struct iwl_mvm *mvm, void *data) -{ - struct iwl_tof_range_rsp_ntfy *resp = (void *)data; - - if (resp->request_id != mvm->tof_data.active_range_request) { - IWL_ERR(mvm, "Request id mismatch, got %d, active %d\n", - resp->request_id, mvm->tof_data.active_range_request); - return -EIO; - } - - memcpy(&mvm->tof_data.range_resp, resp, - sizeof(struct iwl_tof_range_rsp_ntfy)); - mvm->tof_data.active_range_request = IWL_MVM_TOF_RANGE_REQ_MAX_ID; - - return 0; -} - -static int iwl_mvm_tof_mcsi_notif(struct iwl_mvm *mvm, void *data) -{ - struct iwl_tof_mcsi_notif *resp = (struct iwl_tof_mcsi_notif *)data; - - IWL_DEBUG_INFO(mvm, "MCSI notification, token %d\n", resp->token); - return 0; -} - -static int iwl_mvm_tof_nb_report_notif(struct iwl_mvm *mvm, void *data) -{ - struct iwl_tof_neighbor_report *report = - (struct iwl_tof_neighbor_report *)data; - - IWL_DEBUG_INFO(mvm, "NB report, bssid %pM, token %d, status 0x%x\n", - report->bssid, report->request_token, report->status); - return 0; -} - -void iwl_mvm_tof_resp_handler(struct iwl_mvm *mvm, - struct iwl_rx_cmd_buffer *rxb) -{ - struct iwl_rx_packet *pkt = rxb_addr(rxb); - struct iwl_tof_gen_resp_cmd *resp = (void *)pkt->data; - - lockdep_assert_held(&mvm->mutex); - - switch (le32_to_cpu(resp->sub_grp_cmd_id)) { - case TOF_RANGE_RESPONSE_NOTIF: - iwl_mvm_tof_range_resp(mvm, resp->data); - break; - case TOF_MCSI_DEBUG_NOTIF: - iwl_mvm_tof_mcsi_notif(mvm, resp->data); - break; - case TOF_NEIGHBOR_REPORT_RSP_NOTIF: - iwl_mvm_tof_nb_report_notif(mvm, resp->data); - break; - default: - IWL_ERR(mvm, "Unknown sub-group command 0x%x\n", - resp->sub_grp_cmd_id); - break; - } -} diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tof.h b/drivers/net/wireless/intel/iwlwifi/mvm/tof.h deleted file mode 100644 index 8138d0606c52..000000000000 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tof.h +++ /dev/null @@ -1,89 +0,0 @@ -/****************************************************************************** - * - * This file is provided under a dual BSD/GPLv2 license. When using or - * redistributing this file, you may do so under either license. - * - * GPL LICENSE SUMMARY - * - * Copyright(c) 2015 Intel Deutschland GmbH - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of version 2 of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * The full GNU General Public License is included in this distribution - * in the file called COPYING. - * - * Contact Information: - * Intel Linux Wireless <linuxwifi@intel.com> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - * BSD LICENSE - * - * Copyright(c) 2015 Intel Deutschland GmbH - * All rights reserved. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in - * the documentation and/or other materials provided with the - * distribution. - * * Neither the name Intel Corporation nor the names of its - * contributors may be used to endorse or promote products derived - * from this software without specific prior written permission. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - * - *****************************************************************************/ -#ifndef __tof_h__ -#define __tof_h__ - -#include "fw/api/tof.h" - -struct iwl_mvm_tof_data { - struct iwl_tof_config_cmd tof_cfg; - struct iwl_tof_range_req_cmd range_req; - struct iwl_tof_range_req_ext_cmd range_req_ext; -#ifdef CONFIG_IWLWIFI_DEBUGFS - struct iwl_tof_responder_config_cmd responder_cfg; -#endif - struct iwl_tof_range_rsp_ntfy range_resp; - u8 last_abort_id; - u16 active_range_request; -}; - -void iwl_mvm_tof_init(struct iwl_mvm *mvm); -void iwl_mvm_tof_clean(struct iwl_mvm *mvm); -int iwl_mvm_tof_config_cmd(struct iwl_mvm *mvm); -int iwl_mvm_tof_range_abort_cmd(struct iwl_mvm *mvm, u8 id); -int iwl_mvm_tof_range_request_cmd(struct iwl_mvm *mvm, - struct ieee80211_vif *vif); -void iwl_mvm_tof_resp_handler(struct iwl_mvm *mvm, - struct iwl_rx_cmd_buffer *rxb); -int iwl_mvm_tof_range_request_ext_cmd(struct iwl_mvm *mvm, - struct ieee80211_vif *vif); -#ifdef CONFIG_IWLWIFI_DEBUGFS -int iwl_mvm_tof_responder_cmd(struct iwl_mvm *mvm, - struct ieee80211_vif *vif); -#endif -#endif /* __tof_h__ */ diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c index 995fe2a6abbb..ac62eb8c4b36 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c @@ -533,10 +533,11 @@ iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb, /* * For data packets rate info comes from the fw. Only - * set rate/antenna during connection establishment. + * set rate/antenna during connection establishment or in case + * no station is given. */ - if (sta && (!ieee80211_is_data(hdr->frame_control) || - mvmsta->sta_state < IEEE80211_STA_AUTHORIZED)) { + if (!sta || !ieee80211_is_data(hdr->frame_control) || + mvmsta->sta_state < IEEE80211_STA_AUTHORIZED) { flags |= IWL_TX_FLAGS_CMD_RATE; rate_n_flags = iwl_mvm_get_tx_rate_n_flags(mvm, info, sta, @@ -602,11 +603,12 @@ static void iwl_mvm_skb_prepare_status(struct sk_buff *skb, } static int iwl_mvm_get_ctrl_vif_queue(struct iwl_mvm *mvm, - struct ieee80211_tx_info *info, __le16 fc) + struct ieee80211_tx_info *info, + struct ieee80211_hdr *hdr) { - struct iwl_mvm_vif *mvmvif; - - mvmvif = iwl_mvm_vif_from_mac80211(info->control.vif); + struct iwl_mvm_vif *mvmvif = + iwl_mvm_vif_from_mac80211(info->control.vif); + __le16 fc = hdr->frame_control; switch (info->control.vif->type) { case NL80211_IFTYPE_AP: @@ -625,7 +627,9 @@ static int iwl_mvm_get_ctrl_vif_queue(struct iwl_mvm *mvm, (!ieee80211_is_bufferable_mmpdu(fc) || ieee80211_is_deauth(fc) || ieee80211_is_disassoc(fc))) return mvm->probe_queue; - if (info->hw_queue == info->control.vif->cab_queue) + + if (!ieee80211_has_order(fc) && !ieee80211_is_probe_req(fc) && + is_multicast_ether_addr(hdr->addr1)) return mvmvif->cab_queue; WARN_ONCE(info->control.vif->type != NL80211_IFTYPE_ADHOC, @@ -634,8 +638,6 @@ static int iwl_mvm_get_ctrl_vif_queue(struct iwl_mvm *mvm, case NL80211_IFTYPE_P2P_DEVICE: if (ieee80211_is_mgmt(fc)) return mvm->p2p_dev_queue; - if (info->hw_queue == info->control.vif->cab_queue) - return mvmvif->cab_queue; WARN_ON_ONCE(1); return mvm->p2p_dev_queue; @@ -713,6 +715,8 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb) u8 sta_id; int hdrlen = ieee80211_hdrlen(hdr->frame_control); __le16 fc = hdr->frame_control; + bool offchannel = IEEE80211_SKB_CB(skb)->flags & + IEEE80211_TX_CTL_TX_OFFCHAN; int queue = -1; memcpy(&info, skb->cb, sizeof(info)); @@ -720,11 +724,6 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb) if (WARN_ON_ONCE(info.flags & IEEE80211_TX_CTL_AMPDU)) return -1; - if (WARN_ON_ONCE(info.flags & IEEE80211_TX_CTL_SEND_AFTER_DTIM && - (!info.control.vif || - info.hw_queue != info.control.vif->cab_queue))) - return -1; - if (info.control.vif) { struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(info.control.vif); @@ -737,14 +736,12 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb) else sta_id = mvmvif->mcast_sta.sta_id; - queue = iwl_mvm_get_ctrl_vif_queue(mvm, &info, - hdr->frame_control); - + queue = iwl_mvm_get_ctrl_vif_queue(mvm, &info, hdr); } else if (info.control.vif->type == NL80211_IFTYPE_MONITOR) { queue = mvm->snif_queue; sta_id = mvm->snif_sta.sta_id; } else if (info.control.vif->type == NL80211_IFTYPE_STATION && - info.hw_queue == IWL_MVM_OFFCHANNEL_QUEUE) { + offchannel) { /* * IWL_MVM_OFFCHANNEL_QUEUE is used for ROC packets * that can be used in 2 different types of vifs, P2P & @@ -758,8 +755,10 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb) } } - if (queue < 0) + if (queue < 0) { + IWL_ERR(mvm, "No queue was found. Dropping TX\n"); return -1; + } if (unlikely(ieee80211_is_probe_resp(fc))) iwl_mvm_probe_resp_set_noa(mvm, skb); @@ -781,6 +780,35 @@ int iwl_mvm_tx_skb_non_sta(struct iwl_mvm *mvm, struct sk_buff *skb) return 0; } +unsigned int iwl_mvm_max_amsdu_size(struct iwl_mvm *mvm, + struct ieee80211_sta *sta, unsigned int tid) +{ + struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); + enum nl80211_band band = mvmsta->vif->bss_conf.chandef.chan->band; + u8 ac = tid_to_mac80211_ac[tid]; + unsigned int txf; + int lmac = IWL_LMAC_24G_INDEX; + + if (iwl_mvm_is_cdb_supported(mvm) && + band == NL80211_BAND_5GHZ) + lmac = IWL_LMAC_5G_INDEX; + + /* For HE redirect to trigger based fifos */ + if (sta->he_cap.has_he && !WARN_ON(!iwl_mvm_has_new_tx_api(mvm))) + ac += 4; + + txf = iwl_mvm_mac_ac_to_tx_fifo(mvm, ac); + + /* + * Don't send an AMSDU that will be longer than the TXF. + * Add a security margin of 256 for the TX command + headers. + * We also want to have the start of the next packet inside the + * fifo to be able to send bursts. + */ + return min_t(unsigned int, mvmsta->max_amsdu_len, + mvm->fwrt.smem_cfg.lmac[lmac].txfifo_size[txf] - 256); +} + #ifdef CONFIG_INET static int @@ -850,36 +878,6 @@ iwl_mvm_tx_tso_segment(struct sk_buff *skb, unsigned int num_subframes, return 0; } -static unsigned int iwl_mvm_max_amsdu_size(struct iwl_mvm *mvm, - struct ieee80211_sta *sta, - unsigned int tid) -{ - struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta); - enum nl80211_band band = mvmsta->vif->bss_conf.chandef.chan->band; - u8 ac = tid_to_mac80211_ac[tid]; - unsigned int txf; - int lmac = IWL_LMAC_24G_INDEX; - - if (iwl_mvm_is_cdb_supported(mvm) && - band == NL80211_BAND_5GHZ) - lmac = IWL_LMAC_5G_INDEX; - - /* For HE redirect to trigger based fifos */ - if (sta->he_cap.has_he && !WARN_ON(!iwl_mvm_has_new_tx_api(mvm))) - ac += 4; - - txf = iwl_mvm_mac_ac_to_tx_fifo(mvm, ac); - - /* - * Don't send an AMSDU that will be longer than the TXF. - * Add a security margin of 256 for the TX command + headers. - * We also want to have the start of the next packet inside the - * fifo to be able to send bursts. - */ - return min_t(unsigned int, mvmsta->max_amsdu_len, - mvm->fwrt.smem_cfg.lmac[lmac].txfifo_size[txf] - 256); -} - static int iwl_mvm_tx_tso(struct iwl_mvm *mvm, struct sk_buff *skb, struct ieee80211_tx_info *info, struct ieee80211_sta *sta, @@ -1002,34 +1000,6 @@ static int iwl_mvm_tx_tso(struct iwl_mvm *mvm, struct sk_buff *skb, } #endif -static void iwl_mvm_tx_add_stream(struct iwl_mvm *mvm, - struct iwl_mvm_sta *mvm_sta, u8 tid, - struct sk_buff *skb) -{ - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - u8 mac_queue = info->hw_queue; - struct sk_buff_head *deferred_tx_frames; - - lockdep_assert_held(&mvm_sta->lock); - - mvm_sta->deferred_traffic_tid_map |= BIT(tid); - set_bit(mvm_sta->sta_id, mvm->sta_deferred_frames); - - deferred_tx_frames = &mvm_sta->tid_data[tid].deferred_tx_frames; - - skb_queue_tail(deferred_tx_frames, skb); - - /* - * The first deferred frame should've stopped the MAC queues, so we - * should never get a second deferred frame for the RA/TID. - * In case of GSO the first packet may have been split, so don't warn. - */ - if (skb_queue_len(deferred_tx_frames) == 1) { - iwl_mvm_stop_mac_queues(mvm, BIT(mac_queue)); - schedule_work(&mvm->add_stream_wk); - } -} - /* Check if there are any timed-out TIDs on a given shared TXQ */ static bool iwl_mvm_txq_should_update(struct iwl_mvm *mvm, int txq_id) { @@ -1054,7 +1024,12 @@ static void iwl_mvm_tx_airtime(struct iwl_mvm *mvm, int airtime) { int mac = mvmsta->mac_id_n_color & FW_CTXT_ID_MSK; - struct iwl_mvm_tcm_mac *mdata = &mvm->tcm.data[mac]; + struct iwl_mvm_tcm_mac *mdata; + + if (mac >= NUM_MAC_INDEX_DRIVER) + return; + + mdata = &mvm->tcm.data[mac]; if (mvm->tcm.paused) return; @@ -1065,14 +1040,21 @@ static void iwl_mvm_tx_airtime(struct iwl_mvm *mvm, mdata->tx.airtime += airtime; } -static void iwl_mvm_tx_pkt_queued(struct iwl_mvm *mvm, - struct iwl_mvm_sta *mvmsta, int tid) +static int iwl_mvm_tx_pkt_queued(struct iwl_mvm *mvm, + struct iwl_mvm_sta *mvmsta, int tid) { u32 ac = tid_to_mac80211_ac[tid]; int mac = mvmsta->mac_id_n_color & FW_CTXT_ID_MSK; - struct iwl_mvm_tcm_mac *mdata = &mvm->tcm.data[mac]; + struct iwl_mvm_tcm_mac *mdata; + + if (mac >= NUM_MAC_INDEX_DRIVER) + return -EINVAL; + + mdata = &mvm->tcm.data[mac]; mdata->tx.pkts[ac]++; + + return 0; } /* @@ -1088,7 +1070,7 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb, __le16 fc; u16 seq_number = 0; u8 tid = IWL_MAX_TID_COUNT; - u16 txq_id = info->hw_queue; + u16 txq_id; bool is_ampdu = false; int hdrlen; @@ -1152,14 +1134,7 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb, WARN_ON_ONCE(info->flags & IEEE80211_TX_CTL_SEND_AFTER_DTIM); - /* Check if TXQ needs to be allocated or re-activated */ - if (unlikely(txq_id == IWL_MVM_INVALID_QUEUE)) { - iwl_mvm_tx_add_stream(mvm, mvmsta, tid, skb); - - /* - * The frame is now deferred, and the worker scheduled - * will re-allocate it, so we can free it for now. - */ + if (WARN_ON_ONCE(txq_id == IWL_MVM_INVALID_QUEUE)) { iwl_trans_free_tx_cmd(mvm->trans, dev_cmd); spin_unlock(&mvmsta->lock); return 0; @@ -1199,7 +1174,9 @@ static int iwl_mvm_tx_mpdu(struct iwl_mvm *mvm, struct sk_buff *skb, spin_unlock(&mvmsta->lock); - iwl_mvm_tx_pkt_queued(mvm, mvmsta, tid == IWL_MAX_TID_COUNT ? 0 : tid); + if (iwl_mvm_tx_pkt_queued(mvm, mvmsta, + tid == IWL_MAX_TID_COUNT ? 0 : tid)) + goto drop; return 0; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c index d116c6ae18ff..211c4638d690 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c @@ -248,7 +248,7 @@ void iwl_mvm_rx_fw_error(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb) IWL_ERR(mvm, "FW Error notification: seq 0x%04X service 0x%08X\n", le16_to_cpu(err_resp->bad_cmd_seq_num), le32_to_cpu(err_resp->error_service)); - IWL_ERR(mvm, "FW Error notification: timestamp 0x%16llX\n", + IWL_ERR(mvm, "FW Error notification: timestamp 0x%016llX\n", le64_to_cpu(err_resp->timestamp)); } @@ -463,6 +463,9 @@ static void iwl_mvm_dump_umac_error_log(struct iwl_mvm *mvm) iwl_trans_read_mem_bytes(trans, mvm->umac_error_event_table, &table, sizeof(table)); + if (table.valid) + mvm->fwrt.dump.umac_err_id = table.error_id; + if (ERROR_START_OFFSET <= table.valid * ERROR_ELEM_SIZE) { IWL_ERR(trans, "Start IWL Error Log Dump:\n"); IWL_ERR(trans, "Status: 0x%08lX, count: %d\n", @@ -486,11 +489,11 @@ static void iwl_mvm_dump_umac_error_log(struct iwl_mvm *mvm) IWL_ERR(mvm, "0x%08X | isr status reg\n", table.nic_isr_pref); } -static void iwl_mvm_dump_lmac_error_log(struct iwl_mvm *mvm, u32 base) +static void iwl_mvm_dump_lmac_error_log(struct iwl_mvm *mvm, u8 lmac_num) { struct iwl_trans *trans = mvm->trans; struct iwl_error_event_table table; - u32 val; + u32 val, base = mvm->error_event_table[lmac_num]; if (mvm->fwrt.cur_fw_img == IWL_UCODE_INIT) { if (!base) @@ -541,7 +544,7 @@ static void iwl_mvm_dump_lmac_error_log(struct iwl_mvm *mvm, u32 base) iwl_trans_read_mem_bytes(trans, base, &table, sizeof(table)); if (table.valid) - mvm->fwrt.dump.rt_status = table.error_id; + mvm->fwrt.dump.lmac_err_id[lmac_num] = table.error_id; if (ERROR_START_OFFSET <= table.valid * ERROR_ELEM_SIZE) { IWL_ERR(trans, "Start IWL Error Log Dump:\n"); @@ -598,10 +601,10 @@ void iwl_mvm_dump_nic_error_log(struct iwl_mvm *mvm) return; } - iwl_mvm_dump_lmac_error_log(mvm, mvm->error_event_table[0]); + iwl_mvm_dump_lmac_error_log(mvm, 0); if (mvm->error_event_table[1]) - iwl_mvm_dump_lmac_error_log(mvm, mvm->error_event_table[1]); + iwl_mvm_dump_lmac_error_log(mvm, 1); iwl_mvm_dump_umac_error_log(mvm); } @@ -1133,19 +1136,14 @@ static void iwl_mvm_tcm_uapsd_nonagg_detected_wk(struct work_struct *wk) "AP isn't using AMPDU with uAPSD enabled"); } -static void iwl_mvm_uapsd_agg_disconnect_iter(void *data, u8 *mac, - struct ieee80211_vif *vif) +static void iwl_mvm_uapsd_agg_disconnect(struct iwl_mvm *mvm, + struct ieee80211_vif *vif) { struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif); - struct iwl_mvm *mvm = mvmvif->mvm; - int *mac_id = data; if (vif->type != NL80211_IFTYPE_STATION) return; - if (mvmvif->id != *mac_id) - return; - if (!vif->bss_conf.assoc) return; @@ -1155,10 +1153,10 @@ static void iwl_mvm_uapsd_agg_disconnect_iter(void *data, u8 *mac, !mvmvif->queue_params[IEEE80211_AC_BK].uapsd) return; - if (mvm->tcm.data[*mac_id].uapsd_nonagg_detect.detected) + if (mvm->tcm.data[mvmvif->id].uapsd_nonagg_detect.detected) return; - mvm->tcm.data[*mac_id].uapsd_nonagg_detect.detected = true; + mvm->tcm.data[mvmvif->id].uapsd_nonagg_detect.detected = true; IWL_INFO(mvm, "detected AP should do aggregation but isn't, likely due to U-APSD\n"); schedule_delayed_work(&mvmvif->uapsd_nonagg_detected_wk, 15 * HZ); @@ -1171,6 +1169,7 @@ static void iwl_mvm_check_uapsd_agg_expected_tpt(struct iwl_mvm *mvm, u64 bytes = mvm->tcm.data[mac].uapsd_nonagg_detect.rx_bytes; u64 tpt; unsigned long rate; + struct ieee80211_vif *vif; rate = ewma_rate_read(&mvm->tcm.data[mac].uapsd_nonagg_detect.rate); @@ -1199,9 +1198,11 @@ static void iwl_mvm_check_uapsd_agg_expected_tpt(struct iwl_mvm *mvm, return; } - ieee80211_iterate_active_interfaces_atomic( - mvm->hw, IEEE80211_IFACE_ITER_NORMAL, - iwl_mvm_uapsd_agg_disconnect_iter, &mac); + rcu_read_lock(); + vif = rcu_dereference(mvm->vif_id_to_mac[mac]); + if (vif) + iwl_mvm_uapsd_agg_disconnect(mvm, vif); + rcu_read_unlock(); } static void iwl_mvm_tcm_iterator(void *_data, u8 *mac, diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index 353581ccc01e..a22e47639a4e 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -513,10 +513,10 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x24FD, 0x9074, iwl8265_2ac_cfg)}, /* 9000 Series */ - {IWL_PCI_DEVICE(0x02F0, 0x0030, iwl9560_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x02F0, 0x0030, iwl9560_2ac_160_cfg_soc)}, {IWL_PCI_DEVICE(0x02F0, 0x0034, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x02F0, 0x0038, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x02F0, 0x003C, iwl9560_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x02F0, 0x0038, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0x02F0, 0x003C, iwl9560_2ac_160_cfg_soc)}, {IWL_PCI_DEVICE(0x02F0, 0x0060, iwl9461_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x02F0, 0x0064, iwl9461_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x02F0, 0x00A0, iwl9462_2ac_cfg_soc)}, @@ -531,17 +531,17 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x02F0, 0x02A4, iwl9462_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x02F0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x02F0, 0x1552, iwl9560_killer_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x02F0, 0x2030, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x02F0, 0x2034, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x02F0, 0x4030, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x02F0, 0x4034, iwl9560_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x02F0, 0x2030, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0x02F0, 0x2034, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0x02F0, 0x4030, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0x02F0, 0x4034, iwl9560_2ac_160_cfg_soc)}, {IWL_PCI_DEVICE(0x02F0, 0x40A4, iwl9462_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x02F0, 0x4234, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x02F0, 0x42A4, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x06F0, 0x0030, iwl9560_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x06F0, 0x0030, iwl9560_2ac_160_cfg_soc)}, {IWL_PCI_DEVICE(0x06F0, 0x0034, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x06F0, 0x0038, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x06F0, 0x003C, iwl9560_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x06F0, 0x0038, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0x06F0, 0x003C, iwl9560_2ac_160_cfg_soc)}, {IWL_PCI_DEVICE(0x06F0, 0x0060, iwl9461_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x06F0, 0x0064, iwl9461_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x06F0, 0x00A0, iwl9462_2ac_cfg_soc)}, @@ -556,20 +556,21 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x06F0, 0x02A4, iwl9462_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x06F0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x06F0, 0x1552, iwl9560_killer_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x06F0, 0x2030, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x06F0, 0x2034, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x06F0, 0x4030, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x06F0, 0x4034, iwl9560_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x06F0, 0x2030, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0x06F0, 0x2034, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0x06F0, 0x4030, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0x06F0, 0x4034, iwl9560_2ac_160_cfg_soc)}, {IWL_PCI_DEVICE(0x06F0, 0x40A4, iwl9462_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x06F0, 0x4234, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x06F0, 0x42A4, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x2526, 0x0010, iwl9260_2ac_cfg)}, - {IWL_PCI_DEVICE(0x2526, 0x0014, iwl9260_2ac_cfg)}, - {IWL_PCI_DEVICE(0x2526, 0x0018, iwl9260_2ac_cfg)}, - {IWL_PCI_DEVICE(0x2526, 0x0030, iwl9560_2ac_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x0010, iwl9260_2ac_160_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x0014, iwl9260_2ac_160_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x0018, iwl9260_2ac_160_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x001C, iwl9260_2ac_160_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x0030, iwl9560_2ac_160_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x0034, iwl9560_2ac_cfg)}, - {IWL_PCI_DEVICE(0x2526, 0x0038, iwl9560_2ac_cfg)}, - {IWL_PCI_DEVICE(0x2526, 0x003C, iwl9560_2ac_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x0038, iwl9560_2ac_160_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x003C, iwl9560_2ac_160_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x0060, iwl9460_2ac_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x0064, iwl9460_2ac_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x00A0, iwl9460_2ac_cfg)}, @@ -593,24 +594,26 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x2526, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2526, 0x1552, iwl9560_killer_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2526, 0x1610, iwl9270_2ac_cfg)}, - {IWL_PCI_DEVICE(0x2526, 0x2030, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x2526, 0x2034, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x2526, 0x4010, iwl9260_2ac_cfg)}, - {IWL_PCI_DEVICE(0x2526, 0x4030, iwl9560_2ac_cfg)}, - {IWL_PCI_DEVICE(0x2526, 0x4034, iwl9560_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x2526, 0x2030, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0x2526, 0x2034, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0x2526, 0x4010, iwl9260_2ac_160_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x401C, iwl9260_2ac_160_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x4030, iwl9560_2ac_160_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x4034, iwl9560_2ac_160_cfg_soc)}, {IWL_PCI_DEVICE(0x2526, 0x40A4, iwl9460_2ac_cfg)}, {IWL_PCI_DEVICE(0x2526, 0x4234, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2526, 0x42A4, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x2526, 0x8014, iwl9260_2ac_cfg)}, - {IWL_PCI_DEVICE(0x2526, 0xA014, iwl9260_2ac_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x8014, iwl9260_2ac_160_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0x8010, iwl9260_2ac_160_cfg)}, + {IWL_PCI_DEVICE(0x2526, 0xA014, iwl9260_2ac_160_cfg)}, {IWL_PCI_DEVICE(0x271B, 0x0010, iwl9160_2ac_cfg)}, {IWL_PCI_DEVICE(0x271B, 0x0014, iwl9160_2ac_cfg)}, {IWL_PCI_DEVICE(0x271B, 0x0210, iwl9160_2ac_cfg)}, {IWL_PCI_DEVICE(0x271B, 0x0214, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x271C, 0x0214, iwl9260_2ac_cfg)}, - {IWL_PCI_DEVICE(0x2720, 0x0034, iwl9560_2ac_cfg)}, - {IWL_PCI_DEVICE(0x2720, 0x0038, iwl9560_2ac_cfg)}, - {IWL_PCI_DEVICE(0x2720, 0x003C, iwl9560_2ac_cfg)}, + {IWL_PCI_DEVICE(0x2720, 0x0034, iwl9560_2ac_160_cfg)}, + {IWL_PCI_DEVICE(0x2720, 0x0038, iwl9560_2ac_160_cfg)}, + {IWL_PCI_DEVICE(0x2720, 0x003C, iwl9560_2ac_160_cfg)}, {IWL_PCI_DEVICE(0x2720, 0x0060, iwl9461_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2720, 0x0064, iwl9461_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2720, 0x00A0, iwl9462_2ac_cfg_soc)}, @@ -628,17 +631,17 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x2720, 0x1210, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x2720, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2720, 0x1552, iwl9560_killer_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x2720, 0x2030, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x2720, 0x2034, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x2720, 0x4030, iwl9560_2ac_cfg)}, - {IWL_PCI_DEVICE(0x2720, 0x4034, iwl9560_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x2720, 0x2030, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0x2720, 0x2034, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0x2720, 0x4030, iwl9560_2ac_160_cfg)}, + {IWL_PCI_DEVICE(0x2720, 0x4034, iwl9560_2ac_160_cfg_soc)}, {IWL_PCI_DEVICE(0x2720, 0x40A4, iwl9462_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2720, 0x4234, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x2720, 0x42A4, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x30DC, 0x0030, iwl9560_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x30DC, 0x0030, iwl9560_2ac_160_cfg_soc)}, {IWL_PCI_DEVICE(0x30DC, 0x0034, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x30DC, 0x0038, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x30DC, 0x003C, iwl9560_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x30DC, 0x0038, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0x30DC, 0x003C, iwl9560_2ac_160_cfg_soc)}, {IWL_PCI_DEVICE(0x30DC, 0x0060, iwl9460_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x30DC, 0x0064, iwl9461_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x30DC, 0x00A0, iwl9462_2ac_cfg_soc)}, @@ -656,17 +659,17 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x30DC, 0x1210, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x30DC, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x30DC, 0x1552, iwl9560_killer_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x30DC, 0x2030, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x30DC, 0x2034, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x30DC, 0x4030, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x30DC, 0x4034, iwl9560_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x30DC, 0x2030, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0x30DC, 0x2034, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0x30DC, 0x4030, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0x30DC, 0x4034, iwl9560_2ac_160_cfg_soc)}, {IWL_PCI_DEVICE(0x30DC, 0x40A4, iwl9462_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x30DC, 0x4234, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x30DC, 0x42A4, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x31DC, 0x0030, iwl9560_2ac_cfg_shared_clk)}, + {IWL_PCI_DEVICE(0x31DC, 0x0030, iwl9560_2ac_160_cfg_shared_clk)}, {IWL_PCI_DEVICE(0x31DC, 0x0034, iwl9560_2ac_cfg_shared_clk)}, - {IWL_PCI_DEVICE(0x31DC, 0x0038, iwl9560_2ac_cfg_shared_clk)}, - {IWL_PCI_DEVICE(0x31DC, 0x003C, iwl9560_2ac_cfg_shared_clk)}, + {IWL_PCI_DEVICE(0x31DC, 0x0038, iwl9560_2ac_160_cfg_shared_clk)}, + {IWL_PCI_DEVICE(0x31DC, 0x003C, iwl9560_2ac_160_cfg_shared_clk)}, {IWL_PCI_DEVICE(0x31DC, 0x0060, iwl9460_2ac_cfg_shared_clk)}, {IWL_PCI_DEVICE(0x31DC, 0x0064, iwl9461_2ac_cfg_shared_clk)}, {IWL_PCI_DEVICE(0x31DC, 0x00A0, iwl9462_2ac_cfg_shared_clk)}, @@ -684,18 +687,18 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x31DC, 0x1210, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x31DC, 0x1551, iwl9560_killer_s_2ac_cfg_shared_clk)}, {IWL_PCI_DEVICE(0x31DC, 0x1552, iwl9560_killer_2ac_cfg_shared_clk)}, - {IWL_PCI_DEVICE(0x31DC, 0x2030, iwl9560_2ac_cfg_shared_clk)}, - {IWL_PCI_DEVICE(0x31DC, 0x2034, iwl9560_2ac_cfg_shared_clk)}, - {IWL_PCI_DEVICE(0x31DC, 0x4030, iwl9560_2ac_cfg_shared_clk)}, - {IWL_PCI_DEVICE(0x31DC, 0x4034, iwl9560_2ac_cfg_shared_clk)}, + {IWL_PCI_DEVICE(0x31DC, 0x2030, iwl9560_2ac_160_cfg_shared_clk)}, + {IWL_PCI_DEVICE(0x31DC, 0x2034, iwl9560_2ac_160_cfg_shared_clk)}, + {IWL_PCI_DEVICE(0x31DC, 0x4030, iwl9560_2ac_160_cfg_shared_clk)}, + {IWL_PCI_DEVICE(0x31DC, 0x4034, iwl9560_2ac_160_cfg_shared_clk)}, {IWL_PCI_DEVICE(0x31DC, 0x40A4, iwl9462_2ac_cfg_shared_clk)}, {IWL_PCI_DEVICE(0x31DC, 0x4234, iwl9560_2ac_cfg_shared_clk)}, {IWL_PCI_DEVICE(0x31DC, 0x42A4, iwl9462_2ac_cfg_shared_clk)}, - {IWL_PCI_DEVICE(0x34F0, 0x0030, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x34F0, 0x0030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, {IWL_PCI_DEVICE(0x34F0, 0x0034, iwl9560_2ac_cfg_qu_b0_jf_b0)}, - {IWL_PCI_DEVICE(0x34F0, 0x0038, iwl9560_2ac_cfg_qu_b0_jf_b0)}, - {IWL_PCI_DEVICE(0x34F0, 0x003C, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x34F0, 0x0038, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x34F0, 0x003C, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, {IWL_PCI_DEVICE(0x34F0, 0x0060, iwl9461_2ac_cfg_qu_b0_jf_b0)}, {IWL_PCI_DEVICE(0x34F0, 0x0064, iwl9461_2ac_cfg_qu_b0_jf_b0)}, {IWL_PCI_DEVICE(0x34F0, 0x00A0, iwl9462_2ac_cfg_qu_b0_jf_b0)}, @@ -710,18 +713,18 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x34F0, 0x02A4, iwl9462_2ac_cfg_qu_b0_jf_b0)}, {IWL_PCI_DEVICE(0x34F0, 0x1551, killer1550s_2ac_cfg_qu_b0_jf_b0)}, {IWL_PCI_DEVICE(0x34F0, 0x1552, killer1550i_2ac_cfg_qu_b0_jf_b0)}, - {IWL_PCI_DEVICE(0x34F0, 0x2030, iwl9560_2ac_cfg_qu_b0_jf_b0)}, - {IWL_PCI_DEVICE(0x34F0, 0x2034, iwl9560_2ac_cfg_qu_b0_jf_b0)}, - {IWL_PCI_DEVICE(0x34F0, 0x4030, iwl9560_2ac_cfg_qu_b0_jf_b0)}, - {IWL_PCI_DEVICE(0x34F0, 0x4034, iwl9560_2ac_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x34F0, 0x2030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x34F0, 0x2034, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x34F0, 0x4030, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, + {IWL_PCI_DEVICE(0x34F0, 0x4034, iwl9560_2ac_160_cfg_qu_b0_jf_b0)}, {IWL_PCI_DEVICE(0x34F0, 0x40A4, iwl9462_2ac_cfg_qu_b0_jf_b0)}, {IWL_PCI_DEVICE(0x34F0, 0x4234, iwl9560_2ac_cfg_qu_b0_jf_b0)}, {IWL_PCI_DEVICE(0x34F0, 0x42A4, iwl9462_2ac_cfg_qu_b0_jf_b0)}, - {IWL_PCI_DEVICE(0x3DF0, 0x0030, iwl9560_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x3DF0, 0x0030, iwl9560_2ac_160_cfg_soc)}, {IWL_PCI_DEVICE(0x3DF0, 0x0034, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x3DF0, 0x0038, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x3DF0, 0x003C, iwl9560_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x3DF0, 0x0038, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0x3DF0, 0x003C, iwl9560_2ac_160_cfg_soc)}, {IWL_PCI_DEVICE(0x3DF0, 0x0060, iwl9461_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x3DF0, 0x0064, iwl9461_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x3DF0, 0x00A0, iwl9462_2ac_cfg_soc)}, @@ -739,17 +742,17 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x3DF0, 0x1210, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x3DF0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x3DF0, 0x1552, iwl9560_killer_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x3DF0, 0x2030, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x3DF0, 0x2034, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x3DF0, 0x4030, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x3DF0, 0x4034, iwl9560_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x3DF0, 0x2030, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0x3DF0, 0x2034, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0x3DF0, 0x4030, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0x3DF0, 0x4034, iwl9560_2ac_160_cfg_soc)}, {IWL_PCI_DEVICE(0x3DF0, 0x40A4, iwl9462_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x3DF0, 0x4234, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x3DF0, 0x42A4, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x43F0, 0x0030, iwl9560_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x43F0, 0x0030, iwl9560_2ac_160_cfg_soc)}, {IWL_PCI_DEVICE(0x43F0, 0x0034, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x43F0, 0x0038, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x43F0, 0x003C, iwl9560_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x43F0, 0x0038, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0x43F0, 0x003C, iwl9560_2ac_160_cfg_soc)}, {IWL_PCI_DEVICE(0x43F0, 0x0060, iwl9461_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x43F0, 0x0064, iwl9461_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x43F0, 0x00A0, iwl9462_2ac_cfg_soc)}, @@ -767,19 +770,19 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x43F0, 0x1210, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0x43F0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x43F0, 0x1552, iwl9560_killer_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x43F0, 0x2030, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x43F0, 0x2034, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x43F0, 0x4030, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x43F0, 0x4034, iwl9560_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x43F0, 0x2030, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0x43F0, 0x2034, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0x43F0, 0x4030, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0x43F0, 0x4034, iwl9560_2ac_160_cfg_soc)}, {IWL_PCI_DEVICE(0x43F0, 0x40A4, iwl9462_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x43F0, 0x4234, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x43F0, 0x42A4, iwl9462_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x9DF0, 0x0000, iwl9460_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x9DF0, 0x0010, iwl9460_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x9DF0, 0x0030, iwl9560_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x9DF0, 0x0030, iwl9560_2ac_160_cfg_soc)}, {IWL_PCI_DEVICE(0x9DF0, 0x0034, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x9DF0, 0x0038, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x9DF0, 0x003C, iwl9560_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x9DF0, 0x0038, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0x9DF0, 0x003C, iwl9560_2ac_160_cfg_soc)}, {IWL_PCI_DEVICE(0x9DF0, 0x0060, iwl9460_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x9DF0, 0x0064, iwl9461_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x9DF0, 0x00A0, iwl9462_2ac_cfg_soc)}, @@ -805,18 +808,18 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0x9DF0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x9DF0, 0x1552, iwl9560_killer_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x9DF0, 0x2010, iwl9460_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x9DF0, 0x2030, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x9DF0, 0x2034, iwl9560_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x9DF0, 0x2030, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0x9DF0, 0x2034, iwl9560_2ac_160_cfg_soc)}, {IWL_PCI_DEVICE(0x9DF0, 0x2A10, iwl9460_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x9DF0, 0x4030, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0x9DF0, 0x4034, iwl9560_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0x9DF0, 0x4030, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0x9DF0, 0x4034, iwl9560_2ac_160_cfg_soc)}, {IWL_PCI_DEVICE(0x9DF0, 0x40A4, iwl9462_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x9DF0, 0x4234, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0x9DF0, 0x42A4, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0xA0F0, 0x0030, iwl9560_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0xA0F0, 0x0030, iwl9560_2ac_160_cfg_soc)}, {IWL_PCI_DEVICE(0xA0F0, 0x0034, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0xA0F0, 0x0038, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0xA0F0, 0x003C, iwl9560_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0xA0F0, 0x0038, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0xA0F0, 0x003C, iwl9560_2ac_160_cfg_soc)}, {IWL_PCI_DEVICE(0xA0F0, 0x0060, iwl9461_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0xA0F0, 0x0064, iwl9461_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0xA0F0, 0x00A0, iwl9462_2ac_cfg_soc)}, @@ -834,17 +837,17 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0xA0F0, 0x1210, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0xA0F0, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0xA0F0, 0x1552, iwl9560_killer_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0xA0F0, 0x2030, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0xA0F0, 0x2034, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0xA0F0, 0x4030, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0xA0F0, 0x4034, iwl9560_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0xA0F0, 0x2030, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0xA0F0, 0x2034, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0xA0F0, 0x4030, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0xA0F0, 0x4034, iwl9560_2ac_160_cfg_soc)}, {IWL_PCI_DEVICE(0xA0F0, 0x40A4, iwl9462_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0xA0F0, 0x4234, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0xA0F0, 0x42A4, iwl9462_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0xA370, 0x0030, iwl9560_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0xA370, 0x0030, iwl9560_2ac_160_cfg_soc)}, {IWL_PCI_DEVICE(0xA370, 0x0034, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0xA370, 0x0038, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0xA370, 0x003C, iwl9560_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0xA370, 0x0038, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0xA370, 0x003C, iwl9560_2ac_160_cfg_soc)}, {IWL_PCI_DEVICE(0xA370, 0x0060, iwl9460_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0xA370, 0x0064, iwl9461_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0xA370, 0x00A0, iwl9462_2ac_cfg_soc)}, @@ -862,41 +865,88 @@ static const struct pci_device_id iwl_hw_card_ids[] = { {IWL_PCI_DEVICE(0xA370, 0x1210, iwl9260_2ac_cfg)}, {IWL_PCI_DEVICE(0xA370, 0x1551, iwl9560_killer_s_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0xA370, 0x1552, iwl9560_killer_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0xA370, 0x2030, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0xA370, 0x2034, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0xA370, 0x4030, iwl9560_2ac_cfg_soc)}, - {IWL_PCI_DEVICE(0xA370, 0x4034, iwl9560_2ac_cfg_soc)}, + {IWL_PCI_DEVICE(0xA370, 0x2030, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0xA370, 0x2034, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0xA370, 0x4030, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0xA370, 0x4034, iwl9560_2ac_160_cfg_soc)}, {IWL_PCI_DEVICE(0xA370, 0x40A4, iwl9462_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0xA370, 0x4234, iwl9560_2ac_cfg_soc)}, {IWL_PCI_DEVICE(0xA370, 0x42A4, iwl9462_2ac_cfg_soc)}, /* 22000 Series */ - {IWL_PCI_DEVICE(0x2720, 0x0000, iwl22000_2ax_cfg_hr)}, - {IWL_PCI_DEVICE(0x2720, 0x0040, iwl22000_2ax_cfg_hr)}, - {IWL_PCI_DEVICE(0x2720, 0x0078, iwl22000_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0x02F0, 0x0070, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0x02F0, 0x0074, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0x02F0, 0x0078, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0x02F0, 0x007C, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0x02F0, 0x0310, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0x02F0, 0x1651, killer1650s_2ax_cfg_qu_b0_hr_b0)}, + {IWL_PCI_DEVICE(0x02F0, 0x1652, killer1650i_2ax_cfg_qu_b0_hr_b0)}, + {IWL_PCI_DEVICE(0x02F0, 0x4070, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0x06F0, 0x0070, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0x06F0, 0x0074, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0x06F0, 0x0078, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0x06F0, 0x007C, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0x06F0, 0x0310, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0x06F0, 0x1651, killer1650s_2ax_cfg_qu_b0_hr_b0)}, + {IWL_PCI_DEVICE(0x06F0, 0x1652, killer1650i_2ax_cfg_qu_b0_hr_b0)}, + {IWL_PCI_DEVICE(0x06F0, 0x4070, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0x2720, 0x0000, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0x2720, 0x0030, iwl9560_2ac_160_cfg_soc)}, + {IWL_PCI_DEVICE(0x2720, 0x0040, iwl22560_2ax_cfg_hr)}, {IWL_PCI_DEVICE(0x2720, 0x0070, iwl22000_2ac_cfg_hr_cdb)}, - {IWL_PCI_DEVICE(0x2720, 0x0030, iwl22000_2ac_cfg_hr_cdb)}, - {IWL_PCI_DEVICE(0x2720, 0x1080, iwl22000_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0x2720, 0x0074, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0x2720, 0x0078, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0x2720, 0x007C, iwl22560_2ax_cfg_hr)}, {IWL_PCI_DEVICE(0x2720, 0x0090, iwl22000_2ac_cfg_hr_cdb)}, {IWL_PCI_DEVICE(0x2720, 0x0310, iwl22000_2ac_cfg_hr_cdb)}, - {IWL_PCI_DEVICE(0x34F0, 0x0040, iwl22000_2ax_cfg_hr)}, - {IWL_PCI_DEVICE(0x34F0, 0x0070, iwl22000_2ax_cfg_hr)}, - {IWL_PCI_DEVICE(0x34F0, 0x0078, iwl22000_2ax_cfg_hr)}, - {IWL_PCI_DEVICE(0x34F0, 0x0310, iwl22000_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0x2720, 0x0A10, iwl22000_2ac_cfg_hr_cdb)}, + {IWL_PCI_DEVICE(0x2720, 0x1080, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0x2720, 0x1651, killer1650s_2ax_cfg_qu_b0_hr_b0)}, + {IWL_PCI_DEVICE(0x2720, 0x1652, killer1650i_2ax_cfg_qu_b0_hr_b0)}, + {IWL_PCI_DEVICE(0x2720, 0x4070, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0x34F0, 0x0040, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0x34F0, 0x0070, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0x34F0, 0x0074, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0x34F0, 0x0078, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0x34F0, 0x007C, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0x34F0, 0x0310, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0x34F0, 0x1651, killer1650s_2ax_cfg_qu_b0_hr_b0)}, + {IWL_PCI_DEVICE(0x34F0, 0x1652, killer1650i_2ax_cfg_qu_b0_hr_b0)}, + {IWL_PCI_DEVICE(0x34F0, 0x4070, iwl22560_2ax_cfg_hr)}, {IWL_PCI_DEVICE(0x40C0, 0x0000, iwl22560_2ax_cfg_su_cdb)}, {IWL_PCI_DEVICE(0x40C0, 0x0010, iwl22560_2ax_cfg_su_cdb)}, {IWL_PCI_DEVICE(0x40c0, 0x0090, iwl22560_2ax_cfg_su_cdb)}, {IWL_PCI_DEVICE(0x40C0, 0x0310, iwl22560_2ax_cfg_su_cdb)}, {IWL_PCI_DEVICE(0x40C0, 0x0A10, iwl22560_2ax_cfg_su_cdb)}, - {IWL_PCI_DEVICE(0x43F0, 0x0040, iwl22000_2ax_cfg_hr)}, - {IWL_PCI_DEVICE(0x43F0, 0x0070, iwl22000_2ax_cfg_hr)}, - {IWL_PCI_DEVICE(0x43F0, 0x0078, iwl22000_2ax_cfg_hr)}, - {IWL_PCI_DEVICE(0xA0F0, 0x0000, iwl22000_2ax_cfg_hr)}, - {IWL_PCI_DEVICE(0xA0F0, 0x0040, iwl22000_2ax_cfg_hr)}, - {IWL_PCI_DEVICE(0xA0F0, 0x0070, iwl22000_2ax_cfg_hr)}, - {IWL_PCI_DEVICE(0xA0F0, 0x0078, iwl22000_2ax_cfg_hr)}, - {IWL_PCI_DEVICE(0xA0F0, 0x00B0, iwl22000_2ax_cfg_hr)}, - {IWL_PCI_DEVICE(0xA0F0, 0x0A10, iwl22000_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0x43F0, 0x0040, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0x43F0, 0x0070, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0x43F0, 0x0074, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0x43F0, 0x0078, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0x43F0, 0x007C, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0x43F0, 0x1651, killer1650s_2ax_cfg_qu_b0_hr_b0)}, + {IWL_PCI_DEVICE(0x43F0, 0x1652, killer1650i_2ax_cfg_qu_b0_hr_b0)}, + {IWL_PCI_DEVICE(0x43F0, 0x4070, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0xA0F0, 0x0000, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0xA0F0, 0x0040, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0xA0F0, 0x0070, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0xA0F0, 0x0074, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0xA0F0, 0x0078, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0xA0F0, 0x007C, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0xA0F0, 0x00B0, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0xA0F0, 0x0A10, iwl22560_2ax_cfg_hr)}, + {IWL_PCI_DEVICE(0xA0F0, 0x1651, killer1650s_2ax_cfg_qu_b0_hr_b0)}, + {IWL_PCI_DEVICE(0xA0F0, 0x1652, killer1650i_2ax_cfg_qu_b0_hr_b0)}, + {IWL_PCI_DEVICE(0xA0F0, 0x4070, iwl22560_2ax_cfg_hr)}, + + {IWL_PCI_DEVICE(0x2723, 0x0080, iwl22260_2ax_cfg)}, + {IWL_PCI_DEVICE(0x2723, 0x0084, iwl22260_2ax_cfg)}, + {IWL_PCI_DEVICE(0x2723, 0x0088, iwl22260_2ax_cfg)}, + {IWL_PCI_DEVICE(0x2723, 0x008C, iwl22260_2ax_cfg)}, + {IWL_PCI_DEVICE(0x2723, 0x4080, iwl22260_2ax_cfg)}, + {IWL_PCI_DEVICE(0x2723, 0x4088, iwl22260_2ax_cfg)}, + + {IWL_PCI_DEVICE(0x1a56, 0x1653, killer1650w_2ax_cfg)}, + {IWL_PCI_DEVICE(0x1a56, 0x1654, killer1650x_2ax_cfg)}, #endif /* CONFIG_IWLMVM */ diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h index d6fc6ce73e0a..0d16bcc3141f 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h +++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h @@ -1,13 +1,15 @@ /****************************************************************************** * + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * * Copyright(c) 2003 - 2015 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH * Copyright(c) 2016 - 2017 Intel Deutschland GmbH * Copyright(c) 2018 Intel Corporation * - * Portions of this file are derived from the ipw3945 project, as well - * as portions of the ieee80211 subsystem header files. - * * This program is free software; you can redistribute it and/or modify it * under the terms of version 2 of the GNU General Public License as * published by the Free Software Foundation. @@ -18,12 +20,46 @@ * more details. * * The full GNU General Public License is included in this distribution in the - * file called LICENSE. + * file called COPYING. * * Contact Information: * Intel Linux Wireless <linuxwifi@intel.com> * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 * + * BSD LICENSE + * + * Copyright(c) 2003 - 2015 Intel Corporation. All rights reserved. + * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH + * Copyright(c) 2016 - 2017 Intel Deutschland GmbH + * Copyright(c) 2018 Intel Corporation + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * *****************************************************************************/ #ifndef __iwl_trans_int_pcie_h__ #define __iwl_trans_int_pcie_h__ @@ -1029,8 +1065,6 @@ static inline int iwl_trans_pcie_dbgfs_register(struct iwl_trans *trans) int iwl_pci_fw_exit_d0i3(struct iwl_trans *trans); int iwl_pci_fw_enter_d0i3(struct iwl_trans *trans); -void iwl_pcie_enable_rx_wake(struct iwl_trans *trans, bool enable); - void iwl_pcie_rx_allocator_work(struct work_struct *data); /* common functions that are used by gen2 transport */ diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c index 9e850c25877b..c260d1251b5f 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c @@ -1,13 +1,15 @@ /****************************************************************************** * + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * * Copyright(c) 2003 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH * Copyright(c) 2016 - 2017 Intel Deutschland GmbH * Copyright(c) 2018 Intel Corporation * - * Portions of this file are derived from the ipw3945 project, as well - * as portions of the ieee80211 subsystem header files. - * * This program is free software; you can redistribute it and/or modify it * under the terms of version 2 of the GNU General Public License as * published by the Free Software Foundation. @@ -18,12 +20,46 @@ * more details. * * The full GNU General Public License is included in this distribution in the - * file called LICENSE. + * file called COPYING. * * Contact Information: * Intel Linux Wireless <linuxwifi@intel.com> * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 * + * BSD LICENSE + * + * Copyright(c) 2003 - 2014 Intel Corporation. All rights reserved. + * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH + * Copyright(c) 2016 - 2017 Intel Deutschland GmbH + * Copyright(c) 2018 Intel Corporation + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * *****************************************************************************/ #include <linux/sched.h> #include <linux/wait.h> @@ -256,6 +292,9 @@ static void iwl_pcie_restock_bd(struct iwl_trans *trans, bd[rxq->write] = cpu_to_le64(rxb->page_dma | rxb->vid); } + + IWL_DEBUG_RX(trans, "Assigned virtual RB ID %u to queue %d index %d\n", + (u32)rxb->vid, rxq->id, rxq->write); } /* @@ -860,30 +899,6 @@ static void iwl_pcie_rx_hw_init(struct iwl_trans *trans, struct iwl_rxq *rxq) iwl_set_bit(trans, CSR_INT_COALESCING, IWL_HOST_INT_OPER_MODE); } -void iwl_pcie_enable_rx_wake(struct iwl_trans *trans, bool enable) -{ - if (trans->cfg->device_family != IWL_DEVICE_FAMILY_9000) - return; - - if (CSR_HW_REV_STEP(trans->hw_rev) != SILICON_A_STEP) - return; - - if (!trans->cfg->integrated) - return; - - /* - * Turn on the chicken-bits that cause MAC wakeup for RX-related - * values. - * This costs some power, but needed for W/A 9000 integrated A-step - * bug where shadow registers are not in the retention list and their - * value is lost when NIC powers down - */ - iwl_set_bit(trans, CSR_MAC_SHADOW_REG_CTRL, - CSR_MAC_SHADOW_REG_CTRL_RX_WAKE); - iwl_set_bit(trans, CSR_MAC_SHADOW_REG_CTL2, - CSR_MAC_SHADOW_REG_CTL2_RX_WAKE); -} - static void iwl_pcie_rx_mq_hw_init(struct iwl_trans *trans) { struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); @@ -971,8 +986,6 @@ static void iwl_pcie_rx_mq_hw_init(struct iwl_trans *trans) /* Set interrupt coalescing timer to default (2048 usecs) */ iwl_write8(trans, CSR_INT_COALESCING, IWL_HOST_INT_TIMEOUT_DEF); - - iwl_pcie_enable_rx_wake(trans, true); } void iwl_pcie_rx_init_rxb_lists(struct iwl_rxq *rxq) @@ -1360,6 +1373,8 @@ static struct iwl_rx_mem_buffer *iwl_pcie_get_rxb(struct iwl_trans *trans, if (rxb->invalid) goto out_err; + IWL_DEBUG_RX(trans, "Got virtual RB ID %u\n", (u32)rxb->vid); + if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560) rxb->size = le32_to_cpu(rxq->cd[i].size) & IWL_RX_CD_SIZE; @@ -1411,11 +1426,12 @@ restart: emergency = true; } + IWL_DEBUG_RX(trans, "Q %d: HW = %d, SW = %d\n", rxq->id, r, i); + rxb = iwl_pcie_get_rxb(trans, rxq, i); if (!rxb) goto out; - IWL_DEBUG_RX(trans, "Q %d: HW = %d, SW = %d\n", rxq->id, r, i); iwl_pcie_rx_handle_rb(trans, rxq, rxb, emergency, i); i = (i + 1) & (rxq->queue_size - 1); diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c index f97aea5ffc44..f74281508197 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c @@ -1530,8 +1530,6 @@ static void iwl_trans_pcie_d3_suspend(struct iwl_trans *trans, bool test, iwl_clear_bit(trans, CSR_GP_CNTRL, BIT(trans->cfg->csr->flag_init_done)); - iwl_pcie_enable_rx_wake(trans, false); - if (reset) { /* * reset TX queues -- some of their registers reset during S3 @@ -1558,8 +1556,6 @@ static int iwl_trans_pcie_d3_resume(struct iwl_trans *trans, return 0; } - iwl_pcie_enable_rx_wake(trans, true); - iwl_set_bit(trans, CSR_GP_CNTRL, BIT(trans->cfg->csr->flag_mac_access_req)); iwl_set_bit(trans, CSR_GP_CNTRL, @@ -1968,7 +1964,7 @@ static void iwl_trans_pcie_removal_wk(struct work_struct *wk) struct iwl_trans_pcie_removal *removal = container_of(wk, struct iwl_trans_pcie_removal, work); struct pci_dev *pdev = removal->pdev; - char *prop[] = {"EVENT=INACCESSIBLE", NULL}; + static char *prop[] = {"EVENT=INACCESSIBLE", NULL}; dev_err(&pdev->dev, "Device gone - attempting removal\n"); kobject_uevent_env(&pdev->dev.kobj, KOBJ_CHANGE, prop); @@ -3118,7 +3114,7 @@ iwl_trans_pcie_dump_monitor(struct iwl_trans *trans, return len; } -static int iwl_trans_get_fw_monitor_len(struct iwl_trans *trans, int *len) +static int iwl_trans_get_fw_monitor_len(struct iwl_trans *trans, u32 *len) { if (trans->num_blocks) { *len += sizeof(struct iwl_fw_error_dump_data) + @@ -3173,8 +3169,7 @@ static struct iwl_trans_dump_data struct iwl_txq *cmdq = trans_pcie->txq[trans_pcie->cmd_queue]; struct iwl_fw_error_dump_txcmd *txcmd; struct iwl_trans_dump_data *dump_data; - u32 len, num_rbs = 0; - u32 monitor_len; + u32 len, num_rbs = 0, monitor_len = 0; int i, ptr; bool dump_rbs = test_bit(STATUS_FW_ERROR, &trans->status) && !trans->cfg->mq_rx_supported && @@ -3191,19 +3186,8 @@ static struct iwl_trans_dump_data cmdq->n_window * (sizeof(*txcmd) + TFD_MAX_PAYLOAD_SIZE); /* FW monitor */ - monitor_len = iwl_trans_get_fw_monitor_len(trans, &len); - - if (dump_mask == BIT(IWL_FW_ERROR_DUMP_FW_MONITOR)) { - dump_data = vzalloc(len); - if (!dump_data) - return NULL; - - data = (void *)dump_data->data; - len = iwl_trans_pcie_dump_monitor(trans, &data, monitor_len); - dump_data->len = len; - - return dump_data; - } + if (dump_mask & BIT(IWL_FW_ERROR_DUMP_FW_MONITOR)) + monitor_len = iwl_trans_get_fw_monitor_len(trans, &len); /* CSR registers */ if (dump_mask & BIT(IWL_FW_ERROR_DUMP_CSR)) @@ -3569,24 +3553,15 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev, } } - /* - * 9000-series integrated A-step has a problem with suspend/resume - * and sometimes even causes the whole platform to get stuck. This - * workaround makes the hardware not go into the problematic state. - */ - if (trans->cfg->integrated && - trans->cfg->device_family == IWL_DEVICE_FAMILY_9000 && - CSR_HW_REV_STEP(trans->hw_rev) == SILICON_A_STEP) - iwl_set_bit(trans, CSR_HOST_CHICKEN, - CSR_HOST_CHICKEN_PM_IDLE_SRC_DIS_SB_PME); + IWL_DEBUG_INFO(trans, "HW REV: 0x%0x\n", trans->hw_rev); #if IS_ENABLED(CONFIG_IWLMVM) trans->hw_rf_id = iwl_read32(trans, CSR_HW_RF_ID); - if (cfg == &iwl22000_2ax_cfg_hr) { + if (cfg == &iwl22560_2ax_cfg_hr) { if (CSR_HW_RF_ID_TYPE_CHIP_ID(trans->hw_rf_id) == CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_HR)) { - trans->cfg = &iwl22000_2ax_cfg_hr; + trans->cfg = &iwl22560_2ax_cfg_hr; } else if (CSR_HW_RF_ID_TYPE_CHIP_ID(trans->hw_rf_id) == CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_JF)) { trans->cfg = &iwl22000_2ax_cfg_jf; @@ -3602,7 +3577,9 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev, goto out_no_pci; } } else if (CSR_HW_RF_ID_TYPE_CHIP_ID(trans->hw_rf_id) == - CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_HR)) { + CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_HR) && + (trans->cfg != &iwl22260_2ax_cfg || + trans->hw_rev == CSR_HW_REV_TYPE_QNJ_B0)) { u32 hw_status; hw_status = iwl_read_prph(trans, UMAG_GEN_HW_STATUS); diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c index 156ca1b1f621..f3d2e8fe920b 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c @@ -214,7 +214,11 @@ static int iwl_pcie_gen2_set_tb(struct iwl_trans *trans, { struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); int idx = iwl_pcie_gen2_get_num_tbs(trans, tfd); - struct iwl_tfh_tb *tb = &tfd->tbs[idx]; + struct iwl_tfh_tb *tb; + + if (WARN_ON(idx >= IWL_TFH_NUM_TBS)) + return -EINVAL; + tb = &tfd->tbs[idx]; /* Each TFD can point to a maximum max_tbs Tx buffers */ if (le16_to_cpu(tfd->num_tbs) >= trans_pcie->max_tbs) { @@ -408,7 +412,7 @@ iwl_tfh_tfd *iwl_pcie_gen2_build_tx_amsdu(struct iwl_trans *trans, goto out_err; /* building the A-MSDU might have changed this data, memcpy it now */ - memcpy(&txq->first_tb_bufs[idx], &dev_cmd->hdr, IWL_FIRST_TB_SIZE); + memcpy(&txq->first_tb_bufs[idx], dev_cmd, IWL_FIRST_TB_SIZE); return tfd; out_err: @@ -469,7 +473,7 @@ iwl_tfh_tfd *iwl_pcie_gen2_build_tx(struct iwl_trans *trans, tb_phys = iwl_pcie_get_first_tb_dma(txq, idx); /* The first TB points to bi-directional DMA data */ - memcpy(&txq->first_tb_bufs[idx], &dev_cmd->hdr, IWL_FIRST_TB_SIZE); + memcpy(&txq->first_tb_bufs[idx], dev_cmd, IWL_FIRST_TB_SIZE); iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, IWL_FIRST_TB_SIZE); @@ -834,14 +838,14 @@ static int iwl_pcie_gen2_enqueue_hcmd(struct iwl_trans *trans, /* start the TFD with the minimum copy bytes */ tb0_size = min_t(int, copy_size, IWL_FIRST_TB_SIZE); - memcpy(&txq->first_tb_bufs[idx], &out_cmd->hdr, tb0_size); + memcpy(&txq->first_tb_bufs[idx], out_cmd, tb0_size); iwl_pcie_gen2_set_tb(trans, tfd, iwl_pcie_get_first_tb_dma(txq, idx), tb0_size); /* map first command fragment, if any remains */ if (copy_size > tb0_size) { phys_addr = dma_map_single(trans->dev, - ((u8 *)&out_cmd->hdr) + tb0_size, + (u8 *)out_cmd + tb0_size, copy_size - tb0_size, DMA_TO_DEVICE); if (dma_mapping_error(trans->dev, phys_addr)) { diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c index ee990a7a5411..07395502f419 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c @@ -1,13 +1,15 @@ /****************************************************************************** * + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * * Copyright(c) 2003 - 2014 Intel Corporation. All rights reserved. * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH * Copyright(c) 2016 - 2017 Intel Deutschland GmbH * Copyright(c) 2018 Intel Corporation * - * Portions of this file are derived from the ipw3945 project, as well - * as portions of the ieee80211 subsystem header files. - * * This program is free software; you can redistribute it and/or modify it * under the terms of version 2 of the GNU General Public License as * published by the Free Software Foundation. @@ -18,12 +20,46 @@ * more details. * * The full GNU General Public License is included in this distribution in the - * file called LICENSE. + * file called COPYING. * * Contact Information: * Intel Linux Wireless <linuxwifi@intel.com> * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 * + * BSD LICENSE + * + * Copyright(c) 2003 - 2014 Intel Corporation. All rights reserved. + * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH + * Copyright(c) 2016 - 2017 Intel Deutschland GmbH + * Copyright(c) 2018 Intel Corporation + * All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * * Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * * Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in + * the documentation and/or other materials provided with the + * distribution. + * * Neither the name Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + * *****************************************************************************/ #include <linux/etherdevice.h> #include <linux/ieee80211.h> @@ -2438,8 +2474,7 @@ int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb, } /* building the A-MSDU might have changed this data, so memcpy it now */ - memcpy(&txq->first_tb_bufs[txq->write_ptr], &dev_cmd->hdr, - IWL_FIRST_TB_SIZE); + memcpy(&txq->first_tb_bufs[txq->write_ptr], dev_cmd, IWL_FIRST_TB_SIZE); tfd = iwl_pcie_get_tfd(trans, txq, txq->write_ptr); /* Set up entry for this TFD in Tx byte-count array */ diff --git a/drivers/net/wireless/marvell/libertas/debugfs.c b/drivers/net/wireless/marvell/libertas/debugfs.c index c83f44f9ddf1..fe14814af300 100644 --- a/drivers/net/wireless/marvell/libertas/debugfs.c +++ b/drivers/net/wireless/marvell/libertas/debugfs.c @@ -708,8 +708,6 @@ void lbs_debugfs_init_one(struct lbs_private *priv, struct net_device *dev) goto exit; priv->debugfs_dir = debugfs_create_dir(dev->name, lbs_dir); - if (!priv->debugfs_dir) - goto exit; for (i=0; i<ARRAY_SIZE(debugfs_files); i++) { files = &debugfs_files[i]; @@ -721,8 +719,6 @@ void lbs_debugfs_init_one(struct lbs_private *priv, struct net_device *dev) } priv->events_dir = debugfs_create_dir("subscribed_events", priv->debugfs_dir); - if (!priv->events_dir) - goto exit; for (i=0; i<ARRAY_SIZE(debugfs_events_files); i++) { files = &debugfs_events_files[i]; @@ -734,8 +730,6 @@ void lbs_debugfs_init_one(struct lbs_private *priv, struct net_device *dev) } priv->regs_dir = debugfs_create_dir("registers", priv->debugfs_dir); - if (!priv->regs_dir) - goto exit; for (i=0; i<ARRAY_SIZE(debugfs_regs_files); i++) { files = &debugfs_regs_files[i]; diff --git a/drivers/net/wireless/marvell/libertas/mesh.c b/drivers/net/wireless/marvell/libertas/mesh.c index b0cb16ef8d1d..2315fdff56c2 100644 --- a/drivers/net/wireless/marvell/libertas/mesh.c +++ b/drivers/net/wireless/marvell/libertas/mesh.c @@ -797,7 +797,12 @@ static void lbs_persist_config_init(struct net_device *dev) { int ret; ret = sysfs_create_group(&(dev->dev.kobj), &boot_opts_group); + if (ret) + pr_err("failed to create boot_opts_group.\n"); + ret = sysfs_create_group(&(dev->dev.kobj), &mesh_ie_group); + if (ret) + pr_err("failed to create mesh_ie_group.\n"); } static void lbs_persist_config_remove(struct net_device *dev) diff --git a/drivers/net/wireless/marvell/libertas_tf/main.c b/drivers/net/wireless/marvell/libertas_tf/main.c index 1d45da187b9b..a7cb7d06e5e6 100644 --- a/drivers/net/wireless/marvell/libertas_tf/main.c +++ b/drivers/net/wireless/marvell/libertas_tf/main.c @@ -676,7 +676,7 @@ int lbtf_remove_card(struct lbtf_private *priv) ieee80211_unregister_hw(hw); ieee80211_free_hw(hw); - lbtf_deb_leave(LBTF_DEB_MAIN); + lbtf_deb_leave(LBTF_DEB_MAIN); return 0; } EXPORT_SYMBOL_GPL(lbtf_remove_card); diff --git a/drivers/net/wireless/marvell/mwifiex/Kconfig b/drivers/net/wireless/marvell/mwifiex/Kconfig index 279167ddd293..524fd565cb2a 100644 --- a/drivers/net/wireless/marvell/mwifiex/Kconfig +++ b/drivers/net/wireless/marvell/mwifiex/Kconfig @@ -9,7 +9,7 @@ config MWIFIEX mwifiex. config MWIFIEX_SDIO - tristate "Marvell WiFi-Ex Driver for SD8786/SD8787/SD8797/SD8887/SD8897/SD8997" + tristate "Marvell WiFi-Ex Driver for SD8786/SD8787/SD8797/SD8887/SD8897/SD8977/SD8997" depends on MWIFIEX && MMC select FW_LOADER select WANT_DEV_COREDUMP diff --git a/drivers/net/wireless/marvell/mwifiex/debugfs.c b/drivers/net/wireless/marvell/mwifiex/debugfs.c index cbe4493b3266..8ab114cf3467 100644 --- a/drivers/net/wireless/marvell/mwifiex/debugfs.c +++ b/drivers/net/wireless/marvell/mwifiex/debugfs.c @@ -922,9 +922,8 @@ mwifiex_reset_write(struct file *file, } #define MWIFIEX_DFS_ADD_FILE(name) do { \ - if (!debugfs_create_file(#name, 0644, priv->dfs_dev_dir, \ - priv, &mwifiex_dfs_##name##_fops)) \ - return; \ + debugfs_create_file(#name, 0644, priv->dfs_dev_dir, priv, \ + &mwifiex_dfs_##name##_fops); \ } while (0); #define MWIFIEX_DFS_FILE_OPS(name) \ diff --git a/drivers/net/wireless/marvell/mwifiex/sdio.c b/drivers/net/wireless/marvell/mwifiex/sdio.c index d49fbd58afa7..a85648342d15 100644 --- a/drivers/net/wireless/marvell/mwifiex/sdio.c +++ b/drivers/net/wireless/marvell/mwifiex/sdio.c @@ -489,6 +489,8 @@ static void mwifiex_sdio_coredump(struct device *dev) #define SDIO_DEVICE_ID_MARVELL_8887 (0x9135) /* Device ID for SD8801 */ #define SDIO_DEVICE_ID_MARVELL_8801 (0x9139) +/* Device ID for SD8977 */ +#define SDIO_DEVICE_ID_MARVELL_8977 (0x9145) /* Device ID for SD8997 */ #define SDIO_DEVICE_ID_MARVELL_8997 (0x9141) @@ -507,6 +509,8 @@ static const struct sdio_device_id mwifiex_ids[] = { .driver_data = (unsigned long)&mwifiex_sdio_sd8887}, {SDIO_DEVICE(SDIO_VENDOR_ID_MARVELL, SDIO_DEVICE_ID_MARVELL_8801), .driver_data = (unsigned long)&mwifiex_sdio_sd8801}, + {SDIO_DEVICE(SDIO_VENDOR_ID_MARVELL, SDIO_DEVICE_ID_MARVELL_8977), + .driver_data = (unsigned long)&mwifiex_sdio_sd8977}, {SDIO_DEVICE(SDIO_VENDOR_ID_MARVELL, SDIO_DEVICE_ID_MARVELL_8997), .driver_data = (unsigned long)&mwifiex_sdio_sd8997}, {}, @@ -2726,4 +2730,5 @@ MODULE_FIRMWARE(SD8787_DEFAULT_FW_NAME); MODULE_FIRMWARE(SD8797_DEFAULT_FW_NAME); MODULE_FIRMWARE(SD8897_DEFAULT_FW_NAME); MODULE_FIRMWARE(SD8887_DEFAULT_FW_NAME); +MODULE_FIRMWARE(SD8977_DEFAULT_FW_NAME); MODULE_FIRMWARE(SD8997_DEFAULT_FW_NAME); diff --git a/drivers/net/wireless/marvell/mwifiex/sdio.h b/drivers/net/wireless/marvell/mwifiex/sdio.h index dccf7fd1aef3..912de2cde8d9 100644 --- a/drivers/net/wireless/marvell/mwifiex/sdio.h +++ b/drivers/net/wireless/marvell/mwifiex/sdio.h @@ -36,6 +36,7 @@ #define SD8897_DEFAULT_FW_NAME "mrvl/sd8897_uapsta.bin" #define SD8887_DEFAULT_FW_NAME "mrvl/sd8887_uapsta.bin" #define SD8801_DEFAULT_FW_NAME "mrvl/sd8801_uapsta.bin" +#define SD8977_DEFAULT_FW_NAME "mrvl/sd8977_uapsta.bin" #define SD8997_DEFAULT_FW_NAME "mrvl/sd8997_uapsta.bin" #define BLOCK_MODE 1 @@ -371,6 +372,59 @@ static const struct mwifiex_sdio_card_reg mwifiex_reg_sd8897 = { 0x59, 0x5c, 0x5d}, }; +static const struct mwifiex_sdio_card_reg mwifiex_reg_sd8977 = { + .start_rd_port = 0, + .start_wr_port = 0, + .base_0_reg = 0xF8, + .base_1_reg = 0xF9, + .poll_reg = 0x5C, + .host_int_enable = UP_LD_HOST_INT_MASK | DN_LD_HOST_INT_MASK | + CMD_PORT_UPLD_INT_MASK | CMD_PORT_DNLD_INT_MASK, + .host_int_rsr_reg = 0x4, + .host_int_status_reg = 0x0C, + .host_int_mask_reg = 0x08, + .status_reg_0 = 0xE8, + .status_reg_1 = 0xE9, + .sdio_int_mask = 0xff, + .data_port_mask = 0xffffffff, + .io_port_0_reg = 0xE4, + .io_port_1_reg = 0xE5, + .io_port_2_reg = 0xE6, + .max_mp_regs = 196, + .rd_bitmap_l = 0x10, + .rd_bitmap_u = 0x11, + .rd_bitmap_1l = 0x12, + .rd_bitmap_1u = 0x13, + .wr_bitmap_l = 0x14, + .wr_bitmap_u = 0x15, + .wr_bitmap_1l = 0x16, + .wr_bitmap_1u = 0x17, + .rd_len_p0_l = 0x18, + .rd_len_p0_u = 0x19, + .card_misc_cfg_reg = 0xd8, + .card_cfg_2_1_reg = 0xd9, + .cmd_rd_len_0 = 0xc0, + .cmd_rd_len_1 = 0xc1, + .cmd_rd_len_2 = 0xc2, + .cmd_rd_len_3 = 0xc3, + .cmd_cfg_0 = 0xc4, + .cmd_cfg_1 = 0xc5, + .cmd_cfg_2 = 0xc6, + .cmd_cfg_3 = 0xc7, + .fw_dump_host_ready = 0xcc, + .fw_dump_ctrl = 0xf0, + .fw_dump_start = 0xf1, + .fw_dump_end = 0xf8, + .func1_dump_reg_start = 0x10, + .func1_dump_reg_end = 0x17, + .func1_scratch_reg = 0xe8, + .func1_spec_reg_num = 13, + .func1_spec_reg_table = {0x08, 0x58, 0x5C, 0x5D, + 0x60, 0x61, 0x62, 0x64, + 0x65, 0x66, 0x68, 0x69, + 0x6a}, +}; + static const struct mwifiex_sdio_card_reg mwifiex_reg_sd8997 = { .start_rd_port = 0, .start_wr_port = 0, @@ -532,6 +586,22 @@ static const struct mwifiex_sdio_device mwifiex_sdio_sd8897 = { .can_ext_scan = true, }; +static const struct mwifiex_sdio_device mwifiex_sdio_sd8977 = { + .firmware = SD8977_DEFAULT_FW_NAME, + .reg = &mwifiex_reg_sd8977, + .max_ports = 32, + .mp_agg_pkt_limit = 16, + .tx_buf_size = MWIFIEX_TX_DATA_BUF_SIZE_4K, + .mp_tx_agg_buf_size = MWIFIEX_MP_AGGR_BUF_SIZE_MAX, + .mp_rx_agg_buf_size = MWIFIEX_MP_AGGR_BUF_SIZE_MAX, + .supports_sdio_new_mode = true, + .has_control_mask = false, + .can_dump_fw = true, + .fw_dump_enh = true, + .can_auto_tdls = false, + .can_ext_scan = true, +}; + static const struct mwifiex_sdio_device mwifiex_sdio_sd8997 = { .firmware = SD8997_DEFAULT_FW_NAME, .reg = &mwifiex_reg_sd8997, diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c index e2ba26378575..e769c8a555dd 100644 --- a/drivers/net/wireless/mediatek/mt76/dma.c +++ b/drivers/net/wireless/mediatek/mt76/dma.c @@ -300,7 +300,7 @@ int mt76_dma_tx_queue_skb(struct mt76_dev *dev, struct mt76_queue *q, if (q->queued + (n + 1) / 2 >= q->ndesc - 1) goto unmap; - return dev->queue_ops->add_buf(dev, q, buf, n, tx_info, skb, t); + return mt76_dma_add_buf(dev, q, buf, n, tx_info, skb, t); unmap: ret = -ENOMEM; @@ -318,7 +318,7 @@ free: EXPORT_SYMBOL_GPL(mt76_dma_tx_queue_skb); static int -mt76_dma_rx_fill(struct mt76_dev *dev, struct mt76_queue *q, bool napi) +mt76_dma_rx_fill(struct mt76_dev *dev, struct mt76_queue *q) { dma_addr_t addr; void *buf; @@ -392,7 +392,7 @@ mt76_dma_rx_reset(struct mt76_dev *dev, enum mt76_rxq_id qid) mt76_dma_rx_cleanup(dev, q); mt76_dma_sync_idx(dev, q); - mt76_dma_rx_fill(dev, q, false); + mt76_dma_rx_fill(dev, q); } static void @@ -417,10 +417,9 @@ mt76_add_fragment(struct mt76_dev *dev, struct mt76_queue *q, void *data, static int mt76_dma_rx_process(struct mt76_dev *dev, struct mt76_queue *q, int budget) { + int len, data_len, done = 0; struct sk_buff *skb; unsigned char *data; - int len; - int done = 0; bool more; while (done < budget) { @@ -430,6 +429,19 @@ mt76_dma_rx_process(struct mt76_dev *dev, struct mt76_queue *q, int budget) if (!data) break; + if (q->rx_head) + data_len = q->buf_size; + else + data_len = SKB_WITH_OVERHEAD(q->buf_size); + + if (data_len < len + q->buf_offset) { + dev_kfree_skb(q->rx_head); + q->rx_head = NULL; + + skb_free_frag(data); + continue; + } + if (q->rx_head) { mt76_add_fragment(dev, q, data, len, more); continue; @@ -440,12 +452,7 @@ mt76_dma_rx_process(struct mt76_dev *dev, struct mt76_queue *q, int budget) skb_free_frag(data); continue; } - skb_reserve(skb, q->buf_offset); - if (skb->tail + len > skb->end) { - dev_kfree_skb(skb); - continue; - } if (q == &dev->q_rx[MT_RXQ_MCU]) { u32 *rxfce = (u32 *) skb->cb; @@ -463,7 +470,7 @@ mt76_dma_rx_process(struct mt76_dev *dev, struct mt76_queue *q, int budget) dev->drv->rx_skb(dev, q - dev->q_rx, skb); } - mt76_dma_rx_fill(dev, q, true); + mt76_dma_rx_fill(dev, q); return done; } @@ -504,7 +511,7 @@ mt76_dma_init(struct mt76_dev *dev) for (i = 0; i < ARRAY_SIZE(dev->q_rx); i++) { netif_napi_add(&dev->napi_dev, &dev->napi[i], mt76_dma_rx_poll, 64); - mt76_dma_rx_fill(dev, &dev->q_rx[i], false); + mt76_dma_rx_fill(dev, &dev->q_rx[i]); skb_queue_head_init(&dev->rx_skb[i]); napi_enable(&dev->napi[i]); } diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c index 7b926dfa6b97..ee3b65a14870 100644 --- a/drivers/net/wireless/mediatek/mt76/mac80211.c +++ b/drivers/net/wireless/mediatek/mt76/mac80211.c @@ -328,6 +328,7 @@ int mt76_register_device(struct mt76_dev *dev, bool vht, ieee80211_hw_set(hw, MFP_CAPABLE); ieee80211_hw_set(hw, AP_LINK_PS); ieee80211_hw_set(hw, REPORTS_TX_ACK_STATUS); + ieee80211_hw_set(hw, NEEDS_UNIQUE_STA_ADDR); wiphy->flags |= WIPHY_FLAG_IBSS_RSN; @@ -547,7 +548,7 @@ mt76_check_ccmp_pn(struct sk_buff *skb) } static void -mt76_check_ps(struct mt76_dev *dev, struct sk_buff *skb) +mt76_check_sta(struct mt76_dev *dev, struct sk_buff *skb) { struct mt76_rx_status *status = (struct mt76_rx_status *) skb->cb; struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; @@ -566,6 +567,11 @@ mt76_check_ps(struct mt76_dev *dev, struct sk_buff *skb) sta = container_of((void *) wcid, struct ieee80211_sta, drv_priv); + if (status->signal <= 0) + ewma_signal_add(&wcid->rssi, -status->signal); + + wcid->inactive_count = 0; + if (!test_bit(MT_WCID_FLAG_CHECK_PS, &wcid->flags)) return; @@ -625,7 +631,7 @@ void mt76_rx_poll_complete(struct mt76_dev *dev, enum mt76_rxq_id q, __skb_queue_head_init(&frames); while ((skb = __skb_dequeue(&dev->rx_skb[q])) != NULL) { - mt76_check_ps(dev, skb); + mt76_check_sta(dev, skb); mt76_rx_aggr_reorder(skb, &frames); } @@ -659,6 +665,7 @@ mt76_sta_add(struct mt76_dev *dev, struct ieee80211_vif *vif, mt76_txq_init(dev, sta->txq[i]); } + ewma_signal_init(&wcid->rssi); rcu_assign_pointer(dev->wcid[wcid->idx], wcid); out: @@ -709,3 +716,60 @@ int mt76_sta_state(struct ieee80211_hw *hw, struct ieee80211_vif *vif, return 0; } EXPORT_SYMBOL_GPL(mt76_sta_state); + +int mt76_get_txpower(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + int *dbm) +{ + struct mt76_dev *dev = hw->priv; + int n_chains = __sw_hweight8(dev->antenna_mask); + + *dbm = dev->txpower_cur / 2; + + /* convert from per-chain power to combined + * output on 2x2 devices + */ + if (n_chains > 1) + *dbm += 3; + + return 0; +} +EXPORT_SYMBOL_GPL(mt76_get_txpower); + +static void +__mt76_csa_finish(void *priv, u8 *mac, struct ieee80211_vif *vif) +{ + if (vif->csa_active && ieee80211_csa_is_complete(vif)) + ieee80211_csa_finish(vif); +} + +void mt76_csa_finish(struct mt76_dev *dev) +{ + if (!dev->csa_complete) + return; + + ieee80211_iterate_active_interfaces_atomic(dev->hw, + IEEE80211_IFACE_ITER_RESUME_ALL, + __mt76_csa_finish, dev); + + dev->csa_complete = 0; +} +EXPORT_SYMBOL_GPL(mt76_csa_finish); + +static void +__mt76_csa_check(void *priv, u8 *mac, struct ieee80211_vif *vif) +{ + struct mt76_dev *dev = priv; + + if (!vif->csa_active) + return; + + dev->csa_complete |= ieee80211_csa_is_complete(vif); +} + +void mt76_csa_check(struct mt76_dev *dev) +{ + ieee80211_iterate_active_interfaces_atomic(dev->hw, + IEEE80211_IFACE_ITER_RESUME_ALL, + __mt76_csa_check, dev); +} +EXPORT_SYMBOL_GPL(mt76_csa_check); diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h index 5cd508a68609..2bb9db4ed80a 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76.h +++ b/drivers/net/wireless/mediatek/mt76/mt76.h @@ -23,6 +23,7 @@ #include <linux/skbuff.h> #include <linux/leds.h> #include <linux/usb.h> +#include <linux/average.h> #include <net/mac80211.h> #include "util.h" @@ -174,6 +175,8 @@ enum mt76_wcid_flags { #define MT76_N_WCIDS 128 +DECLARE_EWMA(signal, 10, 8); + struct mt76_wcid { struct mt76_rx_tid __rcu *aggr[IEEE80211_NUM_TIDS]; @@ -181,6 +184,9 @@ struct mt76_wcid { unsigned long flags; + struct ewma_signal rssi; + int inactive_count; + u8 idx; u8 hw_key_idx; @@ -239,7 +245,9 @@ struct mt76_rx_tid { #define MT_TX_CB_TXS_FAILED BIT(2) #define MT_PACKET_ID_MASK GENMASK(7, 0) -#define MT_PACKET_ID_NO_ACK MT_PACKET_ID_MASK +#define MT_PACKET_ID_NO_ACK 0 +#define MT_PACKET_ID_NO_SKB 1 +#define MT_PACKET_ID_FIRST 2 #define MT_TX_STATUS_SKB_TIMEOUT HZ @@ -421,6 +429,7 @@ struct mt76_dev { struct mt76_queue q_tx[__MT_TXQ_MAX]; struct mt76_queue q_rx[__MT_RXQ_MAX]; const struct mt76_queue_ops *queue_ops; + int tx_dma_idx[4]; wait_queue_head_t tx_wait; struct sk_buff_head status_list; @@ -454,6 +463,8 @@ struct mt76_dev { bool led_al; u8 led_pin; + u8 csa_complete; + u32 rxfilter; union { @@ -488,7 +499,7 @@ struct mt76_rx_status { u8 rate_idx; u8 nss; u8 band; - u8 signal; + s8 signal; u8 chains; s8 chain_signal[IEEE80211_MAX_CHAINS]; }; @@ -677,6 +688,14 @@ int mt76_sta_state(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *mt76_rx_convert(struct sk_buff *skb); +int mt76_get_min_avg_rssi(struct mt76_dev *dev); + +int mt76_get_txpower(struct ieee80211_hw *hw, struct ieee80211_vif *vif, + int *dbm); + +void mt76_csa_check(struct mt76_dev *dev); +void mt76_csa_finish(struct mt76_dev *dev); + /* internal */ void mt76_tx_free(struct mt76_dev *dev); struct mt76_txwi_cache *mt76_get_txwi(struct mt76_dev *dev); diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c index 497e762978cc..b2cabce1d74d 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c @@ -212,24 +212,24 @@ void mt76x0_get_tx_power_per_rate(struct mt76x02_dev *dev) mt76x02_add_rate_power_offset(t, delta); } -void mt76x0_get_power_info(struct mt76x02_dev *dev, u8 *info) +void mt76x0_get_power_info(struct mt76x02_dev *dev, s8 *tp) { struct mt76x0_chan_map { u8 chan; u8 offset; } chan_map[] = { - { 2, 0 }, { 4, 1 }, { 6, 2 }, { 8, 3 }, - { 10, 4 }, { 12, 5 }, { 14, 6 }, { 38, 0 }, - { 44, 1 }, { 48, 2 }, { 54, 3 }, { 60, 4 }, - { 64, 5 }, { 102, 6 }, { 108, 7 }, { 112, 8 }, - { 118, 9 }, { 124, 10 }, { 128, 11 }, { 134, 12 }, - { 140, 13 }, { 151, 14 }, { 157, 15 }, { 161, 16 }, - { 167, 17 }, { 171, 18 }, { 173, 19 }, + { 2, 0 }, { 4, 2 }, { 6, 4 }, { 8, 6 }, + { 10, 8 }, { 12, 10 }, { 14, 12 }, { 38, 0 }, + { 44, 2 }, { 48, 4 }, { 54, 6 }, { 60, 8 }, + { 64, 10 }, { 102, 12 }, { 108, 14 }, { 112, 16 }, + { 118, 18 }, { 124, 20 }, { 128, 22 }, { 134, 24 }, + { 140, 26 }, { 151, 28 }, { 157, 30 }, { 161, 32 }, + { 167, 34 }, { 171, 36 }, { 175, 38 }, }; struct ieee80211_channel *chan = dev->mt76.chandef.chan; u8 offset, addr; + int i, idx = 0; u16 data; - int i; if (mt76x0_tssi_enabled(dev)) { s8 target_power; @@ -239,14 +239,14 @@ void mt76x0_get_power_info(struct mt76x02_dev *dev, u8 *info) else data = mt76x02_eeprom_get(dev, MT_EE_2G_TARGET_POWER); target_power = (data & 0xff) - dev->mt76.rate_power.ofdm[7]; - info[0] = target_power + mt76x0_get_delta(dev); - info[1] = 0; + *tp = target_power + mt76x0_get_delta(dev); return; } for (i = 0; i < ARRAY_SIZE(chan_map); i++) { - if (chan_map[i].chan <= chan->hw_value) { + if (chan->hw_value <= chan_map[i].chan) { + idx = (chan->hw_value == chan_map[i].chan); offset = chan_map[i].offset; break; } @@ -258,13 +258,16 @@ void mt76x0_get_power_info(struct mt76x02_dev *dev, u8 *info) addr = MT_EE_TX_POWER_DELTA_BW80 + offset; } else { switch (chan->hw_value) { + case 42: + offset = 2; + break; case 58: offset = 8; break; case 106: offset = 14; break; - case 112: + case 122: offset = 20; break; case 155: @@ -277,14 +280,9 @@ void mt76x0_get_power_info(struct mt76x02_dev *dev, u8 *info) } data = mt76x02_eeprom_get(dev, addr); - - info[0] = data; - if (!info[0] || info[0] > 0x3f) - info[0] = 5; - - info[1] = data >> 8; - if (!info[1] || info[1] > 0x3f) - info[1] = 5; + *tp = data >> (8 * idx); + if (*tp < 0 || *tp > 0x3f) + *tp = 5; } static int mt76x0_check_eeprom(struct mt76x02_dev *dev) diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.h b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.h index ee9ade9f3c8b..42b259f90b6d 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.h +++ b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.h @@ -26,7 +26,7 @@ struct mt76x02_dev; int mt76x0_eeprom_init(struct mt76x02_dev *dev); void mt76x0_read_rx_gain(struct mt76x02_dev *dev); void mt76x0_get_tx_power_per_rate(struct mt76x02_dev *dev); -void mt76x0_get_power_info(struct mt76x02_dev *dev, u8 *info); +void mt76x0_get_power_info(struct mt76x02_dev *dev, s8 *tp); static inline s8 s6_to_s8(u32 val) { diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/initvals.h b/drivers/net/wireless/mediatek/mt76/mt76x0/initvals.h index a1657922758e..0290ba5869a5 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x0/initvals.h +++ b/drivers/net/wireless/mediatek/mt76/mt76x0/initvals.h @@ -88,6 +88,7 @@ static const struct mt76_reg_pair mt76x0_mac_reg_table[] = { { MT_TX_PROT_CFG6, 0xe3f42004 }, { MT_TX_PROT_CFG7, 0xe3f42084 }, { MT_TX_PROT_CFG8, 0xe3f42104 }, + { MT_VHT_HT_FBK_CFG1, 0xedcba980 }, }; static const struct mt76_reg_pair mt76x0_bbp_init_tab[] = { diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c index d895b6f3dc44..1472c8699b29 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c @@ -99,7 +99,7 @@ static const struct ieee80211_ops mt76x0e_ops = { .sta_rate_tbl_update = mt76x02_sta_rate_tbl_update, .wake_tx_queue = mt76_wake_tx_queue, .get_survey = mt76_get_survey, - .get_txpower = mt76x02_get_txpower, + .get_txpower = mt76_get_txpower, .flush = mt76x0e_flush, .set_tim = mt76x0e_set_tim, .release_buffered_frames = mt76_release_buffered_frames, @@ -141,6 +141,15 @@ static int mt76x0e_register_device(struct mt76x02_dev *dev) mt76_clear(dev, 0x110, BIT(9)); mt76_set(dev, MT_MAX_LEN_CFG, BIT(13)); + mt76_wr(dev, MT_CH_TIME_CFG, + MT_CH_TIME_CFG_TIMER_EN | + MT_CH_TIME_CFG_TX_AS_BUSY | + MT_CH_TIME_CFG_RX_AS_BUSY | + MT_CH_TIME_CFG_NAV_AS_BUSY | + MT_CH_TIME_CFG_EIFS_AS_BUSY | + MT_CH_CCA_RC_EN | + FIELD_PREP(MT_CH_TIME_CFG_CH_TIMER_CLR, 1)); + err = mt76x0_register_device(dev); if (err < 0) return err; diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c index 1eb1a802ed20..1117cdc15b04 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c @@ -845,17 +845,17 @@ static void mt76x0_phy_tssi_calibrate(struct mt76x02_dev *dev) void mt76x0_phy_set_txpower(struct mt76x02_dev *dev) { struct mt76_rate_power *t = &dev->mt76.rate_power; - u8 info[2]; + s8 info; mt76x0_get_tx_power_per_rate(dev); - mt76x0_get_power_info(dev, info); + mt76x0_get_power_info(dev, &info); - mt76x02_add_rate_power_offset(t, info[0]); + mt76x02_add_rate_power_offset(t, info); mt76x02_limit_rate_power(t, dev->mt76.txpower_conf); dev->mt76.txpower_cur = mt76x02_get_max_rate_power(t); - mt76x02_add_rate_power_offset(t, -info[0]); + mt76x02_add_rate_power_offset(t, -info); - mt76x02_phy_set_txpower(dev, info[0], info[1]); + mt76x02_phy_set_txpower(dev, info, info); } void mt76x0_phy_calibrate(struct mt76x02_dev *dev, bool power_on) @@ -1013,6 +1013,8 @@ int mt76x0_phy_set_channel(struct mt76x02_dev *dev, mt76x0_phy_calibrate(dev, false); mt76x0_phy_set_txpower(dev); + mt76x02_edcca_init(dev); + ieee80211_queue_delayed_work(dev->mt76.hw, &dev->cal_work, MT_CALIBRATE_INTERVAL); @@ -1075,7 +1077,9 @@ mt76x0_phy_update_channel_gain(struct mt76x02_dev *dev) u8 gain_delta; int low_gain; - dev->cal.avg_rssi_all = mt76x02_phy_get_min_avg_rssi(dev); + dev->cal.avg_rssi_all = mt76_get_min_avg_rssi(&dev->mt76); + if (!dev->cal.avg_rssi_all) + dev->cal.avg_rssi_all = -75; low_gain = (dev->cal.avg_rssi_all > mt76x02_get_rssi_gain_thresh(dev)) + (dev->cal.avg_rssi_all > mt76x02_get_low_rssi_gain_thresh(dev)); diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c index 0e6b43bb4678..f66e1b2f0980 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c @@ -155,7 +155,7 @@ static const struct ieee80211_ops mt76x0u_ops = { .sta_rate_tbl_update = mt76x02_sta_rate_tbl_update, .set_rts_threshold = mt76x02_set_rts_threshold, .wake_tx_queue = mt76_wake_tx_queue, - .get_txpower = mt76x02_get_txpower, + .get_txpower = mt76_get_txpower, }; static int mt76x0u_register_device(struct mt76x02_dev *dev) diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/usb_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76x0/usb_mcu.c index 9d7585029df9..f391d2d21fbc 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x0/usb_mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x0/usb_mcu.c @@ -15,6 +15,7 @@ */ #include <linux/kernel.h> #include <linux/firmware.h> +#include <linux/module.h> #include "mt76x0.h" #include "mcu.h" diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02.h b/drivers/net/wireless/mediatek/mt76/mt76x02.h index 6782665049dd..6d96766a6ed3 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02.h +++ b/drivers/net/wireless/mediatek/mt76/mt76x02.h @@ -15,8 +15,8 @@ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. */ -#ifndef __MT76X02_UTIL_H -#define __MT76X02_UTIL_H +#ifndef __MT76x02_H +#define __MT76x02_H #include <linux/kfifo.h> @@ -28,6 +28,9 @@ #define MT_CALIBRATE_INTERVAL HZ +#define MT_WATCHDOG_TIME (HZ / 10) +#define MT_TX_HANG_TH 10 + #define MT_MAX_CHAINS 2 struct mt76x02_rx_freq_cal { s8 high_gain[MT_MAX_CHAINS]; @@ -79,6 +82,7 @@ struct mt76x02_dev { struct tasklet_struct pre_tbtt_tasklet; struct delayed_work cal_work; struct delayed_work mac_work; + struct delayed_work wdt_work; u32 aggr_stats[32]; @@ -89,6 +93,9 @@ struct mt76x02_dev { u8 tbtt_count; u16 beacon_int; + u32 tx_hang_reset; + u8 tx_hang_check; + struct mt76x02_calibration cal; s8 target_power; @@ -101,6 +108,12 @@ struct mt76x02_dev { u8 slottime; struct mt76x02_dfs_pattern_detector dfs_pd; + + /* edcca monitor */ + bool ed_tx_blocked; + bool ed_monitor; + u8 ed_trigger; + u8 ed_silent; }; extern struct ieee80211_rate mt76x02_rates[12]; @@ -136,6 +149,7 @@ s8 mt76x02_tx_get_max_txpwr_adj(struct mt76x02_dev *dev, const struct ieee80211_tx_rate *rate); s8 mt76x02_tx_get_txpwr_adj(struct mt76x02_dev *dev, s8 txpwr, s8 max_txpwr_adj); +void mt76x02_wdt_work(struct work_struct *work); void mt76x02_tx_set_txpwr_auto(struct mt76x02_dev *dev, s8 txpwr); void mt76x02_set_tx_ackto(struct mt76x02_dev *dev); void mt76x02_set_coverage_class(struct ieee80211_hw *hw, @@ -158,8 +172,6 @@ void mt76x02_sw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif, const u8 *mac); void mt76x02_sw_scan_complete(struct ieee80211_hw *hw, struct ieee80211_vif *vif); -int mt76x02_get_txpower(struct ieee80211_hw *hw, - struct ieee80211_vif *vif, int *dbm); void mt76x02_sta_ps(struct mt76_dev *dev, struct ieee80211_sta *sta, bool ps); void mt76x02_bss_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif, @@ -224,4 +236,4 @@ mt76x02_rx_get_sta_wcid(struct mt76x02_sta *sta, bool unicast) return &sta->vif->group_wcid; } -#endif +#endif /* __MT76x02_H */ diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_debugfs.c b/drivers/net/wireless/mediatek/mt76/mt76x02_debugfs.c index a9d52ba1e270..7580c5c986ff 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_debugfs.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_debugfs.c @@ -133,5 +133,7 @@ void mt76x02_init_debugfs(struct mt76x02_dev *dev) read_txpower); debugfs_create_devm_seqfile(dev->mt76.dev, "agc", dir, read_agc); + + debugfs_create_u32("tx_hang_reset", 0400, dir, &dev->tx_hang_reset); } EXPORT_SYMBOL_GPL(mt76x02_init_debugfs); diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c b/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c index 054609c634a2..19fdcab746a0 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_dfs.c @@ -881,12 +881,18 @@ mt76x02_dfs_set_domain(struct mt76x02_dev *dev, { struct mt76x02_dfs_pattern_detector *dfs_pd = &dev->dfs_pd; + mutex_lock(&dev->mt76.mutex); if (dfs_pd->region != region) { tasklet_disable(&dfs_pd->dfs_tasklet); + + dev->ed_monitor = region == NL80211_DFS_ETSI; + mt76x02_edcca_init(dev); + dfs_pd->region = region; mt76x02_dfs_init_params(dev); tasklet_enable(&dfs_pd->dfs_tasklet); } + mutex_unlock(&dev->mt76.mutex); } void mt76x02_regd_notifier(struct wiphy *wiphy, diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c index c08bf371e527..63fa27d2c404 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.c @@ -130,10 +130,8 @@ static __le16 mt76x02_mac_tx_rate_val(struct mt76x02_dev *dev, const struct ieee80211_tx_rate *rate, u8 *nss_val) { + u8 phy, rate_idx, nss, bw = 0; u16 rateval; - u8 phy, rate_idx; - u8 nss = 1; - u8 bw = 0; if (rate->flags & IEEE80211_TX_RC_VHT_MCS) { rate_idx = rate->idx; @@ -164,7 +162,7 @@ mt76x02_mac_tx_rate_val(struct mt76x02_dev *dev, phy = val >> 8; rate_idx = val & 0xff; - bw = 0; + nss = 1; } rateval = FIELD_PREP(MT_RXWI_RATE_INDEX, rate_idx); @@ -435,7 +433,7 @@ void mt76x02_send_tx_status(struct mt76x02_dev *dev, } if (wcid) { - if (stat->pktid) + if (stat->pktid >= MT_PACKET_ID_FIRST) status.skb = mt76_tx_status_skb_get(mdev, wcid, stat->pktid, &list); if (status.skb) @@ -478,7 +476,9 @@ out: } static int -mt76x02_mac_process_rate(struct mt76_rx_status *status, u16 rate) +mt76x02_mac_process_rate(struct mt76x02_dev *dev, + struct mt76_rx_status *status, + u16 rate) { u8 idx = FIELD_GET(MT_RXWI_RATE_INDEX, rate); @@ -510,11 +510,15 @@ mt76x02_mac_process_rate(struct mt76_rx_status *status, u16 rate) status->encoding = RX_ENC_HT; status->rate_idx = idx; break; - case MT_PHY_TYPE_VHT: + case MT_PHY_TYPE_VHT: { + u8 n_rxstream = dev->mt76.chainmask & 0xf; + status->encoding = RX_ENC_VHT; status->rate_idx = FIELD_GET(MT_RATE_INDEX_VHT_IDX, idx); - status->nss = FIELD_GET(MT_RATE_INDEX_VHT_NSS, idx) + 1; + status->nss = min_t(u8, n_rxstream, + FIELD_GET(MT_RATE_INDEX_VHT_NSS, idx) + 1); break; + } default: return -EINVAL; } @@ -644,7 +648,7 @@ int mt76x02_mac_process_rx(struct mt76x02_dev *dev, struct sk_buff *skb, status->chains = BIT(0); signal = mt76x02_mac_get_rssi(dev, rxwi->rssi[0], 0); - for (i = 1; i < nstreams; i++) { + for (i = 0; i < nstreams; i++) { status->chains |= BIT(i); status->chain_signal[i] = mt76x02_mac_get_rssi(dev, rxwi->rssi[i], @@ -658,12 +662,7 @@ int mt76x02_mac_process_rx(struct mt76x02_dev *dev, struct sk_buff *skb, status->tid = FIELD_GET(MT_RXWI_TID, tid_sn); status->seqno = FIELD_GET(MT_RXWI_SN, tid_sn); - if (sta) { - ewma_signal_add(&sta->rssi, status->signal); - sta->inactive_count = 0; - } - - return mt76x02_mac_process_rate(status, rate); + return mt76x02_mac_process_rate(dev, status, rate); } void mt76x02_mac_poll_tx_status(struct mt76x02_dev *dev, bool irq) @@ -715,7 +714,7 @@ void mt76x02_tx_complete_skb(struct mt76_dev *mdev, struct mt76_queue *q, } EXPORT_SYMBOL_GPL(mt76x02_tx_complete_skb); -void mt76x02_mac_set_tx_protection(struct mt76x02_dev *dev, u32 val) +void mt76x02_mac_set_rts_thresh(struct mt76x02_dev *dev, u32 val) { u32 data = 0; @@ -729,20 +728,89 @@ void mt76x02_mac_set_tx_protection(struct mt76x02_dev *dev, u32 val) MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data); mt76_rmw(dev, MT_OFDM_PROT_CFG, MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data); - mt76_rmw(dev, MT_MM20_PROT_CFG, - MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data); - mt76_rmw(dev, MT_MM40_PROT_CFG, - MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data); - mt76_rmw(dev, MT_GF20_PROT_CFG, - MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data); - mt76_rmw(dev, MT_GF40_PROT_CFG, - MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data); - mt76_rmw(dev, MT_TX_PROT_CFG6, - MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data); - mt76_rmw(dev, MT_TX_PROT_CFG7, - MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data); - mt76_rmw(dev, MT_TX_PROT_CFG8, - MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data); +} + +void mt76x02_mac_set_tx_protection(struct mt76x02_dev *dev, bool legacy_prot, + int ht_mode) +{ + int mode = ht_mode & IEEE80211_HT_OP_MODE_PROTECTION; + bool non_gf = !!(ht_mode & IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT); + u32 prot[6]; + u32 vht_prot[3]; + int i; + u16 rts_thr; + + for (i = 0; i < ARRAY_SIZE(prot); i++) { + prot[i] = mt76_rr(dev, MT_CCK_PROT_CFG + i * 4); + prot[i] &= ~MT_PROT_CFG_CTRL; + if (i >= 2) + prot[i] &= ~MT_PROT_CFG_RATE; + } + + for (i = 0; i < ARRAY_SIZE(vht_prot); i++) { + vht_prot[i] = mt76_rr(dev, MT_TX_PROT_CFG6 + i * 4); + vht_prot[i] &= ~(MT_PROT_CFG_CTRL | MT_PROT_CFG_RATE); + } + + rts_thr = mt76_get_field(dev, MT_TX_RTS_CFG, MT_TX_RTS_CFG_THRESH); + + if (rts_thr != 0xffff) + prot[0] |= MT_PROT_CTRL_RTS_CTS; + + if (legacy_prot) { + prot[1] |= MT_PROT_CTRL_CTS2SELF; + + prot[2] |= MT_PROT_RATE_CCK_11; + prot[3] |= MT_PROT_RATE_CCK_11; + prot[4] |= MT_PROT_RATE_CCK_11; + prot[5] |= MT_PROT_RATE_CCK_11; + + vht_prot[0] |= MT_PROT_RATE_CCK_11; + vht_prot[1] |= MT_PROT_RATE_CCK_11; + vht_prot[2] |= MT_PROT_RATE_CCK_11; + } else { + if (rts_thr != 0xffff) + prot[1] |= MT_PROT_CTRL_RTS_CTS; + + prot[2] |= MT_PROT_RATE_OFDM_24; + prot[3] |= MT_PROT_RATE_DUP_OFDM_24; + prot[4] |= MT_PROT_RATE_OFDM_24; + prot[5] |= MT_PROT_RATE_DUP_OFDM_24; + + vht_prot[0] |= MT_PROT_RATE_OFDM_24; + vht_prot[1] |= MT_PROT_RATE_DUP_OFDM_24; + vht_prot[2] |= MT_PROT_RATE_SGI_OFDM_24; + } + + switch (mode) { + case IEEE80211_HT_OP_MODE_PROTECTION_NONMEMBER: + case IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED: + prot[2] |= MT_PROT_CTRL_RTS_CTS; + prot[3] |= MT_PROT_CTRL_RTS_CTS; + prot[4] |= MT_PROT_CTRL_RTS_CTS; + prot[5] |= MT_PROT_CTRL_RTS_CTS; + vht_prot[0] |= MT_PROT_CTRL_RTS_CTS; + vht_prot[1] |= MT_PROT_CTRL_RTS_CTS; + vht_prot[2] |= MT_PROT_CTRL_RTS_CTS; + break; + case IEEE80211_HT_OP_MODE_PROTECTION_20MHZ: + prot[3] |= MT_PROT_CTRL_RTS_CTS; + prot[5] |= MT_PROT_CTRL_RTS_CTS; + vht_prot[1] |= MT_PROT_CTRL_RTS_CTS; + vht_prot[2] |= MT_PROT_CTRL_RTS_CTS; + break; + } + + if (non_gf) { + prot[4] |= MT_PROT_CTRL_RTS_CTS; + prot[5] |= MT_PROT_CTRL_RTS_CTS; + } + + for (i = 0; i < ARRAY_SIZE(prot); i++) + mt76_wr(dev, MT_CCK_PROT_CFG + i * 4, prot[i]); + + for (i = 0; i < ARRAY_SIZE(vht_prot); i++) + mt76_wr(dev, MT_TX_PROT_CFG6 + i * 4, vht_prot[i]); } void mt76x02_update_channel(struct mt76_dev *mdev) @@ -774,8 +842,90 @@ static void mt76x02_check_mac_err(struct mt76x02_dev *dev) mt76_set(dev, MT_MAC_SYS_CTRL, MT_MAC_SYS_CTRL_RESET_CSR); udelay(10); - mt76_clear(dev, MT_MAC_SYS_CTRL, - MT_MAC_SYS_CTRL_ENABLE_TX | MT_MAC_SYS_CTRL_ENABLE_RX); + mt76_wr(dev, MT_MAC_SYS_CTRL, + MT_MAC_SYS_CTRL_ENABLE_TX | MT_MAC_SYS_CTRL_ENABLE_RX); +} + +static void +mt76x02_edcca_tx_enable(struct mt76x02_dev *dev, bool enable) +{ + if (enable) { + u32 data; + + mt76_set(dev, MT_MAC_SYS_CTRL, MT_MAC_SYS_CTRL_ENABLE_TX); + mt76_set(dev, MT_AUTO_RSP_CFG, MT_AUTO_RSP_EN); + /* enable pa-lna */ + data = mt76_rr(dev, MT_TX_PIN_CFG); + data |= MT_TX_PIN_CFG_TXANT | + MT_TX_PIN_CFG_RXANT | + MT_TX_PIN_RFTR_EN | + MT_TX_PIN_TRSW_EN; + mt76_wr(dev, MT_TX_PIN_CFG, data); + } else { + mt76_clear(dev, MT_MAC_SYS_CTRL, MT_MAC_SYS_CTRL_ENABLE_TX); + mt76_clear(dev, MT_AUTO_RSP_CFG, MT_AUTO_RSP_EN); + /* disable pa-lna */ + mt76_clear(dev, MT_TX_PIN_CFG, MT_TX_PIN_CFG_TXANT); + mt76_clear(dev, MT_TX_PIN_CFG, MT_TX_PIN_CFG_RXANT); + } + dev->ed_tx_blocked = !enable; +} + +void mt76x02_edcca_init(struct mt76x02_dev *dev) +{ + dev->ed_trigger = 0; + dev->ed_silent = 0; + + if (dev->ed_monitor) { + struct ieee80211_channel *chan = dev->mt76.chandef.chan; + u8 ed_th = chan->band == NL80211_BAND_5GHZ ? 0x0e : 0x20; + + mt76_clear(dev, MT_TX_LINK_CFG, MT_TX_CFACK_EN); + mt76_set(dev, MT_TXOP_CTRL_CFG, MT_TXOP_ED_CCA_EN); + mt76_rmw(dev, MT_BBP(AGC, 2), GENMASK(15, 0), + ed_th << 8 | ed_th); + if (!is_mt76x2(dev)) + mt76_set(dev, MT_TXOP_HLDR_ET, + MT_TXOP_HLDR_TX40M_BLK_EN); + } else { + mt76_set(dev, MT_TX_LINK_CFG, MT_TX_CFACK_EN); + mt76_clear(dev, MT_TXOP_CTRL_CFG, MT_TXOP_ED_CCA_EN); + if (is_mt76x2(dev)) { + mt76_wr(dev, MT_BBP(AGC, 2), 0x00007070); + } else { + mt76_wr(dev, MT_BBP(AGC, 2), 0x003a6464); + mt76_clear(dev, MT_TXOP_HLDR_ET, + MT_TXOP_HLDR_TX40M_BLK_EN); + } + } + mt76x02_edcca_tx_enable(dev, true); +} +EXPORT_SYMBOL_GPL(mt76x02_edcca_init); + +#define MT_EDCCA_TH 90 +#define MT_EDCCA_BLOCK_TH 2 +static void mt76x02_edcca_check(struct mt76x02_dev *dev) +{ + u32 val, busy; + + val = mt76_rr(dev, MT_ED_CCA_TIMER); + busy = (val * 100) / jiffies_to_usecs(MT_CALIBRATE_INTERVAL); + busy = min_t(u32, busy, 100); + + if (busy > MT_EDCCA_TH) { + dev->ed_trigger++; + dev->ed_silent = 0; + } else { + dev->ed_silent++; + dev->ed_trigger = 0; + } + + if (dev->ed_trigger > MT_EDCCA_BLOCK_TH && + !dev->ed_tx_blocked) + mt76x02_edcca_tx_enable(dev, false); + else if (dev->ed_silent > MT_EDCCA_BLOCK_TH && + dev->ed_tx_blocked) + mt76x02_edcca_tx_enable(dev, true); } void mt76x02_mac_work(struct work_struct *work) @@ -784,6 +934,8 @@ void mt76x02_mac_work(struct work_struct *work) mac_work.work); int i, idx; + mutex_lock(&dev->mt76.mutex); + mt76x02_update_channel(&dev->mt76); for (i = 0, idx = 0; i < 16; i++) { u32 val = mt76_rr(dev, MT_TX_AGG_CNT(i)); @@ -792,10 +944,14 @@ void mt76x02_mac_work(struct work_struct *work) dev->aggr_stats[idx++] += val >> 16; } - /* XXX: check beacon stuck for ap mode */ if (!dev->beacon_mask) mt76x02_check_mac_err(dev); + if (dev->ed_monitor) + mt76x02_edcca_check(dev); + + mutex_unlock(&dev->mt76.mutex); + mt76_tx_status_check(&dev->mt76, NULL, false); ieee80211_queue_delayed_work(mt76_hw(dev), &dev->mac_work, diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h index 4e597004c445..940c07f665cd 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mac.h @@ -18,8 +18,6 @@ #ifndef __MT76X02_MAC_H #define __MT76X02_MAC_H -#include <linux/average.h> - struct mt76x02_dev; struct mt76x02_tx_status { @@ -41,8 +39,6 @@ struct mt76x02_vif { u8 idx; }; -DECLARE_EWMA(signal, 10, 8); - struct mt76x02_sta { struct mt76_wcid wcid; /* must be first */ @@ -50,8 +46,6 @@ struct mt76x02_sta { struct mt76x02_tx_status status; int n_frames; - struct ewma_signal rssi; - int inactive_count; }; #define MT_RXINFO_BA BIT(0) @@ -194,7 +188,9 @@ void mt76x02_send_tx_status(struct mt76x02_dev *dev, struct mt76x02_tx_status *stat, u8 *update); int mt76x02_mac_process_rx(struct mt76x02_dev *dev, struct sk_buff *skb, void *rxi); -void mt76x02_mac_set_tx_protection(struct mt76x02_dev *dev, u32 val); +void mt76x02_mac_set_tx_protection(struct mt76x02_dev *dev, bool legacy_prot, + int ht_mode); +void mt76x02_mac_set_rts_thresh(struct mt76x02_dev *dev, u32 val); void mt76x02_mac_setaddr(struct mt76x02_dev *dev, u8 *addr); void mt76x02_mac_write_txwi(struct mt76x02_dev *dev, struct mt76x02_txwi *txwi, struct sk_buff *skb, struct mt76_wcid *wcid, @@ -210,4 +206,6 @@ int mt76x02_mac_set_beacon(struct mt76x02_dev *dev, u8 vif_idx, struct sk_buff *skb); void mt76x02_mac_set_beacon_enable(struct mt76x02_dev *dev, u8 vif_idx, bool val); + +void mt76x02_edcca_init(struct mt76x02_dev *dev); #endif diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c index 66315410aebe..374bc9d91f12 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c @@ -116,14 +116,20 @@ static void mt76x02_pre_tbtt_tasklet(unsigned long arg) IEEE80211_IFACE_ITER_RESUME_ALL, mt76x02_update_beacon_iter, dev); + mt76_csa_check(&dev->mt76); + + if (dev->mt76.csa_complete) + return; + do { nframes = skb_queue_len(&data.q); ieee80211_iterate_active_interfaces_atomic(mt76_hw(dev), IEEE80211_IFACE_ITER_RESUME_ALL, mt76x02_add_buffered_bc, &data); - } while (nframes != skb_queue_len(&data.q)); + } while (nframes != skb_queue_len(&data.q) && + skb_queue_len(&data.q) < 8); - if (!nframes) + if (!skb_queue_len(&data.q)) return; for (i = 0; i < ARRAY_SIZE(data.tail); i++) { @@ -308,8 +314,12 @@ irqreturn_t mt76x02_irq_handler(int irq, void *dev_instance) tasklet_schedule(&dev->pre_tbtt_tasklet); /* send buffered multicast frames now */ - if (intr & MT_INT_TBTT) - mt76_queue_kick(dev, &dev->mt76.q_tx[MT_TXQ_PSD]); + if (intr & MT_INT_TBTT) { + if (dev->mt76.csa_complete) + mt76_csa_finish(&dev->mt76); + else + mt76_queue_kick(dev, &dev->mt76.q_tx[MT_TXQ_PSD]); + } if (intr & MT_INT_TX_STAT) { mt76x02_mac_poll_tx_status(dev, true); @@ -384,3 +394,127 @@ void mt76x02_mac_start(struct mt76x02_dev *dev) MT_INT_TX_STAT); } EXPORT_SYMBOL_GPL(mt76x02_mac_start); + +static bool mt76x02_tx_hang(struct mt76x02_dev *dev) +{ + u32 dma_idx, prev_dma_idx; + struct mt76_queue *q; + int i; + + for (i = 0; i < 4; i++) { + q = &dev->mt76.q_tx[i]; + + if (!q->queued) + continue; + + prev_dma_idx = dev->mt76.tx_dma_idx[i]; + dma_idx = ioread32(&q->regs->dma_idx); + dev->mt76.tx_dma_idx[i] = dma_idx; + + if (prev_dma_idx == dma_idx) + break; + } + + return i < 4; +} + +static void mt76x02_watchdog_reset(struct mt76x02_dev *dev) +{ + u32 mask = dev->mt76.mmio.irqmask; + int i; + + ieee80211_stop_queues(dev->mt76.hw); + set_bit(MT76_RESET, &dev->mt76.state); + + tasklet_disable(&dev->pre_tbtt_tasklet); + tasklet_disable(&dev->tx_tasklet); + + for (i = 0; i < ARRAY_SIZE(dev->mt76.napi); i++) + napi_disable(&dev->mt76.napi[i]); + + mutex_lock(&dev->mt76.mutex); + + if (dev->beacon_mask) + mt76_clear(dev, MT_BEACON_TIME_CFG, + MT_BEACON_TIME_CFG_BEACON_TX | + MT_BEACON_TIME_CFG_TBTT_EN); + + mt76x02_irq_disable(dev, mask); + + /* perform device reset */ + mt76_clear(dev, MT_TXOP_CTRL_CFG, MT_TXOP_ED_CCA_EN); + mt76_wr(dev, MT_MAC_SYS_CTRL, 0); + mt76_clear(dev, MT_WPDMA_GLO_CFG, + MT_WPDMA_GLO_CFG_TX_DMA_EN | MT_WPDMA_GLO_CFG_RX_DMA_EN); + usleep_range(5000, 10000); + mt76_wr(dev, MT_INT_SOURCE_CSR, 0xffffffff); + + /* let fw reset DMA */ + mt76_set(dev, 0x734, 0x3); + + for (i = 0; i < ARRAY_SIZE(dev->mt76.q_tx); i++) + mt76_queue_tx_cleanup(dev, i, true); + + for (i = 0; i < ARRAY_SIZE(dev->mt76.q_rx); i++) + mt76_queue_rx_reset(dev, i); + + mt76_wr(dev, MT_MAC_SYS_CTRL, + MT_MAC_SYS_CTRL_ENABLE_TX | MT_MAC_SYS_CTRL_ENABLE_RX); + mt76_set(dev, MT_WPDMA_GLO_CFG, + MT_WPDMA_GLO_CFG_TX_DMA_EN | MT_WPDMA_GLO_CFG_RX_DMA_EN); + if (dev->ed_monitor) + mt76_set(dev, MT_TXOP_CTRL_CFG, MT_TXOP_ED_CCA_EN); + + if (dev->beacon_mask) + mt76_set(dev, MT_BEACON_TIME_CFG, + MT_BEACON_TIME_CFG_BEACON_TX | + MT_BEACON_TIME_CFG_TBTT_EN); + + mt76x02_irq_enable(dev, mask); + + mutex_unlock(&dev->mt76.mutex); + + clear_bit(MT76_RESET, &dev->mt76.state); + + tasklet_enable(&dev->tx_tasklet); + tasklet_schedule(&dev->tx_tasklet); + + tasklet_enable(&dev->pre_tbtt_tasklet); + + for (i = 0; i < ARRAY_SIZE(dev->mt76.napi); i++) { + napi_enable(&dev->mt76.napi[i]); + napi_schedule(&dev->mt76.napi[i]); + } + + ieee80211_wake_queues(dev->mt76.hw); + + mt76_txq_schedule_all(&dev->mt76); +} + +static void mt76x02_check_tx_hang(struct mt76x02_dev *dev) +{ + if (mt76x02_tx_hang(dev)) { + if (++dev->tx_hang_check < MT_TX_HANG_TH) + return; + + mt76x02_watchdog_reset(dev); + + dev->tx_hang_reset++; + dev->tx_hang_check = 0; + memset(dev->mt76.tx_dma_idx, 0xff, + sizeof(dev->mt76.tx_dma_idx)); + } else { + dev->tx_hang_check = 0; + } +} + +void mt76x02_wdt_work(struct work_struct *work) +{ + struct mt76x02_dev *dev = container_of(work, struct mt76x02_dev, + wdt_work.work); + + mt76x02_check_tx_hang(dev); + + ieee80211_queue_delayed_work(mt76_hw(dev), &dev->wdt_work, + MT_WATCHDOG_TIME); +} diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_phy.c b/drivers/net/wireless/mediatek/mt76/mt76x02_phy.c index 977a8e7e26df..a020c757ba5c 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_phy.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_phy.c @@ -132,53 +132,6 @@ void mt76x02_phy_set_txpower(struct mt76x02_dev *dev, int txp_0, int txp_1) } EXPORT_SYMBOL_GPL(mt76x02_phy_set_txpower); -int mt76x02_phy_get_min_avg_rssi(struct mt76x02_dev *dev) -{ - struct mt76x02_sta *sta; - struct mt76_wcid *wcid; - int i, j, min_rssi = 0; - s8 cur_rssi; - - local_bh_disable(); - rcu_read_lock(); - - for (i = 0; i < ARRAY_SIZE(dev->mt76.wcid_mask); i++) { - unsigned long mask = dev->mt76.wcid_mask[i]; - - if (!mask) - continue; - - for (j = i * BITS_PER_LONG; mask; j++, mask >>= 1) { - if (!(mask & 1)) - continue; - - wcid = rcu_dereference(dev->mt76.wcid[j]); - if (!wcid) - continue; - - sta = container_of(wcid, struct mt76x02_sta, wcid); - spin_lock(&dev->mt76.rx_lock); - if (sta->inactive_count++ < 5) - cur_rssi = ewma_signal_read(&sta->rssi); - else - cur_rssi = 0; - spin_unlock(&dev->mt76.rx_lock); - - if (cur_rssi < min_rssi) - min_rssi = cur_rssi; - } - } - - rcu_read_unlock(); - local_bh_enable(); - - if (!min_rssi) - return -75; - - return min_rssi; -} -EXPORT_SYMBOL_GPL(mt76x02_phy_get_min_avg_rssi); - void mt76x02_phy_set_bw(struct mt76x02_dev *dev, int width, u8 ctrl) { int core_val, agc_val; diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_phy.h b/drivers/net/wireless/mediatek/mt76/mt76x02_phy.h index 2b316cf7c70c..d2971db06f13 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_phy.h +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_phy.h @@ -51,7 +51,6 @@ void mt76x02_limit_rate_power(struct mt76_rate_power *r, int limit); int mt76x02_get_max_rate_power(struct mt76_rate_power *r); void mt76x02_phy_set_rxpath(struct mt76x02_dev *dev); void mt76x02_phy_set_txdac(struct mt76x02_dev *dev); -int mt76x02_phy_get_min_avg_rssi(struct mt76x02_dev *dev); void mt76x02_phy_set_bw(struct mt76x02_dev *dev, int width, u8 ctrl); void mt76x02_phy_set_band(struct mt76x02_dev *dev, int band, bool primary_upper); diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_regs.h b/drivers/net/wireless/mediatek/mt76/mt76x02_regs.h index f7de77d09d28..7401cb94fb72 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_regs.h +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_regs.h @@ -230,6 +230,29 @@ #define MT_COM_REG2 0x0738 #define MT_COM_REG3 0x073C +#define MT_LED_CTRL 0x0770 +#define MT_LED_CTRL_REPLAY(_n) BIT(0 + (8 * (_n))) +#define MT_LED_CTRL_POLARITY(_n) BIT(1 + (8 * (_n))) +#define MT_LED_CTRL_TX_BLINK_MODE(_n) BIT(2 + (8 * (_n))) +#define MT_LED_CTRL_KICK(_n) BIT(7 + (8 * (_n))) + +#define MT_LED_TX_BLINK_0 0x0774 +#define MT_LED_TX_BLINK_1 0x0778 + +#define MT_LED_S0_BASE 0x077C +#define MT_LED_S0(_n) (MT_LED_S0_BASE + 8 * (_n)) +#define MT_LED_S1_BASE 0x0780 +#define MT_LED_S1(_n) (MT_LED_S1_BASE + 8 * (_n)) +#define MT_LED_STATUS_OFF_MASK GENMASK(31, 24) +#define MT_LED_STATUS_OFF(_v) (((_v) << __ffs(MT_LED_STATUS_OFF_MASK)) & \ + MT_LED_STATUS_OFF_MASK) +#define MT_LED_STATUS_ON_MASK GENMASK(23, 16) +#define MT_LED_STATUS_ON(_v) (((_v) << __ffs(MT_LED_STATUS_ON_MASK)) & \ + MT_LED_STATUS_ON_MASK) +#define MT_LED_STATUS_DURATION_MASK GENMASK(15, 8) +#define MT_LED_STATUS_DURATION(_v) (((_v) << __ffs(MT_LED_STATUS_DURATION_MASK)) & \ + MT_LED_STATUS_DURATION_MASK) + #define MT_FCE_PSE_CTRL 0x0800 #define MT_FCE_PARAMETERS 0x0804 #define MT_FCE_CSO 0x0808 @@ -318,6 +341,7 @@ #define MT_CH_TIME_CFG_NAV_AS_BUSY BIT(3) #define MT_CH_TIME_CFG_EIFS_AS_BUSY BIT(4) #define MT_CH_TIME_CFG_MDRDY_CNT_EN BIT(5) +#define MT_CH_CCA_RC_EN BIT(6) #define MT_CH_TIME_CFG_CH_TIMER_CLR GENMASK(9, 8) #define MT_CH_TIME_CFG_MDRDY_CLR GENMASK(11, 10) @@ -378,6 +402,9 @@ #define MT_TX_PWR_CFG_4 0x1324 #define MT_TX_PIN_CFG 0x1328 #define MT_TX_PIN_CFG_TXANT GENMASK(3, 0) +#define MT_TX_PIN_CFG_RXANT GENMASK(11, 8) +#define MT_TX_PIN_RFTR_EN BIT(16) +#define MT_TX_PIN_TRSW_EN BIT(18) #define MT_TX_BAND_CFG 0x132c #define MT_TX_BAND_CFG_UPPER_40M BIT(0) @@ -398,6 +425,7 @@ #define MT_TXOP_CTRL_CFG 0x1340 #define MT_TXOP_TRUN_EN GENMASK(5, 0) #define MT_TXOP_EXT_CCA_DLY GENMASK(15, 8) +#define MT_TXOP_ED_CCA_EN BIT(20) #define MT_TX_RTS_CFG 0x1344 #define MT_TX_RTS_CFG_RETRY_LIMIT GENMASK(7, 0) @@ -409,6 +437,7 @@ #define MT_TX_RETRY_CFG 0x134c #define MT_TX_LINK_CFG 0x1350 +#define MT_TX_CFACK_EN BIT(12) #define MT_VHT_HT_FBK_CFG0 0x1354 #define MT_VHT_HT_FBK_CFG1 0x1358 #define MT_LG_FBK_CFG0 0x135c @@ -440,9 +469,10 @@ #define MT_PROT_TXOP_ALLOW_GF40 BIT(25) #define MT_PROT_RTS_THR_EN BIT(26) #define MT_PROT_RATE_CCK_11 0x0003 -#define MT_PROT_RATE_OFDM_6 0x4000 -#define MT_PROT_RATE_OFDM_24 0x4004 -#define MT_PROT_RATE_DUP_OFDM_24 0x4084 +#define MT_PROT_RATE_OFDM_6 0x2000 +#define MT_PROT_RATE_OFDM_24 0x2004 +#define MT_PROT_RATE_DUP_OFDM_24 0x2084 +#define MT_PROT_RATE_SGI_OFDM_24 0x2104 #define MT_PROT_TXOP_ALLOW_ALL GENMASK(25, 20) #define MT_PROT_TXOP_ALLOW_BW20 (MT_PROT_TXOP_ALLOW_ALL & \ ~MT_PROT_TXOP_ALLOW_MM40 & \ @@ -511,6 +541,7 @@ #define MT_RX_FILTR_CFG_CTRL_RSV BIT(16) #define MT_AUTO_RSP_CFG 0x1404 +#define MT_AUTO_RSP_EN BIT(0) #define MT_AUTO_RSP_PREAMB_SHORT BIT(4) #define MT_LEGACY_BASIC_RATE 0x1408 #define MT_HT_BASIC_RATE 0x140c @@ -532,6 +563,7 @@ #define MT_PN_PAD_MODE 0x150c #define MT_TXOP_HLDR_ET 0x1608 +#define MT_TXOP_HLDR_TX40M_BLK_EN BIT(1) #define MT_PROT_AUTO_TX_CFG 0x1648 #define MT_PROT_AUTO_TX_CFG_PROT_PADJ GENMASK(11, 8) diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_txrx.c b/drivers/net/wireless/mediatek/mt76/mt76x02_txrx.c index 4598cb2cc3ff..a5413a309a0a 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_txrx.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_txrx.c @@ -177,7 +177,7 @@ int mt76x02_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr, if (ret < 0) return ret; - if (pid && pid != MT_PACKET_ID_NO_ACK) + if (pid >= MT_PACKET_ID_FIRST) qsel = MT_QSEL_MGMT; *tx_info = FIELD_PREP(MT_TXD_INFO_QSEL, qsel) | diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c b/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c index 81970cf777c0..098d05e109e7 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_usb_core.c @@ -87,8 +87,7 @@ int mt76x02u_tx_prepare_skb(struct mt76_dev *mdev, void *data, pid = mt76_tx_status_skb_add(mdev, wcid, skb); txwi->pktid = pid; - if ((pid && pid != MT_PACKET_ID_NO_ACK) || - q2ep(q->hw_idx) == MT_EP_OUT_HCCA) + if (pid >= MT_PACKET_ID_FIRST || q2ep(q->hw_idx) == MT_EP_OUT_HCCA) qsel = MT_QSEL_MGMT; else qsel = MT_QSEL_EDCA; diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c index 38bd466cff16..062614ad0d51 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c @@ -75,6 +75,58 @@ static const struct ieee80211_iface_combination mt76x02_if_comb[] = { } }; +static void +mt76x02_led_set_config(struct mt76_dev *mdev, u8 delay_on, + u8 delay_off) +{ + struct mt76x02_dev *dev = container_of(mdev, struct mt76x02_dev, + mt76); + u32 val; + + val = MT_LED_STATUS_DURATION(0xff) | + MT_LED_STATUS_OFF(delay_off) | + MT_LED_STATUS_ON(delay_on); + + mt76_wr(dev, MT_LED_S0(mdev->led_pin), val); + mt76_wr(dev, MT_LED_S1(mdev->led_pin), val); + + val = MT_LED_CTRL_REPLAY(mdev->led_pin) | + MT_LED_CTRL_KICK(mdev->led_pin); + if (mdev->led_al) + val |= MT_LED_CTRL_POLARITY(mdev->led_pin); + mt76_wr(dev, MT_LED_CTRL, val); +} + +static int +mt76x02_led_set_blink(struct led_classdev *led_cdev, + unsigned long *delay_on, + unsigned long *delay_off) +{ + struct mt76_dev *mdev = container_of(led_cdev, struct mt76_dev, + led_cdev); + u8 delta_on, delta_off; + + delta_off = max_t(u8, *delay_off / 10, 1); + delta_on = max_t(u8, *delay_on / 10, 1); + + mt76x02_led_set_config(mdev, delta_on, delta_off); + + return 0; +} + +static void +mt76x02_led_set_brightness(struct led_classdev *led_cdev, + enum led_brightness brightness) +{ + struct mt76_dev *mdev = container_of(led_cdev, struct mt76_dev, + led_cdev); + + if (!brightness) + mt76x02_led_set_config(mdev, 0, 0xff); + else + mt76x02_led_set_config(mdev, 0xff, 0); +} + void mt76x02_init_device(struct mt76x02_dev *dev) { struct ieee80211_hw *hw = mt76_hw(dev); @@ -93,6 +145,8 @@ void mt76x02_init_device(struct mt76x02_dev *dev) MT_DMA_HDR_LEN; wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION); } else { + INIT_DELAYED_WORK(&dev->wdt_work, mt76x02_wdt_work); + mt76x02_dfs_init_detector(dev); wiphy->reg_notifier = mt76x02_regd_notifier; @@ -106,7 +160,16 @@ void mt76x02_init_device(struct mt76x02_dev *dev) #endif BIT(NL80211_IFTYPE_ADHOC); + wiphy->flags |= WIPHY_FLAG_HAS_CHANNEL_SWITCH; + wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_VHT_IBSS); + + /* init led callbacks */ + if (IS_ENABLED(CONFIG_MT76_LEDS)) { + dev->mt76.led_cdev.brightness_set = + mt76x02_led_set_brightness; + dev->mt76.led_cdev.blink_set = mt76x02_led_set_blink; + } } hw->sta_data_size = sizeof(struct mt76x02_sta); @@ -189,8 +252,6 @@ int mt76x02_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif, if (vif->type == NL80211_IFTYPE_AP) set_bit(MT_WCID_FLAG_CHECK_PS, &msta->wcid.flags); - ewma_signal_init(&msta->rssi); - return 0; } EXPORT_SYMBOL_GPL(mt76x02_sta_add); @@ -463,7 +524,7 @@ int mt76x02_set_rts_threshold(struct ieee80211_hw *hw, u32 val) return -EINVAL; mutex_lock(&dev->mt76.mutex); - mt76x02_mac_set_tx_protection(dev, val); + mt76x02_mac_set_rts_thresh(dev, val); mutex_unlock(&dev->mt76.mutex); return 0; @@ -546,24 +607,6 @@ void mt76x02_sw_scan_complete(struct ieee80211_hw *hw, } EXPORT_SYMBOL_GPL(mt76x02_sw_scan_complete); -int mt76x02_get_txpower(struct ieee80211_hw *hw, - struct ieee80211_vif *vif, int *dbm) -{ - struct mt76x02_dev *dev = hw->priv; - u8 nstreams = dev->mt76.chainmask & 0xf; - - *dbm = dev->mt76.txpower_cur / 2; - - /* convert from per-chain power to combined - * output on 2x2 devices - */ - if (nstreams > 1) - *dbm += 3; - - return 0; -} -EXPORT_SYMBOL_GPL(mt76x02_get_txpower); - void mt76x02_sta_ps(struct mt76_dev *mdev, struct ieee80211_sta *sta, bool ps) { @@ -661,6 +704,10 @@ void mt76x02_bss_info_changed(struct ieee80211_hw *hw, tasklet_enable(&dev->pre_tbtt_tasklet); } + if (changed & BSS_CHANGED_HT || changed & BSS_CHANGED_ERP_CTS_PROT) + mt76x02_mac_set_tx_protection(dev, info->use_cts_prot, + info->ht_operation_mode); + if (changed & BSS_CHANGED_BEACON_INT) { mt76_rmw_field(dev, MT_BEACON_TIME_CFG, MT_BEACON_TIME_CFG_INTVAL, diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/init.c index 54a9b5fac787..f8534362e2c8 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x2/init.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x2/init.c @@ -143,6 +143,7 @@ void mt76_write_mac_initvals(struct mt76x02_dev *dev) { MT_VHT_HT_FBK_CFG1, 0xedcba980 }, { MT_PROT_AUTO_TX_CFG, 0x00830083 }, { MT_HT_CTRL_CFG, 0x000001ff }, + { MT_TX_LINK_CFG, 0x00001020 }, }; struct mt76_reg_pair prot_vals[] = { { MT_CCK_PROT_CFG, DEFAULT_PROT_CFG_CCK }, diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/mcu.h b/drivers/net/wireless/mediatek/mt76/mt76x2/mcu.h index acfa2b570c7c..40ef43926c06 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x2/mcu.h +++ b/drivers/net/wireless/mediatek/mt76/mt76x2/mcu.h @@ -26,29 +26,6 @@ #define MT_MCU_PCIE_REMAP_BASE2 0x0744 #define MT_MCU_PCIE_REMAP_BASE3 0x0748 -#define MT_LED_CTRL 0x0770 -#define MT_LED_CTRL_REPLAY(_n) BIT(0 + (8 * (_n))) -#define MT_LED_CTRL_POLARITY(_n) BIT(1 + (8 * (_n))) -#define MT_LED_CTRL_TX_BLINK_MODE(_n) BIT(2 + (8 * (_n))) -#define MT_LED_CTRL_KICK(_n) BIT(7 + (8 * (_n))) - -#define MT_LED_TX_BLINK_0 0x0774 -#define MT_LED_TX_BLINK_1 0x0778 - -#define MT_LED_S0_BASE 0x077C -#define MT_LED_S0(_n) (MT_LED_S0_BASE + 8 * (_n)) -#define MT_LED_S1_BASE 0x0780 -#define MT_LED_S1(_n) (MT_LED_S1_BASE + 8 * (_n)) -#define MT_LED_STATUS_OFF_MASK GENMASK(31, 24) -#define MT_LED_STATUS_OFF(_v) (((_v) << __ffs(MT_LED_STATUS_OFF_MASK)) & \ - MT_LED_STATUS_OFF_MASK) -#define MT_LED_STATUS_ON_MASK GENMASK(23, 16) -#define MT_LED_STATUS_ON(_v) (((_v) << __ffs(MT_LED_STATUS_ON_MASK)) & \ - MT_LED_STATUS_ON_MASK) -#define MT_LED_STATUS_DURATION_MASK GENMASK(15, 8) -#define MT_LED_STATUS_DURATION(_v) (((_v) << __ffs(MT_LED_STATUS_DURATION_MASK)) & \ - MT_LED_STATUS_DURATION_MASK) - #define MT_MCU_ROM_PATCH_OFFSET 0x80000 #define MT_MCU_ROM_PATCH_ADDR 0x90000 diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h index b259e4b50f1e..28ec19acf9db 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h +++ b/drivers/net/wireless/mediatek/mt76/mt76x2/mt76x2.h @@ -53,7 +53,6 @@ struct mt76x02_dev *mt76x2_alloc_device(struct device *pdev); int mt76x2_register_device(struct mt76x02_dev *dev); void mt76x2_phy_power_on(struct mt76x02_dev *dev); -int mt76x2_init_hardware(struct mt76x02_dev *dev); void mt76x2_stop_hardware(struct mt76x02_dev *dev); int mt76x2_eeprom_init(struct mt76x02_dev *dev); int mt76x2_apply_calibration_data(struct mt76x02_dev *dev, int channel); diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c index 7f4ea2d00f42..4347d5e7a915 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_init.c @@ -151,6 +151,7 @@ static int mt76x2_mac_reset(struct mt76x02_dev *dev, bool hard) MT_CH_TIME_CFG_RX_AS_BUSY | MT_CH_TIME_CFG_NAV_AS_BUSY | MT_CH_TIME_CFG_EIFS_AS_BUSY | + MT_CH_CCA_RC_EN | FIELD_PREP(MT_CH_TIME_CFG_CH_TIMER_CLR, 1)); mt76x02_set_tx_ackto(dev); @@ -260,7 +261,7 @@ mt76x2_power_on(struct mt76x02_dev *dev) mt76x2_power_on_rf(dev, 1); } -int mt76x2_init_hardware(struct mt76x02_dev *dev) +static int mt76x2_init_hardware(struct mt76x02_dev *dev) { int ret; @@ -300,6 +301,7 @@ void mt76x2_stop_hardware(struct mt76x02_dev *dev) { cancel_delayed_work_sync(&dev->cal_work); cancel_delayed_work_sync(&dev->mac_work); + cancel_delayed_work_sync(&dev->wdt_work); mt76x02_mcu_set_radio_state(dev, false); mt76x2_mac_stop(dev, false); } @@ -340,54 +342,6 @@ struct mt76x02_dev *mt76x2_alloc_device(struct device *pdev) return dev; } -static void mt76x2_led_set_config(struct mt76_dev *mt76, u8 delay_on, - u8 delay_off) -{ - struct mt76x02_dev *dev = container_of(mt76, struct mt76x02_dev, - mt76); - u32 val; - - val = MT_LED_STATUS_DURATION(0xff) | - MT_LED_STATUS_OFF(delay_off) | - MT_LED_STATUS_ON(delay_on); - - mt76_wr(dev, MT_LED_S0(mt76->led_pin), val); - mt76_wr(dev, MT_LED_S1(mt76->led_pin), val); - - val = MT_LED_CTRL_REPLAY(mt76->led_pin) | - MT_LED_CTRL_KICK(mt76->led_pin); - if (mt76->led_al) - val |= MT_LED_CTRL_POLARITY(mt76->led_pin); - mt76_wr(dev, MT_LED_CTRL, val); -} - -static int mt76x2_led_set_blink(struct led_classdev *led_cdev, - unsigned long *delay_on, - unsigned long *delay_off) -{ - struct mt76_dev *mt76 = container_of(led_cdev, struct mt76_dev, - led_cdev); - u8 delta_on, delta_off; - - delta_off = max_t(u8, *delay_off / 10, 1); - delta_on = max_t(u8, *delay_on / 10, 1); - - mt76x2_led_set_config(mt76, delta_on, delta_off); - return 0; -} - -static void mt76x2_led_set_brightness(struct led_classdev *led_cdev, - enum led_brightness brightness) -{ - struct mt76_dev *mt76 = container_of(led_cdev, struct mt76_dev, - led_cdev); - - if (!brightness) - mt76x2_led_set_config(mt76, 0, 0xff); - else - mt76x2_led_set_config(mt76, 0xff, 0); -} - int mt76x2_register_device(struct mt76x02_dev *dev) { int ret; @@ -402,12 +356,6 @@ int mt76x2_register_device(struct mt76x02_dev *dev) mt76x02_config_mac_addr_list(dev); - /* init led callbacks */ - if (IS_ENABLED(CONFIG_MT76_LEDS)) { - dev->mt76.led_cdev.brightness_set = mt76x2_led_set_brightness; - dev->mt76.led_cdev.blink_set = mt76x2_led_set_blink; - } - ret = mt76_register_device(&dev->mt76, true, mt76x02_rates, ARRAY_SIZE(mt76x02_rates)); if (ret) diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c index b54a32397486..06a26a152ba4 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_main.c @@ -34,6 +34,8 @@ mt76x2_start(struct ieee80211_hw *hw) ieee80211_queue_delayed_work(mt76_hw(dev), &dev->mac_work, MT_CALIBRATE_INTERVAL); + ieee80211_queue_delayed_work(mt76_hw(dev), &dev->wdt_work, + MT_WATCHDOG_TIME); set_bit(MT76_STATE_RUNNING, &dev->mt76.state); @@ -189,7 +191,7 @@ const struct ieee80211_ops mt76x2_ops = { .sw_scan_complete = mt76x02_sw_scan_complete, .flush = mt76x2_flush, .ampdu_action = mt76x02_ampdu_action, - .get_txpower = mt76x02_get_txpower, + .get_txpower = mt76_get_txpower, .wake_tx_queue = mt76_wake_tx_queue, .sta_rate_tbl_update = mt76x02_sta_rate_tbl_update, .release_buffered_frames = mt76_release_buffered_frames, diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_phy.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_phy.c index da7cd40f56ff..65ed62229a5b 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci_phy.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci_phy.c @@ -254,6 +254,8 @@ int mt76x2_phy_set_channel(struct mt76x02_dev *dev, 0x38); } + mt76x02_edcca_init(dev); + ieee80211_queue_delayed_work(mt76_hw(dev), &dev->cal_work, MT_CALIBRATE_INTERVAL); diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/phy.c b/drivers/net/wireless/mediatek/mt76/mt76x2/phy.c index c9634a774705..e2ee5e498da7 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x2/phy.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x2/phy.c @@ -284,7 +284,9 @@ void mt76x2_phy_update_channel_gain(struct mt76x02_dev *dev) int low_gain; u32 val; - dev->cal.avg_rssi_all = mt76x02_phy_get_min_avg_rssi(dev); + dev->cal.avg_rssi_all = mt76_get_min_avg_rssi(&dev->mt76); + if (!dev->cal.avg_rssi_all) + dev->cal.avg_rssi_all = -75; low_gain = (dev->cal.avg_rssi_all > mt76x02_get_rssi_gain_thresh(dev)) + (dev->cal.avg_rssi_all > mt76x02_get_low_rssi_gain_thresh(dev)); diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c index 2b48cc51a30d..286c7f451090 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c @@ -138,5 +138,5 @@ const struct ieee80211_ops mt76x2u_ops = { .sw_scan_start = mt76x02_sw_scan, .sw_scan_complete = mt76x02_sw_scan_complete, .sta_rate_tbl_update = mt76x02_sta_rate_tbl_update, - .get_txpower = mt76x02_get_txpower, + .get_txpower = mt76_get_txpower, }; diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_mcu.c index 45a95ee3a415..152d41fe9ff5 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_mcu.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_mcu.c @@ -39,7 +39,7 @@ static void mt76x2u_mcu_load_ivb(struct mt76x02_dev *dev) static void mt76x2u_mcu_enable_patch(struct mt76x02_dev *dev) { struct mt76_usb *usb = &dev->mt76.usb; - const u8 data[] = { + static const u8 data[] = { 0x6f, 0xfc, 0x08, 0x01, 0x20, 0x04, 0x00, 0x00, 0x00, 0x09, 0x00, diff --git a/drivers/net/wireless/mediatek/mt76/tx.c b/drivers/net/wireless/mediatek/mt76/tx.c index 7b711058807d..ef38e8626da9 100644 --- a/drivers/net/wireless/mediatek/mt76/tx.c +++ b/drivers/net/wireless/mediatek/mt76/tx.c @@ -170,21 +170,22 @@ mt76_tx_status_skb_add(struct mt76_dev *dev, struct mt76_wcid *wcid, int pid; if (!wcid) - return 0; + return MT_PACKET_ID_NO_ACK; if (info->flags & IEEE80211_TX_CTL_NO_ACK) return MT_PACKET_ID_NO_ACK; if (!(info->flags & (IEEE80211_TX_CTL_REQ_TX_STATUS | IEEE80211_TX_CTL_RATE_CTRL_PROBE))) - return 0; + return MT_PACKET_ID_NO_SKB; spin_lock_bh(&dev->status_list.lock); memset(cb, 0, sizeof(*cb)); wcid->packet_id = (wcid->packet_id + 1) & MT_PACKET_ID_MASK; - if (!wcid->packet_id || wcid->packet_id == MT_PACKET_ID_NO_ACK) - wcid->packet_id = 1; + if (wcid->packet_id == MT_PACKET_ID_NO_ACK || + wcid->packet_id == MT_PACKET_ID_NO_SKB) + wcid->packet_id = MT_PACKET_ID_FIRST; pid = wcid->packet_id; cb->wcid = wcid->idx; @@ -330,7 +331,8 @@ mt76_queue_ps_skb(struct mt76_dev *dev, struct ieee80211_sta *sta, info->control.flags |= IEEE80211_TX_CTRL_PS_RESPONSE; if (last) - info->flags |= IEEE80211_TX_STATUS_EOSP; + info->flags |= IEEE80211_TX_STATUS_EOSP | + IEEE80211_TX_CTL_REQ_TX_STATUS; mt76_skb_set_moredata(skb, !last); dev->queue_ops->tx_queue_skb(dev, hwq, skb, wcid, sta); @@ -394,6 +396,11 @@ mt76_txq_send_burst(struct mt76_dev *dev, struct mt76_queue *hwq, bool probe; int idx; + if (test_bit(MT_WCID_FLAG_PS, &wcid->flags)) { + *empty = true; + return 0; + } + skb = mt76_txq_dequeue(dev, mtxq, false); if (!skb) { *empty = true; diff --git a/drivers/net/wireless/mediatek/mt76/usb.c b/drivers/net/wireless/mediatek/mt76/usb.c index b061263453d4..6a2507524c6c 100644 --- a/drivers/net/wireless/mediatek/mt76/usb.c +++ b/drivers/net/wireless/mediatek/mt76/usb.c @@ -407,17 +407,15 @@ mt76u_process_rx_entry(struct mt76_dev *dev, struct urb *urb) if (len < 0) return 0; + data_len = min_t(int, len, urb->sg[0].length - MT_DMA_HDR_LEN); + if (MT_DMA_HDR_LEN + data_len > SKB_WITH_OVERHEAD(q->buf_size)) + return 0; + skb = build_skb(data, q->buf_size); if (!skb) return 0; - data_len = min_t(int, len, urb->sg[0].length - MT_DMA_HDR_LEN); skb_reserve(skb, MT_DMA_HDR_LEN); - if (skb->tail + data_len > skb->end) { - dev_kfree_skb(skb); - return 1; - } - __skb_put(skb, data_len); len -= data_len; @@ -585,6 +583,7 @@ static void mt76u_stop_rx(struct mt76_dev *dev) static void mt76u_tx_tasklet(unsigned long data) { struct mt76_dev *dev = (struct mt76_dev *)data; + struct mt76_queue_entry entry; struct mt76u_buf *buf; struct mt76_queue *q; bool wake; @@ -599,17 +598,18 @@ static void mt76u_tx_tasklet(unsigned long data) if (!buf->done || !q->queued) break; - dev->drv->tx_complete_skb(dev, q, - &q->entry[q->head], - false); - if (q->entry[q->head].schedule) { q->entry[q->head].schedule = false; q->swq_queued--; } + entry = q->entry[q->head]; q->head = (q->head + 1) % q->ndesc; q->queued--; + + spin_unlock_bh(&q->lock); + dev->drv->tx_complete_skb(dev, q, &entry, false); + spin_lock_bh(&q->lock); } mt76_txq_schedule(dev, q); wake = i < IEEE80211_NUM_ACS && q->queued < q->ndesc - 8; diff --git a/drivers/net/wireless/mediatek/mt76/util.c b/drivers/net/wireless/mediatek/mt76/util.c index 0c35b8db58cd..69270c1a9091 100644 --- a/drivers/net/wireless/mediatek/mt76/util.c +++ b/drivers/net/wireless/mediatek/mt76/util.c @@ -75,4 +75,46 @@ int mt76_wcid_alloc(unsigned long *mask, int size) } EXPORT_SYMBOL_GPL(mt76_wcid_alloc); +int mt76_get_min_avg_rssi(struct mt76_dev *dev) +{ + struct mt76_wcid *wcid; + int i, j, min_rssi = 0; + s8 cur_rssi; + + local_bh_disable(); + rcu_read_lock(); + + for (i = 0; i < ARRAY_SIZE(dev->wcid_mask); i++) { + unsigned long mask = dev->wcid_mask[i]; + + if (!mask) + continue; + + for (j = i * BITS_PER_LONG; mask; j++, mask >>= 1) { + if (!(mask & 1)) + continue; + + wcid = rcu_dereference(dev->wcid[j]); + if (!wcid) + continue; + + spin_lock(&dev->rx_lock); + if (wcid->inactive_count++ < 5) + cur_rssi = -ewma_signal_read(&wcid->rssi); + else + cur_rssi = 0; + spin_unlock(&dev->rx_lock); + + if (cur_rssi < min_rssi) + min_rssi = cur_rssi; + } + } + + rcu_read_unlock(); + local_bh_enable(); + + return min_rssi; +} +EXPORT_SYMBOL_GPL(mt76_get_min_avg_rssi); + MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/net/wireless/mediatek/mt7601u/dma.c b/drivers/net/wireless/mediatek/mt7601u/dma.c index 7f3e3983b781..f7edeffb2b19 100644 --- a/drivers/net/wireless/mediatek/mt7601u/dma.c +++ b/drivers/net/wireless/mediatek/mt7601u/dma.c @@ -124,9 +124,9 @@ static u16 mt7601u_rx_next_seg_len(u8 *data, u32 data_len) u16 dma_len = get_unaligned_le16(data); if (data_len < min_seg_len || - WARN_ON(!dma_len) || - WARN_ON(dma_len + MT_DMA_HDRS > data_len) || - WARN_ON(dma_len & 0x3)) + WARN_ON_ONCE(!dma_len) || + WARN_ON_ONCE(dma_len + MT_DMA_HDRS > data_len) || + WARN_ON_ONCE(dma_len & 0x3)) return 0; return MT_DMA_HDRS + dma_len; diff --git a/drivers/net/wireless/mediatek/mt7601u/eeprom.h b/drivers/net/wireless/mediatek/mt7601u/eeprom.h index 662d12703b69..57b503ae63f1 100644 --- a/drivers/net/wireless/mediatek/mt7601u/eeprom.h +++ b/drivers/net/wireless/mediatek/mt7601u/eeprom.h @@ -17,7 +17,7 @@ struct mt7601u_dev; -#define MT7601U_EE_MAX_VER 0x0c +#define MT7601U_EE_MAX_VER 0x0d #define MT7601U_EEPROM_SIZE 256 #define MT7601U_DEFAULT_TX_POWER 6 diff --git a/drivers/net/wireless/quantenna/Makefile b/drivers/net/wireless/quantenna/Makefile index baebfbde119e..cea83d178d2e 100644 --- a/drivers/net/wireless/quantenna/Makefile +++ b/drivers/net/wireless/quantenna/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # Copyright (c) 2015-2016 Quantenna Communications, Inc. # All rights reserved. diff --git a/drivers/net/wireless/quantenna/qtnfmac/bus.h b/drivers/net/wireless/quantenna/qtnfmac/bus.h index 528ca7f5e070..14b569b6d1b5 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/bus.h +++ b/drivers/net/wireless/quantenna/qtnfmac/bus.h @@ -1,18 +1,5 @@ -/* - * Copyright (c) 2015 Quantenna Communications - * - * Permission to use, copy, modify, and/or distribute this software for any - * purpose with or without fee is hereby granted, provided that the above - * copyright notice and this permission notice appear in all copies. - * - * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES - * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF - * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY - * SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES - * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION - * OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN - * CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. - */ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* Copyright (c) 2015 Quantenna Communications. All rights reserved. */ #ifndef QTNFMAC_BUS_H #define QTNFMAC_BUS_H @@ -135,7 +122,5 @@ static __always_inline void qtnf_bus_unlock(struct qtnf_bus *bus) int qtnf_core_attach(struct qtnf_bus *bus); void qtnf_core_detach(struct qtnf_bus *bus); -void qtnf_txflowblock(struct device *dev, bool state); -void qtnf_txcomplete(struct device *dev, struct sk_buff *txp, bool success); #endif /* QTNFMAC_BUS_H */ diff --git a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c index 51b33ec78fac..45f4cef7de9c 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c +++ b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c @@ -1,18 +1,5 @@ -/* - * Copyright (c) 2012-2012 Quantenna Communications, Inc. - * All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - */ +// SPDX-License-Identifier: GPL-2.0+ +/* Copyright (c) 2015-2016 Quantenna Communications. All rights reserved. */ #include <linux/kernel.h> #include <linux/etherdevice.h> @@ -122,7 +109,8 @@ qtnf_change_virtual_intf(struct wiphy *wiphy, struct vif_params *params) { struct qtnf_vif *vif = qtnf_netdev_get_priv(dev); - u8 *mac_addr; + u8 *mac_addr = NULL; + int use4addr = 0; int ret; ret = qtnf_validate_iface_combinations(wiphy, vif, type); @@ -132,14 +120,14 @@ qtnf_change_virtual_intf(struct wiphy *wiphy, return ret; } - if (params) + if (params) { mac_addr = params->macaddr; - else - mac_addr = NULL; + use4addr = params->use_4addr; + } qtnf_scan_done(vif->mac, true); - ret = qtnf_cmd_send_change_intf_type(vif, type, mac_addr); + ret = qtnf_cmd_send_change_intf_type(vif, type, use4addr, mac_addr); if (ret) { pr_err("VIF%u.%u: failed to change type to %d\n", vif->mac->macid, vif->vifid, type); @@ -190,6 +178,7 @@ static struct wireless_dev *qtnf_add_virtual_intf(struct wiphy *wiphy, struct qtnf_wmac *mac; struct qtnf_vif *vif; u8 *mac_addr = NULL; + int use4addr = 0; int ret; mac = wiphy_priv(wiphy); @@ -225,10 +214,12 @@ static struct wireless_dev *qtnf_add_virtual_intf(struct wiphy *wiphy, return ERR_PTR(-ENOTSUPP); } - if (params) + if (params) { mac_addr = params->macaddr; + use4addr = params->use_4addr; + } - ret = qtnf_cmd_send_add_intf(vif, type, mac_addr); + ret = qtnf_cmd_send_add_intf(vif, type, use4addr, mac_addr); if (ret) { pr_err("VIF%u.%u: failed to add VIF %pM\n", mac->macid, vif->vifid, mac_addr); @@ -359,11 +350,6 @@ static int qtnf_set_wiphy_params(struct wiphy *wiphy, u32 changed) return -EFAULT; } - if (changed & (WIPHY_PARAM_RETRY_LONG | WIPHY_PARAM_RETRY_SHORT)) { - pr_err("MAC%u: can't modify retry params\n", mac->macid); - return -EOPNOTSUPP; - } - ret = qtnf_cmd_send_update_phy_params(mac, changed); if (ret) pr_err("MAC%u: failed to update PHY params\n", mac->macid); @@ -1107,7 +1093,8 @@ int qtnf_wiphy_register(struct qtnf_hw_info *hw_info, struct qtnf_wmac *mac) wiphy->flags |= WIPHY_FLAG_HAVE_AP_SME | WIPHY_FLAG_AP_PROBE_RESP_OFFLOAD | WIPHY_FLAG_AP_UAPSD | - WIPHY_FLAG_HAS_CHANNEL_SWITCH; + WIPHY_FLAG_HAS_CHANNEL_SWITCH | + WIPHY_FLAG_4ADDR_STATION; wiphy->flags &= ~WIPHY_FLAG_PS_ON_BY_DEFAULT; if (hw_info->hw_capab & QLINK_HW_CAPAB_DFS_OFFLOAD) diff --git a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.h b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.h index b73425122a10..c374857283ac 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.h +++ b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.h @@ -1,18 +1,5 @@ -/* - * Copyright (c) 2015-2016 Quantenna Communications, Inc. - * All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - */ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* Copyright (c) 2015-2016 Quantenna Communications. All rights reserved. */ #ifndef _QTN_FMAC_CFG80211_H_ #define _QTN_FMAC_CFG80211_H_ diff --git a/drivers/net/wireless/quantenna/qtnfmac/commands.c b/drivers/net/wireless/quantenna/qtnfmac/commands.c index 659e7649fe22..0f48f541de41 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/commands.c +++ b/drivers/net/wireless/quantenna/qtnfmac/commands.c @@ -1,17 +1,5 @@ -/* - * Copyright (c) 2015-2016 Quantenna Communications, Inc. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - */ +// SPDX-License-Identifier: GPL-2.0+ +/* Copyright (c) 2015-2016 Quantenna Communications. All rights reserved. */ #include <linux/types.h> #include <linux/skbuff.h> @@ -72,6 +60,8 @@ static int qtnf_cmd_resp_result_decode(enum qlink_cmd_result qcode) return -EADDRINUSE; case QLINK_CMD_RESULT_EADDRNOTAVAIL: return -EADDRNOTAVAIL; + case QLINK_CMD_RESULT_EBUSY: + return -EBUSY; default: return -EFAULT; } @@ -97,14 +87,12 @@ static int qtnf_cmd_send_with_reply(struct qtnf_bus *bus, vif_id = cmd->vifid; cmd->mhdr.len = cpu_to_le16(cmd_skb->len); - pr_debug("VIF%u.%u cmd=0x%.4X\n", mac_id, vif_id, - le16_to_cpu(cmd->cmd_id)); + pr_debug("VIF%u.%u cmd=0x%.4X\n", mac_id, vif_id, cmd_id); if (bus->fw_state != QTNF_FW_STATE_ACTIVE && - le16_to_cpu(cmd->cmd_id) != QLINK_CMD_FW_INIT) { + cmd_id != QLINK_CMD_FW_INIT) { pr_warn("VIF%u.%u: drop cmd 0x%.4X in fw state %d\n", - mac_id, vif_id, le16_to_cpu(cmd->cmd_id), - bus->fw_state); + mac_id, vif_id, cmd_id, bus->fw_state); dev_kfree_skb(cmd_skb); return -ENODEV; } @@ -138,7 +126,7 @@ out: return qtnf_cmd_resp_result_decode(le16_to_cpu(resp->result)); pr_warn("VIF%u.%u: cmd 0x%.4X failed: %d\n", - mac_id, vif_id, le16_to_cpu(cmd->cmd_id), ret); + mac_id, vif_id, cmd_id, ret); return ret; } @@ -732,6 +720,7 @@ out: static int qtnf_cmd_send_add_change_intf(struct qtnf_vif *vif, enum nl80211_iftype iftype, + int use4addr, u8 *mac_addr, enum qlink_cmd_type cmd_type) { @@ -749,6 +738,7 @@ static int qtnf_cmd_send_add_change_intf(struct qtnf_vif *vif, qtnf_bus_lock(vif->mac->bus); cmd = (struct qlink_cmd_manage_intf *)cmd_skb->data; + cmd->intf_info.use4addr = use4addr; switch (iftype) { case NL80211_IFTYPE_AP: @@ -784,17 +774,19 @@ out: return ret; } -int qtnf_cmd_send_add_intf(struct qtnf_vif *vif, - enum nl80211_iftype iftype, u8 *mac_addr) +int qtnf_cmd_send_add_intf(struct qtnf_vif *vif, enum nl80211_iftype iftype, + int use4addr, u8 *mac_addr) { - return qtnf_cmd_send_add_change_intf(vif, iftype, mac_addr, + return qtnf_cmd_send_add_change_intf(vif, iftype, use4addr, mac_addr, QLINK_CMD_ADD_INTF); } int qtnf_cmd_send_change_intf_type(struct qtnf_vif *vif, - enum nl80211_iftype iftype, u8 *mac_addr) + enum nl80211_iftype iftype, + int use4addr, + u8 *mac_addr) { - return qtnf_cmd_send_add_change_intf(vif, iftype, mac_addr, + return qtnf_cmd_send_add_change_intf(vif, iftype, use4addr, mac_addr, QLINK_CMD_CHANGE_INTF); } @@ -914,9 +906,8 @@ qtnf_cmd_resp_proc_hw_info(struct qtnf_bus *bus, if (WARN_ON(resp->n_reg_rules > NL80211_MAX_SUPP_REG_RULES)) return -E2BIG; - hwinfo->rd = kzalloc(sizeof(*hwinfo->rd) - + sizeof(struct ieee80211_reg_rule) - * resp->n_reg_rules, GFP_KERNEL); + hwinfo->rd = kzalloc(struct_size(hwinfo->rd, reg_rules, + resp->n_reg_rules), GFP_KERNEL); if (!hwinfo->rd) return -ENOMEM; @@ -1558,11 +1549,11 @@ static int qtnf_cmd_resp_proc_phy_params(struct qtnf_wmac *mac, switch (tlv_type) { case QTN_TLV_ID_FRAG_THRESH: phy_thr = (void *)tlv; - mac_info->frag_thr = (u32)le16_to_cpu(phy_thr->thr); + mac_info->frag_thr = le32_to_cpu(phy_thr->thr); break; case QTN_TLV_ID_RTS_THRESH: phy_thr = (void *)tlv; - mac_info->rts_thr = (u32)le16_to_cpu(phy_thr->thr); + mac_info->rts_thr = le32_to_cpu(phy_thr->thr); break; case QTN_TLV_ID_SRETRY_LIMIT: limit = (void *)tlv; @@ -1810,15 +1801,23 @@ int qtnf_cmd_send_update_phy_params(struct qtnf_wmac *mac, u32 changed) qtnf_bus_lock(mac->bus); if (changed & WIPHY_PARAM_FRAG_THRESHOLD) - qtnf_cmd_skb_put_tlv_u16(cmd_skb, QTN_TLV_ID_FRAG_THRESH, + qtnf_cmd_skb_put_tlv_u32(cmd_skb, QTN_TLV_ID_FRAG_THRESH, wiphy->frag_threshold); if (changed & WIPHY_PARAM_RTS_THRESHOLD) - qtnf_cmd_skb_put_tlv_u16(cmd_skb, QTN_TLV_ID_RTS_THRESH, + qtnf_cmd_skb_put_tlv_u32(cmd_skb, QTN_TLV_ID_RTS_THRESH, wiphy->rts_threshold); if (changed & WIPHY_PARAM_COVERAGE_CLASS) qtnf_cmd_skb_put_tlv_u8(cmd_skb, QTN_TLV_ID_COVERAGE_CLASS, wiphy->coverage_class); + if (changed & WIPHY_PARAM_RETRY_LONG) + qtnf_cmd_skb_put_tlv_u8(cmd_skb, QTN_TLV_ID_LRETRY_LIMIT, + wiphy->retry_long); + + if (changed & WIPHY_PARAM_RETRY_SHORT) + qtnf_cmd_skb_put_tlv_u8(cmd_skb, QTN_TLV_ID_SRETRY_LIMIT, + wiphy->retry_short); + ret = qtnf_cmd_send(mac->bus, cmd_skb); if (ret) goto out; diff --git a/drivers/net/wireless/quantenna/qtnfmac/commands.h b/drivers/net/wireless/quantenna/qtnfmac/commands.h index 1ac41156c192..96dff643bbc4 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/commands.h +++ b/drivers/net/wireless/quantenna/qtnfmac/commands.h @@ -1,17 +1,5 @@ -/* - * Copyright (c) 2016 Quantenna Communications, Inc. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - */ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* Copyright (c) 2016 Quantenna Communications. All rights reserved. */ #ifndef QLINK_COMMANDS_H_ #define QLINK_COMMANDS_H_ @@ -26,9 +14,11 @@ void qtnf_cmd_send_deinit_fw(struct qtnf_bus *bus); int qtnf_cmd_get_hw_info(struct qtnf_bus *bus); int qtnf_cmd_get_mac_info(struct qtnf_wmac *mac); int qtnf_cmd_send_add_intf(struct qtnf_vif *vif, enum nl80211_iftype iftype, - u8 *mac_addr); + int use4addr, u8 *mac_addr); int qtnf_cmd_send_change_intf_type(struct qtnf_vif *vif, - enum nl80211_iftype iftype, u8 *mac_addr); + enum nl80211_iftype iftype, + int use4addr, + u8 *mac_addr); int qtnf_cmd_send_del_intf(struct qtnf_vif *vif); int qtnf_cmd_band_info_get(struct qtnf_wmac *mac, struct ieee80211_supported_band *band); diff --git a/drivers/net/wireless/quantenna/qtnfmac/core.c b/drivers/net/wireless/quantenna/qtnfmac/core.c index 5d18a4a917c9..ee1b75fda1dd 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/core.c +++ b/drivers/net/wireless/quantenna/qtnfmac/core.c @@ -1,18 +1,5 @@ -/* - * Copyright (c) 2015-2016 Quantenna Communications, Inc. - * All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - */ +// SPDX-License-Identifier: GPL-2.0+ +/* Copyright (c) 2015-2016 Quantenna Communications. All rights reserved. */ #include <linux/kernel.h> #include <linux/module.h> @@ -195,6 +182,7 @@ static int qtnf_netdev_set_mac_address(struct net_device *ndev, void *addr) qtnf_scan_done(vif->mac, true); ret = qtnf_cmd_send_change_intf_type(vif, vif->wdev.iftype, + vif->wdev.use_4addr, sa->sa_data); if (ret) @@ -545,7 +533,8 @@ static int qtnf_core_mac_attach(struct qtnf_bus *bus, unsigned int macid) goto error; } - ret = qtnf_cmd_send_add_intf(vif, vif->wdev.iftype, vif->mac_addr); + ret = qtnf_cmd_send_add_intf(vif, vif->wdev.iftype, + vif->wdev.use_4addr, vif->mac_addr); if (ret) { pr_err("MAC%u: failed to add VIF\n", macid); goto error; diff --git a/drivers/net/wireless/quantenna/qtnfmac/core.h b/drivers/net/wireless/quantenna/qtnfmac/core.h index 293055049caa..a31cff46e964 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/core.h +++ b/drivers/net/wireless/quantenna/qtnfmac/core.h @@ -1,18 +1,5 @@ -/* - * Copyright (c) 2015-2016 Quantenna Communications, Inc. - * All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - */ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* Copyright (c) 2015-2016 Quantenna Communications. All rights reserved. */ #ifndef _QTN_FMAC_CORE_H_ #define _QTN_FMAC_CORE_H_ diff --git a/drivers/net/wireless/quantenna/qtnfmac/debug.c b/drivers/net/wireless/quantenna/qtnfmac/debug.c index 9f826b9ef5d9..598ece753a4b 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/debug.c +++ b/drivers/net/wireless/quantenna/qtnfmac/debug.c @@ -1,32 +1,11 @@ -/* - * Copyright (c) 2015-2016 Quantenna Communications, Inc. - * All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - */ +// SPDX-License-Identifier: GPL-2.0+ +/* Copyright (c) 2015-2016 Quantenna Communications. All rights reserved. */ #include "debug.h" -#undef pr_fmt -#define pr_fmt(fmt) "qtnfmac dbg: %s: " fmt, __func__ - void qtnf_debugfs_init(struct qtnf_bus *bus, const char *name) { bus->dbg_dir = debugfs_create_dir(name, NULL); - - if (IS_ERR_OR_NULL(bus->dbg_dir)) { - pr_warn("failed to create debugfs root dir\n"); - bus->dbg_dir = NULL; - } } void qtnf_debugfs_remove(struct qtnf_bus *bus) @@ -38,9 +17,5 @@ void qtnf_debugfs_remove(struct qtnf_bus *bus) void qtnf_debugfs_add_entry(struct qtnf_bus *bus, const char *name, int (*fn)(struct seq_file *seq, void *data)) { - struct dentry *entry; - - entry = debugfs_create_devm_seqfile(bus->dev, name, bus->dbg_dir, fn); - if (IS_ERR_OR_NULL(entry)) - pr_warn("failed to add entry (%s)\n", name); + debugfs_create_devm_seqfile(bus->dev, name, bus->dbg_dir, fn); } diff --git a/drivers/net/wireless/quantenna/qtnfmac/debug.h b/drivers/net/wireless/quantenna/qtnfmac/debug.h index d6dd12b5d434..61b45536b83a 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/debug.h +++ b/drivers/net/wireless/quantenna/qtnfmac/debug.h @@ -1,18 +1,5 @@ -/* - * Copyright (c) 2015-2016 Quantenna Communications, Inc. - * All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - */ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* Copyright (c) 2015-2016 Quantenna Communications. All rights reserved. */ #ifndef _QTN_FMAC_DEBUG_H_ #define _QTN_FMAC_DEBUG_H_ diff --git a/drivers/net/wireless/quantenna/qtnfmac/event.c b/drivers/net/wireless/quantenna/qtnfmac/event.c index 8b542b431b75..3fd1a9217737 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/event.c +++ b/drivers/net/wireless/quantenna/qtnfmac/event.c @@ -1,18 +1,5 @@ -/* - * Copyright (c) 2015-2016 Quantenna Communications, Inc. - * All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - */ +// SPDX-License-Identifier: GPL-2.0+ +/* Copyright (c) 2015-2016 Quantenna Communications. All rights reserved. */ #include <linux/kernel.h> #include <linux/module.h> @@ -158,6 +145,12 @@ qtnf_event_handle_bss_join(struct qtnf_vif *vif, const struct qlink_event_bss_join *join_info, u16 len) { + struct wiphy *wiphy = priv_to_wiphy(vif->mac); + enum ieee80211_statuscode status = le16_to_cpu(join_info->status); + struct cfg80211_chan_def chandef; + struct cfg80211_bss *bss = NULL; + u8 *ie = NULL; + if (unlikely(len < sizeof(*join_info))) { pr_err("VIF%u.%u: payload is too short (%u < %zu)\n", vif->mac->macid, vif->vifid, len, @@ -171,15 +164,80 @@ qtnf_event_handle_bss_join(struct qtnf_vif *vif, return -EPROTO; } - pr_debug("VIF%u.%u: BSSID:%pM\n", vif->mac->macid, vif->vifid, - join_info->bssid); + pr_debug("VIF%u.%u: BSSID:%pM status:%u\n", + vif->mac->macid, vif->vifid, join_info->bssid, status); + + if (status == WLAN_STATUS_SUCCESS) { + qlink_chandef_q2cfg(wiphy, &join_info->chan, &chandef); + if (!cfg80211_chandef_valid(&chandef)) { + pr_warn("MAC%u.%u: bad channel freq=%u cf1=%u cf2=%u bw=%u\n", + vif->mac->macid, vif->vifid, + chandef.chan->center_freq, + chandef.center_freq1, + chandef.center_freq2, + chandef.width); + status = WLAN_STATUS_UNSPECIFIED_FAILURE; + goto done; + } + bss = cfg80211_get_bss(wiphy, chandef.chan, join_info->bssid, + NULL, 0, IEEE80211_BSS_TYPE_ESS, + IEEE80211_PRIVACY_ANY); + if (!bss) { + pr_warn("VIF%u.%u: add missing BSS:%pM chan:%u\n", + vif->mac->macid, vif->vifid, + join_info->bssid, chandef.chan->hw_value); + + if (!vif->wdev.ssid_len) { + pr_warn("VIF%u.%u: SSID unknown for BSS:%pM\n", + vif->mac->macid, vif->vifid, + join_info->bssid); + status = WLAN_STATUS_UNSPECIFIED_FAILURE; + goto done; + } + + ie = kzalloc(2 + vif->wdev.ssid_len, GFP_KERNEL); + if (!ie) { + pr_warn("VIF%u.%u: IE alloc failed for BSS:%pM\n", + vif->mac->macid, vif->vifid, + join_info->bssid); + status = WLAN_STATUS_UNSPECIFIED_FAILURE; + goto done; + } + + ie[0] = WLAN_EID_SSID; + ie[1] = vif->wdev.ssid_len; + memcpy(ie + 2, vif->wdev.ssid, vif->wdev.ssid_len); + + bss = cfg80211_inform_bss(wiphy, chandef.chan, + CFG80211_BSS_FTYPE_UNKNOWN, + join_info->bssid, 0, + WLAN_CAPABILITY_ESS, 100, + ie, 2 + vif->wdev.ssid_len, + 0, GFP_KERNEL); + if (!bss) { + pr_warn("VIF%u.%u: can't connect to unknown BSS: %pM\n", + vif->mac->macid, vif->vifid, + join_info->bssid); + status = WLAN_STATUS_UNSPECIFIED_FAILURE; + goto done; + } + } + } + +done: cfg80211_connect_result(vif->netdev, join_info->bssid, NULL, 0, NULL, - 0, le16_to_cpu(join_info->status), GFP_KERNEL); + 0, status, GFP_KERNEL); + if (bss) { + if (!ether_addr_equal(vif->bssid, join_info->bssid)) + ether_addr_copy(vif->bssid, join_info->bssid); + cfg80211_put_bss(wiphy, bss); + } - if (le16_to_cpu(join_info->status) == WLAN_STATUS_SUCCESS) + if (status == WLAN_STATUS_SUCCESS) netif_carrier_on(vif->netdev); + kfree(ie); return 0; } diff --git a/drivers/net/wireless/quantenna/qtnfmac/event.h b/drivers/net/wireless/quantenna/qtnfmac/event.h index ae759b602c2a..533ad99d045d 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/event.h +++ b/drivers/net/wireless/quantenna/qtnfmac/event.h @@ -1,18 +1,5 @@ -/* - * Copyright (c) 2015-2016 Quantenna Communications, Inc. - * All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - */ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* Copyright (c) 2015-2016 Quantenna Communications. All rights reserved. */ #ifndef _QTN_FMAC_EVENT_H_ #define _QTN_FMAC_EVENT_H_ diff --git a/drivers/net/wireless/quantenna/qtnfmac/pcie/topaz_pcie.c b/drivers/net/wireless/quantenna/qtnfmac/pcie/topaz_pcie.c index 598edb814421..cbcda57105f3 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/pcie/topaz_pcie.c +++ b/drivers/net/wireless/quantenna/qtnfmac/pcie/topaz_pcie.c @@ -559,6 +559,9 @@ static irqreturn_t qtnf_pcie_topaz_interrupt(int irq, void *data) if (!priv->msi_enabled && !qtnf_topaz_intx_asserted(ts)) return IRQ_NONE; + if (!priv->msi_enabled) + qtnf_deassert_intx(ts); + priv->pcie_irq_count++; qtnf_shm_ipc_irq_handler(&priv->shm_ipc_ep_in); @@ -571,9 +574,6 @@ static irqreturn_t qtnf_pcie_topaz_interrupt(int irq, void *data) tasklet_hi_schedule(&priv->reclaim_tq); - if (!priv->msi_enabled) - qtnf_deassert_intx(ts); - return IRQ_HANDLED; } diff --git a/drivers/net/wireless/quantenna/qtnfmac/qlink.h b/drivers/net/wireless/quantenna/qtnfmac/qlink.h index 8d62addea895..27fdb5b01ee3 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/qlink.h +++ b/drivers/net/wireless/quantenna/qtnfmac/qlink.h @@ -1,25 +1,12 @@ -/* - * Copyright (c) 2015-2016 Quantenna Communications, Inc. - * All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - */ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* Copyright (c) 2015-2016 Quantenna Communications. All rights reserved. */ #ifndef _QTN_QLINK_H_ #define _QTN_QLINK_H_ #include <linux/ieee80211.h> -#define QLINK_PROTO_VER 11 +#define QLINK_PROTO_VER 13 #define QLINK_MACID_RSVD 0xFF #define QLINK_VIFID_RSVD 0xFF @@ -105,7 +92,8 @@ struct qlink_intf_info { __le16 if_type; __le16 vlanid; u8 mac_addr[ETH_ALEN]; - u8 rsvd[2]; + u8 use4addr; + u8 rsvd[1]; } __packed; enum qlink_sta_flags { @@ -733,6 +721,7 @@ enum qlink_cmd_result { QLINK_CMD_RESULT_EALREADY, QLINK_CMD_RESULT_EADDRINUSE, QLINK_CMD_RESULT_EADDRNOTAVAIL, + QLINK_CMD_RESULT_EBUSY, }; /** @@ -986,11 +975,13 @@ struct qlink_event_sta_deauth { /** * struct qlink_event_bss_join - data for QLINK_EVENT_BSS_JOIN event * + * @chan: new operating channel definition * @bssid: BSSID of a BSS which interface tried to joined. * @status: status of joining attempt, see &enum ieee80211_statuscode. */ struct qlink_event_bss_join { struct qlink_event ehdr; + struct qlink_chandef chan; u8 bssid[ETH_ALEN]; __le16 status; } __packed; @@ -1182,7 +1173,7 @@ struct qlink_iface_limit_record { struct qlink_tlv_frag_rts_thr { struct qlink_tlv_hdr hdr; - __le16 thr; + __le32 thr; } __packed; struct qlink_tlv_rlimit { diff --git a/drivers/net/wireless/quantenna/qtnfmac/qlink_util.c b/drivers/net/wireless/quantenna/qtnfmac/qlink_util.c index aeeda81b09ea..72bfd17cb687 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/qlink_util.c +++ b/drivers/net/wireless/quantenna/qtnfmac/qlink_util.c @@ -1,17 +1,5 @@ -/* - * Copyright (c) 2015-2016 Quantenna Communications, Inc. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - */ +// SPDX-License-Identifier: GPL-2.0+ +/* Copyright (c) 2015-2016 Quantenna Communications. All rights reserved. */ #include <linux/nl80211.h> diff --git a/drivers/net/wireless/quantenna/qtnfmac/qlink_util.h b/drivers/net/wireless/quantenna/qtnfmac/qlink_util.h index 960d5d97492f..781ea7fe79f2 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/qlink_util.h +++ b/drivers/net/wireless/quantenna/qtnfmac/qlink_util.h @@ -1,18 +1,5 @@ -/* - * Copyright (c) 2015-2016 Quantenna Communications, Inc. - * All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - */ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* Copyright (c) 2015-2016 Quantenna Communications. All rights reserved. */ #ifndef _QTN_FMAC_QLINK_UTIL_H_ #define _QTN_FMAC_QLINK_UTIL_H_ @@ -69,6 +56,17 @@ static inline void qtnf_cmd_skb_put_tlv_u16(struct sk_buff *skb, memcpy(hdr->val, &tmp, sizeof(tmp)); } +static inline void qtnf_cmd_skb_put_tlv_u32(struct sk_buff *skb, + u16 tlv_id, u32 value) +{ + struct qlink_tlv_hdr *hdr = skb_put(skb, sizeof(*hdr) + sizeof(value)); + __le32 tmp = cpu_to_le32(value); + + hdr->type = cpu_to_le16(tlv_id); + hdr->len = cpu_to_le16(sizeof(value)); + memcpy(hdr->val, &tmp, sizeof(tmp)); +} + u16 qlink_iface_type_to_nl_mask(u16 qlink_type); u8 qlink_chan_width_mask_to_nl(u16 qlink_mask); void qlink_chandef_q2cfg(struct wiphy *wiphy, diff --git a/drivers/net/wireless/quantenna/qtnfmac/qtn_hw_ids.h b/drivers/net/wireless/quantenna/qtnfmac/qtn_hw_ids.h index 40295a511224..82d879950b62 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/qtn_hw_ids.h +++ b/drivers/net/wireless/quantenna/qtnfmac/qtn_hw_ids.h @@ -1,18 +1,5 @@ -/* - * Copyright (c) 2015-2016 Quantenna Communications, Inc. - * All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - */ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* Copyright (c) 2015-2016 Quantenna Communications. All rights reserved. */ #ifndef _QTN_HW_IDS_H_ #define _QTN_HW_IDS_H_ diff --git a/drivers/net/wireless/quantenna/qtnfmac/shm_ipc.c b/drivers/net/wireless/quantenna/qtnfmac/shm_ipc.c index 2ec334199c2b..ff678951d3b2 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/shm_ipc.c +++ b/drivers/net/wireless/quantenna/qtnfmac/shm_ipc.c @@ -1,18 +1,5 @@ -/* - * Copyright (c) 2015-2016 Quantenna Communications, Inc. - * All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - */ +// SPDX-License-Identifier: GPL-2.0+ +/* Copyright (c) 2015-2016 Quantenna Communications. All rights reserved. */ #include <linux/types.h> #include <linux/io.h> diff --git a/drivers/net/wireless/quantenna/qtnfmac/shm_ipc.h b/drivers/net/wireless/quantenna/qtnfmac/shm_ipc.h index c2a3702a9ee7..52cac5439b03 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/shm_ipc.h +++ b/drivers/net/wireless/quantenna/qtnfmac/shm_ipc.h @@ -1,18 +1,5 @@ -/* - * Copyright (c) 2015-2016 Quantenna Communications, Inc. - * All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - */ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* Copyright (c) 2015-2016 Quantenna Communications. All rights reserved. */ #ifndef _QTN_FMAC_SHM_IPC_H_ #define _QTN_FMAC_SHM_IPC_H_ diff --git a/drivers/net/wireless/quantenna/qtnfmac/shm_ipc_defs.h b/drivers/net/wireless/quantenna/qtnfmac/shm_ipc_defs.h index 95a5f89a8b1a..78be70df1218 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/shm_ipc_defs.h +++ b/drivers/net/wireless/quantenna/qtnfmac/shm_ipc_defs.h @@ -1,18 +1,5 @@ -/* - * Copyright (c) 2015-2016 Quantenna Communications, Inc. - * All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - */ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* Copyright (c) 2015-2016 Quantenna Communications. All rights reserved. */ #ifndef _QTN_FMAC_SHM_IPC_DEFS_H_ #define _QTN_FMAC_SHM_IPC_DEFS_H_ diff --git a/drivers/net/wireless/quantenna/qtnfmac/trans.c b/drivers/net/wireless/quantenna/qtnfmac/trans.c index 345f34ec9750..95356e280e23 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/trans.c +++ b/drivers/net/wireless/quantenna/qtnfmac/trans.c @@ -1,18 +1,5 @@ -/* - * Copyright (c) 2015-2016 Quantenna Communications, Inc. - * All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - */ +// SPDX-License-Identifier: GPL-2.0+ +/* Copyright (c) 2015-2016 Quantenna Communications. All rights reserved. */ #include <linux/types.h> #include <linux/export.h> diff --git a/drivers/net/wireless/quantenna/qtnfmac/trans.h b/drivers/net/wireless/quantenna/qtnfmac/trans.h index 9a473e07af0f..c0b76f871b31 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/trans.h +++ b/drivers/net/wireless/quantenna/qtnfmac/trans.h @@ -1,18 +1,5 @@ -/* - * Copyright (c) 2015-2016 Quantenna Communications, Inc. - * All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - */ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* Copyright (c) 2015-2016 Quantenna Communications. All rights reserved. */ #ifndef _QTN_FMAC_TRANS_H_ #define _QTN_FMAC_TRANS_H_ diff --git a/drivers/net/wireless/quantenna/qtnfmac/util.c b/drivers/net/wireless/quantenna/qtnfmac/util.c index 3bc96b264769..cda6f5f3f38a 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/util.c +++ b/drivers/net/wireless/quantenna/qtnfmac/util.c @@ -1,18 +1,5 @@ -/* - * Copyright (c) 2015-2016 Quantenna Communications, Inc. - * All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - */ +// SPDX-License-Identifier: GPL-2.0+ +/* Copyright (c) 2015-2016 Quantenna Communications. All rights reserved. */ #include "util.h" #include "qtn_hw_ids.h" diff --git a/drivers/net/wireless/quantenna/qtnfmac/util.h b/drivers/net/wireless/quantenna/qtnfmac/util.h index b8744baac332..a14b7078a9c7 100644 --- a/drivers/net/wireless/quantenna/qtnfmac/util.h +++ b/drivers/net/wireless/quantenna/qtnfmac/util.h @@ -1,18 +1,5 @@ -/* - * Copyright (c) 2015 Quantenna Communications - * - * Permission to use, copy, modify, and/or distribute this software for any - * purpose with or without fee is hereby granted, provided that the above - * copyright notice and this permission notice appear in all copies. - * - * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES - * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF - * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY - * SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES - * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION - * OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN - * CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. - */ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* Copyright (c) 2015 Quantenna Communications. All rights reserved. */ #ifndef QTNFMAC_UTIL_H #define QTNFMAC_UTIL_H diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c index 0e95555aec62..7f813f6f8792 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c @@ -5477,7 +5477,7 @@ static int rt2800_init_registers(struct rt2x00_dev *rt2x00dev) rt2800_register_write(rt2x00dev, TX_SW_CFG2, 0x00000000); rt2800_register_write(rt2x00dev, MIMO_PS_CFG, 0x00000002); rt2800_register_write(rt2x00dev, TX_PIN_CFG, 0x00150F0F); - rt2800_register_write(rt2x00dev, TX_ALC_VGA3, 0x06060606); + rt2800_register_write(rt2x00dev, TX_ALC_VGA3, 0x00000000); rt2800_register_write(rt2x00dev, TX0_BB_GAIN_ATTEN, 0x0); rt2800_register_write(rt2x00dev, TX1_BB_GAIN_ATTEN, 0x0); rt2800_register_write(rt2x00dev, TX0_RF_GAIN_ATTEN, 0x6C6C666C); diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00debug.c b/drivers/net/wireless/ralink/rt2x00/rt2x00debug.c index 61ba573e8bf1..05a2e8da412c 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2x00debug.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2x00debug.c @@ -656,36 +656,24 @@ void rt2x00debug_register(struct rt2x00_dev *rt2x00dev) intf->driver_folder = debugfs_create_dir(intf->rt2x00dev->ops->name, rt2x00dev->hw->wiphy->debugfsdir); - if (IS_ERR(intf->driver_folder) || !intf->driver_folder) - goto exit; intf->driver_entry = rt2x00debug_create_file_driver("driver", intf, &intf->driver_blob); - if (IS_ERR(intf->driver_entry) || !intf->driver_entry) - goto exit; intf->chipset_entry = rt2x00debug_create_file_chipset("chipset", intf, &intf->chipset_blob); - if (IS_ERR(intf->chipset_entry) || !intf->chipset_entry) - goto exit; intf->dev_flags = debugfs_create_file("dev_flags", 0400, intf->driver_folder, intf, &rt2x00debug_fop_dev_flags); - if (IS_ERR(intf->dev_flags) || !intf->dev_flags) - goto exit; intf->cap_flags = debugfs_create_file("cap_flags", 0400, intf->driver_folder, intf, &rt2x00debug_fop_cap_flags); - if (IS_ERR(intf->cap_flags) || !intf->cap_flags) - goto exit; intf->register_folder = debugfs_create_dir("register", intf->driver_folder); - if (IS_ERR(intf->register_folder) || !intf->register_folder) - goto exit; #define RT2X00DEBUGFS_CREATE_REGISTER_ENTRY(__intf, __name) \ ({ \ @@ -695,9 +683,6 @@ void rt2x00debug_register(struct rt2x00_dev *rt2x00dev) 0600, \ (__intf)->register_folder, \ &(__intf)->offset_##__name); \ - if (IS_ERR((__intf)->__name##_off_entry) || \ - !(__intf)->__name##_off_entry) \ - goto exit; \ \ (__intf)->__name##_val_entry = \ debugfs_create_file(__stringify(__name) "_value", \ @@ -705,9 +690,6 @@ void rt2x00debug_register(struct rt2x00_dev *rt2x00dev) (__intf)->register_folder, \ (__intf), \ &rt2x00debug_fop_##__name); \ - if (IS_ERR((__intf)->__name##_val_entry) || \ - !(__intf)->__name##_val_entry) \ - goto exit; \ } \ }) @@ -721,15 +703,10 @@ void rt2x00debug_register(struct rt2x00_dev *rt2x00dev) intf->queue_folder = debugfs_create_dir("queue", intf->driver_folder); - if (IS_ERR(intf->queue_folder) || !intf->queue_folder) - goto exit; intf->queue_frame_dump_entry = debugfs_create_file("dump", 0400, intf->queue_folder, intf, &rt2x00debug_fop_queue_dump); - if (IS_ERR(intf->queue_frame_dump_entry) - || !intf->queue_frame_dump_entry) - goto exit; skb_queue_head_init(&intf->frame_dump_skbqueue); init_waitqueue_head(&intf->frame_dump_waitqueue); @@ -747,10 +724,6 @@ void rt2x00debug_register(struct rt2x00_dev *rt2x00dev) #endif return; - -exit: - rt2x00debug_deregister(rt2x00dev); - rt2x00_err(rt2x00dev, "Failed to register debug handler\n"); } void rt2x00debug_deregister(struct rt2x00_dev *rt2x00dev) diff --git a/drivers/net/wireless/ralink/rt2x00/rt61pci.c b/drivers/net/wireless/ralink/rt2x00/rt61pci.c index 4c5de8fc8f12..52b9fc480f8b 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt61pci.c +++ b/drivers/net/wireless/ralink/rt2x00/rt61pci.c @@ -321,97 +321,12 @@ static int rt61pci_config_shared_key(struct rt2x00_dev *rt2x00dev, struct rt2x00lib_crypto *crypto, struct ieee80211_key_conf *key) { - struct hw_key_entry key_entry; - struct rt2x00_field32 field; - u32 mask; - u32 reg; - - if (crypto->cmd == SET_KEY) { - /* - * rt2x00lib can't determine the correct free - * key_idx for shared keys. We have 1 register - * with key valid bits. The goal is simple, read - * the register, if that is full we have no slots - * left. - * Note that each BSS is allowed to have up to 4 - * shared keys, so put a mask over the allowed - * entries. - */ - mask = (0xf << crypto->bssidx); - - reg = rt2x00mmio_register_read(rt2x00dev, SEC_CSR0); - reg &= mask; - - if (reg && reg == mask) - return -ENOSPC; - - key->hw_key_idx += reg ? ffz(reg) : 0; - - /* - * Upload key to hardware - */ - memcpy(key_entry.key, crypto->key, - sizeof(key_entry.key)); - memcpy(key_entry.tx_mic, crypto->tx_mic, - sizeof(key_entry.tx_mic)); - memcpy(key_entry.rx_mic, crypto->rx_mic, - sizeof(key_entry.rx_mic)); - - reg = SHARED_KEY_ENTRY(key->hw_key_idx); - rt2x00mmio_register_multiwrite(rt2x00dev, reg, - &key_entry, sizeof(key_entry)); - - /* - * The cipher types are stored over 2 registers. - * bssidx 0 and 1 keys are stored in SEC_CSR1 and - * bssidx 1 and 2 keys are stored in SEC_CSR5. - * Using the correct defines correctly will cause overhead, - * so just calculate the correct offset. - */ - if (key->hw_key_idx < 8) { - field.bit_offset = (3 * key->hw_key_idx); - field.bit_mask = 0x7 << field.bit_offset; - - reg = rt2x00mmio_register_read(rt2x00dev, SEC_CSR1); - rt2x00_set_field32(®, field, crypto->cipher); - rt2x00mmio_register_write(rt2x00dev, SEC_CSR1, reg); - } else { - field.bit_offset = (3 * (key->hw_key_idx - 8)); - field.bit_mask = 0x7 << field.bit_offset; - - reg = rt2x00mmio_register_read(rt2x00dev, SEC_CSR5); - rt2x00_set_field32(®, field, crypto->cipher); - rt2x00mmio_register_write(rt2x00dev, SEC_CSR5, reg); - } - - /* - * The driver does not support the IV/EIV generation - * in hardware. However it doesn't support the IV/EIV - * inside the ieee80211 frame either, but requires it - * to be provided separately for the descriptor. - * rt2x00lib will cut the IV/EIV data out of all frames - * given to us by mac80211, but we must tell mac80211 - * to generate the IV/EIV data. - */ - key->flags |= IEEE80211_KEY_FLAG_GENERATE_IV; - } - /* - * SEC_CSR0 contains only single-bit fields to indicate - * a particular key is valid. Because using the FIELD32() - * defines directly will cause a lot of overhead, we use - * a calculation to determine the correct bit directly. + * Let the software handle the shared keys, + * since the hardware decryption does not work reliably, + * because the firmware does not know the key's keyidx. */ - mask = 1 << key->hw_key_idx; - - reg = rt2x00mmio_register_read(rt2x00dev, SEC_CSR0); - if (crypto->cmd == SET_KEY) - reg |= mask; - else if (crypto->cmd == DISABLE_KEY) - reg &= ~mask; - rt2x00mmio_register_write(rt2x00dev, SEC_CSR0, reg); - - return 0; + return -EOPNOTSUPP; } static int rt61pci_config_pairwise_key(struct rt2x00_dev *rt2x00dev, diff --git a/drivers/net/wireless/ray_cs.c b/drivers/net/wireless/ray_cs.c index 33ad87528d9a..44a943d18b84 100644 --- a/drivers/net/wireless/ray_cs.c +++ b/drivers/net/wireless/ray_cs.c @@ -959,7 +959,7 @@ static int translate_frame(ray_dev_t *local, struct tx_msg __iomem *ptx, if (proto == htons(ETH_P_AARP) || proto == htons(ETH_P_IPX)) { /* This is the selective translation table, only 2 entries */ writeb(0xf8, - &((struct snaphdr_t __iomem *)ptx->var)->org[3]); + &((struct snaphdr_t __iomem *)ptx->var)->org[2]); } /* Copy body of ethernet packet without ethernet header */ memcpy_toio((void __iomem *)&ptx->var + @@ -2211,7 +2211,7 @@ static void rx_data(struct net_device *dev, struct rcs __iomem *prcs, untranslate(local, skb, total_len); } } else { /* sniffer mode, so just pass whole packet */ - }; + } /************************/ /* Now pick up the rest of the fragments if any */ diff --git a/drivers/net/wireless/realtek/rtl818x/rtl8180/Makefile b/drivers/net/wireless/realtek/rtl818x/rtl8180/Makefile index 2966681efaef..5d6b06d3c02c 100644 --- a/drivers/net/wireless/realtek/rtl818x/rtl8180/Makefile +++ b/drivers/net/wireless/realtek/rtl818x/rtl8180/Makefile @@ -2,4 +2,4 @@ rtl818x_pci-objs := dev.o rtl8225.o sa2400.o max2820.o grf5101.o rtl8225se.o obj-$(CONFIG_RTL8180) += rtl818x_pci.o -ccflags-y += -Idrivers/net/wireless/realtek/rtl818x +ccflags-y += -I $(srctree)/$(src)/.. diff --git a/drivers/net/wireless/realtek/rtl818x/rtl8180/dev.c b/drivers/net/wireless/realtek/rtl818x/rtl8180/dev.c index 225c1c8851cc..e2b1bfbcfbd4 100644 --- a/drivers/net/wireless/realtek/rtl818x/rtl8180/dev.c +++ b/drivers/net/wireless/realtek/rtl818x/rtl8180/dev.c @@ -803,7 +803,7 @@ static void rtl8180_config_cardbus(struct ieee80211_hw *dev) rtl818x_iowrite16(priv, FEMR_SE, 0xffff); } else { reg16 = rtl818x_ioread16(priv, &priv->map->FEMR); - reg16 |= (1 << 15) | (1 << 14) | (1 << 4); + reg16 |= (1 << 15) | (1 << 14) | (1 << 4); rtl818x_iowrite16(priv, &priv->map->FEMR, reg16); } diff --git a/drivers/net/wireless/realtek/rtl818x/rtl8187/Makefile b/drivers/net/wireless/realtek/rtl818x/rtl8187/Makefile index ff074912a095..95bac73ece7c 100644 --- a/drivers/net/wireless/realtek/rtl818x/rtl8187/Makefile +++ b/drivers/net/wireless/realtek/rtl818x/rtl8187/Makefile @@ -2,4 +2,4 @@ rtl8187-objs := dev.o rtl8225.o leds.o rfkill.o obj-$(CONFIG_RTL8187) += rtl8187.o -ccflags-y += -Idrivers/net/wireless/realtek/rtl818x +ccflags-y += -I $(srctree)/$(src)/.. diff --git a/drivers/net/wireless/realtek/rtlwifi/base.c b/drivers/net/wireless/realtek/rtlwifi/base.c index ef9b502ce576..7aa68fe5d791 100644 --- a/drivers/net/wireless/realtek/rtlwifi/base.c +++ b/drivers/net/wireless/realtek/rtlwifi/base.c @@ -2172,8 +2172,6 @@ label_lps_done: ; } - rtlpriv->link_info.num_rx_inperiod = 0; - rtlpriv->link_info.num_tx_inperiod = 0; for (tid = 0; tid <= 7; tid++) rtlpriv->link_info.tidtx_inperiod[tid] = 0; @@ -2236,6 +2234,8 @@ label_lps_done: rtlpriv->btcoexist.btc_info.in_4way = false; } + rtlpriv->link_info.num_rx_inperiod = 0; + rtlpriv->link_info.num_tx_inperiod = 0; rtlpriv->link_info.bcn_rx_inperiod = 0; /* <6> scan list */ diff --git a/drivers/net/wireless/realtek/rtlwifi/core.c b/drivers/net/wireless/realtek/rtlwifi/core.c index 4bf7967590ca..ce23339bf9fb 100644 --- a/drivers/net/wireless/realtek/rtlwifi/core.c +++ b/drivers/net/wireless/realtek/rtlwifi/core.c @@ -1957,5 +1957,7 @@ void rtl_dm_diginit(struct ieee80211_hw *hw, u32 cur_igvalue) dm_digtable->bt30_cur_igi = 0x32; dm_digtable->pre_cck_pd_state = CCK_PD_STAGE_MAX; dm_digtable->cur_cck_pd_state = CCK_PD_STAGE_LOWRSSI; + dm_digtable->pre_cck_fa_state = 0; + dm_digtable->cur_cck_fa_state = 0; } EXPORT_SYMBOL(rtl_dm_diginit); diff --git a/drivers/net/wireless/realtek/rtlwifi/debug.c b/drivers/net/wireless/realtek/rtlwifi/debug.c index d70385be9976..8186650efc56 100644 --- a/drivers/net/wireless/realtek/rtlwifi/debug.c +++ b/drivers/net/wireless/realtek/rtlwifi/debug.c @@ -463,12 +463,9 @@ static const struct file_operations file_ops_common_write = { #define RTL_DEBUGFS_ADD_CORE(name, mode, fopname) \ do { \ rtl_debug_priv_ ##name.rtlpriv = rtlpriv; \ - if (!debugfs_create_file(#name, mode, \ - parent, &rtl_debug_priv_ ##name, \ - &file_ops_ ##fopname)) \ - pr_err("Unable to initialize debugfs:%s/%s\n", \ - rtlpriv->dbg.debugfs_name, \ - #name); \ + debugfs_create_file(#name, mode, parent, \ + &rtl_debug_priv_ ##name, \ + &file_ops_ ##fopname); \ } while (0) #define RTL_DEBUGFS_ADD(name) \ @@ -486,11 +483,6 @@ void rtl_debug_add_one(struct ieee80211_hw *hw) rtlpriv->dbg.debugfs_dir = debugfs_create_dir(rtlpriv->dbg.debugfs_name, debugfs_topdir); - if (!rtlpriv->dbg.debugfs_dir) { - pr_err("Unable to init debugfs:/%s/%s\n", rtlpriv->cfg->name, - rtlpriv->dbg.debugfs_name); - return; - } parent = rtlpriv->dbg.debugfs_dir; diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/dm.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/dm.c index 42a6fba90ba9..acfd54c6f8dd 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/dm.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/dm.c @@ -151,8 +151,14 @@ static u8 rtl8723e_dm_initial_gain_min_pwdb(struct ieee80211_hw *hw) { struct rtl_priv *rtlpriv = rtl_priv(hw); struct dig_t *dm_digtable = &rtlpriv->dm_digtable; + struct rtl_mac *mac = rtl_mac(rtlpriv); long rssi_val_min = 0; + if (mac->link_state == MAC80211_LINKED && + mac->opmode == NL80211_IFTYPE_STATION && + rtlpriv->link_info.bcn_rx_inperiod == 0) + return 0; + if ((dm_digtable->curmultista_cstate == DIG_MULTISTA_CONNECT) && (dm_digtable->cursta_cstate == DIG_STA_CONNECT)) { if (rtlpriv->dm.entry_min_undec_sm_pwdb != 0) @@ -417,6 +423,8 @@ static void rtl8723e_dm_cck_packet_detection_thresh(struct ieee80211_hw *hw) } else { rtl_set_bbreg(hw, RCCK0_CCA, MASKBYTE2, 0xcd); rtl_set_bbreg(hw, RCCK0_SYSTEM, MASKBYTE1, 0x47); + dm_digtable->pre_cck_fa_state = 0; + dm_digtable->cur_cck_fa_state = 0; } dm_digtable->pre_cck_pd_state = dm_digtable->cur_cck_pd_state; @@ -665,7 +673,7 @@ void rtl8723e_dm_check_txpower_tracking(struct ieee80211_hw *hw) void rtl8723e_dm_init_rate_adaptive_mask(struct ieee80211_hw *hw) { struct rtl_priv *rtlpriv = rtl_priv(hw); - struct rate_adaptive *p_ra = &(rtlpriv->ra); + struct rate_adaptive *p_ra = &rtlpriv->ra; p_ra->ratr_state = DM_RATR_STA_INIT; p_ra->pre_ratr_state = DM_RATR_STA_INIT; @@ -677,6 +685,89 @@ void rtl8723e_dm_init_rate_adaptive_mask(struct ieee80211_hw *hw) } +void rtl8723e_dm_refresh_rate_adaptive_mask(struct ieee80211_hw *hw) +{ + struct rtl_priv *rtlpriv = rtl_priv(hw); + struct rtl_hal *rtlhal = rtl_hal(rtl_priv(hw)); + struct rtl_mac *mac = rtl_mac(rtl_priv(hw)); + struct rate_adaptive *p_ra = &rtlpriv->ra; + u32 low_rssithresh_for_ra, high_rssithresh_for_ra; + struct ieee80211_sta *sta = NULL; + + if (is_hal_stop(rtlhal)) { + RT_TRACE(rtlpriv, COMP_RATE, DBG_LOUD, + " driver is going to unload\n"); + return; + } + + if (!rtlpriv->dm.useramask) { + RT_TRACE(rtlpriv, COMP_RATE, DBG_LOUD, + " driver does not control rate adaptive mask\n"); + return; + } + + if (mac->link_state == MAC80211_LINKED && + mac->opmode == NL80211_IFTYPE_STATION) { + switch (p_ra->pre_ratr_state) { + case DM_RATR_STA_HIGH: + high_rssithresh_for_ra = 50; + low_rssithresh_for_ra = 20; + break; + case DM_RATR_STA_MIDDLE: + high_rssithresh_for_ra = 55; + low_rssithresh_for_ra = 20; + break; + case DM_RATR_STA_LOW: + high_rssithresh_for_ra = 60; + low_rssithresh_for_ra = 25; + break; + default: + high_rssithresh_for_ra = 50; + low_rssithresh_for_ra = 20; + break; + } + + if (rtlpriv->link_info.bcn_rx_inperiod == 0) + switch (p_ra->pre_ratr_state) { + case DM_RATR_STA_HIGH: + default: + p_ra->ratr_state = DM_RATR_STA_MIDDLE; + break; + case DM_RATR_STA_MIDDLE: + case DM_RATR_STA_LOW: + p_ra->ratr_state = DM_RATR_STA_LOW; + break; + } + else if (rtlpriv->dm.undec_sm_pwdb > high_rssithresh_for_ra) + p_ra->ratr_state = DM_RATR_STA_HIGH; + else if (rtlpriv->dm.undec_sm_pwdb > low_rssithresh_for_ra) + p_ra->ratr_state = DM_RATR_STA_MIDDLE; + else + p_ra->ratr_state = DM_RATR_STA_LOW; + + if (p_ra->pre_ratr_state != p_ra->ratr_state) { + RT_TRACE(rtlpriv, COMP_RATE, DBG_LOUD, + "RSSI = %ld\n", + rtlpriv->dm.undec_sm_pwdb); + RT_TRACE(rtlpriv, COMP_RATE, DBG_LOUD, + "RSSI_LEVEL = %d\n", p_ra->ratr_state); + RT_TRACE(rtlpriv, COMP_RATE, DBG_LOUD, + "PreState = %d, CurState = %d\n", + p_ra->pre_ratr_state, p_ra->ratr_state); + + rcu_read_lock(); + sta = rtl_find_sta(hw, mac->bssid); + if (sta) + rtlpriv->cfg->ops->update_rate_tbl(hw, sta, + p_ra->ratr_state, + true); + rcu_read_unlock(); + + p_ra->pre_ratr_state = p_ra->ratr_state; + } + } +} + void rtl8723e_dm_rf_saving(struct ieee80211_hw *hw, u8 bforce_in_normal) { struct rtl_priv *rtlpriv = rtl_priv(hw); @@ -826,7 +917,7 @@ void rtl8723e_dm_watchdog(struct ieee80211_hw *hw) rtl8723e_dm_dynamic_bb_powersaving(hw); rtl8723e_dm_dynamic_txpower(hw); rtl8723e_dm_check_txpower_tracking(hw); - /* rtl92c_dm_refresh_rate_adaptive_mask(hw); */ + rtl8723e_dm_refresh_rate_adaptive_mask(hw); rtl8723e_dm_bt_coexist(hw); rtl8723e_dm_check_edca_turbo(hw); } diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/sw.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/sw.c index 07b82700d1de..3103151dda2b 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/sw.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723ae/sw.c @@ -266,8 +266,8 @@ static struct rtl_hal_ops rtl8723e_hal_ops = { static struct rtl_mod_params rtl8723e_mod_params = { .sw_crypto = false, .inactiveps = true, - .swctrl_lps = false, - .fwctrl_lps = true, + .swctrl_lps = true, + .fwctrl_lps = false, .aspm_support = 1, .debug_level = 0, .debug_mask = 0, @@ -395,8 +395,8 @@ module_param_named(disable_watchdog, rtl8723e_mod_params.disable_watchdog, bool, 0444); MODULE_PARM_DESC(swenc, "Set to 1 for software crypto (default 0)\n"); MODULE_PARM_DESC(ips, "Set to 0 to not use link power save (default 1)\n"); -MODULE_PARM_DESC(swlps, "Set to 1 to use SW control power save (default 0)\n"); -MODULE_PARM_DESC(fwlps, "Set to 1 to use FW control power save (default 1)\n"); +MODULE_PARM_DESC(swlps, "Set to 1 to use SW control power save (default 1)\n"); +MODULE_PARM_DESC(fwlps, "Set to 1 to use FW control power save (default 0)\n"); MODULE_PARM_DESC(msi, "Set to 1 to use MSI interrupts mode (default 0)\n"); MODULE_PARM_DESC(aspm, "Set to 1 to enable ASPM (default 1)\n"); MODULE_PARM_DESC(debug_level, "Set debug level (0-5) (default 0)"); diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/phy.c index 1263b12db5dc..11f94b1a436f 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rtl8723be/phy.c +++ b/drivers/net/wireless/realtek/rtlwifi/rtl8723be/phy.c @@ -332,7 +332,7 @@ static void _rtl8723be_phy_set_txpower_by_rate_base(struct ieee80211_hw *hw, "Invalid RateSection %d in Band 2.4G, Rf Path %d, %dTx in PHY_SetTxPowerByRateBase()\n", rate_section, path, txnum); break; - }; + } } else { RT_TRACE(rtlpriv, COMP_INIT, DBG_LOUD, "Invalid Band %d in PHY_SetTxPowerByRateBase()\n", @@ -374,7 +374,7 @@ static u8 _rtl8723be_phy_get_txpower_by_rate_base(struct ieee80211_hw *hw, "Invalid RateSection %d in Band 2.4G, Rf Path %d, %dTx in PHY_GetTxPowerByRateBase()\n", rate_section, path, txnum); break; - }; + } } else { RT_TRACE(rtlpriv, COMP_INIT, DBG_LOUD, "Invalid Band %d in PHY_GetTxPowerByRateBase()\n", @@ -694,7 +694,7 @@ static u8 _rtl8723be_get_rate_section_index(u32 regaddr) else if (regaddr >= 0xE20 && regaddr <= 0xE4C) index = (u8)((regaddr - 0xE20) / 4); break; - }; + } return index; } diff --git a/drivers/net/wireless/rsi/rsi_91x_debugfs.c b/drivers/net/wireless/rsi/rsi_91x_debugfs.c index 8c6ca8e689e4..d0c35f3e2012 100644 --- a/drivers/net/wireless/rsi/rsi_91x_debugfs.c +++ b/drivers/net/wireless/rsi/rsi_91x_debugfs.c @@ -297,11 +297,6 @@ int rsi_init_dbgfs(struct rsi_hw *adapter) dev_dbgfs->subdir = debugfs_create_dir(devdir, NULL); - if (!dev_dbgfs->subdir) { - kfree(dev_dbgfs); - return -ENOMEM; - } - for (ii = 0; ii < adapter->num_debugfs_entries; ii++) { files = &dev_debugfs_files[ii]; dev_dbgfs->rsi_files[ii] = diff --git a/drivers/net/wireless/rsi/rsi_91x_hal.c b/drivers/net/wireless/rsi/rsi_91x_hal.c index 182b06629371..1dbaab2a96b7 100644 --- a/drivers/net/wireless/rsi/rsi_91x_hal.c +++ b/drivers/net/wireless/rsi/rsi_91x_hal.c @@ -100,6 +100,9 @@ int rsi_prepare_mgmt_desc(struct rsi_common *common, struct sk_buff *skb) mgmt_desc->frame_type = TX_DOT11_MGMT; mgmt_desc->header_len = MIN_802_11_HDR_LEN; mgmt_desc->xtend_desc_size = header_size - FRAME_DESC_SZ; + + if (ieee80211_is_probe_req(wh->frame_control)) + mgmt_desc->frame_info = cpu_to_le16(RSI_INSERT_SEQ_IN_FW); mgmt_desc->frame_info |= cpu_to_le16(RATE_INFO_ENABLE); if (is_broadcast_ether_addr(wh->addr1)) mgmt_desc->frame_info |= cpu_to_le16(RSI_BROADCAST_PKT); diff --git a/drivers/net/wireless/rsi/rsi_91x_mac80211.c b/drivers/net/wireless/rsi/rsi_91x_mac80211.c index e56fc83faf0e..aded1ae4fad5 100644 --- a/drivers/net/wireless/rsi/rsi_91x_mac80211.c +++ b/drivers/net/wireless/rsi/rsi_91x_mac80211.c @@ -229,6 +229,68 @@ static void rsi_register_rates_channels(struct rsi_hw *adapter, int band) /* sbands->ht_cap.mcs.rx_highest = 0x82; */ } +static int rsi_mac80211_hw_scan_start(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_scan_request *hw_req) +{ + struct cfg80211_scan_request *scan_req = &hw_req->req; + struct rsi_hw *adapter = hw->priv; + struct rsi_common *common = adapter->priv; + struct ieee80211_bss_conf *bss = &vif->bss_conf; + + rsi_dbg(INFO_ZONE, "***** Hardware scan start *****\n"); + + if (common->fsm_state != FSM_MAC_INIT_DONE) + return -ENODEV; + + if ((common->wow_flags & RSI_WOW_ENABLED) || + scan_req->n_channels == 0) + return -EINVAL; + + /* Scan already in progress. So return */ + if (common->bgscan_en) + return -EBUSY; + + /* If STA is not connected, return with special value 1, in order + * to start sw_scan in mac80211 + */ + if (!bss->assoc) + return 1; + + mutex_lock(&common->mutex); + common->hwscan = scan_req; + if (!rsi_send_bgscan_params(common, RSI_START_BGSCAN)) { + if (!rsi_send_bgscan_probe_req(common, vif)) { + rsi_dbg(INFO_ZONE, "Background scan started...\n"); + common->bgscan_en = true; + } + } + mutex_unlock(&common->mutex); + + return 0; +} + +static void rsi_mac80211_cancel_hw_scan(struct ieee80211_hw *hw, + struct ieee80211_vif *vif) +{ + struct rsi_hw *adapter = hw->priv; + struct rsi_common *common = adapter->priv; + struct cfg80211_scan_info info; + + rsi_dbg(INFO_ZONE, "***** Hardware scan stop *****\n"); + mutex_lock(&common->mutex); + + if (common->bgscan_en) { + if (!rsi_send_bgscan_params(common, RSI_STOP_BGSCAN)) + common->bgscan_en = false; + info.aborted = false; + ieee80211_scan_completed(adapter->hw, &info); + rsi_dbg(INFO_ZONE, "Back ground scan cancelled\b\n"); + } + common->hwscan = NULL; + mutex_unlock(&common->mutex); +} + /** * rsi_mac80211_detach() - This function is used to de-initialize the * Mac80211 stack. @@ -1917,6 +1979,8 @@ static const struct ieee80211_ops mac80211_ops = { .suspend = rsi_mac80211_suspend, .resume = rsi_mac80211_resume, #endif + .hw_scan = rsi_mac80211_hw_scan_start, + .cancel_hw_scan = rsi_mac80211_cancel_hw_scan, }; /** @@ -1999,6 +2063,9 @@ int rsi_mac80211_attach(struct rsi_common *common) common->max_stations = wiphy->max_ap_assoc_sta; rsi_dbg(ERR_ZONE, "Max Stations Allowed = %d\n", common->max_stations); hw->sta_data_size = sizeof(struct rsi_sta); + + wiphy->max_scan_ssids = RSI_MAX_SCAN_SSIDS; + wiphy->max_scan_ie_len = RSI_MAX_SCAN_IE_LEN; wiphy->flags = WIPHY_FLAG_REPORTS_OBSS; wiphy->flags |= WIPHY_FLAG_AP_UAPSD; wiphy->features |= NL80211_FEATURE_INACTIVITY_TIMER; diff --git a/drivers/net/wireless/rsi/rsi_91x_main.c b/drivers/net/wireless/rsi/rsi_91x_main.c index 01d99ed985ee..ca3a55ed72e4 100644 --- a/drivers/net/wireless/rsi/rsi_91x_main.c +++ b/drivers/net/wireless/rsi/rsi_91x_main.c @@ -328,6 +328,7 @@ struct rsi_hw *rsi_91x_init(u16 oper_mode) } rsi_default_ps_params(adapter); + init_bgscan_params(common); spin_lock_init(&adapter->ps_lock); timer_setup(&common->roc_timer, rsi_roc_timeout, 0); init_completion(&common->wlan_init_completion); diff --git a/drivers/net/wireless/rsi/rsi_91x_mgmt.c b/drivers/net/wireless/rsi/rsi_91x_mgmt.c index 1095df7d9573..404241424a62 100644 --- a/drivers/net/wireless/rsi/rsi_91x_mgmt.c +++ b/drivers/net/wireless/rsi/rsi_91x_mgmt.c @@ -15,6 +15,7 @@ */ #include <linux/etherdevice.h> +#include <linux/timer.h> #include "rsi_mgmt.h" #include "rsi_common.h" #include "rsi_ps.h" @@ -236,6 +237,18 @@ static void rsi_set_default_parameters(struct rsi_common *common) common->dtim_cnt = RSI_DTIM_COUNT; } +void init_bgscan_params(struct rsi_common *common) +{ + memset((u8 *)&common->bgscan, 0, sizeof(struct rsi_bgscan_params)); + common->bgscan.bgscan_threshold = RSI_DEF_BGSCAN_THRLD; + common->bgscan.roam_threshold = RSI_DEF_ROAM_THRLD; + common->bgscan.bgscan_periodicity = RSI_BGSCAN_PERIODICITY; + common->bgscan.num_bgscan_channels = 0; + common->bgscan.two_probe = 1; + common->bgscan.active_scan_duration = RSI_ACTIVE_SCAN_TIME; + common->bgscan.passive_scan_duration = RSI_PASSIVE_SCAN_TIME; +} + /** * rsi_set_contention_vals() - This function sets the contention values for the * backoff procedure. @@ -1628,6 +1641,107 @@ int rsi_send_wowlan_request(struct rsi_common *common, u16 flags, } #endif +int rsi_send_bgscan_params(struct rsi_common *common, int enable) +{ + struct rsi_bgscan_params *params = &common->bgscan; + struct cfg80211_scan_request *scan_req = common->hwscan; + struct rsi_bgscan_config *bgscan; + struct sk_buff *skb; + u16 frame_len = sizeof(*bgscan); + u8 i; + + rsi_dbg(MGMT_TX_ZONE, "%s: Sending bgscan params frame\n", __func__); + + skb = dev_alloc_skb(frame_len); + if (!skb) + return -ENOMEM; + memset(skb->data, 0, frame_len); + + bgscan = (struct rsi_bgscan_config *)skb->data; + rsi_set_len_qno(&bgscan->desc_dword0.len_qno, + (frame_len - FRAME_DESC_SZ), RSI_WIFI_MGMT_Q); + bgscan->desc_dword0.frame_type = BG_SCAN_PARAMS; + bgscan->bgscan_threshold = cpu_to_le16(params->bgscan_threshold); + bgscan->roam_threshold = cpu_to_le16(params->roam_threshold); + if (enable) + bgscan->bgscan_periodicity = + cpu_to_le16(params->bgscan_periodicity); + bgscan->active_scan_duration = + cpu_to_le16(params->active_scan_duration); + bgscan->passive_scan_duration = + cpu_to_le16(params->passive_scan_duration); + bgscan->two_probe = params->two_probe; + + bgscan->num_bgscan_channels = scan_req->n_channels; + for (i = 0; i < bgscan->num_bgscan_channels; i++) + bgscan->channels2scan[i] = + cpu_to_le16(scan_req->channels[i]->hw_value); + + skb_put(skb, frame_len); + + return rsi_send_internal_mgmt_frame(common, skb); +} + +/* This function sends the probe request to be used by firmware in + * background scan + */ +int rsi_send_bgscan_probe_req(struct rsi_common *common, + struct ieee80211_vif *vif) +{ + struct cfg80211_scan_request *scan_req = common->hwscan; + struct rsi_bgscan_probe *bgscan; + struct sk_buff *skb; + struct sk_buff *probereq_skb; + u16 frame_len = sizeof(*bgscan); + size_t ssid_len = 0; + u8 *ssid = NULL; + + rsi_dbg(MGMT_TX_ZONE, + "%s: Sending bgscan probe req frame\n", __func__); + + if (common->priv->sc_nvifs <= 0) + return -ENODEV; + + if (scan_req->n_ssids) { + ssid = scan_req->ssids[0].ssid; + ssid_len = scan_req->ssids[0].ssid_len; + } + + skb = dev_alloc_skb(frame_len + MAX_BGSCAN_PROBE_REQ_LEN); + if (!skb) + return -ENOMEM; + memset(skb->data, 0, frame_len + MAX_BGSCAN_PROBE_REQ_LEN); + + bgscan = (struct rsi_bgscan_probe *)skb->data; + bgscan->desc_dword0.frame_type = BG_SCAN_PROBE_REQ; + bgscan->flags = cpu_to_le16(HOST_BG_SCAN_TRIG); + if (common->band == NL80211_BAND_5GHZ) { + bgscan->mgmt_rate = cpu_to_le16(RSI_RATE_6); + bgscan->def_chan = cpu_to_le16(40); + } else { + bgscan->mgmt_rate = cpu_to_le16(RSI_RATE_1); + bgscan->def_chan = cpu_to_le16(11); + } + bgscan->channel_scan_time = cpu_to_le16(RSI_CHANNEL_SCAN_TIME); + + probereq_skb = ieee80211_probereq_get(common->priv->hw, vif->addr, ssid, + ssid_len, scan_req->ie_len); + + memcpy(&skb->data[frame_len], probereq_skb->data, probereq_skb->len); + + bgscan->probe_req_length = cpu_to_le16(probereq_skb->len); + + rsi_set_len_qno(&bgscan->desc_dword0.len_qno, + (frame_len - FRAME_DESC_SZ + probereq_skb->len), + RSI_WIFI_MGMT_Q); + + skb_put(skb, frame_len + probereq_skb->len); + + dev_kfree_skb(probereq_skb); + + return rsi_send_internal_mgmt_frame(common, skb); +} + /** * rsi_handle_ta_confirm_type() - This function handles the confirm frames. * @common: Pointer to the driver private structure. @@ -1771,9 +1885,28 @@ static int rsi_handle_ta_confirm_type(struct rsi_common *common, return 0; } break; + + case SCAN_REQUEST: + rsi_dbg(INFO_ZONE, "Set channel confirm\n"); + break; + case WAKEUP_SLEEP_REQUEST: rsi_dbg(INFO_ZONE, "Wakeup/Sleep confirmation.\n"); return rsi_handle_ps_confirm(adapter, msg); + + case BG_SCAN_PROBE_REQ: + rsi_dbg(INFO_ZONE, "BG scan complete event\n"); + if (common->bgscan_en) { + struct cfg80211_scan_info info; + + if (!rsi_send_bgscan_params(common, RSI_STOP_BGSCAN)) + common->bgscan_en = 0; + info.aborted = false; + ieee80211_scan_completed(adapter->hw, &info); + } + rsi_dbg(INFO_ZONE, "Background scan completed\n"); + break; + default: rsi_dbg(INFO_ZONE, "%s: Invalid TA confirm pkt received\n", __func__); diff --git a/drivers/net/wireless/rsi/rsi_91x_sdio.c b/drivers/net/wireless/rsi/rsi_91x_sdio.c index 5733e440ecaf..b412b65eb1f4 100644 --- a/drivers/net/wireless/rsi/rsi_91x_sdio.c +++ b/drivers/net/wireless/rsi/rsi_91x_sdio.c @@ -230,16 +230,19 @@ static void rsi_reset_card(struct sdio_func *pfunction) rsi_dbg(ERR_ZONE, "%s: CMD0 failed : %d\n", __func__, err); /* Issue CMD5, arg = 0 */ - err = rsi_issue_sdiocommand(pfunction, SD_IO_SEND_OP_COND, 0, - (MMC_RSP_R4 | MMC_CMD_BCR), &resp); - if (err) - rsi_dbg(ERR_ZONE, "%s: CMD5 failed : %d\n", __func__, err); - card->ocr = resp; + if (!host->ocr_avail) { + err = rsi_issue_sdiocommand(pfunction, SD_IO_SEND_OP_COND, 0, + (MMC_RSP_R4 | MMC_CMD_BCR), &resp); + if (err) + rsi_dbg(ERR_ZONE, "%s: CMD5 failed : %d\n", + __func__, err); + host->ocr_avail = resp; + } /* Issue CMD5, arg = ocr. Wait till card is ready */ for (i = 0; i < 100; i++) { err = rsi_issue_sdiocommand(pfunction, SD_IO_SEND_OP_COND, - card->ocr, + host->ocr_avail, (MMC_RSP_R4 | MMC_CMD_BCR), &resp); if (err) { rsi_dbg(ERR_ZONE, "%s: CMD5 failed : %d\n", diff --git a/drivers/net/wireless/rsi/rsi_main.h b/drivers/net/wireless/rsi/rsi_main.h index a084f224bb03..4dc0c0123469 100644 --- a/drivers/net/wireless/rsi/rsi_main.h +++ b/drivers/net/wireless/rsi/rsi_main.h @@ -164,6 +164,24 @@ struct transmit_q_stats { u32 total_tx_pkt_freed[NUM_EDCA_QUEUES + 2]; }; +#define MAX_BGSCAN_CHANNELS_DUAL_BAND 38 +#define MAX_BGSCAN_PROBE_REQ_LEN 0x64 +#define RSI_DEF_BGSCAN_THRLD 0x0 +#define RSI_DEF_ROAM_THRLD 0xa +#define RSI_BGSCAN_PERIODICITY 0x1e +#define RSI_ACTIVE_SCAN_TIME 0x14 +#define RSI_PASSIVE_SCAN_TIME 0x46 +#define RSI_CHANNEL_SCAN_TIME 20 +struct rsi_bgscan_params { + u16 bgscan_threshold; + u16 roam_threshold; + u16 bgscan_periodicity; + u8 num_bgscan_channels; + u8 two_probe; + u16 active_scan_duration; + u16 passive_scan_duration; +}; + struct vif_priv { bool is_ht; bool sgi; @@ -289,6 +307,10 @@ struct rsi_common { bool eapol4_confirm; void *bt_adapter; + + struct cfg80211_scan_request *hwscan; + struct rsi_bgscan_params bgscan; + u8 bgscan_en; }; struct eepromrw_info { diff --git a/drivers/net/wireless/rsi/rsi_mgmt.h b/drivers/net/wireless/rsi/rsi_mgmt.h index 359fbdf85739..ea83faa15c7e 100644 --- a/drivers/net/wireless/rsi/rsi_mgmt.h +++ b/drivers/net/wireless/rsi/rsi_mgmt.h @@ -228,6 +228,9 @@ #define RSI_MAX_TX_AGGR_FRMS 8 #define RSI_MAX_RX_AGGR_FRMS 8 +#define RSI_MAX_SCAN_SSIDS 16 +#define RSI_MAX_SCAN_IE_LEN 256 + enum opmode { RSI_OPMODE_UNSUPPORTED = -1, RSI_OPMODE_AP = 0, @@ -623,6 +626,34 @@ struct rsi_wowlan_req { u16 host_sleep_status; } __packed; +#define RSI_START_BGSCAN 1 +#define RSI_STOP_BGSCAN 0 +#define HOST_BG_SCAN_TRIG BIT(4) +struct rsi_bgscan_config { + struct rsi_cmd_desc_dword0 desc_dword0; + __le64 reserved; + __le32 reserved1; + __le16 bgscan_threshold; + __le16 roam_threshold; + __le16 bgscan_periodicity; + u8 num_bgscan_channels; + u8 two_probe; + __le16 active_scan_duration; + __le16 passive_scan_duration; + __le16 channels2scan[MAX_BGSCAN_CHANNELS_DUAL_BAND]; +} __packed; + +struct rsi_bgscan_probe { + struct rsi_cmd_desc_dword0 desc_dword0; + __le64 reserved; + __le32 reserved1; + __le16 mgmt_rate; + __le16 flags; + __le16 def_chan; + __le16 channel_scan_time; + __le16 probe_req_length; +} __packed; + static inline u32 rsi_get_queueno(u8 *addr, u16 offset) { return (le16_to_cpu(*(__le16 *)&addr[offset]) & 0x7000) >> 12; @@ -694,4 +725,8 @@ int rsi_send_wowlan_request(struct rsi_common *common, u16 flags, #endif int rsi_send_ps_request(struct rsi_hw *adapter, bool enable, struct ieee80211_vif *vif); +void init_bgscan_params(struct rsi_common *common); +int rsi_send_bgscan_params(struct rsi_common *common, int enable); +int rsi_send_bgscan_probe_req(struct rsi_common *common, + struct ieee80211_vif *vif); #endif diff --git a/drivers/net/wireless/st/cw1200/debug.c b/drivers/net/wireless/st/cw1200/debug.c index 2231ba08bc1f..d94266d9d0b8 100644 --- a/drivers/net/wireless/st/cw1200/debug.c +++ b/drivers/net/wireless/st/cw1200/debug.c @@ -371,28 +371,14 @@ int cw1200_debug_init(struct cw1200_common *priv) d->debugfs_phy = debugfs_create_dir("cw1200", priv->hw->wiphy->debugfsdir); - if (!d->debugfs_phy) - goto err; - - if (!debugfs_create_file("status", 0400, d->debugfs_phy, - priv, &cw1200_status_fops)) - goto err; - - if (!debugfs_create_file("counters", 0400, d->debugfs_phy, - priv, &cw1200_counters_fops)) - goto err; - - if (!debugfs_create_file("wsm_dumps", 0200, d->debugfs_phy, - priv, &fops_wsm_dumps)) - goto err; + debugfs_create_file("status", 0400, d->debugfs_phy, priv, + &cw1200_status_fops); + debugfs_create_file("counters", 0400, d->debugfs_phy, priv, + &cw1200_counters_fops); + debugfs_create_file("wsm_dumps", 0200, d->debugfs_phy, priv, + &fops_wsm_dumps); return 0; - -err: - priv->debug = NULL; - debugfs_remove_recursive(d->debugfs_phy); - kfree(d); - return ret; } void cw1200_debug_release(struct cw1200_common *priv) diff --git a/drivers/net/wireless/st/cw1200/fwio.c b/drivers/net/wireless/st/cw1200/fwio.c index 30e7646d04af..b7881232499c 100644 --- a/drivers/net/wireless/st/cw1200/fwio.c +++ b/drivers/net/wireless/st/cw1200/fwio.c @@ -465,8 +465,8 @@ int cw1200_load_firmware(struct cw1200_common *priv) if (!(val32 & ST90TDS_CONFIG_ACCESS_MODE_BIT)) { pr_err("Device is already in QUEUE mode!\n"); - ret = -EINVAL; - goto out; + ret = -EINVAL; + goto out; } switch (priv->hw_type) { diff --git a/drivers/net/wireless/st/cw1200/queue.c b/drivers/net/wireless/st/cw1200/queue.c index 7c31b63b8258..7895efefa95d 100644 --- a/drivers/net/wireless/st/cw1200/queue.c +++ b/drivers/net/wireless/st/cw1200/queue.c @@ -283,7 +283,6 @@ int cw1200_queue_put(struct cw1200_queue *queue, struct cw1200_txpriv *txpriv) { int ret = 0; - LIST_HEAD(gc_list); struct cw1200_queue_stats *stats = queue->stats; if (txpriv->link_id >= queue->stats->map_capacity) diff --git a/drivers/net/wireless/st/cw1200/scan.c b/drivers/net/wireless/st/cw1200/scan.c index 0a9eac93dd01..71e9b91cf15b 100644 --- a/drivers/net/wireless/st/cw1200/scan.c +++ b/drivers/net/wireless/st/cw1200/scan.c @@ -84,8 +84,11 @@ int cw1200_hw_scan(struct ieee80211_hw *hw, frame.skb = ieee80211_probereq_get(hw, priv->vif->addr, NULL, 0, req->ie_len); - if (!frame.skb) + if (!frame.skb) { + mutex_unlock(&priv->conf_mutex); + up(&priv->scan.lock); return -ENOMEM; + } if (req->ie_len) skb_put_data(frame.skb, req->ie, req->ie_len); diff --git a/drivers/net/wireless/ti/wl1251/debugfs.c b/drivers/net/wireless/ti/wl1251/debugfs.c index 448da1f8c22f..c99b23aaa70e 100644 --- a/drivers/net/wireless/ti/wl1251/debugfs.c +++ b/drivers/net/wireless/ti/wl1251/debugfs.c @@ -54,11 +54,6 @@ static const struct file_operations name## _ops = { \ #define DEBUGFS_ADD(name, parent) \ wl->debugfs.name = debugfs_create_file(#name, 0400, parent, \ wl, &name## _ops); \ - if (IS_ERR(wl->debugfs.name)) { \ - ret = PTR_ERR(wl->debugfs.name); \ - wl->debugfs.name = NULL; \ - goto out; \ - } #define DEBUGFS_DEL(name) \ do { \ @@ -354,10 +349,8 @@ static void wl1251_debugfs_delete_files(struct wl1251 *wl) DEBUGFS_DEL(excessive_retries); } -static int wl1251_debugfs_add_files(struct wl1251 *wl) +static void wl1251_debugfs_add_files(struct wl1251 *wl) { - int ret = 0; - DEBUGFS_FWSTATS_ADD(tx, internal_desc_overflow); DEBUGFS_FWSTATS_ADD(rx, out_of_mem); @@ -453,12 +446,6 @@ static int wl1251_debugfs_add_files(struct wl1251 *wl) DEBUGFS_ADD(tx_queue_status, wl->debugfs.rootdir); DEBUGFS_ADD(retry_count, wl->debugfs.rootdir); DEBUGFS_ADD(excessive_retries, wl->debugfs.rootdir); - -out: - if (ret < 0) - wl1251_debugfs_delete_files(wl); - - return ret; } void wl1251_debugfs_reset(struct wl1251 *wl) @@ -471,56 +458,20 @@ void wl1251_debugfs_reset(struct wl1251 *wl) int wl1251_debugfs_init(struct wl1251 *wl) { - int ret; + wl->stats.fw_stats = kzalloc(sizeof(*wl->stats.fw_stats), GFP_KERNEL); + if (!wl->stats.fw_stats) + return -ENOMEM; wl->debugfs.rootdir = debugfs_create_dir(KBUILD_MODNAME, NULL); - if (IS_ERR(wl->debugfs.rootdir)) { - ret = PTR_ERR(wl->debugfs.rootdir); - wl->debugfs.rootdir = NULL; - goto err; - } - wl->debugfs.fw_statistics = debugfs_create_dir("fw-statistics", wl->debugfs.rootdir); - if (IS_ERR(wl->debugfs.fw_statistics)) { - ret = PTR_ERR(wl->debugfs.fw_statistics); - wl->debugfs.fw_statistics = NULL; - goto err_root; - } - - wl->stats.fw_stats = kzalloc(sizeof(*wl->stats.fw_stats), - GFP_KERNEL); - - if (!wl->stats.fw_stats) { - ret = -ENOMEM; - goto err_fw; - } - wl->stats.fw_stats_update = jiffies; - ret = wl1251_debugfs_add_files(wl); - - if (ret < 0) - goto err_file; + wl1251_debugfs_add_files(wl); return 0; - -err_file: - kfree(wl->stats.fw_stats); - wl->stats.fw_stats = NULL; - -err_fw: - debugfs_remove(wl->debugfs.fw_statistics); - wl->debugfs.fw_statistics = NULL; - -err_root: - debugfs_remove(wl->debugfs.rootdir); - wl->debugfs.rootdir = NULL; - -err: - return ret; } void wl1251_debugfs_exit(struct wl1251 *wl) diff --git a/drivers/net/wireless/ti/wl12xx/debugfs.c b/drivers/net/wireless/ti/wl12xx/debugfs.c index 0521cbf858cf..6c3c04eca8fd 100644 --- a/drivers/net/wireless/ti/wl12xx/debugfs.c +++ b/drivers/net/wireless/ti/wl12xx/debugfs.c @@ -125,20 +125,10 @@ WL12XX_DEBUGFS_FWSTATS_FILE(rxpipe, tx_xfr_host_int_trig_rx_data, "%u"); int wl12xx_debugfs_add_files(struct wl1271 *wl, struct dentry *rootdir) { - int ret = 0; - struct dentry *entry, *stats, *moddir; + struct dentry *stats, *moddir; moddir = debugfs_create_dir(KBUILD_MODNAME, rootdir); - if (!moddir || IS_ERR(moddir)) { - entry = moddir; - goto err; - } - stats = debugfs_create_dir("fw_stats", moddir); - if (!stats || IS_ERR(stats)) { - entry = stats; - goto err; - } DEBUGFS_FWSTATS_ADD(tx, internal_desc_overflow); @@ -232,12 +222,4 @@ int wl12xx_debugfs_add_files(struct wl1271 *wl, DEBUGFS_FWSTATS_ADD(rxpipe, tx_xfr_host_int_trig_rx_data); return 0; - -err: - if (IS_ERR(entry)) - ret = PTR_ERR(entry); - else - ret = -ENOMEM; - - return ret; } diff --git a/drivers/net/wireless/ti/wl18xx/debugfs.c b/drivers/net/wireless/ti/wl18xx/debugfs.c index 597e934c4630..5f4ec997ca59 100644 --- a/drivers/net/wireless/ti/wl18xx/debugfs.c +++ b/drivers/net/wireless/ti/wl18xx/debugfs.c @@ -422,20 +422,10 @@ static const struct file_operations radar_debug_mode_ops = { int wl18xx_debugfs_add_files(struct wl1271 *wl, struct dentry *rootdir) { - int ret = 0; - struct dentry *entry, *stats, *moddir; + struct dentry *stats, *moddir; moddir = debugfs_create_dir(KBUILD_MODNAME, rootdir); - if (!moddir || IS_ERR(moddir)) { - entry = moddir; - goto err; - } - stats = debugfs_create_dir("fw_stats", moddir); - if (!stats || IS_ERR(stats)) { - entry = stats; - goto err; - } DEBUGFS_ADD(clear_fw_stats, stats); @@ -590,12 +580,4 @@ int wl18xx_debugfs_add_files(struct wl1271 *wl, DEBUGFS_ADD(dynamic_fw_traces, moddir); return 0; - -err: - if (IS_ERR(entry)) - ret = PTR_ERR(entry); - else - ret = -ENOMEM; - - return ret; } diff --git a/drivers/net/wireless/ti/wlcore/cmd.c b/drivers/net/wireless/ti/wlcore/cmd.c index 903968735a74..348be0aed97e 100644 --- a/drivers/net/wireless/ti/wlcore/cmd.c +++ b/drivers/net/wireless/ti/wlcore/cmd.c @@ -1427,7 +1427,7 @@ int wl1271_cmd_set_sta_key(struct wl1271 *wl, struct wl12xx_vif *wlvif, ret = wl1271_cmd_send(wl, CMD_SET_KEYS, cmd, sizeof(*cmd), 0); if (ret < 0) { wl1271_warning("could not set keys"); - goto out; + goto out; } out: diff --git a/drivers/net/wireless/ti/wlcore/debugfs.c b/drivers/net/wireless/ti/wlcore/debugfs.c index aeb74e74698e..68acd901d384 100644 --- a/drivers/net/wireless/ti/wlcore/debugfs.c +++ b/drivers/net/wireless/ti/wlcore/debugfs.c @@ -1301,11 +1301,10 @@ static const struct file_operations fw_logger_ops = { .llseek = default_llseek, }; -static int wl1271_debugfs_add_files(struct wl1271 *wl, - struct dentry *rootdir) +static void wl1271_debugfs_add_files(struct wl1271 *wl, + struct dentry *rootdir) { - int ret = 0; - struct dentry *entry, *streaming; + struct dentry *streaming; DEBUGFS_ADD(tx_queue_len, rootdir); DEBUGFS_ADD(retry_count, rootdir); @@ -1330,23 +1329,11 @@ static int wl1271_debugfs_add_files(struct wl1271 *wl, DEBUGFS_ADD(fw_logger, rootdir); streaming = debugfs_create_dir("rx_streaming", rootdir); - if (!streaming || IS_ERR(streaming)) - goto err; DEBUGFS_ADD_PREFIX(rx_streaming, interval, streaming); DEBUGFS_ADD_PREFIX(rx_streaming, always, streaming); DEBUGFS_ADD_PREFIX(dev, mem, rootdir); - - return 0; - -err: - if (IS_ERR(entry)) - ret = PTR_ERR(entry); - else - ret = -ENOMEM; - - return ret; } void wl1271_debugfs_reset(struct wl1271 *wl) @@ -1367,11 +1354,6 @@ int wl1271_debugfs_init(struct wl1271 *wl) rootdir = debugfs_create_dir(KBUILD_MODNAME, wl->hw->wiphy->debugfsdir); - if (IS_ERR(rootdir)) { - ret = PTR_ERR(rootdir); - goto out; - } - wl->stats.fw_stats = kzalloc(wl->stats.fw_stats_len, GFP_KERNEL); if (!wl->stats.fw_stats) { ret = -ENOMEM; @@ -1380,9 +1362,7 @@ int wl1271_debugfs_init(struct wl1271 *wl) wl->stats.fw_stats_update = jiffies; - ret = wl1271_debugfs_add_files(wl, rootdir); - if (ret < 0) - goto out_exit; + wl1271_debugfs_add_files(wl, rootdir); ret = wlcore_debugfs_init(wl, rootdir); if (ret < 0) diff --git a/drivers/net/wireless/ti/wlcore/debugfs.h b/drivers/net/wireless/ti/wlcore/debugfs.h index bf14676e6515..a4952c4f587e 100644 --- a/drivers/net/wireless/ti/wlcore/debugfs.h +++ b/drivers/net/wireless/ti/wlcore/debugfs.h @@ -53,19 +53,15 @@ static const struct file_operations name## _ops = { \ #define DEBUGFS_ADD(name, parent) \ do { \ - entry = debugfs_create_file(#name, 0400, parent, \ - wl, &name## _ops); \ - if (!entry || IS_ERR(entry)) \ - goto err; \ + debugfs_create_file(#name, 0400, parent, \ + wl, &name## _ops); \ } while (0) #define DEBUGFS_ADD_PREFIX(prefix, name, parent) \ do { \ - entry = debugfs_create_file(#name, 0400, parent, \ + debugfs_create_file(#name, 0400, parent, \ wl, &prefix## _## name## _ops); \ - if (!entry || IS_ERR(entry)) \ - goto err; \ } while (0) #define DEBUGFS_FWSTATS_FILE(sub, name, fmt, struct_type) \ diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c index 26b187336875..2e12de813a5b 100644 --- a/drivers/net/wireless/ti/wlcore/main.c +++ b/drivers/net/wireless/ti/wlcore/main.c @@ -1085,8 +1085,11 @@ static int wl12xx_chip_wakeup(struct wl1271 *wl, bool plt) goto out; ret = wl12xx_fetch_firmware(wl, plt); - if (ret < 0) - goto out; + if (ret < 0) { + kfree(wl->fw_status); + kfree(wl->raw_fw_status); + kfree(wl->tx_res_if); + } out: return ret; diff --git a/drivers/net/wireless/ti/wlcore/sdio.c b/drivers/net/wireless/ti/wlcore/sdio.c index bd10165d7eec..4d4b07701149 100644 --- a/drivers/net/wireless/ti/wlcore/sdio.c +++ b/drivers/net/wireless/ti/wlcore/sdio.c @@ -164,6 +164,12 @@ static int wl12xx_sdio_power_on(struct wl12xx_sdio_glue *glue) } sdio_claim_host(func); + /* + * To guarantee that the SDIO card is power cycled, as required to make + * the FW programming to succeed, let's do a brute force HW reset. + */ + mmc_hw_reset(card->host); + sdio_enable_func(func); sdio_release_host(func); @@ -174,20 +180,13 @@ static int wl12xx_sdio_power_off(struct wl12xx_sdio_glue *glue) { struct sdio_func *func = dev_to_sdio_func(glue->dev); struct mmc_card *card = func->card; - int error; sdio_claim_host(func); sdio_disable_func(func); sdio_release_host(func); /* Let runtime PM know the card is powered off */ - error = pm_runtime_put(&card->dev); - if (error < 0 && error != -EBUSY) { - dev_err(&card->dev, "%s failed: %i\n", __func__, error); - - return error; - } - + pm_runtime_put(&card->dev); return 0; } diff --git a/drivers/net/wireless/virt_wifi.c b/drivers/net/wireless/virt_wifi.c index 3a93e4d9828b..71044c6cfd8c 100644 --- a/drivers/net/wireless/virt_wifi.c +++ b/drivers/net/wireless/virt_wifi.c @@ -14,11 +14,6 @@ #include <linux/etherdevice.h> #include <linux/module.h> -#include <net/cfg80211.h> -#include <net/rtnetlink.h> -#include <linux/etherdevice.h> -#include <linux/module.h> - static struct wiphy *common_wiphy; struct virt_wifi_wiphy_priv { @@ -429,13 +424,11 @@ static int virt_wifi_net_device_open(struct net_device *dev) static int virt_wifi_net_device_stop(struct net_device *dev) { struct virt_wifi_netdev_priv *n_priv = netdev_priv(dev); - struct virt_wifi_wiphy_priv *w_priv; n_priv->is_up = false; if (!dev->ieee80211_ptr) return 0; - w_priv = wiphy_priv(dev->ieee80211_ptr->wiphy); virt_wifi_cancel_scan(dev->ieee80211_ptr->wiphy); virt_wifi_cancel_connect(dev); diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c index 2625740bdc4a..330ddb64930f 100644 --- a/drivers/net/xen-netback/xenbus.c +++ b/drivers/net/xen-netback/xenbus.c @@ -655,7 +655,7 @@ static void frontend_changed(struct xenbus_device *dev, set_backend_state(be, XenbusStateClosed); if (xenbus_dev_is_online(dev)) break; - /* fall through if not online */ + /* fall through - if not online */ case XenbusStateUnknown: set_backend_state(be, XenbusStateClosed); device_unregister(&dev->dev); diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 150e49723c15..6a9dd68c0f4f 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1253,6 +1253,7 @@ static u32 nvme_passthru_start(struct nvme_ctrl *ctrl, struct nvme_ns *ns, * effects say only one namespace is affected. */ if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK)) { + mutex_lock(&ctrl->scan_lock); nvme_start_freeze(ctrl); nvme_wait_freeze(ctrl); } @@ -1281,8 +1282,10 @@ static void nvme_passthru_end(struct nvme_ctrl *ctrl, u32 effects) */ if (effects & NVME_CMD_EFFECTS_LBCC) nvme_update_formats(ctrl); - if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK)) + if (effects & (NVME_CMD_EFFECTS_LBCC | NVME_CMD_EFFECTS_CSE_MASK)) { nvme_unfreeze(ctrl); + mutex_unlock(&ctrl->scan_lock); + } if (effects & NVME_CMD_EFFECTS_CCC) nvme_init_identify(ctrl); if (effects & (NVME_CMD_EFFECTS_NIC | NVME_CMD_EFFECTS_NCC)) @@ -3401,6 +3404,7 @@ static void nvme_scan_work(struct work_struct *work) if (nvme_identify_ctrl(ctrl, &id)) return; + mutex_lock(&ctrl->scan_lock); nn = le32_to_cpu(id->nn); if (ctrl->vs >= NVME_VS(1, 1, 0) && !(ctrl->quirks & NVME_QUIRK_IDENTIFY_CNS)) { @@ -3409,6 +3413,7 @@ static void nvme_scan_work(struct work_struct *work) } nvme_scan_ns_sequential(ctrl, nn); out_free_id: + mutex_unlock(&ctrl->scan_lock); kfree(id); down_write(&ctrl->namespaces_rwsem); list_sort(NULL, &ctrl->namespaces, ns_cmp); @@ -3652,6 +3657,7 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev, ctrl->state = NVME_CTRL_NEW; spin_lock_init(&ctrl->lock); + mutex_init(&ctrl->scan_lock); INIT_LIST_HEAD(&ctrl->namespaces); init_rwsem(&ctrl->namespaces_rwsem); ctrl->dev = dev; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index ab961bdeea89..c4a1bb41abf0 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -154,6 +154,7 @@ struct nvme_ctrl { enum nvme_ctrl_state state; bool identified; spinlock_t lock; + struct mutex scan_lock; const struct nvme_ctrl_ops *ops; struct request_queue *admin_q; struct request_queue *connect_q; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 9bc585415d9b..7fee665ec45e 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2557,27 +2557,18 @@ static void nvme_reset_work(struct work_struct *work) if (dev->ctrl.ctrl_config & NVME_CC_ENABLE) nvme_dev_disable(dev, false); - /* - * Introduce CONNECTING state from nvme-fc/rdma transports to mark the - * initializing procedure here. - */ - if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_CONNECTING)) { - dev_warn(dev->ctrl.device, - "failed to mark controller CONNECTING\n"); - goto out; - } - + mutex_lock(&dev->shutdown_lock); result = nvme_pci_enable(dev); if (result) - goto out; + goto out_unlock; result = nvme_pci_configure_admin_queue(dev); if (result) - goto out; + goto out_unlock; result = nvme_alloc_admin_tags(dev); if (result) - goto out; + goto out_unlock; /* * Limit the max command size to prevent iod->sg allocations going @@ -2585,6 +2576,17 @@ static void nvme_reset_work(struct work_struct *work) */ dev->ctrl.max_hw_sectors = NVME_MAX_KB_SZ << 1; dev->ctrl.max_segments = NVME_MAX_SEGS; + mutex_unlock(&dev->shutdown_lock); + + /* + * Introduce CONNECTING state from nvme-fc/rdma transports to mark the + * initializing procedure here. + */ + if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_CONNECTING)) { + dev_warn(dev->ctrl.device, + "failed to mark controller CONNECTING\n"); + goto out; + } result = nvme_init_identify(&dev->ctrl); if (result) @@ -2649,6 +2651,8 @@ static void nvme_reset_work(struct work_struct *work) nvme_start_ctrl(&dev->ctrl); return; + out_unlock: + mutex_unlock(&dev->shutdown_lock); out: nvme_remove_dead_ctrl(dev, result); } diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c index 5ad1342f5682..de6157357e26 100644 --- a/drivers/of/of_mdio.c +++ b/drivers/of/of_mdio.c @@ -16,7 +16,6 @@ #include <linux/phy.h> #include <linux/phy_fixed.h> #include <linux/of.h> -#include <linux/of_gpio.h> #include <linux/of_irq.h> #include <linux/of_mdio.h> #include <linux/of_net.h> @@ -463,7 +462,6 @@ int of_phy_register_fixed_link(struct device_node *np) struct device_node *fixed_link_node; u32 fixed_link_prop[5]; const char *managed; - int link_gpio = -1; if (of_property_read_string(np, "managed", &managed) == 0 && strcmp(managed, "in-band-status") == 0) { @@ -485,11 +483,7 @@ int of_phy_register_fixed_link(struct device_node *np) status.pause = of_property_read_bool(fixed_link_node, "pause"); status.asym_pause = of_property_read_bool(fixed_link_node, "asym-pause"); - link_gpio = of_get_named_gpio_flags(fixed_link_node, - "link-gpios", 0, NULL); of_node_put(fixed_link_node); - if (link_gpio == -EPROBE_DEFER) - return -EPROBE_DEFER; goto register_phy; } @@ -508,8 +502,7 @@ int of_phy_register_fixed_link(struct device_node *np) return -ENODEV; register_phy: - return PTR_ERR_OR_ZERO(fixed_phy_register(PHY_POLL, &status, link_gpio, - np)); + return PTR_ERR_OR_ZERO(fixed_phy_register(PHY_POLL, &status, np)); } EXPORT_SYMBOL(of_phy_register_fixed_link); diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c index 52e47dac028f..80f843030e36 100644 --- a/drivers/pci/controller/dwc/pci-imx6.c +++ b/drivers/pci/controller/dwc/pci-imx6.c @@ -310,6 +310,9 @@ static int imx6_pcie_attach_pd(struct device *dev) imx6_pcie->pd_pcie = dev_pm_domain_attach_by_name(dev, "pcie"); if (IS_ERR(imx6_pcie->pd_pcie)) return PTR_ERR(imx6_pcie->pd_pcie); + /* Do nothing when power domain missing */ + if (!imx6_pcie->pd_pcie) + return 0; link = device_link_add(dev, imx6_pcie->pd_pcie, DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME | @@ -323,13 +326,13 @@ static int imx6_pcie_attach_pd(struct device *dev) if (IS_ERR(imx6_pcie->pd_pcie_phy)) return PTR_ERR(imx6_pcie->pd_pcie_phy); - device_link_add(dev, imx6_pcie->pd_pcie_phy, + link = device_link_add(dev, imx6_pcie->pd_pcie_phy, DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME | DL_FLAG_RPM_ACTIVE); - if (IS_ERR(link)) { - dev_err(dev, "Failed to add device_link to pcie_phy pd: %ld\n", PTR_ERR(link)); - return PTR_ERR(link); + if (!link) { + dev_err(dev, "Failed to add device_link to pcie_phy pd.\n"); + return -EINVAL; } return 0; diff --git a/drivers/pci/controller/dwc/pcie-armada8k.c b/drivers/pci/controller/dwc/pcie-armada8k.c index b171b6bc15c8..0c389a30ef5d 100644 --- a/drivers/pci/controller/dwc/pcie-armada8k.c +++ b/drivers/pci/controller/dwc/pcie-armada8k.c @@ -22,7 +22,6 @@ #include <linux/resource.h> #include <linux/of_pci.h> #include <linux/of_irq.h> -#include <linux/gpio/consumer.h> #include "pcie-designware.h" @@ -30,7 +29,6 @@ struct armada8k_pcie { struct dw_pcie *pci; struct clk *clk; struct clk *clk_reg; - struct gpio_desc *reset_gpio; }; #define PCIE_VENDOR_REGS_OFFSET 0x8000 @@ -139,12 +137,6 @@ static int armada8k_pcie_host_init(struct pcie_port *pp) struct dw_pcie *pci = to_dw_pcie_from_pp(pp); struct armada8k_pcie *pcie = to_armada8k_pcie(pci); - if (pcie->reset_gpio) { - /* assert and then deassert the reset signal */ - gpiod_set_value_cansleep(pcie->reset_gpio, 1); - msleep(100); - gpiod_set_value_cansleep(pcie->reset_gpio, 0); - } dw_pcie_setup_rc(pp); armada8k_pcie_establish_link(pcie); @@ -257,14 +249,6 @@ static int armada8k_pcie_probe(struct platform_device *pdev) goto fail_clkreg; } - /* Get reset gpio signal and hold asserted (logically high) */ - pcie->reset_gpio = devm_gpiod_get_optional(dev, "reset", - GPIOD_OUT_HIGH); - if (IS_ERR(pcie->reset_gpio)) { - ret = PTR_ERR(pcie->reset_gpio); - goto fail_clkreg; - } - platform_set_drvdata(pdev, pcie); ret = armada8k_add_pcie_port(pcie, pdev); diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index b0a413f3f7ca..e2a879e93d86 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -639,8 +639,9 @@ static void quirk_synopsys_haps(struct pci_dev *pdev) break; } } -DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_SYNOPSYS, PCI_ANY_ID, - quirk_synopsys_haps); +DECLARE_PCI_FIXUP_CLASS_HEADER(PCI_VENDOR_ID_SYNOPSYS, PCI_ANY_ID, + PCI_CLASS_SERIAL_USB_XHCI, 0, + quirk_synopsys_haps); /* * Let's make the southbridge information explicit instead of having to diff --git a/drivers/phy/marvell/Kconfig b/drivers/phy/marvell/Kconfig index 6fb4b56e4c14..224ea4e6a46d 100644 --- a/drivers/phy/marvell/Kconfig +++ b/drivers/phy/marvell/Kconfig @@ -21,6 +21,16 @@ config PHY_BERLIN_USB help Enable this to support the USB PHY on Marvell Berlin SoCs. +config PHY_MVEBU_A38X_COMPHY + tristate "Marvell Armada 38x comphy driver" + depends on ARCH_MVEBU || COMPILE_TEST + depends on OF + select GENERIC_PHY + help + This driver allows to control the comphy, an hardware block providing + shared serdes PHYs on Marvell Armada 38x. Its serdes lanes can be + used by various controllers (Ethernet, sata, usb, PCIe...). + config PHY_MVEBU_CP110_COMPHY tristate "Marvell CP110 comphy driver" depends on ARCH_MVEBU || COMPILE_TEST diff --git a/drivers/phy/marvell/Makefile b/drivers/phy/marvell/Makefile index 3975b144f8ec..59b6c03ef756 100644 --- a/drivers/phy/marvell/Makefile +++ b/drivers/phy/marvell/Makefile @@ -2,6 +2,7 @@ obj-$(CONFIG_ARMADA375_USBCLUSTER_PHY) += phy-armada375-usb2.o obj-$(CONFIG_PHY_BERLIN_SATA) += phy-berlin-sata.o obj-$(CONFIG_PHY_BERLIN_USB) += phy-berlin-usb.o +obj-$(CONFIG_PHY_MVEBU_A38X_COMPHY) += phy-armada38x-comphy.o obj-$(CONFIG_PHY_MVEBU_CP110_COMPHY) += phy-mvebu-cp110-comphy.o obj-$(CONFIG_PHY_MVEBU_SATA) += phy-mvebu-sata.o obj-$(CONFIG_PHY_PXA_28NM_HSIC) += phy-pxa-28nm-hsic.o diff --git a/drivers/phy/marvell/phy-armada38x-comphy.c b/drivers/phy/marvell/phy-armada38x-comphy.c new file mode 100644 index 000000000000..3e00bc679d4e --- /dev/null +++ b/drivers/phy/marvell/phy-armada38x-comphy.c @@ -0,0 +1,237 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2018 Russell King, Deep Blue Solutions Ltd. + * + * Partly derived from CP110 comphy driver by Antoine Tenart + * <antoine.tenart@bootlin.com> + */ +#include <linux/delay.h> +#include <linux/iopoll.h> +#include <linux/module.h> +#include <linux/phy/phy.h> +#include <linux/phy.h> +#include <linux/platform_device.h> + +#define MAX_A38X_COMPHY 6 +#define MAX_A38X_PORTS 3 + +#define COMPHY_CFG1 0x00 +#define COMPHY_CFG1_GEN_TX(x) ((x) << 26) +#define COMPHY_CFG1_GEN_TX_MSK COMPHY_CFG1_GEN_TX(15) +#define COMPHY_CFG1_GEN_RX(x) ((x) << 22) +#define COMPHY_CFG1_GEN_RX_MSK COMPHY_CFG1_GEN_RX(15) +#define GEN_SGMII_1_25GBPS 6 +#define GEN_SGMII_3_125GBPS 8 + +#define COMPHY_STAT1 0x18 +#define COMPHY_STAT1_PLL_RDY_TX BIT(3) +#define COMPHY_STAT1_PLL_RDY_RX BIT(2) + +#define COMPHY_SELECTOR 0xfc + +struct a38x_comphy; + +struct a38x_comphy_lane { + void __iomem *base; + struct a38x_comphy *priv; + unsigned int n; + + int port; +}; + +struct a38x_comphy { + void __iomem *base; + struct device *dev; + struct a38x_comphy_lane lane[MAX_A38X_COMPHY]; +}; + +static const u8 gbe_mux[MAX_A38X_COMPHY][MAX_A38X_PORTS] = { + { 0, 0, 0 }, + { 4, 5, 0 }, + { 0, 4, 0 }, + { 0, 0, 4 }, + { 0, 3, 0 }, + { 0, 0, 3 }, +}; + +static void a38x_comphy_set_reg(struct a38x_comphy_lane *lane, + unsigned int offset, u32 mask, u32 value) +{ + u32 val; + + val = readl_relaxed(lane->base + offset) & ~mask; + writel(val | value, lane->base + offset); +} + +static void a38x_comphy_set_speed(struct a38x_comphy_lane *lane, + unsigned int gen_tx, unsigned int gen_rx) +{ + a38x_comphy_set_reg(lane, COMPHY_CFG1, + COMPHY_CFG1_GEN_TX_MSK | COMPHY_CFG1_GEN_RX_MSK, + COMPHY_CFG1_GEN_TX(gen_tx) | + COMPHY_CFG1_GEN_RX(gen_rx)); +} + +static int a38x_comphy_poll(struct a38x_comphy_lane *lane, + unsigned int offset, u32 mask, u32 value) +{ + u32 val; + int ret; + + ret = readl_relaxed_poll_timeout_atomic(lane->base + offset, val, + (val & mask) == value, + 1000, 150000); + + if (ret) + dev_err(lane->priv->dev, + "comphy%u: timed out waiting for status\n", lane->n); + + return ret; +} + +/* + * We only support changing the speed for comphys configured for GBE. + * Since that is all we do, we only poll for PLL ready status. + */ +static int a38x_comphy_set_mode(struct phy *phy, enum phy_mode mode, int sub) +{ + struct a38x_comphy_lane *lane = phy_get_drvdata(phy); + unsigned int gen; + + if (mode != PHY_MODE_ETHERNET) + return -EINVAL; + + switch (sub) { + case PHY_INTERFACE_MODE_SGMII: + case PHY_INTERFACE_MODE_1000BASEX: + gen = GEN_SGMII_1_25GBPS; + break; + + case PHY_INTERFACE_MODE_2500BASEX: + gen = GEN_SGMII_3_125GBPS; + break; + + default: + return -EINVAL; + } + + a38x_comphy_set_speed(lane, gen, gen); + + return a38x_comphy_poll(lane, COMPHY_STAT1, + COMPHY_STAT1_PLL_RDY_TX | + COMPHY_STAT1_PLL_RDY_RX, + COMPHY_STAT1_PLL_RDY_TX | + COMPHY_STAT1_PLL_RDY_RX); +} + +static const struct phy_ops a38x_comphy_ops = { + .set_mode = a38x_comphy_set_mode, + .owner = THIS_MODULE, +}; + +static struct phy *a38x_comphy_xlate(struct device *dev, + struct of_phandle_args *args) +{ + struct a38x_comphy_lane *lane; + struct phy *phy; + u32 val; + + if (WARN_ON(args->args[0] >= MAX_A38X_PORTS)) + return ERR_PTR(-EINVAL); + + phy = of_phy_simple_xlate(dev, args); + if (IS_ERR(phy)) + return phy; + + lane = phy_get_drvdata(phy); + if (lane->port >= 0) + return ERR_PTR(-EBUSY); + + lane->port = args->args[0]; + + val = readl_relaxed(lane->priv->base + COMPHY_SELECTOR); + val = (val >> (4 * lane->n)) & 0xf; + + if (!gbe_mux[lane->n][lane->port] || + val != gbe_mux[lane->n][lane->port]) { + dev_warn(lane->priv->dev, + "comphy%u: not configured for GBE\n", lane->n); + phy = ERR_PTR(-EINVAL); + } + + return phy; +} + +static int a38x_comphy_probe(struct platform_device *pdev) +{ + struct phy_provider *provider; + struct device_node *child; + struct a38x_comphy *priv; + struct resource *res; + void __iomem *base; + + priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(base)) + return PTR_ERR(base); + + priv->dev = &pdev->dev; + priv->base = base; + + for_each_available_child_of_node(pdev->dev.of_node, child) { + struct phy *phy; + int ret; + u32 val; + + ret = of_property_read_u32(child, "reg", &val); + if (ret < 0) { + dev_err(&pdev->dev, "missing 'reg' property (%d)\n", + ret); + continue; + } + + if (val >= MAX_A38X_COMPHY || priv->lane[val].base) { + dev_err(&pdev->dev, "invalid 'reg' property\n"); + continue; + } + + phy = devm_phy_create(&pdev->dev, child, &a38x_comphy_ops); + if (IS_ERR(phy)) + return PTR_ERR(phy); + + priv->lane[val].base = base + 0x28 * val; + priv->lane[val].priv = priv; + priv->lane[val].n = val; + priv->lane[val].port = -1; + phy_set_drvdata(phy, &priv->lane[val]); + } + + dev_set_drvdata(&pdev->dev, priv); + + provider = devm_of_phy_provider_register(&pdev->dev, a38x_comphy_xlate); + + return PTR_ERR_OR_ZERO(provider); +} + +static const struct of_device_id a38x_comphy_of_match_table[] = { + { .compatible = "marvell,armada-380-comphy" }, + { }, +}; +MODULE_DEVICE_TABLE(of, a38x_comphy_of_match_table); + +static struct platform_driver a38x_comphy_driver = { + .probe = a38x_comphy_probe, + .driver = { + .name = "armada-38x-comphy", + .of_match_table = a38x_comphy_of_match_table, + }, +}; +module_platform_driver(a38x_comphy_driver); + +MODULE_AUTHOR("Russell King <rmk+kernel@armlinux.org.uk>"); +MODULE_DESCRIPTION("Common PHY driver for Armada 38x SoCs"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c index 05044e323ea5..03ec7a5d9d0b 100644 --- a/drivers/pinctrl/intel/pinctrl-cherryview.c +++ b/drivers/pinctrl/intel/pinctrl-cherryview.c @@ -1513,7 +1513,7 @@ static const struct dmi_system_id chv_no_valid_mask[] = { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"), DMI_MATCH(DMI_PRODUCT_FAMILY, "Intel_Strago"), - DMI_MATCH(DMI_BOARD_VERSION, "1.0"), + DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"), }, }, { @@ -1521,7 +1521,7 @@ static const struct dmi_system_id chv_no_valid_mask[] = { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "HP"), DMI_MATCH(DMI_PRODUCT_NAME, "Setzer"), - DMI_MATCH(DMI_BOARD_VERSION, "1.0"), + DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"), }, }, { @@ -1529,7 +1529,7 @@ static const struct dmi_system_id chv_no_valid_mask[] = { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"), DMI_MATCH(DMI_PRODUCT_NAME, "Cyan"), - DMI_MATCH(DMI_BOARD_VERSION, "1.0"), + DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"), }, }, { @@ -1537,7 +1537,7 @@ static const struct dmi_system_id chv_no_valid_mask[] = { .matches = { DMI_MATCH(DMI_SYS_VENDOR, "GOOGLE"), DMI_MATCH(DMI_PRODUCT_NAME, "Celes"), - DMI_MATCH(DMI_BOARD_VERSION, "1.0"), + DMI_MATCH(DMI_PRODUCT_VERSION, "1.0"), }, }, {} diff --git a/drivers/pinctrl/mediatek/Kconfig b/drivers/pinctrl/mediatek/Kconfig index 1817786ab6aa..a005cbccb4f7 100644 --- a/drivers/pinctrl/mediatek/Kconfig +++ b/drivers/pinctrl/mediatek/Kconfig @@ -45,12 +45,14 @@ config PINCTRL_MT2701 config PINCTRL_MT7623 bool "Mediatek MT7623 pin control with generic binding" depends on MACH_MT7623 || COMPILE_TEST + depends on OF default MACH_MT7623 select PINCTRL_MTK_MOORE config PINCTRL_MT7629 bool "Mediatek MT7629 pin control" depends on MACH_MT7629 || COMPILE_TEST + depends on OF default MACH_MT7629 select PINCTRL_MTK_MOORE @@ -92,6 +94,7 @@ config PINCTRL_MT6797 config PINCTRL_MT7622 bool "MediaTek MT7622 pin control" + depends on OF depends on ARM64 || COMPILE_TEST default ARM64 && ARCH_MEDIATEK select PINCTRL_MTK_MOORE diff --git a/drivers/pinctrl/pinctrl-mcp23s08.c b/drivers/pinctrl/pinctrl-mcp23s08.c index b03481ef99a1..98905d4a79ca 100644 --- a/drivers/pinctrl/pinctrl-mcp23s08.c +++ b/drivers/pinctrl/pinctrl-mcp23s08.c @@ -832,8 +832,13 @@ static int mcp23s08_probe_one(struct mcp23s08 *mcp, struct device *dev, break; case MCP_TYPE_S18: + one_regmap_config = + devm_kmemdup(dev, &mcp23x17_regmap, + sizeof(struct regmap_config), GFP_KERNEL); + if (!one_regmap_config) + return -ENOMEM; mcp->regmap = devm_regmap_init(dev, &mcp23sxx_spi_regmap, mcp, - &mcp23x17_regmap); + one_regmap_config); mcp->reg_shift = 1; mcp->chip.ngpio = 16; mcp->chip.label = "mcp23s18"; diff --git a/drivers/pinctrl/sunxi/pinctrl-sun50i-h6.c b/drivers/pinctrl/sunxi/pinctrl-sun50i-h6.c index aa8b58125568..ef4268cc6227 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sun50i-h6.c +++ b/drivers/pinctrl/sunxi/pinctrl-sun50i-h6.c @@ -588,7 +588,7 @@ static const unsigned int h6_irq_bank_map[] = { 1, 5, 6, 7 }; static const struct sunxi_pinctrl_desc h6_pinctrl_data = { .pins = h6_pins, .npins = ARRAY_SIZE(h6_pins), - .irq_banks = 3, + .irq_banks = 4, .irq_bank_map = h6_irq_bank_map, .irq_read_needs_mux = true, }; diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c index 5d9184d18c16..0e7fa69e93df 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c +++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c @@ -698,26 +698,24 @@ static int sunxi_pmx_request(struct pinctrl_dev *pctldev, unsigned offset) { struct sunxi_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev); unsigned short bank = offset / PINS_PER_BANK; - struct sunxi_pinctrl_regulator *s_reg = &pctl->regulators[bank]; - struct regulator *reg; + unsigned short bank_offset = bank - pctl->desc->pin_base / + PINS_PER_BANK; + struct sunxi_pinctrl_regulator *s_reg = &pctl->regulators[bank_offset]; + struct regulator *reg = s_reg->regulator; + char supply[16]; int ret; - reg = s_reg->regulator; - if (!reg) { - char supply[16]; - - snprintf(supply, sizeof(supply), "vcc-p%c", 'a' + bank); - reg = regulator_get(pctl->dev, supply); - if (IS_ERR(reg)) { - dev_err(pctl->dev, "Couldn't get bank P%c regulator\n", - 'A' + bank); - return PTR_ERR(reg); - } - - s_reg->regulator = reg; - refcount_set(&s_reg->refcount, 1); - } else { + if (reg) { refcount_inc(&s_reg->refcount); + return 0; + } + + snprintf(supply, sizeof(supply), "vcc-p%c", 'a' + bank); + reg = regulator_get(pctl->dev, supply); + if (IS_ERR(reg)) { + dev_err(pctl->dev, "Couldn't get bank P%c regulator\n", + 'A' + bank); + return PTR_ERR(reg); } ret = regulator_enable(reg); @@ -727,13 +725,13 @@ static int sunxi_pmx_request(struct pinctrl_dev *pctldev, unsigned offset) goto out; } + s_reg->regulator = reg; + refcount_set(&s_reg->refcount, 1); + return 0; out: - if (refcount_dec_and_test(&s_reg->refcount)) { - regulator_put(s_reg->regulator); - s_reg->regulator = NULL; - } + regulator_put(s_reg->regulator); return ret; } @@ -742,7 +740,9 @@ static int sunxi_pmx_free(struct pinctrl_dev *pctldev, unsigned offset) { struct sunxi_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev); unsigned short bank = offset / PINS_PER_BANK; - struct sunxi_pinctrl_regulator *s_reg = &pctl->regulators[bank]; + unsigned short bank_offset = bank - pctl->desc->pin_base / + PINS_PER_BANK; + struct sunxi_pinctrl_regulator *s_reg = &pctl->regulators[bank_offset]; if (!refcount_dec_and_test(&s_reg->refcount)) return 0; diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.h b/drivers/pinctrl/sunxi/pinctrl-sunxi.h index e340d2a24b44..034c0317c8d6 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sunxi.h +++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.h @@ -136,7 +136,7 @@ struct sunxi_pinctrl { struct gpio_chip *chip; const struct sunxi_pinctrl_desc *desc; struct device *dev; - struct sunxi_pinctrl_regulator regulators[12]; + struct sunxi_pinctrl_regulator regulators[9]; struct irq_domain *domain; struct sunxi_pinctrl_function *functions; unsigned nfunctions; diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig index 5e2109c54c7c..b5e9db85e881 100644 --- a/drivers/platform/x86/Kconfig +++ b/drivers/platform/x86/Kconfig @@ -905,6 +905,7 @@ config TOSHIBA_WMI config ACPI_CMPC tristate "CMPC Laptop Extras" depends on ACPI && INPUT + depends on BACKLIGHT_LCD_SUPPORT depends on RFKILL || RFKILL=n select BACKLIGHT_CLASS_DEVICE help @@ -1128,6 +1129,7 @@ config INTEL_OAKTRAIL config SAMSUNG_Q10 tristate "Samsung Q10 Extras" depends on ACPI + depends on BACKLIGHT_LCD_SUPPORT select BACKLIGHT_CLASS_DEVICE ---help--- This driver provides support for backlight control on Samsung Q10 diff --git a/drivers/ptp/Kconfig b/drivers/ptp/Kconfig index aeb4a8b2e0af..7fe18636915a 100644 --- a/drivers/ptp/Kconfig +++ b/drivers/ptp/Kconfig @@ -43,7 +43,7 @@ config PTP_1588_CLOCK_DTE config PTP_1588_CLOCK_QORIQ tristate "Freescale QorIQ 1588 timer as PTP clock" - depends on GIANFAR || FSL_DPAA_ETH + depends on GIANFAR || FSL_DPAA_ETH || FSL_ENETC || FSL_ENETC_VF depends on PTP_1588_CLOCK default y help diff --git a/drivers/ptp/ptp_qoriq.c b/drivers/ptp/ptp_qoriq.c index 43416b2e8a13..42d3654f77f0 100644 --- a/drivers/ptp/ptp_qoriq.c +++ b/drivers/ptp/ptp_qoriq.c @@ -22,7 +22,6 @@ #include <linux/device.h> #include <linux/hrtimer.h> -#include <linux/interrupt.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/of.h> @@ -37,61 +36,61 @@ * Register access functions */ -/* Caller must hold qoriq_ptp->lock. */ -static u64 tmr_cnt_read(struct qoriq_ptp *qoriq_ptp) +/* Caller must hold ptp_qoriq->lock. */ +static u64 tmr_cnt_read(struct ptp_qoriq *ptp_qoriq) { - struct qoriq_ptp_registers *regs = &qoriq_ptp->regs; + struct ptp_qoriq_registers *regs = &ptp_qoriq->regs; u64 ns; u32 lo, hi; - lo = qoriq_read(®s->ctrl_regs->tmr_cnt_l); - hi = qoriq_read(®s->ctrl_regs->tmr_cnt_h); + lo = ptp_qoriq->read(®s->ctrl_regs->tmr_cnt_l); + hi = ptp_qoriq->read(®s->ctrl_regs->tmr_cnt_h); ns = ((u64) hi) << 32; ns |= lo; return ns; } -/* Caller must hold qoriq_ptp->lock. */ -static void tmr_cnt_write(struct qoriq_ptp *qoriq_ptp, u64 ns) +/* Caller must hold ptp_qoriq->lock. */ +static void tmr_cnt_write(struct ptp_qoriq *ptp_qoriq, u64 ns) { - struct qoriq_ptp_registers *regs = &qoriq_ptp->regs; + struct ptp_qoriq_registers *regs = &ptp_qoriq->regs; u32 hi = ns >> 32; u32 lo = ns & 0xffffffff; - qoriq_write(®s->ctrl_regs->tmr_cnt_l, lo); - qoriq_write(®s->ctrl_regs->tmr_cnt_h, hi); + ptp_qoriq->write(®s->ctrl_regs->tmr_cnt_l, lo); + ptp_qoriq->write(®s->ctrl_regs->tmr_cnt_h, hi); } -/* Caller must hold qoriq_ptp->lock. */ -static void set_alarm(struct qoriq_ptp *qoriq_ptp) +/* Caller must hold ptp_qoriq->lock. */ +static void set_alarm(struct ptp_qoriq *ptp_qoriq) { - struct qoriq_ptp_registers *regs = &qoriq_ptp->regs; + struct ptp_qoriq_registers *regs = &ptp_qoriq->regs; u64 ns; u32 lo, hi; - ns = tmr_cnt_read(qoriq_ptp) + 1500000000ULL; + ns = tmr_cnt_read(ptp_qoriq) + 1500000000ULL; ns = div_u64(ns, 1000000000UL) * 1000000000ULL; - ns -= qoriq_ptp->tclk_period; + ns -= ptp_qoriq->tclk_period; hi = ns >> 32; lo = ns & 0xffffffff; - qoriq_write(®s->alarm_regs->tmr_alarm1_l, lo); - qoriq_write(®s->alarm_regs->tmr_alarm1_h, hi); + ptp_qoriq->write(®s->alarm_regs->tmr_alarm1_l, lo); + ptp_qoriq->write(®s->alarm_regs->tmr_alarm1_h, hi); } -/* Caller must hold qoriq_ptp->lock. */ -static void set_fipers(struct qoriq_ptp *qoriq_ptp) +/* Caller must hold ptp_qoriq->lock. */ +static void set_fipers(struct ptp_qoriq *ptp_qoriq) { - struct qoriq_ptp_registers *regs = &qoriq_ptp->regs; + struct ptp_qoriq_registers *regs = &ptp_qoriq->regs; - set_alarm(qoriq_ptp); - qoriq_write(®s->fiper_regs->tmr_fiper1, qoriq_ptp->tmr_fiper1); - qoriq_write(®s->fiper_regs->tmr_fiper2, qoriq_ptp->tmr_fiper2); + set_alarm(ptp_qoriq); + ptp_qoriq->write(®s->fiper_regs->tmr_fiper1, ptp_qoriq->tmr_fiper1); + ptp_qoriq->write(®s->fiper_regs->tmr_fiper2, ptp_qoriq->tmr_fiper2); } -static int extts_clean_up(struct qoriq_ptp *qoriq_ptp, int index, +static int extts_clean_up(struct ptp_qoriq *ptp_qoriq, int index, bool update_event) { - struct qoriq_ptp_registers *regs = &qoriq_ptp->regs; + struct ptp_qoriq_registers *regs = &ptp_qoriq->regs; struct ptp_clock_event event; void __iomem *reg_etts_l; void __iomem *reg_etts_h; @@ -116,17 +115,17 @@ static int extts_clean_up(struct qoriq_ptp *qoriq_ptp, int index, event.index = index; do { - lo = qoriq_read(reg_etts_l); - hi = qoriq_read(reg_etts_h); + lo = ptp_qoriq->read(reg_etts_l); + hi = ptp_qoriq->read(reg_etts_h); if (update_event) { event.timestamp = ((u64) hi) << 32; event.timestamp |= lo; - ptp_clock_event(qoriq_ptp->clock, &event); + ptp_clock_event(ptp_qoriq->clock, &event); } - stat = qoriq_read(®s->ctrl_regs->tmr_stat); - } while (qoriq_ptp->extts_fifo_support && (stat & valid)); + stat = ptp_qoriq->read(®s->ctrl_regs->tmr_stat); + } while (ptp_qoriq->extts_fifo_support && (stat & valid)); return 0; } @@ -135,89 +134,90 @@ static int extts_clean_up(struct qoriq_ptp *qoriq_ptp, int index, * Interrupt service routine */ -static irqreturn_t isr(int irq, void *priv) +irqreturn_t ptp_qoriq_isr(int irq, void *priv) { - struct qoriq_ptp *qoriq_ptp = priv; - struct qoriq_ptp_registers *regs = &qoriq_ptp->regs; + struct ptp_qoriq *ptp_qoriq = priv; + struct ptp_qoriq_registers *regs = &ptp_qoriq->regs; struct ptp_clock_event event; u64 ns; u32 ack = 0, lo, hi, mask, val, irqs; - spin_lock(&qoriq_ptp->lock); + spin_lock(&ptp_qoriq->lock); - val = qoriq_read(®s->ctrl_regs->tmr_tevent); - mask = qoriq_read(®s->ctrl_regs->tmr_temask); + val = ptp_qoriq->read(®s->ctrl_regs->tmr_tevent); + mask = ptp_qoriq->read(®s->ctrl_regs->tmr_temask); - spin_unlock(&qoriq_ptp->lock); + spin_unlock(&ptp_qoriq->lock); irqs = val & mask; if (irqs & ETS1) { ack |= ETS1; - extts_clean_up(qoriq_ptp, 0, true); + extts_clean_up(ptp_qoriq, 0, true); } if (irqs & ETS2) { ack |= ETS2; - extts_clean_up(qoriq_ptp, 1, true); + extts_clean_up(ptp_qoriq, 1, true); } if (irqs & ALM2) { ack |= ALM2; - if (qoriq_ptp->alarm_value) { + if (ptp_qoriq->alarm_value) { event.type = PTP_CLOCK_ALARM; event.index = 0; - event.timestamp = qoriq_ptp->alarm_value; - ptp_clock_event(qoriq_ptp->clock, &event); + event.timestamp = ptp_qoriq->alarm_value; + ptp_clock_event(ptp_qoriq->clock, &event); } - if (qoriq_ptp->alarm_interval) { - ns = qoriq_ptp->alarm_value + qoriq_ptp->alarm_interval; + if (ptp_qoriq->alarm_interval) { + ns = ptp_qoriq->alarm_value + ptp_qoriq->alarm_interval; hi = ns >> 32; lo = ns & 0xffffffff; - qoriq_write(®s->alarm_regs->tmr_alarm2_l, lo); - qoriq_write(®s->alarm_regs->tmr_alarm2_h, hi); - qoriq_ptp->alarm_value = ns; + ptp_qoriq->write(®s->alarm_regs->tmr_alarm2_l, lo); + ptp_qoriq->write(®s->alarm_regs->tmr_alarm2_h, hi); + ptp_qoriq->alarm_value = ns; } else { - spin_lock(&qoriq_ptp->lock); - mask = qoriq_read(®s->ctrl_regs->tmr_temask); + spin_lock(&ptp_qoriq->lock); + mask = ptp_qoriq->read(®s->ctrl_regs->tmr_temask); mask &= ~ALM2EN; - qoriq_write(®s->ctrl_regs->tmr_temask, mask); - spin_unlock(&qoriq_ptp->lock); - qoriq_ptp->alarm_value = 0; - qoriq_ptp->alarm_interval = 0; + ptp_qoriq->write(®s->ctrl_regs->tmr_temask, mask); + spin_unlock(&ptp_qoriq->lock); + ptp_qoriq->alarm_value = 0; + ptp_qoriq->alarm_interval = 0; } } if (irqs & PP1) { ack |= PP1; event.type = PTP_CLOCK_PPS; - ptp_clock_event(qoriq_ptp->clock, &event); + ptp_clock_event(ptp_qoriq->clock, &event); } if (ack) { - qoriq_write(®s->ctrl_regs->tmr_tevent, ack); + ptp_qoriq->write(®s->ctrl_regs->tmr_tevent, ack); return IRQ_HANDLED; } else return IRQ_NONE; } +EXPORT_SYMBOL_GPL(ptp_qoriq_isr); /* * PTP clock operations */ -static int ptp_qoriq_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) +int ptp_qoriq_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) { u64 adj, diff; u32 tmr_add; int neg_adj = 0; - struct qoriq_ptp *qoriq_ptp = container_of(ptp, struct qoriq_ptp, caps); - struct qoriq_ptp_registers *regs = &qoriq_ptp->regs; + struct ptp_qoriq *ptp_qoriq = container_of(ptp, struct ptp_qoriq, caps); + struct ptp_qoriq_registers *regs = &ptp_qoriq->regs; if (scaled_ppm < 0) { neg_adj = 1; scaled_ppm = -scaled_ppm; } - tmr_add = qoriq_ptp->tmr_add; + tmr_add = ptp_qoriq->tmr_add; adj = tmr_add; /* calculate diff as adj*(scaled_ppm/65536)/1000000 @@ -229,71 +229,74 @@ static int ptp_qoriq_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) tmr_add = neg_adj ? tmr_add - diff : tmr_add + diff; - qoriq_write(®s->ctrl_regs->tmr_add, tmr_add); + ptp_qoriq->write(®s->ctrl_regs->tmr_add, tmr_add); return 0; } +EXPORT_SYMBOL_GPL(ptp_qoriq_adjfine); -static int ptp_qoriq_adjtime(struct ptp_clock_info *ptp, s64 delta) +int ptp_qoriq_adjtime(struct ptp_clock_info *ptp, s64 delta) { s64 now; unsigned long flags; - struct qoriq_ptp *qoriq_ptp = container_of(ptp, struct qoriq_ptp, caps); + struct ptp_qoriq *ptp_qoriq = container_of(ptp, struct ptp_qoriq, caps); - spin_lock_irqsave(&qoriq_ptp->lock, flags); + spin_lock_irqsave(&ptp_qoriq->lock, flags); - now = tmr_cnt_read(qoriq_ptp); + now = tmr_cnt_read(ptp_qoriq); now += delta; - tmr_cnt_write(qoriq_ptp, now); - set_fipers(qoriq_ptp); + tmr_cnt_write(ptp_qoriq, now); + set_fipers(ptp_qoriq); - spin_unlock_irqrestore(&qoriq_ptp->lock, flags); + spin_unlock_irqrestore(&ptp_qoriq->lock, flags); return 0; } +EXPORT_SYMBOL_GPL(ptp_qoriq_adjtime); -static int ptp_qoriq_gettime(struct ptp_clock_info *ptp, - struct timespec64 *ts) +int ptp_qoriq_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) { u64 ns; unsigned long flags; - struct qoriq_ptp *qoriq_ptp = container_of(ptp, struct qoriq_ptp, caps); + struct ptp_qoriq *ptp_qoriq = container_of(ptp, struct ptp_qoriq, caps); - spin_lock_irqsave(&qoriq_ptp->lock, flags); + spin_lock_irqsave(&ptp_qoriq->lock, flags); - ns = tmr_cnt_read(qoriq_ptp); + ns = tmr_cnt_read(ptp_qoriq); - spin_unlock_irqrestore(&qoriq_ptp->lock, flags); + spin_unlock_irqrestore(&ptp_qoriq->lock, flags); *ts = ns_to_timespec64(ns); return 0; } +EXPORT_SYMBOL_GPL(ptp_qoriq_gettime); -static int ptp_qoriq_settime(struct ptp_clock_info *ptp, - const struct timespec64 *ts) +int ptp_qoriq_settime(struct ptp_clock_info *ptp, + const struct timespec64 *ts) { u64 ns; unsigned long flags; - struct qoriq_ptp *qoriq_ptp = container_of(ptp, struct qoriq_ptp, caps); + struct ptp_qoriq *ptp_qoriq = container_of(ptp, struct ptp_qoriq, caps); ns = timespec64_to_ns(ts); - spin_lock_irqsave(&qoriq_ptp->lock, flags); + spin_lock_irqsave(&ptp_qoriq->lock, flags); - tmr_cnt_write(qoriq_ptp, ns); - set_fipers(qoriq_ptp); + tmr_cnt_write(ptp_qoriq, ns); + set_fipers(ptp_qoriq); - spin_unlock_irqrestore(&qoriq_ptp->lock, flags); + spin_unlock_irqrestore(&ptp_qoriq->lock, flags); return 0; } +EXPORT_SYMBOL_GPL(ptp_qoriq_settime); -static int ptp_qoriq_enable(struct ptp_clock_info *ptp, - struct ptp_clock_request *rq, int on) +int ptp_qoriq_enable(struct ptp_clock_info *ptp, + struct ptp_clock_request *rq, int on) { - struct qoriq_ptp *qoriq_ptp = container_of(ptp, struct qoriq_ptp, caps); - struct qoriq_ptp_registers *regs = &qoriq_ptp->regs; + struct ptp_qoriq *ptp_qoriq = container_of(ptp, struct ptp_qoriq, caps); + struct ptp_qoriq_registers *regs = &ptp_qoriq->regs; unsigned long flags; u32 bit, mask = 0; @@ -311,7 +314,7 @@ static int ptp_qoriq_enable(struct ptp_clock_info *ptp, } if (on) - extts_clean_up(qoriq_ptp, rq->extts.index, false); + extts_clean_up(ptp_qoriq, rq->extts.index, false); break; case PTP_CLK_REQ_PPS: @@ -321,21 +324,22 @@ static int ptp_qoriq_enable(struct ptp_clock_info *ptp, return -EOPNOTSUPP; } - spin_lock_irqsave(&qoriq_ptp->lock, flags); + spin_lock_irqsave(&ptp_qoriq->lock, flags); - mask = qoriq_read(®s->ctrl_regs->tmr_temask); + mask = ptp_qoriq->read(®s->ctrl_regs->tmr_temask); if (on) { mask |= bit; - qoriq_write(®s->ctrl_regs->tmr_tevent, bit); + ptp_qoriq->write(®s->ctrl_regs->tmr_tevent, bit); } else { mask &= ~bit; } - qoriq_write(®s->ctrl_regs->tmr_temask, mask); + ptp_qoriq->write(®s->ctrl_regs->tmr_temask, mask); - spin_unlock_irqrestore(&qoriq_ptp->lock, flags); + spin_unlock_irqrestore(&ptp_qoriq->lock, flags); return 0; } +EXPORT_SYMBOL_GPL(ptp_qoriq_enable); static const struct ptp_clock_info ptp_qoriq_caps = { .owner = THIS_MODULE, @@ -354,7 +358,7 @@ static const struct ptp_clock_info ptp_qoriq_caps = { }; /** - * qoriq_ptp_nominal_freq - calculate nominal frequency according to + * ptp_qoriq_nominal_freq - calculate nominal frequency according to * reference clock frequency * * @clk_src: reference clock frequency @@ -365,7 +369,7 @@ static const struct ptp_clock_info ptp_qoriq_caps = { * * Return the nominal frequency */ -static u32 qoriq_ptp_nominal_freq(u32 clk_src) +static u32 ptp_qoriq_nominal_freq(u32 clk_src) { u32 remainder = 0; @@ -385,9 +389,9 @@ static u32 qoriq_ptp_nominal_freq(u32 clk_src) } /** - * qoriq_ptp_auto_config - calculate a set of default configurations + * ptp_qoriq_auto_config - calculate a set of default configurations * - * @qoriq_ptp: pointer to qoriq_ptp + * @ptp_qoriq: pointer to ptp_qoriq * @node: pointer to device_node * * If below dts properties are not provided, this function will be @@ -401,7 +405,7 @@ static u32 qoriq_ptp_nominal_freq(u32 clk_src) * * Return 0 if success */ -static int qoriq_ptp_auto_config(struct qoriq_ptp *qoriq_ptp, +static int ptp_qoriq_auto_config(struct ptp_qoriq *ptp_qoriq, struct device_node *node) { struct clk *clk; @@ -411,7 +415,7 @@ static int qoriq_ptp_auto_config(struct qoriq_ptp *qoriq_ptp, u32 remainder = 0; u32 clk_src = 0; - qoriq_ptp->cksel = DEFAULT_CKSEL; + ptp_qoriq->cksel = DEFAULT_CKSEL; clk = of_clk_get(node, 0); if (!IS_ERR(clk)) { @@ -424,12 +428,12 @@ static int qoriq_ptp_auto_config(struct qoriq_ptp *qoriq_ptp, return -EINVAL; } - nominal_freq = qoriq_ptp_nominal_freq(clk_src); + nominal_freq = ptp_qoriq_nominal_freq(clk_src); if (!nominal_freq) return -EINVAL; - qoriq_ptp->tclk_period = 1000000000UL / nominal_freq; - qoriq_ptp->tmr_prsc = DEFAULT_TMR_PRSC; + ptp_qoriq->tclk_period = 1000000000UL / nominal_freq; + ptp_qoriq->tmr_prsc = DEFAULT_TMR_PRSC; /* Calculate initial frequency compensation value for TMR_ADD register. * freq_comp = ceil(2^32 / freq_ratio) @@ -440,172 +444,193 @@ static int qoriq_ptp_auto_config(struct qoriq_ptp *qoriq_ptp, if (remainder) freq_comp++; - qoriq_ptp->tmr_add = freq_comp; - qoriq_ptp->tmr_fiper1 = DEFAULT_FIPER1_PERIOD - qoriq_ptp->tclk_period; - qoriq_ptp->tmr_fiper2 = DEFAULT_FIPER2_PERIOD - qoriq_ptp->tclk_period; + ptp_qoriq->tmr_add = freq_comp; + ptp_qoriq->tmr_fiper1 = DEFAULT_FIPER1_PERIOD - ptp_qoriq->tclk_period; + ptp_qoriq->tmr_fiper2 = DEFAULT_FIPER2_PERIOD - ptp_qoriq->tclk_period; /* max_adj = 1000000000 * (freq_ratio - 1.0) - 1 * freq_ratio = reference_clock_freq / nominal_freq */ max_adj = 1000000000ULL * (clk_src - nominal_freq); max_adj = div_u64(max_adj, nominal_freq) - 1; - qoriq_ptp->caps.max_adj = max_adj; + ptp_qoriq->caps.max_adj = max_adj; return 0; } -static int qoriq_ptp_probe(struct platform_device *dev) +int ptp_qoriq_init(struct ptp_qoriq *ptp_qoriq, void __iomem *base, + const struct ptp_clock_info caps) { - struct device_node *node = dev->dev.of_node; - struct qoriq_ptp *qoriq_ptp; - struct qoriq_ptp_registers *regs; + struct device_node *node = ptp_qoriq->dev->of_node; + struct ptp_qoriq_registers *regs; struct timespec64 now; - int err = -ENOMEM; - u32 tmr_ctrl; unsigned long flags; - void __iomem *base; - - qoriq_ptp = kzalloc(sizeof(*qoriq_ptp), GFP_KERNEL); - if (!qoriq_ptp) - goto no_memory; - - err = -EINVAL; + u32 tmr_ctrl; - qoriq_ptp->dev = &dev->dev; - qoriq_ptp->caps = ptp_qoriq_caps; + ptp_qoriq->base = base; + ptp_qoriq->caps = caps; - if (of_property_read_u32(node, "fsl,cksel", &qoriq_ptp->cksel)) - qoriq_ptp->cksel = DEFAULT_CKSEL; + if (of_property_read_u32(node, "fsl,cksel", &ptp_qoriq->cksel)) + ptp_qoriq->cksel = DEFAULT_CKSEL; if (of_property_read_bool(node, "fsl,extts-fifo")) - qoriq_ptp->extts_fifo_support = true; + ptp_qoriq->extts_fifo_support = true; else - qoriq_ptp->extts_fifo_support = false; + ptp_qoriq->extts_fifo_support = false; if (of_property_read_u32(node, - "fsl,tclk-period", &qoriq_ptp->tclk_period) || + "fsl,tclk-period", &ptp_qoriq->tclk_period) || of_property_read_u32(node, - "fsl,tmr-prsc", &qoriq_ptp->tmr_prsc) || + "fsl,tmr-prsc", &ptp_qoriq->tmr_prsc) || of_property_read_u32(node, - "fsl,tmr-add", &qoriq_ptp->tmr_add) || + "fsl,tmr-add", &ptp_qoriq->tmr_add) || of_property_read_u32(node, - "fsl,tmr-fiper1", &qoriq_ptp->tmr_fiper1) || + "fsl,tmr-fiper1", &ptp_qoriq->tmr_fiper1) || of_property_read_u32(node, - "fsl,tmr-fiper2", &qoriq_ptp->tmr_fiper2) || + "fsl,tmr-fiper2", &ptp_qoriq->tmr_fiper2) || of_property_read_u32(node, - "fsl,max-adj", &qoriq_ptp->caps.max_adj)) { + "fsl,max-adj", &ptp_qoriq->caps.max_adj)) { pr_warn("device tree node missing required elements, try automatic configuration\n"); - if (qoriq_ptp_auto_config(qoriq_ptp, node)) - goto no_config; + if (ptp_qoriq_auto_config(ptp_qoriq, node)) + return -ENODEV; } - err = -ENODEV; + if (of_property_read_bool(node, "little-endian")) { + ptp_qoriq->read = qoriq_read_le; + ptp_qoriq->write = qoriq_write_le; + } else { + ptp_qoriq->read = qoriq_read_be; + ptp_qoriq->write = qoriq_write_be; + } + + /* The eTSEC uses differnt memory map with DPAA/ENETC */ + if (of_device_is_compatible(node, "fsl,etsec-ptp")) { + ptp_qoriq->regs.ctrl_regs = base + ETSEC_CTRL_REGS_OFFSET; + ptp_qoriq->regs.alarm_regs = base + ETSEC_ALARM_REGS_OFFSET; + ptp_qoriq->regs.fiper_regs = base + ETSEC_FIPER_REGS_OFFSET; + ptp_qoriq->regs.etts_regs = base + ETSEC_ETTS_REGS_OFFSET; + } else { + ptp_qoriq->regs.ctrl_regs = base + CTRL_REGS_OFFSET; + ptp_qoriq->regs.alarm_regs = base + ALARM_REGS_OFFSET; + ptp_qoriq->regs.fiper_regs = base + FIPER_REGS_OFFSET; + ptp_qoriq->regs.etts_regs = base + ETTS_REGS_OFFSET; + } + + ktime_get_real_ts64(&now); + ptp_qoriq_settime(&ptp_qoriq->caps, &now); + + tmr_ctrl = + (ptp_qoriq->tclk_period & TCLK_PERIOD_MASK) << TCLK_PERIOD_SHIFT | + (ptp_qoriq->cksel & CKSEL_MASK) << CKSEL_SHIFT; + + spin_lock_init(&ptp_qoriq->lock); + spin_lock_irqsave(&ptp_qoriq->lock, flags); + + regs = &ptp_qoriq->regs; + ptp_qoriq->write(®s->ctrl_regs->tmr_ctrl, tmr_ctrl); + ptp_qoriq->write(®s->ctrl_regs->tmr_add, ptp_qoriq->tmr_add); + ptp_qoriq->write(®s->ctrl_regs->tmr_prsc, ptp_qoriq->tmr_prsc); + ptp_qoriq->write(®s->fiper_regs->tmr_fiper1, ptp_qoriq->tmr_fiper1); + ptp_qoriq->write(®s->fiper_regs->tmr_fiper2, ptp_qoriq->tmr_fiper2); + set_alarm(ptp_qoriq); + ptp_qoriq->write(®s->ctrl_regs->tmr_ctrl, + tmr_ctrl|FIPERST|RTPE|TE|FRD); + + spin_unlock_irqrestore(&ptp_qoriq->lock, flags); + + ptp_qoriq->clock = ptp_clock_register(&ptp_qoriq->caps, ptp_qoriq->dev); + if (IS_ERR(ptp_qoriq->clock)) + return PTR_ERR(ptp_qoriq->clock); + + ptp_qoriq->phc_index = ptp_clock_index(ptp_qoriq->clock); + ptp_qoriq_create_debugfs(ptp_qoriq); + return 0; +} +EXPORT_SYMBOL_GPL(ptp_qoriq_init); + +void ptp_qoriq_free(struct ptp_qoriq *ptp_qoriq) +{ + struct ptp_qoriq_registers *regs = &ptp_qoriq->regs; + + ptp_qoriq->write(®s->ctrl_regs->tmr_temask, 0); + ptp_qoriq->write(®s->ctrl_regs->tmr_ctrl, 0); + + ptp_qoriq_remove_debugfs(ptp_qoriq); + ptp_clock_unregister(ptp_qoriq->clock); + iounmap(ptp_qoriq->base); + free_irq(ptp_qoriq->irq, ptp_qoriq); +} +EXPORT_SYMBOL_GPL(ptp_qoriq_free); - qoriq_ptp->irq = platform_get_irq(dev, 0); +static int ptp_qoriq_probe(struct platform_device *dev) +{ + struct ptp_qoriq *ptp_qoriq; + int err = -ENOMEM; + void __iomem *base; + + ptp_qoriq = kzalloc(sizeof(*ptp_qoriq), GFP_KERNEL); + if (!ptp_qoriq) + goto no_memory; + + ptp_qoriq->dev = &dev->dev; - if (qoriq_ptp->irq < 0) { + err = -ENODEV; + + ptp_qoriq->irq = platform_get_irq(dev, 0); + if (ptp_qoriq->irq < 0) { pr_err("irq not in device tree\n"); goto no_node; } - if (request_irq(qoriq_ptp->irq, isr, IRQF_SHARED, DRIVER, qoriq_ptp)) { + if (request_irq(ptp_qoriq->irq, ptp_qoriq_isr, IRQF_SHARED, + DRIVER, ptp_qoriq)) { pr_err("request_irq failed\n"); goto no_node; } - qoriq_ptp->rsrc = platform_get_resource(dev, IORESOURCE_MEM, 0); - if (!qoriq_ptp->rsrc) { + ptp_qoriq->rsrc = platform_get_resource(dev, IORESOURCE_MEM, 0); + if (!ptp_qoriq->rsrc) { pr_err("no resource\n"); goto no_resource; } - if (request_resource(&iomem_resource, qoriq_ptp->rsrc)) { + if (request_resource(&iomem_resource, ptp_qoriq->rsrc)) { pr_err("resource busy\n"); goto no_resource; } - spin_lock_init(&qoriq_ptp->lock); - - base = ioremap(qoriq_ptp->rsrc->start, - resource_size(qoriq_ptp->rsrc)); + base = ioremap(ptp_qoriq->rsrc->start, + resource_size(ptp_qoriq->rsrc)); if (!base) { pr_err("ioremap ptp registers failed\n"); goto no_ioremap; } - qoriq_ptp->base = base; - - if (of_device_is_compatible(node, "fsl,fman-ptp-timer")) { - qoriq_ptp->regs.ctrl_regs = base + FMAN_CTRL_REGS_OFFSET; - qoriq_ptp->regs.alarm_regs = base + FMAN_ALARM_REGS_OFFSET; - qoriq_ptp->regs.fiper_regs = base + FMAN_FIPER_REGS_OFFSET; - qoriq_ptp->regs.etts_regs = base + FMAN_ETTS_REGS_OFFSET; - } else { - qoriq_ptp->regs.ctrl_regs = base + CTRL_REGS_OFFSET; - qoriq_ptp->regs.alarm_regs = base + ALARM_REGS_OFFSET; - qoriq_ptp->regs.fiper_regs = base + FIPER_REGS_OFFSET; - qoriq_ptp->regs.etts_regs = base + ETTS_REGS_OFFSET; - } - - ktime_get_real_ts64(&now); - ptp_qoriq_settime(&qoriq_ptp->caps, &now); - - tmr_ctrl = - (qoriq_ptp->tclk_period & TCLK_PERIOD_MASK) << TCLK_PERIOD_SHIFT | - (qoriq_ptp->cksel & CKSEL_MASK) << CKSEL_SHIFT; - - spin_lock_irqsave(&qoriq_ptp->lock, flags); - - regs = &qoriq_ptp->regs; - qoriq_write(®s->ctrl_regs->tmr_ctrl, tmr_ctrl); - qoriq_write(®s->ctrl_regs->tmr_add, qoriq_ptp->tmr_add); - qoriq_write(®s->ctrl_regs->tmr_prsc, qoriq_ptp->tmr_prsc); - qoriq_write(®s->fiper_regs->tmr_fiper1, qoriq_ptp->tmr_fiper1); - qoriq_write(®s->fiper_regs->tmr_fiper2, qoriq_ptp->tmr_fiper2); - set_alarm(qoriq_ptp); - qoriq_write(®s->ctrl_regs->tmr_ctrl, tmr_ctrl|FIPERST|RTPE|TE|FRD); - - spin_unlock_irqrestore(&qoriq_ptp->lock, flags); - - qoriq_ptp->clock = ptp_clock_register(&qoriq_ptp->caps, &dev->dev); - if (IS_ERR(qoriq_ptp->clock)) { - err = PTR_ERR(qoriq_ptp->clock); + err = ptp_qoriq_init(ptp_qoriq, base, ptp_qoriq_caps); + if (err) goto no_clock; - } - qoriq_ptp->phc_index = ptp_clock_index(qoriq_ptp->clock); - - ptp_qoriq_create_debugfs(qoriq_ptp); - platform_set_drvdata(dev, qoriq_ptp); + platform_set_drvdata(dev, ptp_qoriq); return 0; no_clock: - iounmap(qoriq_ptp->base); + iounmap(ptp_qoriq->base); no_ioremap: - release_resource(qoriq_ptp->rsrc); + release_resource(ptp_qoriq->rsrc); no_resource: - free_irq(qoriq_ptp->irq, qoriq_ptp); -no_config: + free_irq(ptp_qoriq->irq, ptp_qoriq); no_node: - kfree(qoriq_ptp); + kfree(ptp_qoriq); no_memory: return err; } -static int qoriq_ptp_remove(struct platform_device *dev) +static int ptp_qoriq_remove(struct platform_device *dev) { - struct qoriq_ptp *qoriq_ptp = platform_get_drvdata(dev); - struct qoriq_ptp_registers *regs = &qoriq_ptp->regs; - - qoriq_write(®s->ctrl_regs->tmr_temask, 0); - qoriq_write(®s->ctrl_regs->tmr_ctrl, 0); - - ptp_qoriq_remove_debugfs(qoriq_ptp); - ptp_clock_unregister(qoriq_ptp->clock); - iounmap(qoriq_ptp->base); - release_resource(qoriq_ptp->rsrc); - free_irq(qoriq_ptp->irq, qoriq_ptp); - kfree(qoriq_ptp); + struct ptp_qoriq *ptp_qoriq = platform_get_drvdata(dev); + ptp_qoriq_free(ptp_qoriq); + release_resource(ptp_qoriq->rsrc); + kfree(ptp_qoriq); return 0; } @@ -616,16 +641,16 @@ static const struct of_device_id match_table[] = { }; MODULE_DEVICE_TABLE(of, match_table); -static struct platform_driver qoriq_ptp_driver = { +static struct platform_driver ptp_qoriq_driver = { .driver = { .name = "ptp_qoriq", .of_match_table = match_table, }, - .probe = qoriq_ptp_probe, - .remove = qoriq_ptp_remove, + .probe = ptp_qoriq_probe, + .remove = ptp_qoriq_remove, }; -module_platform_driver(qoriq_ptp_driver); +module_platform_driver(ptp_qoriq_driver); MODULE_AUTHOR("Richard Cochran <richardcochran@gmail.com>"); MODULE_DESCRIPTION("PTP clock for Freescale QorIQ 1588 timer"); diff --git a/drivers/ptp/ptp_qoriq_debugfs.c b/drivers/ptp/ptp_qoriq_debugfs.c index 970595021088..e8dddcedf288 100644 --- a/drivers/ptp/ptp_qoriq_debugfs.c +++ b/drivers/ptp/ptp_qoriq_debugfs.c @@ -7,11 +7,11 @@ static int ptp_qoriq_fiper1_lpbk_get(void *data, u64 *val) { - struct qoriq_ptp *qoriq_ptp = data; - struct qoriq_ptp_registers *regs = &qoriq_ptp->regs; + struct ptp_qoriq *ptp_qoriq = data; + struct ptp_qoriq_registers *regs = &ptp_qoriq->regs; u32 ctrl; - ctrl = qoriq_read(®s->ctrl_regs->tmr_ctrl); + ctrl = ptp_qoriq->read(®s->ctrl_regs->tmr_ctrl); *val = ctrl & PP1L ? 1 : 0; return 0; @@ -19,17 +19,17 @@ static int ptp_qoriq_fiper1_lpbk_get(void *data, u64 *val) static int ptp_qoriq_fiper1_lpbk_set(void *data, u64 val) { - struct qoriq_ptp *qoriq_ptp = data; - struct qoriq_ptp_registers *regs = &qoriq_ptp->regs; + struct ptp_qoriq *ptp_qoriq = data; + struct ptp_qoriq_registers *regs = &ptp_qoriq->regs; u32 ctrl; - ctrl = qoriq_read(®s->ctrl_regs->tmr_ctrl); + ctrl = ptp_qoriq->read(®s->ctrl_regs->tmr_ctrl); if (val == 0) ctrl &= ~PP1L; else ctrl |= PP1L; - qoriq_write(®s->ctrl_regs->tmr_ctrl, ctrl); + ptp_qoriq->write(®s->ctrl_regs->tmr_ctrl, ctrl); return 0; } @@ -38,11 +38,11 @@ DEFINE_DEBUGFS_ATTRIBUTE(ptp_qoriq_fiper1_fops, ptp_qoriq_fiper1_lpbk_get, static int ptp_qoriq_fiper2_lpbk_get(void *data, u64 *val) { - struct qoriq_ptp *qoriq_ptp = data; - struct qoriq_ptp_registers *regs = &qoriq_ptp->regs; + struct ptp_qoriq *ptp_qoriq = data; + struct ptp_qoriq_registers *regs = &ptp_qoriq->regs; u32 ctrl; - ctrl = qoriq_read(®s->ctrl_regs->tmr_ctrl); + ctrl = ptp_qoriq->read(®s->ctrl_regs->tmr_ctrl); *val = ctrl & PP2L ? 1 : 0; return 0; @@ -50,52 +50,52 @@ static int ptp_qoriq_fiper2_lpbk_get(void *data, u64 *val) static int ptp_qoriq_fiper2_lpbk_set(void *data, u64 val) { - struct qoriq_ptp *qoriq_ptp = data; - struct qoriq_ptp_registers *regs = &qoriq_ptp->regs; + struct ptp_qoriq *ptp_qoriq = data; + struct ptp_qoriq_registers *regs = &ptp_qoriq->regs; u32 ctrl; - ctrl = qoriq_read(®s->ctrl_regs->tmr_ctrl); + ctrl = ptp_qoriq->read(®s->ctrl_regs->tmr_ctrl); if (val == 0) ctrl &= ~PP2L; else ctrl |= PP2L; - qoriq_write(®s->ctrl_regs->tmr_ctrl, ctrl); + ptp_qoriq->write(®s->ctrl_regs->tmr_ctrl, ctrl); return 0; } DEFINE_DEBUGFS_ATTRIBUTE(ptp_qoriq_fiper2_fops, ptp_qoriq_fiper2_lpbk_get, ptp_qoriq_fiper2_lpbk_set, "%llu\n"); -void ptp_qoriq_create_debugfs(struct qoriq_ptp *qoriq_ptp) +void ptp_qoriq_create_debugfs(struct ptp_qoriq *ptp_qoriq) { struct dentry *root; - root = debugfs_create_dir(dev_name(qoriq_ptp->dev), NULL); + root = debugfs_create_dir(dev_name(ptp_qoriq->dev), NULL); if (IS_ERR(root)) return; if (!root) goto err_root; - qoriq_ptp->debugfs_root = root; + ptp_qoriq->debugfs_root = root; if (!debugfs_create_file_unsafe("fiper1-loopback", 0600, root, - qoriq_ptp, &ptp_qoriq_fiper1_fops)) + ptp_qoriq, &ptp_qoriq_fiper1_fops)) goto err_node; if (!debugfs_create_file_unsafe("fiper2-loopback", 0600, root, - qoriq_ptp, &ptp_qoriq_fiper2_fops)) + ptp_qoriq, &ptp_qoriq_fiper2_fops)) goto err_node; return; err_node: debugfs_remove_recursive(root); - qoriq_ptp->debugfs_root = NULL; + ptp_qoriq->debugfs_root = NULL; err_root: - dev_err(qoriq_ptp->dev, "failed to initialize debugfs\n"); + dev_err(ptp_qoriq->dev, "failed to initialize debugfs\n"); } -void ptp_qoriq_remove_debugfs(struct qoriq_ptp *qoriq_ptp) +void ptp_qoriq_remove_debugfs(struct ptp_qoriq *ptp_qoriq) { - debugfs_remove_recursive(qoriq_ptp->debugfs_root); - qoriq_ptp->debugfs_root = NULL; + debugfs_remove_recursive(ptp_qoriq->debugfs_root); + ptp_qoriq->debugfs_root = NULL; } diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index 4e7b55a14b1a..6e294b4d3635 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -4469,6 +4469,14 @@ static int dasd_symm_io(struct dasd_device *device, void __user *argp) usrparm.psf_data &= 0x7fffffffULL; usrparm.rssd_result &= 0x7fffffffULL; } + /* at least 2 bytes are accessed and should be allocated */ + if (usrparm.psf_data_len < 2) { + DBF_DEV_EVENT(DBF_WARNING, device, + "Symmetrix ioctl invalid data length %d", + usrparm.psf_data_len); + rc = -EINVAL; + goto out; + } /* alloc I/O data area */ psf_data = kzalloc(usrparm.psf_data_len, GFP_KERNEL | GFP_DMA); rssd_result = kzalloc(usrparm.rssd_result_len, GFP_KERNEL | GFP_DMA); diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index 48ea0004a56d..5a699746c357 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -248,7 +248,8 @@ static inline int ap_test_config(unsigned int *field, unsigned int nr) static inline int ap_test_config_card_id(unsigned int id) { if (!ap_configuration) /* QCI not supported */ - return 1; + /* only ids 0...3F may be probed */ + return id < 0x40 ? 1 : 0; return ap_test_config(ap_configuration->apm, id); } diff --git a/drivers/s390/net/Makefile b/drivers/s390/net/Makefile index f2d6bbe57a6f..bc55ec316adb 100644 --- a/drivers/s390/net/Makefile +++ b/drivers/s390/net/Makefile @@ -9,7 +9,7 @@ obj-$(CONFIG_NETIUCV) += netiucv.o fsm.o obj-$(CONFIG_SMSGIUCV) += smsgiucv.o obj-$(CONFIG_SMSGIUCV_EVENT) += smsgiucv_app.o obj-$(CONFIG_LCS) += lcs.o -qeth-y += qeth_core_sys.o qeth_core_main.o qeth_core_mpc.o +qeth-y += qeth_core_sys.o qeth_core_main.o qeth_core_mpc.o qeth_ethtool.o obj-$(CONFIG_QETH) += qeth.o qeth_l2-y += qeth_l2_main.o qeth_l2_sys.o obj-$(CONFIG_QETH_L2) += qeth_l2.o diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index d65650ef6b41..c0c46be0b251 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -18,10 +18,10 @@ #include <linux/in6.h> #include <linux/bitops.h> #include <linux/seq_file.h> -#include <linux/ethtool.h> #include <linux/hashtable.h> #include <linux/ip.h> #include <linux/refcount.h> +#include <linux/workqueue.h> #include <net/ipv6.h> #include <net/if_inet6.h> @@ -34,6 +34,8 @@ #include <asm/ccwgroup.h> #include <asm/sysinfo.h> +#include <uapi/linux/if_link.h> + #include "qeth_core_mpc.h" /** @@ -112,59 +114,6 @@ static inline u32 qeth_get_device_id(struct ccw_device *cdev) #define CCW_DEVID(cdev) (qeth_get_device_id(cdev)) #define CARD_DEVID(card) (CCW_DEVID(CARD_RDEV(card))) -/** - * card stuff - */ -struct qeth_perf_stats { - unsigned int bufs_rec; - unsigned int bufs_sent; - unsigned int buf_elements_sent; - - unsigned int skbs_sent_pack; - unsigned int bufs_sent_pack; - - unsigned int sc_dp_p; - unsigned int sc_p_dp; - /* qdio_cq_handler: number of times called, time spent in */ - __u64 cq_start_time; - unsigned int cq_cnt; - unsigned int cq_time; - /* qdio_input_handler: number of times called, time spent in */ - __u64 inbound_start_time; - unsigned int inbound_cnt; - unsigned int inbound_time; - /* qeth_send_packet: number of times called, time spent in */ - __u64 outbound_start_time; - unsigned int outbound_cnt; - unsigned int outbound_time; - /* qdio_output_handler: number of times called, time spent in */ - __u64 outbound_handler_start_time; - unsigned int outbound_handler_cnt; - unsigned int outbound_handler_time; - /* number of calls to and time spent in do_QDIO for inbound queue */ - __u64 inbound_do_qdio_start_time; - unsigned int inbound_do_qdio_cnt; - unsigned int inbound_do_qdio_time; - /* number of calls to and time spent in do_QDIO for outbound queues */ - __u64 outbound_do_qdio_start_time; - unsigned int outbound_do_qdio_cnt; - unsigned int outbound_do_qdio_time; - unsigned int large_send_bytes; - unsigned int large_send_cnt; - unsigned int sg_skbs_sent; - /* initial values when measuring starts */ - unsigned long initial_rx_packets; - unsigned long initial_tx_packets; - /* inbound scatter gather data */ - unsigned int sg_skbs_rx; - unsigned int sg_frags_rx; - unsigned int sg_alloc_page_rx; - unsigned int tx_csum; - unsigned int tx_lin; - unsigned int tx_linfail; - unsigned int rx_csum; -}; - /* Routing stuff */ struct qeth_routing_info { enum qeth_routing_types type; @@ -494,10 +443,54 @@ enum qeth_out_q_states { QETH_OUT_Q_LOCKED_FLUSH, }; +#define QETH_CARD_STAT_ADD(_c, _stat, _val) ((_c)->stats._stat += (_val)) +#define QETH_CARD_STAT_INC(_c, _stat) QETH_CARD_STAT_ADD(_c, _stat, 1) + +#define QETH_TXQ_STAT_ADD(_q, _stat, _val) ((_q)->stats._stat += (_val)) +#define QETH_TXQ_STAT_INC(_q, _stat) QETH_TXQ_STAT_ADD(_q, _stat, 1) + +struct qeth_card_stats { + u64 rx_bufs; + u64 rx_skb_csum; + u64 rx_sg_skbs; + u64 rx_sg_frags; + u64 rx_sg_alloc_page; + + /* rtnl_link_stats64 */ + u64 rx_packets; + u64 rx_bytes; + u64 rx_errors; + u64 rx_dropped; + u64 rx_multicast; + u64 tx_errors; +}; + +struct qeth_out_q_stats { + u64 bufs; + u64 bufs_pack; + u64 buf_elements; + u64 skbs_pack; + u64 skbs_sg; + u64 skbs_csum; + u64 skbs_tso; + u64 skbs_linearized; + u64 skbs_linearized_fail; + u64 tso_bytes; + u64 packing_mode_switch; + + /* rtnl_link_stats64 */ + u64 tx_packets; + u64 tx_bytes; + u64 tx_errors; + u64 tx_dropped; + u64 tx_carrier_errors; +}; + struct qeth_qdio_out_q { struct qdio_buffer *qdio_bufs[QDIO_MAX_BUFFERS_PER_Q]; struct qeth_qdio_out_buffer *bufs[QDIO_MAX_BUFFERS_PER_Q]; struct qdio_outbuf_state *bufstates; /* convenience pointer */ + struct qeth_out_q_stats stats; int queue_no; struct qeth_card *card; atomic_t state; @@ -527,7 +520,7 @@ struct qeth_qdio_info { /* output */ int no_out_queues; - struct qeth_qdio_out_q **out_qs; + struct qeth_qdio_out_q *out_qs[QETH_MAX_QUEUES]; struct qdio_outbuf_state *out_bufstates; /* priority queueing */ @@ -594,8 +587,8 @@ struct qeth_channel; struct qeth_cmd_buffer { enum qeth_cmd_buffer_state state; struct qeth_channel *channel; + struct qeth_reply *reply; unsigned char *data; - int rc; void (*callback)(struct qeth_card *card, struct qeth_channel *channel, struct qeth_cmd_buffer *iob); }; @@ -701,7 +694,6 @@ struct qeth_card_options { struct qeth_vnicc_info vnicc; /* VNICC options */ int fake_broadcast; enum qeth_discipline_id layer; - int performance_stats; int rx_sg_cb; enum qeth_ipa_isolation_modes isolation; enum qeth_ipa_isolation_modes prev_isolation; @@ -777,13 +769,13 @@ struct qeth_card { struct qeth_channel data; struct net_device *dev; - struct net_device_stats stats; - + struct qeth_card_stats stats; struct qeth_card_info info; struct qeth_token token; struct qeth_seqno seqno; struct qeth_card_options options; + struct workqueue_struct *event_wq; wait_queue_head_t wait_q; spinlock_t mclock; unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; @@ -800,7 +792,6 @@ struct qeth_card { struct list_head cmd_waiter_list; /* QDIO buffer handling */ struct qeth_qdio_info qdio; - struct qeth_perf_stats perf_stats; int read_or_write_problem; struct qeth_osn_info osn_info; struct qeth_discipline *discipline; @@ -857,11 +848,6 @@ static inline int qeth_get_elements_for_range(addr_t start, addr_t end) return PFN_UP(end) - PFN_DOWN(start); } -static inline int qeth_get_micros(void) -{ - return (int) (get_tod_clock() >> 12); -} - static inline int qeth_get_ip_version(struct sk_buff *skb) { struct vlan_ethhdr *veth = vlan_eth_hdr(skb); @@ -886,8 +872,7 @@ static inline void qeth_rx_csum(struct qeth_card *card, struct sk_buff *skb, if ((card->dev->features & NETIF_F_RXCSUM) && (flags & QETH_HDR_EXT_CSUM_TRANSP_REQ)) { skb->ip_summed = CHECKSUM_UNNECESSARY; - if (card->options.performance_stats) - card->perf_stats.rx_csum++; + QETH_CARD_STAT_INC(card, rx_skb_csum); } else { skb->ip_summed = CHECKSUM_NONE; } @@ -949,12 +934,13 @@ static inline struct qeth_qdio_out_q *qeth_get_tx_queue(struct qeth_card *card, extern struct qeth_discipline qeth_l2_discipline; extern struct qeth_discipline qeth_l3_discipline; +extern const struct ethtool_ops qeth_ethtool_ops; +extern const struct ethtool_ops qeth_osn_ethtool_ops; extern const struct attribute_group *qeth_generic_attr_groups[]; extern const struct attribute_group *qeth_osn_attr_groups[]; extern const struct attribute_group qeth_device_attr_group; extern const struct attribute_group qeth_device_blkt_group; extern const struct device_type qeth_generic_devtype; -extern struct workqueue_struct *qeth_wq; int qeth_card_hw_is_reachable(struct qeth_card *); const char *qeth_get_cardname_short(struct qeth_card *); @@ -993,33 +979,25 @@ void qeth_clear_working_pool_list(struct qeth_card *); void qeth_clear_cmd_buffers(struct qeth_channel *); void qeth_clear_qdio_buffers(struct qeth_card *); void qeth_setadp_promisc_mode(struct qeth_card *); -struct net_device_stats *qeth_get_stats(struct net_device *); int qeth_setadpparms_change_macaddr(struct qeth_card *); void qeth_tx_timeout(struct net_device *); void qeth_prepare_control_data(struct qeth_card *, int, struct qeth_cmd_buffer *); void qeth_release_buffer(struct qeth_channel *, struct qeth_cmd_buffer *); -void qeth_prepare_ipa_cmd(struct qeth_card *card, struct qeth_cmd_buffer *iob); +void qeth_prepare_ipa_cmd(struct qeth_card *card, struct qeth_cmd_buffer *iob, + u16 cmd_length); struct qeth_cmd_buffer *qeth_wait_for_buffer(struct qeth_channel *); int qeth_query_switch_attributes(struct qeth_card *card, struct qeth_switch_info *sw_info); -int qeth_send_control_data(struct qeth_card *, int, struct qeth_cmd_buffer *, - int (*reply_cb)(struct qeth_card *, struct qeth_reply*, unsigned long), - void *reply_param); +int qeth_query_card_info(struct qeth_card *card, + struct carrier_info *carrier_info); unsigned int qeth_count_elements(struct sk_buff *skb, unsigned int data_offset); int qeth_do_send_packet(struct qeth_card *card, struct qeth_qdio_out_q *queue, struct sk_buff *skb, struct qeth_hdr *hdr, unsigned int offset, unsigned int hd_len, int elements_needed); int qeth_do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd); -int qeth_core_get_sset_count(struct net_device *, int); -void qeth_core_get_ethtool_stats(struct net_device *, - struct ethtool_stats *, u64 *); -void qeth_core_get_strings(struct net_device *, u32, u8 *); -void qeth_core_get_drvinfo(struct net_device *, struct ethtool_drvinfo *); void qeth_dbf_longtext(debug_info_t *id, int level, char *text, ...); -int qeth_core_ethtool_get_link_ksettings(struct net_device *netdev, - struct ethtool_link_ksettings *cmd); int qeth_set_access_ctrl_online(struct qeth_card *card, int fallback); int qeth_configure_cq(struct qeth_card *, enum qeth_cq); int qeth_hw_trap(struct qeth_card *, enum qeth_diags_trap_action); @@ -1036,14 +1014,16 @@ netdev_features_t qeth_fix_features(struct net_device *, netdev_features_t); netdev_features_t qeth_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features); +void qeth_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats); int qeth_open(struct net_device *dev); int qeth_stop(struct net_device *dev); int qeth_vm_request_mac(struct qeth_card *card); int qeth_xmit(struct qeth_card *card, struct sk_buff *skb, struct qeth_qdio_out_q *queue, int ipv, int cast_type, - void (*fill_header)(struct qeth_card *card, struct qeth_hdr *hdr, - struct sk_buff *skb, int ipv, int cast_type, + void (*fill_header)(struct qeth_qdio_out_q *queue, + struct qeth_hdr *hdr, struct sk_buff *skb, + int ipv, int cast_type, unsigned int data_len)); /* exports for OSN */ diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index dcc06e48b70b..4708df39f129 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -74,8 +74,7 @@ static void qeth_notify_skbs(struct qeth_qdio_out_q *queue, static void qeth_release_skbs(struct qeth_qdio_out_buffer *buf); static int qeth_init_qdio_out_buf(struct qeth_qdio_out_q *, int); -struct workqueue_struct *qeth_wq; -EXPORT_SYMBOL_GPL(qeth_wq); +static struct workqueue_struct *qeth_wq; int qeth_card_hw_is_reachable(struct qeth_card *card) { @@ -540,6 +539,7 @@ static int __qeth_issue_next_read(struct qeth_card *card) QETH_DBF_MESSAGE(2, "error %i on device %x when starting next read ccw!\n", rc, CARD_DEVID(card)); atomic_set(&channel->irq_pending, 0); + qeth_release_buffer(channel, iob); card->read_or_write_problem = 1; qeth_schedule_recovery(card); wake_up(&card->wait_q); @@ -566,6 +566,7 @@ static struct qeth_reply *qeth_alloc_reply(struct qeth_card *card) if (reply) { refcount_set(&reply->refcnt, 1); atomic_set(&reply->received, 0); + init_waitqueue_head(&reply->wait_q); } return reply; } @@ -581,6 +582,26 @@ static void qeth_put_reply(struct qeth_reply *reply) kfree(reply); } +static void qeth_enqueue_reply(struct qeth_card *card, struct qeth_reply *reply) +{ + spin_lock_irq(&card->lock); + list_add_tail(&reply->list, &card->cmd_waiter_list); + spin_unlock_irq(&card->lock); +} + +static void qeth_dequeue_reply(struct qeth_card *card, struct qeth_reply *reply) +{ + spin_lock_irq(&card->lock); + list_del(&reply->list); + spin_unlock_irq(&card->lock); +} + +static void qeth_notify_reply(struct qeth_reply *reply) +{ + atomic_inc(&reply->received); + wake_up(&reply->wait_q); +} + static void qeth_issue_ipa_msg(struct qeth_ipa_cmd *cmd, int rc, struct qeth_card *card) { @@ -657,19 +678,15 @@ static struct qeth_ipa_cmd *qeth_check_ipa_data(struct qeth_card *card, void qeth_clear_ipacmd_list(struct qeth_card *card) { - struct qeth_reply *reply, *r; + struct qeth_reply *reply; unsigned long flags; QETH_CARD_TEXT(card, 4, "clipalst"); spin_lock_irqsave(&card->lock, flags); - list_for_each_entry_safe(reply, r, &card->cmd_waiter_list, list) { - qeth_get_reply(reply); + list_for_each_entry(reply, &card->cmd_waiter_list, list) { reply->rc = -EIO; - atomic_inc(&reply->received); - list_del_init(&reply->list); - wake_up(&reply->wait_q); - qeth_put_reply(reply); + qeth_notify_reply(reply); } spin_unlock_irqrestore(&card->lock, flags); } @@ -726,7 +743,10 @@ void qeth_release_buffer(struct qeth_channel *channel, spin_lock_irqsave(&channel->iob_lock, flags); iob->state = BUF_STATE_FREE; iob->callback = qeth_send_control_data_cb; - iob->rc = 0; + if (iob->reply) { + qeth_put_reply(iob->reply); + iob->reply = NULL; + } spin_unlock_irqrestore(&channel->iob_lock, flags); wake_up(&channel->wait_q); } @@ -739,6 +759,17 @@ static void qeth_release_buffer_cb(struct qeth_card *card, qeth_release_buffer(channel, iob); } +static void qeth_cancel_cmd(struct qeth_cmd_buffer *iob, int rc) +{ + struct qeth_reply *reply = iob->reply; + + if (reply) { + reply->rc = rc; + qeth_notify_reply(reply); + } + qeth_release_buffer(iob->channel, iob); +} + static struct qeth_cmd_buffer *qeth_get_buffer(struct qeth_channel *channel) { struct qeth_cmd_buffer *buffer = NULL; @@ -774,9 +805,9 @@ static void qeth_send_control_data_cb(struct qeth_card *card, struct qeth_cmd_buffer *iob) { struct qeth_ipa_cmd *cmd = NULL; - struct qeth_reply *reply, *r; + struct qeth_reply *reply = NULL; + struct qeth_reply *r; unsigned long flags; - int keep_reply; int rc = 0; QETH_CARD_TEXT(card, 4, "sndctlcb"); @@ -808,44 +839,40 @@ static void qeth_send_control_data_cb(struct qeth_card *card, goto out; } + /* match against pending cmd requests */ spin_lock_irqsave(&card->lock, flags); - list_for_each_entry_safe(reply, r, &card->cmd_waiter_list, list) { - if ((reply->seqno == QETH_IDX_COMMAND_SEQNO) || - ((cmd) && (reply->seqno == cmd->hdr.seqno))) { + list_for_each_entry(r, &card->cmd_waiter_list, list) { + if ((r->seqno == QETH_IDX_COMMAND_SEQNO) || + (cmd && (r->seqno == cmd->hdr.seqno))) { + reply = r; + /* take the object outside the lock */ qeth_get_reply(reply); - list_del_init(&reply->list); - spin_unlock_irqrestore(&card->lock, flags); - keep_reply = 0; - if (reply->callback != NULL) { - if (cmd) { - reply->offset = (__u16)((char *)cmd - - (char *)iob->data); - keep_reply = reply->callback(card, - reply, - (unsigned long)cmd); - } else - keep_reply = reply->callback(card, - reply, - (unsigned long)iob); - } - if (cmd) - reply->rc = (u16) cmd->hdr.return_code; - else if (iob->rc) - reply->rc = iob->rc; - if (keep_reply) { - spin_lock_irqsave(&card->lock, flags); - list_add_tail(&reply->list, - &card->cmd_waiter_list); - spin_unlock_irqrestore(&card->lock, flags); - } else { - atomic_inc(&reply->received); - wake_up(&reply->wait_q); - } - qeth_put_reply(reply); - goto out; + break; } } spin_unlock_irqrestore(&card->lock, flags); + + if (!reply) + goto out; + + if (!reply->callback) { + rc = 0; + } else { + if (cmd) { + reply->offset = (u16)((char *)cmd - (char *)iob->data); + rc = reply->callback(card, reply, (unsigned long)cmd); + } else { + rc = reply->callback(card, reply, (unsigned long)iob); + } + } + + if (rc <= 0) { + reply->rc = rc; + qeth_notify_reply(reply); + } + + qeth_put_reply(reply); + out: memcpy(&card->seqno.pdu_hdr_ack, QETH_PDU_HEADER_SEQ_NO(iob->data), @@ -976,9 +1003,8 @@ static int qeth_get_problem(struct qeth_card *card, struct ccw_device *cdev, return 0; } -static long qeth_check_irb_error(struct qeth_card *card, - struct ccw_device *cdev, unsigned long intparm, - struct irb *irb) +static int qeth_check_irb_error(struct qeth_card *card, struct ccw_device *cdev, + unsigned long intparm, struct irb *irb) { if (!IS_ERR(irb)) return 0; @@ -989,7 +1015,7 @@ static long qeth_check_irb_error(struct qeth_card *card, CCW_DEVID(cdev)); QETH_CARD_TEXT(card, 2, "ckirberr"); QETH_CARD_TEXT_(card, 2, " rc%d", -EIO); - break; + return -EIO; case -ETIMEDOUT: dev_warn(&cdev->dev, "A hardware operation timed out" " on the device\n"); @@ -1001,14 +1027,14 @@ static long qeth_check_irb_error(struct qeth_card *card, wake_up(&card->wait_q); } } - break; + return -ETIMEDOUT; default: QETH_DBF_MESSAGE(2, "unknown error %ld on channel %x\n", PTR_ERR(irb), CCW_DEVID(cdev)); QETH_CARD_TEXT(card, 2, "ckirberr"); QETH_CARD_TEXT(card, 2, " rc???"); + return PTR_ERR(irb); } - return PTR_ERR(irb); } static void qeth_irq(struct ccw_device *cdev, unsigned long intparm, @@ -1043,10 +1069,11 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm, if (qeth_intparm_is_iob(intparm)) iob = (struct qeth_cmd_buffer *) __va((addr_t)intparm); - if (qeth_check_irb_error(card, cdev, intparm, irb)) { + rc = qeth_check_irb_error(card, cdev, intparm, irb); + if (rc) { /* IO was terminated, free its resources. */ if (iob) - qeth_release_buffer(iob->channel, iob); + qeth_cancel_cmd(iob, rc); atomic_set(&channel->irq_pending, 0); wake_up(&card->wait_q); return; @@ -1101,6 +1128,8 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm, rc = qeth_get_problem(card, cdev, irb); if (rc) { card->read_or_write_problem = 1; + if (iob) + qeth_cancel_cmd(iob, rc); qeth_clear_ipacmd_list(card); qeth_schedule_recovery(card); goto out; @@ -1262,7 +1291,6 @@ static int qeth_setup_channel(struct qeth_channel *channel, bool alloc_buffers) channel->iob[cnt].state = BUF_STATE_FREE; channel->iob[cnt].channel = channel; channel->iob[cnt].callback = qeth_send_control_data_cb; - channel->iob[cnt].rc = 0; } if (cnt < QETH_CMD_BUFFER_NO) { qeth_clean_channel(channel); @@ -1439,6 +1467,10 @@ static struct qeth_card *qeth_alloc_card(struct ccwgroup_device *gdev) CARD_RDEV(card) = gdev->cdev[0]; CARD_WDEV(card) = gdev->cdev[1]; CARD_DDEV(card) = gdev->cdev[2]; + + card->event_wq = alloc_ordered_workqueue("%s", 0, dev_name(&gdev->dev)); + if (!card->event_wq) + goto out_wq; if (qeth_setup_channel(&card->read, true)) goto out_ip; if (qeth_setup_channel(&card->write, true)) @@ -1454,6 +1486,8 @@ out_data: out_channel: qeth_clean_channel(&card->read); out_ip: + destroy_workqueue(card->event_wq); +out_wq: dev_set_drvdata(&gdev->dev, NULL); kfree(card); out: @@ -1782,6 +1816,7 @@ static int qeth_idx_activate_get_answer(struct qeth_card *card, QETH_DBF_MESSAGE(2, "Error2 in activating channel rc=%d\n", rc); QETH_DBF_TEXT_(SETUP, 2, "2err%d", rc); atomic_set(&channel->irq_pending, 0); + qeth_release_buffer(channel, iob); wake_up(&card->wait_q); return rc; } @@ -1851,6 +1886,7 @@ static int qeth_idx_activate_channel(struct qeth_card *card, rc); QETH_DBF_TEXT_(SETUP, 2, "1err%d", rc); atomic_set(&channel->irq_pending, 0); + qeth_release_buffer(channel, iob); wake_up(&card->wait_q); return rc; } @@ -1981,7 +2017,7 @@ void qeth_prepare_control_data(struct qeth_card *card, int len, card->seqno.pdu_hdr++; memcpy(QETH_PDU_HEADER_ACK_SEQ_NO(iob->data), &card->seqno.pdu_hdr_ack, QETH_SEQ_NO_LENGTH); - QETH_DBF_HEX(CTRL, 2, iob->data, QETH_DBF_CTRL_LEN); + QETH_DBF_HEX(CTRL, 2, iob->data, min(len, QETH_DBF_CTRL_LEN)); } EXPORT_SYMBOL_GPL(qeth_prepare_control_data); @@ -1998,24 +2034,22 @@ EXPORT_SYMBOL_GPL(qeth_prepare_control_data); * for the IPA commands. * @reply_param: private pointer passed to the callback * - * Returns the value of the `return_code' field of the response - * block returned from the hardware, or other error indication. - * Value of zero indicates successful execution of the command. - * * Callback function gets called one or more times, with cb_cmd * pointing to the response returned by the hardware. Callback - * function must return non-zero if more reply blocks are expected, - * and zero if the last or only reply block is received. Callback - * function can get the value of the reply_param pointer from the + * function must return + * > 0 if more reply blocks are expected, + * 0 if the last or only reply block is received, and + * < 0 on error. + * Callback function can get the value of the reply_param pointer from the * field 'param' of the structure qeth_reply. */ -int qeth_send_control_data(struct qeth_card *card, int len, - struct qeth_cmd_buffer *iob, - int (*reply_cb)(struct qeth_card *cb_card, - struct qeth_reply *cb_reply, - unsigned long cb_cmd), - void *reply_param) +static int qeth_send_control_data(struct qeth_card *card, int len, + struct qeth_cmd_buffer *iob, + int (*reply_cb)(struct qeth_card *cb_card, + struct qeth_reply *cb_reply, + unsigned long cb_cmd), + void *reply_param) { struct qeth_channel *channel = iob->channel; int rc; @@ -2031,12 +2065,15 @@ int qeth_send_control_data(struct qeth_card *card, int len, } reply = qeth_alloc_reply(card); if (!reply) { + qeth_release_buffer(channel, iob); return -ENOMEM; } reply->callback = reply_cb; reply->param = reply_param; - init_waitqueue_head(&reply->wait_q); + /* pairs with qeth_release_buffer(): */ + qeth_get_reply(reply); + iob->reply = reply; while (atomic_cmpxchg(&channel->irq_pending, 0, 1)) ; @@ -2051,9 +2088,7 @@ int qeth_send_control_data(struct qeth_card *card, int len, } qeth_prepare_control_data(card, len, iob); - spin_lock_irq(&card->lock); - list_add_tail(&reply->list, &card->cmd_waiter_list); - spin_unlock_irq(&card->lock); + qeth_enqueue_reply(card, reply); timeout = jiffies + event_timeout; @@ -2066,10 +2101,8 @@ int qeth_send_control_data(struct qeth_card *card, int len, QETH_DBF_MESSAGE(2, "qeth_send_control_data on device %x: ccw_device_start rc = %i\n", CARD_DEVID(card), rc); QETH_CARD_TEXT_(card, 2, " err%d", rc); - spin_lock_irq(&card->lock); - list_del_init(&reply->list); + qeth_dequeue_reply(card, reply); qeth_put_reply(reply); - spin_unlock_irq(&card->lock); qeth_release_buffer(channel, iob); atomic_set(&channel->irq_pending, 0); wake_up(&card->wait_q); @@ -2091,21 +2124,16 @@ int qeth_send_control_data(struct qeth_card *card, int len, } } + qeth_dequeue_reply(card, reply); rc = reply->rc; qeth_put_reply(reply); return rc; time_err: - reply->rc = -ETIME; - spin_lock_irq(&card->lock); - list_del_init(&reply->list); - spin_unlock_irq(&card->lock); - atomic_inc(&reply->received); - rc = reply->rc; + qeth_dequeue_reply(card, reply); qeth_put_reply(reply); - return rc; + return -ETIME; } -EXPORT_SYMBOL_GPL(qeth_send_control_data); static int qeth_cm_enable_cb(struct qeth_card *card, struct qeth_reply *reply, unsigned long data) @@ -2310,9 +2338,8 @@ static int qeth_ulp_setup_cb(struct qeth_card *card, struct qeth_reply *reply, QETH_DBF_TEXT(SETUP, 2, "olmlimit"); dev_err(&card->gdev->dev, "A connection could not be " "established because of an OLM limit\n"); - iob->rc = -EMLINK; + return -EMLINK; } - QETH_DBF_TEXT_(SETUP, 2, " rc%d", iob->rc); return 0; } @@ -2362,11 +2389,12 @@ static int qeth_init_qdio_out_buf(struct qeth_qdio_out_q *q, int bidx) return 0; } -static void qeth_free_qdio_out_buf(struct qeth_qdio_out_q *q) +static void qeth_free_output_queue(struct qeth_qdio_out_q *q) { if (!q) return; + qeth_clear_outq_buffers(q, 1); qdio_free_buffers(q->qdio_bufs, QDIO_MAX_BUFFERS_PER_Q); kfree(q); } @@ -2405,12 +2433,6 @@ static int qeth_alloc_qdio_buffers(struct qeth_card *card) goto out_freeinq; /* outbound */ - card->qdio.out_qs = - kcalloc(card->qdio.no_out_queues, - sizeof(struct qeth_qdio_out_q *), - GFP_KERNEL); - if (!card->qdio.out_qs) - goto out_freepool; for (i = 0; i < card->qdio.no_out_queues; ++i) { card->qdio.out_qs[i] = qeth_alloc_qdio_out_buf(); if (!card->qdio.out_qs[i]) @@ -2441,12 +2463,9 @@ out_freeoutqbufs: } out_freeoutq: while (i > 0) { - qeth_free_qdio_out_buf(card->qdio.out_qs[--i]); - qeth_clear_outq_buffers(card->qdio.out_qs[i], 1); + qeth_free_output_queue(card->qdio.out_qs[--i]); + card->qdio.out_qs[i] = NULL; } - kfree(card->qdio.out_qs); - card->qdio.out_qs = NULL; -out_freepool: qeth_free_buffer_pool(card); out_freeinq: qeth_free_qdio_queue(card->qdio.in_q); @@ -2475,13 +2494,9 @@ static void qeth_free_qdio_buffers(struct qeth_card *card) /* inbound buffer pool */ qeth_free_buffer_pool(card); /* free outbound qdio_qs */ - if (card->qdio.out_qs) { - for (i = 0; i < card->qdio.no_out_queues; ++i) { - qeth_clear_outq_buffers(card->qdio.out_qs[i], 1); - qeth_free_qdio_out_buf(card->qdio.out_qs[i]); - } - kfree(card->qdio.out_qs); - card->qdio.out_qs = NULL; + for (i = 0; i < card->qdio.no_out_queues; i++) { + qeth_free_output_queue(card->qdio.out_qs[i]); + card->qdio.out_qs[i] = NULL; } } @@ -2688,8 +2703,7 @@ static struct qeth_buffer_pool_entry *qeth_find_free_buffer_pool_entry( } else { free_page((unsigned long)entry->elements[i]); entry->elements[i] = page_address(page); - if (card->options.performance_stats) - card->perf_stats.sg_alloc_page_rx++; + QETH_CARD_STAT_INC(card, rx_sg_alloc_page); } } } @@ -2808,14 +2822,20 @@ static void qeth_fill_ipacmd_header(struct qeth_card *card, cmd->hdr.prot_version = prot; } -void qeth_prepare_ipa_cmd(struct qeth_card *card, struct qeth_cmd_buffer *iob) +void qeth_prepare_ipa_cmd(struct qeth_card *card, struct qeth_cmd_buffer *iob, + u16 cmd_length) { + u16 total_length = IPA_PDU_HEADER_SIZE + cmd_length; u8 prot_type = qeth_mpc_select_prot_type(card); memcpy(iob->data, IPA_PDU_HEADER, IPA_PDU_HEADER_SIZE); + memcpy(QETH_IPA_PDU_LEN_TOTAL(iob->data), &total_length, 2); memcpy(QETH_IPA_CMD_PROT_TYPE(iob->data), &prot_type, 1); + memcpy(QETH_IPA_PDU_LEN_PDU1(iob->data), &cmd_length, 2); + memcpy(QETH_IPA_PDU_LEN_PDU2(iob->data), &cmd_length, 2); memcpy(QETH_IPA_CMD_DEST_ADDR(iob->data), &card->token.ulp_connection_r, QETH_MPC_TOKEN_LENGTH); + memcpy(QETH_IPA_PDU_LEN_PDU3(iob->data), &cmd_length, 2); } EXPORT_SYMBOL_GPL(qeth_prepare_ipa_cmd); @@ -2826,7 +2846,7 @@ struct qeth_cmd_buffer *qeth_get_ipacmd_buffer(struct qeth_card *card, iob = qeth_get_buffer(&card->write); if (iob) { - qeth_prepare_ipa_cmd(card, iob); + qeth_prepare_ipa_cmd(card, iob, sizeof(struct qeth_ipa_cmd)); qeth_fill_ipacmd_header(card, __ipa_cmd(iob), ipacmd, prot); } else { dev_warn(&card->gdev->dev, @@ -2839,6 +2859,14 @@ struct qeth_cmd_buffer *qeth_get_ipacmd_buffer(struct qeth_card *card, } EXPORT_SYMBOL_GPL(qeth_get_ipacmd_buffer); +static int qeth_send_ipa_cmd_cb(struct qeth_card *card, + struct qeth_reply *reply, unsigned long data) +{ + struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data; + + return (cmd->hdr.return_code) ? -EIO : 0; +} + /** * qeth_send_ipa_cmd() - send an IPA command * @@ -2850,11 +2878,15 @@ int qeth_send_ipa_cmd(struct qeth_card *card, struct qeth_cmd_buffer *iob, unsigned long), void *reply_param) { + u16 length; int rc; QETH_CARD_TEXT(card, 4, "sendipa"); - rc = qeth_send_control_data(card, IPA_CMD_LENGTH, - iob, reply_cb, reply_param); + + if (reply_cb == NULL) + reply_cb = qeth_send_ipa_cmd_cb; + memcpy(&length, QETH_IPA_PDU_LEN_TOTAL(iob->data), 2); + rc = qeth_send_control_data(card, length, iob, reply_cb, reply_param); if (rc == -ETIME) { qeth_clear_ipacmd_list(card); qeth_schedule_recovery(card); @@ -2863,9 +2895,19 @@ int qeth_send_ipa_cmd(struct qeth_card *card, struct qeth_cmd_buffer *iob, } EXPORT_SYMBOL_GPL(qeth_send_ipa_cmd); +static int qeth_send_startlan_cb(struct qeth_card *card, + struct qeth_reply *reply, unsigned long data) +{ + struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data; + + if (cmd->hdr.return_code == IPA_RC_LAN_OFFLINE) + return -ENETDOWN; + + return (cmd->hdr.return_code) ? -EIO : 0; +} + static int qeth_send_startlan(struct qeth_card *card) { - int rc; struct qeth_cmd_buffer *iob; QETH_DBF_TEXT(SETUP, 2, "strtlan"); @@ -2873,8 +2915,7 @@ static int qeth_send_startlan(struct qeth_card *card) iob = qeth_get_ipacmd_buffer(card, IPA_CMD_STARTLAN, 0); if (!iob) return -ENOMEM; - rc = qeth_send_ipa_cmd(card, iob, NULL, NULL); - return rc; + return qeth_send_ipa_cmd(card, iob, qeth_send_startlan_cb, NULL); } static int qeth_setadpparms_inspect_rc(struct qeth_ipa_cmd *cmd) @@ -2892,7 +2933,7 @@ static int qeth_query_setadapterparms_cb(struct qeth_card *card, QETH_CARD_TEXT(card, 3, "quyadpcb"); if (qeth_setadpparms_inspect_rc(cmd)) - return 0; + return -EIO; if (cmd->data.setadapterparms.data.query_cmds_supp.lan_type & 0x7f) { card->info.link_type = @@ -2947,19 +2988,18 @@ static int qeth_query_ipassists_cb(struct qeth_card *card, cmd = (struct qeth_ipa_cmd *) data; switch (cmd->hdr.return_code) { + case IPA_RC_SUCCESS: + break; case IPA_RC_NOTSUPP: case IPA_RC_L2_UNSUPPORTED_CMD: QETH_DBF_TEXT(SETUP, 2, "ipaunsup"); card->options.ipa4.supported_funcs |= IPA_SETADAPTERPARMS; card->options.ipa6.supported_funcs |= IPA_SETADAPTERPARMS; - return 0; + return -EOPNOTSUPP; default: - if (cmd->hdr.return_code) { - QETH_DBF_MESSAGE(1, "IPA_CMD_QIPASSIST on device %x: Unhandled rc=%#x\n", - CARD_DEVID(card), - cmd->hdr.return_code); - return 0; - } + QETH_DBF_MESSAGE(1, "IPA_CMD_QIPASSIST on device %x: Unhandled rc=%#x\n", + CARD_DEVID(card), cmd->hdr.return_code); + return -EIO; } if (cmd->hdr.prot_version == QETH_PROT_IPV4) { @@ -2997,7 +3037,7 @@ static int qeth_query_switch_attributes_cb(struct qeth_card *card, QETH_CARD_TEXT(card, 2, "qswiatcb"); if (qeth_setadpparms_inspect_rc(cmd)) - return 0; + return -EIO; sw_info = (struct qeth_switch_info *)reply->param; attrs = &cmd->data.setadapterparms.data.query_switch_attributes; @@ -3029,15 +3069,15 @@ int qeth_query_switch_attributes(struct qeth_card *card, static int qeth_query_setdiagass_cb(struct qeth_card *card, struct qeth_reply *reply, unsigned long data) { - struct qeth_ipa_cmd *cmd; - __u16 rc; + struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data; + u16 rc = cmd->hdr.return_code; - cmd = (struct qeth_ipa_cmd *)data; - rc = cmd->hdr.return_code; - if (rc) + if (rc) { QETH_CARD_TEXT_(card, 2, "diagq:%x", rc); - else - card->info.diagass_support = cmd->data.diagass.ext; + return -EIO; + } + + card->info.diagass_support = cmd->data.diagass.ext; return 0; } @@ -3084,13 +3124,13 @@ static void qeth_get_trap_id(struct qeth_card *card, struct qeth_trap_id *tid) static int qeth_hw_trap_cb(struct qeth_card *card, struct qeth_reply *reply, unsigned long data) { - struct qeth_ipa_cmd *cmd; - __u16 rc; + struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data; + u16 rc = cmd->hdr.return_code; - cmd = (struct qeth_ipa_cmd *)data; - rc = cmd->hdr.return_code; - if (rc) + if (rc) { QETH_CARD_TEXT_(card, 2, "trapc:%x", rc); + return -EIO; + } return 0; } @@ -3139,7 +3179,7 @@ static int qeth_check_qdio_errors(struct qeth_card *card, buf->element[14].sflags); QETH_CARD_TEXT_(card, 2, " qerr=%X", qdio_error); if ((buf->element[15].sflags) == 0x12) { - card->stats.rx_dropped++; + QETH_CARD_STAT_INC(card, rx_dropped); return 0; } else return 1; @@ -3203,17 +3243,8 @@ static void qeth_queue_input_buffer(struct qeth_card *card, int index) * 'index') un-requeued -> this buffer is the first buffer that * will be requeued the next time */ - if (card->options.performance_stats) { - card->perf_stats.inbound_do_qdio_cnt++; - card->perf_stats.inbound_do_qdio_start_time = - qeth_get_micros(); - } rc = do_QDIO(CARD_DDEV(card), QDIO_FLAG_SYNC_INPUT, 0, queue->next_buf_to_init, count); - if (card->options.performance_stats) - card->perf_stats.inbound_do_qdio_time += - qeth_get_micros() - - card->perf_stats.inbound_do_qdio_start_time; if (rc) { QETH_CARD_TEXT(card, 2, "qinberr"); } @@ -3290,8 +3321,7 @@ static void qeth_switch_to_packing_if_needed(struct qeth_qdio_out_q *queue) >= QETH_HIGH_WATERMARK_PACK){ /* switch non-PACKING -> PACKING */ QETH_CARD_TEXT(queue->card, 6, "np->pack"); - if (queue->card->options.performance_stats) - queue->card->perf_stats.sc_dp_p++; + QETH_TXQ_STAT_INC(queue, packing_mode_switch); queue->do_pack = 1; } } @@ -3310,8 +3340,7 @@ static int qeth_switch_to_nonpacking_if_needed(struct qeth_qdio_out_q *queue) <= QETH_LOW_WATERMARK_PACK) { /* switch PACKING -> non-PACKING */ QETH_CARD_TEXT(queue->card, 6, "pack->np"); - if (queue->card->options.performance_stats) - queue->card->perf_stats.sc_p_dp++; + QETH_TXQ_STAT_INC(queue, packing_mode_switch); queue->do_pack = 0; return qeth_prep_flush_pack_buffer(queue); } @@ -3365,25 +3394,16 @@ static void qeth_flush_buffers(struct qeth_qdio_out_q *queue, int index, } } + QETH_TXQ_STAT_ADD(queue, bufs, count); netif_trans_update(queue->card->dev); - if (queue->card->options.performance_stats) { - queue->card->perf_stats.outbound_do_qdio_cnt++; - queue->card->perf_stats.outbound_do_qdio_start_time = - qeth_get_micros(); - } qdio_flags = QDIO_FLAG_SYNC_OUTPUT; if (atomic_read(&queue->set_pci_flags_count)) qdio_flags |= QDIO_FLAG_PCI_OUT; atomic_add(count, &queue->used_buffers); - rc = do_QDIO(CARD_DDEV(queue->card), qdio_flags, queue->queue_no, index, count); - if (queue->card->options.performance_stats) - queue->card->perf_stats.outbound_do_qdio_time += - qeth_get_micros() - - queue->card->perf_stats.outbound_do_qdio_start_time; if (rc) { - queue->card->stats.tx_errors += count; + QETH_TXQ_STAT_ADD(queue, tx_errors, count); /* ignore temporary SIGA errors without busy condition */ if (rc == -ENOBUFS) return; @@ -3398,8 +3418,6 @@ static void qeth_flush_buffers(struct qeth_qdio_out_q *queue, int index, qeth_schedule_recovery(queue->card); return; } - if (queue->card->options.performance_stats) - queue->card->perf_stats.bufs_sent += count; } static void qeth_check_outbound_queue(struct qeth_qdio_out_q *queue) @@ -3430,10 +3448,8 @@ static void qeth_check_outbound_queue(struct qeth_qdio_out_q *queue) if (!flush_cnt && !atomic_read(&queue->set_pci_flags_count)) flush_cnt += qeth_prep_flush_pack_buffer(queue); - if (queue->card->options.performance_stats && - q_was_packing) - queue->card->perf_stats.bufs_sent_pack += - flush_cnt; + if (q_was_packing) + QETH_TXQ_STAT_ADD(queue, bufs_pack, flush_cnt); if (flush_cnt) qeth_flush_buffers(queue, index, flush_cnt); atomic_set(&queue->state, QETH_OUT_Q_UNLOCKED); @@ -3488,7 +3504,7 @@ static void qeth_qdio_cq_handler(struct qeth_card *card, unsigned int qdio_err, int rc; if (!qeth_is_cq(card, queue)) - goto out; + return; QETH_CARD_TEXT_(card, 5, "qcqhe%d", first_element); QETH_CARD_TEXT_(card, 5, "qcqhc%d", count); @@ -3497,12 +3513,7 @@ static void qeth_qdio_cq_handler(struct qeth_card *card, unsigned int qdio_err, if (qdio_err) { netif_stop_queue(card->dev); qeth_schedule_recovery(card); - goto out; - } - - if (card->options.performance_stats) { - card->perf_stats.cq_cnt++; - card->perf_stats.cq_start_time = qeth_get_micros(); + return; } for (i = first_element; i < first_element + count; ++i) { @@ -3530,14 +3541,6 @@ static void qeth_qdio_cq_handler(struct qeth_card *card, unsigned int qdio_err, } card->qdio.c_q->next_buf_to_init = (card->qdio.c_q->next_buf_to_init + count) % QDIO_MAX_BUFFERS_PER_Q; - - if (card->options.performance_stats) { - int delta_t = qeth_get_micros(); - delta_t -= card->perf_stats.cq_start_time; - card->perf_stats.cq_time += delta_t; - } -out: - return; } static void qeth_qdio_input_handler(struct ccw_device *ccwdev, @@ -3573,11 +3576,7 @@ static void qeth_qdio_output_handler(struct ccw_device *ccwdev, qeth_schedule_recovery(card); return; } - if (card->options.performance_stats) { - card->perf_stats.outbound_handler_cnt++; - card->perf_stats.outbound_handler_start_time = - qeth_get_micros(); - } + for (i = first_element; i < (first_element + count); ++i) { int bidx = i % QDIO_MAX_BUFFERS_PER_Q; buffer = queue->bufs[bidx]; @@ -3623,9 +3622,6 @@ static void qeth_qdio_output_handler(struct ccw_device *ccwdev, qeth_check_outbound_queue(queue); netif_wake_queue(queue->card->dev); - if (card->options.performance_stats) - card->perf_stats.outbound_handler_time += qeth_get_micros() - - card->perf_stats.outbound_handler_start_time; } /* We cannot use outbound queue 3 for unicast packets on HiperSockets */ @@ -3746,11 +3742,12 @@ EXPORT_SYMBOL_GPL(qeth_count_elements); * The number of needed buffer elements is returned in @elements. * Error to create the hdr is indicated by returning with < 0. */ -static int qeth_add_hw_header(struct qeth_card *card, struct sk_buff *skb, - struct qeth_hdr **hdr, unsigned int hdr_len, - unsigned int proto_len, unsigned int *elements) +static int qeth_add_hw_header(struct qeth_qdio_out_q *queue, + struct sk_buff *skb, struct qeth_hdr **hdr, + unsigned int hdr_len, unsigned int proto_len, + unsigned int *elements) { - const unsigned int max_elements = QETH_MAX_BUFFER_ELEMENTS(card); + const unsigned int max_elements = QETH_MAX_BUFFER_ELEMENTS(queue->card); const unsigned int contiguous = proto_len ? proto_len : 1; unsigned int __elements; addr_t start, end; @@ -3789,15 +3786,12 @@ check_layout: } rc = skb_linearize(skb); - if (card->options.performance_stats) { - if (rc) - card->perf_stats.tx_linfail++; - else - card->perf_stats.tx_lin++; - } - if (rc) + if (rc) { + QETH_TXQ_STAT_INC(queue, skbs_linearized_fail); return rc; + } + QETH_TXQ_STAT_INC(queue, skbs_linearized); /* Linearization changed the layout, re-evaluate: */ goto check_layout; } @@ -3921,9 +3915,8 @@ static int qeth_fill_buffer(struct qeth_qdio_out_q *queue, QETH_CARD_TEXT(queue->card, 6, "fillbfnp"); } else { QETH_CARD_TEXT(queue->card, 6, "fillbfpa"); - if (queue->card->options.performance_stats) - queue->card->perf_stats.skbs_sent_pack++; + QETH_TXQ_STAT_INC(queue, skbs_pack); /* If the buffer still has free elements, keep using it. */ if (buf->next_element_to_fill < QETH_MAX_BUFFER_ELEMENTS(queue->card)) @@ -4037,8 +4030,8 @@ int qeth_do_send_packet(struct qeth_card *card, struct qeth_qdio_out_q *queue, } out: /* at this point the queue is UNLOCKED again */ - if (queue->card->options.performance_stats && do_pack) - queue->card->perf_stats.bufs_sent_pack += flush_count; + if (do_pack) + QETH_TXQ_STAT_ADD(queue, bufs_pack, flush_count); return rc; } @@ -4062,8 +4055,9 @@ static void qeth_fill_tso_ext(struct qeth_hdr_tso *hdr, int qeth_xmit(struct qeth_card *card, struct sk_buff *skb, struct qeth_qdio_out_q *queue, int ipv, int cast_type, - void (*fill_header)(struct qeth_card *card, struct qeth_hdr *hdr, - struct sk_buff *skb, int ipv, int cast_type, + void (*fill_header)(struct qeth_qdio_out_q *queue, + struct qeth_hdr *hdr, struct sk_buff *skb, + int ipv, int cast_type, unsigned int data_len)) { unsigned int proto_len, hw_hdr_len; @@ -4088,7 +4082,7 @@ int qeth_xmit(struct qeth_card *card, struct sk_buff *skb, if (rc) return rc; - push_len = qeth_add_hw_header(card, skb, &hdr, hw_hdr_len, proto_len, + push_len = qeth_add_hw_header(queue, skb, &hdr, hw_hdr_len, proto_len, &elements); if (push_len < 0) return push_len; @@ -4098,7 +4092,7 @@ int qeth_xmit(struct qeth_card *card, struct sk_buff *skb, data_offset = push_len + proto_len; } memset(hdr, 0, hw_hdr_len); - fill_header(card, hdr, skb, ipv, cast_type, frame_len); + fill_header(queue, hdr, skb, ipv, cast_type, frame_len); if (is_tso) qeth_fill_tso_ext((struct qeth_hdr_tso *) hdr, frame_len - proto_len, skb, proto_len); @@ -4115,14 +4109,12 @@ int qeth_xmit(struct qeth_card *card, struct sk_buff *skb, } if (!rc) { - if (card->options.performance_stats) { - card->perf_stats.buf_elements_sent += elements; - if (is_sg) - card->perf_stats.sg_skbs_sent++; - if (is_tso) { - card->perf_stats.large_send_bytes += frame_len; - card->perf_stats.large_send_cnt++; - } + QETH_TXQ_STAT_ADD(queue, buf_elements, elements); + if (is_sg) + QETH_TXQ_STAT_INC(queue, skbs_sg); + if (is_tso) { + QETH_TXQ_STAT_INC(queue, skbs_tso); + QETH_TXQ_STAT_ADD(queue, tso_bytes, frame_len); } } else { if (!push_len) @@ -4149,7 +4141,7 @@ static int qeth_setadp_promisc_mode_cb(struct qeth_card *card, setparms->data.mode = SET_PROMISC_MODE_OFF; } card->info.promisc_mode = setparms->data.mode; - return 0; + return (cmd->hdr.return_code) ? -EIO : 0; } void qeth_setadp_promisc_mode(struct qeth_card *card) @@ -4181,18 +4173,6 @@ void qeth_setadp_promisc_mode(struct qeth_card *card) } EXPORT_SYMBOL_GPL(qeth_setadp_promisc_mode); -struct net_device_stats *qeth_get_stats(struct net_device *dev) -{ - struct qeth_card *card; - - card = dev->ml_priv; - - QETH_CARD_TEXT(card, 5, "getstat"); - - return &card->stats; -} -EXPORT_SYMBOL_GPL(qeth_get_stats); - static int qeth_setadpparms_change_macaddr_cb(struct qeth_card *card, struct qeth_reply *reply, unsigned long data) { @@ -4201,12 +4181,15 @@ static int qeth_setadpparms_change_macaddr_cb(struct qeth_card *card, QETH_CARD_TEXT(card, 4, "chgmaccb"); if (qeth_setadpparms_inspect_rc(cmd)) - return 0; + return -EIO; adp_cmd = &cmd->data.setadapterparms; + if (!is_valid_ether_addr(adp_cmd->data.change_addr.addr)) + return -EADDRNOTAVAIL; + if (IS_LAYER2(card) && IS_OSD(card) && !IS_VM_NIC(card) && !(adp_cmd->hdr.flags & QETH_SETADP_FLAGS_VIRTUAL_MAC)) - return 0; + return -EADDRNOTAVAIL; ether_addr_copy(card->dev->dev_addr, adp_cmd->data.change_addr.addr); return 0; @@ -4245,7 +4228,7 @@ static int qeth_setadpparms_set_access_ctrl_cb(struct qeth_card *card, QETH_CARD_TEXT(card, 4, "setaccb"); if (cmd->hdr.return_code) - return 0; + return -EIO; qeth_setadpparms_inspect_rc(cmd); access_ctrl_req = &cmd->data.setadapterparms.data.set_access_ctrl; @@ -4319,7 +4302,7 @@ static int qeth_setadpparms_set_access_ctrl_cb(struct qeth_card *card, card->options.isolation = card->options.prev_isolation; break; } - return 0; + return (cmd->hdr.return_code) ? -EIO : 0; } static int qeth_setadpparms_set_access_ctrl(struct qeth_card *card, @@ -4383,7 +4366,7 @@ void qeth_tx_timeout(struct net_device *dev) card = dev->ml_priv; QETH_CARD_TEXT(card, 4, "txtimeo"); - card->stats.tx_errors++; + QETH_CARD_STAT_INC(card, tx_errors); qeth_schedule_recovery(card); } EXPORT_SYMBOL_GPL(qeth_tx_timeout); @@ -4453,27 +4436,6 @@ static int qeth_mdio_read(struct net_device *dev, int phy_id, int regnum) return rc; } -static int qeth_send_ipa_snmp_cmd(struct qeth_card *card, - struct qeth_cmd_buffer *iob, int len, - int (*reply_cb)(struct qeth_card *, struct qeth_reply *, - unsigned long), - void *reply_param) -{ - u16 s1, s2; - - QETH_CARD_TEXT(card, 4, "sendsnmp"); - - /* adjust PDU length fields in IPA_PDU_HEADER */ - s1 = (u32) IPA_PDU_HEADER_SIZE + len; - s2 = (u32) len; - memcpy(QETH_IPA_PDU_LEN_TOTAL(iob->data), &s1, 2); - memcpy(QETH_IPA_PDU_LEN_PDU1(iob->data), &s2, 2); - memcpy(QETH_IPA_PDU_LEN_PDU2(iob->data), &s2, 2); - memcpy(QETH_IPA_PDU_LEN_PDU3(iob->data), &s2, 2); - return qeth_send_control_data(card, IPA_PDU_HEADER_SIZE + len, iob, - reply_cb, reply_param); -} - static int qeth_snmp_command_cb(struct qeth_card *card, struct qeth_reply *reply, unsigned long sdata) { @@ -4491,13 +4453,13 @@ static int qeth_snmp_command_cb(struct qeth_card *card, if (cmd->hdr.return_code) { QETH_CARD_TEXT_(card, 4, "scer1%x", cmd->hdr.return_code); - return 0; + return -EIO; } if (cmd->data.setadapterparms.hdr.return_code) { cmd->hdr.return_code = cmd->data.setadapterparms.hdr.return_code; QETH_CARD_TEXT_(card, 4, "scer2%x", cmd->hdr.return_code); - return 0; + return -EIO; } data_len = *((__u16 *)QETH_IPA_PDU_LEN_PDU1(data)); if (cmd->data.setadapterparms.hdr.seq_no == 1) { @@ -4512,9 +4474,8 @@ static int qeth_snmp_command_cb(struct qeth_card *card, /* check if there is enough room in userspace */ if ((qinfo->udata_len - qinfo->udata_offset) < data_len) { - QETH_CARD_TEXT_(card, 4, "scer3%i", -ENOMEM); - cmd->hdr.return_code = IPA_RC_ENOMEM; - return 0; + QETH_CARD_TEXT_(card, 4, "scer3%i", -ENOSPC); + return -ENOSPC; } QETH_CARD_TEXT_(card, 4, "snore%i", cmd->data.setadapterparms.hdr.used_total); @@ -4579,10 +4540,13 @@ static int qeth_snmp_command(struct qeth_card *card, char __user *udata) rc = -ENOMEM; goto out; } + + /* for large requests, fix-up the length fields: */ + qeth_prepare_ipa_cmd(card, iob, QETH_SETADP_BASE_LEN + req_len); + cmd = __ipa_cmd(iob); memcpy(&cmd->data.setadapterparms.data.snmp, &ureq->cmd, req_len); - rc = qeth_send_ipa_snmp_cmd(card, iob, QETH_SETADP_BASE_LEN + req_len, - qeth_snmp_command_cb, (void *)&qinfo); + rc = qeth_send_ipa_cmd(card, iob, qeth_snmp_command_cb, &qinfo); if (rc) QETH_DBF_MESSAGE(2, "SNMP command failed on device %x: (%#x)\n", CARD_DEVID(card), rc); @@ -4606,16 +4570,14 @@ static int qeth_setadpparms_query_oat_cb(struct qeth_card *card, QETH_CARD_TEXT(card, 3, "qoatcb"); if (qeth_setadpparms_inspect_rc(cmd)) - return 0; + return -EIO; priv = (struct qeth_qoat_priv *)reply->param; resdatalen = cmd->data.setadapterparms.hdr.cmdlength; resdata = (char *)data + 28; - if (resdatalen > (priv->buffer_len - priv->response_len)) { - cmd->hdr.return_code = IPA_RC_FFFF; - return 0; - } + if (resdatalen > (priv->buffer_len - priv->response_len)) + return -ENOSPC; memcpy((priv->buffer + priv->response_len), resdata, resdatalen); @@ -4688,9 +4650,7 @@ static int qeth_query_oat_command(struct qeth_card *card, char __user *udata) if (copy_to_user(udata, &oat_data, sizeof(struct qeth_query_oat_data))) rc = -EFAULT; - } else - if (rc == IPA_RC_FFFF) - rc = -EFAULT; + } out_free: vfree(priv.buffer); @@ -4707,7 +4667,7 @@ static int qeth_query_card_info_cb(struct qeth_card *card, QETH_CARD_TEXT(card, 2, "qcrdincb"); if (qeth_setadpparms_inspect_rc(cmd)) - return 0; + return -EIO; card_info = &cmd->data.setadapterparms.data.card_info; carrier_info->card_type = card_info->card_type; @@ -4716,8 +4676,8 @@ static int qeth_query_card_info_cb(struct qeth_card *card, return 0; } -static int qeth_query_card_info(struct qeth_card *card, - struct carrier_info *carrier_info) +int qeth_query_card_info(struct qeth_card *card, + struct carrier_info *carrier_info) { struct qeth_cmd_buffer *iob; @@ -4994,6 +4954,7 @@ static void qeth_core_free_card(struct qeth_card *card) qeth_clean_channel(&card->read); qeth_clean_channel(&card->write); qeth_clean_channel(&card->data); + destroy_workqueue(card->event_wq); qeth_free_qdio_buffers(card); unregister_service_level(&card->qeth_service_level); dev_set_drvdata(&card->gdev->dev, NULL); @@ -5108,12 +5069,10 @@ retriable: rc = qeth_send_startlan(card); if (rc) { QETH_DBF_TEXT_(SETUP, 2, "6err%d", rc); - if (rc == IPA_RC_LAN_OFFLINE) { - dev_warn(&card->gdev->dev, - "The LAN is offline\n"); + if (rc == -ENETDOWN) { + dev_warn(&card->gdev->dev, "The LAN is offline\n"); *carrier_ok = false; } else { - rc = -ENODEV; goto out; } } else { @@ -5265,7 +5224,7 @@ struct sk_buff *qeth_core_get_next_skb(struct qeth_card *card, QETH_CARD_TEXT(card, 4, "unexeob"); QETH_CARD_HEX(card, 2, buffer, sizeof(void *)); dev_kfree_skb_any(skb); - card->stats.rx_errors++; + QETH_CARD_STAT_INC(card, rx_errors); return NULL; } element++; @@ -5277,16 +5236,17 @@ struct sk_buff *qeth_core_get_next_skb(struct qeth_card *card, } *__element = element; *__offset = offset; - if (use_rx_sg && card->options.performance_stats) { - card->perf_stats.sg_skbs_rx++; - card->perf_stats.sg_frags_rx += skb_shinfo(skb)->nr_frags; + if (use_rx_sg) { + QETH_CARD_STAT_INC(card, rx_sg_skbs); + QETH_CARD_STAT_ADD(card, rx_sg_frags, + skb_shinfo(skb)->nr_frags); } return skb; no_mem: if (net_ratelimit()) { QETH_CARD_TEXT(card, 2, "noskbmem"); } - card->stats.rx_dropped++; + QETH_CARD_STAT_INC(card, rx_dropped); return NULL; } EXPORT_SYMBOL_GPL(qeth_core_get_next_skb); @@ -5299,11 +5259,6 @@ int qeth_poll(struct napi_struct *napi, int budget) int done; int new_budget = budget; - if (card->options.performance_stats) { - card->perf_stats.inbound_cnt++; - card->perf_stats.inbound_start_time = qeth_get_micros(); - } - while (1) { if (!card->rx.b_count) { card->rx.qdio_err = 0; @@ -5332,8 +5287,7 @@ int qeth_poll(struct napi_struct *napi, int budget) done = 1; if (done) { - if (card->options.performance_stats) - card->perf_stats.bufs_rec++; + QETH_CARD_STAT_INC(card, rx_bufs); qeth_put_buffer_pool_entry(card, buffer->pool_entry); qeth_queue_input_buffer(card, card->rx.b_index); @@ -5361,9 +5315,6 @@ int qeth_poll(struct napi_struct *napi, int budget) if (qdio_start_irq(card->data.ccwdev, 0)) napi_schedule(&card->napi); out: - if (card->options.performance_stats) - card->perf_stats.inbound_time += qeth_get_micros() - - card->perf_stats.inbound_start_time; return work_done; } EXPORT_SYMBOL_GPL(qeth_poll); @@ -5383,7 +5334,7 @@ static int qeth_setassparms_get_caps_cb(struct qeth_card *card, struct qeth_ipa_caps *caps = reply->param; if (qeth_setassparms_inspect_rc(cmd)) - return 0; + return -EIO; caps->supported = cmd->data.setassparms.data.caps.supported; caps->enabled = cmd->data.setassparms.data.caps.enabled; @@ -5393,18 +5344,18 @@ static int qeth_setassparms_get_caps_cb(struct qeth_card *card, int qeth_setassparms_cb(struct qeth_card *card, struct qeth_reply *reply, unsigned long data) { - struct qeth_ipa_cmd *cmd; + struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data; QETH_CARD_TEXT(card, 4, "defadpcb"); - cmd = (struct qeth_ipa_cmd *) data; - if (cmd->hdr.return_code == 0) { - cmd->hdr.return_code = cmd->data.setassparms.hdr.return_code; - if (cmd->hdr.prot_version == QETH_PROT_IPV4) - card->options.ipa4.enabled_funcs = cmd->hdr.ipa_enabled; - if (cmd->hdr.prot_version == QETH_PROT_IPV6) - card->options.ipa6.enabled_funcs = cmd->hdr.ipa_enabled; - } + if (cmd->hdr.return_code) + return -EIO; + + cmd->hdr.return_code = cmd->data.setassparms.hdr.return_code; + if (cmd->hdr.prot_version == QETH_PROT_IPV4) + card->options.ipa4.enabled_funcs = cmd->hdr.ipa_enabled; + if (cmd->hdr.prot_version == QETH_PROT_IPV6) + card->options.ipa6.enabled_funcs = cmd->hdr.ipa_enabled; return 0; } EXPORT_SYMBOL_GPL(qeth_setassparms_cb); @@ -5650,7 +5601,10 @@ static struct net_device *qeth_alloc_netdev(struct qeth_card *card) SET_NETDEV_DEV(dev, &card->gdev->dev); netif_carrier_off(dev); - if (!IS_OSN(card)) { + if (IS_OSN(card)) { + dev->ethtool_ops = &qeth_osn_ethtool_ops; + } else { + dev->ethtool_ops = &qeth_ethtool_ops; dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->hw_features |= NETIF_F_SG; dev->vlan_features |= NETIF_F_SG; @@ -5896,9 +5850,6 @@ int qeth_do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) if (!card) return -ENODEV; - if (card->info.type == QETH_CARD_TYPE_OSN) - return -EPERM; - switch (cmd) { case SIOC_QETH_ADP_SET_SNMP_CONTROL: rc = qeth_snmp_command(card, rq->ifr_ifru.ifru_data); @@ -5938,452 +5889,91 @@ int qeth_do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) } EXPORT_SYMBOL_GPL(qeth_do_ioctl); -static struct { - const char str[ETH_GSTRING_LEN]; -} qeth_ethtool_stats_keys[] = { -/* 0 */{"rx skbs"}, - {"rx buffers"}, - {"tx skbs"}, - {"tx buffers"}, - {"tx skbs no packing"}, - {"tx buffers no packing"}, - {"tx skbs packing"}, - {"tx buffers packing"}, - {"tx sg skbs"}, - {"tx buffer elements"}, -/* 10 */{"rx sg skbs"}, - {"rx sg frags"}, - {"rx sg page allocs"}, - {"tx large kbytes"}, - {"tx large count"}, - {"tx pk state ch n->p"}, - {"tx pk state ch p->n"}, - {"tx pk watermark low"}, - {"tx pk watermark high"}, - {"queue 0 buffer usage"}, -/* 20 */{"queue 1 buffer usage"}, - {"queue 2 buffer usage"}, - {"queue 3 buffer usage"}, - {"rx poll time"}, - {"rx poll count"}, - {"rx do_QDIO time"}, - {"rx do_QDIO count"}, - {"tx handler time"}, - {"tx handler count"}, - {"tx time"}, -/* 30 */{"tx count"}, - {"tx do_QDIO time"}, - {"tx do_QDIO count"}, - {"tx csum"}, - {"tx lin"}, - {"tx linfail"}, - {"cq handler count"}, - {"cq handler time"}, - {"rx csum"} -}; - -int qeth_core_get_sset_count(struct net_device *dev, int stringset) -{ - switch (stringset) { - case ETH_SS_STATS: - return (sizeof(qeth_ethtool_stats_keys) / ETH_GSTRING_LEN); - default: - return -EINVAL; - } -} -EXPORT_SYMBOL_GPL(qeth_core_get_sset_count); - -void qeth_core_get_ethtool_stats(struct net_device *dev, - struct ethtool_stats *stats, u64 *data) -{ - struct qeth_card *card = dev->ml_priv; - data[0] = card->stats.rx_packets - - card->perf_stats.initial_rx_packets; - data[1] = card->perf_stats.bufs_rec; - data[2] = card->stats.tx_packets - - card->perf_stats.initial_tx_packets; - data[3] = card->perf_stats.bufs_sent; - data[4] = card->stats.tx_packets - card->perf_stats.initial_tx_packets - - card->perf_stats.skbs_sent_pack; - data[5] = card->perf_stats.bufs_sent - card->perf_stats.bufs_sent_pack; - data[6] = card->perf_stats.skbs_sent_pack; - data[7] = card->perf_stats.bufs_sent_pack; - data[8] = card->perf_stats.sg_skbs_sent; - data[9] = card->perf_stats.buf_elements_sent; - data[10] = card->perf_stats.sg_skbs_rx; - data[11] = card->perf_stats.sg_frags_rx; - data[12] = card->perf_stats.sg_alloc_page_rx; - data[13] = (card->perf_stats.large_send_bytes >> 10); - data[14] = card->perf_stats.large_send_cnt; - data[15] = card->perf_stats.sc_dp_p; - data[16] = card->perf_stats.sc_p_dp; - data[17] = QETH_LOW_WATERMARK_PACK; - data[18] = QETH_HIGH_WATERMARK_PACK; - data[19] = atomic_read(&card->qdio.out_qs[0]->used_buffers); - data[20] = (card->qdio.no_out_queues > 1) ? - atomic_read(&card->qdio.out_qs[1]->used_buffers) : 0; - data[21] = (card->qdio.no_out_queues > 2) ? - atomic_read(&card->qdio.out_qs[2]->used_buffers) : 0; - data[22] = (card->qdio.no_out_queues > 3) ? - atomic_read(&card->qdio.out_qs[3]->used_buffers) : 0; - data[23] = card->perf_stats.inbound_time; - data[24] = card->perf_stats.inbound_cnt; - data[25] = card->perf_stats.inbound_do_qdio_time; - data[26] = card->perf_stats.inbound_do_qdio_cnt; - data[27] = card->perf_stats.outbound_handler_time; - data[28] = card->perf_stats.outbound_handler_cnt; - data[29] = card->perf_stats.outbound_time; - data[30] = card->perf_stats.outbound_cnt; - data[31] = card->perf_stats.outbound_do_qdio_time; - data[32] = card->perf_stats.outbound_do_qdio_cnt; - data[33] = card->perf_stats.tx_csum; - data[34] = card->perf_stats.tx_lin; - data[35] = card->perf_stats.tx_linfail; - data[36] = card->perf_stats.cq_cnt; - data[37] = card->perf_stats.cq_time; - data[38] = card->perf_stats.rx_csum; -} -EXPORT_SYMBOL_GPL(qeth_core_get_ethtool_stats); - -void qeth_core_get_strings(struct net_device *dev, u32 stringset, u8 *data) -{ - switch (stringset) { - case ETH_SS_STATS: - memcpy(data, &qeth_ethtool_stats_keys, - sizeof(qeth_ethtool_stats_keys)); - break; - default: - WARN_ON(1); - break; - } -} -EXPORT_SYMBOL_GPL(qeth_core_get_strings); - -void qeth_core_get_drvinfo(struct net_device *dev, - struct ethtool_drvinfo *info) -{ - struct qeth_card *card = dev->ml_priv; - - strlcpy(info->driver, IS_LAYER2(card) ? "qeth_l2" : "qeth_l3", - sizeof(info->driver)); - strlcpy(info->version, "1.0", sizeof(info->version)); - strlcpy(info->fw_version, card->info.mcl_level, - sizeof(info->fw_version)); - snprintf(info->bus_info, sizeof(info->bus_info), "%s/%s/%s", - CARD_RDEV_ID(card), CARD_WDEV_ID(card), CARD_DDEV_ID(card)); -} -EXPORT_SYMBOL_GPL(qeth_core_get_drvinfo); - -/* Helper function to fill 'advertising' and 'supported' which are the same. */ -/* Autoneg and full-duplex are supported and advertised unconditionally. */ -/* Always advertise and support all speeds up to specified, and only one */ -/* specified port type. */ -static void qeth_set_cmd_adv_sup(struct ethtool_link_ksettings *cmd, - int maxspeed, int porttype) -{ - ethtool_link_ksettings_zero_link_mode(cmd, supported); - ethtool_link_ksettings_zero_link_mode(cmd, advertising); - ethtool_link_ksettings_zero_link_mode(cmd, lp_advertising); - - ethtool_link_ksettings_add_link_mode(cmd, supported, Autoneg); - ethtool_link_ksettings_add_link_mode(cmd, advertising, Autoneg); - - switch (porttype) { - case PORT_TP: - ethtool_link_ksettings_add_link_mode(cmd, supported, TP); - ethtool_link_ksettings_add_link_mode(cmd, advertising, TP); - break; - case PORT_FIBRE: - ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE); - ethtool_link_ksettings_add_link_mode(cmd, advertising, FIBRE); - break; - default: - ethtool_link_ksettings_add_link_mode(cmd, supported, TP); - ethtool_link_ksettings_add_link_mode(cmd, advertising, TP); - WARN_ON_ONCE(1); - } - - /* partially does fall through, to also select lower speeds */ - switch (maxspeed) { - case SPEED_25000: - ethtool_link_ksettings_add_link_mode(cmd, supported, - 25000baseSR_Full); - ethtool_link_ksettings_add_link_mode(cmd, advertising, - 25000baseSR_Full); - break; - case SPEED_10000: - ethtool_link_ksettings_add_link_mode(cmd, supported, - 10000baseT_Full); - ethtool_link_ksettings_add_link_mode(cmd, advertising, - 10000baseT_Full); - case SPEED_1000: - ethtool_link_ksettings_add_link_mode(cmd, supported, - 1000baseT_Full); - ethtool_link_ksettings_add_link_mode(cmd, advertising, - 1000baseT_Full); - ethtool_link_ksettings_add_link_mode(cmd, supported, - 1000baseT_Half); - ethtool_link_ksettings_add_link_mode(cmd, advertising, - 1000baseT_Half); - case SPEED_100: - ethtool_link_ksettings_add_link_mode(cmd, supported, - 100baseT_Full); - ethtool_link_ksettings_add_link_mode(cmd, advertising, - 100baseT_Full); - ethtool_link_ksettings_add_link_mode(cmd, supported, - 100baseT_Half); - ethtool_link_ksettings_add_link_mode(cmd, advertising, - 100baseT_Half); - case SPEED_10: - ethtool_link_ksettings_add_link_mode(cmd, supported, - 10baseT_Full); - ethtool_link_ksettings_add_link_mode(cmd, advertising, - 10baseT_Full); - ethtool_link_ksettings_add_link_mode(cmd, supported, - 10baseT_Half); - ethtool_link_ksettings_add_link_mode(cmd, advertising, - 10baseT_Half); - /* end fallthrough */ - break; - default: - ethtool_link_ksettings_add_link_mode(cmd, supported, - 10baseT_Full); - ethtool_link_ksettings_add_link_mode(cmd, advertising, - 10baseT_Full); - ethtool_link_ksettings_add_link_mode(cmd, supported, - 10baseT_Half); - ethtool_link_ksettings_add_link_mode(cmd, advertising, - 10baseT_Half); - WARN_ON_ONCE(1); - } -} - -int qeth_core_ethtool_get_link_ksettings(struct net_device *netdev, - struct ethtool_link_ksettings *cmd) -{ - struct qeth_card *card = netdev->ml_priv; - enum qeth_link_types link_type; - struct carrier_info carrier_info; - int rc; - - if ((card->info.type == QETH_CARD_TYPE_IQD) || (card->info.guestlan)) - link_type = QETH_LINK_TYPE_10GBIT_ETH; - else - link_type = card->info.link_type; - - cmd->base.duplex = DUPLEX_FULL; - cmd->base.autoneg = AUTONEG_ENABLE; - cmd->base.phy_address = 0; - cmd->base.mdio_support = 0; - cmd->base.eth_tp_mdix = ETH_TP_MDI_INVALID; - cmd->base.eth_tp_mdix_ctrl = ETH_TP_MDI_INVALID; - - switch (link_type) { - case QETH_LINK_TYPE_FAST_ETH: - case QETH_LINK_TYPE_LANE_ETH100: - cmd->base.speed = SPEED_100; - cmd->base.port = PORT_TP; - break; - case QETH_LINK_TYPE_GBIT_ETH: - case QETH_LINK_TYPE_LANE_ETH1000: - cmd->base.speed = SPEED_1000; - cmd->base.port = PORT_FIBRE; - break; - case QETH_LINK_TYPE_10GBIT_ETH: - cmd->base.speed = SPEED_10000; - cmd->base.port = PORT_FIBRE; - break; - case QETH_LINK_TYPE_25GBIT_ETH: - cmd->base.speed = SPEED_25000; - cmd->base.port = PORT_FIBRE; - break; - default: - cmd->base.speed = SPEED_10; - cmd->base.port = PORT_TP; - } - qeth_set_cmd_adv_sup(cmd, cmd->base.speed, cmd->base.port); - - /* Check if we can obtain more accurate information. */ - /* If QUERY_CARD_INFO command is not supported or fails, */ - /* just return the heuristics that was filled above. */ - rc = qeth_query_card_info(card, &carrier_info); - if (rc == -EOPNOTSUPP) /* for old hardware, return heuristic */ - return 0; - if (rc) /* report error from the hardware operation */ - return rc; - /* on success, fill in the information got from the hardware */ - - netdev_dbg(netdev, - "card info: card_type=0x%02x, port_mode=0x%04x, port_speed=0x%08x\n", - carrier_info.card_type, - carrier_info.port_mode, - carrier_info.port_speed); - - /* Update attributes for which we've obtained more authoritative */ - /* information, leave the rest the way they where filled above. */ - switch (carrier_info.card_type) { - case CARD_INFO_TYPE_1G_COPPER_A: - case CARD_INFO_TYPE_1G_COPPER_B: - cmd->base.port = PORT_TP; - qeth_set_cmd_adv_sup(cmd, SPEED_1000, cmd->base.port); - break; - case CARD_INFO_TYPE_1G_FIBRE_A: - case CARD_INFO_TYPE_1G_FIBRE_B: - cmd->base.port = PORT_FIBRE; - qeth_set_cmd_adv_sup(cmd, SPEED_1000, cmd->base.port); - break; - case CARD_INFO_TYPE_10G_FIBRE_A: - case CARD_INFO_TYPE_10G_FIBRE_B: - cmd->base.port = PORT_FIBRE; - qeth_set_cmd_adv_sup(cmd, SPEED_10000, cmd->base.port); - break; - } - - switch (carrier_info.port_mode) { - case CARD_INFO_PORTM_FULLDUPLEX: - cmd->base.duplex = DUPLEX_FULL; - break; - case CARD_INFO_PORTM_HALFDUPLEX: - cmd->base.duplex = DUPLEX_HALF; - break; - } - - switch (carrier_info.port_speed) { - case CARD_INFO_PORTS_10M: - cmd->base.speed = SPEED_10; - break; - case CARD_INFO_PORTS_100M: - cmd->base.speed = SPEED_100; - break; - case CARD_INFO_PORTS_1G: - cmd->base.speed = SPEED_1000; - break; - case CARD_INFO_PORTS_10G: - cmd->base.speed = SPEED_10000; - break; - case CARD_INFO_PORTS_25G: - cmd->base.speed = SPEED_25000; - break; - } - - return 0; -} -EXPORT_SYMBOL_GPL(qeth_core_ethtool_get_link_ksettings); - -/* Callback to handle checksum offload command reply from OSA card. - * Verify that required features have been enabled on the card. - * Return error in hdr->return_code as this value is checked by caller. - * - * Always returns zero to indicate no further messages from the OSA card. - */ -static int qeth_ipa_checksum_run_cmd_cb(struct qeth_card *card, - struct qeth_reply *reply, - unsigned long data) +static int qeth_start_csum_cb(struct qeth_card *card, struct qeth_reply *reply, + unsigned long data) { struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data; - struct qeth_checksum_cmd *chksum_cb = - (struct qeth_checksum_cmd *)reply->param; + u32 *features = reply->param; - QETH_CARD_TEXT(card, 4, "chkdoccb"); if (qeth_setassparms_inspect_rc(cmd)) - return 0; + return -EIO; - memset(chksum_cb, 0, sizeof(*chksum_cb)); - if (cmd->data.setassparms.hdr.command_code == IPA_CMD_ASS_START) { - chksum_cb->supported = - cmd->data.setassparms.data.chksum.supported; - QETH_CARD_TEXT_(card, 3, "strt:%x", chksum_cb->supported); - } - if (cmd->data.setassparms.hdr.command_code == IPA_CMD_ASS_ENABLE) { - chksum_cb->supported = - cmd->data.setassparms.data.chksum.supported; - chksum_cb->enabled = - cmd->data.setassparms.data.chksum.enabled; - QETH_CARD_TEXT_(card, 3, "supp:%x", chksum_cb->supported); - QETH_CARD_TEXT_(card, 3, "enab:%x", chksum_cb->enabled); - } + *features = cmd->data.setassparms.data.flags_32bit; return 0; } -/* Send command to OSA card and check results. */ -static int qeth_ipa_checksum_run_cmd(struct qeth_card *card, - enum qeth_ipa_funcs ipa_func, - __u16 cmd_code, long data, - struct qeth_checksum_cmd *chksum_cb, - enum qeth_prot_versions prot) +static int qeth_set_csum_off(struct qeth_card *card, enum qeth_ipa_funcs cstype, + enum qeth_prot_versions prot) { - struct qeth_cmd_buffer *iob; - - QETH_CARD_TEXT(card, 4, "chkdocmd"); - iob = qeth_get_setassparms_cmd(card, ipa_func, cmd_code, - sizeof(__u32), prot); - if (!iob) - return -ENOMEM; - - __ipa_cmd(iob)->data.setassparms.data.flags_32bit = (__u32) data; - return qeth_send_ipa_cmd(card, iob, qeth_ipa_checksum_run_cmd_cb, - chksum_cb); + return qeth_send_simple_setassparms_prot(card, cstype, + IPA_CMD_ASS_STOP, 0, prot); } -static int qeth_send_checksum_on(struct qeth_card *card, int cstype, - enum qeth_prot_versions prot) +static int qeth_set_csum_on(struct qeth_card *card, enum qeth_ipa_funcs cstype, + enum qeth_prot_versions prot) { u32 required_features = QETH_IPA_CHECKSUM_UDP | QETH_IPA_CHECKSUM_TCP; - struct qeth_checksum_cmd chksum_cb; + struct qeth_cmd_buffer *iob; + struct qeth_ipa_caps caps; + u32 features; int rc; - if (prot == QETH_PROT_IPV4) + /* some L3 HW requires combined L3+L4 csum offload: */ + if (IS_LAYER3(card) && prot == QETH_PROT_IPV4 && + cstype == IPA_OUTBOUND_CHECKSUM) required_features |= QETH_IPA_CHECKSUM_IP_HDR; - rc = qeth_ipa_checksum_run_cmd(card, cstype, IPA_CMD_ASS_START, 0, - &chksum_cb, prot); - if (!rc) { - if ((required_features & chksum_cb.supported) != - required_features) - rc = -EIO; - else if (!(QETH_IPA_CHECKSUM_LP2LP & chksum_cb.supported) && - cstype == IPA_INBOUND_CHECKSUM) - dev_warn(&card->gdev->dev, - "Hardware checksumming is performed only if %s and its peer use different OSA Express 3 ports\n", - QETH_CARD_IFNAME(card)); - } - if (rc) { - qeth_send_simple_setassparms_prot(card, cstype, - IPA_CMD_ASS_STOP, 0, prot); - dev_warn(&card->gdev->dev, - "Starting HW IPv%d checksumming for %s failed, using SW checksumming\n", - prot, QETH_CARD_IFNAME(card)); + + iob = qeth_get_setassparms_cmd(card, cstype, IPA_CMD_ASS_START, 0, + prot); + if (!iob) + return -ENOMEM; + + rc = qeth_send_ipa_cmd(card, iob, qeth_start_csum_cb, &features); + if (rc) return rc; + + if ((required_features & features) != required_features) { + qeth_set_csum_off(card, cstype, prot); + return -EOPNOTSUPP; } - rc = qeth_ipa_checksum_run_cmd(card, cstype, IPA_CMD_ASS_ENABLE, - chksum_cb.supported, &chksum_cb, + + iob = qeth_get_setassparms_cmd(card, cstype, IPA_CMD_ASS_ENABLE, 4, prot); - if (!rc) { - if ((required_features & chksum_cb.enabled) != - required_features) - rc = -EIO; + if (!iob) { + qeth_set_csum_off(card, cstype, prot); + return -ENOMEM; } + + if (features & QETH_IPA_CHECKSUM_LP2LP) + required_features |= QETH_IPA_CHECKSUM_LP2LP; + __ipa_cmd(iob)->data.setassparms.data.flags_32bit = required_features; + rc = qeth_send_ipa_cmd(card, iob, qeth_setassparms_get_caps_cb, &caps); if (rc) { - qeth_send_simple_setassparms_prot(card, cstype, - IPA_CMD_ASS_STOP, 0, prot); - dev_warn(&card->gdev->dev, - "Enabling HW IPv%d checksumming for %s failed, using SW checksumming\n", - prot, QETH_CARD_IFNAME(card)); + qeth_set_csum_off(card, cstype, prot); return rc; } + if (!qeth_ipa_caps_supported(&caps, required_features) || + !qeth_ipa_caps_enabled(&caps, required_features)) { + qeth_set_csum_off(card, cstype, prot); + return -EOPNOTSUPP; + } + dev_info(&card->gdev->dev, "HW Checksumming (%sbound IPv%d) enabled\n", cstype == IPA_INBOUND_CHECKSUM ? "in" : "out", prot); + if (!qeth_ipa_caps_enabled(&caps, QETH_IPA_CHECKSUM_LP2LP) && + cstype == IPA_OUTBOUND_CHECKSUM) + dev_warn(&card->gdev->dev, + "Hardware checksumming is performed only if %s and its peer use different OSA Express 3 ports\n", + QETH_CARD_IFNAME(card)); return 0; } static int qeth_set_ipa_csum(struct qeth_card *card, bool on, int cstype, enum qeth_prot_versions prot) { - int rc = (on) ? qeth_send_checksum_on(card, cstype, prot) - : qeth_send_simple_setassparms_prot(card, cstype, - IPA_CMD_ASS_STOP, 0, - prot); - return rc ? -EIO : 0; + return on ? qeth_set_csum_on(card, cstype, prot) : + qeth_set_csum_off(card, cstype, prot); } static int qeth_start_tso_cb(struct qeth_card *card, struct qeth_reply *reply, @@ -6393,7 +5983,7 @@ static int qeth_start_tso_cb(struct qeth_card *card, struct qeth_reply *reply, struct qeth_tso_start_data *tso_data = reply->param; if (qeth_setassparms_inspect_rc(cmd)) - return 0; + return -EIO; tso_data->mss = cmd->data.setassparms.data.tso.mss; tso_data->supported = cmd->data.setassparms.data.tso.supported; @@ -6459,10 +6049,7 @@ static int qeth_set_tso_on(struct qeth_card *card, static int qeth_set_ipa_tso(struct qeth_card *card, bool on, enum qeth_prot_versions prot) { - int rc = on ? qeth_set_tso_on(card, prot) : - qeth_set_tso_off(card, prot); - - return rc ? -EIO : 0; + return on ? qeth_set_tso_on(card, prot) : qeth_set_tso_off(card, prot); } static int qeth_set_ipa_rx_csum(struct qeth_card *card, bool on) @@ -6611,6 +6198,33 @@ netdev_features_t qeth_features_check(struct sk_buff *skb, } EXPORT_SYMBOL_GPL(qeth_features_check); +void qeth_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) +{ + struct qeth_card *card = dev->ml_priv; + struct qeth_qdio_out_q *queue; + unsigned int i; + + QETH_CARD_TEXT(card, 5, "getstat"); + + stats->rx_packets = card->stats.rx_packets; + stats->rx_bytes = card->stats.rx_bytes; + stats->rx_errors = card->stats.rx_errors; + stats->rx_dropped = card->stats.rx_dropped; + stats->multicast = card->stats.rx_multicast; + stats->tx_errors = card->stats.tx_errors; + + for (i = 0; i < card->qdio.no_out_queues; i++) { + queue = card->qdio.out_qs[i]; + + stats->tx_packets += queue->stats.tx_packets; + stats->tx_bytes += queue->stats.tx_bytes; + stats->tx_errors += queue->stats.tx_errors; + stats->tx_dropped += queue->stats.tx_dropped; + stats->tx_carrier_errors += queue->stats.tx_carrier_errors; + } +} +EXPORT_SYMBOL_GPL(qeth_get_stats64); + int qeth_open(struct net_device *dev) { struct qeth_card *card = dev->ml_priv; diff --git a/drivers/s390/net/qeth_core_mpc.c b/drivers/s390/net/qeth_core_mpc.c index 16fc51ad0514..e3f4866c158e 100644 --- a/drivers/s390/net/qeth_core_mpc.c +++ b/drivers/s390/net/qeth_core_mpc.c @@ -125,24 +125,13 @@ unsigned char DM_ACT[] = { unsigned char IPA_PDU_HEADER[] = { 0x00, 0xe0, 0x00, 0x00, 0x77, 0x77, 0x77, 0x77, - 0x00, 0x00, 0x00, 0x14, 0x00, 0x00, - (IPA_PDU_HEADER_SIZE+sizeof(struct qeth_ipa_cmd)) / 256, - (IPA_PDU_HEADER_SIZE+sizeof(struct qeth_ipa_cmd)) % 256, + 0x00, 0x00, 0x00, 0x14, 0x00, 0x00, 0x00, 0x00, 0x10, 0x00, 0x00, 0x01, 0x00, 0x00, 0x00, 0x00, 0xc1, 0x03, 0x00, 0x01, 0x00, 0x00, 0x00, 0x00, - 0x00, 0x00, 0x00, 0x00, 0x00, 0x24, - sizeof(struct qeth_ipa_cmd) / 256, - sizeof(struct qeth_ipa_cmd) % 256, - 0x00, - sizeof(struct qeth_ipa_cmd) / 256, - sizeof(struct qeth_ipa_cmd) % 256, - 0x05, - 0x77, 0x77, 0x77, 0x77, + 0x00, 0x00, 0x00, 0x00, 0x00, 0x24, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x05, 0x77, 0x77, 0x77, 0x77, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, - 0x01, 0x00, - sizeof(struct qeth_ipa_cmd) / 256, - sizeof(struct qeth_ipa_cmd) % 256, - 0x00, 0x00, 0x00, 0x40, + 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x40, }; struct ipa_rc_msg { @@ -212,12 +201,10 @@ static const struct ipa_rc_msg qeth_ipa_rc_msg[] = { {IPA_RC_LAN_OFFLINE, "STRTLAN_LAN_DISABLED - LAN offline"}, {IPA_RC_VEPA_TO_VEB_TRANSITION, "Adj. switch disabled port mode RR"}, {IPA_RC_INVALID_IP_VERSION2, "Invalid IP version"}, - {IPA_RC_ENOMEM, "Memory problem"}, + /* default for qeth_get_ipa_msg(): */ {IPA_RC_FFFF, "Unknown Error"} }; - - const char *qeth_get_ipa_msg(enum qeth_ipa_return_codes rc) { int x; diff --git a/drivers/s390/net/qeth_core_mpc.h b/drivers/s390/net/qeth_core_mpc.h index c7fb14a61eed..f8c5d4a9be13 100644 --- a/drivers/s390/net/qeth_core_mpc.h +++ b/drivers/s390/net/qeth_core_mpc.h @@ -21,8 +21,6 @@ extern unsigned char IPA_PDU_HEADER[]; #define QETH_IPA_CMD_DEST_ADDR(buffer) (buffer + 0x2c) -#define IPA_CMD_LENGTH (IPA_PDU_HEADER_SIZE + sizeof(struct qeth_ipa_cmd)) - #define QETH_SEQ_NO_LENGTH 4 #define QETH_MPC_TOKEN_LENGTH 4 #define QETH_MCL_LENGTH 4 @@ -83,6 +81,7 @@ enum qeth_card_types { #define IS_OSD(card) ((card)->info.type == QETH_CARD_TYPE_OSD) #define IS_OSM(card) ((card)->info.type == QETH_CARD_TYPE_OSM) #define IS_OSN(card) ((card)->info.type == QETH_CARD_TYPE_OSN) +#define IS_OSX(card) ((card)->info.type == QETH_CARD_TYPE_OSX) #define IS_VM_NIC(card) ((card)->info.guestlan) #define QETH_MPC_DIFINFO_LEN_INDICATES_LINK_TYPE 0x18 @@ -231,7 +230,6 @@ enum qeth_ipa_return_codes { IPA_RC_LAN_OFFLINE = 0xe080, IPA_RC_VEPA_TO_VEB_TRANSITION = 0xe090, IPA_RC_INVALID_IP_VERSION2 = 0xf001, - IPA_RC_ENOMEM = 0xfffe, IPA_RC_FFFF = 0xffff }; /* for VNIC Characteristics */ @@ -419,12 +417,6 @@ enum qeth_ipa_checksum_bits { QETH_IPA_CHECKSUM_LP2LP = 0x0020 }; -/* IPA Assist checksum offload reply layout. */ -struct qeth_checksum_cmd { - __u32 supported; - __u32 enabled; -} __packed; - enum qeth_ipa_large_send_caps { QETH_IPA_LARGE_SEND_TCP = 0x00000001, }; @@ -440,7 +432,6 @@ struct qeth_ipacmd_setassparms { union { __u32 flags_32bit; struct qeth_ipa_caps caps; - struct qeth_checksum_cmd chksum; struct qeth_arp_cache_entry arp_entry; struct qeth_arp_query_data query_arp; struct qeth_tso_start_data tso; @@ -834,15 +825,10 @@ enum qeth_ipa_arp_return_codes { extern const char *qeth_get_ipa_msg(enum qeth_ipa_return_codes rc); extern const char *qeth_get_ipa_cmd_name(enum qeth_ipa_cmds cmd); -#define QETH_SETASS_BASE_LEN (IPA_PDU_HEADER_SIZE + \ - sizeof(struct qeth_ipacmd_hdr) + \ - sizeof(struct qeth_ipacmd_setassparms_hdr)) #define QETH_SETADP_BASE_LEN (sizeof(struct qeth_ipacmd_hdr) + \ sizeof(struct qeth_ipacmd_setadpparms_hdr)) #define QETH_SNMP_SETADP_CMDLENGTH 16 -#define QETH_ARP_DATA_SIZE 3968 -#define QETH_ARP_CMD_LEN (QETH_ARP_DATA_SIZE + 8) /* Helper functions */ #define IS_IPA_REPLY(cmd) ((cmd->hdr.initiator == IPA_CMD_INITIATOR_HOST) || \ (cmd->hdr.initiator == IPA_CMD_INITIATOR_OSA_REPLY)) diff --git a/drivers/s390/net/qeth_core_sys.c b/drivers/s390/net/qeth_core_sys.c index 30f61608fa22..8b223cc2c19b 100644 --- a/drivers/s390/net/qeth_core_sys.c +++ b/drivers/s390/net/qeth_core_sys.c @@ -316,7 +316,7 @@ static ssize_t qeth_dev_recover_store(struct device *dev, if (!card) return -EINVAL; - if (card->state != CARD_STATE_UP) + if (!qeth_card_hw_is_reachable(card)) return -EPERM; i = simple_strtoul(buf, &tmp, 16); @@ -336,35 +336,36 @@ static ssize_t qeth_dev_performance_stats_show(struct device *dev, if (!card) return -EINVAL; - return sprintf(buf, "%i\n", card->options.performance_stats ? 1:0); + return sprintf(buf, "1\n"); } static ssize_t qeth_dev_performance_stats_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct qeth_card *card = dev_get_drvdata(dev); - char *tmp; - int i, rc = 0; + struct qeth_qdio_out_q *queue; + unsigned int i; + bool reset; + int rc; if (!card) return -EINVAL; - mutex_lock(&card->conf_mutex); - i = simple_strtoul(buf, &tmp, 16); - if ((i == 0) || (i == 1)) { - if (i == card->options.performance_stats) - goto out; - card->options.performance_stats = i; - if (i == 0) - memset(&card->perf_stats, 0, - sizeof(struct qeth_perf_stats)); - card->perf_stats.initial_rx_packets = card->stats.rx_packets; - card->perf_stats.initial_tx_packets = card->stats.tx_packets; - } else - rc = -EINVAL; -out: - mutex_unlock(&card->conf_mutex); - return rc ? rc : count; + rc = kstrtobool(buf, &reset); + if (rc) + return rc; + + if (reset) { + memset(&card->stats, 0, sizeof(card->stats)); + for (i = 0; i < card->qdio.no_out_queues; i++) { + queue = card->qdio.out_qs[i]; + if (!queue) + break; + memset(&queue->stats, 0, sizeof(queue->stats)); + } + } + + return count; } static DEVICE_ATTR(performance_stats, 0644, qeth_dev_performance_stats_show, diff --git a/drivers/s390/net/qeth_ethtool.c b/drivers/s390/net/qeth_ethtool.c new file mode 100644 index 000000000000..93a53fed4cf8 --- /dev/null +++ b/drivers/s390/net/qeth_ethtool.c @@ -0,0 +1,370 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright IBM Corp. 2018 + */ + +#define KMSG_COMPONENT "qeth" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + +#include <linux/ethtool.h> +#include "qeth_core.h" + + +#define QETH_TXQ_STAT(_name, _stat) { \ + .name = _name, \ + .offset = offsetof(struct qeth_out_q_stats, _stat) \ +} + +#define QETH_CARD_STAT(_name, _stat) { \ + .name = _name, \ + .offset = offsetof(struct qeth_card_stats, _stat) \ +} + +struct qeth_stats { + char name[ETH_GSTRING_LEN]; + unsigned int offset; +}; + +static const struct qeth_stats txq_stats[] = { + QETH_TXQ_STAT("IO buffers", bufs), + QETH_TXQ_STAT("IO buffer elements", buf_elements), + QETH_TXQ_STAT("packed IO buffers", bufs_pack), + QETH_TXQ_STAT("skbs", tx_packets), + QETH_TXQ_STAT("packed skbs", skbs_pack), + QETH_TXQ_STAT("SG skbs", skbs_sg), + QETH_TXQ_STAT("HW csum skbs", skbs_csum), + QETH_TXQ_STAT("TSO skbs", skbs_tso), + QETH_TXQ_STAT("linearized skbs", skbs_linearized), + QETH_TXQ_STAT("linearized+error skbs", skbs_linearized_fail), + QETH_TXQ_STAT("TSO bytes", tso_bytes), + QETH_TXQ_STAT("Packing mode switches", packing_mode_switch), +}; + +static const struct qeth_stats card_stats[] = { + QETH_CARD_STAT("rx0 IO buffers", rx_bufs), + QETH_CARD_STAT("rx0 HW csum skbs", rx_skb_csum), + QETH_CARD_STAT("rx0 SG skbs", rx_sg_skbs), + QETH_CARD_STAT("rx0 SG page frags", rx_sg_frags), + QETH_CARD_STAT("rx0 SG page allocs", rx_sg_alloc_page), +}; + +#define TXQ_STATS_LEN ARRAY_SIZE(txq_stats) +#define CARD_STATS_LEN ARRAY_SIZE(card_stats) + +static void qeth_add_stat_data(u64 **dst, void *src, + const struct qeth_stats stats[], + unsigned int size) +{ + unsigned int i; + char *stat; + + for (i = 0; i < size; i++) { + stat = (char *)src + stats[i].offset; + **dst = *(u64 *)stat; + (*dst)++; + } +} + +static void qeth_add_stat_strings(u8 **data, const char *prefix, + const struct qeth_stats stats[], + unsigned int size) +{ + unsigned int i; + + for (i = 0; i < size; i++) { + snprintf(*data, ETH_GSTRING_LEN, "%s%s", prefix, stats[i].name); + *data += ETH_GSTRING_LEN; + } +} + +static int qeth_get_sset_count(struct net_device *dev, int stringset) +{ + struct qeth_card *card = dev->ml_priv; + + switch (stringset) { + case ETH_SS_STATS: + return CARD_STATS_LEN + + card->qdio.no_out_queues * TXQ_STATS_LEN; + default: + return -EINVAL; + } +} + +static void qeth_get_ethtool_stats(struct net_device *dev, + struct ethtool_stats *stats, u64 *data) +{ + struct qeth_card *card = dev->ml_priv; + unsigned int i; + + qeth_add_stat_data(&data, &card->stats, card_stats, CARD_STATS_LEN); + for (i = 0; i < card->qdio.no_out_queues; i++) + qeth_add_stat_data(&data, &card->qdio.out_qs[i]->stats, + txq_stats, TXQ_STATS_LEN); +} + +static void qeth_get_ringparam(struct net_device *dev, + struct ethtool_ringparam *param) +{ + struct qeth_card *card = dev->ml_priv; + + param->rx_max_pending = QDIO_MAX_BUFFERS_PER_Q; + param->rx_mini_max_pending = 0; + param->rx_jumbo_max_pending = 0; + param->tx_max_pending = QDIO_MAX_BUFFERS_PER_Q; + + param->rx_pending = card->qdio.in_buf_pool.buf_count; + param->rx_mini_pending = 0; + param->rx_jumbo_pending = 0; + param->tx_pending = QDIO_MAX_BUFFERS_PER_Q; +} + +static void qeth_get_strings(struct net_device *dev, u32 stringset, u8 *data) +{ + struct qeth_card *card = dev->ml_priv; + char prefix[ETH_GSTRING_LEN] = ""; + unsigned int i; + + switch (stringset) { + case ETH_SS_STATS: + qeth_add_stat_strings(&data, prefix, card_stats, + CARD_STATS_LEN); + for (i = 0; i < card->qdio.no_out_queues; i++) { + snprintf(prefix, ETH_GSTRING_LEN, "tx%u ", i); + qeth_add_stat_strings(&data, prefix, txq_stats, + TXQ_STATS_LEN); + } + break; + default: + WARN_ON(1); + break; + } +} + +static void qeth_get_drvinfo(struct net_device *dev, + struct ethtool_drvinfo *info) +{ + struct qeth_card *card = dev->ml_priv; + + strlcpy(info->driver, IS_LAYER2(card) ? "qeth_l2" : "qeth_l3", + sizeof(info->driver)); + strlcpy(info->version, "1.0", sizeof(info->version)); + strlcpy(info->fw_version, card->info.mcl_level, + sizeof(info->fw_version)); + snprintf(info->bus_info, sizeof(info->bus_info), "%s/%s/%s", + CARD_RDEV_ID(card), CARD_WDEV_ID(card), CARD_DDEV_ID(card)); +} + +/* Helper function to fill 'advertising' and 'supported' which are the same. */ +/* Autoneg and full-duplex are supported and advertised unconditionally. */ +/* Always advertise and support all speeds up to specified, and only one */ +/* specified port type. */ +static void qeth_set_cmd_adv_sup(struct ethtool_link_ksettings *cmd, + int maxspeed, int porttype) +{ + ethtool_link_ksettings_zero_link_mode(cmd, supported); + ethtool_link_ksettings_zero_link_mode(cmd, advertising); + ethtool_link_ksettings_zero_link_mode(cmd, lp_advertising); + + ethtool_link_ksettings_add_link_mode(cmd, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(cmd, advertising, Autoneg); + + switch (porttype) { + case PORT_TP: + ethtool_link_ksettings_add_link_mode(cmd, supported, TP); + ethtool_link_ksettings_add_link_mode(cmd, advertising, TP); + break; + case PORT_FIBRE: + ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE); + ethtool_link_ksettings_add_link_mode(cmd, advertising, FIBRE); + break; + default: + ethtool_link_ksettings_add_link_mode(cmd, supported, TP); + ethtool_link_ksettings_add_link_mode(cmd, advertising, TP); + WARN_ON_ONCE(1); + } + + /* partially does fall through, to also select lower speeds */ + switch (maxspeed) { + case SPEED_25000: + ethtool_link_ksettings_add_link_mode(cmd, supported, + 25000baseSR_Full); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + 25000baseSR_Full); + break; + case SPEED_10000: + ethtool_link_ksettings_add_link_mode(cmd, supported, + 10000baseT_Full); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + 10000baseT_Full); + /* fall through */ + case SPEED_1000: + ethtool_link_ksettings_add_link_mode(cmd, supported, + 1000baseT_Full); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + 1000baseT_Full); + ethtool_link_ksettings_add_link_mode(cmd, supported, + 1000baseT_Half); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + 1000baseT_Half); + /* fall through */ + case SPEED_100: + ethtool_link_ksettings_add_link_mode(cmd, supported, + 100baseT_Full); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + 100baseT_Full); + ethtool_link_ksettings_add_link_mode(cmd, supported, + 100baseT_Half); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + 100baseT_Half); + /* fall through */ + case SPEED_10: + ethtool_link_ksettings_add_link_mode(cmd, supported, + 10baseT_Full); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + 10baseT_Full); + ethtool_link_ksettings_add_link_mode(cmd, supported, + 10baseT_Half); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + 10baseT_Half); + break; + default: + ethtool_link_ksettings_add_link_mode(cmd, supported, + 10baseT_Full); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + 10baseT_Full); + ethtool_link_ksettings_add_link_mode(cmd, supported, + 10baseT_Half); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + 10baseT_Half); + WARN_ON_ONCE(1); + } +} + + +static int qeth_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) +{ + struct qeth_card *card = netdev->ml_priv; + enum qeth_link_types link_type; + struct carrier_info carrier_info; + int rc; + + if (IS_IQD(card) || IS_VM_NIC(card)) + link_type = QETH_LINK_TYPE_10GBIT_ETH; + else + link_type = card->info.link_type; + + cmd->base.duplex = DUPLEX_FULL; + cmd->base.autoneg = AUTONEG_ENABLE; + cmd->base.phy_address = 0; + cmd->base.mdio_support = 0; + cmd->base.eth_tp_mdix = ETH_TP_MDI_INVALID; + cmd->base.eth_tp_mdix_ctrl = ETH_TP_MDI_INVALID; + + switch (link_type) { + case QETH_LINK_TYPE_FAST_ETH: + case QETH_LINK_TYPE_LANE_ETH100: + cmd->base.speed = SPEED_100; + cmd->base.port = PORT_TP; + break; + case QETH_LINK_TYPE_GBIT_ETH: + case QETH_LINK_TYPE_LANE_ETH1000: + cmd->base.speed = SPEED_1000; + cmd->base.port = PORT_FIBRE; + break; + case QETH_LINK_TYPE_10GBIT_ETH: + cmd->base.speed = SPEED_10000; + cmd->base.port = PORT_FIBRE; + break; + case QETH_LINK_TYPE_25GBIT_ETH: + cmd->base.speed = SPEED_25000; + cmd->base.port = PORT_FIBRE; + break; + default: + cmd->base.speed = SPEED_10; + cmd->base.port = PORT_TP; + } + qeth_set_cmd_adv_sup(cmd, cmd->base.speed, cmd->base.port); + + /* Check if we can obtain more accurate information. */ + /* If QUERY_CARD_INFO command is not supported or fails, */ + /* just return the heuristics that was filled above. */ + rc = qeth_query_card_info(card, &carrier_info); + if (rc == -EOPNOTSUPP) /* for old hardware, return heuristic */ + return 0; + if (rc) /* report error from the hardware operation */ + return rc; + /* on success, fill in the information got from the hardware */ + + netdev_dbg(netdev, + "card info: card_type=0x%02x, port_mode=0x%04x, port_speed=0x%08x\n", + carrier_info.card_type, + carrier_info.port_mode, + carrier_info.port_speed); + + /* Update attributes for which we've obtained more authoritative */ + /* information, leave the rest the way they where filled above. */ + switch (carrier_info.card_type) { + case CARD_INFO_TYPE_1G_COPPER_A: + case CARD_INFO_TYPE_1G_COPPER_B: + cmd->base.port = PORT_TP; + qeth_set_cmd_adv_sup(cmd, SPEED_1000, cmd->base.port); + break; + case CARD_INFO_TYPE_1G_FIBRE_A: + case CARD_INFO_TYPE_1G_FIBRE_B: + cmd->base.port = PORT_FIBRE; + qeth_set_cmd_adv_sup(cmd, SPEED_1000, cmd->base.port); + break; + case CARD_INFO_TYPE_10G_FIBRE_A: + case CARD_INFO_TYPE_10G_FIBRE_B: + cmd->base.port = PORT_FIBRE; + qeth_set_cmd_adv_sup(cmd, SPEED_10000, cmd->base.port); + break; + } + + switch (carrier_info.port_mode) { + case CARD_INFO_PORTM_FULLDUPLEX: + cmd->base.duplex = DUPLEX_FULL; + break; + case CARD_INFO_PORTM_HALFDUPLEX: + cmd->base.duplex = DUPLEX_HALF; + break; + } + + switch (carrier_info.port_speed) { + case CARD_INFO_PORTS_10M: + cmd->base.speed = SPEED_10; + break; + case CARD_INFO_PORTS_100M: + cmd->base.speed = SPEED_100; + break; + case CARD_INFO_PORTS_1G: + cmd->base.speed = SPEED_1000; + break; + case CARD_INFO_PORTS_10G: + cmd->base.speed = SPEED_10000; + break; + case CARD_INFO_PORTS_25G: + cmd->base.speed = SPEED_25000; + break; + } + + return 0; +} + +const struct ethtool_ops qeth_ethtool_ops = { + .get_link = ethtool_op_get_link, + .get_ringparam = qeth_get_ringparam, + .get_strings = qeth_get_strings, + .get_ethtool_stats = qeth_get_ethtool_stats, + .get_sset_count = qeth_get_sset_count, + .get_drvinfo = qeth_get_drvinfo, + .get_link_ksettings = qeth_get_link_ksettings, +}; + +const struct ethtool_ops qeth_osn_ethtool_ops = { + .get_strings = qeth_get_strings, + .get_ethtool_stats = qeth_get_ethtool_stats, + .get_sset_count = qeth_get_sset_count, + .get_drvinfo = qeth_get_drvinfo, +}; diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 82f50cc30b0a..2c9714215775 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -35,7 +35,7 @@ static void qeth_l2_vnicc_init(struct qeth_card *card); static bool qeth_l2_vnicc_recover_timeout(struct qeth_card *card, u32 vnicc, u32 *timeout); -static int qeth_setdelmac_makerc(struct qeth_card *card, int retcode) +static int qeth_l2_setdelmac_makerc(struct qeth_card *card, u16 retcode) { int rc; @@ -62,9 +62,6 @@ static int qeth_setdelmac_makerc(struct qeth_card *card, int retcode) case IPA_RC_L2_MAC_NOT_FOUND: rc = -ENOENT; break; - case -ENOMEM: - rc = -ENOMEM; - break; default: rc = -EIO; break; @@ -72,6 +69,15 @@ static int qeth_setdelmac_makerc(struct qeth_card *card, int retcode) return rc; } +static int qeth_l2_send_setdelmac_cb(struct qeth_card *card, + struct qeth_reply *reply, + unsigned long data) +{ + struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data; + + return qeth_l2_setdelmac_makerc(card, cmd->hdr.return_code); +} + static int qeth_l2_send_setdelmac(struct qeth_card *card, __u8 *mac, enum qeth_ipa_cmds ipacmd) { @@ -85,8 +91,7 @@ static int qeth_l2_send_setdelmac(struct qeth_card *card, __u8 *mac, cmd = __ipa_cmd(iob); cmd->data.setdelmac.mac_length = ETH_ALEN; ether_addr_copy(cmd->data.setdelmac.mac, mac); - return qeth_setdelmac_makerc(card, qeth_send_ipa_cmd(card, iob, - NULL, NULL)); + return qeth_send_ipa_cmd(card, iob, qeth_l2_send_setdelmac_cb, NULL); } static int qeth_l2_send_setmac(struct qeth_card *card, __u8 *mac) @@ -169,9 +174,9 @@ static int qeth_l2_get_cast_type(struct qeth_card *card, struct sk_buff *skb) return RTN_UNICAST; } -static void qeth_l2_fill_header(struct qeth_card *card, struct qeth_hdr *hdr, - struct sk_buff *skb, int ipv, int cast_type, - unsigned int data_len) +static void qeth_l2_fill_header(struct qeth_qdio_out_q *queue, + struct qeth_hdr *hdr, struct sk_buff *skb, + int ipv, int cast_type, unsigned int data_len) { struct vlan_ethhdr *veth = vlan_eth_hdr(skb); @@ -183,8 +188,7 @@ static void qeth_l2_fill_header(struct qeth_card *card, struct qeth_hdr *hdr, hdr->hdr.l2.id = QETH_HEADER_TYPE_LAYER2; if (skb->ip_summed == CHECKSUM_PARTIAL) { qeth_tx_csum(skb, &hdr->hdr.l2.flags[1], ipv); - if (card->options.performance_stats) - card->perf_stats.tx_csum++; + QETH_TXQ_STAT_INC(queue, skbs_csum); } } @@ -205,7 +209,7 @@ static void qeth_l2_fill_header(struct qeth_card *card, struct qeth_hdr *hdr, } } -static int qeth_setdelvlan_makerc(struct qeth_card *card, int retcode) +static int qeth_l2_setdelvlan_makerc(struct qeth_card *card, u16 retcode) { if (retcode) QETH_CARD_TEXT_(card, 2, "err%04x", retcode); @@ -221,8 +225,6 @@ static int qeth_setdelvlan_makerc(struct qeth_card *card, int retcode) return -ENOENT; case IPA_RC_L2_VLAN_ID_NOT_ALLOWED: return -EPERM; - case -ENOMEM: - return -ENOMEM; default: return -EIO; } @@ -240,9 +242,8 @@ static int qeth_l2_send_setdelvlan_cb(struct qeth_card *card, cmd->data.setdelvlan.vlan_id, CARD_DEVID(card), cmd->hdr.return_code); QETH_CARD_TEXT_(card, 2, "L2VL%4x", cmd->hdr.command); - QETH_CARD_TEXT_(card, 2, "err%d", cmd->hdr.return_code); } - return 0; + return qeth_l2_setdelvlan_makerc(card, cmd->hdr.return_code); } static int qeth_l2_send_setdelvlan(struct qeth_card *card, __u16 i, @@ -257,8 +258,7 @@ static int qeth_l2_send_setdelvlan(struct qeth_card *card, __u16 i, return -ENOMEM; cmd = __ipa_cmd(iob); cmd->data.setdelvlan.vlan_id = i; - return qeth_setdelvlan_makerc(card, qeth_send_ipa_cmd(card, iob, - qeth_l2_send_setdelvlan_cb, NULL)); + return qeth_send_ipa_cmd(card, iob, qeth_l2_send_setdelvlan_cb, NULL); } static int qeth_l2_vlan_rx_add_vid(struct net_device *dev, @@ -319,6 +319,8 @@ static void qeth_l2_stop_card(struct qeth_card *card, int recovery_mode) qeth_clear_cmd_buffers(&card->read); qeth_clear_cmd_buffers(&card->write); } + + flush_workqueue(card->event_wq); } static int qeth_l2_process_inbound_buffer(struct qeth_card *card, @@ -366,8 +368,8 @@ static int qeth_l2_process_inbound_buffer(struct qeth_card *card, } work_done++; budget--; - card->stats.rx_packets++; - card->stats.rx_bytes += len; + QETH_CARD_STAT_INC(card, rx_packets); + QETH_CARD_STAT_ADD(card, rx_bytes, len); } return work_done; } @@ -391,7 +393,7 @@ static int qeth_l2_request_initial_mac(struct qeth_card *card) if (!IS_OSN(card)) { rc = qeth_setadpparms_change_macaddr(card); - if (!rc && is_valid_ether_addr(card->dev->dev_addr)) + if (!rc) goto out; QETH_DBF_MESSAGE(2, "READ_MAC Assist failed on device %x: %#x\n", CARD_DEVID(card), rc); @@ -423,7 +425,7 @@ static int qeth_l2_validate_addr(struct net_device *dev) { struct qeth_card *card = dev->ml_priv; - if (IS_OSN(card) || (card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED)) + if (card->info.mac_bits & QETH_LAYER2_MAC_REGISTERED) return eth_validate_addr(dev); QETH_CARD_TEXT(card, 4, "nomacadr"); @@ -439,9 +441,7 @@ static int qeth_l2_set_mac_address(struct net_device *dev, void *p) QETH_CARD_TEXT(card, 3, "setmac"); - if (card->info.type == QETH_CARD_TYPE_OSN || - card->info.type == QETH_CARD_TYPE_OSM || - card->info.type == QETH_CARD_TYPE_OSX) { + if (IS_OSM(card) || IS_OSX(card)) { QETH_CARD_TEXT(card, 3, "setmcTYP"); return -EOPNOTSUPP; } @@ -535,9 +535,6 @@ static void qeth_l2_set_rx_mode(struct net_device *dev) int i; int rc; - if (card->info.type == QETH_CARD_TYPE_OSN) - return; - QETH_CARD_TEXT(card, 3, "setmulti"); spin_lock_bh(&card->mclock); @@ -623,17 +620,13 @@ static netdev_tx_t qeth_l2_hard_start_xmit(struct sk_buff *skb, int tx_bytes = skb->len; int rc; + queue = qeth_get_tx_queue(card, skb, ipv, cast_type); + if (card->state != CARD_STATE_UP) { - card->stats.tx_carrier_errors++; + QETH_TXQ_STAT_INC(queue, tx_carrier_errors); goto tx_drop; } - queue = qeth_get_tx_queue(card, skb, ipv, cast_type); - - if (card->options.performance_stats) { - card->perf_stats.outbound_cnt++; - card->perf_stats.outbound_start_time = qeth_get_micros(); - } netif_stop_queue(dev); if (IS_OSN(card)) @@ -643,11 +636,8 @@ static netdev_tx_t qeth_l2_hard_start_xmit(struct sk_buff *skb, qeth_l2_fill_header); if (!rc) { - card->stats.tx_packets++; - card->stats.tx_bytes += tx_bytes; - if (card->options.performance_stats) - card->perf_stats.outbound_time += qeth_get_micros() - - card->perf_stats.outbound_start_time; + QETH_TXQ_STAT_INC(queue, tx_packets); + QETH_TXQ_STAT_ADD(queue, tx_bytes, tx_bytes); netif_wake_queue(dev); return NETDEV_TX_OK; } else if (rc == -EBUSY) { @@ -655,8 +645,8 @@ static netdev_tx_t qeth_l2_hard_start_xmit(struct sk_buff *skb, } /* else fall through */ tx_drop: - card->stats.tx_dropped++; - card->stats.tx_errors++; + QETH_TXQ_STAT_INC(queue, tx_dropped); + QETH_TXQ_STAT_INC(queue, tx_errors); dev_kfree_skb_any(skb); netif_wake_queue(dev); return NETDEV_TX_OK; @@ -695,30 +685,16 @@ static void qeth_l2_remove_device(struct ccwgroup_device *cgdev) if (cgdev->state == CCWGROUP_ONLINE) qeth_l2_set_offline(cgdev); + + cancel_work_sync(&card->close_dev_work); if (qeth_netdev_is_registered(card->dev)) unregister_netdev(card->dev); } -static const struct ethtool_ops qeth_l2_ethtool_ops = { - .get_link = ethtool_op_get_link, - .get_strings = qeth_core_get_strings, - .get_ethtool_stats = qeth_core_get_ethtool_stats, - .get_sset_count = qeth_core_get_sset_count, - .get_drvinfo = qeth_core_get_drvinfo, - .get_link_ksettings = qeth_core_ethtool_get_link_ksettings, -}; - -static const struct ethtool_ops qeth_l2_osn_ops = { - .get_strings = qeth_core_get_strings, - .get_ethtool_stats = qeth_core_get_ethtool_stats, - .get_sset_count = qeth_core_get_sset_count, - .get_drvinfo = qeth_core_get_drvinfo, -}; - static const struct net_device_ops qeth_l2_netdev_ops = { .ndo_open = qeth_open, .ndo_stop = qeth_stop, - .ndo_get_stats = qeth_get_stats, + .ndo_get_stats64 = qeth_get_stats64, .ndo_start_xmit = qeth_l2_hard_start_xmit, .ndo_features_check = qeth_features_check, .ndo_validate_addr = qeth_l2_validate_addr, @@ -732,20 +708,29 @@ static const struct net_device_ops qeth_l2_netdev_ops = { .ndo_set_features = qeth_set_features }; +static const struct net_device_ops qeth_osn_netdev_ops = { + .ndo_open = qeth_open, + .ndo_stop = qeth_stop, + .ndo_get_stats64 = qeth_get_stats64, + .ndo_start_xmit = qeth_l2_hard_start_xmit, + .ndo_validate_addr = eth_validate_addr, + .ndo_tx_timeout = qeth_tx_timeout, +}; + static int qeth_l2_setup_netdev(struct qeth_card *card, bool carrier_ok) { int rc; - card->dev->priv_flags |= IFF_UNICAST_FLT; - card->dev->netdev_ops = &qeth_l2_netdev_ops; - if (card->info.type == QETH_CARD_TYPE_OSN) { - card->dev->ethtool_ops = &qeth_l2_osn_ops; + if (IS_OSN(card)) { + card->dev->netdev_ops = &qeth_osn_netdev_ops; card->dev->flags |= IFF_NOARP; - } else { - card->dev->ethtool_ops = &qeth_l2_ethtool_ops; - card->dev->needed_headroom = sizeof(struct qeth_hdr); + goto add_napi; } + card->dev->needed_headroom = sizeof(struct qeth_hdr); + card->dev->netdev_ops = &qeth_l2_netdev_ops; + card->dev->priv_flags |= IFF_UNICAST_FLT; + if (IS_OSM(card)) { card->dev->features |= NETIF_F_VLAN_CHALLENGED; } else { @@ -786,6 +771,7 @@ static int qeth_l2_setup_netdev(struct qeth_card *card, bool carrier_ok) PAGE_SIZE * (QDIO_MAX_ELEMENTS_PER_BUFFER - 1)); } +add_napi: netif_napi_add(card->dev, &card->napi, qeth_poll, QETH_NAPI_WEIGHT); rc = register_netdev(card->dev); if (!rc && carrier_ok) @@ -1120,20 +1106,14 @@ static int qeth_osn_send_control_data(struct qeth_card *card, int len, } static int qeth_osn_send_ipa_cmd(struct qeth_card *card, - struct qeth_cmd_buffer *iob, int data_len) + struct qeth_cmd_buffer *iob) { - u16 s1, s2; + u16 length; QETH_CARD_TEXT(card, 4, "osndipa"); - qeth_prepare_ipa_cmd(card, iob); - s1 = (u16)(IPA_PDU_HEADER_SIZE + data_len); - s2 = (u16)data_len; - memcpy(QETH_IPA_PDU_LEN_TOTAL(iob->data), &s1, 2); - memcpy(QETH_IPA_PDU_LEN_PDU1(iob->data), &s2, 2); - memcpy(QETH_IPA_PDU_LEN_PDU2(iob->data), &s2, 2); - memcpy(QETH_IPA_PDU_LEN_PDU3(iob->data), &s2, 2); - return qeth_osn_send_control_data(card, s1, iob); + memcpy(&length, QETH_IPA_PDU_LEN_TOTAL(iob->data), 2); + return qeth_osn_send_control_data(card, length, iob); } int qeth_osn_assist(struct net_device *dev, void *data, int data_len) @@ -1150,8 +1130,9 @@ int qeth_osn_assist(struct net_device *dev, void *data, int data_len) if (!qeth_card_hw_is_reachable(card)) return -ENODEV; iob = qeth_wait_for_buffer(&card->write); + qeth_prepare_ipa_cmd(card, iob, (u16) data_len); memcpy(__ipa_cmd(iob), data, data_len); - return qeth_osn_send_ipa_cmd(card, iob, data_len); + return qeth_osn_send_ipa_cmd(card, iob); } EXPORT_SYMBOL(qeth_osn_assist); @@ -1330,7 +1311,7 @@ static void qeth_bridge_state_change(struct qeth_card *card, data->card = card; memcpy(&data->qports, qports, sizeof(struct qeth_sbp_state_change) + extrasize); - queue_work(qeth_wq, &data->worker); + queue_work(card->event_wq, &data->worker); } struct qeth_bridge_host_data { @@ -1402,14 +1383,12 @@ static void qeth_bridge_host_event(struct qeth_card *card, data->card = card; memcpy(&data->hostevs, hostevs, sizeof(struct qeth_ipacmd_addr_change) + extrasize); - queue_work(qeth_wq, &data->worker); + queue_work(card->event_wq, &data->worker); } /* SETBRIDGEPORT support; sending commands */ struct _qeth_sbp_cbctl { - u16 ipa_rc; - u16 cmd_rc; union { u32 supported; struct { @@ -1419,23 +1398,21 @@ struct _qeth_sbp_cbctl { } data; }; -/** - * qeth_bridgeport_makerc() - derive "traditional" error from hardware codes. - * @card: qeth_card structure pointer, for debug messages. - * @cbctl: state structure with hardware return codes. - * @setcmd: IPA command code - * - * Returns negative errno-compatible error indication or 0 on success. - */ static int qeth_bridgeport_makerc(struct qeth_card *card, - struct _qeth_sbp_cbctl *cbctl, enum qeth_ipa_sbp_cmd setcmd) + struct qeth_ipa_cmd *cmd) { + struct qeth_ipacmd_setbridgeport *sbp = &cmd->data.sbp; + enum qeth_ipa_sbp_cmd setcmd = sbp->hdr.command_code; + u16 ipa_rc = cmd->hdr.return_code; + u16 sbp_rc = sbp->hdr.return_code; int rc; - int is_iqd = (card->info.type == QETH_CARD_TYPE_IQD); - if ((is_iqd && (cbctl->ipa_rc == IPA_RC_SUCCESS)) || - (!is_iqd && (cbctl->ipa_rc == cbctl->cmd_rc))) - switch (cbctl->cmd_rc) { + if (ipa_rc == IPA_RC_SUCCESS && sbp_rc == IPA_RC_SUCCESS) + return 0; + + if ((IS_IQD(card) && ipa_rc == IPA_RC_SUCCESS) || + (!IS_IQD(card) && ipa_rc == sbp_rc)) { + switch (sbp_rc) { case IPA_RC_SUCCESS: rc = 0; break; @@ -1499,8 +1476,8 @@ static int qeth_bridgeport_makerc(struct qeth_card *card, default: rc = -EIO; } - else - switch (cbctl->ipa_rc) { + } else { + switch (ipa_rc) { case IPA_RC_NOTSUPP: rc = -EOPNOTSUPP; break; @@ -1510,10 +1487,11 @@ static int qeth_bridgeport_makerc(struct qeth_card *card, default: rc = -EIO; } + } if (rc) { - QETH_CARD_TEXT_(card, 2, "SBPi%04x", cbctl->ipa_rc); - QETH_CARD_TEXT_(card, 2, "SBPc%04x", cbctl->cmd_rc); + QETH_CARD_TEXT_(card, 2, "SBPi%04x", ipa_rc); + QETH_CARD_TEXT_(card, 2, "SBPc%04x", sbp_rc); } return rc; } @@ -1545,15 +1523,15 @@ static int qeth_bridgeport_query_support_cb(struct qeth_card *card, { struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data; struct _qeth_sbp_cbctl *cbctl = (struct _qeth_sbp_cbctl *)reply->param; + int rc; + QETH_CARD_TEXT(card, 2, "brqsupcb"); - cbctl->ipa_rc = cmd->hdr.return_code; - cbctl->cmd_rc = cmd->data.sbp.hdr.return_code; - if ((cbctl->ipa_rc == 0) && (cbctl->cmd_rc == 0)) { - cbctl->data.supported = - cmd->data.sbp.data.query_cmds_supp.supported_cmds; - } else { - cbctl->data.supported = 0; - } + rc = qeth_bridgeport_makerc(card, cmd); + if (rc) + return rc; + + cbctl->data.supported = + cmd->data.sbp.data.query_cmds_supp.supported_cmds; return 0; } @@ -1574,12 +1552,11 @@ static void qeth_bridgeport_query_support(struct qeth_card *card) sizeof(struct qeth_sbp_query_cmds_supp)); if (!iob) return; + if (qeth_send_ipa_cmd(card, iob, qeth_bridgeport_query_support_cb, - (void *)&cbctl) || - qeth_bridgeport_makerc(card, &cbctl, - IPA_SBP_QUERY_COMMANDS_SUPPORTED)) { - /* non-zero makerc signifies failure, and produce messages */ + &cbctl)) { card->options.sbp.role = QETH_SBP_ROLE_NONE; + card->options.sbp.supported_funcs = 0; return; } card->options.sbp.supported_funcs = cbctl.data.supported; @@ -1591,16 +1568,16 @@ static int qeth_bridgeport_query_ports_cb(struct qeth_card *card, struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data; struct qeth_sbp_query_ports *qports = &cmd->data.sbp.data.query_ports; struct _qeth_sbp_cbctl *cbctl = (struct _qeth_sbp_cbctl *)reply->param; + int rc; QETH_CARD_TEXT(card, 2, "brqprtcb"); - cbctl->ipa_rc = cmd->hdr.return_code; - cbctl->cmd_rc = cmd->data.sbp.hdr.return_code; - if ((cbctl->ipa_rc != 0) || (cbctl->cmd_rc != 0)) - return 0; + rc = qeth_bridgeport_makerc(card, cmd); + if (rc) + return rc; + if (qports->entry_length != sizeof(struct qeth_sbp_port_entry)) { - cbctl->cmd_rc = 0xffff; QETH_CARD_TEXT_(card, 2, "SBPs%04x", qports->entry_length); - return 0; + return -EINVAL; } /* first entry contains the state of the local port */ if (qports->num_entries > 0) { @@ -1625,7 +1602,6 @@ static int qeth_bridgeport_query_ports_cb(struct qeth_card *card, int qeth_bridgeport_query_ports(struct qeth_card *card, enum qeth_sbp_roles *role, enum qeth_sbp_states *state) { - int rc = 0; struct qeth_cmd_buffer *iob; struct _qeth_sbp_cbctl cbctl = { .data = { @@ -1642,22 +1618,18 @@ int qeth_bridgeport_query_ports(struct qeth_card *card, iob = qeth_sbp_build_cmd(card, IPA_SBP_QUERY_BRIDGE_PORTS, 0); if (!iob) return -ENOMEM; - rc = qeth_send_ipa_cmd(card, iob, qeth_bridgeport_query_ports_cb, - (void *)&cbctl); - if (rc < 0) - return rc; - return qeth_bridgeport_makerc(card, &cbctl, IPA_SBP_QUERY_BRIDGE_PORTS); + + return qeth_send_ipa_cmd(card, iob, qeth_bridgeport_query_ports_cb, + &cbctl); } static int qeth_bridgeport_set_cb(struct qeth_card *card, struct qeth_reply *reply, unsigned long data) { struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *)data; - struct _qeth_sbp_cbctl *cbctl = (struct _qeth_sbp_cbctl *)reply->param; + QETH_CARD_TEXT(card, 2, "brsetrcb"); - cbctl->ipa_rc = cmd->hdr.return_code; - cbctl->cmd_rc = cmd->data.sbp.hdr.return_code; - return 0; + return qeth_bridgeport_makerc(card, cmd); } /** @@ -1669,10 +1641,8 @@ static int qeth_bridgeport_set_cb(struct qeth_card *card, */ int qeth_bridgeport_setrole(struct qeth_card *card, enum qeth_sbp_roles role) { - int rc = 0; int cmdlength; struct qeth_cmd_buffer *iob; - struct _qeth_sbp_cbctl cbctl; enum qeth_ipa_sbp_cmd setcmd; QETH_CARD_TEXT(card, 2, "brsetrol"); @@ -1697,11 +1667,8 @@ int qeth_bridgeport_setrole(struct qeth_card *card, enum qeth_sbp_roles role) iob = qeth_sbp_build_cmd(card, setcmd, cmdlength); if (!iob) return -ENOMEM; - rc = qeth_send_ipa_cmd(card, iob, qeth_bridgeport_set_cb, - (void *)&cbctl); - if (rc < 0) - return rc; - return qeth_bridgeport_makerc(card, &cbctl, setcmd); + + return qeth_send_ipa_cmd(card, iob, qeth_bridgeport_set_cb, NULL); } /** @@ -1805,7 +1772,7 @@ static bool qeth_bridgeport_is_in_use(struct qeth_card *card) /* VNIC Characteristics support */ /* handle VNICC IPA command return codes; convert to error codes */ -static int qeth_l2_vnicc_makerc(struct qeth_card *card, int ipa_rc) +static int qeth_l2_vnicc_makerc(struct qeth_card *card, u16 ipa_rc) { int rc; @@ -1863,7 +1830,7 @@ static int qeth_l2_vnicc_request_cb(struct qeth_card *card, QETH_CARD_TEXT(card, 2, "vniccrcb"); if (cmd->hdr.return_code) - return 0; + return qeth_l2_vnicc_makerc(card, cmd->hdr.return_code); /* return results to caller */ card->options.vnicc.sup_chars = rep->hdr.sup; card->options.vnicc.cur_chars = rep->hdr.cur; @@ -1884,7 +1851,6 @@ static int qeth_l2_vnicc_request(struct qeth_card *card, struct qeth_ipacmd_vnicc *req; struct qeth_cmd_buffer *iob; struct qeth_ipa_cmd *cmd; - int rc; QETH_CARD_TEXT(card, 2, "vniccreq"); @@ -1927,10 +1893,7 @@ static int qeth_l2_vnicc_request(struct qeth_card *card, } /* send request */ - rc = qeth_send_ipa_cmd(card, iob, qeth_l2_vnicc_request_cb, - (void *) cbctl); - - return qeth_l2_vnicc_makerc(card, rc); + return qeth_send_ipa_cmd(card, iob, qeth_l2_vnicc_request_cb, cbctl); } /* VNICC query VNIC characteristics request */ diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 59535ecb1487..07c3149e228c 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -253,8 +253,7 @@ static int qeth_l3_add_ip(struct qeth_card *card, struct qeth_ipaddr *tmp_addr) } else rc = qeth_l3_register_addr_entry(card, addr); - if (!rc || (rc == IPA_RC_DUPLICATE_IP_ADDRESS) || - (rc == IPA_RC_LAN_OFFLINE)) { + if (!rc || rc == -EADDRINUSE || rc == -ENETDOWN) { addr->disp_flag = QETH_DISP_ADDR_DO_NOTHING; if (addr->ref_counter < 1) { qeth_l3_deregister_addr_entry(card, addr); @@ -338,10 +337,28 @@ static void qeth_l3_recover_ip(struct qeth_card *card) } +static int qeth_l3_setdelip_cb(struct qeth_card *card, struct qeth_reply *reply, + unsigned long data) +{ + struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data; + + switch (cmd->hdr.return_code) { + case IPA_RC_SUCCESS: + return 0; + case IPA_RC_DUPLICATE_IP_ADDRESS: + return -EADDRINUSE; + case IPA_RC_MC_ADDR_NOT_FOUND: + return -ENOENT; + case IPA_RC_LAN_OFFLINE: + return -ENETDOWN; + default: + return -EIO; + } +} + static int qeth_l3_send_setdelmc(struct qeth_card *card, struct qeth_ipaddr *addr, int ipacmd) { - int rc; struct qeth_cmd_buffer *iob; struct qeth_ipa_cmd *cmd; @@ -358,9 +375,7 @@ static int qeth_l3_send_setdelmc(struct qeth_card *card, else memcpy(&cmd->data.setdelipm.ip4, &addr->u.a4.addr, 4); - rc = qeth_send_ipa_cmd(card, iob, NULL, NULL); - - return rc; + return qeth_send_ipa_cmd(card, iob, qeth_l3_setdelip_cb, NULL); } static void qeth_l3_fill_netmask(u8 *netmask, unsigned int len) @@ -422,7 +437,7 @@ static int qeth_l3_send_setdelip(struct qeth_card *card, cmd->data.setdelip4.flags = flags; } - return qeth_send_ipa_cmd(card, iob, NULL, NULL); + return qeth_send_ipa_cmd(card, iob, qeth_l3_setdelip_cb, NULL); } static int qeth_l3_send_setrouting(struct qeth_card *card, @@ -942,12 +957,13 @@ static int qeth_l3_start_ipassists(struct qeth_card *card) static int qeth_l3_iqd_read_initial_mac_cb(struct qeth_card *card, struct qeth_reply *reply, unsigned long data) { - struct qeth_ipa_cmd *cmd; + struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data; - cmd = (struct qeth_ipa_cmd *) data; - if (cmd->hdr.return_code == 0) - ether_addr_copy(card->dev->dev_addr, - cmd->data.create_destroy_addr.unique_id); + if (cmd->hdr.return_code) + return -EIO; + + ether_addr_copy(card->dev->dev_addr, + cmd->data.create_destroy_addr.unique_id); return 0; } @@ -975,19 +991,18 @@ static int qeth_l3_iqd_read_initial_mac(struct qeth_card *card) static int qeth_l3_get_unique_id_cb(struct qeth_card *card, struct qeth_reply *reply, unsigned long data) { - struct qeth_ipa_cmd *cmd; + struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data; - cmd = (struct qeth_ipa_cmd *) data; - if (cmd->hdr.return_code == 0) + if (cmd->hdr.return_code == 0) { card->info.unique_id = *((__u16 *) &cmd->data.create_destroy_addr.unique_id[6]); - else { - card->info.unique_id = UNIQUE_ID_IF_CREATE_ADDR_FAILED | - UNIQUE_ID_NOT_BY_CARD; - dev_warn(&card->gdev->dev, "The network adapter failed to " - "generate a unique ID\n"); + return 0; } - return 0; + + card->info.unique_id = UNIQUE_ID_IF_CREATE_ADDR_FAILED | + UNIQUE_ID_NOT_BY_CARD; + dev_warn(&card->gdev->dev, "The network adapter failed to generate a unique ID\n"); + return -EIO; } static int qeth_l3_get_unique_id(struct qeth_card *card) @@ -1070,7 +1085,7 @@ qeth_diags_trace_cb(struct qeth_card *card, struct qeth_reply *reply, cmd->data.diagass.action, CARD_DEVID(card)); } - return 0; + return rc ? -EIO : 0; } static int @@ -1300,12 +1315,11 @@ static void qeth_l3_rebuild_skb(struct qeth_card *card, struct sk_buff *skb, ip_eth_mc_map(ip_hdr(skb)->daddr, tg_addr); else ipv6_eth_mc_map(&ipv6_hdr(skb)->daddr, tg_addr); - - card->stats.multicast++; + QETH_CARD_STAT_INC(card, rx_multicast); break; case QETH_CAST_BROADCAST: ether_addr_copy(tg_addr, card->dev->broadcast); - card->stats.multicast++; + QETH_CARD_STAT_INC(card, rx_multicast); break; default: if (card->options.sniffer) @@ -1386,8 +1400,8 @@ static int qeth_l3_process_inbound_buffer(struct qeth_card *card, } work_done++; budget--; - card->stats.rx_packets++; - card->stats.rx_bytes += len; + QETH_CARD_STAT_INC(card, rx_packets); + QETH_CARD_STAT_ADD(card, rx_bytes, len); } return work_done; } @@ -1428,6 +1442,8 @@ static void qeth_l3_stop_card(struct qeth_card *card, int recovery_mode) qeth_clear_cmd_buffers(&card->read); qeth_clear_cmd_buffers(&card->write); } + + flush_workqueue(card->event_wq); } /* @@ -1479,14 +1495,14 @@ static void qeth_l3_set_rx_mode(struct net_device *dev) switch (addr->disp_flag) { case QETH_DISP_ADDR_DELETE: rc = qeth_l3_deregister_addr_entry(card, addr); - if (!rc || rc == IPA_RC_MC_ADDR_NOT_FOUND) { + if (!rc || rc == -ENOENT) { hash_del(&addr->hnode); kfree(addr); } break; case QETH_DISP_ADDR_ADD: rc = qeth_l3_register_addr_entry(card, addr); - if (rc && rc != IPA_RC_LAN_OFFLINE) { + if (rc && rc != -ENETDOWN) { hash_del(&addr->hnode); kfree(addr); break; @@ -1507,7 +1523,7 @@ static void qeth_l3_set_rx_mode(struct net_device *dev) qeth_l3_handle_promisc_mode(card); } -static int qeth_l3_arp_makerc(int rc) +static int qeth_l3_arp_makerc(u16 rc) { switch (rc) { case IPA_RC_SUCCESS: @@ -1524,8 +1540,18 @@ static int qeth_l3_arp_makerc(int rc) } } +static int qeth_l3_arp_cmd_cb(struct qeth_card *card, struct qeth_reply *reply, + unsigned long data) +{ + struct qeth_ipa_cmd *cmd = (struct qeth_ipa_cmd *) data; + + qeth_setassparms_cb(card, reply, data); + return qeth_l3_arp_makerc(cmd->hdr.return_code); +} + static int qeth_l3_arp_set_no_entries(struct qeth_card *card, int no_entries) { + struct qeth_cmd_buffer *iob; int rc; QETH_CARD_TEXT(card, 3, "arpstnoe"); @@ -1540,13 +1566,19 @@ static int qeth_l3_arp_set_no_entries(struct qeth_card *card, int no_entries) if (!qeth_is_supported(card, IPA_ARP_PROCESSING)) { return -EOPNOTSUPP; } - rc = qeth_send_simple_setassparms(card, IPA_ARP_PROCESSING, - IPA_CMD_ASS_ARP_SET_NO_ENTRIES, - no_entries); + + iob = qeth_get_setassparms_cmd(card, IPA_ARP_PROCESSING, + IPA_CMD_ASS_ARP_SET_NO_ENTRIES, 4, + QETH_PROT_IPV4); + if (!iob) + return -ENOMEM; + + __ipa_cmd(iob)->data.setassparms.data.flags_32bit = (u32) no_entries; + rc = qeth_send_ipa_cmd(card, iob, qeth_l3_arp_cmd_cb, NULL); if (rc) QETH_DBF_MESSAGE(2, "Could not set number of ARP entries on device %x: %#x\n", CARD_DEVID(card), rc); - return qeth_l3_arp_makerc(rc); + return rc; } static __u32 get_arp_entry_size(struct qeth_card *card, @@ -1597,7 +1629,6 @@ static int qeth_l3_arp_query_cb(struct qeth_card *card, struct qeth_ipa_cmd *cmd; struct qeth_arp_query_data *qdata; struct qeth_arp_query_info *qinfo; - int i; int e; int entrybytes_done; int stripped_bytes; @@ -1611,13 +1642,13 @@ static int qeth_l3_arp_query_cb(struct qeth_card *card, if (cmd->hdr.return_code) { QETH_CARD_TEXT(card, 4, "arpcberr"); QETH_CARD_TEXT_(card, 4, "%i", cmd->hdr.return_code); - return 0; + return qeth_l3_arp_makerc(cmd->hdr.return_code); } if (cmd->data.setassparms.hdr.return_code) { cmd->hdr.return_code = cmd->data.setassparms.hdr.return_code; QETH_CARD_TEXT(card, 4, "setaperr"); QETH_CARD_TEXT_(card, 4, "%i", cmd->hdr.return_code); - return 0; + return qeth_l3_arp_makerc(cmd->hdr.return_code); } qdata = &cmd->data.setassparms.data.query_arp; QETH_CARD_TEXT_(card, 4, "anoen%i", qdata->no_entries); @@ -1644,9 +1675,9 @@ static int qeth_l3_arp_query_cb(struct qeth_card *card, break; if ((qinfo->udata_len - qinfo->udata_offset) < esize) { - QETH_CARD_TEXT_(card, 4, "qaer3%i", -ENOMEM); - cmd->hdr.return_code = IPA_RC_ENOMEM; - goto out_error; + QETH_CARD_TEXT_(card, 4, "qaer3%i", -ENOSPC); + memset(qinfo->udata, 0, 4); + return -ENOSPC; } memcpy(qinfo->udata + qinfo->udata_offset, @@ -1669,10 +1700,6 @@ static int qeth_l3_arp_query_cb(struct qeth_card *card, memcpy(qinfo->udata + QETH_QARP_MASK_OFFSET, &qdata->reply_bits, 2); QETH_CARD_TEXT_(card, 4, "rc%i", 0); return 0; -out_error: - i = 0; - memcpy(qinfo->udata, &i, 4); - return 0; } static int qeth_l3_query_arp_cache_info(struct qeth_card *card, @@ -1694,13 +1721,11 @@ static int qeth_l3_query_arp_cache_info(struct qeth_card *card, return -ENOMEM; cmd = __ipa_cmd(iob); cmd->data.setassparms.data.query_arp.request_bits = 0x000F; - rc = qeth_send_control_data(card, - QETH_SETASS_BASE_LEN + QETH_ARP_CMD_LEN, - iob, qeth_l3_arp_query_cb, qinfo); + rc = qeth_send_ipa_cmd(card, iob, qeth_l3_arp_query_cb, qinfo); if (rc) QETH_DBF_MESSAGE(2, "Error while querying ARP cache on device %x: %#x\n", CARD_DEVID(card), rc); - return qeth_l3_arp_makerc(rc); + return rc; } static int qeth_l3_arp_query(struct qeth_card *card, char __user *udata) @@ -1782,16 +1807,16 @@ static int qeth_l3_arp_modify_entry(struct qeth_card *card, cmd_entry = &__ipa_cmd(iob)->data.setassparms.data.arp_entry; ether_addr_copy(cmd_entry->macaddr, entry->macaddr); memcpy(cmd_entry->ipaddr, entry->ipaddr, 4); - rc = qeth_send_ipa_cmd(card, iob, qeth_setassparms_cb, NULL); + rc = qeth_send_ipa_cmd(card, iob, qeth_l3_arp_cmd_cb, NULL); if (rc) QETH_DBF_MESSAGE(2, "Could not modify (cmd: %#x) ARP entry on device %x: %#x\n", arp_cmd, CARD_DEVID(card), rc); - - return qeth_l3_arp_makerc(rc); + return rc; } static int qeth_l3_arp_flush_cache(struct qeth_card *card) { + struct qeth_cmd_buffer *iob; int rc; QETH_CARD_TEXT(card, 3, "arpflush"); @@ -1806,12 +1831,18 @@ static int qeth_l3_arp_flush_cache(struct qeth_card *card) if (!qeth_is_supported(card, IPA_ARP_PROCESSING)) { return -EOPNOTSUPP; } - rc = qeth_send_simple_setassparms(card, IPA_ARP_PROCESSING, - IPA_CMD_ASS_ARP_FLUSH_CACHE, 0); + + iob = qeth_get_setassparms_cmd(card, IPA_ARP_PROCESSING, + IPA_CMD_ASS_ARP_FLUSH_CACHE, 0, + QETH_PROT_IPV4); + if (!iob) + return -ENOMEM; + + rc = qeth_send_ipa_cmd(card, iob, qeth_l3_arp_cmd_cb, NULL); if (rc) QETH_DBF_MESSAGE(2, "Could not flush ARP cache on device %x: %#x\n", CARD_DEVID(card), rc); - return qeth_l3_arp_makerc(rc); + return rc; } static int qeth_l3_do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) @@ -1913,12 +1944,13 @@ static u8 qeth_l3_cast_type_to_flag(int cast_type) return QETH_CAST_UNICAST; } -static void qeth_l3_fill_header(struct qeth_card *card, struct qeth_hdr *hdr, - struct sk_buff *skb, int ipv, int cast_type, - unsigned int data_len) +static void qeth_l3_fill_header(struct qeth_qdio_out_q *queue, + struct qeth_hdr *hdr, struct sk_buff *skb, + int ipv, int cast_type, unsigned int data_len) { struct qeth_hdr_layer3 *l3_hdr = &hdr->hdr.l3; struct vlan_ethhdr *veth = vlan_eth_hdr(skb); + struct qeth_card *card = queue->card; hdr->hdr.l3.length = data_len; @@ -1940,8 +1972,7 @@ static void qeth_l3_fill_header(struct qeth_card *card, struct qeth_hdr *hdr, /* some HW requires combined L3+L4 csum offload: */ if (ipv == 4) hdr->hdr.l3.ext_flags |= QETH_HDR_EXT_CSUM_HDR_REQ; - if (card->options.performance_stats) - card->perf_stats.tx_csum++; + QETH_TXQ_STAT_INC(queue, skbs_csum); } } @@ -2042,6 +2073,8 @@ static netdev_tx_t qeth_l3_hard_start_xmit(struct sk_buff *skb, int tx_bytes = skb->len; int rc; + queue = qeth_get_tx_queue(card, skb, ipv, cast_type); + if (IS_IQD(card)) { if (card->options.sniffer) goto tx_drop; @@ -2052,19 +2085,13 @@ static netdev_tx_t qeth_l3_hard_start_xmit(struct sk_buff *skb, } if (card->state != CARD_STATE_UP) { - card->stats.tx_carrier_errors++; + QETH_TXQ_STAT_INC(queue, tx_carrier_errors); goto tx_drop; } if (cast_type == RTN_BROADCAST && !card->info.broadcast_capable) goto tx_drop; - queue = qeth_get_tx_queue(card, skb, ipv, cast_type); - - if (card->options.performance_stats) { - card->perf_stats.outbound_cnt++; - card->perf_stats.outbound_start_time = qeth_get_micros(); - } netif_stop_queue(dev); if (ipv == 4 || IS_IQD(card)) @@ -2074,11 +2101,8 @@ static netdev_tx_t qeth_l3_hard_start_xmit(struct sk_buff *skb, qeth_l3_fill_header); if (!rc) { - card->stats.tx_packets++; - card->stats.tx_bytes += tx_bytes; - if (card->options.performance_stats) - card->perf_stats.outbound_time += qeth_get_micros() - - card->perf_stats.outbound_start_time; + QETH_TXQ_STAT_INC(queue, tx_packets); + QETH_TXQ_STAT_ADD(queue, tx_bytes, tx_bytes); netif_wake_queue(dev); return NETDEV_TX_OK; } else if (rc == -EBUSY) { @@ -2086,22 +2110,13 @@ static netdev_tx_t qeth_l3_hard_start_xmit(struct sk_buff *skb, } /* else fall through */ tx_drop: - card->stats.tx_dropped++; - card->stats.tx_errors++; + QETH_TXQ_STAT_INC(queue, tx_dropped); + QETH_TXQ_STAT_INC(queue, tx_errors); dev_kfree_skb_any(skb); netif_wake_queue(dev); return NETDEV_TX_OK; } -static const struct ethtool_ops qeth_l3_ethtool_ops = { - .get_link = ethtool_op_get_link, - .get_strings = qeth_core_get_strings, - .get_ethtool_stats = qeth_core_get_ethtool_stats, - .get_sset_count = qeth_core_get_sset_count, - .get_drvinfo = qeth_core_get_drvinfo, - .get_link_ksettings = qeth_core_ethtool_get_link_ksettings, -}; - /* * we need NOARP for IPv4 but we want neighbor solicitation for IPv6. Setting * NOARP on the netdevice is no option because it also turns off neighbor @@ -2138,7 +2153,7 @@ static netdev_features_t qeth_l3_osa_features_check(struct sk_buff *skb, static const struct net_device_ops qeth_l3_netdev_ops = { .ndo_open = qeth_open, .ndo_stop = qeth_stop, - .ndo_get_stats = qeth_get_stats, + .ndo_get_stats64 = qeth_get_stats64, .ndo_start_xmit = qeth_l3_hard_start_xmit, .ndo_validate_addr = eth_validate_addr, .ndo_set_rx_mode = qeth_l3_set_rx_mode, @@ -2153,7 +2168,7 @@ static const struct net_device_ops qeth_l3_netdev_ops = { static const struct net_device_ops qeth_l3_osa_netdev_ops = { .ndo_open = qeth_open, .ndo_stop = qeth_stop, - .ndo_get_stats = qeth_get_stats, + .ndo_get_stats64 = qeth_get_stats64, .ndo_start_xmit = qeth_l3_hard_start_xmit, .ndo_features_check = qeth_l3_osa_features_check, .ndo_validate_addr = eth_validate_addr, @@ -2223,7 +2238,6 @@ static int qeth_l3_setup_netdev(struct qeth_card *card, bool carrier_ok) return -ENODEV; card->dev->needed_headroom = headroom; - card->dev->ethtool_ops = &qeth_l3_ethtool_ops; card->dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER; @@ -2278,6 +2292,7 @@ static void qeth_l3_remove_device(struct ccwgroup_device *cgdev) if (cgdev->state == CCWGROUP_ONLINE) qeth_l3_set_offline(cgdev); + cancel_work_sync(&card->close_dev_work); if (qeth_netdev_is_registered(card->dev)) unregister_netdev(card->dev); qeth_l3_clear_ip_htable(card, 0); diff --git a/drivers/s390/scsi/zfcp_aux.c b/drivers/s390/scsi/zfcp_aux.c index 9cf30d124b9e..e390f8c6d5f3 100644 --- a/drivers/s390/scsi/zfcp_aux.c +++ b/drivers/s390/scsi/zfcp_aux.c @@ -403,7 +403,6 @@ struct zfcp_adapter *zfcp_adapter_enqueue(struct ccw_device *ccw_device) goto failed; /* report size limit per scatter-gather segment */ - adapter->dma_parms.max_segment_size = ZFCP_QDIO_SBALE_LEN; adapter->ccw_device->dev.dma_parms = &adapter->dma_parms; adapter->stat_read_buf_num = FSF_STATUS_READS_RECOM; diff --git a/drivers/s390/scsi/zfcp_scsi.c b/drivers/s390/scsi/zfcp_scsi.c index 00acc7144bbc..f4f6a07c5222 100644 --- a/drivers/s390/scsi/zfcp_scsi.c +++ b/drivers/s390/scsi/zfcp_scsi.c @@ -428,6 +428,8 @@ static struct scsi_host_template zfcp_scsi_host_template = { .max_sectors = (((QDIO_MAX_ELEMENTS_PER_BUFFER - 1) * ZFCP_QDIO_MAX_SBALS_PER_REQ) - 2) * 8, /* GCD, adjusted later */ + /* report size limit per scatter-gather segment */ + .max_segment_size = ZFCP_QDIO_SBALE_LEN, .dma_boundary = ZFCP_QDIO_SBALE_LEN - 1, .shost_attrs = zfcp_sysfs_shost_attrs, .sdev_attrs = zfcp_sysfs_sdev_attrs, diff --git a/drivers/scsi/53c700.c b/drivers/scsi/53c700.c index 128d658d472a..16957d7ac414 100644 --- a/drivers/scsi/53c700.c +++ b/drivers/scsi/53c700.c @@ -295,7 +295,7 @@ NCR_700_detect(struct scsi_host_template *tpnt, if(tpnt->sdev_attrs == NULL) tpnt->sdev_attrs = NCR_700_dev_attrs; - memory = dma_alloc_attrs(hostdata->dev, TOTAL_MEM_SIZE, &pScript, + memory = dma_alloc_attrs(dev, TOTAL_MEM_SIZE, &pScript, GFP_KERNEL, DMA_ATTR_NON_CONSISTENT); if(memory == NULL) { printk(KERN_ERR "53c700: Failed to allocate memory for driver, detaching\n"); diff --git a/drivers/scsi/aic94xx/aic94xx_init.c b/drivers/scsi/aic94xx/aic94xx_init.c index f83f79b07b50..07efcb9b5b94 100644 --- a/drivers/scsi/aic94xx/aic94xx_init.c +++ b/drivers/scsi/aic94xx/aic94xx_init.c @@ -280,7 +280,7 @@ static ssize_t asd_show_dev_rev(struct device *dev, return snprintf(buf, PAGE_SIZE, "%s\n", asd_dev_rev[asd_ha->revision_id]); } -static DEVICE_ATTR(revision, S_IRUGO, asd_show_dev_rev, NULL); +static DEVICE_ATTR(aic_revision, S_IRUGO, asd_show_dev_rev, NULL); static ssize_t asd_show_dev_bios_build(struct device *dev, struct device_attribute *attr,char *buf) @@ -477,7 +477,7 @@ static int asd_create_dev_attrs(struct asd_ha_struct *asd_ha) { int err; - err = device_create_file(&asd_ha->pcidev->dev, &dev_attr_revision); + err = device_create_file(&asd_ha->pcidev->dev, &dev_attr_aic_revision); if (err) return err; @@ -499,13 +499,13 @@ err_update_bios: err_biosb: device_remove_file(&asd_ha->pcidev->dev, &dev_attr_bios_build); err_rev: - device_remove_file(&asd_ha->pcidev->dev, &dev_attr_revision); + device_remove_file(&asd_ha->pcidev->dev, &dev_attr_aic_revision); return err; } static void asd_remove_dev_attrs(struct asd_ha_struct *asd_ha) { - device_remove_file(&asd_ha->pcidev->dev, &dev_attr_revision); + device_remove_file(&asd_ha->pcidev->dev, &dev_attr_aic_revision); device_remove_file(&asd_ha->pcidev->dev, &dev_attr_bios_build); device_remove_file(&asd_ha->pcidev->dev, &dev_attr_pcba_sn); device_remove_file(&asd_ha->pcidev->dev, &dev_attr_update_bios); diff --git a/drivers/scsi/bnx2fc/bnx2fc_io.c b/drivers/scsi/bnx2fc/bnx2fc_io.c index 350257c13a5b..bc9f2a2365f4 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_io.c +++ b/drivers/scsi/bnx2fc/bnx2fc_io.c @@ -240,6 +240,7 @@ struct bnx2fc_cmd_mgr *bnx2fc_cmd_mgr_alloc(struct bnx2fc_hba *hba) return NULL; } + cmgr->hba = hba; cmgr->free_list = kcalloc(arr_sz, sizeof(*cmgr->free_list), GFP_KERNEL); if (!cmgr->free_list) { @@ -256,7 +257,6 @@ struct bnx2fc_cmd_mgr *bnx2fc_cmd_mgr_alloc(struct bnx2fc_hba *hba) goto mem_err; } - cmgr->hba = hba; cmgr->cmds = (struct bnx2fc_cmd **)(cmgr + 1); for (i = 0; i < arr_sz; i++) { @@ -295,7 +295,7 @@ struct bnx2fc_cmd_mgr *bnx2fc_cmd_mgr_alloc(struct bnx2fc_hba *hba) /* Allocate pool of io_bdts - one for each bnx2fc_cmd */ mem_size = num_ios * sizeof(struct io_bdt *); - cmgr->io_bdt_pool = kmalloc(mem_size, GFP_KERNEL); + cmgr->io_bdt_pool = kzalloc(mem_size, GFP_KERNEL); if (!cmgr->io_bdt_pool) { printk(KERN_ERR PFX "failed to alloc io_bdt_pool\n"); goto mem_err; diff --git a/drivers/scsi/cxlflash/main.c b/drivers/scsi/cxlflash/main.c index bfa13e3b191c..c8bad2c093b8 100644 --- a/drivers/scsi/cxlflash/main.c +++ b/drivers/scsi/cxlflash/main.c @@ -3687,6 +3687,7 @@ static int cxlflash_probe(struct pci_dev *pdev, host->max_cmd_len = CXLFLASH_MAX_CDB_LEN; cfg = shost_priv(host); + cfg->state = STATE_PROBING; cfg->host = host; rc = alloc_mem(cfg); if (rc) { @@ -3775,6 +3776,7 @@ out: return rc; out_remove: + cfg->state = STATE_PROBED; cxlflash_remove(pdev); goto out; } diff --git a/drivers/scsi/libfc/fc_lport.c b/drivers/scsi/libfc/fc_lport.c index be83590ed955..ff943f477d6f 100644 --- a/drivers/scsi/libfc/fc_lport.c +++ b/drivers/scsi/libfc/fc_lport.c @@ -1726,14 +1726,14 @@ void fc_lport_flogi_resp(struct fc_seq *sp, struct fc_frame *fp, fc_frame_payload_op(fp) != ELS_LS_ACC) { FC_LPORT_DBG(lport, "FLOGI not accepted or bad response\n"); fc_lport_error(lport, fp); - goto err; + goto out; } flp = fc_frame_payload_get(fp, sizeof(*flp)); if (!flp) { FC_LPORT_DBG(lport, "FLOGI bad response\n"); fc_lport_error(lport, fp); - goto err; + goto out; } mfs = ntohs(flp->fl_csp.sp_bb_data) & @@ -1743,7 +1743,7 @@ void fc_lport_flogi_resp(struct fc_seq *sp, struct fc_frame *fp, FC_LPORT_DBG(lport, "FLOGI bad mfs:%hu response, " "lport->mfs:%hu\n", mfs, lport->mfs); fc_lport_error(lport, fp); - goto err; + goto out; } if (mfs <= lport->mfs) { diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c index 9192a1d9dec6..dfba4921b265 100644 --- a/drivers/scsi/libfc/fc_rport.c +++ b/drivers/scsi/libfc/fc_rport.c @@ -184,7 +184,6 @@ void fc_rport_destroy(struct kref *kref) struct fc_rport_priv *rdata; rdata = container_of(kref, struct fc_rport_priv, kref); - WARN_ON(!list_empty(&rdata->peers)); kfree_rcu(rdata, rcu); } EXPORT_SYMBOL(fc_rport_destroy); diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index 661512bec3ac..e27f4df24021 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -62,7 +62,7 @@ /* make sure inq_product_rev string corresponds to this version */ #define SDEBUG_VERSION "0188" /* format to fit INQUIRY revision field */ -static const char *sdebug_version_date = "20180128"; +static const char *sdebug_version_date = "20190125"; #define MY_NAME "scsi_debug" @@ -735,7 +735,7 @@ static inline bool scsi_debug_lbp(void) (sdebug_lbpu || sdebug_lbpws || sdebug_lbpws10); } -static void *fake_store(unsigned long long lba) +static void *lba2fake_store(unsigned long long lba) { lba = do_div(lba, sdebug_store_sectors); @@ -2514,8 +2514,8 @@ static int do_device_access(struct scsi_cmnd *scmd, u32 sg_skip, u64 lba, return ret; } -/* If fake_store(lba,num) compares equal to arr(num), then copy top half of - * arr into fake_store(lba,num) and return true. If comparison fails then +/* If lba2fake_store(lba,num) compares equal to arr(num), then copy top half of + * arr into lba2fake_store(lba,num) and return true. If comparison fails then * return false. */ static bool comp_write_worker(u64 lba, u32 num, const u8 *arr) { @@ -2643,7 +2643,7 @@ static int prot_verify_read(struct scsi_cmnd *SCpnt, sector_t start_sec, if (sdt->app_tag == cpu_to_be16(0xffff)) continue; - ret = dif_verify(sdt, fake_store(sector), sector, ei_lba); + ret = dif_verify(sdt, lba2fake_store(sector), sector, ei_lba); if (ret) { dif_errors++; return ret; @@ -3261,10 +3261,12 @@ err_out: static int resp_write_same(struct scsi_cmnd *scp, u64 lba, u32 num, u32 ei_lba, bool unmap, bool ndob) { + int ret; unsigned long iflags; unsigned long long i; - int ret; - u64 lba_off; + u32 lb_size = sdebug_sector_size; + u64 block, lbaa; + u8 *fs1p; ret = check_device_access_params(scp, lba, num); if (ret) @@ -3276,31 +3278,30 @@ static int resp_write_same(struct scsi_cmnd *scp, u64 lba, u32 num, unmap_region(lba, num); goto out; } - - lba_off = lba * sdebug_sector_size; + lbaa = lba; + block = do_div(lbaa, sdebug_store_sectors); /* if ndob then zero 1 logical block, else fetch 1 logical block */ + fs1p = fake_storep + (block * lb_size); if (ndob) { - memset(fake_storep + lba_off, 0, sdebug_sector_size); + memset(fs1p, 0, lb_size); ret = 0; } else - ret = fetch_to_dev_buffer(scp, fake_storep + lba_off, - sdebug_sector_size); + ret = fetch_to_dev_buffer(scp, fs1p, lb_size); if (-1 == ret) { write_unlock_irqrestore(&atomic_rw, iflags); return DID_ERROR << 16; - } else if (sdebug_verbose && !ndob && (ret < sdebug_sector_size)) + } else if (sdebug_verbose && !ndob && (ret < lb_size)) sdev_printk(KERN_INFO, scp->device, "%s: %s: lb size=%u, IO sent=%d bytes\n", - my_name, "write same", - sdebug_sector_size, ret); + my_name, "write same", lb_size, ret); /* Copy first sector to remaining blocks */ - for (i = 1 ; i < num ; i++) - memcpy(fake_storep + ((lba + i) * sdebug_sector_size), - fake_storep + lba_off, - sdebug_sector_size); - + for (i = 1 ; i < num ; i++) { + lbaa = lba + i; + block = do_div(lbaa, sdebug_store_sectors); + memmove(fake_storep + (block * lb_size), fs1p, lb_size); + } if (scsi_debug_lbp()) map_region(lba, num); out: diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index 83365b29a4d8..fff86940388b 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -462,12 +462,16 @@ int sd_zbc_read_zones(struct scsi_disk *sdkp, unsigned char *buf) sdkp->device->use_10_for_rw = 0; /* - * If something changed, revalidate the disk zone bitmaps once we have - * the capacity, that is on the second revalidate execution during disk - * scan and always during normal revalidate. + * Revalidate the disk zone bitmaps once the block device capacity is + * set on the second revalidate execution during disk scan and if + * something changed when executing a normal revalidate. */ - if (sdkp->first_scan) + if (sdkp->first_scan) { + sdkp->zone_blocks = zone_blocks; + sdkp->nr_zones = nr_zones; return 0; + } + if (sdkp->zone_blocks != zone_blocks || sdkp->nr_zones != nr_zones || disk->queue->nr_zones != nr_zones) { diff --git a/drivers/soc/fsl/qbman/qman.c b/drivers/soc/fsl/qbman/qman.c index 52c153cd795a..636f83f781f5 100644 --- a/drivers/soc/fsl/qbman/qman.c +++ b/drivers/soc/fsl/qbman/qman.c @@ -1143,18 +1143,19 @@ static void qm_mr_process_task(struct work_struct *work); static irqreturn_t portal_isr(int irq, void *ptr) { struct qman_portal *p = ptr; - - u32 clear = QM_DQAVAIL_MASK | p->irq_sources; u32 is = qm_in(&p->p, QM_REG_ISR) & p->irq_sources; + u32 clear = 0; if (unlikely(!is)) return IRQ_NONE; /* DQRR-handling if it's interrupt-driven */ - if (is & QM_PIRQ_DQRI) + if (is & QM_PIRQ_DQRI) { __poll_portal_fast(p, QMAN_POLL_LIMIT); + clear = QM_DQAVAIL_MASK | QM_PIRQ_DQRI; + } /* Handling of anything else that's interrupt-driven */ - clear |= __poll_portal_slow(p, is); + clear |= __poll_portal_slow(p, is) & QM_PIRQ_SLOW; qm_out(&p->p, QM_REG_ISR, clear); return IRQ_HANDLED; } diff --git a/drivers/staging/fsl-dpaa2/ethsw/ethsw.c b/drivers/staging/fsl-dpaa2/ethsw/ethsw.c index daabaceeea52..1b3943b71254 100644 --- a/drivers/staging/fsl-dpaa2/ethsw/ethsw.c +++ b/drivers/staging/fsl-dpaa2/ethsw/ethsw.c @@ -505,6 +505,17 @@ static netdev_tx_t port_dropframe(struct sk_buff *skb, return NETDEV_TX_OK; } +static int swdev_get_port_parent_id(struct net_device *dev, + struct netdev_phys_item_id *ppid) +{ + struct ethsw_port_priv *port_priv = netdev_priv(dev); + + ppid->id_len = 1; + ppid->id[0] = port_priv->ethsw_data->dev_id; + + return 0; +} + static const struct net_device_ops ethsw_port_ops = { .ndo_open = port_open, .ndo_stop = port_stop, @@ -515,6 +526,7 @@ static const struct net_device_ops ethsw_port_ops = { .ndo_get_offload_stats = port_get_offload_stats, .ndo_start_xmit = port_dropframe, + .ndo_get_port_parent_id = swdev_get_port_parent_id, }; static void ethsw_links_state_update(struct ethsw_core *ethsw) @@ -631,18 +643,7 @@ static void ethsw_teardown_irqs(struct fsl_mc_device *sw_dev) static int swdev_port_attr_get(struct net_device *netdev, struct switchdev_attr *attr) { - struct ethsw_port_priv *port_priv = netdev_priv(netdev); - switch (attr->id) { - case SWITCHDEV_ATTR_ID_PORT_PARENT_ID: - attr->u.ppid.id_len = 1; - attr->u.ppid.id[0] = port_priv->ethsw_data->dev_id; - break; - case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS: - attr->u.brport_flags = - (port_priv->ethsw_data->learning ? BR_LEARNING : 0) | - (port_priv->flood ? BR_FLOOD : 0); - break; case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT: attr->u.brport_flags_support = BR_LEARNING | BR_FLOOD; break; diff --git a/drivers/staging/octeon/ethernet-mdio.c b/drivers/staging/octeon/ethernet-mdio.c index 2848fa71a33d..d6248eecf123 100644 --- a/drivers/staging/octeon/ethernet-mdio.c +++ b/drivers/staging/octeon/ethernet-mdio.c @@ -170,7 +170,7 @@ int cvm_oct_phy_setup_device(struct net_device *dev) return -ENODEV; priv->last_link = 0; - phy_start_aneg(phydev); + phy_start(phydev); return 0; no_phy: diff --git a/drivers/staging/speakup/spk_ttyio.c b/drivers/staging/speakup/spk_ttyio.c index c92bbd05516e..005de0024dd4 100644 --- a/drivers/staging/speakup/spk_ttyio.c +++ b/drivers/staging/speakup/spk_ttyio.c @@ -265,7 +265,8 @@ static void spk_ttyio_send_xchar(char ch) return; } - speakup_tty->ops->send_xchar(speakup_tty, ch); + if (speakup_tty->ops->send_xchar) + speakup_tty->ops->send_xchar(speakup_tty, ch); mutex_unlock(&speakup_tty_mutex); } @@ -277,7 +278,8 @@ static void spk_ttyio_tiocmset(unsigned int set, unsigned int clear) return; } - speakup_tty->ops->tiocmset(speakup_tty, set, clear); + if (speakup_tty->ops->tiocmset) + speakup_tty->ops->tiocmset(speakup_tty, set, clear); mutex_unlock(&speakup_tty_mutex); } diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c index 72016d0dfca5..8e7fffbb8802 100644 --- a/drivers/target/target_core_configfs.c +++ b/drivers/target/target_core_configfs.c @@ -852,6 +852,12 @@ static ssize_t pi_prot_type_store(struct config_item *item, return count; } +/* always zero, but attr needs to remain RW to avoid userspace breakage */ +static ssize_t pi_prot_format_show(struct config_item *item, char *page) +{ + return snprintf(page, PAGE_SIZE, "0\n"); +} + static ssize_t pi_prot_format_store(struct config_item *item, const char *page, size_t count) { @@ -1132,7 +1138,7 @@ CONFIGFS_ATTR(, emulate_3pc); CONFIGFS_ATTR(, emulate_pr); CONFIGFS_ATTR(, pi_prot_type); CONFIGFS_ATTR_RO(, hw_pi_prot_type); -CONFIGFS_ATTR_WO(, pi_prot_format); +CONFIGFS_ATTR(, pi_prot_format); CONFIGFS_ATTR(, pi_prot_verify); CONFIGFS_ATTR(, enforce_pr_isids); CONFIGFS_ATTR(, is_nonrot); diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c index dfd23245f778..6fff16113628 100644 --- a/drivers/thermal/cpu_cooling.c +++ b/drivers/thermal/cpu_cooling.c @@ -774,7 +774,7 @@ of_cpufreq_cooling_register(struct cpufreq_policy *policy) cdev = __cpufreq_cooling_register(np, policy, capacitance); if (IS_ERR(cdev)) { - pr_err("cpu_cooling: cpu%d is not running as cooling device: %ld\n", + pr_err("cpu_cooling: cpu%d failed to register as cooling device: %ld\n", policy->cpu, PTR_ERR(cdev)); cdev = NULL; } diff --git a/drivers/thermal/of-thermal.c b/drivers/thermal/of-thermal.c index 4bfdb4a1e47d..2df059cc07e2 100644 --- a/drivers/thermal/of-thermal.c +++ b/drivers/thermal/of-thermal.c @@ -867,14 +867,14 @@ __init *thermal_of_build_thermal_zone(struct device_node *np) ret = of_property_read_u32(np, "polling-delay-passive", &prop); if (ret < 0) { - pr_err("missing polling-delay-passive property\n"); + pr_err("%pOFn: missing polling-delay-passive property\n", np); goto free_tz; } tz->passive_delay = prop; ret = of_property_read_u32(np, "polling-delay", &prop); if (ret < 0) { - pr_err("missing polling-delay property\n"); + pr_err("%pOFn: missing polling-delay property\n", np); goto free_tz; } tz->polling_delay = prop; diff --git a/drivers/tty/serial/8250/8250_mtk.c b/drivers/tty/serial/8250/8250_mtk.c index e2c407656fa6..c1fdbc0b6840 100644 --- a/drivers/tty/serial/8250/8250_mtk.c +++ b/drivers/tty/serial/8250/8250_mtk.c @@ -357,6 +357,9 @@ static int mtk8250_probe_of(struct platform_device *pdev, struct uart_port *p, if (dmacnt == 2) { data->dma = devm_kzalloc(&pdev->dev, sizeof(*data->dma), GFP_KERNEL); + if (!data->dma) + return -ENOMEM; + data->dma->fn = mtk8250_dma_filter; data->dma->rx_size = MTK_UART_RX_SIZE; data->dma->rxconf.src_maxburst = MTK_UART_RX_TRIGGER; diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c index f80a300b5d68..48bd694a5fa1 100644 --- a/drivers/tty/serial/8250/8250_pci.c +++ b/drivers/tty/serial/8250/8250_pci.c @@ -3420,6 +3420,11 @@ static int serial_pci_guess_board(struct pci_dev *dev, struct pciserial_board *board) { int num_iomem, num_port, first_port = -1, i; + int rc; + + rc = serial_pci_is_class_communication(dev); + if (rc) + return rc; /* * Should we try to make guesses for multiport serial devices later? @@ -3647,10 +3652,6 @@ pciserial_init_one(struct pci_dev *dev, const struct pci_device_id *ent) board = &pci_boards[ent->driver_data]; - rc = serial_pci_is_class_communication(dev); - if (rc) - return rc; - rc = serial_pci_is_blacklisted(dev); if (rc) return rc; diff --git a/drivers/tty/serial/earlycon-riscv-sbi.c b/drivers/tty/serial/earlycon-riscv-sbi.c index e1a551aae336..ce81523c3113 100644 --- a/drivers/tty/serial/earlycon-riscv-sbi.c +++ b/drivers/tty/serial/earlycon-riscv-sbi.c @@ -10,13 +10,16 @@ #include <linux/serial_core.h> #include <asm/sbi.h> -static void sbi_console_write(struct console *con, - const char *s, unsigned int n) +static void sbi_putc(struct uart_port *port, int c) { - int i; + sbi_console_putchar(c); +} - for (i = 0; i < n; ++i) - sbi_console_putchar(s[i]); +static void sbi_console_write(struct console *con, + const char *s, unsigned n) +{ + struct earlycon_device *dev = con->data; + uart_console_write(&dev->port, s, n, sbi_putc); } static int __init early_sbi_setup(struct earlycon_device *device, diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 5c01bb6d1c24..556f50aa1b58 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -130,6 +130,9 @@ static void uart_start(struct tty_struct *tty) struct uart_port *port; unsigned long flags; + if (!state) + return; + port = uart_port_lock(state, flags); __uart_start(tty); uart_port_unlock(port, flags); @@ -727,6 +730,9 @@ static void uart_unthrottle(struct tty_struct *tty) upstat_t mask = UPSTAT_SYNC_FIFO; struct uart_port *port; + if (!state) + return; + port = uart_port_ref(state); if (!port) return; diff --git a/drivers/tty/serial/sh-sci.c b/drivers/tty/serial/sh-sci.c index 8df0fd824520..64bbeb7d7e0c 100644 --- a/drivers/tty/serial/sh-sci.c +++ b/drivers/tty/serial/sh-sci.c @@ -1921,7 +1921,7 @@ out_nomem: static void sci_free_irq(struct sci_port *port) { - int i; + int i, j; /* * Intentionally in reverse order so we iterate over the muxed @@ -1937,6 +1937,13 @@ static void sci_free_irq(struct sci_port *port) if (unlikely(irq < 0)) continue; + /* Check if already freed (irq was muxed) */ + for (j = 0; j < i; j++) + if (port->irqs[j] == irq) + j = i + 1; + if (j > i) + continue; + free_irq(port->irqs[i], port); kfree(port->irqstr[i]); diff --git a/drivers/usb/dwc3/dwc3-exynos.c b/drivers/usb/dwc3/dwc3-exynos.c index cb7fcd7c0ad8..c1e9ea621f41 100644 --- a/drivers/usb/dwc3/dwc3-exynos.c +++ b/drivers/usb/dwc3/dwc3-exynos.c @@ -78,7 +78,7 @@ static int dwc3_exynos_probe(struct platform_device *pdev) for (i = 0; i < exynos->num_clks; i++) { ret = clk_prepare_enable(exynos->clks[i]); if (ret) { - while (--i > 0) + while (i-- > 0) clk_disable_unprepare(exynos->clks[i]); return ret; } @@ -223,7 +223,7 @@ static int dwc3_exynos_resume(struct device *dev) for (i = 0; i < exynos->num_clks; i++) { ret = clk_prepare_enable(exynos->clks[i]); if (ret) { - while (--i > 0) + while (i-- > 0) clk_disable_unprepare(exynos->clks[i]); return ret; } diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index bed2ff42780b..6c9b76bcc2e1 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -1119,7 +1119,7 @@ static void dwc3_prepare_one_trb_linear(struct dwc3_ep *dep, unsigned int maxp = usb_endpoint_maxp(dep->endpoint.desc); unsigned int rem = length % maxp; - if (rem && usb_endpoint_dir_out(dep->endpoint.desc)) { + if ((!length || rem) && usb_endpoint_dir_out(dep->endpoint.desc)) { struct dwc3 *dwc = dep->dwc; struct dwc3_trb *trb; diff --git a/drivers/usb/gadget/udc/net2272.c b/drivers/usb/gadget/udc/net2272.c index 660878a19505..b77f3126580e 100644 --- a/drivers/usb/gadget/udc/net2272.c +++ b/drivers/usb/gadget/udc/net2272.c @@ -2083,7 +2083,7 @@ static irqreturn_t net2272_irq(int irq, void *_dev) #if defined(PLX_PCI_RDK2) /* see if PCI int for us by checking irqstat */ intcsr = readl(dev->rdk2.fpga_base_addr + RDK2_IRQSTAT); - if (!intcsr & (1 << NET2272_PCI_IRQ)) { + if (!(intcsr & (1 << NET2272_PCI_IRQ))) { spin_unlock(&dev->lock); return IRQ_NONE; } diff --git a/drivers/usb/musb/musb_gadget.c b/drivers/usb/musb/musb_gadget.c index eae8b1b1b45b..ffe462a657b1 100644 --- a/drivers/usb/musb/musb_gadget.c +++ b/drivers/usb/musb/musb_gadget.c @@ -452,13 +452,10 @@ void musb_g_tx(struct musb *musb, u8 epnum) } if (request) { - u8 is_dma = 0; - bool short_packet = false; trace_musb_req_tx(req); if (dma && (csr & MUSB_TXCSR_DMAENAB)) { - is_dma = 1; csr |= MUSB_TXCSR_P_WZC_BITS; csr &= ~(MUSB_TXCSR_DMAENAB | MUSB_TXCSR_P_UNDERRUN | MUSB_TXCSR_TXPKTRDY | MUSB_TXCSR_AUTOSET); @@ -476,16 +473,8 @@ void musb_g_tx(struct musb *musb, u8 epnum) */ if ((request->zero && request->length) && (request->length % musb_ep->packet_sz == 0) - && (request->actual == request->length)) - short_packet = true; + && (request->actual == request->length)) { - if ((musb_dma_inventra(musb) || musb_dma_ux500(musb)) && - (is_dma && (!dma->desired_mode || - (request->actual & - (musb_ep->packet_sz - 1))))) - short_packet = true; - - if (short_packet) { /* * On DMA completion, FIFO may not be * available yet... diff --git a/drivers/usb/musb/musbhsdma.c b/drivers/usb/musb/musbhsdma.c index a688f7f87829..5fc6825745f2 100644 --- a/drivers/usb/musb/musbhsdma.c +++ b/drivers/usb/musb/musbhsdma.c @@ -346,12 +346,10 @@ static irqreturn_t dma_controller_irq(int irq, void *private_data) channel->status = MUSB_DMA_STATUS_FREE; /* completed */ - if ((devctl & MUSB_DEVCTL_HM) - && (musb_channel->transmit) - && ((channel->desired_mode == 0) - || (channel->actual_len & - (musb_channel->max_packet_sz - 1))) - ) { + if (musb_channel->transmit && + (!channel->desired_mode || + (channel->actual_len % + musb_channel->max_packet_sz))) { u8 epnum = musb_channel->epnum; int offset = musb->io.ep_offset(epnum, MUSB_TXCSR); @@ -363,11 +361,14 @@ static irqreturn_t dma_controller_irq(int irq, void *private_data) */ musb_ep_select(mbase, epnum); txcsr = musb_readw(mbase, offset); - txcsr &= ~(MUSB_TXCSR_DMAENAB + if (channel->desired_mode == 1) { + txcsr &= ~(MUSB_TXCSR_DMAENAB | MUSB_TXCSR_AUTOSET); - musb_writew(mbase, offset, txcsr); - /* Send out the packet */ - txcsr &= ~MUSB_TXCSR_DMAMODE; + musb_writew(mbase, offset, txcsr); + /* Send out the packet */ + txcsr &= ~MUSB_TXCSR_DMAMODE; + txcsr |= MUSB_TXCSR_DMAENAB; + } txcsr |= MUSB_TXCSR_TXPKTRDY; musb_writew(mbase, offset, txcsr); } diff --git a/drivers/usb/phy/Kconfig b/drivers/usb/phy/Kconfig index d7312eed6088..91ea3083e7ad 100644 --- a/drivers/usb/phy/Kconfig +++ b/drivers/usb/phy/Kconfig @@ -21,7 +21,7 @@ config AB8500_USB config FSL_USB2_OTG bool "Freescale USB OTG Transceiver Driver" - depends on USB_EHCI_FSL && USB_FSL_USB2 && USB_OTG_FSM && PM + depends on USB_EHCI_FSL && USB_FSL_USB2 && USB_OTG_FSM=y && PM depends on USB_GADGET || !USB_GADGET # if USB_GADGET=m, this can't be 'y' select USB_PHY help diff --git a/drivers/usb/phy/phy-am335x.c b/drivers/usb/phy/phy-am335x.c index 27bdb7222527..f5f0568d8533 100644 --- a/drivers/usb/phy/phy-am335x.c +++ b/drivers/usb/phy/phy-am335x.c @@ -61,9 +61,6 @@ static int am335x_phy_probe(struct platform_device *pdev) if (ret) return ret; - ret = usb_add_phy_dev(&am_phy->usb_phy_gen.phy); - if (ret) - return ret; am_phy->usb_phy_gen.phy.init = am335x_init; am_phy->usb_phy_gen.phy.shutdown = am335x_shutdown; @@ -82,7 +79,7 @@ static int am335x_phy_probe(struct platform_device *pdev) device_set_wakeup_enable(dev, false); phy_ctrl_power(am_phy->phy_ctrl, am_phy->id, am_phy->dr_mode, false); - return 0; + return usb_add_phy_dev(&am_phy->usb_phy_gen.phy); } static int am335x_phy_remove(struct platform_device *pdev) diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index 4bc29b586698..f1c39a3c7534 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -2297,7 +2297,8 @@ static unsigned int tcpm_pd_select_pps_apdo(struct tcpm_port *port) pdo_pps_apdo_max_voltage(snk)); port->pps_data.max_curr = min_pps_apdo_current(src, snk); port->pps_data.out_volt = min(port->pps_data.max_volt, - port->pps_data.out_volt); + max(port->pps_data.min_volt, + port->pps_data.out_volt)); port->pps_data.op_curr = min(port->pps_data.max_curr, port->pps_data.op_curr); } diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index bca86bf7189f..df51a35cf537 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -1337,7 +1337,8 @@ static int vhost_net_open(struct inode *inode, struct file *f) n->vqs[i].rx_ring = NULL; vhost_net_buf_init(&n->vqs[i].rxq); } - vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX); + vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX, + UIO_MAXIOV + VHOST_NET_BATCH); vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, EPOLLOUT, dev); vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, EPOLLIN, dev); diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 344684f3e2e4..23593cb23dd0 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -1627,7 +1627,7 @@ static int vhost_scsi_open(struct inode *inode, struct file *f) vqs[i] = &vs->vqs[i].vq; vs->vqs[i].vq.handle_kick = vhost_scsi_handle_kick; } - vhost_dev_init(&vs->dev, vqs, VHOST_SCSI_MAX_VQ); + vhost_dev_init(&vs->dev, vqs, VHOST_SCSI_MAX_VQ, UIO_MAXIOV); vhost_scsi_init_inflight(vs, NULL); diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 15a216cdd507..24a129fcdd61 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -390,9 +390,9 @@ static long vhost_dev_alloc_iovecs(struct vhost_dev *dev) vq->indirect = kmalloc_array(UIO_MAXIOV, sizeof(*vq->indirect), GFP_KERNEL); - vq->log = kmalloc_array(UIO_MAXIOV, sizeof(*vq->log), + vq->log = kmalloc_array(dev->iov_limit, sizeof(*vq->log), GFP_KERNEL); - vq->heads = kmalloc_array(UIO_MAXIOV, sizeof(*vq->heads), + vq->heads = kmalloc_array(dev->iov_limit, sizeof(*vq->heads), GFP_KERNEL); if (!vq->indirect || !vq->log || !vq->heads) goto err_nomem; @@ -414,7 +414,7 @@ static void vhost_dev_free_iovecs(struct vhost_dev *dev) } void vhost_dev_init(struct vhost_dev *dev, - struct vhost_virtqueue **vqs, int nvqs) + struct vhost_virtqueue **vqs, int nvqs, int iov_limit) { struct vhost_virtqueue *vq; int i; @@ -427,6 +427,7 @@ void vhost_dev_init(struct vhost_dev *dev, dev->iotlb = NULL; dev->mm = NULL; dev->worker = NULL; + dev->iov_limit = iov_limit; init_llist_head(&dev->work_list); init_waitqueue_head(&dev->wait); INIT_LIST_HEAD(&dev->read_list); diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h index 1b675dad5e05..9490e7ddb340 100644 --- a/drivers/vhost/vhost.h +++ b/drivers/vhost/vhost.h @@ -170,9 +170,11 @@ struct vhost_dev { struct list_head read_list; struct list_head pending_list; wait_queue_head_t wait; + int iov_limit; }; -void vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue **vqs, int nvqs); +void vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue **vqs, + int nvqs, int iov_limit); long vhost_dev_set_owner(struct vhost_dev *dev); bool vhost_dev_has_owner(struct vhost_dev *dev); long vhost_dev_check_owner(struct vhost_dev *); diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 3fbc068eaa9b..bb5fc0e9fbc2 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -531,7 +531,7 @@ static int vhost_vsock_dev_open(struct inode *inode, struct file *file) vsock->vqs[VSOCK_VQ_TX].handle_kick = vhost_vsock_handle_tx_kick; vsock->vqs[VSOCK_VQ_RX].handle_kick = vhost_vsock_handle_rx_kick; - vhost_dev_init(&vsock->dev, vqs, ARRAY_SIZE(vsock->vqs)); + vhost_dev_init(&vsock->dev, vqs, ARRAY_SIZE(vsock->vqs), UIO_MAXIOV); file->private_data = vsock; spin_lock_init(&vsock->send_pkt_list_lock); diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index cd7e755484e3..a0b07c331255 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -152,7 +152,12 @@ struct vring_virtqueue { /* Available for packed ring */ struct { /* Actual memory layout for this queue. */ - struct vring_packed vring; + struct { + unsigned int num; + struct vring_packed_desc *desc; + struct vring_packed_desc_event *driver; + struct vring_packed_desc_event *device; + } vring; /* Driver ring wrap counter. */ bool avail_wrap_counter; @@ -1609,6 +1614,9 @@ static struct virtqueue *vring_create_virtqueue_packed( !context; vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX); + if (virtio_has_feature(vdev, VIRTIO_F_ORDER_PLATFORM)) + vq->weak_barriers = false; + vq->packed.ring_dma_addr = ring_dma_addr; vq->packed.driver_event_dma_addr = driver_event_dma_addr; vq->packed.device_event_dma_addr = device_event_dma_addr; @@ -2079,6 +2087,9 @@ struct virtqueue *__vring_new_virtqueue(unsigned int index, !context; vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX); + if (virtio_has_feature(vdev, VIRTIO_F_ORDER_PLATFORM)) + vq->weak_barriers = false; + vq->split.queue_dma_addr = 0; vq->split.queue_size_in_bytes = 0; @@ -2213,6 +2224,8 @@ void vring_transport_features(struct virtio_device *vdev) break; case VIRTIO_F_RING_PACKED: break; + case VIRTIO_F_ORDER_PLATFORM: + break; default: /* We don't understand this bit. */ __virtio_clear_bit(vdev, i); @@ -1436,6 +1436,7 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) if (unlikely(!req->ki_filp)) return -EBADF; req->ki_complete = aio_complete_rw; + req->private = NULL; req->ki_pos = iocb->aio_offset; req->ki_flags = iocb_flags(req->ki_filp); if (iocb->aio_flags & IOCB_FLAG_RESFD) diff --git a/fs/autofs/expire.c b/fs/autofs/expire.c index d441244b79df..28d9c2b1b3bb 100644 --- a/fs/autofs/expire.c +++ b/fs/autofs/expire.c @@ -596,7 +596,6 @@ int autofs_expire_run(struct super_block *sb, pkt.len = dentry->d_name.len; memcpy(pkt.name, dentry->d_name.name, pkt.len); pkt.name[pkt.len] = '\0'; - dput(dentry); if (copy_to_user(pkt_p, &pkt, sizeof(struct autofs_packet_expire))) ret = -EFAULT; @@ -609,6 +608,8 @@ int autofs_expire_run(struct super_block *sb, complete_all(&ino->expire_complete); spin_unlock(&sbi->fs_lock); + dput(dentry); + return ret; } diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c index 0e8ea2d9a2bb..078992eee299 100644 --- a/fs/autofs/inode.c +++ b/fs/autofs/inode.c @@ -266,8 +266,10 @@ int autofs_fill_super(struct super_block *s, void *data, int silent) } root_inode = autofs_get_inode(s, S_IFDIR | 0755); root = d_make_root(root_inode); - if (!root) + if (!root) { + ret = -ENOMEM; goto fail_ino; + } pipe = NULL; root->d_fsdata = ino; diff --git a/fs/binfmt_script.c b/fs/binfmt_script.c index d0078cbb718b..7cde3f46ad26 100644 --- a/fs/binfmt_script.c +++ b/fs/binfmt_script.c @@ -42,14 +42,10 @@ static int load_script(struct linux_binprm *bprm) fput(bprm->file); bprm->file = NULL; - for (cp = bprm->buf+2;; cp++) { - if (cp >= bprm->buf + BINPRM_BUF_SIZE) - return -ENOEXEC; - if (!*cp || (*cp == '\n')) - break; - } + bprm->buf[BINPRM_BUF_SIZE - 1] = '\0'; + if ((cp = strchr(bprm->buf, '\n')) == NULL) + cp = bprm->buf+BINPRM_BUF_SIZE-1; *cp = '\0'; - while (cp > bprm->buf) { cp--; if ((*cp == ' ') || (*cp == '\t')) diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index f64aad613727..5a6c39b44c84 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -968,6 +968,48 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, return 0; } +static struct extent_buffer *alloc_tree_block_no_bg_flush( + struct btrfs_trans_handle *trans, + struct btrfs_root *root, + u64 parent_start, + const struct btrfs_disk_key *disk_key, + int level, + u64 hint, + u64 empty_size) +{ + struct btrfs_fs_info *fs_info = root->fs_info; + struct extent_buffer *ret; + + /* + * If we are COWing a node/leaf from the extent, chunk, device or free + * space trees, make sure that we do not finish block group creation of + * pending block groups. We do this to avoid a deadlock. + * COWing can result in allocation of a new chunk, and flushing pending + * block groups (btrfs_create_pending_block_groups()) can be triggered + * when finishing allocation of a new chunk. Creation of a pending block + * group modifies the extent, chunk, device and free space trees, + * therefore we could deadlock with ourselves since we are holding a + * lock on an extent buffer that btrfs_create_pending_block_groups() may + * try to COW later. + * For similar reasons, we also need to delay flushing pending block + * groups when splitting a leaf or node, from one of those trees, since + * we are holding a write lock on it and its parent or when inserting a + * new root node for one of those trees. + */ + if (root == fs_info->extent_root || + root == fs_info->chunk_root || + root == fs_info->dev_root || + root == fs_info->free_space_root) + trans->can_flush_pending_bgs = false; + + ret = btrfs_alloc_tree_block(trans, root, parent_start, + root->root_key.objectid, disk_key, level, + hint, empty_size); + trans->can_flush_pending_bgs = true; + + return ret; +} + /* * does the dirty work in cow of a single block. The parent block (if * supplied) is updated to point to the new cow copy. The new buffer is marked @@ -1015,28 +1057,8 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, if ((root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) && parent) parent_start = parent->start; - /* - * If we are COWing a node/leaf from the extent, chunk, device or free - * space trees, make sure that we do not finish block group creation of - * pending block groups. We do this to avoid a deadlock. - * COWing can result in allocation of a new chunk, and flushing pending - * block groups (btrfs_create_pending_block_groups()) can be triggered - * when finishing allocation of a new chunk. Creation of a pending block - * group modifies the extent, chunk, device and free space trees, - * therefore we could deadlock with ourselves since we are holding a - * lock on an extent buffer that btrfs_create_pending_block_groups() may - * try to COW later. - */ - if (root == fs_info->extent_root || - root == fs_info->chunk_root || - root == fs_info->dev_root || - root == fs_info->free_space_root) - trans->can_flush_pending_bgs = false; - - cow = btrfs_alloc_tree_block(trans, root, parent_start, - root->root_key.objectid, &disk_key, level, - search_start, empty_size); - trans->can_flush_pending_bgs = true; + cow = alloc_tree_block_no_bg_flush(trans, root, parent_start, &disk_key, + level, search_start, empty_size); if (IS_ERR(cow)) return PTR_ERR(cow); @@ -3345,8 +3367,8 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans, else btrfs_node_key(lower, &lower_key, 0); - c = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid, - &lower_key, level, root->node->start, 0); + c = alloc_tree_block_no_bg_flush(trans, root, 0, &lower_key, level, + root->node->start, 0); if (IS_ERR(c)) return PTR_ERR(c); @@ -3475,8 +3497,8 @@ static noinline int split_node(struct btrfs_trans_handle *trans, mid = (c_nritems + 1) / 2; btrfs_node_key(c, &disk_key, mid); - split = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid, - &disk_key, level, c->start, 0); + split = alloc_tree_block_no_bg_flush(trans, root, 0, &disk_key, level, + c->start, 0); if (IS_ERR(split)) return PTR_ERR(split); @@ -4260,8 +4282,8 @@ again: else btrfs_item_key(l, &disk_key, mid); - right = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid, - &disk_key, 0, l->start, 0); + right = alloc_tree_block_no_bg_flush(trans, root, 0, &disk_key, 0, + l->start, 0); if (IS_ERR(right)) return PTR_ERR(right); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index c5586ffd1426..0a3f122dd61f 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1621,6 +1621,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, flags | SB_RDONLY, device_name, data); if (IS_ERR(mnt_root)) { root = ERR_CAST(mnt_root); + kfree(subvol_name); goto out; } @@ -1630,12 +1631,14 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, if (error < 0) { root = ERR_PTR(error); mntput(mnt_root); + kfree(subvol_name); goto out; } } } if (IS_ERR(mnt_root)) { root = ERR_CAST(mnt_root); + kfree(subvol_name); goto out; } diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 127fa1535f58..4ec2b660d014 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -850,14 +850,6 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans, btrfs_trans_release_chunk_metadata(trans); - if (lock && should_end_transaction(trans) && - READ_ONCE(cur_trans->state) == TRANS_STATE_RUNNING) { - spin_lock(&info->trans_lock); - if (cur_trans->state == TRANS_STATE_RUNNING) - cur_trans->state = TRANS_STATE_BLOCKED; - spin_unlock(&info->trans_lock); - } - if (lock && READ_ONCE(cur_trans->state) == TRANS_STATE_BLOCKED) { if (throttle) return btrfs_commit_transaction(trans); @@ -1879,6 +1871,21 @@ static void cleanup_transaction(struct btrfs_trans_handle *trans, int err) kmem_cache_free(btrfs_trans_handle_cachep, trans); } +/* + * Release reserved delayed ref space of all pending block groups of the + * transaction and remove them from the list + */ +static void btrfs_cleanup_pending_block_groups(struct btrfs_trans_handle *trans) +{ + struct btrfs_fs_info *fs_info = trans->fs_info; + struct btrfs_block_group_cache *block_group, *tmp; + + list_for_each_entry_safe(block_group, tmp, &trans->new_bgs, bg_list) { + btrfs_delayed_refs_rsv_release(fs_info, 1); + list_del_init(&block_group->bg_list); + } +} + static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info) { /* @@ -2270,6 +2277,7 @@ scrub_continue: btrfs_scrub_continue(fs_info); cleanup_transaction: btrfs_trans_release_metadata(trans); + btrfs_cleanup_pending_block_groups(trans); btrfs_trans_release_chunk_metadata(trans); trans->block_rsv = NULL; btrfs_warn(fs_info, "Skipping commit of aborted transaction."); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 3e4f8f88353e..15561926ab32 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -957,11 +957,11 @@ static noinline struct btrfs_device *device_list_add(const char *path, else fs_devices = alloc_fs_devices(disk_super->fsid, NULL); - fs_devices->fsid_change = fsid_change_in_progress; - if (IS_ERR(fs_devices)) return ERR_CAST(fs_devices); + fs_devices->fsid_change = fsid_change_in_progress; + mutex_lock(&fs_devices->device_list_mutex); list_add(&fs_devices->fs_list, &fs_uuids); diff --git a/fs/buffer.c b/fs/buffer.c index 52d024bfdbc1..48318fb74938 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -200,6 +200,7 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) struct buffer_head *head; struct page *page; int all_mapped = 1; + static DEFINE_RATELIMIT_STATE(last_warned, HZ, 1); index = block >> (PAGE_SHIFT - bd_inode->i_blkbits); page = find_get_page_flags(bd_mapping, index, FGP_ACCESSED); @@ -227,15 +228,15 @@ __find_get_block_slow(struct block_device *bdev, sector_t block) * file io on the block device and getblk. It gets dealt with * elsewhere, don't buffer_error if we had some unmapped buffers */ - if (all_mapped) { - printk("__find_get_block_slow() failed. " - "block=%llu, b_blocknr=%llu\n", - (unsigned long long)block, - (unsigned long long)bh->b_blocknr); - printk("b_state=0x%08lx, b_size=%zu\n", - bh->b_state, bh->b_size); - printk("device %pg blocksize: %d\n", bdev, - 1 << bd_inode->i_blkbits); + ratelimit_set_flags(&last_warned, RATELIMIT_MSG_ON_RELEASE); + if (all_mapped && __ratelimit(&last_warned)) { + printk("__find_get_block_slow() failed. block=%llu, " + "b_blocknr=%llu, b_state=0x%08lx, b_size=%zu, " + "device %pg blocksize: %d\n", + (unsigned long long)block, + (unsigned long long)bh->b_blocknr, + bh->b_state, bh->b_size, bdev, + 1 << bd_inode->i_blkbits); } out_unlock: spin_unlock(&bd_mapping->private_lock); diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index d1f9c2f3f575..7652551a1fc4 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -150,5 +150,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg); extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ -#define CIFS_VERSION "2.16" +#define CIFS_VERSION "2.17" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 2c7689f3998d..659ce1b92c44 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -2696,6 +2696,7 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from, rc = cifs_write_allocate_pages(wdata->pages, nr_pages); if (rc) { + kvfree(wdata->pages); kfree(wdata); add_credits_and_wake_if(server, credits, 0); break; @@ -2707,6 +2708,7 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from, if (rc) { for (i = 0; i < nr_pages; i++) put_page(wdata->pages[i]); + kvfree(wdata->pages); kfree(wdata); add_credits_and_wake_if(server, credits, 0); break; @@ -3386,8 +3388,12 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file, } rc = cifs_read_allocate_pages(rdata, npages); - if (rc) - goto error; + if (rc) { + kvfree(rdata->pages); + kfree(rdata); + add_credits_and_wake_if(server, credits, 0); + break; + } rdata->tailsz = PAGE_SIZE; } @@ -3407,7 +3413,6 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file, if (!rdata->cfile->invalidHandle || !(rc = cifs_reopen_file(rdata->cfile, true))) rc = server->ops->async_readv(rdata); -error: if (rc) { add_credits_and_wake_if(server, rdata->credits, 0); kref_put(&rdata->refcount, diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 153238fc4fa9..6f96e2292856 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -866,7 +866,9 @@ smb2_query_eas(const unsigned int xid, struct cifs_tcon *tcon, FILE_READ_EA, FILE_FULL_EA_INFORMATION, SMB2_O_INFO_FILE, - SMB2_MAX_EA_BUF, + CIFSMaxBufSize - + MAX_SMB2_CREATE_RESPONSE_SIZE - + MAX_SMB2_CLOSE_RESPONSE_SIZE, &rsp_iov, &buftype, cifs_sb); if (rc) { /* diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 2ff209ec4fab..77b3aaa39b35 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -3241,8 +3241,17 @@ smb2_readv_callback(struct mid_q_entry *mid) rdata->mr = NULL; } #endif - if (rdata->result) + if (rdata->result && rdata->result != -ENODATA) { cifs_stats_fail_inc(tcon, SMB2_READ_HE); + trace_smb3_read_err(0 /* xid */, + rdata->cfile->fid.persistent_fid, + tcon->tid, tcon->ses->Suid, rdata->offset, + rdata->bytes, rdata->result); + } else + trace_smb3_read_done(0 /* xid */, + rdata->cfile->fid.persistent_fid, + tcon->tid, tcon->ses->Suid, + rdata->offset, rdata->got_bytes); queue_work(cifsiod_wq, &rdata->work); DeleteMidQEntry(mid); @@ -3317,13 +3326,11 @@ smb2_async_readv(struct cifs_readdata *rdata) if (rc) { kref_put(&rdata->refcount, cifs_readdata_release); cifs_stats_fail_inc(io_parms.tcon, SMB2_READ_HE); - trace_smb3_read_err(rc, 0 /* xid */, io_parms.persistent_fid, - io_parms.tcon->tid, io_parms.tcon->ses->Suid, - io_parms.offset, io_parms.length); - } else - trace_smb3_read_done(0 /* xid */, io_parms.persistent_fid, - io_parms.tcon->tid, io_parms.tcon->ses->Suid, - io_parms.offset, io_parms.length); + trace_smb3_read_err(0 /* xid */, io_parms.persistent_fid, + io_parms.tcon->tid, + io_parms.tcon->ses->Suid, + io_parms.offset, io_parms.length, rc); + } cifs_small_buf_release(buf); return rc; @@ -3367,10 +3374,11 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms, if (rc != -ENODATA) { cifs_stats_fail_inc(io_parms->tcon, SMB2_READ_HE); cifs_dbg(VFS, "Send error in read = %d\n", rc); + trace_smb3_read_err(xid, req->PersistentFileId, + io_parms->tcon->tid, ses->Suid, + io_parms->offset, io_parms->length, + rc); } - trace_smb3_read_err(rc, xid, req->PersistentFileId, - io_parms->tcon->tid, ses->Suid, - io_parms->offset, io_parms->length); free_rsp_buf(resp_buftype, rsp_iov.iov_base); return rc == -ENODATA ? 0 : rc; } else @@ -3459,8 +3467,17 @@ smb2_writev_callback(struct mid_q_entry *mid) wdata->mr = NULL; } #endif - if (wdata->result) + if (wdata->result) { cifs_stats_fail_inc(tcon, SMB2_WRITE_HE); + trace_smb3_write_err(0 /* no xid */, + wdata->cfile->fid.persistent_fid, + tcon->tid, tcon->ses->Suid, wdata->offset, + wdata->bytes, wdata->result); + } else + trace_smb3_write_done(0 /* no xid */, + wdata->cfile->fid.persistent_fid, + tcon->tid, tcon->ses->Suid, + wdata->offset, wdata->bytes); queue_work(cifsiod_wq, &wdata->work); DeleteMidQEntry(mid); @@ -3602,10 +3619,7 @@ smb2_async_writev(struct cifs_writedata *wdata, wdata->bytes, rc); kref_put(&wdata->refcount, release); cifs_stats_fail_inc(tcon, SMB2_WRITE_HE); - } else - trace_smb3_write_done(0 /* no xid */, req->PersistentFileId, - tcon->tid, tcon->ses->Suid, wdata->offset, - wdata->bytes); + } async_writev_out: cifs_small_buf_release(req); @@ -3831,8 +3845,8 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon, rsp->sync_hdr.Status == STATUS_NO_MORE_FILES) { srch_inf->endOfSearch = true; rc = 0; - } - cifs_stats_fail_inc(tcon, SMB2_QUERY_DIRECTORY_HE); + } else + cifs_stats_fail_inc(tcon, SMB2_QUERY_DIRECTORY_HE); goto qdir_exit; } @@ -4427,8 +4441,8 @@ SMB2_lease_break(const unsigned int xid, struct cifs_tcon *tcon, rc = cifs_send_recv(xid, ses, &rqst, &resp_buf_type, flags, &rsp_iov); cifs_small_buf_release(req); - please_key_low = (__u64 *)req->LeaseKey; - please_key_high = (__u64 *)(req->LeaseKey+8); + please_key_low = (__u64 *)lease_key; + please_key_high = (__u64 *)(lease_key+8); if (rc) { cifs_stats_fail_inc(tcon, SMB2_OPLOCK_BREAK_HE); trace_smb3_lease_err(le32_to_cpu(lease_state), tcon->tid, diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 7a2d0a2255e6..538e2299805f 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -84,8 +84,9 @@ #define NUMBER_OF_SMB2_COMMANDS 0x0013 -/* 4 len + 52 transform hdr + 64 hdr + 56 create rsp */ -#define MAX_SMB2_HDR_SIZE 0x00b0 +/* 52 transform hdr + 64 hdr + 88 create rsp */ +#define SMB2_TRANSFORM_HEADER_SIZE 52 +#define MAX_SMB2_HDR_SIZE 204 #define SMB2_PROTO_NUMBER cpu_to_le32(0x424d53fe) #define SMB2_TRANSFORM_PROTO_NUM cpu_to_le32(0x424d53fd) @@ -648,6 +649,13 @@ struct smb2_create_req { __u8 Buffer[0]; } __packed; +/* + * Maximum size of a SMB2_CREATE response is 64 (smb2 header) + + * 88 (fixed part of create response) + 520 (path) + 150 (contexts) + + * 2 bytes of padding. + */ +#define MAX_SMB2_CREATE_RESPONSE_SIZE 824 + struct smb2_create_rsp { struct smb2_sync_hdr sync_hdr; __le16 StructureSize; /* Must be 89 */ @@ -996,6 +1004,11 @@ struct smb2_close_req { __u64 VolatileFileId; /* opaque endianness */ } __packed; +/* + * Maximum size of a SMB2_CLOSE response is 64 (smb2 header) + 60 (data) + */ +#define MAX_SMB2_CLOSE_RESPONSE_SIZE 124 + struct smb2_close_rsp { struct smb2_sync_hdr sync_hdr; __le16 StructureSize; /* 60 */ @@ -1398,8 +1411,6 @@ struct smb2_file_link_info { /* encoding of request for level 11 */ char FileName[0]; /* Name to be assigned to new link */ } __packed; /* level 11 Set */ -#define SMB2_MAX_EA_BUF 65536 - struct smb2_file_full_ea_info { /* encoding of response for level 15 */ __le32 next_entry_offset; __u8 flags; diff --git a/fs/dcache.c b/fs/dcache.c index 2593153471cf..aac41adf4743 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -119,6 +119,7 @@ struct dentry_stat_t dentry_stat = { static DEFINE_PER_CPU(long, nr_dentry); static DEFINE_PER_CPU(long, nr_dentry_unused); +static DEFINE_PER_CPU(long, nr_dentry_negative); #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) @@ -152,11 +153,22 @@ static long get_nr_dentry_unused(void) return sum < 0 ? 0 : sum; } +static long get_nr_dentry_negative(void) +{ + int i; + long sum = 0; + + for_each_possible_cpu(i) + sum += per_cpu(nr_dentry_negative, i); + return sum < 0 ? 0 : sum; +} + int proc_nr_dentry(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { dentry_stat.nr_dentry = get_nr_dentry(); dentry_stat.nr_unused = get_nr_dentry_unused(); + dentry_stat.nr_negative = get_nr_dentry_negative(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } #endif @@ -317,6 +329,8 @@ static inline void __d_clear_type_and_inode(struct dentry *dentry) flags &= ~(DCACHE_ENTRY_TYPE | DCACHE_FALLTHRU); WRITE_ONCE(dentry->d_flags, flags); dentry->d_inode = NULL; + if (dentry->d_flags & DCACHE_LRU_LIST) + this_cpu_inc(nr_dentry_negative); } static void dentry_free(struct dentry *dentry) @@ -371,6 +385,11 @@ static void dentry_unlink_inode(struct dentry * dentry) * The per-cpu "nr_dentry_unused" counters are updated with * the DCACHE_LRU_LIST bit. * + * The per-cpu "nr_dentry_negative" counters are only updated + * when deleted from or added to the per-superblock LRU list, not + * from/to the shrink list. That is to avoid an unneeded dec/inc + * pair when moving from LRU to shrink list in select_collect(). + * * These helper functions make sure we always follow the * rules. d_lock must be held by the caller. */ @@ -380,6 +399,8 @@ static void d_lru_add(struct dentry *dentry) D_FLAG_VERIFY(dentry, 0); dentry->d_flags |= DCACHE_LRU_LIST; this_cpu_inc(nr_dentry_unused); + if (d_is_negative(dentry)) + this_cpu_inc(nr_dentry_negative); WARN_ON_ONCE(!list_lru_add(&dentry->d_sb->s_dentry_lru, &dentry->d_lru)); } @@ -388,6 +409,8 @@ static void d_lru_del(struct dentry *dentry) D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags &= ~DCACHE_LRU_LIST; this_cpu_dec(nr_dentry_unused); + if (d_is_negative(dentry)) + this_cpu_dec(nr_dentry_negative); WARN_ON_ONCE(!list_lru_del(&dentry->d_sb->s_dentry_lru, &dentry->d_lru)); } @@ -418,6 +441,8 @@ static void d_lru_isolate(struct list_lru_one *lru, struct dentry *dentry) D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags &= ~DCACHE_LRU_LIST; this_cpu_dec(nr_dentry_unused); + if (d_is_negative(dentry)) + this_cpu_dec(nr_dentry_negative); list_lru_isolate(lru, &dentry->d_lru); } @@ -426,6 +451,8 @@ static void d_lru_shrink_move(struct list_lru_one *lru, struct dentry *dentry, { D_FLAG_VERIFY(dentry, DCACHE_LRU_LIST); dentry->d_flags |= DCACHE_SHRINK_LIST; + if (d_is_negative(dentry)) + this_cpu_dec(nr_dentry_negative); list_lru_isolate_move(lru, &dentry->d_lru, list); } @@ -1188,15 +1215,11 @@ static enum lru_status dentry_lru_isolate_shrink(struct list_head *item, */ void shrink_dcache_sb(struct super_block *sb) { - long freed; - do { LIST_HEAD(dispose); - freed = list_lru_walk(&sb->s_dentry_lru, + list_lru_walk(&sb->s_dentry_lru, dentry_lru_isolate_shrink, &dispose, 1024); - - this_cpu_sub(nr_dentry_unused, freed); shrink_dentry_list(&dispose); } while (list_lru_count(&sb->s_dentry_lru) > 0); } @@ -1820,6 +1843,11 @@ static void __d_instantiate(struct dentry *dentry, struct inode *inode) WARN_ON(d_in_lookup(dentry)); spin_lock(&dentry->d_lock); + /* + * Decrement negative dentry count if it was in the LRU list. + */ + if (dentry->d_flags & DCACHE_LRU_LIST) + this_cpu_dec(nr_dentry_negative); hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry); raw_write_seqcount_begin(&dentry->d_seq); __d_set_inode_and_type(dentry, inode, add_flags); diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 13b01351dd1c..29c68c5d44d5 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -324,7 +324,7 @@ static struct dentry *failed_creating(struct dentry *dentry) inode_unlock(d_inode(dentry->d_parent)); dput(dentry); simple_release_fs(&debugfs_mount, &debugfs_mount_count); - return NULL; + return ERR_PTR(-ENOMEM); } static struct dentry *end_creating(struct dentry *dentry) @@ -347,7 +347,7 @@ static struct dentry *__debugfs_create_file(const char *name, umode_t mode, dentry = start_creating(name, parent); if (IS_ERR(dentry)) - return NULL; + return dentry; inode = debugfs_get_inode(dentry->d_sb); if (unlikely(!inode)) @@ -386,7 +386,8 @@ static struct dentry *__debugfs_create_file(const char *name, umode_t mode, * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, - * you are responsible here.) If an error occurs, %NULL will be returned. + * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be + * returned. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. @@ -464,7 +465,8 @@ EXPORT_SYMBOL_GPL(debugfs_create_file_unsafe); * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, - * you are responsible here.) If an error occurs, %NULL will be returned. + * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be + * returned. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. @@ -495,7 +497,8 @@ EXPORT_SYMBOL_GPL(debugfs_create_file_size); * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, - * you are responsible here.) If an error occurs, %NULL will be returned. + * you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) will be + * returned. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. @@ -506,7 +509,7 @@ struct dentry *debugfs_create_dir(const char *name, struct dentry *parent) struct inode *inode; if (IS_ERR(dentry)) - return NULL; + return dentry; inode = debugfs_get_inode(dentry->d_sb); if (unlikely(!inode)) @@ -545,7 +548,7 @@ struct dentry *debugfs_create_automount(const char *name, struct inode *inode; if (IS_ERR(dentry)) - return NULL; + return dentry; inode = debugfs_get_inode(dentry->d_sb); if (unlikely(!inode)) @@ -581,8 +584,8 @@ EXPORT_SYMBOL(debugfs_create_automount); * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the symbolic * link is to be removed (no automatic cleanup happens if your module is - * unloaded, you are responsible here.) If an error occurs, %NULL will be - * returned. + * unloaded, you are responsible here.) If an error occurs, %ERR_PTR(-ERROR) + * will be returned. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. @@ -594,12 +597,12 @@ struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent, struct inode *inode; char *link = kstrdup(target, GFP_KERNEL); if (!link) - return NULL; + return ERR_PTR(-ENOMEM); dentry = start_creating(name, parent); if (IS_ERR(dentry)) { kfree(link); - return NULL; + return dentry; } inode = debugfs_get_inode(dentry->d_sb); @@ -787,6 +790,13 @@ struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry, struct dentry *dentry = NULL, *trap; struct name_snapshot old_name; + if (IS_ERR(old_dir)) + return old_dir; + if (IS_ERR(new_dir)) + return new_dir; + if (IS_ERR_OR_NULL(old_dentry)) + return old_dentry; + trap = lock_rename(new_dir, old_dir); /* Source or destination directories don't exist? */ if (d_really_is_negative(old_dir) || d_really_is_negative(new_dir)) @@ -820,7 +830,9 @@ exit: if (dentry && !IS_ERR(dentry)) dput(dentry); unlock_rename(new_dir, old_dir); - return NULL; + if (IS_ERR(dentry)) + return dentry; + return ERR_PTR(-EINVAL); } EXPORT_SYMBOL_GPL(debugfs_rename); diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index 76976d6e50f9..c98ad9777ad9 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -1089,12 +1089,12 @@ static void sctp_connect_to_sock(struct connection *con) * since O_NONBLOCK argument in connect() function does not work here, * then, we should restore the default value of this attribute. */ - kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO, (char *)&tv, + kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO_OLD, (char *)&tv, sizeof(tv)); result = sock->ops->connect(sock, (struct sockaddr *)&daddr, addr_len, 0); memset(&tv, 0, sizeof(tv)); - kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO, (char *)&tv, + kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO_OLD, (char *)&tv, sizeof(tv)); if (result == -EINPROGRESS) diff --git a/fs/drop_caches.c b/fs/drop_caches.c index 82377017130f..d31b6c72b476 100644 --- a/fs/drop_caches.c +++ b/fs/drop_caches.c @@ -21,8 +21,13 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused) spin_lock(&sb->s_inode_list_lock); list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { spin_lock(&inode->i_lock); + /* + * We must skip inodes in unusual state. We may also skip + * inodes without pages but we deliberately won't in case + * we need to reschedule to avoid softlockups. + */ if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) || - (inode->i_mapping->nrpages == 0)) { + (inode->i_mapping->nrpages == 0 && !need_resched())) { spin_unlock(&inode->i_lock); continue; } @@ -30,6 +35,7 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused) spin_unlock(&inode->i_lock); spin_unlock(&sb->s_inode_list_lock); + cond_resched(); invalidate_mapping_pages(inode->i_mapping, 0, -1); iput(toput_inode); toput_inode = inode; diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 712f00995390..5508baa11bb6 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -116,16 +116,8 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) goto out; } - ret = file_write_and_wait_range(file, start, end); - if (ret) - return ret; - if (!journal) { - struct writeback_control wbc = { - .sync_mode = WB_SYNC_ALL - }; - - ret = ext4_write_inode(inode, &wbc); + ret = __generic_file_fsync(file, start, end, datasync); if (!ret) ret = ext4_sync_parent(inode); if (test_opt(inode->i_sb, BARRIER)) @@ -133,6 +125,9 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync) goto out; } + ret = file_write_and_wait_range(file, start, end); + if (ret) + return ret; /* * data=writeback,ordered: * The caller's filemap_fdatawrite()/wait will sync the data. diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index a5e516a40e7a..809c0f2f9942 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -1742,7 +1742,6 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode, req->in.h.nodeid = outarg->nodeid; req->in.numargs = 2; req->in.argpages = 1; - req->page_descs[0].offset = offset; req->end = fuse_retrieve_end; index = outarg->offset >> PAGE_SHIFT; @@ -1757,6 +1756,7 @@ static int fuse_retrieve(struct fuse_conn *fc, struct inode *inode, this_num = min_t(unsigned, num, PAGE_SIZE - offset); req->pages[req->num_pages] = page; + req->page_descs[req->num_pages].offset = offset; req->page_descs[req->num_pages].length = this_num; req->num_pages++; @@ -2077,8 +2077,10 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, ret = fuse_dev_do_write(fud, &cs, len); + pipe_lock(pipe); for (idx = 0; idx < nbuf; idx++) pipe_buf_release(pipe, &bufs[idx]); + pipe_unlock(pipe); out: kvfree(bufs); diff --git a/fs/fuse/file.c b/fs/fuse/file.c index ffaffe18352a..a59c16bd90ac 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1782,7 +1782,7 @@ static bool fuse_writepage_in_flight(struct fuse_req *new_req, spin_unlock(&fc->lock); dec_wb_stat(&bdi->wb, WB_WRITEBACK); - dec_node_page_state(page, NR_WRITEBACK_TEMP); + dec_node_page_state(new_req->pages[0], NR_WRITEBACK_TEMP); wb_writeout_inc(&bdi->wb); fuse_writepage_free(fc, new_req); fuse_request_free(new_req); diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 76baaa6be393..c2d4099429be 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -628,6 +628,7 @@ void fuse_conn_init(struct fuse_conn *fc, struct user_namespace *user_ns) get_random_bytes(&fc->scramble_key, sizeof(fc->scramble_key)); fc->pid_ns = get_pid_ns(task_active_pid_ns(current)); fc->user_ns = get_user_ns(user_ns); + fc->max_pages = FUSE_DEFAULT_MAX_PAGES_PER_REQ; } EXPORT_SYMBOL_GPL(fuse_conn_init); @@ -1162,7 +1163,6 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent) fc->user_id = d.user_id; fc->group_id = d.group_id; fc->max_read = max_t(unsigned, 4096, d.max_read); - fc->max_pages = FUSE_DEFAULT_MAX_PAGES_PER_REQ; /* Used by get_root_inode() */ sb->s_fs_info = fc; diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index f15b4c57c4bd..78510ab91835 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -28,7 +28,6 @@ #include "util.h" #include "trans.h" #include "dir.h" -#include "lops.h" struct workqueue_struct *gfs2_freeze_wq; diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c index 5bfaf381921a..b8830fda51e8 100644 --- a/fs/gfs2/log.c +++ b/fs/gfs2/log.c @@ -733,7 +733,7 @@ void gfs2_write_log_header(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd, lh->lh_crc = cpu_to_be32(crc); gfs2_log_write(sdp, page, sb->s_blocksize, 0, addr); - gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE | op_flags); + gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE, op_flags); log_flush_wait(sdp); } @@ -810,7 +810,7 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl, u32 flags) gfs2_ordered_write(sdp); lops_before_commit(sdp, tr); - gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE); + gfs2_log_submit_bio(&sdp->sd_log_bio, REQ_OP_WRITE, 0); if (sdp->sd_log_head != sdp->sd_log_flush_head) { log_flush_wait(sdp); diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index 94dcab655bc0..2295042bc625 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -17,9 +17,7 @@ #include <linux/bio.h> #include <linux/fs.h> #include <linux/list_sort.h> -#include <linux/blkdev.h> -#include "bmap.h" #include "dir.h" #include "gfs2.h" #include "incore.h" @@ -195,6 +193,7 @@ static void gfs2_end_log_write_bh(struct gfs2_sbd *sdp, struct bio_vec *bvec, /** * gfs2_end_log_write - end of i/o to the log * @bio: The bio + * @error: Status of i/o request * * Each bio_vec contains either data from the pagecache or data * relating to the log itself. Here we iterate over the bio_vec @@ -231,19 +230,20 @@ static void gfs2_end_log_write(struct bio *bio) /** * gfs2_log_submit_bio - Submit any pending log bio * @biop: Address of the bio pointer - * @opf: REQ_OP | op_flags + * @op: REQ_OP + * @op_flags: req_flag_bits * * Submit any pending part-built or full bio to the block device. If * there is no pending bio, then this is a no-op. */ -void gfs2_log_submit_bio(struct bio **biop, int opf) +void gfs2_log_submit_bio(struct bio **biop, int op, int op_flags) { struct bio *bio = *biop; if (bio) { struct gfs2_sbd *sdp = bio->bi_private; atomic_inc(&sdp->sd_log_in_flight); - bio->bi_opf = opf; + bio_set_op_attrs(bio, op, op_flags); submit_bio(bio); *biop = NULL; } @@ -304,7 +304,7 @@ static struct bio *gfs2_log_get_bio(struct gfs2_sbd *sdp, u64 blkno, nblk >>= sdp->sd_fsb2bb_shift; if (blkno == nblk && !flush) return bio; - gfs2_log_submit_bio(biop, op); + gfs2_log_submit_bio(biop, op, 0); } *biop = gfs2_log_alloc_bio(sdp, blkno, end_io); @@ -375,184 +375,6 @@ void gfs2_log_write_page(struct gfs2_sbd *sdp, struct page *page) gfs2_log_bmap(sdp)); } -/** - * gfs2_end_log_read - end I/O callback for reads from the log - * @bio: The bio - * - * Simply unlock the pages in the bio. The main thread will wait on them and - * process them in order as necessary. - */ - -static void gfs2_end_log_read(struct bio *bio) -{ - struct page *page; - struct bio_vec *bvec; - int i; - - bio_for_each_segment_all(bvec, bio, i) { - page = bvec->bv_page; - if (bio->bi_status) { - int err = blk_status_to_errno(bio->bi_status); - - SetPageError(page); - mapping_set_error(page->mapping, err); - } - unlock_page(page); - } - - bio_put(bio); -} - -/** - * gfs2_jhead_pg_srch - Look for the journal head in a given page. - * @jd: The journal descriptor - * @page: The page to look in - * - * Returns: 1 if found, 0 otherwise. - */ - -static bool gfs2_jhead_pg_srch(struct gfs2_jdesc *jd, - struct gfs2_log_header_host *head, - struct page *page) -{ - struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode); - struct gfs2_log_header_host uninitialized_var(lh); - void *kaddr = kmap_atomic(page); - unsigned int offset; - bool ret = false; - - for (offset = 0; offset < PAGE_SIZE; offset += sdp->sd_sb.sb_bsize) { - if (!__get_log_header(sdp, kaddr + offset, 0, &lh)) { - if (lh.lh_sequence > head->lh_sequence) - *head = lh; - else { - ret = true; - break; - } - } - } - kunmap_atomic(kaddr); - return ret; -} - -/** - * gfs2_jhead_process_page - Search/cleanup a page - * @jd: The journal descriptor - * @index: Index of the page to look into - * @done: If set, perform only cleanup, else search and set if found. - * - * Find the page with 'index' in the journal's mapping. Search the page for - * the journal head if requested (cleanup == false). Release refs on the - * page so the page cache can reclaim it (put_page() twice). We grabbed a - * reference on this page two times, first when we did a find_or_create_page() - * to obtain the page to add it to the bio and second when we do a - * find_get_page() here to get the page to wait on while I/O on it is being - * completed. - * This function is also used to free up a page we might've grabbed but not - * used. Maybe we added it to a bio, but not submitted it for I/O. Or we - * submitted the I/O, but we already found the jhead so we only need to drop - * our references to the page. - */ - -static void gfs2_jhead_process_page(struct gfs2_jdesc *jd, unsigned long index, - struct gfs2_log_header_host *head, - bool *done) -{ - struct page *page; - - page = find_get_page(jd->jd_inode->i_mapping, index); - wait_on_page_locked(page); - - if (PageError(page)) - *done = true; - - if (!*done) - *done = gfs2_jhead_pg_srch(jd, head, page); - - put_page(page); /* Once for find_get_page */ - put_page(page); /* Once more for find_or_create_page */ -} - -/** - * gfs2_find_jhead - find the head of a log - * @jd: The journal descriptor - * @head: The log descriptor for the head of the log is returned here - * - * Do a search of a journal by reading it in large chunks using bios and find - * the valid log entry with the highest sequence number. (i.e. the log head) - * - * Returns: 0 on success, errno otherwise - */ - -int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head) -{ - struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode); - struct address_space *mapping = jd->jd_inode->i_mapping; - struct gfs2_journal_extent *je; - u32 block, read_idx = 0, submit_idx = 0, index = 0; - int shift = PAGE_SHIFT - sdp->sd_sb.sb_bsize_shift; - int blocks_per_page = 1 << shift, sz, ret = 0; - struct bio *bio = NULL; - struct page *page; - bool done = false; - errseq_t since; - - memset(head, 0, sizeof(*head)); - if (list_empty(&jd->extent_list)) - gfs2_map_journal_extents(sdp, jd); - - since = filemap_sample_wb_err(mapping); - list_for_each_entry(je, &jd->extent_list, list) { - for (block = 0; block < je->blocks; block += blocks_per_page) { - index = (je->lblock + block) >> shift; - - page = find_or_create_page(mapping, index, GFP_NOFS); - if (!page) { - ret = -ENOMEM; - done = true; - goto out; - } - - if (bio) { - sz = bio_add_page(bio, page, PAGE_SIZE, 0); - if (sz == PAGE_SIZE) - goto page_added; - submit_idx = index; - submit_bio(bio); - bio = NULL; - } - - bio = gfs2_log_alloc_bio(sdp, - je->dblock + (index << shift), - gfs2_end_log_read); - bio->bi_opf = REQ_OP_READ; - sz = bio_add_page(bio, page, PAGE_SIZE, 0); - gfs2_assert_warn(sdp, sz == PAGE_SIZE); - -page_added: - if (submit_idx <= read_idx + BIO_MAX_PAGES) { - /* Keep at least one bio in flight */ - continue; - } - - gfs2_jhead_process_page(jd, read_idx++, head, &done); - if (done) - goto out; /* found */ - } - } - -out: - if (bio) - submit_bio(bio); - while (read_idx <= index) - gfs2_jhead_process_page(jd, read_idx++, head, &done); - - if (!ret) - ret = filemap_check_wb_err(mapping, since); - - return ret; -} - static struct page *gfs2_get_log_desc(struct gfs2_sbd *sdp, u32 ld_type, u32 ld_length, u32 ld_data1) { diff --git a/fs/gfs2/lops.h b/fs/gfs2/lops.h index 331160fc568b..711c4d89c063 100644 --- a/fs/gfs2/lops.h +++ b/fs/gfs2/lops.h @@ -30,10 +30,8 @@ extern u64 gfs2_log_bmap(struct gfs2_sbd *sdp); extern void gfs2_log_write(struct gfs2_sbd *sdp, struct page *page, unsigned size, unsigned offset, u64 blkno); extern void gfs2_log_write_page(struct gfs2_sbd *sdp, struct page *page); -extern void gfs2_log_submit_bio(struct bio **biop, int opf); +extern void gfs2_log_submit_bio(struct bio **biop, int op, int op_flags); extern void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh); -extern int gfs2_find_jhead(struct gfs2_jdesc *jd, - struct gfs2_log_header_host *head); static inline unsigned int buf_limit(struct gfs2_sbd *sdp) { diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c index 1179763f6370..b041cb8ae383 100644 --- a/fs/gfs2/ops_fstype.c +++ b/fs/gfs2/ops_fstype.c @@ -41,7 +41,6 @@ #include "dir.h" #include "meta_io.h" #include "trace_gfs2.h" -#include "lops.h" #define DO 0 #define UNDO 1 diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c index 7389e445a7a7..2dac43065382 100644 --- a/fs/gfs2/recovery.c +++ b/fs/gfs2/recovery.c @@ -182,6 +182,129 @@ static int get_log_header(struct gfs2_jdesc *jd, unsigned int blk, } /** + * find_good_lh - find a good log header + * @jd: the journal + * @blk: the segment to start searching from + * @lh: the log header to fill in + * @forward: if true search forward in the log, else search backward + * + * Call get_log_header() to get a log header for a segment, but if the + * segment is bad, either scan forward or backward until we find a good one. + * + * Returns: errno + */ + +static int find_good_lh(struct gfs2_jdesc *jd, unsigned int *blk, + struct gfs2_log_header_host *head) +{ + unsigned int orig_blk = *blk; + int error; + + for (;;) { + error = get_log_header(jd, *blk, head); + if (error <= 0) + return error; + + if (++*blk == jd->jd_blocks) + *blk = 0; + + if (*blk == orig_blk) { + gfs2_consist_inode(GFS2_I(jd->jd_inode)); + return -EIO; + } + } +} + +/** + * jhead_scan - make sure we've found the head of the log + * @jd: the journal + * @head: this is filled in with the log descriptor of the head + * + * At this point, seg and lh should be either the head of the log or just + * before. Scan forward until we find the head. + * + * Returns: errno + */ + +static int jhead_scan(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head) +{ + unsigned int blk = head->lh_blkno; + struct gfs2_log_header_host lh; + int error; + + for (;;) { + if (++blk == jd->jd_blocks) + blk = 0; + + error = get_log_header(jd, blk, &lh); + if (error < 0) + return error; + if (error == 1) + continue; + + if (lh.lh_sequence == head->lh_sequence) { + gfs2_consist_inode(GFS2_I(jd->jd_inode)); + return -EIO; + } + if (lh.lh_sequence < head->lh_sequence) + break; + + *head = lh; + } + + return 0; +} + +/** + * gfs2_find_jhead - find the head of a log + * @jd: the journal + * @head: the log descriptor for the head of the log is returned here + * + * Do a binary search of a journal and find the valid log entry with the + * highest sequence number. (i.e. the log head) + * + * Returns: errno + */ + +int gfs2_find_jhead(struct gfs2_jdesc *jd, struct gfs2_log_header_host *head) +{ + struct gfs2_log_header_host lh_1, lh_m; + u32 blk_1, blk_2, blk_m; + int error; + + blk_1 = 0; + blk_2 = jd->jd_blocks - 1; + + for (;;) { + blk_m = (blk_1 + blk_2) / 2; + + error = find_good_lh(jd, &blk_1, &lh_1); + if (error) + return error; + + error = find_good_lh(jd, &blk_m, &lh_m); + if (error) + return error; + + if (blk_1 == blk_m || blk_m == blk_2) + break; + + if (lh_1.lh_sequence <= lh_m.lh_sequence) + blk_1 = blk_m; + else + blk_2 = blk_m; + } + + error = jhead_scan(jd, &lh_1); + if (error) + return error; + + *head = lh_1; + + return error; +} + +/** * foreach_descriptor - go through the active part of the log * @jd: the journal * @start: the first log header in the active region diff --git a/fs/gfs2/recovery.h b/fs/gfs2/recovery.h index 99575ab81202..11d81248be85 100644 --- a/fs/gfs2/recovery.h +++ b/fs/gfs2/recovery.h @@ -27,6 +27,8 @@ extern int gfs2_revoke_add(struct gfs2_jdesc *jd, u64 blkno, unsigned int where) extern int gfs2_revoke_check(struct gfs2_jdesc *jd, u64 blkno, unsigned int where); extern void gfs2_revoke_clean(struct gfs2_jdesc *jd); +extern int gfs2_find_jhead(struct gfs2_jdesc *jd, + struct gfs2_log_header_host *head); extern int gfs2_recover_journal(struct gfs2_jdesc *gfs2_jd, bool wait); extern void gfs2_recover_func(struct work_struct *work); extern int __get_log_header(struct gfs2_sbd *sdp, diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c index 831d7cb5a49c..17a8d3b43990 100644 --- a/fs/gfs2/rgrp.c +++ b/fs/gfs2/rgrp.c @@ -1780,9 +1780,9 @@ static int gfs2_rbm_find(struct gfs2_rbm *rbm, u8 state, u32 *minext, goto next_iter; } if (ret == -E2BIG) { - n += rbm->bii - initial_bii; rbm->bii = 0; rbm->offset = 0; + n += (rbm->bii - initial_bii); goto res_covered_end_of_rgrp; } return ret; diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index d4b11c903971..ca71163ff7cf 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -45,7 +45,6 @@ #include "util.h" #include "sys.h" #include "xattr.h" -#include "lops.h" #define args_neq(a1, a2, x) ((a1)->ar_##x != (a2)->ar_##x) diff --git a/fs/inode.c b/fs/inode.c index 0cd47fe0dbe5..73432e64f874 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -730,11 +730,8 @@ static enum lru_status inode_lru_isolate(struct list_head *item, return LRU_REMOVED; } - /* - * Recently referenced inodes and inodes with many attached pages - * get one more pass. - */ - if (inode->i_state & I_REFERENCED || inode->i_data.nrpages > 1) { + /* recently referenced inodes get one more pass */ + if (inode->i_state & I_REFERENCED) { inode->i_state &= ~I_REFERENCED; spin_unlock(&inode->i_lock); return LRU_ROTATE; diff --git a/fs/iomap.c b/fs/iomap.c index a3088fae567b..897c60215dd1 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -116,6 +116,12 @@ iomap_page_create(struct inode *inode, struct page *page) atomic_set(&iop->read_count, 0); atomic_set(&iop->write_count, 0); bitmap_zero(iop->uptodate, PAGE_SIZE / SECTOR_SIZE); + + /* + * migrate_page_move_mapping() assumes that pages with private data have + * their count elevated by 1. + */ + get_page(page); set_page_private(page, (unsigned long)iop); SetPagePrivate(page); return iop; @@ -132,6 +138,7 @@ iomap_page_release(struct page *page) WARN_ON_ONCE(atomic_read(&iop->write_count)); ClearPagePrivate(page); set_page_private(page, 0); + put_page(page); kfree(iop); } @@ -569,8 +576,10 @@ iomap_migrate_page(struct address_space *mapping, struct page *newpage, if (page_has_private(page)) { ClearPagePrivate(page); + get_page(newpage); set_page_private(newpage, page_private(page)); set_page_private(page, 0); + put_page(page); SetPagePrivate(newpage); } @@ -1804,6 +1813,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, loff_t pos = iocb->ki_pos, start = pos; loff_t end = iocb->ki_pos + count - 1, ret = 0; unsigned int flags = IOMAP_DIRECT; + bool wait_for_completion = is_sync_kiocb(iocb); struct blk_plug plug; struct iomap_dio *dio; @@ -1823,7 +1833,6 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, dio->end_io = end_io; dio->error = 0; dio->flags = 0; - dio->wait_for_completion = is_sync_kiocb(iocb); dio->submit.iter = iter; dio->submit.waiter = current; @@ -1878,7 +1887,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, dio_warn_stale_pagecache(iocb->ki_filp); ret = 0; - if (iov_iter_rw(iter) == WRITE && !dio->wait_for_completion && + if (iov_iter_rw(iter) == WRITE && !wait_for_completion && !inode->i_sb->s_dio_done_wq) { ret = sb_init_dio_done_wq(inode->i_sb); if (ret < 0) @@ -1894,7 +1903,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, if (ret <= 0) { /* magic error code to fall back to buffered I/O */ if (ret == -ENOTBLK) { - dio->wait_for_completion = true; + wait_for_completion = true; ret = 0; } break; @@ -1916,8 +1925,24 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, if (dio->flags & IOMAP_DIO_WRITE_FUA) dio->flags &= ~IOMAP_DIO_NEED_SYNC; + /* + * We are about to drop our additional submission reference, which + * might be the last reference to the dio. There are three three + * different ways we can progress here: + * + * (a) If this is the last reference we will always complete and free + * the dio ourselves. + * (b) If this is not the last reference, and we serve an asynchronous + * iocb, we must never touch the dio after the decrement, the + * I/O completion handler will complete and free it. + * (c) If this is not the last reference, but we serve a synchronous + * iocb, the I/O completion handler will wake us up on the drop + * of the final reference, and we will complete and free it here + * after we got woken by the I/O completion handler. + */ + dio->wait_for_completion = wait_for_completion; if (!atomic_dec_and_test(&dio->ref)) { - if (!dio->wait_for_completion) + if (!wait_for_completion) return -EIOCBQUEUED; for (;;) { @@ -1934,9 +1959,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, __set_current_state(TASK_RUNNING); } - ret = iomap_dio_complete(dio); - - return ret; + return iomap_dio_complete(dio); out_free_dio: kfree(dio); diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 22ce3c8a2f46..0570391eaa16 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1895,6 +1895,11 @@ static int nfs_parse_devname(const char *dev_name, size_t len; char *end; + if (unlikely(!dev_name || !*dev_name)) { + dfprintk(MOUNT, "NFS: device name not specified\n"); + return -EINVAL; + } + /* Is the host name protected with square brakcets? */ if (*dev_name == '[') { end = strchr(++dev_name, ']'); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 5a0bbf917a32..f12cb31a41e5 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -621,11 +621,12 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio, nfs_set_page_writeback(page); WARN_ON_ONCE(test_bit(PG_CLEAN, &req->wb_flags)); - ret = 0; + ret = req->wb_context->error; /* If there is a fatal error that covers this write, just exit */ - if (nfs_error_is_fatal_on_server(req->wb_context->error)) + if (nfs_error_is_fatal_on_server(ret)) goto out_launder; + ret = 0; if (!nfs_pageio_add_request(pgio, req)) { ret = pgio->pg_error; /* @@ -635,9 +636,9 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio, nfs_context_set_write_error(req->wb_context, ret); if (nfs_error_is_fatal_on_server(ret)) goto out_launder; - } + } else + ret = -EAGAIN; nfs_redirty_request(req); - ret = -EAGAIN; } else nfs_add_stats(page_file_mapping(page)->host, NFSIOS_WRITEPAGES, 1); diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 9824e32b2f23..7dc98e14655d 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -557,9 +557,11 @@ __be32 nfsd4_clone_file_range(struct file *src, u64 src_pos, struct file *dst, loff_t cloned; cloned = vfs_clone_file_range(src, src_pos, dst, dst_pos, count, 0); + if (cloned < 0) + return nfserrno(cloned); if (count && cloned != count) - cloned = -EINVAL; - return nfserrno(cloned < 0 ? cloned : 0); + return nfserrno(-EINVAL); + return 0; } ssize_t nfsd_copy_file_range(struct file *src, u64 src_pos, struct file *dst, diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 8ae109429a88..e39bac94dead 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -256,7 +256,7 @@ struct dentry *proc_lookup_de(struct inode *dir, struct dentry *dentry, inode = proc_get_inode(dir->i_sb, de); if (!inode) return ERR_PTR(-ENOMEM); - d_set_d_op(dentry, &proc_misc_dentry_ops); + d_set_d_op(dentry, de->proc_dops); return d_splice_alias(inode, dentry); } read_unlock(&proc_subdir_lock); @@ -429,6 +429,8 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent, INIT_LIST_HEAD(&ent->pde_openers); proc_set_user(ent, (*parent)->uid, (*parent)->gid); + ent->proc_dops = &proc_misc_dentry_ops; + out: return ent; } diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 5185d7f6a51e..95b14196f284 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -44,6 +44,7 @@ struct proc_dir_entry { struct completion *pde_unload_completion; const struct inode_operations *proc_iops; const struct file_operations *proc_fops; + const struct dentry_operations *proc_dops; union { const struct seq_operations *seq_ops; int (*single_show)(struct seq_file *, void *); diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c index d5e0fcb3439e..a7b12435519e 100644 --- a/fs/proc/proc_net.c +++ b/fs/proc/proc_net.c @@ -38,6 +38,22 @@ static struct net *get_proc_net(const struct inode *inode) return maybe_get_net(PDE_NET(PDE(inode))); } +static int proc_net_d_revalidate(struct dentry *dentry, unsigned int flags) +{ + return 0; +} + +static const struct dentry_operations proc_net_dentry_ops = { + .d_revalidate = proc_net_d_revalidate, + .d_delete = always_delete_dentry, +}; + +static void pde_force_lookup(struct proc_dir_entry *pde) +{ + /* /proc/net/ entries can be changed under us by setns(CLONE_NEWNET) */ + pde->proc_dops = &proc_net_dentry_ops; +} + static int seq_open_net(struct inode *inode, struct file *file) { unsigned int state_size = PDE(inode)->state_size; @@ -90,6 +106,7 @@ struct proc_dir_entry *proc_create_net_data(const char *name, umode_t mode, p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; + pde_force_lookup(p); p->proc_fops = &proc_net_seq_fops; p->seq_ops = ops; p->state_size = state_size; @@ -133,6 +150,7 @@ struct proc_dir_entry *proc_create_net_data_write(const char *name, umode_t mode p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; + pde_force_lookup(p); p->proc_fops = &proc_net_seq_fops; p->seq_ops = ops; p->state_size = state_size; @@ -181,6 +199,7 @@ struct proc_dir_entry *proc_create_net_single(const char *name, umode_t mode, p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; + pde_force_lookup(p); p->proc_fops = &proc_net_single_fops; p->single_show = show; return proc_register(parent, p); @@ -223,6 +242,7 @@ struct proc_dir_entry *proc_create_net_single_write(const char *name, umode_t mo p = proc_create_reg(name, mode, &parent, data); if (!p) return NULL; + pde_force_lookup(p); p->proc_fops = &proc_net_single_fops; p->single_show = show; p->write = write; diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index f0ec9edab2f3..85b0ef890b28 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -423,7 +423,7 @@ struct mem_size_stats { }; static void smaps_account(struct mem_size_stats *mss, struct page *page, - bool compound, bool young, bool dirty) + bool compound, bool young, bool dirty, bool locked) { int i, nr = compound ? 1 << compound_order(page) : 1; unsigned long size = nr * PAGE_SIZE; @@ -450,24 +450,31 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page, else mss->private_clean += size; mss->pss += (u64)size << PSS_SHIFT; + if (locked) + mss->pss_locked += (u64)size << PSS_SHIFT; return; } for (i = 0; i < nr; i++, page++) { int mapcount = page_mapcount(page); + unsigned long pss = (PAGE_SIZE << PSS_SHIFT); if (mapcount >= 2) { if (dirty || PageDirty(page)) mss->shared_dirty += PAGE_SIZE; else mss->shared_clean += PAGE_SIZE; - mss->pss += (PAGE_SIZE << PSS_SHIFT) / mapcount; + mss->pss += pss / mapcount; + if (locked) + mss->pss_locked += pss / mapcount; } else { if (dirty || PageDirty(page)) mss->private_dirty += PAGE_SIZE; else mss->private_clean += PAGE_SIZE; - mss->pss += PAGE_SIZE << PSS_SHIFT; + mss->pss += pss; + if (locked) + mss->pss_locked += pss; } } } @@ -490,6 +497,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, { struct mem_size_stats *mss = walk->private; struct vm_area_struct *vma = walk->vma; + bool locked = !!(vma->vm_flags & VM_LOCKED); struct page *page = NULL; if (pte_present(*pte)) { @@ -532,7 +540,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, if (!page) return; - smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte)); + smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte), locked); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -541,6 +549,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, { struct mem_size_stats *mss = walk->private; struct vm_area_struct *vma = walk->vma; + bool locked = !!(vma->vm_flags & VM_LOCKED); struct page *page; /* FOLL_DUMP will return -EFAULT on huge zero page */ @@ -555,7 +564,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, /* pass */; else VM_BUG_ON_PAGE(1, page); - smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd)); + smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd), locked); } #else static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, @@ -737,11 +746,8 @@ static void smap_gather_stats(struct vm_area_struct *vma, } } #endif - /* mmap_sem is held in m_start */ walk_page_vma(vma, &smaps_walk); - if (vma->vm_flags & VM_LOCKED) - mss->pss_locked += mss->pss; } #define SEQ_PUT_DEC(str, val) \ diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c index 1c8eecfe52b8..6acf1bfa0bfe 100644 --- a/fs/xfs/scrub/repair.c +++ b/fs/xfs/scrub/repair.c @@ -768,18 +768,23 @@ xrep_findroot_block( if (!uuid_equal(&btblock->bb_u.s.bb_uuid, &mp->m_sb.sb_meta_uuid)) goto out; + /* + * Read verifiers can reference b_ops, so we set the pointer + * here. If the verifier fails we'll reset the buffer state + * to what it was before we touched the buffer. + */ + bp->b_ops = fab->buf_ops; fab->buf_ops->verify_read(bp); if (bp->b_error) { + bp->b_ops = NULL; bp->b_error = 0; goto out; } /* * Some read verifiers will (re)set b_ops, so we must be - * careful not to blow away any such assignment. + * careful not to change b_ops after running the verifier. */ - if (!bp->b_ops) - bp->b_ops = fab->buf_ops; } /* diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 338b9d9984e0..d9048bcea49c 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -449,6 +449,7 @@ xfs_map_blocks( } wpc->imap = imap; + xfs_trim_extent_eof(&wpc->imap, ip); trace_xfs_map_blocks_found(ip, offset, count, wpc->io_type, &imap); return 0; allocate_blocks: @@ -459,6 +460,7 @@ allocate_blocks: ASSERT(whichfork == XFS_COW_FORK || cow_fsb == NULLFILEOFF || imap.br_startoff + imap.br_blockcount <= cow_fsb); wpc->imap = imap; + xfs_trim_extent_eof(&wpc->imap, ip); trace_xfs_map_blocks_alloc(ip, offset, count, wpc->io_type, &imap); return 0; } diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index eedc5e0156ff..4f5f2ff3f70f 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -776,10 +776,26 @@ _xfs_buf_read( } /* + * Set buffer ops on an unchecked buffer and validate it, if possible. + * * If the caller passed in an ops structure and the buffer doesn't have ops * assigned, set the ops and use them to verify the contents. If the contents * cannot be verified, we'll clear XBF_DONE. We assume the buffer has no * recorded errors and is already in XBF_DONE state. + * + * Under normal operations, every in-core buffer must have buffer ops assigned + * to them when the buffer is read in from disk so that we can validate the + * metadata. + * + * However, there are two scenarios where one can encounter in-core buffers + * that don't have buffer ops. The first is during log recovery of buffers on + * a V4 filesystem, though these buffers are purged at the end of recovery. + * + * The other is online repair, which tries to match arbitrary metadata blocks + * with btree types in order to find the root. If online repair doesn't match + * the buffer with /any/ btree type, the buffer remains in memory in DONE state + * with no ops, and a subsequent read_buf call from elsewhere will not set the + * ops. This function helps us fix this situation. */ int xfs_buf_ensure_ops( @@ -1536,8 +1552,7 @@ __xfs_buf_submit( xfs_buf_ioerror(bp, -EIO); bp->b_flags &= ~XBF_DONE; xfs_buf_stale(bp); - if (bp->b_flags & XBF_ASYNC) - xfs_buf_ioend(bp); + xfs_buf_ioend(bp); return -EIO; } diff --git a/include/uapi/asm-generic/shmparam.h b/include/asm-generic/shmparam.h index 8b78c0ba08b1..8b78c0ba08b1 100644 --- a/include/uapi/asm-generic/shmparam.h +++ b/include/asm-generic/shmparam.h diff --git a/include/dt-bindings/clock/imx8mq-clock.h b/include/dt-bindings/clock/imx8mq-clock.h index b53be41929be..04f7ac345984 100644 --- a/include/dt-bindings/clock/imx8mq-clock.h +++ b/include/dt-bindings/clock/imx8mq-clock.h @@ -350,7 +350,7 @@ #define IMX8MQ_CLK_VPU_G2_ROOT 241 /* SCCG PLL GATE */ -#define IMX8MQ_SYS1_PLL_OUT 232 +#define IMX8MQ_SYS1_PLL_OUT 242 #define IMX8MQ_SYS2_PLL_OUT 243 #define IMX8MQ_SYS3_PLL_OUT 244 #define IMX8MQ_DRAM_PLL_OUT 245 @@ -372,24 +372,24 @@ /* txesc clock */ #define IMX8MQ_CLK_DSI_IPG_DIV 256 -#define IMX8MQ_CLK_TMU_ROOT 265 +#define IMX8MQ_CLK_TMU_ROOT 257 /* Display root clocks */ -#define IMX8MQ_CLK_DISP_AXI_ROOT 266 -#define IMX8MQ_CLK_DISP_APB_ROOT 267 -#define IMX8MQ_CLK_DISP_RTRM_ROOT 268 +#define IMX8MQ_CLK_DISP_AXI_ROOT 258 +#define IMX8MQ_CLK_DISP_APB_ROOT 259 +#define IMX8MQ_CLK_DISP_RTRM_ROOT 260 -#define IMX8MQ_CLK_OCOTP_ROOT 269 +#define IMX8MQ_CLK_OCOTP_ROOT 261 -#define IMX8MQ_CLK_DRAM_ALT_ROOT 270 -#define IMX8MQ_CLK_DRAM_CORE 271 +#define IMX8MQ_CLK_DRAM_ALT_ROOT 262 +#define IMX8MQ_CLK_DRAM_CORE 263 -#define IMX8MQ_CLK_MU_ROOT 272 -#define IMX8MQ_VIDEO2_PLL_OUT 273 +#define IMX8MQ_CLK_MU_ROOT 264 +#define IMX8MQ_VIDEO2_PLL_OUT 265 -#define IMX8MQ_CLK_CLKO2 274 +#define IMX8MQ_CLK_CLKO2 266 -#define IMX8MQ_CLK_NAND_USDHC_BUS_RAWNAND_CLK 275 +#define IMX8MQ_CLK_NAND_USDHC_BUS_RAWNAND_CLK 267 -#define IMX8MQ_CLK_END 276 +#define IMX8MQ_CLK_END 268 #endif /* __DT_BINDINGS_CLOCK_IMX8MQ_H */ diff --git a/include/dt-bindings/clock/marvell,mmp2.h b/include/dt-bindings/clock/marvell,mmp2.h index 7b24fc791146..228a5e234af0 100644 --- a/include/dt-bindings/clock/marvell,mmp2.h +++ b/include/dt-bindings/clock/marvell,mmp2.h @@ -71,7 +71,6 @@ #define MMP2_CLK_CCIC1_MIX 117 #define MMP2_CLK_CCIC1_PHY 118 #define MMP2_CLK_CCIC1_SPHY 119 -#define MMP2_CLK_SP 120 #define MMP2_NR_CLKS 200 #endif diff --git a/include/linux/bcma/bcma.h b/include/linux/bcma/bcma.h index ef61f3607e99..60b94b944e9f 100644 --- a/include/linux/bcma/bcma.h +++ b/include/linux/bcma/bcma.h @@ -332,6 +332,8 @@ extern int bcma_arch_register_fallback_sprom( struct ssb_sprom *out)); struct bcma_bus { + struct device *dev; + /* The MMIO area. */ void __iomem *mmio; @@ -339,14 +341,7 @@ struct bcma_bus { enum bcma_hosttype hosttype; bool host_is_pcie2; /* Used for BCMA_HOSTTYPE_PCI only */ - union { - /* Pointer to the PCI bus (only for BCMA_HOSTTYPE_PCI) */ - struct pci_dev *host_pci; - /* Pointer to the SDIO device (only for BCMA_HOSTTYPE_SDIO) */ - struct sdio_func *host_sdio; - /* Pointer to platform device (only for BCMA_HOSTTYPE_SOC) */ - struct platform_device *host_pdev; - }; + struct pci_dev *host_pci; /* PCI bus pointer (BCMA_HOSTTYPE_PCI only) */ struct bcma_chipinfo chipinfo; diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 8804753805ac..7bb2d8de9f30 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -116,7 +116,13 @@ extern void blk_fill_rwbs(char *rwbs, unsigned int op, int bytes); static inline sector_t blk_rq_trace_sector(struct request *rq) { - return blk_rq_is_passthrough(rq) ? 0 : blk_rq_pos(rq); + /* + * Tracing should ignore starting sector for passthrough requests and + * requests where starting sector didn't get set. + */ + if (blk_rq_is_passthrough(rq) || blk_rq_pos(rq) == (sector_t)-1) + return 0; + return blk_rq_pos(rq); } static inline unsigned int blk_rq_trace_nr_sectors(struct request *rq) diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 588dd5f0bd85..695b2a880d9a 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -78,7 +78,7 @@ int cgroup_bpf_inherit(struct cgroup *cgrp); int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, enum bpf_attach_type type, u32 flags); int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, - enum bpf_attach_type type, u32 flags); + enum bpf_attach_type type); int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, union bpf_attr __user *uattr); diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 0394f1f9213b..de18227b3d95 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -72,14 +72,15 @@ struct bpf_map { u32 value_size; u32 max_entries; u32 map_flags; - u32 pages; + int spin_lock_off; /* >=0 valid offset, <0 error */ u32 id; int numa_node; u32 btf_key_type_id; u32 btf_value_type_id; struct btf *btf; + u32 pages; bool unpriv_array; - /* 55 bytes hole */ + /* 51 bytes hole */ /* The 3rd and 4th cacheline with misc members to avoid false sharing * particularly with refcounting. @@ -91,6 +92,36 @@ struct bpf_map { char name[BPF_OBJ_NAME_LEN]; }; +static inline bool map_value_has_spin_lock(const struct bpf_map *map) +{ + return map->spin_lock_off >= 0; +} + +static inline void check_and_init_map_lock(struct bpf_map *map, void *dst) +{ + if (likely(!map_value_has_spin_lock(map))) + return; + *(struct bpf_spin_lock *)(dst + map->spin_lock_off) = + (struct bpf_spin_lock){}; +} + +/* copy everything but bpf_spin_lock */ +static inline void copy_map_value(struct bpf_map *map, void *dst, void *src) +{ + if (unlikely(map_value_has_spin_lock(map))) { + u32 off = map->spin_lock_off; + + memcpy(dst, src, off); + memcpy(dst + off + sizeof(struct bpf_spin_lock), + src + off + sizeof(struct bpf_spin_lock), + map->value_size - off - sizeof(struct bpf_spin_lock)); + } else { + memcpy(dst, src, map->value_size); + } +} +void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, + bool lock_src); + struct bpf_offload_dev; struct bpf_offloaded_map; @@ -162,6 +193,8 @@ enum bpf_arg_type { ARG_PTR_TO_CTX, /* pointer to context */ ARG_ANYTHING, /* any (initialized) argument is ok */ ARG_PTR_TO_SOCKET, /* pointer to bpf_sock */ + ARG_PTR_TO_SPIN_LOCK, /* pointer to bpf_spin_lock */ + ARG_PTR_TO_SOCK_COMMON, /* pointer to sock_common */ }; /* type of values returned from helper functions */ @@ -171,6 +204,7 @@ enum bpf_return_type { RET_PTR_TO_MAP_VALUE, /* returns a pointer to map elem value */ RET_PTR_TO_MAP_VALUE_OR_NULL, /* returns a pointer to map elem value or NULL */ RET_PTR_TO_SOCKET_OR_NULL, /* returns a pointer to a socket or NULL */ + RET_PTR_TO_TCP_SOCK_OR_NULL, /* returns a pointer to a tcp_sock or NULL */ }; /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs @@ -224,6 +258,10 @@ enum bpf_reg_type { PTR_TO_FLOW_KEYS, /* reg points to bpf_flow_keys */ PTR_TO_SOCKET, /* reg points to struct bpf_sock */ PTR_TO_SOCKET_OR_NULL, /* reg points to struct bpf_sock or NULL */ + PTR_TO_SOCK_COMMON, /* reg points to sock_common */ + PTR_TO_SOCK_COMMON_OR_NULL, /* reg points to sock_common or NULL */ + PTR_TO_TCP_SOCK, /* reg points to struct tcp_sock */ + PTR_TO_TCP_SOCK_OR_NULL, /* reg points to struct tcp_sock or NULL */ }; /* The information passed from prog-specific *_is_valid_access @@ -735,8 +773,9 @@ int bpf_map_offload_get_next_key(struct bpf_map *map, bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map); struct bpf_offload_dev * -bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops); +bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops, void *priv); void bpf_offload_dev_destroy(struct bpf_offload_dev *offdev); +void *bpf_offload_dev_priv(struct bpf_offload_dev *offdev); int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev, struct net_device *netdev); void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev, @@ -879,7 +918,8 @@ extern const struct bpf_func_proto bpf_msg_redirect_hash_proto; extern const struct bpf_func_proto bpf_msg_redirect_map_proto; extern const struct bpf_func_proto bpf_sk_redirect_hash_proto; extern const struct bpf_func_proto bpf_sk_redirect_map_proto; - +extern const struct bpf_func_proto bpf_spin_lock_proto; +extern const struct bpf_func_proto bpf_spin_unlock_proto; extern const struct bpf_func_proto bpf_get_local_storage_proto; /* Shared helpers among cBPF and eBPF. */ @@ -887,6 +927,9 @@ void bpf_user_rnd_init_once(void); u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); #if defined(CONFIG_NET) +bool bpf_sock_common_is_valid_access(int off, int size, + enum bpf_access_type type, + struct bpf_insn_access_aux *info); bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info); u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, @@ -895,6 +938,12 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, struct bpf_prog *prog, u32 *target_size); #else +static inline bool bpf_sock_common_is_valid_access(int off, int size, + enum bpf_access_type type, + struct bpf_insn_access_aux *info) +{ + return false; +} static inline bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) @@ -911,4 +960,31 @@ static inline u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, } #endif +#ifdef CONFIG_INET +bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type, + struct bpf_insn_access_aux *info); + +u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog, + u32 *target_size); +#else +static inline bool bpf_tcp_sock_is_valid_access(int off, int size, + enum bpf_access_type type, + struct bpf_insn_access_aux *info) +{ + return false; +} + +static inline u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog, + u32 *target_size) +{ + return 0; +} +#endif /* CONFIG_INET */ + #endif /* _LINUX_BPF_H */ diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 44d9ab4809bd..08bf2f1fe553 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -6,9 +6,11 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_SOCKET_FILTER, sk_filter) BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_CLS, tc_cls_act) BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_ACT, tc_cls_act) BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp) +#ifdef CONFIG_CGROUP_BPF BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SKB, cg_skb) BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock) BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK_ADDR, cg_sock_addr) +#endif BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_in) BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_out) BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 0620e418dde5..69f7a3449eda 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -148,6 +148,7 @@ struct bpf_verifier_state { /* call stack tracking */ struct bpf_func_state *frame[MAX_CALL_FRAMES]; u32 curframe; + u32 active_spin_lock; bool speculative; }; diff --git a/include/linux/btf.h b/include/linux/btf.h index 12502e25e767..455d31b55828 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -50,6 +50,7 @@ u32 btf_id(const struct btf *btf); bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, const struct btf_member *m, u32 expected_offset, u32 expected_size); +int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t); #ifdef CONFIG_BPF_SYSCALL const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 218df7f4d3e1..5041357d0297 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -180,12 +180,10 @@ enum cpuhp_smt_control { #if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT) extern enum cpuhp_smt_control cpu_smt_control; extern void cpu_smt_disable(bool force); -extern void cpu_smt_check_topology_early(void); extern void cpu_smt_check_topology(void); #else # define cpu_smt_control (CPU_SMT_ENABLED) static inline void cpu_smt_disable(bool force) { } -static inline void cpu_smt_check_topology_early(void) { } static inline void cpu_smt_check_topology(void) { } #endif diff --git a/include/linux/dcache.h b/include/linux/dcache.h index ef4b70f64f33..60996e64c579 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -62,9 +62,10 @@ extern const struct qstr slash_name; struct dentry_stat_t { long nr_dentry; long nr_unused; - long age_limit; /* age in seconds */ - long want_pages; /* pages requested by system */ - long dummy[2]; + long age_limit; /* age in seconds */ + long want_pages; /* pages requested by system */ + long nr_negative; /* # of unused negative dentries */ + long dummy; /* Reserved for future use */ }; extern struct dentry_stat_t dentry_stat; diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index afd9596ce636..19a8de5326fb 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -400,4 +400,19 @@ struct ethtool_ops { void (*get_ethtool_phy_stats)(struct net_device *, struct ethtool_stats *, u64 *); }; + +struct ethtool_rx_flow_rule { + struct flow_rule *rule; + unsigned long priv[0]; +}; + +struct ethtool_rx_flow_spec_input { + const struct ethtool_rx_flow_spec *fs; + u32 rss_ctx; +}; + +struct ethtool_rx_flow_rule * +ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input); +void ethtool_rx_flow_rule_destroy(struct ethtool_rx_flow_rule *rule); + #endif /* _LINUX_ETHTOOL_H */ diff --git a/include/linux/filter.h b/include/linux/filter.h index e4b473f85b46..95e2d7ebdf21 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -611,8 +611,8 @@ static inline u8 *bpf_skb_cb(struct sk_buff *skb) return qdisc_skb_cb(skb)->data; } -static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog, - struct sk_buff *skb) +static inline u32 __bpf_prog_run_save_cb(const struct bpf_prog *prog, + struct sk_buff *skb) { u8 *cb_data = bpf_skb_cb(skb); u8 cb_saved[BPF_SKB_CB_LEN]; @@ -631,15 +631,30 @@ static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog, return res; } +static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog, + struct sk_buff *skb) +{ + u32 res; + + preempt_disable(); + res = __bpf_prog_run_save_cb(prog, skb); + preempt_enable(); + return res; +} + static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog, struct sk_buff *skb) { u8 *cb_data = bpf_skb_cb(skb); + u32 res; if (unlikely(prog->cb_access)) memset(cb_data, 0, BPF_SKB_CB_LEN); - return BPF_PROG_RUN(prog, skb); + preempt_disable(); + res = BPF_PROG_RUN(prog, skb); + preempt_enable(); + return res; } static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog, @@ -880,7 +895,9 @@ bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, unsigned int alignment, bpf_jit_fill_hole_t bpf_fill_ill_insns); void bpf_jit_binary_free(struct bpf_binary_header *hdr); - +u64 bpf_jit_alloc_exec_limit(void); +void *bpf_jit_alloc_exec(unsigned long size); +void bpf_jit_free_exec(void *addr); void bpf_jit_free(struct bpf_prog *fp); int bpf_jit_get_func_addr(const struct bpf_prog *prog, diff --git a/include/linux/fs.h b/include/linux/fs.h index 811c77743dad..29d8e2cfed0e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1479,11 +1479,12 @@ struct super_block { struct user_namespace *s_user_ns; /* - * Keep the lru lists last in the structure so they always sit on their - * own individual cachelines. + * The list_lru structure is essentially just a pointer to a table + * of per-node lru lists, each of which has its own spinlock. + * There is no need to put them into separate cachelines. */ - struct list_lru s_dentry_lru ____cacheline_aligned_in_smp; - struct list_lru s_inode_lru ____cacheline_aligned_in_smp; + struct list_lru s_dentry_lru; + struct list_lru s_inode_lru; struct rcu_head rcu; struct work_struct destroy_work; diff --git a/include/linux/fsl/ptp_qoriq.h b/include/linux/fsl/ptp_qoriq.h index 94e9797e434c..f127adb71041 100644 --- a/include/linux/fsl/ptp_qoriq.h +++ b/include/linux/fsl/ptp_qoriq.h @@ -7,6 +7,7 @@ #define __PTP_QORIQ_H__ #include <linux/io.h> +#include <linux/interrupt.h> #include <linux/ptp_clock_kernel.h> /* @@ -49,7 +50,7 @@ struct etts_regs { u32 tmr_etts2_l; /* Timestamp of general purpose external trigger */ }; -struct qoriq_ptp_registers { +struct ptp_qoriq_registers { struct ctrl_regs __iomem *ctrl_regs; struct alarm_regs __iomem *alarm_regs; struct fiper_regs __iomem *fiper_regs; @@ -57,15 +58,15 @@ struct qoriq_ptp_registers { }; /* Offset definitions for the four register groups */ -#define CTRL_REGS_OFFSET 0x0 -#define ALARM_REGS_OFFSET 0x40 -#define FIPER_REGS_OFFSET 0x80 -#define ETTS_REGS_OFFSET 0xa0 +#define ETSEC_CTRL_REGS_OFFSET 0x0 +#define ETSEC_ALARM_REGS_OFFSET 0x40 +#define ETSEC_FIPER_REGS_OFFSET 0x80 +#define ETSEC_ETTS_REGS_OFFSET 0xa0 -#define FMAN_CTRL_REGS_OFFSET 0x80 -#define FMAN_ALARM_REGS_OFFSET 0xb8 -#define FMAN_FIPER_REGS_OFFSET 0xd0 -#define FMAN_ETTS_REGS_OFFSET 0xe0 +#define CTRL_REGS_OFFSET 0x80 +#define ALARM_REGS_OFFSET 0xb8 +#define FIPER_REGS_OFFSET 0xd0 +#define ETTS_REGS_OFFSET 0xe0 /* Bit definitions for the TMR_CTRL register */ @@ -136,9 +137,9 @@ struct qoriq_ptp_registers { #define DEFAULT_FIPER1_PERIOD 1000000000 #define DEFAULT_FIPER2_PERIOD 100000 -struct qoriq_ptp { +struct ptp_qoriq { void __iomem *base; - struct qoriq_ptp_registers regs; + struct ptp_qoriq_registers regs; spinlock_t lock; /* protects regs */ struct ptp_clock *clock; struct ptp_clock_info caps; @@ -156,28 +157,48 @@ struct qoriq_ptp { u32 cksel; u32 tmr_fiper1; u32 tmr_fiper2; + u32 (*read)(unsigned __iomem *addr); + void (*write)(unsigned __iomem *addr, u32 val); }; -static inline u32 qoriq_read(unsigned __iomem *addr) +static inline u32 qoriq_read_be(unsigned __iomem *addr) { - u32 val; - - val = ioread32be(addr); - return val; + return ioread32be(addr); } -static inline void qoriq_write(unsigned __iomem *addr, u32 val) +static inline void qoriq_write_be(unsigned __iomem *addr, u32 val) { iowrite32be(val, addr); } +static inline u32 qoriq_read_le(unsigned __iomem *addr) +{ + return ioread32(addr); +} + +static inline void qoriq_write_le(unsigned __iomem *addr, u32 val) +{ + iowrite32(val, addr); +} + +irqreturn_t ptp_qoriq_isr(int irq, void *priv); +int ptp_qoriq_init(struct ptp_qoriq *ptp_qoriq, void __iomem *base, + const struct ptp_clock_info caps); +void ptp_qoriq_free(struct ptp_qoriq *ptp_qoriq); +int ptp_qoriq_adjfine(struct ptp_clock_info *ptp, long scaled_ppm); +int ptp_qoriq_adjtime(struct ptp_clock_info *ptp, s64 delta); +int ptp_qoriq_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts); +int ptp_qoriq_settime(struct ptp_clock_info *ptp, + const struct timespec64 *ts); +int ptp_qoriq_enable(struct ptp_clock_info *ptp, + struct ptp_clock_request *rq, int on); #ifdef CONFIG_DEBUG_FS -void ptp_qoriq_create_debugfs(struct qoriq_ptp *qoriq_ptp); -void ptp_qoriq_remove_debugfs(struct qoriq_ptp *qoriq_ptp); +void ptp_qoriq_create_debugfs(struct ptp_qoriq *ptp_qoriq); +void ptp_qoriq_remove_debugfs(struct ptp_qoriq *ptp_qoriq); #else -static inline void ptp_qoriq_create_debugfs(struct qoriq_ptp *qoriq_ptp) +static inline void ptp_qoriq_create_debugfs(struct ptp_qoriq *ptp_qoriq) { } -static inline void ptp_qoriq_remove_debugfs(struct qoriq_ptp *qoriq_ptp) +static inline void ptp_qoriq_remove_debugfs(struct ptp_qoriq *ptp_qoriq) { } #endif diff --git a/include/linux/hid-debug.h b/include/linux/hid-debug.h index 8663f216c563..2d6100edf204 100644 --- a/include/linux/hid-debug.h +++ b/include/linux/hid-debug.h @@ -24,7 +24,10 @@ #ifdef CONFIG_DEBUG_FS +#include <linux/kfifo.h> + #define HID_DEBUG_BUFSIZE 512 +#define HID_DEBUG_FIFOSIZE 512 void hid_dump_input(struct hid_device *, struct hid_usage *, __s32); void hid_dump_report(struct hid_device *, int , u8 *, int); @@ -37,11 +40,8 @@ void hid_debug_init(void); void hid_debug_exit(void); void hid_debug_event(struct hid_device *, char *); - struct hid_debug_list { - char *hid_debug_buf; - int head; - int tail; + DECLARE_KFIFO_PTR(hid_debug_fifo, char); struct fasync_struct *fasync; struct hid_device *hdev; struct list_head node; @@ -64,4 +64,3 @@ struct hid_debug_list { #endif #endif - diff --git a/include/linux/ide.h b/include/linux/ide.h index e7d29ae633cd..971cf76a78a0 100644 --- a/include/linux/ide.h +++ b/include/linux/ide.h @@ -615,6 +615,7 @@ struct ide_drive_s { /* current sense rq and buffer */ bool sense_rq_armed; + bool sense_rq_active; struct request *sense_rq; struct request_sense sense_data; @@ -1219,6 +1220,7 @@ extern void ide_stall_queue(ide_drive_t *drive, unsigned long timeout); extern void ide_timer_expiry(struct timer_list *t); extern irqreturn_t ide_intr(int irq, void *dev_id); extern blk_status_t ide_queue_rq(struct blk_mq_hw_ctx *, const struct blk_mq_queue_data *); +extern blk_status_t ide_issue_rq(ide_drive_t *, struct request *, bool); extern void ide_requeue_and_plug(ide_drive_t *drive, struct request *rq); void ide_init_disk(struct gendisk *, ide_drive_t *); diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 8b4348f69bc5..cc85f4524dbf 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -137,7 +137,13 @@ extern void ip_mc_up(struct in_device *); extern void ip_mc_down(struct in_device *); extern void ip_mc_unmap(struct in_device *); extern void ip_mc_remap(struct in_device *); -extern void ip_mc_dec_group(struct in_device *in_dev, __be32 addr); +extern void __ip_mc_dec_group(struct in_device *in_dev, __be32 addr, gfp_t gfp); +static inline void ip_mc_dec_group(struct in_device *in_dev, __be32 addr) +{ + return __ip_mc_dec_group(in_dev, addr, GFP_KERNEL); +} +extern void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, + gfp_t gfp); extern void ip_mc_inc_group(struct in_device *in_dev, __be32 addr); int ip_mc_check_igmp(struct sk_buff *skb); diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index c672f34235e7..4a728dba02e2 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -260,6 +260,7 @@ struct irq_affinity { /** * struct irq_affinity_desc - Interrupt affinity descriptor * @mask: cpumask to hold the affinity assignment + * @is_managed: 1 if the interrupt is managed internally */ struct irq_affinity_desc { struct cpumask mask; diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 071b4cbdf010..c848a7cc502e 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -319,7 +319,7 @@ #define GITS_TYPER_PLPIS (1UL << 0) #define GITS_TYPER_VLPIS (1UL << 1) #define GITS_TYPER_ITT_ENTRY_SIZE_SHIFT 4 -#define GITS_TYPER_ITT_ENTRY_SIZE(r) ((((r) >> GITS_TYPER_ITT_ENTRY_SIZE_SHIFT) & 0x1f) + 1) +#define GITS_TYPER_ITT_ENTRY_SIZE(r) ((((r) >> GITS_TYPER_ITT_ENTRY_SIZE_SHIFT) & 0xf) + 1) #define GITS_TYPER_IDBITS_SHIFT 8 #define GITS_TYPER_DEVBITS_SHIFT 13 #define GITS_TYPER_DEVBITS(r) ((((r) >> GITS_TYPER_DEVBITS_SHIFT) & 0x1f) + 1) diff --git a/include/linux/mdio.h b/include/linux/mdio.h index bfa7114167d7..dd46828b4c47 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -261,6 +261,31 @@ static inline u16 ethtool_adv_to_mmd_eee_adv_t(u32 adv) return reg; } +/** + * linkmode_adv_to_mii_10gbt_adv_t + * @advertising: the linkmode advertisement settings + * + * A small helper function that translates linkmode advertisement + * settings to phy autonegotiation advertisements for the C45 + * 10GBASE-T AN CONTROL (7.32) register. + */ +static inline u32 linkmode_adv_to_mii_10gbt_adv_t(unsigned long *advertising) +{ + u32 result = 0; + + if (linkmode_test_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT, + advertising)) + result |= MDIO_AN_10GBT_CTRL_ADV2_5G; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_5000baseT_Full_BIT, + advertising)) + result |= MDIO_AN_10GBT_CTRL_ADV5G; + if (linkmode_test_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT, + advertising)) + result |= MDIO_AN_10GBT_CTRL_ADV10G; + + return result; +} + int __mdiobus_read(struct mii_bus *bus, int addr, u32 regnum); int __mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val); diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 07da5c6c5ba0..368267c1b71b 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -21,14 +21,16 @@ struct vmem_altmap; * walkers which rely on the fully initialized page->flags and others * should use this rather than pfn_valid && pfn_to_page */ -#define pfn_to_online_page(pfn) \ -({ \ - struct page *___page = NULL; \ - unsigned long ___nr = pfn_to_section_nr(pfn); \ - \ - if (___nr < NR_MEM_SECTIONS && online_section_nr(___nr))\ - ___page = pfn_to_page(pfn); \ - ___page; \ +#define pfn_to_online_page(pfn) \ +({ \ + struct page *___page = NULL; \ + unsigned long ___pfn = pfn; \ + unsigned long ___nr = pfn_to_section_nr(___pfn); \ + \ + if (___nr < NR_MEM_SECTIONS && online_section_nr(___nr) && \ + pfn_valid_within(___pfn)) \ + ___page = pfn_to_page(___pfn); \ + ___page; \ }) /* diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 8c4a820bd4c1..f93a5598b942 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -67,7 +67,7 @@ #define MLX5_UN_SZ_BYTES(typ) (sizeof(union mlx5_ifc_##typ##_bits) / 8) #define MLX5_UN_SZ_DW(typ) (sizeof(union mlx5_ifc_##typ##_bits) / 32) #define MLX5_BYTE_OFF(typ, fld) (__mlx5_bit_off(typ, fld) / 8) -#define MLX5_ADDR_OF(typ, p, fld) ((char *)(p) + MLX5_BYTE_OFF(typ, fld)) +#define MLX5_ADDR_OF(typ, p, fld) ((void *)((uint8_t *)(p) + MLX5_BYTE_OFF(typ, fld))) /* insert a value to a struct */ #define MLX5_SET(typ, p, fld, v) do { \ @@ -342,6 +342,8 @@ enum mlx5_event { MLX5_EVENT_TYPE_PAGE_FAULT = 0xc, MLX5_EVENT_TYPE_NIC_VPORT_CHANGE = 0xd, + MLX5_EVENT_TYPE_HOST_PARAMS_CHANGE = 0xe, + MLX5_EVENT_TYPE_DCT_DRAINED = 0x1c, MLX5_EVENT_TYPE_FPGA_ERROR = 0x20, @@ -591,7 +593,7 @@ struct mlx5_eqe_cmd { }; struct mlx5_eqe_page_req { - u8 rsvd0[2]; + __be16 ec_function; __be16 func_id; __be32 num_pages; __be32 rsvd1[5]; @@ -1201,6 +1203,9 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_ODP(mdev, cap)\ MLX5_GET(odp_cap, mdev->caps.hca_cur[MLX5_CAP_ODP], cap) +#define MLX5_CAP_ODP_MAX(mdev, cap)\ + MLX5_GET(odp_cap, mdev->caps.hca_max[MLX5_CAP_ODP], cap) + #define MLX5_CAP_VECTOR_CALC(mdev, cap) \ MLX5_GET(vector_calc_cap, \ mdev->caps.hca_cur[MLX5_CAP_VECTOR_CALC], cap) diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 54299251d40d..c2de50f02b33 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -522,6 +522,7 @@ struct mlx5_priv { atomic_t reg_pages; struct list_head free_list; int vfs_pages; + int peer_pf_pages; struct mlx5_core_health health; @@ -652,6 +653,7 @@ struct mlx5_core_dev { u32 mcam[MLX5_ST_SZ_DW(mcam_reg)]; u32 fpga[MLX5_ST_SZ_DW(fpga_cap)]; u32 qcam[MLX5_ST_SZ_DW(qcam_reg)]; + u8 embedded_cpu; } caps; u64 sys_image_guid; phys_addr_t iseg_base; @@ -850,11 +852,30 @@ void mlx5_cmd_cleanup(struct mlx5_core_dev *dev); void mlx5_cmd_use_events(struct mlx5_core_dev *dev); void mlx5_cmd_use_polling(struct mlx5_core_dev *dev); +struct mlx5_async_ctx { + struct mlx5_core_dev *dev; + atomic_t num_inflight; + struct wait_queue_head wait; +}; + +struct mlx5_async_work; + +typedef void (*mlx5_async_cbk_t)(int status, struct mlx5_async_work *context); + +struct mlx5_async_work { + struct mlx5_async_ctx *ctx; + mlx5_async_cbk_t user_callback; +}; + +void mlx5_cmd_init_async_ctx(struct mlx5_core_dev *dev, + struct mlx5_async_ctx *ctx); +void mlx5_cmd_cleanup_async_ctx(struct mlx5_async_ctx *ctx); +int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size, + void *out, int out_size, mlx5_async_cbk_t callback, + struct mlx5_async_work *work); + int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size); -int mlx5_cmd_exec_cb(struct mlx5_core_dev *dev, void *in, int in_size, - void *out, int out_size, mlx5_cmd_cbk_t callback, - void *context); int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size); void mlx5_cmd_mbox_status(void *out, u8 *status, u32 *syndrome); @@ -885,9 +906,10 @@ void mlx5_init_mkey_table(struct mlx5_core_dev *dev); void mlx5_cleanup_mkey_table(struct mlx5_core_dev *dev); int mlx5_core_create_mkey_cb(struct mlx5_core_dev *dev, struct mlx5_core_mkey *mkey, - u32 *in, int inlen, - u32 *out, int outlen, - mlx5_cmd_cbk_t callback, void *context); + struct mlx5_async_ctx *async_ctx, u32 *in, + int inlen, u32 *out, int outlen, + mlx5_async_cbk_t callback, + struct mlx5_async_work *context); int mlx5_core_create_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mkey *mkey, u32 *in, int inlen); @@ -897,14 +919,12 @@ int mlx5_core_query_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mkey *mkey, u32 *out, int outlen); int mlx5_core_alloc_pd(struct mlx5_core_dev *dev, u32 *pdn); int mlx5_core_dealloc_pd(struct mlx5_core_dev *dev, u32 pdn); -int mlx5_core_mad_ifc(struct mlx5_core_dev *dev, const void *inb, void *outb, - u16 opmod, u8 port); int mlx5_pagealloc_init(struct mlx5_core_dev *dev); void mlx5_pagealloc_cleanup(struct mlx5_core_dev *dev); void mlx5_pagealloc_start(struct mlx5_core_dev *dev); void mlx5_pagealloc_stop(struct mlx5_core_dev *dev); void mlx5_core_req_pages_handler(struct mlx5_core_dev *dev, u16 func_id, - s32 npages); + s32 npages, bool ec_function); int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot); int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev); void mlx5_register_debugfs(void); @@ -1058,11 +1078,29 @@ static inline int mlx5_core_is_pf(struct mlx5_core_dev *dev) return !(dev->priv.pci_dev_data & MLX5_PCI_DEV_IS_VF); } -#define MLX5_TOTAL_VPORTS(mdev) (1 + pci_sriov_get_totalvfs((mdev)->pdev)) -#define MLX5_VPORT_MANAGER(mdev) \ - (MLX5_CAP_GEN(mdev, vport_group_manager) && \ - (MLX5_CAP_GEN(mdev, port_type) == MLX5_CAP_PORT_TYPE_ETH) && \ - mlx5_core_is_pf(mdev)) +static inline bool mlx5_core_is_ecpf(struct mlx5_core_dev *dev) +{ + return dev->caps.embedded_cpu; +} + +static inline bool mlx5_core_is_ecpf_esw_manager(struct mlx5_core_dev *dev) +{ + return dev->caps.embedded_cpu && MLX5_CAP_GEN(dev, eswitch_manager); +} + +static inline bool mlx5_ecpf_vport_exists(struct mlx5_core_dev *dev) +{ + return mlx5_core_is_pf(dev) && MLX5_CAP_ESW(dev, ecpf_vport_exists); +} + +#define MLX5_HOST_PF_MAX_VFS (127u) +static inline u16 mlx5_core_max_vfs(struct mlx5_core_dev *dev) +{ + if (mlx5_core_is_ecpf_esw_manager(dev)) + return MLX5_HOST_PF_MAX_VFS; + else + return pci_sriov_get_totalvfs(dev->pdev); +} static inline int mlx5_get_gid_table_len(u16 param) { diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index fab5121ffb8f..96d8435421de 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -22,6 +22,12 @@ enum { NUM_REP_TYPES, }; +enum { + REP_UNREGISTERED, + REP_REGISTERED, + REP_LOADED, +}; + struct mlx5_eswitch_rep; struct mlx5_eswitch_rep_if { int (*load)(struct mlx5_core_dev *dev, @@ -29,7 +35,7 @@ struct mlx5_eswitch_rep_if { void (*unload)(struct mlx5_eswitch_rep *rep); void *(*get_proto_dev)(struct mlx5_eswitch_rep *rep); void *priv; - bool valid; + u8 state; }; struct mlx5_eswitch_rep { @@ -40,13 +46,10 @@ struct mlx5_eswitch_rep { u32 vlan_refcount; }; -void mlx5_eswitch_register_vport_rep(struct mlx5_eswitch *esw, - int vport_index, - struct mlx5_eswitch_rep_if *rep_if, - u8 rep_type); -void mlx5_eswitch_unregister_vport_rep(struct mlx5_eswitch *esw, - int vport_index, - u8 rep_type); +void mlx5_eswitch_register_vport_reps(struct mlx5_eswitch *esw, + struct mlx5_eswitch_rep_if *rep_if, + u8 rep_type); +void mlx5_eswitch_unregister_vport_reps(struct mlx5_eswitch *esw, u8 rep_type); void *mlx5_eswitch_get_proto_dev(struct mlx5_eswitch *esw, int vport, u8 rep_type); diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 35fe5217b244..b7bb774b57b0 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -72,6 +72,7 @@ enum { enum { MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE = 0x0, + MLX5_SET_HCA_CAP_OP_MOD_ODP = 0x2, MLX5_SET_HCA_CAP_OP_MOD_ATOMIC = 0x3, }; @@ -141,6 +142,7 @@ enum { MLX5_CMD_OP_QUERY_XRQ_DC_PARAMS_ENTRY = 0x725, MLX5_CMD_OP_SET_XRQ_DC_PARAMS_ENTRY = 0x726, MLX5_CMD_OP_QUERY_XRQ_ERROR_PARAMS = 0x727, + MLX5_CMD_OP_QUERY_HOST_PARAMS = 0x740, MLX5_CMD_OP_QUERY_VPORT_STATE = 0x750, MLX5_CMD_OP_MODIFY_VPORT_STATE = 0x751, MLX5_CMD_OP_QUERY_ESW_VPORT_CONTEXT = 0x752, @@ -629,7 +631,8 @@ struct mlx5_ifc_e_switch_cap_bits { u8 vport_svlan_insert[0x1]; u8 vport_cvlan_insert_if_not_exist[0x1]; u8 vport_cvlan_insert_overwrite[0x1]; - u8 reserved_at_5[0x17]; + u8 reserved_at_5[0x16]; + u8 ecpf_vport_exists[0x1]; u8 counter_eswitch_affinity[0x1]; u8 merged_eswitch[0x1]; u8 nic_vport_node_guid_modify[0x1]; @@ -831,7 +834,9 @@ struct mlx5_ifc_odp_cap_bits { struct mlx5_ifc_odp_per_transport_service_cap_bits ud_odp_caps; - u8 reserved_at_e0[0x720]; + struct mlx5_ifc_odp_per_transport_service_cap_bits xrc_odp_caps; + + u8 reserved_at_100[0x700]; }; struct mlx5_ifc_calc_op { @@ -4438,7 +4443,8 @@ struct mlx5_ifc_query_pages_out_bits { u8 syndrome[0x20]; - u8 reserved_at_40[0x10]; + u8 embedded_cpu_function[0x1]; + u8 reserved_at_41[0xf]; u8 function_id[0x10]; u8 num_pages[0x20]; @@ -4457,7 +4463,8 @@ struct mlx5_ifc_query_pages_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x10]; + u8 embedded_cpu_function[0x1]; + u8 reserved_at_41[0xf]; u8 function_id[0x10]; u8 reserved_at_60[0x20]; @@ -5877,7 +5884,8 @@ struct mlx5_ifc_manage_pages_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x10]; + u8 embedded_cpu_function[0x1]; + u8 reserved_at_41[0xf]; u8 function_id[0x10]; u8 input_num_entries[0x20]; @@ -6055,7 +6063,8 @@ struct mlx5_ifc_enable_hca_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x10]; + u8 embedded_cpu_function[0x1]; + u8 reserved_at_41[0xf]; u8 function_id[0x10]; u8 reserved_at_60[0x20]; @@ -6099,7 +6108,8 @@ struct mlx5_ifc_disable_hca_in_bits { u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_at_40[0x10]; + u8 embedded_cpu_function[0x1]; + u8 reserved_at_41[0xf]; u8 function_id[0x10]; u8 reserved_at_60[0x20]; @@ -7817,21 +7827,23 @@ struct mlx5_ifc_ptys_reg_bits { u8 proto_mask[0x3]; u8 an_status[0x4]; - u8 reserved_at_24[0x3c]; + u8 reserved_at_24[0x1c]; + + u8 ext_eth_proto_capability[0x20]; u8 eth_proto_capability[0x20]; u8 ib_link_width_capability[0x10]; u8 ib_proto_capability[0x10]; - u8 reserved_at_a0[0x20]; + u8 ext_eth_proto_admin[0x20]; u8 eth_proto_admin[0x20]; u8 ib_link_width_admin[0x10]; u8 ib_proto_admin[0x10]; - u8 reserved_at_100[0x20]; + u8 ext_eth_proto_oper[0x20]; u8 eth_proto_oper[0x20]; @@ -8280,7 +8292,9 @@ struct mlx5_ifc_mpegc_reg_bits { struct mlx5_ifc_pcam_enhanced_features_bits { u8 reserved_at_0[0x6d]; u8 rx_icrc_encapsulated_counter[0x1]; - u8 reserved_at_6e[0x8]; + u8 reserved_at_6e[0x4]; + u8 ptys_extended_ethernet[0x1]; + u8 reserved_at_73[0x3]; u8 pfcc_mask[0x1]; u8 reserved_at_77[0x3]; u8 per_lane_error_counters[0x1]; @@ -8746,7 +8760,8 @@ struct mlx5_ifc_initial_seg_bits { u8 initializing[0x1]; u8 reserved_at_fe1[0x4]; u8 nic_interface_supported[0x3]; - u8 reserved_at_fe8[0x18]; + u8 embedded_cpu[0x1]; + u8 reserved_at_fe9[0x17]; struct mlx5_ifc_health_buffer_bits health_buffer; @@ -9513,4 +9528,44 @@ struct mlx5_ifc_mtrc_ctrl_bits { u8 reserved_at_80[0x180]; }; +struct mlx5_ifc_host_params_context_bits { + u8 host_number[0x8]; + u8 reserved_at_8[0x8]; + u8 host_num_of_vfs[0x10]; + + u8 reserved_at_20[0x10]; + u8 host_pci_bus[0x10]; + + u8 reserved_at_40[0x10]; + u8 host_pci_device[0x10]; + + u8 reserved_at_60[0x10]; + u8 host_pci_function[0x10]; + + u8 reserved_at_80[0x180]; +}; + +struct mlx5_ifc_query_host_params_in_bits { + u8 opcode[0x10]; + u8 reserved_at_10[0x10]; + + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_query_host_params_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + + u8 syndrome[0x20]; + + u8 reserved_at_40[0x40]; + + struct mlx5_ifc_host_params_context_bits host_params_context; + + u8 reserved_at_280[0x180]; +}; + #endif /* MLX5_IFC_H */ diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index bf4bc01ffb0c..814fa194663b 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -92,6 +92,22 @@ enum mlx5e_link_mode { MLX5E_LINK_MODES_NUMBER, }; +enum mlx5e_ext_link_mode { + MLX5E_SGMII_100M = 0, + MLX5E_1000BASE_X_SGMII = 1, + MLX5E_5GBASE_R = 3, + MLX5E_10GBASE_XFI_XAUI_1 = 4, + MLX5E_40GBASE_XLAUI_4_XLPPI_4 = 5, + MLX5E_25GAUI_1_25GBASE_CR_KR = 6, + MLX5E_50GAUI_2_LAUI_2_50GBASE_CR2_KR2 = 7, + MLX5E_50GAUI_1_LAUI_1_50GBASE_CR_KR = 8, + MLX5E_CAUI_4_100GBASE_CR4_KR4 = 9, + MLX5E_100GAUI_2_100GBASE_CR2_KR2 = 10, + MLX5E_200GAUI_4_200GBASE_CR4_KR4 = 12, + MLX5E_400GAUI_8 = 15, + MLX5E_EXT_LINK_MODES_NUMBER, +}; + enum mlx5e_connector_type { MLX5E_PORT_UNKNOWN = 0, MLX5E_PORT_NONE = 1, @@ -106,31 +122,23 @@ enum mlx5e_connector_type { }; #define MLX5E_PROT_MASK(link_mode) (1 << link_mode) +#define MLX5_GET_ETH_PROTO(reg, out, ext, field) \ + (ext ? MLX5_GET(reg, out, ext_##field) : \ + MLX5_GET(reg, out, field)) int mlx5_set_port_caps(struct mlx5_core_dev *dev, u8 port_num, u32 caps); int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys, int ptys_size, int proto_mask, u8 local_port); -int mlx5_query_port_proto_cap(struct mlx5_core_dev *dev, - u32 *proto_cap, int proto_mask); -int mlx5_query_port_proto_admin(struct mlx5_core_dev *dev, - u32 *proto_admin, int proto_mask); int mlx5_query_port_link_width_oper(struct mlx5_core_dev *dev, u8 *link_width_oper, u8 local_port); int mlx5_query_port_ib_proto_oper(struct mlx5_core_dev *dev, u8 *proto_oper, u8 local_port); -int mlx5_query_port_eth_proto_oper(struct mlx5_core_dev *dev, - u32 *proto_oper, u8 local_port); -int mlx5_set_port_ptys(struct mlx5_core_dev *dev, bool an_disable, - u32 proto_admin, int proto_mask); void mlx5_toggle_port_link(struct mlx5_core_dev *dev); int mlx5_set_port_admin_status(struct mlx5_core_dev *dev, enum mlx5_port_status status); int mlx5_query_port_admin_status(struct mlx5_core_dev *dev, enum mlx5_port_status *status); int mlx5_set_port_beacon(struct mlx5_core_dev *dev, u16 beacon_duration); -void mlx5_query_port_autoneg(struct mlx5_core_dev *dev, int proto_mask, - u8 *an_status, - u8 *an_disable_cap, u8 *an_disable_admin); int mlx5_set_port_mtu(struct mlx5_core_dev *dev, u16 mtu, u8 port); void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, u16 *max_mtu, u8 port); diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index 9c694808c212..0eef548b9946 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -36,15 +36,38 @@ #include <linux/mlx5/driver.h> #include <linux/mlx5/device.h> +#define MLX5_VPORT_PF_PLACEHOLDER (1u) +#define MLX5_VPORT_UPLINK_PLACEHOLDER (1u) +#define MLX5_VPORT_ECPF_PLACEHOLDER(mdev) (mlx5_ecpf_vport_exists(mdev)) + +#define MLX5_SPECIAL_VPORTS(mdev) (MLX5_VPORT_PF_PLACEHOLDER + \ + MLX5_VPORT_UPLINK_PLACEHOLDER + \ + MLX5_VPORT_ECPF_PLACEHOLDER(mdev)) + +#define MLX5_TOTAL_VPORTS(mdev) (MLX5_SPECIAL_VPORTS(mdev) + \ + mlx5_core_max_vfs(mdev)) + +#define MLX5_VPORT_MANAGER(mdev) \ + (MLX5_CAP_GEN(mdev, vport_group_manager) && \ + (MLX5_CAP_GEN(mdev, port_type) == MLX5_CAP_PORT_TYPE_ETH) && \ + mlx5_core_is_pf(mdev)) + enum { MLX5_CAP_INLINE_MODE_L2, MLX5_CAP_INLINE_MODE_VPORT_CONTEXT, MLX5_CAP_INLINE_MODE_NOT_REQUIRED, }; +enum { + MLX5_VPORT_PF = 0x0, + MLX5_VPORT_FIRST_VF = 0x1, + MLX5_VPORT_ECPF = 0xfffe, + MLX5_VPORT_UPLINK = 0xffff +}; + u8 mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport); int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod, - u16 vport, u8 state); + u16 vport, u8 other_vport, u8 state); int mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev, u16 vport, u8 *addr); int mlx5_query_nic_vport_min_inline(struct mlx5_core_dev *mdev, @@ -60,7 +83,7 @@ int mlx5_query_nic_vport_system_image_guid(struct mlx5_core_dev *mdev, u64 *system_image_guid); int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid); int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev, - u32 vport, u64 node_guid); + u16 vport, u64 node_guid); int mlx5_query_nic_vport_qkey_viol_cntr(struct mlx5_core_dev *mdev, u16 *qkey_viol_cntr); int mlx5_query_hca_vport_gid(struct mlx5_core_dev *dev, u8 other_vport, @@ -78,7 +101,7 @@ int mlx5_query_hca_vport_system_image_guid(struct mlx5_core_dev *dev, int mlx5_query_hca_vport_node_guid(struct mlx5_core_dev *dev, u64 *node_guid); int mlx5_query_nic_vport_mac_list(struct mlx5_core_dev *dev, - u32 vport, + u16 vport, enum mlx5_list_type list_type, u8 addr_list[][ETH_ALEN], int *list_size); @@ -87,7 +110,7 @@ int mlx5_modify_nic_vport_mac_list(struct mlx5_core_dev *dev, u8 addr_list[][ETH_ALEN], int list_size); int mlx5_query_nic_vport_promisc(struct mlx5_core_dev *mdev, - u32 vport, + u16 vport, int *promisc_uc, int *promisc_mc, int *promisc_all); @@ -96,7 +119,7 @@ int mlx5_modify_nic_vport_promisc(struct mlx5_core_dev *mdev, int promisc_mc, int promisc_all); int mlx5_query_nic_vport_vlans(struct mlx5_core_dev *dev, - u32 vport, + u16 vport, u16 vlans[], int *size); int mlx5_modify_nic_vport_vlans(struct mlx5_core_dev *dev, @@ -106,7 +129,7 @@ int mlx5_modify_nic_vport_vlans(struct mlx5_core_dev *dev, int mlx5_nic_vport_enable_roce(struct mlx5_core_dev *mdev); int mlx5_nic_vport_disable_roce(struct mlx5_core_dev *mdev); int mlx5_query_vport_down_stats(struct mlx5_core_dev *mdev, u16 vport, - u64 *rx_discard_vport_down, + u8 other_vport, u64 *rx_discard_vport_down, u64 *tx_discard_vport_down); int mlx5_core_query_vport_counter(struct mlx5_core_dev *dev, u8 other_vport, int vf, u8 port_num, void *out, diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 2c471a2c43fa..0a36a22228e7 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -95,6 +95,13 @@ struct page { */ unsigned long private; }; + struct { /* page_pool used by netstack */ + /** + * @dma_addr: might require a 64-bit value even on + * 32-bit architectures. + */ + dma_addr_t dma_addr; + }; struct { /* slab, slob and slub */ union { struct list_head slab_list; /* uses lru */ diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index de7377815b6b..8ef330027b13 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -308,6 +308,7 @@ struct mmc_card { unsigned int nr_parts; unsigned int bouncesz; /* Bounce buffer size */ + struct workqueue_struct *complete_wq; /* Private workqueue */ }; static inline bool mmc_large_sector(struct mmc_card *card) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e675ef97a426..aab4d9f6613d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -868,7 +868,6 @@ enum bpf_netdev_command { /* BPF program for offload callbacks, invoked at program load time. */ BPF_OFFLOAD_MAP_ALLOC, BPF_OFFLOAD_MAP_FREE, - XDP_QUERY_XSK_UMEM, XDP_SETUP_XSK_UMEM, }; @@ -895,10 +894,10 @@ struct netdev_bpf { struct { struct bpf_offloaded_map *offmap; }; - /* XDP_QUERY_XSK_UMEM, XDP_SETUP_XSK_UMEM */ + /* XDP_SETUP_XSK_UMEM */ struct { - struct xdp_umem *umem; /* out for query*/ - u16 queue_id; /* in for query */ + struct xdp_umem *umem; + u16 queue_id; } xsk; }; }; @@ -1188,6 +1187,10 @@ struct dev_ifalias { * not implement this, it is assumed that the hw is not able to have * multiple net devices on single physical port. * + * int (*ndo_get_port_parent_id)(struct net_device *dev, + * struct netdev_phys_item_id *ppid) + * Called to get the parent ID of the physical port of this device. + * * void (*ndo_udp_tunnel_add)(struct net_device *dev, * struct udp_tunnel_info *ti); * Called by UDP tunnel to notify a driver about the UDP port and socket @@ -1412,6 +1415,8 @@ struct net_device_ops { bool new_carrier); int (*ndo_get_phys_port_id)(struct net_device *dev, struct netdev_phys_item_id *ppid); + int (*ndo_get_port_parent_id)(struct net_device *dev, + struct netdev_phys_item_id *ppid); int (*ndo_get_phys_port_name)(struct net_device *dev, char *name, size_t len); void (*ndo_udp_tunnel_add)(struct net_device *dev, @@ -1486,6 +1491,7 @@ struct net_device_ops { * @IFF_NO_RX_HANDLER: device doesn't support the rx_handler hook * @IFF_FAILOVER: device is a failover master device * @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device + * @IFF_L3MDEV_RX_HANDLER: only invoke the rx handler of L3 master device */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1517,6 +1523,7 @@ enum netdev_priv_flags { IFF_NO_RX_HANDLER = 1<<26, IFF_FAILOVER = 1<<27, IFF_FAILOVER_SLAVE = 1<<28, + IFF_L3MDEV_RX_HANDLER = 1<<29, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1547,6 +1554,7 @@ enum netdev_priv_flags { #define IFF_NO_RX_HANDLER IFF_NO_RX_HANDLER #define IFF_FAILOVER IFF_FAILOVER #define IFF_FAILOVER_SLAVE IFF_FAILOVER_SLAVE +#define IFF_L3MDEV_RX_HANDLER IFF_L3MDEV_RX_HANDLER /** * struct net_device - The DEVICE structure. @@ -3651,6 +3659,9 @@ int dev_get_phys_port_id(struct net_device *dev, struct netdev_phys_item_id *ppid); int dev_get_phys_port_name(struct net_device *dev, char *name, size_t len); +int dev_get_port_parent_id(struct net_device *dev, + struct netdev_phys_item_id *ppid, bool recurse); +bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b); int dev_change_proto_down(struct net_device *dev, bool proto_down); struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again); struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, @@ -4552,6 +4563,11 @@ static inline bool netif_supports_nofcs(struct net_device *dev) return dev->priv_flags & IFF_SUPP_NOFCS; } +static inline bool netif_has_l3_rx_handler(const struct net_device *dev) +{ + return dev->priv_flags & IFF_L3MDEV_RX_HANDLER; +} + static inline bool netif_is_l3_master(const struct net_device *dev) { return dev->priv_flags & IFF_L3MDEV_MASTER; @@ -4663,22 +4679,22 @@ static inline const char *netdev_reg_state(const struct net_device *dev) return " (unknown)"; } -__printf(3, 4) +__printf(3, 4) __cold void netdev_printk(const char *level, const struct net_device *dev, const char *format, ...); -__printf(2, 3) +__printf(2, 3) __cold void netdev_emerg(const struct net_device *dev, const char *format, ...); -__printf(2, 3) +__printf(2, 3) __cold void netdev_alert(const struct net_device *dev, const char *format, ...); -__printf(2, 3) +__printf(2, 3) __cold void netdev_crit(const struct net_device *dev, const char *format, ...); -__printf(2, 3) +__printf(2, 3) __cold void netdev_err(const struct net_device *dev, const char *format, ...); -__printf(2, 3) +__printf(2, 3) __cold void netdev_warn(const struct net_device *dev, const char *format, ...); -__printf(2, 3) +__printf(2, 3) __cold void netdev_notice(const struct net_device *dev, const char *format, ...); -__printf(2, 3) +__printf(2, 3) __cold void netdev_info(const struct net_device *dev, const char *format, ...); #define netdev_level_once(level, dev, fmt, ...) \ diff --git a/include/linux/objagg.h b/include/linux/objagg.h index 34f38c186ea0..78021777df46 100644 --- a/include/linux/objagg.h +++ b/include/linux/objagg.h @@ -6,14 +6,19 @@ struct objagg_ops { size_t obj_size; + bool (*delta_check)(void *priv, const void *parent_obj, + const void *obj); + int (*hints_obj_cmp)(const void *obj1, const void *obj2); void * (*delta_create)(void *priv, void *parent_obj, void *obj); void (*delta_destroy)(void *priv, void *delta_priv); - void * (*root_create)(void *priv, void *obj); + void * (*root_create)(void *priv, void *obj, unsigned int root_id); +#define OBJAGG_OBJ_ROOT_ID_INVALID UINT_MAX void (*root_destroy)(void *priv, void *root_priv); }; struct objagg; struct objagg_obj; +struct objagg_hints; const void *objagg_obj_root_priv(const struct objagg_obj *objagg_obj); const void *objagg_obj_delta_priv(const struct objagg_obj *objagg_obj); @@ -21,7 +26,8 @@ const void *objagg_obj_raw(const struct objagg_obj *objagg_obj); struct objagg_obj *objagg_obj_get(struct objagg *objagg, void *obj); void objagg_obj_put(struct objagg *objagg, struct objagg_obj *objagg_obj); -struct objagg *objagg_create(const struct objagg_ops *ops, void *priv); +struct objagg *objagg_create(const struct objagg_ops *ops, + struct objagg_hints *hints, void *priv); void objagg_destroy(struct objagg *objagg); struct objagg_obj_stats { @@ -36,6 +42,7 @@ struct objagg_obj_stats_info { }; struct objagg_stats { + unsigned int root_count; unsigned int stats_info_count; struct objagg_obj_stats_info stats_info[]; }; @@ -43,4 +50,14 @@ struct objagg_stats { const struct objagg_stats *objagg_stats_get(struct objagg *objagg); void objagg_stats_put(const struct objagg_stats *objagg_stats); +enum objagg_opt_algo_type { + OBJAGG_OPT_ALGO_SIMPLE_GREEDY, +}; + +struct objagg_hints *objagg_hints_get(struct objagg *objagg, + enum objagg_opt_algo_type opt_algo_type); +void objagg_hints_put(struct objagg_hints *objagg_hints); +const struct objagg_stats * +objagg_hints_stats_get(struct objagg_hints *objagg_hints); + #endif diff --git a/include/linux/phy.h b/include/linux/phy.h index 70f83d0d7469..3db507e68191 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -502,6 +502,12 @@ struct phy_driver { */ int (*probe)(struct phy_device *phydev); + /* + * Probe the hardware to determine what abilities it has. + * Should only set phydev->supported. + */ + int (*get_features)(struct phy_device *phydev); + /* PHY Power Management */ int (*suspend)(struct phy_device *phydev); int (*resume)(struct phy_device *phydev); @@ -667,13 +673,8 @@ phy_lookup_setting(int speed, int duplex, const unsigned long *mask, bool exact); size_t phy_speeds(unsigned int *speeds, size_t size, unsigned long *mask); - -static inline bool __phy_is_started(struct phy_device *phydev) -{ - WARN_ON(!mutex_is_locked(&phydev->lock)); - - return phydev->state >= PHY_UP; -} +void of_set_phy_supported(struct phy_device *phydev); +void of_set_phy_eee_broken(struct phy_device *phydev); /** * phy_is_started - Convenience function to check whether PHY is started @@ -681,29 +682,12 @@ static inline bool __phy_is_started(struct phy_device *phydev) */ static inline bool phy_is_started(struct phy_device *phydev) { - bool started; - - mutex_lock(&phydev->lock); - started = __phy_is_started(phydev); - mutex_unlock(&phydev->lock); - - return started; + return phydev->state >= PHY_UP; } void phy_resolve_aneg_linkmode(struct phy_device *phydev); /** - * phy_read_mmd - Convenience function for reading a register - * from an MMD on a given PHY. - * @phydev: The phy_device struct - * @devad: The MMD to read from - * @regnum: The register on the MMD to read - * - * Same rules as for phy_read(); - */ -int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum); - -/** * phy_read - Convenience function for reading a given PHY register * @phydev: the phy_device struct * @regnum: register number to read @@ -758,9 +742,68 @@ static inline int __phy_write(struct phy_device *phydev, u32 regnum, u16 val) val); } +/** + * phy_read_mmd - Convenience function for reading a register + * from an MMD on a given PHY. + * @phydev: The phy_device struct + * @devad: The MMD to read from + * @regnum: The register on the MMD to read + * + * Same rules as for phy_read(); + */ +int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum); + +/** + * __phy_read_mmd - Convenience function for reading a register + * from an MMD on a given PHY. + * @phydev: The phy_device struct + * @devad: The MMD to read from + * @regnum: The register on the MMD to read + * + * Same rules as for __phy_read(); + */ +int __phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum); + +/** + * phy_write_mmd - Convenience function for writing a register + * on an MMD on a given PHY. + * @phydev: The phy_device struct + * @devad: The MMD to write to + * @regnum: The register on the MMD to read + * @val: value to write to @regnum + * + * Same rules as for phy_write(); + */ +int phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val); + +/** + * __phy_write_mmd - Convenience function for writing a register + * on an MMD on a given PHY. + * @phydev: The phy_device struct + * @devad: The MMD to write to + * @regnum: The register on the MMD to read + * @val: value to write to @regnum + * + * Same rules as for __phy_write(); + */ +int __phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val); + +int __phy_modify_changed(struct phy_device *phydev, u32 regnum, u16 mask, + u16 set); +int phy_modify_changed(struct phy_device *phydev, u32 regnum, u16 mask, + u16 set); int __phy_modify(struct phy_device *phydev, u32 regnum, u16 mask, u16 set); int phy_modify(struct phy_device *phydev, u32 regnum, u16 mask, u16 set); +int __phy_modify_mmd_changed(struct phy_device *phydev, int devad, u32 regnum, + u16 mask, u16 set); +int phy_modify_mmd_changed(struct phy_device *phydev, int devad, u32 regnum, + u16 mask, u16 set); +int __phy_modify_mmd(struct phy_device *phydev, int devad, u32 regnum, + u16 mask, u16 set); +int phy_modify_mmd(struct phy_device *phydev, int devad, u32 regnum, + u16 mask, u16 set); + /** * __phy_set_bits - Convenience function for setting bits in a PHY register * @phydev: the phy_device struct @@ -811,6 +854,66 @@ static inline int phy_clear_bits(struct phy_device *phydev, u32 regnum, u16 val) } /** + * __phy_set_bits_mmd - Convenience function for setting bits in a register + * on MMD + * @phydev: the phy_device struct + * @devad: the MMD containing register to modify + * @regnum: register number to modify + * @val: bits to set + * + * The caller must have taken the MDIO bus lock. + */ +static inline int __phy_set_bits_mmd(struct phy_device *phydev, int devad, + u32 regnum, u16 val) +{ + return __phy_modify_mmd(phydev, devad, regnum, 0, val); +} + +/** + * __phy_clear_bits_mmd - Convenience function for clearing bits in a register + * on MMD + * @phydev: the phy_device struct + * @devad: the MMD containing register to modify + * @regnum: register number to modify + * @val: bits to clear + * + * The caller must have taken the MDIO bus lock. + */ +static inline int __phy_clear_bits_mmd(struct phy_device *phydev, int devad, + u32 regnum, u16 val) +{ + return __phy_modify_mmd(phydev, devad, regnum, val, 0); +} + +/** + * phy_set_bits_mmd - Convenience function for setting bits in a register + * on MMD + * @phydev: the phy_device struct + * @devad: the MMD containing register to modify + * @regnum: register number to modify + * @val: bits to set + */ +static inline int phy_set_bits_mmd(struct phy_device *phydev, int devad, + u32 regnum, u16 val) +{ + return phy_modify_mmd(phydev, devad, regnum, 0, val); +} + +/** + * phy_clear_bits_mmd - Convenience function for clearing bits in a register + * on MMD + * @phydev: the phy_device struct + * @devad: the MMD containing register to modify + * @regnum: register number to modify + * @val: bits to clear + */ +static inline int phy_clear_bits_mmd(struct phy_device *phydev, int devad, + u32 regnum, u16 val) +{ + return phy_modify_mmd(phydev, devad, regnum, val, 0); +} + +/** * phy_interrupt_is_valid - Convenience function for testing a given PHY irq * @phydev: the phy_device struct * @@ -886,18 +989,6 @@ static inline bool phy_is_pseudo_fixed_link(struct phy_device *phydev) return phydev->is_pseudo_fixed_link; } -/** - * phy_write_mmd - Convenience function for writing a register - * on an MMD on a given PHY. - * @phydev: The phy_device struct - * @devad: The MMD to read from - * @regnum: The register on the MMD to read - * @val: value to write to @regnum - * - * Same rules as for phy_write(); - */ -int phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val); - int phy_save_page(struct phy_device *phydev); int phy_select_page(struct phy_device *phydev, int page); int phy_restore_page(struct phy_device *phydev, int oldpage, int ret); @@ -1006,12 +1097,14 @@ int genphy_write_mmd_unsupported(struct phy_device *phdev, int devnum, /* Clause 45 PHY */ int genphy_c45_restart_aneg(struct phy_device *phydev); int genphy_c45_aneg_done(struct phy_device *phydev); -int genphy_c45_read_link(struct phy_device *phydev, u32 mmd_mask); +int genphy_c45_read_link(struct phy_device *phydev); int genphy_c45_read_lpa(struct phy_device *phydev); int genphy_c45_read_pma(struct phy_device *phydev); int genphy_c45_pma_setup_forced(struct phy_device *phydev); +int genphy_c45_an_config_aneg(struct phy_device *phydev); int genphy_c45_an_disable_aneg(struct phy_device *phydev); int genphy_c45_read_mdix(struct phy_device *phydev); +int genphy_c45_pma_read_abilities(struct phy_device *phydev); /* The gen10g_* functions are the old Clause 45 stub */ int gen10g_config_aneg(struct phy_device *phydev); diff --git a/include/linux/phy_fixed.h b/include/linux/phy_fixed.h index 9525567b1951..1e5d86ebdaeb 100644 --- a/include/linux/phy_fixed.h +++ b/include/linux/phy_fixed.h @@ -15,30 +15,41 @@ struct device_node; #if IS_ENABLED(CONFIG_FIXED_PHY) extern int fixed_phy_change_carrier(struct net_device *dev, bool new_carrier); extern int fixed_phy_add(unsigned int irq, int phy_id, - struct fixed_phy_status *status, - int link_gpio); + struct fixed_phy_status *status); extern struct phy_device *fixed_phy_register(unsigned int irq, struct fixed_phy_status *status, - int link_gpio, struct device_node *np); + +extern struct phy_device * +fixed_phy_register_with_gpiod(unsigned int irq, + struct fixed_phy_status *status, + struct gpio_desc *gpiod); + extern void fixed_phy_unregister(struct phy_device *phydev); extern int fixed_phy_set_link_update(struct phy_device *phydev, int (*link_update)(struct net_device *, struct fixed_phy_status *)); #else static inline int fixed_phy_add(unsigned int irq, int phy_id, - struct fixed_phy_status *status, - int link_gpio) + struct fixed_phy_status *status) { return -ENODEV; } static inline struct phy_device *fixed_phy_register(unsigned int irq, struct fixed_phy_status *status, - int gpio_link, struct device_node *np) { return ERR_PTR(-ENODEV); } + +static inline struct phy_device * +fixed_phy_register_with_gpiod(unsigned int irq, + struct fixed_phy_status *status, + struct gpio_desc *gpiod) +{ + return ERR_PTR(-ENODEV); +} + static inline void fixed_phy_unregister(struct phy_device *phydev) { } diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 021fc6595856..f57059e4353f 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -220,6 +220,7 @@ void phylink_ethtool_get_pauseparam(struct phylink *, int phylink_ethtool_set_pauseparam(struct phylink *, struct ethtool_pauseparam *); int phylink_get_eee_err(struct phylink *); +int phylink_init_eee(struct phylink *, bool); int phylink_ethtool_get_eee(struct phylink *, struct ethtool_eee *); int phylink_ethtool_set_eee(struct phylink *, struct ethtool_eee *); int phylink_mii_ioctl(struct phylink *, struct ifreq *, int); diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index 54af4eef169f..fed5be706bc9 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -105,7 +105,7 @@ static inline bool pm_runtime_callbacks_present(struct device *dev) static inline void pm_runtime_mark_last_busy(struct device *dev) { - WRITE_ONCE(dev->power.last_busy, ktime_to_ns(ktime_get())); + WRITE_ONCE(dev->power.last_busy, ktime_get_mono_fast_ns()); } static inline bool pm_runtime_is_irq_safe(struct device *dev) diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h index 186cd8e970c7..8da46ac44a2e 100644 --- a/include/linux/ptr_ring.h +++ b/include/linux/ptr_ring.h @@ -26,7 +26,6 @@ #include <linux/cache.h> #include <linux/types.h> #include <linux/compiler.h> -#include <linux/cache.h> #include <linux/slab.h> #include <asm/errno.h> #endif diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 35170f74ed80..f6165d304b4d 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -643,6 +643,7 @@ struct qed_dev_info { u16 mtu; bool wol_support; + bool smart_an; /* MBI version */ u32 mbi_version; diff --git a/include/linux/sched.h b/include/linux/sched.h index d2f90fa92468..bba3afb4e9bf 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -995,7 +995,7 @@ struct task_struct { /* cg_list protected by css_set_lock and tsk->alloc_lock: */ struct list_head cg_list; #endif -#ifdef CONFIG_X86_RESCTRL +#ifdef CONFIG_X86_CPU_RESCTRL u32 closid; u32 rmid; #endif diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index ec912d01126f..ecdc6542070f 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -71,6 +71,7 @@ static inline int get_dumpable(struct mm_struct *mm) #define MMF_HUGE_ZERO_PAGE 23 /* mm has ever used the global huge zero page */ #define MMF_DISABLE_THP 24 /* disable THP for all VMAs */ #define MMF_OOM_VICTIM 25 /* mm is the oom victim */ +#define MMF_OOM_REAP_QUEUED 26 /* mm was queued for oom_reaper */ #define MMF_DISABLE_THP_MASK (1 << MMF_DISABLE_THP) #define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\ diff --git a/include/linux/sched/wake_q.h b/include/linux/sched/wake_q.h index 10b19a192b2d..545f37138057 100644 --- a/include/linux/sched/wake_q.h +++ b/include/linux/sched/wake_q.h @@ -24,9 +24,13 @@ * called near the end of a function. Otherwise, the list can be * re-initialized for later re-use by wake_q_init(). * - * Note that this can cause spurious wakeups. schedule() callers + * NOTE that this can cause spurious wakeups. schedule() callers * must ensure the call is done inside a loop, confirming that the * wakeup condition has in fact occurred. + * + * NOTE that there is no guarantee the wakeup will happen any later than the + * wake_q_add() location. Therefore task must be ready to be woken at the + * location of the wake_q_add(). */ #include <linux/sched.h> diff --git a/include/linux/signal.h b/include/linux/signal.h index cc7e2c1cd444..9702016734b1 100644 --- a/include/linux/signal.h +++ b/include/linux/signal.h @@ -392,7 +392,7 @@ extern bool unhandled_signal(struct task_struct *tsk, int sig); #endif #define siginmask(sig, mask) \ - ((sig) < SIGRTMIN && (rt_sigmask(sig) & (mask))) + ((sig) > 0 && (sig) < SIGRTMIN && (rt_sigmask(sig) & (mask))) #define SIG_KERNEL_ONLY_MASK (\ rt_sigmask(SIGKILL) | rt_sigmask(SIGSTOP)) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index c34595374e93..a41e84f7730c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1889,12 +1889,12 @@ static inline void __skb_queue_before(struct sk_buff_head *list, * * A buffer cannot be placed on two lists at the same time. */ -void skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk); static inline void __skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk) { __skb_queue_after(list, (struct sk_buff *)list, newsk); } +void skb_queue_head(struct sk_buff_head *list, struct sk_buff *newsk); /** * __skb_queue_tail - queue a buffer at the list tail @@ -1906,12 +1906,12 @@ static inline void __skb_queue_head(struct sk_buff_head *list, * * A buffer cannot be placed on two lists at the same time. */ -void skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk); static inline void __skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk) { __skb_queue_before(list, (struct sk_buff *)list, newsk); } +void skb_queue_tail(struct sk_buff_head *list, struct sk_buff *newsk); /* * remove sk_buff from list. _Must_ be called atomically, and with @@ -1938,7 +1938,6 @@ static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list) * so must be used with appropriate locks held only. The head item is * returned or %NULL if the list is empty. */ -struct sk_buff *skb_dequeue(struct sk_buff_head *list); static inline struct sk_buff *__skb_dequeue(struct sk_buff_head *list) { struct sk_buff *skb = skb_peek(list); @@ -1946,6 +1945,7 @@ static inline struct sk_buff *__skb_dequeue(struct sk_buff_head *list) __skb_unlink(skb, list); return skb; } +struct sk_buff *skb_dequeue(struct sk_buff_head *list); /** * __skb_dequeue_tail - remove from the tail of the queue @@ -1955,7 +1955,6 @@ static inline struct sk_buff *__skb_dequeue(struct sk_buff_head *list) * so must be used with appropriate locks held only. The tail item is * returned or %NULL if the list is empty. */ -struct sk_buff *skb_dequeue_tail(struct sk_buff_head *list); static inline struct sk_buff *__skb_dequeue_tail(struct sk_buff_head *list) { struct sk_buff *skb = skb_peek_tail(list); @@ -1963,6 +1962,7 @@ static inline struct sk_buff *__skb_dequeue_tail(struct sk_buff_head *list) __skb_unlink(skb, list); return skb; } +struct sk_buff *skb_dequeue_tail(struct sk_buff_head *list); static inline bool skb_is_nonlinear(const struct sk_buff *skb) @@ -2653,13 +2653,13 @@ static inline int skb_orphan_frags_rx(struct sk_buff *skb, gfp_t gfp_mask) * the list and one reference dropped. This function does not take the * list lock and the caller must hold the relevant locks to use it. */ -void skb_queue_purge(struct sk_buff_head *list); static inline void __skb_queue_purge(struct sk_buff_head *list) { struct sk_buff *skb; while ((skb = __skb_dequeue(list)) != NULL) kfree_skb(skb); } +void skb_queue_purge(struct sk_buff_head *list); unsigned int skb_rbtree_purge(struct rb_root *root); @@ -3028,7 +3028,7 @@ static inline int skb_padto(struct sk_buff *skb, unsigned int len) } /** - * skb_put_padto - increase size and pad an skbuff up to a minimal size + * __skb_put_padto - increase size and pad an skbuff up to a minimal size * @skb: buffer to pad * @len: minimal length * @free_on_error: free buffer on error @@ -3486,16 +3486,25 @@ static inline ktime_t skb_get_ktime(const struct sk_buff *skb) /** * skb_get_timestamp - get timestamp from a skb * @skb: skb to get stamp from - * @stamp: pointer to struct timeval to store stamp in + * @stamp: pointer to struct __kernel_old_timeval to store stamp in * * Timestamps are stored in the skb as offsets to a base timestamp. * This function converts the offset back to a struct timeval and stores * it in stamp. */ static inline void skb_get_timestamp(const struct sk_buff *skb, - struct timeval *stamp) + struct __kernel_old_timeval *stamp) { - *stamp = ktime_to_timeval(skb->tstamp); + *stamp = ns_to_kernel_old_timeval(skb->tstamp); +} + +static inline void skb_get_new_timestamp(const struct sk_buff *skb, + struct __kernel_sock_timeval *stamp) +{ + struct timespec64 ts = ktime_to_timespec64(skb->tstamp); + + stamp->tv_sec = ts.tv_sec; + stamp->tv_usec = ts.tv_nsec / 1000; } static inline void skb_get_timestampns(const struct sk_buff *skb, @@ -3504,6 +3513,15 @@ static inline void skb_get_timestampns(const struct sk_buff *skb, *stamp = ktime_to_timespec(skb->tstamp); } +static inline void skb_get_new_timestampns(const struct sk_buff *skb, + struct __kernel_timespec *stamp) +{ + struct timespec64 ts = ktime_to_timespec64(skb->tstamp); + + stamp->tv_sec = ts.tv_sec; + stamp->tv_nsec = ts.tv_nsec; +} + static inline void __net_timestamp(struct sk_buff *skb) { skb->tstamp = ktime_get_real(); diff --git a/include/linux/socket.h b/include/linux/socket.h index ab2041a00e01..6016daeecee4 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -349,9 +349,17 @@ struct ucred { extern int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr_storage *kaddr); extern int put_cmsg(struct msghdr*, int level, int type, int len, void *data); +struct timespec64; struct __kernel_timespec; struct old_timespec32; +struct scm_timestamping_internal { + struct timespec64 ts[3]; +}; + +extern void put_cmsg_scm_timestamping64(struct msghdr *msg, struct scm_timestamping_internal *tss); +extern void put_cmsg_scm_timestamping(struct msghdr *msg, struct scm_timestamping_internal *tss); + /* The __sys_...msg variants allow MSG_CMSG_COMPAT iff * forbid_cmsg_compat==false */ diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index 7ddfc65586b0..4335bd771ce5 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -184,6 +184,7 @@ struct plat_stmmacenet_data { struct clk *pclk; struct clk *clk_ptp_ref; unsigned int clk_ptp_rate; + unsigned int clk_ref_rate; struct reset_control *stmmac_rst; struct stmmac_axi *axi; int has_gmac4; diff --git a/include/net/act_api.h b/include/net/act_api.h index dbc795ec659e..c745e9ccfab2 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -80,7 +80,7 @@ static inline void tcf_tm_dump(struct tcf_t *dtm, const struct tcf_t *stm) struct tc_action_ops { struct list_head head; char kind[IFNAMSIZ]; - __u32 type; /* TBD to match kind */ + enum tca_id id; /* identifier should match kind */ size_t size; struct module *owner; int (*act)(struct sk_buff *, const struct tc_action *, diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 20d523ee2fec..269ec27385e9 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -248,6 +248,7 @@ struct ipv6_stub { const struct in6_addr *addr); int (*ipv6_dst_lookup)(struct net *net, struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6); + int (*ipv6_route_input)(struct sk_buff *skb); struct fib6_table *(*fib6_get_table)(struct net *net, u32 id); struct fib6_info *(*fib6_lookup)(struct net *net, int oif, diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index e0c41eb1c860..7f2739a90bdb 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -836,6 +836,17 @@ struct cfg80211_bitrate_mask { }; /** + * enum cfg80211_ap_settings_flags - AP settings flags + * + * Used by cfg80211_ap_settings + * + * @AP_SETTINGS_EXTERNAL_AUTH_SUPPORT: AP supports external authentication + */ +enum cfg80211_ap_settings_flags { + AP_SETTINGS_EXTERNAL_AUTH_SUPPORT = BIT(0), +}; + +/** * struct cfg80211_ap_settings - AP configuration * * Used to configure an AP interface. @@ -865,6 +876,7 @@ struct cfg80211_bitrate_mask { * @he_cap: HE capabilities (or %NULL if HE isn't enabled) * @ht_required: stations must support HT * @vht_required: stations must support VHT + * @flags: flags, as defined in enum cfg80211_ap_settings_flags */ struct cfg80211_ap_settings { struct cfg80211_chan_def chandef; @@ -890,6 +902,7 @@ struct cfg80211_ap_settings { const struct ieee80211_vht_cap *vht_cap; const struct ieee80211_he_cap_elem *he_cap; bool ht_required, vht_required; + u32 flags; }; /** @@ -1003,6 +1016,7 @@ enum station_parameters_apply_mask { * @support_p2p_ps: information if station supports P2P PS mechanism * @he_capa: HE capabilities of station * @he_capa_len: the length of the HE capabilities + * @airtime_weight: airtime scheduler weight for this station */ struct station_parameters { const u8 *supported_rates; @@ -1032,6 +1046,7 @@ struct station_parameters { int support_p2p_ps; const struct ieee80211_he_cap_elem *he_capa; u8 he_capa_len; + u16 airtime_weight; }; /** @@ -1300,6 +1315,8 @@ struct cfg80211_tid_stats { * from this peer * @connected_to_gate: true if mesh STA has a path to mesh gate * @rx_duration: aggregate PPDU duration(usecs) for all the frames from a peer + * @tx_duration: aggregate PPDU duration(usecs) for all the frames to a peer + * @airtime_weight: current airtime scheduling weight * @pertid: per-TID statistics, see &struct cfg80211_tid_stats, using the last * (IEEE80211_NUM_TIDS) index for MSDUs not encapsulated in QoS-MPDUs. * Note that this doesn't use the @filled bit, but is used if non-NULL. @@ -1350,8 +1367,9 @@ struct station_info { u32 expected_throughput; - u64 rx_beacon; + u64 tx_duration; u64 rx_duration; + u64 rx_beacon; u8 rx_beacon_signal_avg; u8 connected_to_gate; @@ -1359,6 +1377,8 @@ struct station_info { s8 ack_signal; s8 avg_ack_signal; + u16 airtime_weight; + u32 rx_mpdu_count; u32 fcs_err_count; }; @@ -1422,6 +1442,8 @@ enum monitor_flags { * @MPATH_INFO_DISCOVERY_TIMEOUT: @discovery_timeout filled * @MPATH_INFO_DISCOVERY_RETRIES: @discovery_retries filled * @MPATH_INFO_FLAGS: @flags filled + * @MPATH_INFO_HOP_COUNT: @hop_count filled + * @MPATH_INFO_PATH_CHANGE: @path_change_count filled */ enum mpath_info_flags { MPATH_INFO_FRAME_QLEN = BIT(0), @@ -1431,6 +1453,8 @@ enum mpath_info_flags { MPATH_INFO_DISCOVERY_TIMEOUT = BIT(4), MPATH_INFO_DISCOVERY_RETRIES = BIT(5), MPATH_INFO_FLAGS = BIT(6), + MPATH_INFO_HOP_COUNT = BIT(7), + MPATH_INFO_PATH_CHANGE = BIT(8), }; /** @@ -1450,6 +1474,8 @@ enum mpath_info_flags { * This number should increase every time the list of mesh paths * changes, i.e. when a station is added or removed, so that * userspace can tell whether it got a consistent snapshot. + * @hop_count: hops to destination + * @path_change_count: total number of path changes to destination */ struct mpath_info { u32 filled; @@ -1460,6 +1486,8 @@ struct mpath_info { u32 discovery_timeout; u8 discovery_retries; u8 flags; + u8 hop_count; + u32 path_change_count; int generation; }; @@ -2391,6 +2419,8 @@ enum wiphy_params_flags { WIPHY_PARAM_TXQ_QUANTUM = 1 << 8, }; +#define IEEE80211_DEFAULT_AIRTIME_WEIGHT 256 + /** * struct cfg80211_pmksa - PMK Security Association * @@ -2815,6 +2845,7 @@ struct cfg80211_pmk_conf { * use %WLAN_STATUS_UNSPECIFIED_FAILURE if user space cannot give you * the real status code for failures. Used only for the authentication * response command interface (user space to driver). + * @pmkid: The identifier to refer a PMKSA. */ struct cfg80211_external_auth_params { enum nl80211_external_auth_action action; @@ -2822,6 +2853,7 @@ struct cfg80211_external_auth_params { struct cfg80211_ssid ssid; unsigned int key_mgmt_suite; u16 status; + const u8 *pmkid; }; /** @@ -4112,6 +4144,8 @@ struct cfg80211_pmsr_capabilities { * @signal_type: signal type reported in &struct cfg80211_bss. * @cipher_suites: supported cipher suites * @n_cipher_suites: number of supported cipher suites + * @akm_suites: supported AKM suites + * @n_akm_suites: number of supported AKM suites * @retry_short: Retry limit for short frames (dot11ShortRetryLimit) * @retry_long: Retry limit for long frames (dot11LongRetryLimit) * @frag_threshold: Fragmentation threshold (dot11FragmentationThreshold); @@ -4310,6 +4344,9 @@ struct wiphy { int n_cipher_suites; const u32 *cipher_suites; + int n_akm_suites; + const u32 *akm_suites; + u8 retry_short; u8 retry_long; u32 frag_threshold; @@ -4573,6 +4610,17 @@ struct cfg80211_cqm_config; * @mesh_id_len: (private) Used by the internal configuration code * @mesh_id_up_len: (private) Used by the internal configuration code * @wext: (private) Used by the internal wireless extensions compat code + * @wext.ibss: (private) IBSS data part of wext handling + * @wext.connect: (private) connection handling data + * @wext.keys: (private) (WEP) key data + * @wext.ie: (private) extra elements for association + * @wext.ie_len: (private) length of extra elements + * @wext.bssid: (private) selected network BSSID + * @wext.ssid: (private) selected network SSID + * @wext.default_key: (private) selected default key index + * @wext.default_mgmt_key: (private) selected default management key index + * @wext.prev_bssid: (private) previous BSSID for reassociation + * @wext.prev_bssid_valid: (private) previous BSSID validity * @use_4addr: indicates 4addr mode is used on this interface, must be * set by driver (if supported) on add_interface BEFORE registering the * netdev and may otherwise be used by driver read-only, will be update @@ -4672,7 +4720,8 @@ struct wireless_dev { struct cfg80211_cached_keys *keys; const u8 *ie; size_t ie_len; - u8 bssid[ETH_ALEN], prev_bssid[ETH_ALEN]; + u8 bssid[ETH_ALEN]; + u8 prev_bssid[ETH_ALEN]; u8 ssid[IEEE80211_MAX_SSID_LEN]; s8 default_key, default_mgmt_key; bool prev_bssid_valid; @@ -5568,7 +5617,7 @@ void cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid, * @dev: network device * @macaddr: the MAC address of the new candidate * @ie: information elements advertised by the peer candidate - * @ie_len: lenght of the information elements buffer + * @ie_len: length of the information elements buffer * @gfp: allocation flags * * This function notifies cfg80211 that the mesh peer candidate has been diff --git a/include/net/devlink.h b/include/net/devlink.h index 67f4293bc970..a2da49dd9147 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -30,6 +30,7 @@ struct devlink { struct list_head param_list; struct list_head region_list; u32 snapshot_id; + struct list_head reporter_list; struct devlink_dpipe_headers *dpipe_headers; const struct devlink_ops *ops; struct device *dev; @@ -48,6 +49,7 @@ struct devlink_port_attrs { struct devlink_port { struct list_head list; + struct list_head param_list; struct devlink *devlink; unsigned index; bool registered; @@ -61,6 +63,7 @@ struct devlink_sb_pool_info { enum devlink_sb_pool_type pool_type; u32 size; enum devlink_sb_threshold_type threshold_type; + u32 cell_size; }; /** @@ -355,6 +358,7 @@ struct devlink_param_item { const struct devlink_param *param; union devlink_param_value driverinit_value; bool driverinit_value_valid; + bool published; }; enum devlink_param_generic_id { @@ -419,10 +423,50 @@ enum devlink_param_generic_id { .validate = _validate, \ } +/* Part number, identifier of board design */ +#define DEVLINK_INFO_VERSION_GENERIC_BOARD_ID "board.id" +/* Revision of board design */ +#define DEVLINK_INFO_VERSION_GENERIC_BOARD_REV "board.rev" +/* Maker of the board */ +#define DEVLINK_INFO_VERSION_GENERIC_BOARD_MANUFACTURE "board.manufacture" + +/* Control processor FW version */ +#define DEVLINK_INFO_VERSION_GENERIC_FW_MGMT "fw.mgmt" +/* Data path microcode controlling high-speed packet processing */ +#define DEVLINK_INFO_VERSION_GENERIC_FW_APP "fw.app" +/* UNDI software version */ +#define DEVLINK_INFO_VERSION_GENERIC_FW_UNDI "fw.undi" +/* NCSI support/handler version */ +#define DEVLINK_INFO_VERSION_GENERIC_FW_NCSI "fw.ncsi" + struct devlink_region; +struct devlink_info_req; typedef void devlink_snapshot_data_dest_t(const void *data); +struct devlink_fmsg; +struct devlink_health_reporter; + +/** + * struct devlink_health_reporter_ops - Reporter operations + * @name: reporter name + * @recover: callback to recover from reported error + * if priv_ctx is NULL, run a full recover + * @dump: callback to dump an object + * if priv_ctx is NULL, run a full dump + * @diagnose: callback to diagnose the current status + */ + +struct devlink_health_reporter_ops { + char *name; + int (*recover)(struct devlink_health_reporter *reporter, + void *priv_ctx); + int (*dump)(struct devlink_health_reporter *reporter, + struct devlink_fmsg *fmsg, void *priv_ctx); + int (*diagnose)(struct devlink_health_reporter *reporter, + struct devlink_fmsg *fmsg); +}; + struct devlink_ops { int (*reload)(struct devlink *devlink, struct netlink_ext_ack *extack); int (*port_type_set)(struct devlink_port *devlink_port, @@ -475,6 +519,11 @@ struct devlink_ops { int (*eswitch_encap_mode_get)(struct devlink *devlink, u8 *p_encap_mode); int (*eswitch_encap_mode_set)(struct devlink *devlink, u8 encap_mode, struct netlink_ext_ack *extack); + int (*info_get)(struct devlink *devlink, struct devlink_info_req *req, + struct netlink_ext_ack *extack); + int (*flash_update)(struct devlink *devlink, const char *file_name, + const char *component, + struct netlink_ext_ack *extack); }; static inline void *devlink_priv(struct devlink *devlink) @@ -567,11 +616,28 @@ int devlink_params_register(struct devlink *devlink, void devlink_params_unregister(struct devlink *devlink, const struct devlink_param *params, size_t params_count); +void devlink_params_publish(struct devlink *devlink); +void devlink_params_unpublish(struct devlink *devlink); +int devlink_port_params_register(struct devlink_port *devlink_port, + const struct devlink_param *params, + size_t params_count); +void devlink_port_params_unregister(struct devlink_port *devlink_port, + const struct devlink_param *params, + size_t params_count); int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, union devlink_param_value *init_val); int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id, union devlink_param_value init_val); +int +devlink_port_param_driverinit_value_get(struct devlink_port *devlink_port, + u32 param_id, + union devlink_param_value *init_val); +int devlink_port_param_driverinit_value_set(struct devlink_port *devlink_port, + u32 param_id, + union devlink_param_value init_val); void devlink_param_value_changed(struct devlink *devlink, u32 param_id); +void devlink_port_param_value_changed(struct devlink_port *devlink_port, + u32 param_id); void devlink_param_value_str_fill(union devlink_param_value *dst_val, const char *src); struct devlink_region *devlink_region_create(struct devlink *devlink, @@ -583,6 +649,63 @@ u32 devlink_region_shapshot_id_get(struct devlink *devlink); int devlink_region_snapshot_create(struct devlink_region *region, u64 data_len, u8 *data, u32 snapshot_id, devlink_snapshot_data_dest_t *data_destructor); +int devlink_info_serial_number_put(struct devlink_info_req *req, + const char *sn); +int devlink_info_driver_name_put(struct devlink_info_req *req, + const char *name); +int devlink_info_version_fixed_put(struct devlink_info_req *req, + const char *version_name, + const char *version_value); +int devlink_info_version_stored_put(struct devlink_info_req *req, + const char *version_name, + const char *version_value); +int devlink_info_version_running_put(struct devlink_info_req *req, + const char *version_name, + const char *version_value); + +int devlink_fmsg_obj_nest_start(struct devlink_fmsg *fmsg); +int devlink_fmsg_obj_nest_end(struct devlink_fmsg *fmsg); + +int devlink_fmsg_pair_nest_start(struct devlink_fmsg *fmsg, const char *name); +int devlink_fmsg_pair_nest_end(struct devlink_fmsg *fmsg); + +int devlink_fmsg_arr_pair_nest_start(struct devlink_fmsg *fmsg, + const char *name); +int devlink_fmsg_arr_pair_nest_end(struct devlink_fmsg *fmsg); + +int devlink_fmsg_bool_put(struct devlink_fmsg *fmsg, bool value); +int devlink_fmsg_u8_put(struct devlink_fmsg *fmsg, u8 value); +int devlink_fmsg_u32_put(struct devlink_fmsg *fmsg, u32 value); +int devlink_fmsg_u64_put(struct devlink_fmsg *fmsg, u64 value); +int devlink_fmsg_string_put(struct devlink_fmsg *fmsg, const char *value); +int devlink_fmsg_binary_put(struct devlink_fmsg *fmsg, const void *value, + u16 value_len); + +int devlink_fmsg_bool_pair_put(struct devlink_fmsg *fmsg, const char *name, + bool value); +int devlink_fmsg_u8_pair_put(struct devlink_fmsg *fmsg, const char *name, + u8 value); +int devlink_fmsg_u32_pair_put(struct devlink_fmsg *fmsg, const char *name, + u32 value); +int devlink_fmsg_u64_pair_put(struct devlink_fmsg *fmsg, const char *name, + u64 value); +int devlink_fmsg_string_pair_put(struct devlink_fmsg *fmsg, const char *name, + const char *value); +int devlink_fmsg_binary_pair_put(struct devlink_fmsg *fmsg, const char *name, + const void *value, u16 value_len); + +struct devlink_health_reporter * +devlink_health_reporter_create(struct devlink *devlink, + const struct devlink_health_reporter_ops *ops, + u64 graceful_period, bool auto_recover, + void *priv); +void +devlink_health_reporter_destroy(struct devlink_health_reporter *reporter); + +void * +devlink_health_reporter_priv(struct devlink_health_reporter *reporter); +int devlink_health_report(struct devlink_health_reporter *reporter, + const char *msg, void *priv_ctx); #else @@ -601,6 +724,14 @@ static inline void devlink_unregister(struct devlink *devlink) { } +static inline void devlink_params_publish(struct devlink *devlink) +{ +} + +static inline void devlink_params_unpublish(struct devlink *devlink) +{ +} + static inline void devlink_free(struct devlink *devlink) { kfree(devlink); @@ -792,6 +923,21 @@ devlink_params_unregister(struct devlink *devlink, } static inline int +devlink_port_params_register(struct devlink_port *devlink_port, + const struct devlink_param *params, + size_t params_count) +{ + return 0; +} + +static inline void +devlink_port_params_unregister(struct devlink_port *devlink_port, + const struct devlink_param *params, + size_t params_count) +{ +} + +static inline int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, union devlink_param_value *init_val) { @@ -805,12 +951,34 @@ devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id, return -EOPNOTSUPP; } +static inline int +devlink_port_param_driverinit_value_get(struct devlink_port *devlink_port, + u32 param_id, + union devlink_param_value *init_val) +{ + return -EOPNOTSUPP; +} + +static inline int +devlink_port_param_driverinit_value_set(struct devlink_port *devlink_port, + u32 param_id, + union devlink_param_value init_val) +{ + return -EOPNOTSUPP; +} + static inline void devlink_param_value_changed(struct devlink *devlink, u32 param_id) { } static inline void +devlink_port_param_value_changed(struct devlink_port *devlink_port, + u32 param_id) +{ +} + +static inline void devlink_param_value_str_fill(union devlink_param_value *dst_val, const char *src) { @@ -844,6 +1012,201 @@ devlink_region_snapshot_create(struct devlink_region *region, u64 data_len, return 0; } +static inline int +devlink_info_driver_name_put(struct devlink_info_req *req, const char *name) +{ + return 0; +} + +static inline int +devlink_info_serial_number_put(struct devlink_info_req *req, const char *sn) +{ + return 0; +} + +static inline int +devlink_info_version_fixed_put(struct devlink_info_req *req, + const char *version_name, + const char *version_value) +{ + return 0; +} + +static inline int +devlink_info_version_stored_put(struct devlink_info_req *req, + const char *version_name, + const char *version_value) +{ + return 0; +} + +static inline int +devlink_info_version_running_put(struct devlink_info_req *req, + const char *version_name, + const char *version_value) +{ + return 0; +} + +static inline int +devlink_fmsg_obj_nest_start(struct devlink_fmsg *fmsg) +{ + return 0; +} + +static inline int +devlink_fmsg_obj_nest_end(struct devlink_fmsg *fmsg) +{ + return 0; +} + +static inline int +devlink_fmsg_pair_nest_start(struct devlink_fmsg *fmsg, const char *name) +{ + return 0; +} + +static inline int +devlink_fmsg_pair_nest_end(struct devlink_fmsg *fmsg) +{ + return 0; +} + +static inline int +devlink_fmsg_arr_pair_nest_start(struct devlink_fmsg *fmsg, + const char *name) +{ + return 0; +} + +static inline int +devlink_fmsg_arr_pair_nest_end(struct devlink_fmsg *fmsg) +{ + return 0; +} + +static inline int +devlink_fmsg_bool_put(struct devlink_fmsg *fmsg, bool value) +{ + return 0; +} + +static inline int +devlink_fmsg_u8_put(struct devlink_fmsg *fmsg, u8 value) +{ + return 0; +} + +static inline int +devlink_fmsg_u32_put(struct devlink_fmsg *fmsg, u32 value) +{ + return 0; +} + +static inline int +devlink_fmsg_u64_put(struct devlink_fmsg *fmsg, u64 value) +{ + return 0; +} + +static inline int +devlink_fmsg_string_put(struct devlink_fmsg *fmsg, const char *value) +{ + return 0; +} + +static inline int +devlink_fmsg_binary_put(struct devlink_fmsg *fmsg, const void *value, + u16 value_len) +{ + return 0; +} + +static inline int +devlink_fmsg_bool_pair_put(struct devlink_fmsg *fmsg, const char *name, + bool value) +{ + return 0; +} + +static inline int +devlink_fmsg_u8_pair_put(struct devlink_fmsg *fmsg, const char *name, + u8 value) +{ + return 0; +} + +static inline int +devlink_fmsg_u32_pair_put(struct devlink_fmsg *fmsg, const char *name, + u32 value) +{ + return 0; +} + +static inline int +devlink_fmsg_u64_pair_put(struct devlink_fmsg *fmsg, const char *name, + u64 value) +{ + return 0; +} + +static inline int +devlink_fmsg_string_pair_put(struct devlink_fmsg *fmsg, const char *name, + const char *value) +{ + return 0; +} + +static inline int +devlink_fmsg_binary_pair_put(struct devlink_fmsg *fmsg, const char *name, + const void *value, u16 value_len) +{ + return 0; +} + +static inline struct devlink_health_reporter * +devlink_health_reporter_create(struct devlink *devlink, + const struct devlink_health_reporter_ops *ops, + u64 graceful_period, bool auto_recover, + void *priv) +{ + return NULL; +} + +static inline void +devlink_health_reporter_destroy(struct devlink_health_reporter *reporter) +{ +} + +static inline void * +devlink_health_reporter_priv(struct devlink_health_reporter *reporter) +{ + return NULL; +} + +static inline int +devlink_health_report(struct devlink_health_reporter *reporter, + const char *msg, void *priv_ctx) +{ + return 0; +} +#endif + +#if IS_REACHABLE(CONFIG_NET_DEVLINK) +void devlink_compat_running_version(struct net_device *dev, + char *buf, size_t len); +int devlink_compat_flash_update(struct net_device *dev, const char *file_name); +#else +static inline void +devlink_compat_running_version(struct net_device *dev, char *buf, size_t len) +{ +} + +static inline int +devlink_compat_flash_update(struct net_device *dev, const char *file_name) +{ + return -EOPNOTSUPP; +} #endif #endif /* _NET_DEVLINK_H_ */ diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h new file mode 100644 index 000000000000..d035183c8d03 --- /dev/null +++ b/include/net/flow_offload.h @@ -0,0 +1,203 @@ +#ifndef _NET_FLOW_OFFLOAD_H +#define _NET_FLOW_OFFLOAD_H + +#include <net/flow_dissector.h> + +struct flow_match { + struct flow_dissector *dissector; + void *mask; + void *key; +}; + +struct flow_match_basic { + struct flow_dissector_key_basic *key, *mask; +}; + +struct flow_match_control { + struct flow_dissector_key_control *key, *mask; +}; + +struct flow_match_eth_addrs { + struct flow_dissector_key_eth_addrs *key, *mask; +}; + +struct flow_match_vlan { + struct flow_dissector_key_vlan *key, *mask; +}; + +struct flow_match_ipv4_addrs { + struct flow_dissector_key_ipv4_addrs *key, *mask; +}; + +struct flow_match_ipv6_addrs { + struct flow_dissector_key_ipv6_addrs *key, *mask; +}; + +struct flow_match_ip { + struct flow_dissector_key_ip *key, *mask; +}; + +struct flow_match_ports { + struct flow_dissector_key_ports *key, *mask; +}; + +struct flow_match_icmp { + struct flow_dissector_key_icmp *key, *mask; +}; + +struct flow_match_tcp { + struct flow_dissector_key_tcp *key, *mask; +}; + +struct flow_match_mpls { + struct flow_dissector_key_mpls *key, *mask; +}; + +struct flow_match_enc_keyid { + struct flow_dissector_key_keyid *key, *mask; +}; + +struct flow_match_enc_opts { + struct flow_dissector_key_enc_opts *key, *mask; +}; + +struct flow_rule; + +void flow_rule_match_basic(const struct flow_rule *rule, + struct flow_match_basic *out); +void flow_rule_match_control(const struct flow_rule *rule, + struct flow_match_control *out); +void flow_rule_match_eth_addrs(const struct flow_rule *rule, + struct flow_match_eth_addrs *out); +void flow_rule_match_vlan(const struct flow_rule *rule, + struct flow_match_vlan *out); +void flow_rule_match_ipv4_addrs(const struct flow_rule *rule, + struct flow_match_ipv4_addrs *out); +void flow_rule_match_ipv6_addrs(const struct flow_rule *rule, + struct flow_match_ipv6_addrs *out); +void flow_rule_match_ip(const struct flow_rule *rule, + struct flow_match_ip *out); +void flow_rule_match_ports(const struct flow_rule *rule, + struct flow_match_ports *out); +void flow_rule_match_tcp(const struct flow_rule *rule, + struct flow_match_tcp *out); +void flow_rule_match_icmp(const struct flow_rule *rule, + struct flow_match_icmp *out); +void flow_rule_match_mpls(const struct flow_rule *rule, + struct flow_match_mpls *out); +void flow_rule_match_enc_control(const struct flow_rule *rule, + struct flow_match_control *out); +void flow_rule_match_enc_ipv4_addrs(const struct flow_rule *rule, + struct flow_match_ipv4_addrs *out); +void flow_rule_match_enc_ipv6_addrs(const struct flow_rule *rule, + struct flow_match_ipv6_addrs *out); +void flow_rule_match_enc_ip(const struct flow_rule *rule, + struct flow_match_ip *out); +void flow_rule_match_enc_ports(const struct flow_rule *rule, + struct flow_match_ports *out); +void flow_rule_match_enc_keyid(const struct flow_rule *rule, + struct flow_match_enc_keyid *out); +void flow_rule_match_enc_opts(const struct flow_rule *rule, + struct flow_match_enc_opts *out); + +enum flow_action_id { + FLOW_ACTION_ACCEPT = 0, + FLOW_ACTION_DROP, + FLOW_ACTION_TRAP, + FLOW_ACTION_GOTO, + FLOW_ACTION_REDIRECT, + FLOW_ACTION_MIRRED, + FLOW_ACTION_VLAN_PUSH, + FLOW_ACTION_VLAN_POP, + FLOW_ACTION_VLAN_MANGLE, + FLOW_ACTION_TUNNEL_ENCAP, + FLOW_ACTION_TUNNEL_DECAP, + FLOW_ACTION_MANGLE, + FLOW_ACTION_ADD, + FLOW_ACTION_CSUM, + FLOW_ACTION_MARK, + FLOW_ACTION_WAKE, + FLOW_ACTION_QUEUE, +}; + +/* This is mirroring enum pedit_header_type definition for easy mapping between + * tc pedit action. Legacy TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK is mapped to + * FLOW_ACT_MANGLE_UNSPEC, which is supported by no driver. + */ +enum flow_action_mangle_base { + FLOW_ACT_MANGLE_UNSPEC = 0, + FLOW_ACT_MANGLE_HDR_TYPE_ETH, + FLOW_ACT_MANGLE_HDR_TYPE_IP4, + FLOW_ACT_MANGLE_HDR_TYPE_IP6, + FLOW_ACT_MANGLE_HDR_TYPE_TCP, + FLOW_ACT_MANGLE_HDR_TYPE_UDP, +}; + +struct flow_action_entry { + enum flow_action_id id; + union { + u32 chain_index; /* FLOW_ACTION_GOTO */ + struct net_device *dev; /* FLOW_ACTION_REDIRECT */ + struct { /* FLOW_ACTION_VLAN */ + u16 vid; + __be16 proto; + u8 prio; + } vlan; + struct { /* FLOW_ACTION_PACKET_EDIT */ + enum flow_action_mangle_base htype; + u32 offset; + u32 mask; + u32 val; + } mangle; + const struct ip_tunnel_info *tunnel; /* FLOW_ACTION_TUNNEL_ENCAP */ + u32 csum_flags; /* FLOW_ACTION_CSUM */ + u32 mark; /* FLOW_ACTION_MARK */ + struct { /* FLOW_ACTION_QUEUE */ + u32 ctx; + u32 index; + u8 vf; + } queue; + }; +}; + +struct flow_action { + unsigned int num_entries; + struct flow_action_entry entries[0]; +}; + +static inline bool flow_action_has_entries(const struct flow_action *action) +{ + return action->num_entries; +} + +#define flow_action_for_each(__i, __act, __actions) \ + for (__i = 0, __act = &(__actions)->entries[0]; __i < (__actions)->num_entries; __act = &(__actions)->entries[++__i]) + +struct flow_rule { + struct flow_match match; + struct flow_action action; +}; + +struct flow_rule *flow_rule_alloc(unsigned int num_actions); + +static inline bool flow_rule_match_key(const struct flow_rule *rule, + enum flow_dissector_key_id key) +{ + return dissector_uses_key(rule->match.dissector, key); +} + +struct flow_stats { + u64 pkts; + u64 bytes; + u64 lastused; +}; + +static inline void flow_stats_update(struct flow_stats *flow_stats, + u64 bytes, u64 pkts, u64 lastused) +{ + flow_stats->pkts += pkts; + flow_stats->bytes += bytes; + flow_stats->lastused = max_t(u64, flow_stats->lastused, lastused); +} + +#endif /* _NET_FLOW_OFFLOAD_H */ diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h index 00b5e7825508..74ff688568a0 100644 --- a/include/net/inetpeer.h +++ b/include/net/inetpeer.h @@ -39,6 +39,7 @@ struct inet_peer { u32 metrics[RTAX_MAX]; u32 rate_tokens; /* rate limiting for ICMP */ + u32 n_redirects; unsigned long rate_last; /* * Once inet_peer is queued for deletion (refcnt == 0), following field diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h index 78fa0ac4613c..5175fd63cd82 100644 --- a/include/net/l3mdev.h +++ b/include/net/l3mdev.h @@ -153,7 +153,8 @@ struct sk_buff *l3mdev_l3_rcv(struct sk_buff *skb, u16 proto) if (netif_is_l3_slave(skb->dev)) master = netdev_master_upper_dev_get_rcu(skb->dev); - else if (netif_is_l3_master(skb->dev)) + else if (netif_is_l3_master(skb->dev) || + netif_has_l3_rx_handler(skb->dev)) master = skb->dev; if (master && master->l3mdev_ops->l3mdev_l3_rcv) diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h index 33fd9ba7e0e5..671113bcb2cc 100644 --- a/include/net/lwtunnel.h +++ b/include/net/lwtunnel.h @@ -126,6 +126,8 @@ int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b); int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb); int lwtunnel_input(struct sk_buff *skb); int lwtunnel_xmit(struct sk_buff *skb); +int bpf_lwt_push_ip_encap(struct sk_buff *skb, void *hdr, u32 len, + bool ingress); static inline void lwtunnel_set_redirect(struct dst_entry *dst) { diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 88219cc137c3..de866a7253c9 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -108,9 +108,15 @@ * The driver is expected to initialize its private per-queue data for stations * and interfaces in the .add_interface and .sta_add ops. * - * The driver can't access the queue directly. To dequeue a frame, it calls - * ieee80211_tx_dequeue(). Whenever mac80211 adds a new frame to a queue, it - * calls the .wake_tx_queue driver op. + * The driver can't access the queue directly. To dequeue a frame from a + * txq, it calls ieee80211_tx_dequeue(). Whenever mac80211 adds a new frame to a + * queue, it calls the .wake_tx_queue driver op. + * + * Drivers can optionally delegate responsibility for scheduling queues to + * mac80211, to take advantage of airtime fairness accounting. In this case, to + * obtain the next queue to pull frames from, the driver calls + * ieee80211_next_txq(). The driver is then expected to return the txq using + * ieee80211_return_txq(). * * For AP powersave TIM handling, the driver only needs to indicate if it has * buffered packets in the driver specific data structures by calling @@ -936,8 +942,32 @@ ieee80211_rate_get_vht_nss(const struct ieee80211_tx_rate *rate) * @band: the band to transmit on (use for checking for races) * @hw_queue: HW queue to put the frame on, skb_get_queue_mapping() gives the AC * @ack_frame_id: internal frame ID for TX status, used internally - * @control: union for control data - * @status: union for status data + * @control: union part for control data + * @control.rates: TX rates array to try + * @control.rts_cts_rate_idx: rate for RTS or CTS + * @control.use_rts: use RTS + * @control.use_cts_prot: use RTS/CTS + * @control.short_preamble: use short preamble (CCK only) + * @control.skip_table: skip externally configured rate table + * @control.jiffies: timestamp for expiry on powersave clients + * @control.vif: virtual interface (may be NULL) + * @control.hw_key: key to encrypt with (may be NULL) + * @control.flags: control flags, see &enum mac80211_tx_control_flags + * @control.enqueue_time: enqueue time (for iTXQs) + * @driver_rates: alias to @control.rates to reserve space + * @pad: padding + * @rate_driver_data: driver use area if driver needs @control.rates + * @status: union part for status data + * @status.rates: attempted rates + * @status.ack_signal: ACK signal + * @status.ampdu_ack_len: AMPDU ack length + * @status.ampdu_len: AMPDU length + * @status.antenna: (legacy, kept only for iwlegacy) + * @status.tx_time: airtime consumed for transmission + * @status.is_valid_ack_signal: ACK signal is valid + * @status.status_driver_data: driver use area + * @ack: union part for pure ACK data + * @ack.cookie: cookie for the ACK * @driver_data: array of driver_data pointers * @ampdu_ack_len: number of acked aggregated frames. * relevant only if IEEE80211_TX_STAT_AMPDU was set. @@ -1157,6 +1187,7 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) * @RX_FLAG_AMPDU_EOF_BIT_KNOWN: The EOF value is known * @RX_FLAG_RADIOTAP_HE: HE radiotap data is present * (&struct ieee80211_radiotap_he, mac80211 will fill in + * * - DATA3_DATA_MCS * - DATA3_DATA_DCM * - DATA3_CODING @@ -1164,6 +1195,7 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) * - DATA5_DATA_BW_RU_ALLOC * - DATA6_NSTS * - DATA3_STBC + * * from the RX info data, so leave those zeroed when building this data) * @RX_FLAG_RADIOTAP_HE_MU: HE MU radiotap data is present * (&struct ieee80211_radiotap_he_mu) @@ -1214,7 +1246,7 @@ enum mac80211_rx_flags { * @RX_ENC_FLAG_HT_GF: This frame was received in a HT-greenfield transmission, * if the driver fills this value it should add * %IEEE80211_RADIOTAP_MCS_HAVE_FMT - * to hw.radiotap_mcs_details to advertise that fact + * to @hw.radiotap_mcs_details to advertise that fact. * @RX_ENC_FLAG_LDPC: LDPC was used * @RX_ENC_FLAG_STBC_MASK: STBC 2 bit bitmask. 1 - Nss=1, 2 - Nss=2, 3 - Nss=3 * @RX_ENC_FLAG_BF: packet was beamformed @@ -2184,6 +2216,9 @@ struct ieee80211_txq { * MMPDUs on station interfaces. This of course requires the driver to use * TXQs to start with. * + * @IEEE80211_HW_TX_STATUS_NO_AMPDU_LEN: Driver does not report accurate A-MPDU + * length in tx status information + * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ enum ieee80211_hw_flags { @@ -2232,6 +2267,7 @@ enum ieee80211_hw_flags { IEEE80211_HW_BUFF_MMPDU_TXQ, IEEE80211_HW_SUPPORTS_VHT_EXT_NSS_BW, IEEE80211_HW_STA_MMPDU_TXQ, + IEEE80211_HW_TX_STATUS_NO_AMPDU_LEN, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS @@ -2323,12 +2359,14 @@ enum ieee80211_hw_flags { * @radiotap_he: HE radiotap validity flags * * @radiotap_timestamp: Information for the radiotap timestamp field; if the - * 'units_pos' member is set to a non-negative value it must be set to - * a combination of a IEEE80211_RADIOTAP_TIMESTAMP_UNIT_* and a - * IEEE80211_RADIOTAP_TIMESTAMP_SPOS_* value, and then the timestamp + * @units_pos member is set to a non-negative value then the timestamp * field will be added and populated from the &struct ieee80211_rx_status - * device_timestamp. If the 'accuracy' member is non-negative, it's put - * into the accuracy radiotap field and the accuracy known flag is set. + * device_timestamp. + * @radiotap_timestamp.units_pos: Must be set to a combination of a + * IEEE80211_RADIOTAP_TIMESTAMP_UNIT_* and a + * IEEE80211_RADIOTAP_TIMESTAMP_SPOS_* value. + * @radiotap_timestamp.accuracy: If non-negative, fills the accuracy in the + * radiotap field and the accuracy known flag will be set. * * @netdev_features: netdev features to be set in each netdev created * from this HW. Note that not all features are usable with mac80211, @@ -2354,6 +2392,9 @@ enum ieee80211_hw_flags { * @tx_sk_pacing_shift: Pacing shift to set on TCP sockets when frames from * them are encountered. The default should typically not be changed, * unless the driver has good reasons for needing more buffers. + * + * @weight_multiplier: Driver specific airtime weight multiplier used while + * refilling deficit of each TXQ. */ struct ieee80211_hw { struct ieee80211_conf conf; @@ -2390,6 +2431,7 @@ struct ieee80211_hw { const struct ieee80211_cipher_scheme *cipher_schemes; u8 max_nan_de_entries; u8 tx_sk_pacing_shift; + u8 weight_multiplier; }; static inline bool _ieee80211_hw_check(struct ieee80211_hw *hw, @@ -5402,6 +5444,34 @@ void ieee80211_sta_eosp(struct ieee80211_sta *pubsta); void ieee80211_send_eosp_nullfunc(struct ieee80211_sta *pubsta, int tid); /** + * ieee80211_sta_register_airtime - register airtime usage for a sta/tid + * + * Register airtime usage for a given sta on a given tid. The driver can call + * this function to notify mac80211 that a station used a certain amount of + * airtime. This information will be used by the TXQ scheduler to schedule + * stations in a way that ensures airtime fairness. + * + * The reported airtime should as a minimum include all time that is spent + * transmitting to the remote station, including overhead and padding, but not + * including time spent waiting for a TXOP. If the time is not reported by the + * hardware it can in some cases be calculated from the rate and known frame + * composition. When possible, the time should include any failed transmission + * attempts. + * + * The driver can either call this function synchronously for every packet or + * aggregate, or asynchronously as airtime usage information becomes available. + * TX and RX airtime can be reported together, or separately by setting one of + * them to 0. + * + * @pubsta: the station + * @tid: the TID to register airtime for + * @tx_airtime: airtime used during TX (in usec) + * @rx_airtime: airtime used during RX (in usec) + */ +void ieee80211_sta_register_airtime(struct ieee80211_sta *pubsta, u8 tid, + u32 tx_airtime, u32 rx_airtime); + +/** * ieee80211_iter_keys - iterate keys programmed into the device * @hw: pointer obtained from ieee80211_alloc_hw() * @vif: virtual interface to iterate, may be %NULL for all @@ -6103,7 +6173,8 @@ void ieee80211_unreserve_tid(struct ieee80211_sta *sta, u8 tid); * ieee80211_tx_dequeue - dequeue a packet from a software tx queue * * @hw: pointer as obtained from ieee80211_alloc_hw() - * @txq: pointer obtained from station or virtual interface + * @txq: pointer obtained from station or virtual interface, or from + * ieee80211_next_txq() * * Returns the skb if successful, %NULL if no frame was available. * @@ -6119,6 +6190,94 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw, struct ieee80211_txq *txq); /** + * ieee80211_next_txq - get next tx queue to pull packets from + * + * @hw: pointer as obtained from ieee80211_alloc_hw() + * @ac: AC number to return packets from. + * + * Should only be called between calls to ieee80211_txq_schedule_start() + * and ieee80211_txq_schedule_end(). + * Returns the next txq if successful, %NULL if no queue is eligible. If a txq + * is returned, it should be returned with ieee80211_return_txq() after the + * driver has finished scheduling it. + */ +struct ieee80211_txq *ieee80211_next_txq(struct ieee80211_hw *hw, u8 ac); + +/** + * ieee80211_return_txq - return a TXQ previously acquired by ieee80211_next_txq() + * + * @hw: pointer as obtained from ieee80211_alloc_hw() + * @txq: pointer obtained from station or virtual interface + * + * Should only be called between calls to ieee80211_txq_schedule_start() + * and ieee80211_txq_schedule_end(). + */ +void ieee80211_return_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq); + +/** + * ieee80211_txq_schedule_start - acquire locks for safe scheduling of an AC + * + * @hw: pointer as obtained from ieee80211_alloc_hw() + * @ac: AC number to acquire locks for + * + * Acquire locks needed to schedule TXQs from the given AC. Should be called + * before ieee80211_next_txq() or ieee80211_return_txq(). + */ +void ieee80211_txq_schedule_start(struct ieee80211_hw *hw, u8 ac) + __acquires(txq_lock); + +/** + * ieee80211_txq_schedule_end - release locks for safe scheduling of an AC + * + * @hw: pointer as obtained from ieee80211_alloc_hw() + * @ac: AC number to acquire locks for + * + * Release locks previously acquired by ieee80211_txq_schedule_end(). + */ +void ieee80211_txq_schedule_end(struct ieee80211_hw *hw, u8 ac) + __releases(txq_lock); + +/** + * ieee80211_schedule_txq - schedule a TXQ for transmission + * + * @hw: pointer as obtained from ieee80211_alloc_hw() + * @txq: pointer obtained from station or virtual interface + * + * Schedules a TXQ for transmission if it is not already scheduled. Takes a + * lock, which means it must *not* be called between + * ieee80211_txq_schedule_start() and ieee80211_txq_schedule_end() + */ +void ieee80211_schedule_txq(struct ieee80211_hw *hw, struct ieee80211_txq *txq) + __acquires(txq_lock) __releases(txq_lock); + +/** + * ieee80211_txq_may_transmit - check whether TXQ is allowed to transmit + * + * This function is used to check whether given txq is allowed to transmit by + * the airtime scheduler, and can be used by drivers to access the airtime + * fairness accounting without going using the scheduling order enfored by + * next_txq(). + * + * Returns %true if the airtime scheduler thinks the TXQ should be allowed to + * transmit, and %false if it should be throttled. This function can also have + * the side effect of rotating the TXQ in the scheduler rotation, which will + * eventually bring the deficit to positive and allow the station to transmit + * again. + * + * The API ieee80211_txq_may_transmit() also ensures that TXQ list will be + * aligned aginst driver's own round-robin scheduler list. i.e it rotates + * the TXQ list till it makes the requested node becomes the first entry + * in TXQ list. Thus both the TXQ list and driver's list are in sync. If this + * function returns %true, the driver is expected to schedule packets + * for transmission, and then return the TXQ through ieee80211_return_txq(). + * + * @hw: pointer as obtained from ieee80211_alloc_hw() + * @txq: pointer obtained from station or virtual interface + */ +bool ieee80211_txq_may_transmit(struct ieee80211_hw *hw, + struct ieee80211_txq *txq); + +/** * ieee80211_txq_get_depth - get pending frame/byte count of given txq * * The values are not guaranteed to be coherent with regard to each other, i.e. diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 45eba7d7ab38..a66fcd316734 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -469,9 +469,7 @@ struct nft_set_binding { int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding); void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, - struct nft_set_binding *binding); -void nf_tables_rebind_set(const struct nft_ctx *ctx, struct nft_set *set, - struct nft_set_binding *binding); + struct nft_set_binding *binding, bool commit); void nf_tables_destroy_set(const struct nft_ctx *ctx, struct nft_set *set); /** @@ -721,6 +719,13 @@ struct nft_expr_type { #define NFT_EXPR_STATEFUL 0x1 #define NFT_EXPR_GC 0x2 +enum nft_trans_phase { + NFT_TRANS_PREPARE, + NFT_TRANS_ABORT, + NFT_TRANS_COMMIT, + NFT_TRANS_RELEASE +}; + /** * struct nft_expr_ops - nf_tables expression operations * @@ -750,7 +755,8 @@ struct nft_expr_ops { void (*activate)(const struct nft_ctx *ctx, const struct nft_expr *expr); void (*deactivate)(const struct nft_ctx *ctx, - const struct nft_expr *expr); + const struct nft_expr *expr, + enum nft_trans_phase phase); void (*destroy)(const struct nft_ctx *ctx, const struct nft_expr *expr); void (*destroy_clone)(const struct nft_ctx *ctx, @@ -1335,12 +1341,15 @@ struct nft_trans_rule { struct nft_trans_set { struct nft_set *set; u32 set_id; + bool bound; }; #define nft_trans_set(trans) \ (((struct nft_trans_set *)trans->data)->set) #define nft_trans_set_id(trans) \ (((struct nft_trans_set *)trans->data)->set_id) +#define nft_trans_set_bound(trans) \ + (((struct nft_trans_set *)trans->data)->bound) struct nft_trans_chain { bool update; diff --git a/include/net/netlink.h b/include/net/netlink.h index 4c1e99303b5a..23f27b0b3cef 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -306,10 +306,14 @@ struct nla_policy { #define NLA_POLICY_ETH_ADDR NLA_POLICY_EXACT_LEN(ETH_ALEN) #define NLA_POLICY_ETH_ADDR_COMPAT NLA_POLICY_EXACT_LEN_WARN(ETH_ALEN) -#define NLA_POLICY_NESTED(maxattr, policy) \ +#define _NLA_POLICY_NESTED(maxattr, policy) \ { .type = NLA_NESTED, .validation_data = policy, .len = maxattr } -#define NLA_POLICY_NESTED_ARRAY(maxattr, policy) \ +#define _NLA_POLICY_NESTED_ARRAY(maxattr, policy) \ { .type = NLA_NESTED_ARRAY, .validation_data = policy, .len = maxattr } +#define NLA_POLICY_NESTED(policy) \ + _NLA_POLICY_NESTED(ARRAY_SIZE(policy) - 1, policy) +#define NLA_POLICY_NESTED_ARRAY(policy) \ + _NLA_POLICY_NESTED_ARRAY(ARRAY_SIZE(policy) - 1, policy) #define __NLA_ENSURE(condition) BUILD_BUG_ON_ZERO(!(condition)) #define NLA_ENSURE_INT_TYPE(tp) \ diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 40965fbbcd31..6a530bef9253 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -6,6 +6,7 @@ #include <linux/workqueue.h> #include <net/sch_generic.h> #include <net/act_api.h> +#include <net/flow_offload.h> /* TC action not accessible from user space */ #define TC_ACT_REINSERT (TC_ACT_VALUE_MAX + 1) @@ -43,6 +44,10 @@ bool tcf_queue_work(struct rcu_work *rwork, work_func_t func); struct tcf_chain *tcf_chain_get_by_act(struct tcf_block *block, u32 chain_index); void tcf_chain_put_by_act(struct tcf_chain *chain); +struct tcf_chain *tcf_get_next_chain(struct tcf_block *block, + struct tcf_chain *chain); +struct tcf_proto *tcf_get_next_proto(struct tcf_chain *chain, + struct tcf_proto *tp, bool rtnl_held); void tcf_block_netif_keep_dst(struct tcf_block *block); int tcf_block_get(struct tcf_block **p_block, struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q, @@ -411,7 +416,7 @@ tcf_exts_exec(struct sk_buff *skb, struct tcf_exts *exts, int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, struct nlattr *rate_tlv, - struct tcf_exts *exts, bool ovr, + struct tcf_exts *exts, bool ovr, bool rtnl_held, struct netlink_ext_ack *extack); void tcf_exts_destroy(struct tcf_exts *exts); void tcf_exts_change(struct tcf_exts *dst, struct tcf_exts *src); @@ -619,8 +624,11 @@ tcf_match_indev(struct sk_buff *skb, int ifindex) } #endif /* CONFIG_NET_CLS_IND */ +int tc_setup_flow_action(struct flow_action *flow_action, + const struct tcf_exts *exts); int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type, void *type_data, bool err_stop); +unsigned int tcf_exts_num_actions(struct tcf_exts *exts); enum tc_block_command { TC_BLOCK_BIND, @@ -760,13 +768,17 @@ struct tc_cls_flower_offload { struct tc_cls_common_offload common; enum tc_fl_command command; unsigned long cookie; - struct flow_dissector *dissector; - struct fl_flow_key *mask; - struct fl_flow_key *key; - struct tcf_exts *exts; + struct flow_rule *rule; + struct flow_stats stats; u32 classid; }; +static inline struct flow_rule * +tc_cls_flower_offload_flow_rule(struct tc_cls_flower_offload *tc_flow_cmd) +{ + return tc_flow_cmd->rule; +} + enum tc_matchall_command { TC_CLSMATCHALL_REPLACE, TC_CLSMATCHALL_DESTROY, diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 7a4957599874..e50b729f8691 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -12,6 +12,7 @@ #include <linux/list.h> #include <linux/refcount.h> #include <linux/workqueue.h> +#include <linux/mutex.h> #include <net/gen_stats.h> #include <net/rtnetlink.h> @@ -178,6 +179,7 @@ static inline int qdisc_avail_bulklimit(const struct netdev_queue *txq) } struct Qdisc_class_ops { + unsigned int flags; /* Child qdisc manipulation */ struct netdev_queue * (*select_queue)(struct Qdisc *, struct tcmsg *); int (*graft)(struct Qdisc *, unsigned long cl, @@ -209,6 +211,13 @@ struct Qdisc_class_ops { struct gnet_dump *); }; +/* Qdisc_class_ops flag values */ + +/* Implements API that doesn't require rtnl lock */ +enum qdisc_class_ops_flags { + QDISC_CLASS_OPS_DOIT_UNLOCKED = 1, +}; + struct Qdisc_ops { struct Qdisc_ops *next; const struct Qdisc_class_ops *cl_ops; @@ -272,19 +281,21 @@ struct tcf_proto_ops { const struct tcf_proto *, struct tcf_result *); int (*init)(struct tcf_proto*); - void (*destroy)(struct tcf_proto *tp, + void (*destroy)(struct tcf_proto *tp, bool rtnl_held, struct netlink_ext_ack *extack); void* (*get)(struct tcf_proto*, u32 handle); + void (*put)(struct tcf_proto *tp, void *f); int (*change)(struct net *net, struct sk_buff *, struct tcf_proto*, unsigned long, u32 handle, struct nlattr **, - void **, bool, + void **, bool, bool, struct netlink_ext_ack *); int (*delete)(struct tcf_proto *tp, void *arg, - bool *last, + bool *last, bool rtnl_held, struct netlink_ext_ack *); - void (*walk)(struct tcf_proto*, struct tcf_walker *arg); + void (*walk)(struct tcf_proto *tp, + struct tcf_walker *arg, bool rtnl_held); int (*reoffload)(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb, void *cb_priv, struct netlink_ext_ack *extack); @@ -297,12 +308,18 @@ struct tcf_proto_ops { /* rtnetlink specific */ int (*dump)(struct net*, struct tcf_proto*, void *, - struct sk_buff *skb, struct tcmsg*); + struct sk_buff *skb, struct tcmsg*, + bool); int (*tmplt_dump)(struct sk_buff *skb, struct net *net, void *tmplt_priv); struct module *owner; + int flags; +}; + +enum tcf_proto_ops_flags { + TCF_PROTO_OPS_DOIT_UNLOCKED = 1, }; struct tcf_proto { @@ -321,6 +338,12 @@ struct tcf_proto { void *data; const struct tcf_proto_ops *ops; struct tcf_chain *chain; + /* Lock protects tcf_proto shared state and can be used by unlocked + * classifiers to protect their private data. + */ + spinlock_t lock; + bool deleting; + refcount_t refcnt; struct rcu_head rcu; }; @@ -340,6 +363,8 @@ struct qdisc_skb_cb { typedef void tcf_chain_head_change_t(struct tcf_proto *tp_head, void *priv); struct tcf_chain { + /* Protects filter_chain. */ + struct mutex filter_chain_lock; struct tcf_proto __rcu *filter_chain; struct list_head list; struct tcf_block *block; @@ -347,11 +372,16 @@ struct tcf_chain { unsigned int refcnt; unsigned int action_refcnt; bool explicitly_created; + bool flushing; const struct tcf_proto_ops *tmplt_ops; void *tmplt_priv; }; struct tcf_block { + /* Lock protects tcf_block and lifetime-management data of chains + * attached to the block (refcnt, action_refcnt, explicitly_created). + */ + struct mutex lock; struct list_head chain_list; u32 index; /* block index for shared blocks */ refcount_t refcnt; @@ -369,6 +399,34 @@ struct tcf_block { struct rcu_head rcu; }; +#ifdef CONFIG_PROVE_LOCKING +static inline bool lockdep_tcf_chain_is_locked(struct tcf_chain *chain) +{ + return lockdep_is_held(&chain->filter_chain_lock); +} + +static inline bool lockdep_tcf_proto_is_locked(struct tcf_proto *tp) +{ + return lockdep_is_held(&tp->lock); +} +#else +static inline bool lockdep_tcf_chain_is_locked(struct tcf_block *chain) +{ + return true; +} + +static inline bool lockdep_tcf_proto_is_locked(struct tcf_proto *tp) +{ + return true; +} +#endif /* #ifdef CONFIG_PROVE_LOCKING */ + +#define tcf_chain_dereference(p, chain) \ + rcu_dereference_protected(p, lockdep_tcf_chain_is_locked(chain)) + +#define tcf_proto_dereference(p, tp) \ + rcu_dereference_protected(p, lockdep_tcf_proto_is_locked(tp)) + static inline void tcf_block_offload_inc(struct tcf_block *block, u32 *flags) { if (*flags & TCA_CLS_FLAGS_IN_HW) diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 003020eb6e66..58e4b23cecf4 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -199,6 +199,8 @@ struct sctp_sock { __u32 flowlabel; __u8 dscp; + int pf_retrans; + /* The initial Path MTU to use for new associations. */ __u32 pathmtu; @@ -209,6 +211,8 @@ struct sctp_sock { /* Flags controlling Heartbeat, SACK delay, and Path MTU Discovery. */ __u32 param_flags; + __u32 default_ss; + struct sctp_rtoinfo rtoinfo; struct sctp_paddrparams paddrparam; struct sctp_assocparams assocparams; diff --git a/include/net/sock.h b/include/net/sock.h index 2b229f7be8eb..328cb7cb7b0b 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -805,6 +805,7 @@ enum sock_flags { SOCK_RCU_FREE, /* wait rcu grace period in sk_destruct() */ SOCK_TXTIME, SOCK_XDP, /* XDP is attached */ + SOCK_TSTAMP_NEW, /* Indicates 64 bit timestamps always */ }; #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) @@ -1277,7 +1278,7 @@ static inline void sk_sockets_allocated_inc(struct sock *sk) percpu_counter_inc(sk->sk_prot->sockets_allocated); } -static inline int +static inline u64 sk_sockets_allocated_read_positive(struct sock *sk) { return percpu_counter_read_positive(sk->sk_prot->sockets_allocated); diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 63843ae5dc81..5e87b54c5dc5 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -43,7 +43,6 @@ static inline bool switchdev_trans_ph_commit(struct switchdev_trans *trans) enum switchdev_attr_id { SWITCHDEV_ATTR_ID_UNDEFINED, - SWITCHDEV_ATTR_ID_PORT_PARENT_ID, SWITCHDEV_ATTR_ID_PORT_STP_STATE, SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS, SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT, @@ -61,7 +60,6 @@ struct switchdev_attr { void *complete_priv; void (*complete)(struct net_device *dev, int err, void *priv); union { - struct netdev_phys_item_id ppid; /* PORT_PARENT_ID */ u8 stp_state; /* PORT_STP_STATE */ unsigned long brport_flags; /* PORT_BRIDGE_FLAGS */ unsigned long brport_flags_support; /* PORT_BRIDGE_FLAGS_SUPPORT */ @@ -208,9 +206,6 @@ void switchdev_port_fwd_mark_set(struct net_device *dev, struct net_device *group_dev, bool joining); -bool switchdev_port_same_parent_id(struct net_device *a, - struct net_device *b); - int switchdev_handle_port_obj_add(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), @@ -295,12 +290,6 @@ call_switchdev_blocking_notifiers(unsigned long val, return NOTIFY_DONE; } -static inline bool switchdev_port_same_parent_id(struct net_device *a, - struct net_device *b) -{ - return false; -} - static inline int switchdev_handle_port_obj_add(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, diff --git a/include/net/tc_act/tc_csum.h b/include/net/tc_act/tc_csum.h index 32d2454c0479..68269e4581b7 100644 --- a/include/net/tc_act/tc_csum.h +++ b/include/net/tc_act/tc_csum.h @@ -21,7 +21,7 @@ struct tcf_csum { static inline bool is_tcf_csum(const struct tc_action *a) { #ifdef CONFIG_NET_CLS_ACT - if (a->ops && a->ops->type == TCA_ACT_CSUM) + if (a->ops && a->ops->id == TCA_ID_CSUM) return true; #endif return false; diff --git a/include/net/tc_act/tc_gact.h b/include/net/tc_act/tc_gact.h index ef8dd0db70ce..ee8d005f56fc 100644 --- a/include/net/tc_act/tc_gact.h +++ b/include/net/tc_act/tc_gact.h @@ -22,7 +22,7 @@ static inline bool __is_tcf_gact_act(const struct tc_action *a, int act, #ifdef CONFIG_NET_CLS_ACT struct tcf_gact *gact; - if (a->ops && a->ops->type != TCA_ACT_GACT) + if (a->ops && a->ops->id != TCA_ID_GACT) return false; gact = to_gact(a); diff --git a/include/net/tc_act/tc_mirred.h b/include/net/tc_act/tc_mirred.h index a2e9cbca5c9e..c757585a05b0 100644 --- a/include/net/tc_act/tc_mirred.h +++ b/include/net/tc_act/tc_mirred.h @@ -17,7 +17,7 @@ struct tcf_mirred { static inline bool is_tcf_mirred_egress_redirect(const struct tc_action *a) { #ifdef CONFIG_NET_CLS_ACT - if (a->ops && a->ops->type == TCA_ACT_MIRRED) + if (a->ops && a->ops->id == TCA_ID_MIRRED) return to_mirred(a)->tcfm_eaction == TCA_EGRESS_REDIR; #endif return false; @@ -26,7 +26,7 @@ static inline bool is_tcf_mirred_egress_redirect(const struct tc_action *a) static inline bool is_tcf_mirred_egress_mirror(const struct tc_action *a) { #ifdef CONFIG_NET_CLS_ACT - if (a->ops && a->ops->type == TCA_ACT_MIRRED) + if (a->ops && a->ops->id == TCA_ID_MIRRED) return to_mirred(a)->tcfm_eaction == TCA_EGRESS_MIRROR; #endif return false; diff --git a/include/net/tc_act/tc_pedit.h b/include/net/tc_act/tc_pedit.h index fac3ad4a86de..748cf87a4d7e 100644 --- a/include/net/tc_act/tc_pedit.h +++ b/include/net/tc_act/tc_pedit.h @@ -23,7 +23,7 @@ struct tcf_pedit { static inline bool is_tcf_pedit(const struct tc_action *a) { #ifdef CONFIG_NET_CLS_ACT - if (a->ops && a->ops->type == TCA_ACT_PEDIT) + if (a->ops && a->ops->id == TCA_ID_PEDIT) return true; #endif return false; diff --git a/include/net/tc_act/tc_sample.h b/include/net/tc_act/tc_sample.h index 01dbfea32672..0a559d4b6f0f 100644 --- a/include/net/tc_act/tc_sample.h +++ b/include/net/tc_act/tc_sample.h @@ -20,7 +20,7 @@ struct tcf_sample { static inline bool is_tcf_sample(const struct tc_action *a) { #ifdef CONFIG_NET_CLS_ACT - return a->ops && a->ops->type == TCA_ACT_SAMPLE; + return a->ops && a->ops->id == TCA_ID_SAMPLE; #else return false; #endif diff --git a/include/net/tc_act/tc_skbedit.h b/include/net/tc_act/tc_skbedit.h index 911bbac838a2..85c5c4756d92 100644 --- a/include/net/tc_act/tc_skbedit.h +++ b/include/net/tc_act/tc_skbedit.h @@ -44,7 +44,7 @@ static inline bool is_tcf_skbedit_mark(const struct tc_action *a) #ifdef CONFIG_NET_CLS_ACT u32 flags; - if (a->ops && a->ops->type == TCA_ACT_SKBEDIT) { + if (a->ops && a->ops->id == TCA_ID_SKBEDIT) { rcu_read_lock(); flags = rcu_dereference(to_skbedit(a)->params)->flags; rcu_read_unlock(); diff --git a/include/net/tc_act/tc_tunnel_key.h b/include/net/tc_act/tc_tunnel_key.h index 46b8c7f1c8d5..23d5b8b19f3e 100644 --- a/include/net/tc_act/tc_tunnel_key.h +++ b/include/net/tc_act/tc_tunnel_key.h @@ -34,7 +34,7 @@ static inline bool is_tcf_tunnel_set(const struct tc_action *a) struct tcf_tunnel_key *t = to_tunnel_key(a); struct tcf_tunnel_key_params *params = rtnl_dereference(t->params); - if (a->ops && a->ops->type == TCA_ACT_TUNNEL_KEY) + if (a->ops && a->ops->id == TCA_ID_TUNNEL_KEY) return params->tcft_action == TCA_TUNNEL_KEY_ACT_SET; #endif return false; @@ -46,7 +46,7 @@ static inline bool is_tcf_tunnel_release(const struct tc_action *a) struct tcf_tunnel_key *t = to_tunnel_key(a); struct tcf_tunnel_key_params *params = rtnl_dereference(t->params); - if (a->ops && a->ops->type == TCA_ACT_TUNNEL_KEY) + if (a->ops && a->ops->id == TCA_ID_TUNNEL_KEY) return params->tcft_action == TCA_TUNNEL_KEY_ACT_RELEASE; #endif return false; diff --git a/include/net/tc_act/tc_vlan.h b/include/net/tc_act/tc_vlan.h index 22ae260d6869..fe39ed502bef 100644 --- a/include/net/tc_act/tc_vlan.h +++ b/include/net/tc_act/tc_vlan.h @@ -30,7 +30,7 @@ struct tcf_vlan { static inline bool is_tcf_vlan(const struct tc_action *a) { #ifdef CONFIG_NET_CLS_ACT - if (a->ops && a->ops->type == TCA_ACT_VLAN) + if (a->ops && a->ops->id == TCA_ID_VLAN) return true; #endif return false; diff --git a/include/net/tls.h b/include/net/tls.h index 90bf52db573e..a93a8ed8f716 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -119,7 +119,12 @@ struct tls_rec { /* AAD | msg_encrypted.sg.data (data contains overhead for hdr & iv & tag) */ struct scatterlist sg_aead_out[2]; + char content_type; + struct scatterlist sg_content_type; + char aad_space[TLS_AAD_SPACE_SIZE]; + u8 iv_data[TLS_CIPHER_AES_GCM_128_IV_SIZE + + TLS_CIPHER_AES_GCM_128_SALT_SIZE]; struct aead_request aead_req; u8 aead_req_ctx[]; }; @@ -137,6 +142,7 @@ struct tls_sw_context_tx { struct list_head tx_list; atomic_t encrypt_pending; int async_notify; + int async_capable; #define BIT_TX_SCHEDULED 0 unsigned long tx_bitmask; @@ -200,11 +206,16 @@ struct cipher_context { char *iv; u16 rec_seq_size; char *rec_seq; + u16 aad_size; + u16 tail_size; }; union tls_crypto_context { struct tls_crypto_info info; - struct tls12_crypto_info_aes_gcm_128 aes_gcm_128; + union { + struct tls12_crypto_info_aes_gcm_128 aes_gcm_128; + struct tls12_crypto_info_aes_gcm_256 aes_gcm_256; + }; }; struct tls_context { @@ -391,49 +402,77 @@ static inline bool tls_bigint_increment(unsigned char *seq, int len) } static inline void tls_advance_record_sn(struct sock *sk, - struct cipher_context *ctx) + struct cipher_context *ctx, + int version) { if (tls_bigint_increment(ctx->rec_seq, ctx->rec_seq_size)) tls_err_abort(sk, EBADMSG); - tls_bigint_increment(ctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, - ctx->iv_size); + + if (version != TLS_1_3_VERSION) { + tls_bigint_increment(ctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, + ctx->iv_size); + } } static inline void tls_fill_prepend(struct tls_context *ctx, char *buf, size_t plaintext_len, - unsigned char record_type) + unsigned char record_type, + int version) { size_t pkt_len, iv_size = ctx->tx.iv_size; - pkt_len = plaintext_len + iv_size + ctx->tx.tag_size; + pkt_len = plaintext_len + ctx->tx.tag_size; + if (version != TLS_1_3_VERSION) { + pkt_len += iv_size; + + memcpy(buf + TLS_NONCE_OFFSET, + ctx->tx.iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv_size); + } /* we cover nonce explicit here as well, so buf should be of * size KTLS_DTLS_HEADER_SIZE + KTLS_DTLS_NONCE_EXPLICIT_SIZE */ - buf[0] = record_type; - buf[1] = TLS_VERSION_MINOR(ctx->crypto_send.info.version); - buf[2] = TLS_VERSION_MAJOR(ctx->crypto_send.info.version); + buf[0] = version == TLS_1_3_VERSION ? + TLS_RECORD_TYPE_DATA : record_type; + /* Note that VERSION must be TLS_1_2 for both TLS1.2 and TLS1.3 */ + buf[1] = TLS_1_2_VERSION_MINOR; + buf[2] = TLS_1_2_VERSION_MAJOR; /* we can use IV for nonce explicit according to spec */ buf[3] = pkt_len >> 8; buf[4] = pkt_len & 0xFF; - memcpy(buf + TLS_NONCE_OFFSET, - ctx->tx.iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv_size); } static inline void tls_make_aad(char *buf, size_t size, char *record_sequence, int record_sequence_size, - unsigned char record_type) + unsigned char record_type, + int version) { - memcpy(buf, record_sequence, record_sequence_size); + if (version != TLS_1_3_VERSION) { + memcpy(buf, record_sequence, record_sequence_size); + buf += 8; + } else { + size += TLS_CIPHER_AES_GCM_128_TAG_SIZE; + } - buf[8] = record_type; - buf[9] = TLS_1_2_VERSION_MAJOR; - buf[10] = TLS_1_2_VERSION_MINOR; - buf[11] = size >> 8; - buf[12] = size & 0xFF; + buf[0] = version == TLS_1_3_VERSION ? + TLS_RECORD_TYPE_DATA : record_type; + buf[1] = TLS_1_2_VERSION_MAJOR; + buf[2] = TLS_1_2_VERSION_MINOR; + buf[3] = size >> 8; + buf[4] = size & 0xFF; +} + +static inline void xor_iv_with_seq(int version, char *iv, char *seq) +{ + int i; + + if (version == TLS_1_3_VERSION) { + for (i = 0; i < 8; i++) + iv[i + 4] ^= seq[i]; + } } static inline struct tls_context *tls_get_ctx(const struct sock *sk) diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index a3ceed3a040a..80debf5982ac 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -2579,9 +2579,10 @@ struct ib_device { const struct uapi_definition *driver_def; enum rdma_driver_id driver_id; + /* - * Provides synchronization between device unregistration and netlink - * commands on a device. To be used only by core. + * Positive refcount indicates that the device is currently + * registered and cannot be unregistered. */ refcount_t refcount; struct completion unreg_completion; @@ -3926,6 +3927,25 @@ static inline bool ib_access_writable(int access_flags) int ib_check_mr_status(struct ib_mr *mr, u32 check_mask, struct ib_mr_status *mr_status); +/** + * ib_device_try_get: Hold a registration lock + * device: The device to lock + * + * A device under an active registration lock cannot become unregistered. It + * is only possible to obtain a registration lock on a device that is fully + * registered, otherwise this function returns false. + * + * The registration lock is only necessary for actions which require the + * device to still be registered. Uses that only require the device pointer to + * be valid should use get_device(&ibdev->dev) to hold the memory. + * + */ +static inline bool ib_device_try_get(struct ib_device *dev) +{ + return refcount_inc_not_zero(&dev->refcount); +} + +void ib_device_put(struct ib_device *device); struct net_device *ib_get_net_dev_by_params(struct ib_device *dev, u8 port, u16 pkey, const union ib_gid *gid, const struct sockaddr *addr); diff --git a/include/sound/compress_driver.h b/include/sound/compress_driver.h index 0cdc3999ecfa..c5188ff724d1 100644 --- a/include/sound/compress_driver.h +++ b/include/sound/compress_driver.h @@ -173,7 +173,11 @@ static inline void snd_compr_drain_notify(struct snd_compr_stream *stream) if (snd_BUG_ON(!stream)) return; - stream->runtime->state = SNDRV_PCM_STATE_SETUP; + if (stream->direction == SND_COMPRESS_PLAYBACK) + stream->runtime->state = SNDRV_PCM_STATE_SETUP; + else + stream->runtime->state = SNDRV_PCM_STATE_PREPARED; + wake_up(&stream->runtime->sleep); } diff --git a/include/sound/hda_codec.h b/include/sound/hda_codec.h index 7fa48b100936..cc7c8d42d4fd 100644 --- a/include/sound/hda_codec.h +++ b/include/sound/hda_codec.h @@ -68,6 +68,7 @@ struct hda_bus { unsigned int response_reset:1; /* controller was reset */ unsigned int in_reset:1; /* during reset operation */ unsigned int no_response_fallback:1; /* don't fallback at RIRB error */ + unsigned int bus_probing :1; /* during probing process */ int primary_dig_out_type; /* primary digital out PCM type */ unsigned int mixer_assigned; /* codec addr for mixer name */ diff --git a/include/trace/events/devlink.h b/include/trace/events/devlink.h index 44acfbca1266..191ddf67d769 100644 --- a/include/trace/events/devlink.h +++ b/include/trace/events/devlink.h @@ -46,6 +46,100 @@ TRACE_EVENT(devlink_hwmsg, (int) __entry->len, __get_dynamic_array(buf), __entry->len) ); +/* + * Tracepoint for devlink hardware error: + */ +TRACE_EVENT(devlink_hwerr, + TP_PROTO(const struct devlink *devlink, int err, const char *msg), + + TP_ARGS(devlink, err, msg), + + TP_STRUCT__entry( + __string(bus_name, devlink->dev->bus->name) + __string(dev_name, dev_name(devlink->dev)) + __string(driver_name, devlink->dev->driver->name) + __field(int, err) + __string(msg, msg) + ), + + TP_fast_assign( + __assign_str(bus_name, devlink->dev->bus->name); + __assign_str(dev_name, dev_name(devlink->dev)); + __assign_str(driver_name, devlink->dev->driver->name); + __entry->err = err; + __assign_str(msg, msg); + ), + + TP_printk("bus_name=%s dev_name=%s driver_name=%s err=%d %s", + __get_str(bus_name), __get_str(dev_name), + __get_str(driver_name), __entry->err, __get_str(msg)) +); + +/* + * Tracepoint for devlink health message: + */ +TRACE_EVENT(devlink_health_report, + TP_PROTO(const struct devlink *devlink, const char *reporter_name, + const char *msg), + + TP_ARGS(devlink, reporter_name, msg), + + TP_STRUCT__entry( + __string(bus_name, devlink->dev->bus->name) + __string(dev_name, dev_name(devlink->dev)) + __string(driver_name, devlink->dev->driver->name) + __string(reporter_name, msg) + __string(msg, msg) + ), + + TP_fast_assign( + __assign_str(bus_name, devlink->dev->bus->name); + __assign_str(dev_name, dev_name(devlink->dev)); + __assign_str(driver_name, devlink->dev->driver->name); + __assign_str(reporter_name, reporter_name); + __assign_str(msg, msg); + ), + + TP_printk("bus_name=%s dev_name=%s driver_name=%s reporter_name=%s: %s", + __get_str(bus_name), __get_str(dev_name), + __get_str(driver_name), __get_str(reporter_name), + __get_str(msg)) +); + +/* + * Tracepoint for devlink health recover aborted message: + */ +TRACE_EVENT(devlink_health_recover_aborted, + TP_PROTO(const struct devlink *devlink, const char *reporter_name, + bool health_state, u64 time_since_last_recover), + + TP_ARGS(devlink, reporter_name, health_state, time_since_last_recover), + + TP_STRUCT__entry( + __string(bus_name, devlink->dev->bus->name) + __string(dev_name, dev_name(devlink->dev)) + __string(driver_name, devlink->dev->driver->name) + __string(reporter_name, reporter_name) + __field(bool, health_state) + __field(u64, time_since_last_recover) + ), + + TP_fast_assign( + __assign_str(bus_name, devlink->dev->bus->name); + __assign_str(dev_name, dev_name(devlink->dev)); + __assign_str(driver_name, devlink->dev->driver->name); + __assign_str(reporter_name, reporter_name); + __entry->health_state = health_state; + __entry->time_since_last_recover = time_since_last_recover; + ), + + TP_printk("bus_name=%s dev_name=%s driver_name=%s reporter_name=%s: health_state=%d time_since_last_recover=%llu recover aborted", + __get_str(bus_name), __get_str(dev_name), + __get_str(driver_name), __get_str(reporter_name), + __entry->health_state, + __entry->time_since_last_recover) +); + #endif /* _TRACE_DEVLINK_H */ /* This part must be outside protection */ @@ -64,6 +158,10 @@ static inline void trace_devlink_hwmsg(const struct devlink *devlink, { } +static inline void trace_devlink_hwerr(const struct devlink *devlink, + int err, const char *msg) +{ +} #endif /* _TRACE_DEVLINK_H */ #endif diff --git a/include/trace/events/mlxsw.h b/include/trace/events/mlxsw.h new file mode 100644 index 000000000000..a5ce6df9dc49 --- /dev/null +++ b/include/trace/events/mlxsw.h @@ -0,0 +1,99 @@ +/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */ +/* Copyright (c) 2019 Mellanox Technologies. All rights reserved */ + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM mlxsw + +#if !defined(_MLXSW_TRACEPOINT_H) || defined(TRACE_HEADER_MULTI_READ) +#define _MLXSW_TRACEPOINT_H + +#include <linux/tracepoint.h> + +struct mlxsw_sp; +struct mlxsw_sp_acl_atcam_region; +struct mlxsw_sp_acl_tcam_vregion; + +TRACE_EVENT(mlxsw_sp_acl_atcam_entry_add_ctcam_spill, + TP_PROTO(const struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_acl_atcam_region *aregion), + + TP_ARGS(mlxsw_sp, aregion), + + TP_STRUCT__entry( + __field(const void *, mlxsw_sp) + __field(const void *, aregion) + ), + + TP_fast_assign( + __entry->mlxsw_sp = mlxsw_sp; + __entry->aregion = aregion; + ), + + TP_printk("mlxsw_sp %p, aregion %p", + __entry->mlxsw_sp, __entry->aregion) +); + +TRACE_EVENT(mlxsw_sp_acl_tcam_vregion_rehash, + TP_PROTO(const struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_acl_tcam_vregion *vregion), + + TP_ARGS(mlxsw_sp, vregion), + + TP_STRUCT__entry( + __field(const void *, mlxsw_sp) + __field(const void *, vregion) + ), + + TP_fast_assign( + __entry->mlxsw_sp = mlxsw_sp; + __entry->vregion = vregion; + ), + + TP_printk("mlxsw_sp %p, vregion %p", + __entry->mlxsw_sp, __entry->vregion) +); + +TRACE_EVENT(mlxsw_sp_acl_tcam_vregion_migrate, + TP_PROTO(const struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_acl_tcam_vregion *vregion), + + TP_ARGS(mlxsw_sp, vregion), + + TP_STRUCT__entry( + __field(const void *, mlxsw_sp) + __field(const void *, vregion) + ), + + TP_fast_assign( + __entry->mlxsw_sp = mlxsw_sp; + __entry->vregion = vregion; + ), + + TP_printk("mlxsw_sp %p, vregion %p", + __entry->mlxsw_sp, __entry->vregion) +); + +TRACE_EVENT(mlxsw_sp_acl_tcam_vregion_rehash_dis, + TP_PROTO(const struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_acl_tcam_vregion *vregion), + + TP_ARGS(mlxsw_sp, vregion), + + TP_STRUCT__entry( + __field(const void *, mlxsw_sp) + __field(const void *, vregion) + ), + + TP_fast_assign( + __entry->mlxsw_sp = mlxsw_sp; + __entry->vregion = vregion; + ), + + TP_printk("mlxsw_sp %p, vregion %p", + __entry->mlxsw_sp, __entry->vregion) +); + +#endif /* _MLXSW_TRACEPOINT_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/trace/events/neigh.h b/include/trace/events/neigh.h new file mode 100644 index 000000000000..ed10353eee73 --- /dev/null +++ b/include/trace/events/neigh.h @@ -0,0 +1,204 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM neigh + +#if !defined(_TRACE_NEIGH_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_NEIGH_H + +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include <linux/tracepoint.h> +#include <net/neighbour.h> + +#define neigh_state_str(state) \ + __print_symbolic(state, \ + { NUD_INCOMPLETE, "incomplete" }, \ + { NUD_REACHABLE, "reachable" }, \ + { NUD_STALE, "stale" }, \ + { NUD_DELAY, "delay" }, \ + { NUD_PROBE, "probe" }, \ + { NUD_FAILED, "failed" }) + +TRACE_EVENT(neigh_update, + + TP_PROTO(struct neighbour *n, const u8 *lladdr, u8 new, + u32 flags, u32 nlmsg_pid), + + TP_ARGS(n, lladdr, new, flags, nlmsg_pid), + + TP_STRUCT__entry( + __field(u32, family) + __string(dev, (n->dev ? n->dev->name : "NULL")) + __array(u8, lladdr, MAX_ADDR_LEN) + __field(u8, lladdr_len) + __field(u8, flags) + __field(u8, nud_state) + __field(u8, type) + __field(u8, dead) + __field(int, refcnt) + __array(__u8, primary_key4, 4) + __array(__u8, primary_key6, 16) + __field(unsigned long, confirmed) + __field(unsigned long, updated) + __field(unsigned long, used) + __array(u8, new_lladdr, MAX_ADDR_LEN) + __field(u8, new_state) + __field(u32, update_flags) + __field(u32, pid) + ), + + TP_fast_assign( + int lladdr_len = (n->dev ? n->dev->addr_len : MAX_ADDR_LEN); + struct in6_addr *pin6; + __be32 *p32; + + __entry->family = n->tbl->family; + __assign_str(dev, (n->dev ? n->dev->name : "NULL")); + __entry->lladdr_len = lladdr_len; + memcpy(__entry->lladdr, n->ha, lladdr_len); + __entry->flags = n->flags; + __entry->nud_state = n->nud_state; + __entry->type = n->type; + __entry->dead = n->dead; + __entry->refcnt = refcount_read(&n->refcnt); + pin6 = (struct in6_addr *)__entry->primary_key6; + p32 = (__be32 *)__entry->primary_key4; + + if (n->tbl->family == AF_INET) + *p32 = *(__be32 *)n->primary_key; + else + *p32 = 0; + +#if IS_ENABLED(CONFIG_IPV6) + if (n->tbl->family == AF_INET6) { + pin6 = (struct in6_addr *)__entry->primary_key6; + *pin6 = *(struct in6_addr *)n->primary_key; + } else +#endif + { + ipv6_addr_set_v4mapped(*p32, pin6); + } + __entry->confirmed = n->confirmed; + __entry->updated = n->updated; + __entry->used = n->used; + if (lladdr) + memcpy(__entry->new_lladdr, lladdr, lladdr_len); + __entry->new_state = new; + __entry->update_flags = flags; + __entry->pid = nlmsg_pid; + ), + + TP_printk("family %d dev %s lladdr %s flags %02x nud_state %s type %02x " + "dead %d refcnt %d primary_key4 %pI4 primary_key6 %pI6c " + "confirmed %lu updated %lu used %lu new_lladdr %s " + "new_state %02x update_flags %02x pid %d", + __entry->family, __get_str(dev), + __print_hex_str(__entry->lladdr, __entry->lladdr_len), + __entry->flags, neigh_state_str(__entry->nud_state), + __entry->type, __entry->dead, __entry->refcnt, + __entry->primary_key4, __entry->primary_key6, + __entry->confirmed, __entry->updated, __entry->used, + __print_hex_str(__entry->new_lladdr, __entry->lladdr_len), + __entry->new_state, + __entry->update_flags, __entry->pid) +); + +DECLARE_EVENT_CLASS(neigh__update, + TP_PROTO(struct neighbour *n, int err), + TP_ARGS(n, err), + TP_STRUCT__entry( + __field(u32, family) + __string(dev, (n->dev ? n->dev->name : "NULL")) + __array(u8, lladdr, MAX_ADDR_LEN) + __field(u8, lladdr_len) + __field(u8, flags) + __field(u8, nud_state) + __field(u8, type) + __field(u8, dead) + __field(int, refcnt) + __array(__u8, primary_key4, 4) + __array(__u8, primary_key6, 16) + __field(unsigned long, confirmed) + __field(unsigned long, updated) + __field(unsigned long, used) + __field(u32, err) + ), + + TP_fast_assign( + int lladdr_len = (n->dev ? n->dev->addr_len : MAX_ADDR_LEN); + struct in6_addr *pin6; + __be32 *p32; + + __entry->family = n->tbl->family; + __assign_str(dev, (n->dev ? n->dev->name : "NULL")); + __entry->lladdr_len = lladdr_len; + memcpy(__entry->lladdr, n->ha, lladdr_len); + __entry->flags = n->flags; + __entry->nud_state = n->nud_state; + __entry->type = n->type; + __entry->dead = n->dead; + __entry->refcnt = refcount_read(&n->refcnt); + pin6 = (struct in6_addr *)__entry->primary_key6; + p32 = (__be32 *)__entry->primary_key4; + + if (n->tbl->family == AF_INET) + *p32 = *(__be32 *)n->primary_key; + else + *p32 = 0; + +#if IS_ENABLED(CONFIG_IPV6) + if (n->tbl->family == AF_INET6) { + pin6 = (struct in6_addr *)__entry->primary_key6; + *pin6 = *(struct in6_addr *)n->primary_key; + } else +#endif + { + ipv6_addr_set_v4mapped(*p32, pin6); + } + + __entry->confirmed = n->confirmed; + __entry->updated = n->updated; + __entry->used = n->used; + __entry->err = err; + ), + + TP_printk("family %d dev %s lladdr %s flags %02x nud_state %s type %02x " + "dead %d refcnt %d primary_key4 %pI4 primary_key6 %pI6c " + "confirmed %lu updated %lu used %lu err %d", + __entry->family, __get_str(dev), + __print_hex_str(__entry->lladdr, __entry->lladdr_len), + __entry->flags, neigh_state_str(__entry->nud_state), + __entry->type, __entry->dead, __entry->refcnt, + __entry->primary_key4, __entry->primary_key6, + __entry->confirmed, __entry->updated, __entry->used, + __entry->err) +); + +DEFINE_EVENT(neigh__update, neigh_update_done, + TP_PROTO(struct neighbour *neigh, int err), + TP_ARGS(neigh, err) +); + +DEFINE_EVENT(neigh__update, neigh_timer_handler, + TP_PROTO(struct neighbour *neigh, int err), + TP_ARGS(neigh, err) +); + +DEFINE_EVENT(neigh__update, neigh_event_send_done, + TP_PROTO(struct neighbour *neigh, int err), + TP_ARGS(neigh, err) +); + +DEFINE_EVENT(neigh__update, neigh_event_send_dead, + TP_PROTO(struct neighbour *neigh, int err), + TP_ARGS(neigh, err) +); + +DEFINE_EVENT(neigh__update, neigh_cleanup_and_release, + TP_PROTO(struct neighbour *neigh, int rc), + TP_ARGS(neigh, rc) +); + +#endif /* _TRACE_NEIGH_H */ + +/* This part must be outside protection */ +#include <trace/define_trace.h> diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 3066ab3853a8..c8b430cb6dc4 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -3,6 +3,7 @@ #define __ASM_GENERIC_SOCKET_H #include <asm/sockios.h> +#include <asm/bitsperlong.h> /* For setsockopt(2) */ #define SOL_SOCKET 1 @@ -29,8 +30,8 @@ #define SO_PEERCRED 17 #define SO_RCVLOWAT 18 #define SO_SNDLOWAT 19 -#define SO_RCVTIMEO 20 -#define SO_SNDTIMEO 21 +#define SO_RCVTIMEO_OLD 20 +#define SO_SNDTIMEO_OLD 21 #endif /* Security levels - as per NRL IPv6 - don't actually do anything */ @@ -46,21 +47,14 @@ #define SO_GET_FILTER SO_ATTACH_FILTER #define SO_PEERNAME 28 -#define SO_TIMESTAMP 29 -#define SCM_TIMESTAMP SO_TIMESTAMP #define SO_ACCEPTCONN 30 #define SO_PEERSEC 31 #define SO_PASSSEC 34 -#define SO_TIMESTAMPNS 35 -#define SCM_TIMESTAMPNS SO_TIMESTAMPNS #define SO_MARK 36 -#define SO_TIMESTAMPING 37 -#define SCM_TIMESTAMPING SO_TIMESTAMPING - #define SO_PROTOCOL 38 #define SO_DOMAIN 39 @@ -112,4 +106,40 @@ #define SO_BINDTOIFINDEX 62 +#define SO_TIMESTAMP_OLD 29 +#define SO_TIMESTAMPNS_OLD 35 +#define SO_TIMESTAMPING_OLD 37 + +#define SO_TIMESTAMP_NEW 63 +#define SO_TIMESTAMPNS_NEW 64 +#define SO_TIMESTAMPING_NEW 65 + +#define SO_RCVTIMEO_NEW 66 +#define SO_SNDTIMEO_NEW 67 + +#if !defined(__KERNEL__) + +#if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) +/* on 64-bit and x32, avoid the ?: operator */ +#define SO_TIMESTAMP SO_TIMESTAMP_OLD +#define SO_TIMESTAMPNS SO_TIMESTAMPNS_OLD +#define SO_TIMESTAMPING SO_TIMESTAMPING_OLD + +#define SO_RCVTIMEO SO_RCVTIMEO_OLD +#define SO_SNDTIMEO SO_SNDTIMEO_OLD +#else +#define SO_TIMESTAMP (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMP_OLD : SO_TIMESTAMP_NEW) +#define SO_TIMESTAMPNS (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPNS_OLD : SO_TIMESTAMPNS_NEW) +#define SO_TIMESTAMPING (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_TIMESTAMPING_OLD : SO_TIMESTAMPING_NEW) + +#define SO_RCVTIMEO (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_RCVTIMEO_OLD : SO_RCVTIMEO_NEW) +#define SO_SNDTIMEO (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_SNDTIMEO_OLD : SO_SNDTIMEO_NEW) +#endif + +#define SCM_TIMESTAMP SO_TIMESTAMP +#define SCM_TIMESTAMPNS SO_TIMESTAMPNS +#define SCM_TIMESTAMPING SO_TIMESTAMPING + +#endif + #endif /* __ASM_GENERIC_SOCKET_H */ diff --git a/include/uapi/linux/batadv_packet.h b/include/uapi/linux/batadv_packet.h index 894d8d2f713d..c99336f4eefe 100644 --- a/include/uapi/linux/batadv_packet.h +++ b/include/uapi/linux/batadv_packet.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) */ -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -229,7 +229,7 @@ struct batadv_ogm_packet { * @packet_type: batman-adv packet type, part of the general header * @version: batman-adv protocol version, part of the general header * @ttl: time to live for this packet, part of the general header - * @flags: reseved for routing relevant flags - currently always 0 + * @flags: reserved for routing relevant flags - currently always 0 * @seqno: sequence number * @orig: originator mac address * @tvlv_len: length of the appended tvlv buffer (in bytes) diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h index 324a0e1143e7..305bf316dd03 100644 --- a/include/uapi/linux/batman_adv.h +++ b/include/uapi/linux/batman_adv.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: MIT */ -/* Copyright (C) 2016-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2016-2019 B.A.T.M.A.N. contributors: * * Matthias Schiffer * @@ -27,6 +27,7 @@ #define BATADV_NL_NAME "batadv" +#define BATADV_NL_MCAST_GROUP_CONFIG "config" #define BATADV_NL_MCAST_GROUP_TPMETER "tpmeter" /** @@ -139,6 +140,20 @@ enum batadv_mcast_flags_priv { }; /** + * enum batadv_gw_modes - gateway mode of node + */ +enum batadv_gw_modes { + /** @BATADV_GW_MODE_OFF: gw mode disabled */ + BATADV_GW_MODE_OFF, + + /** @BATADV_GW_MODE_CLIENT: send DHCP requests to gw servers */ + BATADV_GW_MODE_CLIENT, + + /** @BATADV_GW_MODE_SERVER: announce itself as gatway server */ + BATADV_GW_MODE_SERVER, +}; + +/** * enum batadv_nl_attrs - batman-adv netlink attributes */ enum batadv_nl_attrs { @@ -344,6 +359,138 @@ enum batadv_nl_attrs { */ BATADV_ATTR_MCAST_FLAGS_PRIV, + /** + * @BATADV_ATTR_VLANID: VLAN id on top of soft interface + */ + BATADV_ATTR_VLANID, + + /** + * @BATADV_ATTR_AGGREGATED_OGMS_ENABLED: whether the batman protocol + * messages of the mesh interface shall be aggregated or not. + */ + BATADV_ATTR_AGGREGATED_OGMS_ENABLED, + + /** + * @BATADV_ATTR_AP_ISOLATION_ENABLED: whether the data traffic going + * from a wireless client to another wireless client will be silently + * dropped. + */ + BATADV_ATTR_AP_ISOLATION_ENABLED, + + /** + * @BATADV_ATTR_ISOLATION_MARK: the isolation mark which is used to + * classify clients as "isolated" by the Extended Isolation feature. + */ + BATADV_ATTR_ISOLATION_MARK, + + /** + * @BATADV_ATTR_ISOLATION_MASK: the isolation (bit)mask which is used to + * classify clients as "isolated" by the Extended Isolation feature. + */ + BATADV_ATTR_ISOLATION_MASK, + + /** + * @BATADV_ATTR_BONDING_ENABLED: whether the data traffic going through + * the mesh will be sent using multiple interfaces at the same time. + */ + BATADV_ATTR_BONDING_ENABLED, + + /** + * @BATADV_ATTR_BRIDGE_LOOP_AVOIDANCE_ENABLED: whether the bridge loop + * avoidance feature is enabled. This feature detects and avoids loops + * between the mesh and devices bridged with the soft interface + */ + BATADV_ATTR_BRIDGE_LOOP_AVOIDANCE_ENABLED, + + /** + * @BATADV_ATTR_DISTRIBUTED_ARP_TABLE_ENABLED: whether the distributed + * arp table feature is enabled. This feature uses a distributed hash + * table to answer ARP requests without flooding the request through + * the whole mesh. + */ + BATADV_ATTR_DISTRIBUTED_ARP_TABLE_ENABLED, + + /** + * @BATADV_ATTR_FRAGMENTATION_ENABLED: whether the data traffic going + * through the mesh will be fragmented or silently discarded if the + * packet size exceeds the outgoing interface MTU. + */ + BATADV_ATTR_FRAGMENTATION_ENABLED, + + /** + * @BATADV_ATTR_GW_BANDWIDTH_DOWN: defines the download bandwidth which + * is propagated by this node if %BATADV_ATTR_GW_BANDWIDTH_MODE was set + * to 'server'. + */ + BATADV_ATTR_GW_BANDWIDTH_DOWN, + + /** + * @BATADV_ATTR_GW_BANDWIDTH_UP: defines the upload bandwidth which + * is propagated by this node if %BATADV_ATTR_GW_BANDWIDTH_MODE was set + * to 'server'. + */ + BATADV_ATTR_GW_BANDWIDTH_UP, + + /** + * @BATADV_ATTR_GW_MODE: defines the state of the gateway features. + * Possible values are specified in enum batadv_gw_modes + */ + BATADV_ATTR_GW_MODE, + + /** + * @BATADV_ATTR_GW_SEL_CLASS: defines the selection criteria this node + * will use to choose a gateway if gw_mode was set to 'client'. + */ + BATADV_ATTR_GW_SEL_CLASS, + + /** + * @BATADV_ATTR_HOP_PENALTY: defines the penalty which will be applied + * to an originator message's tq-field on every hop. + */ + BATADV_ATTR_HOP_PENALTY, + + /** + * @BATADV_ATTR_LOG_LEVEL: bitmask with to define which debug messages + * should be send to the debug log/trace ring buffer + */ + BATADV_ATTR_LOG_LEVEL, + + /** + * @BATADV_ATTR_MULTICAST_FORCEFLOOD_ENABLED: whether multicast + * optimizations should be replaced by simple broadcast-like flooding + * of multicast packets. If set to non-zero then all nodes in the mesh + * are going to use classic flooding for any multicast packet with no + * optimizations. + */ + BATADV_ATTR_MULTICAST_FORCEFLOOD_ENABLED, + + /** + * @BATADV_ATTR_NETWORK_CODING_ENABLED: whether Network Coding (using + * some magic to send fewer wifi packets but still the same content) is + * enabled or not. + */ + BATADV_ATTR_NETWORK_CODING_ENABLED, + + /** + * @BATADV_ATTR_ORIG_INTERVAL: defines the interval in milliseconds in + * which batman sends its protocol messages. + */ + BATADV_ATTR_ORIG_INTERVAL, + + /** + * @BATADV_ATTR_ELP_INTERVAL: defines the interval in milliseconds in + * which batman emits probing packets for neighbor sensing (ELP). + */ + BATADV_ATTR_ELP_INTERVAL, + + /** + * @BATADV_ATTR_THROUGHPUT_OVERRIDE: defines the throughput value to be + * used by B.A.T.M.A.N. V when estimating the link throughput using + * this interface. If the value is set to 0 then batman-adv will try to + * estimate the throughput by itself. + */ + BATADV_ATTR_THROUGHPUT_OVERRIDE, + /* add attributes above here, update the policy in netlink.c */ /** @@ -372,10 +519,14 @@ enum batadv_nl_commands { BATADV_CMD_UNSPEC, /** - * @BATADV_CMD_GET_MESH_INFO: Query basic information about batman-adv - * device + * @BATADV_CMD_GET_MESH: Get attributes from softif/mesh + */ + BATADV_CMD_GET_MESH, + + /** + * @BATADV_CMD_GET_MESH_INFO: Alias for @BATADV_CMD_GET_MESH */ - BATADV_CMD_GET_MESH_INFO, + BATADV_CMD_GET_MESH_INFO = BATADV_CMD_GET_MESH, /** * @BATADV_CMD_TP_METER: Start a tp meter session @@ -393,9 +544,15 @@ enum batadv_nl_commands { BATADV_CMD_GET_ROUTING_ALGOS, /** - * @BATADV_CMD_GET_HARDIFS: Query list of hard interfaces + * @BATADV_CMD_GET_HARDIF: Get attributes from a hardif of the + * current softif */ - BATADV_CMD_GET_HARDIFS, + BATADV_CMD_GET_HARDIF, + + /** + * @BATADV_CMD_GET_HARDIFS: Alias for @BATADV_CMD_GET_HARDIF + */ + BATADV_CMD_GET_HARDIFS = BATADV_CMD_GET_HARDIF, /** * @BATADV_CMD_GET_TRANSTABLE_LOCAL: Query list of local translations @@ -443,6 +600,29 @@ enum batadv_nl_commands { */ BATADV_CMD_GET_MCAST_FLAGS, + /** + * @BATADV_CMD_SET_MESH: Set attributes for softif/mesh + */ + BATADV_CMD_SET_MESH, + + /** + * @BATADV_CMD_SET_HARDIF: Set attributes for hardif of the + * current softif + */ + BATADV_CMD_SET_HARDIF, + + /** + * @BATADV_CMD_GET_VLAN: Get attributes from a VLAN of the + * current softif + */ + BATADV_CMD_GET_VLAN, + + /** + * @BATADV_CMD_SET_VLAN: Set attributes for VLAN of the + * current softif + */ + BATADV_CMD_SET_VLAN, + /* add new commands above here */ /** diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 60b99b730a41..bcdd2474eee7 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -267,6 +267,7 @@ enum bpf_attach_type { #define BPF_ANY 0 /* create new element or update existing */ #define BPF_NOEXIST 1 /* create new element if it didn't exist */ #define BPF_EXIST 2 /* update existing element */ +#define BPF_F_LOCK 4 /* spin_lock-ed map_lookup/map_update */ /* flags for BPF_MAP_CREATE command */ #define BPF_F_NO_PREALLOC (1U << 0) @@ -2015,6 +2016,19 @@ union bpf_attr { * Only works if *skb* contains an IPv6 packet. Insert a * Segment Routing Header (**struct ipv6_sr_hdr**) inside * the IPv6 header. + * **BPF_LWT_ENCAP_IP** + * IP encapsulation (GRE/GUE/IPIP/etc). The outer header + * must be IPv4 or IPv6, followed by zero or more + * additional headers, up to LWT_BPF_MAX_HEADROOM total + * bytes in all prepended headers. Please note that + * if skb_is_gso(skb) is true, no more than two headers + * can be prepended, and the inner header, if present, + * should be either GRE or UDP/GUE. + * + * BPF_LWT_ENCAP_SEG6*** types can be called by bpf programs of + * type BPF_PROG_TYPE_LWT_IN; BPF_LWT_ENCAP_IP type can be called + * by bpf programs of types BPF_PROG_TYPE_LWT_IN and + * BPF_PROG_TYPE_LWT_XMIT. * * A call to this helper is susceptible to change the underlaying * packet buffer. Therefore, at load time, all checks on pointers @@ -2328,6 +2342,23 @@ union bpf_attr { * "**y**". * Return * 0 + * + * struct bpf_sock *bpf_sk_fullsock(struct bpf_sock *sk) + * Description + * This helper gets a **struct bpf_sock** pointer such + * that all the fields in bpf_sock can be accessed. + * Return + * A **struct bpf_sock** pointer on success, or NULL in + * case of failure. + * + * struct bpf_tcp_sock *bpf_tcp_sock(struct bpf_sock *sk) + * Description + * This helper gets a **struct bpf_tcp_sock** pointer from a + * **struct bpf_sock** pointer. + * + * Return + * A **struct bpf_tcp_sock** pointer on success, or NULL in + * case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2422,7 +2453,11 @@ union bpf_attr { FN(map_peek_elem), \ FN(msg_push_data), \ FN(msg_pop_data), \ - FN(rc_pointer_rel), + FN(rc_pointer_rel), \ + FN(spin_lock), \ + FN(spin_unlock), \ + FN(sk_fullsock), \ + FN(tcp_sock), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -2495,7 +2530,8 @@ enum bpf_hdr_start_off { /* Encapsulation type for BPF_FUNC_lwt_push_encap helper. */ enum bpf_lwt_encap_mode { BPF_LWT_ENCAP_SEG6, - BPF_LWT_ENCAP_SEG6_INLINE + BPF_LWT_ENCAP_SEG6_INLINE, + BPF_LWT_ENCAP_IP, }; #define __bpf_md_ptr(type, name) \ @@ -2542,6 +2578,7 @@ struct __sk_buff { __u64 tstamp; __u32 wire_len; __u32 gso_segs; + __bpf_md_ptr(struct bpf_sock *, sk); }; struct bpf_tunnel_key { @@ -2583,7 +2620,15 @@ enum bpf_ret_code { BPF_DROP = 2, /* 3-6 reserved */ BPF_REDIRECT = 7, - /* >127 are reserved for prog type specific return codes */ + /* >127 are reserved for prog type specific return codes. + * + * BPF_LWT_REROUTE: used by BPF_PROG_TYPE_LWT_IN and + * BPF_PROG_TYPE_LWT_XMIT to indicate that skb had been + * changed and should be routed based on its new L3 header. + * (This is an L3 redirect, as opposed to L2 redirect + * represented by BPF_REDIRECT above). + */ + BPF_LWT_REROUTE = 128, }; struct bpf_sock { @@ -2593,14 +2638,52 @@ struct bpf_sock { __u32 protocol; __u32 mark; __u32 priority; - __u32 src_ip4; /* Allows 1,2,4-byte read. - * Stored in network byte order. + /* IP address also allows 1 and 2 bytes access */ + __u32 src_ip4; + __u32 src_ip6[4]; + __u32 src_port; /* host byte order */ + __u32 dst_port; /* network byte order */ + __u32 dst_ip4; + __u32 dst_ip6[4]; + __u32 state; +}; + +struct bpf_tcp_sock { + __u32 snd_cwnd; /* Sending congestion window */ + __u32 srtt_us; /* smoothed round trip time << 3 in usecs */ + __u32 rtt_min; + __u32 snd_ssthresh; /* Slow start size threshold */ + __u32 rcv_nxt; /* What we want to receive next */ + __u32 snd_nxt; /* Next sequence we send */ + __u32 snd_una; /* First byte we want an ack for */ + __u32 mss_cache; /* Cached effective mss, not including SACKS */ + __u32 ecn_flags; /* ECN status bits. */ + __u32 rate_delivered; /* saved rate sample: packets delivered */ + __u32 rate_interval_us; /* saved rate sample: time elapsed */ + __u32 packets_out; /* Packets which are "in flight" */ + __u32 retrans_out; /* Retransmitted packets out */ + __u32 total_retrans; /* Total retransmits for entire connection */ + __u32 segs_in; /* RFC4898 tcpEStatsPerfSegsIn + * total number of segments in. */ - __u32 src_ip6[4]; /* Allows 1,2,4-byte read. - * Stored in network byte order. + __u32 data_segs_in; /* RFC4898 tcpEStatsPerfDataSegsIn + * total number of data segments in. */ - __u32 src_port; /* Allows 4-byte read. - * Stored in host byte order + __u32 segs_out; /* RFC4898 tcpEStatsPerfSegsOut + * The total number of segments sent. + */ + __u32 data_segs_out; /* RFC4898 tcpEStatsPerfDataSegsOut + * total number of data segments sent. + */ + __u32 lost_out; /* Lost packets */ + __u32 sacked_out; /* SACK'd packets */ + __u64 bytes_received; /* RFC4898 tcpEStatsAppHCThruOctetsReceived + * sum(delta(rcv_nxt)), or how many bytes + * were acked. + */ + __u64 bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked + * sum(delta(snd_una)), or how many bytes + * were acked. */ }; @@ -3056,4 +3139,7 @@ struct bpf_line_info { __u32 line_col; }; +struct bpf_spin_lock { + __u32 val; +}; #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 6e52d3660654..53de8802a000 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -89,6 +89,22 @@ enum devlink_command { DEVLINK_CMD_REGION_DEL, DEVLINK_CMD_REGION_READ, + DEVLINK_CMD_PORT_PARAM_GET, /* can dump */ + DEVLINK_CMD_PORT_PARAM_SET, + DEVLINK_CMD_PORT_PARAM_NEW, + DEVLINK_CMD_PORT_PARAM_DEL, + + DEVLINK_CMD_INFO_GET, /* can dump */ + + DEVLINK_CMD_HEALTH_REPORTER_GET, + DEVLINK_CMD_HEALTH_REPORTER_SET, + DEVLINK_CMD_HEALTH_REPORTER_RECOVER, + DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, + DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET, + DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR, + + DEVLINK_CMD_FLASH_UPDATE, + /* add new commands above here */ __DEVLINK_CMD_MAX, DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1 @@ -285,6 +301,37 @@ enum devlink_attr { DEVLINK_ATTR_REGION_CHUNK_ADDR, /* u64 */ DEVLINK_ATTR_REGION_CHUNK_LEN, /* u64 */ + DEVLINK_ATTR_INFO_DRIVER_NAME, /* string */ + DEVLINK_ATTR_INFO_SERIAL_NUMBER, /* string */ + DEVLINK_ATTR_INFO_VERSION_FIXED, /* nested */ + DEVLINK_ATTR_INFO_VERSION_RUNNING, /* nested */ + DEVLINK_ATTR_INFO_VERSION_STORED, /* nested */ + DEVLINK_ATTR_INFO_VERSION_NAME, /* string */ + DEVLINK_ATTR_INFO_VERSION_VALUE, /* string */ + + DEVLINK_ATTR_SB_POOL_CELL_SIZE, /* u32 */ + + DEVLINK_ATTR_FMSG, /* nested */ + DEVLINK_ATTR_FMSG_OBJ_NEST_START, /* flag */ + DEVLINK_ATTR_FMSG_PAIR_NEST_START, /* flag */ + DEVLINK_ATTR_FMSG_ARR_NEST_START, /* flag */ + DEVLINK_ATTR_FMSG_NEST_END, /* flag */ + DEVLINK_ATTR_FMSG_OBJ_NAME, /* string */ + DEVLINK_ATTR_FMSG_OBJ_VALUE_TYPE, /* u8 */ + DEVLINK_ATTR_FMSG_OBJ_VALUE_DATA, /* dynamic */ + + DEVLINK_ATTR_HEALTH_REPORTER, /* nested */ + DEVLINK_ATTR_HEALTH_REPORTER_NAME, /* string */ + DEVLINK_ATTR_HEALTH_REPORTER_STATE, /* u8 */ + DEVLINK_ATTR_HEALTH_REPORTER_ERR, /* u64 */ + DEVLINK_ATTR_HEALTH_REPORTER_RECOVER, /* u64 */ + DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS, /* u64 */ + DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD, /* u64 */ + DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER, /* u8 */ + + DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME, /* string */ + DEVLINK_ATTR_FLASH_UPDATE_COMPONENT, /* string */ + /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, diff --git a/include/uapi/linux/errqueue.h b/include/uapi/linux/errqueue.h index c0151200f7d1..28491dac074b 100644 --- a/include/uapi/linux/errqueue.h +++ b/include/uapi/linux/errqueue.h @@ -3,6 +3,7 @@ #define _UAPI_LINUX_ERRQUEUE_H #include <linux/types.h> +#include <linux/time_types.h> struct sock_extended_err { __u32 ee_errno; @@ -41,6 +42,10 @@ struct scm_timestamping { struct timespec ts[3]; }; +struct scm_timestamping64 { + struct __kernel_timespec ts[3]; +}; + /* The type of scm_timestamping, passed in sock_extended_err ee_info. * This defines the type of ts[0]. For SCM_TSTAMP_SND only, if ts[0] * is zero, then this is a hardware timestamp and recorded in ts[2]. diff --git a/include/uapi/linux/inet_diag.h b/include/uapi/linux/inet_diag.h index 14565d703291..e8baca85bac6 100644 --- a/include/uapi/linux/inet_diag.h +++ b/include/uapi/linux/inet_diag.h @@ -137,15 +137,21 @@ enum { INET_DIAG_TCLASS, INET_DIAG_SKMEMINFO, INET_DIAG_SHUTDOWN, - INET_DIAG_DCTCPINFO, - INET_DIAG_PROTOCOL, /* response attribute only */ + + /* + * Next extenstions cannot be requested in struct inet_diag_req_v2: + * its field idiag_ext has only 8 bits. + */ + + INET_DIAG_DCTCPINFO, /* request as INET_DIAG_VEGASINFO */ + INET_DIAG_PROTOCOL, /* response attribute only */ INET_DIAG_SKV6ONLY, INET_DIAG_LOCALS, INET_DIAG_PEERS, INET_DIAG_PAD, - INET_DIAG_MARK, - INET_DIAG_BBRINFO, - INET_DIAG_CLASS_ID, + INET_DIAG_MARK, /* only with CAP_NET_ADMIN */ + INET_DIAG_BBRINFO, /* request as INET_DIAG_VEGASINFO */ + INET_DIAG_CLASS_ID, /* request as INET_DIAG_TCLASS */ INET_DIAG_MD5SIG, __INET_DIAG_MAX, }; diff --git a/include/uapi/linux/mdio.h b/include/uapi/linux/mdio.h index d435b00d64ad..0a552061ff1c 100644 --- a/include/uapi/linux/mdio.h +++ b/include/uapi/linux/mdio.h @@ -45,6 +45,7 @@ #define MDIO_AN_ADVERTISE 16 /* AN advertising (base page) */ #define MDIO_AN_LPA 19 /* AN LP abilities (base page) */ #define MDIO_PCS_EEE_ABLE 20 /* EEE Capability register */ +#define MDIO_PMA_NG_EXTABLE 21 /* 2.5G/5G PMA/PMD extended ability */ #define MDIO_PCS_EEE_WK_ERR 22 /* EEE wake error counter */ #define MDIO_PHYXS_LNSTAT 24 /* PHY XGXS lane state */ #define MDIO_AN_EEE_ADV 60 /* EEE advertisement */ @@ -92,6 +93,10 @@ #define MDIO_CTRL1_SPEED10G (MDIO_CTRL1_SPEEDSELEXT | 0x00) /* 10PASS-TS/2BASE-TL */ #define MDIO_CTRL1_SPEED10P2B (MDIO_CTRL1_SPEEDSELEXT | 0x04) +/* 2.5 Gb/s */ +#define MDIO_CTRL1_SPEED2_5G (MDIO_CTRL1_SPEEDSELEXT | 0x18) +/* 5 Gb/s */ +#define MDIO_CTRL1_SPEED5G (MDIO_CTRL1_SPEEDSELEXT | 0x1c) /* Status register 1. */ #define MDIO_STAT1_LPOWERABLE 0x0002 /* Low-power ability */ @@ -115,6 +120,7 @@ /* Device present registers. */ #define MDIO_DEVS_PRESENT(devad) (1 << (devad)) +#define MDIO_DEVS_C22PRESENT MDIO_DEVS_PRESENT(0) #define MDIO_DEVS_PMAPMD MDIO_DEVS_PRESENT(MDIO_MMD_PMAPMD) #define MDIO_DEVS_WIS MDIO_DEVS_PRESENT(MDIO_MMD_WIS) #define MDIO_DEVS_PCS MDIO_DEVS_PRESENT(MDIO_MMD_PCS) @@ -123,6 +129,8 @@ #define MDIO_DEVS_TC MDIO_DEVS_PRESENT(MDIO_MMD_TC) #define MDIO_DEVS_AN MDIO_DEVS_PRESENT(MDIO_MMD_AN) #define MDIO_DEVS_C22EXT MDIO_DEVS_PRESENT(MDIO_MMD_C22EXT) +#define MDIO_DEVS_VEND1 MDIO_DEVS_PRESENT(MDIO_MMD_VEND1) +#define MDIO_DEVS_VEND2 MDIO_DEVS_PRESENT(MDIO_MMD_VEND2) /* Control register 2. */ #define MDIO_PMA_CTRL2_TYPE 0x000f /* PMA/PMD type selection */ @@ -142,6 +150,8 @@ #define MDIO_PMA_CTRL2_1000BKX 0x000d /* 1000BASE-KX type */ #define MDIO_PMA_CTRL2_100BTX 0x000e /* 100BASE-TX type */ #define MDIO_PMA_CTRL2_10BT 0x000f /* 10BASE-T type */ +#define MDIO_PMA_CTRL2_2_5GBT 0x0030 /* 2.5GBaseT type */ +#define MDIO_PMA_CTRL2_5GBT 0x0031 /* 5GBaseT type */ #define MDIO_PCS_CTRL2_TYPE 0x0003 /* PCS type selection */ #define MDIO_PCS_CTRL2_10GBR 0x0000 /* 10GBASE-R type */ #define MDIO_PCS_CTRL2_10GBX 0x0001 /* 10GBASE-X type */ @@ -195,6 +205,7 @@ #define MDIO_PMA_EXTABLE_1000BKX 0x0040 /* 1000BASE-KX ability */ #define MDIO_PMA_EXTABLE_100BTX 0x0080 /* 100BASE-TX ability */ #define MDIO_PMA_EXTABLE_10BT 0x0100 /* 10BASE-T ability */ +#define MDIO_PMA_EXTABLE_NBT 0x4000 /* 2.5/5GBASE-T ability */ /* PHY XGXS lane state register. */ #define MDIO_PHYXS_LNSTAT_SYNC0 0x0001 @@ -231,9 +242,13 @@ #define MDIO_PCS_10GBRT_STAT2_BER 0x3f00 /* AN 10GBASE-T control register. */ +#define MDIO_AN_10GBT_CTRL_ADV2_5G 0x0080 /* Advertise 2.5GBASE-T */ +#define MDIO_AN_10GBT_CTRL_ADV5G 0x0100 /* Advertise 5GBASE-T */ #define MDIO_AN_10GBT_CTRL_ADV10G 0x1000 /* Advertise 10GBASE-T */ /* AN 10GBASE-T status register. */ +#define MDIO_AN_10GBT_STAT_LP2_5G 0x0020 /* LP is 2.5GBT capable */ +#define MDIO_AN_10GBT_STAT_LP5G 0x0040 /* LP is 5GBT capable */ #define MDIO_AN_10GBT_STAT_LPTRR 0x0200 /* LP training reset req. */ #define MDIO_AN_10GBT_STAT_LPLTABLE 0x0400 /* LP loop timing ability */ #define MDIO_AN_10GBT_STAT_LP10G 0x0800 /* LP is 10GBT capable */ @@ -262,6 +277,10 @@ #define MDIO_EEE_10GKX4 0x0020 /* 10G KX4 EEE cap */ #define MDIO_EEE_10GKR 0x0040 /* 10G KR EEE cap */ +/* 2.5G/5G Extended abilities register. */ +#define MDIO_PMA_NG_EXTABLE_2_5GBT 0x0001 /* 2.5GBASET ability */ +#define MDIO_PMA_NG_EXTABLE_5GBT 0x0002 /* 5GBASET ability */ + /* LASI RX_ALARM control/status registers. */ #define MDIO_PMA_LASI_RX_PHYXSLFLT 0x0001 /* PHY XS RX local fault */ #define MDIO_PMA_LASI_RX_PCSLFLT 0x0008 /* PCS RX local fault */ diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 31ae5c7f10e3..dd4f86ee286e 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1565,6 +1565,12 @@ enum nl80211_commands { * (a u32 with flags from &enum nl80211_wpa_versions). * @NL80211_ATTR_AKM_SUITES: Used with CONNECT, ASSOCIATE, and NEW_BEACON to * indicate which key management algorithm(s) to use (an array of u32). + * This attribute is also sent in response to @NL80211_CMD_GET_WIPHY, + * indicating the supported AKM suites, intended for specific drivers which + * implement SME and have constraints on which AKMs are supported and also + * the cases where an AKM support is offloaded to the driver/firmware. + * If there is no such notification from the driver, user space should + * assume the driver supports all the AKM suites. * * @NL80211_ATTR_REQ_IE: (Re)association request information elements as * sent out by the card, for ROAM and successful CONNECT events. @@ -2260,10 +2266,10 @@ enum nl80211_commands { * &enum nl80211_external_auth_action value). This is used with the * %NL80211_CMD_EXTERNAL_AUTH request event. * @NL80211_ATTR_EXTERNAL_AUTH_SUPPORT: Flag attribute indicating that the user - * space supports external authentication. This attribute shall be used - * only with %NL80211_CMD_CONNECT request. The driver may offload - * authentication processing to user space if this capability is indicated - * in NL80211_CMD_CONNECT requests from the user space. + * space supports external authentication. This attribute shall be used + * with %NL80211_CMD_CONNECT and %NL80211_CMD_START_AP request. The driver + * may offload authentication processing to user space if this capability + * is indicated in the respective requests from the user space. * * @NL80211_ATTR_NSS: Station's New/updated RX_NSS value notified using this * u8 attribute. This is used with %NL80211_CMD_STA_OPMODE_CHANGED. @@ -2299,6 +2305,9 @@ enum nl80211_commands { * This is also used for capability advertisement in the wiphy information, * with the appropriate sub-attributes. * + * @NL80211_ATTR_AIRTIME_WEIGHT: Station's weight when scheduled by the airtime + * scheduler. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -2748,6 +2757,8 @@ enum nl80211_attrs { NL80211_ATTR_PEER_MEASUREMENTS, + NL80211_ATTR_AIRTIME_WEIGHT, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -3125,6 +3136,9 @@ enum nl80211_sta_bss_param { * might not be fully accurate. * @NL80211_STA_INFO_CONNECTED_TO_GATE: set to true if STA has a path to a * mesh gate (u8, 0 or 1) + * @NL80211_STA_INFO_TX_DURATION: aggregate PPDU duration for all frames + * sent to the station (u64, usec) + * @NL80211_STA_INFO_AIRTIME_WEIGHT: current airtime weight for station (u16) * @__NL80211_STA_INFO_AFTER_LAST: internal * @NL80211_STA_INFO_MAX: highest possible station info attribute */ @@ -3168,6 +3182,8 @@ enum nl80211_sta_info { NL80211_STA_INFO_RX_MPDUS, NL80211_STA_INFO_FCS_ERROR_COUNT, NL80211_STA_INFO_CONNECTED_TO_GATE, + NL80211_STA_INFO_TX_DURATION, + NL80211_STA_INFO_AIRTIME_WEIGHT, /* keep last */ __NL80211_STA_INFO_AFTER_LAST, @@ -3277,8 +3293,10 @@ enum nl80211_mpath_flags { * &enum nl80211_mpath_flags; * @NL80211_MPATH_INFO_DISCOVERY_TIMEOUT: total path discovery timeout, in msec * @NL80211_MPATH_INFO_DISCOVERY_RETRIES: mesh path discovery retries + * @NL80211_MPATH_INFO_HOP_COUNT: hop count to destination + * @NL80211_MPATH_INFO_PATH_CHANGE: total number of path changes to destination * @NL80211_MPATH_INFO_MAX: highest mesh path information attribute number - * currently defind + * currently defined * @__NL80211_MPATH_INFO_AFTER_LAST: internal use */ enum nl80211_mpath_info { @@ -3290,6 +3308,8 @@ enum nl80211_mpath_info { NL80211_MPATH_INFO_FLAGS, NL80211_MPATH_INFO_DISCOVERY_TIMEOUT, NL80211_MPATH_INFO_DISCOVERY_RETRIES, + NL80211_MPATH_INFO_HOP_COUNT, + NL80211_MPATH_INFO_PATH_CHANGE, /* keep last */ __NL80211_MPATH_INFO_AFTER_LAST, @@ -5316,6 +5336,13 @@ enum nl80211_feature_flags { * if this flag is not set. Ignoring this can leak clear text packets and/or * freeze the connection. * + * @NL80211_EXT_FEATURE_AIRTIME_FAIRNESS: Driver supports getting airtime + * fairness for transmitted packets and has enabled airtime fairness + * scheduling. + * + * @NL80211_EXT_FEATURE_AP_PMKSA_CACHING: Driver/device supports PMKSA caching + * (set/del PMKSA operations) in AP mode. + * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@ -5355,6 +5382,8 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_SCAN_MIN_PREQ_CONTENT, NL80211_EXT_FEATURE_CAN_REPLACE_PTK0, NL80211_EXT_FEATURE_ENABLE_FTM_RESPONDER, + NL80211_EXT_FEATURE_AIRTIME_FAIRNESS, + NL80211_EXT_FEATURE_AP_PMKSA_CACHING, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, @@ -5606,9 +5635,14 @@ enum nl80211_crit_proto_id { * Used by cfg80211_rx_mgmt() * * @NL80211_RXMGMT_FLAG_ANSWERED: frame was answered by device/driver. + * @NL80211_RXMGMT_FLAG_EXTERNAL_AUTH: Host driver intends to offload + * the authentication. Exclusively defined for host drivers that + * advertises the SME functionality but would like the userspace + * to handle certain authentication algorithms (e.g. SAE). */ enum nl80211_rxmgmt_flags { NL80211_RXMGMT_FLAG_ANSWERED = 1 << 0, + NL80211_RXMGMT_FLAG_EXTERNAL_AUTH = 1 << 1, }; /* diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 02ac251be8c4..51a0496f78ea 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -63,12 +63,49 @@ enum { #define TC_ACT_GOTO_CHAIN __TC_ACT_EXT(2) #define TC_ACT_EXT_OPCODE_MAX TC_ACT_GOTO_CHAIN +/* These macros are put here for binary compatibility with userspace apps that + * make use of them. For kernel code and new userspace apps, use the TCA_ID_* + * versions. + */ +#define TCA_ACT_GACT 5 +#define TCA_ACT_IPT 6 +#define TCA_ACT_PEDIT 7 +#define TCA_ACT_MIRRED 8 +#define TCA_ACT_NAT 9 +#define TCA_ACT_XT 10 +#define TCA_ACT_SKBEDIT 11 +#define TCA_ACT_VLAN 12 +#define TCA_ACT_BPF 13 +#define TCA_ACT_CONNMARK 14 +#define TCA_ACT_SKBMOD 15 +#define TCA_ACT_CSUM 16 +#define TCA_ACT_TUNNEL_KEY 17 +#define TCA_ACT_SIMP 22 +#define TCA_ACT_IFE 25 +#define TCA_ACT_SAMPLE 26 + /* Action type identifiers*/ -enum { - TCA_ID_UNSPEC=0, - TCA_ID_POLICE=1, +enum tca_id { + TCA_ID_UNSPEC = 0, + TCA_ID_POLICE = 1, + TCA_ID_GACT = TCA_ACT_GACT, + TCA_ID_IPT = TCA_ACT_IPT, + TCA_ID_PEDIT = TCA_ACT_PEDIT, + TCA_ID_MIRRED = TCA_ACT_MIRRED, + TCA_ID_NAT = TCA_ACT_NAT, + TCA_ID_XT = TCA_ACT_XT, + TCA_ID_SKBEDIT = TCA_ACT_SKBEDIT, + TCA_ID_VLAN = TCA_ACT_VLAN, + TCA_ID_BPF = TCA_ACT_BPF, + TCA_ID_CONNMARK = TCA_ACT_CONNMARK, + TCA_ID_SKBMOD = TCA_ACT_SKBMOD, + TCA_ID_CSUM = TCA_ACT_CSUM, + TCA_ID_TUNNEL_KEY = TCA_ACT_TUNNEL_KEY, + TCA_ID_SIMP = TCA_ACT_SIMP, + TCA_ID_IFE = TCA_ACT_IFE, + TCA_ID_SAMPLE = TCA_ACT_SAMPLE, /* other actions go here */ - __TCA_ID_MAX=255 + __TCA_ID_MAX = 255 }; #define TCA_ID_MAX __TCA_ID_MAX diff --git a/include/uapi/linux/rds.h b/include/uapi/linux/rds.h index 8b73cb603c5f..5d0f76c780e5 100644 --- a/include/uapi/linux/rds.h +++ b/include/uapi/linux/rds.h @@ -69,6 +69,12 @@ #define RDS_TRANS_COUNT 3 #define RDS_TRANS_NONE (~0) +/* IOCTLS commands for SOL_RDS */ +#define SIOCRDSSETTOS (SIOCPROTOPRIVATE) +#define SIOCRDSGETTOS (SIOCPROTOPRIVATE + 1) + +typedef __u8 rds_tos_t; + /* * Control message types for SOL_RDS. * @@ -149,6 +155,7 @@ struct rds_info_connection { __be32 faddr; __u8 transport[TRANSNAMSIZ]; /* null term ascii */ __u8 flags; + __u8 tos; } __attribute__((packed)); struct rds6_info_connection { @@ -171,6 +178,7 @@ struct rds_info_message { __be16 lport; __be16 fport; __u8 flags; + __u8 tos; } __attribute__((packed)); struct rds6_info_message { @@ -214,6 +222,7 @@ struct rds_info_tcp_socket { __u32 last_sent_nxt; __u32 last_expected_una; __u32 last_seen_una; + __u8 tos; } __attribute__((packed)); struct rds6_info_tcp_socket { @@ -240,6 +249,7 @@ struct rds_info_rdma_connection { __u32 max_send_sge; __u32 rdma_mr_max; __u32 rdma_mr_size; + __u8 tos; }; struct rds6_info_rdma_connection { @@ -253,6 +263,7 @@ struct rds6_info_rdma_connection { __u32 max_send_sge; __u32 rdma_mr_max; __u32 rdma_mr_size; + __u8 tos; }; /* RDS message Receive Path Latency points */ diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index d584073532b8..b8f2c4d56532 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -59,6 +59,10 @@ typedef __s32 sctp_assoc_t; +#define SCTP_FUTURE_ASSOC 0 +#define SCTP_CURRENT_ASSOC 1 +#define SCTP_ALL_ASSOC 2 + /* The following symbols come from the Sockets API Extensions for * SCTP <draft-ietf-tsvwg-sctpsocket-07.txt>. */ diff --git a/include/uapi/linux/tc_act/tc_bpf.h b/include/uapi/linux/tc_act/tc_bpf.h index 6e89a5df49a4..653c4f94f76e 100644 --- a/include/uapi/linux/tc_act/tc_bpf.h +++ b/include/uapi/linux/tc_act/tc_bpf.h @@ -13,8 +13,6 @@ #include <linux/pkt_cls.h> -#define TCA_ACT_BPF 13 - struct tc_act_bpf { tc_gen; }; diff --git a/include/uapi/linux/tc_act/tc_connmark.h b/include/uapi/linux/tc_act/tc_connmark.h index 80caa47b1933..9f8f6f709feb 100644 --- a/include/uapi/linux/tc_act/tc_connmark.h +++ b/include/uapi/linux/tc_act/tc_connmark.h @@ -5,8 +5,6 @@ #include <linux/types.h> #include <linux/pkt_cls.h> -#define TCA_ACT_CONNMARK 14 - struct tc_connmark { tc_gen; __u16 zone; diff --git a/include/uapi/linux/tc_act/tc_csum.h b/include/uapi/linux/tc_act/tc_csum.h index 0ecf4d29e2f3..94b2044929de 100644 --- a/include/uapi/linux/tc_act/tc_csum.h +++ b/include/uapi/linux/tc_act/tc_csum.h @@ -5,8 +5,6 @@ #include <linux/types.h> #include <linux/pkt_cls.h> -#define TCA_ACT_CSUM 16 - enum { TCA_CSUM_UNSPEC, TCA_CSUM_PARMS, diff --git a/include/uapi/linux/tc_act/tc_gact.h b/include/uapi/linux/tc_act/tc_gact.h index 94273c3b81b0..37e5392e02c7 100644 --- a/include/uapi/linux/tc_act/tc_gact.h +++ b/include/uapi/linux/tc_act/tc_gact.h @@ -5,7 +5,6 @@ #include <linux/types.h> #include <linux/pkt_cls.h> -#define TCA_ACT_GACT 5 struct tc_gact { tc_gen; diff --git a/include/uapi/linux/tc_act/tc_ife.h b/include/uapi/linux/tc_act/tc_ife.h index 2f48490ef386..8c401f185675 100644 --- a/include/uapi/linux/tc_act/tc_ife.h +++ b/include/uapi/linux/tc_act/tc_ife.h @@ -6,7 +6,6 @@ #include <linux/pkt_cls.h> #include <linux/ife.h> -#define TCA_ACT_IFE 25 /* Flag bits for now just encoding/decoding; mutually exclusive */ #define IFE_ENCODE 1 #define IFE_DECODE 0 diff --git a/include/uapi/linux/tc_act/tc_ipt.h b/include/uapi/linux/tc_act/tc_ipt.h index b743c8bddd13..c48d7da6750d 100644 --- a/include/uapi/linux/tc_act/tc_ipt.h +++ b/include/uapi/linux/tc_act/tc_ipt.h @@ -4,9 +4,6 @@ #include <linux/pkt_cls.h> -#define TCA_ACT_IPT 6 -#define TCA_ACT_XT 10 - enum { TCA_IPT_UNSPEC, TCA_IPT_TABLE, diff --git a/include/uapi/linux/tc_act/tc_mirred.h b/include/uapi/linux/tc_act/tc_mirred.h index 5dd671cf5776..2500a0005d05 100644 --- a/include/uapi/linux/tc_act/tc_mirred.h +++ b/include/uapi/linux/tc_act/tc_mirred.h @@ -5,7 +5,6 @@ #include <linux/types.h> #include <linux/pkt_cls.h> -#define TCA_ACT_MIRRED 8 #define TCA_EGRESS_REDIR 1 /* packet redirect to EGRESS*/ #define TCA_EGRESS_MIRROR 2 /* mirror packet to EGRESS */ #define TCA_INGRESS_REDIR 3 /* packet redirect to INGRESS*/ diff --git a/include/uapi/linux/tc_act/tc_nat.h b/include/uapi/linux/tc_act/tc_nat.h index 086be842587b..21399c2c6130 100644 --- a/include/uapi/linux/tc_act/tc_nat.h +++ b/include/uapi/linux/tc_act/tc_nat.h @@ -5,8 +5,6 @@ #include <linux/pkt_cls.h> #include <linux/types.h> -#define TCA_ACT_NAT 9 - enum { TCA_NAT_UNSPEC, TCA_NAT_PARMS, diff --git a/include/uapi/linux/tc_act/tc_pedit.h b/include/uapi/linux/tc_act/tc_pedit.h index 24ec792dacc1..f3e61b04fa01 100644 --- a/include/uapi/linux/tc_act/tc_pedit.h +++ b/include/uapi/linux/tc_act/tc_pedit.h @@ -5,8 +5,6 @@ #include <linux/types.h> #include <linux/pkt_cls.h> -#define TCA_ACT_PEDIT 7 - enum { TCA_PEDIT_UNSPEC, TCA_PEDIT_TM, diff --git a/include/uapi/linux/tc_act/tc_sample.h b/include/uapi/linux/tc_act/tc_sample.h index bd7e9f03abd2..fee1bcc20793 100644 --- a/include/uapi/linux/tc_act/tc_sample.h +++ b/include/uapi/linux/tc_act/tc_sample.h @@ -6,8 +6,6 @@ #include <linux/pkt_cls.h> #include <linux/if_ether.h> -#define TCA_ACT_SAMPLE 26 - struct tc_sample { tc_gen; }; diff --git a/include/uapi/linux/tc_act/tc_skbedit.h b/include/uapi/linux/tc_act/tc_skbedit.h index 6de6071ebed6..800e93377218 100644 --- a/include/uapi/linux/tc_act/tc_skbedit.h +++ b/include/uapi/linux/tc_act/tc_skbedit.h @@ -23,8 +23,6 @@ #include <linux/pkt_cls.h> -#define TCA_ACT_SKBEDIT 11 - #define SKBEDIT_F_PRIORITY 0x1 #define SKBEDIT_F_QUEUE_MAPPING 0x2 #define SKBEDIT_F_MARK 0x4 diff --git a/include/uapi/linux/tc_act/tc_skbmod.h b/include/uapi/linux/tc_act/tc_skbmod.h index 38c072f66f2f..c525b3503797 100644 --- a/include/uapi/linux/tc_act/tc_skbmod.h +++ b/include/uapi/linux/tc_act/tc_skbmod.h @@ -13,8 +13,6 @@ #include <linux/pkt_cls.h> -#define TCA_ACT_SKBMOD 15 - #define SKBMOD_F_DMAC 0x1 #define SKBMOD_F_SMAC 0x2 #define SKBMOD_F_ETYPE 0x4 diff --git a/include/uapi/linux/tc_act/tc_tunnel_key.h b/include/uapi/linux/tc_act/tc_tunnel_key.h index be384d63e1b5..41c8b462c177 100644 --- a/include/uapi/linux/tc_act/tc_tunnel_key.h +++ b/include/uapi/linux/tc_act/tc_tunnel_key.h @@ -14,8 +14,6 @@ #include <linux/pkt_cls.h> -#define TCA_ACT_TUNNEL_KEY 17 - #define TCA_TUNNEL_KEY_ACT_SET 1 #define TCA_TUNNEL_KEY_ACT_RELEASE 2 diff --git a/include/uapi/linux/tc_act/tc_vlan.h b/include/uapi/linux/tc_act/tc_vlan.h index 0d7b5fd6605b..168995b54a70 100644 --- a/include/uapi/linux/tc_act/tc_vlan.h +++ b/include/uapi/linux/tc_act/tc_vlan.h @@ -13,8 +13,6 @@ #include <linux/pkt_cls.h> -#define TCA_ACT_VLAN 12 - #define TCA_VLAN_ACT_POP 1 #define TCA_VLAN_ACT_PUSH 2 #define TCA_VLAN_ACT_MODIFY 3 diff --git a/include/uapi/linux/time.h b/include/uapi/linux/time.h index 6b56a2208be7..958932effc5e 100644 --- a/include/uapi/linux/time.h +++ b/include/uapi/linux/time.h @@ -3,7 +3,7 @@ #define _UAPI_LINUX_TIME_H #include <linux/types.h> - +#include <linux/time_types.h> #ifndef _STRUCT_TIMESPEC #define _STRUCT_TIMESPEC @@ -23,7 +23,6 @@ struct timezone { int tz_dsttime; /* type of dst correction */ }; - /* * Names of the interval timers, and structure * defining a timer setting: @@ -42,32 +41,6 @@ struct itimerval { struct timeval it_value; /* current value */ }; -#ifndef __kernel_timespec -struct __kernel_timespec { - __kernel_time64_t tv_sec; /* seconds */ - long long tv_nsec; /* nanoseconds */ -}; -#endif - -#ifndef __kernel_itimerspec -struct __kernel_itimerspec { - struct __kernel_timespec it_interval; /* timer period */ - struct __kernel_timespec it_value; /* timer expiration */ -}; -#endif - -/* - * legacy timeval structure, only embedded in structures that - * traditionally used 'timeval' to pass time intervals (not absolute - * times). Do not add new users. If user space fails to compile - * here, this is probably because it is not y2038 safe and needs to - * be changed to use another interface. - */ -struct __kernel_old_timeval { - __kernel_long_t tv_sec; - __kernel_long_t tv_usec; -}; - /* * The IDs of the various system clocks (for POSIX.1b interval timers): */ diff --git a/include/uapi/linux/time_types.h b/include/uapi/linux/time_types.h new file mode 100644 index 000000000000..459070c61d47 --- /dev/null +++ b/include/uapi/linux/time_types.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_LINUX_TIME_TYPES_H +#define _UAPI_LINUX_TIME_TYPES_H + +#include <linux/types.h> + +#ifndef __kernel_timespec +struct __kernel_timespec { + __kernel_time64_t tv_sec; /* seconds */ + long long tv_nsec; /* nanoseconds */ +}; +#endif + +#ifndef __kernel_itimerspec +struct __kernel_itimerspec { + struct __kernel_timespec it_interval; /* timer period */ + struct __kernel_timespec it_value; /* timer expiration */ +}; +#endif + +/* + * legacy timeval structure, only embedded in structures that + * traditionally used 'timeval' to pass time intervals (not absolute + * times). Do not add new users. If user space fails to compile + * here, this is probably because it is not y2038 safe and needs to + * be changed to use another interface. + */ +#ifndef __kernel_old_timeval +struct __kernel_old_timeval { + __kernel_long_t tv_sec; + __kernel_long_t tv_usec; +}; +#endif + +struct __kernel_sock_timeval { + __s64 tv_sec; + __s64 tv_usec; +}; + +#endif /* _UAPI_LINUX_TIME_TYPES_H */ diff --git a/include/uapi/linux/tls.h b/include/uapi/linux/tls.h index ff02287495ac..401d6f01de6a 100644 --- a/include/uapi/linux/tls.h +++ b/include/uapi/linux/tls.h @@ -51,6 +51,10 @@ #define TLS_1_2_VERSION_MINOR 0x3 #define TLS_1_2_VERSION TLS_VERSION_NUMBER(TLS_1_2) +#define TLS_1_3_VERSION_MAJOR 0x3 +#define TLS_1_3_VERSION_MINOR 0x4 +#define TLS_1_3_VERSION TLS_VERSION_NUMBER(TLS_1_3) + /* Supported ciphers */ #define TLS_CIPHER_AES_GCM_128 51 #define TLS_CIPHER_AES_GCM_128_IV_SIZE 8 @@ -59,6 +63,13 @@ #define TLS_CIPHER_AES_GCM_128_TAG_SIZE 16 #define TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE 8 +#define TLS_CIPHER_AES_GCM_256 52 +#define TLS_CIPHER_AES_GCM_256_IV_SIZE 8 +#define TLS_CIPHER_AES_GCM_256_KEY_SIZE 32 +#define TLS_CIPHER_AES_GCM_256_SALT_SIZE 4 +#define TLS_CIPHER_AES_GCM_256_TAG_SIZE 16 +#define TLS_CIPHER_AES_GCM_256_REC_SEQ_SIZE 8 + #define TLS_SET_RECORD_TYPE 1 #define TLS_GET_RECORD_TYPE 2 @@ -75,4 +86,12 @@ struct tls12_crypto_info_aes_gcm_128 { unsigned char rec_seq[TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE]; }; +struct tls12_crypto_info_aes_gcm_256 { + struct tls_crypto_info info; + unsigned char iv[TLS_CIPHER_AES_GCM_256_IV_SIZE]; + unsigned char key[TLS_CIPHER_AES_GCM_256_KEY_SIZE]; + unsigned char salt[TLS_CIPHER_AES_GCM_256_SALT_SIZE]; + unsigned char rec_seq[TLS_CIPHER_AES_GCM_256_REC_SEQ_SIZE]; +}; + #endif /* _UAPI_LINUX_TLS_H */ diff --git a/include/uapi/linux/virtio_config.h b/include/uapi/linux/virtio_config.h index 1196e1c1d4f6..ff8e7dc9d4dd 100644 --- a/include/uapi/linux/virtio_config.h +++ b/include/uapi/linux/virtio_config.h @@ -79,6 +79,12 @@ #define VIRTIO_F_RING_PACKED 34 /* + * This feature indicates that memory accesses by the driver and the + * device are ordered in a way described by the platform. + */ +#define VIRTIO_F_ORDER_PLATFORM 36 + +/* * Does the device support Single Root I/O Virtualization? */ #define VIRTIO_F_SR_IOV 37 diff --git a/include/uapi/linux/virtio_ring.h b/include/uapi/linux/virtio_ring.h index 2414f8af26b3..4c4e24c291a5 100644 --- a/include/uapi/linux/virtio_ring.h +++ b/include/uapi/linux/virtio_ring.h @@ -213,14 +213,4 @@ struct vring_packed_desc { __le16 flags; }; -struct vring_packed { - unsigned int num; - - struct vring_packed_desc *desc; - - struct vring_packed_desc_event *driver; - - struct vring_packed_desc_event *device; -}; - #endif /* _UAPI_LINUX_VIRTIO_RING_H */ diff --git a/include/uapi/rdma/hns-abi.h b/include/uapi/rdma/hns-abi.h index ef3c7ec793a7..eb76b38a00d4 100644 --- a/include/uapi/rdma/hns-abi.h +++ b/include/uapi/rdma/hns-abi.h @@ -52,6 +52,11 @@ struct hns_roce_ib_create_srq { __aligned_u64 que_addr; }; +struct hns_roce_ib_create_srq_resp { + __u32 srqn; + __u32 reserved; +}; + struct hns_roce_ib_create_qp { __aligned_u64 buf_addr; __aligned_u64 db_addr; diff --git a/init/Kconfig b/init/Kconfig index 513fa544a134..c9386a365eea 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -512,6 +512,17 @@ config PSI_DEFAULT_DISABLED per default but can be enabled through passing psi=1 on the kernel commandline during boot. + This feature adds some code to the task wakeup and sleep + paths of the scheduler. The overhead is too low to affect + common scheduling-intense workloads in practice (such as + webservers, memcache), but it does show up in artificial + scheduler stress tests, such as hackbench. + + If you are paranoid and not sure what the kernel will be + used for, say Y. + + Say N if unsure. + endmenu # "CPU/Task time and stats accounting" config CPU_ISOLATION @@ -825,7 +836,7 @@ config CGROUP_PIDS PIDs controller is designed to stop this from happening. It should be noted that organisational operations (such as attaching - to a cgroup hierarchy will *not* be blocked by the PIDs controller), + to a cgroup hierarchy) will *not* be blocked by the PIDs controller, since the PIDs limit only affects a process's ability to fork, not to attach to a cgroup. diff --git a/init/main.c b/init/main.c index e2e80ca3165a..c86a1c8f19f4 100644 --- a/init/main.c +++ b/init/main.c @@ -695,7 +695,6 @@ asmlinkage __visible void __init start_kernel(void) initrd_start = 0; } #endif - page_ext_init(); kmemleak_init(); setup_per_cpu_pageset(); numa_policy_init(); @@ -1131,6 +1130,8 @@ static noinline void __init kernel_init_freeable(void) sched_init_smp(); page_alloc_init_late(); + /* Initialize page ext after all struct pages are initialized. */ + page_ext_init(); do_basic_setup(); diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks index 84d882f3e299..fbba478ae522 100644 --- a/kernel/Kconfig.locks +++ b/kernel/Kconfig.locks @@ -242,6 +242,9 @@ config QUEUED_SPINLOCKS def_bool y if ARCH_USE_QUEUED_SPINLOCKS depends on SMP +config BPF_ARCH_SPINLOCK + bool + config ARCH_USE_QUEUED_RWLOCKS bool diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 25632a75d630..c72e0d8e1e65 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -253,8 +253,9 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value, { struct bpf_array *array = container_of(map, struct bpf_array, map); u32 index = *(u32 *)key; + char *val; - if (unlikely(map_flags > BPF_EXIST)) + if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST)) /* unknown flags */ return -EINVAL; @@ -262,17 +263,25 @@ static int array_map_update_elem(struct bpf_map *map, void *key, void *value, /* all elements were pre-allocated, cannot insert a new one */ return -E2BIG; - if (unlikely(map_flags == BPF_NOEXIST)) + if (unlikely(map_flags & BPF_NOEXIST)) /* all elements already exist */ return -EEXIST; - if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) + if (unlikely((map_flags & BPF_F_LOCK) && + !map_value_has_spin_lock(map))) + return -EINVAL; + + if (array->map.map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { memcpy(this_cpu_ptr(array->pptrs[index & array->index_mask]), value, map->value_size); - else - memcpy(array->value + - array->elem_size * (index & array->index_mask), - value, map->value_size); + } else { + val = array->value + + array->elem_size * (index & array->index_mask); + if (map_flags & BPF_F_LOCK) + copy_map_value_locked(map, val, value, false); + else + copy_map_value(map, val, value); + } return 0; } diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 3d661f0606fe..bd3921b1514b 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -355,6 +355,11 @@ static bool btf_type_is_struct(const struct btf_type *t) return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION; } +static bool __btf_type_is_struct(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_STRUCT; +} + static bool btf_type_is_array(const struct btf_type *t) { return BTF_INFO_KIND(t->info) == BTF_KIND_ARRAY; @@ -1525,7 +1530,8 @@ static int btf_modifier_resolve(struct btf_verifier_env *env, /* "typedef void new_void", "const void"...etc */ if (!btf_type_is_void(next_type) && - !btf_type_is_fwd(next_type)) { + !btf_type_is_fwd(next_type) && + !btf_type_is_func_proto(next_type)) { btf_verifier_log_type(env, v->t, "Invalid type_id"); return -EINVAL; } @@ -2045,6 +2051,43 @@ static void btf_struct_log(struct btf_verifier_env *env, btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t)); } +/* find 'struct bpf_spin_lock' in map value. + * return >= 0 offset if found + * and < 0 in case of error + */ +int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t) +{ + const struct btf_member *member; + u32 i, off = -ENOENT; + + if (!__btf_type_is_struct(t)) + return -EINVAL; + + for_each_member(i, t, member) { + const struct btf_type *member_type = btf_type_by_id(btf, + member->type); + if (!__btf_type_is_struct(member_type)) + continue; + if (member_type->size != sizeof(struct bpf_spin_lock)) + continue; + if (strcmp(__btf_name_by_offset(btf, member_type->name_off), + "bpf_spin_lock")) + continue; + if (off != -ENOENT) + /* only one 'struct bpf_spin_lock' is allowed */ + return -E2BIG; + off = btf_member_bit_offset(t, member); + if (off % 8) + /* valid C code cannot generate such BTF */ + return -EINVAL; + off /= 8; + if (off % __alignof__(struct bpf_spin_lock)) + /* valid struct bpf_spin_lock will be 4 byte aligned */ + return -EINVAL; + } + return off; +} + static void btf_struct_seq_show(const struct btf *btf, const struct btf_type *t, u32 type_id, void *data, u8 bits_offset, struct seq_file *m) diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index ab612fe9862f..4e807973aa80 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -230,6 +230,7 @@ cleanup: * @cgrp: The cgroup which descendants to traverse * @prog: A program to attach * @type: Type of attach operation + * @flags: Option flags * * Must be called with cgroup_mutex held. */ @@ -363,7 +364,7 @@ cleanup: * Must be called with cgroup_mutex held. */ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, - enum bpf_attach_type type, u32 unused_flags) + enum bpf_attach_type type) { struct list_head *progs = &cgrp->bpf.progs[type]; enum bpf_cgroup_storage_type stype; @@ -572,7 +573,7 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk, bpf_compute_and_save_data_end(skb, &saved_data_end); ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[type], skb, - bpf_prog_run_save_cb); + __bpf_prog_run_save_cb); bpf_restore_data_end(skb, saved_data_end); __skb_pull(skb, offset); skb->sk = save_sk; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index a7bcb23bee84..ef88b167959d 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1263,8 +1263,9 @@ bool bpf_opcode_in_insntable(u8 code) #ifndef CONFIG_BPF_JIT_ALWAYS_ON /** * __bpf_prog_run - run eBPF program on a given context - * @ctx: is the data we are operating on + * @regs: is the array of MAX_BPF_EXT_REG eBPF pseudo-registers * @insn: is the array of eBPF instructions + * @stack: is the eBPF storage stack * * Decode and execute eBPF instructions. */ @@ -2001,6 +2002,8 @@ const struct bpf_func_proto bpf_map_delete_elem_proto __weak; const struct bpf_func_proto bpf_map_push_elem_proto __weak; const struct bpf_func_proto bpf_map_pop_elem_proto __weak; const struct bpf_func_proto bpf_map_peek_elem_proto __weak; +const struct bpf_func_proto bpf_spin_lock_proto __weak; +const struct bpf_func_proto bpf_spin_unlock_proto __weak; const struct bpf_func_proto bpf_get_prandom_u32_proto __weak; const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak; diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 4b7c76765d9d..fed15cf94dca 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -686,7 +686,7 @@ static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) } if (htab_is_prealloc(htab)) { - pcpu_freelist_push(&htab->freelist, &l->fnode); + __pcpu_freelist_push(&htab->freelist, &l->fnode); } else { atomic_dec(&htab->count); l->htab = htab; @@ -718,21 +718,12 @@ static bool fd_htab_map_needs_adjust(const struct bpf_htab *htab) BITS_PER_LONG == 64; } -static u32 htab_size_value(const struct bpf_htab *htab, bool percpu) -{ - u32 size = htab->map.value_size; - - if (percpu || fd_htab_map_needs_adjust(htab)) - size = round_up(size, 8); - return size; -} - static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, void *value, u32 key_size, u32 hash, bool percpu, bool onallcpus, struct htab_elem *old_elem) { - u32 size = htab_size_value(htab, percpu); + u32 size = htab->map.value_size; bool prealloc = htab_is_prealloc(htab); struct htab_elem *l_new, **pl_new; void __percpu *pptr; @@ -748,7 +739,7 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, } else { struct pcpu_freelist_node *l; - l = pcpu_freelist_pop(&htab->freelist); + l = __pcpu_freelist_pop(&htab->freelist); if (!l) return ERR_PTR(-E2BIG); l_new = container_of(l, struct htab_elem, fnode); @@ -770,10 +761,13 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, l_new = ERR_PTR(-ENOMEM); goto dec_count; } + check_and_init_map_lock(&htab->map, + l_new->key + round_up(key_size, 8)); } memcpy(l_new->key, key, key_size); if (percpu) { + size = round_up(size, 8); if (prealloc) { pptr = htab_elem_get_ptr(l_new, key_size); } else { @@ -791,8 +785,13 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, if (!prealloc) htab_elem_set_ptr(l_new, key_size, pptr); - } else { + } else if (fd_htab_map_needs_adjust(htab)) { + size = round_up(size, 8); memcpy(l_new->key + round_up(key_size, 8), value, size); + } else { + copy_map_value(&htab->map, + l_new->key + round_up(key_size, 8), + value); } l_new->hash = hash; @@ -805,11 +804,11 @@ dec_count: static int check_flags(struct bpf_htab *htab, struct htab_elem *l_old, u64 map_flags) { - if (l_old && map_flags == BPF_NOEXIST) + if (l_old && (map_flags & ~BPF_F_LOCK) == BPF_NOEXIST) /* elem already exists */ return -EEXIST; - if (!l_old && map_flags == BPF_EXIST) + if (!l_old && (map_flags & ~BPF_F_LOCK) == BPF_EXIST) /* elem doesn't exist, cannot update it */ return -ENOENT; @@ -828,7 +827,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, u32 key_size, hash; int ret; - if (unlikely(map_flags > BPF_EXIST)) + if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST)) /* unknown flags */ return -EINVAL; @@ -841,6 +840,28 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, b = __select_bucket(htab, hash); head = &b->head; + if (unlikely(map_flags & BPF_F_LOCK)) { + if (unlikely(!map_value_has_spin_lock(map))) + return -EINVAL; + /* find an element without taking the bucket lock */ + l_old = lookup_nulls_elem_raw(head, hash, key, key_size, + htab->n_buckets); + ret = check_flags(htab, l_old, map_flags); + if (ret) + return ret; + if (l_old) { + /* grab the element lock and update value in place */ + copy_map_value_locked(map, + l_old->key + round_up(key_size, 8), + value, false); + return 0; + } + /* fall through, grab the bucket lock and lookup again. + * 99.9% chance that the element won't be found, + * but second lookup under lock has to be done. + */ + } + /* bpf_map_update_elem() can be called in_irq() */ raw_spin_lock_irqsave(&b->lock, flags); @@ -850,6 +871,20 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, if (ret) goto err; + if (unlikely(l_old && (map_flags & BPF_F_LOCK))) { + /* first lookup without the bucket lock didn't find the element, + * but second lookup with the bucket lock found it. + * This case is highly unlikely, but has to be dealt with: + * grab the element lock in addition to the bucket lock + * and update element in place + */ + copy_map_value_locked(map, + l_old->key + round_up(key_size, 8), + value, false); + ret = 0; + goto err; + } + l_new = alloc_htab_elem(htab, key, value, key_size, hash, false, false, l_old); if (IS_ERR(l_new)) { diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index a74972b07e74..a411fc17d265 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -221,6 +221,102 @@ const struct bpf_func_proto bpf_get_current_comm_proto = { .arg2_type = ARG_CONST_SIZE, }; +#if defined(CONFIG_QUEUED_SPINLOCKS) || defined(CONFIG_BPF_ARCH_SPINLOCK) + +static inline void __bpf_spin_lock(struct bpf_spin_lock *lock) +{ + arch_spinlock_t *l = (void *)lock; + union { + __u32 val; + arch_spinlock_t lock; + } u = { .lock = __ARCH_SPIN_LOCK_UNLOCKED }; + + compiletime_assert(u.val == 0, "__ARCH_SPIN_LOCK_UNLOCKED not 0"); + BUILD_BUG_ON(sizeof(*l) != sizeof(__u32)); + BUILD_BUG_ON(sizeof(*lock) != sizeof(__u32)); + arch_spin_lock(l); +} + +static inline void __bpf_spin_unlock(struct bpf_spin_lock *lock) +{ + arch_spinlock_t *l = (void *)lock; + + arch_spin_unlock(l); +} + +#else + +static inline void __bpf_spin_lock(struct bpf_spin_lock *lock) +{ + atomic_t *l = (void *)lock; + + BUILD_BUG_ON(sizeof(*l) != sizeof(*lock)); + do { + atomic_cond_read_relaxed(l, !VAL); + } while (atomic_xchg(l, 1)); +} + +static inline void __bpf_spin_unlock(struct bpf_spin_lock *lock) +{ + atomic_t *l = (void *)lock; + + atomic_set_release(l, 0); +} + +#endif + +static DEFINE_PER_CPU(unsigned long, irqsave_flags); + +notrace BPF_CALL_1(bpf_spin_lock, struct bpf_spin_lock *, lock) +{ + unsigned long flags; + + local_irq_save(flags); + __bpf_spin_lock(lock); + __this_cpu_write(irqsave_flags, flags); + return 0; +} + +const struct bpf_func_proto bpf_spin_lock_proto = { + .func = bpf_spin_lock, + .gpl_only = false, + .ret_type = RET_VOID, + .arg1_type = ARG_PTR_TO_SPIN_LOCK, +}; + +notrace BPF_CALL_1(bpf_spin_unlock, struct bpf_spin_lock *, lock) +{ + unsigned long flags; + + flags = __this_cpu_read(irqsave_flags); + __bpf_spin_unlock(lock); + local_irq_restore(flags); + return 0; +} + +const struct bpf_func_proto bpf_spin_unlock_proto = { + .func = bpf_spin_unlock, + .gpl_only = false, + .ret_type = RET_VOID, + .arg1_type = ARG_PTR_TO_SPIN_LOCK, +}; + +void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, + bool lock_src) +{ + struct bpf_spin_lock *lock; + + if (lock_src) + lock = src + map->spin_lock_off; + else + lock = dst + map->spin_lock_off; + preempt_disable(); + ____bpf_spin_lock(lock); + copy_map_value(map, dst, src); + ____bpf_spin_unlock(lock); + preempt_enable(); +} + #ifdef CONFIG_CGROUPS BPF_CALL_0(bpf_get_current_cgroup_id) { diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index 07a34ef562a0..6b572e2de7fb 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -131,7 +131,14 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *_key, struct bpf_cgroup_storage *storage; struct bpf_storage_buffer *new; - if (flags != BPF_ANY && flags != BPF_EXIST) + if (unlikely(flags & ~(BPF_F_LOCK | BPF_EXIST | BPF_NOEXIST))) + return -EINVAL; + + if (unlikely(flags & BPF_NOEXIST)) + return -EINVAL; + + if (unlikely((flags & BPF_F_LOCK) && + !map_value_has_spin_lock(map))) return -EINVAL; storage = cgroup_storage_lookup((struct bpf_cgroup_storage_map *)map, @@ -139,6 +146,11 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *_key, if (!storage) return -ENOENT; + if (flags & BPF_F_LOCK) { + copy_map_value_locked(map, storage->buf->data, value, false); + return 0; + } + new = kmalloc_node(sizeof(struct bpf_storage_buffer) + map->value_size, __GFP_ZERO | GFP_ATOMIC | __GFP_NOWARN, @@ -147,6 +159,7 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *_key, return -ENOMEM; memcpy(&new->data[0], value, map->value_size); + check_and_init_map_lock(map, new->data); new = xchg(&storage->buf, new); kfree_rcu(new, rcu); @@ -483,6 +496,7 @@ struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog, storage->buf = kmalloc_node(size, flags, map->numa_node); if (!storage->buf) goto enomem; + check_and_init_map_lock(map, storage->buf->data); } else { storage->percpu_buf = __alloc_percpu_gfp(size, 8, flags); if (!storage->percpu_buf) diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c index 52378d3e34b3..583346a0ab29 100644 --- a/kernel/bpf/map_in_map.c +++ b/kernel/bpf/map_in_map.c @@ -37,6 +37,11 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd) return ERR_PTR(-EINVAL); } + if (map_value_has_spin_lock(inner_map)) { + fdput(f); + return ERR_PTR(-ENOTSUPP); + } + inner_map_meta_size = sizeof(*inner_map_meta); /* In some cases verifier needs to access beyond just base map. */ if (inner_map->ops == &array_map_ops) diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index 39dba8c90331..ba635209ae9a 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -35,6 +35,7 @@ static DECLARE_RWSEM(bpf_devs_lock); struct bpf_offload_dev { const struct bpf_prog_offload_ops *ops; struct list_head netdevs; + void *priv; }; struct bpf_offload_netdev { @@ -669,7 +670,7 @@ unlock: EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_unregister); struct bpf_offload_dev * -bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops) +bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops, void *priv) { struct bpf_offload_dev *offdev; int err; @@ -688,6 +689,7 @@ bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops) return ERR_PTR(-ENOMEM); offdev->ops = ops; + offdev->priv = priv; INIT_LIST_HEAD(&offdev->netdevs); return offdev; @@ -700,3 +702,9 @@ void bpf_offload_dev_destroy(struct bpf_offload_dev *offdev) kfree(offdev); } EXPORT_SYMBOL_GPL(bpf_offload_dev_destroy); + +void *bpf_offload_dev_priv(struct bpf_offload_dev *offdev) +{ + return offdev->priv; +} +EXPORT_SYMBOL_GPL(bpf_offload_dev_priv); diff --git a/kernel/bpf/percpu_freelist.c b/kernel/bpf/percpu_freelist.c index 673fa6fe2d73..0c1b4ba9e90e 100644 --- a/kernel/bpf/percpu_freelist.c +++ b/kernel/bpf/percpu_freelist.c @@ -28,8 +28,8 @@ void pcpu_freelist_destroy(struct pcpu_freelist *s) free_percpu(s->freelist); } -static inline void __pcpu_freelist_push(struct pcpu_freelist_head *head, - struct pcpu_freelist_node *node) +static inline void ___pcpu_freelist_push(struct pcpu_freelist_head *head, + struct pcpu_freelist_node *node) { raw_spin_lock(&head->lock); node->next = head->first; @@ -37,12 +37,22 @@ static inline void __pcpu_freelist_push(struct pcpu_freelist_head *head, raw_spin_unlock(&head->lock); } -void pcpu_freelist_push(struct pcpu_freelist *s, +void __pcpu_freelist_push(struct pcpu_freelist *s, struct pcpu_freelist_node *node) { struct pcpu_freelist_head *head = this_cpu_ptr(s->freelist); - __pcpu_freelist_push(head, node); + ___pcpu_freelist_push(head, node); +} + +void pcpu_freelist_push(struct pcpu_freelist *s, + struct pcpu_freelist_node *node) +{ + unsigned long flags; + + local_irq_save(flags); + __pcpu_freelist_push(s, node); + local_irq_restore(flags); } void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size, @@ -63,7 +73,7 @@ void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size, for_each_possible_cpu(cpu) { again: head = per_cpu_ptr(s->freelist, cpu); - __pcpu_freelist_push(head, buf); + ___pcpu_freelist_push(head, buf); i++; buf += elem_size; if (i == nr_elems) @@ -74,14 +84,12 @@ again: local_irq_restore(flags); } -struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *s) +struct pcpu_freelist_node *__pcpu_freelist_pop(struct pcpu_freelist *s) { struct pcpu_freelist_head *head; struct pcpu_freelist_node *node; - unsigned long flags; int orig_cpu, cpu; - local_irq_save(flags); orig_cpu = cpu = raw_smp_processor_id(); while (1) { head = per_cpu_ptr(s->freelist, cpu); @@ -89,16 +97,25 @@ struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *s) node = head->first; if (node) { head->first = node->next; - raw_spin_unlock_irqrestore(&head->lock, flags); + raw_spin_unlock(&head->lock); return node; } raw_spin_unlock(&head->lock); cpu = cpumask_next(cpu, cpu_possible_mask); if (cpu >= nr_cpu_ids) cpu = 0; - if (cpu == orig_cpu) { - local_irq_restore(flags); + if (cpu == orig_cpu) return NULL; - } } } + +struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *s) +{ + struct pcpu_freelist_node *ret; + unsigned long flags; + + local_irq_save(flags); + ret = __pcpu_freelist_pop(s); + local_irq_restore(flags); + return ret; +} diff --git a/kernel/bpf/percpu_freelist.h b/kernel/bpf/percpu_freelist.h index 3049aae8ea1e..c3960118e617 100644 --- a/kernel/bpf/percpu_freelist.h +++ b/kernel/bpf/percpu_freelist.h @@ -22,8 +22,12 @@ struct pcpu_freelist_node { struct pcpu_freelist_node *next; }; +/* pcpu_freelist_* do spin_lock_irqsave. */ void pcpu_freelist_push(struct pcpu_freelist *, struct pcpu_freelist_node *); struct pcpu_freelist_node *pcpu_freelist_pop(struct pcpu_freelist *); +/* __pcpu_freelist_* do spin_lock only. caller must disable irqs. */ +void __pcpu_freelist_push(struct pcpu_freelist *, struct pcpu_freelist_node *); +struct pcpu_freelist_node *__pcpu_freelist_pop(struct pcpu_freelist *); void pcpu_freelist_populate(struct pcpu_freelist *s, void *buf, u32 elem_size, u32 nr_elems); int pcpu_freelist_init(struct pcpu_freelist *); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index b155cd17c1bd..ec7c552af76b 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -463,7 +463,7 @@ int map_check_no_btf(const struct bpf_map *map, return -ENOTSUPP; } -static int map_check_btf(const struct bpf_map *map, const struct btf *btf, +static int map_check_btf(struct bpf_map *map, const struct btf *btf, u32 btf_key_id, u32 btf_value_id) { const struct btf_type *key_type, *value_type; @@ -478,6 +478,22 @@ static int map_check_btf(const struct bpf_map *map, const struct btf *btf, if (!value_type || value_size != map->value_size) return -EINVAL; + map->spin_lock_off = btf_find_spin_lock(btf, value_type); + + if (map_value_has_spin_lock(map)) { + if (map->map_type != BPF_MAP_TYPE_HASH && + map->map_type != BPF_MAP_TYPE_ARRAY && + map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE) + return -ENOTSUPP; + if (map->spin_lock_off + sizeof(struct bpf_spin_lock) > + map->value_size) { + WARN_ONCE(1, + "verifier bug spin_lock_off %d value_size %d\n", + map->spin_lock_off, map->value_size); + return -EFAULT; + } + } + if (map->ops->map_check_btf) ret = map->ops->map_check_btf(map, btf, key_type, value_type); @@ -542,6 +558,8 @@ static int map_create(union bpf_attr *attr) map->btf = btf; map->btf_key_type_id = attr->btf_key_type_id; map->btf_value_type_id = attr->btf_value_type_id; + } else { + map->spin_lock_off = -EINVAL; } err = security_bpf_map_alloc(map); @@ -664,7 +682,7 @@ static void *__bpf_copy_key(void __user *ukey, u64 key_size) } /* last field in 'union bpf_attr' used by this command */ -#define BPF_MAP_LOOKUP_ELEM_LAST_FIELD value +#define BPF_MAP_LOOKUP_ELEM_LAST_FIELD flags static int map_lookup_elem(union bpf_attr *attr) { @@ -680,6 +698,9 @@ static int map_lookup_elem(union bpf_attr *attr) if (CHECK_ATTR(BPF_MAP_LOOKUP_ELEM)) return -EINVAL; + if (attr->flags & ~BPF_F_LOCK) + return -EINVAL; + f = fdget(ufd); map = __bpf_map_get(f); if (IS_ERR(map)) @@ -690,6 +711,12 @@ static int map_lookup_elem(union bpf_attr *attr) goto err_put; } + if ((attr->flags & BPF_F_LOCK) && + !map_value_has_spin_lock(map)) { + err = -EINVAL; + goto err_put; + } + key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); @@ -713,8 +740,13 @@ static int map_lookup_elem(union bpf_attr *attr) if (bpf_map_is_dev_bound(map)) { err = bpf_map_offload_lookup_elem(map, key, value); - } else if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || - map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { + goto done; + } + + preempt_disable(); + this_cpu_inc(bpf_prog_active); + if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || + map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH) { err = bpf_percpu_hash_copy(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) { err = bpf_percpu_array_copy(map, key, value); @@ -740,11 +772,20 @@ static int map_lookup_elem(union bpf_attr *attr) err = -ENOENT; } else { err = 0; - memcpy(value, ptr, value_size); + if (attr->flags & BPF_F_LOCK) + /* lock 'ptr' and copy everything but lock */ + copy_map_value_locked(map, value, ptr, true); + else + copy_map_value(map, value, ptr); + /* mask lock, since value wasn't zero inited */ + check_and_init_map_lock(map, value); } rcu_read_unlock(); } + this_cpu_dec(bpf_prog_active); + preempt_enable(); +done: if (err) goto free_value; @@ -800,6 +841,12 @@ static int map_update_elem(union bpf_attr *attr) goto err_put; } + if ((attr->flags & BPF_F_LOCK) && + !map_value_has_spin_lock(map)) { + err = -EINVAL; + goto err_put; + } + key = __bpf_copy_key(ukey, map->key_size); if (IS_ERR(key)) { err = PTR_ERR(key); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 8c1c21cd50b4..1b9496c41383 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -213,6 +213,7 @@ struct bpf_call_arg_meta { s64 msize_smax_value; u64 msize_umax_value; int ptr_id; + int func_id; }; static DEFINE_MUTEX(bpf_verifier_lock); @@ -330,10 +331,19 @@ static bool type_is_pkt_pointer(enum bpf_reg_type type) type == PTR_TO_PACKET_META; } +static bool type_is_sk_pointer(enum bpf_reg_type type) +{ + return type == PTR_TO_SOCKET || + type == PTR_TO_SOCK_COMMON || + type == PTR_TO_TCP_SOCK; +} + static bool reg_type_may_be_null(enum bpf_reg_type type) { return type == PTR_TO_MAP_VALUE_OR_NULL || - type == PTR_TO_SOCKET_OR_NULL; + type == PTR_TO_SOCKET_OR_NULL || + type == PTR_TO_SOCK_COMMON_OR_NULL || + type == PTR_TO_TCP_SOCK_OR_NULL; } static bool type_is_refcounted(enum bpf_reg_type type) @@ -351,6 +361,12 @@ static bool reg_is_refcounted(const struct bpf_reg_state *reg) return type_is_refcounted(reg->type); } +static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg) +{ + return reg->type == PTR_TO_MAP_VALUE && + map_value_has_spin_lock(reg->map_ptr); +} + static bool reg_is_refcounted_or_null(const struct bpf_reg_state *reg) { return type_is_refcounted_or_null(reg->type); @@ -370,6 +386,12 @@ static bool is_release_function(enum bpf_func_id func_id) return func_id == BPF_FUNC_sk_release; } +static bool is_acquire_function(enum bpf_func_id func_id) +{ + return func_id == BPF_FUNC_sk_lookup_tcp || + func_id == BPF_FUNC_sk_lookup_udp; +} + /* string representation of 'enum bpf_reg_type' */ static const char * const reg_type_str[] = { [NOT_INIT] = "?", @@ -385,6 +407,10 @@ static const char * const reg_type_str[] = { [PTR_TO_FLOW_KEYS] = "flow_keys", [PTR_TO_SOCKET] = "sock", [PTR_TO_SOCKET_OR_NULL] = "sock_or_null", + [PTR_TO_SOCK_COMMON] = "sock_common", + [PTR_TO_SOCK_COMMON_OR_NULL] = "sock_common_or_null", + [PTR_TO_TCP_SOCK] = "tcp_sock", + [PTR_TO_TCP_SOCK_OR_NULL] = "tcp_sock_or_null", }; static char slot_type_char[] = { @@ -611,13 +637,10 @@ static int acquire_reference_state(struct bpf_verifier_env *env, int insn_idx) } /* release function corresponding to acquire_reference_state(). Idempotent. */ -static int __release_reference_state(struct bpf_func_state *state, int ptr_id) +static int release_reference_state(struct bpf_func_state *state, int ptr_id) { int i, last_idx; - if (!ptr_id) - return -EFAULT; - last_idx = state->acquired_refs - 1; for (i = 0; i < state->acquired_refs; i++) { if (state->refs[i].id == ptr_id) { @@ -629,21 +652,7 @@ static int __release_reference_state(struct bpf_func_state *state, int ptr_id) return 0; } } - return -EFAULT; -} - -/* variation on the above for cases where we expect that there must be an - * outstanding reference for the specified ptr_id. - */ -static int release_reference_state(struct bpf_verifier_env *env, int ptr_id) -{ - struct bpf_func_state *state = cur_func(env); - int err; - - err = __release_reference_state(state, ptr_id); - if (WARN_ON_ONCE(err != 0)) - verbose(env, "verifier internal error: can't release reference\n"); - return err; + return -EINVAL; } static int transfer_reference_state(struct bpf_func_state *dst, @@ -712,6 +721,7 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state, } dst_state->speculative = src->speculative; dst_state->curframe = src->curframe; + dst_state->active_spin_lock = src->active_spin_lock; for (i = 0; i <= src->curframe; i++) { dst = dst_state->frame[i]; if (!dst) { @@ -1201,6 +1211,10 @@ static bool is_spillable_regtype(enum bpf_reg_type type) case CONST_PTR_TO_MAP: case PTR_TO_SOCKET: case PTR_TO_SOCKET_OR_NULL: + case PTR_TO_SOCK_COMMON: + case PTR_TO_SOCK_COMMON_OR_NULL: + case PTR_TO_TCP_SOCK: + case PTR_TO_TCP_SOCK_OR_NULL: return true; default: return false; @@ -1483,6 +1497,21 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno, if (err) verbose(env, "R%d max value is outside of the array range\n", regno); + + if (map_value_has_spin_lock(reg->map_ptr)) { + u32 lock = reg->map_ptr->spin_lock_off; + + /* if any part of struct bpf_spin_lock can be touched by + * load/store reject this program. + * To check that [x1, x2) overlaps with [y1, y2) + * it is sufficient to check x1 < y2 && y1 < x2. + */ + if (reg->smin_value + off < lock + sizeof(struct bpf_spin_lock) && + lock < reg->umax_value + off + size) { + verbose(env, "bpf_spin_lock cannot be accessed directly by load/store\n"); + return -EACCES; + } + } return err; } @@ -1617,12 +1646,14 @@ static int check_flow_keys_access(struct bpf_verifier_env *env, int off, return 0; } -static int check_sock_access(struct bpf_verifier_env *env, u32 regno, int off, - int size, enum bpf_access_type t) +static int check_sock_access(struct bpf_verifier_env *env, int insn_idx, + u32 regno, int off, int size, + enum bpf_access_type t) { struct bpf_reg_state *regs = cur_regs(env); struct bpf_reg_state *reg = ®s[regno]; - struct bpf_insn_access_aux info; + struct bpf_insn_access_aux info = {}; + bool valid; if (reg->smin_value < 0) { verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", @@ -1630,13 +1661,31 @@ static int check_sock_access(struct bpf_verifier_env *env, u32 regno, int off, return -EACCES; } - if (!bpf_sock_is_valid_access(off, size, t, &info)) { - verbose(env, "invalid bpf_sock access off=%d size=%d\n", - off, size); - return -EACCES; + switch (reg->type) { + case PTR_TO_SOCK_COMMON: + valid = bpf_sock_common_is_valid_access(off, size, t, &info); + break; + case PTR_TO_SOCKET: + valid = bpf_sock_is_valid_access(off, size, t, &info); + break; + case PTR_TO_TCP_SOCK: + valid = bpf_tcp_sock_is_valid_access(off, size, t, &info); + break; + default: + valid = false; } - return 0; + + if (valid) { + env->insn_aux_data[insn_idx].ctx_field_size = + info.ctx_field_size; + return 0; + } + + verbose(env, "R%d invalid %s access off=%d size=%d\n", + regno, reg_type_str[reg->type], off, size); + + return -EACCES; } static bool __is_pointer_value(bool allow_ptr_leaks, @@ -1662,8 +1711,14 @@ static bool is_ctx_reg(struct bpf_verifier_env *env, int regno) { const struct bpf_reg_state *reg = reg_state(env, regno); - return reg->type == PTR_TO_CTX || - reg->type == PTR_TO_SOCKET; + return reg->type == PTR_TO_CTX; +} + +static bool is_sk_reg(struct bpf_verifier_env *env, int regno) +{ + const struct bpf_reg_state *reg = reg_state(env, regno); + + return type_is_sk_pointer(reg->type); } static bool is_pkt_reg(struct bpf_verifier_env *env, int regno) @@ -1774,6 +1829,12 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, case PTR_TO_SOCKET: pointer_desc = "sock "; break; + case PTR_TO_SOCK_COMMON: + pointer_desc = "sock_common "; + break; + case PTR_TO_TCP_SOCK: + pointer_desc = "tcp_sock "; + break; default: break; } @@ -1977,11 +2038,14 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn * PTR_TO_PACKET[_META,_END]. In the latter * case, we know the offset is zero. */ - if (reg_type == SCALAR_VALUE) + if (reg_type == SCALAR_VALUE) { mark_reg_unknown(env, regs, value_regno); - else + } else { mark_reg_known_zero(env, regs, value_regno); + if (reg_type_may_be_null(reg_type)) + regs[value_regno].id = ++env->id_gen; + } regs[value_regno].type = reg_type; } @@ -2027,12 +2091,13 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn err = check_flow_keys_access(env, off, size); if (!err && t == BPF_READ && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); - } else if (reg->type == PTR_TO_SOCKET) { + } else if (type_is_sk_pointer(reg->type)) { if (t == BPF_WRITE) { - verbose(env, "cannot write into socket\n"); + verbose(env, "R%d cannot write into %s\n", + regno, reg_type_str[reg->type]); return -EACCES; } - err = check_sock_access(env, regno, off, size, t); + err = check_sock_access(env, insn_idx, regno, off, size, t); if (!err && value_regno >= 0) mark_reg_unknown(env, regs, value_regno); } else { @@ -2076,7 +2141,8 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins if (is_ctx_reg(env, insn->dst_reg) || is_pkt_reg(env, insn->dst_reg) || - is_flow_key_reg(env, insn->dst_reg)) { + is_flow_key_reg(env, insn->dst_reg) || + is_sk_reg(env, insn->dst_reg)) { verbose(env, "BPF_XADD stores into R%d %s is not allowed\n", insn->dst_reg, reg_type_str[reg_state(env, insn->dst_reg)->type]); @@ -2192,6 +2258,91 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno, } } +/* Implementation details: + * bpf_map_lookup returns PTR_TO_MAP_VALUE_OR_NULL + * Two bpf_map_lookups (even with the same key) will have different reg->id. + * For traditional PTR_TO_MAP_VALUE the verifier clears reg->id after + * value_or_null->value transition, since the verifier only cares about + * the range of access to valid map value pointer and doesn't care about actual + * address of the map element. + * For maps with 'struct bpf_spin_lock' inside map value the verifier keeps + * reg->id > 0 after value_or_null->value transition. By doing so + * two bpf_map_lookups will be considered two different pointers that + * point to different bpf_spin_locks. + * The verifier allows taking only one bpf_spin_lock at a time to avoid + * dead-locks. + * Since only one bpf_spin_lock is allowed the checks are simpler than + * reg_is_refcounted() logic. The verifier needs to remember only + * one spin_lock instead of array of acquired_refs. + * cur_state->active_spin_lock remembers which map value element got locked + * and clears it after bpf_spin_unlock. + */ +static int process_spin_lock(struct bpf_verifier_env *env, int regno, + bool is_lock) +{ + struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; + struct bpf_verifier_state *cur = env->cur_state; + bool is_const = tnum_is_const(reg->var_off); + struct bpf_map *map = reg->map_ptr; + u64 val = reg->var_off.value; + + if (reg->type != PTR_TO_MAP_VALUE) { + verbose(env, "R%d is not a pointer to map_value\n", regno); + return -EINVAL; + } + if (!is_const) { + verbose(env, + "R%d doesn't have constant offset. bpf_spin_lock has to be at the constant offset\n", + regno); + return -EINVAL; + } + if (!map->btf) { + verbose(env, + "map '%s' has to have BTF in order to use bpf_spin_lock\n", + map->name); + return -EINVAL; + } + if (!map_value_has_spin_lock(map)) { + if (map->spin_lock_off == -E2BIG) + verbose(env, + "map '%s' has more than one 'struct bpf_spin_lock'\n", + map->name); + else if (map->spin_lock_off == -ENOENT) + verbose(env, + "map '%s' doesn't have 'struct bpf_spin_lock'\n", + map->name); + else + verbose(env, + "map '%s' is not a struct type or bpf_spin_lock is mangled\n", + map->name); + return -EINVAL; + } + if (map->spin_lock_off != val + reg->off) { + verbose(env, "off %lld doesn't point to 'struct bpf_spin_lock'\n", + val + reg->off); + return -EINVAL; + } + if (is_lock) { + if (cur->active_spin_lock) { + verbose(env, + "Locking two bpf_spin_locks are not allowed\n"); + return -EINVAL; + } + cur->active_spin_lock = reg->id; + } else { + if (!cur->active_spin_lock) { + verbose(env, "bpf_spin_unlock without taking a lock\n"); + return -EINVAL; + } + if (cur->active_spin_lock != reg->id) { + verbose(env, "bpf_spin_unlock of different lock\n"); + return -EINVAL; + } + cur->active_spin_lock = 0; + } + return 0; +} + static bool arg_type_is_mem_ptr(enum bpf_arg_type type) { return type == ARG_PTR_TO_MEM || @@ -2258,6 +2409,11 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, err = check_ctx_reg(env, reg, regno); if (err < 0) return err; + } else if (arg_type == ARG_PTR_TO_SOCK_COMMON) { + expected_type = PTR_TO_SOCK_COMMON; + /* Any sk pointer can be ARG_PTR_TO_SOCK_COMMON */ + if (!type_is_sk_pointer(type)) + goto err_type; } else if (arg_type == ARG_PTR_TO_SOCKET) { expected_type = PTR_TO_SOCKET; if (type != expected_type) @@ -2268,6 +2424,17 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, return -EFAULT; } meta->ptr_id = reg->id; + } else if (arg_type == ARG_PTR_TO_SPIN_LOCK) { + if (meta->func_id == BPF_FUNC_spin_lock) { + if (process_spin_lock(env, regno, true)) + return -EACCES; + } else if (meta->func_id == BPF_FUNC_spin_unlock) { + if (process_spin_lock(env, regno, false)) + return -EACCES; + } else { + verbose(env, "verifier internal error\n"); + return -EFAULT; + } } else if (arg_type_is_mem_ptr(arg_type)) { expected_type = PTR_TO_STACK; /* One exception here. In case function allows for NULL to be @@ -2661,7 +2828,7 @@ static int release_reference(struct bpf_verifier_env *env, for (i = 0; i <= vstate->curframe; i++) release_reg_references(env, vstate->frame[i], meta->ptr_id); - return release_reference_state(env, meta->ptr_id); + return release_reference_state(cur_func(env), meta->ptr_id); } static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, @@ -2887,6 +3054,7 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn return err; } + meta.func_id = func_id; /* check args */ err = check_func_arg(env, BPF_REG_1, fn->arg1_type, &meta); if (err) @@ -2926,8 +3094,11 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn } } else if (is_release_function(func_id)) { err = release_reference(env, &meta); - if (err) + if (err) { + verbose(env, "func %s#%d reference has not been acquired before\n", + func_id_name(func_id), func_id); return err; + } } regs = cur_regs(env); @@ -2969,17 +3140,30 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn regs[BPF_REG_0].map_ptr = meta.map_ptr; if (fn->ret_type == RET_PTR_TO_MAP_VALUE) { regs[BPF_REG_0].type = PTR_TO_MAP_VALUE; + if (map_value_has_spin_lock(meta.map_ptr)) + regs[BPF_REG_0].id = ++env->id_gen; } else { regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL; regs[BPF_REG_0].id = ++env->id_gen; } } else if (fn->ret_type == RET_PTR_TO_SOCKET_OR_NULL) { - int id = acquire_reference_state(env, insn_idx); - if (id < 0) - return id; mark_reg_known_zero(env, regs, BPF_REG_0); regs[BPF_REG_0].type = PTR_TO_SOCKET_OR_NULL; - regs[BPF_REG_0].id = id; + if (is_acquire_function(func_id)) { + int id = acquire_reference_state(env, insn_idx); + + if (id < 0) + return id; + /* For release_reference() */ + regs[BPF_REG_0].id = id; + } else { + /* For mark_ptr_or_null_reg() */ + regs[BPF_REG_0].id = ++env->id_gen; + } + } else if (fn->ret_type == RET_PTR_TO_TCP_SOCK_OR_NULL) { + mark_reg_known_zero(env, regs, BPF_REG_0); + regs[BPF_REG_0].type = PTR_TO_TCP_SOCK_OR_NULL; + regs[BPF_REG_0].id = ++env->id_gen; } else { verbose(env, "unknown return type %d of func %s#%d\n", fn->ret_type, func_id_name(func_id), func_id); @@ -3239,6 +3423,10 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, case PTR_TO_PACKET_END: case PTR_TO_SOCKET: case PTR_TO_SOCKET_OR_NULL: + case PTR_TO_SOCK_COMMON: + case PTR_TO_SOCK_COMMON_OR_NULL: + case PTR_TO_TCP_SOCK: + case PTR_TO_TCP_SOCK_OR_NULL: verbose(env, "R%d pointer arithmetic on %s prohibited\n", dst, reg_type_str[ptr_reg->type]); return -EACCES; @@ -4472,8 +4660,13 @@ static void mark_ptr_or_null_reg(struct bpf_func_state *state, } } else if (reg->type == PTR_TO_SOCKET_OR_NULL) { reg->type = PTR_TO_SOCKET; + } else if (reg->type == PTR_TO_SOCK_COMMON_OR_NULL) { + reg->type = PTR_TO_SOCK_COMMON; + } else if (reg->type == PTR_TO_TCP_SOCK_OR_NULL) { + reg->type = PTR_TO_TCP_SOCK; } - if (is_null || !reg_is_refcounted(reg)) { + if (is_null || !(reg_is_refcounted(reg) || + reg_may_point_to_spin_lock(reg))) { /* We don't need id from this point onwards anymore, * thus we should better reset it, so that state * pruning has chances to take effect. @@ -4495,7 +4688,7 @@ static void mark_ptr_or_null_regs(struct bpf_verifier_state *vstate, u32 regno, int i, j; if (reg_is_refcounted_or_null(®s[regno]) && is_null) - __release_reference_state(state, id); + release_reference_state(state, id); for (i = 0; i < MAX_BPF_REG; i++) mark_ptr_or_null_reg(state, ®s[i], id, is_null); @@ -4871,6 +5064,11 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return err; } + if (env->cur_state->active_spin_lock) { + verbose(env, "BPF_LD_[ABS|IND] cannot be used inside bpf_spin_lock-ed region\n"); + return -EINVAL; + } + if (regs[BPF_REG_6].type != PTR_TO_CTX) { verbose(env, "at the time of BPF_LD_ABS|IND R6 != pointer to skb\n"); @@ -5607,8 +5805,11 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, case PTR_TO_MAP_VALUE: /* If the new min/max/var_off satisfy the old ones and * everything else matches, we are OK. - * We don't care about the 'id' value, because nothing - * uses it for PTR_TO_MAP_VALUE (only for ..._OR_NULL) + * 'id' is not compared, since it's only used for maps with + * bpf_spin_lock inside map element and in such cases if + * the rest of the prog is valid for one map element then + * it's valid for all map elements regardless of the key + * used in bpf_map_lookup() */ return memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)) == 0 && range_within(rold, rcur) && @@ -5656,6 +5857,10 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, case PTR_TO_FLOW_KEYS: case PTR_TO_SOCKET: case PTR_TO_SOCKET_OR_NULL: + case PTR_TO_SOCK_COMMON: + case PTR_TO_SOCK_COMMON_OR_NULL: + case PTR_TO_TCP_SOCK: + case PTR_TO_TCP_SOCK_OR_NULL: /* Only valid matches are exact, which memcmp() above * would have accepted */ @@ -5811,6 +6016,9 @@ static bool states_equal(struct bpf_verifier_env *env, if (old->speculative && !cur->speculative) return false; + if (old->active_spin_lock != cur->active_spin_lock) + return false; + /* for states to be equal callsites have to be the same * and all frame states need to be equivalent */ @@ -5973,6 +6181,10 @@ static bool reg_type_mismatch_ok(enum bpf_reg_type type) case PTR_TO_CTX: case PTR_TO_SOCKET: case PTR_TO_SOCKET_OR_NULL: + case PTR_TO_SOCK_COMMON: + case PTR_TO_SOCK_COMMON_OR_NULL: + case PTR_TO_TCP_SOCK: + case PTR_TO_TCP_SOCK_OR_NULL: return false; default: return true; @@ -6229,6 +6441,12 @@ static int do_check(struct bpf_verifier_env *env) return -EINVAL; } + if (env->cur_state->active_spin_lock && + (insn->src_reg == BPF_PSEUDO_CALL || + insn->imm != BPF_FUNC_spin_unlock)) { + verbose(env, "function calls are not allowed while holding a lock\n"); + return -EINVAL; + } if (insn->src_reg == BPF_PSEUDO_CALL) err = check_func_call(env, insn, &env->insn_idx); else @@ -6259,6 +6477,11 @@ static int do_check(struct bpf_verifier_env *env) return -EINVAL; } + if (env->cur_state->active_spin_lock) { + verbose(env, "bpf_spin_unlock is missing\n"); + return -EINVAL; + } + if (state->curframe) { /* exit from nested function */ env->prev_insn_idx = env->insn_idx; @@ -6356,6 +6579,19 @@ static int check_map_prealloc(struct bpf_map *map) !(map->map_flags & BPF_F_NO_PREALLOC); } +static bool is_tracing_prog_type(enum bpf_prog_type type) +{ + switch (type) { + case BPF_PROG_TYPE_KPROBE: + case BPF_PROG_TYPE_TRACEPOINT: + case BPF_PROG_TYPE_PERF_EVENT: + case BPF_PROG_TYPE_RAW_TRACEPOINT: + return true; + default: + return false; + } +} + static int check_map_prog_compatibility(struct bpf_verifier_env *env, struct bpf_map *map, struct bpf_prog *prog) @@ -6378,6 +6614,13 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, } } + if ((is_tracing_prog_type(prog->type) || + prog->type == BPF_PROG_TYPE_SOCKET_FILTER) && + map_value_has_spin_lock(map)) { + verbose(env, "tracing progs cannot use bpf_spin_lock yet\n"); + return -EINVAL; + } + if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) && !bpf_offload_prog_map_match(prog, map)) { verbose(env, "offload device mismatch between prog and map\n"); @@ -6944,8 +7187,12 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) convert_ctx_access = ops->convert_ctx_access; break; case PTR_TO_SOCKET: + case PTR_TO_SOCK_COMMON: convert_ctx_access = bpf_sock_convert_ctx_access; break; + case PTR_TO_TCP_SOCK: + convert_ctx_access = bpf_tcp_sock_convert_ctx_access; + break; default: continue; } diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index f31bd61c9466..9f617605dacb 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -5996,7 +5996,7 @@ int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, int ret; mutex_lock(&cgroup_mutex); - ret = __cgroup_bpf_detach(cgrp, prog, type, flags); + ret = __cgroup_bpf_detach(cgrp, prog, type); mutex_unlock(&cgroup_mutex); return ret; } diff --git a/kernel/cpu.c b/kernel/cpu.c index 91d5c38eb7e5..d1c6d152da89 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -376,9 +376,6 @@ void __weak arch_smt_update(void) { } #ifdef CONFIG_HOTPLUG_SMT enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED; -EXPORT_SYMBOL_GPL(cpu_smt_control); - -static bool cpu_smt_available __read_mostly; void __init cpu_smt_disable(bool force) { @@ -397,25 +394,11 @@ void __init cpu_smt_disable(bool force) /* * The decision whether SMT is supported can only be done after the full - * CPU identification. Called from architecture code before non boot CPUs - * are brought up. - */ -void __init cpu_smt_check_topology_early(void) -{ - if (!topology_smt_supported()) - cpu_smt_control = CPU_SMT_NOT_SUPPORTED; -} - -/* - * If SMT was disabled by BIOS, detect it here, after the CPUs have been - * brought online. This ensures the smt/l1tf sysfs entries are consistent - * with reality. cpu_smt_available is set to true during the bringup of non - * boot CPUs when a SMT sibling is detected. Note, this may overwrite - * cpu_smt_control's previous setting. + * CPU identification. Called from architecture code. */ void __init cpu_smt_check_topology(void) { - if (!cpu_smt_available) + if (!topology_smt_supported()) cpu_smt_control = CPU_SMT_NOT_SUPPORTED; } @@ -428,18 +411,10 @@ early_param("nosmt", smt_cmdline_disable); static inline bool cpu_smt_allowed(unsigned int cpu) { - if (topology_is_primary_thread(cpu)) + if (cpu_smt_control == CPU_SMT_ENABLED) return true; - /* - * If the CPU is not a 'primary' thread and the booted_once bit is - * set then the processor has SMT support. Store this information - * for the late check of SMT support in cpu_smt_check_topology(). - */ - if (per_cpu(cpuhp_state, cpu).booted_once) - cpu_smt_available = true; - - if (cpu_smt_control == CPU_SMT_ENABLED) + if (topology_is_primary_thread(cpu)) return true; /* @@ -2090,10 +2065,8 @@ static int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) */ cpuhp_offline_cpu_device(cpu); } - if (!ret) { + if (!ret) cpu_smt_control = ctrlval; - arch_smt_update(); - } cpu_maps_update_done(); return ret; } @@ -2104,7 +2077,6 @@ static int cpuhp_smt_enable(void) cpu_maps_update_begin(); cpu_smt_control = CPU_SMT_ENABLED; - arch_smt_update(); for_each_present_cpu(cpu) { /* Skip online CPUs and CPUs on offline nodes */ if (cpu_online(cpu) || !node_online(cpu_to_node(cpu))) diff --git a/kernel/events/core.c b/kernel/events/core.c index 3cd13a30f732..e5ede6918050 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -436,18 +436,18 @@ int perf_proc_update_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - - if (ret || !write) - return ret; - + int ret; + int perf_cpu = sysctl_perf_cpu_time_max_percent; /* * If throttling is disabled don't allow the write: */ - if (sysctl_perf_cpu_time_max_percent == 100 || - sysctl_perf_cpu_time_max_percent == 0) + if (write && (perf_cpu == 100 || perf_cpu == 0)) return -EINVAL; + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + if (ret || !write) + return ret; + max_samples_per_tick = DIV_ROUND_UP(sysctl_perf_event_sample_rate, HZ); perf_sample_period_ns = NSEC_PER_SEC / sysctl_perf_event_sample_rate; update_perf_cpu_limits(); diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 4a9937076331..309ef5a64af5 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -734,6 +734,9 @@ struct ring_buffer *rb_alloc(int nr_pages, long watermark, int cpu, int flags) size = sizeof(struct ring_buffer); size += nr_pages * sizeof(void *); + if (order_base_2(size) >= MAX_ORDER) + goto fail; + rb = kzalloc(size, GFP_KERNEL); if (!rb) goto fail; diff --git a/kernel/exit.c b/kernel/exit.c index 284f2fe9a293..2639a30a8aa5 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -307,7 +307,7 @@ void rcuwait_wake_up(struct rcuwait *w) * MB (A) MB (B) * [L] cond [L] tsk */ - smp_rmb(); /* (B) */ + smp_mb(); /* (B) */ /* * Avoid using task_rcu_dereference() magic as long as we are careful, @@ -558,12 +558,14 @@ static struct task_struct *find_alive_thread(struct task_struct *p) return NULL; } -static struct task_struct *find_child_reaper(struct task_struct *father) +static struct task_struct *find_child_reaper(struct task_struct *father, + struct list_head *dead) __releases(&tasklist_lock) __acquires(&tasklist_lock) { struct pid_namespace *pid_ns = task_active_pid_ns(father); struct task_struct *reaper = pid_ns->child_reaper; + struct task_struct *p, *n; if (likely(reaper != father)) return reaper; @@ -579,6 +581,12 @@ static struct task_struct *find_child_reaper(struct task_struct *father) panic("Attempted to kill init! exitcode=0x%08x\n", father->signal->group_exit_code ?: father->exit_code); } + + list_for_each_entry_safe(p, n, dead, ptrace_entry) { + list_del_init(&p->ptrace_entry); + release_task(p); + } + zap_pid_ns_processes(pid_ns); write_lock_irq(&tasklist_lock); @@ -668,7 +676,7 @@ static void forget_original_parent(struct task_struct *father, exit_ptrace(father, dead); /* Can drop and reacquire tasklist_lock */ - reaper = find_child_reaper(father); + reaper = find_child_reaper(father, dead); if (list_empty(&father->children)) return; diff --git a/kernel/futex.c b/kernel/futex.c index be3bff2315ff..a0514e01c3eb 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1452,11 +1452,7 @@ static void mark_wake_futex(struct wake_q_head *wake_q, struct futex_q *q) if (WARN(q->pi_state || q->rt_waiter, "refusing to wake PI futex\n")) return; - /* - * Queue the task for later wakeup for after we've released - * the hb->lock. wake_q_add() grabs reference to p. - */ - wake_q_add(wake_q, p); + get_task_struct(p); __unqueue_futex(q); /* * The waiting task can free the futex_q as soon as q->lock_ptr = NULL @@ -1466,6 +1462,13 @@ static void mark_wake_futex(struct wake_q_head *wake_q, struct futex_q *q) * plist_del in __unqueue_futex(). */ smp_store_release(&q->lock_ptr, NULL); + + /* + * Queue the task for later wakeup for after we've released + * the hb->lock. wake_q_add() grabs reference to p. + */ + wake_q_add(wake_q, p); + put_task_struct(p); } /* @@ -2218,11 +2221,11 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q) * decrement the counter at queue_unlock() when some error has * occurred and we don't end up adding the task to the list. */ - hb_waiters_inc(hb); + hb_waiters_inc(hb); /* implies smp_mb(); (A) */ q->lock_ptr = &hb->lock; - spin_lock(&hb->lock); /* implies smp_mb(); (A) */ + spin_lock(&hb->lock); return hb; } @@ -2858,35 +2861,39 @@ retry_private: * and BUG when futex_unlock_pi() interleaves with this. * * Therefore acquire wait_lock while holding hb->lock, but drop the - * latter before calling rt_mutex_start_proxy_lock(). This still fully - * serializes against futex_unlock_pi() as that does the exact same - * lock handoff sequence. + * latter before calling __rt_mutex_start_proxy_lock(). This + * interleaves with futex_unlock_pi() -- which does a similar lock + * handoff -- such that the latter can observe the futex_q::pi_state + * before __rt_mutex_start_proxy_lock() is done. */ raw_spin_lock_irq(&q.pi_state->pi_mutex.wait_lock); spin_unlock(q.lock_ptr); + /* + * __rt_mutex_start_proxy_lock() unconditionally enqueues the @rt_waiter + * such that futex_unlock_pi() is guaranteed to observe the waiter when + * it sees the futex_q::pi_state. + */ ret = __rt_mutex_start_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter, current); raw_spin_unlock_irq(&q.pi_state->pi_mutex.wait_lock); if (ret) { if (ret == 1) ret = 0; - - spin_lock(q.lock_ptr); - goto no_block; + goto cleanup; } - if (unlikely(to)) hrtimer_start_expires(&to->timer, HRTIMER_MODE_ABS); ret = rt_mutex_wait_proxy_lock(&q.pi_state->pi_mutex, to, &rt_waiter); +cleanup: spin_lock(q.lock_ptr); /* - * If we failed to acquire the lock (signal/timeout), we must + * If we failed to acquire the lock (deadlock/signal/timeout), we must * first acquire the hb->lock before removing the lock from the - * rt_mutex waitqueue, such that we can keep the hb and rt_mutex - * wait lists consistent. + * rt_mutex waitqueue, such that we can keep the hb and rt_mutex wait + * lists consistent. * * In particular; it is important that futex_unlock_pi() can not * observe this inconsistency. @@ -3010,6 +3017,10 @@ retry: * there is no point where we hold neither; and therefore * wake_futex_pi() must observe a state consistent with what we * observed. + * + * In particular; this forces __rt_mutex_start_proxy() to + * complete such that we're guaranteed to observe the + * rt_waiter. Also see the WARN in wake_futex_pi(). */ raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); spin_unlock(&hb->lock); diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index ee062b7939d3..ef8ad36cadcf 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -457,7 +457,7 @@ static int alloc_descs(unsigned int start, unsigned int cnt, int node, /* Validate affinity mask(s) */ if (affinity) { - for (i = 0; i < cnt; i++, i++) { + for (i = 0; i < cnt; i++) { if (cpumask_empty(&affinity[i].mask)) return -EINVAL; } diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index a4888ce4667a..84b54a17b95d 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -393,6 +393,9 @@ int irq_setup_affinity(struct irq_desc *desc) } cpumask_and(&mask, cpu_online_mask, set); + if (cpumask_empty(&mask)) + cpumask_copy(&mask, cpu_online_mask); + if (node != NUMA_NO_NODE) { const struct cpumask *nodemask = cpumask_of_node(node); diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 581edcc63c26..978d63a8261c 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1726,12 +1726,33 @@ void rt_mutex_proxy_unlock(struct rt_mutex *lock, rt_mutex_set_owner(lock, NULL); } +/** + * __rt_mutex_start_proxy_lock() - Start lock acquisition for another task + * @lock: the rt_mutex to take + * @waiter: the pre-initialized rt_mutex_waiter + * @task: the task to prepare + * + * Starts the rt_mutex acquire; it enqueues the @waiter and does deadlock + * detection. It does not wait, see rt_mutex_wait_proxy_lock() for that. + * + * NOTE: does _NOT_ remove the @waiter on failure; must either call + * rt_mutex_wait_proxy_lock() or rt_mutex_cleanup_proxy_lock() after this. + * + * Returns: + * 0 - task blocked on lock + * 1 - acquired the lock for task, caller should wake it up + * <0 - error + * + * Special API call for PI-futex support. + */ int __rt_mutex_start_proxy_lock(struct rt_mutex *lock, struct rt_mutex_waiter *waiter, struct task_struct *task) { int ret; + lockdep_assert_held(&lock->wait_lock); + if (try_to_take_rt_mutex(lock, task, NULL)) return 1; @@ -1749,9 +1770,6 @@ int __rt_mutex_start_proxy_lock(struct rt_mutex *lock, ret = 0; } - if (unlikely(ret)) - remove_waiter(lock, waiter); - debug_rt_mutex_print_deadlock(waiter); return ret; @@ -1763,12 +1781,18 @@ int __rt_mutex_start_proxy_lock(struct rt_mutex *lock, * @waiter: the pre-initialized rt_mutex_waiter * @task: the task to prepare * + * Starts the rt_mutex acquire; it enqueues the @waiter and does deadlock + * detection. It does not wait, see rt_mutex_wait_proxy_lock() for that. + * + * NOTE: unlike __rt_mutex_start_proxy_lock this _DOES_ remove the @waiter + * on failure. + * * Returns: * 0 - task blocked on lock * 1 - acquired the lock for task, caller should wake it up * <0 - error * - * Special API call for FUTEX_REQUEUE_PI support. + * Special API call for PI-futex support. */ int rt_mutex_start_proxy_lock(struct rt_mutex *lock, struct rt_mutex_waiter *waiter, @@ -1778,6 +1802,8 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock, raw_spin_lock_irq(&lock->wait_lock); ret = __rt_mutex_start_proxy_lock(lock, waiter, task); + if (unlikely(ret)) + remove_waiter(lock, waiter); raw_spin_unlock_irq(&lock->wait_lock); return ret; @@ -1845,7 +1871,8 @@ int rt_mutex_wait_proxy_lock(struct rt_mutex *lock, * @lock: the rt_mutex we were woken on * @waiter: the pre-initialized rt_mutex_waiter * - * Attempt to clean up after a failed rt_mutex_wait_proxy_lock(). + * Attempt to clean up after a failed __rt_mutex_start_proxy_lock() or + * rt_mutex_wait_proxy_lock(). * * Unless we acquired the lock; we're still enqueued on the wait-list and can * in fact still be granted ownership until we're removed. Therefore we can diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index 09b180063ee1..50d9af615dc4 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -198,15 +198,22 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem, woken++; tsk = waiter->task; - wake_q_add(wake_q, tsk); + get_task_struct(tsk); list_del(&waiter->list); /* - * Ensure that the last operation is setting the reader + * Ensure calling get_task_struct() before setting the reader * waiter to nil such that rwsem_down_read_failed() cannot * race with do_exit() by always holding a reference count * to the task to wakeup. */ smp_store_release(&waiter->task, NULL); + /* + * Ensure issuing the wakeup (either by us or someone else) + * after setting the reader waiter to nil. + */ + wake_q_add(wake_q, tsk); + /* wake_q_add() already take the task ref */ + put_task_struct(tsk); } adjustment = woken * RWSEM_ACTIVE_READ_BIAS - adjustment; diff --git a/kernel/relay.c b/kernel/relay.c index 04f248644e06..9e0f52375487 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -428,6 +428,8 @@ static struct dentry *relay_create_buf_file(struct rchan *chan, dentry = chan->cb->create_buf_file(tmpname, chan->parent, S_IRUSR, buf, &chan->is_global); + if (IS_ERR(dentry)) + dentry = NULL; kfree(tmpname); @@ -461,7 +463,7 @@ static struct rchan_buf *relay_open_buf(struct rchan *chan, unsigned int cpu) dentry = chan->cb->create_buf_file(NULL, NULL, S_IRUSR, buf, &chan->is_global); - if (WARN_ON(dentry)) + if (IS_ERR_OR_NULL(dentry)) goto free_buf; } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index a674c7db2f29..d8d76a65cfdd 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -396,6 +396,18 @@ static bool set_nr_if_polling(struct task_struct *p) #endif #endif +/** + * wake_q_add() - queue a wakeup for 'later' waking. + * @head: the wake_q_head to add @task to + * @task: the task to queue for 'later' wakeup + * + * Queue a task for later wakeup, most likely by the wake_up_q() call in the + * same context, _HOWEVER_ this is not guaranteed, the wakeup can come + * instantly. + * + * This function must be used as-if it were wake_up_process(); IOW the task + * must be ready to be woken at this location. + */ void wake_q_add(struct wake_q_head *head, struct task_struct *task) { struct wake_q_node *node = &task->wake_q; @@ -405,10 +417,11 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task) * its already queued (either by us or someone else) and will get the * wakeup due to that. * - * This cmpxchg() executes a full barrier, which pairs with the full - * barrier executed by the wakeup in wake_up_q(). + * In order to ensure that a pending wakeup will observe our pending + * state, even in the failed case, an explicit smp_mb() must be used. */ - if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL)) + smp_mb__before_atomic(); + if (cmpxchg_relaxed(&node->next, NULL, WAKE_Q_TAIL)) return; get_task_struct(task); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 50aa2aba69bd..310d0637fe4b 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5980,6 +5980,7 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p #ifdef CONFIG_SCHED_SMT DEFINE_STATIC_KEY_FALSE(sched_smt_present); +EXPORT_SYMBOL_GPL(sched_smt_present); static inline void set_idle_cores(int cpu, int val) { diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index fe24de3fbc93..c3484785b179 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -124,6 +124,7 @@ * sampling of the aggregate task states would be. */ +#include "../workqueue_internal.h" #include <linux/sched/loadavg.h> #include <linux/seq_file.h> #include <linux/proc_fs.h> @@ -480,9 +481,6 @@ static void psi_group_change(struct psi_group *group, int cpu, groupc->tasks[t]++; write_seqcount_end(&groupc->seq); - - if (!delayed_work_pending(&group->clock_work)) - schedule_delayed_work(&group->clock_work, PSI_FREQ); } static struct psi_group *iterate_groups(struct task_struct *task, void **iter) @@ -513,6 +511,7 @@ void psi_task_change(struct task_struct *task, int clear, int set) { int cpu = task_cpu(task); struct psi_group *group; + bool wake_clock = true; void *iter = NULL; if (!task->pid) @@ -530,8 +529,22 @@ void psi_task_change(struct task_struct *task, int clear, int set) task->psi_flags &= ~clear; task->psi_flags |= set; - while ((group = iterate_groups(task, &iter))) + /* + * Periodic aggregation shuts off if there is a period of no + * task changes, so we wake it back up if necessary. However, + * don't do this if the task change is the aggregation worker + * itself going to sleep, or we'll ping-pong forever. + */ + if (unlikely((clear & TSK_RUNNING) && + (task->flags & PF_WQ_WORKER) && + wq_worker_last_func(task) == psi_update_work)) + wake_clock = false; + + while ((group = iterate_groups(task, &iter))) { psi_group_change(group, cpu, clear, set); + if (wake_clock && !delayed_work_pending(&group->clock_work)) + schedule_delayed_work(&group->clock_work, PSI_FREQ); + } } void psi_memstall_tick(struct task_struct *task, int cpu) diff --git a/kernel/signal.c b/kernel/signal.c index e1d7ad8e6ab1..57b7771e20d7 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -688,6 +688,48 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, kernel_siginfo_t *in } EXPORT_SYMBOL_GPL(dequeue_signal); +static int dequeue_synchronous_signal(kernel_siginfo_t *info) +{ + struct task_struct *tsk = current; + struct sigpending *pending = &tsk->pending; + struct sigqueue *q, *sync = NULL; + + /* + * Might a synchronous signal be in the queue? + */ + if (!((pending->signal.sig[0] & ~tsk->blocked.sig[0]) & SYNCHRONOUS_MASK)) + return 0; + + /* + * Return the first synchronous signal in the queue. + */ + list_for_each_entry(q, &pending->list, list) { + /* Synchronous signals have a postive si_code */ + if ((q->info.si_code > SI_USER) && + (sigmask(q->info.si_signo) & SYNCHRONOUS_MASK)) { + sync = q; + goto next; + } + } + return 0; +next: + /* + * Check if there is another siginfo for the same signal. + */ + list_for_each_entry_continue(q, &pending->list, list) { + if (q->info.si_signo == sync->info.si_signo) + goto still_pending; + } + + sigdelset(&pending->signal, sync->info.si_signo); + recalc_sigpending(); +still_pending: + list_del_init(&sync->list); + copy_siginfo(info, &sync->info); + __sigqueue_free(sync); + return info->si_signo; +} + /* * Tell a process that it has a new active signal.. * @@ -1057,10 +1099,9 @@ static int __send_signal(int sig, struct kernel_siginfo *info, struct task_struc result = TRACE_SIGNAL_DELIVERED; /* - * Skip useless siginfo allocation for SIGKILL SIGSTOP, - * and kernel threads. + * Skip useless siginfo allocation for SIGKILL and kernel threads. */ - if (sig_kernel_only(sig) || (t->flags & PF_KTHREAD)) + if ((sig == SIGKILL) || (t->flags & PF_KTHREAD)) goto out_set; /* @@ -2394,6 +2435,14 @@ relock: goto relock; } + /* Has this task already been marked for death? */ + if (signal_group_exit(signal)) { + ksig->info.si_signo = signr = SIGKILL; + sigdelset(¤t->pending.signal, SIGKILL); + recalc_sigpending(); + goto fatal; + } + for (;;) { struct k_sigaction *ka; @@ -2407,7 +2456,15 @@ relock: goto relock; } - signr = dequeue_signal(current, ¤t->blocked, &ksig->info); + /* + * Signals generated by the execution of an instruction + * need to be delivered before any other pending signals + * so that the instruction pointer in the signal stack + * frame points to the faulting instruction. + */ + signr = dequeue_synchronous_signal(&ksig->info); + if (!signr) + signr = dequeue_signal(current, ¤t->blocked, &ksig->info); if (!signr) break; /* will return 0 */ @@ -2489,6 +2546,7 @@ relock: continue; } + fatal: spin_unlock_irq(&sighand->siglock); /* diff --git a/kernel/smp.c b/kernel/smp.c index 163c451af42e..f4cf1b0bb3b8 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -584,8 +584,6 @@ void __init smp_init(void) num_nodes, (num_nodes > 1 ? "s" : ""), num_cpus, (num_cpus > 1 ? "s" : "")); - /* Final decision about SMT support */ - cpu_smt_check_topology(); /* Any cleanup work */ smp_cpus_done(setup_max_cpus); } diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 8f0644af40be..80f955210861 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -685,6 +685,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, * set up the signal and overrun bookkeeping. */ timer->it.cpu.incr = timespec64_to_ns(&new->it_interval); + timer->it_interval = ns_to_ktime(timer->it.cpu.incr); /* * This acts as a modification timestamp for the timer, diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 8b068adb9da1..f1a86a0d881d 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1204,22 +1204,12 @@ static int __bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog * int bpf_probe_register(struct bpf_raw_event_map *btp, struct bpf_prog *prog) { - int err; - - mutex_lock(&bpf_event_mutex); - err = __bpf_probe_register(btp, prog); - mutex_unlock(&bpf_event_mutex); - return err; + return __bpf_probe_register(btp, prog); } int bpf_probe_unregister(struct bpf_raw_event_map *btp, struct bpf_prog *prog) { - int err; - - mutex_lock(&bpf_event_mutex); - err = tracepoint_probe_unregister(btp->tp, (void *)btp->bpf_func, prog); - mutex_unlock(&bpf_event_mutex); - return err; + return tracepoint_probe_unregister(btp->tp, (void *)btp->bpf_func, prog); } int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, diff --git a/kernel/trace/trace_probe_tmpl.h b/kernel/trace/trace_probe_tmpl.h index 5c56afc17cf8..4737bb8c07a3 100644 --- a/kernel/trace/trace_probe_tmpl.h +++ b/kernel/trace/trace_probe_tmpl.h @@ -180,10 +180,12 @@ store_trace_args(void *data, struct trace_probe *tp, struct pt_regs *regs, if (unlikely(arg->dynamic)) *dl = make_data_loc(maxlen, dyndata - base); ret = process_fetch_insn(arg->code, regs, dl, base); - if (unlikely(ret < 0 && arg->dynamic)) + if (unlikely(ret < 0 && arg->dynamic)) { *dl = make_data_loc(0, dyndata - base); - else + } else { dyndata += ret; + maxlen -= ret; + } } } diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index e335576b9411..9bde07c06362 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -5,7 +5,7 @@ * Copyright (C) IBM Corporation, 2010-2012 * Author: Srikar Dronamraju <srikar@linux.vnet.ibm.com> */ -#define pr_fmt(fmt) "trace_kprobe: " fmt +#define pr_fmt(fmt) "trace_uprobe: " fmt #include <linux/ctype.h> #include <linux/module.h> @@ -160,6 +160,13 @@ fetch_store_string(unsigned long addr, void *dest, void *base) if (ret >= 0) { if (ret == maxlen) dst[ret - 1] = '\0'; + else + /* + * Include the terminating null byte. In this case it + * was copied by strncpy_from_user but not accounted + * for in ret. + */ + ret++; *(u32 *)dest = make_data_loc(ret, (void *)dst - base); } diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 392be4b252f6..fc5d23d752a5 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -910,6 +910,26 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task) } /** + * wq_worker_last_func - retrieve worker's last work function + * + * Determine the last function a worker executed. This is called from + * the scheduler to get a worker's last known identity. + * + * CONTEXT: + * spin_lock_irq(rq->lock) + * + * Return: + * The last work function %current executed as a worker, NULL if it + * hasn't executed any work yet. + */ +work_func_t wq_worker_last_func(struct task_struct *task) +{ + struct worker *worker = kthread_data(task); + + return worker->last_func; +} + +/** * worker_set_flags - set worker flags and adjust nr_running accordingly * @worker: self * @flags: flags to set @@ -2184,6 +2204,9 @@ __acquires(&pool->lock) if (unlikely(cpu_intensive)) worker_clr_flags(worker, WORKER_CPU_INTENSIVE); + /* tag the worker for identification in schedule() */ + worker->last_func = worker->current_func; + /* we're done with it, release */ hash_del(&worker->hentry); worker->current_work = NULL; diff --git a/kernel/workqueue_internal.h b/kernel/workqueue_internal.h index 66fbb5a9e633..cb68b03ca89a 100644 --- a/kernel/workqueue_internal.h +++ b/kernel/workqueue_internal.h @@ -53,6 +53,9 @@ struct worker { /* used only by rescuers to point to the target workqueue */ struct workqueue_struct *rescue_wq; /* I: the workqueue to rescue */ + + /* used by the scheduler to determine a worker's last known identity */ + work_func_t last_func; }; /** @@ -67,9 +70,10 @@ static inline struct worker *current_wq_worker(void) /* * Scheduler hooks for concurrency managed workqueue. Only to be used from - * sched/core.c and workqueue.c. + * sched/ and workqueue.c. */ void wq_worker_waking_up(struct task_struct *task, int cpu); struct task_struct *wq_worker_sleeping(struct task_struct *task); +work_func_t wq_worker_last_func(struct task_struct *task); #endif /* _KERNEL_WORKQUEUE_INTERNAL_H */ diff --git a/lib/objagg.c b/lib/objagg.c index c9b457a91153..576be22e86de 100644 --- a/lib/objagg.c +++ b/lib/objagg.c @@ -4,6 +4,7 @@ #include <linux/module.h> #include <linux/slab.h> #include <linux/rhashtable.h> +#include <linux/idr.h> #include <linux/list.h> #include <linux/sort.h> #include <linux/objagg.h> @@ -11,6 +12,34 @@ #define CREATE_TRACE_POINTS #include <trace/events/objagg.h> +struct objagg_hints { + struct rhashtable node_ht; + struct rhashtable_params ht_params; + struct list_head node_list; + unsigned int node_count; + unsigned int root_count; + unsigned int refcount; + const struct objagg_ops *ops; +}; + +struct objagg_hints_node { + struct rhash_head ht_node; /* member of objagg_hints->node_ht */ + struct list_head list; /* member of objagg_hints->node_list */ + struct objagg_hints_node *parent; + unsigned int root_id; + struct objagg_obj_stats_info stats_info; + unsigned long obj[0]; +}; + +static struct objagg_hints_node * +objagg_hints_lookup(struct objagg_hints *objagg_hints, void *obj) +{ + if (!objagg_hints) + return NULL; + return rhashtable_lookup_fast(&objagg_hints->node_ht, obj, + objagg_hints->ht_params); +} + struct objagg { const struct objagg_ops *ops; void *priv; @@ -18,6 +47,8 @@ struct objagg { struct rhashtable_params ht_params; struct list_head obj_list; unsigned int obj_count; + struct ida root_ida; + struct objagg_hints *hints; }; struct objagg_obj { @@ -30,6 +61,7 @@ struct objagg_obj { void *delta_priv; /* user delta private */ void *root_priv; /* user root private */ }; + unsigned int root_id; unsigned int refcount; /* counts number of users of this object * including nested objects */ @@ -130,7 +162,8 @@ static struct objagg_obj *objagg_obj_lookup(struct objagg *objagg, void *obj) static int objagg_obj_parent_assign(struct objagg *objagg, struct objagg_obj *objagg_obj, - struct objagg_obj *parent) + struct objagg_obj *parent, + bool take_parent_ref) { void *delta_priv; @@ -144,7 +177,8 @@ static int objagg_obj_parent_assign(struct objagg *objagg, */ objagg_obj->parent = parent; objagg_obj->delta_priv = delta_priv; - objagg_obj_ref_inc(objagg_obj->parent); + if (take_parent_ref) + objagg_obj_ref_inc(objagg_obj->parent); trace_objagg_obj_parent_assign(objagg, objagg_obj, parent, parent->refcount); @@ -164,7 +198,7 @@ static int objagg_obj_parent_lookup_assign(struct objagg *objagg, if (!objagg_obj_is_root(objagg_obj_cur)) continue; err = objagg_obj_parent_assign(objagg, objagg_obj, - objagg_obj_cur); + objagg_obj_cur, true); if (!err) return 0; } @@ -184,16 +218,68 @@ static void objagg_obj_parent_unassign(struct objagg *objagg, __objagg_obj_put(objagg, objagg_obj->parent); } +static int objagg_obj_root_id_alloc(struct objagg *objagg, + struct objagg_obj *objagg_obj, + struct objagg_hints_node *hnode) +{ + unsigned int min, max; + int root_id; + + /* In case there are no hints available, the root id is invalid. */ + if (!objagg->hints) { + objagg_obj->root_id = OBJAGG_OBJ_ROOT_ID_INVALID; + return 0; + } + + if (hnode) { + min = hnode->root_id; + max = hnode->root_id; + } else { + /* For objects with no hint, start after the last + * hinted root_id. + */ + min = objagg->hints->root_count; + max = ~0; + } + + root_id = ida_alloc_range(&objagg->root_ida, min, max, GFP_KERNEL); + + if (root_id < 0) + return root_id; + objagg_obj->root_id = root_id; + return 0; +} + +static void objagg_obj_root_id_free(struct objagg *objagg, + struct objagg_obj *objagg_obj) +{ + if (!objagg->hints) + return; + ida_free(&objagg->root_ida, objagg_obj->root_id); +} + static int objagg_obj_root_create(struct objagg *objagg, - struct objagg_obj *objagg_obj) + struct objagg_obj *objagg_obj, + struct objagg_hints_node *hnode) { - objagg_obj->root_priv = objagg->ops->root_create(objagg->priv, - objagg_obj->obj); - if (IS_ERR(objagg_obj->root_priv)) - return PTR_ERR(objagg_obj->root_priv); + int err; + err = objagg_obj_root_id_alloc(objagg, objagg_obj, hnode); + if (err) + return err; + objagg_obj->root_priv = objagg->ops->root_create(objagg->priv, + objagg_obj->obj, + objagg_obj->root_id); + if (IS_ERR(objagg_obj->root_priv)) { + err = PTR_ERR(objagg_obj->root_priv); + goto err_root_create; + } trace_objagg_obj_root_create(objagg, objagg_obj); return 0; + +err_root_create: + objagg_obj_root_id_free(objagg, objagg_obj); + return err; } static void objagg_obj_root_destroy(struct objagg *objagg, @@ -201,19 +287,69 @@ static void objagg_obj_root_destroy(struct objagg *objagg, { trace_objagg_obj_root_destroy(objagg, objagg_obj); objagg->ops->root_destroy(objagg->priv, objagg_obj->root_priv); + objagg_obj_root_id_free(objagg, objagg_obj); +} + +static struct objagg_obj *__objagg_obj_get(struct objagg *objagg, void *obj); + +static int objagg_obj_init_with_hints(struct objagg *objagg, + struct objagg_obj *objagg_obj, + bool *hint_found) +{ + struct objagg_hints_node *hnode; + struct objagg_obj *parent; + int err; + + hnode = objagg_hints_lookup(objagg->hints, objagg_obj->obj); + if (!hnode) { + *hint_found = false; + return 0; + } + *hint_found = true; + + if (!hnode->parent) + return objagg_obj_root_create(objagg, objagg_obj, hnode); + + parent = __objagg_obj_get(objagg, hnode->parent->obj); + if (IS_ERR(parent)) + return PTR_ERR(parent); + + err = objagg_obj_parent_assign(objagg, objagg_obj, parent, false); + if (err) { + *hint_found = false; + err = 0; + goto err_parent_assign; + } + + return 0; + +err_parent_assign: + objagg_obj_put(objagg, parent); + return err; } static int objagg_obj_init(struct objagg *objagg, struct objagg_obj *objagg_obj) { + bool hint_found; int err; + /* First, try to use hints if they are available and + * if they provide result. + */ + err = objagg_obj_init_with_hints(objagg, objagg_obj, &hint_found); + if (err) + return err; + + if (hint_found) + return 0; + /* Try to find if the object can be aggregated under an existing one. */ err = objagg_obj_parent_lookup_assign(objagg, objagg_obj); if (!err) return 0; /* If aggregation is not possible, make the object a root. */ - return objagg_obj_root_create(objagg, objagg_obj); + return objagg_obj_root_create(objagg, objagg_obj, NULL); } static void objagg_obj_fini(struct objagg *objagg, @@ -349,8 +485,9 @@ EXPORT_SYMBOL(objagg_obj_put); /** * objagg_create - creates a new objagg instance - * @ops: user-specific callbacks - * @priv: pointer to a private data passed to the ops + * @ops: user-specific callbacks + * @objagg_hints: hints, can be NULL + * @priv: pointer to a private data passed to the ops * * Note: all locking must be provided by the caller. * @@ -374,18 +511,25 @@ EXPORT_SYMBOL(objagg_obj_put); * Returns a pointer to newly created objagg instance in case of success, * otherwise it returns pointer error using ERR_PTR macro. */ -struct objagg *objagg_create(const struct objagg_ops *ops, void *priv) +struct objagg *objagg_create(const struct objagg_ops *ops, + struct objagg_hints *objagg_hints, void *priv) { struct objagg *objagg; int err; if (WARN_ON(!ops || !ops->root_create || !ops->root_destroy || - !ops->delta_create || !ops->delta_destroy)) + !ops->delta_check || !ops->delta_create || + !ops->delta_destroy)) return ERR_PTR(-EINVAL); + objagg = kzalloc(sizeof(*objagg), GFP_KERNEL); if (!objagg) return ERR_PTR(-ENOMEM); objagg->ops = ops; + if (objagg_hints) { + objagg->hints = objagg_hints; + objagg_hints->refcount++; + } objagg->priv = priv; INIT_LIST_HEAD(&objagg->obj_list); @@ -397,6 +541,8 @@ struct objagg *objagg_create(const struct objagg_ops *ops, void *priv) if (err) goto err_rhashtable_init; + ida_init(&objagg->root_ida); + trace_objagg_create(objagg); return objagg; @@ -415,8 +561,11 @@ EXPORT_SYMBOL(objagg_create); void objagg_destroy(struct objagg *objagg) { trace_objagg_destroy(objagg); + ida_destroy(&objagg->root_ida); WARN_ON(!list_empty(&objagg->obj_list)); rhashtable_destroy(&objagg->obj_ht); + if (objagg->hints) + objagg_hints_put(objagg->hints); kfree(objagg); } EXPORT_SYMBOL(objagg_destroy); @@ -472,6 +621,8 @@ const struct objagg_stats *objagg_stats_get(struct objagg *objagg) objagg_stats->stats_info[i].objagg_obj = objagg_obj; objagg_stats->stats_info[i].is_root = objagg_obj_is_root(objagg_obj); + if (objagg_stats->stats_info[i].is_root) + objagg_stats->root_count++; i++; } objagg_stats->stats_info_count = i; @@ -485,7 +636,7 @@ const struct objagg_stats *objagg_stats_get(struct objagg *objagg) EXPORT_SYMBOL(objagg_stats_get); /** - * objagg_stats_puts - puts stats of the objagg instance + * objagg_stats_put - puts stats of the objagg instance * @objagg_stats: objagg instance stats * * Note: all locking must be provided by the caller. @@ -496,6 +647,410 @@ void objagg_stats_put(const struct objagg_stats *objagg_stats) } EXPORT_SYMBOL(objagg_stats_put); +static struct objagg_hints_node * +objagg_hints_node_create(struct objagg_hints *objagg_hints, + struct objagg_obj *objagg_obj, size_t obj_size, + struct objagg_hints_node *parent_hnode) +{ + unsigned int user_count = objagg_obj->stats.user_count; + struct objagg_hints_node *hnode; + int err; + + hnode = kzalloc(sizeof(*hnode) + obj_size, GFP_KERNEL); + if (!hnode) + return ERR_PTR(-ENOMEM); + memcpy(hnode->obj, &objagg_obj->obj, obj_size); + hnode->stats_info.stats.user_count = user_count; + hnode->stats_info.stats.delta_user_count = user_count; + if (parent_hnode) { + parent_hnode->stats_info.stats.delta_user_count += user_count; + } else { + hnode->root_id = objagg_hints->root_count++; + hnode->stats_info.is_root = true; + } + hnode->stats_info.objagg_obj = objagg_obj; + + err = rhashtable_insert_fast(&objagg_hints->node_ht, &hnode->ht_node, + objagg_hints->ht_params); + if (err) + goto err_ht_insert; + + list_add(&hnode->list, &objagg_hints->node_list); + hnode->parent = parent_hnode; + objagg_hints->node_count++; + + return hnode; + +err_ht_insert: + kfree(hnode); + return ERR_PTR(err); +} + +static void objagg_hints_flush(struct objagg_hints *objagg_hints) +{ + struct objagg_hints_node *hnode, *tmp; + + list_for_each_entry_safe(hnode, tmp, &objagg_hints->node_list, list) { + list_del(&hnode->list); + rhashtable_remove_fast(&objagg_hints->node_ht, &hnode->ht_node, + objagg_hints->ht_params); + kfree(hnode); + } +} + +struct objagg_tmp_node { + struct objagg_obj *objagg_obj; + bool crossed_out; +}; + +struct objagg_tmp_graph { + struct objagg_tmp_node *nodes; + unsigned long nodes_count; + unsigned long *edges; +}; + +static int objagg_tmp_graph_edge_index(struct objagg_tmp_graph *graph, + int parent_index, int index) +{ + return index * graph->nodes_count + parent_index; +} + +static void objagg_tmp_graph_edge_set(struct objagg_tmp_graph *graph, + int parent_index, int index) +{ + int edge_index = objagg_tmp_graph_edge_index(graph, index, + parent_index); + + __set_bit(edge_index, graph->edges); +} + +static bool objagg_tmp_graph_is_edge(struct objagg_tmp_graph *graph, + int parent_index, int index) +{ + int edge_index = objagg_tmp_graph_edge_index(graph, index, + parent_index); + + return test_bit(edge_index, graph->edges); +} + +static unsigned int objagg_tmp_graph_node_weight(struct objagg_tmp_graph *graph, + unsigned int index) +{ + struct objagg_tmp_node *node = &graph->nodes[index]; + unsigned int weight = node->objagg_obj->stats.user_count; + int j; + + /* Node weight is sum of node users and all other nodes users + * that this node can represent with delta. + */ + + for (j = 0; j < graph->nodes_count; j++) { + if (!objagg_tmp_graph_is_edge(graph, index, j)) + continue; + node = &graph->nodes[j]; + if (node->crossed_out) + continue; + weight += node->objagg_obj->stats.user_count; + } + return weight; +} + +static int objagg_tmp_graph_node_max_weight(struct objagg_tmp_graph *graph) +{ + struct objagg_tmp_node *node; + unsigned int max_weight = 0; + unsigned int weight; + int max_index = -1; + int i; + + for (i = 0; i < graph->nodes_count; i++) { + node = &graph->nodes[i]; + if (node->crossed_out) + continue; + weight = objagg_tmp_graph_node_weight(graph, i); + if (weight >= max_weight) { + max_weight = weight; + max_index = i; + } + } + return max_index; +} + +static struct objagg_tmp_graph *objagg_tmp_graph_create(struct objagg *objagg) +{ + unsigned int nodes_count = objagg->obj_count; + struct objagg_tmp_graph *graph; + struct objagg_tmp_node *node; + struct objagg_tmp_node *pnode; + struct objagg_obj *objagg_obj; + size_t alloc_size; + int i, j; + + graph = kzalloc(sizeof(*graph), GFP_KERNEL); + if (!graph) + return NULL; + + graph->nodes = kcalloc(nodes_count, sizeof(*graph->nodes), GFP_KERNEL); + if (!graph->nodes) + goto err_nodes_alloc; + graph->nodes_count = nodes_count; + + alloc_size = BITS_TO_LONGS(nodes_count * nodes_count) * + sizeof(unsigned long); + graph->edges = kzalloc(alloc_size, GFP_KERNEL); + if (!graph->edges) + goto err_edges_alloc; + + i = 0; + list_for_each_entry(objagg_obj, &objagg->obj_list, list) { + node = &graph->nodes[i++]; + node->objagg_obj = objagg_obj; + } + + /* Assemble a temporary graph. Insert edge X->Y in case Y can be + * in delta of X. + */ + for (i = 0; i < nodes_count; i++) { + for (j = 0; j < nodes_count; j++) { + if (i == j) + continue; + pnode = &graph->nodes[i]; + node = &graph->nodes[j]; + if (objagg->ops->delta_check(objagg->priv, + pnode->objagg_obj->obj, + node->objagg_obj->obj)) { + objagg_tmp_graph_edge_set(graph, i, j); + + } + } + } + return graph; + +err_edges_alloc: + kfree(graph->nodes); +err_nodes_alloc: + kfree(graph); + return NULL; +} + +static void objagg_tmp_graph_destroy(struct objagg_tmp_graph *graph) +{ + kfree(graph->edges); + kfree(graph->nodes); + kfree(graph); +} + +static int +objagg_opt_simple_greedy_fillup_hints(struct objagg_hints *objagg_hints, + struct objagg *objagg) +{ + struct objagg_hints_node *hnode, *parent_hnode; + struct objagg_tmp_graph *graph; + struct objagg_tmp_node *node; + int index; + int j; + int err; + + graph = objagg_tmp_graph_create(objagg); + if (!graph) + return -ENOMEM; + + /* Find the nodes from the ones that can accommodate most users + * and cross them out of the graph. Save them to the hint list. + */ + while ((index = objagg_tmp_graph_node_max_weight(graph)) != -1) { + node = &graph->nodes[index]; + node->crossed_out = true; + hnode = objagg_hints_node_create(objagg_hints, + node->objagg_obj, + objagg->ops->obj_size, + NULL); + if (IS_ERR(hnode)) { + err = PTR_ERR(hnode); + goto out; + } + parent_hnode = hnode; + for (j = 0; j < graph->nodes_count; j++) { + if (!objagg_tmp_graph_is_edge(graph, index, j)) + continue; + node = &graph->nodes[j]; + if (node->crossed_out) + continue; + node->crossed_out = true; + hnode = objagg_hints_node_create(objagg_hints, + node->objagg_obj, + objagg->ops->obj_size, + parent_hnode); + if (IS_ERR(hnode)) { + err = PTR_ERR(hnode); + goto out; + } + } + } + + err = 0; +out: + objagg_tmp_graph_destroy(graph); + return err; +} + +struct objagg_opt_algo { + int (*fillup_hints)(struct objagg_hints *objagg_hints, + struct objagg *objagg); +}; + +static const struct objagg_opt_algo objagg_opt_simple_greedy = { + .fillup_hints = objagg_opt_simple_greedy_fillup_hints, +}; + + +static const struct objagg_opt_algo *objagg_opt_algos[] = { + [OBJAGG_OPT_ALGO_SIMPLE_GREEDY] = &objagg_opt_simple_greedy, +}; + +static int objagg_hints_obj_cmp(struct rhashtable_compare_arg *arg, + const void *obj) +{ + struct rhashtable *ht = arg->ht; + struct objagg_hints *objagg_hints = + container_of(ht, struct objagg_hints, node_ht); + const struct objagg_ops *ops = objagg_hints->ops; + const char *ptr = obj; + + ptr += ht->p.key_offset; + return ops->hints_obj_cmp ? ops->hints_obj_cmp(ptr, arg->key) : + memcmp(ptr, arg->key, ht->p.key_len); +} + +/** + * objagg_hints_get - obtains hints instance + * @objagg: objagg instance + * @opt_algo_type: type of hints finding algorithm + * + * Note: all locking must be provided by the caller. + * + * According to the algo type, the existing objects of objagg instance + * are going to be went-through to assemble an optimal tree. We call this + * tree hints. These hints can be later on used for creation of + * a new objagg instance. There, the future object creations are going + * to be consulted with these hints in order to find out, where exactly + * the new object should be put as a root or delta. + * + * Returns a pointer to hints instance in case of success, + * otherwise it returns pointer error using ERR_PTR macro. + */ +struct objagg_hints *objagg_hints_get(struct objagg *objagg, + enum objagg_opt_algo_type opt_algo_type) +{ + const struct objagg_opt_algo *algo = objagg_opt_algos[opt_algo_type]; + struct objagg_hints *objagg_hints; + int err; + + objagg_hints = kzalloc(sizeof(*objagg_hints), GFP_KERNEL); + if (!objagg_hints) + return ERR_PTR(-ENOMEM); + + objagg_hints->ops = objagg->ops; + objagg_hints->refcount = 1; + + INIT_LIST_HEAD(&objagg_hints->node_list); + + objagg_hints->ht_params.key_len = objagg->ops->obj_size; + objagg_hints->ht_params.key_offset = + offsetof(struct objagg_hints_node, obj); + objagg_hints->ht_params.head_offset = + offsetof(struct objagg_hints_node, ht_node); + objagg_hints->ht_params.obj_cmpfn = objagg_hints_obj_cmp; + + err = rhashtable_init(&objagg_hints->node_ht, &objagg_hints->ht_params); + if (err) + goto err_rhashtable_init; + + err = algo->fillup_hints(objagg_hints, objagg); + if (err) + goto err_fillup_hints; + + if (WARN_ON(objagg_hints->node_count != objagg->obj_count)) { + err = -EINVAL; + goto err_node_count_check; + } + + return objagg_hints; + +err_node_count_check: +err_fillup_hints: + objagg_hints_flush(objagg_hints); + rhashtable_destroy(&objagg_hints->node_ht); +err_rhashtable_init: + kfree(objagg_hints); + return ERR_PTR(err); +} +EXPORT_SYMBOL(objagg_hints_get); + +/** + * objagg_hints_put - puts hints instance + * @objagg_hints: objagg hints instance + * + * Note: all locking must be provided by the caller. + */ +void objagg_hints_put(struct objagg_hints *objagg_hints) +{ + if (--objagg_hints->refcount) + return; + objagg_hints_flush(objagg_hints); + rhashtable_destroy(&objagg_hints->node_ht); + kfree(objagg_hints); +} +EXPORT_SYMBOL(objagg_hints_put); + +/** + * objagg_hints_stats_get - obtains stats of the hints instance + * @objagg_hints: hints instance + * + * Note: all locking must be provided by the caller. + * + * The returned structure contains statistics of all objects + * currently in use, ordered by following rules: + * 1) Root objects are always on lower indexes than the rest. + * 2) Objects with higher delta user count are always on lower + * indexes. + * 3) In case multiple objects have the same delta user count, + * the objects are ordered by user count. + * + * Returns a pointer to stats instance in case of success, + * otherwise it returns pointer error using ERR_PTR macro. + */ +const struct objagg_stats * +objagg_hints_stats_get(struct objagg_hints *objagg_hints) +{ + struct objagg_stats *objagg_stats; + struct objagg_hints_node *hnode; + int i; + + objagg_stats = kzalloc(struct_size(objagg_stats, stats_info, + objagg_hints->node_count), + GFP_KERNEL); + if (!objagg_stats) + return ERR_PTR(-ENOMEM); + + i = 0; + list_for_each_entry(hnode, &objagg_hints->node_list, list) { + memcpy(&objagg_stats->stats_info[i], &hnode->stats_info, + sizeof(objagg_stats->stats_info[0])); + if (objagg_stats->stats_info[i].is_root) + objagg_stats->root_count++; + i++; + } + objagg_stats->stats_info_count = i; + + sort(objagg_stats->stats_info, objagg_stats->stats_info_count, + sizeof(struct objagg_obj_stats_info), + objagg_stats_info_sort_cmp_func, NULL); + + return objagg_stats; +} +EXPORT_SYMBOL(objagg_hints_stats_get); + MODULE_LICENSE("Dual BSD/GPL"); MODULE_AUTHOR("Jiri Pirko <jiri@mellanox.com>"); MODULE_DESCRIPTION("Object aggregation manager"); diff --git a/lib/test_kmod.c b/lib/test_kmod.c index d82d022111e0..9cf77628fc91 100644 --- a/lib/test_kmod.c +++ b/lib/test_kmod.c @@ -632,7 +632,7 @@ static void __kmod_config_free(struct test_config *config) config->test_driver = NULL; kfree_const(config->test_fs); - config->test_driver = NULL; + config->test_fs = NULL; } static void kmod_config_free(struct kmod_test_device *test_dev) diff --git a/lib/test_objagg.c b/lib/test_objagg.c index ab57144bb0cd..72c1abfa154d 100644 --- a/lib/test_objagg.c +++ b/lib/test_objagg.c @@ -87,6 +87,15 @@ static void world_obj_put(struct world *world, struct objagg *objagg, #define MAX_KEY_ID_DIFF 5 +static bool delta_check(void *priv, const void *parent_obj, const void *obj) +{ + const struct tokey *parent_key = parent_obj; + const struct tokey *key = obj; + int diff = key->id - parent_key->id; + + return diff >= 0 && diff <= MAX_KEY_ID_DIFF; +} + static void *delta_create(void *priv, void *parent_obj, void *obj) { struct tokey *parent_key = parent_obj; @@ -95,7 +104,7 @@ static void *delta_create(void *priv, void *parent_obj, void *obj) int diff = key->id - parent_key->id; struct delta *delta; - if (diff < 0 || diff > MAX_KEY_ID_DIFF) + if (!delta_check(priv, parent_obj, obj)) return ERR_PTR(-EINVAL); delta = kzalloc(sizeof(*delta), GFP_KERNEL); @@ -115,7 +124,7 @@ static void delta_destroy(void *priv, void *delta_priv) kfree(delta); } -static void *root_create(void *priv, void *obj) +static void *root_create(void *priv, void *obj, unsigned int id) { struct world *world = priv; struct tokey *key = obj; @@ -268,6 +277,12 @@ stats_put: return err; } +static bool delta_check_dummy(void *priv, const void *parent_obj, + const void *obj) +{ + return false; +} + static void *delta_create_dummy(void *priv, void *parent_obj, void *obj) { return ERR_PTR(-EOPNOTSUPP); @@ -279,6 +294,7 @@ static void delta_destroy_dummy(void *priv, void *delta_priv) static const struct objagg_ops nodelta_ops = { .obj_size = sizeof(struct tokey), + .delta_check = delta_check_dummy, .delta_create = delta_create_dummy, .delta_destroy = delta_destroy_dummy, .root_create = root_create, @@ -292,7 +308,7 @@ static int test_nodelta(void) int i; int err; - objagg = objagg_create(&nodelta_ops, &world); + objagg = objagg_create(&nodelta_ops, NULL, &world); if (IS_ERR(objagg)) return PTR_ERR(objagg); @@ -357,6 +373,7 @@ err_stats_second_zero: static const struct objagg_ops delta_ops = { .obj_size = sizeof(struct tokey), + .delta_check = delta_check, .delta_create = delta_create, .delta_destroy = delta_destroy, .root_create = root_create, @@ -728,8 +745,10 @@ static int check_expect_stats(struct objagg *objagg, int err; stats = objagg_stats_get(objagg); - if (IS_ERR(stats)) + if (IS_ERR(stats)) { + *errmsg = "objagg_stats_get() failed."; return PTR_ERR(stats); + } err = __check_expect_stats(stats, expect_stats, errmsg); objagg_stats_put(stats); return err; @@ -769,7 +788,6 @@ static int test_delta_action_item(struct world *world, if (err) goto errout; - errmsg = NULL; err = check_expect_stats(objagg, &action_item->expect_stats, &errmsg); if (err) { pr_err("Key %u: Stats: %s\n", action_item->key_id, errmsg); @@ -793,7 +811,7 @@ static int test_delta(void) int i; int err; - objagg = objagg_create(&delta_ops, &world); + objagg = objagg_create(&delta_ops, NULL, &world); if (IS_ERR(objagg)) return PTR_ERR(objagg); @@ -815,6 +833,170 @@ err_do_action_item: return err; } +struct hints_case { + const unsigned int *key_ids; + size_t key_ids_count; + struct expect_stats expect_stats; + struct expect_stats expect_stats_hints; +}; + +static const unsigned int hints_case_key_ids[] = { + 1, 7, 3, 5, 3, 1, 30, 8, 8, 5, 6, 8, +}; + +static const struct hints_case hints_case = { + .key_ids = hints_case_key_ids, + .key_ids_count = ARRAY_SIZE(hints_case_key_ids), + .expect_stats = + EXPECT_STATS(7, ROOT(1, 2, 7), ROOT(7, 1, 4), ROOT(30, 1, 1), + DELTA(8, 3), DELTA(3, 2), + DELTA(5, 2), DELTA(6, 1)), + .expect_stats_hints = + EXPECT_STATS(7, ROOT(3, 2, 9), ROOT(1, 2, 2), ROOT(30, 1, 1), + DELTA(8, 3), DELTA(5, 2), + DELTA(6, 1), DELTA(7, 1)), +}; + +static void __pr_debug_stats(const struct objagg_stats *stats) +{ + int i; + + for (i = 0; i < stats->stats_info_count; i++) + pr_debug("Stat index %d key %u: u %d, d %d, %s\n", i, + obj_to_key_id(stats->stats_info[i].objagg_obj), + stats->stats_info[i].stats.user_count, + stats->stats_info[i].stats.delta_user_count, + stats->stats_info[i].is_root ? "root" : "noroot"); +} + +static void pr_debug_stats(struct objagg *objagg) +{ + const struct objagg_stats *stats; + + stats = objagg_stats_get(objagg); + if (IS_ERR(stats)) + return; + __pr_debug_stats(stats); + objagg_stats_put(stats); +} + +static void pr_debug_hints_stats(struct objagg_hints *objagg_hints) +{ + const struct objagg_stats *stats; + + stats = objagg_hints_stats_get(objagg_hints); + if (IS_ERR(stats)) + return; + __pr_debug_stats(stats); + objagg_stats_put(stats); +} + +static int check_expect_hints_stats(struct objagg_hints *objagg_hints, + const struct expect_stats *expect_stats, + const char **errmsg) +{ + const struct objagg_stats *stats; + int err; + + stats = objagg_hints_stats_get(objagg_hints); + if (IS_ERR(stats)) + return PTR_ERR(stats); + err = __check_expect_stats(stats, expect_stats, errmsg); + objagg_stats_put(stats); + return err; +} + +static int test_hints_case(const struct hints_case *hints_case) +{ + struct objagg_obj *objagg_obj; + struct objagg_hints *hints; + struct world world2 = {}; + struct world world = {}; + struct objagg *objagg2; + struct objagg *objagg; + const char *errmsg; + int i; + int err; + + objagg = objagg_create(&delta_ops, NULL, &world); + if (IS_ERR(objagg)) + return PTR_ERR(objagg); + + for (i = 0; i < hints_case->key_ids_count; i++) { + objagg_obj = world_obj_get(&world, objagg, + hints_case->key_ids[i]); + if (IS_ERR(objagg_obj)) { + err = PTR_ERR(objagg_obj); + goto err_world_obj_get; + } + } + + pr_debug_stats(objagg); + err = check_expect_stats(objagg, &hints_case->expect_stats, &errmsg); + if (err) { + pr_err("Stats: %s\n", errmsg); + goto err_check_expect_stats; + } + + hints = objagg_hints_get(objagg, OBJAGG_OPT_ALGO_SIMPLE_GREEDY); + if (IS_ERR(hints)) { + err = PTR_ERR(hints); + goto err_hints_get; + } + + pr_debug_hints_stats(hints); + err = check_expect_hints_stats(hints, &hints_case->expect_stats_hints, + &errmsg); + if (err) { + pr_err("Hints stats: %s\n", errmsg); + goto err_check_expect_hints_stats; + } + + objagg2 = objagg_create(&delta_ops, hints, &world2); + if (IS_ERR(objagg2)) + return PTR_ERR(objagg2); + + for (i = 0; i < hints_case->key_ids_count; i++) { + objagg_obj = world_obj_get(&world2, objagg2, + hints_case->key_ids[i]); + if (IS_ERR(objagg_obj)) { + err = PTR_ERR(objagg_obj); + goto err_world2_obj_get; + } + } + + pr_debug_stats(objagg2); + err = check_expect_stats(objagg2, &hints_case->expect_stats_hints, + &errmsg); + if (err) { + pr_err("Stats2: %s\n", errmsg); + goto err_check_expect_stats2; + } + + err = 0; + +err_check_expect_stats2: +err_world2_obj_get: + for (i--; i >= 0; i--) + world_obj_put(&world2, objagg, hints_case->key_ids[i]); + objagg_hints_put(hints); + objagg_destroy(objagg2); + i = hints_case->key_ids_count; +err_check_expect_hints_stats: +err_hints_get: +err_check_expect_stats: +err_world_obj_get: + for (i--; i >= 0; i--) + world_obj_put(&world, objagg, hints_case->key_ids[i]); + + objagg_destroy(objagg); + return err; +} +static int test_hints(void) +{ + return test_hints_case(&hints_case); +} + static int __init test_objagg_init(void) { int err; @@ -822,7 +1004,10 @@ static int __init test_objagg_init(void) err = test_nodelta(); if (err) return err; - return test_delta(); + err = test_delta(); + if (err) + return err; + return test_hints(); } static void __exit test_objagg_exit(void) diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c index 6a8ac7626797..e52f8cafe227 100644 --- a/lib/test_rhashtable.c +++ b/lib/test_rhashtable.c @@ -541,38 +541,45 @@ static unsigned int __init print_ht(struct rhltable *rhlt) static int __init test_insert_dup(struct test_obj_rhl *rhl_test_objects, int cnt, bool slow) { - struct rhltable rhlt; + struct rhltable *rhlt; unsigned int i, ret; const char *key; int err = 0; - err = rhltable_init(&rhlt, &test_rht_params_dup); - if (WARN_ON(err)) + rhlt = kmalloc(sizeof(*rhlt), GFP_KERNEL); + if (WARN_ON(!rhlt)) + return -EINVAL; + + err = rhltable_init(rhlt, &test_rht_params_dup); + if (WARN_ON(err)) { + kfree(rhlt); return err; + } for (i = 0; i < cnt; i++) { rhl_test_objects[i].value.tid = i; - key = rht_obj(&rhlt.ht, &rhl_test_objects[i].list_node.rhead); + key = rht_obj(&rhlt->ht, &rhl_test_objects[i].list_node.rhead); key += test_rht_params_dup.key_offset; if (slow) { - err = PTR_ERR(rhashtable_insert_slow(&rhlt.ht, key, + err = PTR_ERR(rhashtable_insert_slow(&rhlt->ht, key, &rhl_test_objects[i].list_node.rhead)); if (err == -EAGAIN) err = 0; } else - err = rhltable_insert(&rhlt, + err = rhltable_insert(rhlt, &rhl_test_objects[i].list_node, test_rht_params_dup); if (WARN(err, "error %d on element %d/%d (%s)\n", err, i, cnt, slow? "slow" : "fast")) goto skip_print; } - ret = print_ht(&rhlt); + ret = print_ht(rhlt); WARN(ret != cnt, "missing rhltable elements (%d != %d, %s)\n", ret, cnt, slow? "slow" : "fast"); skip_print: - rhltable_destroy(&rhlt); + rhltable_destroy(rhlt); + kfree(rhlt); return 0; } @@ -1674,7 +1674,8 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, if (!pmd_present(pmd)) return 0; - if (unlikely(pmd_trans_huge(pmd) || pmd_huge(pmd))) { + if (unlikely(pmd_trans_huge(pmd) || pmd_huge(pmd) || + pmd_devmap(pmd))) { /* * NUMA hinting faults need to be handled in the GUP * slowpath for accounting purposes and so that they diff --git a/mm/hugetlb.c b/mm/hugetlb.c index df2e7dd5ff17..afef61656c1e 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4268,7 +4268,8 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, break; } if (ret & VM_FAULT_RETRY) { - if (nonblocking) + if (nonblocking && + !(fault_flags & FAULT_FLAG_RETRY_NOWAIT)) *nonblocking = 0; *nr_pages = 0; /* diff --git a/mm/kasan/Makefile b/mm/kasan/Makefile index 0a14fcff70ed..e2bb06c1b45e 100644 --- a/mm/kasan/Makefile +++ b/mm/kasan/Makefile @@ -5,6 +5,7 @@ UBSAN_SANITIZE_generic.o := n UBSAN_SANITIZE_tags.o := n KCOV_INSTRUMENT := n +CFLAGS_REMOVE_common.o = -pg CFLAGS_REMOVE_generic.o = -pg # Function splitter causes unnecessary splits in __asan_load1/__asan_store1 # see: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63533 diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 7c72f2a95785..831be5ff5f4d 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -372,7 +372,8 @@ static void kill_procs(struct list_head *to_kill, int forcekill, bool fail, if (fail || tk->addr_valid == 0) { pr_err("Memory failure: %#lx: forcibly killing %s:%d because of failure to unmap corrupted page\n", pfn, tk->tsk->comm, tk->tsk->pid); - force_sig(SIGKILL, tk->tsk); + do_send_sig_info(SIGKILL, SEND_SIG_PRIV, + tk->tsk, PIDTYPE_PID); } /* diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index b9a667d36c55..124e794867c5 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1233,7 +1233,8 @@ static bool is_pageblock_removable_nolock(struct page *page) bool is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages) { struct page *page = pfn_to_page(start_pfn); - struct page *end_page = page + nr_pages; + unsigned long end_pfn = min(start_pfn + nr_pages, zone_end_pfn(page_zone(page))); + struct page *end_page = pfn_to_page(end_pfn); /* Check the starting page of each pageblock within the range */ for (; page < end_page; page = next_active_pageblock(page)) { @@ -1273,6 +1274,9 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn, i++; if (i == MAX_ORDER_NR_PAGES || pfn + i >= end_pfn) continue; + /* Check if we got outside of the zone */ + if (zone && !zone_spans_pfn(zone, pfn + i)) + return 0; page = pfn_to_page(pfn + i); if (zone && page_zone(page) != zone) return 0; @@ -1301,23 +1305,27 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn, static unsigned long scan_movable_pages(unsigned long start, unsigned long end) { unsigned long pfn; - struct page *page; + for (pfn = start; pfn < end; pfn++) { - if (pfn_valid(pfn)) { - page = pfn_to_page(pfn); - if (PageLRU(page)) - return pfn; - if (__PageMovable(page)) - return pfn; - if (PageHuge(page)) { - if (hugepage_migration_supported(page_hstate(page)) && - page_huge_active(page)) - return pfn; - else - pfn = round_up(pfn + 1, - 1 << compound_order(page)) - 1; - } - } + struct page *page, *head; + unsigned long skip; + + if (!pfn_valid(pfn)) + continue; + page = pfn_to_page(pfn); + if (PageLRU(page)) + return pfn; + if (__PageMovable(page)) + return pfn; + + if (!PageHuge(page)) + continue; + head = compound_head(page); + if (hugepage_migration_supported(page_hstate(head)) && + page_huge_active(head)) + return pfn; + skip = (1 << compound_order(head)) - (page - head); + pfn += skip - 1; } return 0; } @@ -1344,7 +1352,6 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) { unsigned long pfn; struct page *page; - int not_managed = 0; int ret = 0; LIST_HEAD(source); @@ -1392,7 +1399,6 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) else ret = isolate_movable_page(page, ISOLATE_UNEVICTABLE); if (!ret) { /* Success */ - put_page(page); list_add_tail(&page->lru, &source); if (!__PageMovable(page)) inc_node_page_state(page, NR_ISOLATED_ANON + @@ -1401,22 +1407,10 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) } else { pr_warn("failed to isolate pfn %lx\n", pfn); dump_page(page, "isolation failed"); - put_page(page); - /* Because we don't have big zone->lock. we should - check this again here. */ - if (page_count(page)) { - not_managed++; - ret = -EBUSY; - break; - } } + put_page(page); } if (!list_empty(&source)) { - if (not_managed) { - putback_movable_pages(&source); - goto out; - } - /* Allocate a new page from the nearest neighbor node */ ret = migrate_pages(&source, new_node_page, NULL, 0, MIGRATE_SYNC, MR_MEMORY_HOTPLUG); @@ -1429,7 +1423,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) putback_movable_pages(&source); } } -out: + return ret; } @@ -1576,7 +1570,6 @@ static int __ref __offline_pages(unsigned long start_pfn, we assume this for now. .*/ if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, &valid_end)) { - mem_hotplug_done(); ret = -EINVAL; reason = "multizone range"; goto failed_removal; @@ -1591,7 +1584,6 @@ static int __ref __offline_pages(unsigned long start_pfn, MIGRATE_MOVABLE, SKIP_HWPOISON | REPORT_FAILURE); if (ret) { - mem_hotplug_done(); reason = "failure to isolate range"; goto failed_removal; } diff --git a/mm/migrate.c b/mm/migrate.c index a16b15090df3..d4fd680be3b0 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -709,7 +709,6 @@ static bool buffer_migrate_lock_buffers(struct buffer_head *head, /* Simple case, sync compaction */ if (mode != MIGRATE_ASYNC) { do { - get_bh(bh); lock_buffer(bh); bh = bh->b_this_page; @@ -720,18 +719,15 @@ static bool buffer_migrate_lock_buffers(struct buffer_head *head, /* async case, we cannot block on lock_buffer so use trylock_buffer */ do { - get_bh(bh); if (!trylock_buffer(bh)) { /* * We failed to lock the buffer and cannot stall in * async migration. Release the taken locks */ struct buffer_head *failed_bh = bh; - put_bh(failed_bh); bh = head; while (bh != failed_bh) { unlock_buffer(bh); - put_bh(bh); bh = bh->b_this_page; } return false; @@ -818,7 +814,6 @@ unlock_buffers: bh = head; do { unlock_buffer(bh); - put_bh(bh); bh = bh->b_this_page; } while (bh != head); @@ -1135,10 +1130,13 @@ out: * If migration is successful, decrease refcount of the newpage * which will not free the page because new page owner increased * refcounter. As well, if it is LRU page, add the page to LRU - * list in here. + * list in here. Use the old state of the isolated source page to + * determine if we migrated a LRU page. newpage was already unlocked + * and possibly modified by its owner - don't rely on the page + * state. */ if (rc == MIGRATEPAGE_SUCCESS) { - if (unlikely(__PageMovable(newpage))) + if (unlikely(!is_lru)) put_page(newpage); else putback_lru_page(newpage); diff --git a/mm/oom_kill.c b/mm/oom_kill.c index f0e8cd9edb1a..26ea8636758f 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -647,8 +647,8 @@ static int oom_reaper(void *unused) static void wake_oom_reaper(struct task_struct *tsk) { - /* tsk is already queued? */ - if (tsk == oom_reaper_list || tsk->oom_reaper_list) + /* mm is already queued? */ + if (test_and_set_bit(MMF_OOM_REAP_QUEUED, &tsk->signal->oom_mm->flags)) return; get_task_struct(tsk); @@ -975,6 +975,13 @@ static void oom_kill_process(struct oom_control *oc, const char *message) * still freeing memory. */ read_lock(&tasklist_lock); + + /* + * The task 'p' might have already exited before reaching here. The + * put_task_struct() will free task_struct 'p' while the loop still try + * to access the field of 'p', so, get an extra reference. + */ + get_task_struct(p); for_each_thread(p, t) { list_for_each_entry(child, &t->children, sibling) { unsigned int child_points; @@ -994,6 +1001,7 @@ static void oom_kill_process(struct oom_control *oc, const char *message) } } } + put_task_struct(p); read_unlock(&tasklist_lock); /* diff --git a/mm/page_alloc.c b/mm/page_alloc.c index d295c9bc01a8..46285d28e43b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4675,11 +4675,11 @@ refill: /* Even if we own the page, we do not use atomic_set(). * This would break get_page_unless_zero() users. */ - page_ref_add(page, size - 1); + page_ref_add(page, size); /* reset page count bias and offset to start of new frag */ nc->pfmemalloc = page_is_pfmemalloc(page); - nc->pagecnt_bias = size; + nc->pagecnt_bias = size + 1; nc->offset = size; } @@ -4695,10 +4695,10 @@ refill: size = nc->size; #endif /* OK, page count is 0, we can safely set it */ - set_page_count(page, size); + set_page_count(page, size + 1); /* reset page count bias and offset to start of new frag */ - nc->pagecnt_bias = size; + nc->pagecnt_bias = size + 1; offset = size - fragsz; } @@ -5701,18 +5701,6 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, cond_resched(); } } -#ifdef CONFIG_SPARSEMEM - /* - * If the zone does not span the rest of the section then - * we should at least initialize those pages. Otherwise we - * could blow up on a poisoned page in some paths which depend - * on full sections being initialized (e.g. memory hotplug). - */ - while (end_pfn % PAGES_PER_SECTION) { - __init_single_page(pfn_to_page(end_pfn), end_pfn, zone, nid); - end_pfn++; - } -#endif } #ifdef CONFIG_ZONE_DEVICE diff --git a/mm/page_ext.c b/mm/page_ext.c index ae44f7adbe07..8c78b8d45117 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -398,10 +398,8 @@ void __init page_ext_init(void) * We know some arch can have a nodes layout such as * -------------pfn--------------> * N0 | N1 | N2 | N0 | N1 | N2|.... - * - * Take into account DEFERRED_STRUCT_PAGE_INIT. */ - if (early_pfn_to_nid(pfn) != nid) + if (pfn_to_nid(pfn) != nid) continue; if (init_section_page_ext(pfn, nid)) goto oom; diff --git a/mm/vmscan.c b/mm/vmscan.c index a714c4f800e9..e979705bbf32 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -491,16 +491,6 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, delta = freeable / 2; } - /* - * Make sure we apply some minimal pressure on default priority - * even on small cgroups. Stale objects are not only consuming memory - * by themselves, but can also hold a reference to a dying cgroup, - * preventing it from being reclaimed. A dying cgroup with all - * corresponding structures like per-cpu stats and kmem caches - * can be really big, so it may lead to a significant waste of memory. - */ - delta = max_t(unsigned long long, delta, min(freeable, batch_size)); - total_scan += delta; if (total_scan < 0) { pr_err("shrink_slab: %pF negative objects to delete nr=%ld\n", diff --git a/net/Kconfig b/net/Kconfig index 5cb9de1aaf88..62da6148e9f8 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -403,7 +403,7 @@ config LWTUNNEL config LWTUNNEL_BPF bool "Execute BPF program as route nexthop action" - depends on LWTUNNEL + depends on LWTUNNEL && INET default y if LWTUNNEL=y ---help--- Allows to run BPF programs as a nexthop action following a route diff --git a/net/atm/proc.c b/net/atm/proc.c index 0b0495a41bbe..d79221fd4dae 100644 --- a/net/atm/proc.c +++ b/net/atm/proc.c @@ -134,7 +134,8 @@ static void vcc_seq_stop(struct seq_file *seq, void *v) static void *vcc_seq_next(struct seq_file *seq, void *v, loff_t *pos) { v = vcc_walk(seq, 1); - *pos += !!PTR_ERR(v); + if (v) + (*pos)++; return v; } diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig index c386e6981416..a31db5e9ac8e 100644 --- a/net/batman-adv/Kconfig +++ b/net/batman-adv/Kconfig @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -# Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +# Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: # # Marek Lindner, Simon Wunderlich # diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile index 9b58160fe485..a887ecc3efa1 100644 --- a/net/batman-adv/Makefile +++ b/net/batman-adv/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -# Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +# Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: # # Marek Lindner, Simon Wunderlich # diff --git a/net/batman-adv/bat_algo.c b/net/batman-adv/bat_algo.c index ea309ad06175..7b7e15641fef 100644 --- a/net/batman-adv/bat_algo.c +++ b/net/batman-adv/bat_algo.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/bat_algo.h b/net/batman-adv/bat_algo.h index 534b790c3753..25e7bb51928c 100644 --- a/net/batman-adv/bat_algo.h +++ b/net/batman-adv/bat_algo.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2011-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Linus Lüssing * diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index f97e566f0402..de61091af666 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/bat_iv_ogm.h b/net/batman-adv/bat_iv_ogm.h index 3dc6a7a43eb7..785f6666273c 100644 --- a/net/batman-adv/bat_iv_ogm.h +++ b/net/batman-adv/bat_iv_ogm.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c index 90e33f84d37a..445594ed58af 100644 --- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2013-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2019 B.A.T.M.A.N. contributors: * * Linus Lüssing, Marek Lindner * diff --git a/net/batman-adv/bat_v.h b/net/batman-adv/bat_v.h index ec4a2a569750..465a4fc23354 100644 --- a/net/batman-adv/bat_v.h +++ b/net/batman-adv/bat_v.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2011-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Linus Lüssing * diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index e8090f099eb8..a9b7919c9de5 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2011-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors: * * Linus Lüssing, Marek Lindner * @@ -104,6 +104,9 @@ static u32 batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh) ret = cfg80211_get_station(real_netdev, neigh->addr, &sinfo); + /* free the TID stats immediately */ + cfg80211_sinfo_release_content(&sinfo); + dev_put(real_netdev); if (ret == -ENOENT) { /* Node is not associated anymore! It would be diff --git a/net/batman-adv/bat_v_elp.h b/net/batman-adv/bat_v_elp.h index e8c7b7fd290d..75f189ee4a1c 100644 --- a/net/batman-adv/bat_v_elp.h +++ b/net/batman-adv/bat_v_elp.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2013-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2019 B.A.T.M.A.N. contributors: * * Linus Lüssing, Marek Lindner * diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index 2948b41b06d4..c9698ad41854 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2013-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2019 B.A.T.M.A.N. contributors: * * Antonio Quartulli * diff --git a/net/batman-adv/bat_v_ogm.h b/net/batman-adv/bat_v_ogm.h index e5be14c908c6..f67cf7ee06b2 100644 --- a/net/batman-adv/bat_v_ogm.h +++ b/net/batman-adv/bat_v_ogm.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2013-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2019 B.A.T.M.A.N. contributors: * * Antonio Quartulli * diff --git a/net/batman-adv/bitarray.c b/net/batman-adv/bitarray.c index a296a4d851f5..63e134e763e3 100644 --- a/net/batman-adv/bitarray.c +++ b/net/batman-adv/bitarray.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2006-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2019 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/bitarray.h b/net/batman-adv/bitarray.h index 48f683289531..f3a05ad9afad 100644 --- a/net/batman-adv/bitarray.h +++ b/net/batman-adv/bitarray.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2006-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2019 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 5fdde2947802..ef39aabdb694 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2011-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors: * * Simon Wunderlich * diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h index 71f95a3e4d3f..31771c751efb 100644 --- a/net/batman-adv/bridge_loop_avoidance.h +++ b/net/batman-adv/bridge_loop_avoidance.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2011-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors: * * Simon Wunderlich * diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c index d4a7702e48d8..3b9d1ad2f467 100644 --- a/net/batman-adv/debugfs.c +++ b/net/batman-adv/debugfs.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2010-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/debugfs.h b/net/batman-adv/debugfs.h index 8de018e5c577..c0b8694041ec 100644 --- a/net/batman-adv/debugfs.h +++ b/net/batman-adv/debugfs.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2010-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index b9ffe1826527..310a4f353008 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2011-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors: * * Antonio Quartulli * @@ -19,6 +19,7 @@ #include "distributed-arp-table.h" #include "main.h" +#include <asm/unaligned.h> #include <linux/atomic.h> #include <linux/bitops.h> #include <linux/byteorder/generic.h> @@ -29,6 +30,7 @@ #include <linux/if_ether.h> #include <linux/if_vlan.h> #include <linux/in.h> +#include <linux/ip.h> #include <linux/jiffies.h> #include <linux/kernel.h> #include <linux/kref.h> @@ -42,6 +44,7 @@ #include <linux/spinlock.h> #include <linux/stddef.h> #include <linux/string.h> +#include <linux/udp.h> #include <linux/workqueue.h> #include <net/arp.h> #include <net/genetlink.h> @@ -60,6 +63,49 @@ #include "translation-table.h" #include "tvlv.h" +enum batadv_bootpop { + BATADV_BOOTREPLY = 2, +}; + +enum batadv_boothtype { + BATADV_HTYPE_ETHERNET = 1, +}; + +enum batadv_dhcpoptioncode { + BATADV_DHCP_OPT_PAD = 0, + BATADV_DHCP_OPT_MSG_TYPE = 53, + BATADV_DHCP_OPT_END = 255, +}; + +enum batadv_dhcptype { + BATADV_DHCPACK = 5, +}; + +/* { 99, 130, 83, 99 } */ +#define BATADV_DHCP_MAGIC 1669485411 + +struct batadv_dhcp_packet { + __u8 op; + __u8 htype; + __u8 hlen; + __u8 hops; + __be32 xid; + __be16 secs; + __be16 flags; + __be32 ciaddr; + __be32 yiaddr; + __be32 siaddr; + __be32 giaddr; + __u8 chaddr[16]; + __u8 sname[64]; + __u8 file[128]; + __be32 magic; + __u8 options[0]; +}; + +#define BATADV_DHCP_YIADDR_LEN sizeof(((struct batadv_dhcp_packet *)0)->yiaddr) +#define BATADV_DHCP_CHADDR_LEN sizeof(((struct batadv_dhcp_packet *)0)->chaddr) + static void batadv_dat_purge(struct work_struct *work); /** @@ -1440,6 +1486,361 @@ out: } /** + * batadv_dat_check_dhcp_ipudp() - check skb for IP+UDP headers valid for DHCP + * @skb: the packet to check + * @ip_src: a buffer to store the IPv4 source address in + * + * Checks whether the given skb has an IP and UDP header valid for a DHCP + * message from a DHCP server. And if so, stores the IPv4 source address in + * the provided buffer. + * + * Return: True if valid, false otherwise. + */ +static bool +batadv_dat_check_dhcp_ipudp(struct sk_buff *skb, __be32 *ip_src) +{ + unsigned int offset = skb_network_offset(skb); + struct udphdr *udphdr, _udphdr; + struct iphdr *iphdr, _iphdr; + + iphdr = skb_header_pointer(skb, offset, sizeof(_iphdr), &_iphdr); + if (!iphdr || iphdr->version != 4 || iphdr->ihl * 4 < sizeof(_iphdr)) + return false; + + if (iphdr->protocol != IPPROTO_UDP) + return false; + + offset += iphdr->ihl * 4; + skb_set_transport_header(skb, offset); + + udphdr = skb_header_pointer(skb, offset, sizeof(_udphdr), &_udphdr); + if (!udphdr || udphdr->source != htons(67)) + return false; + + *ip_src = get_unaligned(&iphdr->saddr); + + return true; +} + +/** + * batadv_dat_check_dhcp() - examine packet for valid DHCP message + * @skb: the packet to check + * @proto: ethernet protocol hint (behind a potential vlan) + * @ip_src: a buffer to store the IPv4 source address in + * + * Checks whether the given skb is a valid DHCP packet. And if so, stores the + * IPv4 source address in the provided buffer. + * + * Caller needs to ensure that the skb network header is set correctly. + * + * Return: If skb is a valid DHCP packet, then returns its op code + * (e.g. BOOTREPLY vs. BOOTREQUEST). Otherwise returns -EINVAL. + */ +static int +batadv_dat_check_dhcp(struct sk_buff *skb, __be16 proto, __be32 *ip_src) +{ + __be32 *magic, _magic; + unsigned int offset; + struct { + __u8 op; + __u8 htype; + __u8 hlen; + __u8 hops; + } *dhcp_h, _dhcp_h; + + if (proto != htons(ETH_P_IP)) + return -EINVAL; + + if (!batadv_dat_check_dhcp_ipudp(skb, ip_src)) + return -EINVAL; + + offset = skb_transport_offset(skb) + sizeof(struct udphdr); + if (skb->len < offset + sizeof(struct batadv_dhcp_packet)) + return -EINVAL; + + dhcp_h = skb_header_pointer(skb, offset, sizeof(_dhcp_h), &_dhcp_h); + if (!dhcp_h || dhcp_h->htype != BATADV_HTYPE_ETHERNET || + dhcp_h->hlen != ETH_ALEN) + return -EINVAL; + + offset += offsetof(struct batadv_dhcp_packet, magic); + + magic = skb_header_pointer(skb, offset, sizeof(_magic), &_magic); + if (!magic || get_unaligned(magic) != htonl(BATADV_DHCP_MAGIC)) + return -EINVAL; + + return dhcp_h->op; +} + +/** + * batadv_dat_get_dhcp_message_type() - get message type of a DHCP packet + * @skb: the DHCP packet to parse + * + * Iterates over the DHCP options of the given DHCP packet to find a + * DHCP Message Type option and parse it. + * + * Caller needs to ensure that the given skb is a valid DHCP packet and + * that the skb transport header is set correctly. + * + * Return: The found DHCP message type value, if found. -EINVAL otherwise. + */ +static int batadv_dat_get_dhcp_message_type(struct sk_buff *skb) +{ + unsigned int offset = skb_transport_offset(skb) + sizeof(struct udphdr); + u8 *type, _type; + struct { + u8 type; + u8 len; + } *tl, _tl; + + offset += sizeof(struct batadv_dhcp_packet); + + while ((tl = skb_header_pointer(skb, offset, sizeof(_tl), &_tl))) { + if (tl->type == BATADV_DHCP_OPT_MSG_TYPE) + break; + + if (tl->type == BATADV_DHCP_OPT_END) + break; + + if (tl->type == BATADV_DHCP_OPT_PAD) + offset++; + else + offset += tl->len + sizeof(_tl); + } + + /* Option Overload Code not supported */ + if (!tl || tl->type != BATADV_DHCP_OPT_MSG_TYPE || + tl->len != sizeof(_type)) + return -EINVAL; + + offset += sizeof(_tl); + + type = skb_header_pointer(skb, offset, sizeof(_type), &_type); + if (!type) + return -EINVAL; + + return *type; +} + +/** + * batadv_dat_get_dhcp_yiaddr() - get yiaddr from a DHCP packet + * @skb: the DHCP packet to parse + * @buf: a buffer to store the yiaddr in + * + * Caller needs to ensure that the given skb is a valid DHCP packet and + * that the skb transport header is set correctly. + * + * Return: True on success, false otherwise. + */ +static bool batadv_dat_dhcp_get_yiaddr(struct sk_buff *skb, __be32 *buf) +{ + unsigned int offset = skb_transport_offset(skb) + sizeof(struct udphdr); + __be32 *yiaddr; + + offset += offsetof(struct batadv_dhcp_packet, yiaddr); + yiaddr = skb_header_pointer(skb, offset, BATADV_DHCP_YIADDR_LEN, buf); + + if (!yiaddr) + return false; + + if (yiaddr != buf) + *buf = get_unaligned(yiaddr); + + return true; +} + +/** + * batadv_dat_get_dhcp_chaddr() - get chaddr from a DHCP packet + * @skb: the DHCP packet to parse + * @buf: a buffer to store the chaddr in + * + * Caller needs to ensure that the given skb is a valid DHCP packet and + * that the skb transport header is set correctly. + * + * Return: True on success, false otherwise + */ +static bool batadv_dat_get_dhcp_chaddr(struct sk_buff *skb, u8 *buf) +{ + unsigned int offset = skb_transport_offset(skb) + sizeof(struct udphdr); + u8 *chaddr; + + offset += offsetof(struct batadv_dhcp_packet, chaddr); + chaddr = skb_header_pointer(skb, offset, BATADV_DHCP_CHADDR_LEN, buf); + + if (!chaddr) + return false; + + if (chaddr != buf) + memcpy(buf, chaddr, BATADV_DHCP_CHADDR_LEN); + + return true; +} + +/** + * batadv_dat_put_dhcp() - puts addresses from a DHCP packet into the DHT and + * DAT cache + * @bat_priv: the bat priv with all the soft interface information + * @chaddr: the DHCP client MAC address + * @yiaddr: the DHCP client IP address + * @hw_dst: the DHCP server MAC address + * @ip_dst: the DHCP server IP address + * @vid: VLAN identifier + * + * Adds given MAC/IP pairs to the local DAT cache and propagates them further + * into the DHT. + * + * For the DHT propagation, client MAC + IP will appear as the ARP Reply + * transmitter (and hw_dst/ip_dst as the target). + */ +static void batadv_dat_put_dhcp(struct batadv_priv *bat_priv, u8 *chaddr, + __be32 yiaddr, u8 *hw_dst, __be32 ip_dst, + unsigned short vid) +{ + struct sk_buff *skb; + + skb = batadv_dat_arp_create_reply(bat_priv, yiaddr, ip_dst, chaddr, + hw_dst, vid); + if (!skb) + return; + + skb_set_network_header(skb, ETH_HLEN); + + batadv_dat_entry_add(bat_priv, yiaddr, chaddr, vid); + batadv_dat_entry_add(bat_priv, ip_dst, hw_dst, vid); + + batadv_dat_send_data(bat_priv, skb, yiaddr, vid, BATADV_P_DAT_DHT_PUT); + batadv_dat_send_data(bat_priv, skb, ip_dst, vid, BATADV_P_DAT_DHT_PUT); + + consume_skb(skb); + + batadv_dbg(BATADV_DBG_DAT, bat_priv, + "Snooped from outgoing DHCPACK (server address): %pI4, %pM (vid: %i)\n", + &ip_dst, hw_dst, batadv_print_vid(vid)); + batadv_dbg(BATADV_DBG_DAT, bat_priv, + "Snooped from outgoing DHCPACK (client address): %pI4, %pM (vid: %i)\n", + &yiaddr, chaddr, batadv_print_vid(vid)); +} + +/** + * batadv_dat_check_dhcp_ack() - examine packet for valid DHCP message + * @skb: the packet to check + * @proto: ethernet protocol hint (behind a potential vlan) + * @ip_src: a buffer to store the IPv4 source address in + * @chaddr: a buffer to store the DHCP Client Hardware Address in + * @yiaddr: a buffer to store the DHCP Your IP Address in + * + * Checks whether the given skb is a valid DHCPACK. And if so, stores the + * IPv4 server source address (ip_src), client MAC address (chaddr) and client + * IPv4 address (yiaddr) in the provided buffers. + * + * Caller needs to ensure that the skb network header is set correctly. + * + * Return: True if the skb is a valid DHCPACK. False otherwise. + */ +static bool +batadv_dat_check_dhcp_ack(struct sk_buff *skb, __be16 proto, __be32 *ip_src, + u8 *chaddr, __be32 *yiaddr) +{ + int type; + + type = batadv_dat_check_dhcp(skb, proto, ip_src); + if (type != BATADV_BOOTREPLY) + return false; + + type = batadv_dat_get_dhcp_message_type(skb); + if (type != BATADV_DHCPACK) + return false; + + if (!batadv_dat_dhcp_get_yiaddr(skb, yiaddr)) + return false; + + if (!batadv_dat_get_dhcp_chaddr(skb, chaddr)) + return false; + + return true; +} + +/** + * batadv_dat_snoop_outgoing_dhcp_ack() - snoop DHCPACK and fill DAT with it + * @bat_priv: the bat priv with all the soft interface information + * @skb: the packet to snoop + * @proto: ethernet protocol hint (behind a potential vlan) + * @vid: VLAN identifier + * + * This function first checks whether the given skb is a valid DHCPACK. If + * so then its source MAC and IP as well as its DHCP Client Hardware Address + * field and DHCP Your IP Address field are added to the local DAT cache and + * propagated into the DHT. + * + * Caller needs to ensure that the skb mac and network headers are set + * correctly. + */ +void batadv_dat_snoop_outgoing_dhcp_ack(struct batadv_priv *bat_priv, + struct sk_buff *skb, + __be16 proto, + unsigned short vid) +{ + u8 chaddr[BATADV_DHCP_CHADDR_LEN]; + __be32 ip_src, yiaddr; + + if (!atomic_read(&bat_priv->distributed_arp_table)) + return; + + if (!batadv_dat_check_dhcp_ack(skb, proto, &ip_src, chaddr, &yiaddr)) + return; + + batadv_dat_put_dhcp(bat_priv, chaddr, yiaddr, eth_hdr(skb)->h_source, + ip_src, vid); +} + +/** + * batadv_dat_snoop_incoming_dhcp_ack() - snoop DHCPACK and fill DAT cache + * @bat_priv: the bat priv with all the soft interface information + * @skb: the packet to snoop + * @hdr_size: header size, up to the tail of the batman-adv header + * + * This function first checks whether the given skb is a valid DHCPACK. If + * so then its source MAC and IP as well as its DHCP Client Hardware Address + * field and DHCP Your IP Address field are added to the local DAT cache. + */ +void batadv_dat_snoop_incoming_dhcp_ack(struct batadv_priv *bat_priv, + struct sk_buff *skb, int hdr_size) +{ + u8 chaddr[BATADV_DHCP_CHADDR_LEN]; + struct ethhdr *ethhdr; + __be32 ip_src, yiaddr; + unsigned short vid; + __be16 proto; + u8 *hw_src; + + if (!atomic_read(&bat_priv->distributed_arp_table)) + return; + + if (unlikely(!pskb_may_pull(skb, hdr_size + ETH_HLEN))) + return; + + ethhdr = (struct ethhdr *)(skb->data + hdr_size); + skb_set_network_header(skb, hdr_size + ETH_HLEN); + proto = ethhdr->h_proto; + + if (!batadv_dat_check_dhcp_ack(skb, proto, &ip_src, chaddr, &yiaddr)) + return; + + hw_src = ethhdr->h_source; + vid = batadv_dat_get_vid(skb, &hdr_size); + + batadv_dat_entry_add(bat_priv, yiaddr, chaddr, vid); + batadv_dat_entry_add(bat_priv, ip_src, hw_src, vid); + + batadv_dbg(BATADV_DBG_DAT, bat_priv, + "Snooped from incoming DHCPACK (server address): %pI4, %pM (vid: %i)\n", + &ip_src, hw_src, batadv_print_vid(vid)); + batadv_dbg(BATADV_DBG_DAT, bat_priv, + "Snooped from incoming DHCPACK (client address): %pI4, %pM (vid: %i)\n", + &yiaddr, chaddr, batadv_print_vid(vid)); +} + +/** * batadv_dat_drop_broadcast_packet() - check if an ARP request has to be * dropped (because the node has already obtained the reply via DAT) or not * @bat_priv: the bat priv with all the soft interface information diff --git a/net/batman-adv/distributed-arp-table.h b/net/batman-adv/distributed-arp-table.h index a04596028337..68c0ff321acd 100644 --- a/net/batman-adv/distributed-arp-table.h +++ b/net/batman-adv/distributed-arp-table.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2011-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors: * * Antonio Quartulli * @@ -46,6 +46,12 @@ void batadv_dat_snoop_outgoing_arp_reply(struct batadv_priv *bat_priv, struct sk_buff *skb); bool batadv_dat_snoop_incoming_arp_reply(struct batadv_priv *bat_priv, struct sk_buff *skb, int hdr_size); +void batadv_dat_snoop_outgoing_dhcp_ack(struct batadv_priv *bat_priv, + struct sk_buff *skb, + __be16 proto, + unsigned short vid); +void batadv_dat_snoop_incoming_dhcp_ack(struct batadv_priv *bat_priv, + struct sk_buff *skb, int hdr_size); bool batadv_dat_drop_broadcast_packet(struct batadv_priv *bat_priv, struct batadv_forw_packet *forw_packet); @@ -140,6 +146,19 @@ batadv_dat_snoop_incoming_arp_reply(struct batadv_priv *bat_priv, return false; } +static inline void +batadv_dat_snoop_outgoing_dhcp_ack(struct batadv_priv *bat_priv, + struct sk_buff *skb, __be16 proto, + unsigned short vid) +{ +} + +static inline void +batadv_dat_snoop_incoming_dhcp_ack(struct batadv_priv *bat_priv, + struct sk_buff *skb, int hdr_size) +{ +} + static inline bool batadv_dat_drop_broadcast_packet(struct batadv_priv *bat_priv, struct batadv_forw_packet *forw_packet) diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 5b71a289d04f..b506d15b8230 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2013-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2019 B.A.T.M.A.N. contributors: * * Martin Hundebøll <martin@hundeboll.net> * diff --git a/net/batman-adv/fragmentation.h b/net/batman-adv/fragmentation.h index 944512e07782..abdac26579bf 100644 --- a/net/batman-adv/fragmentation.h +++ b/net/batman-adv/fragmentation.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2013-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2019 B.A.T.M.A.N. contributors: * * Martin Hundebøll <martin@hundeboll.net> * diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 9d8e5eda2314..f5811f61aa92 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2009-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2019 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -47,7 +47,6 @@ #include <uapi/linux/batadv_packet.h> #include <uapi/linux/batman_adv.h> -#include "gateway_common.h" #include "hard-interface.h" #include "log.h" #include "netlink.h" diff --git a/net/batman-adv/gateway_client.h b/net/batman-adv/gateway_client.h index f0b86fcb2493..b5732c8be81a 100644 --- a/net/batman-adv/gateway_client.h +++ b/net/batman-adv/gateway_client.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2009-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2019 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c index 936c107f3199..e064de45e22c 100644 --- a/net/batman-adv/gateway_common.c +++ b/net/batman-adv/gateway_common.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2009-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2019 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -28,6 +28,7 @@ #include <linux/stddef.h> #include <linux/string.h> #include <uapi/linux/batadv_packet.h> +#include <uapi/linux/batman_adv.h> #include "gateway_client.h" #include "log.h" diff --git a/net/batman-adv/gateway_common.h b/net/batman-adv/gateway_common.h index 80afb2793687..128467a0fb89 100644 --- a/net/batman-adv/gateway_common.h +++ b/net/batman-adv/gateway_common.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2009-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2019 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -25,12 +25,6 @@ struct net_device; -enum batadv_gw_modes { - BATADV_GW_MODE_OFF, - BATADV_GW_MODE_CLIENT, - BATADV_GW_MODE_SERVER, -}; - /** * enum batadv_bandwidth_units - bandwidth unit types */ diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 508f4416dfc9..96ef7c70b4d9 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -20,7 +20,6 @@ #include "main.h" #include <linux/atomic.h> -#include <linux/bug.h> #include <linux/byteorder/generic.h> #include <linux/errno.h> #include <linux/gfp.h> @@ -179,8 +178,10 @@ static bool batadv_is_on_batman_iface(const struct net_device *net_dev) parent_dev = __dev_get_by_index((struct net *)parent_net, dev_get_iflink(net_dev)); /* if we got a NULL parent_dev there is something broken.. */ - if (WARN(!parent_dev, "Cannot find parent device")) + if (!parent_dev) { + pr_err("Cannot find parent device\n"); return false; + } if (batadv_mutual_parents(net_dev, net, parent_dev, parent_net)) return false; diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index d1c0f6189301..48de28c83401 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/hash.c b/net/batman-adv/hash.c index 9194f4d891b1..56a08ce193d5 100644 --- a/net/batman-adv/hash.c +++ b/net/batman-adv/hash.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2006-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2019 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/hash.h b/net/batman-adv/hash.h index 0e36fa1c7c3e..37507b6d4006 100644 --- a/net/batman-adv/hash.h +++ b/net/batman-adv/hash.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2006-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2019 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner * diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c index 6d5859714f52..9859ababb82e 100644 --- a/net/batman-adv/icmp_socket.c +++ b/net/batman-adv/icmp_socket.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/icmp_socket.h b/net/batman-adv/icmp_socket.h index 958be22beda9..5f8926522ff0 100644 --- a/net/batman-adv/icmp_socket.h +++ b/net/batman-adv/icmp_socket.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/log.c b/net/batman-adv/log.c index 75f602e1ce94..3e610df8debf 100644 --- a/net/batman-adv/log.c +++ b/net/batman-adv/log.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2010-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/log.h b/net/batman-adv/log.h index 35f4f397ed57..660e9bcc85a2 100644 --- a/net/batman-adv/log.h +++ b/net/batman-adv/log.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index d1ed839fd32b..75750870cf04 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index b572066325e4..3ed669d7dc6b 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -25,7 +25,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2019.0" +#define BATADV_SOURCE_VERSION "2019.1" #endif /* B.A.T.M.A.N. parameters */ diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index 1dd70f048e7b..f91b1b6265cf 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2014-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2014-2019 B.A.T.M.A.N. contributors: * * Linus Lüssing * diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h index 3b04ab13f0eb..466013fe88af 100644 --- a/net/batman-adv/multicast.h +++ b/net/batman-adv/multicast.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2014-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2014-2019 B.A.T.M.A.N. contributors: * * Linus Lüssing * diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index 2dc3304cee54..67a58da2e6a0 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2016-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2016-2019 B.A.T.M.A.N. contributors: * * Matthias Schiffer * @@ -20,13 +20,17 @@ #include "main.h" #include <linux/atomic.h> +#include <linux/bitops.h> +#include <linux/bug.h> #include <linux/byteorder/generic.h> #include <linux/cache.h> +#include <linux/err.h> #include <linux/errno.h> #include <linux/export.h> #include <linux/genetlink.h> #include <linux/gfp.h> #include <linux/if_ether.h> +#include <linux/if_vlan.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/list.h> @@ -47,21 +51,54 @@ #include "bridge_loop_avoidance.h" #include "distributed-arp-table.h" #include "gateway_client.h" +#include "gateway_common.h" #include "hard-interface.h" +#include "log.h" #include "multicast.h" +#include "network-coding.h" #include "originator.h" #include "soft-interface.h" #include "tp_meter.h" #include "translation-table.h" +struct net; + struct genl_family batadv_netlink_family; /* multicast groups */ enum batadv_netlink_multicast_groups { + BATADV_NL_MCGRP_CONFIG, BATADV_NL_MCGRP_TPMETER, }; +/** + * enum batadv_genl_ops_flags - flags for genl_ops's internal_flags + */ +enum batadv_genl_ops_flags { + /** + * @BATADV_FLAG_NEED_MESH: request requires valid soft interface in + * attribute BATADV_ATTR_MESH_IFINDEX and expects a pointer to it to be + * saved in info->user_ptr[0] + */ + BATADV_FLAG_NEED_MESH = BIT(0), + + /** + * @BATADV_FLAG_NEED_HARDIF: request requires valid hard interface in + * attribute BATADV_ATTR_HARD_IFINDEX and expects a pointer to it to be + * saved in info->user_ptr[1] + */ + BATADV_FLAG_NEED_HARDIF = BIT(1), + + /** + * @BATADV_FLAG_NEED_VLAN: request requires valid vlan in + * attribute BATADV_ATTR_VLANID and expects a pointer to it to be + * saved in info->user_ptr[1] + */ + BATADV_FLAG_NEED_VLAN = BIT(2), +}; + static const struct genl_multicast_group batadv_netlink_mcgrps[] = { + [BATADV_NL_MCGRP_CONFIG] = { .name = BATADV_NL_MCAST_GROUP_CONFIG }, [BATADV_NL_MCGRP_TPMETER] = { .name = BATADV_NL_MCAST_GROUP_TPMETER }, }; @@ -104,6 +141,26 @@ static const struct nla_policy batadv_netlink_policy[NUM_BATADV_ATTR] = { [BATADV_ATTR_DAT_CACHE_VID] = { .type = NLA_U16 }, [BATADV_ATTR_MCAST_FLAGS] = { .type = NLA_U32 }, [BATADV_ATTR_MCAST_FLAGS_PRIV] = { .type = NLA_U32 }, + [BATADV_ATTR_VLANID] = { .type = NLA_U16 }, + [BATADV_ATTR_AGGREGATED_OGMS_ENABLED] = { .type = NLA_U8 }, + [BATADV_ATTR_AP_ISOLATION_ENABLED] = { .type = NLA_U8 }, + [BATADV_ATTR_ISOLATION_MARK] = { .type = NLA_U32 }, + [BATADV_ATTR_ISOLATION_MASK] = { .type = NLA_U32 }, + [BATADV_ATTR_BONDING_ENABLED] = { .type = NLA_U8 }, + [BATADV_ATTR_BRIDGE_LOOP_AVOIDANCE_ENABLED] = { .type = NLA_U8 }, + [BATADV_ATTR_DISTRIBUTED_ARP_TABLE_ENABLED] = { .type = NLA_U8 }, + [BATADV_ATTR_FRAGMENTATION_ENABLED] = { .type = NLA_U8 }, + [BATADV_ATTR_GW_BANDWIDTH_DOWN] = { .type = NLA_U32 }, + [BATADV_ATTR_GW_BANDWIDTH_UP] = { .type = NLA_U32 }, + [BATADV_ATTR_GW_MODE] = { .type = NLA_U8 }, + [BATADV_ATTR_GW_SEL_CLASS] = { .type = NLA_U32 }, + [BATADV_ATTR_HOP_PENALTY] = { .type = NLA_U8 }, + [BATADV_ATTR_LOG_LEVEL] = { .type = NLA_U32 }, + [BATADV_ATTR_MULTICAST_FORCEFLOOD_ENABLED] = { .type = NLA_U8 }, + [BATADV_ATTR_NETWORK_CODING_ENABLED] = { .type = NLA_U8 }, + [BATADV_ATTR_ORIG_INTERVAL] = { .type = NLA_U32 }, + [BATADV_ATTR_ELP_INTERVAL] = { .type = NLA_U32 }, + [BATADV_ATTR_THROUGHPUT_OVERRIDE] = { .type = NLA_U32 }, }; /** @@ -122,20 +179,75 @@ batadv_netlink_get_ifindex(const struct nlmsghdr *nlh, int attrtype) } /** - * batadv_netlink_mesh_info_put() - fill in generic information about mesh - * interface - * @msg: netlink message to be sent back - * @soft_iface: interface for which the data should be taken + * batadv_netlink_mesh_fill_ap_isolation() - Add ap_isolation softif attribute + * @msg: Netlink message to dump into + * @bat_priv: the bat priv with all the soft interface information * - * Return: 0 on success, < 0 on error + * Return: 0 on success or negative error number in case of failure */ -static int -batadv_netlink_mesh_info_put(struct sk_buff *msg, struct net_device *soft_iface) +static int batadv_netlink_mesh_fill_ap_isolation(struct sk_buff *msg, + struct batadv_priv *bat_priv) +{ + struct batadv_softif_vlan *vlan; + u8 ap_isolation; + + vlan = batadv_softif_vlan_get(bat_priv, BATADV_NO_FLAGS); + if (!vlan) + return 0; + + ap_isolation = atomic_read(&vlan->ap_isolation); + batadv_softif_vlan_put(vlan); + + return nla_put_u8(msg, BATADV_ATTR_AP_ISOLATION_ENABLED, + !!ap_isolation); +} + +/** + * batadv_option_set_ap_isolation() - Set ap_isolation from genl msg + * @attr: parsed BATADV_ATTR_AP_ISOLATION_ENABLED attribute + * @bat_priv: the bat priv with all the soft interface information + * + * Return: 0 on success or negative error number in case of failure + */ +static int batadv_netlink_set_mesh_ap_isolation(struct nlattr *attr, + struct batadv_priv *bat_priv) +{ + struct batadv_softif_vlan *vlan; + + vlan = batadv_softif_vlan_get(bat_priv, BATADV_NO_FLAGS); + if (!vlan) + return -ENOENT; + + atomic_set(&vlan->ap_isolation, !!nla_get_u8(attr)); + batadv_softif_vlan_put(vlan); + + return 0; +} + +/** + * batadv_netlink_mesh_fill() - Fill message with mesh attributes + * @msg: Netlink message to dump into + * @bat_priv: the bat priv with all the soft interface information + * @cmd: type of message to generate + * @portid: Port making netlink request + * @seq: sequence number for message + * @flags: Additional flags for message + * + * Return: 0 on success or negative error number in case of failure + */ +static int batadv_netlink_mesh_fill(struct sk_buff *msg, + struct batadv_priv *bat_priv, + enum batadv_nl_commands cmd, + u32 portid, u32 seq, int flags) { - struct batadv_priv *bat_priv = netdev_priv(soft_iface); + struct net_device *soft_iface = bat_priv->soft_iface; struct batadv_hard_iface *primary_if = NULL; struct net_device *hard_iface; - int ret = -ENOBUFS; + void *hdr; + + hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, flags, cmd); + if (!hdr) + return -ENOBUFS; if (nla_put_string(msg, BATADV_ATTR_VERSION, BATADV_SOURCE_VERSION) || nla_put_string(msg, BATADV_ATTR_ALGO_NAME, @@ -146,16 +258,16 @@ batadv_netlink_mesh_info_put(struct sk_buff *msg, struct net_device *soft_iface) soft_iface->dev_addr) || nla_put_u8(msg, BATADV_ATTR_TT_TTVN, (u8)atomic_read(&bat_priv->tt.vn))) - goto out; + goto nla_put_failure; #ifdef CONFIG_BATMAN_ADV_BLA if (nla_put_u16(msg, BATADV_ATTR_BLA_CRC, ntohs(bat_priv->bla.claim_dest.group))) - goto out; + goto nla_put_failure; #endif if (batadv_mcast_mesh_info_put(msg, bat_priv)) - goto out; + goto nla_put_failure; primary_if = batadv_primary_if_get_selected(bat_priv); if (primary_if && primary_if->if_status == BATADV_IF_ACTIVE) { @@ -167,77 +279,345 @@ batadv_netlink_mesh_info_put(struct sk_buff *msg, struct net_device *soft_iface) hard_iface->name) || nla_put(msg, BATADV_ATTR_HARD_ADDRESS, ETH_ALEN, hard_iface->dev_addr)) - goto out; + goto nla_put_failure; } - ret = 0; + if (nla_put_u8(msg, BATADV_ATTR_AGGREGATED_OGMS_ENABLED, + !!atomic_read(&bat_priv->aggregated_ogms))) + goto nla_put_failure; + + if (batadv_netlink_mesh_fill_ap_isolation(msg, bat_priv)) + goto nla_put_failure; + + if (nla_put_u32(msg, BATADV_ATTR_ISOLATION_MARK, + bat_priv->isolation_mark)) + goto nla_put_failure; + + if (nla_put_u32(msg, BATADV_ATTR_ISOLATION_MASK, + bat_priv->isolation_mark_mask)) + goto nla_put_failure; + + if (nla_put_u8(msg, BATADV_ATTR_BONDING_ENABLED, + !!atomic_read(&bat_priv->bonding))) + goto nla_put_failure; + +#ifdef CONFIG_BATMAN_ADV_BLA + if (nla_put_u8(msg, BATADV_ATTR_BRIDGE_LOOP_AVOIDANCE_ENABLED, + !!atomic_read(&bat_priv->bridge_loop_avoidance))) + goto nla_put_failure; +#endif /* CONFIG_BATMAN_ADV_BLA */ + +#ifdef CONFIG_BATMAN_ADV_DAT + if (nla_put_u8(msg, BATADV_ATTR_DISTRIBUTED_ARP_TABLE_ENABLED, + !!atomic_read(&bat_priv->distributed_arp_table))) + goto nla_put_failure; +#endif /* CONFIG_BATMAN_ADV_DAT */ + + if (nla_put_u8(msg, BATADV_ATTR_FRAGMENTATION_ENABLED, + !!atomic_read(&bat_priv->fragmentation))) + goto nla_put_failure; + + if (nla_put_u32(msg, BATADV_ATTR_GW_BANDWIDTH_DOWN, + atomic_read(&bat_priv->gw.bandwidth_down))) + goto nla_put_failure; + + if (nla_put_u32(msg, BATADV_ATTR_GW_BANDWIDTH_UP, + atomic_read(&bat_priv->gw.bandwidth_up))) + goto nla_put_failure; + + if (nla_put_u8(msg, BATADV_ATTR_GW_MODE, + atomic_read(&bat_priv->gw.mode))) + goto nla_put_failure; + + if (bat_priv->algo_ops->gw.get_best_gw_node && + bat_priv->algo_ops->gw.is_eligible) { + /* GW selection class is not available if the routing algorithm + * in use does not implement the GW API + */ + if (nla_put_u32(msg, BATADV_ATTR_GW_SEL_CLASS, + atomic_read(&bat_priv->gw.sel_class))) + goto nla_put_failure; + } + + if (nla_put_u8(msg, BATADV_ATTR_HOP_PENALTY, + atomic_read(&bat_priv->hop_penalty))) + goto nla_put_failure; + +#ifdef CONFIG_BATMAN_ADV_DEBUG + if (nla_put_u32(msg, BATADV_ATTR_LOG_LEVEL, + atomic_read(&bat_priv->log_level))) + goto nla_put_failure; +#endif /* CONFIG_BATMAN_ADV_DEBUG */ + +#ifdef CONFIG_BATMAN_ADV_MCAST + if (nla_put_u8(msg, BATADV_ATTR_MULTICAST_FORCEFLOOD_ENABLED, + !atomic_read(&bat_priv->multicast_mode))) + goto nla_put_failure; +#endif /* CONFIG_BATMAN_ADV_MCAST */ + +#ifdef CONFIG_BATMAN_ADV_NC + if (nla_put_u8(msg, BATADV_ATTR_NETWORK_CODING_ENABLED, + !!atomic_read(&bat_priv->network_coding))) + goto nla_put_failure; +#endif /* CONFIG_BATMAN_ADV_NC */ + + if (nla_put_u32(msg, BATADV_ATTR_ORIG_INTERVAL, + atomic_read(&bat_priv->orig_interval))) + goto nla_put_failure; - out: if (primary_if) batadv_hardif_put(primary_if); - return ret; + genlmsg_end(msg, hdr); + return 0; + +nla_put_failure: + if (primary_if) + batadv_hardif_put(primary_if); + + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; } /** - * batadv_netlink_get_mesh_info() - handle incoming BATADV_CMD_GET_MESH_INFO - * netlink request - * @skb: received netlink message - * @info: receiver information + * batadv_netlink_notify_mesh() - send softif attributes to listener + * @bat_priv: the bat priv with all the soft interface information * * Return: 0 on success, < 0 on error */ -static int -batadv_netlink_get_mesh_info(struct sk_buff *skb, struct genl_info *info) +int batadv_netlink_notify_mesh(struct batadv_priv *bat_priv) { - struct net *net = genl_info_net(info); - struct net_device *soft_iface; - struct sk_buff *msg = NULL; - void *msg_head; - int ifindex; + struct sk_buff *msg; int ret; - if (!info->attrs[BATADV_ATTR_MESH_IFINDEX]) - return -EINVAL; - - ifindex = nla_get_u32(info->attrs[BATADV_ATTR_MESH_IFINDEX]); - if (!ifindex) - return -EINVAL; + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; - soft_iface = dev_get_by_index(net, ifindex); - if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { - ret = -ENODEV; - goto out; + ret = batadv_netlink_mesh_fill(msg, bat_priv, BATADV_CMD_SET_MESH, + 0, 0, 0); + if (ret < 0) { + nlmsg_free(msg); + return ret; } + genlmsg_multicast_netns(&batadv_netlink_family, + dev_net(bat_priv->soft_iface), msg, 0, + BATADV_NL_MCGRP_CONFIG, GFP_KERNEL); + + return 0; +} + +/** + * batadv_netlink_get_mesh() - Get softif attributes + * @skb: Netlink message with request data + * @info: receiver information + * + * Return: 0 on success or negative error number in case of failure + */ +static int batadv_netlink_get_mesh(struct sk_buff *skb, struct genl_info *info) +{ + struct batadv_priv *bat_priv = info->user_ptr[0]; + struct sk_buff *msg; + int ret; + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) { - ret = -ENOMEM; - goto out; + if (!msg) + return -ENOMEM; + + ret = batadv_netlink_mesh_fill(msg, bat_priv, BATADV_CMD_GET_MESH, + info->snd_portid, info->snd_seq, 0); + if (ret < 0) { + nlmsg_free(msg); + return ret; } - msg_head = genlmsg_put(msg, info->snd_portid, info->snd_seq, - &batadv_netlink_family, 0, - BATADV_CMD_GET_MESH_INFO); - if (!msg_head) { - ret = -ENOBUFS; - goto out; + ret = genlmsg_reply(msg, info); + + return ret; +} + +/** + * batadv_netlink_set_mesh() - Set softif attributes + * @skb: Netlink message with request data + * @info: receiver information + * + * Return: 0 on success or negative error number in case of failure + */ +static int batadv_netlink_set_mesh(struct sk_buff *skb, struct genl_info *info) +{ + struct batadv_priv *bat_priv = info->user_ptr[0]; + struct nlattr *attr; + + if (info->attrs[BATADV_ATTR_AGGREGATED_OGMS_ENABLED]) { + attr = info->attrs[BATADV_ATTR_AGGREGATED_OGMS_ENABLED]; + + atomic_set(&bat_priv->aggregated_ogms, !!nla_get_u8(attr)); } - ret = batadv_netlink_mesh_info_put(msg, soft_iface); + if (info->attrs[BATADV_ATTR_AP_ISOLATION_ENABLED]) { + attr = info->attrs[BATADV_ATTR_AP_ISOLATION_ENABLED]; - out: - if (soft_iface) - dev_put(soft_iface); + batadv_netlink_set_mesh_ap_isolation(attr, bat_priv); + } - if (ret) { - if (msg) - nlmsg_free(msg); - return ret; + if (info->attrs[BATADV_ATTR_ISOLATION_MARK]) { + attr = info->attrs[BATADV_ATTR_ISOLATION_MARK]; + + bat_priv->isolation_mark = nla_get_u32(attr); } - genlmsg_end(msg, msg_head); - return genlmsg_reply(msg, info); + if (info->attrs[BATADV_ATTR_ISOLATION_MASK]) { + attr = info->attrs[BATADV_ATTR_ISOLATION_MASK]; + + bat_priv->isolation_mark_mask = nla_get_u32(attr); + } + + if (info->attrs[BATADV_ATTR_BONDING_ENABLED]) { + attr = info->attrs[BATADV_ATTR_BONDING_ENABLED]; + + atomic_set(&bat_priv->bonding, !!nla_get_u8(attr)); + } + +#ifdef CONFIG_BATMAN_ADV_BLA + if (info->attrs[BATADV_ATTR_BRIDGE_LOOP_AVOIDANCE_ENABLED]) { + attr = info->attrs[BATADV_ATTR_BRIDGE_LOOP_AVOIDANCE_ENABLED]; + + atomic_set(&bat_priv->bridge_loop_avoidance, + !!nla_get_u8(attr)); + batadv_bla_status_update(bat_priv->soft_iface); + } +#endif /* CONFIG_BATMAN_ADV_BLA */ + +#ifdef CONFIG_BATMAN_ADV_DAT + if (info->attrs[BATADV_ATTR_DISTRIBUTED_ARP_TABLE_ENABLED]) { + attr = info->attrs[BATADV_ATTR_DISTRIBUTED_ARP_TABLE_ENABLED]; + + atomic_set(&bat_priv->distributed_arp_table, + !!nla_get_u8(attr)); + batadv_dat_status_update(bat_priv->soft_iface); + } +#endif /* CONFIG_BATMAN_ADV_DAT */ + + if (info->attrs[BATADV_ATTR_FRAGMENTATION_ENABLED]) { + attr = info->attrs[BATADV_ATTR_FRAGMENTATION_ENABLED]; + + atomic_set(&bat_priv->fragmentation, !!nla_get_u8(attr)); + batadv_update_min_mtu(bat_priv->soft_iface); + } + + if (info->attrs[BATADV_ATTR_GW_BANDWIDTH_DOWN]) { + attr = info->attrs[BATADV_ATTR_GW_BANDWIDTH_DOWN]; + + atomic_set(&bat_priv->gw.bandwidth_down, nla_get_u32(attr)); + batadv_gw_tvlv_container_update(bat_priv); + } + + if (info->attrs[BATADV_ATTR_GW_BANDWIDTH_UP]) { + attr = info->attrs[BATADV_ATTR_GW_BANDWIDTH_UP]; + + atomic_set(&bat_priv->gw.bandwidth_up, nla_get_u32(attr)); + batadv_gw_tvlv_container_update(bat_priv); + } + + if (info->attrs[BATADV_ATTR_GW_MODE]) { + u8 gw_mode; + + attr = info->attrs[BATADV_ATTR_GW_MODE]; + gw_mode = nla_get_u8(attr); + + if (gw_mode <= BATADV_GW_MODE_SERVER) { + /* Invoking batadv_gw_reselect() is not enough to really + * de-select the current GW. It will only instruct the + * gateway client code to perform a re-election the next + * time that this is needed. + * + * When gw client mode is being switched off the current + * GW must be de-selected explicitly otherwise no GW_ADD + * uevent is thrown on client mode re-activation. This + * is operation is performed in + * batadv_gw_check_client_stop(). + */ + batadv_gw_reselect(bat_priv); + + /* always call batadv_gw_check_client_stop() before + * changing the gateway state + */ + batadv_gw_check_client_stop(bat_priv); + atomic_set(&bat_priv->gw.mode, gw_mode); + batadv_gw_tvlv_container_update(bat_priv); + } + } + + if (info->attrs[BATADV_ATTR_GW_SEL_CLASS] && + bat_priv->algo_ops->gw.get_best_gw_node && + bat_priv->algo_ops->gw.is_eligible) { + /* setting the GW selection class is allowed only if the routing + * algorithm in use implements the GW API + */ + + u32 sel_class_max = 0xffffffffu; + u32 sel_class; + + attr = info->attrs[BATADV_ATTR_GW_SEL_CLASS]; + sel_class = nla_get_u32(attr); + + if (!bat_priv->algo_ops->gw.store_sel_class) + sel_class_max = BATADV_TQ_MAX_VALUE; + + if (sel_class >= 1 && sel_class <= sel_class_max) { + atomic_set(&bat_priv->gw.sel_class, sel_class); + batadv_gw_reselect(bat_priv); + } + } + + if (info->attrs[BATADV_ATTR_HOP_PENALTY]) { + attr = info->attrs[BATADV_ATTR_HOP_PENALTY]; + + atomic_set(&bat_priv->hop_penalty, nla_get_u8(attr)); + } + +#ifdef CONFIG_BATMAN_ADV_DEBUG + if (info->attrs[BATADV_ATTR_LOG_LEVEL]) { + attr = info->attrs[BATADV_ATTR_LOG_LEVEL]; + + atomic_set(&bat_priv->log_level, + nla_get_u32(attr) & BATADV_DBG_ALL); + } +#endif /* CONFIG_BATMAN_ADV_DEBUG */ + +#ifdef CONFIG_BATMAN_ADV_MCAST + if (info->attrs[BATADV_ATTR_MULTICAST_FORCEFLOOD_ENABLED]) { + attr = info->attrs[BATADV_ATTR_MULTICAST_FORCEFLOOD_ENABLED]; + + atomic_set(&bat_priv->multicast_mode, !nla_get_u8(attr)); + } +#endif /* CONFIG_BATMAN_ADV_MCAST */ + +#ifdef CONFIG_BATMAN_ADV_NC + if (info->attrs[BATADV_ATTR_NETWORK_CODING_ENABLED]) { + attr = info->attrs[BATADV_ATTR_NETWORK_CODING_ENABLED]; + + atomic_set(&bat_priv->network_coding, !!nla_get_u8(attr)); + batadv_nc_status_update(bat_priv->soft_iface); + } +#endif /* CONFIG_BATMAN_ADV_NC */ + + if (info->attrs[BATADV_ATTR_ORIG_INTERVAL]) { + u32 orig_interval; + + attr = info->attrs[BATADV_ATTR_ORIG_INTERVAL]; + orig_interval = nla_get_u32(attr); + + orig_interval = min_t(u32, orig_interval, INT_MAX); + orig_interval = max_t(u32, orig_interval, 2 * BATADV_JITTER); + + atomic_set(&bat_priv->orig_interval, orig_interval); + } + + batadv_netlink_notify_mesh(bat_priv); + + return 0; } /** @@ -329,40 +709,24 @@ err_genlmsg: static int batadv_netlink_tp_meter_start(struct sk_buff *skb, struct genl_info *info) { - struct net *net = genl_info_net(info); - struct net_device *soft_iface; - struct batadv_priv *bat_priv; + struct batadv_priv *bat_priv = info->user_ptr[0]; struct sk_buff *msg = NULL; u32 test_length; void *msg_head; - int ifindex; u32 cookie; u8 *dst; int ret; - if (!info->attrs[BATADV_ATTR_MESH_IFINDEX]) - return -EINVAL; - if (!info->attrs[BATADV_ATTR_ORIG_ADDRESS]) return -EINVAL; if (!info->attrs[BATADV_ATTR_TPMETER_TEST_TIME]) return -EINVAL; - ifindex = nla_get_u32(info->attrs[BATADV_ATTR_MESH_IFINDEX]); - if (!ifindex) - return -EINVAL; - dst = nla_data(info->attrs[BATADV_ATTR_ORIG_ADDRESS]); test_length = nla_get_u32(info->attrs[BATADV_ATTR_TPMETER_TEST_TIME]); - soft_iface = dev_get_by_index(net, ifindex); - if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { - ret = -ENODEV; - goto out; - } - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { ret = -ENOMEM; @@ -377,15 +741,11 @@ batadv_netlink_tp_meter_start(struct sk_buff *skb, struct genl_info *info) goto out; } - bat_priv = netdev_priv(soft_iface); batadv_tp_start(bat_priv, dst, test_length, &cookie); ret = batadv_netlink_tp_meter_put(msg, cookie); out: - if (soft_iface) - dev_put(soft_iface); - if (ret) { if (msg) nlmsg_free(msg); @@ -406,65 +766,53 @@ batadv_netlink_tp_meter_start(struct sk_buff *skb, struct genl_info *info) static int batadv_netlink_tp_meter_cancel(struct sk_buff *skb, struct genl_info *info) { - struct net *net = genl_info_net(info); - struct net_device *soft_iface; - struct batadv_priv *bat_priv; - int ifindex; + struct batadv_priv *bat_priv = info->user_ptr[0]; u8 *dst; int ret = 0; - if (!info->attrs[BATADV_ATTR_MESH_IFINDEX]) - return -EINVAL; - if (!info->attrs[BATADV_ATTR_ORIG_ADDRESS]) return -EINVAL; - ifindex = nla_get_u32(info->attrs[BATADV_ATTR_MESH_IFINDEX]); - if (!ifindex) - return -EINVAL; - dst = nla_data(info->attrs[BATADV_ATTR_ORIG_ADDRESS]); - soft_iface = dev_get_by_index(net, ifindex); - if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { - ret = -ENODEV; - goto out; - } - - bat_priv = netdev_priv(soft_iface); batadv_tp_stop(bat_priv, dst, BATADV_TP_REASON_CANCEL); -out: - if (soft_iface) - dev_put(soft_iface); - return ret; } /** - * batadv_netlink_dump_hardif_entry() - Dump one hard interface into a message + * batadv_netlink_hardif_fill() - Fill message with hardif attributes * @msg: Netlink message to dump into + * @bat_priv: the bat priv with all the soft interface information + * @hard_iface: hard interface which was modified + * @cmd: type of message to generate * @portid: Port making netlink request + * @seq: sequence number for message + * @flags: Additional flags for message * @cb: Control block containing additional options - * @hard_iface: Hard interface to dump * - * Return: error code, or 0 on success + * Return: 0 on success or negative error number in case of failure */ -static int -batadv_netlink_dump_hardif_entry(struct sk_buff *msg, u32 portid, - struct netlink_callback *cb, - struct batadv_hard_iface *hard_iface) +static int batadv_netlink_hardif_fill(struct sk_buff *msg, + struct batadv_priv *bat_priv, + struct batadv_hard_iface *hard_iface, + enum batadv_nl_commands cmd, + u32 portid, u32 seq, int flags, + struct netlink_callback *cb) { struct net_device *net_dev = hard_iface->net_dev; void *hdr; - hdr = genlmsg_put(msg, portid, cb->nlh->nlmsg_seq, - &batadv_netlink_family, NLM_F_MULTI, - BATADV_CMD_GET_HARDIFS); + hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, flags, cmd); if (!hdr) - return -EMSGSIZE; + return -ENOBUFS; + + if (cb) + genl_dump_check_consistent(cb, hdr); - genl_dump_check_consistent(cb, hdr); + if (nla_put_u32(msg, BATADV_ATTR_MESH_IFINDEX, + bat_priv->soft_iface->ifindex)) + goto nla_put_failure; if (nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX, net_dev->ifindex) || @@ -479,27 +827,137 @@ batadv_netlink_dump_hardif_entry(struct sk_buff *msg, u32 portid, goto nla_put_failure; } +#ifdef CONFIG_BATMAN_ADV_BATMAN_V + if (nla_put_u32(msg, BATADV_ATTR_ELP_INTERVAL, + atomic_read(&hard_iface->bat_v.elp_interval))) + goto nla_put_failure; + + if (nla_put_u32(msg, BATADV_ATTR_THROUGHPUT_OVERRIDE, + atomic_read(&hard_iface->bat_v.throughput_override))) + goto nla_put_failure; +#endif /* CONFIG_BATMAN_ADV_BATMAN_V */ + genlmsg_end(msg, hdr); return 0; - nla_put_failure: +nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } /** - * batadv_netlink_dump_hardifs() - Dump all hard interface into a messages + * batadv_netlink_notify_hardif() - send hardif attributes to listener + * @bat_priv: the bat priv with all the soft interface information + * @hard_iface: hard interface which was modified + * + * Return: 0 on success, < 0 on error + */ +int batadv_netlink_notify_hardif(struct batadv_priv *bat_priv, + struct batadv_hard_iface *hard_iface) +{ + struct sk_buff *msg; + int ret; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + ret = batadv_netlink_hardif_fill(msg, bat_priv, hard_iface, + BATADV_CMD_SET_HARDIF, 0, 0, 0, NULL); + if (ret < 0) { + nlmsg_free(msg); + return ret; + } + + genlmsg_multicast_netns(&batadv_netlink_family, + dev_net(bat_priv->soft_iface), msg, 0, + BATADV_NL_MCGRP_CONFIG, GFP_KERNEL); + + return 0; +} + +/** + * batadv_netlink_get_hardif() - Get hardif attributes + * @skb: Netlink message with request data + * @info: receiver information + * + * Return: 0 on success or negative error number in case of failure + */ +static int batadv_netlink_get_hardif(struct sk_buff *skb, + struct genl_info *info) +{ + struct batadv_hard_iface *hard_iface = info->user_ptr[1]; + struct batadv_priv *bat_priv = info->user_ptr[0]; + struct sk_buff *msg; + int ret; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + ret = batadv_netlink_hardif_fill(msg, bat_priv, hard_iface, + BATADV_CMD_GET_HARDIF, + info->snd_portid, info->snd_seq, 0, + NULL); + if (ret < 0) { + nlmsg_free(msg); + return ret; + } + + ret = genlmsg_reply(msg, info); + + return ret; +} + +/** + * batadv_netlink_set_hardif() - Set hardif attributes + * @skb: Netlink message with request data + * @info: receiver information + * + * Return: 0 on success or negative error number in case of failure + */ +static int batadv_netlink_set_hardif(struct sk_buff *skb, + struct genl_info *info) +{ + struct batadv_hard_iface *hard_iface = info->user_ptr[1]; + struct batadv_priv *bat_priv = info->user_ptr[0]; + +#ifdef CONFIG_BATMAN_ADV_BATMAN_V + struct nlattr *attr; + + if (info->attrs[BATADV_ATTR_ELP_INTERVAL]) { + attr = info->attrs[BATADV_ATTR_ELP_INTERVAL]; + + atomic_set(&hard_iface->bat_v.elp_interval, nla_get_u32(attr)); + } + + if (info->attrs[BATADV_ATTR_THROUGHPUT_OVERRIDE]) { + attr = info->attrs[BATADV_ATTR_THROUGHPUT_OVERRIDE]; + + atomic_set(&hard_iface->bat_v.throughput_override, + nla_get_u32(attr)); + } +#endif /* CONFIG_BATMAN_ADV_BATMAN_V */ + + batadv_netlink_notify_hardif(bat_priv, hard_iface); + + return 0; +} + +/** + * batadv_netlink_dump_hardif() - Dump all hard interface into a messages * @msg: Netlink message to dump into * @cb: Parameters from query * * Return: error code, or length of reply message on success */ static int -batadv_netlink_dump_hardifs(struct sk_buff *msg, struct netlink_callback *cb) +batadv_netlink_dump_hardif(struct sk_buff *msg, struct netlink_callback *cb) { struct net *net = sock_net(cb->skb->sk); struct net_device *soft_iface; struct batadv_hard_iface *hard_iface; + struct batadv_priv *bat_priv; int ifindex; int portid = NETLINK_CB(cb->skb).portid; int skip = cb->args[0]; @@ -519,6 +977,8 @@ batadv_netlink_dump_hardifs(struct sk_buff *msg, struct netlink_callback *cb) return -ENODEV; } + bat_priv = netdev_priv(soft_iface); + rtnl_lock(); cb->seq = batadv_hardif_generation << 1 | 1; @@ -529,8 +989,10 @@ batadv_netlink_dump_hardifs(struct sk_buff *msg, struct netlink_callback *cb) if (i++ < skip) continue; - if (batadv_netlink_dump_hardif_entry(msg, portid, cb, - hard_iface)) { + if (batadv_netlink_hardif_fill(msg, bat_priv, hard_iface, + BATADV_CMD_GET_HARDIF, + portid, cb->nlh->nlmsg_seq, + NLM_F_MULTI, cb)) { i--; break; } @@ -545,24 +1007,361 @@ batadv_netlink_dump_hardifs(struct sk_buff *msg, struct netlink_callback *cb) return msg->len; } +/** + * batadv_netlink_vlan_fill() - Fill message with vlan attributes + * @msg: Netlink message to dump into + * @bat_priv: the bat priv with all the soft interface information + * @vlan: vlan which was modified + * @cmd: type of message to generate + * @portid: Port making netlink request + * @seq: sequence number for message + * @flags: Additional flags for message + * + * Return: 0 on success or negative error number in case of failure + */ +static int batadv_netlink_vlan_fill(struct sk_buff *msg, + struct batadv_priv *bat_priv, + struct batadv_softif_vlan *vlan, + enum batadv_nl_commands cmd, + u32 portid, u32 seq, int flags) +{ + void *hdr; + + hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, flags, cmd); + if (!hdr) + return -ENOBUFS; + + if (nla_put_u32(msg, BATADV_ATTR_MESH_IFINDEX, + bat_priv->soft_iface->ifindex)) + goto nla_put_failure; + + if (nla_put_u32(msg, BATADV_ATTR_VLANID, vlan->vid & VLAN_VID_MASK)) + goto nla_put_failure; + + if (nla_put_u8(msg, BATADV_ATTR_AP_ISOLATION_ENABLED, + !!atomic_read(&vlan->ap_isolation))) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +/** + * batadv_netlink_notify_vlan() - send vlan attributes to listener + * @bat_priv: the bat priv with all the soft interface information + * @vlan: vlan which was modified + * + * Return: 0 on success, < 0 on error + */ +int batadv_netlink_notify_vlan(struct batadv_priv *bat_priv, + struct batadv_softif_vlan *vlan) +{ + struct sk_buff *msg; + int ret; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + ret = batadv_netlink_vlan_fill(msg, bat_priv, vlan, + BATADV_CMD_SET_VLAN, 0, 0, 0); + if (ret < 0) { + nlmsg_free(msg); + return ret; + } + + genlmsg_multicast_netns(&batadv_netlink_family, + dev_net(bat_priv->soft_iface), msg, 0, + BATADV_NL_MCGRP_CONFIG, GFP_KERNEL); + + return 0; +} + +/** + * batadv_netlink_get_vlan() - Get vlan attributes + * @skb: Netlink message with request data + * @info: receiver information + * + * Return: 0 on success or negative error number in case of failure + */ +static int batadv_netlink_get_vlan(struct sk_buff *skb, struct genl_info *info) +{ + struct batadv_softif_vlan *vlan = info->user_ptr[1]; + struct batadv_priv *bat_priv = info->user_ptr[0]; + struct sk_buff *msg; + int ret; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + ret = batadv_netlink_vlan_fill(msg, bat_priv, vlan, BATADV_CMD_GET_VLAN, + info->snd_portid, info->snd_seq, 0); + if (ret < 0) { + nlmsg_free(msg); + return ret; + } + + ret = genlmsg_reply(msg, info); + + return ret; +} + +/** + * batadv_netlink_set_vlan() - Get vlan attributes + * @skb: Netlink message with request data + * @info: receiver information + * + * Return: 0 on success or negative error number in case of failure + */ +static int batadv_netlink_set_vlan(struct sk_buff *skb, struct genl_info *info) +{ + struct batadv_softif_vlan *vlan = info->user_ptr[1]; + struct batadv_priv *bat_priv = info->user_ptr[0]; + struct nlattr *attr; + + if (info->attrs[BATADV_ATTR_AP_ISOLATION_ENABLED]) { + attr = info->attrs[BATADV_ATTR_AP_ISOLATION_ENABLED]; + + atomic_set(&vlan->ap_isolation, !!nla_get_u8(attr)); + } + + batadv_netlink_notify_vlan(bat_priv, vlan); + + return 0; +} + +/** + * batadv_get_softif_from_info() - Retrieve soft interface from genl attributes + * @net: the applicable net namespace + * @info: receiver information + * + * Return: Pointer to soft interface (with increased refcnt) on success, error + * pointer on error + */ +static struct net_device * +batadv_get_softif_from_info(struct net *net, struct genl_info *info) +{ + struct net_device *soft_iface; + int ifindex; + + if (!info->attrs[BATADV_ATTR_MESH_IFINDEX]) + return ERR_PTR(-EINVAL); + + ifindex = nla_get_u32(info->attrs[BATADV_ATTR_MESH_IFINDEX]); + + soft_iface = dev_get_by_index(net, ifindex); + if (!soft_iface) + return ERR_PTR(-ENODEV); + + if (!batadv_softif_is_valid(soft_iface)) + goto err_put_softif; + + return soft_iface; + +err_put_softif: + dev_put(soft_iface); + + return ERR_PTR(-EINVAL); +} + +/** + * batadv_get_hardif_from_info() - Retrieve hardif from genl attributes + * @bat_priv: the bat priv with all the soft interface information + * @net: the applicable net namespace + * @info: receiver information + * + * Return: Pointer to hard interface (with increased refcnt) on success, error + * pointer on error + */ +static struct batadv_hard_iface * +batadv_get_hardif_from_info(struct batadv_priv *bat_priv, struct net *net, + struct genl_info *info) +{ + struct batadv_hard_iface *hard_iface; + struct net_device *hard_dev; + unsigned int hardif_index; + + if (!info->attrs[BATADV_ATTR_HARD_IFINDEX]) + return ERR_PTR(-EINVAL); + + hardif_index = nla_get_u32(info->attrs[BATADV_ATTR_HARD_IFINDEX]); + + hard_dev = dev_get_by_index(net, hardif_index); + if (!hard_dev) + return ERR_PTR(-ENODEV); + + hard_iface = batadv_hardif_get_by_netdev(hard_dev); + if (!hard_iface) + goto err_put_harddev; + + if (hard_iface->soft_iface != bat_priv->soft_iface) + goto err_put_hardif; + + /* hard_dev is referenced by hard_iface and not needed here */ + dev_put(hard_dev); + + return hard_iface; + +err_put_hardif: + batadv_hardif_put(hard_iface); +err_put_harddev: + dev_put(hard_dev); + + return ERR_PTR(-EINVAL); +} + +/** + * batadv_get_vlan_from_info() - Retrieve vlan from genl attributes + * @bat_priv: the bat priv with all the soft interface information + * @net: the applicable net namespace + * @info: receiver information + * + * Return: Pointer to vlan on success (with increased refcnt), error pointer + * on error + */ +static struct batadv_softif_vlan * +batadv_get_vlan_from_info(struct batadv_priv *bat_priv, struct net *net, + struct genl_info *info) +{ + struct batadv_softif_vlan *vlan; + u16 vid; + + if (!info->attrs[BATADV_ATTR_VLANID]) + return ERR_PTR(-EINVAL); + + vid = nla_get_u16(info->attrs[BATADV_ATTR_VLANID]); + + vlan = batadv_softif_vlan_get(bat_priv, vid | BATADV_VLAN_HAS_TAG); + if (!vlan) + return ERR_PTR(-ENOENT); + + return vlan; +} + +/** + * batadv_pre_doit() - Prepare batman-adv genl doit request + * @ops: requested netlink operation + * @skb: Netlink message with request data + * @info: receiver information + * + * Return: 0 on success or negative error number in case of failure + */ +static int batadv_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, + struct genl_info *info) +{ + struct net *net = genl_info_net(info); + struct batadv_hard_iface *hard_iface; + struct batadv_priv *bat_priv = NULL; + struct batadv_softif_vlan *vlan; + struct net_device *soft_iface; + u8 user_ptr1_flags; + u8 mesh_dep_flags; + int ret; + + user_ptr1_flags = BATADV_FLAG_NEED_HARDIF | BATADV_FLAG_NEED_VLAN; + if (WARN_ON(hweight8(ops->internal_flags & user_ptr1_flags) > 1)) + return -EINVAL; + + mesh_dep_flags = BATADV_FLAG_NEED_HARDIF | BATADV_FLAG_NEED_VLAN; + if (WARN_ON((ops->internal_flags & mesh_dep_flags) && + (~ops->internal_flags & BATADV_FLAG_NEED_MESH))) + return -EINVAL; + + if (ops->internal_flags & BATADV_FLAG_NEED_MESH) { + soft_iface = batadv_get_softif_from_info(net, info); + if (IS_ERR(soft_iface)) + return PTR_ERR(soft_iface); + + bat_priv = netdev_priv(soft_iface); + info->user_ptr[0] = bat_priv; + } + + if (ops->internal_flags & BATADV_FLAG_NEED_HARDIF) { + hard_iface = batadv_get_hardif_from_info(bat_priv, net, info); + if (IS_ERR(hard_iface)) { + ret = PTR_ERR(hard_iface); + goto err_put_softif; + } + + info->user_ptr[1] = hard_iface; + } + + if (ops->internal_flags & BATADV_FLAG_NEED_VLAN) { + vlan = batadv_get_vlan_from_info(bat_priv, net, info); + if (IS_ERR(vlan)) { + ret = PTR_ERR(vlan); + goto err_put_softif; + } + + info->user_ptr[1] = vlan; + } + + return 0; + +err_put_softif: + if (bat_priv) + dev_put(bat_priv->soft_iface); + + return ret; +} + +/** + * batadv_post_doit() - End batman-adv genl doit request + * @ops: requested netlink operation + * @skb: Netlink message with request data + * @info: receiver information + */ +static void batadv_post_doit(const struct genl_ops *ops, struct sk_buff *skb, + struct genl_info *info) +{ + struct batadv_hard_iface *hard_iface; + struct batadv_softif_vlan *vlan; + struct batadv_priv *bat_priv; + + if (ops->internal_flags & BATADV_FLAG_NEED_HARDIF && + info->user_ptr[1]) { + hard_iface = info->user_ptr[1]; + + batadv_hardif_put(hard_iface); + } + + if (ops->internal_flags & BATADV_FLAG_NEED_VLAN && info->user_ptr[1]) { + vlan = info->user_ptr[1]; + batadv_softif_vlan_put(vlan); + } + + if (ops->internal_flags & BATADV_FLAG_NEED_MESH && info->user_ptr[0]) { + bat_priv = info->user_ptr[0]; + dev_put(bat_priv->soft_iface); + } +} + static const struct genl_ops batadv_netlink_ops[] = { { - .cmd = BATADV_CMD_GET_MESH_INFO, - .flags = GENL_ADMIN_PERM, + .cmd = BATADV_CMD_GET_MESH, + /* can be retrieved by unprivileged users */ .policy = batadv_netlink_policy, - .doit = batadv_netlink_get_mesh_info, + .doit = batadv_netlink_get_mesh, + .internal_flags = BATADV_FLAG_NEED_MESH, }, { .cmd = BATADV_CMD_TP_METER, .flags = GENL_ADMIN_PERM, .policy = batadv_netlink_policy, .doit = batadv_netlink_tp_meter_start, + .internal_flags = BATADV_FLAG_NEED_MESH, }, { .cmd = BATADV_CMD_TP_METER_CANCEL, .flags = GENL_ADMIN_PERM, .policy = batadv_netlink_policy, .doit = batadv_netlink_tp_meter_cancel, + .internal_flags = BATADV_FLAG_NEED_MESH, }, { .cmd = BATADV_CMD_GET_ROUTING_ALGOS, @@ -571,10 +1370,13 @@ static const struct genl_ops batadv_netlink_ops[] = { .dumpit = batadv_algo_dump, }, { - .cmd = BATADV_CMD_GET_HARDIFS, - .flags = GENL_ADMIN_PERM, + .cmd = BATADV_CMD_GET_HARDIF, + /* can be retrieved by unprivileged users */ .policy = batadv_netlink_policy, - .dumpit = batadv_netlink_dump_hardifs, + .dumpit = batadv_netlink_dump_hardif, + .doit = batadv_netlink_get_hardif, + .internal_flags = BATADV_FLAG_NEED_MESH | + BATADV_FLAG_NEED_HARDIF, }, { .cmd = BATADV_CMD_GET_TRANSTABLE_LOCAL, @@ -630,7 +1432,37 @@ static const struct genl_ops batadv_netlink_ops[] = { .policy = batadv_netlink_policy, .dumpit = batadv_mcast_flags_dump, }, - + { + .cmd = BATADV_CMD_SET_MESH, + .flags = GENL_ADMIN_PERM, + .policy = batadv_netlink_policy, + .doit = batadv_netlink_set_mesh, + .internal_flags = BATADV_FLAG_NEED_MESH, + }, + { + .cmd = BATADV_CMD_SET_HARDIF, + .flags = GENL_ADMIN_PERM, + .policy = batadv_netlink_policy, + .doit = batadv_netlink_set_hardif, + .internal_flags = BATADV_FLAG_NEED_MESH | + BATADV_FLAG_NEED_HARDIF, + }, + { + .cmd = BATADV_CMD_GET_VLAN, + /* can be retrieved by unprivileged users */ + .policy = batadv_netlink_policy, + .doit = batadv_netlink_get_vlan, + .internal_flags = BATADV_FLAG_NEED_MESH | + BATADV_FLAG_NEED_VLAN, + }, + { + .cmd = BATADV_CMD_SET_VLAN, + .flags = GENL_ADMIN_PERM, + .policy = batadv_netlink_policy, + .doit = batadv_netlink_set_vlan, + .internal_flags = BATADV_FLAG_NEED_MESH | + BATADV_FLAG_NEED_VLAN, + }, }; struct genl_family batadv_netlink_family __ro_after_init = { @@ -639,6 +1471,8 @@ struct genl_family batadv_netlink_family __ro_after_init = { .version = 1, .maxattr = BATADV_ATTR_MAX, .netnsok = true, + .pre_doit = batadv_pre_doit, + .post_doit = batadv_post_doit, .module = THIS_MODULE, .ops = batadv_netlink_ops, .n_ops = ARRAY_SIZE(batadv_netlink_ops), diff --git a/net/batman-adv/netlink.h b/net/batman-adv/netlink.h index 571d9a5ae7aa..7273368544fc 100644 --- a/net/batman-adv/netlink.h +++ b/net/batman-adv/netlink.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2016-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2016-2019 B.A.T.M.A.N. contributors: * * Matthias Schiffer * @@ -34,6 +34,12 @@ int batadv_netlink_tpmeter_notify(struct batadv_priv *bat_priv, const u8 *dst, u8 result, u32 test_time, u64 total_bytes, u32 cookie); +int batadv_netlink_notify_mesh(struct batadv_priv *bat_priv); +int batadv_netlink_notify_hardif(struct batadv_priv *bat_priv, + struct batadv_hard_iface *hard_iface); +int batadv_netlink_notify_vlan(struct batadv_priv *bat_priv, + struct batadv_softif_vlan *vlan); + extern struct genl_family batadv_netlink_family; #endif /* _NET_BATMAN_ADV_NETLINK_H_ */ diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index 34caf129a9bf..278762bd94c6 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2012-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2019 B.A.T.M.A.N. contributors: * * Martin Hundebøll, Jeppe Ledet-Pedersen * diff --git a/net/batman-adv/network-coding.h b/net/batman-adv/network-coding.h index 65c346812bc1..96ef0a511fc7 100644 --- a/net/batman-adv/network-coding.h +++ b/net/batman-adv/network-coding.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2012-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2019 B.A.T.M.A.N. contributors: * * Martin Hundebøll, Jeppe Ledet-Pedersen * diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 56a981af5c92..e5cdf89ef63c 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2009-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index a8b4c7b667ec..dca1e4a34ec6 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index cc3ed93a6d51..cae0e5dd0768 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -1043,6 +1043,8 @@ int batadv_recv_unicast_packet(struct sk_buff *skb, hdr_size)) goto rx_success; + batadv_dat_snoop_incoming_dhcp_ack(bat_priv, skb, hdr_size); + batadv_interface_rx(recv_if->soft_iface, skb, hdr_size, orig_node); @@ -1278,6 +1280,8 @@ int batadv_recv_bcast_packet(struct sk_buff *skb, if (batadv_dat_snoop_incoming_arp_reply(bat_priv, skb, hdr_size)) goto rx_success; + batadv_dat_snoop_incoming_dhcp_ack(bat_priv, skb, hdr_size); + /* broadcast for me */ batadv_interface_rx(recv_if->soft_iface, skb, hdr_size, orig_node); diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h index db54c2d9b8bf..0102d69d345c 100644 --- a/net/batman-adv/routing.h +++ b/net/batman-adv/routing.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 4a35f5c2f52b..66a8b3e44501 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h index 64cce07b8fe6..1f6132922e60 100644 --- a/net/batman-adv/send.h +++ b/net/batman-adv/send.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 5db5a0a4c959..2e367230376b 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -50,13 +50,13 @@ #include <linux/string.h> #include <linux/types.h> #include <uapi/linux/batadv_packet.h> +#include <uapi/linux/batman_adv.h> #include "bat_algo.h" #include "bridge_loop_avoidance.h" #include "debugfs.h" #include "distributed-arp-table.h" #include "gateway_client.h" -#include "gateway_common.h" #include "hard-interface.h" #include "multicast.h" #include "network-coding.h" @@ -212,6 +212,7 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb, enum batadv_forw_mode forw_mode; struct batadv_orig_node *mcast_single_orig = NULL; int network_offset = ETH_HLEN; + __be16 proto; if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE) goto dropped; @@ -221,14 +222,21 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb, netif_trans_update(soft_iface); vid = batadv_get_vid(skb, 0); + + skb_reset_mac_header(skb); ethhdr = eth_hdr(skb); - switch (ntohs(ethhdr->h_proto)) { + proto = ethhdr->h_proto; + + switch (ntohs(proto)) { case ETH_P_8021Q: + if (!pskb_may_pull(skb, sizeof(*vhdr))) + goto dropped; vhdr = vlan_eth_hdr(skb); + proto = vhdr->h_vlan_encapsulated_proto; /* drop batman-in-batman packets to prevent loops */ - if (vhdr->h_vlan_encapsulated_proto != htons(ETH_P_BATMAN)) { + if (proto != htons(ETH_P_BATMAN)) { network_offset += VLAN_HLEN; break; } @@ -256,6 +264,9 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb, goto dropped; } + /* Snoop address candidates from DHCPACKs for early DAT filling */ + batadv_dat_snoop_outgoing_dhcp_ack(bat_priv, skb, proto, vid); + /* don't accept stp packets. STP does not help in meshes. * better use the bridge loop avoidance ... * diff --git a/net/batman-adv/soft-interface.h b/net/batman-adv/soft-interface.h index daf87f07fadd..538bb661878c 100644 --- a/net/batman-adv/soft-interface.h +++ b/net/batman-adv/soft-interface.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c index 09427fc6494a..0b4b3fb778a6 100644 --- a/net/batman-adv/sysfs.c +++ b/net/batman-adv/sysfs.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2010-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -40,6 +40,7 @@ #include <linux/stringify.h> #include <linux/workqueue.h> #include <uapi/linux/batadv_packet.h> +#include <uapi/linux/batman_adv.h> #include "bridge_loop_avoidance.h" #include "distributed-arp-table.h" @@ -47,6 +48,7 @@ #include "gateway_common.h" #include "hard-interface.h" #include "log.h" +#include "netlink.h" #include "network-coding.h" #include "soft-interface.h" @@ -153,9 +155,14 @@ ssize_t batadv_store_##_name(struct kobject *kobj, \ { \ struct net_device *net_dev = batadv_kobj_to_netdev(kobj); \ struct batadv_priv *bat_priv = netdev_priv(net_dev); \ + ssize_t length; \ + \ + length = __batadv_store_bool_attr(buff, count, _post_func, attr,\ + &bat_priv->_name, net_dev); \ \ - return __batadv_store_bool_attr(buff, count, _post_func, attr, \ - &bat_priv->_name, net_dev); \ + batadv_netlink_notify_mesh(bat_priv); \ + \ + return length; \ } #define BATADV_ATTR_SIF_SHOW_BOOL(_name) \ @@ -185,11 +192,16 @@ ssize_t batadv_store_##_name(struct kobject *kobj, \ { \ struct net_device *net_dev = batadv_kobj_to_netdev(kobj); \ struct batadv_priv *bat_priv = netdev_priv(net_dev); \ + ssize_t length; \ \ - return __batadv_store_uint_attr(buff, count, _min, _max, \ - _post_func, attr, \ - &bat_priv->_var, net_dev, \ - NULL); \ + length = __batadv_store_uint_attr(buff, count, _min, _max, \ + _post_func, attr, \ + &bat_priv->_var, net_dev, \ + NULL); \ + \ + batadv_netlink_notify_mesh(bat_priv); \ + \ + return length; \ } #define BATADV_ATTR_SIF_SHOW_UINT(_name, _var) \ @@ -222,6 +234,11 @@ ssize_t batadv_store_vlan_##_name(struct kobject *kobj, \ attr, &vlan->_name, \ bat_priv->soft_iface); \ \ + if (vlan->vid) \ + batadv_netlink_notify_vlan(bat_priv, vlan); \ + else \ + batadv_netlink_notify_mesh(bat_priv); \ + \ batadv_softif_vlan_put(vlan); \ return res; \ } @@ -255,6 +272,7 @@ ssize_t batadv_store_##_name(struct kobject *kobj, \ { \ struct net_device *net_dev = batadv_kobj_to_netdev(kobj); \ struct batadv_hard_iface *hard_iface; \ + struct batadv_priv *bat_priv; \ ssize_t length; \ \ hard_iface = batadv_hardif_get_by_netdev(net_dev); \ @@ -267,6 +285,11 @@ ssize_t batadv_store_##_name(struct kobject *kobj, \ hard_iface->soft_iface, \ net_dev); \ \ + if (hard_iface->soft_iface) { \ + bat_priv = netdev_priv(hard_iface->soft_iface); \ + batadv_netlink_notify_hardif(bat_priv, hard_iface); \ + } \ + \ batadv_hardif_put(hard_iface); \ return length; \ } @@ -536,6 +559,9 @@ static ssize_t batadv_store_gw_mode(struct kobject *kobj, batadv_gw_check_client_stop(bat_priv); atomic_set(&bat_priv->gw.mode, (unsigned int)gw_mode_tmp); batadv_gw_tvlv_container_update(bat_priv); + + batadv_netlink_notify_mesh(bat_priv); + return count; } @@ -562,6 +588,7 @@ static ssize_t batadv_store_gw_sel_class(struct kobject *kobj, size_t count) { struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj); + ssize_t length; /* setting the GW selection class is allowed only if the routing * algorithm in use implements the GW API @@ -577,10 +604,14 @@ static ssize_t batadv_store_gw_sel_class(struct kobject *kobj, return bat_priv->algo_ops->gw.store_sel_class(bat_priv, buff, count); - return __batadv_store_uint_attr(buff, count, 1, BATADV_TQ_MAX_VALUE, - batadv_post_gw_reselect, attr, - &bat_priv->gw.sel_class, - bat_priv->soft_iface, NULL); + length = __batadv_store_uint_attr(buff, count, 1, BATADV_TQ_MAX_VALUE, + batadv_post_gw_reselect, attr, + &bat_priv->gw.sel_class, + bat_priv->soft_iface, NULL); + + batadv_netlink_notify_mesh(bat_priv); + + return length; } static ssize_t batadv_show_gw_bwidth(struct kobject *kobj, @@ -600,12 +631,18 @@ static ssize_t batadv_store_gw_bwidth(struct kobject *kobj, struct attribute *attr, char *buff, size_t count) { + struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj); struct net_device *net_dev = batadv_kobj_to_netdev(kobj); + ssize_t length; if (buff[count - 1] == '\n') buff[count - 1] = '\0'; - return batadv_gw_bandwidth_set(net_dev, buff, count); + length = batadv_gw_bandwidth_set(net_dev, buff, count); + + batadv_netlink_notify_mesh(bat_priv); + + return length; } /** @@ -673,6 +710,8 @@ static ssize_t batadv_store_isolation_mark(struct kobject *kobj, "New skb mark for extended isolation: %#.8x/%#.8x\n", bat_priv->isolation_mark, bat_priv->isolation_mark_mask); + batadv_netlink_notify_mesh(bat_priv); + return count; } @@ -1077,6 +1116,7 @@ static ssize_t batadv_store_throughput_override(struct kobject *kobj, struct attribute *attr, char *buff, size_t count) { + struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj); struct net_device *net_dev = batadv_kobj_to_netdev(kobj); struct batadv_hard_iface *hard_iface; u32 tp_override; @@ -1107,6 +1147,8 @@ static ssize_t batadv_store_throughput_override(struct kobject *kobj, atomic_set(&hard_iface->bat_v.throughput_override, tp_override); + batadv_netlink_notify_hardif(bat_priv, hard_iface); + out: batadv_hardif_put(hard_iface); return count; diff --git a/net/batman-adv/sysfs.h b/net/batman-adv/sysfs.h index c1e3fb69952d..705ffbe763f4 100644 --- a/net/batman-adv/sysfs.h +++ b/net/batman-adv/sysfs.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2010-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c index 11520de96ccb..500109bbd551 100644 --- a/net/batman-adv/tp_meter.c +++ b/net/batman-adv/tp_meter.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2012-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2019 B.A.T.M.A.N. contributors: * * Edo Monticelli, Antonio Quartulli * diff --git a/net/batman-adv/tp_meter.h b/net/batman-adv/tp_meter.h index 68e600974759..6b4d0f733896 100644 --- a/net/batman-adv/tp_meter.h +++ b/net/batman-adv/tp_meter.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2012-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2019 B.A.T.M.A.N. contributors: * * Edo Monticelli, Antonio Quartulli * diff --git a/net/batman-adv/trace.c b/net/batman-adv/trace.c index 8e1024217cff..f77c917ed20d 100644 --- a/net/batman-adv/trace.c +++ b/net/batman-adv/trace.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2010-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors: * * Sven Eckelmann * diff --git a/net/batman-adv/trace.h b/net/batman-adv/trace.h index 104784be94d7..5e5579051400 100644 --- a/net/batman-adv/trace.h +++ b/net/batman-adv/trace.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2010-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors: * * Sven Eckelmann * diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 8dcd4968cde7..f73d79139ae7 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich, Antonio Quartulli * diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h index 01b6c8eafaf9..61bca75e5911 100644 --- a/net/batman-adv/translation-table.h +++ b/net/batman-adv/translation-table.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich, Antonio Quartulli * diff --git a/net/batman-adv/tvlv.c b/net/batman-adv/tvlv.c index 40e69c9346d2..7e947b01919d 100644 --- a/net/batman-adv/tvlv.c +++ b/net/batman-adv/tvlv.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/tvlv.h b/net/batman-adv/tvlv.h index ef5867f49824..c0f033b1acb8 100644 --- a/net/batman-adv/tvlv.h +++ b/net/batman-adv/tvlv.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index cbe17da36fcb..a21b34ed6548 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 1506e1632394..65228bfa4487 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -1383,9 +1383,9 @@ static void hci_sock_cmsg(struct sock *sk, struct msghdr *msg, if (mask & HCI_CMSG_TSTAMP) { #ifdef CONFIG_COMPAT - struct compat_timeval ctv; + struct old_timeval32 ctv; #endif - struct timeval tv; + struct __kernel_old_timeval tv; void *data; int len; diff --git a/net/bpfilter/Makefile b/net/bpfilter/Makefile index 0947ee7f70d5..5d6c7760142d 100644 --- a/net/bpfilter/Makefile +++ b/net/bpfilter/Makefile @@ -5,7 +5,6 @@ hostprogs-y := bpfilter_umh bpfilter_umh-objs := main.o -KBUILD_HOSTCFLAGS += -I. -Itools/include/ -Itools/include/uapi HOSTCC := $(CC) ifeq ($(CONFIG_BPFILTER_UMH), y) diff --git a/net/bpfilter/main.c b/net/bpfilter/main.c index 1317f108df8a..61ce8454a88e 100644 --- a/net/bpfilter/main.c +++ b/net/bpfilter/main.c @@ -6,7 +6,7 @@ #include <sys/socket.h> #include <fcntl.h> #include <unistd.h> -#include "include/uapi/linux/bpf.h" +#include "../../include/uapi/linux/bpf.h" #include <asm/unistd.h> #include "msgfmt.h" diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 780757b7a82f..4a048fd1cbea 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1018,8 +1018,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, if (!nsrcs) return -EINVAL; - grec_len = sizeof(*grec) + - sizeof(struct in6_addr) * ntohs(*nsrcs); + grec_len = struct_size(grec, grec_src, ntohs(*nsrcs)); if (!ipv6_mc_may_pull(skb, len + grec_len)) return -EINVAL; @@ -1841,7 +1840,7 @@ static void br_ip4_multicast_join_snoopers(struct net_bridge *br) if (!in_dev) return; - ip_mc_inc_group(in_dev, htonl(INADDR_ALLSNOOPERS_GROUP)); + __ip_mc_inc_group(in_dev, htonl(INADDR_ALLSNOOPERS_GROUP), GFP_ATOMIC); in_dev_put(in_dev); } @@ -1872,7 +1871,7 @@ static void br_ip4_multicast_leave_snoopers(struct net_bridge *br) if (WARN_ON(!in_dev)) return; - ip_mc_dec_group(in_dev, htonl(INADDR_ALLSNOOPERS_GROUP)); + __ip_mc_dec_group(in_dev, htonl(INADDR_ALLSNOOPERS_GROUP), GFP_ATOMIC); in_dev_put(in_dev); } diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index 4d2b9eb7604a..db9e8ab96d48 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -14,7 +14,7 @@ static int br_switchdev_mark_get(struct net_bridge *br, struct net_device *dev) /* dev is yet to be added to the port list. */ list_for_each_entry(p, &br->port_list, list) { - if (switchdev_port_same_parent_id(dev, p->dev)) + if (netdev_port_same_parent_id(dev, p->dev)) return p->offload_fwd_mark; } @@ -23,15 +23,12 @@ static int br_switchdev_mark_get(struct net_bridge *br, struct net_device *dev) int nbp_switchdev_mark_set(struct net_bridge_port *p) { - struct switchdev_attr attr = { - .orig_dev = p->dev, - .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, - }; + struct netdev_phys_item_id ppid = { }; int err; ASSERT_RTNL(); - err = switchdev_port_attr_get(p->dev, &attr); + err = dev_get_port_parent_id(p->dev, &ppid, true); if (err) { if (err == -EOPNOTSUPP) return 0; diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 5e55cef0cec3..6693e209efe8 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -2293,9 +2293,12 @@ static int compat_do_replace(struct net *net, void __user *user, xt_compat_lock(NFPROTO_BRIDGE); - ret = xt_compat_init_offsets(NFPROTO_BRIDGE, tmp.nentries); - if (ret < 0) - goto out_unlock; + if (tmp.nentries) { + ret = xt_compat_init_offsets(NFPROTO_BRIDGE, tmp.nentries); + if (ret < 0) + goto out_unlock; + } + ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state); if (ret < 0) goto out_unlock; diff --git a/net/caif/cfpkt_skbuff.c b/net/caif/cfpkt_skbuff.c index 38c2b7a890dd..37ac5ca0ffdf 100644 --- a/net/caif/cfpkt_skbuff.c +++ b/net/caif/cfpkt_skbuff.c @@ -319,16 +319,12 @@ struct cfpkt *cfpkt_append(struct cfpkt *dstpkt, if (tmppkt == NULL) return NULL; tmp = pkt_to_skb(tmppkt); - skb_set_tail_pointer(tmp, dstlen); - tmp->len = dstlen; - memcpy(tmp->data, dst->data, dstlen); + skb_put_data(tmp, dst->data, dstlen); cfpkt_destroy(dstpkt); dst = tmp; } - memcpy(skb_tail_pointer(dst), add->data, skb_headlen(add)); + skb_put_data(dst, add->data, skb_headlen(add)); cfpkt_destroy(addpkt); - dst->tail += addlen; - dst->len += addlen; return skb_to_pkt(dst); } @@ -359,13 +355,11 @@ struct cfpkt *cfpkt_split(struct cfpkt *pkt, u16 pos) if (skb2 == NULL) return NULL; + skb_put_data(skb2, split, len2nd); + /* Reduce the length of the original packet */ - skb_set_tail_pointer(skb, pos); - skb->len = pos; + skb_trim(skb, pos); - memcpy(skb2->data, split, len2nd); - skb2->tail += len2nd; - skb2->len += len2nd; skb2->priority = skb->priority; return skb_to_pkt(skb2); } diff --git a/net/compat.c b/net/compat.c index 959d1c51826d..9629f053d4fa 100644 --- a/net/compat.c +++ b/net/compat.c @@ -209,8 +209,8 @@ int put_cmsg_compat(struct msghdr *kmsg, int level, int type, int len, void *dat { struct compat_cmsghdr __user *cm = (struct compat_cmsghdr __user *) kmsg->msg_control; struct compat_cmsghdr cmhdr; - struct compat_timeval ctv; - struct compat_timespec cts[3]; + struct old_timeval32 ctv; + struct old_timespec32 cts[3]; int cmlen; if (cm == NULL || kmsg->msg_controllen < sizeof(*cm)) { @@ -219,16 +219,16 @@ int put_cmsg_compat(struct msghdr *kmsg, int level, int type, int len, void *dat } if (!COMPAT_USE_64BIT_TIME) { - if (level == SOL_SOCKET && type == SCM_TIMESTAMP) { - struct timeval *tv = (struct timeval *)data; + if (level == SOL_SOCKET && type == SO_TIMESTAMP_OLD) { + struct __kernel_old_timeval *tv = (struct __kernel_old_timeval *)data; ctv.tv_sec = tv->tv_sec; ctv.tv_usec = tv->tv_usec; data = &ctv; len = sizeof(ctv); } if (level == SOL_SOCKET && - (type == SCM_TIMESTAMPNS || type == SCM_TIMESTAMPING)) { - int count = type == SCM_TIMESTAMPNS ? 1 : 3; + (type == SO_TIMESTAMPNS_OLD || type == SO_TIMESTAMPING_OLD)) { + int count = type == SO_TIMESTAMPNS_OLD ? 1 : 3; int i; struct timespec *ts = (struct timespec *)data; for (i = 0; i < count; i++) { @@ -348,28 +348,6 @@ static int do_set_attach_filter(struct socket *sock, int level, int optname, sizeof(struct sock_fprog)); } -static int do_set_sock_timeout(struct socket *sock, int level, - int optname, char __user *optval, unsigned int optlen) -{ - struct compat_timeval __user *up = (struct compat_timeval __user *)optval; - struct timeval ktime; - mm_segment_t old_fs; - int err; - - if (optlen < sizeof(*up)) - return -EINVAL; - if (!access_ok(up, sizeof(*up)) || - __get_user(ktime.tv_sec, &up->tv_sec) || - __get_user(ktime.tv_usec, &up->tv_usec)) - return -EFAULT; - old_fs = get_fs(); - set_fs(KERNEL_DS); - err = sock_setsockopt(sock, level, optname, (char *)&ktime, sizeof(ktime)); - set_fs(old_fs); - - return err; -} - static int compat_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen) { @@ -377,10 +355,6 @@ static int compat_sock_setsockopt(struct socket *sock, int level, int optname, optname == SO_ATTACH_REUSEPORT_CBPF) return do_set_attach_filter(sock, level, optname, optval, optlen); - if (!COMPAT_USE_64BIT_TIME && - (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO)) - return do_set_sock_timeout(sock, level, optname, optval, optlen); - return sock_setsockopt(sock, level, optname, optval, optlen); } @@ -417,44 +391,6 @@ COMPAT_SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname, return __compat_sys_setsockopt(fd, level, optname, optval, optlen); } -static int do_get_sock_timeout(struct socket *sock, int level, int optname, - char __user *optval, int __user *optlen) -{ - struct compat_timeval __user *up; - struct timeval ktime; - mm_segment_t old_fs; - int len, err; - - up = (struct compat_timeval __user *) optval; - if (get_user(len, optlen)) - return -EFAULT; - if (len < sizeof(*up)) - return -EINVAL; - len = sizeof(ktime); - old_fs = get_fs(); - set_fs(KERNEL_DS); - err = sock_getsockopt(sock, level, optname, (char *) &ktime, &len); - set_fs(old_fs); - - if (!err) { - if (put_user(sizeof(*up), optlen) || - !access_ok(up, sizeof(*up)) || - __put_user(ktime.tv_sec, &up->tv_sec) || - __put_user(ktime.tv_usec, &up->tv_usec)) - err = -EFAULT; - } - return err; -} - -static int compat_sock_getsockopt(struct socket *sock, int level, int optname, - char __user *optval, int __user *optlen) -{ - if (!COMPAT_USE_64BIT_TIME && - (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO)) - return do_get_sock_timeout(sock, level, optname, optval, optlen); - return sock_getsockopt(sock, level, optname, optval, optlen); -} - int compat_sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp) { struct compat_timeval __user *ctv; @@ -527,7 +463,7 @@ static int __compat_sys_getsockopt(int fd, int level, int optname, } if (level == SOL_SOCKET) - err = compat_sock_getsockopt(sock, level, + err = sock_getsockopt(sock, level, optname, optval, optlen); else if (sock->ops->compat_getsockopt) err = sock->ops->compat_getsockopt(sock, level, diff --git a/net/core/Makefile b/net/core/Makefile index fccd31e0e7f7..f97d6254e564 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -11,7 +11,7 @@ obj-$(CONFIG_SYSCTL) += sysctl_net_core.o obj-y += dev.o ethtool.o dev_addr_lists.o dst.o netevent.o \ neighbour.o rtnetlink.o utils.o link_watch.o filter.o \ sock_diag.o dev_ioctl.o tso.o sock_reuseport.o \ - fib_notifier.o xdp.o + fib_notifier.o xdp.o flow_offload.o obj-y += net-sysfs.o obj-$(CONFIG_PAGE_POOL) += page_pool.o diff --git a/net/core/dev.c b/net/core/dev.c index 82f20022259d..ecbe419e05ab 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -7878,6 +7878,63 @@ int dev_get_phys_port_name(struct net_device *dev, EXPORT_SYMBOL(dev_get_phys_port_name); /** + * dev_get_port_parent_id - Get the device's port parent identifier + * @dev: network device + * @ppid: pointer to a storage for the port's parent identifier + * @recurse: allow/disallow recursion to lower devices + * + * Get the devices's port parent identifier + */ +int dev_get_port_parent_id(struct net_device *dev, + struct netdev_phys_item_id *ppid, + bool recurse) +{ + const struct net_device_ops *ops = dev->netdev_ops; + struct netdev_phys_item_id first = { }; + struct net_device *lower_dev; + struct list_head *iter; + int err = -EOPNOTSUPP; + + if (ops->ndo_get_port_parent_id) + return ops->ndo_get_port_parent_id(dev, ppid); + + if (!recurse) + return err; + + netdev_for_each_lower_dev(dev, lower_dev, iter) { + err = dev_get_port_parent_id(lower_dev, ppid, recurse); + if (err) + break; + if (!first.id_len) + first = *ppid; + else if (memcmp(&first, ppid, sizeof(*ppid))) + return -ENODATA; + } + + return err; +} +EXPORT_SYMBOL(dev_get_port_parent_id); + +/** + * netdev_port_same_parent_id - Indicate if two network devices have + * the same port parent identifier + * @a: first network device + * @b: second network device + */ +bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b) +{ + struct netdev_phys_item_id a_id = { }; + struct netdev_phys_item_id b_id = { }; + + if (dev_get_port_parent_id(a, &a_id, true) || + dev_get_port_parent_id(b, &b_id, true)) + return false; + + return netdev_phys_item_id_same(&a_id, &b_id); +} +EXPORT_SYMBOL(netdev_port_same_parent_id); + +/** * dev_change_proto_down - update protocol port state information * @dev: device * @proto_down: new value @@ -7976,35 +8033,41 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, enum bpf_netdev_command query; struct bpf_prog *prog = NULL; bpf_op_t bpf_op, bpf_chk; + bool offload; int err; ASSERT_RTNL(); - query = flags & XDP_FLAGS_HW_MODE ? XDP_QUERY_PROG_HW : XDP_QUERY_PROG; + offload = flags & XDP_FLAGS_HW_MODE; + query = offload ? XDP_QUERY_PROG_HW : XDP_QUERY_PROG; bpf_op = bpf_chk = ops->ndo_bpf; - if (!bpf_op && (flags & (XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE))) + if (!bpf_op && (flags & (XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE))) { + NL_SET_ERR_MSG(extack, "underlying driver does not support XDP in native mode"); return -EOPNOTSUPP; + } if (!bpf_op || (flags & XDP_FLAGS_SKB_MODE)) bpf_op = generic_xdp_install; if (bpf_op == bpf_chk) bpf_chk = generic_xdp_install; if (fd >= 0) { - if (__dev_xdp_query(dev, bpf_chk, XDP_QUERY_PROG) || - __dev_xdp_query(dev, bpf_chk, XDP_QUERY_PROG_HW)) + if (!offload && __dev_xdp_query(dev, bpf_chk, XDP_QUERY_PROG)) { + NL_SET_ERR_MSG(extack, "native and generic XDP can't be active at the same time"); return -EEXIST; + } if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && - __dev_xdp_query(dev, bpf_op, query)) + __dev_xdp_query(dev, bpf_op, query)) { + NL_SET_ERR_MSG(extack, "XDP program already attached"); return -EBUSY; + } prog = bpf_prog_get_type_dev(fd, BPF_PROG_TYPE_XDP, bpf_op == ops->ndo_bpf); if (IS_ERR(prog)) return PTR_ERR(prog); - if (!(flags & XDP_FLAGS_HW_MODE) && - bpf_prog_is_dev_bound(prog->aux)) { + if (!offload && bpf_prog_is_dev_bound(prog->aux)) { NL_SET_ERR_MSG(extack, "using device-bound program without HW_MODE flag is not supported"); bpf_prog_put(prog); return -EINVAL; @@ -8712,6 +8775,9 @@ int init_dummy_netdev(struct net_device *dev) set_bit(__LINK_STATE_PRESENT, &dev->state); set_bit(__LINK_STATE_START, &dev->state); + /* napi_busy_loop stats accounting wants this */ + dev_net_set(dev, &init_net); + /* Note : We dont allocate pcpu_refcnt for dummy devices, * because users of this 'device' dont need to change * its refcount. diff --git a/net/core/devlink.c b/net/core/devlink.c index abb0da9d7b4b..04d98550c78c 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -81,6 +81,7 @@ struct devlink_dpipe_header devlink_dpipe_header_ipv6 = { EXPORT_SYMBOL(devlink_dpipe_header_ipv6); EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwmsg); +EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwerr); static LIST_HEAD(devlink_list); @@ -115,6 +116,8 @@ static struct devlink *devlink_get_from_attrs(struct net *net, busname = nla_data(attrs[DEVLINK_ATTR_BUS_NAME]); devname = nla_data(attrs[DEVLINK_ATTR_DEV_NAME]); + lockdep_assert_held(&devlink_mutex); + list_for_each_entry(devlink, &devlink_list, list) { if (strcmp(devlink->dev->bus->name, busname) == 0 && strcmp(dev_name(devlink->dev), devname) == 0 && @@ -932,6 +935,9 @@ static int devlink_nl_sb_pool_fill(struct sk_buff *msg, struct devlink *devlink, if (nla_put_u8(msg, DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE, pool_info.threshold_type)) goto nla_put_failure; + if (nla_put_u32(msg, DEVLINK_ATTR_SB_POOL_CELL_SIZE, + pool_info.cell_size)) + goto nla_put_failure; genlmsg_end(msg, hdr); return 0; @@ -2656,6 +2662,27 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) return devlink->ops->reload(devlink, info->extack); } +static int devlink_nl_cmd_flash_update(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + const char *file_name, *component; + struct nlattr *nla_component; + + if (!devlink->ops->flash_update) + return -EOPNOTSUPP; + + if (!info->attrs[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME]) + return -EINVAL; + file_name = nla_data(info->attrs[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME]); + + nla_component = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_COMPONENT]; + component = nla_component ? nla_data(nla_component) : NULL; + + return devlink->ops->flash_update(devlink, file_name, component, + info->extack); +} + static const struct devlink_param devlink_param_generic[] = { { .id = DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET, @@ -2843,11 +2870,13 @@ nla_put_failure: } static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink, + unsigned int port_index, struct devlink_param_item *param_item, enum devlink_command cmd, u32 portid, u32 seq, int flags) { union devlink_param_value param_value[DEVLINK_PARAM_CMODE_MAX + 1]; + bool param_value_set[DEVLINK_PARAM_CMODE_MAX + 1] = {}; const struct devlink_param *param = param_item->param; struct devlink_param_gset_ctx ctx; struct nlattr *param_values_list; @@ -2866,12 +2895,15 @@ static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink, return -EOPNOTSUPP; param_value[i] = param_item->driverinit_value; } else { + if (!param_item->published) + continue; ctx.cmode = i; err = devlink_param_get(devlink, param, &ctx); if (err) return err; param_value[i] = ctx.val; } + param_value_set[i] = true; } hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); @@ -2880,6 +2912,13 @@ static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink, if (devlink_nl_put_handle(msg, devlink)) goto genlmsg_cancel; + + if (cmd == DEVLINK_CMD_PORT_PARAM_GET || + cmd == DEVLINK_CMD_PORT_PARAM_NEW || + cmd == DEVLINK_CMD_PORT_PARAM_DEL) + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, port_index)) + goto genlmsg_cancel; + param_attr = nla_nest_start(msg, DEVLINK_ATTR_PARAM); if (!param_attr) goto genlmsg_cancel; @@ -2899,7 +2938,7 @@ static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink, goto param_nest_cancel; for (i = 0; i <= DEVLINK_PARAM_CMODE_MAX; i++) { - if (!devlink_param_cmode_is_supported(param, i)) + if (!param_value_set[i]) continue; err = devlink_nl_param_value_fill_one(msg, param->type, i, param_value[i]); @@ -2922,18 +2961,22 @@ genlmsg_cancel: } static void devlink_param_notify(struct devlink *devlink, + unsigned int port_index, struct devlink_param_item *param_item, enum devlink_command cmd) { struct sk_buff *msg; int err; - WARN_ON(cmd != DEVLINK_CMD_PARAM_NEW && cmd != DEVLINK_CMD_PARAM_DEL); + WARN_ON(cmd != DEVLINK_CMD_PARAM_NEW && cmd != DEVLINK_CMD_PARAM_DEL && + cmd != DEVLINK_CMD_PORT_PARAM_NEW && + cmd != DEVLINK_CMD_PORT_PARAM_DEL); msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return; - err = devlink_nl_param_fill(msg, devlink, param_item, cmd, 0, 0, 0); + err = devlink_nl_param_fill(msg, devlink, port_index, param_item, cmd, + 0, 0, 0); if (err) { nlmsg_free(msg); return; @@ -2962,7 +3005,7 @@ static int devlink_nl_cmd_param_get_dumpit(struct sk_buff *msg, idx++; continue; } - err = devlink_nl_param_fill(msg, devlink, param_item, + err = devlink_nl_param_fill(msg, devlink, 0, param_item, DEVLINK_CMD_PARAM_GET, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, @@ -3051,7 +3094,7 @@ devlink_param_value_get_from_info(const struct devlink_param *param, } static struct devlink_param_item * -devlink_param_get_from_info(struct devlink *devlink, +devlink_param_get_from_info(struct list_head *param_list, struct genl_info *info) { char *param_name; @@ -3060,7 +3103,7 @@ devlink_param_get_from_info(struct devlink *devlink, return NULL; param_name = nla_data(info->attrs[DEVLINK_ATTR_PARAM_NAME]); - return devlink_param_find_by_name(&devlink->param_list, param_name); + return devlink_param_find_by_name(param_list, param_name); } static int devlink_nl_cmd_param_get_doit(struct sk_buff *skb, @@ -3071,7 +3114,7 @@ static int devlink_nl_cmd_param_get_doit(struct sk_buff *skb, struct sk_buff *msg; int err; - param_item = devlink_param_get_from_info(devlink, info); + param_item = devlink_param_get_from_info(&devlink->param_list, info); if (!param_item) return -EINVAL; @@ -3079,7 +3122,7 @@ static int devlink_nl_cmd_param_get_doit(struct sk_buff *skb, if (!msg) return -ENOMEM; - err = devlink_nl_param_fill(msg, devlink, param_item, + err = devlink_nl_param_fill(msg, devlink, 0, param_item, DEVLINK_CMD_PARAM_GET, info->snd_portid, info->snd_seq, 0); if (err) { @@ -3090,10 +3133,12 @@ static int devlink_nl_cmd_param_get_doit(struct sk_buff *skb, return genlmsg_reply(msg, info); } -static int devlink_nl_cmd_param_set_doit(struct sk_buff *skb, - struct genl_info *info) +static int __devlink_nl_cmd_param_set_doit(struct devlink *devlink, + unsigned int port_index, + struct list_head *param_list, + struct genl_info *info, + enum devlink_command cmd) { - struct devlink *devlink = info->user_ptr[0]; enum devlink_param_type param_type; struct devlink_param_gset_ctx ctx; enum devlink_param_cmode cmode; @@ -3102,7 +3147,7 @@ static int devlink_nl_cmd_param_set_doit(struct sk_buff *skb, union devlink_param_value value; int err = 0; - param_item = devlink_param_get_from_info(devlink, info); + param_item = devlink_param_get_from_info(param_list, info); if (!param_item) return -EINVAL; param = param_item->param; @@ -3142,17 +3187,28 @@ static int devlink_nl_cmd_param_set_doit(struct sk_buff *skb, return err; } - devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW); + devlink_param_notify(devlink, port_index, param_item, cmd); return 0; } +static int devlink_nl_cmd_param_set_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + + return __devlink_nl_cmd_param_set_doit(devlink, 0, &devlink->param_list, + info, DEVLINK_CMD_PARAM_NEW); +} + static int devlink_param_register_one(struct devlink *devlink, - const struct devlink_param *param) + unsigned int port_index, + struct list_head *param_list, + const struct devlink_param *param, + enum devlink_command cmd) { struct devlink_param_item *param_item; - if (devlink_param_find_by_name(&devlink->param_list, - param->name)) + if (devlink_param_find_by_name(param_list, param->name)) return -EEXIST; if (param->supported_cmodes == BIT(DEVLINK_PARAM_CMODE_DRIVERINIT)) @@ -3165,24 +3221,111 @@ static int devlink_param_register_one(struct devlink *devlink, return -ENOMEM; param_item->param = param; - list_add_tail(¶m_item->list, &devlink->param_list); - devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW); + list_add_tail(¶m_item->list, param_list); + devlink_param_notify(devlink, port_index, param_item, cmd); return 0; } static void devlink_param_unregister_one(struct devlink *devlink, - const struct devlink_param *param) + unsigned int port_index, + struct list_head *param_list, + const struct devlink_param *param, + enum devlink_command cmd) { struct devlink_param_item *param_item; - param_item = devlink_param_find_by_name(&devlink->param_list, - param->name); + param_item = devlink_param_find_by_name(param_list, param->name); WARN_ON(!param_item); - devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_DEL); + devlink_param_notify(devlink, port_index, param_item, cmd); list_del(¶m_item->list); kfree(param_item); } +static int devlink_nl_cmd_port_param_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink_param_item *param_item; + struct devlink_port *devlink_port; + struct devlink *devlink; + int start = cb->args[0]; + int idx = 0; + int err; + + mutex_lock(&devlink_mutex); + list_for_each_entry(devlink, &devlink_list, list) { + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + continue; + mutex_lock(&devlink->lock); + list_for_each_entry(devlink_port, &devlink->port_list, list) { + list_for_each_entry(param_item, + &devlink_port->param_list, list) { + if (idx < start) { + idx++; + continue; + } + err = devlink_nl_param_fill(msg, + devlink_port->devlink, + devlink_port->index, param_item, + DEVLINK_CMD_PORT_PARAM_GET, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI); + if (err) { + mutex_unlock(&devlink->lock); + goto out; + } + idx++; + } + } + mutex_unlock(&devlink->lock); + } +out: + mutex_unlock(&devlink_mutex); + + cb->args[0] = idx; + return msg->len; +} + +static int devlink_nl_cmd_port_param_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink_port *devlink_port = info->user_ptr[0]; + struct devlink_param_item *param_item; + struct sk_buff *msg; + int err; + + param_item = devlink_param_get_from_info(&devlink_port->param_list, + info); + if (!param_item) + return -EINVAL; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_param_fill(msg, devlink_port->devlink, + devlink_port->index, param_item, + DEVLINK_CMD_PORT_PARAM_GET, + info->snd_portid, info->snd_seq, 0); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int devlink_nl_cmd_port_param_set_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink_port *devlink_port = info->user_ptr[0]; + + return __devlink_nl_cmd_param_set_doit(devlink_port->devlink, + devlink_port->index, + &devlink_port->param_list, info, + DEVLINK_CMD_PORT_PARAM_NEW); +} + static int devlink_nl_region_snapshot_id_put(struct sk_buff *msg, struct devlink *devlink, struct devlink_snapshot *snapshot) @@ -3504,44 +3647,56 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { u64 ret_offset, start_offset, end_offset = 0; - struct nlattr *attrs[DEVLINK_ATTR_MAX + 1]; const struct genl_ops *ops = cb->data; struct devlink_region *region; struct nlattr *chunks_attr; const char *region_name; struct devlink *devlink; + struct nlattr **attrs; bool dump = true; void *hdr; int err; start_offset = *((u64 *)&cb->args[0]); + attrs = kmalloc_array(DEVLINK_ATTR_MAX + 1, sizeof(*attrs), GFP_KERNEL); + if (!attrs) + return -ENOMEM; + err = nlmsg_parse(cb->nlh, GENL_HDRLEN + devlink_nl_family.hdrsize, attrs, DEVLINK_ATTR_MAX, ops->policy, cb->extack); if (err) - goto out; + goto out_free; + mutex_lock(&devlink_mutex); devlink = devlink_get_from_attrs(sock_net(cb->skb->sk), attrs); - if (IS_ERR(devlink)) - goto out; + if (IS_ERR(devlink)) { + err = PTR_ERR(devlink); + goto out_dev; + } - mutex_lock(&devlink_mutex); mutex_lock(&devlink->lock); if (!attrs[DEVLINK_ATTR_REGION_NAME] || - !attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]) + !attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]) { + err = -EINVAL; goto out_unlock; + } region_name = nla_data(attrs[DEVLINK_ATTR_REGION_NAME]); region = devlink_region_get_by_name(devlink, region_name); - if (!region) + if (!region) { + err = -EINVAL; goto out_unlock; + } hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &devlink_nl_family, NLM_F_ACK | NLM_F_MULTI, DEVLINK_CMD_REGION_READ); - if (!hdr) + if (!hdr) { + err = -EMSGSIZE; goto out_unlock; + } err = devlink_nl_put_handle(skb, devlink); if (err) @@ -3552,8 +3707,10 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, goto nla_put_failure; chunks_attr = nla_nest_start(skb, DEVLINK_ATTR_REGION_CHUNKS); - if (!chunks_attr) + if (!chunks_attr) { + err = -EMSGSIZE; goto nla_put_failure; + } if (attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR] && attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]) { @@ -3576,8 +3733,10 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, goto nla_put_failure; /* Check if there was any progress done to prevent infinite loop */ - if (ret_offset == start_offset) + if (ret_offset == start_offset) { + err = -EINVAL; goto nla_put_failure; + } *((u64 *)&cb->args[0]) = ret_offset; @@ -3585,6 +3744,7 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, genlmsg_end(skb, hdr); mutex_unlock(&devlink->lock); mutex_unlock(&devlink_mutex); + kfree(attrs); return skb->len; @@ -3592,8 +3752,1127 @@ nla_put_failure: genlmsg_cancel(skb, hdr); out_unlock: mutex_unlock(&devlink->lock); +out_dev: + mutex_unlock(&devlink_mutex); +out_free: + kfree(attrs); + return err; +} + +struct devlink_info_req { + struct sk_buff *msg; +}; + +int devlink_info_driver_name_put(struct devlink_info_req *req, const char *name) +{ + return nla_put_string(req->msg, DEVLINK_ATTR_INFO_DRIVER_NAME, name); +} +EXPORT_SYMBOL_GPL(devlink_info_driver_name_put); + +int devlink_info_serial_number_put(struct devlink_info_req *req, const char *sn) +{ + return nla_put_string(req->msg, DEVLINK_ATTR_INFO_SERIAL_NUMBER, sn); +} +EXPORT_SYMBOL_GPL(devlink_info_serial_number_put); + +static int devlink_info_version_put(struct devlink_info_req *req, int attr, + const char *version_name, + const char *version_value) +{ + struct nlattr *nest; + int err; + + nest = nla_nest_start(req->msg, attr); + if (!nest) + return -EMSGSIZE; + + err = nla_put_string(req->msg, DEVLINK_ATTR_INFO_VERSION_NAME, + version_name); + if (err) + goto nla_put_failure; + + err = nla_put_string(req->msg, DEVLINK_ATTR_INFO_VERSION_VALUE, + version_value); + if (err) + goto nla_put_failure; + + nla_nest_end(req->msg, nest); + + return 0; + +nla_put_failure: + nla_nest_cancel(req->msg, nest); + return err; +} + +int devlink_info_version_fixed_put(struct devlink_info_req *req, + const char *version_name, + const char *version_value) +{ + return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_FIXED, + version_name, version_value); +} +EXPORT_SYMBOL_GPL(devlink_info_version_fixed_put); + +int devlink_info_version_stored_put(struct devlink_info_req *req, + const char *version_name, + const char *version_value) +{ + return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_STORED, + version_name, version_value); +} +EXPORT_SYMBOL_GPL(devlink_info_version_stored_put); + +int devlink_info_version_running_put(struct devlink_info_req *req, + const char *version_name, + const char *version_value) +{ + return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_RUNNING, + version_name, version_value); +} +EXPORT_SYMBOL_GPL(devlink_info_version_running_put); + +static int +devlink_nl_info_fill(struct sk_buff *msg, struct devlink *devlink, + enum devlink_command cmd, u32 portid, + u32 seq, int flags, struct netlink_ext_ack *extack) +{ + struct devlink_info_req req; + void *hdr; + int err; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + err = -EMSGSIZE; + if (devlink_nl_put_handle(msg, devlink)) + goto err_cancel_msg; + + req.msg = msg; + err = devlink->ops->info_get(devlink, &req, extack); + if (err) + goto err_cancel_msg; + + genlmsg_end(msg, hdr); + return 0; + +err_cancel_msg: + genlmsg_cancel(msg, hdr); + return err; +} + +static int devlink_nl_cmd_info_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct sk_buff *msg; + int err; + + if (!devlink->ops || !devlink->ops->info_get) + return -EOPNOTSUPP; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_info_fill(msg, devlink, DEVLINK_CMD_INFO_GET, + info->snd_portid, info->snd_seq, 0, + info->extack); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int devlink_nl_cmd_info_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink *devlink; + int start = cb->args[0]; + int idx = 0; + int err; + + mutex_lock(&devlink_mutex); + list_for_each_entry(devlink, &devlink_list, list) { + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + continue; + if (idx < start) { + idx++; + continue; + } + + mutex_lock(&devlink->lock); + err = devlink_nl_info_fill(msg, devlink, DEVLINK_CMD_INFO_GET, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + cb->extack); + mutex_unlock(&devlink->lock); + if (err) + break; + idx++; + } + mutex_unlock(&devlink_mutex); + + cb->args[0] = idx; + return msg->len; +} + +struct devlink_fmsg_item { + struct list_head list; + int attrtype; + u8 nla_type; + u16 len; + int value[0]; +}; + +struct devlink_fmsg { + struct list_head item_list; +}; + +static struct devlink_fmsg *devlink_fmsg_alloc(void) +{ + struct devlink_fmsg *fmsg; + + fmsg = kzalloc(sizeof(*fmsg), GFP_KERNEL); + if (!fmsg) + return NULL; + + INIT_LIST_HEAD(&fmsg->item_list); + + return fmsg; +} + +static void devlink_fmsg_free(struct devlink_fmsg *fmsg) +{ + struct devlink_fmsg_item *item, *tmp; + + list_for_each_entry_safe(item, tmp, &fmsg->item_list, list) { + list_del(&item->list); + kfree(item); + } + kfree(fmsg); +} + +static int devlink_fmsg_nest_common(struct devlink_fmsg *fmsg, + int attrtype) +{ + struct devlink_fmsg_item *item; + + item = kzalloc(sizeof(*item), GFP_KERNEL); + if (!item) + return -ENOMEM; + + item->attrtype = attrtype; + list_add_tail(&item->list, &fmsg->item_list); + + return 0; +} + +int devlink_fmsg_obj_nest_start(struct devlink_fmsg *fmsg) +{ + return devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_OBJ_NEST_START); +} +EXPORT_SYMBOL_GPL(devlink_fmsg_obj_nest_start); + +static int devlink_fmsg_nest_end(struct devlink_fmsg *fmsg) +{ + return devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_NEST_END); +} + +int devlink_fmsg_obj_nest_end(struct devlink_fmsg *fmsg) +{ + return devlink_fmsg_nest_end(fmsg); +} +EXPORT_SYMBOL_GPL(devlink_fmsg_obj_nest_end); + +#define DEVLINK_FMSG_MAX_SIZE (GENLMSG_DEFAULT_SIZE - GENL_HDRLEN - NLA_HDRLEN) + +static int devlink_fmsg_put_name(struct devlink_fmsg *fmsg, const char *name) +{ + struct devlink_fmsg_item *item; + + if (strlen(name) + 1 > DEVLINK_FMSG_MAX_SIZE) + return -EMSGSIZE; + + item = kzalloc(sizeof(*item) + strlen(name) + 1, GFP_KERNEL); + if (!item) + return -ENOMEM; + + item->nla_type = NLA_NUL_STRING; + item->len = strlen(name) + 1; + item->attrtype = DEVLINK_ATTR_FMSG_OBJ_NAME; + memcpy(&item->value, name, item->len); + list_add_tail(&item->list, &fmsg->item_list); + + return 0; +} + +int devlink_fmsg_pair_nest_start(struct devlink_fmsg *fmsg, const char *name) +{ + int err; + + err = devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_PAIR_NEST_START); + if (err) + return err; + + err = devlink_fmsg_put_name(fmsg, name); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_fmsg_pair_nest_start); + +int devlink_fmsg_pair_nest_end(struct devlink_fmsg *fmsg) +{ + return devlink_fmsg_nest_end(fmsg); +} +EXPORT_SYMBOL_GPL(devlink_fmsg_pair_nest_end); + +int devlink_fmsg_arr_pair_nest_start(struct devlink_fmsg *fmsg, + const char *name) +{ + int err; + + err = devlink_fmsg_pair_nest_start(fmsg, name); + if (err) + return err; + + err = devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_ARR_NEST_START); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_fmsg_arr_pair_nest_start); + +int devlink_fmsg_arr_pair_nest_end(struct devlink_fmsg *fmsg) +{ + int err; + + err = devlink_fmsg_nest_end(fmsg); + if (err) + return err; + + err = devlink_fmsg_nest_end(fmsg); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_fmsg_arr_pair_nest_end); + +static int devlink_fmsg_put_value(struct devlink_fmsg *fmsg, + const void *value, u16 value_len, + u8 value_nla_type) +{ + struct devlink_fmsg_item *item; + + if (value_len > DEVLINK_FMSG_MAX_SIZE) + return -EMSGSIZE; + + item = kzalloc(sizeof(*item) + value_len, GFP_KERNEL); + if (!item) + return -ENOMEM; + + item->nla_type = value_nla_type; + item->len = value_len; + item->attrtype = DEVLINK_ATTR_FMSG_OBJ_VALUE_DATA; + memcpy(&item->value, value, item->len); + list_add_tail(&item->list, &fmsg->item_list); + + return 0; +} + +int devlink_fmsg_bool_put(struct devlink_fmsg *fmsg, bool value) +{ + return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_FLAG); +} +EXPORT_SYMBOL_GPL(devlink_fmsg_bool_put); + +int devlink_fmsg_u8_put(struct devlink_fmsg *fmsg, u8 value) +{ + return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U8); +} +EXPORT_SYMBOL_GPL(devlink_fmsg_u8_put); + +int devlink_fmsg_u32_put(struct devlink_fmsg *fmsg, u32 value) +{ + return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U32); +} +EXPORT_SYMBOL_GPL(devlink_fmsg_u32_put); + +int devlink_fmsg_u64_put(struct devlink_fmsg *fmsg, u64 value) +{ + return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U64); +} +EXPORT_SYMBOL_GPL(devlink_fmsg_u64_put); + +int devlink_fmsg_string_put(struct devlink_fmsg *fmsg, const char *value) +{ + return devlink_fmsg_put_value(fmsg, value, strlen(value) + 1, + NLA_NUL_STRING); +} +EXPORT_SYMBOL_GPL(devlink_fmsg_string_put); + +int devlink_fmsg_binary_put(struct devlink_fmsg *fmsg, const void *value, + u16 value_len) +{ + return devlink_fmsg_put_value(fmsg, value, value_len, NLA_BINARY); +} +EXPORT_SYMBOL_GPL(devlink_fmsg_binary_put); + +int devlink_fmsg_bool_pair_put(struct devlink_fmsg *fmsg, const char *name, + bool value) +{ + int err; + + err = devlink_fmsg_pair_nest_start(fmsg, name); + if (err) + return err; + + err = devlink_fmsg_bool_put(fmsg, value); + if (err) + return err; + + err = devlink_fmsg_pair_nest_end(fmsg); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_fmsg_bool_pair_put); + +int devlink_fmsg_u8_pair_put(struct devlink_fmsg *fmsg, const char *name, + u8 value) +{ + int err; + + err = devlink_fmsg_pair_nest_start(fmsg, name); + if (err) + return err; + + err = devlink_fmsg_u8_put(fmsg, value); + if (err) + return err; + + err = devlink_fmsg_pair_nest_end(fmsg); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_fmsg_u8_pair_put); + +int devlink_fmsg_u32_pair_put(struct devlink_fmsg *fmsg, const char *name, + u32 value) +{ + int err; + + err = devlink_fmsg_pair_nest_start(fmsg, name); + if (err) + return err; + + err = devlink_fmsg_u32_put(fmsg, value); + if (err) + return err; + + err = devlink_fmsg_pair_nest_end(fmsg); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_fmsg_u32_pair_put); + +int devlink_fmsg_u64_pair_put(struct devlink_fmsg *fmsg, const char *name, + u64 value) +{ + int err; + + err = devlink_fmsg_pair_nest_start(fmsg, name); + if (err) + return err; + + err = devlink_fmsg_u64_put(fmsg, value); + if (err) + return err; + + err = devlink_fmsg_pair_nest_end(fmsg); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_fmsg_u64_pair_put); + +int devlink_fmsg_string_pair_put(struct devlink_fmsg *fmsg, const char *name, + const char *value) +{ + int err; + + err = devlink_fmsg_pair_nest_start(fmsg, name); + if (err) + return err; + + err = devlink_fmsg_string_put(fmsg, value); + if (err) + return err; + + err = devlink_fmsg_pair_nest_end(fmsg); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_fmsg_string_pair_put); + +int devlink_fmsg_binary_pair_put(struct devlink_fmsg *fmsg, const char *name, + const void *value, u16 value_len) +{ + int err; + + err = devlink_fmsg_pair_nest_start(fmsg, name); + if (err) + return err; + + err = devlink_fmsg_binary_put(fmsg, value, value_len); + if (err) + return err; + + err = devlink_fmsg_pair_nest_end(fmsg); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_fmsg_binary_pair_put); + +static int +devlink_fmsg_item_fill_type(struct devlink_fmsg_item *msg, struct sk_buff *skb) +{ + switch (msg->nla_type) { + case NLA_FLAG: + case NLA_U8: + case NLA_U32: + case NLA_U64: + case NLA_NUL_STRING: + case NLA_BINARY: + return nla_put_u8(skb, DEVLINK_ATTR_FMSG_OBJ_VALUE_TYPE, + msg->nla_type); + default: + return -EINVAL; + } +} + +static int +devlink_fmsg_item_fill_data(struct devlink_fmsg_item *msg, struct sk_buff *skb) +{ + int attrtype = DEVLINK_ATTR_FMSG_OBJ_VALUE_DATA; + u8 tmp; + + switch (msg->nla_type) { + case NLA_FLAG: + /* Always provide flag data, regardless of its value */ + tmp = *(bool *) msg->value; + + return nla_put_u8(skb, attrtype, tmp); + case NLA_U8: + return nla_put_u8(skb, attrtype, *(u8 *) msg->value); + case NLA_U32: + return nla_put_u32(skb, attrtype, *(u32 *) msg->value); + case NLA_U64: + return nla_put_u64_64bit(skb, attrtype, *(u64 *) msg->value, + DEVLINK_ATTR_PAD); + case NLA_NUL_STRING: + return nla_put_string(skb, attrtype, (char *) &msg->value); + case NLA_BINARY: + return nla_put(skb, attrtype, msg->len, (void *) &msg->value); + default: + return -EINVAL; + } +} + +static int +devlink_fmsg_prepare_skb(struct devlink_fmsg *fmsg, struct sk_buff *skb, + int *start) +{ + struct devlink_fmsg_item *item; + struct nlattr *fmsg_nlattr; + int i = 0; + int err; + + fmsg_nlattr = nla_nest_start(skb, DEVLINK_ATTR_FMSG); + if (!fmsg_nlattr) + return -EMSGSIZE; + + list_for_each_entry(item, &fmsg->item_list, list) { + if (i < *start) { + i++; + continue; + } + + switch (item->attrtype) { + case DEVLINK_ATTR_FMSG_OBJ_NEST_START: + case DEVLINK_ATTR_FMSG_PAIR_NEST_START: + case DEVLINK_ATTR_FMSG_ARR_NEST_START: + case DEVLINK_ATTR_FMSG_NEST_END: + err = nla_put_flag(skb, item->attrtype); + break; + case DEVLINK_ATTR_FMSG_OBJ_VALUE_DATA: + err = devlink_fmsg_item_fill_type(item, skb); + if (err) + break; + err = devlink_fmsg_item_fill_data(item, skb); + break; + case DEVLINK_ATTR_FMSG_OBJ_NAME: + err = nla_put_string(skb, item->attrtype, + (char *) &item->value); + break; + default: + err = -EINVAL; + break; + } + if (!err) + *start = ++i; + else + break; + } + + nla_nest_end(skb, fmsg_nlattr); + return err; +} + +static int devlink_fmsg_snd(struct devlink_fmsg *fmsg, + struct genl_info *info, + enum devlink_command cmd, int flags) +{ + struct nlmsghdr *nlh; + struct sk_buff *skb; + bool last = false; + int index = 0; + void *hdr; + int err; + + while (!last) { + int tmp_index = index; + + skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!skb) + return -ENOMEM; + + hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq, + &devlink_nl_family, flags | NLM_F_MULTI, cmd); + if (!hdr) { + err = -EMSGSIZE; + goto nla_put_failure; + } + + err = devlink_fmsg_prepare_skb(fmsg, skb, &index); + if (!err) + last = true; + else if (err != -EMSGSIZE || tmp_index == index) + goto nla_put_failure; + + genlmsg_end(skb, hdr); + err = genlmsg_reply(skb, info); + if (err) + return err; + } + + skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!skb) + return -ENOMEM; + nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq, + NLMSG_DONE, 0, flags | NLM_F_MULTI); + if (!nlh) { + err = -EMSGSIZE; + goto nla_put_failure; + } + + return genlmsg_reply(skb, info); + +nla_put_failure: + nlmsg_free(skb); + return err; +} + +struct devlink_health_reporter { + struct list_head list; + void *priv; + const struct devlink_health_reporter_ops *ops; + struct devlink *devlink; + struct devlink_fmsg *dump_fmsg; + struct mutex dump_lock; /* lock parallel read/write from dump buffers */ + u64 graceful_period; + bool auto_recover; + u8 health_state; + u64 dump_ts; + u64 error_count; + u64 recovery_count; + u64 last_recovery_ts; +}; + +enum devlink_health_reporter_state { + DEVLINK_HEALTH_REPORTER_STATE_HEALTHY, + DEVLINK_HEALTH_REPORTER_STATE_ERROR, +}; + +void * +devlink_health_reporter_priv(struct devlink_health_reporter *reporter) +{ + return reporter->priv; +} +EXPORT_SYMBOL_GPL(devlink_health_reporter_priv); + +static struct devlink_health_reporter * +devlink_health_reporter_find_by_name(struct devlink *devlink, + const char *reporter_name) +{ + struct devlink_health_reporter *reporter; + + list_for_each_entry(reporter, &devlink->reporter_list, list) + if (!strcmp(reporter->ops->name, reporter_name)) + return reporter; + return NULL; +} + +/** + * devlink_health_reporter_create - create devlink health reporter + * + * @devlink: devlink + * @ops: ops + * @graceful_period: to avoid recovery loops, in msecs + * @auto_recover: auto recover when error occurs + * @priv: priv + */ +struct devlink_health_reporter * +devlink_health_reporter_create(struct devlink *devlink, + const struct devlink_health_reporter_ops *ops, + u64 graceful_period, bool auto_recover, + void *priv) +{ + struct devlink_health_reporter *reporter; + + mutex_lock(&devlink->lock); + if (devlink_health_reporter_find_by_name(devlink, ops->name)) { + reporter = ERR_PTR(-EEXIST); + goto unlock; + } + + if (WARN_ON(auto_recover && !ops->recover) || + WARN_ON(graceful_period && !ops->recover)) { + reporter = ERR_PTR(-EINVAL); + goto unlock; + } + + reporter = kzalloc(sizeof(*reporter), GFP_KERNEL); + if (!reporter) { + reporter = ERR_PTR(-ENOMEM); + goto unlock; + } + + reporter->priv = priv; + reporter->ops = ops; + reporter->devlink = devlink; + reporter->graceful_period = graceful_period; + reporter->auto_recover = auto_recover; + mutex_init(&reporter->dump_lock); + list_add_tail(&reporter->list, &devlink->reporter_list); +unlock: + mutex_unlock(&devlink->lock); + return reporter; +} +EXPORT_SYMBOL_GPL(devlink_health_reporter_create); + +/** + * devlink_health_reporter_destroy - destroy devlink health reporter + * + * @reporter: devlink health reporter to destroy + */ +void +devlink_health_reporter_destroy(struct devlink_health_reporter *reporter) +{ + mutex_lock(&reporter->devlink->lock); + list_del(&reporter->list); + mutex_unlock(&reporter->devlink->lock); + if (reporter->dump_fmsg) + devlink_fmsg_free(reporter->dump_fmsg); + kfree(reporter); +} +EXPORT_SYMBOL_GPL(devlink_health_reporter_destroy); + +static int +devlink_health_reporter_recover(struct devlink_health_reporter *reporter, + void *priv_ctx) +{ + int err; + + if (!reporter->ops->recover) + return -EOPNOTSUPP; + + err = reporter->ops->recover(reporter, priv_ctx); + if (err) + return err; + + reporter->recovery_count++; + reporter->health_state = DEVLINK_HEALTH_REPORTER_STATE_HEALTHY; + reporter->last_recovery_ts = jiffies; + + return 0; +} + +static void +devlink_health_dump_clear(struct devlink_health_reporter *reporter) +{ + if (!reporter->dump_fmsg) + return; + devlink_fmsg_free(reporter->dump_fmsg); + reporter->dump_fmsg = NULL; +} + +static int devlink_health_do_dump(struct devlink_health_reporter *reporter, + void *priv_ctx) +{ + int err; + + if (!reporter->ops->dump) + return 0; + + if (reporter->dump_fmsg) + return 0; + + reporter->dump_fmsg = devlink_fmsg_alloc(); + if (!reporter->dump_fmsg) { + err = -ENOMEM; + return err; + } + + err = devlink_fmsg_obj_nest_start(reporter->dump_fmsg); + if (err) + goto dump_err; + + err = reporter->ops->dump(reporter, reporter->dump_fmsg, + priv_ctx); + if (err) + goto dump_err; + + err = devlink_fmsg_obj_nest_end(reporter->dump_fmsg); + if (err) + goto dump_err; + + reporter->dump_ts = jiffies; + + return 0; + +dump_err: + devlink_health_dump_clear(reporter); + return err; +} + +int devlink_health_report(struct devlink_health_reporter *reporter, + const char *msg, void *priv_ctx) +{ + struct devlink *devlink = reporter->devlink; + + /* write a log message of the current error */ + WARN_ON(!msg); + trace_devlink_health_report(devlink, reporter->ops->name, msg); + reporter->error_count++; + + /* abort if the previous error wasn't recovered */ + if (reporter->auto_recover && + (reporter->health_state != DEVLINK_HEALTH_REPORTER_STATE_HEALTHY || + jiffies - reporter->last_recovery_ts < + msecs_to_jiffies(reporter->graceful_period))) { + trace_devlink_health_recover_aborted(devlink, + reporter->ops->name, + reporter->health_state, + jiffies - + reporter->last_recovery_ts); + return -ECANCELED; + } + + reporter->health_state = DEVLINK_HEALTH_REPORTER_STATE_ERROR; + + mutex_lock(&reporter->dump_lock); + /* store current dump of current error, for later analysis */ + devlink_health_do_dump(reporter, priv_ctx); + mutex_unlock(&reporter->dump_lock); + + if (reporter->auto_recover) + return devlink_health_reporter_recover(reporter, priv_ctx); + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_health_report); + +static struct devlink_health_reporter * +devlink_health_reporter_get_from_info(struct devlink *devlink, + struct genl_info *info) +{ + char *reporter_name; + + if (!info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_NAME]) + return NULL; + + reporter_name = + nla_data(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_NAME]); + return devlink_health_reporter_find_by_name(devlink, reporter_name); +} + +static int +devlink_nl_health_reporter_fill(struct sk_buff *msg, + struct devlink *devlink, + struct devlink_health_reporter *reporter, + enum devlink_command cmd, u32 portid, + u32 seq, int flags) +{ + struct nlattr *reporter_attr; + void *hdr; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto genlmsg_cancel; + + reporter_attr = nla_nest_start(msg, DEVLINK_ATTR_HEALTH_REPORTER); + if (!reporter_attr) + goto genlmsg_cancel; + if (nla_put_string(msg, DEVLINK_ATTR_HEALTH_REPORTER_NAME, + reporter->ops->name)) + goto reporter_nest_cancel; + if (nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_STATE, + reporter->health_state)) + goto reporter_nest_cancel; + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_ERR, + reporter->error_count, DEVLINK_ATTR_PAD)) + goto reporter_nest_cancel; + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_RECOVER, + reporter->recovery_count, DEVLINK_ATTR_PAD)) + goto reporter_nest_cancel; + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD, + reporter->graceful_period, + DEVLINK_ATTR_PAD)) + goto reporter_nest_cancel; + if (nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER, + reporter->auto_recover)) + goto reporter_nest_cancel; + if (reporter->dump_fmsg && + nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS, + jiffies_to_msecs(reporter->dump_ts), + DEVLINK_ATTR_PAD)) + goto reporter_nest_cancel; + + nla_nest_end(msg, reporter_attr); + genlmsg_end(msg, hdr); + return 0; + +reporter_nest_cancel: + nla_nest_end(msg, reporter_attr); +genlmsg_cancel: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static int devlink_nl_cmd_health_reporter_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_health_reporter *reporter; + struct sk_buff *msg; + int err; + + reporter = devlink_health_reporter_get_from_info(devlink, info); + if (!reporter) + return -EINVAL; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_health_reporter_fill(msg, devlink, reporter, + DEVLINK_CMD_HEALTH_REPORTER_GET, + info->snd_portid, info->snd_seq, + 0); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int +devlink_nl_cmd_health_reporter_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink_health_reporter *reporter; + struct devlink *devlink; + int start = cb->args[0]; + int idx = 0; + int err; + + mutex_lock(&devlink_mutex); + list_for_each_entry(devlink, &devlink_list, list) { + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + continue; + mutex_lock(&devlink->lock); + list_for_each_entry(reporter, &devlink->reporter_list, + list) { + if (idx < start) { + idx++; + continue; + } + err = devlink_nl_health_reporter_fill(msg, devlink, + reporter, + DEVLINK_CMD_HEALTH_REPORTER_GET, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI); + if (err) { + mutex_unlock(&devlink->lock); + goto out; + } + idx++; + } + mutex_unlock(&devlink->lock); + } +out: mutex_unlock(&devlink_mutex); + + cb->args[0] = idx; + return msg->len; +} + +static int +devlink_nl_cmd_health_reporter_set_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_health_reporter *reporter; + + reporter = devlink_health_reporter_get_from_info(devlink, info); + if (!reporter) + return -EINVAL; + + if (!reporter->ops->recover && + (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] || + info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER])) + return -EOPNOTSUPP; + + if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD]) + reporter->graceful_period = + nla_get_u64(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD]); + + if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER]) + reporter->auto_recover = + nla_get_u8(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER]); + + return 0; +} + +static int devlink_nl_cmd_health_reporter_recover_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_health_reporter *reporter; + + reporter = devlink_health_reporter_get_from_info(devlink, info); + if (!reporter) + return -EINVAL; + + return devlink_health_reporter_recover(reporter, NULL); +} + +static int devlink_nl_cmd_health_reporter_diagnose_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_health_reporter *reporter; + struct devlink_fmsg *fmsg; + int err; + + reporter = devlink_health_reporter_get_from_info(devlink, info); + if (!reporter) + return -EINVAL; + + if (!reporter->ops->diagnose) + return -EOPNOTSUPP; + + fmsg = devlink_fmsg_alloc(); + if (!fmsg) + return -ENOMEM; + + err = devlink_fmsg_obj_nest_start(fmsg); + if (err) + goto out; + + err = reporter->ops->diagnose(reporter, fmsg); + if (err) + goto out; + + err = devlink_fmsg_obj_nest_end(fmsg); + if (err) + goto out; + + err = devlink_fmsg_snd(fmsg, info, + DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, 0); + out: + devlink_fmsg_free(fmsg); + return err; +} + +static int devlink_nl_cmd_health_reporter_dump_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_health_reporter *reporter; + int err; + + reporter = devlink_health_reporter_get_from_info(devlink, info); + if (!reporter) + return -EINVAL; + + if (!reporter->ops->dump) + return -EOPNOTSUPP; + + mutex_lock(&reporter->dump_lock); + err = devlink_health_do_dump(reporter, NULL); + if (err) + goto out; + + err = devlink_fmsg_snd(reporter->dump_fmsg, info, + DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET, 0); + +out: + mutex_unlock(&reporter->dump_lock); + return err; +} + +static int +devlink_nl_cmd_health_reporter_dump_clear_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_health_reporter *reporter; + + reporter = devlink_health_reporter_get_from_info(devlink, info); + if (!reporter) + return -EINVAL; + + if (!reporter->ops->dump) + return -EOPNOTSUPP; + + mutex_lock(&reporter->dump_lock); + devlink_health_dump_clear(reporter); + mutex_unlock(&reporter->dump_lock); return 0; } @@ -3622,6 +4901,11 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_PARAM_VALUE_CMODE] = { .type = NLA_U8 }, [DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .type = NLA_U32 }, + [DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] = { .type = NLA_U64 }, + [DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] = { .type = NLA_U8 }, + [DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_FLASH_UPDATE_COMPONENT] = { .type = NLA_NUL_STRING }, }; static const struct genl_ops devlink_nl_ops[] = { @@ -3821,6 +5105,21 @@ static const struct genl_ops devlink_nl_ops[] = { .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, { + .cmd = DEVLINK_CMD_PORT_PARAM_GET, + .doit = devlink_nl_cmd_port_param_get_doit, + .dumpit = devlink_nl_cmd_port_param_get_dumpit, + .policy = devlink_nl_policy, + .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_PORT_PARAM_SET, + .doit = devlink_nl_cmd_port_param_set_doit, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, + }, + { .cmd = DEVLINK_CMD_REGION_GET, .doit = devlink_nl_cmd_region_get_doit, .dumpit = devlink_nl_cmd_region_get_dumpit, @@ -3842,6 +5141,66 @@ static const struct genl_ops devlink_nl_ops[] = { .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, + { + .cmd = DEVLINK_CMD_INFO_GET, + .doit = devlink_nl_cmd_info_get_doit, + .dumpit = devlink_nl_cmd_info_get_dumpit, + .policy = devlink_nl_policy, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_GET, + .doit = devlink_nl_cmd_health_reporter_get_doit, + .dumpit = devlink_nl_cmd_health_reporter_get_dumpit, + .policy = devlink_nl_policy, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_SET, + .doit = devlink_nl_cmd_health_reporter_set_doit, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_RECOVER, + .doit = devlink_nl_cmd_health_reporter_recover_doit, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, + .doit = devlink_nl_cmd_health_reporter_diagnose_doit, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET, + .doit = devlink_nl_cmd_health_reporter_dump_get_doit, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | + DEVLINK_NL_FLAG_NO_LOCK, + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR, + .doit = devlink_nl_cmd_health_reporter_dump_clear_doit, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | + DEVLINK_NL_FLAG_NO_LOCK, + }, + { + .cmd = DEVLINK_CMD_FLASH_UPDATE, + .doit = devlink_nl_cmd_flash_update, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + }, }; static struct genl_family devlink_nl_family __ro_after_init = { @@ -3882,6 +5241,7 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size) INIT_LIST_HEAD(&devlink->resource_list); INIT_LIST_HEAD(&devlink->param_list); INIT_LIST_HEAD(&devlink->region_list); + INIT_LIST_HEAD(&devlink->reporter_list); mutex_init(&devlink->lock); return devlink; } @@ -3924,6 +5284,14 @@ EXPORT_SYMBOL_GPL(devlink_unregister); */ void devlink_free(struct devlink *devlink) { + WARN_ON(!list_empty(&devlink->reporter_list)); + WARN_ON(!list_empty(&devlink->region_list)); + WARN_ON(!list_empty(&devlink->param_list)); + WARN_ON(!list_empty(&devlink->resource_list)); + WARN_ON(!list_empty(&devlink->dpipe_table_list)); + WARN_ON(!list_empty(&devlink->sb_list)); + WARN_ON(!list_empty(&devlink->port_list)); + kfree(devlink); } EXPORT_SYMBOL_GPL(devlink_free); @@ -3954,6 +5322,7 @@ int devlink_port_register(struct devlink *devlink, devlink_port->index = port_index; devlink_port->registered = true; list_add_tail(&devlink_port->list, &devlink->port_list); + INIT_LIST_HEAD(&devlink_port->param_list); mutex_unlock(&devlink->lock); devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); return 0; @@ -4471,18 +5840,23 @@ out: } EXPORT_SYMBOL_GPL(devlink_resource_occ_get_unregister); -/** - * devlink_params_register - register configuration parameters - * - * @devlink: devlink - * @params: configuration parameters array - * @params_count: number of parameters provided - * - * Register the configuration parameters supported by the driver. - */ -int devlink_params_register(struct devlink *devlink, - const struct devlink_param *params, - size_t params_count) +static int devlink_param_verify(const struct devlink_param *param) +{ + if (!param || !param->name || !param->supported_cmodes) + return -EINVAL; + if (param->generic) + return devlink_param_generic_verify(param); + else + return devlink_param_driver_verify(param); +} + +static int __devlink_params_register(struct devlink *devlink, + unsigned int port_index, + struct list_head *param_list, + const struct devlink_param *params, + size_t params_count, + enum devlink_command reg_cmd, + enum devlink_command unreg_cmd) { const struct devlink_param *param = params; int i; @@ -4490,20 +5864,12 @@ int devlink_params_register(struct devlink *devlink, mutex_lock(&devlink->lock); for (i = 0; i < params_count; i++, param++) { - if (!param || !param->name || !param->supported_cmodes) { - err = -EINVAL; + err = devlink_param_verify(param); + if (err) goto rollback; - } - if (param->generic) { - err = devlink_param_generic_verify(param); - if (err) - goto rollback; - } else { - err = devlink_param_driver_verify(param); - if (err) - goto rollback; - } - err = devlink_param_register_one(devlink, param); + + err = devlink_param_register_one(devlink, port_index, + param_list, param, reg_cmd); if (err) goto rollback; } @@ -4515,11 +5881,48 @@ rollback: if (!i) goto unlock; for (param--; i > 0; i--, param--) - devlink_param_unregister_one(devlink, param); + devlink_param_unregister_one(devlink, port_index, param_list, + param, unreg_cmd); unlock: mutex_unlock(&devlink->lock); return err; } + +static void __devlink_params_unregister(struct devlink *devlink, + unsigned int port_index, + struct list_head *param_list, + const struct devlink_param *params, + size_t params_count, + enum devlink_command cmd) +{ + const struct devlink_param *param = params; + int i; + + mutex_lock(&devlink->lock); + for (i = 0; i < params_count; i++, param++) + devlink_param_unregister_one(devlink, 0, param_list, param, + cmd); + mutex_unlock(&devlink->lock); +} + +/** + * devlink_params_register - register configuration parameters + * + * @devlink: devlink + * @params: configuration parameters array + * @params_count: number of parameters provided + * + * Register the configuration parameters supported by the driver. + */ +int devlink_params_register(struct devlink *devlink, + const struct devlink_param *params, + size_t params_count) +{ + return __devlink_params_register(devlink, 0, &devlink->param_list, + params, params_count, + DEVLINK_CMD_PARAM_NEW, + DEVLINK_CMD_PARAM_DEL); +} EXPORT_SYMBOL_GPL(devlink_params_register); /** @@ -4532,36 +5935,103 @@ void devlink_params_unregister(struct devlink *devlink, const struct devlink_param *params, size_t params_count) { - const struct devlink_param *param = params; - int i; - - mutex_lock(&devlink->lock); - for (i = 0; i < params_count; i++, param++) - devlink_param_unregister_one(devlink, param); - mutex_unlock(&devlink->lock); + return __devlink_params_unregister(devlink, 0, &devlink->param_list, + params, params_count, + DEVLINK_CMD_PARAM_DEL); } EXPORT_SYMBOL_GPL(devlink_params_unregister); /** - * devlink_param_driverinit_value_get - get configuration parameter - * value for driver initializing + * devlink_params_publish - publish configuration parameters * * @devlink: devlink - * @param_id: parameter ID - * @init_val: value of parameter in driverinit configuration mode * - * This function should be used by the driver to get driverinit - * configuration for initialization after reload command. + * Publish previously registered configuration parameters. */ -int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, - union devlink_param_value *init_val) +void devlink_params_publish(struct devlink *devlink) { struct devlink_param_item *param_item; - if (!devlink->ops || !devlink->ops->reload) - return -EOPNOTSUPP; + list_for_each_entry(param_item, &devlink->param_list, list) { + if (param_item->published) + continue; + param_item->published = true; + devlink_param_notify(devlink, 0, param_item, + DEVLINK_CMD_PARAM_NEW); + } +} +EXPORT_SYMBOL_GPL(devlink_params_publish); - param_item = devlink_param_find_by_id(&devlink->param_list, param_id); +/** + * devlink_params_unpublish - unpublish configuration parameters + * + * @devlink: devlink + * + * Unpublish previously registered configuration parameters. + */ +void devlink_params_unpublish(struct devlink *devlink) +{ + struct devlink_param_item *param_item; + + list_for_each_entry(param_item, &devlink->param_list, list) { + if (!param_item->published) + continue; + param_item->published = false; + devlink_param_notify(devlink, 0, param_item, + DEVLINK_CMD_PARAM_DEL); + } +} +EXPORT_SYMBOL_GPL(devlink_params_unpublish); + +/** + * devlink_port_params_register - register port configuration parameters + * + * @devlink_port: devlink port + * @params: configuration parameters array + * @params_count: number of parameters provided + * + * Register the configuration parameters supported by the port. + */ +int devlink_port_params_register(struct devlink_port *devlink_port, + const struct devlink_param *params, + size_t params_count) +{ + return __devlink_params_register(devlink_port->devlink, + devlink_port->index, + &devlink_port->param_list, params, + params_count, + DEVLINK_CMD_PORT_PARAM_NEW, + DEVLINK_CMD_PORT_PARAM_DEL); +} +EXPORT_SYMBOL_GPL(devlink_port_params_register); + +/** + * devlink_port_params_unregister - unregister port configuration + * parameters + * + * @devlink_port: devlink port + * @params: configuration parameters array + * @params_count: number of parameters provided + */ +void devlink_port_params_unregister(struct devlink_port *devlink_port, + const struct devlink_param *params, + size_t params_count) +{ + return __devlink_params_unregister(devlink_port->devlink, + devlink_port->index, + &devlink_port->param_list, + params, params_count, + DEVLINK_CMD_PORT_PARAM_DEL); +} +EXPORT_SYMBOL_GPL(devlink_port_params_unregister); + +static int +__devlink_param_driverinit_value_get(struct list_head *param_list, u32 param_id, + union devlink_param_value *init_val) +{ + struct devlink_param_item *param_item; + + param_item = devlink_param_find_by_id(param_list, param_id); if (!param_item) return -EINVAL; @@ -4577,6 +6047,54 @@ int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, return 0; } + +static int +__devlink_param_driverinit_value_set(struct devlink *devlink, + unsigned int port_index, + struct list_head *param_list, u32 param_id, + union devlink_param_value init_val, + enum devlink_command cmd) +{ + struct devlink_param_item *param_item; + + param_item = devlink_param_find_by_id(param_list, param_id); + if (!param_item) + return -EINVAL; + + if (!devlink_param_cmode_is_supported(param_item->param, + DEVLINK_PARAM_CMODE_DRIVERINIT)) + return -EOPNOTSUPP; + + if (param_item->param->type == DEVLINK_PARAM_TYPE_STRING) + strcpy(param_item->driverinit_value.vstr, init_val.vstr); + else + param_item->driverinit_value = init_val; + param_item->driverinit_value_valid = true; + + devlink_param_notify(devlink, port_index, param_item, cmd); + return 0; +} + +/** + * devlink_param_driverinit_value_get - get configuration parameter + * value for driver initializing + * + * @devlink: devlink + * @param_id: parameter ID + * @init_val: value of parameter in driverinit configuration mode + * + * This function should be used by the driver to get driverinit + * configuration for initialization after reload command. + */ +int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, + union devlink_param_value *init_val) +{ + if (!devlink->ops || !devlink->ops->reload) + return -EOPNOTSUPP; + + return __devlink_param_driverinit_value_get(&devlink->param_list, + param_id, init_val); +} EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_get); /** @@ -4594,26 +6112,61 @@ EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_get); int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id, union devlink_param_value init_val) { - struct devlink_param_item *param_item; + return __devlink_param_driverinit_value_set(devlink, 0, + &devlink->param_list, + param_id, init_val, + DEVLINK_CMD_PARAM_NEW); +} +EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_set); - param_item = devlink_param_find_by_id(&devlink->param_list, param_id); - if (!param_item) - return -EINVAL; +/** + * devlink_port_param_driverinit_value_get - get configuration parameter + * value for driver initializing + * + * @devlink_port: devlink_port + * @param_id: parameter ID + * @init_val: value of parameter in driverinit configuration mode + * + * This function should be used by the driver to get driverinit + * configuration for initialization after reload command. + */ +int devlink_port_param_driverinit_value_get(struct devlink_port *devlink_port, + u32 param_id, + union devlink_param_value *init_val) +{ + struct devlink *devlink = devlink_port->devlink; - if (!devlink_param_cmode_is_supported(param_item->param, - DEVLINK_PARAM_CMODE_DRIVERINIT)) + if (!devlink->ops || !devlink->ops->reload) return -EOPNOTSUPP; - if (param_item->param->type == DEVLINK_PARAM_TYPE_STRING) - strcpy(param_item->driverinit_value.vstr, init_val.vstr); - else - param_item->driverinit_value = init_val; - param_item->driverinit_value_valid = true; + return __devlink_param_driverinit_value_get(&devlink_port->param_list, + param_id, init_val); +} +EXPORT_SYMBOL_GPL(devlink_port_param_driverinit_value_get); - devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW); - return 0; +/** + * devlink_port_param_driverinit_value_set - set value of configuration + * parameter for driverinit + * configuration mode + * + * @devlink_port: devlink_port + * @param_id: parameter ID + * @init_val: value of parameter to set for driverinit configuration mode + * + * This function should be used by the driver to set driverinit + * configuration mode default value. + */ +int devlink_port_param_driverinit_value_set(struct devlink_port *devlink_port, + u32 param_id, + union devlink_param_value init_val) +{ + return __devlink_param_driverinit_value_set(devlink_port->devlink, + devlink_port->index, + &devlink_port->param_list, + param_id, init_val, + DEVLINK_CMD_PORT_PARAM_NEW); } -EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_set); +EXPORT_SYMBOL_GPL(devlink_port_param_driverinit_value_set); /** * devlink_param_value_changed - notify devlink on a parameter's value @@ -4626,7 +6179,6 @@ EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_set); * This function should be used by the driver to notify devlink on value * change, excluding driverinit configuration mode. * For driverinit configuration mode driver should use the function - * devlink_param_driverinit_value_set() instead. */ void devlink_param_value_changed(struct devlink *devlink, u32 param_id) { @@ -4635,11 +6187,38 @@ void devlink_param_value_changed(struct devlink *devlink, u32 param_id) param_item = devlink_param_find_by_id(&devlink->param_list, param_id); WARN_ON(!param_item); - devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW); + devlink_param_notify(devlink, 0, param_item, DEVLINK_CMD_PARAM_NEW); } EXPORT_SYMBOL_GPL(devlink_param_value_changed); /** + * devlink_port_param_value_changed - notify devlink on a parameter's value + * change. Should be called by the driver + * right after the change. + * + * @devlink_port: devlink_port + * @param_id: parameter ID + * + * This function should be used by the driver to notify devlink on value + * change, excluding driverinit configuration mode. + * For driverinit configuration mode driver should use the function + * devlink_port_param_driverinit_value_set() instead. + */ +void devlink_port_param_value_changed(struct devlink_port *devlink_port, + u32 param_id) +{ + struct devlink_param_item *param_item; + + param_item = devlink_param_find_by_id(&devlink_port->param_list, + param_id); + WARN_ON(!param_item); + + devlink_param_notify(devlink_port->devlink, devlink_port->index, + param_item, DEVLINK_CMD_PORT_PARAM_NEW); +} +EXPORT_SYMBOL_GPL(devlink_port_param_value_changed); + +/** * devlink_param_value_str_fill - Safely fill-up the string preventing * from overflow of the preallocated buffer * @@ -4808,6 +6387,99 @@ unlock: } EXPORT_SYMBOL_GPL(devlink_region_snapshot_create); +static void __devlink_compat_running_version(struct devlink *devlink, + char *buf, size_t len) +{ + const struct nlattr *nlattr; + struct devlink_info_req req; + struct sk_buff *msg; + int rem, err; + + if (!devlink->ops->info_get) + return; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + req.msg = msg; + err = devlink->ops->info_get(devlink, &req, NULL); + if (err) + goto free_msg; + + nla_for_each_attr(nlattr, (void *)msg->data, msg->len, rem) { + const struct nlattr *kv; + int rem_kv; + + if (nla_type(nlattr) != DEVLINK_ATTR_INFO_VERSION_RUNNING) + continue; + + nla_for_each_nested(kv, nlattr, rem_kv) { + if (nla_type(kv) != DEVLINK_ATTR_INFO_VERSION_VALUE) + continue; + + strlcat(buf, nla_data(kv), len); + strlcat(buf, " ", len); + } + } +free_msg: + nlmsg_free(msg); +} + +void devlink_compat_running_version(struct net_device *dev, + char *buf, size_t len) +{ + struct devlink_port *devlink_port; + struct devlink *devlink; + + mutex_lock(&devlink_mutex); + list_for_each_entry(devlink, &devlink_list, list) { + mutex_lock(&devlink->lock); + list_for_each_entry(devlink_port, &devlink->port_list, list) { + if (devlink_port->type == DEVLINK_PORT_TYPE_ETH && + devlink_port->type_dev == dev) { + __devlink_compat_running_version(devlink, + buf, len); + mutex_unlock(&devlink->lock); + goto out; + } + } + mutex_unlock(&devlink->lock); + } +out: + mutex_unlock(&devlink_mutex); +} + +int devlink_compat_flash_update(struct net_device *dev, const char *file_name) +{ + struct devlink_port *devlink_port; + struct devlink *devlink; + + mutex_lock(&devlink_mutex); + list_for_each_entry(devlink, &devlink_list, list) { + mutex_lock(&devlink->lock); + list_for_each_entry(devlink_port, &devlink->port_list, list) { + int ret = -EOPNOTSUPP; + + if (devlink_port->type != DEVLINK_PORT_TYPE_ETH || + devlink_port->type_dev != dev) + continue; + + mutex_unlock(&devlink_mutex); + if (devlink->ops->flash_update) + ret = devlink->ops->flash_update(devlink, + file_name, + NULL, NULL); + mutex_unlock(&devlink->lock); + return ret; + } + mutex_unlock(&devlink->lock); + } + mutex_unlock(&devlink_mutex); + + return -EOPNOTSUPP; +} + static int __init devlink_module_init(void) { return genl_register_family(&devlink_nl_family); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 158264f7cfaf..1320e8dce559 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -27,7 +27,9 @@ #include <linux/rtnetlink.h> #include <linux/sched/signal.h> #include <linux/net.h> +#include <net/devlink.h> #include <net/xdp_sock.h> +#include <net/flow_offload.h> /* * Some useful ethtool_ops methods that're device independent. @@ -803,6 +805,12 @@ static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev, if (ops->get_eeprom_len) info.eedump_len = ops->get_eeprom_len(dev); + rtnl_unlock(); + if (!info.fw_version[0]) + devlink_compat_running_version(dev, info.fw_version, + sizeof(info.fw_version)); + rtnl_lock(); + if (copy_to_user(useraddr, &info, sizeof(info))) return -EFAULT; return 0; @@ -1348,12 +1356,9 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr) if (regs.len > reglen) regs.len = reglen; - regbuf = NULL; - if (reglen) { - regbuf = vzalloc(reglen); - if (!regbuf) - return -ENOMEM; - } + regbuf = vzalloc(reglen); + if (!regbuf) + return -ENOMEM; ops->get_regs(dev, ®s, regbuf); @@ -2033,11 +2038,17 @@ static noinline_for_stack int ethtool_flash_device(struct net_device *dev, if (copy_from_user(&efl, useraddr, sizeof(efl))) return -EFAULT; + efl.data[ETHTOOL_FLASH_MAX_FILENAME - 1] = 0; - if (!dev->ethtool_ops->flash_device) - return -EOPNOTSUPP; + if (!dev->ethtool_ops->flash_device) { + int ret; - efl.data[ETHTOOL_FLASH_MAX_FILENAME - 1] = 0; + rtnl_unlock(); + ret = devlink_compat_flash_update(dev, efl.data); + rtnl_lock(); + + return ret; + } return dev->ethtool_ops->flash_device(dev, &efl); } @@ -2816,3 +2827,241 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) return rc; } + +struct ethtool_rx_flow_key { + struct flow_dissector_key_basic basic; + union { + struct flow_dissector_key_ipv4_addrs ipv4; + struct flow_dissector_key_ipv6_addrs ipv6; + }; + struct flow_dissector_key_ports tp; + struct flow_dissector_key_ip ip; + struct flow_dissector_key_vlan vlan; + struct flow_dissector_key_eth_addrs eth_addrs; +} __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */ + +struct ethtool_rx_flow_match { + struct flow_dissector dissector; + struct ethtool_rx_flow_key key; + struct ethtool_rx_flow_key mask; +}; + +struct ethtool_rx_flow_rule * +ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input) +{ + const struct ethtool_rx_flow_spec *fs = input->fs; + static struct in6_addr zero_addr = {}; + struct ethtool_rx_flow_match *match; + struct ethtool_rx_flow_rule *flow; + struct flow_action_entry *act; + + flow = kzalloc(sizeof(struct ethtool_rx_flow_rule) + + sizeof(struct ethtool_rx_flow_match), GFP_KERNEL); + if (!flow) + return ERR_PTR(-ENOMEM); + + /* ethtool_rx supports only one single action per rule. */ + flow->rule = flow_rule_alloc(1); + if (!flow->rule) { + kfree(flow); + return ERR_PTR(-ENOMEM); + } + + match = (struct ethtool_rx_flow_match *)flow->priv; + flow->rule->match.dissector = &match->dissector; + flow->rule->match.mask = &match->mask; + flow->rule->match.key = &match->key; + + match->mask.basic.n_proto = htons(0xffff); + + switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT | FLOW_RSS)) { + case TCP_V4_FLOW: + case UDP_V4_FLOW: { + const struct ethtool_tcpip4_spec *v4_spec, *v4_m_spec; + + match->key.basic.n_proto = htons(ETH_P_IP); + + v4_spec = &fs->h_u.tcp_ip4_spec; + v4_m_spec = &fs->m_u.tcp_ip4_spec; + + if (v4_m_spec->ip4src) { + match->key.ipv4.src = v4_spec->ip4src; + match->mask.ipv4.src = v4_m_spec->ip4src; + } + if (v4_m_spec->ip4dst) { + match->key.ipv4.dst = v4_spec->ip4dst; + match->mask.ipv4.dst = v4_m_spec->ip4dst; + } + if (v4_m_spec->ip4src || + v4_m_spec->ip4dst) { + match->dissector.used_keys |= + BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS); + match->dissector.offset[FLOW_DISSECTOR_KEY_IPV4_ADDRS] = + offsetof(struct ethtool_rx_flow_key, ipv4); + } + if (v4_m_spec->psrc) { + match->key.tp.src = v4_spec->psrc; + match->mask.tp.src = v4_m_spec->psrc; + } + if (v4_m_spec->pdst) { + match->key.tp.dst = v4_spec->pdst; + match->mask.tp.dst = v4_m_spec->pdst; + } + if (v4_m_spec->psrc || + v4_m_spec->pdst) { + match->dissector.used_keys |= + BIT(FLOW_DISSECTOR_KEY_PORTS); + match->dissector.offset[FLOW_DISSECTOR_KEY_PORTS] = + offsetof(struct ethtool_rx_flow_key, tp); + } + if (v4_m_spec->tos) { + match->key.ip.tos = v4_spec->tos; + match->mask.ip.tos = v4_m_spec->tos; + match->dissector.used_keys |= + BIT(FLOW_DISSECTOR_KEY_IP); + match->dissector.offset[FLOW_DISSECTOR_KEY_IP] = + offsetof(struct ethtool_rx_flow_key, ip); + } + } + break; + case TCP_V6_FLOW: + case UDP_V6_FLOW: { + const struct ethtool_tcpip6_spec *v6_spec, *v6_m_spec; + + match->key.basic.n_proto = htons(ETH_P_IPV6); + + v6_spec = &fs->h_u.tcp_ip6_spec; + v6_m_spec = &fs->m_u.tcp_ip6_spec; + if (memcmp(v6_m_spec->ip6src, &zero_addr, sizeof(zero_addr))) { + memcpy(&match->key.ipv6.src, v6_spec->ip6src, + sizeof(match->key.ipv6.src)); + memcpy(&match->mask.ipv6.src, v6_m_spec->ip6src, + sizeof(match->mask.ipv6.src)); + } + if (memcmp(v6_m_spec->ip6dst, &zero_addr, sizeof(zero_addr))) { + memcpy(&match->key.ipv6.dst, v6_spec->ip6dst, + sizeof(match->key.ipv6.dst)); + memcpy(&match->mask.ipv6.dst, v6_m_spec->ip6dst, + sizeof(match->mask.ipv6.dst)); + } + if (memcmp(v6_m_spec->ip6src, &zero_addr, sizeof(zero_addr)) || + memcmp(v6_m_spec->ip6src, &zero_addr, sizeof(zero_addr))) { + match->dissector.used_keys |= + BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS); + match->dissector.offset[FLOW_DISSECTOR_KEY_IPV6_ADDRS] = + offsetof(struct ethtool_rx_flow_key, ipv6); + } + if (v6_m_spec->psrc) { + match->key.tp.src = v6_spec->psrc; + match->mask.tp.src = v6_m_spec->psrc; + } + if (v6_m_spec->pdst) { + match->key.tp.dst = v6_spec->pdst; + match->mask.tp.dst = v6_m_spec->pdst; + } + if (v6_m_spec->psrc || + v6_m_spec->pdst) { + match->dissector.used_keys |= + BIT(FLOW_DISSECTOR_KEY_PORTS); + match->dissector.offset[FLOW_DISSECTOR_KEY_PORTS] = + offsetof(struct ethtool_rx_flow_key, tp); + } + if (v6_m_spec->tclass) { + match->key.ip.tos = v6_spec->tclass; + match->mask.ip.tos = v6_m_spec->tclass; + match->dissector.used_keys |= + BIT(FLOW_DISSECTOR_KEY_IP); + match->dissector.offset[FLOW_DISSECTOR_KEY_IP] = + offsetof(struct ethtool_rx_flow_key, ip); + } + } + break; + default: + ethtool_rx_flow_rule_destroy(flow); + return ERR_PTR(-EINVAL); + } + + switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT | FLOW_RSS)) { + case TCP_V4_FLOW: + case TCP_V6_FLOW: + match->key.basic.ip_proto = IPPROTO_TCP; + break; + case UDP_V4_FLOW: + case UDP_V6_FLOW: + match->key.basic.ip_proto = IPPROTO_UDP; + break; + } + match->mask.basic.ip_proto = 0xff; + + match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_BASIC); + match->dissector.offset[FLOW_DISSECTOR_KEY_BASIC] = + offsetof(struct ethtool_rx_flow_key, basic); + + if (fs->flow_type & FLOW_EXT) { + const struct ethtool_flow_ext *ext_h_spec = &fs->h_ext; + const struct ethtool_flow_ext *ext_m_spec = &fs->m_ext; + + if (ext_m_spec->vlan_etype && + ext_m_spec->vlan_tci) { + match->key.vlan.vlan_tpid = ext_h_spec->vlan_etype; + match->mask.vlan.vlan_tpid = ext_m_spec->vlan_etype; + + match->key.vlan.vlan_id = + ntohs(ext_h_spec->vlan_tci) & 0x0fff; + match->mask.vlan.vlan_id = + ntohs(ext_m_spec->vlan_tci) & 0x0fff; + + match->key.vlan.vlan_priority = + (ntohs(ext_h_spec->vlan_tci) & 0xe000) >> 13; + match->mask.vlan.vlan_priority = + (ntohs(ext_m_spec->vlan_tci) & 0xe000) >> 13; + + match->dissector.used_keys |= + BIT(FLOW_DISSECTOR_KEY_VLAN); + match->dissector.offset[FLOW_DISSECTOR_KEY_VLAN] = + offsetof(struct ethtool_rx_flow_key, vlan); + } + } + if (fs->flow_type & FLOW_MAC_EXT) { + const struct ethtool_flow_ext *ext_h_spec = &fs->h_ext; + const struct ethtool_flow_ext *ext_m_spec = &fs->m_ext; + + memcpy(match->key.eth_addrs.dst, ext_h_spec->h_dest, + ETH_ALEN); + memcpy(match->mask.eth_addrs.dst, ext_m_spec->h_dest, + ETH_ALEN); + + match->dissector.used_keys |= + BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS); + match->dissector.offset[FLOW_DISSECTOR_KEY_ETH_ADDRS] = + offsetof(struct ethtool_rx_flow_key, eth_addrs); + } + + act = &flow->rule->action.entries[0]; + switch (fs->ring_cookie) { + case RX_CLS_FLOW_DISC: + act->id = FLOW_ACTION_DROP; + break; + case RX_CLS_FLOW_WAKE: + act->id = FLOW_ACTION_WAKE; + break; + default: + act->id = FLOW_ACTION_QUEUE; + if (fs->flow_type & FLOW_RSS) + act->queue.ctx = input->rss_ctx; + + act->queue.vf = ethtool_get_flow_spec_ring_vf(fs->ring_cookie); + act->queue.index = ethtool_get_flow_spec_ring(fs->ring_cookie); + break; + } + + return flow; +} +EXPORT_SYMBOL(ethtool_rx_flow_rule_create); + +void ethtool_rx_flow_rule_destroy(struct ethtool_rx_flow_rule *flow) +{ + kfree(flow->rule); + kfree(flow); +} +EXPORT_SYMBOL(ethtool_rx_flow_rule_destroy); diff --git a/net/core/filter.c b/net/core/filter.c index 41984ad4b9b4..b584cb42a803 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -73,6 +73,7 @@ #include <linux/seg6_local.h> #include <net/seg6.h> #include <net/seg6_local.h> +#include <net/lwtunnel.h> /** * sk_filter_trim_cap - run a packet through a socket filter @@ -1793,6 +1794,20 @@ static const struct bpf_func_proto bpf_skb_pull_data_proto = { .arg2_type = ARG_ANYTHING, }; +BPF_CALL_1(bpf_sk_fullsock, struct sock *, sk) +{ + sk = sk_to_full_sk(sk); + + return sk_fullsock(sk) ? (unsigned long)sk : (unsigned long)NULL; +} + +static const struct bpf_func_proto bpf_sk_fullsock_proto = { + .func = bpf_sk_fullsock, + .gpl_only = false, + .ret_type = RET_PTR_TO_SOCKET_OR_NULL, + .arg1_type = ARG_PTR_TO_SOCK_COMMON, +}; + static inline int sk_skb_try_make_writable(struct sk_buff *skb, unsigned int write_len) { @@ -4112,10 +4127,12 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, /* Only some socketops are supported */ switch (optname) { case SO_RCVBUF: + val = min_t(u32, val, sysctl_rmem_max); sk->sk_userlocks |= SOCK_RCVBUF_LOCK; sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF); break; case SO_SNDBUF: + val = min_t(u32, val, sysctl_wmem_max); sk->sk_userlocks |= SOCK_SNDBUF_LOCK; sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF); break; @@ -4801,7 +4818,15 @@ static int bpf_push_seg6_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len } #endif /* CONFIG_IPV6_SEG6_BPF */ -BPF_CALL_4(bpf_lwt_push_encap, struct sk_buff *, skb, u32, type, void *, hdr, +#if IS_ENABLED(CONFIG_LWTUNNEL_BPF) +static int bpf_push_ip_encap(struct sk_buff *skb, void *hdr, u32 len, + bool ingress) +{ + return bpf_lwt_push_ip_encap(skb, hdr, len, ingress); +} +#endif + +BPF_CALL_4(bpf_lwt_in_push_encap, struct sk_buff *, skb, u32, type, void *, hdr, u32, len) { switch (type) { @@ -4810,13 +4835,40 @@ BPF_CALL_4(bpf_lwt_push_encap, struct sk_buff *, skb, u32, type, void *, hdr, case BPF_LWT_ENCAP_SEG6_INLINE: return bpf_push_seg6_encap(skb, type, hdr, len); #endif +#if IS_ENABLED(CONFIG_LWTUNNEL_BPF) + case BPF_LWT_ENCAP_IP: + return bpf_push_ip_encap(skb, hdr, len, true /* ingress */); +#endif default: return -EINVAL; } } -static const struct bpf_func_proto bpf_lwt_push_encap_proto = { - .func = bpf_lwt_push_encap, +BPF_CALL_4(bpf_lwt_xmit_push_encap, struct sk_buff *, skb, u32, type, + void *, hdr, u32, len) +{ + switch (type) { +#if IS_ENABLED(CONFIG_LWTUNNEL_BPF) + case BPF_LWT_ENCAP_IP: + return bpf_push_ip_encap(skb, hdr, len, false /* egress */); +#endif + default: + return -EINVAL; + } +} + +static const struct bpf_func_proto bpf_lwt_in_push_encap_proto = { + .func = bpf_lwt_in_push_encap, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_MEM, + .arg4_type = ARG_CONST_SIZE +}; + +static const struct bpf_func_proto bpf_lwt_xmit_push_encap_proto = { + .func = bpf_lwt_xmit_push_encap, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, @@ -5016,6 +5068,54 @@ static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = { }; #endif /* CONFIG_IPV6_SEG6_BPF */ +#define CONVERT_COMMON_TCP_SOCK_FIELDS(md_type, CONVERT) \ +do { \ + switch (si->off) { \ + case offsetof(md_type, snd_cwnd): \ + CONVERT(snd_cwnd); break; \ + case offsetof(md_type, srtt_us): \ + CONVERT(srtt_us); break; \ + case offsetof(md_type, snd_ssthresh): \ + CONVERT(snd_ssthresh); break; \ + case offsetof(md_type, rcv_nxt): \ + CONVERT(rcv_nxt); break; \ + case offsetof(md_type, snd_nxt): \ + CONVERT(snd_nxt); break; \ + case offsetof(md_type, snd_una): \ + CONVERT(snd_una); break; \ + case offsetof(md_type, mss_cache): \ + CONVERT(mss_cache); break; \ + case offsetof(md_type, ecn_flags): \ + CONVERT(ecn_flags); break; \ + case offsetof(md_type, rate_delivered): \ + CONVERT(rate_delivered); break; \ + case offsetof(md_type, rate_interval_us): \ + CONVERT(rate_interval_us); break; \ + case offsetof(md_type, packets_out): \ + CONVERT(packets_out); break; \ + case offsetof(md_type, retrans_out): \ + CONVERT(retrans_out); break; \ + case offsetof(md_type, total_retrans): \ + CONVERT(total_retrans); break; \ + case offsetof(md_type, segs_in): \ + CONVERT(segs_in); break; \ + case offsetof(md_type, data_segs_in): \ + CONVERT(data_segs_in); break; \ + case offsetof(md_type, segs_out): \ + CONVERT(segs_out); break; \ + case offsetof(md_type, data_segs_out): \ + CONVERT(data_segs_out); break; \ + case offsetof(md_type, lost_out): \ + CONVERT(lost_out); break; \ + case offsetof(md_type, sacked_out): \ + CONVERT(sacked_out); break; \ + case offsetof(md_type, bytes_received): \ + CONVERT(bytes_received); break; \ + case offsetof(md_type, bytes_acked): \ + CONVERT(bytes_acked); break; \ + } \ +} while (0) + #ifdef CONFIG_INET static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple, int dif, int sdif, u8 family, u8 proto) @@ -5253,6 +5353,79 @@ static const struct bpf_func_proto bpf_sock_addr_sk_lookup_udp_proto = { .arg5_type = ARG_ANYTHING, }; +bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type, + struct bpf_insn_access_aux *info) +{ + if (off < 0 || off >= offsetofend(struct bpf_tcp_sock, bytes_acked)) + return false; + + if (off % size != 0) + return false; + + switch (off) { + case offsetof(struct bpf_tcp_sock, bytes_received): + case offsetof(struct bpf_tcp_sock, bytes_acked): + return size == sizeof(__u64); + default: + return size == sizeof(__u32); + } +} + +u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog, u32 *target_size) +{ + struct bpf_insn *insn = insn_buf; + +#define BPF_TCP_SOCK_GET_COMMON(FIELD) \ + do { \ + BUILD_BUG_ON(FIELD_SIZEOF(struct tcp_sock, FIELD) > \ + FIELD_SIZEOF(struct bpf_tcp_sock, FIELD)); \ + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct tcp_sock, FIELD),\ + si->dst_reg, si->src_reg, \ + offsetof(struct tcp_sock, FIELD)); \ + } while (0) + + CONVERT_COMMON_TCP_SOCK_FIELDS(struct bpf_tcp_sock, + BPF_TCP_SOCK_GET_COMMON); + + if (insn > insn_buf) + return insn - insn_buf; + + switch (si->off) { + case offsetof(struct bpf_tcp_sock, rtt_min): + BUILD_BUG_ON(FIELD_SIZEOF(struct tcp_sock, rtt_min) != + sizeof(struct minmax)); + BUILD_BUG_ON(sizeof(struct minmax) < + sizeof(struct minmax_sample)); + + *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, + offsetof(struct tcp_sock, rtt_min) + + offsetof(struct minmax_sample, v)); + break; + } + + return insn - insn_buf; +} + +BPF_CALL_1(bpf_tcp_sock, struct sock *, sk) +{ + sk = sk_to_full_sk(sk); + + if (sk_fullsock(sk) && sk->sk_protocol == IPPROTO_TCP) + return (unsigned long)sk; + + return (unsigned long)NULL; +} + +static const struct bpf_func_proto bpf_tcp_sock_proto = { + .func = bpf_tcp_sock, + .gpl_only = false, + .ret_type = RET_PTR_TO_TCP_SOCK_OR_NULL, + .arg1_type = ARG_PTR_TO_SOCK_COMMON, +}; + #endif /* CONFIG_INET */ bool bpf_helper_changes_pkt_data(void *func) @@ -5282,7 +5455,8 @@ bool bpf_helper_changes_pkt_data(void *func) func == bpf_lwt_seg6_adjust_srh || func == bpf_lwt_seg6_action || #endif - func == bpf_lwt_push_encap) + func == bpf_lwt_in_push_encap || + func == bpf_lwt_xmit_push_encap) return true; return false; @@ -5314,10 +5488,20 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_tail_call_proto; case BPF_FUNC_ktime_get_ns: return &bpf_ktime_get_ns_proto; + default: + break; + } + + if (!capable(CAP_SYS_ADMIN)) + return NULL; + + switch (func_id) { + case BPF_FUNC_spin_lock: + return &bpf_spin_lock_proto; + case BPF_FUNC_spin_unlock: + return &bpf_spin_unlock_proto; case BPF_FUNC_trace_printk: - if (capable(CAP_SYS_ADMIN)) - return bpf_get_trace_printk_proto(); - /* else, fall through */ + return bpf_get_trace_printk_proto(); default: return NULL; } @@ -5396,6 +5580,12 @@ cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) switch (func_id) { case BPF_FUNC_get_local_storage: return &bpf_get_local_storage_proto; + case BPF_FUNC_sk_fullsock: + return &bpf_sk_fullsock_proto; +#ifdef CONFIG_INET + case BPF_FUNC_tcp_sock: + return &bpf_tcp_sock_proto; +#endif default: return sk_filter_func_proto(func_id, prog); } @@ -5467,6 +5657,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_socket_uid_proto; case BPF_FUNC_fib_lookup: return &bpf_skb_fib_lookup_proto; + case BPF_FUNC_sk_fullsock: + return &bpf_sk_fullsock_proto; #ifdef CONFIG_XFRM case BPF_FUNC_skb_get_xfrm_state: return &bpf_skb_get_xfrm_state_proto; @@ -5484,6 +5676,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_sk_lookup_udp_proto; case BPF_FUNC_sk_release: return &bpf_sk_release_proto; + case BPF_FUNC_tcp_sock: + return &bpf_tcp_sock_proto; #endif default: return bpf_base_func_proto(func_id); @@ -5660,7 +5854,7 @@ lwt_in_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_lwt_push_encap: - return &bpf_lwt_push_encap_proto; + return &bpf_lwt_in_push_encap_proto; default: return lwt_out_func_proto(func_id, prog); } @@ -5696,6 +5890,8 @@ lwt_xmit_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_l4_csum_replace_proto; case BPF_FUNC_set_hash_invalid: return &bpf_set_hash_invalid_proto; + case BPF_FUNC_lwt_push_encap: + return &bpf_lwt_xmit_push_encap_proto; default: return lwt_out_func_proto(func_id, prog); } @@ -5754,6 +5950,11 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type if (size != sizeof(__u64)) return false; break; + case offsetof(struct __sk_buff, sk): + if (type == BPF_WRITE || size != sizeof(__u64)) + return false; + info->reg_type = PTR_TO_SOCK_COMMON_OR_NULL; + break; default: /* Only narrow read access allowed for now. */ if (type == BPF_WRITE) { @@ -5925,31 +6126,44 @@ full_access: return true; } -static bool __sock_filter_check_size(int off, int size, +bool bpf_sock_common_is_valid_access(int off, int size, + enum bpf_access_type type, struct bpf_insn_access_aux *info) { - const int size_default = sizeof(__u32); - switch (off) { - case bpf_ctx_range(struct bpf_sock, src_ip4): - case bpf_ctx_range_till(struct bpf_sock, src_ip6[0], src_ip6[3]): - bpf_ctx_record_field_size(info, size_default); - return bpf_ctx_narrow_access_ok(off, size, size_default); + case bpf_ctx_range_till(struct bpf_sock, type, priority): + return false; + default: + return bpf_sock_is_valid_access(off, size, type, info); } - - return size == size_default; } bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { + const int size_default = sizeof(__u32); + if (off < 0 || off >= sizeof(struct bpf_sock)) return false; if (off % size != 0) return false; - if (!__sock_filter_check_size(off, size, info)) - return false; - return true; + + switch (off) { + case offsetof(struct bpf_sock, state): + case offsetof(struct bpf_sock, family): + case offsetof(struct bpf_sock, type): + case offsetof(struct bpf_sock, protocol): + case offsetof(struct bpf_sock, dst_port): + case offsetof(struct bpf_sock, src_port): + case bpf_ctx_range(struct bpf_sock, src_ip4): + case bpf_ctx_range_till(struct bpf_sock, src_ip6[0], src_ip6[3]): + case bpf_ctx_range(struct bpf_sock, dst_ip4): + case bpf_ctx_range_till(struct bpf_sock, dst_ip6[0], dst_ip6[3]): + bpf_ctx_record_field_size(info, size_default); + return bpf_ctx_narrow_access_ok(off, size, size_default); + } + + return size == size_default; } static bool sock_filter_is_valid_access(int off, int size, @@ -6738,6 +6952,13 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, off += offsetof(struct qdisc_skb_cb, pkt_len); *target_size = 4; *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, off); + break; + + case offsetof(struct __sk_buff, sk): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), + si->dst_reg, si->src_reg, + offsetof(struct sk_buff, sk)); + break; } return insn - insn_buf; @@ -6786,24 +7007,32 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock, family): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock, sk_family) != 2); - - *insn++ = BPF_LDX_MEM(BPF_H, si->dst_reg, si->src_reg, - offsetof(struct sock, sk_family)); + *insn++ = BPF_LDX_MEM( + BPF_FIELD_SIZEOF(struct sock_common, skc_family), + si->dst_reg, si->src_reg, + bpf_target_off(struct sock_common, + skc_family, + FIELD_SIZEOF(struct sock_common, + skc_family), + target_size)); break; case offsetof(struct bpf_sock, type): + BUILD_BUG_ON(HWEIGHT32(SK_FL_TYPE_MASK) != BITS_PER_BYTE * 2); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct sock, __sk_flags_offset)); *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_TYPE_MASK); *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, SK_FL_TYPE_SHIFT); + *target_size = 2; break; case offsetof(struct bpf_sock, protocol): + BUILD_BUG_ON(HWEIGHT32(SK_FL_PROTO_MASK) != BITS_PER_BYTE); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, offsetof(struct sock, __sk_flags_offset)); *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_PROTO_MASK); *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, SK_FL_PROTO_SHIFT); + *target_size = 1; break; case offsetof(struct bpf_sock, src_ip4): @@ -6815,6 +7044,15 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, target_size)); break; + case offsetof(struct bpf_sock, dst_ip4): + *insn++ = BPF_LDX_MEM( + BPF_SIZE(si->code), si->dst_reg, si->src_reg, + bpf_target_off(struct sock_common, skc_daddr, + FIELD_SIZEOF(struct sock_common, + skc_daddr), + target_size)); + break; + case bpf_ctx_range_till(struct bpf_sock, src_ip6[0], src_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) off = si->off; @@ -6833,6 +7071,23 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, #endif break; + case bpf_ctx_range_till(struct bpf_sock, dst_ip6[0], dst_ip6[3]): +#if IS_ENABLED(CONFIG_IPV6) + off = si->off; + off -= offsetof(struct bpf_sock, dst_ip6[0]); + *insn++ = BPF_LDX_MEM( + BPF_SIZE(si->code), si->dst_reg, si->src_reg, + bpf_target_off(struct sock_common, + skc_v6_daddr.s6_addr32[0], + FIELD_SIZEOF(struct sock_common, + skc_v6_daddr.s6_addr32[0]), + target_size) + off); +#else + *insn++ = BPF_MOV32_IMM(si->dst_reg, 0); + *target_size = 4; +#endif + break; + case offsetof(struct bpf_sock, src_port): *insn++ = BPF_LDX_MEM( BPF_FIELD_SIZEOF(struct sock_common, skc_num), @@ -6842,6 +7097,26 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, skc_num), target_size)); break; + + case offsetof(struct bpf_sock, dst_port): + *insn++ = BPF_LDX_MEM( + BPF_FIELD_SIZEOF(struct sock_common, skc_dport), + si->dst_reg, si->src_reg, + bpf_target_off(struct sock_common, skc_dport, + FIELD_SIZEOF(struct sock_common, + skc_dport), + target_size)); + break; + + case offsetof(struct bpf_sock, state): + *insn++ = BPF_LDX_MEM( + BPF_FIELD_SIZEOF(struct sock_common, skc_state), + si->dst_reg, si->src_reg, + bpf_target_off(struct sock_common, skc_state, + FIELD_SIZEOF(struct sock_common, + skc_state), + target_size)); + break; } return insn - insn_buf; @@ -7089,6 +7364,85 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, struct bpf_insn *insn = insn_buf; int off; +/* Helper macro for adding read access to tcp_sock or sock fields. */ +#define SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ) \ + do { \ + BUILD_BUG_ON(FIELD_SIZEOF(OBJ, OBJ_FIELD) > \ + FIELD_SIZEOF(struct bpf_sock_ops, BPF_FIELD)); \ + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ + struct bpf_sock_ops_kern, \ + is_fullsock), \ + si->dst_reg, si->src_reg, \ + offsetof(struct bpf_sock_ops_kern, \ + is_fullsock)); \ + *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 2); \ + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ + struct bpf_sock_ops_kern, sk),\ + si->dst_reg, si->src_reg, \ + offsetof(struct bpf_sock_ops_kern, sk));\ + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(OBJ, \ + OBJ_FIELD), \ + si->dst_reg, si->dst_reg, \ + offsetof(OBJ, OBJ_FIELD)); \ + } while (0) + +#define SOCK_OPS_GET_TCP_SOCK_FIELD(FIELD) \ + SOCK_OPS_GET_FIELD(FIELD, FIELD, struct tcp_sock) + +/* Helper macro for adding write access to tcp_sock or sock fields. + * The macro is called with two registers, dst_reg which contains a pointer + * to ctx (context) and src_reg which contains the value that should be + * stored. However, we need an additional register since we cannot overwrite + * dst_reg because it may be used later in the program. + * Instead we "borrow" one of the other register. We first save its value + * into a new (temp) field in bpf_sock_ops_kern, use it, and then restore + * it at the end of the macro. + */ +#define SOCK_OPS_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ) \ + do { \ + int reg = BPF_REG_9; \ + BUILD_BUG_ON(FIELD_SIZEOF(OBJ, OBJ_FIELD) > \ + FIELD_SIZEOF(struct bpf_sock_ops, BPF_FIELD)); \ + if (si->dst_reg == reg || si->src_reg == reg) \ + reg--; \ + if (si->dst_reg == reg || si->src_reg == reg) \ + reg--; \ + *insn++ = BPF_STX_MEM(BPF_DW, si->dst_reg, reg, \ + offsetof(struct bpf_sock_ops_kern, \ + temp)); \ + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ + struct bpf_sock_ops_kern, \ + is_fullsock), \ + reg, si->dst_reg, \ + offsetof(struct bpf_sock_ops_kern, \ + is_fullsock)); \ + *insn++ = BPF_JMP_IMM(BPF_JEQ, reg, 0, 2); \ + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ + struct bpf_sock_ops_kern, sk),\ + reg, si->dst_reg, \ + offsetof(struct bpf_sock_ops_kern, sk));\ + *insn++ = BPF_STX_MEM(BPF_FIELD_SIZEOF(OBJ, OBJ_FIELD), \ + reg, si->src_reg, \ + offsetof(OBJ, OBJ_FIELD)); \ + *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->dst_reg, \ + offsetof(struct bpf_sock_ops_kern, \ + temp)); \ + } while (0) + +#define SOCK_OPS_GET_OR_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ, TYPE) \ + do { \ + if (TYPE == BPF_WRITE) \ + SOCK_OPS_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ); \ + else \ + SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ); \ + } while (0) + + CONVERT_COMMON_TCP_SOCK_FIELDS(struct bpf_sock_ops, + SOCK_OPS_GET_TCP_SOCK_FIELD); + + if (insn > insn_buf) + return insn - insn_buf; + switch (si->off) { case offsetof(struct bpf_sock_ops, op) ... offsetof(struct bpf_sock_ops, replylong[3]): @@ -7246,175 +7600,15 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, FIELD_SIZEOF(struct minmax_sample, t)); break; -/* Helper macro for adding read access to tcp_sock or sock fields. */ -#define SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ) \ - do { \ - BUILD_BUG_ON(FIELD_SIZEOF(OBJ, OBJ_FIELD) > \ - FIELD_SIZEOF(struct bpf_sock_ops, BPF_FIELD)); \ - *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ - struct bpf_sock_ops_kern, \ - is_fullsock), \ - si->dst_reg, si->src_reg, \ - offsetof(struct bpf_sock_ops_kern, \ - is_fullsock)); \ - *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 2); \ - *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ - struct bpf_sock_ops_kern, sk),\ - si->dst_reg, si->src_reg, \ - offsetof(struct bpf_sock_ops_kern, sk));\ - *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(OBJ, \ - OBJ_FIELD), \ - si->dst_reg, si->dst_reg, \ - offsetof(OBJ, OBJ_FIELD)); \ - } while (0) - -/* Helper macro for adding write access to tcp_sock or sock fields. - * The macro is called with two registers, dst_reg which contains a pointer - * to ctx (context) and src_reg which contains the value that should be - * stored. However, we need an additional register since we cannot overwrite - * dst_reg because it may be used later in the program. - * Instead we "borrow" one of the other register. We first save its value - * into a new (temp) field in bpf_sock_ops_kern, use it, and then restore - * it at the end of the macro. - */ -#define SOCK_OPS_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ) \ - do { \ - int reg = BPF_REG_9; \ - BUILD_BUG_ON(FIELD_SIZEOF(OBJ, OBJ_FIELD) > \ - FIELD_SIZEOF(struct bpf_sock_ops, BPF_FIELD)); \ - if (si->dst_reg == reg || si->src_reg == reg) \ - reg--; \ - if (si->dst_reg == reg || si->src_reg == reg) \ - reg--; \ - *insn++ = BPF_STX_MEM(BPF_DW, si->dst_reg, reg, \ - offsetof(struct bpf_sock_ops_kern, \ - temp)); \ - *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ - struct bpf_sock_ops_kern, \ - is_fullsock), \ - reg, si->dst_reg, \ - offsetof(struct bpf_sock_ops_kern, \ - is_fullsock)); \ - *insn++ = BPF_JMP_IMM(BPF_JEQ, reg, 0, 2); \ - *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ - struct bpf_sock_ops_kern, sk),\ - reg, si->dst_reg, \ - offsetof(struct bpf_sock_ops_kern, sk));\ - *insn++ = BPF_STX_MEM(BPF_FIELD_SIZEOF(OBJ, OBJ_FIELD), \ - reg, si->src_reg, \ - offsetof(OBJ, OBJ_FIELD)); \ - *insn++ = BPF_LDX_MEM(BPF_DW, reg, si->dst_reg, \ - offsetof(struct bpf_sock_ops_kern, \ - temp)); \ - } while (0) - -#define SOCK_OPS_GET_OR_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ, TYPE) \ - do { \ - if (TYPE == BPF_WRITE) \ - SOCK_OPS_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ); \ - else \ - SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ); \ - } while (0) - - case offsetof(struct bpf_sock_ops, snd_cwnd): - SOCK_OPS_GET_FIELD(snd_cwnd, snd_cwnd, struct tcp_sock); - break; - - case offsetof(struct bpf_sock_ops, srtt_us): - SOCK_OPS_GET_FIELD(srtt_us, srtt_us, struct tcp_sock); - break; - case offsetof(struct bpf_sock_ops, bpf_sock_ops_cb_flags): SOCK_OPS_GET_FIELD(bpf_sock_ops_cb_flags, bpf_sock_ops_cb_flags, struct tcp_sock); break; - case offsetof(struct bpf_sock_ops, snd_ssthresh): - SOCK_OPS_GET_FIELD(snd_ssthresh, snd_ssthresh, struct tcp_sock); - break; - - case offsetof(struct bpf_sock_ops, rcv_nxt): - SOCK_OPS_GET_FIELD(rcv_nxt, rcv_nxt, struct tcp_sock); - break; - - case offsetof(struct bpf_sock_ops, snd_nxt): - SOCK_OPS_GET_FIELD(snd_nxt, snd_nxt, struct tcp_sock); - break; - - case offsetof(struct bpf_sock_ops, snd_una): - SOCK_OPS_GET_FIELD(snd_una, snd_una, struct tcp_sock); - break; - - case offsetof(struct bpf_sock_ops, mss_cache): - SOCK_OPS_GET_FIELD(mss_cache, mss_cache, struct tcp_sock); - break; - - case offsetof(struct bpf_sock_ops, ecn_flags): - SOCK_OPS_GET_FIELD(ecn_flags, ecn_flags, struct tcp_sock); - break; - - case offsetof(struct bpf_sock_ops, rate_delivered): - SOCK_OPS_GET_FIELD(rate_delivered, rate_delivered, - struct tcp_sock); - break; - - case offsetof(struct bpf_sock_ops, rate_interval_us): - SOCK_OPS_GET_FIELD(rate_interval_us, rate_interval_us, - struct tcp_sock); - break; - - case offsetof(struct bpf_sock_ops, packets_out): - SOCK_OPS_GET_FIELD(packets_out, packets_out, struct tcp_sock); - break; - - case offsetof(struct bpf_sock_ops, retrans_out): - SOCK_OPS_GET_FIELD(retrans_out, retrans_out, struct tcp_sock); - break; - - case offsetof(struct bpf_sock_ops, total_retrans): - SOCK_OPS_GET_FIELD(total_retrans, total_retrans, - struct tcp_sock); - break; - - case offsetof(struct bpf_sock_ops, segs_in): - SOCK_OPS_GET_FIELD(segs_in, segs_in, struct tcp_sock); - break; - - case offsetof(struct bpf_sock_ops, data_segs_in): - SOCK_OPS_GET_FIELD(data_segs_in, data_segs_in, struct tcp_sock); - break; - - case offsetof(struct bpf_sock_ops, segs_out): - SOCK_OPS_GET_FIELD(segs_out, segs_out, struct tcp_sock); - break; - - case offsetof(struct bpf_sock_ops, data_segs_out): - SOCK_OPS_GET_FIELD(data_segs_out, data_segs_out, - struct tcp_sock); - break; - - case offsetof(struct bpf_sock_ops, lost_out): - SOCK_OPS_GET_FIELD(lost_out, lost_out, struct tcp_sock); - break; - - case offsetof(struct bpf_sock_ops, sacked_out): - SOCK_OPS_GET_FIELD(sacked_out, sacked_out, struct tcp_sock); - break; - case offsetof(struct bpf_sock_ops, sk_txhash): SOCK_OPS_GET_OR_SET_FIELD(sk_txhash, sk_txhash, struct sock, type); break; - - case offsetof(struct bpf_sock_ops, bytes_received): - SOCK_OPS_GET_FIELD(bytes_received, bytes_received, - struct tcp_sock); - break; - - case offsetof(struct bpf_sock_ops, bytes_acked): - SOCK_OPS_GET_FIELD(bytes_acked, bytes_acked, struct tcp_sock); - break; - } return insn - insn_buf; } diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c new file mode 100644 index 000000000000..c3a00eac4804 --- /dev/null +++ b/net/core/flow_offload.c @@ -0,0 +1,153 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/kernel.h> +#include <linux/slab.h> +#include <net/flow_offload.h> + +struct flow_rule *flow_rule_alloc(unsigned int num_actions) +{ + struct flow_rule *rule; + + rule = kzalloc(sizeof(struct flow_rule) + + sizeof(struct flow_action_entry) * num_actions, + GFP_KERNEL); + if (!rule) + return NULL; + + rule->action.num_entries = num_actions; + + return rule; +} +EXPORT_SYMBOL(flow_rule_alloc); + +#define FLOW_DISSECTOR_MATCH(__rule, __type, __out) \ + const struct flow_match *__m = &(__rule)->match; \ + struct flow_dissector *__d = (__m)->dissector; \ + \ + (__out)->key = skb_flow_dissector_target(__d, __type, (__m)->key); \ + (__out)->mask = skb_flow_dissector_target(__d, __type, (__m)->mask); \ + +void flow_rule_match_basic(const struct flow_rule *rule, + struct flow_match_basic *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_BASIC, out); +} +EXPORT_SYMBOL(flow_rule_match_basic); + +void flow_rule_match_control(const struct flow_rule *rule, + struct flow_match_control *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_CONTROL, out); +} +EXPORT_SYMBOL(flow_rule_match_control); + +void flow_rule_match_eth_addrs(const struct flow_rule *rule, + struct flow_match_eth_addrs *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS, out); +} +EXPORT_SYMBOL(flow_rule_match_eth_addrs); + +void flow_rule_match_vlan(const struct flow_rule *rule, + struct flow_match_vlan *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_VLAN, out); +} +EXPORT_SYMBOL(flow_rule_match_vlan); + +void flow_rule_match_ipv4_addrs(const struct flow_rule *rule, + struct flow_match_ipv4_addrs *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS, out); +} +EXPORT_SYMBOL(flow_rule_match_ipv4_addrs); + +void flow_rule_match_ipv6_addrs(const struct flow_rule *rule, + struct flow_match_ipv6_addrs *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS, out); +} +EXPORT_SYMBOL(flow_rule_match_ipv6_addrs); + +void flow_rule_match_ip(const struct flow_rule *rule, + struct flow_match_ip *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_IP, out); +} +EXPORT_SYMBOL(flow_rule_match_ip); + +void flow_rule_match_ports(const struct flow_rule *rule, + struct flow_match_ports *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_PORTS, out); +} +EXPORT_SYMBOL(flow_rule_match_ports); + +void flow_rule_match_tcp(const struct flow_rule *rule, + struct flow_match_tcp *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_TCP, out); +} +EXPORT_SYMBOL(flow_rule_match_tcp); + +void flow_rule_match_icmp(const struct flow_rule *rule, + struct flow_match_icmp *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ICMP, out); +} +EXPORT_SYMBOL(flow_rule_match_icmp); + +void flow_rule_match_mpls(const struct flow_rule *rule, + struct flow_match_mpls *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_MPLS, out); +} +EXPORT_SYMBOL(flow_rule_match_mpls); + +void flow_rule_match_enc_control(const struct flow_rule *rule, + struct flow_match_control *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_CONTROL, out); +} +EXPORT_SYMBOL(flow_rule_match_enc_control); + +void flow_rule_match_enc_ipv4_addrs(const struct flow_rule *rule, + struct flow_match_ipv4_addrs *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, out); +} +EXPORT_SYMBOL(flow_rule_match_enc_ipv4_addrs); + +void flow_rule_match_enc_ipv6_addrs(const struct flow_rule *rule, + struct flow_match_ipv6_addrs *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS, out); +} +EXPORT_SYMBOL(flow_rule_match_enc_ipv6_addrs); + +void flow_rule_match_enc_ip(const struct flow_rule *rule, + struct flow_match_ip *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_IP, out); +} +EXPORT_SYMBOL(flow_rule_match_enc_ip); + +void flow_rule_match_enc_ports(const struct flow_rule *rule, + struct flow_match_ports *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_PORTS, out); +} +EXPORT_SYMBOL(flow_rule_match_enc_ports); + +void flow_rule_match_enc_keyid(const struct flow_rule *rule, + struct flow_match_enc_keyid *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_KEYID, out); +} +EXPORT_SYMBOL(flow_rule_match_enc_keyid); + +void flow_rule_match_enc_opts(const struct flow_rule *rule, + struct flow_match_enc_opts *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_OPTS, out); +} +EXPORT_SYMBOL(flow_rule_match_enc_opts); diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index a648568c5e8f..a5c8c79d468a 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -16,6 +16,8 @@ #include <linux/types.h> #include <linux/bpf.h> #include <net/lwtunnel.h> +#include <net/gre.h> +#include <net/ip6_route.h> struct bpf_lwt_prog { struct bpf_prog *prog; @@ -55,6 +57,7 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt, switch (ret) { case BPF_OK: + case BPF_LWT_REROUTE: break; case BPF_REDIRECT: @@ -87,6 +90,30 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt, return ret; } +static int bpf_lwt_input_reroute(struct sk_buff *skb) +{ + int err = -EINVAL; + + if (skb->protocol == htons(ETH_P_IP)) { + struct iphdr *iph = ip_hdr(skb); + + err = ip_route_input_noref(skb, iph->daddr, iph->saddr, + iph->tos, skb_dst(skb)->dev); + } else if (skb->protocol == htons(ETH_P_IPV6)) { + err = ipv6_stub->ipv6_route_input(skb); + } else { + err = -EAFNOSUPPORT; + } + + if (err) + goto err; + return dst_input(skb); + +err: + kfree_skb(skb); + return err; +} + static int bpf_input(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); @@ -98,11 +125,11 @@ static int bpf_input(struct sk_buff *skb) ret = run_lwt_bpf(skb, &bpf->in, dst, NO_REDIRECT); if (ret < 0) return ret; + if (ret == BPF_LWT_REROUTE) + return bpf_lwt_input_reroute(skb); } if (unlikely(!dst->lwtstate->orig_input)) { - pr_warn_once("orig_input not set on dst for prog %s\n", - bpf->out.name); kfree_skb(skb); return -EINVAL; } @@ -147,6 +174,102 @@ static int xmit_check_hhlen(struct sk_buff *skb) return 0; } +static int bpf_lwt_xmit_reroute(struct sk_buff *skb) +{ + struct net_device *l3mdev = l3mdev_master_dev_rcu(skb_dst(skb)->dev); + int oif = l3mdev ? l3mdev->ifindex : 0; + struct dst_entry *dst = NULL; + int err = -EAFNOSUPPORT; + struct sock *sk; + struct net *net; + bool ipv4; + + if (skb->protocol == htons(ETH_P_IP)) + ipv4 = true; + else if (skb->protocol == htons(ETH_P_IPV6)) + ipv4 = false; + else + goto err; + + sk = sk_to_full_sk(skb->sk); + if (sk) { + if (sk->sk_bound_dev_if) + oif = sk->sk_bound_dev_if; + net = sock_net(sk); + } else { + net = dev_net(skb_dst(skb)->dev); + } + + if (ipv4) { + struct iphdr *iph = ip_hdr(skb); + struct flowi4 fl4 = {}; + struct rtable *rt; + + fl4.flowi4_oif = oif; + fl4.flowi4_mark = skb->mark; + fl4.flowi4_uid = sock_net_uid(net, sk); + fl4.flowi4_tos = RT_TOS(iph->tos); + fl4.flowi4_flags = FLOWI_FLAG_ANYSRC; + fl4.flowi4_proto = iph->protocol; + fl4.daddr = iph->daddr; + fl4.saddr = iph->saddr; + + rt = ip_route_output_key(net, &fl4); + if (IS_ERR(rt)) { + err = PTR_ERR(rt); + goto err; + } + dst = &rt->dst; + } else { + struct ipv6hdr *iph6 = ipv6_hdr(skb); + struct flowi6 fl6 = {}; + + fl6.flowi6_oif = oif; + fl6.flowi6_mark = skb->mark; + fl6.flowi6_uid = sock_net_uid(net, sk); + fl6.flowlabel = ip6_flowinfo(iph6); + fl6.flowi6_proto = iph6->nexthdr; + fl6.daddr = iph6->daddr; + fl6.saddr = iph6->saddr; + + err = ipv6_stub->ipv6_dst_lookup(net, skb->sk, &dst, &fl6); + if (unlikely(err)) + goto err; + if (IS_ERR(dst)) { + err = PTR_ERR(dst); + goto err; + } + } + if (unlikely(dst->error)) { + err = dst->error; + dst_release(dst); + goto err; + } + + /* Although skb header was reserved in bpf_lwt_push_ip_encap(), it + * was done for the previous dst, so we are doing it here again, in + * case the new dst needs much more space. The call below is a noop + * if there is enough header space in skb. + */ + err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev)); + if (unlikely(err)) + goto err; + + skb_dst_drop(skb); + skb_dst_set(skb, dst); + + err = dst_output(dev_net(skb_dst(skb)->dev), skb->sk, skb); + if (unlikely(err)) + goto err; + + /* ip[6]_finish_output2 understand LWTUNNEL_XMIT_DONE */ + return LWTUNNEL_XMIT_DONE; + +err: + kfree_skb(skb); + return err; +} + static int bpf_xmit(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); @@ -154,11 +277,20 @@ static int bpf_xmit(struct sk_buff *skb) bpf = bpf_lwt_lwtunnel(dst->lwtstate); if (bpf->xmit.prog) { + __be16 proto = skb->protocol; int ret; ret = run_lwt_bpf(skb, &bpf->xmit, dst, CAN_REDIRECT); switch (ret) { case BPF_OK: + /* If the header changed, e.g. via bpf_lwt_push_encap, + * BPF_LWT_REROUTE below should have been used if the + * protocol was also changed. + */ + if (skb->protocol != proto) { + kfree_skb(skb); + return -EINVAL; + } /* If the header was expanded, headroom might be too * small for L2 header to come, expand as needed. */ @@ -169,6 +301,8 @@ static int bpf_xmit(struct sk_buff *skb) return LWTUNNEL_XMIT_CONTINUE; case BPF_REDIRECT: return LWTUNNEL_XMIT_DONE; + case BPF_LWT_REROUTE: + return bpf_lwt_xmit_reroute(skb); default: return ret; } @@ -390,6 +524,133 @@ static const struct lwtunnel_encap_ops bpf_encap_ops = { .owner = THIS_MODULE, }; +static int handle_gso_type(struct sk_buff *skb, unsigned int gso_type, + int encap_len) +{ + struct skb_shared_info *shinfo = skb_shinfo(skb); + + gso_type |= SKB_GSO_DODGY; + shinfo->gso_type |= gso_type; + skb_decrease_gso_size(shinfo, encap_len); + shinfo->gso_segs = 0; + return 0; +} + +static int handle_gso_encap(struct sk_buff *skb, bool ipv4, int encap_len) +{ + int next_hdr_offset; + void *next_hdr; + __u8 protocol; + + /* SCTP and UDP_L4 gso need more nuanced handling than what + * handle_gso_type() does above: skb_decrease_gso_size() is not enough. + * So at the moment only TCP GSO packets are let through. + */ + if (!(skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) + return -ENOTSUPP; + + if (ipv4) { + protocol = ip_hdr(skb)->protocol; + next_hdr_offset = sizeof(struct iphdr); + next_hdr = skb_network_header(skb) + next_hdr_offset; + } else { + protocol = ipv6_hdr(skb)->nexthdr; + next_hdr_offset = sizeof(struct ipv6hdr); + next_hdr = skb_network_header(skb) + next_hdr_offset; + } + + switch (protocol) { + case IPPROTO_GRE: + next_hdr_offset += sizeof(struct gre_base_hdr); + if (next_hdr_offset > encap_len) + return -EINVAL; + + if (((struct gre_base_hdr *)next_hdr)->flags & GRE_CSUM) + return handle_gso_type(skb, SKB_GSO_GRE_CSUM, + encap_len); + return handle_gso_type(skb, SKB_GSO_GRE, encap_len); + + case IPPROTO_UDP: + next_hdr_offset += sizeof(struct udphdr); + if (next_hdr_offset > encap_len) + return -EINVAL; + + if (((struct udphdr *)next_hdr)->check) + return handle_gso_type(skb, SKB_GSO_UDP_TUNNEL_CSUM, + encap_len); + return handle_gso_type(skb, SKB_GSO_UDP_TUNNEL, encap_len); + + case IPPROTO_IP: + case IPPROTO_IPV6: + if (ipv4) + return handle_gso_type(skb, SKB_GSO_IPXIP4, encap_len); + else + return handle_gso_type(skb, SKB_GSO_IPXIP6, encap_len); + + default: + return -EPROTONOSUPPORT; + } +} + +int bpf_lwt_push_ip_encap(struct sk_buff *skb, void *hdr, u32 len, bool ingress) +{ + struct iphdr *iph; + bool ipv4; + int err; + + if (unlikely(len < sizeof(struct iphdr) || len > LWT_BPF_MAX_HEADROOM)) + return -EINVAL; + + /* validate protocol and length */ + iph = (struct iphdr *)hdr; + if (iph->version == 4) { + ipv4 = true; + if (unlikely(len < iph->ihl * 4)) + return -EINVAL; + } else if (iph->version == 6) { + ipv4 = false; + if (unlikely(len < sizeof(struct ipv6hdr))) + return -EINVAL; + } else { + return -EINVAL; + } + + if (ingress) + err = skb_cow_head(skb, len + skb->mac_len); + else + err = skb_cow_head(skb, + len + LL_RESERVED_SPACE(skb_dst(skb)->dev)); + if (unlikely(err)) + return err; + + /* push the encap headers and fix pointers */ + skb_reset_inner_headers(skb); + skb->encapsulation = 1; + skb_push(skb, len); + if (ingress) + skb_postpush_rcsum(skb, iph, len); + skb_reset_network_header(skb); + memcpy(skb_network_header(skb), hdr, len); + bpf_compute_data_pointers(skb); + skb_clear_hash(skb); + + if (ipv4) { + skb->protocol = htons(ETH_P_IP); + iph = ip_hdr(skb); + + if (!iph->check) + iph->check = ip_fast_csum((unsigned char *)iph, + iph->ihl); + } else { + skb->protocol = htons(ETH_P_IPV6); + } + + if (skb_is_gso(skb)) + return handle_gso_encap(skb, ipv4, len); + + return 0; +} + static int __init bpf_lwt_init(void) { return lwtunnel_encap_add_ops(&bpf_encap_ops, LWTUNNEL_ENCAP_BPF); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 4230400b9a30..30f6fd8f68e0 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -42,6 +42,8 @@ #include <linux/inetdevice.h> #include <net/addrconf.h> +#include <trace/events/neigh.h> + #define DEBUG #define NEIGH_DEBUG 1 #define neigh_dbg(level, fmt, ...) \ @@ -102,6 +104,7 @@ static void neigh_cleanup_and_release(struct neighbour *neigh) if (neigh->parms->neigh_cleanup) neigh->parms->neigh_cleanup(neigh); + trace_neigh_cleanup_and_release(neigh, 0); __neigh_notify(neigh, RTM_DELNEIGH, 0, 0); call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh); neigh_release(neigh); @@ -1095,6 +1098,8 @@ out: if (notify) neigh_update_notify(neigh, 0); + trace_neigh_timer_handler(neigh, 0); + neigh_release(neigh); } @@ -1165,6 +1170,7 @@ out_unlock_bh: else write_unlock(&neigh->lock); local_bh_enable(); + trace_neigh_event_send_done(neigh, rc); return rc; out_dead: @@ -1172,6 +1178,7 @@ out_dead: goto out_unlock_bh; write_unlock_bh(&neigh->lock); kfree_skb(skb); + trace_neigh_event_send_dead(neigh, 1); return 1; } EXPORT_SYMBOL(__neigh_event_send); @@ -1227,6 +1234,8 @@ static int __neigh_update(struct neighbour *neigh, const u8 *lladdr, struct net_device *dev; int update_isrouter = 0; + trace_neigh_update(neigh, lladdr, new, flags, nlmsg_pid); + write_lock_bh(&neigh->lock); dev = neigh->dev; @@ -1393,6 +1402,8 @@ out: if (notify) neigh_update_notify(neigh, nlmsg_pid); + trace_neigh_update_done(neigh, err); + return err; } diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index ff9fd2bb4ce4..7c5061123ead 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -12,7 +12,6 @@ #include <linux/capability.h> #include <linux/kernel.h> #include <linux/netdevice.h> -#include <net/switchdev.h> #include <linux/if_arp.h> #include <linux/slab.h> #include <linux/sched/signal.h> @@ -501,16 +500,11 @@ static ssize_t phys_switch_id_show(struct device *dev, return restart_syscall(); if (dev_isalive(netdev)) { - struct switchdev_attr attr = { - .orig_dev = netdev, - .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, - .flags = SWITCHDEV_F_NO_RECURSE, - }; + struct netdev_phys_item_id ppid = { }; - ret = switchdev_port_attr_get(netdev, &attr); + ret = dev_get_port_parent_id(netdev, &ppid, false); if (!ret) - ret = sprintf(buf, "%*phN\n", attr.u.ppid.id_len, - attr.u.ppid.id); + ret = sprintf(buf, "%*phN\n", ppid.id_len, ppid.id); } rtnl_unlock(); diff --git a/net/core/net-traces.c b/net/core/net-traces.c index 419af6dfe29f..470b179d599e 100644 --- a/net/core/net-traces.c +++ b/net/core/net-traces.c @@ -43,6 +43,14 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(fdb_delete); EXPORT_TRACEPOINT_SYMBOL_GPL(br_fdb_update); #endif +#include <trace/events/neigh.h> +EXPORT_TRACEPOINT_SYMBOL_GPL(neigh_update); +EXPORT_TRACEPOINT_SYMBOL_GPL(neigh_update_done); +EXPORT_TRACEPOINT_SYMBOL_GPL(neigh_timer_handler); +EXPORT_TRACEPOINT_SYMBOL_GPL(neigh_event_send_done); +EXPORT_TRACEPOINT_SYMBOL_GPL(neigh_event_send_dead); +EXPORT_TRACEPOINT_SYMBOL_GPL(neigh_cleanup_and_release); + EXPORT_TRACEPOINT_SYMBOL_GPL(kfree_skb); EXPORT_TRACEPOINT_SYMBOL_GPL(napi_poll); diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 43a932cb609b..5b2252c6d49b 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -136,17 +136,19 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool, if (!(pool->p.flags & PP_FLAG_DMA_MAP)) goto skip_dma_map; - /* Setup DMA mapping: use page->private for DMA-addr + /* Setup DMA mapping: use 'struct page' area for storing DMA-addr + * since dma_addr_t can be either 32 or 64 bits and does not always fit + * into page private data (i.e 32bit cpu with 64bit DMA caps) * This mapping is kept for lifetime of page, until leaving pool. */ - dma = dma_map_page(pool->p.dev, page, 0, - (PAGE_SIZE << pool->p.order), - pool->p.dma_dir); + dma = dma_map_page_attrs(pool->p.dev, page, 0, + (PAGE_SIZE << pool->p.order), + pool->p.dma_dir, DMA_ATTR_SKIP_CPU_SYNC); if (dma_mapping_error(pool->p.dev, dma)) { put_page(page); return NULL; } - set_page_private(page, dma); /* page->private = dma; */ + page->dma_addr = dma; skip_dma_map: /* When page just alloc'ed is should/must have refcnt 1. */ @@ -175,13 +177,17 @@ EXPORT_SYMBOL(page_pool_alloc_pages); static void __page_pool_clean_page(struct page_pool *pool, struct page *page) { + dma_addr_t dma; + if (!(pool->p.flags & PP_FLAG_DMA_MAP)) return; + dma = page->dma_addr; /* DMA unmap */ - dma_unmap_page(pool->p.dev, page_private(page), - PAGE_SIZE << pool->p.order, pool->p.dma_dir); - set_page_private(page, 0); + dma_unmap_page_attrs(pool->p.dev, dma, + PAGE_SIZE << pool->p.order, pool->p.dma_dir, + DMA_ATTR_SKIP_CPU_SYNC); + page->dma_addr = 0; } /* Return a page to the page allocator, cleaning up our state */ diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index f5a98082ac7a..a51cab95ba64 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -46,7 +46,6 @@ #include <linux/inet.h> #include <linux/netdevice.h> -#include <net/switchdev.h> #include <net/ip.h> #include <net/protocol.h> #include <net/arp.h> @@ -1146,22 +1145,17 @@ static int rtnl_phys_port_name_fill(struct sk_buff *skb, struct net_device *dev) static int rtnl_phys_switch_id_fill(struct sk_buff *skb, struct net_device *dev) { + struct netdev_phys_item_id ppid = { }; int err; - struct switchdev_attr attr = { - .orig_dev = dev, - .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, - .flags = SWITCHDEV_F_NO_RECURSE, - }; - err = switchdev_port_attr_get(dev, &attr); + err = dev_get_port_parent_id(dev, &ppid, false); if (err) { if (err == -EOPNOTSUPP) return 0; return err; } - if (nla_put(skb, IFLA_PHYS_SWITCH_ID, attr.u.ppid.id_len, - attr.u.ppid.id)) + if (nla_put(skb, IFLA_PHYS_SWITCH_ID, ppid.id_len, ppid.id)) return -EMSGSIZE; return 0; diff --git a/net/core/scm.c b/net/core/scm.c index b1ff8a441748..52ef219cf6df 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -29,6 +29,7 @@ #include <linux/pid.h> #include <linux/nsproxy.h> #include <linux/slab.h> +#include <linux/errqueue.h> #include <linux/uaccess.h> @@ -252,6 +253,32 @@ out: } EXPORT_SYMBOL(put_cmsg); +void put_cmsg_scm_timestamping64(struct msghdr *msg, struct scm_timestamping_internal *tss_internal) +{ + struct scm_timestamping64 tss; + int i; + + for (i = 0; i < ARRAY_SIZE(tss.ts); i++) { + tss.ts[i].tv_sec = tss_internal->ts[i].tv_sec; + tss.ts[i].tv_nsec = tss_internal->ts[i].tv_nsec; + } + + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPING_NEW, sizeof(tss), &tss); +} +EXPORT_SYMBOL(put_cmsg_scm_timestamping64); + +void put_cmsg_scm_timestamping(struct msghdr *msg, struct scm_timestamping_internal *tss_internal) +{ + struct scm_timestamping tss; + int i; + + for (i = 0; i < ARRAY_SIZE(tss.ts); i++) + tss.ts[i] = timespec64_to_timespec(tss_internal->ts[i]); + + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPING_OLD, sizeof(tss), &tss); +} +EXPORT_SYMBOL(put_cmsg_scm_timestamping); + void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm) { struct cmsghdr __user *cm diff --git a/net/core/skmsg.c b/net/core/skmsg.c index e76ed8df9f13..ae6f06e45737 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -554,8 +554,7 @@ static void sk_psock_destroy_deferred(struct work_struct *gc) struct sk_psock *psock = container_of(gc, struct sk_psock, gc); /* No sk_callback_lock since already detached. */ - if (psock->parser.enabled) - strp_done(&psock->parser.strp); + strp_done(&psock->parser.strp); cancel_work_sync(&psock->work); diff --git a/net/core/sock.c b/net/core/sock.c index 900e8a9435f5..f4b8b78535f8 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -335,14 +335,68 @@ int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(__sk_backlog_rcv); -static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen) +static int sock_get_timeout(long timeo, void *optval, bool old_timeval) { - struct timeval tv; + struct __kernel_sock_timeval tv; + int size; - if (optlen < sizeof(tv)) - return -EINVAL; - if (copy_from_user(&tv, optval, sizeof(tv))) - return -EFAULT; + if (timeo == MAX_SCHEDULE_TIMEOUT) { + tv.tv_sec = 0; + tv.tv_usec = 0; + } else { + tv.tv_sec = timeo / HZ; + tv.tv_usec = ((timeo % HZ) * USEC_PER_SEC) / HZ; + } + + if (in_compat_syscall() && !COMPAT_USE_64BIT_TIME) { + struct old_timeval32 tv32 = { tv.tv_sec, tv.tv_usec }; + *(struct old_timeval32 *)optval = tv32; + return sizeof(tv32); + } + + if (old_timeval) { + struct __kernel_old_timeval old_tv; + old_tv.tv_sec = tv.tv_sec; + old_tv.tv_usec = tv.tv_usec; + *(struct __kernel_old_timeval *)optval = old_tv; + size = sizeof(old_tv); + } else { + *(struct __kernel_sock_timeval *)optval = tv; + size = sizeof(tv); + } + + return size; +} + +static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen, bool old_timeval) +{ + struct __kernel_sock_timeval tv; + + if (in_compat_syscall() && !COMPAT_USE_64BIT_TIME) { + struct old_timeval32 tv32; + + if (optlen < sizeof(tv32)) + return -EINVAL; + + if (copy_from_user(&tv32, optval, sizeof(tv32))) + return -EFAULT; + tv.tv_sec = tv32.tv_sec; + tv.tv_usec = tv32.tv_usec; + } else if (old_timeval) { + struct __kernel_old_timeval old_tv; + + if (optlen < sizeof(old_tv)) + return -EINVAL; + if (copy_from_user(&old_tv, optval, sizeof(old_tv))) + return -EFAULT; + tv.tv_sec = old_tv.tv_sec; + tv.tv_usec = old_tv.tv_usec; + } else { + if (optlen < sizeof(tv)) + return -EINVAL; + if (copy_from_user(&tv, optval, sizeof(tv))) + return -EFAULT; + } if (tv.tv_usec < 0 || tv.tv_usec >= USEC_PER_SEC) return -EDOM; @@ -360,8 +414,8 @@ static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen) *timeo_p = MAX_SCHEDULE_TIMEOUT; if (tv.tv_sec == 0 && tv.tv_usec == 0) return 0; - if (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT/HZ - 1)) - *timeo_p = tv.tv_sec * HZ + DIV_ROUND_UP(tv.tv_usec, USEC_PER_SEC / HZ); + if (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1)) + *timeo_p = tv.tv_sec * HZ + DIV_ROUND_UP((unsigned long)tv.tv_usec, USEC_PER_SEC / HZ); return 0; } @@ -731,6 +785,10 @@ int sock_setsockopt(struct socket *sock, int level, int optname, */ val = min_t(u32, val, sysctl_wmem_max); set_sndbuf: + /* Ensure val * 2 fits into an int, to prevent max_t() + * from treating it as a negative value. + */ + val = min_t(int, val, INT_MAX / 2); sk->sk_userlocks |= SOCK_SNDBUF_LOCK; sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF); /* Wake up sending tasks if we upped the value. */ @@ -742,6 +800,12 @@ set_sndbuf: ret = -EPERM; break; } + + /* No negative values (to prevent underflow, as val will be + * multiplied by 2). + */ + if (val < 0) + val = 0; goto set_sndbuf; case SO_RCVBUF: @@ -752,6 +816,10 @@ set_sndbuf: */ val = min_t(u32, val, sysctl_rmem_max); set_rcvbuf: + /* Ensure val * 2 fits into an int, to prevent max_t() + * from treating it as a negative value. + */ + val = min_t(int, val, INT_MAX / 2); sk->sk_userlocks |= SOCK_RCVBUF_LOCK; /* * We double it on the way in to account for @@ -776,6 +844,12 @@ set_rcvbuf: ret = -EPERM; break; } + + /* No negative values (to prevent underflow, as val will be + * multiplied by 2). + */ + if (val < 0) + val = 0; goto set_rcvbuf; case SO_KEEPALIVE: @@ -833,10 +907,17 @@ set_rcvbuf: clear_bit(SOCK_PASSCRED, &sock->flags); break; - case SO_TIMESTAMP: - case SO_TIMESTAMPNS: + case SO_TIMESTAMP_OLD: + case SO_TIMESTAMP_NEW: + case SO_TIMESTAMPNS_OLD: + case SO_TIMESTAMPNS_NEW: if (valbool) { - if (optname == SO_TIMESTAMP) + if (optname == SO_TIMESTAMP_NEW || optname == SO_TIMESTAMPNS_NEW) + sock_set_flag(sk, SOCK_TSTAMP_NEW); + else + sock_reset_flag(sk, SOCK_TSTAMP_NEW); + + if (optname == SO_TIMESTAMP_OLD || optname == SO_TIMESTAMP_NEW) sock_reset_flag(sk, SOCK_RCVTSTAMPNS); else sock_set_flag(sk, SOCK_RCVTSTAMPNS); @@ -845,10 +926,14 @@ set_rcvbuf: } else { sock_reset_flag(sk, SOCK_RCVTSTAMP); sock_reset_flag(sk, SOCK_RCVTSTAMPNS); + sock_reset_flag(sk, SOCK_TSTAMP_NEW); } break; - case SO_TIMESTAMPING: + case SO_TIMESTAMPING_NEW: + sock_set_flag(sk, SOCK_TSTAMP_NEW); + /* fall through */ + case SO_TIMESTAMPING_OLD: if (val & ~SOF_TIMESTAMPING_MASK) { ret = -EINVAL; break; @@ -879,9 +964,13 @@ set_rcvbuf: if (val & SOF_TIMESTAMPING_RX_SOFTWARE) sock_enable_timestamp(sk, SOCK_TIMESTAMPING_RX_SOFTWARE); - else + else { + if (optname == SO_TIMESTAMPING_NEW) + sock_reset_flag(sk, SOCK_TSTAMP_NEW); + sock_disable_timestamp(sk, (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)); + } break; case SO_RCVLOWAT: @@ -893,12 +982,14 @@ set_rcvbuf: sk->sk_rcvlowat = val ? : 1; break; - case SO_RCVTIMEO: - ret = sock_set_timeout(&sk->sk_rcvtimeo, optval, optlen); + case SO_RCVTIMEO_OLD: + case SO_RCVTIMEO_NEW: + ret = sock_set_timeout(&sk->sk_rcvtimeo, optval, optlen, optname == SO_RCVTIMEO_OLD); break; - case SO_SNDTIMEO: - ret = sock_set_timeout(&sk->sk_sndtimeo, optval, optlen); + case SO_SNDTIMEO_OLD: + case SO_SNDTIMEO_NEW: + ret = sock_set_timeout(&sk->sk_sndtimeo, optval, optlen, optname == SO_SNDTIMEO_OLD); break; case SO_ATTACH_FILTER: @@ -1121,7 +1212,9 @@ int sock_getsockopt(struct socket *sock, int level, int optname, int val; u64 val64; struct linger ling; - struct timeval tm; + struct old_timeval32 tm32; + struct __kernel_old_timeval tm; + struct __kernel_sock_timeval stm; struct sock_txtime txtime; } v; @@ -1208,39 +1301,36 @@ int sock_getsockopt(struct socket *sock, int level, int optname, sock_warn_obsolete_bsdism("getsockopt"); break; - case SO_TIMESTAMP: + case SO_TIMESTAMP_OLD: v.val = sock_flag(sk, SOCK_RCVTSTAMP) && + !sock_flag(sk, SOCK_TSTAMP_NEW) && !sock_flag(sk, SOCK_RCVTSTAMPNS); break; - case SO_TIMESTAMPNS: - v.val = sock_flag(sk, SOCK_RCVTSTAMPNS); + case SO_TIMESTAMPNS_OLD: + v.val = sock_flag(sk, SOCK_RCVTSTAMPNS) && !sock_flag(sk, SOCK_TSTAMP_NEW); + break; + + case SO_TIMESTAMP_NEW: + v.val = sock_flag(sk, SOCK_RCVTSTAMP) && sock_flag(sk, SOCK_TSTAMP_NEW); break; - case SO_TIMESTAMPING: + case SO_TIMESTAMPNS_NEW: + v.val = sock_flag(sk, SOCK_RCVTSTAMPNS) && sock_flag(sk, SOCK_TSTAMP_NEW); + break; + + case SO_TIMESTAMPING_OLD: v.val = sk->sk_tsflags; break; - case SO_RCVTIMEO: - lv = sizeof(struct timeval); - if (sk->sk_rcvtimeo == MAX_SCHEDULE_TIMEOUT) { - v.tm.tv_sec = 0; - v.tm.tv_usec = 0; - } else { - v.tm.tv_sec = sk->sk_rcvtimeo / HZ; - v.tm.tv_usec = ((sk->sk_rcvtimeo % HZ) * USEC_PER_SEC) / HZ; - } + case SO_RCVTIMEO_OLD: + case SO_RCVTIMEO_NEW: + lv = sock_get_timeout(sk->sk_rcvtimeo, &v, SO_RCVTIMEO_OLD == optname); break; - case SO_SNDTIMEO: - lv = sizeof(struct timeval); - if (sk->sk_sndtimeo == MAX_SCHEDULE_TIMEOUT) { - v.tm.tv_sec = 0; - v.tm.tv_usec = 0; - } else { - v.tm.tv_sec = sk->sk_sndtimeo / HZ; - v.tm.tv_usec = ((sk->sk_sndtimeo % HZ) * USEC_PER_SEC) / HZ; - } + case SO_SNDTIMEO_OLD: + case SO_SNDTIMEO_NEW: + lv = sock_get_timeout(sk->sk_sndtimeo, &v, SO_SNDTIMEO_OLD == optname); break; case SO_RCVLOWAT: @@ -2147,7 +2237,7 @@ int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg, return -EINVAL; sockc->mark = *(u32 *)CMSG_DATA(cmsg); break; - case SO_TIMESTAMPING: + case SO_TIMESTAMPING_OLD: if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) return -EINVAL; @@ -2405,7 +2495,7 @@ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind) } if (sk_has_memory_pressure(sk)) { - int alloc; + u64 alloc; if (!sk_under_memory_pressure(sk)) return 1; diff --git a/net/dccp/ccid.h b/net/dccp/ccid.h index 6eb837a47b5c..baaaeb2b2c42 100644 --- a/net/dccp/ccid.h +++ b/net/dccp/ccid.h @@ -202,7 +202,7 @@ static inline void ccid_hc_tx_packet_recv(struct ccid *ccid, struct sock *sk, static inline int ccid_hc_tx_parse_options(struct ccid *ccid, struct sock *sk, u8 pkt, u8 opt, u8 *val, u8 len) { - if (ccid->ccid_ops->ccid_hc_tx_parse_options == NULL) + if (!ccid || !ccid->ccid_ops->ccid_hc_tx_parse_options) return 0; return ccid->ccid_ops->ccid_hc_tx_parse_options(sk, pkt, opt, val, len); } @@ -214,7 +214,7 @@ static inline int ccid_hc_tx_parse_options(struct ccid *ccid, struct sock *sk, static inline int ccid_hc_rx_parse_options(struct ccid *ccid, struct sock *sk, u8 pkt, u8 opt, u8 *val, u8 len) { - if (ccid->ccid_ops->ccid_hc_rx_parse_options == NULL) + if (!ccid || !ccid->ccid_ops->ccid_hc_rx_parse_options) return 0; return ccid->ccid_ops->ccid_hc_rx_parse_options(sk, pkt, opt, val, len); } diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index d0b3e69c6b39..0962f9201baa 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -56,7 +56,7 @@ #include <net/dn_neigh.h> #include <net/dn_fib.h> -#define DN_IFREQ_SIZE (sizeof(struct ifreq) - sizeof(struct sockaddr) + sizeof(struct sockaddr_dn)) +#define DN_IFREQ_SIZE (offsetof(struct ifreq, ifr_ifru) + sizeof(struct sockaddr_dn)) static char dn_rt_all_end_mcast[ETH_ALEN] = {0xAB,0x00,0x00,0x04,0x00,0x00}; static char dn_rt_all_rt_mcast[ETH_ALEN] = {0xAB,0x00,0x00,0x03,0x00,0x00}; diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index a1917025e155..8c431e0f3627 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -767,11 +767,10 @@ static int dsa_switch_probe(struct dsa_switch *ds) struct dsa_switch *dsa_switch_alloc(struct device *dev, size_t n) { - size_t size = sizeof(struct dsa_switch) + n * sizeof(struct dsa_port); struct dsa_switch *ds; int i; - ds = devm_kzalloc(dev, size, GFP_KERNEL); + ds = devm_kzalloc(dev, struct_size(ds, ports, n), GFP_KERNEL); if (!ds) return NULL; diff --git a/net/dsa/master.c b/net/dsa/master.c index 79e97d2f2d9b..c58f33931be1 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -248,6 +248,8 @@ static void dsa_master_reset_mtu(struct net_device *dev) rtnl_unlock(); } +static struct lock_class_key dsa_master_addr_list_lock_key; + int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) { int ret; @@ -261,6 +263,8 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) wmb(); dev->dsa_ptr = cpu_dp; + lockdep_set_class(&dev->addr_list_lock, + &dsa_master_addr_list_lock_key); ret = dsa_master_ethtool_setup(dev); if (ret) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 91de3a663226..2e5e7c04821b 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -140,11 +140,14 @@ static int dsa_slave_close(struct net_device *dev) static void dsa_slave_change_rx_flags(struct net_device *dev, int change) { struct net_device *master = dsa_slave_to_master(dev); - - if (change & IFF_ALLMULTI) - dev_set_allmulti(master, dev->flags & IFF_ALLMULTI ? 1 : -1); - if (change & IFF_PROMISC) - dev_set_promiscuity(master, dev->flags & IFF_PROMISC ? 1 : -1); + if (dev->flags & IFF_UP) { + if (change & IFF_ALLMULTI) + dev_set_allmulti(master, + dev->flags & IFF_ALLMULTI ? 1 : -1); + if (change & IFF_PROMISC) + dev_set_promiscuity(master, + dev->flags & IFF_PROMISC ? 1 : -1); + } } static void dsa_slave_set_rx_mode(struct net_device *dev) @@ -362,18 +365,23 @@ static int dsa_slave_port_obj_del(struct net_device *dev, return err; } -static int dsa_slave_port_attr_get(struct net_device *dev, - struct switchdev_attr *attr) +static int dsa_slave_get_port_parent_id(struct net_device *dev, + struct netdev_phys_item_id *ppid) { struct dsa_port *dp = dsa_slave_to_port(dev); struct dsa_switch *ds = dp->ds; struct dsa_switch_tree *dst = ds->dst; + ppid->id_len = sizeof(dst->index); + memcpy(&ppid->id, &dst->index, ppid->id_len); + + return 0; +} + +static int dsa_slave_port_attr_get(struct net_device *dev, + struct switchdev_attr *attr) +{ switch (attr->id) { - case SWITCHDEV_ATTR_ID_PORT_PARENT_ID: - attr->u.ppid.id_len = sizeof(dst->index); - memcpy(&attr->u.ppid.id, &dst->index, attr->u.ppid.id_len); - break; case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT: attr->u.brport_flags_support = 0; break; @@ -639,7 +647,7 @@ static int dsa_slave_set_eee(struct net_device *dev, struct ethtool_eee *e) int ret; /* Port's PHY and MAC both need to be EEE capable */ - if (!dev->phydev && !dp->pl) + if (!dev->phydev || !dp->pl) return -ENODEV; if (!ds->ops->set_mac_eee) @@ -659,7 +667,7 @@ static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e) int ret; /* Port's PHY and MAC both need to be EEE capable */ - if (!dev->phydev && !dp->pl) + if (!dev->phydev || !dp->pl) return -ENODEV; if (!ds->ops->get_mac_eee) @@ -1046,6 +1054,7 @@ static const struct net_device_ops dsa_slave_netdev_ops = { .ndo_get_phys_port_name = dsa_slave_get_phys_port_name, .ndo_setup_tc = dsa_slave_setup_tc, .ndo_get_stats64 = dsa_slave_get_stats64, + .ndo_get_port_parent_id = dsa_slave_get_port_parent_id, }; static const struct switchdev_ops dsa_slave_switchdev_ops = { diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index da71b9e2af52..927e9c86f745 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -67,6 +67,8 @@ static struct sk_buff *ksz_common_rcv(struct sk_buff *skb, pskb_trim_rcsum(skb, skb->len - len); + skb->offload_fwd_mark = true; + return skb; } diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 5022bc63863a..8e185b5a2bf6 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1072,7 +1072,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg, goto failure; } - fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL); + fi = kzalloc(struct_size(fi, fib_nh, nhs), GFP_KERNEL); if (!fi) goto failure; fi->fib_metrics = ip_fib_metrics_init(fi->fib_net, cfg->fc_mx, diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index a40e48ded10d..b448cf32296c 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -159,7 +159,8 @@ static int unsolicited_report_interval(struct in_device *in_dev) return interval_jiffies; } -static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im); +static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im, + gfp_t gfp); static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im); static void igmpv3_clear_delrec(struct in_device *in_dev); static int sf_setstate(struct ip_mc_list *pmc); @@ -1145,7 +1146,8 @@ static void ip_mc_filter_del(struct in_device *in_dev, __be32 addr) /* * deleted ip_mc_list manipulation */ -static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im) +static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im, + gfp_t gfp) { struct ip_mc_list *pmc; struct net *net = dev_net(in_dev->dev); @@ -1156,7 +1158,7 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im) * for deleted items allows change reports to use common code with * non-deleted or query-response MCA's. */ - pmc = kzalloc(sizeof(*pmc), GFP_KERNEL); + pmc = kzalloc(sizeof(*pmc), gfp); if (!pmc) return; spin_lock_init(&pmc->lock); @@ -1261,7 +1263,7 @@ static void igmpv3_clear_delrec(struct in_device *in_dev) } #endif -static void igmp_group_dropped(struct ip_mc_list *im) +static void __igmp_group_dropped(struct ip_mc_list *im, gfp_t gfp) { struct in_device *in_dev = im->interface; #ifdef CONFIG_IP_MULTICAST @@ -1292,13 +1294,18 @@ static void igmp_group_dropped(struct ip_mc_list *im) return; } /* IGMPv3 */ - igmpv3_add_delrec(in_dev, im); + igmpv3_add_delrec(in_dev, im, gfp); igmp_ifc_event(in_dev); } #endif } +static void igmp_group_dropped(struct ip_mc_list *im) +{ + __igmp_group_dropped(im, GFP_KERNEL); +} + static void igmp_group_added(struct ip_mc_list *im) { struct in_device *in_dev = im->interface; @@ -1400,8 +1407,8 @@ static void ip_mc_hash_remove(struct in_device *in_dev, /* * A socket has joined a multicast group on device dev. */ -static void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, - unsigned int mode) +static void ____ip_mc_inc_group(struct in_device *in_dev, __be32 addr, + unsigned int mode, gfp_t gfp) { struct ip_mc_list *im; @@ -1415,7 +1422,7 @@ static void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, } } - im = kzalloc(sizeof(*im), GFP_KERNEL); + im = kzalloc(sizeof(*im), gfp); if (!im) goto out; @@ -1448,6 +1455,12 @@ out: return; } +void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, gfp_t gfp) +{ + ____ip_mc_inc_group(in_dev, addr, MCAST_EXCLUDE, gfp); +} +EXPORT_SYMBOL(__ip_mc_inc_group); + void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) { __ip_mc_inc_group(in_dev, addr, MCAST_EXCLUDE); @@ -1634,7 +1647,7 @@ static void ip_mc_rejoin_groups(struct in_device *in_dev) * A socket has left a multicast group on device dev */ -void ip_mc_dec_group(struct in_device *in_dev, __be32 addr) +void __ip_mc_dec_group(struct in_device *in_dev, __be32 addr, gfp_t gfp) { struct ip_mc_list *i; struct ip_mc_list __rcu **ip; @@ -1649,7 +1662,7 @@ void ip_mc_dec_group(struct in_device *in_dev, __be32 addr) ip_mc_hash_remove(in_dev, i); *ip = i->next_rcu; in_dev->mc_count--; - igmp_group_dropped(i); + __igmp_group_dropped(i, gfp); ip_mc_clear_src(i); if (!in_dev->dead) @@ -1662,7 +1675,7 @@ void ip_mc_dec_group(struct in_device *in_dev, __be32 addr) } } } -EXPORT_SYMBOL(ip_mc_dec_group); +EXPORT_SYMBOL(__ip_mc_dec_group); /* Device changing type */ diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 1a4e9ff02762..5731670c560b 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -108,6 +108,7 @@ static size_t inet_sk_attr_size(struct sock *sk, + nla_total_size(1) /* INET_DIAG_TOS */ + nla_total_size(1) /* INET_DIAG_TCLASS */ + nla_total_size(4) /* INET_DIAG_MARK */ + + nla_total_size(4) /* INET_DIAG_CLASS_ID */ + nla_total_size(sizeof(struct inet_diag_meminfo)) + nla_total_size(sizeof(struct inet_diag_msg)) + nla_total_size(SK_MEMINFO_VARS * sizeof(u32)) @@ -287,12 +288,19 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, goto errout; } - if (ext & (1 << (INET_DIAG_CLASS_ID - 1))) { + if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) || + ext & (1 << (INET_DIAG_TCLASS - 1))) { u32 classid = 0; #ifdef CONFIG_SOCK_CGROUP_DATA classid = sock_cgroup_classid(&sk->sk_cgrp_data); #endif + /* Fallback to socket priority if class id isn't set. + * Classful qdiscs use it as direct reference to class. + * For cgroup2 classid is always zero. + */ + if (!classid) + classid = sk->sk_priority; if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid)) goto errout; diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index d757b9642d0d..be778599bfed 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -216,6 +216,7 @@ struct inet_peer *inet_getpeer(struct inet_peer_base *base, atomic_set(&p->rid, 0); p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW; p->rate_tokens = 0; + p->n_redirects = 0; /* 60*HZ is arbitrary, but chosen enough high so that the first * calculation of tokens is at its maximum. */ diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index d1cef66820d3..ccee9411dae1 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1381,12 +1381,17 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm *p = &t->parms; + __be16 o_flags = p->o_flags; + + if ((t->erspan_ver == 1 || t->erspan_ver == 2) && + !t->collect_md) + o_flags |= TUNNEL_KEY; if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) || nla_put_be16(skb, IFLA_GRE_IFLAGS, gre_tnl_flags_to_gre_flags(p->i_flags)) || nla_put_be16(skb, IFLA_GRE_OFLAGS, - gre_tnl_flags_to_gre_flags(p->o_flags)) || + gre_tnl_flags_to_gre_flags(o_flags)) || nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) || nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) || nla_put_in_addr(skb, IFLA_GRE_LOCAL, p->iph.saddr) || diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index d7b43e700023..68a21bf75dd0 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -74,6 +74,33 @@ drop: return 0; } +static int vti_input_ipip(struct sk_buff *skb, int nexthdr, __be32 spi, + int encap_type) +{ + struct ip_tunnel *tunnel; + const struct iphdr *iph = ip_hdr(skb); + struct net *net = dev_net(skb->dev); + struct ip_tunnel_net *itn = net_generic(net, vti_net_id); + + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, + iph->saddr, iph->daddr, 0); + if (tunnel) { + if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) + goto drop; + + XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel; + + skb->dev = tunnel->dev; + + return xfrm_input(skb, nexthdr, spi, encap_type); + } + + return -EINVAL; +drop: + kfree_skb(skb); + return 0; +} + static int vti_rcv(struct sk_buff *skb) { XFRM_SPI_SKB_CB(skb)->family = AF_INET; @@ -82,6 +109,14 @@ static int vti_rcv(struct sk_buff *skb) return vti_input(skb, ip_hdr(skb)->protocol, 0, 0); } +static int vti_rcv_ipip(struct sk_buff *skb) +{ + XFRM_SPI_SKB_CB(skb)->family = AF_INET; + XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); + + return vti_input_ipip(skb, ip_hdr(skb)->protocol, ip_hdr(skb)->saddr, 0); +} + static int vti_rcv_cb(struct sk_buff *skb, int err) { unsigned short family; @@ -435,6 +470,12 @@ static struct xfrm4_protocol vti_ipcomp4_protocol __read_mostly = { .priority = 100, }; +static struct xfrm_tunnel ipip_handler __read_mostly = { + .handler = vti_rcv_ipip, + .err_handler = vti4_err, + .priority = 0, +}; + static int __net_init vti_init_net(struct net *net) { int err; @@ -603,6 +644,13 @@ static int __init vti_init(void) if (err < 0) goto xfrm_proto_comp_failed; + msg = "ipip tunnel"; + err = xfrm4_tunnel_register(&ipip_handler, AF_INET); + if (err < 0) { + pr_info("%s: cant't register tunnel\n",__func__); + goto xfrm_tunnel_failed; + } + msg = "netlink interface"; err = rtnl_link_register(&vti_link_ops); if (err < 0) @@ -612,6 +660,8 @@ static int __init vti_init(void) rtnl_link_failed: xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP); +xfrm_tunnel_failed: + xfrm4_tunnel_deregister(&ipip_handler, AF_INET); xfrm_proto_comp_failed: xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH); xfrm_proto_ah_failed: diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index b9a9873c25c6..9bcca08efec9 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -85,7 +85,6 @@ /* Define the friendly delay before and after opening net devices */ #define CONF_POST_OPEN 10 /* After opening: 10 msecs */ -#define CONF_CARRIER_TIMEOUT 120000 /* Wait for carrier timeout */ /* Define the timeout for waiting for a DHCP/BOOTP/RARP reply */ #define CONF_OPEN_RETRIES 2 /* (Re)open devices twice */ @@ -101,6 +100,9 @@ #define NONE cpu_to_be32(INADDR_NONE) #define ANY cpu_to_be32(INADDR_ANY) +/* Wait for carrier timeout default in seconds */ +static unsigned int carrier_timeout = 120; + /* * Public IP configuration */ @@ -268,9 +270,9 @@ static int __init ic_open_devs(void) /* wait for a carrier on at least one device */ start = jiffies; - next_msg = start + msecs_to_jiffies(CONF_CARRIER_TIMEOUT/12); + next_msg = start + msecs_to_jiffies(20000); while (time_before(jiffies, start + - msecs_to_jiffies(CONF_CARRIER_TIMEOUT))) { + msecs_to_jiffies(carrier_timeout * 1000))) { int wait, elapsed; for_each_netdev(&init_net, dev) @@ -283,9 +285,9 @@ static int __init ic_open_devs(void) continue; elapsed = jiffies_to_msecs(jiffies - start); - wait = (CONF_CARRIER_TIMEOUT - elapsed + 500)/1000; + wait = (carrier_timeout * 1000 - elapsed + 500) / 1000; pr_info("Waiting up to %d more seconds for network.\n", wait); - next_msg = jiffies + msecs_to_jiffies(CONF_CARRIER_TIMEOUT/12); + next_msg = jiffies + msecs_to_jiffies(20000); } have_carrier: rtnl_unlock(); @@ -1780,3 +1782,18 @@ static int __init vendor_class_identifier_setup(char *addrs) return 1; } __setup("dhcpclass=", vendor_class_identifier_setup); + +static int __init set_carrier_timeout(char *str) +{ + ssize_t ret; + + if (!str) + return 0; + + ret = kstrtouint(str, 0, &carrier_timeout); + if (ret) + return 0; + + return 1; +} +__setup("carrier_timeout=", set_carrier_timeout); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index fb99002c3d4e..e536970557dd 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -67,7 +67,6 @@ #include <net/fib_rules.h> #include <linux/netconf.h> #include <net/nexthop.h> -#include <net/switchdev.h> #include <linux/nospec.h> @@ -837,10 +836,8 @@ static void ipmr_update_thresholds(struct mr_table *mrt, struct mr_mfc *cache, static int vif_add(struct net *net, struct mr_table *mrt, struct vifctl *vifc, int mrtsock) { + struct netdev_phys_item_id ppid = { }; int vifi = vifc->vifc_vifi; - struct switchdev_attr attr = { - .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, - }; struct vif_device *v = &mrt->vif_table[vifi]; struct net_device *dev; struct in_device *in_dev; @@ -919,10 +916,10 @@ static int vif_add(struct net *net, struct mr_table *mrt, vifc->vifc_flags | (!mrtsock ? VIFF_STATIC : 0), (VIFF_TUNNEL | VIFF_REGISTER)); - attr.orig_dev = dev; - if (!switchdev_port_attr_get(dev, &attr)) { - memcpy(v->dev_parent_id.id, attr.u.ppid.id, attr.u.ppid.id_len); - v->dev_parent_id.id_len = attr.u.ppid.id_len; + err = dev_get_port_parent_id(dev, &ppid, true); + if (err == 0) { + memcpy(v->dev_parent_id.id, ppid.id, ppid.id_len); + v->dev_parent_id.id_len = ppid.id_len; } else { v->dev_parent_id.id_len = 0; } diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 91b369bc44f9..835d50b279f5 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -846,9 +846,9 @@ static int clusterip_net_init(struct net *net) static void clusterip_net_exit(struct net *net) { +#ifdef CONFIG_PROC_FS struct clusterip_net *cn = clusterip_pernet(net); -#ifdef CONFIG_PROC_FS mutex_lock(&cn->mutex); proc_remove(cn->procdir); cn->procdir = NULL; diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c index e26165af45cb..4b07eb8a9b18 100644 --- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c @@ -215,6 +215,7 @@ int nf_nat_icmp_reply_translation(struct sk_buff *skb, /* Change outer to look like the reply to an incoming packet */ nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple); + target.dst.protonum = IPPROTO_ICMP; if (!nf_nat_ipv4_manip_pkt(skb, 0, &target, manip)) return 0; diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic_main.c b/net/ipv4/netfilter/nf_nat_snmp_basic_main.c index a0aa13bcabda..0a8a60c1bf9a 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic_main.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic_main.c @@ -105,6 +105,8 @@ static void fast_csum(struct snmp_ctx *ctx, unsigned char offset) int snmp_version(void *context, size_t hdrlen, unsigned char tag, const void *data, size_t datalen) { + if (datalen != 1) + return -EINVAL; if (*(unsigned char *)data > 1) return -ENOTSUPP; return 1; @@ -114,8 +116,11 @@ int snmp_helper(void *context, size_t hdrlen, unsigned char tag, const void *data, size_t datalen) { struct snmp_ctx *ctx = (struct snmp_ctx *)context; - __be32 *pdata = (__be32 *)data; + __be32 *pdata; + if (datalen != 4) + return -EINVAL; + pdata = (__be32 *)data; if (*pdata == ctx->from) { pr_debug("%s: %pI4 to %pI4\n", __func__, (void *)&ctx->from, (void *)&ctx->to); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 99be68b15da0..ecc12a768191 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -887,13 +887,15 @@ void ip_rt_send_redirect(struct sk_buff *skb) /* No redirected packets during ip_rt_redirect_silence; * reset the algorithm. */ - if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence)) + if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence)) { peer->rate_tokens = 0; + peer->n_redirects = 0; + } /* Too many ignored redirects; do not send anything * set dst.rate_last to the last seen redirected packet. */ - if (peer->rate_tokens >= ip_rt_redirect_number) { + if (peer->n_redirects >= ip_rt_redirect_number) { peer->rate_last = jiffies; goto out_put_peer; } @@ -910,6 +912,7 @@ void ip_rt_send_redirect(struct sk_buff *skb) icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw); peer->rate_last = jiffies; ++peer->rate_tokens; + ++peer->n_redirects; #ifdef CONFIG_IP_ROUTE_VERBOSE if (log_martians && peer->rate_tokens == ip_rt_redirect_number) @@ -1608,7 +1611,8 @@ int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr, return -EINVAL; if (ipv4_is_zeronet(saddr)) { - if (!ipv4_is_local_multicast(daddr)) + if (!ipv4_is_local_multicast(daddr) && + ip_hdr(skb)->protocol != IPPROTO_IGMP) return -EINVAL; } else { err = fib_validate_source(skb, saddr, 0, tos, 0, dev, diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 6f8d292ad501..cab6b2f2f61d 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1844,57 +1844,78 @@ out: #endif static void tcp_update_recv_tstamps(struct sk_buff *skb, - struct scm_timestamping *tss) + struct scm_timestamping_internal *tss) { if (skb->tstamp) - tss->ts[0] = ktime_to_timespec(skb->tstamp); + tss->ts[0] = ktime_to_timespec64(skb->tstamp); else - tss->ts[0] = (struct timespec) {0}; + tss->ts[0] = (struct timespec64) {0}; if (skb_hwtstamps(skb)->hwtstamp) - tss->ts[2] = ktime_to_timespec(skb_hwtstamps(skb)->hwtstamp); + tss->ts[2] = ktime_to_timespec64(skb_hwtstamps(skb)->hwtstamp); else - tss->ts[2] = (struct timespec) {0}; + tss->ts[2] = (struct timespec64) {0}; } /* Similar to __sock_recv_timestamp, but does not require an skb */ static void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, - struct scm_timestamping *tss) + struct scm_timestamping_internal *tss) { - struct timeval tv; + int new_tstamp = sock_flag(sk, SOCK_TSTAMP_NEW); bool has_timestamping = false; if (tss->ts[0].tv_sec || tss->ts[0].tv_nsec) { if (sock_flag(sk, SOCK_RCVTSTAMP)) { if (sock_flag(sk, SOCK_RCVTSTAMPNS)) { - put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPNS, - sizeof(tss->ts[0]), &tss->ts[0]); - } else { - tv.tv_sec = tss->ts[0].tv_sec; - tv.tv_usec = tss->ts[0].tv_nsec / 1000; + if (new_tstamp) { + struct __kernel_timespec kts = {tss->ts[0].tv_sec, tss->ts[0].tv_nsec}; + + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_NEW, + sizeof(kts), &kts); + } else { + struct timespec ts_old = timespec64_to_timespec(tss->ts[0]); - put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMP, - sizeof(tv), &tv); + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_OLD, + sizeof(ts_old), &ts_old); + } + } else { + if (new_tstamp) { + struct __kernel_sock_timeval stv; + + stv.tv_sec = tss->ts[0].tv_sec; + stv.tv_usec = tss->ts[0].tv_nsec / 1000; + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_NEW, + sizeof(stv), &stv); + } else { + struct __kernel_old_timeval tv; + + tv.tv_sec = tss->ts[0].tv_sec; + tv.tv_usec = tss->ts[0].tv_nsec / 1000; + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_OLD, + sizeof(tv), &tv); + } } } if (sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) has_timestamping = true; else - tss->ts[0] = (struct timespec) {0}; + tss->ts[0] = (struct timespec64) {0}; } if (tss->ts[2].tv_sec || tss->ts[2].tv_nsec) { if (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) has_timestamping = true; else - tss->ts[2] = (struct timespec) {0}; + tss->ts[2] = (struct timespec64) {0}; } if (has_timestamping) { - tss->ts[1] = (struct timespec) {0}; - put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPING, - sizeof(*tss), tss); + tss->ts[1] = (struct timespec64) {0}; + if (sock_flag(sk, SOCK_TSTAMP_NEW)) + put_cmsg_scm_timestamping64(msg, tss); + else + put_cmsg_scm_timestamping(msg, tss); } } @@ -1935,7 +1956,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, long timeo; struct sk_buff *skb, *last; u32 urg_hole = 0; - struct scm_timestamping tss; + struct scm_timestamping_internal tss; bool has_tss = false; bool has_cmsg; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index dcb1d434f7da..da5a21050ba9 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1200,7 +1200,8 @@ check_cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long *expires) list_for_each_entry(ifa, &idev->addr_list, if_list) { if (ifa == ifp) continue; - if (!ipv6_prefix_equal(&ifa->addr, &ifp->addr, + if (ifa->prefix_len != ifp->prefix_len || + !ipv6_prefix_equal(&ifa->addr, &ifp->addr, ifp->prefix_len)) continue; if (ifa->flags & (IFA_F_PERMANENT | IFA_F_NOPREFIXROUTE)) diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index 5cd0029d930e..6c79af056d9b 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -134,6 +134,11 @@ static int eafnosupport_ipv6_dst_lookup(struct net *net, struct sock *u1, return -EAFNOSUPPORT; } +static int eafnosupport_ipv6_route_input(struct sk_buff *skb) +{ + return -EAFNOSUPPORT; +} + static struct fib6_table *eafnosupport_fib6_get_table(struct net *net, u32 id) { return NULL; @@ -170,6 +175,7 @@ eafnosupport_ip6_mtu_from_fib6(struct fib6_info *f6i, struct in6_addr *daddr, const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) { .ipv6_dst_lookup = eafnosupport_ipv6_dst_lookup, + .ipv6_route_input = eafnosupport_ipv6_route_input, .fib6_get_table = eafnosupport_fib6_get_table, .fib6_table_lookup = eafnosupport_fib6_table_lookup, .fib6_lookup = eafnosupport_fib6_lookup, diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index d99753b5e39b..2f45d2a3e3a3 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -900,10 +900,17 @@ static struct pernet_operations inet6_net_ops = { .exit = inet6_net_exit, }; +static int ipv6_route_input(struct sk_buff *skb) +{ + ip6_route_input(skb); + return skb_dst(skb)->error; +} + static const struct ipv6_stub ipv6_stub_impl = { .ipv6_sock_mc_join = ipv6_sock_mc_join, .ipv6_sock_mc_drop = ipv6_sock_mc_drop, .ipv6_dst_lookup = ip6_dst_lookup, + .ipv6_route_input = ipv6_route_input, .fib6_get_table = fib6_get_table, .fib6_table_lookup = fib6_table_lookup, .fib6_lookup = fib6_lookup, diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index e081e69d534e..65a4f96dc462 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -2098,12 +2098,17 @@ static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct __ip6_tnl_parm *p = &t->parms; + __be16 o_flags = p->o_flags; + + if ((p->erspan_ver == 1 || p->erspan_ver == 2) && + !p->collect_md) + o_flags |= TUNNEL_KEY; if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) || nla_put_be16(skb, IFLA_GRE_IFLAGS, gre_tnl_flags_to_gre_flags(p->i_flags)) || nla_put_be16(skb, IFLA_GRE_OFLAGS, - gre_tnl_flags_to_gre_flags(p->o_flags)) || + gre_tnl_flags_to_gre_flags(o_flags)) || nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) || nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) || nla_put_in6_addr(skb, IFLA_GRE_LOCAL, &p->laddr) || diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 30337b38274b..cc01aa3f2b5e 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1516,6 +1516,9 @@ static void mroute_clean_tables(struct mr_table *mrt, bool all) continue; rhltable_remove(&mrt->mfc_hash, &c->mnode, ip6mr_rht_params); list_del_rcu(&c->list); + call_ip6mr_mfc_entry_notifiers(read_pnet(&mrt->net), + FIB_EVENT_ENTRY_DEL, + (struct mfc6_cache *)c, mrt->id); mr6_netlink_event(mrt, (struct mfc6_cache *)c, RTM_DELROUTE); mr_cache_put(c); } @@ -1524,10 +1527,6 @@ static void mroute_clean_tables(struct mr_table *mrt, bool all) spin_lock_bh(&mfc_unres_lock); list_for_each_entry_safe(c, tmp, &mrt->mfc_unres_queue, list) { list_del(&c->list); - call_ip6mr_mfc_entry_notifiers(read_pnet(&mrt->net), - FIB_EVENT_ENTRY_DEL, - (struct mfc6_cache *)c, - mrt->id); mr6_netlink_event(mrt, (struct mfc6_cache *)c, RTM_DELROUTE); ip6mr_destroy_unres(mrt, (struct mfc6_cache *)c); diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index a8263031f3a6..1240ccd57f39 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -23,9 +23,11 @@ int ip6_route_me_harder(struct net *net, struct sk_buff *skb) struct sock *sk = sk_to_full_sk(skb->sk); unsigned int hh_len; struct dst_entry *dst; + int strict = (ipv6_addr_type(&iph->daddr) & + (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL)); struct flowi6 fl6 = { .flowi6_oif = sk && sk->sk_bound_dev_if ? sk->sk_bound_dev_if : - rt6_need_strict(&iph->daddr) ? skb_dst(skb)->dev->ifindex : 0, + strict ? skb_dst(skb)->dev->ifindex : 0, .flowi6_mark = skb->mark, .flowi6_uid = sock_net_uid(net, sk), .daddr = iph->daddr, diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c index b52026adb3e7..490bfd3c9162 100644 --- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c @@ -227,6 +227,7 @@ int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, } nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple); + target.dst.protonum = IPPROTO_ICMPV6; if (!nf_nat_ipv6_manip_pkt(skb, 0, &target, manip)) return 0; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index dc066fdf7e46..87a0561136dd 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2277,14 +2277,8 @@ static void rt6_do_update_pmtu(struct rt6_info *rt, u32 mtu) static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt) { - bool from_set; - - rcu_read_lock(); - from_set = !!rcu_dereference(rt->from); - rcu_read_unlock(); - return !(rt->rt6i_flags & RTF_CACHE) && - (rt->rt6i_flags & RTF_PCPU || from_set); + (rt->rt6i_flags & RTF_PCPU || rcu_access_pointer(rt->from)); } static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index 8d0ba757a46c..9b2f272ca164 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -221,9 +221,7 @@ static int seg6_genl_get_tunsrc(struct sk_buff *skb, struct genl_info *info) rcu_read_unlock(); genlmsg_end(msg, hdr); - genlmsg_reply(msg, info); - - return 0; + return genlmsg_reply(msg, info); nla_put_failure: rcu_read_unlock(); diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 8181ee7e1e27..ee5403cbe655 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -146,6 +146,8 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) } else { ip6_flow_hdr(hdr, 0, flowlabel); hdr->hop_limit = ip6_dst_hoplimit(skb_dst(skb)); + + memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); } hdr->nexthdr = NEXTHDR_ROUTING; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 1e03305c0549..e8a1dabef803 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -546,7 +546,8 @@ static int ipip6_err(struct sk_buff *skb, u32 info) } err = 0; - if (!ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4, type, data_len)) + if (__in6_dev_get(skb->dev) && + !ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4, type, data_len)) goto out; if (t->parms.iph.daddr == 0) diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 26f1d435696a..fed6becc5daf 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -83,8 +83,7 @@ #define L2TP_SLFLAG_S 0x40000000 #define L2TP_SL_SEQ_MASK 0x00ffffff -#define L2TP_HDR_SIZE_SEQ 10 -#define L2TP_HDR_SIZE_NOSEQ 6 +#define L2TP_HDR_SIZE_MAX 14 /* Default trace flags */ #define L2TP_DEFAULT_DEBUG_FLAGS 0 @@ -808,7 +807,7 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) __skb_pull(skb, sizeof(struct udphdr)); /* Short packet? */ - if (!pskb_may_pull(skb, L2TP_HDR_SIZE_SEQ)) { + if (!pskb_may_pull(skb, L2TP_HDR_SIZE_MAX)) { l2tp_info(tunnel, L2TP_MSG_DATA, "%s: recv short packet (len=%d)\n", tunnel->name, skb->len); @@ -884,6 +883,10 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb) goto error; } + if (tunnel->version == L2TP_HDR_VER_3 && + l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) + goto error; + l2tp_recv_common(session, skb, ptr, optr, hdrflags, length); l2tp_session_dec_refcount(session); diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 9c9afe94d389..b2ce90260c35 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -301,6 +301,26 @@ static inline bool l2tp_tunnel_uses_xfrm(const struct l2tp_tunnel *tunnel) } #endif +static inline int l2tp_v3_ensure_opt_in_linear(struct l2tp_session *session, struct sk_buff *skb, + unsigned char **ptr, unsigned char **optr) +{ + int opt_len = session->peer_cookie_len + l2tp_get_l2specific_len(session); + + if (opt_len > 0) { + int off = *ptr - *optr; + + if (!pskb_may_pull(skb, off + opt_len)) + return -1; + + if (skb->data != *optr) { + *optr = skb->data; + *ptr = skb->data + off; + } + } + + return 0; +} + #define l2tp_printk(ptr, type, func, fmt, ...) \ do { \ if (((ptr)->debug) & (type)) \ diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 35f6f86d4dcc..d4c60523c549 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -165,6 +165,9 @@ static int l2tp_ip_recv(struct sk_buff *skb) print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length); } + if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) + goto discard_sess; + l2tp_recv_common(session, skb, ptr, optr, 0, skb->len); l2tp_session_dec_refcount(session); diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 237f1a4a0b0c..0ae6899edac0 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -178,6 +178,9 @@ static int l2tp_ip6_recv(struct sk_buff *skb) print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length); } + if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr)) + goto discard_sess; + l2tp_recv_common(session, skb, ptr, optr, 0, skb->len); l2tp_session_dec_refcount(session); diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index 69e831bc317b..2c4cd4183bf9 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -8,7 +8,7 @@ * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2007-2010, Intel Corporation * Copyright(c) 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018 Intel Corporation + * Copyright (C) 2018 - 2019 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -229,7 +229,7 @@ ieee80211_agg_start_txq(struct sta_info *sta, int tid, bool enable) clear_bit(IEEE80211_TXQ_STOP, &txqi->flags); local_bh_disable(); rcu_read_lock(); - drv_wake_tx_queue(sta->sdata->local, txqi); + schedule_and_wake_txq(sta->sdata->local, txqi); rcu_read_unlock(); local_bh_enable(); } @@ -366,6 +366,8 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, set_bit(HT_AGG_STATE_STOPPING, &tid_tx->state); + ieee80211_agg_stop_txq(sta, tid); + spin_unlock_bh(&sta->lock); ht_dbg(sta->sdata, "Tx BA session stop requested for %pM tid %u\n", diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 2493c74c2d37..d65aa019ce85 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1231,6 +1231,11 @@ static void sta_apply_mesh_params(struct ieee80211_local *local, ieee80211_mps_sta_status_update(sta); changed |= ieee80211_mps_set_sta_local_pm(sta, sdata->u.mesh.mshcfg.power_mode); + + ewma_mesh_tx_rate_avg_init(&sta->mesh->tx_rate_avg); + /* init at low value */ + ewma_mesh_tx_rate_avg_add(&sta->mesh->tx_rate_avg, 10); + break; case NL80211_PLINK_LISTEN: case NL80211_PLINK_BLOCKED: @@ -1447,6 +1452,9 @@ static int sta_apply_parameters(struct ieee80211_local *local, if (ieee80211_vif_is_mesh(&sdata->vif)) sta_apply_mesh_params(local, sta, params); + if (params->airtime_weight) + sta->airtime_weight = params->airtime_weight; + /* set the STA state after all sta info from usermode has been set */ if (test_sta_flag(sta, WLAN_STA_TDLS_PEER) || set & BIT(NL80211_STA_FLAG_ASSOCIATED)) { @@ -1746,7 +1754,9 @@ static void mpath_set_pinfo(struct mesh_path *mpath, u8 *next_hop, MPATH_INFO_EXPTIME | MPATH_INFO_DISCOVERY_TIMEOUT | MPATH_INFO_DISCOVERY_RETRIES | - MPATH_INFO_FLAGS; + MPATH_INFO_FLAGS | + MPATH_INFO_HOP_COUNT | + MPATH_INFO_PATH_CHANGE; pinfo->frame_qlen = mpath->frame_queue.qlen; pinfo->sn = mpath->sn; @@ -1766,6 +1776,8 @@ static void mpath_set_pinfo(struct mesh_path *mpath, u8 *next_hop, pinfo->flags |= NL80211_MPATH_FLAG_FIXED; if (mpath->flags & MESH_PATH_RESOLVED) pinfo->flags |= NL80211_MPATH_FLAG_RESOLVED; + pinfo->hop_count = mpath->hop_count; + pinfo->path_change_count = mpath->path_change_count; } static int ieee80211_get_mpath(struct wiphy *wiphy, struct net_device *dev, diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 3fe541e358f3..343ad0a915e4 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -218,6 +218,7 @@ static const char *hw_flag_names[] = { FLAG(BUFF_MMPDU_TXQ), FLAG(SUPPORTS_VHT_EXT_NSS_BW), FLAG(STA_MMPDU_TXQ), + FLAG(TX_STATUS_NO_AMPDU_LEN), #undef FLAG }; @@ -383,6 +384,9 @@ void debugfs_hw_add(struct ieee80211_local *local) if (local->ops->wake_tx_queue) DEBUGFS_ADD_MODE(aqm, 0600); + debugfs_create_u16("airtime_flags", 0600, + phyd, &local->airtime_flags); + statsd = debugfs_create_dir("statistics", phyd); /* if the dir failed, don't put all the other things into the root! */ diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index b753194710ad..3aa618dcc58e 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -181,9 +181,9 @@ static ssize_t sta_aqm_read(struct file *file, char __user *userbuf, txqi->tin.tx_bytes, txqi->tin.tx_packets, txqi->flags, - txqi->flags & (1<<IEEE80211_TXQ_STOP) ? "STOP" : "RUN", - txqi->flags & (1<<IEEE80211_TXQ_AMPDU) ? " AMPDU" : "", - txqi->flags & (1<<IEEE80211_TXQ_NO_AMSDU) ? " NO-AMSDU" : ""); + test_bit(IEEE80211_TXQ_STOP, &txqi->flags) ? "STOP" : "RUN", + test_bit(IEEE80211_TXQ_AMPDU, &txqi->flags) ? " AMPDU" : "", + test_bit(IEEE80211_TXQ_NO_AMSDU, &txqi->flags) ? " NO-AMSDU" : ""); } rcu_read_unlock(); @@ -195,6 +195,64 @@ static ssize_t sta_aqm_read(struct file *file, char __user *userbuf, } STA_OPS(aqm); +static ssize_t sta_airtime_read(struct file *file, char __user *userbuf, + size_t count, loff_t *ppos) +{ + struct sta_info *sta = file->private_data; + struct ieee80211_local *local = sta->sdata->local; + size_t bufsz = 200; + char *buf = kzalloc(bufsz, GFP_KERNEL), *p = buf; + u64 rx_airtime = 0, tx_airtime = 0; + s64 deficit[IEEE80211_NUM_ACS]; + ssize_t rv; + int ac; + + if (!buf) + return -ENOMEM; + + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { + spin_lock_bh(&local->active_txq_lock[ac]); + rx_airtime += sta->airtime[ac].rx_airtime; + tx_airtime += sta->airtime[ac].tx_airtime; + deficit[ac] = sta->airtime[ac].deficit; + spin_unlock_bh(&local->active_txq_lock[ac]); + } + + p += scnprintf(p, bufsz + buf - p, + "RX: %llu us\nTX: %llu us\nWeight: %u\n" + "Deficit: VO: %lld us VI: %lld us BE: %lld us BK: %lld us\n", + rx_airtime, + tx_airtime, + sta->airtime_weight, + deficit[0], + deficit[1], + deficit[2], + deficit[3]); + + rv = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); + kfree(buf); + return rv; +} + +static ssize_t sta_airtime_write(struct file *file, const char __user *userbuf, + size_t count, loff_t *ppos) +{ + struct sta_info *sta = file->private_data; + struct ieee80211_local *local = sta->sdata->local; + int ac; + + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { + spin_lock_bh(&local->active_txq_lock[ac]); + sta->airtime[ac].rx_airtime = 0; + sta->airtime[ac].tx_airtime = 0; + sta->airtime[ac].deficit = sta->airtime_weight; + spin_unlock_bh(&local->active_txq_lock[ac]); + } + + return count; +} +STA_OPS_RW(airtime); + static ssize_t sta_agg_status_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { @@ -906,6 +964,10 @@ void ieee80211_sta_debugfs_add(struct sta_info *sta) if (local->ops->wake_tx_queue) DEBUGFS_ADD(aqm); + if (wiphy_ext_feature_isset(local->hw.wiphy, + NL80211_EXT_FEATURE_AIRTIME_FAIRNESS)) + DEBUGFS_ADD(airtime); + if (sizeof(sta->driver_buffered_tids) == sizeof(u32)) debugfs_create_x32("driver_buffered_tids", 0400, sta->debugfs_dir, diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 3e0d5922a440..ba3c07b10cd0 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -1173,6 +1173,13 @@ static inline void drv_wake_tx_queue(struct ieee80211_local *local, local->ops->wake_tx_queue(&local->hw, &txq->txq); } +static inline void schedule_and_wake_txq(struct ieee80211_local *local, + struct txq_info *txqi) +{ + ieee80211_schedule_txq(&local->hw, &txqi->txq); + drv_wake_tx_queue(local, txqi); +} + static inline int drv_can_aggregate_in_amsdu(struct ieee80211_local *local, struct sk_buff *head, struct sk_buff *skb) diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index f849ea814993..e03c46ac8e4d 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -107,6 +107,14 @@ void ieee80211_apply_htcap_overrides(struct ieee80211_sub_if_data *sdata, __check_htcap_enable(ht_capa, ht_capa_mask, ht_cap, IEEE80211_HT_CAP_40MHZ_INTOLERANT); + /* Allow user to enable TX STBC bit */ + __check_htcap_enable(ht_capa, ht_capa_mask, ht_cap, + IEEE80211_HT_CAP_TX_STBC); + + /* Allow user to configure RX STBC bits */ + if (ht_capa_mask->cap_info & IEEE80211_HT_CAP_RX_STBC) + ht_cap->cap |= ht_capa->cap_info & IEEE80211_HT_CAP_RX_STBC; + /* Allow user to decrease AMPDU factor */ if (ht_capa_mask->ampdu_params_info & IEEE80211_HT_AMPDU_PARM_FACTOR) { diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 7dfb4e2f98b2..056b16bce3b0 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -831,6 +831,8 @@ enum txq_info_flags { * a fq_flow which is already owned by a different tin * @def_cvars: codel vars for @def_flow * @frags: used to keep fragments created after dequeue + * @schedule_order: used with ieee80211_local->active_txqs + * @schedule_round: counter to prevent infinite loops on TXQ scheduling */ struct txq_info { struct fq_tin tin; @@ -838,6 +840,8 @@ struct txq_info { struct codel_vars def_cvars; struct codel_stats cstats; struct sk_buff_head frags; + struct list_head schedule_order; + u16 schedule_round; unsigned long flags; /* keep last! */ @@ -1129,6 +1133,13 @@ struct ieee80211_local { struct codel_vars *cvars; struct codel_params cparams; + /* protects active_txqs and txqi->schedule_order */ + spinlock_t active_txq_lock[IEEE80211_NUM_ACS]; + struct list_head active_txqs[IEEE80211_NUM_ACS]; + u16 schedule_round[IEEE80211_NUM_ACS]; + + u16 airtime_flags; + const struct ieee80211_ops *ops; /* diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 87a729926734..71005b6dfcd1 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -478,6 +478,8 @@ static const struct ieee80211_ht_cap mac80211_ht_capa_mod_mask = { IEEE80211_HT_CAP_MAX_AMSDU | IEEE80211_HT_CAP_SGI_20 | IEEE80211_HT_CAP_SGI_40 | + IEEE80211_HT_CAP_TX_STBC | + IEEE80211_HT_CAP_RX_STBC | IEEE80211_HT_CAP_LDPC_CODING | IEEE80211_HT_CAP_40MHZ_INTOLERANT), .mcs = { @@ -663,6 +665,12 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, spin_lock_init(&local->rx_path_lock); spin_lock_init(&local->queue_stop_reason_lock); + for (i = 0; i < IEEE80211_NUM_ACS; i++) { + INIT_LIST_HEAD(&local->active_txqs[i]); + spin_lock_init(&local->active_txq_lock[i]); + } + local->airtime_flags = AIRTIME_USE_TX | AIRTIME_USE_RX; + INIT_LIST_HEAD(&local->chanctx_list); mutex_init(&local->chanctx_mtx); @@ -1148,6 +1156,9 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) if (!local->hw.max_nan_de_entries) local->hw.max_nan_de_entries = IEEE80211_MAX_NAN_INSTANCE_ID; + if (!local->hw.weight_multiplier) + local->hw.weight_multiplier = 1; + result = ieee80211_wep_init(local); if (result < 0) wiphy_debug(local->hw.wiphy, "Failed to initialize wep: %d\n", diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index cad6592c52a1..8b26858ab4d5 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -94,6 +94,7 @@ enum mesh_deferred_task_flags { * @last_preq_to_root: Timestamp of last PREQ sent to root * @is_root: the destination station of this path is a root node * @is_gate: the destination station of this path is a mesh gate + * @path_change_count: the number of path changes to destination * * * The dst address is unique in the mesh path table. Since the mesh_path is @@ -124,6 +125,7 @@ struct mesh_path { unsigned long last_preq_to_root; bool is_root; bool is_gate; + u32 path_change_count; }; /** diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 6950cd0bf594..e00284afdda5 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -300,6 +300,7 @@ void ieee80211s_update_metric(struct ieee80211_local *local, { struct ieee80211_tx_info *txinfo = st->info; int failed; + struct rate_info rinfo; failed = !(txinfo->flags & IEEE80211_TX_STAT_ACK); @@ -310,12 +311,15 @@ void ieee80211s_update_metric(struct ieee80211_local *local, if (ewma_mesh_fail_avg_read(&sta->mesh->fail_avg) > LINK_FAIL_THRESH) mesh_plink_broken(sta); + + sta_set_rate_info_tx(sta, &sta->tx_stats.last_rate, &rinfo); + ewma_mesh_tx_rate_avg_add(&sta->mesh->tx_rate_avg, + cfg80211_calculate_bitrate(&rinfo)); } static u32 airtime_link_metric_get(struct ieee80211_local *local, struct sta_info *sta) { - struct rate_info rinfo; /* This should be adjusted for each device */ int device_constant = 1 << ARITH_SHIFT; int test_frame_len = TEST_FRAME_LEN << ARITH_SHIFT; @@ -339,8 +343,7 @@ static u32 airtime_link_metric_get(struct ieee80211_local *local, if (fail_avg > LINK_FAIL_THRESH) return MAX_METRIC; - sta_set_rate_info_tx(sta, &sta->tx_stats.last_rate, &rinfo); - rate = cfg80211_calculate_bitrate(&rinfo); + rate = ewma_mesh_tx_rate_avg_read(&sta->mesh->tx_rate_avg); if (WARN_ON(!rate)) return MAX_METRIC; @@ -386,6 +389,7 @@ static u32 hwmp_route_info_get(struct ieee80211_sub_if_data *sdata, unsigned long orig_lifetime, exp_time; u32 last_hop_metric, new_metric; bool process = true; + u8 hopcount; rcu_read_lock(); sta = sta_info_get(sdata, mgmt->sa); @@ -404,6 +408,7 @@ static u32 hwmp_route_info_get(struct ieee80211_sub_if_data *sdata, orig_sn = PREQ_IE_ORIG_SN(hwmp_ie); orig_lifetime = PREQ_IE_LIFETIME(hwmp_ie); orig_metric = PREQ_IE_METRIC(hwmp_ie); + hopcount = PREQ_IE_HOPCOUNT(hwmp_ie) + 1; break; case MPATH_PREP: /* Originator here refers to the MP that was the target in the @@ -415,6 +420,7 @@ static u32 hwmp_route_info_get(struct ieee80211_sub_if_data *sdata, orig_sn = PREP_IE_TARGET_SN(hwmp_ie); orig_lifetime = PREP_IE_LIFETIME(hwmp_ie); orig_metric = PREP_IE_METRIC(hwmp_ie); + hopcount = PREP_IE_HOPCOUNT(hwmp_ie) + 1; break; default: rcu_read_unlock(); @@ -441,7 +447,10 @@ static u32 hwmp_route_info_get(struct ieee80211_sub_if_data *sdata, (mpath->flags & MESH_PATH_SN_VALID)) { if (SN_GT(mpath->sn, orig_sn) || (mpath->sn == orig_sn && - new_metric >= mpath->metric)) { + (rcu_access_pointer(mpath->next_hop) != + sta ? + mult_frac(new_metric, 10, 9) : + new_metric) >= mpath->metric)) { process = false; fresh_info = false; } @@ -476,12 +485,15 @@ static u32 hwmp_route_info_get(struct ieee80211_sub_if_data *sdata, } if (fresh_info) { + if (rcu_access_pointer(mpath->next_hop) != sta) + mpath->path_change_count++; mesh_path_assign_nexthop(mpath, sta); mpath->flags |= MESH_PATH_SN_VALID; mpath->metric = new_metric; mpath->sn = orig_sn; mpath->exp_time = time_after(mpath->exp_time, exp_time) ? mpath->exp_time : exp_time; + mpath->hop_count = hopcount; mesh_path_activate(mpath); spin_unlock_bh(&mpath->state_lock); ewma_mesh_fail_avg_init(&sta->mesh->fail_avg); @@ -506,8 +518,10 @@ static u32 hwmp_route_info_get(struct ieee80211_sub_if_data *sdata, if (mpath) { spin_lock_bh(&mpath->state_lock); if ((mpath->flags & MESH_PATH_FIXED) || - ((mpath->flags & MESH_PATH_ACTIVE) && - (last_hop_metric > mpath->metric))) + ((mpath->flags & MESH_PATH_ACTIVE) && + ((rcu_access_pointer(mpath->next_hop) != sta ? + mult_frac(last_hop_metric, 10, 9) : + last_hop_metric) > mpath->metric))) fresh_info = false; } else { mpath = mesh_path_add(sdata, ta); @@ -519,10 +533,13 @@ static u32 hwmp_route_info_get(struct ieee80211_sub_if_data *sdata, } if (fresh_info) { + if (rcu_access_pointer(mpath->next_hop) != sta) + mpath->path_change_count++; mesh_path_assign_nexthop(mpath, sta); mpath->metric = last_hop_metric; mpath->exp_time = time_after(mpath->exp_time, exp_time) ? mpath->exp_time : exp_time; + mpath->hop_count = 1; mesh_path_activate(mpath); spin_unlock_bh(&mpath->state_lock); ewma_mesh_fail_avg_init(&sta->mesh->fail_avg); diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index f466ec37d161..ccaf951e4e31 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -294,6 +294,15 @@ minstrel_get_ratestats(struct minstrel_ht_sta *mi, int index) return &mi->groups[index / MCS_GROUP_RATES].rates[index % MCS_GROUP_RATES]; } +static unsigned int +minstrel_ht_avg_ampdu_len(struct minstrel_ht_sta *mi) +{ + if (!mi->avg_ampdu_len) + return AVG_AMPDU_SIZE; + + return MINSTREL_TRUNC(mi->avg_ampdu_len); +} + /* * Return current throughput based on the average A-MPDU length, taking into * account the expected number of retransmissions and their expected length @@ -309,7 +318,7 @@ minstrel_ht_get_tp_avg(struct minstrel_ht_sta *mi, int group, int rate, return 0; if (group != MINSTREL_CCK_GROUP) - nsecs = 1000 * mi->overhead / MINSTREL_TRUNC(mi->avg_ampdu_len); + nsecs = 1000 * mi->overhead / minstrel_ht_avg_ampdu_len(mi); nsecs += minstrel_mcs_groups[group].duration[rate] << minstrel_mcs_groups[group].shift; @@ -503,8 +512,12 @@ minstrel_ht_update_stats(struct minstrel_priv *mp, struct minstrel_ht_sta *mi) u16 tmp_cck_tp_rate[MAX_THR_RATES], index; if (mi->ampdu_packets > 0) { - mi->avg_ampdu_len = minstrel_ewma(mi->avg_ampdu_len, - MINSTREL_FRAC(mi->ampdu_len, mi->ampdu_packets), EWMA_LEVEL); + if (!ieee80211_hw_check(mp->hw, TX_STATUS_NO_AMPDU_LEN)) + mi->avg_ampdu_len = minstrel_ewma(mi->avg_ampdu_len, + MINSTREL_FRAC(mi->ampdu_len, mi->ampdu_packets), + EWMA_LEVEL); + else + mi->avg_ampdu_len = 0; mi->ampdu_len = 0; mi->ampdu_packets = 0; } @@ -709,7 +722,9 @@ minstrel_ht_tx_status(void *priv, struct ieee80211_supported_band *sband, mi->ampdu_len += info->status.ampdu_len; if (!mi->sample_wait && !mi->sample_tries && mi->sample_count > 0) { - mi->sample_wait = 16 + 2 * MINSTREL_TRUNC(mi->avg_ampdu_len); + int avg_ampdu_len = minstrel_ht_avg_ampdu_len(mi); + + mi->sample_wait = 16 + 2 * avg_ampdu_len; mi->sample_tries = 1; mi->sample_count--; } @@ -777,7 +792,7 @@ minstrel_calc_retransmit(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, unsigned int cw = mp->cw_min; unsigned int ctime = 0; unsigned int t_slot = 9; /* FIXME */ - unsigned int ampdu_len = MINSTREL_TRUNC(mi->avg_ampdu_len); + unsigned int ampdu_len = minstrel_ht_avg_ampdu_len(mi); unsigned int overhead = 0, overhead_rtscts = 0; mrs = minstrel_get_ratestats(mi, index); diff --git a/net/mac80211/rc80211_minstrel_ht_debugfs.c b/net/mac80211/rc80211_minstrel_ht_debugfs.c index 57820a5f2c16..31641d0b0f5c 100644 --- a/net/mac80211/rc80211_minstrel_ht_debugfs.c +++ b/net/mac80211/rc80211_minstrel_ht_debugfs.c @@ -160,9 +160,10 @@ minstrel_ht_stats_open(struct inode *inode, struct file *file) "lookaround %d\n", max(0, (int) mi->total_packets - (int) mi->sample_packets), mi->sample_packets); - p += sprintf(p, "Average # of aggregated frames per A-MPDU: %d.%d\n", - MINSTREL_TRUNC(mi->avg_ampdu_len), - MINSTREL_TRUNC(mi->avg_ampdu_len * 10) % 10); + if (mi->avg_ampdu_len) + p += sprintf(p, "Average # of aggregated frames per A-MPDU: %d.%d\n", + MINSTREL_TRUNC(mi->avg_ampdu_len), + MINSTREL_TRUNC(mi->avg_ampdu_len * 10) % 10); ms->len = p - ms->buf; WARN_ON(ms->len + sizeof(*ms) > 32768); diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index c4a8f115ed33..11f058987a54 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -90,7 +90,6 @@ static void __cleanup_single_sta(struct sta_info *sta) struct tid_ampdu_tx *tid_tx; struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; - struct fq *fq = &local->fq; struct ps_data *ps; if (test_sta_flag(sta, WLAN_STA_PS_STA) || @@ -120,9 +119,7 @@ static void __cleanup_single_sta(struct sta_info *sta) txqi = to_txq_info(sta->sta.txq[i]); - spin_lock_bh(&fq->lock); ieee80211_txq_purge(local, txqi); - spin_unlock_bh(&fq->lock); } } @@ -387,9 +384,12 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, if (sta_prepare_rate_control(local, sta, gfp)) goto free_txq; + sta->airtime_weight = IEEE80211_DEFAULT_AIRTIME_WEIGHT; + for (i = 0; i < IEEE80211_NUM_ACS; i++) { skb_queue_head_init(&sta->ps_tx_buf[i]); skb_queue_head_init(&sta->tx_filtered[i]); + sta->airtime[i].deficit = sta->airtime_weight; } for (i = 0; i < IEEE80211_NUM_TIDS; i++) @@ -1249,7 +1249,7 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) if (!sta->sta.txq[i] || !txq_has_queue(sta->sta.txq[i])) continue; - drv_wake_tx_queue(local, to_txq_info(sta->sta.txq[i])); + schedule_and_wake_txq(local, to_txq_info(sta->sta.txq[i])); } skb_queue_head_init(&pending); @@ -1826,6 +1826,27 @@ void ieee80211_sta_set_buffered(struct ieee80211_sta *pubsta, } EXPORT_SYMBOL(ieee80211_sta_set_buffered); +void ieee80211_sta_register_airtime(struct ieee80211_sta *pubsta, u8 tid, + u32 tx_airtime, u32 rx_airtime) +{ + struct sta_info *sta = container_of(pubsta, struct sta_info, sta); + struct ieee80211_local *local = sta->sdata->local; + u8 ac = ieee80211_ac_from_tid(tid); + u32 airtime = 0; + + if (sta->local->airtime_flags & AIRTIME_USE_TX) + airtime += tx_airtime; + if (sta->local->airtime_flags & AIRTIME_USE_RX) + airtime += rx_airtime; + + spin_lock_bh(&local->active_txq_lock[ac]); + sta->airtime[ac].tx_airtime += tx_airtime; + sta->airtime[ac].rx_airtime += rx_airtime; + sta->airtime[ac].deficit -= airtime; + spin_unlock_bh(&local->active_txq_lock[ac]); +} +EXPORT_SYMBOL(ieee80211_sta_register_airtime); + int sta_info_move_state(struct sta_info *sta, enum ieee80211_sta_state new_state) { @@ -2188,6 +2209,23 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo, sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_FAILED); } + if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_RX_DURATION))) { + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) + sinfo->rx_duration += sta->airtime[ac].rx_airtime; + sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_DURATION); + } + + if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_TX_DURATION))) { + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) + sinfo->tx_duration += sta->airtime[ac].tx_airtime; + sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_DURATION); + } + + if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_AIRTIME_WEIGHT))) { + sinfo->airtime_weight = sta->airtime_weight; + sinfo->filled |= BIT_ULL(NL80211_STA_INFO_AIRTIME_WEIGHT); + } + sinfo->rx_dropped_misc = sta->rx_stats.dropped; if (sta->pcpu_rx_stats) { for_each_possible_cpu(cpu) { diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 8eb29041be54..71f7e4973329 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -127,6 +127,16 @@ enum ieee80211_agg_stop_reason { AGG_STOP_DESTROY_STA, }; +/* Debugfs flags to enable/disable use of RX/TX airtime in scheduler */ +#define AIRTIME_USE_TX BIT(0) +#define AIRTIME_USE_RX BIT(1) + +struct airtime_info { + u64 rx_airtime; + u64 tx_airtime; + s64 deficit; +}; + struct sta_info; /** @@ -343,6 +353,7 @@ struct ieee80211_fast_rx { /* we use only values in the range 0-100, so pick a large precision */ DECLARE_EWMA(mesh_fail_avg, 20, 8) +DECLARE_EWMA(mesh_tx_rate_avg, 8, 16) /** * struct mesh_sta - mesh STA information @@ -366,6 +377,7 @@ DECLARE_EWMA(mesh_fail_avg, 20, 8) * processed * @connected_to_gate: true if mesh STA has a path to a mesh gate * @fail_avg: moving percentage of failed MSDUs + * @tx_rate_avg: moving average of tx bitrate */ struct mesh_sta { struct timer_list plink_timer; @@ -394,6 +406,8 @@ struct mesh_sta { /* moving percentage of failed MSDUs */ struct ewma_mesh_fail_avg fail_avg; + /* moving average of tx bitrate */ + struct ewma_mesh_tx_rate_avg tx_rate_avg; }; DECLARE_EWMA(signal, 10, 8) @@ -459,6 +473,9 @@ struct ieee80211_sta_rx_stats { * @last_seq_ctrl: last received seq/frag number from this STA (per TID * plus one for non-QoS frames) * @tid_seq: per-TID sequence numbers for sending to this STA + * @airtime: per-AC struct airtime_info describing airtime statistics for this + * station + * @airtime_weight: station weight for airtime fairness calculation purposes * @ampdu_mlme: A-MPDU state machine state * @mesh: mesh STA information * @debugfs_dir: debug filesystem directory dentry @@ -480,10 +497,28 @@ struct ieee80211_sta_rx_stats { * @tdls_chandef: a TDLS peer can have a wider chandef that is compatible to * the BSS one. * @tx_stats: TX statistics + * @tx_stats.packets: # of packets transmitted + * @tx_stats.bytes: # of bytes in all packets transmitted + * @tx_stats.last_rate: last TX rate + * @tx_stats.msdu: # of transmitted MSDUs per TID * @rx_stats: RX statistics + * @rx_stats_avg: averaged RX statistics + * @rx_stats_avg.signal: averaged signal + * @rx_stats_avg.chain_signal: averaged per-chain signal * @pcpu_rx_stats: per-CPU RX statistics, assigned only if the driver needs * this (by advertising the USES_RSS hw flag) * @status_stats: TX status statistics + * @status_stats.filtered: # of filtered frames + * @status_stats.retry_failed: # of frames that failed after retry + * @status_stats.retry_count: # of retries attempted + * @status_stats.lost_packets: # of lost packets + * @status_stats.last_tdls_pkt_time: timestamp of last TDLS packet + * @status_stats.msdu_retries: # of MSDU retries + * @status_stats.msdu_failed: # of failed MSDUs + * @status_stats.last_ack: last ack timestamp (jiffies) + * @status_stats.last_ack_signal: last ACK signal + * @status_stats.ack_signal_filled: last ACK signal validity + * @status_stats.avg_ack_signal: average ACK signal */ struct sta_info { /* General information, mostly static */ @@ -565,6 +600,9 @@ struct sta_info { } tx_stats; u16 tid_seq[IEEE80211_QOS_CTL_TID_MASK + 1]; + struct airtime_info airtime[IEEE80211_NUM_ACS]; + u16 airtime_weight; + /* * Aggregation information, locked with lock. */ diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 3f0b96e1e02f..5b9952b1caf3 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -823,6 +823,12 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, ieee80211_sta_tx_notify(sta->sdata, (void *) skb->data, acked, info->status.tx_time); + if (info->status.tx_time && + wiphy_ext_feature_isset(local->hw.wiphy, + NL80211_EXT_FEATURE_AIRTIME_FAIRNESS)) + ieee80211_sta_register_airtime(&sta->sta, tid, + info->status.tx_time, 0); + if (ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)) { if (info->flags & IEEE80211_TX_STAT_ACK) { if (sta->status_stats.lost_packets) diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index f170d6c6629a..8a49a74c0a37 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1449,6 +1449,7 @@ void ieee80211_txq_init(struct ieee80211_sub_if_data *sdata, codel_vars_init(&txqi->def_cvars); codel_stats_init(&txqi->cstats); __skb_queue_head_init(&txqi->frags); + INIT_LIST_HEAD(&txqi->schedule_order); txqi->txq.vif = &sdata->vif; @@ -1487,8 +1488,14 @@ void ieee80211_txq_purge(struct ieee80211_local *local, struct fq *fq = &local->fq; struct fq_tin *tin = &txqi->tin; + spin_lock_bh(&fq->lock); fq_tin_reset(fq, tin, fq_skb_free_func); ieee80211_purge_tx_queue(&local->hw, &txqi->frags); + spin_unlock_bh(&fq->lock); + + spin_lock_bh(&local->active_txq_lock[txqi->txq.ac]); + list_del_init(&txqi->schedule_order); + spin_unlock_bh(&local->active_txq_lock[txqi->txq.ac]); } void ieee80211_txq_set_params(struct ieee80211_local *local) @@ -1605,7 +1612,7 @@ static bool ieee80211_queue_skb(struct ieee80211_local *local, ieee80211_txq_enqueue(local, txqi, skb); spin_unlock_bh(&fq->lock); - drv_wake_tx_queue(local, txqi); + schedule_and_wake_txq(local, txqi); return true; } @@ -1938,9 +1945,16 @@ static int ieee80211_skb_resize(struct ieee80211_sub_if_data *sdata, int head_need, bool may_encrypt) { struct ieee80211_local *local = sdata->local; + struct ieee80211_hdr *hdr; + bool enc_tailroom; int tail_need = 0; - if (may_encrypt && sdata->crypto_tx_tailroom_needed_cnt) { + hdr = (struct ieee80211_hdr *) skb->data; + enc_tailroom = may_encrypt && + (sdata->crypto_tx_tailroom_needed_cnt || + ieee80211_is_mgmt(hdr->frame_control)); + + if (enc_tailroom) { tail_need = IEEE80211_ENCRYPT_TAILROOM; tail_need -= skb_tailroom(skb); tail_need = max_t(int, tail_need, 0); @@ -1948,8 +1962,7 @@ static int ieee80211_skb_resize(struct ieee80211_sub_if_data *sdata, if (skb_cloned(skb) && (!ieee80211_hw_check(&local->hw, SUPPORTS_CLONED_SKBS) || - !skb_clone_writable(skb, ETH_HLEN) || - (may_encrypt && sdata->crypto_tx_tailroom_needed_cnt))) + !skb_clone_writable(skb, ETH_HLEN) || enc_tailroom)) I802_DEBUG_INC(local->tx_expand_skb_head_cloned); else if (head_need || tail_need) I802_DEBUG_INC(local->tx_expand_skb_head); @@ -3630,6 +3643,151 @@ out: } EXPORT_SYMBOL(ieee80211_tx_dequeue); +struct ieee80211_txq *ieee80211_next_txq(struct ieee80211_hw *hw, u8 ac) +{ + struct ieee80211_local *local = hw_to_local(hw); + struct txq_info *txqi = NULL; + + lockdep_assert_held(&local->active_txq_lock[ac]); + + begin: + txqi = list_first_entry_or_null(&local->active_txqs[ac], + struct txq_info, + schedule_order); + if (!txqi) + return NULL; + + if (txqi->txq.sta) { + struct sta_info *sta = container_of(txqi->txq.sta, + struct sta_info, sta); + + if (sta->airtime[txqi->txq.ac].deficit < 0) { + sta->airtime[txqi->txq.ac].deficit += + sta->airtime_weight; + list_move_tail(&txqi->schedule_order, + &local->active_txqs[txqi->txq.ac]); + goto begin; + } + } + + + if (txqi->schedule_round == local->schedule_round[ac]) + return NULL; + + list_del_init(&txqi->schedule_order); + txqi->schedule_round = local->schedule_round[ac]; + return &txqi->txq; +} +EXPORT_SYMBOL(ieee80211_next_txq); + +void ieee80211_return_txq(struct ieee80211_hw *hw, + struct ieee80211_txq *txq) +{ + struct ieee80211_local *local = hw_to_local(hw); + struct txq_info *txqi = to_txq_info(txq); + + lockdep_assert_held(&local->active_txq_lock[txq->ac]); + + if (list_empty(&txqi->schedule_order) && + (!skb_queue_empty(&txqi->frags) || txqi->tin.backlog_packets)) { + /* If airtime accounting is active, always enqueue STAs at the + * head of the list to ensure that they only get moved to the + * back by the airtime DRR scheduler once they have a negative + * deficit. A station that already has a negative deficit will + * get immediately moved to the back of the list on the next + * call to ieee80211_next_txq(). + */ + if (txqi->txq.sta && + wiphy_ext_feature_isset(local->hw.wiphy, + NL80211_EXT_FEATURE_AIRTIME_FAIRNESS)) + list_add(&txqi->schedule_order, + &local->active_txqs[txq->ac]); + else + list_add_tail(&txqi->schedule_order, + &local->active_txqs[txq->ac]); + } +} +EXPORT_SYMBOL(ieee80211_return_txq); + +void ieee80211_schedule_txq(struct ieee80211_hw *hw, + struct ieee80211_txq *txq) + __acquires(txq_lock) __releases(txq_lock) +{ + struct ieee80211_local *local = hw_to_local(hw); + + spin_lock_bh(&local->active_txq_lock[txq->ac]); + ieee80211_return_txq(hw, txq); + spin_unlock_bh(&local->active_txq_lock[txq->ac]); +} +EXPORT_SYMBOL(ieee80211_schedule_txq); + +bool ieee80211_txq_may_transmit(struct ieee80211_hw *hw, + struct ieee80211_txq *txq) +{ + struct ieee80211_local *local = hw_to_local(hw); + struct txq_info *iter, *tmp, *txqi = to_txq_info(txq); + struct sta_info *sta; + u8 ac = txq->ac; + + lockdep_assert_held(&local->active_txq_lock[ac]); + + if (!txqi->txq.sta) + goto out; + + if (list_empty(&txqi->schedule_order)) + goto out; + + list_for_each_entry_safe(iter, tmp, &local->active_txqs[ac], + schedule_order) { + if (iter == txqi) + break; + + if (!iter->txq.sta) { + list_move_tail(&iter->schedule_order, + &local->active_txqs[ac]); + continue; + } + sta = container_of(iter->txq.sta, struct sta_info, sta); + if (sta->airtime[ac].deficit < 0) + sta->airtime[ac].deficit += sta->airtime_weight; + list_move_tail(&iter->schedule_order, &local->active_txqs[ac]); + } + + sta = container_of(txqi->txq.sta, struct sta_info, sta); + if (sta->airtime[ac].deficit >= 0) + goto out; + + sta->airtime[ac].deficit += sta->airtime_weight; + list_move_tail(&txqi->schedule_order, &local->active_txqs[ac]); + + return false; +out: + if (!list_empty(&txqi->schedule_order)) + list_del_init(&txqi->schedule_order); + + return true; +} +EXPORT_SYMBOL(ieee80211_txq_may_transmit); + +void ieee80211_txq_schedule_start(struct ieee80211_hw *hw, u8 ac) + __acquires(txq_lock) +{ + struct ieee80211_local *local = hw_to_local(hw); + + spin_lock_bh(&local->active_txq_lock[ac]); + local->schedule_round[ac]++; +} +EXPORT_SYMBOL(ieee80211_txq_schedule_start); + +void ieee80211_txq_schedule_end(struct ieee80211_hw *hw, u8 ac) + __releases(txq_lock) +{ + struct ieee80211_local *local = hw_to_local(hw); + + spin_unlock_bh(&local->active_txq_lock[ac]); +} +EXPORT_SYMBOL(ieee80211_txq_schedule_end); + void __ieee80211_subif_start_xmit(struct sk_buff *skb, struct net_device *dev, u32 info_flags) diff --git a/net/mac80211/util.c b/net/mac80211/util.c index d0eb38b890aa..ba950ae974fc 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -5,7 +5,7 @@ * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018 Intel Corporation + * Copyright (C) 2018-2019 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -2146,6 +2146,10 @@ int ieee80211_reconfig(struct ieee80211_local *local) case NL80211_IFTYPE_AP_VLAN: case NL80211_IFTYPE_MONITOR: break; + case NL80211_IFTYPE_ADHOC: + if (sdata->vif.bss_conf.ibss_joined) + WARN_ON(drv_join_ibss(local, sdata)); + /* fall through */ default: ieee80211_reconfig_stations(sdata); /* fall through */ diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c index 94f53a9b7d1a..dda8930f20e7 100644 --- a/net/mpls/mpls_iptunnel.c +++ b/net/mpls/mpls_iptunnel.c @@ -183,8 +183,8 @@ static int mpls_build_state(struct nlattr *nla, &n_labels, NULL, extack)) return -EINVAL; - newts = lwtunnel_state_alloc(sizeof(*tun_encap_info) + - n_labels * sizeof(u32)); + newts = lwtunnel_state_alloc(struct_size(tun_encap_info, label, + n_labels)); if (!newts) return -ENOMEM; diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig index cad48d07c818..8401cefd9f65 100644 --- a/net/netfilter/ipvs/Kconfig +++ b/net/netfilter/ipvs/Kconfig @@ -29,6 +29,7 @@ config IP_VS_IPV6 bool "IPv6 support for IPVS" depends on IPV6 = y || IP_VS = IPV6 select IP6_NF_IPTABLES + select NF_DEFRAG_IPV6 ---help--- Add IPv6 support to IPVS. diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index e969dad66991..43bbaa32b1d6 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1566,14 +1566,12 @@ ip_vs_try_to_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, /* sorry, all this trouble for a no-hit :) */ IP_VS_DBG_PKT(12, af, pp, skb, iph->off, "ip_vs_in: packet continues traversal as normal"); - if (iph->fragoffs) { - /* Fragment that couldn't be mapped to a conn entry - * is missing module nf_defrag_ipv6 - */ - IP_VS_DBG_RL("Unhandled frag, load nf_defrag_ipv6\n"); + + /* Fragment couldn't be mapped to a conn entry */ + if (iph->fragoffs) IP_VS_DBG_PKT(7, af, pp, skb, iph->off, "unhandled fragment"); - } + *verdict = NF_ACCEPT; return 0; } diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 446beeb5e7b2..3c36480559f9 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -43,6 +43,7 @@ #ifdef CONFIG_IP_VS_IPV6 #include <net/ipv6.h> #include <net/ip6_route.h> +#include <net/netfilter/ipv6/nf_defrag_ipv6.h> #endif #include <net/route.h> #include <net/sock.h> @@ -895,6 +896,7 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest, { struct ip_vs_dest *dest; unsigned int atype, i; + int ret = 0; EnterFunction(2); @@ -905,6 +907,10 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest, atype & IPV6_ADDR_LINKLOCAL) && !__ip_vs_addr_is_local_v6(svc->ipvs->net, &udest->addr.in6)) return -EINVAL; + + ret = nf_defrag_ipv6_enable(svc->ipvs->net); + if (ret) + return ret; } else #endif { @@ -1228,6 +1234,10 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u, ret = -EINVAL; goto out_err; } + + ret = nf_defrag_ipv6_enable(ipvs->net); + if (ret) + goto out_err; } #endif @@ -2221,6 +2231,18 @@ static int ip_vs_set_timeout(struct netns_ipvs *ipvs, struct ip_vs_timeout_user u->udp_timeout); #ifdef CONFIG_IP_VS_PROTO_TCP + if (u->tcp_timeout < 0 || u->tcp_timeout > (INT_MAX / HZ) || + u->tcp_fin_timeout < 0 || u->tcp_fin_timeout > (INT_MAX / HZ)) { + return -EINVAL; + } +#endif + +#ifdef CONFIG_IP_VS_PROTO_UDP + if (u->udp_timeout < 0 || u->udp_timeout > (INT_MAX / HZ)) + return -EINVAL; +#endif + +#ifdef CONFIG_IP_VS_PROTO_TCP if (u->tcp_timeout) { pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP); pd->timeout_table[IP_VS_TCP_S_ESTABLISHED] diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 85de2a7b0ede..e139c256e269 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1050,6 +1050,22 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple, } if (nf_ct_key_equal(h, tuple, zone, net)) { + /* Tuple is taken already, so caller will need to find + * a new source port to use. + * + * Only exception: + * If the *original tuples* are identical, then both + * conntracks refer to the same flow. + * This is a rare situation, it can occur e.g. when + * more than one UDP packet is sent from same socket + * in different threads. + * + * Let nf_ct_resolve_clash() deal with this later. + */ + if (nf_ct_tuple_equal(&ignored_conntrack->tuplehash[IP_CT_DIR_ORIGINAL].tuple, + &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple)) + continue; + NF_CT_STAT_INC_ATOMIC(net, found); rcu_read_unlock(); return 1; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 7495f29d24e8..de3f1e2acae0 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -131,6 +131,23 @@ static void nft_trans_destroy(struct nft_trans *trans) kfree(trans); } +static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set) +{ + struct net *net = ctx->net; + struct nft_trans *trans; + + if (!nft_set_is_anonymous(set)) + return; + + list_for_each_entry_reverse(trans, &net->nft.commit_list, list) { + if (trans->msg_type == NFT_MSG_NEWSET && + nft_trans_set(trans) == set) { + nft_trans_set_bound(trans) = true; + break; + } + } +} + static int nf_tables_register_hook(struct net *net, const struct nft_table *table, struct nft_chain *chain) @@ -226,18 +243,6 @@ static int nft_delchain(struct nft_ctx *ctx) return err; } -/* either expr ops provide both activate/deactivate, or neither */ -static bool nft_expr_check_ops(const struct nft_expr_ops *ops) -{ - if (!ops) - return true; - - if (WARN_ON_ONCE((!ops->activate ^ !ops->deactivate))) - return false; - - return true; -} - static void nft_rule_expr_activate(const struct nft_ctx *ctx, struct nft_rule *rule) { @@ -253,14 +258,15 @@ static void nft_rule_expr_activate(const struct nft_ctx *ctx, } static void nft_rule_expr_deactivate(const struct nft_ctx *ctx, - struct nft_rule *rule) + struct nft_rule *rule, + enum nft_trans_phase phase) { struct nft_expr *expr; expr = nft_expr_first(rule); while (expr != nft_expr_last(rule) && expr->ops) { if (expr->ops->deactivate) - expr->ops->deactivate(ctx, expr); + expr->ops->deactivate(ctx, expr, phase); expr = nft_expr_next(expr); } @@ -311,7 +317,7 @@ static int nft_delrule(struct nft_ctx *ctx, struct nft_rule *rule) nft_trans_destroy(trans); return err; } - nft_rule_expr_deactivate(ctx, rule); + nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_PREPARE); return 0; } @@ -1972,9 +1978,6 @@ static int nf_tables_delchain(struct net *net, struct sock *nlsk, */ int nft_register_expr(struct nft_expr_type *type) { - if (!nft_expr_check_ops(type->ops)) - return -EINVAL; - nfnl_lock(NFNL_SUBSYS_NFTABLES); if (type->family == NFPROTO_UNSPEC) list_add_tail_rcu(&type->list, &nf_tables_expressions); @@ -2122,10 +2125,6 @@ static int nf_tables_expr_parse(const struct nft_ctx *ctx, err = PTR_ERR(ops); goto err1; } - if (!nft_expr_check_ops(ops)) { - err = -EINVAL; - goto err1; - } } else ops = type->ops; @@ -2555,7 +2554,7 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx, static void nf_tables_rule_release(const struct nft_ctx *ctx, struct nft_rule *rule) { - nft_rule_expr_deactivate(ctx, rule); + nft_rule_expr_deactivate(ctx, rule, NFT_TRANS_RELEASE); nf_tables_rule_destroy(ctx, rule); } @@ -3761,39 +3760,30 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, bind: binding->chain = ctx->chain; list_add_tail_rcu(&binding->list, &set->bindings); + nft_set_trans_bind(ctx, set); + return 0; } EXPORT_SYMBOL_GPL(nf_tables_bind_set); -void nf_tables_rebind_set(const struct nft_ctx *ctx, struct nft_set *set, - struct nft_set_binding *binding) -{ - if (list_empty(&set->bindings) && nft_set_is_anonymous(set) && - nft_is_active(ctx->net, set)) - list_add_tail_rcu(&set->list, &ctx->table->sets); - - list_add_tail_rcu(&binding->list, &set->bindings); -} -EXPORT_SYMBOL_GPL(nf_tables_rebind_set); - void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, - struct nft_set_binding *binding) + struct nft_set_binding *binding, bool event) { list_del_rcu(&binding->list); - if (list_empty(&set->bindings) && nft_set_is_anonymous(set) && - nft_is_active(ctx->net, set)) + if (list_empty(&set->bindings) && nft_set_is_anonymous(set)) { list_del_rcu(&set->list); + if (event) + nf_tables_set_notify(ctx, set, NFT_MSG_DELSET, + GFP_KERNEL); + } } EXPORT_SYMBOL_GPL(nf_tables_unbind_set); void nf_tables_destroy_set(const struct nft_ctx *ctx, struct nft_set *set) { - if (list_empty(&set->bindings) && nft_set_is_anonymous(set) && - nft_is_active(ctx->net, set)) { - nf_tables_set_notify(ctx, set, NFT_MSG_DELSET, GFP_ATOMIC); + if (list_empty(&set->bindings) && nft_set_is_anonymous(set)) nft_set_destroy(set); - } } EXPORT_SYMBOL_GPL(nf_tables_destroy_set); @@ -6622,6 +6612,9 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nf_tables_rule_notify(&trans->ctx, nft_trans_rule(trans), NFT_MSG_DELRULE); + nft_rule_expr_deactivate(&trans->ctx, + nft_trans_rule(trans), + NFT_TRANS_COMMIT); break; case NFT_MSG_NEWSET: nft_clear(net, nft_trans_set(trans)); @@ -6708,7 +6701,8 @@ static void nf_tables_abort_release(struct nft_trans *trans) nf_tables_rule_destroy(&trans->ctx, nft_trans_rule(trans)); break; case NFT_MSG_NEWSET: - nft_set_destroy(nft_trans_set(trans)); + if (!nft_trans_set_bound(trans)) + nft_set_destroy(nft_trans_set(trans)); break; case NFT_MSG_NEWSETELEM: nft_set_elem_destroy(nft_trans_elem_set(trans), @@ -6769,7 +6763,9 @@ static int __nf_tables_abort(struct net *net) case NFT_MSG_NEWRULE: trans->ctx.chain->use--; list_del_rcu(&nft_trans_rule(trans)->list); - nft_rule_expr_deactivate(&trans->ctx, nft_trans_rule(trans)); + nft_rule_expr_deactivate(&trans->ctx, + nft_trans_rule(trans), + NFT_TRANS_ABORT); break; case NFT_MSG_DELRULE: trans->ctx.chain->use++; @@ -6779,7 +6775,8 @@ static int __nf_tables_abort(struct net *net) break; case NFT_MSG_NEWSET: trans->ctx.table->use--; - list_del_rcu(&nft_trans_set(trans)->list); + if (!nft_trans_set_bound(trans)) + list_del_rcu(&nft_trans_set(trans)->list); break; case NFT_MSG_DELSET: trans->ctx.table->use++; diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c index 6f41dd74729d..1f1d90c1716b 100644 --- a/net/netfilter/nfnetlink_osf.c +++ b/net/netfilter/nfnetlink_osf.c @@ -66,6 +66,7 @@ static bool nf_osf_match_one(const struct sk_buff *skb, int ttl_check, struct nf_osf_hdr_ctx *ctx) { + const __u8 *optpinit = ctx->optp; unsigned int check_WSS = 0; int fmatch = FMATCH_WRONG; int foptsize, optnum; @@ -155,6 +156,9 @@ static bool nf_osf_match_one(const struct sk_buff *skb, } } + if (fmatch != FMATCH_OK) + ctx->optp = optpinit; + return fmatch == FMATCH_OK; } diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 7334e0b80a5e..0a4bad55a8aa 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -22,11 +22,15 @@ #include <linux/netfilter_bridge/ebtables.h> #include <linux/netfilter_arp/arp_tables.h> #include <net/netfilter/nf_tables.h> +#include <net/netns/generic.h> struct nft_xt { struct list_head head; struct nft_expr_ops ops; - unsigned int refcnt; + refcount_t refcnt; + + /* used only when transaction mutex is locked */ + unsigned int listcnt; /* Unlike other expressions, ops doesn't have static storage duration. * nft core assumes they do. We use kfree_rcu so that nft core can @@ -43,10 +47,39 @@ struct nft_xt_match_priv { void *info; }; +struct nft_compat_net { + struct list_head nft_target_list; + struct list_head nft_match_list; +}; + +static unsigned int nft_compat_net_id __read_mostly; +static struct nft_expr_type nft_match_type; +static struct nft_expr_type nft_target_type; + +static struct nft_compat_net *nft_compat_pernet(struct net *net) +{ + return net_generic(net, nft_compat_net_id); +} + +static void nft_xt_get(struct nft_xt *xt) +{ + /* refcount_inc() warns on 0 -> 1 transition, but we can't + * init the reference count to 1 in .select_ops -- we can't + * undo such an increase when another expression inside the same + * rule fails afterwards. + */ + if (xt->listcnt == 0) + refcount_set(&xt->refcnt, 1); + else + refcount_inc(&xt->refcnt); + + xt->listcnt++; +} + static bool nft_xt_put(struct nft_xt *xt) { - if (--xt->refcnt == 0) { - list_del(&xt->head); + if (refcount_dec_and_test(&xt->refcnt)) { + WARN_ON_ONCE(!list_empty(&xt->head)); kfree_rcu(xt, rcu_head); return true; } @@ -273,7 +306,7 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr, return -EINVAL; nft_xt = container_of(expr->ops, struct nft_xt, ops); - nft_xt->refcnt++; + nft_xt_get(nft_xt); return 0; } @@ -282,6 +315,7 @@ nft_target_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { struct xt_target *target = expr->ops->data; void *info = nft_expr_priv(expr); + struct module *me = target->me; struct xt_tgdtor_param par; par.net = ctx->net; @@ -292,7 +326,7 @@ nft_target_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) par.target->destroy(&par); if (nft_xt_put(container_of(expr->ops, struct nft_xt, ops))) - module_put(target->me); + module_put(me); } static int nft_extension_dump_info(struct sk_buff *skb, int attr, @@ -486,7 +520,7 @@ __nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr, return ret; nft_xt = container_of(expr->ops, struct nft_xt, ops); - nft_xt->refcnt++; + nft_xt_get(nft_xt); return 0; } @@ -540,6 +574,18 @@ nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) __nft_match_destroy(ctx, expr, nft_expr_priv(expr)); } +static void nft_compat_deactivate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + enum nft_trans_phase phase) +{ + struct nft_xt *xt = container_of(expr->ops, struct nft_xt, ops); + + if (phase == NFT_TRANS_ABORT || phase == NFT_TRANS_COMMIT) { + if (--xt->listcnt == 0) + list_del_init(&xt->head); + } +} + static void nft_match_large_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { @@ -734,10 +780,6 @@ static const struct nfnetlink_subsystem nfnl_compat_subsys = { .cb = nfnl_nft_compat_cb, }; -static LIST_HEAD(nft_match_list); - -static struct nft_expr_type nft_match_type; - static bool nft_match_cmp(const struct xt_match *match, const char *name, u32 rev, u32 family) { @@ -749,6 +791,7 @@ static const struct nft_expr_ops * nft_match_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { + struct nft_compat_net *cn; struct nft_xt *nft_match; struct xt_match *match; unsigned int matchsize; @@ -765,8 +808,10 @@ nft_match_select_ops(const struct nft_ctx *ctx, rev = ntohl(nla_get_be32(tb[NFTA_MATCH_REV])); family = ctx->family; + cn = nft_compat_pernet(ctx->net); + /* Re-use the existing match if it's already loaded. */ - list_for_each_entry(nft_match, &nft_match_list, head) { + list_for_each_entry(nft_match, &cn->nft_match_list, head) { struct xt_match *match = nft_match->ops.data; if (nft_match_cmp(match, mt_name, rev, family)) @@ -789,11 +834,12 @@ nft_match_select_ops(const struct nft_ctx *ctx, goto err; } - nft_match->refcnt = 0; + refcount_set(&nft_match->refcnt, 0); nft_match->ops.type = &nft_match_type; nft_match->ops.eval = nft_match_eval; nft_match->ops.init = nft_match_init; nft_match->ops.destroy = nft_match_destroy; + nft_match->ops.deactivate = nft_compat_deactivate; nft_match->ops.dump = nft_match_dump; nft_match->ops.validate = nft_match_validate; nft_match->ops.data = match; @@ -810,7 +856,8 @@ nft_match_select_ops(const struct nft_ctx *ctx, nft_match->ops.size = matchsize; - list_add(&nft_match->head, &nft_match_list); + nft_match->listcnt = 0; + list_add(&nft_match->head, &cn->nft_match_list); return &nft_match->ops; err: @@ -826,10 +873,6 @@ static struct nft_expr_type nft_match_type __read_mostly = { .owner = THIS_MODULE, }; -static LIST_HEAD(nft_target_list); - -static struct nft_expr_type nft_target_type; - static bool nft_target_cmp(const struct xt_target *tg, const char *name, u32 rev, u32 family) { @@ -841,6 +884,7 @@ static const struct nft_expr_ops * nft_target_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { + struct nft_compat_net *cn; struct nft_xt *nft_target; struct xt_target *target; char *tg_name; @@ -861,8 +905,9 @@ nft_target_select_ops(const struct nft_ctx *ctx, strcmp(tg_name, "standard") == 0) return ERR_PTR(-EINVAL); + cn = nft_compat_pernet(ctx->net); /* Re-use the existing target if it's already loaded. */ - list_for_each_entry(nft_target, &nft_target_list, head) { + list_for_each_entry(nft_target, &cn->nft_target_list, head) { struct xt_target *target = nft_target->ops.data; if (!target->target) @@ -893,11 +938,12 @@ nft_target_select_ops(const struct nft_ctx *ctx, goto err; } - nft_target->refcnt = 0; + refcount_set(&nft_target->refcnt, 0); nft_target->ops.type = &nft_target_type; nft_target->ops.size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize)); nft_target->ops.init = nft_target_init; nft_target->ops.destroy = nft_target_destroy; + nft_target->ops.deactivate = nft_compat_deactivate; nft_target->ops.dump = nft_target_dump; nft_target->ops.validate = nft_target_validate; nft_target->ops.data = target; @@ -907,7 +953,8 @@ nft_target_select_ops(const struct nft_ctx *ctx, else nft_target->ops.eval = nft_target_eval_xt; - list_add(&nft_target->head, &nft_target_list); + nft_target->listcnt = 0; + list_add(&nft_target->head, &cn->nft_target_list); return &nft_target->ops; err: @@ -923,13 +970,74 @@ static struct nft_expr_type nft_target_type __read_mostly = { .owner = THIS_MODULE, }; +static int __net_init nft_compat_init_net(struct net *net) +{ + struct nft_compat_net *cn = nft_compat_pernet(net); + + INIT_LIST_HEAD(&cn->nft_target_list); + INIT_LIST_HEAD(&cn->nft_match_list); + + return 0; +} + +static void __net_exit nft_compat_exit_net(struct net *net) +{ + struct nft_compat_net *cn = nft_compat_pernet(net); + struct nft_xt *xt, *next; + + if (list_empty(&cn->nft_match_list) && + list_empty(&cn->nft_target_list)) + return; + + /* If there was an error that caused nft_xt expr to not be initialized + * fully and noone else requested the same expression later, the lists + * contain 0-refcount entries that still hold module reference. + * + * Clean them here. + */ + mutex_lock(&net->nft.commit_mutex); + list_for_each_entry_safe(xt, next, &cn->nft_target_list, head) { + struct xt_target *target = xt->ops.data; + + list_del_init(&xt->head); + + if (refcount_read(&xt->refcnt)) + continue; + module_put(target->me); + kfree(xt); + } + + list_for_each_entry_safe(xt, next, &cn->nft_match_list, head) { + struct xt_match *match = xt->ops.data; + + list_del_init(&xt->head); + + if (refcount_read(&xt->refcnt)) + continue; + module_put(match->me); + kfree(xt); + } + mutex_unlock(&net->nft.commit_mutex); +} + +static struct pernet_operations nft_compat_net_ops = { + .init = nft_compat_init_net, + .exit = nft_compat_exit_net, + .id = &nft_compat_net_id, + .size = sizeof(struct nft_compat_net), +}; + static int __init nft_compat_module_init(void) { int ret; + ret = register_pernet_subsys(&nft_compat_net_ops); + if (ret < 0) + goto err_target; + ret = nft_register_expr(&nft_match_type); if (ret < 0) - return ret; + goto err_pernet; ret = nft_register_expr(&nft_target_type); if (ret < 0) @@ -942,45 +1050,21 @@ static int __init nft_compat_module_init(void) } return ret; - err_target: nft_unregister_expr(&nft_target_type); err_match: nft_unregister_expr(&nft_match_type); +err_pernet: + unregister_pernet_subsys(&nft_compat_net_ops); return ret; } static void __exit nft_compat_module_exit(void) { - struct nft_xt *xt, *next; - - /* list should be empty here, it can be non-empty only in case there - * was an error that caused nft_xt expr to not be initialized fully - * and noone else requested the same expression later. - * - * In this case, the lists contain 0-refcount entries that still - * hold module reference. - */ - list_for_each_entry_safe(xt, next, &nft_target_list, head) { - struct xt_target *target = xt->ops.data; - - if (WARN_ON_ONCE(xt->refcnt)) - continue; - module_put(target->me); - kfree(xt); - } - - list_for_each_entry_safe(xt, next, &nft_match_list, head) { - struct xt_match *match = xt->ops.data; - - if (WARN_ON_ONCE(xt->refcnt)) - continue; - module_put(match->me); - kfree(xt); - } nfnetlink_subsys_unregister(&nfnl_compat_subsys); nft_unregister_expr(&nft_target_type); nft_unregister_expr(&nft_match_type); + unregister_pernet_subsys(&nft_compat_net_ops); } MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_NFT_COMPAT); diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 9658493d37d4..a8a74a16f9c4 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -234,20 +234,17 @@ err1: return err; } -static void nft_dynset_activate(const struct nft_ctx *ctx, - const struct nft_expr *expr) -{ - struct nft_dynset *priv = nft_expr_priv(expr); - - nf_tables_rebind_set(ctx, priv->set, &priv->binding); -} - static void nft_dynset_deactivate(const struct nft_ctx *ctx, - const struct nft_expr *expr) + const struct nft_expr *expr, + enum nft_trans_phase phase) { struct nft_dynset *priv = nft_expr_priv(expr); - nf_tables_unbind_set(ctx, priv->set, &priv->binding); + if (phase == NFT_TRANS_PREPARE) + return; + + nf_tables_unbind_set(ctx, priv->set, &priv->binding, + phase == NFT_TRANS_COMMIT); } static void nft_dynset_destroy(const struct nft_ctx *ctx, @@ -295,7 +292,6 @@ static const struct nft_expr_ops nft_dynset_ops = { .eval = nft_dynset_eval, .init = nft_dynset_init, .destroy = nft_dynset_destroy, - .activate = nft_dynset_activate, .deactivate = nft_dynset_deactivate, .dump = nft_dynset_dump, }; diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index 3e5ed787b1d4..5ec43124cbca 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -72,10 +72,14 @@ static void nft_immediate_activate(const struct nft_ctx *ctx, } static void nft_immediate_deactivate(const struct nft_ctx *ctx, - const struct nft_expr *expr) + const struct nft_expr *expr, + enum nft_trans_phase phase) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); + if (phase == NFT_TRANS_COMMIT) + return; + return nft_data_release(&priv->data, nft_dreg_to_type(priv->dreg)); } diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index 227b2b15a19c..14496da5141d 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -121,20 +121,17 @@ static int nft_lookup_init(const struct nft_ctx *ctx, return 0; } -static void nft_lookup_activate(const struct nft_ctx *ctx, - const struct nft_expr *expr) -{ - struct nft_lookup *priv = nft_expr_priv(expr); - - nf_tables_rebind_set(ctx, priv->set, &priv->binding); -} - static void nft_lookup_deactivate(const struct nft_ctx *ctx, - const struct nft_expr *expr) + const struct nft_expr *expr, + enum nft_trans_phase phase) { struct nft_lookup *priv = nft_expr_priv(expr); - nf_tables_unbind_set(ctx, priv->set, &priv->binding); + if (phase == NFT_TRANS_PREPARE) + return; + + nf_tables_unbind_set(ctx, priv->set, &priv->binding, + phase == NFT_TRANS_COMMIT); } static void nft_lookup_destroy(const struct nft_ctx *ctx, @@ -225,7 +222,6 @@ static const struct nft_expr_ops nft_lookup_ops = { .size = NFT_EXPR_SIZE(sizeof(struct nft_lookup)), .eval = nft_lookup_eval, .init = nft_lookup_init, - .activate = nft_lookup_activate, .deactivate = nft_lookup_deactivate, .destroy = nft_lookup_destroy, .dump = nft_lookup_dump, diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index c1f2adf198a0..79ef074c18ca 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -156,20 +156,17 @@ nla_put_failure: return -1; } -static void nft_objref_map_activate(const struct nft_ctx *ctx, - const struct nft_expr *expr) -{ - struct nft_objref_map *priv = nft_expr_priv(expr); - - nf_tables_rebind_set(ctx, priv->set, &priv->binding); -} - static void nft_objref_map_deactivate(const struct nft_ctx *ctx, - const struct nft_expr *expr) + const struct nft_expr *expr, + enum nft_trans_phase phase) { struct nft_objref_map *priv = nft_expr_priv(expr); - nf_tables_unbind_set(ctx, priv->set, &priv->binding); + if (phase == NFT_TRANS_PREPARE) + return; + + nf_tables_unbind_set(ctx, priv->set, &priv->binding, + phase == NFT_TRANS_COMMIT); } static void nft_objref_map_destroy(const struct nft_ctx *ctx, @@ -186,7 +183,6 @@ static const struct nft_expr_ops nft_objref_map_ops = { .size = NFT_EXPR_SIZE(sizeof(struct nft_objref_map)), .eval = nft_objref_map_eval, .init = nft_objref_map_init, - .activate = nft_objref_map_activate, .deactivate = nft_objref_map_deactivate, .destroy = nft_objref_map_destroy, .dump = nft_objref_map_dump, diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index aecadd471e1d..13e1ac333fa4 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1899,7 +1899,7 @@ static int __init xt_init(void) seqcount_init(&per_cpu(xt_recseq, i)); } - xt = kmalloc_array(NFPROTO_NUMPROTO, sizeof(struct xt_af), GFP_KERNEL); + xt = kcalloc(NFPROTO_NUMPROTO, sizeof(struct xt_af), GFP_KERNEL); if (!xt) return -ENOMEM; diff --git a/net/netrom/nr_timer.c b/net/netrom/nr_timer.c index cbd51ed5a2d7..908e53ab47a4 100644 --- a/net/netrom/nr_timer.c +++ b/net/netrom/nr_timer.c @@ -52,21 +52,21 @@ void nr_start_t1timer(struct sock *sk) { struct nr_sock *nr = nr_sk(sk); - mod_timer(&nr->t1timer, jiffies + nr->t1); + sk_reset_timer(sk, &nr->t1timer, jiffies + nr->t1); } void nr_start_t2timer(struct sock *sk) { struct nr_sock *nr = nr_sk(sk); - mod_timer(&nr->t2timer, jiffies + nr->t2); + sk_reset_timer(sk, &nr->t2timer, jiffies + nr->t2); } void nr_start_t4timer(struct sock *sk) { struct nr_sock *nr = nr_sk(sk); - mod_timer(&nr->t4timer, jiffies + nr->t4); + sk_reset_timer(sk, &nr->t4timer, jiffies + nr->t4); } void nr_start_idletimer(struct sock *sk) @@ -74,37 +74,37 @@ void nr_start_idletimer(struct sock *sk) struct nr_sock *nr = nr_sk(sk); if (nr->idle > 0) - mod_timer(&nr->idletimer, jiffies + nr->idle); + sk_reset_timer(sk, &nr->idletimer, jiffies + nr->idle); } void nr_start_heartbeat(struct sock *sk) { - mod_timer(&sk->sk_timer, jiffies + 5 * HZ); + sk_reset_timer(sk, &sk->sk_timer, jiffies + 5 * HZ); } void nr_stop_t1timer(struct sock *sk) { - del_timer(&nr_sk(sk)->t1timer); + sk_stop_timer(sk, &nr_sk(sk)->t1timer); } void nr_stop_t2timer(struct sock *sk) { - del_timer(&nr_sk(sk)->t2timer); + sk_stop_timer(sk, &nr_sk(sk)->t2timer); } void nr_stop_t4timer(struct sock *sk) { - del_timer(&nr_sk(sk)->t4timer); + sk_stop_timer(sk, &nr_sk(sk)->t4timer); } void nr_stop_idletimer(struct sock *sk) { - del_timer(&nr_sk(sk)->idletimer); + sk_stop_timer(sk, &nr_sk(sk)->idletimer); } void nr_stop_heartbeat(struct sock *sk) { - del_timer(&sk->sk_timer); + sk_stop_timer(sk, &sk->sk_timer); } int nr_t1timer_running(struct sock *sk) diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 3b1a78906bc0..1cd1d83a4be0 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -4292,7 +4292,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, rb->frames_per_block = req->tp_block_size / req->tp_frame_size; if (unlikely(rb->frames_per_block == 0)) goto out; - if (unlikely(req->tp_block_size > UINT_MAX / req->tp_block_nr)) + if (unlikely(rb->frames_per_block > UINT_MAX / req->tp_block_nr)) goto out; if (unlikely((rb->frames_per_block * req->tp_block_nr) != req->tp_frame_nr)) diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index 65387e1e6964..d6cc97fbbbb0 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -254,7 +254,40 @@ static __poll_t rds_poll(struct file *file, struct socket *sock, static int rds_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { - return -ENOIOCTLCMD; + struct rds_sock *rs = rds_sk_to_rs(sock->sk); + rds_tos_t utos, tos = 0; + + switch (cmd) { + case SIOCRDSSETTOS: + if (get_user(utos, (rds_tos_t __user *)arg)) + return -EFAULT; + + if (rs->rs_transport && + rs->rs_transport->get_tos_map) + tos = rs->rs_transport->get_tos_map(utos); + else + return -ENOIOCTLCMD; + + spin_lock_bh(&rds_sock_lock); + if (rs->rs_tos || rs->rs_conn) { + spin_unlock_bh(&rds_sock_lock); + return -EINVAL; + } + rs->rs_tos = tos; + spin_unlock_bh(&rds_sock_lock); + break; + case SIOCRDSGETTOS: + spin_lock_bh(&rds_sock_lock); + tos = rs->rs_tos; + spin_unlock_bh(&rds_sock_lock); + if (put_user(tos, (rds_tos_t __user *)arg)) + return -EFAULT; + break; + default: + return -ENOIOCTLCMD; + } + + return 0; } static int rds_cancel_sent_to(struct rds_sock *rs, char __user *optval, @@ -348,7 +381,7 @@ static int rds_set_transport(struct rds_sock *rs, char __user *optval, } static int rds_enable_recvtstamp(struct sock *sk, char __user *optval, - int optlen) + int optlen, int optname) { int val, valbool; @@ -360,6 +393,9 @@ static int rds_enable_recvtstamp(struct sock *sk, char __user *optval, valbool = val ? 1 : 0; + if (optname == SO_TIMESTAMP_NEW) + sock_set_flag(sk, SOCK_TSTAMP_NEW); + if (valbool) sock_set_flag(sk, SOCK_RCVTSTAMP); else @@ -430,9 +466,10 @@ static int rds_setsockopt(struct socket *sock, int level, int optname, ret = rds_set_transport(rs, optval, optlen); release_sock(sock->sk); break; - case SO_TIMESTAMP: + case SO_TIMESTAMP_OLD: + case SO_TIMESTAMP_NEW: lock_sock(sock->sk); - ret = rds_enable_recvtstamp(sock->sk, optval, optlen); + ret = rds_enable_recvtstamp(sock->sk, optval, optlen, optname); release_sock(sock->sk); break; case SO_RDS_MSG_RXPATH_LATENCY: @@ -646,6 +683,8 @@ static int __rds_create(struct socket *sock, struct sock *sk, int protocol) spin_lock_init(&rs->rs_rdma_lock); rs->rs_rdma_keys = RB_ROOT; rs->rs_rx_traces = 0; + rs->rs_tos = 0; + rs->rs_conn = NULL; spin_lock_bh(&rds_sock_lock); list_add_tail(&rs->rs_item, &rds_sock_list); diff --git a/net/rds/bind.c b/net/rds/bind.c index 762d2c6788a3..17c9d9f0c848 100644 --- a/net/rds/bind.c +++ b/net/rds/bind.c @@ -78,10 +78,10 @@ struct rds_sock *rds_find_bound(const struct in6_addr *addr, __be16 port, __rds_create_bind_key(key, addr, port, scope_id); rcu_read_lock(); rs = rhashtable_lookup(&bind_hash_table, key, ht_parms); - if (rs && !sock_flag(rds_rs_to_sk(rs), SOCK_DEAD)) - rds_sock_addref(rs); - else + if (rs && (sock_flag(rds_rs_to_sk(rs), SOCK_DEAD) || + !refcount_inc_not_zero(&rds_rs_to_sk(rs)->sk_refcnt))) rs = NULL; + rcu_read_unlock(); rdsdebug("returning rs %p for %pI6c:%u\n", rs, addr, diff --git a/net/rds/connection.c b/net/rds/connection.c index 3bd2f4a5a30d..7ea134f9a825 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -84,7 +84,7 @@ static struct rds_connection *rds_conn_lookup(struct net *net, const struct in6_addr *laddr, const struct in6_addr *faddr, struct rds_transport *trans, - int dev_if) + u8 tos, int dev_if) { struct rds_connection *conn, *ret = NULL; @@ -92,6 +92,7 @@ static struct rds_connection *rds_conn_lookup(struct net *net, if (ipv6_addr_equal(&conn->c_faddr, faddr) && ipv6_addr_equal(&conn->c_laddr, laddr) && conn->c_trans == trans && + conn->c_tos == tos && net == rds_conn_net(conn) && conn->c_dev_if == dev_if) { ret = conn; @@ -139,6 +140,7 @@ static void __rds_conn_path_init(struct rds_connection *conn, atomic_set(&cp->cp_state, RDS_CONN_DOWN); cp->cp_send_gen = 0; cp->cp_reconnect_jiffies = 0; + cp->cp_conn->c_proposed_version = RDS_PROTOCOL_VERSION; INIT_DELAYED_WORK(&cp->cp_send_w, rds_send_worker); INIT_DELAYED_WORK(&cp->cp_recv_w, rds_recv_worker); INIT_DELAYED_WORK(&cp->cp_conn_w, rds_connect_worker); @@ -159,7 +161,7 @@ static struct rds_connection *__rds_conn_create(struct net *net, const struct in6_addr *laddr, const struct in6_addr *faddr, struct rds_transport *trans, - gfp_t gfp, + gfp_t gfp, u8 tos, int is_outgoing, int dev_if) { @@ -171,7 +173,7 @@ static struct rds_connection *__rds_conn_create(struct net *net, int npaths = (trans->t_mp_capable ? RDS_MPATH_WORKERS : 1); rcu_read_lock(); - conn = rds_conn_lookup(net, head, laddr, faddr, trans, dev_if); + conn = rds_conn_lookup(net, head, laddr, faddr, trans, tos, dev_if); if (conn && conn->c_loopback && conn->c_trans != &rds_loop_transport && @@ -205,6 +207,7 @@ static struct rds_connection *__rds_conn_create(struct net *net, conn->c_isv6 = !ipv6_addr_v4mapped(laddr); conn->c_faddr = *faddr; conn->c_dev_if = dev_if; + conn->c_tos = tos; #if IS_ENABLED(CONFIG_IPV6) /* If the local address is link local, set c_bound_if to be the @@ -297,7 +300,7 @@ static struct rds_connection *__rds_conn_create(struct net *net, struct rds_connection *found; found = rds_conn_lookup(net, head, laddr, faddr, trans, - dev_if); + tos, dev_if); if (found) { struct rds_conn_path *cp; int i; @@ -332,10 +335,10 @@ out: struct rds_connection *rds_conn_create(struct net *net, const struct in6_addr *laddr, const struct in6_addr *faddr, - struct rds_transport *trans, gfp_t gfp, - int dev_if) + struct rds_transport *trans, u8 tos, + gfp_t gfp, int dev_if) { - return __rds_conn_create(net, laddr, faddr, trans, gfp, 0, dev_if); + return __rds_conn_create(net, laddr, faddr, trans, gfp, tos, 0, dev_if); } EXPORT_SYMBOL_GPL(rds_conn_create); @@ -343,9 +346,9 @@ struct rds_connection *rds_conn_create_outgoing(struct net *net, const struct in6_addr *laddr, const struct in6_addr *faddr, struct rds_transport *trans, - gfp_t gfp, int dev_if) + u8 tos, gfp_t gfp, int dev_if) { - return __rds_conn_create(net, laddr, faddr, trans, gfp, 1, dev_if); + return __rds_conn_create(net, laddr, faddr, trans, gfp, tos, 1, dev_if); } EXPORT_SYMBOL_GPL(rds_conn_create_outgoing); diff --git a/net/rds/ib.c b/net/rds/ib.c index 9d7b7586f240..2da9b75bad16 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -301,6 +301,7 @@ static int rds_ib_conn_info_visitor(struct rds_connection *conn, iinfo->src_addr = conn->c_laddr.s6_addr32[3]; iinfo->dst_addr = conn->c_faddr.s6_addr32[3]; + iinfo->tos = conn->c_tos; memset(&iinfo->src_gid, 0, sizeof(iinfo->src_gid)); memset(&iinfo->dst_gid, 0, sizeof(iinfo->dst_gid)); @@ -514,6 +515,15 @@ void rds_ib_exit(void) rds_ib_mr_exit(); } +static u8 rds_ib_get_tos_map(u8 tos) +{ + /* 1:1 user to transport map for RDMA transport. + * In future, if custom map is desired, hook can export + * user configurable map. + */ + return tos; +} + struct rds_transport rds_ib_transport = { .laddr_check = rds_ib_laddr_check, .xmit_path_complete = rds_ib_xmit_path_complete, @@ -536,6 +546,7 @@ struct rds_transport rds_ib_transport = { .sync_mr = rds_ib_sync_mr, .free_mr = rds_ib_free_mr, .flush_mrs = rds_ib_flush_mrs, + .get_tos_map = rds_ib_get_tos_map, .t_owner = THIS_MODULE, .t_name = "infiniband", .t_unloading = rds_ib_is_unloading, diff --git a/net/rds/ib.h b/net/rds/ib.h index 71ff356ee702..752f92235a38 100644 --- a/net/rds/ib.h +++ b/net/rds/ib.h @@ -67,7 +67,9 @@ struct rds_ib_conn_priv_cmn { u8 ricpc_protocol_major; u8 ricpc_protocol_minor; __be16 ricpc_protocol_minor_mask; /* bitmask */ - __be32 ricpc_reserved1; + u8 ricpc_dp_toss; + u8 ripc_reserved1; + __be16 ripc_reserved2; __be64 ricpc_ack_seq; __be32 ricpc_credit; /* non-zero enables flow ctl */ }; diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index bfbb31f0c7fd..66c6eb56072b 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -133,23 +133,24 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_even rds_ib_set_flow_control(conn, be32_to_cpu(credit)); } - if (conn->c_version < RDS_PROTOCOL(3, 1)) { - pr_notice("RDS/IB: Connection <%pI6c,%pI6c> version %u.%u no longer supported\n", - &conn->c_laddr, &conn->c_faddr, - RDS_PROTOCOL_MAJOR(conn->c_version), - RDS_PROTOCOL_MINOR(conn->c_version)); - set_bit(RDS_DESTROY_PENDING, &conn->c_path[0].cp_flags); - rds_conn_destroy(conn); - return; - } else { - pr_notice("RDS/IB: %s conn connected <%pI6c,%pI6c> version %u.%u%s\n", - ic->i_active_side ? "Active" : "Passive", - &conn->c_laddr, &conn->c_faddr, - RDS_PROTOCOL_MAJOR(conn->c_version), - RDS_PROTOCOL_MINOR(conn->c_version), - ic->i_flowctl ? ", flow control" : ""); + if (conn->c_version < RDS_PROTOCOL_VERSION) { + if (conn->c_version != RDS_PROTOCOL_COMPAT_VERSION) { + pr_notice("RDS/IB: Connection <%pI6c,%pI6c> version %u.%u no longer supported\n", + &conn->c_laddr, &conn->c_faddr, + RDS_PROTOCOL_MAJOR(conn->c_version), + RDS_PROTOCOL_MINOR(conn->c_version)); + rds_conn_destroy(conn); + return; + } } + pr_notice("RDS/IB: %s conn connected <%pI6c,%pI6c,%d> version %u.%u%s\n", + ic->i_active_side ? "Active" : "Passive", + &conn->c_laddr, &conn->c_faddr, conn->c_tos, + RDS_PROTOCOL_MAJOR(conn->c_version), + RDS_PROTOCOL_MINOR(conn->c_version), + ic->i_flowctl ? ", flow control" : ""); + atomic_set(&ic->i_cq_quiesce, 0); /* Init rings and fill recv. this needs to wait until protocol @@ -184,6 +185,7 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_even NULL); } + conn->c_proposed_version = conn->c_version; rds_connect_complete(conn); } @@ -220,6 +222,7 @@ static void rds_ib_cm_fill_conn_param(struct rds_connection *conn, cpu_to_be16(RDS_IB_SUPPORTED_PROTOCOLS); dp->ricp_v6.dp_ack_seq = cpu_to_be64(rds_ib_piggyb_ack(ic)); + dp->ricp_v6.dp_cmn.ricpc_dp_toss = conn->c_tos; conn_param->private_data = &dp->ricp_v6; conn_param->private_data_len = sizeof(dp->ricp_v6); @@ -234,6 +237,7 @@ static void rds_ib_cm_fill_conn_param(struct rds_connection *conn, cpu_to_be16(RDS_IB_SUPPORTED_PROTOCOLS); dp->ricp_v4.dp_ack_seq = cpu_to_be64(rds_ib_piggyb_ack(ic)); + dp->ricp_v4.dp_cmn.ricpc_dp_toss = conn->c_tos; conn_param->private_data = &dp->ricp_v4; conn_param->private_data_len = sizeof(dp->ricp_v4); @@ -389,10 +393,9 @@ static void rds_ib_qp_event_handler(struct ib_event *event, void *data) rdma_notify(ic->i_cm_id, IB_EVENT_COMM_EST); break; default: - rdsdebug("Fatal QP Event %u (%s) " - "- connection %pI6c->%pI6c, reconnecting\n", - event->event, ib_event_msg(event->event), - &conn->c_laddr, &conn->c_faddr); + rdsdebug("Fatal QP Event %u (%s) - connection %pI6c->%pI6c, reconnecting\n", + event->event, ib_event_msg(event->event), + &conn->c_laddr, &conn->c_faddr); rds_conn_drop(conn); break; } @@ -660,13 +663,16 @@ static u32 rds_ib_protocol_compatible(struct rdma_cm_event *event, bool isv6) /* Even if len is crap *now* I still want to check it. -ASG */ if (event->param.conn.private_data_len < data_len || major == 0) - return RDS_PROTOCOL_3_0; + return RDS_PROTOCOL_4_0; common = be16_to_cpu(mask) & RDS_IB_SUPPORTED_PROTOCOLS; - if (major == 3 && common) { - version = RDS_PROTOCOL_3_0; + if (major == 4 && common) { + version = RDS_PROTOCOL_4_0; while ((common >>= 1) != 0) version++; + } else if (RDS_PROTOCOL_COMPAT_VERSION == + RDS_PROTOCOL(major, minor)) { + version = RDS_PROTOCOL_COMPAT_VERSION; } else { if (isv6) printk_ratelimited(KERN_NOTICE "RDS: Connection from %pI6c using incompatible protocol version %u.%u\n", @@ -729,8 +735,10 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id, /* Check whether the remote protocol version matches ours. */ version = rds_ib_protocol_compatible(event, isv6); - if (!version) + if (!version) { + err = RDS_RDMA_REJ_INCOMPAT; goto out; + } dp = event->param.conn.private_data; if (isv6) { @@ -771,15 +779,16 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id, daddr6 = &d_mapped_addr; } - rdsdebug("saddr %pI6c daddr %pI6c RDSv%u.%u lguid 0x%llx fguid " - "0x%llx\n", saddr6, daddr6, - RDS_PROTOCOL_MAJOR(version), RDS_PROTOCOL_MINOR(version), + rdsdebug("saddr %pI6c daddr %pI6c RDSv%u.%u lguid 0x%llx fguid 0x%llx, tos:%d\n", + saddr6, daddr6, RDS_PROTOCOL_MAJOR(version), + RDS_PROTOCOL_MINOR(version), (unsigned long long)be64_to_cpu(lguid), - (unsigned long long)be64_to_cpu(fguid)); + (unsigned long long)be64_to_cpu(fguid), dp_cmn->ricpc_dp_toss); /* RDS/IB is not currently netns aware, thus init_net */ conn = rds_conn_create(&init_net, daddr6, saddr6, - &rds_ib_transport, GFP_KERNEL, ifindex); + &rds_ib_transport, dp_cmn->ricpc_dp_toss, + GFP_KERNEL, ifindex); if (IS_ERR(conn)) { rdsdebug("rds_conn_create failed (%ld)\n", PTR_ERR(conn)); conn = NULL; @@ -846,7 +855,7 @@ out: if (conn) mutex_unlock(&conn->c_cm_lock); if (err) - rdma_reject(cm_id, NULL, 0); + rdma_reject(cm_id, &err, sizeof(int)); return destroy; } @@ -861,7 +870,7 @@ int rds_ib_cm_initiate_connect(struct rdma_cm_id *cm_id, bool isv6) /* If the peer doesn't do protocol negotiation, we must * default to RDSv3.0 */ - rds_ib_set_protocol(conn, RDS_PROTOCOL_3_0); + rds_ib_set_protocol(conn, RDS_PROTOCOL_4_1); ic->i_flowctl = rds_ib_sysctl_flow_control; /* advertise flow control */ ret = rds_ib_setup_qp(conn); @@ -870,7 +879,8 @@ int rds_ib_cm_initiate_connect(struct rdma_cm_id *cm_id, bool isv6) goto out; } - rds_ib_cm_fill_conn_param(conn, &conn_param, &dp, RDS_PROTOCOL_VERSION, + rds_ib_cm_fill_conn_param(conn, &conn_param, &dp, + conn->c_proposed_version, UINT_MAX, UINT_MAX, isv6); ret = rdma_connect(cm_id, &conn_param); if (ret) diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index 2f16146e4ec9..d395eec98959 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -986,9 +986,9 @@ void rds_ib_recv_cqe_handler(struct rds_ib_connection *ic, } else { /* We expect errors as the qp is drained during shutdown */ if (rds_conn_up(conn) || rds_conn_connecting(conn)) - rds_ib_conn_error(conn, "recv completion on <%pI6c,%pI6c> had status %u (%s), disconnecting and reconnecting\n", + rds_ib_conn_error(conn, "recv completion on <%pI6c,%pI6c, %d> had status %u (%s), disconnecting and reconnecting\n", &conn->c_laddr, &conn->c_faddr, - wc->status, + conn->c_tos, wc->status, ib_wc_status_msg(wc->status)); } diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c index 4e0c36acf866..09c46f2e97fa 100644 --- a/net/rds/ib_send.c +++ b/net/rds/ib_send.c @@ -305,8 +305,9 @@ void rds_ib_send_cqe_handler(struct rds_ib_connection *ic, struct ib_wc *wc) /* We expect errors as the qp is drained during shutdown */ if (wc->status != IB_WC_SUCCESS && rds_conn_up(conn)) { - rds_ib_conn_error(conn, "send completion on <%pI6c,%pI6c> had status %u (%s), disconnecting and reconnecting\n", - &conn->c_laddr, &conn->c_faddr, wc->status, + rds_ib_conn_error(conn, "send completion on <%pI6c,%pI6c,%d> had status %u (%s), disconnecting and reconnecting\n", + &conn->c_laddr, &conn->c_faddr, + conn->c_tos, wc->status, ib_wc_status_msg(wc->status)); } } diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c index 6b0f57c83a2a..46bce8389066 100644 --- a/net/rds/rdma_transport.c +++ b/net/rds/rdma_transport.c @@ -51,6 +51,8 @@ static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id, struct rds_connection *conn = cm_id->context; struct rds_transport *trans; int ret = 0; + int *err; + u8 len; rdsdebug("conn %p id %p handling event %u (%s)\n", conn, cm_id, event->event, rdma_event_msg(event->event)); @@ -81,6 +83,7 @@ static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id, break; case RDMA_CM_EVENT_ADDR_RESOLVED: + rdma_set_service_type(cm_id, conn->c_tos); /* XXX do we need to clean up if this fails? */ ret = rdma_resolve_route(cm_id, RDS_RDMA_RESOLVE_TIMEOUT_MS); @@ -106,8 +109,19 @@ static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id, break; case RDMA_CM_EVENT_REJECTED: + if (!conn) + break; + err = (int *)rdma_consumer_reject_data(cm_id, event, &len); + if (!err || (err && ((*err) == RDS_RDMA_REJ_INCOMPAT))) { + pr_warn("RDS/RDMA: conn <%pI6c, %pI6c> rejected, dropping connection\n", + &conn->c_laddr, &conn->c_faddr); + conn->c_proposed_version = RDS_PROTOCOL_COMPAT_VERSION; + conn->c_tos = 0; + rds_conn_drop(conn); + } rdsdebug("Connection rejected: %s\n", rdma_reject_msg(cm_id, event->status)); + break; /* FALLTHROUGH */ case RDMA_CM_EVENT_ADDR_ERROR: case RDMA_CM_EVENT_ROUTE_ERROR: diff --git a/net/rds/rdma_transport.h b/net/rds/rdma_transport.h index 200d3134aaae..bfafd4a6d827 100644 --- a/net/rds/rdma_transport.h +++ b/net/rds/rdma_transport.h @@ -11,6 +11,12 @@ #define RDS_RDMA_RESOLVE_TIMEOUT_MS 5000 +/* Below reject reason is for legacy interoperability issue with non-linux + * RDS endpoints where older version incompatibility is conveyed via value 1. + * For future version(s), proper encoded reject reason should be be used. + */ +#define RDS_RDMA_REJ_INCOMPAT 1 + int rds_rdma_conn_connect(struct rds_connection *conn); int rds_rdma_cm_event_handler(struct rdma_cm_id *cm_id, struct rdma_cm_event *event); diff --git a/net/rds/rds.h b/net/rds/rds.h index 4ffe100ff5e6..0d8f67cadd74 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -19,10 +19,13 @@ */ #define RDS_PROTOCOL_3_0 0x0300 #define RDS_PROTOCOL_3_1 0x0301 +#define RDS_PROTOCOL_4_0 0x0400 +#define RDS_PROTOCOL_4_1 0x0401 #define RDS_PROTOCOL_VERSION RDS_PROTOCOL_3_1 #define RDS_PROTOCOL_MAJOR(v) ((v) >> 8) #define RDS_PROTOCOL_MINOR(v) ((v) & 255) #define RDS_PROTOCOL(maj, min) (((maj) << 8) | min) +#define RDS_PROTOCOL_COMPAT_VERSION RDS_PROTOCOL_3_1 /* The following ports, 16385, 18634, 18635, are registered with IANA as * the ports to be used for RDS over TCP and UDP. Currently, only RDS over @@ -151,9 +154,13 @@ struct rds_connection { struct rds_cong_map *c_fcong; /* Protocol version */ + unsigned int c_proposed_version; unsigned int c_version; possible_net_t c_net; + /* TOS */ + u8 c_tos; + struct list_head c_map_item; unsigned long c_map_queued; @@ -567,6 +574,7 @@ struct rds_transport { void (*free_mr)(void *trans_private, int invalidate); void (*flush_mrs)(void); bool (*t_unloading)(struct rds_connection *conn); + u8 (*get_tos_map)(u8 tos); }; /* Bind hash table key length. It is the sum of the size of a struct @@ -648,6 +656,7 @@ struct rds_sock { u8 rs_rx_traces; u8 rs_rx_trace[RDS_MSG_RX_DGRAM_TRACE_MAX]; struct rds_msg_zcopy_queue rs_zcookie_queue; + u8 rs_tos; }; static inline struct rds_sock *rds_sk_to_rs(const struct sock *sk) @@ -756,13 +765,14 @@ void rds_conn_exit(void); struct rds_connection *rds_conn_create(struct net *net, const struct in6_addr *laddr, const struct in6_addr *faddr, - struct rds_transport *trans, gfp_t gfp, + struct rds_transport *trans, + u8 tos, gfp_t gfp, int dev_if); struct rds_connection *rds_conn_create_outgoing(struct net *net, const struct in6_addr *laddr, const struct in6_addr *faddr, struct rds_transport *trans, - gfp_t gfp, int dev_if); + u8 tos, gfp_t gfp, int dev_if); void rds_conn_shutdown(struct rds_conn_path *cpath); void rds_conn_destroy(struct rds_connection *conn); void rds_conn_drop(struct rds_connection *conn); diff --git a/net/rds/recv.c b/net/rds/recv.c index 727639dac8a7..853de4876088 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -549,9 +549,21 @@ static int rds_cmsg_recv(struct rds_incoming *inc, struct msghdr *msg, if ((inc->i_rx_tstamp != 0) && sock_flag(rds_rs_to_sk(rs), SOCK_RCVTSTAMP)) { - struct timeval tv = ktime_to_timeval(inc->i_rx_tstamp); - ret = put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMP, - sizeof(tv), &tv); + struct __kernel_old_timeval tv = ns_to_kernel_old_timeval(inc->i_rx_tstamp); + + if (!sock_flag(rds_rs_to_sk(rs), SOCK_TSTAMP_NEW)) { + ret = put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_OLD, + sizeof(tv), &tv); + } else { + struct __kernel_sock_timeval sk_tv; + + sk_tv.tv_sec = tv.tv_sec; + sk_tv.tv_usec = tv.tv_usec; + + ret = put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_NEW, + sizeof(sk_tv), &sk_tv); + } + if (ret) goto out; } @@ -770,6 +782,7 @@ void rds_inc_info_copy(struct rds_incoming *inc, minfo.seq = be64_to_cpu(inc->i_hdr.h_sequence); minfo.len = be32_to_cpu(inc->i_hdr.h_len); + minfo.tos = inc->i_conn->c_tos; if (flip) { minfo.laddr = daddr; diff --git a/net/rds/send.c b/net/rds/send.c index fd8b687d5c05..166dd578c1cc 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -1277,12 +1277,13 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) /* rds_conn_create has a spinlock that runs with IRQ off. * Caching the conn in the socket helps a lot. */ - if (rs->rs_conn && ipv6_addr_equal(&rs->rs_conn->c_faddr, &daddr)) + if (rs->rs_conn && ipv6_addr_equal(&rs->rs_conn->c_faddr, &daddr) && + rs->rs_tos == rs->rs_conn->c_tos) { conn = rs->rs_conn; - else { + } else { conn = rds_conn_create_outgoing(sock_net(sock->sk), &rs->rs_bound_addr, &daddr, - rs->rs_transport, + rs->rs_transport, rs->rs_tos, sock->sk->sk_allocation, scope_id); if (IS_ERR(conn)) { diff --git a/net/rds/tcp.c b/net/rds/tcp.c index c16f0a362c32..fd2694174607 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -267,6 +267,7 @@ static void rds_tcp_tc_info(struct socket *rds_sock, unsigned int len, tsinfo.last_sent_nxt = tc->t_last_sent_nxt; tsinfo.last_expected_una = tc->t_last_expected_una; tsinfo.last_seen_una = tc->t_last_seen_una; + tsinfo.tos = tc->t_cpath->cp_conn->c_tos; rds_info_copy(iter, &tsinfo, sizeof(tsinfo)); } @@ -452,6 +453,12 @@ static void rds_tcp_destroy_conns(void) static void rds_tcp_exit(void); +static u8 rds_tcp_get_tos_map(u8 tos) +{ + /* all user tos mapped to default 0 for TCP transport */ + return 0; +} + struct rds_transport rds_tcp_transport = { .laddr_check = rds_tcp_laddr_check, .xmit_path_prepare = rds_tcp_xmit_path_prepare, @@ -466,6 +473,7 @@ struct rds_transport rds_tcp_transport = { .inc_free = rds_tcp_inc_free, .stats_info_copy = rds_tcp_stats_info_copy, .exit = rds_tcp_exit, + .get_tos_map = rds_tcp_get_tos_map, .t_owner = THIS_MODULE, .t_name = "tcp", .t_type = RDS_TRANS_TCP, diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index c12203f646da..810a3a49e947 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -200,7 +200,7 @@ int rds_tcp_accept_one(struct socket *sock) conn = rds_conn_create(sock_net(sock->sk), my_addr, peer_addr, - &rds_tcp_transport, GFP_KERNEL, dev_if); + &rds_tcp_transport, 0, GFP_KERNEL, dev_if); if (IS_ERR(conn)) { ret = PTR_ERR(conn); diff --git a/net/rds/threads.c b/net/rds/threads.c index e64f9e4c3cda..32dc50f0a303 100644 --- a/net/rds/threads.c +++ b/net/rds/threads.c @@ -93,6 +93,7 @@ void rds_connect_path_complete(struct rds_conn_path *cp, int curr) queue_delayed_work(rds_wq, &cp->cp_recv_w, 0); } rcu_read_unlock(); + cp->cp_conn->c_proposed_version = RDS_PROTOCOL_VERSION; } EXPORT_SYMBOL_GPL(rds_connect_path_complete); diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c index 77e9f85a2c92..f2ff21d7df08 100644 --- a/net/rose/rose_route.c +++ b/net/rose/rose_route.c @@ -850,6 +850,7 @@ void rose_link_device_down(struct net_device *dev) /* * Route a frame to an appropriate AX.25 connection. + * A NULL ax25_cb indicates an internally generated frame. */ int rose_route_frame(struct sk_buff *skb, ax25_cb *ax25) { @@ -867,6 +868,10 @@ int rose_route_frame(struct sk_buff *skb, ax25_cb *ax25) if (skb->len < ROSE_MIN_LEN) return res; + + if (!ax25) + return rose_loopback_queue(skb, NULL); + frametype = skb->data[2]; lci = ((skb->data[0] << 8) & 0xF00) + ((skb->data[1] << 0) & 0x0FF); if (frametype == ROSE_CALL_REQUEST && diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 0906e51d3cfb..15cf42d5b53a 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -202,7 +202,7 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net) /* We want receive timestamps. */ opt = 1; - ret = kernel_setsockopt(local->socket, SOL_SOCKET, SO_TIMESTAMPNS, + ret = kernel_setsockopt(local->socket, SOL_SOCKET, SO_TIMESTAMPNS_OLD, (char *)&opt, sizeof(opt)); if (ret < 0) { _debug("setsockopt failed"); diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index eaf19ebaa964..3f7bb11f3290 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -596,6 +596,7 @@ error_requeue_call: } error_no_call: release_sock(&rx->sk); +error_trace: trace_rxrpc_recvmsg(call, rxrpc_recvmsg_return, 0, 0, 0, ret); return ret; @@ -604,7 +605,7 @@ wait_interrupted: wait_error: finish_wait(sk_sleep(&rx->sk), &wait); call = NULL; - goto error_no_call; + goto error_trace; } /** diff --git a/net/sched/act_api.c b/net/sched/act_api.c index d4b8355737d8..aecf1bf233c8 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -543,7 +543,7 @@ int tcf_register_action(struct tc_action_ops *act, write_lock(&act_mod_lock); list_for_each_entry(a, &act_base, head) { - if (act->type == a->type || (strcmp(act->kind, a->kind) == 0)) { + if (act->id == a->id || (strcmp(act->kind, a->kind) == 0)) { write_unlock(&act_mod_lock); unregister_pernet_subsys(ops); return -EEXIST; diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index c7633843e223..aa5c38d11a30 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -396,7 +396,7 @@ static int tcf_bpf_search(struct net *net, struct tc_action **a, u32 index) static struct tc_action_ops act_bpf_ops __read_mostly = { .kind = "bpf", - .type = TCA_ACT_BPF, + .id = TCA_ID_BPF, .owner = THIS_MODULE, .act = tcf_bpf_act, .dump = tcf_bpf_dump, diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 8475913f2070..5d24993cccfe 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -204,7 +204,7 @@ static int tcf_connmark_search(struct net *net, struct tc_action **a, u32 index) static struct tc_action_ops act_connmark_ops = { .kind = "connmark", - .type = TCA_ACT_CONNMARK, + .id = TCA_ID_CONNMARK, .owner = THIS_MODULE, .act = tcf_connmark_act, .dump = tcf_connmark_dump, diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 3dc25b7806d7..945fb34ae721 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -660,7 +660,7 @@ static size_t tcf_csum_get_fill_size(const struct tc_action *act) static struct tc_action_ops act_csum_ops = { .kind = "csum", - .type = TCA_ACT_CSUM, + .id = TCA_ID_CSUM, .owner = THIS_MODULE, .act = tcf_csum_act, .dump = tcf_csum_dump, diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index b61c20ebb314..93da0004e9f4 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -253,7 +253,7 @@ static size_t tcf_gact_get_fill_size(const struct tc_action *act) static struct tc_action_ops act_gact_ops = { .kind = "gact", - .type = TCA_ACT_GACT, + .id = TCA_ID_GACT, .owner = THIS_MODULE, .act = tcf_gact_act, .stats_update = tcf_gact_stats_update, diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 30b63fa23ee2..9b1f2b3990ee 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -864,7 +864,7 @@ static int tcf_ife_search(struct net *net, struct tc_action **a, u32 index) static struct tc_action_ops act_ife_ops = { .kind = "ife", - .type = TCA_ACT_IFE, + .id = TCA_ID_IFE, .owner = THIS_MODULE, .act = tcf_ife_act, .dump = tcf_ife_dump, diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 8af6c11d2482..1bad190710ad 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -338,7 +338,7 @@ static int tcf_ipt_search(struct net *net, struct tc_action **a, u32 index) static struct tc_action_ops act_ipt_ops = { .kind = "ipt", - .type = TCA_ACT_IPT, + .id = TCA_ID_IPT, .owner = THIS_MODULE, .act = tcf_ipt_act, .dump = tcf_ipt_dump, @@ -387,7 +387,7 @@ static int tcf_xt_search(struct net *net, struct tc_action **a, u32 index) static struct tc_action_ops act_xt_ops = { .kind = "xt", - .type = TCA_ACT_XT, + .id = TCA_ID_XT, .owner = THIS_MODULE, .act = tcf_ipt_act, .dump = tcf_ipt_dump, diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index c8cf4d10c435..6692fd054617 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -400,7 +400,7 @@ static void tcf_mirred_put_dev(struct net_device *dev) static struct tc_action_ops act_mirred_ops = { .kind = "mirred", - .type = TCA_ACT_MIRRED, + .id = TCA_ID_MIRRED, .owner = THIS_MODULE, .act = tcf_mirred_act, .stats_update = tcf_stats_update, diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index c5c1e23add77..543eab9193f1 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -304,7 +304,7 @@ static int tcf_nat_search(struct net *net, struct tc_action **a, u32 index) static struct tc_action_ops act_nat_ops = { .kind = "nat", - .type = TCA_ACT_NAT, + .id = TCA_ID_NAT, .owner = THIS_MODULE, .act = tcf_nat_act, .dump = tcf_nat_dump, diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 2b372a06b432..a80373878df7 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -406,7 +406,7 @@ static int tcf_pedit_dump(struct sk_buff *skb, struct tc_action *a, struct tcf_t t; int s; - s = sizeof(*opt) + p->tcfp_nkeys * sizeof(struct tc_pedit_key); + s = struct_size(opt, keys, p->tcfp_nkeys); /* netlink spinlocks held above us - must use ATOMIC */ opt = kzalloc(s, GFP_ATOMIC); @@ -470,7 +470,7 @@ static int tcf_pedit_search(struct net *net, struct tc_action **a, u32 index) static struct tc_action_ops act_pedit_ops = { .kind = "pedit", - .type = TCA_ACT_PEDIT, + .id = TCA_ID_PEDIT, .owner = THIS_MODULE, .act = tcf_pedit_act, .dump = tcf_pedit_dump, diff --git a/net/sched/act_police.c b/net/sched/act_police.c index ec8ec55e0fe8..8271a6263824 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -366,7 +366,7 @@ MODULE_LICENSE("GPL"); static struct tc_action_ops act_police_ops = { .kind = "police", - .type = TCA_ID_POLICE, + .id = TCA_ID_POLICE, .owner = THIS_MODULE, .act = tcf_police_act, .dump = tcf_police_dump, diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 1a0c682fd734..203e399e5c85 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -233,7 +233,7 @@ static int tcf_sample_search(struct net *net, struct tc_action **a, u32 index) static struct tc_action_ops act_sample_ops = { .kind = "sample", - .type = TCA_ACT_SAMPLE, + .id = TCA_ID_SAMPLE, .owner = THIS_MODULE, .act = tcf_sample_act, .dump = tcf_sample_dump, diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 902957beceb3..d54cb608dbaf 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -19,8 +19,6 @@ #include <net/netlink.h> #include <net/pkt_sched.h> -#define TCA_ACT_SIMP 22 - #include <linux/tc_act/tc_defact.h> #include <net/tc_act/tc_defact.h> @@ -197,7 +195,7 @@ static int tcf_simp_search(struct net *net, struct tc_action **a, u32 index) static struct tc_action_ops act_simp_ops = { .kind = "simple", - .type = TCA_ACT_SIMP, + .id = TCA_ID_SIMP, .owner = THIS_MODULE, .act = tcf_simp_act, .dump = tcf_simp_dump, diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 64dba3708fce..39f8a67ea940 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -305,7 +305,7 @@ static int tcf_skbedit_search(struct net *net, struct tc_action **a, u32 index) static struct tc_action_ops act_skbedit_ops = { .kind = "skbedit", - .type = TCA_ACT_SKBEDIT, + .id = TCA_ID_SKBEDIT, .owner = THIS_MODULE, .act = tcf_skbedit_act, .dump = tcf_skbedit_dump, diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index 59710a183bd3..7bac1d78e7a3 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -260,7 +260,7 @@ static int tcf_skbmod_search(struct net *net, struct tc_action **a, u32 index) static struct tc_action_ops act_skbmod_ops = { .kind = "skbmod", - .type = TCA_ACT_SKBMOD, + .id = TCA_ACT_SKBMOD, .owner = THIS_MODULE, .act = tcf_skbmod_act, .dump = tcf_skbmod_dump, diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 8b43fe0130f7..9104b8e36482 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -563,7 +563,7 @@ static int tunnel_key_search(struct net *net, struct tc_action **a, u32 index) static struct tc_action_ops act_tunnel_key_ops = { .kind = "tunnel_key", - .type = TCA_ACT_TUNNEL_KEY, + .id = TCA_ID_TUNNEL_KEY, .owner = THIS_MODULE, .act = tunnel_key_act, .dump = tunnel_key_dump, diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 93fdaf707313..ac0061599225 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -297,7 +297,7 @@ static int tcf_vlan_search(struct net *net, struct tc_action **a, u32 index) static struct tc_action_ops act_vlan_ops = { .kind = "vlan", - .type = TCA_ACT_VLAN, + .id = TCA_ID_VLAN, .owner = THIS_MODULE, .act = tcf_vlan_act, .dump = tcf_vlan_dump, diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index e2b5cb2eb34e..9ad53895e604 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -31,6 +31,13 @@ #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> +#include <net/tc_act/tc_pedit.h> +#include <net/tc_act/tc_mirred.h> +#include <net/tc_act/tc_vlan.h> +#include <net/tc_act/tc_tunnel_key.h> +#include <net/tc_act/tc_csum.h> +#include <net/tc_act/tc_gact.h> +#include <net/tc_act/tc_skbedit.h> extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1]; @@ -61,7 +68,8 @@ static const struct tcf_proto_ops *__tcf_proto_lookup_ops(const char *kind) } static const struct tcf_proto_ops * -tcf_proto_lookup_ops(const char *kind, struct netlink_ext_ack *extack) +tcf_proto_lookup_ops(const char *kind, bool rtnl_held, + struct netlink_ext_ack *extack) { const struct tcf_proto_ops *ops; @@ -69,9 +77,11 @@ tcf_proto_lookup_ops(const char *kind, struct netlink_ext_ack *extack) if (ops) return ops; #ifdef CONFIG_MODULES - rtnl_unlock(); + if (rtnl_held) + rtnl_unlock(); request_module("cls_%s", kind); - rtnl_lock(); + if (rtnl_held) + rtnl_lock(); ops = __tcf_proto_lookup_ops(kind); /* We dropped the RTNL semaphore in order to perform * the module load. So, even if we succeeded in loading @@ -152,8 +162,26 @@ static inline u32 tcf_auto_prio(struct tcf_proto *tp) return TC_H_MAJ(first); } +static bool tcf_proto_is_unlocked(const char *kind) +{ + const struct tcf_proto_ops *ops; + bool ret; + + ops = tcf_proto_lookup_ops(kind, false, NULL); + /* On error return false to take rtnl lock. Proto lookup/create + * functions will perform lookup again and properly handle errors. + */ + if (IS_ERR(ops)) + return false; + + ret = !!(ops->flags & TCF_PROTO_OPS_DOIT_UNLOCKED); + module_put(ops->owner); + return ret; +} + static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol, u32 prio, struct tcf_chain *chain, + bool rtnl_held, struct netlink_ext_ack *extack) { struct tcf_proto *tp; @@ -163,7 +191,7 @@ static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol, if (!tp) return ERR_PTR(-ENOBUFS); - tp->ops = tcf_proto_lookup_ops(kind, extack); + tp->ops = tcf_proto_lookup_ops(kind, rtnl_held, extack); if (IS_ERR(tp->ops)) { err = PTR_ERR(tp->ops); goto errout; @@ -172,6 +200,8 @@ static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol, tp->protocol = protocol; tp->prio = prio; tp->chain = chain; + spin_lock_init(&tp->lock); + refcount_set(&tp->refcnt, 1); err = tp->ops->init(tp); if (err) { @@ -185,14 +215,75 @@ errout: return ERR_PTR(err); } -static void tcf_proto_destroy(struct tcf_proto *tp, +static void tcf_proto_get(struct tcf_proto *tp) +{ + refcount_inc(&tp->refcnt); +} + +static void tcf_chain_put(struct tcf_chain *chain); + +static void tcf_proto_destroy(struct tcf_proto *tp, bool rtnl_held, struct netlink_ext_ack *extack) { - tp->ops->destroy(tp, extack); + tp->ops->destroy(tp, rtnl_held, extack); + tcf_chain_put(tp->chain); module_put(tp->ops->owner); kfree_rcu(tp, rcu); } +static void tcf_proto_put(struct tcf_proto *tp, bool rtnl_held, + struct netlink_ext_ack *extack) +{ + if (refcount_dec_and_test(&tp->refcnt)) + tcf_proto_destroy(tp, rtnl_held, extack); +} + +static int walker_noop(struct tcf_proto *tp, void *d, struct tcf_walker *arg) +{ + return -1; +} + +static bool tcf_proto_is_empty(struct tcf_proto *tp, bool rtnl_held) +{ + struct tcf_walker walker = { .fn = walker_noop, }; + + if (tp->ops->walk) { + tp->ops->walk(tp, &walker, rtnl_held); + return !walker.stop; + } + return true; +} + +static bool tcf_proto_check_delete(struct tcf_proto *tp, bool rtnl_held) +{ + spin_lock(&tp->lock); + if (tcf_proto_is_empty(tp, rtnl_held)) + tp->deleting = true; + spin_unlock(&tp->lock); + return tp->deleting; +} + +static void tcf_proto_mark_delete(struct tcf_proto *tp) +{ + spin_lock(&tp->lock); + tp->deleting = true; + spin_unlock(&tp->lock); +} + +static bool tcf_proto_is_deleting(struct tcf_proto *tp) +{ + bool deleting; + + spin_lock(&tp->lock); + deleting = tp->deleting; + spin_unlock(&tp->lock); + + return deleting; +} + +#define ASSERT_BLOCK_LOCKED(block) \ + lockdep_assert_held(&(block)->lock) + struct tcf_filter_chain_list_item { struct list_head list; tcf_chain_head_change_t *chain_head_change; @@ -204,10 +295,13 @@ static struct tcf_chain *tcf_chain_create(struct tcf_block *block, { struct tcf_chain *chain; + ASSERT_BLOCK_LOCKED(block); + chain = kzalloc(sizeof(*chain), GFP_KERNEL); if (!chain) return NULL; list_add_tail(&chain->list, &block->chain_list); + mutex_init(&chain->filter_chain_lock); chain->block = block; chain->index = chain_index; chain->refcnt = 1; @@ -231,29 +325,59 @@ static void tcf_chain0_head_change(struct tcf_chain *chain, if (chain->index) return; + + mutex_lock(&block->lock); list_for_each_entry(item, &block->chain0.filter_chain_list, list) tcf_chain_head_change_item(item, tp_head); + mutex_unlock(&block->lock); } -static void tcf_chain_destroy(struct tcf_chain *chain) +/* Returns true if block can be safely freed. */ + +static bool tcf_chain_detach(struct tcf_chain *chain) { struct tcf_block *block = chain->block; + ASSERT_BLOCK_LOCKED(block); + list_del(&chain->list); if (!chain->index) block->chain0.chain = NULL; + + if (list_empty(&block->chain_list) && + refcount_read(&block->refcnt) == 0) + return true; + + return false; +} + +static void tcf_block_destroy(struct tcf_block *block) +{ + mutex_destroy(&block->lock); + kfree_rcu(block, rcu); +} + +static void tcf_chain_destroy(struct tcf_chain *chain, bool free_block) +{ + struct tcf_block *block = chain->block; + + mutex_destroy(&chain->filter_chain_lock); kfree(chain); - if (list_empty(&block->chain_list) && !refcount_read(&block->refcnt)) - kfree_rcu(block, rcu); + if (free_block) + tcf_block_destroy(block); } static void tcf_chain_hold(struct tcf_chain *chain) { + ASSERT_BLOCK_LOCKED(chain->block); + ++chain->refcnt; } static bool tcf_chain_held_by_acts_only(struct tcf_chain *chain) { + ASSERT_BLOCK_LOCKED(chain->block); + /* In case all the references are action references, this * chain should not be shown to the user. */ @@ -265,6 +389,8 @@ static struct tcf_chain *tcf_chain_lookup(struct tcf_block *block, { struct tcf_chain *chain; + ASSERT_BLOCK_LOCKED(block); + list_for_each_entry(chain, &block->chain_list, list) { if (chain->index == chain_index) return chain; @@ -279,31 +405,40 @@ static struct tcf_chain *__tcf_chain_get(struct tcf_block *block, u32 chain_index, bool create, bool by_act) { - struct tcf_chain *chain = tcf_chain_lookup(block, chain_index); + struct tcf_chain *chain = NULL; + bool is_first_reference; + mutex_lock(&block->lock); + chain = tcf_chain_lookup(block, chain_index); if (chain) { tcf_chain_hold(chain); } else { if (!create) - return NULL; + goto errout; chain = tcf_chain_create(block, chain_index); if (!chain) - return NULL; + goto errout; } if (by_act) ++chain->action_refcnt; + is_first_reference = chain->refcnt - chain->action_refcnt == 1; + mutex_unlock(&block->lock); /* Send notification only in case we got the first * non-action reference. Until then, the chain acts only as * a placeholder for actions pointing to it and user ought * not know about them. */ - if (chain->refcnt - chain->action_refcnt == 1 && !by_act) + if (is_first_reference && !by_act) tc_chain_notify(chain, NULL, 0, NLM_F_CREATE | NLM_F_EXCL, RTM_NEWCHAIN, false); return chain; + +errout: + mutex_unlock(&block->lock); + return chain; } static struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index, @@ -318,51 +453,94 @@ struct tcf_chain *tcf_chain_get_by_act(struct tcf_block *block, u32 chain_index) } EXPORT_SYMBOL(tcf_chain_get_by_act); -static void tc_chain_tmplt_del(struct tcf_chain *chain); +static void tc_chain_tmplt_del(const struct tcf_proto_ops *tmplt_ops, + void *tmplt_priv); +static int tc_chain_notify_delete(const struct tcf_proto_ops *tmplt_ops, + void *tmplt_priv, u32 chain_index, + struct tcf_block *block, struct sk_buff *oskb, + u32 seq, u16 flags, bool unicast); -static void __tcf_chain_put(struct tcf_chain *chain, bool by_act) +static void __tcf_chain_put(struct tcf_chain *chain, bool by_act, + bool explicitly_created) { + struct tcf_block *block = chain->block; + const struct tcf_proto_ops *tmplt_ops; + bool is_last, free_block = false; + unsigned int refcnt; + void *tmplt_priv; + u32 chain_index; + + mutex_lock(&block->lock); + if (explicitly_created) { + if (!chain->explicitly_created) { + mutex_unlock(&block->lock); + return; + } + chain->explicitly_created = false; + } + if (by_act) chain->action_refcnt--; - chain->refcnt--; + + /* tc_chain_notify_delete can't be called while holding block lock. + * However, when block is unlocked chain can be changed concurrently, so + * save these to temporary variables. + */ + refcnt = --chain->refcnt; + is_last = refcnt - chain->action_refcnt == 0; + tmplt_ops = chain->tmplt_ops; + tmplt_priv = chain->tmplt_priv; + chain_index = chain->index; + + if (refcnt == 0) + free_block = tcf_chain_detach(chain); + mutex_unlock(&block->lock); /* The last dropped non-action reference will trigger notification. */ - if (chain->refcnt - chain->action_refcnt == 0 && !by_act) - tc_chain_notify(chain, NULL, 0, 0, RTM_DELCHAIN, false); + if (is_last && !by_act) { + tc_chain_notify_delete(tmplt_ops, tmplt_priv, chain_index, + block, NULL, 0, 0, false); + /* Last reference to chain, no need to lock. */ + chain->flushing = false; + } - if (chain->refcnt == 0) { - tc_chain_tmplt_del(chain); - tcf_chain_destroy(chain); + if (refcnt == 0) { + tc_chain_tmplt_del(tmplt_ops, tmplt_priv); + tcf_chain_destroy(chain, free_block); } } static void tcf_chain_put(struct tcf_chain *chain) { - __tcf_chain_put(chain, false); + __tcf_chain_put(chain, false, false); } void tcf_chain_put_by_act(struct tcf_chain *chain) { - __tcf_chain_put(chain, true); + __tcf_chain_put(chain, true, false); } EXPORT_SYMBOL(tcf_chain_put_by_act); static void tcf_chain_put_explicitly_created(struct tcf_chain *chain) { - if (chain->explicitly_created) - tcf_chain_put(chain); + __tcf_chain_put(chain, false, true); } -static void tcf_chain_flush(struct tcf_chain *chain) +static void tcf_chain_flush(struct tcf_chain *chain, bool rtnl_held) { - struct tcf_proto *tp = rtnl_dereference(chain->filter_chain); + struct tcf_proto *tp, *tp_next; + mutex_lock(&chain->filter_chain_lock); + tp = tcf_chain_dereference(chain->filter_chain, chain); + RCU_INIT_POINTER(chain->filter_chain, NULL); tcf_chain0_head_change(chain, NULL); + chain->flushing = true; + mutex_unlock(&chain->filter_chain_lock); + while (tp) { - RCU_INIT_POINTER(chain->filter_chain, tp->next); - tcf_proto_destroy(tp, NULL); - tp = rtnl_dereference(chain->filter_chain); - tcf_chain_put(chain); + tp_next = rcu_dereference_protected(tp->next, 1); + tcf_proto_put(tp, rtnl_held, NULL); + tp = tp_next; } } @@ -684,8 +862,8 @@ tcf_chain0_head_change_cb_add(struct tcf_block *block, struct tcf_block_ext_info *ei, struct netlink_ext_ack *extack) { - struct tcf_chain *chain0 = block->chain0.chain; struct tcf_filter_chain_list_item *item; + struct tcf_chain *chain0; item = kmalloc(sizeof(*item), GFP_KERNEL); if (!item) { @@ -694,9 +872,32 @@ tcf_chain0_head_change_cb_add(struct tcf_block *block, } item->chain_head_change = ei->chain_head_change; item->chain_head_change_priv = ei->chain_head_change_priv; - if (chain0 && chain0->filter_chain) - tcf_chain_head_change_item(item, chain0->filter_chain); - list_add(&item->list, &block->chain0.filter_chain_list); + + mutex_lock(&block->lock); + chain0 = block->chain0.chain; + if (chain0) + tcf_chain_hold(chain0); + else + list_add(&item->list, &block->chain0.filter_chain_list); + mutex_unlock(&block->lock); + + if (chain0) { + struct tcf_proto *tp_head; + + mutex_lock(&chain0->filter_chain_lock); + + tp_head = tcf_chain_dereference(chain0->filter_chain, chain0); + if (tp_head) + tcf_chain_head_change_item(item, tp_head); + + mutex_lock(&block->lock); + list_add(&item->list, &block->chain0.filter_chain_list); + mutex_unlock(&block->lock); + + mutex_unlock(&chain0->filter_chain_lock); + tcf_chain_put(chain0); + } + return 0; } @@ -704,20 +905,23 @@ static void tcf_chain0_head_change_cb_del(struct tcf_block *block, struct tcf_block_ext_info *ei) { - struct tcf_chain *chain0 = block->chain0.chain; struct tcf_filter_chain_list_item *item; + mutex_lock(&block->lock); list_for_each_entry(item, &block->chain0.filter_chain_list, list) { if ((!ei->chain_head_change && !ei->chain_head_change_priv) || (item->chain_head_change == ei->chain_head_change && item->chain_head_change_priv == ei->chain_head_change_priv)) { - if (chain0) + if (block->chain0.chain) tcf_chain_head_change_item(item, NULL); list_del(&item->list); + mutex_unlock(&block->lock); + kfree(item); return; } } + mutex_unlock(&block->lock); WARN_ON(1); } @@ -764,6 +968,7 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q, NL_SET_ERR_MSG(extack, "Memory allocation for block failed"); return ERR_PTR(-ENOMEM); } + mutex_init(&block->lock); INIT_LIST_HEAD(&block->chain_list); INIT_LIST_HEAD(&block->cb_list); INIT_LIST_HEAD(&block->owner_list); @@ -799,157 +1004,241 @@ static struct tcf_block *tcf_block_refcnt_get(struct net *net, u32 block_index) return block; } -static void tcf_block_flush_all_chains(struct tcf_block *block) +static struct tcf_chain * +__tcf_get_next_chain(struct tcf_block *block, struct tcf_chain *chain) { - struct tcf_chain *chain; + mutex_lock(&block->lock); + if (chain) + chain = list_is_last(&chain->list, &block->chain_list) ? + NULL : list_next_entry(chain, list); + else + chain = list_first_entry_or_null(&block->chain_list, + struct tcf_chain, list); - /* Hold a refcnt for all chains, so that they don't disappear - * while we are iterating. - */ - list_for_each_entry(chain, &block->chain_list, list) + /* skip all action-only chains */ + while (chain && tcf_chain_held_by_acts_only(chain)) + chain = list_is_last(&chain->list, &block->chain_list) ? + NULL : list_next_entry(chain, list); + + if (chain) tcf_chain_hold(chain); + mutex_unlock(&block->lock); - list_for_each_entry(chain, &block->chain_list, list) - tcf_chain_flush(chain); + return chain; } -static void tcf_block_put_all_chains(struct tcf_block *block) +/* Function to be used by all clients that want to iterate over all chains on + * block. It properly obtains block->lock and takes reference to chain before + * returning it. Users of this function must be tolerant to concurrent chain + * insertion/deletion or ensure that no concurrent chain modification is + * possible. Note that all netlink dump callbacks cannot guarantee to provide + * consistent dump because rtnl lock is released each time skb is filled with + * data and sent to user-space. + */ + +struct tcf_chain * +tcf_get_next_chain(struct tcf_block *block, struct tcf_chain *chain) { - struct tcf_chain *chain, *tmp; + struct tcf_chain *chain_next = __tcf_get_next_chain(block, chain); - /* At this point, all the chains should have refcnt >= 1. */ - list_for_each_entry_safe(chain, tmp, &block->chain_list, list) { - tcf_chain_put_explicitly_created(chain); + if (chain) tcf_chain_put(chain); - } + + return chain_next; } +EXPORT_SYMBOL(tcf_get_next_chain); -static void __tcf_block_put(struct tcf_block *block, struct Qdisc *q, - struct tcf_block_ext_info *ei) +static struct tcf_proto * +__tcf_get_next_proto(struct tcf_chain *chain, struct tcf_proto *tp) { - if (refcount_dec_and_test(&block->refcnt)) { - /* Flushing/putting all chains will cause the block to be - * deallocated when last chain is freed. However, if chain_list - * is empty, block has to be manually deallocated. After block - * reference counter reached 0, it is no longer possible to - * increment it or add new chains to block. - */ - bool free_block = list_empty(&block->chain_list); + u32 prio = 0; - if (tcf_block_shared(block)) - tcf_block_remove(block, block->net); - if (!free_block) - tcf_block_flush_all_chains(block); + ASSERT_RTNL(); + mutex_lock(&chain->filter_chain_lock); - if (q) - tcf_block_offload_unbind(block, q, ei); + if (!tp) { + tp = tcf_chain_dereference(chain->filter_chain, chain); + } else if (tcf_proto_is_deleting(tp)) { + /* 'deleting' flag is set and chain->filter_chain_lock was + * unlocked, which means next pointer could be invalid. Restart + * search. + */ + prio = tp->prio + 1; + tp = tcf_chain_dereference(chain->filter_chain, chain); - if (free_block) - kfree_rcu(block, rcu); - else - tcf_block_put_all_chains(block); - } else if (q) { - tcf_block_offload_unbind(block, q, ei); + for (; tp; tp = tcf_chain_dereference(tp->next, chain)) + if (!tp->deleting && tp->prio >= prio) + break; + } else { + tp = tcf_chain_dereference(tp->next, chain); } + + if (tp) + tcf_proto_get(tp); + + mutex_unlock(&chain->filter_chain_lock); + + return tp; } -static void tcf_block_refcnt_put(struct tcf_block *block) +/* Function to be used by all clients that want to iterate over all tp's on + * chain. Users of this function must be tolerant to concurrent tp + * insertion/deletion or ensure that no concurrent chain modification is + * possible. Note that all netlink dump callbacks cannot guarantee to provide + * consistent dump because rtnl lock is released each time skb is filled with + * data and sent to user-space. + */ + +struct tcf_proto * +tcf_get_next_proto(struct tcf_chain *chain, struct tcf_proto *tp, + bool rtnl_held) { - __tcf_block_put(block, NULL, NULL); + struct tcf_proto *tp_next = __tcf_get_next_proto(chain, tp); + + if (tp) + tcf_proto_put(tp, rtnl_held, NULL); + + return tp_next; } +EXPORT_SYMBOL(tcf_get_next_proto); -/* Find tcf block. - * Set q, parent, cl when appropriate. +static void tcf_block_flush_all_chains(struct tcf_block *block, bool rtnl_held) +{ + struct tcf_chain *chain; + + /* Last reference to block. At this point chains cannot be added or + * removed concurrently. + */ + for (chain = tcf_get_next_chain(block, NULL); + chain; + chain = tcf_get_next_chain(block, chain)) { + tcf_chain_put_explicitly_created(chain); + tcf_chain_flush(chain, rtnl_held); + } +} + +/* Lookup Qdisc and increments its reference counter. + * Set parent, if necessary. */ -static struct tcf_block *tcf_block_find(struct net *net, struct Qdisc **q, - u32 *parent, unsigned long *cl, - int ifindex, u32 block_index, - struct netlink_ext_ack *extack) +static int __tcf_qdisc_find(struct net *net, struct Qdisc **q, + u32 *parent, int ifindex, bool rtnl_held, + struct netlink_ext_ack *extack) { - struct tcf_block *block; + const struct Qdisc_class_ops *cops; + struct net_device *dev; int err = 0; - if (ifindex == TCM_IFINDEX_MAGIC_BLOCK) { - block = tcf_block_refcnt_get(net, block_index); - if (!block) { - NL_SET_ERR_MSG(extack, "Block of given index was not found"); - return ERR_PTR(-EINVAL); - } - } else { - const struct Qdisc_class_ops *cops; - struct net_device *dev; - - rcu_read_lock(); + if (ifindex == TCM_IFINDEX_MAGIC_BLOCK) + return 0; - /* Find link */ - dev = dev_get_by_index_rcu(net, ifindex); - if (!dev) { - rcu_read_unlock(); - return ERR_PTR(-ENODEV); - } + rcu_read_lock(); - /* Find qdisc */ - if (!*parent) { - *q = dev->qdisc; - *parent = (*q)->handle; - } else { - *q = qdisc_lookup_rcu(dev, TC_H_MAJ(*parent)); - if (!*q) { - NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists"); - err = -EINVAL; - goto errout_rcu; - } - } + /* Find link */ + dev = dev_get_by_index_rcu(net, ifindex); + if (!dev) { + rcu_read_unlock(); + return -ENODEV; + } - *q = qdisc_refcount_inc_nz(*q); + /* Find qdisc */ + if (!*parent) { + *q = dev->qdisc; + *parent = (*q)->handle; + } else { + *q = qdisc_lookup_rcu(dev, TC_H_MAJ(*parent)); if (!*q) { NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists"); err = -EINVAL; goto errout_rcu; } + } - /* Is it classful? */ - cops = (*q)->ops->cl_ops; - if (!cops) { - NL_SET_ERR_MSG(extack, "Qdisc not classful"); - err = -EINVAL; - goto errout_rcu; - } + *q = qdisc_refcount_inc_nz(*q); + if (!*q) { + NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists"); + err = -EINVAL; + goto errout_rcu; + } - if (!cops->tcf_block) { - NL_SET_ERR_MSG(extack, "Class doesn't support blocks"); - err = -EOPNOTSUPP; - goto errout_rcu; - } + /* Is it classful? */ + cops = (*q)->ops->cl_ops; + if (!cops) { + NL_SET_ERR_MSG(extack, "Qdisc not classful"); + err = -EINVAL; + goto errout_qdisc; + } - /* At this point we know that qdisc is not noop_qdisc, - * which means that qdisc holds a reference to net_device - * and we hold a reference to qdisc, so it is safe to release - * rcu read lock. - */ - rcu_read_unlock(); + if (!cops->tcf_block) { + NL_SET_ERR_MSG(extack, "Class doesn't support blocks"); + err = -EOPNOTSUPP; + goto errout_qdisc; + } - /* Do we search for filter, attached to class? */ - if (TC_H_MIN(*parent)) { - *cl = cops->find(*q, *parent); - if (*cl == 0) { - NL_SET_ERR_MSG(extack, "Specified class doesn't exist"); - err = -ENOENT; - goto errout_qdisc; - } +errout_rcu: + /* At this point we know that qdisc is not noop_qdisc, + * which means that qdisc holds a reference to net_device + * and we hold a reference to qdisc, so it is safe to release + * rcu read lock. + */ + rcu_read_unlock(); + return err; + +errout_qdisc: + rcu_read_unlock(); + + if (rtnl_held) + qdisc_put(*q); + else + qdisc_put_unlocked(*q); + *q = NULL; + + return err; +} + +static int __tcf_qdisc_cl_find(struct Qdisc *q, u32 parent, unsigned long *cl, + int ifindex, struct netlink_ext_ack *extack) +{ + if (ifindex == TCM_IFINDEX_MAGIC_BLOCK) + return 0; + + /* Do we search for filter, attached to class? */ + if (TC_H_MIN(parent)) { + const struct Qdisc_class_ops *cops = q->ops->cl_ops; + + *cl = cops->find(q, parent); + if (*cl == 0) { + NL_SET_ERR_MSG(extack, "Specified class doesn't exist"); + return -ENOENT; } + } - /* And the last stroke */ - block = cops->tcf_block(*q, *cl, extack); + return 0; +} + +static struct tcf_block *__tcf_block_find(struct net *net, struct Qdisc *q, + unsigned long cl, int ifindex, + u32 block_index, + struct netlink_ext_ack *extack) +{ + struct tcf_block *block; + + if (ifindex == TCM_IFINDEX_MAGIC_BLOCK) { + block = tcf_block_refcnt_get(net, block_index); if (!block) { - err = -EINVAL; - goto errout_qdisc; + NL_SET_ERR_MSG(extack, "Block of given index was not found"); + return ERR_PTR(-EINVAL); } + } else { + const struct Qdisc_class_ops *cops = q->ops->cl_ops; + + block = cops->tcf_block(q, cl, extack); + if (!block) + return ERR_PTR(-EINVAL); + if (tcf_block_shared(block)) { NL_SET_ERR_MSG(extack, "This filter block is shared. Please use the block index to manipulate the filters"); - err = -EOPNOTSUPP; - goto errout_qdisc; + return ERR_PTR(-EOPNOTSUPP); } /* Always take reference to block in order to support execution @@ -962,24 +1251,89 @@ static struct tcf_block *tcf_block_find(struct net *net, struct Qdisc **q, } return block; +} + +static void __tcf_block_put(struct tcf_block *block, struct Qdisc *q, + struct tcf_block_ext_info *ei, bool rtnl_held) +{ + if (refcount_dec_and_mutex_lock(&block->refcnt, &block->lock)) { + /* Flushing/putting all chains will cause the block to be + * deallocated when last chain is freed. However, if chain_list + * is empty, block has to be manually deallocated. After block + * reference counter reached 0, it is no longer possible to + * increment it or add new chains to block. + */ + bool free_block = list_empty(&block->chain_list); + + mutex_unlock(&block->lock); + if (tcf_block_shared(block)) + tcf_block_remove(block, block->net); + + if (q) + tcf_block_offload_unbind(block, q, ei); + + if (free_block) + tcf_block_destroy(block); + else + tcf_block_flush_all_chains(block, rtnl_held); + } else if (q) { + tcf_block_offload_unbind(block, q, ei); + } +} + +static void tcf_block_refcnt_put(struct tcf_block *block, bool rtnl_held) +{ + __tcf_block_put(block, NULL, NULL, rtnl_held); +} + +/* Find tcf block. + * Set q, parent, cl when appropriate. + */ + +static struct tcf_block *tcf_block_find(struct net *net, struct Qdisc **q, + u32 *parent, unsigned long *cl, + int ifindex, u32 block_index, + struct netlink_ext_ack *extack) +{ + struct tcf_block *block; + int err = 0; + + ASSERT_RTNL(); + + err = __tcf_qdisc_find(net, q, parent, ifindex, true, extack); + if (err) + goto errout; + + err = __tcf_qdisc_cl_find(*q, *parent, cl, ifindex, extack); + if (err) + goto errout_qdisc; + + block = __tcf_block_find(net, *q, *cl, ifindex, block_index, extack); + if (IS_ERR(block)) + goto errout_qdisc; + + return block; -errout_rcu: - rcu_read_unlock(); errout_qdisc: - if (*q) { + if (*q) qdisc_put(*q); - *q = NULL; - } +errout: + *q = NULL; return ERR_PTR(err); } -static void tcf_block_release(struct Qdisc *q, struct tcf_block *block) +static void tcf_block_release(struct Qdisc *q, struct tcf_block *block, + bool rtnl_held) { if (!IS_ERR_OR_NULL(block)) - tcf_block_refcnt_put(block); + tcf_block_refcnt_put(block, rtnl_held); - if (q) - qdisc_put(q); + if (q) { + if (rtnl_held) + qdisc_put(q); + else + qdisc_put_unlocked(q); + } } struct tcf_block_owner_item { @@ -1087,7 +1441,7 @@ err_chain0_head_change_cb_add: tcf_block_owner_del(block, q, ei->binder_type); err_block_owner_add: err_block_insert: - tcf_block_refcnt_put(block); + tcf_block_refcnt_put(block, true); return err; } EXPORT_SYMBOL(tcf_block_get_ext); @@ -1124,7 +1478,7 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q, tcf_chain0_head_change_cb_del(block, ei); tcf_block_owner_del(block, q, ei->binder_type); - __tcf_block_put(block, q, ei); + __tcf_block_put(block, q, ei, true); } EXPORT_SYMBOL(tcf_block_put_ext); @@ -1181,13 +1535,19 @@ tcf_block_playback_offloads(struct tcf_block *block, tc_setup_cb_t *cb, void *cb_priv, bool add, bool offload_in_use, struct netlink_ext_ack *extack) { - struct tcf_chain *chain; - struct tcf_proto *tp; + struct tcf_chain *chain, *chain_prev; + struct tcf_proto *tp, *tp_prev; int err; - list_for_each_entry(chain, &block->chain_list, list) { - for (tp = rtnl_dereference(chain->filter_chain); tp; - tp = rtnl_dereference(tp->next)) { + for (chain = __tcf_get_next_chain(block, NULL); + chain; + chain_prev = chain, + chain = __tcf_get_next_chain(block, chain), + tcf_chain_put(chain_prev)) { + for (tp = __tcf_get_next_proto(chain, NULL); tp; + tp_prev = tp, + tp = __tcf_get_next_proto(chain, tp), + tcf_proto_put(tp_prev, true, NULL)) { if (tp->ops->reoffload) { err = tp->ops->reoffload(tp, add, cb, cb_priv, extack); @@ -1204,6 +1564,8 @@ tcf_block_playback_offloads(struct tcf_block *block, tc_setup_cb_t *cb, return 0; err_playback_remove: + tcf_proto_put(tp, true, NULL); + tcf_chain_put(chain); tcf_block_playback_offloads(block, cb, cb_priv, false, offload_in_use, extack); return err; @@ -1329,32 +1691,116 @@ struct tcf_chain_info { struct tcf_proto __rcu *next; }; -static struct tcf_proto *tcf_chain_tp_prev(struct tcf_chain_info *chain_info) +static struct tcf_proto *tcf_chain_tp_prev(struct tcf_chain *chain, + struct tcf_chain_info *chain_info) { - return rtnl_dereference(*chain_info->pprev); + return tcf_chain_dereference(*chain_info->pprev, chain); } -static void tcf_chain_tp_insert(struct tcf_chain *chain, - struct tcf_chain_info *chain_info, - struct tcf_proto *tp) +static int tcf_chain_tp_insert(struct tcf_chain *chain, + struct tcf_chain_info *chain_info, + struct tcf_proto *tp) { + if (chain->flushing) + return -EAGAIN; + if (*chain_info->pprev == chain->filter_chain) tcf_chain0_head_change(chain, tp); - RCU_INIT_POINTER(tp->next, tcf_chain_tp_prev(chain_info)); + tcf_proto_get(tp); + RCU_INIT_POINTER(tp->next, tcf_chain_tp_prev(chain, chain_info)); rcu_assign_pointer(*chain_info->pprev, tp); - tcf_chain_hold(chain); + + return 0; } static void tcf_chain_tp_remove(struct tcf_chain *chain, struct tcf_chain_info *chain_info, struct tcf_proto *tp) { - struct tcf_proto *next = rtnl_dereference(chain_info->next); + struct tcf_proto *next = tcf_chain_dereference(chain_info->next, chain); + tcf_proto_mark_delete(tp); if (tp == chain->filter_chain) tcf_chain0_head_change(chain, next); RCU_INIT_POINTER(*chain_info->pprev, next); - tcf_chain_put(chain); +} + +static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain, + struct tcf_chain_info *chain_info, + u32 protocol, u32 prio, + bool prio_allocate); + +/* Try to insert new proto. + * If proto with specified priority already exists, free new proto + * and return existing one. + */ + +static struct tcf_proto *tcf_chain_tp_insert_unique(struct tcf_chain *chain, + struct tcf_proto *tp_new, + u32 protocol, u32 prio, + bool rtnl_held) +{ + struct tcf_chain_info chain_info; + struct tcf_proto *tp; + int err = 0; + + mutex_lock(&chain->filter_chain_lock); + + tp = tcf_chain_tp_find(chain, &chain_info, + protocol, prio, false); + if (!tp) + err = tcf_chain_tp_insert(chain, &chain_info, tp_new); + mutex_unlock(&chain->filter_chain_lock); + + if (tp) { + tcf_proto_destroy(tp_new, rtnl_held, NULL); + tp_new = tp; + } else if (err) { + tcf_proto_destroy(tp_new, rtnl_held, NULL); + tp_new = ERR_PTR(err); + } + + return tp_new; +} + +static void tcf_chain_tp_delete_empty(struct tcf_chain *chain, + struct tcf_proto *tp, bool rtnl_held, + struct netlink_ext_ack *extack) +{ + struct tcf_chain_info chain_info; + struct tcf_proto *tp_iter; + struct tcf_proto **pprev; + struct tcf_proto *next; + + mutex_lock(&chain->filter_chain_lock); + + /* Atomically find and remove tp from chain. */ + for (pprev = &chain->filter_chain; + (tp_iter = tcf_chain_dereference(*pprev, chain)); + pprev = &tp_iter->next) { + if (tp_iter == tp) { + chain_info.pprev = pprev; + chain_info.next = tp_iter->next; + WARN_ON(tp_iter->deleting); + break; + } + } + /* Verify that tp still exists and no new filters were inserted + * concurrently. + * Mark tp for deletion if it is empty. + */ + if (!tp_iter || !tcf_proto_check_delete(tp, rtnl_held)) { + mutex_unlock(&chain->filter_chain_lock); + return; + } + + next = tcf_chain_dereference(chain_info.next, chain); + if (tp == chain->filter_chain) + tcf_chain0_head_change(chain, next); + RCU_INIT_POINTER(*chain_info.pprev, next); + mutex_unlock(&chain->filter_chain_lock); + + tcf_proto_put(tp, rtnl_held, extack); } static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain, @@ -1367,7 +1813,8 @@ static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain, /* Check the chain for existence of proto-tcf with this priority */ for (pprev = &chain->filter_chain; - (tp = rtnl_dereference(*pprev)); pprev = &tp->next) { + (tp = tcf_chain_dereference(*pprev, chain)); + pprev = &tp->next) { if (tp->prio >= prio) { if (tp->prio == prio) { if (prio_allocate || @@ -1380,14 +1827,20 @@ static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain, } } chain_info->pprev = pprev; - chain_info->next = tp ? tp->next : NULL; + if (tp) { + chain_info->next = tp->next; + tcf_proto_get(tp); + } else { + chain_info->next = NULL; + } return tp; } static int tcf_fill_node(struct net *net, struct sk_buff *skb, struct tcf_proto *tp, struct tcf_block *block, struct Qdisc *q, u32 parent, void *fh, - u32 portid, u32 seq, u16 flags, int event) + u32 portid, u32 seq, u16 flags, int event, + bool rtnl_held) { struct tcmsg *tcm; struct nlmsghdr *nlh; @@ -1415,7 +1868,8 @@ static int tcf_fill_node(struct net *net, struct sk_buff *skb, if (!fh) { tcm->tcm_handle = 0; } else { - if (tp->ops->dump && tp->ops->dump(net, tp, fh, skb, tcm) < 0) + if (tp->ops->dump && + tp->ops->dump(net, tp, fh, skb, tcm, rtnl_held) < 0) goto nla_put_failure; } nlh->nlmsg_len = skb_tail_pointer(skb) - b; @@ -1430,7 +1884,8 @@ nla_put_failure: static int tfilter_notify(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, struct tcf_proto *tp, struct tcf_block *block, struct Qdisc *q, - u32 parent, void *fh, int event, bool unicast) + u32 parent, void *fh, int event, bool unicast, + bool rtnl_held) { struct sk_buff *skb; u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; @@ -1440,7 +1895,8 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb, return -ENOBUFS; if (tcf_fill_node(net, skb, tp, block, q, parent, fh, portid, - n->nlmsg_seq, n->nlmsg_flags, event) <= 0) { + n->nlmsg_seq, n->nlmsg_flags, event, + rtnl_held) <= 0) { kfree_skb(skb); return -EINVAL; } @@ -1456,7 +1912,7 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, struct tcf_proto *tp, struct tcf_block *block, struct Qdisc *q, u32 parent, void *fh, bool unicast, bool *last, - struct netlink_ext_ack *extack) + bool rtnl_held, struct netlink_ext_ack *extack) { struct sk_buff *skb; u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; @@ -1467,13 +1923,14 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb, return -ENOBUFS; if (tcf_fill_node(net, skb, tp, block, q, parent, fh, portid, - n->nlmsg_seq, n->nlmsg_flags, RTM_DELTFILTER) <= 0) { + n->nlmsg_seq, n->nlmsg_flags, RTM_DELTFILTER, + rtnl_held) <= 0) { NL_SET_ERR_MSG(extack, "Failed to build del event notification"); kfree_skb(skb); return -EINVAL; } - err = tp->ops->delete(tp, fh, last, extack); + err = tp->ops->delete(tp, fh, last, rtnl_held, extack); if (err) { kfree_skb(skb); return err; @@ -1492,14 +1949,21 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb, static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb, struct tcf_block *block, struct Qdisc *q, u32 parent, struct nlmsghdr *n, - struct tcf_chain *chain, int event) + struct tcf_chain *chain, int event, + bool rtnl_held) { struct tcf_proto *tp; - for (tp = rtnl_dereference(chain->filter_chain); - tp; tp = rtnl_dereference(tp->next)) + for (tp = tcf_get_next_proto(chain, NULL, rtnl_held); + tp; tp = tcf_get_next_proto(chain, tp, rtnl_held)) tfilter_notify(net, oskb, n, tp, block, - q, parent, NULL, event, false); + q, parent, NULL, event, false, rtnl_held); +} + +static void tfilter_put(struct tcf_proto *tp, void *fh) +{ + if (tp->ops->put && fh) + tp->ops->put(tp, fh); } static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n, @@ -1522,6 +1986,7 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n, void *fh; int err; int tp_created; + bool rtnl_held = false; if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) return -EPERM; @@ -1538,7 +2003,9 @@ replay: prio = TC_H_MAJ(t->tcm_info); prio_allocate = false; parent = t->tcm_parent; + tp = NULL; cl = 0; + block = NULL; if (prio == 0) { /* If no priority is provided by the user, @@ -1555,8 +2022,27 @@ replay: /* Find head of filter chain. */ - block = tcf_block_find(net, &q, &parent, &cl, - t->tcm_ifindex, t->tcm_block_index, extack); + err = __tcf_qdisc_find(net, &q, &parent, t->tcm_ifindex, false, extack); + if (err) + return err; + + /* Take rtnl mutex if rtnl_held was set to true on previous iteration, + * block is shared (no qdisc found), qdisc is not unlocked, classifier + * type is not specified, classifier is not unlocked. + */ + if (rtnl_held || + (q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) || + !tca[TCA_KIND] || !tcf_proto_is_unlocked(nla_data(tca[TCA_KIND]))) { + rtnl_held = true; + rtnl_lock(); + } + + err = __tcf_qdisc_cl_find(q, parent, &cl, t->tcm_ifindex, extack); + if (err) + goto errout; + + block = __tcf_block_find(net, q, cl, t->tcm_ifindex, t->tcm_block_index, + extack); if (IS_ERR(block)) { err = PTR_ERR(block); goto errout; @@ -1575,40 +2061,62 @@ replay: goto errout; } + mutex_lock(&chain->filter_chain_lock); tp = tcf_chain_tp_find(chain, &chain_info, protocol, prio, prio_allocate); if (IS_ERR(tp)) { NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found"); err = PTR_ERR(tp); - goto errout; + goto errout_locked; } if (tp == NULL) { + struct tcf_proto *tp_new = NULL; + + if (chain->flushing) { + err = -EAGAIN; + goto errout_locked; + } + /* Proto-tcf does not exist, create new one */ if (tca[TCA_KIND] == NULL || !protocol) { NL_SET_ERR_MSG(extack, "Filter kind and protocol must be specified"); err = -EINVAL; - goto errout; + goto errout_locked; } if (!(n->nlmsg_flags & NLM_F_CREATE)) { NL_SET_ERR_MSG(extack, "Need both RTM_NEWTFILTER and NLM_F_CREATE to create a new filter"); err = -ENOENT; - goto errout; + goto errout_locked; } if (prio_allocate) - prio = tcf_auto_prio(tcf_chain_tp_prev(&chain_info)); + prio = tcf_auto_prio(tcf_chain_tp_prev(chain, + &chain_info)); - tp = tcf_proto_create(nla_data(tca[TCA_KIND]), - protocol, prio, chain, extack); + mutex_unlock(&chain->filter_chain_lock); + tp_new = tcf_proto_create(nla_data(tca[TCA_KIND]), + protocol, prio, chain, rtnl_held, + extack); + if (IS_ERR(tp_new)) { + err = PTR_ERR(tp_new); + goto errout_tp; + } + + tp_created = 1; + tp = tcf_chain_tp_insert_unique(chain, tp_new, protocol, prio, + rtnl_held); if (IS_ERR(tp)) { err = PTR_ERR(tp); - goto errout; + goto errout_tp; } - tp_created = 1; - } else if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) { + } else { + mutex_unlock(&chain->filter_chain_lock); + } + + if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) { NL_SET_ERR_MSG(extack, "Specified filter kind does not match existing one"); err = -EINVAL; goto errout; @@ -1623,6 +2131,7 @@ replay: goto errout; } } else if (n->nlmsg_flags & NLM_F_EXCL) { + tfilter_put(tp, fh); NL_SET_ERR_MSG(extack, "Filter already exists"); err = -EEXIST; goto errout; @@ -1636,25 +2145,41 @@ replay: err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh, n->nlmsg_flags & NLM_F_CREATE ? TCA_ACT_NOREPLACE : TCA_ACT_REPLACE, - extack); + rtnl_held, extack); if (err == 0) { - if (tp_created) - tcf_chain_tp_insert(chain, &chain_info, tp); tfilter_notify(net, skb, n, tp, block, q, parent, fh, - RTM_NEWTFILTER, false); - } else { - if (tp_created) - tcf_proto_destroy(tp, NULL); + RTM_NEWTFILTER, false, rtnl_held); + tfilter_put(tp, fh); } errout: - if (chain) - tcf_chain_put(chain); - tcf_block_release(q, block); - if (err == -EAGAIN) + if (err && tp_created) + tcf_chain_tp_delete_empty(chain, tp, rtnl_held, NULL); +errout_tp: + if (chain) { + if (tp && !IS_ERR(tp)) + tcf_proto_put(tp, rtnl_held, NULL); + if (!tp_created) + tcf_chain_put(chain); + } + tcf_block_release(q, block, rtnl_held); + + if (rtnl_held) + rtnl_unlock(); + + if (err == -EAGAIN) { + /* Take rtnl lock in case EAGAIN is caused by concurrent flush + * of target chain. + */ + rtnl_held = true; /* Replay the request. */ goto replay; + } return err; + +errout_locked: + mutex_unlock(&chain->filter_chain_lock); + goto errout; } static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, @@ -1670,11 +2195,12 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, struct Qdisc *q = NULL; struct tcf_chain_info chain_info; struct tcf_chain *chain = NULL; - struct tcf_block *block; + struct tcf_block *block = NULL; struct tcf_proto *tp = NULL; unsigned long cl = 0; void *fh = NULL; int err; + bool rtnl_held = false; if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) return -EPERM; @@ -1695,8 +2221,27 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, /* Find head of filter chain. */ - block = tcf_block_find(net, &q, &parent, &cl, - t->tcm_ifindex, t->tcm_block_index, extack); + err = __tcf_qdisc_find(net, &q, &parent, t->tcm_ifindex, false, extack); + if (err) + return err; + + /* Take rtnl mutex if flushing whole chain, block is shared (no qdisc + * found), qdisc is not unlocked, classifier type is not specified, + * classifier is not unlocked. + */ + if (!prio || + (q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) || + !tca[TCA_KIND] || !tcf_proto_is_unlocked(nla_data(tca[TCA_KIND]))) { + rtnl_held = true; + rtnl_lock(); + } + + err = __tcf_qdisc_cl_find(q, parent, &cl, t->tcm_ifindex, extack); + if (err) + goto errout; + + block = __tcf_block_find(net, q, cl, t->tcm_ifindex, t->tcm_block_index, + extack); if (IS_ERR(block)) { err = PTR_ERR(block); goto errout; @@ -1724,56 +2269,69 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, if (prio == 0) { tfilter_notify_chain(net, skb, block, q, parent, n, - chain, RTM_DELTFILTER); - tcf_chain_flush(chain); + chain, RTM_DELTFILTER, rtnl_held); + tcf_chain_flush(chain, rtnl_held); err = 0; goto errout; } + mutex_lock(&chain->filter_chain_lock); tp = tcf_chain_tp_find(chain, &chain_info, protocol, prio, false); if (!tp || IS_ERR(tp)) { NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found"); err = tp ? PTR_ERR(tp) : -ENOENT; - goto errout; + goto errout_locked; } else if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) { NL_SET_ERR_MSG(extack, "Specified filter kind does not match existing one"); err = -EINVAL; + goto errout_locked; + } else if (t->tcm_handle == 0) { + tcf_chain_tp_remove(chain, &chain_info, tp); + mutex_unlock(&chain->filter_chain_lock); + + tcf_proto_put(tp, rtnl_held, NULL); + tfilter_notify(net, skb, n, tp, block, q, parent, fh, + RTM_DELTFILTER, false, rtnl_held); + err = 0; goto errout; } + mutex_unlock(&chain->filter_chain_lock); fh = tp->ops->get(tp, t->tcm_handle); if (!fh) { - if (t->tcm_handle == 0) { - tcf_chain_tp_remove(chain, &chain_info, tp); - tfilter_notify(net, skb, n, tp, block, q, parent, fh, - RTM_DELTFILTER, false); - tcf_proto_destroy(tp, extack); - err = 0; - } else { - NL_SET_ERR_MSG(extack, "Specified filter handle not found"); - err = -ENOENT; - } + NL_SET_ERR_MSG(extack, "Specified filter handle not found"); + err = -ENOENT; } else { bool last; err = tfilter_del_notify(net, skb, n, tp, block, q, parent, fh, false, &last, - extack); + rtnl_held, extack); + if (err) goto errout; - if (last) { - tcf_chain_tp_remove(chain, &chain_info, tp); - tcf_proto_destroy(tp, extack); - } + if (last) + tcf_chain_tp_delete_empty(chain, tp, rtnl_held, extack); } errout: - if (chain) + if (chain) { + if (tp && !IS_ERR(tp)) + tcf_proto_put(tp, rtnl_held, NULL); tcf_chain_put(chain); - tcf_block_release(q, block); + } + tcf_block_release(q, block, rtnl_held); + + if (rtnl_held) + rtnl_unlock(); + return err; + +errout_locked: + mutex_unlock(&chain->filter_chain_lock); + goto errout; } static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n, @@ -1789,11 +2347,12 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n, struct Qdisc *q = NULL; struct tcf_chain_info chain_info; struct tcf_chain *chain = NULL; - struct tcf_block *block; + struct tcf_block *block = NULL; struct tcf_proto *tp = NULL; unsigned long cl = 0; void *fh = NULL; int err; + bool rtnl_held = false; err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, rtm_tca_policy, extack); if (err < 0) @@ -1811,8 +2370,26 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n, /* Find head of filter chain. */ - block = tcf_block_find(net, &q, &parent, &cl, - t->tcm_ifindex, t->tcm_block_index, extack); + err = __tcf_qdisc_find(net, &q, &parent, t->tcm_ifindex, false, extack); + if (err) + return err; + + /* Take rtnl mutex if block is shared (no qdisc found), qdisc is not + * unlocked, classifier type is not specified, classifier is not + * unlocked. + */ + if ((q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) || + !tca[TCA_KIND] || !tcf_proto_is_unlocked(nla_data(tca[TCA_KIND]))) { + rtnl_held = true; + rtnl_lock(); + } + + err = __tcf_qdisc_cl_find(q, parent, &cl, t->tcm_ifindex, extack); + if (err) + goto errout; + + block = __tcf_block_find(net, q, cl, t->tcm_ifindex, t->tcm_block_index, + extack); if (IS_ERR(block)) { err = PTR_ERR(block); goto errout; @@ -1831,8 +2408,10 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n, goto errout; } + mutex_lock(&chain->filter_chain_lock); tp = tcf_chain_tp_find(chain, &chain_info, protocol, prio, false); + mutex_unlock(&chain->filter_chain_lock); if (!tp || IS_ERR(tp)) { NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found"); err = tp ? PTR_ERR(tp) : -ENOENT; @@ -1850,15 +2429,23 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n, err = -ENOENT; } else { err = tfilter_notify(net, skb, n, tp, block, q, parent, - fh, RTM_NEWTFILTER, true); + fh, RTM_NEWTFILTER, true, rtnl_held); if (err < 0) NL_SET_ERR_MSG(extack, "Failed to send filter notify message"); } + tfilter_put(tp, fh); errout: - if (chain) + if (chain) { + if (tp && !IS_ERR(tp)) + tcf_proto_put(tp, rtnl_held, NULL); tcf_chain_put(chain); - tcf_block_release(q, block); + } + tcf_block_release(q, block, rtnl_held); + + if (rtnl_held) + rtnl_unlock(); + return err; } @@ -1879,7 +2466,7 @@ static int tcf_node_dump(struct tcf_proto *tp, void *n, struct tcf_walker *arg) return tcf_fill_node(net, a->skb, tp, a->block, a->q, a->parent, n, NETLINK_CB(a->cb->skb).portid, a->cb->nlh->nlmsg_seq, NLM_F_MULTI, - RTM_NEWTFILTER); + RTM_NEWTFILTER, true); } static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent, @@ -1889,11 +2476,15 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent, struct net *net = sock_net(skb->sk); struct tcf_block *block = chain->block; struct tcmsg *tcm = nlmsg_data(cb->nlh); + struct tcf_proto *tp, *tp_prev; struct tcf_dump_args arg; - struct tcf_proto *tp; - for (tp = rtnl_dereference(chain->filter_chain); - tp; tp = rtnl_dereference(tp->next), (*p_index)++) { + for (tp = __tcf_get_next_proto(chain, NULL); + tp; + tp_prev = tp, + tp = __tcf_get_next_proto(chain, tp), + tcf_proto_put(tp_prev, true, NULL), + (*p_index)++) { if (*p_index < index_start) continue; if (TC_H_MAJ(tcm->tcm_info) && @@ -1909,9 +2500,8 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent, if (tcf_fill_node(net, skb, tp, block, q, parent, NULL, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - RTM_NEWTFILTER) <= 0) - return false; - + RTM_NEWTFILTER, true) <= 0) + goto errout; cb->args[1] = 1; } if (!tp->ops->walk) @@ -1926,23 +2516,27 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent, arg.w.skip = cb->args[1] - 1; arg.w.count = 0; arg.w.cookie = cb->args[2]; - tp->ops->walk(tp, &arg.w); + tp->ops->walk(tp, &arg.w, true); cb->args[2] = arg.w.cookie; cb->args[1] = arg.w.count + 1; if (arg.w.stop) - return false; + goto errout; } return true; + +errout: + tcf_proto_put(tp, true, NULL); + return false; } /* called with RTNL */ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) { + struct tcf_chain *chain, *chain_prev; struct net *net = sock_net(skb->sk); struct nlattr *tca[TCA_MAX + 1]; struct Qdisc *q = NULL; struct tcf_block *block; - struct tcf_chain *chain; struct tcmsg *tcm = nlmsg_data(cb->nlh); long index_start; long index; @@ -2006,19 +2600,24 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) index_start = cb->args[0]; index = 0; - list_for_each_entry(chain, &block->chain_list, list) { + for (chain = __tcf_get_next_chain(block, NULL); + chain; + chain_prev = chain, + chain = __tcf_get_next_chain(block, chain), + tcf_chain_put(chain_prev)) { if (tca[TCA_CHAIN] && nla_get_u32(tca[TCA_CHAIN]) != chain->index) continue; if (!tcf_chain_dump(chain, q, parent, skb, cb, index_start, &index)) { + tcf_chain_put(chain); err = -EMSGSIZE; break; } } if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) - tcf_block_refcnt_put(block); + tcf_block_refcnt_put(block, true); cb->args[0] = index; out: @@ -2028,8 +2627,10 @@ out: return skb->len; } -static int tc_chain_fill_node(struct tcf_chain *chain, struct net *net, - struct sk_buff *skb, struct tcf_block *block, +static int tc_chain_fill_node(const struct tcf_proto_ops *tmplt_ops, + void *tmplt_priv, u32 chain_index, + struct net *net, struct sk_buff *skb, + struct tcf_block *block, u32 portid, u32 seq, u16 flags, int event) { unsigned char *b = skb_tail_pointer(skb); @@ -2038,8 +2639,8 @@ static int tc_chain_fill_node(struct tcf_chain *chain, struct net *net, struct tcmsg *tcm; void *priv; - ops = chain->tmplt_ops; - priv = chain->tmplt_priv; + ops = tmplt_ops; + priv = tmplt_priv; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags); if (!nlh) @@ -2057,7 +2658,7 @@ static int tc_chain_fill_node(struct tcf_chain *chain, struct net *net, tcm->tcm_block_index = block->index; } - if (nla_put_u32(skb, TCA_CHAIN, chain->index)) + if (nla_put_u32(skb, TCA_CHAIN, chain_index)) goto nla_put_failure; if (ops) { @@ -2088,7 +2689,8 @@ static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb, if (!skb) return -ENOBUFS; - if (tc_chain_fill_node(chain, net, skb, block, portid, + if (tc_chain_fill_node(chain->tmplt_ops, chain->tmplt_priv, + chain->index, net, skb, block, portid, seq, flags, event) <= 0) { kfree_skb(skb); return -EINVAL; @@ -2100,6 +2702,31 @@ static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb, return rtnetlink_send(skb, net, portid, RTNLGRP_TC, flags & NLM_F_ECHO); } +static int tc_chain_notify_delete(const struct tcf_proto_ops *tmplt_ops, + void *tmplt_priv, u32 chain_index, + struct tcf_block *block, struct sk_buff *oskb, + u32 seq, u16 flags, bool unicast) +{ + u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; + struct net *net = block->net; + struct sk_buff *skb; + + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + if (!skb) + return -ENOBUFS; + + if (tc_chain_fill_node(tmplt_ops, tmplt_priv, chain_index, net, skb, + block, portid, seq, flags, RTM_DELCHAIN) <= 0) { + kfree_skb(skb); + return -EINVAL; + } + + if (unicast) + return netlink_unicast(net->rtnl, skb, portid, MSG_DONTWAIT); + + return rtnetlink_send(skb, net, portid, RTNLGRP_TC, flags & NLM_F_ECHO); +} + static int tc_chain_tmplt_add(struct tcf_chain *chain, struct net *net, struct nlattr **tca, struct netlink_ext_ack *extack) @@ -2111,7 +2738,7 @@ static int tc_chain_tmplt_add(struct tcf_chain *chain, struct net *net, if (!tca[TCA_KIND]) return 0; - ops = tcf_proto_lookup_ops(nla_data(tca[TCA_KIND]), extack); + ops = tcf_proto_lookup_ops(nla_data(tca[TCA_KIND]), true, extack); if (IS_ERR(ops)) return PTR_ERR(ops); if (!ops->tmplt_create || !ops->tmplt_destroy || !ops->tmplt_dump) { @@ -2129,16 +2756,15 @@ static int tc_chain_tmplt_add(struct tcf_chain *chain, struct net *net, return 0; } -static void tc_chain_tmplt_del(struct tcf_chain *chain) +static void tc_chain_tmplt_del(const struct tcf_proto_ops *tmplt_ops, + void *tmplt_priv) { - const struct tcf_proto_ops *ops = chain->tmplt_ops; - /* If template ops are set, no work to do for us. */ - if (!ops) + if (!tmplt_ops) return; - ops->tmplt_destroy(chain->tmplt_priv); - module_put(ops->owner); + tmplt_ops->tmplt_destroy(tmplt_priv); + module_put(tmplt_ops->owner); } /* Add/delete/get a chain */ @@ -2181,6 +2807,8 @@ replay: err = -EINVAL; goto errout_block; } + + mutex_lock(&block->lock); chain = tcf_chain_lookup(block, chain_index); if (n->nlmsg_type == RTM_NEWCHAIN) { if (chain) { @@ -2192,54 +2820,61 @@ replay: } else { NL_SET_ERR_MSG(extack, "Filter chain already exists"); err = -EEXIST; - goto errout_block; + goto errout_block_locked; } } else { if (!(n->nlmsg_flags & NLM_F_CREATE)) { NL_SET_ERR_MSG(extack, "Need both RTM_NEWCHAIN and NLM_F_CREATE to create a new chain"); err = -ENOENT; - goto errout_block; + goto errout_block_locked; } chain = tcf_chain_create(block, chain_index); if (!chain) { NL_SET_ERR_MSG(extack, "Failed to create filter chain"); err = -ENOMEM; - goto errout_block; + goto errout_block_locked; } } } else { if (!chain || tcf_chain_held_by_acts_only(chain)) { NL_SET_ERR_MSG(extack, "Cannot find specified filter chain"); err = -EINVAL; - goto errout_block; + goto errout_block_locked; } tcf_chain_hold(chain); } + if (n->nlmsg_type == RTM_NEWCHAIN) { + /* Modifying chain requires holding parent block lock. In case + * the chain was successfully added, take a reference to the + * chain. This ensures that an empty chain does not disappear at + * the end of this function. + */ + tcf_chain_hold(chain); + chain->explicitly_created = true; + } + mutex_unlock(&block->lock); + switch (n->nlmsg_type) { case RTM_NEWCHAIN: err = tc_chain_tmplt_add(chain, net, tca, extack); - if (err) + if (err) { + tcf_chain_put_explicitly_created(chain); goto errout; - /* In case the chain was successfully added, take a reference - * to the chain. This ensures that an empty chain - * does not disappear at the end of this function. - */ - tcf_chain_hold(chain); - chain->explicitly_created = true; + } + tc_chain_notify(chain, NULL, 0, NLM_F_CREATE | NLM_F_EXCL, RTM_NEWCHAIN, false); break; case RTM_DELCHAIN: tfilter_notify_chain(net, skb, block, q, parent, n, - chain, RTM_DELTFILTER); + chain, RTM_DELTFILTER, true); /* Flush the chain first as the user requested chain removal. */ - tcf_chain_flush(chain); + tcf_chain_flush(chain, true); /* In case the chain was successfully deleted, put a reference * to the chain previously taken during addition. */ tcf_chain_put_explicitly_created(chain); - chain->explicitly_created = false; break; case RTM_GETCHAIN: err = tc_chain_notify(chain, skb, n->nlmsg_seq, @@ -2256,21 +2891,25 @@ replay: errout: tcf_chain_put(chain); errout_block: - tcf_block_release(q, block); + tcf_block_release(q, block, true); if (err == -EAGAIN) /* Replay the request. */ goto replay; return err; + +errout_block_locked: + mutex_unlock(&block->lock); + goto errout_block; } /* called with RTNL */ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb) { + struct tcf_chain *chain, *chain_prev; struct net *net = sock_net(skb->sk); struct nlattr *tca[TCA_MAX + 1]; struct Qdisc *q = NULL; struct tcf_block *block; - struct tcf_chain *chain; struct tcmsg *tcm = nlmsg_data(cb->nlh); long index_start; long index; @@ -2334,7 +2973,11 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb) index_start = cb->args[0]; index = 0; - list_for_each_entry(chain, &block->chain_list, list) { + for (chain = __tcf_get_next_chain(block, NULL); + chain; + chain_prev = chain, + chain = __tcf_get_next_chain(block, chain), + tcf_chain_put(chain_prev)) { if ((tca[TCA_CHAIN] && nla_get_u32(tca[TCA_CHAIN]) != chain->index)) continue; @@ -2342,19 +2985,20 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb) index++; continue; } - if (tcf_chain_held_by_acts_only(chain)) - continue; - err = tc_chain_fill_node(chain, net, skb, block, + err = tc_chain_fill_node(chain->tmplt_ops, chain->tmplt_priv, + chain->index, net, skb, block, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWCHAIN); - if (err <= 0) + if (err <= 0) { + tcf_chain_put(chain); break; + } index++; } if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) - tcf_block_refcnt_put(block); + tcf_block_refcnt_put(block, true); cb->args[0] = index; out: @@ -2376,7 +3020,7 @@ EXPORT_SYMBOL(tcf_exts_destroy); int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, struct nlattr *rate_tlv, struct tcf_exts *exts, bool ovr, - struct netlink_ext_ack *extack) + bool rtnl_held, struct netlink_ext_ack *extack) { #ifdef CONFIG_NET_CLS_ACT { @@ -2386,7 +3030,8 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, if (exts->police && tb[exts->police]) { act = tcf_action_init_1(net, tp, tb[exts->police], rate_tlv, "police", ovr, - TCA_ACT_BIND, true, extack); + TCA_ACT_BIND, rtnl_held, + extack); if (IS_ERR(act)) return PTR_ERR(act); @@ -2398,8 +3043,8 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, err = tcf_action_init(net, tp, tb[exts->action], rate_tlv, NULL, ovr, TCA_ACT_BIND, - exts->actions, &attr_size, true, - extack); + exts->actions, &attr_size, + rtnl_held, extack); if (err < 0) return err; exts->nr_actions = err; @@ -2515,6 +3160,114 @@ int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type, } EXPORT_SYMBOL(tc_setup_cb_call); +int tc_setup_flow_action(struct flow_action *flow_action, + const struct tcf_exts *exts) +{ + const struct tc_action *act; + int i, j, k; + + if (!exts) + return 0; + + j = 0; + tcf_exts_for_each_action(i, act, exts) { + struct flow_action_entry *entry; + + entry = &flow_action->entries[j]; + if (is_tcf_gact_ok(act)) { + entry->id = FLOW_ACTION_ACCEPT; + } else if (is_tcf_gact_shot(act)) { + entry->id = FLOW_ACTION_DROP; + } else if (is_tcf_gact_trap(act)) { + entry->id = FLOW_ACTION_TRAP; + } else if (is_tcf_gact_goto_chain(act)) { + entry->id = FLOW_ACTION_GOTO; + entry->chain_index = tcf_gact_goto_chain_index(act); + } else if (is_tcf_mirred_egress_redirect(act)) { + entry->id = FLOW_ACTION_REDIRECT; + entry->dev = tcf_mirred_dev(act); + } else if (is_tcf_mirred_egress_mirror(act)) { + entry->id = FLOW_ACTION_MIRRED; + entry->dev = tcf_mirred_dev(act); + } else if (is_tcf_vlan(act)) { + switch (tcf_vlan_action(act)) { + case TCA_VLAN_ACT_PUSH: + entry->id = FLOW_ACTION_VLAN_PUSH; + entry->vlan.vid = tcf_vlan_push_vid(act); + entry->vlan.proto = tcf_vlan_push_proto(act); + entry->vlan.prio = tcf_vlan_push_prio(act); + break; + case TCA_VLAN_ACT_POP: + entry->id = FLOW_ACTION_VLAN_POP; + break; + case TCA_VLAN_ACT_MODIFY: + entry->id = FLOW_ACTION_VLAN_MANGLE; + entry->vlan.vid = tcf_vlan_push_vid(act); + entry->vlan.proto = tcf_vlan_push_proto(act); + entry->vlan.prio = tcf_vlan_push_prio(act); + break; + default: + goto err_out; + } + } else if (is_tcf_tunnel_set(act)) { + entry->id = FLOW_ACTION_TUNNEL_ENCAP; + entry->tunnel = tcf_tunnel_info(act); + } else if (is_tcf_tunnel_release(act)) { + entry->id = FLOW_ACTION_TUNNEL_DECAP; + entry->tunnel = tcf_tunnel_info(act); + } else if (is_tcf_pedit(act)) { + for (k = 0; k < tcf_pedit_nkeys(act); k++) { + switch (tcf_pedit_cmd(act, k)) { + case TCA_PEDIT_KEY_EX_CMD_SET: + entry->id = FLOW_ACTION_MANGLE; + break; + case TCA_PEDIT_KEY_EX_CMD_ADD: + entry->id = FLOW_ACTION_ADD; + break; + default: + goto err_out; + } + entry->mangle.htype = tcf_pedit_htype(act, k); + entry->mangle.mask = tcf_pedit_mask(act, k); + entry->mangle.val = tcf_pedit_val(act, k); + entry->mangle.offset = tcf_pedit_offset(act, k); + entry = &flow_action->entries[++j]; + } + } else if (is_tcf_csum(act)) { + entry->id = FLOW_ACTION_CSUM; + entry->csum_flags = tcf_csum_update_flags(act); + } else if (is_tcf_skbedit_mark(act)) { + entry->id = FLOW_ACTION_MARK; + entry->mark = tcf_skbedit_mark(act); + } else { + goto err_out; + } + + if (!is_tcf_pedit(act)) + j++; + } + return 0; +err_out: + return -EOPNOTSUPP; +} +EXPORT_SYMBOL(tc_setup_flow_action); + +unsigned int tcf_exts_num_actions(struct tcf_exts *exts) +{ + unsigned int num_acts = 0; + struct tc_action *act; + int i; + + tcf_exts_for_each_action(i, act, exts) { + if (is_tcf_pedit(act)) + num_acts += tcf_pedit_nkeys(act); + else + num_acts++; + } + return num_acts; +} +EXPORT_SYMBOL(tcf_exts_num_actions); + static __net_init int tcf_net_init(struct net *net) { struct tcf_net *tn = net_generic(net, tcf_net_id); @@ -2555,10 +3308,12 @@ static int __init tc_filter_init(void) if (err) goto err_rhash_setup_block_ht; - rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_new_tfilter, NULL, 0); - rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_del_tfilter, NULL, 0); + rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_new_tfilter, NULL, + RTNL_FLAG_DOIT_UNLOCKED); + rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_del_tfilter, NULL, + RTNL_FLAG_DOIT_UNLOCKED); rtnl_register(PF_UNSPEC, RTM_GETTFILTER, tc_get_tfilter, - tc_dump_tfilter, 0); + tc_dump_tfilter, RTNL_FLAG_DOIT_UNLOCKED); rtnl_register(PF_UNSPEC, RTM_NEWCHAIN, tc_ctl_chain, NULL, 0); rtnl_register(PF_UNSPEC, RTM_DELCHAIN, tc_ctl_chain, NULL, 0); rtnl_register(PF_UNSPEC, RTM_GETCHAIN, tc_ctl_chain, diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index 4a57fec6f306..2383f449d2bc 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -107,7 +107,8 @@ static void basic_delete_filter_work(struct work_struct *work) rtnl_unlock(); } -static void basic_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) +static void basic_destroy(struct tcf_proto *tp, bool rtnl_held, + struct netlink_ext_ack *extack) { struct basic_head *head = rtnl_dereference(tp->root); struct basic_filter *f, *n; @@ -126,7 +127,7 @@ static void basic_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) } static int basic_delete(struct tcf_proto *tp, void *arg, bool *last, - struct netlink_ext_ack *extack) + bool rtnl_held, struct netlink_ext_ack *extack) { struct basic_head *head = rtnl_dereference(tp->root); struct basic_filter *f = arg; @@ -153,7 +154,7 @@ static int basic_set_parms(struct net *net, struct tcf_proto *tp, { int err; - err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr, extack); + err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr, true, extack); if (err < 0) return err; @@ -173,7 +174,7 @@ static int basic_set_parms(struct net *net, struct tcf_proto *tp, static int basic_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, void **arg, bool ovr, - struct netlink_ext_ack *extack) + bool rtnl_held, struct netlink_ext_ack *extack) { int err; struct basic_head *head = rtnl_dereference(tp->root); @@ -247,7 +248,8 @@ errout: return err; } -static void basic_walk(struct tcf_proto *tp, struct tcf_walker *arg) +static void basic_walk(struct tcf_proto *tp, struct tcf_walker *arg, + bool rtnl_held) { struct basic_head *head = rtnl_dereference(tp->root); struct basic_filter *f; @@ -274,7 +276,7 @@ static void basic_bind_class(void *fh, u32 classid, unsigned long cl) } static int basic_dump(struct net *net, struct tcf_proto *tp, void *fh, - struct sk_buff *skb, struct tcmsg *t) + struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) { struct tc_basic_pcnt gpf = {}; struct basic_filter *f = fh; diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index a95cb240a606..062350c6621c 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -298,7 +298,7 @@ static void __cls_bpf_delete(struct tcf_proto *tp, struct cls_bpf_prog *prog, } static int cls_bpf_delete(struct tcf_proto *tp, void *arg, bool *last, - struct netlink_ext_ack *extack) + bool rtnl_held, struct netlink_ext_ack *extack) { struct cls_bpf_head *head = rtnl_dereference(tp->root); @@ -307,7 +307,7 @@ static int cls_bpf_delete(struct tcf_proto *tp, void *arg, bool *last, return 0; } -static void cls_bpf_destroy(struct tcf_proto *tp, +static void cls_bpf_destroy(struct tcf_proto *tp, bool rtnl_held, struct netlink_ext_ack *extack) { struct cls_bpf_head *head = rtnl_dereference(tp->root); @@ -417,7 +417,8 @@ static int cls_bpf_set_parms(struct net *net, struct tcf_proto *tp, if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf)) return -EINVAL; - ret = tcf_exts_validate(net, tp, tb, est, &prog->exts, ovr, extack); + ret = tcf_exts_validate(net, tp, tb, est, &prog->exts, ovr, true, + extack); if (ret < 0) return ret; @@ -455,7 +456,8 @@ static int cls_bpf_set_parms(struct net *net, struct tcf_proto *tp, static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, - void **arg, bool ovr, struct netlink_ext_ack *extack) + void **arg, bool ovr, bool rtnl_held, + struct netlink_ext_ack *extack) { struct cls_bpf_head *head = rtnl_dereference(tp->root); struct cls_bpf_prog *oldprog = *arg; @@ -575,7 +577,7 @@ static int cls_bpf_dump_ebpf_info(const struct cls_bpf_prog *prog, } static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, void *fh, - struct sk_buff *skb, struct tcmsg *tm) + struct sk_buff *skb, struct tcmsg *tm, bool rtnl_held) { struct cls_bpf_prog *prog = fh; struct nlattr *nest; @@ -635,7 +637,8 @@ static void cls_bpf_bind_class(void *fh, u32 classid, unsigned long cl) prog->res.class = cl; } -static void cls_bpf_walk(struct tcf_proto *tp, struct tcf_walker *arg) +static void cls_bpf_walk(struct tcf_proto *tp, struct tcf_walker *arg, + bool rtnl_held) { struct cls_bpf_head *head = rtnl_dereference(tp->root); struct cls_bpf_prog *prog; diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index 3bc01bdde165..02b05066b635 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -78,7 +78,7 @@ static void cls_cgroup_destroy_work(struct work_struct *work) static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, - void **arg, bool ovr, + void **arg, bool ovr, bool rtnl_held, struct netlink_ext_ack *extack) { struct nlattr *tb[TCA_CGROUP_MAX + 1]; @@ -110,7 +110,7 @@ static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb, goto errout; err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &new->exts, ovr, - extack); + true, extack); if (err < 0) goto errout; @@ -130,7 +130,7 @@ errout: return err; } -static void cls_cgroup_destroy(struct tcf_proto *tp, +static void cls_cgroup_destroy(struct tcf_proto *tp, bool rtnl_held, struct netlink_ext_ack *extack) { struct cls_cgroup_head *head = rtnl_dereference(tp->root); @@ -145,18 +145,21 @@ static void cls_cgroup_destroy(struct tcf_proto *tp, } static int cls_cgroup_delete(struct tcf_proto *tp, void *arg, bool *last, - struct netlink_ext_ack *extack) + bool rtnl_held, struct netlink_ext_ack *extack) { return -EOPNOTSUPP; } -static void cls_cgroup_walk(struct tcf_proto *tp, struct tcf_walker *arg) +static void cls_cgroup_walk(struct tcf_proto *tp, struct tcf_walker *arg, + bool rtnl_held) { struct cls_cgroup_head *head = rtnl_dereference(tp->root); if (arg->count < arg->skip) goto skip; + if (!head) + return; if (arg->fn(tp, head, arg) < 0) { arg->stop = 1; return; @@ -166,7 +169,7 @@ skip: } static int cls_cgroup_dump(struct net *net, struct tcf_proto *tp, void *fh, - struct sk_buff *skb, struct tcmsg *t) + struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) { struct cls_cgroup_head *head = rtnl_dereference(tp->root); struct nlattr *nest; diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 2bb043cd436b..204e2edae8d5 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -391,7 +391,8 @@ static void flow_destroy_filter_work(struct work_struct *work) static int flow_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, - void **arg, bool ovr, struct netlink_ext_ack *extack) + void **arg, bool ovr, bool rtnl_held, + struct netlink_ext_ack *extack) { struct flow_head *head = rtnl_dereference(tp->root); struct flow_filter *fold, *fnew; @@ -445,7 +446,7 @@ static int flow_change(struct net *net, struct sk_buff *in_skb, goto err2; err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &fnew->exts, ovr, - extack); + true, extack); if (err < 0) goto err2; @@ -566,7 +567,7 @@ err1: } static int flow_delete(struct tcf_proto *tp, void *arg, bool *last, - struct netlink_ext_ack *extack) + bool rtnl_held, struct netlink_ext_ack *extack) { struct flow_head *head = rtnl_dereference(tp->root); struct flow_filter *f = arg; @@ -590,7 +591,8 @@ static int flow_init(struct tcf_proto *tp) return 0; } -static void flow_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) +static void flow_destroy(struct tcf_proto *tp, bool rtnl_held, + struct netlink_ext_ack *extack) { struct flow_head *head = rtnl_dereference(tp->root); struct flow_filter *f, *next; @@ -617,7 +619,7 @@ static void *flow_get(struct tcf_proto *tp, u32 handle) } static int flow_dump(struct net *net, struct tcf_proto *tp, void *fh, - struct sk_buff *skb, struct tcmsg *t) + struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) { struct flow_filter *f = fh; struct nlattr *nest; @@ -677,7 +679,8 @@ nla_put_failure: return -1; } -static void flow_walk(struct tcf_proto *tp, struct tcf_walker *arg) +static void flow_walk(struct tcf_proto *tp, struct tcf_walker *arg, + bool rtnl_held) { struct flow_head *head = rtnl_dereference(tp->root); struct flow_filter *f; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index f6aa57fbbbaf..640f83e7f93f 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -381,16 +381,31 @@ static int fl_hw_replace_filter(struct tcf_proto *tp, bool skip_sw = tc_skip_sw(f->flags); int err; + cls_flower.rule = flow_rule_alloc(tcf_exts_num_actions(&f->exts)); + if (!cls_flower.rule) + return -ENOMEM; + tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, extack); cls_flower.command = TC_CLSFLOWER_REPLACE; cls_flower.cookie = (unsigned long) f; - cls_flower.dissector = &f->mask->dissector; - cls_flower.mask = &f->mask->key; - cls_flower.key = &f->mkey; - cls_flower.exts = &f->exts; + cls_flower.rule->match.dissector = &f->mask->dissector; + cls_flower.rule->match.mask = &f->mask->key; + cls_flower.rule->match.key = &f->mkey; cls_flower.classid = f->res.classid; + err = tc_setup_flow_action(&cls_flower.rule->action, &f->exts); + if (err) { + kfree(cls_flower.rule); + if (skip_sw) { + NL_SET_ERR_MSG_MOD(extack, "Failed to setup flow action"); + return err; + } + return 0; + } + err = tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, skip_sw); + kfree(cls_flower.rule); + if (err < 0) { fl_hw_destroy_filter(tp, f, NULL); return err; @@ -413,10 +428,13 @@ static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f) tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, NULL); cls_flower.command = TC_CLSFLOWER_STATS; cls_flower.cookie = (unsigned long) f; - cls_flower.exts = &f->exts; cls_flower.classid = f->res.classid; tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false); + + tcf_exts_stats_update(&f->exts, cls_flower.stats.bytes, + cls_flower.stats.pkts, + cls_flower.stats.lastused); } static bool __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f, @@ -451,7 +469,8 @@ static void fl_destroy_sleepable(struct work_struct *work) module_put(THIS_MODULE); } -static void fl_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) +static void fl_destroy(struct tcf_proto *tp, bool rtnl_held, + struct netlink_ext_ack *extack) { struct cls_fl_head *head = rtnl_dereference(tp->root); struct fl_flow_mask *mask, *next_mask; @@ -1258,7 +1277,8 @@ static int fl_set_parms(struct net *net, struct tcf_proto *tp, { int err; - err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr, extack); + err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr, true, + extack); if (err < 0) return err; @@ -1285,7 +1305,8 @@ static int fl_set_parms(struct net *net, struct tcf_proto *tp, static int fl_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, - void **arg, bool ovr, struct netlink_ext_ack *extack) + void **arg, bool ovr, bool rtnl_held, + struct netlink_ext_ack *extack) { struct cls_fl_head *head = rtnl_dereference(tp->root); struct cls_fl_filter *fold = *arg; @@ -1371,7 +1392,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, if (!tc_skip_hw(fnew->flags)) { err = fl_hw_replace_filter(tp, fnew, extack); if (err) - goto errout_mask; + goto errout_mask_ht; } if (!tc_in_hw(fnew->flags)) @@ -1401,6 +1422,10 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, kfree(mask); return 0; +errout_mask_ht: + rhashtable_remove_fast(&fnew->mask->ht, &fnew->ht_node, + fnew->mask->filter_ht_params); + errout_mask: fl_mask_put(head, fnew->mask, false); @@ -1418,7 +1443,7 @@ errout_mask_alloc: } static int fl_delete(struct tcf_proto *tp, void *arg, bool *last, - struct netlink_ext_ack *extack) + bool rtnl_held, struct netlink_ext_ack *extack) { struct cls_fl_head *head = rtnl_dereference(tp->root); struct cls_fl_filter *f = arg; @@ -1430,7 +1455,8 @@ static int fl_delete(struct tcf_proto *tp, void *arg, bool *last, return 0; } -static void fl_walk(struct tcf_proto *tp, struct tcf_walker *arg) +static void fl_walk(struct tcf_proto *tp, struct tcf_walker *arg, + bool rtnl_held) { struct cls_fl_head *head = rtnl_dereference(tp->root); struct cls_fl_filter *f; @@ -1463,18 +1489,36 @@ static int fl_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb, if (tc_skip_hw(f->flags)) continue; + cls_flower.rule = + flow_rule_alloc(tcf_exts_num_actions(&f->exts)); + if (!cls_flower.rule) + return -ENOMEM; + tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, extack); cls_flower.command = add ? TC_CLSFLOWER_REPLACE : TC_CLSFLOWER_DESTROY; cls_flower.cookie = (unsigned long)f; - cls_flower.dissector = &mask->dissector; - cls_flower.mask = &mask->key; - cls_flower.key = &f->mkey; - cls_flower.exts = &f->exts; + cls_flower.rule->match.dissector = &mask->dissector; + cls_flower.rule->match.mask = &mask->key; + cls_flower.rule->match.key = &f->mkey; + + err = tc_setup_flow_action(&cls_flower.rule->action, + &f->exts); + if (err) { + kfree(cls_flower.rule); + if (tc_skip_sw(f->flags)) { + NL_SET_ERR_MSG_MOD(extack, "Failed to setup flow action"); + return err; + } + continue; + } + cls_flower.classid = f->res.classid; err = cb(TC_SETUP_CLSFLOWER, &cls_flower, cb_priv); + kfree(cls_flower.rule); + if (err) { if (add && tc_skip_sw(f->flags)) return err; @@ -1489,25 +1533,30 @@ static int fl_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb, return 0; } -static void fl_hw_create_tmplt(struct tcf_chain *chain, - struct fl_flow_tmplt *tmplt) +static int fl_hw_create_tmplt(struct tcf_chain *chain, + struct fl_flow_tmplt *tmplt) { struct tc_cls_flower_offload cls_flower = {}; struct tcf_block *block = chain->block; - struct tcf_exts dummy_exts = { 0, }; + + cls_flower.rule = flow_rule_alloc(0); + if (!cls_flower.rule) + return -ENOMEM; cls_flower.common.chain_index = chain->index; cls_flower.command = TC_CLSFLOWER_TMPLT_CREATE; cls_flower.cookie = (unsigned long) tmplt; - cls_flower.dissector = &tmplt->dissector; - cls_flower.mask = &tmplt->mask; - cls_flower.key = &tmplt->dummy_key; - cls_flower.exts = &dummy_exts; + cls_flower.rule->match.dissector = &tmplt->dissector; + cls_flower.rule->match.mask = &tmplt->mask; + cls_flower.rule->match.key = &tmplt->dummy_key; /* We don't care if driver (any of them) fails to handle this * call. It serves just as a hint for it. */ tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false); + kfree(cls_flower.rule); + + return 0; } static void fl_hw_destroy_tmplt(struct tcf_chain *chain, @@ -1551,12 +1600,14 @@ static void *fl_tmplt_create(struct net *net, struct tcf_chain *chain, err = fl_set_key(net, tb, &tmplt->dummy_key, &tmplt->mask, extack); if (err) goto errout_tmplt; - kfree(tb); fl_init_dissector(&tmplt->dissector, &tmplt->mask); - fl_hw_create_tmplt(chain, tmplt); + err = fl_hw_create_tmplt(chain, tmplt); + if (err) + goto errout_tmplt; + kfree(tb); return tmplt; errout_tmplt: @@ -2004,7 +2055,7 @@ nla_put_failure: } static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh, - struct sk_buff *skb, struct tcmsg *t) + struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) { struct cls_fl_filter *f = fh; struct nlattr *nest; diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index 29eeeaf3ea44..4e34966f2ae2 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -139,7 +139,8 @@ static void fw_delete_filter_work(struct work_struct *work) rtnl_unlock(); } -static void fw_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) +static void fw_destroy(struct tcf_proto *tp, bool rtnl_held, + struct netlink_ext_ack *extack) { struct fw_head *head = rtnl_dereference(tp->root); struct fw_filter *f; @@ -163,7 +164,7 @@ static void fw_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) } static int fw_delete(struct tcf_proto *tp, void *arg, bool *last, - struct netlink_ext_ack *extack) + bool rtnl_held, struct netlink_ext_ack *extack) { struct fw_head *head = rtnl_dereference(tp->root); struct fw_filter *f = arg; @@ -217,7 +218,7 @@ static int fw_set_parms(struct net *net, struct tcf_proto *tp, int err; err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &f->exts, ovr, - extack); + true, extack); if (err < 0) return err; @@ -250,7 +251,8 @@ static int fw_set_parms(struct net *net, struct tcf_proto *tp, static int fw_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, void **arg, - bool ovr, struct netlink_ext_ack *extack) + bool ovr, bool rtnl_held, + struct netlink_ext_ack *extack) { struct fw_head *head = rtnl_dereference(tp->root); struct fw_filter *f = *arg; @@ -354,15 +356,13 @@ errout: return err; } -static void fw_walk(struct tcf_proto *tp, struct tcf_walker *arg) +static void fw_walk(struct tcf_proto *tp, struct tcf_walker *arg, + bool rtnl_held) { struct fw_head *head = rtnl_dereference(tp->root); int h; - if (head == NULL) - arg->stop = 1; - - if (arg->stop) + if (head == NULL || arg->stop) return; for (h = 0; h < HTSIZE; h++) { @@ -384,7 +384,7 @@ static void fw_walk(struct tcf_proto *tp, struct tcf_walker *arg) } static int fw_dump(struct net *net, struct tcf_proto *tp, void *fh, - struct sk_buff *skb, struct tcmsg *t) + struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) { struct fw_head *head = rtnl_dereference(tp->root); struct fw_filter *f = fh; diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index a1b803fd372e..1f9d481b0fbb 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -109,7 +109,8 @@ static int mall_replace_hw_filter(struct tcf_proto *tp, return 0; } -static void mall_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) +static void mall_destroy(struct tcf_proto *tp, bool rtnl_held, + struct netlink_ext_ack *extack) { struct cls_mall_head *head = rtnl_dereference(tp->root); @@ -145,7 +146,8 @@ static int mall_set_parms(struct net *net, struct tcf_proto *tp, { int err; - err = tcf_exts_validate(net, tp, tb, est, &head->exts, ovr, extack); + err = tcf_exts_validate(net, tp, tb, est, &head->exts, ovr, true, + extack); if (err < 0) return err; @@ -159,7 +161,8 @@ static int mall_set_parms(struct net *net, struct tcf_proto *tp, static int mall_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, - void **arg, bool ovr, struct netlink_ext_ack *extack) + void **arg, bool ovr, bool rtnl_held, + struct netlink_ext_ack *extack) { struct cls_mall_head *head = rtnl_dereference(tp->root); struct nlattr *tb[TCA_MATCHALL_MAX + 1]; @@ -232,17 +235,21 @@ err_exts_init: } static int mall_delete(struct tcf_proto *tp, void *arg, bool *last, - struct netlink_ext_ack *extack) + bool rtnl_held, struct netlink_ext_ack *extack) { return -EOPNOTSUPP; } -static void mall_walk(struct tcf_proto *tp, struct tcf_walker *arg) +static void mall_walk(struct tcf_proto *tp, struct tcf_walker *arg, + bool rtnl_held) { struct cls_mall_head *head = rtnl_dereference(tp->root); if (arg->count < arg->skip) goto skip; + + if (!head) + return; if (arg->fn(tp, head, arg) < 0) arg->stop = 1; skip: @@ -279,7 +286,7 @@ static int mall_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb, } static int mall_dump(struct net *net, struct tcf_proto *tp, void *fh, - struct sk_buff *skb, struct tcmsg *t) + struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) { struct tc_matchall_pcnt gpf = {}; struct cls_mall_head *head = fh; diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index 0404aa5fa7cb..444d15a75d98 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -276,7 +276,8 @@ static void route4_queue_work(struct route4_filter *f) tcf_queue_work(&f->rwork, route4_delete_filter_work); } -static void route4_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) +static void route4_destroy(struct tcf_proto *tp, bool rtnl_held, + struct netlink_ext_ack *extack) { struct route4_head *head = rtnl_dereference(tp->root); int h1, h2; @@ -312,7 +313,7 @@ static void route4_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) } static int route4_delete(struct tcf_proto *tp, void *arg, bool *last, - struct netlink_ext_ack *extack) + bool rtnl_held, struct netlink_ext_ack *extack) { struct route4_head *head = rtnl_dereference(tp->root); struct route4_filter *f = arg; @@ -393,7 +394,7 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp, struct route4_bucket *b; int err; - err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr, extack); + err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr, true, extack); if (err < 0) return err; @@ -468,7 +469,7 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp, static int route4_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, void **arg, bool ovr, - struct netlink_ext_ack *extack) + bool rtnl_held, struct netlink_ext_ack *extack) { struct route4_head *head = rtnl_dereference(tp->root); struct route4_filter __rcu **fp; @@ -560,15 +561,13 @@ errout: return err; } -static void route4_walk(struct tcf_proto *tp, struct tcf_walker *arg) +static void route4_walk(struct tcf_proto *tp, struct tcf_walker *arg, + bool rtnl_held) { struct route4_head *head = rtnl_dereference(tp->root); unsigned int h, h1; - if (head == NULL) - arg->stop = 1; - - if (arg->stop) + if (head == NULL || arg->stop) return; for (h = 0; h <= 256; h++) { @@ -597,7 +596,7 @@ static void route4_walk(struct tcf_proto *tp, struct tcf_walker *arg) } static int route4_dump(struct net *net, struct tcf_proto *tp, void *fh, - struct sk_buff *skb, struct tcmsg *t) + struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) { struct route4_filter *f = fh; struct nlattr *nest; diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h index e9ccf7daea7d..4d3836178fa5 100644 --- a/net/sched/cls_rsvp.h +++ b/net/sched/cls_rsvp.h @@ -312,7 +312,8 @@ static void rsvp_delete_filter(struct tcf_proto *tp, struct rsvp_filter *f) __rsvp_delete_filter(f); } -static void rsvp_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) +static void rsvp_destroy(struct tcf_proto *tp, bool rtnl_held, + struct netlink_ext_ack *extack) { struct rsvp_head *data = rtnl_dereference(tp->root); int h1, h2; @@ -341,7 +342,7 @@ static void rsvp_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) } static int rsvp_delete(struct tcf_proto *tp, void *arg, bool *last, - struct netlink_ext_ack *extack) + bool rtnl_held, struct netlink_ext_ack *extack) { struct rsvp_head *head = rtnl_dereference(tp->root); struct rsvp_filter *nfp, *f = arg; @@ -477,7 +478,8 @@ static int rsvp_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, - void **arg, bool ovr, struct netlink_ext_ack *extack) + void **arg, bool ovr, bool rtnl_held, + struct netlink_ext_ack *extack) { struct rsvp_head *data = rtnl_dereference(tp->root); struct rsvp_filter *f, *nfp; @@ -502,7 +504,8 @@ static int rsvp_change(struct net *net, struct sk_buff *in_skb, err = tcf_exts_init(&e, TCA_RSVP_ACT, TCA_RSVP_POLICE); if (err < 0) return err; - err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr, extack); + err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr, true, + extack); if (err < 0) goto errout2; @@ -654,7 +657,8 @@ errout2: return err; } -static void rsvp_walk(struct tcf_proto *tp, struct tcf_walker *arg) +static void rsvp_walk(struct tcf_proto *tp, struct tcf_walker *arg, + bool rtnl_held) { struct rsvp_head *head = rtnl_dereference(tp->root); unsigned int h, h1; @@ -688,7 +692,7 @@ static void rsvp_walk(struct tcf_proto *tp, struct tcf_walker *arg) } static int rsvp_dump(struct net *net, struct tcf_proto *tp, void *fh, - struct sk_buff *skb, struct tcmsg *t) + struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) { struct rsvp_filter *f = fh; struct rsvp_session *s; diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index 9ccc93f257db..e1981628047b 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -173,7 +173,7 @@ static void tcindex_destroy_fexts_work(struct work_struct *work) } static int tcindex_delete(struct tcf_proto *tp, void *arg, bool *last, - struct netlink_ext_ack *extack) + bool rtnl_held, struct netlink_ext_ack *extack) { struct tcindex_data *p = rtnl_dereference(tp->root); struct tcindex_filter_result *r = arg; @@ -226,7 +226,7 @@ static int tcindex_destroy_element(struct tcf_proto *tp, { bool last; - return tcindex_delete(tp, arg, &last, NULL); + return tcindex_delete(tp, arg, &last, false, NULL); } static void __tcindex_destroy(struct rcu_head *head) @@ -275,7 +275,7 @@ static void tcindex_free_perfect_hash(struct tcindex_data *cp) kfree(cp->perfect); } -static int tcindex_alloc_perfect_hash(struct tcindex_data *cp) +static int tcindex_alloc_perfect_hash(struct net *net, struct tcindex_data *cp) { int i, err = 0; @@ -289,6 +289,9 @@ static int tcindex_alloc_perfect_hash(struct tcindex_data *cp) TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); if (err < 0) goto errout; +#ifdef CONFIG_NET_CLS_ACT + cp->perfect[i].exts.net = net; +#endif } return 0; @@ -305,16 +308,16 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, struct nlattr *est, bool ovr, struct netlink_ext_ack *extack) { struct tcindex_filter_result new_filter_result, *old_r = r; - struct tcindex_filter_result cr; struct tcindex_data *cp = NULL, *oldp; struct tcindex_filter *f = NULL; /* make gcc behave */ + struct tcf_result cr = {}; int err, balloc = 0; struct tcf_exts e; err = tcf_exts_init(&e, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); if (err < 0) return err; - err = tcf_exts_validate(net, tp, tb, est, &e, ovr, extack); + err = tcf_exts_validate(net, tp, tb, est, &e, ovr, true, extack); if (err < 0) goto errout; @@ -337,7 +340,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, if (p->perfect) { int i; - if (tcindex_alloc_perfect_hash(cp) < 0) + if (tcindex_alloc_perfect_hash(net, cp) < 0) goto errout; for (i = 0; i < cp->hash; i++) cp->perfect[i].res = p->perfect[i].res; @@ -348,11 +351,8 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, err = tcindex_filter_result_init(&new_filter_result); if (err < 0) goto errout1; - err = tcindex_filter_result_init(&cr); - if (err < 0) - goto errout1; if (old_r) - cr.res = r->res; + cr = r->res; if (tb[TCA_TCINDEX_HASH]) cp->hash = nla_get_u32(tb[TCA_TCINDEX_HASH]); @@ -406,7 +406,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, err = -ENOMEM; if (!cp->perfect && !cp->h) { if (valid_perfect_hash(cp)) { - if (tcindex_alloc_perfect_hash(cp) < 0) + if (tcindex_alloc_perfect_hash(net, cp) < 0) goto errout_alloc; balloc = 1; } else { @@ -443,8 +443,8 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, } if (tb[TCA_TCINDEX_CLASSID]) { - cr.res.classid = nla_get_u32(tb[TCA_TCINDEX_CLASSID]); - tcf_bind_filter(tp, &cr.res, base); + cr.classid = nla_get_u32(tb[TCA_TCINDEX_CLASSID]); + tcf_bind_filter(tp, &cr, base); } if (old_r && old_r != r) { @@ -456,7 +456,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, } oldp = p; - r->res = cr.res; + r->res = cr; tcf_exts_change(&r->exts, &e); rcu_assign_pointer(tp->root, cp); @@ -475,6 +475,8 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, ; /* nothing */ rcu_assign_pointer(*fp, f); + } else { + tcf_exts_destroy(&new_filter_result.exts); } if (oldp) @@ -487,7 +489,6 @@ errout_alloc: else if (balloc == 2) kfree(cp->h); errout1: - tcf_exts_destroy(&cr.exts); tcf_exts_destroy(&new_filter_result.exts); errout: kfree(cp); @@ -499,7 +500,7 @@ static int tcindex_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, void **arg, bool ovr, - struct netlink_ext_ack *extack) + bool rtnl_held, struct netlink_ext_ack *extack) { struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_TCINDEX_MAX + 1]; @@ -522,7 +523,8 @@ tcindex_change(struct net *net, struct sk_buff *in_skb, tca[TCA_RATE], ovr, extack); } -static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker) +static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker, + bool rtnl_held) { struct tcindex_data *p = rtnl_dereference(tp->root); struct tcindex_filter *f, *next; @@ -558,7 +560,7 @@ static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker) } } -static void tcindex_destroy(struct tcf_proto *tp, +static void tcindex_destroy(struct tcf_proto *tp, bool rtnl_held, struct netlink_ext_ack *extack) { struct tcindex_data *p = rtnl_dereference(tp->root); @@ -568,14 +570,14 @@ static void tcindex_destroy(struct tcf_proto *tp, walker.count = 0; walker.skip = 0; walker.fn = tcindex_destroy_element; - tcindex_walk(tp, &walker); + tcindex_walk(tp, &walker, true); call_rcu(&p->rcu, __tcindex_destroy); } static int tcindex_dump(struct net *net, struct tcf_proto *tp, void *fh, - struct sk_buff *skb, struct tcmsg *t) + struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) { struct tcindex_data *p = rtnl_dereference(tp->root); struct tcindex_filter_result *r = fh; diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index dcea21004604..27d29c04dcc9 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -629,7 +629,8 @@ static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht, return -ENOENT; } -static void u32_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) +static void u32_destroy(struct tcf_proto *tp, bool rtnl_held, + struct netlink_ext_ack *extack) { struct tc_u_common *tp_c = tp->data; struct tc_u_hnode *root_ht = rtnl_dereference(tp->root); @@ -663,7 +664,7 @@ static void u32_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) } static int u32_delete(struct tcf_proto *tp, void *arg, bool *last, - struct netlink_ext_ack *extack) + bool rtnl_held, struct netlink_ext_ack *extack) { struct tc_u_hnode *ht = arg; struct tc_u_common *tp_c = tp->data; @@ -726,7 +727,7 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp, { int err; - err = tcf_exts_validate(net, tp, tb, est, &n->exts, ovr, extack); + err = tcf_exts_validate(net, tp, tb, est, &n->exts, ovr, true, extack); if (err < 0) return err; @@ -858,7 +859,7 @@ static struct tc_u_knode *u32_init_knode(struct tcf_proto *tp, static int u32_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, - struct nlattr **tca, void **arg, bool ovr, + struct nlattr **tca, void **arg, bool ovr, bool rtnl_held, struct netlink_ext_ack *extack) { struct tc_u_common *tp_c = tp->data; @@ -1123,7 +1124,8 @@ erridr: return err; } -static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg) +static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg, + bool rtnl_held) { struct tc_u_common *tp_c = tp->data; struct tc_u_hnode *ht; @@ -1281,7 +1283,7 @@ static void u32_bind_class(void *fh, u32 classid, unsigned long cl) } static int u32_dump(struct net *net, struct tcf_proto *tp, void *fh, - struct sk_buff *skb, struct tcmsg *t) + struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) { struct tc_u_knode *n = fh; struct tc_u_hnode *ht_up, *ht_down; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 03e26e8d0ec9..b8a388e4bcc4 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1201,9 +1201,11 @@ static struct Qdisc *qdisc_create(struct net_device *dev, } else { if (handle == 0) { handle = qdisc_alloc_handle(dev); - err = -ENOMEM; - if (handle == 0) + if (handle == 0) { + NL_SET_ERR_MSG(extack, "Maximum number of qdisc handles was exceeded"); + err = -ENOSPC; goto err_out3; + } } if (!netif_is_multiqueue(dev)) sch->flags |= TCQ_F_ONETXQUEUE; @@ -1909,17 +1911,19 @@ static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid, block = cops->tcf_block(q, cl, NULL); if (!block) return; - list_for_each_entry(chain, &block->chain_list, list) { + for (chain = tcf_get_next_chain(block, NULL); + chain; + chain = tcf_get_next_chain(block, chain)) { struct tcf_proto *tp; - for (tp = rtnl_dereference(chain->filter_chain); - tp; tp = rtnl_dereference(tp->next)) { + for (tp = tcf_get_next_proto(chain, NULL, true); + tp; tp = tcf_get_next_proto(chain, tp, true)) { struct tcf_bind_args arg = {}; arg.w.fn = tcf_node_bind; arg.classid = clid; arg.cl = new_cl; - tp->ops->walk(tp, &arg.w); + tp->ops->walk(tp, &arg.w, true); } } } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 66ba2ce2320f..38e5add14fab 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -500,7 +500,7 @@ static void dev_watchdog_down(struct net_device *dev) * netif_carrier_on - set carrier * @dev: network device * - * Device has detected that carrier. + * Device has detected acquisition of carrier. */ void netif_carrier_on(struct net_device *dev) { @@ -1366,7 +1366,11 @@ static void mini_qdisc_rcu_func(struct rcu_head *head) void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp, struct tcf_proto *tp_head) { - struct mini_Qdisc *miniq_old = rtnl_dereference(*miniqp->p_miniq); + /* Protected with chain0->filter_chain_lock. + * Can't access chain directly because tp_head can be NULL. + */ + struct mini_Qdisc *miniq_old = + rcu_dereference_protected(*miniqp->p_miniq, 1); struct mini_Qdisc *miniq; if (!tp_head) { diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 201c888604e4..d2c7d0d2abc1 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -101,7 +101,7 @@ static struct sctp_association *sctp_association_init( * socket values. */ asoc->max_retrans = sp->assocparams.sasoc_asocmaxrxt; - asoc->pf_retrans = net->sctp.pf_retrans; + asoc->pf_retrans = sp->pf_retrans; asoc->rto_initial = msecs_to_jiffies(sp->rtoinfo.srto_initial); asoc->rto_max = msecs_to_jiffies(sp->rtoinfo.srto_max); @@ -1651,8 +1651,11 @@ int sctp_assoc_set_id(struct sctp_association *asoc, gfp_t gfp) if (preload) idr_preload(gfp); spin_lock_bh(&sctp_assocs_id_lock); - /* 0 is not a valid assoc_id, must be >= 1 */ - ret = idr_alloc_cyclic(&sctp_assocs_id, asoc, 1, 0, GFP_NOWAIT); + /* 0, 1, 2 are used as SCTP_FUTURE_ASSOC, SCTP_CURRENT_ASSOC and + * SCTP_ALL_ASSOC, so an available id must be > SCTP_ALL_ASSOC. + */ + ret = idr_alloc_cyclic(&sctp_assocs_id, asoc, SCTP_ALL_ASSOC + 1, 0, + GFP_NOWAIT); spin_unlock_bh(&sctp_assocs_id_lock); if (preload) idr_preload_end(); diff --git a/net/sctp/diag.c b/net/sctp/diag.c index 078f01a8d582..435847d98b51 100644 --- a/net/sctp/diag.c +++ b/net/sctp/diag.c @@ -256,6 +256,7 @@ static size_t inet_assoc_attr_size(struct sctp_association *asoc) + nla_total_size(1) /* INET_DIAG_TOS */ + nla_total_size(1) /* INET_DIAG_TCLASS */ + nla_total_size(4) /* INET_DIAG_MARK */ + + nla_total_size(4) /* INET_DIAG_CLASS_ID */ + nla_total_size(addrlen * asoc->peer.transport_count) + nla_total_size(addrlen * addrcnt) + nla_total_size(sizeof(struct inet_diag_meminfo)) diff --git a/net/sctp/offload.c b/net/sctp/offload.c index 123e9f2dc226..edfcf16e704c 100644 --- a/net/sctp/offload.c +++ b/net/sctp/offload.c @@ -36,6 +36,7 @@ static __le32 sctp_gso_make_checksum(struct sk_buff *skb) { skb->ip_summed = CHECKSUM_NONE; skb->csum_not_inet = 0; + gso_reset_checksum(skb, ~0); return sctp_compute_cksum(skb, skb_transport_offset(skb)); } diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index c37e1c2dec9d..fd33281999b5 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -212,7 +212,7 @@ void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q) INIT_LIST_HEAD(&q->retransmit); INIT_LIST_HEAD(&q->sacked); INIT_LIST_HEAD(&q->abandoned); - sctp_sched_set_sched(asoc, SCTP_SS_DEFAULT); + sctp_sched_set_sched(asoc, sctp_sk(asoc->base.sk)->default_ss); } /* Free the outqueue structure and any related pending chunks. diff --git a/net/sctp/socket.c b/net/sctp/socket.c index f93c3cf9e567..a78e55a1bb9c 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -248,7 +248,7 @@ struct sctp_association *sctp_id2assoc(struct sock *sk, sctp_assoc_t id) } /* Otherwise this is a UDP-style socket. */ - if (!id || (id == (sctp_assoc_t)-1)) + if (id <= SCTP_ALL_ASSOC) return NULL; spin_lock_bh(&sctp_assocs_id_lock); @@ -2027,7 +2027,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_transport *transport = NULL; struct sctp_sndrcvinfo _sinfo, *sinfo; - struct sctp_association *asoc; + struct sctp_association *asoc, *tmp; struct sctp_cmsgs cmsgs; union sctp_addr *daddr; bool new = false; @@ -2053,7 +2053,7 @@ static int sctp_sendmsg(struct sock *sk, struct msghdr *msg, size_t msg_len) /* SCTP_SENDALL process */ if ((sflags & SCTP_SENDALL) && sctp_style(sk, UDP)) { - list_for_each_entry(asoc, &ep->asocs, asocs) { + list_for_each_entry_safe(asoc, tmp, &ep->asocs, asocs) { err = sctp_sendmsg_check_sflags(asoc, sflags, msg, msg_len); if (err == 0) @@ -2750,12 +2750,13 @@ static int sctp_setsockopt_peer_addr_params(struct sock *sk, return -EINVAL; } - /* Get association, if assoc_id != 0 and the socket is a one - * to many style socket, and an association was not found, then - * the id was invalid. + /* Get association, if assoc_id != SCTP_FUTURE_ASSOC and the + * socket is a one to many style socket, and an association + * was not found, then the id was invalid. */ asoc = sctp_id2assoc(sk, params.spp_assoc_id); - if (!asoc && params.spp_assoc_id && sctp_style(sk, UDP)) + if (!asoc && params.spp_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) return -EINVAL; /* Heartbeat demand can only be sent on a transport or @@ -2797,6 +2798,43 @@ static inline __u32 sctp_spp_sackdelay_disable(__u32 param_flags) return (param_flags & ~SPP_SACKDELAY) | SPP_SACKDELAY_DISABLE; } +static void sctp_apply_asoc_delayed_ack(struct sctp_sack_info *params, + struct sctp_association *asoc) +{ + struct sctp_transport *trans; + + if (params->sack_delay) { + asoc->sackdelay = msecs_to_jiffies(params->sack_delay); + asoc->param_flags = + sctp_spp_sackdelay_enable(asoc->param_flags); + } + if (params->sack_freq == 1) { + asoc->param_flags = + sctp_spp_sackdelay_disable(asoc->param_flags); + } else if (params->sack_freq > 1) { + asoc->sackfreq = params->sack_freq; + asoc->param_flags = + sctp_spp_sackdelay_enable(asoc->param_flags); + } + + list_for_each_entry(trans, &asoc->peer.transport_addr_list, + transports) { + if (params->sack_delay) { + trans->sackdelay = msecs_to_jiffies(params->sack_delay); + trans->param_flags = + sctp_spp_sackdelay_enable(trans->param_flags); + } + if (params->sack_freq == 1) { + trans->param_flags = + sctp_spp_sackdelay_disable(trans->param_flags); + } else if (params->sack_freq > 1) { + trans->sackfreq = params->sack_freq; + trans->param_flags = + sctp_spp_sackdelay_enable(trans->param_flags); + } + } +} + /* * 7.1.23. Get or set delayed ack timer (SCTP_DELAYED_SACK) * @@ -2836,10 +2874,9 @@ static inline __u32 sctp_spp_sackdelay_disable(__u32 param_flags) static int sctp_setsockopt_delayed_ack(struct sock *sk, char __user *optval, unsigned int optlen) { - struct sctp_sack_info params; - struct sctp_transport *trans = NULL; - struct sctp_association *asoc = NULL; - struct sctp_sock *sp = sctp_sk(sk); + struct sctp_sock *sp = sctp_sk(sk); + struct sctp_association *asoc; + struct sctp_sack_info params; if (optlen == sizeof(struct sctp_sack_info)) { if (copy_from_user(¶ms, optval, optlen)) @@ -2867,67 +2904,42 @@ static int sctp_setsockopt_delayed_ack(struct sock *sk, if (params.sack_delay > 500) return -EINVAL; - /* Get association, if sack_assoc_id != 0 and the socket is a one - * to many style socket, and an association was not found, then - * the id was invalid. + /* Get association, if sack_assoc_id != SCTP_FUTURE_ASSOC and the + * socket is a one to many style socket, and an association + * was not found, then the id was invalid. */ asoc = sctp_id2assoc(sk, params.sack_assoc_id); - if (!asoc && params.sack_assoc_id && sctp_style(sk, UDP)) + if (!asoc && params.sack_assoc_id > SCTP_ALL_ASSOC && + sctp_style(sk, UDP)) return -EINVAL; - if (params.sack_delay) { - if (asoc) { - asoc->sackdelay = - msecs_to_jiffies(params.sack_delay); - asoc->param_flags = - sctp_spp_sackdelay_enable(asoc->param_flags); - } else { + if (asoc) { + sctp_apply_asoc_delayed_ack(¶ms, asoc); + + return 0; + } + + if (params.sack_assoc_id == SCTP_FUTURE_ASSOC || + params.sack_assoc_id == SCTP_ALL_ASSOC) { + if (params.sack_delay) { sp->sackdelay = params.sack_delay; sp->param_flags = sctp_spp_sackdelay_enable(sp->param_flags); } - } - - if (params.sack_freq == 1) { - if (asoc) { - asoc->param_flags = - sctp_spp_sackdelay_disable(asoc->param_flags); - } else { + if (params.sack_freq == 1) { sp->param_flags = sctp_spp_sackdelay_disable(sp->param_flags); - } - } else if (params.sack_freq > 1) { - if (asoc) { - asoc->sackfreq = params.sack_freq; - asoc->param_flags = - sctp_spp_sackdelay_enable(asoc->param_flags); - } else { + } else if (params.sack_freq > 1) { sp->sackfreq = params.sack_freq; sp->param_flags = sctp_spp_sackdelay_enable(sp->param_flags); } } - /* If change is for association, also apply to each transport. */ - if (asoc) { - list_for_each_entry(trans, &asoc->peer.transport_addr_list, - transports) { - if (params.sack_delay) { - trans->sackdelay = - msecs_to_jiffies(params.sack_delay); - trans->param_flags = - sctp_spp_sackdelay_enable(trans->param_flags); - } - if (params.sack_freq == 1) { - trans->param_flags = - sctp_spp_sackdelay_disable(trans->param_flags); - } else if (params.sack_freq > 1) { - trans->sackfreq = params.sack_freq; - trans->param_flags = - sctp_spp_sackdelay_enable(trans->param_flags); - } - } - } + if (params.sack_assoc_id == SCTP_CURRENT_ASSOC || + params.sack_assoc_id == SCTP_ALL_ASSOC) + list_for_each_entry(asoc, &sp->ep->asocs, asocs) + sctp_apply_asoc_delayed_ack(¶ms, asoc); return 0; } @@ -2997,15 +3009,22 @@ static int sctp_setsockopt_default_send_param(struct sock *sk, return -EINVAL; asoc = sctp_id2assoc(sk, info.sinfo_assoc_id); - if (!asoc && info.sinfo_assoc_id && sctp_style(sk, UDP)) + if (!asoc && info.sinfo_assoc_id > SCTP_ALL_ASSOC && + sctp_style(sk, UDP)) return -EINVAL; + if (asoc) { asoc->default_stream = info.sinfo_stream; asoc->default_flags = info.sinfo_flags; asoc->default_ppid = info.sinfo_ppid; asoc->default_context = info.sinfo_context; asoc->default_timetolive = info.sinfo_timetolive; - } else { + + return 0; + } + + if (info.sinfo_assoc_id == SCTP_FUTURE_ASSOC || + info.sinfo_assoc_id == SCTP_ALL_ASSOC) { sp->default_stream = info.sinfo_stream; sp->default_flags = info.sinfo_flags; sp->default_ppid = info.sinfo_ppid; @@ -3013,6 +3032,17 @@ static int sctp_setsockopt_default_send_param(struct sock *sk, sp->default_timetolive = info.sinfo_timetolive; } + if (info.sinfo_assoc_id == SCTP_CURRENT_ASSOC || + info.sinfo_assoc_id == SCTP_ALL_ASSOC) { + list_for_each_entry(asoc, &sp->ep->asocs, asocs) { + asoc->default_stream = info.sinfo_stream; + asoc->default_flags = info.sinfo_flags; + asoc->default_ppid = info.sinfo_ppid; + asoc->default_context = info.sinfo_context; + asoc->default_timetolive = info.sinfo_timetolive; + } + } + return 0; } @@ -3037,20 +3067,37 @@ static int sctp_setsockopt_default_sndinfo(struct sock *sk, return -EINVAL; asoc = sctp_id2assoc(sk, info.snd_assoc_id); - if (!asoc && info.snd_assoc_id && sctp_style(sk, UDP)) + if (!asoc && info.snd_assoc_id > SCTP_ALL_ASSOC && + sctp_style(sk, UDP)) return -EINVAL; + if (asoc) { asoc->default_stream = info.snd_sid; asoc->default_flags = info.snd_flags; asoc->default_ppid = info.snd_ppid; asoc->default_context = info.snd_context; - } else { + + return 0; + } + + if (info.snd_assoc_id == SCTP_FUTURE_ASSOC || + info.snd_assoc_id == SCTP_ALL_ASSOC) { sp->default_stream = info.snd_sid; sp->default_flags = info.snd_flags; sp->default_ppid = info.snd_ppid; sp->default_context = info.snd_context; } + if (info.snd_assoc_id == SCTP_CURRENT_ASSOC || + info.snd_assoc_id == SCTP_ALL_ASSOC) { + list_for_each_entry(asoc, &sp->ep->asocs, asocs) { + asoc->default_stream = info.snd_sid; + asoc->default_flags = info.snd_flags; + asoc->default_ppid = info.snd_ppid; + asoc->default_context = info.snd_context; + } + } + return 0; } @@ -3144,7 +3191,8 @@ static int sctp_setsockopt_rtoinfo(struct sock *sk, char __user *optval, unsigne asoc = sctp_id2assoc(sk, rtoinfo.srto_assoc_id); /* Set the values to the specific association */ - if (!asoc && rtoinfo.srto_assoc_id && sctp_style(sk, UDP)) + if (!asoc && rtoinfo.srto_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) return -EINVAL; rto_max = rtoinfo.srto_max; @@ -3206,7 +3254,8 @@ static int sctp_setsockopt_associnfo(struct sock *sk, char __user *optval, unsig asoc = sctp_id2assoc(sk, assocparams.sasoc_assoc_id); - if (!asoc && assocparams.sasoc_assoc_id && sctp_style(sk, UDP)) + if (!asoc && assocparams.sasoc_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) return -EINVAL; /* Set the values to the specific association */ @@ -3319,7 +3368,7 @@ static int sctp_setsockopt_maxseg(struct sock *sk, char __user *optval, unsigned current->comm, task_pid_nr(current)); if (copy_from_user(&val, optval, optlen)) return -EFAULT; - params.assoc_id = 0; + params.assoc_id = SCTP_FUTURE_ASSOC; } else if (optlen == sizeof(struct sctp_assoc_value)) { if (copy_from_user(¶ms, optval, optlen)) return -EFAULT; @@ -3329,6 +3378,9 @@ static int sctp_setsockopt_maxseg(struct sock *sk, char __user *optval, unsigned } asoc = sctp_id2assoc(sk, params.assoc_id); + if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) + return -EINVAL; if (val) { int min_len, max_len; @@ -3346,8 +3398,6 @@ static int sctp_setsockopt_maxseg(struct sock *sk, char __user *optval, unsigned asoc->user_frag = val; sctp_assoc_update_frag_point(asoc); } else { - if (params.assoc_id && sctp_style(sk, UDP)) - return -EINVAL; sp->user_frag = val; } @@ -3460,8 +3510,8 @@ static int sctp_setsockopt_adaptation_layer(struct sock *sk, char __user *optval static int sctp_setsockopt_context(struct sock *sk, char __user *optval, unsigned int optlen) { + struct sctp_sock *sp = sctp_sk(sk); struct sctp_assoc_value params; - struct sctp_sock *sp; struct sctp_association *asoc; if (optlen != sizeof(struct sctp_assoc_value)) @@ -3469,17 +3519,26 @@ static int sctp_setsockopt_context(struct sock *sk, char __user *optval, if (copy_from_user(¶ms, optval, optlen)) return -EFAULT; - sp = sctp_sk(sk); + asoc = sctp_id2assoc(sk, params.assoc_id); + if (!asoc && params.assoc_id > SCTP_ALL_ASSOC && + sctp_style(sk, UDP)) + return -EINVAL; - if (params.assoc_id != 0) { - asoc = sctp_id2assoc(sk, params.assoc_id); - if (!asoc) - return -EINVAL; + if (asoc) { asoc->default_rcv_context = params.assoc_value; - } else { - sp->default_rcv_context = params.assoc_value; + + return 0; } + if (params.assoc_id == SCTP_FUTURE_ASSOC || + params.assoc_id == SCTP_ALL_ASSOC) + sp->default_rcv_context = params.assoc_value; + + if (params.assoc_id == SCTP_CURRENT_ASSOC || + params.assoc_id == SCTP_ALL_ASSOC) + list_for_each_entry(asoc, &sp->ep->asocs, asocs) + asoc->default_rcv_context = params.assoc_value; + return 0; } @@ -3580,11 +3639,9 @@ static int sctp_setsockopt_maxburst(struct sock *sk, char __user *optval, unsigned int optlen) { + struct sctp_sock *sp = sctp_sk(sk); struct sctp_assoc_value params; - struct sctp_sock *sp; struct sctp_association *asoc; - int val; - int assoc_id = 0; if (optlen == sizeof(int)) { pr_warn_ratelimited(DEPRECATED @@ -3592,25 +3649,34 @@ static int sctp_setsockopt_maxburst(struct sock *sk, "Use of int in max_burst socket option deprecated.\n" "Use struct sctp_assoc_value instead\n", current->comm, task_pid_nr(current)); - if (copy_from_user(&val, optval, optlen)) + if (copy_from_user(¶ms.assoc_value, optval, optlen)) return -EFAULT; + params.assoc_id = SCTP_FUTURE_ASSOC; } else if (optlen == sizeof(struct sctp_assoc_value)) { if (copy_from_user(¶ms, optval, optlen)) return -EFAULT; - val = params.assoc_value; - assoc_id = params.assoc_id; } else return -EINVAL; - sp = sctp_sk(sk); + asoc = sctp_id2assoc(sk, params.assoc_id); + if (!asoc && params.assoc_id > SCTP_ALL_ASSOC && + sctp_style(sk, UDP)) + return -EINVAL; - if (assoc_id != 0) { - asoc = sctp_id2assoc(sk, assoc_id); - if (!asoc) - return -EINVAL; - asoc->max_burst = val; - } else - sp->max_burst = val; + if (asoc) { + asoc->max_burst = params.assoc_value; + + return 0; + } + + if (params.assoc_id == SCTP_FUTURE_ASSOC || + params.assoc_id == SCTP_ALL_ASSOC) + sp->max_burst = params.assoc_value; + + if (params.assoc_id == SCTP_CURRENT_ASSOC || + params.assoc_id == SCTP_ALL_ASSOC) + list_for_each_entry(asoc, &sp->ep->asocs, asocs) + asoc->max_burst = params.assoc_value; return 0; } @@ -3702,7 +3768,7 @@ static int sctp_setsockopt_auth_key(struct sock *sk, struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_authkey *authkey; struct sctp_association *asoc; - int ret; + int ret = -EINVAL; if (!ep->auth_enable) return -EACCES; @@ -3712,25 +3778,44 @@ static int sctp_setsockopt_auth_key(struct sock *sk, /* authkey->sca_keylength is u16, so optlen can't be bigger than * this. */ - optlen = min_t(unsigned int, optlen, USHRT_MAX + - sizeof(struct sctp_authkey)); + optlen = min_t(unsigned int, optlen, USHRT_MAX + sizeof(*authkey)); authkey = memdup_user(optval, optlen); if (IS_ERR(authkey)) return PTR_ERR(authkey); - if (authkey->sca_keylength > optlen - sizeof(struct sctp_authkey)) { - ret = -EINVAL; + if (authkey->sca_keylength > optlen - sizeof(*authkey)) goto out; - } asoc = sctp_id2assoc(sk, authkey->sca_assoc_id); - if (!asoc && authkey->sca_assoc_id && sctp_style(sk, UDP)) { - ret = -EINVAL; + if (!asoc && authkey->sca_assoc_id > SCTP_ALL_ASSOC && + sctp_style(sk, UDP)) + goto out; + + if (asoc) { + ret = sctp_auth_set_key(ep, asoc, authkey); goto out; } - ret = sctp_auth_set_key(ep, asoc, authkey); + if (authkey->sca_assoc_id == SCTP_FUTURE_ASSOC || + authkey->sca_assoc_id == SCTP_ALL_ASSOC) { + ret = sctp_auth_set_key(ep, asoc, authkey); + if (ret) + goto out; + } + + ret = 0; + + if (authkey->sca_assoc_id == SCTP_CURRENT_ASSOC || + authkey->sca_assoc_id == SCTP_ALL_ASSOC) { + list_for_each_entry(asoc, &ep->asocs, asocs) { + int res = sctp_auth_set_key(ep, asoc, authkey); + + if (res && !ret) + ret = res; + } + } + out: kzfree(authkey); return ret; @@ -3747,8 +3832,9 @@ static int sctp_setsockopt_active_key(struct sock *sk, unsigned int optlen) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; - struct sctp_authkeyid val; struct sctp_association *asoc; + struct sctp_authkeyid val; + int ret = 0; if (!ep->auth_enable) return -EACCES; @@ -3759,10 +3845,32 @@ static int sctp_setsockopt_active_key(struct sock *sk, return -EFAULT; asoc = sctp_id2assoc(sk, val.scact_assoc_id); - if (!asoc && val.scact_assoc_id && sctp_style(sk, UDP)) + if (!asoc && val.scact_assoc_id > SCTP_ALL_ASSOC && + sctp_style(sk, UDP)) return -EINVAL; - return sctp_auth_set_active_key(ep, asoc, val.scact_keynumber); + if (asoc) + return sctp_auth_set_active_key(ep, asoc, val.scact_keynumber); + + if (val.scact_assoc_id == SCTP_FUTURE_ASSOC || + val.scact_assoc_id == SCTP_ALL_ASSOC) { + ret = sctp_auth_set_active_key(ep, asoc, val.scact_keynumber); + if (ret) + return ret; + } + + if (val.scact_assoc_id == SCTP_CURRENT_ASSOC || + val.scact_assoc_id == SCTP_ALL_ASSOC) { + list_for_each_entry(asoc, &ep->asocs, asocs) { + int res = sctp_auth_set_active_key(ep, asoc, + val.scact_keynumber); + + if (res && !ret) + ret = res; + } + } + + return ret; } /* @@ -3775,8 +3883,9 @@ static int sctp_setsockopt_del_key(struct sock *sk, unsigned int optlen) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; - struct sctp_authkeyid val; struct sctp_association *asoc; + struct sctp_authkeyid val; + int ret = 0; if (!ep->auth_enable) return -EACCES; @@ -3787,11 +3896,32 @@ static int sctp_setsockopt_del_key(struct sock *sk, return -EFAULT; asoc = sctp_id2assoc(sk, val.scact_assoc_id); - if (!asoc && val.scact_assoc_id && sctp_style(sk, UDP)) + if (!asoc && val.scact_assoc_id > SCTP_ALL_ASSOC && + sctp_style(sk, UDP)) return -EINVAL; - return sctp_auth_del_key_id(ep, asoc, val.scact_keynumber); + if (asoc) + return sctp_auth_del_key_id(ep, asoc, val.scact_keynumber); + + if (val.scact_assoc_id == SCTP_FUTURE_ASSOC || + val.scact_assoc_id == SCTP_ALL_ASSOC) { + ret = sctp_auth_del_key_id(ep, asoc, val.scact_keynumber); + if (ret) + return ret; + } + + if (val.scact_assoc_id == SCTP_CURRENT_ASSOC || + val.scact_assoc_id == SCTP_ALL_ASSOC) { + list_for_each_entry(asoc, &ep->asocs, asocs) { + int res = sctp_auth_del_key_id(ep, asoc, + val.scact_keynumber); + if (res && !ret) + ret = res; + } + } + + return ret; } /* @@ -3803,8 +3933,9 @@ static int sctp_setsockopt_deactivate_key(struct sock *sk, char __user *optval, unsigned int optlen) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; - struct sctp_authkeyid val; struct sctp_association *asoc; + struct sctp_authkeyid val; + int ret = 0; if (!ep->auth_enable) return -EACCES; @@ -3815,10 +3946,32 @@ static int sctp_setsockopt_deactivate_key(struct sock *sk, char __user *optval, return -EFAULT; asoc = sctp_id2assoc(sk, val.scact_assoc_id); - if (!asoc && val.scact_assoc_id && sctp_style(sk, UDP)) + if (!asoc && val.scact_assoc_id > SCTP_ALL_ASSOC && + sctp_style(sk, UDP)) return -EINVAL; - return sctp_auth_deact_key_id(ep, asoc, val.scact_keynumber); + if (asoc) + return sctp_auth_deact_key_id(ep, asoc, val.scact_keynumber); + + if (val.scact_assoc_id == SCTP_FUTURE_ASSOC || + val.scact_assoc_id == SCTP_ALL_ASSOC) { + ret = sctp_auth_deact_key_id(ep, asoc, val.scact_keynumber); + if (ret) + return ret; + } + + if (val.scact_assoc_id == SCTP_CURRENT_ASSOC || + val.scact_assoc_id == SCTP_ALL_ASSOC) { + list_for_each_entry(asoc, &ep->asocs, asocs) { + int res = sctp_auth_deact_key_id(ep, asoc, + val.scact_keynumber); + + if (res && !ret) + ret = res; + } + } + + return ret; } /* @@ -3884,11 +4037,25 @@ static int sctp_setsockopt_paddr_thresholds(struct sock *sk, sizeof(struct sctp_paddrthlds))) return -EFAULT; - - if (sctp_is_any(sk, (const union sctp_addr *)&val.spt_address)) { - asoc = sctp_id2assoc(sk, val.spt_assoc_id); - if (!asoc) + if (!sctp_is_any(sk, (const union sctp_addr *)&val.spt_address)) { + trans = sctp_addr_id2transport(sk, &val.spt_address, + val.spt_assoc_id); + if (!trans) return -ENOENT; + + if (val.spt_pathmaxrxt) + trans->pathmaxrxt = val.spt_pathmaxrxt; + trans->pf_retrans = val.spt_pathpfthld; + + return 0; + } + + asoc = sctp_id2assoc(sk, val.spt_assoc_id); + if (!asoc && val.spt_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) + return -EINVAL; + + if (asoc) { list_for_each_entry(trans, &asoc->peer.transport_addr_list, transports) { if (val.spt_pathmaxrxt) @@ -3900,14 +4067,11 @@ static int sctp_setsockopt_paddr_thresholds(struct sock *sk, asoc->pathmaxrxt = val.spt_pathmaxrxt; asoc->pf_retrans = val.spt_pathpfthld; } else { - trans = sctp_addr_id2transport(sk, &val.spt_address, - val.spt_assoc_id); - if (!trans) - return -ENOENT; + struct sctp_sock *sp = sctp_sk(sk); if (val.spt_pathmaxrxt) - trans->pathmaxrxt = val.spt_pathmaxrxt; - trans->pf_retrans = val.spt_pathpfthld; + sp->pathmaxrxt = val.spt_pathmaxrxt; + sp->pf_retrans = val.spt_pathpfthld; } return 0; @@ -3950,6 +4114,7 @@ static int sctp_setsockopt_pr_supported(struct sock *sk, unsigned int optlen) { struct sctp_assoc_value params; + struct sctp_association *asoc; if (optlen != sizeof(params)) return -EINVAL; @@ -3957,6 +4122,11 @@ static int sctp_setsockopt_pr_supported(struct sock *sk, if (copy_from_user(¶ms, optval, optlen)) return -EFAULT; + asoc = sctp_id2assoc(sk, params.assoc_id); + if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) + return -EINVAL; + sctp_sk(sk)->ep->prsctp_enable = !!params.assoc_value; return 0; @@ -3966,6 +4136,7 @@ static int sctp_setsockopt_default_prinfo(struct sock *sk, char __user *optval, unsigned int optlen) { + struct sctp_sock *sp = sctp_sk(sk); struct sctp_default_prinfo info; struct sctp_association *asoc; int retval = -EINVAL; @@ -3985,19 +4156,31 @@ static int sctp_setsockopt_default_prinfo(struct sock *sk, info.pr_value = 0; asoc = sctp_id2assoc(sk, info.pr_assoc_id); + if (!asoc && info.pr_assoc_id > SCTP_ALL_ASSOC && + sctp_style(sk, UDP)) + goto out; + + retval = 0; + if (asoc) { SCTP_PR_SET_POLICY(asoc->default_flags, info.pr_policy); asoc->default_timetolive = info.pr_value; - } else if (!info.pr_assoc_id) { - struct sctp_sock *sp = sctp_sk(sk); + goto out; + } + if (info.pr_assoc_id == SCTP_FUTURE_ASSOC || + info.pr_assoc_id == SCTP_ALL_ASSOC) { SCTP_PR_SET_POLICY(sp->default_flags, info.pr_policy); sp->default_timetolive = info.pr_value; - } else { - goto out; } - retval = 0; + if (info.pr_assoc_id == SCTP_CURRENT_ASSOC || + info.pr_assoc_id == SCTP_ALL_ASSOC) { + list_for_each_entry(asoc, &sp->ep->asocs, asocs) { + SCTP_PR_SET_POLICY(asoc->default_flags, info.pr_policy); + asoc->default_timetolive = info.pr_value; + } + } out: return retval; @@ -4020,15 +4203,14 @@ static int sctp_setsockopt_reconfig_supported(struct sock *sk, } asoc = sctp_id2assoc(sk, params.assoc_id); - if (asoc) { - asoc->reconf_enable = !!params.assoc_value; - } else if (!params.assoc_id) { - struct sctp_sock *sp = sctp_sk(sk); - - sp->ep->reconf_enable = !!params.assoc_value; - } else { + if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) goto out; - } + + if (asoc) + asoc->reconf_enable = !!params.assoc_value; + else + sctp_sk(sk)->ep->reconf_enable = !!params.assoc_value; retval = 0; @@ -4040,6 +4222,7 @@ static int sctp_setsockopt_enable_strreset(struct sock *sk, char __user *optval, unsigned int optlen) { + struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_assoc_value params; struct sctp_association *asoc; int retval = -EINVAL; @@ -4056,17 +4239,25 @@ static int sctp_setsockopt_enable_strreset(struct sock *sk, goto out; asoc = sctp_id2assoc(sk, params.assoc_id); + if (!asoc && params.assoc_id > SCTP_ALL_ASSOC && + sctp_style(sk, UDP)) + goto out; + + retval = 0; + if (asoc) { asoc->strreset_enable = params.assoc_value; - } else if (!params.assoc_id) { - struct sctp_sock *sp = sctp_sk(sk); - - sp->ep->strreset_enable = params.assoc_value; - } else { goto out; } - retval = 0; + if (params.assoc_id == SCTP_FUTURE_ASSOC || + params.assoc_id == SCTP_ALL_ASSOC) + ep->strreset_enable = params.assoc_value; + + if (params.assoc_id == SCTP_CURRENT_ASSOC || + params.assoc_id == SCTP_ALL_ASSOC) + list_for_each_entry(asoc, &ep->asocs, asocs) + asoc->strreset_enable = params.assoc_value; out: return retval; @@ -4161,29 +4352,44 @@ static int sctp_setsockopt_scheduler(struct sock *sk, char __user *optval, unsigned int optlen) { + struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; struct sctp_assoc_value params; - int retval = -EINVAL; + int retval = 0; if (optlen < sizeof(params)) - goto out; + return -EINVAL; optlen = sizeof(params); - if (copy_from_user(¶ms, optval, optlen)) { - retval = -EFAULT; - goto out; - } + if (copy_from_user(¶ms, optval, optlen)) + return -EFAULT; if (params.assoc_value > SCTP_SS_MAX) - goto out; + return -EINVAL; asoc = sctp_id2assoc(sk, params.assoc_id); - if (!asoc) - goto out; + if (!asoc && params.assoc_id > SCTP_ALL_ASSOC && + sctp_style(sk, UDP)) + return -EINVAL; + + if (asoc) + return sctp_sched_set_sched(asoc, params.assoc_value); - retval = sctp_sched_set_sched(asoc, params.assoc_value); + if (params.assoc_id == SCTP_FUTURE_ASSOC || + params.assoc_id == SCTP_ALL_ASSOC) + sp->default_ss = params.assoc_value; + + if (params.assoc_id == SCTP_CURRENT_ASSOC || + params.assoc_id == SCTP_ALL_ASSOC) { + list_for_each_entry(asoc, &sp->ep->asocs, asocs) { + int ret = sctp_sched_set_sched(asoc, + params.assoc_value); + + if (ret && !retval) + retval = ret; + } + } -out: return retval; } @@ -4191,8 +4397,8 @@ static int sctp_setsockopt_scheduler_value(struct sock *sk, char __user *optval, unsigned int optlen) { - struct sctp_association *asoc; struct sctp_stream_value params; + struct sctp_association *asoc; int retval = -EINVAL; if (optlen < sizeof(params)) @@ -4205,11 +4411,24 @@ static int sctp_setsockopt_scheduler_value(struct sock *sk, } asoc = sctp_id2assoc(sk, params.assoc_id); - if (!asoc) + if (!asoc && params.assoc_id != SCTP_CURRENT_ASSOC && + sctp_style(sk, UDP)) goto out; - retval = sctp_sched_set_value(asoc, params.stream_id, - params.stream_value, GFP_KERNEL); + if (asoc) { + retval = sctp_sched_set_value(asoc, params.stream_id, + params.stream_value, GFP_KERNEL); + goto out; + } + + retval = 0; + + list_for_each_entry(asoc, &sctp_sk(sk)->ep->asocs, asocs) { + int ret = sctp_sched_set_value(asoc, params.stream_id, + params.stream_value, GFP_KERNEL); + if (ret && !retval) /* try to return the 1st error. */ + retval = ret; + } out: return retval; @@ -4220,8 +4439,8 @@ static int sctp_setsockopt_interleaving_supported(struct sock *sk, unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); - struct net *net = sock_net(sk); struct sctp_assoc_value params; + struct sctp_association *asoc; int retval = -EINVAL; if (optlen < sizeof(params)) @@ -4233,10 +4452,12 @@ static int sctp_setsockopt_interleaving_supported(struct sock *sk, goto out; } - if (params.assoc_id) + asoc = sctp_id2assoc(sk, params.assoc_id); + if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) goto out; - if (!net->sctp.intl_enable || !sp->frag_interleave) { + if (!sock_net(sk)->sctp.intl_enable || !sp->frag_interleave) { retval = -EPERM; goto out; } @@ -4271,54 +4492,69 @@ static int sctp_setsockopt_reuse_port(struct sock *sk, char __user *optval, return 0; } +static int sctp_assoc_ulpevent_type_set(struct sctp_event *param, + struct sctp_association *asoc) +{ + struct sctp_ulpevent *event; + + sctp_ulpevent_type_set(&asoc->subscribe, param->se_type, param->se_on); + + if (param->se_type == SCTP_SENDER_DRY_EVENT && param->se_on) { + if (sctp_outq_is_empty(&asoc->outqueue)) { + event = sctp_ulpevent_make_sender_dry_event(asoc, + GFP_USER | __GFP_NOWARN); + if (!event) + return -ENOMEM; + + asoc->stream.si->enqueue_event(&asoc->ulpq, event); + } + } + + return 0; +} + static int sctp_setsockopt_event(struct sock *sk, char __user *optval, unsigned int optlen) { + struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; - struct sctp_ulpevent *event; struct sctp_event param; int retval = 0; - if (optlen < sizeof(param)) { - retval = -EINVAL; - goto out; - } + if (optlen < sizeof(param)) + return -EINVAL; optlen = sizeof(param); - if (copy_from_user(¶m, optval, optlen)) { - retval = -EFAULT; - goto out; - } + if (copy_from_user(¶m, optval, optlen)) + return -EFAULT; if (param.se_type < SCTP_SN_TYPE_BASE || - param.se_type > SCTP_SN_TYPE_MAX) { - retval = -EINVAL; - goto out; - } + param.se_type > SCTP_SN_TYPE_MAX) + return -EINVAL; asoc = sctp_id2assoc(sk, param.se_assoc_id); - if (!asoc) { - sctp_ulpevent_type_set(&sctp_sk(sk)->subscribe, - param.se_type, param.se_on); - goto out; - } + if (!asoc && param.se_assoc_id > SCTP_ALL_ASSOC && + sctp_style(sk, UDP)) + return -EINVAL; - sctp_ulpevent_type_set(&asoc->subscribe, param.se_type, param.se_on); + if (asoc) + return sctp_assoc_ulpevent_type_set(¶m, asoc); - if (param.se_type == SCTP_SENDER_DRY_EVENT && param.se_on) { - if (sctp_outq_is_empty(&asoc->outqueue)) { - event = sctp_ulpevent_make_sender_dry_event(asoc, - GFP_USER | __GFP_NOWARN); - if (!event) { - retval = -ENOMEM; - goto out; - } + if (param.se_assoc_id == SCTP_FUTURE_ASSOC || + param.se_assoc_id == SCTP_ALL_ASSOC) + sctp_ulpevent_type_set(&sp->subscribe, + param.se_type, param.se_on); - asoc->stream.si->enqueue_event(&asoc->ulpq, event); + if (param.se_assoc_id == SCTP_CURRENT_ASSOC || + param.se_assoc_id == SCTP_ALL_ASSOC) { + list_for_each_entry(asoc, &sp->ep->asocs, asocs) { + int ret = sctp_assoc_ulpevent_type_set(¶m, asoc); + + if (ret && !retval) + retval = ret; } } -out: return retval; } @@ -4777,12 +5013,14 @@ static int sctp_init_sock(struct sock *sk) */ sp->hbinterval = net->sctp.hb_interval; sp->pathmaxrxt = net->sctp.max_retrans_path; + sp->pf_retrans = net->sctp.pf_retrans; sp->pathmtu = 0; /* allow default discovery */ sp->sackdelay = net->sctp.sack_timeout; sp->sackfreq = 2; sp->param_flags = SPP_HB_ENABLE | SPP_PMTUD_ENABLE | SPP_SACKDELAY_ENABLE; + sp->default_ss = SCTP_SS_DEFAULT; /* If enabled no SCTP message fragmentation will be performed. * Configure through SCTP_DISABLE_FRAGMENTS socket option. @@ -5676,12 +5914,13 @@ static int sctp_getsockopt_peer_addr_params(struct sock *sk, int len, } } - /* Get association, if assoc_id != 0 and the socket is a one - * to many style socket, and an association was not found, then - * the id was invalid. + /* Get association, if assoc_id != SCTP_FUTURE_ASSOC and the + * socket is a one to many style socket, and an association + * was not found, then the id was invalid. */ asoc = sctp_id2assoc(sk, params.spp_assoc_id); - if (!asoc && params.spp_assoc_id && sctp_style(sk, UDP)) { + if (!asoc && params.spp_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) { pr_debug("%s: failed no association\n", __func__); return -EINVAL; } @@ -5810,19 +6049,19 @@ static int sctp_getsockopt_delayed_ack(struct sock *sk, int len, } else return -EINVAL; - /* Get association, if sack_assoc_id != 0 and the socket is a one - * to many style socket, and an association was not found, then - * the id was invalid. + /* Get association, if sack_assoc_id != SCTP_FUTURE_ASSOC and the + * socket is a one to many style socket, and an association + * was not found, then the id was invalid. */ asoc = sctp_id2assoc(sk, params.sack_assoc_id); - if (!asoc && params.sack_assoc_id && sctp_style(sk, UDP)) + if (!asoc && params.sack_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) return -EINVAL; if (asoc) { /* Fetch association values. */ if (asoc->param_flags & SPP_SACKDELAY_ENABLE) { - params.sack_delay = jiffies_to_msecs( - asoc->sackdelay); + params.sack_delay = jiffies_to_msecs(asoc->sackdelay); params.sack_freq = asoc->sackfreq; } else { @@ -6175,8 +6414,10 @@ static int sctp_getsockopt_default_send_param(struct sock *sk, return -EFAULT; asoc = sctp_id2assoc(sk, info.sinfo_assoc_id); - if (!asoc && info.sinfo_assoc_id && sctp_style(sk, UDP)) + if (!asoc && info.sinfo_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) return -EINVAL; + if (asoc) { info.sinfo_stream = asoc->default_stream; info.sinfo_flags = asoc->default_flags; @@ -6219,8 +6460,10 @@ static int sctp_getsockopt_default_sndinfo(struct sock *sk, int len, return -EFAULT; asoc = sctp_id2assoc(sk, info.snd_assoc_id); - if (!asoc && info.snd_assoc_id && sctp_style(sk, UDP)) + if (!asoc && info.snd_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) return -EINVAL; + if (asoc) { info.snd_sid = asoc->default_stream; info.snd_flags = asoc->default_flags; @@ -6296,7 +6539,8 @@ static int sctp_getsockopt_rtoinfo(struct sock *sk, int len, asoc = sctp_id2assoc(sk, rtoinfo.srto_assoc_id); - if (!asoc && rtoinfo.srto_assoc_id && sctp_style(sk, UDP)) + if (!asoc && rtoinfo.srto_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) return -EINVAL; /* Values corresponding to the specific association. */ @@ -6353,7 +6597,8 @@ static int sctp_getsockopt_associnfo(struct sock *sk, int len, asoc = sctp_id2assoc(sk, assocparams.sasoc_assoc_id); - if (!asoc && assocparams.sasoc_assoc_id && sctp_style(sk, UDP)) + if (!asoc && assocparams.sasoc_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) return -EINVAL; /* Values correspoinding to the specific association */ @@ -6428,7 +6673,6 @@ static int sctp_getsockopt_context(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_assoc_value params; - struct sctp_sock *sp; struct sctp_association *asoc; if (len < sizeof(struct sctp_assoc_value)) @@ -6439,16 +6683,13 @@ static int sctp_getsockopt_context(struct sock *sk, int len, if (copy_from_user(¶ms, optval, len)) return -EFAULT; - sp = sctp_sk(sk); + asoc = sctp_id2assoc(sk, params.assoc_id); + if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) + return -EINVAL; - if (params.assoc_id != 0) { - asoc = sctp_id2assoc(sk, params.assoc_id); - if (!asoc) - return -EINVAL; - params.assoc_value = asoc->default_rcv_context; - } else { - params.assoc_value = sp->default_rcv_context; - } + params.assoc_value = asoc ? asoc->default_rcv_context + : sctp_sk(sk)->default_rcv_context; if (put_user(len, optlen)) return -EFAULT; @@ -6497,7 +6738,7 @@ static int sctp_getsockopt_maxseg(struct sock *sk, int len, "Use of int in maxseg socket option.\n" "Use struct sctp_assoc_value instead\n", current->comm, task_pid_nr(current)); - params.assoc_id = 0; + params.assoc_id = SCTP_FUTURE_ASSOC; } else if (len >= sizeof(struct sctp_assoc_value)) { len = sizeof(struct sctp_assoc_value); if (copy_from_user(¶ms, optval, len)) @@ -6506,7 +6747,8 @@ static int sctp_getsockopt_maxseg(struct sock *sk, int len, return -EINVAL; asoc = sctp_id2assoc(sk, params.assoc_id); - if (!asoc && params.assoc_id && sctp_style(sk, UDP)) + if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) return -EINVAL; if (asoc) @@ -6583,7 +6825,6 @@ static int sctp_getsockopt_maxburst(struct sock *sk, int len, int __user *optlen) { struct sctp_assoc_value params; - struct sctp_sock *sp; struct sctp_association *asoc; if (len == sizeof(int)) { @@ -6592,7 +6833,7 @@ static int sctp_getsockopt_maxburst(struct sock *sk, int len, "Use of int in max_burst socket option.\n" "Use struct sctp_assoc_value instead\n", current->comm, task_pid_nr(current)); - params.assoc_id = 0; + params.assoc_id = SCTP_FUTURE_ASSOC; } else if (len >= sizeof(struct sctp_assoc_value)) { len = sizeof(struct sctp_assoc_value); if (copy_from_user(¶ms, optval, len)) @@ -6600,15 +6841,12 @@ static int sctp_getsockopt_maxburst(struct sock *sk, int len, } else return -EINVAL; - sp = sctp_sk(sk); + asoc = sctp_id2assoc(sk, params.assoc_id); + if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) + return -EINVAL; - if (params.assoc_id != 0) { - asoc = sctp_id2assoc(sk, params.assoc_id); - if (!asoc) - return -EINVAL; - params.assoc_value = asoc->max_burst; - } else - params.assoc_value = sp->max_burst; + params.assoc_value = asoc ? asoc->max_burst : sctp_sk(sk)->max_burst; if (len == sizeof(int)) { if (copy_to_user(optval, ¶ms.assoc_value, len)) @@ -6759,14 +6997,12 @@ static int sctp_getsockopt_local_auth_chunks(struct sock *sk, int len, to = p->gauth_chunks; asoc = sctp_id2assoc(sk, val.gauth_assoc_id); - if (!asoc && val.gauth_assoc_id && sctp_style(sk, UDP)) + if (!asoc && val.gauth_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) return -EINVAL; - if (asoc) - ch = (struct sctp_chunks_param *)asoc->c.auth_chunks; - else - ch = ep->auth_chunk_list; - + ch = asoc ? (struct sctp_chunks_param *)asoc->c.auth_chunks + : ep->auth_chunk_list; if (!ch) goto num; @@ -6911,14 +7147,7 @@ static int sctp_getsockopt_paddr_thresholds(struct sock *sk, if (copy_from_user(&val, (struct sctp_paddrthlds __user *)optval, len)) return -EFAULT; - if (sctp_is_any(sk, (const union sctp_addr *)&val.spt_address)) { - asoc = sctp_id2assoc(sk, val.spt_assoc_id); - if (!asoc) - return -ENOENT; - - val.spt_pathpfthld = asoc->pf_retrans; - val.spt_pathmaxrxt = asoc->pathmaxrxt; - } else { + if (!sctp_is_any(sk, (const union sctp_addr *)&val.spt_address)) { trans = sctp_addr_id2transport(sk, &val.spt_address, val.spt_assoc_id); if (!trans) @@ -6926,6 +7155,23 @@ static int sctp_getsockopt_paddr_thresholds(struct sock *sk, val.spt_pathmaxrxt = trans->pathmaxrxt; val.spt_pathpfthld = trans->pf_retrans; + + return 0; + } + + asoc = sctp_id2assoc(sk, val.spt_assoc_id); + if (!asoc && val.spt_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) + return -EINVAL; + + if (asoc) { + val.spt_pathpfthld = asoc->pf_retrans; + val.spt_pathmaxrxt = asoc->pathmaxrxt; + } else { + struct sctp_sock *sp = sctp_sk(sk); + + val.spt_pathpfthld = sp->pf_retrans; + val.spt_pathmaxrxt = sp->pathmaxrxt; } if (put_user(len, optlen) || copy_to_user(optval, &val, len)) @@ -7056,17 +7302,15 @@ static int sctp_getsockopt_pr_supported(struct sock *sk, int len, goto out; asoc = sctp_id2assoc(sk, params.assoc_id); - if (asoc) { - params.assoc_value = asoc->prsctp_enable; - } else if (!params.assoc_id) { - struct sctp_sock *sp = sctp_sk(sk); - - params.assoc_value = sp->ep->prsctp_enable; - } else { + if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) { retval = -EINVAL; goto out; } + params.assoc_value = asoc ? asoc->prsctp_enable + : sctp_sk(sk)->ep->prsctp_enable; + if (put_user(len, optlen)) goto out; @@ -7097,17 +7341,20 @@ static int sctp_getsockopt_default_prinfo(struct sock *sk, int len, goto out; asoc = sctp_id2assoc(sk, info.pr_assoc_id); + if (!asoc && info.pr_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) { + retval = -EINVAL; + goto out; + } + if (asoc) { info.pr_policy = SCTP_PR_POLICY(asoc->default_flags); info.pr_value = asoc->default_timetolive; - } else if (!info.pr_assoc_id) { + } else { struct sctp_sock *sp = sctp_sk(sk); info.pr_policy = SCTP_PR_POLICY(sp->default_flags); info.pr_value = sp->default_timetolive; - } else { - retval = -EINVAL; - goto out; } if (put_user(len, optlen)) @@ -7263,17 +7510,15 @@ static int sctp_getsockopt_reconfig_supported(struct sock *sk, int len, goto out; asoc = sctp_id2assoc(sk, params.assoc_id); - if (asoc) { - params.assoc_value = asoc->reconf_enable; - } else if (!params.assoc_id) { - struct sctp_sock *sp = sctp_sk(sk); - - params.assoc_value = sp->ep->reconf_enable; - } else { + if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) { retval = -EINVAL; goto out; } + params.assoc_value = asoc ? asoc->reconf_enable + : sctp_sk(sk)->ep->reconf_enable; + if (put_user(len, optlen)) goto out; @@ -7304,17 +7549,15 @@ static int sctp_getsockopt_enable_strreset(struct sock *sk, int len, goto out; asoc = sctp_id2assoc(sk, params.assoc_id); - if (asoc) { - params.assoc_value = asoc->strreset_enable; - } else if (!params.assoc_id) { - struct sctp_sock *sp = sctp_sk(sk); - - params.assoc_value = sp->ep->strreset_enable; - } else { + if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) { retval = -EINVAL; goto out; } + params.assoc_value = asoc ? asoc->strreset_enable + : sctp_sk(sk)->ep->strreset_enable; + if (put_user(len, optlen)) goto out; @@ -7345,12 +7588,14 @@ static int sctp_getsockopt_scheduler(struct sock *sk, int len, goto out; asoc = sctp_id2assoc(sk, params.assoc_id); - if (!asoc) { + if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) { retval = -EINVAL; goto out; } - params.assoc_value = sctp_sched_get_sched(asoc); + params.assoc_value = asoc ? sctp_sched_get_sched(asoc) + : sctp_sk(sk)->default_ss; if (put_user(len, optlen)) goto out; @@ -7424,17 +7669,15 @@ static int sctp_getsockopt_interleaving_supported(struct sock *sk, int len, goto out; asoc = sctp_id2assoc(sk, params.assoc_id); - if (asoc) { - params.assoc_value = asoc->intl_enable; - } else if (!params.assoc_id) { - struct sctp_sock *sp = sctp_sk(sk); - - params.assoc_value = sp->strm_interleave; - } else { + if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) { retval = -EINVAL; goto out; } + params.assoc_value = asoc ? asoc->intl_enable + : sctp_sk(sk)->strm_interleave; + if (put_user(len, optlen)) goto out; @@ -7486,6 +7729,10 @@ static int sctp_getsockopt_event(struct sock *sk, int len, char __user *optval, return -EINVAL; asoc = sctp_id2assoc(sk, param.se_assoc_id); + if (!asoc && param.se_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) + return -EINVAL; + subscribe = asoc ? asoc->subscribe : sctp_sk(sk)->subscribe; param.se_on = sctp_ulpevent_type_enabled(subscribe, param.se_type); diff --git a/net/sctp/stream.c b/net/sctp/stream.c index 80e0ae5534ec..2936ed17bf9e 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -84,6 +84,19 @@ static void fa_zero(struct flex_array *fa, size_t index, size_t count) } } +static size_t fa_index(struct flex_array *fa, void *elem, size_t count) +{ + size_t index = 0; + + while (count--) { + if (elem == flex_array_get(fa, index)) + break; + index++; + } + + return index; +} + /* Migrates chunks from stream queues to new stream queues if needed, * but not across associations. Also, removes those chunks to streams * higher than the new max. @@ -131,8 +144,10 @@ static void sctp_stream_outq_migrate(struct sctp_stream *stream, } } - for (i = outcnt; i < stream->outcnt; i++) + for (i = outcnt; i < stream->outcnt; i++) { kfree(SCTP_SO(stream, i)->ext); + SCTP_SO(stream, i)->ext = NULL; + } } static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt, @@ -147,6 +162,13 @@ static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt, if (stream->out) { fa_copy(out, stream->out, 0, min(outcnt, stream->outcnt)); + if (stream->out_curr) { + size_t index = fa_index(stream->out, stream->out_curr, + stream->outcnt); + + BUG_ON(index == stream->outcnt); + stream->out_curr = flex_array_get(out, index); + } fa_free(stream->out); } diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index c4e56602e0c6..46fa9f3016cc 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -42,8 +42,11 @@ #include "smc_rx.h" #include "smc_close.h" -static DEFINE_MUTEX(smc_create_lgr_pending); /* serialize link group - * creation +static DEFINE_MUTEX(smc_server_lgr_pending); /* serialize link group + * creation on server + */ +static DEFINE_MUTEX(smc_client_lgr_pending); /* serialize link group + * creation on client */ static void smc_tcp_listen_work(struct work_struct *); @@ -145,32 +148,33 @@ static int smc_release(struct socket *sock) rc = smc_close_active(smc); sock_set_flag(sk, SOCK_DEAD); sk->sk_shutdown |= SHUTDOWN_MASK; - } - - sk->sk_prot->unhash(sk); - - if (smc->clcsock) { - if (smc->use_fallback && sk->sk_state == SMC_LISTEN) { + } else { + if (sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_INIT) + sock_put(sk); /* passive closing */ + if (sk->sk_state == SMC_LISTEN) { /* wake up clcsock accept */ rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR); } - mutex_lock(&smc->clcsock_release_lock); - sock_release(smc->clcsock); - smc->clcsock = NULL; - mutex_unlock(&smc->clcsock_release_lock); - } - if (smc->use_fallback) { - if (sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_INIT) - sock_put(sk); /* passive closing */ sk->sk_state = SMC_CLOSED; sk->sk_state_change(sk); } + sk->sk_prot->unhash(sk); + + if (sk->sk_state == SMC_CLOSED) { + if (smc->clcsock) { + mutex_lock(&smc->clcsock_release_lock); + sock_release(smc->clcsock); + smc->clcsock = NULL; + mutex_unlock(&smc->clcsock_release_lock); + } + if (!smc->use_fallback) + smc_conn_free(&smc->conn); + } + /* detach socket */ sock_orphan(sk); sock->sk = NULL; - if (!smc->use_fallback && sk->sk_state == SMC_CLOSED) - smc_conn_free(&smc->conn); release_sock(sk); sock_put(sk); /* final sock_put */ @@ -291,7 +295,8 @@ static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk, (1UL << SOCK_RXQ_OVFL) | \ (1UL << SOCK_WIFI_STATUS) | \ (1UL << SOCK_NOFCS) | \ - (1UL << SOCK_FILTER_LOCKED)) + (1UL << SOCK_FILTER_LOCKED) | \ + (1UL << SOCK_TSTAMP_NEW)) /* copy only relevant settings and flags of SOL_SOCKET level from smc to * clc socket (since smc is not called for these options from net/core) */ @@ -475,7 +480,12 @@ static int smc_connect_abort(struct smc_sock *smc, int reason_code, { if (local_contact == SMC_FIRST_CONTACT) smc_lgr_forget(smc->conn.lgr); - mutex_unlock(&smc_create_lgr_pending); + if (smc->conn.lgr->is_smcd) + /* there is only one lgr role for SMC-D; use server lock */ + mutex_unlock(&smc_server_lgr_pending); + else + mutex_unlock(&smc_client_lgr_pending); + smc_conn_free(&smc->conn); return reason_code; } @@ -560,7 +570,7 @@ static int smc_connect_rdma(struct smc_sock *smc, struct smc_link *link; int reason_code = 0; - mutex_lock(&smc_create_lgr_pending); + mutex_lock(&smc_client_lgr_pending); local_contact = smc_conn_create(smc, false, aclc->hdr.flag, ibdev, ibport, ntoh24(aclc->qpn), &aclc->lcl, NULL, 0); @@ -571,7 +581,8 @@ static int smc_connect_rdma(struct smc_sock *smc, reason_code = SMC_CLC_DECL_SYNCERR; /* synchr. error */ else reason_code = SMC_CLC_DECL_INTERR; /* other error */ - return smc_connect_abort(smc, reason_code, 0); + mutex_unlock(&smc_client_lgr_pending); + return reason_code; } link = &smc->conn.lgr->lnk[SMC_SINGLE_LINK]; @@ -615,7 +626,7 @@ static int smc_connect_rdma(struct smc_sock *smc, return smc_connect_abort(smc, reason_code, local_contact); } - mutex_unlock(&smc_create_lgr_pending); + mutex_unlock(&smc_client_lgr_pending); smc_copy_sock_settings_to_clc(smc); if (smc->sk.sk_state == SMC_INIT) @@ -632,11 +643,14 @@ static int smc_connect_ism(struct smc_sock *smc, int local_contact = SMC_FIRST_CONTACT; int rc = 0; - mutex_lock(&smc_create_lgr_pending); + /* there is only one lgr role for SMC-D; use server lock */ + mutex_lock(&smc_server_lgr_pending); local_contact = smc_conn_create(smc, true, aclc->hdr.flag, NULL, 0, 0, NULL, ismdev, aclc->gid); - if (local_contact < 0) - return smc_connect_abort(smc, SMC_CLC_DECL_MEM, 0); + if (local_contact < 0) { + mutex_unlock(&smc_server_lgr_pending); + return SMC_CLC_DECL_MEM; + } /* Create send and receive buffers */ if (smc_buf_create(smc, true)) @@ -650,7 +664,7 @@ static int smc_connect_ism(struct smc_sock *smc, rc = smc_clc_send_confirm(smc); if (rc) return smc_connect_abort(smc, rc, local_contact); - mutex_unlock(&smc_create_lgr_pending); + mutex_unlock(&smc_server_lgr_pending); smc_copy_sock_settings_to_clc(smc); if (smc->sk.sk_state == SMC_INIT) @@ -1249,7 +1263,7 @@ static void smc_listen_work(struct work_struct *work) return; } - mutex_lock(&smc_create_lgr_pending); + mutex_lock(&smc_server_lgr_pending); smc_close_init(new_smc); smc_rx_init(new_smc); smc_tx_init(new_smc); @@ -1271,7 +1285,7 @@ static void smc_listen_work(struct work_struct *work) &local_contact) || smc_listen_rdma_reg(new_smc, local_contact))) { /* SMC not supported, decline */ - mutex_unlock(&smc_create_lgr_pending); + mutex_unlock(&smc_server_lgr_pending); smc_listen_decline(new_smc, SMC_CLC_DECL_MODEUNSUPP, local_contact); return; @@ -1280,29 +1294,33 @@ static void smc_listen_work(struct work_struct *work) /* send SMC Accept CLC message */ rc = smc_clc_send_accept(new_smc, local_contact); if (rc) { - mutex_unlock(&smc_create_lgr_pending); + mutex_unlock(&smc_server_lgr_pending); smc_listen_decline(new_smc, rc, local_contact); return; } + /* SMC-D does not need this lock any more */ + if (ism_supported) + mutex_unlock(&smc_server_lgr_pending); + /* receive SMC Confirm CLC message */ reason_code = smc_clc_wait_msg(new_smc, &cclc, sizeof(cclc), SMC_CLC_CONFIRM, CLC_WAIT_TIME); if (reason_code) { - mutex_unlock(&smc_create_lgr_pending); + if (!ism_supported) + mutex_unlock(&smc_server_lgr_pending); smc_listen_decline(new_smc, reason_code, local_contact); return; } /* finish worker */ if (!ism_supported) { - if (smc_listen_rdma_finish(new_smc, &cclc, local_contact)) { - mutex_unlock(&smc_create_lgr_pending); + rc = smc_listen_rdma_finish(new_smc, &cclc, local_contact); + mutex_unlock(&smc_server_lgr_pending); + if (rc) return; - } } smc_conn_save_peer_info(new_smc, &cclc); - mutex_unlock(&smc_create_lgr_pending); smc_listen_out_connected(new_smc); } @@ -1505,6 +1523,11 @@ static int smc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, smc = smc_sk(sk); lock_sock(sk); + if (sk->sk_state == SMC_CLOSED && (sk->sk_shutdown & RCV_SHUTDOWN)) { + /* socket was connected before, no more data to read */ + rc = 0; + goto out; + } if ((sk->sk_state == SMC_INIT) || (sk->sk_state == SMC_LISTEN) || (sk->sk_state == SMC_CLOSED)) @@ -1840,7 +1863,11 @@ static ssize_t smc_splice_read(struct socket *sock, loff_t *ppos, smc = smc_sk(sk); lock_sock(sk); - + if (sk->sk_state == SMC_CLOSED && (sk->sk_shutdown & RCV_SHUTDOWN)) { + /* socket was connected before, no more data to read */ + rc = 0; + goto out; + } if (sk->sk_state == SMC_INIT || sk->sk_state == SMC_LISTEN || sk->sk_state == SMC_CLOSED) diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index db83332ac1c8..d0b0f4c865b4 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -21,13 +21,6 @@ /********************************** send *************************************/ -struct smc_cdc_tx_pend { - struct smc_connection *conn; /* socket connection */ - union smc_host_cursor cursor; /* tx sndbuf cursor sent */ - union smc_host_cursor p_cursor; /* rx RMBE cursor produced */ - u16 ctrl_seq; /* conn. tx sequence # */ -}; - /* handler for send/transmission completion of a CDC msg */ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd, struct smc_link *link, @@ -61,12 +54,14 @@ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd, int smc_cdc_get_free_slot(struct smc_connection *conn, struct smc_wr_buf **wr_buf, + struct smc_rdma_wr **wr_rdma_buf, struct smc_cdc_tx_pend **pend) { struct smc_link *link = &conn->lgr->lnk[SMC_SINGLE_LINK]; int rc; rc = smc_wr_tx_get_free_slot(link, smc_cdc_tx_handler, wr_buf, + wr_rdma_buf, (struct smc_wr_tx_pend_priv **)pend); if (!conn->alert_token_local) /* abnormal termination */ @@ -96,6 +91,7 @@ int smc_cdc_msg_send(struct smc_connection *conn, struct smc_wr_buf *wr_buf, struct smc_cdc_tx_pend *pend) { + union smc_host_cursor cfed; struct smc_link *link; int rc; @@ -105,12 +101,12 @@ int smc_cdc_msg_send(struct smc_connection *conn, conn->tx_cdc_seq++; conn->local_tx_ctrl.seqno = conn->tx_cdc_seq; - smc_host_msg_to_cdc((struct smc_cdc_msg *)wr_buf, - &conn->local_tx_ctrl, conn); + smc_host_msg_to_cdc((struct smc_cdc_msg *)wr_buf, conn, &cfed); rc = smc_wr_tx_send(link, (struct smc_wr_tx_pend_priv *)pend); - if (!rc) - smc_curs_copy(&conn->rx_curs_confirmed, - &conn->local_tx_ctrl.cons, conn); + if (!rc) { + smc_curs_copy(&conn->rx_curs_confirmed, &cfed, conn); + conn->local_rx_ctrl.prod_flags.cons_curs_upd_req = 0; + } return rc; } @@ -121,11 +117,14 @@ static int smcr_cdc_get_slot_and_msg_send(struct smc_connection *conn) struct smc_wr_buf *wr_buf; int rc; - rc = smc_cdc_get_free_slot(conn, &wr_buf, &pend); + rc = smc_cdc_get_free_slot(conn, &wr_buf, NULL, &pend); if (rc) return rc; - return smc_cdc_msg_send(conn, wr_buf, pend); + spin_lock_bh(&conn->send_lock); + rc = smc_cdc_msg_send(conn, wr_buf, pend); + spin_unlock_bh(&conn->send_lock); + return rc; } int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn) @@ -195,6 +194,7 @@ int smcd_cdc_msg_send(struct smc_connection *conn) if (rc) return rc; smc_curs_copy(&conn->rx_curs_confirmed, &curs, conn); + conn->local_rx_ctrl.prod_flags.cons_curs_upd_req = 0; /* Calculate transmitted data and increment free send buffer space */ diff = smc_curs_diff(conn->sndbuf_desc->len, &conn->tx_curs_fin, &conn->tx_curs_sent); @@ -271,26 +271,18 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc, smp_mb__after_atomic(); smc->sk.sk_data_ready(&smc->sk); } else { - if (conn->local_rx_ctrl.prod_flags.write_blocked || - conn->local_rx_ctrl.prod_flags.cons_curs_upd_req || - conn->local_rx_ctrl.prod_flags.urg_data_pending) { - if (conn->local_rx_ctrl.prod_flags.urg_data_pending) - conn->urg_state = SMC_URG_NOTYET; - /* force immediate tx of current consumer cursor, but - * under send_lock to guarantee arrival in seqno-order - */ - if (smc->sk.sk_state != SMC_INIT) - smc_tx_sndbuf_nonempty(conn); - } + if (conn->local_rx_ctrl.prod_flags.write_blocked) + smc->sk.sk_data_ready(&smc->sk); + if (conn->local_rx_ctrl.prod_flags.urg_data_pending) + conn->urg_state = SMC_URG_NOTYET; } - /* piggy backed tx info */ /* trigger sndbuf consumer: RDMA write into peer RMBE and CDC */ - if (diff_cons && smc_tx_prepared_sends(conn)) { + if ((diff_cons && smc_tx_prepared_sends(conn)) || + conn->local_rx_ctrl.prod_flags.cons_curs_upd_req || + conn->local_rx_ctrl.prod_flags.urg_data_pending) smc_tx_sndbuf_nonempty(conn); - /* trigger socket release if connection closed */ - smc_close_wake_tx_prepared(smc); - } + if (diff_cons && conn->urg_tx_pend && atomic_read(&conn->peer_rmbe_space) == conn->peer_rmbe_size) { /* urg data confirmed by peer, indicate we're ready for more */ diff --git a/net/smc/smc_cdc.h b/net/smc/smc_cdc.h index b5bfe38c7f9b..861dc24c588c 100644 --- a/net/smc/smc_cdc.h +++ b/net/smc/smc_cdc.h @@ -160,7 +160,9 @@ static inline void smcd_curs_copy(union smcd_cdc_cursor *tgt, #endif } -/* calculate cursor difference between old and new, where old <= new */ +/* calculate cursor difference between old and new, where old <= new and + * difference cannot exceed size + */ static inline int smc_curs_diff(unsigned int size, union smc_host_cursor *old, union smc_host_cursor *new) @@ -185,28 +187,51 @@ static inline int smc_curs_comp(unsigned int size, return smc_curs_diff(size, old, new); } +/* calculate cursor difference between old and new, where old <= new and + * difference may exceed size + */ +static inline int smc_curs_diff_large(unsigned int size, + union smc_host_cursor *old, + union smc_host_cursor *new) +{ + if (old->wrap < new->wrap) + return min_t(int, + (size - old->count) + new->count + + (new->wrap - old->wrap - 1) * size, + size); + + if (old->wrap > new->wrap) /* wrap has switched from 0xffff to 0x0000 */ + return min_t(int, + (size - old->count) + new->count + + (new->wrap + 0xffff - old->wrap) * size, + size); + + return max_t(int, 0, (new->count - old->count)); +} + static inline void smc_host_cursor_to_cdc(union smc_cdc_cursor *peer, union smc_host_cursor *local, + union smc_host_cursor *save, struct smc_connection *conn) { - union smc_host_cursor temp; - - smc_curs_copy(&temp, local, conn); - peer->count = htonl(temp.count); - peer->wrap = htons(temp.wrap); + smc_curs_copy(save, local, conn); + peer->count = htonl(save->count); + peer->wrap = htons(save->wrap); /* peer->reserved = htons(0); must be ensured by caller */ } static inline void smc_host_msg_to_cdc(struct smc_cdc_msg *peer, - struct smc_host_cdc_msg *local, - struct smc_connection *conn) + struct smc_connection *conn, + union smc_host_cursor *save) { + struct smc_host_cdc_msg *local = &conn->local_tx_ctrl; + peer->common.type = local->common.type; peer->len = local->len; peer->seqno = htons(local->seqno); peer->token = htonl(local->token); - smc_host_cursor_to_cdc(&peer->prod, &local->prod, conn); - smc_host_cursor_to_cdc(&peer->cons, &local->cons, conn); + smc_host_cursor_to_cdc(&peer->prod, &local->prod, save, conn); + smc_host_cursor_to_cdc(&peer->cons, &local->cons, save, conn); peer->prod_flags = local->prod_flags; peer->conn_state_flags = local->conn_state_flags; } @@ -245,17 +270,18 @@ static inline void smcr_cdc_msg_to_host(struct smc_host_cdc_msg *local, } static inline void smcd_cdc_msg_to_host(struct smc_host_cdc_msg *local, - struct smcd_cdc_msg *peer) + struct smcd_cdc_msg *peer, + struct smc_connection *conn) { union smc_host_cursor temp; temp.wrap = peer->prod.wrap; temp.count = peer->prod.count; - atomic64_set(&local->prod.acurs, atomic64_read(&temp.acurs)); + smc_curs_copy(&local->prod, &temp, conn); temp.wrap = peer->cons.wrap; temp.count = peer->cons.count; - atomic64_set(&local->cons.acurs, atomic64_read(&temp.acurs)); + smc_curs_copy(&local->cons, &temp, conn); local->prod_flags = peer->cons.prod_flags; local->conn_state_flags = peer->cons.conn_state_flags; } @@ -265,15 +291,21 @@ static inline void smc_cdc_msg_to_host(struct smc_host_cdc_msg *local, struct smc_connection *conn) { if (conn->lgr->is_smcd) - smcd_cdc_msg_to_host(local, (struct smcd_cdc_msg *)peer); + smcd_cdc_msg_to_host(local, (struct smcd_cdc_msg *)peer, conn); else smcr_cdc_msg_to_host(local, peer, conn); } -struct smc_cdc_tx_pend; +struct smc_cdc_tx_pend { + struct smc_connection *conn; /* socket connection */ + union smc_host_cursor cursor; /* tx sndbuf cursor sent */ + union smc_host_cursor p_cursor; /* rx RMBE cursor produced */ + u16 ctrl_seq; /* conn. tx sequence # */ +}; int smc_cdc_get_free_slot(struct smc_connection *conn, struct smc_wr_buf **wr_buf, + struct smc_rdma_wr **wr_rdma_buf, struct smc_cdc_tx_pend **pend); void smc_cdc_tx_dismiss_slots(struct smc_connection *conn); int smc_cdc_msg_send(struct smc_connection *conn, struct smc_wr_buf *wr_buf, diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 776e9dfc915d..d53fd588d1f5 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -378,7 +378,7 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info) vec.iov_len = sizeof(struct smc_clc_msg_decline); len = kernel_sendmsg(smc->clcsock, &msg, &vec, 1, sizeof(struct smc_clc_msg_decline)); - if (len < sizeof(struct smc_clc_msg_decline)) + if (len < 0 || len < sizeof(struct smc_clc_msg_decline)) len = -EPROTO; return len > 0 ? 0 : len; } diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index ea2b87f29469..2ad37e998509 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -345,14 +345,7 @@ static void smc_close_passive_work(struct work_struct *work) switch (sk->sk_state) { case SMC_INIT: - if (atomic_read(&conn->bytes_to_rcv) || - (rxflags->peer_done_writing && - !smc_cdc_rxed_any_close(conn))) { - sk->sk_state = SMC_APPCLOSEWAIT1; - } else { - sk->sk_state = SMC_CLOSED; - sock_put(sk); /* passive closing */ - } + sk->sk_state = SMC_APPCLOSEWAIT1; break; case SMC_ACTIVE: sk->sk_state = SMC_APPCLOSEWAIT1; @@ -405,8 +398,13 @@ wakeup: if (old_state != sk->sk_state) { sk->sk_state_change(sk); if ((sk->sk_state == SMC_CLOSED) && - (sock_flag(sk, SOCK_DEAD) || !sk->sk_socket)) + (sock_flag(sk, SOCK_DEAD) || !sk->sk_socket)) { smc_conn_free(conn); + if (smc->clcsock) { + sock_release(smc->clcsock); + smc->clcsock = NULL; + } + } } release_sock(sk); sock_put(sk); /* sock_hold done by schedulers of close_work */ diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 35c1cdc93e1c..53a17cfa61af 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -118,7 +118,6 @@ static void __smc_lgr_unregister_conn(struct smc_connection *conn) rb_erase(&conn->alert_node, &lgr->conns_all); lgr->conns_num--; conn->alert_token_local = 0; - conn->lgr = NULL; sock_put(&smc->sk); /* sock_hold in smc_lgr_register_conn() */ } @@ -128,6 +127,8 @@ static void smc_lgr_unregister_conn(struct smc_connection *conn) { struct smc_link_group *lgr = conn->lgr; + if (!lgr) + return; write_lock_bh(&lgr->conns_lock); if (conn->alert_token_local) { __smc_lgr_unregister_conn(conn); @@ -159,8 +160,6 @@ static void smc_lgr_free_work(struct work_struct *work) bool conns; spin_lock_bh(&smc_lgr_list.lock); - if (list_empty(&lgr->list)) - goto free; read_lock_bh(&lgr->conns_lock); conns = RB_EMPTY_ROOT(&lgr->conns_all); read_unlock_bh(&lgr->conns_lock); @@ -168,8 +167,8 @@ static void smc_lgr_free_work(struct work_struct *work) spin_unlock_bh(&smc_lgr_list.lock); return; } - list_del_init(&lgr->list); /* remove from smc_lgr_list */ -free: + if (!list_empty(&lgr->list)) + list_del_init(&lgr->list); /* remove from smc_lgr_list */ spin_unlock_bh(&smc_lgr_list.lock); if (!lgr->is_smcd && !lgr->terminating) { @@ -300,13 +299,13 @@ static void smc_buf_unuse(struct smc_connection *conn, conn->sndbuf_desc->used = 0; if (conn->rmb_desc) { if (!conn->rmb_desc->regerr) { - conn->rmb_desc->used = 0; if (!lgr->is_smcd) { /* unregister rmb with peer */ smc_llc_do_delete_rkey( &lgr->lnk[SMC_SINGLE_LINK], conn->rmb_desc); } + conn->rmb_desc->used = 0; } else { /* buf registration failed, reuse not possible */ write_lock_bh(&lgr->rmbs_lock); @@ -331,8 +330,9 @@ void smc_conn_free(struct smc_connection *conn) } else { smc_cdc_tx_dismiss_slots(conn); } - smc_lgr_unregister_conn(conn); /* unsets conn->lgr */ + smc_lgr_unregister_conn(conn); smc_buf_unuse(conn, lgr); /* allow buffer reuse */ + conn->lgr = NULL; if (!lgr->conns_num) smc_lgr_schedule_free_work(lgr); @@ -462,6 +462,7 @@ static void __smc_lgr_terminate(struct smc_link_group *lgr) sock_hold(&smc->sk); /* sock_put in close work */ conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1; __smc_lgr_unregister_conn(conn); + conn->lgr = NULL; write_unlock_bh(&lgr->conns_lock); if (!schedule_work(&conn->close_work)) sock_put(&smc->sk); @@ -628,6 +629,8 @@ int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact, local_contact = SMC_REUSE_CONTACT; conn->lgr = lgr; smc_lgr_register_conn(conn); /* add smc conn to lgr */ + if (delayed_work_pending(&lgr->free_work)) + cancel_delayed_work(&lgr->free_work); write_unlock_bh(&lgr->conns_lock); break; } diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index b00287989a3d..8806d2afa6ed 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -52,6 +52,24 @@ enum smc_wr_reg_state { FAILED /* ib_wr_reg_mr response: failure */ }; +struct smc_rdma_sge { /* sges for RDMA writes */ + struct ib_sge wr_tx_rdma_sge[SMC_IB_MAX_SEND_SGE]; +}; + +#define SMC_MAX_RDMA_WRITES 2 /* max. # of RDMA writes per + * message send + */ + +struct smc_rdma_sges { /* sges per message send */ + struct smc_rdma_sge tx_rdma_sge[SMC_MAX_RDMA_WRITES]; +}; + +struct smc_rdma_wr { /* work requests per message + * send + */ + struct ib_rdma_wr wr_tx_rdma[SMC_MAX_RDMA_WRITES]; +}; + struct smc_link { struct smc_ib_device *smcibdev; /* ib-device */ u8 ibport; /* port - values 1 | 2 */ @@ -64,6 +82,8 @@ struct smc_link { struct smc_wr_buf *wr_tx_bufs; /* WR send payload buffers */ struct ib_send_wr *wr_tx_ibs; /* WR send meta data */ struct ib_sge *wr_tx_sges; /* WR send gather meta data */ + struct smc_rdma_sges *wr_tx_rdma_sges;/*RDMA WRITE gather meta data*/ + struct smc_rdma_wr *wr_tx_rdmas; /* WR RDMA WRITE */ struct smc_wr_tx_pend *wr_tx_pends; /* WR send waiting for CQE */ /* above four vectors have wr_tx_cnt elements and use the same index */ dma_addr_t wr_tx_dma_addr; /* DMA address of wr_tx_bufs */ diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index dbf64a93d68a..371b4cf31fcd 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -38,6 +38,7 @@ static void smc_diag_msg_common_fill(struct smc_diag_msg *r, struct sock *sk) { struct smc_sock *smc = smc_sk(sk); + r->diag_family = sk->sk_family; if (!smc->clcsock) return; r->id.idiag_sport = htons(smc->clcsock->sk->sk_num); @@ -45,14 +46,12 @@ static void smc_diag_msg_common_fill(struct smc_diag_msg *r, struct sock *sk) r->id.idiag_if = smc->clcsock->sk->sk_bound_dev_if; sock_diag_save_cookie(sk, r->id.idiag_cookie); if (sk->sk_protocol == SMCPROTO_SMC) { - r->diag_family = PF_INET; memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src)); memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst)); r->id.idiag_src[0] = smc->clcsock->sk->sk_rcv_saddr; r->id.idiag_dst[0] = smc->clcsock->sk->sk_daddr; #if IS_ENABLED(CONFIG_IPV6) } else if (sk->sk_protocol == SMCPROTO_SMC6) { - r->diag_family = PF_INET6; memcpy(&r->id.idiag_src, &smc->clcsock->sk->sk_v6_rcv_saddr, sizeof(smc->clcsock->sk->sk_v6_rcv_saddr)); memcpy(&r->id.idiag_dst, &smc->clcsock->sk->sk_v6_daddr, diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index e519ef29c0ff..0b244be24fe0 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -257,12 +257,20 @@ static void smc_ib_global_event_handler(struct ib_event_handler *handler, smcibdev = container_of(handler, struct smc_ib_device, event_handler); switch (ibevent->event) { - case IB_EVENT_PORT_ERR: case IB_EVENT_DEVICE_FATAL: + /* terminate all ports on device */ + for (port_idx = 0; port_idx < SMC_MAX_PORTS; port_idx++) + set_bit(port_idx, &smcibdev->port_event_mask); + schedule_work(&smcibdev->port_event_work); + break; + case IB_EVENT_PORT_ERR: case IB_EVENT_PORT_ACTIVE: + case IB_EVENT_GID_CHANGE: port_idx = ibevent->element.port_num - 1; - set_bit(port_idx, &smcibdev->port_event_mask); - schedule_work(&smcibdev->port_event_work); + if (port_idx < SMC_MAX_PORTS) { + set_bit(port_idx, &smcibdev->port_event_mask); + schedule_work(&smcibdev->port_event_work); + } break; default: break; @@ -289,18 +297,18 @@ int smc_ib_create_protection_domain(struct smc_link *lnk) static void smc_ib_qp_event_handler(struct ib_event *ibevent, void *priv) { - struct smc_ib_device *smcibdev = - (struct smc_ib_device *)ibevent->device; + struct smc_link *lnk = (struct smc_link *)priv; + struct smc_ib_device *smcibdev = lnk->smcibdev; u8 port_idx; switch (ibevent->event) { - case IB_EVENT_DEVICE_FATAL: - case IB_EVENT_GID_CHANGE: - case IB_EVENT_PORT_ERR: + case IB_EVENT_QP_FATAL: case IB_EVENT_QP_ACCESS_ERR: - port_idx = ibevent->element.port_num - 1; - set_bit(port_idx, &smcibdev->port_event_mask); - schedule_work(&smcibdev->port_event_work); + port_idx = ibevent->element.qp->port - 1; + if (port_idx < SMC_MAX_PORTS) { + set_bit(port_idx, &smcibdev->port_event_mask); + schedule_work(&smcibdev->port_event_work); + } break; default: break; diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index a6d3623d06f4..4fd60c522802 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -166,7 +166,8 @@ static int smc_llc_add_pending_send(struct smc_link *link, { int rc; - rc = smc_wr_tx_get_free_slot(link, smc_llc_tx_handler, wr_buf, pend); + rc = smc_wr_tx_get_free_slot(link, smc_llc_tx_handler, wr_buf, NULL, + pend); if (rc < 0) return rc; BUILD_BUG_ON_MSG( diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 7cb3e4f07c10..632c3109dee5 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -27,7 +27,7 @@ static struct nla_policy smc_pnet_policy[SMC_PNETID_MAX + 1] = { [SMC_PNETID_NAME] = { .type = NLA_NUL_STRING, - .len = SMC_MAX_PNETID_LEN - 1 + .len = SMC_MAX_PNETID_LEN }, [SMC_PNETID_ETHNAME] = { .type = NLA_NUL_STRING, diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index d8366ed51757..a3bff08ff8c8 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -24,10 +24,11 @@ #include "smc.h" #include "smc_wr.h" #include "smc_cdc.h" +#include "smc_close.h" #include "smc_ism.h" #include "smc_tx.h" -#define SMC_TX_WORK_DELAY HZ +#define SMC_TX_WORK_DELAY 0 #define SMC_TX_CORK_DELAY (HZ >> 2) /* 250 ms */ /***************************** sndbuf producer *******************************/ @@ -165,12 +166,11 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len) conn->local_tx_ctrl.prod_flags.urg_data_pending = 1; if (!atomic_read(&conn->sndbuf_space) || conn->urg_tx_pend) { + if (send_done) + return send_done; rc = smc_tx_wait(smc, msg->msg_flags); - if (rc) { - if (send_done) - return send_done; + if (rc) goto out_err; - } continue; } @@ -267,27 +267,23 @@ int smcd_tx_ism_write(struct smc_connection *conn, void *data, size_t len, /* sndbuf consumer: actual data transfer of one target chunk with RDMA write */ static int smc_tx_rdma_write(struct smc_connection *conn, int peer_rmbe_offset, - int num_sges, struct ib_sge sges[]) + int num_sges, struct ib_rdma_wr *rdma_wr) { struct smc_link_group *lgr = conn->lgr; - struct ib_rdma_wr rdma_wr; struct smc_link *link; int rc; - memset(&rdma_wr, 0, sizeof(rdma_wr)); link = &lgr->lnk[SMC_SINGLE_LINK]; - rdma_wr.wr.wr_id = smc_wr_tx_get_next_wr_id(link); - rdma_wr.wr.sg_list = sges; - rdma_wr.wr.num_sge = num_sges; - rdma_wr.wr.opcode = IB_WR_RDMA_WRITE; - rdma_wr.remote_addr = + rdma_wr->wr.wr_id = smc_wr_tx_get_next_wr_id(link); + rdma_wr->wr.num_sge = num_sges; + rdma_wr->remote_addr = lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].dma_addr + /* RMBE within RMB */ conn->tx_off + /* offset within RMBE */ peer_rmbe_offset; - rdma_wr.rkey = lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].rkey; - rc = ib_post_send(link->roce_qp, &rdma_wr.wr, NULL); + rdma_wr->rkey = lgr->rtokens[conn->rtoken_idx][SMC_SINGLE_LINK].rkey; + rc = ib_post_send(link->roce_qp, &rdma_wr->wr, NULL); if (rc) { conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1; smc_lgr_terminate(lgr); @@ -314,24 +310,25 @@ static inline void smc_tx_advance_cursors(struct smc_connection *conn, /* SMC-R helper for smc_tx_rdma_writes() */ static int smcr_tx_rdma_writes(struct smc_connection *conn, size_t len, size_t src_off, size_t src_len, - size_t dst_off, size_t dst_len) + size_t dst_off, size_t dst_len, + struct smc_rdma_wr *wr_rdma_buf) { dma_addr_t dma_addr = sg_dma_address(conn->sndbuf_desc->sgt[SMC_SINGLE_LINK].sgl); - struct smc_link *link = &conn->lgr->lnk[SMC_SINGLE_LINK]; int src_len_sum = src_len, dst_len_sum = dst_len; - struct ib_sge sges[SMC_IB_MAX_SEND_SGE]; int sent_count = src_off; int srcchunk, dstchunk; int num_sges; int rc; for (dstchunk = 0; dstchunk < 2; dstchunk++) { + struct ib_sge *sge = + wr_rdma_buf->wr_tx_rdma[dstchunk].wr.sg_list; + num_sges = 0; for (srcchunk = 0; srcchunk < 2; srcchunk++) { - sges[srcchunk].addr = dma_addr + src_off; - sges[srcchunk].length = src_len; - sges[srcchunk].lkey = link->roce_pd->local_dma_lkey; + sge[srcchunk].addr = dma_addr + src_off; + sge[srcchunk].length = src_len; num_sges++; src_off += src_len; @@ -344,7 +341,8 @@ static int smcr_tx_rdma_writes(struct smc_connection *conn, size_t len, src_len = dst_len - src_len; /* remainder */ src_len_sum += src_len; } - rc = smc_tx_rdma_write(conn, dst_off, num_sges, sges); + rc = smc_tx_rdma_write(conn, dst_off, num_sges, + &wr_rdma_buf->wr_tx_rdma[dstchunk]); if (rc) return rc; if (dst_len_sum == len) @@ -403,7 +401,8 @@ static int smcd_tx_rdma_writes(struct smc_connection *conn, size_t len, /* sndbuf consumer: prepare all necessary (src&dst) chunks of data transmit; * usable snd_wnd as max transmit */ -static int smc_tx_rdma_writes(struct smc_connection *conn) +static int smc_tx_rdma_writes(struct smc_connection *conn, + struct smc_rdma_wr *wr_rdma_buf) { size_t len, src_len, dst_off, dst_len; /* current chunk values */ union smc_host_cursor sent, prep, prod, cons; @@ -464,7 +463,7 @@ static int smc_tx_rdma_writes(struct smc_connection *conn) dst_off, dst_len); else rc = smcr_tx_rdma_writes(conn, len, sent.count, src_len, - dst_off, dst_len); + dst_off, dst_len, wr_rdma_buf); if (rc) return rc; @@ -485,31 +484,30 @@ static int smc_tx_rdma_writes(struct smc_connection *conn) static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn) { struct smc_cdc_producer_flags *pflags; + struct smc_rdma_wr *wr_rdma_buf; struct smc_cdc_tx_pend *pend; struct smc_wr_buf *wr_buf; int rc; - spin_lock_bh(&conn->send_lock); - rc = smc_cdc_get_free_slot(conn, &wr_buf, &pend); + rc = smc_cdc_get_free_slot(conn, &wr_buf, &wr_rdma_buf, &pend); if (rc < 0) { if (rc == -EBUSY) { struct smc_sock *smc = container_of(conn, struct smc_sock, conn); - if (smc->sk.sk_err == ECONNABORTED) { - rc = sock_error(&smc->sk); - goto out_unlock; - } + if (smc->sk.sk_err == ECONNABORTED) + return sock_error(&smc->sk); rc = 0; if (conn->alert_token_local) /* connection healthy */ mod_delayed_work(system_wq, &conn->tx_work, SMC_TX_WORK_DELAY); } - goto out_unlock; + return rc; } + spin_lock_bh(&conn->send_lock); if (!conn->local_tx_ctrl.prod_flags.urg_data_present) { - rc = smc_tx_rdma_writes(conn); + rc = smc_tx_rdma_writes(conn, wr_rdma_buf); if (rc) { smc_wr_tx_put_slot(&conn->lgr->lnk[SMC_SINGLE_LINK], (struct smc_wr_tx_pend_priv *)pend); @@ -536,7 +534,7 @@ static int smcd_tx_sndbuf_nonempty(struct smc_connection *conn) spin_lock_bh(&conn->send_lock); if (!pflags->urg_data_present) - rc = smc_tx_rdma_writes(conn); + rc = smc_tx_rdma_writes(conn, NULL); if (!rc) rc = smcd_cdc_msg_send(conn); @@ -557,6 +555,12 @@ int smc_tx_sndbuf_nonempty(struct smc_connection *conn) else rc = smcr_tx_sndbuf_nonempty(conn); + if (!rc) { + /* trigger socket release if connection is closing */ + struct smc_sock *smc = container_of(conn, struct smc_sock, + conn); + smc_close_wake_tx_prepared(smc); + } return rc; } @@ -598,7 +602,8 @@ void smc_tx_consumer_update(struct smc_connection *conn, bool force) if (to_confirm > conn->rmbe_update_limit) { smc_curs_copy(&prod, &conn->local_rx_ctrl.prod, conn); sender_free = conn->rmb_desc->len - - smc_curs_diff(conn->rmb_desc->len, &prod, &cfed); + smc_curs_diff_large(conn->rmb_desc->len, + &cfed, &prod); } if (conn->local_rx_ctrl.prod_flags.cons_curs_upd_req || @@ -612,9 +617,6 @@ void smc_tx_consumer_update(struct smc_connection *conn, bool force) SMC_TX_WORK_DELAY); return; } - smc_curs_copy(&conn->rx_curs_confirmed, - &conn->local_tx_ctrl.cons, conn); - conn->local_rx_ctrl.prod_flags.cons_curs_upd_req = 0; } if (conn->local_rx_ctrl.prod_flags.write_blocked && !atomic_read(&conn->bytes_to_rcv)) diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c index c2694750a6a8..253aa75dc2b6 100644 --- a/net/smc/smc_wr.c +++ b/net/smc/smc_wr.c @@ -160,6 +160,7 @@ static inline int smc_wr_tx_get_free_slot_index(struct smc_link *link, u32 *idx) * @link: Pointer to smc_link used to later send the message. * @handler: Send completion handler function pointer. * @wr_buf: Out value returns pointer to message buffer. + * @wr_rdma_buf: Out value returns pointer to rdma work request. * @wr_pend_priv: Out value returns pointer serving as handler context. * * Return: 0 on success, or -errno on error. @@ -167,6 +168,7 @@ static inline int smc_wr_tx_get_free_slot_index(struct smc_link *link, u32 *idx) int smc_wr_tx_get_free_slot(struct smc_link *link, smc_wr_tx_handler handler, struct smc_wr_buf **wr_buf, + struct smc_rdma_wr **wr_rdma_buf, struct smc_wr_tx_pend_priv **wr_pend_priv) { struct smc_wr_tx_pend *wr_pend; @@ -204,6 +206,8 @@ int smc_wr_tx_get_free_slot(struct smc_link *link, wr_ib = &link->wr_tx_ibs[idx]; wr_ib->wr_id = wr_id; *wr_buf = &link->wr_tx_bufs[idx]; + if (wr_rdma_buf) + *wr_rdma_buf = &link->wr_tx_rdmas[idx]; *wr_pend_priv = &wr_pend->priv; return 0; } @@ -218,10 +222,10 @@ int smc_wr_tx_put_slot(struct smc_link *link, u32 idx = pend->idx; /* clear the full struct smc_wr_tx_pend including .priv */ - memset(&link->wr_tx_pends[pend->idx], 0, - sizeof(link->wr_tx_pends[pend->idx])); - memset(&link->wr_tx_bufs[pend->idx], 0, - sizeof(link->wr_tx_bufs[pend->idx])); + memset(&link->wr_tx_pends[idx], 0, + sizeof(link->wr_tx_pends[idx])); + memset(&link->wr_tx_bufs[idx], 0, + sizeof(link->wr_tx_bufs[idx])); test_and_clear_bit(idx, link->wr_tx_mask); return 1; } @@ -465,12 +469,26 @@ static void smc_wr_init_sge(struct smc_link *lnk) lnk->wr_tx_dma_addr + i * SMC_WR_BUF_SIZE; lnk->wr_tx_sges[i].length = SMC_WR_TX_SIZE; lnk->wr_tx_sges[i].lkey = lnk->roce_pd->local_dma_lkey; + lnk->wr_tx_rdma_sges[i].tx_rdma_sge[0].wr_tx_rdma_sge[0].lkey = + lnk->roce_pd->local_dma_lkey; + lnk->wr_tx_rdma_sges[i].tx_rdma_sge[0].wr_tx_rdma_sge[1].lkey = + lnk->roce_pd->local_dma_lkey; + lnk->wr_tx_rdma_sges[i].tx_rdma_sge[1].wr_tx_rdma_sge[0].lkey = + lnk->roce_pd->local_dma_lkey; + lnk->wr_tx_rdma_sges[i].tx_rdma_sge[1].wr_tx_rdma_sge[1].lkey = + lnk->roce_pd->local_dma_lkey; lnk->wr_tx_ibs[i].next = NULL; lnk->wr_tx_ibs[i].sg_list = &lnk->wr_tx_sges[i]; lnk->wr_tx_ibs[i].num_sge = 1; lnk->wr_tx_ibs[i].opcode = IB_WR_SEND; lnk->wr_tx_ibs[i].send_flags = IB_SEND_SIGNALED | IB_SEND_SOLICITED; + lnk->wr_tx_rdmas[i].wr_tx_rdma[0].wr.opcode = IB_WR_RDMA_WRITE; + lnk->wr_tx_rdmas[i].wr_tx_rdma[1].wr.opcode = IB_WR_RDMA_WRITE; + lnk->wr_tx_rdmas[i].wr_tx_rdma[0].wr.sg_list = + lnk->wr_tx_rdma_sges[i].tx_rdma_sge[0].wr_tx_rdma_sge; + lnk->wr_tx_rdmas[i].wr_tx_rdma[1].wr.sg_list = + lnk->wr_tx_rdma_sges[i].tx_rdma_sge[1].wr_tx_rdma_sge; } for (i = 0; i < lnk->wr_rx_cnt; i++) { lnk->wr_rx_sges[i].addr = @@ -521,8 +539,12 @@ void smc_wr_free_link_mem(struct smc_link *lnk) lnk->wr_tx_mask = NULL; kfree(lnk->wr_tx_sges); lnk->wr_tx_sges = NULL; + kfree(lnk->wr_tx_rdma_sges); + lnk->wr_tx_rdma_sges = NULL; kfree(lnk->wr_rx_sges); lnk->wr_rx_sges = NULL; + kfree(lnk->wr_tx_rdmas); + lnk->wr_tx_rdmas = NULL; kfree(lnk->wr_rx_ibs); lnk->wr_rx_ibs = NULL; kfree(lnk->wr_tx_ibs); @@ -552,10 +574,20 @@ int smc_wr_alloc_link_mem(struct smc_link *link) GFP_KERNEL); if (!link->wr_rx_ibs) goto no_mem_wr_tx_ibs; + link->wr_tx_rdmas = kcalloc(SMC_WR_BUF_CNT, + sizeof(link->wr_tx_rdmas[0]), + GFP_KERNEL); + if (!link->wr_tx_rdmas) + goto no_mem_wr_rx_ibs; + link->wr_tx_rdma_sges = kcalloc(SMC_WR_BUF_CNT, + sizeof(link->wr_tx_rdma_sges[0]), + GFP_KERNEL); + if (!link->wr_tx_rdma_sges) + goto no_mem_wr_tx_rdmas; link->wr_tx_sges = kcalloc(SMC_WR_BUF_CNT, sizeof(link->wr_tx_sges[0]), GFP_KERNEL); if (!link->wr_tx_sges) - goto no_mem_wr_rx_ibs; + goto no_mem_wr_tx_rdma_sges; link->wr_rx_sges = kcalloc(SMC_WR_BUF_CNT * 3, sizeof(link->wr_rx_sges[0]), GFP_KERNEL); @@ -579,6 +611,10 @@ no_mem_wr_rx_sges: kfree(link->wr_rx_sges); no_mem_wr_tx_sges: kfree(link->wr_tx_sges); +no_mem_wr_tx_rdma_sges: + kfree(link->wr_tx_rdma_sges); +no_mem_wr_tx_rdmas: + kfree(link->wr_tx_rdmas); no_mem_wr_rx_ibs: kfree(link->wr_rx_ibs); no_mem_wr_tx_ibs: diff --git a/net/smc/smc_wr.h b/net/smc/smc_wr.h index 1d85bb14fd6f..09bf32fd3959 100644 --- a/net/smc/smc_wr.h +++ b/net/smc/smc_wr.h @@ -85,6 +85,7 @@ void smc_wr_add_dev(struct smc_ib_device *smcibdev); int smc_wr_tx_get_free_slot(struct smc_link *link, smc_wr_tx_handler handler, struct smc_wr_buf **wr_buf, + struct smc_rdma_wr **wrs, struct smc_wr_tx_pend_priv **wr_pend_priv); int smc_wr_tx_put_slot(struct smc_link *link, struct smc_wr_tx_pend_priv *wr_pend_priv); diff --git a/net/socket.c b/net/socket.c index e89884e2197b..643a1648fcc2 100644 --- a/net/socket.c +++ b/net/socket.c @@ -669,7 +669,7 @@ static bool skb_is_err_queue(const struct sk_buff *skb) * before the software timestamp is received, a hardware TX timestamp may be * returned only if there is no software TX timestamp. Ignore false software * timestamps, which may be made in the __sock_recv_timestamp() call when the - * option SO_TIMESTAMP(NS) is enabled on the socket, even when the skb has a + * option SO_TIMESTAMP_OLD(NS) is enabled on the socket, even when the skb has a * hardware timestamp. */ static bool skb_is_swtx_tstamp(const struct sk_buff *skb, int false_tstamp) @@ -705,7 +705,9 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { int need_software_tstamp = sock_flag(sk, SOCK_RCVTSTAMP); - struct scm_timestamping tss; + int new_tstamp = sock_flag(sk, SOCK_TSTAMP_NEW); + struct scm_timestamping_internal tss; + int empty = 1, false_tstamp = 0; struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); @@ -719,34 +721,54 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, if (need_software_tstamp) { if (!sock_flag(sk, SOCK_RCVTSTAMPNS)) { - struct timeval tv; - skb_get_timestamp(skb, &tv); - put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMP, - sizeof(tv), &tv); + if (new_tstamp) { + struct __kernel_sock_timeval tv; + + skb_get_new_timestamp(skb, &tv); + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_NEW, + sizeof(tv), &tv); + } else { + struct __kernel_old_timeval tv; + + skb_get_timestamp(skb, &tv); + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_OLD, + sizeof(tv), &tv); + } } else { - struct timespec ts; - skb_get_timestampns(skb, &ts); - put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPNS, - sizeof(ts), &ts); + if (new_tstamp) { + struct __kernel_timespec ts; + + skb_get_new_timestampns(skb, &ts); + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_NEW, + sizeof(ts), &ts); + } else { + struct timespec ts; + + skb_get_timestampns(skb, &ts); + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_OLD, + sizeof(ts), &ts); + } } } memset(&tss, 0, sizeof(tss)); if ((sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) && - ktime_to_timespec_cond(skb->tstamp, tss.ts + 0)) + ktime_to_timespec64_cond(skb->tstamp, tss.ts + 0)) empty = 0; if (shhwtstamps && (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) && !skb_is_swtx_tstamp(skb, false_tstamp) && - ktime_to_timespec_cond(shhwtstamps->hwtstamp, tss.ts + 2)) { + ktime_to_timespec64_cond(shhwtstamps->hwtstamp, tss.ts + 2)) { empty = 0; if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) && !skb_is_err_queue(skb)) put_ts_pktinfo(msg, skb); } if (!empty) { - put_cmsg(msg, SOL_SOCKET, - SCM_TIMESTAMPING, sizeof(tss), &tss); + if (sock_flag(sk, SOCK_TSTAMP_NEW)) + put_cmsg_scm_timestamping64(msg, &tss); + else + put_cmsg_scm_timestamping(msg, &tss); if (skb_is_err_queue(skb) && skb->len && SKB_EXT_ERR(skb)->opt_stats) @@ -941,8 +963,7 @@ void dlci_ioctl_set(int (*hook) (unsigned int, void __user *)) EXPORT_SYMBOL(dlci_ioctl_set); static long sock_do_ioctl(struct net *net, struct socket *sock, - unsigned int cmd, unsigned long arg, - unsigned int ifreq_size) + unsigned int cmd, unsigned long arg) { int err; void __user *argp = (void __user *)arg; @@ -968,11 +989,11 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, } else { struct ifreq ifr; bool need_copyout; - if (copy_from_user(&ifr, argp, ifreq_size)) + if (copy_from_user(&ifr, argp, sizeof(struct ifreq))) return -EFAULT; err = dev_ioctl(net, cmd, &ifr, &need_copyout); if (!err && need_copyout) - if (copy_to_user(argp, &ifr, ifreq_size)) + if (copy_to_user(argp, &ifr, sizeof(struct ifreq))) return -EFAULT; } return err; @@ -1071,8 +1092,7 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) err = open_related_ns(&net->ns, get_net_ns); break; default: - err = sock_do_ioctl(net, sock, cmd, arg, - sizeof(struct ifreq)); + err = sock_do_ioctl(net, sock, cmd, arg); break; } return err; @@ -2780,8 +2800,7 @@ static int do_siocgstamp(struct net *net, struct socket *sock, int err; set_fs(KERNEL_DS); - err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv, - sizeof(struct compat_ifreq)); + err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv); set_fs(old_fs); if (!err) err = compat_put_timeval(&ktv, up); @@ -2797,8 +2816,7 @@ static int do_siocgstampns(struct net *net, struct socket *sock, int err; set_fs(KERNEL_DS); - err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts, - sizeof(struct compat_ifreq)); + err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts); set_fs(old_fs); if (!err) err = compat_put_timespec(&kts, up); @@ -2994,6 +3012,54 @@ static int compat_ifr_data_ioctl(struct net *net, unsigned int cmd, return dev_ioctl(net, cmd, &ifreq, NULL); } +static int compat_ifreq_ioctl(struct net *net, struct socket *sock, + unsigned int cmd, + struct compat_ifreq __user *uifr32) +{ + struct ifreq __user *uifr; + int err; + + /* Handle the fact that while struct ifreq has the same *layout* on + * 32/64 for everything but ifreq::ifru_ifmap and ifreq::ifru_data, + * which are handled elsewhere, it still has different *size* due to + * ifreq::ifru_ifmap (which is 16 bytes on 32 bit, 24 bytes on 64-bit, + * resulting in struct ifreq being 32 and 40 bytes respectively). + * As a result, if the struct happens to be at the end of a page and + * the next page isn't readable/writable, we get a fault. To prevent + * that, copy back and forth to the full size. + */ + + uifr = compat_alloc_user_space(sizeof(*uifr)); + if (copy_in_user(uifr, uifr32, sizeof(*uifr32))) + return -EFAULT; + + err = sock_do_ioctl(net, sock, cmd, (unsigned long)uifr); + + if (!err) { + switch (cmd) { + case SIOCGIFFLAGS: + case SIOCGIFMETRIC: + case SIOCGIFMTU: + case SIOCGIFMEM: + case SIOCGIFHWADDR: + case SIOCGIFINDEX: + case SIOCGIFADDR: + case SIOCGIFBRDADDR: + case SIOCGIFDSTADDR: + case SIOCGIFNETMASK: + case SIOCGIFPFLAGS: + case SIOCGIFTXQLEN: + case SIOCGMIIPHY: + case SIOCGMIIREG: + case SIOCGIFNAME: + if (copy_in_user(uifr32, uifr, sizeof(*uifr32))) + err = -EFAULT; + break; + } + } + return err; +} + static int compat_sioc_ifmap(struct net *net, unsigned int cmd, struct compat_ifreq __user *uifr32) { @@ -3109,8 +3175,7 @@ static int routing_ioctl(struct net *net, struct socket *sock, } set_fs(KERNEL_DS); - ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r, - sizeof(struct compat_ifreq)); + ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r); set_fs(old_fs); out: @@ -3210,21 +3275,22 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, case SIOCSIFTXQLEN: case SIOCBRADDIF: case SIOCBRDELIF: + case SIOCGIFNAME: case SIOCSIFNAME: case SIOCGMIIPHY: case SIOCGMIIREG: case SIOCSMIIREG: - case SIOCSARP: - case SIOCGARP: - case SIOCDARP: - case SIOCATMARK: case SIOCBONDENSLAVE: case SIOCBONDRELEASE: case SIOCBONDSETHWADDR: case SIOCBONDCHANGEACTIVE: - case SIOCGIFNAME: - return sock_do_ioctl(net, sock, cmd, arg, - sizeof(struct compat_ifreq)); + return compat_ifreq_ioctl(net, sock, cmd, argp); + + case SIOCSARP: + case SIOCGARP: + case SIOCDARP: + case SIOCATMARK: + return sock_do_ioctl(net, sock, cmd, arg); } return -ENOIOCTLCMD; diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index cf51b8f9b15f..1f200119268c 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -537,6 +537,99 @@ void svc_rdma_sync_reply_hdr(struct svcxprt_rdma *rdma, DMA_TO_DEVICE); } +/* If the xdr_buf has more elements than the device can + * transmit in a single RDMA Send, then the reply will + * have to be copied into a bounce buffer. + */ +static bool svc_rdma_pull_up_needed(struct svcxprt_rdma *rdma, + struct xdr_buf *xdr, + __be32 *wr_lst) +{ + int elements; + + /* xdr->head */ + elements = 1; + + /* xdr->pages */ + if (!wr_lst) { + unsigned int remaining; + unsigned long pageoff; + + pageoff = xdr->page_base & ~PAGE_MASK; + remaining = xdr->page_len; + while (remaining) { + ++elements; + remaining -= min_t(u32, PAGE_SIZE - pageoff, + remaining); + pageoff = 0; + } + } + + /* xdr->tail */ + if (xdr->tail[0].iov_len) + ++elements; + + /* assume 1 SGE is needed for the transport header */ + return elements >= rdma->sc_max_send_sges; +} + +/* The device is not capable of sending the reply directly. + * Assemble the elements of @xdr into the transport header + * buffer. + */ +static int svc_rdma_pull_up_reply_msg(struct svcxprt_rdma *rdma, + struct svc_rdma_send_ctxt *ctxt, + struct xdr_buf *xdr, __be32 *wr_lst) +{ + unsigned char *dst, *tailbase; + unsigned int taillen; + + dst = ctxt->sc_xprt_buf; + dst += ctxt->sc_sges[0].length; + + memcpy(dst, xdr->head[0].iov_base, xdr->head[0].iov_len); + dst += xdr->head[0].iov_len; + + tailbase = xdr->tail[0].iov_base; + taillen = xdr->tail[0].iov_len; + if (wr_lst) { + u32 xdrpad; + + xdrpad = xdr_padsize(xdr->page_len); + if (taillen && xdrpad) { + tailbase += xdrpad; + taillen -= xdrpad; + } + } else { + unsigned int len, remaining; + unsigned long pageoff; + struct page **ppages; + + ppages = xdr->pages + (xdr->page_base >> PAGE_SHIFT); + pageoff = xdr->page_base & ~PAGE_MASK; + remaining = xdr->page_len; + while (remaining) { + len = min_t(u32, PAGE_SIZE - pageoff, remaining); + + memcpy(dst, page_address(*ppages), len); + remaining -= len; + dst += len; + pageoff = 0; + } + } + + if (taillen) + memcpy(dst, tailbase, taillen); + + ctxt->sc_sges[0].length += xdr->len; + ib_dma_sync_single_for_device(rdma->sc_pd->device, + ctxt->sc_sges[0].addr, + ctxt->sc_sges[0].length, + DMA_TO_DEVICE); + + return 0; +} + /* svc_rdma_map_reply_msg - Map the buffer holding RPC message * @rdma: controlling transport * @ctxt: send_ctxt for the Send WR @@ -559,8 +652,10 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma, u32 xdr_pad; int ret; - if (++ctxt->sc_cur_sge_no >= rdma->sc_max_send_sges) - return -EIO; + if (svc_rdma_pull_up_needed(rdma, xdr, wr_lst)) + return svc_rdma_pull_up_reply_msg(rdma, ctxt, xdr, wr_lst); + + ++ctxt->sc_cur_sge_no; ret = svc_rdma_dma_map_buf(rdma, ctxt, xdr->head[0].iov_base, xdr->head[0].iov_len); @@ -591,8 +686,7 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma, while (remaining) { len = min_t(u32, PAGE_SIZE - page_off, remaining); - if (++ctxt->sc_cur_sge_no >= rdma->sc_max_send_sges) - return -EIO; + ++ctxt->sc_cur_sge_no; ret = svc_rdma_dma_map_page(rdma, ctxt, *ppages++, page_off, len); if (ret < 0) @@ -606,8 +700,7 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma, len = xdr->tail[0].iov_len; tail: if (len) { - if (++ctxt->sc_cur_sge_no >= rdma->sc_max_send_sges) - return -EIO; + ++ctxt->sc_cur_sge_no; ret = svc_rdma_dma_map_buf(rdma, ctxt, base, len); if (ret < 0) return ret; diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 924c17d46903..57f86c63a463 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -419,12 +419,9 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) /* Transport header, head iovec, tail iovec */ newxprt->sc_max_send_sges = 3; /* Add one SGE per page list entry */ - newxprt->sc_max_send_sges += svcrdma_max_req_size / PAGE_SIZE; - if (newxprt->sc_max_send_sges > dev->attrs.max_send_sge) { - pr_err("svcrdma: too few Send SGEs available (%d needed)\n", - newxprt->sc_max_send_sges); - goto errout; - } + newxprt->sc_max_send_sges += (svcrdma_max_req_size / PAGE_SIZE) + 1; + if (newxprt->sc_max_send_sges > dev->attrs.max_send_sge) + newxprt->sc_max_send_sges = dev->attrs.max_send_sge; newxprt->sc_max_req_size = svcrdma_max_req_size; newxprt->sc_max_requests = svcrdma_max_requests; newxprt->sc_max_bc_requests = svcrdma_max_bc_requests; diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index cd78253de31d..7e1357db33d7 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -592,26 +592,6 @@ int call_switchdev_blocking_notifiers(unsigned long val, struct net_device *dev, } EXPORT_SYMBOL_GPL(call_switchdev_blocking_notifiers); -bool switchdev_port_same_parent_id(struct net_device *a, - struct net_device *b) -{ - struct switchdev_attr a_attr = { - .orig_dev = a, - .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, - }; - struct switchdev_attr b_attr = { - .orig_dev = b, - .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, - }; - - if (switchdev_port_attr_get(a, &a_attr) || - switchdev_port_attr_get(b, &b_attr)) - return false; - - return netdev_phys_item_id_same(&a_attr.u.ppid, &b_attr.u.ppid); -} -EXPORT_SYMBOL_GPL(switchdev_port_same_parent_id); - static int __switchdev_handle_port_obj_add(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), diff --git a/net/tipc/link.c b/net/tipc/link.c index ac306d17f8ad..341ecd796aa4 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1145,7 +1145,7 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb, default: pr_warn("Dropping received illegal msg type\n"); kfree_skb(skb); - return false; + return true; }; } @@ -1425,6 +1425,10 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe, l->rcv_unacked = 0; } else { /* RESET_MSG or ACTIVATE_MSG */ + if (mtyp == ACTIVATE_MSG) { + msg_set_dest_session_valid(hdr, 1); + msg_set_dest_session(hdr, l->peer_session); + } msg_set_max_pkt(hdr, l->advertised_mtu); strcpy(data, l->if_name); msg_set_size(hdr, INT_H_SIZE + TIPC_MAX_IF_NAME); @@ -1642,6 +1646,17 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb, rc = tipc_link_fsm_evt(l, LINK_FAILURE_EVT); break; } + + /* If this endpoint was re-created while peer was ESTABLISHING + * it doesn't know current session number. Force re-synch. + */ + if (mtyp == ACTIVATE_MSG && msg_dest_session_valid(hdr) && + l->session != msg_dest_session(hdr)) { + if (less(l->session, msg_dest_session(hdr))) + l->session = msg_dest_session(hdr) + 1; + break; + } + /* ACTIVATE_MSG serves as PEER_RESET if link is already down */ if (mtyp == RESET_MSG || !link_is_up(l)) rc = tipc_link_fsm_evt(l, LINK_PEER_RESET_EVT); diff --git a/net/tipc/msg.h b/net/tipc/msg.h index a0924956bb61..d7e4b8b93f9d 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -360,6 +360,28 @@ static inline void msg_set_bcast_ack(struct tipc_msg *m, u16 n) msg_set_bits(m, 1, 0, 0xffff, n); } +/* Note: reusing bits in word 1 for ACTIVATE_MSG only, to re-synch + * link peer session number + */ +static inline bool msg_dest_session_valid(struct tipc_msg *m) +{ + return msg_bits(m, 1, 16, 0x1); +} + +static inline void msg_set_dest_session_valid(struct tipc_msg *m, bool valid) +{ + msg_set_bits(m, 1, 16, 0x1, valid); +} + +static inline u16 msg_dest_session(struct tipc_msg *m) +{ + return msg_bits(m, 1, 0, 0xffff); +} + +static inline void msg_set_dest_session(struct tipc_msg *m, u16 n) +{ + msg_set_bits(m, 1, 0, 0xffff, n); +} /* * Word 2 diff --git a/net/tipc/node.c b/net/tipc/node.c index db2a6c3e0be9..2dc4919ab23c 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -830,15 +830,16 @@ static void tipc_node_link_down(struct tipc_node *n, int bearer_id, bool delete) tipc_node_write_lock(n); if (!tipc_link_is_establishing(l)) { __tipc_node_link_down(n, &bearer_id, &xmitq, &maddr); - if (delete) { - kfree(l); - le->link = NULL; - n->link_cnt--; - } } else { /* Defuse pending tipc_node_link_up() */ + tipc_link_reset(l); tipc_link_fsm_evt(l, LINK_RESET_EVT); } + if (delete) { + kfree(l); + le->link = NULL; + n->link_cnt--; + } trace_tipc_node_link_down(n, true, "node link down or deleted!"); tipc_node_write_unlock(n); if (delete) diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index d753e362d2d9..7ee9008b2187 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -257,7 +257,8 @@ static int tls_push_record(struct sock *sk, tls_fill_prepend(ctx, skb_frag_address(frag), record->len - ctx->tx.prepend_size, - record_type); + record_type, + ctx->crypto_send.info.version); /* HW doesn't care about the data in the tag, because it fills it. */ dummy_tag_frag.page = skb_frag_page(frag); @@ -270,7 +271,7 @@ static int tls_push_record(struct sock *sk, spin_unlock_irq(&offload_ctx->lock); offload_ctx->open_record = NULL; set_bit(TLS_PENDING_CLOSED_RECORD, &ctx->flags); - tls_advance_record_sn(sk, &ctx->tx); + tls_advance_record_sn(sk, &ctx->tx, ctx->crypto_send.info.version); for (i = 0; i < record->num_frags; i++) { frag = &record->frags[i]; diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c index 450a6dbc5a88..54c3a758f2a7 100644 --- a/net/tls/tls_device_fallback.c +++ b/net/tls/tls_device_fallback.c @@ -73,7 +73,8 @@ static int tls_enc_record(struct aead_request *aead_req, len -= TLS_CIPHER_AES_GCM_128_IV_SIZE; tls_make_aad(aad, len - TLS_CIPHER_AES_GCM_128_TAG_SIZE, - (char *)&rcd_sn, sizeof(rcd_sn), buf[0]); + (char *)&rcd_sn, sizeof(rcd_sn), buf[0], + TLS_1_2_VERSION); memcpy(iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, buf + TLS_HEADER_SIZE, TLS_CIPHER_AES_GCM_128_IV_SIZE); diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index d36d095cbcf0..d1c2fd9a3f63 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -372,6 +372,30 @@ static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval, rc = -EFAULT; break; } + case TLS_CIPHER_AES_GCM_256: { + struct tls12_crypto_info_aes_gcm_256 * + crypto_info_aes_gcm_256 = + container_of(crypto_info, + struct tls12_crypto_info_aes_gcm_256, + info); + + if (len != sizeof(*crypto_info_aes_gcm_256)) { + rc = -EINVAL; + goto out; + } + lock_sock(sk); + memcpy(crypto_info_aes_gcm_256->iv, + ctx->tx.iv + TLS_CIPHER_AES_GCM_256_SALT_SIZE, + TLS_CIPHER_AES_GCM_256_IV_SIZE); + memcpy(crypto_info_aes_gcm_256->rec_seq, ctx->tx.rec_seq, + TLS_CIPHER_AES_GCM_256_REC_SEQ_SIZE); + release_sock(sk); + if (copy_to_user(optval, + crypto_info_aes_gcm_256, + sizeof(*crypto_info_aes_gcm_256))) + rc = -EFAULT; + break; + } default: rc = -EINVAL; } @@ -412,6 +436,7 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval, { struct tls_crypto_info *crypto_info; struct tls_context *ctx = tls_get_ctx(sk); + size_t optsize; int rc = 0; int conf; @@ -438,14 +463,19 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval, } /* check version */ - if (crypto_info->version != TLS_1_2_VERSION) { + if (crypto_info->version != TLS_1_2_VERSION && + crypto_info->version != TLS_1_3_VERSION) { rc = -ENOTSUPP; goto err_crypto_info; } switch (crypto_info->cipher_type) { - case TLS_CIPHER_AES_GCM_128: { - if (optlen != sizeof(struct tls12_crypto_info_aes_gcm_128)) { + case TLS_CIPHER_AES_GCM_128: + case TLS_CIPHER_AES_GCM_256: { + optsize = crypto_info->cipher_type == TLS_CIPHER_AES_GCM_128 ? + sizeof(struct tls12_crypto_info_aes_gcm_128) : + sizeof(struct tls12_crypto_info_aes_gcm_256); + if (optlen != optsize) { rc = -EINVAL; goto err_crypto_info; } diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 86b9527c4826..ae4784734547 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -120,6 +120,34 @@ static int skb_nsg(struct sk_buff *skb, int offset, int len) return __skb_nsg(skb, offset, len, 0); } +static int padding_length(struct tls_sw_context_rx *ctx, + struct tls_context *tls_ctx, struct sk_buff *skb) +{ + struct strp_msg *rxm = strp_msg(skb); + int sub = 0; + + /* Determine zero-padding length */ + if (tls_ctx->crypto_recv.info.version == TLS_1_3_VERSION) { + char content_type = 0; + int err; + int back = 17; + + while (content_type == 0) { + if (back > rxm->full_len) + return -EBADMSG; + err = skb_copy_bits(skb, + rxm->offset + rxm->full_len - back, + &content_type, 1); + if (content_type) + break; + sub++; + back++; + } + ctx->control = content_type; + } + return sub; +} + static void tls_decrypt_done(struct crypto_async_request *req, int err) { struct aead_request *aead_req = (struct aead_request *)req; @@ -142,7 +170,7 @@ static void tls_decrypt_done(struct crypto_async_request *req, int err) tls_err_abort(skb->sk, err); } else { struct strp_msg *rxm = strp_msg(skb); - + rxm->full_len -= padding_length(ctx, tls_ctx, skb); rxm->offset += tls_ctx->rx.prepend_size; rxm->full_len -= tls_ctx->rx.overhead_size; } @@ -185,7 +213,7 @@ static int tls_do_decryption(struct sock *sk, int ret; aead_request_set_tfm(aead_req, ctx->aead_recv); - aead_request_set_ad(aead_req, TLS_AAD_SPACE_SIZE); + aead_request_set_ad(aead_req, tls_ctx->rx.aad_size); aead_request_set_crypt(aead_req, sgin, sgout, data_len + tls_ctx->rx.tag_size, (u8 *)iv_recv); @@ -289,12 +317,12 @@ static struct tls_rec *tls_get_rec(struct sock *sk) sg_init_table(rec->sg_aead_in, 2); sg_set_buf(&rec->sg_aead_in[0], rec->aad_space, - sizeof(rec->aad_space)); + tls_ctx->tx.aad_size); sg_unmark_end(&rec->sg_aead_in[1]); sg_init_table(rec->sg_aead_out, 2); sg_set_buf(&rec->sg_aead_out[0], rec->aad_space, - sizeof(rec->aad_space)); + tls_ctx->tx.aad_size); sg_unmark_end(&rec->sg_aead_out[1]); return rec; @@ -447,16 +475,20 @@ static int tls_do_encryption(struct sock *sk, struct scatterlist *sge = sk_msg_elem(msg_en, start); int rc; + memcpy(rec->iv_data, tls_ctx->tx.iv, sizeof(rec->iv_data)); + xor_iv_with_seq(tls_ctx->crypto_send.info.version, rec->iv_data, + tls_ctx->tx.rec_seq); + sge->offset += tls_ctx->tx.prepend_size; sge->length -= tls_ctx->tx.prepend_size; msg_en->sg.curr = start; aead_request_set_tfm(aead_req, ctx->aead_send); - aead_request_set_ad(aead_req, TLS_AAD_SPACE_SIZE); + aead_request_set_ad(aead_req, tls_ctx->tx.aad_size); aead_request_set_crypt(aead_req, rec->sg_aead_in, rec->sg_aead_out, - data_len, tls_ctx->tx.iv); + data_len, rec->iv_data); aead_request_set_callback(aead_req, CRYPTO_TFM_REQ_MAY_BACKLOG, tls_encrypt_done, sk); @@ -481,7 +513,8 @@ static int tls_do_encryption(struct sock *sk, /* Unhook the record from context if encryption is not failure */ ctx->open_rec = NULL; - tls_advance_record_sn(sk, &tls_ctx->tx); + tls_advance_record_sn(sk, &tls_ctx->tx, + tls_ctx->crypto_send.info.version); return rc; } @@ -638,7 +671,17 @@ static int tls_push_record(struct sock *sk, int flags, i = msg_pl->sg.end; sk_msg_iter_var_prev(i); - sg_mark_end(sk_msg_elem(msg_pl, i)); + + rec->content_type = record_type; + if (tls_ctx->crypto_send.info.version == TLS_1_3_VERSION) { + /* Add content type to end of message. No padding added */ + sg_set_buf(&rec->sg_content_type, &rec->content_type, 1); + sg_mark_end(&rec->sg_content_type); + sg_chain(msg_pl->sg.data, msg_pl->sg.end + 1, + &rec->sg_content_type); + } else { + sg_mark_end(sk_msg_elem(msg_pl, i)); + } i = msg_pl->sg.start; sg_chain(rec->sg_aead_in, 2, rec->inplace_crypto ? @@ -651,18 +694,22 @@ static int tls_push_record(struct sock *sk, int flags, i = msg_en->sg.start; sg_chain(rec->sg_aead_out, 2, &msg_en->sg.data[i]); - tls_make_aad(rec->aad_space, msg_pl->sg.size, + tls_make_aad(rec->aad_space, msg_pl->sg.size + tls_ctx->tx.tail_size, tls_ctx->tx.rec_seq, tls_ctx->tx.rec_seq_size, - record_type); + record_type, + tls_ctx->crypto_send.info.version); tls_fill_prepend(tls_ctx, page_address(sg_page(&msg_en->sg.data[i])) + - msg_en->sg.data[i].offset, msg_pl->sg.size, - record_type); + msg_en->sg.data[i].offset, + msg_pl->sg.size + tls_ctx->tx.tail_size, + record_type, + tls_ctx->crypto_send.info.version); tls_ctx->pending_open_record_frags = false; - rc = tls_do_encryption(sk, tls_ctx, ctx, req, msg_pl->sg.size, i); + rc = tls_do_encryption(sk, tls_ctx, ctx, req, + msg_pl->sg.size + tls_ctx->tx.tail_size, i); if (rc < 0) { if (rc != -EINPROGRESS) { tls_err_abort(sk, EBADMSG); @@ -671,6 +718,7 @@ static int tls_push_record(struct sock *sk, int flags, tls_merge_open_record(sk, rec, tmp, orig_end); } } + ctx->async_capable = 1; return rc; } else if (split) { msg_pl = &tmp->msg_plaintext; @@ -812,8 +860,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) long timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); - struct crypto_tfm *tfm = crypto_aead_tfm(ctx->aead_send); - bool async_capable = tfm->__crt_alg->cra_flags & CRYPTO_ALG_ASYNC; + bool async_capable = ctx->async_capable; unsigned char record_type = TLS_RECORD_TYPE_DATA; bool is_kvec = iov_iter_is_kvec(&msg->msg_iter); bool eor = !(msg->msg_flags & MSG_MORE); @@ -1290,7 +1337,8 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb, u8 *aad, *iv, *mem = NULL; struct scatterlist *sgin = NULL; struct scatterlist *sgout = NULL; - const int data_len = rxm->full_len - tls_ctx->rx.overhead_size; + const int data_len = rxm->full_len - tls_ctx->rx.overhead_size + + tls_ctx->rx.tail_size; if (*zc && (out_iov || out_sg)) { if (out_iov) @@ -1315,7 +1363,7 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb, aead_size = sizeof(*aead_req) + crypto_aead_reqsize(ctx->aead_recv); mem_size = aead_size + (nsg * sizeof(struct scatterlist)); - mem_size = mem_size + TLS_AAD_SPACE_SIZE; + mem_size = mem_size + tls_ctx->rx.aad_size; mem_size = mem_size + crypto_aead_ivsize(ctx->aead_recv); /* Allocate a single block of memory which contains @@ -1331,7 +1379,7 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb, sgin = (struct scatterlist *)(mem + aead_size); sgout = sgin + n_sgin; aad = (u8 *)(sgout + n_sgout); - iv = aad + TLS_AAD_SPACE_SIZE; + iv = aad + tls_ctx->rx.aad_size; /* Prepare IV */ err = skb_copy_bits(skb, rxm->offset + TLS_HEADER_SIZE, @@ -1341,16 +1389,24 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb, kfree(mem); return err; } - memcpy(iv, tls_ctx->rx.iv, TLS_CIPHER_AES_GCM_128_SALT_SIZE); + if (tls_ctx->crypto_recv.info.version == TLS_1_3_VERSION) + memcpy(iv, tls_ctx->rx.iv, crypto_aead_ivsize(ctx->aead_recv)); + else + memcpy(iv, tls_ctx->rx.iv, TLS_CIPHER_AES_GCM_128_SALT_SIZE); + + xor_iv_with_seq(tls_ctx->crypto_recv.info.version, iv, + tls_ctx->rx.rec_seq); /* Prepare AAD */ - tls_make_aad(aad, rxm->full_len - tls_ctx->rx.overhead_size, + tls_make_aad(aad, rxm->full_len - tls_ctx->rx.overhead_size + + tls_ctx->rx.tail_size, tls_ctx->rx.rec_seq, tls_ctx->rx.rec_seq_size, - ctx->control); + ctx->control, + tls_ctx->crypto_recv.info.version); /* Prepare sgin */ sg_init_table(sgin, n_sgin); - sg_set_buf(&sgin[0], aad, TLS_AAD_SPACE_SIZE); + sg_set_buf(&sgin[0], aad, tls_ctx->rx.aad_size); err = skb_to_sgvec(skb, &sgin[1], rxm->offset + tls_ctx->rx.prepend_size, rxm->full_len - tls_ctx->rx.prepend_size); @@ -1362,7 +1418,7 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb, if (n_sgout) { if (out_iov) { sg_init_table(sgout, n_sgout); - sg_set_buf(&sgout[0], aad, TLS_AAD_SPACE_SIZE); + sg_set_buf(&sgout[0], aad, tls_ctx->rx.aad_size); *chunk = 0; err = tls_setup_from_iter(sk, out_iov, data_len, @@ -1403,6 +1459,7 @@ static int decrypt_skb_update(struct sock *sk, struct sk_buff *skb, { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); + int version = tls_ctx->crypto_recv.info.version; struct strp_msg *rxm = strp_msg(skb); int err = 0; @@ -1415,20 +1472,23 @@ static int decrypt_skb_update(struct sock *sk, struct sk_buff *skb, err = decrypt_internal(sk, skb, dest, NULL, chunk, zc, async); if (err < 0) { if (err == -EINPROGRESS) - tls_advance_record_sn(sk, &tls_ctx->rx); + tls_advance_record_sn(sk, &tls_ctx->rx, + version); return err; } + + rxm->full_len -= padding_length(ctx, tls_ctx, skb); + + rxm->offset += tls_ctx->rx.prepend_size; + rxm->full_len -= tls_ctx->rx.overhead_size; + tls_advance_record_sn(sk, &tls_ctx->rx, version); + ctx->decrypted = true; + ctx->saved_data_ready(sk); } else { *zc = false; } - rxm->offset += tls_ctx->rx.prepend_size; - rxm->full_len -= tls_ctx->rx.overhead_size; - tls_advance_record_sn(sk, &tls_ctx->rx); - ctx->decrypted = true; - ctx->saved_data_ready(sk); - return err; } @@ -1585,10 +1645,10 @@ int tls_sw_recvmsg(struct sock *sk, do { bool retain_skb = false; - bool async = false; bool zc = false; int to_decrypt; int chunk = 0; + bool async; skb = tls_wait_data(sk, psock, flags, timeo, &err); if (!skb) { @@ -1607,6 +1667,29 @@ int tls_sw_recvmsg(struct sock *sk, rxm = strp_msg(skb); + to_decrypt = rxm->full_len - tls_ctx->rx.overhead_size; + + if (to_decrypt <= len && !is_kvec && !is_peek && + ctx->control == TLS_RECORD_TYPE_DATA && + tls_ctx->crypto_recv.info.version != TLS_1_3_VERSION) + zc = true; + + /* Do not use async mode if record is non-data */ + if (ctx->control == TLS_RECORD_TYPE_DATA) + async = ctx->async_capable; + else + async = false; + + err = decrypt_skb_update(sk, skb, &msg->msg_iter, + &chunk, &zc, async); + if (err < 0 && err != -EINPROGRESS) { + tls_err_abort(sk, EBADMSG); + goto recv_end; + } + + if (err == -EINPROGRESS) + num_async++; + if (!cmsg) { int cerr; @@ -1624,40 +1707,25 @@ int tls_sw_recvmsg(struct sock *sk, goto recv_end; } - to_decrypt = rxm->full_len - tls_ctx->rx.overhead_size; - - if (to_decrypt <= len && !is_kvec && !is_peek) - zc = true; - - err = decrypt_skb_update(sk, skb, &msg->msg_iter, - &chunk, &zc, ctx->async_capable); - if (err < 0 && err != -EINPROGRESS) { - tls_err_abort(sk, EBADMSG); - goto recv_end; - } - - if (err == -EINPROGRESS) { - async = true; - num_async++; + if (async) goto pick_next_record; - } else { - if (!zc) { - if (rxm->full_len > len) { - retain_skb = true; - chunk = len; - } else { - chunk = rxm->full_len; - } - err = skb_copy_datagram_msg(skb, rxm->offset, - msg, chunk); - if (err < 0) - goto recv_end; + if (!zc) { + if (rxm->full_len > len) { + retain_skb = true; + chunk = len; + } else { + chunk = rxm->full_len; + } - if (!is_peek) { - rxm->offset = rxm->offset + chunk; - rxm->full_len = rxm->full_len - chunk; - } + err = skb_copy_datagram_msg(skb, rxm->offset, + msg, chunk); + if (err < 0) + goto recv_end; + + if (!is_peek) { + rxm->offset = rxm->offset + chunk; + rxm->full_len = rxm->full_len - chunk; } } @@ -1757,15 +1825,15 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, if (!skb) goto splice_read_end; - /* splice does not support reading control messages */ - if (ctx->control != TLS_RECORD_TYPE_DATA) { - err = -ENOTSUPP; - goto splice_read_end; - } - if (!ctx->decrypted) { err = decrypt_skb_update(sk, skb, NULL, &chunk, &zc, false); + /* splice does not support reading control messages */ + if (ctx->control != TLS_RECORD_TYPE_DATA) { + err = -ENOTSUPP; + goto splice_read_end; + } + if (err < 0) { tls_err_abort(sk, EBADMSG); goto splice_read_end; @@ -1833,9 +1901,12 @@ static int tls_read_size(struct strparser *strp, struct sk_buff *skb) data_len = ((header[4] & 0xFF) | (header[3] << 8)); - cipher_overhead = tls_ctx->rx.tag_size + tls_ctx->rx.iv_size; + cipher_overhead = tls_ctx->rx.tag_size; + if (tls_ctx->crypto_recv.info.version != TLS_1_3_VERSION) + cipher_overhead += tls_ctx->rx.iv_size; - if (data_len > TLS_MAX_PAYLOAD_SIZE + cipher_overhead) { + if (data_len > TLS_MAX_PAYLOAD_SIZE + cipher_overhead + + tls_ctx->rx.tail_size) { ret = -EMSGSIZE; goto read_failure; } @@ -1844,12 +1915,12 @@ static int tls_read_size(struct strparser *strp, struct sk_buff *skb) goto read_failure; } - if (header[1] != TLS_VERSION_MINOR(tls_ctx->crypto_recv.info.version) || - header[2] != TLS_VERSION_MAJOR(tls_ctx->crypto_recv.info.version)) { + /* Note that both TLS1.3 and TLS1.2 use TLS_1_2 version here */ + if (header[1] != TLS_1_2_VERSION_MINOR || + header[2] != TLS_1_2_VERSION_MAJOR) { ret = -EINVAL; goto read_failure; } - #ifdef CONFIG_TLS_DEVICE handle_device_resync(strp->sk, TCP_SKB_CB(skb)->seq + rxm->offset, *(u64*)tls_ctx->rx.rec_seq); @@ -1901,7 +1972,9 @@ void tls_sw_free_resources_tx(struct sock *sk) if (atomic_read(&ctx->encrypt_pending)) crypto_wait_req(-EINPROGRESS, &ctx->async_wait); + release_sock(sk); cancel_delayed_work_sync(&ctx->tx_work.work); + lock_sock(sk); /* Tx whatever records we can transmit and abandon the rest */ tls_tx_records(sk, -1); @@ -1995,6 +2068,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) { struct tls_crypto_info *crypto_info; struct tls12_crypto_info_aes_gcm_128 *gcm_128_info; + struct tls12_crypto_info_aes_gcm_256 *gcm_256_info; struct tls_sw_context_tx *sw_ctx_tx = NULL; struct tls_sw_context_rx *sw_ctx_rx = NULL; struct cipher_context *cctx; @@ -2002,7 +2076,8 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) struct strp_callbacks cb; u16 nonce_size, tag_size, iv_size, rec_seq_size; struct crypto_tfm *tfm; - char *iv, *rec_seq; + char *iv, *rec_seq, *key, *salt; + size_t keysize; int rc = 0; if (!ctx) { @@ -2063,6 +2138,24 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) ((struct tls12_crypto_info_aes_gcm_128 *)crypto_info)->rec_seq; gcm_128_info = (struct tls12_crypto_info_aes_gcm_128 *)crypto_info; + keysize = TLS_CIPHER_AES_GCM_128_KEY_SIZE; + key = gcm_128_info->key; + salt = gcm_128_info->salt; + break; + } + case TLS_CIPHER_AES_GCM_256: { + nonce_size = TLS_CIPHER_AES_GCM_256_IV_SIZE; + tag_size = TLS_CIPHER_AES_GCM_256_TAG_SIZE; + iv_size = TLS_CIPHER_AES_GCM_256_IV_SIZE; + iv = ((struct tls12_crypto_info_aes_gcm_256 *)crypto_info)->iv; + rec_seq_size = TLS_CIPHER_AES_GCM_256_REC_SEQ_SIZE; + rec_seq = + ((struct tls12_crypto_info_aes_gcm_256 *)crypto_info)->rec_seq; + gcm_256_info = + (struct tls12_crypto_info_aes_gcm_256 *)crypto_info; + keysize = TLS_CIPHER_AES_GCM_256_KEY_SIZE; + key = gcm_256_info->key; + salt = gcm_256_info->salt; break; } default: @@ -2076,9 +2169,19 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) goto free_priv; } + if (crypto_info->version == TLS_1_3_VERSION) { + nonce_size = 0; + cctx->aad_size = TLS_HEADER_SIZE; + cctx->tail_size = 1; + } else { + cctx->aad_size = TLS_AAD_SPACE_SIZE; + cctx->tail_size = 0; + } + cctx->prepend_size = TLS_HEADER_SIZE + nonce_size; cctx->tag_size = tag_size; - cctx->overhead_size = cctx->prepend_size + cctx->tag_size; + cctx->overhead_size = cctx->prepend_size + cctx->tag_size + + cctx->tail_size; cctx->iv_size = iv_size; cctx->iv = kmalloc(iv_size + TLS_CIPHER_AES_GCM_128_SALT_SIZE, GFP_KERNEL); @@ -2086,7 +2189,8 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) rc = -ENOMEM; goto free_priv; } - memcpy(cctx->iv, gcm_128_info->salt, TLS_CIPHER_AES_GCM_128_SALT_SIZE); + /* Note: 128 & 256 bit salt are the same size */ + memcpy(cctx->iv, salt, TLS_CIPHER_AES_GCM_128_SALT_SIZE); memcpy(cctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv, iv_size); cctx->rec_seq_size = rec_seq_size; cctx->rec_seq = kmemdup(rec_seq, rec_seq_size, GFP_KERNEL); @@ -2106,8 +2210,8 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) ctx->push_pending_record = tls_sw_push_pending_record; - rc = crypto_aead_setkey(*aead, gcm_128_info->key, - TLS_CIPHER_AES_GCM_128_KEY_SIZE); + rc = crypto_aead_setkey(*aead, key, keysize); + if (rc) goto free_aead; @@ -2117,8 +2221,12 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) if (sw_ctx_rx) { tfm = crypto_aead_tfm(sw_ctx_rx->aead_recv); - sw_ctx_rx->async_capable = - tfm->__crt_alg->cra_flags & CRYPTO_ALG_ASYNC; + + if (crypto_info->version == TLS_1_3_VERSION) + sw_ctx_rx->async_capable = false; + else + sw_ctx_rx->async_capable = + tfm->__crt_alg->cra_flags & CRYPTO_ALG_ASYNC; /* Set up strparser */ memset(&cb, 0, sizeof(cb)); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index a60df252d3cc..d892000770cf 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1439,7 +1439,7 @@ static int vsock_stream_setsockopt(struct socket *sock, break; case SO_VM_SOCKETS_CONNECT_TIMEOUT: { - struct timeval tv; + struct __kernel_old_timeval tv; COPY_IN(tv); if (tv.tv_sec >= 0 && tv.tv_usec < USEC_PER_SEC && tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1)) { @@ -1517,7 +1517,7 @@ static int vsock_stream_getsockopt(struct socket *sock, break; case SO_VM_SOCKETS_CONNECT_TIMEOUT: { - struct timeval tv; + struct __kernel_old_timeval tv; tv.tv_sec = vsk->connect_timeout / HZ; tv.tv_usec = (vsk->connect_timeout - diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 5d3cce9e8744..15eb5d3d4750 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -75,6 +75,9 @@ static u32 virtio_transport_get_local_cid(void) { struct virtio_vsock *vsock = virtio_vsock_get(); + if (!vsock) + return VMADDR_CID_ANY; + return vsock->guest_cid; } @@ -584,10 +587,6 @@ static int virtio_vsock_probe(struct virtio_device *vdev) virtio_vsock_update_guest_cid(vsock); - ret = vsock_core_init(&virtio_transport.transport); - if (ret < 0) - goto out_vqs; - vsock->rx_buf_nr = 0; vsock->rx_buf_max_nr = 0; atomic_set(&vsock->queued_replies, 0); @@ -618,8 +617,6 @@ static int virtio_vsock_probe(struct virtio_device *vdev) mutex_unlock(&the_virtio_vsock_mutex); return 0; -out_vqs: - vsock->vdev->config->del_vqs(vsock->vdev); out: kfree(vsock); mutex_unlock(&the_virtio_vsock_mutex); @@ -637,6 +634,9 @@ static void virtio_vsock_remove(struct virtio_device *vdev) flush_work(&vsock->event_work); flush_work(&vsock->send_pkt_work); + /* Reset all connected sockets when the device disappear */ + vsock_for_each_connected_socket(virtio_vsock_reset_sock); + vdev->config->reset(vdev); mutex_lock(&vsock->rx_lock); @@ -669,7 +669,6 @@ static void virtio_vsock_remove(struct virtio_device *vdev) mutex_lock(&the_virtio_vsock_mutex); the_virtio_vsock = NULL; - vsock_core_exit(); mutex_unlock(&the_virtio_vsock_mutex); vdev->config->del_vqs(vdev); @@ -702,14 +701,28 @@ static int __init virtio_vsock_init(void) virtio_vsock_workqueue = alloc_workqueue("virtio_vsock", 0, 0); if (!virtio_vsock_workqueue) return -ENOMEM; + ret = register_virtio_driver(&virtio_vsock_driver); if (ret) - destroy_workqueue(virtio_vsock_workqueue); + goto out_wq; + + ret = vsock_core_init(&virtio_transport.transport); + if (ret) + goto out_vdr; + + return 0; + +out_vdr: + unregister_virtio_driver(&virtio_vsock_driver); +out_wq: + destroy_workqueue(virtio_vsock_workqueue); return ret; + } static void __exit virtio_vsock_exit(void) { + vsock_core_exit(); unregister_virtio_driver(&virtio_vsock_driver); destroy_workqueue(virtio_vsock_workqueue); } diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index c361ce782412..c3d5ab01fba7 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -1651,6 +1651,10 @@ static void vmci_transport_cleanup(struct work_struct *work) static void vmci_transport_destruct(struct vsock_sock *vsk) { + /* transport can be NULL if we hit a failure at init() time */ + if (!vmci_trans(vsk)) + return; + /* Ensure that the detach callback doesn't use the sk/vsk * we are about to destruct. */ diff --git a/net/wireless/ap.c b/net/wireless/ap.c index 882d97bdc6bf..550ac9d827fe 100644 --- a/net/wireless/ap.c +++ b/net/wireless/ap.c @@ -41,6 +41,8 @@ int __cfg80211_stop_ap(struct cfg80211_registered_device *rdev, cfg80211_sched_dfs_chan_update(rdev); } + schedule_work(&cfg80211_disconnect_work); + return err; } diff --git a/net/wireless/core.c b/net/wireless/core.c index 623dfe5e211c..b36ad8efb5e5 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1068,6 +1068,8 @@ static void __cfg80211_unregister_wdev(struct wireless_dev *wdev, bool sync) ASSERT_RTNL(); + flush_work(&wdev->pmsr_free_wk); + nl80211_notify_iface(rdev, wdev, NL80211_CMD_DEL_INTERFACE); list_del_rcu(&wdev->list); diff --git a/net/wireless/core.h b/net/wireless/core.h index c5d6f3418601..f6b40563dc63 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -445,6 +445,8 @@ void cfg80211_process_wdev_events(struct wireless_dev *wdev); bool cfg80211_does_bw_fit_range(const struct ieee80211_freq_range *freq_range, u32 center_freq_khz, u32 bw_khz); +extern struct work_struct cfg80211_disconnect_work; + /** * cfg80211_chandef_dfs_usable - checks if chandef is DFS usable * @wiphy: the wiphy to validate against diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 74150ad95823..e36437abc45a 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -250,7 +250,7 @@ nl80211_pmsr_ftm_req_attr_policy[NL80211_PMSR_FTM_REQ_ATTR_MAX + 1] = { [NL80211_PMSR_FTM_REQ_ATTR_BURST_DURATION] = NLA_POLICY_MAX(NLA_U8, 15), [NL80211_PMSR_FTM_REQ_ATTR_FTMS_PER_BURST] = - NLA_POLICY_MAX(NLA_U8, 15), + NLA_POLICY_MAX(NLA_U8, 31), [NL80211_PMSR_FTM_REQ_ATTR_NUM_FTMR_RETRIES] = { .type = NLA_U8 }, [NL80211_PMSR_FTM_REQ_ATTR_REQUEST_LCI] = { .type = NLA_FLAG }, [NL80211_PMSR_FTM_REQ_ATTR_REQUEST_CIVICLOC] = { .type = NLA_FLAG }, @@ -259,15 +259,13 @@ nl80211_pmsr_ftm_req_attr_policy[NL80211_PMSR_FTM_REQ_ATTR_MAX + 1] = { static const struct nla_policy nl80211_pmsr_req_data_policy[NL80211_PMSR_TYPE_MAX + 1] = { [NL80211_PMSR_TYPE_FTM] = - NLA_POLICY_NESTED(NL80211_PMSR_FTM_REQ_ATTR_MAX, - nl80211_pmsr_ftm_req_attr_policy), + NLA_POLICY_NESTED(nl80211_pmsr_ftm_req_attr_policy), }; static const struct nla_policy nl80211_pmsr_req_attr_policy[NL80211_PMSR_REQ_ATTR_MAX + 1] = { [NL80211_PMSR_REQ_ATTR_DATA] = - NLA_POLICY_NESTED(NL80211_PMSR_TYPE_MAX, - nl80211_pmsr_req_data_policy), + NLA_POLICY_NESTED(nl80211_pmsr_req_data_policy), [NL80211_PMSR_REQ_ATTR_GET_AP_TSF] = { .type = NLA_FLAG }, }; @@ -280,8 +278,7 @@ nl80211_psmr_peer_attr_policy[NL80211_PMSR_PEER_ATTR_MAX + 1] = { */ [NL80211_PMSR_PEER_ATTR_CHAN] = { .type = NLA_NESTED }, [NL80211_PMSR_PEER_ATTR_REQ] = - NLA_POLICY_NESTED(NL80211_PMSR_REQ_ATTR_MAX, - nl80211_pmsr_req_attr_policy), + NLA_POLICY_NESTED(nl80211_pmsr_req_attr_policy), [NL80211_PMSR_PEER_ATTR_RESP] = { .type = NLA_REJECT }, }; @@ -292,8 +289,7 @@ nl80211_pmsr_attr_policy[NL80211_PMSR_ATTR_MAX + 1] = { [NL80211_PMSR_ATTR_RANDOMIZE_MAC_ADDR] = { .type = NLA_REJECT }, [NL80211_PMSR_ATTR_TYPE_CAPA] = { .type = NLA_REJECT }, [NL80211_PMSR_ATTR_PEERS] = - NLA_POLICY_NESTED_ARRAY(NL80211_PMSR_PEER_ATTR_MAX, - nl80211_psmr_peer_attr_policy), + NLA_POLICY_NESTED_ARRAY(nl80211_psmr_peer_attr_policy), }; const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { @@ -555,8 +551,8 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { }, [NL80211_ATTR_TIMEOUT] = NLA_POLICY_MIN(NLA_U32, 1), [NL80211_ATTR_PEER_MEASUREMENTS] = - NLA_POLICY_NESTED(NL80211_PMSR_ATTR_MAX, - nl80211_pmsr_attr_policy), + NLA_POLICY_NESTED(nl80211_pmsr_attr_policy), + [NL80211_ATTR_AIRTIME_WEIGHT] = NLA_POLICY_MIN(NLA_U16, 1), }; /* policy for the key attributes */ @@ -2278,6 +2274,15 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, if (nl80211_send_pmsr_capa(rdev, msg)) goto nla_put_failure; + state->split_start++; + break; + case 15: + if (rdev->wiphy.akm_suites && + nla_put(msg, NL80211_ATTR_AKM_SUITES, + sizeof(u32) * rdev->wiphy.n_akm_suites, + rdev->wiphy.akm_suites)) + goto nla_put_failure; + /* done */ state->split_start = 0; break; @@ -4540,6 +4545,9 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) nl80211_calculate_ap_params(¶ms); + if (info->attrs[NL80211_ATTR_EXTERNAL_AUTH_SUPPORT]) + params.flags |= AP_SETTINGS_EXTERNAL_AUTH_SUPPORT; + wdev_lock(wdev); err = rdev_start_ap(rdev, dev, ¶ms); if (!err) { @@ -4851,6 +4859,11 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid, PUT_SINFO(PLID, plid, u16); PUT_SINFO(PLINK_STATE, plink_state, u8); PUT_SINFO_U64(RX_DURATION, rx_duration); + PUT_SINFO_U64(TX_DURATION, tx_duration); + + if (wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_AIRTIME_FAIRNESS)) + PUT_SINFO(AIRTIME_WEIGHT, airtime_weight, u16); switch (rdev->wiphy.signal_type) { case CFG80211_SIGNAL_TYPE_MBM: @@ -5470,6 +5483,15 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info) nla_get_u8(info->attrs[NL80211_ATTR_OPMODE_NOTIF]); } + if (info->attrs[NL80211_ATTR_AIRTIME_WEIGHT]) + params.airtime_weight = + nla_get_u16(info->attrs[NL80211_ATTR_AIRTIME_WEIGHT]); + + if (params.airtime_weight && + !wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_AIRTIME_FAIRNESS)) + return -EOPNOTSUPP; + /* Include parameters for TDLS peer (will check later) */ err = nl80211_set_station_tdls(info, ¶ms); if (err) @@ -5598,6 +5620,15 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) params.plink_action = nla_get_u8(info->attrs[NL80211_ATTR_STA_PLINK_ACTION]); + if (info->attrs[NL80211_ATTR_AIRTIME_WEIGHT]) + params.airtime_weight = + nla_get_u16(info->attrs[NL80211_ATTR_AIRTIME_WEIGHT]); + + if (params.airtime_weight && + !wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_AIRTIME_FAIRNESS)) + return -EOPNOTSUPP; + err = nl80211_parse_sta_channel_info(info, ¶ms); if (err) return err; @@ -5803,7 +5834,13 @@ static int nl80211_send_mpath(struct sk_buff *msg, u32 portid, u32 seq, pinfo->discovery_timeout)) || ((pinfo->filled & MPATH_INFO_DISCOVERY_RETRIES) && nla_put_u8(msg, NL80211_MPATH_INFO_DISCOVERY_RETRIES, - pinfo->discovery_retries))) + pinfo->discovery_retries)) || + ((pinfo->filled & MPATH_INFO_HOP_COUNT) && + nla_put_u8(msg, NL80211_MPATH_INFO_HOP_COUNT, + pinfo->hop_count)) || + ((pinfo->filled & MPATH_INFO_PATH_CHANGE) && + nla_put_u32(msg, NL80211_MPATH_INFO_PATH_CHANGE, + pinfo->path_change_count))) goto nla_put_failure; nla_nest_end(msg, pinfoattr); @@ -9857,7 +9894,10 @@ static int nl80211_setdel_pmksa(struct sk_buff *skb, struct genl_info *info) } if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION && - dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_CLIENT) + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_CLIENT && + !(dev->ieee80211_ptr->iftype == NL80211_IFTYPE_AP && + wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_AP_PMKSA_CACHING))) return -EOPNOTSUPP; switch (info->genlhdr->cmd) { @@ -13047,7 +13087,9 @@ static int nl80211_external_auth(struct sk_buff *skb, struct genl_info *info) if (!rdev->ops->external_auth) return -EOPNOTSUPP; - if (!info->attrs[NL80211_ATTR_SSID]) + if (!info->attrs[NL80211_ATTR_SSID] && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) return -EINVAL; if (!info->attrs[NL80211_ATTR_BSSID]) @@ -13058,18 +13100,24 @@ static int nl80211_external_auth(struct sk_buff *skb, struct genl_info *info) memset(¶ms, 0, sizeof(params)); - params.ssid.ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]); - if (params.ssid.ssid_len == 0 || - params.ssid.ssid_len > IEEE80211_MAX_SSID_LEN) - return -EINVAL; - memcpy(params.ssid.ssid, nla_data(info->attrs[NL80211_ATTR_SSID]), - params.ssid.ssid_len); + if (info->attrs[NL80211_ATTR_SSID]) { + params.ssid.ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]); + if (params.ssid.ssid_len == 0 || + params.ssid.ssid_len > IEEE80211_MAX_SSID_LEN) + return -EINVAL; + memcpy(params.ssid.ssid, + nla_data(info->attrs[NL80211_ATTR_SSID]), + params.ssid.ssid_len); + } memcpy(params.bssid, nla_data(info->attrs[NL80211_ATTR_BSSID]), ETH_ALEN); params.status = nla_get_u16(info->attrs[NL80211_ATTR_STATUS_CODE]); + if (info->attrs[NL80211_ATTR_PMKID]) + params.pmkid = nla_data(info->attrs[NL80211_ATTR_PMKID]); + return rdev_external_auth(rdev, dev, ¶ms); } diff --git a/net/wireless/pmsr.c b/net/wireless/pmsr.c index de9286703280..0216ab555249 100644 --- a/net/wireless/pmsr.c +++ b/net/wireless/pmsr.c @@ -256,8 +256,7 @@ int nl80211_pmsr_start(struct sk_buff *skb, struct genl_info *info) if (err) goto out_err; } else { - memcpy(req->mac_addr, nla_data(info->attrs[NL80211_ATTR_MAC]), - ETH_ALEN); + memcpy(req->mac_addr, wdev_address(wdev), ETH_ALEN); memset(req->mac_addr_mask, 0xff, ETH_ALEN); } @@ -272,6 +271,7 @@ int nl80211_pmsr_start(struct sk_buff *skb, struct genl_info *info) req->n_peers = count; req->cookie = cfg80211_assign_cookie(rdev); + req->nl_portid = info->snd_portid; err = rdev_start_pmsr(rdev, wdev, req); if (err) @@ -530,14 +530,14 @@ free: } EXPORT_SYMBOL_GPL(cfg80211_pmsr_report); -void cfg80211_pmsr_free_wk(struct work_struct *work) +static void cfg80211_pmsr_process_abort(struct wireless_dev *wdev) { - struct wireless_dev *wdev = container_of(work, struct wireless_dev, - pmsr_free_wk); struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct cfg80211_pmsr_request *req, *tmp; LIST_HEAD(free_list); + lockdep_assert_held(&wdev->mtx); + spin_lock_bh(&wdev->pmsr_lock); list_for_each_entry_safe(req, tmp, &wdev->pmsr_list, list) { if (req->nl_portid) @@ -547,14 +547,22 @@ void cfg80211_pmsr_free_wk(struct work_struct *work) spin_unlock_bh(&wdev->pmsr_lock); list_for_each_entry_safe(req, tmp, &free_list, list) { - wdev_lock(wdev); rdev_abort_pmsr(rdev, wdev, req); - wdev_unlock(wdev); kfree(req); } } +void cfg80211_pmsr_free_wk(struct work_struct *work) +{ + struct wireless_dev *wdev = container_of(work, struct wireless_dev, + pmsr_free_wk); + + wdev_lock(wdev); + cfg80211_pmsr_process_abort(wdev); + wdev_unlock(wdev); +} + void cfg80211_pmsr_wdev_down(struct wireless_dev *wdev) { struct cfg80211_pmsr_request *req; @@ -568,8 +576,8 @@ void cfg80211_pmsr_wdev_down(struct wireless_dev *wdev) spin_unlock_bh(&wdev->pmsr_lock); if (found) - schedule_work(&wdev->pmsr_free_wk); - flush_work(&wdev->pmsr_free_wk); + cfg80211_pmsr_process_abort(wdev); + WARN_ON(!list_empty(&wdev->pmsr_list)); } diff --git a/net/wireless/reg.c b/net/wireless/reg.c index dd58b9909ac9..adfa58fa6536 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -2729,9 +2729,7 @@ static void notify_self_managed_wiphys(struct regulatory_request *request) list_for_each_entry(rdev, &cfg80211_rdev_list, list) { wiphy = &rdev->wiphy; if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED && - request->initiator == NL80211_REGDOM_SET_BY_USER && - request->user_reg_hint_type == - NL80211_USER_REG_HINT_CELL_BASE) + request->initiator == NL80211_REGDOM_SET_BY_USER) reg_call_notifier(wiphy, request); } } diff --git a/net/wireless/sme.c b/net/wireless/sme.c index f741d8376a46..7d34cb884840 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -667,7 +667,7 @@ static void disconnect_work(struct work_struct *work) rtnl_unlock(); } -static DECLARE_WORK(cfg80211_disconnect_work, disconnect_work); +DECLARE_WORK(cfg80211_disconnect_work, disconnect_work); /* diff --git a/net/wireless/util.c b/net/wireless/util.c index cd48cdd582c0..ec30e3732c7b 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -5,7 +5,7 @@ * Copyright 2007-2009 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2017 Intel Deutschland GmbH - * Copyright (C) 2018 Intel Corporation + * Copyright (C) 2018-2019 Intel Corporation */ #include <linux/export.h> #include <linux/bitops.h> @@ -19,6 +19,7 @@ #include <linux/mpls.h> #include <linux/gcd.h> #include <linux/bitfield.h> +#include <linux/nospec.h> #include "core.h" #include "rdev-ops.h" @@ -715,20 +716,25 @@ unsigned int cfg80211_classify8021d(struct sk_buff *skb, { unsigned int dscp; unsigned char vlan_priority; + unsigned int ret; /* skb->priority values from 256->263 are magic values to * directly indicate a specific 802.1d priority. This is used * to allow 802.1d priority to be passed directly in from VLAN * tags, etc. */ - if (skb->priority >= 256 && skb->priority <= 263) - return skb->priority - 256; + if (skb->priority >= 256 && skb->priority <= 263) { + ret = skb->priority - 256; + goto out; + } if (skb_vlan_tag_present(skb)) { vlan_priority = (skb_vlan_tag_get(skb) & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; - if (vlan_priority > 0) - return vlan_priority; + if (vlan_priority > 0) { + ret = vlan_priority; + goto out; + } } switch (skb->protocol) { @@ -747,8 +753,9 @@ unsigned int cfg80211_classify8021d(struct sk_buff *skb, if (!mpls) return 0; - return (ntohl(mpls->entry) & MPLS_LS_TC_MASK) + ret = (ntohl(mpls->entry) & MPLS_LS_TC_MASK) >> MPLS_LS_TC_SHIFT; + goto out; } case htons(ETH_P_80221): /* 802.21 is always network control traffic */ @@ -761,18 +768,24 @@ unsigned int cfg80211_classify8021d(struct sk_buff *skb, unsigned int i, tmp_dscp = dscp >> 2; for (i = 0; i < qos_map->num_des; i++) { - if (tmp_dscp == qos_map->dscp_exception[i].dscp) - return qos_map->dscp_exception[i].up; + if (tmp_dscp == qos_map->dscp_exception[i].dscp) { + ret = qos_map->dscp_exception[i].up; + goto out; + } } for (i = 0; i < 8; i++) { if (tmp_dscp >= qos_map->up[i].low && - tmp_dscp <= qos_map->up[i].high) - return i; + tmp_dscp <= qos_map->up[i].high) { + ret = i; + goto out; + } } } - return dscp >> 5; + ret = dscp >> 5; +out: + return array_index_nospec(ret, IEEE80211_NUM_TIDS); } EXPORT_SYMBOL(cfg80211_classify8021d); diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index 06943d9c9835..d522787c7354 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -1337,6 +1337,7 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev) wstats.qual.qual = sig + 110; break; } + /* fall through */ case CFG80211_SIGNAL_TYPE_UNSPEC: if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_SIGNAL)) { wstats.qual.updated |= IW_QUAL_LEVEL_UPDATED; @@ -1345,6 +1346,7 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev) wstats.qual.qual = sinfo.signal; break; } + /* fall through */ default: wstats.qual.updated |= IW_QUAL_LEVEL_INVALID; wstats.qual.updated |= IW_QUAL_QUAL_INVALID; diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 5121729b8b63..ec3a828672ef 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -352,17 +352,15 @@ static unsigned int x25_new_lci(struct x25_neigh *nb) unsigned int lci = 1; struct sock *sk; - read_lock_bh(&x25_list_lock); - - while ((sk = __x25_find_socket(lci, nb)) != NULL) { + while ((sk = x25_find_socket(lci, nb)) != NULL) { sock_put(sk); if (++lci == 4096) { lci = 0; break; } + cond_resched(); } - read_unlock_bh(&x25_list_lock); return lci; } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 934492bad8e0..ba0a4048c846 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -680,16 +680,6 @@ static void xfrm_hash_resize(struct work_struct *work) mutex_unlock(&hash_resize_mutex); } -static void xfrm_hash_reset_inexact_table(struct net *net) -{ - struct xfrm_pol_inexact_bin *b; - - lockdep_assert_held(&net->xfrm.xfrm_policy_lock); - - list_for_each_entry(b, &net->xfrm.inexact_bins, inexact_bins) - INIT_HLIST_HEAD(&b->hhead); -} - /* Make sure *pol can be inserted into fastbin. * Useful to check that later insert requests will be sucessful * (provided xfrm_policy_lock is held throughout). @@ -833,13 +823,13 @@ static void xfrm_policy_inexact_list_reinsert(struct net *net, u16 family) { unsigned int matched_s, matched_d; - struct hlist_node *newpos = NULL; struct xfrm_policy *policy, *p; matched_s = 0; matched_d = 0; list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) { + struct hlist_node *newpos = NULL; bool matches_s, matches_d; if (!policy->bydst_reinsert) @@ -849,16 +839,19 @@ static void xfrm_policy_inexact_list_reinsert(struct net *net, policy->bydst_reinsert = false; hlist_for_each_entry(p, &n->hhead, bydst) { - if (policy->priority >= p->priority) + if (policy->priority > p->priority) + newpos = &p->bydst; + else if (policy->priority == p->priority && + policy->pos > p->pos) newpos = &p->bydst; else break; } if (newpos) - hlist_add_behind(&policy->bydst, newpos); + hlist_add_behind_rcu(&policy->bydst, newpos); else - hlist_add_head(&policy->bydst, &n->hhead); + hlist_add_head_rcu(&policy->bydst, &n->hhead); /* paranoia checks follow. * Check that the reinserted policy matches at least @@ -893,12 +886,13 @@ static void xfrm_policy_inexact_node_reinsert(struct net *net, struct rb_root *new, u16 family) { - struct rb_node **p, *parent = NULL; struct xfrm_pol_inexact_node *node; + struct rb_node **p, *parent; /* we should not have another subtree here */ WARN_ON_ONCE(!RB_EMPTY_ROOT(&n->root)); - +restart: + parent = NULL; p = &new->rb_node; while (*p) { u8 prefixlen; @@ -918,12 +912,11 @@ static void xfrm_policy_inexact_node_reinsert(struct net *net, } else { struct xfrm_policy *tmp; - hlist_for_each_entry(tmp, &node->hhead, bydst) - tmp->bydst_reinsert = true; - hlist_for_each_entry(tmp, &n->hhead, bydst) + hlist_for_each_entry(tmp, &n->hhead, bydst) { tmp->bydst_reinsert = true; + hlist_del_rcu(&tmp->bydst); + } - INIT_HLIST_HEAD(&node->hhead); xfrm_policy_inexact_list_reinsert(net, node, family); if (node->prefixlen == n->prefixlen) { @@ -935,8 +928,7 @@ static void xfrm_policy_inexact_node_reinsert(struct net *net, kfree_rcu(n, rcu); n = node; n->prefixlen = prefixlen; - *p = new->rb_node; - parent = NULL; + goto restart; } } @@ -965,12 +957,11 @@ static void xfrm_policy_inexact_node_merge(struct net *net, family); } - hlist_for_each_entry(tmp, &v->hhead, bydst) - tmp->bydst_reinsert = true; - hlist_for_each_entry(tmp, &n->hhead, bydst) + hlist_for_each_entry(tmp, &v->hhead, bydst) { tmp->bydst_reinsert = true; + hlist_del_rcu(&tmp->bydst); + } - INIT_HLIST_HEAD(&n->hhead); xfrm_policy_inexact_list_reinsert(net, n, family); } @@ -1235,6 +1226,7 @@ static void xfrm_hash_rebuild(struct work_struct *work) } while (read_seqretry(&net->xfrm.policy_hthresh.lock, seq)); spin_lock_bh(&net->xfrm.xfrm_policy_lock); + write_seqcount_begin(&xfrm_policy_hash_generation); /* make sure that we can insert the indirect policies again before * we start with destructive action. @@ -1278,10 +1270,14 @@ static void xfrm_hash_rebuild(struct work_struct *work) } /* reset the bydst and inexact table in all directions */ - xfrm_hash_reset_inexact_table(net); - for (dir = 0; dir < XFRM_POLICY_MAX; dir++) { - INIT_HLIST_HEAD(&net->xfrm.policy_inexact[dir]); + struct hlist_node *n; + + hlist_for_each_entry_safe(policy, n, + &net->xfrm.policy_inexact[dir], + bydst_inexact_list) + hlist_del_init(&policy->bydst_inexact_list); + hmask = net->xfrm.policy_bydst[dir].hmask; odst = net->xfrm.policy_bydst[dir].table; for (i = hmask; i >= 0; i--) @@ -1313,6 +1309,9 @@ static void xfrm_hash_rebuild(struct work_struct *work) newpos = NULL; chain = policy_hash_bysel(net, &policy->selector, policy->family, dir); + + hlist_del_rcu(&policy->bydst); + if (!chain) { void *p = xfrm_policy_inexact_insert(policy, dir, 0); @@ -1334,6 +1333,7 @@ static void xfrm_hash_rebuild(struct work_struct *work) out_unlock: __xfrm_policy_inexact_flush(net); + write_seqcount_end(&xfrm_policy_hash_generation); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); mutex_unlock(&hash_resize_mutex); @@ -2600,7 +2600,10 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, dst_copy_metrics(dst1, dst); if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) { - __u32 mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]); + __u32 mark = 0; + + if (xfrm[i]->props.smark.v || xfrm[i]->props.smark.m) + mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]); family = xfrm[i]->props.family; dst = xfrm_dst_lookup(xfrm[i], tos, fl->flowi_oif, diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 277c1c46fe94..c6d26afcf89d 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1488,10 +1488,15 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family) if (!ut[i].family) ut[i].family = family; - if ((ut[i].mode == XFRM_MODE_TRANSPORT) && - (ut[i].family != prev_family)) - return -EINVAL; - + switch (ut[i].mode) { + case XFRM_MODE_TUNNEL: + case XFRM_MODE_BEET: + break; + default: + if (ut[i].family != prev_family) + return -EINVAL; + break; + } if (ut[i].mode >= XFRM_MODE_MAX) return -EINVAL; diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index db1a91dfa702..a0ef7eddd0b3 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -87,18 +87,18 @@ test_cgrp2_sock2-objs := bpf_load.o test_cgrp2_sock2.o xdp1-objs := xdp1_user.o # reuse xdp1 source intentionally xdp2-objs := xdp1_user.o -xdp_router_ipv4-objs := bpf_load.o xdp_router_ipv4_user.o +xdp_router_ipv4-objs := xdp_router_ipv4_user.o test_current_task_under_cgroup-objs := bpf_load.o $(CGROUP_HELPERS) \ test_current_task_under_cgroup_user.o trace_event-objs := bpf_load.o trace_event_user.o $(TRACE_HELPERS) sampleip-objs := bpf_load.o sampleip_user.o $(TRACE_HELPERS) tc_l2_redirect-objs := bpf_load.o tc_l2_redirect_user.o lwt_len_hist-objs := bpf_load.o lwt_len_hist_user.o -xdp_tx_iptunnel-objs := bpf_load.o xdp_tx_iptunnel_user.o +xdp_tx_iptunnel-objs := xdp_tx_iptunnel_user.o test_map_in_map-objs := bpf_load.o test_map_in_map_user.o per_socket_stats_example-objs := cookie_uid_helper_example.o -xdp_redirect-objs := bpf_load.o xdp_redirect_user.o -xdp_redirect_map-objs := bpf_load.o xdp_redirect_map_user.o +xdp_redirect-objs := xdp_redirect_user.o +xdp_redirect_map-objs := xdp_redirect_map_user.o xdp_redirect_cpu-objs := bpf_load.o xdp_redirect_cpu_user.o xdp_monitor-objs := bpf_load.o xdp_monitor_user.o xdp_rxq_info-objs := xdp_rxq_info_user.o diff --git a/samples/bpf/xdp1_user.c b/samples/bpf/xdp1_user.c index 8bfda95c77ad..6a64e93365e1 100644 --- a/samples/bpf/xdp1_user.c +++ b/samples/bpf/xdp1_user.c @@ -22,11 +22,23 @@ #include "bpf/libbpf.h" static int ifindex; -static __u32 xdp_flags; +static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; +static __u32 prog_id; static void int_exit(int sig) { - bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); + __u32 curr_prog_id = 0; + + if (bpf_get_link_xdp_id(ifindex, &curr_prog_id, xdp_flags)) { + printf("bpf_get_link_xdp_id failed\n"); + exit(1); + } + if (prog_id == curr_prog_id) + bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); + else if (!curr_prog_id) + printf("couldn't find a prog id on a given interface\n"); + else + printf("program on interface changed, not removing\n"); exit(0); } @@ -63,7 +75,8 @@ static void usage(const char *prog) "usage: %s [OPTS] IFACE\n\n" "OPTS:\n" " -S use skb-mode\n" - " -N enforce native mode\n", + " -N enforce native mode\n" + " -F force loading prog\n", prog); } @@ -73,11 +86,14 @@ int main(int argc, char **argv) struct bpf_prog_load_attr prog_load_attr = { .prog_type = BPF_PROG_TYPE_XDP, }; - const char *optstr = "SN"; + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + const char *optstr = "FSN"; int prog_fd, map_fd, opt; struct bpf_object *obj; struct bpf_map *map; char filename[256]; + int err; while ((opt = getopt(argc, argv, optstr)) != -1) { switch (opt) { @@ -87,6 +103,9 @@ int main(int argc, char **argv) case 'N': xdp_flags |= XDP_FLAGS_DRV_MODE; break; + case 'F': + xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST; + break; default: usage(basename(argv[0])); return 1; @@ -135,6 +154,13 @@ int main(int argc, char **argv) return 1; } + err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + if (err) { + printf("can't get prog info - %s\n", strerror(errno)); + return err; + } + prog_id = info.id; + poll_stats(map_fd, 2); return 0; diff --git a/samples/bpf/xdp_adjust_tail_user.c b/samples/bpf/xdp_adjust_tail_user.c index 3042ce37dae8..07e1b9269e49 100644 --- a/samples/bpf/xdp_adjust_tail_user.c +++ b/samples/bpf/xdp_adjust_tail_user.c @@ -24,12 +24,25 @@ #define STATS_INTERVAL_S 2U static int ifindex = -1; -static __u32 xdp_flags; +static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; +static __u32 prog_id; static void int_exit(int sig) { - if (ifindex > -1) - bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); + __u32 curr_prog_id = 0; + + if (ifindex > -1) { + if (bpf_get_link_xdp_id(ifindex, &curr_prog_id, xdp_flags)) { + printf("bpf_get_link_xdp_id failed\n"); + exit(1); + } + if (prog_id == curr_prog_id) + bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); + else if (!curr_prog_id) + printf("couldn't find a prog id on a given iface\n"); + else + printf("program on interface changed, not removing\n"); + } exit(0); } @@ -60,6 +73,7 @@ static void usage(const char *cmd) printf(" -T <stop-after-X-seconds> Default: 0 (forever)\n"); printf(" -S use skb-mode\n"); printf(" -N enforce native mode\n"); + printf(" -F force loading prog\n"); printf(" -h Display this help\n"); } @@ -70,12 +84,15 @@ int main(int argc, char **argv) .prog_type = BPF_PROG_TYPE_XDP, }; unsigned char opt_flags[256] = {}; + const char *optstr = "i:T:SNFh"; + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); unsigned int kill_after_s = 0; - const char *optstr = "i:T:SNh"; int i, prog_fd, map_fd, opt; struct bpf_object *obj; struct bpf_map *map; char filename[256]; + int err; for (i = 0; i < strlen(optstr); i++) if (optstr[i] != 'h' && 'a' <= optstr[i] && optstr[i] <= 'z') @@ -96,6 +113,9 @@ int main(int argc, char **argv) case 'N': xdp_flags |= XDP_FLAGS_DRV_MODE; break; + case 'F': + xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST; + break; default: usage(argv[0]); return 1; @@ -142,9 +162,15 @@ int main(int argc, char **argv) return 1; } - poll_stats(map_fd, kill_after_s); + err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + if (err) { + printf("can't get prog info - %s\n", strerror(errno)); + return 1; + } + prog_id = info.id; - bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); + poll_stats(map_fd, kill_after_s); + int_exit(0); return 0; } diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c index 2d23054aaccf..586b294d72d3 100644 --- a/samples/bpf/xdp_redirect_cpu_user.c +++ b/samples/bpf/xdp_redirect_cpu_user.c @@ -24,20 +24,26 @@ static const char *__doc__ = /* How many xdp_progs are defined in _kern.c */ #define MAX_PROG 6 -/* Wanted to get rid of bpf_load.h and fake-"libbpf.h" (and instead - * use bpf/libbpf.h), but cannot as (currently) needed for XDP - * attaching to a device via bpf_set_link_xdp_fd() - */ #include <bpf/bpf.h> -#include "bpf_load.h" +#include "bpf/libbpf.h" #include "bpf_util.h" static int ifindex = -1; static char ifname_buf[IF_NAMESIZE]; static char *ifname; - -static __u32 xdp_flags; +static __u32 prog_id; + +static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; +static int cpu_map_fd; +static int rx_cnt_map_fd; +static int redirect_err_cnt_map_fd; +static int cpumap_enqueue_cnt_map_fd; +static int cpumap_kthread_cnt_map_fd; +static int cpus_available_map_fd; +static int cpus_count_map_fd; +static int cpus_iterator_map_fd; +static int exception_cnt_map_fd; /* Exit return codes */ #define EXIT_OK 0 @@ -51,27 +57,50 @@ static const struct option long_options[] = { {"help", no_argument, NULL, 'h' }, {"dev", required_argument, NULL, 'd' }, {"skb-mode", no_argument, NULL, 'S' }, - {"debug", no_argument, NULL, 'D' }, {"sec", required_argument, NULL, 's' }, - {"prognum", required_argument, NULL, 'p' }, + {"progname", required_argument, NULL, 'p' }, {"qsize", required_argument, NULL, 'q' }, {"cpu", required_argument, NULL, 'c' }, {"stress-mode", no_argument, NULL, 'x' }, {"no-separators", no_argument, NULL, 'z' }, + {"force", no_argument, NULL, 'F' }, {0, 0, NULL, 0 } }; static void int_exit(int sig) { - fprintf(stderr, - "Interrupted: Removing XDP program on ifindex:%d device:%s\n", - ifindex, ifname); - if (ifindex > -1) - bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); + __u32 curr_prog_id = 0; + + if (ifindex > -1) { + if (bpf_get_link_xdp_id(ifindex, &curr_prog_id, xdp_flags)) { + printf("bpf_get_link_xdp_id failed\n"); + exit(EXIT_FAIL); + } + if (prog_id == curr_prog_id) { + fprintf(stderr, + "Interrupted: Removing XDP program on ifindex:%d device:%s\n", + ifindex, ifname); + bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); + } else if (!curr_prog_id) { + printf("couldn't find a prog id on a given iface\n"); + } else { + printf("program on interface changed, not removing\n"); + } + } exit(EXIT_OK); } -static void usage(char *argv[]) +static void print_avail_progs(struct bpf_object *obj) +{ + struct bpf_program *pos; + + bpf_object__for_each_program(pos, obj) { + if (bpf_program__is_xdp(pos)) + printf(" %s\n", bpf_program__title(pos, false)); + } +} + +static void usage(char *argv[], struct bpf_object *obj) { int i; @@ -89,6 +118,8 @@ static void usage(char *argv[]) long_options[i].val); printf("\n"); } + printf("\n Programs to be used for --progname:\n"); + print_avail_progs(obj); printf("\n"); } @@ -263,7 +294,7 @@ static __u64 calc_errs_pps(struct datarec *r, static void stats_print(struct stats_record *stats_rec, struct stats_record *stats_prev, - int prog_num) + char *prog_name) { unsigned int nr_cpus = bpf_num_possible_cpus(); double pps = 0, drop = 0, err = 0; @@ -273,7 +304,7 @@ static void stats_print(struct stats_record *stats_rec, int i; /* Header */ - printf("Running XDP/eBPF prog_num:%d\n", prog_num); + printf("Running XDP/eBPF prog_name:%s\n", prog_name); printf("%-15s %-7s %-14s %-11s %-9s\n", "XDP-cpumap", "CPU:to", "pps", "drop-pps", "extra-info"); @@ -424,20 +455,20 @@ static void stats_collect(struct stats_record *rec) { int fd, i; - fd = map_fd[1]; /* map: rx_cnt */ + fd = rx_cnt_map_fd; map_collect_percpu(fd, 0, &rec->rx_cnt); - fd = map_fd[2]; /* map: redirect_err_cnt */ + fd = redirect_err_cnt_map_fd; map_collect_percpu(fd, 1, &rec->redir_err); - fd = map_fd[3]; /* map: cpumap_enqueue_cnt */ + fd = cpumap_enqueue_cnt_map_fd; for (i = 0; i < MAX_CPUS; i++) map_collect_percpu(fd, i, &rec->enq[i]); - fd = map_fd[4]; /* map: cpumap_kthread_cnt */ + fd = cpumap_kthread_cnt_map_fd; map_collect_percpu(fd, 0, &rec->kthread); - fd = map_fd[8]; /* map: exception_cnt */ + fd = exception_cnt_map_fd; map_collect_percpu(fd, 0, &rec->exception); } @@ -462,7 +493,7 @@ static int create_cpu_entry(__u32 cpu, __u32 queue_size, /* Add a CPU entry to cpumap, as this allocate a cpu entry in * the kernel for the cpu. */ - ret = bpf_map_update_elem(map_fd[0], &cpu, &queue_size, 0); + ret = bpf_map_update_elem(cpu_map_fd, &cpu, &queue_size, 0); if (ret) { fprintf(stderr, "Create CPU entry failed (err:%d)\n", ret); exit(EXIT_FAIL_BPF); @@ -471,23 +502,22 @@ static int create_cpu_entry(__u32 cpu, __u32 queue_size, /* Inform bpf_prog's that a new CPU is available to select * from via some control maps. */ - /* map_fd[5] = cpus_available */ - ret = bpf_map_update_elem(map_fd[5], &avail_idx, &cpu, 0); + ret = bpf_map_update_elem(cpus_available_map_fd, &avail_idx, &cpu, 0); if (ret) { fprintf(stderr, "Add to avail CPUs failed\n"); exit(EXIT_FAIL_BPF); } /* When not replacing/updating existing entry, bump the count */ - /* map_fd[6] = cpus_count */ - ret = bpf_map_lookup_elem(map_fd[6], &key, &curr_cpus_count); + ret = bpf_map_lookup_elem(cpus_count_map_fd, &key, &curr_cpus_count); if (ret) { fprintf(stderr, "Failed reading curr cpus_count\n"); exit(EXIT_FAIL_BPF); } if (new) { curr_cpus_count++; - ret = bpf_map_update_elem(map_fd[6], &key, &curr_cpus_count, 0); + ret = bpf_map_update_elem(cpus_count_map_fd, &key, + &curr_cpus_count, 0); if (ret) { fprintf(stderr, "Failed write curr cpus_count\n"); exit(EXIT_FAIL_BPF); @@ -510,8 +540,8 @@ static void mark_cpus_unavailable(void) int ret, i; for (i = 0; i < MAX_CPUS; i++) { - /* map_fd[5] = cpus_available */ - ret = bpf_map_update_elem(map_fd[5], &i, &invalid_cpu, 0); + ret = bpf_map_update_elem(cpus_available_map_fd, &i, + &invalid_cpu, 0); if (ret) { fprintf(stderr, "Failed marking CPU unavailable\n"); exit(EXIT_FAIL_BPF); @@ -531,7 +561,7 @@ static void stress_cpumap(void) create_cpu_entry(1, 16000, 0, false); } -static void stats_poll(int interval, bool use_separators, int prog_num, +static void stats_poll(int interval, bool use_separators, char *prog_name, bool stress_mode) { struct stats_record *record, *prev; @@ -547,7 +577,7 @@ static void stats_poll(int interval, bool use_separators, int prog_num, while (1) { swap(&prev, &record); stats_collect(record); - stats_print(record, prev, prog_num); + stats_print(record, prev, prog_name); sleep(interval); if (stress_mode) stress_cpumap(); @@ -557,20 +587,55 @@ static void stats_poll(int interval, bool use_separators, int prog_num, free_stats_record(prev); } +static int init_map_fds(struct bpf_object *obj) +{ + cpu_map_fd = bpf_object__find_map_fd_by_name(obj, "cpu_map"); + rx_cnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rx_cnt"); + redirect_err_cnt_map_fd = + bpf_object__find_map_fd_by_name(obj, "redirect_err_cnt"); + cpumap_enqueue_cnt_map_fd = + bpf_object__find_map_fd_by_name(obj, "cpumap_enqueue_cnt"); + cpumap_kthread_cnt_map_fd = + bpf_object__find_map_fd_by_name(obj, "cpumap_kthread_cnt"); + cpus_available_map_fd = + bpf_object__find_map_fd_by_name(obj, "cpus_available"); + cpus_count_map_fd = bpf_object__find_map_fd_by_name(obj, "cpus_count"); + cpus_iterator_map_fd = + bpf_object__find_map_fd_by_name(obj, "cpus_iterator"); + exception_cnt_map_fd = + bpf_object__find_map_fd_by_name(obj, "exception_cnt"); + + if (cpu_map_fd < 0 || rx_cnt_map_fd < 0 || + redirect_err_cnt_map_fd < 0 || cpumap_enqueue_cnt_map_fd < 0 || + cpumap_kthread_cnt_map_fd < 0 || cpus_available_map_fd < 0 || + cpus_count_map_fd < 0 || cpus_iterator_map_fd < 0 || + exception_cnt_map_fd < 0) + return -ENOENT; + + return 0; +} + int main(int argc, char **argv) { struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY}; + char *prog_name = "xdp_cpu_map5_lb_hash_ip_pairs"; + struct bpf_prog_load_attr prog_load_attr = { + .prog_type = BPF_PROG_TYPE_UNSPEC, + }; + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); bool use_separators = true; bool stress_mode = false; + struct bpf_program *prog; + struct bpf_object *obj; char filename[256]; - bool debug = false; int added_cpus = 0; int longindex = 0; int interval = 2; - int prog_num = 5; int add_cpu = -1; + int opt, err; + int prog_fd; __u32 qsize; - int opt; /* Notice: choosing he queue size is very important with the * ixgbe driver, because it's driver page recycling trick is @@ -581,26 +646,29 @@ int main(int argc, char **argv) qsize = 128+64; snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + prog_load_attr.file = filename; if (setrlimit(RLIMIT_MEMLOCK, &r)) { perror("setrlimit(RLIMIT_MEMLOCK)"); return 1; } - if (load_bpf_file(filename)) { - fprintf(stderr, "ERR in load_bpf_file(): %s", bpf_log_buf); + if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) return EXIT_FAIL; - } - if (!prog_fd[0]) { - fprintf(stderr, "ERR: load_bpf_file: %s\n", strerror(errno)); + if (prog_fd < 0) { + fprintf(stderr, "ERR: bpf_prog_load_xattr: %s\n", + strerror(errno)); + return EXIT_FAIL; + } + if (init_map_fds(obj) < 0) { + fprintf(stderr, "bpf_object__find_map_fd_by_name failed\n"); return EXIT_FAIL; } - mark_cpus_unavailable(); /* Parse commands line args */ - while ((opt = getopt_long(argc, argv, "hSd:", + while ((opt = getopt_long(argc, argv, "hSd:s:p:q:c:xzF", long_options, &longindex)) != -1) { switch (opt) { case 'd': @@ -624,9 +692,6 @@ int main(int argc, char **argv) case 'S': xdp_flags |= XDP_FLAGS_SKB_MODE; break; - case 'D': - debug = true; - break; case 'x': stress_mode = true; break; @@ -635,13 +700,7 @@ int main(int argc, char **argv) break; case 'p': /* Selecting eBPF prog to load */ - prog_num = atoi(optarg); - if (prog_num < 0 || prog_num >= MAX_PROG) { - fprintf(stderr, - "--prognum too large err(%d):%s\n", - errno, strerror(errno)); - goto error; - } + prog_name = optarg; break; case 'c': /* Add multiple CPUs */ @@ -658,24 +717,27 @@ int main(int argc, char **argv) case 'q': qsize = atoi(optarg); break; + case 'F': + xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST; + break; case 'h': error: default: - usage(argv); + usage(argv, obj); return EXIT_FAIL_OPTION; } } /* Required option */ if (ifindex == -1) { fprintf(stderr, "ERR: required option --dev missing\n"); - usage(argv); + usage(argv, obj); return EXIT_FAIL_OPTION; } /* Required option */ if (add_cpu == -1) { fprintf(stderr, "ERR: required option --cpu missing\n"); fprintf(stderr, " Specify multiple --cpu option to add more\n"); - usage(argv); + usage(argv, obj); return EXIT_FAIL_OPTION; } @@ -683,16 +745,30 @@ int main(int argc, char **argv) signal(SIGINT, int_exit); signal(SIGTERM, int_exit); - if (bpf_set_link_xdp_fd(ifindex, prog_fd[prog_num], xdp_flags) < 0) { + prog = bpf_object__find_program_by_title(obj, prog_name); + if (!prog) { + fprintf(stderr, "bpf_object__find_program_by_title failed\n"); + return EXIT_FAIL; + } + + prog_fd = bpf_program__fd(prog); + if (prog_fd < 0) { + fprintf(stderr, "bpf_program__fd failed\n"); + return EXIT_FAIL; + } + + if (bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags) < 0) { fprintf(stderr, "link set xdp fd failed\n"); return EXIT_FAIL_XDP; } - if (debug) { - printf("Debug-mode reading trace pipe (fix #define DEBUG)\n"); - read_trace_pipe(); + err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + if (err) { + printf("can't get prog info - %s\n", strerror(errno)); + return err; } + prog_id = info.id; - stats_poll(interval, use_separators, prog_num, stress_mode); + stats_poll(interval, use_separators, prog_name, stress_mode); return EXIT_OK; } diff --git a/samples/bpf/xdp_redirect_map_user.c b/samples/bpf/xdp_redirect_map_user.c index 4445e76854b5..327226be5a06 100644 --- a/samples/bpf/xdp_redirect_map_user.c +++ b/samples/bpf/xdp_redirect_map_user.c @@ -22,21 +22,48 @@ #include <libgen.h> #include <sys/resource.h> -#include "bpf_load.h" #include "bpf_util.h" #include <bpf/bpf.h> +#include "bpf/libbpf.h" static int ifindex_in; static int ifindex_out; static bool ifindex_out_xdp_dummy_attached = true; +static __u32 prog_id; +static __u32 dummy_prog_id; -static __u32 xdp_flags; +static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; +static int rxcnt_map_fd; static void int_exit(int sig) { - bpf_set_link_xdp_fd(ifindex_in, -1, xdp_flags); - if (ifindex_out_xdp_dummy_attached) - bpf_set_link_xdp_fd(ifindex_out, -1, xdp_flags); + __u32 curr_prog_id = 0; + + if (bpf_get_link_xdp_id(ifindex_in, &curr_prog_id, xdp_flags)) { + printf("bpf_get_link_xdp_id failed\n"); + exit(1); + } + if (prog_id == curr_prog_id) + bpf_set_link_xdp_fd(ifindex_in, -1, xdp_flags); + else if (!curr_prog_id) + printf("couldn't find a prog id on iface IN\n"); + else + printf("program on iface IN changed, not removing\n"); + + if (ifindex_out_xdp_dummy_attached) { + curr_prog_id = 0; + if (bpf_get_link_xdp_id(ifindex_out, &curr_prog_id, + xdp_flags)) { + printf("bpf_get_link_xdp_id failed\n"); + exit(1); + } + if (prog_id == curr_prog_id) + bpf_set_link_xdp_fd(ifindex_out, -1, xdp_flags); + else if (!curr_prog_id) + printf("couldn't find a prog id on iface OUT\n"); + else + printf("program on iface OUT changed, not removing\n"); + } exit(0); } @@ -53,7 +80,7 @@ static void poll_stats(int interval, int ifindex) int i; sleep(interval); - assert(bpf_map_lookup_elem(map_fd[1], &key, values) == 0); + assert(bpf_map_lookup_elem(rxcnt_map_fd, &key, values) == 0); for (i = 0; i < nr_cpus; i++) sum += (values[i] - prev[i]); if (sum) @@ -69,16 +96,26 @@ static void usage(const char *prog) "usage: %s [OPTS] IFINDEX_IN IFINDEX_OUT\n\n" "OPTS:\n" " -S use skb-mode\n" - " -N enforce native mode\n", + " -N enforce native mode\n" + " -F force loading prog\n", prog); } int main(int argc, char **argv) { struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; - const char *optstr = "SN"; - char filename[256]; + struct bpf_prog_load_attr prog_load_attr = { + .prog_type = BPF_PROG_TYPE_XDP, + }; + struct bpf_program *prog, *dummy_prog; + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + int prog_fd, dummy_prog_fd; + const char *optstr = "FSN"; + struct bpf_object *obj; int ret, opt, key = 0; + char filename[256]; + int tx_port_map_fd; while ((opt = getopt(argc, argv, optstr)) != -1) { switch (opt) { @@ -88,6 +125,9 @@ int main(int argc, char **argv) case 'N': xdp_flags |= XDP_FLAGS_DRV_MODE; break; + case 'F': + xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST; + break; default: usage(basename(argv[0])); return 1; @@ -109,37 +149,65 @@ int main(int argc, char **argv) printf("input: %d output: %d\n", ifindex_in, ifindex_out); snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + prog_load_attr.file = filename; + + if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) + return 1; - if (load_bpf_file(filename)) { - printf("%s", bpf_log_buf); + prog = bpf_program__next(NULL, obj); + dummy_prog = bpf_program__next(prog, obj); + if (!prog || !dummy_prog) { + printf("finding a prog in obj file failed\n"); + return 1; + } + /* bpf_prog_load_xattr gives us the pointer to first prog's fd, + * so we're missing only the fd for dummy prog + */ + dummy_prog_fd = bpf_program__fd(dummy_prog); + if (prog_fd < 0 || dummy_prog_fd < 0) { + printf("bpf_prog_load_xattr: %s\n", strerror(errno)); return 1; } - if (!prog_fd[0]) { - printf("load_bpf_file: %s\n", strerror(errno)); + tx_port_map_fd = bpf_object__find_map_fd_by_name(obj, "tx_port"); + rxcnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rxcnt"); + if (tx_port_map_fd < 0 || rxcnt_map_fd < 0) { + printf("bpf_object__find_map_fd_by_name failed\n"); return 1; } - if (bpf_set_link_xdp_fd(ifindex_in, prog_fd[0], xdp_flags) < 0) { + if (bpf_set_link_xdp_fd(ifindex_in, prog_fd, xdp_flags) < 0) { printf("ERROR: link set xdp fd failed on %d\n", ifindex_in); return 1; } + ret = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + if (ret) { + printf("can't get prog info - %s\n", strerror(errno)); + return ret; + } + prog_id = info.id; + /* Loading dummy XDP prog on out-device */ - if (bpf_set_link_xdp_fd(ifindex_out, prog_fd[1], + if (bpf_set_link_xdp_fd(ifindex_out, dummy_prog_fd, (xdp_flags | XDP_FLAGS_UPDATE_IF_NOEXIST)) < 0) { printf("WARN: link set xdp fd failed on %d\n", ifindex_out); ifindex_out_xdp_dummy_attached = false; } + memset(&info, 0, sizeof(info)); + ret = bpf_obj_get_info_by_fd(dummy_prog_fd, &info, &info_len); + if (ret) { + printf("can't get prog info - %s\n", strerror(errno)); + return ret; + } + dummy_prog_id = info.id; + signal(SIGINT, int_exit); signal(SIGTERM, int_exit); - printf("map[0] (vports) = %i, map[1] (map) = %i, map[2] (count) = %i\n", - map_fd[0], map_fd[1], map_fd[2]); - /* populate virtual to physical port map */ - ret = bpf_map_update_elem(map_fd[0], &key, &ifindex_out, 0); + ret = bpf_map_update_elem(tx_port_map_fd, &key, &ifindex_out, 0); if (ret) { perror("bpf_update_elem"); goto out; diff --git a/samples/bpf/xdp_redirect_user.c b/samples/bpf/xdp_redirect_user.c index 81a69e36cb78..a5d8ad3129ed 100644 --- a/samples/bpf/xdp_redirect_user.c +++ b/samples/bpf/xdp_redirect_user.c @@ -22,21 +22,48 @@ #include <libgen.h> #include <sys/resource.h> -#include "bpf_load.h" #include "bpf_util.h" #include <bpf/bpf.h> +#include "bpf/libbpf.h" static int ifindex_in; static int ifindex_out; static bool ifindex_out_xdp_dummy_attached = true; +static __u32 prog_id; +static __u32 dummy_prog_id; -static __u32 xdp_flags; +static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; +static int rxcnt_map_fd; static void int_exit(int sig) { - bpf_set_link_xdp_fd(ifindex_in, -1, xdp_flags); - if (ifindex_out_xdp_dummy_attached) - bpf_set_link_xdp_fd(ifindex_out, -1, xdp_flags); + __u32 curr_prog_id = 0; + + if (bpf_get_link_xdp_id(ifindex_in, &curr_prog_id, xdp_flags)) { + printf("bpf_get_link_xdp_id failed\n"); + exit(1); + } + if (prog_id == curr_prog_id) + bpf_set_link_xdp_fd(ifindex_in, -1, xdp_flags); + else if (!curr_prog_id) + printf("couldn't find a prog id on iface IN\n"); + else + printf("program on iface IN changed, not removing\n"); + + if (ifindex_out_xdp_dummy_attached) { + curr_prog_id = 0; + if (bpf_get_link_xdp_id(ifindex_out, &curr_prog_id, + xdp_flags)) { + printf("bpf_get_link_xdp_id failed\n"); + exit(1); + } + if (prog_id == curr_prog_id) + bpf_set_link_xdp_fd(ifindex_out, -1, xdp_flags); + else if (!curr_prog_id) + printf("couldn't find a prog id on iface OUT\n"); + else + printf("program on iface OUT changed, not removing\n"); + } exit(0); } @@ -53,7 +80,7 @@ static void poll_stats(int interval, int ifindex) int i; sleep(interval); - assert(bpf_map_lookup_elem(map_fd[1], &key, values) == 0); + assert(bpf_map_lookup_elem(rxcnt_map_fd, &key, values) == 0); for (i = 0; i < nr_cpus; i++) sum += (values[i] - prev[i]); if (sum) @@ -69,7 +96,8 @@ static void usage(const char *prog) "usage: %s [OPTS] IFINDEX_IN IFINDEX_OUT\n\n" "OPTS:\n" " -S use skb-mode\n" - " -N enforce native mode\n", + " -N enforce native mode\n" + " -F force loading prog\n", prog); } @@ -77,9 +105,18 @@ static void usage(const char *prog) int main(int argc, char **argv) { struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; - const char *optstr = "SN"; + struct bpf_prog_load_attr prog_load_attr = { + .prog_type = BPF_PROG_TYPE_XDP, + }; + struct bpf_program *prog, *dummy_prog; + int prog_fd, tx_port_map_fd, opt; + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + const char *optstr = "FSN"; + struct bpf_object *obj; char filename[256]; - int ret, opt, key = 0; + int dummy_prog_fd; + int ret, key = 0; while ((opt = getopt(argc, argv, optstr)) != -1) { switch (opt) { @@ -89,6 +126,9 @@ int main(int argc, char **argv) case 'N': xdp_flags |= XDP_FLAGS_DRV_MODE; break; + case 'F': + xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST; + break; default: usage(basename(argv[0])); return 1; @@ -110,34 +150,65 @@ int main(int argc, char **argv) printf("input: %d output: %d\n", ifindex_in, ifindex_out); snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + prog_load_attr.file = filename; + + if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) + return 1; - if (load_bpf_file(filename)) { - printf("%s", bpf_log_buf); + prog = bpf_program__next(NULL, obj); + dummy_prog = bpf_program__next(prog, obj); + if (!prog || !dummy_prog) { + printf("finding a prog in obj file failed\n"); + return 1; + } + /* bpf_prog_load_xattr gives us the pointer to first prog's fd, + * so we're missing only the fd for dummy prog + */ + dummy_prog_fd = bpf_program__fd(dummy_prog); + if (prog_fd < 0 || dummy_prog_fd < 0) { + printf("bpf_prog_load_xattr: %s\n", strerror(errno)); return 1; } - if (!prog_fd[0]) { - printf("load_bpf_file: %s\n", strerror(errno)); + tx_port_map_fd = bpf_object__find_map_fd_by_name(obj, "tx_port"); + rxcnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rxcnt"); + if (tx_port_map_fd < 0 || rxcnt_map_fd < 0) { + printf("bpf_object__find_map_fd_by_name failed\n"); return 1; } - if (bpf_set_link_xdp_fd(ifindex_in, prog_fd[0], xdp_flags) < 0) { + if (bpf_set_link_xdp_fd(ifindex_in, prog_fd, xdp_flags) < 0) { printf("ERROR: link set xdp fd failed on %d\n", ifindex_in); return 1; } + ret = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + if (ret) { + printf("can't get prog info - %s\n", strerror(errno)); + return ret; + } + prog_id = info.id; + /* Loading dummy XDP prog on out-device */ - if (bpf_set_link_xdp_fd(ifindex_out, prog_fd[1], + if (bpf_set_link_xdp_fd(ifindex_out, dummy_prog_fd, (xdp_flags | XDP_FLAGS_UPDATE_IF_NOEXIST)) < 0) { printf("WARN: link set xdp fd failed on %d\n", ifindex_out); ifindex_out_xdp_dummy_attached = false; } + memset(&info, 0, sizeof(info)); + ret = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + if (ret) { + printf("can't get prog info - %s\n", strerror(errno)); + return ret; + } + dummy_prog_id = info.id; + signal(SIGINT, int_exit); signal(SIGTERM, int_exit); /* bpf redirect port */ - ret = bpf_map_update_elem(map_fd[0], &key, &ifindex_out, 0); + ret = bpf_map_update_elem(tx_port_map_fd, &key, &ifindex_out, 0); if (ret) { perror("bpf_update_elem"); goto out; diff --git a/samples/bpf/xdp_router_ipv4_user.c b/samples/bpf/xdp_router_ipv4_user.c index b2b4dfa776c8..79fe7bc26ab4 100644 --- a/samples/bpf/xdp_router_ipv4_user.c +++ b/samples/bpf/xdp_router_ipv4_user.c @@ -15,7 +15,6 @@ #include <string.h> #include <sys/socket.h> #include <unistd.h> -#include "bpf_load.h" #include <bpf/bpf.h> #include <arpa/inet.h> #include <fcntl.h> @@ -25,32 +24,52 @@ #include <sys/ioctl.h> #include <sys/syscall.h> #include "bpf_util.h" +#include "bpf/libbpf.h" +#include <sys/resource.h> +#include <libgen.h> -int sock, sock_arp, flags = 0; +int sock, sock_arp, flags = XDP_FLAGS_UPDATE_IF_NOEXIST; static int total_ifindex; -int *ifindex_list; +static int *ifindex_list; +static __u32 *prog_id_list; char buf[8192]; +static int lpm_map_fd; +static int rxcnt_map_fd; +static int arp_table_map_fd; +static int exact_match_map_fd; +static int tx_port_map_fd; static int get_route_table(int rtm_family); static void int_exit(int sig) { + __u32 prog_id = 0; int i = 0; - for (i = 0; i < total_ifindex; i++) - bpf_set_link_xdp_fd(ifindex_list[i], -1, flags); + for (i = 0; i < total_ifindex; i++) { + if (bpf_get_link_xdp_id(ifindex_list[i], &prog_id, flags)) { + printf("bpf_get_link_xdp_id on iface %d failed\n", + ifindex_list[i]); + exit(1); + } + if (prog_id_list[i] == prog_id) + bpf_set_link_xdp_fd(ifindex_list[i], -1, flags); + else if (!prog_id) + printf("couldn't find a prog id on iface %d\n", + ifindex_list[i]); + else + printf("program on iface %d changed, not removing\n", + ifindex_list[i]); + prog_id = 0; + } exit(0); } static void close_and_exit(int sig) { - int i = 0; - close(sock); close(sock_arp); - for (i = 0; i < total_ifindex; i++) - bpf_set_link_xdp_fd(ifindex_list[i], -1, flags); - exit(0); + int_exit(0); } /* Get the mac address of the interface given interface name */ @@ -179,14 +198,10 @@ static void read_route(struct nlmsghdr *nh, int nll) route.iface_name = alloca(sizeof(char *) * IFNAMSIZ); route.iface_name = if_indextoname(route.iface, route.iface_name); route.mac = getmac(route.iface_name); - if (route.mac == -1) { - int i = 0; - - for (i = 0; i < total_ifindex; i++) - bpf_set_link_xdp_fd(ifindex_list[i], -1, flags); - exit(0); - } - assert(bpf_map_update_elem(map_fd[4], &route.iface, &route.iface, 0) == 0); + if (route.mac == -1) + int_exit(0); + assert(bpf_map_update_elem(tx_port_map_fd, + &route.iface, &route.iface, 0) == 0); if (rtm_family == AF_INET) { struct trie_value { __u8 prefix[4]; @@ -207,11 +222,16 @@ static void read_route(struct nlmsghdr *nh, int nll) direct_entry.arp.dst = 0; if (route.dst_len == 32) { if (nh->nlmsg_type == RTM_DELROUTE) { - assert(bpf_map_delete_elem(map_fd[3], &route.dst) == 0); + assert(bpf_map_delete_elem(exact_match_map_fd, + &route.dst) == 0); } else { - if (bpf_map_lookup_elem(map_fd[2], &route.dst, &direct_entry.arp.mac) == 0) + if (bpf_map_lookup_elem(arp_table_map_fd, + &route.dst, + &direct_entry.arp.mac) == 0) direct_entry.arp.dst = route.dst; - assert(bpf_map_update_elem(map_fd[3], &route.dst, &direct_entry, 0) == 0); + assert(bpf_map_update_elem(exact_match_map_fd, + &route.dst, + &direct_entry, 0) == 0); } } for (i = 0; i < 4; i++) @@ -225,7 +245,7 @@ static void read_route(struct nlmsghdr *nh, int nll) route.gw, route.dst_len, route.metric, route.iface_name); - if (bpf_map_lookup_elem(map_fd[0], prefix_key, + if (bpf_map_lookup_elem(lpm_map_fd, prefix_key, prefix_value) < 0) { for (i = 0; i < 4; i++) prefix_value->prefix[i] = prefix_key->data[i]; @@ -234,7 +254,7 @@ static void read_route(struct nlmsghdr *nh, int nll) prefix_value->gw = route.gw; prefix_value->metric = route.metric; - assert(bpf_map_update_elem(map_fd[0], + assert(bpf_map_update_elem(lpm_map_fd, prefix_key, prefix_value, 0 ) == 0); @@ -247,7 +267,7 @@ static void read_route(struct nlmsghdr *nh, int nll) prefix_key->data[2], prefix_key->data[3], prefix_key->prefixlen); - assert(bpf_map_delete_elem(map_fd[0], + assert(bpf_map_delete_elem(lpm_map_fd, prefix_key ) == 0); /* Rereading the route table to check if @@ -275,8 +295,7 @@ static void read_route(struct nlmsghdr *nh, int nll) prefix_value->ifindex = route.iface; prefix_value->gw = route.gw; prefix_value->metric = route.metric; - assert(bpf_map_update_elem( - map_fd[0], + assert(bpf_map_update_elem(lpm_map_fd, prefix_key, prefix_value, 0) == 0); @@ -401,7 +420,8 @@ static void read_arp(struct nlmsghdr *nh, int nll) arp_entry.mac = atol(mac); printf("%x\t\t%llx\n", arp_entry.dst, arp_entry.mac); if (ndm_family == AF_INET) { - if (bpf_map_lookup_elem(map_fd[3], &arp_entry.dst, + if (bpf_map_lookup_elem(exact_match_map_fd, + &arp_entry.dst, &direct_entry) == 0) { if (nh->nlmsg_type == RTM_DELNEIGH) { direct_entry.arp.dst = 0; @@ -410,16 +430,17 @@ static void read_arp(struct nlmsghdr *nh, int nll) direct_entry.arp.dst = arp_entry.dst; direct_entry.arp.mac = arp_entry.mac; } - assert(bpf_map_update_elem(map_fd[3], + assert(bpf_map_update_elem(exact_match_map_fd, &arp_entry.dst, &direct_entry, 0 ) == 0); memset(&direct_entry, 0, sizeof(direct_entry)); } if (nh->nlmsg_type == RTM_DELNEIGH) { - assert(bpf_map_delete_elem(map_fd[2], &arp_entry.dst) == 0); + assert(bpf_map_delete_elem(arp_table_map_fd, + &arp_entry.dst) == 0); } else if (nh->nlmsg_type == RTM_NEWNEIGH) { - assert(bpf_map_update_elem(map_fd[2], + assert(bpf_map_update_elem(arp_table_map_fd, &arp_entry.dst, &arp_entry.mac, 0 ) == 0); @@ -553,7 +574,8 @@ static int monitor_route(void) for (key = 0; key < nr_keys; key++) { __u64 sum = 0; - assert(bpf_map_lookup_elem(map_fd[1], &key, values) == 0); + assert(bpf_map_lookup_elem(rxcnt_map_fd, + &key, values) == 0); for (i = 0; i < nr_cpus; i++) sum += (values[i] - prev[key][i]); if (sum) @@ -594,36 +616,87 @@ cleanup: return ret; } +static void usage(const char *prog) +{ + fprintf(stderr, + "%s: %s [OPTS] interface name list\n\n" + "OPTS:\n" + " -S use skb-mode\n" + " -F force loading prog\n", + __func__, prog); +} + int main(int ac, char **argv) { + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + struct bpf_prog_load_attr prog_load_attr = { + .prog_type = BPF_PROG_TYPE_XDP, + }; + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); + const char *optstr = "SF"; + struct bpf_object *obj; char filename[256]; char **ifname_list; - int i = 1; + int prog_fd, opt; + int err, i = 1; snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); - if (ac < 2) { - printf("usage: %s [-S] Interface name list\n", argv[0]); - return 1; + prog_load_attr.file = filename; + + total_ifindex = ac - 1; + ifname_list = (argv + 1); + + while ((opt = getopt(ac, argv, optstr)) != -1) { + switch (opt) { + case 'S': + flags |= XDP_FLAGS_SKB_MODE; + total_ifindex--; + ifname_list++; + break; + case 'F': + flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST; + total_ifindex--; + ifname_list++; + break; + default: + usage(basename(argv[0])); + return 1; + } } - if (!strcmp(argv[1], "-S")) { - flags = XDP_FLAGS_SKB_MODE; - total_ifindex = ac - 2; - ifname_list = (argv + 2); - } else { - flags = 0; - total_ifindex = ac - 1; - ifname_list = (argv + 1); + + if (optind == ac) { + usage(basename(argv[0])); + return 1; } - if (load_bpf_file(filename)) { - printf("%s", bpf_log_buf); + + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + perror("setrlimit(RLIMIT_MEMLOCK)"); return 1; } + + if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) + return 1; + printf("\n**************loading bpf file*********************\n\n\n"); - if (!prog_fd[0]) { - printf("load_bpf_file: %s\n", strerror(errno)); + if (!prog_fd) { + printf("bpf_prog_load_xattr: %s\n", strerror(errno)); return 1; } - ifindex_list = (int *)malloc(total_ifindex * sizeof(int *)); + + lpm_map_fd = bpf_object__find_map_fd_by_name(obj, "lpm_map"); + rxcnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rxcnt"); + arp_table_map_fd = bpf_object__find_map_fd_by_name(obj, "arp_table"); + exact_match_map_fd = bpf_object__find_map_fd_by_name(obj, + "exact_match"); + tx_port_map_fd = bpf_object__find_map_fd_by_name(obj, "tx_port"); + if (lpm_map_fd < 0 || rxcnt_map_fd < 0 || arp_table_map_fd < 0 || + exact_match_map_fd < 0 || tx_port_map_fd < 0) { + printf("bpf_object__find_map_fd_by_name failed\n"); + return 1; + } + + ifindex_list = (int *)calloc(total_ifindex, sizeof(int *)); for (i = 0; i < total_ifindex; i++) { ifindex_list[i] = if_nametoindex(ifname_list[i]); if (!ifindex_list[i]) { @@ -632,8 +705,9 @@ int main(int ac, char **argv) return 1; } } + prog_id_list = (__u32 *)calloc(total_ifindex, sizeof(__u32 *)); for (i = 0; i < total_ifindex; i++) { - if (bpf_set_link_xdp_fd(ifindex_list[i], prog_fd[0], flags) < 0) { + if (bpf_set_link_xdp_fd(ifindex_list[i], prog_fd, flags) < 0) { printf("link set xdp fd failed\n"); int recovery_index = i; @@ -642,6 +716,13 @@ int main(int ac, char **argv) return 1; } + err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + if (err) { + printf("can't get prog info - %s\n", strerror(errno)); + return err; + } + prog_id_list[i] = info.id; + memset(&info, 0, sizeof(info)); printf("Attached to %d\n", ifindex_list[i]); } signal(SIGINT, int_exit); diff --git a/samples/bpf/xdp_rxq_info_user.c b/samples/bpf/xdp_rxq_info_user.c index ef26f882f92f..1210f3b170f0 100644 --- a/samples/bpf/xdp_rxq_info_user.c +++ b/samples/bpf/xdp_rxq_info_user.c @@ -29,8 +29,9 @@ static const char *__doc__ = " XDP RX-queue info extract example\n\n" static int ifindex = -1; static char ifname_buf[IF_NAMESIZE]; static char *ifname; +static __u32 prog_id; -static __u32 xdp_flags; +static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; static struct bpf_map *stats_global_map; static struct bpf_map *rx_queue_index_map; @@ -52,16 +53,30 @@ static const struct option long_options[] = { {"action", required_argument, NULL, 'a' }, {"readmem", no_argument, NULL, 'r' }, {"swapmac", no_argument, NULL, 'm' }, + {"force", no_argument, NULL, 'F' }, {0, 0, NULL, 0 } }; static void int_exit(int sig) { - fprintf(stderr, - "Interrupted: Removing XDP program on ifindex:%d device:%s\n", - ifindex, ifname); - if (ifindex > -1) - bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); + __u32 curr_prog_id = 0; + + if (ifindex > -1) { + if (bpf_get_link_xdp_id(ifindex, &curr_prog_id, xdp_flags)) { + printf("bpf_get_link_xdp_id failed\n"); + exit(EXIT_FAIL); + } + if (prog_id == curr_prog_id) { + fprintf(stderr, + "Interrupted: Removing XDP program on ifindex:%d device:%s\n", + ifindex, ifname); + bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); + } else if (!curr_prog_id) { + printf("couldn't find a prog id on a given iface\n"); + } else { + printf("program on interface changed, not removing\n"); + } + } exit(EXIT_OK); } @@ -446,6 +461,8 @@ int main(int argc, char **argv) struct bpf_prog_load_attr prog_load_attr = { .prog_type = BPF_PROG_TYPE_XDP, }; + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); int prog_fd, map_fd, opt, err; bool use_separators = true; struct config cfg = { 0 }; @@ -487,7 +504,7 @@ int main(int argc, char **argv) } /* Parse commands line args */ - while ((opt = getopt_long(argc, argv, "hSd:", + while ((opt = getopt_long(argc, argv, "FhSrmzd:s:a:", long_options, &longindex)) != -1) { switch (opt) { case 'd': @@ -524,6 +541,9 @@ int main(int argc, char **argv) case 'm': cfg_options |= SWAP_MAC; break; + case 'F': + xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST; + break; case 'h': error: default: @@ -576,6 +596,13 @@ int main(int argc, char **argv) return EXIT_FAIL_XDP; } + err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + if (err) { + printf("can't get prog info - %s\n", strerror(errno)); + return err; + } + prog_id = info.id; + stats_poll(interval, action, cfg_options); return EXIT_OK; } diff --git a/samples/bpf/xdp_sample_pkts_user.c b/samples/bpf/xdp_sample_pkts_user.c index 8dd87c1eb560..dc66345a929a 100644 --- a/samples/bpf/xdp_sample_pkts_user.c +++ b/samples/bpf/xdp_sample_pkts_user.c @@ -12,6 +12,9 @@ #include <signal.h> #include <libbpf.h> #include <bpf/bpf.h> +#include <sys/resource.h> +#include <libgen.h> +#include <linux/if_link.h> #include "perf-sys.h" #include "trace_helpers.h" @@ -20,25 +23,50 @@ static int pmu_fds[MAX_CPUS], if_idx; static struct perf_event_mmap_page *headers[MAX_CPUS]; static char *if_name; +static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; +static __u32 prog_id; static int do_attach(int idx, int fd, const char *name) { + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); int err; - err = bpf_set_link_xdp_fd(idx, fd, 0); - if (err < 0) + err = bpf_set_link_xdp_fd(idx, fd, xdp_flags); + if (err < 0) { printf("ERROR: failed to attach program to %s\n", name); + return err; + } + + err = bpf_obj_get_info_by_fd(fd, &info, &info_len); + if (err) { + printf("can't get prog info - %s\n", strerror(errno)); + return err; + } + prog_id = info.id; return err; } static int do_detach(int idx, const char *name) { - int err; + __u32 curr_prog_id = 0; + int err = 0; - err = bpf_set_link_xdp_fd(idx, -1, 0); - if (err < 0) - printf("ERROR: failed to detach program from %s\n", name); + err = bpf_get_link_xdp_id(idx, &curr_prog_id, 0); + if (err) { + printf("bpf_get_link_xdp_id failed\n"); + return err; + } + if (prog_id == curr_prog_id) { + err = bpf_set_link_xdp_fd(idx, -1, 0); + if (err < 0) + printf("ERROR: failed to detach prog from %s\n", name); + } else if (!curr_prog_id) { + printf("couldn't find a prog id on a %s\n", name); + } else { + printf("program on interface changed, not removing\n"); + } return err; } @@ -97,20 +125,47 @@ static void sig_handler(int signo) exit(0); } +static void usage(const char *prog) +{ + fprintf(stderr, + "%s: %s [OPTS] <ifname|ifindex>\n\n" + "OPTS:\n" + " -F force loading prog\n", + __func__, prog); +} + int main(int argc, char **argv) { + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_prog_load_attr prog_load_attr = { .prog_type = BPF_PROG_TYPE_XDP, }; + const char *optstr = "F"; + int prog_fd, map_fd, opt; struct bpf_object *obj; struct bpf_map *map; - int prog_fd, map_fd; char filename[256]; int ret, err, i; int numcpus; - if (argc < 2) { - printf("Usage: %s <ifname>\n", argv[0]); + while ((opt = getopt(argc, argv, optstr)) != -1) { + switch (opt) { + case 'F': + xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST; + break; + default: + usage(basename(argv[0])); + return 1; + } + } + + if (optind == argc) { + usage(basename(argv[0])); + return 1; + } + + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + perror("setrlimit(RLIMIT_MEMLOCK)"); return 1; } @@ -136,16 +191,16 @@ int main(int argc, char **argv) } map_fd = bpf_map__fd(map); - if_idx = if_nametoindex(argv[1]); + if_idx = if_nametoindex(argv[optind]); if (!if_idx) - if_idx = strtoul(argv[1], NULL, 0); + if_idx = strtoul(argv[optind], NULL, 0); if (!if_idx) { fprintf(stderr, "Invalid ifname\n"); return 1; } - if_name = argv[1]; - err = do_attach(if_idx, prog_fd, argv[1]); + if_name = argv[optind]; + err = do_attach(if_idx, prog_fd, if_name); if (err) return err; diff --git a/samples/bpf/xdp_tx_iptunnel_user.c b/samples/bpf/xdp_tx_iptunnel_user.c index a4ccc33adac0..4a1511eb7812 100644 --- a/samples/bpf/xdp_tx_iptunnel_user.c +++ b/samples/bpf/xdp_tx_iptunnel_user.c @@ -17,7 +17,7 @@ #include <netinet/ether.h> #include <unistd.h> #include <time.h> -#include "bpf_load.h" +#include "bpf/libbpf.h" #include <bpf/bpf.h> #include "bpf_util.h" #include "xdp_tx_iptunnel_common.h" @@ -25,12 +25,26 @@ #define STATS_INTERVAL_S 2U static int ifindex = -1; -static __u32 xdp_flags = 0; +static __u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; +static int rxcnt_map_fd; +static __u32 prog_id; static void int_exit(int sig) { - if (ifindex > -1) - bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); + __u32 curr_prog_id = 0; + + if (ifindex > -1) { + if (bpf_get_link_xdp_id(ifindex, &curr_prog_id, xdp_flags)) { + printf("bpf_get_link_xdp_id failed\n"); + exit(1); + } + if (prog_id == curr_prog_id) + bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); + else if (!curr_prog_id) + printf("couldn't find a prog id on a given iface\n"); + else + printf("program on interface changed, not removing\n"); + } exit(0); } @@ -53,7 +67,8 @@ static void poll_stats(unsigned int kill_after_s) for (proto = 0; proto < nr_protos; proto++) { __u64 sum = 0; - assert(bpf_map_lookup_elem(map_fd[0], &proto, values) == 0); + assert(bpf_map_lookup_elem(rxcnt_map_fd, &proto, + values) == 0); for (i = 0; i < nr_cpus; i++) sum += (values[i] - prev[proto][i]); @@ -81,6 +96,7 @@ static void usage(const char *cmd) printf(" -P <IP-Protocol> Default is TCP\n"); printf(" -S use skb-mode\n"); printf(" -N enforce native mode\n"); + printf(" -F Force loading the XDP prog\n"); printf(" -h Display this help\n"); } @@ -138,16 +154,22 @@ static int parse_ports(const char *port_str, int *min_port, int *max_port) int main(int argc, char **argv) { + struct bpf_prog_load_attr prog_load_attr = { + .prog_type = BPF_PROG_TYPE_XDP, + }; + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + int min_port = 0, max_port = 0, vip2tnl_map_fd; + const char *optstr = "i:a:p:s:d:m:T:P:FSNh"; unsigned char opt_flags[256] = {}; + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); unsigned int kill_after_s = 0; - const char *optstr = "i:a:p:s:d:m:T:P:SNh"; - int min_port = 0, max_port = 0; struct iptnl_info tnl = {}; - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + struct bpf_object *obj; struct vip vip = {}; char filename[256]; - int opt; - int i; + int opt, prog_fd; + int i, err; tnl.family = AF_UNSPEC; vip.protocol = IPPROTO_TCP; @@ -211,6 +233,9 @@ int main(int argc, char **argv) case 'N': xdp_flags |= XDP_FLAGS_DRV_MODE; break; + case 'F': + xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST; + break; default: usage(argv[0]); return 1; @@ -232,33 +257,47 @@ int main(int argc, char **argv) } snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + prog_load_attr.file = filename; - if (load_bpf_file(filename)) { - printf("%s", bpf_log_buf); + if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) return 1; - } - if (!prog_fd[0]) { + if (!prog_fd) { printf("load_bpf_file: %s\n", strerror(errno)); return 1; } + rxcnt_map_fd = bpf_object__find_map_fd_by_name(obj, "rxcnt"); + vip2tnl_map_fd = bpf_object__find_map_fd_by_name(obj, "vip2tnl"); + if (vip2tnl_map_fd < 0 || rxcnt_map_fd < 0) { + printf("bpf_object__find_map_fd_by_name failed\n"); + return 1; + } + signal(SIGINT, int_exit); signal(SIGTERM, int_exit); while (min_port <= max_port) { vip.dport = htons(min_port++); - if (bpf_map_update_elem(map_fd[1], &vip, &tnl, BPF_NOEXIST)) { + if (bpf_map_update_elem(vip2tnl_map_fd, &vip, &tnl, + BPF_NOEXIST)) { perror("bpf_map_update_elem(&vip2tnl)"); return 1; } } - if (bpf_set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) { + if (bpf_set_link_xdp_fd(ifindex, prog_fd, xdp_flags) < 0) { printf("link set xdp fd failed\n"); return 1; } + err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + if (err) { + printf("can't get prog info - %s\n", strerror(errno)); + return err; + } + prog_id = info.id; + poll_stats(kill_after_s); bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c index 57ecadc58403..f73055e0191f 100644 --- a/samples/bpf/xdpsock_user.c +++ b/samples/bpf/xdpsock_user.c @@ -68,7 +68,7 @@ enum benchmark_type { }; static enum benchmark_type opt_bench = BENCH_RXDROP; -static u32 opt_xdp_flags; +static u32 opt_xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST; static const char *opt_if = ""; static int opt_ifindex; static int opt_queue; @@ -76,6 +76,7 @@ static int opt_poll; static int opt_shared_packet_buffer; static int opt_interval = 1; static u32 opt_xdp_bind_flags; +static __u32 prog_id; struct xdp_umem_uqueue { u32 cached_prod; @@ -631,9 +632,20 @@ static void *poller(void *arg) static void int_exit(int sig) { + __u32 curr_prog_id = 0; + (void)sig; dump_stats(); - bpf_set_link_xdp_fd(opt_ifindex, -1, opt_xdp_flags); + if (bpf_get_link_xdp_id(opt_ifindex, &curr_prog_id, opt_xdp_flags)) { + printf("bpf_get_link_xdp_id failed\n"); + exit(EXIT_FAILURE); + } + if (prog_id == curr_prog_id) + bpf_set_link_xdp_fd(opt_ifindex, -1, opt_xdp_flags); + else if (!curr_prog_id) + printf("couldn't find a prog id on a given interface\n"); + else + printf("program on interface changed, not removing\n"); exit(EXIT_SUCCESS); } @@ -682,7 +694,7 @@ static void parse_command_line(int argc, char **argv) opterr = 0; for (;;) { - c = getopt_long(argc, argv, "rtli:q:psSNn:cz", long_options, + c = getopt_long(argc, argv, "Frtli:q:psSNn:cz", long_options, &option_index); if (c == -1) break; @@ -725,6 +737,9 @@ static void parse_command_line(int argc, char **argv) case 'c': opt_xdp_bind_flags |= XDP_COPY; break; + case 'F': + opt_xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST; + break; default: usage(basename(argv[0])); } @@ -904,6 +919,8 @@ int main(int argc, char **argv) .prog_type = BPF_PROG_TYPE_XDP, }; int prog_fd, qidconf_map, xsks_map; + struct bpf_prog_info info = {}; + __u32 info_len = sizeof(info); struct bpf_object *obj; char xdp_filename[256]; struct bpf_map *map; @@ -950,6 +967,13 @@ int main(int argc, char **argv) exit(EXIT_FAILURE); } + ret = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + if (ret) { + printf("can't get prog info - %s\n", strerror(errno)); + return 1; + } + prog_id = info.id; + ret = bpf_map_update_elem(qidconf_map, &key, &opt_queue, 0); if (ret) { fprintf(stderr, "ERROR: bpf_map_update_elem qidconf\n"); diff --git a/samples/mei/mei-amt-version.c b/samples/mei/mei-amt-version.c index 33e67bd1dc34..32234481ad7d 100644 --- a/samples/mei/mei-amt-version.c +++ b/samples/mei/mei-amt-version.c @@ -117,7 +117,7 @@ static bool mei_init(struct mei *me, const uuid_le *guid, me->verbose = verbose; - me->fd = open("/dev/mei", O_RDWR); + me->fd = open("/dev/mei0", O_RDWR); if (me->fd == -1) { mei_err(me, "Cannot establish a handle to the Intel MEI driver\n"); goto err; diff --git a/security/apparmor/domain.c b/security/apparmor/domain.c index 08c88de0ffda..11975ec8d566 100644 --- a/security/apparmor/domain.c +++ b/security/apparmor/domain.c @@ -1444,7 +1444,10 @@ check: new = aa_label_merge(label, target, GFP_KERNEL); if (IS_ERR_OR_NULL(new)) { info = "failed to build target label"; - error = PTR_ERR(new); + if (!new) + error = -ENOMEM; + else + error = PTR_ERR(new); new = NULL; perms.allow = 0; goto audit; diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c index 2c010874329f..8db1731d046a 100644 --- a/security/apparmor/lsm.c +++ b/security/apparmor/lsm.c @@ -1599,12 +1599,14 @@ static unsigned int apparmor_ipv4_postroute(void *priv, return apparmor_ip_postroute(priv, skb, state); } +#if IS_ENABLED(CONFIG_IPV6) static unsigned int apparmor_ipv6_postroute(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return apparmor_ip_postroute(priv, skb, state); } +#endif static const struct nf_hook_ops apparmor_nf_ops[] = { { diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c index 40013b26f671..6c0b30391ba9 100644 --- a/sound/core/pcm_lib.c +++ b/sound/core/pcm_lib.c @@ -2177,16 +2177,11 @@ snd_pcm_sframes_t __snd_pcm_lib_xfer(struct snd_pcm_substream *substream, snd_pcm_update_hw_ptr(substream); if (!is_playback && - runtime->status->state == SNDRV_PCM_STATE_PREPARED) { - if (size >= runtime->start_threshold) { - err = snd_pcm_start(substream); - if (err < 0) - goto _end_unlock; - } else { - /* nothing to do */ - err = 0; + runtime->status->state == SNDRV_PCM_STATE_PREPARED && + size >= runtime->start_threshold) { + err = snd_pcm_start(substream); + if (err < 0) goto _end_unlock; - } } avail = snd_pcm_avail(substream); diff --git a/sound/pci/hda/hda_bind.c b/sound/pci/hda/hda_bind.c index 9174f1b3a987..1ec706ced75c 100644 --- a/sound/pci/hda/hda_bind.c +++ b/sound/pci/hda/hda_bind.c @@ -115,7 +115,8 @@ static int hda_codec_driver_probe(struct device *dev) err = snd_hda_codec_build_controls(codec); if (err < 0) goto error_module; - if (codec->card->registered) { + /* only register after the bus probe finished; otherwise it's racy */ + if (!codec->bus->bus_probing && codec->card->registered) { err = snd_card_register(codec->card); if (err < 0) goto error_module; diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index e784130ea4e0..e5c49003e75f 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2185,6 +2185,7 @@ static int azx_probe_continue(struct azx *chip) int dev = chip->dev_index; int err; + to_hda_bus(bus)->bus_probing = 1; hda->probe_continued = 1; /* bind with i915 if needed */ @@ -2269,6 +2270,7 @@ out_free: if (err < 0) hda->init_failed = 1; complete_all(&hda->probe_wait); + to_hda_bus(bus)->bus_probing = 0; return err; } diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c index e5bdbc245682..29882bda7632 100644 --- a/sound/pci/hda/patch_ca0132.c +++ b/sound/pci/hda/patch_ca0132.c @@ -8451,8 +8451,10 @@ static void ca0132_free(struct hda_codec *codec) ca0132_exit_chip(codec); snd_hda_power_down(codec); - if (IS_ENABLED(CONFIG_PCI) && spec->mem_base) +#ifdef CONFIG_PCI + if (spec->mem_base) pci_iounmap(codec->bus->pci, spec->mem_base); +#endif kfree(spec->spec_init_verbs); kfree(codec->spec); } diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c index 152f54137082..a4ee7656d9ee 100644 --- a/sound/pci/hda/patch_conexant.c +++ b/sound/pci/hda/patch_conexant.c @@ -924,6 +924,7 @@ static const struct snd_pci_quirk cxt5066_fixups[] = { SND_PCI_QUIRK(0x103c, 0x807C, "HP EliteBook 820 G3", CXT_FIXUP_HP_DOCK), SND_PCI_QUIRK(0x103c, 0x80FD, "HP ProBook 640 G2", CXT_FIXUP_HP_DOCK), SND_PCI_QUIRK(0x103c, 0x828c, "HP EliteBook 840 G4", CXT_FIXUP_HP_DOCK), + SND_PCI_QUIRK(0x103c, 0x83b2, "HP EliteBook 840 G5", CXT_FIXUP_HP_DOCK), SND_PCI_QUIRK(0x103c, 0x83b3, "HP EliteBook 830 G5", CXT_FIXUP_HP_DOCK), SND_PCI_QUIRK(0x103c, 0x83d3, "HP ProBook 640 G4", CXT_FIXUP_HP_DOCK), SND_PCI_QUIRK(0x103c, 0x8174, "HP Spectre x360", CXT_FIXUP_HP_SPECTRE), diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index b4f472157ebd..6df758adff84 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -117,6 +117,7 @@ struct alc_spec { int codec_variant; /* flag for other variants */ unsigned int has_alc5505_dsp:1; unsigned int no_depop_delay:1; + unsigned int done_hp_init:1; /* for PLL fix */ hda_nid_t pll_nid; @@ -514,6 +515,15 @@ static void alc_auto_init_amp(struct hda_codec *codec, int type) } } +/* get a primary headphone pin if available */ +static hda_nid_t alc_get_hp_pin(struct alc_spec *spec) +{ + if (spec->gen.autocfg.hp_pins[0]) + return spec->gen.autocfg.hp_pins[0]; + if (spec->gen.autocfg.line_out_type == AC_JACK_HP_OUT) + return spec->gen.autocfg.line_out_pins[0]; + return 0; +} /* * Realtek SSID verification @@ -724,9 +734,7 @@ do_sku: * 15 : 1 --> enable the function "Mute internal speaker * when the external headphone out jack is plugged" */ - if (!spec->gen.autocfg.hp_pins[0] && - !(spec->gen.autocfg.line_out_pins[0] && - spec->gen.autocfg.line_out_type == AUTO_PIN_HP_OUT)) { + if (!alc_get_hp_pin(spec)) { hda_nid_t nid; tmp = (ass >> 11) & 0x3; /* HP to chassis */ nid = ports[tmp]; @@ -2958,7 +2966,7 @@ static void alc282_restore_default_value(struct hda_codec *codec) static void alc282_init(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + hda_nid_t hp_pin = alc_get_hp_pin(spec); bool hp_pin_sense; int coef78; @@ -2995,7 +3003,7 @@ static void alc282_init(struct hda_codec *codec) static void alc282_shutup(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + hda_nid_t hp_pin = alc_get_hp_pin(spec); bool hp_pin_sense; int coef78; @@ -3073,14 +3081,9 @@ static void alc283_restore_default_value(struct hda_codec *codec) static void alc283_init(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + hda_nid_t hp_pin = alc_get_hp_pin(spec); bool hp_pin_sense; - if (!spec->gen.autocfg.hp_outs) { - if (spec->gen.autocfg.line_out_type == AC_JACK_HP_OUT) - hp_pin = spec->gen.autocfg.line_out_pins[0]; - } - alc283_restore_default_value(codec); if (!hp_pin) @@ -3114,14 +3117,9 @@ static void alc283_init(struct hda_codec *codec) static void alc283_shutup(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + hda_nid_t hp_pin = alc_get_hp_pin(spec); bool hp_pin_sense; - if (!spec->gen.autocfg.hp_outs) { - if (spec->gen.autocfg.line_out_type == AC_JACK_HP_OUT) - hp_pin = spec->gen.autocfg.line_out_pins[0]; - } - if (!hp_pin) { alc269_shutup(codec); return; @@ -3155,7 +3153,7 @@ static void alc283_shutup(struct hda_codec *codec) static void alc256_init(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + hda_nid_t hp_pin = alc_get_hp_pin(spec); bool hp_pin_sense; if (!hp_pin) @@ -3191,7 +3189,7 @@ static void alc256_init(struct hda_codec *codec) static void alc256_shutup(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + hda_nid_t hp_pin = alc_get_hp_pin(spec); bool hp_pin_sense; if (!hp_pin) { @@ -3227,7 +3225,7 @@ static void alc256_shutup(struct hda_codec *codec) static void alc225_init(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + hda_nid_t hp_pin = alc_get_hp_pin(spec); bool hp1_pin_sense, hp2_pin_sense; if (!hp_pin) @@ -3270,7 +3268,7 @@ static void alc225_init(struct hda_codec *codec) static void alc225_shutup(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + hda_nid_t hp_pin = alc_get_hp_pin(spec); bool hp1_pin_sense, hp2_pin_sense; if (!hp_pin) { @@ -3314,7 +3312,7 @@ static void alc225_shutup(struct hda_codec *codec) static void alc_default_init(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + hda_nid_t hp_pin = alc_get_hp_pin(spec); bool hp_pin_sense; if (!hp_pin) @@ -3343,7 +3341,7 @@ static void alc_default_init(struct hda_codec *codec) static void alc_default_shutup(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + hda_nid_t hp_pin = alc_get_hp_pin(spec); bool hp_pin_sense; if (!hp_pin) { @@ -3372,6 +3370,48 @@ static void alc_default_shutup(struct hda_codec *codec) snd_hda_shutup_pins(codec); } +static void alc294_hp_init(struct hda_codec *codec) +{ + struct alc_spec *spec = codec->spec; + hda_nid_t hp_pin = alc_get_hp_pin(spec); + int i, val; + + if (!hp_pin) + return; + + snd_hda_codec_write(codec, hp_pin, 0, + AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE); + + msleep(100); + + snd_hda_codec_write(codec, hp_pin, 0, + AC_VERB_SET_PIN_WIDGET_CONTROL, 0x0); + + alc_update_coef_idx(codec, 0x6f, 0x000f, 0);/* Set HP depop to manual mode */ + alc_update_coefex_idx(codec, 0x58, 0x00, 0x8000, 0x8000); /* HP depop procedure start */ + + /* Wait for depop procedure finish */ + val = alc_read_coefex_idx(codec, 0x58, 0x01); + for (i = 0; i < 20 && val & 0x0080; i++) { + msleep(50); + val = alc_read_coefex_idx(codec, 0x58, 0x01); + } + /* Set HP depop to auto mode */ + alc_update_coef_idx(codec, 0x6f, 0x000f, 0x000b); + msleep(50); +} + +static void alc294_init(struct hda_codec *codec) +{ + struct alc_spec *spec = codec->spec; + + if (!spec->done_hp_init) { + alc294_hp_init(codec); + spec->done_hp_init = true; + } + alc_default_init(codec); +} + static void alc5505_coef_set(struct hda_codec *codec, unsigned int index_reg, unsigned int val) { @@ -4737,7 +4777,7 @@ static void alc_update_headset_mode(struct hda_codec *codec) struct alc_spec *spec = codec->spec; hda_nid_t mux_pin = spec->gen.imux_pins[spec->gen.cur_mux[0]]; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; + hda_nid_t hp_pin = alc_get_hp_pin(spec); int new_headset_mode; @@ -5016,7 +5056,7 @@ static void alc_fixup_tpt470_dock(struct hda_codec *codec, static void alc_shutup_dell_xps13(struct hda_codec *codec) { struct alc_spec *spec = codec->spec; - int hp_pin = spec->gen.autocfg.hp_pins[0]; + int hp_pin = alc_get_hp_pin(spec); /* Prevent pop noises when headphones are plugged in */ snd_hda_codec_write(codec, hp_pin, 0, @@ -5109,7 +5149,7 @@ static void alc271_hp_gate_mic_jack(struct hda_codec *codec, if (action == HDA_FIXUP_ACT_PROBE) { int mic_pin = find_ext_mic_pin(codec); - int hp_pin = spec->gen.autocfg.hp_pins[0]; + int hp_pin = alc_get_hp_pin(spec); if (snd_BUG_ON(!mic_pin || !hp_pin)) return; @@ -5591,6 +5631,7 @@ enum { ALC294_FIXUP_ASUS_HEADSET_MIC, ALC294_FIXUP_ASUS_SPK, ALC225_FIXUP_HEADSET_JACK, + ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE, }; static const struct hda_fixup alc269_fixups[] = { @@ -6537,6 +6578,15 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc_fixup_headset_jack, }, + [ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE] = { + .type = HDA_FIXUP_PINS, + .v.pins = (const struct hda_pintbl[]) { + { 0x1a, 0x01a1913c }, /* use as headset mic, without its own jack detect */ + { } + }, + .chained = true, + .chain_id = ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -6715,6 +6765,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1458, 0xfa53, "Gigabyte BXBT-2807", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1462, 0xb120, "MSI Cubi MS-B120", ALC283_FIXUP_HEADSET_MIC), SND_PCI_QUIRK(0x1462, 0xb171, "Cubi N 8GL (MS-B171)", ALC283_FIXUP_HEADSET_MIC), + SND_PCI_QUIRK(0x1558, 0x1325, "System76 Darter Pro (darp5)", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x17aa, 0x1036, "Lenovo P520", ALC233_FIXUP_LENOVO_MULTI_CODECS), SND_PCI_QUIRK(0x17aa, 0x20f2, "Thinkpad SL410/510", ALC269_FIXUP_SKU_IGNORE), SND_PCI_QUIRK(0x17aa, 0x215e, "Thinkpad L512", ALC269_FIXUP_SKU_IGNORE), @@ -7373,37 +7424,6 @@ static void alc269_fill_coef(struct hda_codec *codec) alc_update_coef_idx(codec, 0x4, 0, 1<<11); } -static void alc294_hp_init(struct hda_codec *codec) -{ - struct alc_spec *spec = codec->spec; - hda_nid_t hp_pin = spec->gen.autocfg.hp_pins[0]; - int i, val; - - if (!hp_pin) - return; - - snd_hda_codec_write(codec, hp_pin, 0, - AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE); - - msleep(100); - - snd_hda_codec_write(codec, hp_pin, 0, - AC_VERB_SET_PIN_WIDGET_CONTROL, 0x0); - - alc_update_coef_idx(codec, 0x6f, 0x000f, 0);/* Set HP depop to manual mode */ - alc_update_coefex_idx(codec, 0x58, 0x00, 0x8000, 0x8000); /* HP depop procedure start */ - - /* Wait for depop procedure finish */ - val = alc_read_coefex_idx(codec, 0x58, 0x01); - for (i = 0; i < 20 && val & 0x0080; i++) { - msleep(50); - val = alc_read_coefex_idx(codec, 0x58, 0x01); - } - /* Set HP depop to auto mode */ - alc_update_coef_idx(codec, 0x6f, 0x000f, 0x000b); - msleep(50); -} - /* */ static int patch_alc269(struct hda_codec *codec) @@ -7529,7 +7549,7 @@ static int patch_alc269(struct hda_codec *codec) spec->codec_variant = ALC269_TYPE_ALC294; spec->gen.mixer_nid = 0; /* ALC2x4 does not have any loopback mixer path */ alc_update_coef_idx(codec, 0x6b, 0x0018, (1<<4) | (1<<3)); /* UAJ MIC Vref control by verb */ - alc294_hp_init(codec); + spec->init_hook = alc294_init; break; case 0x10ec0300: spec->codec_variant = ALC269_TYPE_ALC300; @@ -7541,7 +7561,7 @@ static int patch_alc269(struct hda_codec *codec) spec->codec_variant = ALC269_TYPE_ALC700; spec->gen.mixer_nid = 0; /* ALC700 does not have any loopback mixer path */ alc_update_coef_idx(codec, 0x4a, 1 << 15, 0); /* Combo jack auto trigger control */ - alc294_hp_init(codec); + spec->init_hook = alc294_init; break; } diff --git a/sound/soc/codecs/hdmi-codec.c b/sound/soc/codecs/hdmi-codec.c index d00734d31e04..e5b6769b9797 100644 --- a/sound/soc/codecs/hdmi-codec.c +++ b/sound/soc/codecs/hdmi-codec.c @@ -795,6 +795,8 @@ static int hdmi_codec_probe(struct platform_device *pdev) if (hcd->spdif) hcp->daidrv[i] = hdmi_spdif_dai; + dev_set_drvdata(dev, hcp); + ret = devm_snd_soc_register_component(dev, &hdmi_driver, hcp->daidrv, dai_count); if (ret) { @@ -802,8 +804,6 @@ static int hdmi_codec_probe(struct platform_device *pdev) __func__, ret); return ret; } - - dev_set_drvdata(dev, hcp); return 0; } diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c index 89c43b26c379..a9b91bcfcc09 100644 --- a/sound/soc/codecs/rt5682.c +++ b/sound/soc/codecs/rt5682.c @@ -1778,7 +1778,9 @@ static const struct snd_soc_dapm_route rt5682_dapm_routes[] = { {"ADC Stereo1 Filter", NULL, "ADC STO1 ASRC", is_using_asrc}, {"DAC Stereo1 Filter", NULL, "DAC STO1 ASRC", is_using_asrc}, {"ADC STO1 ASRC", NULL, "AD ASRC"}, + {"ADC STO1 ASRC", NULL, "DA ASRC"}, {"ADC STO1 ASRC", NULL, "CLKDET"}, + {"DAC STO1 ASRC", NULL, "AD ASRC"}, {"DAC STO1 ASRC", NULL, "DA ASRC"}, {"DAC STO1 ASRC", NULL, "CLKDET"}, diff --git a/sound/soc/samsung/i2s.c b/sound/soc/samsung/i2s.c index d6c62aa13041..ce00fe2f6aae 100644 --- a/sound/soc/samsung/i2s.c +++ b/sound/soc/samsung/i2s.c @@ -700,6 +700,7 @@ static int i2s_hw_params(struct snd_pcm_substream *substream, { struct i2s_dai *i2s = to_info(dai); u32 mod, mask = 0, val = 0; + struct clk *rclksrc; unsigned long flags; WARN_ON(!pm_runtime_active(dai->dev)); @@ -782,6 +783,10 @@ static int i2s_hw_params(struct snd_pcm_substream *substream, i2s->frmclk = params_rate(params); + rclksrc = i2s->clk_table[CLK_I2S_RCLK_SRC]; + if (rclksrc && !IS_ERR(rclksrc)) + i2s->rclk_srcrate = clk_get_rate(rclksrc); + return 0; } @@ -886,11 +891,6 @@ static int config_setup(struct i2s_dai *i2s) return 0; if (!(i2s->quirks & QUIRK_NO_MUXPSR)) { - struct clk *rclksrc = i2s->clk_table[CLK_I2S_RCLK_SRC]; - - if (rclksrc && !IS_ERR(rclksrc)) - i2s->rclk_srcrate = clk_get_rate(rclksrc); - psr = i2s->rclk_srcrate / i2s->frmclk / rfs; writel(((psr - 1) << 8) | PSR_PSREN, i2s->addr + I2SPSR); dev_dbg(&i2s->pdev->dev, diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c index 59e250cc2e9d..e819e965e1db 100644 --- a/sound/soc/sh/rcar/core.c +++ b/sound/soc/sh/rcar/core.c @@ -1526,14 +1526,14 @@ int rsnd_kctrl_new(struct rsnd_mod *mod, int ret; /* - * 1) Avoid duplicate register (ex. MIXer case) - * 2) re-register if card was rebinded + * 1) Avoid duplicate register for DVC with MIX case + * 2) Allow duplicate register for MIX + * 3) re-register if card was rebinded */ list_for_each_entry(kctrl, &card->controls, list) { struct rsnd_kctrl_cfg *c = kctrl->private_data; - if (strcmp(kctrl->id.name, name) == 0 && - c->mod == mod) + if (c == cfg) return 0; } diff --git a/sound/soc/sh/rcar/ssi.c b/sound/soc/sh/rcar/ssi.c index 45ef295743ec..f5afab631abb 100644 --- a/sound/soc/sh/rcar/ssi.c +++ b/sound/soc/sh/rcar/ssi.c @@ -286,7 +286,7 @@ static int rsnd_ssi_master_clk_start(struct rsnd_mod *mod, if (rsnd_ssi_is_multi_slave(mod, io)) return 0; - if (ssi->usrcnt > 1) { + if (ssi->usrcnt > 0) { if (ssi->rate != rate) { dev_err(dev, "SSI parent/child should use same rate\n"); return -EINVAL; diff --git a/sound/soc/sh/rcar/ssiu.c b/sound/soc/sh/rcar/ssiu.c index c5934adcfd01..c74991dd18ab 100644 --- a/sound/soc/sh/rcar/ssiu.c +++ b/sound/soc/sh/rcar/ssiu.c @@ -79,7 +79,7 @@ static int rsnd_ssiu_init(struct rsnd_mod *mod, break; case 9: for (i = 0; i < 4; i++) - rsnd_mod_write(mod, SSI_SYS_STATUS((i * 2) + 1), 0xf << (id * 4)); + rsnd_mod_write(mod, SSI_SYS_STATUS((i * 2) + 1), 0xf << 4); break; } diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c index aae450ba4f08..50617db05c46 100644 --- a/sound/soc/soc-core.c +++ b/sound/soc/soc-core.c @@ -735,12 +735,17 @@ static struct snd_soc_component *soc_find_component( const struct device_node *of_node, const char *name) { struct snd_soc_component *component; + struct device_node *component_of_node; lockdep_assert_held(&client_mutex); for_each_component(component) { if (of_node) { - if (component->dev->of_node == of_node) + component_of_node = component->dev->of_node; + if (!component_of_node && component->dev->parent) + component_of_node = component->dev->parent->of_node; + + if (component_of_node == of_node) return component; } else if (name && strcmp(component->name, name) == 0) { return component; @@ -951,7 +956,7 @@ static void soc_remove_dai(struct snd_soc_dai *dai, int order) { int err; - if (!dai || !dai->probed || + if (!dai || !dai->probed || !dai->driver || dai->driver->remove_order != order) return; diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index 2c4c13419539..20bad755888b 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -70,12 +70,16 @@ static int dapm_up_seq[] = { [snd_soc_dapm_clock_supply] = 1, [snd_soc_dapm_supply] = 2, [snd_soc_dapm_micbias] = 3, + [snd_soc_dapm_vmid] = 3, [snd_soc_dapm_dai_link] = 2, [snd_soc_dapm_dai_in] = 4, [snd_soc_dapm_dai_out] = 4, [snd_soc_dapm_aif_in] = 4, [snd_soc_dapm_aif_out] = 4, [snd_soc_dapm_mic] = 5, + [snd_soc_dapm_siggen] = 5, + [snd_soc_dapm_input] = 5, + [snd_soc_dapm_output] = 5, [snd_soc_dapm_mux] = 6, [snd_soc_dapm_demux] = 6, [snd_soc_dapm_dac] = 7, @@ -83,11 +87,19 @@ static int dapm_up_seq[] = { [snd_soc_dapm_mixer] = 8, [snd_soc_dapm_mixer_named_ctl] = 8, [snd_soc_dapm_pga] = 9, + [snd_soc_dapm_buffer] = 9, + [snd_soc_dapm_scheduler] = 9, + [snd_soc_dapm_effect] = 9, + [snd_soc_dapm_src] = 9, + [snd_soc_dapm_asrc] = 9, + [snd_soc_dapm_encoder] = 9, + [snd_soc_dapm_decoder] = 9, [snd_soc_dapm_adc] = 10, [snd_soc_dapm_out_drv] = 11, [snd_soc_dapm_hp] = 11, [snd_soc_dapm_spk] = 11, [snd_soc_dapm_line] = 11, + [snd_soc_dapm_sink] = 11, [snd_soc_dapm_kcontrol] = 12, [snd_soc_dapm_post] = 13, }; @@ -100,13 +112,25 @@ static int dapm_down_seq[] = { [snd_soc_dapm_spk] = 3, [snd_soc_dapm_line] = 3, [snd_soc_dapm_out_drv] = 3, + [snd_soc_dapm_sink] = 3, [snd_soc_dapm_pga] = 4, + [snd_soc_dapm_buffer] = 4, + [snd_soc_dapm_scheduler] = 4, + [snd_soc_dapm_effect] = 4, + [snd_soc_dapm_src] = 4, + [snd_soc_dapm_asrc] = 4, + [snd_soc_dapm_encoder] = 4, + [snd_soc_dapm_decoder] = 4, [snd_soc_dapm_switch] = 5, [snd_soc_dapm_mixer_named_ctl] = 5, [snd_soc_dapm_mixer] = 5, [snd_soc_dapm_dac] = 6, [snd_soc_dapm_mic] = 7, + [snd_soc_dapm_siggen] = 7, + [snd_soc_dapm_input] = 7, + [snd_soc_dapm_output] = 7, [snd_soc_dapm_micbias] = 8, + [snd_soc_dapm_vmid] = 8, [snd_soc_dapm_mux] = 9, [snd_soc_dapm_demux] = 9, [snd_soc_dapm_aif_in] = 10, diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index 045ef136903d..fc79ec6927e3 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -502,6 +502,7 @@ static void remove_dai(struct snd_soc_component *comp, { struct snd_soc_dai_driver *dai_drv = container_of(dobj, struct snd_soc_dai_driver, dobj); + struct snd_soc_dai *dai; if (pass != SOC_TPLG_PASS_PCM_DAI) return; @@ -509,6 +510,10 @@ static void remove_dai(struct snd_soc_component *comp, if (dobj->ops && dobj->ops->dai_unload) dobj->ops->dai_unload(comp, dobj); + list_for_each_entry(dai, &comp->dai_list, list) + if (dai->driver == dai_drv) + dai->driver = NULL; + kfree(dai_drv->name); list_del(&dobj->list); kfree(dai_drv); diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c index 382847154227..db114f3977e0 100644 --- a/sound/usb/pcm.c +++ b/sound/usb/pcm.c @@ -314,6 +314,9 @@ static int search_roland_implicit_fb(struct usb_device *dev, int ifnum, return 0; } +/* Setup an implicit feedback endpoint from a quirk. Returns 0 if no quirk + * applies. Returns 1 if a quirk was found. + */ static int set_sync_ep_implicit_fb_quirk(struct snd_usb_substream *subs, struct usb_device *dev, struct usb_interface_descriptor *altsd, @@ -384,7 +387,7 @@ add_sync_ep: subs->data_endpoint->sync_master = subs->sync_endpoint; - return 0; + return 1; } static int set_sync_endpoint(struct snd_usb_substream *subs, @@ -423,6 +426,10 @@ static int set_sync_endpoint(struct snd_usb_substream *subs, if (err < 0) return err; + /* endpoint set by quirk */ + if (err > 0) + return 0; + if (altsd->bNumEndpoints < 2) return 0; diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index ebbadb3a7094..7e65fe853ee3 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1492,6 +1492,7 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip, return SNDRV_PCM_FMTBIT_DSD_U32_BE; break; + case USB_ID(0x10cb, 0x0103): /* The Bit Opus #3; with fp->dsd_raw */ case USB_ID(0x152a, 0x85de): /* SMSL D1 DAC */ case USB_ID(0x16d0, 0x09dd): /* Encore mDSD */ case USB_ID(0x0d8c, 0x0316): /* Hegel HD12 DSD */ @@ -1566,6 +1567,7 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip, case 0x20b1: /* XMOS based devices */ case 0x152a: /* Thesycon devices */ case 0x25ce: /* Mytek devices */ + case 0x2ab6: /* T+A devices */ if (fp->dsd_raw) return SNDRV_PCM_FMTBIT_DSD_U32_BE; break; diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst index d43fce568ef7..9bb9ace54ba8 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst @@ -17,8 +17,8 @@ SYNOPSIS *COMMANDS* := { **show** | **list** | **tree** | **attach** | **detach** | **help** } -MAP COMMANDS -============= +CGROUP COMMANDS +=============== | **bpftool** **cgroup { show | list }** *CGROUP* | **bpftool** **cgroup tree** [*CGROUP_ROOT*] diff --git a/tools/bpf/bpftool/Documentation/bpftool-feature.rst b/tools/bpf/bpftool/Documentation/bpftool-feature.rst index 8d489a26e3c9..82de03dd8f52 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-feature.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-feature.rst @@ -16,8 +16,8 @@ SYNOPSIS *COMMANDS* := { **probe** | **help** } -MAP COMMANDS -============= +FEATURE COMMANDS +================ | **bpftool** **feature probe** [*COMPONENT*] [**macros** [**prefix** *PREFIX*]] | **bpftool** **feature help** diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index 13b56102f528..7e59495cb028 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -18,7 +18,7 @@ SYNOPSIS { **show** | **list** | **dump xlated** | **dump jited** | **pin** | **load** | **loadall** | **help** } -MAP COMMANDS +PROG COMMANDS ============= | **bpftool** **prog { show | list }** [*PROG*] diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst index 27153bb816ac..4f2188845dd8 100644 --- a/tools/bpf/bpftool/Documentation/bpftool.rst +++ b/tools/bpf/bpftool/Documentation/bpftool.rst @@ -16,7 +16,7 @@ SYNOPSIS **bpftool** **version** - *OBJECT* := { **map** | **program** | **cgroup** | **perf** | **net** } + *OBJECT* := { **map** | **program** | **cgroup** | **perf** | **net** | **feature** } *OPTIONS* := { { **-V** | **--version** } | { **-h** | **--help** } | { **-j** | **--json** } [{ **-p** | **--pretty** }] } @@ -34,6 +34,8 @@ SYNOPSIS *NET-COMMANDS* := { **show** | **list** | **help** } + *FEATURE-COMMANDS* := { **probe** | **help** } + DESCRIPTION =========== *bpftool* allows for inspection and simple modification of BPF objects diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index 897483457bf0..f7261fad45c1 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -297,10 +297,8 @@ char *get_fdinfo(int fd, const char *key) snprintf(path, sizeof(path), "/proc/self/fdinfo/%d", fd); fdi = fopen(path, "r"); - if (!fdi) { - p_err("can't open fdinfo: %s", strerror(errno)); + if (!fdi) return NULL; - } while ((n = getline(&line, &line_n, fdi)) > 0) { char *value; @@ -313,7 +311,6 @@ char *get_fdinfo(int fd, const char *key) value = strchr(line, '\t'); if (!value || !value[1]) { - p_err("malformed fdinfo!?"); free(line); return NULL; } @@ -326,7 +323,6 @@ char *get_fdinfo(int fd, const char *key) return line; } - p_err("key '%s' not found in fdinfo", key); free(line); fclose(fdi); return NULL; diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index 2160a8ef17e5..e0c650d91784 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -358,6 +358,20 @@ static char **parse_bytes(char **argv, const char *name, unsigned char *val, return argv + i; } +/* on per cpu maps we must copy the provided value on all value instances */ +static void fill_per_cpu_value(struct bpf_map_info *info, void *value) +{ + unsigned int i, n, step; + + if (!map_is_per_cpu(info->type)) + return; + + n = get_possible_cpus(); + step = round_up(info->value_size, 8); + for (i = 1; i < n; i++) + memcpy(value + i * step, value, info->value_size); +} + static int parse_elem(char **argv, struct bpf_map_info *info, void *key, void *value, __u32 key_size, __u32 value_size, __u32 *flags, __u32 **value_fd) @@ -440,6 +454,8 @@ static int parse_elem(char **argv, struct bpf_map_info *info, argv = parse_bytes(argv, "value", value, value_size); if (!argv) return -1; + + fill_per_cpu_value(info, value); } return parse_elem(argv, info, key, NULL, key_size, value_size, @@ -511,10 +527,9 @@ static int show_map_close_json(int fd, struct bpf_map_info *info) jsonw_uint_field(json_wtr, "owner_prog_type", prog_type); } - if (atoi(owner_jited)) - jsonw_bool_field(json_wtr, "owner_jited", true); - else - jsonw_bool_field(json_wtr, "owner_jited", false); + if (owner_jited) + jsonw_bool_field(json_wtr, "owner_jited", + !!atoi(owner_jited)); free(owner_prog_type); free(owner_jited); @@ -567,7 +582,8 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info) char *owner_prog_type = get_fdinfo(fd, "owner_prog_type"); char *owner_jited = get_fdinfo(fd, "owner_jited"); - printf("\n\t"); + if (owner_prog_type || owner_jited) + printf("\n\t"); if (owner_prog_type) { unsigned int prog_type = atoi(owner_prog_type); @@ -577,10 +593,9 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info) else printf("owner_prog_type %d ", prog_type); } - if (atoi(owner_jited)) - printf("owner jited"); - else - printf("owner not jited"); + if (owner_jited) + printf("owner%s jited", + atoi(owner_jited) ? "" : " not"); free(owner_prog_type); free(owner_jited); diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 0640e9bc0ada..33ed0806ccc0 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -78,13 +78,14 @@ static void print_boot_time(__u64 nsecs, char *buf, unsigned int size) static int prog_fd_by_tag(unsigned char *tag) { - struct bpf_prog_info info = {}; - __u32 len = sizeof(info); unsigned int id = 0; int err; int fd; while (true) { + struct bpf_prog_info info = {}; + __u32 len = sizeof(info); + err = bpf_prog_get_next_id(id, &id); if (err) { p_err("%s", strerror(errno)); diff --git a/tools/iio/iio_generic_buffer.c b/tools/iio/iio_generic_buffer.c index 3040830d7797..84545666a09c 100644 --- a/tools/iio/iio_generic_buffer.c +++ b/tools/iio/iio_generic_buffer.c @@ -330,7 +330,7 @@ static const struct option longopts[] = { int main(int argc, char **argv) { - unsigned long long num_loops = 2; + long long num_loops = 2; unsigned long timedelay = 1000000; unsigned long buf_len = 128; diff --git a/tools/include/uapi/asm/bitsperlong.h b/tools/include/uapi/asm/bitsperlong.h index fd92ce8388fc..57aaeaf8e192 100644 --- a/tools/include/uapi/asm/bitsperlong.h +++ b/tools/include/uapi/asm/bitsperlong.h @@ -15,6 +15,8 @@ #include "../../arch/ia64/include/uapi/asm/bitsperlong.h" #elif defined(__riscv) #include "../../arch/riscv/include/uapi/asm/bitsperlong.h" +#elif defined(__alpha__) +#include "../../arch/alpha/include/uapi/asm/bitsperlong.h" #else #include <asm-generic/bitsperlong.h> #endif diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 60b99b730a41..bcdd2474eee7 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -267,6 +267,7 @@ enum bpf_attach_type { #define BPF_ANY 0 /* create new element or update existing */ #define BPF_NOEXIST 1 /* create new element if it didn't exist */ #define BPF_EXIST 2 /* update existing element */ +#define BPF_F_LOCK 4 /* spin_lock-ed map_lookup/map_update */ /* flags for BPF_MAP_CREATE command */ #define BPF_F_NO_PREALLOC (1U << 0) @@ -2015,6 +2016,19 @@ union bpf_attr { * Only works if *skb* contains an IPv6 packet. Insert a * Segment Routing Header (**struct ipv6_sr_hdr**) inside * the IPv6 header. + * **BPF_LWT_ENCAP_IP** + * IP encapsulation (GRE/GUE/IPIP/etc). The outer header + * must be IPv4 or IPv6, followed by zero or more + * additional headers, up to LWT_BPF_MAX_HEADROOM total + * bytes in all prepended headers. Please note that + * if skb_is_gso(skb) is true, no more than two headers + * can be prepended, and the inner header, if present, + * should be either GRE or UDP/GUE. + * + * BPF_LWT_ENCAP_SEG6*** types can be called by bpf programs of + * type BPF_PROG_TYPE_LWT_IN; BPF_LWT_ENCAP_IP type can be called + * by bpf programs of types BPF_PROG_TYPE_LWT_IN and + * BPF_PROG_TYPE_LWT_XMIT. * * A call to this helper is susceptible to change the underlaying * packet buffer. Therefore, at load time, all checks on pointers @@ -2328,6 +2342,23 @@ union bpf_attr { * "**y**". * Return * 0 + * + * struct bpf_sock *bpf_sk_fullsock(struct bpf_sock *sk) + * Description + * This helper gets a **struct bpf_sock** pointer such + * that all the fields in bpf_sock can be accessed. + * Return + * A **struct bpf_sock** pointer on success, or NULL in + * case of failure. + * + * struct bpf_tcp_sock *bpf_tcp_sock(struct bpf_sock *sk) + * Description + * This helper gets a **struct bpf_tcp_sock** pointer from a + * **struct bpf_sock** pointer. + * + * Return + * A **struct bpf_tcp_sock** pointer on success, or NULL in + * case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2422,7 +2453,11 @@ union bpf_attr { FN(map_peek_elem), \ FN(msg_push_data), \ FN(msg_pop_data), \ - FN(rc_pointer_rel), + FN(rc_pointer_rel), \ + FN(spin_lock), \ + FN(spin_unlock), \ + FN(sk_fullsock), \ + FN(tcp_sock), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -2495,7 +2530,8 @@ enum bpf_hdr_start_off { /* Encapsulation type for BPF_FUNC_lwt_push_encap helper. */ enum bpf_lwt_encap_mode { BPF_LWT_ENCAP_SEG6, - BPF_LWT_ENCAP_SEG6_INLINE + BPF_LWT_ENCAP_SEG6_INLINE, + BPF_LWT_ENCAP_IP, }; #define __bpf_md_ptr(type, name) \ @@ -2542,6 +2578,7 @@ struct __sk_buff { __u64 tstamp; __u32 wire_len; __u32 gso_segs; + __bpf_md_ptr(struct bpf_sock *, sk); }; struct bpf_tunnel_key { @@ -2583,7 +2620,15 @@ enum bpf_ret_code { BPF_DROP = 2, /* 3-6 reserved */ BPF_REDIRECT = 7, - /* >127 are reserved for prog type specific return codes */ + /* >127 are reserved for prog type specific return codes. + * + * BPF_LWT_REROUTE: used by BPF_PROG_TYPE_LWT_IN and + * BPF_PROG_TYPE_LWT_XMIT to indicate that skb had been + * changed and should be routed based on its new L3 header. + * (This is an L3 redirect, as opposed to L2 redirect + * represented by BPF_REDIRECT above). + */ + BPF_LWT_REROUTE = 128, }; struct bpf_sock { @@ -2593,14 +2638,52 @@ struct bpf_sock { __u32 protocol; __u32 mark; __u32 priority; - __u32 src_ip4; /* Allows 1,2,4-byte read. - * Stored in network byte order. + /* IP address also allows 1 and 2 bytes access */ + __u32 src_ip4; + __u32 src_ip6[4]; + __u32 src_port; /* host byte order */ + __u32 dst_port; /* network byte order */ + __u32 dst_ip4; + __u32 dst_ip6[4]; + __u32 state; +}; + +struct bpf_tcp_sock { + __u32 snd_cwnd; /* Sending congestion window */ + __u32 srtt_us; /* smoothed round trip time << 3 in usecs */ + __u32 rtt_min; + __u32 snd_ssthresh; /* Slow start size threshold */ + __u32 rcv_nxt; /* What we want to receive next */ + __u32 snd_nxt; /* Next sequence we send */ + __u32 snd_una; /* First byte we want an ack for */ + __u32 mss_cache; /* Cached effective mss, not including SACKS */ + __u32 ecn_flags; /* ECN status bits. */ + __u32 rate_delivered; /* saved rate sample: packets delivered */ + __u32 rate_interval_us; /* saved rate sample: time elapsed */ + __u32 packets_out; /* Packets which are "in flight" */ + __u32 retrans_out; /* Retransmitted packets out */ + __u32 total_retrans; /* Total retransmits for entire connection */ + __u32 segs_in; /* RFC4898 tcpEStatsPerfSegsIn + * total number of segments in. */ - __u32 src_ip6[4]; /* Allows 1,2,4-byte read. - * Stored in network byte order. + __u32 data_segs_in; /* RFC4898 tcpEStatsPerfDataSegsIn + * total number of data segments in. */ - __u32 src_port; /* Allows 4-byte read. - * Stored in host byte order + __u32 segs_out; /* RFC4898 tcpEStatsPerfSegsOut + * The total number of segments sent. + */ + __u32 data_segs_out; /* RFC4898 tcpEStatsPerfDataSegsOut + * total number of data segments sent. + */ + __u32 lost_out; /* Lost packets */ + __u32 sacked_out; /* SACK'd packets */ + __u64 bytes_received; /* RFC4898 tcpEStatsAppHCThruOctetsReceived + * sum(delta(rcv_nxt)), or how many bytes + * were acked. + */ + __u64 bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked + * sum(delta(snd_una)), or how many bytes + * were acked. */ }; @@ -3056,4 +3139,7 @@ struct bpf_line_info { __u32 line_col; }; +struct bpf_spin_lock { + __u32 val; +}; #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index d6533828123a..5b225ff63b48 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -925,6 +925,7 @@ enum { enum { LINK_XSTATS_TYPE_UNSPEC, LINK_XSTATS_TYPE_BRIDGE, + LINK_XSTATS_TYPE_BOND, __LINK_XSTATS_TYPE_MAX }; #define LINK_XSTATS_TYPE_MAX (__LINK_XSTATS_TYPE_MAX - 1) diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h index f6052e70bf40..a55cb8b10165 100644 --- a/tools/include/uapi/linux/in.h +++ b/tools/include/uapi/linux/in.h @@ -268,7 +268,7 @@ struct sockaddr_in { #define IN_MULTICAST(a) IN_CLASSD(a) #define IN_MULTICAST_NET 0xe0000000 -#define IN_BADCLASS(a) ((((long int) (a) ) == 0xffffffff) +#define IN_BADCLASS(a) (((long int) (a) ) == (long int)0xffffffff) #define IN_EXPERIMENTAL(a) IN_BADCLASS((a)) #define IN_CLASSE(a) ((((long int) (a)) & 0xf0000000) == 0xf0000000) diff --git a/tools/include/uapi/linux/tc_act/tc_bpf.h b/tools/include/uapi/linux/tc_act/tc_bpf.h index 6e89a5df49a4..653c4f94f76e 100644 --- a/tools/include/uapi/linux/tc_act/tc_bpf.h +++ b/tools/include/uapi/linux/tc_act/tc_bpf.h @@ -13,8 +13,6 @@ #include <linux/pkt_cls.h> -#define TCA_ACT_BPF 13 - struct tc_act_bpf { tc_gen; }; diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 88cbd110ae58..9cd015574e83 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -22,6 +22,7 @@ */ #include <stdlib.h> +#include <string.h> #include <memory.h> #include <unistd.h> #include <asm/unistd.h> @@ -214,23 +215,35 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, { void *finfo = NULL, *linfo = NULL; union bpf_attr attr; + __u32 log_level; __u32 name_len; int fd; - if (!load_attr) + if (!load_attr || !log_buf != !log_buf_sz) + return -EINVAL; + + log_level = load_attr->log_level; + if (log_level > 2 || (log_level && !log_buf)) return -EINVAL; name_len = load_attr->name ? strlen(load_attr->name) : 0; - bzero(&attr, sizeof(attr)); + memset(&attr, 0, sizeof(attr)); attr.prog_type = load_attr->prog_type; attr.expected_attach_type = load_attr->expected_attach_type; attr.insn_cnt = (__u32)load_attr->insns_cnt; attr.insns = ptr_to_u64(load_attr->insns); attr.license = ptr_to_u64(load_attr->license); - attr.log_buf = ptr_to_u64(NULL); - attr.log_size = 0; - attr.log_level = 0; + + attr.log_level = log_level; + if (log_level) { + attr.log_buf = ptr_to_u64(log_buf); + attr.log_size = log_buf_sz; + } else { + attr.log_buf = ptr_to_u64(NULL); + attr.log_size = 0; + } + attr.kern_version = load_attr->kern_version; attr.prog_ifindex = load_attr->prog_ifindex; attr.prog_btf_fd = load_attr->prog_btf_fd; @@ -286,7 +299,7 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, goto done; } - if (!log_buf || !log_buf_sz) + if (log_level || !log_buf) goto done; /* Try again with log */ @@ -327,7 +340,7 @@ int bpf_verify_program(enum bpf_prog_type type, const struct bpf_insn *insns, { union bpf_attr attr; - bzero(&attr, sizeof(attr)); + memset(&attr, 0, sizeof(attr)); attr.prog_type = type; attr.insn_cnt = (__u32)insns_cnt; attr.insns = ptr_to_u64(insns); @@ -347,7 +360,7 @@ int bpf_map_update_elem(int fd, const void *key, const void *value, { union bpf_attr attr; - bzero(&attr, sizeof(attr)); + memset(&attr, 0, sizeof(attr)); attr.map_fd = fd; attr.key = ptr_to_u64(key); attr.value = ptr_to_u64(value); @@ -360,7 +373,7 @@ int bpf_map_lookup_elem(int fd, const void *key, void *value) { union bpf_attr attr; - bzero(&attr, sizeof(attr)); + memset(&attr, 0, sizeof(attr)); attr.map_fd = fd; attr.key = ptr_to_u64(key); attr.value = ptr_to_u64(value); @@ -368,11 +381,24 @@ int bpf_map_lookup_elem(int fd, const void *key, void *value) return sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr)); } +int bpf_map_lookup_elem_flags(int fd, const void *key, void *value, __u64 flags) +{ + union bpf_attr attr; + + memset(&attr, 0, sizeof(attr)); + attr.map_fd = fd; + attr.key = ptr_to_u64(key); + attr.value = ptr_to_u64(value); + attr.flags = flags; + + return sys_bpf(BPF_MAP_LOOKUP_ELEM, &attr, sizeof(attr)); +} + int bpf_map_lookup_and_delete_elem(int fd, const void *key, void *value) { union bpf_attr attr; - bzero(&attr, sizeof(attr)); + memset(&attr, 0, sizeof(attr)); attr.map_fd = fd; attr.key = ptr_to_u64(key); attr.value = ptr_to_u64(value); @@ -384,7 +410,7 @@ int bpf_map_delete_elem(int fd, const void *key) { union bpf_attr attr; - bzero(&attr, sizeof(attr)); + memset(&attr, 0, sizeof(attr)); attr.map_fd = fd; attr.key = ptr_to_u64(key); @@ -395,7 +421,7 @@ int bpf_map_get_next_key(int fd, const void *key, void *next_key) { union bpf_attr attr; - bzero(&attr, sizeof(attr)); + memset(&attr, 0, sizeof(attr)); attr.map_fd = fd; attr.key = ptr_to_u64(key); attr.next_key = ptr_to_u64(next_key); @@ -407,7 +433,7 @@ int bpf_obj_pin(int fd, const char *pathname) { union bpf_attr attr; - bzero(&attr, sizeof(attr)); + memset(&attr, 0, sizeof(attr)); attr.pathname = ptr_to_u64((void *)pathname); attr.bpf_fd = fd; @@ -418,7 +444,7 @@ int bpf_obj_get(const char *pathname) { union bpf_attr attr; - bzero(&attr, sizeof(attr)); + memset(&attr, 0, sizeof(attr)); attr.pathname = ptr_to_u64((void *)pathname); return sys_bpf(BPF_OBJ_GET, &attr, sizeof(attr)); @@ -429,7 +455,7 @@ int bpf_prog_attach(int prog_fd, int target_fd, enum bpf_attach_type type, { union bpf_attr attr; - bzero(&attr, sizeof(attr)); + memset(&attr, 0, sizeof(attr)); attr.target_fd = target_fd; attr.attach_bpf_fd = prog_fd; attr.attach_type = type; @@ -442,7 +468,7 @@ int bpf_prog_detach(int target_fd, enum bpf_attach_type type) { union bpf_attr attr; - bzero(&attr, sizeof(attr)); + memset(&attr, 0, sizeof(attr)); attr.target_fd = target_fd; attr.attach_type = type; @@ -453,7 +479,7 @@ int bpf_prog_detach2(int prog_fd, int target_fd, enum bpf_attach_type type) { union bpf_attr attr; - bzero(&attr, sizeof(attr)); + memset(&attr, 0, sizeof(attr)); attr.target_fd = target_fd; attr.attach_bpf_fd = prog_fd; attr.attach_type = type; @@ -467,7 +493,7 @@ int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags, union bpf_attr attr; int ret; - bzero(&attr, sizeof(attr)); + memset(&attr, 0, sizeof(attr)); attr.query.target_fd = target_fd; attr.query.attach_type = type; attr.query.query_flags = query_flags; @@ -488,7 +514,7 @@ int bpf_prog_test_run(int prog_fd, int repeat, void *data, __u32 size, union bpf_attr attr; int ret; - bzero(&attr, sizeof(attr)); + memset(&attr, 0, sizeof(attr)); attr.test.prog_fd = prog_fd; attr.test.data_in = ptr_to_u64(data); attr.test.data_out = ptr_to_u64(data_out); @@ -513,7 +539,7 @@ int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr) if (!test_attr->data_out && test_attr->data_size_out > 0) return -EINVAL; - bzero(&attr, sizeof(attr)); + memset(&attr, 0, sizeof(attr)); attr.test.prog_fd = test_attr->prog_fd; attr.test.data_in = ptr_to_u64(test_attr->data_in); attr.test.data_out = ptr_to_u64(test_attr->data_out); @@ -533,7 +559,7 @@ int bpf_prog_get_next_id(__u32 start_id, __u32 *next_id) union bpf_attr attr; int err; - bzero(&attr, sizeof(attr)); + memset(&attr, 0, sizeof(attr)); attr.start_id = start_id; err = sys_bpf(BPF_PROG_GET_NEXT_ID, &attr, sizeof(attr)); @@ -548,7 +574,7 @@ int bpf_map_get_next_id(__u32 start_id, __u32 *next_id) union bpf_attr attr; int err; - bzero(&attr, sizeof(attr)); + memset(&attr, 0, sizeof(attr)); attr.start_id = start_id; err = sys_bpf(BPF_MAP_GET_NEXT_ID, &attr, sizeof(attr)); @@ -562,7 +588,7 @@ int bpf_prog_get_fd_by_id(__u32 id) { union bpf_attr attr; - bzero(&attr, sizeof(attr)); + memset(&attr, 0, sizeof(attr)); attr.prog_id = id; return sys_bpf(BPF_PROG_GET_FD_BY_ID, &attr, sizeof(attr)); @@ -572,7 +598,7 @@ int bpf_map_get_fd_by_id(__u32 id) { union bpf_attr attr; - bzero(&attr, sizeof(attr)); + memset(&attr, 0, sizeof(attr)); attr.map_id = id; return sys_bpf(BPF_MAP_GET_FD_BY_ID, &attr, sizeof(attr)); @@ -582,7 +608,7 @@ int bpf_btf_get_fd_by_id(__u32 id) { union bpf_attr attr; - bzero(&attr, sizeof(attr)); + memset(&attr, 0, sizeof(attr)); attr.btf_id = id; return sys_bpf(BPF_BTF_GET_FD_BY_ID, &attr, sizeof(attr)); @@ -593,7 +619,7 @@ int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len) union bpf_attr attr; int err; - bzero(&attr, sizeof(attr)); + memset(&attr, 0, sizeof(attr)); attr.info.bpf_fd = prog_fd; attr.info.info_len = *info_len; attr.info.info = ptr_to_u64(info); @@ -609,7 +635,7 @@ int bpf_raw_tracepoint_open(const char *name, int prog_fd) { union bpf_attr attr; - bzero(&attr, sizeof(attr)); + memset(&attr, 0, sizeof(attr)); attr.raw_tracepoint.name = ptr_to_u64(name); attr.raw_tracepoint.prog_fd = prog_fd; diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 8f09de482839..6ffdd79bea89 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -85,6 +85,7 @@ struct bpf_load_program_attr { __u32 line_info_rec_size; const void *line_info; __u32 line_info_cnt; + __u32 log_level; }; /* Flags to direct loading requirements */ @@ -110,6 +111,8 @@ LIBBPF_API int bpf_map_update_elem(int fd, const void *key, const void *value, __u64 flags); LIBBPF_API int bpf_map_lookup_elem(int fd, const void *key, void *value); +LIBBPF_API int bpf_map_lookup_elem_flags(int fd, const void *key, void *value, + __u64 flags); LIBBPF_API int bpf_map_lookup_and_delete_elem(int fd, const void *key, void *value); LIBBPF_API int bpf_map_delete_elem(int fd, const void *key); diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index d682d3b8f7b9..68b50e9bbde1 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) /* Copyright (c) 2018 Facebook */ +#include <stdio.h> #include <stdlib.h> #include <string.h> #include <unistd.h> @@ -9,12 +10,14 @@ #include <linux/btf.h> #include "btf.h" #include "bpf.h" +#include "libbpf.h" +#include "libbpf_util.h" -#define elog(fmt, ...) { if (err_log) err_log(fmt, ##__VA_ARGS__); } #define max(a, b) ((a) > (b) ? (a) : (b)) #define min(a, b) ((a) < (b) ? (a) : (b)) -#define BTF_MAX_NR_TYPES 65535 +#define BTF_MAX_NR_TYPES 0x7fffffff +#define BTF_MAX_STR_OFFSET 0x7fffffff #define IS_MODIFIER(k) (((k) == BTF_KIND_TYPEDEF) || \ ((k) == BTF_KIND_VOLATILE) || \ @@ -39,9 +42,8 @@ struct btf { struct btf_ext_info { /* - * info points to a deep copy of the individual info section - * (e.g. func_info and line_info) from the .BTF.ext. - * It does not include the __u32 rec_size. + * info points to the individual info section (e.g. func_info and + * line_info) from the .BTF.ext. It does not include the __u32 rec_size. */ void *info; __u32 rec_size; @@ -49,8 +51,13 @@ struct btf_ext_info { }; struct btf_ext { + union { + struct btf_ext_header *hdr; + void *data; + }; struct btf_ext_info func_info; struct btf_ext_info line_info; + __u32 data_size; }; struct btf_ext_info_sec { @@ -107,54 +114,54 @@ static int btf_add_type(struct btf *btf, struct btf_type *t) return 0; } -static int btf_parse_hdr(struct btf *btf, btf_print_fn_t err_log) +static int btf_parse_hdr(struct btf *btf) { const struct btf_header *hdr = btf->hdr; __u32 meta_left; if (btf->data_size < sizeof(struct btf_header)) { - elog("BTF header not found\n"); + pr_debug("BTF header not found\n"); return -EINVAL; } if (hdr->magic != BTF_MAGIC) { - elog("Invalid BTF magic:%x\n", hdr->magic); + pr_debug("Invalid BTF magic:%x\n", hdr->magic); return -EINVAL; } if (hdr->version != BTF_VERSION) { - elog("Unsupported BTF version:%u\n", hdr->version); + pr_debug("Unsupported BTF version:%u\n", hdr->version); return -ENOTSUP; } if (hdr->flags) { - elog("Unsupported BTF flags:%x\n", hdr->flags); + pr_debug("Unsupported BTF flags:%x\n", hdr->flags); return -ENOTSUP; } meta_left = btf->data_size - sizeof(*hdr); if (!meta_left) { - elog("BTF has no data\n"); + pr_debug("BTF has no data\n"); return -EINVAL; } if (meta_left < hdr->type_off) { - elog("Invalid BTF type section offset:%u\n", hdr->type_off); + pr_debug("Invalid BTF type section offset:%u\n", hdr->type_off); return -EINVAL; } if (meta_left < hdr->str_off) { - elog("Invalid BTF string section offset:%u\n", hdr->str_off); + pr_debug("Invalid BTF string section offset:%u\n", hdr->str_off); return -EINVAL; } if (hdr->type_off >= hdr->str_off) { - elog("BTF type section offset >= string section offset. No type?\n"); + pr_debug("BTF type section offset >= string section offset. No type?\n"); return -EINVAL; } if (hdr->type_off & 0x02) { - elog("BTF type section is not aligned to 4 bytes\n"); + pr_debug("BTF type section is not aligned to 4 bytes\n"); return -EINVAL; } @@ -163,15 +170,15 @@ static int btf_parse_hdr(struct btf *btf, btf_print_fn_t err_log) return 0; } -static int btf_parse_str_sec(struct btf *btf, btf_print_fn_t err_log) +static int btf_parse_str_sec(struct btf *btf) { const struct btf_header *hdr = btf->hdr; const char *start = btf->nohdr_data + hdr->str_off; const char *end = start + btf->hdr->str_len; - if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_NAME_OFFSET || + if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_STR_OFFSET || start[0] || end[-1]) { - elog("Invalid BTF string section\n"); + pr_debug("Invalid BTF string section\n"); return -EINVAL; } @@ -180,7 +187,38 @@ static int btf_parse_str_sec(struct btf *btf, btf_print_fn_t err_log) return 0; } -static int btf_parse_type_sec(struct btf *btf, btf_print_fn_t err_log) +static int btf_type_size(struct btf_type *t) +{ + int base_size = sizeof(struct btf_type); + __u16 vlen = BTF_INFO_VLEN(t->info); + + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_FWD: + case BTF_KIND_CONST: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_PTR: + case BTF_KIND_TYPEDEF: + case BTF_KIND_FUNC: + return base_size; + case BTF_KIND_INT: + return base_size + sizeof(__u32); + case BTF_KIND_ENUM: + return base_size + vlen * sizeof(struct btf_enum); + case BTF_KIND_ARRAY: + return base_size + sizeof(struct btf_array); + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + return base_size + vlen * sizeof(struct btf_member); + case BTF_KIND_FUNC_PROTO: + return base_size + vlen * sizeof(struct btf_param); + default: + pr_debug("Unsupported BTF_KIND:%u\n", BTF_INFO_KIND(t->info)); + return -EINVAL; + } +} + +static int btf_parse_type_sec(struct btf *btf) { struct btf_header *hdr = btf->hdr; void *nohdr_data = btf->nohdr_data; @@ -189,41 +227,13 @@ static int btf_parse_type_sec(struct btf *btf, btf_print_fn_t err_log) while (next_type < end_type) { struct btf_type *t = next_type; - __u16 vlen = BTF_INFO_VLEN(t->info); + int type_size; int err; - next_type += sizeof(*t); - switch (BTF_INFO_KIND(t->info)) { - case BTF_KIND_INT: - next_type += sizeof(int); - break; - case BTF_KIND_ARRAY: - next_type += sizeof(struct btf_array); - break; - case BTF_KIND_STRUCT: - case BTF_KIND_UNION: - next_type += vlen * sizeof(struct btf_member); - break; - case BTF_KIND_ENUM: - next_type += vlen * sizeof(struct btf_enum); - break; - case BTF_KIND_FUNC_PROTO: - next_type += vlen * sizeof(struct btf_param); - break; - case BTF_KIND_FUNC: - case BTF_KIND_TYPEDEF: - case BTF_KIND_PTR: - case BTF_KIND_FWD: - case BTF_KIND_VOLATILE: - case BTF_KIND_CONST: - case BTF_KIND_RESTRICT: - break; - default: - elog("Unsupported BTF_KIND:%u\n", - BTF_INFO_KIND(t->info)); - return -EINVAL; - } - + type_size = btf_type_size(t); + if (type_size < 0) + return type_size; + next_type += type_size; err = btf_add_type(btf, t); if (err) return err; @@ -232,6 +242,11 @@ static int btf_parse_type_sec(struct btf *btf, btf_print_fn_t err_log) return 0; } +__u32 btf__get_nr_types(const struct btf *btf) +{ + return btf->nr_types; +} + const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id) { if (type_id > btf->nr_types) @@ -250,21 +265,6 @@ static bool btf_type_is_void_or_null(const struct btf_type *t) return !t || btf_type_is_void(t); } -static __s64 btf_type_size(const struct btf_type *t) -{ - switch (BTF_INFO_KIND(t->info)) { - case BTF_KIND_INT: - case BTF_KIND_STRUCT: - case BTF_KIND_UNION: - case BTF_KIND_ENUM: - return t->size; - case BTF_KIND_PTR: - return sizeof(void *); - default: - return -EINVAL; - } -} - #define MAX_RESOLVE_DEPTH 32 __s64 btf__resolve_size(const struct btf *btf, __u32 type_id) @@ -278,11 +278,16 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id) t = btf__type_by_id(btf, type_id); for (i = 0; i < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t); i++) { - size = btf_type_size(t); - if (size >= 0) - break; - switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_INT: + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + case BTF_KIND_ENUM: + size = t->size; + goto done; + case BTF_KIND_PTR: + size = sizeof(void *); + goto done; case BTF_KIND_TYPEDEF: case BTF_KIND_VOLATILE: case BTF_KIND_CONST: @@ -306,6 +311,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id) if (size < 0) return -EINVAL; +done: if (nelems && size > UINT32_MAX / nelems) return -E2BIG; @@ -363,10 +369,8 @@ void btf__free(struct btf *btf) free(btf); } -struct btf *btf__new(__u8 *data, __u32 size, btf_print_fn_t err_log) +struct btf *btf__new(__u8 *data, __u32 size) { - __u32 log_buf_size = 0; - char *log_buf = NULL; struct btf *btf; int err; @@ -376,16 +380,6 @@ struct btf *btf__new(__u8 *data, __u32 size, btf_print_fn_t err_log) btf->fd = -1; - if (err_log) { - log_buf = malloc(BPF_LOG_BUF_SIZE); - if (!log_buf) { - err = -ENOMEM; - goto done; - } - *log_buf = 0; - log_buf_size = BPF_LOG_BUF_SIZE; - } - btf->data = malloc(size); if (!btf->data) { err = -ENOMEM; @@ -395,30 +389,17 @@ struct btf *btf__new(__u8 *data, __u32 size, btf_print_fn_t err_log) memcpy(btf->data, data, size); btf->data_size = size; - btf->fd = bpf_load_btf(btf->data, btf->data_size, - log_buf, log_buf_size, false); - - if (btf->fd == -1) { - err = -errno; - elog("Error loading BTF: %s(%d)\n", strerror(errno), errno); - if (log_buf && *log_buf) - elog("%s\n", log_buf); - goto done; - } - - err = btf_parse_hdr(btf, err_log); + err = btf_parse_hdr(btf); if (err) goto done; - err = btf_parse_str_sec(btf, err_log); + err = btf_parse_str_sec(btf); if (err) goto done; - err = btf_parse_type_sec(btf, err_log); + err = btf_parse_type_sec(btf); done: - free(log_buf); - if (err) { btf__free(btf); return ERR_PTR(err); @@ -427,11 +408,47 @@ done: return btf; } +int btf__load(struct btf *btf) +{ + __u32 log_buf_size = BPF_LOG_BUF_SIZE; + char *log_buf = NULL; + int err = 0; + + if (btf->fd >= 0) + return -EEXIST; + + log_buf = malloc(log_buf_size); + if (!log_buf) + return -ENOMEM; + + *log_buf = 0; + + btf->fd = bpf_load_btf(btf->data, btf->data_size, + log_buf, log_buf_size, false); + if (btf->fd < 0) { + err = -errno; + pr_warning("Error loading BTF: %s(%d)\n", strerror(errno), errno); + if (*log_buf) + pr_warning("%s\n", log_buf); + goto done; + } + +done: + free(log_buf); + return err; +} + int btf__fd(const struct btf *btf) { return btf->fd; } +const void *btf__get_raw_data(const struct btf *btf, __u32 *size) +{ + *size = btf->data_size; + return btf->data; +} + const char *btf__name_by_offset(const struct btf *btf, __u32 offset) { if (offset < btf->hdr->str_len) @@ -467,7 +484,7 @@ int btf__get_from_id(__u32 id, struct btf **btf) goto exit_free; } - bzero(ptr, last_size); + memset(ptr, 0, last_size); btf_info.btf = ptr_to_u64(ptr); err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len); @@ -481,7 +498,7 @@ int btf__get_from_id(__u32 id, struct btf **btf) goto exit_free; } ptr = temp_ptr; - bzero(ptr, last_size); + memset(ptr, 0, last_size); btf_info.btf = ptr_to_u64(ptr); err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len); } @@ -491,7 +508,7 @@ int btf__get_from_id(__u32 id, struct btf **btf) goto exit_free; } - *btf = btf__new((__u8 *)(long)btf_info.btf, btf_info.btf_size, NULL); + *btf = btf__new((__u8 *)(long)btf_info.btf, btf_info.btf_size); if (IS_ERR(*btf)) { err = PTR_ERR(*btf); *btf = NULL; @@ -504,7 +521,79 @@ exit_free: return err; } -struct btf_ext_sec_copy_param { +int btf__get_map_kv_tids(const struct btf *btf, const char *map_name, + __u32 expected_key_size, __u32 expected_value_size, + __u32 *key_type_id, __u32 *value_type_id) +{ + const struct btf_type *container_type; + const struct btf_member *key, *value; + const size_t max_name = 256; + char container_name[max_name]; + __s64 key_size, value_size; + __s32 container_id; + + if (snprintf(container_name, max_name, "____btf_map_%s", map_name) == + max_name) { + pr_warning("map:%s length of '____btf_map_%s' is too long\n", + map_name, map_name); + return -EINVAL; + } + + container_id = btf__find_by_name(btf, container_name); + if (container_id < 0) { + pr_debug("map:%s container_name:%s cannot be found in BTF. Missing BPF_ANNOTATE_KV_PAIR?\n", + map_name, container_name); + return container_id; + } + + container_type = btf__type_by_id(btf, container_id); + if (!container_type) { + pr_warning("map:%s cannot find BTF type for container_id:%u\n", + map_name, container_id); + return -EINVAL; + } + + if (BTF_INFO_KIND(container_type->info) != BTF_KIND_STRUCT || + BTF_INFO_VLEN(container_type->info) < 2) { + pr_warning("map:%s container_name:%s is an invalid container struct\n", + map_name, container_name); + return -EINVAL; + } + + key = (struct btf_member *)(container_type + 1); + value = key + 1; + + key_size = btf__resolve_size(btf, key->type); + if (key_size < 0) { + pr_warning("map:%s invalid BTF key_type_size\n", map_name); + return key_size; + } + + if (expected_key_size != key_size) { + pr_warning("map:%s btf_key_type_size:%u != map_def_key_size:%u\n", + map_name, (__u32)key_size, expected_key_size); + return -EINVAL; + } + + value_size = btf__resolve_size(btf, value->type); + if (value_size < 0) { + pr_warning("map:%s invalid BTF value_type_size\n", map_name); + return value_size; + } + + if (expected_value_size != value_size) { + pr_warning("map:%s btf_value_type_size:%u != map_def_value_size:%u\n", + map_name, (__u32)value_size, expected_value_size); + return -EINVAL; + } + + *key_type_id = key->type; + *value_type_id = value->type; + + return 0; +} + +struct btf_ext_sec_setup_param { __u32 off; __u32 len; __u32 min_rec_size; @@ -512,41 +601,33 @@ struct btf_ext_sec_copy_param { const char *desc; }; -static int btf_ext_copy_info(struct btf_ext *btf_ext, - __u8 *data, __u32 data_size, - struct btf_ext_sec_copy_param *ext_sec, - btf_print_fn_t err_log) +static int btf_ext_setup_info(struct btf_ext *btf_ext, + struct btf_ext_sec_setup_param *ext_sec) { - const struct btf_ext_header *hdr = (struct btf_ext_header *)data; const struct btf_ext_info_sec *sinfo; struct btf_ext_info *ext_info; __u32 info_left, record_size; /* The start of the info sec (including the __u32 record_size). */ - const void *info; - - /* data and data_size do not include btf_ext_header from now on */ - data = data + hdr->hdr_len; - data_size -= hdr->hdr_len; + void *info; if (ext_sec->off & 0x03) { - elog(".BTF.ext %s section is not aligned to 4 bytes\n", + pr_debug(".BTF.ext %s section is not aligned to 4 bytes\n", ext_sec->desc); return -EINVAL; } - if (data_size < ext_sec->off || - ext_sec->len > data_size - ext_sec->off) { - elog("%s section (off:%u len:%u) is beyond the end of the ELF section .BTF.ext\n", - ext_sec->desc, ext_sec->off, ext_sec->len); + info = btf_ext->data + btf_ext->hdr->hdr_len + ext_sec->off; + info_left = ext_sec->len; + + if (btf_ext->data + btf_ext->data_size < info + ext_sec->len) { + pr_debug("%s section (off:%u len:%u) is beyond the end of the ELF section .BTF.ext\n", + ext_sec->desc, ext_sec->off, ext_sec->len); return -EINVAL; } - info = data + ext_sec->off; - info_left = ext_sec->len; - /* At least a record size */ if (info_left < sizeof(__u32)) { - elog(".BTF.ext %s record size not found\n", ext_sec->desc); + pr_debug(".BTF.ext %s record size not found\n", ext_sec->desc); return -EINVAL; } @@ -554,8 +635,8 @@ static int btf_ext_copy_info(struct btf_ext *btf_ext, record_size = *(__u32 *)info; if (record_size < ext_sec->min_rec_size || record_size & 0x03) { - elog("%s section in .BTF.ext has invalid record size %u\n", - ext_sec->desc, record_size); + pr_debug("%s section in .BTF.ext has invalid record size %u\n", + ext_sec->desc, record_size); return -EINVAL; } @@ -564,7 +645,7 @@ static int btf_ext_copy_info(struct btf_ext *btf_ext, /* If no records, return failure now so .BTF.ext won't be used. */ if (!info_left) { - elog("%s section in .BTF.ext has no records", ext_sec->desc); + pr_debug("%s section in .BTF.ext has no records", ext_sec->desc); return -EINVAL; } @@ -574,14 +655,14 @@ static int btf_ext_copy_info(struct btf_ext *btf_ext, __u32 num_records; if (info_left < sec_hdrlen) { - elog("%s section header is not found in .BTF.ext\n", + pr_debug("%s section header is not found in .BTF.ext\n", ext_sec->desc); return -EINVAL; } num_records = sinfo->num_info; if (num_records == 0) { - elog("%s section has incorrect num_records in .BTF.ext\n", + pr_debug("%s section has incorrect num_records in .BTF.ext\n", ext_sec->desc); return -EINVAL; } @@ -589,7 +670,7 @@ static int btf_ext_copy_info(struct btf_ext *btf_ext, total_record_size = sec_hdrlen + (__u64)num_records * record_size; if (info_left < total_record_size) { - elog("%s section has incorrect num_records in .BTF.ext\n", + pr_debug("%s section has incorrect num_records in .BTF.ext\n", ext_sec->desc); return -EINVAL; } @@ -601,74 +682,64 @@ static int btf_ext_copy_info(struct btf_ext *btf_ext, ext_info = ext_sec->ext_info; ext_info->len = ext_sec->len - sizeof(__u32); ext_info->rec_size = record_size; - ext_info->info = malloc(ext_info->len); - if (!ext_info->info) - return -ENOMEM; - memcpy(ext_info->info, info + sizeof(__u32), ext_info->len); + ext_info->info = info + sizeof(__u32); return 0; } -static int btf_ext_copy_func_info(struct btf_ext *btf_ext, - __u8 *data, __u32 data_size, - btf_print_fn_t err_log) +static int btf_ext_setup_func_info(struct btf_ext *btf_ext) { - const struct btf_ext_header *hdr = (struct btf_ext_header *)data; - struct btf_ext_sec_copy_param param = { - .off = hdr->func_info_off, - .len = hdr->func_info_len, + struct btf_ext_sec_setup_param param = { + .off = btf_ext->hdr->func_info_off, + .len = btf_ext->hdr->func_info_len, .min_rec_size = sizeof(struct bpf_func_info_min), .ext_info = &btf_ext->func_info, .desc = "func_info" }; - return btf_ext_copy_info(btf_ext, data, data_size, ¶m, err_log); + return btf_ext_setup_info(btf_ext, ¶m); } -static int btf_ext_copy_line_info(struct btf_ext *btf_ext, - __u8 *data, __u32 data_size, - btf_print_fn_t err_log) +static int btf_ext_setup_line_info(struct btf_ext *btf_ext) { - const struct btf_ext_header *hdr = (struct btf_ext_header *)data; - struct btf_ext_sec_copy_param param = { - .off = hdr->line_info_off, - .len = hdr->line_info_len, + struct btf_ext_sec_setup_param param = { + .off = btf_ext->hdr->line_info_off, + .len = btf_ext->hdr->line_info_len, .min_rec_size = sizeof(struct bpf_line_info_min), .ext_info = &btf_ext->line_info, .desc = "line_info", }; - return btf_ext_copy_info(btf_ext, data, data_size, ¶m, err_log); + return btf_ext_setup_info(btf_ext, ¶m); } -static int btf_ext_parse_hdr(__u8 *data, __u32 data_size, - btf_print_fn_t err_log) +static int btf_ext_parse_hdr(__u8 *data, __u32 data_size) { const struct btf_ext_header *hdr = (struct btf_ext_header *)data; if (data_size < offsetof(struct btf_ext_header, func_info_off) || data_size < hdr->hdr_len) { - elog("BTF.ext header not found"); + pr_debug("BTF.ext header not found"); return -EINVAL; } if (hdr->magic != BTF_MAGIC) { - elog("Invalid BTF.ext magic:%x\n", hdr->magic); + pr_debug("Invalid BTF.ext magic:%x\n", hdr->magic); return -EINVAL; } if (hdr->version != BTF_VERSION) { - elog("Unsupported BTF.ext version:%u\n", hdr->version); + pr_debug("Unsupported BTF.ext version:%u\n", hdr->version); return -ENOTSUP; } if (hdr->flags) { - elog("Unsupported BTF.ext flags:%x\n", hdr->flags); + pr_debug("Unsupported BTF.ext flags:%x\n", hdr->flags); return -ENOTSUP; } if (data_size == hdr->hdr_len) { - elog("BTF.ext has no data\n"); + pr_debug("BTF.ext has no data\n"); return -EINVAL; } @@ -679,18 +750,16 @@ void btf_ext__free(struct btf_ext *btf_ext) { if (!btf_ext) return; - - free(btf_ext->func_info.info); - free(btf_ext->line_info.info); + free(btf_ext->data); free(btf_ext); } -struct btf_ext *btf_ext__new(__u8 *data, __u32 size, btf_print_fn_t err_log) +struct btf_ext *btf_ext__new(__u8 *data, __u32 size) { struct btf_ext *btf_ext; int err; - err = btf_ext_parse_hdr(data, size, err_log); + err = btf_ext_parse_hdr(data, size); if (err) return ERR_PTR(err); @@ -698,13 +767,23 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size, btf_print_fn_t err_log) if (!btf_ext) return ERR_PTR(-ENOMEM); - err = btf_ext_copy_func_info(btf_ext, data, size, err_log); - if (err) { - btf_ext__free(btf_ext); - return ERR_PTR(err); + btf_ext->data_size = size; + btf_ext->data = malloc(size); + if (!btf_ext->data) { + err = -ENOMEM; + goto done; } + memcpy(btf_ext->data, data, size); - err = btf_ext_copy_line_info(btf_ext, data, size, err_log); + err = btf_ext_setup_func_info(btf_ext); + if (err) + goto done; + + err = btf_ext_setup_line_info(btf_ext); + if (err) + goto done; + +done: if (err) { btf_ext__free(btf_ext); return ERR_PTR(err); @@ -713,6 +792,12 @@ struct btf_ext *btf_ext__new(__u8 *data, __u32 size, btf_print_fn_t err_log) return btf_ext; } +const void *btf_ext__get_raw_data(const struct btf_ext *btf_ext, __u32 *size) +{ + *size = btf_ext->data_size; + return btf_ext->data; +} + static int btf_ext_reloc_info(const struct btf *btf, const struct btf_ext_info *ext_info, const char *sec_name, __u32 insns_cnt, @@ -761,7 +846,8 @@ static int btf_ext_reloc_info(const struct btf *btf, return -ENOENT; } -int btf_ext__reloc_func_info(const struct btf *btf, const struct btf_ext *btf_ext, +int btf_ext__reloc_func_info(const struct btf *btf, + const struct btf_ext *btf_ext, const char *sec_name, __u32 insns_cnt, void **func_info, __u32 *cnt) { @@ -769,7 +855,8 @@ int btf_ext__reloc_func_info(const struct btf *btf, const struct btf_ext *btf_ex insns_cnt, func_info, cnt); } -int btf_ext__reloc_line_info(const struct btf *btf, const struct btf_ext *btf_ext, +int btf_ext__reloc_line_info(const struct btf *btf, + const struct btf_ext *btf_ext, const char *sec_name, __u32 insns_cnt, void **line_info, __u32 *cnt) { @@ -786,3 +873,1744 @@ __u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext) { return btf_ext->line_info.rec_size; } + +struct btf_dedup; + +static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext, + const struct btf_dedup_opts *opts); +static void btf_dedup_free(struct btf_dedup *d); +static int btf_dedup_strings(struct btf_dedup *d); +static int btf_dedup_prim_types(struct btf_dedup *d); +static int btf_dedup_struct_types(struct btf_dedup *d); +static int btf_dedup_ref_types(struct btf_dedup *d); +static int btf_dedup_compact_types(struct btf_dedup *d); +static int btf_dedup_remap_types(struct btf_dedup *d); + +/* + * Deduplicate BTF types and strings. + * + * BTF dedup algorithm takes as an input `struct btf` representing `.BTF` ELF + * section with all BTF type descriptors and string data. It overwrites that + * memory in-place with deduplicated types and strings without any loss of + * information. If optional `struct btf_ext` representing '.BTF.ext' ELF section + * is provided, all the strings referenced from .BTF.ext section are honored + * and updated to point to the right offsets after deduplication. + * + * If function returns with error, type/string data might be garbled and should + * be discarded. + * + * More verbose and detailed description of both problem btf_dedup is solving, + * as well as solution could be found at: + * https://facebookmicrosites.github.io/bpf/blog/2018/11/14/btf-enhancement.html + * + * Problem description and justification + * ===================================== + * + * BTF type information is typically emitted either as a result of conversion + * from DWARF to BTF or directly by compiler. In both cases, each compilation + * unit contains information about a subset of all the types that are used + * in an application. These subsets are frequently overlapping and contain a lot + * of duplicated information when later concatenated together into a single + * binary. This algorithm ensures that each unique type is represented by single + * BTF type descriptor, greatly reducing resulting size of BTF data. + * + * Compilation unit isolation and subsequent duplication of data is not the only + * problem. The same type hierarchy (e.g., struct and all the type that struct + * references) in different compilation units can be represented in BTF to + * various degrees of completeness (or, rather, incompleteness) due to + * struct/union forward declarations. + * + * Let's take a look at an example, that we'll use to better understand the + * problem (and solution). Suppose we have two compilation units, each using + * same `struct S`, but each of them having incomplete type information about + * struct's fields: + * + * // CU #1: + * struct S; + * struct A { + * int a; + * struct A* self; + * struct S* parent; + * }; + * struct B; + * struct S { + * struct A* a_ptr; + * struct B* b_ptr; + * }; + * + * // CU #2: + * struct S; + * struct A; + * struct B { + * int b; + * struct B* self; + * struct S* parent; + * }; + * struct S { + * struct A* a_ptr; + * struct B* b_ptr; + * }; + * + * In case of CU #1, BTF data will know only that `struct B` exist (but no + * more), but will know the complete type information about `struct A`. While + * for CU #2, it will know full type information about `struct B`, but will + * only know about forward declaration of `struct A` (in BTF terms, it will + * have `BTF_KIND_FWD` type descriptor with name `B`). + * + * This compilation unit isolation means that it's possible that there is no + * single CU with complete type information describing structs `S`, `A`, and + * `B`. Also, we might get tons of duplicated and redundant type information. + * + * Additional complication we need to keep in mind comes from the fact that + * types, in general, can form graphs containing cycles, not just DAGs. + * + * While algorithm does deduplication, it also merges and resolves type + * information (unless disabled throught `struct btf_opts`), whenever possible. + * E.g., in the example above with two compilation units having partial type + * information for structs `A` and `B`, the output of algorithm will emit + * a single copy of each BTF type that describes structs `A`, `B`, and `S` + * (as well as type information for `int` and pointers), as if they were defined + * in a single compilation unit as: + * + * struct A { + * int a; + * struct A* self; + * struct S* parent; + * }; + * struct B { + * int b; + * struct B* self; + * struct S* parent; + * }; + * struct S { + * struct A* a_ptr; + * struct B* b_ptr; + * }; + * + * Algorithm summary + * ================= + * + * Algorithm completes its work in 6 separate passes: + * + * 1. Strings deduplication. + * 2. Primitive types deduplication (int, enum, fwd). + * 3. Struct/union types deduplication. + * 4. Reference types deduplication (pointers, typedefs, arrays, funcs, func + * protos, and const/volatile/restrict modifiers). + * 5. Types compaction. + * 6. Types remapping. + * + * Algorithm determines canonical type descriptor, which is a single + * representative type for each truly unique type. This canonical type is the + * one that will go into final deduplicated BTF type information. For + * struct/unions, it is also the type that algorithm will merge additional type + * information into (while resolving FWDs), as it discovers it from data in + * other CUs. Each input BTF type eventually gets either mapped to itself, if + * that type is canonical, or to some other type, if that type is equivalent + * and was chosen as canonical representative. This mapping is stored in + * `btf_dedup->map` array. This map is also used to record STRUCT/UNION that + * FWD type got resolved to. + * + * To facilitate fast discovery of canonical types, we also maintain canonical + * index (`btf_dedup->dedup_table`), which maps type descriptor's signature hash + * (i.e., hashed kind, name, size, fields, etc) into a list of canonical types + * that match that signature. With sufficiently good choice of type signature + * hashing function, we can limit number of canonical types for each unique type + * signature to a very small number, allowing to find canonical type for any + * duplicated type very quickly. + * + * Struct/union deduplication is the most critical part and algorithm for + * deduplicating structs/unions is described in greater details in comments for + * `btf_dedup_is_equiv` function. + */ +int btf__dedup(struct btf *btf, struct btf_ext *btf_ext, + const struct btf_dedup_opts *opts) +{ + struct btf_dedup *d = btf_dedup_new(btf, btf_ext, opts); + int err; + + if (IS_ERR(d)) { + pr_debug("btf_dedup_new failed: %ld", PTR_ERR(d)); + return -EINVAL; + } + + err = btf_dedup_strings(d); + if (err < 0) { + pr_debug("btf_dedup_strings failed:%d\n", err); + goto done; + } + err = btf_dedup_prim_types(d); + if (err < 0) { + pr_debug("btf_dedup_prim_types failed:%d\n", err); + goto done; + } + err = btf_dedup_struct_types(d); + if (err < 0) { + pr_debug("btf_dedup_struct_types failed:%d\n", err); + goto done; + } + err = btf_dedup_ref_types(d); + if (err < 0) { + pr_debug("btf_dedup_ref_types failed:%d\n", err); + goto done; + } + err = btf_dedup_compact_types(d); + if (err < 0) { + pr_debug("btf_dedup_compact_types failed:%d\n", err); + goto done; + } + err = btf_dedup_remap_types(d); + if (err < 0) { + pr_debug("btf_dedup_remap_types failed:%d\n", err); + goto done; + } + +done: + btf_dedup_free(d); + return err; +} + +#define BTF_DEDUP_TABLE_SIZE_LOG 14 +#define BTF_DEDUP_TABLE_MOD ((1 << BTF_DEDUP_TABLE_SIZE_LOG) - 1) +#define BTF_UNPROCESSED_ID ((__u32)-1) +#define BTF_IN_PROGRESS_ID ((__u32)-2) + +struct btf_dedup_node { + struct btf_dedup_node *next; + __u32 type_id; +}; + +struct btf_dedup { + /* .BTF section to be deduped in-place */ + struct btf *btf; + /* + * Optional .BTF.ext section. When provided, any strings referenced + * from it will be taken into account when deduping strings + */ + struct btf_ext *btf_ext; + /* + * This is a map from any type's signature hash to a list of possible + * canonical representative type candidates. Hash collisions are + * ignored, so even types of various kinds can share same list of + * candidates, which is fine because we rely on subsequent + * btf_xxx_equal() checks to authoritatively verify type equality. + */ + struct btf_dedup_node **dedup_table; + /* Canonical types map */ + __u32 *map; + /* Hypothetical mapping, used during type graph equivalence checks */ + __u32 *hypot_map; + __u32 *hypot_list; + size_t hypot_cnt; + size_t hypot_cap; + /* Various option modifying behavior of algorithm */ + struct btf_dedup_opts opts; +}; + +struct btf_str_ptr { + const char *str; + __u32 new_off; + bool used; +}; + +struct btf_str_ptrs { + struct btf_str_ptr *ptrs; + const char *data; + __u32 cnt; + __u32 cap; +}; + +static inline __u32 hash_combine(__u32 h, __u32 value) +{ +/* 2^31 + 2^29 - 2^25 + 2^22 - 2^19 - 2^16 + 1 */ +#define GOLDEN_RATIO_PRIME 0x9e370001UL + return h * 37 + value * GOLDEN_RATIO_PRIME; +#undef GOLDEN_RATIO_PRIME +} + +#define for_each_hash_node(table, hash, node) \ + for (node = table[hash & BTF_DEDUP_TABLE_MOD]; node; node = node->next) + +static int btf_dedup_table_add(struct btf_dedup *d, __u32 hash, __u32 type_id) +{ + struct btf_dedup_node *node = malloc(sizeof(struct btf_dedup_node)); + + if (!node) + return -ENOMEM; + node->type_id = type_id; + node->next = d->dedup_table[hash & BTF_DEDUP_TABLE_MOD]; + d->dedup_table[hash & BTF_DEDUP_TABLE_MOD] = node; + return 0; +} + +static int btf_dedup_hypot_map_add(struct btf_dedup *d, + __u32 from_id, __u32 to_id) +{ + if (d->hypot_cnt == d->hypot_cap) { + __u32 *new_list; + + d->hypot_cap += max(16, d->hypot_cap / 2); + new_list = realloc(d->hypot_list, sizeof(__u32) * d->hypot_cap); + if (!new_list) + return -ENOMEM; + d->hypot_list = new_list; + } + d->hypot_list[d->hypot_cnt++] = from_id; + d->hypot_map[from_id] = to_id; + return 0; +} + +static void btf_dedup_clear_hypot_map(struct btf_dedup *d) +{ + int i; + + for (i = 0; i < d->hypot_cnt; i++) + d->hypot_map[d->hypot_list[i]] = BTF_UNPROCESSED_ID; + d->hypot_cnt = 0; +} + +static void btf_dedup_table_free(struct btf_dedup *d) +{ + struct btf_dedup_node *head, *tmp; + int i; + + if (!d->dedup_table) + return; + + for (i = 0; i < (1 << BTF_DEDUP_TABLE_SIZE_LOG); i++) { + while (d->dedup_table[i]) { + tmp = d->dedup_table[i]; + d->dedup_table[i] = tmp->next; + free(tmp); + } + + head = d->dedup_table[i]; + while (head) { + tmp = head; + head = head->next; + free(tmp); + } + } + + free(d->dedup_table); + d->dedup_table = NULL; +} + +static void btf_dedup_free(struct btf_dedup *d) +{ + btf_dedup_table_free(d); + + free(d->map); + d->map = NULL; + + free(d->hypot_map); + d->hypot_map = NULL; + + free(d->hypot_list); + d->hypot_list = NULL; + + free(d); +} + +static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext, + const struct btf_dedup_opts *opts) +{ + struct btf_dedup *d = calloc(1, sizeof(struct btf_dedup)); + int i, err = 0; + + if (!d) + return ERR_PTR(-ENOMEM); + + d->btf = btf; + d->btf_ext = btf_ext; + + d->dedup_table = calloc(1 << BTF_DEDUP_TABLE_SIZE_LOG, + sizeof(struct btf_dedup_node *)); + if (!d->dedup_table) { + err = -ENOMEM; + goto done; + } + + d->map = malloc(sizeof(__u32) * (1 + btf->nr_types)); + if (!d->map) { + err = -ENOMEM; + goto done; + } + /* special BTF "void" type is made canonical immediately */ + d->map[0] = 0; + for (i = 1; i <= btf->nr_types; i++) + d->map[i] = BTF_UNPROCESSED_ID; + + d->hypot_map = malloc(sizeof(__u32) * (1 + btf->nr_types)); + if (!d->hypot_map) { + err = -ENOMEM; + goto done; + } + for (i = 0; i <= btf->nr_types; i++) + d->hypot_map[i] = BTF_UNPROCESSED_ID; + + d->opts.dont_resolve_fwds = opts && opts->dont_resolve_fwds; + +done: + if (err) { + btf_dedup_free(d); + return ERR_PTR(err); + } + + return d; +} + +typedef int (*str_off_fn_t)(__u32 *str_off_ptr, void *ctx); + +/* + * Iterate over all possible places in .BTF and .BTF.ext that can reference + * string and pass pointer to it to a provided callback `fn`. + */ +static int btf_for_each_str_off(struct btf_dedup *d, str_off_fn_t fn, void *ctx) +{ + void *line_data_cur, *line_data_end; + int i, j, r, rec_size; + struct btf_type *t; + + for (i = 1; i <= d->btf->nr_types; i++) { + t = d->btf->types[i]; + r = fn(&t->name_off, ctx); + if (r) + return r; + + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: { + struct btf_member *m = (struct btf_member *)(t + 1); + __u16 vlen = BTF_INFO_VLEN(t->info); + + for (j = 0; j < vlen; j++) { + r = fn(&m->name_off, ctx); + if (r) + return r; + m++; + } + break; + } + case BTF_KIND_ENUM: { + struct btf_enum *m = (struct btf_enum *)(t + 1); + __u16 vlen = BTF_INFO_VLEN(t->info); + + for (j = 0; j < vlen; j++) { + r = fn(&m->name_off, ctx); + if (r) + return r; + m++; + } + break; + } + case BTF_KIND_FUNC_PROTO: { + struct btf_param *m = (struct btf_param *)(t + 1); + __u16 vlen = BTF_INFO_VLEN(t->info); + + for (j = 0; j < vlen; j++) { + r = fn(&m->name_off, ctx); + if (r) + return r; + m++; + } + break; + } + default: + break; + } + } + + if (!d->btf_ext) + return 0; + + line_data_cur = d->btf_ext->line_info.info; + line_data_end = d->btf_ext->line_info.info + d->btf_ext->line_info.len; + rec_size = d->btf_ext->line_info.rec_size; + + while (line_data_cur < line_data_end) { + struct btf_ext_info_sec *sec = line_data_cur; + struct bpf_line_info_min *line_info; + __u32 num_info = sec->num_info; + + r = fn(&sec->sec_name_off, ctx); + if (r) + return r; + + line_data_cur += sizeof(struct btf_ext_info_sec); + for (i = 0; i < num_info; i++) { + line_info = line_data_cur; + r = fn(&line_info->file_name_off, ctx); + if (r) + return r; + r = fn(&line_info->line_off, ctx); + if (r) + return r; + line_data_cur += rec_size; + } + } + + return 0; +} + +static int str_sort_by_content(const void *a1, const void *a2) +{ + const struct btf_str_ptr *p1 = a1; + const struct btf_str_ptr *p2 = a2; + + return strcmp(p1->str, p2->str); +} + +static int str_sort_by_offset(const void *a1, const void *a2) +{ + const struct btf_str_ptr *p1 = a1; + const struct btf_str_ptr *p2 = a2; + + if (p1->str != p2->str) + return p1->str < p2->str ? -1 : 1; + return 0; +} + +static int btf_dedup_str_ptr_cmp(const void *str_ptr, const void *pelem) +{ + const struct btf_str_ptr *p = pelem; + + if (str_ptr != p->str) + return (const char *)str_ptr < p->str ? -1 : 1; + return 0; +} + +static int btf_str_mark_as_used(__u32 *str_off_ptr, void *ctx) +{ + struct btf_str_ptrs *strs; + struct btf_str_ptr *s; + + if (*str_off_ptr == 0) + return 0; + + strs = ctx; + s = bsearch(strs->data + *str_off_ptr, strs->ptrs, strs->cnt, + sizeof(struct btf_str_ptr), btf_dedup_str_ptr_cmp); + if (!s) + return -EINVAL; + s->used = true; + return 0; +} + +static int btf_str_remap_offset(__u32 *str_off_ptr, void *ctx) +{ + struct btf_str_ptrs *strs; + struct btf_str_ptr *s; + + if (*str_off_ptr == 0) + return 0; + + strs = ctx; + s = bsearch(strs->data + *str_off_ptr, strs->ptrs, strs->cnt, + sizeof(struct btf_str_ptr), btf_dedup_str_ptr_cmp); + if (!s) + return -EINVAL; + *str_off_ptr = s->new_off; + return 0; +} + +/* + * Dedup string and filter out those that are not referenced from either .BTF + * or .BTF.ext (if provided) sections. + * + * This is done by building index of all strings in BTF's string section, + * then iterating over all entities that can reference strings (e.g., type + * names, struct field names, .BTF.ext line info, etc) and marking corresponding + * strings as used. After that all used strings are deduped and compacted into + * sequential blob of memory and new offsets are calculated. Then all the string + * references are iterated again and rewritten using new offsets. + */ +static int btf_dedup_strings(struct btf_dedup *d) +{ + const struct btf_header *hdr = d->btf->hdr; + char *start = (char *)d->btf->nohdr_data + hdr->str_off; + char *end = start + d->btf->hdr->str_len; + char *p = start, *tmp_strs = NULL; + struct btf_str_ptrs strs = { + .cnt = 0, + .cap = 0, + .ptrs = NULL, + .data = start, + }; + int i, j, err = 0, grp_idx; + bool grp_used; + + /* build index of all strings */ + while (p < end) { + if (strs.cnt + 1 > strs.cap) { + struct btf_str_ptr *new_ptrs; + + strs.cap += max(strs.cnt / 2, 16); + new_ptrs = realloc(strs.ptrs, + sizeof(strs.ptrs[0]) * strs.cap); + if (!new_ptrs) { + err = -ENOMEM; + goto done; + } + strs.ptrs = new_ptrs; + } + + strs.ptrs[strs.cnt].str = p; + strs.ptrs[strs.cnt].used = false; + + p += strlen(p) + 1; + strs.cnt++; + } + + /* temporary storage for deduplicated strings */ + tmp_strs = malloc(d->btf->hdr->str_len); + if (!tmp_strs) { + err = -ENOMEM; + goto done; + } + + /* mark all used strings */ + strs.ptrs[0].used = true; + err = btf_for_each_str_off(d, btf_str_mark_as_used, &strs); + if (err) + goto done; + + /* sort strings by context, so that we can identify duplicates */ + qsort(strs.ptrs, strs.cnt, sizeof(strs.ptrs[0]), str_sort_by_content); + + /* + * iterate groups of equal strings and if any instance in a group was + * referenced, emit single instance and remember new offset + */ + p = tmp_strs; + grp_idx = 0; + grp_used = strs.ptrs[0].used; + /* iterate past end to avoid code duplication after loop */ + for (i = 1; i <= strs.cnt; i++) { + /* + * when i == strs.cnt, we want to skip string comparison and go + * straight to handling last group of strings (otherwise we'd + * need to handle last group after the loop w/ duplicated code) + */ + if (i < strs.cnt && + !strcmp(strs.ptrs[i].str, strs.ptrs[grp_idx].str)) { + grp_used = grp_used || strs.ptrs[i].used; + continue; + } + + /* + * this check would have been required after the loop to handle + * last group of strings, but due to <= condition in a loop + * we avoid that duplication + */ + if (grp_used) { + int new_off = p - tmp_strs; + __u32 len = strlen(strs.ptrs[grp_idx].str); + + memmove(p, strs.ptrs[grp_idx].str, len + 1); + for (j = grp_idx; j < i; j++) + strs.ptrs[j].new_off = new_off; + p += len + 1; + } + + if (i < strs.cnt) { + grp_idx = i; + grp_used = strs.ptrs[i].used; + } + } + + /* replace original strings with deduped ones */ + d->btf->hdr->str_len = p - tmp_strs; + memmove(start, tmp_strs, d->btf->hdr->str_len); + end = start + d->btf->hdr->str_len; + + /* restore original order for further binary search lookups */ + qsort(strs.ptrs, strs.cnt, sizeof(strs.ptrs[0]), str_sort_by_offset); + + /* remap string offsets */ + err = btf_for_each_str_off(d, btf_str_remap_offset, &strs); + if (err) + goto done; + + d->btf->hdr->str_len = end - start; + +done: + free(tmp_strs); + free(strs.ptrs); + return err; +} + +static __u32 btf_hash_common(struct btf_type *t) +{ + __u32 h; + + h = hash_combine(0, t->name_off); + h = hash_combine(h, t->info); + h = hash_combine(h, t->size); + return h; +} + +static bool btf_equal_common(struct btf_type *t1, struct btf_type *t2) +{ + return t1->name_off == t2->name_off && + t1->info == t2->info && + t1->size == t2->size; +} + +/* Calculate type signature hash of INT. */ +static __u32 btf_hash_int(struct btf_type *t) +{ + __u32 info = *(__u32 *)(t + 1); + __u32 h; + + h = btf_hash_common(t); + h = hash_combine(h, info); + return h; +} + +/* Check structural equality of two INTs. */ +static bool btf_equal_int(struct btf_type *t1, struct btf_type *t2) +{ + __u32 info1, info2; + + if (!btf_equal_common(t1, t2)) + return false; + info1 = *(__u32 *)(t1 + 1); + info2 = *(__u32 *)(t2 + 1); + return info1 == info2; +} + +/* Calculate type signature hash of ENUM. */ +static __u32 btf_hash_enum(struct btf_type *t) +{ + struct btf_enum *member = (struct btf_enum *)(t + 1); + __u32 vlen = BTF_INFO_VLEN(t->info); + __u32 h = btf_hash_common(t); + int i; + + for (i = 0; i < vlen; i++) { + h = hash_combine(h, member->name_off); + h = hash_combine(h, member->val); + member++; + } + return h; +} + +/* Check structural equality of two ENUMs. */ +static bool btf_equal_enum(struct btf_type *t1, struct btf_type *t2) +{ + struct btf_enum *m1, *m2; + __u16 vlen; + int i; + + if (!btf_equal_common(t1, t2)) + return false; + + vlen = BTF_INFO_VLEN(t1->info); + m1 = (struct btf_enum *)(t1 + 1); + m2 = (struct btf_enum *)(t2 + 1); + for (i = 0; i < vlen; i++) { + if (m1->name_off != m2->name_off || m1->val != m2->val) + return false; + m1++; + m2++; + } + return true; +} + +/* + * Calculate type signature hash of STRUCT/UNION, ignoring referenced type IDs, + * as referenced type IDs equivalence is established separately during type + * graph equivalence check algorithm. + */ +static __u32 btf_hash_struct(struct btf_type *t) +{ + struct btf_member *member = (struct btf_member *)(t + 1); + __u32 vlen = BTF_INFO_VLEN(t->info); + __u32 h = btf_hash_common(t); + int i; + + for (i = 0; i < vlen; i++) { + h = hash_combine(h, member->name_off); + h = hash_combine(h, member->offset); + /* no hashing of referenced type ID, it can be unresolved yet */ + member++; + } + return h; +} + +/* + * Check structural compatibility of two FUNC_PROTOs, ignoring referenced type + * IDs. This check is performed during type graph equivalence check and + * referenced types equivalence is checked separately. + */ +static bool btf_equal_struct(struct btf_type *t1, struct btf_type *t2) +{ + struct btf_member *m1, *m2; + __u16 vlen; + int i; + + if (!btf_equal_common(t1, t2)) + return false; + + vlen = BTF_INFO_VLEN(t1->info); + m1 = (struct btf_member *)(t1 + 1); + m2 = (struct btf_member *)(t2 + 1); + for (i = 0; i < vlen; i++) { + if (m1->name_off != m2->name_off || m1->offset != m2->offset) + return false; + m1++; + m2++; + } + return true; +} + +/* + * Calculate type signature hash of ARRAY, including referenced type IDs, + * under assumption that they were already resolved to canonical type IDs and + * are not going to change. + */ +static __u32 btf_hash_array(struct btf_type *t) +{ + struct btf_array *info = (struct btf_array *)(t + 1); + __u32 h = btf_hash_common(t); + + h = hash_combine(h, info->type); + h = hash_combine(h, info->index_type); + h = hash_combine(h, info->nelems); + return h; +} + +/* + * Check exact equality of two ARRAYs, taking into account referenced + * type IDs, under assumption that they were already resolved to canonical + * type IDs and are not going to change. + * This function is called during reference types deduplication to compare + * ARRAY to potential canonical representative. + */ +static bool btf_equal_array(struct btf_type *t1, struct btf_type *t2) +{ + struct btf_array *info1, *info2; + + if (!btf_equal_common(t1, t2)) + return false; + + info1 = (struct btf_array *)(t1 + 1); + info2 = (struct btf_array *)(t2 + 1); + return info1->type == info2->type && + info1->index_type == info2->index_type && + info1->nelems == info2->nelems; +} + +/* + * Check structural compatibility of two ARRAYs, ignoring referenced type + * IDs. This check is performed during type graph equivalence check and + * referenced types equivalence is checked separately. + */ +static bool btf_compat_array(struct btf_type *t1, struct btf_type *t2) +{ + struct btf_array *info1, *info2; + + if (!btf_equal_common(t1, t2)) + return false; + + info1 = (struct btf_array *)(t1 + 1); + info2 = (struct btf_array *)(t2 + 1); + return info1->nelems == info2->nelems; +} + +/* + * Calculate type signature hash of FUNC_PROTO, including referenced type IDs, + * under assumption that they were already resolved to canonical type IDs and + * are not going to change. + */ +static inline __u32 btf_hash_fnproto(struct btf_type *t) +{ + struct btf_param *member = (struct btf_param *)(t + 1); + __u16 vlen = BTF_INFO_VLEN(t->info); + __u32 h = btf_hash_common(t); + int i; + + for (i = 0; i < vlen; i++) { + h = hash_combine(h, member->name_off); + h = hash_combine(h, member->type); + member++; + } + return h; +} + +/* + * Check exact equality of two FUNC_PROTOs, taking into account referenced + * type IDs, under assumption that they were already resolved to canonical + * type IDs and are not going to change. + * This function is called during reference types deduplication to compare + * FUNC_PROTO to potential canonical representative. + */ +static inline bool btf_equal_fnproto(struct btf_type *t1, struct btf_type *t2) +{ + struct btf_param *m1, *m2; + __u16 vlen; + int i; + + if (!btf_equal_common(t1, t2)) + return false; + + vlen = BTF_INFO_VLEN(t1->info); + m1 = (struct btf_param *)(t1 + 1); + m2 = (struct btf_param *)(t2 + 1); + for (i = 0; i < vlen; i++) { + if (m1->name_off != m2->name_off || m1->type != m2->type) + return false; + m1++; + m2++; + } + return true; +} + +/* + * Check structural compatibility of two FUNC_PROTOs, ignoring referenced type + * IDs. This check is performed during type graph equivalence check and + * referenced types equivalence is checked separately. + */ +static inline bool btf_compat_fnproto(struct btf_type *t1, struct btf_type *t2) +{ + struct btf_param *m1, *m2; + __u16 vlen; + int i; + + /* skip return type ID */ + if (t1->name_off != t2->name_off || t1->info != t2->info) + return false; + + vlen = BTF_INFO_VLEN(t1->info); + m1 = (struct btf_param *)(t1 + 1); + m2 = (struct btf_param *)(t2 + 1); + for (i = 0; i < vlen; i++) { + if (m1->name_off != m2->name_off) + return false; + m1++; + m2++; + } + return true; +} + +/* + * Deduplicate primitive types, that can't reference other types, by calculating + * their type signature hash and comparing them with any possible canonical + * candidate. If no canonical candidate matches, type itself is marked as + * canonical and is added into `btf_dedup->dedup_table` as another candidate. + */ +static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id) +{ + struct btf_type *t = d->btf->types[type_id]; + struct btf_type *cand; + struct btf_dedup_node *cand_node; + /* if we don't find equivalent type, then we are canonical */ + __u32 new_id = type_id; + __u32 h; + + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_CONST: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_PTR: + case BTF_KIND_TYPEDEF: + case BTF_KIND_ARRAY: + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + case BTF_KIND_FUNC: + case BTF_KIND_FUNC_PROTO: + return 0; + + case BTF_KIND_INT: + h = btf_hash_int(t); + for_each_hash_node(d->dedup_table, h, cand_node) { + cand = d->btf->types[cand_node->type_id]; + if (btf_equal_int(t, cand)) { + new_id = cand_node->type_id; + break; + } + } + break; + + case BTF_KIND_ENUM: + h = btf_hash_enum(t); + for_each_hash_node(d->dedup_table, h, cand_node) { + cand = d->btf->types[cand_node->type_id]; + if (btf_equal_enum(t, cand)) { + new_id = cand_node->type_id; + break; + } + } + break; + + case BTF_KIND_FWD: + h = btf_hash_common(t); + for_each_hash_node(d->dedup_table, h, cand_node) { + cand = d->btf->types[cand_node->type_id]; + if (btf_equal_common(t, cand)) { + new_id = cand_node->type_id; + break; + } + } + break; + + default: + return -EINVAL; + } + + d->map[type_id] = new_id; + if (type_id == new_id && btf_dedup_table_add(d, h, type_id)) + return -ENOMEM; + + return 0; +} + +static int btf_dedup_prim_types(struct btf_dedup *d) +{ + int i, err; + + for (i = 1; i <= d->btf->nr_types; i++) { + err = btf_dedup_prim_type(d, i); + if (err) + return err; + } + return 0; +} + +/* + * Check whether type is already mapped into canonical one (could be to itself). + */ +static inline bool is_type_mapped(struct btf_dedup *d, uint32_t type_id) +{ + return d->map[type_id] <= BTF_MAX_NR_TYPES; +} + +/* + * Resolve type ID into its canonical type ID, if any; otherwise return original + * type ID. If type is FWD and is resolved into STRUCT/UNION already, follow + * STRUCT/UNION link and resolve it into canonical type ID as well. + */ +static inline __u32 resolve_type_id(struct btf_dedup *d, __u32 type_id) +{ + while (is_type_mapped(d, type_id) && d->map[type_id] != type_id) + type_id = d->map[type_id]; + return type_id; +} + +/* + * Resolve FWD to underlying STRUCT/UNION, if any; otherwise return original + * type ID. + */ +static uint32_t resolve_fwd_id(struct btf_dedup *d, uint32_t type_id) +{ + __u32 orig_type_id = type_id; + + if (BTF_INFO_KIND(d->btf->types[type_id]->info) != BTF_KIND_FWD) + return type_id; + + while (is_type_mapped(d, type_id) && d->map[type_id] != type_id) + type_id = d->map[type_id]; + + if (BTF_INFO_KIND(d->btf->types[type_id]->info) != BTF_KIND_FWD) + return type_id; + + return orig_type_id; +} + + +static inline __u16 btf_fwd_kind(struct btf_type *t) +{ + return BTF_INFO_KFLAG(t->info) ? BTF_KIND_UNION : BTF_KIND_STRUCT; +} + +/* + * Check equivalence of BTF type graph formed by candidate struct/union (we'll + * call it "candidate graph" in this description for brevity) to a type graph + * formed by (potential) canonical struct/union ("canonical graph" for brevity + * here, though keep in mind that not all types in canonical graph are + * necessarily canonical representatives themselves, some of them might be + * duplicates or its uniqueness might not have been established yet). + * Returns: + * - >0, if type graphs are equivalent; + * - 0, if not equivalent; + * - <0, on error. + * + * Algorithm performs side-by-side DFS traversal of both type graphs and checks + * equivalence of BTF types at each step. If at any point BTF types in candidate + * and canonical graphs are not compatible structurally, whole graphs are + * incompatible. If types are structurally equivalent (i.e., all information + * except referenced type IDs is exactly the same), a mapping from `canon_id` to + * a `cand_id` is recored in hypothetical mapping (`btf_dedup->hypot_map`). + * If a type references other types, then those referenced types are checked + * for equivalence recursively. + * + * During DFS traversal, if we find that for current `canon_id` type we + * already have some mapping in hypothetical map, we check for two possible + * situations: + * - `canon_id` is mapped to exactly the same type as `cand_id`. This will + * happen when type graphs have cycles. In this case we assume those two + * types are equivalent. + * - `canon_id` is mapped to different type. This is contradiction in our + * hypothetical mapping, because same graph in canonical graph corresponds + * to two different types in candidate graph, which for equivalent type + * graphs shouldn't happen. This condition terminates equivalence check + * with negative result. + * + * If type graphs traversal exhausts types to check and find no contradiction, + * then type graphs are equivalent. + * + * When checking types for equivalence, there is one special case: FWD types. + * If FWD type resolution is allowed and one of the types (either from canonical + * or candidate graph) is FWD and other is STRUCT/UNION (depending on FWD's kind + * flag) and their names match, hypothetical mapping is updated to point from + * FWD to STRUCT/UNION. If graphs will be determined as equivalent successfully, + * this mapping will be used to record FWD -> STRUCT/UNION mapping permanently. + * + * Technically, this could lead to incorrect FWD to STRUCT/UNION resolution, + * if there are two exactly named (or anonymous) structs/unions that are + * compatible structurally, one of which has FWD field, while other is concrete + * STRUCT/UNION, but according to C sources they are different structs/unions + * that are referencing different types with the same name. This is extremely + * unlikely to happen, but btf_dedup API allows to disable FWD resolution if + * this logic is causing problems. + * + * Doing FWD resolution means that both candidate and/or canonical graphs can + * consists of portions of the graph that come from multiple compilation units. + * This is due to the fact that types within single compilation unit are always + * deduplicated and FWDs are already resolved, if referenced struct/union + * definiton is available. So, if we had unresolved FWD and found corresponding + * STRUCT/UNION, they will be from different compilation units. This + * consequently means that when we "link" FWD to corresponding STRUCT/UNION, + * type graph will likely have at least two different BTF types that describe + * same type (e.g., most probably there will be two different BTF types for the + * same 'int' primitive type) and could even have "overlapping" parts of type + * graph that describe same subset of types. + * + * This in turn means that our assumption that each type in canonical graph + * must correspond to exactly one type in candidate graph might not hold + * anymore and will make it harder to detect contradictions using hypothetical + * map. To handle this problem, we allow to follow FWD -> STRUCT/UNION + * resolution only in canonical graph. FWDs in candidate graphs are never + * resolved. To see why it's OK, let's check all possible situations w.r.t. FWDs + * that can occur: + * - Both types in canonical and candidate graphs are FWDs. If they are + * structurally equivalent, then they can either be both resolved to the + * same STRUCT/UNION or not resolved at all. In both cases they are + * equivalent and there is no need to resolve FWD on candidate side. + * - Both types in canonical and candidate graphs are concrete STRUCT/UNION, + * so nothing to resolve as well, algorithm will check equivalence anyway. + * - Type in canonical graph is FWD, while type in candidate is concrete + * STRUCT/UNION. In this case candidate graph comes from single compilation + * unit, so there is exactly one BTF type for each unique C type. After + * resolving FWD into STRUCT/UNION, there might be more than one BTF type + * in canonical graph mapping to single BTF type in candidate graph, but + * because hypothetical mapping maps from canonical to candidate types, it's + * alright, and we still maintain the property of having single `canon_id` + * mapping to single `cand_id` (there could be two different `canon_id` + * mapped to the same `cand_id`, but it's not contradictory). + * - Type in canonical graph is concrete STRUCT/UNION, while type in candidate + * graph is FWD. In this case we are just going to check compatibility of + * STRUCT/UNION and corresponding FWD, and if they are compatible, we'll + * assume that whatever STRUCT/UNION FWD resolves to must be equivalent to + * a concrete STRUCT/UNION from canonical graph. If the rest of type graphs + * turn out equivalent, we'll re-resolve FWD to concrete STRUCT/UNION from + * canonical graph. + */ +static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id, + __u32 canon_id) +{ + struct btf_type *cand_type; + struct btf_type *canon_type; + __u32 hypot_type_id; + __u16 cand_kind; + __u16 canon_kind; + int i, eq; + + /* if both resolve to the same canonical, they must be equivalent */ + if (resolve_type_id(d, cand_id) == resolve_type_id(d, canon_id)) + return 1; + + canon_id = resolve_fwd_id(d, canon_id); + + hypot_type_id = d->hypot_map[canon_id]; + if (hypot_type_id <= BTF_MAX_NR_TYPES) + return hypot_type_id == cand_id; + + if (btf_dedup_hypot_map_add(d, canon_id, cand_id)) + return -ENOMEM; + + cand_type = d->btf->types[cand_id]; + canon_type = d->btf->types[canon_id]; + cand_kind = BTF_INFO_KIND(cand_type->info); + canon_kind = BTF_INFO_KIND(canon_type->info); + + if (cand_type->name_off != canon_type->name_off) + return 0; + + /* FWD <--> STRUCT/UNION equivalence check, if enabled */ + if (!d->opts.dont_resolve_fwds + && (cand_kind == BTF_KIND_FWD || canon_kind == BTF_KIND_FWD) + && cand_kind != canon_kind) { + __u16 real_kind; + __u16 fwd_kind; + + if (cand_kind == BTF_KIND_FWD) { + real_kind = canon_kind; + fwd_kind = btf_fwd_kind(cand_type); + } else { + real_kind = cand_kind; + fwd_kind = btf_fwd_kind(canon_type); + } + return fwd_kind == real_kind; + } + + if (cand_type->info != canon_type->info) + return 0; + + switch (cand_kind) { + case BTF_KIND_INT: + return btf_equal_int(cand_type, canon_type); + + case BTF_KIND_ENUM: + return btf_equal_enum(cand_type, canon_type); + + case BTF_KIND_FWD: + return btf_equal_common(cand_type, canon_type); + + case BTF_KIND_CONST: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_PTR: + case BTF_KIND_TYPEDEF: + case BTF_KIND_FUNC: + return btf_dedup_is_equiv(d, cand_type->type, canon_type->type); + + case BTF_KIND_ARRAY: { + struct btf_array *cand_arr, *canon_arr; + + if (!btf_compat_array(cand_type, canon_type)) + return 0; + cand_arr = (struct btf_array *)(cand_type + 1); + canon_arr = (struct btf_array *)(canon_type + 1); + eq = btf_dedup_is_equiv(d, + cand_arr->index_type, canon_arr->index_type); + if (eq <= 0) + return eq; + return btf_dedup_is_equiv(d, cand_arr->type, canon_arr->type); + } + + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: { + struct btf_member *cand_m, *canon_m; + __u16 vlen; + + if (!btf_equal_struct(cand_type, canon_type)) + return 0; + vlen = BTF_INFO_VLEN(cand_type->info); + cand_m = (struct btf_member *)(cand_type + 1); + canon_m = (struct btf_member *)(canon_type + 1); + for (i = 0; i < vlen; i++) { + eq = btf_dedup_is_equiv(d, cand_m->type, canon_m->type); + if (eq <= 0) + return eq; + cand_m++; + canon_m++; + } + + return 1; + } + + case BTF_KIND_FUNC_PROTO: { + struct btf_param *cand_p, *canon_p; + __u16 vlen; + + if (!btf_compat_fnproto(cand_type, canon_type)) + return 0; + eq = btf_dedup_is_equiv(d, cand_type->type, canon_type->type); + if (eq <= 0) + return eq; + vlen = BTF_INFO_VLEN(cand_type->info); + cand_p = (struct btf_param *)(cand_type + 1); + canon_p = (struct btf_param *)(canon_type + 1); + for (i = 0; i < vlen; i++) { + eq = btf_dedup_is_equiv(d, cand_p->type, canon_p->type); + if (eq <= 0) + return eq; + cand_p++; + canon_p++; + } + return 1; + } + + default: + return -EINVAL; + } + return 0; +} + +/* + * Use hypothetical mapping, produced by successful type graph equivalence + * check, to augment existing struct/union canonical mapping, where possible. + * + * If BTF_KIND_FWD resolution is allowed, this mapping is also used to record + * FWD -> STRUCT/UNION correspondence as well. FWD resolution is bidirectional: + * it doesn't matter if FWD type was part of canonical graph or candidate one, + * we are recording the mapping anyway. As opposed to carefulness required + * for struct/union correspondence mapping (described below), for FWD resolution + * it's not important, as by the time that FWD type (reference type) will be + * deduplicated all structs/unions will be deduped already anyway. + * + * Recording STRUCT/UNION mapping is purely a performance optimization and is + * not required for correctness. It needs to be done carefully to ensure that + * struct/union from candidate's type graph is not mapped into corresponding + * struct/union from canonical type graph that itself hasn't been resolved into + * canonical representative. The only guarantee we have is that canonical + * struct/union was determined as canonical and that won't change. But any + * types referenced through that struct/union fields could have been not yet + * resolved, so in case like that it's too early to establish any kind of + * correspondence between structs/unions. + * + * No canonical correspondence is derived for primitive types (they are already + * deduplicated completely already anyway) or reference types (they rely on + * stability of struct/union canonical relationship for equivalence checks). + */ +static void btf_dedup_merge_hypot_map(struct btf_dedup *d) +{ + __u32 cand_type_id, targ_type_id; + __u16 t_kind, c_kind; + __u32 t_id, c_id; + int i; + + for (i = 0; i < d->hypot_cnt; i++) { + cand_type_id = d->hypot_list[i]; + targ_type_id = d->hypot_map[cand_type_id]; + t_id = resolve_type_id(d, targ_type_id); + c_id = resolve_type_id(d, cand_type_id); + t_kind = BTF_INFO_KIND(d->btf->types[t_id]->info); + c_kind = BTF_INFO_KIND(d->btf->types[c_id]->info); + /* + * Resolve FWD into STRUCT/UNION. + * It's ok to resolve FWD into STRUCT/UNION that's not yet + * mapped to canonical representative (as opposed to + * STRUCT/UNION <--> STRUCT/UNION mapping logic below), because + * eventually that struct is going to be mapped and all resolved + * FWDs will automatically resolve to correct canonical + * representative. This will happen before ref type deduping, + * which critically depends on stability of these mapping. This + * stability is not a requirement for STRUCT/UNION equivalence + * checks, though. + */ + if (t_kind != BTF_KIND_FWD && c_kind == BTF_KIND_FWD) + d->map[c_id] = t_id; + else if (t_kind == BTF_KIND_FWD && c_kind != BTF_KIND_FWD) + d->map[t_id] = c_id; + + if ((t_kind == BTF_KIND_STRUCT || t_kind == BTF_KIND_UNION) && + c_kind != BTF_KIND_FWD && + is_type_mapped(d, c_id) && + !is_type_mapped(d, t_id)) { + /* + * as a perf optimization, we can map struct/union + * that's part of type graph we just verified for + * equivalence. We can do that for struct/union that has + * canonical representative only, though. + */ + d->map[t_id] = c_id; + } + } +} + +/* + * Deduplicate struct/union types. + * + * For each struct/union type its type signature hash is calculated, taking + * into account type's name, size, number, order and names of fields, but + * ignoring type ID's referenced from fields, because they might not be deduped + * completely until after reference types deduplication phase. This type hash + * is used to iterate over all potential canonical types, sharing same hash. + * For each canonical candidate we check whether type graphs that they form + * (through referenced types in fields and so on) are equivalent using algorithm + * implemented in `btf_dedup_is_equiv`. If such equivalence is found and + * BTF_KIND_FWD resolution is allowed, then hypothetical mapping + * (btf_dedup->hypot_map) produced by aforementioned type graph equivalence + * algorithm is used to record FWD -> STRUCT/UNION mapping. It's also used to + * potentially map other structs/unions to their canonical representatives, + * if such relationship hasn't yet been established. This speeds up algorithm + * by eliminating some of the duplicate work. + * + * If no matching canonical representative was found, struct/union is marked + * as canonical for itself and is added into btf_dedup->dedup_table hash map + * for further look ups. + */ +static int btf_dedup_struct_type(struct btf_dedup *d, __u32 type_id) +{ + struct btf_dedup_node *cand_node; + struct btf_type *t; + /* if we don't find equivalent type, then we are canonical */ + __u32 new_id = type_id; + __u16 kind; + __u32 h; + + /* already deduped or is in process of deduping (loop detected) */ + if (d->map[type_id] <= BTF_MAX_NR_TYPES) + return 0; + + t = d->btf->types[type_id]; + kind = BTF_INFO_KIND(t->info); + + if (kind != BTF_KIND_STRUCT && kind != BTF_KIND_UNION) + return 0; + + h = btf_hash_struct(t); + for_each_hash_node(d->dedup_table, h, cand_node) { + int eq; + + btf_dedup_clear_hypot_map(d); + eq = btf_dedup_is_equiv(d, type_id, cand_node->type_id); + if (eq < 0) + return eq; + if (!eq) + continue; + new_id = cand_node->type_id; + btf_dedup_merge_hypot_map(d); + break; + } + + d->map[type_id] = new_id; + if (type_id == new_id && btf_dedup_table_add(d, h, type_id)) + return -ENOMEM; + + return 0; +} + +static int btf_dedup_struct_types(struct btf_dedup *d) +{ + int i, err; + + for (i = 1; i <= d->btf->nr_types; i++) { + err = btf_dedup_struct_type(d, i); + if (err) + return err; + } + return 0; +} + +/* + * Deduplicate reference type. + * + * Once all primitive and struct/union types got deduplicated, we can easily + * deduplicate all other (reference) BTF types. This is done in two steps: + * + * 1. Resolve all referenced type IDs into their canonical type IDs. This + * resolution can be done either immediately for primitive or struct/union types + * (because they were deduped in previous two phases) or recursively for + * reference types. Recursion will always terminate at either primitive or + * struct/union type, at which point we can "unwind" chain of reference types + * one by one. There is no danger of encountering cycles because in C type + * system the only way to form type cycle is through struct/union, so any chain + * of reference types, even those taking part in a type cycle, will inevitably + * reach struct/union at some point. + * + * 2. Once all referenced type IDs are resolved into canonical ones, BTF type + * becomes "stable", in the sense that no further deduplication will cause + * any changes to it. With that, it's now possible to calculate type's signature + * hash (this time taking into account referenced type IDs) and loop over all + * potential canonical representatives. If no match was found, current type + * will become canonical representative of itself and will be added into + * btf_dedup->dedup_table as another possible canonical representative. + */ +static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id) +{ + struct btf_dedup_node *cand_node; + struct btf_type *t, *cand; + /* if we don't find equivalent type, then we are representative type */ + __u32 new_id = type_id; + __u32 h, ref_type_id; + + if (d->map[type_id] == BTF_IN_PROGRESS_ID) + return -ELOOP; + if (d->map[type_id] <= BTF_MAX_NR_TYPES) + return resolve_type_id(d, type_id); + + t = d->btf->types[type_id]; + d->map[type_id] = BTF_IN_PROGRESS_ID; + + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_CONST: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_PTR: + case BTF_KIND_TYPEDEF: + case BTF_KIND_FUNC: + ref_type_id = btf_dedup_ref_type(d, t->type); + if (ref_type_id < 0) + return ref_type_id; + t->type = ref_type_id; + + h = btf_hash_common(t); + for_each_hash_node(d->dedup_table, h, cand_node) { + cand = d->btf->types[cand_node->type_id]; + if (btf_equal_common(t, cand)) { + new_id = cand_node->type_id; + break; + } + } + break; + + case BTF_KIND_ARRAY: { + struct btf_array *info = (struct btf_array *)(t + 1); + + ref_type_id = btf_dedup_ref_type(d, info->type); + if (ref_type_id < 0) + return ref_type_id; + info->type = ref_type_id; + + ref_type_id = btf_dedup_ref_type(d, info->index_type); + if (ref_type_id < 0) + return ref_type_id; + info->index_type = ref_type_id; + + h = btf_hash_array(t); + for_each_hash_node(d->dedup_table, h, cand_node) { + cand = d->btf->types[cand_node->type_id]; + if (btf_equal_array(t, cand)) { + new_id = cand_node->type_id; + break; + } + } + break; + } + + case BTF_KIND_FUNC_PROTO: { + struct btf_param *param; + __u16 vlen; + int i; + + ref_type_id = btf_dedup_ref_type(d, t->type); + if (ref_type_id < 0) + return ref_type_id; + t->type = ref_type_id; + + vlen = BTF_INFO_VLEN(t->info); + param = (struct btf_param *)(t + 1); + for (i = 0; i < vlen; i++) { + ref_type_id = btf_dedup_ref_type(d, param->type); + if (ref_type_id < 0) + return ref_type_id; + param->type = ref_type_id; + param++; + } + + h = btf_hash_fnproto(t); + for_each_hash_node(d->dedup_table, h, cand_node) { + cand = d->btf->types[cand_node->type_id]; + if (btf_equal_fnproto(t, cand)) { + new_id = cand_node->type_id; + break; + } + } + break; + } + + default: + return -EINVAL; + } + + d->map[type_id] = new_id; + if (type_id == new_id && btf_dedup_table_add(d, h, type_id)) + return -ENOMEM; + + return new_id; +} + +static int btf_dedup_ref_types(struct btf_dedup *d) +{ + int i, err; + + for (i = 1; i <= d->btf->nr_types; i++) { + err = btf_dedup_ref_type(d, i); + if (err < 0) + return err; + } + btf_dedup_table_free(d); + return 0; +} + +/* + * Compact types. + * + * After we established for each type its corresponding canonical representative + * type, we now can eliminate types that are not canonical and leave only + * canonical ones layed out sequentially in memory by copying them over + * duplicates. During compaction btf_dedup->hypot_map array is reused to store + * a map from original type ID to a new compacted type ID, which will be used + * during next phase to "fix up" type IDs, referenced from struct/union and + * reference types. + */ +static int btf_dedup_compact_types(struct btf_dedup *d) +{ + struct btf_type **new_types; + __u32 next_type_id = 1; + char *types_start, *p; + int i, len; + + /* we are going to reuse hypot_map to store compaction remapping */ + d->hypot_map[0] = 0; + for (i = 1; i <= d->btf->nr_types; i++) + d->hypot_map[i] = BTF_UNPROCESSED_ID; + + types_start = d->btf->nohdr_data + d->btf->hdr->type_off; + p = types_start; + + for (i = 1; i <= d->btf->nr_types; i++) { + if (d->map[i] != i) + continue; + + len = btf_type_size(d->btf->types[i]); + if (len < 0) + return len; + + memmove(p, d->btf->types[i], len); + d->hypot_map[i] = next_type_id; + d->btf->types[next_type_id] = (struct btf_type *)p; + p += len; + next_type_id++; + } + + /* shrink struct btf's internal types index and update btf_header */ + d->btf->nr_types = next_type_id - 1; + d->btf->types_size = d->btf->nr_types; + d->btf->hdr->type_len = p - types_start; + new_types = realloc(d->btf->types, + (1 + d->btf->nr_types) * sizeof(struct btf_type *)); + if (!new_types) + return -ENOMEM; + d->btf->types = new_types; + + /* make sure string section follows type information without gaps */ + d->btf->hdr->str_off = p - (char *)d->btf->nohdr_data; + memmove(p, d->btf->strings, d->btf->hdr->str_len); + d->btf->strings = p; + p += d->btf->hdr->str_len; + + d->btf->data_size = p - (char *)d->btf->data; + return 0; +} + +/* + * Figure out final (deduplicated and compacted) type ID for provided original + * `type_id` by first resolving it into corresponding canonical type ID and + * then mapping it to a deduplicated type ID, stored in btf_dedup->hypot_map, + * which is populated during compaction phase. + */ +static int btf_dedup_remap_type_id(struct btf_dedup *d, __u32 type_id) +{ + __u32 resolved_type_id, new_type_id; + + resolved_type_id = resolve_type_id(d, type_id); + new_type_id = d->hypot_map[resolved_type_id]; + if (new_type_id > BTF_MAX_NR_TYPES) + return -EINVAL; + return new_type_id; +} + +/* + * Remap referenced type IDs into deduped type IDs. + * + * After BTF types are deduplicated and compacted, their final type IDs may + * differ from original ones. The map from original to a corresponding + * deduped type ID is stored in btf_dedup->hypot_map and is populated during + * compaction phase. During remapping phase we are rewriting all type IDs + * referenced from any BTF type (e.g., struct fields, func proto args, etc) to + * their final deduped type IDs. + */ +static int btf_dedup_remap_type(struct btf_dedup *d, __u32 type_id) +{ + struct btf_type *t = d->btf->types[type_id]; + int i, r; + + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_INT: + case BTF_KIND_ENUM: + break; + + case BTF_KIND_FWD: + case BTF_KIND_CONST: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_PTR: + case BTF_KIND_TYPEDEF: + case BTF_KIND_FUNC: + r = btf_dedup_remap_type_id(d, t->type); + if (r < 0) + return r; + t->type = r; + break; + + case BTF_KIND_ARRAY: { + struct btf_array *arr_info = (struct btf_array *)(t + 1); + + r = btf_dedup_remap_type_id(d, arr_info->type); + if (r < 0) + return r; + arr_info->type = r; + r = btf_dedup_remap_type_id(d, arr_info->index_type); + if (r < 0) + return r; + arr_info->index_type = r; + break; + } + + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: { + struct btf_member *member = (struct btf_member *)(t + 1); + __u16 vlen = BTF_INFO_VLEN(t->info); + + for (i = 0; i < vlen; i++) { + r = btf_dedup_remap_type_id(d, member->type); + if (r < 0) + return r; + member->type = r; + member++; + } + break; + } + + case BTF_KIND_FUNC_PROTO: { + struct btf_param *param = (struct btf_param *)(t + 1); + __u16 vlen = BTF_INFO_VLEN(t->info); + + r = btf_dedup_remap_type_id(d, t->type); + if (r < 0) + return r; + t->type = r; + + for (i = 0; i < vlen; i++) { + r = btf_dedup_remap_type_id(d, param->type); + if (r < 0) + return r; + param->type = r; + param++; + } + break; + } + + default: + return -EINVAL; + } + + return 0; +} + +static int btf_dedup_remap_types(struct btf_dedup *d) +{ + int i, r; + + for (i = 1; i <= d->btf->nr_types; i++) { + r = btf_dedup_remap_type(d, i); + if (r < 0) + return r; + } + return 0; +} diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index b0610dcdae6b..94bbc249b0f1 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -55,33 +55,46 @@ struct btf_ext_header { __u32 line_info_len; }; -typedef int (*btf_print_fn_t)(const char *, ...) - __attribute__((format(printf, 1, 2))); - LIBBPF_API void btf__free(struct btf *btf); -LIBBPF_API struct btf *btf__new(__u8 *data, __u32 size, btf_print_fn_t err_log); +LIBBPF_API struct btf *btf__new(__u8 *data, __u32 size); +LIBBPF_API int btf__load(struct btf *btf); LIBBPF_API __s32 btf__find_by_name(const struct btf *btf, const char *type_name); +LIBBPF_API __u32 btf__get_nr_types(const struct btf *btf); LIBBPF_API const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 id); LIBBPF_API __s64 btf__resolve_size(const struct btf *btf, __u32 type_id); LIBBPF_API int btf__resolve_type(const struct btf *btf, __u32 type_id); LIBBPF_API int btf__fd(const struct btf *btf); +LIBBPF_API const void *btf__get_raw_data(const struct btf *btf, __u32 *size); LIBBPF_API const char *btf__name_by_offset(const struct btf *btf, __u32 offset); LIBBPF_API int btf__get_from_id(__u32 id, struct btf **btf); +LIBBPF_API int btf__get_map_kv_tids(const struct btf *btf, const char *map_name, + __u32 expected_key_size, + __u32 expected_value_size, + __u32 *key_type_id, __u32 *value_type_id); + +LIBBPF_API struct btf_ext *btf_ext__new(__u8 *data, __u32 size); +LIBBPF_API void btf_ext__free(struct btf_ext *btf_ext); +LIBBPF_API const void *btf_ext__get_raw_data(const struct btf_ext* btf_ext, + __u32 *size); +LIBBPF_API int btf_ext__reloc_func_info(const struct btf *btf, + const struct btf_ext *btf_ext, + const char *sec_name, __u32 insns_cnt, + void **func_info, __u32 *cnt); +LIBBPF_API int btf_ext__reloc_line_info(const struct btf *btf, + const struct btf_ext *btf_ext, + const char *sec_name, __u32 insns_cnt, + void **line_info, __u32 *cnt); +LIBBPF_API __u32 btf_ext__func_info_rec_size(const struct btf_ext *btf_ext); +LIBBPF_API __u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext); + +struct btf_dedup_opts { + bool dont_resolve_fwds; +}; -struct btf_ext *btf_ext__new(__u8 *data, __u32 size, btf_print_fn_t err_log); -void btf_ext__free(struct btf_ext *btf_ext); -int btf_ext__reloc_func_info(const struct btf *btf, - const struct btf_ext *btf_ext, - const char *sec_name, __u32 insns_cnt, - void **func_info, __u32 *func_info_len); -int btf_ext__reloc_line_info(const struct btf *btf, - const struct btf_ext *btf_ext, - const char *sec_name, __u32 insns_cnt, - void **line_info, __u32 *cnt); -__u32 btf_ext__func_info_rec_size(const struct btf_ext *btf_ext); -__u32 btf_ext__line_info_rec_size(const struct btf_ext *btf_ext); +LIBBPF_API int btf__dedup(struct btf *btf, struct btf_ext *btf_ext, + const struct btf_dedup_opts *opts); #ifdef __cplusplus } /* extern "C" */ diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 2ccde17957e6..b38dcbe7460a 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -42,6 +42,7 @@ #include "bpf.h" #include "btf.h" #include "str_error.h" +#include "libbpf_util.h" #ifndef EM_BPF #define EM_BPF 247 @@ -53,39 +54,33 @@ #define __printf(a, b) __attribute__((format(printf, a, b))) -__printf(1, 2) -static int __base_pr(const char *format, ...) +static int __base_pr(enum libbpf_print_level level, const char *format, + va_list args) { - va_list args; - int err; + if (level == LIBBPF_DEBUG) + return 0; - va_start(args, format); - err = vfprintf(stderr, format, args); - va_end(args); - return err; + return vfprintf(stderr, format, args); } -static __printf(1, 2) libbpf_print_fn_t __pr_warning = __base_pr; -static __printf(1, 2) libbpf_print_fn_t __pr_info = __base_pr; -static __printf(1, 2) libbpf_print_fn_t __pr_debug; - -#define __pr(func, fmt, ...) \ -do { \ - if ((func)) \ - (func)("libbpf: " fmt, ##__VA_ARGS__); \ -} while (0) +static libbpf_print_fn_t __libbpf_pr = __base_pr; -#define pr_warning(fmt, ...) __pr(__pr_warning, fmt, ##__VA_ARGS__) -#define pr_info(fmt, ...) __pr(__pr_info, fmt, ##__VA_ARGS__) -#define pr_debug(fmt, ...) __pr(__pr_debug, fmt, ##__VA_ARGS__) +void libbpf_set_print(libbpf_print_fn_t fn) +{ + __libbpf_pr = fn; +} -void libbpf_set_print(libbpf_print_fn_t warn, - libbpf_print_fn_t info, - libbpf_print_fn_t debug) +__printf(2, 3) +void libbpf_print(enum libbpf_print_level level, const char *format, ...) { - __pr_warning = warn; - __pr_info = info; - __pr_debug = debug; + va_list args; + + if (!__libbpf_pr) + return; + + va_start(args, format); + __libbpf_pr(level, format, args); + va_end(args); } #define STRERR_BUFSIZE 128 @@ -312,7 +307,7 @@ bpf_program__init(void *data, size_t size, char *section_name, int idx, return -EINVAL; } - bzero(prog, sizeof(*prog)); + memset(prog, 0, sizeof(*prog)); prog->section_name = strdup(section_name); if (!prog->section_name) { @@ -839,9 +834,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) else if (strcmp(name, "maps") == 0) obj->efile.maps_shndx = idx; else if (strcmp(name, BTF_ELF_SEC) == 0) { - obj->btf = btf__new(data->d_buf, data->d_size, - __pr_debug); - if (IS_ERR(obj->btf)) { + obj->btf = btf__new(data->d_buf, data->d_size); + if (IS_ERR(obj->btf) || btf__load(obj->btf)) { pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n", BTF_ELF_SEC, PTR_ERR(obj->btf)); obj->btf = NULL; @@ -915,8 +909,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags) BTF_EXT_ELF_SEC, BTF_ELF_SEC); } else { obj->btf_ext = btf_ext__new(btf_ext_data->d_buf, - btf_ext_data->d_size, - __pr_debug); + btf_ext_data->d_size); if (IS_ERR(obj->btf_ext)) { pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n", BTF_EXT_ELF_SEC, @@ -1057,72 +1050,18 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf) { - const struct btf_type *container_type; - const struct btf_member *key, *value; struct bpf_map_def *def = &map->def; - const size_t max_name = 256; - char container_name[max_name]; - __s64 key_size, value_size; - __s32 container_id; - - if (snprintf(container_name, max_name, "____btf_map_%s", map->name) == - max_name) { - pr_warning("map:%s length of '____btf_map_%s' is too long\n", - map->name, map->name); - return -EINVAL; - } - - container_id = btf__find_by_name(btf, container_name); - if (container_id < 0) { - pr_debug("map:%s container_name:%s cannot be found in BTF. Missing BPF_ANNOTATE_KV_PAIR?\n", - map->name, container_name); - return container_id; - } - - container_type = btf__type_by_id(btf, container_id); - if (!container_type) { - pr_warning("map:%s cannot find BTF type for container_id:%u\n", - map->name, container_id); - return -EINVAL; - } - - if (BTF_INFO_KIND(container_type->info) != BTF_KIND_STRUCT || - BTF_INFO_VLEN(container_type->info) < 2) { - pr_warning("map:%s container_name:%s is an invalid container struct\n", - map->name, container_name); - return -EINVAL; - } - - key = (struct btf_member *)(container_type + 1); - value = key + 1; - - key_size = btf__resolve_size(btf, key->type); - if (key_size < 0) { - pr_warning("map:%s invalid BTF key_type_size\n", - map->name); - return key_size; - } - - if (def->key_size != key_size) { - pr_warning("map:%s btf_key_type_size:%u != map_def_key_size:%u\n", - map->name, (__u32)key_size, def->key_size); - return -EINVAL; - } - - value_size = btf__resolve_size(btf, value->type); - if (value_size < 0) { - pr_warning("map:%s invalid BTF value_type_size\n", map->name); - return value_size; - } + __u32 key_type_id, value_type_id; + int ret; - if (def->value_size != value_size) { - pr_warning("map:%s btf_value_type_size:%u != map_def_value_size:%u\n", - map->name, (__u32)value_size, def->value_size); - return -EINVAL; - } + ret = btf__get_map_kv_tids(btf, map->name, def->key_size, + def->value_size, &key_type_id, + &value_type_id); + if (ret) + return ret; - map->btf_key_type_id = key->type; - map->btf_value_type_id = value->type; + map->btf_key_type_id = key_type_id; + map->btf_value_type_id = value_type_id; return 0; } @@ -1174,6 +1113,20 @@ err_free_new_name: return -errno; } +int bpf_map__resize(struct bpf_map *map, __u32 max_entries) +{ + if (!map || !max_entries) + return -EINVAL; + + /* If map already created, its attributes can't be changed. */ + if (map->fd >= 0) + return -EBUSY; + + map->def.max_entries = max_entries; + + return 0; +} + static int bpf_object__probe_name(struct bpf_object *obj) { @@ -1637,7 +1590,7 @@ bpf_program__load(struct bpf_program *prog, struct bpf_prog_prep_result result; bpf_program_prep_t preprocessor = prog->preprocessor; - bzero(&result, sizeof(result)); + memset(&result, 0, sizeof(result)); err = preprocessor(prog, i, prog->insns, prog->insns_cnt, &result); if (err) { @@ -2378,6 +2331,11 @@ unsigned int bpf_object__kversion(struct bpf_object *obj) return obj ? obj->kern_version : 0; } +struct btf *bpf_object__btf(struct bpf_object *obj) +{ + return obj ? obj->btf : NULL; +} + int bpf_object__btf_fd(const struct bpf_object *obj) { return obj->btf ? btf__fd(obj->btf) : -1; @@ -2884,6 +2842,12 @@ bpf_object__find_map_by_name(struct bpf_object *obj, const char *name) return NULL; } +int +bpf_object__find_map_fd_by_name(struct bpf_object *obj, const char *name) +{ + return bpf_map__fd(bpf_object__find_map_by_name(obj, name)); +} + struct bpf_map * bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset) { diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 62ae6cb93da1..6c0168f8bba5 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -47,17 +47,16 @@ enum libbpf_errno { LIBBPF_API int libbpf_strerror(int err, char *buf, size_t size); -/* - * __printf is defined in include/linux/compiler-gcc.h. However, - * it would be better if libbpf.h didn't depend on Linux header files. - * So instead of __printf, here we use gcc attribute directly. - */ -typedef int (*libbpf_print_fn_t)(const char *, ...) - __attribute__((format(printf, 1, 2))); +enum libbpf_print_level { + LIBBPF_WARN, + LIBBPF_INFO, + LIBBPF_DEBUG, +}; + +typedef int (*libbpf_print_fn_t)(enum libbpf_print_level level, + const char *, va_list ap); -LIBBPF_API void libbpf_set_print(libbpf_print_fn_t warn, - libbpf_print_fn_t info, - libbpf_print_fn_t debug); +LIBBPF_API void libbpf_set_print(libbpf_print_fn_t fn); /* Hide internal to user */ struct bpf_object; @@ -90,6 +89,9 @@ LIBBPF_API int bpf_object__load(struct bpf_object *obj); LIBBPF_API int bpf_object__unload(struct bpf_object *obj); LIBBPF_API const char *bpf_object__name(struct bpf_object *obj); LIBBPF_API unsigned int bpf_object__kversion(struct bpf_object *obj); + +struct btf; +LIBBPF_API struct btf *bpf_object__btf(struct bpf_object *obj); LIBBPF_API int bpf_object__btf_fd(const struct bpf_object *obj); LIBBPF_API struct bpf_program * @@ -264,6 +266,9 @@ struct bpf_map; LIBBPF_API struct bpf_map * bpf_object__find_map_by_name(struct bpf_object *obj, const char *name); +LIBBPF_API int +bpf_object__find_map_fd_by_name(struct bpf_object *obj, const char *name); + /* * Get bpf_map through the offset of corresponding struct bpf_map_def * in the BPF object file. @@ -292,6 +297,7 @@ LIBBPF_API int bpf_map__set_priv(struct bpf_map *map, void *priv, bpf_map_clear_priv_t clear_priv); LIBBPF_API void *bpf_map__priv(struct bpf_map *map); LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd); +LIBBPF_API int bpf_map__resize(struct bpf_map *map, __u32 max_entries); LIBBPF_API bool bpf_map__is_offload_neutral(struct bpf_map *map); LIBBPF_API void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex); LIBBPF_API int bpf_map__pin(struct bpf_map *map, const char *path); @@ -314,6 +320,7 @@ LIBBPF_API int bpf_prog_load(const char *file, enum bpf_prog_type type, struct bpf_object **pobj, int *prog_fd); LIBBPF_API int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags); +LIBBPF_API int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags); enum bpf_perf_event_ret { LIBBPF_PERF_EVENT_DONE = 0, diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 266bc95d0142..99dfa710c818 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -130,4 +130,21 @@ LIBBPF_0.0.2 { bpf_probe_helper; bpf_probe_map_type; bpf_probe_prog_type; + bpf_map__resize; + bpf_map_lookup_elem_flags; + bpf_object__btf; + bpf_object__find_map_fd_by_name; + bpf_get_link_xdp_id; + btf__dedup; + btf__get_map_kv_tids; + btf__get_nr_types; + btf__get_raw_data; + btf__load; + btf_ext__free; + btf_ext__func_info_rec_size; + btf_ext__get_raw_data; + btf_ext__line_info_rec_size; + btf_ext__new; + btf_ext__reloc_func_info; + btf_ext__reloc_line_info; } LIBBPF_0.0.1; diff --git a/tools/lib/bpf/libbpf_util.h b/tools/lib/bpf/libbpf_util.h new file mode 100644 index 000000000000..81ecda0cb9c9 --- /dev/null +++ b/tools/lib/bpf/libbpf_util.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */ +/* Copyright (c) 2019 Facebook */ + +#ifndef __LIBBPF_LIBBPF_UTIL_H +#define __LIBBPF_LIBBPF_UTIL_H + +#include <stdbool.h> + +#ifdef __cplusplus +extern "C" { +#endif + +extern void libbpf_print(enum libbpf_print_level level, + const char *format, ...) + __attribute__((format(printf, 2, 3))); + +#define __pr(level, fmt, ...) \ +do { \ + libbpf_print(level, "libbpf: " fmt, ##__VA_ARGS__); \ +} while (0) + +#define pr_warning(fmt, ...) __pr(LIBBPF_WARN, fmt, ##__VA_ARGS__) +#define pr_info(fmt, ...) __pr(LIBBPF_INFO, fmt, ##__VA_ARGS__) +#define pr_debug(fmt, ...) __pr(LIBBPF_DEBUG, fmt, ##__VA_ARGS__) + +#ifdef __cplusplus +} /* extern "C" */ +#endif + +#endif diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c index 0ce67aea8f3b..ce3ec81b71c0 100644 --- a/tools/lib/bpf/netlink.c +++ b/tools/lib/bpf/netlink.c @@ -21,6 +21,12 @@ typedef int (*__dump_nlmsg_t)(struct nlmsghdr *nlmsg, libbpf_dump_nlmsg_t, void *cookie); +struct xdp_id_md { + int ifindex; + __u32 flags; + __u32 id; +}; + int libbpf_netlink_open(__u32 *nl_pid) { struct sockaddr_nl sa; @@ -196,6 +202,85 @@ static int __dump_link_nlmsg(struct nlmsghdr *nlh, return dump_link_nlmsg(cookie, ifi, tb); } +static unsigned char get_xdp_id_attr(unsigned char mode, __u32 flags) +{ + if (mode != XDP_ATTACHED_MULTI) + return IFLA_XDP_PROG_ID; + if (flags & XDP_FLAGS_DRV_MODE) + return IFLA_XDP_DRV_PROG_ID; + if (flags & XDP_FLAGS_HW_MODE) + return IFLA_XDP_HW_PROG_ID; + if (flags & XDP_FLAGS_SKB_MODE) + return IFLA_XDP_SKB_PROG_ID; + + return IFLA_XDP_UNSPEC; +} + +static int get_xdp_id(void *cookie, void *msg, struct nlattr **tb) +{ + struct nlattr *xdp_tb[IFLA_XDP_MAX + 1]; + struct xdp_id_md *xdp_id = cookie; + struct ifinfomsg *ifinfo = msg; + unsigned char mode, xdp_attr; + int ret; + + if (xdp_id->ifindex && xdp_id->ifindex != ifinfo->ifi_index) + return 0; + + if (!tb[IFLA_XDP]) + return 0; + + ret = libbpf_nla_parse_nested(xdp_tb, IFLA_XDP_MAX, tb[IFLA_XDP], NULL); + if (ret) + return ret; + + if (!xdp_tb[IFLA_XDP_ATTACHED]) + return 0; + + mode = libbpf_nla_getattr_u8(xdp_tb[IFLA_XDP_ATTACHED]); + if (mode == XDP_ATTACHED_NONE) + return 0; + + xdp_attr = get_xdp_id_attr(mode, xdp_id->flags); + if (!xdp_attr || !xdp_tb[xdp_attr]) + return 0; + + xdp_id->id = libbpf_nla_getattr_u32(xdp_tb[xdp_attr]); + + return 0; +} + +int bpf_get_link_xdp_id(int ifindex, __u32 *prog_id, __u32 flags) +{ + struct xdp_id_md xdp_id = {}; + int sock, ret; + __u32 nl_pid; + __u32 mask; + + if (flags & ~XDP_FLAGS_MASK) + return -EINVAL; + + /* Check whether the single {HW,DRV,SKB} mode is set */ + flags &= (XDP_FLAGS_SKB_MODE | XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE); + mask = flags - 1; + if (flags && flags & mask) + return -EINVAL; + + sock = libbpf_netlink_open(&nl_pid); + if (sock < 0) + return sock; + + xdp_id.ifindex = ifindex; + xdp_id.flags = flags; + + ret = libbpf_nl_get_link(sock, nl_pid, get_xdp_id, &xdp_id); + if (!ret) + *prog_id = xdp_id.id; + + close(sock); + return ret; +} + int libbpf_nl_get_link(int sock, unsigned int nl_pid, libbpf_dump_nlmsg_t dump_link_nlmsg, void *cookie) { diff --git a/tools/lib/bpf/test_libbpf.cpp b/tools/lib/bpf/test_libbpf.cpp index abf3fc25c9fa..fc134873bb6d 100644 --- a/tools/lib/bpf/test_libbpf.cpp +++ b/tools/lib/bpf/test_libbpf.cpp @@ -8,11 +8,11 @@ int main(int argc, char *argv[]) { /* libbpf.h */ - libbpf_set_print(NULL, NULL, NULL); + libbpf_set_print(NULL); /* bpf.h */ bpf_prog_get_fd_by_id(0); /* btf.h */ - btf__new(NULL, 0, NULL); + btf__new(NULL, 0); } diff --git a/tools/perf/Documentation/perf-c2c.txt b/tools/perf/Documentation/perf-c2c.txt index 095aebdc5bb7..e6150f21267d 100644 --- a/tools/perf/Documentation/perf-c2c.txt +++ b/tools/perf/Documentation/perf-c2c.txt @@ -19,8 +19,11 @@ C2C stands for Cache To Cache. The perf c2c tool provides means for Shared Data C2C/HITM analysis. It allows you to track down the cacheline contentions. -The tool is based on x86's load latency and precise store facility events -provided by Intel CPUs. These events provide: +On x86, the tool is based on load latency and precise store facility events +provided by Intel CPUs. On PowerPC, the tool uses random instruction sampling +with thresholding feature. + +These events provide: - memory address of the access - type of the access (load and store details) - latency (in cycles) of the load access @@ -46,7 +49,7 @@ RECORD OPTIONS -l:: --ldlat:: - Configure mem-loads latency. + Configure mem-loads latency. (x86 only) -k:: --all-kernel:: @@ -119,11 +122,16 @@ Following perf record options are configured by default: -W,-d,--phys-data,--sample-cpu Unless specified otherwise with '-e' option, following events are monitored by -default: +default on x86: cpu/mem-loads,ldlat=30/P cpu/mem-stores/P +and following on PowerPC: + + cpu/mem-loads/ + cpu/mem-stores/ + User can pass any 'perf record' option behind '--' mark, like (to enable callchains and system wide monitoring): diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt index f8d2167cf3e7..199ea0f0a6c0 100644 --- a/tools/perf/Documentation/perf-mem.txt +++ b/tools/perf/Documentation/perf-mem.txt @@ -82,7 +82,7 @@ RECORD OPTIONS Be more verbose (show counter open errors, etc) --ldlat <n>:: - Specify desired latency for loads event. + Specify desired latency for loads event. (x86 only) In addition, for report all perf report options are valid, and for record all perf record options. diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build index 2e6595310420..ba98bd006488 100644 --- a/tools/perf/arch/powerpc/util/Build +++ b/tools/perf/arch/powerpc/util/Build @@ -2,6 +2,7 @@ libperf-y += header.o libperf-y += sym-handling.o libperf-y += kvm-stat.o libperf-y += perf_regs.o +libperf-y += mem-events.o libperf-$(CONFIG_DWARF) += dwarf-regs.o libperf-$(CONFIG_DWARF) += skip-callchain-idx.o diff --git a/tools/perf/arch/powerpc/util/mem-events.c b/tools/perf/arch/powerpc/util/mem-events.c new file mode 100644 index 000000000000..d08311f04e95 --- /dev/null +++ b/tools/perf/arch/powerpc/util/mem-events.c @@ -0,0 +1,11 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "mem-events.h" + +/* PowerPC does not support 'ldlat' parameter. */ +char *perf_mem_events__name(int i) +{ + if (i == PERF_MEM_EVENTS__LOAD) + return (char *) "cpu/mem-loads/"; + + return (char *) "cpu/mem-stores/"; +} diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index d079f36d342d..ac221f137ed2 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1681,13 +1681,8 @@ static void perf_sample__fprint_metric(struct perf_script *script, .force_header = false, }; struct perf_evsel *ev2; - static bool init; u64 val; - if (!init) { - perf_stat__init_shadow_stats(); - init = true; - } if (!evsel->stats) perf_evlist__alloc_stats(script->session->evlist, false); if (evsel_script(evsel->leader)->gnum++ == 0) @@ -1794,7 +1789,7 @@ static void process_event(struct perf_script *script, return; } - if (PRINT_FIELD(TRACE)) { + if (PRINT_FIELD(TRACE) && sample->raw_data) { event_format__fprintf(evsel->tp_format, sample->cpu, sample->raw_data, sample->raw_size, fp); } @@ -2359,6 +2354,8 @@ static int __cmd_script(struct perf_script *script) signal(SIGINT, sig_handler); + perf_stat__init_shadow_stats(); + /* override event processing functions */ if (script->show_task_events) { script->tool.comm = process_comm_event; diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index ed4583128b9c..b36061cd1ab8 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -2514,19 +2514,30 @@ static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp); static bool perf_evlist__add_vfs_getname(struct perf_evlist *evlist) { - struct perf_evsel *evsel = perf_evsel__newtp("probe", "vfs_getname"); + bool found = false; + struct perf_evsel *evsel, *tmp; + struct parse_events_error err = { .idx = 0, }; + int ret = parse_events(evlist, "probe:vfs_getname*", &err); - if (IS_ERR(evsel)) + if (ret) return false; - if (perf_evsel__field(evsel, "pathname") == NULL) { + evlist__for_each_entry_safe(evlist, evsel, tmp) { + if (!strstarts(perf_evsel__name(evsel), "probe:vfs_getname")) + continue; + + if (perf_evsel__field(evsel, "pathname")) { + evsel->handler = trace__vfs_getname; + found = true; + continue; + } + + list_del_init(&evsel->node); + evsel->evlist = NULL; perf_evsel__delete(evsel); - return false; } - evsel->handler = trace__vfs_getname; - perf_evlist__add(evlist, evsel); - return true; + return found; } static struct perf_evsel *perf_evsel__new_pgfault(u64 config) diff --git a/tools/perf/tests/attr.py b/tools/perf/tests/attr.py index 44090a9a19f3..e952127e4fb0 100644 --- a/tools/perf/tests/attr.py +++ b/tools/perf/tests/attr.py @@ -1,6 +1,8 @@ #! /usr/bin/python # SPDX-License-Identifier: GPL-2.0 +from __future__ import print_function + import os import sys import glob @@ -8,7 +10,11 @@ import optparse import tempfile import logging import shutil -import ConfigParser + +try: + import configparser +except ImportError: + import ConfigParser as configparser def data_equal(a, b): # Allow multiple values in assignment separated by '|' @@ -100,20 +106,20 @@ class Event(dict): def equal(self, other): for t in Event.terms: log.debug(" [%s] %s %s" % (t, self[t], other[t])); - if not self.has_key(t) or not other.has_key(t): + if t not in self or t not in other: return False if not data_equal(self[t], other[t]): return False return True def optional(self): - if self.has_key('optional') and self['optional'] == '1': + if 'optional' in self and self['optional'] == '1': return True return False def diff(self, other): for t in Event.terms: - if not self.has_key(t) or not other.has_key(t): + if t not in self or t not in other: continue if not data_equal(self[t], other[t]): log.warning("expected %s=%s, got %s" % (t, self[t], other[t])) @@ -134,7 +140,7 @@ class Event(dict): # - expected values assignments class Test(object): def __init__(self, path, options): - parser = ConfigParser.SafeConfigParser() + parser = configparser.SafeConfigParser() parser.read(path) log.warning("running '%s'" % path) @@ -193,7 +199,7 @@ class Test(object): return True def load_events(self, path, events): - parser_event = ConfigParser.SafeConfigParser() + parser_event = configparser.SafeConfigParser() parser_event.read(path) # The event record section header contains 'event' word, @@ -207,7 +213,7 @@ class Test(object): # Read parent event if there's any if (':' in section): base = section[section.index(':') + 1:] - parser_base = ConfigParser.SafeConfigParser() + parser_base = configparser.SafeConfigParser() parser_base.read(self.test_dir + '/' + base) base_items = parser_base.items('event') @@ -322,9 +328,9 @@ def run_tests(options): for f in glob.glob(options.test_dir + '/' + options.test): try: Test(f, options).run() - except Unsup, obj: + except Unsup as obj: log.warning("unsupp %s" % obj.getMsg()) - except Notest, obj: + except Notest as obj: log.warning("skipped %s" % obj.getMsg()) def setup_log(verbose): @@ -363,7 +369,7 @@ def main(): parser.add_option("-p", "--perf", action="store", type="string", dest="perf") parser.add_option("-v", "--verbose", - action="count", dest="verbose") + default=0, action="count", dest="verbose") options, args = parser.parse_args() if args: @@ -373,7 +379,7 @@ def main(): setup_log(options.verbose) if not options.test_dir: - print 'FAILED no -d option specified' + print('FAILED no -d option specified') sys.exit(-1) if not options.test: @@ -382,8 +388,8 @@ def main(): try: run_tests(options) - except Fail, obj: - print "FAILED %s" % obj.getMsg(); + except Fail as obj: + print("FAILED %s" % obj.getMsg()) sys.exit(-1) sys.exit(0) diff --git a/tools/perf/tests/evsel-tp-sched.c b/tools/perf/tests/evsel-tp-sched.c index 5f8501c68da4..5cbba70bcdd0 100644 --- a/tools/perf/tests/evsel-tp-sched.c +++ b/tools/perf/tests/evsel-tp-sched.c @@ -17,7 +17,7 @@ static int perf_evsel__test_field(struct perf_evsel *evsel, const char *name, return -1; } - is_signed = !!(field->flags | TEP_FIELD_IS_SIGNED); + is_signed = !!(field->flags & TEP_FIELD_IS_SIGNED); if (should_be_signed && !is_signed) { pr_debug("%s: \"%s\" signedness(%d) is wrong, should be %d\n", evsel->name, name, is_signed, should_be_signed); diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c index 1d00e5ec7906..82e16bf84466 100644 --- a/tools/perf/ui/browsers/annotate.c +++ b/tools/perf/ui/browsers/annotate.c @@ -224,20 +224,24 @@ static unsigned int annotate_browser__refresh(struct ui_browser *browser) return ret; } -static int disasm__cmp(struct annotation_line *a, struct annotation_line *b) +static double disasm__cmp(struct annotation_line *a, struct annotation_line *b, + int percent_type) { int i; for (i = 0; i < a->data_nr; i++) { - if (a->data[i].percent == b->data[i].percent) + if (a->data[i].percent[percent_type] == b->data[i].percent[percent_type]) continue; - return a->data[i].percent < b->data[i].percent; + return a->data[i].percent[percent_type] - + b->data[i].percent[percent_type]; } return 0; } -static void disasm_rb_tree__insert(struct rb_root *root, struct annotation_line *al) +static void disasm_rb_tree__insert(struct annotate_browser *browser, + struct annotation_line *al) { + struct rb_root *root = &browser->entries; struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; struct annotation_line *l; @@ -246,7 +250,7 @@ static void disasm_rb_tree__insert(struct rb_root *root, struct annotation_line parent = *p; l = rb_entry(parent, struct annotation_line, rb_node); - if (disasm__cmp(al, l)) + if (disasm__cmp(al, l, browser->opts->percent_type) < 0) p = &(*p)->rb_left; else p = &(*p)->rb_right; @@ -329,7 +333,7 @@ static void annotate_browser__calc_percent(struct annotate_browser *browser, RB_CLEAR_NODE(&pos->al.rb_node); continue; } - disasm_rb_tree__insert(&browser->entries, &pos->al); + disasm_rb_tree__insert(browser, &pos->al); } pthread_mutex_unlock(¬es->lock); diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c index 2f3eb6d293ee..037d8ff6a634 100644 --- a/tools/perf/util/bpf-loader.c +++ b/tools/perf/util/bpf-loader.c @@ -24,22 +24,12 @@ #include "llvm-utils.h" #include "c++/clang-c.h" -#define DEFINE_PRINT_FN(name, level) \ -static int libbpf_##name(const char *fmt, ...) \ -{ \ - va_list args; \ - int ret; \ - \ - va_start(args, fmt); \ - ret = veprintf(level, verbose, pr_fmt(fmt), args);\ - va_end(args); \ - return ret; \ +static int libbpf_perf_print(enum libbpf_print_level level __attribute__((unused)), + const char *fmt, va_list args) +{ + return veprintf(1, verbose, pr_fmt(fmt), args); } -DEFINE_PRINT_FN(warning, 1) -DEFINE_PRINT_FN(info, 1) -DEFINE_PRINT_FN(debug, 1) - struct bpf_prog_priv { bool is_tp; char *sys_name; @@ -59,9 +49,7 @@ bpf__prepare_load_buffer(void *obj_buf, size_t obj_buf_sz, const char *name) struct bpf_object *obj; if (!libbpf_initialized) { - libbpf_set_print(libbpf_warning, - libbpf_info, - libbpf_debug); + libbpf_set_print(libbpf_perf_print); libbpf_initialized = true; } @@ -79,9 +67,7 @@ struct bpf_object *bpf__prepare_load(const char *filename, bool source) struct bpf_object *obj; if (!libbpf_initialized) { - libbpf_set_print(libbpf_warning, - libbpf_info, - libbpf_debug); + libbpf_set_print(libbpf_perf_print); libbpf_initialized = true; } diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp index 89512504551b..39c0004f2886 100644 --- a/tools/perf/util/c++/clang.cpp +++ b/tools/perf/util/c++/clang.cpp @@ -160,7 +160,7 @@ getBPFObjectFromModule(llvm::Module *Module) } PM.run(*Module); - return std::move(Buffer); + return Buffer; } } diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 1ccbd3342069..383674f448fc 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -134,7 +134,12 @@ struct cpu_map *cpu_map__new(const char *cpu_list) if (!cpu_list) return cpu_map__read_all_cpu_map(); - if (!isdigit(*cpu_list)) + /* + * must handle the case of empty cpumap to cover + * TOPOLOGY header for NUMA nodes with no CPU + * ( e.g., because of CPU hotplug) + */ + if (!isdigit(*cpu_list) && *cpu_list != '\0') goto out; while (isdigit(*cpu_list)) { @@ -181,8 +186,10 @@ struct cpu_map *cpu_map__new(const char *cpu_list) if (nr_cpus > 0) cpus = cpu_map__trim_new(nr_cpus, tmp_cpus); - else + else if (*cpu_list != '\0') cpus = cpu_map__default_new(); + else + cpus = cpu_map__dummy_new(); invalid: free(tmp_cpus); out: diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index 93f74d8d3cdd..42c3e5a229d2 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -28,7 +28,7 @@ struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = { static char mem_loads_name[100]; static bool mem_loads_name__init; -char *perf_mem_events__name(int i) +char * __weak perf_mem_events__name(int i) { if (i == PERF_MEM_EVENTS__LOAD) { if (!mem_loads_name__init) { diff --git a/tools/perf/util/ordered-events.c b/tools/perf/util/ordered-events.c index 897589507d97..ea523d3b248f 100644 --- a/tools/perf/util/ordered-events.c +++ b/tools/perf/util/ordered-events.c @@ -391,8 +391,10 @@ void ordered_events__free(struct ordered_events *oe) * Current buffer might not have all the events allocated * yet, we need to free only allocated ones ... */ - list_del(&oe->buffer->list); - ordered_events_buffer__free(oe->buffer, oe->buffer_idx, oe); + if (oe->buffer) { + list_del(&oe->buffer->list); + ordered_events_buffer__free(oe->buffer, oe->buffer_idx, oe); + } /* ... and continue with the rest */ list_for_each_entry_safe(buffer, tmp, &oe->to_free, list) { diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py index 63f758c655d5..64d1f36dee99 100644 --- a/tools/perf/util/setup.py +++ b/tools/perf/util/setup.py @@ -17,6 +17,8 @@ if cc == "clang": vars[var] = sub("-mcet", "", vars[var]) if not clang_has_option("-fcf-protection"): vars[var] = sub("-fcf-protection", "", vars[var]) + if not clang_has_option("-fstack-clash-protection"): + vars[var] = sub("-fstack-clash-protection", "", vars[var]) from distutils.core import setup, Extension diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 66a84d5846c8..dca7dfae69ad 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -19,6 +19,20 @@ #define EM_AARCH64 183 /* ARM 64 bit */ #endif +#ifndef ELF32_ST_VISIBILITY +#define ELF32_ST_VISIBILITY(o) ((o) & 0x03) +#endif + +/* For ELF64 the definitions are the same. */ +#ifndef ELF64_ST_VISIBILITY +#define ELF64_ST_VISIBILITY(o) ELF32_ST_VISIBILITY (o) +#endif + +/* How to extract information held in the st_other field. */ +#ifndef GELF_ST_VISIBILITY +#define GELF_ST_VISIBILITY(val) ELF64_ST_VISIBILITY (val) +#endif + typedef Elf64_Nhdr GElf_Nhdr; #ifdef HAVE_CPLUS_DEMANGLE_SUPPORT @@ -87,6 +101,11 @@ static inline uint8_t elf_sym__type(const GElf_Sym *sym) return GELF_ST_TYPE(sym->st_info); } +static inline uint8_t elf_sym__visibility(const GElf_Sym *sym) +{ + return GELF_ST_VISIBILITY(sym->st_other); +} + #ifndef STT_GNU_IFUNC #define STT_GNU_IFUNC 10 #endif @@ -111,7 +130,9 @@ static inline int elf_sym__is_label(const GElf_Sym *sym) return elf_sym__type(sym) == STT_NOTYPE && sym->st_name != 0 && sym->st_shndx != SHN_UNDEF && - sym->st_shndx != SHN_ABS; + sym->st_shndx != SHN_ABS && + elf_sym__visibility(sym) != STV_HIDDEN && + elf_sym__visibility(sym) != STV_INTERNAL; } static bool elf_sym__filter(GElf_Sym *sym) diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 1a2bd15c5b6e..400ee81a3043 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -10,6 +10,7 @@ TARGETS += drivers/dma-buf TARGETS += efivarfs TARGETS += exec TARGETS += filesystems +TARGETS += filesystems/binderfs TARGETS += firmware TARGETS += ftrace TARGETS += futex diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index dd093bd91aa9..e47168d1257d 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -29,3 +29,4 @@ test_netcnt test_section_names test_tcpnotify_user test_libbpf +alu32 diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 8993e9c8f410..ccffaa0a0787 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -23,42 +23,19 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \ test_sock test_btf test_sockmap test_lirc_mode2_user get_cgroup_id_user \ test_socket_cookie test_cgroup_storage test_select_reuseport test_section_names \ - test_netcnt test_tcpnotify_user - -BPF_OBJ_FILES = \ - test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o \ - sockmap_verdict_prog.o dev_cgroup.o sample_ret0.o \ - test_tcpnotify_kern.o sample_map_ret0.o test_tcpbpf_kern.o \ - sockmap_tcp_msg_prog.o connect4_prog.o connect6_prog.o \ - test_btf_haskv.o test_btf_nokv.o test_sockmap_kern.o \ - test_tunnel_kern.o test_sockhash_kern.o test_lwt_seg6local.o \ - sendmsg4_prog.o sendmsg6_prog.o test_lirc_mode2_kern.o \ - get_cgroup_id_kern.o socket_cookie_prog.o test_select_reuseport_kern.o \ - test_skb_cgroup_id_kern.o bpf_flow.o netcnt_prog.o test_xdp_vlan.o \ - xdp_dummy.o test_map_in_map.o - -# Objects are built with default compilation flags and with sub-register -# code-gen enabled. -BPF_OBJ_FILES_DUAL_COMPILE = \ - test_pkt_access.o test_pkt_access.o test_xdp.o test_adjust_tail.o \ - test_l4lb.o test_l4lb_noinline.o test_xdp_noinline.o test_tcp_estats.o \ - test_obj_id.o test_pkt_md_access.o test_tracepoint.o \ - test_stacktrace_map.o test_stacktrace_map.o test_stacktrace_build_id.o \ - test_stacktrace_build_id.o test_get_stack_rawtp.o \ - test_get_stack_rawtp.o test_tracepoint.o test_sk_lookup_kern.o \ - test_queue_map.o test_stack_map.o - -TEST_GEN_FILES = $(BPF_OBJ_FILES) $(BPF_OBJ_FILES_DUAL_COMPILE) - -# Also test sub-register code-gen if LLVM + kernel both has eBPF v3 processor -# support which is the first version to contain both ALU32 and JMP32 -# instructions. + test_netcnt test_tcpnotify_user test_sock_fields + +BPF_OBJ_FILES = $(patsubst %.c,%.o, $(notdir $(wildcard progs/*.c))) +TEST_GEN_FILES = $(BPF_OBJ_FILES) + +# Also test sub-register code-gen if LLVM has eBPF v3 processor support which +# contains both ALU32 and JMP32 instructions. SUBREG_CODEGEN := $(shell echo "int cal(int a) { return a > 0; }" | \ $(CLANG) -target bpf -O2 -emit-llvm -S -x c - -o - | \ - $(LLC) -mattr=+alu32 -mcpu=probe 2>&1 | \ + $(LLC) -mattr=+alu32 -mcpu=v3 2>&1 | \ grep 'if w') ifneq ($(SUBREG_CODEGEN),) -TEST_GEN_FILES += $(patsubst %.o,alu32/%.o, $(BPF_OBJ_FILES_DUAL_COMPILE)) +TEST_GEN_FILES += $(patsubst %.o,alu32/%.o, $(BPF_OBJ_FILES)) endif # Order correspond to 'make run_tests' order @@ -73,7 +50,8 @@ TEST_PROGS := test_kmod.sh \ test_lirc_mode2.sh \ test_skb_cgroup_id.sh \ test_flow_dissector.sh \ - test_xdp_vlan.sh + test_xdp_vlan.sh \ + test_lwt_ip_encap.sh TEST_PROGS_EXTENDED := with_addr.sh \ with_tunnels.sh \ @@ -111,6 +89,7 @@ $(OUTPUT)/test_progs: trace_helpers.c $(OUTPUT)/get_cgroup_id_user: cgroup_helpers.c $(OUTPUT)/test_cgroup_storage: cgroup_helpers.c $(OUTPUT)/test_netcnt: cgroup_helpers.c +$(OUTPUT)/test_sock_fields: cgroup_helpers.c .PHONY: force @@ -188,7 +167,8 @@ $(ALU32_BUILD_DIR)/test_progs_32: test_progs.c $(ALU32_BUILD_DIR) \ $(CC) $(CFLAGS) -o $(ALU32_BUILD_DIR)/test_progs_32 $< \ trace_helpers.c $(OUTPUT)/libbpf.a $(LDLIBS) -$(ALU32_BUILD_DIR)/%.o: %.c $(ALU32_BUILD_DIR) $(ALU32_BUILD_DIR)/test_progs_32 +$(ALU32_BUILD_DIR)/%.o: progs/%.c $(ALU32_BUILD_DIR) \ + $(ALU32_BUILD_DIR)/test_progs_32 $(CLANG) $(CLANG_FLAGS) \ -O2 -target bpf -emit-llvm -c $< -o - | \ $(LLC) -march=bpf -mattr=+alu32 -mcpu=$(CPU) $(LLC_FLAGS) \ @@ -200,7 +180,7 @@ endif # Have one program compiled without "-target bpf" to test whether libbpf loads # it successfully -$(OUTPUT)/test_xdp.o: test_xdp.c +$(OUTPUT)/test_xdp.o: progs/test_xdp.c $(CLANG) $(CLANG_FLAGS) \ -O2 -emit-llvm -c $< -o - | \ $(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@ @@ -208,7 +188,7 @@ ifeq ($(DWARF2BTF),y) $(BTF_PAHOLE) -J $@ endif -$(OUTPUT)/%.o: %.c +$(OUTPUT)/%.o: progs/%.c $(CLANG) $(CLANG_FLAGS) \ -O2 -target bpf -emit-llvm -c $< -o - | \ $(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@ @@ -216,7 +196,8 @@ ifeq ($(DWARF2BTF),y) $(BTF_PAHOLE) -J $@ endif -$(OUTPUT)/test_verifier: $(OUTPUT)/verifier/tests.h +VERIFIER_TESTS_H := $(OUTPUT)/verifier/tests.h +$(OUTPUT)/test_verifier: $(VERIFIER_TESTS_H) $(OUTPUT)/test_verifier: CFLAGS += -I$(OUTPUT) VERIFIER_TEST_FILES := $(wildcard verifier/*.c) @@ -227,6 +208,7 @@ $(OUTPUT)/verifier/tests.h: $(VERIFIER_TEST_FILES) ls *.c 2> /dev/null | \ sed -e 's@\(.*\)@#include \"\1\"@'; \ echo '#endif' \ - ) > $(OUTPUT)/verifier/tests.h) + ) > $(VERIFIER_TESTS_H)) -EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(ALU32_BUILD_DIR) +EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(ALU32_BUILD_DIR) \ + $(VERIFIER_TESTS_H) diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index 6c77cf7bedce..d9999f1ed1d2 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -172,6 +172,14 @@ static int (*bpf_skb_vlan_pop)(void *ctx) = (void *) BPF_FUNC_skb_vlan_pop; static int (*bpf_rc_pointer_rel)(void *ctx, int rel_x, int rel_y) = (void *) BPF_FUNC_rc_pointer_rel; +static void (*bpf_spin_lock)(struct bpf_spin_lock *lock) = + (void *) BPF_FUNC_spin_lock; +static void (*bpf_spin_unlock)(struct bpf_spin_lock *lock) = + (void *) BPF_FUNC_spin_unlock; +static struct bpf_sock *(*bpf_sk_fullsock)(struct bpf_sock *sk) = + (void *) BPF_FUNC_sk_fullsock; +static struct bpf_tcp_sock *(*bpf_tcp_sock)(struct bpf_sock *sk) = + (void *) BPF_FUNC_tcp_sock; /* llvm builtin functions that eBPF C program may use to * emit BPF_LD_ABS and BPF_LD_IND instructions diff --git a/tools/testing/selftests/bpf/bpf_util.h b/tools/testing/selftests/bpf/bpf_util.h index 315a44fa32af..a29206ebbd13 100644 --- a/tools/testing/selftests/bpf/bpf_util.h +++ b/tools/testing/selftests/bpf/bpf_util.h @@ -13,7 +13,7 @@ static inline unsigned int bpf_num_possible_cpus(void) unsigned int start, end, possible_cpus = 0; char buff[128]; FILE *fp; - int n; + int len, n, i, j = 0; fp = fopen(fcpu, "r"); if (!fp) { @@ -21,17 +21,27 @@ static inline unsigned int bpf_num_possible_cpus(void) exit(1); } - while (fgets(buff, sizeof(buff), fp)) { - n = sscanf(buff, "%u-%u", &start, &end); - if (n == 0) { - printf("Failed to retrieve # possible CPUs!\n"); - exit(1); - } else if (n == 1) { - end = start; + if (!fgets(buff, sizeof(buff), fp)) { + printf("Failed to read %s!\n", fcpu); + exit(1); + } + + len = strlen(buff); + for (i = 0; i <= len; i++) { + if (buff[i] == ',' || buff[i] == '\0') { + buff[i] = '\0'; + n = sscanf(&buff[j], "%u-%u", &start, &end); + if (n <= 0) { + printf("Failed to retrieve # possible CPUs!\n"); + exit(1); + } else if (n == 1) { + end = start; + } + possible_cpus += end - start + 1; + j = i + 1; } - possible_cpus = start == 0 ? end + 1 : 0; - break; } + fclose(fp); return possible_cpus; @@ -48,4 +58,13 @@ static inline unsigned int bpf_num_possible_cpus(void) # define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) #endif +#ifndef sizeof_field +#define sizeof_field(TYPE, MEMBER) sizeof((((TYPE *)0)->MEMBER)) +#endif + +#ifndef offsetofend +#define offsetofend(TYPE, MEMBER) \ + (offsetof(TYPE, MEMBER) + sizeof_field(TYPE, MEMBER)) +#endif + #endif /* __BPF_UTIL__ */ diff --git a/tools/testing/selftests/bpf/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c index 284660f5aa95..284660f5aa95 100644 --- a/tools/testing/selftests/bpf/bpf_flow.c +++ b/tools/testing/selftests/bpf/progs/bpf_flow.c diff --git a/tools/testing/selftests/bpf/connect4_prog.c b/tools/testing/selftests/bpf/progs/connect4_prog.c index 1fd244d35ba9..1fd244d35ba9 100644 --- a/tools/testing/selftests/bpf/connect4_prog.c +++ b/tools/testing/selftests/bpf/progs/connect4_prog.c diff --git a/tools/testing/selftests/bpf/connect6_prog.c b/tools/testing/selftests/bpf/progs/connect6_prog.c index 26397ab7b3c7..26397ab7b3c7 100644 --- a/tools/testing/selftests/bpf/connect6_prog.c +++ b/tools/testing/selftests/bpf/progs/connect6_prog.c diff --git a/tools/testing/selftests/bpf/dev_cgroup.c b/tools/testing/selftests/bpf/progs/dev_cgroup.c index ce41a3475f27..ce41a3475f27 100644 --- a/tools/testing/selftests/bpf/dev_cgroup.c +++ b/tools/testing/selftests/bpf/progs/dev_cgroup.c diff --git a/tools/testing/selftests/bpf/get_cgroup_id_kern.c b/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c index 014dba10b8a5..014dba10b8a5 100644 --- a/tools/testing/selftests/bpf/get_cgroup_id_kern.c +++ b/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c diff --git a/tools/testing/selftests/bpf/netcnt_prog.c b/tools/testing/selftests/bpf/progs/netcnt_prog.c index 9f741e69cebe..9f741e69cebe 100644 --- a/tools/testing/selftests/bpf/netcnt_prog.c +++ b/tools/testing/selftests/bpf/progs/netcnt_prog.c diff --git a/tools/testing/selftests/bpf/sample_map_ret0.c b/tools/testing/selftests/bpf/progs/sample_map_ret0.c index 0756303676ac..0756303676ac 100644 --- a/tools/testing/selftests/bpf/sample_map_ret0.c +++ b/tools/testing/selftests/bpf/progs/sample_map_ret0.c diff --git a/tools/testing/selftests/bpf/sample_ret0.c b/tools/testing/selftests/bpf/progs/sample_ret0.c index fec99750d6ea..fec99750d6ea 100644 --- a/tools/testing/selftests/bpf/sample_ret0.c +++ b/tools/testing/selftests/bpf/progs/sample_ret0.c diff --git a/tools/testing/selftests/bpf/sendmsg4_prog.c b/tools/testing/selftests/bpf/progs/sendmsg4_prog.c index a91536b1c47e..a91536b1c47e 100644 --- a/tools/testing/selftests/bpf/sendmsg4_prog.c +++ b/tools/testing/selftests/bpf/progs/sendmsg4_prog.c diff --git a/tools/testing/selftests/bpf/sendmsg6_prog.c b/tools/testing/selftests/bpf/progs/sendmsg6_prog.c index 5aeaa284fc47..5aeaa284fc47 100644 --- a/tools/testing/selftests/bpf/sendmsg6_prog.c +++ b/tools/testing/selftests/bpf/progs/sendmsg6_prog.c diff --git a/tools/testing/selftests/bpf/socket_cookie_prog.c b/tools/testing/selftests/bpf/progs/socket_cookie_prog.c index 9ff8ac4b0bf6..9ff8ac4b0bf6 100644 --- a/tools/testing/selftests/bpf/socket_cookie_prog.c +++ b/tools/testing/selftests/bpf/progs/socket_cookie_prog.c diff --git a/tools/testing/selftests/bpf/sockmap_parse_prog.c b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c index 0f92858f6226..0f92858f6226 100644 --- a/tools/testing/selftests/bpf/sockmap_parse_prog.c +++ b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c diff --git a/tools/testing/selftests/bpf/sockmap_tcp_msg_prog.c b/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c index 12a7b5c82ed6..12a7b5c82ed6 100644 --- a/tools/testing/selftests/bpf/sockmap_tcp_msg_prog.c +++ b/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c diff --git a/tools/testing/selftests/bpf/sockmap_verdict_prog.c b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c index 2ce7634a4012..2ce7634a4012 100644 --- a/tools/testing/selftests/bpf/sockmap_verdict_prog.c +++ b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c diff --git a/tools/testing/selftests/bpf/test_adjust_tail.c b/tools/testing/selftests/bpf/progs/test_adjust_tail.c index 4cd5e860c903..4cd5e860c903 100644 --- a/tools/testing/selftests/bpf/test_adjust_tail.c +++ b/tools/testing/selftests/bpf/progs/test_adjust_tail.c diff --git a/tools/testing/selftests/bpf/test_btf_haskv.c b/tools/testing/selftests/bpf/progs/test_btf_haskv.c index e5c79fe0ffdb..e5c79fe0ffdb 100644 --- a/tools/testing/selftests/bpf/test_btf_haskv.c +++ b/tools/testing/selftests/bpf/progs/test_btf_haskv.c diff --git a/tools/testing/selftests/bpf/test_btf_nokv.c b/tools/testing/selftests/bpf/progs/test_btf_nokv.c index 434188c37774..434188c37774 100644 --- a/tools/testing/selftests/bpf/test_btf_nokv.c +++ b/tools/testing/selftests/bpf/progs/test_btf_nokv.c diff --git a/tools/testing/selftests/bpf/test_get_stack_rawtp.c b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c index f6d9f238e00a..f6d9f238e00a 100644 --- a/tools/testing/selftests/bpf/test_get_stack_rawtp.c +++ b/tools/testing/selftests/bpf/progs/test_get_stack_rawtp.c diff --git a/tools/testing/selftests/bpf/test_l4lb.c b/tools/testing/selftests/bpf/progs/test_l4lb.c index 1e10c9590991..1e10c9590991 100644 --- a/tools/testing/selftests/bpf/test_l4lb.c +++ b/tools/testing/selftests/bpf/progs/test_l4lb.c diff --git a/tools/testing/selftests/bpf/test_l4lb_noinline.c b/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c index ba44a14e6dc4..ba44a14e6dc4 100644 --- a/tools/testing/selftests/bpf/test_l4lb_noinline.c +++ b/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c diff --git a/tools/testing/selftests/bpf/test_lirc_mode2_kern.c b/tools/testing/selftests/bpf/progs/test_lirc_mode2_kern.c index 4147130cc3b7..4147130cc3b7 100644 --- a/tools/testing/selftests/bpf/test_lirc_mode2_kern.c +++ b/tools/testing/selftests/bpf/progs/test_lirc_mode2_kern.c diff --git a/tools/testing/selftests/bpf/progs/test_lwt_ip_encap.c b/tools/testing/selftests/bpf/progs/test_lwt_ip_encap.c new file mode 100644 index 000000000000..c957d6dfe6d7 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_lwt_ip_encap.c @@ -0,0 +1,85 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stddef.h> +#include <string.h> +#include <linux/bpf.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include "bpf_helpers.h" +#include "bpf_endian.h" + +struct grehdr { + __be16 flags; + __be16 protocol; +}; + +SEC("encap_gre") +int bpf_lwt_encap_gre(struct __sk_buff *skb) +{ + struct encap_hdr { + struct iphdr iph; + struct grehdr greh; + } hdr; + int err; + + memset(&hdr, 0, sizeof(struct encap_hdr)); + + hdr.iph.ihl = 5; + hdr.iph.version = 4; + hdr.iph.ttl = 0x40; + hdr.iph.protocol = 47; /* IPPROTO_GRE */ +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ + hdr.iph.saddr = 0x640110ac; /* 172.16.1.100 */ + hdr.iph.daddr = 0x641010ac; /* 172.16.16.100 */ +#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ + hdr.iph.saddr = 0xac100164; /* 172.16.1.100 */ + hdr.iph.daddr = 0xac101064; /* 172.16.16.100 */ +#else +#error "Fix your compiler's __BYTE_ORDER__?!" +#endif + hdr.iph.tot_len = bpf_htons(skb->len + sizeof(struct encap_hdr)); + + hdr.greh.protocol = skb->protocol; + + err = bpf_lwt_push_encap(skb, BPF_LWT_ENCAP_IP, &hdr, + sizeof(struct encap_hdr)); + if (err) + return BPF_DROP; + + return BPF_LWT_REROUTE; +} + +SEC("encap_gre6") +int bpf_lwt_encap_gre6(struct __sk_buff *skb) +{ + struct encap_hdr { + struct ipv6hdr ip6hdr; + struct grehdr greh; + } hdr; + int err; + + memset(&hdr, 0, sizeof(struct encap_hdr)); + + hdr.ip6hdr.version = 6; + hdr.ip6hdr.payload_len = bpf_htons(skb->len + sizeof(struct grehdr)); + hdr.ip6hdr.nexthdr = 47; /* IPPROTO_GRE */ + hdr.ip6hdr.hop_limit = 0x40; + /* fb01::1 */ + hdr.ip6hdr.saddr.s6_addr[0] = 0xfb; + hdr.ip6hdr.saddr.s6_addr[1] = 1; + hdr.ip6hdr.saddr.s6_addr[15] = 1; + /* fb10::1 */ + hdr.ip6hdr.daddr.s6_addr[0] = 0xfb; + hdr.ip6hdr.daddr.s6_addr[1] = 0x10; + hdr.ip6hdr.daddr.s6_addr[15] = 1; + + hdr.greh.protocol = skb->protocol; + + err = bpf_lwt_push_encap(skb, BPF_LWT_ENCAP_IP, &hdr, + sizeof(struct encap_hdr)); + if (err) + return BPF_DROP; + + return BPF_LWT_REROUTE; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_lwt_seg6local.c b/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c index 0575751bc1bc..0575751bc1bc 100644 --- a/tools/testing/selftests/bpf/test_lwt_seg6local.c +++ b/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c diff --git a/tools/testing/selftests/bpf/test_map_in_map.c b/tools/testing/selftests/bpf/progs/test_map_in_map.c index ce923e67e08e..ce923e67e08e 100644 --- a/tools/testing/selftests/bpf/test_map_in_map.c +++ b/tools/testing/selftests/bpf/progs/test_map_in_map.c diff --git a/tools/testing/selftests/bpf/progs/test_map_lock.c b/tools/testing/selftests/bpf/progs/test_map_lock.c new file mode 100644 index 000000000000..af8cc68ed2f9 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_map_lock.c @@ -0,0 +1,66 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <linux/bpf.h> +#include <linux/version.h> +#include "bpf_helpers.h" + +#define VAR_NUM 16 + +struct hmap_elem { + struct bpf_spin_lock lock; + int var[VAR_NUM]; +}; + +struct bpf_map_def SEC("maps") hash_map = { + .type = BPF_MAP_TYPE_HASH, + .key_size = sizeof(int), + .value_size = sizeof(struct hmap_elem), + .max_entries = 1, +}; + +BPF_ANNOTATE_KV_PAIR(hash_map, int, struct hmap_elem); + +struct array_elem { + struct bpf_spin_lock lock; + int var[VAR_NUM]; +}; + +struct bpf_map_def SEC("maps") array_map = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(struct array_elem), + .max_entries = 1, +}; + +BPF_ANNOTATE_KV_PAIR(array_map, int, struct array_elem); + +SEC("map_lock_demo") +int bpf_map_lock_test(struct __sk_buff *skb) +{ + struct hmap_elem zero = {}, *val; + int rnd = bpf_get_prandom_u32(); + int key = 0, err = 1, i; + struct array_elem *q; + + val = bpf_map_lookup_elem(&hash_map, &key); + if (!val) + goto err; + /* spin_lock in hash map */ + bpf_spin_lock(&val->lock); + for (i = 0; i < VAR_NUM; i++) + val->var[i] = rnd; + bpf_spin_unlock(&val->lock); + + /* spin_lock in array */ + q = bpf_map_lookup_elem(&array_map, &key); + if (!q) + goto err; + bpf_spin_lock(&q->lock); + for (i = 0; i < VAR_NUM; i++) + q->var[i] = rnd; + bpf_spin_unlock(&q->lock); + err = 0; +err: + return err; +} +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_obj_id.c b/tools/testing/selftests/bpf/progs/test_obj_id.c index 880d2963b472..880d2963b472 100644 --- a/tools/testing/selftests/bpf/test_obj_id.c +++ b/tools/testing/selftests/bpf/progs/test_obj_id.c diff --git a/tools/testing/selftests/bpf/test_pkt_access.c b/tools/testing/selftests/bpf/progs/test_pkt_access.c index 6e11ba11709e..6e11ba11709e 100644 --- a/tools/testing/selftests/bpf/test_pkt_access.c +++ b/tools/testing/selftests/bpf/progs/test_pkt_access.c diff --git a/tools/testing/selftests/bpf/test_pkt_md_access.c b/tools/testing/selftests/bpf/progs/test_pkt_md_access.c index 7956302ecdf2..7956302ecdf2 100644 --- a/tools/testing/selftests/bpf/test_pkt_md_access.c +++ b/tools/testing/selftests/bpf/progs/test_pkt_md_access.c diff --git a/tools/testing/selftests/bpf/test_queue_map.c b/tools/testing/selftests/bpf/progs/test_queue_map.c index 87db1f9da33d..87db1f9da33d 100644 --- a/tools/testing/selftests/bpf/test_queue_map.c +++ b/tools/testing/selftests/bpf/progs/test_queue_map.c diff --git a/tools/testing/selftests/bpf/test_select_reuseport_kern.c b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c index 5b54ec637ada..5b54ec637ada 100644 --- a/tools/testing/selftests/bpf/test_select_reuseport_kern.c +++ b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c diff --git a/tools/testing/selftests/bpf/test_sk_lookup_kern.c b/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c index e21cd736c196..e21cd736c196 100644 --- a/tools/testing/selftests/bpf/test_sk_lookup_kern.c +++ b/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c diff --git a/tools/testing/selftests/bpf/test_skb_cgroup_id_kern.c b/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c index 68cf9829f5a7..68cf9829f5a7 100644 --- a/tools/testing/selftests/bpf/test_skb_cgroup_id_kern.c +++ b/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c diff --git a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c new file mode 100644 index 000000000000..de1a43e8f610 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c @@ -0,0 +1,152 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ + +#include <linux/bpf.h> +#include <netinet/in.h> +#include <stdbool.h> + +#include "bpf_helpers.h" +#include "bpf_endian.h" + +enum bpf_array_idx { + SRV_IDX, + CLI_IDX, + __NR_BPF_ARRAY_IDX, +}; + +struct bpf_map_def SEC("maps") addr_map = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(struct sockaddr_in6), + .max_entries = __NR_BPF_ARRAY_IDX, +}; + +struct bpf_map_def SEC("maps") sock_result_map = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(struct bpf_sock), + .max_entries = __NR_BPF_ARRAY_IDX, +}; + +struct bpf_map_def SEC("maps") tcp_sock_result_map = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(struct bpf_tcp_sock), + .max_entries = __NR_BPF_ARRAY_IDX, +}; + +struct bpf_map_def SEC("maps") linum_map = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(__u32), + .max_entries = 1, +}; + +static bool is_loopback6(__u32 *a6) +{ + return !a6[0] && !a6[1] && !a6[2] && a6[3] == bpf_htonl(1); +} + +static void skcpy(struct bpf_sock *dst, + const struct bpf_sock *src) +{ + dst->bound_dev_if = src->bound_dev_if; + dst->family = src->family; + dst->type = src->type; + dst->protocol = src->protocol; + dst->mark = src->mark; + dst->priority = src->priority; + dst->src_ip4 = src->src_ip4; + dst->src_ip6[0] = src->src_ip6[0]; + dst->src_ip6[1] = src->src_ip6[1]; + dst->src_ip6[2] = src->src_ip6[2]; + dst->src_ip6[3] = src->src_ip6[3]; + dst->src_port = src->src_port; + dst->dst_ip4 = src->dst_ip4; + dst->dst_ip6[0] = src->dst_ip6[0]; + dst->dst_ip6[1] = src->dst_ip6[1]; + dst->dst_ip6[2] = src->dst_ip6[2]; + dst->dst_ip6[3] = src->dst_ip6[3]; + dst->dst_port = src->dst_port; + dst->state = src->state; +} + +static void tpcpy(struct bpf_tcp_sock *dst, + const struct bpf_tcp_sock *src) +{ + dst->snd_cwnd = src->snd_cwnd; + dst->srtt_us = src->srtt_us; + dst->rtt_min = src->rtt_min; + dst->snd_ssthresh = src->snd_ssthresh; + dst->rcv_nxt = src->rcv_nxt; + dst->snd_nxt = src->snd_nxt; + dst->snd_una = src->snd_una; + dst->mss_cache = src->mss_cache; + dst->ecn_flags = src->ecn_flags; + dst->rate_delivered = src->rate_delivered; + dst->rate_interval_us = src->rate_interval_us; + dst->packets_out = src->packets_out; + dst->retrans_out = src->retrans_out; + dst->total_retrans = src->total_retrans; + dst->segs_in = src->segs_in; + dst->data_segs_in = src->data_segs_in; + dst->segs_out = src->segs_out; + dst->data_segs_out = src->data_segs_out; + dst->lost_out = src->lost_out; + dst->sacked_out = src->sacked_out; + dst->bytes_received = src->bytes_received; + dst->bytes_acked = src->bytes_acked; +} + +#define RETURN { \ + linum = __LINE__; \ + bpf_map_update_elem(&linum_map, &idx0, &linum, 0); \ + return 1; \ +} + +SEC("cgroup_skb/egress") +int read_sock_fields(struct __sk_buff *skb) +{ + __u32 srv_idx = SRV_IDX, cli_idx = CLI_IDX, idx; + struct sockaddr_in6 *srv_sa6, *cli_sa6; + struct bpf_tcp_sock *tp, *tp_ret; + struct bpf_sock *sk, *sk_ret; + __u32 linum, idx0 = 0; + + sk = skb->sk; + if (!sk || sk->state == 10) + RETURN; + + sk = bpf_sk_fullsock(sk); + if (!sk || sk->family != AF_INET6 || sk->protocol != IPPROTO_TCP || + !is_loopback6(sk->src_ip6)) + RETURN; + + tp = bpf_tcp_sock(sk); + if (!tp) + RETURN; + + srv_sa6 = bpf_map_lookup_elem(&addr_map, &srv_idx); + cli_sa6 = bpf_map_lookup_elem(&addr_map, &cli_idx); + if (!srv_sa6 || !cli_sa6) + RETURN; + + if (sk->src_port == bpf_ntohs(srv_sa6->sin6_port)) + idx = srv_idx; + else if (sk->src_port == bpf_ntohs(cli_sa6->sin6_port)) + idx = cli_idx; + else + RETURN; + + sk_ret = bpf_map_lookup_elem(&sock_result_map, &idx); + tp_ret = bpf_map_lookup_elem(&tcp_sock_result_map, &idx); + if (!sk_ret || !tp_ret) + RETURN; + + skcpy(sk_ret, sk); + tpcpy(tp_ret, tp); + + RETURN; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_sockhash_kern.c b/tools/testing/selftests/bpf/progs/test_sockhash_kern.c index e6755916442a..e6755916442a 100644 --- a/tools/testing/selftests/bpf/test_sockhash_kern.c +++ b/tools/testing/selftests/bpf/progs/test_sockhash_kern.c diff --git a/tools/testing/selftests/bpf/test_sockmap_kern.c b/tools/testing/selftests/bpf/progs/test_sockmap_kern.c index 677b2ed1cc1e..677b2ed1cc1e 100644 --- a/tools/testing/selftests/bpf/test_sockmap_kern.c +++ b/tools/testing/selftests/bpf/progs/test_sockmap_kern.c diff --git a/tools/testing/selftests/bpf/progs/test_spin_lock.c b/tools/testing/selftests/bpf/progs/test_spin_lock.c new file mode 100644 index 000000000000..40f904312090 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_spin_lock.c @@ -0,0 +1,108 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include <linux/bpf.h> +#include <linux/version.h> +#include "bpf_helpers.h" + +struct hmap_elem { + volatile int cnt; + struct bpf_spin_lock lock; + int test_padding; +}; + +struct bpf_map_def SEC("maps") hmap = { + .type = BPF_MAP_TYPE_HASH, + .key_size = sizeof(int), + .value_size = sizeof(struct hmap_elem), + .max_entries = 1, +}; + +BPF_ANNOTATE_KV_PAIR(hmap, int, struct hmap_elem); + + +struct cls_elem { + struct bpf_spin_lock lock; + volatile int cnt; +}; + +struct bpf_map_def SEC("maps") cls_map = { + .type = BPF_MAP_TYPE_CGROUP_STORAGE, + .key_size = sizeof(struct bpf_cgroup_storage_key), + .value_size = sizeof(struct cls_elem), +}; + +BPF_ANNOTATE_KV_PAIR(cls_map, struct bpf_cgroup_storage_key, + struct cls_elem); + +struct bpf_vqueue { + struct bpf_spin_lock lock; + /* 4 byte hole */ + unsigned long long lasttime; + int credit; + unsigned int rate; +}; + +struct bpf_map_def SEC("maps") vqueue = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(struct bpf_vqueue), + .max_entries = 1, +}; + +BPF_ANNOTATE_KV_PAIR(vqueue, int, struct bpf_vqueue); +#define CREDIT_PER_NS(delta, rate) (((delta) * rate) >> 20) + +SEC("spin_lock_demo") +int bpf_sping_lock_test(struct __sk_buff *skb) +{ + volatile int credit = 0, max_credit = 100, pkt_len = 64; + struct hmap_elem zero = {}, *val; + unsigned long long curtime; + struct bpf_vqueue *q; + struct cls_elem *cls; + int key = 0; + int err = 0; + + val = bpf_map_lookup_elem(&hmap, &key); + if (!val) { + bpf_map_update_elem(&hmap, &key, &zero, 0); + val = bpf_map_lookup_elem(&hmap, &key); + if (!val) { + err = 1; + goto err; + } + } + /* spin_lock in hash map run time test */ + bpf_spin_lock(&val->lock); + if (val->cnt) + val->cnt--; + else + val->cnt++; + if (val->cnt != 0 && val->cnt != 1) + err = 1; + bpf_spin_unlock(&val->lock); + + /* spin_lock in array. virtual queue demo */ + q = bpf_map_lookup_elem(&vqueue, &key); + if (!q) + goto err; + curtime = bpf_ktime_get_ns(); + bpf_spin_lock(&q->lock); + q->credit += CREDIT_PER_NS(curtime - q->lasttime, q->rate); + q->lasttime = curtime; + if (q->credit > max_credit) + q->credit = max_credit; + q->credit -= pkt_len; + credit = q->credit; + bpf_spin_unlock(&q->lock); + + /* spin_lock in cgroup local storage */ + cls = bpf_get_local_storage(&cls_map, 0); + bpf_spin_lock(&cls->lock); + cls->cnt++; + bpf_spin_unlock(&cls->lock); + +err: + return err; +} +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_stack_map.c b/tools/testing/selftests/bpf/progs/test_stack_map.c index 31c3880e6da0..31c3880e6da0 100644 --- a/tools/testing/selftests/bpf/test_stack_map.c +++ b/tools/testing/selftests/bpf/progs/test_stack_map.c diff --git a/tools/testing/selftests/bpf/test_stacktrace_build_id.c b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c index d86c281e957f..d86c281e957f 100644 --- a/tools/testing/selftests/bpf/test_stacktrace_build_id.c +++ b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c diff --git a/tools/testing/selftests/bpf/test_stacktrace_map.c b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c index af111af7ca1a..af111af7ca1a 100644 --- a/tools/testing/selftests/bpf/test_stacktrace_map.c +++ b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c diff --git a/tools/testing/selftests/bpf/test_tcp_estats.c b/tools/testing/selftests/bpf/progs/test_tcp_estats.c index bee3bbecc0c4..bee3bbecc0c4 100644 --- a/tools/testing/selftests/bpf/test_tcp_estats.c +++ b/tools/testing/selftests/bpf/progs/test_tcp_estats.c diff --git a/tools/testing/selftests/bpf/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c index 74f73b33a7b0..74f73b33a7b0 100644 --- a/tools/testing/selftests/bpf/test_tcpbpf_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c diff --git a/tools/testing/selftests/bpf/test_tcpnotify_kern.c b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c index edbca203ce2d..edbca203ce2d 100644 --- a/tools/testing/selftests/bpf/test_tcpnotify_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c diff --git a/tools/testing/selftests/bpf/test_tracepoint.c b/tools/testing/selftests/bpf/progs/test_tracepoint.c index 04bf084517e0..04bf084517e0 100644 --- a/tools/testing/selftests/bpf/test_tracepoint.c +++ b/tools/testing/selftests/bpf/progs/test_tracepoint.c diff --git a/tools/testing/selftests/bpf/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c index 504df69c83df..504df69c83df 100644 --- a/tools/testing/selftests/bpf/test_tunnel_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c diff --git a/tools/testing/selftests/bpf/test_xdp.c b/tools/testing/selftests/bpf/progs/test_xdp.c index 5e7df8bb5b5d..5e7df8bb5b5d 100644 --- a/tools/testing/selftests/bpf/test_xdp.c +++ b/tools/testing/selftests/bpf/progs/test_xdp.c diff --git a/tools/testing/selftests/bpf/test_xdp_meta.c b/tools/testing/selftests/bpf/progs/test_xdp_meta.c index 8d0182650653..8d0182650653 100644 --- a/tools/testing/selftests/bpf/test_xdp_meta.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_meta.c diff --git a/tools/testing/selftests/bpf/test_xdp_noinline.c b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c index 5e4aac74f9d0..5e4aac74f9d0 100644 --- a/tools/testing/selftests/bpf/test_xdp_noinline.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c diff --git a/tools/testing/selftests/bpf/test_xdp_redirect.c b/tools/testing/selftests/bpf/progs/test_xdp_redirect.c index ef9e704be140..ef9e704be140 100644 --- a/tools/testing/selftests/bpf/test_xdp_redirect.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_redirect.c diff --git a/tools/testing/selftests/bpf/test_xdp_vlan.c b/tools/testing/selftests/bpf/progs/test_xdp_vlan.c index 365a7d2d9f5c..365a7d2d9f5c 100644 --- a/tools/testing/selftests/bpf/test_xdp_vlan.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_vlan.c diff --git a/tools/testing/selftests/bpf/xdp_dummy.c b/tools/testing/selftests/bpf/progs/xdp_dummy.c index 43b0ef1001ed..43b0ef1001ed 100644 --- a/tools/testing/selftests/bpf/xdp_dummy.c +++ b/tools/testing/selftests/bpf/progs/xdp_dummy.c diff --git a/tools/testing/selftests/bpf/tcp_client.py b/tools/testing/selftests/bpf/tcp_client.py index 7f8200a8702b..a53ed58528d6 100755 --- a/tools/testing/selftests/bpf/tcp_client.py +++ b/tools/testing/selftests/bpf/tcp_client.py @@ -30,12 +30,11 @@ def send(sock, s): serverPort = int(sys.argv[1]) -HostName = socket.gethostname() # create active socket sock = socket.socket(socket.AF_INET6, socket.SOCK_STREAM) try: - sock.connect((HostName, serverPort)) + sock.connect(('localhost', serverPort)) except socket.error as e: sys.exit(1) diff --git a/tools/testing/selftests/bpf/tcp_server.py b/tools/testing/selftests/bpf/tcp_server.py index b39903fca4c8..0ca60d193bed 100755 --- a/tools/testing/selftests/bpf/tcp_server.py +++ b/tools/testing/selftests/bpf/tcp_server.py @@ -35,13 +35,10 @@ MAX_PORTS = 2 serverPort = SERVER_PORT serverSocket = None -HostName = socket.gethostname() - # create passive socket serverSocket = socket.socket(socket.AF_INET6, socket.SOCK_STREAM) -host = socket.gethostname() -try: serverSocket.bind((host, 0)) +try: serverSocket.bind(('localhost', 0)) except socket.error as msg: print('bind fails: ' + str(msg)) diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c index 179f1d8ec5bf..02d314383a9c 100644 --- a/tools/testing/selftests/bpf/test_btf.c +++ b/tools/testing/selftests/bpf/test_btf.c @@ -52,18 +52,10 @@ static int count_result(int err) return err; } -#define __printf(a, b) __attribute__((format(printf, a, b))) - -__printf(1, 2) -static int __base_pr(const char *format, ...) +static int __base_pr(enum libbpf_print_level level __attribute__((unused)), + const char *format, va_list args) { - va_list args; - int err; - - va_start(args, format); - err = vfprintf(stderr, format, args); - va_end(args); - return err; + return vfprintf(stderr, format, args); } #define BTF_INFO_ENC(kind, kind_flag, vlen) \ @@ -78,12 +70,21 @@ static int __base_pr(const char *format, ...) BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz), \ BTF_INT_ENC(encoding, bits_offset, bits) +#define BTF_FWD_ENC(name, kind_flag) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FWD, kind_flag, 0), 0) + #define BTF_ARRAY_ENC(type, index_type, nr_elems) \ (type), (index_type), (nr_elems) #define BTF_TYPE_ARRAY_ENC(type, index_type, nr_elems) \ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ARRAY, 0, 0), 0), \ BTF_ARRAY_ENC(type, index_type, nr_elems) +#define BTF_STRUCT_ENC(name, nr_elems, sz) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, nr_elems), sz) + +#define BTF_UNION_ENC(name, nr_elems, sz) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_UNION, 0, nr_elems), sz) + #define BTF_MEMBER_ENC(name, type, bits_offset) \ (name), (type), (bits_offset) #define BTF_ENUM_ENC(name, val) (name), (val) @@ -99,6 +100,12 @@ static int __base_pr(const char *format, ...) #define BTF_CONST_ENC(type) \ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), type) +#define BTF_VOLATILE_ENC(type) \ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_VOLATILE, 0, 0), type) + +#define BTF_RESTRICT_ENC(type) \ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_RESTRICT, 0, 0), type) + #define BTF_FUNC_PROTO_ENC(ret_type, nargs) \ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, nargs), ret_type) @@ -111,6 +118,10 @@ static int __base_pr(const char *format, ...) #define BTF_END_RAW 0xdeadbeef #define NAME_TBD 0xdeadb33f +#define NAME_NTH(N) (0xffff0000 | N) +#define IS_NAME_NTH(X) ((X & 0xffff0000) == 0xffff0000) +#define GET_NAME_NTH_IDX(X) (X & 0x0000ffff) + #define MAX_NR_RAW_U32 1024 #define BTF_LOG_BUF_SIZE 65535 @@ -119,12 +130,14 @@ static struct args { unsigned int file_test_num; unsigned int get_info_test_num; unsigned int info_raw_test_num; + unsigned int dedup_test_num; bool raw_test; bool file_test; bool get_info_test; bool pprint_test; bool always_log; bool info_raw_test; + bool dedup_test; } args; static char btf_log_buf[BTF_LOG_BUF_SIZE]; @@ -1889,13 +1902,12 @@ static struct btf_raw_test raw_tests[] = { }, { - .descr = "func proto (CONST=>TYPEDEF=>FUNC_PROTO)", + .descr = "func proto (TYPEDEF=>FUNC_PROTO)", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_TYPE_INT_ENC(0, 0, 0, 32, 4), /* [2] */ - BTF_CONST_ENC(4), /* [3] */ - BTF_TYPEDEF_ENC(NAME_TBD, 5), /* [4] */ - BTF_FUNC_PROTO_ENC(0, 2), /* [5] */ + BTF_TYPEDEF_ENC(NAME_TBD, 4), /* [3] */ + BTF_FUNC_PROTO_ENC(0, 2), /* [4] */ BTF_FUNC_PROTO_ARG_ENC(0, 1), BTF_FUNC_PROTO_ARG_ENC(0, 2), BTF_END_RAW, @@ -1909,8 +1921,6 @@ static struct btf_raw_test raw_tests[] = { .key_type_id = 1, .value_type_id = 1, .max_entries = 4, - .btf_load_err = true, - .err_str = "Invalid type_id", }, { @@ -1965,7 +1975,7 @@ static struct btf_raw_test raw_tests[] = { /* void (*)(int a, unsigned int <bad_name_off>) */ BTF_FUNC_PROTO_ENC(0, 2), /* [3] */ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), - BTF_FUNC_PROTO_ARG_ENC(0xffffffff, 2), + BTF_FUNC_PROTO_ARG_ENC(0x0fffffff, 2), BTF_END_RAW, }, .str_sec = "\0a", @@ -2835,11 +2845,13 @@ static void *btf_raw_create(const struct btf_header *hdr, const char **ret_next_str) { const char *next_str = str, *end_str = str + str_sec_size; + const char **strs_idx = NULL, **tmp_strs_idx; + int strs_cap = 0, strs_cnt = 0, next_str_idx = 0; unsigned int size_needed, offset; struct btf_header *ret_hdr; - int i, type_sec_size; + int i, type_sec_size, err = 0; uint32_t *ret_types; - void *raw_btf; + void *raw_btf = NULL; type_sec_size = get_raw_sec_size(raw_types); if (CHECK(type_sec_size < 0, "Cannot get nr_raw_types")) @@ -2854,17 +2866,44 @@ static void *btf_raw_create(const struct btf_header *hdr, memcpy(raw_btf, hdr, sizeof(*hdr)); offset = sizeof(*hdr); + /* Index strings */ + while ((next_str = get_next_str(next_str, end_str))) { + if (strs_cnt == strs_cap) { + strs_cap += max(16, strs_cap / 2); + tmp_strs_idx = realloc(strs_idx, + sizeof(*strs_idx) * strs_cap); + if (CHECK(!tmp_strs_idx, + "Cannot allocate memory for strs_idx")) { + err = -1; + goto done; + } + strs_idx = tmp_strs_idx; + } + strs_idx[strs_cnt++] = next_str; + next_str += strlen(next_str); + } + /* Copy type section */ ret_types = raw_btf + offset; for (i = 0; i < type_sec_size / sizeof(raw_types[0]); i++) { if (raw_types[i] == NAME_TBD) { - next_str = get_next_str(next_str, end_str); - if (CHECK(!next_str, "Error in getting next_str")) { - free(raw_btf); - return NULL; + if (CHECK(next_str_idx == strs_cnt, + "Error in getting next_str #%d", + next_str_idx)) { + err = -1; + goto done; } - ret_types[i] = next_str - str; - next_str += strlen(next_str); + ret_types[i] = strs_idx[next_str_idx++] - str; + } else if (IS_NAME_NTH(raw_types[i])) { + int idx = GET_NAME_NTH_IDX(raw_types[i]); + + if (CHECK(idx <= 0 || idx > strs_cnt, + "Error getting string #%d, strs_cnt:%d", + idx, strs_cnt)) { + err = -1; + goto done; + } + ret_types[i] = strs_idx[idx-1] - str; } else { ret_types[i] = raw_types[i]; } @@ -2881,8 +2920,17 @@ static void *btf_raw_create(const struct btf_header *hdr, *btf_size = size_needed; if (ret_next_str) - *ret_next_str = next_str; + *ret_next_str = + next_str_idx < strs_cnt ? strs_idx[next_str_idx] : NULL; +done: + if (err) { + if (raw_btf) + free(raw_btf); + if (strs_idx) + free(strs_idx); + return NULL; + } return raw_btf; } @@ -5551,20 +5599,463 @@ static int test_info_raw(void) return err; } +struct btf_raw_data { + __u32 raw_types[MAX_NR_RAW_U32]; + const char *str_sec; + __u32 str_sec_size; +}; + +struct btf_dedup_test { + const char *descr; + struct btf_raw_data input; + struct btf_raw_data expect; + struct btf_dedup_opts opts; +}; + +const struct btf_dedup_test dedup_tests[] = { + +{ + .descr = "dedup: unused strings filtering", + .input = { + .raw_types = { + BTF_TYPE_INT_ENC(NAME_NTH(2), BTF_INT_SIGNED, 0, 32, 4), + BTF_TYPE_INT_ENC(NAME_NTH(5), BTF_INT_SIGNED, 0, 64, 8), + BTF_END_RAW, + }, + BTF_STR_SEC("\0unused\0int\0foo\0bar\0long"), + }, + .expect = { + .raw_types = { + BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 32, 4), + BTF_TYPE_INT_ENC(NAME_NTH(2), BTF_INT_SIGNED, 0, 64, 8), + BTF_END_RAW, + }, + BTF_STR_SEC("\0int\0long"), + }, + .opts = { + .dont_resolve_fwds = false, + }, +}, +{ + .descr = "dedup: strings deduplication", + .input = { + .raw_types = { + BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 32, 4), + BTF_TYPE_INT_ENC(NAME_NTH(2), BTF_INT_SIGNED, 0, 64, 8), + BTF_TYPE_INT_ENC(NAME_NTH(3), BTF_INT_SIGNED, 0, 32, 4), + BTF_TYPE_INT_ENC(NAME_NTH(4), BTF_INT_SIGNED, 0, 64, 8), + BTF_TYPE_INT_ENC(NAME_NTH(5), BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + BTF_STR_SEC("\0int\0long int\0int\0long int\0int"), + }, + .expect = { + .raw_types = { + BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 32, 4), + BTF_TYPE_INT_ENC(NAME_NTH(2), BTF_INT_SIGNED, 0, 64, 8), + BTF_END_RAW, + }, + BTF_STR_SEC("\0int\0long int"), + }, + .opts = { + .dont_resolve_fwds = false, + }, +}, +{ + .descr = "dedup: struct example #1", + /* + * struct s { + * struct s *next; + * const int *a; + * int b[16]; + * int c; + * } + */ + .input = { + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* int[16] */ + BTF_TYPE_ARRAY_ENC(1, 1, 16), /* [2] */ + /* struct s { */ + BTF_STRUCT_ENC(NAME_NTH(2), 4, 84), /* [3] */ + BTF_MEMBER_ENC(NAME_NTH(3), 4, 0), /* struct s *next; */ + BTF_MEMBER_ENC(NAME_NTH(4), 5, 64), /* const int *a; */ + BTF_MEMBER_ENC(NAME_NTH(5), 2, 128), /* int b[16]; */ + BTF_MEMBER_ENC(NAME_NTH(6), 1, 640), /* int c; */ + /* ptr -> [3] struct s */ + BTF_PTR_ENC(3), /* [4] */ + /* ptr -> [6] const int */ + BTF_PTR_ENC(6), /* [5] */ + /* const -> [1] int */ + BTF_CONST_ENC(1), /* [6] */ + + /* full copy of the above */ + BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 32, 4), /* [7] */ + BTF_TYPE_ARRAY_ENC(7, 7, 16), /* [8] */ + BTF_STRUCT_ENC(NAME_NTH(2), 4, 84), /* [9] */ + BTF_MEMBER_ENC(NAME_NTH(3), 10, 0), + BTF_MEMBER_ENC(NAME_NTH(4), 11, 64), + BTF_MEMBER_ENC(NAME_NTH(5), 8, 128), + BTF_MEMBER_ENC(NAME_NTH(6), 7, 640), + BTF_PTR_ENC(9), /* [10] */ + BTF_PTR_ENC(12), /* [11] */ + BTF_CONST_ENC(7), /* [12] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0int\0s\0next\0a\0b\0c\0"), + }, + .expect = { + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(NAME_NTH(4), BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* int[16] */ + BTF_TYPE_ARRAY_ENC(1, 1, 16), /* [2] */ + /* struct s { */ + BTF_STRUCT_ENC(NAME_NTH(6), 4, 84), /* [3] */ + BTF_MEMBER_ENC(NAME_NTH(5), 4, 0), /* struct s *next; */ + BTF_MEMBER_ENC(NAME_NTH(1), 5, 64), /* const int *a; */ + BTF_MEMBER_ENC(NAME_NTH(2), 2, 128), /* int b[16]; */ + BTF_MEMBER_ENC(NAME_NTH(3), 1, 640), /* int c; */ + /* ptr -> [3] struct s */ + BTF_PTR_ENC(3), /* [4] */ + /* ptr -> [6] const int */ + BTF_PTR_ENC(6), /* [5] */ + /* const -> [1] int */ + BTF_CONST_ENC(1), /* [6] */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0a\0b\0c\0int\0next\0s"), + }, + .opts = { + .dont_resolve_fwds = false, + }, +}, +{ + .descr = "dedup: all possible kinds (no duplicates)", + .input = { + .raw_types = { + BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 8), /* [1] int */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 2), 4), /* [2] enum */ + BTF_ENUM_ENC(NAME_TBD, 0), + BTF_ENUM_ENC(NAME_TBD, 1), + BTF_FWD_ENC(NAME_TBD, 1 /* union kind_flag */), /* [3] fwd */ + BTF_TYPE_ARRAY_ENC(2, 1, 7), /* [4] array */ + BTF_STRUCT_ENC(NAME_TBD, 1, 4), /* [5] struct */ + BTF_MEMBER_ENC(NAME_TBD, 1, 0), + BTF_UNION_ENC(NAME_TBD, 1, 4), /* [6] union */ + BTF_MEMBER_ENC(NAME_TBD, 1, 0), + BTF_TYPEDEF_ENC(NAME_TBD, 1), /* [7] typedef */ + BTF_PTR_ENC(0), /* [8] ptr */ + BTF_CONST_ENC(8), /* [9] const */ + BTF_VOLATILE_ENC(8), /* [10] volatile */ + BTF_RESTRICT_ENC(8), /* [11] restrict */ + BTF_FUNC_PROTO_ENC(1, 2), /* [12] func_proto */ + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 8), + BTF_FUNC_ENC(NAME_TBD, 12), /* [13] func */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M"), + }, + .expect = { + .raw_types = { + BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 8), /* [1] int */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 2), 4), /* [2] enum */ + BTF_ENUM_ENC(NAME_TBD, 0), + BTF_ENUM_ENC(NAME_TBD, 1), + BTF_FWD_ENC(NAME_TBD, 1 /* union kind_flag */), /* [3] fwd */ + BTF_TYPE_ARRAY_ENC(2, 1, 7), /* [4] array */ + BTF_STRUCT_ENC(NAME_TBD, 1, 4), /* [5] struct */ + BTF_MEMBER_ENC(NAME_TBD, 1, 0), + BTF_UNION_ENC(NAME_TBD, 1, 4), /* [6] union */ + BTF_MEMBER_ENC(NAME_TBD, 1, 0), + BTF_TYPEDEF_ENC(NAME_TBD, 1), /* [7] typedef */ + BTF_PTR_ENC(0), /* [8] ptr */ + BTF_CONST_ENC(8), /* [9] const */ + BTF_VOLATILE_ENC(8), /* [10] volatile */ + BTF_RESTRICT_ENC(8), /* [11] restrict */ + BTF_FUNC_PROTO_ENC(1, 2), /* [12] func_proto */ + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), + BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 8), + BTF_FUNC_ENC(NAME_TBD, 12), /* [13] func */ + BTF_END_RAW, + }, + BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M"), + }, + .opts = { + .dont_resolve_fwds = false, + }, +}, +{ + .descr = "dedup: no int duplicates", + .input = { + .raw_types = { + BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 32, 8), + /* different name */ + BTF_TYPE_INT_ENC(NAME_NTH(2), BTF_INT_SIGNED, 0, 32, 8), + /* different encoding */ + BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_CHAR, 0, 32, 8), + BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_BOOL, 0, 32, 8), + /* different bit offset */ + BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 8, 32, 8), + /* different bit size */ + BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 27, 8), + /* different byte size */ + BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + BTF_STR_SEC("\0int\0some other int"), + }, + .expect = { + .raw_types = { + BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 32, 8), + /* different name */ + BTF_TYPE_INT_ENC(NAME_NTH(2), BTF_INT_SIGNED, 0, 32, 8), + /* different encoding */ + BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_CHAR, 0, 32, 8), + BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_BOOL, 0, 32, 8), + /* different bit offset */ + BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 8, 32, 8), + /* different bit size */ + BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 27, 8), + /* different byte size */ + BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + BTF_STR_SEC("\0int\0some other int"), + }, + .opts = { + .dont_resolve_fwds = false, + }, +}, + +}; + +static int btf_type_size(const struct btf_type *t) +{ + int base_size = sizeof(struct btf_type); + __u16 vlen = BTF_INFO_VLEN(t->info); + __u16 kind = BTF_INFO_KIND(t->info); + + switch (kind) { + case BTF_KIND_FWD: + case BTF_KIND_CONST: + case BTF_KIND_VOLATILE: + case BTF_KIND_RESTRICT: + case BTF_KIND_PTR: + case BTF_KIND_TYPEDEF: + case BTF_KIND_FUNC: + return base_size; + case BTF_KIND_INT: + return base_size + sizeof(__u32); + case BTF_KIND_ENUM: + return base_size + vlen * sizeof(struct btf_enum); + case BTF_KIND_ARRAY: + return base_size + sizeof(struct btf_array); + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + return base_size + vlen * sizeof(struct btf_member); + case BTF_KIND_FUNC_PROTO: + return base_size + vlen * sizeof(struct btf_param); + default: + fprintf(stderr, "Unsupported BTF_KIND:%u\n", kind); + return -EINVAL; + } +} + +static void dump_btf_strings(const char *strs, __u32 len) +{ + const char *cur = strs; + int i = 0; + + while (cur < strs + len) { + fprintf(stderr, "string #%d: '%s'\n", i, cur); + cur += strlen(cur) + 1; + i++; + } +} + +static int do_test_dedup(unsigned int test_num) +{ + const struct btf_dedup_test *test = &dedup_tests[test_num - 1]; + __u32 test_nr_types, expect_nr_types, test_btf_size, expect_btf_size; + const struct btf_header *test_hdr, *expect_hdr; + struct btf *test_btf = NULL, *expect_btf = NULL; + const void *test_btf_data, *expect_btf_data; + const char *ret_test_next_str, *ret_expect_next_str; + const char *test_strs, *expect_strs; + const char *test_str_cur, *test_str_end; + const char *expect_str_cur, *expect_str_end; + unsigned int raw_btf_size; + void *raw_btf; + int err = 0, i; + + fprintf(stderr, "BTF dedup test[%u] (%s):", test_num, test->descr); + + raw_btf = btf_raw_create(&hdr_tmpl, test->input.raw_types, + test->input.str_sec, test->input.str_sec_size, + &raw_btf_size, &ret_test_next_str); + if (!raw_btf) + return -1; + test_btf = btf__new((__u8 *)raw_btf, raw_btf_size); + free(raw_btf); + if (CHECK(IS_ERR(test_btf), "invalid test_btf errno:%ld", + PTR_ERR(test_btf))) { + err = -1; + goto done; + } + + raw_btf = btf_raw_create(&hdr_tmpl, test->expect.raw_types, + test->expect.str_sec, + test->expect.str_sec_size, + &raw_btf_size, &ret_expect_next_str); + if (!raw_btf) + return -1; + expect_btf = btf__new((__u8 *)raw_btf, raw_btf_size); + free(raw_btf); + if (CHECK(IS_ERR(expect_btf), "invalid expect_btf errno:%ld", + PTR_ERR(expect_btf))) { + err = -1; + goto done; + } + + err = btf__dedup(test_btf, NULL, &test->opts); + if (CHECK(err, "btf_dedup failed errno:%d", err)) { + err = -1; + goto done; + } + + test_btf_data = btf__get_raw_data(test_btf, &test_btf_size); + expect_btf_data = btf__get_raw_data(expect_btf, &expect_btf_size); + if (CHECK(test_btf_size != expect_btf_size, + "test_btf_size:%u != expect_btf_size:%u", + test_btf_size, expect_btf_size)) { + err = -1; + goto done; + } + + test_hdr = test_btf_data; + test_strs = test_btf_data + test_hdr->str_off; + expect_hdr = expect_btf_data; + expect_strs = expect_btf_data + expect_hdr->str_off; + if (CHECK(test_hdr->str_len != expect_hdr->str_len, + "test_hdr->str_len:%u != expect_hdr->str_len:%u", + test_hdr->str_len, expect_hdr->str_len)) { + fprintf(stderr, "\ntest strings:\n"); + dump_btf_strings(test_strs, test_hdr->str_len); + fprintf(stderr, "\nexpected strings:\n"); + dump_btf_strings(expect_strs, expect_hdr->str_len); + err = -1; + goto done; + } + + test_str_cur = test_strs; + test_str_end = test_strs + test_hdr->str_len; + expect_str_cur = expect_strs; + expect_str_end = expect_strs + expect_hdr->str_len; + while (test_str_cur < test_str_end && expect_str_cur < expect_str_end) { + size_t test_len, expect_len; + + test_len = strlen(test_str_cur); + expect_len = strlen(expect_str_cur); + if (CHECK(test_len != expect_len, + "test_len:%zu != expect_len:%zu " + "(test_str:%s, expect_str:%s)", + test_len, expect_len, test_str_cur, expect_str_cur)) { + err = -1; + goto done; + } + if (CHECK(strcmp(test_str_cur, expect_str_cur), + "test_str:%s != expect_str:%s", + test_str_cur, expect_str_cur)) { + err = -1; + goto done; + } + test_str_cur += test_len + 1; + expect_str_cur += expect_len + 1; + } + if (CHECK(test_str_cur != test_str_end, + "test_str_cur:%p != test_str_end:%p", + test_str_cur, test_str_end)) { + err = -1; + goto done; + } + + test_nr_types = btf__get_nr_types(test_btf); + expect_nr_types = btf__get_nr_types(expect_btf); + if (CHECK(test_nr_types != expect_nr_types, + "test_nr_types:%u != expect_nr_types:%u", + test_nr_types, expect_nr_types)) { + err = -1; + goto done; + } + + for (i = 1; i <= test_nr_types; i++) { + const struct btf_type *test_type, *expect_type; + int test_size, expect_size; + + test_type = btf__type_by_id(test_btf, i); + expect_type = btf__type_by_id(expect_btf, i); + test_size = btf_type_size(test_type); + expect_size = btf_type_size(expect_type); + + if (CHECK(test_size != expect_size, + "type #%d: test_size:%d != expect_size:%u", + i, test_size, expect_size)) { + err = -1; + goto done; + } + if (CHECK(memcmp((void *)test_type, + (void *)expect_type, + test_size), + "type #%d: contents differ", i)) { + err = -1; + goto done; + } + } + +done: + if (!err) + fprintf(stderr, "OK"); + if (!IS_ERR(test_btf)) + btf__free(test_btf); + if (!IS_ERR(expect_btf)) + btf__free(expect_btf); + + return err; +} + +static int test_dedup(void) +{ + unsigned int i; + int err = 0; + + if (args.dedup_test_num) + return count_result(do_test_dedup(args.dedup_test_num)); + + for (i = 1; i <= ARRAY_SIZE(dedup_tests); i++) + err |= count_result(do_test_dedup(i)); + + return err; +} + static void usage(const char *cmd) { fprintf(stderr, "Usage: %s [-l] [[-r btf_raw_test_num (1 - %zu)] |\n" "\t[-g btf_get_info_test_num (1 - %zu)] |\n" "\t[-f btf_file_test_num (1 - %zu)] |\n" "\t[-k btf_prog_info_raw_test_num (1 - %zu)] |\n" - "\t[-p (pretty print test)]]\n", + "\t[-p (pretty print test)] |\n" + "\t[-d btf_dedup_test_num (1 - %zu)]]\n", cmd, ARRAY_SIZE(raw_tests), ARRAY_SIZE(get_info_tests), - ARRAY_SIZE(file_tests), ARRAY_SIZE(info_raw_tests)); + ARRAY_SIZE(file_tests), ARRAY_SIZE(info_raw_tests), + ARRAY_SIZE(dedup_tests)); } static int parse_args(int argc, char **argv) { - const char *optstr = "lpk:f:r:g:"; + const char *optstr = "hlpk:f:r:g:d:"; int opt; while ((opt = getopt(argc, argv, optstr)) != -1) { @@ -5591,12 +6082,16 @@ static int parse_args(int argc, char **argv) args.info_raw_test_num = atoi(optarg); args.info_raw_test = true; break; + case 'd': + args.dedup_test_num = atoi(optarg); + args.dedup_test = true; + break; case 'h': usage(argv[0]); exit(0); default: - usage(argv[0]); - return -1; + usage(argv[0]); + return -1; } } @@ -5632,6 +6127,14 @@ static int parse_args(int argc, char **argv) return -1; } + if (args.dedup_test_num && + (args.dedup_test_num < 1 || + args.dedup_test_num > ARRAY_SIZE(dedup_tests))) { + fprintf(stderr, "BTF dedup test number must be [1 - %zu]\n", + ARRAY_SIZE(dedup_tests)); + return -1; + } + return 0; } @@ -5650,7 +6153,7 @@ int main(int argc, char **argv) return err; if (args.always_log) - libbpf_set_print(__base_pr, __base_pr, __base_pr); + libbpf_set_print(__base_pr); if (args.raw_test) err |= test_raw(); @@ -5667,14 +6170,18 @@ int main(int argc, char **argv) if (args.info_raw_test) err |= test_info_raw(); + if (args.dedup_test) + err |= test_dedup(); + if (args.raw_test || args.get_info_test || args.file_test || - args.pprint_test || args.info_raw_test) + args.pprint_test || args.info_raw_test || args.dedup_test) goto done; err |= test_raw(); err |= test_get_info(); err |= test_file(); err |= test_info_raw(); + err |= test_dedup(); done: print_summary(); diff --git a/tools/testing/selftests/bpf/test_libbpf_open.c b/tools/testing/selftests/bpf/test_libbpf_open.c index 8fcd1c076add..1909ecf4d999 100644 --- a/tools/testing/selftests/bpf/test_libbpf_open.c +++ b/tools/testing/selftests/bpf/test_libbpf_open.c @@ -34,23 +34,16 @@ static void usage(char *argv[]) printf("\n"); } -#define DEFINE_PRINT_FN(name, enabled) \ -static int libbpf_##name(const char *fmt, ...) \ -{ \ - va_list args; \ - int ret; \ - \ - va_start(args, fmt); \ - if (enabled) { \ - fprintf(stderr, "[" #name "] "); \ - ret = vfprintf(stderr, fmt, args); \ - } \ - va_end(args); \ - return ret; \ +static bool debug = 0; +static int libbpf_debug_print(enum libbpf_print_level level, + const char *fmt, va_list args) +{ + if (level == LIBBPF_DEBUG && !debug) + return 0; + + fprintf(stderr, "[%d] ", level); + return vfprintf(stderr, fmt, args); } -DEFINE_PRINT_FN(warning, 1) -DEFINE_PRINT_FN(info, 1) -DEFINE_PRINT_FN(debug, 1) #define EXIT_FAIL_LIBBPF EXIT_FAILURE #define EXIT_FAIL_OPTION 2 @@ -120,15 +113,14 @@ int main(int argc, char **argv) int longindex = 0; int opt; - libbpf_set_print(libbpf_warning, libbpf_info, NULL); + libbpf_set_print(libbpf_debug_print); /* Parse commands line args */ while ((opt = getopt_long(argc, argv, "hDq", long_options, &longindex)) != -1) { switch (opt) { case 'D': - libbpf_set_print(libbpf_warning, libbpf_info, - libbpf_debug); + debug = 1; break; case 'q': /* Use in scripting mode */ verbose = 0; diff --git a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh new file mode 100755 index 000000000000..612632c1425f --- /dev/null +++ b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh @@ -0,0 +1,376 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Setup/topology: +# +# NS1 NS2 NS3 +# veth1 <---> veth2 veth3 <---> veth4 (the top route) +# veth5 <---> veth6 veth7 <---> veth8 (the bottom route) +# +# each vethN gets IPv[4|6]_N address +# +# IPv*_SRC = IPv*_1 +# IPv*_DST = IPv*_4 +# +# all tests test pings from IPv*_SRC to IPv*_DST +# +# by default, routes are configured to allow packets to go +# IP*_1 <=> IP*_2 <=> IP*_3 <=> IP*_4 (the top route) +# +# a GRE device is installed in NS3 with IPv*_GRE, and +# NS1/NS2 are configured to route packets to IPv*_GRE via IP*_8 +# (the bottom route) +# +# Tests: +# +# 1. routes NS2->IPv*_DST are brought down, so the only way a ping +# from IP*_SRC to IP*_DST can work is via IPv*_GRE +# +# 2a. in an egress test, a bpf LWT_XMIT program is installed on veth1 +# that encaps the packets with an IP/GRE header to route to IPv*_GRE +# +# ping: SRC->[encap at veth1:egress]->GRE:decap->DST +# ping replies go DST->SRC directly +# +# 2b. in an ingress test, a bpf LWT_IN program is installed on veth2 +# that encaps the packets with an IP/GRE header to route to IPv*_GRE +# +# ping: SRC->[encap at veth2:ingress]->GRE:decap->DST +# ping replies go DST->SRC directly + +if [[ $EUID -ne 0 ]]; then + echo "This script must be run as root" + echo "FAIL" + exit 1 +fi + +readonly NS1="ns1-$(mktemp -u XXXXXX)" +readonly NS2="ns2-$(mktemp -u XXXXXX)" +readonly NS3="ns3-$(mktemp -u XXXXXX)" + +readonly IPv4_1="172.16.1.100" +readonly IPv4_2="172.16.2.100" +readonly IPv4_3="172.16.3.100" +readonly IPv4_4="172.16.4.100" +readonly IPv4_5="172.16.5.100" +readonly IPv4_6="172.16.6.100" +readonly IPv4_7="172.16.7.100" +readonly IPv4_8="172.16.8.100" +readonly IPv4_GRE="172.16.16.100" + +readonly IPv4_SRC=$IPv4_1 +readonly IPv4_DST=$IPv4_4 + +readonly IPv6_1="fb01::1" +readonly IPv6_2="fb02::1" +readonly IPv6_3="fb03::1" +readonly IPv6_4="fb04::1" +readonly IPv6_5="fb05::1" +readonly IPv6_6="fb06::1" +readonly IPv6_7="fb07::1" +readonly IPv6_8="fb08::1" +readonly IPv6_GRE="fb10::1" + +readonly IPv6_SRC=$IPv6_1 +readonly IPv6_DST=$IPv6_4 + +TEST_STATUS=0 +TESTS_SUCCEEDED=0 +TESTS_FAILED=0 + +process_test_results() +{ + if [[ "${TEST_STATUS}" -eq 0 ]] ; then + echo "PASS" + TESTS_SUCCEEDED=$((TESTS_SUCCEEDED+1)) + else + echo "FAIL" + TESTS_FAILED=$((TESTS_FAILED+1)) + fi +} + +print_test_summary_and_exit() +{ + echo "passed tests: ${TESTS_SUCCEEDED}" + echo "failed tests: ${TESTS_FAILED}" + if [ "${TESTS_FAILED}" -eq "0" ] ; then + exit 0 + else + exit 1 + fi +} + +setup() +{ + set -e # exit on error + TEST_STATUS=0 + + # create devices and namespaces + ip netns add "${NS1}" + ip netns add "${NS2}" + ip netns add "${NS3}" + + ip link add veth1 type veth peer name veth2 + ip link add veth3 type veth peer name veth4 + ip link add veth5 type veth peer name veth6 + ip link add veth7 type veth peer name veth8 + + ip netns exec ${NS2} sysctl -wq net.ipv4.ip_forward=1 + ip netns exec ${NS2} sysctl -wq net.ipv6.conf.all.forwarding=1 + + ip link set veth1 netns ${NS1} + ip link set veth2 netns ${NS2} + ip link set veth3 netns ${NS2} + ip link set veth4 netns ${NS3} + ip link set veth5 netns ${NS1} + ip link set veth6 netns ${NS2} + ip link set veth7 netns ${NS2} + ip link set veth8 netns ${NS3} + + # configure addesses: the top route (1-2-3-4) + ip -netns ${NS1} addr add ${IPv4_1}/24 dev veth1 + ip -netns ${NS2} addr add ${IPv4_2}/24 dev veth2 + ip -netns ${NS2} addr add ${IPv4_3}/24 dev veth3 + ip -netns ${NS3} addr add ${IPv4_4}/24 dev veth4 + ip -netns ${NS1} -6 addr add ${IPv6_1}/128 nodad dev veth1 + ip -netns ${NS2} -6 addr add ${IPv6_2}/128 nodad dev veth2 + ip -netns ${NS2} -6 addr add ${IPv6_3}/128 nodad dev veth3 + ip -netns ${NS3} -6 addr add ${IPv6_4}/128 nodad dev veth4 + + # configure addresses: the bottom route (5-6-7-8) + ip -netns ${NS1} addr add ${IPv4_5}/24 dev veth5 + ip -netns ${NS2} addr add ${IPv4_6}/24 dev veth6 + ip -netns ${NS2} addr add ${IPv4_7}/24 dev veth7 + ip -netns ${NS3} addr add ${IPv4_8}/24 dev veth8 + ip -netns ${NS1} -6 addr add ${IPv6_5}/128 nodad dev veth5 + ip -netns ${NS2} -6 addr add ${IPv6_6}/128 nodad dev veth6 + ip -netns ${NS2} -6 addr add ${IPv6_7}/128 nodad dev veth7 + ip -netns ${NS3} -6 addr add ${IPv6_8}/128 nodad dev veth8 + + + ip -netns ${NS1} link set dev veth1 up + ip -netns ${NS2} link set dev veth2 up + ip -netns ${NS2} link set dev veth3 up + ip -netns ${NS3} link set dev veth4 up + ip -netns ${NS1} link set dev veth5 up + ip -netns ${NS2} link set dev veth6 up + ip -netns ${NS2} link set dev veth7 up + ip -netns ${NS3} link set dev veth8 up + + # configure routes: IP*_SRC -> veth1/IP*_2 (= top route) default; + # the bottom route to specific bottom addresses + + # NS1 + # top route + ip -netns ${NS1} route add ${IPv4_2}/32 dev veth1 + ip -netns ${NS1} route add default dev veth1 via ${IPv4_2} # go top by default + ip -netns ${NS1} -6 route add ${IPv6_2}/128 dev veth1 + ip -netns ${NS1} -6 route add default dev veth1 via ${IPv6_2} # go top by default + # bottom route + ip -netns ${NS1} route add ${IPv4_6}/32 dev veth5 + ip -netns ${NS1} route add ${IPv4_7}/32 dev veth5 via ${IPv4_6} + ip -netns ${NS1} route add ${IPv4_8}/32 dev veth5 via ${IPv4_6} + ip -netns ${NS1} -6 route add ${IPv6_6}/128 dev veth5 + ip -netns ${NS1} -6 route add ${IPv6_7}/128 dev veth5 via ${IPv6_6} + ip -netns ${NS1} -6 route add ${IPv6_8}/128 dev veth5 via ${IPv6_6} + + # NS2 + # top route + ip -netns ${NS2} route add ${IPv4_1}/32 dev veth2 + ip -netns ${NS2} route add ${IPv4_4}/32 dev veth3 + ip -netns ${NS2} -6 route add ${IPv6_1}/128 dev veth2 + ip -netns ${NS2} -6 route add ${IPv6_4}/128 dev veth3 + # bottom route + ip -netns ${NS2} route add ${IPv4_5}/32 dev veth6 + ip -netns ${NS2} route add ${IPv4_8}/32 dev veth7 + ip -netns ${NS2} -6 route add ${IPv6_5}/128 dev veth6 + ip -netns ${NS2} -6 route add ${IPv6_8}/128 dev veth7 + + # NS3 + # top route + ip -netns ${NS3} route add ${IPv4_3}/32 dev veth4 + ip -netns ${NS3} route add ${IPv4_1}/32 dev veth4 via ${IPv4_3} + ip -netns ${NS3} route add ${IPv4_2}/32 dev veth4 via ${IPv4_3} + ip -netns ${NS3} -6 route add ${IPv6_3}/128 dev veth4 + ip -netns ${NS3} -6 route add ${IPv6_1}/128 dev veth4 via ${IPv6_3} + ip -netns ${NS3} -6 route add ${IPv6_2}/128 dev veth4 via ${IPv6_3} + # bottom route + ip -netns ${NS3} route add ${IPv4_7}/32 dev veth8 + ip -netns ${NS3} route add ${IPv4_5}/32 dev veth8 via ${IPv4_7} + ip -netns ${NS3} route add ${IPv4_6}/32 dev veth8 via ${IPv4_7} + ip -netns ${NS3} -6 route add ${IPv6_7}/128 dev veth8 + ip -netns ${NS3} -6 route add ${IPv6_5}/128 dev veth8 via ${IPv6_7} + ip -netns ${NS3} -6 route add ${IPv6_6}/128 dev veth8 via ${IPv6_7} + + # configure IPv4 GRE device in NS3, and a route to it via the "bottom" route + ip -netns ${NS3} tunnel add gre_dev mode gre remote ${IPv4_1} local ${IPv4_GRE} ttl 255 + ip -netns ${NS3} link set gre_dev up + ip -netns ${NS3} addr add ${IPv4_GRE} nodad dev gre_dev + ip -netns ${NS1} route add ${IPv4_GRE}/32 dev veth5 via ${IPv4_6} + ip -netns ${NS2} route add ${IPv4_GRE}/32 dev veth7 via ${IPv4_8} + + + # configure IPv6 GRE device in NS3, and a route to it via the "bottom" route + ip -netns ${NS3} -6 tunnel add name gre6_dev mode ip6gre remote ${IPv6_1} local ${IPv6_GRE} ttl 255 + ip -netns ${NS3} link set gre6_dev up + ip -netns ${NS3} -6 addr add ${IPv6_GRE} nodad dev gre6_dev + ip -netns ${NS1} -6 route add ${IPv6_GRE}/128 dev veth5 via ${IPv6_6} + ip -netns ${NS2} -6 route add ${IPv6_GRE}/128 dev veth7 via ${IPv6_8} + + # rp_filter gets confused by what these tests are doing, so disable it + ip netns exec ${NS1} sysctl -wq net.ipv4.conf.all.rp_filter=0 + ip netns exec ${NS2} sysctl -wq net.ipv4.conf.all.rp_filter=0 + ip netns exec ${NS3} sysctl -wq net.ipv4.conf.all.rp_filter=0 + + sleep 1 # reduce flakiness + set +e +} + +cleanup() +{ + ip netns del ${NS1} 2> /dev/null + ip netns del ${NS2} 2> /dev/null + ip netns del ${NS3} 2> /dev/null +} + +trap cleanup EXIT + +remove_routes_to_gredev() +{ + ip -netns ${NS1} route del ${IPv4_GRE} dev veth5 + ip -netns ${NS2} route del ${IPv4_GRE} dev veth7 + ip -netns ${NS1} -6 route del ${IPv6_GRE}/128 dev veth5 + ip -netns ${NS2} -6 route del ${IPv6_GRE}/128 dev veth7 +} + +add_unreachable_routes_to_gredev() +{ + ip -netns ${NS1} route add unreachable ${IPv4_GRE}/32 + ip -netns ${NS2} route add unreachable ${IPv4_GRE}/32 + ip -netns ${NS1} -6 route add unreachable ${IPv6_GRE}/128 + ip -netns ${NS2} -6 route add unreachable ${IPv6_GRE}/128 +} + +test_ping() +{ + local readonly PROTO=$1 + local readonly EXPECTED=$2 + local RET=0 + + if [ "${PROTO}" == "IPv4" ] ; then + ip netns exec ${NS1} ping -c 1 -W 1 -I ${IPv4_SRC} ${IPv4_DST} 2>&1 > /dev/null + RET=$? + elif [ "${PROTO}" == "IPv6" ] ; then + ip netns exec ${NS1} ping6 -c 1 -W 6 -I ${IPv6_SRC} ${IPv6_DST} 2>&1 > /dev/null + RET=$? + else + echo " test_ping: unknown PROTO: ${PROTO}" + TEST_STATUS=1 + fi + + if [ "0" != "${RET}" ]; then + RET=1 + fi + + if [ "${EXPECTED}" != "${RET}" ] ; then + echo " test_ping failed: expected: ${EXPECTED}; got ${RET}" + TEST_STATUS=1 + fi +} + +test_egress() +{ + local readonly ENCAP=$1 + echo "starting egress ${ENCAP} encap test" + setup + + # by default, pings work + test_ping IPv4 0 + test_ping IPv6 0 + + # remove NS2->DST routes, ping fails + ip -netns ${NS2} route del ${IPv4_DST}/32 dev veth3 + ip -netns ${NS2} -6 route del ${IPv6_DST}/128 dev veth3 + test_ping IPv4 1 + test_ping IPv6 1 + + # install replacement routes (LWT/eBPF), pings succeed + if [ "${ENCAP}" == "IPv4" ] ; then + ip -netns ${NS1} route add ${IPv4_DST} encap bpf xmit obj test_lwt_ip_encap.o sec encap_gre dev veth1 + ip -netns ${NS1} -6 route add ${IPv6_DST} encap bpf xmit obj test_lwt_ip_encap.o sec encap_gre dev veth1 + elif [ "${ENCAP}" == "IPv6" ] ; then + ip -netns ${NS1} route add ${IPv4_DST} encap bpf xmit obj test_lwt_ip_encap.o sec encap_gre6 dev veth1 + ip -netns ${NS1} -6 route add ${IPv6_DST} encap bpf xmit obj test_lwt_ip_encap.o sec encap_gre6 dev veth1 + else + echo " unknown encap ${ENCAP}" + TEST_STATUS=1 + fi + test_ping IPv4 0 + test_ping IPv6 0 + + # a negative test: remove routes to GRE devices: ping fails + remove_routes_to_gredev + test_ping IPv4 1 + test_ping IPv6 1 + + # another negative test + add_unreachable_routes_to_gredev + test_ping IPv4 1 + test_ping IPv6 1 + + cleanup + process_test_results +} + +test_ingress() +{ + local readonly ENCAP=$1 + echo "starting ingress ${ENCAP} encap test" + setup + + # need to wait a bit for IPv6 to autoconf, otherwise + # ping6 sometimes fails with "unable to bind to address" + + # by default, pings work + test_ping IPv4 0 + test_ping IPv6 0 + + # remove NS2->DST routes, pings fail + ip -netns ${NS2} route del ${IPv4_DST}/32 dev veth3 + ip -netns ${NS2} -6 route del ${IPv6_DST}/128 dev veth3 + test_ping IPv4 1 + test_ping IPv6 1 + + # install replacement routes (LWT/eBPF), pings succeed + if [ "${ENCAP}" == "IPv4" ] ; then + ip -netns ${NS2} route add ${IPv4_DST} encap bpf in obj test_lwt_ip_encap.o sec encap_gre dev veth2 + ip -netns ${NS2} -6 route add ${IPv6_DST} encap bpf in obj test_lwt_ip_encap.o sec encap_gre dev veth2 + elif [ "${ENCAP}" == "IPv6" ] ; then + ip -netns ${NS2} route add ${IPv4_DST} encap bpf in obj test_lwt_ip_encap.o sec encap_gre6 dev veth2 + ip -netns ${NS2} -6 route add ${IPv6_DST} encap bpf in obj test_lwt_ip_encap.o sec encap_gre6 dev veth2 + else + echo "FAIL: unknown encap ${ENCAP}" + fi + test_ping IPv4 0 + test_ping IPv6 0 + + # a negative test: remove routes to GRE devices: ping fails + remove_routes_to_gredev + test_ping IPv4 1 + test_ping IPv6 1 + + # another negative test + add_unreachable_routes_to_gredev + test_ping IPv4 1 + test_ping IPv6 1 + + cleanup + process_test_results +} + +test_egress IPv4 +test_egress IPv6 +test_ingress IPv4 +test_ingress IPv6 + +print_test_summary_and_exit diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index 1dfef77cff6f..3c627771f965 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -32,6 +32,8 @@ #define ENOTSUPP 524 #endif +static int skips; + static int map_flags; #define CHECK(condition, tag, format...) ({ \ @@ -43,7 +45,7 @@ static int map_flags; } \ }) -static void test_hashmap(int task, void *data) +static void test_hashmap(unsigned int task, void *data) { long long key, next_key, first_key, value; int fd; @@ -133,7 +135,7 @@ static void test_hashmap(int task, void *data) close(fd); } -static void test_hashmap_sizes(int task, void *data) +static void test_hashmap_sizes(unsigned int task, void *data) { int fd, i, j; @@ -153,7 +155,7 @@ static void test_hashmap_sizes(int task, void *data) } } -static void test_hashmap_percpu(int task, void *data) +static void test_hashmap_percpu(unsigned int task, void *data) { unsigned int nr_cpus = bpf_num_possible_cpus(); BPF_DECLARE_PERCPU(long, value); @@ -280,7 +282,7 @@ static int helper_fill_hashmap(int max_entries) return fd; } -static void test_hashmap_walk(int task, void *data) +static void test_hashmap_walk(unsigned int task, void *data) { int fd, i, max_entries = 1000; long long key, value, next_key; @@ -351,7 +353,7 @@ static void test_hashmap_zero_seed(void) close(second); } -static void test_arraymap(int task, void *data) +static void test_arraymap(unsigned int task, void *data) { int key, next_key, fd; long long value; @@ -406,7 +408,7 @@ static void test_arraymap(int task, void *data) close(fd); } -static void test_arraymap_percpu(int task, void *data) +static void test_arraymap_percpu(unsigned int task, void *data) { unsigned int nr_cpus = bpf_num_possible_cpus(); BPF_DECLARE_PERCPU(long, values); @@ -502,7 +504,7 @@ static void test_arraymap_percpu_many_keys(void) close(fd); } -static void test_devmap(int task, void *data) +static void test_devmap(unsigned int task, void *data) { int fd; __u32 key, value; @@ -517,7 +519,7 @@ static void test_devmap(int task, void *data) close(fd); } -static void test_queuemap(int task, void *data) +static void test_queuemap(unsigned int task, void *data) { const int MAP_SIZE = 32; __u32 vals[MAP_SIZE + MAP_SIZE/2], val; @@ -575,7 +577,7 @@ static void test_queuemap(int task, void *data) close(fd); } -static void test_stackmap(int task, void *data) +static void test_stackmap(unsigned int task, void *data) { const int MAP_SIZE = 32; __u32 vals[MAP_SIZE + MAP_SIZE/2], val; @@ -640,7 +642,7 @@ static void test_stackmap(int task, void *data) #define SOCKMAP_PARSE_PROG "./sockmap_parse_prog.o" #define SOCKMAP_VERDICT_PROG "./sockmap_verdict_prog.o" #define SOCKMAP_TCP_MSG_PROG "./sockmap_tcp_msg_prog.o" -static void test_sockmap(int tasks, void *data) +static void test_sockmap(unsigned int tasks, void *data) { struct bpf_map *bpf_map_rx, *bpf_map_tx, *bpf_map_msg, *bpf_map_break; int map_fd_msg = 0, map_fd_rx = 0, map_fd_tx = 0, map_fd_break; @@ -724,6 +726,15 @@ static void test_sockmap(int tasks, void *data) sizeof(key), sizeof(value), 6, 0); if (fd < 0) { + if (!bpf_probe_map_type(BPF_MAP_TYPE_SOCKMAP, 0)) { + printf("%s SKIP (unsupported map type BPF_MAP_TYPE_SOCKMAP)\n", + __func__); + skips++; + for (i = 0; i < 6; i++) + close(sfd[i]); + return; + } + printf("Failed to create sockmap %i\n", fd); goto out_sockmap; } @@ -1257,10 +1268,11 @@ static void test_map_large(void) } #define run_parallel(N, FN, DATA) \ - printf("Fork %d tasks to '" #FN "'\n", N); \ + printf("Fork %u tasks to '" #FN "'\n", N); \ __run_parallel(N, FN, DATA) -static void __run_parallel(int tasks, void (*fn)(int task, void *data), +static void __run_parallel(unsigned int tasks, + void (*fn)(unsigned int task, void *data), void *data) { pid_t pid[tasks]; @@ -1301,7 +1313,7 @@ static void test_map_stress(void) #define DO_UPDATE 1 #define DO_DELETE 0 -static void test_update_delete(int fn, void *data) +static void test_update_delete(unsigned int fn, void *data) { int do_update = ((int *)data)[1]; int fd = ((int *)data)[0]; @@ -1701,6 +1713,6 @@ int main(void) map_flags = BPF_F_NO_PREALLOC; run_all_tests(); - printf("test_maps: OK\n"); + printf("test_maps: OK, %d SKIPPED\n", skips); return 0; } diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py index d59642e70f56..84bea3985d64 100755 --- a/tools/testing/selftests/bpf/test_offload.py +++ b/tools/testing/selftests/bpf/test_offload.py @@ -23,6 +23,7 @@ import string import struct import subprocess import time +import traceback logfile = None log_level = 1 @@ -78,7 +79,9 @@ def fail(cond, msg): if not cond: return print("FAIL: " + msg) - log("FAIL: " + msg, "", level=1) + tb = "".join(traceback.extract_stack().format()) + print(tb) + log("FAIL: " + msg, tb, level=1) os.sys.exit(1) def start_test(msg): @@ -589,6 +592,15 @@ def check_verifier_log(output, reference): return fail(True, "Missing or incorrect message from netdevsim in verifier log") +def check_multi_basic(two_xdps): + fail(two_xdps["mode"] != 4, "Bad mode reported with multiple programs") + fail("prog" in two_xdps, "Base program reported in multi program mode") + fail(len(two_xdps["attached"]) != 2, + "Wrong attached program count with two programs") + fail(two_xdps["attached"][0]["prog"]["id"] == + two_xdps["attached"][1]["prog"]["id"], + "Offloaded and other programs have the same id") + def test_spurios_extack(sim, obj, skip_hw, needle): res = sim.cls_bpf_add_filter(obj, prio=1, handle=1, skip_hw=skip_hw, include_stderr=True) @@ -600,6 +612,67 @@ def test_spurios_extack(sim, obj, skip_hw, needle): include_stderr=True) check_no_extack(res, needle) +def test_multi_prog(sim, obj, modename, modeid): + start_test("Test multi-attachment XDP - %s + offload..." % + (modename or "default", )) + sim.set_xdp(obj, "offload") + xdp = sim.ip_link_show(xdp=True)["xdp"] + offloaded = sim.dfs_read("bpf_offloaded_id") + fail("prog" not in xdp, "Base program not reported in single program mode") + fail(len(xdp["attached"]) != 1, + "Wrong attached program count with one program") + + sim.set_xdp(obj, modename) + two_xdps = sim.ip_link_show(xdp=True)["xdp"] + + fail(xdp["attached"][0] not in two_xdps["attached"], + "Offload program not reported after other activated") + check_multi_basic(two_xdps) + + offloaded2 = sim.dfs_read("bpf_offloaded_id") + fail(offloaded != offloaded2, + "Offload ID changed after loading other program") + + start_test("Test multi-attachment XDP - replace...") + ret, _, err = sim.set_xdp(obj, "offload", fail=False, include_stderr=True) + fail(ret == 0, "Replaced one of programs without -force") + check_extack(err, "XDP program already attached.", args) + + if modename == "" or modename == "drv": + othermode = "" if modename == "drv" else "drv" + start_test("Test multi-attachment XDP - detach...") + ret, _, err = sim.unset_xdp(othermode, force=True, + fail=False, include_stderr=True) + fail(ret == 0, "Removed program with a bad mode") + check_extack(err, "program loaded with different flags.", args) + + sim.unset_xdp("offload") + xdp = sim.ip_link_show(xdp=True)["xdp"] + offloaded = sim.dfs_read("bpf_offloaded_id") + + fail(xdp["mode"] != modeid, "Bad mode reported after multiple programs") + fail("prog" not in xdp, + "Base program not reported after multi program mode") + fail(xdp["attached"][0] not in two_xdps["attached"], + "Offload program not reported after other activated") + fail(len(xdp["attached"]) != 1, + "Wrong attached program count with remaining programs") + fail(offloaded != "0", "Offload ID reported with only other program left") + + start_test("Test multi-attachment XDP - reattach...") + sim.set_xdp(obj, "offload") + two_xdps = sim.ip_link_show(xdp=True)["xdp"] + + fail(xdp["attached"][0] not in two_xdps["attached"], + "Other program not reported after offload activated") + check_multi_basic(two_xdps) + + start_test("Test multi-attachment XDP - device remove...") + sim.remove() + + sim = NetdevSim() + sim.set_ethtool_tc_offloads(True) + return sim # Parse command line parser = argparse.ArgumentParser() @@ -842,7 +915,9 @@ try: ret, _, err = sim.set_xdp(obj, "generic", force=True, fail=False, include_stderr=True) fail(ret == 0, "Replaced XDP program with a program in different mode") - fail(err.count("File exists") != 1, "Replaced driver XDP with generic") + check_extack(err, + "native and generic XDP can't be active at the same time.", + args) ret, _, err = sim.set_xdp(obj, "", force=True, fail=False, include_stderr=True) fail(ret == 0, "Replaced XDP program with a program in different mode") @@ -931,59 +1006,9 @@ try: rm(pin_file) bpftool_prog_list_wait(expected=0) - start_test("Test multi-attachment XDP - attach...") - sim.set_xdp(obj, "offload") - xdp = sim.ip_link_show(xdp=True)["xdp"] - offloaded = sim.dfs_read("bpf_offloaded_id") - fail("prog" not in xdp, "Base program not reported in single program mode") - fail(len(ipl["xdp"]["attached"]) != 1, - "Wrong attached program count with one program") - - sim.set_xdp(obj, "") - two_xdps = sim.ip_link_show(xdp=True)["xdp"] - offloaded2 = sim.dfs_read("bpf_offloaded_id") - - fail(two_xdps["mode"] != 4, "Bad mode reported with multiple programs") - fail("prog" in two_xdps, "Base program reported in multi program mode") - fail(xdp["attached"][0] not in two_xdps["attached"], - "Offload program not reported after driver activated") - fail(len(two_xdps["attached"]) != 2, - "Wrong attached program count with two programs") - fail(two_xdps["attached"][0]["prog"]["id"] == - two_xdps["attached"][1]["prog"]["id"], - "offloaded and drv programs have the same id") - fail(offloaded != offloaded2, - "offload ID changed after loading driver program") - - start_test("Test multi-attachment XDP - replace...") - ret, _, err = sim.set_xdp(obj, "offload", fail=False, include_stderr=True) - fail(err.count("busy") != 1, "Replaced one of programs without -force") - - start_test("Test multi-attachment XDP - detach...") - ret, _, err = sim.unset_xdp("drv", force=True, - fail=False, include_stderr=True) - fail(ret == 0, "Removed program with a bad mode") - check_extack(err, "program loaded with different flags.", args) - - sim.unset_xdp("offload") - xdp = sim.ip_link_show(xdp=True)["xdp"] - offloaded = sim.dfs_read("bpf_offloaded_id") - - fail(xdp["mode"] != 1, "Bad mode reported after multiple programs") - fail("prog" not in xdp, - "Base program not reported after multi program mode") - fail(xdp["attached"][0] not in two_xdps["attached"], - "Offload program not reported after driver activated") - fail(len(ipl["xdp"]["attached"]) != 1, - "Wrong attached program count with remaining programs") - fail(offloaded != "0", "offload ID reported with only driver program left") - - start_test("Test multi-attachment XDP - device remove...") - sim.set_xdp(obj, "offload") - sim.remove() - - sim = NetdevSim() - sim.set_ethtool_tc_offloads(True) + sim = test_multi_prog(sim, obj, "", 1) + sim = test_multi_prog(sim, obj, "drv", 1) + sim = test_multi_prog(sim, obj, "generic", 2) start_test("Test mixing of TC and XDP...") sim.tc_add_ingress() diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index d8940b8b2f8d..c52bd90fbb34 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -10,6 +10,7 @@ #include <string.h> #include <assert.h> #include <stdlib.h> +#include <stdarg.h> #include <time.h> #include <linux/types.h> @@ -28,7 +29,7 @@ typedef __u16 __sum16; #include <sys/wait.h> #include <sys/types.h> #include <fcntl.h> - +#include <pthread.h> #include <linux/bpf.h> #include <linux/err.h> #include <bpf/bpf.h> @@ -1783,6 +1784,15 @@ static void test_task_fd_query_tp(void) "sys_enter_read"); } +static int libbpf_debug_print(enum libbpf_print_level level, + const char *format, va_list args) +{ + if (level == LIBBPF_DEBUG) + return 0; + + return vfprintf(stderr, format, args); +} + static void test_reference_tracking() { const char *file = "./test_sk_lookup_kern.o"; @@ -1809,9 +1819,9 @@ static void test_reference_tracking() /* Expect verifier failure if test name has 'fail' */ if (strstr(title, "fail") != NULL) { - libbpf_set_print(NULL, NULL, NULL); + libbpf_set_print(NULL); err = !bpf_program__load(prog, "GPL", 0); - libbpf_set_print(printf, printf, NULL); + libbpf_set_print(libbpf_debug_print); } else { err = bpf_program__load(prog, "GPL", 0); } @@ -1985,6 +1995,119 @@ static void test_flow_dissector(void) bpf_object__close(obj); } +static void *test_spin_lock(void *arg) +{ + __u32 duration, retval; + int err, prog_fd = *(u32 *) arg; + + err = bpf_prog_test_run(prog_fd, 10000, &pkt_v4, sizeof(pkt_v4), + NULL, NULL, &retval, &duration); + CHECK(err || retval, "", + "err %d errno %d retval %d duration %d\n", + err, errno, retval, duration); + pthread_exit(arg); +} + +static void test_spinlock(void) +{ + const char *file = "./test_spin_lock.o"; + pthread_t thread_id[4]; + struct bpf_object *obj; + int prog_fd; + int err = 0, i; + void *ret; + + err = bpf_prog_load(file, BPF_PROG_TYPE_CGROUP_SKB, &obj, &prog_fd); + if (err) { + printf("test_spin_lock:bpf_prog_load errno %d\n", errno); + goto close_prog; + } + for (i = 0; i < 4; i++) + assert(pthread_create(&thread_id[i], NULL, + &test_spin_lock, &prog_fd) == 0); + for (i = 0; i < 4; i++) + assert(pthread_join(thread_id[i], &ret) == 0 && + ret == (void *)&prog_fd); + goto close_prog_noerr; +close_prog: + error_cnt++; +close_prog_noerr: + bpf_object__close(obj); +} + +static void *parallel_map_access(void *arg) +{ + int err, map_fd = *(u32 *) arg; + int vars[17], i, j, rnd, key = 0; + + for (i = 0; i < 10000; i++) { + err = bpf_map_lookup_elem_flags(map_fd, &key, vars, BPF_F_LOCK); + if (err) { + printf("lookup failed\n"); + error_cnt++; + goto out; + } + if (vars[0] != 0) { + printf("lookup #%d var[0]=%d\n", i, vars[0]); + error_cnt++; + goto out; + } + rnd = vars[1]; + for (j = 2; j < 17; j++) { + if (vars[j] == rnd) + continue; + printf("lookup #%d var[1]=%d var[%d]=%d\n", + i, rnd, j, vars[j]); + error_cnt++; + goto out; + } + } +out: + pthread_exit(arg); +} + +static void test_map_lock(void) +{ + const char *file = "./test_map_lock.o"; + int prog_fd, map_fd[2], vars[17] = {}; + pthread_t thread_id[6]; + struct bpf_object *obj; + int err = 0, key = 0, i; + void *ret; + + err = bpf_prog_load(file, BPF_PROG_TYPE_CGROUP_SKB, &obj, &prog_fd); + if (err) { + printf("test_map_lock:bpf_prog_load errno %d\n", errno); + goto close_prog; + } + map_fd[0] = bpf_find_map(__func__, obj, "hash_map"); + if (map_fd[0] < 0) + goto close_prog; + map_fd[1] = bpf_find_map(__func__, obj, "array_map"); + if (map_fd[1] < 0) + goto close_prog; + + bpf_map_update_elem(map_fd[0], &key, vars, BPF_F_LOCK); + + for (i = 0; i < 4; i++) + assert(pthread_create(&thread_id[i], NULL, + &test_spin_lock, &prog_fd) == 0); + for (i = 4; i < 6; i++) + assert(pthread_create(&thread_id[i], NULL, + ¶llel_map_access, &map_fd[i - 4]) == 0); + for (i = 0; i < 4; i++) + assert(pthread_join(thread_id[i], &ret) == 0 && + ret == (void *)&prog_fd); + for (i = 4; i < 6; i++) + assert(pthread_join(thread_id[i], &ret) == 0 && + ret == (void *)&map_fd[i - 4]); + goto close_prog_noerr; +close_prog: + error_cnt++; +close_prog_noerr: + bpf_object__close(obj); +} + int main(void) { srand(time(NULL)); @@ -2013,6 +2136,8 @@ int main(void) test_queue_stack_map(QUEUE); test_queue_stack_map(STACK); test_flow_dissector(); + test_spinlock(); + test_map_lock(); printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt); return error_cnt ? EXIT_FAILURE : EXIT_SUCCESS; diff --git a/tools/testing/selftests/bpf/test_sock.c b/tools/testing/selftests/bpf/test_sock.c index 561ffb6d6433..fb679ac3d4b0 100644 --- a/tools/testing/selftests/bpf/test_sock.c +++ b/tools/testing/selftests/bpf/test_sock.c @@ -20,6 +20,7 @@ #define MAX_INSNS 512 char bpf_log_buf[BPF_LOG_BUF_SIZE]; +static bool verbose = false; struct sock_test { const char *descr; @@ -325,6 +326,7 @@ static int load_sock_prog(const struct bpf_insn *prog, enum bpf_attach_type attach_type) { struct bpf_load_program_attr attr; + int ret; memset(&attr, 0, sizeof(struct bpf_load_program_attr)); attr.prog_type = BPF_PROG_TYPE_CGROUP_SOCK; @@ -332,8 +334,13 @@ static int load_sock_prog(const struct bpf_insn *prog, attr.insns = prog; attr.insns_cnt = probe_prog_length(attr.insns); attr.license = "GPL"; + attr.log_level = 2; - return bpf_load_program_xattr(&attr, bpf_log_buf, BPF_LOG_BUF_SIZE); + ret = bpf_load_program_xattr(&attr, bpf_log_buf, BPF_LOG_BUF_SIZE); + if (verbose && ret < 0) + fprintf(stderr, "%s\n", bpf_log_buf); + + return ret; } static int attach_sock_prog(int cgfd, int progfd, diff --git a/tools/testing/selftests/bpf/test_sock_fields.c b/tools/testing/selftests/bpf/test_sock_fields.c new file mode 100644 index 000000000000..9bb58369b481 --- /dev/null +++ b/tools/testing/selftests/bpf/test_sock_fields.c @@ -0,0 +1,327 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook */ + +#include <sys/socket.h> +#include <sys/epoll.h> +#include <netinet/in.h> +#include <arpa/inet.h> +#include <unistd.h> +#include <stdlib.h> +#include <string.h> +#include <errno.h> + +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +#include "cgroup_helpers.h" + +enum bpf_array_idx { + SRV_IDX, + CLI_IDX, + __NR_BPF_ARRAY_IDX, +}; + +#define CHECK(condition, tag, format...) ({ \ + int __ret = !!(condition); \ + if (__ret) { \ + printf("%s(%d):FAIL:%s ", __func__, __LINE__, tag); \ + printf(format); \ + printf("\n"); \ + exit(-1); \ + } \ +}) + +#define TEST_CGROUP "/test-bpf-sock-fields" +#define DATA "Hello BPF!" +#define DATA_LEN sizeof(DATA) + +static struct sockaddr_in6 srv_sa6, cli_sa6; +static int linum_map_fd; +static int addr_map_fd; +static int tp_map_fd; +static int sk_map_fd; +static __u32 srv_idx = SRV_IDX; +static __u32 cli_idx = CLI_IDX; + +static void init_loopback6(struct sockaddr_in6 *sa6) +{ + memset(sa6, 0, sizeof(*sa6)); + sa6->sin6_family = AF_INET6; + sa6->sin6_addr = in6addr_loopback; +} + +static void print_sk(const struct bpf_sock *sk) +{ + char src_ip4[24], dst_ip4[24]; + char src_ip6[64], dst_ip6[64]; + + inet_ntop(AF_INET, &sk->src_ip4, src_ip4, sizeof(src_ip4)); + inet_ntop(AF_INET6, &sk->src_ip6, src_ip6, sizeof(src_ip6)); + inet_ntop(AF_INET, &sk->dst_ip4, dst_ip4, sizeof(dst_ip4)); + inet_ntop(AF_INET6, &sk->dst_ip6, dst_ip6, sizeof(dst_ip6)); + + printf("state:%u bound_dev_if:%u family:%u type:%u protocol:%u mark:%u priority:%u " + "src_ip4:%x(%s) src_ip6:%x:%x:%x:%x(%s) src_port:%u " + "dst_ip4:%x(%s) dst_ip6:%x:%x:%x:%x(%s) dst_port:%u\n", + sk->state, sk->bound_dev_if, sk->family, sk->type, sk->protocol, + sk->mark, sk->priority, + sk->src_ip4, src_ip4, + sk->src_ip6[0], sk->src_ip6[1], sk->src_ip6[2], sk->src_ip6[3], + src_ip6, sk->src_port, + sk->dst_ip4, dst_ip4, + sk->dst_ip6[0], sk->dst_ip6[1], sk->dst_ip6[2], sk->dst_ip6[3], + dst_ip6, ntohs(sk->dst_port)); +} + +static void print_tp(const struct bpf_tcp_sock *tp) +{ + printf("snd_cwnd:%u srtt_us:%u rtt_min:%u snd_ssthresh:%u rcv_nxt:%u " + "snd_nxt:%u snd:una:%u mss_cache:%u ecn_flags:%u " + "rate_delivered:%u rate_interval_us:%u packets_out:%u " + "retrans_out:%u total_retrans:%u segs_in:%u data_segs_in:%u " + "segs_out:%u data_segs_out:%u lost_out:%u sacked_out:%u " + "bytes_received:%llu bytes_acked:%llu\n", + tp->snd_cwnd, tp->srtt_us, tp->rtt_min, tp->snd_ssthresh, + tp->rcv_nxt, tp->snd_nxt, tp->snd_una, tp->mss_cache, + tp->ecn_flags, tp->rate_delivered, tp->rate_interval_us, + tp->packets_out, tp->retrans_out, tp->total_retrans, + tp->segs_in, tp->data_segs_in, tp->segs_out, + tp->data_segs_out, tp->lost_out, tp->sacked_out, + tp->bytes_received, tp->bytes_acked); +} + +static void check_result(void) +{ + struct bpf_tcp_sock srv_tp, cli_tp; + struct bpf_sock srv_sk, cli_sk; + __u32 linum, idx0 = 0; + int err; + + err = bpf_map_lookup_elem(linum_map_fd, &idx0, &linum); + CHECK(err == -1, "bpf_map_lookup_elem(linum_map_fd)", + "err:%d errno:%d", err, errno); + + err = bpf_map_lookup_elem(sk_map_fd, &srv_idx, &srv_sk); + CHECK(err == -1, "bpf_map_lookup_elem(sk_map_fd, &srv_idx)", + "err:%d errno:%d", err, errno); + err = bpf_map_lookup_elem(tp_map_fd, &srv_idx, &srv_tp); + CHECK(err == -1, "bpf_map_lookup_elem(tp_map_fd, &srv_idx)", + "err:%d errno:%d", err, errno); + + err = bpf_map_lookup_elem(sk_map_fd, &cli_idx, &cli_sk); + CHECK(err == -1, "bpf_map_lookup_elem(sk_map_fd, &cli_idx)", + "err:%d errno:%d", err, errno); + err = bpf_map_lookup_elem(tp_map_fd, &cli_idx, &cli_tp); + CHECK(err == -1, "bpf_map_lookup_elem(tp_map_fd, &cli_idx)", + "err:%d errno:%d", err, errno); + + printf("srv_sk: "); + print_sk(&srv_sk); + printf("\n"); + + printf("cli_sk: "); + print_sk(&cli_sk); + printf("\n"); + + printf("srv_tp: "); + print_tp(&srv_tp); + printf("\n"); + + printf("cli_tp: "); + print_tp(&cli_tp); + printf("\n"); + + CHECK(srv_sk.state == 10 || + !srv_sk.state || + srv_sk.family != AF_INET6 || + srv_sk.protocol != IPPROTO_TCP || + memcmp(srv_sk.src_ip6, &in6addr_loopback, + sizeof(srv_sk.src_ip6)) || + memcmp(srv_sk.dst_ip6, &in6addr_loopback, + sizeof(srv_sk.dst_ip6)) || + srv_sk.src_port != ntohs(srv_sa6.sin6_port) || + srv_sk.dst_port != cli_sa6.sin6_port, + "Unexpected srv_sk", "Check srv_sk output. linum:%u", linum); + + CHECK(cli_sk.state == 10 || + !cli_sk.state || + cli_sk.family != AF_INET6 || + cli_sk.protocol != IPPROTO_TCP || + memcmp(cli_sk.src_ip6, &in6addr_loopback, + sizeof(cli_sk.src_ip6)) || + memcmp(cli_sk.dst_ip6, &in6addr_loopback, + sizeof(cli_sk.dst_ip6)) || + cli_sk.src_port != ntohs(cli_sa6.sin6_port) || + cli_sk.dst_port != srv_sa6.sin6_port, + "Unexpected cli_sk", "Check cli_sk output. linum:%u", linum); + + CHECK(srv_tp.data_segs_out != 1 || + srv_tp.data_segs_in || + srv_tp.snd_cwnd != 10 || + srv_tp.total_retrans || + srv_tp.bytes_acked != DATA_LEN, + "Unexpected srv_tp", "Check srv_tp output. linum:%u", linum); + + CHECK(cli_tp.data_segs_out || + cli_tp.data_segs_in != 1 || + cli_tp.snd_cwnd != 10 || + cli_tp.total_retrans || + cli_tp.bytes_received != DATA_LEN, + "Unexpected cli_tp", "Check cli_tp output. linum:%u", linum); +} + +static void test(void) +{ + int listen_fd, cli_fd, accept_fd, epfd, err; + struct epoll_event ev; + socklen_t addrlen; + + addrlen = sizeof(struct sockaddr_in6); + ev.events = EPOLLIN; + + epfd = epoll_create(1); + CHECK(epfd == -1, "epoll_create()", "epfd:%d errno:%d", epfd, errno); + + /* Prepare listen_fd */ + listen_fd = socket(AF_INET6, SOCK_STREAM | SOCK_NONBLOCK, 0); + CHECK(listen_fd == -1, "socket()", "listen_fd:%d errno:%d", + listen_fd, errno); + + init_loopback6(&srv_sa6); + err = bind(listen_fd, (struct sockaddr *)&srv_sa6, sizeof(srv_sa6)); + CHECK(err, "bind(listen_fd)", "err:%d errno:%d", err, errno); + + err = getsockname(listen_fd, (struct sockaddr *)&srv_sa6, &addrlen); + CHECK(err, "getsockname(listen_fd)", "err:%d errno:%d", err, errno); + + err = listen(listen_fd, 1); + CHECK(err, "listen(listen_fd)", "err:%d errno:%d", err, errno); + + /* Prepare cli_fd */ + cli_fd = socket(AF_INET6, SOCK_STREAM | SOCK_NONBLOCK, 0); + CHECK(cli_fd == -1, "socket()", "cli_fd:%d errno:%d", cli_fd, errno); + + init_loopback6(&cli_sa6); + err = bind(cli_fd, (struct sockaddr *)&cli_sa6, sizeof(cli_sa6)); + CHECK(err, "bind(cli_fd)", "err:%d errno:%d", err, errno); + + err = getsockname(cli_fd, (struct sockaddr *)&cli_sa6, &addrlen); + CHECK(err, "getsockname(cli_fd)", "err:%d errno:%d", + err, errno); + + /* Update addr_map with srv_sa6 and cli_sa6 */ + err = bpf_map_update_elem(addr_map_fd, &srv_idx, &srv_sa6, 0); + CHECK(err, "map_update", "err:%d errno:%d", err, errno); + + err = bpf_map_update_elem(addr_map_fd, &cli_idx, &cli_sa6, 0); + CHECK(err, "map_update", "err:%d errno:%d", err, errno); + + /* Connect from cli_sa6 to srv_sa6 */ + err = connect(cli_fd, (struct sockaddr *)&srv_sa6, addrlen); + printf("srv_sa6.sin6_port:%u cli_sa6.sin6_port:%u\n\n", + ntohs(srv_sa6.sin6_port), ntohs(cli_sa6.sin6_port)); + CHECK(err && errno != EINPROGRESS, + "connect(cli_fd)", "err:%d errno:%d", err, errno); + + ev.data.fd = listen_fd; + err = epoll_ctl(epfd, EPOLL_CTL_ADD, listen_fd, &ev); + CHECK(err, "epoll_ctl(EPOLL_CTL_ADD, listen_fd)", "err:%d errno:%d", + err, errno); + + /* Accept the connection */ + /* Have some timeout in accept(listen_fd). Just in case. */ + err = epoll_wait(epfd, &ev, 1, 1000); + CHECK(err != 1 || ev.data.fd != listen_fd, + "epoll_wait(listen_fd)", + "err:%d errno:%d ev.data.fd:%d listen_fd:%d", + err, errno, ev.data.fd, listen_fd); + + accept_fd = accept(listen_fd, NULL, NULL); + CHECK(accept_fd == -1, "accept(listen_fd)", "accept_fd:%d errno:%d", + accept_fd, errno); + close(listen_fd); + + /* Send some data from accept_fd to cli_fd */ + err = send(accept_fd, DATA, DATA_LEN, 0); + CHECK(err != DATA_LEN, "send(accept_fd)", "err:%d errno:%d", + err, errno); + + /* Have some timeout in recv(cli_fd). Just in case. */ + ev.data.fd = cli_fd; + err = epoll_ctl(epfd, EPOLL_CTL_ADD, cli_fd, &ev); + CHECK(err, "epoll_ctl(EPOLL_CTL_ADD, cli_fd)", "err:%d errno:%d", + err, errno); + + err = epoll_wait(epfd, &ev, 1, 1000); + CHECK(err != 1 || ev.data.fd != cli_fd, + "epoll_wait(cli_fd)", "err:%d errno:%d ev.data.fd:%d cli_fd:%d", + err, errno, ev.data.fd, cli_fd); + + err = recv(cli_fd, NULL, 0, MSG_TRUNC); + CHECK(err, "recv(cli_fd)", "err:%d errno:%d", err, errno); + + close(epfd); + close(accept_fd); + close(cli_fd); + + check_result(); +} + +int main(int argc, char **argv) +{ + struct bpf_prog_load_attr attr = { + .file = "test_sock_fields_kern.o", + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .expected_attach_type = BPF_CGROUP_INET_EGRESS, + }; + int cgroup_fd, prog_fd, err; + struct bpf_object *obj; + struct bpf_map *map; + + err = setup_cgroup_environment(); + CHECK(err, "setup_cgroup_environment()", "err:%d errno:%d", + err, errno); + + atexit(cleanup_cgroup_environment); + + /* Create a cgroup, get fd, and join it */ + cgroup_fd = create_and_get_cgroup(TEST_CGROUP); + CHECK(cgroup_fd == -1, "create_and_get_cgroup()", + "cgroup_fd:%d errno:%d", cgroup_fd, errno); + + err = join_cgroup(TEST_CGROUP); + CHECK(err, "join_cgroup", "err:%d errno:%d", err, errno); + + err = bpf_prog_load_xattr(&attr, &obj, &prog_fd); + CHECK(err, "bpf_prog_load_xattr()", "err:%d", err); + + err = bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_INET_EGRESS, 0); + CHECK(err == -1, "bpf_prog_attach(CPF_CGROUP_INET_EGRESS)", + "err:%d errno%d", err, errno); + close(cgroup_fd); + + map = bpf_object__find_map_by_name(obj, "addr_map"); + CHECK(!map, "cannot find addr_map", "(null)"); + addr_map_fd = bpf_map__fd(map); + + map = bpf_object__find_map_by_name(obj, "sock_result_map"); + CHECK(!map, "cannot find sock_result_map", "(null)"); + sk_map_fd = bpf_map__fd(map); + + map = bpf_object__find_map_by_name(obj, "tcp_sock_result_map"); + CHECK(!map, "cannot find tcp_sock_result_map", "(null)"); + tp_map_fd = bpf_map__fd(map); + + map = bpf_object__find_map_by_name(obj, "linum_map"); + CHECK(!map, "cannot find linum_map", "(null)"); + linum_map_fd = bpf_map__fd(map); + + test(); + + bpf_object__close(obj); + cleanup_cgroup_environment(); + + printf("PASS\n"); + + return 0; +} diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index c5e22422a852..477a9dcf9fff 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -32,8 +32,10 @@ #include <linux/bpf_perf_event.h> #include <linux/bpf.h> #include <linux/if_ether.h> +#include <linux/btf.h> #include <bpf/bpf.h> +#include <bpf/libbpf.h> #ifdef HAVE_GENHDR # include "autoconf.h" @@ -49,7 +51,7 @@ #define MAX_INSNS BPF_MAXINSNS #define MAX_FIXUPS 8 -#define MAX_NR_MAPS 13 +#define MAX_NR_MAPS 14 #define MAX_TEST_RUNS 8 #define POINTER_VALUE 0xcafe4all #define TEST_DATA_LEN 64 @@ -59,6 +61,7 @@ #define UNPRIV_SYSCTL "kernel/unprivileged_bpf_disabled" static bool unpriv_disabled = false; +static int skips; struct bpf_test { const char *descr; @@ -76,6 +79,7 @@ struct bpf_test { int fixup_map_in_map[MAX_FIXUPS]; int fixup_cgroup_storage[MAX_FIXUPS]; int fixup_percpu_cgroup_storage[MAX_FIXUPS]; + int fixup_map_spin_lock[MAX_FIXUPS]; const char *errstr; const char *errstr_unpriv; uint32_t retval, retval_unpriv, insn_processed; @@ -263,6 +267,16 @@ static int probe_filter_length(const struct bpf_insn *fp) return len + 1; } +static bool skip_unsupported_map(enum bpf_map_type map_type) +{ + if (!bpf_probe_map_type(map_type, 0)) { + printf("SKIP (unsupported map type %d)\n", map_type); + skips++; + return true; + } + return false; +} + static int create_map(uint32_t type, uint32_t size_key, uint32_t size_value, uint32_t max_elem) { @@ -270,8 +284,11 @@ static int create_map(uint32_t type, uint32_t size_key, fd = bpf_create_map(type, size_key, size_value, max_elem, type == BPF_MAP_TYPE_HASH ? BPF_F_NO_PREALLOC : 0); - if (fd < 0) + if (fd < 0) { + if (skip_unsupported_map(type)) + return -1; printf("Failed to create hash map '%s'!\n", strerror(errno)); + } return fd; } @@ -321,6 +338,8 @@ static int create_prog_array(enum bpf_prog_type prog_type, uint32_t max_elem, mfd = bpf_create_map(BPF_MAP_TYPE_PROG_ARRAY, sizeof(int), sizeof(int), max_elem, 0); if (mfd < 0) { + if (skip_unsupported_map(BPF_MAP_TYPE_PROG_ARRAY)) + return -1; printf("Failed to create prog array '%s'!\n", strerror(errno)); return -1; } @@ -351,15 +370,20 @@ static int create_map_in_map(void) inner_map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, sizeof(int), sizeof(int), 1, 0); if (inner_map_fd < 0) { + if (skip_unsupported_map(BPF_MAP_TYPE_ARRAY)) + return -1; printf("Failed to create array '%s'!\n", strerror(errno)); return inner_map_fd; } outer_map_fd = bpf_create_map_in_map(BPF_MAP_TYPE_ARRAY_OF_MAPS, NULL, sizeof(int), inner_map_fd, 1, 0); - if (outer_map_fd < 0) + if (outer_map_fd < 0) { + if (skip_unsupported_map(BPF_MAP_TYPE_ARRAY_OF_MAPS)) + return -1; printf("Failed to create array of maps '%s'!\n", strerror(errno)); + } close(inner_map_fd); @@ -374,10 +398,105 @@ static int create_cgroup_storage(bool percpu) fd = bpf_create_map(type, sizeof(struct bpf_cgroup_storage_key), TEST_DATA_LEN, 0, 0); - if (fd < 0) + if (fd < 0) { + if (skip_unsupported_map(type)) + return -1; printf("Failed to create cgroup storage '%s'!\n", strerror(errno)); + } + + return fd; +} + +#define BTF_INFO_ENC(kind, kind_flag, vlen) \ + ((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN)) +#define BTF_TYPE_ENC(name, info, size_or_type) \ + (name), (info), (size_or_type) +#define BTF_INT_ENC(encoding, bits_offset, nr_bits) \ + ((encoding) << 24 | (bits_offset) << 16 | (nr_bits)) +#define BTF_TYPE_INT_ENC(name, encoding, bits_offset, bits, sz) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz), \ + BTF_INT_ENC(encoding, bits_offset, bits) +#define BTF_MEMBER_ENC(name, type, bits_offset) \ + (name), (type), (bits_offset) + +struct btf_raw_data { + __u32 raw_types[64]; + const char *str_sec; + __u32 str_sec_size; +}; + +/* struct bpf_spin_lock { + * int val; + * }; + * struct val { + * int cnt; + * struct bpf_spin_lock l; + * }; + */ +static const char btf_str_sec[] = "\0bpf_spin_lock\0val\0cnt\0l"; +static __u32 btf_raw_types[] = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* struct bpf_spin_lock */ /* [2] */ + BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), 4), + BTF_MEMBER_ENC(15, 1, 0), /* int val; */ + /* struct val */ /* [3] */ + BTF_TYPE_ENC(15, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8), + BTF_MEMBER_ENC(19, 1, 0), /* int cnt; */ + BTF_MEMBER_ENC(23, 2, 32),/* struct bpf_spin_lock l; */ +}; + +static int load_btf(void) +{ + struct btf_header hdr = { + .magic = BTF_MAGIC, + .version = BTF_VERSION, + .hdr_len = sizeof(struct btf_header), + .type_len = sizeof(btf_raw_types), + .str_off = sizeof(btf_raw_types), + .str_len = sizeof(btf_str_sec), + }; + void *ptr, *raw_btf; + int btf_fd; + + ptr = raw_btf = malloc(sizeof(hdr) + sizeof(btf_raw_types) + + sizeof(btf_str_sec)); + + memcpy(ptr, &hdr, sizeof(hdr)); + ptr += sizeof(hdr); + memcpy(ptr, btf_raw_types, hdr.type_len); + ptr += hdr.type_len; + memcpy(ptr, btf_str_sec, hdr.str_len); + ptr += hdr.str_len; + + btf_fd = bpf_load_btf(raw_btf, ptr - raw_btf, 0, 0, 0); + free(raw_btf); + if (btf_fd < 0) + return -1; + return btf_fd; +} + +static int create_map_spin_lock(void) +{ + struct bpf_create_map_attr attr = { + .name = "test_map", + .map_type = BPF_MAP_TYPE_ARRAY, + .key_size = 4, + .value_size = 8, + .max_entries = 1, + .btf_key_type_id = 1, + .btf_value_type_id = 3, + }; + int fd, btf_fd; + btf_fd = load_btf(); + if (btf_fd < 0) + return -1; + attr.btf_fd = btf_fd; + fd = bpf_create_map_xattr(&attr); + if (fd < 0) + printf("Failed to create map with spin_lock\n"); return fd; } @@ -399,6 +518,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, int *fixup_map_in_map = test->fixup_map_in_map; int *fixup_cgroup_storage = test->fixup_cgroup_storage; int *fixup_percpu_cgroup_storage = test->fixup_percpu_cgroup_storage; + int *fixup_map_spin_lock = test->fixup_map_spin_lock; if (test->fill_helper) test->fill_helper(test); @@ -515,6 +635,13 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type, fixup_map_stacktrace++; } while (*fixup_map_stacktrace); } + if (*fixup_map_spin_lock) { + map_fds[13] = create_map_spin_lock(); + do { + prog[*fixup_map_spin_lock].imm = map_fds[13]; + fixup_map_spin_lock++; + } while (*fixup_map_spin_lock); + } } static int set_admin(bool admin) @@ -580,6 +707,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv, int run_errs, run_successes; int map_fds[MAX_NR_MAPS]; const char *expected_err; + int fixup_skips; __u32 pflags; int i, err; @@ -588,7 +716,13 @@ static void do_test_single(struct bpf_test *test, bool unpriv, if (!prog_type) prog_type = BPF_PROG_TYPE_SOCKET_FILTER; + fixup_skips = skips; do_test_fixup(test, prog_type, prog, map_fds); + /* If there were some map skips during fixup due to missing bpf + * features, skip this test. + */ + if (fixup_skips != skips) + return; prog_len = probe_filter_length(prog); pflags = 0; @@ -598,6 +732,11 @@ static void do_test_single(struct bpf_test *test, bool unpriv, pflags |= BPF_F_ANY_ALIGNMENT; fd_prog = bpf_verify_program(prog_type, prog, prog_len, pflags, "GPL", 0, bpf_vlog, sizeof(bpf_vlog), 1); + if (fd_prog < 0 && !bpf_probe_prog_type(prog_type, 0)) { + printf("SKIP (unsupported program type %d)\n", prog_type); + skips++; + goto close_fds; + } expected_ret = unpriv && test->result_unpriv != UNDEF ? test->result_unpriv : test->result; @@ -751,7 +890,7 @@ static bool test_as_unpriv(struct bpf_test *test) static int do_test(bool unpriv, unsigned int from, unsigned int to) { - int i, passes = 0, errors = 0, skips = 0; + int i, passes = 0, errors = 0; for (i = from; i < to; i++) { struct bpf_test *test = &tests[i]; diff --git a/tools/testing/selftests/bpf/verifier/ctx_sk_msg.c b/tools/testing/selftests/bpf/verifier/ctx_sk_msg.c index b0195770da6a..c6c69220a569 100644 --- a/tools/testing/selftests/bpf/verifier/ctx_sk_msg.c +++ b/tools/testing/selftests/bpf/verifier/ctx_sk_msg.c @@ -100,6 +100,7 @@ .errstr = "invalid bpf_context access", .result = REJECT, .prog_type = BPF_PROG_TYPE_SK_MSG, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "invalid read past end of SK_MSG", diff --git a/tools/testing/selftests/bpf/verifier/ctx_skb.c b/tools/testing/selftests/bpf/verifier/ctx_skb.c index 881f1c7f57a1..c660deb582f1 100644 --- a/tools/testing/selftests/bpf/verifier/ctx_skb.c +++ b/tools/testing/selftests/bpf/verifier/ctx_skb.c @@ -687,6 +687,7 @@ }, .errstr = "invalid bpf_context access", .result = REJECT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "check skb->hash half load not permitted, unaligned 3", diff --git a/tools/testing/selftests/bpf/verifier/jmp32.c b/tools/testing/selftests/bpf/verifier/jmp32.c index ceb39ffa0e88..f0961c58581e 100644 --- a/tools/testing/selftests/bpf/verifier/jmp32.c +++ b/tools/testing/selftests/bpf/verifier/jmp32.c @@ -27,6 +27,7 @@ .data64 = { 1ULL << 63 | 1, } }, }, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "jset32: BPF_X", @@ -58,6 +59,7 @@ .data64 = { 1ULL << 63 | 1, } }, }, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "jset32: min/max deduction", @@ -93,6 +95,7 @@ .data64 = { -1, } }, }, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "jeq32: BPF_X", @@ -119,6 +122,7 @@ .data64 = { 1ULL << 63 | 1, } }, }, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "jeq32: min/max deduction", @@ -154,6 +158,7 @@ .data64 = { -1, } }, }, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "jne32: BPF_X", @@ -180,6 +185,7 @@ .data64 = { 1ULL << 63 | 2, } }, }, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "jne32: min/max deduction", @@ -218,6 +224,7 @@ .data64 = { 0, } }, }, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "jge32: BPF_X", @@ -244,6 +251,7 @@ .data64 = { (UINT_MAX - 1) | 2ULL << 32, } }, }, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "jge32: min/max deduction", @@ -284,6 +292,7 @@ .data64 = { 0, } }, }, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "jgt32: BPF_X", @@ -310,6 +319,7 @@ .data64 = { (UINT_MAX - 1) | 2ULL << 32, } }, }, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "jgt32: min/max deduction", @@ -350,6 +360,7 @@ .data64 = { INT_MAX, } }, }, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "jle32: BPF_X", @@ -376,6 +387,7 @@ .data64 = { UINT_MAX, } }, }, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "jle32: min/max deduction", @@ -416,6 +428,7 @@ .data64 = { INT_MAX - 1, } }, }, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "jlt32: BPF_X", @@ -442,6 +455,7 @@ .data64 = { (INT_MAX - 1) | 3ULL << 32, } }, }, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "jlt32: min/max deduction", @@ -482,6 +496,7 @@ .data64 = { -2, } }, }, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "jsge32: BPF_X", @@ -508,6 +523,7 @@ .data64 = { -2, } }, }, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "jsge32: min/max deduction", @@ -548,6 +564,7 @@ .data64 = { 1, } }, }, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "jsgt32: BPF_X", @@ -574,6 +591,7 @@ .data64 = { 0x7fffffff, } }, }, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "jsgt32: min/max deduction", @@ -614,6 +632,7 @@ .data64 = { 1, } }, }, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "jsle32: BPF_X", @@ -640,6 +659,7 @@ .data64 = { 0x7fffffff | 2ULL << 32, } }, }, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "jsle32: min/max deduction", @@ -680,6 +700,7 @@ .data64 = { 1, } }, }, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "jslt32: BPF_X", @@ -706,6 +727,7 @@ .data64 = { 0x7fffffff | 2ULL << 32, } }, }, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "jslt32: min/max deduction", diff --git a/tools/testing/selftests/bpf/verifier/jset.c b/tools/testing/selftests/bpf/verifier/jset.c index 7e14037acfaf..8dcd4e0383d5 100644 --- a/tools/testing/selftests/bpf/verifier/jset.c +++ b/tools/testing/selftests/bpf/verifier/jset.c @@ -53,6 +53,7 @@ .data64 = { ~0ULL, } }, }, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "jset: sign-extend", @@ -70,6 +71,7 @@ .result = ACCEPT, .retval = 2, .data = { 1, 0, 0, 0, 0, 0, 0, 1, }, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "jset: known const compare", diff --git a/tools/testing/selftests/bpf/verifier/ref_tracking.c b/tools/testing/selftests/bpf/verifier/ref_tracking.c index dc2cc823df2b..3ed3593bd8b6 100644 --- a/tools/testing/selftests/bpf/verifier/ref_tracking.c +++ b/tools/testing/selftests/bpf/verifier/ref_tracking.c @@ -547,7 +547,7 @@ BPF_EXIT_INSN(), }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, - .errstr = "cannot write into socket", + .errstr = "cannot write into sock", .result = REJECT, }, { @@ -562,7 +562,7 @@ BPF_EXIT_INSN(), }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, - .errstr = "invalid bpf_sock access off=0 size=8", + .errstr = "invalid sock access off=0 size=8", .result = REJECT, }, { diff --git a/tools/testing/selftests/bpf/verifier/sock.c b/tools/testing/selftests/bpf/verifier/sock.c new file mode 100644 index 000000000000..0ddfdf76aba5 --- /dev/null +++ b/tools/testing/selftests/bpf/verifier/sock.c @@ -0,0 +1,384 @@ +{ + "skb->sk: no NULL check", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = REJECT, + .errstr = "invalid mem access 'sock_common_or_null'", +}, +{ + "skb->sk: sk->family [non fullsock field]", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, offsetof(struct bpf_sock, family)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = ACCEPT, +}, +{ + "skb->sk: sk->type [fullsock field]", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, offsetof(struct bpf_sock, type)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = REJECT, + .errstr = "invalid sock_common access", +}, +{ + "bpf_sk_fullsock(skb->sk): no !skb->sk check", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = REJECT, + .errstr = "type=sock_common_or_null expected=sock_common", +}, +{ + "sk_fullsock(skb->sk): no NULL check on ret", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, type)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = REJECT, + .errstr = "invalid mem access 'sock_or_null'", +}, +{ + "sk_fullsock(skb->sk): sk->type [fullsock field]", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, type)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = ACCEPT, +}, +{ + "sk_fullsock(skb->sk): sk->family [non fullsock field]", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, family)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = ACCEPT, +}, +{ + "sk_fullsock(skb->sk): sk->state [narrow load]", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, state)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = ACCEPT, +}, +{ + "sk_fullsock(skb->sk): sk->dst_port [narrow load]", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = ACCEPT, +}, +{ + "sk_fullsock(skb->sk): sk->dst_port [load 2nd byte]", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_port) + 1), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = REJECT, + .errstr = "invalid sock access", +}, +{ + "sk_fullsock(skb->sk): sk->dst_ip6 [load 2nd byte]", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, dst_ip6[0]) + 1), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = ACCEPT, +}, +{ + "sk_fullsock(skb->sk): sk->type [narrow load]", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, type)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = ACCEPT, +}, +{ + "sk_fullsock(skb->sk): sk->protocol [narrow load]", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_sock, protocol)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = ACCEPT, +}, +{ + "sk_fullsock(skb->sk): beyond last field", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetofend(struct bpf_sock, state)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = REJECT, + .errstr = "invalid sock access", +}, +{ + "bpf_tcp_sock(skb->sk): no !skb->sk check", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_EMIT_CALL(BPF_FUNC_tcp_sock), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = REJECT, + .errstr = "type=sock_common_or_null expected=sock_common", +}, +{ + "bpf_tcp_sock(skb->sk): no NULL check on ret", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_tcp_sock), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_tcp_sock, snd_cwnd)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = REJECT, + .errstr = "invalid mem access 'tcp_sock_or_null'", +}, +{ + "bpf_tcp_sock(skb->sk): tp->snd_cwnd", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_tcp_sock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_tcp_sock, snd_cwnd)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = ACCEPT, +}, +{ + "bpf_tcp_sock(skb->sk): tp->bytes_acked", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_tcp_sock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_tcp_sock, bytes_acked)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = ACCEPT, +}, +{ + "bpf_tcp_sock(skb->sk): beyond last field", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_tcp_sock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, offsetofend(struct bpf_tcp_sock, bytes_acked)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = REJECT, + .errstr = "invalid tcp_sock access", +}, +{ + "bpf_tcp_sock(bpf_sk_fullsock(skb->sk)): tp->snd_cwnd", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_tcp_sock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, offsetof(struct bpf_tcp_sock, snd_cwnd)), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .result = ACCEPT, +}, +{ + "bpf_sk_release(skb->sk)", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "type=sock_common expected=sock", +}, +{ + "bpf_sk_release(bpf_sk_fullsock(skb->sk))", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_sk_fullsock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "reference has not been acquired before", +}, +{ + "bpf_sk_release(bpf_tcp_sock(skb->sk))", + .insns = { + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + BPF_EMIT_CALL(BPF_FUNC_tcp_sock), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_EMIT_CALL(BPF_FUNC_sk_release), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "type=tcp_sock expected=sock", +}, diff --git a/tools/testing/selftests/bpf/verifier/spill_fill.c b/tools/testing/selftests/bpf/verifier/spill_fill.c index d58db72fdfe8..45d43bf82f26 100644 --- a/tools/testing/selftests/bpf/verifier/spill_fill.c +++ b/tools/testing/selftests/bpf/verifier/spill_fill.c @@ -46,6 +46,7 @@ .errstr_unpriv = "attempt to corrupt spilled", .errstr = "R0 invalid mem access 'inv", .result = REJECT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "check corrupted spill/fill, LSB", diff --git a/tools/testing/selftests/bpf/verifier/spin_lock.c b/tools/testing/selftests/bpf/verifier/spin_lock.c new file mode 100644 index 000000000000..781621facae4 --- /dev/null +++ b/tools/testing/selftests/bpf/verifier/spin_lock.c @@ -0,0 +1,333 @@ +{ + "spin_lock: test1 success", + .insns = { + BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_LD_MAP_FD(BPF_REG_1, + 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_lock), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_unlock), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_spin_lock = { 3 }, + .result = ACCEPT, + .result_unpriv = REJECT, + .errstr_unpriv = "", + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, +}, +{ + "spin_lock: test2 direct ld/st", + .insns = { + BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_LD_MAP_FD(BPF_REG_1, + 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_lock), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_unlock), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_spin_lock = { 3 }, + .result = REJECT, + .errstr = "cannot be accessed directly", + .result_unpriv = REJECT, + .errstr_unpriv = "", + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, +}, +{ + "spin_lock: test3 direct ld/st", + .insns = { + BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_LD_MAP_FD(BPF_REG_1, + 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_lock), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, 1), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_unlock), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_spin_lock = { 3 }, + .result = REJECT, + .errstr = "cannot be accessed directly", + .result_unpriv = REJECT, + .errstr_unpriv = "", + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "spin_lock: test4 direct ld/st", + .insns = { + BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_LD_MAP_FD(BPF_REG_1, + 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_lock), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4), + BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_6, 3), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_unlock), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_spin_lock = { 3 }, + .result = REJECT, + .errstr = "cannot be accessed directly", + .result_unpriv = REJECT, + .errstr_unpriv = "", + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, +}, +{ + "spin_lock: test5 call within a locked region", + .insns = { + BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_LD_MAP_FD(BPF_REG_1, + 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_lock), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_unlock), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_spin_lock = { 3 }, + .result = REJECT, + .errstr = "calls are not allowed", + .result_unpriv = REJECT, + .errstr_unpriv = "", + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, +}, +{ + "spin_lock: test6 missing unlock", + .insns = { + BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_LD_MAP_FD(BPF_REG_1, + 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_lock), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, 0), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_unlock), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_spin_lock = { 3 }, + .result = REJECT, + .errstr = "unlock is missing", + .result_unpriv = REJECT, + .errstr_unpriv = "", + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, +}, +{ + "spin_lock: test7 unlock without lock", + .insns = { + BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_LD_MAP_FD(BPF_REG_1, + 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4), + BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_lock), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_unlock), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_spin_lock = { 3 }, + .result = REJECT, + .errstr = "without taking a lock", + .result_unpriv = REJECT, + .errstr_unpriv = "", + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, +}, +{ + "spin_lock: test8 double lock", + .insns = { + BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_LD_MAP_FD(BPF_REG_1, + 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_lock), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_lock), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_unlock), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_spin_lock = { 3 }, + .result = REJECT, + .errstr = "calls are not allowed", + .result_unpriv = REJECT, + .errstr_unpriv = "", + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, +}, +{ + "spin_lock: test9 different lock", + .insns = { + BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_LD_MAP_FD(BPF_REG_1, + 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_LD_MAP_FD(BPF_REG_1, + 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_lock), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_unlock), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_spin_lock = { 3, 11 }, + .result = REJECT, + .errstr = "unlock of different lock", + .result_unpriv = REJECT, + .errstr_unpriv = "", + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, +}, +{ + "spin_lock: test10 lock in subprog without unlock", + .insns = { + BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_LD_MAP_FD(BPF_REG_1, + 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 5), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_unlock), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_lock), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_spin_lock = { 3 }, + .result = REJECT, + .errstr = "unlock is missing", + .result_unpriv = REJECT, + .errstr_unpriv = "", + .prog_type = BPF_PROG_TYPE_CGROUP_SKB, +}, +{ + "spin_lock: test11 ld_abs under lock", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_LD_MAP_FD(BPF_REG_1, + 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1), + BPF_EXIT_INSN(), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_lock), + BPF_LD_ABS(BPF_B, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 4), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_spin_unlock), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .fixup_map_spin_lock = { 4 }, + .result = REJECT, + .errstr = "inside bpf_spin_lock", + .prog_type = BPF_PROG_TYPE_SCHED_CLS, +}, diff --git a/tools/testing/selftests/bpf/verifier/unpriv.c b/tools/testing/selftests/bpf/verifier/unpriv.c index dca58cf1a4ab..dbaf5be947b2 100644 --- a/tools/testing/selftests/bpf/verifier/unpriv.c +++ b/tools/testing/selftests/bpf/verifier/unpriv.c @@ -76,6 +76,7 @@ .errstr_unpriv = "unknown func bpf_trace_printk#6", .result_unpriv = REJECT, .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, { "unpriv: pass pointer to helper function", @@ -364,7 +365,7 @@ }, .result = REJECT, //.errstr = "same insn cannot be used with different pointers", - .errstr = "cannot write into socket", + .errstr = "cannot write into sock", .prog_type = BPF_PROG_TYPE_SCHED_CLS, }, { diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c index 9ab5ace83e02..4b721a77bebb 100644 --- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c +++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c @@ -512,6 +512,7 @@ .fixup_map_array_48b = { 3 }, .result = ACCEPT, .retval = 0xabcdef12, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "map access: unknown scalar += value_ptr, 3", @@ -537,6 +538,7 @@ .result_unpriv = REJECT, .errstr_unpriv = "R0 pointer arithmetic of map value goes out of range", .retval = 0xabcdef12, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "map access: unknown scalar += value_ptr, 4", @@ -559,6 +561,7 @@ .result = REJECT, .errstr = "R1 max value is outside of the array range", .errstr_unpriv = "R1 pointer arithmetic of map value goes out of range", + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "map access: value_ptr += unknown scalar, 1", @@ -598,6 +601,7 @@ .fixup_map_array_48b = { 3 }, .result = ACCEPT, .retval = 0xabcdef12, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "map access: value_ptr += unknown scalar, 3", diff --git a/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh b/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh index bab13dd025a6..0d26b5e3f966 100755 --- a/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh +++ b/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh @@ -37,6 +37,10 @@ prerequisite() exit $ksft_skip fi + present_cpus=`cat $SYSFS/devices/system/cpu/present` + present_max=${present_cpus##*-} + echo "present_cpus = $present_cpus present_max = $present_max" + echo -e "\t Cpus in online state: $online_cpus" offline_cpus=`cat $SYSFS/devices/system/cpu/offline` @@ -151,6 +155,8 @@ online_cpus=0 online_max=0 offline_cpus=0 offline_max=0 +present_cpus=0 +present_max=0 while getopts e:ahp: opt; do case $opt in @@ -190,9 +196,10 @@ if [ $allcpus -eq 0 ]; then online_cpu_expect_success $online_max if [[ $offline_cpus -gt 0 ]]; then - echo -e "\t offline to online to offline: cpu $offline_max" - online_cpu_expect_success $offline_max - offline_cpu_expect_success $offline_max + echo -e "\t offline to online to offline: cpu $present_max" + online_cpu_expect_success $present_max + offline_cpu_expect_success $present_max + online_cpu $present_max fi exit 0 else diff --git a/tools/testing/selftests/drivers/net/mlxsw/blackhole_routes.sh b/tools/testing/selftests/drivers/net/mlxsw/blackhole_routes.sh new file mode 100755 index 000000000000..5ba5bef44d5b --- /dev/null +++ b/tools/testing/selftests/drivers/net/mlxsw/blackhole_routes.sh @@ -0,0 +1,200 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test that blackhole routes are marked as offloaded and that packets hitting +# them are dropped by the ASIC and not by the kernel. +# +# +---------------------------------+ +# | H1 (vrf) | +# | + $h1 | +# | | 192.0.2.1/24 | +# | | 2001:db8:1::1/64 | +# | | | +# | | default via 192.0.2.2 | +# | | default via 2001:db8:1::2 | +# +----|----------------------------+ +# | +# +----|----------------------------------------------------------------------+ +# | SW | | +# | + $rp1 | +# | 192.0.2.2/24 | +# | 2001:db8:1::2/64 | +# | | +# | 2001:db8:2::2/64 | +# | 198.51.100.2/24 | +# | + $rp2 | +# | | | +# +----|----------------------------------------------------------------------+ +# | +# +----|----------------------------+ +# | | default via 198.51.100.2 | +# | | default via 2001:db8:2::2 | +# | | | +# | | 2001:db8:2::1/64 | +# | | 198.51.100.1/24 | +# | + $h2 | +# | H2 (vrf) | +# +---------------------------------+ + +lib_dir=$(dirname $0)/../../../net/forwarding + +ALL_TESTS=" + ping_ipv4 + ping_ipv6 + blackhole_ipv4 + blackhole_ipv6 +" +NUM_NETIFS=4 +source $lib_dir/tc_common.sh +source $lib_dir/lib.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/24 2001:db8:1::1/64 + + ip -4 route add default vrf v$h1 nexthop via 192.0.2.2 + ip -6 route add default vrf v$h1 nexthop via 2001:db8:1::2 +} + +h1_destroy() +{ + ip -6 route del default vrf v$h1 nexthop via 2001:db8:1::2 + ip -4 route del default vrf v$h1 nexthop via 192.0.2.2 + + simple_if_fini $h1 192.0.2.1/24 2001:db8:1::1/64 +} + +h2_create() +{ + simple_if_init $h2 198.51.100.1/24 2001:db8:2::1/64 + + ip -4 route add default vrf v$h2 nexthop via 198.51.100.2 + ip -6 route add default vrf v$h2 nexthop via 2001:db8:2::2 +} + +h2_destroy() +{ + ip -6 route del default vrf v$h2 nexthop via 2001:db8:2::2 + ip -4 route del default vrf v$h2 nexthop via 198.51.100.2 + + simple_if_fini $h2 198.51.100.1/24 2001:db8:2::1/64 +} + +router_create() +{ + ip link set dev $rp1 up + ip link set dev $rp2 up + + tc qdisc add dev $rp1 clsact + + __addr_add_del $rp1 add 192.0.2.2/24 2001:db8:1::2/64 + __addr_add_del $rp2 add 198.51.100.2/24 2001:db8:2::2/64 +} + +router_destroy() +{ + __addr_add_del $rp2 del 198.51.100.2/24 2001:db8:2::2/64 + __addr_add_del $rp1 del 192.0.2.2/24 2001:db8:1::2/64 + + tc qdisc del dev $rp1 clsact + + ip link set dev $rp2 down + ip link set dev $rp1 down +} + +ping_ipv4() +{ + ping_test $h1 198.51.100.1 ": h1->h2" +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:2::1 ": h1->h2" +} + +blackhole_ipv4() +{ + # Transmit packets from H1 to H2 and make sure they are dropped by the + # ASIC and not by the kernel + RET=0 + + ip -4 route add blackhole 198.51.100.0/30 + tc filter add dev $rp1 ingress protocol ip pref 1 handle 101 flower \ + skip_hw dst_ip 198.51.100.1 src_ip 192.0.2.1 ip_proto icmp \ + action pass + + ip -4 route show 198.51.100.0/30 | grep -q offload + check_err $? "route not marked as offloaded when should" + + ping_do $h1 198.51.100.1 + check_fail $? "ping passed when should not" + + tc_check_packets "dev $rp1 ingress" 101 0 + check_err $? "packets trapped and not dropped by ASIC" + + log_test "IPv4 blackhole route" + + tc filter del dev $rp1 ingress protocol ip pref 1 handle 101 flower + ip -4 route del blackhole 198.51.100.0/30 +} + +blackhole_ipv6() +{ + RET=0 + + ip -6 route add blackhole 2001:db8:2::/120 + tc filter add dev $rp1 ingress protocol ipv6 pref 1 handle 101 flower \ + skip_hw dst_ip 2001:db8:2::1 src_ip 2001:db8:1::1 \ + ip_proto icmpv6 action pass + + ip -6 route show 2001:db8:2::/120 | grep -q offload + check_err $? "route not marked as offloaded when should" + + ping6_do $h1 2001:db8:2::1 + check_fail $? "ping passed when should not" + + tc_check_packets "dev $rp1 ingress" 101 0 + check_err $? "packets trapped and not dropped by ASIC" + + log_test "IPv6 blackhole route" + + tc filter del dev $rp1 ingress protocol ipv6 pref 1 handle 101 flower + ip -6 route del blackhole 2001:db8:2::/120 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + rp1=${NETIFS[p2]} + + rp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + vrf_prepare + forwarding_enable + + h1_create + h2_create + router_create +} + +cleanup() +{ + pre_cleanup + + router_destroy + h2_destroy + h1_destroy + + forwarding_restore + vrf_cleanup +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh index 1ca631d5aaba..40f16f2a3afd 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh @@ -148,9 +148,10 @@ dscp_ping_test() eval "t0s=($(dscp_fetch_stats $dev_10 10) $(dscp_fetch_stats $dev_20 20))" + local ping_timeout=$((PING_TIMEOUT * 5)) ip vrf exec $vrf_name \ ${PING} -Q $dscp_10 ${sip:+-I $sip} $dip \ - -c 10 -i 0.1 -w 2 &> /dev/null + -c 10 -i 0.5 -w $ping_timeout &> /dev/null local -A t1s eval "t1s=($(dscp_fetch_stats $dev_10 10) diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh index 281d90766e12..9faf02e32627 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh @@ -169,9 +169,10 @@ dscp_ping_test() eval "local -A dev1_t0s=($(dscp_fetch_stats $dev1 0))" eval "local -A dev2_t0s=($(dscp_fetch_stats $dev2 0))" + local ping_timeout=$((PING_TIMEOUT * 5)) ip vrf exec $vrf_name \ ${PING} -Q $dscp ${sip:+-I $sip} $dip \ - -c 10 -i 0.1 -w 2 &> /dev/null + -c 10 -i 0.5 -w $ping_timeout &> /dev/null eval "local -A dev1_t1s=($(dscp_fetch_stats $dev1 0))" eval "local -A dev2_t1s=($(dscp_fetch_stats $dev2 0))" diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh index b41d6256b2d0..4d5b880b1d96 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh @@ -9,10 +9,11 @@ lib_dir=$(dirname $0)/../../../../net/forwarding ALL_TESTS="single_mask_test identical_filters_test two_masks_test \ multiple_masks_test ctcam_edge_cases_test delta_simple_test \ + delta_two_masks_one_key_test delta_simple_rehash_test \ bloom_simple_test bloom_complex_test bloom_delta_test" NUM_NETIFS=2 source $lib_dir/tc_common.sh -source $lib_dir/lib.sh +source $lib_dir/devlink_lib.sh tcflags="skip_hw" @@ -38,6 +39,55 @@ h2_destroy() simple_if_fini $h2 192.0.2.2/24 198.51.100.2/24 } +tp_record() +{ + local tracepoint=$1 + local cmd=$2 + + perf record -q -e $tracepoint $cmd + return $? +} + +tp_record_all() +{ + local tracepoint=$1 + local seconds=$2 + + perf record -a -q -e $tracepoint sleep $seconds + return $? +} + +__tp_hit_count() +{ + local tracepoint=$1 + + local perf_output=`perf script -F trace:event,trace` + return `echo $perf_output | grep "$tracepoint:" | wc -l` +} + +tp_check_hits() +{ + local tracepoint=$1 + local count=$2 + + __tp_hit_count $tracepoint + if [[ "$?" -ne "$count" ]]; then + return 1 + fi + return 0 +} + +tp_check_hits_any() +{ + local tracepoint=$1 + + __tp_hit_count $tracepoint + if [[ "$?" -eq "0" ]]; then + return 1 + fi + return 0 +} + single_mask_test() { # When only a single mask is required, the device uses the master @@ -182,20 +232,38 @@ multiple_masks_test() # spillage is performed correctly and that the right filter is # matched + if [[ "$tcflags" != "skip_sw" ]]; then + return 0; + fi + local index RET=0 NUM_MASKS=32 + NUM_ERPS=16 BASE_INDEX=100 for i in $(eval echo {1..$NUM_MASKS}); do index=$((BASE_INDEX - i)) - tc filter add dev $h2 ingress protocol ip pref $index \ - handle $index \ - flower $tcflags dst_ip 192.0.2.2/${i} src_ip 192.0.2.1 \ - action drop + if ((i > NUM_ERPS)); then + exp_hits=1 + err_msg="$i filters - C-TCAM spill did not happen when it was expected" + else + exp_hits=0 + err_msg="$i filters - C-TCAM spill happened when it should not" + fi + + tp_record "mlxsw:mlxsw_sp_acl_atcam_entry_add_ctcam_spill" \ + "tc filter add dev $h2 ingress protocol ip pref $index \ + handle $index \ + flower $tcflags \ + dst_ip 192.0.2.2/${i} src_ip 192.0.2.1/${i} \ + action drop" + tp_check_hits "mlxsw:mlxsw_sp_acl_atcam_entry_add_ctcam_spill" \ + $exp_hits + check_err $? "$err_msg" $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 \ -B 192.0.2.2 -t ip -q @@ -325,28 +393,6 @@ ctcam_edge_cases_test() ctcam_no_atcam_masks_test } -tp_record() -{ - local tracepoint=$1 - local cmd=$2 - - perf record -q -e $tracepoint $cmd - return $? -} - -tp_check_hits() -{ - local tracepoint=$1 - local count=$2 - - perf_output=`perf script -F trace:event,trace` - hits=`echo $perf_output | grep "$tracepoint:" | wc -l` - if [[ "$count" -ne "$hits" ]]; then - return 1 - fi - return 0 -} - delta_simple_test() { # The first filter will create eRP, the second filter will fit into @@ -405,6 +451,120 @@ delta_simple_test() log_test "delta simple test ($tcflags)" } +delta_two_masks_one_key_test() +{ + # If 2 keys are the same and only differ in mask in a way that + # they belong under the same ERP (second is delta of the first), + # there should be no C-TCAM spill. + + RET=0 + + if [[ "$tcflags" != "skip_sw" ]]; then + return 0; + fi + + tp_record "mlxsw:*" "tc filter add dev $h2 ingress protocol ip \ + pref 1 handle 101 flower $tcflags dst_ip 192.0.2.0/24 \ + action drop" + tp_check_hits "mlxsw:mlxsw_sp_acl_atcam_entry_add_ctcam_spill" 0 + check_err $? "incorrect C-TCAM spill while inserting the first rule" + + tp_record "mlxsw:*" "tc filter add dev $h2 ingress protocol ip \ + pref 2 handle 102 flower $tcflags dst_ip 192.0.2.2 \ + action drop" + tp_check_hits "mlxsw:mlxsw_sp_acl_atcam_entry_add_ctcam_spill" 0 + check_err $? "incorrect C-TCAM spill while inserting the second rule" + + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip -q + + tc_check_packets "dev $h2 ingress" 101 1 + check_err $? "Did not match on correct filter" + + tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower + + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip -q + + tc_check_packets "dev $h2 ingress" 102 1 + check_err $? "Did not match on correct filter" + + tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower + + log_test "delta two masks one key test ($tcflags)" +} + +delta_simple_rehash_test() +{ + RET=0 + + if [[ "$tcflags" != "skip_sw" ]]; then + return 0; + fi + + devlink dev param set $DEVLINK_DEV \ + name acl_region_rehash_interval cmode runtime value 0 + check_err $? "Failed to set ACL region rehash interval" + + tp_record_all mlxsw:mlxsw_sp_acl_tcam_vregion_rehash 7 + tp_check_hits_any mlxsw:mlxsw_sp_acl_tcam_vregion_rehash + check_fail $? "Rehash trace was hit even when rehash should be disabled" + + devlink dev param set $DEVLINK_DEV \ + name acl_region_rehash_interval cmode runtime value 3000 + check_err $? "Failed to set ACL region rehash interval" + + sleep 1 + + tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \ + $tcflags dst_ip 192.0.1.0/25 action drop + tc filter add dev $h2 ingress protocol ip pref 2 handle 102 flower \ + $tcflags dst_ip 192.0.2.2 action drop + tc filter add dev $h2 ingress protocol ip pref 3 handle 103 flower \ + $tcflags dst_ip 192.0.3.0/24 action drop + + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip -q + + tc_check_packets "dev $h2 ingress" 101 1 + check_fail $? "Matched a wrong filter" + + tc_check_packets "dev $h2 ingress" 103 1 + check_fail $? "Matched a wrong filter" + + tc_check_packets "dev $h2 ingress" 102 1 + check_err $? "Did not match on correct filter" + + tp_record_all mlxsw:* 3 + tp_check_hits_any mlxsw:mlxsw_sp_acl_tcam_vregion_rehash + check_err $? "Rehash trace was not hit" + tp_check_hits_any mlxsw:mlxsw_sp_acl_tcam_vregion_migrate + check_err $? "Migrate trace was not hit" + tp_record_all mlxsw:* 3 + tp_check_hits_any mlxsw:mlxsw_sp_acl_tcam_vregion_rehash + check_err $? "Rehash trace was not hit" + tp_check_hits_any mlxsw:mlxsw_sp_acl_tcam_vregion_migrate + check_fail $? "Migrate trace was hit when no migration should happen" + + $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip -q + + tc_check_packets "dev $h2 ingress" 101 1 + check_fail $? "Matched a wrong filter after rehash" + + tc_check_packets "dev $h2 ingress" 103 1 + check_fail $? "Matched a wrong filter after rehash" + + tc_check_packets "dev $h2 ingress" 102 2 + check_err $? "Did not match on correct filter after rehash" + + tc filter del dev $h2 ingress protocol ip pref 3 handle 103 flower + tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower + tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower + + log_test "delta simple rehash test ($tcflags)" +} + bloom_simple_test() { # Bloom filter requires that the eRP table is used. This test diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh index a0a80e1a69e8..e7ffc79561b7 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh @@ -2,7 +2,6 @@ # SPDX-License-Identifier: GPL-2.0 NUM_NETIFS=6 -source ../../../../net/forwarding/lib.sh source ../../../../net/forwarding/tc_common.sh source devlink_lib_spectrum.sh diff --git a/tools/testing/selftests/filesystems/binderfs/.gitignore b/tools/testing/selftests/filesystems/binderfs/.gitignore new file mode 100644 index 000000000000..8a5d9bf63dd4 --- /dev/null +++ b/tools/testing/selftests/filesystems/binderfs/.gitignore @@ -0,0 +1 @@ +binderfs_test diff --git a/tools/testing/selftests/filesystems/binderfs/Makefile b/tools/testing/selftests/filesystems/binderfs/Makefile new file mode 100644 index 000000000000..58cb659b56b4 --- /dev/null +++ b/tools/testing/selftests/filesystems/binderfs/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 + +CFLAGS += -I../../../../../usr/include/ +TEST_GEN_PROGS := binderfs_test + +include ../../lib.mk diff --git a/tools/testing/selftests/filesystems/binderfs/binderfs_test.c b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c new file mode 100644 index 000000000000..8c2ed962e1c7 --- /dev/null +++ b/tools/testing/selftests/filesystems/binderfs/binderfs_test.c @@ -0,0 +1,275 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <errno.h> +#include <fcntl.h> +#include <sched.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> +#include <sys/mount.h> +#include <sys/stat.h> +#include <sys/types.h> +#include <unistd.h> +#include <linux/android/binder.h> +#include <linux/android/binderfs.h> +#include "../../kselftest.h" + +static ssize_t write_nointr(int fd, const void *buf, size_t count) +{ + ssize_t ret; +again: + ret = write(fd, buf, count); + if (ret < 0 && errno == EINTR) + goto again; + + return ret; +} + +static void write_to_file(const char *filename, const void *buf, size_t count, + int allowed_errno) +{ + int fd, saved_errno; + ssize_t ret; + + fd = open(filename, O_WRONLY | O_CLOEXEC); + if (fd < 0) + ksft_exit_fail_msg("%s - Failed to open file %s\n", + strerror(errno), filename); + + ret = write_nointr(fd, buf, count); + if (ret < 0) { + if (allowed_errno && (errno == allowed_errno)) { + close(fd); + return; + } + + goto on_error; + } + + if ((size_t)ret != count) + goto on_error; + + close(fd); + return; + +on_error: + saved_errno = errno; + close(fd); + errno = saved_errno; + + if (ret < 0) + ksft_exit_fail_msg("%s - Failed to write to file %s\n", + strerror(errno), filename); + + ksft_exit_fail_msg("Failed to write to file %s\n", filename); +} + +static void change_to_userns(void) +{ + int ret; + uid_t uid; + gid_t gid; + /* {g,u}id_map files only allow a max of 4096 bytes written to them */ + char idmap[4096]; + + uid = getuid(); + gid = getgid(); + + ret = unshare(CLONE_NEWUSER); + if (ret < 0) + ksft_exit_fail_msg("%s - Failed to unshare user namespace\n", + strerror(errno)); + + write_to_file("/proc/self/setgroups", "deny", strlen("deny"), ENOENT); + + ret = snprintf(idmap, sizeof(idmap), "0 %d 1", uid); + if (ret < 0 || (size_t)ret >= sizeof(idmap)) + ksft_exit_fail_msg("%s - Failed to prepare uid mapping\n", + strerror(errno)); + + write_to_file("/proc/self/uid_map", idmap, strlen(idmap), 0); + + ret = snprintf(idmap, sizeof(idmap), "0 %d 1", gid); + if (ret < 0 || (size_t)ret >= sizeof(idmap)) + ksft_exit_fail_msg("%s - Failed to prepare uid mapping\n", + strerror(errno)); + + write_to_file("/proc/self/gid_map", idmap, strlen(idmap), 0); + + ret = setgid(0); + if (ret) + ksft_exit_fail_msg("%s - Failed to setgid(0)\n", + strerror(errno)); + + ret = setuid(0); + if (ret) + ksft_exit_fail_msg("%s - Failed to setgid(0)\n", + strerror(errno)); +} + +static void change_to_mountns(void) +{ + int ret; + + ret = unshare(CLONE_NEWNS); + if (ret < 0) + ksft_exit_fail_msg("%s - Failed to unshare mount namespace\n", + strerror(errno)); + + ret = mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, 0); + if (ret < 0) + ksft_exit_fail_msg("%s - Failed to mount / as private\n", + strerror(errno)); +} + +static void rmdir_protect_errno(const char *dir) +{ + int saved_errno = errno; + (void)rmdir(dir); + errno = saved_errno; +} + +static void __do_binderfs_test(void) +{ + int fd, ret, saved_errno; + size_t len; + ssize_t wret; + bool keep = false; + struct binderfs_device device = { 0 }; + struct binder_version version = { 0 }; + + change_to_mountns(); + + ret = mkdir("/dev/binderfs", 0755); + if (ret < 0) { + if (errno != EEXIST) + ksft_exit_fail_msg( + "%s - Failed to create binderfs mountpoint\n", + strerror(errno)); + + keep = true; + } + + ret = mount(NULL, "/dev/binderfs", "binder", 0, 0); + if (ret < 0) { + if (errno != ENODEV) + ksft_exit_fail_msg("%s - Failed to mount binderfs\n", + strerror(errno)); + + keep ? : rmdir_protect_errno("/dev/binderfs"); + ksft_exit_skip( + "The Android binderfs filesystem is not available\n"); + } + + /* binderfs mount test passed */ + ksft_inc_pass_cnt(); + + memcpy(device.name, "my-binder", strlen("my-binder")); + + fd = open("/dev/binderfs/binder-control", O_RDONLY | O_CLOEXEC); + if (fd < 0) + ksft_exit_fail_msg( + "%s - Failed to open binder-control device\n", + strerror(errno)); + + ret = ioctl(fd, BINDER_CTL_ADD, &device); + saved_errno = errno; + close(fd); + errno = saved_errno; + if (ret < 0) { + keep ? : rmdir_protect_errno("/dev/binderfs"); + ksft_exit_fail_msg( + "%s - Failed to allocate new binder device\n", + strerror(errno)); + } + + ksft_print_msg( + "Allocated new binder device with major %d, minor %d, and name %s\n", + device.major, device.minor, device.name); + + /* binder device allocation test passed */ + ksft_inc_pass_cnt(); + + fd = open("/dev/binderfs/my-binder", O_CLOEXEC | O_RDONLY); + if (fd < 0) { + keep ? : rmdir_protect_errno("/dev/binderfs"); + ksft_exit_fail_msg("%s - Failed to open my-binder device\n", + strerror(errno)); + } + + ret = ioctl(fd, BINDER_VERSION, &version); + saved_errno = errno; + close(fd); + errno = saved_errno; + if (ret < 0) { + keep ? : rmdir_protect_errno("/dev/binderfs"); + ksft_exit_fail_msg( + "%s - Failed to open perform BINDER_VERSION request\n", + strerror(errno)); + } + + ksft_print_msg("Detected binder version: %d\n", + version.protocol_version); + + /* binder transaction with binderfs binder device passed */ + ksft_inc_pass_cnt(); + + ret = unlink("/dev/binderfs/my-binder"); + if (ret < 0) { + keep ? : rmdir_protect_errno("/dev/binderfs"); + ksft_exit_fail_msg("%s - Failed to delete binder device\n", + strerror(errno)); + } + + /* binder device removal passed */ + ksft_inc_pass_cnt(); + + ret = unlink("/dev/binderfs/binder-control"); + if (!ret) { + keep ? : rmdir_protect_errno("/dev/binderfs"); + ksft_exit_fail_msg("Managed to delete binder-control device\n"); + } else if (errno != EPERM) { + keep ? : rmdir_protect_errno("/dev/binderfs"); + ksft_exit_fail_msg( + "%s - Failed to delete binder-control device but exited with unexpected error code\n", + strerror(errno)); + } + + /* binder-control device removal failed as expected */ + ksft_inc_xfail_cnt(); + +on_error: + ret = umount2("/dev/binderfs", MNT_DETACH); + keep ?: rmdir_protect_errno("/dev/binderfs"); + if (ret < 0) + ksft_exit_fail_msg("%s - Failed to unmount binderfs\n", + strerror(errno)); + + /* binderfs unmount test passed */ + ksft_inc_pass_cnt(); +} + +static void binderfs_test_privileged() +{ + if (geteuid() != 0) + ksft_print_msg( + "Tests are not run as root. Skipping privileged tests\n"); + else + __do_binderfs_test(); +} + +static void binderfs_test_unprivileged() +{ + change_to_userns(); + __do_binderfs_test(); +} + +int main(int argc, char *argv[]) +{ + binderfs_test_privileged(); + binderfs_test_unprivileged(); + ksft_exit_pass(); +} diff --git a/tools/testing/selftests/filesystems/binderfs/config b/tools/testing/selftests/filesystems/binderfs/config new file mode 100644 index 000000000000..02dd6cc9cf99 --- /dev/null +++ b/tools/testing/selftests/filesystems/binderfs/config @@ -0,0 +1,3 @@ +CONFIG_ANDROID=y +CONFIG_ANDROID_BINDERFS=y +CONFIG_ANDROID_BINDER_IPC=y diff --git a/tools/testing/selftests/ir/Makefile b/tools/testing/selftests/ir/Makefile index f4ba8eb84b95..ad06489c22a5 100644 --- a/tools/testing/selftests/ir/Makefile +++ b/tools/testing/selftests/ir/Makefile @@ -1,5 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 TEST_PROGS := ir_loopback.sh TEST_GEN_PROGS_EXTENDED := ir_loopback +APIDIR := ../../../include/uapi +CFLAGS += -Wall -O2 -I$(APIDIR) include ../lib.mk diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index f8f3e90700c0..1e6d14d2825c 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -21,6 +21,6 @@ TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls KSFT_KHDR_INSTALL := 1 include ../lib.mk -$(OUTPUT)/reuseport_bpf_numa: LDFLAGS += -lnuma +$(OUTPUT)/reuseport_bpf_numa: LDLIBS += -lnuma $(OUTPUT)/tcp_mmap: LDFLAGS += -lpthread $(OUTPUT)/tcp_inq: LDFLAGS += -lpthread diff --git a/tools/testing/selftests/net/forwarding/config b/tools/testing/selftests/net/forwarding/config index 5cd2aed97958..da96eff72a8e 100644 --- a/tools/testing/selftests/net/forwarding/config +++ b/tools/testing/selftests/net/forwarding/config @@ -10,3 +10,5 @@ CONFIG_NET_CLS_FLOWER=m CONFIG_NET_SCH_INGRESS=m CONFIG_NET_ACT_GACT=m CONFIG_VETH=m +CONFIG_NAMESPACES=y +CONFIG_NET_NS=y diff --git a/tools/testing/selftests/net/forwarding/forwarding.config.sample b/tools/testing/selftests/net/forwarding/forwarding.config.sample index e819d049d9ce..e2adb533c8fc 100644 --- a/tools/testing/selftests/net/forwarding/forwarding.config.sample +++ b/tools/testing/selftests/net/forwarding/forwarding.config.sample @@ -33,3 +33,6 @@ PAUSE_ON_CLEANUP=no NETIF_TYPE=veth # Whether to create virtual interfaces (veth) or not NETIF_CREATE=yes +# Timeout (in seconds) before ping exits regardless of how many packets have +# been sent or received +PING_TIMEOUT=5 diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index c1f16bb992dc..9385dc971269 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -17,6 +17,7 @@ NETIF_TYPE=${NETIF_TYPE:=veth} NETIF_CREATE=${NETIF_CREATE:=yes} MCD=${MCD:=smcrouted} MC_CLI=${MC_CLI:=smcroutectl} +PING_TIMEOUT=${PING_TIMEOUT:=5} relative_path="${BASH_SOURCE%/*}" if [[ "$relative_path" == "${BASH_SOURCE}" ]]; then @@ -820,7 +821,8 @@ ping_do() local vrf_name vrf_name=$(master_name_get $if_name) - ip vrf exec $vrf_name $PING $args $dip -c 10 -i 0.1 -w 2 &> /dev/null + ip vrf exec $vrf_name \ + $PING $args $dip -c 10 -i 0.1 -w $PING_TIMEOUT &> /dev/null } ping_test() @@ -840,7 +842,8 @@ ping6_do() local vrf_name vrf_name=$(master_name_get $if_name) - ip vrf exec $vrf_name $PING6 $args $dip -c 10 -i 0.1 -w 2 &> /dev/null + ip vrf exec $vrf_name \ + $PING6 $args $dip -c 10 -i 0.1 -w $PING_TIMEOUT &> /dev/null } ping6_test() diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh index 61844caf671e..28d568c48a73 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh @@ -190,6 +190,8 @@ setup_prepare() h4_create switch_create + forwarding_enable + trap_install $h3 ingress trap_install $h4 ingress } @@ -201,6 +203,8 @@ cleanup() trap_uninstall $h4 ingress trap_uninstall $h3 ingress + forwarding_restore + switch_destroy h4_destroy h3_destroy @@ -220,11 +224,15 @@ test_lag_slave() RET=0 + tc filter add dev $swp1 ingress pref 999 \ + proto 802.1q flower vlan_ethtype arp $tcflags \ + action pass mirror_install $swp1 ingress gt4 \ - "proto 802.1q flower vlan_id 333 $tcflags" + "proto 802.1q flower vlan_id 333 $tcflags" # Test connectivity through $up_dev when $down_dev is set down. ip link set dev $down_dev down + ip neigh flush dev br1 setup_wait_dev $up_dev setup_wait_dev $host_dev $ARPING -I br1 192.0.2.130 -qfc 1 @@ -240,6 +248,7 @@ test_lag_slave() ip link set dev $up_dev up ip link set dev $down_dev up mirror_uninstall $swp1 ingress + tc filter del dev $swp1 ingress pref 999 log_test "$what ($tcflags)" } diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh b/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh index 135902aa8b11..472bd023e2a5 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh @@ -79,6 +79,7 @@ test_span_gre_ttl() mirror_test v$h1 192.0.2.1 192.0.2.2 $h3 77 0 ip link set dev $tundev type $type ttl 50 + sleep 2 mirror_test v$h1 192.0.2.1 192.0.2.2 $h3 77 10 ip link set dev $tundev type $type ttl 100 diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_flower.sh b/tools/testing/selftests/net/forwarding/mirror_gre_flower.sh index 12914f40612d..09389f3b9369 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_flower.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_flower.sh @@ -81,6 +81,8 @@ full_test_span_gre_dir_acl() local match_dip=$1; shift local what=$1; shift + RET=0 + mirror_install $swp1 $direction $tundev \ "protocol ip flower $tcflags dst_ip $match_dip" fail_test_span_gre_dir $tundev $direction @@ -108,8 +110,6 @@ test_ip6gretap() test_all() { - RET=0 - slow_path_trap_install $swp1 ingress slow_path_trap_install $swp1 egress diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh index 204b25f13934..c02291e9841e 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh @@ -1,11 +1,44 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -# This test uses standard topology for testing gretap. See -# mirror_gre_topo_lib.sh for more details. -# # Test for "tc action mirred egress mirror" when the underlay route points at a # vlan device on top of a bridge device with vlan filtering (802.1q). +# +# +---------------------+ +---------------------+ +# | H1 | | H2 | +# | + $h1 | | $h2 + | +# | | 192.0.2.1/28 | | 192.0.2.2/28 | | +# +-----|---------------+ +---------------|-----+ +# | | +# +-----|-------------------------------------------------------------|-----+ +# | SW o--> mirred egress mirror dev {gt4,gt6} | | +# | | | | +# | +---|-------------------------------------------------------------|---+ | +# | | + $swp1 br1 $swp2 + | | +# | | | | +# | | + $swp3 | | +# | +---|-----------------------------------------------------------------+ | +# | | | | +# | | + br1.555 | +# | | 192.0.2.130/28 | +# | | 2001:db8:2::2/64 | +# | | | +# | | + gt6 (ip6gretap) + gt4 (gretap) | +# | | : loc=2001:db8:2::1 : loc=192.0.2.129 | +# | | : rem=2001:db8:2::2 : rem=192.0.2.130 | +# | | : ttl=100 : ttl=100 | +# | | : tos=inherit : tos=inherit | +# | | : : | +# +-----|---------------------:----------------------:----------------------+ +# | : : +# +-----|---------------------:----------------------:----------------------+ +# | H3 + $h3 + h3-gt6 (ip6gretap) + h3-gt4 (gretap) | +# | | loc=2001:db8:2::2 loc=192.0.2.130 | +# | + $h3.555 rem=2001:db8:2::1 rem=192.0.2.129 | +# | 192.0.2.130/28 ttl=100 ttl=100 | +# | 2001:db8:2::2/64 tos=inherit tos=inherit | +# | | +# +-------------------------------------------------------------------------+ ALL_TESTS=" test_gretap @@ -30,6 +63,15 @@ source mirror_gre_topo_lib.sh require_command $ARPING +h3_addr_add_del() +{ + local add_del=$1; shift + local dev=$1; shift + + ip addr $add_del dev $dev 192.0.2.130/28 + ip addr $add_del dev $dev 2001:db8:2::2/64 +} + setup_prepare() { h1=${NETIFS[p1]} @@ -55,7 +97,8 @@ setup_prepare() ip route rep 192.0.2.130/32 dev br1.555 ip -6 route rep 2001:db8:2::2/128 dev br1.555 - vlan_create $h3 555 v$h3 192.0.2.130/28 2001:db8:2::2/64 + vlan_create $h3 555 v$h3 + h3_addr_add_del add $h3.555 ip link set dev $swp3 master br1 bridge vlan add dev $swp3 vid 555 @@ -68,6 +111,8 @@ cleanup() ip link set dev $swp2 nomaster ip link set dev $swp3 nomaster + + h3_addr_add_del del $h3.555 vlan_destroy $h3 555 vlan_destroy br1 555 @@ -182,13 +227,19 @@ test_span_gre_untagged_egress() quick_test_span_gre_dir $tundev ingress quick_test_span_vlan_dir $h3 555 ingress + h3_addr_add_del del $h3.555 bridge vlan add dev $swp3 vid 555 pvid untagged - sleep 1 + h3_addr_add_del add $h3 + sleep 5 + quick_test_span_gre_dir $tundev ingress fail_test_span_vlan_dir $h3 555 ingress + h3_addr_add_del del $h3 bridge vlan add dev $swp3 vid 555 - sleep 1 + h3_addr_add_del add $h3.555 + sleep 5 + quick_test_span_gre_dir $tundev ingress quick_test_span_vlan_dir $h3 555 ingress @@ -218,12 +269,25 @@ test_span_gre_fdb_roaming() mirror_install $swp1 ingress $tundev "matchall $tcflags" quick_test_span_gre_dir $tundev ingress - bridge fdb del dev $swp3 $h3mac vlan 555 master - bridge fdb add dev $swp2 $h3mac vlan 555 master - sleep 1 - fail_test_span_gre_dir $tundev ingress - - bridge fdb del dev $swp2 $h3mac vlan 555 master + while ((RET == 0)); do + bridge fdb del dev $swp3 $h3mac vlan 555 master 2>/dev/null + bridge fdb add dev $swp2 $h3mac vlan 555 master + sleep 1 + fail_test_span_gre_dir $tundev ingress + + if ! bridge fdb sh dev $swp2 vlan 555 master \ + | grep -q $h3mac; then + printf "TEST: %-60s [RETRY]\n" \ + "$what: MAC roaming ($tcflags)" + # ARP or ND probably reprimed the FDB while the test + # was running. We would get a spurious failure. + RET=0 + continue + fi + break + done + + bridge fdb del dev $swp2 $h3mac vlan 555 master 2>/dev/null # Re-prime FDB $ARPING -I br1.555 192.0.2.130 -fqc 1 sleep 1 diff --git a/tools/testing/selftests/net/forwarding/mirror_lib.sh b/tools/testing/selftests/net/forwarding/mirror_lib.sh index 07991e1025c7..00797597fcf5 100644 --- a/tools/testing/selftests/net/forwarding/mirror_lib.sh +++ b/tools/testing/selftests/net/forwarding/mirror_lib.sh @@ -29,9 +29,12 @@ mirror_test() local pref=$1; shift local expect=$1; shift + local ping_timeout=$((PING_TIMEOUT * 5)) local t0=$(tc_rule_stats_get $dev $pref) ip vrf exec $vrf_name \ - ${PING} ${sip:+-I $sip} $dip -c 10 -i 0.1 -w 2 &> /dev/null + ${PING} ${sip:+-I $sip} $dip -c 10 -i 0.5 -w $ping_timeout \ + &> /dev/null + sleep 0.5 local t1=$(tc_rule_stats_get $dev $pref) local delta=$((t1 - t0)) # Tolerate a couple stray extra packets. diff --git a/tools/testing/selftests/net/forwarding/router_broadcast.sh b/tools/testing/selftests/net/forwarding/router_broadcast.sh index 7bd2ebb6e9de..9a678ece32b4 100755 --- a/tools/testing/selftests/net/forwarding/router_broadcast.sh +++ b/tools/testing/selftests/net/forwarding/router_broadcast.sh @@ -170,7 +170,8 @@ ping_test_from() log_info "ping $dip, expected reply from $from" ip vrf exec $(master_name_get $oif) \ - $PING -I $oif $dip -c 10 -i 0.1 -w 2 -b 2>&1 | grep $from &> /dev/null + $PING -I $oif $dip -c 10 -i 0.1 -w $PING_TIMEOUT -b 2>&1 \ + | grep $from &> /dev/null check_err_fail $fail $? } diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index ff68ed19c0ef..4ac50ccb3272 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -42,7 +42,7 @@ FIXTURE_SETUP(tls) len = sizeof(addr); memset(&tls12, 0, sizeof(tls12)); - tls12.info.version = TLS_1_2_VERSION; + tls12.info.version = TLS_1_3_VERSION; tls12.info.cipher_type = TLS_CIPHER_AES_GCM_128; addr.sin_family = AF_INET; @@ -763,4 +763,140 @@ TEST_F(tls, control_msg) EXPECT_EQ(memcmp(buf, test_str, send_len), 0); } +TEST(keysizes) { + struct tls12_crypto_info_aes_gcm_256 tls12; + struct sockaddr_in addr; + int sfd, ret, fd, cfd; + socklen_t len; + bool notls; + + notls = false; + len = sizeof(addr); + + memset(&tls12, 0, sizeof(tls12)); + tls12.info.version = TLS_1_2_VERSION; + tls12.info.cipher_type = TLS_CIPHER_AES_GCM_256; + + addr.sin_family = AF_INET; + addr.sin_addr.s_addr = htonl(INADDR_ANY); + addr.sin_port = 0; + + fd = socket(AF_INET, SOCK_STREAM, 0); + sfd = socket(AF_INET, SOCK_STREAM, 0); + + ret = bind(sfd, &addr, sizeof(addr)); + ASSERT_EQ(ret, 0); + ret = listen(sfd, 10); + ASSERT_EQ(ret, 0); + + ret = getsockname(sfd, &addr, &len); + ASSERT_EQ(ret, 0); + + ret = connect(fd, &addr, sizeof(addr)); + ASSERT_EQ(ret, 0); + + ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + if (ret != 0) { + notls = true; + printf("Failure setting TCP_ULP, testing without tls\n"); + } + + if (!notls) { + ret = setsockopt(fd, SOL_TLS, TLS_TX, &tls12, + sizeof(tls12)); + EXPECT_EQ(ret, 0); + } + + cfd = accept(sfd, &addr, &len); + ASSERT_GE(cfd, 0); + + if (!notls) { + ret = setsockopt(cfd, IPPROTO_TCP, TCP_ULP, "tls", + sizeof("tls")); + EXPECT_EQ(ret, 0); + + ret = setsockopt(cfd, SOL_TLS, TLS_RX, &tls12, + sizeof(tls12)); + EXPECT_EQ(ret, 0); + } + + close(sfd); + close(fd); + close(cfd); +} + +TEST(tls12) { + int fd, cfd; + bool notls; + + struct tls12_crypto_info_aes_gcm_128 tls12; + struct sockaddr_in addr; + socklen_t len; + int sfd, ret; + + notls = false; + len = sizeof(addr); + + memset(&tls12, 0, sizeof(tls12)); + tls12.info.version = TLS_1_2_VERSION; + tls12.info.cipher_type = TLS_CIPHER_AES_GCM_128; + + addr.sin_family = AF_INET; + addr.sin_addr.s_addr = htonl(INADDR_ANY); + addr.sin_port = 0; + + fd = socket(AF_INET, SOCK_STREAM, 0); + sfd = socket(AF_INET, SOCK_STREAM, 0); + + ret = bind(sfd, &addr, sizeof(addr)); + ASSERT_EQ(ret, 0); + ret = listen(sfd, 10); + ASSERT_EQ(ret, 0); + + ret = getsockname(sfd, &addr, &len); + ASSERT_EQ(ret, 0); + + ret = connect(fd, &addr, sizeof(addr)); + ASSERT_EQ(ret, 0); + + ret = setsockopt(fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls")); + if (ret != 0) { + notls = true; + printf("Failure setting TCP_ULP, testing without tls\n"); + } + + if (!notls) { + ret = setsockopt(fd, SOL_TLS, TLS_TX, &tls12, + sizeof(tls12)); + ASSERT_EQ(ret, 0); + } + + cfd = accept(sfd, &addr, &len); + ASSERT_GE(cfd, 0); + + if (!notls) { + ret = setsockopt(cfd, IPPROTO_TCP, TCP_ULP, "tls", + sizeof("tls")); + ASSERT_EQ(ret, 0); + + ret = setsockopt(cfd, SOL_TLS, TLS_RX, &tls12, + sizeof(tls12)); + ASSERT_EQ(ret, 0); + } + + close(sfd); + + char const *test_str = "test_read"; + int send_len = 10; + char buf[10]; + + send_len = strlen(test_str) + 1; + EXPECT_EQ(send(fd, test_str, send_len, 0), send_len); + EXPECT_NE(recv(cfd, buf, send_len, 0), -1); + EXPECT_EQ(memcmp(buf, test_str, send_len), 0); + + close(fd); + close(cfd); +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/net/xfrm_policy.sh b/tools/testing/selftests/net/xfrm_policy.sh index 8db35b99457c..71d7fdc513c1 100755 --- a/tools/testing/selftests/net/xfrm_policy.sh +++ b/tools/testing/selftests/net/xfrm_policy.sh @@ -28,6 +28,19 @@ KEY_AES=0x0123456789abcdef0123456789012345 SPI1=0x1 SPI2=0x2 +do_esp_policy() { + local ns=$1 + local me=$2 + local remote=$3 + local lnet=$4 + local rnet=$5 + + # to encrypt packets as they go out (includes forwarded packets that need encapsulation) + ip -net $ns xfrm policy add src $lnet dst $rnet dir out tmpl src $me dst $remote proto esp mode tunnel priority 100 action allow + # to fwd decrypted packets after esp processing: + ip -net $ns xfrm policy add src $rnet dst $lnet dir fwd tmpl src $remote dst $me proto esp mode tunnel priority 100 action allow +} + do_esp() { local ns=$1 local me=$2 @@ -40,10 +53,59 @@ do_esp() { ip -net $ns xfrm state add src $remote dst $me proto esp spi $spi_in enc aes $KEY_AES auth sha1 $KEY_SHA mode tunnel sel src $rnet dst $lnet ip -net $ns xfrm state add src $me dst $remote proto esp spi $spi_out enc aes $KEY_AES auth sha1 $KEY_SHA mode tunnel sel src $lnet dst $rnet - # to encrypt packets as they go out (includes forwarded packets that need encapsulation) - ip -net $ns xfrm policy add src $lnet dst $rnet dir out tmpl src $me dst $remote proto esp mode tunnel priority 100 action allow - # to fwd decrypted packets after esp processing: - ip -net $ns xfrm policy add src $rnet dst $lnet dir fwd tmpl src $remote dst $me proto esp mode tunnel priority 100 action allow + do_esp_policy $ns $me $remote $lnet $rnet +} + +# add policies with different netmasks, to make sure kernel carries +# the policies contained within new netmask over when search tree is +# re-built. +# peer netns that are supposed to be encapsulated via esp have addresses +# in the 10.0.1.0/24 and 10.0.2.0/24 subnets, respectively. +# +# Adding a policy for '10.0.1.0/23' will make it necessary to +# alter the prefix of 10.0.1.0 subnet. +# In case new prefix overlaps with existing node, the node and all +# policies it carries need to be merged with the existing one(s). +# +# Do that here. +do_overlap() +{ + local ns=$1 + + # adds new nodes to tree (neither network exists yet in policy database). + ip -net $ns xfrm policy add src 10.1.0.0/24 dst 10.0.0.0/24 dir fwd priority 200 action block + + # adds a new node in the 10.0.0.0/24 tree (dst node exists). + ip -net $ns xfrm policy add src 10.2.0.0/24 dst 10.0.0.0/24 dir fwd priority 200 action block + + # adds a 10.2.0.0/23 node, but for different dst. + ip -net $ns xfrm policy add src 10.2.0.0/23 dst 10.0.1.0/24 dir fwd priority 200 action block + + # dst now overlaps with the 10.0.1.0/24 ESP policy in fwd. + # kernel must 'promote' existing one (10.0.0.0/24) to 10.0.0.0/23. + # But 10.0.0.0/23 also includes existing 10.0.1.0/24, so that node + # also has to be merged too, including source-sorted subtrees. + # old: + # 10.0.0.0/24 (node 1 in dst tree of the bin) + # 10.1.0.0/24 (node in src tree of dst node 1) + # 10.2.0.0/24 (node in src tree of dst node 1) + # 10.0.1.0/24 (node 2 in dst tree of the bin) + # 10.0.2.0/24 (node in src tree of dst node 2) + # 10.2.0.0/24 (node in src tree of dst node 2) + # + # The next 'policy add' adds dst '10.0.0.0/23', which means + # that dst node 1 and dst node 2 have to be merged including + # the sub-tree. As no duplicates are allowed, policies in + # the two '10.0.2.0/24' are also merged. + # + # after the 'add', internal search tree should look like this: + # 10.0.0.0/23 (node in dst tree of bin) + # 10.0.2.0/24 (node in src tree of dst node) + # 10.1.0.0/24 (node in src tree of dst node) + # 10.2.0.0/24 (node in src tree of dst node) + # + # 10.0.0.0/24 and 10.0.1.0/24 nodes have been merged as 10.0.0.0/23. + ip -net $ns xfrm policy add src 10.1.0.0/24 dst 10.0.0.0/23 dir fwd priority 200 action block } do_esp_policy_get_check() { @@ -160,6 +222,41 @@ check_xfrm() { return $lret } +check_exceptions() +{ + logpostfix="$1" + local lret=0 + + # ping to .254 should be excluded from the tunnel (exception is in place). + check_xfrm 0 254 + if [ $? -ne 0 ]; then + echo "FAIL: expected ping to .254 to fail ($logpostfix)" + lret=1 + else + echo "PASS: ping to .254 bypassed ipsec tunnel ($logpostfix)" + fi + + # ping to .253 should use use ipsec due to direct policy exception. + check_xfrm 1 253 + if [ $? -ne 0 ]; then + echo "FAIL: expected ping to .253 to use ipsec tunnel ($logpostfix)" + lret=1 + else + echo "PASS: direct policy matches ($logpostfix)" + fi + + # ping to .2 should use ipsec. + check_xfrm 1 2 + if [ $? -ne 0 ]; then + echo "FAIL: expected ping to .2 to use ipsec tunnel ($logpostfix)" + lret=1 + else + echo "PASS: policy matches ($logpostfix)" + fi + + return $lret +} + #check for needed privileges if [ "$(id -u)" -ne 0 ];then echo "SKIP: Need root privileges" @@ -270,33 +367,45 @@ do_exception ns4 10.0.3.10 10.0.3.1 10.0.1.253 10.0.1.240/28 do_exception ns3 dead:3::1 dead:3::10 dead:2::fd dead:2:f0::/96 do_exception ns4 dead:3::10 dead:3::1 dead:1::fd dead:1:f0::/96 -# ping to .254 should now be excluded from the tunnel -check_xfrm 0 254 +check_exceptions "exceptions" if [ $? -ne 0 ]; then - echo "FAIL: expected ping to .254 to fail" ret=1 -else - echo "PASS: ping to .254 bypassed ipsec tunnel" fi -# ping to .253 should use use ipsec due to direct policy exception. -check_xfrm 1 253 -if [ $? -ne 0 ]; then - echo "FAIL: expected ping to .253 to use ipsec tunnel" - ret=1 -else - echo "PASS: direct policy matches" -fi +# insert block policies with adjacent/overlapping netmasks +do_overlap ns3 -# ping to .2 should use ipsec. -check_xfrm 1 2 +check_exceptions "exceptions and block policies" if [ $? -ne 0 ]; then - echo "FAIL: expected ping to .2 to use ipsec tunnel" ret=1 -else - echo "PASS: policy matches" fi +for n in ns3 ns4;do + ip -net $n xfrm policy set hthresh4 28 24 hthresh6 126 125 + sleep $((RANDOM%5)) +done + +check_exceptions "exceptions and block policies after hresh changes" + +# full flush of policy db, check everything gets freed incl. internal meta data +ip -net ns3 xfrm policy flush + +do_esp_policy ns3 10.0.3.1 10.0.3.10 10.0.1.0/24 10.0.2.0/24 +do_exception ns3 10.0.3.1 10.0.3.10 10.0.2.253 10.0.2.240/28 + +# move inexact policies to hash table +ip -net ns3 xfrm policy set hthresh4 16 16 + +sleep $((RANDOM%5)) +check_exceptions "exceptions and block policies after hthresh change in ns3" + +# restore original hthresh settings -- move policies back to tables +for n in ns3 ns4;do + ip -net $n xfrm policy set hthresh4 32 32 hthresh6 128 128 + sleep $((RANDOM%5)) +done +check_exceptions "exceptions and block policies after hresh change to normal" + for i in 1 2 3 4;do ip netns del ns$i;done exit $ret diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index 47ed6cef93fb..c9ff2b47bd1c 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for netfilter selftests -TEST_PROGS := nft_trans_stress.sh +TEST_PROGS := nft_trans_stress.sh nft_nat.sh include ../lib.mk diff --git a/tools/testing/selftests/netfilter/config b/tools/testing/selftests/netfilter/config index 1017313e41a8..59caa8f71cd8 100644 --- a/tools/testing/selftests/netfilter/config +++ b/tools/testing/selftests/netfilter/config @@ -1,2 +1,2 @@ CONFIG_NET_NS=y -NF_TABLES_INET=y +CONFIG_NF_TABLES_INET=y diff --git a/tools/testing/selftests/netfilter/nft_nat.sh b/tools/testing/selftests/netfilter/nft_nat.sh new file mode 100755 index 000000000000..8ec76681605c --- /dev/null +++ b/tools/testing/selftests/netfilter/nft_nat.sh @@ -0,0 +1,762 @@ +#!/bin/bash +# +# This test is for basic NAT functionality: snat, dnat, redirect, masquerade. +# + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 +ret=0 + +nft --version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without nft tool" + exit $ksft_skip +fi + +ip -Version > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run test without ip tool" + exit $ksft_skip +fi + +ip netns add ns0 +ip netns add ns1 +ip netns add ns2 + +ip link add veth0 netns ns0 type veth peer name eth0 netns ns1 +ip link add veth1 netns ns0 type veth peer name eth0 netns ns2 + +ip -net ns0 link set lo up +ip -net ns0 link set veth0 up +ip -net ns0 addr add 10.0.1.1/24 dev veth0 +ip -net ns0 addr add dead:1::1/64 dev veth0 + +ip -net ns0 link set veth1 up +ip -net ns0 addr add 10.0.2.1/24 dev veth1 +ip -net ns0 addr add dead:2::1/64 dev veth1 + +for i in 1 2; do + ip -net ns$i link set lo up + ip -net ns$i link set eth0 up + ip -net ns$i addr add 10.0.$i.99/24 dev eth0 + ip -net ns$i route add default via 10.0.$i.1 + ip -net ns$i addr add dead:$i::99/64 dev eth0 + ip -net ns$i route add default via dead:$i::1 +done + +bad_counter() +{ + local ns=$1 + local counter=$2 + local expect=$3 + + echo "ERROR: $counter counter in $ns has unexpected value (expected $expect)" 1>&2 + ip netns exec $ns nft list counter inet filter $counter 1>&2 +} + +check_counters() +{ + ns=$1 + local lret=0 + + cnt=$(ip netns exec $ns nft list counter inet filter ns0in | grep -q "packets 1 bytes 84") + if [ $? -ne 0 ]; then + bad_counter $ns ns0in "packets 1 bytes 84" + lret=1 + fi + cnt=$(ip netns exec $ns nft list counter inet filter ns0out | grep -q "packets 1 bytes 84") + if [ $? -ne 0 ]; then + bad_counter $ns ns0out "packets 1 bytes 84" + lret=1 + fi + + expect="packets 1 bytes 104" + cnt=$(ip netns exec $ns nft list counter inet filter ns0in6 | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter $ns ns0in6 "$expect" + lret=1 + fi + cnt=$(ip netns exec $ns nft list counter inet filter ns0out6 | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter $ns ns0out6 "$expect" + lret=1 + fi + + return $lret +} + +check_ns0_counters() +{ + local ns=$1 + local lret=0 + + cnt=$(ip netns exec ns0 nft list counter inet filter ns0in | grep -q "packets 0 bytes 0") + if [ $? -ne 0 ]; then + bad_counter ns0 ns0in "packets 0 bytes 0" + lret=1 + fi + + cnt=$(ip netns exec ns0 nft list counter inet filter ns0in6 | grep -q "packets 0 bytes 0") + if [ $? -ne 0 ]; then + bad_counter ns0 ns0in6 "packets 0 bytes 0" + lret=1 + fi + + cnt=$(ip netns exec ns0 nft list counter inet filter ns0out | grep -q "packets 0 bytes 0") + if [ $? -ne 0 ]; then + bad_counter ns0 ns0out "packets 0 bytes 0" + lret=1 + fi + cnt=$(ip netns exec ns0 nft list counter inet filter ns0out6 | grep -q "packets 0 bytes 0") + if [ $? -ne 0 ]; then + bad_counter ns0 ns0out6 "packets 0 bytes 0" + lret=1 + fi + + for dir in "in" "out" ; do + expect="packets 1 bytes 84" + cnt=$(ip netns exec ns0 nft list counter inet filter ${ns}${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns0 $ns$dir "$expect" + lret=1 + fi + + expect="packets 1 bytes 104" + cnt=$(ip netns exec ns0 nft list counter inet filter ${ns}${dir}6 | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns0 $ns$dir6 "$expect" + lret=1 + fi + done + + return $lret +} + +reset_counters() +{ + for i in 0 1 2;do + ip netns exec ns$i nft reset counters inet > /dev/null + done +} + +test_local_dnat6() +{ + local lret=0 +ip netns exec ns0 nft -f - <<EOF +table ip6 nat { + chain output { + type nat hook output priority 0; policy accept; + ip6 daddr dead:1::99 dnat to dead:2::99 + } +} +EOF + if [ $? -ne 0 ]; then + echo "SKIP: Could not add add ip6 dnat hook" + return $ksft_skip + fi + + # ping netns1, expect rewrite to netns2 + ip netns exec ns0 ping -q -c 1 dead:1::99 > /dev/null + if [ $? -ne 0 ]; then + lret=1 + echo "ERROR: ping6 failed" + return $lret + fi + + expect="packets 0 bytes 0" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns0 ns1$dir "$expect" + lret=1 + fi + done + + expect="packets 1 bytes 104" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns0 ns2$dir "$expect" + lret=1 + fi + done + + # expect 0 count in ns1 + expect="packets 0 bytes 0" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + done + + # expect 1 packet in ns2 + expect="packets 1 bytes 104" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns0$dir "$expect" + lret=1 + fi + done + + test $lret -eq 0 && echo "PASS: ipv6 ping to ns1 was NATted to ns2" + ip netns exec ns0 nft flush chain ip6 nat output + + return $lret +} + +test_local_dnat() +{ + local lret=0 +ip netns exec ns0 nft -f - <<EOF +table ip nat { + chain output { + type nat hook output priority 0; policy accept; + ip daddr 10.0.1.99 dnat to 10.0.2.99 + } +} +EOF + # ping netns1, expect rewrite to netns2 + ip netns exec ns0 ping -q -c 1 10.0.1.99 > /dev/null + if [ $? -ne 0 ]; then + lret=1 + echo "ERROR: ping failed" + return $lret + fi + + expect="packets 0 bytes 0" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns0 ns1$dir "$expect" + lret=1 + fi + done + + expect="packets 1 bytes 84" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns0 ns2$dir "$expect" + lret=1 + fi + done + + # expect 0 count in ns1 + expect="packets 0 bytes 0" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + done + + # expect 1 packet in ns2 + expect="packets 1 bytes 84" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns0$dir "$expect" + lret=1 + fi + done + + test $lret -eq 0 && echo "PASS: ping to ns1 was NATted to ns2" + + ip netns exec ns0 nft flush chain ip nat output + + reset_counters + ip netns exec ns0 ping -q -c 1 10.0.1.99 > /dev/null + if [ $? -ne 0 ]; then + lret=1 + echo "ERROR: ping failed" + return $lret + fi + + expect="packets 1 bytes 84" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns0 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns1$dir "$expect" + lret=1 + fi + done + expect="packets 0 bytes 0" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns0 ns2$dir "$expect" + lret=1 + fi + done + + # expect 1 count in ns1 + expect="packets 1 bytes 84" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns0 ns0$dir "$expect" + lret=1 + fi + done + + # expect 0 packet in ns2 + expect="packets 0 bytes 0" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns2 nft list counter inet filter ns0${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns2$dir "$expect" + lret=1 + fi + done + + test $lret -eq 0 && echo "PASS: ping to ns1 OK after nat output chain flush" + + return $lret +} + + +test_masquerade6() +{ + local lret=0 + + ip netns exec ns0 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null + + ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping ns1 from ns2 via ipv6" + return 1 + lret=1 + fi + + expect="packets 1 bytes 104" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns2$dir "$expect" + lret=1 + fi + + cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns1$dir "$expect" + lret=1 + fi + done + + reset_counters + +# add masquerading rule +ip netns exec ns0 nft -f - <<EOF +table ip6 nat { + chain postrouting { + type nat hook postrouting priority 0; policy accept; + meta oif veth0 masquerade + } +} +EOF + ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping ns1 from ns2 with active ipv6 masquerading" + lret=1 + fi + + # ns1 should have seen packets from ns0, due to masquerade + expect="packets 1 bytes 104" + for dir in "in6" "out6" ; do + + cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + + cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns1$dir "$expect" + lret=1 + fi + done + + # ns1 should not have seen packets from ns2, due to masquerade + expect="packets 0 bytes 0" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns1$dir "$expect" + lret=1 + fi + done + + ip netns exec ns0 nft flush chain ip6 nat postrouting + if [ $? -ne 0 ]; then + echo "ERROR: Could not flush ip6 nat postrouting" 1>&2 + lret=1 + fi + + test $lret -eq 0 && echo "PASS: IPv6 masquerade for ns2" + + return $lret +} + +test_masquerade() +{ + local lret=0 + + ip netns exec ns0 sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null + ip netns exec ns0 sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null + + ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: canot ping ns1 from ns2" + lret=1 + fi + + expect="packets 1 bytes 84" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns2$dir "$expect" + lret=1 + fi + + cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns1$dir "$expect" + lret=1 + fi + done + + reset_counters + +# add masquerading rule +ip netns exec ns0 nft -f - <<EOF +table ip nat { + chain postrouting { + type nat hook postrouting priority 0; policy accept; + meta oif veth0 masquerade + } +} +EOF + ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping ns1 from ns2 with active ip masquerading" + lret=1 + fi + + # ns1 should have seen packets from ns0, due to masquerade + expect="packets 1 bytes 84" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns0${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + + cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns1$dir "$expect" + lret=1 + fi + done + + # ns1 should not have seen packets from ns2, due to masquerade + expect="packets 0 bytes 0" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns1$dir "$expect" + lret=1 + fi + done + + ip netns exec ns0 nft flush chain ip nat postrouting + if [ $? -ne 0 ]; then + echo "ERROR: Could not flush nat postrouting" 1>&2 + lret=1 + fi + + test $lret -eq 0 && echo "PASS: IP masquerade for ns2" + + return $lret +} + +test_redirect6() +{ + local lret=0 + + ip netns exec ns0 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null + + ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannnot ping ns1 from ns2 via ipv6" + lret=1 + fi + + expect="packets 1 bytes 104" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns2$dir "$expect" + lret=1 + fi + + cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns1$dir "$expect" + lret=1 + fi + done + + reset_counters + +# add redirect rule +ip netns exec ns0 nft -f - <<EOF +table ip6 nat { + chain prerouting { + type nat hook prerouting priority 0; policy accept; + meta iif veth1 meta l4proto icmpv6 ip6 saddr dead:2::99 ip6 daddr dead:1::99 redirect + } +} +EOF + ip netns exec ns2 ping -q -c 1 dead:1::99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping ns1 from ns2 with active ip6 redirect" + lret=1 + fi + + # ns1 should have seen no packets from ns2, due to redirection + expect="packets 0 bytes 0" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + done + + # ns0 should have seen packets from ns2, due to masquerade + expect="packets 1 bytes 104" + for dir in "in6" "out6" ; do + cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + done + + ip netns exec ns0 nft delete table ip6 nat + if [ $? -ne 0 ]; then + echo "ERROR: Could not delete ip6 nat table" 1>&2 + lret=1 + fi + + test $lret -eq 0 && echo "PASS: IPv6 redirection for ns2" + + return $lret +} + +test_redirect() +{ + local lret=0 + + ip netns exec ns0 sysctl net.ipv4.conf.veth0.forwarding=1 > /dev/null + ip netns exec ns0 sysctl net.ipv4.conf.veth1.forwarding=1 > /dev/null + + ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping ns1 from ns2" + lret=1 + fi + + expect="packets 1 bytes 84" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns2$dir "$expect" + lret=1 + fi + + cnt=$(ip netns exec ns2 nft list counter inet filter ns1${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns2 ns1$dir "$expect" + lret=1 + fi + done + + reset_counters + +# add redirect rule +ip netns exec ns0 nft -f - <<EOF +table ip nat { + chain prerouting { + type nat hook prerouting priority 0; policy accept; + meta iif veth1 ip protocol icmp ip saddr 10.0.2.99 ip daddr 10.0.1.99 redirect + } +} +EOF + ip netns exec ns2 ping -q -c 1 10.0.1.99 > /dev/null # ping ns2->ns1 + if [ $? -ne 0 ] ; then + echo "ERROR: cannot ping ns1 from ns2 with active ip redirect" + lret=1 + fi + + # ns1 should have seen no packets from ns2, due to redirection + expect="packets 0 bytes 0" + for dir in "in" "out" ; do + + cnt=$(ip netns exec ns1 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + done + + # ns0 should have seen packets from ns2, due to masquerade + expect="packets 1 bytes 84" + for dir in "in" "out" ; do + cnt=$(ip netns exec ns0 nft list counter inet filter ns2${dir} | grep -q "$expect") + if [ $? -ne 0 ]; then + bad_counter ns1 ns0$dir "$expect" + lret=1 + fi + done + + ip netns exec ns0 nft delete table ip nat + if [ $? -ne 0 ]; then + echo "ERROR: Could not delete nat table" 1>&2 + lret=1 + fi + + test $lret -eq 0 && echo "PASS: IP redirection for ns2" + + return $lret +} + + +# ip netns exec ns0 ping -c 1 -q 10.0.$i.99 +for i in 0 1 2; do +ip netns exec ns$i nft -f - <<EOF +table inet filter { + counter ns0in {} + counter ns1in {} + counter ns2in {} + + counter ns0out {} + counter ns1out {} + counter ns2out {} + + counter ns0in6 {} + counter ns1in6 {} + counter ns2in6 {} + + counter ns0out6 {} + counter ns1out6 {} + counter ns2out6 {} + + map nsincounter { + type ipv4_addr : counter + elements = { 10.0.1.1 : "ns0in", + 10.0.2.1 : "ns0in", + 10.0.1.99 : "ns1in", + 10.0.2.99 : "ns2in" } + } + + map nsincounter6 { + type ipv6_addr : counter + elements = { dead:1::1 : "ns0in6", + dead:2::1 : "ns0in6", + dead:1::99 : "ns1in6", + dead:2::99 : "ns2in6" } + } + + map nsoutcounter { + type ipv4_addr : counter + elements = { 10.0.1.1 : "ns0out", + 10.0.2.1 : "ns0out", + 10.0.1.99: "ns1out", + 10.0.2.99: "ns2out" } + } + + map nsoutcounter6 { + type ipv6_addr : counter + elements = { dead:1::1 : "ns0out6", + dead:2::1 : "ns0out6", + dead:1::99 : "ns1out6", + dead:2::99 : "ns2out6" } + } + + chain input { + type filter hook input priority 0; policy accept; + counter name ip saddr map @nsincounter + icmpv6 type { "echo-request", "echo-reply" } counter name ip6 saddr map @nsincounter6 + } + chain output { + type filter hook output priority 0; policy accept; + counter name ip daddr map @nsoutcounter + icmpv6 type { "echo-request", "echo-reply" } counter name ip6 daddr map @nsoutcounter6 + } +} +EOF +done + +sleep 3 +# test basic connectivity +for i in 1 2; do + ip netns exec ns0 ping -c 1 -q 10.0.$i.99 > /dev/null + if [ $? -ne 0 ];then + echo "ERROR: Could not reach other namespace(s)" 1>&2 + ret=1 + fi + + ip netns exec ns0 ping -c 1 -q dead:$i::99 > /dev/null + if [ $? -ne 0 ];then + echo "ERROR: Could not reach other namespace(s) via ipv6" 1>&2 + ret=1 + fi + check_counters ns$i + if [ $? -ne 0 ]; then + ret=1 + fi + + check_ns0_counters ns$i + if [ $? -ne 0 ]; then + ret=1 + fi + reset_counters +done + +if [ $ret -eq 0 ];then + echo "PASS: netns routing/connectivity: ns0 can reach ns1 and ns2" +fi + +reset_counters +test_local_dnat +test_local_dnat6 + +reset_counters +test_masquerade +test_masquerade6 + +reset_counters +test_redirect +test_redirect6 + +for i in 0 1 2; do ip netns del ns$i;done + +exit $ret diff --git a/tools/testing/selftests/networking/timestamping/Makefile b/tools/testing/selftests/networking/timestamping/Makefile index 9050eeea5f5f..1de8bd8ccf5d 100644 --- a/tools/testing/selftests/networking/timestamping/Makefile +++ b/tools/testing/selftests/networking/timestamping/Makefile @@ -9,6 +9,3 @@ all: $(TEST_PROGS) top_srcdir = ../../../../.. KSFT_KHDR_INSTALL := 1 include ../../lib.mk - -clean: - rm -fr $(TEST_GEN_FILES) diff --git a/tools/testing/selftests/networking/timestamping/rxtimestamp.c b/tools/testing/selftests/networking/timestamping/rxtimestamp.c index dd4162fc0419..6dee9e636a95 100644 --- a/tools/testing/selftests/networking/timestamping/rxtimestamp.c +++ b/tools/testing/selftests/networking/timestamping/rxtimestamp.c @@ -5,6 +5,7 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> +#include <unistd.h> #include <sys/time.h> #include <sys/socket.h> diff --git a/tools/testing/selftests/proc/.gitignore b/tools/testing/selftests/proc/.gitignore index 82121a81681f..29bac5ef9a93 100644 --- a/tools/testing/selftests/proc/.gitignore +++ b/tools/testing/selftests/proc/.gitignore @@ -10,4 +10,5 @@ /proc-uptime-002 /read /self +/setns-dcache /thread-self diff --git a/tools/testing/selftests/proc/Makefile b/tools/testing/selftests/proc/Makefile index 1c12c34cf85d..434d033ee067 100644 --- a/tools/testing/selftests/proc/Makefile +++ b/tools/testing/selftests/proc/Makefile @@ -14,6 +14,7 @@ TEST_GEN_PROGS += proc-uptime-001 TEST_GEN_PROGS += proc-uptime-002 TEST_GEN_PROGS += read TEST_GEN_PROGS += self +TEST_GEN_PROGS += setns-dcache TEST_GEN_PROGS += thread-self include ../lib.mk diff --git a/tools/testing/selftests/proc/setns-dcache.c b/tools/testing/selftests/proc/setns-dcache.c new file mode 100644 index 000000000000..60ab197a73fc --- /dev/null +++ b/tools/testing/selftests/proc/setns-dcache.c @@ -0,0 +1,129 @@ +/* + * Copyright © 2019 Alexey Dobriyan <adobriyan@gmail.com> + * + * Permission to use, copy, modify, and distribute this software for any + * purpose with or without fee is hereby granted, provided that the above + * copyright notice and this permission notice appear in all copies. + * + * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES + * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF + * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR + * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES + * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN + * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF + * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. + */ +/* + * Test that setns(CLONE_NEWNET) points to new /proc/net content even + * if old one is in dcache. + * + * FIXME /proc/net/unix is under CONFIG_UNIX which can be disabled. + */ +#undef NDEBUG +#include <assert.h> +#include <errno.h> +#include <sched.h> +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <sys/socket.h> + +static pid_t pid = -1; + +static void f(void) +{ + if (pid > 0) { + kill(pid, SIGTERM); + } +} + +int main(void) +{ + int fd[2]; + char _ = 0; + int nsfd; + + atexit(f); + + /* Check for priviledges and syscall availability straight away. */ + if (unshare(CLONE_NEWNET) == -1) { + if (errno == ENOSYS || errno == EPERM) { + return 4; + } + return 1; + } + /* Distinguisher between two otherwise empty net namespaces. */ + if (socket(AF_UNIX, SOCK_STREAM, 0) == -1) { + return 1; + } + + if (pipe(fd) == -1) { + return 1; + } + + pid = fork(); + if (pid == -1) { + return 1; + } + + if (pid == 0) { + if (unshare(CLONE_NEWNET) == -1) { + return 1; + } + + if (write(fd[1], &_, 1) != 1) { + return 1; + } + + pause(); + + return 0; + } + + if (read(fd[0], &_, 1) != 1) { + return 1; + } + + { + char buf[64]; + snprintf(buf, sizeof(buf), "/proc/%u/ns/net", pid); + nsfd = open(buf, O_RDONLY); + if (nsfd == -1) { + return 1; + } + } + + /* Reliably pin dentry into dcache. */ + (void)open("/proc/net/unix", O_RDONLY); + + if (setns(nsfd, CLONE_NEWNET) == -1) { + return 1; + } + + kill(pid, SIGTERM); + pid = 0; + + { + char buf[4096]; + ssize_t rv; + int fd; + + fd = open("/proc/net/unix", O_RDONLY); + if (fd == -1) { + return 1; + } + +#define S "Num RefCount Protocol Flags Type St Inode Path\n" + rv = read(fd, buf, sizeof(buf)); + + assert(rv == strlen(S)); + assert(memcmp(buf, S, strlen(S)) == 0); + } + + return 0; +} diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 496a9a8c773a..7e632b465ab4 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -1608,7 +1608,16 @@ TEST_F(TRACE_poke, getpid_runs_normally) #ifdef SYSCALL_NUM_RET_SHARE_REG # define EXPECT_SYSCALL_RETURN(val, action) EXPECT_EQ(-1, action) #else -# define EXPECT_SYSCALL_RETURN(val, action) EXPECT_EQ(val, action) +# define EXPECT_SYSCALL_RETURN(val, action) \ + do { \ + errno = 0; \ + if (val < 0) { \ + EXPECT_EQ(-1, action); \ + EXPECT_EQ(-(val), errno); \ + } else { \ + EXPECT_EQ(val, action); \ + } \ + } while (0) #endif /* Use PTRACE_GETREGS and PTRACE_SETREGS when available. This is useful for @@ -1647,7 +1656,7 @@ int get_syscall(struct __test_metadata *_metadata, pid_t tracee) /* Architecture-specific syscall changing routine. */ void change_syscall(struct __test_metadata *_metadata, - pid_t tracee, int syscall) + pid_t tracee, int syscall, int result) { int ret; ARCH_REGS regs; @@ -1706,7 +1715,7 @@ void change_syscall(struct __test_metadata *_metadata, #ifdef SYSCALL_NUM_RET_SHARE_REG TH_LOG("Can't modify syscall return on this architecture"); #else - regs.SYSCALL_RET = EPERM; + regs.SYSCALL_RET = result; #endif #ifdef HAVE_GETREGS @@ -1734,14 +1743,19 @@ void tracer_syscall(struct __test_metadata *_metadata, pid_t tracee, case 0x1002: /* change getpid to getppid. */ EXPECT_EQ(__NR_getpid, get_syscall(_metadata, tracee)); - change_syscall(_metadata, tracee, __NR_getppid); + change_syscall(_metadata, tracee, __NR_getppid, 0); break; case 0x1003: - /* skip gettid. */ + /* skip gettid with valid return code. */ EXPECT_EQ(__NR_gettid, get_syscall(_metadata, tracee)); - change_syscall(_metadata, tracee, -1); + change_syscall(_metadata, tracee, -1, 45000); break; case 0x1004: + /* skip openat with error. */ + EXPECT_EQ(__NR_openat, get_syscall(_metadata, tracee)); + change_syscall(_metadata, tracee, -1, -ESRCH); + break; + case 0x1005: /* do nothing (allow getppid) */ EXPECT_EQ(__NR_getppid, get_syscall(_metadata, tracee)); break; @@ -1774,9 +1788,11 @@ void tracer_ptrace(struct __test_metadata *_metadata, pid_t tracee, nr = get_syscall(_metadata, tracee); if (nr == __NR_getpid) - change_syscall(_metadata, tracee, __NR_getppid); + change_syscall(_metadata, tracee, __NR_getppid, 0); + if (nr == __NR_gettid) + change_syscall(_metadata, tracee, -1, 45000); if (nr == __NR_openat) - change_syscall(_metadata, tracee, -1); + change_syscall(_metadata, tracee, -1, -ESRCH); } FIXTURE_DATA(TRACE_syscall) { @@ -1793,8 +1809,10 @@ FIXTURE_SETUP(TRACE_syscall) BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE | 0x1002), BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_gettid, 0, 1), BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE | 0x1003), - BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getppid, 0, 1), + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_openat, 0, 1), BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE | 0x1004), + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_getppid, 0, 1), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_TRACE | 0x1005), BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), }; @@ -1842,15 +1860,26 @@ TEST_F(TRACE_syscall, ptrace_syscall_redirected) EXPECT_NE(self->mypid, syscall(__NR_getpid)); } -TEST_F(TRACE_syscall, ptrace_syscall_dropped) +TEST_F(TRACE_syscall, ptrace_syscall_errno) +{ + /* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */ + teardown_trace_fixture(_metadata, self->tracer); + self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL, + true); + + /* Tracer should skip the open syscall, resulting in ESRCH. */ + EXPECT_SYSCALL_RETURN(-ESRCH, syscall(__NR_openat)); +} + +TEST_F(TRACE_syscall, ptrace_syscall_faked) { /* Swap SECCOMP_RET_TRACE tracer for PTRACE_SYSCALL tracer. */ teardown_trace_fixture(_metadata, self->tracer); self->tracer = setup_trace_fixture(_metadata, tracer_ptrace, NULL, true); - /* Tracer should skip the open syscall, resulting in EPERM. */ - EXPECT_SYSCALL_RETURN(EPERM, syscall(__NR_openat)); + /* Tracer should skip the gettid syscall, resulting fake pid. */ + EXPECT_SYSCALL_RETURN(45000, syscall(__NR_gettid)); } TEST_F(TRACE_syscall, syscall_allowed) @@ -1883,7 +1912,21 @@ TEST_F(TRACE_syscall, syscall_redirected) EXPECT_NE(self->mypid, syscall(__NR_getpid)); } -TEST_F(TRACE_syscall, syscall_dropped) +TEST_F(TRACE_syscall, syscall_errno) +{ + long ret; + + ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0); + ASSERT_EQ(0, ret); + + ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &self->prog, 0, 0); + ASSERT_EQ(0, ret); + + /* openat has been skipped and an errno return. */ + EXPECT_SYSCALL_RETURN(-ESRCH, syscall(__NR_openat)); +} + +TEST_F(TRACE_syscall, syscall_faked) { long ret; @@ -1894,8 +1937,7 @@ TEST_F(TRACE_syscall, syscall_dropped) ASSERT_EQ(0, ret); /* gettid has been skipped and an altered return value stored. */ - EXPECT_SYSCALL_RETURN(EPERM, syscall(__NR_gettid)); - EXPECT_NE(self->mytid, syscall(__NR_gettid)); + EXPECT_SYSCALL_RETURN(45000, syscall(__NR_gettid)); } TEST_F(TRACE_syscall, skip_after_RET_TRACE) diff --git a/tools/testing/selftests/timers/Makefile b/tools/testing/selftests/timers/Makefile index c02683cfb6c9..7656c7ce79d9 100644 --- a/tools/testing/selftests/timers/Makefile +++ b/tools/testing/selftests/timers/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 CFLAGS += -O3 -Wl,-no-as-needed -Wall -LDFLAGS += -lrt -lpthread -lm +LDLIBS += -lrt -lpthread -lm # these are all "safe" tests that don't modify # system time or require escalated privileges diff --git a/tools/testing/selftests/x86/protection_keys.c b/tools/testing/selftests/x86/protection_keys.c index 460b4bdf4c1e..5d546dcdbc80 100644 --- a/tools/testing/selftests/x86/protection_keys.c +++ b/tools/testing/selftests/x86/protection_keys.c @@ -1133,6 +1133,21 @@ void test_pkey_syscalls_bad_args(int *ptr, u16 pkey) pkey_assert(err); } +void become_child(void) +{ + pid_t forkret; + + forkret = fork(); + pkey_assert(forkret >= 0); + dprintf3("[%d] fork() ret: %d\n", getpid(), forkret); + + if (!forkret) { + /* in the child */ + return; + } + exit(0); +} + /* Assumes that all pkeys other than 'pkey' are unallocated */ void test_pkey_alloc_exhaust(int *ptr, u16 pkey) { @@ -1141,7 +1156,7 @@ void test_pkey_alloc_exhaust(int *ptr, u16 pkey) int nr_allocated_pkeys = 0; int i; - for (i = 0; i < NR_PKEYS*2; i++) { + for (i = 0; i < NR_PKEYS*3; i++) { int new_pkey; dprintf1("%s() alloc loop: %d\n", __func__, i); new_pkey = alloc_pkey(); @@ -1152,21 +1167,27 @@ void test_pkey_alloc_exhaust(int *ptr, u16 pkey) if ((new_pkey == -1) && (errno == ENOSPC)) { dprintf2("%s() failed to allocate pkey after %d tries\n", __func__, nr_allocated_pkeys); - break; + } else { + /* + * Ensure the number of successes never + * exceeds the number of keys supported + * in the hardware. + */ + pkey_assert(nr_allocated_pkeys < NR_PKEYS); + allocated_pkeys[nr_allocated_pkeys++] = new_pkey; } - pkey_assert(nr_allocated_pkeys < NR_PKEYS); - allocated_pkeys[nr_allocated_pkeys++] = new_pkey; + + /* + * Make sure that allocation state is properly + * preserved across fork(). + */ + if (i == NR_PKEYS*2) + become_child(); } dprintf3("%s()::%d\n", __func__, __LINE__); /* - * ensure it did not reach the end of the loop without - * failure: - */ - pkey_assert(i < NR_PKEYS*2); - - /* * There are 16 pkeys supported in hardware. Three are * allocated by the time we get here: * 1. The default key (0) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 5ecea812cb6a..585845203db8 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -3000,8 +3000,10 @@ static int kvm_ioctl_create_device(struct kvm *kvm, if (ops->init) ops->init(dev); + kvm_get_kvm(kvm); ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR | O_CLOEXEC); if (ret < 0) { + kvm_put_kvm(kvm); mutex_lock(&kvm->lock); list_del(&dev->vm_node); mutex_unlock(&kvm->lock); @@ -3009,7 +3011,6 @@ static int kvm_ioctl_create_device(struct kvm *kvm, return ret; } - kvm_get_kvm(kvm); cd->fd = ret; return 0; } |