diff options
403 files changed, 14492 insertions, 3030 deletions
diff --git a/Documentation/admin-guide/index.rst b/Documentation/admin-guide/index.rst index 4e0c4ae44acd..5857347f6ce8 100644 --- a/Documentation/admin-guide/index.rst +++ b/Documentation/admin-guide/index.rst @@ -117,7 +117,6 @@ configure specific aspects of kernel behavior to your liking. unicode vga-softcursor video-output - wimax/index xfs .. only:: subproject and html diff --git a/Documentation/devicetree/bindings/net/dsa/hirschmann,hellcreek.yaml b/Documentation/devicetree/bindings/net/dsa/hirschmann,hellcreek.yaml new file mode 100644 index 000000000000..5592f58fa6f0 --- /dev/null +++ b/Documentation/devicetree/bindings/net/dsa/hirschmann,hellcreek.yaml @@ -0,0 +1,127 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/dsa/hirschmann,hellcreek.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Hirschmann Hellcreek TSN Switch Device Tree Bindings + +allOf: + - $ref: dsa.yaml# + +maintainers: + - Andrew Lunn <andrew@lunn.ch> + - Florian Fainelli <f.fainelli@gmail.com> + - Vivien Didelot <vivien.didelot@gmail.com> + - Kurt Kanzenbach <kurt@linutronix.de> + +description: + The Hellcreek TSN Switch IP is a 802.1Q Ethernet compliant switch. It supports + the Precision Time Protocol, Hardware Timestamping as well the Time Aware + Shaper. + +properties: + compatible: + items: + - const: hirschmann,hellcreek-de1soc-r1 + + reg: + description: + The physical base address and size of TSN and PTP memory base + minItems: 2 + maxItems: 2 + + reg-names: + items: + - const: tsn + - const: ptp + + leds: + type: object + properties: + '#address-cells': + const: 1 + '#size-cells': + const: 0 + + patternProperties: + "^led@[01]$": + type: object + description: Hellcreek leds + $ref: ../../leds/common.yaml# + + properties: + reg: + items: + - enum: [0, 1] + description: Led number + + label: true + + default-state: true + + required: + - reg + + additionalProperties: false + + additionalProperties: false + +required: + - compatible + - reg + - reg-names + - ethernet-ports + - leds + +unevaluatedProperties: false + +examples: + - | + switch0: switch@ff240000 { + compatible = "hirschmann,hellcreek-de1soc-r1"; + reg = <0xff240000 0x1000>, + <0xff250000 0x1000>; + reg-names = "tsn", "ptp"; + dsa,member = <0 0>; + + ethernet-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + label = "cpu"; + ethernet = <&gmac0>; + }; + + port@2 { + reg = <2>; + label = "lan0"; + phy-handle = <&phy1>; + }; + + port@3 { + reg = <3>; + label = "lan1"; + phy-handle = <&phy2>; + }; + }; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + label = "sync_good"; + default-state = "on"; + }; + + led@1 { + reg = <1>; + label = "is_gm"; + default-state = "off"; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/net/ftgmac100.txt b/Documentation/devicetree/bindings/net/ftgmac100.txt index f878c1103463..29234021f601 100644 --- a/Documentation/devicetree/bindings/net/ftgmac100.txt +++ b/Documentation/devicetree/bindings/net/ftgmac100.txt @@ -15,6 +15,7 @@ Required properties: - interrupts: Should contain ethernet controller interrupt Optional properties: +- phy-handle: See ethernet.txt file in the same directory. - phy-mode: See ethernet.txt file in the same directory. If the property is absent, "rgmii" is assumed. Supported values are "rgmii*" and "rmii" for aspeed parts. Other (unknown) parts will accept any value. @@ -32,6 +33,9 @@ Optional properties: - "MACCLK": The MAC IP clock - "RCLK": Clock gate for the RMII RCLK +Optional subnodes: +- mdio: See mdio.txt file in the same directory. + Example: mac0: ethernet@1e660000 { @@ -40,3 +44,24 @@ Example: interrupts = <2>; use-ncsi; }; + +Example with phy-handle: + + mac1: ethernet@1e680000 { + compatible = "aspeed,ast2500-mac", "faraday,ftgmac100"; + reg = <0x1e680000 0x180>; + interrupts = <2>; + + phy-handle = <&phy>; + phy-mode = "rgmii"; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + + phy: ethernet-phy@1 { + compatible = "ethernet-phy-ieee802.3-c22"; + reg = <1>; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml index 2735be1a8470..bc8347c6cf56 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.yaml +++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml @@ -441,6 +441,8 @@ patternProperties: description: HiDeep Inc. "^himax,.*": description: Himax Technologies, Inc. + "^hirschmann,.*": + description: Hirschmann Automation and Control GmbH "^hisilicon,.*": description: Hisilicon Limited. "^hit,.*": diff --git a/Documentation/networking/devlink/netdevsim.rst b/Documentation/networking/devlink/netdevsim.rst index 2a266b7e7b38..02c2d20dc673 100644 --- a/Documentation/networking/devlink/netdevsim.rst +++ b/Documentation/networking/devlink/netdevsim.rst @@ -46,7 +46,7 @@ Resources ========= The ``netdevsim`` driver exposes resources to control the number of FIB -entries and FIB rule entries that the driver will allow. +entries, FIB rule entries and nexthops that the driver will allow. .. code:: shell @@ -54,6 +54,7 @@ entries and FIB rule entries that the driver will allow. $ devlink resource set netdevsim/netdevsim0 path /IPv4/fib-rules size 16 $ devlink resource set netdevsim/netdevsim0 path /IPv6/fib size 64 $ devlink resource set netdevsim/netdevsim0 path /IPv6/fib-rules size 16 + $ devlink resource set netdevsim/netdevsim0 path /nexthops size 16 $ devlink dev reload netdevsim/netdevsim0 Driver-specific Traps diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index 63ef386afd0a..70c71c9206e2 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -70,6 +70,7 @@ Contents: lapb-module mac80211-injection mpls-sysctl + mptcp-sysctl multiqueue netconsole netdev-features diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 25e6673a085a..2aaf40b2d2cd 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -2642,6 +2642,37 @@ addr_scope_policy - INTEGER Default: 1 +udp_port - INTEGER + The listening port for the local UDP tunneling sock. Normally it's + using the IANA-assigned UDP port number 9899 (sctp-tunneling). + + This UDP sock is used for processing the incoming UDP-encapsulated + SCTP packets (from RFC6951), and shared by all applications in the + same net namespace. This UDP sock will be closed when the value is + set to 0. + + The value will also be used to set the src port of the UDP header + for the outgoing UDP-encapsulated SCTP packets. For the dest port, + please refer to 'encap_port' below. + + Default: 0 + +encap_port - INTEGER + The default remote UDP encapsulation port. + + This value is used to set the dest port of the UDP header for the + outgoing UDP-encapsulated SCTP packets by default. Users can also + change the value for each sock/asoc/transport by using setsockopt. + For further information, please refer to RFC6951. + + Note that when connecting to a remote server, the client should set + this to the port that the UDP tunneling sock on the peer server is + listening to and the local UDP tunneling sock on the client also + must be started. On the server, it would get the encap_port from + the incoming packet's source port. + + Default: 0 + ``/proc/sys/net/core/*`` ======================== diff --git a/Documentation/networking/kapi.rst b/Documentation/networking/kapi.rst index d198fa5eaacd..ea55f462cefa 100644 --- a/Documentation/networking/kapi.rst +++ b/Documentation/networking/kapi.rst @@ -83,27 +83,6 @@ SUN RPC subsystem .. kernel-doc:: net/sunrpc/clnt.c :export: -WiMAX ------ - -.. kernel-doc:: net/wimax/op-msg.c - :export: - -.. kernel-doc:: net/wimax/op-reset.c - :export: - -.. kernel-doc:: net/wimax/op-rfkill.c - :export: - -.. kernel-doc:: net/wimax/stack.c - :export: - -.. kernel-doc:: include/net/wimax.h - :internal: - -.. kernel-doc:: include/uapi/linux/wimax.h - :internal: - Network device support ====================== diff --git a/Documentation/networking/mptcp-sysctl.rst b/Documentation/networking/mptcp-sysctl.rst new file mode 100644 index 000000000000..6af0196c4297 --- /dev/null +++ b/Documentation/networking/mptcp-sysctl.rst @@ -0,0 +1,26 @@ +.. SPDX-License-Identifier: GPL-2.0 + +===================== +MPTCP Sysfs variables +===================== + +/proc/sys/net/mptcp/* Variables +=============================== + +enabled - INTEGER + Control whether MPTCP sockets can be created. + + MPTCP sockets can be created if the value is nonzero. This is + a per-namespace sysctl. + + Default: 1 + +add_addr_timeout - INTEGER (seconds) + Set the timeout after which an ADD_ADDR control message will be + resent to an MPTCP peer that has not acknowledged a previous + ADD_ADDR message. + + The default value matches TCP_RTO_MAX. This is a per-namespace + sysctl. + + Default: 120 diff --git a/Documentation/translations/zh_CN/admin-guide/index.rst b/Documentation/translations/zh_CN/admin-guide/index.rst index ed5ab7e37f38..48bbd3ebad48 100644 --- a/Documentation/translations/zh_CN/admin-guide/index.rst +++ b/Documentation/translations/zh_CN/admin-guide/index.rst @@ -114,7 +114,6 @@ Todolist: unicode vga-softcursor video-output - wimax/index xfs .. only:: subproject and html diff --git a/MAINTAINERS b/MAINTAINERS index cd123d0a6a2d..2a0fde12b650 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9086,16 +9086,6 @@ W: https://wireless.wiki.kernel.org/en/users/drivers/iwlwifi T: git git://git.kernel.org/pub/scm/linux/kernel/git/iwlwifi/iwlwifi.git F: drivers/net/wireless/intel/iwlwifi/ -INTEL WIRELESS WIMAX CONNECTION 2400 -M: Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com> -M: linux-wimax@intel.com -L: wimax@linuxwimax.org (subscribers-only) -S: Supported -W: http://linuxwimax.org -F: Documentation/admin-guide/wimax/i2400m.rst -F: drivers/net/wimax/i2400m/ -F: include/uapi/linux/wimax/i2400m.h - INTEL WMI SLIM BOOTLOADER (SBL) FIRMWARE UPDATE DRIVER M: Jithu Joseph <jithu.joseph@intel.com> R: Maurice Ma <maurice.ma@intel.com> @@ -12255,6 +12245,7 @@ L: mptcp@lists.01.org S: Maintained W: https://github.com/multipath-tcp/mptcp_net-next/wiki B: https://github.com/multipath-tcp/mptcp_net-next/issues +F: Documentation/networking/mptcp-sysctl.rst F: include/net/mptcp.h F: include/uapi/linux/mptcp.h F: net/mptcp/ @@ -18891,18 +18882,6 @@ S: Supported W: https://wireless.wiki.kernel.org/en/users/Drivers/wil6210 F: drivers/net/wireless/ath/wil6210/ -WIMAX STACK -M: Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com> -M: linux-wimax@intel.com -L: wimax@linuxwimax.org (subscribers-only) -S: Supported -W: http://linuxwimax.org -F: Documentation/admin-guide/wimax/wimax.rst -F: include/linux/wimax/debug.h -F: include/net/wimax.h -F: include/uapi/linux/wimax.h -F: net/wimax/ - WINBOND CIR DRIVER M: David Härdeman <david@hardeman.nu> S: Maintained diff --git a/drivers/bus/mhi/core/main.c b/drivers/bus/mhi/core/main.c index 2cff5ddff225..ba9e721d61b7 100644 --- a/drivers/bus/mhi/core/main.c +++ b/drivers/bus/mhi/core/main.c @@ -1165,6 +1165,17 @@ int mhi_queue_buf(struct mhi_device *mhi_dev, enum dma_data_direction dir, } EXPORT_SYMBOL_GPL(mhi_queue_buf); +bool mhi_queue_is_full(struct mhi_device *mhi_dev, enum dma_data_direction dir) +{ + struct mhi_controller *mhi_cntrl = mhi_dev->mhi_cntrl; + struct mhi_chan *mhi_chan = (dir == DMA_TO_DEVICE) ? + mhi_dev->ul_chan : mhi_dev->dl_chan; + struct mhi_ring *tre_ring = &mhi_chan->tre_ring; + + return mhi_is_ring_full(mhi_cntrl, tre_ring); +} +EXPORT_SYMBOL_GPL(mhi_queue_is_full); + int mhi_send_cmd(struct mhi_controller *mhi_cntrl, struct mhi_chan *mhi_chan, enum mhi_cmd_type cmd) diff --git a/drivers/crypto/caam/qi.c b/drivers/crypto/caam/qi.c index ec53528d8205..8163f5df8ebf 100644 --- a/drivers/crypto/caam/qi.c +++ b/drivers/crypto/caam/qi.c @@ -545,14 +545,10 @@ static void cgr_cb(struct qman_portal *qm, struct qman_cgr *cgr, int congested) } } -static int caam_qi_napi_schedule(struct qman_portal *p, struct caam_napi *np) +static int caam_qi_napi_schedule(struct qman_portal *p, struct caam_napi *np, + bool sched_napi) { - /* - * In case of threaded ISR, for RT kernels in_irq() does not return - * appropriate value, so use in_serving_softirq to distinguish between - * softirq and irq contexts. - */ - if (unlikely(in_irq() || !in_serving_softirq())) { + if (sched_napi) { /* Disable QMan IRQ source and invoke NAPI */ qman_p_irqsource_remove(p, QM_PIRQ_DQRI); np->p = p; @@ -564,7 +560,8 @@ static int caam_qi_napi_schedule(struct qman_portal *p, struct caam_napi *np) static enum qman_cb_dqrr_result caam_rsp_fq_dqrr_cb(struct qman_portal *p, struct qman_fq *rsp_fq, - const struct qm_dqrr_entry *dqrr) + const struct qm_dqrr_entry *dqrr, + bool sched_napi) { struct caam_napi *caam_napi = raw_cpu_ptr(&pcpu_qipriv.caam_napi); struct caam_drv_req *drv_req; @@ -573,7 +570,7 @@ static enum qman_cb_dqrr_result caam_rsp_fq_dqrr_cb(struct qman_portal *p, struct caam_drv_private *priv = dev_get_drvdata(qidev); u32 status; - if (caam_qi_napi_schedule(p, caam_napi)) + if (caam_qi_napi_schedule(p, caam_napi, sched_napi)) return qman_cb_dqrr_stop; fd = &dqrr->fd; diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index c3dbe64e628e..4ee41924cdf1 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -426,6 +426,13 @@ config VSOCKMON mostly intended for developers or support to debug vsock issues. If unsure, say N. +config MHI_NET + tristate "MHI network driver" + depends on MHI_BUS + help + This is the network driver for MHI bus. It can be used with + QCOM based WWAN modems (like SDX55). Say Y or M. + endif # NET_CORE config SUNGEM_PHY @@ -489,8 +496,6 @@ source "drivers/net/usb/Kconfig" source "drivers/net/wireless/Kconfig" -source "drivers/net/wimax/Kconfig" - source "drivers/net/wan/Kconfig" source "drivers/net/ieee802154/Kconfig" diff --git a/drivers/net/Makefile b/drivers/net/Makefile index 72e18d505d1a..36e2e41ed2aa 100644 --- a/drivers/net/Makefile +++ b/drivers/net/Makefile @@ -36,6 +36,7 @@ obj-$(CONFIG_GTP) += gtp.o obj-$(CONFIG_NLMON) += nlmon.o obj-$(CONFIG_NET_VRF) += vrf.o obj-$(CONFIG_VSOCKMON) += vsockmon.o +obj-$(CONFIG_MHI_NET) += mhi_net.o # # Networking Drivers @@ -66,7 +67,6 @@ obj-$(CONFIG_NET_SB1000) += sb1000.o obj-$(CONFIG_SUNGEM_PHY) += sungem_phy.o obj-$(CONFIG_WAN) += wan/ obj-$(CONFIG_WLAN) += wireless/ -obj-$(CONFIG_WIMAX) += wimax/ obj-$(CONFIG_IEEE802154) += ieee802154/ obj-$(CONFIG_VMXNET3) += vmxnet3/ diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 84ecbc6fa0ff..71c9677d135f 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1228,14 +1228,14 @@ static netdev_features_t bond_fix_features(struct net_device *dev, } #define BOND_VLAN_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ - NETIF_F_FRAGLIST | NETIF_F_ALL_TSO | \ + NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE | \ NETIF_F_HIGHDMA | NETIF_F_LRO) #define BOND_ENC_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ - NETIF_F_RXCSUM | NETIF_F_ALL_TSO) + NETIF_F_RXCSUM | NETIF_F_GSO_SOFTWARE) #define BOND_MPLS_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ - NETIF_F_ALL_TSO) + NETIF_F_GSO_SOFTWARE) static void bond_compute_features(struct bonding *bond) @@ -1291,8 +1291,7 @@ done: bond_dev->vlan_features = vlan_features; bond_dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL | NETIF_F_HW_VLAN_CTAG_TX | - NETIF_F_HW_VLAN_STAG_TX | - NETIF_F_GSO_UDP_L4; + NETIF_F_HW_VLAN_STAG_TX; #ifdef CONFIG_XFRM_OFFLOAD bond_dev->hw_enc_features |= xfrm_features; #endif /* CONFIG_XFRM_OFFLOAD */ @@ -4721,7 +4720,7 @@ void bond_setup(struct net_device *bond_dev) NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER; - bond_dev->hw_features |= NETIF_F_GSO_ENCAP_ALL | NETIF_F_GSO_UDP_L4; + bond_dev->hw_features |= NETIF_F_GSO_ENCAP_ALL; #ifdef CONFIG_XFRM_OFFLOAD bond_dev->hw_features |= BOND_XFRM_FEATURES; #endif /* CONFIG_XFRM_OFFLOAD */ diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig index 2451f61a38e4..f6a0488589fc 100644 --- a/drivers/net/dsa/Kconfig +++ b/drivers/net/dsa/Kconfig @@ -24,6 +24,8 @@ config NET_DSA_LOOP This enables support for a fake mock-up switch chip which exercises the DSA APIs. +source "drivers/net/dsa/hirschmann/Kconfig" + config NET_DSA_LANTIQ_GSWIP tristate "Lantiq / Intel GSWIP" depends on HAS_IOMEM && NET_DSA diff --git a/drivers/net/dsa/Makefile b/drivers/net/dsa/Makefile index 4a943ccc2ca4..a84adb140a04 100644 --- a/drivers/net/dsa/Makefile +++ b/drivers/net/dsa/Makefile @@ -18,6 +18,7 @@ obj-$(CONFIG_NET_DSA_VITESSE_VSC73XX) += vitesse-vsc73xx-core.o obj-$(CONFIG_NET_DSA_VITESSE_VSC73XX_PLATFORM) += vitesse-vsc73xx-platform.o obj-$(CONFIG_NET_DSA_VITESSE_VSC73XX_SPI) += vitesse-vsc73xx-spi.o obj-y += b53/ +obj-y += hirschmann/ obj-y += microchip/ obj-y += mv88e6xxx/ obj-y += ocelot/ diff --git a/drivers/net/dsa/hirschmann/Kconfig b/drivers/net/dsa/hirschmann/Kconfig new file mode 100644 index 000000000000..222dd35e2c9d --- /dev/null +++ b/drivers/net/dsa/hirschmann/Kconfig @@ -0,0 +1,9 @@ +# SPDX-License-Identifier: GPL-2.0 +config NET_DSA_HIRSCHMANN_HELLCREEK + tristate "Hirschmann Hellcreek TSN Switch support" + depends on HAS_IOMEM + depends on NET_DSA + depends on PTP_1588_CLOCK + select NET_DSA_TAG_HELLCREEK + help + This driver adds support for Hirschmann Hellcreek TSN switches. diff --git a/drivers/net/dsa/hirschmann/Makefile b/drivers/net/dsa/hirschmann/Makefile new file mode 100644 index 000000000000..f4075c2998b5 --- /dev/null +++ b/drivers/net/dsa/hirschmann/Makefile @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_NET_DSA_HIRSCHMANN_HELLCREEK) += hellcreek_sw.o +hellcreek_sw-objs := hellcreek.o +hellcreek_sw-objs += hellcreek_ptp.o +hellcreek_sw-objs += hellcreek_hwtstamp.o diff --git a/drivers/net/dsa/hirschmann/hellcreek.c b/drivers/net/dsa/hirschmann/hellcreek.c new file mode 100644 index 000000000000..dfa66f7260d6 --- /dev/null +++ b/drivers/net/dsa/hirschmann/hellcreek.c @@ -0,0 +1,1339 @@ +// SPDX-License-Identifier: (GPL-2.0 or MIT) +/* + * DSA driver for: + * Hirschmann Hellcreek TSN switch. + * + * Copyright (C) 2019,2020 Linutronix GmbH + * Author Kurt Kanzenbach <kurt@linutronix.de> + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/device.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <linux/of_mdio.h> +#include <linux/platform_device.h> +#include <linux/bitops.h> +#include <linux/if_bridge.h> +#include <linux/if_vlan.h> +#include <linux/etherdevice.h> +#include <linux/random.h> +#include <linux/iopoll.h> +#include <linux/mutex.h> +#include <linux/delay.h> +#include <net/dsa.h> + +#include "hellcreek.h" +#include "hellcreek_ptp.h" +#include "hellcreek_hwtstamp.h" + +static const struct hellcreek_counter hellcreek_counter[] = { + { 0x00, "RxFiltered", }, + { 0x01, "RxOctets1k", }, + { 0x02, "RxVTAG", }, + { 0x03, "RxL2BAD", }, + { 0x04, "RxOverloadDrop", }, + { 0x05, "RxUC", }, + { 0x06, "RxMC", }, + { 0x07, "RxBC", }, + { 0x08, "RxRS<64", }, + { 0x09, "RxRS64", }, + { 0x0a, "RxRS65_127", }, + { 0x0b, "RxRS128_255", }, + { 0x0c, "RxRS256_511", }, + { 0x0d, "RxRS512_1023", }, + { 0x0e, "RxRS1024_1518", }, + { 0x0f, "RxRS>1518", }, + { 0x10, "TxTailDropQueue0", }, + { 0x11, "TxTailDropQueue1", }, + { 0x12, "TxTailDropQueue2", }, + { 0x13, "TxTailDropQueue3", }, + { 0x14, "TxTailDropQueue4", }, + { 0x15, "TxTailDropQueue5", }, + { 0x16, "TxTailDropQueue6", }, + { 0x17, "TxTailDropQueue7", }, + { 0x18, "RxTrafficClass0", }, + { 0x19, "RxTrafficClass1", }, + { 0x1a, "RxTrafficClass2", }, + { 0x1b, "RxTrafficClass3", }, + { 0x1c, "RxTrafficClass4", }, + { 0x1d, "RxTrafficClass5", }, + { 0x1e, "RxTrafficClass6", }, + { 0x1f, "RxTrafficClass7", }, + { 0x21, "TxOctets1k", }, + { 0x22, "TxVTAG", }, + { 0x23, "TxL2BAD", }, + { 0x25, "TxUC", }, + { 0x26, "TxMC", }, + { 0x27, "TxBC", }, + { 0x28, "TxTS<64", }, + { 0x29, "TxTS64", }, + { 0x2a, "TxTS65_127", }, + { 0x2b, "TxTS128_255", }, + { 0x2c, "TxTS256_511", }, + { 0x2d, "TxTS512_1023", }, + { 0x2e, "TxTS1024_1518", }, + { 0x2f, "TxTS>1518", }, + { 0x30, "TxTrafficClassOverrun0", }, + { 0x31, "TxTrafficClassOverrun1", }, + { 0x32, "TxTrafficClassOverrun2", }, + { 0x33, "TxTrafficClassOverrun3", }, + { 0x34, "TxTrafficClassOverrun4", }, + { 0x35, "TxTrafficClassOverrun5", }, + { 0x36, "TxTrafficClassOverrun6", }, + { 0x37, "TxTrafficClassOverrun7", }, + { 0x38, "TxTrafficClass0", }, + { 0x39, "TxTrafficClass1", }, + { 0x3a, "TxTrafficClass2", }, + { 0x3b, "TxTrafficClass3", }, + { 0x3c, "TxTrafficClass4", }, + { 0x3d, "TxTrafficClass5", }, + { 0x3e, "TxTrafficClass6", }, + { 0x3f, "TxTrafficClass7", }, +}; + +static u16 hellcreek_read(struct hellcreek *hellcreek, unsigned int offset) +{ + return readw(hellcreek->base + offset); +} + +static u16 hellcreek_read_ctrl(struct hellcreek *hellcreek) +{ + return readw(hellcreek->base + HR_CTRL_C); +} + +static u16 hellcreek_read_stat(struct hellcreek *hellcreek) +{ + return readw(hellcreek->base + HR_SWSTAT); +} + +static void hellcreek_write(struct hellcreek *hellcreek, u16 data, + unsigned int offset) +{ + writew(data, hellcreek->base + offset); +} + +static void hellcreek_select_port(struct hellcreek *hellcreek, int port) +{ + u16 val = port << HR_PSEL_PTWSEL_SHIFT; + + hellcreek_write(hellcreek, val, HR_PSEL); +} + +static void hellcreek_select_prio(struct hellcreek *hellcreek, int prio) +{ + u16 val = prio << HR_PSEL_PRTCWSEL_SHIFT; + + hellcreek_write(hellcreek, val, HR_PSEL); +} + +static void hellcreek_select_counter(struct hellcreek *hellcreek, int counter) +{ + u16 val = counter << HR_CSEL_SHIFT; + + hellcreek_write(hellcreek, val, HR_CSEL); + + /* Data sheet states to wait at least 20 internal clock cycles */ + ndelay(200); +} + +static void hellcreek_select_vlan(struct hellcreek *hellcreek, int vid, + bool pvid) +{ + u16 val = 0; + + /* Set pvid bit first */ + if (pvid) + val |= HR_VIDCFG_PVID; + hellcreek_write(hellcreek, val, HR_VIDCFG); + + /* Set vlan */ + val |= vid << HR_VIDCFG_VID_SHIFT; + hellcreek_write(hellcreek, val, HR_VIDCFG); +} + +static int hellcreek_wait_until_ready(struct hellcreek *hellcreek) +{ + u16 val; + + /* Wait up to 1ms, although 3 us should be enough */ + return readx_poll_timeout(hellcreek_read_ctrl, hellcreek, + val, val & HR_CTRL_C_READY, + 3, 1000); +} + +static int hellcreek_wait_until_transitioned(struct hellcreek *hellcreek) +{ + u16 val; + + return readx_poll_timeout_atomic(hellcreek_read_ctrl, hellcreek, + val, !(val & HR_CTRL_C_TRANSITION), + 1, 1000); +} + +static int hellcreek_wait_fdb_ready(struct hellcreek *hellcreek) +{ + u16 val; + + return readx_poll_timeout_atomic(hellcreek_read_stat, hellcreek, + val, !(val & HR_SWSTAT_BUSY), + 1, 1000); +} + +static int hellcreek_detect(struct hellcreek *hellcreek) +{ + u16 id, rel_low, rel_high, date_low, date_high, tgd_ver; + u8 tgd_maj, tgd_min; + u32 rel, date; + + id = hellcreek_read(hellcreek, HR_MODID_C); + rel_low = hellcreek_read(hellcreek, HR_REL_L_C); + rel_high = hellcreek_read(hellcreek, HR_REL_H_C); + date_low = hellcreek_read(hellcreek, HR_BLD_L_C); + date_high = hellcreek_read(hellcreek, HR_BLD_H_C); + tgd_ver = hellcreek_read(hellcreek, TR_TGDVER); + + if (id != hellcreek->pdata->module_id) + return -ENODEV; + + rel = rel_low | (rel_high << 16); + date = date_low | (date_high << 16); + tgd_maj = (tgd_ver & TR_TGDVER_REV_MAJ_MASK) >> TR_TGDVER_REV_MAJ_SHIFT; + tgd_min = (tgd_ver & TR_TGDVER_REV_MIN_MASK) >> TR_TGDVER_REV_MIN_SHIFT; + + dev_info(hellcreek->dev, "Module ID=%02x Release=%04x Date=%04x TGD Version=%02x.%02x\n", + id, rel, date, tgd_maj, tgd_min); + + return 0; +} + +static void hellcreek_feature_detect(struct hellcreek *hellcreek) +{ + u16 features; + + features = hellcreek_read(hellcreek, HR_FEABITS0); + + /* Currently we only detect the size of the FDB table */ + hellcreek->fdb_entries = ((features & HR_FEABITS0_FDBBINS_MASK) >> + HR_FEABITS0_FDBBINS_SHIFT) * 32; + + dev_info(hellcreek->dev, "Feature detect: FDB entries=%zu\n", + hellcreek->fdb_entries); +} + +static enum dsa_tag_protocol hellcreek_get_tag_protocol(struct dsa_switch *ds, + int port, + enum dsa_tag_protocol mp) +{ + return DSA_TAG_PROTO_HELLCREEK; +} + +static int hellcreek_port_enable(struct dsa_switch *ds, int port, + struct phy_device *phy) +{ + struct hellcreek *hellcreek = ds->priv; + struct hellcreek_port *hellcreek_port; + u16 val; + + hellcreek_port = &hellcreek->ports[port]; + + dev_dbg(hellcreek->dev, "Enable port %d\n", port); + + mutex_lock(&hellcreek->reg_lock); + + hellcreek_select_port(hellcreek, port); + val = hellcreek_port->ptcfg; + val |= HR_PTCFG_ADMIN_EN; + hellcreek_write(hellcreek, val, HR_PTCFG); + hellcreek_port->ptcfg = val; + + mutex_unlock(&hellcreek->reg_lock); + + return 0; +} + +static void hellcreek_port_disable(struct dsa_switch *ds, int port) +{ + struct hellcreek *hellcreek = ds->priv; + struct hellcreek_port *hellcreek_port; + u16 val; + + hellcreek_port = &hellcreek->ports[port]; + + dev_dbg(hellcreek->dev, "Disable port %d\n", port); + + mutex_lock(&hellcreek->reg_lock); + + hellcreek_select_port(hellcreek, port); + val = hellcreek_port->ptcfg; + val &= ~HR_PTCFG_ADMIN_EN; + hellcreek_write(hellcreek, val, HR_PTCFG); + hellcreek_port->ptcfg = val; + + mutex_unlock(&hellcreek->reg_lock); +} + +static void hellcreek_get_strings(struct dsa_switch *ds, int port, + u32 stringset, uint8_t *data) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(hellcreek_counter); ++i) { + const struct hellcreek_counter *counter = &hellcreek_counter[i]; + + strlcpy(data + i * ETH_GSTRING_LEN, + counter->name, ETH_GSTRING_LEN); + } +} + +static int hellcreek_get_sset_count(struct dsa_switch *ds, int port, int sset) +{ + if (sset != ETH_SS_STATS) + return 0; + + return ARRAY_SIZE(hellcreek_counter); +} + +static void hellcreek_get_ethtool_stats(struct dsa_switch *ds, int port, + uint64_t *data) +{ + struct hellcreek *hellcreek = ds->priv; + struct hellcreek_port *hellcreek_port; + int i; + + hellcreek_port = &hellcreek->ports[port]; + + for (i = 0; i < ARRAY_SIZE(hellcreek_counter); ++i) { + const struct hellcreek_counter *counter = &hellcreek_counter[i]; + u8 offset = counter->offset + port * 64; + u16 high, low; + u64 value = 0; + + mutex_lock(&hellcreek->reg_lock); + + hellcreek_select_counter(hellcreek, offset); + + /* The registers are locked internally by selecting the + * counter. So low and high can be read without reading high + * again. + */ + high = hellcreek_read(hellcreek, HR_CRDH); + low = hellcreek_read(hellcreek, HR_CRDL); + value = (high << 16) | low; + + hellcreek_port->counter_values[i] += value; + data[i] = hellcreek_port->counter_values[i]; + + mutex_unlock(&hellcreek->reg_lock); + } +} + +static u16 hellcreek_private_vid(int port) +{ + return VLAN_N_VID - port + 1; +} + +static int hellcreek_vlan_prepare(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_vlan *vlan) +{ + struct hellcreek *hellcreek = ds->priv; + int i; + + dev_dbg(hellcreek->dev, "VLAN prepare for port %d\n", port); + + /* Restriction: Make sure that nobody uses the "private" VLANs. These + * VLANs are internally used by the driver to ensure port + * separation. Thus, they cannot be used by someone else. + */ + for (i = 0; i < hellcreek->pdata->num_ports; ++i) { + const u16 restricted_vid = hellcreek_private_vid(i); + u16 vid; + + if (!dsa_is_user_port(ds, i)) + continue; + + for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) + if (vid == restricted_vid) + return -EBUSY; + } + + return 0; +} + +static void hellcreek_select_vlan_params(struct hellcreek *hellcreek, int port, + int *shift, int *mask) +{ + switch (port) { + case 0: + *shift = HR_VIDMBRCFG_P0MBR_SHIFT; + *mask = HR_VIDMBRCFG_P0MBR_MASK; + break; + case 1: + *shift = HR_VIDMBRCFG_P1MBR_SHIFT; + *mask = HR_VIDMBRCFG_P1MBR_MASK; + break; + case 2: + *shift = HR_VIDMBRCFG_P2MBR_SHIFT; + *mask = HR_VIDMBRCFG_P2MBR_MASK; + break; + case 3: + *shift = HR_VIDMBRCFG_P3MBR_SHIFT; + *mask = HR_VIDMBRCFG_P3MBR_MASK; + break; + default: + *shift = *mask = 0; + dev_err(hellcreek->dev, "Unknown port %d selected!\n", port); + } +} + +static void hellcreek_apply_vlan(struct hellcreek *hellcreek, int port, u16 vid, + bool pvid, bool untagged) +{ + int shift, mask; + u16 val; + + dev_dbg(hellcreek->dev, "Apply VLAN: port=%d vid=%u pvid=%d untagged=%d", + port, vid, pvid, untagged); + + mutex_lock(&hellcreek->reg_lock); + + hellcreek_select_port(hellcreek, port); + hellcreek_select_vlan(hellcreek, vid, pvid); + + /* Setup port vlan membership */ + hellcreek_select_vlan_params(hellcreek, port, &shift, &mask); + val = hellcreek->vidmbrcfg[vid]; + val &= ~mask; + if (untagged) + val |= HELLCREEK_VLAN_UNTAGGED_MEMBER << shift; + else + val |= HELLCREEK_VLAN_TAGGED_MEMBER << shift; + + hellcreek_write(hellcreek, val, HR_VIDMBRCFG); + hellcreek->vidmbrcfg[vid] = val; + + mutex_unlock(&hellcreek->reg_lock); +} + +static void hellcreek_unapply_vlan(struct hellcreek *hellcreek, int port, + u16 vid) +{ + int shift, mask; + u16 val; + + dev_dbg(hellcreek->dev, "Unapply VLAN: port=%d vid=%u\n", port, vid); + + mutex_lock(&hellcreek->reg_lock); + + hellcreek_select_vlan(hellcreek, vid, 0); + + /* Setup port vlan membership */ + hellcreek_select_vlan_params(hellcreek, port, &shift, &mask); + val = hellcreek->vidmbrcfg[vid]; + val &= ~mask; + val |= HELLCREEK_VLAN_NO_MEMBER << shift; + + hellcreek_write(hellcreek, val, HR_VIDMBRCFG); + hellcreek->vidmbrcfg[vid] = val; + + mutex_unlock(&hellcreek->reg_lock); +} + +static void hellcreek_vlan_add(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_vlan *vlan) +{ + bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED; + bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID; + struct hellcreek *hellcreek = ds->priv; + u16 vid; + + dev_dbg(hellcreek->dev, "Add VLANs (%d -- %d) on port %d, %s, %s\n", + vlan->vid_begin, vlan->vid_end, port, + untagged ? "untagged" : "tagged", + pvid ? "PVID" : "no PVID"); + + for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) + hellcreek_apply_vlan(hellcreek, port, vid, pvid, untagged); +} + +static int hellcreek_vlan_del(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_vlan *vlan) +{ + struct hellcreek *hellcreek = ds->priv; + u16 vid; + + dev_dbg(hellcreek->dev, "Remove VLANs (%d -- %d) on port %d\n", + vlan->vid_begin, vlan->vid_end, port); + + for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) + hellcreek_unapply_vlan(hellcreek, port, vid); + + return 0; +} + +static void hellcreek_port_stp_state_set(struct dsa_switch *ds, int port, + u8 state) +{ + struct hellcreek *hellcreek = ds->priv; + struct hellcreek_port *hellcreek_port; + const char *new_state; + u16 val; + + mutex_lock(&hellcreek->reg_lock); + + hellcreek_port = &hellcreek->ports[port]; + val = hellcreek_port->ptcfg; + + switch (state) { + case BR_STATE_DISABLED: + new_state = "DISABLED"; + val |= HR_PTCFG_BLOCKED; + val &= ~HR_PTCFG_LEARNING_EN; + break; + case BR_STATE_BLOCKING: + new_state = "BLOCKING"; + val |= HR_PTCFG_BLOCKED; + val &= ~HR_PTCFG_LEARNING_EN; + break; + case BR_STATE_LISTENING: + new_state = "LISTENING"; + val |= HR_PTCFG_BLOCKED; + val &= ~HR_PTCFG_LEARNING_EN; + break; + case BR_STATE_LEARNING: + new_state = "LEARNING"; + val |= HR_PTCFG_BLOCKED; + val |= HR_PTCFG_LEARNING_EN; + break; + case BR_STATE_FORWARDING: + new_state = "FORWARDING"; + val &= ~HR_PTCFG_BLOCKED; + val |= HR_PTCFG_LEARNING_EN; + break; + default: + new_state = "UNKNOWN"; + } + + hellcreek_select_port(hellcreek, port); + hellcreek_write(hellcreek, val, HR_PTCFG); + hellcreek_port->ptcfg = val; + + mutex_unlock(&hellcreek->reg_lock); + + dev_dbg(hellcreek->dev, "Configured STP state for port %d: %s\n", + port, new_state); +} + +static void hellcreek_setup_ingressflt(struct hellcreek *hellcreek, int port, + bool enable) +{ + struct hellcreek_port *hellcreek_port = &hellcreek->ports[port]; + u16 ptcfg; + + mutex_lock(&hellcreek->reg_lock); + + ptcfg = hellcreek_port->ptcfg; + + if (enable) + ptcfg |= HR_PTCFG_INGRESSFLT; + else + ptcfg &= ~HR_PTCFG_INGRESSFLT; + + hellcreek_select_port(hellcreek, port); + hellcreek_write(hellcreek, ptcfg, HR_PTCFG); + hellcreek_port->ptcfg = ptcfg; + + mutex_unlock(&hellcreek->reg_lock); +} + +static void hellcreek_setup_vlan_awareness(struct hellcreek *hellcreek, + bool enable) +{ + u16 swcfg; + + mutex_lock(&hellcreek->reg_lock); + + swcfg = hellcreek->swcfg; + + if (enable) + swcfg |= HR_SWCFG_VLAN_UNAWARE; + else + swcfg &= ~HR_SWCFG_VLAN_UNAWARE; + + hellcreek_write(hellcreek, swcfg, HR_SWCFG); + + mutex_unlock(&hellcreek->reg_lock); +} + +/* Default setup for DSA: VLAN <X>: CPU and Port <X> egress untagged. */ +static void hellcreek_setup_vlan_membership(struct dsa_switch *ds, int port, + bool enabled) +{ + const u16 vid = hellcreek_private_vid(port); + int upstream = dsa_upstream_port(ds, port); + struct hellcreek *hellcreek = ds->priv; + + /* Apply vid to port as egress untagged and port vlan id */ + if (enabled) + hellcreek_apply_vlan(hellcreek, port, vid, true, true); + else + hellcreek_unapply_vlan(hellcreek, port, vid); + + /* Apply vid to cpu port as well */ + if (enabled) + hellcreek_apply_vlan(hellcreek, upstream, vid, false, true); + else + hellcreek_unapply_vlan(hellcreek, upstream, vid); +} + +static int hellcreek_port_bridge_join(struct dsa_switch *ds, int port, + struct net_device *br) +{ + struct hellcreek *hellcreek = ds->priv; + + dev_dbg(hellcreek->dev, "Port %d joins a bridge\n", port); + + /* When joining a vlan_filtering bridge, keep the switch VLAN aware */ + if (!ds->vlan_filtering) + hellcreek_setup_vlan_awareness(hellcreek, false); + + /* Drop private vlans */ + hellcreek_setup_vlan_membership(ds, port, false); + + return 0; +} + +static void hellcreek_port_bridge_leave(struct dsa_switch *ds, int port, + struct net_device *br) +{ + struct hellcreek *hellcreek = ds->priv; + + dev_dbg(hellcreek->dev, "Port %d leaves a bridge\n", port); + + /* Enable VLAN awareness */ + hellcreek_setup_vlan_awareness(hellcreek, true); + + /* Enable private vlans */ + hellcreek_setup_vlan_membership(ds, port, true); +} + +static int __hellcreek_fdb_add(struct hellcreek *hellcreek, + const struct hellcreek_fdb_entry *entry) +{ + u16 meta = 0; + + dev_dbg(hellcreek->dev, "Add static FDB entry: MAC=%pM, MASK=0x%02x, " + "OBT=%d, REPRIO_EN=%d, PRIO=%d\n", entry->mac, entry->portmask, + entry->is_obt, entry->reprio_en, entry->reprio_tc); + + /* Add mac address */ + hellcreek_write(hellcreek, entry->mac[1] | (entry->mac[0] << 8), HR_FDBWDH); + hellcreek_write(hellcreek, entry->mac[3] | (entry->mac[2] << 8), HR_FDBWDM); + hellcreek_write(hellcreek, entry->mac[5] | (entry->mac[4] << 8), HR_FDBWDL); + + /* Meta data */ + meta |= entry->portmask << HR_FDBWRM0_PORTMASK_SHIFT; + if (entry->is_obt) + meta |= HR_FDBWRM0_OBT; + if (entry->reprio_en) { + meta |= HR_FDBWRM0_REPRIO_EN; + meta |= entry->reprio_tc << HR_FDBWRM0_REPRIO_TC_SHIFT; + } + hellcreek_write(hellcreek, meta, HR_FDBWRM0); + + /* Commit */ + hellcreek_write(hellcreek, 0x00, HR_FDBWRCMD); + + /* Wait until done */ + return hellcreek_wait_fdb_ready(hellcreek); +} + +static int __hellcreek_fdb_del(struct hellcreek *hellcreek, + const struct hellcreek_fdb_entry *entry) +{ + dev_dbg(hellcreek->dev, "Delete FDB entry: MAC=%pM!\n", entry->mac); + + /* Delete by matching idx */ + hellcreek_write(hellcreek, entry->idx | HR_FDBWRCMD_FDBDEL, HR_FDBWRCMD); + + /* Wait until done */ + return hellcreek_wait_fdb_ready(hellcreek); +} + +/* Retrieve the index of a FDB entry by mac address. Currently we search through + * the complete table in hardware. If that's too slow, we might have to cache + * the complete FDB table in software. + */ +static int hellcreek_fdb_get(struct hellcreek *hellcreek, + const unsigned char *dest, + struct hellcreek_fdb_entry *entry) +{ + size_t i; + + /* Set read pointer to zero: The read of HR_FDBMAX (read-only register) + * should reset the internal pointer. But, that doesn't work. The vendor + * suggested a subsequent write as workaround. Same for HR_FDBRDH below. + */ + hellcreek_read(hellcreek, HR_FDBMAX); + hellcreek_write(hellcreek, 0x00, HR_FDBMAX); + + /* We have to read the complete table, because the switch/driver might + * enter new entries anywhere. + */ + for (i = 0; i < hellcreek->fdb_entries; ++i) { + unsigned char addr[ETH_ALEN]; + u16 meta, mac; + + meta = hellcreek_read(hellcreek, HR_FDBMDRD); + mac = hellcreek_read(hellcreek, HR_FDBRDL); + addr[5] = mac & 0xff; + addr[4] = (mac & 0xff00) >> 8; + mac = hellcreek_read(hellcreek, HR_FDBRDM); + addr[3] = mac & 0xff; + addr[2] = (mac & 0xff00) >> 8; + mac = hellcreek_read(hellcreek, HR_FDBRDH); + addr[1] = mac & 0xff; + addr[0] = (mac & 0xff00) >> 8; + + /* Force next entry */ + hellcreek_write(hellcreek, 0x00, HR_FDBRDH); + + if (memcmp(addr, dest, ETH_ALEN)) + continue; + + /* Match found */ + entry->idx = i; + entry->portmask = (meta & HR_FDBMDRD_PORTMASK_MASK) >> + HR_FDBMDRD_PORTMASK_SHIFT; + entry->age = (meta & HR_FDBMDRD_AGE_MASK) >> + HR_FDBMDRD_AGE_SHIFT; + entry->is_obt = !!(meta & HR_FDBMDRD_OBT); + entry->pass_blocked = !!(meta & HR_FDBMDRD_PASS_BLOCKED); + entry->is_static = !!(meta & HR_FDBMDRD_STATIC); + entry->reprio_tc = (meta & HR_FDBMDRD_REPRIO_TC_MASK) >> + HR_FDBMDRD_REPRIO_TC_SHIFT; + entry->reprio_en = !!(meta & HR_FDBMDRD_REPRIO_EN); + memcpy(entry->mac, addr, sizeof(addr)); + + return 0; + } + + return -ENOENT; +} + +static int hellcreek_fdb_add(struct dsa_switch *ds, int port, + const unsigned char *addr, u16 vid) +{ + struct hellcreek_fdb_entry entry = { 0 }; + struct hellcreek *hellcreek = ds->priv; + int ret; + + dev_dbg(hellcreek->dev, "Add FDB entry for MAC=%pM\n", addr); + + mutex_lock(&hellcreek->reg_lock); + + ret = hellcreek_fdb_get(hellcreek, addr, &entry); + if (ret) { + /* Not found */ + memcpy(entry.mac, addr, sizeof(entry.mac)); + entry.portmask = BIT(port); + + ret = __hellcreek_fdb_add(hellcreek, &entry); + if (ret) { + dev_err(hellcreek->dev, "Failed to add FDB entry!\n"); + goto out; + } + } else { + /* Found */ + ret = __hellcreek_fdb_del(hellcreek, &entry); + if (ret) { + dev_err(hellcreek->dev, "Failed to delete FDB entry!\n"); + goto out; + } + + entry.portmask |= BIT(port); + + ret = __hellcreek_fdb_add(hellcreek, &entry); + if (ret) { + dev_err(hellcreek->dev, "Failed to add FDB entry!\n"); + goto out; + } + } + +out: + mutex_unlock(&hellcreek->reg_lock); + + return ret; +} + +static int hellcreek_fdb_del(struct dsa_switch *ds, int port, + const unsigned char *addr, u16 vid) +{ + struct hellcreek_fdb_entry entry = { 0 }; + struct hellcreek *hellcreek = ds->priv; + int ret; + + dev_dbg(hellcreek->dev, "Delete FDB entry for MAC=%pM\n", addr); + + mutex_lock(&hellcreek->reg_lock); + + ret = hellcreek_fdb_get(hellcreek, addr, &entry); + if (ret) { + /* Not found */ + dev_err(hellcreek->dev, "FDB entry for deletion not found!\n"); + } else { + /* Found */ + ret = __hellcreek_fdb_del(hellcreek, &entry); + if (ret) { + dev_err(hellcreek->dev, "Failed to delete FDB entry!\n"); + goto out; + } + + entry.portmask &= ~BIT(port); + + if (entry.portmask != 0x00) { + ret = __hellcreek_fdb_add(hellcreek, &entry); + if (ret) { + dev_err(hellcreek->dev, "Failed to add FDB entry!\n"); + goto out; + } + } + } + +out: + mutex_unlock(&hellcreek->reg_lock); + + return ret; +} + +static int hellcreek_fdb_dump(struct dsa_switch *ds, int port, + dsa_fdb_dump_cb_t *cb, void *data) +{ + struct hellcreek *hellcreek = ds->priv; + u16 entries; + size_t i; + + mutex_lock(&hellcreek->reg_lock); + + /* Set read pointer to zero: The read of HR_FDBMAX (read-only register) + * should reset the internal pointer. But, that doesn't work. The vendor + * suggested a subsequent write as workaround. Same for HR_FDBRDH below. + */ + entries = hellcreek_read(hellcreek, HR_FDBMAX); + hellcreek_write(hellcreek, 0x00, HR_FDBMAX); + + dev_dbg(hellcreek->dev, "FDB dump for port %d, entries=%d!\n", port, entries); + + /* Read table */ + for (i = 0; i < hellcreek->fdb_entries; ++i) { + unsigned char null_addr[ETH_ALEN] = { 0 }; + struct hellcreek_fdb_entry entry = { 0 }; + u16 meta, mac; + + meta = hellcreek_read(hellcreek, HR_FDBMDRD); + mac = hellcreek_read(hellcreek, HR_FDBRDL); + entry.mac[5] = mac & 0xff; + entry.mac[4] = (mac & 0xff00) >> 8; + mac = hellcreek_read(hellcreek, HR_FDBRDM); + entry.mac[3] = mac & 0xff; + entry.mac[2] = (mac & 0xff00) >> 8; + mac = hellcreek_read(hellcreek, HR_FDBRDH); + entry.mac[1] = mac & 0xff; + entry.mac[0] = (mac & 0xff00) >> 8; + + /* Force next entry */ + hellcreek_write(hellcreek, 0x00, HR_FDBRDH); + + /* Check valid */ + if (!memcmp(entry.mac, null_addr, ETH_ALEN)) + continue; + + entry.portmask = (meta & HR_FDBMDRD_PORTMASK_MASK) >> + HR_FDBMDRD_PORTMASK_SHIFT; + entry.is_static = !!(meta & HR_FDBMDRD_STATIC); + + /* Check port mask */ + if (!(entry.portmask & BIT(port))) + continue; + + cb(entry.mac, 0, entry.is_static, data); + } + + mutex_unlock(&hellcreek->reg_lock); + + return 0; +} + +static int hellcreek_vlan_filtering(struct dsa_switch *ds, int port, + bool vlan_filtering, + struct switchdev_trans *trans) +{ + struct hellcreek *hellcreek = ds->priv; + + if (switchdev_trans_ph_prepare(trans)) + return 0; + + dev_dbg(hellcreek->dev, "%s VLAN filtering on port %d\n", + vlan_filtering ? "Enable" : "Disable", port); + + /* Configure port to drop packages with not known vids */ + hellcreek_setup_ingressflt(hellcreek, port, vlan_filtering); + + /* Enable VLAN awareness on the switch. This save due to + * ds->vlan_filtering_is_global. + */ + hellcreek_setup_vlan_awareness(hellcreek, vlan_filtering); + + return 0; +} + +static int hellcreek_enable_ip_core(struct hellcreek *hellcreek) +{ + int ret; + u16 val; + + mutex_lock(&hellcreek->reg_lock); + + val = hellcreek_read(hellcreek, HR_CTRL_C); + val |= HR_CTRL_C_ENABLE; + hellcreek_write(hellcreek, val, HR_CTRL_C); + ret = hellcreek_wait_until_transitioned(hellcreek); + + mutex_unlock(&hellcreek->reg_lock); + + return ret; +} + +static void hellcreek_setup_cpu_and_tunnel_port(struct hellcreek *hellcreek) +{ + struct hellcreek_port *tunnel_port = &hellcreek->ports[TUNNEL_PORT]; + struct hellcreek_port *cpu_port = &hellcreek->ports[CPU_PORT]; + u16 ptcfg = 0; + + ptcfg |= HR_PTCFG_LEARNING_EN | HR_PTCFG_ADMIN_EN; + + mutex_lock(&hellcreek->reg_lock); + + hellcreek_select_port(hellcreek, CPU_PORT); + hellcreek_write(hellcreek, ptcfg, HR_PTCFG); + + hellcreek_select_port(hellcreek, TUNNEL_PORT); + hellcreek_write(hellcreek, ptcfg, HR_PTCFG); + + cpu_port->ptcfg = ptcfg; + tunnel_port->ptcfg = ptcfg; + + mutex_unlock(&hellcreek->reg_lock); +} + +static void hellcreek_setup_tc_identity_mapping(struct hellcreek *hellcreek) +{ + int i; + + /* The switch has multiple egress queues per port. The queue is selected + * via the PCP field in the VLAN header. The switch internally deals + * with traffic classes instead of PCP values and this mapping is + * configurable. + * + * The default mapping is (PCP - TC): + * 7 - 7 + * 6 - 6 + * 5 - 5 + * 4 - 4 + * 3 - 3 + * 2 - 1 + * 1 - 0 + * 0 - 2 + * + * The default should be an identity mapping. + */ + + for (i = 0; i < 8; ++i) { + mutex_lock(&hellcreek->reg_lock); + + hellcreek_select_prio(hellcreek, i); + hellcreek_write(hellcreek, + i << HR_PRTCCFG_PCP_TC_MAP_SHIFT, + HR_PRTCCFG); + + mutex_unlock(&hellcreek->reg_lock); + } +} + +static int hellcreek_setup_fdb(struct hellcreek *hellcreek) +{ + static struct hellcreek_fdb_entry ptp = { + /* MAC: 01-1B-19-00-00-00 */ + .mac = { 0x01, 0x1b, 0x19, 0x00, 0x00, 0x00 }, + .portmask = 0x03, /* Management ports */ + .age = 0, + .is_obt = 0, + .pass_blocked = 0, + .is_static = 1, + .reprio_tc = 6, /* TC: 6 as per IEEE 802.1AS */ + .reprio_en = 1, + }; + static struct hellcreek_fdb_entry p2p = { + /* MAC: 01-80-C2-00-00-0E */ + .mac = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x0e }, + .portmask = 0x03, /* Management ports */ + .age = 0, + .is_obt = 0, + .pass_blocked = 0, + .is_static = 1, + .reprio_tc = 6, /* TC: 6 as per IEEE 802.1AS */ + .reprio_en = 1, + }; + int ret; + + mutex_lock(&hellcreek->reg_lock); + ret = __hellcreek_fdb_add(hellcreek, &ptp); + if (ret) + goto out; + ret = __hellcreek_fdb_add(hellcreek, &p2p); +out: + mutex_unlock(&hellcreek->reg_lock); + + return ret; +} + +static int hellcreek_setup(struct dsa_switch *ds) +{ + struct hellcreek *hellcreek = ds->priv; + u16 swcfg = 0; + int ret, i; + + dev_dbg(hellcreek->dev, "Set up the switch\n"); + + /* Let's go */ + ret = hellcreek_enable_ip_core(hellcreek); + if (ret) { + dev_err(hellcreek->dev, "Failed to enable IP core!\n"); + return ret; + } + + /* Enable CPU/Tunnel ports */ + hellcreek_setup_cpu_and_tunnel_port(hellcreek); + + /* Switch config: Keep defaults, enable FDB aging and learning and tag + * each frame from/to cpu port for DSA tagging. Also enable the length + * aware shaping mode. This eliminates the need for Qbv guard bands. + */ + swcfg |= HR_SWCFG_FDBAGE_EN | + HR_SWCFG_FDBLRN_EN | + HR_SWCFG_ALWAYS_OBT | + (HR_SWCFG_LAS_ON << HR_SWCFG_LAS_MODE_SHIFT); + hellcreek->swcfg = swcfg; + hellcreek_write(hellcreek, swcfg, HR_SWCFG); + + /* Initial vlan membership to reflect port separation */ + for (i = 0; i < ds->num_ports; ++i) { + if (!dsa_is_user_port(ds, i)) + continue; + + hellcreek_setup_vlan_membership(ds, i, true); + } + + /* Configure PCP <-> TC mapping */ + hellcreek_setup_tc_identity_mapping(hellcreek); + + /* Allow VLAN configurations while not filtering which is the default + * for new DSA drivers. + */ + ds->configure_vlan_while_not_filtering = true; + + /* The VLAN awareness is a global switch setting. Therefore, mixed vlan + * filtering setups are not supported. + */ + ds->vlan_filtering_is_global = true; + + /* Intercept _all_ PTP multicast traffic */ + ret = hellcreek_setup_fdb(hellcreek); + if (ret) { + dev_err(hellcreek->dev, + "Failed to insert static PTP FDB entries\n"); + return ret; + } + + return 0; +} + +static void hellcreek_phylink_validate(struct dsa_switch *ds, int port, + unsigned long *supported, + struct phylink_link_state *state) +{ + __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; + struct hellcreek *hellcreek = ds->priv; + + dev_dbg(hellcreek->dev, "Phylink validate for port %d\n", port); + + /* The MAC settings are a hardware configuration option and cannot be + * changed at run time or by strapping. Therefore the attached PHYs + * should be programmed to only advertise settings which are supported + * by the hardware. + */ + if (hellcreek->pdata->is_100_mbits) + phylink_set(mask, 100baseT_Full); + else + phylink_set(mask, 1000baseT_Full); + + bitmap_and(supported, supported, mask, + __ETHTOOL_LINK_MODE_MASK_NBITS); + bitmap_and(state->advertising, state->advertising, mask, + __ETHTOOL_LINK_MODE_MASK_NBITS); +} + +static int +hellcreek_port_prechangeupper(struct dsa_switch *ds, int port, + struct netdev_notifier_changeupper_info *info) +{ + struct hellcreek *hellcreek = ds->priv; + bool used = true; + int ret = -EBUSY; + u16 vid; + int i; + + dev_dbg(hellcreek->dev, "Pre change upper for port %d\n", port); + + /* + * Deny VLAN devices on top of lan ports with the same VLAN ids, because + * it breaks the port separation due to the private VLANs. Example: + * + * lan0.100 *and* lan1.100 cannot be used in parallel. However, lan0.99 + * and lan1.100 works. + */ + + if (!is_vlan_dev(info->upper_dev)) + return 0; + + vid = vlan_dev_vlan_id(info->upper_dev); + + /* For all ports, check bitmaps */ + mutex_lock(&hellcreek->vlan_lock); + for (i = 0; i < hellcreek->pdata->num_ports; ++i) { + if (!dsa_is_user_port(ds, i)) + continue; + + if (port == i) + continue; + + used = used && test_bit(vid, hellcreek->ports[i].vlan_dev_bitmap); + } + + if (used) + goto out; + + /* Update bitmap */ + set_bit(vid, hellcreek->ports[port].vlan_dev_bitmap); + + ret = 0; + +out: + mutex_unlock(&hellcreek->vlan_lock); + + return ret; +} + +static const struct dsa_switch_ops hellcreek_ds_ops = { + .get_ethtool_stats = hellcreek_get_ethtool_stats, + .get_sset_count = hellcreek_get_sset_count, + .get_strings = hellcreek_get_strings, + .get_tag_protocol = hellcreek_get_tag_protocol, + .get_ts_info = hellcreek_get_ts_info, + .phylink_validate = hellcreek_phylink_validate, + .port_bridge_join = hellcreek_port_bridge_join, + .port_bridge_leave = hellcreek_port_bridge_leave, + .port_disable = hellcreek_port_disable, + .port_enable = hellcreek_port_enable, + .port_fdb_add = hellcreek_fdb_add, + .port_fdb_del = hellcreek_fdb_del, + .port_fdb_dump = hellcreek_fdb_dump, + .port_hwtstamp_set = hellcreek_port_hwtstamp_set, + .port_hwtstamp_get = hellcreek_port_hwtstamp_get, + .port_prechangeupper = hellcreek_port_prechangeupper, + .port_rxtstamp = hellcreek_port_rxtstamp, + .port_stp_state_set = hellcreek_port_stp_state_set, + .port_txtstamp = hellcreek_port_txtstamp, + .port_vlan_add = hellcreek_vlan_add, + .port_vlan_del = hellcreek_vlan_del, + .port_vlan_filtering = hellcreek_vlan_filtering, + .port_vlan_prepare = hellcreek_vlan_prepare, + .setup = hellcreek_setup, +}; + +static int hellcreek_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct hellcreek *hellcreek; + struct resource *res; + int ret, i; + + hellcreek = devm_kzalloc(dev, sizeof(*hellcreek), GFP_KERNEL); + if (!hellcreek) + return -ENOMEM; + + hellcreek->vidmbrcfg = devm_kcalloc(dev, VLAN_N_VID, + sizeof(*hellcreek->vidmbrcfg), + GFP_KERNEL); + if (!hellcreek->vidmbrcfg) + return -ENOMEM; + + hellcreek->pdata = of_device_get_match_data(dev); + + hellcreek->ports = devm_kcalloc(dev, hellcreek->pdata->num_ports, + sizeof(*hellcreek->ports), + GFP_KERNEL); + if (!hellcreek->ports) + return -ENOMEM; + + for (i = 0; i < hellcreek->pdata->num_ports; ++i) { + struct hellcreek_port *port = &hellcreek->ports[i]; + + port->counter_values = + devm_kcalloc(dev, + ARRAY_SIZE(hellcreek_counter), + sizeof(*port->counter_values), + GFP_KERNEL); + if (!port->counter_values) + return -ENOMEM; + + port->vlan_dev_bitmap = + devm_kcalloc(dev, + BITS_TO_LONGS(VLAN_N_VID), + sizeof(unsigned long), + GFP_KERNEL); + if (!port->vlan_dev_bitmap) + return -ENOMEM; + + port->hellcreek = hellcreek; + port->port = i; + } + + mutex_init(&hellcreek->reg_lock); + mutex_init(&hellcreek->vlan_lock); + mutex_init(&hellcreek->ptp_lock); + + hellcreek->dev = dev; + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "tsn"); + if (!res) { + dev_err(dev, "No memory region provided!\n"); + return -ENODEV; + } + + hellcreek->base = devm_ioremap_resource(dev, res); + if (IS_ERR(hellcreek->base)) { + dev_err(dev, "No memory available!\n"); + return PTR_ERR(hellcreek->base); + } + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "ptp"); + if (!res) { + dev_err(dev, "No PTP memory region provided!\n"); + return -ENODEV; + } + + hellcreek->ptp_base = devm_ioremap_resource(dev, res); + if (IS_ERR(hellcreek->ptp_base)) { + dev_err(dev, "No memory available!\n"); + return PTR_ERR(hellcreek->ptp_base); + } + + ret = hellcreek_detect(hellcreek); + if (ret) { + dev_err(dev, "No (known) chip found!\n"); + return ret; + } + + ret = hellcreek_wait_until_ready(hellcreek); + if (ret) { + dev_err(dev, "Switch didn't become ready!\n"); + return ret; + } + + hellcreek_feature_detect(hellcreek); + + hellcreek->ds = devm_kzalloc(dev, sizeof(*hellcreek->ds), GFP_KERNEL); + if (!hellcreek->ds) + return -ENOMEM; + + hellcreek->ds->dev = dev; + hellcreek->ds->priv = hellcreek; + hellcreek->ds->ops = &hellcreek_ds_ops; + hellcreek->ds->num_ports = hellcreek->pdata->num_ports; + hellcreek->ds->num_tx_queues = HELLCREEK_NUM_EGRESS_QUEUES; + + ret = dsa_register_switch(hellcreek->ds); + if (ret) { + dev_err(dev, "Unable to register switch\n"); + return ret; + } + + ret = hellcreek_ptp_setup(hellcreek); + if (ret) { + dev_err(dev, "Failed to setup PTP!\n"); + goto err_ptp_setup; + } + + ret = hellcreek_hwtstamp_setup(hellcreek); + if (ret) { + dev_err(dev, "Failed to setup hardware timestamping!\n"); + goto err_tstamp_setup; + } + + platform_set_drvdata(pdev, hellcreek); + + return 0; + +err_tstamp_setup: + hellcreek_ptp_free(hellcreek); +err_ptp_setup: + dsa_unregister_switch(hellcreek->ds); + + return ret; +} + +static int hellcreek_remove(struct platform_device *pdev) +{ + struct hellcreek *hellcreek = platform_get_drvdata(pdev); + + hellcreek_hwtstamp_free(hellcreek); + hellcreek_ptp_free(hellcreek); + dsa_unregister_switch(hellcreek->ds); + platform_set_drvdata(pdev, NULL); + + return 0; +} + +static const struct hellcreek_platform_data de1soc_r1_pdata = { + .num_ports = 4, + .is_100_mbits = 1, + .qbv_support = 1, + .qbv_on_cpu_port = 1, + .qbu_support = 0, + .module_id = 0x4c30, +}; + +static const struct of_device_id hellcreek_of_match[] = { + { + .compatible = "hirschmann,hellcreek-de1soc-r1", + .data = &de1soc_r1_pdata, + }, + { /* sentinel */ }, +}; +MODULE_DEVICE_TABLE(of, hellcreek_of_match); + +static struct platform_driver hellcreek_driver = { + .probe = hellcreek_probe, + .remove = hellcreek_remove, + .driver = { + .name = "hellcreek", + .of_match_table = hellcreek_of_match, + }, +}; +module_platform_driver(hellcreek_driver); + +MODULE_AUTHOR("Kurt Kanzenbach <kurt@linutronix.de>"); +MODULE_DESCRIPTION("Hirschmann Hellcreek driver"); +MODULE_LICENSE("Dual MIT/GPL"); diff --git a/drivers/net/dsa/hirschmann/hellcreek.h b/drivers/net/dsa/hirschmann/hellcreek.h new file mode 100644 index 000000000000..e81781ebc31c --- /dev/null +++ b/drivers/net/dsa/hirschmann/hellcreek.h @@ -0,0 +1,286 @@ +/* SPDX-License-Identifier: (GPL-2.0 or MIT) */ +/* + * DSA driver for: + * Hirschmann Hellcreek TSN switch. + * + * Copyright (C) 2019,2020 Linutronix GmbH + * Author Kurt Kanzenbach <kurt@linutronix.de> + */ + +#ifndef _HELLCREEK_H_ +#define _HELLCREEK_H_ + +#include <linux/bitmap.h> +#include <linux/bitops.h> +#include <linux/device.h> +#include <linux/kernel.h> +#include <linux/mutex.h> +#include <linux/workqueue.h> +#include <linux/leds.h> +#include <linux/platform_data/hirschmann-hellcreek.h> +#include <linux/ptp_clock_kernel.h> +#include <linux/timecounter.h> +#include <net/dsa.h> + +/* Ports: + * - 0: CPU + * - 1: Tunnel + * - 2: TSN front port 1 + * - 3: TSN front port 2 + * - ... + */ +#define CPU_PORT 0 +#define TUNNEL_PORT 1 + +#define HELLCREEK_VLAN_NO_MEMBER 0x0 +#define HELLCREEK_VLAN_UNTAGGED_MEMBER 0x1 +#define HELLCREEK_VLAN_TAGGED_MEMBER 0x3 +#define HELLCREEK_NUM_EGRESS_QUEUES 8 + +/* Register definitions */ +#define HR_MODID_C (0 * 2) +#define HR_REL_L_C (1 * 2) +#define HR_REL_H_C (2 * 2) +#define HR_BLD_L_C (3 * 2) +#define HR_BLD_H_C (4 * 2) +#define HR_CTRL_C (5 * 2) +#define HR_CTRL_C_READY BIT(14) +#define HR_CTRL_C_TRANSITION BIT(13) +#define HR_CTRL_C_ENABLE BIT(0) + +#define HR_PSEL (0xa6 * 2) +#define HR_PSEL_PTWSEL_SHIFT 4 +#define HR_PSEL_PTWSEL_MASK GENMASK(5, 4) +#define HR_PSEL_PRTCWSEL_SHIFT 0 +#define HR_PSEL_PRTCWSEL_MASK GENMASK(2, 0) + +#define HR_PTCFG (0xa7 * 2) +#define HR_PTCFG_MLIMIT_EN BIT(13) +#define HR_PTCFG_UMC_FLT BIT(10) +#define HR_PTCFG_UUC_FLT BIT(9) +#define HR_PTCFG_UNTRUST BIT(8) +#define HR_PTCFG_TAG_REQUIRED BIT(7) +#define HR_PTCFG_PPRIO_SHIFT 4 +#define HR_PTCFG_PPRIO_MASK GENMASK(6, 4) +#define HR_PTCFG_INGRESSFLT BIT(3) +#define HR_PTCFG_BLOCKED BIT(2) +#define HR_PTCFG_LEARNING_EN BIT(1) +#define HR_PTCFG_ADMIN_EN BIT(0) + +#define HR_PRTCCFG (0xa8 * 2) +#define HR_PRTCCFG_PCP_TC_MAP_SHIFT 0 +#define HR_PRTCCFG_PCP_TC_MAP_MASK GENMASK(2, 0) + +#define HR_CSEL (0x8d * 2) +#define HR_CSEL_SHIFT 0 +#define HR_CSEL_MASK GENMASK(7, 0) +#define HR_CRDL (0x8e * 2) +#define HR_CRDH (0x8f * 2) + +#define HR_SWTRC_CFG (0x90 * 2) +#define HR_SWTRC0 (0x91 * 2) +#define HR_SWTRC1 (0x92 * 2) +#define HR_PFREE (0x93 * 2) +#define HR_MFREE (0x94 * 2) + +#define HR_FDBAGE (0x97 * 2) +#define HR_FDBMAX (0x98 * 2) +#define HR_FDBRDL (0x99 * 2) +#define HR_FDBRDM (0x9a * 2) +#define HR_FDBRDH (0x9b * 2) + +#define HR_FDBMDRD (0x9c * 2) +#define HR_FDBMDRD_PORTMASK_SHIFT 0 +#define HR_FDBMDRD_PORTMASK_MASK GENMASK(3, 0) +#define HR_FDBMDRD_AGE_SHIFT 4 +#define HR_FDBMDRD_AGE_MASK GENMASK(7, 4) +#define HR_FDBMDRD_OBT BIT(8) +#define HR_FDBMDRD_PASS_BLOCKED BIT(9) +#define HR_FDBMDRD_STATIC BIT(11) +#define HR_FDBMDRD_REPRIO_TC_SHIFT 12 +#define HR_FDBMDRD_REPRIO_TC_MASK GENMASK(14, 12) +#define HR_FDBMDRD_REPRIO_EN BIT(15) + +#define HR_FDBWDL (0x9d * 2) +#define HR_FDBWDM (0x9e * 2) +#define HR_FDBWDH (0x9f * 2) +#define HR_FDBWRM0 (0xa0 * 2) +#define HR_FDBWRM0_PORTMASK_SHIFT 0 +#define HR_FDBWRM0_PORTMASK_MASK GENMASK(3, 0) +#define HR_FDBWRM0_OBT BIT(8) +#define HR_FDBWRM0_PASS_BLOCKED BIT(9) +#define HR_FDBWRM0_REPRIO_TC_SHIFT 12 +#define HR_FDBWRM0_REPRIO_TC_MASK GENMASK(14, 12) +#define HR_FDBWRM0_REPRIO_EN BIT(15) +#define HR_FDBWRM1 (0xa1 * 2) + +#define HR_FDBWRCMD (0xa2 * 2) +#define HR_FDBWRCMD_FDBDEL BIT(9) + +#define HR_SWCFG (0xa3 * 2) +#define HR_SWCFG_GM_STATEMD BIT(15) +#define HR_SWCFG_LAS_MODE_SHIFT 12 +#define HR_SWCFG_LAS_MODE_MASK GENMASK(13, 12) +#define HR_SWCFG_LAS_OFF (0x00) +#define HR_SWCFG_LAS_ON (0x01) +#define HR_SWCFG_LAS_STATIC (0x10) +#define HR_SWCFG_CT_EN BIT(11) +#define HR_SWCFG_VLAN_UNAWARE BIT(10) +#define HR_SWCFG_ALWAYS_OBT BIT(9) +#define HR_SWCFG_FDBAGE_EN BIT(5) +#define HR_SWCFG_FDBLRN_EN BIT(4) + +#define HR_SWSTAT (0xa4 * 2) +#define HR_SWSTAT_FAIL BIT(4) +#define HR_SWSTAT_BUSY BIT(0) + +#define HR_SWCMD (0xa5 * 2) +#define HW_SWCMD_FLUSH BIT(0) + +#define HR_VIDCFG (0xaa * 2) +#define HR_VIDCFG_VID_SHIFT 0 +#define HR_VIDCFG_VID_MASK GENMASK(11, 0) +#define HR_VIDCFG_PVID BIT(12) + +#define HR_VIDMBRCFG (0xab * 2) +#define HR_VIDMBRCFG_P0MBR_SHIFT 0 +#define HR_VIDMBRCFG_P0MBR_MASK GENMASK(1, 0) +#define HR_VIDMBRCFG_P1MBR_SHIFT 2 +#define HR_VIDMBRCFG_P1MBR_MASK GENMASK(3, 2) +#define HR_VIDMBRCFG_P2MBR_SHIFT 4 +#define HR_VIDMBRCFG_P2MBR_MASK GENMASK(5, 4) +#define HR_VIDMBRCFG_P3MBR_SHIFT 6 +#define HR_VIDMBRCFG_P3MBR_MASK GENMASK(7, 6) + +#define HR_FEABITS0 (0xac * 2) +#define HR_FEABITS0_FDBBINS_SHIFT 4 +#define HR_FEABITS0_FDBBINS_MASK GENMASK(7, 4) +#define HR_FEABITS0_PCNT_SHIFT 8 +#define HR_FEABITS0_PCNT_MASK GENMASK(11, 8) +#define HR_FEABITS0_MCNT_SHIFT 12 +#define HR_FEABITS0_MCNT_MASK GENMASK(15, 12) + +#define TR_QTRACK (0xb1 * 2) +#define TR_TGDVER (0xb3 * 2) +#define TR_TGDVER_REV_MIN_MASK GENMASK(7, 0) +#define TR_TGDVER_REV_MIN_SHIFT 0 +#define TR_TGDVER_REV_MAJ_MASK GENMASK(15, 8) +#define TR_TGDVER_REV_MAJ_SHIFT 8 +#define TR_TGDSEL (0xb4 * 2) +#define TR_TGDSEL_TDGSEL_MASK GENMASK(1, 0) +#define TR_TGDSEL_TDGSEL_SHIFT 0 +#define TR_TGDCTRL (0xb5 * 2) +#define TR_TGDCTRL_GATE_EN BIT(0) +#define TR_TGDCTRL_CYC_SNAP BIT(4) +#define TR_TGDCTRL_SNAP_EST BIT(5) +#define TR_TGDCTRL_ADMINGATESTATES_MASK GENMASK(15, 8) +#define TR_TGDCTRL_ADMINGATESTATES_SHIFT 8 +#define TR_TGDSTAT0 (0xb6 * 2) +#define TR_TGDSTAT1 (0xb7 * 2) +#define TR_ESTWRL (0xb8 * 2) +#define TR_ESTWRH (0xb9 * 2) +#define TR_ESTCMD (0xba * 2) +#define TR_ESTCMD_ESTSEC_MASK GENMASK(2, 0) +#define TR_ESTCMD_ESTSEC_SHIFT 0 +#define TR_ESTCMD_ESTARM BIT(4) +#define TR_ESTCMD_ESTSWCFG BIT(5) +#define TR_EETWRL (0xbb * 2) +#define TR_EETWRH (0xbc * 2) +#define TR_EETCMD (0xbd * 2) +#define TR_EETCMD_EETSEC_MASK GEMASK(2, 0) +#define TR_EETCMD_EETSEC_SHIFT 0 +#define TR_EETCMD_EETARM BIT(4) +#define TR_CTWRL (0xbe * 2) +#define TR_CTWRH (0xbf * 2) +#define TR_LCNSL (0xc1 * 2) +#define TR_LCNSH (0xc2 * 2) +#define TR_LCS (0xc3 * 2) +#define TR_GCLDAT (0xc4 * 2) +#define TR_GCLDAT_GCLWRGATES_MASK GENMASK(7, 0) +#define TR_GCLDAT_GCLWRGATES_SHIFT 0 +#define TR_GCLDAT_GCLWRLAST BIT(8) +#define TR_GCLDAT_GCLOVRI BIT(9) +#define TR_GCLTIL (0xc5 * 2) +#define TR_GCLTIH (0xc6 * 2) +#define TR_GCLCMD (0xc7 * 2) +#define TR_GCLCMD_GCLWRADR_MASK GENMASK(7, 0) +#define TR_GCLCMD_GCLWRADR_SHIFT 0 +#define TR_GCLCMD_INIT_GATE_STATES_MASK GENMASK(15, 8) +#define TR_GCLCMD_INIT_GATE_STATES_SHIFT 8 + +struct hellcreek_counter { + u8 offset; + const char *name; +}; + +struct hellcreek; + +/* State flags for hellcreek_port_hwtstamp::state */ +enum { + HELLCREEK_HWTSTAMP_ENABLED, + HELLCREEK_HWTSTAMP_TX_IN_PROGRESS, +}; + +/* A structure to hold hardware timestamping information per port */ +struct hellcreek_port_hwtstamp { + /* Timestamping state */ + unsigned long state; + + /* Resources for receive timestamping */ + struct sk_buff_head rx_queue; /* For synchronization messages */ + + /* Resources for transmit timestamping */ + unsigned long tx_tstamp_start; + struct sk_buff *tx_skb; + + /* Current timestamp configuration */ + struct hwtstamp_config tstamp_config; +}; + +struct hellcreek_port { + struct hellcreek *hellcreek; + unsigned long *vlan_dev_bitmap; + int port; + u16 ptcfg; /* ptcfg shadow */ + u64 *counter_values; + + /* Per-port timestamping resources */ + struct hellcreek_port_hwtstamp port_hwtstamp; +}; + +struct hellcreek_fdb_entry { + size_t idx; + unsigned char mac[ETH_ALEN]; + u8 portmask; + u8 age; + u8 is_obt; + u8 pass_blocked; + u8 is_static; + u8 reprio_tc; + u8 reprio_en; +}; + +struct hellcreek { + const struct hellcreek_platform_data *pdata; + struct device *dev; + struct dsa_switch *ds; + struct ptp_clock *ptp_clock; + struct ptp_clock_info ptp_clock_info; + struct hellcreek_port *ports; + struct delayed_work overflow_work; + struct led_classdev led_is_gm; + struct led_classdev led_sync_good; + struct mutex reg_lock; /* Switch IP register lock */ + struct mutex vlan_lock; /* VLAN bitmaps lock */ + struct mutex ptp_lock; /* PTP IP register lock */ + void __iomem *base; + void __iomem *ptp_base; + u16 swcfg; /* swcfg shadow */ + u8 *vidmbrcfg; /* vidmbrcfg shadow */ + u64 seconds; /* PTP seconds */ + u64 last_ts; /* Used for overflow detection */ + u16 status_out; /* ptp.status_out shadow */ + size_t fdb_entries; +}; + +#endif /* _HELLCREEK_H_ */ diff --git a/drivers/net/dsa/hirschmann/hellcreek_hwtstamp.c b/drivers/net/dsa/hirschmann/hellcreek_hwtstamp.c new file mode 100644 index 000000000000..69dd9a2e8bb6 --- /dev/null +++ b/drivers/net/dsa/hirschmann/hellcreek_hwtstamp.c @@ -0,0 +1,479 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * DSA driver for: + * Hirschmann Hellcreek TSN switch. + * + * Copyright (C) 2019,2020 Hochschule Offenburg + * Copyright (C) 2019,2020 Linutronix GmbH + * Authors: Kamil Alkhouri <kamil.alkhouri@hs-offenburg.de> + * Kurt Kanzenbach <kurt@linutronix.de> + */ + +#include <linux/ptp_classify.h> + +#include "hellcreek.h" +#include "hellcreek_hwtstamp.h" +#include "hellcreek_ptp.h" + +int hellcreek_get_ts_info(struct dsa_switch *ds, int port, + struct ethtool_ts_info *info) +{ + struct hellcreek *hellcreek = ds->priv; + + info->phc_index = hellcreek->ptp_clock ? + ptp_clock_index(hellcreek->ptp_clock) : -1; + info->so_timestamping = SOF_TIMESTAMPING_TX_HARDWARE | + SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE; + + /* enabled tx timestamping */ + info->tx_types = BIT(HWTSTAMP_TX_ON); + + /* L2 & L4 PTPv2 event rx messages are timestamped */ + info->rx_filters = BIT(HWTSTAMP_FILTER_PTP_V2_EVENT); + + return 0; +} + +/* Enabling/disabling TX and RX HW timestamping for different PTP messages is + * not available in the switch. Thus, this function only serves as a check if + * the user requested what is actually available or not + */ +static int hellcreek_set_hwtstamp_config(struct hellcreek *hellcreek, int port, + struct hwtstamp_config *config) +{ + struct hellcreek_port_hwtstamp *ps = + &hellcreek->ports[port].port_hwtstamp; + bool tx_tstamp_enable = false; + bool rx_tstamp_enable = false; + + /* Interaction with the timestamp hardware is prevented here. It is + * enabled when this config function ends successfully + */ + clear_bit_unlock(HELLCREEK_HWTSTAMP_ENABLED, &ps->state); + + /* Reserved for future extensions */ + if (config->flags) + return -EINVAL; + + switch (config->tx_type) { + case HWTSTAMP_TX_ON: + tx_tstamp_enable = true; + break; + + /* TX HW timestamping can't be disabled on the switch */ + case HWTSTAMP_TX_OFF: + config->tx_type = HWTSTAMP_TX_ON; + break; + + default: + return -ERANGE; + } + + switch (config->rx_filter) { + /* RX HW timestamping can't be disabled on the switch */ + case HWTSTAMP_FILTER_NONE: + config->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; + break; + + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + config->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; + rx_tstamp_enable = true; + break; + + /* RX HW timestamping can't be enabled for all messages on the switch */ + case HWTSTAMP_FILTER_ALL: + config->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; + break; + + default: + return -ERANGE; + } + + if (!tx_tstamp_enable) + return -ERANGE; + + if (!rx_tstamp_enable) + return -ERANGE; + + /* If this point is reached, then the requested hwtstamp config is + * compatible with the hwtstamp offered by the switch. Therefore, + * enable the interaction with the HW timestamping + */ + set_bit(HELLCREEK_HWTSTAMP_ENABLED, &ps->state); + + return 0; +} + +int hellcreek_port_hwtstamp_set(struct dsa_switch *ds, int port, + struct ifreq *ifr) +{ + struct hellcreek *hellcreek = ds->priv; + struct hellcreek_port_hwtstamp *ps; + struct hwtstamp_config config; + int err; + + ps = &hellcreek->ports[port].port_hwtstamp; + + if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) + return -EFAULT; + + err = hellcreek_set_hwtstamp_config(hellcreek, port, &config); + if (err) + return err; + + /* Save the chosen configuration to be returned later */ + memcpy(&ps->tstamp_config, &config, sizeof(config)); + + return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? + -EFAULT : 0; +} + +int hellcreek_port_hwtstamp_get(struct dsa_switch *ds, int port, + struct ifreq *ifr) +{ + struct hellcreek *hellcreek = ds->priv; + struct hellcreek_port_hwtstamp *ps; + struct hwtstamp_config *config; + + ps = &hellcreek->ports[port].port_hwtstamp; + config = &ps->tstamp_config; + + return copy_to_user(ifr->ifr_data, config, sizeof(*config)) ? + -EFAULT : 0; +} + +/* Returns a pointer to the PTP header if the caller should time stamp, or NULL + * if the caller should not. + */ +static struct ptp_header *hellcreek_should_tstamp(struct hellcreek *hellcreek, + int port, struct sk_buff *skb, + unsigned int type) +{ + struct hellcreek_port_hwtstamp *ps = + &hellcreek->ports[port].port_hwtstamp; + struct ptp_header *hdr; + + hdr = ptp_parse_header(skb, type); + if (!hdr) + return NULL; + + if (!test_bit(HELLCREEK_HWTSTAMP_ENABLED, &ps->state)) + return NULL; + + return hdr; +} + +static u64 hellcreek_get_reserved_field(const struct ptp_header *hdr) +{ + return be32_to_cpu(hdr->reserved2); +} + +static void hellcreek_clear_reserved_field(struct ptp_header *hdr) +{ + hdr->reserved2 = 0; +} + +static int hellcreek_ptp_hwtstamp_available(struct hellcreek *hellcreek, + unsigned int ts_reg) +{ + u16 status; + + status = hellcreek_ptp_read(hellcreek, ts_reg); + + if (status & PR_TS_STATUS_TS_LOST) + dev_err(hellcreek->dev, + "Tx time stamp lost! This should never happen!\n"); + + /* If hwtstamp is not available, this means the previous hwtstamp was + * successfully read, and the one we need is not yet available + */ + return (status & PR_TS_STATUS_TS_AVAIL) ? 1 : 0; +} + +/* Get nanoseconds timestamp from timestamping unit */ +static u64 hellcreek_ptp_hwtstamp_read(struct hellcreek *hellcreek, + unsigned int ts_reg) +{ + u16 nsl, nsh; + + nsh = hellcreek_ptp_read(hellcreek, ts_reg); + nsh = hellcreek_ptp_read(hellcreek, ts_reg); + nsh = hellcreek_ptp_read(hellcreek, ts_reg); + nsh = hellcreek_ptp_read(hellcreek, ts_reg); + nsl = hellcreek_ptp_read(hellcreek, ts_reg); + + return (u64)nsl | ((u64)nsh << 16); +} + +static int hellcreek_txtstamp_work(struct hellcreek *hellcreek, + struct hellcreek_port_hwtstamp *ps, int port) +{ + struct skb_shared_hwtstamps shhwtstamps; + unsigned int status_reg, data_reg; + struct sk_buff *tmp_skb; + int ts_status; + u64 ns = 0; + + if (!ps->tx_skb) + return 0; + + switch (port) { + case 2: + status_reg = PR_TS_TX_P1_STATUS_C; + data_reg = PR_TS_TX_P1_DATA_C; + break; + case 3: + status_reg = PR_TS_TX_P2_STATUS_C; + data_reg = PR_TS_TX_P2_DATA_C; + break; + default: + dev_err(hellcreek->dev, "Wrong port for timestamping!\n"); + return 0; + } + + ts_status = hellcreek_ptp_hwtstamp_available(hellcreek, status_reg); + + /* Not available yet? */ + if (ts_status == 0) { + /* Check whether the operation of reading the tx timestamp has + * exceeded its allowed period + */ + if (time_is_before_jiffies(ps->tx_tstamp_start + + TX_TSTAMP_TIMEOUT)) { + dev_err(hellcreek->dev, + "Timeout while waiting for Tx timestamp!\n"); + goto free_and_clear_skb; + } + + /* The timestamp should be available quickly, while getting it + * in high priority. Restart the work + */ + return 1; + } + + mutex_lock(&hellcreek->ptp_lock); + ns = hellcreek_ptp_hwtstamp_read(hellcreek, data_reg); + ns += hellcreek_ptp_gettime_seconds(hellcreek, ns); + mutex_unlock(&hellcreek->ptp_lock); + + /* Now we have the timestamp in nanoseconds, store it in the correct + * structure in order to send it to the user + */ + memset(&shhwtstamps, 0, sizeof(shhwtstamps)); + shhwtstamps.hwtstamp = ns_to_ktime(ns); + + tmp_skb = ps->tx_skb; + ps->tx_skb = NULL; + + /* skb_complete_tx_timestamp() frees up the client to make another + * timestampable transmit. We have to be ready for it by clearing the + * ps->tx_skb "flag" beforehand + */ + clear_bit_unlock(HELLCREEK_HWTSTAMP_TX_IN_PROGRESS, &ps->state); + + /* Deliver a clone of the original outgoing tx_skb with tx hwtstamp */ + skb_complete_tx_timestamp(tmp_skb, &shhwtstamps); + + return 0; + +free_and_clear_skb: + dev_kfree_skb_any(ps->tx_skb); + ps->tx_skb = NULL; + clear_bit_unlock(HELLCREEK_HWTSTAMP_TX_IN_PROGRESS, &ps->state); + + return 0; +} + +static void hellcreek_get_rxts(struct hellcreek *hellcreek, + struct hellcreek_port_hwtstamp *ps, + struct sk_buff *skb, struct sk_buff_head *rxq, + int port) +{ + struct skb_shared_hwtstamps *shwt; + struct sk_buff_head received; + unsigned long flags; + + /* The latched timestamp belongs to one of the received frames. */ + __skb_queue_head_init(&received); + + /* Lock & disable interrupts */ + spin_lock_irqsave(&rxq->lock, flags); + + /* Add the reception queue "rxq" to the "received" queue an reintialize + * "rxq". From now on, we deal with "received" not with "rxq" + */ + skb_queue_splice_tail_init(rxq, &received); + + spin_unlock_irqrestore(&rxq->lock, flags); + + for (; skb; skb = __skb_dequeue(&received)) { + struct ptp_header *hdr; + unsigned int type; + u64 ns; + + /* Get nanoseconds from ptp packet */ + type = SKB_PTP_TYPE(skb); + hdr = ptp_parse_header(skb, type); + ns = hellcreek_get_reserved_field(hdr); + hellcreek_clear_reserved_field(hdr); + + /* Add seconds part */ + mutex_lock(&hellcreek->ptp_lock); + ns += hellcreek_ptp_gettime_seconds(hellcreek, ns); + mutex_unlock(&hellcreek->ptp_lock); + + /* Save time stamp */ + shwt = skb_hwtstamps(skb); + memset(shwt, 0, sizeof(*shwt)); + shwt->hwtstamp = ns_to_ktime(ns); + netif_rx_ni(skb); + } +} + +static void hellcreek_rxtstamp_work(struct hellcreek *hellcreek, + struct hellcreek_port_hwtstamp *ps, + int port) +{ + struct sk_buff *skb; + + skb = skb_dequeue(&ps->rx_queue); + if (skb) + hellcreek_get_rxts(hellcreek, ps, skb, &ps->rx_queue, port); +} + +long hellcreek_hwtstamp_work(struct ptp_clock_info *ptp) +{ + struct hellcreek *hellcreek = ptp_to_hellcreek(ptp); + struct dsa_switch *ds = hellcreek->ds; + int i, restart = 0; + + for (i = 0; i < ds->num_ports; i++) { + struct hellcreek_port_hwtstamp *ps; + + if (!dsa_is_user_port(ds, i)) + continue; + + ps = &hellcreek->ports[i].port_hwtstamp; + + if (test_bit(HELLCREEK_HWTSTAMP_TX_IN_PROGRESS, &ps->state)) + restart |= hellcreek_txtstamp_work(hellcreek, ps, i); + + hellcreek_rxtstamp_work(hellcreek, ps, i); + } + + return restart ? 1 : -1; +} + +bool hellcreek_port_txtstamp(struct dsa_switch *ds, int port, + struct sk_buff *clone, unsigned int type) +{ + struct hellcreek *hellcreek = ds->priv; + struct hellcreek_port_hwtstamp *ps; + struct ptp_header *hdr; + + ps = &hellcreek->ports[port].port_hwtstamp; + + /* Check if the driver is expected to do HW timestamping */ + if (!(skb_shinfo(clone)->tx_flags & SKBTX_HW_TSTAMP)) + return false; + + /* Make sure the message is a PTP message that needs to be timestamped + * and the interaction with the HW timestamping is enabled. If not, stop + * here + */ + hdr = hellcreek_should_tstamp(hellcreek, port, clone, type); + if (!hdr) + return false; + + if (test_and_set_bit_lock(HELLCREEK_HWTSTAMP_TX_IN_PROGRESS, + &ps->state)) + return false; + + ps->tx_skb = clone; + + /* store the number of ticks occurred since system start-up till this + * moment + */ + ps->tx_tstamp_start = jiffies; + + ptp_schedule_worker(hellcreek->ptp_clock, 0); + + return true; +} + +bool hellcreek_port_rxtstamp(struct dsa_switch *ds, int port, + struct sk_buff *skb, unsigned int type) +{ + struct hellcreek *hellcreek = ds->priv; + struct hellcreek_port_hwtstamp *ps; + struct ptp_header *hdr; + + ps = &hellcreek->ports[port].port_hwtstamp; + + /* This check only fails if the user did not initialize hardware + * timestamping beforehand. + */ + if (ps->tstamp_config.rx_filter != HWTSTAMP_FILTER_PTP_V2_EVENT) + return false; + + /* Make sure the message is a PTP message that needs to be timestamped + * and the interaction with the HW timestamping is enabled. If not, stop + * here + */ + hdr = hellcreek_should_tstamp(hellcreek, port, skb, type); + if (!hdr) + return false; + + SKB_PTP_TYPE(skb) = type; + + skb_queue_tail(&ps->rx_queue, skb); + + ptp_schedule_worker(hellcreek->ptp_clock, 0); + + return true; +} + +static void hellcreek_hwtstamp_port_setup(struct hellcreek *hellcreek, int port) +{ + struct hellcreek_port_hwtstamp *ps = + &hellcreek->ports[port].port_hwtstamp; + + skb_queue_head_init(&ps->rx_queue); +} + +int hellcreek_hwtstamp_setup(struct hellcreek *hellcreek) +{ + struct dsa_switch *ds = hellcreek->ds; + int i; + + /* Initialize timestamping ports. */ + for (i = 0; i < ds->num_ports; ++i) { + if (!dsa_is_user_port(ds, i)) + continue; + + hellcreek_hwtstamp_port_setup(hellcreek, i); + } + + /* Select the synchronized clock as the source timekeeper for the + * timestamps and enable inline timestamping. + */ + hellcreek_ptp_write(hellcreek, PR_SETTINGS_C_TS_SRC_TK_MASK | + PR_SETTINGS_C_RES3TS, + PR_SETTINGS_C); + + return 0; +} + +void hellcreek_hwtstamp_free(struct hellcreek *hellcreek) +{ + /* Nothing todo */ +} diff --git a/drivers/net/dsa/hirschmann/hellcreek_hwtstamp.h b/drivers/net/dsa/hirschmann/hellcreek_hwtstamp.h new file mode 100644 index 000000000000..c0745ffa1ebb --- /dev/null +++ b/drivers/net/dsa/hirschmann/hellcreek_hwtstamp.h @@ -0,0 +1,58 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */ +/* + * DSA driver for: + * Hirschmann Hellcreek TSN switch. + * + * Copyright (C) 2019,2020 Hochschule Offenburg + * Copyright (C) 2019,2020 Linutronix GmbH + * Authors: Kurt Kanzenbach <kurt@linutronix.de> + * Kamil Alkhouri <kamil.alkhouri@hs-offenburg.de> + */ + +#ifndef _HELLCREEK_HWTSTAMP_H_ +#define _HELLCREEK_HWTSTAMP_H_ + +#include <net/dsa.h> +#include "hellcreek.h" + +/* Timestamp Register */ +#define PR_TS_RX_P1_STATUS_C (0x1d * 2) +#define PR_TS_RX_P1_DATA_C (0x1e * 2) +#define PR_TS_TX_P1_STATUS_C (0x1f * 2) +#define PR_TS_TX_P1_DATA_C (0x20 * 2) +#define PR_TS_RX_P2_STATUS_C (0x25 * 2) +#define PR_TS_RX_P2_DATA_C (0x26 * 2) +#define PR_TS_TX_P2_STATUS_C (0x27 * 2) +#define PR_TS_TX_P2_DATA_C (0x28 * 2) + +#define PR_TS_STATUS_TS_AVAIL BIT(2) +#define PR_TS_STATUS_TS_LOST BIT(3) + +#define SKB_PTP_TYPE(__skb) (*(unsigned int *)((__skb)->cb)) + +/* TX_TSTAMP_TIMEOUT: This limits the time spent polling for a TX + * timestamp. When working properly, hardware will produce a timestamp + * within 1ms. Software may enounter delays, so the timeout is set + * accordingly. + */ +#define TX_TSTAMP_TIMEOUT msecs_to_jiffies(40) + +int hellcreek_port_hwtstamp_set(struct dsa_switch *ds, int port, + struct ifreq *ifr); +int hellcreek_port_hwtstamp_get(struct dsa_switch *ds, int port, + struct ifreq *ifr); + +bool hellcreek_port_rxtstamp(struct dsa_switch *ds, int port, + struct sk_buff *clone, unsigned int type); +bool hellcreek_port_txtstamp(struct dsa_switch *ds, int port, + struct sk_buff *clone, unsigned int type); + +int hellcreek_get_ts_info(struct dsa_switch *ds, int port, + struct ethtool_ts_info *info); + +long hellcreek_hwtstamp_work(struct ptp_clock_info *ptp); + +int hellcreek_hwtstamp_setup(struct hellcreek *chip); +void hellcreek_hwtstamp_free(struct hellcreek *chip); + +#endif /* _HELLCREEK_HWTSTAMP_H_ */ diff --git a/drivers/net/dsa/hirschmann/hellcreek_ptp.c b/drivers/net/dsa/hirschmann/hellcreek_ptp.c new file mode 100644 index 000000000000..2572c6087bb5 --- /dev/null +++ b/drivers/net/dsa/hirschmann/hellcreek_ptp.c @@ -0,0 +1,452 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * DSA driver for: + * Hirschmann Hellcreek TSN switch. + * + * Copyright (C) 2019,2020 Hochschule Offenburg + * Copyright (C) 2019,2020 Linutronix GmbH + * Authors: Kamil Alkhouri <kamil.alkhouri@hs-offenburg.de> + * Kurt Kanzenbach <kurt@linutronix.de> + */ + +#include <linux/ptp_clock_kernel.h> +#include "hellcreek.h" +#include "hellcreek_ptp.h" +#include "hellcreek_hwtstamp.h" + +u16 hellcreek_ptp_read(struct hellcreek *hellcreek, unsigned int offset) +{ + return readw(hellcreek->ptp_base + offset); +} + +void hellcreek_ptp_write(struct hellcreek *hellcreek, u16 data, + unsigned int offset) +{ + writew(data, hellcreek->ptp_base + offset); +} + +/* Get nanoseconds from PTP clock */ +static u64 hellcreek_ptp_clock_read(struct hellcreek *hellcreek) +{ + u16 nsl, nsh; + + /* Take a snapshot */ + hellcreek_ptp_write(hellcreek, PR_COMMAND_C_SS, PR_COMMAND_C); + + /* The time of the day is saved as 96 bits. However, due to hardware + * limitations the seconds are not or only partly kept in the PTP + * core. Currently only three bits for the seconds are available. That's + * why only the nanoseconds are used and the seconds are tracked in + * software. Anyway due to internal locking all five registers should be + * read. + */ + nsh = hellcreek_ptp_read(hellcreek, PR_SS_SYNC_DATA_C); + nsh = hellcreek_ptp_read(hellcreek, PR_SS_SYNC_DATA_C); + nsh = hellcreek_ptp_read(hellcreek, PR_SS_SYNC_DATA_C); + nsh = hellcreek_ptp_read(hellcreek, PR_SS_SYNC_DATA_C); + nsl = hellcreek_ptp_read(hellcreek, PR_SS_SYNC_DATA_C); + + return (u64)nsl | ((u64)nsh << 16); +} + +static u64 __hellcreek_ptp_gettime(struct hellcreek *hellcreek) +{ + u64 ns; + + ns = hellcreek_ptp_clock_read(hellcreek); + if (ns < hellcreek->last_ts) + hellcreek->seconds++; + hellcreek->last_ts = ns; + ns += hellcreek->seconds * NSEC_PER_SEC; + + return ns; +} + +/* Retrieve the seconds parts in nanoseconds for a packet timestamped with @ns. + * There has to be a check whether an overflow occurred between the packet + * arrival and now. If so use the correct seconds (-1) for calculating the + * packet arrival time. + */ +u64 hellcreek_ptp_gettime_seconds(struct hellcreek *hellcreek, u64 ns) +{ + u64 s; + + __hellcreek_ptp_gettime(hellcreek); + if (hellcreek->last_ts > ns) + s = hellcreek->seconds * NSEC_PER_SEC; + else + s = (hellcreek->seconds - 1) * NSEC_PER_SEC; + + return s; +} + +static int hellcreek_ptp_gettime(struct ptp_clock_info *ptp, + struct timespec64 *ts) +{ + struct hellcreek *hellcreek = ptp_to_hellcreek(ptp); + u64 ns; + + mutex_lock(&hellcreek->ptp_lock); + ns = __hellcreek_ptp_gettime(hellcreek); + mutex_unlock(&hellcreek->ptp_lock); + + *ts = ns_to_timespec64(ns); + + return 0; +} + +static int hellcreek_ptp_settime(struct ptp_clock_info *ptp, + const struct timespec64 *ts) +{ + struct hellcreek *hellcreek = ptp_to_hellcreek(ptp); + u16 secl, nsh, nsl; + + secl = ts->tv_sec & 0xffff; + nsh = ((u32)ts->tv_nsec & 0xffff0000) >> 16; + nsl = ts->tv_nsec & 0xffff; + + mutex_lock(&hellcreek->ptp_lock); + + /* Update overflow data structure */ + hellcreek->seconds = ts->tv_sec; + hellcreek->last_ts = ts->tv_nsec; + + /* Set time in clock */ + hellcreek_ptp_write(hellcreek, 0x00, PR_CLOCK_WRITE_C); + hellcreek_ptp_write(hellcreek, 0x00, PR_CLOCK_WRITE_C); + hellcreek_ptp_write(hellcreek, secl, PR_CLOCK_WRITE_C); + hellcreek_ptp_write(hellcreek, nsh, PR_CLOCK_WRITE_C); + hellcreek_ptp_write(hellcreek, nsl, PR_CLOCK_WRITE_C); + + mutex_unlock(&hellcreek->ptp_lock); + + return 0; +} + +static int hellcreek_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) +{ + struct hellcreek *hellcreek = ptp_to_hellcreek(ptp); + u16 negative = 0, addendh, addendl; + u32 addend; + u64 adj; + + if (scaled_ppm < 0) { + negative = 1; + scaled_ppm = -scaled_ppm; + } + + /* IP-Core adjusts the nominal frequency by adding or subtracting 1 ns + * from the 8 ns (period of the oscillator) every time the accumulator + * register overflows. The value stored in the addend register is added + * to the accumulator register every 8 ns. + * + * addend value = (2^30 * accumulator_overflow_rate) / + * oscillator_frequency + * where: + * + * oscillator_frequency = 125 MHz + * accumulator_overflow_rate = 125 MHz * scaled_ppm * 2^-16 * 10^-6 * 8 + */ + adj = scaled_ppm; + adj <<= 11; + addend = (u32)div_u64(adj, 15625); + + addendh = (addend & 0xffff0000) >> 16; + addendl = addend & 0xffff; + + negative = (negative << 15) & 0x8000; + + mutex_lock(&hellcreek->ptp_lock); + + /* Set drift register */ + hellcreek_ptp_write(hellcreek, negative, PR_CLOCK_DRIFT_C); + hellcreek_ptp_write(hellcreek, 0x00, PR_CLOCK_DRIFT_C); + hellcreek_ptp_write(hellcreek, 0x00, PR_CLOCK_DRIFT_C); + hellcreek_ptp_write(hellcreek, addendh, PR_CLOCK_DRIFT_C); + hellcreek_ptp_write(hellcreek, addendl, PR_CLOCK_DRIFT_C); + + mutex_unlock(&hellcreek->ptp_lock); + + return 0; +} + +static int hellcreek_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) +{ + struct hellcreek *hellcreek = ptp_to_hellcreek(ptp); + u16 negative = 0, counth, countl; + u32 count_val; + + /* If the offset is larger than IP-Core slow offset resources. Don't + * consider slow adjustment. Rather, add the offset directly to the + * current time + */ + if (abs(delta) > MAX_SLOW_OFFSET_ADJ) { + struct timespec64 now, then = ns_to_timespec64(delta); + + hellcreek_ptp_gettime(ptp, &now); + now = timespec64_add(now, then); + hellcreek_ptp_settime(ptp, &now); + + return 0; + } + + if (delta < 0) { + negative = 1; + delta = -delta; + } + + /* 'count_val' does not exceed the maximum register size (2^30) */ + count_val = div_s64(delta, MAX_NS_PER_STEP); + + counth = (count_val & 0xffff0000) >> 16; + countl = count_val & 0xffff; + + negative = (negative << 15) & 0x8000; + + mutex_lock(&hellcreek->ptp_lock); + + /* Set offset write register */ + hellcreek_ptp_write(hellcreek, negative, PR_CLOCK_OFFSET_C); + hellcreek_ptp_write(hellcreek, MAX_NS_PER_STEP, PR_CLOCK_OFFSET_C); + hellcreek_ptp_write(hellcreek, MIN_CLK_CYCLES_BETWEEN_STEPS, + PR_CLOCK_OFFSET_C); + hellcreek_ptp_write(hellcreek, countl, PR_CLOCK_OFFSET_C); + hellcreek_ptp_write(hellcreek, counth, PR_CLOCK_OFFSET_C); + + mutex_unlock(&hellcreek->ptp_lock); + + return 0; +} + +static int hellcreek_ptp_enable(struct ptp_clock_info *ptp, + struct ptp_clock_request *rq, int on) +{ + return -EOPNOTSUPP; +} + +static void hellcreek_ptp_overflow_check(struct work_struct *work) +{ + struct delayed_work *dw = to_delayed_work(work); + struct hellcreek *hellcreek; + + hellcreek = dw_overflow_to_hellcreek(dw); + + mutex_lock(&hellcreek->ptp_lock); + __hellcreek_ptp_gettime(hellcreek); + mutex_unlock(&hellcreek->ptp_lock); + + schedule_delayed_work(&hellcreek->overflow_work, + HELLCREEK_OVERFLOW_PERIOD); +} + +static enum led_brightness hellcreek_get_brightness(struct hellcreek *hellcreek, + int led) +{ + return (hellcreek->status_out & led) ? 1 : 0; +} + +static void hellcreek_set_brightness(struct hellcreek *hellcreek, int led, + enum led_brightness b) +{ + mutex_lock(&hellcreek->ptp_lock); + + if (b) + hellcreek->status_out |= led; + else + hellcreek->status_out &= ~led; + + hellcreek_ptp_write(hellcreek, hellcreek->status_out, STATUS_OUT); + + mutex_unlock(&hellcreek->ptp_lock); +} + +static void hellcreek_led_sync_good_set(struct led_classdev *ldev, + enum led_brightness b) +{ + struct hellcreek *hellcreek = led_to_hellcreek(ldev, led_sync_good); + + hellcreek_set_brightness(hellcreek, STATUS_OUT_SYNC_GOOD, b); +} + +static enum led_brightness hellcreek_led_sync_good_get(struct led_classdev *ldev) +{ + struct hellcreek *hellcreek = led_to_hellcreek(ldev, led_sync_good); + + return hellcreek_get_brightness(hellcreek, STATUS_OUT_SYNC_GOOD); +} + +static void hellcreek_led_is_gm_set(struct led_classdev *ldev, + enum led_brightness b) +{ + struct hellcreek *hellcreek = led_to_hellcreek(ldev, led_is_gm); + + hellcreek_set_brightness(hellcreek, STATUS_OUT_IS_GM, b); +} + +static enum led_brightness hellcreek_led_is_gm_get(struct led_classdev *ldev) +{ + struct hellcreek *hellcreek = led_to_hellcreek(ldev, led_is_gm); + + return hellcreek_get_brightness(hellcreek, STATUS_OUT_IS_GM); +} + +/* There two available LEDs internally called sync_good and is_gm. However, the + * user might want to use a different label and specify the default state. Take + * those properties from device tree. + */ +static int hellcreek_led_setup(struct hellcreek *hellcreek) +{ + struct device_node *leds, *led = NULL; + const char *label, *state; + int ret = -EINVAL; + + leds = of_find_node_by_name(hellcreek->dev->of_node, "leds"); + if (!leds) { + dev_err(hellcreek->dev, "No LEDs specified in device tree!\n"); + return ret; + } + + hellcreek->status_out = 0; + + led = of_get_next_available_child(leds, led); + if (!led) { + dev_err(hellcreek->dev, "First LED not specified!\n"); + goto out; + } + + ret = of_property_read_string(led, "label", &label); + hellcreek->led_sync_good.name = ret ? "sync_good" : label; + + ret = of_property_read_string(led, "default-state", &state); + if (!ret) { + if (!strcmp(state, "on")) + hellcreek->led_sync_good.brightness = 1; + else if (!strcmp(state, "off")) + hellcreek->led_sync_good.brightness = 0; + else if (!strcmp(state, "keep")) + hellcreek->led_sync_good.brightness = + hellcreek_get_brightness(hellcreek, + STATUS_OUT_SYNC_GOOD); + } + + hellcreek->led_sync_good.max_brightness = 1; + hellcreek->led_sync_good.brightness_set = hellcreek_led_sync_good_set; + hellcreek->led_sync_good.brightness_get = hellcreek_led_sync_good_get; + + led = of_get_next_available_child(leds, led); + if (!led) { + dev_err(hellcreek->dev, "Second LED not specified!\n"); + ret = -EINVAL; + goto out; + } + + ret = of_property_read_string(led, "label", &label); + hellcreek->led_is_gm.name = ret ? "is_gm" : label; + + ret = of_property_read_string(led, "default-state", &state); + if (!ret) { + if (!strcmp(state, "on")) + hellcreek->led_is_gm.brightness = 1; + else if (!strcmp(state, "off")) + hellcreek->led_is_gm.brightness = 0; + else if (!strcmp(state, "keep")) + hellcreek->led_is_gm.brightness = + hellcreek_get_brightness(hellcreek, + STATUS_OUT_IS_GM); + } + + hellcreek->led_is_gm.max_brightness = 1; + hellcreek->led_is_gm.brightness_set = hellcreek_led_is_gm_set; + hellcreek->led_is_gm.brightness_get = hellcreek_led_is_gm_get; + + /* Set initial state */ + if (hellcreek->led_sync_good.brightness == 1) + hellcreek_set_brightness(hellcreek, STATUS_OUT_SYNC_GOOD, 1); + if (hellcreek->led_is_gm.brightness == 1) + hellcreek_set_brightness(hellcreek, STATUS_OUT_IS_GM, 1); + + /* Register both leds */ + led_classdev_register(hellcreek->dev, &hellcreek->led_sync_good); + led_classdev_register(hellcreek->dev, &hellcreek->led_is_gm); + + ret = 0; + +out: + of_node_put(leds); + + return ret; +} + +int hellcreek_ptp_setup(struct hellcreek *hellcreek) +{ + u16 status; + int ret; + + /* Set up the overflow work */ + INIT_DELAYED_WORK(&hellcreek->overflow_work, + hellcreek_ptp_overflow_check); + + /* Setup PTP clock */ + hellcreek->ptp_clock_info.owner = THIS_MODULE; + snprintf(hellcreek->ptp_clock_info.name, + sizeof(hellcreek->ptp_clock_info.name), + dev_name(hellcreek->dev)); + + /* IP-Core can add up to 0.5 ns per 8 ns cycle, which means + * accumulator_overflow_rate shall not exceed 62.5 MHz (which adjusts + * the nominal frequency by 6.25%) + */ + hellcreek->ptp_clock_info.max_adj = 62500000; + hellcreek->ptp_clock_info.n_alarm = 0; + hellcreek->ptp_clock_info.n_pins = 0; + hellcreek->ptp_clock_info.n_ext_ts = 0; + hellcreek->ptp_clock_info.n_per_out = 0; + hellcreek->ptp_clock_info.pps = 0; + hellcreek->ptp_clock_info.adjfine = hellcreek_ptp_adjfine; + hellcreek->ptp_clock_info.adjtime = hellcreek_ptp_adjtime; + hellcreek->ptp_clock_info.gettime64 = hellcreek_ptp_gettime; + hellcreek->ptp_clock_info.settime64 = hellcreek_ptp_settime; + hellcreek->ptp_clock_info.enable = hellcreek_ptp_enable; + hellcreek->ptp_clock_info.do_aux_work = hellcreek_hwtstamp_work; + + hellcreek->ptp_clock = ptp_clock_register(&hellcreek->ptp_clock_info, + hellcreek->dev); + if (IS_ERR(hellcreek->ptp_clock)) + return PTR_ERR(hellcreek->ptp_clock); + + /* Enable the offset correction process, if no offset correction is + * already taking place + */ + status = hellcreek_ptp_read(hellcreek, PR_CLOCK_STATUS_C); + if (!(status & PR_CLOCK_STATUS_C_OFS_ACT)) + hellcreek_ptp_write(hellcreek, + status | PR_CLOCK_STATUS_C_ENA_OFS, + PR_CLOCK_STATUS_C); + + /* Enable the drift correction process */ + hellcreek_ptp_write(hellcreek, status | PR_CLOCK_STATUS_C_ENA_DRIFT, + PR_CLOCK_STATUS_C); + + /* LED setup */ + ret = hellcreek_led_setup(hellcreek); + if (ret) { + if (hellcreek->ptp_clock) + ptp_clock_unregister(hellcreek->ptp_clock); + return ret; + } + + schedule_delayed_work(&hellcreek->overflow_work, + HELLCREEK_OVERFLOW_PERIOD); + + return 0; +} + +void hellcreek_ptp_free(struct hellcreek *hellcreek) +{ + led_classdev_unregister(&hellcreek->led_is_gm); + led_classdev_unregister(&hellcreek->led_sync_good); + cancel_delayed_work_sync(&hellcreek->overflow_work); + if (hellcreek->ptp_clock) + ptp_clock_unregister(hellcreek->ptp_clock); + hellcreek->ptp_clock = NULL; +} diff --git a/drivers/net/dsa/hirschmann/hellcreek_ptp.h b/drivers/net/dsa/hirschmann/hellcreek_ptp.h new file mode 100644 index 000000000000..0b51392c7e56 --- /dev/null +++ b/drivers/net/dsa/hirschmann/hellcreek_ptp.h @@ -0,0 +1,76 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */ +/* + * DSA driver for: + * Hirschmann Hellcreek TSN switch. + * + * Copyright (C) 2019,2020 Hochschule Offenburg + * Copyright (C) 2019,2020 Linutronix GmbH + * Authors: Kurt Kanzenbach <kurt@linutronix.de> + * Kamil Alkhouri <kamil.alkhouri@hs-offenburg.de> + */ + +#ifndef _HELLCREEK_PTP_H_ +#define _HELLCREEK_PTP_H_ + +#include <linux/bitops.h> +#include <linux/ptp_clock_kernel.h> + +#include "hellcreek.h" + +/* Every jump in time is 7 ns */ +#define MAX_NS_PER_STEP 7L + +/* Correct offset at every clock cycle */ +#define MIN_CLK_CYCLES_BETWEEN_STEPS 0 + +/* Maximum available slow offset resources */ +#define MAX_SLOW_OFFSET_ADJ \ + ((unsigned long long)((1 << 30) - 1) * MAX_NS_PER_STEP) + +/* four times a second overflow check */ +#define HELLCREEK_OVERFLOW_PERIOD (HZ / 4) + +/* PTP Register */ +#define PR_SETTINGS_C (0x09 * 2) +#define PR_SETTINGS_C_RES3TS BIT(4) +#define PR_SETTINGS_C_TS_SRC_TK_SHIFT 8 +#define PR_SETTINGS_C_TS_SRC_TK_MASK GENMASK(9, 8) +#define PR_COMMAND_C (0x0a * 2) +#define PR_COMMAND_C_SS BIT(0) + +#define PR_CLOCK_STATUS_C (0x0c * 2) +#define PR_CLOCK_STATUS_C_ENA_DRIFT BIT(12) +#define PR_CLOCK_STATUS_C_OFS_ACT BIT(13) +#define PR_CLOCK_STATUS_C_ENA_OFS BIT(14) + +#define PR_CLOCK_READ_C (0x0d * 2) +#define PR_CLOCK_WRITE_C (0x0e * 2) +#define PR_CLOCK_OFFSET_C (0x0f * 2) +#define PR_CLOCK_DRIFT_C (0x10 * 2) + +#define PR_SS_FREE_DATA_C (0x12 * 2) +#define PR_SS_SYNT_DATA_C (0x14 * 2) +#define PR_SS_SYNC_DATA_C (0x16 * 2) +#define PR_SS_DRAC_DATA_C (0x18 * 2) + +#define STATUS_OUT (0x60 * 2) +#define STATUS_OUT_SYNC_GOOD BIT(0) +#define STATUS_OUT_IS_GM BIT(1) + +int hellcreek_ptp_setup(struct hellcreek *hellcreek); +void hellcreek_ptp_free(struct hellcreek *hellcreek); +u16 hellcreek_ptp_read(struct hellcreek *hellcreek, unsigned int offset); +void hellcreek_ptp_write(struct hellcreek *hellcreek, u16 data, + unsigned int offset); +u64 hellcreek_ptp_gettime_seconds(struct hellcreek *hellcreek, u64 ns); + +#define ptp_to_hellcreek(ptp) \ + container_of(ptp, struct hellcreek, ptp_clock_info) + +#define dw_overflow_to_hellcreek(dw) \ + container_of(dw, struct hellcreek, overflow_work) + +#define led_to_hellcreek(ldev, led) \ + container_of(ldev, struct hellcreek, led) + +#endif /* _HELLCREEK_PTP_H_ */ diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index de7692b763d8..6408402a44f5 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -558,7 +558,7 @@ mt7531_pad_setup(struct dsa_switch *ds, phy_interface_t interface) val |= 0x190000 << RG_COREPLL_SDM_PCW_S; mt7530_write(priv, MT7531_PLLGP_CR0, val); break; - }; + } /* Set feedback divide ratio update signal to high */ val = mt7530_read(priv, MT7531_PLLGP_CR0); @@ -1021,6 +1021,53 @@ mt7530_port_disable(struct dsa_switch *ds, int port) mutex_unlock(&priv->reg_mutex); } +static int +mt7530_port_change_mtu(struct dsa_switch *ds, int port, int new_mtu) +{ + struct mt7530_priv *priv = ds->priv; + struct mii_bus *bus = priv->bus; + int length; + u32 val; + + /* When a new MTU is set, DSA always set the CPU port's MTU to the + * largest MTU of the slave ports. Because the switch only has a global + * RX length register, only allowing CPU port here is enough. + */ + if (!dsa_is_cpu_port(ds, port)) + return 0; + + mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED); + + val = mt7530_mii_read(priv, MT7530_GMACCR); + val &= ~MAX_RX_PKT_LEN_MASK; + + /* RX length also includes Ethernet header, MTK tag, and FCS length */ + length = new_mtu + ETH_HLEN + MTK_HDR_LEN + ETH_FCS_LEN; + if (length <= 1522) { + val |= MAX_RX_PKT_LEN_1522; + } else if (length <= 1536) { + val |= MAX_RX_PKT_LEN_1536; + } else if (length <= 1552) { + val |= MAX_RX_PKT_LEN_1552; + } else { + val &= ~MAX_RX_JUMBO_MASK; + val |= MAX_RX_JUMBO(DIV_ROUND_UP(length, 1024)); + val |= MAX_RX_PKT_LEN_JUMBO; + } + + mt7530_mii_write(priv, MT7530_GMACCR, val); + + mutex_unlock(&bus->mdio_lock); + + return 0; +} + +static int +mt7530_port_max_mtu(struct dsa_switch *ds, int port) +{ + return MT7530_MAX_MTU; +} + static void mt7530_stp_state_set(struct dsa_switch *ds, int port, u8 state) { @@ -2519,6 +2566,8 @@ static const struct dsa_switch_ops mt7530_switch_ops = { .get_sset_count = mt7530_get_sset_count, .port_enable = mt7530_port_enable, .port_disable = mt7530_port_disable, + .port_change_mtu = mt7530_port_change_mtu, + .port_max_mtu = mt7530_port_max_mtu, .port_stp_state_set = mt7530_stp_state_set, .port_bridge_join = mt7530_port_bridge_join, .port_bridge_leave = mt7530_port_bridge_leave, diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h index 9278a8e3d04e..ee3523a7537e 100644 --- a/drivers/net/dsa/mt7530.h +++ b/drivers/net/dsa/mt7530.h @@ -11,6 +11,9 @@ #define MT7530_NUM_FDB_RECORDS 2048 #define MT7530_ALL_MEMBERS 0xff +#define MTK_HDR_LEN 4 +#define MT7530_MAX_MTU (15 * 1024 - ETH_HLEN - ETH_FCS_LEN - MTK_HDR_LEN) + enum mt753x_id { ID_MT7530 = 0, ID_MT7621 = 1, @@ -289,6 +292,15 @@ enum mt7530_vlan_port_attr { #define MT7531_DBG_CNT(x) (0x3018 + (x) * 0x100) #define MT7531_DIS_CLR BIT(31) +#define MT7530_GMACCR 0x30e0 +#define MAX_RX_JUMBO(x) ((x) << 2) +#define MAX_RX_JUMBO_MASK GENMASK(5, 2) +#define MAX_RX_PKT_LEN_MASK GENMASK(1, 0) +#define MAX_RX_PKT_LEN_1522 0x0 +#define MAX_RX_PKT_LEN_1536 0x1 +#define MAX_RX_PKT_LEN_1552 0x2 +#define MAX_RX_PKT_LEN_JUMBO 0x3 + /* Register for MIB */ #define MT7530_PORT_MIB_COUNTER(x) (0x4000 + (x) * 0x100) #define MT7530_MIB_CCR 0x4fe0 diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index bd297ae7cf9e..72340c17f099 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -2851,6 +2851,7 @@ static int mv88e6xxx_setup(struct dsa_switch *ds) chip->ds = ds; ds->slave_mii_bus = mv88e6xxx_default_mdio_bus(chip); + ds->configure_vlan_while_not_filtering = true; mv88e6xxx_reg_lock(chip); diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index f791860d495f..ada75fa15861 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -112,10 +112,32 @@ static void felix_bridge_leave(struct dsa_switch *ds, int port, ocelot_port_bridge_leave(ocelot, port, br); } -/* This callback needs to be present */ static int felix_vlan_prepare(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan) { + struct ocelot *ocelot = ds->priv; + u16 vid, flags = vlan->flags; + int err; + + /* Ocelot switches copy frames as-is to the CPU, so the flags: + * egress-untagged or not, pvid or not, make no difference. This + * behavior is already better than what DSA just tries to approximate + * when it installs the VLAN with the same flags on the CPU port. + * Just accept any configuration, and don't let ocelot deny installing + * multiple native VLANs on the NPI port, because the switch doesn't + * look at the port tag settings towards the NPI interface anyway. + */ + if (port == ocelot->npi) + return 0; + + for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) { + err = ocelot_vlan_prepare(ocelot, port, vid, + flags & BRIDGE_VLAN_INFO_PVID, + flags & BRIDGE_VLAN_INFO_UNTAGGED); + if (err) + return err; + } + return 0; } @@ -135,9 +157,6 @@ static void felix_vlan_add(struct dsa_switch *ds, int port, u16 vid; int err; - if (dsa_is_cpu_port(ds, port)) - flags &= ~BRIDGE_VLAN_INFO_UNTAGGED; - for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) { err = ocelot_vlan_add(ocelot, port, vid, flags & BRIDGE_VLAN_INFO_PVID, diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c index bab3a9bb5e6f..f82ad7419508 100644 --- a/drivers/net/dummy.c +++ b/drivers/net/dummy.c @@ -124,7 +124,7 @@ static void dummy_setup(struct net_device *dev) dev->flags &= ~IFF_MULTICAST; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE; dev->features |= NETIF_F_SG | NETIF_F_FRAGLIST; - dev->features |= NETIF_F_ALL_TSO; + dev->features |= NETIF_F_GSO_SOFTWARE; dev->features |= NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_LLTX; dev->features |= NETIF_F_GSO_ENCAP_ALL; dev->hw_features |= dev->features; diff --git a/drivers/net/ethernet/8390/mac8390.c b/drivers/net/ethernet/8390/mac8390.c index d60a86aa8aa8..9aac7119d382 100644 --- a/drivers/net/ethernet/8390/mac8390.c +++ b/drivers/net/ethernet/8390/mac8390.c @@ -175,7 +175,6 @@ static enum mac8390_type mac8390_ident(struct nubus_rsrc *fres) default: return MAC8390_APPLE; } - break; case NUBUS_DRSW_APPLE: switch (fres->dr_hw) { @@ -186,11 +185,9 @@ static enum mac8390_type mac8390_ident(struct nubus_rsrc *fres) default: return MAC8390_APPLE; } - break; case NUBUS_DRSW_ASANTE: return MAC8390_ASANTE; - break; case NUBUS_DRSW_TECHWORKS: case NUBUS_DRSW_DAYNA2: @@ -199,11 +196,9 @@ static enum mac8390_type mac8390_ident(struct nubus_rsrc *fres) return MAC8390_CABLETRON; else return MAC8390_APPLE; - break; case NUBUS_DRSW_FARALLON: return MAC8390_FARALLON; - break; case NUBUS_DRSW_KINETICS: switch (fres->dr_hw) { @@ -212,7 +207,6 @@ static enum mac8390_type mac8390_ident(struct nubus_rsrc *fres) default: return MAC8390_KINETICS; } - break; case NUBUS_DRSW_DAYNA: /* @@ -224,7 +218,6 @@ static enum mac8390_type mac8390_ident(struct nubus_rsrc *fres) return MAC8390_NONE; else return MAC8390_DAYNA; - break; } return MAC8390_NONE; } diff --git a/drivers/net/ethernet/8390/ne.c b/drivers/net/ethernet/8390/ne.c index 1c97e39b478e..e9756d0ea5b8 100644 --- a/drivers/net/ethernet/8390/ne.c +++ b/drivers/net/ethernet/8390/ne.c @@ -710,7 +710,7 @@ static void ne_block_output(struct net_device *dev, int count, retry: #endif -#ifdef NE8390_RW_BUGFIX +#ifdef NE_RW_BUGFIX /* Handle the read-before-write bug the same way as the Crynwr packet driver -- the NatSemi method doesn't work. Actually this doesn't always work either, but if you have diff --git a/drivers/net/ethernet/8390/ne2k-pci.c b/drivers/net/ethernet/8390/ne2k-pci.c index bc6edb3f1af3..d6715008e04d 100644 --- a/drivers/net/ethernet/8390/ne2k-pci.c +++ b/drivers/net/ethernet/8390/ne2k-pci.c @@ -610,7 +610,7 @@ static void ne2k_pci_block_output(struct net_device *dev, int count, /* We should already be in page 0, but to be safe... */ outb(E8390_PAGE0+E8390_START+E8390_NODMA, nic_base + NE_CMD); -#ifdef NE8390_RW_BUGFIX +#ifdef NE_RW_BUGFIX /* Handle the read-before-write bug the same way as the * Crynwr packet driver -- the NatSemi method doesn't work. * Actually this doesn't always work either, but if you have diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index 5de47f6fde5a..1f5da4e4f4b2 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -77,10 +77,12 @@ #define MACB_RBQPH 0x04D4 /* GEM register offsets. */ +#define GEM_NCR 0x0000 /* Network Control */ #define GEM_NCFGR 0x0004 /* Network Config */ #define GEM_USRIO 0x000c /* User IO */ #define GEM_DMACFG 0x0010 /* DMA Configuration */ #define GEM_JML 0x0048 /* Jumbo Max Length */ +#define GEM_HS_MAC_CONFIG 0x0050 /* GEM high speed config */ #define GEM_HRB 0x0080 /* Hash Bottom */ #define GEM_HRT 0x0084 /* Hash Top */ #define GEM_SA1B 0x0088 /* Specific1 Bottom */ @@ -166,6 +168,9 @@ #define GEM_DCFG7 0x0298 /* Design Config 7 */ #define GEM_DCFG8 0x029C /* Design Config 8 */ #define GEM_DCFG10 0x02A4 /* Design Config 10 */ +#define GEM_DCFG12 0x02AC /* Design Config 12 */ +#define GEM_USX_CONTROL 0x0A80 /* High speed PCS control register */ +#define GEM_USX_STATUS 0x0A88 /* High speed PCS status register */ #define GEM_TXBDCTRL 0x04cc /* TX Buffer Descriptor control register */ #define GEM_RXBDCTRL 0x04d0 /* RX Buffer Descriptor control register */ @@ -272,11 +277,19 @@ #define MACB_IRXFCS_OFFSET 19 #define MACB_IRXFCS_SIZE 1 +/* GEM specific NCR bitfields. */ +#define GEM_ENABLE_HS_MAC_OFFSET 31 +#define GEM_ENABLE_HS_MAC_SIZE 1 + /* GEM specific NCFGR bitfields. */ +#define GEM_FD_OFFSET 1 /* Full duplex */ +#define GEM_FD_SIZE 1 #define GEM_GBE_OFFSET 10 /* Gigabit mode enable */ #define GEM_GBE_SIZE 1 #define GEM_PCSSEL_OFFSET 11 #define GEM_PCSSEL_SIZE 1 +#define GEM_PAE_OFFSET 13 /* Pause enable */ +#define GEM_PAE_SIZE 1 #define GEM_CLK_OFFSET 18 /* MDC clock division */ #define GEM_CLK_SIZE 3 #define GEM_DBW_OFFSET 21 /* Data bus width */ @@ -461,11 +474,17 @@ #define MACB_REV_OFFSET 0 #define MACB_REV_SIZE 16 +/* Bitfield in HS_MAC_CONFIG */ +#define GEM_HS_MAC_SPEED_OFFSET 0 +#define GEM_HS_MAC_SPEED_SIZE 3 + /* Bitfields in DCFG1. */ #define GEM_IRQCOR_OFFSET 23 #define GEM_IRQCOR_SIZE 1 #define GEM_DBWDEF_OFFSET 25 #define GEM_DBWDEF_SIZE 3 +#define GEM_NO_PCS_OFFSET 0 +#define GEM_NO_PCS_SIZE 1 /* Bitfields in DCFG2. */ #define GEM_RX_PKT_BUFF_OFFSET 20 @@ -500,6 +519,28 @@ #define GEM_RXBD_RDBUFF_OFFSET 8 #define GEM_RXBD_RDBUFF_SIZE 4 +/* Bitfields in DCFG12. */ +#define GEM_HIGH_SPEED_OFFSET 26 +#define GEM_HIGH_SPEED_SIZE 1 + +/* Bitfields in USX_CONTROL. */ +#define GEM_USX_CTRL_SPEED_OFFSET 14 +#define GEM_USX_CTRL_SPEED_SIZE 3 +#define GEM_SERDES_RATE_OFFSET 12 +#define GEM_SERDES_RATE_SIZE 2 +#define GEM_RX_SCR_BYPASS_OFFSET 9 +#define GEM_RX_SCR_BYPASS_SIZE 1 +#define GEM_TX_SCR_BYPASS_OFFSET 8 +#define GEM_TX_SCR_BYPASS_SIZE 1 +#define GEM_TX_EN_OFFSET 1 +#define GEM_TX_EN_SIZE 1 +#define GEM_SIGNAL_OK_OFFSET 0 +#define GEM_SIGNAL_OK_SIZE 1 + +/* Bitfields in USX_STATUS. */ +#define GEM_USX_BLOCK_LOCK_OFFSET 0 +#define GEM_USX_BLOCK_LOCK_SIZE 1 + /* Bitfields in TISUBN */ #define GEM_SUBNSINCR_OFFSET 0 #define GEM_SUBNSINCRL_OFFSET 24 @@ -663,6 +704,8 @@ #define MACB_CAPS_GIGABIT_MODE_AVAILABLE 0x20000000 #define MACB_CAPS_SG_DISABLED 0x40000000 #define MACB_CAPS_MACB_IS_GEM 0x80000000 +#define MACB_CAPS_PCS 0x01000000 +#define MACB_CAPS_HIGH_SPEED 0x02000000 /* LSO settings */ #define MACB_LSO_UFO_ENABLE 0x01 @@ -1201,6 +1244,7 @@ struct macb { struct mii_bus *mii_bus; struct phylink *phylink; struct phylink_config phylink_config; + struct phylink_pcs phylink_pcs; u32 caps; unsigned int dma_burst_length; diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 286f0341bdf8..2bb26bc9278c 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -84,6 +84,9 @@ struct sifive_fu540_macb_mgmt { #define MACB_WOL_HAS_MAGIC_PACKET (0x1 << 0) #define MACB_WOL_ENABLED (0x1 << 1) +#define HS_SPEED_10000M 4 +#define MACB_SERDES_RATE_10G 1 + /* Graceful stop timeouts in us. We should allow up to * 1 frame time (10 Mbits/s, full-duplex, ignoring collisions) */ @@ -513,6 +516,7 @@ static void macb_validate(struct phylink_config *config, state->interface != PHY_INTERFACE_MODE_RMII && state->interface != PHY_INTERFACE_MODE_GMII && state->interface != PHY_INTERFACE_MODE_SGMII && + state->interface != PHY_INTERFACE_MODE_10GBASER && !phy_interface_mode_is_rgmii(state->interface)) { bitmap_zero(supported, __ETHTOOL_LINK_MODE_MASK_NBITS); return; @@ -525,10 +529,31 @@ static void macb_validate(struct phylink_config *config, return; } + if (state->interface == PHY_INTERFACE_MODE_10GBASER && + !(bp->caps & MACB_CAPS_HIGH_SPEED && + bp->caps & MACB_CAPS_PCS)) { + bitmap_zero(supported, __ETHTOOL_LINK_MODE_MASK_NBITS); + return; + } + phylink_set_port_modes(mask); phylink_set(mask, Autoneg); phylink_set(mask, Asym_Pause); + if (bp->caps & MACB_CAPS_GIGABIT_MODE_AVAILABLE && + (state->interface == PHY_INTERFACE_MODE_NA || + state->interface == PHY_INTERFACE_MODE_10GBASER)) { + phylink_set(mask, 10000baseCR_Full); + phylink_set(mask, 10000baseER_Full); + phylink_set(mask, 10000baseKR_Full); + phylink_set(mask, 10000baseLR_Full); + phylink_set(mask, 10000baseLRM_Full); + phylink_set(mask, 10000baseSR_Full); + phylink_set(mask, 10000baseT_Full); + if (state->interface != PHY_INTERFACE_MODE_NA) + goto out; + } + phylink_set(mask, 10baseT_Half); phylink_set(mask, 10baseT_Full); phylink_set(mask, 100baseT_Half); @@ -545,23 +570,80 @@ static void macb_validate(struct phylink_config *config, if (!(bp->caps & MACB_CAPS_NO_GIGABIT_HALF)) phylink_set(mask, 1000baseT_Half); } - +out: bitmap_and(supported, supported, mask, __ETHTOOL_LINK_MODE_MASK_NBITS); bitmap_and(state->advertising, state->advertising, mask, __ETHTOOL_LINK_MODE_MASK_NBITS); } -static void macb_mac_pcs_get_state(struct phylink_config *config, +static void macb_usx_pcs_link_up(struct phylink_pcs *pcs, unsigned int mode, + phy_interface_t interface, int speed, + int duplex) +{ + struct macb *bp = container_of(pcs, struct macb, phylink_pcs); + u32 config; + + config = gem_readl(bp, USX_CONTROL); + config = GEM_BFINS(SERDES_RATE, MACB_SERDES_RATE_10G, config); + config = GEM_BFINS(USX_CTRL_SPEED, HS_SPEED_10000M, config); + config &= ~(GEM_BIT(TX_SCR_BYPASS) | GEM_BIT(RX_SCR_BYPASS)); + config |= GEM_BIT(TX_EN); + gem_writel(bp, USX_CONTROL, config); +} + +static void macb_usx_pcs_get_state(struct phylink_pcs *pcs, struct phylink_link_state *state) { + struct macb *bp = container_of(pcs, struct macb, phylink_pcs); + u32 val; + + state->speed = SPEED_10000; + state->duplex = 1; + state->an_complete = 1; + + val = gem_readl(bp, USX_STATUS); + state->link = !!(val & GEM_BIT(USX_BLOCK_LOCK)); + val = gem_readl(bp, NCFGR); + if (val & GEM_BIT(PAE)) + state->pause = MLO_PAUSE_RX; +} + +static int macb_usx_pcs_config(struct phylink_pcs *pcs, + unsigned int mode, + phy_interface_t interface, + const unsigned long *advertising, + bool permit_pause_to_mac) +{ + struct macb *bp = container_of(pcs, struct macb, phylink_pcs); + + gem_writel(bp, USX_CONTROL, gem_readl(bp, USX_CONTROL) | + GEM_BIT(SIGNAL_OK)); + + return 0; +} + +static void macb_pcs_get_state(struct phylink_pcs *pcs, + struct phylink_link_state *state) +{ state->link = 0; } -static void macb_mac_an_restart(struct phylink_config *config) +static void macb_pcs_an_restart(struct phylink_pcs *pcs) { /* Not supported */ } +static const struct phylink_pcs_ops macb_phylink_usx_pcs_ops = { + .pcs_get_state = macb_usx_pcs_get_state, + .pcs_config = macb_usx_pcs_config, + .pcs_link_up = macb_usx_pcs_link_up, +}; + +static const struct phylink_pcs_ops macb_phylink_pcs_ops = { + .pcs_get_state = macb_pcs_get_state, + .pcs_an_restart = macb_pcs_an_restart, +}; + static void macb_mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state) { @@ -569,25 +651,35 @@ static void macb_mac_config(struct phylink_config *config, unsigned int mode, struct macb *bp = netdev_priv(ndev); unsigned long flags; u32 old_ctrl, ctrl; + u32 old_ncr, ncr; spin_lock_irqsave(&bp->lock, flags); old_ctrl = ctrl = macb_or_gem_readl(bp, NCFGR); + old_ncr = ncr = macb_or_gem_readl(bp, NCR); if (bp->caps & MACB_CAPS_MACB_IS_EMAC) { if (state->interface == PHY_INTERFACE_MODE_RMII) ctrl |= MACB_BIT(RM9200_RMII); } else if (macb_is_gem(bp)) { ctrl &= ~(GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL)); + ncr &= ~GEM_BIT(ENABLE_HS_MAC); - if (state->interface == PHY_INTERFACE_MODE_SGMII) + if (state->interface == PHY_INTERFACE_MODE_SGMII) { ctrl |= GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL); + } else if (state->interface == PHY_INTERFACE_MODE_10GBASER) { + ctrl |= GEM_BIT(PCSSEL); + ncr |= GEM_BIT(ENABLE_HS_MAC); + } } /* Apply the new configuration, if any */ if (old_ctrl ^ ctrl) macb_or_gem_writel(bp, NCFGR, ctrl); + if (old_ncr ^ ncr) + macb_or_gem_writel(bp, NCR, ncr); + spin_unlock_irqrestore(&bp->lock, flags); } @@ -664,6 +756,10 @@ static void macb_mac_link_up(struct phylink_config *config, macb_or_gem_writel(bp, NCFGR, ctrl); + if (bp->phy_interface == PHY_INTERFACE_MODE_10GBASER) + gem_writel(bp, HS_MAC_CONFIG, GEM_BFINS(HS_MAC_SPEED, HS_SPEED_10000M, + gem_readl(bp, HS_MAC_CONFIG))); + spin_unlock_irqrestore(&bp->lock, flags); /* Enable Rx and Tx */ @@ -672,10 +768,25 @@ static void macb_mac_link_up(struct phylink_config *config, netif_tx_wake_all_queues(ndev); } +static int macb_mac_prepare(struct phylink_config *config, unsigned int mode, + phy_interface_t interface) +{ + struct net_device *ndev = to_net_dev(config->dev); + struct macb *bp = netdev_priv(ndev); + + if (interface == PHY_INTERFACE_MODE_10GBASER) + bp->phylink_pcs.ops = &macb_phylink_usx_pcs_ops; + else + bp->phylink_pcs.ops = &macb_phylink_pcs_ops; + + phylink_set_pcs(bp->phylink, &bp->phylink_pcs); + + return 0; +} + static const struct phylink_mac_ops macb_phylink_ops = { .validate = macb_validate, - .mac_pcs_get_state = macb_mac_pcs_get_state, - .mac_an_restart = macb_mac_an_restart, + .mac_prepare = macb_mac_prepare, .mac_config = macb_mac_config, .mac_link_down = macb_mac_link_down, .mac_link_up = macb_mac_link_up, @@ -3524,6 +3635,11 @@ static void macb_configure_caps(struct macb *bp, dcfg = gem_readl(bp, DCFG1); if (GEM_BFEXT(IRQCOR, dcfg) == 0) bp->caps |= MACB_CAPS_ISR_CLEAR_ON_WRITE; + if (GEM_BFEXT(NO_PCS, dcfg) == 0) + bp->caps |= MACB_CAPS_PCS; + dcfg = gem_readl(bp, DCFG12); + if (GEM_BFEXT(HIGH_SPEED, dcfg) == 1) + bp->caps |= MACB_CAPS_HIGH_SPEED; dcfg = gem_readl(bp, DCFG2); if ((dcfg & (GEM_BIT(RX_PKT_BUFF) | GEM_BIT(TX_PKT_BUFF))) == 0) bp->caps |= MACB_CAPS_FIFO_MODE; diff --git a/drivers/net/ethernet/cavium/liquidio/cn68xx_device.c b/drivers/net/ethernet/cavium/liquidio/cn68xx_device.c index 2a6d1cadac9e..30254e4cf70f 100644 --- a/drivers/net/ethernet/cavium/liquidio/cn68xx_device.c +++ b/drivers/net/ethernet/cavium/liquidio/cn68xx_device.c @@ -27,7 +27,6 @@ #include "cn66xx_device.h" #include "cn68xx_device.h" #include "cn68xx_regs.h" -#include "cn68xx_device.h" static void lio_cn68xx_set_dpi_regs(struct octeon_device *oct) { diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h index 2d3dfdd2a716..e7b78b68eaac 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h @@ -235,6 +235,7 @@ struct chtls_dev { struct list_head na_node; unsigned int send_page_order; int max_host_sndbuf; + u32 round_robin_cnt; struct key_map kmap; unsigned int cdev_state; }; diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c index 96d561653496..63aacc184f68 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c @@ -1217,8 +1217,9 @@ static struct sock *chtls_recv_sock(struct sock *lsk, csk->sndbuf = csk->snd_win; csk->ulp_mode = ULP_MODE_TLS; step = cdev->lldi->nrxq / cdev->lldi->nchan; - csk->rss_qid = cdev->lldi->rxq_ids[port_id * step]; rxq_idx = port_id * step; + rxq_idx += cdev->round_robin_cnt++ % step; + csk->rss_qid = cdev->lldi->rxq_ids[rxq_idx]; csk->txq_idx = (rxq_idx < cdev->lldi->ntxq) ? rxq_idx : port_id * step; csk->sndbuf = newsk->sk_sndbuf; diff --git a/drivers/net/ethernet/davicom/Kconfig b/drivers/net/ethernet/davicom/Kconfig index 76247103e566..7af86b6d4150 100644 --- a/drivers/net/ethernet/davicom/Kconfig +++ b/drivers/net/ethernet/davicom/Kconfig @@ -5,7 +5,7 @@ config DM9000 tristate "DM9000 support" - depends on ARM || MIPS || COLDFIRE || NIOS2 + depends on ARM || MIPS || COLDFIRE || NIOS2 || COMPILE_TEST select CRC32 select MII help diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c index 5c6c8c5ec747..3fdc70dab5c1 100644 --- a/drivers/net/ethernet/davicom/dm9000.c +++ b/drivers/net/ethernet/davicom/dm9000.c @@ -232,32 +232,29 @@ static void dm9000_inblk_32bit(void __iomem *reg, void *data, int count) static void dm9000_dumpblk_8bit(void __iomem *reg, int count) { int i; - int tmp; for (i = 0; i < count; i++) - tmp = readb(reg); + readb(reg); } static void dm9000_dumpblk_16bit(void __iomem *reg, int count) { int i; - int tmp; count = (count + 1) >> 1; for (i = 0; i < count; i++) - tmp = readw(reg); + readw(reg); } static void dm9000_dumpblk_32bit(void __iomem *reg, int count) { int i; - int tmp; count = (count + 3) >> 2; for (i = 0; i < count; i++) - tmp = readl(reg); + readl(reg); } /* diff --git a/drivers/net/ethernet/dec/tulip/de2104x.c b/drivers/net/ethernet/dec/tulip/de2104x.c index d9f6c19940ef..c3cbe55205a7 100644 --- a/drivers/net/ethernet/dec/tulip/de2104x.c +++ b/drivers/net/ethernet/dec/tulip/de2104x.c @@ -2175,11 +2175,21 @@ out: static SIMPLE_DEV_PM_OPS(de_pm_ops, de_suspend, de_resume); +static void de_shutdown(struct pci_dev *pdev) +{ + struct net_device *dev = pci_get_drvdata(pdev); + + rtnl_lock(); + dev_close(dev); + rtnl_unlock(); +} + static struct pci_driver de_driver = { .name = DRV_NAME, .id_table = de_pci_tbl, .probe = de_init_one, .remove = de_remove_one, + .shutdown = de_shutdown, .driver.pm = &de_pm_ops, }; diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c index e7b0d7de40fd..c1dcd6ca1457 100644 --- a/drivers/net/ethernet/dec/tulip/tulip_core.c +++ b/drivers/net/ethernet/dec/tulip/tulip_core.c @@ -1293,7 +1293,9 @@ static int tulip_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) static unsigned char last_phys_addr[ETH_ALEN] = { 0x00, 'L', 'i', 'n', 'u', 'x' }; +#if defined(__i386__) || defined(__x86_64__) /* Patch up x86 BIOS bug. */ static int last_irq; +#endif int i, irq; unsigned short sum; unsigned char *ee_data; @@ -1617,7 +1619,9 @@ static int tulip_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) for (i = 0; i < 6; i++) last_phys_addr[i] = dev->dev_addr[i]; +#if defined(__i386__) || defined(__x86_64__) /* Patch up x86 BIOS bug. */ last_irq = irq; +#endif /* The lower four bits are the media type. */ if (board_idx >= 0 && board_idx < MAX_UNITS) { diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index 00024dd41147..983b6db2d80d 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -1044,10 +1044,39 @@ static void ftgmac100_adjust_link(struct net_device *netdev) schedule_work(&priv->reset_task); } -static int ftgmac100_mii_probe(struct ftgmac100 *priv, phy_interface_t intf) +static int ftgmac100_mii_probe(struct net_device *netdev) { - struct net_device *netdev = priv->netdev; + struct ftgmac100 *priv = netdev_priv(netdev); + struct platform_device *pdev = to_platform_device(priv->dev); + struct device_node *np = pdev->dev.of_node; struct phy_device *phydev; + phy_interface_t phy_intf; + int err; + + /* Default to RGMII. It's a gigabit part after all */ + err = of_get_phy_mode(np, &phy_intf); + if (err) + phy_intf = PHY_INTERFACE_MODE_RGMII; + + /* Aspeed only supports these. I don't know about other IP + * block vendors so I'm going to just let them through for + * now. Note that this is only a warning if for some obscure + * reason the DT really means to lie about it or it's a newer + * part we don't know about. + * + * On the Aspeed SoC there are additionally straps and SCU + * control bits that could tell us what the interface is + * (or allow us to configure it while the IP block is held + * in reset). For now I chose to keep this driver away from + * those SoC specific bits and assume the device-tree is + * right and the SCU has been configured properly by pinmux + * or the firmware. + */ + if (priv->is_aspeed && !(phy_interface_mode_is_rgmii(phy_intf))) { + netdev_warn(netdev, + "Unsupported PHY mode %s !\n", + phy_modes(phy_intf)); + } phydev = phy_find_first(priv->mii_bus); if (!phydev) { @@ -1056,7 +1085,7 @@ static int ftgmac100_mii_probe(struct ftgmac100 *priv, phy_interface_t intf) } phydev = phy_connect(netdev, phydev_name(phydev), - &ftgmac100_adjust_link, intf); + &ftgmac100_adjust_link, phy_intf); if (IS_ERR(phydev)) { netdev_err(netdev, "%s: Could not attach to PHY\n", netdev->name); @@ -1601,8 +1630,8 @@ static int ftgmac100_setup_mdio(struct net_device *netdev) { struct ftgmac100 *priv = netdev_priv(netdev); struct platform_device *pdev = to_platform_device(priv->dev); - phy_interface_t phy_intf = PHY_INTERFACE_MODE_RGMII; struct device_node *np = pdev->dev.of_node; + struct device_node *mdio_np; int i, err = 0; u32 reg; @@ -1623,39 +1652,6 @@ static int ftgmac100_setup_mdio(struct net_device *netdev) iowrite32(reg, priv->base + FTGMAC100_OFFSET_REVR); } - /* Get PHY mode from device-tree */ - if (np) { - /* Default to RGMII. It's a gigabit part after all */ - err = of_get_phy_mode(np, &phy_intf); - if (err) - phy_intf = PHY_INTERFACE_MODE_RGMII; - - /* Aspeed only supports these. I don't know about other IP - * block vendors so I'm going to just let them through for - * now. Note that this is only a warning if for some obscure - * reason the DT really means to lie about it or it's a newer - * part we don't know about. - * - * On the Aspeed SoC there are additionally straps and SCU - * control bits that could tell us what the interface is - * (or allow us to configure it while the IP block is held - * in reset). For now I chose to keep this driver away from - * those SoC specific bits and assume the device-tree is - * right and the SCU has been configured properly by pinmux - * or the firmware. - */ - if (priv->is_aspeed && - phy_intf != PHY_INTERFACE_MODE_RMII && - phy_intf != PHY_INTERFACE_MODE_RGMII && - phy_intf != PHY_INTERFACE_MODE_RGMII_ID && - phy_intf != PHY_INTERFACE_MODE_RGMII_RXID && - phy_intf != PHY_INTERFACE_MODE_RGMII_TXID) { - netdev_warn(netdev, - "Unsupported PHY mode %s !\n", - phy_modes(phy_intf)); - } - } - priv->mii_bus->name = "ftgmac100_mdio"; snprintf(priv->mii_bus->id, MII_BUS_ID_SIZE, "%s-%d", pdev->name, pdev->id); @@ -1667,35 +1663,38 @@ static int ftgmac100_setup_mdio(struct net_device *netdev) for (i = 0; i < PHY_MAX_ADDR; i++) priv->mii_bus->irq[i] = PHY_POLL; - err = mdiobus_register(priv->mii_bus); + mdio_np = of_get_child_by_name(np, "mdio"); + + err = of_mdiobus_register(priv->mii_bus, mdio_np); if (err) { dev_err(priv->dev, "Cannot register MDIO bus!\n"); goto err_register_mdiobus; } - err = ftgmac100_mii_probe(priv, phy_intf); - if (err) { - dev_err(priv->dev, "MII Probe failed!\n"); - goto err_mii_probe; - } + of_node_put(mdio_np); return 0; -err_mii_probe: - mdiobus_unregister(priv->mii_bus); err_register_mdiobus: mdiobus_free(priv->mii_bus); return err; } +static void ftgmac100_phy_disconnect(struct net_device *netdev) +{ + if (!netdev->phydev) + return; + + phy_disconnect(netdev->phydev); +} + static void ftgmac100_destroy_mdio(struct net_device *netdev) { struct ftgmac100 *priv = netdev_priv(netdev); - if (!netdev->phydev) + if (!priv->mii_bus) return; - phy_disconnect(netdev->phydev); mdiobus_unregister(priv->mii_bus); mdiobus_free(priv->mii_bus); } @@ -1830,22 +1829,33 @@ static int ftgmac100_probe(struct platform_device *pdev) if (np && of_get_property(np, "use-ncsi", NULL)) { if (!IS_ENABLED(CONFIG_NET_NCSI)) { dev_err(&pdev->dev, "NCSI stack not enabled\n"); - goto err_ncsi_dev; + goto err_phy_connect; } dev_info(&pdev->dev, "Using NCSI interface\n"); priv->use_ncsi = true; priv->ndev = ncsi_register_dev(netdev, ftgmac100_ncsi_handler); if (!priv->ndev) - goto err_ncsi_dev; + goto err_phy_connect; } else if (np && of_get_property(np, "phy-handle", NULL)) { struct phy_device *phy; + /* Support "mdio"/"phy" child nodes for ast2400/2500 with + * an embedded MDIO controller. Automatically scan the DTS for + * available PHYs and register them. + */ + if (of_device_is_compatible(np, "aspeed,ast2400-mac") || + of_device_is_compatible(np, "aspeed,ast2500-mac")) { + err = ftgmac100_setup_mdio(netdev); + if (err) + goto err_setup_mdio; + } + phy = of_phy_get_and_connect(priv->netdev, np, &ftgmac100_adjust_link); if (!phy) { dev_err(&pdev->dev, "Failed to connect to phy\n"); - goto err_setup_mdio; + goto err_phy_connect; } /* Indicate that we support PAUSE frames (see comment in @@ -1865,12 +1875,19 @@ static int ftgmac100_probe(struct platform_device *pdev) err = ftgmac100_setup_mdio(netdev); if (err) goto err_setup_mdio; + + err = ftgmac100_mii_probe(netdev); + if (err) { + dev_err(priv->dev, "MII probe failed!\n"); + goto err_ncsi_dev; + } + } if (priv->is_aspeed) { err = ftgmac100_setup_clk(priv); if (err) - goto err_ncsi_dev; + goto err_phy_connect; } /* Default ring sizes */ @@ -1906,6 +1923,8 @@ static int ftgmac100_probe(struct platform_device *pdev) err_register_netdev: clk_disable_unprepare(priv->rclk); clk_disable_unprepare(priv->clk); +err_phy_connect: + ftgmac100_phy_disconnect(netdev); err_ncsi_dev: ftgmac100_destroy_mdio(netdev); err_setup_mdio: @@ -1936,6 +1955,7 @@ static int ftgmac100_remove(struct platform_device *pdev) */ cancel_work_sync(&priv->reset_task); + ftgmac100_phy_disconnect(netdev); ftgmac100_destroy_mdio(netdev); iounmap(priv->base); diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index d9c285948fc2..8867693e0fb3 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -2305,9 +2305,9 @@ static void dpaa_tx_conf(struct net_device *net_dev, } static inline int dpaa_eth_napi_schedule(struct dpaa_percpu_priv *percpu_priv, - struct qman_portal *portal) + struct qman_portal *portal, bool sched_napi) { - if (unlikely(in_irq() || !in_serving_softirq())) { + if (sched_napi) { /* Disable QMan IRQ and invoke NAPI */ qman_p_irqsource_remove(portal, QM_PIRQ_DQRI); @@ -2321,7 +2321,8 @@ static inline int dpaa_eth_napi_schedule(struct dpaa_percpu_priv *percpu_priv, static enum qman_cb_dqrr_result rx_error_dqrr(struct qman_portal *portal, struct qman_fq *fq, - const struct qm_dqrr_entry *dq) + const struct qm_dqrr_entry *dq, + bool sched_napi) { struct dpaa_fq *dpaa_fq = container_of(fq, struct dpaa_fq, fq_base); struct dpaa_percpu_priv *percpu_priv; @@ -2337,7 +2338,7 @@ static enum qman_cb_dqrr_result rx_error_dqrr(struct qman_portal *portal, percpu_priv = this_cpu_ptr(priv->percpu_priv); - if (dpaa_eth_napi_schedule(percpu_priv, portal)) + if (dpaa_eth_napi_schedule(percpu_priv, portal, sched_napi)) return qman_cb_dqrr_stop; dpaa_eth_refill_bpools(priv); @@ -2348,7 +2349,8 @@ static enum qman_cb_dqrr_result rx_error_dqrr(struct qman_portal *portal, static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal, struct qman_fq *fq, - const struct qm_dqrr_entry *dq) + const struct qm_dqrr_entry *dq, + bool sched_napi) { struct skb_shared_hwtstamps *shhwtstamps; struct rtnl_link_stats64 *percpu_stats; @@ -2380,7 +2382,7 @@ static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal, percpu_priv = this_cpu_ptr(priv->percpu_priv); percpu_stats = &percpu_priv->stats; - if (unlikely(dpaa_eth_napi_schedule(percpu_priv, portal))) + if (unlikely(dpaa_eth_napi_schedule(percpu_priv, portal, sched_napi))) return qman_cb_dqrr_stop; /* Make sure we didn't run out of buffers */ @@ -2465,7 +2467,8 @@ static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal, static enum qman_cb_dqrr_result conf_error_dqrr(struct qman_portal *portal, struct qman_fq *fq, - const struct qm_dqrr_entry *dq) + const struct qm_dqrr_entry *dq, + bool sched_napi) { struct dpaa_percpu_priv *percpu_priv; struct net_device *net_dev; @@ -2476,7 +2479,7 @@ static enum qman_cb_dqrr_result conf_error_dqrr(struct qman_portal *portal, percpu_priv = this_cpu_ptr(priv->percpu_priv); - if (dpaa_eth_napi_schedule(percpu_priv, portal)) + if (dpaa_eth_napi_schedule(percpu_priv, portal, sched_napi)) return qman_cb_dqrr_stop; dpaa_tx_error(net_dev, priv, percpu_priv, &dq->fd, fq->fqid); @@ -2486,7 +2489,8 @@ static enum qman_cb_dqrr_result conf_error_dqrr(struct qman_portal *portal, static enum qman_cb_dqrr_result conf_dflt_dqrr(struct qman_portal *portal, struct qman_fq *fq, - const struct qm_dqrr_entry *dq) + const struct qm_dqrr_entry *dq, + bool sched_napi) { struct dpaa_percpu_priv *percpu_priv; struct net_device *net_dev; @@ -2500,7 +2504,7 @@ static enum qman_cb_dqrr_result conf_dflt_dqrr(struct qman_portal *portal, percpu_priv = this_cpu_ptr(priv->percpu_priv); - if (dpaa_eth_napi_schedule(percpu_priv, portal)) + if (dpaa_eth_napi_schedule(percpu_priv, portal, sched_napi)) return qman_cb_dqrr_stop; dpaa_tx_conf(net_dev, priv, percpu_priv, &dq->fd, fq->fqid); @@ -2546,7 +2550,7 @@ static void dpaa_eth_napi_enable(struct dpaa_priv *priv) for_each_online_cpu(i) { percpu_priv = per_cpu_ptr(priv->percpu_priv, i); - percpu_priv->np.down = 0; + percpu_priv->np.down = false; napi_enable(&percpu_priv->np.napi); } } @@ -2559,7 +2563,7 @@ static void dpaa_eth_napi_disable(struct dpaa_priv *priv) for_each_online_cpu(i) { percpu_priv = per_cpu_ptr(priv->percpu_priv, i); - percpu_priv->np.down = 1; + percpu_priv->np.down = true; napi_disable(&percpu_priv->np.napi); } } diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 52be6e315752..01089c30b462 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -47,40 +47,6 @@ drop_packet_err: return NETDEV_TX_OK; } -static bool enetc_tx_csum(struct sk_buff *skb, union enetc_tx_bd *txbd) -{ - int l3_start, l3_hsize; - u16 l3_flags, l4_flags; - - if (skb->ip_summed != CHECKSUM_PARTIAL) - return false; - - switch (skb->csum_offset) { - case offsetof(struct tcphdr, check): - l4_flags = ENETC_TXBD_L4_TCP; - break; - case offsetof(struct udphdr, check): - l4_flags = ENETC_TXBD_L4_UDP; - break; - default: - skb_checksum_help(skb); - return false; - } - - l3_start = skb_network_offset(skb); - l3_hsize = skb_network_header_len(skb); - - l3_flags = 0; - if (skb->protocol == htons(ETH_P_IPV6)) - l3_flags = ENETC_TXBD_L3_IPV6; - - /* write BD fields */ - txbd->l3_csoff = enetc_txbd_l3_csoff(l3_start, l3_hsize, l3_flags); - txbd->l4_csoff = l4_flags; - - return true; -} - static void enetc_unmap_tx_buff(struct enetc_bdr *tx_ring, struct enetc_tx_swbd *tx_swbd) { @@ -146,22 +112,16 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb, if (do_vlan || do_tstamp) flags |= ENETC_TXBD_FLAGS_EX; - if (enetc_tx_csum(skb, &temp_bd)) - flags |= ENETC_TXBD_FLAGS_CSUM | ENETC_TXBD_FLAGS_L4CS; - else if (tx_ring->tsd_enable) + if (tx_ring->tsd_enable) flags |= ENETC_TXBD_FLAGS_TSE | ENETC_TXBD_FLAGS_TXSTART; /* first BD needs frm_len and offload flags set */ temp_bd.frm_len = cpu_to_le16(skb->len); temp_bd.flags = flags; - if (flags & ENETC_TXBD_FLAGS_TSE) { - u32 temp; - - temp = (skb->skb_mstamp_ns >> 5 & ENETC_TXBD_TXSTART_MASK) - | (flags << ENETC_TXBD_FLAGS_OFFSET); - temp_bd.txstart = cpu_to_le32(temp); - } + if (flags & ENETC_TXBD_FLAGS_TSE) + temp_bd.txstart = enetc_txbd_set_tx_start(skb->skb_mstamp_ns, + flags); if (flags & ENETC_TXBD_FLAGS_EX) { u8 e_flags = 0; @@ -1897,8 +1857,7 @@ static void enetc_kfree_si(struct enetc_si *si) static void enetc_detect_errata(struct enetc_si *si) { if (si->pdev->revision == ENETC_REV1) - si->errata = ENETC_ERR_TXCSUM | ENETC_ERR_VLAN_ISOL | - ENETC_ERR_UCMCSWP; + si->errata = ENETC_ERR_VLAN_ISOL | ENETC_ERR_UCMCSWP; } int enetc_pci_probe(struct pci_dev *pdev, const char *name, int sizeof_priv) diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h index dd0fb0c066d7..8532d23b54f5 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.h +++ b/drivers/net/ethernet/freescale/enetc/enetc.h @@ -147,9 +147,8 @@ struct enetc_msg_swbd { #define ENETC_REV1 0x1 enum enetc_errata { - ENETC_ERR_TXCSUM = BIT(0), - ENETC_ERR_VLAN_ISOL = BIT(1), - ENETC_ERR_UCMCSWP = BIT(2), + ENETC_ERR_VLAN_ISOL = BIT(0), + ENETC_ERR_UCMCSWP = BIT(1), }; #define ENETC_SI_F_QBV BIT(0) diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h index 17cf7c94fdb5..68ef4f959982 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h +++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h @@ -374,8 +374,7 @@ union enetc_tx_bd { __le16 frm_len; union { struct { - __le16 l3_csoff; - u8 l4_csoff; + u8 reserved[3]; u8 flags; }; /* default layout */ __le32 txstart; @@ -398,41 +397,37 @@ union enetc_tx_bd { } wb; /* writeback descriptor */ }; -#define ENETC_TXBD_FLAGS_L4CS BIT(0) -#define ENETC_TXBD_FLAGS_TSE BIT(1) -#define ENETC_TXBD_FLAGS_W BIT(2) -#define ENETC_TXBD_FLAGS_CSUM BIT(3) -#define ENETC_TXBD_FLAGS_TXSTART BIT(4) -#define ENETC_TXBD_FLAGS_EX BIT(6) -#define ENETC_TXBD_FLAGS_F BIT(7) +enum enetc_txbd_flags { + ENETC_TXBD_FLAGS_RES0 = BIT(0), /* reserved */ + ENETC_TXBD_FLAGS_TSE = BIT(1), + ENETC_TXBD_FLAGS_W = BIT(2), + ENETC_TXBD_FLAGS_RES3 = BIT(3), /* reserved */ + ENETC_TXBD_FLAGS_TXSTART = BIT(4), + ENETC_TXBD_FLAGS_EX = BIT(6), + ENETC_TXBD_FLAGS_F = BIT(7) +}; #define ENETC_TXBD_TXSTART_MASK GENMASK(24, 0) #define ENETC_TXBD_FLAGS_OFFSET 24 + +static inline __le32 enetc_txbd_set_tx_start(u64 tx_start, u8 flags) +{ + u32 temp; + + temp = (tx_start >> 5 & ENETC_TXBD_TXSTART_MASK) | + (flags << ENETC_TXBD_FLAGS_OFFSET); + + return cpu_to_le32(temp); +} + static inline void enetc_clear_tx_bd(union enetc_tx_bd *txbd) { memset(txbd, 0, sizeof(*txbd)); } -/* L3 csum flags */ -#define ENETC_TXBD_L3_IPCS BIT(7) -#define ENETC_TXBD_L3_IPV6 BIT(15) - -#define ENETC_TXBD_L3_START_MASK GENMASK(6, 0) -#define ENETC_TXBD_L3_SET_HSIZE(val) ((((val) >> 2) & 0x7f) << 8) - /* Extension flags */ #define ENETC_TXBD_E_FLAGS_VLAN_INS BIT(0) #define ENETC_TXBD_E_FLAGS_TWO_STEP_PTP BIT(2) -static inline __le16 enetc_txbd_l3_csoff(int start, int hdr_sz, u16 l3_flags) -{ - return cpu_to_le16(l3_flags | ENETC_TXBD_L3_SET_HSIZE(hdr_sz) | - (start & ENETC_TXBD_L3_START_MASK)); -} - -/* L4 csum flags */ -#define ENETC_TXBD_L4_UDP BIT(5) -#define ENETC_TXBD_L4_TCP BIT(6) - union enetc_rx_bd { struct { __le64 addr; diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index 419306342ac5..ecdc2af8c292 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -714,22 +714,16 @@ static void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev, ndev->watchdog_timeo = 5 * HZ; ndev->max_mtu = ENETC_MAX_MTU; - ndev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM | NETIF_F_HW_CSUM | + ndev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_LOOPBACK; - ndev->features = NETIF_F_HIGHDMA | NETIF_F_SG | - NETIF_F_RXCSUM | NETIF_F_HW_CSUM | + ndev->features = NETIF_F_HIGHDMA | NETIF_F_SG | NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX; if (si->num_rss) ndev->hw_features |= NETIF_F_RXHASH; - if (si->errata & ENETC_ERR_TXCSUM) { - ndev->hw_features &= ~NETIF_F_HW_CSUM; - ndev->features &= ~NETIF_F_HW_CSUM; - } - ndev->priv_flags |= IFF_UNICAST_FLT; if (si->hw_features & ENETC_SI_F_QBV) diff --git a/drivers/net/ethernet/freescale/enetc/enetc_vf.c b/drivers/net/ethernet/freescale/enetc/enetc_vf.c index 7b5c82c7e4e5..39c1a09e69a9 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_vf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_vf.c @@ -120,22 +120,16 @@ static void enetc_vf_netdev_setup(struct enetc_si *si, struct net_device *ndev, ndev->watchdog_timeo = 5 * HZ; ndev->max_mtu = ENETC_MAX_MTU; - ndev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM | NETIF_F_HW_CSUM | + ndev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX; - ndev->features = NETIF_F_HIGHDMA | NETIF_F_SG | - NETIF_F_RXCSUM | NETIF_F_HW_CSUM | + ndev->features = NETIF_F_HIGHDMA | NETIF_F_SG | NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX; if (si->num_rss) ndev->hw_features |= NETIF_F_RXHASH; - if (si->errata & ENETC_ERR_TXCSUM) { - ndev->hw_features &= ~NETIF_F_HW_CSUM; - ndev->features &= ~NETIF_F_HW_CSUM; - } - /* pick up primary MAC address from SI */ enetc_get_primary_mac_addr(&si->hw, ndev->dev_addr); } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c index 3606240025a8..f990f6915226 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c @@ -4,7 +4,6 @@ #include "hclge_main.h" #include "hclge_dcb.h" #include "hclge_tm.h" -#include "hclge_dcb.h" #include "hnae3.h" #define BW_PERCENT 100 diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c index 8f17e26dca53..7d0f96290943 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c @@ -145,6 +145,16 @@ int cgx_get_cgxid(void *cgxd) return cgx->cgx_id; } +u8 cgx_lmac_get_p2x(int cgx_id, int lmac_id) +{ + struct cgx *cgx_dev = cgx_get_pdata(cgx_id); + u64 cfg; + + cfg = cgx_read(cgx_dev, lmac_id, CGXX_CMRX_CFG); + + return (cfg & CMR_P2X_SEL_MASK) >> CMR_P2X_SEL_SHIFT; +} + /* Ensure the required lock for event queue(where asynchronous events are * posted) is acquired before calling this API. Else an asynchronous event(with * latest link status) can reach the destination before this function returns @@ -814,8 +824,7 @@ static int cgx_lmac_verify_fwi_version(struct cgx *cgx) minor_ver = FIELD_GET(RESP_MINOR_VER, resp); dev_dbg(dev, "Firmware command interface version = %d.%d\n", major_ver, minor_ver); - if (major_ver != CGX_FIRMWARE_MAJOR_VER || - minor_ver != CGX_FIRMWARE_MINOR_VER) + if (major_ver != CGX_FIRMWARE_MAJOR_VER) return -EIO; else return 0; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h index 27ca3291682b..bcfc3e5f66bb 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.h @@ -27,6 +27,10 @@ /* Registers */ #define CGXX_CMRX_CFG 0x00 +#define CMR_P2X_SEL_MASK GENMASK_ULL(61, 59) +#define CMR_P2X_SEL_SHIFT 59ULL +#define CMR_P2X_SEL_NIX0 1ULL +#define CMR_P2X_SEL_NIX1 2ULL #define CMR_EN BIT_ULL(55) #define DATA_PKT_TX_EN BIT_ULL(53) #define DATA_PKT_RX_EN BIT_ULL(54) @@ -142,5 +146,6 @@ int cgx_lmac_get_pause_frm(void *cgxd, int lmac_id, int cgx_lmac_set_pause_frm(void *cgxd, int lmac_id, u8 tx_pause, u8 rx_pause); void cgx_lmac_ptp_config(void *cgxd, int lmac_id, bool enable); +u8 cgx_lmac_get_p2x(int cgx_id, int lmac_id); #endif /* CGX_H */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/common.h b/drivers/net/ethernet/marvell/octeontx2/af/common.h index f48eb66ed021..8f68e7a8b882 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/common.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/common.h @@ -174,8 +174,12 @@ enum nix_scheduler { #define NPC_MCAM_KEY_X2 1 #define NPC_MCAM_KEY_X4 2 -#define NIX_INTF_RX 0 -#define NIX_INTF_TX 1 +#define NIX_INTFX_RX(a) (0x0ull | (a) << 1) +#define NIX_INTFX_TX(a) (0x1ull | (a) << 1) + +/* Default interfaces are NIX0_RX and NIX0_TX */ +#define NIX_INTF_RX NIX_INTFX_RX(0) +#define NIX_INTF_TX NIX_INTFX_TX(0) #define NIX_INTF_TYPE_CGX 0 #define NIX_INTF_TYPE_LBK 1 @@ -206,6 +210,8 @@ enum ndc_idx_e { NIX0_RX = 0x0, NIX0_TX = 0x1, NPA0_U = 0x2, + NIX1_RX = 0x4, + NIX1_TX = 0x5, }; enum ndc_ctype_e { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index 263a21129416..f46de8419b77 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -86,7 +86,7 @@ struct mbox_msghdr { #define OTX2_MBOX_REQ_SIG (0xdead) #define OTX2_MBOX_RSP_SIG (0xbeef) u16 sig; /* Signature, for validating corrupted msgs */ -#define OTX2_MBOX_VERSION (0x0001) +#define OTX2_MBOX_VERSION (0x0007) u16 ver; /* Version of msg's structure for this ID */ u16 next_msgoff; /* Offset of next msg within mailbox region */ int rc; /* Msg process'ed response code */ @@ -271,6 +271,17 @@ struct ready_msg_rsp { * or to detach partial of a cetain resource type. * Rest of the fields specify how many of what type to * be attached. + * To request LFs from two blocks of same type this mailbox + * can be sent twice as below: + * struct rsrc_attach *attach; + * .. Allocate memory for message .. + * attach->cptlfs = 3; <3 LFs from CPT0> + * .. Send message .. + * .. Allocate memory for message .. + * attach->modify = 1; + * attach->cpt_blkaddr = BLKADDR_CPT1; + * attach->cptlfs = 2; <2 LFs from CPT1> + * .. Send message .. */ struct rsrc_attach { struct mbox_msghdr hdr; @@ -281,6 +292,7 @@ struct rsrc_attach { u16 ssow; u16 timlfs; u16 cptlfs; + int cpt_blkaddr; /* BLKADDR_CPT0/BLKADDR_CPT1 or 0 for BLKADDR_CPT0 */ }; /* Structure for relinquishing resources. @@ -314,6 +326,8 @@ struct msix_offset_rsp { u16 ssow_msixoff[MAX_RVU_BLKLF_CNT]; u16 timlf_msixoff[MAX_RVU_BLKLF_CNT]; u16 cptlf_msixoff[MAX_RVU_BLKLF_CNT]; + u8 cpt1_lfs; + u16 cpt1_lf_msixoff[MAX_RVU_BLKLF_CNT]; }; struct get_hw_cap_rsp { @@ -491,6 +505,9 @@ struct nix_lf_alloc_rsp { u8 lf_tx_stats; /* NIX_AF_CONST1::LF_TX_STATS */ u16 cints; /* NIX_AF_CONST2::CINTS */ u16 qints; /* NIX_AF_CONST2::QINTS */ + u8 cgx_links; /* No. of CGX links present in HW */ + u8 lbk_links; /* No. of LBK links present in HW */ + u8 sdp_links; /* No. of SDP links present in HW */ }; /* NIX AQ enqueue msg */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h b/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h index 77bb4ed32600..199448610e3e 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/npc_profile.h @@ -13380,7 +13380,7 @@ static const struct npc_lt_def_cfg npc_lt_defaults = { }, }; -static const struct npc_mcam_kex npc_mkex_default = { +static struct npc_mcam_kex npc_mkex_default = { .mkex_sign = MKEX_SIGN, .name = "default", .kpu_version = NPC_KPU_PROFILE_VER, diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index e1f918960730..a28a518c0eae 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -66,6 +66,7 @@ static void rvu_setup_hw_capabilities(struct rvu *rvu) hw->cap.nix_shaping = true; hw->cap.nix_tx_link_bp = true; hw->cap.nix_rx_multicast = true; + hw->rvu = rvu; if (is_rvu_96xx_B0(rvu)) { hw->cap.nix_fixed_txschq_mapping = true; @@ -210,6 +211,9 @@ int rvu_get_lf(struct rvu *rvu, struct rvu_block *block, u16 pcifunc, u16 slot) * multiple blocks of same type. * * @pcifunc has to be zero when no LF is yet attached. + * + * For a pcifunc if LFs are attached from multiple blocks of same type, then + * return blkaddr of first encountered block. */ int rvu_get_blkaddr(struct rvu *rvu, int blktype, u16 pcifunc) { @@ -258,20 +262,39 @@ int rvu_get_blkaddr(struct rvu *rvu, int blktype, u16 pcifunc) devnum = rvu_get_pf(pcifunc); } - /* Check if the 'pcifunc' has a NIX LF from 'BLKADDR_NIX0' */ + /* Check if the 'pcifunc' has a NIX LF from 'BLKADDR_NIX0' or + * 'BLKADDR_NIX1'. + */ if (blktype == BLKTYPE_NIX) { - reg = is_pf ? RVU_PRIV_PFX_NIX0_CFG : RVU_PRIV_HWVFX_NIX0_CFG; + reg = is_pf ? RVU_PRIV_PFX_NIXX_CFG(0) : + RVU_PRIV_HWVFX_NIXX_CFG(0); cfg = rvu_read64(rvu, BLKADDR_RVUM, reg | (devnum << 16)); - if (cfg) + if (cfg) { blkaddr = BLKADDR_NIX0; + goto exit; + } + + reg = is_pf ? RVU_PRIV_PFX_NIXX_CFG(1) : + RVU_PRIV_HWVFX_NIXX_CFG(1); + cfg = rvu_read64(rvu, BLKADDR_RVUM, reg | (devnum << 16)); + if (cfg) + blkaddr = BLKADDR_NIX1; } - /* Check if the 'pcifunc' has a CPT LF from 'BLKADDR_CPT0' */ if (blktype == BLKTYPE_CPT) { - reg = is_pf ? RVU_PRIV_PFX_CPT0_CFG : RVU_PRIV_HWVFX_CPT0_CFG; + reg = is_pf ? RVU_PRIV_PFX_CPTX_CFG(0) : + RVU_PRIV_HWVFX_CPTX_CFG(0); cfg = rvu_read64(rvu, BLKADDR_RVUM, reg | (devnum << 16)); - if (cfg) + if (cfg) { blkaddr = BLKADDR_CPT0; + goto exit; + } + + reg = is_pf ? RVU_PRIV_PFX_CPTX_CFG(1) : + RVU_PRIV_HWVFX_CPTX_CFG(1); + cfg = rvu_read64(rvu, BLKADDR_RVUM, reg | (devnum << 16)); + if (cfg) + blkaddr = BLKADDR_CPT1; } exit: @@ -306,31 +329,36 @@ static void rvu_update_rsrc_map(struct rvu *rvu, struct rvu_pfvf *pfvf, block->fn_map[lf] = attach ? pcifunc : 0; - switch (block->type) { - case BLKTYPE_NPA: + switch (block->addr) { + case BLKADDR_NPA: pfvf->npalf = attach ? true : false; num_lfs = pfvf->npalf; break; - case BLKTYPE_NIX: + case BLKADDR_NIX0: + case BLKADDR_NIX1: pfvf->nixlf = attach ? true : false; num_lfs = pfvf->nixlf; break; - case BLKTYPE_SSO: + case BLKADDR_SSO: attach ? pfvf->sso++ : pfvf->sso--; num_lfs = pfvf->sso; break; - case BLKTYPE_SSOW: + case BLKADDR_SSOW: attach ? pfvf->ssow++ : pfvf->ssow--; num_lfs = pfvf->ssow; break; - case BLKTYPE_TIM: + case BLKADDR_TIM: attach ? pfvf->timlfs++ : pfvf->timlfs--; num_lfs = pfvf->timlfs; break; - case BLKTYPE_CPT: + case BLKADDR_CPT0: attach ? pfvf->cptlfs++ : pfvf->cptlfs--; num_lfs = pfvf->cptlfs; break; + case BLKADDR_CPT1: + attach ? pfvf->cpt1_lfs++ : pfvf->cpt1_lfs--; + num_lfs = pfvf->cpt1_lfs; + break; } reg = is_pf ? block->pf_lfcnt_reg : block->vf_lfcnt_reg; @@ -466,12 +494,16 @@ static void rvu_reset_all_blocks(struct rvu *rvu) /* Do a HW reset of all RVU blocks */ rvu_block_reset(rvu, BLKADDR_NPA, NPA_AF_BLK_RST); rvu_block_reset(rvu, BLKADDR_NIX0, NIX_AF_BLK_RST); + rvu_block_reset(rvu, BLKADDR_NIX1, NIX_AF_BLK_RST); rvu_block_reset(rvu, BLKADDR_NPC, NPC_AF_BLK_RST); rvu_block_reset(rvu, BLKADDR_SSO, SSO_AF_BLK_RST); rvu_block_reset(rvu, BLKADDR_TIM, TIM_AF_BLK_RST); rvu_block_reset(rvu, BLKADDR_CPT0, CPT_AF_BLK_RST); + rvu_block_reset(rvu, BLKADDR_CPT1, CPT_AF_BLK_RST); rvu_block_reset(rvu, BLKADDR_NDC_NIX0_RX, NDC_AF_BLK_RST); rvu_block_reset(rvu, BLKADDR_NDC_NIX0_TX, NDC_AF_BLK_RST); + rvu_block_reset(rvu, BLKADDR_NDC_NIX1_RX, NDC_AF_BLK_RST); + rvu_block_reset(rvu, BLKADDR_NDC_NIX1_TX, NDC_AF_BLK_RST); rvu_block_reset(rvu, BLKADDR_NDC_NPA0, NDC_AF_BLK_RST); } @@ -757,6 +789,62 @@ static void rvu_fwdata_exit(struct rvu *rvu) iounmap(rvu->fwdata); } +static int rvu_setup_nix_hw_resource(struct rvu *rvu, int blkaddr) +{ + struct rvu_hwinfo *hw = rvu->hw; + struct rvu_block *block; + int blkid; + u64 cfg; + + /* Init NIX LF's bitmap */ + block = &hw->block[blkaddr]; + if (!block->implemented) + return 0; + blkid = (blkaddr == BLKADDR_NIX0) ? 0 : 1; + cfg = rvu_read64(rvu, blkaddr, NIX_AF_CONST2); + block->lf.max = cfg & 0xFFF; + block->addr = blkaddr; + block->type = BLKTYPE_NIX; + block->lfshift = 8; + block->lookup_reg = NIX_AF_RVU_LF_CFG_DEBUG; + block->pf_lfcnt_reg = RVU_PRIV_PFX_NIXX_CFG(blkid); + block->vf_lfcnt_reg = RVU_PRIV_HWVFX_NIXX_CFG(blkid); + block->lfcfg_reg = NIX_PRIV_LFX_CFG; + block->msixcfg_reg = NIX_PRIV_LFX_INT_CFG; + block->lfreset_reg = NIX_AF_LF_RST; + sprintf(block->name, "NIX%d", blkid); + rvu->nix_blkaddr[blkid] = blkaddr; + return rvu_alloc_bitmap(&block->lf); +} + +static int rvu_setup_cpt_hw_resource(struct rvu *rvu, int blkaddr) +{ + struct rvu_hwinfo *hw = rvu->hw; + struct rvu_block *block; + int blkid; + u64 cfg; + + /* Init CPT LF's bitmap */ + block = &hw->block[blkaddr]; + if (!block->implemented) + return 0; + blkid = (blkaddr == BLKADDR_CPT0) ? 0 : 1; + cfg = rvu_read64(rvu, blkaddr, CPT_AF_CONSTANTS0); + block->lf.max = cfg & 0xFF; + block->addr = blkaddr; + block->type = BLKTYPE_CPT; + block->multislot = true; + block->lfshift = 3; + block->lookup_reg = CPT_AF_RVU_LF_CFG_DEBUG; + block->pf_lfcnt_reg = RVU_PRIV_PFX_CPTX_CFG(blkid); + block->vf_lfcnt_reg = RVU_PRIV_HWVFX_CPTX_CFG(blkid); + block->lfcfg_reg = CPT_PRIV_LFX_CFG; + block->msixcfg_reg = CPT_PRIV_LFX_INT_CFG; + block->lfreset_reg = CPT_AF_LF_RST; + sprintf(block->name, "CPT%d", blkid); + return rvu_alloc_bitmap(&block->lf); +} + static int rvu_setup_hw_resources(struct rvu *rvu) { struct rvu_hwinfo *hw = rvu->hw; @@ -791,27 +879,13 @@ static int rvu_setup_hw_resources(struct rvu *rvu) return err; nix: - /* Init NIX LF's bitmap */ - block = &hw->block[BLKADDR_NIX0]; - if (!block->implemented) - goto sso; - cfg = rvu_read64(rvu, BLKADDR_NIX0, NIX_AF_CONST2); - block->lf.max = cfg & 0xFFF; - block->addr = BLKADDR_NIX0; - block->type = BLKTYPE_NIX; - block->lfshift = 8; - block->lookup_reg = NIX_AF_RVU_LF_CFG_DEBUG; - block->pf_lfcnt_reg = RVU_PRIV_PFX_NIX0_CFG; - block->vf_lfcnt_reg = RVU_PRIV_HWVFX_NIX0_CFG; - block->lfcfg_reg = NIX_PRIV_LFX_CFG; - block->msixcfg_reg = NIX_PRIV_LFX_INT_CFG; - block->lfreset_reg = NIX_AF_LF_RST; - sprintf(block->name, "NIX"); - err = rvu_alloc_bitmap(&block->lf); + err = rvu_setup_nix_hw_resource(rvu, BLKADDR_NIX0); + if (err) + return err; + err = rvu_setup_nix_hw_resource(rvu, BLKADDR_NIX1); if (err) return err; -sso: /* Init SSO group's bitmap */ block = &hw->block[BLKADDR_SSO]; if (!block->implemented) @@ -877,28 +951,13 @@ tim: return err; cpt: - /* Init CPT LF's bitmap */ - block = &hw->block[BLKADDR_CPT0]; - if (!block->implemented) - goto init; - cfg = rvu_read64(rvu, BLKADDR_CPT0, CPT_AF_CONSTANTS0); - block->lf.max = cfg & 0xFF; - block->addr = BLKADDR_CPT0; - block->type = BLKTYPE_CPT; - block->multislot = true; - block->lfshift = 3; - block->lookup_reg = CPT_AF_RVU_LF_CFG_DEBUG; - block->pf_lfcnt_reg = RVU_PRIV_PFX_CPT0_CFG; - block->vf_lfcnt_reg = RVU_PRIV_HWVFX_CPT0_CFG; - block->lfcfg_reg = CPT_PRIV_LFX_CFG; - block->msixcfg_reg = CPT_PRIV_LFX_INT_CFG; - block->lfreset_reg = CPT_AF_LF_RST; - sprintf(block->name, "CPT"); - err = rvu_alloc_bitmap(&block->lf); + err = rvu_setup_cpt_hw_resource(rvu, BLKADDR_CPT0); + if (err) + return err; + err = rvu_setup_cpt_hw_resource(rvu, BLKADDR_CPT1); if (err) return err; -init: /* Allocate memory for PFVF data */ rvu->pf = devm_kcalloc(rvu->dev, hw->total_pfs, sizeof(struct rvu_pfvf), GFP_KERNEL); @@ -1025,7 +1084,30 @@ int rvu_mbox_handler_ready(struct rvu *rvu, struct msg_req *req, /* Get current count of a RVU block's LF/slots * provisioned to a given RVU func. */ -static u16 rvu_get_rsrc_mapcount(struct rvu_pfvf *pfvf, int blktype) +u16 rvu_get_rsrc_mapcount(struct rvu_pfvf *pfvf, int blkaddr) +{ + switch (blkaddr) { + case BLKADDR_NPA: + return pfvf->npalf ? 1 : 0; + case BLKADDR_NIX0: + case BLKADDR_NIX1: + return pfvf->nixlf ? 1 : 0; + case BLKADDR_SSO: + return pfvf->sso; + case BLKADDR_SSOW: + return pfvf->ssow; + case BLKADDR_TIM: + return pfvf->timlfs; + case BLKADDR_CPT0: + return pfvf->cptlfs; + case BLKADDR_CPT1: + return pfvf->cpt1_lfs; + } + return 0; +} + +/* Return true if LFs of block type are attached to pcifunc */ +static bool is_blktype_attached(struct rvu_pfvf *pfvf, int blktype) { switch (blktype) { case BLKTYPE_NPA: @@ -1033,15 +1115,16 @@ static u16 rvu_get_rsrc_mapcount(struct rvu_pfvf *pfvf, int blktype) case BLKTYPE_NIX: return pfvf->nixlf ? 1 : 0; case BLKTYPE_SSO: - return pfvf->sso; + return !!pfvf->sso; case BLKTYPE_SSOW: - return pfvf->ssow; + return !!pfvf->ssow; case BLKTYPE_TIM: - return pfvf->timlfs; + return !!pfvf->timlfs; case BLKTYPE_CPT: - return pfvf->cptlfs; + return pfvf->cptlfs || pfvf->cpt1_lfs; } - return 0; + + return false; } bool is_pffunc_map_valid(struct rvu *rvu, u16 pcifunc, int blktype) @@ -1054,7 +1137,7 @@ bool is_pffunc_map_valid(struct rvu *rvu, u16 pcifunc, int blktype) pfvf = rvu_get_pfvf(rvu, pcifunc); /* Check if this PFFUNC has a LF of type blktype attached */ - if (!rvu_get_rsrc_mapcount(pfvf, blktype)) + if (!is_blktype_attached(pfvf, blktype)) return false; return true; @@ -1095,7 +1178,7 @@ static void rvu_detach_block(struct rvu *rvu, int pcifunc, int blktype) block = &hw->block[blkaddr]; - num_lfs = rvu_get_rsrc_mapcount(pfvf, block->type); + num_lfs = rvu_get_rsrc_mapcount(pfvf, block->addr); if (!num_lfs) return; @@ -1146,6 +1229,8 @@ static int rvu_detach_rsrcs(struct rvu *rvu, struct rsrc_detach *detach, continue; else if ((blkid == BLKADDR_NIX0) && !detach->nixlf) continue; + else if ((blkid == BLKADDR_NIX1) && !detach->nixlf) + continue; else if ((blkid == BLKADDR_SSO) && !detach->sso) continue; else if ((blkid == BLKADDR_SSOW) && !detach->ssow) @@ -1154,6 +1239,8 @@ static int rvu_detach_rsrcs(struct rvu *rvu, struct rsrc_detach *detach, continue; else if ((blkid == BLKADDR_CPT0) && !detach->cptlfs) continue; + else if ((blkid == BLKADDR_CPT1) && !detach->cptlfs) + continue; } rvu_detach_block(rvu, pcifunc, block->type); } @@ -1169,8 +1256,73 @@ int rvu_mbox_handler_detach_resources(struct rvu *rvu, return rvu_detach_rsrcs(rvu, detach, detach->hdr.pcifunc); } -static void rvu_attach_block(struct rvu *rvu, int pcifunc, - int blktype, int num_lfs) +static int rvu_get_nix_blkaddr(struct rvu *rvu, u16 pcifunc) +{ + struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc); + int blkaddr = BLKADDR_NIX0, vf; + struct rvu_pfvf *pf; + + /* All CGX mapped PFs are set with assigned NIX block during init */ + if (is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc))) { + pf = rvu_get_pfvf(rvu, pcifunc & ~RVU_PFVF_FUNC_MASK); + blkaddr = pf->nix_blkaddr; + } else if (is_afvf(pcifunc)) { + vf = pcifunc - 1; + /* Assign NIX based on VF number. All even numbered VFs get + * NIX0 and odd numbered gets NIX1 + */ + blkaddr = (vf & 1) ? BLKADDR_NIX1 : BLKADDR_NIX0; + /* NIX1 is not present on all silicons */ + if (!is_block_implemented(rvu->hw, BLKADDR_NIX1)) + blkaddr = BLKADDR_NIX0; + } + + switch (blkaddr) { + case BLKADDR_NIX1: + pfvf->nix_blkaddr = BLKADDR_NIX1; + pfvf->nix_rx_intf = NIX_INTFX_RX(1); + pfvf->nix_tx_intf = NIX_INTFX_TX(1); + break; + case BLKADDR_NIX0: + default: + pfvf->nix_blkaddr = BLKADDR_NIX0; + pfvf->nix_rx_intf = NIX_INTFX_RX(0); + pfvf->nix_tx_intf = NIX_INTFX_TX(0); + break; + } + + return pfvf->nix_blkaddr; +} + +static int rvu_get_attach_blkaddr(struct rvu *rvu, int blktype, + u16 pcifunc, struct rsrc_attach *attach) +{ + int blkaddr; + + switch (blktype) { + case BLKTYPE_NIX: + blkaddr = rvu_get_nix_blkaddr(rvu, pcifunc); + break; + case BLKTYPE_CPT: + if (attach->hdr.ver < RVU_MULTI_BLK_VER) + return rvu_get_blkaddr(rvu, blktype, 0); + blkaddr = attach->cpt_blkaddr ? attach->cpt_blkaddr : + BLKADDR_CPT0; + if (blkaddr != BLKADDR_CPT0 && blkaddr != BLKADDR_CPT1) + return -ENODEV; + break; + default: + return rvu_get_blkaddr(rvu, blktype, 0); + }; + + if (is_block_implemented(rvu->hw, blkaddr)) + return blkaddr; + + return -ENODEV; +} + +static void rvu_attach_block(struct rvu *rvu, int pcifunc, int blktype, + int num_lfs, struct rsrc_attach *attach) { struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc); struct rvu_hwinfo *hw = rvu->hw; @@ -1182,7 +1334,7 @@ static void rvu_attach_block(struct rvu *rvu, int pcifunc, if (!num_lfs) return; - blkaddr = rvu_get_blkaddr(rvu, blktype, 0); + blkaddr = rvu_get_attach_blkaddr(rvu, blktype, pcifunc, attach); if (blkaddr < 0) return; @@ -1211,12 +1363,12 @@ static int rvu_check_rsrc_availability(struct rvu *rvu, struct rsrc_attach *req, u16 pcifunc) { struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc); + int free_lfs, mappedlfs, blkaddr; struct rvu_hwinfo *hw = rvu->hw; struct rvu_block *block; - int free_lfs, mappedlfs; /* Only one NPA LF can be attached */ - if (req->npalf && !rvu_get_rsrc_mapcount(pfvf, BLKTYPE_NPA)) { + if (req->npalf && !is_blktype_attached(pfvf, BLKTYPE_NPA)) { block = &hw->block[BLKADDR_NPA]; free_lfs = rvu_rsrc_free_count(&block->lf); if (!free_lfs) @@ -1229,8 +1381,12 @@ static int rvu_check_rsrc_availability(struct rvu *rvu, } /* Only one NIX LF can be attached */ - if (req->nixlf && !rvu_get_rsrc_mapcount(pfvf, BLKTYPE_NIX)) { - block = &hw->block[BLKADDR_NIX0]; + if (req->nixlf && !is_blktype_attached(pfvf, BLKTYPE_NIX)) { + blkaddr = rvu_get_attach_blkaddr(rvu, BLKTYPE_NIX, + pcifunc, req); + if (blkaddr < 0) + return blkaddr; + block = &hw->block[blkaddr]; free_lfs = rvu_rsrc_free_count(&block->lf); if (!free_lfs) goto fail; @@ -1250,7 +1406,7 @@ static int rvu_check_rsrc_availability(struct rvu *rvu, pcifunc, req->sso, block->lf.max); return -EINVAL; } - mappedlfs = rvu_get_rsrc_mapcount(pfvf, block->type); + mappedlfs = rvu_get_rsrc_mapcount(pfvf, block->addr); free_lfs = rvu_rsrc_free_count(&block->lf); /* Check if additional resources are available */ if (req->sso > mappedlfs && @@ -1266,7 +1422,7 @@ static int rvu_check_rsrc_availability(struct rvu *rvu, pcifunc, req->sso, block->lf.max); return -EINVAL; } - mappedlfs = rvu_get_rsrc_mapcount(pfvf, block->type); + mappedlfs = rvu_get_rsrc_mapcount(pfvf, block->addr); free_lfs = rvu_rsrc_free_count(&block->lf); if (req->ssow > mappedlfs && ((req->ssow - mappedlfs) > free_lfs)) @@ -1281,7 +1437,7 @@ static int rvu_check_rsrc_availability(struct rvu *rvu, pcifunc, req->timlfs, block->lf.max); return -EINVAL; } - mappedlfs = rvu_get_rsrc_mapcount(pfvf, block->type); + mappedlfs = rvu_get_rsrc_mapcount(pfvf, block->addr); free_lfs = rvu_rsrc_free_count(&block->lf); if (req->timlfs > mappedlfs && ((req->timlfs - mappedlfs) > free_lfs)) @@ -1289,14 +1445,18 @@ static int rvu_check_rsrc_availability(struct rvu *rvu, } if (req->cptlfs) { - block = &hw->block[BLKADDR_CPT0]; + blkaddr = rvu_get_attach_blkaddr(rvu, BLKTYPE_CPT, + pcifunc, req); + if (blkaddr < 0) + return blkaddr; + block = &hw->block[blkaddr]; if (req->cptlfs > block->lf.max) { dev_err(&rvu->pdev->dev, "Func 0x%x: Invalid CPTLF req, %d > max %d\n", pcifunc, req->cptlfs, block->lf.max); return -EINVAL; } - mappedlfs = rvu_get_rsrc_mapcount(pfvf, block->type); + mappedlfs = rvu_get_rsrc_mapcount(pfvf, block->addr); free_lfs = rvu_rsrc_free_count(&block->lf); if (req->cptlfs > mappedlfs && ((req->cptlfs - mappedlfs) > free_lfs)) @@ -1310,6 +1470,22 @@ fail: return -ENOSPC; } +static bool rvu_attach_from_same_block(struct rvu *rvu, int blktype, + struct rsrc_attach *attach) +{ + int blkaddr, num_lfs; + + blkaddr = rvu_get_attach_blkaddr(rvu, blktype, + attach->hdr.pcifunc, attach); + if (blkaddr < 0) + return false; + + num_lfs = rvu_get_rsrc_mapcount(rvu_get_pfvf(rvu, attach->hdr.pcifunc), + blkaddr); + /* Requester already has LFs from given block ? */ + return !!num_lfs; +} + int rvu_mbox_handler_attach_resources(struct rvu *rvu, struct rsrc_attach *attach, struct msg_rsp *rsp) @@ -1330,10 +1506,10 @@ int rvu_mbox_handler_attach_resources(struct rvu *rvu, /* Now attach the requested resources */ if (attach->npalf) - rvu_attach_block(rvu, pcifunc, BLKTYPE_NPA, 1); + rvu_attach_block(rvu, pcifunc, BLKTYPE_NPA, 1, attach); if (attach->nixlf) - rvu_attach_block(rvu, pcifunc, BLKTYPE_NIX, 1); + rvu_attach_block(rvu, pcifunc, BLKTYPE_NIX, 1, attach); if (attach->sso) { /* RVU func doesn't know which exact LF or slot is attached @@ -1343,25 +1519,30 @@ int rvu_mbox_handler_attach_resources(struct rvu *rvu, */ if (attach->modify) rvu_detach_block(rvu, pcifunc, BLKTYPE_SSO); - rvu_attach_block(rvu, pcifunc, BLKTYPE_SSO, attach->sso); + rvu_attach_block(rvu, pcifunc, BLKTYPE_SSO, + attach->sso, attach); } if (attach->ssow) { if (attach->modify) rvu_detach_block(rvu, pcifunc, BLKTYPE_SSOW); - rvu_attach_block(rvu, pcifunc, BLKTYPE_SSOW, attach->ssow); + rvu_attach_block(rvu, pcifunc, BLKTYPE_SSOW, + attach->ssow, attach); } if (attach->timlfs) { if (attach->modify) rvu_detach_block(rvu, pcifunc, BLKTYPE_TIM); - rvu_attach_block(rvu, pcifunc, BLKTYPE_TIM, attach->timlfs); + rvu_attach_block(rvu, pcifunc, BLKTYPE_TIM, + attach->timlfs, attach); } if (attach->cptlfs) { - if (attach->modify) + if (attach->modify && + rvu_attach_from_same_block(rvu, BLKTYPE_CPT, attach)) rvu_detach_block(rvu, pcifunc, BLKTYPE_CPT); - rvu_attach_block(rvu, pcifunc, BLKTYPE_CPT, attach->cptlfs); + rvu_attach_block(rvu, pcifunc, BLKTYPE_CPT, + attach->cptlfs, attach); } exit: @@ -1439,7 +1620,7 @@ int rvu_mbox_handler_msix_offset(struct rvu *rvu, struct msg_req *req, struct rvu_hwinfo *hw = rvu->hw; u16 pcifunc = req->hdr.pcifunc; struct rvu_pfvf *pfvf; - int lf, slot; + int lf, slot, blkaddr; pfvf = rvu_get_pfvf(rvu, pcifunc); if (!pfvf->msix.bmap) @@ -1449,8 +1630,14 @@ int rvu_mbox_handler_msix_offset(struct rvu *rvu, struct msg_req *req, lf = rvu_get_lf(rvu, &hw->block[BLKADDR_NPA], pcifunc, 0); rsp->npa_msixoff = rvu_get_msix_offset(rvu, pfvf, BLKADDR_NPA, lf); - lf = rvu_get_lf(rvu, &hw->block[BLKADDR_NIX0], pcifunc, 0); - rsp->nix_msixoff = rvu_get_msix_offset(rvu, pfvf, BLKADDR_NIX0, lf); + /* Get BLKADDR from which LFs are attached to pcifunc */ + blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc); + if (blkaddr < 0) { + rsp->nix_msixoff = MSIX_VECTOR_INVALID; + } else { + lf = rvu_get_lf(rvu, &hw->block[blkaddr], pcifunc, 0); + rsp->nix_msixoff = rvu_get_msix_offset(rvu, pfvf, blkaddr, lf); + } rsp->sso = pfvf->sso; for (slot = 0; slot < rsp->sso; slot++) { @@ -1479,6 +1666,14 @@ int rvu_mbox_handler_msix_offset(struct rvu *rvu, struct msg_req *req, rsp->cptlf_msixoff[slot] = rvu_get_msix_offset(rvu, pfvf, BLKADDR_CPT0, lf); } + + rsp->cpt1_lfs = pfvf->cpt1_lfs; + for (slot = 0; slot < rsp->cpt1_lfs; slot++) { + lf = rvu_get_lf(rvu, &hw->block[BLKADDR_CPT1], pcifunc, slot); + rsp->cpt1_lf_msixoff[slot] = + rvu_get_msix_offset(rvu, pfvf, BLKADDR_CPT1, lf); + } + return 0; } @@ -1932,7 +2127,7 @@ static void rvu_blklf_teardown(struct rvu *rvu, u16 pcifunc, u8 blkaddr) block = &rvu->hw->block[blkaddr]; num_lfs = rvu_get_rsrc_mapcount(rvu_get_pfvf(rvu, pcifunc), - block->type); + block->addr); if (!num_lfs) return; for (slot = 0; slot < num_lfs; slot++) { @@ -1941,7 +2136,7 @@ static void rvu_blklf_teardown(struct rvu *rvu, u16 pcifunc, u8 blkaddr) continue; /* Cleanup LF and reset it */ - if (block->addr == BLKADDR_NIX0) + if (block->addr == BLKADDR_NIX0 || block->addr == BLKADDR_NIX1) rvu_nix_lf_teardown(rvu, pcifunc, block->addr, lf); else if (block->addr == BLKADDR_NPA) rvu_npa_lf_teardown(rvu, pcifunc, lf); @@ -1963,7 +2158,9 @@ static void __rvu_flr_handler(struct rvu *rvu, u16 pcifunc) * 3. Cleanup pools (NPA) */ rvu_blklf_teardown(rvu, pcifunc, BLKADDR_NIX0); + rvu_blklf_teardown(rvu, pcifunc, BLKADDR_NIX1); rvu_blklf_teardown(rvu, pcifunc, BLKADDR_CPT0); + rvu_blklf_teardown(rvu, pcifunc, BLKADDR_CPT1); rvu_blklf_teardown(rvu, pcifunc, BLKADDR_TIM); rvu_blklf_teardown(rvu, pcifunc, BLKADDR_SSOW); rvu_blklf_teardown(rvu, pcifunc, BLKADDR_SSO); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index 90eed3160915..5ac9bb12415f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -28,6 +28,7 @@ #define PCI_MBOX_BAR_NUM 4 #define NAME_SIZE 32 +#define MAX_NIX_BLKS 2 /* PF_FUNC */ #define RVU_PFVF_PF_SHIFT 10 @@ -137,6 +138,7 @@ struct rvu_pfvf { u16 ssow; u16 cptlfs; u16 timlfs; + u16 cpt1_lfs; u8 cgx_lmac; /* Block LF's MSIX vector info */ @@ -182,6 +184,10 @@ struct rvu_pfvf { bool cgx_in_use; /* this PF/VF using CGX? */ int cgx_users; /* number of cgx users - used only by PFs */ + + u8 nix_blkaddr; /* BLKADDR_NIX0/1 assigned to this PF */ + u8 nix_rx_intf; /* NIX0_RX/NIX1_RX interface to NPC */ + u8 nix_tx_intf; /* NIX0_TX/NIX1_TX interface to NPC */ }; struct nix_txsch { @@ -219,6 +225,8 @@ struct nix_lso { }; struct nix_hw { + int blkaddr; + struct rvu *rvu; struct nix_txsch txsch[NIX_TXSCH_LVL_CNT]; /* Tx schedulers */ struct nix_mcast mcast; struct nix_flowkey flowkey; @@ -251,10 +259,16 @@ struct rvu_hwinfo { u8 lbk_links; u8 sdp_links; u8 npc_kpus; /* No of parser units */ + u8 npc_pkinds; /* No of port kinds */ + u8 npc_intfs; /* No of interfaces */ + u8 npc_kpu_entries; /* No of KPU entries */ + u16 npc_counters; /* No of match stats counters */ + bool npc_ext_set; /* Extended register set */ struct hw_cap cap; struct rvu_block block[BLK_COUNT]; /* Block info */ - struct nix_hw *nix0; + struct nix_hw *nix; + struct rvu *rvu; struct npc_pkind pkind; struct npc_mcam mcam; }; @@ -300,7 +314,7 @@ struct npc_kpu_profile_adapter { const struct npc_lt_def_cfg *lt_def; const struct npc_kpu_profile_action *ikpu; /* array[pkinds] */ const struct npc_kpu_profile *kpu; /* array[kpus] */ - const struct npc_mcam_kex *mkex; + struct npc_mcam_kex *mkex; size_t pkinds; size_t kpus; }; @@ -315,6 +329,7 @@ struct rvu { struct rvu_pfvf *hwvf; struct mutex rsrc_lock; /* Serialize resource alloc/free */ int vfs; /* Number of VFs attached to RVU */ + int nix_blkaddr[MAX_NIX_BLKS]; /* Mbox */ struct mbox_wq_info afpf_wq_info; @@ -420,6 +435,7 @@ void rvu_free_rsrc(struct rsrc_bmap *rsrc, int id); int rvu_rsrc_free_count(struct rsrc_bmap *rsrc); int rvu_alloc_rsrc_contig(struct rsrc_bmap *rsrc, int nrsrc); bool rvu_rsrc_check_contig(struct rsrc_bmap *rsrc, int nrsrc); +u16 rvu_get_rsrc_mapcount(struct rvu_pfvf *pfvf, int blkaddr); int rvu_get_pf(u16 pcifunc); struct rvu_pfvf *rvu_get_pfvf(struct rvu *rvu, int pcifunc); void rvu_get_pf_numvfs(struct rvu *rvu, int pf, int *numvfs, int *hwvf); @@ -485,6 +501,8 @@ int rvu_get_nixlf_count(struct rvu *rvu); void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int npalf); int nix_get_nixlf(struct rvu *rvu, u16 pcifunc, int *nixlf, int *nix_blkaddr); int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add); +struct nix_hw *get_nix_hw(struct rvu_hwinfo *hw, int blkaddr); +int rvu_get_next_nix_blkaddr(struct rvu *rvu, int blkaddr); /* NPC APIs */ int rvu_npc_init(struct rvu *rvu); @@ -513,6 +531,10 @@ void rvu_npc_get_mcam_entry_alloc_info(struct rvu *rvu, u16 pcifunc, void rvu_npc_get_mcam_counter_alloc_info(struct rvu *rvu, u16 pcifunc, int blkaddr, int *alloc_cnt, int *enable_cnt); +bool is_npc_intf_tx(u8 intf); +bool is_npc_intf_rx(u8 intf); +bool is_npc_interface_valid(struct rvu *rvu, u8 intf); +int rvu_npc_get_tx_nibble_cfg(struct rvu *rvu, u64 nibble_ena); #ifdef CONFIG_DEBUG_FS void rvu_dbg_init(struct rvu *rvu); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c index fa9152ff5e2a..d298b9357177 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c @@ -74,6 +74,20 @@ void *rvu_cgx_pdata(u8 cgx_id, struct rvu *rvu) return rvu->cgx_idmap[cgx_id]; } +/* Based on P2X connectivity find mapped NIX block for a PF */ +static void rvu_map_cgx_nix_block(struct rvu *rvu, int pf, + int cgx_id, int lmac_id) +{ + struct rvu_pfvf *pfvf = &rvu->pf[pf]; + u8 p2x; + + p2x = cgx_lmac_get_p2x(cgx_id, lmac_id); + /* Firmware sets P2X_SELECT as either NIX0 or NIX1 */ + pfvf->nix_blkaddr = BLKADDR_NIX0; + if (p2x == CMR_P2X_SEL_NIX1) + pfvf->nix_blkaddr = BLKADDR_NIX1; +} + static int rvu_map_cgx_lmac_pf(struct rvu *rvu) { struct npc_pkind *pkind = &rvu->hw->pkind; @@ -117,6 +131,7 @@ static int rvu_map_cgx_lmac_pf(struct rvu *rvu) rvu->cgxlmac2pf_map[CGX_OFFSET(cgx) + lmac] = 1 << pf; free_pkind = rvu_alloc_rsrc(&pkind->rsrc); pkind->pfchan_map[free_pkind] = ((pf) & 0x3F) << 16; + rvu_map_cgx_nix_block(rvu, pf, cgx, lmac); rvu->cgx_mapped_pfs++; } } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index 77adad4adb1b..b7b6b6f8865a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -224,18 +224,53 @@ static ssize_t rvu_dbg_rsrc_attach_status(struct file *filp, RVU_DEBUG_FOPS(rsrc_status, rsrc_attach_status, NULL); -static bool rvu_dbg_is_valid_lf(struct rvu *rvu, int blktype, int lf, +static int rvu_dbg_rvu_pf_cgx_map_display(struct seq_file *filp, void *unused) +{ + struct rvu *rvu = filp->private; + struct pci_dev *pdev = NULL; + char cgx[10], lmac[10]; + struct rvu_pfvf *pfvf; + int pf, domain, blkid; + u8 cgx_id, lmac_id; + u16 pcifunc; + + domain = 2; + seq_puts(filp, "PCI dev\t\tRVU PF Func\tNIX block\tCGX\tLMAC\n"); + for (pf = 0; pf < rvu->hw->total_pfs; pf++) { + if (!is_pf_cgxmapped(rvu, pf)) + continue; + + pdev = pci_get_domain_bus_and_slot(domain, pf + 1, 0); + if (!pdev) + continue; + + cgx[0] = 0; + lmac[0] = 0; + pcifunc = pf << 10; + pfvf = rvu_get_pfvf(rvu, pcifunc); + + if (pfvf->nix_blkaddr == BLKADDR_NIX0) + blkid = 0; + else + blkid = 1; + + rvu_get_cgx_lmac_id(rvu->pf2cgxlmac_map[pf], &cgx_id, + &lmac_id); + sprintf(cgx, "CGX%d", cgx_id); + sprintf(lmac, "LMAC%d", lmac_id); + seq_printf(filp, "%s\t0x%x\t\tNIX%d\t\t%s\t%s\n", + dev_name(&pdev->dev), pcifunc, blkid, cgx, lmac); + } + return 0; +} + +RVU_DEBUG_SEQ_FOPS(rvu_pf_cgx_map, rvu_pf_cgx_map_display, NULL); + +static bool rvu_dbg_is_valid_lf(struct rvu *rvu, int blkaddr, int lf, u16 *pcifunc) { struct rvu_block *block; struct rvu_hwinfo *hw; - int blkaddr; - - blkaddr = rvu_get_blkaddr(rvu, blktype, 0); - if (blkaddr < 0) { - dev_warn(rvu->dev, "Invalid blktype\n"); - return false; - } hw = rvu->hw; block = &hw->block[blkaddr]; @@ -291,10 +326,12 @@ static int rvu_dbg_qsize_display(struct seq_file *filp, void *unsused, { void (*print_qsize)(struct seq_file *filp, struct rvu_pfvf *pfvf) = NULL; + struct dentry *current_dir; struct rvu_pfvf *pfvf; struct rvu *rvu; int qsize_id; u16 pcifunc; + int blkaddr; rvu = filp->private; switch (blktype) { @@ -312,7 +349,15 @@ static int rvu_dbg_qsize_display(struct seq_file *filp, void *unsused, return -EINVAL; } - if (!rvu_dbg_is_valid_lf(rvu, blktype, qsize_id, &pcifunc)) + if (blktype == BLKTYPE_NPA) { + blkaddr = BLKADDR_NPA; + } else { + current_dir = filp->file->f_path.dentry->d_parent; + blkaddr = (!strcmp(current_dir->d_name.name, "nix1") ? + BLKADDR_NIX1 : BLKADDR_NIX0); + } + + if (!rvu_dbg_is_valid_lf(rvu, blkaddr, qsize_id, &pcifunc)) return -EINVAL; pfvf = rvu_get_pfvf(rvu, pcifunc); @@ -329,6 +374,8 @@ static ssize_t rvu_dbg_qsize_write(struct file *filp, struct seq_file *seqfile = filp->private_data; char *cmd_buf, *cmd_buf_tmp, *subtoken; struct rvu *rvu = seqfile->private; + struct dentry *current_dir; + int blkaddr; u16 pcifunc; int ret, lf; @@ -355,7 +402,15 @@ static ssize_t rvu_dbg_qsize_write(struct file *filp, goto qsize_write_done; } - if (!rvu_dbg_is_valid_lf(rvu, blktype, lf, &pcifunc)) { + if (blktype == BLKTYPE_NPA) { + blkaddr = BLKADDR_NPA; + } else { + current_dir = filp->f_path.dentry->d_parent; + blkaddr = (!strcmp(current_dir->d_name.name, "nix1") ? + BLKADDR_NIX1 : BLKADDR_NIX0); + } + + if (!rvu_dbg_is_valid_lf(rvu, blkaddr, lf, &pcifunc)) { ret = -EINVAL; goto qsize_write_done; } @@ -498,7 +553,7 @@ static int rvu_dbg_npa_ctx_display(struct seq_file *m, void *unused, int ctype) return -EINVAL; } - if (!rvu_dbg_is_valid_lf(rvu, BLKTYPE_NPA, npalf, &pcifunc)) + if (!rvu_dbg_is_valid_lf(rvu, BLKADDR_NPA, npalf, &pcifunc)) return -EINVAL; pfvf = rvu_get_pfvf(rvu, pcifunc); @@ -556,7 +611,7 @@ static int write_npa_ctx(struct rvu *rvu, bool all, int max_id = 0; u16 pcifunc; - if (!rvu_dbg_is_valid_lf(rvu, BLKTYPE_NPA, npalf, &pcifunc)) + if (!rvu_dbg_is_valid_lf(rvu, BLKADDR_NPA, npalf, &pcifunc)) return -EINVAL; pfvf = rvu_get_pfvf(rvu, pcifunc); @@ -704,9 +759,17 @@ static void ndc_cache_stats(struct seq_file *s, int blk_addr, int ctype, int transaction) { u64 req, out_req, lat, cant_alloc; - struct rvu *rvu = s->private; + struct nix_hw *nix_hw; + struct rvu *rvu; int port; + if (blk_addr == BLKADDR_NDC_NPA0) { + rvu = s->private; + } else { + nix_hw = s->private; + rvu = nix_hw->rvu; + } + for (port = 0; port < NDC_MAX_PORT; port++) { req = rvu_read64(rvu, blk_addr, NDC_AF_PORTX_RTX_RWX_REQ_PC (port, ctype, transaction)); @@ -749,9 +812,17 @@ RVU_DEBUG_SEQ_FOPS(npa_ndc_cache, npa_ndc_cache_display, NULL); static int ndc_blk_hits_miss_stats(struct seq_file *s, int idx, int blk_addr) { - struct rvu *rvu = s->private; + struct nix_hw *nix_hw; + struct rvu *rvu; int bank, max_bank; + if (blk_addr == BLKADDR_NDC_NPA0) { + rvu = s->private; + } else { + nix_hw = s->private; + rvu = nix_hw->rvu; + } + max_bank = NDC_MAX_BANK(rvu, blk_addr); for (bank = 0; bank < max_bank; bank++) { seq_printf(s, "BANK:%d\n", bank); @@ -767,16 +838,30 @@ static int ndc_blk_hits_miss_stats(struct seq_file *s, int idx, int blk_addr) static int rvu_dbg_nix_ndc_rx_cache_display(struct seq_file *filp, void *unused) { - return ndc_blk_cache_stats(filp, NIX0_RX, - BLKADDR_NDC_NIX0_RX); + struct nix_hw *nix_hw = filp->private; + int blkaddr = 0; + int ndc_idx = 0; + + blkaddr = (nix_hw->blkaddr == BLKADDR_NIX1 ? + BLKADDR_NDC_NIX1_RX : BLKADDR_NDC_NIX0_RX); + ndc_idx = (nix_hw->blkaddr == BLKADDR_NIX1 ? NIX1_RX : NIX0_RX); + + return ndc_blk_cache_stats(filp, ndc_idx, blkaddr); } RVU_DEBUG_SEQ_FOPS(nix_ndc_rx_cache, nix_ndc_rx_cache_display, NULL); static int rvu_dbg_nix_ndc_tx_cache_display(struct seq_file *filp, void *unused) { - return ndc_blk_cache_stats(filp, NIX0_TX, - BLKADDR_NDC_NIX0_TX); + struct nix_hw *nix_hw = filp->private; + int blkaddr = 0; + int ndc_idx = 0; + + blkaddr = (nix_hw->blkaddr == BLKADDR_NIX1 ? + BLKADDR_NDC_NIX1_TX : BLKADDR_NDC_NIX0_TX); + ndc_idx = (nix_hw->blkaddr == BLKADDR_NIX1 ? NIX1_TX : NIX0_TX); + + return ndc_blk_cache_stats(filp, ndc_idx, blkaddr); } RVU_DEBUG_SEQ_FOPS(nix_ndc_tx_cache, nix_ndc_tx_cache_display, NULL); @@ -792,8 +877,14 @@ RVU_DEBUG_SEQ_FOPS(npa_ndc_hits_miss, npa_ndc_hits_miss_display, NULL); static int rvu_dbg_nix_ndc_rx_hits_miss_display(struct seq_file *filp, void *unused) { - return ndc_blk_hits_miss_stats(filp, - NPA0_U, BLKADDR_NDC_NIX0_RX); + struct nix_hw *nix_hw = filp->private; + int ndc_idx = NPA0_U; + int blkaddr = 0; + + blkaddr = (nix_hw->blkaddr == BLKADDR_NIX1 ? + BLKADDR_NDC_NIX1_RX : BLKADDR_NDC_NIX0_RX); + + return ndc_blk_hits_miss_stats(filp, ndc_idx, blkaddr); } RVU_DEBUG_SEQ_FOPS(nix_ndc_rx_hits_miss, nix_ndc_rx_hits_miss_display, NULL); @@ -801,8 +892,14 @@ RVU_DEBUG_SEQ_FOPS(nix_ndc_rx_hits_miss, nix_ndc_rx_hits_miss_display, NULL); static int rvu_dbg_nix_ndc_tx_hits_miss_display(struct seq_file *filp, void *unused) { - return ndc_blk_hits_miss_stats(filp, - NPA0_U, BLKADDR_NDC_NIX0_TX); + struct nix_hw *nix_hw = filp->private; + int ndc_idx = NPA0_U; + int blkaddr = 0; + + blkaddr = (nix_hw->blkaddr == BLKADDR_NIX1 ? + BLKADDR_NDC_NIX1_TX : BLKADDR_NDC_NIX0_TX); + + return ndc_blk_hits_miss_stats(filp, ndc_idx, blkaddr); } RVU_DEBUG_SEQ_FOPS(nix_ndc_tx_hits_miss, nix_ndc_tx_hits_miss_display, NULL); @@ -969,7 +1066,8 @@ static int rvu_dbg_nix_queue_ctx_display(struct seq_file *filp, { void (*print_nix_ctx)(struct seq_file *filp, struct nix_aq_enq_rsp *rsp) = NULL; - struct rvu *rvu = filp->private; + struct nix_hw *nix_hw = filp->private; + struct rvu *rvu = nix_hw->rvu; struct nix_aq_enq_req aq_req; struct nix_aq_enq_rsp rsp; char *ctype_string = NULL; @@ -1001,7 +1099,7 @@ static int rvu_dbg_nix_queue_ctx_display(struct seq_file *filp, return -EINVAL; } - if (!rvu_dbg_is_valid_lf(rvu, BLKTYPE_NIX, nixlf, &pcifunc)) + if (!rvu_dbg_is_valid_lf(rvu, nix_hw->blkaddr, nixlf, &pcifunc)) return -EINVAL; pfvf = rvu_get_pfvf(rvu, pcifunc); @@ -1053,13 +1151,15 @@ static int rvu_dbg_nix_queue_ctx_display(struct seq_file *filp, } static int write_nix_queue_ctx(struct rvu *rvu, bool all, int nixlf, - int id, int ctype, char *ctype_string) + int id, int ctype, char *ctype_string, + struct seq_file *m) { + struct nix_hw *nix_hw = m->private; struct rvu_pfvf *pfvf; int max_id = 0; u16 pcifunc; - if (!rvu_dbg_is_valid_lf(rvu, BLKTYPE_NIX, nixlf, &pcifunc)) + if (!rvu_dbg_is_valid_lf(rvu, nix_hw->blkaddr, nixlf, &pcifunc)) return -EINVAL; pfvf = rvu_get_pfvf(rvu, pcifunc); @@ -1119,7 +1219,8 @@ static ssize_t rvu_dbg_nix_queue_ctx_write(struct file *filp, int ctype) { struct seq_file *m = filp->private_data; - struct rvu *rvu = m->private; + struct nix_hw *nix_hw = m->private; + struct rvu *rvu = nix_hw->rvu; char *cmd_buf, *ctype_string; int nixlf, id = 0, ret; bool all = false; @@ -1155,7 +1256,7 @@ static ssize_t rvu_dbg_nix_queue_ctx_write(struct file *filp, goto done; } else { ret = write_nix_queue_ctx(rvu, all, nixlf, id, ctype, - ctype_string); + ctype_string, m); } done: kfree(cmd_buf); @@ -1259,49 +1360,67 @@ static int rvu_dbg_nix_qsize_display(struct seq_file *filp, void *unused) RVU_DEBUG_SEQ_FOPS(nix_qsize, nix_qsize_display, nix_qsize_write); -static void rvu_dbg_nix_init(struct rvu *rvu) +static void rvu_dbg_nix_init(struct rvu *rvu, int blkaddr) { const struct device *dev = &rvu->pdev->dev; + struct nix_hw *nix_hw; struct dentry *pfile; - rvu->rvu_dbg.nix = debugfs_create_dir("nix", rvu->rvu_dbg.root); - if (!rvu->rvu_dbg.nix) { - dev_err(rvu->dev, "create debugfs dir failed for nix\n"); + if (!is_block_implemented(rvu->hw, blkaddr)) return; + + if (blkaddr == BLKADDR_NIX0) { + rvu->rvu_dbg.nix = debugfs_create_dir("nix", rvu->rvu_dbg.root); + if (!rvu->rvu_dbg.nix) { + dev_err(rvu->dev, "create debugfs dir failed for nix\n"); + return; + } + nix_hw = &rvu->hw->nix[0]; + } else { + rvu->rvu_dbg.nix = debugfs_create_dir("nix1", + rvu->rvu_dbg.root); + if (!rvu->rvu_dbg.nix) { + dev_err(rvu->dev, + "create debugfs dir failed for nix1\n"); + return; + } + nix_hw = &rvu->hw->nix[1]; } - pfile = debugfs_create_file("sq_ctx", 0600, rvu->rvu_dbg.nix, rvu, + pfile = debugfs_create_file("sq_ctx", 0600, rvu->rvu_dbg.nix, nix_hw, &rvu_dbg_nix_sq_ctx_fops); if (!pfile) goto create_failed; - pfile = debugfs_create_file("rq_ctx", 0600, rvu->rvu_dbg.nix, rvu, + pfile = debugfs_create_file("rq_ctx", 0600, rvu->rvu_dbg.nix, nix_hw, &rvu_dbg_nix_rq_ctx_fops); if (!pfile) goto create_failed; - pfile = debugfs_create_file("cq_ctx", 0600, rvu->rvu_dbg.nix, rvu, + pfile = debugfs_create_file("cq_ctx", 0600, rvu->rvu_dbg.nix, nix_hw, &rvu_dbg_nix_cq_ctx_fops); if (!pfile) goto create_failed; - pfile = debugfs_create_file("ndc_tx_cache", 0600, rvu->rvu_dbg.nix, rvu, - &rvu_dbg_nix_ndc_tx_cache_fops); + pfile = debugfs_create_file("ndc_tx_cache", 0600, rvu->rvu_dbg.nix, + nix_hw, &rvu_dbg_nix_ndc_tx_cache_fops); if (!pfile) goto create_failed; - pfile = debugfs_create_file("ndc_rx_cache", 0600, rvu->rvu_dbg.nix, rvu, - &rvu_dbg_nix_ndc_rx_cache_fops); + pfile = debugfs_create_file("ndc_rx_cache", 0600, rvu->rvu_dbg.nix, + nix_hw, &rvu_dbg_nix_ndc_rx_cache_fops); if (!pfile) goto create_failed; pfile = debugfs_create_file("ndc_tx_hits_miss", 0600, rvu->rvu_dbg.nix, - rvu, &rvu_dbg_nix_ndc_tx_hits_miss_fops); + nix_hw, + &rvu_dbg_nix_ndc_tx_hits_miss_fops); if (!pfile) goto create_failed; pfile = debugfs_create_file("ndc_rx_hits_miss", 0600, rvu->rvu_dbg.nix, - rvu, &rvu_dbg_nix_ndc_rx_hits_miss_fops); + nix_hw, + &rvu_dbg_nix_ndc_rx_hits_miss_fops); if (!pfile) goto create_failed; @@ -1312,7 +1431,8 @@ static void rvu_dbg_nix_init(struct rvu *rvu) return; create_failed: - dev_err(dev, "Failed to create debugfs dir/file for NIX\n"); + dev_err(dev, + "Failed to create debugfs dir/file for NIX blk\n"); debugfs_remove_recursive(rvu->rvu_dbg.nix); } @@ -1565,7 +1685,7 @@ static int rvu_dbg_npc_mcam_info_display(struct seq_file *filp, void *unsued) struct rvu *rvu = filp->private; int pf, vf, numvfs, blkaddr; struct npc_mcam *mcam; - u16 pcifunc; + u16 pcifunc, counters; u64 cfg; blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0); @@ -1573,6 +1693,7 @@ static int rvu_dbg_npc_mcam_info_display(struct seq_file *filp, void *unsued) return -ENODEV; mcam = &rvu->hw->mcam; + counters = rvu->hw->npc_counters; seq_puts(filp, "\nNPC MCAM info:\n"); /* MCAM keywidth on receive and transmit sides */ @@ -1595,10 +1716,9 @@ static int rvu_dbg_npc_mcam_info_display(struct seq_file *filp, void *unsued) seq_printf(filp, "\t\t Available \t: %d\n", mcam->bmap_fcnt); /* MCAM counters */ - cfg = rvu_read64(rvu, blkaddr, NPC_AF_CONST); - cfg = (cfg >> 48) & 0xFFFF; - seq_printf(filp, "\n\t\t MCAM counters \t: %lld\n", cfg); - seq_printf(filp, "\t\t Reserved \t: %lld\n", cfg - mcam->counters.max); + seq_printf(filp, "\n\t\t MCAM counters \t: %d\n", counters); + seq_printf(filp, "\t\t Reserved \t: %d\n", + counters - mcam->counters.max); seq_printf(filp, "\t\t Available \t: %d\n", rvu_rsrc_free_count(&mcam->counters)); @@ -1691,8 +1811,15 @@ void rvu_dbg_init(struct rvu *rvu) if (!pfile) goto create_failed; + pfile = debugfs_create_file("rvu_pf_cgx_map", 0444, rvu->rvu_dbg.root, + rvu, &rvu_dbg_rvu_pf_cgx_map_fops); + if (!pfile) + goto create_failed; + rvu_dbg_npa_init(rvu); - rvu_dbg_nix_init(rvu); + rvu_dbg_nix_init(rvu, BLKADDR_NIX0); + + rvu_dbg_nix_init(rvu, BLKADDR_NIX1); rvu_dbg_cgx_init(rvu); rvu_dbg_npc_init(rvu); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 21a89dd76d3c..8bac1dd3a1c2 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -68,6 +68,23 @@ struct mce { u16 pcifunc; }; +int rvu_get_next_nix_blkaddr(struct rvu *rvu, int blkaddr) +{ + int i = 0; + + /*If blkaddr is 0, return the first nix block address*/ + if (blkaddr == 0) + return rvu->nix_blkaddr[blkaddr]; + + while (i + 1 < MAX_NIX_BLKS) { + if (rvu->nix_blkaddr[i] == blkaddr) + return rvu->nix_blkaddr[i + 1]; + i++; + } + + return 0; +} + bool is_nixlf_attached(struct rvu *rvu, u16 pcifunc) { struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc); @@ -81,14 +98,16 @@ bool is_nixlf_attached(struct rvu *rvu, u16 pcifunc) int rvu_get_nixlf_count(struct rvu *rvu) { + int blkaddr = 0, max = 0; struct rvu_block *block; - int blkaddr; - blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, 0); - if (blkaddr < 0) - return 0; - block = &rvu->hw->block[blkaddr]; - return block->lf.max; + blkaddr = rvu_get_next_nix_blkaddr(rvu, blkaddr); + while (blkaddr) { + block = &rvu->hw->block[blkaddr]; + max += block->lf.max; + blkaddr = rvu_get_next_nix_blkaddr(rvu, blkaddr); + } + return max; } int nix_get_nixlf(struct rvu *rvu, u16 pcifunc, int *nixlf, int *nix_blkaddr) @@ -130,11 +149,18 @@ static u16 nix_alloc_mce_list(struct nix_mcast *mcast, int count) return idx; } -static inline struct nix_hw *get_nix_hw(struct rvu_hwinfo *hw, int blkaddr) +struct nix_hw *get_nix_hw(struct rvu_hwinfo *hw, int blkaddr) { - if (blkaddr == BLKADDR_NIX0 && hw->nix0) - return hw->nix0; + int nix_blkaddr = 0, i = 0; + struct rvu *rvu = hw->rvu; + nix_blkaddr = rvu_get_next_nix_blkaddr(rvu, nix_blkaddr); + while (nix_blkaddr) { + if (blkaddr == nix_blkaddr && hw->nix) + return &hw->nix[i]; + nix_blkaddr = rvu_get_next_nix_blkaddr(rvu, nix_blkaddr); + i++; + } return NULL; } @@ -187,8 +213,8 @@ static bool is_valid_txschq(struct rvu *rvu, int blkaddr, static int nix_interface_init(struct rvu *rvu, u16 pcifunc, int type, int nixlf) { struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc); + int pkind, pf, vf, lbkid; u8 cgx_id, lmac_id; - int pkind, pf, vf; int err; pf = rvu_get_pf(pcifunc); @@ -221,13 +247,24 @@ static int nix_interface_init(struct rvu *rvu, u16 pcifunc, int type, int nixlf) case NIX_INTF_TYPE_LBK: vf = (pcifunc & RVU_PFVF_FUNC_MASK) - 1; + /* If NIX1 block is present on the silicon then NIXes are + * assigned alternatively for lbk interfaces. NIX0 should + * send packets on lbk link 1 channels and NIX1 should send + * on lbk link 0 channels for the communication between + * NIX0 and NIX1. + */ + lbkid = 0; + if (rvu->hw->lbk_links > 1) + lbkid = vf & 0x1 ? 0 : 1; + /* Note that AF's VFs work in pairs and talk over consecutive * loopback channels.Therefore if odd number of AF VFs are * enabled then the last VF remains with no pair. */ - pfvf->rx_chan_base = NIX_CHAN_LBK_CHX(0, vf); - pfvf->tx_chan_base = vf & 0x1 ? NIX_CHAN_LBK_CHX(0, vf - 1) : - NIX_CHAN_LBK_CHX(0, vf + 1); + pfvf->rx_chan_base = NIX_CHAN_LBK_CHX(lbkid, vf); + pfvf->tx_chan_base = vf & 0x1 ? + NIX_CHAN_LBK_CHX(lbkid, vf - 1) : + NIX_CHAN_LBK_CHX(lbkid, vf + 1); pfvf->rx_chan_cnt = 1; pfvf->tx_chan_cnt = 1; rvu_npc_install_promisc_entry(rvu, pcifunc, nixlf, @@ -612,8 +649,9 @@ static int nix_aq_enqueue_wait(struct rvu *rvu, struct rvu_block *block, return 0; } -static int rvu_nix_aq_enq_inst(struct rvu *rvu, struct nix_aq_enq_req *req, - struct nix_aq_enq_rsp *rsp) +static int rvu_nix_blk_aq_enq_inst(struct rvu *rvu, struct nix_hw *nix_hw, + struct nix_aq_enq_req *req, + struct nix_aq_enq_rsp *rsp) { struct rvu_hwinfo *hw = rvu->hw; u16 pcifunc = req->hdr.pcifunc; @@ -626,10 +664,7 @@ static int rvu_nix_aq_enq_inst(struct rvu *rvu, struct nix_aq_enq_req *req, bool ena; u64 cfg; - blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc); - if (blkaddr < 0) - return NIX_AF_ERR_AF_LF_INVALID; - + blkaddr = nix_hw->blkaddr; block = &hw->block[blkaddr]; aq = block->aq; if (!aq) { @@ -669,8 +704,9 @@ static int rvu_nix_aq_enq_inst(struct rvu *rvu, struct nix_aq_enq_req *req, break; case NIX_AQ_CTYPE_MCE: cfg = rvu_read64(rvu, blkaddr, NIX_AF_RX_MCAST_CFG); + /* Check if index exceeds MCE list length */ - if (!hw->nix0->mcast.mce_ctx || + if (!nix_hw->mcast.mce_ctx || (req->qidx >= (256UL << (cfg & 0xF)))) rc = NIX_AF_ERR_AQ_ENQUEUE; @@ -832,6 +868,23 @@ static int rvu_nix_aq_enq_inst(struct rvu *rvu, struct nix_aq_enq_req *req, return 0; } +static int rvu_nix_aq_enq_inst(struct rvu *rvu, struct nix_aq_enq_req *req, + struct nix_aq_enq_rsp *rsp) +{ + struct nix_hw *nix_hw; + int blkaddr; + + blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, req->hdr.pcifunc); + if (blkaddr < 0) + return NIX_AF_ERR_AF_LF_INVALID; + + nix_hw = get_nix_hw(rvu->hw, blkaddr); + if (!nix_hw) + return -EINVAL; + + return rvu_nix_blk_aq_enq_inst(rvu, nix_hw, req, rsp); +} + static const char *nix_get_ctx_name(int ctype) { switch (ctype) { @@ -1164,6 +1217,10 @@ exit: cfg = rvu_read64(rvu, blkaddr, NIX_AF_CONST2); rsp->qints = ((cfg >> 12) & 0xFFF); rsp->cints = ((cfg >> 24) & 0xFFF); + rsp->cgx_links = hw->cgx_links; + rsp->lbk_links = hw->lbk_links; + rsp->sdp_links = hw->sdp_links; + return rc; } @@ -1950,8 +2007,8 @@ int rvu_mbox_handler_nix_vtag_cfg(struct rvu *rvu, return 0; } -static int nix_setup_mce(struct rvu *rvu, int mce, u8 op, - u16 pcifunc, int next, bool eol) +static int nix_blk_setup_mce(struct rvu *rvu, struct nix_hw *nix_hw, + int mce, u8 op, u16 pcifunc, int next, bool eol) { struct nix_aq_enq_req aq_req; int err; @@ -1971,7 +2028,7 @@ static int nix_setup_mce(struct rvu *rvu, int mce, u8 op, /* All fields valid */ *(u64 *)(&aq_req.mce_mask) = ~0ULL; - err = rvu_nix_aq_enq_inst(rvu, &aq_req, NULL); + err = rvu_nix_blk_aq_enq_inst(rvu, nix_hw, &aq_req, NULL); if (err) { dev_err(rvu->dev, "Failed to setup Bcast MCE for PF%d:VF%d\n", rvu_get_pf(pcifunc), pcifunc & RVU_PFVF_FUNC_MASK); @@ -2077,9 +2134,9 @@ int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add) next_idx = idx + 1; /* EOL should be set in last MCE */ - err = nix_setup_mce(rvu, idx, NIX_AQ_INSTOP_WRITE, - mce->pcifunc, next_idx, - (next_idx > last_idx) ? true : false); + err = nix_blk_setup_mce(rvu, nix_hw, idx, NIX_AQ_INSTOP_WRITE, + mce->pcifunc, next_idx, + (next_idx > last_idx) ? true : false); if (err) goto end; idx++; @@ -2108,6 +2165,11 @@ static int nix_setup_bcast_tables(struct rvu *rvu, struct nix_hw *nix_hw) numvfs = (cfg >> 12) & 0xFF; pfvf = &rvu->pf[pf]; + + /* This NIX0/1 block mapped to PF ? */ + if (pfvf->nix_blkaddr != nix_hw->blkaddr) + continue; + /* Save the start MCE */ pfvf->bcast_mce_idx = nix_alloc_mce_list(mcast, numvfs + 1); @@ -2122,9 +2184,10 @@ static int nix_setup_bcast_tables(struct rvu *rvu, struct nix_hw *nix_hw) * Will be updated when a NIXLF is attached/detached to * these PF/VFs. */ - err = nix_setup_mce(rvu, pfvf->bcast_mce_idx + idx, - NIX_AQ_INSTOP_INIT, - pcifunc, 0, true); + err = nix_blk_setup_mce(rvu, nix_hw, + pfvf->bcast_mce_idx + idx, + NIX_AQ_INSTOP_INIT, + pcifunc, 0, true); if (err) return err; } @@ -3109,17 +3172,15 @@ static int nix_aq_init(struct rvu *rvu, struct rvu_block *block) return 0; } -int rvu_nix_init(struct rvu *rvu) +static int rvu_nix_block_init(struct rvu *rvu, struct nix_hw *nix_hw) { const struct npc_lt_def_cfg *ltdefs; struct rvu_hwinfo *hw = rvu->hw; + int blkaddr = nix_hw->blkaddr; struct rvu_block *block; - int blkaddr, err; + int err; u64 cfg; - blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, 0); - if (blkaddr < 0) - return 0; block = &hw->block[blkaddr]; if (is_rvu_96xx_B0(rvu)) { @@ -3153,7 +3214,7 @@ int rvu_nix_init(struct rvu *rvu) hw->cgx = (cfg >> 12) & 0xF; hw->lmac_per_cgx = (cfg >> 8) & 0xF; hw->cgx_links = hw->cgx * hw->lmac_per_cgx; - hw->lbk_links = 1; + hw->lbk_links = (cfg >> 24) & 0xF; hw->sdp_links = 1; /* Initialize admin queue */ @@ -3164,26 +3225,21 @@ int rvu_nix_init(struct rvu *rvu) /* Restore CINT timer delay to HW reset values */ rvu_write64(rvu, blkaddr, NIX_AF_CINT_DELAY, 0x0ULL); - if (blkaddr == BLKADDR_NIX0) { - hw->nix0 = devm_kzalloc(rvu->dev, - sizeof(struct nix_hw), GFP_KERNEL); - if (!hw->nix0) - return -ENOMEM; - - err = nix_setup_txschq(rvu, hw->nix0, blkaddr); + if (is_block_implemented(hw, blkaddr)) { + err = nix_setup_txschq(rvu, nix_hw, blkaddr); if (err) return err; - err = nix_af_mark_format_setup(rvu, hw->nix0, blkaddr); + err = nix_af_mark_format_setup(rvu, nix_hw, blkaddr); if (err) return err; - err = nix_setup_mcast(rvu, hw->nix0, blkaddr); + err = nix_setup_mcast(rvu, nix_hw, blkaddr); if (err) return err; /* Configure segmentation offload formats */ - nix_setup_lso(rvu, hw->nix0, blkaddr); + nix_setup_lso(rvu, nix_hw, blkaddr); /* Config Outer/Inner L2, IP, TCP, UDP and SCTP NPC layer info. * This helps HW protocol checker to identify headers @@ -3236,23 +3292,44 @@ int rvu_nix_init(struct rvu *rvu) return 0; } -void rvu_nix_freemem(struct rvu *rvu) +int rvu_nix_init(struct rvu *rvu) { struct rvu_hwinfo *hw = rvu->hw; - struct rvu_block *block; + struct nix_hw *nix_hw; + int blkaddr = 0, err; + int i = 0; + + hw->nix = devm_kcalloc(rvu->dev, MAX_NIX_BLKS, sizeof(struct nix_hw), + GFP_KERNEL); + if (!hw->nix) + return -ENOMEM; + + blkaddr = rvu_get_next_nix_blkaddr(rvu, blkaddr); + while (blkaddr) { + nix_hw = &hw->nix[i]; + nix_hw->rvu = rvu; + nix_hw->blkaddr = blkaddr; + err = rvu_nix_block_init(rvu, nix_hw); + if (err) + return err; + blkaddr = rvu_get_next_nix_blkaddr(rvu, blkaddr); + i++; + } + + return 0; +} + +static void rvu_nix_block_freemem(struct rvu *rvu, int blkaddr, + struct rvu_block *block) +{ struct nix_txsch *txsch; struct nix_mcast *mcast; struct nix_hw *nix_hw; - int blkaddr, lvl; - - blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, 0); - if (blkaddr < 0) - return; + int lvl; - block = &hw->block[blkaddr]; rvu_aq_free(rvu, block->aq); - if (blkaddr == BLKADDR_NIX0) { + if (is_block_implemented(rvu->hw, blkaddr)) { nix_hw = get_nix_hw(rvu->hw, blkaddr); if (!nix_hw) return; @@ -3269,6 +3346,20 @@ void rvu_nix_freemem(struct rvu *rvu) } } +void rvu_nix_freemem(struct rvu *rvu) +{ + struct rvu_hwinfo *hw = rvu->hw; + struct rvu_block *block; + int blkaddr = 0; + + blkaddr = rvu_get_next_nix_blkaddr(rvu, blkaddr); + while (blkaddr) { + block = &hw->block[blkaddr]; + rvu_nix_block_freemem(rvu, blkaddr, block); + blkaddr = rvu_get_next_nix_blkaddr(rvu, blkaddr); + } +} + int rvu_mbox_handler_nix_lf_start_rx(struct rvu *rvu, struct msg_req *req, struct msg_rsp *rsp) { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index 511b01dd03ed..989533a3d2ce 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -36,6 +36,33 @@ static void npc_mcam_free_all_entries(struct rvu *rvu, struct npc_mcam *mcam, static void npc_mcam_free_all_counters(struct rvu *rvu, struct npc_mcam *mcam, u16 pcifunc); +bool is_npc_intf_tx(u8 intf) +{ + return !!(intf & 0x1); +} + +bool is_npc_intf_rx(u8 intf) +{ + return !(intf & 0x1); +} + +bool is_npc_interface_valid(struct rvu *rvu, u8 intf) +{ + struct rvu_hwinfo *hw = rvu->hw; + + return intf < hw->npc_intfs; +} + +int rvu_npc_get_tx_nibble_cfg(struct rvu *rvu, u64 nibble_ena) +{ + /* Due to a HW issue in these silicon versions, parse nibble enable + * configuration has to be identical for both Rx and Tx interfaces. + */ + if (is_rvu_96xx_B0(rvu)) + return nibble_ena; + return 0; +} + void rvu_npc_set_pkind(struct rvu *rvu, int pkind, struct rvu_pfvf *pfvf) { int blkaddr; @@ -94,6 +121,31 @@ int npc_config_ts_kpuaction(struct rvu *rvu, int pf, u16 pcifunc, bool enable) return 0; } +static int npc_get_ucast_mcam_index(struct npc_mcam *mcam, u16 pcifunc, + int nixlf) +{ + struct rvu_hwinfo *hw = container_of(mcam, struct rvu_hwinfo, mcam); + struct rvu *rvu = hw->rvu; + int blkaddr = 0, max = 0; + struct rvu_block *block; + struct rvu_pfvf *pfvf; + + pfvf = rvu_get_pfvf(rvu, pcifunc); + /* Given a PF/VF and NIX LF number calculate the unicast mcam + * entry index based on the NIX block assigned to the PF/VF. + */ + blkaddr = rvu_get_next_nix_blkaddr(rvu, blkaddr); + while (blkaddr) { + if (pfvf->nix_blkaddr == blkaddr) + break; + block = &rvu->hw->block[blkaddr]; + max += block->lf.max; + blkaddr = rvu_get_next_nix_blkaddr(rvu, blkaddr); + } + + return mcam->nixlf_offset + (max + nixlf) * RSVD_MCAM_ENTRIES_PER_NIXLF; +} + static int npc_get_nixlf_mcam_index(struct npc_mcam *mcam, u16 pcifunc, int nixlf, int type) { @@ -114,7 +166,7 @@ static int npc_get_nixlf_mcam_index(struct npc_mcam *mcam, return index + 1; } - return (mcam->nixlf_offset + (nixlf * RSVD_MCAM_ENTRIES_PER_NIXLF)); + return npc_get_ucast_mcam_index(mcam, pcifunc, nixlf); } static int npc_get_bank(struct npc_mcam *mcam, int index) @@ -413,7 +465,7 @@ void rvu_npc_install_ucast_entry(struct rvu *rvu, u16 pcifunc, entry.action = *(u64 *)&action; npc_config_mcam_entry(rvu, mcam, blkaddr, index, - NIX_INTF_RX, &entry, true); + pfvf->nix_rx_intf, &entry, true); /* add VLAN matching, setup action and save entry back for later */ entry.kw[0] |= (NPC_LT_LB_STAG_QINQ | NPC_LT_LB_CTAG) << 20; @@ -430,6 +482,7 @@ void rvu_npc_install_ucast_entry(struct rvu *rvu, u16 pcifunc, void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf, u64 chan, bool allmulti) { + struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc); struct npc_mcam *mcam = &rvu->hw->mcam; int blkaddr, ucast_idx, index, kwi; struct mcam_entry entry = { {0} }; @@ -473,7 +526,7 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc, entry.action = *(u64 *)&action; npc_config_mcam_entry(rvu, mcam, blkaddr, index, - NIX_INTF_RX, &entry, true); + pfvf->nix_rx_intf, &entry, true); } static void npc_enadis_promisc_entry(struct rvu *rvu, u16 pcifunc, @@ -531,6 +584,7 @@ void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc, /* Get 'pcifunc' of PF device */ pcifunc = pcifunc & ~RVU_PFVF_FUNC_MASK; + pfvf = rvu_get_pfvf(rvu, pcifunc); index = npc_get_nixlf_mcam_index(mcam, pcifunc, nixlf, NIXLF_BCAST_ENTRY); @@ -553,14 +607,13 @@ void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc, action.op = NIX_RX_ACTIONOP_UCAST; action.pf_func = pcifunc; } else { - pfvf = rvu_get_pfvf(rvu, pcifunc); action.index = pfvf->bcast_mce_idx; action.op = NIX_RX_ACTIONOP_MCAST; } entry.action = *(u64 *)&action; npc_config_mcam_entry(rvu, mcam, blkaddr, index, - NIX_INTF_RX, &entry, true); + pfvf->nix_rx_intf, &entry, true); } void rvu_npc_enable_bcast_entry(struct rvu *rvu, u16 pcifunc, bool enable) @@ -732,44 +785,78 @@ void rvu_npc_disable_mcam_entries(struct rvu *rvu, u16 pcifunc, int nixlf) rvu_write64(rvu, blkaddr, \ NPC_AF_INTFX_LDATAX_FLAGSX_CFG(intf, ld, flags), cfg) -static void npc_program_mkex_profile(struct rvu *rvu, int blkaddr, - const struct npc_mcam_kex *mkex) +static void npc_program_mkex_rx(struct rvu *rvu, int blkaddr, + struct npc_mcam_kex *mkex, u8 intf) { int lid, lt, ld, fl; - rvu_write64(rvu, blkaddr, NPC_AF_INTFX_KEX_CFG(NIX_INTF_RX), - mkex->keyx_cfg[NIX_INTF_RX]); - rvu_write64(rvu, blkaddr, NPC_AF_INTFX_KEX_CFG(NIX_INTF_TX), - mkex->keyx_cfg[NIX_INTF_TX]); + if (is_npc_intf_tx(intf)) + return; - for (ld = 0; ld < NPC_MAX_LD; ld++) - rvu_write64(rvu, blkaddr, NPC_AF_KEX_LDATAX_FLAGS_CFG(ld), - mkex->kex_ld_flags[ld]); + rvu_write64(rvu, blkaddr, NPC_AF_INTFX_KEX_CFG(intf), + mkex->keyx_cfg[NIX_INTF_RX]); + /* Program LDATA */ for (lid = 0; lid < NPC_MAX_LID; lid++) { for (lt = 0; lt < NPC_MAX_LT; lt++) { - for (ld = 0; ld < NPC_MAX_LD; ld++) { - SET_KEX_LD(NIX_INTF_RX, lid, lt, ld, + for (ld = 0; ld < NPC_MAX_LD; ld++) + SET_KEX_LD(intf, lid, lt, ld, mkex->intf_lid_lt_ld[NIX_INTF_RX] [lid][lt][ld]); - - SET_KEX_LD(NIX_INTF_TX, lid, lt, ld, - mkex->intf_lid_lt_ld[NIX_INTF_TX] - [lid][lt][ld]); - } } } - + /* Program LFLAGS */ for (ld = 0; ld < NPC_MAX_LD; ld++) { - for (fl = 0; fl < NPC_MAX_LFL; fl++) { - SET_KEX_LDFLAGS(NIX_INTF_RX, ld, fl, + for (fl = 0; fl < NPC_MAX_LFL; fl++) + SET_KEX_LDFLAGS(intf, ld, fl, mkex->intf_ld_flags[NIX_INTF_RX] [ld][fl]); + } +} + +static void npc_program_mkex_tx(struct rvu *rvu, int blkaddr, + struct npc_mcam_kex *mkex, u8 intf) +{ + int lid, lt, ld, fl; - SET_KEX_LDFLAGS(NIX_INTF_TX, ld, fl, + if (is_npc_intf_rx(intf)) + return; + + rvu_write64(rvu, blkaddr, NPC_AF_INTFX_KEX_CFG(intf), + mkex->keyx_cfg[NIX_INTF_TX]); + + /* Program LDATA */ + for (lid = 0; lid < NPC_MAX_LID; lid++) { + for (lt = 0; lt < NPC_MAX_LT; lt++) { + for (ld = 0; ld < NPC_MAX_LD; ld++) + SET_KEX_LD(intf, lid, lt, ld, + mkex->intf_lid_lt_ld[NIX_INTF_TX] + [lid][lt][ld]); + } + } + /* Program LFLAGS */ + for (ld = 0; ld < NPC_MAX_LD; ld++) { + for (fl = 0; fl < NPC_MAX_LFL; fl++) + SET_KEX_LDFLAGS(intf, ld, fl, mkex->intf_ld_flags[NIX_INTF_TX] [ld][fl]); - } + } +} + +static void npc_program_mkex_profile(struct rvu *rvu, int blkaddr, + struct npc_mcam_kex *mkex) +{ + struct rvu_hwinfo *hw = rvu->hw; + u8 intf; + int ld; + + for (ld = 0; ld < NPC_MAX_LD; ld++) + rvu_write64(rvu, blkaddr, NPC_AF_KEX_LDATAX_FLAGS_CFG(ld), + mkex->kex_ld_flags[ld]); + + for (intf = 0; intf < hw->npc_intfs; intf++) { + npc_program_mkex_rx(rvu, blkaddr, mkex, intf); + npc_program_mkex_tx(rvu, blkaddr, mkex, intf); } } @@ -909,7 +996,7 @@ static void npc_program_kpu_profile(struct rvu *rvu, int blkaddr, int kpu, kpu, profile->cam_entries, profile->action_entries); } - max_entries = rvu_read64(rvu, blkaddr, NPC_AF_CONST1) & 0xFFF; + max_entries = rvu->hw->npc_kpu_entries; /* Program CAM match entries for previous KPU extracted data */ num_entries = min_t(int, profile->cam_entries, max_entries); @@ -964,9 +1051,6 @@ static void npc_parser_profile_init(struct rvu *rvu, int blkaddr) int num_pkinds, num_kpus, idx; struct npc_pkind *pkind; - /* Get HW limits */ - hw->npc_kpus = (rvu_read64(rvu, blkaddr, NPC_AF_CONST) >> 8) & 0x1F; - /* Disable all KPUs and their entries */ for (idx = 0; idx < hw->npc_kpus; idx++) { rvu_write64(rvu, blkaddr, @@ -1005,12 +1089,6 @@ static int npc_mcam_rsrcs_init(struct rvu *rvu, int blkaddr) int rsvd, err; u64 cfg; - /* Get HW limits */ - cfg = rvu_read64(rvu, blkaddr, NPC_AF_CONST); - mcam->banks = (cfg >> 44) & 0xF; - mcam->banksize = (cfg >> 28) & 0xFFFF; - mcam->counters.max = (cfg >> 48) & 0xFFFF; - /* Actual number of MCAM entries vary by entry size */ cfg = (rvu_read64(rvu, blkaddr, NPC_AF_INTFX_KEX_CFG(0)) >> 32) & 0x07; @@ -1077,12 +1155,6 @@ static int npc_mcam_rsrcs_init(struct rvu *rvu, int blkaddr) mcam->hprio_count = mcam->lprio_count; mcam->hprio_end = mcam->hprio_count; - /* Reserve last counter for MCAM RX miss action which is set to - * drop pkt. This way we will know how many pkts didn't match - * any MCAM entry. - */ - mcam->counters.max--; - mcam->rx_miss_act_cntr = mcam->counters.max; /* Allocate bitmap for managing MCAM counters and memory * for saving counter to RVU PFFUNC allocation mapping. @@ -1118,12 +1190,110 @@ free_mem: return -ENOMEM; } +static void rvu_npc_hw_init(struct rvu *rvu, int blkaddr) +{ + struct npc_pkind *pkind = &rvu->hw->pkind; + struct npc_mcam *mcam = &rvu->hw->mcam; + struct rvu_hwinfo *hw = rvu->hw; + u64 npc_const, npc_const1; + u64 npc_const2 = 0; + + npc_const = rvu_read64(rvu, blkaddr, NPC_AF_CONST); + npc_const1 = rvu_read64(rvu, blkaddr, NPC_AF_CONST1); + if (npc_const1 & BIT_ULL(63)) + npc_const2 = rvu_read64(rvu, blkaddr, NPC_AF_CONST2); + + pkind->rsrc.max = (npc_const1 >> 12) & 0xFFULL; + hw->npc_kpu_entries = npc_const1 & 0xFFFULL; + hw->npc_kpus = (npc_const >> 8) & 0x1FULL; + hw->npc_intfs = npc_const & 0xFULL; + hw->npc_counters = (npc_const >> 48) & 0xFFFFULL; + + mcam->banks = (npc_const >> 44) & 0xFULL; + mcam->banksize = (npc_const >> 28) & 0xFFFFULL; + /* Extended set */ + if (npc_const2) { + hw->npc_ext_set = true; + hw->npc_counters = (npc_const2 >> 16) & 0xFFFFULL; + mcam->banksize = npc_const2 & 0xFFFFULL; + } + + mcam->counters.max = hw->npc_counters; +} + +static void rvu_npc_setup_interfaces(struct rvu *rvu, int blkaddr) +{ + struct npc_mcam *mcam = &rvu->hw->mcam; + struct rvu_hwinfo *hw = rvu->hw; + u64 nibble_ena, rx_kex, tx_kex; + u8 intf; + + /* Reserve last counter for MCAM RX miss action which is set to + * drop packet. This way we will know how many pkts didn't match + * any MCAM entry. + */ + mcam->counters.max--; + mcam->rx_miss_act_cntr = mcam->counters.max; + + rx_kex = npc_mkex_default.keyx_cfg[NIX_INTF_RX]; + tx_kex = npc_mkex_default.keyx_cfg[NIX_INTF_TX]; + nibble_ena = FIELD_GET(NPC_PARSE_NIBBLE, rx_kex); + + nibble_ena = rvu_npc_get_tx_nibble_cfg(rvu, nibble_ena); + if (nibble_ena) { + tx_kex &= ~NPC_PARSE_NIBBLE; + tx_kex |= FIELD_PREP(NPC_PARSE_NIBBLE, nibble_ena); + npc_mkex_default.keyx_cfg[NIX_INTF_TX] = tx_kex; + } + + /* Configure RX interfaces */ + for (intf = 0; intf < hw->npc_intfs; intf++) { + if (is_npc_intf_tx(intf)) + continue; + + /* Set RX MCAM search key size. LA..LE (ltype only) + Channel */ + rvu_write64(rvu, blkaddr, NPC_AF_INTFX_KEX_CFG(intf), + rx_kex); + + /* If MCAM lookup doesn't result in a match, drop the received + * packet. And map this action to a counter to count dropped + * packets. + */ + rvu_write64(rvu, blkaddr, + NPC_AF_INTFX_MISS_ACT(intf), NIX_RX_ACTIONOP_DROP); + + /* NPC_AF_INTFX_MISS_STAT_ACT[14:12] - counter[11:9] + * NPC_AF_INTFX_MISS_STAT_ACT[8:0] - counter[8:0] + */ + rvu_write64(rvu, blkaddr, + NPC_AF_INTFX_MISS_STAT_ACT(intf), + ((mcam->rx_miss_act_cntr >> 9) << 12) | + BIT_ULL(9) | mcam->rx_miss_act_cntr); + } + + /* Configure TX interfaces */ + for (intf = 0; intf < hw->npc_intfs; intf++) { + if (is_npc_intf_rx(intf)) + continue; + + /* Extract Ltypes LID_LA to LID_LE */ + rvu_write64(rvu, blkaddr, NPC_AF_INTFX_KEX_CFG(intf), + tx_kex); + + /* Set TX miss action to UCAST_DEFAULT i.e + * transmit the packet on NIX LF SQ's default channel. + */ + rvu_write64(rvu, blkaddr, + NPC_AF_INTFX_MISS_ACT(intf), + NIX_TX_ACTIONOP_UCAST_DEFAULT); + } +} + int rvu_npc_init(struct rvu *rvu) { struct npc_kpu_profile_adapter *kpu = &rvu->kpu; struct npc_pkind *pkind = &rvu->hw->pkind; struct npc_mcam *mcam = &rvu->hw->mcam; - u64 cfg, nibble_ena, rx_kex, tx_kex; int blkaddr, entry, bank, err; blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0); @@ -1132,17 +1302,15 @@ int rvu_npc_init(struct rvu *rvu) return -ENODEV; } + rvu_npc_hw_init(rvu, blkaddr); + /* First disable all MCAM entries, to stop traffic towards NIXLFs */ - cfg = rvu_read64(rvu, blkaddr, NPC_AF_CONST); - for (bank = 0; bank < ((cfg >> 44) & 0xF); bank++) { - for (entry = 0; entry < ((cfg >> 28) & 0xFFFF); entry++) + for (bank = 0; bank < mcam->banks; bank++) { + for (entry = 0; entry < mcam->banksize; entry++) rvu_write64(rvu, blkaddr, NPC_AF_MCAMEX_BANKX_CFG(entry, bank), 0); } - /* Allocate resource bimap for pkind*/ - pkind->rsrc.max = (rvu_read64(rvu, blkaddr, - NPC_AF_CONST1) >> 12) & 0xFF; err = rvu_alloc_bitmap(&pkind->rsrc); if (err) return err; @@ -1180,21 +1348,7 @@ int rvu_npc_init(struct rvu *rvu) BIT_ULL(32) | BIT_ULL(24) | BIT_ULL(6) | BIT_ULL(2) | BIT_ULL(1)); - /* Set RX and TX side MCAM search key size. - * LA..LD (ltype only) + Channel - */ - rx_kex = npc_mkex_default.keyx_cfg[NIX_INTF_RX]; - tx_kex = npc_mkex_default.keyx_cfg[NIX_INTF_TX]; - nibble_ena = FIELD_GET(NPC_PARSE_NIBBLE, rx_kex); - rvu_write64(rvu, blkaddr, NPC_AF_INTFX_KEX_CFG(NIX_INTF_RX), rx_kex); - /* Due to an errata (35786) in A0 pass silicon, parse nibble enable - * configuration has to be identical for both Rx and Tx interfaces. - */ - if (is_rvu_96xx_B0(rvu)) { - tx_kex &= ~NPC_PARSE_NIBBLE; - tx_kex |= FIELD_PREP(NPC_PARSE_NIBBLE, nibble_ena); - } - rvu_write64(rvu, blkaddr, NPC_AF_INTFX_KEX_CFG(NIX_INTF_TX), tx_kex); + rvu_npc_setup_interfaces(rvu, blkaddr); err = npc_mcam_rsrcs_init(rvu, blkaddr); if (err) @@ -1203,20 +1357,6 @@ int rvu_npc_init(struct rvu *rvu) /* Configure MKEX profile */ npc_load_mkex_profile(rvu, blkaddr, rvu->mkex_pfl_name); - /* Set TX miss action to UCAST_DEFAULT i.e - * transmit the packet on NIX LF SQ's default channel. - */ - rvu_write64(rvu, blkaddr, NPC_AF_INTFX_MISS_ACT(NIX_INTF_TX), - NIX_TX_ACTIONOP_UCAST_DEFAULT); - - /* If MCAM lookup doesn't result in a match, drop the received packet. - * And map this action to a counter to count dropped pkts. - */ - rvu_write64(rvu, blkaddr, NPC_AF_INTFX_MISS_ACT(NIX_INTF_RX), - NIX_RX_ACTIONOP_DROP); - rvu_write64(rvu, blkaddr, NPC_AF_INTFX_MISS_STAT_ACT(NIX_INTF_RX), - BIT_ULL(9) | mcam->rx_miss_act_cntr); - return 0; } @@ -1307,10 +1447,13 @@ static void npc_map_mcam_entry_and_cntr(struct rvu *rvu, struct npc_mcam *mcam, /* Set mapping and increment counter's refcnt */ mcam->entry2cntr_map[entry] = cntr; mcam->cntr_refcnt[cntr]++; - /* Enable stats */ + /* Enable stats + * NPC_AF_MCAMEX_BANKX_STAT_ACT[14:12] - counter[11:9] + * NPC_AF_MCAMEX_BANKX_STAT_ACT[8:0] - counter[8:0] + */ rvu_write64(rvu, blkaddr, NPC_AF_MCAMEX_BANKX_STAT_ACT(index, bank), - BIT_ULL(9) | cntr); + ((cntr >> 9) << 12) | BIT_ULL(9) | cntr); } static void npc_unmap_mcam_entry_and_cntr(struct rvu *rvu, @@ -1789,9 +1932,11 @@ int rvu_mbox_handler_npc_mcam_write_entry(struct rvu *rvu, struct npc_mcam_write_entry_req *req, struct msg_rsp *rsp) { + struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, req->hdr.pcifunc); struct npc_mcam *mcam = &rvu->hw->mcam; u16 pcifunc = req->hdr.pcifunc; int blkaddr, rc; + u8 nix_intf; blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0); if (blkaddr < 0) @@ -1808,12 +1953,17 @@ int rvu_mbox_handler_npc_mcam_write_entry(struct rvu *rvu, goto exit; } - if (req->intf != NIX_INTF_RX && req->intf != NIX_INTF_TX) { + if (!is_npc_interface_valid(rvu, req->intf)) { rc = NPC_MCAM_INVALID_REQ; goto exit; } - npc_config_mcam_entry(rvu, mcam, blkaddr, req->entry, req->intf, + if (is_npc_intf_tx(req->intf)) + nix_intf = pfvf->nix_tx_intf; + else + nix_intf = pfvf->nix_rx_intf; + + npc_config_mcam_entry(rvu, mcam, blkaddr, req->entry, nix_intf, &req->entry_data, req->enable_entry); if (req->set_cntr) @@ -2141,6 +2291,7 @@ int rvu_mbox_handler_npc_mcam_alloc_and_write_entry(struct rvu *rvu, struct npc_mcam_alloc_and_write_entry_req *req, struct npc_mcam_alloc_and_write_entry_rsp *rsp) { + struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, req->hdr.pcifunc); struct npc_mcam_alloc_counter_req cntr_req; struct npc_mcam_alloc_counter_rsp cntr_rsp; struct npc_mcam_alloc_entry_req entry_req; @@ -2149,12 +2300,13 @@ int rvu_mbox_handler_npc_mcam_alloc_and_write_entry(struct rvu *rvu, u16 entry = NPC_MCAM_ENTRY_INVALID; u16 cntr = NPC_MCAM_ENTRY_INVALID; int blkaddr, rc; + u8 nix_intf; blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0); if (blkaddr < 0) return NPC_MCAM_INVALID_REQ; - if (req->intf != NIX_INTF_RX && req->intf != NIX_INTF_TX) + if (!is_npc_interface_valid(rvu, req->intf)) return NPC_MCAM_INVALID_REQ; /* Try to allocate a MCAM entry */ @@ -2196,7 +2348,13 @@ int rvu_mbox_handler_npc_mcam_alloc_and_write_entry(struct rvu *rvu, write_entry: mutex_lock(&mcam->lock); - npc_config_mcam_entry(rvu, mcam, blkaddr, entry, req->intf, + + if (is_npc_intf_tx(req->intf)) + nix_intf = pfvf->nix_tx_intf; + else + nix_intf = pfvf->nix_rx_intf; + + npc_config_mcam_entry(rvu, mcam, blkaddr, entry, nix_intf, &req->entry_data, req->enable_entry); if (req->alloc_cntr) @@ -2274,7 +2432,7 @@ int rvu_npc_update_rxvlan(struct rvu *rvu, u16 pcifunc, int nixlf) pfvf->entry.action = npc_get_mcam_action(rvu, mcam, blkaddr, index); enable = is_mcam_entry_enabled(rvu, mcam, blkaddr, index); npc_config_mcam_entry(rvu, mcam, blkaddr, pfvf->rxvlan_index, - NIX_INTF_RX, &pfvf->entry, enable); + pfvf->nix_rx_intf, &pfvf->entry, enable); return 0; } diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.c index 9d7c135c7965..e266f0c49559 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.c @@ -35,7 +35,7 @@ static struct hw_reg_map txsch_reg_map[NIX_TXSCH_LVL_CNT] = { {0x1200, 0x12E0} } }, {NIX_TXSCH_LVL_TL3, 3, 0xFFFF, {{0x1000, 0x10E0}, {0x1600, 0x1608}, {0x1610, 0x1618} } }, - {NIX_TXSCH_LVL_TL2, 2, 0xFFFF, {{0x0E00, 0x0EE0}, {0x1700, 0x1768} } }, + {NIX_TXSCH_LVL_TL2, 2, 0xFFFF, {{0x0E00, 0x0EE0}, {0x1700, 0x17B0} } }, {NIX_TXSCH_LVL_TL1, 1, 0xFFFF, {{0x0C00, 0x0D98} } }, }; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h index 7ca599b973c0..1f3379f12b81 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_reg.h @@ -54,20 +54,20 @@ #define RVU_PRIV_PFX_MSIX_CFG(a) (0x8000110 | (a) << 16) #define RVU_PRIV_PFX_ID_CFG(a) (0x8000120 | (a) << 16) #define RVU_PRIV_PFX_INT_CFG(a) (0x8000200 | (a) << 16) -#define RVU_PRIV_PFX_NIX0_CFG (0x8000300) +#define RVU_PRIV_PFX_NIXX_CFG(a) (0x8000300 | (a) << 3) #define RVU_PRIV_PFX_NPA_CFG (0x8000310) #define RVU_PRIV_PFX_SSO_CFG (0x8000320) #define RVU_PRIV_PFX_SSOW_CFG (0x8000330) #define RVU_PRIV_PFX_TIM_CFG (0x8000340) -#define RVU_PRIV_PFX_CPT0_CFG (0x8000350) +#define RVU_PRIV_PFX_CPTX_CFG(a) (0x8000350 | (a) << 3) #define RVU_PRIV_BLOCK_TYPEX_REV(a) (0x8000400 | (a) << 3) #define RVU_PRIV_HWVFX_INT_CFG(a) (0x8001280 | (a) << 16) -#define RVU_PRIV_HWVFX_NIX0_CFG (0x8001300) +#define RVU_PRIV_HWVFX_NIXX_CFG(a) (0x8001300 | (a) << 3) #define RVU_PRIV_HWVFX_NPA_CFG (0x8001310) #define RVU_PRIV_HWVFX_SSO_CFG (0x8001320) #define RVU_PRIV_HWVFX_SSOW_CFG (0x8001330) #define RVU_PRIV_HWVFX_TIM_CFG (0x8001340) -#define RVU_PRIV_HWVFX_CPT0_CFG (0x8001350) +#define RVU_PRIV_HWVFX_CPTX_CFG(a) (0x8001350 | (a) << 3) /* RVU PF registers */ #define RVU_PF_VFX_PFVF_MBOX0 (0x00000) @@ -446,6 +446,8 @@ #define NPC_AF_BLK_RST (0x00040) #define NPC_AF_MCAM_SCRUB_CTL (0x000a0) #define NPC_AF_KCAM_SCRUB_CTL (0x000b0) +#define NPC_AF_CONST2 (0x00100) +#define NPC_AF_CONST3 (0x00110) #define NPC_AF_KPUX_CFG(a) (0x00500 | (a) << 3) #define NPC_AF_PCK_CFG (0x00600) #define NPC_AF_PCK_DEF_OL2 (0x00610) @@ -469,20 +471,7 @@ (0x900000 | (a) << 16 | (b) << 12 | (c) << 5 | (d) << 3) #define NPC_AF_INTFX_LDATAX_FLAGSX_CFG(a, b, c) \ (0x980000 | (a) << 16 | (b) << 12 | (c) << 3) -#define NPC_AF_MCAMEX_BANKX_CAMX_INTF(a, b, c) \ - (0x1000000ull | (a) << 10 | (b) << 6 | (c) << 3) -#define NPC_AF_MCAMEX_BANKX_CAMX_W0(a, b, c) \ - (0x1000010ull | (a) << 10 | (b) << 6 | (c) << 3) -#define NPC_AF_MCAMEX_BANKX_CAMX_W1(a, b, c) \ - (0x1000020ull | (a) << 10 | (b) << 6 | (c) << 3) -#define NPC_AF_MCAMEX_BANKX_CFG(a, b) (0x1800000ull | (a) << 8 | (b) << 4) -#define NPC_AF_MCAMEX_BANKX_STAT_ACT(a, b) \ - (0x1880000 | (a) << 8 | (b) << 4) -#define NPC_AF_MATCH_STATX(a) (0x1880008 | (a) << 8) #define NPC_AF_INTFX_MISS_STAT_ACT(a) (0x1880040 + (a) * 0x8) -#define NPC_AF_MCAMEX_BANKX_ACTION(a, b) (0x1900000ull | (a) << 8 | (b) << 4) -#define NPC_AF_MCAMEX_BANKX_TAG_ACT(a, b) \ - (0x1900008 | (a) << 8 | (b) << 4) #define NPC_AF_INTFX_MISS_ACT(a) (0x1a00000 | (a) << 4) #define NPC_AF_INTFX_MISS_TAG_ACT(a) (0x1b00008 | (a) << 4) #define NPC_AF_MCAM_BANKX_HITX(a, b) (0x1c80000 | (a) << 8 | (b) << 4) @@ -499,6 +488,70 @@ #define NPC_AF_DBG_DATAX(a) (0x3001400 | (a) << 4) #define NPC_AF_DBG_RESULTX(a) (0x3001800 | (a) << 4) +#define NPC_AF_MCAMEX_BANKX_CAMX_INTF(a, b, c) ({ \ + u64 offset; \ + \ + offset = (0x1000000ull | (a) << 10 | (b) << 6 | (c) << 3); \ + if (rvu->hw->npc_ext_set) \ + offset = (0x8000000ull | (a) << 8 | (b) << 22 | (c) << 3); \ + offset; }) + +#define NPC_AF_MCAMEX_BANKX_CAMX_W0(a, b, c) ({ \ + u64 offset; \ + \ + offset = (0x1000010ull | (a) << 10 | (b) << 6 | (c) << 3); \ + if (rvu->hw->npc_ext_set) \ + offset = (0x8000010ull | (a) << 8 | (b) << 22 | (c) << 3); \ + offset; }) + +#define NPC_AF_MCAMEX_BANKX_CAMX_W1(a, b, c) ({ \ + u64 offset; \ + \ + offset = (0x1000020ull | (a) << 10 | (b) << 6 | (c) << 3); \ + if (rvu->hw->npc_ext_set) \ + offset = (0x8000020ull | (a) << 8 | (b) << 22 | (c) << 3); \ + offset; }) + +#define NPC_AF_MCAMEX_BANKX_CFG(a, b) ({ \ + u64 offset; \ + \ + offset = (0x1800000ull | (a) << 8 | (b) << 4); \ + if (rvu->hw->npc_ext_set) \ + offset = (0x8000038ull | (a) << 8 | (b) << 22); \ + offset; }) + +#define NPC_AF_MCAMEX_BANKX_ACTION(a, b) ({ \ + u64 offset; \ + \ + offset = (0x1900000ull | (a) << 8 | (b) << 4); \ + if (rvu->hw->npc_ext_set) \ + offset = (0x8000040ull | (a) << 8 | (b) << 22); \ + offset; }) \ + +#define NPC_AF_MCAMEX_BANKX_TAG_ACT(a, b) ({ \ + u64 offset; \ + \ + offset = (0x1900008ull | (a) << 8 | (b) << 4); \ + if (rvu->hw->npc_ext_set) \ + offset = (0x8000048ull | (a) << 8 | (b) << 22); \ + offset; }) \ + +#define NPC_AF_MCAMEX_BANKX_STAT_ACT(a, b) ({ \ + u64 offset; \ + \ + offset = (0x1880000ull | (a) << 8 | (b) << 4); \ + if (rvu->hw->npc_ext_set) \ + offset = (0x8000050ull | (a) << 8 | (b) << 22); \ + offset; }) \ + +#define NPC_AF_MATCH_STATX(a) ({ \ + u64 offset; \ + \ + offset = (0x1880008ull | (a) << 8); \ + if (rvu->hw->npc_ext_set) \ + offset = (0x8000078ull | (a) << 8); \ + offset; }) \ + /* NDC */ #define NDC_AF_CONST (0x00000) #define NDC_AF_CLK_EN (0x00020) diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h index a3ecb5de9000..9a7eb074cdc2 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h @@ -14,6 +14,8 @@ /* RVU Block revision IDs */ #define RVU_BLK_RVUM_REVID 0x01 +#define RVU_MULTI_BLK_VER 0x7ULL + /* RVU Block Address Enumeration */ enum rvu_block_addr_e { BLKADDR_RVUM = 0x0ULL, @@ -31,7 +33,9 @@ enum rvu_block_addr_e { BLKADDR_NDC_NIX0_RX = 0xcULL, BLKADDR_NDC_NIX0_TX = 0xdULL, BLKADDR_NDC_NPA0 = 0xeULL, - BLK_COUNT = 0xfULL, + BLKADDR_NDC_NIX1_RX = 0x10ULL, + BLKADDR_NDC_NIX1_TX = 0x11ULL, + BLK_COUNT = 0x12ULL, }; /* RVU Block Type Enumeration */ diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index d2581090f9a4..9f3d6715748e 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -531,8 +531,10 @@ static int otx2_get_link(struct otx2_nic *pfvf) link = 4 * ((map >> 8) & 0xF) + ((map >> 4) & 0xF); } /* LBK channel */ - if (pfvf->hw.tx_chan_base < SDP_CHAN_BASE) - link = 12; + if (pfvf->hw.tx_chan_base < SDP_CHAN_BASE) { + map = pfvf->hw.tx_chan_base & 0x7FF; + link = pfvf->hw.cgx_links | ((map >> 8) & 0xF); + } return link; } @@ -1237,7 +1239,7 @@ int otx2_sq_aura_pool_init(struct otx2_nic *pfvf) sq = &qset->sq[qidx]; sq->sqb_count = 0; - sq->sqb_ptrs = kcalloc(num_sqbs, sizeof(u64 *), GFP_KERNEL); + sq->sqb_ptrs = kcalloc(num_sqbs, sizeof(*sq->sqb_ptrs), GFP_KERNEL); if (!sq->sqb_ptrs) return -ENOMEM; @@ -1503,6 +1505,8 @@ void mbox_handler_nix_lf_alloc(struct otx2_nic *pfvf, pfvf->hw.tx_chan_base = rsp->tx_chan_base; pfvf->hw.lso_tsov4_idx = rsp->lso_tsov4_idx; pfvf->hw.lso_tsov6_idx = rsp->lso_tsov6_idx; + pfvf->hw.cgx_links = rsp->cgx_links; + pfvf->hw.lbk_links = rsp->lbk_links; } EXPORT_SYMBOL(mbox_handler_nix_lf_alloc); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index d6253f2a414d..386cb08497e4 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -197,6 +197,8 @@ struct otx2_hw { struct otx2_drv_stats drv_stats; u64 cgx_rx_stats[CGX_RX_STATS_COUNT]; u64 cgx_tx_stats[CGX_TX_STATS_COUNT]; + u8 cgx_links; /* No. of CGX links present in HW */ + u8 lbk_links; /* No. of LBK links present in HW */ }; struct otx2_vf_config { diff --git a/drivers/net/ethernet/mellanox/mlx4/fw_qos.h b/drivers/net/ethernet/mellanox/mlx4/fw_qos.h index 582997577a04..954b86faac29 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw_qos.h +++ b/drivers/net/ethernet/mellanox/mlx4/fw_qos.h @@ -135,7 +135,7 @@ int mlx4_SET_VPORT_QOS_get(struct mlx4_dev *dev, u8 port, u8 vport, * @dev: mlx4_dev. * @port: Physical port number. * @vport: Vport id. - * @out_param: Array of mlx4_vport_qos_param which holds the requested values. + * @in_param: Array of mlx4_vport_qos_param which holds the requested values. * * Returns 0 on success or a negative mlx4_core errno code. **/ diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index 1187ef1375e2..394f43add85c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -300,7 +300,7 @@ static const char *resource_str(enum mlx4_resource rt) case RES_FS_RULE: return "RES_FS_RULE"; case RES_XRCD: return "RES_XRCD"; default: return "Unknown resource type !!!"; - }; + } } static void rem_slave_vlans(struct mlx4_dev *dev, int slave); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 2d477f9a8cb7..83a67ca43a41 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -81,7 +81,7 @@ mlx5_core-$(CONFIG_MLX5_EN_TLS) += en_accel/tls.o en_accel/tls_rxtx.o en_accel/t mlx5_core-$(CONFIG_MLX5_SW_STEERING) += steering/dr_domain.o steering/dr_table.o \ steering/dr_matcher.o steering/dr_rule.o \ - steering/dr_icm_pool.o \ + steering/dr_icm_pool.o steering/dr_buddy.o \ steering/dr_ste.o steering/dr_send.o \ steering/dr_cmd.o steering/dr_fw.o \ steering/dr_action.o steering/fs_dr.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index 38e4f19d69f8..43271a3856ca 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -2,6 +2,8 @@ /* Copyright (c) 2019 Mellanox Technologies. */ #include "en/params.h" +#include "en/txrx.h" +#include "en_accel/tls_rxtx.h" static inline bool mlx5e_rx_is_xdp(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk) @@ -152,3 +154,35 @@ u16 mlx5e_get_rq_headroom(struct mlx5_core_dev *mdev, return is_linear_skb ? mlx5e_get_linear_rq_headroom(params, xsk) : 0; } + +u16 mlx5e_calc_sq_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *params) +{ + bool is_mpwqe = MLX5E_GET_PFLAG(params, MLX5E_PFLAG_SKB_TX_MPWQE); + u16 stop_room; + + stop_room = mlx5e_tls_get_stop_room(mdev, params); + stop_room += mlx5e_stop_room_for_wqe(MLX5_SEND_WQE_MAX_WQEBBS); + if (is_mpwqe) + /* A MPWQE can take up to the maximum-sized WQE + all the normal + * stop room can be taken if a new packet breaks the active + * MPWQE session and allocates its WQEs right away. + */ + stop_room += mlx5e_stop_room_for_wqe(MLX5_SEND_WQE_MAX_WQEBBS); + + return stop_room; +} + +int mlx5e_validate_params(struct mlx5e_priv *priv, struct mlx5e_params *params) +{ + size_t sq_size = 1 << params->log_sq_size; + u16 stop_room; + + stop_room = mlx5e_calc_sq_stop_room(priv->mdev, params); + if (stop_room >= sq_size) { + netdev_err(priv->netdev, "Stop room %hu is bigger than the SQ size %zu\n", + stop_room, sq_size); + return -EINVAL; + } + + return 0; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h index a87273e801b2..187007ad3349 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h @@ -30,6 +30,7 @@ struct mlx5e_sq_param { u32 sqc[MLX5_ST_SZ_DW(sqc)]; struct mlx5_wq_param wq; bool is_mpw; + u16 stop_room; }; struct mlx5e_channel_param { @@ -124,4 +125,7 @@ void mlx5e_build_xdpsq_param(struct mlx5e_priv *priv, struct mlx5e_params *params, struct mlx5e_sq_param *param); +u16 mlx5e_calc_sq_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *params); +int mlx5e_validate_params(struct mlx5e_priv *priv, struct mlx5e_params *params); + #endif /* __MLX5_EN_PARAMS_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c index b140e13fdcc8..d16def68ecff 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c @@ -13,20 +13,20 @@ struct mlx5e_dump_wqe { (DIV_ROUND_UP(sizeof(struct mlx5e_dump_wqe), MLX5_SEND_WQE_BB)) static u8 -mlx5e_ktls_dumps_num_wqes(struct mlx5e_txqsq *sq, unsigned int nfrags, +mlx5e_ktls_dumps_num_wqes(struct mlx5e_params *params, unsigned int nfrags, unsigned int sync_len) { /* Given the MTU and sync_len, calculates an upper bound for the * number of DUMP WQEs needed for the TX resync of a record. */ - return nfrags + DIV_ROUND_UP(sync_len, sq->hw_mtu); + return nfrags + DIV_ROUND_UP(sync_len, MLX5E_SW2HW_MTU(params, params->sw_mtu)); } -u16 mlx5e_ktls_get_stop_room(struct mlx5e_txqsq *sq) +u16 mlx5e_ktls_get_stop_room(struct mlx5e_params *params) { u16 num_dumps, stop_room = 0; - num_dumps = mlx5e_ktls_dumps_num_wqes(sq, MAX_SKB_FRAGS, TLS_MAX_PAYLOAD_SIZE); + num_dumps = mlx5e_ktls_dumps_num_wqes(params, MAX_SKB_FRAGS, TLS_MAX_PAYLOAD_SIZE); stop_room += mlx5e_stop_room_for_wqe(MLX5E_TLS_SET_STATIC_PARAMS_WQEBBS); stop_room += mlx5e_stop_room_for_wqe(MLX5E_TLS_SET_PROGRESS_PARAMS_WQEBBS); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_txrx.h index 7521c9be735b..ee04e916fa21 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_txrx.h @@ -14,7 +14,7 @@ struct mlx5e_accel_tx_tls_state { u32 tls_tisn; }; -u16 mlx5e_ktls_get_stop_room(struct mlx5e_txqsq *sq); +u16 mlx5e_ktls_get_stop_room(struct mlx5e_params *params); bool mlx5e_ktls_handle_tx_skb(struct tls_context *tls_ctx, struct mlx5e_txqsq *sq, struct sk_buff *skb, int datalen, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c index 6982b193ee8a..f51c04284e4d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c @@ -385,15 +385,13 @@ void mlx5e_tls_handle_rx_skb_metadata(struct mlx5e_rq *rq, struct sk_buff *skb, *cqe_bcnt -= MLX5E_METADATA_ETHER_LEN; } -u16 mlx5e_tls_get_stop_room(struct mlx5e_txqsq *sq) +u16 mlx5e_tls_get_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *params) { - struct mlx5_core_dev *mdev = sq->channel->mdev; - if (!mlx5_accel_is_tls_device(mdev)) return 0; if (mlx5_accel_is_ktls_device(mdev)) - return mlx5e_ktls_get_stop_room(sq); + return mlx5e_ktls_get_stop_room(params); /* FPGA */ /* Resync SKB. */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h index 5f162ad2ee8f..9923132c9440 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h @@ -43,7 +43,7 @@ #include "en.h" #include "en/txrx.h" -u16 mlx5e_tls_get_stop_room(struct mlx5e_txqsq *sq); +u16 mlx5e_tls_get_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *params); bool mlx5e_tls_handle_tx_skb(struct net_device *netdev, struct mlx5e_txqsq *sq, struct sk_buff *skb, struct mlx5e_accel_tx_tls_state *state); @@ -71,7 +71,7 @@ mlx5e_accel_is_tls(struct mlx5_cqe64 *cqe, struct sk_buff *skb) { return false; static inline void mlx5e_tls_handle_rx_skb(struct mlx5e_rq *rq, struct sk_buff *skb, struct mlx5_cqe64 *cqe, u32 *cqe_bcnt) {} -static inline u16 mlx5e_tls_get_stop_room(struct mlx5e_txqsq *sq) +static inline u16 mlx5e_tls_get_stop_room(struct mlx5_core_dev *mdev, struct mlx5e_params *params) { return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index d25a56ec6876..42e61dc28ead 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -32,6 +32,7 @@ #include "en.h" #include "en/port.h" +#include "en/params.h" #include "en/xsk/pool.h" #include "lib/clock.h" @@ -369,6 +370,10 @@ int mlx5e_ethtool_set_ringparam(struct mlx5e_priv *priv, new_channels.params.log_rq_mtu_frames = log_rq_size; new_channels.params.log_sq_size = log_sq_size; + err = mlx5e_validate_params(priv, &new_channels.params); + if (err) + goto unlock; + if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { priv->channels.params = new_channels.params; goto unlock; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index b3f02aac7f26..8226a9d2b45e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1121,28 +1121,6 @@ static int mlx5e_alloc_txqsq_db(struct mlx5e_txqsq *sq, int numa) return 0; } -static int mlx5e_calc_sq_stop_room(struct mlx5e_txqsq *sq, u8 log_sq_size) -{ - int sq_size = 1 << log_sq_size; - - sq->stop_room = mlx5e_tls_get_stop_room(sq); - sq->stop_room += mlx5e_stop_room_for_wqe(MLX5_SEND_WQE_MAX_WQEBBS); - if (test_bit(MLX5E_SQ_STATE_MPWQE, &sq->state)) - /* A MPWQE can take up to the maximum-sized WQE + all the normal - * stop room can be taken if a new packet breaks the active - * MPWQE session and allocates its WQEs right away. - */ - sq->stop_room += mlx5e_stop_room_for_wqe(MLX5_SEND_WQE_MAX_WQEBBS); - - if (WARN_ON(sq->stop_room >= sq_size)) { - netdev_err(sq->channel->netdev, "Stop room %hu is bigger than the SQ size %d\n", - sq->stop_room, sq_size); - return -ENOSPC; - } - - return 0; -} - static void mlx5e_tx_err_cqe_work(struct work_struct *recover_work); static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, int txq_ix, @@ -1176,9 +1154,7 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, set_bit(MLX5E_SQ_STATE_TLS, &sq->state); if (param->is_mpw) set_bit(MLX5E_SQ_STATE_MPWQE, &sq->state); - err = mlx5e_calc_sq_stop_room(sq, params->log_sq_size); - if (err) - return err; + sq->stop_room = param->stop_room; param->wq.db_numa_node = cpu_to_node(c->cpu); err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, wq, &sq->wq_ctrl); @@ -2225,6 +2201,7 @@ static void mlx5e_build_sq_param(struct mlx5e_priv *priv, MLX5_SET(wq, wq, log_wq_sz, params->log_sq_size); MLX5_SET(sqc, sqc, allow_swp, allow_swp); param->is_mpw = MLX5E_GET_PFLAG(params, MLX5E_PFLAG_SKB_TX_MPWQE); + param->stop_room = mlx5e_calc_sq_stop_room(priv->mdev, params); mlx5e_build_tx_cq_param(priv, params, ¶m->cqp); } @@ -3999,6 +3976,9 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu, new_channels.params = *params; new_channels.params.sw_mtu = new_mtu; + err = mlx5e_validate_params(priv, &new_channels.params); + if (err) + goto out; if (params->xdp_prog && !mlx5e_rx_is_linear_skb(&new_channels.params, NULL)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 8ebfe782f95e..4ea5d6ddf56a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -189,19 +189,21 @@ u32 mlx5_eq_poll_irq_disabled(struct mlx5_eq_comp *eq) return count_eqe; } -static void mlx5_eq_async_int_lock(struct mlx5_eq_async *eq, unsigned long *flags) +static void mlx5_eq_async_int_lock(struct mlx5_eq_async *eq, bool recovery, + unsigned long *flags) __acquires(&eq->lock) { - if (in_irq()) + if (!recovery) spin_lock(&eq->lock); else spin_lock_irqsave(&eq->lock, *flags); } -static void mlx5_eq_async_int_unlock(struct mlx5_eq_async *eq, unsigned long *flags) +static void mlx5_eq_async_int_unlock(struct mlx5_eq_async *eq, bool recovery, + unsigned long *flags) __releases(&eq->lock) { - if (in_irq()) + if (!recovery) spin_unlock(&eq->lock); else spin_unlock_irqrestore(&eq->lock, *flags); @@ -223,11 +225,13 @@ static int mlx5_eq_async_int(struct notifier_block *nb, struct mlx5_eqe *eqe; unsigned long flags; int num_eqes = 0; + bool recovery; dev = eq->dev; eqt = dev->priv.eq_table; - mlx5_eq_async_int_lock(eq_async, &flags); + recovery = action == ASYNC_EQ_RECOVER; + mlx5_eq_async_int_lock(eq_async, recovery, &flags); eqe = next_eqe_sw(eq); if (!eqe) @@ -249,9 +253,9 @@ static int mlx5_eq_async_int(struct notifier_block *nb, out: eq_update_ci(eq, 1); - mlx5_eq_async_int_unlock(eq_async, &flags); + mlx5_eq_async_int_unlock(eq_async, recovery, &flags); - return unlikely(action == ASYNC_EQ_RECOVER) ? num_eqes : 0; + return unlikely(recovery) ? num_eqes : 0; } void mlx5_cmd_eq_recover(struct mlx5_core_dev *dev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.h index 656f96be6e20..89ef592656c8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.h @@ -47,11 +47,12 @@ /** * enum mlx5_fpga_access_type - Enumerated the different methods possible for * accessing the device memory address space + * + * @MLX5_FPGA_ACCESS_TYPE_I2C: Use the slow CX-FPGA I2C bus + * @MLX5_FPGA_ACCESS_TYPE_DONTCARE: Use the fastest available method */ enum mlx5_fpga_access_type { - /** Use the slow CX-FPGA I2C bus */ MLX5_FPGA_ACCESS_TYPE_I2C = 0x0, - /** Use the fastest available method */ MLX5_FPGA_ACCESS_TYPE_DONTCARE = 0x0, }; @@ -113,6 +114,7 @@ struct mlx5_fpga_conn_attr { * subsequent receives. */ void (*recv_cb)(void *cb_arg, struct mlx5_fpga_dma_buf *buf); + /** @cb_arg: A context to be passed to recv_cb callback */ void *cb_arg; }; @@ -145,7 +147,7 @@ void mlx5_fpga_sbu_conn_destroy(struct mlx5_fpga_conn *conn); /** * mlx5_fpga_sbu_conn_sendmsg() - Queue the transmission of a packet - * @fdev: An FPGA SBU connection + * @conn: An FPGA SBU connection * @buf: The packet buffer * * Queues a packet for transmission over an FPGA SBU connection. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_buddy.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_buddy.c new file mode 100644 index 000000000000..7df11a019df9 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_buddy.c @@ -0,0 +1,170 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2004 Topspin Communications. All rights reserved. + * Copyright (c) 2005 - 2008 Mellanox Technologies. All rights reserved. + * Copyright (c) 2006 - 2007 Cisco Systems, Inc. All rights reserved. + * Copyright (c) 2020 NVIDIA CORPORATION. All rights reserved. + */ + +#include "dr_types.h" + +int mlx5dr_buddy_init(struct mlx5dr_icm_buddy_mem *buddy, + unsigned int max_order) +{ + int i; + + buddy->max_order = max_order; + + INIT_LIST_HEAD(&buddy->list_node); + INIT_LIST_HEAD(&buddy->used_list); + INIT_LIST_HEAD(&buddy->hot_list); + + buddy->bitmap = kcalloc(buddy->max_order + 1, + sizeof(*buddy->bitmap), + GFP_KERNEL); + buddy->num_free = kcalloc(buddy->max_order + 1, + sizeof(*buddy->num_free), + GFP_KERNEL); + + if (!buddy->bitmap || !buddy->num_free) + goto err_free_all; + + /* Allocating max_order bitmaps, one for each order */ + + for (i = 0; i <= buddy->max_order; ++i) { + unsigned int size = 1 << (buddy->max_order - i); + + buddy->bitmap[i] = bitmap_zalloc(size, GFP_KERNEL); + if (!buddy->bitmap[i]) + goto err_out_free_each_bit_per_order; + } + + /* In the beginning, we have only one order that is available for + * use (the biggest one), so mark the first bit in both bitmaps. + */ + + bitmap_set(buddy->bitmap[buddy->max_order], 0, 1); + + buddy->num_free[buddy->max_order] = 1; + + return 0; + +err_out_free_each_bit_per_order: + for (i = 0; i <= buddy->max_order; ++i) + bitmap_free(buddy->bitmap[i]); + +err_free_all: + kfree(buddy->num_free); + kfree(buddy->bitmap); + return -ENOMEM; +} + +void mlx5dr_buddy_cleanup(struct mlx5dr_icm_buddy_mem *buddy) +{ + int i; + + list_del(&buddy->list_node); + + for (i = 0; i <= buddy->max_order; ++i) + bitmap_free(buddy->bitmap[i]); + + kfree(buddy->num_free); + kfree(buddy->bitmap); +} + +static int dr_buddy_find_free_seg(struct mlx5dr_icm_buddy_mem *buddy, + unsigned int start_order, + unsigned int *segment, + unsigned int *order) +{ + unsigned int seg, order_iter, m; + + for (order_iter = start_order; + order_iter <= buddy->max_order; ++order_iter) { + if (!buddy->num_free[order_iter]) + continue; + + m = 1 << (buddy->max_order - order_iter); + seg = find_first_bit(buddy->bitmap[order_iter], m); + + if (WARN(seg >= m, + "ICM Buddy: failed finding free mem for order %d\n", + order_iter)) + return -ENOMEM; + + break; + } + + if (order_iter > buddy->max_order) + return -ENOMEM; + + *segment = seg; + *order = order_iter; + return 0; +} + +/** + * mlx5dr_buddy_alloc_mem() - Update second level bitmap. + * @buddy: Buddy to update. + * @order: Order of the buddy to update. + * @segment: Segment number. + * + * This function finds the first area of the ICM memory managed by this buddy. + * It uses the data structures of the buddy system in order to find the first + * area of free place, starting from the current order till the maximum order + * in the system. + * + * Return: 0 when segment is set, non-zero error status otherwise. + * + * The function returns the location (segment) in the whole buddy ICM memory + * area - the index of the memory segment that is available for use. + */ +int mlx5dr_buddy_alloc_mem(struct mlx5dr_icm_buddy_mem *buddy, + unsigned int order, + unsigned int *segment) +{ + unsigned int seg, order_iter; + int err; + + err = dr_buddy_find_free_seg(buddy, order, &seg, &order_iter); + if (err) + return err; + + bitmap_clear(buddy->bitmap[order_iter], seg, 1); + --buddy->num_free[order_iter]; + + /* If we found free memory in some order that is bigger than the + * required order, we need to split every order between the required + * order and the order that we found into two parts, and mark accordingly. + */ + while (order_iter > order) { + --order_iter; + seg <<= 1; + bitmap_set(buddy->bitmap[order_iter], seg ^ 1, 1); + ++buddy->num_free[order_iter]; + } + + seg <<= order; + *segment = seg; + + return 0; +} + +void mlx5dr_buddy_free_mem(struct mlx5dr_icm_buddy_mem *buddy, + unsigned int seg, unsigned int order) +{ + seg >>= order; + + /* Whenever a segment is free, + * the mem is added to the buddy that gave it. + */ + while (test_bit(seg ^ 1, buddy->bitmap[order])) { + bitmap_clear(buddy->bitmap[order], seg ^ 1, 1); + --buddy->num_free[order]; + seg >>= 1; + ++order; + } + bitmap_set(buddy->bitmap[order], seg, 1); + + ++buddy->num_free[order]; +} + diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c index 6bd34b293007..ebc879052e42 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c @@ -93,12 +93,12 @@ int mlx5dr_cmd_query_device(struct mlx5_core_dev *mdev, caps->gvmi = MLX5_CAP_GEN(mdev, vhca_id); caps->flex_protocols = MLX5_CAP_GEN(mdev, flex_parser_protocols); - if (mlx5dr_matcher_supp_flex_parser_icmp_v4(caps)) { + if (caps->flex_protocols & MLX5_FLEX_PARSER_ICMP_V4_ENABLED) { caps->flex_parser_id_icmp_dw0 = MLX5_CAP_GEN(mdev, flex_parser_id_icmp_dw0); caps->flex_parser_id_icmp_dw1 = MLX5_CAP_GEN(mdev, flex_parser_id_icmp_dw1); } - if (mlx5dr_matcher_supp_flex_parser_icmp_v6(caps)) { + if (caps->flex_protocols & MLX5_FLEX_PARSER_ICMP_V6_ENABLED) { caps->flex_parser_id_icmpv6_dw0 = MLX5_CAP_GEN(mdev, flex_parser_id_icmpv6_dw0); caps->flex_parser_id_icmpv6_dw1 = diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c index cc33515b9aba..66c24767e3b0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c @@ -4,50 +4,16 @@ #include "dr_types.h" #define DR_ICM_MODIFY_HDR_ALIGN_BASE 64 -#define DR_ICM_SYNC_THRESHOLD (64 * 1024 * 1024) - -struct mlx5dr_icm_pool; - -struct mlx5dr_icm_bucket { - struct mlx5dr_icm_pool *pool; - - /* Chunks that aren't visible to HW not directly and not in cache */ - struct list_head free_list; - unsigned int free_list_count; - - /* Used chunks, HW may be accessing this memory */ - struct list_head used_list; - unsigned int used_list_count; - - /* HW may be accessing this memory but at some future, - * undetermined time, it might cease to do so. Before deciding to call - * sync_ste, this list is moved to sync_list - */ - struct list_head hot_list; - unsigned int hot_list_count; - - /* Pending sync list, entries from the hot list are moved to this list. - * sync_ste is executed and then sync_list is concatenated to the free list - */ - struct list_head sync_list; - unsigned int sync_list_count; - - u32 total_chunks; - u32 num_of_entries; - u32 entry_size; - /* protect the ICM bucket */ - struct mutex mutex; -}; +#define DR_ICM_SYNC_THRESHOLD_POOL (64 * 1024 * 1024) struct mlx5dr_icm_pool { - struct mlx5dr_icm_bucket *buckets; enum mlx5dr_icm_type icm_type; enum mlx5dr_icm_chunk_size max_log_chunk_sz; - enum mlx5dr_icm_chunk_size num_of_buckets; - struct list_head icm_mr_list; - /* protect the ICM MR list */ - struct mutex mr_mutex; struct mlx5dr_domain *dmn; + /* memory management */ + struct mutex mutex; /* protect the ICM pool and ICM buddy */ + struct list_head buddy_mem_list; + u64 hot_memory_size; }; struct mlx5dr_icm_dm { @@ -58,13 +24,11 @@ struct mlx5dr_icm_dm { }; struct mlx5dr_icm_mr { - struct mlx5dr_icm_pool *pool; struct mlx5_core_mkey mkey; struct mlx5dr_icm_dm dm; - size_t used_length; + struct mlx5dr_domain *dmn; size_t length; u64 icm_start_addr; - struct list_head mr_list; }; static int dr_icm_create_dm_mkey(struct mlx5_core_dev *mdev, @@ -107,8 +71,7 @@ dr_icm_pool_mr_create(struct mlx5dr_icm_pool *pool) if (!icm_mr) return NULL; - icm_mr->pool = pool; - INIT_LIST_HEAD(&icm_mr->mr_list); + icm_mr->dmn = pool->dmn; icm_mr->dm.length = mlx5dr_icm_pool_chunk_size_to_byte(pool->max_log_chunk_sz, pool->icm_type); @@ -150,8 +113,6 @@ dr_icm_pool_mr_create(struct mlx5dr_icm_pool *pool) goto free_mkey; } - list_add_tail(&icm_mr->mr_list, &pool->icm_mr_list); - return icm_mr; free_mkey: @@ -166,10 +127,9 @@ free_icm_mr: static void dr_icm_pool_mr_destroy(struct mlx5dr_icm_mr *icm_mr) { - struct mlx5_core_dev *mdev = icm_mr->pool->dmn->mdev; + struct mlx5_core_dev *mdev = icm_mr->dmn->mdev; struct mlx5dr_icm_dm *dm = &icm_mr->dm; - list_del(&icm_mr->mr_list); mlx5_core_destroy_mkey(mdev, &icm_mr->mkey); mlx5_dm_sw_icm_dealloc(mdev, dm->type, dm->length, 0, dm->addr, dm->obj_id); @@ -178,19 +138,17 @@ static void dr_icm_pool_mr_destroy(struct mlx5dr_icm_mr *icm_mr) static int dr_icm_chunk_ste_init(struct mlx5dr_icm_chunk *chunk) { - struct mlx5dr_icm_bucket *bucket = chunk->bucket; - - chunk->ste_arr = kvzalloc(bucket->num_of_entries * + chunk->ste_arr = kvzalloc(chunk->num_of_entries * sizeof(chunk->ste_arr[0]), GFP_KERNEL); if (!chunk->ste_arr) return -ENOMEM; - chunk->hw_ste_arr = kvzalloc(bucket->num_of_entries * + chunk->hw_ste_arr = kvzalloc(chunk->num_of_entries * DR_STE_SIZE_REDUCED, GFP_KERNEL); if (!chunk->hw_ste_arr) goto out_free_ste_arr; - chunk->miss_list = kvmalloc(bucket->num_of_entries * + chunk->miss_list = kvmalloc(chunk->num_of_entries * sizeof(chunk->miss_list[0]), GFP_KERNEL); if (!chunk->miss_list) goto out_free_hw_ste_arr; @@ -204,72 +162,6 @@ out_free_ste_arr: return -ENOMEM; } -static int dr_icm_chunks_create(struct mlx5dr_icm_bucket *bucket) -{ - size_t mr_free_size, mr_req_size, mr_row_size; - struct mlx5dr_icm_pool *pool = bucket->pool; - struct mlx5dr_icm_mr *icm_mr = NULL; - struct mlx5dr_icm_chunk *chunk; - int i, err = 0; - - mr_req_size = bucket->num_of_entries * bucket->entry_size; - mr_row_size = mlx5dr_icm_pool_chunk_size_to_byte(pool->max_log_chunk_sz, - pool->icm_type); - mutex_lock(&pool->mr_mutex); - if (!list_empty(&pool->icm_mr_list)) { - icm_mr = list_last_entry(&pool->icm_mr_list, - struct mlx5dr_icm_mr, mr_list); - - if (icm_mr) - mr_free_size = icm_mr->dm.length - icm_mr->used_length; - } - - if (!icm_mr || mr_free_size < mr_row_size) { - icm_mr = dr_icm_pool_mr_create(pool); - if (!icm_mr) { - err = -ENOMEM; - goto out_err; - } - } - - /* Create memory aligned chunks */ - for (i = 0; i < mr_row_size / mr_req_size; i++) { - chunk = kvzalloc(sizeof(*chunk), GFP_KERNEL); - if (!chunk) { - err = -ENOMEM; - goto out_err; - } - - chunk->bucket = bucket; - chunk->rkey = icm_mr->mkey.key; - /* mr start addr is zero based */ - chunk->mr_addr = icm_mr->used_length; - chunk->icm_addr = (uintptr_t)icm_mr->icm_start_addr + icm_mr->used_length; - icm_mr->used_length += mr_req_size; - chunk->num_of_entries = bucket->num_of_entries; - chunk->byte_size = chunk->num_of_entries * bucket->entry_size; - - if (pool->icm_type == DR_ICM_TYPE_STE) { - err = dr_icm_chunk_ste_init(chunk); - if (err) - goto out_free_chunk; - } - - INIT_LIST_HEAD(&chunk->chunk_list); - list_add(&chunk->chunk_list, &bucket->free_list); - bucket->free_list_count++; - bucket->total_chunks++; - } - mutex_unlock(&pool->mr_mutex); - return 0; - -out_free_chunk: - kvfree(chunk); -out_err: - mutex_unlock(&pool->mr_mutex); - return err; -} - static void dr_icm_chunk_ste_cleanup(struct mlx5dr_icm_chunk *chunk) { kvfree(chunk->miss_list); @@ -277,166 +169,199 @@ static void dr_icm_chunk_ste_cleanup(struct mlx5dr_icm_chunk *chunk) kvfree(chunk->ste_arr); } -static void dr_icm_chunk_destroy(struct mlx5dr_icm_chunk *chunk) +static enum mlx5dr_icm_type +get_chunk_icm_type(struct mlx5dr_icm_chunk *chunk) +{ + return chunk->buddy_mem->pool->icm_type; +} + +static void dr_icm_chunk_destroy(struct mlx5dr_icm_chunk *chunk, + struct mlx5dr_icm_buddy_mem *buddy) { - struct mlx5dr_icm_bucket *bucket = chunk->bucket; + enum mlx5dr_icm_type icm_type = get_chunk_icm_type(chunk); + buddy->used_memory -= chunk->byte_size; list_del(&chunk->chunk_list); - bucket->total_chunks--; - if (bucket->pool->icm_type == DR_ICM_TYPE_STE) + if (icm_type == DR_ICM_TYPE_STE) dr_icm_chunk_ste_cleanup(chunk); kvfree(chunk); } -static void dr_icm_bucket_init(struct mlx5dr_icm_pool *pool, - struct mlx5dr_icm_bucket *bucket, - enum mlx5dr_icm_chunk_size chunk_size) +static int dr_icm_buddy_create(struct mlx5dr_icm_pool *pool) { - if (pool->icm_type == DR_ICM_TYPE_STE) - bucket->entry_size = DR_STE_SIZE; - else - bucket->entry_size = DR_MODIFY_ACTION_SIZE; - - bucket->num_of_entries = mlx5dr_icm_pool_chunk_size_to_entries(chunk_size); - bucket->pool = pool; - mutex_init(&bucket->mutex); - INIT_LIST_HEAD(&bucket->free_list); - INIT_LIST_HEAD(&bucket->used_list); - INIT_LIST_HEAD(&bucket->hot_list); - INIT_LIST_HEAD(&bucket->sync_list); + struct mlx5dr_icm_buddy_mem *buddy; + struct mlx5dr_icm_mr *icm_mr; + + icm_mr = dr_icm_pool_mr_create(pool); + if (!icm_mr) + return -ENOMEM; + + buddy = kvzalloc(sizeof(*buddy), GFP_KERNEL); + if (!buddy) + goto free_mr; + + if (mlx5dr_buddy_init(buddy, pool->max_log_chunk_sz)) + goto err_free_buddy; + + buddy->icm_mr = icm_mr; + buddy->pool = pool; + + /* add it to the -start- of the list in order to search in it first */ + list_add(&buddy->list_node, &pool->buddy_mem_list); + + return 0; + +err_free_buddy: + kvfree(buddy); +free_mr: + dr_icm_pool_mr_destroy(icm_mr); + return -ENOMEM; } -static void dr_icm_bucket_cleanup(struct mlx5dr_icm_bucket *bucket) +static void dr_icm_buddy_destroy(struct mlx5dr_icm_buddy_mem *buddy) { struct mlx5dr_icm_chunk *chunk, *next; - mutex_destroy(&bucket->mutex); - list_splice_tail_init(&bucket->sync_list, &bucket->free_list); - list_splice_tail_init(&bucket->hot_list, &bucket->free_list); + list_for_each_entry_safe(chunk, next, &buddy->hot_list, chunk_list) + dr_icm_chunk_destroy(chunk, buddy); + + list_for_each_entry_safe(chunk, next, &buddy->used_list, chunk_list) + dr_icm_chunk_destroy(chunk, buddy); - list_for_each_entry_safe(chunk, next, &bucket->free_list, chunk_list) - dr_icm_chunk_destroy(chunk); + dr_icm_pool_mr_destroy(buddy->icm_mr); - WARN_ON(bucket->total_chunks != 0); + mlx5dr_buddy_cleanup(buddy); - /* Cleanup of unreturned chunks */ - list_for_each_entry_safe(chunk, next, &bucket->used_list, chunk_list) - dr_icm_chunk_destroy(chunk); + kvfree(buddy); } -static u64 dr_icm_hot_mem_size(struct mlx5dr_icm_pool *pool) +static struct mlx5dr_icm_chunk * +dr_icm_chunk_create(struct mlx5dr_icm_pool *pool, + enum mlx5dr_icm_chunk_size chunk_size, + struct mlx5dr_icm_buddy_mem *buddy_mem_pool, + unsigned int seg) { - u64 hot_size = 0; - int chunk_order; + struct mlx5dr_icm_chunk *chunk; + int offset; - for (chunk_order = 0; chunk_order < pool->num_of_buckets; chunk_order++) - hot_size += pool->buckets[chunk_order].hot_list_count * - mlx5dr_icm_pool_chunk_size_to_byte(chunk_order, pool->icm_type); + chunk = kvzalloc(sizeof(*chunk), GFP_KERNEL); + if (!chunk) + return NULL; - return hot_size; -} + offset = mlx5dr_icm_pool_dm_type_to_entry_size(pool->icm_type) * seg; + + chunk->rkey = buddy_mem_pool->icm_mr->mkey.key; + chunk->mr_addr = offset; + chunk->icm_addr = + (uintptr_t)buddy_mem_pool->icm_mr->icm_start_addr + offset; + chunk->num_of_entries = + mlx5dr_icm_pool_chunk_size_to_entries(chunk_size); + chunk->byte_size = + mlx5dr_icm_pool_chunk_size_to_byte(chunk_size, pool->icm_type); + chunk->seg = seg; + + if (pool->icm_type == DR_ICM_TYPE_STE && dr_icm_chunk_ste_init(chunk)) { + mlx5dr_err(pool->dmn, + "Failed to init ste arrays (order: %d)\n", + chunk_size); + goto out_free_chunk; + } -static bool dr_icm_reuse_hot_entries(struct mlx5dr_icm_pool *pool, - struct mlx5dr_icm_bucket *bucket) -{ - u64 bytes_for_sync; + buddy_mem_pool->used_memory += chunk->byte_size; + chunk->buddy_mem = buddy_mem_pool; + INIT_LIST_HEAD(&chunk->chunk_list); - bytes_for_sync = dr_icm_hot_mem_size(pool); - if (bytes_for_sync < DR_ICM_SYNC_THRESHOLD || !bucket->hot_list_count) - return false; + /* chunk now is part of the used_list */ + list_add_tail(&chunk->chunk_list, &buddy_mem_pool->used_list); - return true; -} + return chunk; -static void dr_icm_chill_bucket_start(struct mlx5dr_icm_bucket *bucket) -{ - list_splice_tail_init(&bucket->hot_list, &bucket->sync_list); - bucket->sync_list_count += bucket->hot_list_count; - bucket->hot_list_count = 0; +out_free_chunk: + kvfree(chunk); + return NULL; } -static void dr_icm_chill_bucket_end(struct mlx5dr_icm_bucket *bucket) +static bool dr_icm_pool_is_sync_required(struct mlx5dr_icm_pool *pool) { - list_splice_tail_init(&bucket->sync_list, &bucket->free_list); - bucket->free_list_count += bucket->sync_list_count; - bucket->sync_list_count = 0; -} + if (pool->hot_memory_size > DR_ICM_SYNC_THRESHOLD_POOL) + return true; -static void dr_icm_chill_bucket_abort(struct mlx5dr_icm_bucket *bucket) -{ - list_splice_tail_init(&bucket->sync_list, &bucket->hot_list); - bucket->hot_list_count += bucket->sync_list_count; - bucket->sync_list_count = 0; + return false; } -static void dr_icm_chill_buckets_start(struct mlx5dr_icm_pool *pool, - struct mlx5dr_icm_bucket *cb, - bool buckets[DR_CHUNK_SIZE_MAX]) +static int dr_icm_pool_sync_all_buddy_pools(struct mlx5dr_icm_pool *pool) { - struct mlx5dr_icm_bucket *bucket; - int i; - - for (i = 0; i < pool->num_of_buckets; i++) { - bucket = &pool->buckets[i]; - if (bucket == cb) { - dr_icm_chill_bucket_start(bucket); - continue; - } + struct mlx5dr_icm_buddy_mem *buddy, *tmp_buddy; + int err; - /* Freeing the mutex is done at the end of that process, after - * sync_ste was executed at dr_icm_chill_buckets_end func. - */ - if (mutex_trylock(&bucket->mutex)) { - dr_icm_chill_bucket_start(bucket); - buckets[i] = true; - } + err = mlx5dr_cmd_sync_steering(pool->dmn->mdev); + if (err) { + mlx5dr_err(pool->dmn, "Failed to sync to HW (err: %d)\n", err); + return err; } -} -static void dr_icm_chill_buckets_end(struct mlx5dr_icm_pool *pool, - struct mlx5dr_icm_bucket *cb, - bool buckets[DR_CHUNK_SIZE_MAX]) -{ - struct mlx5dr_icm_bucket *bucket; - int i; - - for (i = 0; i < pool->num_of_buckets; i++) { - bucket = &pool->buckets[i]; - if (bucket == cb) { - dr_icm_chill_bucket_end(bucket); - continue; - } + list_for_each_entry_safe(buddy, tmp_buddy, &pool->buddy_mem_list, list_node) { + struct mlx5dr_icm_chunk *chunk, *tmp_chunk; - if (!buckets[i]) - continue; + list_for_each_entry_safe(chunk, tmp_chunk, &buddy->hot_list, chunk_list) { + mlx5dr_buddy_free_mem(buddy, chunk->seg, + ilog2(chunk->num_of_entries)); + pool->hot_memory_size -= chunk->byte_size; + dr_icm_chunk_destroy(chunk, buddy); + } - dr_icm_chill_bucket_end(bucket); - mutex_unlock(&bucket->mutex); + if (!buddy->used_memory && pool->icm_type == DR_ICM_TYPE_STE) + dr_icm_buddy_destroy(buddy); } + + return 0; } -static void dr_icm_chill_buckets_abort(struct mlx5dr_icm_pool *pool, - struct mlx5dr_icm_bucket *cb, - bool buckets[DR_CHUNK_SIZE_MAX]) +static int dr_icm_handle_buddies_get_mem(struct mlx5dr_icm_pool *pool, + enum mlx5dr_icm_chunk_size chunk_size, + struct mlx5dr_icm_buddy_mem **buddy, + unsigned int *seg) { - struct mlx5dr_icm_bucket *bucket; - int i; - - for (i = 0; i < pool->num_of_buckets; i++) { - bucket = &pool->buckets[i]; - if (bucket == cb) { - dr_icm_chill_bucket_abort(bucket); - continue; - } + struct mlx5dr_icm_buddy_mem *buddy_mem_pool; + bool new_mem = false; + int err; - if (!buckets[i]) - continue; +alloc_buddy_mem: + /* find the next free place from the buddy list */ + list_for_each_entry(buddy_mem_pool, &pool->buddy_mem_list, list_node) { + err = mlx5dr_buddy_alloc_mem(buddy_mem_pool, + chunk_size, seg); + if (!err) + goto found; + + if (WARN_ON(new_mem)) { + /* We have new memory pool, first in the list */ + mlx5dr_err(pool->dmn, + "No memory for order: %d\n", + chunk_size); + goto out; + } + } - dr_icm_chill_bucket_abort(bucket); - mutex_unlock(&bucket->mutex); + /* no more available allocators in that pool, create new */ + err = dr_icm_buddy_create(pool); + if (err) { + mlx5dr_err(pool->dmn, + "Failed creating buddy for order %d\n", + chunk_size); + goto out; } + + /* mark we have new memory, first in list */ + new_mem = true; + goto alloc_buddy_mem; + +found: + *buddy = buddy_mem_pool; +out: + return err; } /* Allocate an ICM chunk, each chunk holds a piece of ICM memory and @@ -446,68 +371,48 @@ struct mlx5dr_icm_chunk * mlx5dr_icm_alloc_chunk(struct mlx5dr_icm_pool *pool, enum mlx5dr_icm_chunk_size chunk_size) { - struct mlx5dr_icm_chunk *chunk = NULL; /* Fix compilation warning */ - bool buckets[DR_CHUNK_SIZE_MAX] = {}; - struct mlx5dr_icm_bucket *bucket; - int err; + struct mlx5dr_icm_chunk *chunk = NULL; + struct mlx5dr_icm_buddy_mem *buddy; + unsigned int seg; + int ret; if (chunk_size > pool->max_log_chunk_sz) return NULL; - bucket = &pool->buckets[chunk_size]; - - mutex_lock(&bucket->mutex); - - /* Take chunk from pool if available, otherwise allocate new chunks */ - if (list_empty(&bucket->free_list)) { - if (dr_icm_reuse_hot_entries(pool, bucket)) { - dr_icm_chill_buckets_start(pool, bucket, buckets); - err = mlx5dr_cmd_sync_steering(pool->dmn->mdev); - if (err) { - dr_icm_chill_buckets_abort(pool, bucket, buckets); - mlx5dr_err(pool->dmn, "Sync_steering failed\n"); - chunk = NULL; - goto out; - } - dr_icm_chill_buckets_end(pool, bucket, buckets); - } else { - dr_icm_chunks_create(bucket); - } - } + mutex_lock(&pool->mutex); + /* find mem, get back the relevant buddy pool and seg in that mem */ + ret = dr_icm_handle_buddies_get_mem(pool, chunk_size, &buddy, &seg); + if (ret) + goto out; - if (!list_empty(&bucket->free_list)) { - chunk = list_last_entry(&bucket->free_list, - struct mlx5dr_icm_chunk, - chunk_list); - if (chunk) { - list_del_init(&chunk->chunk_list); - list_add_tail(&chunk->chunk_list, &bucket->used_list); - bucket->free_list_count--; - bucket->used_list_count++; - } - } + chunk = dr_icm_chunk_create(pool, chunk_size, buddy, seg); + if (!chunk) + goto out_err; + + goto out; + +out_err: + mlx5dr_buddy_free_mem(buddy, seg, chunk_size); out: - mutex_unlock(&bucket->mutex); + mutex_unlock(&pool->mutex); return chunk; } void mlx5dr_icm_free_chunk(struct mlx5dr_icm_chunk *chunk) { - struct mlx5dr_icm_bucket *bucket = chunk->bucket; + struct mlx5dr_icm_buddy_mem *buddy = chunk->buddy_mem; + struct mlx5dr_icm_pool *pool = buddy->pool; - if (bucket->pool->icm_type == DR_ICM_TYPE_STE) { - memset(chunk->ste_arr, 0, - bucket->num_of_entries * sizeof(chunk->ste_arr[0])); - memset(chunk->hw_ste_arr, 0, - bucket->num_of_entries * DR_STE_SIZE_REDUCED); - } + /* move the memory to the waiting list AKA "hot" */ + mutex_lock(&pool->mutex); + list_move_tail(&chunk->chunk_list, &buddy->hot_list); + pool->hot_memory_size += chunk->byte_size; + + /* Check if we have chunks that are waiting for sync-ste */ + if (dr_icm_pool_is_sync_required(pool)) + dr_icm_pool_sync_all_buddy_pools(pool); - mutex_lock(&bucket->mutex); - list_del_init(&chunk->chunk_list); - list_add_tail(&chunk->chunk_list, &bucket->hot_list); - bucket->hot_list_count++; - bucket->used_list_count--; - mutex_unlock(&bucket->mutex); + mutex_unlock(&pool->mutex); } struct mlx5dr_icm_pool *mlx5dr_icm_pool_create(struct mlx5dr_domain *dmn, @@ -515,7 +420,6 @@ struct mlx5dr_icm_pool *mlx5dr_icm_pool_create(struct mlx5dr_domain *dmn, { enum mlx5dr_icm_chunk_size max_log_chunk_sz; struct mlx5dr_icm_pool *pool; - int i; if (icm_type == DR_ICM_TYPE_STE) max_log_chunk_sz = dmn->info.max_log_sw_icm_sz; @@ -526,43 +430,24 @@ struct mlx5dr_icm_pool *mlx5dr_icm_pool_create(struct mlx5dr_domain *dmn, if (!pool) return NULL; - pool->buckets = kcalloc(max_log_chunk_sz + 1, - sizeof(pool->buckets[0]), - GFP_KERNEL); - if (!pool->buckets) - goto free_pool; - pool->dmn = dmn; pool->icm_type = icm_type; pool->max_log_chunk_sz = max_log_chunk_sz; - pool->num_of_buckets = max_log_chunk_sz + 1; - INIT_LIST_HEAD(&pool->icm_mr_list); - for (i = 0; i < pool->num_of_buckets; i++) - dr_icm_bucket_init(pool, &pool->buckets[i], i); + INIT_LIST_HEAD(&pool->buddy_mem_list); - mutex_init(&pool->mr_mutex); + mutex_init(&pool->mutex); return pool; - -free_pool: - kvfree(pool); - return NULL; } void mlx5dr_icm_pool_destroy(struct mlx5dr_icm_pool *pool) { - struct mlx5dr_icm_mr *icm_mr, *next; - int i; - - mutex_destroy(&pool->mr_mutex); - - list_for_each_entry_safe(icm_mr, next, &pool->icm_mr_list, mr_list) - dr_icm_pool_mr_destroy(icm_mr); + struct mlx5dr_icm_buddy_mem *buddy, *tmp_buddy; - for (i = 0; i < pool->num_of_buckets; i++) - dr_icm_bucket_cleanup(&pool->buckets[i]); + list_for_each_entry_safe(buddy, tmp_buddy, &pool->buddy_mem_list, list_node) + dr_icm_buddy_destroy(buddy); - kfree(pool->buckets); + mutex_destroy(&pool->mutex); kvfree(pool); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c index 7df883686d46..cb5202e17856 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c @@ -85,7 +85,7 @@ static bool dr_mask_is_ttl_set(struct mlx5dr_match_spec *spec) (_misc2)._inner_outer##_first_mpls_s_bos || \ (_misc2)._inner_outer##_first_mpls_ttl) -static bool dr_mask_is_gre_set(struct mlx5dr_match_misc *misc) +static bool dr_mask_is_tnl_gre_set(struct mlx5dr_match_misc *misc) { return (misc->gre_key_h || misc->gre_key_l || misc->gre_protocol || misc->gre_c_present || @@ -98,12 +98,12 @@ static bool dr_mask_is_gre_set(struct mlx5dr_match_misc *misc) (_misc2).outer_first_mpls_over_##gre_udp##_s_bos || \ (_misc2).outer_first_mpls_over_##gre_udp##_ttl) -#define DR_MASK_IS_FLEX_PARSER_0_SET(_misc2) ( \ +#define DR_MASK_IS_TNL_MPLS_SET(_misc2) ( \ DR_MASK_IS_OUTER_MPLS_OVER_GRE_UDP_SET((_misc2), gre) || \ DR_MASK_IS_OUTER_MPLS_OVER_GRE_UDP_SET((_misc2), udp)) static bool -dr_mask_is_misc3_vxlan_gpe_set(struct mlx5dr_match_misc3 *misc3) +dr_mask_is_vxlan_gpe_set(struct mlx5dr_match_misc3 *misc3) { return (misc3->outer_vxlan_gpe_vni || misc3->outer_vxlan_gpe_next_protocol || @@ -111,21 +111,20 @@ dr_mask_is_misc3_vxlan_gpe_set(struct mlx5dr_match_misc3 *misc3) } static bool -dr_matcher_supp_flex_parser_vxlan_gpe(struct mlx5dr_cmd_caps *caps) +dr_matcher_supp_vxlan_gpe(struct mlx5dr_cmd_caps *caps) { - return caps->flex_protocols & - MLX5_FLEX_PARSER_VXLAN_GPE_ENABLED; + return caps->flex_protocols & MLX5_FLEX_PARSER_VXLAN_GPE_ENABLED; } static bool -dr_mask_is_flex_parser_tnl_vxlan_gpe_set(struct mlx5dr_match_param *mask, - struct mlx5dr_domain *dmn) +dr_mask_is_tnl_vxlan_gpe(struct mlx5dr_match_param *mask, + struct mlx5dr_domain *dmn) { - return dr_mask_is_misc3_vxlan_gpe_set(&mask->misc3) && - dr_matcher_supp_flex_parser_vxlan_gpe(&dmn->info.caps); + return dr_mask_is_vxlan_gpe_set(&mask->misc3) && + dr_matcher_supp_vxlan_gpe(&dmn->info.caps); } -static bool dr_mask_is_misc_geneve_set(struct mlx5dr_match_misc *misc) +static bool dr_mask_is_tnl_geneve_set(struct mlx5dr_match_misc *misc) { return misc->geneve_vni || misc->geneve_oam || @@ -134,26 +133,46 @@ static bool dr_mask_is_misc_geneve_set(struct mlx5dr_match_misc *misc) } static bool -dr_matcher_supp_flex_parser_geneve(struct mlx5dr_cmd_caps *caps) +dr_matcher_supp_tnl_geneve(struct mlx5dr_cmd_caps *caps) { - return caps->flex_protocols & - MLX5_FLEX_PARSER_GENEVE_ENABLED; + return caps->flex_protocols & MLX5_FLEX_PARSER_GENEVE_ENABLED; } static bool -dr_mask_is_flex_parser_tnl_geneve_set(struct mlx5dr_match_param *mask, - struct mlx5dr_domain *dmn) +dr_mask_is_tnl_geneve(struct mlx5dr_match_param *mask, + struct mlx5dr_domain *dmn) { - return dr_mask_is_misc_geneve_set(&mask->misc) && - dr_matcher_supp_flex_parser_geneve(&dmn->info.caps); + return dr_mask_is_tnl_geneve_set(&mask->misc) && + dr_matcher_supp_tnl_geneve(&dmn->info.caps); } -static bool dr_mask_is_flex_parser_icmpv6_set(struct mlx5dr_match_misc3 *misc3) +static int dr_matcher_supp_icmp_v4(struct mlx5dr_cmd_caps *caps) +{ + return caps->flex_protocols & MLX5_FLEX_PARSER_ICMP_V4_ENABLED; +} + +static int dr_matcher_supp_icmp_v6(struct mlx5dr_cmd_caps *caps) +{ + return caps->flex_protocols & MLX5_FLEX_PARSER_ICMP_V6_ENABLED; +} + +static bool dr_mask_is_icmpv6_set(struct mlx5dr_match_misc3 *misc3) { return (misc3->icmpv6_type || misc3->icmpv6_code || misc3->icmpv6_header_data); } +static bool dr_mask_is_icmp(struct mlx5dr_match_param *mask, + struct mlx5dr_domain *dmn) +{ + if (DR_MASK_IS_ICMPV4_SET(&mask->misc3)) + return dr_matcher_supp_icmp_v4(&dmn->info.caps); + else if (dr_mask_is_icmpv6_set(&mask->misc3)) + return dr_matcher_supp_icmp_v6(&dmn->info.caps); + + return false; +} + static bool dr_mask_is_wqe_metadata_set(struct mlx5dr_match_misc2 *misc2) { return misc2->metadata_reg_a; @@ -257,7 +276,7 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher, if (dr_mask_is_smac_set(&mask.outer) && dr_mask_is_dmac_set(&mask.outer)) { - mlx5dr_ste_build_eth_l2_src_des(&sb[idx++], &mask, + mlx5dr_ste_build_eth_l2_src_dst(&sb[idx++], &mask, inner, rx); } @@ -277,8 +296,8 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher, inner, rx); if (DR_MASK_IS_ETH_L4_SET(mask.outer, mask.misc, outer)) - mlx5dr_ste_build_ipv6_l3_l4(&sb[idx++], &mask, - inner, rx); + mlx5dr_ste_build_eth_ipv6_l3_l4(&sb[idx++], &mask, + inner, rx); } else { if (dr_mask_is_ipv4_5_tuple_set(&mask.outer)) mlx5dr_ste_build_eth_l3_ipv4_5_tuple(&sb[idx++], &mask, @@ -289,14 +308,12 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher, inner, rx); } - if (dr_mask_is_flex_parser_tnl_vxlan_gpe_set(&mask, dmn)) - mlx5dr_ste_build_flex_parser_tnl_vxlan_gpe(&sb[idx++], - &mask, - inner, rx); - else if (dr_mask_is_flex_parser_tnl_geneve_set(&mask, dmn)) - mlx5dr_ste_build_flex_parser_tnl_geneve(&sb[idx++], - &mask, - inner, rx); + if (dr_mask_is_tnl_vxlan_gpe(&mask, dmn)) + mlx5dr_ste_build_tnl_vxlan_gpe(&sb[idx++], &mask, + inner, rx); + else if (dr_mask_is_tnl_geneve(&mask, dmn)) + mlx5dr_ste_build_tnl_geneve(&sb[idx++], &mask, + inner, rx); if (DR_MASK_IS_ETH_L4_MISC_SET(mask.misc3, outer)) mlx5dr_ste_build_eth_l4_misc(&sb[idx++], &mask, inner, rx); @@ -304,22 +321,18 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher, if (DR_MASK_IS_FIRST_MPLS_SET(mask.misc2, outer)) mlx5dr_ste_build_mpls(&sb[idx++], &mask, inner, rx); - if (DR_MASK_IS_FLEX_PARSER_0_SET(mask.misc2)) - mlx5dr_ste_build_flex_parser_0(&sb[idx++], &mask, - inner, rx); + if (DR_MASK_IS_TNL_MPLS_SET(mask.misc2)) + mlx5dr_ste_build_tnl_mpls(&sb[idx++], &mask, inner, rx); - if ((DR_MASK_IS_FLEX_PARSER_ICMPV4_SET(&mask.misc3) && - mlx5dr_matcher_supp_flex_parser_icmp_v4(&dmn->info.caps)) || - (dr_mask_is_flex_parser_icmpv6_set(&mask.misc3) && - mlx5dr_matcher_supp_flex_parser_icmp_v6(&dmn->info.caps))) { - ret = mlx5dr_ste_build_flex_parser_1(&sb[idx++], - &mask, &dmn->info.caps, - inner, rx); + if (dr_mask_is_icmp(&mask, dmn)) { + ret = mlx5dr_ste_build_icmp(&sb[idx++], + &mask, &dmn->info.caps, + inner, rx); if (ret) return ret; } - if (dr_mask_is_gre_set(&mask.misc)) - mlx5dr_ste_build_gre(&sb[idx++], &mask, inner, rx); + if (dr_mask_is_tnl_gre_set(&mask.misc)) + mlx5dr_ste_build_tnl_gre(&sb[idx++], &mask, inner, rx); } /* Inner */ @@ -334,7 +347,7 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher, if (dr_mask_is_smac_set(&mask.inner) && dr_mask_is_dmac_set(&mask.inner)) { - mlx5dr_ste_build_eth_l2_src_des(&sb[idx++], + mlx5dr_ste_build_eth_l2_src_dst(&sb[idx++], &mask, inner, rx); } @@ -354,8 +367,8 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher, inner, rx); if (DR_MASK_IS_ETH_L4_SET(mask.inner, mask.misc, inner)) - mlx5dr_ste_build_ipv6_l3_l4(&sb[idx++], &mask, - inner, rx); + mlx5dr_ste_build_eth_ipv6_l3_l4(&sb[idx++], &mask, + inner, rx); } else { if (dr_mask_is_ipv4_5_tuple_set(&mask.inner)) mlx5dr_ste_build_eth_l3_ipv4_5_tuple(&sb[idx++], &mask, @@ -372,8 +385,8 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher, if (DR_MASK_IS_FIRST_MPLS_SET(mask.misc2, inner)) mlx5dr_ste_build_mpls(&sb[idx++], &mask, inner, rx); - if (DR_MASK_IS_FLEX_PARSER_0_SET(mask.misc2)) - mlx5dr_ste_build_flex_parser_0(&sb[idx++], &mask, inner, rx); + if (DR_MASK_IS_TNL_MPLS_SET(mask.misc2)) + mlx5dr_ste_build_tnl_mpls(&sb[idx++], &mask, inner, rx); } /* Empty matcher, takes all */ if (matcher->match_criteria == DR_MATCHER_CRITERIA_EMPTY) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c index b01aaec75622..d275823bff2f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c @@ -1090,7 +1090,7 @@ static int dr_ste_build_eth_l2_src_des_tag(struct mlx5dr_match_param *value, return 0; } -void mlx5dr_ste_build_eth_l2_src_des(struct mlx5dr_ste_build *sb, +void mlx5dr_ste_build_eth_l2_src_dst(struct mlx5dr_ste_build *sb, struct mlx5dr_match_param *mask, bool inner, bool rx) { @@ -1594,9 +1594,9 @@ static int dr_ste_build_ipv6_l3_l4_tag(struct mlx5dr_match_param *value, return 0; } -void mlx5dr_ste_build_ipv6_l3_l4(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask, - bool inner, bool rx) +void mlx5dr_ste_build_eth_ipv6_l3_l4(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) { dr_ste_build_ipv6_l3_l4_bit_mask(mask, inner, sb->bit_mask); @@ -1693,8 +1693,8 @@ static int dr_ste_build_gre_tag(struct mlx5dr_match_param *value, return 0; } -void mlx5dr_ste_build_gre(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask, bool inner, bool rx) +void mlx5dr_ste_build_tnl_gre(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, bool inner, bool rx) { dr_ste_build_gre_bit_mask(mask, inner, sb->bit_mask); @@ -1771,9 +1771,9 @@ static int dr_ste_build_flex_parser_0_tag(struct mlx5dr_match_param *value, return 0; } -void mlx5dr_ste_build_flex_parser_0(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask, - bool inner, bool rx) +void mlx5dr_ste_build_tnl_mpls(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) { dr_ste_build_flex_parser_0_bit_mask(mask, inner, sb->bit_mask); @@ -1792,8 +1792,8 @@ static int dr_ste_build_flex_parser_1_bit_mask(struct mlx5dr_match_param *mask, struct mlx5dr_cmd_caps *caps, u8 *bit_mask) { + bool is_ipv4_mask = DR_MASK_IS_ICMPV4_SET(&mask->misc3); struct mlx5dr_match_misc3 *misc_3_mask = &mask->misc3; - bool is_ipv4_mask = DR_MASK_IS_FLEX_PARSER_ICMPV4_SET(misc_3_mask); u32 icmp_header_data_mask; u32 icmp_type_mask; u32 icmp_code_mask; @@ -1869,7 +1869,7 @@ static int dr_ste_build_flex_parser_1_tag(struct mlx5dr_match_param *value, u32 icmp_code; bool is_ipv4; - is_ipv4 = DR_MASK_IS_FLEX_PARSER_ICMPV4_SET(misc_3); + is_ipv4 = DR_MASK_IS_ICMPV4_SET(misc_3); if (is_ipv4) { icmp_header_data = misc_3->icmpv4_header_data; icmp_type = misc_3->icmpv4_type; @@ -1928,10 +1928,10 @@ static int dr_ste_build_flex_parser_1_tag(struct mlx5dr_match_param *value, return 0; } -int mlx5dr_ste_build_flex_parser_1(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask, - struct mlx5dr_cmd_caps *caps, - bool inner, bool rx) +int mlx5dr_ste_build_icmp(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + struct mlx5dr_cmd_caps *caps, + bool inner, bool rx) { int ret; @@ -2069,9 +2069,9 @@ dr_ste_build_flex_parser_tnl_vxlan_gpe_tag(struct mlx5dr_match_param *value, return 0; } -void mlx5dr_ste_build_flex_parser_tnl_vxlan_gpe(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask, - bool inner, bool rx) +void mlx5dr_ste_build_tnl_vxlan_gpe(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) { dr_ste_build_flex_parser_tnl_vxlan_gpe_bit_mask(mask, inner, sb->bit_mask); @@ -2122,9 +2122,9 @@ dr_ste_build_flex_parser_tnl_geneve_tag(struct mlx5dr_match_param *value, return 0; } -void mlx5dr_ste_build_flex_parser_tnl_geneve(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask, - bool inner, bool rx) +void mlx5dr_ste_build_tnl_geneve(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) { dr_ste_build_flex_parser_tnl_geneve_bit_mask(mask, sb->bit_mask); sb->rx = rx; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h index f50f3b107aa3..3e423c8ed22f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h @@ -114,7 +114,7 @@ enum mlx5dr_ipv { struct mlx5dr_icm_pool; struct mlx5dr_icm_chunk; -struct mlx5dr_icm_bucket; +struct mlx5dr_icm_buddy_mem; struct mlx5dr_ste_htbl; struct mlx5dr_match_param; struct mlx5dr_cmd_caps; @@ -288,7 +288,7 @@ int mlx5dr_ste_build_ste_arr(struct mlx5dr_matcher *matcher, struct mlx5dr_matcher_rx_tx *nic_matcher, struct mlx5dr_match_param *value, u8 *ste_arr); -void mlx5dr_ste_build_eth_l2_src_des(struct mlx5dr_ste_build *builder, +void mlx5dr_ste_build_eth_l2_src_dst(struct mlx5dr_ste_build *builder, struct mlx5dr_match_param *mask, bool inner, bool rx); void mlx5dr_ste_build_eth_l3_ipv4_5_tuple(struct mlx5dr_ste_build *sb, @@ -312,31 +312,31 @@ void mlx5dr_ste_build_eth_l2_dst(struct mlx5dr_ste_build *sb, void mlx5dr_ste_build_eth_l2_tnl(struct mlx5dr_ste_build *sb, struct mlx5dr_match_param *mask, bool inner, bool rx); -void mlx5dr_ste_build_ipv6_l3_l4(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask, - bool inner, bool rx); +void mlx5dr_ste_build_eth_ipv6_l3_l4(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); void mlx5dr_ste_build_eth_l4_misc(struct mlx5dr_ste_build *sb, struct mlx5dr_match_param *mask, bool inner, bool rx); -void mlx5dr_ste_build_gre(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask, - bool inner, bool rx); +void mlx5dr_ste_build_tnl_gre(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); void mlx5dr_ste_build_mpls(struct mlx5dr_ste_build *sb, struct mlx5dr_match_param *mask, bool inner, bool rx); -void mlx5dr_ste_build_flex_parser_0(struct mlx5dr_ste_build *sb, +void mlx5dr_ste_build_tnl_mpls(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +int mlx5dr_ste_build_icmp(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + struct mlx5dr_cmd_caps *caps, + bool inner, bool rx); +void mlx5dr_ste_build_tnl_vxlan_gpe(struct mlx5dr_ste_build *sb, struct mlx5dr_match_param *mask, bool inner, bool rx); -int mlx5dr_ste_build_flex_parser_1(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask, - struct mlx5dr_cmd_caps *caps, - bool inner, bool rx); -void mlx5dr_ste_build_flex_parser_tnl_vxlan_gpe(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask, - bool inner, bool rx); -void mlx5dr_ste_build_flex_parser_tnl_geneve(struct mlx5dr_ste_build *sb, - struct mlx5dr_match_param *mask, - bool inner, bool rx); +void mlx5dr_ste_build_tnl_geneve(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); void mlx5dr_ste_build_general_purpose(struct mlx5dr_ste_build *sb, struct mlx5dr_match_param *mask, bool inner, bool rx); @@ -588,9 +588,9 @@ struct mlx5dr_match_param { struct mlx5dr_match_misc3 misc3; }; -#define DR_MASK_IS_FLEX_PARSER_ICMPV4_SET(_misc3) ((_misc3)->icmpv4_type || \ - (_misc3)->icmpv4_code || \ - (_misc3)->icmpv4_header_data) +#define DR_MASK_IS_ICMPV4_SET(_misc3) ((_misc3)->icmpv4_type || \ + (_misc3)->icmpv4_code || \ + (_misc3)->icmpv4_header_data) struct mlx5dr_esw_caps { u64 drop_icm_address_rx; @@ -731,7 +731,6 @@ struct mlx5dr_action { struct mlx5dr_domain *dmn; struct mlx5dr_icm_chunk *chunk; u8 *data; - u32 data_size; u16 num_of_actions; u32 index; u8 allow_rx:1; @@ -804,7 +803,7 @@ void mlx5dr_rule_update_rule_member(struct mlx5dr_ste *new_ste, struct mlx5dr_ste *ste); struct mlx5dr_icm_chunk { - struct mlx5dr_icm_bucket *bucket; + struct mlx5dr_icm_buddy_mem *buddy_mem; struct list_head chunk_list; u32 rkey; u32 num_of_entries; @@ -812,6 +811,11 @@ struct mlx5dr_icm_chunk { u64 icm_addr; u64 mr_addr; + /* indicates the index of this chunk in the whole memory, + * used for deleting the chunk from the buddy + */ + unsigned int seg; + /* Memory optimisation */ struct mlx5dr_ste *ste_arr; u8 *hw_ste_arr; @@ -840,23 +844,20 @@ static inline void mlx5dr_domain_unlock(struct mlx5dr_domain *dmn) mlx5dr_domain_nic_unlock(&dmn->info.rx); } -static inline int -mlx5dr_matcher_supp_flex_parser_icmp_v4(struct mlx5dr_cmd_caps *caps) -{ - return caps->flex_protocols & MLX5_FLEX_PARSER_ICMP_V4_ENABLED; -} - -static inline int -mlx5dr_matcher_supp_flex_parser_icmp_v6(struct mlx5dr_cmd_caps *caps) -{ - return caps->flex_protocols & MLX5_FLEX_PARSER_ICMP_V6_ENABLED; -} - int mlx5dr_matcher_select_builders(struct mlx5dr_matcher *matcher, struct mlx5dr_matcher_rx_tx *nic_matcher, enum mlx5dr_ipv outer_ipv, enum mlx5dr_ipv inner_ipv); +static inline int +mlx5dr_icm_pool_dm_type_to_entry_size(enum mlx5dr_icm_type icm_type) +{ + if (icm_type == DR_ICM_TYPE_STE) + return DR_STE_SIZE; + + return DR_MODIFY_ACTION_SIZE; +} + static inline u32 mlx5dr_icm_pool_chunk_size_to_entries(enum mlx5dr_icm_chunk_size chunk_size) { @@ -870,11 +871,7 @@ mlx5dr_icm_pool_chunk_size_to_byte(enum mlx5dr_icm_chunk_size chunk_size, int num_of_entries; int entry_size; - if (icm_type == DR_ICM_TYPE_STE) - entry_size = DR_STE_SIZE; - else - entry_size = DR_MODIFY_ACTION_SIZE; - + entry_size = mlx5dr_icm_pool_dm_type_to_entry_size(icm_type); num_of_entries = mlx5dr_icm_pool_chunk_size_to_entries(chunk_size); return entry_size * num_of_entries; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h index 7914fe3fc68d..4177786b8eaf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h @@ -127,4 +127,36 @@ mlx5dr_is_supported(struct mlx5_core_dev *dev) return MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner); } +/* buddy functions & structure */ + +struct mlx5dr_icm_mr; + +struct mlx5dr_icm_buddy_mem { + unsigned long **bitmap; + unsigned int *num_free; + u32 max_order; + struct list_head list_node; + struct mlx5dr_icm_mr *icm_mr; + struct mlx5dr_icm_pool *pool; + + /* This is the list of used chunks. HW may be accessing this memory */ + struct list_head used_list; + u64 used_memory; + + /* Hardware may be accessing this memory but at some future, + * undetermined time, it might cease to do so. + * sync_ste command sets them free. + */ + struct list_head hot_list; +}; + +int mlx5dr_buddy_init(struct mlx5dr_icm_buddy_mem *buddy, + unsigned int max_order); +void mlx5dr_buddy_cleanup(struct mlx5dr_icm_buddy_mem *buddy); +int mlx5dr_buddy_alloc_mem(struct mlx5dr_icm_buddy_mem *buddy, + unsigned int order, + unsigned int *segment); +void mlx5dr_buddy_free_mem(struct mlx5dr_icm_buddy_mem *buddy, + unsigned int seg, unsigned int order); + #endif /* _MLX5DR_H_ */ diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 39eff6a57ba2..73aab72877fd 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -8245,6 +8245,86 @@ mlxsw_reg_rmft2_ipv6_pack(char *payload, bool v, u16 offset, u16 virtual_router, mlxsw_reg_rmft2_sip6_mask_memcpy_to(payload, (void *)&sip6_mask); } +/* Note that XRALXX register position violates the rule of ordering register + * definition by the ID. However, XRALXX pack helpers are using RALXX pack + * helpers, RALXX registers have higher IDs. + */ + +/* XRALTA - XM Router Algorithmic LPM Tree Allocation Register + * ----------------------------------------------------------- + * The XRALTA is used to allocate the XLT LPM trees. + * + * This register embeds original RALTA register. + */ +#define MLXSW_REG_XRALTA_ID 0x7811 +#define MLXSW_REG_XRALTA_LEN 0x08 +#define MLXSW_REG_XRALTA_RALTA_OFFSET 0x04 + +MLXSW_REG_DEFINE(xralta, MLXSW_REG_XRALTA_ID, MLXSW_REG_XRALTA_LEN); + +static inline void mlxsw_reg_xralta_pack(char *payload, bool alloc, + enum mlxsw_reg_ralxx_protocol protocol, + u8 tree_id) +{ + char *ralta_payload = payload + MLXSW_REG_XRALTA_RALTA_OFFSET; + + MLXSW_REG_ZERO(xralta, payload); + mlxsw_reg_ralta_pack(ralta_payload, alloc, protocol, tree_id); +} + +/* XRALST - XM Router Algorithmic LPM Structure Tree Register + * ---------------------------------------------------------- + * The XRALST is used to set and query the structure of an XLT LPM tree. + * + * This register embeds original RALST register. + */ +#define MLXSW_REG_XRALST_ID 0x7812 +#define MLXSW_REG_XRALST_LEN 0x108 +#define MLXSW_REG_XRALST_RALST_OFFSET 0x04 + +MLXSW_REG_DEFINE(xralst, MLXSW_REG_XRALST_ID, MLXSW_REG_XRALST_LEN); + +static inline void mlxsw_reg_xralst_pack(char *payload, u8 root_bin, u8 tree_id) +{ + char *ralst_payload = payload + MLXSW_REG_XRALST_RALST_OFFSET; + + MLXSW_REG_ZERO(xralst, payload); + mlxsw_reg_ralst_pack(ralst_payload, root_bin, tree_id); +} + +static inline void mlxsw_reg_xralst_bin_pack(char *payload, u8 bin_number, + u8 left_child_bin, + u8 right_child_bin) +{ + char *ralst_payload = payload + MLXSW_REG_XRALST_RALST_OFFSET; + + mlxsw_reg_ralst_bin_pack(ralst_payload, bin_number, left_child_bin, + right_child_bin); +} + +/* XRALTB - XM Router Algorithmic LPM Tree Binding Register + * -------------------------------------------------------- + * The XRALTB register is used to bind virtual router and protocol + * to an allocated LPM tree. + * + * This register embeds original RALTB register. + */ +#define MLXSW_REG_XRALTB_ID 0x7813 +#define MLXSW_REG_XRALTB_LEN 0x08 +#define MLXSW_REG_XRALTB_RALTB_OFFSET 0x04 + +MLXSW_REG_DEFINE(xraltb, MLXSW_REG_XRALTB_ID, MLXSW_REG_XRALTB_LEN); + +static inline void mlxsw_reg_xraltb_pack(char *payload, u16 virtual_router, + enum mlxsw_reg_ralxx_protocol protocol, + u8 tree_id) +{ + char *raltb_payload = payload + MLXSW_REG_XRALTB_RALTB_OFFSET; + + MLXSW_REG_ZERO(xraltb, payload); + mlxsw_reg_raltb_pack(raltb_payload, virtual_router, protocol, tree_id); +} + /* MFCR - Management Fan Control Register * -------------------------------------- * This register controls the settings of the Fan Speed PWM mechanism. @@ -11195,6 +11275,9 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = { MLXSW_REG(rigr2), MLXSW_REG(recr2), MLXSW_REG(rmft2), + MLXSW_REG(xralta), + MLXSW_REG(xralst), + MLXSW_REG(xraltb), MLXSW_REG(mfcr), MLXSW_REG(mfsc), MLXSW_REG(mfsm), diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 4381f8c6c3fb..29fc47821ad7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -409,6 +409,7 @@ struct mlxsw_sp_fib { struct mlxsw_sp_vr *vr; struct mlxsw_sp_lpm_tree *lpm_tree; enum mlxsw_sp_l3proto proto; + const struct mlxsw_sp_router_ll_ops *ll_ops; }; struct mlxsw_sp_vr { @@ -422,12 +423,31 @@ struct mlxsw_sp_vr { refcount_t ul_rif_refcnt; }; +static int mlxsw_sp_router_ll_basic_ralta_write(struct mlxsw_sp *mlxsw_sp, char *xralta_pl) +{ + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralta), + xralta_pl + MLXSW_REG_XRALTA_RALTA_OFFSET); +} + +static int mlxsw_sp_router_ll_basic_ralst_write(struct mlxsw_sp *mlxsw_sp, char *xralst_pl) +{ + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralst), + xralst_pl + MLXSW_REG_XRALST_RALST_OFFSET); +} + +static int mlxsw_sp_router_ll_basic_raltb_write(struct mlxsw_sp *mlxsw_sp, char *xraltb_pl) +{ + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), + xraltb_pl + MLXSW_REG_XRALTB_RALTB_OFFSET); +} + static const struct rhashtable_params mlxsw_sp_fib_ht_params; static struct mlxsw_sp_fib *mlxsw_sp_fib_create(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_vr *vr, enum mlxsw_sp_l3proto proto) { + const struct mlxsw_sp_router_ll_ops *ll_ops = mlxsw_sp->router->proto_ll_ops[proto]; struct mlxsw_sp_lpm_tree *lpm_tree; struct mlxsw_sp_fib *fib; int err; @@ -443,6 +463,7 @@ static struct mlxsw_sp_fib *mlxsw_sp_fib_create(struct mlxsw_sp *mlxsw_sp, fib->proto = proto; fib->vr = vr; fib->lpm_tree = lpm_tree; + fib->ll_ops = ll_ops; mlxsw_sp_lpm_tree_hold(lpm_tree); err = mlxsw_sp_vr_lpm_tree_bind(mlxsw_sp, fib, lpm_tree->id); if (err) @@ -481,33 +502,36 @@ mlxsw_sp_lpm_tree_find_unused(struct mlxsw_sp *mlxsw_sp) } static int mlxsw_sp_lpm_tree_alloc(struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_router_ll_ops *ll_ops, struct mlxsw_sp_lpm_tree *lpm_tree) { - char ralta_pl[MLXSW_REG_RALTA_LEN]; + char xralta_pl[MLXSW_REG_XRALTA_LEN]; - mlxsw_reg_ralta_pack(ralta_pl, true, - (enum mlxsw_reg_ralxx_protocol) lpm_tree->proto, - lpm_tree->id); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralta), ralta_pl); + mlxsw_reg_xralta_pack(xralta_pl, true, + (enum mlxsw_reg_ralxx_protocol) lpm_tree->proto, + lpm_tree->id); + return ll_ops->ralta_write(mlxsw_sp, xralta_pl); } static void mlxsw_sp_lpm_tree_free(struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_router_ll_ops *ll_ops, struct mlxsw_sp_lpm_tree *lpm_tree) { - char ralta_pl[MLXSW_REG_RALTA_LEN]; + char xralta_pl[MLXSW_REG_XRALTA_LEN]; - mlxsw_reg_ralta_pack(ralta_pl, false, - (enum mlxsw_reg_ralxx_protocol) lpm_tree->proto, - lpm_tree->id); - mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralta), ralta_pl); + mlxsw_reg_xralta_pack(xralta_pl, false, + (enum mlxsw_reg_ralxx_protocol) lpm_tree->proto, + lpm_tree->id); + ll_ops->ralta_write(mlxsw_sp, xralta_pl); } static int mlxsw_sp_lpm_tree_left_struct_set(struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_router_ll_ops *ll_ops, struct mlxsw_sp_prefix_usage *prefix_usage, struct mlxsw_sp_lpm_tree *lpm_tree) { - char ralst_pl[MLXSW_REG_RALST_LEN]; + char xralst_pl[MLXSW_REG_XRALST_LEN]; u8 root_bin = 0; u8 prefix; u8 last_prefix = MLXSW_REG_RALST_BIN_NO_CHILD; @@ -515,19 +539,20 @@ mlxsw_sp_lpm_tree_left_struct_set(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_prefix_usage_for_each(prefix, prefix_usage) root_bin = prefix; - mlxsw_reg_ralst_pack(ralst_pl, root_bin, lpm_tree->id); + mlxsw_reg_xralst_pack(xralst_pl, root_bin, lpm_tree->id); mlxsw_sp_prefix_usage_for_each(prefix, prefix_usage) { if (prefix == 0) continue; - mlxsw_reg_ralst_bin_pack(ralst_pl, prefix, last_prefix, - MLXSW_REG_RALST_BIN_NO_CHILD); + mlxsw_reg_xralst_bin_pack(xralst_pl, prefix, last_prefix, + MLXSW_REG_RALST_BIN_NO_CHILD); last_prefix = prefix; } - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralst), ralst_pl); + return ll_ops->ralst_write(mlxsw_sp, xralst_pl); } static struct mlxsw_sp_lpm_tree * mlxsw_sp_lpm_tree_create(struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_router_ll_ops *ll_ops, struct mlxsw_sp_prefix_usage *prefix_usage, enum mlxsw_sp_l3proto proto) { @@ -538,12 +563,11 @@ mlxsw_sp_lpm_tree_create(struct mlxsw_sp *mlxsw_sp, if (!lpm_tree) return ERR_PTR(-EBUSY); lpm_tree->proto = proto; - err = mlxsw_sp_lpm_tree_alloc(mlxsw_sp, lpm_tree); + err = mlxsw_sp_lpm_tree_alloc(mlxsw_sp, ll_ops, lpm_tree); if (err) return ERR_PTR(err); - err = mlxsw_sp_lpm_tree_left_struct_set(mlxsw_sp, prefix_usage, - lpm_tree); + err = mlxsw_sp_lpm_tree_left_struct_set(mlxsw_sp, ll_ops, prefix_usage, lpm_tree); if (err) goto err_left_struct_set; memcpy(&lpm_tree->prefix_usage, prefix_usage, @@ -554,14 +578,15 @@ mlxsw_sp_lpm_tree_create(struct mlxsw_sp *mlxsw_sp, return lpm_tree; err_left_struct_set: - mlxsw_sp_lpm_tree_free(mlxsw_sp, lpm_tree); + mlxsw_sp_lpm_tree_free(mlxsw_sp, ll_ops, lpm_tree); return ERR_PTR(err); } static void mlxsw_sp_lpm_tree_destroy(struct mlxsw_sp *mlxsw_sp, + const struct mlxsw_sp_router_ll_ops *ll_ops, struct mlxsw_sp_lpm_tree *lpm_tree) { - mlxsw_sp_lpm_tree_free(mlxsw_sp, lpm_tree); + mlxsw_sp_lpm_tree_free(mlxsw_sp, ll_ops, lpm_tree); } static struct mlxsw_sp_lpm_tree * @@ -569,6 +594,7 @@ mlxsw_sp_lpm_tree_get(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_prefix_usage *prefix_usage, enum mlxsw_sp_l3proto proto) { + const struct mlxsw_sp_router_ll_ops *ll_ops = mlxsw_sp->router->proto_ll_ops[proto]; struct mlxsw_sp_lpm_tree *lpm_tree; int i; @@ -582,7 +608,7 @@ mlxsw_sp_lpm_tree_get(struct mlxsw_sp *mlxsw_sp, return lpm_tree; } } - return mlxsw_sp_lpm_tree_create(mlxsw_sp, prefix_usage, proto); + return mlxsw_sp_lpm_tree_create(mlxsw_sp, ll_ops, prefix_usage, proto); } static void mlxsw_sp_lpm_tree_hold(struct mlxsw_sp_lpm_tree *lpm_tree) @@ -593,8 +619,11 @@ static void mlxsw_sp_lpm_tree_hold(struct mlxsw_sp_lpm_tree *lpm_tree) static void mlxsw_sp_lpm_tree_put(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_lpm_tree *lpm_tree) { + const struct mlxsw_sp_router_ll_ops *ll_ops = + mlxsw_sp->router->proto_ll_ops[lpm_tree->proto]; + if (--lpm_tree->ref_count == 0) - mlxsw_sp_lpm_tree_destroy(mlxsw_sp, lpm_tree); + mlxsw_sp_lpm_tree_destroy(mlxsw_sp, ll_ops, lpm_tree); } #define MLXSW_SP_LPM_TREE_MIN 1 /* tree 0 is reserved */ @@ -684,23 +713,23 @@ static struct mlxsw_sp_vr *mlxsw_sp_vr_find_unused(struct mlxsw_sp *mlxsw_sp) static int mlxsw_sp_vr_lpm_tree_bind(struct mlxsw_sp *mlxsw_sp, const struct mlxsw_sp_fib *fib, u8 tree_id) { - char raltb_pl[MLXSW_REG_RALTB_LEN]; + char xraltb_pl[MLXSW_REG_XRALTB_LEN]; - mlxsw_reg_raltb_pack(raltb_pl, fib->vr->id, - (enum mlxsw_reg_ralxx_protocol) fib->proto, - tree_id); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl); + mlxsw_reg_xraltb_pack(xraltb_pl, fib->vr->id, + (enum mlxsw_reg_ralxx_protocol) fib->proto, + tree_id); + return fib->ll_ops->raltb_write(mlxsw_sp, xraltb_pl); } static int mlxsw_sp_vr_lpm_tree_unbind(struct mlxsw_sp *mlxsw_sp, const struct mlxsw_sp_fib *fib) { - char raltb_pl[MLXSW_REG_RALTB_LEN]; + char xraltb_pl[MLXSW_REG_XRALTB_LEN]; /* Bind to tree 0 which is default */ - mlxsw_reg_raltb_pack(raltb_pl, fib->vr->id, - (enum mlxsw_reg_ralxx_protocol) fib->proto, 0); - return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), raltb_pl); + mlxsw_reg_xraltb_pack(xraltb_pl, fib->vr->id, + (enum mlxsw_reg_ralxx_protocol) fib->proto, 0); + return fib->ll_ops->raltb_write(mlxsw_sp, xraltb_pl); } static u32 mlxsw_sp_fix_tb_id(u32 tb_id) @@ -5659,28 +5688,28 @@ static int __mlxsw_sp_router_set_abort_trap(struct mlxsw_sp *mlxsw_sp, enum mlxsw_reg_ralxx_protocol proto, u8 tree_id) { - char ralta_pl[MLXSW_REG_RALTA_LEN]; - char ralst_pl[MLXSW_REG_RALST_LEN]; + const struct mlxsw_sp_router_ll_ops *ll_ops = mlxsw_sp->router->proto_ll_ops[proto]; + char xralta_pl[MLXSW_REG_XRALTA_LEN]; + char xralst_pl[MLXSW_REG_XRALST_LEN]; int i, err; - mlxsw_reg_ralta_pack(ralta_pl, true, proto, tree_id); - err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralta), ralta_pl); + mlxsw_reg_xralta_pack(xralta_pl, true, proto, tree_id); + err = ll_ops->ralta_write(mlxsw_sp, xralta_pl); if (err) return err; - mlxsw_reg_ralst_pack(ralst_pl, 0xff, tree_id); - err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ralst), ralst_pl); + mlxsw_reg_xralst_pack(xralst_pl, 0xff, tree_id); + err = ll_ops->ralst_write(mlxsw_sp, xralst_pl); if (err) return err; for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_VRS); i++) { struct mlxsw_sp_vr *vr = &mlxsw_sp->router->vrs[i]; - char raltb_pl[MLXSW_REG_RALTB_LEN]; + char xraltb_pl[MLXSW_REG_XRALTB_LEN]; char ralue_pl[MLXSW_REG_RALUE_LEN]; - mlxsw_reg_raltb_pack(raltb_pl, vr->id, proto, tree_id); - err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(raltb), - raltb_pl); + mlxsw_reg_xraltb_pack(xraltb_pl, vr->id, proto, tree_id); + err = ll_ops->raltb_write(mlxsw_sp, xraltb_pl); if (err) return err; @@ -8057,6 +8086,12 @@ static void __mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp) mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl); } +static const struct mlxsw_sp_router_ll_ops mlxsw_sp_router_ll_basic_ops = { + .ralta_write = mlxsw_sp_router_ll_basic_ralta_write, + .ralst_write = mlxsw_sp_router_ll_basic_ralst_write, + .raltb_write = mlxsw_sp_router_ll_basic_raltb_write, +}; + int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, struct netlink_ext_ack *extack) { @@ -8070,6 +8105,9 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp, mlxsw_sp->router = router; router->mlxsw_sp = mlxsw_sp; + router->proto_ll_ops[MLXSW_SP_L3_PROTO_IPV4] = &mlxsw_sp_router_ll_basic_ops; + router->proto_ll_ops[MLXSW_SP_L3_PROTO_IPV6] = &mlxsw_sp_router_ll_basic_ops; + INIT_LIST_HEAD(&mlxsw_sp->router->nexthop_neighs_list); err = __mlxsw_sp_router_init(mlxsw_sp); if (err) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h index 8418dc3ae967..c5c7346eb815 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h @@ -48,6 +48,17 @@ struct mlxsw_sp_router { bool adj_discard_index_valid; struct mlxsw_sp_router_nve_decap nve_decap_config; struct mutex lock; /* Protects shared router resources */ + /* One set of ops for each protocol: IPv4 and IPv6 */ + const struct mlxsw_sp_router_ll_ops *proto_ll_ops[MLXSW_SP_L3_PROTO_MAX]; +}; + +/* Low-level router ops. Basically this is to handle the different + * register sets to work with ordinary and XM trees and FIB entries. + */ +struct mlxsw_sp_router_ll_ops { + int (*ralta_write)(struct mlxsw_sp *mlxsw_sp, char *xralta_pl); + int (*ralst_write)(struct mlxsw_sp *mlxsw_sp, char *xralst_pl); + int (*raltb_write)(struct mlxsw_sp *mlxsw_sp, char *xraltb_pl); }; struct mlxsw_sp_rif_ipip_lb; diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c index dcde496da7fb..c5de8f46cdd3 100644 --- a/drivers/net/ethernet/microchip/lan743x_ethtool.c +++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c @@ -780,7 +780,9 @@ static void lan743x_ethtool_get_wol(struct net_device *netdev, wol->supported = 0; wol->wolopts = 0; - phy_ethtool_get_wol(netdev->phydev, wol); + + if (netdev->phydev) + phy_ethtool_get_wol(netdev->phydev, wol); wol->supported |= WAKE_BCAST | WAKE_UCAST | WAKE_MCAST | WAKE_MAGIC | WAKE_PHY | WAKE_ARP; @@ -809,9 +811,8 @@ static int lan743x_ethtool_set_wol(struct net_device *netdev, device_set_wakeup_enable(&adapter->pdev->dev, (bool)wol->wolopts); - phy_ethtool_set_wol(netdev->phydev, wol); - - return 0; + return netdev->phydev ? phy_ethtool_set_wol(netdev->phydev, wol) + : -ENETDOWN; } #endif /* CONFIG_PM */ diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index a1938842f828..8ea0b4eec19c 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -834,14 +834,13 @@ static int lan743x_mac_init(struct lan743x_adapter *adapter) static int lan743x_mac_open(struct lan743x_adapter *adapter) { - int ret = 0; u32 temp; temp = lan743x_csr_read(adapter, MAC_RX); lan743x_csr_write(adapter, MAC_RX, temp | MAC_RX_RXEN_); temp = lan743x_csr_read(adapter, MAC_TX); lan743x_csr_write(adapter, MAC_TX, temp | MAC_TX_TXEN_); - return ret; + return 0; } static void lan743x_mac_close(struct lan743x_adapter *adapter) diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 70bf8c67d7ef..2632fe2d2448 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -147,42 +147,20 @@ static int ocelot_vlant_set_mask(struct ocelot *ocelot, u16 vid, u32 mask) return ocelot_vlant_wait_for_completion(ocelot); } -static int ocelot_port_set_native_vlan(struct ocelot *ocelot, int port, - u16 vid) +static void ocelot_port_set_native_vlan(struct ocelot *ocelot, int port, + struct ocelot_vlan native_vlan) { struct ocelot_port *ocelot_port = ocelot->ports[port]; u32 val = 0; - if (ocelot_port->vid != vid) { - /* Always permit deleting the native VLAN (vid = 0) */ - if (ocelot_port->vid && vid) { - dev_err(ocelot->dev, - "Port already has a native VLAN: %d\n", - ocelot_port->vid); - return -EBUSY; - } - ocelot_port->vid = vid; - } + ocelot_port->native_vlan = native_vlan; - ocelot_rmw_gix(ocelot, REW_PORT_VLAN_CFG_PORT_VID(vid), + ocelot_rmw_gix(ocelot, REW_PORT_VLAN_CFG_PORT_VID(native_vlan.vid), REW_PORT_VLAN_CFG_PORT_VID_M, REW_PORT_VLAN_CFG, port); - if (ocelot_port->vlan_aware && !ocelot_port->vid) - /* If port is vlan-aware and tagged, drop untagged and priority - * tagged frames. - */ - val = ANA_PORT_DROP_CFG_DROP_UNTAGGED_ENA | - ANA_PORT_DROP_CFG_DROP_PRIO_S_TAGGED_ENA | - ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA; - ocelot_rmw_gix(ocelot, val, - ANA_PORT_DROP_CFG_DROP_UNTAGGED_ENA | - ANA_PORT_DROP_CFG_DROP_PRIO_S_TAGGED_ENA | - ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA, - ANA_PORT_DROP_CFG, port); - if (ocelot_port->vlan_aware) { - if (ocelot_port->vid) + if (native_vlan.valid) /* Tag all frames except when VID == DEFAULT_VLAN */ val = REW_TAG_CFG_TAG_CFG(1); else @@ -195,8 +173,38 @@ static int ocelot_port_set_native_vlan(struct ocelot *ocelot, int port, ocelot_rmw_gix(ocelot, val, REW_TAG_CFG_TAG_CFG_M, REW_TAG_CFG, port); +} - return 0; +/* Default vlan to clasify for untagged frames (may be zero) */ +static void ocelot_port_set_pvid(struct ocelot *ocelot, int port, + struct ocelot_vlan pvid_vlan) +{ + struct ocelot_port *ocelot_port = ocelot->ports[port]; + u32 val = 0; + + ocelot_port->pvid_vlan = pvid_vlan; + + if (!ocelot_port->vlan_aware) + pvid_vlan.vid = 0; + + ocelot_rmw_gix(ocelot, + ANA_PORT_VLAN_CFG_VLAN_VID(pvid_vlan.vid), + ANA_PORT_VLAN_CFG_VLAN_VID_M, + ANA_PORT_VLAN_CFG, port); + + /* If there's no pvid, we should drop not only untagged traffic (which + * happens automatically), but also 802.1p traffic which gets + * classified to VLAN 0, but that is always in our RX filter, so it + * would get accepted were it not for this setting. + */ + if (!pvid_vlan.valid && ocelot_port->vlan_aware) + val = ANA_PORT_DROP_CFG_DROP_PRIO_S_TAGGED_ENA | + ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA; + + ocelot_rmw_gix(ocelot, val, + ANA_PORT_DROP_CFG_DROP_PRIO_S_TAGGED_ENA | + ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA, + ANA_PORT_DROP_CFG, port); } int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port, @@ -233,24 +241,30 @@ int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port, ANA_PORT_VLAN_CFG_VLAN_POP_CNT_M, ANA_PORT_VLAN_CFG, port); - ocelot_port_set_native_vlan(ocelot, port, ocelot_port->vid); + ocelot_port_set_pvid(ocelot, port, ocelot_port->pvid_vlan); + ocelot_port_set_native_vlan(ocelot, port, ocelot_port->native_vlan); return 0; } EXPORT_SYMBOL(ocelot_port_vlan_filtering); -/* Default vlan to clasify for untagged frames (may be zero) */ -static void ocelot_port_set_pvid(struct ocelot *ocelot, int port, u16 pvid) +int ocelot_vlan_prepare(struct ocelot *ocelot, int port, u16 vid, bool pvid, + bool untagged) { struct ocelot_port *ocelot_port = ocelot->ports[port]; - ocelot_rmw_gix(ocelot, - ANA_PORT_VLAN_CFG_VLAN_VID(pvid), - ANA_PORT_VLAN_CFG_VLAN_VID_M, - ANA_PORT_VLAN_CFG, port); + /* Deny changing the native VLAN, but always permit deleting it */ + if (untagged && ocelot_port->native_vlan.vid != vid && + ocelot_port->native_vlan.valid) { + dev_err(ocelot->dev, + "Port already has a native VLAN: %d\n", + ocelot_port->native_vlan.vid); + return -EBUSY; + } - ocelot_port->pvid = pvid; + return 0; } +EXPORT_SYMBOL(ocelot_vlan_prepare); int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid, bool untagged) @@ -264,14 +278,21 @@ int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid, return ret; /* Default ingress vlan classification */ - if (pvid) - ocelot_port_set_pvid(ocelot, port, vid); + if (pvid) { + struct ocelot_vlan pvid_vlan; + + pvid_vlan.vid = vid; + pvid_vlan.valid = true; + ocelot_port_set_pvid(ocelot, port, pvid_vlan); + } /* Untagged egress vlan clasification */ if (untagged) { - ret = ocelot_port_set_native_vlan(ocelot, port, vid); - if (ret) - return ret; + struct ocelot_vlan native_vlan; + + native_vlan.vid = vid; + native_vlan.valid = true; + ocelot_port_set_native_vlan(ocelot, port, native_vlan); } return 0; @@ -290,12 +311,18 @@ int ocelot_vlan_del(struct ocelot *ocelot, int port, u16 vid) return ret; /* Ingress */ - if (ocelot_port->pvid == vid) - ocelot_port_set_pvid(ocelot, port, 0); + if (ocelot_port->pvid_vlan.vid == vid) { + struct ocelot_vlan pvid_vlan = {0}; + + ocelot_port_set_pvid(ocelot, port, pvid_vlan); + } /* Egress */ - if (ocelot_port->vid == vid) - ocelot_port_set_native_vlan(ocelot, port, 0); + if (ocelot_port->native_vlan.vid == vid) { + struct ocelot_vlan native_vlan = {0}; + + ocelot_port_set_native_vlan(ocelot, port, native_vlan); + } return 0; } @@ -542,26 +569,11 @@ EXPORT_SYMBOL(ocelot_get_txtstamp); int ocelot_fdb_add(struct ocelot *ocelot, int port, const unsigned char *addr, u16 vid) { - struct ocelot_port *ocelot_port = ocelot->ports[port]; int pgid = port; if (port == ocelot->npi) pgid = PGID_CPU; - if (!vid) { - if (!ocelot_port->vlan_aware) - /* If the bridge is not VLAN aware and no VID was - * provided, set it to pvid to ensure the MAC entry - * matches incoming untagged packets - */ - vid = ocelot_port->pvid; - else - /* If the bridge is VLAN aware a VID must be provided as - * otherwise the learnt entry wouldn't match any frame. - */ - return -EINVAL; - } - return ocelot_mact_learn(ocelot, pgid, addr, vid, ENTRYTYPE_LOCKED); } EXPORT_SYMBOL(ocelot_fdb_add); @@ -958,52 +970,88 @@ static enum macaccess_entry_type ocelot_classify_mdb(const unsigned char *addr) return ENTRYTYPE_MACv4; if (addr[0] == 0x33 && addr[1] == 0x33) return ENTRYTYPE_MACv6; - return ENTRYTYPE_NORMAL; + return ENTRYTYPE_LOCKED; +} + +static struct ocelot_pgid *ocelot_pgid_alloc(struct ocelot *ocelot, int index, + unsigned long ports) +{ + struct ocelot_pgid *pgid; + + pgid = kzalloc(sizeof(*pgid), GFP_KERNEL); + if (!pgid) + return ERR_PTR(-ENOMEM); + + pgid->ports = ports; + pgid->index = index; + refcount_set(&pgid->refcount, 1); + list_add_tail(&pgid->list, &ocelot->pgids); + + return pgid; +} + +static void ocelot_pgid_free(struct ocelot *ocelot, struct ocelot_pgid *pgid) +{ + if (!refcount_dec_and_test(&pgid->refcount)) + return; + + list_del(&pgid->list); + kfree(pgid); } -static int ocelot_mdb_get_pgid(struct ocelot *ocelot, - enum macaccess_entry_type entry_type) +static struct ocelot_pgid *ocelot_mdb_get_pgid(struct ocelot *ocelot, + const struct ocelot_multicast *mc) { - int pgid; + struct ocelot_pgid *pgid; + int index; /* According to VSC7514 datasheet 3.9.1.5 IPv4 Multicast Entries and * 3.9.1.6 IPv6 Multicast Entries, "Instead of a lookup in the * destination mask table (PGID), the destination set is programmed as * part of the entry MAC address.", and the DEST_IDX is set to 0. */ - if (entry_type == ENTRYTYPE_MACv4 || - entry_type == ENTRYTYPE_MACv6) - return 0; + if (mc->entry_type == ENTRYTYPE_MACv4 || + mc->entry_type == ENTRYTYPE_MACv6) + return ocelot_pgid_alloc(ocelot, 0, mc->ports); - for_each_nonreserved_multicast_dest_pgid(ocelot, pgid) { - struct ocelot_multicast *mc; + list_for_each_entry(pgid, &ocelot->pgids, list) { + /* When searching for a nonreserved multicast PGID, ignore the + * dummy PGID of zero that we have for MACv4/MACv6 entries + */ + if (pgid->index && pgid->ports == mc->ports) { + refcount_inc(&pgid->refcount); + return pgid; + } + } + + /* Search for a free index in the nonreserved multicast PGID area */ + for_each_nonreserved_multicast_dest_pgid(ocelot, index) { bool used = false; - list_for_each_entry(mc, &ocelot->multicast, list) { - if (mc->pgid == pgid) { + list_for_each_entry(pgid, &ocelot->pgids, list) { + if (pgid->index == index) { used = true; break; } } if (!used) - return pgid; + return ocelot_pgid_alloc(ocelot, index, mc->ports); } - return -1; + return ERR_PTR(-ENOSPC); } static void ocelot_encode_ports_to_mdb(unsigned char *addr, - struct ocelot_multicast *mc, - enum macaccess_entry_type entry_type) + struct ocelot_multicast *mc) { - memcpy(addr, mc->addr, ETH_ALEN); + ether_addr_copy(addr, mc->addr); - if (entry_type == ENTRYTYPE_MACv4) { + if (mc->entry_type == ENTRYTYPE_MACv4) { addr[0] = 0; addr[1] = mc->ports >> 8; addr[2] = mc->ports & 0xff; - } else if (entry_type == ENTRYTYPE_MACv6) { + } else if (mc->entry_type == ENTRYTYPE_MACv6) { addr[0] = mc->ports >> 8; addr[1] = mc->ports & 0xff; } @@ -1012,80 +1060,78 @@ static void ocelot_encode_ports_to_mdb(unsigned char *addr, int ocelot_port_mdb_add(struct ocelot *ocelot, int port, const struct switchdev_obj_port_mdb *mdb) { - struct ocelot_port *ocelot_port = ocelot->ports[port]; - enum macaccess_entry_type entry_type; unsigned char addr[ETH_ALEN]; struct ocelot_multicast *mc; + struct ocelot_pgid *pgid; u16 vid = mdb->vid; - bool new = false; if (port == ocelot->npi) port = ocelot->num_phys_ports; - if (!vid) - vid = ocelot_port->pvid; - - entry_type = ocelot_classify_mdb(mdb->addr); - mc = ocelot_multicast_get(ocelot, mdb->addr, vid); if (!mc) { - int pgid = ocelot_mdb_get_pgid(ocelot, entry_type); - - if (pgid < 0) { - dev_err(ocelot->dev, - "No more PGIDs available for mdb %pM vid %d\n", - mdb->addr, vid); - return -ENOSPC; - } - + /* New entry */ mc = devm_kzalloc(ocelot->dev, sizeof(*mc), GFP_KERNEL); if (!mc) return -ENOMEM; - memcpy(mc->addr, mdb->addr, ETH_ALEN); + mc->entry_type = ocelot_classify_mdb(mdb->addr); + ether_addr_copy(mc->addr, mdb->addr); mc->vid = vid; - mc->pgid = pgid; list_add_tail(&mc->list, &ocelot->multicast); - new = true; - } - - if (!new) { - ocelot_encode_ports_to_mdb(addr, mc, entry_type); + } else { + /* Existing entry. Clean up the current port mask from + * hardware now, because we'll be modifying it. + */ + ocelot_pgid_free(ocelot, mc->pgid); + ocelot_encode_ports_to_mdb(addr, mc); ocelot_mact_forget(ocelot, addr, vid); } mc->ports |= BIT(port); - ocelot_encode_ports_to_mdb(addr, mc, entry_type); - return ocelot_mact_learn(ocelot, mc->pgid, addr, vid, entry_type); + pgid = ocelot_mdb_get_pgid(ocelot, mc); + if (IS_ERR(pgid)) { + dev_err(ocelot->dev, + "Cannot allocate PGID for mdb %pM vid %d\n", + mc->addr, mc->vid); + devm_kfree(ocelot->dev, mc); + return PTR_ERR(pgid); + } + mc->pgid = pgid; + + ocelot_encode_ports_to_mdb(addr, mc); + + if (mc->entry_type != ENTRYTYPE_MACv4 && + mc->entry_type != ENTRYTYPE_MACv6) + ocelot_write_rix(ocelot, pgid->ports, ANA_PGID_PGID, + pgid->index); + + return ocelot_mact_learn(ocelot, pgid->index, addr, vid, + mc->entry_type); } EXPORT_SYMBOL(ocelot_port_mdb_add); int ocelot_port_mdb_del(struct ocelot *ocelot, int port, const struct switchdev_obj_port_mdb *mdb) { - struct ocelot_port *ocelot_port = ocelot->ports[port]; - enum macaccess_entry_type entry_type; unsigned char addr[ETH_ALEN]; struct ocelot_multicast *mc; + struct ocelot_pgid *pgid; u16 vid = mdb->vid; if (port == ocelot->npi) port = ocelot->num_phys_ports; - if (!vid) - vid = ocelot_port->pvid; - mc = ocelot_multicast_get(ocelot, mdb->addr, vid); if (!mc) return -ENOENT; - entry_type = ocelot_classify_mdb(mdb->addr); - - ocelot_encode_ports_to_mdb(addr, mc, entry_type); + ocelot_encode_ports_to_mdb(addr, mc); ocelot_mact_forget(ocelot, addr, vid); + ocelot_pgid_free(ocelot, mc->pgid); mc->ports &= ~BIT(port); if (!mc->ports) { list_del(&mc->list); @@ -1093,9 +1139,21 @@ int ocelot_port_mdb_del(struct ocelot *ocelot, int port, return 0; } - ocelot_encode_ports_to_mdb(addr, mc, entry_type); + /* We have a PGID with fewer ports now */ + pgid = ocelot_mdb_get_pgid(ocelot, mc); + if (IS_ERR(pgid)) + return PTR_ERR(pgid); + mc->pgid = pgid; + + ocelot_encode_ports_to_mdb(addr, mc); + + if (mc->entry_type != ENTRYTYPE_MACv4 && + mc->entry_type != ENTRYTYPE_MACv6) + ocelot_write_rix(ocelot, pgid->ports, ANA_PGID_PGID, + pgid->index); - return ocelot_mact_learn(ocelot, mc->pgid, addr, vid, entry_type); + return ocelot_mact_learn(ocelot, pgid->index, addr, vid, + mc->entry_type); } EXPORT_SYMBOL(ocelot_port_mdb_del); @@ -1120,6 +1178,7 @@ EXPORT_SYMBOL(ocelot_port_bridge_join); int ocelot_port_bridge_leave(struct ocelot *ocelot, int port, struct net_device *bridge) { + struct ocelot_vlan pvid = {0}, native_vlan = {0}; struct switchdev_trans trans; int ret; @@ -1138,8 +1197,10 @@ int ocelot_port_bridge_leave(struct ocelot *ocelot, int port, if (ret) return ret; - ocelot_port_set_pvid(ocelot, port, 0); - return ocelot_port_set_native_vlan(ocelot, port, 0); + ocelot_port_set_pvid(ocelot, port, pvid); + ocelot_port_set_native_vlan(ocelot, port, native_vlan); + + return 0; } EXPORT_SYMBOL(ocelot_port_bridge_leave); @@ -1453,6 +1514,7 @@ int ocelot_init(struct ocelot *ocelot) return -ENOMEM; INIT_LIST_HEAD(&ocelot->multicast); + INIT_LIST_HEAD(&ocelot->pgids); ocelot_mact_init(ocelot); ocelot_vlan_init(ocelot); ocelot_vcap_init(ocelot); diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h index abb407dff93c..291d39d49c4e 100644 --- a/drivers/net/ethernet/mscc/ocelot.h +++ b/drivers/net/ethernet/mscc/ocelot.h @@ -41,14 +41,6 @@ struct frame_info { u32 timestamp; /* rew_val */ }; -struct ocelot_multicast { - struct list_head list; - unsigned char addr[ETH_ALEN]; - u16 vid; - u16 ports; - int pgid; -}; - struct ocelot_port_tc { bool block_shared; unsigned long offload_cnt; @@ -87,6 +79,29 @@ enum macaccess_entry_type { ENTRYTYPE_MACv6, }; +/* A (PGID) port mask structure, encoding the 2^ocelot->num_phys_ports + * possibilities of egress port masks for L2 multicast traffic. + * For a switch with 9 user ports, there are 512 possible port masks, but the + * hardware only has 46 individual PGIDs that it can forward multicast traffic + * to. So we need a structure that maps the limited PGID indices to the port + * destinations requested by the user for L2 multicast. + */ +struct ocelot_pgid { + unsigned long ports; + int index; + refcount_t refcount; + struct list_head list; +}; + +struct ocelot_multicast { + struct list_head list; + enum macaccess_entry_type entry_type; + unsigned char addr[ETH_ALEN]; + u16 vid; + u16 ports; + struct ocelot_pgid *pgid; +}; + int ocelot_port_fdb_do_dump(const unsigned char *addr, u16 vid, bool is_static, void *data); int ocelot_mact_learn(struct ocelot *ocelot, int port, diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c index b34da11acf65..c65ae6f75a16 100644 --- a/drivers/net/ethernet/mscc/ocelot_net.c +++ b/drivers/net/ethernet/mscc/ocelot_net.c @@ -206,6 +206,17 @@ static void ocelot_port_adjust_link(struct net_device *dev) ocelot_adjust_link(ocelot, port, dev->phydev); } +static int ocelot_vlan_vid_prepare(struct net_device *dev, u16 vid, bool pvid, + bool untagged) +{ + struct ocelot_port_private *priv = netdev_priv(dev); + struct ocelot_port *ocelot_port = &priv->port; + struct ocelot *ocelot = ocelot_port->ocelot; + int port = priv->chip_port; + + return ocelot_vlan_prepare(ocelot, port, vid, pvid, untagged); +} + static int ocelot_vlan_vid_add(struct net_device *dev, u16 vid, bool pvid, bool untagged) { @@ -409,7 +420,7 @@ static int ocelot_mc_unsync(struct net_device *dev, const unsigned char *addr) struct ocelot_port *ocelot_port = &priv->port; struct ocelot *ocelot = ocelot_port->ocelot; - return ocelot_mact_forget(ocelot, addr, ocelot_port->pvid); + return ocelot_mact_forget(ocelot, addr, ocelot_port->pvid_vlan.vid); } static int ocelot_mc_sync(struct net_device *dev, const unsigned char *addr) @@ -418,8 +429,8 @@ static int ocelot_mc_sync(struct net_device *dev, const unsigned char *addr) struct ocelot_port *ocelot_port = &priv->port; struct ocelot *ocelot = ocelot_port->ocelot; - return ocelot_mact_learn(ocelot, PGID_CPU, addr, ocelot_port->pvid, - ENTRYTYPE_LOCKED); + return ocelot_mact_learn(ocelot, PGID_CPU, addr, + ocelot_port->pvid_vlan.vid, ENTRYTYPE_LOCKED); } static void ocelot_set_rx_mode(struct net_device *dev) @@ -462,10 +473,10 @@ static int ocelot_port_set_mac_address(struct net_device *dev, void *p) const struct sockaddr *addr = p; /* Learn the new net device MAC address in the mac table. */ - ocelot_mact_learn(ocelot, PGID_CPU, addr->sa_data, ocelot_port->pvid, - ENTRYTYPE_LOCKED); + ocelot_mact_learn(ocelot, PGID_CPU, addr->sa_data, + ocelot_port->pvid_vlan.vid, ENTRYTYPE_LOCKED); /* Then forget the previous one. */ - ocelot_mact_forget(ocelot, dev->dev_addr, ocelot_port->pvid); + ocelot_mact_forget(ocelot, dev->dev_addr, ocelot_port->pvid_vlan.vid); ether_addr_copy(dev->dev_addr, addr->sa_data); return 0; @@ -812,9 +823,14 @@ static int ocelot_port_obj_add_vlan(struct net_device *dev, u16 vid; for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) { - ret = ocelot_vlan_vid_add(dev, vid, - vlan->flags & BRIDGE_VLAN_INFO_PVID, - vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED); + bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID; + bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED; + + if (switchdev_trans_ph_prepare(trans)) + ret = ocelot_vlan_vid_prepare(dev, vid, pvid, + untagged); + else + ret = ocelot_vlan_vid_add(dev, vid, pvid, untagged); if (ret) return ret; } @@ -1074,8 +1090,8 @@ int ocelot_probe_port(struct ocelot *ocelot, int port, struct regmap *target, memcpy(dev->dev_addr, ocelot->base_mac, ETH_ALEN); dev->dev_addr[ETH_ALEN - 1] += port; - ocelot_mact_learn(ocelot, PGID_CPU, dev->dev_addr, ocelot_port->pvid, - ENTRYTYPE_LOCKED); + ocelot_mact_learn(ocelot, PGID_CPU, dev->dev_addr, + ocelot_port->pvid_vlan.vid, ENTRYTYPE_LOCKED); ocelot_init_port(ocelot, port); diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c index d13d92bf7447..8f2f091bce89 100644 --- a/drivers/net/ethernet/neterion/s2io.c +++ b/drivers/net/ethernet/neterion/s2io.c @@ -1106,7 +1106,7 @@ static int s2io_print_pci_mode(struct s2io_nic *nic) * '-1' on failure */ -static int init_tti(struct s2io_nic *nic, int link) +static int init_tti(struct s2io_nic *nic, int link, bool may_sleep) { struct XENA_dev_config __iomem *bar0 = nic->bar0; register u64 val64 = 0; @@ -1166,7 +1166,7 @@ static int init_tti(struct s2io_nic *nic, int link) if (wait_for_cmd_complete(&bar0->tti_command_mem, TTI_CMD_MEM_STROBE_NEW_CMD, - S2IO_BIT_RESET) != SUCCESS) + S2IO_BIT_RESET, may_sleep) != SUCCESS) return FAILURE; } @@ -1659,7 +1659,7 @@ static int init_nic(struct s2io_nic *nic) */ /* Initialize TTI */ - if (SUCCESS != init_tti(nic, nic->last_link_state)) + if (SUCCESS != init_tti(nic, nic->last_link_state, true)) return -ENODEV; /* RTI Initialization */ @@ -3331,7 +3331,7 @@ static void s2io_updt_xpak_counter(struct net_device *dev) */ static int wait_for_cmd_complete(void __iomem *addr, u64 busy_bit, - int bit_state) + int bit_state, bool may_sleep) { int ret = FAILURE, cnt = 0, delay = 1; u64 val64; @@ -3353,7 +3353,7 @@ static int wait_for_cmd_complete(void __iomem *addr, u64 busy_bit, } } - if (in_interrupt()) + if (!may_sleep) mdelay(delay); else msleep(delay); @@ -4877,8 +4877,7 @@ static struct net_device_stats *s2io_get_stats(struct net_device *dev) * Return value: * void. */ - -static void s2io_set_multicast(struct net_device *dev) +static void s2io_set_multicast(struct net_device *dev, bool may_sleep) { int i, j, prev_cnt; struct netdev_hw_addr *ha; @@ -4903,7 +4902,7 @@ static void s2io_set_multicast(struct net_device *dev) /* Wait till command completes */ wait_for_cmd_complete(&bar0->rmac_addr_cmd_mem, RMAC_ADDR_CMD_MEM_STROBE_CMD_EXECUTING, - S2IO_BIT_RESET); + S2IO_BIT_RESET, may_sleep); sp->m_cast_flg = 1; sp->all_multi_pos = config->max_mc_addr - 1; @@ -4920,7 +4919,7 @@ static void s2io_set_multicast(struct net_device *dev) /* Wait till command completes */ wait_for_cmd_complete(&bar0->rmac_addr_cmd_mem, RMAC_ADDR_CMD_MEM_STROBE_CMD_EXECUTING, - S2IO_BIT_RESET); + S2IO_BIT_RESET, may_sleep); sp->m_cast_flg = 0; sp->all_multi_pos = 0; @@ -5000,7 +4999,7 @@ static void s2io_set_multicast(struct net_device *dev) /* Wait for command completes */ if (wait_for_cmd_complete(&bar0->rmac_addr_cmd_mem, RMAC_ADDR_CMD_MEM_STROBE_CMD_EXECUTING, - S2IO_BIT_RESET)) { + S2IO_BIT_RESET, may_sleep)) { DBG_PRINT(ERR_DBG, "%s: Adding Multicasts failed\n", dev->name); @@ -5030,7 +5029,7 @@ static void s2io_set_multicast(struct net_device *dev) /* Wait for command completes */ if (wait_for_cmd_complete(&bar0->rmac_addr_cmd_mem, RMAC_ADDR_CMD_MEM_STROBE_CMD_EXECUTING, - S2IO_BIT_RESET)) { + S2IO_BIT_RESET, may_sleep)) { DBG_PRINT(ERR_DBG, "%s: Adding Multicasts failed\n", dev->name); @@ -5041,6 +5040,12 @@ static void s2io_set_multicast(struct net_device *dev) } } +/* NDO wrapper for s2io_set_multicast */ +static void s2io_ndo_set_multicast(struct net_device *dev) +{ + s2io_set_multicast(dev, false); +} + /* read from CAM unicast & multicast addresses and store it in * def_mac_addr structure */ @@ -5127,7 +5132,7 @@ static int do_s2io_add_mac(struct s2io_nic *sp, u64 addr, int off) /* Wait till command completes */ if (wait_for_cmd_complete(&bar0->rmac_addr_cmd_mem, RMAC_ADDR_CMD_MEM_STROBE_CMD_EXECUTING, - S2IO_BIT_RESET)) { + S2IO_BIT_RESET, true)) { DBG_PRINT(INFO_DBG, "do_s2io_add_mac failed\n"); return FAILURE; } @@ -5171,7 +5176,7 @@ static u64 do_s2io_read_unicast_mc(struct s2io_nic *sp, int offset) /* Wait till command completes */ if (wait_for_cmd_complete(&bar0->rmac_addr_cmd_mem, RMAC_ADDR_CMD_MEM_STROBE_CMD_EXECUTING, - S2IO_BIT_RESET)) { + S2IO_BIT_RESET, true)) { DBG_PRINT(INFO_DBG, "do_s2io_read_unicast_mc failed\n"); return FAILURE; } @@ -7141,7 +7146,7 @@ static int s2io_card_up(struct s2io_nic *sp) } /* Setting its receive mode */ - s2io_set_multicast(dev); + s2io_set_multicast(dev, true); if (dev->features & NETIF_F_LRO) { /* Initialize max aggregatable pkts per session based on MTU */ @@ -7447,7 +7452,7 @@ static void s2io_link(struct s2io_nic *sp, int link) struct swStat *swstats = &sp->mac_control.stats_info->sw_stat; if (link != sp->last_link_state) { - init_tti(sp, link); + init_tti(sp, link, false); if (link == LINK_DOWN) { DBG_PRINT(ERR_DBG, "%s: Link down\n", dev->name); s2io_stop_all_tx_queue(sp); @@ -7604,7 +7609,7 @@ static int rts_ds_steer(struct s2io_nic *nic, u8 ds_codepoint, u8 ring) return wait_for_cmd_complete(&bar0->rts_ds_mem_ctrl, RTS_DS_MEM_CTRL_STROBE_CMD_BEING_EXECUTED, - S2IO_BIT_RESET); + S2IO_BIT_RESET, true); } static const struct net_device_ops s2io_netdev_ops = { @@ -7613,7 +7618,7 @@ static const struct net_device_ops s2io_netdev_ops = { .ndo_get_stats = s2io_get_stats, .ndo_start_xmit = s2io_xmit, .ndo_validate_addr = eth_validate_addr, - .ndo_set_rx_mode = s2io_set_multicast, + .ndo_set_rx_mode = s2io_ndo_set_multicast, .ndo_do_ioctl = s2io_ioctl, .ndo_set_mac_address = s2io_set_mac_addr, .ndo_change_mtu = s2io_change_mtu, @@ -7929,7 +7934,7 @@ s2io_init_nic(struct pci_dev *pdev, const struct pci_device_id *pre) writeq(val64, &bar0->rmac_addr_cmd_mem); wait_for_cmd_complete(&bar0->rmac_addr_cmd_mem, RMAC_ADDR_CMD_MEM_STROBE_CMD_EXECUTING, - S2IO_BIT_RESET); + S2IO_BIT_RESET, true); tmp64 = readq(&bar0->rmac_addr_data0_mem); mac_down = (u32)tmp64; mac_up = (u32) (tmp64 >> 32); diff --git a/drivers/net/ethernet/neterion/s2io.h b/drivers/net/ethernet/neterion/s2io.h index 6fa3159a977f..5a6032212c19 100644 --- a/drivers/net/ethernet/neterion/s2io.h +++ b/drivers/net/ethernet/neterion/s2io.h @@ -1066,7 +1066,7 @@ static void tx_intr_handler(struct fifo_info *fifo_data); static void s2io_handle_errors(void * dev_id); static void s2io_tx_watchdog(struct net_device *dev, unsigned int txqueue); -static void s2io_set_multicast(struct net_device *dev); +static void s2io_set_multicast(struct net_device *dev, bool may_sleep); static int rx_osm_handler(struct ring_info *ring_data, struct RxD_t * rxdp); static void s2io_link(struct s2io_nic * sp, int link); static void s2io_reset(struct s2io_nic * sp); @@ -1087,7 +1087,7 @@ static int s2io_set_swapper(struct s2io_nic * sp); static void s2io_card_down(struct s2io_nic *nic); static int s2io_card_up(struct s2io_nic *nic); static int wait_for_cmd_complete(void __iomem *addr, u64 busy_bit, - int bit_state); + int bit_state, bool may_sleep); static int s2io_add_isr(struct s2io_nic * sp); static void s2io_rem_isr(struct s2io_nic * sp); diff --git a/drivers/net/ethernet/neterion/vxge/vxge-config.c b/drivers/net/ethernet/neterion/vxge/vxge-config.c index f5d48d7c4ce2..da48dd85770c 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-config.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-config.c @@ -1121,7 +1121,7 @@ static void __vxge_hw_blockpool_destroy(struct __vxge_hw_blockpool *blockpool) list_for_each_safe(p, n, &blockpool->free_entry_list) { list_del(&((struct __vxge_hw_blockpool_entry *)p)->item); - kfree((void *)p); + kfree(p); } return; diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c index 2fc10a36afa4..8724d6a9ed02 100644 --- a/drivers/net/ethernet/nvidia/forcedeth.c +++ b/drivers/net/ethernet/nvidia/forcedeth.c @@ -1043,8 +1043,7 @@ static int using_multi_irqs(struct net_device *dev) struct fe_priv *np = get_nvpriv(dev); if (!(np->msi_flags & NV_MSI_X_ENABLED) || - ((np->msi_flags & NV_MSI_X_ENABLED) && - ((np->msi_flags & NV_MSI_X_VECTORS_MASK) == 0x1))) + ((np->msi_flags & NV_MSI_X_VECTORS_MASK) == 0x1)) return 0; else return 1; @@ -1666,11 +1665,7 @@ static void nv_update_stats(struct net_device *dev) struct fe_priv *np = netdev_priv(dev); u8 __iomem *base = get_hwbase(dev); - /* If it happens that this is run in top-half context, then - * replace the spin_lock of hwstats_lock with - * spin_lock_irqsave() in calling functions. */ - WARN_ONCE(in_irq(), "forcedeth: estats spin_lock(_bh) from top-half"); - assert_spin_locked(&np->hwstats_lock); + lockdep_assert_held(&np->hwstats_lock); /* query hardware */ np->estats.tx_bytes += readl(base + NvRegTxCnt); diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 7766d73823eb..07d197141bbe 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -67,7 +67,7 @@ #define R8169_REGS_SIZE 256 #define R8169_RX_BUF_SIZE (SZ_16K - 1) -#define NUM_TX_DESC 64 /* Number of Tx descriptor registers */ +#define NUM_TX_DESC 256 /* Number of Tx descriptor registers */ #define NUM_RX_DESC 256U /* Number of Rx descriptor registers */ #define R8169_TX_RING_BYTES (NUM_TX_DESC * sizeof(struct TxDesc)) #define R8169_RX_RING_BYTES (NUM_RX_DESC * sizeof(struct RxDesc)) @@ -584,12 +584,6 @@ enum rtl_flag { RTL_FLAG_MAX }; -struct rtl8169_stats { - u64 packets; - u64 bytes; - struct u64_stats_sync syncp; -}; - struct rtl8169_private { void __iomem *mmio_addr; /* memory map physical address */ struct pci_dev *pci_dev; @@ -600,8 +594,6 @@ struct rtl8169_private { u32 cur_rx; /* Index into the Rx descriptor buffer of next Rx pkt. */ u32 cur_tx; /* Index into the Tx descriptor buffer of next Rx pkt. */ u32 dirty_tx; - struct rtl8169_stats rx_stats; - struct rtl8169_stats tx_stats; struct TxDesc *TxDescArray; /* 256-aligned Tx descriptor ring */ struct RxDesc *RxDescArray; /* 256-aligned Rx descriptor ring */ dma_addr_t TxPhyAddr; @@ -700,27 +692,6 @@ static bool rtl_supports_eee(struct rtl8169_private *tp) tp->mac_version != RTL_GIGA_MAC_VER_39; } -static void rtl_get_priv_stats(struct rtl8169_stats *stats, - u64 *pkts, u64 *bytes) -{ - unsigned int start; - - do { - start = u64_stats_fetch_begin_irq(&stats->syncp); - *pkts = stats->packets; - *bytes = stats->bytes; - } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); -} - -static void rtl_inc_priv_stats(struct rtl8169_stats *stats, - u64 pkts, u64 bytes) -{ - u64_stats_update_begin(&stats->syncp); - stats->packets += pkts; - stats->bytes += bytes; - u64_stats_update_end(&stats->syncp); -} - static void rtl_read_mac_from_reg(struct rtl8169_private *tp, u8 *mac, int reg) { int i; @@ -4401,9 +4372,8 @@ static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp, unsigned int dirty_tx, tx_left, bytes_compl = 0, pkts_compl = 0; dirty_tx = tp->dirty_tx; - smp_rmb(); - for (tx_left = tp->cur_tx - dirty_tx; tx_left > 0; tx_left--) { + for (tx_left = READ_ONCE(tp->cur_tx) - dirty_tx; tx_left; tx_left--) { unsigned int entry = dirty_tx % NUM_TX_DESC; struct sk_buff *skb = tp->tx_skb[entry].skb; u32 status; @@ -4424,8 +4394,7 @@ static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp, if (tp->dirty_tx != dirty_tx) { netdev_completed_queue(dev, pkts_compl, bytes_compl); - - rtl_inc_priv_stats(&tp->tx_stats, pkts_compl, bytes_compl); + dev_sw_netstats_tx_add(dev, pkts_compl, bytes_compl); tp->dirty_tx = dirty_tx; /* Sync with rtl8169_start_xmit: @@ -4547,7 +4516,7 @@ static int rtl_rx(struct net_device *dev, struct rtl8169_private *tp, u32 budget napi_gro_receive(&tp->napi, skb); - rtl_inc_priv_stats(&tp->rx_stats, 1, pkt_size); + dev_sw_netstats_rx_add(dev, pkt_size); release_descriptor: rtl8169_mark_to_asic(desc); } @@ -4729,6 +4698,7 @@ static int rtl_open(struct net_device *dev) { struct rtl8169_private *tp = netdev_priv(dev); struct pci_dev *pdev = tp->pci_dev; + unsigned long irqflags; int retval = -ENOMEM; pm_runtime_get_sync(&pdev->dev); @@ -4740,7 +4710,7 @@ static int rtl_open(struct net_device *dev) tp->TxDescArray = dma_alloc_coherent(&pdev->dev, R8169_TX_RING_BYTES, &tp->TxPhyAddr, GFP_KERNEL); if (!tp->TxDescArray) - goto err_pm_runtime_put; + goto out; tp->RxDescArray = dma_alloc_coherent(&pdev->dev, R8169_RX_RING_BYTES, &tp->RxPhyAddr, GFP_KERNEL); @@ -4753,8 +4723,9 @@ static int rtl_open(struct net_device *dev) rtl_request_firmware(tp); + irqflags = pci_dev_msi_enabled(pdev) ? IRQF_NO_THREAD : IRQF_SHARED; retval = request_irq(pci_irq_vector(pdev, 0), rtl8169_interrupt, - IRQF_SHARED, dev->name, tp); + irqflags, dev->name, tp); if (retval < 0) goto err_release_fw_2; @@ -4765,9 +4736,9 @@ static int rtl_open(struct net_device *dev) rtl8169_up(tp); rtl8169_init_counter_offsets(tp); netif_start_queue(dev); - - pm_runtime_put_sync(&pdev->dev); out: + pm_runtime_put_sync(&pdev->dev); + return retval; err_free_irq: @@ -4783,8 +4754,6 @@ err_free_tx_0: dma_free_coherent(&pdev->dev, R8169_TX_RING_BYTES, tp->TxDescArray, tp->TxPhyAddr); tp->TxDescArray = NULL; -err_pm_runtime_put: - pm_runtime_put_noidle(&pdev->dev); goto out; } @@ -4798,9 +4767,7 @@ rtl8169_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) pm_runtime_get_noresume(&pdev->dev); netdev_stats_to_stats64(stats, &dev->stats); - - rtl_get_priv_stats(&tp->rx_stats, &stats->rx_packets, &stats->rx_bytes); - rtl_get_priv_stats(&tp->tx_stats, &stats->tx_packets, &stats->tx_bytes); + dev_fetch_sw_netstats(stats, dev->tstats); /* * Fetch additional counter values missing in stats collected by driver @@ -5271,6 +5238,11 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) tp->eee_adv = -1; tp->ocp_base = OCP_STD_PHY_BASE; + dev->tstats = devm_netdev_alloc_pcpu_stats(&pdev->dev, + struct pcpu_sw_netstats); + if (!dev->tstats) + return -ENOMEM; + /* Get the *optional* external "ether_clk" used on some boards */ rc = rtl_get_ether_clk(tp); if (rc) @@ -5348,8 +5320,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) } INIT_WORK(&tp->wk.work, rtl_task); - u64_stats_init(&tp->rx_stats.syncp); - u64_stats_init(&tp->tx_stats.syncp); rtl_init_mac_address(tp); diff --git a/drivers/net/ethernet/sfc/bitfield.h b/drivers/net/ethernet/sfc/bitfield.h index 2590cab53e54..64731eb5dd56 100644 --- a/drivers/net/ethernet/sfc/bitfield.h +++ b/drivers/net/ethernet/sfc/bitfield.h @@ -285,7 +285,11 @@ typedef union efx_oword { field10, value10, \ field11, value11, \ field12, value12, \ - field13, value13) \ + field13, value13, \ + field14, value14, \ + field15, value15, \ + field16, value16, \ + field17, value17) \ (EFX_INSERT_FIELD_NATIVE((min), (max), field1, (value1)) | \ EFX_INSERT_FIELD_NATIVE((min), (max), field2, (value2)) | \ EFX_INSERT_FIELD_NATIVE((min), (max), field3, (value3)) | \ @@ -298,7 +302,11 @@ typedef union efx_oword { EFX_INSERT_FIELD_NATIVE((min), (max), field10, (value10)) | \ EFX_INSERT_FIELD_NATIVE((min), (max), field11, (value11)) | \ EFX_INSERT_FIELD_NATIVE((min), (max), field12, (value12)) | \ - EFX_INSERT_FIELD_NATIVE((min), (max), field13, (value13))) + EFX_INSERT_FIELD_NATIVE((min), (max), field13, (value13)) | \ + EFX_INSERT_FIELD_NATIVE((min), (max), field14, (value14)) | \ + EFX_INSERT_FIELD_NATIVE((min), (max), field15, (value15)) | \ + EFX_INSERT_FIELD_NATIVE((min), (max), field16, (value16)) | \ + EFX_INSERT_FIELD_NATIVE((min), (max), field17, (value17))) #define EFX_INSERT_FIELDS64(...) \ cpu_to_le64(EFX_INSERT_FIELDS_NATIVE(__VA_ARGS__)) @@ -340,7 +348,15 @@ typedef union efx_oword { #endif /* Populate an octword field with various numbers of arguments */ -#define EFX_POPULATE_OWORD_13 EFX_POPULATE_OWORD +#define EFX_POPULATE_OWORD_17 EFX_POPULATE_OWORD +#define EFX_POPULATE_OWORD_16(oword, ...) \ + EFX_POPULATE_OWORD_17(oword, EFX_DUMMY_FIELD, 0, __VA_ARGS__) +#define EFX_POPULATE_OWORD_15(oword, ...) \ + EFX_POPULATE_OWORD_16(oword, EFX_DUMMY_FIELD, 0, __VA_ARGS__) +#define EFX_POPULATE_OWORD_14(oword, ...) \ + EFX_POPULATE_OWORD_15(oword, EFX_DUMMY_FIELD, 0, __VA_ARGS__) +#define EFX_POPULATE_OWORD_13(oword, ...) \ + EFX_POPULATE_OWORD_14(oword, EFX_DUMMY_FIELD, 0, __VA_ARGS__) #define EFX_POPULATE_OWORD_12(oword, ...) \ EFX_POPULATE_OWORD_13(oword, EFX_DUMMY_FIELD, 0, __VA_ARGS__) #define EFX_POPULATE_OWORD_11(oword, ...) \ @@ -375,7 +391,15 @@ typedef union efx_oword { EFX_DWORD_3, 0xffffffff) /* Populate a quadword field with various numbers of arguments */ -#define EFX_POPULATE_QWORD_13 EFX_POPULATE_QWORD +#define EFX_POPULATE_QWORD_17 EFX_POPULATE_QWORD +#define EFX_POPULATE_QWORD_16(qword, ...) \ + EFX_POPULATE_QWORD_17(qword, EFX_DUMMY_FIELD, 0, __VA_ARGS__) +#define EFX_POPULATE_QWORD_15(qword, ...) \ + EFX_POPULATE_QWORD_16(qword, EFX_DUMMY_FIELD, 0, __VA_ARGS__) +#define EFX_POPULATE_QWORD_14(qword, ...) \ + EFX_POPULATE_QWORD_15(qword, EFX_DUMMY_FIELD, 0, __VA_ARGS__) +#define EFX_POPULATE_QWORD_13(qword, ...) \ + EFX_POPULATE_QWORD_14(qword, EFX_DUMMY_FIELD, 0, __VA_ARGS__) #define EFX_POPULATE_QWORD_12(qword, ...) \ EFX_POPULATE_QWORD_13(qword, EFX_DUMMY_FIELD, 0, __VA_ARGS__) #define EFX_POPULATE_QWORD_11(qword, ...) \ @@ -408,7 +432,15 @@ typedef union efx_oword { EFX_DWORD_1, 0xffffffff) /* Populate a dword field with various numbers of arguments */ -#define EFX_POPULATE_DWORD_13 EFX_POPULATE_DWORD +#define EFX_POPULATE_DWORD_17 EFX_POPULATE_DWORD +#define EFX_POPULATE_DWORD_16(dword, ...) \ + EFX_POPULATE_DWORD_17(dword, EFX_DUMMY_FIELD, 0, __VA_ARGS__) +#define EFX_POPULATE_DWORD_15(dword, ...) \ + EFX_POPULATE_DWORD_16(dword, EFX_DUMMY_FIELD, 0, __VA_ARGS__) +#define EFX_POPULATE_DWORD_14(dword, ...) \ + EFX_POPULATE_DWORD_15(dword, EFX_DUMMY_FIELD, 0, __VA_ARGS__) +#define EFX_POPULATE_DWORD_13(dword, ...) \ + EFX_POPULATE_DWORD_14(dword, EFX_DUMMY_FIELD, 0, __VA_ARGS__) #define EFX_POPULATE_DWORD_12(dword, ...) \ EFX_POPULATE_DWORD_13(dword, EFX_DUMMY_FIELD, 0, __VA_ARGS__) #define EFX_POPULATE_DWORD_11(dword, ...) \ diff --git a/drivers/net/ethernet/sfc/ef100_nic.c b/drivers/net/ethernet/sfc/ef100_nic.c index 3148fe770356..cd93c5ffd45c 100644 --- a/drivers/net/ethernet/sfc/ef100_nic.c +++ b/drivers/net/ethernet/sfc/ef100_nic.c @@ -182,8 +182,16 @@ static int efx_ef100_init_datapath_caps(struct efx_nic *efx) if (rc) return rc; - if (efx_ef100_has_cap(nic_data->datapath_caps2, TX_TSO_V3)) - efx->net_dev->features |= NETIF_F_TSO | NETIF_F_TSO6; + if (efx_ef100_has_cap(nic_data->datapath_caps2, TX_TSO_V3)) { + struct net_device *net_dev = efx->net_dev; + netdev_features_t tso = NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_PARTIAL | + NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_UDP_TUNNEL_CSUM; + + net_dev->features |= tso; + net_dev->hw_features |= tso; + net_dev->hw_enc_features |= tso; + net_dev->gso_partial_features |= NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_UDP_TUNNEL_CSUM; + } efx->num_mac_stats = MCDI_WORD(outbuf, GET_CAPABILITIES_V4_OUT_MAC_STATS_NUM_STATS); netif_dbg(efx, probe, efx->net_dev, @@ -686,7 +694,7 @@ static unsigned int ef100_check_caps(const struct efx_nic *efx, #define EF100_OFFLOAD_FEATURES (NETIF_F_HW_CSUM | NETIF_F_RXCSUM | \ NETIF_F_HIGHDMA | NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_NTUPLE | \ NETIF_F_RXHASH | NETIF_F_RXFCS | NETIF_F_TSO_ECN | NETIF_F_RXALL | \ - NETIF_F_TSO_MANGLEID | NETIF_F_HW_VLAN_CTAG_TX) + NETIF_F_HW_VLAN_CTAG_TX) const struct efx_nic_type ef100_pf_nic_type = { .revision = EFX_REV_EF100, @@ -1101,6 +1109,9 @@ static int ef100_probe_main(struct efx_nic *efx) nic_data->efx = efx; net_dev->features |= efx->type->offload_features; net_dev->hw_features |= efx->type->offload_features; + net_dev->hw_enc_features |= efx->type->offload_features; + net_dev->vlan_features |= NETIF_F_HW_CSUM | NETIF_F_SG | + NETIF_F_HIGHDMA | NETIF_F_ALL_TSO; /* Populate design-parameter defaults */ nic_data->tso_max_hdr_len = ESE_EF100_DP_GZ_TSO_MAX_HDR_LEN_DEFAULT; diff --git a/drivers/net/ethernet/sfc/ef100_tx.c b/drivers/net/ethernet/sfc/ef100_tx.c index a90e5a9d2a37..ad0ad9bad423 100644 --- a/drivers/net/ethernet/sfc/ef100_tx.c +++ b/drivers/net/ethernet/sfc/ef100_tx.c @@ -54,8 +54,6 @@ static bool ef100_tx_can_tso(struct efx_tx_queue *tx_queue, struct sk_buff *skb) struct efx_nic *efx = tx_queue->efx; struct ef100_nic_data *nic_data; struct efx_tx_buffer *buffer; - struct tcphdr *tcphdr; - struct iphdr *iphdr; size_t header_len; u32 mss; @@ -98,20 +96,6 @@ static bool ef100_tx_can_tso(struct efx_tx_queue *tx_queue, struct sk_buff *skb) buffer->unmap_len = 0; buffer->skb = skb; ++tx_queue->insert_count; - - /* Adjust the TCP checksum to exclude the total length, since we set - * ED_INNER_IP_LEN in the descriptor. - */ - tcphdr = tcp_hdr(skb); - if (skb_is_gso_v6(skb)) { - tcphdr->check = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, - 0, IPPROTO_TCP, 0); - } else { - iphdr = ip_hdr(skb); - tcphdr->check = ~csum_tcpudp_magic(iphdr->saddr, iphdr->daddr, - 0, IPPROTO_TCP, 0); - } return true; } @@ -203,23 +187,42 @@ static void ef100_make_tso_desc(struct efx_nic *efx, struct efx_tx_buffer *buffer, efx_oword_t *txd, unsigned int segment_count) { - u32 mangleid = (efx->net_dev->features & NETIF_F_TSO_MANGLEID) || - skb_shinfo(skb)->gso_type & SKB_GSO_TCP_FIXEDID ? - ESE_GZ_TX_DESC_IP4_ID_NO_OP : - ESE_GZ_TX_DESC_IP4_ID_INC_MOD16; - u16 vlan_enable = efx->net_dev->features & NETIF_F_HW_VLAN_CTAG_TX ? - skb_vlan_tag_present(skb) : 0; + bool gso_partial = skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL; unsigned int len, ip_offset, tcp_offset, payload_segs; + u32 mangleid = ESE_GZ_TX_DESC_IP4_ID_INC_MOD16; + unsigned int outer_ip_offset, outer_l4_offset; u16 vlan_tci = skb_vlan_tag_get(skb); u32 mss = skb_shinfo(skb)->gso_size; + bool encap = skb->encapsulation; + u16 vlan_enable = 0; + struct tcphdr *tcp; + u32 paylen; + + if (skb_shinfo(skb)->gso_type & SKB_GSO_TCP_FIXEDID) + mangleid = ESE_GZ_TX_DESC_IP4_ID_NO_OP; + if (efx->net_dev->features & NETIF_F_HW_VLAN_CTAG_TX) + vlan_enable = skb_vlan_tag_present(skb); len = skb->len - buffer->len; /* We use 1 for the TSO descriptor and 1 for the header */ payload_segs = segment_count - 2; - ip_offset = skb_network_offset(skb); - tcp_offset = skb_transport_offset(skb); + if (encap) { + outer_ip_offset = skb_network_offset(skb); + outer_l4_offset = skb_transport_offset(skb); + ip_offset = skb_inner_network_offset(skb); + tcp_offset = skb_inner_transport_offset(skb); + } else { + ip_offset = skb_network_offset(skb); + tcp_offset = skb_transport_offset(skb); + outer_ip_offset = outer_l4_offset = 0; + } + + /* subtract TCP payload length from inner checksum */ + tcp = (void *)skb->data + tcp_offset; + paylen = skb->len - tcp_offset; + csum_replace_by_diff(&tcp->check, (__force __wsum)htonl(paylen)); - EFX_POPULATE_OWORD_13(*txd, + EFX_POPULATE_OWORD_17(*txd, ESF_GZ_TX_DESC_TYPE, ESE_GZ_TX_DESC_TYPE_TSO, ESF_GZ_TX_TSO_MSS, mss, ESF_GZ_TX_TSO_HDR_NUM_SEGS, 1, @@ -231,6 +234,11 @@ static void ef100_make_tso_desc(struct efx_nic *efx, ESF_GZ_TX_TSO_INNER_L4_OFF_W, tcp_offset >> 1, ESF_GZ_TX_TSO_ED_INNER_IP4_ID, mangleid, ESF_GZ_TX_TSO_ED_INNER_IP_LEN, 1, + ESF_GZ_TX_TSO_OUTER_L3_OFF_W, outer_ip_offset >> 1, + ESF_GZ_TX_TSO_OUTER_L4_OFF_W, outer_l4_offset >> 1, + ESF_GZ_TX_TSO_ED_OUTER_UDP_LEN, encap && !gso_partial, + ESF_GZ_TX_TSO_ED_OUTER_IP4_ID, encap ? mangleid : + ESE_GZ_TX_DESC_IP4_ID_NO_OP, ESF_GZ_TX_TSO_VLAN_INSERT_EN, vlan_enable, ESF_GZ_TX_TSO_VLAN_INSERT_TCI, vlan_tci ); diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index df7de50497a0..6f271c46368d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -402,6 +402,7 @@ struct dma_features { /* Default LPI timers */ #define STMMAC_DEFAULT_LIT_LS 0x3E8 #define STMMAC_DEFAULT_TWT_LS 0x1E +#define STMMAC_ET_MAX 0xFFFFF #define STMMAC_CHAIN_MODE 0x1 #define STMMAC_RING_MODE 0x2 diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c index 5afcf05bbf9c..dc0b8b6d180d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c @@ -299,7 +299,7 @@ static int meson8b_init_prg_eth(struct meson8b_dwmac *dwmac) dev_err(dwmac->dev, "unsupported phy-mode %s\n", phy_modes(dwmac->phy_mode)); return -EINVAL; - }; + } if (rx_dly_config & PRG_ETH0_ADJ_ENABLE) { if (!dwmac->timing_adj_clk) { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h index 592b043f9676..82df91c130f7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h @@ -176,9 +176,11 @@ enum power_event { */ #define GMAC4_LPI_CTRL_STATUS 0xd0 #define GMAC4_LPI_TIMER_CTRL 0xd4 +#define GMAC4_LPI_ENTRY_TIMER 0xd8 /* LPI control and status defines */ #define GMAC4_LPI_CTRL_STATUS_LPITCSE BIT(21) /* LPI Tx Clock Stop Enable */ +#define GMAC4_LPI_CTRL_STATUS_LPIATE BIT(20) /* LPI Timer Enable */ #define GMAC4_LPI_CTRL_STATUS_LPITXA BIT(19) /* Enable LPI TX Automate */ #define GMAC4_LPI_CTRL_STATUS_PLS BIT(17) /* PHY Link Status */ #define GMAC4_LPI_CTRL_STATUS_LPIEN BIT(16) /* LPI Enable */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index 002791b77356..3ed4f4cda7f9 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -379,6 +379,27 @@ static void dwmac4_set_eee_pls(struct mac_device_info *hw, int link) writel(value, ioaddr + GMAC4_LPI_CTRL_STATUS); } +static void dwmac4_set_eee_lpi_entry_timer(struct mac_device_info *hw, int et) +{ + void __iomem *ioaddr = hw->pcsr; + int value = et & STMMAC_ET_MAX; + int regval; + + /* Program LPI entry timer value into register */ + writel(value, ioaddr + GMAC4_LPI_ENTRY_TIMER); + + /* Enable/disable LPI entry timer */ + regval = readl(ioaddr + GMAC4_LPI_CTRL_STATUS); + regval |= GMAC4_LPI_CTRL_STATUS_LPIEN | GMAC4_LPI_CTRL_STATUS_LPITXA; + + if (et) + regval |= GMAC4_LPI_CTRL_STATUS_LPIATE; + else + regval &= ~GMAC4_LPI_CTRL_STATUS_LPIATE; + + writel(regval, ioaddr + GMAC4_LPI_CTRL_STATUS); +} + static void dwmac4_set_eee_timer(struct mac_device_info *hw, int ls, int tw) { void __iomem *ioaddr = hw->pcsr; @@ -1164,6 +1185,7 @@ const struct stmmac_ops dwmac4_ops = { .get_umac_addr = dwmac4_get_umac_addr, .set_eee_mode = dwmac4_set_eee_mode, .reset_eee_mode = dwmac4_reset_eee_mode, + .set_eee_lpi_entry_timer = dwmac4_set_eee_lpi_entry_timer, .set_eee_timer = dwmac4_set_eee_timer, .set_eee_pls = dwmac4_set_eee_pls, .pcs_ctrl_ane = dwmac4_ctrl_ane, @@ -1206,6 +1228,7 @@ const struct stmmac_ops dwmac410_ops = { .get_umac_addr = dwmac4_get_umac_addr, .set_eee_mode = dwmac4_set_eee_mode, .reset_eee_mode = dwmac4_reset_eee_mode, + .set_eee_lpi_entry_timer = dwmac4_set_eee_lpi_entry_timer, .set_eee_timer = dwmac4_set_eee_timer, .set_eee_pls = dwmac4_set_eee_pls, .pcs_ctrl_ane = dwmac4_ctrl_ane, @@ -1249,6 +1272,7 @@ const struct stmmac_ops dwmac510_ops = { .get_umac_addr = dwmac4_get_umac_addr, .set_eee_mode = dwmac4_set_eee_mode, .reset_eee_mode = dwmac4_reset_eee_mode, + .set_eee_lpi_entry_timer = dwmac4_set_eee_lpi_entry_timer, .set_eee_timer = dwmac4_set_eee_timer, .set_eee_pls = dwmac4_set_eee_pls, .pcs_ctrl_ane = dwmac4_ctrl_ane, diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index e2dca9b6e992..b40b2e0667bb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -337,6 +337,7 @@ struct stmmac_ops { void (*set_eee_mode)(struct mac_device_info *hw, bool en_tx_lpi_clockgating); void (*reset_eee_mode)(struct mac_device_info *hw); + void (*set_eee_lpi_entry_timer)(struct mac_device_info *hw, int et); void (*set_eee_timer)(struct mac_device_info *hw, int ls, int tw); void (*set_eee_pls)(struct mac_device_info *hw, int link); void (*debug)(void __iomem *ioaddr, struct stmmac_extra_stats *x, @@ -439,6 +440,8 @@ struct stmmac_ops { stmmac_do_void_callback(__priv, mac, set_eee_mode, __args) #define stmmac_reset_eee_mode(__priv, __args...) \ stmmac_do_void_callback(__priv, mac, reset_eee_mode, __args) +#define stmmac_set_eee_lpi_timer(__priv, __args...) \ + stmmac_do_void_callback(__priv, mac, set_eee_lpi_entry_timer, __args) #define stmmac_set_eee_timer(__priv, __args...) \ stmmac_do_void_callback(__priv, mac, set_eee_timer, __args) #define stmmac_set_eee_pls(__priv, __args...) \ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 727e68dfaf1c..c88ee8ea4245 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -207,6 +207,7 @@ struct stmmac_priv { int tx_lpi_timer; int tx_lpi_enabled; int eee_tw_timer; + bool eee_sw_timer_en; unsigned int mode; unsigned int chain_mode; int extend_desc; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index d833908b660a..ba855465a2db 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -294,6 +294,16 @@ static inline u32 stmmac_rx_dirty(struct stmmac_priv *priv, u32 queue) return dirty; } +static void stmmac_lpi_entry_timer_config(struct stmmac_priv *priv, bool en) +{ + int tx_lpi_timer; + + /* Clear/set the SW EEE timer flag based on LPI ET enablement */ + priv->eee_sw_timer_en = en ? 0 : 1; + tx_lpi_timer = en ? priv->tx_lpi_timer : 0; + stmmac_set_eee_lpi_timer(priv, priv->hw, tx_lpi_timer); +} + /** * stmmac_enable_eee_mode - check and enter in LPI mode * @priv: driver private structure @@ -327,6 +337,11 @@ static void stmmac_enable_eee_mode(struct stmmac_priv *priv) */ void stmmac_disable_eee_mode(struct stmmac_priv *priv) { + if (!priv->eee_sw_timer_en) { + stmmac_lpi_entry_timer_config(priv, 0); + return; + } + stmmac_reset_eee_mode(priv, priv->hw); del_timer_sync(&priv->eee_ctrl_timer); priv->tx_path_in_lpi_mode = false; @@ -376,6 +391,7 @@ bool stmmac_eee_init(struct stmmac_priv *priv) if (!priv->eee_active) { if (priv->eee_enabled) { netdev_dbg(priv->dev, "disable EEE\n"); + stmmac_lpi_entry_timer_config(priv, 0); del_timer_sync(&priv->eee_ctrl_timer); stmmac_set_eee_timer(priv, priv->hw, 0, eee_tw_timer); } @@ -389,7 +405,15 @@ bool stmmac_eee_init(struct stmmac_priv *priv) eee_tw_timer); } - mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(priv->tx_lpi_timer)); + if (priv->plat->has_gmac4 && priv->tx_lpi_timer <= STMMAC_ET_MAX) { + del_timer_sync(&priv->eee_ctrl_timer); + priv->tx_path_in_lpi_mode = false; + stmmac_lpi_entry_timer_config(priv, 1); + } else { + stmmac_lpi_entry_timer_config(priv, 0); + mod_timer(&priv->eee_ctrl_timer, + STMMAC_LPI_T(priv->tx_lpi_timer)); + } mutex_unlock(&priv->lock); netdev_dbg(priv->dev, "Energy-Efficient Ethernet initialized\n"); @@ -2044,7 +2068,8 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue) netif_tx_wake_queue(netdev_get_tx_queue(priv->dev, queue)); } - if ((priv->eee_enabled) && (!priv->tx_path_in_lpi_mode)) { + if (priv->eee_enabled && !priv->tx_path_in_lpi_mode && + priv->eee_sw_timer_en) { stmmac_enable_eee_mode(priv); mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(priv->tx_lpi_timer)); } @@ -3306,7 +3331,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) tx_q = &priv->tx_queue[queue]; first_tx = tx_q->cur_tx; - if (priv->tx_path_in_lpi_mode) + if (priv->tx_path_in_lpi_mode && priv->eee_sw_timer_en) stmmac_disable_eee_mode(priv); /* Manage oversized TCP frames for GMAC4 device */ diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 501d676fd88b..766e8866bbef 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -241,8 +241,8 @@ static int am65_cpsw_nuss_ndo_slave_add_vid(struct net_device *ndev, if (!vid) unreg_mcast = port_mask; dev_info(common->dev, "Adding vlan %d to vlan filter\n", vid); - ret = cpsw_ale_add_vlan(common->ale, vid, port_mask, - unreg_mcast, port_mask, 0); + ret = cpsw_ale_vlan_add_modify(common->ale, vid, port_mask, + unreg_mcast, port_mask, 0); pm_runtime_put(common->dev); return ret; @@ -252,6 +252,7 @@ static int am65_cpsw_nuss_ndo_slave_kill_vid(struct net_device *ndev, __be16 proto, u16 vid) { struct am65_cpsw_common *common = am65_ndev_to_common(ndev); + struct am65_cpsw_port *port = am65_ndev_to_port(ndev); int ret; if (!netif_running(ndev) || !vid) @@ -264,14 +265,15 @@ static int am65_cpsw_nuss_ndo_slave_kill_vid(struct net_device *ndev, } dev_info(common->dev, "Removing vlan %d from vlan filter\n", vid); - ret = cpsw_ale_del_vlan(common->ale, vid, 0); + ret = cpsw_ale_del_vlan(common->ale, vid, + BIT(port->port_id) | ALE_PORT_HOST); pm_runtime_put(common->dev); return ret; } -static void am65_cpsw_slave_set_promisc_2g(struct am65_cpsw_port *port, - bool promisc) +static void am65_cpsw_slave_set_promisc(struct am65_cpsw_port *port, + bool promisc) { struct am65_cpsw_common *common = port->common; @@ -296,7 +298,7 @@ static void am65_cpsw_nuss_ndo_slave_set_rx_mode(struct net_device *ndev) bool promisc; promisc = !!(ndev->flags & IFF_PROMISC); - am65_cpsw_slave_set_promisc_2g(port, promisc); + am65_cpsw_slave_set_promisc(port, promisc); if (promisc) return; @@ -373,7 +375,7 @@ static int am65_cpsw_nuss_rx_push(struct am65_cpsw_common *common, cppi5_hdesc_init(desc_rx, CPPI5_INFO0_HDESC_EPIB_PRESENT, AM65_CPSW_NAV_PS_DATA_SIZE); - cppi5_hdesc_attach_buf(desc_rx, 0, 0, buf_dma, skb_tailroom(skb)); + cppi5_hdesc_attach_buf(desc_rx, buf_dma, skb_tailroom(skb), buf_dma, skb_tailroom(skb)); swdata = cppi5_hdesc_get_swdata(desc_rx); *((void **)swdata) = skb; @@ -426,9 +428,7 @@ static int am65_cpsw_nuss_common_open(struct am65_cpsw_common *common, writel(common->rx_flow_id_base, host_p->port_base + AM65_CPSW_PORT0_REG_FLOW_ID_OFFSET); /* en tx crc offload */ - if (features & NETIF_F_HW_CSUM) - writel(AM65_CPSW_P0_REG_CTL_RX_CHECKSUM_EN, - host_p->port_base + AM65_CPSW_P0_REG_CTL); + writel(AM65_CPSW_P0_REG_CTL_RX_CHECKSUM_EN, host_p->port_base + AM65_CPSW_P0_REG_CTL); am65_cpsw_nuss_set_p0_ptype(common); @@ -629,13 +629,13 @@ static int am65_cpsw_nuss_ndo_slave_open(struct net_device *ndev) am65_cpsw_port_set_sl_mac(port, ndev->dev_addr); - if (port->slave.mac_only) + if (port->slave.mac_only) { /* enable mac-only mode on port */ cpsw_ale_control_set(common->ale, port->port_id, ALE_PORT_MACONLY, 1); - if (AM65_CPSW_IS_CPSW2G(common)) cpsw_ale_control_set(common->ale, port->port_id, ALE_PORT_NOLEARN, 1); + } port_mask = BIT(port->port_id) | ALE_PORT_HOST; cpsw_ale_add_ucast(common->ale, ndev->dev_addr, @@ -767,7 +767,7 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_common *common, return ret; } - if (desc_dma & 0x1) { + if (cppi5_desc_is_tdcm(desc_dma)) { dev_dbg(dev, "%s RX tdown flow: %u\n", __func__, flow_idx); return 0; } @@ -911,10 +911,57 @@ static void am65_cpsw_nuss_tx_cleanup(void *data, dma_addr_t desc_dma) dev_kfree_skb_any(skb); } +static struct sk_buff * +am65_cpsw_nuss_tx_compl_packet(struct am65_cpsw_tx_chn *tx_chn, + dma_addr_t desc_dma) +{ + struct am65_cpsw_ndev_priv *ndev_priv; + struct am65_cpsw_ndev_stats *stats; + struct cppi5_host_desc_t *desc_tx; + struct net_device *ndev; + struct sk_buff *skb; + void **swdata; + + desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool, + desc_dma); + swdata = cppi5_hdesc_get_swdata(desc_tx); + skb = *(swdata); + am65_cpsw_nuss_xmit_free(tx_chn, tx_chn->common->dev, desc_tx); + + ndev = skb->dev; + + am65_cpts_tx_timestamp(tx_chn->common->cpts, skb); + + ndev_priv = netdev_priv(ndev); + stats = this_cpu_ptr(ndev_priv->stats); + u64_stats_update_begin(&stats->syncp); + stats->tx_packets++; + stats->tx_bytes += skb->len; + u64_stats_update_end(&stats->syncp); + + return skb; +} + +static void am65_cpsw_nuss_tx_wake(struct am65_cpsw_tx_chn *tx_chn, struct net_device *ndev, + struct netdev_queue *netif_txq) +{ + if (netif_tx_queue_stopped(netif_txq)) { + /* Check whether the queue is stopped due to stalled + * tx dma, if the queue is stopped then wake the queue + * as we have free desc for tx + */ + __netif_tx_lock(netif_txq, smp_processor_id()); + if (netif_running(ndev) && + (k3_cppi_desc_pool_avail(tx_chn->desc_pool) >= MAX_SKB_FRAGS)) + netif_tx_wake_queue(netif_txq); + + __netif_tx_unlock(netif_txq); + } +} + static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common, int chn, unsigned int budget) { - struct cppi5_host_desc_t *desc_tx; struct device *dev = common->dev; struct am65_cpsw_tx_chn *tx_chn; struct netdev_queue *netif_txq; @@ -923,41 +970,68 @@ static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common, struct sk_buff *skb; dma_addr_t desc_dma; int res, num_tx = 0; - void **swdata; tx_chn = &common->tx_chns[chn]; while (true) { - struct am65_cpsw_ndev_priv *ndev_priv; - struct am65_cpsw_ndev_stats *stats; - + spin_lock(&tx_chn->lock); res = k3_udma_glue_pop_tx_chn(tx_chn->tx_chn, &desc_dma); + spin_unlock(&tx_chn->lock); if (res == -ENODATA) break; - if (desc_dma & 0x1) { + if (cppi5_desc_is_tdcm(desc_dma)) { if (atomic_dec_and_test(&common->tdown_cnt)) complete(&common->tdown_complete); break; } - desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool, - desc_dma); - swdata = cppi5_hdesc_get_swdata(desc_tx); - skb = *(swdata); - am65_cpsw_nuss_xmit_free(tx_chn, dev, desc_tx); - + skb = am65_cpsw_nuss_tx_compl_packet(tx_chn, desc_dma); + total_bytes = skb->len; ndev = skb->dev; + napi_consume_skb(skb, budget); + num_tx++; - am65_cpts_tx_timestamp(common->cpts, skb); + netif_txq = netdev_get_tx_queue(ndev, chn); - ndev_priv = netdev_priv(ndev); - stats = this_cpu_ptr(ndev_priv->stats); - u64_stats_update_begin(&stats->syncp); - stats->tx_packets++; - stats->tx_bytes += skb->len; - u64_stats_update_end(&stats->syncp); + netdev_tx_completed_queue(netif_txq, num_tx, total_bytes); + am65_cpsw_nuss_tx_wake(tx_chn, ndev, netif_txq); + } + + dev_dbg(dev, "%s:%u pkt:%d\n", __func__, chn, num_tx); + + return num_tx; +} + +static int am65_cpsw_nuss_tx_compl_packets_2g(struct am65_cpsw_common *common, + int chn, unsigned int budget) +{ + struct device *dev = common->dev; + struct am65_cpsw_tx_chn *tx_chn; + struct netdev_queue *netif_txq; + unsigned int total_bytes = 0; + struct net_device *ndev; + struct sk_buff *skb; + dma_addr_t desc_dma; + int res, num_tx = 0; + + tx_chn = &common->tx_chns[chn]; + + while (true) { + res = k3_udma_glue_pop_tx_chn(tx_chn->tx_chn, &desc_dma); + if (res == -ENODATA) + break; + + if (cppi5_desc_is_tdcm(desc_dma)) { + if (atomic_dec_and_test(&common->tdown_cnt)) + complete(&common->tdown_complete); + break; + } + + skb = am65_cpsw_nuss_tx_compl_packet(tx_chn, desc_dma); + + ndev = skb->dev; total_bytes += skb->len; napi_consume_skb(skb, budget); num_tx++; @@ -970,19 +1044,8 @@ static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common, netdev_tx_completed_queue(netif_txq, num_tx, total_bytes); - if (netif_tx_queue_stopped(netif_txq)) { - /* Check whether the queue is stopped due to stalled tx dma, - * if the queue is stopped then wake the queue as - * we have free desc for tx - */ - __netif_tx_lock(netif_txq, smp_processor_id()); - if (netif_running(ndev) && - (k3_cppi_desc_pool_avail(tx_chn->desc_pool) >= - MAX_SKB_FRAGS)) - netif_tx_wake_queue(netif_txq); + am65_cpsw_nuss_tx_wake(tx_chn, ndev, netif_txq); - __netif_tx_unlock(netif_txq); - } dev_dbg(dev, "%s:%u pkt:%d\n", __func__, chn, num_tx); return num_tx; @@ -993,8 +1056,11 @@ static int am65_cpsw_nuss_tx_poll(struct napi_struct *napi_tx, int budget) struct am65_cpsw_tx_chn *tx_chn = am65_cpsw_napi_to_tx_chn(napi_tx); int num_tx; - num_tx = am65_cpsw_nuss_tx_compl_packets(tx_chn->common, tx_chn->id, - budget); + if (AM65_CPSW_IS_CPSW2G(tx_chn->common)) + num_tx = am65_cpsw_nuss_tx_compl_packets_2g(tx_chn->common, tx_chn->id, budget); + else + num_tx = am65_cpsw_nuss_tx_compl_packets(tx_chn->common, tx_chn->id, budget); + num_tx = min(num_tx, budget); if (num_tx < budget) { napi_complete(napi_tx); @@ -1139,7 +1205,13 @@ done_tx: cppi5_hdesc_set_pktlen(first_desc, pkt_len); desc_dma = k3_cppi_desc_pool_virt2dma(tx_chn->desc_pool, first_desc); - ret = k3_udma_glue_push_tx_chn(tx_chn->tx_chn, first_desc, desc_dma); + if (AM65_CPSW_IS_CPSW2G(common)) { + ret = k3_udma_glue_push_tx_chn(tx_chn->tx_chn, first_desc, desc_dma); + } else { + spin_lock_bh(&tx_chn->lock); + ret = k3_udma_glue_push_tx_chn(tx_chn->tx_chn, first_desc, desc_dma); + spin_unlock_bh(&tx_chn->lock); + } if (ret) { dev_err(dev, "can't push desc %d\n", ret); /* inform bql */ @@ -1369,32 +1441,7 @@ static void am65_cpsw_nuss_ndo_get_stats(struct net_device *dev, stats->tx_dropped = dev->stats.tx_dropped; } -static int am65_cpsw_nuss_ndo_slave_set_features(struct net_device *ndev, - netdev_features_t features) -{ - struct am65_cpsw_common *common = am65_ndev_to_common(ndev); - netdev_features_t changes = features ^ ndev->features; - struct am65_cpsw_host *host_p; - - host_p = am65_common_get_host(common); - - if (changes & NETIF_F_HW_CSUM) { - bool enable = !!(features & NETIF_F_HW_CSUM); - - dev_info(common->dev, "Turn %s tx-checksum-ip-generic\n", - enable ? "ON" : "OFF"); - if (enable) - writel(AM65_CPSW_P0_REG_CTL_RX_CHECKSUM_EN, - host_p->port_base + AM65_CPSW_P0_REG_CTL); - else - writel(0, - host_p->port_base + AM65_CPSW_P0_REG_CTL); - } - - return 0; -} - -static const struct net_device_ops am65_cpsw_nuss_netdev_ops_2g = { +static const struct net_device_ops am65_cpsw_nuss_netdev_ops = { .ndo_open = am65_cpsw_nuss_ndo_slave_open, .ndo_stop = am65_cpsw_nuss_ndo_slave_stop, .ndo_start_xmit = am65_cpsw_nuss_ndo_slave_xmit, @@ -1406,7 +1453,6 @@ static const struct net_device_ops am65_cpsw_nuss_netdev_ops_2g = { .ndo_vlan_rx_add_vid = am65_cpsw_nuss_ndo_slave_add_vid, .ndo_vlan_rx_kill_vid = am65_cpsw_nuss_ndo_slave_kill_vid, .ndo_do_ioctl = am65_cpsw_nuss_ndo_slave_ioctl, - .ndo_set_features = am65_cpsw_nuss_ndo_slave_set_features, .ndo_setup_tc = am65_cpsw_qos_ndo_setup_tc, }; @@ -1417,7 +1463,6 @@ static void am65_cpsw_nuss_slave_disable_unused(struct am65_cpsw_port *port) if (!port->disabled) return; - common->disabled_ports_mask |= BIT(port->port_id); cpsw_ale_control_set(common->ale, port->port_id, ALE_PORT_STATE, ALE_PORT_STATE_DISABLE); @@ -1496,6 +1541,7 @@ static int am65_cpsw_nuss_init_tx_chns(struct am65_cpsw_common *common) snprintf(tx_chn->tx_chn_name, sizeof(tx_chn->tx_chn_name), "tx%d", i); + spin_lock_init(&tx_chn->lock); tx_chn->common = common; tx_chn->id = i; tx_chn->descs_num = max_desc_num; @@ -1515,9 +1561,8 @@ static int am65_cpsw_nuss_init_tx_chns(struct am65_cpsw_common *common) tx_chn->tx_chn_name, &tx_cfg); if (IS_ERR(tx_chn->tx_chn)) { - ret = PTR_ERR(tx_chn->tx_chn); - dev_err(dev, "Failed to request tx dma channel %d\n", - ret); + ret = dev_err_probe(dev, PTR_ERR(tx_chn->tx_chn), + "Failed to request tx dma channel\n"); goto err; } @@ -1588,8 +1633,8 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common) rx_chn->rx_chn = k3_udma_glue_request_rx_chn(dev, "rx", &rx_cfg); if (IS_ERR(rx_chn->rx_chn)) { - ret = PTR_ERR(rx_chn->rx_chn); - dev_err(dev, "Failed to request rx dma channel %d\n", ret); + ret = dev_err_probe(dev, PTR_ERR(rx_chn->rx_chn), + "Failed to request rx dma channel\n"); goto err; } @@ -1606,7 +1651,6 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common) }; struct k3_ring_cfg fdqring_cfg = { .elm_size = K3_RINGACC_RING_ELSIZE_8, - .mode = K3_RINGACC_RING_MODE_MESSAGE, .flags = K3_RINGACC_RING_SHARED, }; struct k3_udma_glue_rx_flow_cfg rx_flow_cfg = { @@ -1620,6 +1664,7 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common) rx_flow_cfg.ring_rxfdq0_id = fdqring_id; rx_flow_cfg.rx_cfg.size = max_desc_num; rx_flow_cfg.rxfdq_cfg.size = max_desc_num; + rx_flow_cfg.rxfdq_cfg.mode = common->pdata.fdqring_mode; ret = k3_udma_glue_rx_flow_init(rx_chn->rx_chn, i, &rx_flow_cfg); @@ -1725,6 +1770,13 @@ static int am65_cpsw_init_cpts(struct am65_cpsw_common *common) return ret; } common->cpts = cpts; + /* Forbid PM runtime if CPTS is running. + * K3 CPSWxG modules may completely lose context during ON->OFF + * transitions depending on integration. + * AM65x/J721E MCU CPSW2G: false + * J721E MAIN_CPSW9G: true + */ + pm_runtime_forbid(dev); return 0; } @@ -1778,8 +1830,10 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common) return PTR_ERR(port->slave.mac_sl); port->disabled = !of_device_is_available(port_np); - if (port->disabled) + if (port->disabled) { + common->disabled_ports_mask |= BIT(port->port_id); continue; + } port->slave.ifphy = devm_of_phy_get(dev, port_np, NULL); if (IS_ERR(port->slave.ifphy)) { @@ -1795,12 +1849,10 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common) /* get phy/link info */ if (of_phy_is_fixed_link(port_np)) { ret = of_phy_register_fixed_link(port_np); - if (ret) { - if (ret != -EPROBE_DEFER) - dev_err(dev, "%pOF failed to register fixed-link phy: %d\n", - port_np, ret); - return ret; - } + if (ret) + return dev_err_probe(dev, ret, + "failed to register fixed-link phy %pOF\n", + port_np); port->slave.phy_node = of_node_get(port_np); } else { port->slave.phy_node = @@ -1833,6 +1885,12 @@ static int am65_cpsw_nuss_init_slave_ports(struct am65_cpsw_common *common) } of_node_put(node); + /* is there at least one ext.port */ + if (!(~common->disabled_ports_mask & GENMASK(common->port_num, 1))) { + dev_err(dev, "No Ext. port are available\n"); + return -ENODEV; + } + return 0; } @@ -1843,14 +1901,18 @@ static void am65_cpsw_pcpu_stats_free(void *data) free_percpu(stats); } -static int am65_cpsw_nuss_init_ndev_2g(struct am65_cpsw_common *common) +static int +am65_cpsw_nuss_init_port_ndev(struct am65_cpsw_common *common, u32 port_idx) { struct am65_cpsw_ndev_priv *ndev_priv; struct device *dev = common->dev; struct am65_cpsw_port *port; int ret; - port = am65_common_get_port(common, 1); + port = &common->ports[port_idx]; + + if (port->disabled) + return 0; /* alloc netdev */ port->ndev = devm_alloc_etherdev_mqs(common->dev, @@ -1879,7 +1941,7 @@ static int am65_cpsw_nuss_init_ndev_2g(struct am65_cpsw_common *common) port->ndev->features = port->ndev->hw_features | NETIF_F_HW_VLAN_CTAG_FILTER; port->ndev->vlan_features |= NETIF_F_SG; - port->ndev->netdev_ops = &am65_cpsw_nuss_netdev_ops_2g; + port->ndev->netdev_ops = &am65_cpsw_nuss_netdev_ops; port->ndev->ethtool_ops = &am65_cpsw_ethtool_ops_slave; /* Disable TX checksum offload by default due to HW bug */ @@ -1892,29 +1954,41 @@ static int am65_cpsw_nuss_init_ndev_2g(struct am65_cpsw_common *common) ret = devm_add_action_or_reset(dev, am65_cpsw_pcpu_stats_free, ndev_priv->stats); - if (ret) { - dev_err(dev, "Failed to add percpu stat free action %d\n", ret); - return ret; + if (ret) + dev_err(dev, "failed to add percpu stat free action %d\n", ret); + + if (!common->dma_ndev) + common->dma_ndev = port->ndev; + + return ret; +} + +static int am65_cpsw_nuss_init_ndevs(struct am65_cpsw_common *common) +{ + int ret; + int i; + + for (i = 0; i < common->port_num; i++) { + ret = am65_cpsw_nuss_init_port_ndev(common, i); + if (ret) + return ret; } - netif_napi_add(port->ndev, &common->napi_rx, + netif_napi_add(common->dma_ndev, &common->napi_rx, am65_cpsw_nuss_rx_poll, NAPI_POLL_WEIGHT); return ret; } -static int am65_cpsw_nuss_ndev_add_napi_2g(struct am65_cpsw_common *common) +static int am65_cpsw_nuss_ndev_add_tx_napi(struct am65_cpsw_common *common) { struct device *dev = common->dev; - struct am65_cpsw_port *port; int i, ret = 0; - port = am65_common_get_port(common, 1); - for (i = 0; i < common->tx_ch_num; i++) { struct am65_cpsw_tx_chn *tx_chn = &common->tx_chns[i]; - netif_tx_napi_add(port->ndev, &tx_chn->napi_tx, + netif_tx_napi_add(common->dma_ndev, &tx_chn->napi_tx, am65_cpsw_nuss_tx_poll, NAPI_POLL_WEIGHT); ret = devm_request_irq(dev, tx_chn->irq, @@ -1932,16 +2006,27 @@ err: return ret; } -static int am65_cpsw_nuss_ndev_reg_2g(struct am65_cpsw_common *common) +static void am65_cpsw_nuss_cleanup_ndev(struct am65_cpsw_common *common) +{ + struct am65_cpsw_port *port; + int i; + + for (i = 0; i < common->port_num; i++) { + port = &common->ports[i]; + if (port->ndev) + unregister_netdev(port->ndev); + } +} + +static int am65_cpsw_nuss_register_ndevs(struct am65_cpsw_common *common) { struct device *dev = common->dev; struct am65_cpsw_port *port; - int ret = 0; + int ret = 0, i; - port = am65_common_get_port(common, 1); - ret = am65_cpsw_nuss_ndev_add_napi_2g(common); + ret = am65_cpsw_nuss_ndev_add_tx_napi(common); if (ret) - goto err; + return ret; ret = devm_request_irq(dev, common->rx_chns.irq, am65_cpsw_nuss_rx_irq, @@ -1949,17 +2034,31 @@ static int am65_cpsw_nuss_ndev_reg_2g(struct am65_cpsw_common *common) if (ret) { dev_err(dev, "failure requesting rx irq %u, %d\n", common->rx_chns.irq, ret); - goto err; + return ret; + } + + for (i = 0; i < common->port_num; i++) { + port = &common->ports[i]; + + if (!port->ndev) + continue; + + ret = register_netdev(port->ndev); + if (ret) { + dev_err(dev, "error registering slave net device%i %d\n", + i, ret); + goto err_cleanup_ndev; + } } - ret = register_netdev(port->ndev); - if (ret) - dev_err(dev, "error registering slave net device %d\n", ret); /* can't auto unregister ndev using devm_add_action() due to * devres release sequence in DD core for DMA */ -err: + return 0; + +err_cleanup_ndev: + am65_cpsw_nuss_cleanup_ndev(common); return ret; } @@ -1972,19 +2071,7 @@ int am65_cpsw_nuss_update_tx_chns(struct am65_cpsw_common *common, int num_tx) if (ret) return ret; - return am65_cpsw_nuss_ndev_add_napi_2g(common); -} - -static void am65_cpsw_nuss_cleanup_ndev(struct am65_cpsw_common *common) -{ - struct am65_cpsw_port *port; - int i; - - for (i = 0; i < common->port_num; i++) { - port = &common->ports[i]; - if (port->ndev) - unregister_netdev(port->ndev); - } + return am65_cpsw_nuss_ndev_add_tx_napi(common); } struct am65_cpsw_soc_pdata { @@ -2005,10 +2092,14 @@ static const struct soc_device_attribute am65_cpsw_socinfo[] = { static const struct am65_cpsw_pdata am65x_sr1_0 = { .quirks = AM65_CPSW_QUIRK_I2027_NO_TX_CSUM, + .ale_dev_id = "am65x-cpsw2g", + .fdqring_mode = K3_RINGACC_RING_MODE_MESSAGE, }; static const struct am65_cpsw_pdata j721e_pdata = { .quirks = 0, + .ale_dev_id = "am65x-cpsw2g", + .fdqring_mode = K3_RINGACC_RING_MODE_MESSAGE, }; static const struct of_device_id am65_cpsw_nuss_of_mtable[] = { @@ -2068,9 +2159,6 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev) return -ENOENT; of_node_put(node); - if (common->port_num != 1) - return -EOPNOTSUPP; - common->rx_flow_id_base = -1; init_completion(&common->tdown_complete); common->tx_ch_num = 1; @@ -2089,13 +2177,8 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev) return -ENOMEM; clk = devm_clk_get(dev, "fck"); - if (IS_ERR(clk)) { - ret = PTR_ERR(clk); - - if (ret != -EPROBE_DEFER) - dev_err(dev, "error getting fck clock %d\n", ret); - return ret; - } + if (IS_ERR(clk)) + return dev_err_probe(dev, PTR_ERR(clk), "getting fck clock\n"); common->bus_freq = clk_get_rate(clk); pm_runtime_enable(dev); @@ -2145,7 +2228,7 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev) ale_params.ale_ageout = AM65_CPSW_ALE_AGEOUT_DEFAULT; ale_params.ale_ports = common->port_num + 1; ale_params.ale_regs = common->cpsw_base + AM65_CPSW_NU_ALE_BASE; - ale_params.dev_id = "am65x-cpsw2g"; + ale_params.dev_id = common->pdata.ale_dev_id; ale_params.bus_freq = common->bus_freq; common->ale = cpsw_ale_create(&ale_params); @@ -2165,11 +2248,11 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev) dev_set_drvdata(dev, common); - ret = am65_cpsw_nuss_init_ndev_2g(common); + ret = am65_cpsw_nuss_init_ndevs(common); if (ret) goto err_of_clear; - ret = am65_cpsw_nuss_ndev_reg_2g(common); + ret = am65_cpsw_nuss_register_ndevs(common); if (ret) goto err_of_clear; diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.h b/drivers/net/ethernet/ti/am65-cpsw-nuss.h index 993e1d4d3222..02aed4c0ceba 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.h +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.h @@ -11,6 +11,7 @@ #include <linux/netdevice.h> #include <linux/phy.h> #include <linux/platform_device.h> +#include <linux/soc/ti/k3-ringacc.h> #include "am65-cpsw-qos.h" struct am65_cpts; @@ -59,6 +60,7 @@ struct am65_cpsw_tx_chn { struct am65_cpsw_common *common; struct k3_cppi_desc_pool *desc_pool; struct k3_udma_glue_tx_channel *tx_chn; + spinlock_t lock; /* protect TX rings in multi-port mode */ int irq; u32 id; u32 descs_num; @@ -77,6 +79,8 @@ struct am65_cpsw_rx_chn { struct am65_cpsw_pdata { u32 quirks; + enum k3_ring_mode fdqring_mode; + const char *ale_dev_id; }; struct am65_cpsw_common { @@ -91,6 +95,7 @@ struct am65_cpsw_common { struct am65_cpsw_host host; struct am65_cpsw_port *ports; u32 disabled_ports_mask; + struct net_device *dma_ndev; int usage_count; /* number of opened ports */ struct cpsw_ale *ale; diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c index a6a455c32628..cdc308a2aa3e 100644 --- a/drivers/net/ethernet/ti/cpsw_ale.c +++ b/drivers/net/ethernet/ti/cpsw_ale.c @@ -634,8 +634,8 @@ int cpsw_ale_add_vlan(struct cpsw_ale *ale, u16 vid, int port_mask, int untag, return 0; } -static void cpsw_ale_del_vlan_modify(struct cpsw_ale *ale, u32 *ale_entry, - u16 vid, int port_mask) +static void cpsw_ale_vlan_del_modify_int(struct cpsw_ale *ale, u32 *ale_entry, + u16 vid, int port_mask) { int reg_mcast, unreg_mcast; int members, untag; @@ -644,6 +644,7 @@ static void cpsw_ale_del_vlan_modify(struct cpsw_ale *ale, u32 *ale_entry, ALE_ENT_VID_MEMBER_LIST); members &= ~port_mask; if (!members) { + cpsw_ale_set_vlan_untag(ale, ale_entry, vid, 0); cpsw_ale_set_entry_type(ale_entry, ALE_TYPE_FREE); return; } @@ -673,7 +674,7 @@ static void cpsw_ale_del_vlan_modify(struct cpsw_ale *ale, u32 *ale_entry, ALE_ENT_VID_MEMBER_LIST, members); } -int cpsw_ale_del_vlan(struct cpsw_ale *ale, u16 vid, int port_mask) +int cpsw_ale_vlan_del_modify(struct cpsw_ale *ale, u16 vid, int port_mask) { u32 ale_entry[ALE_ENTRY_WORDS] = {0, 0, 0}; int idx; @@ -684,11 +685,39 @@ int cpsw_ale_del_vlan(struct cpsw_ale *ale, u16 vid, int port_mask) cpsw_ale_read(ale, idx, ale_entry); - if (port_mask) { - cpsw_ale_del_vlan_modify(ale, ale_entry, vid, port_mask); - } else { + cpsw_ale_vlan_del_modify_int(ale, ale_entry, vid, port_mask); + cpsw_ale_write(ale, idx, ale_entry); + + return 0; +} + +int cpsw_ale_del_vlan(struct cpsw_ale *ale, u16 vid, int port_mask) +{ + u32 ale_entry[ALE_ENTRY_WORDS] = {0, 0, 0}; + int members, idx; + + idx = cpsw_ale_match_vlan(ale, vid); + if (idx < 0) + return -ENOENT; + + cpsw_ale_read(ale, idx, ale_entry); + + /* if !port_mask - force remove VLAN (legacy). + * Check if there are other VLAN members ports + * if no - remove VLAN. + * if yes it means same VLAN was added to >1 port in multi port mode, so + * remove port_mask ports from VLAN ALE entry excluding Host port. + */ + members = cpsw_ale_vlan_get_fld(ale, ale_entry, ALE_ENT_VID_MEMBER_LIST); + members &= ~port_mask; + + if (!port_mask || !members) { + /* last port or force remove - remove VLAN */ cpsw_ale_set_vlan_untag(ale, ale_entry, vid, 0); cpsw_ale_set_entry_type(ale_entry, ALE_TYPE_FREE); + } else { + port_mask &= ~ALE_PORT_HOST; + cpsw_ale_vlan_del_modify_int(ale, ale_entry, vid, port_mask); } cpsw_ale_write(ale, idx, ale_entry); diff --git a/drivers/net/ethernet/ti/cpsw_ale.h b/drivers/net/ethernet/ti/cpsw_ale.h index 5e4a69662c5f..13fe47687fde 100644 --- a/drivers/net/ethernet/ti/cpsw_ale.h +++ b/drivers/net/ethernet/ti/cpsw_ale.h @@ -134,6 +134,7 @@ static inline int cpsw_ale_get_vlan_p0_untag(struct cpsw_ale *ale, u16 vid) int cpsw_ale_vlan_add_modify(struct cpsw_ale *ale, u16 vid, int port_mask, int untag_mask, int reg_mcast, int unreg_mcast); +int cpsw_ale_vlan_del_modify(struct cpsw_ale *ale, u16 vid, int port_mask); void cpsw_ale_set_unreg_mcast(struct cpsw_ale *ale, int unreg_mcast_mask, bool add); diff --git a/drivers/net/ethernet/ti/cpsw_switchdev.c b/drivers/net/ethernet/ti/cpsw_switchdev.c index 985a929bb957..29747da5c514 100644 --- a/drivers/net/ethernet/ti/cpsw_switchdev.c +++ b/drivers/net/ethernet/ti/cpsw_switchdev.c @@ -227,7 +227,7 @@ static int cpsw_port_vlan_del(struct cpsw_priv *priv, u16 vid, else port_mask = BIT(priv->emac_port); - ret = cpsw_ale_del_vlan(cpsw->ale, vid, port_mask); + ret = cpsw_ale_vlan_del_modify(cpsw->ale, vid, port_mask); if (ret != 0) return ret; diff --git a/drivers/net/ethernet/ti/tlan.c b/drivers/net/ethernet/ti/tlan.c index 267c080ee084..0b2ce4bdc2c3 100644 --- a/drivers/net/ethernet/ti/tlan.c +++ b/drivers/net/ethernet/ti/tlan.c @@ -186,6 +186,7 @@ static void tlan_reset_adapter(struct net_device *); static void tlan_finish_reset(struct net_device *); static void tlan_set_mac(struct net_device *, int areg, char *mac); +static void __tlan_phy_print(struct net_device *); static void tlan_phy_print(struct net_device *); static void tlan_phy_detect(struct net_device *); static void tlan_phy_power_down(struct net_device *); @@ -201,9 +202,11 @@ static void tlan_phy_finish_auto_neg(struct net_device *); static int tlan_phy_dp83840a_check(struct net_device *); */ -static bool tlan_mii_read_reg(struct net_device *, u16, u16, u16 *); +static bool __tlan_mii_read_reg(struct net_device *, u16, u16, u16 *); +static void tlan_mii_read_reg(struct net_device *, u16, u16, u16 *); static void tlan_mii_send_data(u16, u32, unsigned); static void tlan_mii_sync(u16); +static void __tlan_mii_write_reg(struct net_device *, u16, u16, u16); static void tlan_mii_write_reg(struct net_device *, u16, u16, u16); static void tlan_ee_send_start(u16); @@ -242,23 +245,20 @@ static u32 tlan_handle_rx_eoc }; -static inline void +static void tlan_set_timer(struct net_device *dev, u32 ticks, u32 type) { struct tlan_priv *priv = netdev_priv(dev); unsigned long flags = 0; - if (!in_irq()) - spin_lock_irqsave(&priv->lock, flags); + spin_lock_irqsave(&priv->lock, flags); if (priv->timer.function != NULL && priv->timer_type != TLAN_TIMER_ACTIVITY) { - if (!in_irq()) - spin_unlock_irqrestore(&priv->lock, flags); + spin_unlock_irqrestore(&priv->lock, flags); return; } priv->timer.function = tlan_timer; - if (!in_irq()) - spin_unlock_irqrestore(&priv->lock, flags); + spin_unlock_irqrestore(&priv->lock, flags); priv->timer_set_at = jiffies; priv->timer_type = type; @@ -1703,22 +1703,22 @@ static u32 tlan_handle_status_check(struct net_device *dev, u16 host_int) dev->name, (unsigned) net_sts); } if ((net_sts & TLAN_NET_STS_MIRQ) && (priv->phy_num == 0)) { - tlan_mii_read_reg(dev, phy, TLAN_TLPHY_STS, &tlphy_sts); - tlan_mii_read_reg(dev, phy, TLAN_TLPHY_CTL, &tlphy_ctl); + __tlan_mii_read_reg(dev, phy, TLAN_TLPHY_STS, &tlphy_sts); + __tlan_mii_read_reg(dev, phy, TLAN_TLPHY_CTL, &tlphy_ctl); if (!(tlphy_sts & TLAN_TS_POLOK) && !(tlphy_ctl & TLAN_TC_SWAPOL)) { tlphy_ctl |= TLAN_TC_SWAPOL; - tlan_mii_write_reg(dev, phy, TLAN_TLPHY_CTL, - tlphy_ctl); + __tlan_mii_write_reg(dev, phy, TLAN_TLPHY_CTL, + tlphy_ctl); } else if ((tlphy_sts & TLAN_TS_POLOK) && (tlphy_ctl & TLAN_TC_SWAPOL)) { tlphy_ctl &= ~TLAN_TC_SWAPOL; - tlan_mii_write_reg(dev, phy, TLAN_TLPHY_CTL, - tlphy_ctl); + __tlan_mii_write_reg(dev, phy, TLAN_TLPHY_CTL, + tlphy_ctl); } if (debug) - tlan_phy_print(dev); + __tlan_phy_print(dev); } } @@ -2379,7 +2379,7 @@ ThunderLAN driver PHY layer routines /********************************************************************* - * tlan_phy_print + * __tlan_phy_print * * Returns: * Nothing @@ -2391,11 +2391,13 @@ ThunderLAN driver PHY layer routines * ********************************************************************/ -static void tlan_phy_print(struct net_device *dev) +static void __tlan_phy_print(struct net_device *dev) { struct tlan_priv *priv = netdev_priv(dev); u16 i, data0, data1, data2, data3, phy; + lockdep_assert_held(&priv->lock); + phy = priv->phy[priv->phy_num]; if (priv->adapter->flags & TLAN_ADAPTER_UNMANAGED_PHY) { @@ -2404,10 +2406,10 @@ static void tlan_phy_print(struct net_device *dev) netdev_info(dev, "PHY 0x%02x\n", phy); pr_info(" Off. +0 +1 +2 +3\n"); for (i = 0; i < 0x20; i += 4) { - tlan_mii_read_reg(dev, phy, i, &data0); - tlan_mii_read_reg(dev, phy, i + 1, &data1); - tlan_mii_read_reg(dev, phy, i + 2, &data2); - tlan_mii_read_reg(dev, phy, i + 3, &data3); + __tlan_mii_read_reg(dev, phy, i, &data0); + __tlan_mii_read_reg(dev, phy, i + 1, &data1); + __tlan_mii_read_reg(dev, phy, i + 2, &data2); + __tlan_mii_read_reg(dev, phy, i + 3, &data3); pr_info(" 0x%02x 0x%04hx 0x%04hx 0x%04hx 0x%04hx\n", i, data0, data1, data2, data3); } @@ -2417,7 +2419,15 @@ static void tlan_phy_print(struct net_device *dev) } +static void tlan_phy_print(struct net_device *dev) +{ + struct tlan_priv *priv = netdev_priv(dev); + unsigned long flags; + spin_lock_irqsave(&priv->lock, flags); + __tlan_phy_print(dev); + spin_unlock_irqrestore(&priv->lock, flags); +} /********************************************************************* @@ -2795,7 +2805,7 @@ these routines are based on the information in chap. 2 of the /*************************************************************** - * tlan_mii_read_reg + * __tlan_mii_read_reg * * Returns: * false if ack received ok @@ -2819,7 +2829,7 @@ these routines are based on the information in chap. 2 of the **************************************************************/ static bool -tlan_mii_read_reg(struct net_device *dev, u16 phy, u16 reg, u16 *val) +__tlan_mii_read_reg(struct net_device *dev, u16 phy, u16 reg, u16 *val) { u8 nack; u16 sio, tmp; @@ -2827,15 +2837,13 @@ tlan_mii_read_reg(struct net_device *dev, u16 phy, u16 reg, u16 *val) bool err; int minten; struct tlan_priv *priv = netdev_priv(dev); - unsigned long flags = 0; + + lockdep_assert_held(&priv->lock); err = false; outw(TLAN_NET_SIO, dev->base_addr + TLAN_DIO_ADR); sio = dev->base_addr + TLAN_DIO_DATA + TLAN_NET_SIO; - if (!in_irq()) - spin_lock_irqsave(&priv->lock, flags); - tlan_mii_sync(dev->base_addr); minten = tlan_get_bit(TLAN_NET_SIO_MINTEN, sio); @@ -2881,15 +2889,19 @@ tlan_mii_read_reg(struct net_device *dev, u16 phy, u16 reg, u16 *val) *val = tmp; - if (!in_irq()) - spin_unlock_irqrestore(&priv->lock, flags); - return err; - } +static void tlan_mii_read_reg(struct net_device *dev, u16 phy, u16 reg, + u16 *val) +{ + struct tlan_priv *priv = netdev_priv(dev); + unsigned long flags; - + spin_lock_irqsave(&priv->lock, flags); + __tlan_mii_read_reg(dev, phy, reg, val); + spin_unlock_irqrestore(&priv->lock, flags); +} /*************************************************************** * tlan_mii_send_data @@ -2971,7 +2983,7 @@ static void tlan_mii_sync(u16 base_port) /*************************************************************** - * tlan_mii_write_reg + * __tlan_mii_write_reg * * Returns: * Nothing @@ -2991,19 +3003,17 @@ static void tlan_mii_sync(u16 base_port) **************************************************************/ static void -tlan_mii_write_reg(struct net_device *dev, u16 phy, u16 reg, u16 val) +__tlan_mii_write_reg(struct net_device *dev, u16 phy, u16 reg, u16 val) { u16 sio; int minten; - unsigned long flags = 0; struct tlan_priv *priv = netdev_priv(dev); + lockdep_assert_held(&priv->lock); + outw(TLAN_NET_SIO, dev->base_addr + TLAN_DIO_ADR); sio = dev->base_addr + TLAN_DIO_DATA + TLAN_NET_SIO; - if (!in_irq()) - spin_lock_irqsave(&priv->lock, flags); - tlan_mii_sync(dev->base_addr); minten = tlan_get_bit(TLAN_NET_SIO_MINTEN, sio); @@ -3024,12 +3034,18 @@ tlan_mii_write_reg(struct net_device *dev, u16 phy, u16 reg, u16 val) if (minten) tlan_set_bit(TLAN_NET_SIO_MINTEN, sio); - if (!in_irq()) - spin_unlock_irqrestore(&priv->lock, flags); - } +static void +tlan_mii_write_reg(struct net_device *dev, u16 phy, u16 reg, u16 val) +{ + struct tlan_priv *priv = netdev_priv(dev); + unsigned long flags; + spin_lock_irqsave(&priv->lock, flags); + __tlan_mii_write_reg(dev, phy, reg, val); + spin_unlock_irqrestore(&priv->lock, flags); +} /***************************************************************************** diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h index f34c7903ff52..7326ad4d5e1c 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet.h +++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h @@ -419,6 +419,9 @@ struct axienet_local { struct phylink *phylink; struct phylink_config phylink_config; + /* Reference to PCS/PMA PHY if used */ + struct mdio_device *pcs_phy; + /* Clock for AXI bus */ struct clk *clk; diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 9aafd3ecdaa4..529c167cd5a6 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -1517,10 +1517,27 @@ static void axienet_validate(struct phylink_config *config, phylink_set(mask, Asym_Pause); phylink_set(mask, Pause); - phylink_set(mask, 1000baseX_Full); - phylink_set(mask, 10baseT_Full); - phylink_set(mask, 100baseT_Full); - phylink_set(mask, 1000baseT_Full); + + switch (state->interface) { + case PHY_INTERFACE_MODE_NA: + case PHY_INTERFACE_MODE_1000BASEX: + case PHY_INTERFACE_MODE_SGMII: + case PHY_INTERFACE_MODE_GMII: + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_TXID: + phylink_set(mask, 1000baseX_Full); + phylink_set(mask, 1000baseT_Full); + if (state->interface == PHY_INTERFACE_MODE_1000BASEX) + break; + fallthrough; + case PHY_INTERFACE_MODE_MII: + phylink_set(mask, 100baseT_Full); + phylink_set(mask, 10baseT_Full); + default: + break; + } bitmap_and(supported, supported, mask, __ETHTOOL_LINK_MODE_MASK_NBITS); @@ -1533,38 +1550,46 @@ static void axienet_mac_pcs_get_state(struct phylink_config *config, { struct net_device *ndev = to_net_dev(config->dev); struct axienet_local *lp = netdev_priv(ndev); - u32 emmc_reg, fcc_reg; - - state->interface = lp->phy_mode; - - emmc_reg = axienet_ior(lp, XAE_EMMC_OFFSET); - if (emmc_reg & XAE_EMMC_LINKSPD_1000) - state->speed = SPEED_1000; - else if (emmc_reg & XAE_EMMC_LINKSPD_100) - state->speed = SPEED_100; - else - state->speed = SPEED_10; - - state->pause = 0; - fcc_reg = axienet_ior(lp, XAE_FCC_OFFSET); - if (fcc_reg & XAE_FCC_FCTX_MASK) - state->pause |= MLO_PAUSE_TX; - if (fcc_reg & XAE_FCC_FCRX_MASK) - state->pause |= MLO_PAUSE_RX; - state->an_complete = 0; - state->duplex = 1; + switch (state->interface) { + case PHY_INTERFACE_MODE_SGMII: + case PHY_INTERFACE_MODE_1000BASEX: + phylink_mii_c22_pcs_get_state(lp->pcs_phy, state); + break; + default: + break; + } } static void axienet_mac_an_restart(struct phylink_config *config) { - /* Unsupported, do nothing */ + struct net_device *ndev = to_net_dev(config->dev); + struct axienet_local *lp = netdev_priv(ndev); + + phylink_mii_c22_pcs_an_restart(lp->pcs_phy); } static void axienet_mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state) { - /* nothing meaningful to do */ + struct net_device *ndev = to_net_dev(config->dev); + struct axienet_local *lp = netdev_priv(ndev); + int ret; + + switch (state->interface) { + case PHY_INTERFACE_MODE_SGMII: + case PHY_INTERFACE_MODE_1000BASEX: + ret = phylink_mii_c22_pcs_config(lp->pcs_phy, mode, + state->interface, + state->advertising); + if (ret < 0) + netdev_warn(ndev, "Failed to configure PCS: %d\n", + ret); + break; + + default: + break; + } } static void axienet_mac_link_down(struct phylink_config *config, @@ -1999,6 +2024,20 @@ static int axienet_probe(struct platform_device *pdev) dev_warn(&pdev->dev, "error registering MDIO bus: %d\n", ret); } + if (lp->phy_mode == PHY_INTERFACE_MODE_SGMII || + lp->phy_mode == PHY_INTERFACE_MODE_1000BASEX) { + if (!lp->phy_node) { + dev_err(&pdev->dev, "phy-handle required for 1000BaseX/SGMII\n"); + ret = -EINVAL; + goto free_netdev; + } + lp->pcs_phy = of_mdio_find_device(lp->phy_node); + if (!lp->pcs_phy) { + ret = -EPROBE_DEFER; + goto free_netdev; + } + lp->phylink_config.pcs_poll = true; + } lp->phylink_config.dev = &ndev->dev; lp->phylink_config.type = PHYLINK_NETDEV; @@ -2036,6 +2075,9 @@ static int axienet_remove(struct platform_device *pdev) if (lp->phylink) phylink_destroy(lp->phylink); + if (lp->pcs_phy) + put_device(&lp->pcs_phy->dev); + axienet_mdio_teardown(lp); clk_disable_unprepare(lp->clk); diff --git a/drivers/net/fddi/skfp/drvfbi.c b/drivers/net/fddi/skfp/drvfbi.c index cc9ac572423e..e9b9614639cd 100644 --- a/drivers/net/fddi/skfp/drvfbi.c +++ b/drivers/net/fddi/skfp/drvfbi.c @@ -22,10 +22,6 @@ #include <linux/bitrev.h> #include <linux/pci.h> -#ifndef lint -static const char ID_sccs[] = "@(#)drvfbi.c 1.63 99/02/11 (C) SK " ; -#endif - /* * PCM active state */ diff --git a/drivers/net/fddi/skfp/ecm.c b/drivers/net/fddi/skfp/ecm.c index 15c503f43727..2f5f5f26bb43 100644 --- a/drivers/net/fddi/skfp/ecm.c +++ b/drivers/net/fddi/skfp/ecm.c @@ -40,10 +40,6 @@ #define KERNEL #include "h/smtstate.h" -#ifndef lint -static const char ID_sccs[] = "@(#)ecm.c 2.7 99/08/05 (C) SK " ; -#endif - /* * FSM Macros */ @@ -147,10 +143,11 @@ static void ecm_fsm(struct s_smc *smc, int cmd) /* For AIX event notification: */ /* Is a disconnect command remotely issued ? */ if (cmd == EC_DISCONNECT && - smc->mib.fddiSMTRemoteDisconnectFlag == TRUE) + smc->mib.fddiSMTRemoteDisconnectFlag == TRUE) { AIX_EVENT (smc, (u_long) CIO_HARD_FAIL, (u_long) FDDI_REMOTE_DISCONNECT, smt_get_event_word(smc), smt_get_error_word(smc) ); + } /*jd 05-Aug-1999 Bug #10419 "Port Disconnect fails at Dup MAc Cond."*/ if (cmd == EC_CONNECT) { diff --git a/drivers/net/fddi/skfp/ess.c b/drivers/net/fddi/skfp/ess.c index afd5ca39f43b..35110c0c00a0 100644 --- a/drivers/net/fddi/skfp/ess.c +++ b/drivers/net/fddi/skfp/ess.c @@ -40,7 +40,6 @@ #ifdef ESS #ifndef lint -static const char ID_sccs[] = "@(#)ess.c 1.10 96/02/23 (C) SK" ; #define LINT_USE(x) #else #define LINT_USE(x) (x)=(x) diff --git a/drivers/net/fddi/skfp/hwt.c b/drivers/net/fddi/skfp/hwt.c index 32804ed049cd..5577b8e14b73 100644 --- a/drivers/net/fddi/skfp/hwt.c +++ b/drivers/net/fddi/skfp/hwt.c @@ -27,10 +27,6 @@ #include "h/fddi.h" #include "h/smc.h" -#ifndef lint -static const char ID_sccs[] = "@(#)hwt.c 1.13 97/04/23 (C) SK " ; -#endif - /* * Prototypes of local functions. */ diff --git a/drivers/net/fddi/skfp/pcmplc.c b/drivers/net/fddi/skfp/pcmplc.c index 554cde8d6073..90e8df6d9a88 100644 --- a/drivers/net/fddi/skfp/pcmplc.c +++ b/drivers/net/fddi/skfp/pcmplc.c @@ -45,10 +45,6 @@ #define KERNEL #include "h/smtstate.h" -#ifndef lint -static const char ID_sccs[] = "@(#)pcmplc.c 2.55 99/08/05 (C) SK " ; -#endif - #ifdef FDDI_MIB extern int snmp_fddi_trap( #ifdef ANSIC diff --git a/drivers/net/fddi/skfp/pmf.c b/drivers/net/fddi/skfp/pmf.c index 14f10b4cab0f..563fb7f0b327 100644 --- a/drivers/net/fddi/skfp/pmf.c +++ b/drivers/net/fddi/skfp/pmf.c @@ -24,10 +24,6 @@ #ifndef SLIM_SMT -#ifndef lint -static const char ID_sccs[] = "@(#)pmf.c 1.37 97/08/04 (C) SK " ; -#endif - static int smt_authorize(struct s_smc *smc, struct smt_header *sm); static int smt_check_set_count(struct s_smc *smc, struct smt_header *sm); static const struct s_p_tab* smt_get_ptab(u_short para); diff --git a/drivers/net/fddi/skfp/queue.c b/drivers/net/fddi/skfp/queue.c index ba022f723bd7..abe155ad777f 100644 --- a/drivers/net/fddi/skfp/queue.c +++ b/drivers/net/fddi/skfp/queue.c @@ -18,10 +18,6 @@ #include "h/fddi.h" #include "h/smc.h" -#ifndef lint -static const char ID_sccs[] = "@(#)queue.c 2.9 97/08/04 (C) SK " ; -#endif - #define PRINTF(a,b,c) /* diff --git a/drivers/net/fddi/skfp/rmt.c b/drivers/net/fddi/skfp/rmt.c index c0e62c25332c..37a89675dbeb 100644 --- a/drivers/net/fddi/skfp/rmt.c +++ b/drivers/net/fddi/skfp/rmt.c @@ -45,10 +45,6 @@ #define KERNEL #include "h/smtstate.h" -#ifndef lint -static const char ID_sccs[] = "@(#)rmt.c 2.13 99/07/02 (C) SK " ; -#endif - /* * FSM Macros */ diff --git a/drivers/net/fddi/skfp/smtdef.c b/drivers/net/fddi/skfp/smtdef.c index 0bebde3c6cb9..99cc9a549bd7 100644 --- a/drivers/net/fddi/skfp/smtdef.c +++ b/drivers/net/fddi/skfp/smtdef.c @@ -22,10 +22,6 @@ #define OEM_USER_DATA "SK-NET FDDI V2.0 Userdata" #endif -#ifndef lint -static const char ID_sccs[] = "@(#)smtdef.c 2.53 99/08/11 (C) SK " ; -#endif - /* * defaults */ diff --git a/drivers/net/fddi/skfp/smtinit.c b/drivers/net/fddi/skfp/smtinit.c index 01f6c75cbea8..c9898c83fe30 100644 --- a/drivers/net/fddi/skfp/smtinit.c +++ b/drivers/net/fddi/skfp/smtinit.c @@ -19,10 +19,6 @@ #include "h/fddi.h" #include "h/smc.h" -#ifndef lint -static const char ID_sccs[] = "@(#)smtinit.c 1.15 97/05/06 (C) SK " ; -#endif - void init_fddi_driver(struct s_smc *smc, u_char *mac_addr); /* define global debug variable */ diff --git a/drivers/net/fddi/skfp/smttimer.c b/drivers/net/fddi/skfp/smttimer.c index 9d549bb14f07..5f3e5d7bf415 100644 --- a/drivers/net/fddi/skfp/smttimer.c +++ b/drivers/net/fddi/skfp/smttimer.c @@ -18,10 +18,6 @@ #include "h/fddi.h" #include "h/smc.h" -#ifndef lint -static const char ID_sccs[] = "@(#)smttimer.c 2.4 97/08/04 (C) SK " ; -#endif - static void timer_done(struct s_smc *smc, int restart); void smt_timer_init(struct s_smc *smc) diff --git a/drivers/net/fddi/skfp/srf.c b/drivers/net/fddi/skfp/srf.c index f98d060b0f5b..4cad68c3f49b 100644 --- a/drivers/net/fddi/skfp/srf.c +++ b/drivers/net/fddi/skfp/srf.c @@ -26,11 +26,6 @@ #ifndef SLIM_SMT #ifndef BOOT -#ifndef lint -static const char ID_sccs[] = "@(#)srf.c 1.18 97/08/04 (C) SK " ; -#endif - - /* * function declarations */ diff --git a/drivers/net/hamradio/hdlcdrv.c b/drivers/net/hamradio/hdlcdrv.c index e7413a643929..9e0058154ac3 100644 --- a/drivers/net/hamradio/hdlcdrv.c +++ b/drivers/net/hamradio/hdlcdrv.c @@ -597,7 +597,7 @@ static int hdlcdrv_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) case HDLCDRVCTL_DRIVERNAME: if (s->ops && s->ops->drvname) { - strncpy(bi.data.drivername, s->ops->drvname, + strlcpy(bi.data.drivername, s->ops->drvname, sizeof(bi.data.drivername)); break; } diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c index 4eb64709d44c..3a2824f24caa 100644 --- a/drivers/net/ieee802154/ca8210.c +++ b/drivers/net/ieee802154/ca8210.c @@ -316,6 +316,7 @@ struct cas_control { * struct ca8210_test - ca8210 test interface structure * @ca8210_dfs_spi_int: pointer to the entry in the debug fs for this device * @up_fifo: fifo for upstream messages + * @readq: read wait queue * * This structure stores all the data pertaining to the debug interface */ @@ -346,12 +347,12 @@ struct ca8210_test { * @ca8210_is_awake: nonzero if ca8210 is initialised, ready for comms * @sync_down: counts number of downstream synchronous commands * @sync_up: counts number of upstream synchronous commands - * @spi_transfer_complete completion object for a single spi_transfer - * @sync_exchange_complete completion object for a complete synchronous API - * exchange - * @promiscuous whether the ca8210 is in promiscuous mode or not + * @spi_transfer_complete: completion object for a single spi_transfer + * @sync_exchange_complete: completion object for a complete synchronous API + * exchange + * @promiscuous: whether the ca8210 is in promiscuous mode or not * @retries: records how many times the current pending spi - * transfer has been retried + * transfer has been retried */ struct ca8210_priv { struct spi_device *spi; @@ -420,8 +421,8 @@ struct fulladdr { /** * union macaddr: generic MAC address container - * @short_addr: 16-bit short address - * @ieee_address: 64-bit extended address as LE byte array + * @short_address: 16-bit short address + * @ieee_address: 64-bit extended address as LE byte array * */ union macaddr { @@ -714,7 +715,7 @@ static void ca8210_mlme_reset_worker(struct work_struct *work) /** * ca8210_rx_done() - Calls various message dispatches responding to a received * command - * @arg: Pointer to the cas_control object for the relevant spi transfer + * @cas_ctl: Pointer to the cas_control object for the relevant spi transfer * * Presents a received SAP command from the ca8210 to the Cascoda EVBME, test * interface and network driver. @@ -1277,7 +1278,6 @@ static u8 tdme_channelinit(u8 channel, void *device_ref) * @pib_attribute: Attribute Number * @pib_attribute_length: Attribute length * @pib_attribute_value: Pointer to Attribute Value - * @device_ref: Nondescript pointer to target device * * Return: 802.15.4 status code of checks */ @@ -3046,7 +3046,7 @@ static void ca8210_test_interface_clear(struct ca8210_priv *priv) /** * ca8210_remove() - Shut down a ca8210 upon being disconnected - * @priv: Pointer to private data structure + * @spi_device: Pointer to spi device data structure * * Return: 0 or linux error code */ @@ -3096,7 +3096,7 @@ static int ca8210_remove(struct spi_device *spi_device) /** * ca8210_probe() - Set up a connected ca8210 upon being detected by the system - * @priv: Pointer to private data structure + * @spi_device: Pointer to spi device data structure * * Return: 0 or linux error code */ diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c index 7fe306e76281..fa63d4dee0ba 100644 --- a/drivers/net/ifb.c +++ b/drivers/net/ifb.c @@ -187,8 +187,7 @@ static const struct net_device_ops ifb_netdev_ops = { }; #define IFB_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | NETIF_F_FRAGLIST | \ - NETIF_F_TSO_ECN | NETIF_F_TSO | NETIF_F_TSO6 | \ - NETIF_F_GSO_ENCAP_ALL | \ + NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL | \ NETIF_F_HIGHDMA | NETIF_F_HW_VLAN_CTAG_TX | \ NETIF_F_HW_VLAN_STAG_TX) diff --git a/drivers/net/ipa/gsi.c b/drivers/net/ipa/gsi.c index 6bfac1efe037..12a2001ee1e9 100644 --- a/drivers/net/ipa/gsi.c +++ b/drivers/net/ipa/gsi.c @@ -21,6 +21,7 @@ #include "gsi_trans.h" #include "ipa_gsi.h" #include "ipa_data.h" +#include "ipa_version.h" /** * DOC: The IPA Generic Software Interface @@ -742,11 +743,12 @@ static void gsi_channel_program(struct gsi_channel *channel, bool doorbell) /* Max prefetch is 1 segment (do not set MAX_PREFETCH_FMASK) */ - /* Enable the doorbell engine if requested */ - if (doorbell) + /* We enable the doorbell engine for IPA v3.5.1 */ + if (gsi->version == IPA_VERSION_3_5_1 && doorbell) val |= USE_DB_ENG_FMASK; - if (!channel->use_prefetch) + /* Starting with IPA v4.0 the command channel uses the escape buffer */ + if (gsi->version != IPA_VERSION_3_5_1 && channel->command) val |= USE_ESCAPE_BUF_ONLY_FMASK; iowrite32(val, gsi->virt + GSI_CH_C_QOS_OFFSET(channel_id)); @@ -829,8 +831,8 @@ int gsi_channel_stop(struct gsi *gsi, u32 channel_id) return ret; } -/* Reset and reconfigure a channel (possibly leaving doorbell disabled) */ -void gsi_channel_reset(struct gsi *gsi, u32 channel_id, bool legacy) +/* Reset and reconfigure a channel, (possibly) enabling the doorbell engine */ +void gsi_channel_reset(struct gsi *gsi, u32 channel_id, bool doorbell) { struct gsi_channel *channel = &gsi->channel[channel_id]; @@ -838,10 +840,10 @@ void gsi_channel_reset(struct gsi *gsi, u32 channel_id, bool legacy) gsi_channel_reset_command(channel); /* Due to a hardware quirk we may need to reset RX channels twice. */ - if (legacy && !channel->toward_ipa) + if (gsi->version == IPA_VERSION_3_5_1 && !channel->toward_ipa) gsi_channel_reset_command(channel); - gsi_channel_program(channel, legacy); + gsi_channel_program(channel, doorbell); gsi_channel_trans_cancel_pending(channel); mutex_unlock(&gsi->mutex); @@ -1452,8 +1454,7 @@ static void gsi_evt_ring_teardown(struct gsi *gsi) } /* Setup function for a single channel */ -static int gsi_channel_setup_one(struct gsi *gsi, u32 channel_id, - bool legacy) +static int gsi_channel_setup_one(struct gsi *gsi, u32 channel_id) { struct gsi_channel *channel = &gsi->channel[channel_id]; u32 evt_ring_id = channel->evt_ring_id; @@ -1472,7 +1473,7 @@ static int gsi_channel_setup_one(struct gsi *gsi, u32 channel_id, if (ret) goto err_evt_ring_de_alloc; - gsi_channel_program(channel, legacy); + gsi_channel_program(channel, true); if (channel->toward_ipa) netif_tx_napi_add(&gsi->dummy_dev, &channel->napi, @@ -1549,7 +1550,7 @@ static void gsi_modem_channel_halt(struct gsi *gsi, u32 channel_id) } /* Setup function for channels */ -static int gsi_channel_setup(struct gsi *gsi, bool legacy) +static int gsi_channel_setup(struct gsi *gsi) { u32 channel_id = 0; u32 mask; @@ -1561,7 +1562,7 @@ static int gsi_channel_setup(struct gsi *gsi, bool legacy) mutex_lock(&gsi->mutex); do { - ret = gsi_channel_setup_one(gsi, channel_id, legacy); + ret = gsi_channel_setup_one(gsi, channel_id); if (ret) goto err_unwind; } while (++channel_id < gsi->channel_count); @@ -1647,7 +1648,7 @@ static void gsi_channel_teardown(struct gsi *gsi) } /* Setup function for GSI. GSI firmware must be loaded and initialized */ -int gsi_setup(struct gsi *gsi, bool legacy) +int gsi_setup(struct gsi *gsi) { struct device *dev = gsi->dev; u32 val; @@ -1691,7 +1692,7 @@ int gsi_setup(struct gsi *gsi, bool legacy) /* Writing 1 indicates IRQ interrupts; 0 would be MSI */ iowrite32(1, gsi->virt + GSI_CNTXT_INTSET_OFFSET); - return gsi_channel_setup(gsi, legacy); + return gsi_channel_setup(gsi); } /* Inverse of gsi_setup() */ @@ -1814,7 +1815,7 @@ static bool gsi_channel_data_valid(struct gsi *gsi, /* Init function for a single channel */ static int gsi_channel_init_one(struct gsi *gsi, const struct ipa_gsi_endpoint_data *data, - bool command, bool prefetch) + bool command) { struct gsi_channel *channel; u32 tre_count; @@ -1838,7 +1839,6 @@ static int gsi_channel_init_one(struct gsi *gsi, channel->gsi = gsi; channel->toward_ipa = data->toward_ipa; channel->command = command; - channel->use_prefetch = command && prefetch; channel->tlv_count = data->channel.tlv_count; channel->tre_count = tre_count; channel->event_count = data->channel.event_count; @@ -1892,13 +1892,16 @@ static void gsi_channel_exit_one(struct gsi_channel *channel) } /* Init function for channels */ -static int gsi_channel_init(struct gsi *gsi, bool prefetch, u32 count, - const struct ipa_gsi_endpoint_data *data, - bool modem_alloc) +static int gsi_channel_init(struct gsi *gsi, u32 count, + const struct ipa_gsi_endpoint_data *data) { + bool modem_alloc; int ret = 0; u32 i; + /* IPA v4.2 requires the AP to allocate channels for the modem */ + modem_alloc = gsi->version == IPA_VERSION_4_2; + gsi_evt_ring_init(gsi); /* The endpoint data array is indexed by endpoint name */ @@ -1916,7 +1919,7 @@ static int gsi_channel_init(struct gsi *gsi, bool prefetch, u32 count, continue; } - ret = gsi_channel_init_one(gsi, &data[i], command, prefetch); + ret = gsi_channel_init_one(gsi, &data[i], command); if (ret) goto err_unwind; } @@ -1952,9 +1955,9 @@ static void gsi_channel_exit(struct gsi *gsi) } /* Init function for GSI. GSI hardware does not need to be "ready" */ -int gsi_init(struct gsi *gsi, struct platform_device *pdev, bool prefetch, - u32 count, const struct ipa_gsi_endpoint_data *data, - bool modem_alloc) +int gsi_init(struct gsi *gsi, struct platform_device *pdev, + enum ipa_version version, u32 count, + const struct ipa_gsi_endpoint_data *data) { struct device *dev = &pdev->dev; struct resource *res; @@ -1965,6 +1968,7 @@ int gsi_init(struct gsi *gsi, struct platform_device *pdev, bool prefetch, gsi_validate_build(); gsi->dev = dev; + gsi->version = version; /* The GSI layer performs NAPI on all endpoints. NAPI requires a * network device structure, but the GSI layer does not have one, @@ -2008,7 +2012,7 @@ int gsi_init(struct gsi *gsi, struct platform_device *pdev, bool prefetch, goto err_free_irq; } - ret = gsi_channel_init(gsi, prefetch, count, data, modem_alloc); + ret = gsi_channel_init(gsi, count, data); if (ret) goto err_iounmap; diff --git a/drivers/net/ipa/gsi.h b/drivers/net/ipa/gsi.h index 3f9f29d531c4..59ace83d404c 100644 --- a/drivers/net/ipa/gsi.h +++ b/drivers/net/ipa/gsi.h @@ -13,6 +13,8 @@ #include <linux/platform_device.h> #include <linux/netdevice.h> +#include "ipa_version.h" + /* Maximum number of channels and event rings supported by the driver */ #define GSI_CHANNEL_COUNT_MAX 17 #define GSI_EVT_RING_COUNT_MAX 13 @@ -107,7 +109,6 @@ struct gsi_channel { struct gsi *gsi; bool toward_ipa; bool command; /* AP command TX channel or not */ - bool use_prefetch; /* use prefetch (else escape buf) */ u8 tlv_count; /* # entries in TLV FIFO */ u16 tre_count; @@ -147,6 +148,7 @@ struct gsi_evt_ring { struct gsi { struct device *dev; /* Same as IPA device */ + enum ipa_version version; struct net_device dummy_dev; /* needed for NAPI */ void __iomem *virt; u32 irq; @@ -164,14 +166,13 @@ struct gsi { /** * gsi_setup() - Set up the GSI subsystem * @gsi: Address of GSI structure embedded in an IPA structure - * @legacy: Set up for legacy hardware * * Return: 0 if successful, or a negative error code * * Performs initialization that must wait until the GSI hardware is * ready (including firmware loaded). */ -int gsi_setup(struct gsi *gsi, bool legacy); +int gsi_setup(struct gsi *gsi); /** * gsi_teardown() - Tear down GSI subsystem @@ -219,15 +220,15 @@ int gsi_channel_stop(struct gsi *gsi, u32 channel_id); * gsi_channel_reset() - Reset an allocated GSI channel * @gsi: GSI pointer * @channel_id: Channel to be reset - * @legacy: Legacy behavior + * @doorbell: Whether to (possibly) enable the doorbell engine * - * Reset a channel and reconfigure it. The @legacy flag indicates - * that some steps should be done differently for legacy hardware. + * Reset a channel and reconfigure it. The @doorbell flag indicates + * that the doorbell engine should be enabled if needed. * * GSI hardware relinquishes ownership of all pending receive buffer * transactions and they will complete with their cancelled flag set. */ -void gsi_channel_reset(struct gsi *gsi, u32 channel_id, bool legacy); +void gsi_channel_reset(struct gsi *gsi, u32 channel_id, bool doorbell); int gsi_channel_suspend(struct gsi *gsi, u32 channel_id, bool stop); int gsi_channel_resume(struct gsi *gsi, u32 channel_id, bool start); @@ -236,15 +237,18 @@ int gsi_channel_resume(struct gsi *gsi, u32 channel_id, bool start); * gsi_init() - Initialize the GSI subsystem * @gsi: Address of GSI structure embedded in an IPA structure * @pdev: IPA platform device + * @version: IPA hardware version (implies GSI version) + * @count: Number of entries in the configuration data array + * @data: Endpoint and channel configuration data * * Return: 0 if successful, or a negative error code * * Early stage initialization of the GSI subsystem, performing tasks * that can be done before the GSI hardware is ready to use. */ -int gsi_init(struct gsi *gsi, struct platform_device *pdev, bool prefetch, - u32 count, const struct ipa_gsi_endpoint_data *data, - bool modem_alloc); +int gsi_init(struct gsi *gsi, struct platform_device *pdev, + enum ipa_version version, u32 count, + const struct ipa_gsi_endpoint_data *data); /** * gsi_exit() - Exit the GSI subsystem diff --git a/drivers/net/ipa/ipa_data-sc7180.c b/drivers/net/ipa/ipa_data-sc7180.c index d4c2bc7ad24b..37dada4da680 100644 --- a/drivers/net/ipa/ipa_data-sc7180.c +++ b/drivers/net/ipa/ipa_data-sc7180.c @@ -24,6 +24,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { .endpoint = { .seq_type = IPA_SEQ_DMA_ONLY, .config = { + .resource_group = 0, .dma_mode = true, .dma_endpoint = IPA_ENDPOINT_AP_LAN_RX, }, @@ -42,6 +43,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { .endpoint = { .seq_type = IPA_SEQ_INVALID, .config = { + .resource_group = 0, .aggregation = true, .status_enable = true, .rx = { @@ -65,6 +67,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { .seq_type = IPA_SEQ_PKT_PROCESS_NO_DEC_NO_UCP_DMAP, .config = { + .resource_group = 0, .checksum = true, .qmap = true, .status_enable = true, @@ -88,6 +91,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { .endpoint = { .seq_type = IPA_SEQ_INVALID, .config = { + .resource_group = 0, .checksum = true, .qmap = true, .aggregation = true, diff --git a/drivers/net/ipa/ipa_data-sdm845.c b/drivers/net/ipa/ipa_data-sdm845.c index de2768d71ab5..a9a992404b39 100644 --- a/drivers/net/ipa/ipa_data-sdm845.c +++ b/drivers/net/ipa/ipa_data-sdm845.c @@ -26,6 +26,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { .endpoint = { .seq_type = IPA_SEQ_DMA_ONLY, .config = { + .resource_group = 1, .dma_mode = true, .dma_endpoint = IPA_ENDPOINT_AP_LAN_RX, }, @@ -44,6 +45,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { .endpoint = { .seq_type = IPA_SEQ_INVALID, .config = { + .resource_group = 1, .aggregation = true, .status_enable = true, .rx = { @@ -67,6 +69,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { .seq_type = IPA_SEQ_2ND_PKT_PROCESS_PASS_NO_DEC_UCP, .config = { + .resource_group = 1, .checksum = true, .qmap = true, .status_enable = true, @@ -90,6 +93,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = { .endpoint = { .seq_type = IPA_SEQ_INVALID, .config = { + .resource_group = 1, .checksum = true, .qmap = true, .aggregation = true, diff --git a/drivers/net/ipa/ipa_data.h b/drivers/net/ipa/ipa_data.h index 7fc1058a5ca9..83c4b78373ef 100644 --- a/drivers/net/ipa/ipa_data.h +++ b/drivers/net/ipa/ipa_data.h @@ -45,10 +45,10 @@ * the IPA endpoint. */ -/* The maximum value returned by ipa_resource_group_count() */ -#define IPA_RESOURCE_GROUP_COUNT 4 +/* The maximum value returned by ipa_resource_group_{src,dst}_count() */ +#define IPA_RESOURCE_GROUP_SRC_MAX 5 +#define IPA_RESOURCE_GROUP_DST_MAX 5 -/** enum ipa_resource_type_src - source resource types */ /** * struct gsi_channel_data - GSI channel configuration data * @tre_count: number of TREs in the channel ring @@ -109,6 +109,7 @@ struct ipa_endpoint_rx_data { /** * struct ipa_endpoint_config_data - IPA endpoint hardware configuration + * @resource_group: resource group to assign endpoint to * @checksum: whether checksum offload is enabled * @qmap: whether endpoint uses QMAP protocol * @aggregation: whether endpoint supports aggregation @@ -119,6 +120,7 @@ struct ipa_endpoint_rx_data { * @rx: RX-specific endpoint information (see above) */ struct ipa_endpoint_config_data { + u32 resource_group; bool checksum; bool qmap; bool aggregation; @@ -206,7 +208,7 @@ struct ipa_resource_limits { */ struct ipa_resource_src { enum ipa_resource_type_src type; - struct ipa_resource_limits limits[IPA_RESOURCE_GROUP_COUNT]; + struct ipa_resource_limits limits[IPA_RESOURCE_GROUP_SRC_MAX]; }; /** @@ -216,7 +218,7 @@ struct ipa_resource_src { */ struct ipa_resource_dst { enum ipa_resource_type_dst type; - struct ipa_resource_limits limits[IPA_RESOURCE_GROUP_COUNT]; + struct ipa_resource_limits limits[IPA_RESOURCE_GROUP_DST_MAX]; }; /** diff --git a/drivers/net/ipa/ipa_endpoint.c b/drivers/net/ipa/ipa_endpoint.c index b40b711cf4bd..548121b1531b 100644 --- a/drivers/net/ipa/ipa_endpoint.c +++ b/drivers/net/ipa/ipa_endpoint.c @@ -751,6 +751,16 @@ static void ipa_endpoint_init_deaggr(struct ipa_endpoint *endpoint) iowrite32(val, endpoint->ipa->reg_virt + offset); } +static void ipa_endpoint_init_rsrc_grp(struct ipa_endpoint *endpoint) +{ + u32 offset = IPA_REG_ENDP_INIT_RSRC_GRP_N_OFFSET(endpoint->endpoint_id); + struct ipa *ipa = endpoint->ipa; + u32 val; + + val = rsrc_grp_encoded(ipa->version, endpoint->data->resource_group); + iowrite32(val, ipa->reg_virt + offset); +} + static void ipa_endpoint_init_seq(struct ipa_endpoint *endpoint) { u32 offset = IPA_REG_ENDP_INIT_SEQ_N_OFFSET(endpoint->endpoint_id); @@ -1207,7 +1217,6 @@ static int ipa_endpoint_reset_rx_aggr(struct ipa_endpoint *endpoint) struct gsi *gsi = &ipa->gsi; bool suspended = false; dma_addr_t addr; - bool legacy; u32 retries; u32 len = 1; void *virt; @@ -1269,8 +1278,7 @@ static int ipa_endpoint_reset_rx_aggr(struct ipa_endpoint *endpoint) * complete the channel reset sequence. Finish by suspending the * channel again (if necessary). */ - legacy = ipa->version == IPA_VERSION_3_5_1; - gsi_channel_reset(gsi, endpoint->channel_id, legacy); + gsi_channel_reset(gsi, endpoint->channel_id, true); msleep(1); @@ -1293,21 +1301,19 @@ static void ipa_endpoint_reset(struct ipa_endpoint *endpoint) u32 channel_id = endpoint->channel_id; struct ipa *ipa = endpoint->ipa; bool special; - bool legacy; int ret = 0; /* On IPA v3.5.1, if an RX endpoint is reset while aggregation * is active, we need to handle things specially to recover. * All other cases just need to reset the underlying GSI channel. - * - * IPA v3.5.1 enables the doorbell engine. Newer versions do not. */ - legacy = ipa->version == IPA_VERSION_3_5_1; - special = !endpoint->toward_ipa && endpoint->data->aggregation; + special = ipa->version == IPA_VERSION_3_5_1 && + !endpoint->toward_ipa && + endpoint->data->aggregation; if (special && ipa_endpoint_aggr_active(endpoint)) ret = ipa_endpoint_reset_rx_aggr(endpoint); else - gsi_channel_reset(&ipa->gsi, channel_id, legacy); + gsi_channel_reset(&ipa->gsi, channel_id, true); if (ret) dev_err(&ipa->pdev->dev, @@ -1328,6 +1334,7 @@ static void ipa_endpoint_program(struct ipa_endpoint *endpoint) ipa_endpoint_init_mode(endpoint); ipa_endpoint_init_aggr(endpoint); ipa_endpoint_init_deaggr(endpoint); + ipa_endpoint_init_rsrc_grp(endpoint); ipa_endpoint_init_seq(endpoint); ipa_endpoint_status(endpoint); } diff --git a/drivers/net/ipa/ipa_main.c b/drivers/net/ipa/ipa_main.c index cd4d993b0bbb..a580cab794b1 100644 --- a/drivers/net/ipa/ipa_main.c +++ b/drivers/net/ipa/ipa_main.c @@ -111,8 +111,7 @@ int ipa_setup(struct ipa *ipa) struct device *dev = &ipa->pdev->dev; int ret; - /* Setup for IPA v3.5.1 has some slight differences */ - ret = gsi_setup(&ipa->gsi, ipa->version == IPA_VERSION_3_5_1); + ret = gsi_setup(&ipa->gsi); if (ret) return ret; @@ -363,52 +362,41 @@ static void ipa_hardware_deconfig(struct ipa *ipa) #ifdef IPA_VALIDATION -/* # IPA resources used based on version (see IPA_RESOURCE_GROUP_COUNT) */ -static int ipa_resource_group_count(struct ipa *ipa) -{ - switch (ipa->version) { - case IPA_VERSION_3_5_1: - return 3; - - case IPA_VERSION_4_0: - case IPA_VERSION_4_1: - return 4; - - case IPA_VERSION_4_2: - return 1; - - default: - return 0; - } -} - static bool ipa_resource_limits_valid(struct ipa *ipa, const struct ipa_resource_data *data) { - u32 group_count = ipa_resource_group_count(ipa); + u32 group_count; u32 i; u32 j; - if (!group_count) + /* We program at most 6 source or destination resource group limits */ + BUILD_BUG_ON(IPA_RESOURCE_GROUP_SRC_MAX > 6); + + group_count = ipa_resource_group_src_count(ipa->version); + if (!group_count || group_count > IPA_RESOURCE_GROUP_SRC_MAX) return false; - /* Return an error if a non-zero resource group limit is specified - * for a resource not supported by hardware. + /* Return an error if a non-zero resource limit is specified + * for a resource group not supported by hardware. */ for (i = 0; i < data->resource_src_count; i++) { const struct ipa_resource_src *resource; resource = &data->resource_src[i]; - for (j = group_count; j < IPA_RESOURCE_GROUP_COUNT; j++) + for (j = group_count; j < IPA_RESOURCE_GROUP_SRC_MAX; j++) if (resource->limits[j].min || resource->limits[j].max) return false; } + group_count = ipa_resource_group_dst_count(ipa->version); + if (!group_count || group_count > IPA_RESOURCE_GROUP_DST_MAX) + return false; + for (i = 0; i < data->resource_dst_count; i++) { const struct ipa_resource_dst *resource; resource = &data->resource_dst[i]; - for (j = group_count; j < IPA_RESOURCE_GROUP_COUNT; j++) + for (j = group_count; j < IPA_RESOURCE_GROUP_DST_MAX; j++) if (resource->limits[j].min || resource->limits[j].max) return false; } @@ -435,46 +423,64 @@ ipa_resource_config_common(struct ipa *ipa, u32 offset, val = u32_encode_bits(xlimits->min, X_MIN_LIM_FMASK); val |= u32_encode_bits(xlimits->max, X_MAX_LIM_FMASK); - val |= u32_encode_bits(ylimits->min, Y_MIN_LIM_FMASK); - val |= u32_encode_bits(ylimits->max, Y_MAX_LIM_FMASK); + if (ylimits) { + val |= u32_encode_bits(ylimits->min, Y_MIN_LIM_FMASK); + val |= u32_encode_bits(ylimits->max, Y_MAX_LIM_FMASK); + } iowrite32(val, ipa->reg_virt + offset); } -static void ipa_resource_config_src_01(struct ipa *ipa, - const struct ipa_resource_src *resource) +static void ipa_resource_config_src(struct ipa *ipa, + const struct ipa_resource_src *resource) { - u32 offset = IPA_REG_SRC_RSRC_GRP_01_RSRC_TYPE_N_OFFSET(resource->type); + u32 group_count = ipa_resource_group_src_count(ipa->version); + const struct ipa_resource_limits *ylimits; + u32 offset; - ipa_resource_config_common(ipa, offset, - &resource->limits[0], &resource->limits[1]); -} + offset = IPA_REG_SRC_RSRC_GRP_01_RSRC_TYPE_N_OFFSET(resource->type); + ylimits = group_count == 1 ? NULL : &resource->limits[1]; + ipa_resource_config_common(ipa, offset, &resource->limits[0], ylimits); -static void ipa_resource_config_src_23(struct ipa *ipa, - const struct ipa_resource_src *resource) -{ - u32 offset = IPA_REG_SRC_RSRC_GRP_23_RSRC_TYPE_N_OFFSET(resource->type); + if (group_count < 2) + return; - ipa_resource_config_common(ipa, offset, - &resource->limits[2], &resource->limits[3]); -} + offset = IPA_REG_SRC_RSRC_GRP_23_RSRC_TYPE_N_OFFSET(resource->type); + ylimits = group_count == 3 ? NULL : &resource->limits[3]; + ipa_resource_config_common(ipa, offset, &resource->limits[2], ylimits); -static void ipa_resource_config_dst_01(struct ipa *ipa, - const struct ipa_resource_dst *resource) -{ - u32 offset = IPA_REG_DST_RSRC_GRP_01_RSRC_TYPE_N_OFFSET(resource->type); + if (group_count < 4) + return; - ipa_resource_config_common(ipa, offset, - &resource->limits[0], &resource->limits[1]); + offset = IPA_REG_SRC_RSRC_GRP_45_RSRC_TYPE_N_OFFSET(resource->type); + ylimits = group_count == 5 ? NULL : &resource->limits[5]; + ipa_resource_config_common(ipa, offset, &resource->limits[4], ylimits); } -static void ipa_resource_config_dst_23(struct ipa *ipa, - const struct ipa_resource_dst *resource) +static void ipa_resource_config_dst(struct ipa *ipa, + const struct ipa_resource_dst *resource) { - u32 offset = IPA_REG_DST_RSRC_GRP_23_RSRC_TYPE_N_OFFSET(resource->type); + u32 group_count = ipa_resource_group_dst_count(ipa->version); + const struct ipa_resource_limits *ylimits; + u32 offset; + + offset = IPA_REG_DST_RSRC_GRP_01_RSRC_TYPE_N_OFFSET(resource->type); + ylimits = group_count == 1 ? NULL : &resource->limits[1]; + ipa_resource_config_common(ipa, offset, &resource->limits[0], ylimits); + + if (group_count < 2) + return; + + offset = IPA_REG_DST_RSRC_GRP_23_RSRC_TYPE_N_OFFSET(resource->type); + ylimits = group_count == 3 ? NULL : &resource->limits[3]; + ipa_resource_config_common(ipa, offset, &resource->limits[2], ylimits); - ipa_resource_config_common(ipa, offset, - &resource->limits[2], &resource->limits[3]); + if (group_count < 4) + return; + + offset = IPA_REG_DST_RSRC_GRP_45_RSRC_TYPE_N_OFFSET(resource->type); + ylimits = group_count == 5 ? NULL : &resource->limits[5]; + ipa_resource_config_common(ipa, offset, &resource->limits[4], ylimits); } static int @@ -485,15 +491,11 @@ ipa_resource_config(struct ipa *ipa, const struct ipa_resource_data *data) if (!ipa_resource_limits_valid(ipa, data)) return -EINVAL; - for (i = 0; i < data->resource_src_count; i++) { - ipa_resource_config_src_01(ipa, &data->resource_src[i]); - ipa_resource_config_src_23(ipa, &data->resource_src[i]); - } + for (i = 0; i < data->resource_src_count; i++) + ipa_resource_config_src(ipa, data->resource_src); - for (i = 0; i < data->resource_dst_count; i++) { - ipa_resource_config_dst_01(ipa, &data->resource_dst[i]); - ipa_resource_config_dst_23(ipa, &data->resource_dst[i]); - } + for (i = 0; i < data->resource_dst_count; i++) + ipa_resource_config_dst(ipa, data->resource_dst); return 0; } @@ -720,10 +722,8 @@ static int ipa_probe(struct platform_device *pdev) const struct ipa_data *data; struct ipa_clock *clock; struct rproc *rproc; - bool modem_alloc; bool modem_init; struct ipa *ipa; - bool prefetch; phandle ph; int ret; @@ -785,13 +785,8 @@ static int ipa_probe(struct platform_device *pdev) if (ret) goto err_reg_exit; - /* GSI v2.0+ (IPA v4.0+) uses prefetch for the command channel */ - prefetch = ipa->version != IPA_VERSION_3_5_1; - /* IPA v4.2 requires the AP to allocate channels for the modem */ - modem_alloc = ipa->version == IPA_VERSION_4_2; - - ret = gsi_init(&ipa->gsi, pdev, prefetch, data->endpoint_count, - data->endpoint_data, modem_alloc); + ret = gsi_init(&ipa->gsi, pdev, ipa->version, data->endpoint_count, + data->endpoint_data); if (ret) goto err_mem_exit; diff --git a/drivers/net/ipa/ipa_mem.c b/drivers/net/ipa/ipa_mem.c index 2d45c444a67f..ecfd1f91fce3 100644 --- a/drivers/net/ipa/ipa_mem.c +++ b/drivers/net/ipa/ipa_mem.c @@ -89,7 +89,7 @@ int ipa_mem_setup(struct ipa *ipa) gsi_trans_commit_wait(trans); /* Tell the hardware where the processing context area is located */ - iowrite32(ipa->mem_offset + offset, + iowrite32(ipa->mem_offset + ipa->mem[IPA_MEM_MODEM_PROC_CTX].offset, ipa->reg_virt + IPA_REG_LOCAL_PKT_PROC_CNTXT_BASE_OFFSET); return 0; diff --git a/drivers/net/ipa/ipa_reg.h b/drivers/net/ipa/ipa_reg.h index e542598fd775..8eaf5f209627 100644 --- a/drivers/net/ipa/ipa_reg.h +++ b/drivers/net/ipa/ipa_reg.h @@ -244,6 +244,43 @@ static inline u32 ipa_reg_idle_indication_cfg_offset(enum ipa_version version) #define ENTER_IDLE_DEBOUNCE_THRESH_FMASK GENMASK(15, 0) #define CONST_NON_IDLE_ENABLE_FMASK GENMASK(16, 16) +/* # IPA source resource groups available based on version */ +static inline u32 ipa_resource_group_src_count(enum ipa_version version) +{ + switch (version) { + case IPA_VERSION_3_5_1: + case IPA_VERSION_4_0: + case IPA_VERSION_4_1: + return 4; + + case IPA_VERSION_4_2: + return 1; + + default: + return 0; + } +} + +/* # IPA destination resource groups available based on version */ +static inline u32 ipa_resource_group_dst_count(enum ipa_version version) +{ + switch (version) { + case IPA_VERSION_3_5_1: + return 3; + + case IPA_VERSION_4_0: + case IPA_VERSION_4_1: + return 4; + + case IPA_VERSION_4_2: + return 1; + + default: + return 0; + } +} + +/* Not all of the following are valid (depends on the count, above) */ #define IPA_REG_SRC_RSRC_GRP_01_RSRC_TYPE_N_OFFSET(rt) \ (0x00000400 + 0x0020 * (rt)) #define IPA_REG_SRC_RSRC_GRP_23_RSRC_TYPE_N_OFFSET(rt) \ @@ -341,7 +378,16 @@ static inline u32 ipa_reg_idle_indication_cfg_offset(enum ipa_version version) #define IPA_REG_ENDP_INIT_RSRC_GRP_N_OFFSET(ep) \ (0x00000838 + 0x0070 * (ep)) -#define RSRC_GRP_FMASK GENMASK(1, 0) +/* Encoded value for RSRC_GRP endpoint register RSRC_GRP field */ +static inline u32 rsrc_grp_encoded(enum ipa_version version, u32 rsrc_grp) +{ + switch (version) { + case IPA_VERSION_4_2: + return u32_encode_bits(rsrc_grp, GENMASK(0, 0)); + default: + return u32_encode_bits(rsrc_grp, GENMASK(1, 0)); + } +} /* Valid only for TX (IPA consumer) endpoints */ #define IPA_REG_ENDP_INIT_SEQ_N_OFFSET(txep) \ diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 11ca5fa902a1..92425e1fd70c 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -101,6 +101,7 @@ struct pcpu_secy_stats { * @real_dev: pointer to underlying netdevice * @stats: MACsec device stats * @secys: linked list of SecY's on the underlying device + * @gro_cells: pointer to the Generic Receive Offload cell * @offload: status of offloading on the MACsec device */ struct macsec_dev { diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index c8d803d3616c..dd960209da94 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -1339,7 +1339,7 @@ static int macvlan_validate(struct nlattr *tb[], struct nlattr *data[], return 0; } -/** +/* * reconfigure list of remote source mac address * (only for macvlan devices in source mode) * Note regarding alignment: all netlink data is aligned to 4 Byte, which diff --git a/drivers/net/mhi_net.c b/drivers/net/mhi_net.c new file mode 100644 index 000000000000..d3f92781314e --- /dev/null +++ b/drivers/net/mhi_net.c @@ -0,0 +1,316 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* MHI Network driver - Network over MHI bus + * + * Copyright (C) 2020 Linaro Ltd <loic.poulain@linaro.org> + */ + +#include <linux/if_arp.h> +#include <linux/mhi.h> +#include <linux/mod_devicetable.h> +#include <linux/module.h> +#include <linux/netdevice.h> +#include <linux/skbuff.h> +#include <linux/u64_stats_sync.h> + +#define MHI_NET_MIN_MTU ETH_MIN_MTU +#define MHI_NET_MAX_MTU 0xffff +#define MHI_NET_DEFAULT_MTU 0x4000 + +struct mhi_net_stats { + u64_stats_t rx_packets; + u64_stats_t rx_bytes; + u64_stats_t rx_errors; + u64_stats_t rx_dropped; + u64_stats_t tx_packets; + u64_stats_t tx_bytes; + u64_stats_t tx_errors; + u64_stats_t tx_dropped; + atomic_t rx_queued; + struct u64_stats_sync tx_syncp; + struct u64_stats_sync rx_syncp; +}; + +struct mhi_net_dev { + struct mhi_device *mdev; + struct net_device *ndev; + struct delayed_work rx_refill; + struct mhi_net_stats stats; + u32 rx_queue_sz; +}; + +static int mhi_ndo_open(struct net_device *ndev) +{ + struct mhi_net_dev *mhi_netdev = netdev_priv(ndev); + + /* Feed the rx buffer pool */ + schedule_delayed_work(&mhi_netdev->rx_refill, 0); + + /* Carrier is established via out-of-band channel (e.g. qmi) */ + netif_carrier_on(ndev); + + netif_start_queue(ndev); + + return 0; +} + +static int mhi_ndo_stop(struct net_device *ndev) +{ + struct mhi_net_dev *mhi_netdev = netdev_priv(ndev); + + netif_stop_queue(ndev); + netif_carrier_off(ndev); + cancel_delayed_work_sync(&mhi_netdev->rx_refill); + + return 0; +} + +static int mhi_ndo_xmit(struct sk_buff *skb, struct net_device *ndev) +{ + struct mhi_net_dev *mhi_netdev = netdev_priv(ndev); + struct mhi_device *mdev = mhi_netdev->mdev; + int err; + + err = mhi_queue_skb(mdev, DMA_TO_DEVICE, skb, skb->len, MHI_EOT); + if (unlikely(err)) { + net_err_ratelimited("%s: Failed to queue TX buf (%d)\n", + ndev->name, err); + + u64_stats_update_begin(&mhi_netdev->stats.tx_syncp); + u64_stats_inc(&mhi_netdev->stats.tx_dropped); + u64_stats_update_end(&mhi_netdev->stats.tx_syncp); + + /* drop the packet */ + dev_kfree_skb_any(skb); + } + + if (mhi_queue_is_full(mdev, DMA_TO_DEVICE)) + netif_stop_queue(ndev); + + return NETDEV_TX_OK; +} + +static void mhi_ndo_get_stats64(struct net_device *ndev, + struct rtnl_link_stats64 *stats) +{ + struct mhi_net_dev *mhi_netdev = netdev_priv(ndev); + unsigned int start; + + do { + start = u64_stats_fetch_begin_irq(&mhi_netdev->stats.rx_syncp); + stats->rx_packets = u64_stats_read(&mhi_netdev->stats.rx_packets); + stats->rx_bytes = u64_stats_read(&mhi_netdev->stats.rx_bytes); + stats->rx_errors = u64_stats_read(&mhi_netdev->stats.rx_errors); + stats->rx_dropped = u64_stats_read(&mhi_netdev->stats.rx_dropped); + } while (u64_stats_fetch_retry_irq(&mhi_netdev->stats.rx_syncp, start)); + + do { + start = u64_stats_fetch_begin_irq(&mhi_netdev->stats.tx_syncp); + stats->tx_packets = u64_stats_read(&mhi_netdev->stats.tx_packets); + stats->tx_bytes = u64_stats_read(&mhi_netdev->stats.tx_bytes); + stats->tx_errors = u64_stats_read(&mhi_netdev->stats.tx_errors); + stats->tx_dropped = u64_stats_read(&mhi_netdev->stats.tx_dropped); + } while (u64_stats_fetch_retry_irq(&mhi_netdev->stats.tx_syncp, start)); +} + +static const struct net_device_ops mhi_netdev_ops = { + .ndo_open = mhi_ndo_open, + .ndo_stop = mhi_ndo_stop, + .ndo_start_xmit = mhi_ndo_xmit, + .ndo_get_stats64 = mhi_ndo_get_stats64, +}; + +static void mhi_net_setup(struct net_device *ndev) +{ + ndev->header_ops = NULL; /* No header */ + ndev->type = ARPHRD_NONE; /* QMAP... */ + ndev->hard_header_len = 0; + ndev->addr_len = 0; + ndev->flags = IFF_POINTOPOINT | IFF_NOARP; + ndev->netdev_ops = &mhi_netdev_ops; + ndev->mtu = MHI_NET_DEFAULT_MTU; + ndev->min_mtu = MHI_NET_MIN_MTU; + ndev->max_mtu = MHI_NET_MAX_MTU; + ndev->tx_queue_len = 1000; +} + +static void mhi_net_dl_callback(struct mhi_device *mhi_dev, + struct mhi_result *mhi_res) +{ + struct mhi_net_dev *mhi_netdev = dev_get_drvdata(&mhi_dev->dev); + struct sk_buff *skb = mhi_res->buf_addr; + int remaining; + + remaining = atomic_dec_return(&mhi_netdev->stats.rx_queued); + + if (unlikely(mhi_res->transaction_status)) { + dev_kfree_skb_any(skb); + + /* MHI layer stopping/resetting the DL channel */ + if (mhi_res->transaction_status == -ENOTCONN) + return; + + u64_stats_update_begin(&mhi_netdev->stats.rx_syncp); + u64_stats_inc(&mhi_netdev->stats.rx_errors); + u64_stats_update_end(&mhi_netdev->stats.rx_syncp); + } else { + u64_stats_update_begin(&mhi_netdev->stats.rx_syncp); + u64_stats_inc(&mhi_netdev->stats.rx_packets); + u64_stats_add(&mhi_netdev->stats.rx_bytes, mhi_res->bytes_xferd); + u64_stats_update_end(&mhi_netdev->stats.rx_syncp); + + skb->protocol = htons(ETH_P_MAP); + skb_put(skb, mhi_res->bytes_xferd); + netif_rx(skb); + } + + /* Refill if RX buffers queue becomes low */ + if (remaining <= mhi_netdev->rx_queue_sz / 2) + schedule_delayed_work(&mhi_netdev->rx_refill, 0); +} + +static void mhi_net_ul_callback(struct mhi_device *mhi_dev, + struct mhi_result *mhi_res) +{ + struct mhi_net_dev *mhi_netdev = dev_get_drvdata(&mhi_dev->dev); + struct net_device *ndev = mhi_netdev->ndev; + struct sk_buff *skb = mhi_res->buf_addr; + + /* Hardware has consumed the buffer, so free the skb (which is not + * freed by the MHI stack) and perform accounting. + */ + dev_consume_skb_any(skb); + + u64_stats_update_begin(&mhi_netdev->stats.tx_syncp); + if (unlikely(mhi_res->transaction_status)) { + + /* MHI layer stopping/resetting the UL channel */ + if (mhi_res->transaction_status == -ENOTCONN) { + u64_stats_update_end(&mhi_netdev->stats.tx_syncp); + return; + } + + u64_stats_inc(&mhi_netdev->stats.tx_errors); + } else { + u64_stats_inc(&mhi_netdev->stats.tx_packets); + u64_stats_add(&mhi_netdev->stats.tx_bytes, mhi_res->bytes_xferd); + } + u64_stats_update_end(&mhi_netdev->stats.tx_syncp); + + if (netif_queue_stopped(ndev)) + netif_wake_queue(ndev); +} + +static void mhi_net_rx_refill_work(struct work_struct *work) +{ + struct mhi_net_dev *mhi_netdev = container_of(work, struct mhi_net_dev, + rx_refill.work); + struct net_device *ndev = mhi_netdev->ndev; + struct mhi_device *mdev = mhi_netdev->mdev; + int size = READ_ONCE(ndev->mtu); + struct sk_buff *skb; + int err; + + while (atomic_read(&mhi_netdev->stats.rx_queued) < mhi_netdev->rx_queue_sz) { + skb = netdev_alloc_skb(ndev, size); + if (unlikely(!skb)) + break; + + err = mhi_queue_skb(mdev, DMA_FROM_DEVICE, skb, size, MHI_EOT); + if (unlikely(err)) { + net_err_ratelimited("%s: Failed to queue RX buf (%d)\n", + ndev->name, err); + kfree_skb(skb); + break; + } + + atomic_inc(&mhi_netdev->stats.rx_queued); + + /* Do not hog the CPU if rx buffers are consumed faster than + * queued (unlikely). + */ + cond_resched(); + } + + /* If we're still starved of rx buffers, reschedule later */ + if (unlikely(!atomic_read(&mhi_netdev->stats.rx_queued))) + schedule_delayed_work(&mhi_netdev->rx_refill, HZ / 2); +} + +static int mhi_net_probe(struct mhi_device *mhi_dev, + const struct mhi_device_id *id) +{ + const char *netname = (char *)id->driver_data; + struct device *dev = &mhi_dev->dev; + struct mhi_net_dev *mhi_netdev; + struct net_device *ndev; + int err; + + ndev = alloc_netdev(sizeof(*mhi_netdev), netname, NET_NAME_PREDICTABLE, + mhi_net_setup); + if (!ndev) + return -ENOMEM; + + mhi_netdev = netdev_priv(ndev); + dev_set_drvdata(dev, mhi_netdev); + mhi_netdev->ndev = ndev; + mhi_netdev->mdev = mhi_dev; + SET_NETDEV_DEV(ndev, &mhi_dev->dev); + + /* All MHI net channels have 128 ring elements (at least for now) */ + mhi_netdev->rx_queue_sz = 128; + + INIT_DELAYED_WORK(&mhi_netdev->rx_refill, mhi_net_rx_refill_work); + u64_stats_init(&mhi_netdev->stats.rx_syncp); + u64_stats_init(&mhi_netdev->stats.tx_syncp); + + /* Start MHI channels */ + err = mhi_prepare_for_transfer(mhi_dev); + if (err) + goto out_err; + + err = register_netdev(ndev); + if (err) + goto out_err; + + return 0; + +out_err: + free_netdev(ndev); + return err; +} + +static void mhi_net_remove(struct mhi_device *mhi_dev) +{ + struct mhi_net_dev *mhi_netdev = dev_get_drvdata(&mhi_dev->dev); + + unregister_netdev(mhi_netdev->ndev); + + mhi_unprepare_from_transfer(mhi_netdev->mdev); + + free_netdev(mhi_netdev->ndev); +} + +static const struct mhi_device_id mhi_net_id_table[] = { + { .chan = "IP_HW0", .driver_data = (kernel_ulong_t)"mhi_hwip%d" }, + { .chan = "IP_SW0", .driver_data = (kernel_ulong_t)"mhi_swip%d" }, + {} +}; +MODULE_DEVICE_TABLE(mhi, mhi_net_id_table); + +static struct mhi_driver mhi_net_driver = { + .probe = mhi_net_probe, + .remove = mhi_net_remove, + .dl_xfer_cb = mhi_net_dl_callback, + .ul_xfer_cb = mhi_net_ul_callback, + .id_table = mhi_net_id_table, + .driver = { + .name = "mhi_net", + .owner = THIS_MODULE, + }, +}; + +module_mhi_driver(mhi_net_driver); + +MODULE_AUTHOR("Loic Poulain <loic.poulain@linaro.org>"); +MODULE_DESCRIPTION("Network over MHI"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/mii.c b/drivers/net/mii.c index f6a97c859f3a..e71ebb933266 100644 --- a/drivers/net/mii.c +++ b/drivers/net/mii.c @@ -84,15 +84,16 @@ int mii_ethtool_gset(struct mii_if_info *mii, struct ethtool_cmd *ecmd) ctrl1000 = mii->mdio_read(dev, mii->phy_id, MII_CTRL1000); stat1000 = mii->mdio_read(dev, mii->phy_id, MII_STAT1000); } + + ecmd->advertising |= mii_get_an(mii, MII_ADVERTISE); + if (mii->supports_gmii) + ecmd->advertising |= + mii_ctrl1000_to_ethtool_adv_t(ctrl1000); + if (bmcr & BMCR_ANENABLE) { ecmd->advertising |= ADVERTISED_Autoneg; ecmd->autoneg = AUTONEG_ENABLE; - ecmd->advertising |= mii_get_an(mii, MII_ADVERTISE); - if (mii->supports_gmii) - ecmd->advertising |= - mii_ctrl1000_to_ethtool_adv_t(ctrl1000); - if (bmsr & BMSR_ANEGCOMPLETE) { ecmd->lp_advertising = mii_get_an(mii, MII_LPA); ecmd->lp_advertising |= @@ -171,14 +172,15 @@ void mii_ethtool_get_link_ksettings(struct mii_if_info *mii, ctrl1000 = mii->mdio_read(dev, mii->phy_id, MII_CTRL1000); stat1000 = mii->mdio_read(dev, mii->phy_id, MII_STAT1000); } + + advertising |= mii_get_an(mii, MII_ADVERTISE); + if (mii->supports_gmii) + advertising |= mii_ctrl1000_to_ethtool_adv_t(ctrl1000); + if (bmcr & BMCR_ANENABLE) { advertising |= ADVERTISED_Autoneg; cmd->base.autoneg = AUTONEG_ENABLE; - advertising |= mii_get_an(mii, MII_ADVERTISE); - if (mii->supports_gmii) - advertising |= mii_ctrl1000_to_ethtool_adv_t(ctrl1000); - if (bmsr & BMSR_ANEGCOMPLETE) { lp_advertising = mii_get_an(mii, MII_LPA); lp_advertising |= diff --git a/drivers/net/net_failover.c b/drivers/net/net_failover.c index fb182bec8f06..2a4892402ed8 100644 --- a/drivers/net/net_failover.c +++ b/drivers/net/net_failover.c @@ -697,7 +697,7 @@ static struct failover_ops net_failover_ops = { /** * net_failover_create - Create and register a failover instance * - * @dev: standby netdev + * @standby_dev: standby netdev * * Creates a failover netdev and registers a failover instance for a standby * netdev. Used by paravirtual drivers that use 3-netdev model. diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c index 92001f7af380..ccecba908ded 100644 --- a/drivers/net/netconsole.c +++ b/drivers/net/netconsole.c @@ -83,6 +83,7 @@ static struct console netconsole_ext; * whether the corresponding netpoll is active or inactive. * Also, other parameters of a target may be modified at * runtime only when it is disabled (enabled == 0). + * @extended: Denotes whether console is extended or not. * @np: The netpoll structure for this target. * Contains the other userspace visible parameters: * dev_name (read-write) diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index d07061417675..49cc1fea9e02 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -324,6 +324,12 @@ static int nsim_dev_resources_register(struct devlink *devlink) return err; } + /* Resources for nexthops */ + err = devlink_resource_register(devlink, "nexthops", (u64)-1, + NSIM_RESOURCE_NEXTHOPS, + DEVLINK_RESOURCE_ID_PARENT_TOP, + ¶ms); + out: return err; } diff --git a/drivers/net/netdevsim/fib.c b/drivers/net/netdevsim/fib.c index deea17a0e79c..45d8a7790bd5 100644 --- a/drivers/net/netdevsim/fib.c +++ b/drivers/net/netdevsim/fib.c @@ -25,6 +25,7 @@ #include <net/ip6_fib.h> #include <net/fib_rules.h> #include <net/net_namespace.h> +#include <net/nexthop.h> #include "netdevsim.h" @@ -42,9 +43,12 @@ struct nsim_fib_data { struct notifier_block fib_nb; struct nsim_per_fib_data ipv4; struct nsim_per_fib_data ipv6; + struct nsim_fib_entry nexthops; struct rhashtable fib_rt_ht; struct list_head fib_rt_list; spinlock_t fib_lock; /* Protects hashtable, list and accounting */ + struct notifier_block nexthop_nb; + struct rhashtable nexthop_ht; struct devlink *devlink; }; @@ -86,6 +90,19 @@ static const struct rhashtable_params nsim_fib_rt_ht_params = { .automatic_shrinking = true, }; +struct nsim_nexthop { + struct rhash_head ht_node; + u64 occ; + u32 id; +}; + +static const struct rhashtable_params nsim_nexthop_ht_params = { + .key_offset = offsetof(struct nsim_nexthop, id), + .head_offset = offsetof(struct nsim_nexthop, ht_node), + .key_len = sizeof(u32), + .automatic_shrinking = true, +}; + u64 nsim_fib_get_val(struct nsim_fib_data *fib_data, enum nsim_resource_id res_id, bool max) { @@ -104,6 +121,9 @@ u64 nsim_fib_get_val(struct nsim_fib_data *fib_data, case NSIM_RESOURCE_IPV6_FIB_RULES: entry = &fib_data->ipv6.rules; break; + case NSIM_RESOURCE_NEXTHOPS: + entry = &fib_data->nexthops; + break; default: return 0; } @@ -129,6 +149,9 @@ static void nsim_fib_set_max(struct nsim_fib_data *fib_data, case NSIM_RESOURCE_IPV6_FIB_RULES: entry = &fib_data->ipv6.rules; break; + case NSIM_RESOURCE_NEXTHOPS: + entry = &fib_data->nexthops; + break; default: WARN_ON(1); return; @@ -389,11 +412,6 @@ static int nsim_fib4_event(struct nsim_fib_data *data, fen_info = container_of(info, struct fib_entry_notifier_info, info); - if (fen_info->fi->nh) { - NL_SET_ERR_MSG_MOD(info->extack, "IPv4 route with nexthop objects is not supported"); - return 0; - } - switch (event) { case FIB_EVENT_ENTRY_REPLACE: err = nsim_fib4_rt_insert(data, fen_info); @@ -704,11 +722,6 @@ static int nsim_fib6_event(struct nsim_fib_data *data, fen6_info = container_of(info, struct fib6_entry_notifier_info, info); - if (fen6_info->rt->nh) { - NL_SET_ERR_MSG_MOD(info->extack, "IPv6 route with nexthop objects is not supported"); - return 0; - } - if (fen6_info->rt->fib6_src.plen) { NL_SET_ERR_MSG_MOD(info->extack, "IPv6 source-specific route is not supported"); return 0; @@ -838,6 +851,196 @@ static void nsim_fib_dump_inconsistent(struct notifier_block *nb) data->ipv6.rules.num = 0ULL; } +static struct nsim_nexthop *nsim_nexthop_create(struct nsim_fib_data *data, + struct nh_notifier_info *info) +{ + struct nsim_nexthop *nexthop; + u64 occ = 0; + int i; + + nexthop = kzalloc(sizeof(*nexthop), GFP_KERNEL); + if (!nexthop) + return NULL; + + nexthop->id = info->id; + + /* Determine the number of nexthop entries the new nexthop will + * occupy. + */ + + if (!info->is_grp) { + occ = 1; + goto out; + } + + for (i = 0; i < info->nh_grp->num_nh; i++) + occ += info->nh_grp->nh_entries[i].weight; + +out: + nexthop->occ = occ; + return nexthop; +} + +static void nsim_nexthop_destroy(struct nsim_nexthop *nexthop) +{ + kfree(nexthop); +} + +static int nsim_nexthop_account(struct nsim_fib_data *data, u64 occ, + bool add, struct netlink_ext_ack *extack) +{ + int err = 0; + + if (add) { + if (data->nexthops.num + occ <= data->nexthops.max) { + data->nexthops.num += occ; + } else { + err = -ENOSPC; + NL_SET_ERR_MSG_MOD(extack, "Exceeded number of supported nexthops"); + } + } else { + if (WARN_ON(occ > data->nexthops.num)) + return -EINVAL; + data->nexthops.num -= occ; + } + + return err; +} + +static int nsim_nexthop_add(struct nsim_fib_data *data, + struct nsim_nexthop *nexthop, + struct netlink_ext_ack *extack) +{ + struct net *net = devlink_net(data->devlink); + int err; + + err = nsim_nexthop_account(data, nexthop->occ, true, extack); + if (err) + return err; + + err = rhashtable_insert_fast(&data->nexthop_ht, &nexthop->ht_node, + nsim_nexthop_ht_params); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to insert nexthop"); + goto err_nexthop_dismiss; + } + + nexthop_set_hw_flags(net, nexthop->id, false, true); + + return 0; + +err_nexthop_dismiss: + nsim_nexthop_account(data, nexthop->occ, false, extack); + return err; +} + +static int nsim_nexthop_replace(struct nsim_fib_data *data, + struct nsim_nexthop *nexthop, + struct nsim_nexthop *nexthop_old, + struct netlink_ext_ack *extack) +{ + struct net *net = devlink_net(data->devlink); + int err; + + err = nsim_nexthop_account(data, nexthop->occ, true, extack); + if (err) + return err; + + err = rhashtable_replace_fast(&data->nexthop_ht, + &nexthop_old->ht_node, &nexthop->ht_node, + nsim_nexthop_ht_params); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to replace nexthop"); + goto err_nexthop_dismiss; + } + + nexthop_set_hw_flags(net, nexthop->id, false, true); + nsim_nexthop_account(data, nexthop_old->occ, false, extack); + nsim_nexthop_destroy(nexthop_old); + + return 0; + +err_nexthop_dismiss: + nsim_nexthop_account(data, nexthop->occ, false, extack); + return err; +} + +static int nsim_nexthop_insert(struct nsim_fib_data *data, + struct nh_notifier_info *info) +{ + struct nsim_nexthop *nexthop, *nexthop_old; + int err; + + nexthop = nsim_nexthop_create(data, info); + if (!nexthop) + return -ENOMEM; + + nexthop_old = rhashtable_lookup_fast(&data->nexthop_ht, &info->id, + nsim_nexthop_ht_params); + if (!nexthop_old) + err = nsim_nexthop_add(data, nexthop, info->extack); + else + err = nsim_nexthop_replace(data, nexthop, nexthop_old, + info->extack); + + if (err) + nsim_nexthop_destroy(nexthop); + + return err; +} + +static void nsim_nexthop_remove(struct nsim_fib_data *data, + struct nh_notifier_info *info) +{ + struct nsim_nexthop *nexthop; + + nexthop = rhashtable_lookup_fast(&data->nexthop_ht, &info->id, + nsim_nexthop_ht_params); + if (!nexthop) + return; + + rhashtable_remove_fast(&data->nexthop_ht, &nexthop->ht_node, + nsim_nexthop_ht_params); + nsim_nexthop_account(data, nexthop->occ, false, info->extack); + nsim_nexthop_destroy(nexthop); +} + +static int nsim_nexthop_event_nb(struct notifier_block *nb, unsigned long event, + void *ptr) +{ + struct nsim_fib_data *data = container_of(nb, struct nsim_fib_data, + nexthop_nb); + struct nh_notifier_info *info = ptr; + int err = 0; + + ASSERT_RTNL(); + + switch (event) { + case NEXTHOP_EVENT_REPLACE: + err = nsim_nexthop_insert(data, info); + break; + case NEXTHOP_EVENT_DEL: + nsim_nexthop_remove(data, info); + break; + default: + break; + } + + return notifier_from_errno(err); +} + +static void nsim_nexthop_free(void *ptr, void *arg) +{ + struct nsim_nexthop *nexthop = ptr; + struct nsim_fib_data *data = arg; + struct net *net; + + net = devlink_net(data->devlink); + nexthop_set_hw_flags(net, nexthop->id, false, false); + nsim_nexthop_account(data, nexthop->occ, false, NULL); + nsim_nexthop_destroy(nexthop); +} + static u64 nsim_fib_ipv4_resource_occ_get(void *priv) { struct nsim_fib_data *data = priv; @@ -866,12 +1069,20 @@ static u64 nsim_fib_ipv6_rules_res_occ_get(void *priv) return nsim_fib_get_val(data, NSIM_RESOURCE_IPV6_FIB_RULES, false); } +static u64 nsim_fib_nexthops_res_occ_get(void *priv) +{ + struct nsim_fib_data *data = priv; + + return nsim_fib_get_val(data, NSIM_RESOURCE_NEXTHOPS, false); +} + static void nsim_fib_set_max_all(struct nsim_fib_data *data, struct devlink *devlink) { enum nsim_resource_id res_ids[] = { NSIM_RESOURCE_IPV4_FIB, NSIM_RESOURCE_IPV4_FIB_RULES, - NSIM_RESOURCE_IPV6_FIB, NSIM_RESOURCE_IPV6_FIB_RULES + NSIM_RESOURCE_IPV6_FIB, NSIM_RESOURCE_IPV6_FIB_RULES, + NSIM_RESOURCE_NEXTHOPS, }; int i; @@ -897,20 +1108,32 @@ struct nsim_fib_data *nsim_fib_create(struct devlink *devlink, return ERR_PTR(-ENOMEM); data->devlink = devlink; + err = rhashtable_init(&data->nexthop_ht, &nsim_nexthop_ht_params); + if (err) + goto err_data_free; + spin_lock_init(&data->fib_lock); INIT_LIST_HEAD(&data->fib_rt_list); err = rhashtable_init(&data->fib_rt_ht, &nsim_fib_rt_ht_params); if (err) - goto err_data_free; + goto err_rhashtable_nexthop_destroy; nsim_fib_set_max_all(data, devlink); + data->nexthop_nb.notifier_call = nsim_nexthop_event_nb; + err = register_nexthop_notifier(devlink_net(devlink), &data->nexthop_nb, + extack); + if (err) { + pr_err("Failed to register nexthop notifier\n"); + goto err_rhashtable_fib_destroy; + } + data->fib_nb.notifier_call = nsim_fib_event_nb; err = register_fib_notifier(devlink_net(devlink), &data->fib_nb, nsim_fib_dump_inconsistent, extack); if (err) { pr_err("Failed to register fib notifier\n"); - goto err_rhashtable_destroy; + goto err_nexthop_nb_unregister; } devlink_resource_occ_get_register(devlink, @@ -929,11 +1152,20 @@ struct nsim_fib_data *nsim_fib_create(struct devlink *devlink, NSIM_RESOURCE_IPV6_FIB_RULES, nsim_fib_ipv6_rules_res_occ_get, data); + devlink_resource_occ_get_register(devlink, + NSIM_RESOURCE_NEXTHOPS, + nsim_fib_nexthops_res_occ_get, + data); return data; -err_rhashtable_destroy: +err_nexthop_nb_unregister: + unregister_nexthop_notifier(devlink_net(devlink), &data->nexthop_nb); +err_rhashtable_fib_destroy: rhashtable_free_and_destroy(&data->fib_rt_ht, nsim_fib_rt_free, data); +err_rhashtable_nexthop_destroy: + rhashtable_free_and_destroy(&data->nexthop_ht, nsim_nexthop_free, + data); err_data_free: kfree(data); return ERR_PTR(err); @@ -942,6 +1174,8 @@ err_data_free: void nsim_fib_destroy(struct devlink *devlink, struct nsim_fib_data *data) { devlink_resource_occ_get_unregister(devlink, + NSIM_RESOURCE_NEXTHOPS); + devlink_resource_occ_get_unregister(devlink, NSIM_RESOURCE_IPV6_FIB_RULES); devlink_resource_occ_get_unregister(devlink, NSIM_RESOURCE_IPV6_FIB); @@ -950,8 +1184,11 @@ void nsim_fib_destroy(struct devlink *devlink, struct nsim_fib_data *data) devlink_resource_occ_get_unregister(devlink, NSIM_RESOURCE_IPV4_FIB); unregister_fib_notifier(devlink_net(devlink), &data->fib_nb); + unregister_nexthop_notifier(devlink_net(devlink), &data->nexthop_nb); rhashtable_free_and_destroy(&data->fib_rt_ht, nsim_fib_rt_free, data); + rhashtable_free_and_destroy(&data->nexthop_ht, nsim_nexthop_free, + data); WARN_ON_ONCE(!list_empty(&data->fib_rt_list)); kfree(data); } diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index 827fc80f50a0..698be048041b 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -158,6 +158,7 @@ enum nsim_resource_id { NSIM_RESOURCE_IPV6, NSIM_RESOURCE_IPV6_FIB, NSIM_RESOURCE_IPV6_FIB_RULES, + NSIM_RESOURCE_NEXTHOPS, }; struct nsim_dev_health { diff --git a/drivers/net/phy/adin.c b/drivers/net/phy/adin.c index 307f0ac1287b..3727b38addf7 100644 --- a/drivers/net/phy/adin.c +++ b/drivers/net/phy/adin.c @@ -8,6 +8,7 @@ #include <linux/bitfield.h> #include <linux/delay.h> #include <linux/errno.h> +#include <linux/ethtool_netlink.h> #include <linux/init.h> #include <linux/module.h> #include <linux/mii.h> @@ -23,6 +24,7 @@ #define ADIN1300_PHY_CTRL1 0x0012 #define ADIN1300_AUTO_MDI_EN BIT(10) #define ADIN1300_MAN_MDIX_EN BIT(9) +#define ADIN1300_DIAG_CLK_EN BIT(2) #define ADIN1300_RX_ERR_CNT 0x0014 @@ -69,6 +71,31 @@ #define ADIN1300_CLOCK_STOP_REG 0x9400 #define ADIN1300_LPI_WAKE_ERR_CNT_REG 0xa000 +#define ADIN1300_CDIAG_RUN 0xba1b +#define ADIN1300_CDIAG_RUN_EN BIT(0) + +/* + * The XSIM3/2/1 and XSHRT3/2/1 are actually relative. + * For CDIAG_DTLD_RSLTS(0) it's ADIN1300_CDIAG_RSLT_XSIM3/2/1 + * For CDIAG_DTLD_RSLTS(1) it's ADIN1300_CDIAG_RSLT_XSIM3/2/0 + * For CDIAG_DTLD_RSLTS(2) it's ADIN1300_CDIAG_RSLT_XSIM3/1/0 + * For CDIAG_DTLD_RSLTS(3) it's ADIN1300_CDIAG_RSLT_XSIM2/1/0 + */ +#define ADIN1300_CDIAG_DTLD_RSLTS(x) (0xba1d + (x)) +#define ADIN1300_CDIAG_RSLT_BUSY BIT(10) +#define ADIN1300_CDIAG_RSLT_XSIM3 BIT(9) +#define ADIN1300_CDIAG_RSLT_XSIM2 BIT(8) +#define ADIN1300_CDIAG_RSLT_XSIM1 BIT(7) +#define ADIN1300_CDIAG_RSLT_SIM BIT(6) +#define ADIN1300_CDIAG_RSLT_XSHRT3 BIT(5) +#define ADIN1300_CDIAG_RSLT_XSHRT2 BIT(4) +#define ADIN1300_CDIAG_RSLT_XSHRT1 BIT(3) +#define ADIN1300_CDIAG_RSLT_SHRT BIT(2) +#define ADIN1300_CDIAG_RSLT_OPEN BIT(1) +#define ADIN1300_CDIAG_RSLT_GOOD BIT(0) + +#define ADIN1300_CDIAG_FLT_DIST(x) (0xba21 + (x)) + #define ADIN1300_GE_SOFT_RESET_REG 0xff0c #define ADIN1300_GE_SOFT_RESET BIT(0) @@ -321,10 +348,9 @@ static int adin_set_downshift(struct phy_device *phydev, u8 cnt) return -E2BIG; val = FIELD_PREP(ADIN1300_DOWNSPEED_RETRIES_MSK, cnt); - val |= ADIN1300_LINKING_EN; rc = phy_modify(phydev, ADIN1300_PHY_CTRL3, - ADIN1300_LINKING_EN | ADIN1300_DOWNSPEED_RETRIES_MSK, + ADIN1300_DOWNSPEED_RETRIES_MSK, val); if (rc < 0) return rc; @@ -555,6 +581,14 @@ static int adin_config_aneg(struct phy_device *phydev) { int ret; + ret = phy_clear_bits(phydev, ADIN1300_PHY_CTRL1, ADIN1300_DIAG_CLK_EN); + if (ret < 0) + return ret; + + ret = phy_set_bits(phydev, ADIN1300_PHY_CTRL3, ADIN1300_LINKING_EN); + if (ret < 0) + return ret; + ret = adin_config_mdix(phydev); if (ret) return ret; @@ -725,10 +759,117 @@ static int adin_probe(struct phy_device *phydev) return 0; } +static int adin_cable_test_start(struct phy_device *phydev) +{ + int ret; + + ret = phy_clear_bits(phydev, ADIN1300_PHY_CTRL3, ADIN1300_LINKING_EN); + if (ret < 0) + return ret; + + ret = phy_clear_bits(phydev, ADIN1300_PHY_CTRL1, ADIN1300_DIAG_CLK_EN); + if (ret < 0) + return ret; + + /* wait a bit for the clock to stabilize */ + msleep(50); + + return phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, ADIN1300_CDIAG_RUN, + ADIN1300_CDIAG_RUN_EN); +} + +static int adin_cable_test_report_trans(int result) +{ + int mask; + + if (result & ADIN1300_CDIAG_RSLT_GOOD) + return ETHTOOL_A_CABLE_RESULT_CODE_OK; + if (result & ADIN1300_CDIAG_RSLT_OPEN) + return ETHTOOL_A_CABLE_RESULT_CODE_OPEN; + + /* short with other pairs */ + mask = ADIN1300_CDIAG_RSLT_XSHRT3 | + ADIN1300_CDIAG_RSLT_XSHRT2 | + ADIN1300_CDIAG_RSLT_XSHRT1; + if (result & mask) + return ETHTOOL_A_CABLE_RESULT_CODE_CROSS_SHORT; + + if (result & ADIN1300_CDIAG_RSLT_SHRT) + return ETHTOOL_A_CABLE_RESULT_CODE_SAME_SHORT; + + return ETHTOOL_A_CABLE_RESULT_CODE_UNSPEC; +} + +static int adin_cable_test_report_pair(struct phy_device *phydev, + unsigned int pair) +{ + int fault_rslt; + int ret; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND1, + ADIN1300_CDIAG_DTLD_RSLTS(pair)); + if (ret < 0) + return ret; + + fault_rslt = adin_cable_test_report_trans(ret); + + ret = ethnl_cable_test_result(phydev, pair, fault_rslt); + if (ret < 0) + return ret; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND1, + ADIN1300_CDIAG_FLT_DIST(pair)); + if (ret < 0) + return ret; + + switch (fault_rslt) { + case ETHTOOL_A_CABLE_RESULT_CODE_OPEN: + case ETHTOOL_A_CABLE_RESULT_CODE_SAME_SHORT: + case ETHTOOL_A_CABLE_RESULT_CODE_CROSS_SHORT: + return ethnl_cable_test_fault_length(phydev, pair, ret * 100); + default: + return 0; + } +} + +static int adin_cable_test_report(struct phy_device *phydev) +{ + unsigned int pair; + int ret; + + for (pair = ETHTOOL_A_CABLE_PAIR_A; pair <= ETHTOOL_A_CABLE_PAIR_D; pair++) { + ret = adin_cable_test_report_pair(phydev, pair); + if (ret < 0) + return ret; + } + + return 0; +} + +static int adin_cable_test_get_status(struct phy_device *phydev, + bool *finished) +{ + int ret; + + *finished = false; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND1, ADIN1300_CDIAG_RUN); + if (ret < 0) + return ret; + + if (ret & ADIN1300_CDIAG_RUN_EN) + return 0; + + *finished = true; + + return adin_cable_test_report(phydev); +} + static struct phy_driver adin_driver[] = { { PHY_ID_MATCH_MODEL(PHY_ID_ADIN1200), .name = "ADIN1200", + .flags = PHY_POLL_CABLE_TEST, .probe = adin_probe, .config_init = adin_config_init, .soft_reset = adin_soft_reset, @@ -745,10 +886,13 @@ static struct phy_driver adin_driver[] = { .suspend = genphy_suspend, .read_mmd = adin_read_mmd, .write_mmd = adin_write_mmd, + .cable_test_start = adin_cable_test_start, + .cable_test_get_status = adin_cable_test_get_status, }, { PHY_ID_MATCH_MODEL(PHY_ID_ADIN1300), .name = "ADIN1300", + .flags = PHY_POLL_CABLE_TEST, .probe = adin_probe, .config_init = adin_config_init, .soft_reset = adin_soft_reset, @@ -765,6 +909,8 @@ static struct phy_driver adin_driver[] = { .suspend = genphy_suspend, .read_mmd = adin_read_mmd, .write_mmd = adin_write_mmd, + .cable_test_start = adin_cable_test_start, + .cable_test_get_status = adin_cable_test_get_status, }, }; diff --git a/drivers/net/phy/aquantia_main.c b/drivers/net/phy/aquantia_main.c index 41e7c1432497..345f70f9d39b 100644 --- a/drivers/net/phy/aquantia_main.c +++ b/drivers/net/phy/aquantia_main.c @@ -52,6 +52,7 @@ #define MDIO_AN_TX_VEND_INT_STATUS1_DOWNSHIFT BIT(1) #define MDIO_AN_TX_VEND_INT_STATUS2 0xcc01 +#define MDIO_AN_TX_VEND_INT_STATUS2_MASK BIT(0) #define MDIO_AN_TX_VEND_INT_MASK2 0xd401 #define MDIO_AN_TX_VEND_INT_MASK2_LINK BIT(0) @@ -246,6 +247,13 @@ static int aqr_config_intr(struct phy_device *phydev) bool en = phydev->interrupts == PHY_INTERRUPT_ENABLED; int err; + if (en) { + /* Clear any pending interrupts before enabling them */ + err = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_TX_VEND_INT_STATUS2); + if (err) + return err; + } + err = phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_TX_VEND_INT_MASK2, en ? MDIO_AN_TX_VEND_INT_MASK2_LINK : 0); if (err < 0) @@ -256,18 +264,39 @@ static int aqr_config_intr(struct phy_device *phydev) if (err < 0) return err; - return phy_write_mmd(phydev, MDIO_MMD_VEND1, VEND1_GLOBAL_INT_VEND_MASK, - en ? VEND1_GLOBAL_INT_VEND_MASK_GLOBAL3 | - VEND1_GLOBAL_INT_VEND_MASK_AN : 0); + err = phy_write_mmd(phydev, MDIO_MMD_VEND1, VEND1_GLOBAL_INT_VEND_MASK, + en ? VEND1_GLOBAL_INT_VEND_MASK_GLOBAL3 | + VEND1_GLOBAL_INT_VEND_MASK_AN : 0); + if (err < 0) + return err; + + if (!en) { + /* Clear any pending interrupts after we have disabled them */ + err = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_TX_VEND_INT_STATUS2); + if (err) + return err; + } + + return 0; } -static int aqr_ack_interrupt(struct phy_device *phydev) +static irqreturn_t aqr_handle_interrupt(struct phy_device *phydev) { - int reg; + int irq_status; + + irq_status = phy_read_mmd(phydev, MDIO_MMD_AN, + MDIO_AN_TX_VEND_INT_STATUS2); + if (irq_status < 0) { + phy_error(phydev); + return IRQ_NONE; + } + + if (!(irq_status & MDIO_AN_TX_VEND_INT_STATUS2_MASK)) + return IRQ_NONE; + + phy_trigger_machine(phydev); - reg = phy_read_mmd(phydev, MDIO_MMD_AN, - MDIO_AN_TX_VEND_INT_STATUS2); - return (reg < 0) ? reg : 0; + return IRQ_HANDLED; } static int aqr_read_status(struct phy_device *phydev) @@ -584,7 +613,7 @@ static struct phy_driver aqr_driver[] = { .name = "Aquantia AQ1202", .config_aneg = aqr_config_aneg, .config_intr = aqr_config_intr, - .ack_interrupt = aqr_ack_interrupt, + .handle_interrupt = aqr_handle_interrupt, .read_status = aqr_read_status, }, { @@ -592,7 +621,7 @@ static struct phy_driver aqr_driver[] = { .name = "Aquantia AQ2104", .config_aneg = aqr_config_aneg, .config_intr = aqr_config_intr, - .ack_interrupt = aqr_ack_interrupt, + .handle_interrupt = aqr_handle_interrupt, .read_status = aqr_read_status, }, { @@ -600,7 +629,7 @@ static struct phy_driver aqr_driver[] = { .name = "Aquantia AQR105", .config_aneg = aqr_config_aneg, .config_intr = aqr_config_intr, - .ack_interrupt = aqr_ack_interrupt, + .handle_interrupt = aqr_handle_interrupt, .read_status = aqr_read_status, .suspend = aqr107_suspend, .resume = aqr107_resume, @@ -610,7 +639,7 @@ static struct phy_driver aqr_driver[] = { .name = "Aquantia AQR106", .config_aneg = aqr_config_aneg, .config_intr = aqr_config_intr, - .ack_interrupt = aqr_ack_interrupt, + .handle_interrupt = aqr_handle_interrupt, .read_status = aqr_read_status, }, { @@ -620,7 +649,7 @@ static struct phy_driver aqr_driver[] = { .config_init = aqr107_config_init, .config_aneg = aqr_config_aneg, .config_intr = aqr_config_intr, - .ack_interrupt = aqr_ack_interrupt, + .handle_interrupt = aqr_handle_interrupt, .read_status = aqr107_read_status, .get_tunable = aqr107_get_tunable, .set_tunable = aqr107_set_tunable, @@ -638,7 +667,7 @@ static struct phy_driver aqr_driver[] = { .config_init = aqcs109_config_init, .config_aneg = aqr_config_aneg, .config_intr = aqr_config_intr, - .ack_interrupt = aqr_ack_interrupt, + .handle_interrupt = aqr_handle_interrupt, .read_status = aqr107_read_status, .get_tunable = aqr107_get_tunable, .set_tunable = aqr107_set_tunable, @@ -654,7 +683,7 @@ static struct phy_driver aqr_driver[] = { .name = "Aquantia AQR405", .config_aneg = aqr_config_aneg, .config_intr = aqr_config_intr, - .ack_interrupt = aqr_ack_interrupt, + .handle_interrupt = aqr_handle_interrupt, .read_status = aqr_read_status, }, }; diff --git a/drivers/net/phy/at803x.c b/drivers/net/phy/at803x.c index ed601a7e46a0..d0b36fd6c265 100644 --- a/drivers/net/phy/at803x.c +++ b/drivers/net/phy/at803x.c @@ -614,6 +614,11 @@ static int at803x_config_intr(struct phy_device *phydev) value = phy_read(phydev, AT803X_INTR_ENABLE); if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { + /* Clear any pending interrupts */ + err = at803x_ack_interrupt(phydev); + if (err) + return err; + value |= AT803X_INTR_ENABLE_AUTONEG_ERR; value |= AT803X_INTR_ENABLE_SPEED_CHANGED; value |= AT803X_INTR_ENABLE_DUPLEX_CHANGED; @@ -621,13 +626,44 @@ static int at803x_config_intr(struct phy_device *phydev) value |= AT803X_INTR_ENABLE_LINK_SUCCESS; err = phy_write(phydev, AT803X_INTR_ENABLE, value); - } - else + } else { err = phy_write(phydev, AT803X_INTR_ENABLE, 0); + if (err) + return err; + + /* Clear any pending interrupts */ + err = at803x_ack_interrupt(phydev); + } return err; } +static irqreturn_t at803x_handle_interrupt(struct phy_device *phydev) +{ + int irq_status, int_enabled; + + irq_status = phy_read(phydev, AT803X_INTR_STATUS); + if (irq_status < 0) { + phy_error(phydev); + return IRQ_NONE; + } + + /* Read the current enabled interrupts */ + int_enabled = phy_read(phydev, AT803X_INTR_ENABLE); + if (int_enabled < 0) { + phy_error(phydev); + return IRQ_NONE; + } + + /* See if this was one of our enabled interrupts */ + if (!(irq_status & int_enabled)) + return IRQ_NONE; + + phy_trigger_machine(phydev); + + return IRQ_HANDLED; +} + static void at803x_link_change_notify(struct phy_device *phydev) { /* @@ -1062,8 +1098,8 @@ static struct phy_driver at803x_driver[] = { .resume = at803x_resume, /* PHY_GBIT_FEATURES */ .read_status = at803x_read_status, - .ack_interrupt = at803x_ack_interrupt, .config_intr = at803x_config_intr, + .handle_interrupt = at803x_handle_interrupt, .get_tunable = at803x_get_tunable, .set_tunable = at803x_set_tunable, .cable_test_start = at803x_cable_test_start, @@ -1082,8 +1118,8 @@ static struct phy_driver at803x_driver[] = { .suspend = at803x_suspend, .resume = at803x_resume, /* PHY_BASIC_FEATURES */ - .ack_interrupt = at803x_ack_interrupt, .config_intr = at803x_config_intr, + .handle_interrupt = at803x_handle_interrupt, }, { /* Qualcomm Atheros AR8031/AR8033 */ PHY_ID_MATCH_EXACT(ATH8031_PHY_ID), @@ -1100,8 +1136,8 @@ static struct phy_driver at803x_driver[] = { /* PHY_GBIT_FEATURES */ .read_status = at803x_read_status, .aneg_done = at803x_aneg_done, - .ack_interrupt = &at803x_ack_interrupt, .config_intr = &at803x_config_intr, + .handle_interrupt = at803x_handle_interrupt, .get_tunable = at803x_get_tunable, .set_tunable = at803x_set_tunable, .cable_test_start = at803x_cable_test_start, @@ -1120,8 +1156,8 @@ static struct phy_driver at803x_driver[] = { .suspend = at803x_suspend, .resume = at803x_resume, /* PHY_BASIC_FEATURES */ - .ack_interrupt = at803x_ack_interrupt, .config_intr = at803x_config_intr, + .handle_interrupt = at803x_handle_interrupt, .cable_test_start = at803x_cable_test_start, .cable_test_get_status = at803x_cable_test_get_status, }, { @@ -1132,8 +1168,8 @@ static struct phy_driver at803x_driver[] = { .resume = at803x_resume, .flags = PHY_POLL_CABLE_TEST, /* PHY_BASIC_FEATURES */ - .ack_interrupt = &at803x_ack_interrupt, .config_intr = &at803x_config_intr, + .handle_interrupt = at803x_handle_interrupt, .cable_test_start = at803x_cable_test_start, .cable_test_get_status = at803x_cable_test_get_status, .read_status = at803x_read_status, diff --git a/drivers/net/phy/bcm-cygnus.c b/drivers/net/phy/bcm-cygnus.c index 9ccf28b0a04d..da8f7cb41b44 100644 --- a/drivers/net/phy/bcm-cygnus.c +++ b/drivers/net/phy/bcm-cygnus.c @@ -256,8 +256,8 @@ static struct phy_driver bcm_cygnus_phy_driver[] = { .name = "Broadcom Cygnus PHY", /* PHY_GBIT_FEATURES */ .config_init = bcm_cygnus_config_init, - .ack_interrupt = bcm_phy_ack_intr, .config_intr = bcm_phy_config_intr, + .handle_interrupt = bcm_phy_handle_interrupt, .suspend = genphy_suspend, .resume = bcm_cygnus_resume, }, { diff --git a/drivers/net/phy/bcm-phy-lib.c b/drivers/net/phy/bcm-phy-lib.c index ef6825b30323..53282a6d5928 100644 --- a/drivers/net/phy/bcm-phy-lib.c +++ b/drivers/net/phy/bcm-phy-lib.c @@ -181,21 +181,62 @@ EXPORT_SYMBOL_GPL(bcm_phy_ack_intr); int bcm_phy_config_intr(struct phy_device *phydev) { - int reg; + int reg, err; reg = phy_read(phydev, MII_BCM54XX_ECR); if (reg < 0) return reg; - if (phydev->interrupts == PHY_INTERRUPT_ENABLED) + if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { + err = bcm_phy_ack_intr(phydev); + if (err) + return err; + reg &= ~MII_BCM54XX_ECR_IM; - else + err = phy_write(phydev, MII_BCM54XX_ECR, reg); + } else { reg |= MII_BCM54XX_ECR_IM; + err = phy_write(phydev, MII_BCM54XX_ECR, reg); + if (err) + return err; - return phy_write(phydev, MII_BCM54XX_ECR, reg); + err = bcm_phy_ack_intr(phydev); + } + return err; } EXPORT_SYMBOL_GPL(bcm_phy_config_intr); +irqreturn_t bcm_phy_handle_interrupt(struct phy_device *phydev) +{ + int irq_status, irq_mask; + + irq_status = phy_read(phydev, MII_BCM54XX_ISR); + if (irq_status < 0) { + phy_error(phydev); + return IRQ_NONE; + } + + /* If a bit from the Interrupt Mask register is set, the corresponding + * bit from the Interrupt Status register is masked. So read the IMR + * and then flip the bits to get the list of possible interrupt + * sources. + */ + irq_mask = phy_read(phydev, MII_BCM54XX_IMR); + if (irq_mask < 0) { + phy_error(phydev); + return IRQ_NONE; + } + irq_mask = ~irq_mask; + + if (!(irq_status & irq_mask)) + return IRQ_NONE; + + phy_trigger_machine(phydev); + + return IRQ_HANDLED; +} +EXPORT_SYMBOL_GPL(bcm_phy_handle_interrupt); + int bcm_phy_read_shadow(struct phy_device *phydev, u16 shadow) { phy_write(phydev, MII_BCM54XX_SHD, MII_BCM54XX_SHD_VAL(shadow)); diff --git a/drivers/net/phy/bcm-phy-lib.h b/drivers/net/phy/bcm-phy-lib.h index 237a8503c9b4..c3842f87c33b 100644 --- a/drivers/net/phy/bcm-phy-lib.h +++ b/drivers/net/phy/bcm-phy-lib.h @@ -63,6 +63,7 @@ int bcm_phy_modify_rdb(struct phy_device *phydev, u16 rdb, u16 mask, int bcm_phy_ack_intr(struct phy_device *phydev); int bcm_phy_config_intr(struct phy_device *phydev); +irqreturn_t bcm_phy_handle_interrupt(struct phy_device *phydev); int bcm_phy_enable_apd(struct phy_device *phydev, bool dll_pwr_down); diff --git a/drivers/net/phy/bcm54140.c b/drivers/net/phy/bcm54140.c index 8998e68bb26b..d8f3024860dc 100644 --- a/drivers/net/phy/bcm54140.c +++ b/drivers/net/phy/bcm54140.c @@ -637,13 +637,29 @@ static int bcm54140_config_init(struct phy_device *phydev) BCM54140_RDB_C_PWR_ISOLATE, 0); } -static int bcm54140_did_interrupt(struct phy_device *phydev) +static irqreturn_t bcm54140_handle_interrupt(struct phy_device *phydev) { - int ret; + int irq_status, irq_mask; + + irq_status = bcm_phy_read_rdb(phydev, BCM54140_RDB_ISR); + if (irq_status < 0) { + phy_error(phydev); + return IRQ_NONE; + } + + irq_mask = bcm_phy_read_rdb(phydev, BCM54140_RDB_IMR); + if (irq_mask < 0) { + phy_error(phydev); + return IRQ_NONE; + } + irq_mask = ~irq_mask; + + if (!(irq_status & irq_mask)) + return IRQ_NONE; - ret = bcm_phy_read_rdb(phydev, BCM54140_RDB_ISR); + phy_trigger_machine(phydev); - return (ret < 0) ? 0 : ret; + return IRQ_HANDLED; } static int bcm54140_ack_intr(struct phy_device *phydev) @@ -665,7 +681,7 @@ static int bcm54140_config_intr(struct phy_device *phydev) BCM54140_RDB_TOP_IMR_PORT0, BCM54140_RDB_TOP_IMR_PORT1, BCM54140_RDB_TOP_IMR_PORT2, BCM54140_RDB_TOP_IMR_PORT3, }; - int reg; + int reg, err; if (priv->port >= ARRAY_SIZE(port_to_imr_bit)) return -EINVAL; @@ -674,12 +690,23 @@ static int bcm54140_config_intr(struct phy_device *phydev) if (reg < 0) return reg; - if (phydev->interrupts == PHY_INTERRUPT_ENABLED) + if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { + err = bcm54140_ack_intr(phydev); + if (err) + return err; + reg &= ~port_to_imr_bit[priv->port]; - else + err = bcm54140_base_write_rdb(phydev, BCM54140_RDB_TOP_IMR, reg); + } else { reg |= port_to_imr_bit[priv->port]; + err = bcm54140_base_write_rdb(phydev, BCM54140_RDB_TOP_IMR, reg); + if (err) + return err; + + err = bcm54140_ack_intr(phydev); + } - return bcm54140_base_write_rdb(phydev, BCM54140_RDB_TOP_IMR, reg); + return err; } static int bcm54140_get_downshift(struct phy_device *phydev, u8 *data) @@ -834,8 +861,7 @@ static struct phy_driver bcm54140_drivers[] = { .flags = PHY_POLL_CABLE_TEST, .features = PHY_GBIT_FEATURES, .config_init = bcm54140_config_init, - .did_interrupt = bcm54140_did_interrupt, - .ack_interrupt = bcm54140_ack_intr, + .handle_interrupt = bcm54140_handle_interrupt, .config_intr = bcm54140_config_intr, .probe = bcm54140_probe, .suspend = genphy_suspend, diff --git a/drivers/net/phy/bcm63xx.c b/drivers/net/phy/bcm63xx.c index 459fb2069c7e..0eb33be824f1 100644 --- a/drivers/net/phy/bcm63xx.c +++ b/drivers/net/phy/bcm63xx.c @@ -25,12 +25,22 @@ static int bcm63xx_config_intr(struct phy_device *phydev) if (reg < 0) return reg; - if (phydev->interrupts == PHY_INTERRUPT_ENABLED) + if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { + err = bcm_phy_ack_intr(phydev); + if (err) + return err; + reg &= ~MII_BCM63XX_IR_GMASK; - else + err = phy_write(phydev, MII_BCM63XX_IR, reg); + } else { reg |= MII_BCM63XX_IR_GMASK; + err = phy_write(phydev, MII_BCM63XX_IR, reg); + if (err) + return err; + + err = bcm_phy_ack_intr(phydev); + } - err = phy_write(phydev, MII_BCM63XX_IR, reg); return err; } @@ -67,8 +77,8 @@ static struct phy_driver bcm63xx_driver[] = { /* PHY_BASIC_FEATURES */ .flags = PHY_IS_INTERNAL, .config_init = bcm63xx_config_init, - .ack_interrupt = bcm_phy_ack_intr, .config_intr = bcm63xx_config_intr, + .handle_interrupt = bcm_phy_handle_interrupt, }, { /* same phy as above, with just a different OUI */ .phy_id = 0x002bdc00, @@ -77,8 +87,8 @@ static struct phy_driver bcm63xx_driver[] = { /* PHY_BASIC_FEATURES */ .flags = PHY_IS_INTERNAL, .config_init = bcm63xx_config_init, - .ack_interrupt = bcm_phy_ack_intr, .config_intr = bcm63xx_config_intr, + .handle_interrupt = bcm_phy_handle_interrupt, } }; module_phy_driver(bcm63xx_driver); diff --git a/drivers/net/phy/bcm87xx.c b/drivers/net/phy/bcm87xx.c index df360e1c5069..4ac8fd190e9d 100644 --- a/drivers/net/phy/bcm87xx.c +++ b/drivers/net/phy/bcm87xx.c @@ -144,35 +144,41 @@ static int bcm87xx_config_intr(struct phy_device *phydev) if (reg < 0) return reg; - if (phydev->interrupts == PHY_INTERRUPT_ENABLED) + if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { + err = phy_read(phydev, BCM87XX_LASI_STATUS); + if (err) + return err; + reg |= 1; - else + err = phy_write(phydev, BCM87XX_LASI_CONTROL, reg); + } else { reg &= ~1; + err = phy_write(phydev, BCM87XX_LASI_CONTROL, reg); + if (err) + return err; + + err = phy_read(phydev, BCM87XX_LASI_STATUS); + } - err = phy_write(phydev, BCM87XX_LASI_CONTROL, reg); return err; } -static int bcm87xx_did_interrupt(struct phy_device *phydev) +static irqreturn_t bcm87xx_handle_interrupt(struct phy_device *phydev) { - int reg; + int irq_status; - reg = phy_read(phydev, BCM87XX_LASI_STATUS); - - if (reg < 0) { - phydev_err(phydev, - "Error: Read of BCM87XX_LASI_STATUS failed: %d\n", - reg); - return 0; + irq_status = phy_read(phydev, BCM87XX_LASI_STATUS); + if (irq_status < 0) { + phy_error(phydev); + return IRQ_NONE; } - return (reg & 1) != 0; -} -static int bcm87xx_ack_interrupt(struct phy_device *phydev) -{ - /* Reading the LASI status clears it. */ - bcm87xx_did_interrupt(phydev); - return 0; + if (irq_status == 0) + return IRQ_NONE; + + phy_trigger_machine(phydev); + + return IRQ_HANDLED; } static int bcm8706_match_phy_device(struct phy_device *phydev) @@ -194,9 +200,8 @@ static struct phy_driver bcm87xx_driver[] = { .config_init = bcm87xx_config_init, .config_aneg = bcm87xx_config_aneg, .read_status = bcm87xx_read_status, - .ack_interrupt = bcm87xx_ack_interrupt, .config_intr = bcm87xx_config_intr, - .did_interrupt = bcm87xx_did_interrupt, + .handle_interrupt = bcm87xx_handle_interrupt, .match_phy_device = bcm8706_match_phy_device, }, { .phy_id = PHY_ID_BCM8727, @@ -206,9 +211,8 @@ static struct phy_driver bcm87xx_driver[] = { .config_init = bcm87xx_config_init, .config_aneg = bcm87xx_config_aneg, .read_status = bcm87xx_read_status, - .ack_interrupt = bcm87xx_ack_interrupt, .config_intr = bcm87xx_config_intr, - .did_interrupt = bcm87xx_did_interrupt, + .handle_interrupt = bcm87xx_handle_interrupt, .match_phy_device = bcm8727_match_phy_device, } }; diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index cd271de9609b..8a4ec3222168 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -634,15 +634,43 @@ static int brcm_fet_config_intr(struct phy_device *phydev) if (reg < 0) return reg; - if (phydev->interrupts == PHY_INTERRUPT_ENABLED) + if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { + err = brcm_fet_ack_interrupt(phydev); + if (err) + return err; + reg &= ~MII_BRCM_FET_IR_MASK; - else + err = phy_write(phydev, MII_BRCM_FET_INTREG, reg); + } else { reg |= MII_BRCM_FET_IR_MASK; + err = phy_write(phydev, MII_BRCM_FET_INTREG, reg); + if (err) + return err; + + err = brcm_fet_ack_interrupt(phydev); + } - err = phy_write(phydev, MII_BRCM_FET_INTREG, reg); return err; } +static irqreturn_t brcm_fet_handle_interrupt(struct phy_device *phydev) +{ + int irq_status; + + irq_status = phy_read(phydev, MII_BRCM_FET_INTREG); + if (irq_status < 0) { + phy_error(phydev); + return IRQ_NONE; + } + + if (irq_status == 0) + return IRQ_NONE; + + phy_trigger_machine(phydev); + + return IRQ_HANDLED; +} + struct bcm53xx_phy_priv { u64 *stats; }; @@ -681,40 +709,40 @@ static struct phy_driver broadcom_drivers[] = { .name = "Broadcom BCM5411", /* PHY_GBIT_FEATURES */ .config_init = bcm54xx_config_init, - .ack_interrupt = bcm_phy_ack_intr, .config_intr = bcm_phy_config_intr, + .handle_interrupt = bcm_phy_handle_interrupt, }, { .phy_id = PHY_ID_BCM5421, .phy_id_mask = 0xfffffff0, .name = "Broadcom BCM5421", /* PHY_GBIT_FEATURES */ .config_init = bcm54xx_config_init, - .ack_interrupt = bcm_phy_ack_intr, .config_intr = bcm_phy_config_intr, + .handle_interrupt = bcm_phy_handle_interrupt, }, { .phy_id = PHY_ID_BCM54210E, .phy_id_mask = 0xfffffff0, .name = "Broadcom BCM54210E", /* PHY_GBIT_FEATURES */ .config_init = bcm54xx_config_init, - .ack_interrupt = bcm_phy_ack_intr, .config_intr = bcm_phy_config_intr, + .handle_interrupt = bcm_phy_handle_interrupt, }, { .phy_id = PHY_ID_BCM5461, .phy_id_mask = 0xfffffff0, .name = "Broadcom BCM5461", /* PHY_GBIT_FEATURES */ .config_init = bcm54xx_config_init, - .ack_interrupt = bcm_phy_ack_intr, .config_intr = bcm_phy_config_intr, + .handle_interrupt = bcm_phy_handle_interrupt, }, { .phy_id = PHY_ID_BCM54612E, .phy_id_mask = 0xfffffff0, .name = "Broadcom BCM54612E", /* PHY_GBIT_FEATURES */ .config_init = bcm54xx_config_init, - .ack_interrupt = bcm_phy_ack_intr, .config_intr = bcm_phy_config_intr, + .handle_interrupt = bcm_phy_handle_interrupt, }, { .phy_id = PHY_ID_BCM54616S, .phy_id_mask = 0xfffffff0, @@ -722,8 +750,8 @@ static struct phy_driver broadcom_drivers[] = { /* PHY_GBIT_FEATURES */ .config_init = bcm54xx_config_init, .config_aneg = bcm54616s_config_aneg, - .ack_interrupt = bcm_phy_ack_intr, .config_intr = bcm_phy_config_intr, + .handle_interrupt = bcm_phy_handle_interrupt, .read_status = bcm54616s_read_status, .probe = bcm54616s_probe, }, { @@ -732,8 +760,8 @@ static struct phy_driver broadcom_drivers[] = { .name = "Broadcom BCM5464", /* PHY_GBIT_FEATURES */ .config_init = bcm54xx_config_init, - .ack_interrupt = bcm_phy_ack_intr, .config_intr = bcm_phy_config_intr, + .handle_interrupt = bcm_phy_handle_interrupt, .suspend = genphy_suspend, .resume = genphy_resume, }, { @@ -743,8 +771,8 @@ static struct phy_driver broadcom_drivers[] = { /* PHY_GBIT_FEATURES */ .config_init = bcm54xx_config_init, .config_aneg = bcm5481_config_aneg, - .ack_interrupt = bcm_phy_ack_intr, .config_intr = bcm_phy_config_intr, + .handle_interrupt = bcm_phy_handle_interrupt, }, { .phy_id = PHY_ID_BCM54810, .phy_id_mask = 0xfffffff0, @@ -752,8 +780,8 @@ static struct phy_driver broadcom_drivers[] = { /* PHY_GBIT_FEATURES */ .config_init = bcm54xx_config_init, .config_aneg = bcm5481_config_aneg, - .ack_interrupt = bcm_phy_ack_intr, .config_intr = bcm_phy_config_intr, + .handle_interrupt = bcm_phy_handle_interrupt, .suspend = genphy_suspend, .resume = bcm54xx_resume, }, { @@ -763,8 +791,8 @@ static struct phy_driver broadcom_drivers[] = { /* PHY_GBIT_FEATURES */ .config_init = bcm54811_config_init, .config_aneg = bcm5481_config_aneg, - .ack_interrupt = bcm_phy_ack_intr, .config_intr = bcm_phy_config_intr, + .handle_interrupt = bcm_phy_handle_interrupt, .suspend = genphy_suspend, .resume = bcm54xx_resume, }, { @@ -774,48 +802,48 @@ static struct phy_driver broadcom_drivers[] = { /* PHY_GBIT_FEATURES */ .config_init = bcm5482_config_init, .read_status = bcm5482_read_status, - .ack_interrupt = bcm_phy_ack_intr, .config_intr = bcm_phy_config_intr, + .handle_interrupt = bcm_phy_handle_interrupt, }, { .phy_id = PHY_ID_BCM50610, .phy_id_mask = 0xfffffff0, .name = "Broadcom BCM50610", /* PHY_GBIT_FEATURES */ .config_init = bcm54xx_config_init, - .ack_interrupt = bcm_phy_ack_intr, .config_intr = bcm_phy_config_intr, + .handle_interrupt = bcm_phy_handle_interrupt, }, { .phy_id = PHY_ID_BCM50610M, .phy_id_mask = 0xfffffff0, .name = "Broadcom BCM50610M", /* PHY_GBIT_FEATURES */ .config_init = bcm54xx_config_init, - .ack_interrupt = bcm_phy_ack_intr, .config_intr = bcm_phy_config_intr, + .handle_interrupt = bcm_phy_handle_interrupt, }, { .phy_id = PHY_ID_BCM57780, .phy_id_mask = 0xfffffff0, .name = "Broadcom BCM57780", /* PHY_GBIT_FEATURES */ .config_init = bcm54xx_config_init, - .ack_interrupt = bcm_phy_ack_intr, .config_intr = bcm_phy_config_intr, + .handle_interrupt = bcm_phy_handle_interrupt, }, { .phy_id = PHY_ID_BCMAC131, .phy_id_mask = 0xfffffff0, .name = "Broadcom BCMAC131", /* PHY_BASIC_FEATURES */ .config_init = brcm_fet_config_init, - .ack_interrupt = brcm_fet_ack_interrupt, .config_intr = brcm_fet_config_intr, + .handle_interrupt = brcm_fet_handle_interrupt, }, { .phy_id = PHY_ID_BCM5241, .phy_id_mask = 0xfffffff0, .name = "Broadcom BCM5241", /* PHY_BASIC_FEATURES */ .config_init = brcm_fet_config_init, - .ack_interrupt = brcm_fet_ack_interrupt, .config_intr = brcm_fet_config_intr, + .handle_interrupt = brcm_fet_handle_interrupt, }, { .phy_id = PHY_ID_BCM5395, .phy_id_mask = 0xfffffff0, @@ -837,16 +865,16 @@ static struct phy_driver broadcom_drivers[] = { .get_stats = bcm53xx_phy_get_stats, .probe = bcm53xx_phy_probe, .config_init = bcm54xx_config_init, - .ack_interrupt = bcm_phy_ack_intr, .config_intr = bcm_phy_config_intr, + .handle_interrupt = bcm_phy_handle_interrupt, }, { .phy_id = PHY_ID_BCM89610, .phy_id_mask = 0xfffffff0, .name = "Broadcom BCM89610", /* PHY_GBIT_FEATURES */ .config_init = bcm54xx_config_init, - .ack_interrupt = bcm_phy_ack_intr, .config_intr = bcm_phy_config_intr, + .handle_interrupt = bcm_phy_handle_interrupt, } }; module_phy_driver(broadcom_drivers); diff --git a/drivers/net/phy/cicada.c b/drivers/net/phy/cicada.c index 9d1612a4d7e6..ef5f412e101f 100644 --- a/drivers/net/phy/cicada.c +++ b/drivers/net/phy/cicada.c @@ -87,15 +87,42 @@ static int cis820x_config_intr(struct phy_device *phydev) { int err; - if (phydev->interrupts == PHY_INTERRUPT_ENABLED) + if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { + err = cis820x_ack_interrupt(phydev); + if (err) + return err; + err = phy_write(phydev, MII_CIS8201_IMASK, MII_CIS8201_IMASK_MASK); - else + } else { err = phy_write(phydev, MII_CIS8201_IMASK, 0); + if (err) + return err; + + err = cis820x_ack_interrupt(phydev); + } return err; } +static irqreturn_t cis820x_handle_interrupt(struct phy_device *phydev) +{ + int irq_status; + + irq_status = phy_read(phydev, MII_CIS8201_ISTAT); + if (irq_status < 0) { + phy_error(phydev); + return IRQ_NONE; + } + + if (!(irq_status & MII_CIS8201_IMASK_MASK)) + return IRQ_NONE; + + phy_trigger_machine(phydev); + + return IRQ_HANDLED; +} + /* Cicada 8201, a.k.a Vitesse VSC8201 */ static struct phy_driver cis820x_driver[] = { { @@ -104,16 +131,16 @@ static struct phy_driver cis820x_driver[] = { .phy_id_mask = 0x000ffff0, /* PHY_GBIT_FEATURES */ .config_init = &cis820x_config_init, - .ack_interrupt = &cis820x_ack_interrupt, .config_intr = &cis820x_config_intr, + .handle_interrupt = &cis820x_handle_interrupt, }, { .phy_id = 0x000fc440, .name = "Cicada Cis8204", .phy_id_mask = 0x000fffc0, /* PHY_GBIT_FEATURES */ .config_init = &cis820x_config_init, - .ack_interrupt = &cis820x_ack_interrupt, .config_intr = &cis820x_config_intr, + .handle_interrupt = &cis820x_handle_interrupt, } }; module_phy_driver(cis820x_driver); diff --git a/drivers/net/phy/davicom.c b/drivers/net/phy/davicom.c index 942f277463a4..a3b3842c67e5 100644 --- a/drivers/net/phy/davicom.c +++ b/drivers/net/phy/davicom.c @@ -47,6 +47,10 @@ #define MII_DM9161_INTR_STOP \ (MII_DM9161_INTR_DPLX_MASK | MII_DM9161_INTR_SPD_MASK \ | MII_DM9161_INTR_LINK_MASK | MII_DM9161_INTR_MASK) +#define MII_DM9161_INTR_CHANGE \ + (MII_DM9161_INTR_DPLX_CHANGE | \ + MII_DM9161_INTR_SPD_CHANGE | \ + MII_DM9161_INTR_LINK_CHANGE) /* DM9161 10BT Configuration/Status */ #define MII_DM9161_10BTCSR 0x12 @@ -57,24 +61,58 @@ MODULE_AUTHOR("Andy Fleming"); MODULE_LICENSE("GPL"); +static int dm9161_ack_interrupt(struct phy_device *phydev) +{ + int err = phy_read(phydev, MII_DM9161_INTR); + + return (err < 0) ? err : 0; +} + #define DM9161_DELAY 1 static int dm9161_config_intr(struct phy_device *phydev) { - int temp; + int temp, err; temp = phy_read(phydev, MII_DM9161_INTR); if (temp < 0) return temp; - if (PHY_INTERRUPT_ENABLED == phydev->interrupts) + if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { + err = dm9161_ack_interrupt(phydev); + if (err) + return err; + temp &= ~(MII_DM9161_INTR_STOP); - else + err = phy_write(phydev, MII_DM9161_INTR, temp); + } else { temp |= MII_DM9161_INTR_STOP; + err = phy_write(phydev, MII_DM9161_INTR, temp); + if (err) + return err; + + err = dm9161_ack_interrupt(phydev); + } + + return err; +} - temp = phy_write(phydev, MII_DM9161_INTR, temp); +static irqreturn_t dm9161_handle_interrupt(struct phy_device *phydev) +{ + int irq_status; + + irq_status = phy_read(phydev, MII_DM9161_INTR); + if (irq_status < 0) { + phy_error(phydev); + return IRQ_NONE; + } - return temp; + if (!(irq_status & MII_DM9161_INTR_CHANGE)) + return IRQ_NONE; + + phy_trigger_machine(phydev); + + return IRQ_HANDLED; } static int dm9161_config_aneg(struct phy_device *phydev) @@ -132,13 +170,6 @@ static int dm9161_config_init(struct phy_device *phydev) return phy_write(phydev, MII_BMCR, BMCR_ANENABLE); } -static int dm9161_ack_interrupt(struct phy_device *phydev) -{ - int err = phy_read(phydev, MII_DM9161_INTR); - - return (err < 0) ? err : 0; -} - static struct phy_driver dm91xx_driver[] = { { .phy_id = 0x0181b880, @@ -147,8 +178,8 @@ static struct phy_driver dm91xx_driver[] = { /* PHY_BASIC_FEATURES */ .config_init = dm9161_config_init, .config_aneg = dm9161_config_aneg, - .ack_interrupt = dm9161_ack_interrupt, .config_intr = dm9161_config_intr, + .handle_interrupt = dm9161_handle_interrupt, }, { .phy_id = 0x0181b8b0, .name = "Davicom DM9161B/C", @@ -156,8 +187,8 @@ static struct phy_driver dm91xx_driver[] = { /* PHY_BASIC_FEATURES */ .config_init = dm9161_config_init, .config_aneg = dm9161_config_aneg, - .ack_interrupt = dm9161_ack_interrupt, .config_intr = dm9161_config_intr, + .handle_interrupt = dm9161_handle_interrupt, }, { .phy_id = 0x0181b8a0, .name = "Davicom DM9161A", @@ -165,15 +196,15 @@ static struct phy_driver dm91xx_driver[] = { /* PHY_BASIC_FEATURES */ .config_init = dm9161_config_init, .config_aneg = dm9161_config_aneg, - .ack_interrupt = dm9161_ack_interrupt, .config_intr = dm9161_config_intr, + .handle_interrupt = dm9161_handle_interrupt, }, { .phy_id = 0x00181b80, .name = "Davicom DM9131", .phy_id_mask = 0x0ffffff0, /* PHY_BASIC_FEATURES */ - .ack_interrupt = dm9161_ack_interrupt, .config_intr = dm9161_config_intr, + .handle_interrupt = dm9161_handle_interrupt, } }; module_phy_driver(dm91xx_driver); diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 5aec673a0120..2563526bf4a6 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -80,8 +80,11 @@ #define MII_M1111_HWCFG_MODE_FIBER_RGMII 0x3 #define MII_M1111_HWCFG_MODE_SGMII_NO_CLK 0x4 #define MII_M1111_HWCFG_MODE_RTBI 0x7 +#define MII_M1111_HWCFG_MODE_COPPER_1000X_AN 0x8 #define MII_M1111_HWCFG_MODE_COPPER_RTBI 0x9 #define MII_M1111_HWCFG_MODE_COPPER_RGMII 0xb +#define MII_M1111_HWCFG_MODE_COPPER_1000X_NOAN 0xc +#define MII_M1111_HWCFG_SERIAL_AN_BYPASS BIT(12) #define MII_M1111_HWCFG_FIBER_COPPER_RES BIT(13) #define MII_M1111_HWCFG_FIBER_COPPER_AUTO BIT(15) @@ -629,6 +632,51 @@ static int marvell_config_aneg_fiber(struct phy_device *phydev) return genphy_check_and_restart_aneg(phydev, changed); } +static int m88e1111_config_aneg(struct phy_device *phydev) +{ + int extsr = phy_read(phydev, MII_M1111_PHY_EXT_SR); + int err; + + if (extsr < 0) + return extsr; + + /* If not using SGMII or copper 1000BaseX modes, use normal process. + * Steps below are only required for these modes. + */ + if (phydev->interface != PHY_INTERFACE_MODE_SGMII && + (extsr & MII_M1111_HWCFG_MODE_MASK) != + MII_M1111_HWCFG_MODE_COPPER_1000X_AN) + return marvell_config_aneg(phydev); + + err = marvell_set_page(phydev, MII_MARVELL_COPPER_PAGE); + if (err < 0) + goto error; + + /* Configure the copper link first */ + err = marvell_config_aneg(phydev); + if (err < 0) + goto error; + + /* Do not touch the fiber page if we're in copper->sgmii mode */ + if (phydev->interface == PHY_INTERFACE_MODE_SGMII) + return 0; + + /* Then the fiber link */ + err = marvell_set_page(phydev, MII_MARVELL_FIBER_PAGE); + if (err < 0) + goto error; + + err = marvell_config_aneg_fiber(phydev); + if (err < 0) + goto error; + + return marvell_set_page(phydev, MII_MARVELL_COPPER_PAGE); + +error: + marvell_set_page(phydev, MII_MARVELL_COPPER_PAGE); + return err; +} + static int m88e1510_config_aneg(struct phy_device *phydev) { int err; @@ -696,7 +744,7 @@ static void marvell_config_led(struct phy_device *phydev) static int marvell_config_init(struct phy_device *phydev) { - /* Set defalut LED */ + /* Set default LED */ marvell_config_led(phydev); /* Set registers from marvell,reg-init DT property */ @@ -814,6 +862,28 @@ static int m88e1111_config_init_rtbi(struct phy_device *phydev) MII_M1111_HWCFG_FIBER_COPPER_AUTO); } +static int m88e1111_config_init_1000basex(struct phy_device *phydev) +{ + int extsr = phy_read(phydev, MII_M1111_PHY_EXT_SR); + int err, mode; + + if (extsr < 0) + return extsr; + + /* If using copper mode, ensure 1000BaseX auto-negotiation is enabled */ + mode = extsr & MII_M1111_HWCFG_MODE_MASK; + if (mode == MII_M1111_HWCFG_MODE_COPPER_1000X_NOAN) { + err = phy_modify(phydev, MII_M1111_PHY_EXT_SR, + MII_M1111_HWCFG_MODE_MASK | + MII_M1111_HWCFG_SERIAL_AN_BYPASS, + MII_M1111_HWCFG_MODE_COPPER_1000X_AN | + MII_M1111_HWCFG_SERIAL_AN_BYPASS); + if (err < 0) + return err; + } + return 0; +} + static int m88e1111_config_init(struct phy_device *phydev) { int err; @@ -836,6 +906,12 @@ static int m88e1111_config_init(struct phy_device *phydev) return err; } + if (phydev->interface == PHY_INTERFACE_MODE_1000BASEX) { + err = m88e1111_config_init_1000basex(phydev); + if (err < 0) + return err; + } + err = marvell_of_reg_init(phydev); if (err < 0) return err; @@ -2658,7 +2734,28 @@ static struct phy_driver marvell_drivers[] = { /* PHY_GBIT_FEATURES */ .probe = marvell_probe, .config_init = m88e1111_config_init, - .config_aneg = marvell_config_aneg, + .config_aneg = m88e1111_config_aneg, + .read_status = marvell_read_status, + .ack_interrupt = marvell_ack_interrupt, + .config_intr = marvell_config_intr, + .resume = genphy_resume, + .suspend = genphy_suspend, + .read_page = marvell_read_page, + .write_page = marvell_write_page, + .get_sset_count = marvell_get_sset_count, + .get_strings = marvell_get_strings, + .get_stats = marvell_get_stats, + .get_tunable = m88e1111_get_tunable, + .set_tunable = m88e1111_set_tunable, + }, + { + .phy_id = MARVELL_PHY_ID_88E1111_FINISAR, + .phy_id_mask = MARVELL_PHY_ID_MASK, + .name = "Marvell 88E1111 (Finisar)", + /* PHY_GBIT_FEATURES */ + .probe = marvell_probe, + .config_init = m88e1111_config_init, + .config_aneg = m88e1111_config_aneg, .read_status = marvell_read_status, .ack_interrupt = marvell_ack_interrupt, .config_intr = marvell_config_intr, @@ -2989,6 +3086,7 @@ static struct mdio_device_id __maybe_unused marvell_tbl[] = { { MARVELL_PHY_ID_88E1101, MARVELL_PHY_ID_MASK }, { MARVELL_PHY_ID_88E1112, MARVELL_PHY_ID_MASK }, { MARVELL_PHY_ID_88E1111, MARVELL_PHY_ID_MASK }, + { MARVELL_PHY_ID_88E1111_FINISAR, MARVELL_PHY_ID_MASK }, { MARVELL_PHY_ID_88E1118, MARVELL_PHY_ID_MASK }, { MARVELL_PHY_ID_88E1121R, MARVELL_PHY_ID_MASK }, { MARVELL_PHY_ID_88E1145, MARVELL_PHY_ID_MASK }, diff --git a/drivers/net/phy/mscc/mscc_main.c b/drivers/net/phy/mscc/mscc_main.c index 6bc7406a1ce7..2f2157e3deab 100644 --- a/drivers/net/phy/mscc/mscc_main.c +++ b/drivers/net/phy/mscc/mscc_main.c @@ -1498,7 +1498,7 @@ static irqreturn_t vsc8584_handle_interrupt(struct phy_device *phydev) vsc8584_handle_macsec_interrupt(phydev); if (irq_status & MII_VSC85XX_INT_MASK_LINK_CHG) - phy_mac_interrupt(phydev); + phy_trigger_machine(phydev); return IRQ_HANDLED; } @@ -1541,16 +1541,6 @@ static int vsc85xx_config_init(struct phy_device *phydev) return 0; } -static int vsc8584_did_interrupt(struct phy_device *phydev) -{ - int rc = 0; - - if (phydev->interrupts == PHY_INTERRUPT_ENABLED) - rc = phy_read(phydev, MII_VSC85XX_INT_STATUS); - - return (rc < 0) ? 0 : rc & MII_VSC85XX_INT_MASK_MASK; -} - static int vsc8514_config_pre_init(struct phy_device *phydev) { /* These are the settings to override the silicon default @@ -1933,6 +1923,10 @@ static int vsc85xx_config_intr(struct phy_device *phydev) int rc; if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { + rc = vsc85xx_ack_interrupt(phydev); + if (rc) + return rc; + vsc8584_config_macsec_intr(phydev); vsc8584_config_ts_intr(phydev); @@ -1943,11 +1937,33 @@ static int vsc85xx_config_intr(struct phy_device *phydev) if (rc < 0) return rc; rc = phy_read(phydev, MII_VSC85XX_INT_STATUS); + if (rc < 0) + return rc; + + rc = vsc85xx_ack_interrupt(phydev); } return rc; } +static irqreturn_t vsc85xx_handle_interrupt(struct phy_device *phydev) +{ + int irq_status; + + irq_status = phy_read(phydev, MII_VSC85XX_INT_STATUS); + if (irq_status < 0) { + phy_error(phydev); + return IRQ_NONE; + } + + if (!(irq_status & MII_VSC85XX_INT_MASK_MASK)) + return IRQ_NONE; + + phy_trigger_machine(phydev); + + return IRQ_HANDLED; +} + static int vsc85xx_config_aneg(struct phy_device *phydev) { int rc; @@ -2114,7 +2130,7 @@ static struct phy_driver vsc85xx_driver[] = { .config_init = &vsc85xx_config_init, .config_aneg = &vsc85xx_config_aneg, .read_status = &vsc85xx_read_status, - .ack_interrupt = &vsc85xx_ack_interrupt, + .handle_interrupt = vsc85xx_handle_interrupt, .config_intr = &vsc85xx_config_intr, .suspend = &genphy_suspend, .resume = &genphy_resume, @@ -2139,9 +2155,8 @@ static struct phy_driver vsc85xx_driver[] = { .config_aneg = &vsc85xx_config_aneg, .aneg_done = &genphy_aneg_done, .read_status = &vsc85xx_read_status, - .ack_interrupt = &vsc85xx_ack_interrupt, + .handle_interrupt = vsc85xx_handle_interrupt, .config_intr = &vsc85xx_config_intr, - .did_interrupt = &vsc8584_did_interrupt, .suspend = &genphy_suspend, .resume = &genphy_resume, .probe = &vsc8574_probe, @@ -2163,7 +2178,7 @@ static struct phy_driver vsc85xx_driver[] = { .config_init = &vsc8514_config_init, .config_aneg = &vsc85xx_config_aneg, .read_status = &vsc85xx_read_status, - .ack_interrupt = &vsc85xx_ack_interrupt, + .handle_interrupt = vsc85xx_handle_interrupt, .config_intr = &vsc85xx_config_intr, .suspend = &genphy_suspend, .resume = &genphy_resume, @@ -2187,7 +2202,7 @@ static struct phy_driver vsc85xx_driver[] = { .config_init = &vsc85xx_config_init, .config_aneg = &vsc85xx_config_aneg, .read_status = &vsc85xx_read_status, - .ack_interrupt = &vsc85xx_ack_interrupt, + .handle_interrupt = vsc85xx_handle_interrupt, .config_intr = &vsc85xx_config_intr, .suspend = &genphy_suspend, .resume = &genphy_resume, @@ -2211,7 +2226,7 @@ static struct phy_driver vsc85xx_driver[] = { .config_init = &vsc85xx_config_init, .config_aneg = &vsc85xx_config_aneg, .read_status = &vsc85xx_read_status, - .ack_interrupt = &vsc85xx_ack_interrupt, + .handle_interrupt = vsc85xx_handle_interrupt, .config_intr = &vsc85xx_config_intr, .suspend = &genphy_suspend, .resume = &genphy_resume, @@ -2235,7 +2250,7 @@ static struct phy_driver vsc85xx_driver[] = { .config_init = &vsc85xx_config_init, .config_aneg = &vsc85xx_config_aneg, .read_status = &vsc85xx_read_status, - .ack_interrupt = &vsc85xx_ack_interrupt, + .handle_interrupt = vsc85xx_handle_interrupt, .config_intr = &vsc85xx_config_intr, .suspend = &genphy_suspend, .resume = &genphy_resume, @@ -2259,7 +2274,7 @@ static struct phy_driver vsc85xx_driver[] = { .config_init = &vsc85xx_config_init, .config_aneg = &vsc85xx_config_aneg, .read_status = &vsc85xx_read_status, - .ack_interrupt = &vsc85xx_ack_interrupt, + .handle_interrupt = vsc85xx_handle_interrupt, .config_intr = &vsc85xx_config_intr, .suspend = &genphy_suspend, .resume = &genphy_resume, @@ -2283,9 +2298,8 @@ static struct phy_driver vsc85xx_driver[] = { .config_init = &vsc8584_config_init, .config_aneg = &vsc85xx_config_aneg, .read_status = &vsc85xx_read_status, - .ack_interrupt = &vsc85xx_ack_interrupt, + .handle_interrupt = vsc85xx_handle_interrupt, .config_intr = &vsc85xx_config_intr, - .did_interrupt = &vsc8584_did_interrupt, .suspend = &genphy_suspend, .resume = &genphy_resume, .probe = &vsc8574_probe, @@ -2308,9 +2322,8 @@ static struct phy_driver vsc85xx_driver[] = { .config_init = &vsc8584_config_init, .config_aneg = &vsc85xx_config_aneg, .read_status = &vsc85xx_read_status, - .ack_interrupt = &vsc85xx_ack_interrupt, + .handle_interrupt = vsc85xx_handle_interrupt, .config_intr = &vsc85xx_config_intr, - .did_interrupt = &vsc8584_did_interrupt, .suspend = &genphy_suspend, .resume = &genphy_resume, .probe = &vsc8584_probe, @@ -2333,9 +2346,7 @@ static struct phy_driver vsc85xx_driver[] = { .aneg_done = &genphy_aneg_done, .read_status = &vsc85xx_read_status, .handle_interrupt = &vsc8584_handle_interrupt, - .ack_interrupt = &vsc85xx_ack_interrupt, .config_intr = &vsc85xx_config_intr, - .did_interrupt = &vsc8584_did_interrupt, .suspend = &genphy_suspend, .resume = &genphy_resume, .probe = &vsc8574_probe, @@ -2359,9 +2370,8 @@ static struct phy_driver vsc85xx_driver[] = { .config_aneg = &vsc85xx_config_aneg, .aneg_done = &genphy_aneg_done, .read_status = &vsc85xx_read_status, - .ack_interrupt = &vsc85xx_ack_interrupt, + .handle_interrupt = vsc85xx_handle_interrupt, .config_intr = &vsc85xx_config_intr, - .did_interrupt = &vsc8584_did_interrupt, .suspend = &genphy_suspend, .resume = &genphy_resume, .probe = &vsc8574_probe, @@ -2386,9 +2396,7 @@ static struct phy_driver vsc85xx_driver[] = { .aneg_done = &genphy_aneg_done, .read_status = &vsc85xx_read_status, .handle_interrupt = &vsc8584_handle_interrupt, - .ack_interrupt = &vsc85xx_ack_interrupt, .config_intr = &vsc85xx_config_intr, - .did_interrupt = &vsc8584_did_interrupt, .suspend = &genphy_suspend, .resume = &genphy_resume, .probe = &vsc8584_probe, @@ -2411,9 +2419,7 @@ static struct phy_driver vsc85xx_driver[] = { .aneg_done = &genphy_aneg_done, .read_status = &vsc85xx_read_status, .handle_interrupt = &vsc8584_handle_interrupt, - .ack_interrupt = &vsc85xx_ack_interrupt, .config_intr = &vsc85xx_config_intr, - .did_interrupt = &vsc8584_did_interrupt, .suspend = &genphy_suspend, .resume = &genphy_resume, .probe = &vsc8584_probe, @@ -2436,9 +2442,7 @@ static struct phy_driver vsc85xx_driver[] = { .aneg_done = &genphy_aneg_done, .read_status = &vsc85xx_read_status, .handle_interrupt = &vsc8584_handle_interrupt, - .ack_interrupt = &vsc85xx_ack_interrupt, .config_intr = &vsc85xx_config_intr, - .did_interrupt = &vsc8584_did_interrupt, .suspend = &genphy_suspend, .resume = &genphy_resume, .probe = &vsc8584_probe, diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 35525a671400..477bdf2f94df 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -493,10 +493,11 @@ EXPORT_SYMBOL(phy_queue_state_machine); * * @phydev: the phy_device struct */ -static void phy_trigger_machine(struct phy_device *phydev) +void phy_trigger_machine(struct phy_device *phydev) { phy_queue_state_machine(phydev, 0); } +EXPORT_SYMBOL(phy_trigger_machine); static void phy_abort_cable_test(struct phy_device *phydev) { @@ -924,7 +925,7 @@ void phy_stop_machine(struct phy_device *phydev) * Must not be called from interrupt context, or while the * phydev->lock is held. */ -static void phy_error(struct phy_device *phydev) +void phy_error(struct phy_device *phydev) { WARN_ON(1); @@ -934,6 +935,7 @@ static void phy_error(struct phy_device *phydev) phy_trigger_machine(phydev); } +EXPORT_SYMBOL(phy_error); /** * phy_disable_interrupts - Disable the PHY interrupts from the PHY side diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 5dab6be6fc38..e13a46c25437 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -2463,6 +2463,19 @@ int genphy_soft_reset(struct phy_device *phydev) } EXPORT_SYMBOL(genphy_soft_reset); +irqreturn_t genphy_handle_interrupt_no_ack(struct phy_device *phydev) +{ + /* It seems there are cases where the interrupts are handled by another + * entity (ie an IRQ controller embedded inside the PHY) and do not + * need any other interraction from phylib. In this case, just trigger + * the state machine directly. + */ + phy_trigger_machine(phydev); + + return 0; +} +EXPORT_SYMBOL(genphy_handle_interrupt_no_ack); + /** * genphy_read_abilities - read PHY abilities from Clause 22 registers * @phydev: target phy_device struct @@ -2815,7 +2828,7 @@ EXPORT_SYMBOL(phy_get_internal_delay); static bool phy_drv_supports_irq(struct phy_driver *phydrv) { - return phydrv->config_intr && phydrv->ack_interrupt; + return phydrv->config_intr && (phydrv->ack_interrupt || phydrv->handle_interrupt); } /** @@ -2947,6 +2960,13 @@ static int phy_remove(struct device *dev) return 0; } +static void phy_shutdown(struct device *dev) +{ + struct phy_device *phydev = to_phy_device(dev); + + phy_disable_interrupts(phydev); +} + /** * phy_driver_register - register a phy_driver with the PHY layer * @new_driver: new phy_driver to register @@ -2970,6 +2990,7 @@ int phy_driver_register(struct phy_driver *new_driver, struct module *owner) new_driver->mdiodrv.driver.bus = &mdio_bus_type; new_driver->mdiodrv.driver.probe = phy_probe; new_driver->mdiodrv.driver.remove = phy_remove; + new_driver->mdiodrv.driver.shutdown = phy_shutdown; new_driver->mdiodrv.driver.owner = owner; new_driver->mdiodrv.driver.probe_type = PROBE_FORCE_SYNCHRONOUS; diff --git a/drivers/net/phy/phy_led_triggers.c b/drivers/net/phy/phy_led_triggers.c index 59a94e07e7c5..f550576eb9da 100644 --- a/drivers/net/phy/phy_led_triggers.c +++ b/drivers/net/phy/phy_led_triggers.c @@ -66,11 +66,11 @@ static void phy_led_trigger_format_name(struct phy_device *phy, char *buf, static int phy_led_trigger_register(struct phy_device *phy, struct phy_led_trigger *plt, - unsigned int speed) + unsigned int speed, + const char *suffix) { plt->speed = speed; - phy_led_trigger_format_name(phy, plt->name, sizeof(plt->name), - phy_speed_to_str(speed)); + phy_led_trigger_format_name(phy, plt->name, sizeof(plt->name), suffix); plt->trigger.name = plt->name; return led_trigger_register(&plt->trigger); @@ -99,12 +99,7 @@ int phy_led_triggers_register(struct phy_device *phy) goto out_clear; } - phy_led_trigger_format_name(phy, phy->led_link_trigger->name, - sizeof(phy->led_link_trigger->name), - "link"); - phy->led_link_trigger->trigger.name = phy->led_link_trigger->name; - - err = led_trigger_register(&phy->led_link_trigger->trigger); + err = phy_led_trigger_register(phy, phy->led_link_trigger, 0, "link"); if (err) goto out_free_link; @@ -119,7 +114,8 @@ int phy_led_triggers_register(struct phy_device *phy) for (i = 0; i < phy->phy_num_led_triggers; i++) { err = phy_led_trigger_register(phy, &phy->phy_led_triggers[i], - speeds[i]); + speeds[i], + phy_speed_to_str(speeds[i])); if (err) goto out_unreg; } diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index fe2296fdda19..5d8c015bc9f2 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -2515,9 +2515,10 @@ int phylink_mii_c22_pcs_config(struct mdio_device *pcs, unsigned int mode, changed = ret > 0; + /* Ensure ISOLATE bit is disabled */ bmcr = mode == MLO_AN_INBAND ? BMCR_ANENABLE : 0; ret = mdiobus_modify(pcs->bus, pcs->addr, MII_BMCR, - BMCR_ANENABLE, bmcr); + BMCR_ANENABLE | BMCR_ISOLATE, bmcr); if (ret < 0) return ret; diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index fb1db713b7fb..efc6fc637db3 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -41,6 +41,12 @@ #define RTL8211E_RX_DELAY BIT(11) #define RTL8201F_ISR 0x1e +#define RTL8201F_ISR_ANERR BIT(15) +#define RTL8201F_ISR_DUPLEX BIT(13) +#define RTL8201F_ISR_LINK BIT(11) +#define RTL8201F_ISR_MASK (RTL8201F_ISR_ANERR | \ + RTL8201F_ISR_DUPLEX | \ + RTL8201F_ISR_LINK) #define RTL8201F_IER 0x13 #define RTL8366RB_POWER_SAVE 0x15 @@ -102,24 +108,45 @@ static int rtl8211f_ack_interrupt(struct phy_device *phydev) static int rtl8201_config_intr(struct phy_device *phydev) { u16 val; + int err; + + if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { + err = rtl8201_ack_interrupt(phydev); + if (err) + return err; - if (phydev->interrupts == PHY_INTERRUPT_ENABLED) val = BIT(13) | BIT(12) | BIT(11); - else + err = phy_write_paged(phydev, 0x7, RTL8201F_IER, val); + } else { val = 0; + err = phy_write_paged(phydev, 0x7, RTL8201F_IER, val); + if (err) + return err; - return phy_write_paged(phydev, 0x7, RTL8201F_IER, val); + err = rtl8201_ack_interrupt(phydev); + } + + return err; } static int rtl8211b_config_intr(struct phy_device *phydev) { int err; - if (phydev->interrupts == PHY_INTERRUPT_ENABLED) + if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { + err = rtl821x_ack_interrupt(phydev); + if (err) + return err; + err = phy_write(phydev, RTL821x_INER, RTL8211B_INER_INIT); - else + } else { err = phy_write(phydev, RTL821x_INER, 0); + if (err) + return err; + + err = rtl821x_ack_interrupt(phydev); + } return err; } @@ -128,11 +155,20 @@ static int rtl8211e_config_intr(struct phy_device *phydev) { int err; - if (phydev->interrupts == PHY_INTERRUPT_ENABLED) + if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { + err = rtl821x_ack_interrupt(phydev); + if (err) + return err; + err = phy_write(phydev, RTL821x_INER, RTL8211E_INER_LINK_STATUS); - else + } else { err = phy_write(phydev, RTL821x_INER, 0); + if (err) + return err; + + err = rtl821x_ack_interrupt(phydev); + } return err; } @@ -140,13 +176,85 @@ static int rtl8211e_config_intr(struct phy_device *phydev) static int rtl8211f_config_intr(struct phy_device *phydev) { u16 val; + int err; + + if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { + err = rtl8211f_ack_interrupt(phydev); + if (err) + return err; - if (phydev->interrupts == PHY_INTERRUPT_ENABLED) val = RTL8211F_INER_LINK_STATUS; - else + err = phy_write_paged(phydev, 0xa42, RTL821x_INER, val); + } else { val = 0; + err = phy_write_paged(phydev, 0xa42, RTL821x_INER, val); + if (err) + return err; + + err = rtl8211f_ack_interrupt(phydev); + } + + return err; +} + +static irqreturn_t rtl8201_handle_interrupt(struct phy_device *phydev) +{ + int irq_status; + + irq_status = phy_read(phydev, RTL8201F_ISR); + if (irq_status < 0) { + phy_error(phydev); + return IRQ_NONE; + } + + if (!(irq_status & RTL8201F_ISR_MASK)) + return IRQ_NONE; + + phy_trigger_machine(phydev); + + return IRQ_HANDLED; +} + +static irqreturn_t rtl821x_handle_interrupt(struct phy_device *phydev) +{ + int irq_status, irq_enabled; + + irq_status = phy_read(phydev, RTL821x_INSR); + if (irq_status < 0) { + phy_error(phydev); + return IRQ_NONE; + } + + irq_enabled = phy_read(phydev, RTL821x_INER); + if (irq_enabled < 0) { + phy_error(phydev); + return IRQ_NONE; + } + + if (!(irq_status & irq_enabled)) + return IRQ_NONE; + + phy_trigger_machine(phydev); - return phy_write_paged(phydev, 0xa42, RTL821x_INER, val); + return IRQ_HANDLED; +} + +static irqreturn_t rtl8211f_handle_interrupt(struct phy_device *phydev) +{ + int irq_status; + + irq_status = phy_read_paged(phydev, 0xa43, RTL8211F_INSR); + if (irq_status < 0) { + phy_error(phydev); + return IRQ_NONE; + } + + if (!(irq_status & RTL8211F_INER_LINK_STATUS)) + return IRQ_NONE; + + phy_trigger_machine(phydev); + + return IRQ_HANDLED; } static int rtl8211_config_aneg(struct phy_device *phydev) @@ -554,8 +662,8 @@ static struct phy_driver realtek_drvs[] = { }, { PHY_ID_MATCH_EXACT(0x001cc816), .name = "RTL8201F Fast Ethernet", - .ack_interrupt = &rtl8201_ack_interrupt, .config_intr = &rtl8201_config_intr, + .handle_interrupt = rtl8201_handle_interrupt, .suspend = genphy_suspend, .resume = genphy_resume, .read_page = rtl821x_read_page, @@ -580,8 +688,8 @@ static struct phy_driver realtek_drvs[] = { }, { PHY_ID_MATCH_EXACT(0x001cc912), .name = "RTL8211B Gigabit Ethernet", - .ack_interrupt = &rtl821x_ack_interrupt, .config_intr = &rtl8211b_config_intr, + .handle_interrupt = rtl821x_handle_interrupt, .read_mmd = &genphy_read_mmd_unsupported, .write_mmd = &genphy_write_mmd_unsupported, .suspend = rtl8211b_suspend, @@ -599,8 +707,8 @@ static struct phy_driver realtek_drvs[] = { }, { PHY_ID_MATCH_EXACT(0x001cc914), .name = "RTL8211DN Gigabit Ethernet", - .ack_interrupt = rtl821x_ack_interrupt, .config_intr = rtl8211e_config_intr, + .handle_interrupt = rtl821x_handle_interrupt, .suspend = genphy_suspend, .resume = genphy_resume, .read_page = rtl821x_read_page, @@ -609,8 +717,8 @@ static struct phy_driver realtek_drvs[] = { PHY_ID_MATCH_EXACT(0x001cc915), .name = "RTL8211E Gigabit Ethernet", .config_init = &rtl8211e_config_init, - .ack_interrupt = &rtl821x_ack_interrupt, .config_intr = &rtl8211e_config_intr, + .handle_interrupt = rtl821x_handle_interrupt, .suspend = genphy_suspend, .resume = genphy_resume, .read_page = rtl821x_read_page, @@ -619,8 +727,8 @@ static struct phy_driver realtek_drvs[] = { PHY_ID_MATCH_EXACT(0x001cc916), .name = "RTL8211F Gigabit Ethernet", .config_init = &rtl8211f_config_init, - .ack_interrupt = &rtl8211f_ack_interrupt, .config_intr = &rtl8211f_config_intr, + .handle_interrupt = rtl8211f_handle_interrupt, .suspend = genphy_suspend, .resume = genphy_resume, .read_page = rtl821x_read_page, @@ -660,6 +768,46 @@ static struct phy_driver realtek_drvs[] = { .read_mmd = rtl822x_read_mmd, .write_mmd = rtl822x_write_mmd, }, { + PHY_ID_MATCH_EXACT(0x001cc838), + .name = "RTL8226-CG 2.5Gbps PHY", + .get_features = rtl822x_get_features, + .config_aneg = rtl822x_config_aneg, + .read_status = rtl822x_read_status, + .suspend = genphy_suspend, + .resume = rtlgen_resume, + .read_page = rtl821x_read_page, + .write_page = rtl821x_write_page, + }, { + PHY_ID_MATCH_EXACT(0x001cc848), + .name = "RTL8226B-CG_RTL8221B-CG 2.5Gbps PHY", + .get_features = rtl822x_get_features, + .config_aneg = rtl822x_config_aneg, + .read_status = rtl822x_read_status, + .suspend = genphy_suspend, + .resume = rtlgen_resume, + .read_page = rtl821x_read_page, + .write_page = rtl821x_write_page, + }, { + PHY_ID_MATCH_EXACT(0x001cc849), + .name = "RTL8221B-VB-CG 2.5Gbps PHY", + .get_features = rtl822x_get_features, + .config_aneg = rtl822x_config_aneg, + .read_status = rtl822x_read_status, + .suspend = genphy_suspend, + .resume = rtlgen_resume, + .read_page = rtl821x_read_page, + .write_page = rtl821x_write_page, + }, { + PHY_ID_MATCH_EXACT(0x001cc84a), + .name = "RTL8221B-VM-CG 2.5Gbps PHY", + .get_features = rtl822x_get_features, + .config_aneg = rtl822x_config_aneg, + .read_status = rtl822x_read_status, + .suspend = genphy_suspend, + .resume = rtlgen_resume, + .read_page = rtl821x_read_page, + .write_page = rtl821x_write_page, + }, { PHY_ID_MATCH_EXACT(0x001cc961), .name = "RTL8366RB Gigabit Ethernet", .config_init = &rtl8366rb_config_init, @@ -668,8 +816,8 @@ static struct phy_driver realtek_drvs[] = { * irq is requested and ACKed by reading the status register, * which is done by the irqchip code. */ - .ack_interrupt = genphy_no_ack_interrupt, .config_intr = genphy_no_config_intr, + .handle_interrupt = genphy_handle_interrupt_no_ack, .suspend = genphy_suspend, .resume = genphy_resume, }, diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 07f1f3933927..b4092127a92c 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -975,11 +975,11 @@ static void team_port_disable(struct team *team, } #define TEAM_VLAN_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ - NETIF_F_FRAGLIST | NETIF_F_ALL_TSO | \ + NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE | \ NETIF_F_HIGHDMA | NETIF_F_LRO) #define TEAM_ENC_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ - NETIF_F_RXCSUM | NETIF_F_ALL_TSO) + NETIF_F_RXCSUM | NETIF_F_GSO_SOFTWARE) static void __team_compute_features(struct team *team) { @@ -1009,8 +1009,7 @@ static void __team_compute_features(struct team *team) team->dev->vlan_features = vlan_features; team->dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL | NETIF_F_HW_VLAN_CTAG_TX | - NETIF_F_HW_VLAN_STAG_TX | - NETIF_F_GSO_UDP_L4; + NETIF_F_HW_VLAN_STAG_TX; team->dev->hard_header_len = max_hard_header_len; team->dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; @@ -2175,7 +2174,7 @@ static void team_setup(struct net_device *dev) NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER; - dev->hw_features |= NETIF_F_GSO_ENCAP_ALL | NETIF_F_GSO_UDP_L4; + dev->hw_features |= NETIF_F_GSO_ENCAP_ALL; dev->features |= dev->hw_features; dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; } diff --git a/drivers/net/usb/Makefile b/drivers/net/usb/Makefile index 99fd12be2111..99381e6bea78 100644 --- a/drivers/net/usb/Makefile +++ b/drivers/net/usb/Makefile @@ -13,7 +13,7 @@ obj-$(CONFIG_USB_LAN78XX) += lan78xx.o obj-$(CONFIG_USB_NET_AX8817X) += asix.o asix-y := asix_devices.o asix_common.o ax88172a.o obj-$(CONFIG_USB_NET_AX88179_178A) += ax88179_178a.o -obj-$(CONFIG_USB_NET_CDCETHER) += cdc_ether.o +obj-$(CONFIG_USB_NET_CDCETHER) += cdc_ether.o r8153_ecm.o obj-$(CONFIG_USB_NET_CDC_EEM) += cdc_eem.o obj-$(CONFIG_USB_NET_DM9601) += dm9601.o obj-$(CONFIG_USB_NET_SR9700) += sr9700.o diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 65b315bc60ab..bf243edeb064 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -822,20 +822,19 @@ static int lan78xx_read_raw_otp(struct lan78xx_net *dev, u32 offset, u32 length, u8 *data) { int i; - int ret; u32 buf; unsigned long timeout; - ret = lan78xx_read_reg(dev, OTP_PWR_DN, &buf); + lan78xx_read_reg(dev, OTP_PWR_DN, &buf); if (buf & OTP_PWR_DN_PWRDN_N_) { /* clear it and wait to be cleared */ - ret = lan78xx_write_reg(dev, OTP_PWR_DN, 0); + lan78xx_write_reg(dev, OTP_PWR_DN, 0); timeout = jiffies + HZ; do { usleep_range(1, 10); - ret = lan78xx_read_reg(dev, OTP_PWR_DN, &buf); + lan78xx_read_reg(dev, OTP_PWR_DN, &buf); if (time_after(jiffies, timeout)) { netdev_warn(dev->net, "timeout on OTP_PWR_DN"); @@ -845,18 +844,18 @@ static int lan78xx_read_raw_otp(struct lan78xx_net *dev, u32 offset, } for (i = 0; i < length; i++) { - ret = lan78xx_write_reg(dev, OTP_ADDR1, + lan78xx_write_reg(dev, OTP_ADDR1, ((offset + i) >> 8) & OTP_ADDR1_15_11); - ret = lan78xx_write_reg(dev, OTP_ADDR2, + lan78xx_write_reg(dev, OTP_ADDR2, ((offset + i) & OTP_ADDR2_10_3)); - ret = lan78xx_write_reg(dev, OTP_FUNC_CMD, OTP_FUNC_CMD_READ_); - ret = lan78xx_write_reg(dev, OTP_CMD_GO, OTP_CMD_GO_GO_); + lan78xx_write_reg(dev, OTP_FUNC_CMD, OTP_FUNC_CMD_READ_); + lan78xx_write_reg(dev, OTP_CMD_GO, OTP_CMD_GO_GO_); timeout = jiffies + HZ; do { udelay(1); - ret = lan78xx_read_reg(dev, OTP_STATUS, &buf); + lan78xx_read_reg(dev, OTP_STATUS, &buf); if (time_after(jiffies, timeout)) { netdev_warn(dev->net, "timeout on OTP_STATUS"); @@ -864,7 +863,7 @@ static int lan78xx_read_raw_otp(struct lan78xx_net *dev, u32 offset, } } while (buf & OTP_STATUS_BUSY_); - ret = lan78xx_read_reg(dev, OTP_RD_DATA, &buf); + lan78xx_read_reg(dev, OTP_RD_DATA, &buf); data[i] = (u8)(buf & 0xFF); } @@ -876,20 +875,19 @@ static int lan78xx_write_raw_otp(struct lan78xx_net *dev, u32 offset, u32 length, u8 *data) { int i; - int ret; u32 buf; unsigned long timeout; - ret = lan78xx_read_reg(dev, OTP_PWR_DN, &buf); + lan78xx_read_reg(dev, OTP_PWR_DN, &buf); if (buf & OTP_PWR_DN_PWRDN_N_) { /* clear it and wait to be cleared */ - ret = lan78xx_write_reg(dev, OTP_PWR_DN, 0); + lan78xx_write_reg(dev, OTP_PWR_DN, 0); timeout = jiffies + HZ; do { udelay(1); - ret = lan78xx_read_reg(dev, OTP_PWR_DN, &buf); + lan78xx_read_reg(dev, OTP_PWR_DN, &buf); if (time_after(jiffies, timeout)) { netdev_warn(dev->net, "timeout on OTP_PWR_DN completion"); @@ -899,21 +897,21 @@ static int lan78xx_write_raw_otp(struct lan78xx_net *dev, u32 offset, } /* set to BYTE program mode */ - ret = lan78xx_write_reg(dev, OTP_PRGM_MODE, OTP_PRGM_MODE_BYTE_); + lan78xx_write_reg(dev, OTP_PRGM_MODE, OTP_PRGM_MODE_BYTE_); for (i = 0; i < length; i++) { - ret = lan78xx_write_reg(dev, OTP_ADDR1, + lan78xx_write_reg(dev, OTP_ADDR1, ((offset + i) >> 8) & OTP_ADDR1_15_11); - ret = lan78xx_write_reg(dev, OTP_ADDR2, + lan78xx_write_reg(dev, OTP_ADDR2, ((offset + i) & OTP_ADDR2_10_3)); - ret = lan78xx_write_reg(dev, OTP_PRGM_DATA, data[i]); - ret = lan78xx_write_reg(dev, OTP_TST_CMD, OTP_TST_CMD_PRGVRFY_); - ret = lan78xx_write_reg(dev, OTP_CMD_GO, OTP_CMD_GO_GO_); + lan78xx_write_reg(dev, OTP_PRGM_DATA, data[i]); + lan78xx_write_reg(dev, OTP_TST_CMD, OTP_TST_CMD_PRGVRFY_); + lan78xx_write_reg(dev, OTP_CMD_GO, OTP_CMD_GO_GO_); timeout = jiffies + HZ; do { udelay(1); - ret = lan78xx_read_reg(dev, OTP_STATUS, &buf); + lan78xx_read_reg(dev, OTP_STATUS, &buf); if (time_after(jiffies, timeout)) { netdev_warn(dev->net, "Timeout on OTP_STATUS completion"); @@ -1038,7 +1036,6 @@ static void lan78xx_deferred_multicast_write(struct work_struct *param) container_of(param, struct lan78xx_priv, set_multicast); struct lan78xx_net *dev = pdata->dev; int i; - int ret; netif_dbg(dev, drv, dev->net, "deferred multicast write 0x%08x\n", pdata->rfe_ctl); @@ -1047,14 +1044,14 @@ static void lan78xx_deferred_multicast_write(struct work_struct *param) DP_SEL_VHF_HASH_LEN, pdata->mchash_table); for (i = 1; i < NUM_OF_MAF; i++) { - ret = lan78xx_write_reg(dev, MAF_HI(i), 0); - ret = lan78xx_write_reg(dev, MAF_LO(i), + lan78xx_write_reg(dev, MAF_HI(i), 0); + lan78xx_write_reg(dev, MAF_LO(i), pdata->pfilter_table[i][1]); - ret = lan78xx_write_reg(dev, MAF_HI(i), + lan78xx_write_reg(dev, MAF_HI(i), pdata->pfilter_table[i][0]); } - ret = lan78xx_write_reg(dev, RFE_CTL, pdata->rfe_ctl); + lan78xx_write_reg(dev, RFE_CTL, pdata->rfe_ctl); } static void lan78xx_set_multicast(struct net_device *netdev) @@ -1124,7 +1121,6 @@ static int lan78xx_update_flowcontrol(struct lan78xx_net *dev, u8 duplex, u16 lcladv, u16 rmtadv) { u32 flow = 0, fct_flow = 0; - int ret; u8 cap; if (dev->fc_autoneg) @@ -1147,10 +1143,10 @@ static int lan78xx_update_flowcontrol(struct lan78xx_net *dev, u8 duplex, (cap & FLOW_CTRL_RX ? "enabled" : "disabled"), (cap & FLOW_CTRL_TX ? "enabled" : "disabled")); - ret = lan78xx_write_reg(dev, FCT_FLOW, fct_flow); + lan78xx_write_reg(dev, FCT_FLOW, fct_flow); /* threshold value should be set before enabling flow */ - ret = lan78xx_write_reg(dev, FLOW, flow); + lan78xx_write_reg(dev, FLOW, flow); return 0; } @@ -1663,11 +1659,10 @@ static const struct ethtool_ops lan78xx_ethtool_ops = { static void lan78xx_init_mac_address(struct lan78xx_net *dev) { u32 addr_lo, addr_hi; - int ret; u8 addr[6]; - ret = lan78xx_read_reg(dev, RX_ADDRL, &addr_lo); - ret = lan78xx_read_reg(dev, RX_ADDRH, &addr_hi); + lan78xx_read_reg(dev, RX_ADDRL, &addr_lo); + lan78xx_read_reg(dev, RX_ADDRH, &addr_hi); addr[0] = addr_lo & 0xFF; addr[1] = (addr_lo >> 8) & 0xFF; @@ -1700,12 +1695,12 @@ static void lan78xx_init_mac_address(struct lan78xx_net *dev) (addr[2] << 16) | (addr[3] << 24); addr_hi = addr[4] | (addr[5] << 8); - ret = lan78xx_write_reg(dev, RX_ADDRL, addr_lo); - ret = lan78xx_write_reg(dev, RX_ADDRH, addr_hi); + lan78xx_write_reg(dev, RX_ADDRL, addr_lo); + lan78xx_write_reg(dev, RX_ADDRH, addr_hi); } - ret = lan78xx_write_reg(dev, MAF_LO(0), addr_lo); - ret = lan78xx_write_reg(dev, MAF_HI(0), addr_hi | MAF_HI_VALID_); + lan78xx_write_reg(dev, MAF_LO(0), addr_lo); + lan78xx_write_reg(dev, MAF_HI(0), addr_hi | MAF_HI_VALID_); ether_addr_copy(dev->net->dev_addr, addr); } @@ -1838,7 +1833,7 @@ static void lan78xx_remove_mdio(struct lan78xx_net *dev) static void lan78xx_link_status_change(struct net_device *net) { struct phy_device *phydev = net->phydev; - int ret, temp; + int temp; /* At forced 100 F/H mode, chip may fail to set mode correctly * when cable is switched between long(~50+m) and short one. @@ -1849,7 +1844,7 @@ static void lan78xx_link_status_change(struct net_device *net) /* disable phy interrupt */ temp = phy_read(phydev, LAN88XX_INT_MASK); temp &= ~LAN88XX_INT_MASK_MDINTPIN_EN_; - ret = phy_write(phydev, LAN88XX_INT_MASK, temp); + phy_write(phydev, LAN88XX_INT_MASK, temp); temp = phy_read(phydev, MII_BMCR); temp &= ~(BMCR_SPEED100 | BMCR_SPEED1000); @@ -1863,7 +1858,7 @@ static void lan78xx_link_status_change(struct net_device *net) /* enable phy interrupt back */ temp = phy_read(phydev, LAN88XX_INT_MASK); temp |= LAN88XX_INT_MASK_MDINTPIN_EN_; - ret = phy_write(phydev, LAN88XX_INT_MASK, temp); + phy_write(phydev, LAN88XX_INT_MASK, temp); } } @@ -1917,14 +1912,13 @@ static void lan78xx_irq_bus_sync_unlock(struct irq_data *irqd) struct lan78xx_net *dev = container_of(data, struct lan78xx_net, domain_data); u32 buf; - int ret; /* call register access here because irq_bus_lock & irq_bus_sync_unlock * are only two callbacks executed in non-atomic contex. */ - ret = lan78xx_read_reg(dev, INT_EP_CTL, &buf); + lan78xx_read_reg(dev, INT_EP_CTL, &buf); if (buf != data->irqenable) - ret = lan78xx_write_reg(dev, INT_EP_CTL, data->irqenable); + lan78xx_write_reg(dev, INT_EP_CTL, data->irqenable); mutex_unlock(&data->irq_lock); } @@ -1991,7 +1985,6 @@ static void lan78xx_remove_irq_domain(struct lan78xx_net *dev) static int lan8835_fixup(struct phy_device *phydev) { int buf; - int ret; struct lan78xx_net *dev = netdev_priv(phydev->attached_dev); /* LED2/PME_N/IRQ_N/RGMII_ID pin to IRQ_N mode */ @@ -2001,11 +1994,11 @@ static int lan8835_fixup(struct phy_device *phydev) phy_write_mmd(phydev, MDIO_MMD_PCS, 0x8010, buf); /* RGMII MAC TXC Delay Enable */ - ret = lan78xx_write_reg(dev, MAC_RGMII_ID, + lan78xx_write_reg(dev, MAC_RGMII_ID, MAC_RGMII_ID_TXC_DELAY_EN_); /* RGMII TX DLL Tune Adjust */ - ret = lan78xx_write_reg(dev, RGMII_TX_BYP_DLL, 0x3D00); + lan78xx_write_reg(dev, RGMII_TX_BYP_DLL, 0x3D00); dev->interface = PHY_INTERFACE_MODE_RGMII_TXID; @@ -2189,28 +2182,27 @@ static int lan78xx_phy_init(struct lan78xx_net *dev) static int lan78xx_set_rx_max_frame_length(struct lan78xx_net *dev, int size) { - int ret = 0; u32 buf; bool rxenabled; - ret = lan78xx_read_reg(dev, MAC_RX, &buf); + lan78xx_read_reg(dev, MAC_RX, &buf); rxenabled = ((buf & MAC_RX_RXEN_) != 0); if (rxenabled) { buf &= ~MAC_RX_RXEN_; - ret = lan78xx_write_reg(dev, MAC_RX, buf); + lan78xx_write_reg(dev, MAC_RX, buf); } /* add 4 to size for FCS */ buf &= ~MAC_RX_MAX_SIZE_MASK_; buf |= (((size + 4) << MAC_RX_MAX_SIZE_SHIFT_) & MAC_RX_MAX_SIZE_MASK_); - ret = lan78xx_write_reg(dev, MAC_RX, buf); + lan78xx_write_reg(dev, MAC_RX, buf); if (rxenabled) { buf |= MAC_RX_RXEN_; - ret = lan78xx_write_reg(dev, MAC_RX, buf); + lan78xx_write_reg(dev, MAC_RX, buf); } return 0; @@ -2267,13 +2259,12 @@ static int lan78xx_change_mtu(struct net_device *netdev, int new_mtu) int ll_mtu = new_mtu + netdev->hard_header_len; int old_hard_mtu = dev->hard_mtu; int old_rx_urb_size = dev->rx_urb_size; - int ret; /* no second zero-length packet read wanted after mtu-sized packets */ if ((ll_mtu % dev->maxpacket) == 0) return -EDOM; - ret = lan78xx_set_rx_max_frame_length(dev, new_mtu + VLAN_ETH_HLEN); + lan78xx_set_rx_max_frame_length(dev, new_mtu + VLAN_ETH_HLEN); netdev->mtu = new_mtu; @@ -2296,7 +2287,6 @@ static int lan78xx_set_mac_addr(struct net_device *netdev, void *p) struct lan78xx_net *dev = netdev_priv(netdev); struct sockaddr *addr = p; u32 addr_lo, addr_hi; - int ret; if (netif_running(netdev)) return -EBUSY; @@ -2313,12 +2303,12 @@ static int lan78xx_set_mac_addr(struct net_device *netdev, void *p) addr_hi = netdev->dev_addr[4] | netdev->dev_addr[5] << 8; - ret = lan78xx_write_reg(dev, RX_ADDRL, addr_lo); - ret = lan78xx_write_reg(dev, RX_ADDRH, addr_hi); + lan78xx_write_reg(dev, RX_ADDRL, addr_lo); + lan78xx_write_reg(dev, RX_ADDRH, addr_hi); /* Added to support MAC address changes */ - ret = lan78xx_write_reg(dev, MAF_LO(0), addr_lo); - ret = lan78xx_write_reg(dev, MAF_HI(0), addr_hi | MAF_HI_VALID_); + lan78xx_write_reg(dev, MAF_LO(0), addr_lo); + lan78xx_write_reg(dev, MAF_HI(0), addr_hi | MAF_HI_VALID_); return 0; } @@ -2330,7 +2320,6 @@ static int lan78xx_set_features(struct net_device *netdev, struct lan78xx_net *dev = netdev_priv(netdev); struct lan78xx_priv *pdata = (struct lan78xx_priv *)(dev->data[0]); unsigned long flags; - int ret; spin_lock_irqsave(&pdata->rfe_ctl_lock, flags); @@ -2354,7 +2343,7 @@ static int lan78xx_set_features(struct net_device *netdev, spin_unlock_irqrestore(&pdata->rfe_ctl_lock, flags); - ret = lan78xx_write_reg(dev, RFE_CTL, pdata->rfe_ctl); + lan78xx_write_reg(dev, RFE_CTL, pdata->rfe_ctl); return 0; } @@ -3804,7 +3793,6 @@ static u16 lan78xx_wakeframe_crc16(const u8 *buf, int len) static int lan78xx_set_suspend(struct lan78xx_net *dev, u32 wol) { u32 buf; - int ret; int mask_index; u16 crc; u32 temp_wucsr; @@ -3813,26 +3801,26 @@ static int lan78xx_set_suspend(struct lan78xx_net *dev, u32 wol) const u8 ipv6_multicast[3] = { 0x33, 0x33 }; const u8 arp_type[2] = { 0x08, 0x06 }; - ret = lan78xx_read_reg(dev, MAC_TX, &buf); + lan78xx_read_reg(dev, MAC_TX, &buf); buf &= ~MAC_TX_TXEN_; - ret = lan78xx_write_reg(dev, MAC_TX, buf); - ret = lan78xx_read_reg(dev, MAC_RX, &buf); + lan78xx_write_reg(dev, MAC_TX, buf); + lan78xx_read_reg(dev, MAC_RX, &buf); buf &= ~MAC_RX_RXEN_; - ret = lan78xx_write_reg(dev, MAC_RX, buf); + lan78xx_write_reg(dev, MAC_RX, buf); - ret = lan78xx_write_reg(dev, WUCSR, 0); - ret = lan78xx_write_reg(dev, WUCSR2, 0); - ret = lan78xx_write_reg(dev, WK_SRC, 0xFFF1FF1FUL); + lan78xx_write_reg(dev, WUCSR, 0); + lan78xx_write_reg(dev, WUCSR2, 0); + lan78xx_write_reg(dev, WK_SRC, 0xFFF1FF1FUL); temp_wucsr = 0; temp_pmt_ctl = 0; - ret = lan78xx_read_reg(dev, PMT_CTL, &temp_pmt_ctl); + lan78xx_read_reg(dev, PMT_CTL, &temp_pmt_ctl); temp_pmt_ctl &= ~PMT_CTL_RES_CLR_WKP_EN_; temp_pmt_ctl |= PMT_CTL_RES_CLR_WKP_STS_; for (mask_index = 0; mask_index < NUM_OF_WUF_CFG; mask_index++) - ret = lan78xx_write_reg(dev, WUF_CFG(mask_index), 0); + lan78xx_write_reg(dev, WUF_CFG(mask_index), 0); mask_index = 0; if (wol & WAKE_PHY) { @@ -3861,30 +3849,30 @@ static int lan78xx_set_suspend(struct lan78xx_net *dev, u32 wol) /* set WUF_CFG & WUF_MASK for IPv4 Multicast */ crc = lan78xx_wakeframe_crc16(ipv4_multicast, 3); - ret = lan78xx_write_reg(dev, WUF_CFG(mask_index), + lan78xx_write_reg(dev, WUF_CFG(mask_index), WUF_CFGX_EN_ | WUF_CFGX_TYPE_MCAST_ | (0 << WUF_CFGX_OFFSET_SHIFT_) | (crc & WUF_CFGX_CRC16_MASK_)); - ret = lan78xx_write_reg(dev, WUF_MASK0(mask_index), 7); - ret = lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0); - ret = lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0); - ret = lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0); + lan78xx_write_reg(dev, WUF_MASK0(mask_index), 7); + lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0); + lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0); + lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0); mask_index++; /* for IPv6 Multicast */ crc = lan78xx_wakeframe_crc16(ipv6_multicast, 2); - ret = lan78xx_write_reg(dev, WUF_CFG(mask_index), + lan78xx_write_reg(dev, WUF_CFG(mask_index), WUF_CFGX_EN_ | WUF_CFGX_TYPE_MCAST_ | (0 << WUF_CFGX_OFFSET_SHIFT_) | (crc & WUF_CFGX_CRC16_MASK_)); - ret = lan78xx_write_reg(dev, WUF_MASK0(mask_index), 3); - ret = lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0); - ret = lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0); - ret = lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0); + lan78xx_write_reg(dev, WUF_MASK0(mask_index), 3); + lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0); + lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0); + lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0); mask_index++; temp_pmt_ctl |= PMT_CTL_WOL_EN_; @@ -3905,16 +3893,16 @@ static int lan78xx_set_suspend(struct lan78xx_net *dev, u32 wol) * for packettype (offset 12,13) = ARP (0x0806) */ crc = lan78xx_wakeframe_crc16(arp_type, 2); - ret = lan78xx_write_reg(dev, WUF_CFG(mask_index), + lan78xx_write_reg(dev, WUF_CFG(mask_index), WUF_CFGX_EN_ | WUF_CFGX_TYPE_ALL_ | (0 << WUF_CFGX_OFFSET_SHIFT_) | (crc & WUF_CFGX_CRC16_MASK_)); - ret = lan78xx_write_reg(dev, WUF_MASK0(mask_index), 0x3000); - ret = lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0); - ret = lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0); - ret = lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0); + lan78xx_write_reg(dev, WUF_MASK0(mask_index), 0x3000); + lan78xx_write_reg(dev, WUF_MASK1(mask_index), 0); + lan78xx_write_reg(dev, WUF_MASK2(mask_index), 0); + lan78xx_write_reg(dev, WUF_MASK3(mask_index), 0); mask_index++; temp_pmt_ctl |= PMT_CTL_WOL_EN_; @@ -3922,7 +3910,7 @@ static int lan78xx_set_suspend(struct lan78xx_net *dev, u32 wol) temp_pmt_ctl |= PMT_CTL_SUS_MODE_0_; } - ret = lan78xx_write_reg(dev, WUCSR, temp_wucsr); + lan78xx_write_reg(dev, WUCSR, temp_wucsr); /* when multiple WOL bits are set */ if (hweight_long((unsigned long)wol) > 1) { @@ -3930,16 +3918,16 @@ static int lan78xx_set_suspend(struct lan78xx_net *dev, u32 wol) temp_pmt_ctl &= ~PMT_CTL_SUS_MODE_MASK_; temp_pmt_ctl |= PMT_CTL_SUS_MODE_0_; } - ret = lan78xx_write_reg(dev, PMT_CTL, temp_pmt_ctl); + lan78xx_write_reg(dev, PMT_CTL, temp_pmt_ctl); /* clear WUPS */ - ret = lan78xx_read_reg(dev, PMT_CTL, &buf); + lan78xx_read_reg(dev, PMT_CTL, &buf); buf |= PMT_CTL_WUPS_MASK_; - ret = lan78xx_write_reg(dev, PMT_CTL, buf); + lan78xx_write_reg(dev, PMT_CTL, buf); - ret = lan78xx_read_reg(dev, MAC_RX, &buf); + lan78xx_read_reg(dev, MAC_RX, &buf); buf |= MAC_RX_RXEN_; - ret = lan78xx_write_reg(dev, MAC_RX, buf); + lan78xx_write_reg(dev, MAC_RX, buf); return 0; } diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index b1770489aca5..c448d6089821 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -26,6 +26,7 @@ #include <linux/acpi.h> #include <linux/firmware.h> #include <crypto/hash.h> +#include <linux/usb/r8152.h> /* Information for net-next */ #define NETNEXT_VERSION "11" @@ -653,18 +654,6 @@ enum rtl_register_content { #define INTR_LINK 0x0004 -#define RTL8152_REQT_READ 0xc0 -#define RTL8152_REQT_WRITE 0x40 -#define RTL8152_REQ_GET_REGS 0x05 -#define RTL8152_REQ_SET_REGS 0x05 - -#define BYTE_EN_DWORD 0xff -#define BYTE_EN_WORD 0x33 -#define BYTE_EN_BYTE 0x11 -#define BYTE_EN_SIX_BYTES 0x3f -#define BYTE_EN_START_MASK 0x0f -#define BYTE_EN_END_MASK 0xf0 - #define RTL8153_MAX_PACKET 9216 /* 9K */ #define RTL8153_MAX_MTU (RTL8153_MAX_PACKET - VLAN_ETH_HLEN - \ ETH_FCS_LEN) @@ -689,21 +678,9 @@ enum rtl8152_flags { LENOVO_MACPASSTHRU, }; -/* Define these values to match your device */ -#define VENDOR_ID_REALTEK 0x0bda -#define VENDOR_ID_MICROSOFT 0x045e -#define VENDOR_ID_SAMSUNG 0x04e8 -#define VENDOR_ID_LENOVO 0x17ef -#define VENDOR_ID_LINKSYS 0x13b1 -#define VENDOR_ID_NVIDIA 0x0955 -#define VENDOR_ID_TPLINK 0x2357 - #define DEVICE_ID_THINKPAD_THUNDERBOLT3_DOCK_GEN2 0x3082 #define DEVICE_ID_THINKPAD_USB_C_DOCK_GEN2 0xa387 -#define MCU_TYPE_PLA 0x0100 -#define MCU_TYPE_USB 0x0000 - struct tally_counter { __le64 tx_packets; __le64 rx_packets; @@ -898,6 +875,7 @@ struct fw_header { * struct fw_mac - a firmware block used by RTL_FW_PLA and RTL_FW_USB. * The layout of the firmware block is: * <struct fw_mac> + <info> + <firmware data>. + * @blk_hdr: firmware descriptor (type, length) * @fw_offset: offset of the firmware binary data. The start address of * the data would be the address of struct fw_mac + @fw_offset. * @fw_reg: the register to load the firmware. Depends on chip. @@ -911,6 +889,7 @@ struct fw_header { * @bp_num: the break point number which needs to be set for this firmware. * Depends on the firmware. * @bp: break points. Depends on firmware. + * @reserved: reserved space (unused) * @fw_ver_reg: the register to store the fw version. * @fw_ver_data: the firmware version of the current type. * @info: additional information for debugging, and is followed by the @@ -936,8 +915,10 @@ struct fw_mac { /** * struct fw_phy_patch_key - a firmware block used by RTL_FW_PHY_START. * This is used to set patch key when loading the firmware of PHY. + * @blk_hdr: firmware descriptor (type, length) * @key_reg: the register to write the patch key. * @key_data: patch key. + * @reserved: reserved space (unused) */ struct fw_phy_patch_key { struct fw_block blk_hdr; @@ -950,6 +931,7 @@ struct fw_phy_patch_key { * struct fw_phy_nc - a firmware block used by RTL_FW_PHY_NC. * The layout of the firmware block is: * <struct fw_phy_nc> + <info> + <firmware data>. + * @blk_hdr: firmware descriptor (type, length) * @fw_offset: offset of the firmware binary data. The start address of * the data would be the address of struct fw_phy_nc + @fw_offset. * @fw_reg: the register to load the firmware. Depends on chip. @@ -958,8 +940,9 @@ struct fw_phy_patch_key { * @patch_en_addr: the register of enabling patch mode. Depends on chip. * @patch_en_value: patch mode enabled mask. Depends on the firmware. * @mode_reg: the regitster of switching the mode. - * @mod_pre: the mode needing to be set before loading the firmware. - * @mod_post: the mode to be set when finishing to load the firmware. + * @mode_pre: the mode needing to be set before loading the firmware. + * @mode_post: the mode to be set when finishing to load the firmware. + * @reserved: reserved space (unused) * @bp_start: the start register of break points. Depends on chip. * @bp_num: the break point number which needs to be set for this firmware. * Depends on the firmware. @@ -6615,7 +6598,7 @@ static int rtl_fw_init(struct r8152 *tp) return 0; } -static u8 rtl_get_version(struct usb_interface *intf) +u8 rtl8152_get_version(struct usb_interface *intf) { struct usb_device *udev = interface_to_usbdev(intf); u32 ocp_data = 0; @@ -6673,12 +6656,13 @@ static u8 rtl_get_version(struct usb_interface *intf) return version; } +EXPORT_SYMBOL_GPL(rtl8152_get_version); static int rtl8152_probe(struct usb_interface *intf, const struct usb_device_id *id) { struct usb_device *udev = interface_to_usbdev(intf); - u8 version = rtl_get_version(intf); + u8 version = rtl8152_get_version(intf); struct r8152 *tp; struct net_device *netdev; int ret; diff --git a/drivers/net/usb/r8153_ecm.c b/drivers/net/usb/r8153_ecm.c new file mode 100644 index 000000000000..2c3fabd38b16 --- /dev/null +++ b/drivers/net/usb/r8153_ecm.c @@ -0,0 +1,162 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +#include <linux/module.h> +#include <linux/netdevice.h> +#include <linux/mii.h> +#include <linux/usb.h> +#include <linux/usb/cdc.h> +#include <linux/usb/usbnet.h> +#include <linux/usb/r8152.h> + +#define OCP_BASE 0xe86c + +static int pla_read_word(struct usbnet *dev, u16 index) +{ + u16 byen = BYTE_EN_WORD; + u8 shift = index & 2; + __le32 tmp; + int ret; + + if (shift) + byen <<= shift; + + index &= ~3; + + ret = usbnet_read_cmd(dev, RTL8152_REQ_GET_REGS, RTL8152_REQT_READ, index, + MCU_TYPE_PLA | byen, &tmp, sizeof(tmp)); + if (ret < 0) + goto out; + + ret = __le32_to_cpu(tmp); + ret >>= (shift * 8); + ret &= 0xffff; + +out: + return ret; +} + +static int pla_write_word(struct usbnet *dev, u16 index, u32 data) +{ + u32 mask = 0xffff; + u16 byen = BYTE_EN_WORD; + u8 shift = index & 2; + __le32 tmp; + int ret; + + data &= mask; + + if (shift) { + byen <<= shift; + mask <<= (shift * 8); + data <<= (shift * 8); + } + + index &= ~3; + + ret = usbnet_read_cmd(dev, RTL8152_REQ_GET_REGS, RTL8152_REQT_READ, index, + MCU_TYPE_PLA | byen, &tmp, sizeof(tmp)); + + if (ret < 0) + goto out; + + data |= __le32_to_cpu(tmp) & ~mask; + tmp = __cpu_to_le32(data); + + ret = usbnet_write_cmd(dev, RTL8152_REQ_SET_REGS, RTL8152_REQT_WRITE, index, + MCU_TYPE_PLA | byen, &tmp, sizeof(tmp)); + +out: + return ret; +} + +static int r8153_ecm_mdio_read(struct net_device *netdev, int phy_id, int reg) +{ + struct usbnet *dev = netdev_priv(netdev); + int ret; + + ret = pla_write_word(dev, OCP_BASE, 0xa000); + if (ret < 0) + goto out; + + ret = pla_read_word(dev, 0xb400 + reg * 2); + +out: + return ret; +} + +static void r8153_ecm_mdio_write(struct net_device *netdev, int phy_id, int reg, int val) +{ + struct usbnet *dev = netdev_priv(netdev); + int ret; + + ret = pla_write_word(dev, OCP_BASE, 0xa000); + if (ret < 0) + return; + + ret = pla_write_word(dev, 0xb400 + reg * 2, val); +} + +static int r8153_bind(struct usbnet *dev, struct usb_interface *intf) +{ + int status; + + status = usbnet_cdc_bind(dev, intf); + if (status < 0) + return status; + + dev->mii.dev = dev->net; + dev->mii.mdio_read = r8153_ecm_mdio_read; + dev->mii.mdio_write = r8153_ecm_mdio_write; + dev->mii.reg_num_mask = 0x1f; + dev->mii.supports_gmii = 1; + + return status; +} + +static const struct driver_info r8153_info = { + .description = "RTL8153 ECM Device", + .flags = FLAG_ETHER, + .bind = r8153_bind, + .unbind = usbnet_cdc_unbind, + .status = usbnet_cdc_status, + .manage_power = usbnet_manage_power, +}; + +static const struct usb_device_id products[] = { +{ + USB_DEVICE_AND_INTERFACE_INFO(VENDOR_ID_REALTEK, 0x8153, USB_CLASS_COMM, + USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), + .driver_info = (unsigned long)&r8153_info, +}, + + { }, /* END */ +}; +MODULE_DEVICE_TABLE(usb, products); + +static int rtl8153_ecm_probe(struct usb_interface *intf, + const struct usb_device_id *id) +{ +#if IS_REACHABLE(CONFIG_USB_RTL8152) + if (rtl8152_get_version(intf)) + return -ENODEV; +#endif + + return usbnet_probe(intf, id); +} + +static struct usb_driver r8153_ecm_driver = { + .name = "r8153_ecm", + .id_table = products, + .probe = rtl8153_ecm_probe, + .disconnect = usbnet_disconnect, + .suspend = usbnet_suspend, + .resume = usbnet_resume, + .reset_resume = usbnet_resume, + .supports_autosuspend = 1, + .disable_hub_initiated_lpm = 1, +}; + +module_usb_driver(r8153_ecm_driver); + +MODULE_AUTHOR("Hayes Wang"); +MODULE_DESCRIPTION("Realtek USB ECM device"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 1a557aeba32b..183e708dc6cb 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -66,6 +66,7 @@ struct vxlan_net { struct list_head vxlan_list; struct hlist_head sock_list[PORT_HASH_SIZE]; spinlock_t sock_lock; + struct notifier_block nexthop_notifier_block; }; /* Forwarding table entry */ @@ -4683,9 +4684,14 @@ static void vxlan_fdb_nh_flush(struct nexthop *nh) static int vxlan_nexthop_event(struct notifier_block *nb, unsigned long event, void *ptr) { - struct nexthop *nh = ptr; + struct nh_notifier_info *info = ptr; + struct nexthop *nh; + + if (event != NEXTHOP_EVENT_DEL) + return NOTIFY_DONE; - if (!nh || event != NEXTHOP_EVENT_DEL) + nh = nexthop_find_by_id(info->net, info->id); + if (!nh) return NOTIFY_DONE; vxlan_fdb_nh_flush(nh); @@ -4693,10 +4699,6 @@ static int vxlan_nexthop_event(struct notifier_block *nb, return NOTIFY_DONE; } -static struct notifier_block vxlan_nexthop_notifier_block __read_mostly = { - .notifier_call = vxlan_nexthop_event, -}; - static __net_init int vxlan_init_net(struct net *net) { struct vxlan_net *vn = net_generic(net, vxlan_net_id); @@ -4704,11 +4706,13 @@ static __net_init int vxlan_init_net(struct net *net) INIT_LIST_HEAD(&vn->vxlan_list); spin_lock_init(&vn->sock_lock); + vn->nexthop_notifier_block.notifier_call = vxlan_nexthop_event; for (h = 0; h < PORT_HASH_SIZE; ++h) INIT_HLIST_HEAD(&vn->sock_list[h]); - return register_nexthop_notifier(net, &vxlan_nexthop_notifier_block); + return register_nexthop_notifier(net, &vn->nexthop_notifier_block, + NULL); } static void vxlan_destroy_tunnels(struct net *net, struct list_head *head) @@ -4740,8 +4744,11 @@ static void __net_exit vxlan_exit_batch_net(struct list_head *net_list) LIST_HEAD(list); rtnl_lock(); - list_for_each_entry(net, net_list, exit_list) - unregister_nexthop_notifier(net, &vxlan_nexthop_notifier_block); + list_for_each_entry(net, net_list, exit_list) { + struct vxlan_net *vn = net_generic(net, vxlan_net_id); + + unregister_nexthop_notifier(net, &vn->nexthop_notifier_block); + } list_for_each_entry(net, net_list, exit_list) vxlan_destroy_tunnels(net, &list); diff --git a/drivers/net/wan/hdlc_fr.c b/drivers/net/wan/hdlc_fr.c index 409e5a7ad8e2..0720f5f92caa 100644 --- a/drivers/net/wan/hdlc_fr.c +++ b/drivers/net/wan/hdlc_fr.c @@ -871,6 +871,45 @@ static int fr_lmi_recv(struct net_device *dev, struct sk_buff *skb) return 0; } +static int fr_snap_parse(struct sk_buff *skb, struct pvc_device *pvc) +{ + /* OUI 00-00-00 indicates an Ethertype follows */ + if (skb->data[0] == 0x00 && + skb->data[1] == 0x00 && + skb->data[2] == 0x00) { + if (!pvc->main) + return -1; + skb->dev = pvc->main; + skb->protocol = *(__be16 *)(skb->data + 3); /* Ethertype */ + skb_pull(skb, 5); + skb_reset_mac_header(skb); + return 0; + + /* OUI 00-80-C2 stands for the 802.1 organization */ + } else if (skb->data[0] == 0x00 && + skb->data[1] == 0x80 && + skb->data[2] == 0xC2) { + /* PID 00-07 stands for Ethernet frames without FCS */ + if (skb->data[3] == 0x00 && + skb->data[4] == 0x07) { + if (!pvc->ether) + return -1; + skb_pull(skb, 5); + if (skb->len < ETH_HLEN) + return -1; + skb->protocol = eth_type_trans(skb, pvc->ether); + return 0; + + /* PID unsupported */ + } else { + return -1; + } + + /* OUI unsupported */ + } else { + return -1; + } +} static int fr_rx(struct sk_buff *skb) { @@ -880,9 +919,9 @@ static int fr_rx(struct sk_buff *skb) u8 *data = skb->data; u16 dlci; struct pvc_device *pvc; - struct net_device *dev = NULL; + struct net_device *dev; - if (skb->len <= 4 || fh->ea1 || data[2] != FR_UI) + if (skb->len < 4 || fh->ea1 || !fh->ea2 || data[2] != FR_UI) goto rx_error; dlci = q922_to_dlci(skb->data); @@ -904,8 +943,7 @@ static int fr_rx(struct sk_buff *skb) netdev_info(frad, "No PVC for received frame's DLCI %d\n", dlci); #endif - dev_kfree_skb_any(skb); - return NET_RX_DROP; + goto rx_drop; } if (pvc->state.fecn != fh->fecn) { @@ -931,63 +969,51 @@ static int fr_rx(struct sk_buff *skb) } if (data[3] == NLPID_IP) { + if (!pvc->main) + goto rx_drop; skb_pull(skb, 4); /* Remove 4-byte header (hdr, UI, NLPID) */ - dev = pvc->main; + skb->dev = pvc->main; skb->protocol = htons(ETH_P_IP); + skb_reset_mac_header(skb); } else if (data[3] == NLPID_IPV6) { + if (!pvc->main) + goto rx_drop; skb_pull(skb, 4); /* Remove 4-byte header (hdr, UI, NLPID) */ - dev = pvc->main; + skb->dev = pvc->main; skb->protocol = htons(ETH_P_IPV6); + skb_reset_mac_header(skb); - } else if (skb->len > 10 && data[3] == FR_PAD && - data[4] == NLPID_SNAP && data[5] == FR_PAD) { - u16 oui = ntohs(*(__be16*)(data + 6)); - u16 pid = ntohs(*(__be16*)(data + 8)); - skb_pull(skb, 10); - - switch ((((u32)oui) << 16) | pid) { - case ETH_P_ARP: /* routed frame with SNAP */ - case ETH_P_IPX: - case ETH_P_IP: /* a long variant */ - case ETH_P_IPV6: - dev = pvc->main; - skb->protocol = htons(pid); - break; - - case 0x80C20007: /* bridged Ethernet frame */ - if ((dev = pvc->ether) != NULL) - skb->protocol = eth_type_trans(skb, dev); - break; - - default: - netdev_info(frad, "Unsupported protocol, OUI=%x PID=%x\n", - oui, pid); - dev_kfree_skb_any(skb); - return NET_RX_DROP; + } else if (data[3] == FR_PAD) { + if (skb->len < 5) + goto rx_error; + if (data[4] == NLPID_SNAP) { /* A SNAP header follows */ + skb_pull(skb, 5); + if (skb->len < 5) /* Incomplete SNAP header */ + goto rx_error; + if (fr_snap_parse(skb, pvc)) + goto rx_drop; + } else { + goto rx_drop; } + } else { netdev_info(frad, "Unsupported protocol, NLPID=%x length=%i\n", data[3], skb->len); - dev_kfree_skb_any(skb); - return NET_RX_DROP; + goto rx_drop; } - if (dev) { - dev->stats.rx_packets++; /* PVC traffic */ - dev->stats.rx_bytes += skb->len; - if (pvc->state.becn) - dev->stats.rx_compressed++; - skb->dev = dev; - netif_rx(skb); - return NET_RX_SUCCESS; - } else { - dev_kfree_skb_any(skb); - return NET_RX_DROP; - } + dev = skb->dev; + dev->stats.rx_packets++; /* PVC traffic */ + dev->stats.rx_bytes += skb->len; + if (pvc->state.becn) + dev->stats.rx_compressed++; + netif_rx(skb); + return NET_RX_SUCCESS; - rx_error: +rx_error: frad->stats.rx_errors++; /* Mark error */ +rx_drop: dev_kfree_skb_any(skb); return NET_RX_DROP; } diff --git a/drivers/net/wan/lmc/lmc_main.c b/drivers/net/wan/lmc/lmc_main.c index 36600b0a0ab0..93c7e8502845 100644 --- a/drivers/net/wan/lmc/lmc_main.c +++ b/drivers/net/wan/lmc/lmc_main.c @@ -353,9 +353,8 @@ int lmc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) /*fold00*/ switch(xc.command){ case lmc_xilinx_reset: /*fold02*/ { - u16 mii; spin_lock_irqsave(&sc->lmc_lock, flags); - mii = lmc_mii_readreg (sc, 0, 16); + lmc_mii_readreg (sc, 0, 16); /* * Make all of them 0 and make input @@ -424,10 +423,9 @@ int lmc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) /*fold00*/ break; case lmc_xilinx_load_prom: /*fold02*/ { - u16 mii; int timeout = 500000; spin_lock_irqsave(&sc->lmc_lock, flags); - mii = lmc_mii_readreg (sc, 0, 16); + lmc_mii_readreg (sc, 0, 16); /* * Make all of them 0 and make input @@ -1185,7 +1183,6 @@ static irqreturn_t lmc_interrupt (int irq, void *dev_instance) /*fold00*/ int i; s32 stat; unsigned int badtx; - u32 firstcsr; int max_work = LMC_RXDESCS; int handled = 0; @@ -1203,8 +1200,6 @@ static irqreturn_t lmc_interrupt (int irq, void *dev_instance) /*fold00*/ goto lmc_int_fail_out; } - firstcsr = csr; - /* always go through this loop at least once */ while (csr & sc->lmc_intrmask) { handled = 1; diff --git a/drivers/net/wimax/Kconfig b/drivers/net/wimax/Kconfig deleted file mode 100644 index 2249e3d77a76..000000000000 --- a/drivers/net/wimax/Kconfig +++ /dev/null @@ -1,18 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -# -# WiMAX LAN device drivers configuration -# - - -comment "Enable WiMAX (Networking options) to see the WiMAX drivers" - depends on WIMAX = n - -if WIMAX - -menu "WiMAX Wireless Broadband devices" - -source "drivers/net/wimax/i2400m/Kconfig" - -endmenu - -endif diff --git a/drivers/net/wimax/Makefile b/drivers/net/wimax/Makefile deleted file mode 100644 index b4575bacf994..000000000000 --- a/drivers/net/wimax/Makefile +++ /dev/null @@ -1,2 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -obj-$(CONFIG_WIMAX_I2400M) += i2400m/ diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 3e9895bec15f..920cac4385bf 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -2413,12 +2413,11 @@ static ssize_t store_rxbuf(struct device *dev, const char *buf, size_t len) { char *endp; - unsigned long target; if (!capable(CAP_NET_ADMIN)) return -EPERM; - target = simple_strtoul(buf, &endp, 0); + simple_strtoul(buf, &endp, 0); if (endp == buf) return -EBADMSG; diff --git a/drivers/soc/fsl/qbman/qman.c b/drivers/soc/fsl/qbman/qman.c index 9888a7061873..101def7dc73d 100644 --- a/drivers/soc/fsl/qbman/qman.c +++ b/drivers/soc/fsl/qbman/qman.c @@ -1159,7 +1159,7 @@ static u32 fq_to_tag(struct qman_fq *fq) static u32 __poll_portal_slow(struct qman_portal *p, u32 is); static inline unsigned int __poll_portal_fast(struct qman_portal *p, - unsigned int poll_limit); + unsigned int poll_limit, bool sched_napi); static void qm_congestion_task(struct work_struct *work); static void qm_mr_process_task(struct work_struct *work); @@ -1174,7 +1174,7 @@ static irqreturn_t portal_isr(int irq, void *ptr) /* DQRR-handling if it's interrupt-driven */ if (is & QM_PIRQ_DQRI) { - __poll_portal_fast(p, QMAN_POLL_LIMIT); + __poll_portal_fast(p, QMAN_POLL_LIMIT, true); clear = QM_DQAVAIL_MASK | QM_PIRQ_DQRI; } /* Handling of anything else that's interrupt-driven */ @@ -1602,7 +1602,7 @@ static noinline void clear_vdqcr(struct qman_portal *p, struct qman_fq *fq) * user callbacks to call into any QMan API. */ static inline unsigned int __poll_portal_fast(struct qman_portal *p, - unsigned int poll_limit) + unsigned int poll_limit, bool sched_napi) { const struct qm_dqrr_entry *dq; struct qman_fq *fq; @@ -1636,7 +1636,7 @@ static inline unsigned int __poll_portal_fast(struct qman_portal *p, * and we don't want multiple if()s in the critical * path (SDQCR). */ - res = fq->cb.dqrr(p, fq, dq); + res = fq->cb.dqrr(p, fq, dq, sched_napi); if (res == qman_cb_dqrr_stop) break; /* Check for VDQCR completion */ @@ -1646,7 +1646,7 @@ static inline unsigned int __poll_portal_fast(struct qman_portal *p, /* SDQCR: context_b points to the FQ */ fq = tag_to_fq(be32_to_cpu(dq->context_b)); /* Now let the callback do its stuff */ - res = fq->cb.dqrr(p, fq, dq); + res = fq->cb.dqrr(p, fq, dq, sched_napi); /* * The callback can request that we exit without * consuming this entry nor advancing; @@ -1753,7 +1753,7 @@ EXPORT_SYMBOL(qman_start_using_portal); int qman_p_poll_dqrr(struct qman_portal *p, unsigned int limit) { - return __poll_portal_fast(p, limit); + return __poll_portal_fast(p, limit, false); } EXPORT_SYMBOL(qman_p_poll_dqrr); diff --git a/drivers/soc/fsl/qbman/qman_test_api.c b/drivers/soc/fsl/qbman/qman_test_api.c index 7066b2f1467c..28fbddc3c204 100644 --- a/drivers/soc/fsl/qbman/qman_test_api.c +++ b/drivers/soc/fsl/qbman/qman_test_api.c @@ -45,7 +45,8 @@ static enum qman_cb_dqrr_result cb_dqrr(struct qman_portal *, struct qman_fq *, - const struct qm_dqrr_entry *); + const struct qm_dqrr_entry *, + bool sched_napi); static void cb_ern(struct qman_portal *, struct qman_fq *, const union qm_mr_entry *); static void cb_fqs(struct qman_portal *, struct qman_fq *, @@ -208,7 +209,8 @@ failed: static enum qman_cb_dqrr_result cb_dqrr(struct qman_portal *p, struct qman_fq *fq, - const struct qm_dqrr_entry *dq) + const struct qm_dqrr_entry *dq, + bool sched_napi) { if (WARN_ON(fd_neq(&fd_dq, &dq->fd))) { pr_err("BADNESS: dequeued frame doesn't match;\n"); diff --git a/drivers/soc/fsl/qbman/qman_test_stash.c b/drivers/soc/fsl/qbman/qman_test_stash.c index e87b65403b67..b7e8e5ec884c 100644 --- a/drivers/soc/fsl/qbman/qman_test_stash.c +++ b/drivers/soc/fsl/qbman/qman_test_stash.c @@ -275,7 +275,8 @@ static inline int process_frame_data(struct hp_handler *handler, static enum qman_cb_dqrr_result normal_dqrr(struct qman_portal *portal, struct qman_fq *fq, - const struct qm_dqrr_entry *dqrr) + const struct qm_dqrr_entry *dqrr, + bool sched_napi) { struct hp_handler *handler = (struct hp_handler *)fq; @@ -293,7 +294,8 @@ skip: static enum qman_cb_dqrr_result special_dqrr(struct qman_portal *portal, struct qman_fq *fq, - const struct qm_dqrr_entry *dqrr) + const struct qm_dqrr_entry *dqrr, + bool sched_napi) { struct hp_handler *handler = (struct hp_handler *)fq; diff --git a/drivers/staging/Kconfig b/drivers/staging/Kconfig index 2d0310448eba..443ca3f3cdf0 100644 --- a/drivers/staging/Kconfig +++ b/drivers/staging/Kconfig @@ -114,6 +114,8 @@ source "drivers/staging/kpc2000/Kconfig" source "drivers/staging/qlge/Kconfig" +source "drivers/staging/wimax/Kconfig" + source "drivers/staging/wfx/Kconfig" source "drivers/staging/hikey9xx/Kconfig" diff --git a/drivers/staging/Makefile b/drivers/staging/Makefile index 757a892ab5b9..dc45128ef525 100644 --- a/drivers/staging/Makefile +++ b/drivers/staging/Makefile @@ -47,5 +47,6 @@ obj-$(CONFIG_XIL_AXIS_FIFO) += axis-fifo/ obj-$(CONFIG_FIELDBUS_DEV) += fieldbus/ obj-$(CONFIG_KPC2000) += kpc2000/ obj-$(CONFIG_QLGE) += qlge/ +obj-$(CONFIG_WIMAX) += wimax/ obj-$(CONFIG_WFX) += wfx/ obj-y += hikey9xx/ diff --git a/Documentation/admin-guide/wimax/i2400m.rst b/drivers/staging/wimax/Documentation/i2400m.rst index 194388c0c351..194388c0c351 100644 --- a/Documentation/admin-guide/wimax/i2400m.rst +++ b/drivers/staging/wimax/Documentation/i2400m.rst diff --git a/Documentation/admin-guide/wimax/index.rst b/drivers/staging/wimax/Documentation/index.rst index fdf7c1f99ff5..fdf7c1f99ff5 100644 --- a/Documentation/admin-guide/wimax/index.rst +++ b/drivers/staging/wimax/Documentation/index.rst diff --git a/Documentation/admin-guide/wimax/wimax.rst b/drivers/staging/wimax/Documentation/wimax.rst index 817ee8ba2732..817ee8ba2732 100644 --- a/Documentation/admin-guide/wimax/wimax.rst +++ b/drivers/staging/wimax/Documentation/wimax.rst diff --git a/net/wimax/Kconfig b/drivers/staging/wimax/Kconfig index d13762bc4abc..ded8b70b25ee 100644 --- a/net/wimax/Kconfig +++ b/drivers/staging/wimax/Kconfig @@ -22,6 +22,8 @@ menuconfig WIMAX If unsure, it is safe to select M (module). +if WIMAX + config WIMAX_DEBUG_LEVEL int "WiMAX debug level" depends on WIMAX @@ -38,3 +40,7 @@ config WIMAX_DEBUG_LEVEL If set at zero, this will compile out all the debug code. It is recommended that it is left at 8. + +source "drivers/staging/wimax/i2400m/Kconfig" + +endif diff --git a/net/wimax/Makefile b/drivers/staging/wimax/Makefile index c2a71ae487ac..0e3f988656aa 100644 --- a/net/wimax/Makefile +++ b/drivers/staging/wimax/Makefile @@ -11,3 +11,5 @@ wimax-y := \ stack.o wimax-$(CONFIG_DEBUG_FS) += debugfs.o + +obj-$(CONFIG_WIMAX_I2400M) += i2400m/ diff --git a/drivers/staging/wimax/TODO b/drivers/staging/wimax/TODO new file mode 100644 index 000000000000..26e4cb9e9599 --- /dev/null +++ b/drivers/staging/wimax/TODO @@ -0,0 +1,18 @@ +There are no known users of this driver as of October 2020, and it will +be removed unless someone turns out to still need it in future releases. + +According to https://en.wikipedia.org/wiki/List_of_WiMAX_networks, there +have been many public wimax networks, but it appears that many of these +have migrated to LTE or discontinued their service altogether. As most +PCs and phones lack WiMAX hardware support, the remaining networks tend +to use standalone routers. These almost certainly run Linux, but not a +modern kernel or the mainline wimax driver stack. + +NetworkManager appears to have dropped userspace support in 2015 +https://bugzilla.gnome.org/show_bug.cgi?id=747846, the www.linuxwimax.org +site had already shut down earlier. + +WiMax is apparently still being deployed on airport campus networks +("AeroMACS"), but in a frequency band that was not supported by the old +Intel 2400m (used in Sandy Bridge laptops and earlier), which is the +only driver using the kernel's wimax stack. diff --git a/net/wimax/debug-levels.h b/drivers/staging/wimax/debug-levels.h index ebc287cde336..b854802d1d00 100644 --- a/net/wimax/debug-levels.h +++ b/drivers/staging/wimax/debug-levels.h @@ -13,7 +13,7 @@ #define D_MODULENAME wimax #define D_MASTER CONFIG_WIMAX_DEBUG_LEVEL -#include <linux/wimax/debug.h> +#include "linux-wimax-debug.h" /* List of all the enabled modules */ enum d_module { diff --git a/net/wimax/debugfs.c b/drivers/staging/wimax/debugfs.c index 3c54bb6b925a..e11bff61ffcf 100644 --- a/net/wimax/debugfs.c +++ b/drivers/staging/wimax/debugfs.c @@ -7,7 +7,7 @@ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com> */ #include <linux/debugfs.h> -#include <linux/wimax.h> +#include "linux-wimax.h" #include "wimax-internal.h" #define D_SUBMODULE debugfs diff --git a/drivers/net/wimax/i2400m/Kconfig b/drivers/staging/wimax/i2400m/Kconfig index 843b905a26a3..843b905a26a3 100644 --- a/drivers/net/wimax/i2400m/Kconfig +++ b/drivers/staging/wimax/i2400m/Kconfig diff --git a/drivers/net/wimax/i2400m/Makefile b/drivers/staging/wimax/i2400m/Makefile index b1db1eff0648..b1db1eff0648 100644 --- a/drivers/net/wimax/i2400m/Makefile +++ b/drivers/staging/wimax/i2400m/Makefile diff --git a/drivers/net/wimax/i2400m/control.c b/drivers/staging/wimax/i2400m/control.c index 8df98757d901..fe885aa56cf3 100644 --- a/drivers/net/wimax/i2400m/control.c +++ b/drivers/staging/wimax/i2400m/control.c @@ -77,7 +77,7 @@ #include "i2400m.h" #include <linux/kernel.h> #include <linux/slab.h> -#include <linux/wimax/i2400m.h> +#include "linux-wimax-i2400m.h" #include <linux/export.h> #include <linux/moduleparam.h> diff --git a/drivers/net/wimax/i2400m/debug-levels.h b/drivers/staging/wimax/i2400m/debug-levels.h index 00942bb1489b..a317e9fbb734 100644 --- a/drivers/net/wimax/i2400m/debug-levels.h +++ b/drivers/staging/wimax/i2400m/debug-levels.h @@ -13,7 +13,7 @@ #define D_MODULENAME i2400m #define D_MASTER CONFIG_WIMAX_I2400M_DEBUG_LEVEL -#include <linux/wimax/debug.h> +#include "../linux-wimax-debug.h" /* List of all the enabled modules */ enum d_module { diff --git a/drivers/net/wimax/i2400m/debugfs.c b/drivers/staging/wimax/i2400m/debugfs.c index 1c640b41ea4c..1c640b41ea4c 100644 --- a/drivers/net/wimax/i2400m/debugfs.c +++ b/drivers/staging/wimax/i2400m/debugfs.c diff --git a/drivers/net/wimax/i2400m/driver.c b/drivers/staging/wimax/i2400m/driver.c index ecb3fccca603..dc8939ff78c0 100644 --- a/drivers/net/wimax/i2400m/driver.c +++ b/drivers/staging/wimax/i2400m/driver.c @@ -50,7 +50,7 @@ */ #include "i2400m.h" #include <linux/etherdevice.h> -#include <linux/wimax/i2400m.h> +#include "linux-wimax-i2400m.h" #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/suspend.h> diff --git a/drivers/net/wimax/i2400m/fw.c b/drivers/staging/wimax/i2400m/fw.c index 6c9a41bff2e0..6c9a41bff2e0 100644 --- a/drivers/net/wimax/i2400m/fw.c +++ b/drivers/staging/wimax/i2400m/fw.c diff --git a/drivers/net/wimax/i2400m/i2400m-usb.h b/drivers/staging/wimax/i2400m/i2400m-usb.h index eff4f464a23e..eff4f464a23e 100644 --- a/drivers/net/wimax/i2400m/i2400m-usb.h +++ b/drivers/staging/wimax/i2400m/i2400m-usb.h diff --git a/drivers/net/wimax/i2400m/i2400m.h b/drivers/staging/wimax/i2400m/i2400m.h index a3733a6d14f5..de22cc6f2c5c 100644 --- a/drivers/net/wimax/i2400m/i2400m.h +++ b/drivers/staging/wimax/i2400m/i2400m.h @@ -156,8 +156,8 @@ #include <linux/completion.h> #include <linux/rwsem.h> #include <linux/atomic.h> -#include <net/wimax.h> -#include <linux/wimax/i2400m.h> +#include "../net-wimax.h" +#include "linux-wimax-i2400m.h" #include <asm/byteorder.h> enum { diff --git a/include/uapi/linux/wimax/i2400m.h b/drivers/staging/wimax/i2400m/linux-wimax-i2400m.h index fd198bc24a3c..fd198bc24a3c 100644 --- a/include/uapi/linux/wimax/i2400m.h +++ b/drivers/staging/wimax/i2400m/linux-wimax-i2400m.h diff --git a/drivers/net/wimax/i2400m/netdev.c b/drivers/staging/wimax/i2400m/netdev.c index a7fcbceb6e6b..a7fcbceb6e6b 100644 --- a/drivers/net/wimax/i2400m/netdev.c +++ b/drivers/staging/wimax/i2400m/netdev.c diff --git a/drivers/net/wimax/i2400m/op-rfkill.c b/drivers/staging/wimax/i2400m/op-rfkill.c index 5c79f052cad2..fbddf2e18c14 100644 --- a/drivers/net/wimax/i2400m/op-rfkill.c +++ b/drivers/staging/wimax/i2400m/op-rfkill.c @@ -18,7 +18,7 @@ * switch (coming from sysfs, the wimax stack or user space). */ #include "i2400m.h" -#include <linux/wimax/i2400m.h> +#include "linux-wimax-i2400m.h" #include <linux/slab.h> diff --git a/drivers/net/wimax/i2400m/rx.c b/drivers/staging/wimax/i2400m/rx.c index c9fb619a9e01..c9fb619a9e01 100644 --- a/drivers/net/wimax/i2400m/rx.c +++ b/drivers/staging/wimax/i2400m/rx.c diff --git a/drivers/net/wimax/i2400m/sysfs.c b/drivers/staging/wimax/i2400m/sysfs.c index 895ee265909b..895ee265909b 100644 --- a/drivers/net/wimax/i2400m/sysfs.c +++ b/drivers/staging/wimax/i2400m/sysfs.c diff --git a/drivers/net/wimax/i2400m/tx.c b/drivers/staging/wimax/i2400m/tx.c index 1255302e251e..1255302e251e 100644 --- a/drivers/net/wimax/i2400m/tx.c +++ b/drivers/staging/wimax/i2400m/tx.c diff --git a/drivers/net/wimax/i2400m/usb-debug-levels.h b/drivers/staging/wimax/i2400m/usb-debug-levels.h index b6f7335de765..8fd0111560f6 100644 --- a/drivers/net/wimax/i2400m/usb-debug-levels.h +++ b/drivers/staging/wimax/i2400m/usb-debug-levels.h @@ -13,7 +13,7 @@ #define D_MODULENAME i2400m_usb #define D_MASTER CONFIG_WIMAX_I2400M_DEBUG_LEVEL -#include <linux/wimax/debug.h> +#include "../linux-wimax-debug.h" /* List of all the enabled modules */ enum d_module { diff --git a/drivers/net/wimax/i2400m/usb-fw.c b/drivers/staging/wimax/i2400m/usb-fw.c index 27ab233650d5..27ab233650d5 100644 --- a/drivers/net/wimax/i2400m/usb-fw.c +++ b/drivers/staging/wimax/i2400m/usb-fw.c diff --git a/drivers/net/wimax/i2400m/usb-notif.c b/drivers/staging/wimax/i2400m/usb-notif.c index 5d429f816125..5d429f816125 100644 --- a/drivers/net/wimax/i2400m/usb-notif.c +++ b/drivers/staging/wimax/i2400m/usb-notif.c diff --git a/drivers/net/wimax/i2400m/usb-rx.c b/drivers/staging/wimax/i2400m/usb-rx.c index 5b64bda7d9e7..5b64bda7d9e7 100644 --- a/drivers/net/wimax/i2400m/usb-rx.c +++ b/drivers/staging/wimax/i2400m/usb-rx.c diff --git a/drivers/net/wimax/i2400m/usb-tx.c b/drivers/staging/wimax/i2400m/usb-tx.c index 3ba9d70cca1b..3ba9d70cca1b 100644 --- a/drivers/net/wimax/i2400m/usb-tx.c +++ b/drivers/staging/wimax/i2400m/usb-tx.c diff --git a/drivers/net/wimax/i2400m/usb.c b/drivers/staging/wimax/i2400m/usb.c index b684e97ac976..3b84dd7b5567 100644 --- a/drivers/net/wimax/i2400m/usb.c +++ b/drivers/staging/wimax/i2400m/usb.c @@ -49,7 +49,7 @@ * usb_reset_device() */ #include "i2400m-usb.h" -#include <linux/wimax/i2400m.h> +#include "linux-wimax-i2400m.h" #include <linux/debugfs.h> #include <linux/slab.h> #include <linux/module.h> diff --git a/net/wimax/id-table.c b/drivers/staging/wimax/id-table.c index 02eee37b7e31..0e6f4aa87bc9 100644 --- a/net/wimax/id-table.c +++ b/drivers/staging/wimax/id-table.c @@ -28,7 +28,7 @@ #include <net/genetlink.h> #include <linux/netdevice.h> #include <linux/list.h> -#include <linux/wimax.h> +#include "linux-wimax.h" #include "wimax-internal.h" diff --git a/include/linux/wimax/debug.h b/drivers/staging/wimax/linux-wimax-debug.h index cdae052bcdcd..5b5ec405143b 100644 --- a/include/linux/wimax/debug.h +++ b/drivers/staging/wimax/linux-wimax-debug.h @@ -60,7 +60,7 @@ * #define D_MODULENAME modulename * #define D_MASTER 10 * - * #include <linux/wimax/debug.h> + * #include "linux-wimax-debug.h" * * enum d_module { * D_SUBMODULE_DECLARE(submodule_1), diff --git a/include/uapi/linux/wimax.h b/drivers/staging/wimax/linux-wimax.h index 9f6b77af2f6d..9f6b77af2f6d 100644 --- a/include/uapi/linux/wimax.h +++ b/drivers/staging/wimax/linux-wimax.h diff --git a/include/net/wimax.h b/drivers/staging/wimax/net-wimax.h index f6e31d2f47aa..f578e345e2bd 100644 --- a/include/net/wimax.h +++ b/drivers/staging/wimax/net-wimax.h @@ -236,7 +236,7 @@ #ifndef __NET__WIMAX_H__ #define __NET__WIMAX_H__ -#include <linux/wimax.h> +#include "linux-wimax.h" #include <net/genetlink.h> #include <linux/netdevice.h> diff --git a/net/wimax/op-msg.c b/drivers/staging/wimax/op-msg.c index 6460b5785758..e20ac7d84e82 100644 --- a/net/wimax/op-msg.c +++ b/drivers/staging/wimax/op-msg.c @@ -60,7 +60,7 @@ #include <linux/slab.h> #include <net/genetlink.h> #include <linux/netdevice.h> -#include <linux/wimax.h> +#include "linux-wimax.h" #include <linux/security.h> #include <linux/export.h> #include "wimax-internal.h" diff --git a/net/wimax/op-reset.c b/drivers/staging/wimax/op-reset.c index 9899b2e56721..b3f000cbe112 100644 --- a/net/wimax/op-reset.c +++ b/drivers/staging/wimax/op-reset.c @@ -13,9 +13,9 @@ * disconnect and reconnect the device). */ -#include <net/wimax.h> +#include "net-wimax.h" #include <net/genetlink.h> -#include <linux/wimax.h> +#include "linux-wimax.h" #include <linux/security.h> #include <linux/export.h> #include "wimax-internal.h" diff --git a/net/wimax/op-rfkill.c b/drivers/staging/wimax/op-rfkill.c index 248d10b60b05..78b294481a59 100644 --- a/net/wimax/op-rfkill.c +++ b/drivers/staging/wimax/op-rfkill.c @@ -45,9 +45,9 @@ * wimax_rfkill_rm() [called by wimax_dev_add/rm()] */ -#include <net/wimax.h> +#include "net-wimax.h" #include <net/genetlink.h> -#include <linux/wimax.h> +#include "linux-wimax.h" #include <linux/security.h> #include <linux/rfkill.h> #include <linux/export.h> diff --git a/net/wimax/op-state-get.c b/drivers/staging/wimax/op-state-get.c index 5bc712de1563..c5bfbed505f5 100644 --- a/net/wimax/op-state-get.c +++ b/drivers/staging/wimax/op-state-get.c @@ -10,9 +10,9 @@ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com> */ -#include <net/wimax.h> +#include "net-wimax.h" #include <net/genetlink.h> -#include <linux/wimax.h> +#include "linux-wimax.h" #include <linux/security.h> #include "wimax-internal.h" diff --git a/net/wimax/stack.c b/drivers/staging/wimax/stack.c index b6dd9d956ed8..ace24a6dfd2d 100644 --- a/net/wimax/stack.c +++ b/drivers/staging/wimax/stack.c @@ -39,7 +39,7 @@ #include <linux/gfp.h> #include <net/genetlink.h> #include <linux/netdevice.h> -#include <linux/wimax.h> +#include "linux-wimax.h" #include <linux/module.h> #include "wimax-internal.h" @@ -388,17 +388,24 @@ void wimax_dev_init(struct wimax_dev *wimax_dev) } EXPORT_SYMBOL_GPL(wimax_dev_init); +/* + * There are multiple enums reusing the same values, adding + * others is only possible if they use a compatible policy. + */ static const struct nla_policy wimax_gnl_policy[WIMAX_GNL_ATTR_MAX + 1] = { - [WIMAX_GNL_RESET_IFIDX] = { .type = NLA_U32, }, - [WIMAX_GNL_RFKILL_IFIDX] = { .type = NLA_U32, }, - [WIMAX_GNL_RFKILL_STATE] = { - .type = NLA_U32 /* enum wimax_rf_state */ - }, - [WIMAX_GNL_STGET_IFIDX] = { .type = NLA_U32, }, - [WIMAX_GNL_MSG_IFIDX] = { .type = NLA_U32, }, - [WIMAX_GNL_MSG_DATA] = { - .type = NLA_UNSPEC, /* libnl doesn't grok BINARY yet */ - }, + /* + * WIMAX_GNL_RESET_IFIDX, WIMAX_GNL_RFKILL_IFIDX, + * WIMAX_GNL_STGET_IFIDX, WIMAX_GNL_MSG_IFIDX + */ + [1] = { .type = NLA_U32, }, + /* + * WIMAX_GNL_RFKILL_STATE, WIMAX_GNL_MSG_PIPE_NAME + */ + [2] = { .type = NLA_U32, }, /* enum wimax_rf_state */ + /* + * WIMAX_GNL_MSG_DATA + */ + [3] = { .type = NLA_UNSPEC, }, /* libnl doesn't grok BINARY yet */ }; static const struct genl_small_ops wimax_gnl_ops[] = { diff --git a/net/wimax/wimax-internal.h b/drivers/staging/wimax/wimax-internal.h index 40751207296c..a6b6990642a1 100644 --- a/net/wimax/wimax-internal.h +++ b/drivers/staging/wimax/wimax-internal.h @@ -22,7 +22,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/device.h> -#include <net/wimax.h> +#include "net-wimax.h" /* diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 556caed00258..b979005ea39c 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -25,6 +25,7 @@ struct br_ip { #if IS_ENABLED(CONFIG_IPV6) struct in6_addr ip6; #endif + unsigned char mac_addr[ETH_ALEN]; } dst; __be16 proto; __u16 vid; diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h index ff7b7607c8cf..52b1610eae68 100644 --- a/include/linux/marvell_phy.h +++ b/include/linux/marvell_phy.h @@ -25,6 +25,9 @@ #define MARVELL_PHY_ID_88X3310 0x002b09a0 #define MARVELL_PHY_ID_88E2110 0x002b09b0 +/* Marvel 88E1111 in Finisar SFP module with modified PHY ID */ +#define MARVELL_PHY_ID_88E1111_FINISAR 0x01ff0cc0 + /* The MV88e6390 Ethernet switch contains embedded PHYs. These PHYs do * not have a model ID. So the switch driver traps reads to the ID2 * register and returns the switch family ID diff --git a/include/linux/mhi.h b/include/linux/mhi.h index d4841e5a5f45..b9bb7dff32e2 100644 --- a/include/linux/mhi.h +++ b/include/linux/mhi.h @@ -737,4 +737,11 @@ int mhi_queue_buf(struct mhi_device *mhi_dev, enum dma_data_direction dir, int mhi_queue_skb(struct mhi_device *mhi_dev, enum dma_data_direction dir, struct sk_buff *skb, size_t len, enum mhi_flags mflags); +/** + * mhi_queue_is_full - Determine whether queueing new elements is possible + * @mhi_dev: Device associated with the channels + * @dir: DMA direction for the channel + */ +bool mhi_queue_is_full(struct mhi_device *mhi_dev, enum dma_data_direction dir); + #endif /* _MHI_H_ */ diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 0b17c4322b09..934de56644e7 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -207,8 +207,8 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start) NETIF_F_FSO) /* List of features with software fallbacks. */ -#define NETIF_F_GSO_SOFTWARE (NETIF_F_ALL_TSO | \ - NETIF_F_GSO_SCTP) +#define NETIF_F_GSO_SOFTWARE (NETIF_F_ALL_TSO | NETIF_F_GSO_SCTP | \ + NETIF_F_GSO_UDP_L4 | NETIF_F_GSO_FRAGLIST) /* * If one device supports one of these features, then enable them diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 964b494b0e8d..a53ed2d1ed1d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2557,6 +2557,18 @@ static inline void dev_sw_netstats_rx_add(struct net_device *dev, unsigned int l u64_stats_update_end(&tstats->syncp); } +static inline void dev_sw_netstats_tx_add(struct net_device *dev, + unsigned int packets, + unsigned int len) +{ + struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); + + u64_stats_update_begin(&tstats->syncp); + tstats->tx_bytes += len; + tstats->tx_packets += packets; + u64_stats_update_end(&tstats->syncp); +} + static inline void dev_lstats_add(struct net_device *dev, unsigned int len) { struct pcpu_lstats *lstats = this_cpu_ptr(dev->lstats); @@ -2584,6 +2596,20 @@ static inline void dev_lstats_add(struct net_device *dev, unsigned int len) #define netdev_alloc_pcpu_stats(type) \ __netdev_alloc_pcpu_stats(type, GFP_KERNEL) +#define devm_netdev_alloc_pcpu_stats(dev, type) \ +({ \ + typeof(type) __percpu *pcpu_stats = devm_alloc_percpu(dev, type);\ + if (pcpu_stats) { \ + int __cpu; \ + for_each_possible_cpu(__cpu) { \ + typeof(type) *stat; \ + stat = per_cpu_ptr(pcpu_stats, __cpu); \ + u64_stats_init(&stat->syncp); \ + } \ + } \ + pcpu_stats; \ +}) + enum netdev_lag_tx_type { NETDEV_LAG_TX_TYPE_UNKNOWN, NETDEV_LAG_TX_TYPE_RANDOM, diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index ab192720e2d6..46d9a0c26c67 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -198,6 +198,9 @@ struct ip_set_region { u32 elements; /* Number of elements vs timeout */ }; +/* The max revision number supported by any set type + 1 */ +#define IPSET_REVISION_MAX 9 + /* The core set type structure */ struct ip_set_type { struct list_head list; @@ -215,6 +218,8 @@ struct ip_set_type { u8 family; /* Type revisions */ u8 revision_min, revision_max; + /* Revision-specific supported (create) flags */ + u8 create_flags[IPSET_REVISION_MAX+1]; /* Set features to control swapping */ u16 features; diff --git a/include/linux/phy.h b/include/linux/phy.h index 56563e5e0dc7..8849a00a093f 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1480,6 +1480,7 @@ int genphy_suspend(struct phy_device *phydev); int genphy_resume(struct phy_device *phydev); int genphy_loopback(struct phy_device *phydev, bool enable); int genphy_soft_reset(struct phy_device *phydev); +irqreturn_t genphy_handle_interrupt_no_ack(struct phy_device *phydev); static inline int genphy_config_aneg(struct phy_device *phydev) { @@ -1540,8 +1541,10 @@ void phy_drivers_unregister(struct phy_driver *drv, int n); int phy_driver_register(struct phy_driver *new_driver, struct module *owner); int phy_drivers_register(struct phy_driver *new_driver, int n, struct module *owner); +void phy_error(struct phy_device *phydev); void phy_state_machine(struct work_struct *work); void phy_queue_state_machine(struct phy_device *phydev, unsigned long jiffies); +void phy_trigger_machine(struct phy_device *phydev); void phy_mac_interrupt(struct phy_device *phydev); void phy_start_machine(struct phy_device *phydev); void phy_stop_machine(struct phy_device *phydev); diff --git a/include/linux/platform_data/hirschmann-hellcreek.h b/include/linux/platform_data/hirschmann-hellcreek.h new file mode 100644 index 000000000000..388846766bb2 --- /dev/null +++ b/include/linux/platform_data/hirschmann-hellcreek.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: (GPL-2.0 or MIT) */ +/* + * Hirschmann Hellcreek TSN switch platform data. + * + * Copyright (C) 2020 Linutronix GmbH + * Author Kurt Kanzenbach <kurt@linutronix.de> + */ + +#ifndef _HIRSCHMANN_HELLCREEK_H_ +#define _HIRSCHMANN_HELLCREEK_H_ + +#include <linux/types.h> + +struct hellcreek_platform_data { + int num_ports; /* Amount of switch ports */ + int is_100_mbits; /* Is it configured to 100 or 1000 mbit/s */ + int qbv_support; /* Qbv support on front TSN ports */ + int qbv_on_cpu_port; /* Qbv support on the CPU port */ + int qbu_support; /* Qbu support on front TSN ports */ + u16 module_id; /* Module identificaton */ +}; + +#endif /* _HIRSCHMANN_HELLCREEK_H_ */ diff --git a/include/linux/sctp.h b/include/linux/sctp.h index 76731230bbc5..bb1926589693 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -482,11 +482,13 @@ enum sctp_error { * 11 Restart of an association with new addresses * 12 User Initiated Abort * 13 Protocol Violation + * 14 Restart of an Association with New Encapsulation Port */ SCTP_ERROR_RESTART = cpu_to_be16(0x0b), SCTP_ERROR_USER_ABORT = cpu_to_be16(0x0c), SCTP_ERROR_PROTO_VIOLATION = cpu_to_be16(0x0d), + SCTP_ERROR_NEW_ENCAP_PORT = cpu_to_be16(0x0e), /* ADDIP Section 3.3 New Error Causes * @@ -793,4 +795,22 @@ enum { SCTP_FLOWLABEL_VAL_MASK = 0xfffff }; +/* UDP Encapsulation + * draft-tuexen-tsvwg-sctp-udp-encaps-cons-03.html#section-4-4 + * + * The error cause indicating an "Restart of an Association with + * New Encapsulation Port" + * + * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | Cause Code = 14 | Cause Length = 8 | + * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + * | Current Encapsulation Port | New Encapsulation Port | + * +-------------------------------+-------------------------------+ + */ +struct sctp_new_encap_port_hdr { + __be16 cur_port; + __be16 new_port; +}; + #endif /* __LINUX_SCTP_H__ */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a828cf99c521..2d01b2bbb746 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4151,6 +4151,9 @@ enum skb_ext_id { #if IS_ENABLED(CONFIG_MPTCP) SKB_EXT_MPTCP, #endif +#if IS_ENABLED(CONFIG_KCOV) + SKB_EXT_KCOV_HANDLE, +#endif SKB_EXT_NUM, /* must be last */ }; @@ -4605,5 +4608,35 @@ static inline void skb_reset_redirect(struct sk_buff *skb) #endif } +#ifdef CONFIG_KCOV +static inline void skb_set_kcov_handle(struct sk_buff *skb, + const u64 kcov_handle) +{ + /* Do not allocate skb extensions only to set kcov_handle to zero + * (as it is zero by default). However, if the extensions are + * already allocated, update kcov_handle anyway since + * skb_set_kcov_handle can be called to zero a previously set + * value. + */ + if (skb_has_extensions(skb) || kcov_handle) { + u64 *kcov_handle_ptr = skb_ext_add(skb, SKB_EXT_KCOV_HANDLE); + + if (kcov_handle_ptr) + *kcov_handle_ptr = kcov_handle; + } +} + +static inline u64 skb_get_kcov_handle(struct sk_buff *skb) +{ + u64 *kcov_handle = skb_ext_find(skb, SKB_EXT_KCOV_HANDLE); + + return kcov_handle ? *kcov_handle : 0; +} +#else +static inline void skb_set_kcov_handle(struct sk_buff *skb, + const u64 kcov_handle) { } +static inline u64 skb_get_kcov_handle(struct sk_buff *skb) { return 0; } +#endif /* CONFIG_KCOV */ + #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ diff --git a/include/linux/usb/r8152.h b/include/linux/usb/r8152.h new file mode 100644 index 000000000000..20d88b1defc3 --- /dev/null +++ b/include/linux/usb/r8152.h @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2020 Realtek Semiconductor Corp. All rights reserved. + */ + +#ifndef __LINUX_R8152_H +#define __LINUX_R8152_H + +#define RTL8152_REQT_READ 0xc0 +#define RTL8152_REQT_WRITE 0x40 +#define RTL8152_REQ_GET_REGS 0x05 +#define RTL8152_REQ_SET_REGS 0x05 + +#define BYTE_EN_DWORD 0xff +#define BYTE_EN_WORD 0x33 +#define BYTE_EN_BYTE 0x11 +#define BYTE_EN_SIX_BYTES 0x3f +#define BYTE_EN_START_MASK 0x0f +#define BYTE_EN_END_MASK 0xf0 + +#define MCU_TYPE_PLA 0x0100 +#define MCU_TYPE_USB 0x0000 + +/* Define these values to match your device */ +#define VENDOR_ID_REALTEK 0x0bda +#define VENDOR_ID_MICROSOFT 0x045e +#define VENDOR_ID_SAMSUNG 0x04e8 +#define VENDOR_ID_LENOVO 0x17ef +#define VENDOR_ID_LINKSYS 0x13b1 +#define VENDOR_ID_NVIDIA 0x0955 +#define VENDOR_ID_TPLINK 0x2357 + +#if IS_REACHABLE(CONFIG_USB_RTL8152) +extern u8 rtl8152_get_version(struct usb_interface *intf); +#endif + +#endif /* __LINUX_R8152_H */ diff --git a/include/net/dsa.h b/include/net/dsa.h index 35429a140dfa..4e60d2610f20 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -45,6 +45,7 @@ struct phylink_link_state; #define DSA_TAG_PROTO_OCELOT_VALUE 15 #define DSA_TAG_PROTO_AR9331_VALUE 16 #define DSA_TAG_PROTO_RTL4_A_VALUE 17 +#define DSA_TAG_PROTO_HELLCREEK_VALUE 18 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, @@ -65,6 +66,7 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_OCELOT = DSA_TAG_PROTO_OCELOT_VALUE, DSA_TAG_PROTO_AR9331 = DSA_TAG_PROTO_AR9331_VALUE, DSA_TAG_PROTO_RTL4_A = DSA_TAG_PROTO_RTL4_A_VALUE, + DSA_TAG_PROTO_HELLCREEK = DSA_TAG_PROTO_HELLCREEK_VALUE, }; struct packet_type; @@ -535,6 +537,12 @@ struct dsa_switch_ops { struct ethtool_regs *regs, void *p); /* + * Upper device tracking. + */ + int (*port_prechangeupper)(struct dsa_switch *ds, int port, + struct netdev_notifier_changeupper_info *info); + + /* * Bridge integration */ int (*set_ageing_time)(struct dsa_switch *ds, unsigned int msecs); diff --git a/include/net/dst.h b/include/net/dst.h index 8ea8812b0b41..10f0a8399867 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -400,14 +400,12 @@ static inline struct neighbour *dst_neigh_lookup(const struct dst_entry *dst, co static inline struct neighbour *dst_neigh_lookup_skb(const struct dst_entry *dst, struct sk_buff *skb) { - struct neighbour *n = NULL; + struct neighbour *n; - /* The packets from tunnel devices (eg bareudp) may have only - * metadata in the dst pointer of skb. Hence a pointer check of - * neigh_lookup is needed. - */ - if (dst->ops->neigh_lookup) - n = dst->ops->neigh_lookup(dst, skb, NULL); + if (WARN_ON_ONCE(!dst->ops->neigh_lookup)) + return NULL; + + n = dst->ops->neigh_lookup(dst, skb, NULL); return IS_ERR(n) ? NULL : n; } diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 753ba7e755d6..6e706d838e4e 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -29,7 +29,8 @@ struct mptcp_ext { use_ack:1, ack64:1, mpc_map:1, - __unused:2; + frozen:1, + __unused:1; /* one byte hole */ }; @@ -106,6 +107,19 @@ static inline void mptcp_skb_ext_move(struct sk_buff *to, from->active_extensions = 0; } +static inline void mptcp_skb_ext_copy(struct sk_buff *to, + struct sk_buff *from) +{ + struct mptcp_ext *from_ext; + + from_ext = skb_ext_find(from, SKB_EXT_MPTCP); + if (!from_ext) + return; + + from_ext->frozen = 1; + skb_ext_copy(to, from); +} + static inline bool mptcp_ext_matches(const struct mptcp_ext *to_ext, const struct mptcp_ext *from_ext) { @@ -193,6 +207,11 @@ static inline void mptcp_skb_ext_move(struct sk_buff *to, { } +static inline void mptcp_skb_ext_copy(struct sk_buff *to, + struct sk_buff *from) +{ +} + static inline bool mptcp_skb_can_collapse(const struct sk_buff *to, const struct sk_buff *from) { diff --git a/include/net/netfilter/ipv4/nf_reject.h b/include/net/netfilter/ipv4/nf_reject.h index 40e0e0623f46..0d8ff84a2588 100644 --- a/include/net/netfilter/ipv4/nf_reject.h +++ b/include/net/netfilter/ipv4/nf_reject.h @@ -18,4 +18,14 @@ struct iphdr *nf_reject_iphdr_put(struct sk_buff *nskb, void nf_reject_ip_tcphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb, const struct tcphdr *oth); +struct sk_buff *nf_reject_skb_v4_unreach(struct net *net, + struct sk_buff *oldskb, + const struct net_device *dev, + int hook, u8 code); +struct sk_buff *nf_reject_skb_v4_tcp_reset(struct net *net, + struct sk_buff *oldskb, + const struct net_device *dev, + int hook); + + #endif /* _IPV4_NF_REJECT_H */ diff --git a/include/net/netfilter/ipv6/nf_reject.h b/include/net/netfilter/ipv6/nf_reject.h index 4a3ef9ebdf6f..edcf6d1cd316 100644 --- a/include/net/netfilter/ipv6/nf_reject.h +++ b/include/net/netfilter/ipv6/nf_reject.h @@ -20,4 +20,13 @@ void nf_reject_ip6_tcphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb, const struct tcphdr *oth, unsigned int otcplen); +struct sk_buff *nf_reject_skb_v6_tcp_reset(struct net *net, + struct sk_buff *oldskb, + const struct net_device *dev, + int hook); +struct sk_buff *nf_reject_skb_v6_unreach(struct net *net, + struct sk_buff *oldskb, + const struct net_device *dev, + int hook, u8 code); + #endif /* _IPV6_NF_REJECT_H */ diff --git a/include/net/netns/sctp.h b/include/net/netns/sctp.h index d8d02e4188d1..a0f315effa94 100644 --- a/include/net/netns/sctp.h +++ b/include/net/netns/sctp.h @@ -22,6 +22,14 @@ struct netns_sctp { */ struct sock *ctl_sock; + /* UDP tunneling listening sock. */ + struct sock *udp4_sock; + struct sock *udp6_sock; + /* UDP tunneling listening port. */ + int udp_port; + /* UDP tunneling remote encap port. */ + int encap_port; + /* This is the global local address list. * We actively maintain this complete list of addresses on * the system by catching address add/delete events. diff --git a/include/net/nexthop.h b/include/net/nexthop.h index 2fd76a9b6dc8..226930d66b63 100644 --- a/include/net/nexthop.h +++ b/include/net/nexthop.h @@ -105,11 +105,49 @@ struct nexthop { }; enum nexthop_event_type { - NEXTHOP_EVENT_DEL + NEXTHOP_EVENT_DEL, + NEXTHOP_EVENT_REPLACE, }; -int register_nexthop_notifier(struct net *net, struct notifier_block *nb); +struct nh_notifier_single_info { + struct net_device *dev; + u8 gw_family; + union { + __be32 ipv4; + struct in6_addr ipv6; + }; + u8 is_reject:1, + is_fdb:1, + has_encap:1; +}; + +struct nh_notifier_grp_entry_info { + u8 weight; + u32 id; + struct nh_notifier_single_info nh; +}; + +struct nh_notifier_grp_info { + u16 num_nh; + bool is_fdb; + struct nh_notifier_grp_entry_info nh_entries[]; +}; + +struct nh_notifier_info { + struct net *net; + struct netlink_ext_ack *extack; + u32 id; + bool is_grp; + union { + struct nh_notifier_single_info *nh; + struct nh_notifier_grp_info *nh_grp; + }; +}; + +int register_nexthop_notifier(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack); int unregister_nexthop_notifier(struct net *net, struct notifier_block *nb); +void nexthop_set_hw_flags(struct net *net, u32 id, bool offload, bool trap); /* caller is holding rcu or rtnl; no reference taken to nexthop */ struct nexthop *nexthop_find_by_id(struct net *net, u32 id); diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h index 122d9e2d8dfd..14a0d22c9113 100644 --- a/include/net/sctp/constants.h +++ b/include/net/sctp/constants.h @@ -286,6 +286,8 @@ enum { SCTP_MAX_GABS = 16 }; * functions simpler to write. */ +#define SCTP_DEFAULT_UDP_PORT 9899 /* default UDP tunneling port */ + /* These are the values for pf exposure, UNUSED is to keep compatible with old * applications by default. */ diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 4fc747b778eb..86f74f2fe6de 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -84,6 +84,8 @@ int sctp_copy_local_addr_list(struct net *net, struct sctp_bind_addr *addr, struct sctp_pf *sctp_get_pf_specific(sa_family_t family); int sctp_register_pf(struct sctp_pf *, sa_family_t); void sctp_addr_wq_mgmt(struct net *, struct sctp_sockaddr_entry *, int); +int sctp_udp_sock_start(struct net *net); +void sctp_udp_sock_stop(struct net *net); /* * sctp/socket.c @@ -576,10 +578,13 @@ static inline __u32 sctp_mtu_payload(const struct sctp_sock *sp, { __u32 overhead = sizeof(struct sctphdr) + extra; - if (sp) + if (sp) { overhead += sp->pf->af->net_header_len; - else + if (sp->udp_port) + overhead += sizeof(struct udphdr); + } else { overhead += sizeof(struct ipv6hdr); + } if (WARN_ON_ONCE(mtu && mtu <= overhead)) mtu = overhead; diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index 5c491a3bc27e..fd223c94589a 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -221,6 +221,9 @@ struct sctp_chunk *sctp_make_violation_paramlen( struct sctp_chunk *sctp_make_violation_max_retrans( const struct sctp_association *asoc, const struct sctp_chunk *chunk); +struct sctp_chunk *sctp_make_new_encap_port( + const struct sctp_association *asoc, + const struct sctp_chunk *chunk); struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc, const struct sctp_transport *transport); struct sctp_chunk *sctp_make_heartbeat_ack(const struct sctp_association *asoc, @@ -380,6 +383,7 @@ sctp_vtag_verify(const struct sctp_chunk *chunk, if (ntohl(chunk->sctp_hdr->vtag) == asoc->c.my_vtag) return 1; + chunk->transport->encap_port = SCTP_INPUT_CB(chunk->skb)->encap_port; return 0; } diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 0bdff38eb4bb..1aa585216f34 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -178,6 +178,9 @@ struct sctp_sock { */ __u32 hbinterval; + __be16 udp_port; + __be16 encap_port; + /* This is the max_retrans value for new associations. */ __u16 pathmaxrxt; @@ -877,6 +880,8 @@ struct sctp_transport { */ unsigned long last_time_ecne_reduced; + __be16 encap_port; + /* This is the max_retrans value for the transport and will * be initialized from the assocs value. This can be changed * using the SCTP_SET_PEER_ADDR_PARAMS socket option. @@ -1117,13 +1122,14 @@ static inline void sctp_outq_cork(struct sctp_outq *q) */ struct sctp_input_cb { union { - struct inet_skb_parm h4; + struct inet_skb_parm h4; #if IS_ENABLED(CONFIG_IPV6) - struct inet6_skb_parm h6; + struct inet6_skb_parm h6; #endif } header; struct sctp_chunk *chunk; struct sctp_af *af; + __be16 encap_port; }; #define SCTP_INPUT_CB(__skb) ((struct sctp_input_cb *)&((__skb)->cb[0])) @@ -1790,6 +1796,8 @@ struct sctp_association { */ unsigned long hbinterval; + __be16 encap_port; + /* This is the max_retrans value for new transports in the * association. */ diff --git a/include/net/tcp.h b/include/net/tcp.h index d4ef5bf94168..4aba0f069b05 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -386,7 +386,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, int tcp_child_process(struct sock *parent, struct sock *child, struct sk_buff *skb); void tcp_enter_loss(struct sock *sk); -void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int flag); +void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int newly_lost, int flag); void tcp_clear_retrans(struct tcp_sock *tp); void tcp_update_metrics(struct sock *sk); void tcp_init_metrics(struct sock *sk); diff --git a/include/soc/fsl/qman.h b/include/soc/fsl/qman.h index 9f484113cfda..59eeba31c192 100644 --- a/include/soc/fsl/qman.h +++ b/include/soc/fsl/qman.h @@ -689,7 +689,8 @@ enum qman_cb_dqrr_result { }; typedef enum qman_cb_dqrr_result (*qman_cb_dqrr)(struct qman_portal *qm, struct qman_fq *fq, - const struct qm_dqrr_entry *dqrr); + const struct qm_dqrr_entry *dqrr, + bool sched_napi); /* * This callback type is used when handling ERNs, FQRNs and FQRLs via MR. They diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 1e9db9577441..ea1de185f2e4 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -571,18 +571,21 @@ struct ocelot_vcap_block { int pol_lpr; }; +struct ocelot_vlan { + bool valid; + u16 vid; +}; + struct ocelot_port { struct ocelot *ocelot; struct regmap *target; bool vlan_aware; - - /* Ingress default VLAN (pvid) */ - u16 pvid; - - /* Egress default VLAN (vid) */ - u16 vid; + /* VLAN that untagged frames are classified to, on ingress */ + struct ocelot_vlan pvid_vlan; + /* The VLAN ID that will be transmitted as untagged, on egress */ + struct ocelot_vlan native_vlan; u8 ptp_cmd; struct sk_buff_head tx_skbs; @@ -632,6 +635,7 @@ struct ocelot { u32 *lags; struct list_head multicast; + struct list_head pgids; struct list_head dummy_rules; struct ocelot_vcap_block block[3]; @@ -743,6 +747,8 @@ int ocelot_fdb_add(struct ocelot *ocelot, int port, const unsigned char *addr, u16 vid); int ocelot_fdb_del(struct ocelot *ocelot, int port, const unsigned char *addr, u16 vid); +int ocelot_vlan_prepare(struct ocelot *ocelot, int port, u16 vid, bool pvid, + bool untagged); int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid, bool untagged); int ocelot_vlan_del(struct ocelot *ocelot, int port, u16 vid); diff --git a/include/uapi/linux/cfm_bridge.h b/include/uapi/linux/cfm_bridge.h new file mode 100644 index 000000000000..3c1cbd1db2f5 --- /dev/null +++ b/include/uapi/linux/cfm_bridge.h @@ -0,0 +1,64 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ + +#ifndef _UAPI_LINUX_CFM_BRIDGE_H_ +#define _UAPI_LINUX_CFM_BRIDGE_H_ + +#include <linux/types.h> +#include <linux/if_ether.h> + +#define ETHER_HEADER_LENGTH (6+6+4+2) +#define CFM_MAID_LENGTH 48 +#define CFM_CCM_PDU_LENGTH 75 +#define CFM_PORT_STATUS_TLV_LENGTH 4 +#define CFM_IF_STATUS_TLV_LENGTH 4 +#define CFM_IF_STATUS_TLV_TYPE 4 +#define CFM_PORT_STATUS_TLV_TYPE 2 +#define CFM_ENDE_TLV_TYPE 0 +#define CFM_CCM_MAX_FRAME_LENGTH (ETHER_HEADER_LENGTH+\ + CFM_CCM_PDU_LENGTH+\ + CFM_PORT_STATUS_TLV_LENGTH+\ + CFM_IF_STATUS_TLV_LENGTH) +#define CFM_FRAME_PRIO 7 +#define CFM_CCM_TLV_OFFSET 70 +#define CFM_CCM_PDU_MAID_OFFSET 10 +#define CFM_CCM_PDU_MEPID_OFFSET 8 +#define CFM_CCM_PDU_SEQNR_OFFSET 4 +#define CFM_CCM_PDU_TLV_OFFSET 74 +#define CFM_CCM_ITU_RESERVED_SIZE 16 + +struct br_cfm_common_hdr { + __u8 mdlevel_version; + __u8 opcode; + __u8 flags; + __u8 tlv_offset; +}; + +enum br_cfm_opcodes { + BR_CFM_OPCODE_CCM = 0x1, +}; + +/* MEP domain */ +enum br_cfm_domain { + BR_CFM_PORT, + BR_CFM_VLAN, +}; + +/* MEP direction */ +enum br_cfm_mep_direction { + BR_CFM_MEP_DIRECTION_DOWN, + BR_CFM_MEP_DIRECTION_UP, +}; + +/* CCM interval supported. */ +enum br_cfm_ccm_interval { + BR_CFM_CCM_INTERVAL_NONE, + BR_CFM_CCM_INTERVAL_3_3_MS, + BR_CFM_CCM_INTERVAL_10_MS, + BR_CFM_CCM_INTERVAL_100_MS, + BR_CFM_CCM_INTERVAL_1_SEC, + BR_CFM_CCM_INTERVAL_10_SEC, + BR_CFM_CCM_INTERVAL_1_MIN, + BR_CFM_CCM_INTERVAL_10_MIN, +}; + +#endif diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index 4c687686aa8f..13d59c51ef5b 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -121,6 +121,7 @@ enum { IFLA_BRIDGE_VLAN_INFO, IFLA_BRIDGE_VLAN_TUNNEL_INFO, IFLA_BRIDGE_MRP, + IFLA_BRIDGE_CFM, __IFLA_BRIDGE_MAX, }; #define IFLA_BRIDGE_MAX (__IFLA_BRIDGE_MAX - 1) @@ -328,6 +329,130 @@ struct br_mrp_start_in_test { __u16 in_id; }; +enum { + IFLA_BRIDGE_CFM_UNSPEC, + IFLA_BRIDGE_CFM_MEP_CREATE, + IFLA_BRIDGE_CFM_MEP_DELETE, + IFLA_BRIDGE_CFM_MEP_CONFIG, + IFLA_BRIDGE_CFM_CC_CONFIG, + IFLA_BRIDGE_CFM_CC_PEER_MEP_ADD, + IFLA_BRIDGE_CFM_CC_PEER_MEP_REMOVE, + IFLA_BRIDGE_CFM_CC_RDI, + IFLA_BRIDGE_CFM_CC_CCM_TX, + IFLA_BRIDGE_CFM_MEP_CREATE_INFO, + IFLA_BRIDGE_CFM_MEP_CONFIG_INFO, + IFLA_BRIDGE_CFM_CC_CONFIG_INFO, + IFLA_BRIDGE_CFM_CC_RDI_INFO, + IFLA_BRIDGE_CFM_CC_CCM_TX_INFO, + IFLA_BRIDGE_CFM_CC_PEER_MEP_INFO, + IFLA_BRIDGE_CFM_MEP_STATUS_INFO, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_INFO, + __IFLA_BRIDGE_CFM_MAX, +}; + +#define IFLA_BRIDGE_CFM_MAX (__IFLA_BRIDGE_CFM_MAX - 1) + +enum { + IFLA_BRIDGE_CFM_MEP_CREATE_UNSPEC, + IFLA_BRIDGE_CFM_MEP_CREATE_INSTANCE, + IFLA_BRIDGE_CFM_MEP_CREATE_DOMAIN, + IFLA_BRIDGE_CFM_MEP_CREATE_DIRECTION, + IFLA_BRIDGE_CFM_MEP_CREATE_IFINDEX, + __IFLA_BRIDGE_CFM_MEP_CREATE_MAX, +}; + +#define IFLA_BRIDGE_CFM_MEP_CREATE_MAX (__IFLA_BRIDGE_CFM_MEP_CREATE_MAX - 1) + +enum { + IFLA_BRIDGE_CFM_MEP_DELETE_UNSPEC, + IFLA_BRIDGE_CFM_MEP_DELETE_INSTANCE, + __IFLA_BRIDGE_CFM_MEP_DELETE_MAX, +}; + +#define IFLA_BRIDGE_CFM_MEP_DELETE_MAX (__IFLA_BRIDGE_CFM_MEP_DELETE_MAX - 1) + +enum { + IFLA_BRIDGE_CFM_MEP_CONFIG_UNSPEC, + IFLA_BRIDGE_CFM_MEP_CONFIG_INSTANCE, + IFLA_BRIDGE_CFM_MEP_CONFIG_UNICAST_MAC, + IFLA_BRIDGE_CFM_MEP_CONFIG_MDLEVEL, + IFLA_BRIDGE_CFM_MEP_CONFIG_MEPID, + __IFLA_BRIDGE_CFM_MEP_CONFIG_MAX, +}; + +#define IFLA_BRIDGE_CFM_MEP_CONFIG_MAX (__IFLA_BRIDGE_CFM_MEP_CONFIG_MAX - 1) + +enum { + IFLA_BRIDGE_CFM_CC_CONFIG_UNSPEC, + IFLA_BRIDGE_CFM_CC_CONFIG_INSTANCE, + IFLA_BRIDGE_CFM_CC_CONFIG_ENABLE, + IFLA_BRIDGE_CFM_CC_CONFIG_EXP_INTERVAL, + IFLA_BRIDGE_CFM_CC_CONFIG_EXP_MAID, + __IFLA_BRIDGE_CFM_CC_CONFIG_MAX, +}; + +#define IFLA_BRIDGE_CFM_CC_CONFIG_MAX (__IFLA_BRIDGE_CFM_CC_CONFIG_MAX - 1) + +enum { + IFLA_BRIDGE_CFM_CC_PEER_MEP_UNSPEC, + IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE, + IFLA_BRIDGE_CFM_CC_PEER_MEPID, + __IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX, +}; + +#define IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX (__IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX - 1) + +enum { + IFLA_BRIDGE_CFM_CC_RDI_UNSPEC, + IFLA_BRIDGE_CFM_CC_RDI_INSTANCE, + IFLA_BRIDGE_CFM_CC_RDI_RDI, + __IFLA_BRIDGE_CFM_CC_RDI_MAX, +}; + +#define IFLA_BRIDGE_CFM_CC_RDI_MAX (__IFLA_BRIDGE_CFM_CC_RDI_MAX - 1) + +enum { + IFLA_BRIDGE_CFM_CC_CCM_TX_UNSPEC, + IFLA_BRIDGE_CFM_CC_CCM_TX_INSTANCE, + IFLA_BRIDGE_CFM_CC_CCM_TX_DMAC, + IFLA_BRIDGE_CFM_CC_CCM_TX_SEQ_NO_UPDATE, + IFLA_BRIDGE_CFM_CC_CCM_TX_PERIOD, + IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV, + IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV_VALUE, + IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV, + IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV_VALUE, + __IFLA_BRIDGE_CFM_CC_CCM_TX_MAX, +}; + +#define IFLA_BRIDGE_CFM_CC_CCM_TX_MAX (__IFLA_BRIDGE_CFM_CC_CCM_TX_MAX - 1) + +enum { + IFLA_BRIDGE_CFM_MEP_STATUS_UNSPEC, + IFLA_BRIDGE_CFM_MEP_STATUS_INSTANCE, + IFLA_BRIDGE_CFM_MEP_STATUS_OPCODE_UNEXP_SEEN, + IFLA_BRIDGE_CFM_MEP_STATUS_VERSION_UNEXP_SEEN, + IFLA_BRIDGE_CFM_MEP_STATUS_RX_LEVEL_LOW_SEEN, + __IFLA_BRIDGE_CFM_MEP_STATUS_MAX, +}; + +#define IFLA_BRIDGE_CFM_MEP_STATUS_MAX (__IFLA_BRIDGE_CFM_MEP_STATUS_MAX - 1) + +enum { + IFLA_BRIDGE_CFM_CC_PEER_STATUS_UNSPEC, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_INSTANCE, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_PEER_MEPID, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_CCM_DEFECT, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_RDI, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_PORT_TLV_VALUE, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_IF_TLV_VALUE, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEEN, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_TLV_SEEN, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEQ_UNEXP_SEEN, + __IFLA_BRIDGE_CFM_CC_PEER_STATUS_MAX, +}; + +#define IFLA_BRIDGE_CFM_CC_PEER_STATUS_MAX (__IFLA_BRIDGE_CFM_CC_PEER_STATUS_MAX - 1) + struct bridge_stp_xstats { __u64 transition_blk; __u64 transition_fwd; @@ -526,6 +651,7 @@ struct br_mdb_entry { union { __be32 ip4; struct in6_addr ip6; + unsigned char mac_addr[ETH_ALEN]; } u; __be16 proto; } addr; diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index d6de2b167448..a0b637911d3c 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -99,6 +99,7 @@ #define ETH_P_1588 0x88F7 /* IEEE 1588 Timesync */ #define ETH_P_NCSI 0x88F8 /* NCSI protocol */ #define ETH_P_PRP 0x88FB /* IEC 62439-3 PRP/HSRv0 */ +#define ETH_P_CFM 0x8902 /* Connectivity Fault Management */ #define ETH_P_FCOE 0x8906 /* Fibre Channel over Ethernet */ #define ETH_P_IBOE 0x8915 /* Infiniband over Ethernet */ #define ETH_P_TDLS 0x890D /* TDLS */ diff --git a/include/uapi/linux/netfilter/ipset/ip_set.h b/include/uapi/linux/netfilter/ipset/ip_set.h index 11a72a938eb1..6397d75899bc 100644 --- a/include/uapi/linux/netfilter/ipset/ip_set.h +++ b/include/uapi/linux/netfilter/ipset/ip_set.h @@ -92,11 +92,11 @@ enum { /* Reserve empty slots */ IPSET_ATTR_CADT_MAX = 16, /* Create-only specific attributes */ - IPSET_ATTR_GC, + IPSET_ATTR_INITVAL, /* was unused IPSET_ATTR_GC */ IPSET_ATTR_HASHSIZE, IPSET_ATTR_MAXELEM, IPSET_ATTR_NETMASK, - IPSET_ATTR_PROBES, + IPSET_ATTR_BUCKETSIZE, /* was unused IPSET_ATTR_PROBES */ IPSET_ATTR_RESIZE, IPSET_ATTR_SIZE, /* Kernel-only */ @@ -214,6 +214,8 @@ enum ipset_cadt_flags { enum ipset_create_flags { IPSET_CREATE_FLAG_BIT_FORCEADD = 0, IPSET_CREATE_FLAG_FORCEADD = (1 << IPSET_CREATE_FLAG_BIT_FORCEADD), + IPSET_CREATE_FLAG_BIT_BUCKETSIZE = 1, + IPSET_CREATE_FLAG_BUCKETSIZE = (1 << IPSET_CREATE_FLAG_BIT_BUCKETSIZE), IPSET_CREATE_FLAG_BIT_MAX = 7, }; diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 9b814c92de12..2ffbef5da6c1 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -396,11 +396,13 @@ struct rtnexthop { #define RTNH_F_DEAD 1 /* Nexthop is dead (used by multipath) */ #define RTNH_F_PERVASIVE 2 /* Do recursive gateway lookup */ #define RTNH_F_ONLINK 4 /* Gateway is forced on link */ -#define RTNH_F_OFFLOAD 8 /* offloaded route */ +#define RTNH_F_OFFLOAD 8 /* Nexthop is offloaded */ #define RTNH_F_LINKDOWN 16 /* carrier-down on nexthop */ #define RTNH_F_UNRESOLVED 32 /* The entry is unresolved (ipmr) */ +#define RTNH_F_TRAP 64 /* Nexthop is trapping packets */ -#define RTNH_COMPARE_MASK (RTNH_F_DEAD | RTNH_F_LINKDOWN | RTNH_F_OFFLOAD) +#define RTNH_COMPARE_MASK (RTNH_F_DEAD | RTNH_F_LINKDOWN | \ + RTNH_F_OFFLOAD | RTNH_F_TRAP) /* Macros to handle hexthops */ @@ -770,8 +772,12 @@ enum { * actions in a dump. All dump responses will contain the number of actions * being dumped stored in for user app's consumption in TCA_ROOT_COUNT * + * TCA_FLAG_TERSE_DUMP user->kernel to request terse (brief) dump that only + * includes essential action info (kind, index, etc.) + * */ #define TCA_FLAG_LARGE_DUMP_ON (1 << 0) +#define TCA_FLAG_TERSE_DUMP (1 << 1) /* New extended info filters for IFLA_EXT_MASK */ #define RTEXT_FILTER_VF (1 << 0) @@ -779,6 +785,8 @@ enum { #define RTEXT_FILTER_BRVLAN_COMPRESSED (1 << 2) #define RTEXT_FILTER_SKIP_STATS (1 << 3) #define RTEXT_FILTER_MRP (1 << 4) +#define RTEXT_FILTER_CFM_CONFIG (1 << 5) +#define RTEXT_FILTER_CFM_STATUS (1 << 6) /* End of information exported to user level */ diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index 28ad40d9acba..cb78e7a739da 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -140,6 +140,7 @@ typedef __s32 sctp_assoc_t; #define SCTP_ECN_SUPPORTED 130 #define SCTP_EXPOSE_POTENTIALLY_FAILED_STATE 131 #define SCTP_EXPOSE_PF_STATE SCTP_EXPOSE_POTENTIALLY_FAILED_STATE +#define SCTP_REMOTE_UDP_ENCAPS_PORT 132 /* PR-SCTP policies */ #define SCTP_PR_SCTP_NONE 0x0000 @@ -1197,6 +1198,12 @@ struct sctp_event { uint8_t se_on; }; +struct sctp_udpencaps { + sctp_assoc_t sue_assoc_id; + struct sockaddr_storage sue_address; + uint16_t sue_port; +}; + /* SCTP Stream schedulers */ enum sctp_sched_type { SCTP_SS_FCFS, diff --git a/kernel/kcov.c b/kernel/kcov.c index 6b8368be89c8..80bfe71bbe13 100644 --- a/kernel/kcov.c +++ b/kernel/kcov.c @@ -1023,6 +1023,8 @@ EXPORT_SYMBOL(kcov_remote_stop); /* See the comment before kcov_remote_start() for usage details. */ u64 kcov_common_handle(void) { + if (!in_task()) + return 0; return current->kcov_handle; } EXPORT_SYMBOL(kcov_common_handle); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index c789b39ed527..dd052a272fa7 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1870,6 +1870,7 @@ config KCOV depends on CC_HAS_SANCOV_TRACE_PC || GCC_PLUGINS select DEBUG_FS select GCC_PLUGIN_SANCOV if !CC_HAS_SANCOV_TRACE_PC + select SKB_EXTENSIONS help KCOV exposes kernel code coverage information in a form suitable for coverage-guided fuzzing (randomized testing). diff --git a/net/9p/client.c b/net/9p/client.c index 09f1ec589b80..785a7bb6a539 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -412,8 +412,9 @@ static void p9_tag_cleanup(struct p9_client *c) /** * p9_client_cb - call back from transport to client - * c: client state - * req: request received + * @c: client state + * @req: request received + * @status: request status, one of REQ_STATUS_* * */ void p9_client_cb(struct p9_client *c, struct p9_req_t *req, int status) @@ -555,6 +556,7 @@ out_err: * p9_check_zc_errors - check 9p packet for error return and process it * @c: current client instance * @req: request to parse and check for error conditions + * @uidata: external buffer containing error * @in_hdrlen: Size of response protocol buffer. * * returns error code if one is discovered, otherwise returns 0 diff --git a/net/9p/trans_common.c b/net/9p/trans_common.c index 3dff68f05fb9..6ea5ea548cd4 100644 --- a/net/9p/trans_common.c +++ b/net/9p/trans_common.c @@ -17,7 +17,9 @@ #include "trans_common.h" /** - * p9_release_pages - Release pages after the transaction. + * p9_release_pages - Release pages after the transaction. + * @pages: array of pages to be put + * @nr_pages: size of array */ void p9_release_pages(struct page **pages, int nr_pages) { diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index 8f528e783a6c..fa158397bb63 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -45,7 +45,7 @@ static struct p9_trans_module p9_fd_trans; * @rfd: file descriptor for reading (trans=fd) * @wfd: file descriptor for writing (trans=fd) * @port: port to connect to (trans=tcp) - * + * @privport: port is privileged */ struct p9_fd_opts { @@ -95,6 +95,8 @@ struct p9_poll_wait { * @err: error state * @req_list: accounting for requests which have been sent * @unsent_req_list: accounting for requests that haven't been sent + * @rreq: read request + * @wreq: write request * @req: current request being processed (if any) * @tmp_buf: temporary buffer to read in header * @rc: temporary fcall for reading current frame diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c index 2885ff9c76f0..af0a8a6cd3fd 100644 --- a/net/9p/trans_rdma.c +++ b/net/9p/trans_rdma.c @@ -99,6 +99,7 @@ struct p9_rdma_req; /** * struct p9_rdma_context - Keeps track of in-process WR * + * @cqe: completion queue entry * @busa: Bus address to unmap when the WR completes * @req: Keeps track of requests (send) * @rc: Keepts track of replies (receive) @@ -115,6 +116,7 @@ struct p9_rdma_context { /** * struct p9_rdma_opts - Collection of mount options * @port: port of connection + * @privport: Whether a privileged port may be used * @sq_depth: The requested depth of the SQ. This really doesn't need * to be any deeper than the number of threads used in the client * @rq_depth: The depth of the RQ. Should be greater than or equal to SQ depth diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index a3cd90a74012..93f2f8654882 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -50,7 +50,11 @@ static atomic_t vp_pinned = ATOMIC_INIT(0); * @client: client instance * @vdev: virtio dev associated with this channel * @vq: virtio queue associated with this channel + * @ring_bufs_avail: flag to indicate there is some available in the ring buf + * @vc_wq: wait queue for waiting for thing to be added to ring buf + * @p9_max_pages: maximum number of pinned pages * @sg: scatter gather list which is used to pack a request (protected?) + * @chan_list: linked list of channels * * We keep all per-channel information in a structure. * This structure is allocated within the devices dev->mem space. @@ -74,8 +78,8 @@ struct virtio_chan { unsigned long p9_max_pages; /* Scatterlist: can be too big for stack. */ struct scatterlist sg[VIRTQUEUE_NUM]; - /* - * tag name to identify a mount null terminated + /** + * @tag: name to identify a mount null terminated */ char *tag; @@ -204,6 +208,7 @@ static int p9_virtio_cancelled(struct p9_client *client, struct p9_req_t *req) * this takes a list of pages. * @sg: scatter/gather list to pack into * @start: which segment of the sg_list to start at + * @limit: maximum number of pages in sg list. * @pdata: a list of pages to add into sg. * @nr_pages: number of pages to pack into the scatter/gather list * @offs: amount of data in the beginning of first page _not_ to pack diff --git a/net/Kconfig b/net/Kconfig index d6567162c1cf..f4c32d982af6 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -386,8 +386,6 @@ source "net/mac80211/Kconfig" endif # WIRELESS -source "net/wimax/Kconfig" - source "net/rfkill/Kconfig" source "net/9p/Kconfig" source "net/caif/Kconfig" diff --git a/net/Makefile b/net/Makefile index 5744bf1997fd..d96b0aa8f39f 100644 --- a/net/Makefile +++ b/net/Makefile @@ -66,7 +66,6 @@ obj-$(CONFIG_MAC802154) += mac802154/ ifeq ($(CONFIG_NET),y) obj-$(CONFIG_SYSCTL) += sysctl_net.o endif -obj-$(CONFIG_WIMAX) += wimax/ obj-$(CONFIG_DNS_RESOLVER) += dns_resolver/ obj-$(CONFIG_CEPH_LIB) += ceph/ obj-$(CONFIG_BATMAN_ADV) += batman-adv/ diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c index 45f584171de7..be18af481d7d 100644 --- a/net/appletalk/aarp.c +++ b/net/appletalk/aarp.c @@ -44,15 +44,15 @@ int sysctl_aarp_resolve_time = AARP_RESOLVE_TIME; /* Lists of aarp entries */ /** * struct aarp_entry - AARP entry - * @last_sent - Last time we xmitted the aarp request - * @packet_queue - Queue of frames wait for resolution - * @status - Used for proxy AARP - * expires_at - Entry expiry time - * target_addr - DDP Address - * dev - Device to use - * hwaddr - Physical i/f address of target/router - * xmit_count - When this hits 10 we give up - * next - Next entry in chain + * @last_sent: Last time we xmitted the aarp request + * @packet_queue: Queue of frames wait for resolution + * @status: Used for proxy AARP + * @expires_at: Entry expiry time + * @target_addr: DDP Address + * @dev: Device to use + * @hwaddr: Physical i/f address of target/router + * @xmit_count: When this hits 10 we give up + * @next: Next entry in chain */ struct aarp_entry { /* These first two are only used for unresolved entries */ diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 1d48708c5a2e..ca1a0d07a087 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1407,9 +1407,10 @@ drop: /** * atalk_rcv - Receive a packet (in skb) from device dev - * @skb - packet received - * @dev - network device where the packet comes from - * @pt - packet type + * @skb: packet received + * @dev: network device where the packet comes from + * @pt: packet type + * @orig_dev: the original receive net device * * Receive a packet (in skb) from device dev. This has come from the SNAP * decoder, and on entry skb->transport_header is the DDP header, skb->len diff --git a/net/bridge/Kconfig b/net/bridge/Kconfig index 80879196560c..3c8ded7d3e84 100644 --- a/net/bridge/Kconfig +++ b/net/bridge/Kconfig @@ -73,3 +73,14 @@ config BRIDGE_MRP Say N to exclude this support and reduce the binary size. If unsure, say N. + +config BRIDGE_CFM + bool "CFM protocol" + depends on BRIDGE + help + If you say Y here, then the Ethernet bridge will be able to run CFM + protocol according to 802.1Q section 12.14 + + Say N to exclude this support and reduce the binary size. + + If unsure, say N. diff --git a/net/bridge/Makefile b/net/bridge/Makefile index ccb394236fbd..4702702a74d3 100644 --- a/net/bridge/Makefile +++ b/net/bridge/Makefile @@ -27,3 +27,5 @@ bridge-$(CONFIG_NET_SWITCHDEV) += br_switchdev.o obj-$(CONFIG_NETFILTER) += netfilter/ bridge-$(CONFIG_BRIDGE_MRP) += br_mrp_switchdev.o br_mrp.o br_mrp_netlink.o + +bridge-$(CONFIG_BRIDGE_CFM) += br_cfm.o br_cfm_netlink.o diff --git a/net/bridge/br_cfm.c b/net/bridge/br_cfm.c new file mode 100644 index 000000000000..001064f7583d --- /dev/null +++ b/net/bridge/br_cfm.c @@ -0,0 +1,867 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include <linux/cfm_bridge.h> +#include <uapi/linux/cfm_bridge.h> +#include "br_private_cfm.h" + +static struct br_cfm_mep *br_mep_find(struct net_bridge *br, u32 instance) +{ + struct br_cfm_mep *mep; + + hlist_for_each_entry(mep, &br->mep_list, head) + if (mep->instance == instance) + return mep; + + return NULL; +} + +static struct br_cfm_mep *br_mep_find_ifindex(struct net_bridge *br, + u32 ifindex) +{ + struct br_cfm_mep *mep; + + hlist_for_each_entry_rcu(mep, &br->mep_list, head, + lockdep_rtnl_is_held()) + if (mep->create.ifindex == ifindex) + return mep; + + return NULL; +} + +static struct br_cfm_peer_mep *br_peer_mep_find(struct br_cfm_mep *mep, + u32 mepid) +{ + struct br_cfm_peer_mep *peer_mep; + + hlist_for_each_entry_rcu(peer_mep, &mep->peer_mep_list, head, + lockdep_rtnl_is_held()) + if (peer_mep->mepid == mepid) + return peer_mep; + + return NULL; +} + +static struct net_bridge_port *br_mep_get_port(struct net_bridge *br, + u32 ifindex) +{ + struct net_bridge_port *port; + + list_for_each_entry(port, &br->port_list, list) + if (port->dev->ifindex == ifindex) + return port; + + return NULL; +} + +/* Calculate the CCM interval in us. */ +static u32 interval_to_us(enum br_cfm_ccm_interval interval) +{ + switch (interval) { + case BR_CFM_CCM_INTERVAL_NONE: + return 0; + case BR_CFM_CCM_INTERVAL_3_3_MS: + return 3300; + case BR_CFM_CCM_INTERVAL_10_MS: + return 10 * 1000; + case BR_CFM_CCM_INTERVAL_100_MS: + return 100 * 1000; + case BR_CFM_CCM_INTERVAL_1_SEC: + return 1000 * 1000; + case BR_CFM_CCM_INTERVAL_10_SEC: + return 10 * 1000 * 1000; + case BR_CFM_CCM_INTERVAL_1_MIN: + return 60 * 1000 * 1000; + case BR_CFM_CCM_INTERVAL_10_MIN: + return 10 * 60 * 1000 * 1000; + } + return 0; +} + +/* Convert the interface interval to CCM PDU value. */ +static u32 interval_to_pdu(enum br_cfm_ccm_interval interval) +{ + switch (interval) { + case BR_CFM_CCM_INTERVAL_NONE: + return 0; + case BR_CFM_CCM_INTERVAL_3_3_MS: + return 1; + case BR_CFM_CCM_INTERVAL_10_MS: + return 2; + case BR_CFM_CCM_INTERVAL_100_MS: + return 3; + case BR_CFM_CCM_INTERVAL_1_SEC: + return 4; + case BR_CFM_CCM_INTERVAL_10_SEC: + return 5; + case BR_CFM_CCM_INTERVAL_1_MIN: + return 6; + case BR_CFM_CCM_INTERVAL_10_MIN: + return 7; + } + return 0; +} + +/* Convert the CCM PDU value to interval on interface. */ +static u32 pdu_to_interval(u32 value) +{ + switch (value) { + case 0: + return BR_CFM_CCM_INTERVAL_NONE; + case 1: + return BR_CFM_CCM_INTERVAL_3_3_MS; + case 2: + return BR_CFM_CCM_INTERVAL_10_MS; + case 3: + return BR_CFM_CCM_INTERVAL_100_MS; + case 4: + return BR_CFM_CCM_INTERVAL_1_SEC; + case 5: + return BR_CFM_CCM_INTERVAL_10_SEC; + case 6: + return BR_CFM_CCM_INTERVAL_1_MIN; + case 7: + return BR_CFM_CCM_INTERVAL_10_MIN; + } + return BR_CFM_CCM_INTERVAL_NONE; +} + +static void ccm_rx_timer_start(struct br_cfm_peer_mep *peer_mep) +{ + u32 interval_us; + + interval_us = interval_to_us(peer_mep->mep->cc_config.exp_interval); + /* Function ccm_rx_dwork must be called with 1/4 + * of the configured CC 'expected_interval' + * in order to detect CCM defect after 3.25 interval. + */ + queue_delayed_work(system_wq, &peer_mep->ccm_rx_dwork, + usecs_to_jiffies(interval_us / 4)); +} + +static void br_cfm_notify(int event, const struct net_bridge_port *port) +{ + u32 filter = RTEXT_FILTER_CFM_STATUS; + + return br_info_notify(event, port->br, NULL, filter); +} + +static void cc_peer_enable(struct br_cfm_peer_mep *peer_mep) +{ + memset(&peer_mep->cc_status, 0, sizeof(peer_mep->cc_status)); + peer_mep->ccm_rx_count_miss = 0; + + ccm_rx_timer_start(peer_mep); +} + +static void cc_peer_disable(struct br_cfm_peer_mep *peer_mep) +{ + cancel_delayed_work_sync(&peer_mep->ccm_rx_dwork); +} + +static struct sk_buff *ccm_frame_build(struct br_cfm_mep *mep, + const struct br_cfm_cc_ccm_tx_info *const tx_info) + +{ + struct br_cfm_common_hdr *common_hdr; + struct net_bridge_port *b_port; + struct br_cfm_maid *maid; + u8 *itu_reserved, *e_tlv; + struct ethhdr *eth_hdr; + struct sk_buff *skb; + __be32 *status_tlv; + __be32 *snumber; + __be16 *mepid; + + skb = dev_alloc_skb(CFM_CCM_MAX_FRAME_LENGTH); + if (!skb) + return NULL; + + rcu_read_lock(); + b_port = rcu_dereference(mep->b_port); + if (!b_port) { + kfree_skb(skb); + rcu_read_unlock(); + return NULL; + } + skb->dev = b_port->dev; + rcu_read_unlock(); + /* The device cannot be deleted until the work_queue functions has + * completed. This function is called from ccm_tx_work_expired() + * that is a work_queue functions. + */ + + skb->protocol = htons(ETH_P_CFM); + skb->priority = CFM_FRAME_PRIO; + + /* Ethernet header */ + eth_hdr = skb_put(skb, sizeof(*eth_hdr)); + ether_addr_copy(eth_hdr->h_dest, tx_info->dmac.addr); + ether_addr_copy(eth_hdr->h_source, mep->config.unicast_mac.addr); + eth_hdr->h_proto = htons(ETH_P_CFM); + + /* Common CFM Header */ + common_hdr = skb_put(skb, sizeof(*common_hdr)); + common_hdr->mdlevel_version = mep->config.mdlevel << 5; + common_hdr->opcode = BR_CFM_OPCODE_CCM; + common_hdr->flags = (mep->rdi << 7) | + interval_to_pdu(mep->cc_config.exp_interval); + common_hdr->tlv_offset = CFM_CCM_TLV_OFFSET; + + /* Sequence number */ + snumber = skb_put(skb, sizeof(*snumber)); + if (tx_info->seq_no_update) { + *snumber = cpu_to_be32(mep->ccm_tx_snumber); + mep->ccm_tx_snumber += 1; + } else { + *snumber = 0; + } + + mepid = skb_put(skb, sizeof(*mepid)); + *mepid = cpu_to_be16((u16)mep->config.mepid); + + maid = skb_put(skb, sizeof(*maid)); + memcpy(maid->data, mep->cc_config.exp_maid.data, sizeof(maid->data)); + + /* ITU reserved (CFM_CCM_ITU_RESERVED_SIZE octets) */ + itu_reserved = skb_put(skb, CFM_CCM_ITU_RESERVED_SIZE); + memset(itu_reserved, 0, CFM_CCM_ITU_RESERVED_SIZE); + + /* Generel CFM TLV format: + * TLV type: one byte + * TLV value length: two bytes + * TLV value: 'TLV value length' bytes + */ + + /* Port status TLV. The value length is 1. Total of 4 bytes. */ + if (tx_info->port_tlv) { + status_tlv = skb_put(skb, sizeof(*status_tlv)); + *status_tlv = cpu_to_be32((CFM_PORT_STATUS_TLV_TYPE << 24) | + (1 << 8) | /* Value length */ + (tx_info->port_tlv_value & 0xFF)); + } + + /* Interface status TLV. The value length is 1. Total of 4 bytes. */ + if (tx_info->if_tlv) { + status_tlv = skb_put(skb, sizeof(*status_tlv)); + *status_tlv = cpu_to_be32((CFM_IF_STATUS_TLV_TYPE << 24) | + (1 << 8) | /* Value length */ + (tx_info->if_tlv_value & 0xFF)); + } + + /* End TLV */ + e_tlv = skb_put(skb, sizeof(*e_tlv)); + *e_tlv = CFM_ENDE_TLV_TYPE; + + return skb; +} + +static void ccm_frame_tx(struct sk_buff *skb) +{ + skb_reset_network_header(skb); + dev_queue_xmit(skb); +} + +/* This function is called with the configured CC 'expected_interval' + * in order to drive CCM transmission when enabled. + */ +static void ccm_tx_work_expired(struct work_struct *work) +{ + struct delayed_work *del_work; + struct br_cfm_mep *mep; + struct sk_buff *skb; + u32 interval_us; + + del_work = to_delayed_work(work); + mep = container_of(del_work, struct br_cfm_mep, ccm_tx_dwork); + + if (time_before_eq(mep->ccm_tx_end, jiffies)) { + /* Transmission period has ended */ + mep->cc_ccm_tx_info.period = 0; + return; + } + + skb = ccm_frame_build(mep, &mep->cc_ccm_tx_info); + if (skb) + ccm_frame_tx(skb); + + interval_us = interval_to_us(mep->cc_config.exp_interval); + queue_delayed_work(system_wq, &mep->ccm_tx_dwork, + usecs_to_jiffies(interval_us)); +} + +/* This function is called with 1/4 of the configured CC 'expected_interval' + * in order to detect CCM defect after 3.25 interval. + */ +static void ccm_rx_work_expired(struct work_struct *work) +{ + struct br_cfm_peer_mep *peer_mep; + struct net_bridge_port *b_port; + struct delayed_work *del_work; + + del_work = to_delayed_work(work); + peer_mep = container_of(del_work, struct br_cfm_peer_mep, ccm_rx_dwork); + + /* After 13 counts (4 * 3,25) then 3.25 intervals are expired */ + if (peer_mep->ccm_rx_count_miss < 13) { + /* 3.25 intervals are NOT expired without CCM reception */ + peer_mep->ccm_rx_count_miss++; + + /* Start timer again */ + ccm_rx_timer_start(peer_mep); + } else { + /* 3.25 intervals are expired without CCM reception. + * CCM defect detected + */ + peer_mep->cc_status.ccm_defect = true; + + /* Change in CCM defect status - notify */ + rcu_read_lock(); + b_port = rcu_dereference(peer_mep->mep->b_port); + if (b_port) + br_cfm_notify(RTM_NEWLINK, b_port); + rcu_read_unlock(); + } +} + +static u32 ccm_tlv_extract(struct sk_buff *skb, u32 index, + struct br_cfm_peer_mep *peer_mep) +{ + __be32 *s_tlv; + __be32 _s_tlv; + u32 h_s_tlv; + u8 *e_tlv; + u8 _e_tlv; + + e_tlv = skb_header_pointer(skb, index, sizeof(_e_tlv), &_e_tlv); + if (!e_tlv) + return 0; + + /* TLV is present - get the status TLV */ + s_tlv = skb_header_pointer(skb, + index, + sizeof(_s_tlv), &_s_tlv); + if (!s_tlv) + return 0; + + h_s_tlv = ntohl(*s_tlv); + if ((h_s_tlv >> 24) == CFM_IF_STATUS_TLV_TYPE) { + /* Interface status TLV */ + peer_mep->cc_status.tlv_seen = true; + peer_mep->cc_status.if_tlv_value = (h_s_tlv & 0xFF); + } + + if ((h_s_tlv >> 24) == CFM_PORT_STATUS_TLV_TYPE) { + /* Port status TLV */ + peer_mep->cc_status.tlv_seen = true; + peer_mep->cc_status.port_tlv_value = (h_s_tlv & 0xFF); + } + + /* The Sender ID TLV is not handled */ + /* The Organization-Specific TLV is not handled */ + + /* Return the length of this tlv. + * This is the length of the value field plus 3 bytes for size of type + * field and length field + */ + return ((h_s_tlv >> 8) & 0xFFFF) + 3; +} + +/* note: already called with rcu_read_lock */ +static int br_cfm_frame_rx(struct net_bridge_port *port, struct sk_buff *skb) +{ + u32 mdlevel, interval, size, index, max; + const struct br_cfm_common_hdr *hdr; + struct br_cfm_peer_mep *peer_mep; + const struct br_cfm_maid *maid; + struct br_cfm_common_hdr _hdr; + struct br_cfm_maid _maid; + struct br_cfm_mep *mep; + struct net_bridge *br; + __be32 *snumber; + __be32 _snumber; + __be16 *mepid; + __be16 _mepid; + + if (port->state == BR_STATE_DISABLED) + return 0; + + hdr = skb_header_pointer(skb, 0, sizeof(_hdr), &_hdr); + if (!hdr) + return 1; + + br = port->br; + mep = br_mep_find_ifindex(br, port->dev->ifindex); + if (unlikely(!mep)) + /* No MEP on this port - must be forwarded */ + return 0; + + mdlevel = hdr->mdlevel_version >> 5; + if (mdlevel > mep->config.mdlevel) + /* The level is above this MEP level - must be forwarded */ + return 0; + + if ((hdr->mdlevel_version & 0x1F) != 0) { + /* Invalid version */ + mep->status.version_unexp_seen = true; + return 1; + } + + if (mdlevel < mep->config.mdlevel) { + /* The level is below this MEP level */ + mep->status.rx_level_low_seen = true; + return 1; + } + + if (hdr->opcode == BR_CFM_OPCODE_CCM) { + /* CCM PDU received. */ + /* MA ID is after common header + sequence number + MEP ID */ + maid = skb_header_pointer(skb, + CFM_CCM_PDU_MAID_OFFSET, + sizeof(_maid), &_maid); + if (!maid) + return 1; + if (memcmp(maid->data, mep->cc_config.exp_maid.data, + sizeof(maid->data))) + /* MA ID not as expected */ + return 1; + + /* MEP ID is after common header + sequence number */ + mepid = skb_header_pointer(skb, + CFM_CCM_PDU_MEPID_OFFSET, + sizeof(_mepid), &_mepid); + if (!mepid) + return 1; + peer_mep = br_peer_mep_find(mep, (u32)ntohs(*mepid)); + if (!peer_mep) + return 1; + + /* Interval is in common header flags */ + interval = hdr->flags & 0x07; + if (mep->cc_config.exp_interval != pdu_to_interval(interval)) + /* Interval not as expected */ + return 1; + + /* A valid CCM frame is received */ + if (peer_mep->cc_status.ccm_defect) { + peer_mep->cc_status.ccm_defect = false; + + /* Change in CCM defect status - notify */ + br_cfm_notify(RTM_NEWLINK, port); + + /* Start CCM RX timer */ + ccm_rx_timer_start(peer_mep); + } + + peer_mep->cc_status.seen = true; + peer_mep->ccm_rx_count_miss = 0; + + /* RDI is in common header flags */ + peer_mep->cc_status.rdi = (hdr->flags & 0x80) ? true : false; + + /* Sequence number is after common header */ + snumber = skb_header_pointer(skb, + CFM_CCM_PDU_SEQNR_OFFSET, + sizeof(_snumber), &_snumber); + if (!snumber) + return 1; + if (ntohl(*snumber) != (mep->ccm_rx_snumber + 1)) + /* Unexpected sequence number */ + peer_mep->cc_status.seq_unexp_seen = true; + + mep->ccm_rx_snumber = ntohl(*snumber); + + /* TLV end is after common header + sequence number + MEP ID + + * MA ID + ITU reserved + */ + index = CFM_CCM_PDU_TLV_OFFSET; + max = 0; + do { /* Handle all TLVs */ + size = ccm_tlv_extract(skb, index, peer_mep); + index += size; + max += 1; + } while (size != 0 && max < 4); /* Max four TLVs possible */ + + return 1; + } + + mep->status.opcode_unexp_seen = true; + + return 1; +} + +static struct br_frame_type cfm_frame_type __read_mostly = { + .type = cpu_to_be16(ETH_P_CFM), + .frame_handler = br_cfm_frame_rx, +}; + +int br_cfm_mep_create(struct net_bridge *br, + const u32 instance, + struct br_cfm_mep_create *const create, + struct netlink_ext_ack *extack) +{ + struct net_bridge_port *p; + struct br_cfm_mep *mep; + + ASSERT_RTNL(); + + if (create->domain == BR_CFM_VLAN) { + NL_SET_ERR_MSG_MOD(extack, + "VLAN domain not supported"); + return -EINVAL; + } + if (create->domain != BR_CFM_PORT) { + NL_SET_ERR_MSG_MOD(extack, + "Invalid domain value"); + return -EINVAL; + } + if (create->direction == BR_CFM_MEP_DIRECTION_UP) { + NL_SET_ERR_MSG_MOD(extack, + "Up-MEP not supported"); + return -EINVAL; + } + if (create->direction != BR_CFM_MEP_DIRECTION_DOWN) { + NL_SET_ERR_MSG_MOD(extack, + "Invalid direction value"); + return -EINVAL; + } + p = br_mep_get_port(br, create->ifindex); + if (!p) { + NL_SET_ERR_MSG_MOD(extack, + "Port is not related to bridge"); + return -EINVAL; + } + mep = br_mep_find(br, instance); + if (mep) { + NL_SET_ERR_MSG_MOD(extack, + "MEP instance already exists"); + return -EEXIST; + } + + /* In PORT domain only one instance can be created per port */ + if (create->domain == BR_CFM_PORT) { + mep = br_mep_find_ifindex(br, create->ifindex); + if (mep) { + NL_SET_ERR_MSG_MOD(extack, + "Only one Port MEP on a port allowed"); + return -EINVAL; + } + } + + mep = kzalloc(sizeof(*mep), GFP_KERNEL); + if (!mep) + return -ENOMEM; + + mep->create = *create; + mep->instance = instance; + rcu_assign_pointer(mep->b_port, p); + + INIT_HLIST_HEAD(&mep->peer_mep_list); + INIT_DELAYED_WORK(&mep->ccm_tx_dwork, ccm_tx_work_expired); + + if (hlist_empty(&br->mep_list)) + br_add_frame(br, &cfm_frame_type); + + hlist_add_tail_rcu(&mep->head, &br->mep_list); + + return 0; +} + +static void mep_delete_implementation(struct net_bridge *br, + struct br_cfm_mep *mep) +{ + struct br_cfm_peer_mep *peer_mep; + struct hlist_node *n_store; + + ASSERT_RTNL(); + + /* Empty and free peer MEP list */ + hlist_for_each_entry_safe(peer_mep, n_store, &mep->peer_mep_list, head) { + cancel_delayed_work_sync(&peer_mep->ccm_rx_dwork); + hlist_del_rcu(&peer_mep->head); + kfree_rcu(peer_mep, rcu); + } + + cancel_delayed_work_sync(&mep->ccm_tx_dwork); + + RCU_INIT_POINTER(mep->b_port, NULL); + hlist_del_rcu(&mep->head); + kfree_rcu(mep, rcu); + + if (hlist_empty(&br->mep_list)) + br_del_frame(br, &cfm_frame_type); +} + +int br_cfm_mep_delete(struct net_bridge *br, + const u32 instance, + struct netlink_ext_ack *extack) +{ + struct br_cfm_mep *mep; + + ASSERT_RTNL(); + + mep = br_mep_find(br, instance); + if (!mep) { + NL_SET_ERR_MSG_MOD(extack, + "MEP instance does not exists"); + return -ENOENT; + } + + mep_delete_implementation(br, mep); + + return 0; +} + +int br_cfm_mep_config_set(struct net_bridge *br, + const u32 instance, + const struct br_cfm_mep_config *const config, + struct netlink_ext_ack *extack) +{ + struct br_cfm_mep *mep; + + ASSERT_RTNL(); + + mep = br_mep_find(br, instance); + if (!mep) { + NL_SET_ERR_MSG_MOD(extack, + "MEP instance does not exists"); + return -ENOENT; + } + + mep->config = *config; + + return 0; +} + +int br_cfm_cc_config_set(struct net_bridge *br, + const u32 instance, + const struct br_cfm_cc_config *const config, + struct netlink_ext_ack *extack) +{ + struct br_cfm_peer_mep *peer_mep; + struct br_cfm_mep *mep; + + ASSERT_RTNL(); + + mep = br_mep_find(br, instance); + if (!mep) { + NL_SET_ERR_MSG_MOD(extack, + "MEP instance does not exists"); + return -ENOENT; + } + + /* Check for no change in configuration */ + if (memcmp(config, &mep->cc_config, sizeof(*config)) == 0) + return 0; + + if (config->enable && !mep->cc_config.enable) + /* CC is enabled */ + hlist_for_each_entry(peer_mep, &mep->peer_mep_list, head) + cc_peer_enable(peer_mep); + + if (!config->enable && mep->cc_config.enable) + /* CC is disabled */ + hlist_for_each_entry(peer_mep, &mep->peer_mep_list, head) + cc_peer_disable(peer_mep); + + mep->cc_config = *config; + mep->ccm_rx_snumber = 0; + mep->ccm_tx_snumber = 1; + + return 0; +} + +int br_cfm_cc_peer_mep_add(struct net_bridge *br, const u32 instance, + u32 mepid, + struct netlink_ext_ack *extack) +{ + struct br_cfm_peer_mep *peer_mep; + struct br_cfm_mep *mep; + + ASSERT_RTNL(); + + mep = br_mep_find(br, instance); + if (!mep) { + NL_SET_ERR_MSG_MOD(extack, + "MEP instance does not exists"); + return -ENOENT; + } + + peer_mep = br_peer_mep_find(mep, mepid); + if (peer_mep) { + NL_SET_ERR_MSG_MOD(extack, + "Peer MEP-ID already exists"); + return -EEXIST; + } + + peer_mep = kzalloc(sizeof(*peer_mep), GFP_KERNEL); + if (!peer_mep) + return -ENOMEM; + + peer_mep->mepid = mepid; + peer_mep->mep = mep; + INIT_DELAYED_WORK(&peer_mep->ccm_rx_dwork, ccm_rx_work_expired); + + if (mep->cc_config.enable) + cc_peer_enable(peer_mep); + + hlist_add_tail_rcu(&peer_mep->head, &mep->peer_mep_list); + + return 0; +} + +int br_cfm_cc_peer_mep_remove(struct net_bridge *br, const u32 instance, + u32 mepid, + struct netlink_ext_ack *extack) +{ + struct br_cfm_peer_mep *peer_mep; + struct br_cfm_mep *mep; + + ASSERT_RTNL(); + + mep = br_mep_find(br, instance); + if (!mep) { + NL_SET_ERR_MSG_MOD(extack, + "MEP instance does not exists"); + return -ENOENT; + } + + peer_mep = br_peer_mep_find(mep, mepid); + if (!peer_mep) { + NL_SET_ERR_MSG_MOD(extack, + "Peer MEP-ID does not exists"); + return -ENOENT; + } + + cc_peer_disable(peer_mep); + + hlist_del_rcu(&peer_mep->head); + kfree_rcu(peer_mep, rcu); + + return 0; +} + +int br_cfm_cc_rdi_set(struct net_bridge *br, const u32 instance, + const bool rdi, struct netlink_ext_ack *extack) +{ + struct br_cfm_mep *mep; + + ASSERT_RTNL(); + + mep = br_mep_find(br, instance); + if (!mep) { + NL_SET_ERR_MSG_MOD(extack, + "MEP instance does not exists"); + return -ENOENT; + } + + mep->rdi = rdi; + + return 0; +} + +int br_cfm_cc_ccm_tx(struct net_bridge *br, const u32 instance, + const struct br_cfm_cc_ccm_tx_info *const tx_info, + struct netlink_ext_ack *extack) +{ + struct br_cfm_mep *mep; + + ASSERT_RTNL(); + + mep = br_mep_find(br, instance); + if (!mep) { + NL_SET_ERR_MSG_MOD(extack, + "MEP instance does not exists"); + return -ENOENT; + } + + if (memcmp(tx_info, &mep->cc_ccm_tx_info, sizeof(*tx_info)) == 0) { + /* No change in tx_info. */ + if (mep->cc_ccm_tx_info.period == 0) + /* Transmission is not enabled - just return */ + return 0; + + /* Transmission is ongoing, the end time is recalculated */ + mep->ccm_tx_end = jiffies + + usecs_to_jiffies(tx_info->period * 1000000); + return 0; + } + + if (tx_info->period == 0 && mep->cc_ccm_tx_info.period == 0) + /* Some change in info and transmission is not ongoing */ + goto save; + + if (tx_info->period != 0 && mep->cc_ccm_tx_info.period != 0) { + /* Some change in info and transmission is ongoing + * The end time is recalculated + */ + mep->ccm_tx_end = jiffies + + usecs_to_jiffies(tx_info->period * 1000000); + + goto save; + } + + if (tx_info->period == 0 && mep->cc_ccm_tx_info.period != 0) { + cancel_delayed_work_sync(&mep->ccm_tx_dwork); + goto save; + } + + /* Start delayed work to transmit CCM frames. It is done with zero delay + * to send first frame immediately + */ + mep->ccm_tx_end = jiffies + usecs_to_jiffies(tx_info->period * 1000000); + queue_delayed_work(system_wq, &mep->ccm_tx_dwork, 0); + +save: + mep->cc_ccm_tx_info = *tx_info; + + return 0; +} + +int br_cfm_mep_count(struct net_bridge *br, u32 *count) +{ + struct br_cfm_mep *mep; + + *count = 0; + + rcu_read_lock(); + hlist_for_each_entry_rcu(mep, &br->mep_list, head) + *count += 1; + rcu_read_unlock(); + + return 0; +} + +int br_cfm_peer_mep_count(struct net_bridge *br, u32 *count) +{ + struct br_cfm_peer_mep *peer_mep; + struct br_cfm_mep *mep; + + *count = 0; + + rcu_read_lock(); + hlist_for_each_entry_rcu(mep, &br->mep_list, head) + hlist_for_each_entry_rcu(peer_mep, &mep->peer_mep_list, head) + *count += 1; + rcu_read_unlock(); + + return 0; +} + +bool br_cfm_created(struct net_bridge *br) +{ + return !hlist_empty(&br->mep_list); +} + +/* Deletes the CFM instances on a specific bridge port + */ +void br_cfm_port_del(struct net_bridge *br, struct net_bridge_port *port) +{ + struct hlist_node *n_store; + struct br_cfm_mep *mep; + + ASSERT_RTNL(); + + hlist_for_each_entry_safe(mep, n_store, &br->mep_list, head) + if (mep->create.ifindex == port->dev->ifindex) + mep_delete_implementation(br, mep); +} diff --git a/net/bridge/br_cfm_netlink.c b/net/bridge/br_cfm_netlink.c new file mode 100644 index 000000000000..5c4c369f8536 --- /dev/null +++ b/net/bridge/br_cfm_netlink.c @@ -0,0 +1,726 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include <net/genetlink.h> + +#include "br_private.h" +#include "br_private_cfm.h" + +static const struct nla_policy +br_cfm_mep_create_policy[IFLA_BRIDGE_CFM_MEP_CREATE_MAX + 1] = { + [IFLA_BRIDGE_CFM_MEP_CREATE_UNSPEC] = { .type = NLA_REJECT }, + [IFLA_BRIDGE_CFM_MEP_CREATE_INSTANCE] = { .type = NLA_U32 }, + [IFLA_BRIDGE_CFM_MEP_CREATE_DOMAIN] = { .type = NLA_U32 }, + [IFLA_BRIDGE_CFM_MEP_CREATE_DIRECTION] = { .type = NLA_U32 }, + [IFLA_BRIDGE_CFM_MEP_CREATE_IFINDEX] = { .type = NLA_U32 }, +}; + +static const struct nla_policy +br_cfm_mep_delete_policy[IFLA_BRIDGE_CFM_MEP_DELETE_MAX + 1] = { + [IFLA_BRIDGE_CFM_MEP_DELETE_UNSPEC] = { .type = NLA_REJECT }, + [IFLA_BRIDGE_CFM_MEP_DELETE_INSTANCE] = { .type = NLA_U32 }, +}; + +static const struct nla_policy +br_cfm_mep_config_policy[IFLA_BRIDGE_CFM_MEP_CONFIG_MAX + 1] = { + [IFLA_BRIDGE_CFM_MEP_CONFIG_UNSPEC] = { .type = NLA_REJECT }, + [IFLA_BRIDGE_CFM_MEP_CONFIG_INSTANCE] = { .type = NLA_U32 }, + [IFLA_BRIDGE_CFM_MEP_CONFIG_UNICAST_MAC] = NLA_POLICY_ETH_ADDR, + [IFLA_BRIDGE_CFM_MEP_CONFIG_MDLEVEL] = NLA_POLICY_MAX(NLA_U32, 7), + [IFLA_BRIDGE_CFM_MEP_CONFIG_MEPID] = NLA_POLICY_MAX(NLA_U32, 0x1FFF), +}; + +static const struct nla_policy +br_cfm_cc_config_policy[IFLA_BRIDGE_CFM_CC_CONFIG_MAX + 1] = { + [IFLA_BRIDGE_CFM_CC_CONFIG_UNSPEC] = { .type = NLA_REJECT }, + [IFLA_BRIDGE_CFM_CC_CONFIG_INSTANCE] = { .type = NLA_U32 }, + [IFLA_BRIDGE_CFM_CC_CONFIG_ENABLE] = { .type = NLA_U32 }, + [IFLA_BRIDGE_CFM_CC_CONFIG_EXP_INTERVAL] = { .type = NLA_U32 }, + [IFLA_BRIDGE_CFM_CC_CONFIG_EXP_MAID] = { + .type = NLA_BINARY, .len = CFM_MAID_LENGTH }, +}; + +static const struct nla_policy +br_cfm_cc_peer_mep_policy[IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX + 1] = { + [IFLA_BRIDGE_CFM_CC_PEER_MEP_UNSPEC] = { .type = NLA_REJECT }, + [IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE] = { .type = NLA_U32 }, + [IFLA_BRIDGE_CFM_CC_PEER_MEPID] = NLA_POLICY_MAX(NLA_U32, 0x1FFF), +}; + +static const struct nla_policy +br_cfm_cc_rdi_policy[IFLA_BRIDGE_CFM_CC_RDI_MAX + 1] = { + [IFLA_BRIDGE_CFM_CC_RDI_UNSPEC] = { .type = NLA_REJECT }, + [IFLA_BRIDGE_CFM_CC_RDI_INSTANCE] = { .type = NLA_U32 }, + [IFLA_BRIDGE_CFM_CC_RDI_RDI] = { .type = NLA_U32 }, +}; + +static const struct nla_policy +br_cfm_cc_ccm_tx_policy[IFLA_BRIDGE_CFM_CC_CCM_TX_MAX + 1] = { + [IFLA_BRIDGE_CFM_CC_CCM_TX_UNSPEC] = { .type = NLA_REJECT }, + [IFLA_BRIDGE_CFM_CC_CCM_TX_INSTANCE] = { .type = NLA_U32 }, + [IFLA_BRIDGE_CFM_CC_CCM_TX_DMAC] = NLA_POLICY_ETH_ADDR, + [IFLA_BRIDGE_CFM_CC_CCM_TX_SEQ_NO_UPDATE] = { .type = NLA_U32 }, + [IFLA_BRIDGE_CFM_CC_CCM_TX_PERIOD] = { .type = NLA_U32 }, + [IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV] = { .type = NLA_U32 }, + [IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV_VALUE] = { .type = NLA_U8 }, + [IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV] = { .type = NLA_U32 }, + [IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV_VALUE] = { .type = NLA_U8 }, +}; + +static const struct nla_policy +br_cfm_policy[IFLA_BRIDGE_CFM_MAX + 1] = { + [IFLA_BRIDGE_CFM_UNSPEC] = { .type = NLA_REJECT }, + [IFLA_BRIDGE_CFM_MEP_CREATE] = + NLA_POLICY_NESTED(br_cfm_mep_create_policy), + [IFLA_BRIDGE_CFM_MEP_DELETE] = + NLA_POLICY_NESTED(br_cfm_mep_delete_policy), + [IFLA_BRIDGE_CFM_MEP_CONFIG] = + NLA_POLICY_NESTED(br_cfm_mep_config_policy), + [IFLA_BRIDGE_CFM_CC_CONFIG] = + NLA_POLICY_NESTED(br_cfm_cc_config_policy), + [IFLA_BRIDGE_CFM_CC_PEER_MEP_ADD] = + NLA_POLICY_NESTED(br_cfm_cc_peer_mep_policy), + [IFLA_BRIDGE_CFM_CC_PEER_MEP_REMOVE] = + NLA_POLICY_NESTED(br_cfm_cc_peer_mep_policy), + [IFLA_BRIDGE_CFM_CC_RDI] = + NLA_POLICY_NESTED(br_cfm_cc_rdi_policy), + [IFLA_BRIDGE_CFM_CC_CCM_TX] = + NLA_POLICY_NESTED(br_cfm_cc_ccm_tx_policy), +}; + +static int br_mep_create_parse(struct net_bridge *br, struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[IFLA_BRIDGE_CFM_MEP_CREATE_MAX + 1]; + struct br_cfm_mep_create create; + u32 instance; + int err; + + err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_MEP_CREATE_MAX, attr, + br_cfm_mep_create_policy, extack); + if (err) + return err; + + if (!tb[IFLA_BRIDGE_CFM_MEP_CREATE_INSTANCE]) { + NL_SET_ERR_MSG_MOD(extack, "Missing INSTANCE attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_MEP_CREATE_DOMAIN]) { + NL_SET_ERR_MSG_MOD(extack, "Missing DOMAIN attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_MEP_CREATE_DIRECTION]) { + NL_SET_ERR_MSG_MOD(extack, "Missing DIRECTION attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_MEP_CREATE_IFINDEX]) { + NL_SET_ERR_MSG_MOD(extack, "Missing IFINDEX attribute"); + return -EINVAL; + } + + memset(&create, 0, sizeof(create)); + + instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_CREATE_INSTANCE]); + create.domain = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_CREATE_DOMAIN]); + create.direction = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_CREATE_DIRECTION]); + create.ifindex = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_CREATE_IFINDEX]); + + return br_cfm_mep_create(br, instance, &create, extack); +} + +static int br_mep_delete_parse(struct net_bridge *br, struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[IFLA_BRIDGE_CFM_MEP_DELETE_MAX + 1]; + u32 instance; + int err; + + err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_MEP_DELETE_MAX, attr, + br_cfm_mep_delete_policy, extack); + if (err) + return err; + + if (!tb[IFLA_BRIDGE_CFM_MEP_DELETE_INSTANCE]) { + NL_SET_ERR_MSG_MOD(extack, + "Missing INSTANCE attribute"); + return -EINVAL; + } + + instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_DELETE_INSTANCE]); + + return br_cfm_mep_delete(br, instance, extack); +} + +static int br_mep_config_parse(struct net_bridge *br, struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[IFLA_BRIDGE_CFM_MEP_CONFIG_MAX + 1]; + struct br_cfm_mep_config config; + u32 instance; + int err; + + err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_MEP_CONFIG_MAX, attr, + br_cfm_mep_config_policy, extack); + if (err) + return err; + + if (!tb[IFLA_BRIDGE_CFM_MEP_CONFIG_INSTANCE]) { + NL_SET_ERR_MSG_MOD(extack, "Missing INSTANCE attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_MEP_CONFIG_UNICAST_MAC]) { + NL_SET_ERR_MSG_MOD(extack, "Missing UNICAST_MAC attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_MEP_CONFIG_MDLEVEL]) { + NL_SET_ERR_MSG_MOD(extack, "Missing MDLEVEL attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_MEP_CONFIG_MEPID]) { + NL_SET_ERR_MSG_MOD(extack, "Missing MEPID attribute"); + return -EINVAL; + } + + memset(&config, 0, sizeof(config)); + + instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_CONFIG_INSTANCE]); + nla_memcpy(&config.unicast_mac.addr, + tb[IFLA_BRIDGE_CFM_MEP_CONFIG_UNICAST_MAC], + sizeof(config.unicast_mac.addr)); + config.mdlevel = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_CONFIG_MDLEVEL]); + config.mepid = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_CONFIG_MEPID]); + + return br_cfm_mep_config_set(br, instance, &config, extack); +} + +static int br_cc_config_parse(struct net_bridge *br, struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[IFLA_BRIDGE_CFM_CC_CONFIG_MAX + 1]; + struct br_cfm_cc_config config; + u32 instance; + int err; + + err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_CC_CONFIG_MAX, attr, + br_cfm_cc_config_policy, extack); + if (err) + return err; + + if (!tb[IFLA_BRIDGE_CFM_CC_CONFIG_INSTANCE]) { + NL_SET_ERR_MSG_MOD(extack, "Missing INSTANCE attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_CC_CONFIG_ENABLE]) { + NL_SET_ERR_MSG_MOD(extack, "Missing ENABLE attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_CC_CONFIG_EXP_INTERVAL]) { + NL_SET_ERR_MSG_MOD(extack, "Missing INTERVAL attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_CC_CONFIG_EXP_MAID]) { + NL_SET_ERR_MSG_MOD(extack, "Missing MAID attribute"); + return -EINVAL; + } + + memset(&config, 0, sizeof(config)); + + instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CONFIG_INSTANCE]); + config.enable = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CONFIG_ENABLE]); + config.exp_interval = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CONFIG_EXP_INTERVAL]); + nla_memcpy(&config.exp_maid.data, tb[IFLA_BRIDGE_CFM_CC_CONFIG_EXP_MAID], + sizeof(config.exp_maid.data)); + + return br_cfm_cc_config_set(br, instance, &config, extack); +} + +static int br_cc_peer_mep_add_parse(struct net_bridge *br, struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX + 1]; + u32 instance, peer_mep_id; + int err; + + err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX, attr, + br_cfm_cc_peer_mep_policy, extack); + if (err) + return err; + + if (!tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE]) { + NL_SET_ERR_MSG_MOD(extack, "Missing INSTANCE attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_CC_PEER_MEPID]) { + NL_SET_ERR_MSG_MOD(extack, "Missing PEER_MEP_ID attribute"); + return -EINVAL; + } + + instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE]); + peer_mep_id = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_PEER_MEPID]); + + return br_cfm_cc_peer_mep_add(br, instance, peer_mep_id, extack); +} + +static int br_cc_peer_mep_remove_parse(struct net_bridge *br, struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX + 1]; + u32 instance, peer_mep_id; + int err; + + err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX, attr, + br_cfm_cc_peer_mep_policy, extack); + if (err) + return err; + + if (!tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE]) { + NL_SET_ERR_MSG_MOD(extack, "Missing INSTANCE attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_CC_PEER_MEPID]) { + NL_SET_ERR_MSG_MOD(extack, "Missing PEER_MEP_ID attribute"); + return -EINVAL; + } + + instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE]); + peer_mep_id = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_PEER_MEPID]); + + return br_cfm_cc_peer_mep_remove(br, instance, peer_mep_id, extack); +} + +static int br_cc_rdi_parse(struct net_bridge *br, struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[IFLA_BRIDGE_CFM_CC_RDI_MAX + 1]; + u32 instance, rdi; + int err; + + err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_CC_RDI_MAX, attr, + br_cfm_cc_rdi_policy, extack); + if (err) + return err; + + if (!tb[IFLA_BRIDGE_CFM_CC_RDI_INSTANCE]) { + NL_SET_ERR_MSG_MOD(extack, "Missing INSTANCE attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_CC_RDI_RDI]) { + NL_SET_ERR_MSG_MOD(extack, "Missing RDI attribute"); + return -EINVAL; + } + + instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_RDI_INSTANCE]); + rdi = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_RDI_RDI]); + + return br_cfm_cc_rdi_set(br, instance, rdi, extack); +} + +static int br_cc_ccm_tx_parse(struct net_bridge *br, struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[IFLA_BRIDGE_CFM_CC_CCM_TX_MAX + 1]; + struct br_cfm_cc_ccm_tx_info tx_info; + u32 instance; + int err; + + err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_CC_CCM_TX_MAX, attr, + br_cfm_cc_ccm_tx_policy, extack); + if (err) + return err; + + if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_INSTANCE]) { + NL_SET_ERR_MSG_MOD(extack, "Missing INSTANCE attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_DMAC]) { + NL_SET_ERR_MSG_MOD(extack, "Missing DMAC attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_SEQ_NO_UPDATE]) { + NL_SET_ERR_MSG_MOD(extack, "Missing SEQ_NO_UPDATE attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_PERIOD]) { + NL_SET_ERR_MSG_MOD(extack, "Missing PERIOD attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV]) { + NL_SET_ERR_MSG_MOD(extack, "Missing IF_TLV attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV_VALUE]) { + NL_SET_ERR_MSG_MOD(extack, "Missing IF_TLV_VALUE attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV]) { + NL_SET_ERR_MSG_MOD(extack, "Missing PORT_TLV attribute"); + return -EINVAL; + } + if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV_VALUE]) { + NL_SET_ERR_MSG_MOD(extack, "Missing PORT_TLV_VALUE attribute"); + return -EINVAL; + } + + memset(&tx_info, 0, sizeof(tx_info)); + + instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_RDI_INSTANCE]); + nla_memcpy(&tx_info.dmac.addr, + tb[IFLA_BRIDGE_CFM_CC_CCM_TX_DMAC], + sizeof(tx_info.dmac.addr)); + tx_info.seq_no_update = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CCM_TX_SEQ_NO_UPDATE]); + tx_info.period = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CCM_TX_PERIOD]); + tx_info.if_tlv = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV]); + tx_info.if_tlv_value = nla_get_u8(tb[IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV_VALUE]); + tx_info.port_tlv = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV]); + tx_info.port_tlv_value = nla_get_u8(tb[IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV_VALUE]); + + return br_cfm_cc_ccm_tx(br, instance, &tx_info, extack); +} + +int br_cfm_parse(struct net_bridge *br, struct net_bridge_port *p, + struct nlattr *attr, int cmd, struct netlink_ext_ack *extack) +{ + struct nlattr *tb[IFLA_BRIDGE_CFM_MAX + 1]; + int err; + + /* When this function is called for a port then the br pointer is + * invalid, therefor set the br to point correctly + */ + if (p) + br = p->br; + + err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_MAX, attr, + br_cfm_policy, extack); + if (err) + return err; + + if (tb[IFLA_BRIDGE_CFM_MEP_CREATE]) { + err = br_mep_create_parse(br, tb[IFLA_BRIDGE_CFM_MEP_CREATE], + extack); + if (err) + return err; + } + + if (tb[IFLA_BRIDGE_CFM_MEP_DELETE]) { + err = br_mep_delete_parse(br, tb[IFLA_BRIDGE_CFM_MEP_DELETE], + extack); + if (err) + return err; + } + + if (tb[IFLA_BRIDGE_CFM_MEP_CONFIG]) { + err = br_mep_config_parse(br, tb[IFLA_BRIDGE_CFM_MEP_CONFIG], + extack); + if (err) + return err; + } + + if (tb[IFLA_BRIDGE_CFM_CC_CONFIG]) { + err = br_cc_config_parse(br, tb[IFLA_BRIDGE_CFM_CC_CONFIG], + extack); + if (err) + return err; + } + + if (tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_ADD]) { + err = br_cc_peer_mep_add_parse(br, tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_ADD], + extack); + if (err) + return err; + } + + if (tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_REMOVE]) { + err = br_cc_peer_mep_remove_parse(br, tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_REMOVE], + extack); + if (err) + return err; + } + + if (tb[IFLA_BRIDGE_CFM_CC_RDI]) { + err = br_cc_rdi_parse(br, tb[IFLA_BRIDGE_CFM_CC_RDI], + extack); + if (err) + return err; + } + + if (tb[IFLA_BRIDGE_CFM_CC_CCM_TX]) { + err = br_cc_ccm_tx_parse(br, tb[IFLA_BRIDGE_CFM_CC_CCM_TX], + extack); + if (err) + return err; + } + + return 0; +} + +int br_cfm_config_fill_info(struct sk_buff *skb, struct net_bridge *br) +{ + struct br_cfm_peer_mep *peer_mep; + struct br_cfm_mep *mep; + struct nlattr *tb; + + hlist_for_each_entry_rcu(mep, &br->mep_list, head) { + tb = nla_nest_start(skb, IFLA_BRIDGE_CFM_MEP_CREATE_INFO); + if (!tb) + goto nla_info_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_CREATE_INSTANCE, + mep->instance)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_CREATE_DOMAIN, + mep->create.domain)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_CREATE_DIRECTION, + mep->create.direction)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_CREATE_IFINDEX, + mep->create.ifindex)) + goto nla_put_failure; + + nla_nest_end(skb, tb); + + tb = nla_nest_start(skb, IFLA_BRIDGE_CFM_MEP_CONFIG_INFO); + + if (!tb) + goto nla_info_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_CONFIG_INSTANCE, + mep->instance)) + goto nla_put_failure; + + if (nla_put(skb, IFLA_BRIDGE_CFM_MEP_CONFIG_UNICAST_MAC, + sizeof(mep->config.unicast_mac.addr), + mep->config.unicast_mac.addr)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_CONFIG_MDLEVEL, + mep->config.mdlevel)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_CONFIG_MEPID, + mep->config.mepid)) + goto nla_put_failure; + + nla_nest_end(skb, tb); + + tb = nla_nest_start(skb, IFLA_BRIDGE_CFM_CC_CONFIG_INFO); + + if (!tb) + goto nla_info_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CONFIG_INSTANCE, + mep->instance)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CONFIG_ENABLE, + mep->cc_config.enable)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CONFIG_EXP_INTERVAL, + mep->cc_config.exp_interval)) + goto nla_put_failure; + + if (nla_put(skb, IFLA_BRIDGE_CFM_CC_CONFIG_EXP_MAID, + sizeof(mep->cc_config.exp_maid.data), + mep->cc_config.exp_maid.data)) + goto nla_put_failure; + + nla_nest_end(skb, tb); + + tb = nla_nest_start(skb, IFLA_BRIDGE_CFM_CC_RDI_INFO); + + if (!tb) + goto nla_info_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_RDI_INSTANCE, + mep->instance)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_RDI_RDI, + mep->rdi)) + goto nla_put_failure; + + nla_nest_end(skb, tb); + + tb = nla_nest_start(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_INFO); + + if (!tb) + goto nla_info_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_INSTANCE, + mep->instance)) + goto nla_put_failure; + + if (nla_put(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_DMAC, + sizeof(mep->cc_ccm_tx_info.dmac), + mep->cc_ccm_tx_info.dmac.addr)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_SEQ_NO_UPDATE, + mep->cc_ccm_tx_info.seq_no_update)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_PERIOD, + mep->cc_ccm_tx_info.period)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV, + mep->cc_ccm_tx_info.if_tlv)) + goto nla_put_failure; + + if (nla_put_u8(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV_VALUE, + mep->cc_ccm_tx_info.if_tlv_value)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV, + mep->cc_ccm_tx_info.port_tlv)) + goto nla_put_failure; + + if (nla_put_u8(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV_VALUE, + mep->cc_ccm_tx_info.port_tlv_value)) + goto nla_put_failure; + + nla_nest_end(skb, tb); + + hlist_for_each_entry_rcu(peer_mep, &mep->peer_mep_list, head) { + tb = nla_nest_start(skb, + IFLA_BRIDGE_CFM_CC_PEER_MEP_INFO); + + if (!tb) + goto nla_info_failure; + + if (nla_put_u32(skb, + IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE, + mep->instance)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_PEER_MEPID, + peer_mep->mepid)) + goto nla_put_failure; + + nla_nest_end(skb, tb); + } + } + + return 0; + +nla_put_failure: + nla_nest_cancel(skb, tb); + +nla_info_failure: + return -EMSGSIZE; +} + +int br_cfm_status_fill_info(struct sk_buff *skb, + struct net_bridge *br, + bool getlink) +{ + struct br_cfm_peer_mep *peer_mep; + struct br_cfm_mep *mep; + struct nlattr *tb; + + hlist_for_each_entry_rcu(mep, &br->mep_list, head) { + tb = nla_nest_start(skb, IFLA_BRIDGE_CFM_MEP_STATUS_INFO); + if (!tb) + goto nla_info_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_STATUS_INSTANCE, + mep->instance)) + goto nla_put_failure; + + if (nla_put_u32(skb, + IFLA_BRIDGE_CFM_MEP_STATUS_OPCODE_UNEXP_SEEN, + mep->status.opcode_unexp_seen)) + goto nla_put_failure; + + if (nla_put_u32(skb, + IFLA_BRIDGE_CFM_MEP_STATUS_VERSION_UNEXP_SEEN, + mep->status.version_unexp_seen)) + goto nla_put_failure; + + if (nla_put_u32(skb, + IFLA_BRIDGE_CFM_MEP_STATUS_RX_LEVEL_LOW_SEEN, + mep->status.rx_level_low_seen)) + goto nla_put_failure; + + /* Only clear if this is a GETLINK */ + if (getlink) { + /* Clear all 'seen' indications */ + mep->status.opcode_unexp_seen = false; + mep->status.version_unexp_seen = false; + mep->status.rx_level_low_seen = false; + } + + nla_nest_end(skb, tb); + + hlist_for_each_entry_rcu(peer_mep, &mep->peer_mep_list, head) { + tb = nla_nest_start(skb, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_INFO); + if (!tb) + goto nla_info_failure; + + if (nla_put_u32(skb, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_INSTANCE, + mep->instance)) + goto nla_put_failure; + + if (nla_put_u32(skb, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_PEER_MEPID, + peer_mep->mepid)) + goto nla_put_failure; + + if (nla_put_u32(skb, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_CCM_DEFECT, + peer_mep->cc_status.ccm_defect)) + goto nla_put_failure; + + if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_PEER_STATUS_RDI, + peer_mep->cc_status.rdi)) + goto nla_put_failure; + + if (nla_put_u8(skb, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_PORT_TLV_VALUE, + peer_mep->cc_status.port_tlv_value)) + goto nla_put_failure; + + if (nla_put_u8(skb, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_IF_TLV_VALUE, + peer_mep->cc_status.if_tlv_value)) + goto nla_put_failure; + + if (nla_put_u32(skb, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEEN, + peer_mep->cc_status.seen)) + goto nla_put_failure; + + if (nla_put_u32(skb, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_TLV_SEEN, + peer_mep->cc_status.tlv_seen)) + goto nla_put_failure; + + if (nla_put_u32(skb, + IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEQ_UNEXP_SEEN, + peer_mep->cc_status.seq_unexp_seen)) + goto nla_put_failure; + + if (getlink) { /* Only clear if this is a GETLINK */ + /* Clear all 'seen' indications */ + peer_mep->cc_status.seen = false; + peer_mep->cc_status.tlv_seen = false; + peer_mep->cc_status.seq_unexp_seen = false; + } + + nla_nest_end(skb, tb); + } + } + + return 0; + +nla_put_failure: + nla_nest_cancel(skb, tb); + +nla_info_failure: + return -EMSGSIZE; +} diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 6f742fee874a..2400a66fe76e 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -93,7 +93,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) mdst = br_mdb_get(br, skb, vid); if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) && - br_multicast_querier_exists(br, eth_hdr(skb))) + br_multicast_querier_exists(br, eth_hdr(skb), mdst)) br_multicast_flood(mdst, skb, false, true); else br_flood(br, skb, BR_PKT_MULTICAST, false, true); @@ -454,9 +454,13 @@ void br_dev_setup(struct net_device *dev) spin_lock_init(&br->lock); INIT_LIST_HEAD(&br->port_list); INIT_HLIST_HEAD(&br->fdb_list); + INIT_HLIST_HEAD(&br->frame_type_list); #if IS_ENABLED(CONFIG_BRIDGE_MRP) INIT_LIST_HEAD(&br->mrp_list); #endif +#if IS_ENABLED(CONFIG_BRIDGE_CFM) + INIT_HLIST_HEAD(&br->mep_list); +#endif spin_lock_init(&br->hash_lock); br->bridge_id.prio[0] = 0x80; diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index a0e9a7937412..f7d2f472ae24 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -334,6 +334,7 @@ static void del_nbp(struct net_bridge_port *p) spin_unlock_bh(&br->lock); br_mrp_port_del(br, p); + br_cfm_port_del(br, p); br_ifinfo_notify(RTM_DELLINK, NULL, p); diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 59a318b9f646..21808985f268 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -134,7 +134,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb case BR_PKT_MULTICAST: mdst = br_mdb_get(br, skb, vid); if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) && - br_multicast_querier_exists(br, eth_hdr(skb))) { + br_multicast_querier_exists(br, eth_hdr(skb), mdst)) { if ((mdst && mdst->host_joined) || br_multicast_is_router(br)) { local_rcv = true; @@ -254,6 +254,21 @@ frame_finish: return RX_HANDLER_CONSUMED; } +/* Return 0 if the frame was not processed otherwise 1 + * note: already called with rcu_read_lock + */ +static int br_process_frame_type(struct net_bridge_port *p, + struct sk_buff *skb) +{ + struct br_frame_type *tmp; + + hlist_for_each_entry_rcu(tmp, &p->br->frame_type_list, list) + if (unlikely(tmp->type == skb->protocol)) + return tmp->frame_handler(p, skb); + + return 0; +} + /* * Return NULL if skb is handled * note: already called with rcu_read_lock @@ -343,7 +358,7 @@ static rx_handler_result_t br_handle_frame(struct sk_buff **pskb) } } - if (unlikely(br_mrp_process(p, skb))) + if (unlikely(br_process_frame_type(p, skb))) return RX_HANDLER_PASS; forward: @@ -380,3 +395,19 @@ rx_handler_func_t *br_get_rx_handler(const struct net_device *dev) return br_handle_frame; } + +void br_add_frame(struct net_bridge *br, struct br_frame_type *ft) +{ + hlist_add_head_rcu(&ft->list, &br->frame_type_list); +} + +void br_del_frame(struct net_bridge *br, struct br_frame_type *ft) +{ + struct br_frame_type *tmp; + + hlist_for_each_entry(tmp, &br->frame_type_list, list) + if (ft == tmp) { + hlist_del_rcu(&ft->list); + return; + } +} diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index e15bab19a012..8846c5bcd075 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -87,6 +87,8 @@ static void __mdb_entry_to_br_ip(struct br_mdb_entry *entry, struct br_ip *ip, ip->src.ip6 = nla_get_in6_addr(mdb_attrs[MDBE_ATTR_SOURCE]); break; #endif + default: + ether_addr_copy(ip->dst.mac_addr, entry->addr.u.mac_addr); } } @@ -174,9 +176,11 @@ static int __mdb_fill_info(struct sk_buff *skb, if (mp->addr.proto == htons(ETH_P_IP)) e.addr.u.ip4 = mp->addr.dst.ip4; #if IS_ENABLED(CONFIG_IPV6) - if (mp->addr.proto == htons(ETH_P_IPV6)) + else if (mp->addr.proto == htons(ETH_P_IPV6)) e.addr.u.ip6 = mp->addr.dst.ip6; #endif + else + ether_addr_copy(e.addr.u.mac_addr, mp->addr.dst.mac_addr); e.addr.proto = mp->addr.proto; nest_ent = nla_nest_start_noflag(skb, MDBA_MDB_ENTRY_INFO); @@ -210,6 +214,8 @@ static int __mdb_fill_info(struct sk_buff *skb, } break; #endif + default: + ether_addr_copy(e.addr.u.mac_addr, mp->addr.dst.mac_addr); } if (p) { if (nla_put_u8(skb, MDBA_MDB_EATTR_RTPROT, p->rt_protocol)) @@ -562,9 +568,12 @@ void br_mdb_notify(struct net_device *dev, if (mp->addr.proto == htons(ETH_P_IP)) ip_eth_mc_map(mp->addr.dst.ip4, mdb.addr); #if IS_ENABLED(CONFIG_IPV6) - else + else if (mp->addr.proto == htons(ETH_P_IPV6)) ipv6_eth_mc_map(&mp->addr.dst.ip6, mdb.addr); #endif + else + ether_addr_copy(mdb.addr, mp->addr.dst.mac_addr); + mdb.obj.orig_dev = pg->key.port->dev; switch (type) { case RTM_NEWMDB: @@ -693,6 +702,12 @@ static bool is_valid_mdb_entry(struct br_mdb_entry *entry, return false; } #endif + } else if (entry->addr.proto == 0) { + /* L2 mdb */ + if (!is_multicast_ether_addr(entry->addr.u.mac_addr)) { + NL_SET_ERR_MSG_MOD(extack, "L2 entry group is not multicast"); + return false; + } } else { NL_SET_ERR_MSG_MOD(extack, "Unknown entry protocol"); return false; @@ -831,6 +846,7 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, struct net_bridge_port_group __rcu **pp; struct br_ip group, star_group; unsigned long now = jiffies; + unsigned char flags = 0; u8 filter_mode; int err; @@ -849,6 +865,11 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, } } + if (br_group_is_l2(&group) && entry->state != MDB_PERMANENT) { + NL_SET_ERR_MSG_MOD(extack, "Only permanent L2 entries allowed"); + return -EINVAL; + } + mp = br_mdb_ip_get(br, &group); if (!mp) { mp = br_multicast_new_group(br, &group); @@ -884,7 +905,10 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, filter_mode = br_multicast_is_star_g(&group) ? MCAST_EXCLUDE : MCAST_INCLUDE; - p = br_multicast_new_port_group(port, &group, *pp, entry->state, NULL, + if (entry->state == MDB_PERMANENT) + flags |= MDB_PG_FLAGS_PERMANENT; + + p = br_multicast_new_port_group(port, &group, *pp, flags, NULL, filter_mode, RTPROT_STATIC); if (unlikely(!p)) { NL_SET_ERR_MSG_MOD(extack, "Couldn't allocate new port group"); diff --git a/net/bridge/br_mrp.c b/net/bridge/br_mrp.c index b36689e6e7cb..f94d72bb7c32 100644 --- a/net/bridge/br_mrp.c +++ b/net/bridge/br_mrp.c @@ -6,6 +6,13 @@ static const u8 mrp_test_dmac[ETH_ALEN] = { 0x1, 0x15, 0x4e, 0x0, 0x0, 0x1 }; static const u8 mrp_in_test_dmac[ETH_ALEN] = { 0x1, 0x15, 0x4e, 0x0, 0x0, 0x3 }; +static int br_mrp_process(struct net_bridge_port *p, struct sk_buff *skb); + +static struct br_frame_type mrp_frame_type __read_mostly = { + .type = cpu_to_be16(ETH_P_MRP), + .frame_handler = br_mrp_process, +}; + static bool br_mrp_is_ring_port(struct net_bridge_port *p_port, struct net_bridge_port *s_port, struct net_bridge_port *port) @@ -445,6 +452,9 @@ static void br_mrp_del_impl(struct net_bridge *br, struct br_mrp *mrp) list_del_rcu(&mrp->list); kfree_rcu(mrp, rcu); + + if (list_empty(&br->mrp_list)) + br_del_frame(br, &mrp_frame_type); } /* Adds a new MRP instance. @@ -493,6 +503,9 @@ int br_mrp_add(struct net_bridge *br, struct br_mrp_instance *instance) spin_unlock_bh(&br->lock); rcu_assign_pointer(mrp->s_port, p); + if (list_empty(&br->mrp_list)) + br_add_frame(br, &mrp_frame_type); + INIT_DELAYED_WORK(&mrp->test_work, br_mrp_test_work_expired); INIT_DELAYED_WORK(&mrp->in_test_work, br_mrp_in_test_work_expired); list_add_tail_rcu(&mrp->list, &br->mrp_list); @@ -1172,15 +1185,13 @@ no_forward: * normal forwarding. * note: already called with rcu_read_lock */ -int br_mrp_process(struct net_bridge_port *p, struct sk_buff *skb) +static int br_mrp_process(struct net_bridge_port *p, struct sk_buff *skb) { /* If there is no MRP instance do normal forwarding */ if (likely(!(p->flags & BR_MRP_AWARE))) goto out; - if (unlikely(skb->protocol == htons(ETH_P_MRP))) - return br_mrp_rcv(p, skb, p->dev); - + return br_mrp_rcv(p, skb, p->dev); out: return 0; } diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index eae898c3cff7..484820c223a3 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -179,7 +179,8 @@ struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br, break; #endif default: - return NULL; + ip.proto = 0; + ether_addr_copy(ip.dst.mac_addr, eth_hdr(skb)->h_dest); } return br_mdb_ip_get_rcu(br, &ip); @@ -1203,6 +1204,10 @@ void br_multicast_host_join(struct net_bridge_mdb_entry *mp, bool notify) if (notify) br_mdb_notify(mp->br->dev, mp, NULL, RTM_NEWMDB); } + + if (br_group_is_l2(&mp->addr)) + return; + mod_timer(&mp->timer, jiffies + mp->br->multicast_membership_interval); } @@ -1254,8 +1259,8 @@ __br_multicast_add_group(struct net_bridge *br, break; } - p = br_multicast_new_port_group(port, group, *pp, 0, src, filter_mode, - RTPROT_KERNEL); + p = br_multicast_new_port_group(port, group, *pp, 0, src, + filter_mode, RTPROT_KERNEL); if (unlikely(!p)) { p = ERR_PTR(-ENOMEM); goto out; @@ -3690,7 +3695,7 @@ bool br_multicast_has_querier_anywhere(struct net_device *dev, int proto) memset(ð, 0, sizeof(eth)); eth.h_proto = htons(proto); - ret = br_multicast_querier_exists(br, ð); + ret = br_multicast_querier_exists(br, ð, NULL); unlock: rcu_read_unlock(); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 92d64abffa87..6952d4852942 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -16,6 +16,7 @@ #include "br_private.h" #include "br_private_stp.h" +#include "br_private_cfm.h" #include "br_private_tunnel.h" static int __get_num_vlan_infos(struct net_bridge_vlan_group *vg, @@ -93,9 +94,11 @@ static size_t br_get_link_af_size_filtered(const struct net_device *dev, { struct net_bridge_vlan_group *vg = NULL; struct net_bridge_port *p = NULL; - struct net_bridge *br; - int num_vlan_infos; + struct net_bridge *br = NULL; + u32 num_cfm_peer_mep_infos; + u32 num_cfm_mep_infos; size_t vinfo_sz = 0; + int num_vlan_infos; rcu_read_lock(); if (netif_is_bridge_port(dev)) { @@ -114,6 +117,49 @@ static size_t br_get_link_af_size_filtered(const struct net_device *dev, /* Each VLAN is returned in bridge_vlan_info along with flags */ vinfo_sz += num_vlan_infos * nla_total_size(sizeof(struct bridge_vlan_info)); + if (!(filter_mask & RTEXT_FILTER_CFM_STATUS)) + return vinfo_sz; + + if (!br) + return vinfo_sz; + + /* CFM status info must be added */ + br_cfm_mep_count(br, &num_cfm_mep_infos); + br_cfm_peer_mep_count(br, &num_cfm_peer_mep_infos); + + vinfo_sz += nla_total_size(0); /* IFLA_BRIDGE_CFM */ + /* For each status struct the MEP instance (u32) is added */ + /* MEP instance (u32) + br_cfm_mep_status */ + vinfo_sz += num_cfm_mep_infos * + /*IFLA_BRIDGE_CFM_MEP_STATUS_INSTANCE */ + (nla_total_size(sizeof(u32)) + /* IFLA_BRIDGE_CFM_MEP_STATUS_OPCODE_UNEXP_SEEN */ + + nla_total_size(sizeof(u32)) + /* IFLA_BRIDGE_CFM_MEP_STATUS_VERSION_UNEXP_SEEN */ + + nla_total_size(sizeof(u32)) + /* IFLA_BRIDGE_CFM_MEP_STATUS_RX_LEVEL_LOW_SEEN */ + + nla_total_size(sizeof(u32))); + /* MEP instance (u32) + br_cfm_cc_peer_status */ + vinfo_sz += num_cfm_peer_mep_infos * + /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_INSTANCE */ + (nla_total_size(sizeof(u32)) + /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_PEER_MEPID */ + + nla_total_size(sizeof(u32)) + /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_CCM_DEFECT */ + + nla_total_size(sizeof(u32)) + /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_RDI */ + + nla_total_size(sizeof(u32)) + /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_PORT_TLV_VALUE */ + + nla_total_size(sizeof(u8)) + /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_IF_TLV_VALUE */ + + nla_total_size(sizeof(u8)) + /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEEN */ + + nla_total_size(sizeof(u32)) + /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_TLV_SEEN */ + + nla_total_size(sizeof(u32)) + /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEQ_UNEXP_SEEN */ + + nla_total_size(sizeof(u32))); + return vinfo_sz; } @@ -377,7 +423,8 @@ nla_put_failure: static int br_fill_ifinfo(struct sk_buff *skb, const struct net_bridge_port *port, u32 pid, u32 seq, int event, unsigned int flags, - u32 filter_mask, const struct net_device *dev) + u32 filter_mask, const struct net_device *dev, + bool getlink) { u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN; struct nlattr *af = NULL; @@ -426,7 +473,9 @@ static int br_fill_ifinfo(struct sk_buff *skb, if (filter_mask & (RTEXT_FILTER_BRVLAN | RTEXT_FILTER_BRVLAN_COMPRESSED | - RTEXT_FILTER_MRP)) { + RTEXT_FILTER_MRP | + RTEXT_FILTER_CFM_CONFIG | + RTEXT_FILTER_CFM_STATUS)) { af = nla_nest_start_noflag(skb, IFLA_AF_SPEC); if (!af) goto nla_put_failure; @@ -475,6 +524,36 @@ static int br_fill_ifinfo(struct sk_buff *skb, goto nla_put_failure; } + if (filter_mask & (RTEXT_FILTER_CFM_CONFIG | RTEXT_FILTER_CFM_STATUS)) { + struct nlattr *cfm_nest = NULL; + int err; + + if (!br_cfm_created(br) || port) + goto done; + + cfm_nest = nla_nest_start(skb, IFLA_BRIDGE_CFM); + if (!cfm_nest) + goto nla_put_failure; + + if (filter_mask & RTEXT_FILTER_CFM_CONFIG) { + rcu_read_lock(); + err = br_cfm_config_fill_info(skb, br); + rcu_read_unlock(); + if (err) + goto nla_put_failure; + } + + if (filter_mask & RTEXT_FILTER_CFM_STATUS) { + rcu_read_lock(); + err = br_cfm_status_fill_info(skb, br, getlink); + rcu_read_unlock(); + if (err) + goto nla_put_failure; + } + + nla_nest_end(skb, cfm_nest); + } + done: if (af) nla_nest_end(skb, af); @@ -486,11 +565,9 @@ nla_put_failure: return -EMSGSIZE; } -/* Notify listeners of a change in bridge or port information */ -void br_ifinfo_notify(int event, const struct net_bridge *br, - const struct net_bridge_port *port) +void br_info_notify(int event, const struct net_bridge *br, + const struct net_bridge_port *port, u32 filter) { - u32 filter = RTEXT_FILTER_BRVLAN_COMPRESSED; struct net_device *dev; struct sk_buff *skb; int err = -ENOBUFS; @@ -515,7 +592,7 @@ void br_ifinfo_notify(int event, const struct net_bridge *br, if (skb == NULL) goto errout; - err = br_fill_ifinfo(skb, port, 0, 0, event, 0, filter, dev); + err = br_fill_ifinfo(skb, port, 0, 0, event, 0, filter, dev, false); if (err < 0) { /* -EMSGSIZE implies BUG in br_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); @@ -528,6 +605,15 @@ errout: rtnl_set_sk_err(net, RTNLGRP_LINK, err); } +/* Notify listeners of a change in bridge or port information */ +void br_ifinfo_notify(int event, const struct net_bridge *br, + const struct net_bridge_port *port) +{ + u32 filter = RTEXT_FILTER_BRVLAN_COMPRESSED; + + return br_info_notify(event, br, port, filter); +} + /* * Dump information about all ports, in response to GETLINK */ @@ -538,11 +624,13 @@ int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, if (!port && !(filter_mask & RTEXT_FILTER_BRVLAN) && !(filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED) && - !(filter_mask & RTEXT_FILTER_MRP)) + !(filter_mask & RTEXT_FILTER_MRP) && + !(filter_mask & RTEXT_FILTER_CFM_CONFIG) && + !(filter_mask & RTEXT_FILTER_CFM_STATUS)) return 0; return br_fill_ifinfo(skb, port, pid, seq, RTM_NEWLINK, nlflags, - filter_mask, dev); + filter_mask, dev, true); } static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p, @@ -700,6 +788,11 @@ static int br_afspec(struct net_bridge *br, if (err) return err; break; + case IFLA_BRIDGE_CFM: + err = br_cfm_parse(br, p, attr, cmd, extack); + if (err) + return err; + break; } } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 345118e35c42..891f3b05ffa4 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -383,7 +383,7 @@ enum net_bridge_opts { struct net_bridge { spinlock_t lock; spinlock_t hash_lock; - struct list_head port_list; + struct hlist_head frame_type_list; struct net_device *dev; struct pcpu_sw_netstats __percpu *stats; unsigned long options; @@ -395,6 +395,7 @@ struct net_bridge { #endif struct rhashtable fdb_hash_tbl; + struct list_head port_list; #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) union { struct rtable fake_rtable; @@ -483,6 +484,9 @@ struct net_bridge { #if IS_ENABLED(CONFIG_BRIDGE_MRP) struct list_head mrp_list; #endif +#if IS_ENABLED(CONFIG_BRIDGE_CFM) + struct hlist_head mep_list; +#endif }; struct br_input_skb_cb { @@ -755,6 +759,16 @@ int nbp_backup_change(struct net_bridge_port *p, struct net_device *backup_dev); int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb); rx_handler_func_t *br_get_rx_handler(const struct net_device *dev); +struct br_frame_type { + __be16 type; + int (*frame_handler)(struct net_bridge_port *port, + struct sk_buff *skb); + struct hlist_node list; +}; + +void br_add_frame(struct net_bridge *br, struct br_frame_type *ft); +void br_del_frame(struct net_bridge *br, struct br_frame_type *ft); + static inline bool br_rx_handler_check_rcu(const struct net_device *dev) { return rcu_dereference(dev->rx_handler) == br_get_rx_handler(dev); @@ -840,6 +854,11 @@ void br_multicast_star_g_handle_mode(struct net_bridge_port_group *pg, void br_multicast_sg_add_exclude_ports(struct net_bridge_mdb_entry *star_mp, struct net_bridge_port_group *sg); +static inline bool br_group_is_l2(const struct br_ip *group) +{ + return group->proto == 0; +} + #define mlock_dereference(X, br) \ rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock)) @@ -871,7 +890,8 @@ __br_multicast_querier_exists(struct net_bridge *br, } static inline bool br_multicast_querier_exists(struct net_bridge *br, - struct ethhdr *eth) + struct ethhdr *eth, + const struct net_bridge_mdb_entry *mdb) { switch (eth->h_proto) { case (htons(ETH_P_IP)): @@ -883,7 +903,7 @@ static inline bool br_multicast_querier_exists(struct net_bridge *br, &br->ip6_other_query, true); #endif default: - return false; + return !!mdb && br_group_is_l2(&mdb->addr); } } @@ -993,7 +1013,8 @@ static inline bool br_multicast_is_router(struct net_bridge *br) } static inline bool br_multicast_querier_exists(struct net_bridge *br, - struct ethhdr *eth) + struct ethhdr *eth, + const struct net_bridge_mdb_entry *mdb) { return false; } @@ -1417,7 +1438,6 @@ extern int (*br_fdb_test_addr_hook)(struct net_device *dev, unsigned char *addr) #if IS_ENABLED(CONFIG_BRIDGE_MRP) int br_mrp_parse(struct net_bridge *br, struct net_bridge_port *p, struct nlattr *attr, int cmd, struct netlink_ext_ack *extack); -int br_mrp_process(struct net_bridge_port *p, struct sk_buff *skb); bool br_mrp_enabled(struct net_bridge *br); void br_mrp_port_del(struct net_bridge *br, struct net_bridge_port *p); int br_mrp_fill_info(struct sk_buff *skb, struct net_bridge *br); @@ -1429,11 +1449,6 @@ static inline int br_mrp_parse(struct net_bridge *br, struct net_bridge_port *p, return -EOPNOTSUPP; } -static inline int br_mrp_process(struct net_bridge_port *p, struct sk_buff *skb) -{ - return 0; -} - static inline bool br_mrp_enabled(struct net_bridge *br) { return false; @@ -1451,12 +1466,67 @@ static inline int br_mrp_fill_info(struct sk_buff *skb, struct net_bridge *br) #endif +/* br_cfm.c */ +#if IS_ENABLED(CONFIG_BRIDGE_CFM) +int br_cfm_parse(struct net_bridge *br, struct net_bridge_port *p, + struct nlattr *attr, int cmd, struct netlink_ext_ack *extack); +bool br_cfm_created(struct net_bridge *br); +void br_cfm_port_del(struct net_bridge *br, struct net_bridge_port *p); +int br_cfm_config_fill_info(struct sk_buff *skb, struct net_bridge *br); +int br_cfm_status_fill_info(struct sk_buff *skb, + struct net_bridge *br, + bool getlink); +int br_cfm_mep_count(struct net_bridge *br, u32 *count); +int br_cfm_peer_mep_count(struct net_bridge *br, u32 *count); +#else +static inline int br_cfm_parse(struct net_bridge *br, struct net_bridge_port *p, + struct nlattr *attr, int cmd, + struct netlink_ext_ack *extack) +{ + return -EOPNOTSUPP; +} + +static inline bool br_cfm_created(struct net_bridge *br) +{ + return false; +} + +static inline void br_cfm_port_del(struct net_bridge *br, + struct net_bridge_port *p) +{ +} + +static inline int br_cfm_config_fill_info(struct sk_buff *skb, struct net_bridge *br) +{ + return -EOPNOTSUPP; +} + +static inline int br_cfm_status_fill_info(struct sk_buff *skb, + struct net_bridge *br, + bool getlink) +{ + return -EOPNOTSUPP; +} + +static inline int br_cfm_mep_count(struct net_bridge *br, u32 *count) +{ + return -EOPNOTSUPP; +} + +static inline int br_cfm_peer_mep_count(struct net_bridge *br, u32 *count) +{ + return -EOPNOTSUPP; +} +#endif + /* br_netlink.c */ extern struct rtnl_link_ops br_link_ops; int br_netlink_init(void); void br_netlink_fini(void); void br_ifinfo_notify(int event, const struct net_bridge *br, const struct net_bridge_port *port); +void br_info_notify(int event, const struct net_bridge *br, + const struct net_bridge_port *port, u32 filter); int br_setlink(struct net_device *dev, struct nlmsghdr *nlmsg, u16 flags, struct netlink_ext_ack *extack); int br_dellink(struct net_device *dev, struct nlmsghdr *nlmsg, u16 flags); diff --git a/net/bridge/br_private_cfm.h b/net/bridge/br_private_cfm.h new file mode 100644 index 000000000000..a43a5e7fa2c3 --- /dev/null +++ b/net/bridge/br_private_cfm.h @@ -0,0 +1,147 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef _BR_PRIVATE_CFM_H_ +#define _BR_PRIVATE_CFM_H_ + +#include "br_private.h" +#include <uapi/linux/cfm_bridge.h> + +struct br_cfm_mep_create { + enum br_cfm_domain domain; /* Domain for this MEP */ + enum br_cfm_mep_direction direction; /* Up or Down MEP direction */ + u32 ifindex; /* Residence port */ +}; + +int br_cfm_mep_create(struct net_bridge *br, + const u32 instance, + struct br_cfm_mep_create *const create, + struct netlink_ext_ack *extack); + +int br_cfm_mep_delete(struct net_bridge *br, + const u32 instance, + struct netlink_ext_ack *extack); + +struct br_cfm_mep_config { + u32 mdlevel; + u32 mepid; /* MEPID for this MEP */ + struct mac_addr unicast_mac; /* The MEP unicast MAC */ +}; + +int br_cfm_mep_config_set(struct net_bridge *br, + const u32 instance, + const struct br_cfm_mep_config *const config, + struct netlink_ext_ack *extack); + +struct br_cfm_maid { + u8 data[CFM_MAID_LENGTH]; +}; + +struct br_cfm_cc_config { + /* Expected received CCM PDU MAID. */ + struct br_cfm_maid exp_maid; + + /* Expected received CCM PDU interval. */ + /* Transmitting CCM PDU interval when CCM tx is enabled. */ + enum br_cfm_ccm_interval exp_interval; + + bool enable; /* Enable/disable CCM PDU handling */ +}; + +int br_cfm_cc_config_set(struct net_bridge *br, + const u32 instance, + const struct br_cfm_cc_config *const config, + struct netlink_ext_ack *extack); + +int br_cfm_cc_peer_mep_add(struct net_bridge *br, const u32 instance, + u32 peer_mep_id, + struct netlink_ext_ack *extack); +int br_cfm_cc_peer_mep_remove(struct net_bridge *br, const u32 instance, + u32 peer_mep_id, + struct netlink_ext_ack *extack); + +/* Transmitted CCM Remote Defect Indication status set. + * This RDI is inserted in transmitted CCM PDUs if CCM transmission is enabled. + * See br_cfm_cc_ccm_tx() with interval != BR_CFM_CCM_INTERVAL_NONE + */ +int br_cfm_cc_rdi_set(struct net_bridge *br, const u32 instance, + const bool rdi, struct netlink_ext_ack *extack); + +/* OAM PDU Tx information */ +struct br_cfm_cc_ccm_tx_info { + struct mac_addr dmac; + /* The CCM will be transmitted for this period in seconds. + * Call br_cfm_cc_ccm_tx before timeout to keep transmission alive. + * When period is zero any ongoing transmission will be stopped. + */ + u32 period; + + bool seq_no_update; /* Update Tx CCM sequence number */ + bool if_tlv; /* Insert Interface Status TLV */ + u8 if_tlv_value; /* Interface Status TLV value */ + bool port_tlv; /* Insert Port Status TLV */ + u8 port_tlv_value; /* Port Status TLV value */ + /* Sender ID TLV ?? + * Organization-Specific TLV ?? + */ +}; + +int br_cfm_cc_ccm_tx(struct net_bridge *br, const u32 instance, + const struct br_cfm_cc_ccm_tx_info *const tx_info, + struct netlink_ext_ack *extack); + +struct br_cfm_mep_status { + /* Indications that an OAM PDU has been seen. */ + bool opcode_unexp_seen; /* RX of OAM PDU with unexpected opcode */ + bool version_unexp_seen; /* RX of OAM PDU with unexpected version */ + bool rx_level_low_seen; /* Rx of OAM PDU with level low */ +}; + +struct br_cfm_cc_peer_status { + /* This CCM related status is based on the latest received CCM PDU. */ + u8 port_tlv_value; /* Port Status TLV value */ + u8 if_tlv_value; /* Interface Status TLV value */ + + /* CCM has not been received for 3.25 intervals */ + u8 ccm_defect:1; + + /* (RDI == 1) for last received CCM PDU */ + u8 rdi:1; + + /* Indications that a CCM PDU has been seen. */ + u8 seen:1; /* CCM PDU received */ + u8 tlv_seen:1; /* CCM PDU with TLV received */ + /* CCM PDU with unexpected sequence number received */ + u8 seq_unexp_seen:1; +}; + +struct br_cfm_mep { + /* list header of MEP instances */ + struct hlist_node head; + u32 instance; + struct br_cfm_mep_create create; + struct br_cfm_mep_config config; + struct br_cfm_cc_config cc_config; + struct br_cfm_cc_ccm_tx_info cc_ccm_tx_info; + /* List of multiple peer MEPs */ + struct hlist_head peer_mep_list; + struct net_bridge_port __rcu *b_port; + unsigned long ccm_tx_end; + struct delayed_work ccm_tx_dwork; + u32 ccm_tx_snumber; + u32 ccm_rx_snumber; + struct br_cfm_mep_status status; + bool rdi; + struct rcu_head rcu; +}; + +struct br_cfm_peer_mep { + struct hlist_node head; + struct br_cfm_mep *mep; + struct delayed_work ccm_rx_dwork; + u32 mepid; + struct br_cfm_cc_peer_status cc_status; + u32 ccm_rx_count_miss; + struct rcu_head rcu; +}; + +#endif /* _BR_PRIVATE_CFM_H_ */ diff --git a/net/bridge/netfilter/Kconfig b/net/bridge/netfilter/Kconfig index 5040fe43f4b4..e4d287afc2c9 100644 --- a/net/bridge/netfilter/Kconfig +++ b/net/bridge/netfilter/Kconfig @@ -17,7 +17,7 @@ config NFT_BRIDGE_META config NFT_BRIDGE_REJECT tristate "Netfilter nf_tables bridge reject support" - depends on NFT_REJECT && NFT_REJECT_IPV4 && NFT_REJECT_IPV6 + depends on NFT_REJECT help Add support to reject packets. diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c index deae2c9a0f69..eba0efe64d05 100644 --- a/net/bridge/netfilter/nft_reject_bridge.c +++ b/net/bridge/netfilter/nft_reject_bridge.c @@ -39,30 +39,6 @@ static void nft_reject_br_push_etherhdr(struct sk_buff *oldskb, } } -static int nft_bridge_iphdr_validate(struct sk_buff *skb) -{ - struct iphdr *iph; - u32 len; - - if (!pskb_may_pull(skb, sizeof(struct iphdr))) - return 0; - - iph = ip_hdr(skb); - if (iph->ihl < 5 || iph->version != 4) - return 0; - - len = ntohs(iph->tot_len); - if (skb->len < len) - return 0; - else if (len < (iph->ihl*4)) - return 0; - - if (!pskb_may_pull(skb, iph->ihl*4)) - return 0; - - return 1; -} - /* We cannot use oldskb->dev, it can be either bridge device (NF_BRIDGE INPUT) * or the bridge port (NF_BRIDGE PREROUTING). */ @@ -72,29 +48,11 @@ static void nft_reject_br_send_v4_tcp_reset(struct net *net, int hook) { struct sk_buff *nskb; - struct iphdr *niph; - const struct tcphdr *oth; - struct tcphdr _oth; - if (!nft_bridge_iphdr_validate(oldskb)) - return; - - oth = nf_reject_ip_tcphdr_get(oldskb, &_oth, hook); - if (!oth) - return; - - nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) + - LL_MAX_HEADER, GFP_ATOMIC); + nskb = nf_reject_skb_v4_tcp_reset(net, oldskb, dev, hook); if (!nskb) return; - skb_reserve(nskb, LL_MAX_HEADER); - niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_TCP, - net->ipv4.sysctl_ip_default_ttl); - nf_reject_ip_tcphdr_put(nskb, oldskb, oth); - niph->tot_len = htons(nskb->len); - ip_send_check(niph); - nft_reject_br_push_etherhdr(oldskb, nskb); br_forward(br_port_get_rcu(dev), nskb, false, true); @@ -106,139 +64,32 @@ static void nft_reject_br_send_v4_unreach(struct net *net, int hook, u8 code) { struct sk_buff *nskb; - struct iphdr *niph; - struct icmphdr *icmph; - unsigned int len; - __wsum csum; - u8 proto; - - if (!nft_bridge_iphdr_validate(oldskb)) - return; - - /* IP header checks: fragment. */ - if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET)) - return; - - /* RFC says return as much as we can without exceeding 576 bytes. */ - len = min_t(unsigned int, 536, oldskb->len); - - if (!pskb_may_pull(oldskb, len)) - return; - - if (pskb_trim_rcsum(oldskb, ntohs(ip_hdr(oldskb)->tot_len))) - return; - - proto = ip_hdr(oldskb)->protocol; - - if (!skb_csum_unnecessary(oldskb) && - nf_reject_verify_csum(proto) && - nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), proto)) - return; - nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct icmphdr) + - LL_MAX_HEADER + len, GFP_ATOMIC); + nskb = nf_reject_skb_v4_unreach(net, oldskb, dev, hook, code); if (!nskb) return; - skb_reserve(nskb, LL_MAX_HEADER); - niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_ICMP, - net->ipv4.sysctl_ip_default_ttl); - - skb_reset_transport_header(nskb); - icmph = skb_put_zero(nskb, sizeof(struct icmphdr)); - icmph->type = ICMP_DEST_UNREACH; - icmph->code = code; - - skb_put_data(nskb, skb_network_header(oldskb), len); - - csum = csum_partial((void *)icmph, len + sizeof(struct icmphdr), 0); - icmph->checksum = csum_fold(csum); - - niph->tot_len = htons(nskb->len); - ip_send_check(niph); - nft_reject_br_push_etherhdr(oldskb, nskb); br_forward(br_port_get_rcu(dev), nskb, false, true); } -static int nft_bridge_ip6hdr_validate(struct sk_buff *skb) -{ - struct ipv6hdr *hdr; - u32 pkt_len; - - if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) - return 0; - - hdr = ipv6_hdr(skb); - if (hdr->version != 6) - return 0; - - pkt_len = ntohs(hdr->payload_len); - if (pkt_len + sizeof(struct ipv6hdr) > skb->len) - return 0; - - return 1; -} - static void nft_reject_br_send_v6_tcp_reset(struct net *net, struct sk_buff *oldskb, const struct net_device *dev, int hook) { struct sk_buff *nskb; - const struct tcphdr *oth; - struct tcphdr _oth; - unsigned int otcplen; - struct ipv6hdr *nip6h; - if (!nft_bridge_ip6hdr_validate(oldskb)) - return; - - oth = nf_reject_ip6_tcphdr_get(oldskb, &_oth, &otcplen, hook); - if (!oth) - return; - - nskb = alloc_skb(sizeof(struct ipv6hdr) + sizeof(struct tcphdr) + - LL_MAX_HEADER, GFP_ATOMIC); + nskb = nf_reject_skb_v6_tcp_reset(net, oldskb, dev, hook); if (!nskb) return; - skb_reserve(nskb, LL_MAX_HEADER); - nip6h = nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_TCP, - net->ipv6.devconf_all->hop_limit); - nf_reject_ip6_tcphdr_put(nskb, oldskb, oth, otcplen); - nip6h->payload_len = htons(nskb->len - sizeof(struct ipv6hdr)); - nft_reject_br_push_etherhdr(oldskb, nskb); br_forward(br_port_get_rcu(dev), nskb, false, true); } -static bool reject6_br_csum_ok(struct sk_buff *skb, int hook) -{ - const struct ipv6hdr *ip6h = ipv6_hdr(skb); - int thoff; - __be16 fo; - u8 proto = ip6h->nexthdr; - - if (skb_csum_unnecessary(skb)) - return true; - - if (ip6h->payload_len && - pskb_trim_rcsum(skb, ntohs(ip6h->payload_len) + sizeof(*ip6h))) - return false; - - ip6h = ipv6_hdr(skb); - thoff = ipv6_skip_exthdr(skb, ((u8*)(ip6h+1) - skb->data), &proto, &fo); - if (thoff < 0 || thoff >= skb->len || (fo & htons(~0x7)) != 0) - return false; - - if (!nf_reject_verify_csum(proto)) - return true; - - return nf_ip6_checksum(skb, hook, thoff, proto) == 0; -} static void nft_reject_br_send_v6_unreach(struct net *net, struct sk_buff *oldskb, @@ -246,49 +97,11 @@ static void nft_reject_br_send_v6_unreach(struct net *net, int hook, u8 code) { struct sk_buff *nskb; - struct ipv6hdr *nip6h; - struct icmp6hdr *icmp6h; - unsigned int len; - - if (!nft_bridge_ip6hdr_validate(oldskb)) - return; - /* Include "As much of invoking packet as possible without the ICMPv6 - * packet exceeding the minimum IPv6 MTU" in the ICMP payload. - */ - len = min_t(unsigned int, 1220, oldskb->len); - - if (!pskb_may_pull(oldskb, len)) - return; - - if (!reject6_br_csum_ok(oldskb, hook)) - return; - - nskb = alloc_skb(sizeof(struct ipv6hdr) + sizeof(struct icmp6hdr) + - LL_MAX_HEADER + len, GFP_ATOMIC); + nskb = nf_reject_skb_v6_unreach(net, oldskb, dev, hook, code); if (!nskb) return; - skb_reserve(nskb, LL_MAX_HEADER); - nip6h = nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_ICMPV6, - net->ipv6.devconf_all->hop_limit); - - skb_reset_transport_header(nskb); - icmp6h = skb_put_zero(nskb, sizeof(struct icmp6hdr)); - icmp6h->icmp6_type = ICMPV6_DEST_UNREACH; - icmp6h->icmp6_code = code; - - skb_put_data(nskb, skb_network_header(oldskb), len); - nip6h->payload_len = htons(nskb->len - sizeof(struct ipv6hdr)); - - icmp6h->icmp6_cksum = - csum_ipv6_magic(&nip6h->saddr, &nip6h->daddr, - nskb->len - sizeof(struct ipv6hdr), - IPPROTO_ICMPV6, - csum_partial(icmp6h, - nskb->len - sizeof(struct ipv6hdr), - 0)); - nft_reject_br_push_etherhdr(oldskb, nskb); br_forward(br_port_get_rcu(dev), nskb, false, true); @@ -364,69 +177,13 @@ static int nft_reject_bridge_validate(const struct nft_ctx *ctx, (1 << NF_BR_LOCAL_IN)); } -static int nft_reject_bridge_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) -{ - struct nft_reject *priv = nft_expr_priv(expr); - int icmp_code; - - if (tb[NFTA_REJECT_TYPE] == NULL) - return -EINVAL; - - priv->type = ntohl(nla_get_be32(tb[NFTA_REJECT_TYPE])); - switch (priv->type) { - case NFT_REJECT_ICMP_UNREACH: - case NFT_REJECT_ICMPX_UNREACH: - if (tb[NFTA_REJECT_ICMP_CODE] == NULL) - return -EINVAL; - - icmp_code = nla_get_u8(tb[NFTA_REJECT_ICMP_CODE]); - if (priv->type == NFT_REJECT_ICMPX_UNREACH && - icmp_code > NFT_REJECT_ICMPX_MAX) - return -EINVAL; - - priv->icmp_code = icmp_code; - break; - case NFT_REJECT_TCP_RST: - break; - default: - return -EINVAL; - } - return 0; -} - -static int nft_reject_bridge_dump(struct sk_buff *skb, - const struct nft_expr *expr) -{ - const struct nft_reject *priv = nft_expr_priv(expr); - - if (nla_put_be32(skb, NFTA_REJECT_TYPE, htonl(priv->type))) - goto nla_put_failure; - - switch (priv->type) { - case NFT_REJECT_ICMP_UNREACH: - case NFT_REJECT_ICMPX_UNREACH: - if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code)) - goto nla_put_failure; - break; - default: - break; - } - - return 0; - -nla_put_failure: - return -1; -} - static struct nft_expr_type nft_reject_bridge_type; static const struct nft_expr_ops nft_reject_bridge_ops = { .type = &nft_reject_bridge_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_reject)), .eval = nft_reject_bridge_eval, - .init = nft_reject_bridge_init, - .dump = nft_reject_bridge_dump, + .init = nft_reject_init, + .dump = nft_reject_dump, .validate = nft_reject_bridge_validate, }; diff --git a/net/core/dev.c b/net/core/dev.c index 82dc6b48e45f..bd6100da66f4 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3206,7 +3206,7 @@ int skb_checksum_help(struct sk_buff *skb) if (skb->ip_summed == CHECKSUM_COMPLETE) goto out_set_summed; - if (unlikely(skb_shinfo(skb)->gso_size)) { + if (unlikely(skb_is_gso(skb))) { skb_warn_bad_offload(skb); return -EINVAL; } @@ -8902,7 +8902,7 @@ static bpf_op_t dev_xdp_bpf_op(struct net_device *dev, enum bpf_xdp_mode mode) return dev->netdev_ops->ndo_bpf; default: return NULL; - }; + } } static struct bpf_xdp_link *dev_xdp_link(struct net_device *dev, diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 205e92e604ef..db8a0ff86f36 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -230,7 +230,7 @@ static int dev_do_ioctl(struct net_device *dev, struct ifreq *ifr, unsigned int cmd) { const struct net_device_ops *ops = dev->netdev_ops; - int err = -EOPNOTSUPP; + int err; err = dsa_ndo_do_ioctl(dev, ifr, cmd); if (err == 0 || err != -EOPNOTSUPP) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 1ba8f0163744..c5e6c0b83a92 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -249,6 +249,9 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, fclones->skb2.fclone = SKB_FCLONE_CLONE; } + + skb_set_kcov_handle(skb, kcov_common_handle()); + out: return skb; nodata: @@ -282,6 +285,8 @@ static struct sk_buff *__build_skb_around(struct sk_buff *skb, memset(shinfo, 0, offsetof(struct skb_shared_info, dataref)); atomic_set(&shinfo->dataref, 1); + skb_set_kcov_handle(skb, kcov_common_handle()); + return skb; } @@ -4203,6 +4208,9 @@ static const u8 skb_ext_type_len[] = { #if IS_ENABLED(CONFIG_MPTCP) [SKB_EXT_MPTCP] = SKB_EXT_CHUNKSIZEOF(struct mptcp_ext), #endif +#if IS_ENABLED(CONFIG_KCOV) + [SKB_EXT_KCOV_HANDLE] = SKB_EXT_CHUNKSIZEOF(u64), +#endif }; static __always_inline unsigned int skb_ext_total_length(void) @@ -4220,6 +4228,9 @@ static __always_inline unsigned int skb_ext_total_length(void) #if IS_ENABLED(CONFIG_MPTCP) skb_ext_type_len[SKB_EXT_MPTCP] + #endif +#if IS_ENABLED(CONFIG_KCOV) + skb_ext_type_len[SKB_EXT_KCOV_HANDLE] + +#endif 0; } diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index 16014ad19406..084e159a12ba 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -1827,6 +1827,8 @@ static int dcb_app_add(const struct dcb_app *app, int ifindex) /** * dcb_getapp - retrieve the DCBX application user priority + * @dev: network interface + * @app: application to get user priority of * * On success returns a non-zero 802.1p user priority bitmap * otherwise returns 0 as the invalid user priority bitmap to @@ -1849,6 +1851,8 @@ EXPORT_SYMBOL(dcb_getapp); /** * dcb_setapp - add CEE dcb application data to app list + * @dev: network interface + * @new: application data to add * * Priority 0 is an invalid priority in CEE spec. This routine * removes applications from the app list if the priority is @@ -1890,6 +1894,8 @@ EXPORT_SYMBOL(dcb_setapp); /** * dcb_ieee_getapp_mask - retrieve the IEEE DCB application priority + * @dev: network interface + * @app: where to store the retrieve application data * * Helper routine which on success returns a non-zero 802.1Qaz user * priority bitmap otherwise returns 0 to indicate the dcb_app was @@ -1912,6 +1918,8 @@ EXPORT_SYMBOL(dcb_ieee_getapp_mask); /** * dcb_ieee_setapp - add IEEE dcb application data to app list + * @dev: network interface + * @new: application data to add * * This adds Application data to the list. Multiple application * entries may exists for the same selector and protocol as long @@ -1946,6 +1954,8 @@ EXPORT_SYMBOL(dcb_ieee_setapp); /** * dcb_ieee_delapp - delete IEEE dcb application data from list + * @dev: network interface + * @del: application data to delete * * This removes a matching APP data from the APP list */ @@ -1975,7 +1985,7 @@ int dcb_ieee_delapp(struct net_device *dev, struct dcb_app *del) } EXPORT_SYMBOL(dcb_ieee_delapp); -/** +/* * dcb_ieee_getapp_prio_dscp_mask_map - For a given device, find mapping from * priorities to the DSCP values assigned to that priority. Initialize p_map * such that each map element holds a bit mask of DSCP values configured for @@ -2004,7 +2014,7 @@ void dcb_ieee_getapp_prio_dscp_mask_map(const struct net_device *dev, } EXPORT_SYMBOL(dcb_ieee_getapp_prio_dscp_mask_map); -/** +/* * dcb_ieee_getapp_dscp_prio_mask_map - For a given device, find mapping from * DSCP values to the priorities assigned to that DSCP value. Initialize p_map * such that each map element holds a bit mask of priorities configured for a @@ -2031,7 +2041,7 @@ dcb_ieee_getapp_dscp_prio_mask_map(const struct net_device *dev, } EXPORT_SYMBOL(dcb_ieee_getapp_dscp_prio_mask_map); -/** +/* * Per 802.1Q-2014, the selector value of 1 is used for matching on Ethernet * type, with valid PID values >= 1536. A special meaning is then assigned to * protocol value of 0: "default priority. For use when priority is not diff --git a/net/dccp/ackvec.c b/net/dccp/ackvec.c index 8f3dd3b1d2d0..c4bbac99740d 100644 --- a/net/dccp/ackvec.c +++ b/net/dccp/ackvec.c @@ -242,6 +242,8 @@ static void dccp_ackvec_add_new(struct dccp_ackvec *av, u32 num_packets, /** * dccp_ackvec_input - Register incoming packet in the buffer + * @av: Ack Vector to register packet to + * @skb: Packet to register */ void dccp_ackvec_input(struct dccp_ackvec *av, struct sk_buff *skb) { @@ -273,6 +275,9 @@ void dccp_ackvec_input(struct dccp_ackvec *av, struct sk_buff *skb) /** * dccp_ackvec_clear_state - Perform house-keeping / garbage-collection + * @av: Ack Vector record to clean + * @ackno: last Ack Vector which has been acknowledged + * * This routine is called when the peer acknowledges the receipt of Ack Vectors * up to and including @ackno. While based on section A.3 of RFC 4340, here * are additional precautions to prevent corrupted buffer state. In particular, diff --git a/net/dccp/ccid.c b/net/dccp/ccid.c index 1e9bb121ba72..6beac5d348e2 100644 --- a/net/dccp/ccid.c +++ b/net/dccp/ccid.c @@ -76,7 +76,7 @@ int ccid_getsockopt_builtin_ccids(struct sock *sk, int len, return err; } -static struct kmem_cache *ccid_kmem_cache_create(int obj_size, char *slab_name_fmt, const char *fmt,...) +static __printf(3, 4) struct kmem_cache *ccid_kmem_cache_create(int obj_size, char *slab_name_fmt, const char *fmt,...) { struct kmem_cache *slab; va_list args; diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c index 3da1f77bd039..4d9823d6dced 100644 --- a/net/dccp/ccids/ccid2.c +++ b/net/dccp/ccids/ccid2.c @@ -181,6 +181,9 @@ MODULE_PARM_DESC(ccid2_do_cwv, "Perform RFC2861 Congestion Window Validation"); /** * ccid2_update_used_window - Track how much of cwnd is actually used + * @hc: socket to update window + * @new_wnd: new window values to add into the filter + * * This is done in addition to CWV. The sender needs to have an idea of how many * packets may be in flight, to set the local Sequence Window value accordingly * (RFC 4340, 7.5.2). The CWV mechanism is exploited to keep track of the @@ -349,6 +352,8 @@ static void ccid2_hc_tx_packet_sent(struct sock *sk, unsigned int len) /** * ccid2_rtt_estimator - Sample RTT and compute RTO using RFC2988 algorithm + * @sk: socket to perform estimator on + * * This code is almost identical with TCP's tcp_rtt_estimator(), since * - it has a higher sampling frequency (recommended by RFC 1323), * - the RTO does not collapse into RTT due to RTTVAR going towards zero, diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c index b9ee1a4a8955..ca8670f78ac6 100644 --- a/net/dccp/ccids/ccid3.c +++ b/net/dccp/ccids/ccid3.c @@ -79,6 +79,8 @@ static inline u64 rfc3390_initial_rate(struct sock *sk) /** * ccid3_update_send_interval - Calculate new t_ipi = s / X_inst + * @hc: socket to have the send interval updated + * * This respects the granularity of X_inst (64 * bytes/second). */ static void ccid3_update_send_interval(struct ccid3_hc_tx_sock *hc) @@ -99,6 +101,7 @@ static u32 ccid3_hc_tx_idle_rtt(struct ccid3_hc_tx_sock *hc, ktime_t now) /** * ccid3_hc_tx_update_x - Update allowed sending rate X + * @sk: socket to be updated * @stamp: most recent time if available - can be left NULL. * * This function tracks draft rfc3448bis, check there for latest details. @@ -151,6 +154,7 @@ static void ccid3_hc_tx_update_x(struct sock *sk, ktime_t *stamp) /** * ccid3_hc_tx_update_s - Track the mean packet size `s' + * @hc: socket to be updated * @len: DCCP packet payload size in bytes * * cf. RFC 4342, 5.3 and RFC 3448, 4.1 @@ -259,6 +263,7 @@ out: /** * ccid3_hc_tx_send_packet - Delay-based dequeueing of TX packets + * @sk: socket to send packet from * @skb: next packet candidate to send on @sk * * This function uses the convention of ccid_packet_dequeue_eval() and @@ -655,6 +660,7 @@ static int ccid3_hc_rx_insert_options(struct sock *sk, struct sk_buff *skb) /** * ccid3_first_li - Implements [RFC 5348, 6.3.1] + * @sk: socket to calculate loss interval for * * Determine the length of the first loss interval via inverse lookup. * Assume that X_recv can be computed by the throughput equation diff --git a/net/dccp/ccids/lib/loss_interval.c b/net/dccp/ccids/lib/loss_interval.c index 67abad695e66..da95319842bb 100644 --- a/net/dccp/ccids/lib/loss_interval.c +++ b/net/dccp/ccids/lib/loss_interval.c @@ -79,6 +79,9 @@ static void tfrc_lh_calc_i_mean(struct tfrc_loss_hist *lh) /** * tfrc_lh_update_i_mean - Update the `open' loss interval I_0 + * @lh: histogram to update + * @skb: received socket triggering loss interval update + * * For recomputing p: returns `true' if p > p_prev <=> 1/p < 1/p_prev */ u8 tfrc_lh_update_i_mean(struct tfrc_loss_hist *lh, struct sk_buff *skb) diff --git a/net/dccp/ccids/lib/packet_history.c b/net/dccp/ccids/lib/packet_history.c index af08e2df7108..0cdda3c66fb5 100644 --- a/net/dccp/ccids/lib/packet_history.c +++ b/net/dccp/ccids/lib/packet_history.c @@ -385,6 +385,9 @@ static inline struct tfrc_rx_hist_entry * /** * tfrc_rx_hist_sample_rtt - Sample RTT from timestamp / CCVal + * @h: receive histogram + * @skb: packet containing timestamp. + * * Based on ideas presented in RFC 4342, 8.1. Returns 0 if it was not able * to compute a sample with given data - calling function should check this. */ diff --git a/net/dccp/feat.c b/net/dccp/feat.c index 788dd629c420..305f56804832 100644 --- a/net/dccp/feat.c +++ b/net/dccp/feat.c @@ -996,6 +996,8 @@ int dccp_feat_finalise_settings(struct dccp_sock *dp) /** * dccp_feat_server_ccid_dependencies - Resolve CCID-dependent features + * @dreq: server socket to resolve + * * It is the server which resolves the dependencies once the CCID has been * fully negotiated. If no CCID has been negotiated, it uses the default CCID. */ @@ -1033,6 +1035,10 @@ static int dccp_feat_preflist_match(u8 *servlist, u8 slen, u8 *clilist, u8 clen) /** * dccp_feat_prefer - Move preferred entry to the start of array + * @preferred_value: entry to move to start of array + * @array: array of preferred entries + * @array_len: size of the array + * * Reorder the @array_len elements in @array so that @preferred_value comes * first. Returns >0 to indicate that @preferred_value does occur in @array. */ diff --git a/net/dccp/output.c b/net/dccp/output.c index 50e6d5699bb2..b8a24734385e 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -143,6 +143,8 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) /** * dccp_determine_ccmps - Find out about CCID-specific packet-size limits + * @dp: socket to find packet size limits of + * * We only consider the HC-sender CCID for setting the CCMPS (RFC 4340, 14.), * since the RX CCID is restricted to feedback packets (Acks), which are small * in comparison with the data traffic. A value of 0 means "no current CCMPS". @@ -236,6 +238,8 @@ static int dccp_wait_for_ccid(struct sock *sk, unsigned long delay) /** * dccp_xmit_packet - Send data packet under control of CCID + * @sk: socket to send data packet on + * * Transmits next-queued payload and informs CCID to account for the packet. */ static void dccp_xmit_packet(struct sock *sk) @@ -296,6 +300,9 @@ static void dccp_xmit_packet(struct sock *sk) /** * dccp_flush_write_queue - Drain queue at end of connection + * @sk: socket to be drained + * @time_budget: time allowed to drain the queue + * * Since dccp_sendmsg queues packets without waiting for them to be sent, it may * happen that the TX queue is not empty at the end of a connection. We give the * HC-sender CCID a grace period of up to @time_budget jiffies. If this function @@ -367,6 +374,8 @@ void dccp_write_xmit(struct sock *sk) /** * dccp_retransmit_skb - Retransmit Request, Close, or CloseReq packets + * @sk: socket to perform retransmit on + * * There are only four retransmittable packet types in DCCP: * - Request in client-REQUEST state (sec. 8.1.1), * - CloseReq in server-CLOSEREQ state (sec. 8.3), diff --git a/net/dccp/qpolicy.c b/net/dccp/qpolicy.c index db2448c33a62..5ba204ec0aca 100644 --- a/net/dccp/qpolicy.c +++ b/net/dccp/qpolicy.c @@ -65,14 +65,16 @@ static bool qpolicy_prio_full(struct sock *sk) * @push: add a new @skb to the write queue * @full: indicates that no more packets will be admitted * @top: peeks at whatever the queueing policy defines as its `top' + * @params: parameter passed to policy operation */ -static struct dccp_qpolicy_operations { +struct dccp_qpolicy_operations { void (*push) (struct sock *sk, struct sk_buff *skb); bool (*full) (struct sock *sk); struct sk_buff* (*top) (struct sock *sk); __be32 params; +}; -} qpol_table[DCCPQ_POLICY_MAX] = { +static struct dccp_qpolicy_operations qpol_table[DCCPQ_POLICY_MAX] = { [DCCPQ_POLICY_SIMPLE] = { .push = qpolicy_simple_push, .full = qpolicy_simple_full, diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 1f9b9b11008c..d975614f7dd6 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -56,6 +56,12 @@ config NET_DSA_TAG_BRCM_PREPEND Broadcom switches which places the tag before the Ethernet header (prepended). +config NET_DSA_TAG_HELLCREEK + tristate "Tag driver for Hirschmann Hellcreek TSN switches" + help + Say Y or M if you want to enable support for tagging frames + for the Hirschmann Hellcreek TSN switches. + config NET_DSA_TAG_GSWIP tristate "Tag driver for Lantiq / Intel GSWIP switches" help diff --git a/net/dsa/Makefile b/net/dsa/Makefile index 4f47b2025ff5..e25d5457964a 100644 --- a/net/dsa/Makefile +++ b/net/dsa/Makefile @@ -10,6 +10,7 @@ obj-$(CONFIG_NET_DSA_TAG_BRCM_COMMON) += tag_brcm.o obj-$(CONFIG_NET_DSA_TAG_DSA) += tag_dsa.o obj-$(CONFIG_NET_DSA_TAG_EDSA) += tag_edsa.o obj-$(CONFIG_NET_DSA_TAG_GSWIP) += tag_gswip.o +obj-$(CONFIG_NET_DSA_TAG_HELLCREEK) += tag_hellcreek.o obj-$(CONFIG_NET_DSA_TAG_KSZ) += tag_ksz.o obj-$(CONFIG_NET_DSA_TAG_RTL4_A) += tag_rtl4_a.o obj-$(CONFIG_NET_DSA_TAG_LAN9303) += tag_lan9303.o diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 3bc5ca40c9fb..59c80052e950 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -548,6 +548,30 @@ netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev) } EXPORT_SYMBOL_GPL(dsa_enqueue_skb); +static int dsa_realloc_skb(struct sk_buff *skb, struct net_device *dev) +{ + int needed_headroom = dev->needed_headroom; + int needed_tailroom = dev->needed_tailroom; + + /* For tail taggers, we need to pad short frames ourselves, to ensure + * that the tail tag does not fail at its role of being at the end of + * the packet, once the master interface pads the frame. Account for + * that pad length here, and pad later. + */ + if (unlikely(needed_tailroom && skb->len < ETH_ZLEN)) + needed_tailroom += ETH_ZLEN - skb->len; + /* skb_headroom() returns unsigned int... */ + needed_headroom = max_t(int, needed_headroom - skb_headroom(skb), 0); + needed_tailroom = max_t(int, needed_tailroom - skb_tailroom(skb), 0); + + if (likely(!needed_headroom && !needed_tailroom && !skb_cloned(skb))) + /* No reallocation needed, yay! */ + return 0; + + return pskb_expand_head(skb, needed_headroom, needed_tailroom, + GFP_ATOMIC); +} + static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); @@ -567,6 +591,17 @@ static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev) */ dsa_skb_tx_timestamp(p, skb); + if (dsa_realloc_skb(skb, dev)) { + dev_kfree_skb_any(skb); + return NETDEV_TX_OK; + } + + /* needed_tailroom should still be 'warm' in the cache line from + * dsa_realloc_skb(), which has also ensured that padding is safe. + */ + if (dev->needed_tailroom) + eth_skb_pad(skb); + /* Transmit function may have to reallocate the original SKB, * in which case it must have freed it. Only free it here on error. */ @@ -1791,6 +1826,16 @@ int dsa_slave_create(struct dsa_port *port) slave_dev->netdev_ops = &dsa_slave_netdev_ops; if (ds->ops->port_max_mtu) slave_dev->max_mtu = ds->ops->port_max_mtu(ds, port->index); + if (cpu_dp->tag_ops->tail_tag) + slave_dev->needed_tailroom = cpu_dp->tag_ops->overhead; + else + slave_dev->needed_headroom = cpu_dp->tag_ops->overhead; + /* Try to save one extra realloc later in the TX path (in the master) + * by also inheriting the master's needed headroom and tailroom. + * The 8021q driver also does this. + */ + slave_dev->needed_headroom += master->needed_headroom; + slave_dev->needed_tailroom += master->needed_tailroom; SET_NETDEV_DEVTYPE(slave_dev, &dsa_type); netdev_for_each_tx_queue(slave_dev, dsa_slave_set_lockdep_class_one, @@ -1987,10 +2032,22 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb, switch (event) { case NETDEV_PRECHANGEUPPER: { struct netdev_notifier_changeupper_info *info = ptr; + struct dsa_switch *ds; + struct dsa_port *dp; + int err; if (!dsa_slave_dev_check(dev)) return dsa_prevent_bridging_8021q_upper(dev, ptr); + dp = dsa_slave_to_port(dev); + ds = dp->ds; + + if (ds->ops->port_prechangeupper) { + err = ds->ops->port_prechangeupper(ds, dp->index, info); + if (err) + return notifier_from_errno(err); + } + if (is_vlan_dev(info->upper_dev)) return dsa_slave_check_8021q_upper(dev, ptr); break; diff --git a/net/dsa/tag_ar9331.c b/net/dsa/tag_ar9331.c index 55b00694cdba..002cf7f952e2 100644 --- a/net/dsa/tag_ar9331.c +++ b/net/dsa/tag_ar9331.c @@ -31,9 +31,6 @@ static struct sk_buff *ar9331_tag_xmit(struct sk_buff *skb, __le16 *phdr; u16 hdr; - if (skb_cow_head(skb, AR9331_HDR_LEN) < 0) - return NULL; - phdr = skb_push(skb, AR9331_HDR_LEN); hdr = FIELD_PREP(AR9331_HDR_VERSION_MASK, AR9331_HDR_VERSION); diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index ad72dff8d524..e934dace3922 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -66,9 +66,6 @@ static struct sk_buff *brcm_tag_xmit_ll(struct sk_buff *skb, u16 queue = skb_get_queue_mapping(skb); u8 *brcm_tag; - if (skb_cow_head(skb, BRCM_TAG_LEN) < 0) - return NULL; - /* The Ethernet switch we are interfaced with needs packets to be at * least 64 bytes (including FCS) otherwise they will be discarded when * they enter the switch port logic. When Broadcom tags are enabled, we diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c index 0b756fae68a5..63d690a0fca6 100644 --- a/net/dsa/tag_dsa.c +++ b/net/dsa/tag_dsa.c @@ -23,9 +23,6 @@ static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev) * the ethertype field for untagged packets. */ if (skb->protocol == htons(ETH_P_8021Q)) { - if (skb_cow_head(skb, 0) < 0) - return NULL; - /* * Construct tagged FROM_CPU DSA tag from 802.1q tag. */ @@ -41,8 +38,6 @@ static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev) dsa_header[2] &= ~0x10; } } else { - if (skb_cow_head(skb, DSA_HLEN) < 0) - return NULL; skb_push(skb, DSA_HLEN); memmove(skb->data, skb->data + DSA_HLEN, 2 * ETH_ALEN); diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c index 120614240319..abf70a29deb4 100644 --- a/net/dsa/tag_edsa.c +++ b/net/dsa/tag_edsa.c @@ -35,8 +35,6 @@ static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev) * current ethertype field if the packet is untagged. */ if (skb->protocol == htons(ETH_P_8021Q)) { - if (skb_cow_head(skb, DSA_HLEN) < 0) - return NULL; skb_push(skb, DSA_HLEN); memmove(skb->data, skb->data + DSA_HLEN, 2 * ETH_ALEN); @@ -60,8 +58,6 @@ static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev) edsa_header[6] &= ~0x10; } } else { - if (skb_cow_head(skb, EDSA_HLEN) < 0) - return NULL; skb_push(skb, EDSA_HLEN); memmove(skb->data, skb->data + EDSA_HLEN, 2 * ETH_ALEN); diff --git a/net/dsa/tag_gswip.c b/net/dsa/tag_gswip.c index 408d4af390a0..2f5bd5e338ab 100644 --- a/net/dsa/tag_gswip.c +++ b/net/dsa/tag_gswip.c @@ -60,13 +60,8 @@ static struct sk_buff *gswip_tag_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_port *dp = dsa_slave_to_port(dev); - int err; u8 *gswip_tag; - err = skb_cow_head(skb, GSWIP_TX_HEADER_LEN); - if (err) - return NULL; - skb_push(skb, GSWIP_TX_HEADER_LEN); gswip_tag = skb->data; diff --git a/net/dsa/tag_hellcreek.c b/net/dsa/tag_hellcreek.c new file mode 100644 index 000000000000..2061de06eafb --- /dev/null +++ b/net/dsa/tag_hellcreek.c @@ -0,0 +1,66 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * net/dsa/tag_hellcreek.c - Hirschmann Hellcreek switch tag format handling + * + * Copyright (C) 2019,2020 Linutronix GmbH + * Author Kurt Kanzenbach <kurt@linutronix.de> + * + * Based on tag_ksz.c. + */ + +#include <linux/etherdevice.h> +#include <linux/list.h> +#include <linux/slab.h> +#include <net/dsa.h> + +#include "dsa_priv.h" + +#define HELLCREEK_TAG_LEN 1 + +static struct sk_buff *hellcreek_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + u8 *tag; + + /* Tag encoding */ + tag = skb_put(skb, HELLCREEK_TAG_LEN); + *tag = BIT(dp->index); + + return skb; +} + +static struct sk_buff *hellcreek_rcv(struct sk_buff *skb, + struct net_device *dev, + struct packet_type *pt) +{ + /* Tag decoding */ + u8 *tag = skb_tail_pointer(skb) - HELLCREEK_TAG_LEN; + unsigned int port = tag[0] & 0x03; + + skb->dev = dsa_master_find_slave(dev, 0, port); + if (!skb->dev) { + netdev_warn(dev, "Failed to get source port: %d\n", port); + return NULL; + } + + pskb_trim_rcsum(skb, skb->len - HELLCREEK_TAG_LEN); + + skb->offload_fwd_mark = true; + + return skb; +} + +static const struct dsa_device_ops hellcreek_netdev_ops = { + .name = "hellcreek", + .proto = DSA_TAG_PROTO_HELLCREEK, + .xmit = hellcreek_xmit, + .rcv = hellcreek_rcv, + .overhead = HELLCREEK_TAG_LEN, + .tail_tag = true, +}; + +MODULE_LICENSE("Dual MIT/GPL"); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_HELLCREEK); + +module_dsa_tag_driver(hellcreek_netdev_ops); diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index 0a5aa982c60d..4820dbcedfa2 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -14,46 +14,6 @@ #define KSZ_EGRESS_TAG_LEN 1 #define KSZ_INGRESS_TAG_LEN 1 -static struct sk_buff *ksz_common_xmit(struct sk_buff *skb, - struct net_device *dev, int len) -{ - struct sk_buff *nskb; - int padlen; - - padlen = (skb->len >= ETH_ZLEN) ? 0 : ETH_ZLEN - skb->len; - - if (skb_tailroom(skb) >= padlen + len) { - /* Let dsa_slave_xmit() free skb */ - if (__skb_put_padto(skb, skb->len + padlen, false)) - return NULL; - - nskb = skb; - } else { - nskb = alloc_skb(NET_IP_ALIGN + skb->len + - padlen + len, GFP_ATOMIC); - if (!nskb) - return NULL; - skb_reserve(nskb, NET_IP_ALIGN); - - skb_reset_mac_header(nskb); - skb_set_network_header(nskb, - skb_network_header(skb) - skb->head); - skb_set_transport_header(nskb, - skb_transport_header(skb) - skb->head); - skb_copy_and_csum_dev(skb, skb_put(nskb, skb->len)); - - /* Let skb_put_padto() free nskb, and let dsa_slave_xmit() free - * skb - */ - if (skb_put_padto(nskb, nskb->len + padlen)) - return NULL; - - consume_skb(skb); - } - - return nskb; -} - static struct sk_buff *ksz_common_rcv(struct sk_buff *skb, struct net_device *dev, unsigned int port, unsigned int len) @@ -90,23 +50,18 @@ static struct sk_buff *ksz_common_rcv(struct sk_buff *skb, static struct sk_buff *ksz8795_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_port *dp = dsa_slave_to_port(dev); - struct sk_buff *nskb; u8 *tag; u8 *addr; - nskb = ksz_common_xmit(skb, dev, KSZ_INGRESS_TAG_LEN); - if (!nskb) - return NULL; - /* Tag encoding */ - tag = skb_put(nskb, KSZ_INGRESS_TAG_LEN); - addr = skb_mac_header(nskb); + tag = skb_put(skb, KSZ_INGRESS_TAG_LEN); + addr = skb_mac_header(skb); *tag = 1 << dp->index; if (is_link_local_ether_addr(addr)) *tag |= KSZ8795_TAIL_TAG_OVERRIDE; - return nskb; + return skb; } static struct sk_buff *ksz8795_rcv(struct sk_buff *skb, struct net_device *dev, @@ -156,18 +111,13 @@ static struct sk_buff *ksz9477_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_port *dp = dsa_slave_to_port(dev); - struct sk_buff *nskb; __be16 *tag; u8 *addr; u16 val; - nskb = ksz_common_xmit(skb, dev, KSZ9477_INGRESS_TAG_LEN); - if (!nskb) - return NULL; - /* Tag encoding */ - tag = skb_put(nskb, KSZ9477_INGRESS_TAG_LEN); - addr = skb_mac_header(nskb); + tag = skb_put(skb, KSZ9477_INGRESS_TAG_LEN); + addr = skb_mac_header(skb); val = BIT(dp->index); @@ -176,7 +126,7 @@ static struct sk_buff *ksz9477_xmit(struct sk_buff *skb, *tag = cpu_to_be16(val); - return nskb; + return skb; } static struct sk_buff *ksz9477_rcv(struct sk_buff *skb, struct net_device *dev, @@ -213,24 +163,19 @@ static struct sk_buff *ksz9893_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_port *dp = dsa_slave_to_port(dev); - struct sk_buff *nskb; u8 *addr; u8 *tag; - nskb = ksz_common_xmit(skb, dev, KSZ_INGRESS_TAG_LEN); - if (!nskb) - return NULL; - /* Tag encoding */ - tag = skb_put(nskb, KSZ_INGRESS_TAG_LEN); - addr = skb_mac_header(nskb); + tag = skb_put(skb, KSZ_INGRESS_TAG_LEN); + addr = skb_mac_header(skb); *tag = BIT(dp->index); if (is_link_local_ether_addr(addr)) *tag |= KSZ9893_TAIL_TAG_OVERRIDE; - return nskb; + return skb; } static const struct dsa_device_ops ksz9893_netdev_ops = { diff --git a/net/dsa/tag_lan9303.c b/net/dsa/tag_lan9303.c index ccfb6f641bbf..aa1318dccaf0 100644 --- a/net/dsa/tag_lan9303.c +++ b/net/dsa/tag_lan9303.c @@ -58,15 +58,6 @@ static struct sk_buff *lan9303_xmit(struct sk_buff *skb, struct net_device *dev) __be16 *lan9303_tag; u16 tag; - /* insert a special VLAN tag between the MAC addresses - * and the current ethertype field. - */ - if (skb_cow_head(skb, LAN9303_TAG_LEN) < 0) { - dev_dbg(&dev->dev, - "Cannot make room for the special tag. Dropping packet\n"); - return NULL; - } - /* provide 'LAN9303_TAG_LEN' bytes additional space */ skb_push(skb, LAN9303_TAG_LEN); diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c index 4cdd9cf428fb..38dcdded74c0 100644 --- a/net/dsa/tag_mtk.c +++ b/net/dsa/tag_mtk.c @@ -34,9 +34,6 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, * table with VID. */ if (!skb_vlan_tagged(skb)) { - if (skb_cow_head(skb, MTK_HDR_LEN) < 0) - return NULL; - skb_push(skb, MTK_HDR_LEN); memmove(skb->data, skb->data + MTK_HDR_LEN, 2 * ETH_ALEN); is_vlan_skb = false; diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c index 3b468aca5c53..16a1afd5b8e1 100644 --- a/net/dsa/tag_ocelot.c +++ b/net/dsa/tag_ocelot.c @@ -143,13 +143,6 @@ static struct sk_buff *ocelot_xmit(struct sk_buff *skb, struct ocelot_port *ocelot_port; u8 *prefix, *injection; u64 qos_class, rew_op; - int err; - - err = skb_cow_head(skb, OCELOT_TOTAL_TAG_LEN); - if (unlikely(err < 0)) { - netdev_err(netdev, "Cannot make room for tag.\n"); - return NULL; - } ocelot_port = ocelot->ports[dp->index]; diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c index 1b9e8507112b..88181b52f480 100644 --- a/net/dsa/tag_qca.c +++ b/net/dsa/tag_qca.c @@ -34,9 +34,6 @@ static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev) __be16 *phdr; u16 hdr; - if (skb_cow_head(skb, QCA_HDR_LEN) < 0) - return NULL; - skb_push(skb, QCA_HDR_LEN); memmove(skb->data, skb->data + QCA_HDR_LEN, 2 * ETH_ALEN); diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c index 3a1cc24a4f0a..5b97ede56a0f 100644 --- a/net/dsa/tag_trailer.c +++ b/net/dsa/tag_trailer.c @@ -13,42 +13,15 @@ static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev) { struct dsa_port *dp = dsa_slave_to_port(dev); - struct sk_buff *nskb; - int padlen; u8 *trailer; - /* - * We have to make sure that the trailer ends up as the very - * last 4 bytes of the packet. This means that we have to pad - * the packet to the minimum ethernet frame size, if necessary, - * before adding the trailer. - */ - padlen = 0; - if (skb->len < 60) - padlen = 60 - skb->len; - - nskb = alloc_skb(NET_IP_ALIGN + skb->len + padlen + 4, GFP_ATOMIC); - if (!nskb) - return NULL; - skb_reserve(nskb, NET_IP_ALIGN); - - skb_reset_mac_header(nskb); - skb_set_network_header(nskb, skb_network_header(skb) - skb->head); - skb_set_transport_header(nskb, skb_transport_header(skb) - skb->head); - skb_copy_and_csum_dev(skb, skb_put(nskb, skb->len)); - consume_skb(skb); - - if (padlen) { - skb_put_zero(nskb, padlen); - } - - trailer = skb_put(nskb, 4); + trailer = skb_put(skb, 4); trailer[0] = 0x80; trailer[1] = 1 << dp->index; trailer[2] = 0x10; trailer[3] = 0x00; - return nskb; + return skb; } static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev, diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c index ec2cd7aab5ad..771688e1b0da 100644 --- a/net/ethtool/ioctl.c +++ b/net/ethtool/ioctl.c @@ -2433,7 +2433,7 @@ static int noinline_for_stack ethtool_set_per_queue(struct net_device *dev, return ethtool_set_per_queue_coalesce(dev, useraddr, &per_queue_opt); default: return -EOPNOTSUPP; - }; + } } static int ethtool_phy_tunable_valid(const struct ethtool_tunable *tuna) diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 1f75dc686b6b..f70b9a0c4957 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1644,6 +1644,8 @@ int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nhc, *flags |= (nhc->nhc_flags & RTNH_F_ONLINK); if (nhc->nhc_flags & RTNH_F_OFFLOAD) *flags |= RTNH_F_OFFLOAD; + if (nhc->nhc_flags & RTNH_F_TRAP) + *flags |= RTNH_F_TRAP; if (!skip_oif && nhc->nhc_dev && nla_put_u32(skb, RTA_OIF, nhc->nhc_dev->ifindex)) diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index ffc5332f1390..28117c05dc35 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -2100,15 +2100,6 @@ static void __fib_info_notify_update(struct net *net, struct fib_table *tb, rtmsg_fib(RTM_NEWROUTE, htonl(n->key), fa, KEYLENGTH - fa->fa_slen, tb->tb_id, info, NLM_F_REPLACE); - - /* call_fib_entry_notifiers will be removed when - * in-kernel notifier is implemented and supported - * for nexthop objects - */ - call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE, - n->key, - KEYLENGTH - fa->fa_slen, fa, - NULL); } } } diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index 93b07739807b..4109055cdea6 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -12,6 +12,128 @@ #include <linux/netfilter_ipv4.h> #include <linux/netfilter_bridge.h> +static int nf_reject_iphdr_validate(struct sk_buff *skb) +{ + struct iphdr *iph; + u32 len; + + if (!pskb_may_pull(skb, sizeof(struct iphdr))) + return 0; + + iph = ip_hdr(skb); + if (iph->ihl < 5 || iph->version != 4) + return 0; + + len = ntohs(iph->tot_len); + if (skb->len < len) + return 0; + else if (len < (iph->ihl*4)) + return 0; + + if (!pskb_may_pull(skb, iph->ihl*4)) + return 0; + + return 1; +} + +struct sk_buff *nf_reject_skb_v4_tcp_reset(struct net *net, + struct sk_buff *oldskb, + const struct net_device *dev, + int hook) +{ + const struct tcphdr *oth; + struct sk_buff *nskb; + struct iphdr *niph; + struct tcphdr _oth; + + if (!nf_reject_iphdr_validate(oldskb)) + return NULL; + + oth = nf_reject_ip_tcphdr_get(oldskb, &_oth, hook); + if (!oth) + return NULL; + + nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) + + LL_MAX_HEADER, GFP_ATOMIC); + if (!nskb) + return NULL; + + nskb->dev = (struct net_device *)dev; + + skb_reserve(nskb, LL_MAX_HEADER); + niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_TCP, + net->ipv4.sysctl_ip_default_ttl); + nf_reject_ip_tcphdr_put(nskb, oldskb, oth); + niph->tot_len = htons(nskb->len); + ip_send_check(niph); + + return nskb; +} +EXPORT_SYMBOL_GPL(nf_reject_skb_v4_tcp_reset); + +struct sk_buff *nf_reject_skb_v4_unreach(struct net *net, + struct sk_buff *oldskb, + const struct net_device *dev, + int hook, u8 code) +{ + struct sk_buff *nskb; + struct iphdr *niph; + struct icmphdr *icmph; + unsigned int len; + __wsum csum; + u8 proto; + + if (!nf_reject_iphdr_validate(oldskb)) + return NULL; + + /* IP header checks: fragment. */ + if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET)) + return NULL; + + /* RFC says return as much as we can without exceeding 576 bytes. */ + len = min_t(unsigned int, 536, oldskb->len); + + if (!pskb_may_pull(oldskb, len)) + return NULL; + + if (pskb_trim_rcsum(oldskb, ntohs(ip_hdr(oldskb)->tot_len))) + return NULL; + + proto = ip_hdr(oldskb)->protocol; + + if (!skb_csum_unnecessary(oldskb) && + nf_reject_verify_csum(proto) && + nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), proto)) + return NULL; + + nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct icmphdr) + + LL_MAX_HEADER + len, GFP_ATOMIC); + if (!nskb) + return NULL; + + nskb->dev = (struct net_device *)dev; + + skb_reserve(nskb, LL_MAX_HEADER); + niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_ICMP, + net->ipv4.sysctl_ip_default_ttl); + + skb_reset_transport_header(nskb); + icmph = skb_put_zero(nskb, sizeof(struct icmphdr)); + icmph->type = ICMP_DEST_UNREACH; + icmph->code = code; + + skb_put_data(nskb, skb_network_header(oldskb), len); + + csum = csum_partial((void *)icmph, len + sizeof(struct icmphdr), 0); + icmph->checksum = csum_fold(csum); + + niph->tot_len = htons(nskb->len); + ip_send_check(niph); + + return nskb; +} +EXPORT_SYMBOL_GPL(nf_reject_skb_v4_unreach); + const struct tcphdr *nf_reject_ip_tcphdr_get(struct sk_buff *oldskb, struct tcphdr *_oth, int hook) { @@ -124,7 +246,8 @@ void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook) if (!oth) return; - if (hook == NF_INET_PRE_ROUTING && nf_reject_fill_skb_dst(oldskb)) + if ((hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) && + nf_reject_fill_skb_dst(oldskb) < 0) return; if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) @@ -193,7 +316,8 @@ void nf_send_unreach(struct sk_buff *skb_in, int code, int hook) if (iph->frag_off & htons(IP_OFFSET)) return; - if (hook == NF_INET_PRE_ROUTING && nf_reject_fill_skb_dst(skb_in)) + if ((hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) && + nf_reject_fill_skb_dst(skb_in) < 0) return; if (skb_csum_unnecessary(skb_in) || !nf_reject_verify_csum(proto)) { diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 0dc43ad28eb9..5e1b22d4f939 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -36,14 +36,145 @@ static const struct nla_policy rtm_nh_policy[NHA_MAX + 1] = { [NHA_FDB] = { .type = NLA_FLAG }, }; +static bool nexthop_notifiers_is_empty(struct net *net) +{ + return !net->nexthop.notifier_chain.head; +} + +static void +__nh_notifier_single_info_init(struct nh_notifier_single_info *nh_info, + const struct nexthop *nh) +{ + struct nh_info *nhi = rtnl_dereference(nh->nh_info); + + nh_info->dev = nhi->fib_nhc.nhc_dev; + nh_info->gw_family = nhi->fib_nhc.nhc_gw_family; + if (nh_info->gw_family == AF_INET) + nh_info->ipv4 = nhi->fib_nhc.nhc_gw.ipv4; + else if (nh_info->gw_family == AF_INET6) + nh_info->ipv6 = nhi->fib_nhc.nhc_gw.ipv6; + + nh_info->is_reject = nhi->reject_nh; + nh_info->is_fdb = nhi->fdb_nh; + nh_info->has_encap = !!nhi->fib_nhc.nhc_lwtstate; +} + +static int nh_notifier_single_info_init(struct nh_notifier_info *info, + const struct nexthop *nh) +{ + info->nh = kzalloc(sizeof(*info->nh), GFP_KERNEL); + if (!info->nh) + return -ENOMEM; + + __nh_notifier_single_info_init(info->nh, nh); + + return 0; +} + +static void nh_notifier_single_info_fini(struct nh_notifier_info *info) +{ + kfree(info->nh); +} + +static int nh_notifier_grp_info_init(struct nh_notifier_info *info, + const struct nexthop *nh) +{ + struct nh_group *nhg = rtnl_dereference(nh->nh_grp); + u16 num_nh = nhg->num_nh; + int i; + + info->nh_grp = kzalloc(struct_size(info->nh_grp, nh_entries, num_nh), + GFP_KERNEL); + if (!info->nh_grp) + return -ENOMEM; + + info->nh_grp->num_nh = num_nh; + info->nh_grp->is_fdb = nhg->fdb_nh; + + for (i = 0; i < num_nh; i++) { + struct nh_grp_entry *nhge = &nhg->nh_entries[i]; + + info->nh_grp->nh_entries[i].id = nhge->nh->id; + info->nh_grp->nh_entries[i].weight = nhge->weight; + __nh_notifier_single_info_init(&info->nh_grp->nh_entries[i].nh, + nhge->nh); + } + + return 0; +} + +static void nh_notifier_grp_info_fini(struct nh_notifier_info *info) +{ + kfree(info->nh_grp); +} + +static int nh_notifier_info_init(struct nh_notifier_info *info, + const struct nexthop *nh) +{ + info->id = nh->id; + info->is_grp = nh->is_group; + + if (info->is_grp) + return nh_notifier_grp_info_init(info, nh); + else + return nh_notifier_single_info_init(info, nh); +} + +static void nh_notifier_info_fini(struct nh_notifier_info *info) +{ + if (info->is_grp) + nh_notifier_grp_info_fini(info); + else + nh_notifier_single_info_fini(info); +} + static int call_nexthop_notifiers(struct net *net, enum nexthop_event_type event_type, - struct nexthop *nh) + struct nexthop *nh, + struct netlink_ext_ack *extack) { + struct nh_notifier_info info = { + .net = net, + .extack = extack, + }; int err; + ASSERT_RTNL(); + + if (nexthop_notifiers_is_empty(net)) + return 0; + + err = nh_notifier_info_init(&info, nh); + if (err) { + NL_SET_ERR_MSG(extack, "Failed to initialize nexthop notifier info"); + return err; + } + err = blocking_notifier_call_chain(&net->nexthop.notifier_chain, - event_type, nh); + event_type, &info); + nh_notifier_info_fini(&info); + + return notifier_to_errno(err); +} + +static int call_nexthop_notifier(struct notifier_block *nb, struct net *net, + enum nexthop_event_type event_type, + struct nexthop *nh, + struct netlink_ext_ack *extack) +{ + struct nh_notifier_info info = { + .net = net, + .extack = extack, + }; + int err; + + err = nh_notifier_info_init(&info, nh); + if (err) + return err; + + err = nb->notifier_call(nb, event_type, &info); + nh_notifier_info_fini(&info); + return notifier_to_errno(err); } @@ -782,9 +913,10 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge, { struct nh_grp_entry *nhges, *new_nhges; struct nexthop *nhp = nhge->nh_parent; + struct netlink_ext_ack extack; struct nexthop *nh = nhge->nh; struct nh_group *nhg, *newg; - int i, j; + int i, j, err; WARN_ON(!nh); @@ -832,6 +964,10 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge, list_del(&nhge->nh_list); nexthop_put(nhge->nh); + err = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, nhp, &extack); + if (err) + pr_err("%s\n", extack._msg); + if (nlinfo) nexthop_notify(RTM_NEWNEXTHOP, nhp, nlinfo); } @@ -907,7 +1043,7 @@ static void __remove_nexthop(struct net *net, struct nexthop *nh, static void remove_nexthop(struct net *net, struct nexthop *nh, struct nl_info *nlinfo) { - call_nexthop_notifiers(net, NEXTHOP_EVENT_DEL, nh); + call_nexthop_notifiers(net, NEXTHOP_EVENT_DEL, nh, NULL); /* remove from the tree */ rb_erase(&nh->rb_node, &net->nexthop.rb_root); @@ -940,13 +1076,17 @@ static int replace_nexthop_grp(struct net *net, struct nexthop *old, struct netlink_ext_ack *extack) { struct nh_group *oldg, *newg; - int i; + int i, err; if (!new->is_group) { NL_SET_ERR_MSG(extack, "Can not replace a nexthop group with a nexthop."); return -EINVAL; } + err = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, new, extack); + if (err) + return err; + oldg = rtnl_dereference(old->nh_grp); newg = rtnl_dereference(new->nh_grp); @@ -985,31 +1125,54 @@ static int replace_nexthop_single(struct net *net, struct nexthop *old, struct nexthop *new, struct netlink_ext_ack *extack) { + u8 old_protocol, old_nh_flags; struct nh_info *oldi, *newi; + struct nh_grp_entry *nhge; + int err; if (new->is_group) { NL_SET_ERR_MSG(extack, "Can not replace a nexthop with a nexthop group."); return -EINVAL; } + err = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, new, extack); + if (err) + return err; + + /* Hardware flags were set on 'old' as 'new' is not in the red-black + * tree. Therefore, inherit the flags from 'old' to 'new'. + */ + new->nh_flags |= old->nh_flags & (RTNH_F_OFFLOAD | RTNH_F_TRAP); + oldi = rtnl_dereference(old->nh_info); newi = rtnl_dereference(new->nh_info); newi->nh_parent = old; oldi->nh_parent = new; + old_protocol = old->protocol; + old_nh_flags = old->nh_flags; + old->protocol = new->protocol; old->nh_flags = new->nh_flags; rcu_assign_pointer(old->nh_info, newi); rcu_assign_pointer(new->nh_info, oldi); + /* Send a replace notification for all the groups using the nexthop. */ + list_for_each_entry(nhge, &old->grp_list, nh_list) { + struct nexthop *nhp = nhge->nh_parent; + + err = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, nhp, + extack); + if (err) + goto err_notify; + } + /* When replacing an IPv4 nexthop with an IPv6 nexthop, potentially * update IPv4 indication in all the groups using the nexthop. */ if (oldi->family == AF_INET && newi->family == AF_INET6) { - struct nh_grp_entry *nhge; - list_for_each_entry(nhge, &old->grp_list, nh_list) { struct nexthop *nhp = nhge->nh_parent; struct nh_group *nhg; @@ -1020,6 +1183,21 @@ static int replace_nexthop_single(struct net *net, struct nexthop *old, } return 0; + +err_notify: + rcu_assign_pointer(new->nh_info, newi); + rcu_assign_pointer(old->nh_info, oldi); + old->nh_flags = old_nh_flags; + old->protocol = old_protocol; + oldi->nh_parent = old; + newi->nh_parent = new; + list_for_each_entry_continue_reverse(nhge, &old->grp_list, nh_list) { + struct nexthop *nhp = nhge->nh_parent; + + call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, nhp, extack); + } + call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, old, extack); + return err; } static void __nexthop_replace_notify(struct net *net, struct nexthop *nh, @@ -1168,7 +1346,11 @@ static int insert_nexthop(struct net *net, struct nexthop *new_nh, rb_link_node_rcu(&new_nh->rb_node, parent, pp); rb_insert_color(&new_nh->rb_node, root); - rc = 0; + + rc = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, new_nh, extack); + if (rc) + rb_erase(&new_nh->rb_node, &net->nexthop.rb_root); + out: if (!rc) { nh_base_seq_inc(net); @@ -1957,10 +2139,40 @@ static struct notifier_block nh_netdev_notifier = { .notifier_call = nh_netdev_event, }; -int register_nexthop_notifier(struct net *net, struct notifier_block *nb) +static int nexthops_dump(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) +{ + struct rb_root *root = &net->nexthop.rb_root; + struct rb_node *node; + int err = 0; + + for (node = rb_first(root); node; node = rb_next(node)) { + struct nexthop *nh; + + nh = rb_entry(node, struct nexthop, rb_node); + err = call_nexthop_notifier(nb, net, NEXTHOP_EVENT_REPLACE, nh, + extack); + if (err) + break; + } + + return err; +} + +int register_nexthop_notifier(struct net *net, struct notifier_block *nb, + struct netlink_ext_ack *extack) { - return blocking_notifier_chain_register(&net->nexthop.notifier_chain, - nb); + int err; + + rtnl_lock(); + err = nexthops_dump(net, nb, extack); + if (err) + goto unlock; + err = blocking_notifier_chain_register(&net->nexthop.notifier_chain, + nb); +unlock: + rtnl_unlock(); + return err; } EXPORT_SYMBOL(register_nexthop_notifier); @@ -1971,6 +2183,27 @@ int unregister_nexthop_notifier(struct net *net, struct notifier_block *nb) } EXPORT_SYMBOL(unregister_nexthop_notifier); +void nexthop_set_hw_flags(struct net *net, u32 id, bool offload, bool trap) +{ + struct nexthop *nexthop; + + rcu_read_lock(); + + nexthop = nexthop_find_by_id(net, id); + if (!nexthop) + goto out; + + nexthop->nh_flags &= ~(RTNH_F_OFFLOAD | RTNH_F_TRAP); + if (offload) + nexthop->nh_flags |= RTNH_F_OFFLOAD; + if (trap) + nexthop->nh_flags |= RTNH_F_TRAP; + +out: + rcu_read_unlock(); +} +EXPORT_SYMBOL(nexthop_set_hw_flags); + static void __net_exit nexthop_net_exit(struct net *net) { rtnl_lock(); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 389d1b340248..fb3a7750f623 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2546,7 +2546,7 @@ static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo) * 1) If the packets in flight is larger than ssthresh, PRR spreads the * cwnd reductions across a full RTT. * 2) Otherwise PRR uses packet conservation to send as much as delivered. - * But when the retransmits are acked without further losses, PRR + * But when SND_UNA is acked without further losses, * slow starts cwnd up to ssthresh to speed up the recovery. */ static void tcp_init_cwnd_reduction(struct sock *sk) @@ -2563,7 +2563,7 @@ static void tcp_init_cwnd_reduction(struct sock *sk) tcp_ecn_queue_cwr(tp); } -void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int flag) +void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int newly_lost, int flag) { struct tcp_sock *tp = tcp_sk(sk); int sndcnt = 0; @@ -2577,8 +2577,7 @@ void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int flag) u64 dividend = (u64)tp->snd_ssthresh * tp->prr_delivered + tp->prior_cwnd - 1; sndcnt = div_u64(dividend, tp->prior_cwnd) - tp->prr_out; - } else if ((flag & (FLAG_RETRANS_DATA_ACKED | FLAG_LOST_RETRANS)) == - FLAG_RETRANS_DATA_ACKED) { + } else if (flag & FLAG_SND_UNA_ADVANCED && !newly_lost) { sndcnt = min_t(int, delta, max_t(int, tp->prr_delivered - tp->prr_out, newly_acked_sacked) + 1); @@ -3419,7 +3418,7 @@ static void tcp_cong_control(struct sock *sk, u32 ack, u32 acked_sacked, if (tcp_in_cwnd_reduction(sk)) { /* Reduce cwnd if state mandates */ - tcp_cwnd_reduction(sk, acked_sacked, flag); + tcp_cwnd_reduction(sk, acked_sacked, rs->losses, flag); } else if (tcp_may_raise_cwnd(sk, flag)) { /* Advance cwnd if state allows */ tcp_cong_avoid(sk, ack, acked_sacked); diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c index 8c643a4ffad1..e6459537d4d2 100644 --- a/net/ipv4/tcp_lp.c +++ b/net/ipv4/tcp_lp.c @@ -89,6 +89,7 @@ struct lp { /** * tcp_lp_init + * @sk: socket to initialize congestion control algorithm for * * Init all required variables. * Clone the handling from Vegas module implementation. @@ -111,6 +112,7 @@ static void tcp_lp_init(struct sock *sk) /** * tcp_lp_cong_avoid + * @sk: socket to avoid congesting * * Implementation of cong_avoid. * Will only call newReno CA when away from inference. @@ -126,6 +128,7 @@ static void tcp_lp_cong_avoid(struct sock *sk, u32 ack, u32 acked) /** * tcp_lp_remote_hz_estimator + * @sk: socket which needs an estimate for the remote HZs * * Estimate remote HZ. * We keep on updating the estimated value, where original TCP-LP @@ -176,6 +179,7 @@ static u32 tcp_lp_remote_hz_estimator(struct sock *sk) /** * tcp_lp_owd_calculator + * @sk: socket to calculate one way delay for * * Calculate one way delay (in relative format). * Original implement OWD as minus of remote time difference to local time @@ -210,6 +214,8 @@ static u32 tcp_lp_owd_calculator(struct sock *sk) /** * tcp_lp_rtt_sample + * @sk: socket to add a rtt sample to + * @rtt: round trip time, which is ignored! * * Implementation or rtt_sample. * Will take the following action, @@ -254,6 +260,7 @@ static void tcp_lp_rtt_sample(struct sock *sk, u32 rtt) /** * tcp_lp_pkts_acked + * @sk: socket requiring congestion avoidance calculations * * Implementation of pkts_acked. * Deal with active drop under Early Congestion Indication. diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index bf48cd73e967..9abf5a0358d5 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1569,6 +1569,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, if (!buff) return -ENOMEM; /* We'll just try again later. */ skb_copy_decrypted(buff, skb); + mptcp_skb_ext_copy(buff, skb); sk_wmem_queued_add(sk, buff->truesize); sk_mem_charge(sk, buff->truesize); @@ -2123,6 +2124,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, if (unlikely(!buff)) return -ENOMEM; skb_copy_decrypted(buff, skb); + mptcp_skb_ext_copy(buff, skb); sk_wmem_queued_add(sk, buff->truesize); sk_mem_charge(sk, buff->truesize); @@ -2393,6 +2395,7 @@ static int tcp_mtu_probe(struct sock *sk) skb = tcp_send_head(sk); skb_copy_decrypted(nskb, skb); + mptcp_skb_ext_copy(nskb, skb); TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(skb)->seq; TCP_SKB_CB(nskb)->end_seq = TCP_SKB_CB(skb)->seq + probe_size; diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c index f65a3ddd0d58..177307a3081f 100644 --- a/net/ipv4/tcp_recovery.c +++ b/net/ipv4/tcp_recovery.c @@ -153,6 +153,7 @@ void tcp_rack_reo_timeout(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); u32 timeout, prior_inflight; + u32 lost = tp->lost; prior_inflight = tcp_packets_in_flight(tp); tcp_rack_detect_loss(sk, &timeout); @@ -160,7 +161,7 @@ void tcp_rack_reo_timeout(struct sock *sk) if (inet_csk(sk)->icsk_ca_state != TCP_CA_Recovery) { tcp_enter_recovery(sk, false); if (!inet_csk(sk)->icsk_ca_ops->cong_control) - tcp_cwnd_reduction(sk, 1, 0); + tcp_cwnd_reduction(sk, 1, tp->lost - lost, 0); } tcp_xmit_retransmit_queue(sk); } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 09f0a23d1a01..ca04a8a35e52 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -702,7 +702,7 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) sk = __udp4_lib_lookup(net, iph->daddr, uh->dest, iph->saddr, uh->source, skb->dev->ifindex, inet_sdif(skb), udptable, NULL); - if (!sk) { + if (!sk || udp_sk(sk)->encap_type) { /* No socket for error: try tunnels before discarding */ sk = ERR_PTR(-ENOENT); if (static_branch_unlikely(&udp_encap_needed_key)) { diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index e67a66fbf27b..b8b1fdeb5af9 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -49,6 +49,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, __skb_pull(skb, tnl_hlen); skb_reset_mac_header(skb); skb_set_network_header(skb, skb_inner_network_offset(skb)); + skb_set_transport_header(skb, skb_inner_transport_offset(skb)); skb->mac_len = skb_inner_network_offset(skb); skb->protocol = new_protocol; @@ -67,6 +68,8 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb, (NETIF_F_HW_CSUM | NETIF_F_IP_CSUM)))); features &= skb->dev->hw_enc_features; + /* CRC checksum can't be handled by HW when it's a UDP tunneling packet. */ + features &= ~NETIF_F_SCTP_CRC; /* The only checksum offload we care about from here on out is the * outer one so strip the existing checksum feature flags and diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 01146b66d666..4211e960130c 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1997,6 +1997,7 @@ EXPORT_SYMBOL(ipv6_chk_prefix); * ipv6_dev_find - find the first device with a given source address. * @net: the net namespace * @addr: the source address + * @dev: used to find the L3 domain of interest * * The caller should be protected by RCU, or RTNL. */ diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c index 78f766019b7e..51184a70ac7e 100644 --- a/net/ipv6/calipso.c +++ b/net/ipv6/calipso.c @@ -423,7 +423,7 @@ static void calipso_doi_free_rcu(struct rcu_head *entry) /** * calipso_doi_remove - Remove an existing DOI from the CALIPSO protocol engine * @doi: the DOI value - * @audit_secid: the LSM secid to use in the audit message + * @audit_info: NetLabel audit information * * Description: * Removes a DOI definition from the CALIPSO engine. The NetLabel routines will @@ -1226,7 +1226,7 @@ static int calipso_req_setattr(struct request_sock *req, /** * calipso_req_delattr - Delete the CALIPSO option from a request socket - * @reg: the request socket + * @req: the request socket * * Description: * Removes the CALIPSO option from a request socket, if present. diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 648db3fe508f..74a6ea9f8862 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -204,6 +204,7 @@ ip6_tnl_lookup(struct net *net, int link, /** * ip6_tnl_bucket - get head of list matching given tunnel parameters + * @ip6n: the private data for ip6_vti in the netns * @p: parameters containing tunnel end-points * * Description: @@ -230,6 +231,7 @@ ip6_tnl_bucket(struct ip6_tnl_net *ip6n, const struct __ip6_tnl_parm *p) /** * ip6_tnl_link - add tunnel to hash table + * @ip6n: the private data for ip6_vti in the netns * @t: tunnel to be added **/ @@ -246,6 +248,7 @@ ip6_tnl_link(struct ip6_tnl_net *ip6n, struct ip6_tnl *t) /** * ip6_tnl_unlink - remove tunnel from hash table + * @ip6n: the private data for ip6_vti in the netns * @t: tunnel to be removed **/ @@ -417,6 +420,7 @@ ip6_tnl_dev_uninit(struct net_device *dev) /** * parse_tvl_tnl_enc_lim - handle encapsulation limit option * @skb: received socket buffer + * @raw: the ICMPv6 error message data * * Return: * 0 if none was found, @@ -485,14 +489,9 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw) } EXPORT_SYMBOL(ip6_tnl_parse_tlv_enc_lim); -/** - * ip6_tnl_err - tunnel error handler - * - * Description: - * ip6_tnl_err() should handle errors in the tunnel according - * to the specifications in RFC 2473. - **/ - +/* ip6_tnl_err() should handle errors in the tunnel according to the + * specifications in RFC 2473. + */ static int ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, u8 *type, u8 *code, int *msg, __u32 *info, int offset) diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 5f9c4fdc120d..46d137a693ac 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -125,6 +125,7 @@ vti6_tnl_lookup(struct net *net, const struct in6_addr *remote, /** * vti6_tnl_bucket - get head of list matching given tunnel parameters + * @ip6n: the private data for ip6_vti in the netns * @p: parameters containing tunnel end-points * * Description: diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 8cd2782a31e4..6c8604390266 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -548,7 +548,7 @@ done: } int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf, - struct sockaddr_storage *p) + struct sockaddr_storage __user *p) { int err, i, count, copycount; const struct in6_addr *group; diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index 4aef6baaa55e..aa35e6e37c1f 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -12,6 +12,140 @@ #include <linux/netfilter_ipv6.h> #include <linux/netfilter_bridge.h> +static bool nf_reject_v6_csum_ok(struct sk_buff *skb, int hook) +{ + const struct ipv6hdr *ip6h = ipv6_hdr(skb); + int thoff; + __be16 fo; + u8 proto = ip6h->nexthdr; + + if (skb_csum_unnecessary(skb)) + return true; + + if (ip6h->payload_len && + pskb_trim_rcsum(skb, ntohs(ip6h->payload_len) + sizeof(*ip6h))) + return false; + + ip6h = ipv6_hdr(skb); + thoff = ipv6_skip_exthdr(skb, ((u8*)(ip6h+1) - skb->data), &proto, &fo); + if (thoff < 0 || thoff >= skb->len || (fo & htons(~0x7)) != 0) + return false; + + if (!nf_reject_verify_csum(proto)) + return true; + + return nf_ip6_checksum(skb, hook, thoff, proto) == 0; +} + +static int nf_reject_ip6hdr_validate(struct sk_buff *skb) +{ + struct ipv6hdr *hdr; + u32 pkt_len; + + if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) + return 0; + + hdr = ipv6_hdr(skb); + if (hdr->version != 6) + return 0; + + pkt_len = ntohs(hdr->payload_len); + if (pkt_len + sizeof(struct ipv6hdr) > skb->len) + return 0; + + return 1; +} + +struct sk_buff *nf_reject_skb_v6_tcp_reset(struct net *net, + struct sk_buff *oldskb, + const struct net_device *dev, + int hook) +{ + struct sk_buff *nskb; + const struct tcphdr *oth; + struct tcphdr _oth; + unsigned int otcplen; + struct ipv6hdr *nip6h; + + if (!nf_reject_ip6hdr_validate(oldskb)) + return NULL; + + oth = nf_reject_ip6_tcphdr_get(oldskb, &_oth, &otcplen, hook); + if (!oth) + return NULL; + + nskb = alloc_skb(sizeof(struct ipv6hdr) + sizeof(struct tcphdr) + + LL_MAX_HEADER, GFP_ATOMIC); + if (!nskb) + return NULL; + + nskb->dev = (struct net_device *)dev; + + skb_reserve(nskb, LL_MAX_HEADER); + nip6h = nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_TCP, + net->ipv6.devconf_all->hop_limit); + nf_reject_ip6_tcphdr_put(nskb, oldskb, oth, otcplen); + nip6h->payload_len = htons(nskb->len - sizeof(struct ipv6hdr)); + + return nskb; +} +EXPORT_SYMBOL_GPL(nf_reject_skb_v6_tcp_reset); + +struct sk_buff *nf_reject_skb_v6_unreach(struct net *net, + struct sk_buff *oldskb, + const struct net_device *dev, + int hook, u8 code) +{ + struct sk_buff *nskb; + struct ipv6hdr *nip6h; + struct icmp6hdr *icmp6h; + unsigned int len; + + if (!nf_reject_ip6hdr_validate(oldskb)) + return NULL; + + /* Include "As much of invoking packet as possible without the ICMPv6 + * packet exceeding the minimum IPv6 MTU" in the ICMP payload. + */ + len = min_t(unsigned int, 1220, oldskb->len); + + if (!pskb_may_pull(oldskb, len)) + return NULL; + + if (!nf_reject_v6_csum_ok(oldskb, hook)) + return NULL; + + nskb = alloc_skb(sizeof(struct ipv6hdr) + sizeof(struct icmp6hdr) + + LL_MAX_HEADER + len, GFP_ATOMIC); + if (!nskb) + return NULL; + + nskb->dev = (struct net_device *)dev; + + skb_reserve(nskb, LL_MAX_HEADER); + nip6h = nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_ICMPV6, + net->ipv6.devconf_all->hop_limit); + + skb_reset_transport_header(nskb); + icmp6h = skb_put_zero(nskb, sizeof(struct icmp6hdr)); + icmp6h->icmp6_type = ICMPV6_DEST_UNREACH; + icmp6h->icmp6_code = code; + + skb_put_data(nskb, skb_network_header(oldskb), len); + nip6h->payload_len = htons(nskb->len - sizeof(struct ipv6hdr)); + + icmp6h->icmp6_cksum = + csum_ipv6_magic(&nip6h->saddr, &nip6h->daddr, + nskb->len - sizeof(struct ipv6hdr), + IPPROTO_ICMPV6, + csum_partial(icmp6h, + nskb->len - sizeof(struct ipv6hdr), + 0)); + + return nskb; +} +EXPORT_SYMBOL_GPL(nf_reject_skb_v6_unreach); + const struct tcphdr *nf_reject_ip6_tcphdr_get(struct sk_buff *oldskb, struct tcphdr *otcph, unsigned int *otcplen, int hook) @@ -170,7 +304,7 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook) fl6.fl6_sport = otcph->dest; fl6.fl6_dport = otcph->source; - if (hook == NF_INET_PRE_ROUTING) { + if (hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) { nf_ip6_route(net, &dst, flowi6_to_flowi(&fl6), false); if (!dst) return; @@ -268,7 +402,8 @@ void nf_send_unreach6(struct net *net, struct sk_buff *skb_in, if (hooknum == NF_INET_LOCAL_OUT && skb_in->dev == NULL) skb_in->dev = net->loopback_dev; - if (hooknum == NF_INET_PRE_ROUTING && nf_reject6_fill_skb_dst(skb_in)) + if ((hooknum == NF_INET_PRE_ROUTING || hooknum == NF_INET_INGRESS) && + nf_reject6_fill_skb_dst(skb_in) < 0) return; icmpv6_send(skb_in, ICMPV6_DEST_UNREACH, code, 0); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 7e0ce7af8234..f91a689edafd 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -6039,11 +6039,6 @@ void fib6_rt_update(struct net *net, struct fib6_info *rt, struct sk_buff *skb; int err = -ENOBUFS; - /* call_fib6_entry_notifiers will be removed when in-kernel notifier - * is implemented and supported for nexthop objects - */ - call_fib6_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE, rt, NULL); - skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any()); if (!skb) goto errout; diff --git a/net/ipv6/rpl.c b/net/ipv6/rpl.c index 307f336b5353..488aec9e1a74 100644 --- a/net/ipv6/rpl.c +++ b/net/ipv6/rpl.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/** +/* * Authors: * (C) 2020 Alexander Aring <alex.aring@gmail.com> */ diff --git a/net/ipv6/rpl_iptunnel.c b/net/ipv6/rpl_iptunnel.c index 5fdf3ebb953f..233da43dd8d7 100644 --- a/net/ipv6/rpl_iptunnel.c +++ b/net/ipv6/rpl_iptunnel.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only -/** +/* * Authors: * (C) 2020 Alexander Aring <alex.aring@gmail.com> */ diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 29d9691359b9..cde9b8874d4b 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -560,7 +560,7 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source, inet6_iif(skb), inet6_sdif(skb), udptable, NULL); - if (!sk) { + if (!sk || udp_sk(sk)->encap_type) { /* No socket for error: try tunnels before discarding */ sk = ERR_PTR(-ENOENT); if (static_branch_unlikely(&udpv6_encap_needed_key)) { diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index 584157a07759..aa602af8e49d 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -28,10 +28,6 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, int tnl_hlen; int err; - mss = skb_shinfo(skb)->gso_size; - if (unlikely(skb->len <= mss)) - goto out; - if (skb->encapsulation && skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM)) segs = skb_udp_tunnel_segment(skb, features, true); @@ -48,6 +44,10 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) return __udp_gso_segment(skb, features); + mss = skb_shinfo(skb)->gso_size; + if (unlikely(skb->len <= mss)) + goto out; + /* Do software UFO. Complete and fill in the UDP checksum as HW cannot * do checksum of UDP packets sent as multiple IP fragments. */ diff --git a/net/l3mdev/l3mdev.c b/net/l3mdev/l3mdev.c index 864326f150e2..ad7730b68772 100644 --- a/net/l3mdev/l3mdev.c +++ b/net/l3mdev/l3mdev.c @@ -241,6 +241,7 @@ EXPORT_SYMBOL_GPL(l3mdev_link_scope_lookup); * L3 master device * @net: network namespace for device index lookup * @fl: flow struct + * @arg: store the table the rule matched with here */ int l3mdev_fib_rule_match(struct net *net, struct flowi *fl, diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c index 1144cda2a0fc..912aa9bd5e29 100644 --- a/net/llc/llc_conn.c +++ b/net/llc/llc_conn.c @@ -909,6 +909,8 @@ static void llc_sk_init(struct sock *sk) * @net: network namespace * @family: upper layer protocol family * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc) + * @prot: struct proto associated with this new sock instance + * @kern: is this to be a kernel socket? * * Allocates a LLC sock and initializes it. Returns the new LLC sock * or %NULL if there's no memory available for one diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 1be775979132..56a1bcea2c1c 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1356,6 +1356,7 @@ static void ieee80211_iface_work(struct work_struct *work) while ((skb = skb_dequeue(&sdata->skb_queue))) { struct ieee80211_mgmt *mgmt = (void *)skb->data; + kcov_remote_start_common(skb_get_kcov_handle(skb)); if (ieee80211_is_action(mgmt->frame_control) && mgmt->u.action.category == WLAN_CATEGORY_BACK) { int len = skb->len; @@ -1465,6 +1466,7 @@ static void ieee80211_iface_work(struct work_struct *work) } kfree_skb(skb); + kcov_remote_stop(); } /* then other type-dependent work */ diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 1e2e5a406d58..09d1c9fb8872 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -4742,6 +4742,8 @@ void ieee80211_rx_list(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta, status->rx_flags = 0; + kcov_remote_start_common(skb_get_kcov_handle(skb)); + /* * Frames with failed FCS/PLCP checksum are not returned, * all other frames are returned without radiotap header @@ -4749,15 +4751,15 @@ void ieee80211_rx_list(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta, * Also, frames with less than 16 bytes are dropped. */ skb = ieee80211_rx_monitor(local, skb, rate); - if (!skb) - return; - - ieee80211_tpt_led_trig_rx(local, - ((struct ieee80211_hdr *)skb->data)->frame_control, - skb->len); + if (skb) { + ieee80211_tpt_led_trig_rx(local, + ((struct ieee80211_hdr *)skb->data)->frame_control, + skb->len); - __ieee80211_rx_handle_packet(hw, pubsta, skb, list); + __ieee80211_rx_handle_packet(hw, pubsta, skb, list); + } + kcov_remote_stop(); return; drop: kfree_skb(skb); diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index f2868a8a50c3..47bab701555f 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -377,6 +377,8 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev, if (!pskb_may_pull(skb, sizeof(*hdr))) goto err; + skb_dst_drop(skb); + /* Read and decode the label */ hdr = mpls_hdr(skb); dec = mpls_entry_decode(hdr); diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c index 54b888f94009..96ba616f59bf 100644 --- a/net/mptcp/ctrl.c +++ b/net/mptcp/ctrl.c @@ -18,6 +18,7 @@ struct mptcp_pernet { struct ctl_table_header *ctl_table_hdr; int mptcp_enabled; + unsigned int add_addr_timeout; }; static struct mptcp_pernet *mptcp_get_pernet(struct net *net) @@ -30,6 +31,11 @@ int mptcp_is_enabled(struct net *net) return mptcp_get_pernet(net)->mptcp_enabled; } +unsigned int mptcp_get_add_addr_timeout(struct net *net) +{ + return mptcp_get_pernet(net)->add_addr_timeout; +} + static struct ctl_table mptcp_sysctl_table[] = { { .procname = "enabled", @@ -40,12 +46,19 @@ static struct ctl_table mptcp_sysctl_table[] = { */ .proc_handler = proc_dointvec, }, + { + .procname = "add_addr_timeout", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, {} }; static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet) { pernet->mptcp_enabled = 1; + pernet->add_addr_timeout = TCP_RTO_MAX; } static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet) @@ -61,6 +74,7 @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet) } table[0].data = &pernet->mptcp_enabled; + table[1].data = &pernet->add_addr_timeout; hdr = register_net_sysctl(net, MPTCP_SYSCTL_PATH, table); if (!hdr) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 0d6f3d912891..ed60538df7b2 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -206,6 +206,7 @@ static void mptcp_pm_add_timer(struct timer_list *timer) struct mptcp_pm_add_entry *entry = from_timer(entry, timer, add_timer); struct mptcp_sock *msk = entry->sock; struct sock *sk = (struct sock *)msk; + struct net *net = sock_net(sk); pr_debug("msk=%p", msk); @@ -232,7 +233,8 @@ static void mptcp_pm_add_timer(struct timer_list *timer) } if (entry->retrans_times < ADD_ADDR_RETRANS_MAX) - sk_reset_timer(sk, timer, jiffies + TCP_RTO_MAX); + sk_reset_timer(sk, timer, + jiffies + mptcp_get_add_addr_timeout(net)); spin_unlock_bh(&msk->pm.lock); @@ -264,6 +266,7 @@ static bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk, { struct mptcp_pm_add_entry *add_entry = NULL; struct sock *sk = (struct sock *)msk; + struct net *net = sock_net(sk); if (lookup_anno_list_by_saddr(msk, &entry->addr)) return false; @@ -279,7 +282,8 @@ static bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk, add_entry->retrans_times = 0; timer_setup(&add_entry->add_timer, mptcp_pm_add_timer, 0); - sk_reset_timer(sk, &add_entry->add_timer, jiffies + TCP_RTO_MAX); + sk_reset_timer(sk, &add_entry->add_timer, + jiffies + mptcp_get_add_addr_timeout(net)); return true; } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index e7419fd15d84..b84b84adc9ad 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -466,6 +466,18 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, struct tcp_sock *tp; u32 old_copied_seq; bool done = false; + int sk_rbuf; + + sk_rbuf = READ_ONCE(sk->sk_rcvbuf); + + if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) { + int ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf); + + if (unlikely(ssk_rbuf > sk_rbuf)) { + WRITE_ONCE(sk->sk_rcvbuf, ssk_rbuf); + sk_rbuf = ssk_rbuf; + } + } pr_debug("msk=%p ssk=%p", msk, ssk); tp = tcp_sk(ssk); @@ -528,7 +540,7 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, WRITE_ONCE(tp->copied_seq, seq); more_data_avail = mptcp_subflow_data_available(ssk); - if (atomic_read(&sk->sk_rmem_alloc) > READ_ONCE(sk->sk_rcvbuf)) { + if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf) { done = true; break; } @@ -622,6 +634,7 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct mptcp_sock *msk = mptcp_sk(sk); + int sk_rbuf, ssk_rbuf; bool wake; /* move_skbs_to_msk below can legitly clear the data_avail flag, @@ -632,12 +645,16 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) if (wake) set_bit(MPTCP_DATA_READY, &msk->flags); - if (atomic_read(&sk->sk_rmem_alloc) < READ_ONCE(sk->sk_rcvbuf) && - move_skbs_to_msk(msk, ssk)) + ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf); + sk_rbuf = READ_ONCE(sk->sk_rcvbuf); + if (unlikely(ssk_rbuf > sk_rbuf)) + sk_rbuf = ssk_rbuf; + + /* over limit? can't append more skbs to msk */ + if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf) goto wake; - /* don't schedule if mptcp sk is (still) over limit */ - if (atomic_read(&sk->sk_rmem_alloc) > READ_ONCE(sk->sk_rcvbuf)) + if (move_skbs_to_msk(msk, ssk)) goto wake; /* mptcp socket is owned, release_cb should retry */ @@ -754,8 +771,11 @@ static bool mptcp_skb_can_collapse_to(u64 write_seq, if (!tcp_skb_can_collapse_to(skb)) return false; - /* can collapse only if MPTCP level sequence is in order */ - return mpext && mpext->data_seq + mpext->data_len == write_seq; + /* can collapse only if MPTCP level sequence is in order and this + * mapping has not been xmitted yet + */ + return mpext && mpext->data_seq + mpext->data_len == write_seq && + !mpext->frozen; } static bool mptcp_frag_can_collapse_to(const struct mptcp_sock *msk, @@ -833,19 +853,25 @@ static void mptcp_clean_una(struct sock *sk) } out: - if (cleaned) { + if (cleaned) sk_mem_reclaim_partial(sk); +} - /* Only wake up writers if a subflow is ready */ - if (mptcp_is_writeable(msk)) { - set_bit(MPTCP_SEND_SPACE, &mptcp_sk(sk)->flags); - smp_mb__after_atomic(); +static void mptcp_clean_una_wakeup(struct sock *sk) +{ + struct mptcp_sock *msk = mptcp_sk(sk); - /* set SEND_SPACE before sk_stream_write_space clears - * NOSPACE - */ - sk_stream_write_space(sk); - } + mptcp_clean_una(sk); + + /* Only wake up writers if a subflow is ready */ + if (mptcp_is_writeable(msk)) { + set_bit(MPTCP_SEND_SPACE, &msk->flags); + smp_mb__after_atomic(); + + /* set SEND_SPACE before sk_stream_write_space clears + * NOSPACE + */ + sk_stream_write_space(sk); } } @@ -1476,13 +1502,14 @@ static bool __mptcp_move_skbs(struct mptcp_sock *msk) __mptcp_flush_join_list(msk); do { struct sock *ssk = mptcp_subflow_recv_lookup(msk); + bool slowpath; if (!ssk) break; - lock_sock(ssk); + slowpath = lock_sock_fast(ssk); done = __mptcp_move_skbs_from_subflow(msk, ssk, &moved); - release_sock(ssk); + unlock_sock_fast(ssk, slowpath); } while (!done); if (mptcp_ofo_queue(msk) || moved > 0) { @@ -1748,7 +1775,7 @@ static void mptcp_worker(struct work_struct *work) long timeo = 0; lock_sock(sk); - mptcp_clean_una(sk); + mptcp_clean_una_wakeup(sk); mptcp_check_data_fin_ack(sk); __mptcp_flush_join_list(msk); if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 13ab89dc1914..278c88c405e8 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -362,6 +362,7 @@ mptcp_subflow_get_mapped_dsn(const struct mptcp_subflow_context *subflow) } int mptcp_is_enabled(struct net *net); +unsigned int mptcp_get_add_addr_timeout(struct net *net); void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow, struct mptcp_options_received *mp_opt); bool mptcp_subflow_data_available(struct sock *sk); diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 52370211e46b..49fbef0d99be 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -682,6 +682,16 @@ config NFT_FIB_NETDEV The lookup will be delegated to the IPv4 or IPv6 FIB depending on the protocol of the packet. +config NFT_REJECT_NETDEV + depends on NFT_REJECT_IPV4 + depends on NFT_REJECT_IPV6 + tristate "Netfilter nf_tables netdev REJECT support" + help + This option enables the REJECT support from the netdev table. + The return packet generation will be delegated to the IPv4 + or IPv6 ICMP or TCP RST implementation depending on the + protocol of the packet. + endif # NF_TABLES_NETDEV endif # NF_TABLES diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 0e0ded87e27b..33da7bf1b68e 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -101,6 +101,7 @@ obj-$(CONFIG_NFT_QUEUE) += nft_queue.o obj-$(CONFIG_NFT_QUOTA) += nft_quota.o obj-$(CONFIG_NFT_REJECT) += nft_reject.o obj-$(CONFIG_NFT_REJECT_INET) += nft_reject_inet.o +obj-$(CONFIG_NFT_REJECT_NETDEV) += nft_reject_netdev.o obj-$(CONFIG_NFT_TUNNEL) += nft_tunnel.o obj-$(CONFIG_NFT_COUNTER) += nft_counter.o obj-$(CONFIG_NFT_LOG) += nft_log.o diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 7cff6e5e7445..c7eaa3776238 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1110,6 +1110,8 @@ static int ip_set_create(struct net *net, struct sock *ctnl, ret = -IPSET_ERR_PROTOCOL; goto put_out; } + /* Set create flags depending on the type revision */ + set->flags |= set->type->create_flags[revision]; ret = set->type->create(net, set, tb, flags); if (ret != 0) @@ -1240,10 +1242,12 @@ static int ip_set_destroy(struct net *net, struct sock *ctnl, /* Modified by ip_set_destroy() only, which is serialized */ inst->is_destroyed = false; } else { + u32 flags = flag_exist(nlh); s = find_set_and_id(inst, nla_data(attr[IPSET_ATTR_SETNAME]), &i); if (!s) { - ret = -ENOENT; + if (!(flags & IPSET_FLAG_EXIST)) + ret = -ENOENT; goto out; } else if (s->ref || s->ref_netlink) { ret = -IPSET_ERR_BUSY; diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 521e970be402..5f1208ad049e 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -37,18 +37,18 @@ */ /* Number of elements to store in an initial array block */ -#define AHASH_INIT_SIZE 4 +#define AHASH_INIT_SIZE 2 /* Max number of elements to store in an array block */ -#define AHASH_MAX_SIZE (3 * AHASH_INIT_SIZE) +#define AHASH_MAX_SIZE (6 * AHASH_INIT_SIZE) /* Max muber of elements in the array block when tuned */ #define AHASH_MAX_TUNED 64 +#define AHASH_MAX(h) ((h)->bucketsize) + /* Max number of elements can be tuned */ #ifdef IP_SET_HASH_WITH_MULTI -#define AHASH_MAX(h) ((h)->ahash_max) - static u8 -tune_ahash_max(u8 curr, u32 multi) +tune_bucketsize(u8 curr, u32 multi) { u32 n; @@ -61,12 +61,10 @@ tune_ahash_max(u8 curr, u32 multi) */ return n > curr && n <= AHASH_MAX_TUNED ? n : curr; } - -#define TUNE_AHASH_MAX(h, multi) \ - ((h)->ahash_max = tune_ahash_max((h)->ahash_max, multi)) +#define TUNE_BUCKETSIZE(h, multi) \ + ((h)->bucketsize = tune_bucketsize((h)->bucketsize, multi)) #else -#define AHASH_MAX(h) AHASH_MAX_SIZE -#define TUNE_AHASH_MAX(h, multi) +#define TUNE_BUCKETSIZE(h, multi) #endif /* A hash bucket */ @@ -321,9 +319,7 @@ struct htype { #ifdef IP_SET_HASH_WITH_MARKMASK u32 markmask; /* markmask value for mark mask to store */ #endif -#ifdef IP_SET_HASH_WITH_MULTI - u8 ahash_max; /* max elements in an array block */ -#endif + u8 bucketsize; /* max elements in an array block */ #ifdef IP_SET_HASH_WITH_NETMASK u8 netmask; /* netmask value for subnets to store */ #endif @@ -950,7 +946,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, goto set_full; /* Create a new slot */ if (n->pos >= n->size) { - TUNE_AHASH_MAX(h, multi); + TUNE_BUCKETSIZE(h, multi); if (n->size >= AHASH_MAX(h)) { /* Trigger rehashing */ mtype_data_next(&h->next, d); @@ -1305,6 +1301,11 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) if (nla_put_u32(skb, IPSET_ATTR_MARKMASK, h->markmask)) goto nla_put_failure; #endif + if (set->flags & IPSET_CREATE_FLAG_BUCKETSIZE) { + if (nla_put_u8(skb, IPSET_ATTR_BUCKETSIZE, h->bucketsize) || + nla_put_net32(skb, IPSET_ATTR_INITVAL, htonl(h->initval))) + goto nla_put_failure; + } if (nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref)) || nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)) || nla_put_net32(skb, IPSET_ATTR_ELEMENTS, htonl(elements))) @@ -1547,8 +1548,20 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, #ifdef IP_SET_HASH_WITH_MARKMASK h->markmask = markmask; #endif - get_random_bytes(&h->initval, sizeof(h->initval)); - + if (tb[IPSET_ATTR_INITVAL]) + h->initval = ntohl(nla_get_be32(tb[IPSET_ATTR_INITVAL])); + else + get_random_bytes(&h->initval, sizeof(h->initval)); + h->bucketsize = AHASH_MAX_SIZE; + if (tb[IPSET_ATTR_BUCKETSIZE]) { + h->bucketsize = nla_get_u8(tb[IPSET_ATTR_BUCKETSIZE]); + if (h->bucketsize < AHASH_INIT_SIZE) + h->bucketsize = AHASH_INIT_SIZE; + else if (h->bucketsize > AHASH_MAX_SIZE) + h->bucketsize = AHASH_MAX_SIZE; + else if (h->bucketsize % 2) + h->bucketsize += 1; + } t->htable_bits = hbits; t->maxelem = h->maxelem / ahash_numof_locks(hbits); RCU_INIT_POINTER(h->table, t); diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c index 5d6d68eaf6a9..d1bef23fd4f5 100644 --- a/net/netfilter/ipset/ip_set_hash_ip.c +++ b/net/netfilter/ipset/ip_set_hash_ip.c @@ -23,7 +23,8 @@ /* 1 Counters support */ /* 2 Comments support */ /* 3 Forceadd support */ -#define IPSET_TYPE_REV_MAX 4 /* skbinfo support */ +/* 4 skbinfo support */ +#define IPSET_TYPE_REV_MAX 5 /* bucketsize, initval support */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>"); @@ -277,11 +278,13 @@ static struct ip_set_type hash_ip_type __read_mostly = { .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, + .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE, .create = hash_ip_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, - [IPSET_ATTR_PROBES] = { .type = NLA_U8 }, + [IPSET_ATTR_INITVAL] = { .type = NLA_U32 }, + [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_NETMASK] = { .type = NLA_U8 }, diff --git a/net/netfilter/ipset/ip_set_hash_ipmac.c b/net/netfilter/ipset/ip_set_hash_ipmac.c index eceb7bc4a93a..467c59a83c0a 100644 --- a/net/netfilter/ipset/ip_set_hash_ipmac.c +++ b/net/netfilter/ipset/ip_set_hash_ipmac.c @@ -23,7 +23,7 @@ #include <linux/netfilter/ipset/ip_set_hash.h> #define IPSET_TYPE_REV_MIN 0 -#define IPSET_TYPE_REV_MAX 0 +#define IPSET_TYPE_REV_MAX 1 /* bucketsize, initval support */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Tomasz Chilinski <tomasz.chilinski@chilan.com>"); @@ -268,11 +268,13 @@ static struct ip_set_type hash_ipmac_type __read_mostly = { .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, + .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE, .create = hash_ipmac_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, - [IPSET_ATTR_PROBES] = { .type = NLA_U8 }, + [IPSET_ATTR_INITVAL] = { .type = NLA_U32 }, + [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_ipmark.c b/net/netfilter/ipset/ip_set_hash_ipmark.c index aba1df617d6e..18346d18aa16 100644 --- a/net/netfilter/ipset/ip_set_hash_ipmark.c +++ b/net/netfilter/ipset/ip_set_hash_ipmark.c @@ -21,7 +21,8 @@ #define IPSET_TYPE_REV_MIN 0 /* 1 Forceadd support */ -#define IPSET_TYPE_REV_MAX 2 /* skbinfo support */ +/* 2 skbinfo support */ +#define IPSET_TYPE_REV_MAX 3 /* bucketsize, initval support */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Vytas Dauksa <vytas.dauksa@smoothwall.net>"); @@ -274,12 +275,14 @@ static struct ip_set_type hash_ipmark_type __read_mostly = { .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, + .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE, .create = hash_ipmark_create, .create_policy = { [IPSET_ATTR_MARKMASK] = { .type = NLA_U32 }, [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, - [IPSET_ATTR_PROBES] = { .type = NLA_U8 }, + [IPSET_ATTR_INITVAL] = { .type = NLA_U32 }, + [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c index 1ff228717e29..e1ca11196515 100644 --- a/net/netfilter/ipset/ip_set_hash_ipport.c +++ b/net/netfilter/ipset/ip_set_hash_ipport.c @@ -25,7 +25,8 @@ /* 2 Counters support added */ /* 3 Comments support added */ /* 4 Forceadd support added */ -#define IPSET_TYPE_REV_MAX 5 /* skbinfo support added */ +/* 5 skbinfo support added */ +#define IPSET_TYPE_REV_MAX 6 /* bucketsize, initval support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>"); @@ -341,11 +342,13 @@ static struct ip_set_type hash_ipport_type __read_mostly = { .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, + .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE, .create = hash_ipport_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, - [IPSET_ATTR_PROBES] = { .type = NLA_U8 }, + [IPSET_ATTR_INITVAL] = { .type = NLA_U32 }, + [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_PROTO] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c index fa88afd812fa..ab179e064597 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportip.c +++ b/net/netfilter/ipset/ip_set_hash_ipportip.c @@ -25,7 +25,8 @@ /* 2 Counters support added */ /* 3 Comments support added */ /* 4 Forceadd support added */ -#define IPSET_TYPE_REV_MAX 5 /* skbinfo support added */ +/* 5 skbinfo support added */ +#define IPSET_TYPE_REV_MAX 6 /* bucketsize, initval support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>"); @@ -356,11 +357,13 @@ static struct ip_set_type hash_ipportip_type __read_mostly = { .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, + .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE, .create = hash_ipportip_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, - [IPSET_ATTR_PROBES] = { .type = NLA_U8 }, + [IPSET_ATTR_INITVAL] = { .type = NLA_U32 }, + [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index eef6ecfcb409..8f075b44cf64 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -27,7 +27,8 @@ /* 4 Counters support added */ /* 5 Comments support added */ /* 6 Forceadd support added */ -#define IPSET_TYPE_REV_MAX 7 /* skbinfo support added */ +/* 7 skbinfo support added */ +#define IPSET_TYPE_REV_MAX 8 /* bucketsize, initval support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>"); @@ -513,11 +514,13 @@ static struct ip_set_type hash_ipportnet_type __read_mostly = { .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, + .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE, .create = hash_ipportnet_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, - [IPSET_ATTR_PROBES] = { .type = NLA_U8 }, + [IPSET_ATTR_INITVAL] = { .type = NLA_U32 }, + [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_mac.c b/net/netfilter/ipset/ip_set_hash_mac.c index 0b61593165ef..718814730acf 100644 --- a/net/netfilter/ipset/ip_set_hash_mac.c +++ b/net/netfilter/ipset/ip_set_hash_mac.c @@ -16,7 +16,7 @@ #include <linux/netfilter/ipset/ip_set_hash.h> #define IPSET_TYPE_REV_MIN 0 -#define IPSET_TYPE_REV_MAX 0 +#define IPSET_TYPE_REV_MAX 1 /* bucketsize, initval support */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>"); @@ -125,11 +125,13 @@ static struct ip_set_type hash_mac_type __read_mostly = { .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, + .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE, .create = hash_mac_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, - [IPSET_ATTR_PROBES] = { .type = NLA_U8 }, + [IPSET_ATTR_INITVAL] = { .type = NLA_U32 }, + [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index 136cf0781d3a..c1a11f041ac6 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -24,7 +24,8 @@ /* 3 Counters support added */ /* 4 Comments support added */ /* 5 Forceadd support added */ -#define IPSET_TYPE_REV_MAX 6 /* skbinfo mapping support added */ +/* 6 skbinfo support added */ +#define IPSET_TYPE_REV_MAX 7 /* bucketsize, initval support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>"); @@ -354,11 +355,13 @@ static struct ip_set_type hash_net_type __read_mostly = { .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, + .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE, .create = hash_net_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, - [IPSET_ATTR_PROBES] = { .type = NLA_U8 }, + [IPSET_ATTR_INITVAL] = { .type = NLA_U32 }, + [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index be5e95a0d876..3d74169b794c 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -26,7 +26,8 @@ /* 4 Comments support added */ /* 5 Forceadd support added */ /* 6 skbinfo support added */ -#define IPSET_TYPE_REV_MAX 7 /* interface wildcard support added */ +/* 7 interface wildcard support added */ +#define IPSET_TYPE_REV_MAX 8 /* bucketsize, initval support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>"); @@ -470,11 +471,13 @@ static struct ip_set_type hash_netiface_type __read_mostly = { .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, + .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE, .create = hash_netiface_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, - [IPSET_ATTR_PROBES] = { .type = NLA_U8 }, + [IPSET_ATTR_INITVAL] = { .type = NLA_U32 }, + [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_PROTO] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c index da4ef910b12d..6532f0505e66 100644 --- a/net/netfilter/ipset/ip_set_hash_netnet.c +++ b/net/netfilter/ipset/ip_set_hash_netnet.c @@ -22,7 +22,8 @@ #define IPSET_TYPE_REV_MIN 0 /* 1 Forceadd support added */ -#define IPSET_TYPE_REV_MAX 2 /* skbinfo support added */ +/* 2 skbinfo support added */ +#define IPSET_TYPE_REV_MAX 3 /* bucketsize, initval support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Oliver Smith <oliver@8.c.9.b.0.7.4.0.1.0.0.2.ip6.arpa>"); @@ -459,11 +460,13 @@ static struct ip_set_type hash_netnet_type __read_mostly = { .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, + .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE, .create = hash_netnet_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, - [IPSET_ATTR_PROBES] = { .type = NLA_U8 }, + [IPSET_ATTR_INITVAL] = { .type = NLA_U32 }, + [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index 34448df80fb9..ec1564a1cb5a 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -26,7 +26,8 @@ /* 4 Counters support added */ /* 5 Comments support added */ /* 6 Forceadd support added */ -#define IPSET_TYPE_REV_MAX 7 /* skbinfo support added */ +/* 7 skbinfo support added */ +#define IPSET_TYPE_REV_MAX 8 /* bucketsize, initval support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>"); @@ -460,11 +461,13 @@ static struct ip_set_type hash_netport_type __read_mostly = { .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, + .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE, .create = hash_netport_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, - [IPSET_ATTR_PROBES] = { .type = NLA_U8 }, + [IPSET_ATTR_INITVAL] = { .type = NLA_U32 }, + [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_PROTO] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c index 934c1712cba8..0e91d1e82f1c 100644 --- a/net/netfilter/ipset/ip_set_hash_netportnet.c +++ b/net/netfilter/ipset/ip_set_hash_netportnet.c @@ -23,7 +23,8 @@ #define IPSET_TYPE_REV_MIN 0 /* 0 Comments support added */ /* 1 Forceadd support added */ -#define IPSET_TYPE_REV_MAX 2 /* skbinfo support added */ +/* 2 skbinfo support added */ +#define IPSET_TYPE_REV_MAX 3 /* bucketsize, initval support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Oliver Smith <oliver@8.c.9.b.0.7.4.0.1.0.0.2.ip6.arpa>"); @@ -558,11 +559,13 @@ static struct ip_set_type hash_netportnet_type __read_mostly = { .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, + .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE, .create = hash_netportnet_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, - [IPSET_ATTR_PROBES] = { .type = NLA_U8 }, + [IPSET_ATTR_INITVAL] = { .type = NLA_U32 }, + [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 0f58e98542be..bd0e12bf5770 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -581,7 +581,8 @@ struct nft_module_request { }; #ifdef CONFIG_MODULES -static int nft_request_module(struct net *net, const char *fmt, ...) +static __printf(2, 3) int nft_request_module(struct net *net, const char *fmt, + ...) { char module_name[MODULE_NAME_LEN]; struct nft_module_request *req; diff --git a/net/netfilter/nft_reject.c b/net/netfilter/nft_reject.c index 61fb7e8afbf0..927ff8459bd9 100644 --- a/net/netfilter/nft_reject.c +++ b/net/netfilter/nft_reject.c @@ -40,6 +40,7 @@ int nft_reject_init(const struct nft_ctx *ctx, const struct nlattr * const tb[]) { struct nft_reject *priv = nft_expr_priv(expr); + int icmp_code; if (tb[NFTA_REJECT_TYPE] == NULL) return -EINVAL; @@ -47,9 +48,17 @@ int nft_reject_init(const struct nft_ctx *ctx, priv->type = ntohl(nla_get_be32(tb[NFTA_REJECT_TYPE])); switch (priv->type) { case NFT_REJECT_ICMP_UNREACH: + case NFT_REJECT_ICMPX_UNREACH: if (tb[NFTA_REJECT_ICMP_CODE] == NULL) return -EINVAL; - priv->icmp_code = nla_get_u8(tb[NFTA_REJECT_ICMP_CODE]); + + icmp_code = nla_get_u8(tb[NFTA_REJECT_ICMP_CODE]); + if (priv->type == NFT_REJECT_ICMPX_UNREACH && + icmp_code > NFT_REJECT_ICMPX_MAX) + return -EINVAL; + + priv->icmp_code = icmp_code; + break; case NFT_REJECT_TCP_RST: break; default: @@ -69,6 +78,7 @@ int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr) switch (priv->type) { case NFT_REJECT_ICMP_UNREACH: + case NFT_REJECT_ICMPX_UNREACH: if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code)) goto nla_put_failure; break; diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c index cf8f2646e93c..32f3ea398ddf 100644 --- a/net/netfilter/nft_reject_inet.c +++ b/net/netfilter/nft_reject_inet.c @@ -58,60 +58,16 @@ static void nft_reject_inet_eval(const struct nft_expr *expr, regs->verdict.code = NF_DROP; } -static int nft_reject_inet_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) +static int nft_reject_inet_validate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nft_data **data) { - struct nft_reject *priv = nft_expr_priv(expr); - int icmp_code; - - if (tb[NFTA_REJECT_TYPE] == NULL) - return -EINVAL; - - priv->type = ntohl(nla_get_be32(tb[NFTA_REJECT_TYPE])); - switch (priv->type) { - case NFT_REJECT_ICMP_UNREACH: - case NFT_REJECT_ICMPX_UNREACH: - if (tb[NFTA_REJECT_ICMP_CODE] == NULL) - return -EINVAL; - - icmp_code = nla_get_u8(tb[NFTA_REJECT_ICMP_CODE]); - if (priv->type == NFT_REJECT_ICMPX_UNREACH && - icmp_code > NFT_REJECT_ICMPX_MAX) - return -EINVAL; - - priv->icmp_code = icmp_code; - break; - case NFT_REJECT_TCP_RST: - break; - default: - return -EINVAL; - } - return 0; -} - -static int nft_reject_inet_dump(struct sk_buff *skb, - const struct nft_expr *expr) -{ - const struct nft_reject *priv = nft_expr_priv(expr); - - if (nla_put_be32(skb, NFTA_REJECT_TYPE, htonl(priv->type))) - goto nla_put_failure; - - switch (priv->type) { - case NFT_REJECT_ICMP_UNREACH: - case NFT_REJECT_ICMPX_UNREACH: - if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code)) - goto nla_put_failure; - break; - default: - break; - } - - return 0; - -nla_put_failure: - return -1; + return nft_chain_validate_hooks(ctx->chain, + (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_FORWARD) | + (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_INGRESS)); } static struct nft_expr_type nft_reject_inet_type; @@ -119,9 +75,9 @@ static const struct nft_expr_ops nft_reject_inet_ops = { .type = &nft_reject_inet_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_reject)), .eval = nft_reject_inet_eval, - .init = nft_reject_inet_init, - .dump = nft_reject_inet_dump, - .validate = nft_reject_validate, + .init = nft_reject_init, + .dump = nft_reject_dump, + .validate = nft_reject_inet_validate, }; static struct nft_expr_type nft_reject_inet_type __read_mostly = { diff --git a/net/netfilter/nft_reject_netdev.c b/net/netfilter/nft_reject_netdev.c new file mode 100644 index 000000000000..d89f68754f42 --- /dev/null +++ b/net/netfilter/nft_reject_netdev.c @@ -0,0 +1,189 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2020 Laura Garcia Liebana <nevola@gmail.com> + * Copyright (c) 2020 Jose M. Guisado <guigom@riseup.net> + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables.h> +#include <net/netfilter/nft_reject.h> +#include <net/netfilter/ipv4/nf_reject.h> +#include <net/netfilter/ipv6/nf_reject.h> + +static void nft_reject_queue_xmit(struct sk_buff *nskb, struct sk_buff *oldskb) +{ + dev_hard_header(nskb, nskb->dev, ntohs(oldskb->protocol), + eth_hdr(oldskb)->h_source, eth_hdr(oldskb)->h_dest, + nskb->len); + dev_queue_xmit(nskb); +} + +static void nft_reject_netdev_send_v4_tcp_reset(struct net *net, + struct sk_buff *oldskb, + const struct net_device *dev, + int hook) +{ + struct sk_buff *nskb; + + nskb = nf_reject_skb_v4_tcp_reset(net, oldskb, dev, hook); + if (!nskb) + return; + + nft_reject_queue_xmit(nskb, oldskb); +} + +static void nft_reject_netdev_send_v4_unreach(struct net *net, + struct sk_buff *oldskb, + const struct net_device *dev, + int hook, u8 code) +{ + struct sk_buff *nskb; + + nskb = nf_reject_skb_v4_unreach(net, oldskb, dev, hook, code); + if (!nskb) + return; + + nft_reject_queue_xmit(nskb, oldskb); +} + +static void nft_reject_netdev_send_v6_tcp_reset(struct net *net, + struct sk_buff *oldskb, + const struct net_device *dev, + int hook) +{ + struct sk_buff *nskb; + + nskb = nf_reject_skb_v6_tcp_reset(net, oldskb, dev, hook); + if (!nskb) + return; + + nft_reject_queue_xmit(nskb, oldskb); +} + + +static void nft_reject_netdev_send_v6_unreach(struct net *net, + struct sk_buff *oldskb, + const struct net_device *dev, + int hook, u8 code) +{ + struct sk_buff *nskb; + + nskb = nf_reject_skb_v6_unreach(net, oldskb, dev, hook, code); + if (!nskb) + return; + + nft_reject_queue_xmit(nskb, oldskb); +} + +static void nft_reject_netdev_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct ethhdr *eth = eth_hdr(pkt->skb); + struct nft_reject *priv = nft_expr_priv(expr); + const unsigned char *dest = eth->h_dest; + + if (is_broadcast_ether_addr(dest) || + is_multicast_ether_addr(dest)) + goto out; + + switch (eth->h_proto) { + case htons(ETH_P_IP): + switch (priv->type) { + case NFT_REJECT_ICMP_UNREACH: + nft_reject_netdev_send_v4_unreach(nft_net(pkt), pkt->skb, + nft_in(pkt), + nft_hook(pkt), + priv->icmp_code); + break; + case NFT_REJECT_TCP_RST: + nft_reject_netdev_send_v4_tcp_reset(nft_net(pkt), pkt->skb, + nft_in(pkt), + nft_hook(pkt)); + break; + case NFT_REJECT_ICMPX_UNREACH: + nft_reject_netdev_send_v4_unreach(nft_net(pkt), pkt->skb, + nft_in(pkt), + nft_hook(pkt), + nft_reject_icmp_code(priv->icmp_code)); + break; + } + break; + case htons(ETH_P_IPV6): + switch (priv->type) { + case NFT_REJECT_ICMP_UNREACH: + nft_reject_netdev_send_v6_unreach(nft_net(pkt), pkt->skb, + nft_in(pkt), + nft_hook(pkt), + priv->icmp_code); + break; + case NFT_REJECT_TCP_RST: + nft_reject_netdev_send_v6_tcp_reset(nft_net(pkt), pkt->skb, + nft_in(pkt), + nft_hook(pkt)); + break; + case NFT_REJECT_ICMPX_UNREACH: + nft_reject_netdev_send_v6_unreach(nft_net(pkt), pkt->skb, + nft_in(pkt), + nft_hook(pkt), + nft_reject_icmpv6_code(priv->icmp_code)); + break; + } + break; + default: + /* No explicit way to reject this protocol, drop it. */ + break; + } +out: + regs->verdict.code = NF_DROP; +} + +static int nft_reject_netdev_validate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nft_data **data) +{ + return nft_chain_validate_hooks(ctx->chain, (1 << NF_NETDEV_INGRESS)); +} + +static struct nft_expr_type nft_reject_netdev_type; +static const struct nft_expr_ops nft_reject_netdev_ops = { + .type = &nft_reject_netdev_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_reject)), + .eval = nft_reject_netdev_eval, + .init = nft_reject_init, + .dump = nft_reject_dump, + .validate = nft_reject_netdev_validate, +}; + +static struct nft_expr_type nft_reject_netdev_type __read_mostly = { + .family = NFPROTO_NETDEV, + .name = "reject", + .ops = &nft_reject_netdev_ops, + .policy = nft_reject_policy, + .maxattr = NFTA_REJECT_MAX, + .owner = THIS_MODULE, +}; + +static int __init nft_reject_netdev_module_init(void) +{ + return nft_register_expr(&nft_reject_netdev_type); +} + +static void __exit nft_reject_netdev_module_exit(void) +{ + nft_unregister_expr(&nft_reject_netdev_type); +} + +module_init(nft_reject_netdev_module_init); +module_exit(nft_reject_netdev_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Laura Garcia Liebana <nevola@gmail.com>"); +MODULE_AUTHOR("Jose M. Guisado <guigom@riseup.net>"); +MODULE_DESCRIPTION("Reject packets from netdev via nftables"); +MODULE_ALIAS_NFT_AF_EXPR(5, "reject"); diff --git a/net/netlabel/netlabel_calipso.c b/net/netlabel/netlabel_calipso.c index 4e62f2ad3575..f28c8947c730 100644 --- a/net/netlabel/netlabel_calipso.c +++ b/net/netlabel/netlabel_calipso.c @@ -366,6 +366,7 @@ static const struct netlbl_calipso_ops *calipso_ops; /** * netlbl_calipso_ops_register - Register the CALIPSO operations + * @ops: ops to register * * Description: * Register the CALIPSO packet engine operations. diff --git a/net/nfc/core.c b/net/nfc/core.c index eb377f87bcae..573c80c6ff7a 100644 --- a/net/nfc/core.c +++ b/net/nfc/core.c @@ -189,7 +189,8 @@ static const struct rfkill_ops nfc_rfkill_ops = { * nfc_start_poll - start polling for nfc targets * * @dev: The nfc device that must start polling - * @protocols: bitset of nfc protocols that must be used for polling + * @im_protocols: bitset of nfc initiator protocols to be used for polling + * @tm_protocols: bitset of nfc transport protocols to be used for polling * * The device remains polling for targets until a target is found or * the nfc_stop_poll function is called. @@ -436,6 +437,7 @@ error: * * @dev: The nfc device that found the target * @target_idx: index of the target that must be deactivated + * @mode: idle or sleep? */ int nfc_deactivate_target(struct nfc_dev *dev, u32 target_idx, u8 mode) { @@ -703,7 +705,11 @@ EXPORT_SYMBOL(nfc_tm_deactivated); /** * nfc_alloc_send_skb - allocate a skb for data exchange responses * + * @dev: device sending the response + * @sk: socket sending the response + * @flags: MSG_DONTWAIT flag * @size: size to allocate + * @err: pointer to memory to store the error code */ struct sk_buff *nfc_alloc_send_skb(struct nfc_dev *dev, struct sock *sk, unsigned int flags, unsigned int size, @@ -1039,6 +1045,8 @@ struct nfc_dev *nfc_get_device(unsigned int idx) * * @ops: device operations * @supported_protocols: NFC protocols supported by the device + * @tx_headroom: reserved space at beginning of skb + * @tx_tailroom: reserved space at end of skb */ struct nfc_dev *nfc_allocate_device(struct nfc_ops *ops, u32 supported_protocols, diff --git a/net/nfc/digital_core.c b/net/nfc/digital_core.c index e3599ed4a7a8..da7e2112771f 100644 --- a/net/nfc/digital_core.c +++ b/net/nfc/digital_core.c @@ -458,6 +458,9 @@ static void digital_add_poll_tech(struct nfc_digital_dev *ddev, u8 rf_tech, /** * start_poll operation + * @nfc_dev: device to be polled + * @im_protocols: bitset of nfc initiator protocols to be used for polling + * @tm_protocols: bitset of nfc transport protocols to be used for polling * * For every supported protocol, the corresponding polling function is added * to the table of polling technologies (ddev->poll_techs[]) using diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 741da8f81c2b..4953ee5146e1 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -1112,6 +1112,8 @@ static struct nfc_ops nci_nfc_ops = { * * @ops: device operations * @supported_protocols: NFC protocols supported by the device + * @tx_headroom: Reserved space at beginning of skb + * @tx_tailroom: Reserved space at end of skb */ struct nci_dev *nci_allocate_device(struct nci_ops *ops, __u32 supported_protocols, diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index b03d142ec82e..c7f34d6a9934 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -294,6 +294,10 @@ static bool icmp6hdr_ok(struct sk_buff *skb) /** * Parse vlan tag from vlan header. + * @skb: skb containing frame to parse + * @key_vh: pointer to parsed vlan tag + * @untag_vlan: should the vlan header be removed from the frame + * * Returns ERROR on memory error. * Returns 0 if it encounters a non-vlan or incomplete packet. * Returns 1 after successfully parsing vlan tag. diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c index 8fbefd52af7f..15424d26e85d 100644 --- a/net/openvswitch/meter.c +++ b/net/openvswitch/meter.c @@ -423,7 +423,7 @@ static int ovs_meter_cmd_set(struct sk_buff *skb, struct genl_info *info) return -EINVAL; meter = dp_meter_create(a); - if (IS_ERR_OR_NULL(meter)) + if (IS_ERR(meter)) return PTR_ERR(meter); reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_SET, diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 82d801f063b7..4ed7e52c7012 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -111,10 +111,12 @@ struct vport *ovs_vport_locate(const struct net *net, const char *name) * * @priv_size: Size of private data area to allocate. * @ops: vport device ops + * @parms: information about new vport. * * Allocate and initialize a new vport defined by @ops. The vport will contain * a private data area of size @priv_size that can be accessed using - * vport_priv(). vports that are no longer needed should be released with + * vport_priv(). Some parameters of the vport will be initialized from @parms. + * @vports that are no longer needed should be released with * vport_free(). */ struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops, diff --git a/net/sched/act_api.c b/net/sched/act_api.c index f66417d5d2c3..1341c59c2f40 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -215,6 +215,36 @@ static size_t tcf_action_fill_size(const struct tc_action *act) return sz; } +static int +tcf_action_dump_terse(struct sk_buff *skb, struct tc_action *a, bool from_act) +{ + unsigned char *b = skb_tail_pointer(skb); + struct tc_cookie *cookie; + + if (nla_put_string(skb, TCA_KIND, a->ops->kind)) + goto nla_put_failure; + if (tcf_action_copy_stats(skb, a, 0)) + goto nla_put_failure; + if (from_act && nla_put_u32(skb, TCA_ACT_INDEX, a->tcfa_index)) + goto nla_put_failure; + + rcu_read_lock(); + cookie = rcu_dereference(a->act_cookie); + if (cookie) { + if (nla_put(skb, TCA_ACT_COOKIE, cookie->len, cookie->data)) { + rcu_read_unlock(); + goto nla_put_failure; + } + } + rcu_read_unlock(); + + return 0; + +nla_put_failure: + nlmsg_trim(skb, b); + return -1; +} + static int tcf_dump_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, struct netlink_callback *cb) { @@ -248,7 +278,9 @@ static int tcf_dump_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, index--; goto nla_put_failure; } - err = tcf_action_dump_1(skb, p, 0, 0); + err = (act_flags & TCA_FLAG_TERSE_DUMP) ? + tcf_action_dump_terse(skb, p, true) : + tcf_action_dump_1(skb, p, 0, 0); if (err < 0) { index--; nlmsg_trim(skb, nest); @@ -752,34 +784,6 @@ tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int bind, int ref) return a->ops->dump(skb, a, bind, ref); } -static int -tcf_action_dump_terse(struct sk_buff *skb, struct tc_action *a) -{ - unsigned char *b = skb_tail_pointer(skb); - struct tc_cookie *cookie; - - if (nla_put_string(skb, TCA_KIND, a->ops->kind)) - goto nla_put_failure; - if (tcf_action_copy_stats(skb, a, 0)) - goto nla_put_failure; - - rcu_read_lock(); - cookie = rcu_dereference(a->act_cookie); - if (cookie) { - if (nla_put(skb, TCA_ACT_COOKIE, cookie->len, cookie->data)) { - rcu_read_unlock(); - goto nla_put_failure; - } - } - rcu_read_unlock(); - - return 0; - -nla_put_failure: - nlmsg_trim(skb, b); - return -1; -} - int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { @@ -787,7 +791,7 @@ tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref) unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; - if (tcf_action_dump_terse(skb, a)) + if (tcf_action_dump_terse(skb, a, false)) goto nla_put_failure; if (a->hw_stats != TCA_ACT_HW_STATS_ANY && @@ -832,7 +836,7 @@ int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[], nest = nla_nest_start_noflag(skb, i + 1); if (nest == NULL) goto nla_put_failure; - err = terse ? tcf_action_dump_terse(skb, a) : + err = terse ? tcf_action_dump_terse(skb, a, false) : tcf_action_dump_1(skb, a, bind, ref); if (err < 0) goto errout; @@ -1469,7 +1473,8 @@ static int tcf_action_add(struct net *net, struct nlattr *nla, } static const struct nla_policy tcaa_policy[TCA_ROOT_MAX + 1] = { - [TCA_ROOT_FLAGS] = NLA_POLICY_BITFIELD32(TCA_FLAG_LARGE_DUMP_ON), + [TCA_ROOT_FLAGS] = NLA_POLICY_BITFIELD32(TCA_FLAG_LARGE_DUMP_ON | + TCA_FLAG_TERSE_DUMP), [TCA_ROOT_TIME_DELTA] = { .type = NLA_U32 }, }; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 838b3fd94d77..ba0715ee9eac 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -2940,7 +2940,6 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb) struct tcf_chain *chain; long index_start; long index; - u32 parent; int err; if (nlmsg_len(cb->nlh) < sizeof(*tcm)) @@ -2955,13 +2954,6 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb) block = tcf_block_refcnt_get(net, tcm->tcm_block_index); if (!block) goto out; - /* If we work with block index, q is NULL and parent value - * will never be used in the following code. The check - * in tcf_fill_node prevents it. However, compiler does not - * see that far, so set parent to zero to silence the warning - * about parent being uninitialized. - */ - parent = 0; } else { const struct Qdisc_class_ops *cops; struct net_device *dev; @@ -2971,13 +2963,11 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb) if (!dev) return skb->len; - parent = tcm->tcm_parent; - if (!parent) { + if (!tcm->tcm_parent) q = dev->qdisc; - parent = q->handle; - } else { + else q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent)); - } + if (!q) goto out; cops = q->ops->cl_ops; diff --git a/net/sctp/Kconfig b/net/sctp/Kconfig index 39d7fa9569f8..5da599ff84a9 100644 --- a/net/sctp/Kconfig +++ b/net/sctp/Kconfig @@ -11,6 +11,7 @@ menuconfig IP_SCTP select CRYPTO_HMAC select CRYPTO_SHA1 select LIBCRC32C + select NET_UDP_TUNNEL help Stream Control Transmission Protocol diff --git a/net/sctp/associola.c b/net/sctp/associola.c index fdb69d46276d..336df4b36655 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -99,6 +99,8 @@ static struct sctp_association *sctp_association_init( */ asoc->hbinterval = msecs_to_jiffies(sp->hbinterval); + asoc->encap_port = sp->encap_port; + /* Initialize path max retrans value. */ asoc->pathmaxrxt = sp->pathmaxrxt; @@ -624,6 +626,8 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc, */ peer->hbinterval = asoc->hbinterval; + peer->encap_port = asoc->encap_port; + /* Set the path max_retrans. */ peer->pathmaxrxt = asoc->pathmaxrxt; diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 8a58f42d6d19..c3e89c776e66 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -55,6 +55,7 @@ #include <net/inet_common.h> #include <net/inet_ecn.h> #include <net/sctp/sctp.h> +#include <net/udp_tunnel.h> #include <linux/uaccess.h> @@ -191,33 +192,53 @@ out: return ret; } -static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport) +static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *t) { + struct dst_entry *dst = dst_clone(t->dst); + struct flowi6 *fl6 = &t->fl.u.ip6; struct sock *sk = skb->sk; struct ipv6_pinfo *np = inet6_sk(sk); - struct flowi6 *fl6 = &transport->fl.u.ip6; __u8 tclass = np->tclass; - int res; + __be32 label; pr_debug("%s: skb:%p, len:%d, src:%pI6 dst:%pI6\n", __func__, skb, skb->len, &fl6->saddr, &fl6->daddr); - if (transport->dscp & SCTP_DSCP_SET_MASK) - tclass = transport->dscp & SCTP_DSCP_VAL_MASK; + if (t->dscp & SCTP_DSCP_SET_MASK) + tclass = t->dscp & SCTP_DSCP_VAL_MASK; if (INET_ECN_is_capable(tclass)) IP6_ECN_flow_xmit(sk, fl6->flowlabel); - if (!(transport->param_flags & SPP_PMTUD_ENABLE)) + if (!(t->param_flags & SPP_PMTUD_ENABLE)) skb->ignore_df = 1; SCTP_INC_STATS(sock_net(sk), SCTP_MIB_OUTSCTPPACKS); - rcu_read_lock(); - res = ip6_xmit(sk, skb, fl6, sk->sk_mark, rcu_dereference(np->opt), - tclass, sk->sk_priority); - rcu_read_unlock(); - return res; + if (!t->encap_port || !sctp_sk(sk)->udp_port) { + int res; + + skb_dst_set(skb, dst); + rcu_read_lock(); + res = ip6_xmit(sk, skb, fl6, sk->sk_mark, + rcu_dereference(np->opt), + tclass, sk->sk_priority); + rcu_read_unlock(); + return res; + } + + if (skb_is_gso(skb)) + skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM; + + skb->encapsulation = 1; + skb_reset_inner_mac_header(skb); + skb_reset_inner_transport_header(skb); + skb_set_inner_ipproto(skb, IPPROTO_SCTP); + label = ip6_make_flowlabel(sock_net(sk), skb, fl6->flowlabel, true, fl6); + + return udp_tunnel6_xmit_skb(dst, sk, skb, NULL, &fl6->saddr, + &fl6->daddr, tclass, ip6_dst_hoplimit(dst), + label, sctp_sk(sk)->udp_port, t->encap_port, false); } /* Returns the dst cache entry for the given source and destination ip @@ -1053,6 +1074,7 @@ static struct inet_protosw sctpv6_stream_protosw = { static int sctp6_rcv(struct sk_buff *skb) { + SCTP_INPUT_CB(skb)->encap_port = 0; return sctp_rcv(skb) ? -1 : 0; } diff --git a/net/sctp/offload.c b/net/sctp/offload.c index 74847d613835..ce281a9a2875 100644 --- a/net/sctp/offload.c +++ b/net/sctp/offload.c @@ -27,7 +27,11 @@ 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); + /* csum and csum_start in GSO CB may be needed to do the UDP + * checksum when it's a UDP tunneling packet. + */ + SKB_GSO_CB(skb)->csum = (__force __wsum)~0; + SKB_GSO_CB(skb)->csum_start = skb_headroom(skb) + skb->len; return sctp_compute_cksum(skb, skb_transport_offset(skb)); } diff --git a/net/sctp/output.c b/net/sctp/output.c index 1441eaf460bb..6614c9fdc51e 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -508,20 +508,14 @@ merge: sizeof(struct inet6_skb_parm))); skb_shinfo(head)->gso_segs = pkt_count; skb_shinfo(head)->gso_size = GSO_BY_FRAGS; - rcu_read_lock(); - if (skb_dst(head) != tp->dst) { - dst_hold(tp->dst); - sk_setup_caps(sk, tp->dst); - } - rcu_read_unlock(); goto chksum; } if (sctp_checksum_disable) return 1; - if (!(skb_dst(head)->dev->features & NETIF_F_SCTP_CRC) || - dst_xfrm(skb_dst(head)) || packet->ipfragok) { + if (!(tp->dst->dev->features & NETIF_F_SCTP_CRC) || + dst_xfrm(tp->dst) || packet->ipfragok || tp->encap_port) { struct sctphdr *sh = (struct sctphdr *)skb_transport_header(head); @@ -548,7 +542,6 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) struct sctp_association *asoc = tp->asoc; struct sctp_chunk *chunk, *tmp; int pkt_count, gso = 0; - struct dst_entry *dst; struct sk_buff *head; struct sctphdr *sh; struct sock *sk; @@ -585,13 +578,18 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp) sh->checksum = 0; /* drop packet if no dst */ - dst = dst_clone(tp->dst); - if (!dst) { + if (!tp->dst) { IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); kfree_skb(head); goto out; } - skb_dst_set(head, dst); + + rcu_read_lock(); + if (__sk_dst_get(sk) != tp->dst) { + dst_hold(tp->dst); + sk_setup_caps(sk, tp->dst); + } + rcu_read_unlock(); /* pack up chunks */ pkt_count = sctp_packet_pack(packet, head, gso, gfp); diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 25833238fe93..6f2bbfeec3a4 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -44,6 +44,7 @@ #include <net/addrconf.h> #include <net/inet_common.h> #include <net/inet_ecn.h> +#include <net/udp_tunnel.h> #define MAX_SCTP_PORT_HASH_ENTRIES (64 * 1024) @@ -840,6 +841,92 @@ static int sctp_ctl_sock_init(struct net *net) return 0; } +static int sctp_udp_rcv(struct sock *sk, struct sk_buff *skb) +{ + SCTP_INPUT_CB(skb)->encap_port = udp_hdr(skb)->source; + + skb_set_transport_header(skb, sizeof(struct udphdr)); + sctp_rcv(skb); + return 0; +} + +static int sctp_udp_err_lookup(struct sock *sk, struct sk_buff *skb) +{ + struct sctp_association *asoc; + struct sctp_transport *t; + int family; + + skb->transport_header += sizeof(struct udphdr); + family = (ip_hdr(skb)->version == 4) ? AF_INET : AF_INET6; + sk = sctp_err_lookup(dev_net(skb->dev), family, skb, sctp_hdr(skb), + &asoc, &t); + if (!sk) + return -ENOENT; + + sctp_err_finish(sk, t); + return 0; +} + +int sctp_udp_sock_start(struct net *net) +{ + struct udp_tunnel_sock_cfg tuncfg = {NULL}; + struct udp_port_cfg udp_conf = {0}; + struct socket *sock; + int err; + + udp_conf.family = AF_INET; + udp_conf.local_ip.s_addr = htonl(INADDR_ANY); + udp_conf.local_udp_port = htons(net->sctp.udp_port); + err = udp_sock_create(net, &udp_conf, &sock); + if (err) { + pr_err("Failed to create the SCTP UDP tunneling v4 sock\n"); + return err; + } + + tuncfg.encap_type = 1; + tuncfg.encap_rcv = sctp_udp_rcv; + tuncfg.encap_err_lookup = sctp_udp_err_lookup; + setup_udp_tunnel_sock(net, sock, &tuncfg); + net->sctp.udp4_sock = sock->sk; + +#if IS_ENABLED(CONFIG_IPV6) + memset(&udp_conf, 0, sizeof(udp_conf)); + + udp_conf.family = AF_INET6; + udp_conf.local_ip6 = in6addr_any; + udp_conf.local_udp_port = htons(net->sctp.udp_port); + udp_conf.use_udp6_rx_checksums = true; + udp_conf.ipv6_v6only = true; + err = udp_sock_create(net, &udp_conf, &sock); + if (err) { + pr_err("Failed to create the SCTP UDP tunneling v6 sock\n"); + udp_tunnel_sock_release(net->sctp.udp4_sock->sk_socket); + net->sctp.udp4_sock = NULL; + return err; + } + + tuncfg.encap_type = 1; + tuncfg.encap_rcv = sctp_udp_rcv; + tuncfg.encap_err_lookup = sctp_udp_err_lookup; + setup_udp_tunnel_sock(net, sock, &tuncfg); + net->sctp.udp6_sock = sock->sk; +#endif + + return 0; +} + +void sctp_udp_sock_stop(struct net *net) +{ + if (net->sctp.udp4_sock) { + udp_tunnel_sock_release(net->sctp.udp4_sock->sk_socket); + net->sctp.udp4_sock = NULL; + } + if (net->sctp.udp6_sock) { + udp_tunnel_sock_release(net->sctp.udp6_sock->sk_socket); + net->sctp.udp6_sock = NULL; + } +} + /* Register address family specific functions. */ int sctp_register_af(struct sctp_af *af) { @@ -971,25 +1058,44 @@ static int sctp_inet_supported_addrs(const struct sctp_sock *opt, } /* Wrapper routine that calls the ip transmit routine. */ -static inline int sctp_v4_xmit(struct sk_buff *skb, - struct sctp_transport *transport) +static inline int sctp_v4_xmit(struct sk_buff *skb, struct sctp_transport *t) { - struct inet_sock *inet = inet_sk(skb->sk); + struct dst_entry *dst = dst_clone(t->dst); + struct flowi4 *fl4 = &t->fl.u.ip4; + struct sock *sk = skb->sk; + struct inet_sock *inet = inet_sk(sk); __u8 dscp = inet->tos; + __be16 df = 0; pr_debug("%s: skb:%p, len:%d, src:%pI4, dst:%pI4\n", __func__, skb, - skb->len, &transport->fl.u.ip4.saddr, - &transport->fl.u.ip4.daddr); + skb->len, &fl4->saddr, &fl4->daddr); - if (transport->dscp & SCTP_DSCP_SET_MASK) - dscp = transport->dscp & SCTP_DSCP_VAL_MASK; + if (t->dscp & SCTP_DSCP_SET_MASK) + dscp = t->dscp & SCTP_DSCP_VAL_MASK; + + inet->pmtudisc = t->param_flags & SPP_PMTUD_ENABLE ? IP_PMTUDISC_DO + : IP_PMTUDISC_DONT; + SCTP_INC_STATS(sock_net(sk), SCTP_MIB_OUTSCTPPACKS); - inet->pmtudisc = transport->param_flags & SPP_PMTUD_ENABLE ? - IP_PMTUDISC_DO : IP_PMTUDISC_DONT; + if (!t->encap_port || !sctp_sk(sk)->udp_port) { + skb_dst_set(skb, dst); + return __ip_queue_xmit(sk, skb, &t->fl, dscp); + } - SCTP_INC_STATS(sock_net(&inet->sk), SCTP_MIB_OUTSCTPPACKS); + if (skb_is_gso(skb)) + skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM; - return __ip_queue_xmit(&inet->sk, skb, &transport->fl, dscp); + if (ip_dont_fragment(sk, dst) && !skb->ignore_df) + df = htons(IP_DF); + + skb->encapsulation = 1; + skb_reset_inner_mac_header(skb); + skb_reset_inner_transport_header(skb); + skb_set_inner_ipproto(skb, IPPROTO_SCTP); + udp_tunnel_xmit_skb((struct rtable *)dst, sk, skb, fl4->saddr, + fl4->daddr, dscp, ip4_dst_hoplimit(dst), df, + sctp_sk(sk)->udp_port, t->encap_port, false, false); + return 0; } static struct sctp_af sctp_af_inet; @@ -1054,9 +1160,15 @@ static struct inet_protosw sctp_stream_protosw = { .flags = SCTP_PROTOSW_FLAG }; +static int sctp4_rcv(struct sk_buff *skb) +{ + SCTP_INPUT_CB(skb)->encap_port = 0; + return sctp_rcv(skb); +} + /* Register with IP layer. */ static const struct net_protocol sctp_protocol = { - .handler = sctp_rcv, + .handler = sctp4_rcv, .err_handler = sctp_v4_err, .no_policy = 1, .netns_ok = 1, @@ -1271,6 +1383,12 @@ static int __net_init sctp_defaults_init(struct net *net) /* Enable ECN by default. */ net->sctp.ecn_enable = 1; + /* Set UDP tunneling listening port to 0 by default */ + net->sctp.udp_port = 0; + + /* Set remote encap port to 0 by default */ + net->sctp.encap_port = 0; + /* Set SCOPE policy to enabled */ net->sctp.scope_policy = SCTP_SCOPE_POLICY_ENABLE; diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 9a56ae2f3651..f77484df097b 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -1142,6 +1142,26 @@ nodata: return retval; } +struct sctp_chunk *sctp_make_new_encap_port(const struct sctp_association *asoc, + const struct sctp_chunk *chunk) +{ + struct sctp_new_encap_port_hdr nep; + struct sctp_chunk *retval; + + retval = sctp_make_abort(asoc, chunk, + sizeof(struct sctp_errhdr) + sizeof(nep)); + if (!retval) + goto nodata; + + sctp_init_cause(retval, SCTP_ERROR_NEW_ENCAP_PORT, sizeof(nep)); + nep.cur_port = SCTP_INPUT_CB(chunk->skb)->encap_port; + nep.new_port = chunk->transport->encap_port; + sctp_addto_chunk(retval, sizeof(nep), &nep); + +nodata: + return retval; +} + /* Make a HEARTBEAT chunk. */ struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc, const struct sctp_transport *transport) @@ -2321,6 +2341,7 @@ int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk, * added as the primary transport. The source address seems to * be a better choice than any of the embedded addresses. */ + asoc->encap_port = SCTP_INPUT_CB(chunk->skb)->encap_port; if (!sctp_assoc_add_peer(asoc, peer_addr, gfp, SCTP_ACTIVE)) goto nomem; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index c669f8bd1eab..af2b7041fa4e 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -87,6 +87,13 @@ static enum sctp_disposition sctp_sf_tabort_8_4_8( const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands); +static enum sctp_disposition sctp_sf_new_encap_port( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands); static struct sctp_sackhdr *sctp_sm_pull_sack(struct sctp_chunk *chunk); static enum sctp_disposition sctp_stop_t1_and_abort( @@ -1493,6 +1500,10 @@ static enum sctp_disposition sctp_sf_do_unexpected_init( if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk))) return sctp_sf_violation_chunklen(net, ep, asoc, type, arg, commands); + + if (SCTP_INPUT_CB(chunk->skb)->encap_port != chunk->transport->encap_port) + return sctp_sf_new_encap_port(net, ep, asoc, type, arg, commands); + /* Grab the INIT header. */ chunk->subh.init_hdr = (struct sctp_inithdr *)chunk->skb->data; @@ -3392,6 +3403,45 @@ static enum sctp_disposition sctp_sf_tabort_8_4_8( sctp_packet_append_chunk(packet, abort); + sctp_add_cmd_sf(commands, SCTP_CMD_SEND_PKT, SCTP_PACKET(packet)); + + SCTP_INC_STATS(net, SCTP_MIB_OUTCTRLCHUNKS); + + sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + return SCTP_DISPOSITION_CONSUME; +} + +/* Handling of SCTP Packets Containing an INIT Chunk Matching an + * Existing Associations when the UDP encap port is incorrect. + * + * From Section 4 at draft-tuexen-tsvwg-sctp-udp-encaps-cons-03. + */ +static enum sctp_disposition sctp_sf_new_encap_port( + struct net *net, + const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + const union sctp_subtype type, + void *arg, + struct sctp_cmd_seq *commands) +{ + struct sctp_packet *packet = NULL; + struct sctp_chunk *chunk = arg; + struct sctp_chunk *abort; + + packet = sctp_ootb_pkt_new(net, asoc, chunk); + if (!packet) + return SCTP_DISPOSITION_NOMEM; + + abort = sctp_make_new_encap_port(asoc, chunk); + if (!abort) { + sctp_ootb_pkt_free(packet); + return SCTP_DISPOSITION_NOMEM; + } + + abort->skb->sk = ep->base.sk; + + sctp_packet_append_chunk(packet, abort); + sctp_add_cmd_sf(commands, SCTP_CMD_SEND_PKT, SCTP_PACKET(packet)); @@ -6268,6 +6318,8 @@ static struct sctp_packet *sctp_ootb_pkt_new( if (!transport) goto nomem; + transport->encap_port = SCTP_INPUT_CB(chunk->skb)->encap_port; + /* Cache a route for the transport with the chunk's destination as * the source address. */ diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 53d0a4161df3..a710917c5ac7 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4417,6 +4417,55 @@ out: return retval; } +static int sctp_setsockopt_encap_port(struct sock *sk, + struct sctp_udpencaps *encap, + unsigned int optlen) +{ + struct sctp_association *asoc; + struct sctp_transport *t; + __be16 encap_port; + + if (optlen != sizeof(*encap)) + return -EINVAL; + + /* If an address other than INADDR_ANY is specified, and + * no transport is found, then the request is invalid. + */ + encap_port = (__force __be16)encap->sue_port; + if (!sctp_is_any(sk, (union sctp_addr *)&encap->sue_address)) { + t = sctp_addr_id2transport(sk, &encap->sue_address, + encap->sue_assoc_id); + if (!t) + return -EINVAL; + + t->encap_port = encap_port; + return 0; + } + + /* 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, encap->sue_assoc_id); + if (!asoc && encap->sue_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) + return -EINVAL; + + /* If changes are for association, also apply encap_port to + * each transport. + */ + if (asoc) { + list_for_each_entry(t, &asoc->peer.transport_addr_list, + transports) + t->encap_port = encap_port; + + return 0; + } + + sctp_sk(sk)->encap_port = encap_port; + return 0; +} + /* API 6.2 setsockopt(), getsockopt() * * Applications use setsockopt() and getsockopt() to set or retrieve @@ -4636,6 +4685,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname, case SCTP_EXPOSE_POTENTIALLY_FAILED_STATE: retval = sctp_setsockopt_pf_expose(sk, kopt, optlen); break; + case SCTP_REMOTE_UDP_ENCAPS_PORT: + retval = sctp_setsockopt_encap_port(sk, kopt, optlen); + break; default: retval = -ENOPROTOOPT; break; @@ -4876,6 +4928,8 @@ static int sctp_init_sock(struct sock *sk) * be modified via SCTP_PEER_ADDR_PARAMS */ sp->hbinterval = net->sctp.hb_interval; + sp->udp_port = htons(net->sctp.udp_port); + sp->encap_port = htons(net->sctp.encap_port); sp->pathmaxrxt = net->sctp.max_retrans_path; sp->pf_retrans = net->sctp.pf_retrans; sp->ps_retrans = net->sctp.ps_retrans; @@ -7790,6 +7844,65 @@ out: return retval; } +static int sctp_getsockopt_encap_port(struct sock *sk, int len, + char __user *optval, int __user *optlen) +{ + struct sctp_association *asoc; + struct sctp_udpencaps encap; + struct sctp_transport *t; + __be16 encap_port; + + if (len < sizeof(encap)) + return -EINVAL; + + len = sizeof(encap); + if (copy_from_user(&encap, optval, len)) + return -EFAULT; + + /* If an address other than INADDR_ANY is specified, and + * no transport is found, then the request is invalid. + */ + if (!sctp_is_any(sk, (union sctp_addr *)&encap.sue_address)) { + t = sctp_addr_id2transport(sk, &encap.sue_address, + encap.sue_assoc_id); + if (!t) { + pr_debug("%s: failed no transport\n", __func__); + return -EINVAL; + } + + encap_port = t->encap_port; + goto out; + } + + /* 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, encap.sue_assoc_id); + if (!asoc && encap.sue_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) { + pr_debug("%s: failed no association\n", __func__); + return -EINVAL; + } + + if (asoc) { + encap_port = asoc->encap_port; + goto out; + } + + encap_port = sctp_sk(sk)->encap_port; + +out: + encap.sue_port = (__force uint16_t)encap_port; + if (copy_to_user(optval, &encap, len)) + return -EFAULT; + + if (put_user(len, optlen)) + return -EFAULT; + + return 0; +} + static int sctp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { @@ -8010,6 +8123,9 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname, case SCTP_EXPOSE_POTENTIALLY_FAILED_STATE: retval = sctp_getsockopt_pf_expose(sk, len, optval, optlen); break; + case SCTP_REMOTE_UDP_ENCAPS_PORT: + retval = sctp_getsockopt_encap_port(sk, len, optval, optlen); + break; default: retval = -ENOPROTOOPT; break; diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index c16c80963e55..e92df779af73 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -36,6 +36,7 @@ static int rto_alpha_max = 1000; static int rto_beta_max = 1000; static int pf_expose_max = SCTP_PF_EXPOSE_MAX; static int ps_retrans_max = SCTP_PS_RETRANS_MAX; +static int udp_port_max = 65535; static unsigned long max_autoclose_min = 0; static unsigned long max_autoclose_max = @@ -48,6 +49,8 @@ static int proc_sctp_do_rto_min(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); +static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write, void *buffer, + size_t *lenp, loff_t *ppos); static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); static int proc_sctp_do_auth(struct ctl_table *ctl, int write, @@ -291,6 +294,24 @@ static struct ctl_table sctp_net_table[] = { .proc_handler = proc_dointvec, }, { + .procname = "udp_port", + .data = &init_net.sctp.udp_port, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_sctp_do_udp_port, + .extra1 = SYSCTL_ZERO, + .extra2 = &udp_port_max, + }, + { + .procname = "encap_port", + .data = &init_net.sctp.encap_port, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + .extra1 = SYSCTL_ZERO, + .extra2 = &udp_port_max, + }, + { .procname = "addr_scope_policy", .data = &init_net.sctp.scope_policy, .maxlen = sizeof(int), @@ -477,6 +498,47 @@ static int proc_sctp_do_auth(struct ctl_table *ctl, int write, return ret; } +static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + struct net *net = current->nsproxy->net_ns; + unsigned int min = *(unsigned int *)ctl->extra1; + unsigned int max = *(unsigned int *)ctl->extra2; + struct ctl_table tbl; + int ret, new_value; + + memset(&tbl, 0, sizeof(struct ctl_table)); + tbl.maxlen = sizeof(unsigned int); + + if (write) + tbl.data = &new_value; + else + tbl.data = &net->sctp.udp_port; + + ret = proc_dointvec(&tbl, write, buffer, lenp, ppos); + if (write && ret == 0) { + struct sock *sk = net->sctp.ctl_sock; + + if (new_value > max || new_value < min) + return -EINVAL; + + net->sctp.udp_port = new_value; + sctp_udp_sock_stop(net); + if (new_value) { + ret = sctp_udp_sock_start(net); + if (ret) + net->sctp.udp_port = 0; + } + + /* Update the value in the control socket */ + lock_sock(sk); + sctp_sk(sk)->udp_port = htons(net->sctp.udp_port); + release_sock(sk); + } + + return ret; +} + int sctp_sysctl_net_register(struct net *net) { struct ctl_table *table; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index e9f487c8c6d5..527185af7bf3 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -1346,6 +1346,7 @@ static int smc_listen_v2_check(struct smc_sock *new_smc, { struct smc_clc_smcd_v2_extension *pclc_smcd_v2_ext; struct smc_clc_v2_extension *pclc_v2_ext; + int rc = SMC_CLC_DECL_PEERNOSMC; ini->smc_type_v1 = pclc->hdr.typev1; ini->smc_type_v2 = pclc->hdr.typev2; @@ -1353,29 +1354,30 @@ static int smc_listen_v2_check(struct smc_sock *new_smc, if (pclc->hdr.version > SMC_V1) ini->smcd_version |= ini->smc_type_v2 != SMC_TYPE_N ? SMC_V2 : 0; + if (!(ini->smcd_version & SMC_V2)) { + rc = SMC_CLC_DECL_PEERNOSMC; + goto out; + } if (!smc_ism_v2_capable) { ini->smcd_version &= ~SMC_V2; + rc = SMC_CLC_DECL_NOISM2SUPP; goto out; } pclc_v2_ext = smc_get_clc_v2_ext(pclc); if (!pclc_v2_ext) { ini->smcd_version &= ~SMC_V2; + rc = SMC_CLC_DECL_NOV2EXT; goto out; } pclc_smcd_v2_ext = smc_get_clc_smcd_v2_ext(pclc_v2_ext); - if (!pclc_smcd_v2_ext) + if (!pclc_smcd_v2_ext) { ini->smcd_version &= ~SMC_V2; + rc = SMC_CLC_DECL_NOV2DEXT; + } out: - if (!ini->smcd_version) { - if (pclc->hdr.typev1 == SMC_TYPE_B || - pclc->hdr.typev2 == SMC_TYPE_B) - return SMC_CLC_DECL_NOSMCDEV; - if (pclc->hdr.typev1 == SMC_TYPE_D || - pclc->hdr.typev2 == SMC_TYPE_D) - return SMC_CLC_DECL_NOSMCDDEV; - return SMC_CLC_DECL_NOSMCRDEV; - } + if (!ini->smcd_version) + return rc; return 0; } @@ -1473,6 +1475,12 @@ static void smc_check_ism_v2_match(struct smc_init_info *ini, } } +static void smc_find_ism_store_rc(u32 rc, struct smc_init_info *ini) +{ + if (!ini->rc) + ini->rc = rc; +} + static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, struct smc_clc_msg_proposal *pclc, struct smc_init_info *ini) @@ -1483,7 +1491,7 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, unsigned int matches = 0; u8 smcd_version; u8 *eid = NULL; - int i; + int i, rc; if (!(ini->smcd_version & SMC_V2) || !smcd_indicated(ini->smc_type_v2)) goto not_found; @@ -1492,8 +1500,10 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, smc_v2_ext = smc_get_clc_v2_ext(pclc); smcd_v2_ext = smc_get_clc_smcd_v2_ext(smc_v2_ext); if (!smcd_v2_ext || - !smc_v2_ext->hdr.flag.seid) /* no system EID support for SMCD */ + !smc_v2_ext->hdr.flag.seid) { /* no system EID support for SMCD */ + smc_find_ism_store_rc(SMC_CLC_DECL_NOSEID, ini); goto not_found; + } mutex_lock(&smcd_dev_list.mutex); if (pclc_smcd->ism.chid) @@ -1525,9 +1535,12 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, ini->smcd_version = SMC_V2; ini->is_smcd = true; ini->ism_selected = i; - if (smc_listen_ism_init(new_smc, ini)) + rc = smc_listen_ism_init(new_smc, ini); + if (rc) { + smc_find_ism_store_rc(rc, ini); /* try next active ISM device */ continue; + } return; /* matching and usable V2 ISM device found */ } /* no V2 ISM device could be initialized */ @@ -1544,19 +1557,23 @@ static void smc_find_ism_v1_device_serv(struct smc_sock *new_smc, struct smc_init_info *ini) { struct smc_clc_msg_smcd *pclc_smcd = smc_get_clc_msg_smcd(pclc); + int rc = 0; /* check if ISM V1 is available */ if (!(ini->smcd_version & SMC_V1) || !smcd_indicated(ini->smc_type_v1)) goto not_found; ini->is_smcd = true; /* prepare ISM check */ ini->ism_peer_gid[0] = ntohll(pclc_smcd->ism.gid); - if (smc_find_ism_device(new_smc, ini)) + rc = smc_find_ism_device(new_smc, ini); + if (rc) goto not_found; ini->ism_selected = 0; - if (!smc_listen_ism_init(new_smc, ini)) + rc = smc_listen_ism_init(new_smc, ini); + if (!rc) return; /* V1 ISM device found */ not_found: + smc_find_ism_store_rc(rc, ini); ini->ism_dev[0] = NULL; ini->is_smcd = false; } @@ -1613,16 +1630,16 @@ static int smc_listen_find_device(struct smc_sock *new_smc, return 0; if (!(ini->smcd_version & SMC_V1)) - return SMC_CLC_DECL_NOSMCDEV; + return ini->rc ?: SMC_CLC_DECL_NOSMCD2DEV; /* check for matching IP prefix and subnet length */ rc = smc_listen_prfx_check(new_smc, pclc); if (rc) - return rc; + return ini->rc ?: rc; /* get vlan id from IP device */ if (smc_vlan_by_tcpsk(new_smc->clcsock, ini)) - return SMC_CLC_DECL_GETVLANERR; + return ini->rc ?: SMC_CLC_DECL_GETVLANERR; /* check for ISM device matching V1 proposed device */ smc_find_ism_v1_device_serv(new_smc, pclc, ini); @@ -1630,10 +1647,14 @@ static int smc_listen_find_device(struct smc_sock *new_smc, return 0; if (pclc->hdr.typev1 == SMC_TYPE_D) - return SMC_CLC_DECL_NOSMCDDEV; /* skip RDMA and decline */ + /* skip RDMA and decline */ + return ini->rc ?: SMC_CLC_DECL_NOSMCDDEV; /* check if RDMA is available */ - return smc_find_rdma_v1_device_serv(new_smc, pclc, ini); + rc = smc_find_rdma_v1_device_serv(new_smc, pclc, ini); + smc_find_ism_store_rc(rc, ini); + + return (!rc) ? 0 : ini->rc; } /* listen worker: finish RDMA setup */ diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index c579d1d5995a..49752c997c51 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -37,6 +37,11 @@ #define SMC_CLC_DECL_NOSMCDEV 0x03030000 /* no SMC device found (R or D) */ #define SMC_CLC_DECL_NOSMCDDEV 0x03030001 /* no SMC-D device found */ #define SMC_CLC_DECL_NOSMCRDEV 0x03030002 /* no SMC-R device found */ +#define SMC_CLC_DECL_NOISM2SUPP 0x03030003 /* hardware has no ISMv2 support */ +#define SMC_CLC_DECL_NOV2EXT 0x03030004 /* peer sent no clc v2 extension */ +#define SMC_CLC_DECL_NOV2DEXT 0x03030005 /* peer sent no clc SMC-Dv2 ext. */ +#define SMC_CLC_DECL_NOSEID 0x03030006 /* peer sent no SEID */ +#define SMC_CLC_DECL_NOSMCD2DEV 0x03030007 /* no SMC-Dv2 device found */ #define SMC_CLC_DECL_MODEUNSUPP 0x03040000 /* smc modes do not match (R or D)*/ #define SMC_CLC_DECL_RMBE_EC 0x03050000 /* peer has eyecatcher in RMBE */ #define SMC_CLC_DECL_OPTUNSUPP 0x03060000 /* fastopen sockopt not supported */ diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index f1e867ce2e63..9aee54a6bcba 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -301,6 +301,7 @@ struct smc_init_info { u8 first_contact_peer; u8 first_contact_local; unsigned short vlan_id; + u32 rc; /* SMC-R */ struct smc_clc_msg_local *ib_lcl; struct smc_ib_device *ib_dev; diff --git a/net/tipc/core.c b/net/tipc/core.c index c2ff42900b53..5cc1f0307215 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -81,8 +81,6 @@ static int __net_init tipc_init_net(struct net *net) if (err) goto out_nametbl; - INIT_LIST_HEAD(&tn->dist_queue); - err = tipc_bcast_init(net); if (err) goto out_bclink; diff --git a/net/tipc/core.h b/net/tipc/core.h index 1d57a4d3b05e..df34dcdd0607 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -132,9 +132,6 @@ struct tipc_net { spinlock_t nametbl_lock; struct name_table *nametbl; - /* Name dist queue */ - struct list_head dist_queue; - /* Topology subscription server */ struct tipc_topsrv *topsrv; atomic_t subscription_count; diff --git a/net/tipc/link.c b/net/tipc/link.c index 06b880da2a8e..97b1c6bd45dc 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1260,7 +1260,7 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb, pr_warn("Dropping received illegal msg type\n"); kfree_skb(skb); return true; - }; + } } /* tipc_link_input - process packet that has passed link protocol check diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index fe4edce459ad..4cd90d5c84c8 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -244,24 +244,6 @@ static void tipc_publ_purge(struct net *net, struct publication *publ, u32 addr) kfree_rcu(p, rcu); } -/** - * tipc_dist_queue_purge - remove deferred updates from a node that went down - */ -static void tipc_dist_queue_purge(struct net *net, u32 addr) -{ - struct tipc_net *tn = net_generic(net, tipc_net_id); - struct distr_queue_item *e, *tmp; - - spin_lock_bh(&tn->nametbl_lock); - list_for_each_entry_safe(e, tmp, &tn->dist_queue, next) { - if (e->node != addr) - continue; - list_del(&e->next); - kfree(e); - } - spin_unlock_bh(&tn->nametbl_lock); -} - void tipc_publ_notify(struct net *net, struct list_head *nsub_list, u32 addr, u16 capabilities) { @@ -272,7 +254,6 @@ void tipc_publ_notify(struct net *net, struct list_head *nsub_list, list_for_each_entry_safe(publ, tmp, nsub_list, binding_node) tipc_publ_purge(net, publ, addr); - tipc_dist_queue_purge(net, addr); spin_lock_bh(&tn->nametbl_lock); if (!(capabilities & TIPC_NAMED_BCAST)) nt->rc_dests--; diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index 1c7aa51cc2a3..5c6206c9d6a8 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -118,7 +118,8 @@ static void tipc_tlv_init(struct sk_buff *skb, u16 type) skb_put(skb, sizeof(struct tlv_desc)); } -static int tipc_tlv_sprintf(struct sk_buff *skb, const char *fmt, ...) +static __printf(2, 3) int tipc_tlv_sprintf(struct sk_buff *skb, + const char *fmt, ...) { int n; u16 len; @@ -588,7 +589,7 @@ static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg, return 0; tipc_tlv_sprintf(msg->rep, "\nLink <%s>\n", - nla_data(link[TIPC_NLA_LINK_NAME])); + (char *)nla_data(link[TIPC_NLA_LINK_NAME])); if (link[TIPC_NLA_LINK_BROADCAST]) { __fill_bc_link_stat(msg, prop, stats); diff --git a/net/tipc/node.c b/net/tipc/node.c index d269ebe382e1..cd67b7d5169f 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -1638,7 +1638,7 @@ static void tipc_lxc_xmit(struct net *peer_net, struct sk_buff_head *list) return; default: return; - }; + } } /** diff --git a/net/tipc/socket.c b/net/tipc/socket.c index e795a8a2955b..69c4b16e8184 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -658,8 +658,8 @@ static int tipc_release(struct socket *sock) * NOTE: This routine doesn't need to take the socket lock since it doesn't * access any non-constant socket information. */ -static int tipc_bind(struct socket *sock, struct sockaddr *uaddr, - int uaddr_len) + +int tipc_sk_bind(struct socket *sock, struct sockaddr *uaddr, int uaddr_len) { struct sock *sk = sock->sk; struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr; @@ -691,13 +691,6 @@ static int tipc_bind(struct socket *sock, struct sockaddr *uaddr, goto exit; } - if ((addr->addr.nameseq.type < TIPC_RESERVED_TYPES) && - (addr->addr.nameseq.type != TIPC_TOP_SRV) && - (addr->addr.nameseq.type != TIPC_CFG_SRV)) { - res = -EACCES; - goto exit; - } - res = (addr->scope >= 0) ? tipc_sk_publish(tsk, addr->scope, &addr->addr.nameseq) : tipc_sk_withdraw(tsk, -addr->scope, &addr->addr.nameseq); @@ -706,6 +699,22 @@ exit: return res; } +static int tipc_bind(struct socket *sock, struct sockaddr *skaddr, int alen) +{ + struct sockaddr_tipc *addr = (struct sockaddr_tipc *)skaddr; + + if (alen) { + if (alen < sizeof(struct sockaddr_tipc)) + return -EINVAL; + if (addr->addr.nameseq.type < TIPC_RESERVED_TYPES) { + pr_warn_once("Can't bind to reserved service type %u\n", + addr->addr.nameseq.type); + return -EACCES; + } + } + return tipc_sk_bind(sock, skaddr, alen); +} + /** * tipc_getname - get port ID of socket or peer socket * @sock: socket structure diff --git a/net/tipc/socket.h b/net/tipc/socket.h index b11575afc66f..02cdf166807d 100644 --- a/net/tipc/socket.h +++ b/net/tipc/socket.h @@ -74,7 +74,7 @@ int tipc_dump_done(struct netlink_callback *cb); u32 tipc_sock_get_portid(struct sock *sk); bool tipc_sk_overlimit1(struct sock *sk, struct sk_buff *skb); bool tipc_sk_overlimit2(struct sock *sk, struct sk_buff *skb); - +int tipc_sk_bind(struct socket *sock, struct sockaddr *skaddr, int alen); int tsk_set_importance(struct sock *sk, int imp); #endif diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index 5f6f86051c83..cec029349662 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -520,12 +520,12 @@ static int tipc_topsrv_create_listener(struct tipc_topsrv *srv) saddr.family = AF_TIPC; saddr.addrtype = TIPC_ADDR_NAMESEQ; - saddr.addr.nameseq.type = TIPC_TOP_SRV; + saddr.addr.nameseq.type = TIPC_TOP_SRV; saddr.addr.nameseq.lower = TIPC_TOP_SRV; saddr.addr.nameseq.upper = TIPC_TOP_SRV; saddr.scope = TIPC_NODE_SCOPE; - rc = kernel_bind(lsock, (struct sockaddr *)&saddr, sizeof(saddr)); + rc = tipc_sk_bind(lsock, (struct sockaddr *)&saddr, sizeof(saddr)); if (rc < 0) goto err; rc = kernel_listen(lsock, 0); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index b4d7b8aba003..35613efbb1ec 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -2072,8 +2072,7 @@ static long vsock_dev_do_ioctl(struct file *filp, break; default: - pr_err("Unknown ioctl %d\n", cmd); - retval = -EINVAL; + retval = -ENOIOCTLCMD; } return retval; diff --git a/tools/testing/selftests/drivers/net/netdevsim/nexthop.sh b/tools/testing/selftests/drivers/net/netdevsim/nexthop.sh new file mode 100755 index 000000000000..be0c1b5ee6b8 --- /dev/null +++ b/tools/testing/selftests/drivers/net/netdevsim/nexthop.sh @@ -0,0 +1,436 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# This test is for checking the nexthop offload API. It makes use of netdevsim +# which registers a listener to the nexthop notification chain. + +lib_dir=$(dirname $0)/../../../net/forwarding + +ALL_TESTS=" + nexthop_single_add_test + nexthop_single_add_err_test + nexthop_group_add_test + nexthop_group_add_err_test + nexthop_group_replace_test + nexthop_group_replace_err_test + nexthop_single_replace_test + nexthop_single_replace_err_test + nexthop_single_in_group_replace_test + nexthop_single_in_group_replace_err_test + nexthop_single_in_group_delete_test + nexthop_single_in_group_delete_err_test + nexthop_replay_test + nexthop_replay_err_test +" +NETDEVSIM_PATH=/sys/bus/netdevsim/ +DEV_ADDR=1337 +DEV=netdevsim${DEV_ADDR} +DEVLINK_DEV=netdevsim/${DEV} +SYSFS_NET_DIR=/sys/bus/netdevsim/devices/$DEV/net/ +NUM_NETIFS=0 +source $lib_dir/lib.sh +source $lib_dir/devlink_lib.sh + +nexthop_check() +{ + local nharg="$1"; shift + local expected="$1"; shift + + out=$($IP nexthop show ${nharg} | sed -e 's/ *$//') + if [[ "$out" != "$expected" ]]; then + return 1 + fi + + return 0 +} + +nexthop_resource_check() +{ + local expected_occ=$1; shift + + occ=$($DEVLINK -jp resource show $DEVLINK_DEV \ + | jq '.[][][] | select(.name=="nexthops") | .["occ"]') + + if [ $expected_occ -ne $occ ]; then + return 1 + fi + + return 0 +} + +nexthop_resource_set() +{ + local size=$1; shift + + $DEVLINK resource set $DEVLINK_DEV path nexthops size $size + $DEVLINK dev reload $DEVLINK_DEV +} + +nexthop_single_add_test() +{ + RET=0 + + $IP nexthop add id 1 via 192.0.2.2 dev dummy1 + nexthop_check "id 1" "id 1 via 192.0.2.2 dev dummy1 scope link trap" + check_err $? "Unexpected nexthop entry" + + nexthop_resource_check 1 + check_err $? "Wrong nexthop occupancy" + + $IP nexthop del id 1 + nexthop_resource_check 0 + check_err $? "Wrong nexthop occupancy after delete" + + log_test "Single nexthop add and delete" +} + +nexthop_single_add_err_test() +{ + RET=0 + + nexthop_resource_set 1 + + $IP nexthop add id 1 via 192.0.2.2 dev dummy1 + + $IP nexthop add id 2 via 192.0.2.3 dev dummy1 &> /dev/null + check_fail $? "Nexthop addition succeeded when should fail" + + nexthop_resource_check 1 + check_err $? "Wrong nexthop occupancy" + + log_test "Single nexthop add failure" + + $IP nexthop flush &> /dev/null + nexthop_resource_set 9999 +} + +nexthop_group_add_test() +{ + RET=0 + + $IP nexthop add id 1 via 192.0.2.2 dev dummy1 + $IP nexthop add id 2 via 192.0.2.3 dev dummy1 + + $IP nexthop add id 10 group 1/2 + nexthop_check "id 10" "id 10 group 1/2 trap" + check_err $? "Unexpected nexthop group entry" + + nexthop_resource_check 4 + check_err $? "Wrong nexthop occupancy" + + $IP nexthop del id 10 + nexthop_resource_check 2 + check_err $? "Wrong nexthop occupancy after delete" + + $IP nexthop add id 10 group 1,20/2,39 + nexthop_check "id 10" "id 10 group 1,20/2,39 trap" + check_err $? "Unexpected weighted nexthop group entry" + + nexthop_resource_check 61 + check_err $? "Wrong weighted nexthop occupancy" + + $IP nexthop del id 10 + nexthop_resource_check 2 + check_err $? "Wrong nexthop occupancy after delete" + + log_test "Nexthop group add and delete" + + $IP nexthop flush &> /dev/null +} + +nexthop_group_add_err_test() +{ + RET=0 + + nexthop_resource_set 2 + + $IP nexthop add id 1 via 192.0.2.2 dev dummy1 + $IP nexthop add id 2 via 192.0.2.3 dev dummy1 + + $IP nexthop add id 10 group 1/2 &> /dev/null + check_fail $? "Nexthop group addition succeeded when should fail" + + nexthop_resource_check 2 + check_err $? "Wrong nexthop occupancy" + + log_test "Nexthop group add failure" + + $IP nexthop flush &> /dev/null + nexthop_resource_set 9999 +} + +nexthop_group_replace_test() +{ + RET=0 + + $IP nexthop add id 1 via 192.0.2.2 dev dummy1 + $IP nexthop add id 2 via 192.0.2.3 dev dummy1 + $IP nexthop add id 3 via 192.0.2.4 dev dummy1 + $IP nexthop add id 10 group 1/2 + + $IP nexthop replace id 10 group 1/2/3 + nexthop_check "id 10" "id 10 group 1/2/3 trap" + check_err $? "Unexpected nexthop group entry" + + nexthop_resource_check 6 + check_err $? "Wrong nexthop occupancy" + + log_test "Nexthop group replace" + + $IP nexthop flush &> /dev/null +} + +nexthop_group_replace_err_test() +{ + RET=0 + + nexthop_resource_set 5 + + $IP nexthop add id 1 via 192.0.2.2 dev dummy1 + $IP nexthop add id 2 via 192.0.2.3 dev dummy1 + $IP nexthop add id 3 via 192.0.2.4 dev dummy1 + $IP nexthop add id 10 group 1/2 + + $IP nexthop replace id 10 group 1/2/3 &> /dev/null + check_fail $? "Nexthop group replacement succeeded when should fail" + + nexthop_check "id 10" "id 10 group 1/2 trap" + check_err $? "Unexpected nexthop group entry after failure" + + nexthop_resource_check 5 + check_err $? "Wrong nexthop occupancy after failure" + + log_test "Nexthop group replace failure" + + $IP nexthop flush &> /dev/null + nexthop_resource_set 9999 +} + +nexthop_single_replace_test() +{ + RET=0 + + $IP nexthop add id 1 via 192.0.2.2 dev dummy1 + + $IP nexthop replace id 1 via 192.0.2.3 dev dummy1 + nexthop_check "id 1" "id 1 via 192.0.2.3 dev dummy1 scope link trap" + check_err $? "Unexpected nexthop entry" + + nexthop_resource_check 1 + check_err $? "Wrong nexthop occupancy" + + log_test "Single nexthop replace" + + $IP nexthop flush &> /dev/null +} + +nexthop_single_replace_err_test() +{ + RET=0 + + # This is supposed to cause the replace to fail because the new nexthop + # is programmed before deleting the replaced one. + nexthop_resource_set 1 + + $IP nexthop add id 1 via 192.0.2.2 dev dummy1 + + $IP nexthop replace id 1 via 192.0.2.3 dev dummy1 &> /dev/null + check_fail $? "Nexthop replace succeeded when should fail" + + nexthop_check "id 1" "id 1 via 192.0.2.2 dev dummy1 scope link trap" + check_err $? "Unexpected nexthop entry after failure" + + nexthop_resource_check 1 + check_err $? "Wrong nexthop occupancy after failure" + + log_test "Single nexthop replace failure" + + $IP nexthop flush &> /dev/null + nexthop_resource_set 9999 +} + +nexthop_single_in_group_replace_test() +{ + RET=0 + + $IP nexthop add id 1 via 192.0.2.2 dev dummy1 + $IP nexthop add id 2 via 192.0.2.3 dev dummy1 + $IP nexthop add id 10 group 1/2 + + $IP nexthop replace id 1 via 192.0.2.4 dev dummy1 + check_err $? "Failed to replace nexthop when should not" + + nexthop_check "id 10" "id 10 group 1/2 trap" + check_err $? "Unexpected nexthop group entry" + + nexthop_resource_check 4 + check_err $? "Wrong nexthop occupancy" + + log_test "Single nexthop replace while in group" + + $IP nexthop flush &> /dev/null +} + +nexthop_single_in_group_replace_err_test() +{ + RET=0 + + nexthop_resource_set 5 + + $IP nexthop add id 1 via 192.0.2.2 dev dummy1 + $IP nexthop add id 2 via 192.0.2.3 dev dummy1 + $IP nexthop add id 10 group 1/2 + + $IP nexthop replace id 1 via 192.0.2.4 dev dummy1 &> /dev/null + check_fail $? "Nexthop replacement succeeded when should fail" + + nexthop_check "id 1" "id 1 via 192.0.2.2 dev dummy1 scope link trap" + check_err $? "Unexpected nexthop entry after failure" + + nexthop_check "id 10" "id 10 group 1/2 trap" + check_err $? "Unexpected nexthop group entry after failure" + + nexthop_resource_check 4 + check_err $? "Wrong nexthop occupancy" + + log_test "Single nexthop replace while in group failure" + + $IP nexthop flush &> /dev/null + nexthop_resource_set 9999 +} + +nexthop_single_in_group_delete_test() +{ + RET=0 + + $IP nexthop add id 1 via 192.0.2.2 dev dummy1 + $IP nexthop add id 2 via 192.0.2.3 dev dummy1 + $IP nexthop add id 10 group 1/2 + + $IP nexthop del id 1 + nexthop_check "id 10" "id 10 group 2 trap" + check_err $? "Unexpected nexthop group entry" + + nexthop_resource_check 2 + check_err $? "Wrong nexthop occupancy" + + log_test "Single nexthop delete while in group" + + $IP nexthop flush &> /dev/null +} + +nexthop_single_in_group_delete_err_test() +{ + RET=0 + + # First, nexthop 1 will be deleted, which will reduce the occupancy to + # 5. Afterwards, a replace notification will be sent for nexthop group + # 10 with only two nexthops. Since the new group is allocated before + # the old is deleted, the replacement will fail as it will result in an + # occupancy of 7. + nexthop_resource_set 6 + + $IP nexthop add id 1 via 192.0.2.2 dev dummy1 + $IP nexthop add id 2 via 192.0.2.3 dev dummy1 + $IP nexthop add id 3 via 192.0.2.4 dev dummy1 + $IP nexthop add id 10 group 1/2/3 + + $IP nexthop del id 1 + + nexthop_resource_check 5 + check_err $? "Wrong nexthop occupancy" + + log_test "Single nexthop delete while in group failure" + + $IP nexthop flush &> /dev/null + nexthop_resource_set 9999 +} + +nexthop_replay_test() +{ + RET=0 + + $IP nexthop add id 1 via 192.0.2.2 dev dummy1 + $IP nexthop add id 2 via 192.0.2.3 dev dummy1 + $IP nexthop add id 10 group 1/2 + + $DEVLINK dev reload $DEVLINK_DEV + check_err $? "Failed to reload when should not" + + nexthop_check "id 1" "id 1 via 192.0.2.2 dev dummy1 scope link trap" + check_err $? "Unexpected nexthop entry after reload" + + nexthop_check "id 2" "id 2 via 192.0.2.3 dev dummy1 scope link trap" + check_err $? "Unexpected nexthop entry after reload" + + nexthop_check "id 10" "id 10 group 1/2 trap" + check_err $? "Unexpected nexthop group entry after reload" + + nexthop_resource_check 4 + check_err $? "Wrong nexthop occupancy" + + log_test "Nexthop replay" + + $IP nexthop flush &> /dev/null +} + +nexthop_replay_err_test() +{ + RET=0 + + $IP nexthop add id 1 via 192.0.2.2 dev dummy1 + $IP nexthop add id 2 via 192.0.2.3 dev dummy1 + $IP nexthop add id 10 group 1/2 + + # Reduce size of nexthop resource so that reload will fail. + $DEVLINK resource set $DEVLINK_DEV path nexthops size 3 + $DEVLINK dev reload $DEVLINK_DEV &> /dev/null + check_fail $? "Reload succeeded when should fail" + + $DEVLINK resource set $DEVLINK_DEV path nexthops size 9999 + $DEVLINK dev reload $DEVLINK_DEV + check_err $? "Failed to reload when should not" + + log_test "Nexthop replay failure" + + $IP nexthop flush &> /dev/null +} + +setup_prepare() +{ + local netdev + + modprobe netdevsim &> /dev/null + + echo "$DEV_ADDR 1" > ${NETDEVSIM_PATH}/new_device + while [ ! -d $SYSFS_NET_DIR ] ; do :; done + + set -e + + ip netns add testns1 + devlink dev reload $DEVLINK_DEV netns testns1 + + IP="ip -netns testns1" + DEVLINK="devlink -N testns1" + + $IP link add name dummy1 up type dummy + $IP address add 192.0.2.1/24 dev dummy1 + + set +e +} + +cleanup() +{ + pre_cleanup + ip netns del testns1 + echo "$DEV_ADDR" > ${NETDEVSIM_PATH}/del_device + modprobe -r netdevsim &> /dev/null +} + +trap cleanup EXIT + +setup_prepare + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index ef352477cac6..fa5fa425d148 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -21,6 +21,7 @@ TEST_PROGS += rxtimestamp.sh TEST_PROGS += devlink_port_split.py TEST_PROGS += drop_monitor_tests.sh TEST_PROGS += vrf_route_leaking.sh +TEST_PROGS += bareudp.sh TEST_PROGS_EXTENDED := in_netns.sh TEST_GEN_FILES = socket nettest TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any diff --git a/tools/testing/selftests/net/bareudp.sh b/tools/testing/selftests/net/bareudp.sh new file mode 100755 index 000000000000..c6fe22de7d0e --- /dev/null +++ b/tools/testing/selftests/net/bareudp.sh @@ -0,0 +1,538 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +# Test various bareudp tunnel configurations. +# +# The bareudp module allows to tunnel network protocols like IP or MPLS over +# UDP, without adding any intermediate header. This scripts tests several +# configurations of bareudp (using IPv4 or IPv6 as underlay and transporting +# IPv4, IPv6 or MPLS packets on the overlay). +# +# Network topology: +# +# * A chain of 4 network namespaces, connected with veth pairs. Each veth +# is assigned an IPv4 and an IPv6 address. A host-route allows a veth to +# join its peer. +# +# * NS0 and NS3 are at the extremities of the chain. They have additional +# IPv4 and IPv6 addresses on their loopback device. Routes are added in NS0 +# and NS3, so that they can communicate using these overlay IP addresses. +# For IPv4 and IPv6 reachability tests, the route simply sets the peer's +# veth address as gateway. For MPLS reachability tests, an MPLS header is +# also pushed before the IP header. +# +# * NS1 and NS2 are the intermediate namespaces. They use a bareudp device to +# encapsulate the traffic into UDP. +# +# +-----------------------------------------------------------------------+ +# | NS0 | +# | | +# | lo: | +# | * IPv4 address: 192.0.2.100/32 | +# | * IPv6 address: 2001:db8::100/128 | +# | * IPv6 address: 2001:db8::200/128 | +# | * IPv4 route: 192.0.2.103/32 reachable via 192.0.2.11 | +# | * IPv6 route: 2001:db8::103/128 reachable via 2001:db8::11 | +# | * IPv6 route: 2001:db8::203/128 reachable via 2001:db8::11 | +# | (encapsulated with MPLS label 203) | +# | | +# | veth01: | +# | ^ * IPv4 address: 192.0.2.10, peer 192.0.2.11/32 | +# | | * IPv6 address: 2001:db8::10, peer 2001:db8::11/128 | +# | | | +# +---+-------------------------------------------------------------------+ +# | +# | Traffic type: IP or MPLS (depending on test) +# | +# +---+-------------------------------------------------------------------+ +# | | NS1 | +# | | | +# | v | +# | veth10: | +# | * IPv4 address: 192.0.2.11, peer 192.0.2.10/32 | +# | * IPv6 address: 2001:db8::11, peer 2001:db8::10/128 | +# | | +# | bareudp_ns1: | +# | * Encapsulate IP or MPLS packets received on veth10 into UDP | +# | and send the resulting packets through veth12. | +# | * Decapsulate bareudp packets (either IP or MPLS, over UDP) | +# | received on veth12 and send the inner packets through veth10. | +# | | +# | veth12: | +# | ^ * IPv4 address: 192.0.2.21, peer 192.0.2.22/32 | +# | | * IPv6 address: 2001:db8::21, peer 2001:db8::22/128 | +# | | | +# +---+-------------------------------------------------------------------+ +# | +# | Traffic type: IP or MPLS (depending on test), over UDP +# | +# +---+-------------------------------------------------------------------+ +# | | NS2 | +# | | | +# | v | +# | veth21: | +# | * IPv4 address: 192.0.2.22, peer 192.0.2.21/32 | +# | * IPv6 address: 2001:db8::22, peer 2001:db8::21/128 | +# | | +# | bareudp_ns2: | +# | * Decapsulate bareudp packets (either IP or MPLS, over UDP) | +# | received on veth21 and send the inner packets through veth23. | +# | * Encapsulate IP or MPLS packets received on veth23 into UDP | +# | and send the resulting packets through veth21. | +# | | +# | veth23: | +# | ^ * IPv4 address: 192.0.2.32, peer 192.0.2.33/32 | +# | | * IPv6 address: 2001:db8::32, peer 2001:db8::33/128 | +# | | | +# +---+-------------------------------------------------------------------+ +# | +# | Traffic type: IP or MPLS (depending on test) +# | +# +---+-------------------------------------------------------------------+ +# | | NS3 | +# | v | +# | veth32: | +# | * IPv4 address: 192.0.2.33, peer 192.0.2.32/32 | +# | * IPv6 address: 2001:db8::33, peer 2001:db8::32/128 | +# | | +# | lo: | +# | * IPv4 address: 192.0.2.103/32 | +# | * IPv6 address: 2001:db8::103/128 | +# | * IPv6 address: 2001:db8::203/128 | +# | * IPv4 route: 192.0.2.100/32 reachable via 192.0.2.32 | +# | * IPv6 route: 2001:db8::100/128 reachable via 2001:db8::32 | +# | * IPv6 route: 2001:db8::200/128 reachable via 2001:db8::32 | +# | (encapsulated with MPLS label 200) | +# | | +# +-----------------------------------------------------------------------+ + +ERR=4 # Return 4 by default, which is the SKIP code for kselftest +PING6="ping" +PAUSE_ON_FAIL="no" + +readonly NS0=$(mktemp -u ns0-XXXXXXXX) +readonly NS1=$(mktemp -u ns1-XXXXXXXX) +readonly NS2=$(mktemp -u ns2-XXXXXXXX) +readonly NS3=$(mktemp -u ns3-XXXXXXXX) + +# Exit the script after having removed the network namespaces it created +# +# Parameters: +# +# * The list of network namespaces to delete before exiting. +# +exit_cleanup() +{ + for ns in "$@"; do + ip netns delete "${ns}" 2>/dev/null || true + done + + if [ "${ERR}" -eq 4 ]; then + echo "Error: Setting up the testing environment failed." >&2 + fi + + exit "${ERR}" +} + +# Create the four network namespaces used by the script (NS0, NS1, NS2 and NS3) +# +# New namespaces are cleaned up manually in case of error, to ensure that only +# namespaces created by this script are deleted. +create_namespaces() +{ + ip netns add "${NS0}" || exit_cleanup + ip netns add "${NS1}" || exit_cleanup "${NS0}" + ip netns add "${NS2}" || exit_cleanup "${NS0}" "${NS1}" + ip netns add "${NS3}" || exit_cleanup "${NS0}" "${NS1}" "${NS2}" +} + +# The trap function handler +# +exit_cleanup_all() +{ + exit_cleanup "${NS0}" "${NS1}" "${NS2}" "${NS3}" +} + +# Configure a network interface using a host route +# +# Parameters +# +# * $1: the netns the network interface resides in, +# * $2: the network interface name, +# * $3: the local IPv4 address to assign to this interface, +# * $4: the IPv4 address of the remote network interface, +# * $5: the local IPv6 address to assign to this interface, +# * $6: the IPv6 address of the remote network interface. +# +iface_config() +{ + local NS="${1}"; readonly NS + local DEV="${2}"; readonly DEV + local LOCAL_IP4="${3}"; readonly LOCAL_IP4 + local PEER_IP4="${4}"; readonly PEER_IP4 + local LOCAL_IP6="${5}"; readonly LOCAL_IP6 + local PEER_IP6="${6}"; readonly PEER_IP6 + + ip -netns "${NS}" link set dev "${DEV}" up + ip -netns "${NS}" address add dev "${DEV}" "${LOCAL_IP4}" peer "${PEER_IP4}" + ip -netns "${NS}" address add dev "${DEV}" "${LOCAL_IP6}" peer "${PEER_IP6}" nodad +} + +# Create base networking topology: +# +# * set up the loopback device in all network namespaces (NS0..NS3), +# * set up a veth pair to connect each netns in sequence (NS0 with NS1, +# NS1 with NS2, etc.), +# * add and IPv4 and an IPv6 address on each veth interface, +# * prepare the ingress qdiscs in the intermediate namespaces. +# +setup_underlay() +{ + for ns in "${NS0}" "${NS1}" "${NS2}" "${NS3}"; do + ip -netns "${ns}" link set dev lo up + done; + + ip link add name veth01 netns "${NS0}" type veth peer name veth10 netns "${NS1}" + ip link add name veth12 netns "${NS1}" type veth peer name veth21 netns "${NS2}" + ip link add name veth23 netns "${NS2}" type veth peer name veth32 netns "${NS3}" + iface_config "${NS0}" veth01 192.0.2.10 192.0.2.11/32 2001:db8::10 2001:db8::11/128 + iface_config "${NS1}" veth10 192.0.2.11 192.0.2.10/32 2001:db8::11 2001:db8::10/128 + iface_config "${NS1}" veth12 192.0.2.21 192.0.2.22/32 2001:db8::21 2001:db8::22/128 + iface_config "${NS2}" veth21 192.0.2.22 192.0.2.21/32 2001:db8::22 2001:db8::21/128 + iface_config "${NS2}" veth23 192.0.2.32 192.0.2.33/32 2001:db8::32 2001:db8::33/128 + iface_config "${NS3}" veth32 192.0.2.33 192.0.2.32/32 2001:db8::33 2001:db8::32/128 + + tc -netns "${NS1}" qdisc add dev veth10 ingress + tc -netns "${NS2}" qdisc add dev veth23 ingress +} + +# Set up the IPv4, IPv6 and MPLS overlays. +# +# Configuration is similar for all protocols: +# +# * add an overlay IP address on the loopback interface of each edge +# namespace, +# * route these IP addresses via the intermediate namespaces (for the MPLS +# tests, this is also where MPLS encapsulation is done), +# * add routes for these IP addresses (or MPLS labels) in the intermediate +# namespaces. +# +# The bareudp encapsulation isn't configured in setup_overlay_*(). That will be +# done just before running the reachability tests. + +setup_overlay_ipv4() +{ + # Add the overlay IP addresses and route them through the veth devices + ip -netns "${NS0}" address add 192.0.2.100/32 dev lo + ip -netns "${NS3}" address add 192.0.2.103/32 dev lo + ip -netns "${NS0}" route add 192.0.2.103/32 src 192.0.2.100 via 192.0.2.11 + ip -netns "${NS3}" route add 192.0.2.100/32 src 192.0.2.103 via 192.0.2.32 + + # Route the overlay addresses in the intermediate namespaces + # (used after bareudp decapsulation) + ip netns exec "${NS1}" sysctl -qw net.ipv4.ip_forward=1 + ip netns exec "${NS2}" sysctl -qw net.ipv4.ip_forward=1 + ip -netns "${NS1}" route add 192.0.2.100/32 via 192.0.2.10 + ip -netns "${NS2}" route add 192.0.2.103/32 via 192.0.2.33 +} + +setup_overlay_ipv6() +{ + # Add the overlay IP addresses and route them through the veth devices + ip -netns "${NS0}" address add 2001:db8::100/128 dev lo + ip -netns "${NS3}" address add 2001:db8::103/128 dev lo + ip -netns "${NS0}" route add 2001:db8::103/128 src 2001:db8::100 via 2001:db8::11 + ip -netns "${NS3}" route add 2001:db8::100/128 src 2001:db8::103 via 2001:db8::32 + + # Route the overlay addresses in the intermediate namespaces + # (used after bareudp decapsulation) + ip netns exec "${NS1}" sysctl -qw net.ipv6.conf.all.forwarding=1 + ip netns exec "${NS2}" sysctl -qw net.ipv6.conf.all.forwarding=1 + ip -netns "${NS1}" route add 2001:db8::100/128 via 2001:db8::10 + ip -netns "${NS2}" route add 2001:db8::103/128 via 2001:db8::33 +} + +setup_overlay_mpls() +{ + # Add specific overlay IP addresses, routed over MPLS + ip -netns "${NS0}" address add 2001:db8::200/128 dev lo + ip -netns "${NS3}" address add 2001:db8::203/128 dev lo + ip -netns "${NS0}" route add 2001:db8::203/128 src 2001:db8::200 encap mpls 203 via 2001:db8::11 + ip -netns "${NS3}" route add 2001:db8::200/128 src 2001:db8::203 encap mpls 200 via 2001:db8::32 + + # Route the MPLS packets in the intermediate namespaces + # (used after bareudp decapsulation) + ip netns exec "${NS1}" sysctl -qw net.mpls.platform_labels=256 + ip netns exec "${NS2}" sysctl -qw net.mpls.platform_labels=256 + ip -netns "${NS1}" -family mpls route add 200 via inet6 2001:db8::10 + ip -netns "${NS2}" -family mpls route add 203 via inet6 2001:db8::33 +} + +# Run "ping" from NS0 and print the result +# +# Parameters: +# +# * $1: the variant of ping to use (normally either "ping" or "ping6"), +# * $2: the IP address to ping, +# * $3: a human readable description of the purpose of the test. +# +# If the test fails and PAUSE_ON_FAIL is active, the user is given the +# possibility to continue with the next test or to quit immediately. +# +ping_test_one() +{ + local PING="$1"; readonly PING + local IP="$2"; readonly IP + local MSG="$3"; readonly MSG + local RET + + printf "TEST: %-60s " "${MSG}" + + set +e + ip netns exec "${NS0}" "${PING}" -w 5 -c 1 "${IP}" > /dev/null 2>&1 + RET=$? + set -e + + if [ "${RET}" -eq 0 ]; then + printf "[ OK ]\n" + else + ERR=1 + printf "[FAIL]\n" + if [ "${PAUSE_ON_FAIL}" = "yes" ]; then + printf "\nHit enter to continue, 'q' to quit\n" + read a + if [ "$a" = "q" ]; then + exit 1 + fi + fi + fi +} + +# Run reachability tests +# +# Parameters: +# +# * $1: human readable string describing the underlay protocol. +# +# $IPV4, $IPV6, $MPLS_UC and $MULTIPROTO are inherited from the calling +# function. +# +ping_test() +{ + local UNDERLAY="$1"; readonly UNDERLAY + local MODE + local MSG + + if [ "${MULTIPROTO}" = "multiproto" ]; then + MODE=" (multiproto mode)" + else + MODE="" + fi + + if [ $IPV4 ]; then + ping_test_one "ping" "192.0.2.103" "IPv4 packets over ${UNDERLAY}${MODE}" + fi + if [ $IPV6 ]; then + ping_test_one "${PING6}" "2001:db8::103" "IPv6 packets over ${UNDERLAY}${MODE}" + fi + if [ $MPLS_UC ]; then + ping_test_one "${PING6}" "2001:db8::203" "Unicast MPLS packets over ${UNDERLAY}${MODE}" + fi +} + +# Set up a bareudp overlay and run reachability tests over IPv4 and IPv6 +# +# Parameters: +# +# * $1: the packet type (protocol) to be handled by bareudp, +# * $2: a flag to activate or deactivate bareudp's "multiproto" mode. +# +test_overlay() +{ + local ETHERTYPE="$1"; readonly ETHERTYPE + local MULTIPROTO="$2"; readonly MULTIPROTO + local IPV4 + local IPV6 + local MPLS_UC + + case "${ETHERTYPE}" in + "ipv4") + IPV4="ipv4" + if [ "${MULTIPROTO}" = "multiproto" ]; then + IPV6="ipv6" + else + IPV6="" + fi + MPLS_UC="" + ;; + "ipv6") + IPV6="ipv6" + IPV4="" + MPLS_UC="" + ;; + "mpls_uc") + MPLS_UC="mpls_uc" + IPV4="" + IPV6="" + ;; + *) + exit 1 + ;; + esac + readonly IPV4 + readonly IPV6 + readonly MPLS_UC + + # Create the bareudp devices in the intermediate namespaces + ip -netns "${NS1}" link add name bareudp_ns1 up type bareudp dstport 6635 ethertype "${ETHERTYPE}" "${MULTIPROTO}" + ip -netns "${NS2}" link add name bareudp_ns2 up type bareudp dstport 6635 ethertype "${ETHERTYPE}" "${MULTIPROTO}" + + # IPv4 over UDPv4 + if [ $IPV4 ]; then + # Encapsulation instructions for bareudp over IPv4 + tc -netns "${NS1}" filter add dev veth10 ingress protocol ipv4 \ + flower dst_ip 192.0.2.103/32 \ + action tunnel_key set src_ip 192.0.2.21 dst_ip 192.0.2.22 id 0 \ + action mirred egress redirect dev bareudp_ns1 + tc -netns "${NS2}" filter add dev veth23 ingress protocol ipv4 \ + flower dst_ip 192.0.2.100/32 \ + action tunnel_key set src_ip 192.0.2.22 dst_ip 192.0.2.21 id 0 \ + action mirred egress redirect dev bareudp_ns2 + fi + + # IPv6 over UDPv4 + if [ $IPV6 ]; then + # Encapsulation instructions for bareudp over IPv4 + tc -netns "${NS1}" filter add dev veth10 ingress protocol ipv6 \ + flower dst_ip 2001:db8::103/128 \ + action tunnel_key set src_ip 192.0.2.21 dst_ip 192.0.2.22 id 0 \ + action mirred egress redirect dev bareudp_ns1 + tc -netns "${NS2}" filter add dev veth23 ingress protocol ipv6 \ + flower dst_ip 2001:db8::100/128 \ + action tunnel_key set src_ip 192.0.2.22 dst_ip 192.0.2.21 id 0 \ + action mirred egress redirect dev bareudp_ns2 + fi + + # MPLS (unicast) over UDPv4 + if [ $MPLS_UC ]; then + ip netns exec "${NS1}" sysctl -qw net.mpls.conf.bareudp_ns1.input=1 + ip netns exec "${NS2}" sysctl -qw net.mpls.conf.bareudp_ns2.input=1 + + # Encapsulation instructions for bareudp over IPv4 + tc -netns "${NS1}" filter add dev veth10 ingress protocol mpls_uc \ + flower mpls_label 203 \ + action tunnel_key set src_ip 192.0.2.21 dst_ip 192.0.2.22 id 0 \ + action mirred egress redirect dev bareudp_ns1 + tc -netns "${NS2}" filter add dev veth23 ingress protocol mpls_uc \ + flower mpls_label 200 \ + action tunnel_key set src_ip 192.0.2.22 dst_ip 192.0.2.21 id 0 \ + action mirred egress redirect dev bareudp_ns2 + fi + + # Test IPv4 underlay + ping_test "UDPv4" + + # Cleanup bareudp encapsulation instructions, as they were specific to + # the IPv4 underlay, before setting up and testing the IPv6 underlay + tc -netns "${NS1}" filter delete dev veth10 ingress + tc -netns "${NS2}" filter delete dev veth23 ingress + + # IPv4 over UDPv6 + if [ $IPV4 ]; then + # New encapsulation instructions for bareudp over IPv6 + tc -netns "${NS1}" filter add dev veth10 ingress protocol ipv4 \ + flower dst_ip 192.0.2.103/32 \ + action tunnel_key set src_ip 2001:db8::21 dst_ip 2001:db8::22 id 0 \ + action mirred egress redirect dev bareudp_ns1 + tc -netns "${NS2}" filter add dev veth23 ingress protocol ipv4 \ + flower dst_ip 192.0.2.100/32 \ + action tunnel_key set src_ip 2001:db8::22 dst_ip 2001:db8::21 id 0 \ + action mirred egress redirect dev bareudp_ns2 + fi + + # IPv6 over UDPv6 + if [ $IPV6 ]; then + # New encapsulation instructions for bareudp over IPv6 + tc -netns "${NS1}" filter add dev veth10 ingress protocol ipv6 \ + flower dst_ip 2001:db8::103/128 \ + action tunnel_key set src_ip 2001:db8::21 dst_ip 2001:db8::22 id 0 \ + action mirred egress redirect dev bareudp_ns1 + tc -netns "${NS2}" filter add dev veth23 ingress protocol ipv6 \ + flower dst_ip 2001:db8::100/128 \ + action tunnel_key set src_ip 2001:db8::22 dst_ip 2001:db8::21 id 0 \ + action mirred egress redirect dev bareudp_ns2 + fi + + # MPLS (unicast) over UDPv6 + if [ $MPLS_UC ]; then + # New encapsulation instructions for bareudp over IPv6 + tc -netns "${NS1}" filter add dev veth10 ingress protocol mpls_uc \ + flower mpls_label 203 \ + action tunnel_key set src_ip 2001:db8::21 dst_ip 2001:db8::22 id 0 \ + action mirred egress redirect dev bareudp_ns1 + tc -netns "${NS2}" filter add dev veth23 ingress protocol mpls_uc \ + flower mpls_label 200 \ + action tunnel_key set src_ip 2001:db8::22 dst_ip 2001:db8::21 id 0 \ + action mirred egress redirect dev bareudp_ns2 + fi + + # Test IPv6 underlay + ping_test "UDPv6" + + tc -netns "${NS1}" filter delete dev veth10 ingress + tc -netns "${NS2}" filter delete dev veth23 ingress + ip -netns "${NS1}" link delete bareudp_ns1 + ip -netns "${NS2}" link delete bareudp_ns2 +} + +check_features() +{ + ip link help 2>&1 | grep -q bareudp + if [ $? -ne 0 ]; then + echo "Missing bareudp support in iproute2" >&2 + exit_cleanup + fi + + # Use ping6 on systems where ping doesn't handle IPv6 + ping -w 1 -c 1 ::1 > /dev/null 2>&1 || PING6="ping6" +} + +usage() +{ + echo "Usage: $0 [-p]" + exit 1 +} + +while getopts :p o +do + case $o in + p) PAUSE_ON_FAIL="yes";; + *) usage;; + esac +done + +check_features + +# Create namespaces before setting up the exit trap. +# Otherwise, exit_cleanup_all() could delete namespaces that were not created +# by this script. +create_namespaces + +set -e +trap exit_cleanup_all EXIT + +setup_underlay +setup_overlay_ipv4 +setup_overlay_ipv6 +setup_overlay_mpls + +test_overlay ipv4 nomultiproto +test_overlay ipv6 nomultiproto +test_overlay ipv4 multiproto +test_overlay mpls_uc nomultiproto + +if [ "${ERR}" -eq 1 ]; then + echo "Some tests failed." >&2 +else + ERR=0 +fi diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index 4d5df8e1eee7..614d5477365a 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -34,3 +34,10 @@ CONFIG_TRACEPOINTS=y CONFIG_NET_DROP_MONITOR=m CONFIG_NETDEVSIM=m CONFIG_NET_FOU=m +CONFIG_MPLS_ROUTING=m +CONFIG_MPLS_IPTUNNEL=m +CONFIG_NET_SCH_INGRESS=m +CONFIG_NET_CLS_FLOWER=m +CONFIG_NET_ACT_TUNNEL_KEY=m +CONFIG_NET_ACT_MIRRED=m +CONFIG_BAREUDP=m diff --git a/tools/testing/selftests/net/forwarding/bridge_igmp.sh b/tools/testing/selftests/net/forwarding/bridge_igmp.sh index 88d2472ba151..675eff45b037 100755 --- a/tools/testing/selftests/net/forwarding/bridge_igmp.sh +++ b/tools/testing/selftests/net/forwarding/bridge_igmp.sh @@ -1,11 +1,37 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -ALL_TESTS="reportleave_test" +ALL_TESTS="v2reportleave_test v3include_test v3inc_allow_test v3inc_is_include_test \ + v3inc_is_exclude_test v3inc_to_exclude_test v3exc_allow_test v3exc_is_include_test \ + v3exc_is_exclude_test v3exc_to_exclude_test v3inc_block_test v3exc_block_test \ + v3exc_timeout_test v3star_ex_auto_add_test" NUM_NETIFS=4 CHECK_TC="yes" TEST_GROUP="239.10.10.10" TEST_GROUP_MAC="01:00:5e:0a:0a:0a" + +ALL_GROUP="224.0.0.1" +ALL_MAC="01:00:5e:00:00:01" + +# IGMPv3 is_in report: grp 239.10.10.10 is_include 192.0.2.1,192.0.2.2,192.0.2.3 +MZPKT_IS_INC="22:00:9d:de:00:00:00:01:01:00:00:03:ef:0a:0a:0a:c0:00:02:01:c0:00:02:02:c0:00:02:03" +# IGMPv3 is_in report: grp 239.10.10.10 is_include 192.0.2.10,192.0.2.11,192.0.2.12 +MZPKT_IS_INC2="22:00:9d:c3:00:00:00:01:01:00:00:03:ef:0a:0a:0a:c0:00:02:0a:c0:00:02:0b:c0:00:02:0c" +# IGMPv3 is_in report: grp 239.10.10.10 is_include 192.0.2.20,192.0.2.30 +MZPKT_IS_INC3="22:00:5f:b4:00:00:00:01:01:00:00:02:ef:0a:0a:0a:c0:00:02:14:c0:00:02:1e" +# IGMPv3 allow report: grp 239.10.10.10 allow 192.0.2.10,192.0.2.11,192.0.2.12 +MZPKT_ALLOW="22:00:99:c3:00:00:00:01:05:00:00:03:ef:0a:0a:0a:c0:00:02:0a:c0:00:02:0b:c0:00:02:0c" +# IGMPv3 allow report: grp 239.10.10.10 allow 192.0.2.20,192.0.2.30 +MZPKT_ALLOW2="22:00:5b:b4:00:00:00:01:05:00:00:02:ef:0a:0a:0a:c0:00:02:14:c0:00:02:1e" +# IGMPv3 is_ex report: grp 239.10.10.10 is_exclude 192.0.2.1,192.0.2.2,192.0.2.20,192.0.2.21 +MZPKT_IS_EXC="22:00:da:b6:00:00:00:01:02:00:00:04:ef:0a:0a:0a:c0:00:02:01:c0:00:02:02:c0:00:02:14:c0:00:02:15" +# IGMPv3 is_ex report: grp 239.10.10.10 is_exclude 192.0.2.20,192.0.2.30 +MZPKT_IS_EXC2="22:00:5e:b4:00:00:00:01:02:00:00:02:ef:0a:0a:0a:c0:00:02:14:c0:00:02:1e" +# IGMPv3 to_ex report: grp 239.10.10.10 to_exclude 192.0.2.1,192.0.2.20,192.0.2.30 +MZPKT_TO_EXC="22:00:9a:b1:00:00:00:01:04:00:00:03:ef:0a:0a:0a:c0:00:02:01:c0:00:02:14:c0:00:02:1e" +# IGMPv3 block report: grp 239.10.10.10 block 192.0.2.1,192.0.2.20,192.0.2.30 +MZPKT_BLOCK="22:00:98:b1:00:00:00:01:06:00:00:03:ef:0a:0a:0a:c0:00:02:01:c0:00:02:14:c0:00:02:1e" + source lib.sh h1_create() @@ -79,38 +105,7 @@ cleanup() vrf_cleanup } -# return 0 if the packet wasn't seen on host2_if or 1 if it was -mcast_packet_test() -{ - local mac=$1 - local ip=$2 - local host1_if=$3 - local host2_if=$4 - local seen=0 - - # Add an ACL on `host2_if` which will tell us whether the packet - # was received by it or not. - tc qdisc add dev $host2_if ingress - tc filter add dev $host2_if ingress protocol ip pref 1 handle 101 \ - flower dst_mac $mac action drop - - $MZ $host1_if -c 1 -p 64 -b $mac -B $ip -t udp "dp=4096,sp=2048" -q - sleep 1 - - tc -j -s filter show dev $host2_if ingress \ - | jq -e ".[] | select(.options.handle == 101) \ - | select(.options.actions[0].stats.packets == 1)" &> /dev/null - if [[ $? -eq 0 ]]; then - seen=1 - fi - - tc filter del dev $host2_if ingress protocol ip pref 1 handle 101 flower - tc qdisc del dev $host2_if ingress - - return $seen -} - -reportleave_test() +v2reportleave_test() { RET=0 ip address add dev $h2 $TEST_GROUP/32 autojoin @@ -118,12 +113,12 @@ reportleave_test() sleep 5 bridge mdb show dev br0 | grep $TEST_GROUP 1>/dev/null - check_err $? "Report didn't create mdb entry for $TEST_GROUP" + check_err $? "IGMPv2 report didn't create mdb entry for $TEST_GROUP" - mcast_packet_test $TEST_GROUP_MAC $TEST_GROUP $h1 $h2 + mcast_packet_test $TEST_GROUP_MAC 192.0.2.1 $TEST_GROUP $h1 $h2 check_fail $? "Traffic to $TEST_GROUP wasn't forwarded" - log_test "IGMP report $TEST_GROUP" + log_test "IGMPv2 report $TEST_GROUP" RET=0 bridge mdb show dev br0 | grep $TEST_GROUP 1>/dev/null @@ -136,10 +131,424 @@ reportleave_test() bridge mdb show dev br0 | grep $TEST_GROUP 1>/dev/null check_fail $? "Leave didn't delete mdb entry for $TEST_GROUP" - mcast_packet_test $TEST_GROUP_MAC $TEST_GROUP $h1 $h2 + mcast_packet_test $TEST_GROUP_MAC 192.0.2.1 $TEST_GROUP $h1 $h2 check_err $? "Traffic to $TEST_GROUP was forwarded without mdb entry" - log_test "IGMP leave $TEST_GROUP" + log_test "IGMPv2 leave $TEST_GROUP" +} + +v3include_prepare() +{ + local host1_if=$1 + local mac=$2 + local group=$3 + local X=("192.0.2.1" "192.0.2.2" "192.0.2.3") + + ip link set dev br0 type bridge mcast_igmp_version 3 + check_err $? "Could not change bridge IGMP version to 3" + + $MZ $host1_if -b $mac -c 1 -B $group -t ip "proto=2,p=$MZPKT_IS_INC" -q + sleep 1 + bridge -j -d -s mdb show dev br0 \ + | jq -e ".[].mdb[] | \ + select(.grp == \"$TEST_GROUP\" and .source_list != null)" &>/dev/null + check_err $? "Missing *,G entry with source list" + bridge -j -d -s mdb show dev br0 \ + | jq -e ".[].mdb[] | \ + select(.grp == \"$TEST_GROUP\" and \ + .source_list != null and .filter_mode == \"include\")" &>/dev/null + check_err $? "Wrong *,G entry filter mode" + brmcast_check_sg_entries "is_include" "${X[@]}" +} + +v3exclude_prepare() +{ + local host1_if=$1 + local mac=$2 + local group=$3 + local pkt=$4 + local X=("192.0.2.1" "192.0.2.2") + local Y=("192.0.2.20" "192.0.2.21") + + v3include_prepare $host1_if $mac $group + + $MZ $host1_if -c 1 -b $mac -B $group -t ip "proto=2,p=$MZPKT_IS_EXC" -q + sleep 1 + bridge -j -d -s mdb show dev br0 \ + | jq -e ".[].mdb[] | \ + select(.grp == \"$TEST_GROUP\" and \ + .source_list != null and .filter_mode == \"exclude\")" &>/dev/null + check_err $? "Wrong *,G entry filter mode" + + brmcast_check_sg_entries "is_exclude" "${X[@]}" "${Y[@]}" + + brmcast_check_sg_state 0 "${X[@]}" + brmcast_check_sg_state 1 "${Y[@]}" + + bridge -j -d -s mdb show dev br0 \ + | jq -e ".[].mdb[] | \ + select(.grp == \"$TEST_GROUP\" and \ + .source_list != null and + .source_list[].address == \"192.0.2.3\")" &>/dev/null + check_fail $? "Wrong *,G entry source list, 192.0.2.3 entry still exists" +} + +v3cleanup() +{ + local port=$1 + local group=$2 + + bridge mdb del dev br0 port $port grp $group + ip link set dev br0 type bridge mcast_igmp_version 2 +} + +v3include_test() +{ + RET=0 + local X=("192.0.2.1" "192.0.2.2" "192.0.2.3") + + v3include_prepare $h1 $ALL_MAC $ALL_GROUP + + brmcast_check_sg_state 0 "${X[@]}" + + brmcast_check_sg_fwding 1 "${X[@]}" + brmcast_check_sg_fwding 0 "192.0.2.100" + + log_test "IGMPv3 report $TEST_GROUP is_include" + + v3cleanup $swp1 $TEST_GROUP +} + +v3inc_allow_test() +{ + RET=0 + local X=("192.0.2.10" "192.0.2.11" "192.0.2.12") + + v3include_prepare $h1 $ALL_MAC $ALL_GROUP + + $MZ $h1 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_ALLOW" -q + sleep 1 + brmcast_check_sg_entries "allow" "${X[@]}" + + brmcast_check_sg_state 0 "${X[@]}" + + brmcast_check_sg_fwding 1 "${X[@]}" + brmcast_check_sg_fwding 0 "192.0.2.100" + + log_test "IGMPv3 report $TEST_GROUP include -> allow" + + v3cleanup $swp1 $TEST_GROUP +} + +v3inc_is_include_test() +{ + RET=0 + local X=("192.0.2.10" "192.0.2.11" "192.0.2.12") + + v3include_prepare $h1 $ALL_MAC $ALL_GROUP + + $MZ $h1 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_IS_INC2" -q + sleep 1 + brmcast_check_sg_entries "is_include" "${X[@]}" + + brmcast_check_sg_state 0 "${X[@]}" + + brmcast_check_sg_fwding 1 "${X[@]}" + brmcast_check_sg_fwding 0 "192.0.2.100" + + log_test "IGMPv3 report $TEST_GROUP include -> is_include" + + v3cleanup $swp1 $TEST_GROUP +} + +v3inc_is_exclude_test() +{ + RET=0 + + v3exclude_prepare $h1 $ALL_MAC $ALL_GROUP + + brmcast_check_sg_fwding 1 "${X[@]}" 192.0.2.100 + brmcast_check_sg_fwding 0 "${Y[@]}" + + log_test "IGMPv3 report $TEST_GROUP include -> is_exclude" + + v3cleanup $swp1 $TEST_GROUP +} + +v3inc_to_exclude_test() +{ + RET=0 + local X=("192.0.2.1") + local Y=("192.0.2.20" "192.0.2.30") + + v3include_prepare $h1 $ALL_MAC $ALL_GROUP + + ip link set dev br0 type bridge mcast_last_member_interval 500 + check_err $? "Could not change mcast_last_member_interval to 5s" + + $MZ $h1 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_TO_EXC" -q + sleep 1 + bridge -j -d -s mdb show dev br0 \ + | jq -e ".[].mdb[] | \ + select(.grp == \"$TEST_GROUP\" and \ + .source_list != null and .filter_mode == \"exclude\")" &>/dev/null + check_err $? "Wrong *,G entry filter mode" + + brmcast_check_sg_entries "to_exclude" "${X[@]}" "${Y[@]}" + + brmcast_check_sg_state 0 "${X[@]}" + brmcast_check_sg_state 1 "${Y[@]}" + + bridge -j -d -s mdb show dev br0 \ + | jq -e ".[].mdb[] | \ + select(.grp == \"$TEST_GROUP\" and \ + .source_list != null and + .source_list[].address == \"192.0.2.2\")" &>/dev/null + check_fail $? "Wrong *,G entry source list, 192.0.2.2 entry still exists" + bridge -j -d -s mdb show dev br0 \ + | jq -e ".[].mdb[] | \ + select(.grp == \"$TEST_GROUP\" and \ + .source_list != null and + .source_list[].address == \"192.0.2.21\")" &>/dev/null + check_fail $? "Wrong *,G entry source list, 192.0.2.21 entry still exists" + + brmcast_check_sg_fwding 1 "${X[@]}" 192.0.2.100 + brmcast_check_sg_fwding 0 "${Y[@]}" + + log_test "IGMPv3 report $TEST_GROUP include -> to_exclude" + + ip link set dev br0 type bridge mcast_last_member_interval 100 + + v3cleanup $swp1 $TEST_GROUP +} + +v3exc_allow_test() +{ + RET=0 + local X=("192.0.2.1" "192.0.2.2" "192.0.2.20" "192.0.2.30") + local Y=("192.0.2.21") + + v3exclude_prepare $h1 $ALL_MAC $ALL_GROUP + + $MZ $h1 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_ALLOW2" -q + sleep 1 + brmcast_check_sg_entries "allow" "${X[@]}" "${Y[@]}" + + brmcast_check_sg_state 0 "${X[@]}" + brmcast_check_sg_state 1 "${Y[@]}" + + brmcast_check_sg_fwding 1 "${X[@]}" 192.0.2.100 + brmcast_check_sg_fwding 0 "${Y[@]}" + + log_test "IGMPv3 report $TEST_GROUP exclude -> allow" + + v3cleanup $swp1 $TEST_GROUP +} + +v3exc_is_include_test() +{ + RET=0 + local X=("192.0.2.1" "192.0.2.2" "192.0.2.20" "192.0.2.30") + local Y=("192.0.2.21") + + v3exclude_prepare $h1 $ALL_MAC $ALL_GROUP + + $MZ $h1 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_IS_INC3" -q + sleep 1 + brmcast_check_sg_entries "is_include" "${X[@]}" "${Y[@]}" + + brmcast_check_sg_state 0 "${X[@]}" + brmcast_check_sg_state 1 "${Y[@]}" + + brmcast_check_sg_fwding 1 "${X[@]}" 192.0.2.100 + brmcast_check_sg_fwding 0 "${Y[@]}" + + log_test "IGMPv3 report $TEST_GROUP exclude -> is_include" + + v3cleanup $swp1 $TEST_GROUP +} + +v3exc_is_exclude_test() +{ + RET=0 + local X=("192.0.2.30") + local Y=("192.0.2.20") + + v3exclude_prepare $h1 $ALL_MAC $ALL_GROUP + + $MZ $h1 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_IS_EXC2" -q + sleep 1 + brmcast_check_sg_entries "is_exclude" "${X[@]}" "${Y[@]}" + + brmcast_check_sg_state 0 "${X[@]}" + brmcast_check_sg_state 1 "${Y[@]}" + + brmcast_check_sg_fwding 1 "${X[@]}" 192.0.2.100 + brmcast_check_sg_fwding 0 "${Y[@]}" + + log_test "IGMPv3 report $TEST_GROUP exclude -> is_exclude" + + v3cleanup $swp1 $TEST_GROUP +} + +v3exc_to_exclude_test() +{ + RET=0 + local X=("192.0.2.1" "192.0.2.30") + local Y=("192.0.2.20") + + v3exclude_prepare $h1 $ALL_MAC $ALL_GROUP + + ip link set dev br0 type bridge mcast_last_member_interval 500 + check_err $? "Could not change mcast_last_member_interval to 5s" + + $MZ $h1 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_TO_EXC" -q + sleep 1 + brmcast_check_sg_entries "to_exclude" "${X[@]}" "${Y[@]}" + + brmcast_check_sg_state 0 "${X[@]}" + brmcast_check_sg_state 1 "${Y[@]}" + + brmcast_check_sg_fwding 1 "${X[@]}" 192.0.2.100 + brmcast_check_sg_fwding 0 "${Y[@]}" + + log_test "IGMPv3 report $TEST_GROUP exclude -> to_exclude" + + ip link set dev br0 type bridge mcast_last_member_interval 100 + + v3cleanup $swp1 $TEST_GROUP +} + +v3inc_block_test() +{ + RET=0 + local X=("192.0.2.2" "192.0.2.3") + + v3include_prepare $h1 $ALL_MAC $ALL_GROUP + + $MZ $h1 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_BLOCK" -q + # make sure the lowered timers have expired (by default 2 seconds) + sleep 3 + brmcast_check_sg_entries "block" "${X[@]}" + + brmcast_check_sg_state 0 "${X[@]}" + + bridge -j -d -s mdb show dev br0 \ + | jq -e ".[].mdb[] | \ + select(.grp == \"$TEST_GROUP\" and \ + .source_list != null and + .source_list[].address == \"192.0.2.1\")" &>/dev/null + check_fail $? "Wrong *,G entry source list, 192.0.2.1 entry still exists" + + brmcast_check_sg_fwding 1 "${X[@]}" + brmcast_check_sg_fwding 0 "192.0.2.100" + + log_test "IGMPv3 report $TEST_GROUP include -> block" + + v3cleanup $swp1 $TEST_GROUP +} + +v3exc_block_test() +{ + RET=0 + local X=("192.0.2.1" "192.0.2.2" "192.0.2.30") + local Y=("192.0.2.20" "192.0.2.21") + + v3exclude_prepare $h1 $ALL_MAC $ALL_GROUP + + ip link set dev br0 type bridge mcast_last_member_interval 500 + check_err $? "Could not change mcast_last_member_interval to 5s" + + $MZ $h1 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_BLOCK" -q + sleep 1 + brmcast_check_sg_entries "block" "${X[@]}" "${Y[@]}" + + brmcast_check_sg_state 0 "${X[@]}" + brmcast_check_sg_state 1 "${Y[@]}" + + brmcast_check_sg_fwding 1 "${X[@]}" 192.0.2.100 + brmcast_check_sg_fwding 0 "${Y[@]}" + + log_test "IGMPv3 report $TEST_GROUP exclude -> block" + + ip link set dev br0 type bridge mcast_last_member_interval 100 + + v3cleanup $swp1 $TEST_GROUP +} + +v3exc_timeout_test() +{ + RET=0 + local X=("192.0.2.20" "192.0.2.30") + + # GMI should be 3 seconds + ip link set dev br0 type bridge mcast_query_interval 100 mcast_query_response_interval 100 + + v3exclude_prepare $h1 $ALL_MAC $ALL_GROUP + ip link set dev br0 type bridge mcast_query_interval 500 mcast_query_response_interval 500 + $MZ $h1 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_ALLOW2" -q + sleep 3 + bridge -j -d -s mdb show dev br0 \ + | jq -e ".[].mdb[] | \ + select(.grp == \"$TEST_GROUP\" and \ + .source_list != null and .filter_mode == \"include\")" &>/dev/null + check_err $? "Wrong *,G entry filter mode" + + bridge -j -d -s mdb show dev br0 \ + | jq -e ".[].mdb[] | \ + select(.grp == \"$TEST_GROUP\" and \ + .source_list != null and + .source_list[].address == \"192.0.2.1\")" &>/dev/null + check_fail $? "Wrong *,G entry source list, 192.0.2.1 entry still exists" + bridge -j -d -s mdb show dev br0 \ + | jq -e ".[].mdb[] | \ + select(.grp == \"$TEST_GROUP\" and \ + .source_list != null and + .source_list[].address == \"192.0.2.2\")" &>/dev/null + check_fail $? "Wrong *,G entry source list, 192.0.2.2 entry still exists" + + brmcast_check_sg_entries "allow" "${X[@]}" + + brmcast_check_sg_state 0 "${X[@]}" + + brmcast_check_sg_fwding 1 "${X[@]}" + brmcast_check_sg_fwding 0 192.0.2.100 + + log_test "IGMPv3 group $TEST_GROUP exclude timeout" + + ip link set dev br0 type bridge mcast_query_interval 12500 \ + mcast_query_response_interval 1000 + + v3cleanup $swp1 $TEST_GROUP +} + +v3star_ex_auto_add_test() +{ + RET=0 + + v3exclude_prepare $h1 $ALL_MAC $ALL_GROUP + + $MZ $h2 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_IS_INC" -q + sleep 1 + bridge -j -d -s mdb show dev br0 \ + | jq -e ".[].mdb[] | \ + select(.grp == \"$TEST_GROUP\" and .src == \"192.0.2.3\" and \ + .port == \"$swp1\")" &>/dev/null + check_err $? "S,G entry for *,G port doesn't exist" + + bridge -j -d -s mdb show dev br0 \ + | jq -e ".[].mdb[] | \ + select(.grp == \"$TEST_GROUP\" and .src == \"192.0.2.3\" and \ + .port == \"$swp1\" and \ + .flags[] == \"added_by_star_ex\")" &>/dev/null + check_err $? "Auto-added S,G entry doesn't have added_by_star_ex flag" + + brmcast_check_sg_fwding 1 192.0.2.3 + + log_test "IGMPv3 S,G port entry automatic add to a *,G port" + + v3cleanup $swp1 $TEST_GROUP + v3cleanup $swp2 $TEST_GROUP } trap cleanup EXIT diff --git a/tools/testing/selftests/net/forwarding/bridge_mld.sh b/tools/testing/selftests/net/forwarding/bridge_mld.sh new file mode 100755 index 000000000000..ffdcfa87ca2b --- /dev/null +++ b/tools/testing/selftests/net/forwarding/bridge_mld.sh @@ -0,0 +1,558 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +ALL_TESTS="mldv2include_test mldv2inc_allow_test mldv2inc_is_include_test mldv2inc_is_exclude_test \ + mldv2inc_to_exclude_test mldv2exc_allow_test mldv2exc_is_include_test \ + mldv2exc_is_exclude_test mldv2exc_to_exclude_test mldv2inc_block_test \ + mldv2exc_block_test mldv2exc_timeout_test mldv2star_ex_auto_add_test" +NUM_NETIFS=4 +CHECK_TC="yes" +TEST_GROUP="ff02::cc" +TEST_GROUP_MAC="33:33:00:00:00:cc" + +# MLDv2 is_in report: grp ff02::cc is_include 2001:db8:1::1,2001:db8:1::2,2001:db8:1::3 +MZPKT_IS_INC="33:33:00:00:00:01:fe:54:00:04:5e:ba:86:dd:60:0a:2d:ae:00:54:00:01:fe:80:00:\ +00:00:00:00:00:fc:54:00:ff:fe:04:5e:ba:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:01:3a:\ +00:05:02:00:00:00:00:8f:00:8e:d9:00:00:00:01:01:00:00:03:ff:02:00:00:00:00:00:00:00:00:00:\ +00:00:00:00:cc:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:01:20:01:0d:b8:00:01:00:00:00:\ +00:00:00:00:00:00:02:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:03" +# MLDv2 is_in report: grp ff02::cc is_include 2001:db8:1::10,2001:db8:1::11,2001:db8:1::12 +MZPKT_IS_INC2="33:33:00:00:00:01:fe:54:00:04:5e:ba:86:dd:60:0a:2d:ae:00:54:00:01:fe:80:00:\ +00:00:00:00:00:fc:54:00:ff:fe:04:5e:ba:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:01:3a:00:\ +05:02:00:00:00:00:8f:00:8e:ac:00:00:00:01:01:00:00:03:ff:02:00:00:00:00:00:00:00:00:00:00:00:\ +00:00:cc:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:10:20:01:0d:b8:00:01:00:00:00:00:00:00:\ +00:00:00:11:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:12" +# MLDv2 is_in report: grp ff02::cc is_include 2001:db8:1::20,2001:db8:1::30 +MZPKT_IS_INC3="33:33:00:00:00:01:fe:54:00:04:5e:ba:86:dd:60:0a:2d:ae:00:44:00:01:fe:80:00:00:00:\ +00:00:00:fc:54:00:ff:fe:04:5e:ba:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:01:3a:00:05:02:00:\ +00:00:00:8f:00:bc:5a:00:00:00:01:01:00:00:02:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:cc:20:\ +01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:20:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:30" +# MLDv2 allow report: grp ff02::cc allow 2001:db8:1::10,2001:db8:1::11,2001:db8:1::12 +MZPKT_ALLOW="33:33:00:00:00:01:fe:54:00:04:5e:ba:86:dd:60:0a:2d:ae:00:54:00:01:fe:80:00:00:\ +00:00:00:00:fc:54:00:ff:fe:04:5e:ba:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:01:3a:00:05:\ +02:00:00:00:00:8f:00:8a:ac:00:00:00:01:05:00:00:03:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:\ +00:cc:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:10:20:01:0d:b8:00:01:00:00:00:00:00:00:00:\ +00:00:11:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:12" +# MLDv2 allow report: grp ff02::cc allow 2001:db8:1::20,2001:db8:1::30 +MZPKT_ALLOW2="33:33:00:00:00:01:fe:54:00:04:5e:ba:86:dd:60:0a:2d:ae:00:44:00:01:fe:80:00:00:00:\ +00:00:00:fc:54:00:ff:fe:04:5e:ba:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:01:3a:00:05:02:00:\ +00:00:00:8f:00:b8:5a:00:00:00:01:05:00:00:02:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:cc:20:\ +01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:20:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:30" +# MLDv2 is_ex report: grp ff02::cc is_exclude 2001:db8:1::1,2001:db8:1::2,2001:db8:1::20,2001:db8:1::21 +MZPKT_IS_EXC="33:33:00:00:00:01:fe:54:00:04:5e:ba:86:dd:60:0a:2d:ae:00:64:00:01:fe:80:00:00:00:\ +00:00:00:fc:54:00:ff:fe:04:5e:ba:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:01:3a:00:05:02:00:\ +00:00:00:8f:00:5f:d0:00:00:00:01:02:00:00:04:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:cc:20:\ +01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:01:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:02:20:\ +01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:20:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:21" +# MLDv2 is_ex report: grp ff02::cc is_exclude 2001:db8:1::20,2001:db8:1::30 +MZPKT_IS_EXC2="33:33:00:00:00:01:fe:54:00:04:5e:ba:86:dd:60:0a:2d:ae:00:44:00:01:fe:80:00:00:00:\ +00:00:00:fc:54:00:ff:fe:04:5e:ba:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:01:3a:00:05:02:00:\ +00:00:00:8f:00:bb:5a:00:00:00:01:02:00:00:02:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:cc:20:\ +01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:20:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:30" +# MLDv2 to_ex report: grp ff02::cc to_exclude 2001:db8:1::1,2001:db8:1::20,2001:db8:1::30 +MZPKT_TO_EXC="33:33:00:00:00:01:fe:54:00:04:5e:ba:86:dd:60:0a:2d:ae:00:54:00:01:fe:80:00:00:00:\ +00:00:00:fc:54:00:ff:fe:04:5e:ba:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:01:3a:00:05:02:00:\ +00:00:00:8f:00:8b:8e:00:00:00:01:04:00:00:03:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:cc:20:\ +01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:01:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:20:20:\ +01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:30" +# MLDv2 block report: grp ff02::cc block 2001:db8:1::1,2001:db8:1::20,2001:db8:1::30 +MZPKT_BLOCK="33:33:00:00:00:01:fe:54:00:04:5e:ba:86:dd:60:0a:2d:ae:00:54:00:01:fe:80:00:00:00:00:\ +00:00:fc:54:00:ff:fe:04:5e:ba:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:01:3a:00:05:02:00:00:\ +00:00:8f:00:89:8e:00:00:00:01:06:00:00:03:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:cc:20:01:\ +0d:b8:00:01:00:00:00:00:00:00:00:00:00:01:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:20:20:01:\ +0d:b8:00:01:00:00:00:00:00:00:00:00:00:30" + +source lib.sh + +h1_create() +{ + simple_if_init $h1 2001:db8:1::1/64 +} + +h1_destroy() +{ + simple_if_fini $h1 2001:db8:1::1/64 +} + +h2_create() +{ + simple_if_init $h2 2001:db8:1::2/64 +} + +h2_destroy() +{ + simple_if_fini $h2 2001:db8:1::2/64 +} + +switch_create() +{ + ip link add dev br0 type bridge mcast_snooping 1 mcast_query_response_interval 100 \ + mcast_mld_version 2 mcast_startup_query_interval 300 \ + mcast_querier 1 + + ip link set dev $swp1 master br0 + ip link set dev $swp2 master br0 + + ip link set dev br0 up + ip link set dev $swp1 up + ip link set dev $swp2 up + + # make sure a query has been generated + sleep 5 +} + +switch_destroy() +{ + ip link set dev $swp2 down + ip link set dev $swp1 down + + ip link del dev br0 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + vrf_prepare + + h1_create + h2_create + + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + + h2_destroy + h1_destroy + + vrf_cleanup +} + +mldv2include_prepare() +{ + local host1_if=$1 + local X=("2001:db8:1::1" "2001:db8:1::2" "2001:db8:1::3") + + ip link set dev br0 type bridge mcast_mld_version 2 + check_err $? "Could not change bridge MLD version to 2" + + $MZ $host1_if $MZPKT_IS_INC -q + sleep 1 + bridge -j -d -s mdb show dev br0 \ + | jq -e ".[].mdb[] | \ + select(.grp == \"$TEST_GROUP\" and .source_list != null)" &>/dev/null + check_err $? "Missing *,G entry with source list" + bridge -j -d -s mdb show dev br0 \ + | jq -e ".[].mdb[] | \ + select(.grp == \"$TEST_GROUP\" and \ + .source_list != null and .filter_mode == \"include\")" &>/dev/null + check_err $? "Wrong *,G entry filter mode" + brmcast_check_sg_entries "is_include" "${X[@]}" +} + +mldv2exclude_prepare() +{ + local host1_if=$1 + local mac=$2 + local group=$3 + local pkt=$4 + local X=("2001:db8:1::1" "2001:db8:1::2") + local Y=("2001:db8:1::20" "2001:db8:1::21") + + mldv2include_prepare $h1 + + $MZ $host1_if -c 1 $MZPKT_IS_EXC -q + sleep 1 + bridge -j -d -s mdb show dev br0 \ + | jq -e ".[].mdb[] | \ + select(.grp == \"$TEST_GROUP\" and \ + .source_list != null and .filter_mode == \"exclude\")" &>/dev/null + check_err $? "Wrong *,G entry filter mode" + + brmcast_check_sg_entries "is_exclude" "${X[@]}" "${Y[@]}" + + brmcast_check_sg_state 0 "${X[@]}" + brmcast_check_sg_state 1 "${Y[@]}" + + bridge -j -d -s mdb show dev br0 \ + | jq -e ".[].mdb[] | \ + select(.grp == \"$TEST_GROUP\" and \ + .source_list != null and + .source_list[].address == \"2001:db8:1::3\")" &>/dev/null + check_fail $? "Wrong *,G entry source list, 2001:db8:1::3 entry still exists" +} + +mldv2cleanup() +{ + local port=$1 + + bridge mdb del dev br0 port $port grp $TEST_GROUP + ip link set dev br0 type bridge mcast_mld_version 1 +} + +mldv2include_test() +{ + RET=0 + local X=("2001:db8:1::1" "2001:db8:1::2" "2001:db8:1::3") + + mldv2include_prepare $h1 + + brmcast_check_sg_state 0 "${X[@]}" + + brmcast_check_sg_fwding 1 "${X[@]}" + brmcast_check_sg_fwding 0 "2001:db8:1::100" + + log_test "MLDv2 report $TEST_GROUP is_include" + + mldv2cleanup $swp1 +} + +mldv2inc_allow_test() +{ + RET=0 + local X=("2001:db8:1::10" "2001:db8:1::11" "2001:db8:1::12") + + mldv2include_prepare $h1 + + $MZ $h1 -c 1 $MZPKT_ALLOW -q + sleep 1 + brmcast_check_sg_entries "allow" "${X[@]}" + + brmcast_check_sg_state 0 "${X[@]}" + + brmcast_check_sg_fwding 1 "${X[@]}" + brmcast_check_sg_fwding 0 "2001:db8:1::100" + + log_test "MLDv2 report $TEST_GROUP include -> allow" + + mldv2cleanup $swp1 +} + +mldv2inc_is_include_test() +{ + RET=0 + local X=("2001:db8:1::10" "2001:db8:1::11" "2001:db8:1::12") + + mldv2include_prepare $h1 + + $MZ $h1 -c 1 $MZPKT_IS_INC2 -q + sleep 1 + brmcast_check_sg_entries "is_include" "${X[@]}" + + brmcast_check_sg_state 0 "${X[@]}" + + brmcast_check_sg_fwding 1 "${X[@]}" + brmcast_check_sg_fwding 0 "2001:db8:1::100" + + log_test "MLDv2 report $TEST_GROUP include -> is_include" + + mldv2cleanup $swp1 +} + +mldv2inc_is_exclude_test() +{ + RET=0 + + mldv2exclude_prepare $h1 + + brmcast_check_sg_fwding 1 "${X[@]}" 2001:db8:1::100 + brmcast_check_sg_fwding 0 "${Y[@]}" + + log_test "MLDv2 report $TEST_GROUP include -> is_exclude" + + mldv2cleanup $swp1 +} + +mldv2inc_to_exclude_test() +{ + RET=0 + local X=("2001:db8:1::1") + local Y=("2001:db8:1::20" "2001:db8:1::30") + + mldv2include_prepare $h1 + + ip link set dev br0 type bridge mcast_last_member_interval 500 + check_err $? "Could not change mcast_last_member_interval to 5s" + + $MZ $h1 -c 1 $MZPKT_TO_EXC -q + sleep 1 + bridge -j -d -s mdb show dev br0 \ + | jq -e ".[].mdb[] | \ + select(.grp == \"$TEST_GROUP\" and \ + .source_list != null and .filter_mode == \"exclude\")" &>/dev/null + check_err $? "Wrong *,G entry filter mode" + + brmcast_check_sg_entries "to_exclude" "${X[@]}" "${Y[@]}" + + brmcast_check_sg_state 0 "${X[@]}" + brmcast_check_sg_state 1 "${Y[@]}" + + bridge -j -d -s mdb show dev br0 \ + | jq -e ".[].mdb[] | \ + select(.grp == \"$TEST_GROUP\" and \ + .source_list != null and + .source_list[].address == \"2001:db8:1::2\")" &>/dev/null + check_fail $? "Wrong *,G entry source list, 2001:db8:1::2 entry still exists" + bridge -j -d -s mdb show dev br0 \ + | jq -e ".[].mdb[] | \ + select(.grp == \"$TEST_GROUP\" and \ + .source_list != null and + .source_list[].address == \"2001:db8:1::21\")" &>/dev/null + check_fail $? "Wrong *,G entry source list, 2001:db8:1::21 entry still exists" + + brmcast_check_sg_fwding 1 "${X[@]}" 2001:db8:1::100 + brmcast_check_sg_fwding 0 "${Y[@]}" + + log_test "MLDv2 report $TEST_GROUP include -> to_exclude" + + ip link set dev br0 type bridge mcast_last_member_interval 100 + + mldv2cleanup $swp1 +} + +mldv2exc_allow_test() +{ + RET=0 + local X=("2001:db8:1::1" "2001:db8:1::2" "2001:db8:1::20" "2001:db8:1::30") + local Y=("2001:db8:1::21") + + mldv2exclude_prepare $h1 + + $MZ $h1 -c 1 $MZPKT_ALLOW2 -q + sleep 1 + brmcast_check_sg_entries "allow" "${X[@]}" "${Y[@]}" + + brmcast_check_sg_state 0 "${X[@]}" + brmcast_check_sg_state 1 "${Y[@]}" + + brmcast_check_sg_fwding 1 "${X[@]}" 2001:db8:1::100 + brmcast_check_sg_fwding 0 "${Y[@]}" + + log_test "MLDv2 report $TEST_GROUP exclude -> allow" + + mldv2cleanup $swp1 +} + +mldv2exc_is_include_test() +{ + RET=0 + local X=("2001:db8:1::1" "2001:db8:1::2" "2001:db8:1::20" "2001:db8:1::30") + local Y=("2001:db8:1::21") + + mldv2exclude_prepare $h1 + + $MZ $h1 -c 1 $MZPKT_IS_INC3 -q + sleep 1 + brmcast_check_sg_entries "is_include" "${X[@]}" "${Y[@]}" + + brmcast_check_sg_state 0 "${X[@]}" + brmcast_check_sg_state 1 "${Y[@]}" + + brmcast_check_sg_fwding 1 "${X[@]}" 2001:db8:1::100 + brmcast_check_sg_fwding 0 "${Y[@]}" + + log_test "MLDv2 report $TEST_GROUP exclude -> is_include" + + mldv2cleanup $swp1 +} + +mldv2exc_is_exclude_test() +{ + RET=0 + local X=("2001:db8:1::30") + local Y=("2001:db8:1::20") + + mldv2exclude_prepare $h1 + + $MZ $h1 -c 1 $MZPKT_IS_EXC2 -q + sleep 1 + brmcast_check_sg_entries "is_exclude" "${X[@]}" "${Y[@]}" + + brmcast_check_sg_state 0 "${X[@]}" + brmcast_check_sg_state 1 "${Y[@]}" + + brmcast_check_sg_fwding 1 "${X[@]}" 2001:db8:1::100 + brmcast_check_sg_fwding 0 "${Y[@]}" + + log_test "MLDv2 report $TEST_GROUP exclude -> is_exclude" + + mldv2cleanup $swp1 +} + +mldv2exc_to_exclude_test() +{ + RET=0 + local X=("2001:db8:1::1" "2001:db8:1::30") + local Y=("2001:db8:1::20") + + mldv2exclude_prepare $h1 + + ip link set dev br0 type bridge mcast_last_member_interval 500 + check_err $? "Could not change mcast_last_member_interval to 5s" + + $MZ $h1 -c 1 $MZPKT_TO_EXC -q + sleep 1 + brmcast_check_sg_entries "to_exclude" "${X[@]}" "${Y[@]}" + + brmcast_check_sg_state 0 "${X[@]}" + brmcast_check_sg_state 1 "${Y[@]}" + + brmcast_check_sg_fwding 1 "${X[@]}" 2001:db8:1::100 + brmcast_check_sg_fwding 0 "${Y[@]}" + + log_test "MLDv2 report $TEST_GROUP exclude -> to_exclude" + + ip link set dev br0 type bridge mcast_last_member_interval 100 + + mldv2cleanup $swp1 +} + +mldv2inc_block_test() +{ + RET=0 + local X=("2001:db8:1::2" "2001:db8:1::3") + + mldv2include_prepare $h1 + + $MZ $h1 -c 1 $MZPKT_BLOCK -q + # make sure the lowered timers have expired (by default 2 seconds) + sleep 3 + brmcast_check_sg_entries "block" "${X[@]}" + + brmcast_check_sg_state 0 "${X[@]}" + + bridge -j -d -s mdb show dev br0 \ + | jq -e ".[].mdb[] | \ + select(.grp == \"$TEST_GROUP\" and \ + .source_list != null and + .source_list[].address == \"2001:db8:1::1\")" &>/dev/null + check_fail $? "Wrong *,G entry source list, 2001:db8:1::1 entry still exists" + + brmcast_check_sg_fwding 1 "${X[@]}" + brmcast_check_sg_fwding 0 2001:db8:1::100 + + log_test "MLDv2 report $TEST_GROUP include -> block" + + mldv2cleanup $swp1 +} + +mldv2exc_block_test() +{ + RET=0 + local X=("2001:db8:1::1" "2001:db8:1::2" "2001:db8:1::30") + local Y=("2001:db8:1::20" "2001:db8:1::21") + + mldv2exclude_prepare $h1 + + ip link set dev br0 type bridge mcast_last_member_interval 500 + check_err $? "Could not change mcast_last_member_interval to 5s" + + $MZ $h1 -c 1 $MZPKT_BLOCK -q + sleep 1 + brmcast_check_sg_entries "block" "${X[@]}" "${Y[@]}" + + brmcast_check_sg_state 0 "${X[@]}" + brmcast_check_sg_state 1 "${Y[@]}" + + brmcast_check_sg_fwding 1 "${X[@]}" 2001:db8:1::100 + brmcast_check_sg_fwding 0 "${Y[@]}" + + log_test "MLDv2 report $TEST_GROUP exclude -> block" + + ip link set dev br0 type bridge mcast_last_member_interval 100 + + mldv2cleanup $swp1 +} + +mldv2exc_timeout_test() +{ + RET=0 + local X=("2001:db8:1::20" "2001:db8:1::30") + + # GMI should be 3 seconds + ip link set dev br0 type bridge mcast_query_interval 100 mcast_query_response_interval 100 + + mldv2exclude_prepare $h1 + ip link set dev br0 type bridge mcast_query_interval 500 mcast_query_response_interval 500 + $MZ $h1 -c 1 $MZPKT_ALLOW2 -q + sleep 3 + bridge -j -d -s mdb show dev br0 \ + | jq -e ".[].mdb[] | \ + select(.grp == \"$TEST_GROUP\" and \ + .source_list != null and .filter_mode == \"include\")" &>/dev/null + check_err $? "Wrong *,G entry filter mode" + + bridge -j -d -s mdb show dev br0 \ + | jq -e ".[].mdb[] | \ + select(.grp == \"$TEST_GROUP\" and \ + .source_list != null and + .source_list[].address == \"2001:db8:1::1\")" &>/dev/null + check_fail $? "Wrong *,G entry source list, 2001:db8:1::1 entry still exists" + bridge -j -d -s mdb show dev br0 \ + | jq -e ".[].mdb[] | \ + select(.grp == \"$TEST_GROUP\" and \ + .source_list != null and + .source_list[].address == \"2001:db8:1::2\")" &>/dev/null + check_fail $? "Wrong *,G entry source list, 2001:db8:1::2 entry still exists" + + brmcast_check_sg_entries "allow" "${X[@]}" + + brmcast_check_sg_state 0 "${X[@]}" + + brmcast_check_sg_fwding 1 "${X[@]}" + brmcast_check_sg_fwding 0 2001:db8:1::100 + + log_test "MLDv2 group $TEST_GROUP exclude timeout" + + ip link set dev br0 type bridge mcast_query_interval 12500 \ + mcast_query_response_interval 1000 + + mldv2cleanup $swp1 +} + +mldv2star_ex_auto_add_test() +{ + RET=0 + + mldv2exclude_prepare $h1 + + $MZ $h2 -c 1 $MZPKT_IS_INC -q + sleep 1 + bridge -j -d -s mdb show dev br0 \ + | jq -e ".[].mdb[] | \ + select(.grp == \"$TEST_GROUP\" and .src == \"2001:db8:1::3\" and \ + .port == \"$swp1\")" &>/dev/null + check_err $? "S,G entry for *,G port doesn't exist" + + bridge -j -d -s mdb show dev br0 \ + | jq -e ".[].mdb[] | \ + select(.grp == \"$TEST_GROUP\" and .src == \"2001:db8:1::3\" and \ + .port == \"$swp1\" and \ + .flags[] == \"added_by_star_ex\")" &>/dev/null + check_err $? "Auto-added S,G entry doesn't have added_by_star_ex flag" + + brmcast_check_sg_fwding 1 2001:db8:1::3 + + log_test "MLDv2 S,G port entry automatic add to a *,G port" + + mldv2cleanup $swp1 + mldv2cleanup $swp2 +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 927f9ba49e08..98ea37d26c44 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -1270,3 +1270,110 @@ tcpdump_show() { tcpdump -e -n -r $capfile 2>&1 } + +# return 0 if the packet wasn't seen on host2_if or 1 if it was +mcast_packet_test() +{ + local mac=$1 + local src_ip=$2 + local ip=$3 + local host1_if=$4 + local host2_if=$5 + local seen=0 + local tc_proto="ip" + local mz_v6arg="" + + # basic check to see if we were passed an IPv4 address, if not assume IPv6 + if [[ ! $ip =~ ^[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}$ ]]; then + tc_proto="ipv6" + mz_v6arg="-6" + fi + + # Add an ACL on `host2_if` which will tell us whether the packet + # was received by it or not. + tc qdisc add dev $host2_if ingress + tc filter add dev $host2_if ingress protocol $tc_proto pref 1 handle 101 \ + flower ip_proto udp dst_mac $mac action drop + + $MZ $host1_if $mz_v6arg -c 1 -p 64 -b $mac -A $src_ip -B $ip -t udp "dp=4096,sp=2048" -q + sleep 1 + + tc -j -s filter show dev $host2_if ingress \ + | jq -e ".[] | select(.options.handle == 101) \ + | select(.options.actions[0].stats.packets == 1)" &> /dev/null + if [[ $? -eq 0 ]]; then + seen=1 + fi + + tc filter del dev $host2_if ingress protocol $tc_proto pref 1 handle 101 flower + tc qdisc del dev $host2_if ingress + + return $seen +} + +brmcast_check_sg_entries() +{ + local report=$1; shift + local slist=("$@") + local sarg="" + + for src in "${slist[@]}"; do + sarg="${sarg} and .source_list[].address == \"$src\"" + done + bridge -j -d -s mdb show dev br0 \ + | jq -e ".[].mdb[] | \ + select(.grp == \"$TEST_GROUP\" and .source_list != null $sarg)" &>/dev/null + check_err $? "Wrong *,G entry source list after $report report" + + for sgent in "${slist[@]}"; do + bridge -j -d -s mdb show dev br0 \ + | jq -e ".[].mdb[] | \ + select(.grp == \"$TEST_GROUP\" and .src == \"$sgent\")" &>/dev/null + check_err $? "Missing S,G entry ($sgent, $TEST_GROUP)" + done +} + +brmcast_check_sg_fwding() +{ + local should_fwd=$1; shift + local sources=("$@") + + for src in "${sources[@]}"; do + local retval=0 + + mcast_packet_test $TEST_GROUP_MAC $src $TEST_GROUP $h2 $h1 + retval=$? + if [ $should_fwd -eq 1 ]; then + check_fail $retval "Didn't forward traffic from S,G ($src, $TEST_GROUP)" + else + check_err $retval "Forwarded traffic for blocked S,G ($src, $TEST_GROUP)" + fi + done +} + +brmcast_check_sg_state() +{ + local is_blocked=$1; shift + local sources=("$@") + local should_fail=1 + + if [ $is_blocked -eq 1 ]; then + should_fail=0 + fi + + for src in "${sources[@]}"; do + bridge -j -d -s mdb show dev br0 \ + | jq -e ".[].mdb[] | \ + select(.grp == \"$TEST_GROUP\" and .source_list != null) | + .source_list[] | + select(.address == \"$src\") | + select(.timer == \"0.00\")" &>/dev/null + check_err_fail $should_fail $? "Entry $src has zero timer" + + bridge -j -d -s mdb show dev br0 \ + | jq -e ".[].mdb[] | \ + select(.grp == \"$TEST_GROUP\" and .src == \"$src\" and \ + .flags[] == \"blocked\")" &>/dev/null + check_err_fail $should_fail $? "Entry $src has blocked flag" + done +} diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config index 741a1c4f4ae8..0faaccd21447 100644 --- a/tools/testing/selftests/net/mptcp/config +++ b/tools/testing/selftests/net/mptcp/config @@ -5,3 +5,13 @@ CONFIG_INET_DIAG=m CONFIG_INET_MPTCP_DIAG=m CONFIG_VETH=y CONFIG_NET_SCH_NETEM=m +CONFIG_NETFILTER=y +CONFIG_NETFILTER_ADVANCED=y +CONFIG_NETFILTER_NETLINK=m +CONFIG_NF_TABLES=m +CONFIG_NFT_COUNTER=m +CONFIG_NFT_COMPAT=m +CONFIG_NETFILTER_XTABLES=m +CONFIG_NETFILTER_XT_MATCH_BPF=m +CONFIG_NF_TABLES_IPV4=y +CONFIG_NF_TABLES_IPV6=y diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 08f53d86dedc..0d93b243695f 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -13,6 +13,24 @@ capture=0 TEST_COUNT=0 +# generated using "nfbpf_compile '(ip && (ip[54] & 0xf0) == 0x30) || +# (ip6 && (ip6[74] & 0xf0) == 0x30)'" +CBPF_MPTCP_SUBOPTION_ADD_ADDR="14, + 48 0 0 0, + 84 0 0 240, + 21 0 3 64, + 48 0 0 54, + 84 0 0 240, + 21 6 7 48, + 48 0 0 0, + 84 0 0 240, + 21 0 4 96, + 48 0 0 74, + 84 0 0 240, + 21 0 1 48, + 6 0 0 65535, + 6 0 0 0" + init() { capout=$(mktemp) @@ -82,6 +100,26 @@ reset_with_cookies() done } +reset_with_add_addr_timeout() +{ + local ip="${1:-4}" + local tables + + tables="iptables" + if [ $ip -eq 6 ]; then + tables="ip6tables" + fi + + reset + + ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=1 + ip netns exec $ns2 $tables -A OUTPUT -p tcp \ + -m tcp --tcp-option 30 \ + -m bpf --bytecode \ + "$CBPF_MPTCP_SUBOPTION_ADD_ADDR" \ + -j DROP +} + for arg in "$@"; do if [ "$arg" = "-c" ]; then capture=1 @@ -94,6 +132,17 @@ if [ $? -ne 0 ];then exit $ksft_skip fi +iptables -V > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run all tests without iptables tool" + exit $ksft_skip +fi + +ip6tables -V > /dev/null 2>&1 +if [ $? -ne 0 ];then + echo "SKIP: Could not run all tests without ip6tables tool" + exit $ksft_skip +fi check_transfer() { @@ -135,6 +184,7 @@ do_transfer() connect_addr="$5" rm_nr_ns1="$6" rm_nr_ns2="$7" + speed="$8" port=$((10000+$TEST_COUNT)) TEST_COUNT=$((TEST_COUNT+1)) @@ -159,7 +209,7 @@ do_transfer() sleep 1 fi - if [[ $rm_nr_ns1 -eq 0 && $rm_nr_ns2 -eq 0 ]]; then + if [ $speed = "fast" ]; then mptcp_connect="./mptcp_connect -j" else mptcp_connect="./mptcp_connect -r" @@ -250,26 +300,13 @@ run_tests() listener_ns="$1" connector_ns="$2" connect_addr="$3" + rm_nr_ns1="${4:-0}" + rm_nr_ns2="${5:-0}" + speed="${6:-fast}" lret=0 - do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} 0 0 - lret=$? - if [ $lret -ne 0 ]; then - ret=$lret - return - fi -} - -run_remove_tests() -{ - listener_ns="$1" - connector_ns="$2" - connect_addr="$3" - rm_nr_ns1="$4" - rm_nr_ns2="$5" - lret=0 - - do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} ${rm_nr_ns1} ${rm_nr_ns2} + do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} \ + ${rm_nr_ns1} ${rm_nr_ns2} ${speed} lret=$? if [ $lret -ne 0 ]; then ret=$lret @@ -491,12 +528,21 @@ run_tests $ns1 $ns2 10.0.1.1 chk_join_nr "multiple subflows and signal" 3 3 3 chk_add_nr 1 1 +# add_addr timeout +reset_with_add_addr_timeout +ip netns exec $ns1 ./pm_nl_ctl limits 0 1 +ip netns exec $ns2 ./pm_nl_ctl limits 1 1 +ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal +run_tests $ns1 $ns2 10.0.1.1 0 0 slow +chk_join_nr "signal address, ADD_ADDR timeout" 1 1 1 +chk_add_nr 4 0 + # single subflow, remove reset ip netns exec $ns1 ./pm_nl_ctl limits 0 1 ip netns exec $ns2 ./pm_nl_ctl limits 0 1 ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow -run_remove_tests $ns1 $ns2 10.0.1.1 0 1 +run_tests $ns1 $ns2 10.0.1.1 0 1 slow chk_join_nr "remove single subflow" 1 1 1 chk_rm_nr 1 1 @@ -506,7 +552,7 @@ ip netns exec $ns1 ./pm_nl_ctl limits 0 2 ip netns exec $ns2 ./pm_nl_ctl limits 0 2 ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow -run_remove_tests $ns1 $ns2 10.0.1.1 0 2 +run_tests $ns1 $ns2 10.0.1.1 0 2 slow chk_join_nr "remove multiple subflows" 2 2 2 chk_rm_nr 2 2 @@ -515,7 +561,7 @@ reset ip netns exec $ns1 ./pm_nl_ctl limits 0 1 ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal ip netns exec $ns2 ./pm_nl_ctl limits 1 1 -run_remove_tests $ns1 $ns2 10.0.1.1 1 0 +run_tests $ns1 $ns2 10.0.1.1 1 0 slow chk_join_nr "remove single address" 1 1 1 chk_add_nr 1 1 chk_rm_nr 0 0 @@ -526,7 +572,7 @@ ip netns exec $ns1 ./pm_nl_ctl limits 0 2 ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal ip netns exec $ns2 ./pm_nl_ctl limits 1 2 ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow -run_remove_tests $ns1 $ns2 10.0.1.1 1 1 +run_tests $ns1 $ns2 10.0.1.1 1 1 slow chk_join_nr "remove subflow and signal" 2 2 2 chk_add_nr 1 1 chk_rm_nr 1 1 @@ -538,7 +584,7 @@ ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal ip netns exec $ns2 ./pm_nl_ctl limits 1 3 ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow -run_remove_tests $ns1 $ns2 10.0.1.1 1 2 +run_tests $ns1 $ns2 10.0.1.1 1 2 slow chk_join_nr "remove subflows and signal" 3 3 3 chk_add_nr 1 1 chk_rm_nr 2 2 diff --git a/tools/testing/selftests/net/timestamping.c b/tools/testing/selftests/net/timestamping.c index f4bb4fef0f39..21091be70688 100644 --- a/tools/testing/selftests/net/timestamping.c +++ b/tools/testing/selftests/net/timestamping.c @@ -59,7 +59,8 @@ static void usage(const char *error) " SOF_TIMESTAMPING_SOFTWARE - request reporting of software time stamps\n" " SOF_TIMESTAMPING_RAW_HARDWARE - request reporting of raw HW time stamps\n" " SIOCGSTAMP - check last socket time stamp\n" - " SIOCGSTAMPNS - more accurate socket time stamp\n"); + " SIOCGSTAMPNS - more accurate socket time stamp\n" + " PTPV2 - use PTPv2 messages\n"); exit(1); } @@ -115,13 +116,28 @@ static const unsigned char sync[] = { 0x00, 0x00, 0x00, 0x00 }; -static void sendpacket(int sock, struct sockaddr *addr, socklen_t addr_len) +static const unsigned char sync_v2[] = { + 0x00, 0x02, 0x00, 0x2C, + 0x00, 0x00, 0x02, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0xFF, + 0xFE, 0x00, 0x00, 0x00, + 0x00, 0x01, 0x00, 0x01, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, + 0x00, 0x00, 0x00, 0x00, +}; + +static void sendpacket(int sock, struct sockaddr *addr, socklen_t addr_len, int ptpv2) { + size_t sync_len = ptpv2 ? sizeof(sync_v2) : sizeof(sync); + const void *sync_p = ptpv2 ? sync_v2 : sync; struct timeval now; int res; - res = sendto(sock, sync, sizeof(sync), 0, - addr, addr_len); + res = sendto(sock, sync_p, sync_len, 0, addr, addr_len); gettimeofday(&now, 0); if (res < 0) printf("%s: %s\n", "send", strerror(errno)); @@ -134,9 +150,11 @@ static void sendpacket(int sock, struct sockaddr *addr, socklen_t addr_len) static void printpacket(struct msghdr *msg, int res, char *data, int sock, int recvmsg_flags, - int siocgstamp, int siocgstampns) + int siocgstamp, int siocgstampns, int ptpv2) { struct sockaddr_in *from_addr = (struct sockaddr_in *)msg->msg_name; + size_t sync_len = ptpv2 ? sizeof(sync_v2) : sizeof(sync); + const void *sync_p = ptpv2 ? sync_v2 : sync; struct cmsghdr *cmsg; struct timeval tv; struct timespec ts; @@ -210,10 +228,9 @@ static void printpacket(struct msghdr *msg, int res, "probably SO_EE_ORIGIN_TIMESTAMPING" #endif ); - if (res < sizeof(sync)) + if (res < sync_len) printf(" => truncated data?!"); - else if (!memcmp(sync, data + res - sizeof(sync), - sizeof(sync))) + else if (!memcmp(sync_p, data + res - sync_len, sync_len)) printf(" => GOT OUR DATA BACK (HURRAY!)"); break; } @@ -257,7 +274,7 @@ static void printpacket(struct msghdr *msg, int res, } static void recvpacket(int sock, int recvmsg_flags, - int siocgstamp, int siocgstampns) + int siocgstamp, int siocgstampns, int ptpv2) { char data[256]; struct msghdr msg; @@ -288,7 +305,7 @@ static void recvpacket(int sock, int recvmsg_flags, } else { printpacket(&msg, res, data, sock, recvmsg_flags, - siocgstamp, siocgstampns); + siocgstamp, siocgstampns, ptpv2); } } @@ -300,6 +317,7 @@ int main(int argc, char **argv) int siocgstamp = 0; int siocgstampns = 0; int ip_multicast_loop = 0; + int ptpv2 = 0; char *interface; int i; int enabled = 1; @@ -335,6 +353,8 @@ int main(int argc, char **argv) siocgstampns = 1; else if (!strcasecmp(argv[i], "IP_MULTICAST_LOOP")) ip_multicast_loop = 1; + else if (!strcasecmp(argv[i], "PTPV2")) + ptpv2 = 1; else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_TX_HARDWARE")) so_timestamping_flags |= SOF_TIMESTAMPING_TX_HARDWARE; else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_TX_SOFTWARE")) @@ -369,6 +389,7 @@ int main(int argc, char **argv) HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF; hwconfig.rx_filter = (so_timestamping_flags & SOF_TIMESTAMPING_RX_HARDWARE) ? + ptpv2 ? HWTSTAMP_FILTER_PTP_V2_L4_SYNC : HWTSTAMP_FILTER_PTP_V1_L4_SYNC : HWTSTAMP_FILTER_NONE; hwconfig_requested = hwconfig; if (ioctl(sock, SIOCSHWTSTAMP, &hwtstamp) < 0) { @@ -496,16 +517,16 @@ int main(int argc, char **argv) printf("has error\n"); recvpacket(sock, 0, siocgstamp, - siocgstampns); + siocgstampns, ptpv2); recvpacket(sock, MSG_ERRQUEUE, siocgstamp, - siocgstampns); + siocgstampns, ptpv2); } } else { /* write one packet */ sendpacket(sock, (struct sockaddr *)&addr, - sizeof(addr)); + sizeof(addr), ptpv2); next.tv_sec += 5; continue; } |