diff options
499 files changed, 27586 insertions, 8570 deletions
diff --git a/Documentation/devicetree/bindings/net/can/sun4i_can.txt b/Documentation/devicetree/bindings/net/can/sun4i_can.txt new file mode 100644 index 000000000000..84ed1909df76 --- /dev/null +++ b/Documentation/devicetree/bindings/net/can/sun4i_can.txt @@ -0,0 +1,36 @@ +Allwinner A10/A20 CAN controller Device Tree Bindings +----------------------------------------------------- + +Required properties: +- compatible: "allwinner,sun4i-a10-can" +- reg: physical base address and size of the Allwinner A10/A20 CAN register map. +- interrupts: interrupt specifier for the sole interrupt. +- clock: phandle and clock specifier. + +Example +------- + +SoC common .dtsi file: + + can0_pins_a: can0@0 { + allwinner,pins = "PH20","PH21"; + allwinner,function = "can"; + allwinner,drive = <0>; + allwinner,pull = <0>; + }; +... + can0: can@01c2bc00 { + compatible = "allwinner,sun4i-a10-can"; + reg = <0x01c2bc00 0x400>; + interrupts = <0 26 4>; + clocks = <&apb1_gates 4>; + status = "disabled"; + }; + +Board specific .dts file: + + can0: can@01c2bc00 { + pinctrl-names = "default"; + pinctrl-0 = <&can0_pins_a>; + status = "okay"; + }; diff --git a/Documentation/devicetree/bindings/net/cpsw.txt b/Documentation/devicetree/bindings/net/cpsw.txt index a9df21aaa154..676ecf62491d 100644 --- a/Documentation/devicetree/bindings/net/cpsw.txt +++ b/Documentation/devicetree/bindings/net/cpsw.txt @@ -30,6 +30,13 @@ Optional properties: - dual_emac : Specifies Switch to act as Dual EMAC - syscon : Phandle to the system control device node, which is the control module device of the am33x +- mode-gpios : Should be added if one/multiple gpio lines are + required to be driven so that cpsw data lines + can be connected to the phy via selective mux. + For example in dra72x-evm, pcf gpio has to be + driven low so that cpsw slave 0 and phy data + lines are connected via mux. + Slave Properties: Required properties: diff --git a/Documentation/devicetree/bindings/net/hisilicon-hip04-net.txt b/Documentation/devicetree/bindings/net/hisilicon-hip04-net.txt index 988fc694b663..d1df8a00e1f3 100644 --- a/Documentation/devicetree/bindings/net/hisilicon-hip04-net.txt +++ b/Documentation/devicetree/bindings/net/hisilicon-hip04-net.txt @@ -32,13 +32,13 @@ Required properties: Required properties: -- compatible: should be "hisilicon,hip04-mdio". +- compatible: should be "hisilicon,mdio". - Inherits from MDIO bus node binding [2] [2] Documentation/devicetree/bindings/net/phy.txt Example: mdio { - compatible = "hisilicon,hip04-mdio"; + compatible = "hisilicon,mdio"; reg = <0x28f1000 0x1000>; #address-cells = <1>; #size-cells = <0>; diff --git a/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt b/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt new file mode 100644 index 000000000000..80411b2f0490 --- /dev/null +++ b/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt @@ -0,0 +1,49 @@ +Hisilicon DSA Fabric device controller + +Required properties: +- compatible: should be "hisilicon,hns-dsaf-v1" or "hisilicon,hns-dsaf-v2". + "hisilicon,hns-dsaf-v1" is for hip05. + "hisilicon,hns-dsaf-v2" is for Hi1610 and Hi1612. +- dsa-name: dsa fabric name who provide this interface. + should be "dsafX", X is the dsaf id. +- mode: dsa fabric mode string. only support one of dsaf modes like these: + "2port-64vf", + "6port-16rss", + "6port-16vf". +- interrupt-parent: the interrupt parent of this device. +- interrupts: should contain the DSA Fabric and rcb interrupt. +- reg: specifies base physical address(es) and size of the device registers. + The first region is external interface control register base and size. + The second region is SerDes base register and size. + The third region is the PPE register base and size. + The fourth region is dsa fabric base register and size. + The fifth region is cpld base register and size, it is not required if do not use cpld. +- phy-handle: phy handle of physicl port, 0 if not any phy device. see ethernet.txt [1]. +- buf-size: rx buffer size, should be 16-1024. +- desc-num: number of description in TX and RX queue, should be 512, 1024, 2048 or 4096. + +[1] Documentation/devicetree/bindings/net/phy.txt + +Example: + +dsa: dsa@c7000000 { + compatible = "hisilicon,hns-dsaf-v1"; + dsa_name = "dsaf0"; + mode = "6port-16rss"; + interrupt-parent = <&mbigen_dsa>; + reg = <0x0 0xC0000000 0x0 0x420000 + 0x0 0xC2000000 0x0 0x300000 + 0x0 0xc5000000 0x0 0x890000 + 0x0 0xc7000000 0x0 0x60000>; + phy-handle = <0 0 0 0 &soc0_phy4 &soc0_phy5 0 0>; + interrupts = <131 4>,<132 4>, <133 4>,<134 4>, + <135 4>,<136 4>, <137 4>,<138 4>, + <139 4>,<140 4>, <141 4>,<142 4>, + <143 4>,<144 4>, <145 4>,<146 4>, + <147 4>,<148 4>, <384 1>,<385 1>, + <386 1>,<387 1>, <388 1>,<389 1>, + <390 1>,<391 1>, + buf-size = <4096>; + desc-num = <1024>; + dma-coherent; +}; diff --git a/Documentation/devicetree/bindings/net/hisilicon-hns-mdio.txt b/Documentation/devicetree/bindings/net/hisilicon-hns-mdio.txt new file mode 100644 index 000000000000..9940aa02b8bd --- /dev/null +++ b/Documentation/devicetree/bindings/net/hisilicon-hns-mdio.txt @@ -0,0 +1,22 @@ +Hisilicon MDIO bus controller + +Properties: +- compatible: "hisilicon,mdio","hisilicon,hns-mdio". +- reg: The base address of the MDIO bus controller register bank. +- #address-cells: Must be <1>. +- #size-cells: Must be <0>. MDIO addresses have no size component. + +Typically an MDIO bus might have several children. + +Example: + mdio@803c0000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "hisilicon,mdio","hisilicon,hns-mdio"; + reg = <0x0 0x803c0000 0x0 0x10000>; + + ethernet-phy@0 { + ... + reg = <0>; + }; + }; diff --git a/Documentation/devicetree/bindings/net/hisilicon-hns-nic.txt b/Documentation/devicetree/bindings/net/hisilicon-hns-nic.txt new file mode 100644 index 000000000000..41d19be7011e --- /dev/null +++ b/Documentation/devicetree/bindings/net/hisilicon-hns-nic.txt @@ -0,0 +1,47 @@ +Hisilicon Network Subsystem NIC controller + +Required properties: +- compatible: "hisilicon,hns-nic-v1" or "hisilicon,hns-nic-v2". + "hisilicon,hns-nic-v1" is for hip05. + "hisilicon,hns-nic-v2" is for Hi1610 and Hi1612. +- ae-name: accelerator name who provides this interface, + is simply a name referring to the name of name in the accelerator node. +- port-id: is the index of port provided by DSAF (the accelerator). DSAF can + connect to 8 PHYs. Port 0 to 1 are both used for adminstration purpose. They + are called debug ports. + + The remaining 6 PHYs are taken according to the mode of DSAF. + + In NIC mode of DSAF, all 6 PHYs are taken as ethernet ports to the CPU. The + port-id can be 2 to 7. Here is the diagram: + +-----+---------------+ + | CPU | + +-+-+-+---+-+-+-+-+-+-+ + | | | | | | | | + debug service + port port + (0,1) (2-7) + + In Switch mode of DSAF, all 6 PHYs are taken as physical ports connect to a + LAN Switch while the CPU side assume itself have one single NIC connect to + this switch. In this case, the port-id will be 2 only. + +-----+---------------+ + | CPU | + +-+-+-+---+-+-+-+-+-+-+ + | | service| port(2) + debug +------------+ + port | switch | + (0,1) +-+-+-+-+-+-++ + | | | | | | + external port + +- local-mac-address: mac addr of the ethernet interface + +Example: + + ethernet@0{ + compatible = "hisilicon,hns-nic-v1"; + ae-name = "dsaf0"; + port-id = <0>; + local-mac-address = [a2 14 e4 4b 56 76]; + }; diff --git a/Documentation/networking/ieee802154.txt b/Documentation/networking/ieee802154.txt index 1700756af057..aa69ccc481db 100644 --- a/Documentation/networking/ieee802154.txt +++ b/Documentation/networking/ieee802154.txt @@ -7,11 +7,11 @@ Introduction The IEEE 802.15.4 working group focuses on standardization of bottom two layers: Medium Access Control (MAC) and Physical (PHY). And there are mainly two options available for upper layers: - - ZigBee - proprietary protocol from ZigBee Alliance - - 6LowPAN - IPv6 networking over low rate personal area networks + - ZigBee - proprietary protocol from the ZigBee Alliance + - 6LoWPAN - IPv6 networking over low rate personal area networks -The Linux-ZigBee project goal is to provide complete implementation -of IEEE 802.15.4 and 6LoWPAN protocols. IEEE 802.15.4 is a stack +The linux-wpan project goal is to provide a complete implementation +of the IEEE 802.15.4 and 6LoWPAN protocols. IEEE 802.15.4 is a stack of protocols for organizing Low-Rate Wireless Personal Area Networks. The stack is composed of three main parts: diff --git a/Documentation/networking/ipvs-sysctl.txt b/Documentation/networking/ipvs-sysctl.txt index 3ba709531adb..e6b1c025fdd8 100644 --- a/Documentation/networking/ipvs-sysctl.txt +++ b/Documentation/networking/ipvs-sysctl.txt @@ -157,6 +157,16 @@ expire_quiescent_template - BOOLEAN persistence template if it is to be used to schedule a new connection and the destination server is quiescent. +ignore_tunneled - BOOLEAN + 0 - disabled (default) + not 0 - enabled + + If set, ipvs will set the ipvs_property on all packets which are of + unrecognized protocols. This prevents us from routing tunneled + protocols like ipip, which is useful to prevent rescheduling + packets that have been tunneled to the ipvs host (i.e. to prevent + ipvs routing loops when ipvs is also acting as a real server). + nat_icmp_send - BOOLEAN 0 - disabled (default) not 0 - enabled diff --git a/Documentation/networking/l2tp.txt b/Documentation/networking/l2tp.txt index c74434de2fa5..4650a00ed012 100644 --- a/Documentation/networking/l2tp.txt +++ b/Documentation/networking/l2tp.txt @@ -213,15 +213,12 @@ To create an L2TPv3 ethernet pseudowire between local host 192.168.1.1 and peer 192.168.1.2, using IP addresses 10.5.1.1 and 10.5.1.2 for the tunnel endpoints:- -# modprobe l2tp_eth -# modprobe l2tp_netlink - # ip l2tp add tunnel tunnel_id 1 peer_tunnel_id 1 udp_sport 5000 \ udp_dport 5000 encap udp local 192.168.1.1 remote 192.168.1.2 # ip l2tp add session tunnel_id 1 session_id 1 peer_session_id 1 -# ifconfig -a +# ip -s -d show dev l2tpeth0 # ip addr add 10.5.1.2/32 peer 10.5.1.1/32 dev l2tpeth0 -# ifconfig l2tpeth0 up +# ip li set dev l2tpeth0 up Choose IP addresses to be the address of a local IP interface and that of the remote system. The IP addresses of the l2tpeth0 interface can be diff --git a/Documentation/networking/switchdev.txt b/Documentation/networking/switchdev.txt index 476df0496686..9f9e2587b347 100644 --- a/Documentation/networking/switchdev.txt +++ b/Documentation/networking/switchdev.txt @@ -239,20 +239,20 @@ The driver should initialize the attributes to the hardware defaults. FDB Ageing ^^^^^^^^^^ -There are two FDB ageing models supported: 1) ageing by the device, and 2) -ageing by the kernel. Ageing by the device is preferred if many FDB entries -are supported. The driver calls call_switchdev_notifiers(SWITCHDEV_FDB_DEL, -...) to age out the FDB entry. In this model, ageing by the kernel should be -turned off. XXX: how to turn off ageing in kernel on a per-port basis or -otherwise prevent the kernel from ageing out the FDB entry? - -In the kernel ageing model, the standard bridge ageing mechanism is used to age -out stale FDB entries. To keep an FDB entry "alive", the driver should refresh -the FDB entry by calling call_switchdev_notifiers(SWITCHDEV_FDB_ADD, ...). The +The bridge will skip ageing FDB entries marked with NTF_EXT_LEARNED and it is +the responsibility of the port driver/device to age out these entries. If the +port device supports ageing, when the FDB entry expires, it will notify the +driver which in turn will notify the bridge with SWITCHDEV_FDB_DEL. If the +device does not support ageing, the driver can simulate ageing using a +garbage collection timer to monitor FBD entries. Expired entries will be +notified to the bridge using SWITCHDEV_FDB_DEL. See rocker driver for +example of driver running ageing timer. + +To keep an NTF_EXT_LEARNED entry "alive", the driver should refresh the FDB +entry by calling call_switchdev_notifiers(SWITCHDEV_FDB_ADD, ...). The notification will reset the FDB entry's last-used time to now. The driver should rate limit refresh notifications, for example, no more than once a -second. If the FDB entry expires, fdb_delete is called to remove entry from -the device. +second. (The last-used time is visible using the bridge -s fdb option). STP State Change on Port ^^^^^^^^^^^^^^^^^^^^^^^^ @@ -369,3 +369,22 @@ The driver can monitor for updates to arp_tbl using the netevent notifier NETEVENT_NEIGH_UPDATE. The device can be programmed with resolved nexthops for the routes as arp_tbl updates. The driver implements ndo_neigh_destroy to know when arp_tbl neighbor entries are purged from the port. + +Transaction item queue +^^^^^^^^^^^^^^^^^^^^^^ + +For switchdev ops attr_set and obj_add, there is a 2 phase transaction model +used. First phase is to "prepare" anything needed, including various checks, +memory allocation, etc. The goal is to handle the stuff that is not unlikely +to fail here. The second phase is to "commit" the actual changes. + +Switchdev provides an inftrastructure for sharing items (for example memory +allocations) between the two phases. + +The object created by a driver in "prepare" phase and it is queued up by: +switchdev_trans_item_enqueue() +During the "commit" phase, the driver gets the object by: +switchdev_trans_item_dequeue() + +If a transaction is aborted during "prepare" phase, switchdev code will handle +cleanup of the queued-up objects. diff --git a/MAINTAINERS b/MAINTAINERS index 797236befd27..c22e13e80b6a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6093,6 +6093,13 @@ F: Documentation/auxdisplay/ks0108 F: drivers/auxdisplay/ks0108.c F: include/linux/ks0108.h +L3MDEV +M: David Ahern <dsa@cumulusnetworks.com> +L: netdev@vger.kernel.org +S: Maintained +F: net/l3mdev +F: include/net/l3mdev.h + LAPB module L: linux-x25@vger.kernel.org S: Orphan @@ -7305,7 +7312,6 @@ S: Odd Fixes F: drivers/net/ F: include/linux/if_* F: include/linux/netdevice.h -F: include/linux/arcdevice.h F: include/linux/etherdevice.h F: include/linux/fcdevice.h F: include/linux/fddidevice.h @@ -11265,7 +11271,6 @@ M: Shrijeet Mukherjee <shm@cumulusnetworks.com> L: netdev@vger.kernel.org S: Maintained F: drivers/net/vrf.c -F: include/net/vrf.h F: Documentation/networking/vrf.txt VT1211 HARDWARE MONITOR DRIVER diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi index 0447c04a40cc..d83ff9c9701e 100644 --- a/arch/arm/boot/dts/am4372.dtsi +++ b/arch/arm/boot/dts/am4372.dtsi @@ -591,6 +591,7 @@ cpts_clock_mult = <0x80000000>; cpts_clock_shift = <29>; ranges; + syscon = <&scm_conf>; davinci_mdio: mdio@4a101000 { compatible = "ti,am4372-mdio","ti,davinci_mdio"; diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi index e289c706d27d..8fedddc35999 100644 --- a/arch/arm/boot/dts/dra7.dtsi +++ b/arch/arm/boot/dts/dra7.dtsi @@ -1448,6 +1448,7 @@ <GIC_SPI 336 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 337 IRQ_TYPE_LEVEL_HIGH>; ranges; + syscon = <&scm_conf>; status = "disabled"; davinci_mdio: mdio@48485000 { diff --git a/arch/arm64/boot/dts/apm/apm-storm.dtsi b/arch/arm64/boot/dts/apm/apm-storm.dtsi index d831bc2ac204..d483e7e4f921 100644 --- a/arch/arm64/boot/dts/apm/apm-storm.dtsi +++ b/arch/arm64/boot/dts/apm/apm-storm.dtsi @@ -207,6 +207,17 @@ clock-output-names = "xge0clk"; }; + xge1clk: xge1clk@1f62c000 { + compatible = "apm,xgene-device-clock"; + status = "disabled"; + #clock-cells = <1>; + clocks = <&socplldiv2 0>; + reg = <0x0 0x1f62c000 0x0 0x1000>; + reg-names = "csr-reg"; + csr-mask = <0x3>; + clock-output-names = "xge1clk"; + }; + sataphy1clk: sataphy1clk@1f21c000 { compatible = "apm,xgene-device-clock"; #clock-cells = <1>; @@ -816,6 +827,23 @@ phy-connection-type = "xgmii"; }; + xgenet1: ethernet@1f620000 { + compatible = "apm,xgene1-xgenet"; + status = "disabled"; + reg = <0x0 0x1f620000 0x0 0xd100>, + <0x0 0x1f600000 0x0 0Xc300>, + <0x0 0x18000000 0x0 0X8000>; + reg-names = "enet_csr", "ring_csr", "ring_cmd"; + interrupts = <0x0 0x6C 0x4>, + <0x0 0x6D 0x4>; + port-id = <1>; + dma-coherent; + clocks = <&xge1clk 0>; + /* mac address will be overwritten by the bootloader */ + local-mac-address = [00 00 00 00 00 00]; + phy-connection-type = "xgmii"; + }; + rng: rng@10520000 { compatible = "apm,xgene-rng"; reg = <0x0 0x10520000 0x0 0x100>; diff --git a/arch/arm64/boot/dts/hisilicon/hip05_hns.dtsi b/arch/arm64/boot/dts/hisilicon/hip05_hns.dtsi new file mode 100644 index 000000000000..35005866a34e --- /dev/null +++ b/arch/arm64/boot/dts/hisilicon/hip05_hns.dtsi @@ -0,0 +1,193 @@ +soc0: soc@000000000 { + #address-cells = <2>; + #size-cells = <2>; + device_type = "soc"; + compatible = "simple-bus"; + ranges = <0x0 0x0 0x0 0x0 0x1 0x0>; + chip-id = <0>; + + soc0_mdio0: mdio@803c0000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "hisilicon,hns-mdio"; + reg = <0x0 0x803c0000 0x0 0x10000 + 0x0 0x80000000 0x0 0x10000>; + + soc0_phy4: ethernet-phy@4 { + reg = <0x0>; + device_type = "ethernet-phy"; + compatible = "ethernet-phy-ieee802.3-c22"; + }; + soc0_phy5: ethernet-phy@5 { + reg = <0x1>; + device_type = "ethernet-phy"; + compatible = "ethernet-phy-ieee802.3-c22"; + }; + }; + + dsa: dsa@c7000000 { + compatible = "hisilicon,hns-dsaf-v1"; + dsa_name = "dsaf0"; + mode = "6port-16rss"; + interrupt-parent = <&mbigen_dsa>; + + reg = <0x0 0xC0000000 0x0 0x420000 + 0x0 0xC2000000 0x0 0x300000 + 0x0 0xc5000000 0x0 0x890000 + 0x0 0xc7000000 0x0 0x60000 + >; + + phy-handle = <0 0 0 0 &soc0_phy4 &soc0_phy5 0 0>; + interrupts = < + /* [14] ge fifo err 8 / xge 6**/ + 149 0x4 150 0x4 151 0x4 152 0x4 + 153 0x4 154 0x4 26 0x4 27 0x4 + 155 0x4 156 0x4 157 0x4 158 0x4 159 0x4 160 0x4 + /* [12] rcb com 4*3**/ + 0x6 0x4 0x7 0x4 0x8 0x4 0x9 0x4 + 16 0x4 17 0x4 18 0x4 19 0x4 + 22 0x4 23 0x4 24 0x4 25 0x4 + /* [8] ppe tnl 0-7***/ + 0x0 0x4 0x1 0x4 0x2 0x4 0x3 0x4 + 0x4 0x4 0x5 0x4 12 0x4 13 0x4 + /* [21] dsaf event int 3+18**/ + 128 0x4 129 0x4 130 0x4 + 0x83 0x4 0x84 0x4 0x85 0x4 0x86 0x4 0x87 0x4 0x88 0x4 + 0x89 0x4 0x8a 0x4 0x8b 0x4 0x8c 0x4 0x8d 0x4 0x8e 0x4 + 0x8f 0x4 0x90 0x4 0x91 0x4 0x92 0x4 0x93 0x4 0x94 0x4 + /* [4] debug rcb 2*2*/ + 0xe 0x1 0xf 0x1 0x14 0x1 0x15 0x1 + /* [256] sevice rcb 2*128*/ + 0x180 0x1 0x181 0x1 0x182 0x1 0x183 0x1 + 0x184 0x1 0x185 0x1 0x186 0x1 0x187 0x1 + 0x188 0x1 0x189 0x1 0x18a 0x1 0x18b 0x1 + 0x18c 0x1 0x18d 0x1 0x18e 0x1 0x18f 0x1 + 0x190 0x1 0x191 0x1 0x192 0x1 0x193 0x1 + 0x194 0x1 0x195 0x1 0x196 0x1 0x197 0x1 + 0x198 0x1 0x199 0x1 0x19a 0x1 0x19b 0x1 + 0x19c 0x1 0x19d 0x1 0x19e 0x1 0x19f 0x1 + 0x1a0 0x1 0x1a1 0x1 0x1a2 0x1 0x1a3 0x1 + 0x1a4 0x1 0x1a5 0x1 0x1a6 0x1 0x1a7 0x1 + 0x1a8 0x1 0x1a9 0x1 0x1aa 0x1 0x1ab 0x1 + 0x1ac 0x1 0x1ad 0x1 0x1ae 0x1 0x1af 0x1 + 0x1b0 0x1 0x1b1 0x1 0x1b2 0x1 0x1b3 0x1 + 0x1b4 0x1 0x1b5 0x1 0x1b6 0x1 0x1b7 0x1 + 0x1b8 0x1 0x1b9 0x1 0x1ba 0x1 0x1bb 0x1 + 0x1bc 0x1 0x1bd 0x1 0x1be 0x1 0x1bf 0x1 + 0x1c0 0x1 0x1c1 0x1 0x1c2 0x1 0x1c3 0x1 + 0x1c4 0x1 0x1c5 0x1 0x1c6 0x1 0x1c7 0x1 + 0x1c8 0x1 0x1c9 0x1 0x1ca 0x1 0x1cb 0x1 + 0x1cc 0x1 0x1cd 0x1 0x1ce 0x1 0x1cf 0x1 + 0x1d0 0x1 0x1d1 0x1 0x1d2 0x1 0x1d3 0x1 + 0x1d4 0x1 0x1d5 0x1 0x1d6 0x1 0x1d7 0x1 + 0x1d8 0x1 0x1d9 0x1 0x1da 0x1 0x1db 0x1 + 0x1dc 0x1 0x1dd 0x1 0x1de 0x1 0x1df 0x1 + 0x1e0 0x1 0x1e1 0x1 0x1e2 0x1 0x1e3 0x1 + 0x1e4 0x1 0x1e5 0x1 0x1e6 0x1 0x1e7 0x1 + 0x1e8 0x1 0x1e9 0x1 0x1ea 0x1 0x1eb 0x1 + 0x1ec 0x1 0x1ed 0x1 0x1ee 0x1 0x1ef 0x1 + 0x1f0 0x1 0x1f1 0x1 0x1f2 0x1 0x1f3 0x1 + 0x1f4 0x1 0x1f5 0x1 0x1f6 0x1 0x1f7 0x1 + 0x1f8 0x1 0x1f9 0x1 0x1fa 0x1 0x1fb 0x1 + 0x1fc 0x1 0x1fd 0x1 0x1fe 0x1 0x1ff 0x1 + 0x200 0x1 0x201 0x1 0x202 0x1 0x203 0x1 + 0x204 0x1 0x205 0x1 0x206 0x1 0x207 0x1 + 0x208 0x1 0x209 0x1 0x20a 0x1 0x20b 0x1 + 0x20c 0x1 0x20d 0x1 0x20e 0x1 0x20f 0x1 + 0x210 0x1 0x211 0x1 0x212 0x1 0x213 0x1 + 0x214 0x1 0x215 0x1 0x216 0x1 0x217 0x1 + 0x218 0x1 0x219 0x1 0x21a 0x1 0x21b 0x1 + 0x21c 0x1 0x21d 0x1 0x21e 0x1 0x21f 0x1 + 0x220 0x1 0x221 0x1 0x222 0x1 0x223 0x1 + 0x224 0x1 0x225 0x1 0x226 0x1 0x227 0x1 + 0x228 0x1 0x229 0x1 0x22a 0x1 0x22b 0x1 + 0x22c 0x1 0x22d 0x1 0x22e 0x1 0x22f 0x1 + 0x230 0x1 0x231 0x1 0x232 0x1 0x233 0x1 + 0x234 0x1 0x235 0x1 0x236 0x1 0x237 0x1 + 0x238 0x1 0x239 0x1 0x23a 0x1 0x23b 0x1 + 0x23c 0x1 0x23d 0x1 0x23e 0x1 0x23f 0x1 + 0x240 0x1 0x241 0x1 0x242 0x1 0x243 0x1 + 0x244 0x1 0x245 0x1 0x246 0x1 0x247 0x1 + 0x248 0x1 0x249 0x1 0x24a 0x1 0x24b 0x1 + 0x24c 0x1 0x24d 0x1 0x24e 0x1 0x24f 0x1 + 0x250 0x1 0x251 0x1 0x252 0x1 0x253 0x1 + 0x254 0x1 0x255 0x1 0x256 0x1 0x257 0x1 + 0x258 0x1 0x259 0x1 0x25a 0x1 0x25b 0x1 + 0x25c 0x1 0x25d 0x1 0x25e 0x1 0x25f 0x1 + 0x260 0x1 0x261 0x1 0x262 0x1 0x263 0x1 + 0x264 0x1 0x265 0x1 0x266 0x1 0x267 0x1 + 0x268 0x1 0x269 0x1 0x26a 0x1 0x26b 0x1 + 0x26c 0x1 0x26d 0x1 0x26e 0x1 0x26f 0x1 + 0x270 0x1 0x271 0x1 0x272 0x1 0x273 0x1 + 0x274 0x1 0x275 0x1 0x276 0x1 0x277 0x1 + 0x278 0x1 0x279 0x1 0x27a 0x1 0x27b 0x1 + 0x27c 0x1 0x27d 0x1 0x27e 0x1 0x27f 0x1>; + buf-size = <4096>; + desc-num = <1024>; + dma-coherent; + }; + + eth0: ethernet@0{ + compatible = "hisilicon,hns-nic-v1"; + ae-name = "dsaf0"; + port-id = <0>; + local-mac-address = [00 00 00 01 00 58]; + status = "disabled"; + dma-coherent; + }; + eth1: ethernet@1{ + compatible = "hisilicon,hns-nic-v1"; + ae-name = "dsaf0"; + port-id = <1>; + status = "disabled"; + dma-coherent; + }; + eth2: ethernet@2{ + compatible = "hisilicon,hns-nic-v1"; + ae-name = "dsaf0"; + port-id = <2>; + local-mac-address = [00 00 00 01 00 5a]; + status = "disabled"; + dma-coherent; + }; + eth3: ethernet@3{ + compatible = "hisilicon,hns-nic-v1"; + ae-name = "dsaf0"; + port-id = <3>; + local-mac-address = [00 00 00 01 00 5b]; + status = "disabled"; + dma-coherent; + }; + eth4: ethernet@4{ + compatible = "hisilicon,hns-nic-v1"; + ae-name = "dsaf0"; + port-id = <4>; + local-mac-address = [00 00 00 01 00 5c]; + status = "disabled"; + dma-coherent; + }; + eth5: ethernet@5{ + compatible = "hisilicon,hns-nic-v1"; + ae-name = "dsaf0"; + port-id = <5>; + local-mac-address = [00 00 00 01 00 5d]; + status = "disabled"; + dma-coherent; + }; + eth6: ethernet@6{ + compatible = "hisilicon,hns-nic-v1"; + ae-name = "dsaf0"; + port-id = <6>; + local-mac-address = [00 00 00 01 00 5e]; + status = "disabled"; + dma-coherent; + }; + eth7: ethernet@7{ + compatible = "hisilicon,hns-nic-v1"; + ae-name = "dsaf0"; + port-id = <7>; + local-mac-address = [00 00 00 01 00 5f]; + status = "disabled"; + dma-coherent; + }; +}; diff --git a/arch/m68k/mac/psc.c b/arch/m68k/mac/psc.c index cd38f29955c8..2290c0cae48b 100644 --- a/arch/m68k/mac/psc.c +++ b/arch/m68k/mac/psc.c @@ -29,6 +29,7 @@ int psc_present; volatile __u8 *psc; +EXPORT_SYMBOL_GPL(psc); /* * Debugging dump, used in various places to see what's going on. diff --git a/drivers/bluetooth/bt3c_cs.c b/drivers/bluetooth/bt3c_cs.c index a00bb82eb7c6..772a2770710c 100644 --- a/drivers/bluetooth/bt3c_cs.c +++ b/drivers/bluetooth/bt3c_cs.c @@ -453,7 +453,8 @@ static int bt3c_load_firmware(struct bt3c_info *info, { char *ptr = (char *) firmware; char b[9]; - unsigned int iobase, size, addr, fcs, tmp; + unsigned int iobase, tmp; + unsigned long size, addr, fcs; int i, err = 0; iobase = info->p_dev->resource[0]->start; @@ -478,15 +479,18 @@ static int bt3c_load_firmware(struct bt3c_info *info, memset(b, 0, sizeof(b)); memcpy(b, ptr + 2, 2); - size = simple_strtoul(b, NULL, 16); + if (kstrtoul(b, 16, &size) < 0) + return -EINVAL; memset(b, 0, sizeof(b)); memcpy(b, ptr + 4, 8); - addr = simple_strtoul(b, NULL, 16); + if (kstrtoul(b, 16, &addr) < 0) + return -EINVAL; memset(b, 0, sizeof(b)); memcpy(b, ptr + (size * 2) + 2, 2); - fcs = simple_strtoul(b, NULL, 16); + if (kstrtoul(b, 16, &fcs) < 0) + return -EINVAL; memset(b, 0, sizeof(b)); for (tmp = 0, i = 0; i < size; i++) { diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c index 048423fd83bf..9e18988375eb 100644 --- a/drivers/bluetooth/btintel.c +++ b/drivers/bluetooth/btintel.c @@ -22,6 +22,7 @@ */ #include <linux/module.h> +#include <linux/firmware.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> @@ -169,6 +170,51 @@ int btintel_secure_send(struct hci_dev *hdev, u8 fragment_type, u32 plen, } EXPORT_SYMBOL_GPL(btintel_secure_send); +int btintel_load_ddc_config(struct hci_dev *hdev, const char *ddc_name) +{ + const struct firmware *fw; + struct sk_buff *skb; + const u8 *fw_ptr; + int err; + + err = request_firmware_direct(&fw, ddc_name, &hdev->dev); + if (err < 0) { + bt_dev_err(hdev, "Failed to load Intel DDC file %s (%d)", + ddc_name, err); + return err; + } + + bt_dev_info(hdev, "Found Intel DDC parameters: %s", ddc_name); + + fw_ptr = fw->data; + + /* DDC file contains one or more DDC structure which has + * Length (1 byte), DDC ID (2 bytes), and DDC value (Length - 2). + */ + while (fw->size > fw_ptr - fw->data) { + u8 cmd_plen = fw_ptr[0] + sizeof(u8); + + skb = __hci_cmd_sync(hdev, 0xfc8b, cmd_plen, fw_ptr, + HCI_INIT_TIMEOUT); + if (IS_ERR(skb)) { + bt_dev_err(hdev, "Failed to send Intel_Write_DDC (%ld)", + PTR_ERR(skb)); + release_firmware(fw); + return PTR_ERR(skb); + } + + fw_ptr += cmd_plen; + kfree_skb(skb); + } + + release_firmware(fw); + + bt_dev_info(hdev, "Applying Intel DDC parameters completed"); + + return 0; +} +EXPORT_SYMBOL_GPL(btintel_load_ddc_config); + MODULE_AUTHOR("Marcel Holtmann <marcel@holtmann.org>"); MODULE_DESCRIPTION("Bluetooth support for Intel devices ver " VERSION); MODULE_VERSION(VERSION); diff --git a/drivers/bluetooth/btintel.h b/drivers/bluetooth/btintel.h index b278d14758d5..52deaf2817cf 100644 --- a/drivers/bluetooth/btintel.h +++ b/drivers/bluetooth/btintel.h @@ -78,6 +78,7 @@ void btintel_hw_error(struct hci_dev *hdev, u8 code); void btintel_version_info(struct hci_dev *hdev, struct intel_version *ver); int btintel_secure_send(struct hci_dev *hdev, u8 fragment_type, u32 plen, const void *param); +int btintel_load_ddc_config(struct hci_dev *hdev, const char *ddc_name); #else @@ -95,7 +96,8 @@ static inline void btintel_hw_error(struct hci_dev *hdev, u8 code) { } -static void btintel_version_info(struct hci_dev *hdev, struct intel_version *ver) +static inline void btintel_version_info(struct hci_dev *hdev, + struct intel_version *ver) { } @@ -105,4 +107,10 @@ static inline int btintel_secure_send(struct hci_dev *hdev, u8 fragment_type, return -EOPNOTSUPP; } +static inline int btintel_load_ddc_config(struct hci_dev *hdev, + const char *ddc_name) +{ + return -EOPNOTSUPP; +} + #endif diff --git a/drivers/bluetooth/btmrvl_main.c b/drivers/bluetooth/btmrvl_main.c index de05deb444ce..bc110f61c8b1 100644 --- a/drivers/bluetooth/btmrvl_main.c +++ b/drivers/bluetooth/btmrvl_main.c @@ -377,20 +377,6 @@ static int btmrvl_tx_pkt(struct btmrvl_private *priv, struct sk_buff *skb) return -EINVAL; } - if (skb_headroom(skb) < BTM_HEADER_LEN) { - struct sk_buff *tmp = skb; - - skb = skb_realloc_headroom(skb, BTM_HEADER_LEN); - if (!skb) { - BT_ERR("Tx Error: realloc_headroom failed %d", - BTM_HEADER_LEN); - skb = tmp; - return -EINVAL; - } - - kfree_skb(tmp); - } - skb_push(skb, BTM_HEADER_LEN); /* header type: byte[3] diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index b6aceaf82aa8..dfaaea2efecb 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -1277,6 +1277,20 @@ static void btusb_work(struct work_struct *work) clear_bit(BTUSB_ISOC_RUNNING, &data->flags); usb_kill_anchored_urbs(&data->isoc_anchor); + /* When isochronous alternate setting needs to be + * changed, because SCO connection has been added + * or removed, a packet fragment may be left in the + * reassembling state. This could lead to wrongly + * assembled fragments. + * + * Clear outstanding fragment when selecting a new + * alternate setting. + */ + spin_lock(&data->rxlock); + kfree_skb(data->sco_skb); + data->sco_skb = NULL; + spin_unlock(&data->rxlock); + if (__set_isoc_interface(hdev, new_alts) < 0) return; } @@ -1348,7 +1362,9 @@ static int btusb_setup_csr(struct hci_dev *hdev) rp = (struct hci_rp_read_local_version *)skb->data; - if (le16_to_cpu(rp->manufacturer) != 10) { + /* Detect controllers which aren't real CSR ones. */ + if (le16_to_cpu(rp->manufacturer) != 10 || + le16_to_cpu(rp->lmp_subver) == 0x0c5c) { /* Clear the reset quirk since this is not an actual * early Bluetooth 1.1 device from CSR. */ @@ -2217,36 +2233,7 @@ done: * The device can work without DDC parameters, so even if it fails * to load the file, no need to fail the setup. */ - err = request_firmware_direct(&fw, fwname, &hdev->dev); - if (err < 0) - return 0; - - BT_INFO("%s: Found Intel DDC parameters: %s", hdev->name, fwname); - - fw_ptr = fw->data; - - /* DDC file contains one or more DDC structure which has - * Length (1 byte), DDC ID (2 bytes), and DDC value (Length - 2). - */ - while (fw->size > fw_ptr - fw->data) { - u8 cmd_plen = fw_ptr[0] + sizeof(u8); - - skb = __hci_cmd_sync(hdev, 0xfc8b, cmd_plen, fw_ptr, - HCI_INIT_TIMEOUT); - if (IS_ERR(skb)) { - BT_ERR("%s: Failed to send Intel_Write_DDC (%ld)", - hdev->name, PTR_ERR(skb)); - release_firmware(fw); - return PTR_ERR(skb); - } - - fw_ptr += cmd_plen; - kfree_skb(skb); - } - - release_firmware(fw); - - BT_INFO("%s: Applying Intel DDC parameters completed", hdev->name); + btintel_load_ddc_config(hdev, fwname); return 0; } @@ -2782,7 +2769,7 @@ static int btusb_probe(struct usb_interface *intf, set_bit(HCI_QUIRK_RESET_ON_CLOSE, &hdev->quirks); /* Fake CSR devices with broken commands */ - if (bcdDevice <= 0x100) + if (bcdDevice <= 0x100 || bcdDevice == 0x134) hdev->setup = btusb_setup_csr; set_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks); diff --git a/drivers/bluetooth/hci_bcm.c b/drivers/bluetooth/hci_bcm.c index 835bfab88ef5..f30654149c63 100644 --- a/drivers/bluetooth/hci_bcm.c +++ b/drivers/bluetooth/hci_bcm.c @@ -31,6 +31,7 @@ #include <linux/clk.h> #include <linux/gpio/consumer.h> #include <linux/tty.h> +#include <linux/interrupt.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> @@ -51,6 +52,8 @@ struct bcm_device { bool clk_enabled; u32 init_speed; + int irq; + u8 irq_polarity; #ifdef CONFIG_PM_SLEEP struct hci_uart *hu; @@ -66,7 +69,7 @@ struct bcm_data { }; /* List of BCM BT UART devices */ -static DEFINE_SPINLOCK(bcm_device_lock); +static DEFINE_MUTEX(bcm_device_lock); static LIST_HEAD(bcm_device_list); static int bcm_set_baudrate(struct hci_uart *hu, unsigned int speed) @@ -80,7 +83,7 @@ static int bcm_set_baudrate(struct hci_uart *hu, unsigned int speed) clock.type = BCM_UART_CLOCK_48MHZ; - BT_DBG("%s: Set Controller clock (%d)", hdev->name, clock.type); + bt_dev_dbg(hdev, "Set Controller clock (%d)", clock.type); /* This Broadcom specific command changes the UART's controller * clock for baud rate > 3000000. @@ -88,15 +91,15 @@ static int bcm_set_baudrate(struct hci_uart *hu, unsigned int speed) skb = __hci_cmd_sync(hdev, 0xfc45, 1, &clock, HCI_INIT_TIMEOUT); if (IS_ERR(skb)) { int err = PTR_ERR(skb); - BT_ERR("%s: BCM: failed to write clock command (%d)", - hdev->name, err); + bt_dev_err(hdev, "BCM: failed to write clock (%d)", + err); return err; } kfree_skb(skb); } - BT_DBG("%s: Set Controller UART speed to %d bit/s", hdev->name, speed); + bt_dev_dbg(hdev, "Set Controller UART speed to %d bit/s", speed); param.zero = cpu_to_le16(0); param.baud_rate = cpu_to_le32(speed); @@ -108,8 +111,8 @@ static int bcm_set_baudrate(struct hci_uart *hu, unsigned int speed) HCI_INIT_TIMEOUT); if (IS_ERR(skb)) { int err = PTR_ERR(skb); - BT_ERR("%s: BCM: failed to write update baudrate command (%d)", - hdev->name, err); + bt_dev_err(hdev, "BCM: failed to write update baudrate (%d)", + err); return err; } @@ -149,12 +152,92 @@ static int bcm_gpio_set_power(struct bcm_device *dev, bool powered) return 0; } +#ifdef CONFIG_PM_SLEEP +static irqreturn_t bcm_host_wake(int irq, void *data) +{ + struct bcm_device *bdev = data; + + bt_dev_dbg(bdev, "Host wake IRQ"); + + return IRQ_HANDLED; +} + +static int bcm_request_irq(struct bcm_data *bcm) +{ + struct bcm_device *bdev = bcm->dev; + int err = 0; + + /* If this is not a platform device, do not enable PM functionalities */ + mutex_lock(&bcm_device_lock); + if (!bcm_device_exists(bdev)) { + err = -ENODEV; + goto unlock; + } + + if (bdev->irq > 0) { + err = devm_request_irq(&bdev->pdev->dev, bdev->irq, + bcm_host_wake, IRQF_TRIGGER_RISING, + "host_wake", bdev); + if (err) + goto unlock; + + device_init_wakeup(&bdev->pdev->dev, true); + } + +unlock: + mutex_unlock(&bcm_device_lock); + + return err; +} + +static const struct bcm_set_sleep_mode default_sleep_params = { + .sleep_mode = 1, /* 0=Disabled, 1=UART, 2=Reserved, 3=USB */ + .idle_host = 2, /* idle threshold HOST, in 300ms */ + .idle_dev = 2, /* idle threshold device, in 300ms */ + .bt_wake_active = 1, /* BT_WAKE active mode: 1 = high, 0 = low */ + .host_wake_active = 0, /* HOST_WAKE active mode: 1 = high, 0 = low */ + .allow_host_sleep = 1, /* Allow host sleep in SCO flag */ + .combine_modes = 0, /* Combine sleep and LPM flag */ + .tristate_control = 0, /* Allow tri-state control of UART tx flag */ + /* Irrelevant USB flags */ + .usb_auto_sleep = 0, + .usb_resume_timeout = 0, + .pulsed_host_wake = 0, + .break_to_host = 0 +}; + +static int bcm_setup_sleep(struct hci_uart *hu) +{ + struct bcm_data *bcm = hu->priv; + struct sk_buff *skb; + struct bcm_set_sleep_mode sleep_params = default_sleep_params; + + sleep_params.host_wake_active = !bcm->dev->irq_polarity; + + skb = __hci_cmd_sync(hu->hdev, 0xfc27, sizeof(sleep_params), + &sleep_params, HCI_INIT_TIMEOUT); + if (IS_ERR(skb)) { + int err = PTR_ERR(skb); + bt_dev_err(hu->hdev, "Sleep VSC failed (%d)", err); + return err; + } + kfree_skb(skb); + + bt_dev_dbg(hu->hdev, "Set Sleep Parameters VSC succeeded"); + + return 0; +} +#else +static inline int bcm_request_irq(struct bcm_data *bcm) { return 0; } +static inline int bcm_setup_sleep(struct hci_uart *hu) { return 0; } +#endif + static int bcm_open(struct hci_uart *hu) { struct bcm_data *bcm; struct list_head *p; - BT_DBG("hu %p", hu); + bt_dev_dbg(hu->hdev, "hu %p", hu); bcm = kzalloc(sizeof(*bcm), GFP_KERNEL); if (!bcm) @@ -164,7 +247,7 @@ static int bcm_open(struct hci_uart *hu) hu->priv = bcm; - spin_lock(&bcm_device_lock); + mutex_lock(&bcm_device_lock); list_for_each(p, &bcm_device_list) { struct bcm_device *dev = list_entry(p, struct bcm_device, list); @@ -178,14 +261,12 @@ static int bcm_open(struct hci_uart *hu) #ifdef CONFIG_PM_SLEEP dev->hu = hu; #endif + bcm_gpio_set_power(bcm->dev, true); break; } } - if (bcm->dev) - bcm_gpio_set_power(bcm->dev, true); - - spin_unlock(&bcm_device_lock); + mutex_unlock(&bcm_device_lock); return 0; } @@ -193,18 +274,24 @@ static int bcm_open(struct hci_uart *hu) static int bcm_close(struct hci_uart *hu) { struct bcm_data *bcm = hu->priv; + struct bcm_device *bdev = bcm->dev; - BT_DBG("hu %p", hu); + bt_dev_dbg(hu->hdev, "hu %p", hu); /* Protect bcm->dev against removal of the device or driver */ - spin_lock(&bcm_device_lock); - if (bcm_device_exists(bcm->dev)) { - bcm_gpio_set_power(bcm->dev, false); + mutex_lock(&bcm_device_lock); + if (bcm_device_exists(bdev)) { + bcm_gpio_set_power(bdev, false); #ifdef CONFIG_PM_SLEEP - bcm->dev->hu = NULL; + if (device_can_wakeup(&bdev->pdev->dev)) { + devm_free_irq(&bdev->pdev->dev, bdev->irq, bdev); + device_init_wakeup(&bdev->pdev->dev, false); + } + + bdev->hu = NULL; #endif } - spin_unlock(&bcm_device_lock); + mutex_unlock(&bcm_device_lock); skb_queue_purge(&bcm->txq); kfree_skb(bcm->rx_skb); @@ -218,7 +305,7 @@ static int bcm_flush(struct hci_uart *hu) { struct bcm_data *bcm = hu->priv; - BT_DBG("hu %p", hu); + bt_dev_dbg(hu->hdev, "hu %p", hu); skb_queue_purge(&bcm->txq); @@ -227,12 +314,13 @@ static int bcm_flush(struct hci_uart *hu) static int bcm_setup(struct hci_uart *hu) { + struct bcm_data *bcm = hu->priv; char fw_name[64]; const struct firmware *fw; unsigned int speed; int err; - BT_DBG("hu %p", hu); + bt_dev_dbg(hu->hdev, "hu %p", hu); hu->hdev->set_bdaddr = btbcm_set_bdaddr; @@ -242,13 +330,13 @@ static int bcm_setup(struct hci_uart *hu) err = request_firmware(&fw, fw_name, &hu->hdev->dev); if (err < 0) { - BT_INFO("%s: BCM: Patch %s not found", hu->hdev->name, fw_name); + bt_dev_info(hu->hdev, "BCM: Patch %s not found", fw_name); return 0; } err = btbcm_patchram(hu->hdev, fw); if (err) { - BT_INFO("%s: BCM: Patch failed (%d)", hu->hdev->name, err); + bt_dev_info(hu->hdev, "BCM: Patch failed (%d)", err); goto finalize; } @@ -281,6 +369,12 @@ finalize: release_firmware(fw); err = btbcm_finalize(hu->hdev); + if (err) + return err; + + err = bcm_request_irq(bcm); + if (!err) + err = bcm_setup_sleep(hu); return err; } @@ -302,7 +396,7 @@ static int bcm_recv(struct hci_uart *hu, const void *data, int count) bcm_recv_pkts, ARRAY_SIZE(bcm_recv_pkts)); if (IS_ERR(bcm->rx_skb)) { int err = PTR_ERR(bcm->rx_skb); - BT_ERR("%s: Frame reassembly failed (%d)", hu->hdev->name, err); + bt_dev_err(hu->hdev, "Frame reassembly failed (%d)", err); bcm->rx_skb = NULL; return err; } @@ -314,7 +408,7 @@ static int bcm_enqueue(struct hci_uart *hu, struct sk_buff *skb) { struct bcm_data *bcm = hu->priv; - BT_DBG("hu %p skb %p", hu, skb); + bt_dev_dbg(hu->hdev, "hu %p skb %p", hu, skb); /* Prepend skb with frame type */ memcpy(skb_push(skb, 1), &bt_cb(skb)->pkt_type, 1); @@ -335,10 +429,11 @@ static struct sk_buff *bcm_dequeue(struct hci_uart *hu) static int bcm_suspend(struct device *dev) { struct bcm_device *bdev = platform_get_drvdata(to_platform_device(dev)); + int error; - BT_DBG("suspend (%p): is_suspended %d", bdev, bdev->is_suspended); + bt_dev_dbg(bdev, "suspend: is_suspended %d", bdev->is_suspended); - spin_lock(&bcm_device_lock); + mutex_lock(&bcm_device_lock); if (!bdev->hu) goto unlock; @@ -353,12 +448,18 @@ static int bcm_suspend(struct device *dev) /* Suspend the device */ if (bdev->device_wakeup) { gpiod_set_value(bdev->device_wakeup, false); - BT_DBG("suspend, delaying 15 ms"); + bt_dev_dbg(bdev, "suspend, delaying 15 ms"); mdelay(15); } + if (device_may_wakeup(&bdev->pdev->dev)) { + error = enable_irq_wake(bdev->irq); + if (!error) + bt_dev_dbg(bdev, "BCM irq: enabled"); + } + unlock: - spin_unlock(&bcm_device_lock); + mutex_unlock(&bcm_device_lock); return 0; } @@ -368,16 +469,21 @@ static int bcm_resume(struct device *dev) { struct bcm_device *bdev = platform_get_drvdata(to_platform_device(dev)); - BT_DBG("resume (%p): is_suspended %d", bdev, bdev->is_suspended); + bt_dev_dbg(bdev, "resume: is_suspended %d", bdev->is_suspended); - spin_lock(&bcm_device_lock); + mutex_lock(&bcm_device_lock); if (!bdev->hu) goto unlock; + if (device_may_wakeup(&bdev->pdev->dev)) { + disable_irq_wake(bdev->irq); + bt_dev_dbg(bdev, "BCM irq: disabled"); + } + if (bdev->device_wakeup) { gpiod_set_value(bdev->device_wakeup, true); - BT_DBG("resume, delaying 15 ms"); + bt_dev_dbg(bdev, "resume, delaying 15 ms"); mdelay(15); } @@ -389,7 +495,7 @@ static int bcm_resume(struct device *dev) } unlock: - spin_unlock(&bcm_device_lock); + mutex_unlock(&bcm_device_lock); return 0; } @@ -397,10 +503,12 @@ unlock: static const struct acpi_gpio_params device_wakeup_gpios = { 0, 0, false }; static const struct acpi_gpio_params shutdown_gpios = { 1, 0, false }; +static const struct acpi_gpio_params host_wakeup_gpios = { 2, 0, false }; static const struct acpi_gpio_mapping acpi_bcm_default_gpios[] = { { "device-wakeup-gpios", &device_wakeup_gpios, 1 }, { "shutdown-gpios", &shutdown_gpios, 1 }, + { "host-wakeup-gpios", &host_wakeup_gpios, 1 }, { }, }; @@ -408,13 +516,30 @@ static const struct acpi_gpio_mapping acpi_bcm_default_gpios[] = { static int bcm_resource(struct acpi_resource *ares, void *data) { struct bcm_device *dev = data; - - if (ares->type == ACPI_RESOURCE_TYPE_SERIAL_BUS) { - struct acpi_resource_uart_serialbus *sb; - + struct acpi_resource_extended_irq *irq; + struct acpi_resource_gpio *gpio; + struct acpi_resource_uart_serialbus *sb; + + switch (ares->type) { + case ACPI_RESOURCE_TYPE_EXTENDED_IRQ: + irq = &ares->data.extended_irq; + dev->irq_polarity = irq->polarity; + break; + + case ACPI_RESOURCE_TYPE_GPIO: + gpio = &ares->data.gpio; + if (gpio->connection_type == ACPI_RESOURCE_GPIO_TYPE_INT) + dev->irq_polarity = gpio->polarity; + break; + + case ACPI_RESOURCE_TYPE_SERIAL_BUS: sb = &ares->data.uart_serial_bus; if (sb->type == ACPI_RESOURCE_SERIAL_TYPE_UART) dev->init_speed = sb->default_baud_rate; + break; + + default: + break; } /* Always tell the ACPI core to skip this resource */ @@ -453,6 +578,21 @@ static int bcm_acpi_probe(struct bcm_device *dev) if (IS_ERR(dev->shutdown)) return PTR_ERR(dev->shutdown); + /* IRQ can be declared in ACPI table as Interrupt or GpioInt */ + dev->irq = platform_get_irq(pdev, 0); + if (dev->irq <= 0) { + struct gpio_desc *gpio; + + gpio = devm_gpiod_get_optional(&pdev->dev, "host-wakeup", + GPIOD_IN); + if (IS_ERR(gpio)) + return PTR_ERR(gpio); + + dev->irq = gpiod_to_irq(gpio); + } + + dev_info(&pdev->dev, "BCM irq: %d\n", dev->irq); + /* Make sure at-least one of the GPIO is defined and that * a name is specified for this instance */ @@ -504,9 +644,9 @@ static int bcm_probe(struct platform_device *pdev) dev_info(&pdev->dev, "%s device registered.\n", dev->name); /* Place this instance on the device list */ - spin_lock(&bcm_device_lock); + mutex_lock(&bcm_device_lock); list_add_tail(&dev->list, &bcm_device_list); - spin_unlock(&bcm_device_lock); + mutex_unlock(&bcm_device_lock); bcm_gpio_set_power(dev, false); @@ -517,9 +657,9 @@ static int bcm_remove(struct platform_device *pdev) { struct bcm_device *dev = platform_get_drvdata(pdev); - spin_lock(&bcm_device_lock); + mutex_lock(&bcm_device_lock); list_del(&dev->list); - spin_unlock(&bcm_device_lock); + mutex_unlock(&bcm_device_lock); acpi_dev_remove_driver_gpios(ACPI_COMPANION(&pdev->dev)); diff --git a/drivers/bluetooth/hci_intel.c b/drivers/bluetooth/hci_intel.c index cf07d1121956..49e25409de67 100644 --- a/drivers/bluetooth/hci_intel.c +++ b/drivers/bluetooth/hci_intel.c @@ -31,6 +31,8 @@ #include <linux/platform_device.h> #include <linux/gpio/consumer.h> #include <linux/acpi.h> +#include <linux/interrupt.h> +#include <linux/pm_runtime.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> @@ -43,19 +45,45 @@ #define STATE_FIRMWARE_LOADED 2 #define STATE_FIRMWARE_FAILED 3 #define STATE_BOOTING 4 +#define STATE_LPM_ENABLED 5 +#define STATE_TX_ACTIVE 6 +#define STATE_SUSPENDED 7 +#define STATE_LPM_TRANSACTION 8 + +#define HCI_LPM_WAKE_PKT 0xf0 +#define HCI_LPM_PKT 0xf1 +#define HCI_LPM_MAX_SIZE 10 +#define HCI_LPM_HDR_SIZE HCI_EVENT_HDR_SIZE + +#define LPM_OP_TX_NOTIFY 0x00 +#define LPM_OP_SUSPEND_ACK 0x02 +#define LPM_OP_RESUME_ACK 0x03 + +#define LPM_SUSPEND_DELAY_MS 1000 + +struct hci_lpm_pkt { + __u8 opcode; + __u8 dlen; + __u8 data[0]; +} __packed; struct intel_device { struct list_head list; struct platform_device *pdev; struct gpio_desc *reset; + struct hci_uart *hu; + struct mutex hu_lock; + int irq; }; static LIST_HEAD(intel_device_list); -static DEFINE_SPINLOCK(intel_device_list_lock); +static DEFINE_MUTEX(intel_device_list_lock); struct intel_data { struct sk_buff *rx_skb; struct sk_buff_head txq; + struct work_struct busy_work; + struct hci_uart *hu; unsigned long flags; }; @@ -101,24 +129,185 @@ static int intel_wait_booting(struct hci_uart *hu) msecs_to_jiffies(1000)); if (err == 1) { - BT_ERR("%s: Device boot interrupted", hu->hdev->name); + bt_dev_err(hu->hdev, "Device boot interrupted"); return -EINTR; } if (err) { - BT_ERR("%s: Device boot timeout", hu->hdev->name); + bt_dev_err(hu->hdev, "Device boot timeout"); return -ETIMEDOUT; } return err; } +#ifdef CONFIG_PM +static int intel_wait_lpm_transaction(struct hci_uart *hu) +{ + struct intel_data *intel = hu->priv; + int err; + + err = wait_on_bit_timeout(&intel->flags, STATE_LPM_TRANSACTION, + TASK_INTERRUPTIBLE, + msecs_to_jiffies(1000)); + + if (err == 1) { + bt_dev_err(hu->hdev, "LPM transaction interrupted"); + return -EINTR; + } + + if (err) { + bt_dev_err(hu->hdev, "LPM transaction timeout"); + return -ETIMEDOUT; + } + + return err; +} + +static int intel_lpm_suspend(struct hci_uart *hu) +{ + static const u8 suspend[] = { 0x01, 0x01, 0x01 }; + struct intel_data *intel = hu->priv; + struct sk_buff *skb; + + if (!test_bit(STATE_LPM_ENABLED, &intel->flags) || + test_bit(STATE_SUSPENDED, &intel->flags)) + return 0; + + if (test_bit(STATE_TX_ACTIVE, &intel->flags)) + return -EAGAIN; + + bt_dev_dbg(hu->hdev, "Suspending"); + + skb = bt_skb_alloc(sizeof(suspend), GFP_KERNEL); + if (!skb) { + bt_dev_err(hu->hdev, "Failed to alloc memory for LPM packet"); + return -ENOMEM; + } + + memcpy(skb_put(skb, sizeof(suspend)), suspend, sizeof(suspend)); + bt_cb(skb)->pkt_type = HCI_LPM_PKT; + + set_bit(STATE_LPM_TRANSACTION, &intel->flags); + + /* LPM flow is a priority, enqueue packet at list head */ + skb_queue_head(&intel->txq, skb); + hci_uart_tx_wakeup(hu); + + intel_wait_lpm_transaction(hu); + /* Even in case of failure, continue and test the suspended flag */ + + clear_bit(STATE_LPM_TRANSACTION, &intel->flags); + + if (!test_bit(STATE_SUSPENDED, &intel->flags)) { + bt_dev_err(hu->hdev, "Device suspend error"); + return -EINVAL; + } + + bt_dev_dbg(hu->hdev, "Suspended"); + + hci_uart_set_flow_control(hu, true); + + return 0; +} + +static int intel_lpm_resume(struct hci_uart *hu) +{ + struct intel_data *intel = hu->priv; + struct sk_buff *skb; + + if (!test_bit(STATE_LPM_ENABLED, &intel->flags) || + !test_bit(STATE_SUSPENDED, &intel->flags)) + return 0; + + bt_dev_dbg(hu->hdev, "Resuming"); + + hci_uart_set_flow_control(hu, false); + + skb = bt_skb_alloc(0, GFP_KERNEL); + if (!skb) { + bt_dev_err(hu->hdev, "Failed to alloc memory for LPM packet"); + return -ENOMEM; + } + + bt_cb(skb)->pkt_type = HCI_LPM_WAKE_PKT; + + set_bit(STATE_LPM_TRANSACTION, &intel->flags); + + /* LPM flow is a priority, enqueue packet at list head */ + skb_queue_head(&intel->txq, skb); + hci_uart_tx_wakeup(hu); + + intel_wait_lpm_transaction(hu); + /* Even in case of failure, continue and test the suspended flag */ + + clear_bit(STATE_LPM_TRANSACTION, &intel->flags); + + if (test_bit(STATE_SUSPENDED, &intel->flags)) { + bt_dev_err(hu->hdev, "Device resume error"); + return -EINVAL; + } + + bt_dev_dbg(hu->hdev, "Resumed"); + + return 0; +} +#endif /* CONFIG_PM */ + +static int intel_lpm_host_wake(struct hci_uart *hu) +{ + static const u8 lpm_resume_ack[] = { LPM_OP_RESUME_ACK, 0x00 }; + struct intel_data *intel = hu->priv; + struct sk_buff *skb; + + hci_uart_set_flow_control(hu, false); + + clear_bit(STATE_SUSPENDED, &intel->flags); + + skb = bt_skb_alloc(sizeof(lpm_resume_ack), GFP_KERNEL); + if (!skb) { + bt_dev_err(hu->hdev, "Failed to alloc memory for LPM packet"); + return -ENOMEM; + } + + memcpy(skb_put(skb, sizeof(lpm_resume_ack)), lpm_resume_ack, + sizeof(lpm_resume_ack)); + bt_cb(skb)->pkt_type = HCI_LPM_PKT; + + /* LPM flow is a priority, enqueue packet at list head */ + skb_queue_head(&intel->txq, skb); + hci_uart_tx_wakeup(hu); + + bt_dev_dbg(hu->hdev, "Resumed by controller"); + + return 0; +} + +static irqreturn_t intel_irq(int irq, void *dev_id) +{ + struct intel_device *idev = dev_id; + + dev_info(&idev->pdev->dev, "hci_intel irq\n"); + + mutex_lock(&idev->hu_lock); + if (idev->hu) + intel_lpm_host_wake(idev->hu); + mutex_unlock(&idev->hu_lock); + + /* Host/Controller are now LPM resumed, trigger a new delayed suspend */ + pm_runtime_get(&idev->pdev->dev); + pm_runtime_mark_last_busy(&idev->pdev->dev); + pm_runtime_put_autosuspend(&idev->pdev->dev); + + return IRQ_HANDLED; +} + static int intel_set_power(struct hci_uart *hu, bool powered) { struct list_head *p; int err = -ENODEV; - spin_lock(&intel_device_list_lock); + mutex_lock(&intel_device_list_lock); list_for_each(p, &intel_device_list) { struct intel_device *idev = list_entry(p, struct intel_device, @@ -139,13 +328,73 @@ static int intel_set_power(struct hci_uart *hu, bool powered) hu, dev_name(&idev->pdev->dev), powered); gpiod_set_value(idev->reset, powered); + + /* Provide to idev a hu reference which is used to run LPM + * transactions (lpm suspend/resume) from PM callbacks. + * hu needs to be protected against concurrent removing during + * these PM ops. + */ + mutex_lock(&idev->hu_lock); + idev->hu = powered ? hu : NULL; + mutex_unlock(&idev->hu_lock); + + if (idev->irq < 0) + break; + + if (powered && device_can_wakeup(&idev->pdev->dev)) { + err = devm_request_threaded_irq(&idev->pdev->dev, + idev->irq, NULL, + intel_irq, + IRQF_ONESHOT, + "bt-host-wake", idev); + if (err) { + BT_ERR("hu %p, unable to allocate irq-%d", + hu, idev->irq); + break; + } + + device_wakeup_enable(&idev->pdev->dev); + + pm_runtime_set_active(&idev->pdev->dev); + pm_runtime_use_autosuspend(&idev->pdev->dev); + pm_runtime_set_autosuspend_delay(&idev->pdev->dev, + LPM_SUSPEND_DELAY_MS); + pm_runtime_enable(&idev->pdev->dev); + } else if (!powered && device_may_wakeup(&idev->pdev->dev)) { + devm_free_irq(&idev->pdev->dev, idev->irq, idev); + device_wakeup_disable(&idev->pdev->dev); + + pm_runtime_disable(&idev->pdev->dev); + } } - spin_unlock(&intel_device_list_lock); + mutex_unlock(&intel_device_list_lock); return err; } +static void intel_busy_work(struct work_struct *work) +{ + struct list_head *p; + struct intel_data *intel = container_of(work, struct intel_data, + busy_work); + + /* Link is busy, delay the suspend */ + mutex_lock(&intel_device_list_lock); + list_for_each(p, &intel_device_list) { + struct intel_device *idev = list_entry(p, struct intel_device, + list); + + if (intel->hu->tty->dev->parent == idev->pdev->dev.parent) { + pm_runtime_get(&idev->pdev->dev); + pm_runtime_mark_last_busy(&idev->pdev->dev); + pm_runtime_put_autosuspend(&idev->pdev->dev); + break; + } + } + mutex_unlock(&intel_device_list_lock); +} + static int intel_open(struct hci_uart *hu) { struct intel_data *intel; @@ -157,6 +406,9 @@ static int intel_open(struct hci_uart *hu) return -ENOMEM; skb_queue_head_init(&intel->txq); + INIT_WORK(&intel->busy_work, intel_busy_work); + + intel->hu = hu; hu->priv = intel; @@ -172,6 +424,8 @@ static int intel_close(struct hci_uart *hu) BT_DBG("hu %p", hu); + cancel_work_sync(&intel->busy_work); + intel_set_power(hu, false); skb_queue_purge(&intel->txq); @@ -237,11 +491,11 @@ static int intel_set_baudrate(struct hci_uart *hu, unsigned int speed) if (err && err != ETIMEDOUT) return err; - BT_INFO("%s: Change controller speed to %d", hdev->name, speed); + bt_dev_info(hdev, "Change controller speed to %d", speed); speed_cmd[3] = intel_convert_speed(speed); if (speed_cmd[3] == 0xff) { - BT_ERR("%s: Unsupported speed", hdev->name); + bt_dev_err(hdev, "Unsupported speed"); return -EINVAL; } @@ -250,16 +504,15 @@ static int intel_set_baudrate(struct hci_uart *hu, unsigned int speed) */ skb = __hci_cmd_sync(hdev, 0xfc05, 0, NULL, HCI_INIT_TIMEOUT); if (IS_ERR(skb)) { - BT_ERR("%s: Reading Intel version information failed (%ld)", - hdev->name, PTR_ERR(skb)); + bt_dev_err(hdev, "Reading Intel version information failed (%ld)", + PTR_ERR(skb)); return PTR_ERR(skb); } kfree_skb(skb); skb = bt_skb_alloc(sizeof(speed_cmd), GFP_KERNEL); if (!skb) { - BT_ERR("%s: Failed to allocate memory for baudrate packet", - hdev->name); + bt_dev_err(hdev, "Failed to alloc memory for baudrate packet"); return -ENOMEM; } @@ -284,11 +537,14 @@ static int intel_setup(struct hci_uart *hu) { static const u8 reset_param[] = { 0x00, 0x01, 0x00, 0x01, 0x00, 0x08, 0x04, 0x00 }; + static const u8 lpm_param[] = { 0x03, 0x07, 0x01, 0x0b }; struct intel_data *intel = hu->priv; + struct intel_device *idev = NULL; struct hci_dev *hdev = hu->hdev; struct sk_buff *skb; struct intel_version *ver; struct intel_boot_params *params; + struct list_head *p; const struct firmware *fw; const u8 *fw_ptr; char fwname[64]; @@ -299,7 +555,7 @@ static int intel_setup(struct hci_uart *hu) int speed_change = 0; int err; - BT_DBG("%s", hdev->name); + bt_dev_dbg(hdev, "start intel_setup"); hu->hdev->set_bdaddr = btintel_set_bdaddr; @@ -335,21 +591,21 @@ static int intel_setup(struct hci_uart *hu) */ skb = __hci_cmd_sync(hdev, 0xfc05, 0, NULL, HCI_INIT_TIMEOUT); if (IS_ERR(skb)) { - BT_ERR("%s: Reading Intel version information failed (%ld)", - hdev->name, PTR_ERR(skb)); + bt_dev_err(hdev, "Reading Intel version information failed (%ld)", + PTR_ERR(skb)); return PTR_ERR(skb); } if (skb->len != sizeof(*ver)) { - BT_ERR("%s: Intel version event size mismatch", hdev->name); + bt_dev_err(hdev, "Intel version event size mismatch"); kfree_skb(skb); return -EILSEQ; } ver = (struct intel_version *)skb->data; if (ver->status) { - BT_ERR("%s: Intel version command failure (%02x)", - hdev->name, ver->status); + bt_dev_err(hdev, "Intel version command failure (%02x)", + ver->status); err = -bt_to_errno(ver->status); kfree_skb(skb); return err; @@ -359,8 +615,8 @@ static int intel_setup(struct hci_uart *hu) * for now only accept this single value. */ if (ver->hw_platform != 0x37) { - BT_ERR("%s: Unsupported Intel hardware platform (%u)", - hdev->name, ver->hw_platform); + bt_dev_err(hdev, "Unsupported Intel hardware platform (%u)", + ver->hw_platform); kfree_skb(skb); return -EINVAL; } @@ -371,8 +627,8 @@ static int intel_setup(struct hci_uart *hu) * when newer hardware variants come along. */ if (ver->hw_variant != 0x0b) { - BT_ERR("%s: Unsupported Intel hardware variant (%u)", - hdev->name, ver->hw_variant); + bt_dev_err(hdev, "Unsupported Intel hardware variant (%u)", + ver->hw_variant); kfree_skb(skb); return -EINVAL; } @@ -403,8 +659,8 @@ static int intel_setup(struct hci_uart *hu) * choice is to return an error and abort the device initialization. */ if (ver->fw_variant != 0x06) { - BT_ERR("%s: Unsupported Intel firmware variant (%u)", - hdev->name, ver->fw_variant); + bt_dev_err(hdev, "Unsupported Intel firmware variant (%u)", + ver->fw_variant); kfree_skb(skb); return -ENODEV; } @@ -416,33 +672,33 @@ static int intel_setup(struct hci_uart *hu) */ skb = __hci_cmd_sync(hdev, 0xfc0d, 0, NULL, HCI_INIT_TIMEOUT); if (IS_ERR(skb)) { - BT_ERR("%s: Reading Intel boot parameters failed (%ld)", - hdev->name, PTR_ERR(skb)); + bt_dev_err(hdev, "Reading Intel boot parameters failed (%ld)", + PTR_ERR(skb)); return PTR_ERR(skb); } if (skb->len != sizeof(*params)) { - BT_ERR("%s: Intel boot parameters size mismatch", hdev->name); + bt_dev_err(hdev, "Intel boot parameters size mismatch"); kfree_skb(skb); return -EILSEQ; } params = (struct intel_boot_params *)skb->data; if (params->status) { - BT_ERR("%s: Intel boot parameters command failure (%02x)", - hdev->name, params->status); + bt_dev_err(hdev, "Intel boot parameters command failure (%02x)", + params->status); err = -bt_to_errno(params->status); kfree_skb(skb); return err; } - BT_INFO("%s: Device revision is %u", hdev->name, - le16_to_cpu(params->dev_revid)); + bt_dev_info(hdev, "Device revision is %u", + le16_to_cpu(params->dev_revid)); - BT_INFO("%s: Secure boot is %s", hdev->name, - params->secure_boot ? "enabled" : "disabled"); + bt_dev_info(hdev, "Secure boot is %s", + params->secure_boot ? "enabled" : "disabled"); - BT_INFO("%s: Minimum firmware build %u week %u %u", hdev->name, + bt_dev_info(hdev, "Minimum firmware build %u week %u %u", params->min_fw_build_nn, params->min_fw_build_cw, 2000 + params->min_fw_build_yy); @@ -451,8 +707,8 @@ static int intel_setup(struct hci_uart *hu) * that this bootloader does not send them, then abort the setup. */ if (params->limited_cce != 0x00) { - BT_ERR("%s: Unsupported Intel firmware loading method (%u)", - hdev->name, params->limited_cce); + bt_dev_err(hdev, "Unsupported Intel firmware loading method (%u)", + params->limited_cce); kfree_skb(skb); return -EINVAL; } @@ -461,7 +717,7 @@ static int intel_setup(struct hci_uart *hu) * also be no valid address for the operational firmware. */ if (!bacmp(¶ms->otp_bdaddr, BDADDR_ANY)) { - BT_INFO("%s: No device address configured", hdev->name); + bt_dev_info(hdev, "No device address configured"); set_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks); } @@ -476,19 +732,23 @@ static int intel_setup(struct hci_uart *hu) err = request_firmware(&fw, fwname, &hdev->dev); if (err < 0) { - BT_ERR("%s: Failed to load Intel firmware file (%d)", - hdev->name, err); + bt_dev_err(hdev, "Failed to load Intel firmware file (%d)", + err); kfree_skb(skb); return err; } - BT_INFO("%s: Found device firmware: %s", hdev->name, fwname); + bt_dev_info(hdev, "Found device firmware: %s", fwname); + + /* Save the DDC file name for later */ + snprintf(fwname, sizeof(fwname), "intel/ibt-11-%u.ddc", + le16_to_cpu(params->dev_revid)); kfree_skb(skb); if (fw->size < 644) { - BT_ERR("%s: Invalid size of firmware file (%zu)", - hdev->name, fw->size); + bt_dev_err(hdev, "Invalid size of firmware file (%zu)", + fw->size); err = -EBADF; goto done; } @@ -500,8 +760,7 @@ static int intel_setup(struct hci_uart *hu) */ err = btintel_secure_send(hdev, 0x00, 128, fw->data); if (err < 0) { - BT_ERR("%s: Failed to send firmware header (%d)", - hdev->name, err); + bt_dev_err(hdev, "Failed to send firmware header (%d)", err); goto done; } @@ -510,8 +769,8 @@ static int intel_setup(struct hci_uart *hu) */ err = btintel_secure_send(hdev, 0x03, 256, fw->data + 128); if (err < 0) { - BT_ERR("%s: Failed to send firmware public key (%d)", - hdev->name, err); + bt_dev_err(hdev, "Failed to send firmware public key (%d)", + err); goto done; } @@ -520,8 +779,8 @@ static int intel_setup(struct hci_uart *hu) */ err = btintel_secure_send(hdev, 0x02, 256, fw->data + 388); if (err < 0) { - BT_ERR("%s: Failed to send firmware signature (%d)", - hdev->name, err); + bt_dev_err(hdev, "Failed to send firmware signature (%d)", + err); goto done; } @@ -533,8 +792,8 @@ static int intel_setup(struct hci_uart *hu) frag_len += sizeof(*cmd) + cmd->plen; - BT_DBG("%s: patching %td/%zu", hdev->name, - (fw_ptr - fw->data), fw->size); + bt_dev_dbg(hdev, "Patching %td/%zu", (fw_ptr - fw->data), + fw->size); /* The parameter length of the secure send command requires * a 4 byte alignment. It happens so that the firmware file @@ -552,8 +811,8 @@ static int intel_setup(struct hci_uart *hu) */ err = btintel_secure_send(hdev, 0x01, frag_len, fw_ptr); if (err < 0) { - BT_ERR("%s: Failed to send firmware data (%d)", - hdev->name, err); + bt_dev_err(hdev, "Failed to send firmware data (%d)", + err); goto done; } @@ -563,7 +822,7 @@ static int intel_setup(struct hci_uart *hu) set_bit(STATE_FIRMWARE_LOADED, &intel->flags); - BT_INFO("%s: Waiting for firmware download to complete", hdev->name); + bt_dev_info(hdev, "Waiting for firmware download to complete"); /* Before switching the device into operational mode and with that * booting the loaded firmware, wait for the bootloader notification @@ -580,19 +839,19 @@ static int intel_setup(struct hci_uart *hu) TASK_INTERRUPTIBLE, msecs_to_jiffies(5000)); if (err == 1) { - BT_ERR("%s: Firmware loading interrupted", hdev->name); + bt_dev_err(hdev, "Firmware loading interrupted"); err = -EINTR; goto done; } if (err) { - BT_ERR("%s: Firmware loading timeout", hdev->name); + bt_dev_err(hdev, "Firmware loading timeout"); err = -ETIMEDOUT; goto done; } if (test_bit(STATE_FIRMWARE_FAILED, &intel->flags)) { - BT_ERR("%s: Firmware loading failed", hdev->name); + bt_dev_err(hdev, "Firmware loading failed"); err = -ENOEXEC; goto done; } @@ -601,7 +860,7 @@ static int intel_setup(struct hci_uart *hu) delta = ktime_sub(rettime, calltime); duration = (unsigned long long) ktime_to_ns(delta) >> 10; - BT_INFO("%s: Firmware loaded in %llu usecs", hdev->name, duration); + bt_dev_info(hdev, "Firmware loaded in %llu usecs", duration); done: release_firmware(fw); @@ -634,7 +893,7 @@ done: * 1 second. However if that happens, then just fail the setup * since something went wrong. */ - BT_INFO("%s: Waiting for device to boot", hdev->name); + bt_dev_info(hdev, "Waiting for device to boot"); err = intel_wait_booting(hu); if (err) @@ -646,7 +905,39 @@ done: delta = ktime_sub(rettime, calltime); duration = (unsigned long long) ktime_to_ns(delta) >> 10; - BT_INFO("%s: Device booted in %llu usecs", hdev->name, duration); + bt_dev_info(hdev, "Device booted in %llu usecs", duration); + + /* Enable LPM if matching pdev with wakeup enabled */ + mutex_lock(&intel_device_list_lock); + list_for_each(p, &intel_device_list) { + struct intel_device *dev = list_entry(p, struct intel_device, + list); + if (hu->tty->dev->parent == dev->pdev->dev.parent) { + if (device_may_wakeup(&dev->pdev->dev)) + idev = dev; + break; + } + } + mutex_unlock(&intel_device_list_lock); + + if (!idev) + goto no_lpm; + + bt_dev_info(hdev, "Enabling LPM"); + + skb = __hci_cmd_sync(hdev, 0xfc8b, sizeof(lpm_param), lpm_param, + HCI_CMD_TIMEOUT); + if (IS_ERR(skb)) { + bt_dev_err(hdev, "Failed to enable LPM"); + goto no_lpm; + } + kfree_skb(skb); + + set_bit(STATE_LPM_ENABLED, &intel->flags); + +no_lpm: + /* Ignore errors, device can work without DDC parameters */ + btintel_load_ddc_config(hdev, fwname); skb = __hci_cmd_sync(hdev, HCI_OP_RESET, 0, NULL, HCI_CMD_TIMEOUT); if (IS_ERR(skb)) @@ -659,7 +950,7 @@ done: return err; } - BT_INFO("%s: Setup complete", hdev->name); + bt_dev_info(hdev, "Setup complete"); clear_bit(STATE_BOOTLOADER, &intel->flags); @@ -708,10 +999,71 @@ recv: return hci_recv_frame(hdev, skb); } +static void intel_recv_lpm_notify(struct hci_dev *hdev, int value) +{ + struct hci_uart *hu = hci_get_drvdata(hdev); + struct intel_data *intel = hu->priv; + + bt_dev_dbg(hdev, "TX idle notification (%d)", value); + + if (value) { + set_bit(STATE_TX_ACTIVE, &intel->flags); + schedule_work(&intel->busy_work); + } else { + clear_bit(STATE_TX_ACTIVE, &intel->flags); + } +} + +static int intel_recv_lpm(struct hci_dev *hdev, struct sk_buff *skb) +{ + struct hci_lpm_pkt *lpm = (void *)skb->data; + struct hci_uart *hu = hci_get_drvdata(hdev); + struct intel_data *intel = hu->priv; + + switch (lpm->opcode) { + case LPM_OP_TX_NOTIFY: + if (lpm->dlen < 1) { + bt_dev_err(hu->hdev, "Invalid LPM notification packet"); + break; + } + intel_recv_lpm_notify(hdev, lpm->data[0]); + break; + case LPM_OP_SUSPEND_ACK: + set_bit(STATE_SUSPENDED, &intel->flags); + if (test_and_clear_bit(STATE_LPM_TRANSACTION, &intel->flags)) { + smp_mb__after_atomic(); + wake_up_bit(&intel->flags, STATE_LPM_TRANSACTION); + } + break; + case LPM_OP_RESUME_ACK: + clear_bit(STATE_SUSPENDED, &intel->flags); + if (test_and_clear_bit(STATE_LPM_TRANSACTION, &intel->flags)) { + smp_mb__after_atomic(); + wake_up_bit(&intel->flags, STATE_LPM_TRANSACTION); + } + break; + default: + bt_dev_err(hdev, "Unknown LPM opcode (%02x)", lpm->opcode); + break; + } + + kfree_skb(skb); + + return 0; +} + +#define INTEL_RECV_LPM \ + .type = HCI_LPM_PKT, \ + .hlen = HCI_LPM_HDR_SIZE, \ + .loff = 1, \ + .lsize = 1, \ + .maxlen = HCI_LPM_MAX_SIZE + static const struct h4_recv_pkt intel_recv_pkts[] = { - { H4_RECV_ACL, .recv = hci_recv_frame }, - { H4_RECV_SCO, .recv = hci_recv_frame }, - { H4_RECV_EVENT, .recv = intel_recv_event }, + { H4_RECV_ACL, .recv = hci_recv_frame }, + { H4_RECV_SCO, .recv = hci_recv_frame }, + { H4_RECV_EVENT, .recv = intel_recv_event }, + { INTEL_RECV_LPM, .recv = intel_recv_lpm }, }; static int intel_recv(struct hci_uart *hu, const void *data, int count) @@ -726,7 +1078,7 @@ static int intel_recv(struct hci_uart *hu, const void *data, int count) ARRAY_SIZE(intel_recv_pkts)); if (IS_ERR(intel->rx_skb)) { int err = PTR_ERR(intel->rx_skb); - BT_ERR("%s: Frame reassembly failed (%d)", hu->hdev->name, err); + bt_dev_err(hu->hdev, "Frame reassembly failed (%d)", err); intel->rx_skb = NULL; return err; } @@ -737,9 +1089,27 @@ static int intel_recv(struct hci_uart *hu, const void *data, int count) static int intel_enqueue(struct hci_uart *hu, struct sk_buff *skb) { struct intel_data *intel = hu->priv; + struct list_head *p; BT_DBG("hu %p skb %p", hu, skb); + /* Be sure our controller is resumed and potential LPM transaction + * completed before enqueuing any packet. + */ + mutex_lock(&intel_device_list_lock); + list_for_each(p, &intel_device_list) { + struct intel_device *idev = list_entry(p, struct intel_device, + list); + + if (hu->tty->dev->parent == idev->pdev->dev.parent) { + pm_runtime_get_sync(&idev->pdev->dev); + pm_runtime_mark_last_busy(&idev->pdev->dev); + pm_runtime_put_autosuspend(&idev->pdev->dev); + break; + } + } + mutex_unlock(&intel_device_list_lock); + skb_queue_tail(&intel->txq, skb); return 0; @@ -813,6 +1183,59 @@ static int intel_acpi_probe(struct intel_device *idev) } #endif +#ifdef CONFIG_PM +static int intel_suspend_device(struct device *dev) +{ + struct intel_device *idev = dev_get_drvdata(dev); + + mutex_lock(&idev->hu_lock); + if (idev->hu) + intel_lpm_suspend(idev->hu); + mutex_unlock(&idev->hu_lock); + + return 0; +} + +static int intel_resume_device(struct device *dev) +{ + struct intel_device *idev = dev_get_drvdata(dev); + + mutex_lock(&idev->hu_lock); + if (idev->hu) + intel_lpm_resume(idev->hu); + mutex_unlock(&idev->hu_lock); + + return 0; +} +#endif + +#ifdef CONFIG_PM_SLEEP +static int intel_suspend(struct device *dev) +{ + struct intel_device *idev = dev_get_drvdata(dev); + + if (device_may_wakeup(dev)) + enable_irq_wake(idev->irq); + + return intel_suspend_device(dev); +} + +static int intel_resume(struct device *dev) +{ + struct intel_device *idev = dev_get_drvdata(dev); + + if (device_may_wakeup(dev)) + disable_irq_wake(idev->irq); + + return intel_resume_device(dev); +} +#endif + +static const struct dev_pm_ops intel_pm_ops = { + SET_SYSTEM_SLEEP_PM_OPS(intel_suspend, intel_resume) + SET_RUNTIME_PM_OPS(intel_suspend_device, intel_resume_device, NULL) +}; + static int intel_probe(struct platform_device *pdev) { struct intel_device *idev; @@ -821,6 +1244,8 @@ static int intel_probe(struct platform_device *pdev) if (!idev) return -ENOMEM; + mutex_init(&idev->hu_lock); + idev->pdev = pdev; if (ACPI_HANDLE(&pdev->dev)) { @@ -838,14 +1263,40 @@ static int intel_probe(struct platform_device *pdev) return PTR_ERR(idev->reset); } + idev->irq = platform_get_irq(pdev, 0); + if (idev->irq < 0) { + struct gpio_desc *host_wake; + + dev_err(&pdev->dev, "No IRQ, falling back to gpio-irq\n"); + + host_wake = devm_gpiod_get_optional(&pdev->dev, "host-wake", + GPIOD_IN); + if (IS_ERR(host_wake)) { + dev_err(&pdev->dev, "Unable to retrieve IRQ\n"); + goto no_irq; + } + + idev->irq = gpiod_to_irq(host_wake); + if (idev->irq < 0) { + dev_err(&pdev->dev, "No corresponding irq for gpio\n"); + goto no_irq; + } + } + + /* Only enable wake-up/irq when controller is powered */ + device_set_wakeup_capable(&pdev->dev, true); + device_wakeup_disable(&pdev->dev); + +no_irq: platform_set_drvdata(pdev, idev); /* Place this instance on the device list */ - spin_lock(&intel_device_list_lock); + mutex_lock(&intel_device_list_lock); list_add_tail(&idev->list, &intel_device_list); - spin_unlock(&intel_device_list_lock); + mutex_unlock(&intel_device_list_lock); - dev_info(&pdev->dev, "registered.\n"); + dev_info(&pdev->dev, "registered, gpio(%d)/irq(%d).\n", + desc_to_gpio(idev->reset), idev->irq); return 0; } @@ -854,9 +1305,11 @@ static int intel_remove(struct platform_device *pdev) { struct intel_device *idev = platform_get_drvdata(pdev); - spin_lock(&intel_device_list_lock); + device_wakeup_disable(&pdev->dev); + + mutex_lock(&intel_device_list_lock); list_del(&idev->list); - spin_unlock(&intel_device_list_lock); + mutex_unlock(&intel_device_list_lock); dev_info(&pdev->dev, "unregistered.\n"); @@ -869,6 +1322,7 @@ static struct platform_driver intel_driver = { .driver = { .name = "hci_intel", .acpi_match_table = ACPI_PTR(intel_acpi_match), + .pm = &intel_pm_ops, }, }; diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index 6b9b91267959..21f4ea4ce610 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -41,13 +41,13 @@ #define HCI_IBS_SLEEP_IND 0xFE #define HCI_IBS_WAKE_IND 0xFD #define HCI_IBS_WAKE_ACK 0xFC -#define HCI_MAX_IBS_SIZE 10 +#define HCI_MAX_IBS_SIZE 10 /* Controller states */ #define STATE_IN_BAND_SLEEP_ENABLED 1 -#define IBS_WAKE_RETRANS_TIMEOUT_MS 100 -#define IBS_TX_IDLE_TIMEOUT_MS 2000 +#define IBS_WAKE_RETRANS_TIMEOUT_MS 100 +#define IBS_TX_IDLE_TIMEOUT_MS 2000 #define BAUDRATE_SETTLE_TIMEOUT_MS 300 /* HCI_IBS transmit side sleep protocol states */ @@ -181,8 +181,8 @@ static void serial_clock_vote(unsigned long vote, struct hci_uart *hu) else __serial_clock_off(hu->tty); - BT_DBG("Vote serial clock %s(%s)", new_vote? "true" : "false", - vote? "true" : "false"); + BT_DBG("Vote serial clock %s(%s)", new_vote ? "true" : "false", + vote ? "true" : "false"); diff = jiffies_to_msecs(jiffies - qca->vote_last_jif); @@ -821,7 +821,7 @@ static struct sk_buff *qca_dequeue(struct hci_uart *hu) static uint8_t qca_get_baudrate_value(int speed) { - switch(speed) { + switch (speed) { case 9600: return QCA_BAUDRATE_9600; case 19200: diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c index 655cb967a1f2..9d89900a3f88 100644 --- a/drivers/irqchip/irq-armada-370-xp.c +++ b/drivers/irqchip/irq-armada-370-xp.c @@ -56,9 +56,6 @@ #define ARMADA_370_XP_MAX_PER_CPU_IRQS (28) -#define ARMADA_370_XP_TIMER0_PER_CPU_IRQ (5) -#define ARMADA_370_XP_FABRIC_IRQ (3) - #define IPI_DOORBELL_START (0) #define IPI_DOORBELL_END (8) #define IPI_DOORBELL_MASK 0xFF @@ -81,13 +78,10 @@ static phys_addr_t msi_doorbell_addr; static inline bool is_percpu_irq(irq_hw_number_t irq) { - switch (irq) { - case ARMADA_370_XP_TIMER0_PER_CPU_IRQ: - case ARMADA_370_XP_FABRIC_IRQ: + if (irq <= ARMADA_370_XP_MAX_PER_CPU_IRQS) return true; - default: - return false; - } + + return false; } /* @@ -549,7 +543,7 @@ static void armada_370_xp_mpic_resume(void) if (virq == 0) continue; - if (irq != ARMADA_370_XP_TIMER0_PER_CPU_IRQ) + if (!is_percpu_irq(irq)) writel(irq, per_cpu_int_base + ARMADA_370_XP_INT_CLEAR_MASK_OFFS); else diff --git a/drivers/isdn/hisax/hfc4s8s_l1.c b/drivers/isdn/hisax/hfc4s8s_l1.c index 0e5d673871c0..9600cd771f1a 100644 --- a/drivers/isdn/hisax/hfc4s8s_l1.c +++ b/drivers/isdn/hisax/hfc4s8s_l1.c @@ -646,14 +646,14 @@ rx_d_frame(struct hfc4s8s_l1 *l1p, int ech) f1 = Read_hfc8_stable(l1p->hw, A_F1); f2 = Read_hfc8(l1p->hw, A_F2); - df = f1 - f2; - if ((f1 - f2) < 0) - df = f1 - f2 + MAX_F_CNT + 1; + if (f1 < f2) + df = MAX_F_CNT + 1 + f1 - f2; + else + df = f1 - f2; - if (!df) { + if (!df) return; /* no complete frame in fifo */ - } z1 = Read_hfc16_stable(l1p->hw, A_Z1); z2 = Read_hfc16(l1p->hw, A_Z2); diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index d18eb607bee6..b9ebd0d18a52 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -299,6 +299,7 @@ config NLMON config NET_VRF tristate "Virtual Routing and Forwarding (Lite)" depends on IP_MULTIPLE_TABLES && IPV6_MULTIPLE_TABLES + depends on NET_L3_MASTER_DEV ---help--- This option enables the support for mapping interfaces into VRF's. The support enables VRF devices. diff --git a/drivers/net/arcnet/arc-rawmode.c b/drivers/net/arcnet/arc-rawmode.c index 705e6ce2eb90..d78f30186642 100644 --- a/drivers/net/arcnet/arc-rawmode.c +++ b/drivers/net/arcnet/arc-rawmode.c @@ -1,6 +1,6 @@ /* * Linux ARCnet driver - "raw mode" packet encapsulation (no soft headers) - * + * * Written 1994-1999 by Avery Pennarun. * Derived from skeleton.c by Donald Becker. * @@ -24,6 +24,8 @@ * ********************** */ +#define pr_fmt(fmt) "arcnet:" KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/gfp.h> #include <linux/init.h> @@ -31,58 +33,7 @@ #include <net/arp.h> #include <linux/netdevice.h> #include <linux/skbuff.h> -#include <linux/arcdevice.h> - -#define VERSION "arcnet: raw mode (`r') encapsulation support loaded.\n" - - -static void rx(struct net_device *dev, int bufnum, - struct archdr *pkthdr, int length); -static int build_header(struct sk_buff *skb, struct net_device *dev, - unsigned short type, uint8_t daddr); -static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, - int bufnum); - -static struct ArcProto rawmode_proto = -{ - .suffix = 'r', - .mtu = XMTU, - .rx = rx, - .build_header = build_header, - .prepare_tx = prepare_tx, - .continue_tx = NULL, - .ack_tx = NULL -}; - - -static int __init arcnet_raw_init(void) -{ - int count; - - printk(VERSION); - - for (count = 0; count < 256; count++) - if (arc_proto_map[count] == arc_proto_default) - arc_proto_map[count] = &rawmode_proto; - - /* for raw mode, we only set the bcast proto if there's no better one */ - if (arc_bcast_proto == arc_proto_default) - arc_bcast_proto = &rawmode_proto; - - arc_proto_default = &rawmode_proto; - return 0; -} - -static void __exit arcnet_raw_exit(void) -{ - arcnet_unregister_proto(&rawmode_proto); -} - -module_init(arcnet_raw_init); -module_exit(arcnet_raw_exit); - -MODULE_LICENSE("GPL"); - +#include "arcdevice.h" /* packet receiver */ static void rx(struct net_device *dev, int bufnum, @@ -93,7 +44,7 @@ static void rx(struct net_device *dev, int bufnum, struct archdr *pkt = pkthdr; int ofs; - BUGMSG(D_DURING, "it's a raw packet (length=%d)\n", length); + arc_printk(D_DURING, dev, "it's a raw packet (length=%d)\n", length); if (length > MTU) ofs = 512 - length; @@ -101,15 +52,14 @@ static void rx(struct net_device *dev, int bufnum, ofs = 256 - length; skb = alloc_skb(length + ARC_HDR_SIZE, GFP_ATOMIC); - if (skb == NULL) { - BUGMSG(D_NORMAL, "Memory squeeze, dropping packet.\n"); + if (!skb) { dev->stats.rx_dropped++; return; } skb_put(skb, length + ARC_HDR_SIZE); skb->dev = dev; - pkt = (struct archdr *) skb->data; + pkt = (struct archdr *)skb->data; skb_reset_mac_header(skb); skb_pull(skb, ARC_HDR_SIZE); @@ -121,38 +71,35 @@ static void rx(struct net_device *dev, int bufnum, pkt->soft.raw + sizeof(pkt->soft), length - sizeof(pkt->soft)); - BUGLVL(D_SKB) arcnet_dump_skb(dev, skb, "rx"); + if (BUGLVL(D_SKB)) + arcnet_dump_skb(dev, skb, "rx"); skb->protocol = cpu_to_be16(ETH_P_ARCNET); netif_rx(skb); } - -/* - * Create the ARCnet hard/soft headers for raw mode. +/* Create the ARCnet hard/soft headers for raw mode. * There aren't any soft headers in raw mode - not even the protocol id. */ static int build_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, uint8_t daddr) { int hdr_size = ARC_HDR_SIZE; - struct archdr *pkt = (struct archdr *) skb_push(skb, hdr_size); + struct archdr *pkt = (struct archdr *)skb_push(skb, hdr_size); - /* - * Set the source hardware address. + /* Set the source hardware address. * * This is pretty pointless for most purposes, but it can help in - * debugging. ARCnet does not allow us to change the source address in - * the actual packet sent) + * debugging. ARCnet does not allow us to change the source address + * in the actual packet sent. */ pkt->hard.source = *dev->dev_addr; /* see linux/net/ethernet/eth.c to see where I got the following */ if (dev->flags & (IFF_LOOPBACK | IFF_NOARP)) { - /* - * FIXME: fill in the last byte of the dest ipaddr here to better - * comply with RFC1051 in "noarp" mode. + /* FIXME: fill in the last byte of the dest ipaddr here + * to better comply with RFC1051 in "noarp" mode. */ pkt->hard.dest = 0; return hdr_size; @@ -163,7 +110,6 @@ static int build_header(struct sk_buff *skb, struct net_device *dev, return hdr_size; /* success */ } - static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, int bufnum) { @@ -171,15 +117,16 @@ static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, struct arc_hardware *hard = &pkt->hard; int ofs; - BUGMSG(D_DURING, "prepare_tx: txbufs=%d/%d/%d\n", - lp->next_tx, lp->cur_tx, bufnum); + arc_printk(D_DURING, dev, "prepare_tx: txbufs=%d/%d/%d\n", + lp->next_tx, lp->cur_tx, bufnum); - length -= ARC_HDR_SIZE; /* hard header is not included in packet length */ + /* hard header is not included in packet length */ + length -= ARC_HDR_SIZE; if (length > XMTU) { /* should never happen! other people already check for this. */ - BUGMSG(D_NORMAL, "Bug! prepare_tx with size %d (> %d)\n", - length, XMTU); + arc_printk(D_NORMAL, dev, "Bug! prepare_tx with size %d (> %d)\n", + length, XMTU); length = XMTU; } if (length >= MinTU) { @@ -188,11 +135,12 @@ static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, } else if (length > MTU) { hard->offset[0] = 0; hard->offset[1] = ofs = 512 - length - 3; - } else + } else { hard->offset[0] = ofs = 256 - length; + } - BUGMSG(D_DURING, "prepare_tx: length=%d ofs=%d\n", - length,ofs); + arc_printk(D_DURING, dev, "prepare_tx: length=%d ofs=%d\n", + length, ofs); lp->hw.copy_to_card(dev, bufnum, 0, hard, ARC_HDR_SIZE); lp->hw.copy_to_card(dev, bufnum, ofs, &pkt->soft, length); @@ -201,3 +149,41 @@ static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, return 1; /* done */ } + +static struct ArcProto rawmode_proto = { + .suffix = 'r', + .mtu = XMTU, + .rx = rx, + .build_header = build_header, + .prepare_tx = prepare_tx, + .continue_tx = NULL, + .ack_tx = NULL +}; + +static int __init arcnet_raw_init(void) +{ + int count; + + pr_info("raw mode (`r') encapsulation support loaded\n"); + + for (count = 0; count < 256; count++) + if (arc_proto_map[count] == arc_proto_default) + arc_proto_map[count] = &rawmode_proto; + + /* for raw mode, we only set the bcast proto if there's no better one */ + if (arc_bcast_proto == arc_proto_default) + arc_bcast_proto = &rawmode_proto; + + arc_proto_default = &rawmode_proto; + return 0; +} + +static void __exit arcnet_raw_exit(void) +{ + arcnet_unregister_proto(&rawmode_proto); +} + +module_init(arcnet_raw_init); +module_exit(arcnet_raw_exit); + +MODULE_LICENSE("GPL"); diff --git a/drivers/net/arcnet/arc-rimi.c b/drivers/net/arcnet/arc-rimi.c index b8b4c7ba884f..a07e24970be4 100644 --- a/drivers/net/arcnet/arc-rimi.c +++ b/drivers/net/arcnet/arc-rimi.c @@ -1,6 +1,6 @@ /* * Linux ARCnet driver - "RIM I" (entirely mem-mapped) cards - * + * * Written 1994-1999 by Avery Pennarun. * Written 1999-2000 by Martin Mares <mj@ucw.cz>. * Derived from skeleton.c by Donald Becker. @@ -24,6 +24,9 @@ * * ********************** */ + +#define pr_fmt(fmt) "arcnet:" KBUILD_MODNAME ": " fmt + #include <linux/kernel.h> #include <linux/module.h> #include <linux/moduleparam.h> @@ -33,12 +36,10 @@ #include <linux/bootmem.h> #include <linux/init.h> #include <linux/interrupt.h> -#include <asm/io.h> -#include <linux/arcdevice.h> - - -#define VERSION "arcnet: RIM I (entirely mem-mapped) support\n" +#include <linux/io.h> +#include "arcdevice.h" +#include "com9026.h" /* Internal function declarations */ @@ -50,66 +51,46 @@ static void arcrimi_setmask(struct net_device *dev, int mask); static int arcrimi_reset(struct net_device *dev, int really_reset); static void arcrimi_copy_to_card(struct net_device *dev, int bufnum, int offset, void *buf, int count); -static void arcrimi_copy_from_card(struct net_device *dev, int bufnum, int offset, - void *buf, int count); +static void arcrimi_copy_from_card(struct net_device *dev, int bufnum, + int offset, void *buf, int count); /* Handy defines for ARCnet specific stuff */ /* Amount of I/O memory used by the card */ -#define BUFFER_SIZE (512) -#define MIRROR_SIZE (BUFFER_SIZE*4) +#define BUFFER_SIZE (512) +#define MIRROR_SIZE (BUFFER_SIZE * 4) -/* COM 9026 controller chip --> ARCnet register addresses */ -#define _INTMASK (ioaddr+0) /* writable */ -#define _STATUS (ioaddr+0) /* readable */ -#define _COMMAND (ioaddr+1) /* writable, returns random vals on read (?) */ -#define _RESET (ioaddr+8) /* software reset (on read) */ -#define _MEMDATA (ioaddr+12) /* Data port for IO-mapped memory */ -#define _ADDR_HI (ioaddr+15) /* Control registers for said */ -#define _ADDR_LO (ioaddr+14) -#define _CONFIG (ioaddr+2) /* Configuration register */ - -#undef ASTATUS -#undef ACOMMAND -#undef AINTMASK - -#define ASTATUS() readb(_STATUS) -#define ACOMMAND(cmd) writeb((cmd),_COMMAND) -#define AINTMASK(msk) writeb((msk),_INTMASK) -#define SETCONF() writeb(lp->config,_CONFIG) - - -/* - * We cannot probe for a RIM I card; one reason is I don't know how to reset +/* We cannot probe for a RIM I card; one reason is I don't know how to reset * them. In fact, we can't even get their node ID automatically. So, we * need to be passed a specific shmem address, IRQ, and node ID. */ static int __init arcrimi_probe(struct net_device *dev) { - BUGLVL(D_NORMAL) printk(VERSION); - BUGLVL(D_NORMAL) printk("E-mail me if you actually test the RIM I driver, please!\n"); - - BUGLVL(D_NORMAL) printk("Given: node %02Xh, shmem %lXh, irq %d\n", - dev->dev_addr[0], dev->mem_start, dev->irq); + if (BUGLVL(D_NORMAL)) { + pr_info("%s\n", "RIM I (entirely mem-mapped) support"); + pr_info("E-mail me if you actually test the RIM I driver, please!\n"); + pr_info("Given: node %02Xh, shmem %lXh, irq %d\n", + dev->dev_addr[0], dev->mem_start, dev->irq); + } if (dev->mem_start <= 0 || dev->irq <= 0) { - BUGLVL(D_NORMAL) printk("No autoprobe for RIM I; you " - "must specify the shmem and irq!\n"); + if (BUGLVL(D_NORMAL)) + pr_err("No autoprobe for RIM I; you must specify the shmem and irq!\n"); return -ENODEV; } if (dev->dev_addr[0] == 0) { - BUGLVL(D_NORMAL) printk("You need to specify your card's station " - "ID!\n"); + if (BUGLVL(D_NORMAL)) + pr_err("You need to specify your card's station ID!\n"); return -ENODEV; } - /* - * Grab the memory region at mem_start for MIRROR_SIZE bytes. + /* Grab the memory region at mem_start for MIRROR_SIZE bytes. * Later in arcrimi_found() the real size will be determined * and this reserve will be released and the correct size * will be taken. */ if (!request_mem_region(dev->mem_start, MIRROR_SIZE, "arcnet (90xx)")) { - BUGLVL(D_NORMAL) printk("Card memory already allocated\n"); + if (BUGLVL(D_NORMAL)) + pr_notice("Card memory already allocated\n"); return -ENODEV; } return arcrimi_found(dev); @@ -125,7 +106,7 @@ static int check_mirror(unsigned long addr, size_t size) p = ioremap(addr, size); if (p) { - if (readb(p) == TESTvalue) + if (arcnet_readb(p, COM9026_REG_R_STATUS) == TESTvalue) res = 1; else res = 0; @@ -136,9 +117,8 @@ static int check_mirror(unsigned long addr, size_t size) return res; } -/* - * Set up the struct net_device associated with this card. Called after - * probing succeeds. +/* Set up the struct net_device associated with this card. + * Called after probing succeeds. */ static int __init arcrimi_found(struct net_device *dev) { @@ -151,7 +131,7 @@ static int __init arcrimi_found(struct net_device *dev) p = ioremap(dev->mem_start, MIRROR_SIZE); if (!p) { release_mem_region(dev->mem_start, MIRROR_SIZE); - BUGMSG(D_NORMAL, "Can't ioremap\n"); + arc_printk(D_NORMAL, dev, "Can't ioremap\n"); return -ENODEV; } @@ -159,13 +139,14 @@ static int __init arcrimi_found(struct net_device *dev) if (request_irq(dev->irq, arcnet_interrupt, 0, "arcnet (RIM I)", dev)) { iounmap(p); release_mem_region(dev->mem_start, MIRROR_SIZE); - BUGMSG(D_NORMAL, "Can't get IRQ %d!\n", dev->irq); + arc_printk(D_NORMAL, dev, "Can't get IRQ %d!\n", dev->irq); return -ENODEV; } shmem = dev->mem_start; - writeb(TESTvalue, p); - writeb(dev->dev_addr[0], p + 1); /* actually the node ID */ + arcnet_writeb(TESTvalue, p, COM9026_REG_W_INTMASK); + arcnet_writeb(TESTvalue, p, COM9026_REG_W_COMMAND); + /* actually the station/node ID */ /* find the real shared memory start/end points, including mirrors */ @@ -174,7 +155,7 @@ static int __init arcrimi_found(struct net_device *dev) * 2k (or there are no mirrors at all) but on some, it's 4k. */ mirror_size = MIRROR_SIZE; - if (readb(p) == TESTvalue && + if (arcnet_readb(p, COM9026_REG_R_STATUS) == TESTvalue && check_mirror(shmem - MIRROR_SIZE, MIRROR_SIZE) == 0 && check_mirror(shmem - 2 * MIRROR_SIZE, MIRROR_SIZE) == 1) mirror_size = 2 * MIRROR_SIZE; @@ -204,8 +185,7 @@ static int __init arcrimi_found(struct net_device *dev) lp->hw.copy_to_card = arcrimi_copy_to_card; lp->hw.copy_from_card = arcrimi_copy_from_card; - /* - * re-reserve the memory region - arcrimi_probe() alloced this reqion + /* re-reserve the memory region - arcrimi_probe() alloced this reqion * but didn't know the real size. Free that region and then re-get * with the correct size. There is a VERY slim chance this could * fail. @@ -215,24 +195,25 @@ static int __init arcrimi_found(struct net_device *dev) if (!request_mem_region(dev->mem_start, dev->mem_end - dev->mem_start + 1, "arcnet (90xx)")) { - BUGMSG(D_NORMAL, "Card memory already allocated\n"); + arc_printk(D_NORMAL, dev, "Card memory already allocated\n"); goto err_free_irq; } - lp->mem_start = ioremap(dev->mem_start, dev->mem_end - dev->mem_start + 1); + lp->mem_start = ioremap(dev->mem_start, + dev->mem_end - dev->mem_start + 1); if (!lp->mem_start) { - BUGMSG(D_NORMAL, "Can't remap device memory!\n"); + arc_printk(D_NORMAL, dev, "Can't remap device memory!\n"); goto err_release_mem; } /* get and check the station ID from offset 1 in shmem */ - dev->dev_addr[0] = readb(lp->mem_start + 1); + dev->dev_addr[0] = arcnet_readb(lp->mem_start, COM9026_REG_R_STATION); - BUGMSG(D_NORMAL, "ARCnet RIM I: station %02Xh found at IRQ %d, " - "ShMem %lXh (%ld*%d bytes).\n", - dev->dev_addr[0], - dev->irq, dev->mem_start, - (dev->mem_end - dev->mem_start + 1) / mirror_size, mirror_size); + arc_printk(D_NORMAL, dev, "ARCnet RIM I: station %02Xh found at IRQ %d, ShMem %lXh (%ld*%d bytes)\n", + dev->dev_addr[0], + dev->irq, dev->mem_start, + (dev->mem_end - dev->mem_start + 1) / mirror_size, + mirror_size); err = register_netdev(dev); if (err) @@ -249,9 +230,7 @@ err_free_irq: return -EIO; } - -/* - * Do a hardware reset on the card, and set up necessary registers. +/* Do a hardware reset on the card, and set up necessary registers. * * This should be called as little as possible, because it disrupts the * token on the network (causes a RECON) and requires a significant delay. @@ -263,17 +242,19 @@ static int arcrimi_reset(struct net_device *dev, int really_reset) struct arcnet_local *lp = netdev_priv(dev); void __iomem *ioaddr = lp->mem_start + 0x800; - BUGMSG(D_INIT, "Resetting %s (status=%02Xh)\n", dev->name, ASTATUS()); + arc_printk(D_INIT, dev, "Resetting %s (status=%02Xh)\n", + dev->name, arcnet_readb(ioaddr, COM9026_REG_R_STATUS)); if (really_reset) { - writeb(TESTvalue, ioaddr - 0x800); /* fake reset */ + arcnet_writeb(TESTvalue, ioaddr, -0x800); /* fake reset */ return 0; } - ACOMMAND(CFLAGScmd | RESETclear); /* clear flags & end reset */ - ACOMMAND(CFLAGScmd | CONFIGclear); + /* clear flags & end reset */ + arcnet_writeb(CFLAGScmd | RESETclear, ioaddr, COM9026_REG_W_COMMAND); + arcnet_writeb(CFLAGScmd | CONFIGclear, ioaddr, COM9026_REG_W_COMMAND); /* enable extended (512-byte) packets */ - ACOMMAND(CONFIGcmd | EXTconf); + arcnet_writeb(CONFIGcmd | EXTconf, ioaddr, COM9026_REG_W_COMMAND); /* done! return success. */ return 0; @@ -284,7 +265,7 @@ static void arcrimi_setmask(struct net_device *dev, int mask) struct arcnet_local *lp = netdev_priv(dev); void __iomem *ioaddr = lp->mem_start + 0x800; - AINTMASK(mask); + arcnet_writeb(mask, ioaddr, COM9026_REG_W_INTMASK); } static int arcrimi_status(struct net_device *dev) @@ -292,7 +273,7 @@ static int arcrimi_status(struct net_device *dev) struct arcnet_local *lp = netdev_priv(dev); void __iomem *ioaddr = lp->mem_start + 0x800; - return ASTATUS(); + return arcnet_readb(ioaddr, COM9026_REG_R_STATUS); } static void arcrimi_command(struct net_device *dev, int cmd) @@ -300,7 +281,7 @@ static void arcrimi_command(struct net_device *dev, int cmd) struct arcnet_local *lp = netdev_priv(dev); void __iomem *ioaddr = lp->mem_start + 0x800; - ACOMMAND(cmd); + arcnet_writeb(cmd, ioaddr, COM9026_REG_W_COMMAND); } static void arcrimi_copy_to_card(struct net_device *dev, int bufnum, int offset, @@ -308,16 +289,17 @@ static void arcrimi_copy_to_card(struct net_device *dev, int bufnum, int offset, { struct arcnet_local *lp = netdev_priv(dev); void __iomem *memaddr = lp->mem_start + 0x800 + bufnum * 512 + offset; - TIME("memcpy_toio", count, memcpy_toio(memaddr, buf, count)); -} + TIME(dev, "memcpy_toio", count, memcpy_toio(memaddr, buf, count)); +} -static void arcrimi_copy_from_card(struct net_device *dev, int bufnum, int offset, - void *buf, int count) +static void arcrimi_copy_from_card(struct net_device *dev, int bufnum, + int offset, void *buf, int count) { struct arcnet_local *lp = netdev_priv(dev); void __iomem *memaddr = lp->mem_start + 0x800 + bufnum * 512 + offset; - TIME("memcpy_fromio", count, memcpy_fromio(buf, memaddr, count)); + + TIME(dev, "memcpy_fromio", count, memcpy_fromio(buf, memaddr, count)); } static int node; @@ -374,12 +356,13 @@ static void __exit arc_rimi_exit(void) static int __init arcrimi_setup(char *s) { int ints[8]; + s = get_options(s, 8, ints); if (!ints[0]) return 1; switch (ints[0]) { default: /* ERROR */ - printk("arcrimi: Too many arguments.\n"); + pr_err("Too many arguments\n"); case 3: /* Node ID */ node = ints[3]; case 2: /* IRQ */ diff --git a/include/linux/arcdevice.h b/drivers/net/arcnet/arcdevice.h index df0356220730..d7fdea11e694 100644 --- a/include/linux/arcdevice.h +++ b/drivers/net/arcnet/arcdevice.h @@ -34,7 +34,6 @@ */ #define RECON_THRESHOLD 30 - /* * Define this to the minimum "timeout" value. If a transmit takes longer * than TX_TIMEOUT jiffies, Linux will abort the TX and retry. On a large @@ -44,14 +43,12 @@ */ #define TX_TIMEOUT (HZ * 200 / 1000) - /* Display warnings about the driver being an ALPHA version. */ #undef ALPHA_WARNING - /* * Debugging bitflags: each option can be enabled individually. - * + * * Note: only debug flags included in the ARCNET_DEBUG_MAX define will * actually be available. GCC will (at least, GCC 2.7.0 will) notice * lines using a BUGLVL not in ARCNET_DEBUG_MAX and automatically optimize @@ -77,35 +74,47 @@ #endif #ifndef ARCNET_DEBUG -#define ARCNET_DEBUG (D_NORMAL|D_EXTRA) +#define ARCNET_DEBUG (D_NORMAL | D_EXTRA) #endif extern int arcnet_debug; +#define BUGLVL(x) ((x) & ARCNET_DEBUG_MAX & arcnet_debug) + /* macros to simplify debug checking */ -#define BUGLVL(x) if ((ARCNET_DEBUG_MAX)&arcnet_debug&(x)) -#define BUGMSG2(x,msg,args...) do { BUGLVL(x) printk(msg, ## args); } while (0) -#define BUGMSG(x,msg,args...) \ - BUGMSG2(x, "%s%6s: " msg, \ - x==D_NORMAL ? KERN_WARNING \ - : x < D_DURING ? KERN_INFO : KERN_DEBUG, \ - dev->name , ## args) +#define arc_printk(x, dev, fmt, ...) \ +do { \ + if (BUGLVL(x)) { \ + if ((x) == D_NORMAL) \ + netdev_warn(dev, fmt, ##__VA_ARGS__); \ + else if ((x) < D_DURING) \ + netdev_info(dev, fmt, ##__VA_ARGS__); \ + else \ + netdev_dbg(dev, fmt, ##__VA_ARGS__); \ + } \ +} while (0) + +#define arc_cont(x, fmt, ...) \ +do { \ + if (BUGLVL(x)) \ + pr_cont(fmt, ##__VA_ARGS__); \ +} while (0) /* see how long a function call takes to run, expressed in CPU cycles */ -#define TIME(name, bytes, call) BUGLVL(D_TIMING) { \ - unsigned long _x, _y; \ - _x = get_cycles(); \ - call; \ - _y = get_cycles(); \ - BUGMSG(D_TIMING, \ - "%s: %d bytes in %lu cycles == " \ - "%lu Kbytes/100Mcycle\n",\ - name, bytes, _y - _x, \ - 100000000 / 1024 * bytes / (_y - _x + 1));\ - } \ - else { \ - call;\ - } - +#define TIME(dev, name, bytes, call) \ +do { \ + if (BUGLVL(D_TIMING)) { \ + unsigned long _x, _y; \ + _x = get_cycles(); \ + call; \ + _y = get_cycles(); \ + arc_printk(D_TIMING, dev, \ + "%s: %d bytes in %lu cycles == %lu Kbytes/100Mcycle\n", \ + name, bytes, _y - _x, \ + 100000000 / 1024 * bytes / (_y - _x + 1)); \ + } else { \ + call; \ + } \ +} while (0) /* * Time needed to reset the card - in ms (milliseconds). This works on my @@ -155,6 +164,7 @@ extern int arcnet_debug; #define CONFIGcmd 0x05 /* define configuration */ #define CFLAGScmd 0x06 /* clear flags */ #define TESTcmd 0x07 /* load test flags */ +#define STARTIOcmd 0x18 /* start internal operation */ /* flags for "clear flags" command */ #define RESETclear 0x08 /* power-on-reset */ @@ -182,29 +192,27 @@ extern int arcnet_debug; #define ARC_CAN_10MBIT 2 /* card uses COM20022, supporting 10MBit, but default is 2.5MBit. */ - /* information needed to define an encapsulation driver */ struct ArcProto { char suffix; /* a for RFC1201, e for ether-encap, etc. */ int mtu; /* largest possible packet */ int is_ip; /* This is a ip plugin - not a raw thing */ - void (*rx) (struct net_device * dev, int bufnum, - struct archdr * pkthdr, int length); - int (*build_header) (struct sk_buff * skb, struct net_device *dev, - unsigned short ethproto, uint8_t daddr); + void (*rx)(struct net_device *dev, int bufnum, + struct archdr *pkthdr, int length); + int (*build_header)(struct sk_buff *skb, struct net_device *dev, + unsigned short ethproto, uint8_t daddr); /* these functions return '1' if the skb can now be freed */ - int (*prepare_tx) (struct net_device * dev, struct archdr * pkt, int length, - int bufnum); - int (*continue_tx) (struct net_device * dev, int bufnum); - int (*ack_tx) (struct net_device * dev, int acked); + int (*prepare_tx)(struct net_device *dev, struct archdr *pkt, + int length, int bufnum); + int (*continue_tx)(struct net_device *dev, int bufnum); + int (*ack_tx)(struct net_device *dev, int acked); }; extern struct ArcProto *arc_proto_map[256], *arc_proto_default, *arc_bcast_proto, *arc_raw_proto; - /* * "Incoming" is information needed for each address that could be sending * to us. Mostly for partially-received split packets. @@ -216,7 +224,6 @@ struct Incoming { numpackets; /* number of packets in split */ }; - /* only needed for RFC1201 */ struct Outgoing { struct ArcProto *proto; /* protocol driver that owns this: @@ -230,7 +237,6 @@ struct Outgoing { numsegs; /* number of segments */ }; - struct arcnet_local { uint8_t config, /* current value of CONFIG register */ timeout, /* Extended timeout for COM20020 */ @@ -251,7 +257,6 @@ struct arcnet_local { char *card_name; /* card ident string */ int card_flags; /* special card features */ - /* On preemtive and SMB a lock is needed */ spinlock_t lock; @@ -263,13 +268,13 @@ struct arcnet_local { * situations in which we (for example) want to pre-load a transmit * buffer, or start receiving while we copy a received packet to * memory. - * + * * The rules: only the interrupt handler is allowed to _add_ buffers to * the queue; thus, this doesn't require a lock. Both the interrupt * handler and the transmit function will want to _remove_ buffers, so * we need to handle the situation where they try to do it at the same * time. - * + * * If next_buf == first_free_buf, the queue is empty. Since there are * only four possible buffers, the queue should never be full. */ @@ -298,34 +303,29 @@ struct arcnet_local { /* hardware-specific functions */ struct { struct module *owner; - void (*command) (struct net_device * dev, int cmd); - int (*status) (struct net_device * dev); - void (*intmask) (struct net_device * dev, int mask); - int (*reset) (struct net_device * dev, int really_reset); - void (*open) (struct net_device * dev); - void (*close) (struct net_device * dev); - - void (*copy_to_card) (struct net_device * dev, int bufnum, int offset, - void *buf, int count); - void (*copy_from_card) (struct net_device * dev, int bufnum, int offset, - void *buf, int count); + void (*command)(struct net_device *dev, int cmd); + int (*status)(struct net_device *dev); + void (*intmask)(struct net_device *dev, int mask); + int (*reset)(struct net_device *dev, int really_reset); + void (*open)(struct net_device *dev); + void (*close)(struct net_device *dev); + + void (*copy_to_card)(struct net_device *dev, int bufnum, + int offset, void *buf, int count); + void (*copy_from_card)(struct net_device *dev, int bufnum, + int offset, void *buf, int count); } hw; void __iomem *mem_start; /* pointer to ioremap'ed MMIO */ }; - -#define ARCRESET(x) (lp->hw.reset(dev, (x))) -#define ACOMMAND(x) (lp->hw.command(dev, (x))) -#define ASTATUS() (lp->hw.status(dev)) -#define AINTMASK(x) (lp->hw.intmask(dev, (x))) - - - #if ARCNET_DEBUG_MAX & D_SKB void arcnet_dump_skb(struct net_device *dev, struct sk_buff *skb, char *desc); #else -#define arcnet_dump_skb(dev,skb,desc) ; +static inline +void arcnet_dump_skb(struct net_device *dev, struct sk_buff *skb, char *desc) +{ +} #endif void arcnet_unregister_proto(struct ArcProto *proto); @@ -335,8 +335,34 @@ struct net_device *alloc_arcdev(const char *name); int arcnet_open(struct net_device *dev); int arcnet_close(struct net_device *dev); netdev_tx_t arcnet_send_packet(struct sk_buff *skb, - struct net_device *dev); + struct net_device *dev); void arcnet_timeout(struct net_device *dev); +/* I/O equivalents */ + +#ifdef CONFIG_SA1100_CT6001 +#define BUS_ALIGN 2 /* 8 bit device on a 16 bit bus - needs padding */ +#else +#define BUS_ALIGN 1 +#endif + +/* addr and offset allow register like names to define the actual IO address. + * A configuration option multiplies the offset for alignment. + */ +#define arcnet_inb(addr, offset) \ + inb((addr) + BUS_ALIGN * (offset)) +#define arcnet_outb(value, addr, offset) \ + outb(value, (addr) + BUS_ALIGN * (offset)) + +#define arcnet_insb(addr, offset, buffer, count) \ + insb((addr) + BUS_ALIGN * (offset), buffer, count) +#define arcnet_outsb(addr, offset, buffer, count) \ + outsb((addr) + BUS_ALIGN * (offset), buffer, count) + +#define arcnet_readb(addr, offset) \ + readb((addr) + (offset)) +#define arcnet_writeb(value, addr, offset) \ + writeb(value, (addr) + (offset)) + #endif /* __KERNEL__ */ #endif /* _LINUX_ARCDEVICE_H */ diff --git a/drivers/net/arcnet/arcnet.c b/drivers/net/arcnet/arcnet.c index 816d0e94961c..e41dd36fe832 100644 --- a/drivers/net/arcnet/arcnet.c +++ b/drivers/net/arcnet/arcnet.c @@ -1,6 +1,6 @@ /* * Linux ARCnet driver - device-independent routines - * + * * Written 1997 by David Woodhouse. * Written 1994-1999 by Avery Pennarun. * Written 1999-2000 by Martin Mares <mj@ucw.cz>. @@ -20,12 +20,12 @@ * modified by SRC, incorporated herein by reference. * * ********************** - * + * * The change log is now in a file called ChangeLog in this directory. * * Sources: * - Crynwr arcnet.com/arcether.com packet drivers. - * - arcnet.c v0.00 dated 1/1/94 and apparently by + * - arcnet.c v0.00 dated 1/1/94 and apparently by * Donald Becker - it didn't work :) * - skeleton.c v0.05 dated 11/16/93 by Donald Becker * (from Linux Kernel 1.1.45) @@ -41,7 +41,7 @@ * <jojo@repas.de> */ -#define VERSION "arcnet: v3.94 BETA 2007/02/08 - by Avery Pennarun et al.\n" +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/types.h> @@ -50,9 +50,11 @@ #include <linux/if_arp.h> #include <net/arp.h> #include <linux/init.h> -#include <linux/arcdevice.h> #include <linux/jiffies.h> +#include "arcdevice.h" +#include "com9026.h" + /* "do nothing" functions for protocol drivers */ static void null_rx(struct net_device *dev, int bufnum, struct archdr *pkthdr, int length); @@ -63,17 +65,24 @@ static int null_prepare_tx(struct net_device *dev, struct archdr *pkt, static void arcnet_rx(struct net_device *dev, int bufnum); -/* - * one ArcProto per possible proto ID. None of the elements of +/* one ArcProto per possible proto ID. None of the elements of * arc_proto_map are allowed to be NULL; they will get set to * arc_proto_default instead. It also must not be NULL; if you would like * to set it to NULL, set it to &arc_proto_null instead. */ - struct ArcProto *arc_proto_map[256], *arc_proto_default, - *arc_bcast_proto, *arc_raw_proto; +struct ArcProto *arc_proto_map[256]; +EXPORT_SYMBOL(arc_proto_map); -static struct ArcProto arc_proto_null = -{ +struct ArcProto *arc_proto_default; +EXPORT_SYMBOL(arc_proto_default); + +struct ArcProto *arc_bcast_proto; +EXPORT_SYMBOL(arc_bcast_proto); + +struct ArcProto *arc_raw_proto; +EXPORT_SYMBOL(arc_raw_proto); + +static struct ArcProto arc_proto_null = { .suffix = '?', .mtu = XMTU, .is_ip = 0, @@ -86,19 +95,7 @@ static struct ArcProto arc_proto_null = /* Exported function prototypes */ int arcnet_debug = ARCNET_DEBUG; - -EXPORT_SYMBOL(arc_proto_map); -EXPORT_SYMBOL(arc_proto_default); -EXPORT_SYMBOL(arc_bcast_proto); -EXPORT_SYMBOL(arc_raw_proto); -EXPORT_SYMBOL(arcnet_unregister_proto); EXPORT_SYMBOL(arcnet_debug); -EXPORT_SYMBOL(alloc_arcdev); -EXPORT_SYMBOL(arcnet_interrupt); -EXPORT_SYMBOL(arcnet_open); -EXPORT_SYMBOL(arcnet_close); -EXPORT_SYMBOL(arcnet_send_packet); -EXPORT_SYMBOL(arcnet_timeout); /* Internal function prototypes */ static int arcnet_header(struct sk_buff *skb, struct net_device *dev, @@ -116,29 +113,20 @@ static int __init arcnet_init(void) arcnet_debug = debug; - printk("arcnet loaded.\n"); - -#ifdef ALPHA_WARNING - BUGLVL(D_EXTRA) { - printk("arcnet: ***\n" - "arcnet: * Read arcnet.txt for important release notes!\n" - "arcnet: *\n" - "arcnet: * This is an ALPHA version! (Last stable release: v3.02) E-mail\n" - "arcnet: * me if you have any questions, comments, or bug reports.\n" - "arcnet: ***\n"); - } -#endif + pr_info("arcnet loaded\n"); /* initialize the protocol map */ arc_raw_proto = arc_proto_default = arc_bcast_proto = &arc_proto_null; for (count = 0; count < 256; count++) arc_proto_map[count] = arc_proto_default; - BUGLVL(D_DURING) - printk("arcnet: struct sizes: %Zd %Zd %Zd %Zd %Zd\n", - sizeof(struct arc_hardware), sizeof(struct arc_rfc1201), - sizeof(struct arc_rfc1051), sizeof(struct arc_eth_encap), - sizeof(struct archdr)); + if (BUGLVL(D_DURING)) + pr_info("struct sizes: %Zd %Zd %Zd %Zd %Zd\n", + sizeof(struct arc_hardware), + sizeof(struct arc_rfc1201), + sizeof(struct arc_rfc1051), + sizeof(struct arc_eth_encap), + sizeof(struct archdr)); return 0; } @@ -150,9 +138,7 @@ static void __exit arcnet_exit(void) module_init(arcnet_init); module_exit(arcnet_exit); -/* - * Dump the contents of an sk_buff - */ +/* Dump the contents of an sk_buff */ #if ARCNET_DEBUG_MAX & D_SKB void arcnet_dump_skb(struct net_device *dev, struct sk_buff *skb, char *desc) @@ -164,14 +150,10 @@ void arcnet_dump_skb(struct net_device *dev, print_hex_dump(KERN_DEBUG, hdr, DUMP_PREFIX_OFFSET, 16, 1, skb->data, skb->len, true); } - EXPORT_SYMBOL(arcnet_dump_skb); #endif - -/* - * Dump the contents of an ARCnet buffer - */ +/* Dump the contents of an ARCnet buffer */ #if (ARCNET_DEBUG_MAX & (D_RX | D_TX)) static void arcnet_dump_packet(struct net_device *dev, int bufnum, char *desc, int take_arcnet_lock) @@ -183,12 +165,13 @@ static void arcnet_dump_packet(struct net_device *dev, int bufnum, char hdr[32]; /* hw.copy_from_card expects IRQ context so take the IRQ lock - to keep it single threaded */ - if(take_arcnet_lock) + * to keep it single threaded + */ + if (take_arcnet_lock) spin_lock_irqsave(&lp->lock, flags); lp->hw.copy_from_card(dev, bufnum, 0, buf, 512); - if(take_arcnet_lock) + if (take_arcnet_lock) spin_unlock_irqrestore(&lp->lock, flags); /* if the offset[0] byte is nonzero, this is a 256-byte packet */ @@ -202,13 +185,11 @@ static void arcnet_dump_packet(struct net_device *dev, int bufnum, #else -#define arcnet_dump_packet(dev, bufnum, desc,take_arcnet_lock) do { } while (0) +#define arcnet_dump_packet(dev, bufnum, desc, take_arcnet_lock) do { } while (0) #endif - -/* - * Unregister a protocol driver from the arc_proto_map. Protocol drivers +/* Unregister a protocol driver from the arc_proto_map. Protocol drivers * are responsible for registering themselves, but the unregister routine * is pretty generic so we'll do it here. */ @@ -228,12 +209,11 @@ void arcnet_unregister_proto(struct ArcProto *proto) arc_proto_map[count] = arc_proto_default; } } +EXPORT_SYMBOL(arcnet_unregister_proto); - -/* - * Add a buffer to the queue. Only the interrupt handler is allowed to do +/* Add a buffer to the queue. Only the interrupt handler is allowed to do * this, unless interrupts are disabled. - * + * * Note: we don't check for a full queue, since there aren't enough buffers * to more than fill it. */ @@ -245,19 +225,17 @@ static void release_arcbuf(struct net_device *dev, int bufnum) lp->buf_queue[lp->first_free_buf++] = bufnum; lp->first_free_buf %= 5; - BUGLVL(D_DURING) { - BUGMSG(D_DURING, "release_arcbuf: freed #%d; buffer queue is now: ", - bufnum); - for (i = lp->next_buf; i != lp->first_free_buf; i = (i+1) % 5) - BUGMSG2(D_DURING, "#%d ", lp->buf_queue[i]); - BUGMSG2(D_DURING, "\n"); + if (BUGLVL(D_DURING)) { + arc_printk(D_DURING, dev, "release_arcbuf: freed #%d; buffer queue is now: ", + bufnum); + for (i = lp->next_buf; i != lp->first_free_buf; i = (i + 1) % 5) + arc_cont(D_DURING, "#%d ", lp->buf_queue[i]); + arc_cont(D_DURING, "\n"); } } - -/* - * Get a buffer from the queue. If this returns -1, there are no buffers - * available. +/* Get a buffer from the queue. + * If this returns -1, there are no buffers available. */ static int get_arcbuf(struct net_device *dev) { @@ -266,34 +244,32 @@ static int get_arcbuf(struct net_device *dev) if (!atomic_dec_and_test(&lp->buf_lock)) { /* already in this function */ - BUGMSG(D_NORMAL, "get_arcbuf: overlap (%d)!\n", - lp->buf_lock.counter); - } - else { /* we can continue */ + arc_printk(D_NORMAL, dev, "get_arcbuf: overlap (%d)!\n", + lp->buf_lock.counter); + } else { /* we can continue */ if (lp->next_buf >= 5) lp->next_buf -= 5; - if (lp->next_buf == lp->first_free_buf) - BUGMSG(D_NORMAL, "get_arcbuf: BUG: no buffers are available??\n"); - else { + if (lp->next_buf == lp->first_free_buf) { + arc_printk(D_NORMAL, dev, "get_arcbuf: BUG: no buffers are available??\n"); + } else { buf = lp->buf_queue[lp->next_buf++]; lp->next_buf %= 5; } } - - BUGLVL(D_DURING) { - BUGMSG(D_DURING, "get_arcbuf: got #%d; buffer queue is now: ", buf); - for (i = lp->next_buf; i != lp->first_free_buf; i = (i+1) % 5) - BUGMSG2(D_DURING, "#%d ", lp->buf_queue[i]); - BUGMSG2(D_DURING, "\n"); + if (BUGLVL(D_DURING)) { + arc_printk(D_DURING, dev, "get_arcbuf: got #%d; buffer queue is now: ", + buf); + for (i = lp->next_buf; i != lp->first_free_buf; i = (i + 1) % 5) + arc_cont(D_DURING, "#%d ", lp->buf_queue[i]); + arc_cont(D_DURING, "\n"); } atomic_inc(&lp->buf_lock); return buf; } - static int choose_mtu(void) { int count, mtu = 65535; @@ -336,7 +312,6 @@ static void arcdev_setup(struct net_device *dev) /* New-style flags. */ dev->flags = IFF_BROADCAST; - } struct net_device *alloc_arcdev(const char *name) @@ -346,16 +321,17 @@ struct net_device *alloc_arcdev(const char *name) dev = alloc_netdev(sizeof(struct arcnet_local), name && *name ? name : "arc%d", NET_NAME_UNKNOWN, arcdev_setup); - if(dev) { + if (dev) { struct arcnet_local *lp = netdev_priv(dev); + spin_lock_init(&lp->lock); } return dev; } +EXPORT_SYMBOL(alloc_arcdev); -/* - * Open/initialize the board. This is called sometime after booting when +/* Open/initialize the board. This is called sometime after booting when * the 'ifconfig' program is run. * * This routine should set everything up anew at each open, even registers @@ -367,34 +343,33 @@ int arcnet_open(struct net_device *dev) struct arcnet_local *lp = netdev_priv(dev); int count, newmtu, error; - BUGMSG(D_INIT,"opened."); + arc_printk(D_INIT, dev, "opened."); if (!try_module_get(lp->hw.owner)) return -ENODEV; - BUGLVL(D_PROTO) { - BUGMSG(D_PROTO, "protocol map (default is '%c'): ", - arc_proto_default->suffix); + if (BUGLVL(D_PROTO)) { + arc_printk(D_PROTO, dev, "protocol map (default is '%c'): ", + arc_proto_default->suffix); for (count = 0; count < 256; count++) - BUGMSG2(D_PROTO, "%c", arc_proto_map[count]->suffix); - BUGMSG2(D_PROTO, "\n"); + arc_cont(D_PROTO, "%c", arc_proto_map[count]->suffix); + arc_cont(D_PROTO, "\n"); } - - BUGMSG(D_INIT, "arcnet_open: resetting card.\n"); + arc_printk(D_INIT, dev, "arcnet_open: resetting card.\n"); /* try to put the card in a defined state - if it fails the first * time, actually reset it. */ error = -ENODEV; - if (ARCRESET(0) && ARCRESET(1)) + if (lp->hw.reset(dev, 0) && lp->hw.reset(dev, 1)) goto out_module_put; newmtu = choose_mtu(); if (newmtu < dev->mtu) dev->mtu = newmtu; - BUGMSG(D_INIT, "arcnet_open: mtu: %d.\n", dev->mtu); + arc_printk(D_INIT, dev, "arcnet_open: mtu: %d.\n", dev->mtu); /* autodetect the encapsulation for each host. */ memset(lp->default_proto, 0, sizeof(lp->default_proto)); @@ -425,30 +400,28 @@ int arcnet_open(struct net_device *dev) lp->hw.open(dev); if (dev->dev_addr[0] == 0) - BUGMSG(D_NORMAL, "WARNING! Station address 00 is reserved " - "for broadcasts!\n"); + arc_printk(D_NORMAL, dev, "WARNING! Station address 00 is reserved for broadcasts!\n"); else if (dev->dev_addr[0] == 255) - BUGMSG(D_NORMAL, "WARNING! Station address FF may confuse " - "DOS networking programs!\n"); + arc_printk(D_NORMAL, dev, "WARNING! Station address FF may confuse DOS networking programs!\n"); - BUGMSG(D_DEBUG, "%s: %d: %s\n",__FILE__,__LINE__,__func__); - if (ASTATUS() & RESETflag) { - BUGMSG(D_DEBUG, "%s: %d: %s\n",__FILE__,__LINE__,__func__); - ACOMMAND(CFLAGScmd | RESETclear); + arc_printk(D_DEBUG, dev, "%s: %d: %s\n", __FILE__, __LINE__, __func__); + if (lp->hw.status(dev) & RESETflag) { + arc_printk(D_DEBUG, dev, "%s: %d: %s\n", + __FILE__, __LINE__, __func__); + lp->hw.command(dev, CFLAGScmd | RESETclear); } - - BUGMSG(D_DEBUG, "%s: %d: %s\n",__FILE__,__LINE__,__func__); + arc_printk(D_DEBUG, dev, "%s: %d: %s\n", __FILE__, __LINE__, __func__); /* make sure we're ready to receive IRQ's. */ - AINTMASK(0); + lp->hw.intmask(dev, 0); udelay(1); /* give it time to set the mask before * we reset it again. (may not even be * necessary) */ - BUGMSG(D_DEBUG, "%s: %d: %s\n",__FILE__,__LINE__,__func__); + arc_printk(D_DEBUG, dev, "%s: %d: %s\n", __FILE__, __LINE__, __func__); lp->intmask = NORXflag | RECONflag; - AINTMASK(lp->intmask); - BUGMSG(D_DEBUG, "%s: %d: %s\n",__FILE__,__LINE__,__func__); + lp->hw.intmask(dev, lp->intmask); + arc_printk(D_DEBUG, dev, "%s: %d: %s\n", __FILE__, __LINE__, __func__); netif_start_queue(dev); @@ -458,7 +431,7 @@ int arcnet_open(struct net_device *dev) module_put(lp->hw.owner); return error; } - +EXPORT_SYMBOL(arcnet_open); /* The inverse routine to arcnet_open - shuts down the card. */ int arcnet_close(struct net_device *dev) @@ -468,9 +441,9 @@ int arcnet_close(struct net_device *dev) netif_stop_queue(dev); /* flush TX and disable RX */ - AINTMASK(0); - ACOMMAND(NOTXcmd); /* stop transmit */ - ACOMMAND(NORXcmd); /* disable receive */ + lp->hw.intmask(dev, 0); + lp->hw.command(dev, NOTXcmd); /* stop transmit */ + lp->hw.command(dev, NORXcmd); /* disable receive */ mdelay(1); /* shut down the card */ @@ -478,7 +451,7 @@ int arcnet_close(struct net_device *dev) module_put(lp->hw.owner); return 0; } - +EXPORT_SYMBOL(arcnet_close); static int arcnet_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, @@ -488,48 +461,44 @@ static int arcnet_header(struct sk_buff *skb, struct net_device *dev, uint8_t _daddr, proto_num; struct ArcProto *proto; - BUGMSG(D_DURING, - "create header from %d to %d; protocol %d (%Xh); size %u.\n", - saddr ? *(uint8_t *) saddr : -1, - daddr ? *(uint8_t *) daddr : -1, - type, type, len); - - if (skb->len!=0 && len != skb->len) - BUGMSG(D_NORMAL, "arcnet_header: Yikes! skb->len(%d) != len(%d)!\n", - skb->len, len); - - - /* Type is host order - ? */ - if(type == ETH_P_ARCNET) { - proto = arc_raw_proto; - BUGMSG(D_DEBUG, "arc_raw_proto used. proto='%c'\n",proto->suffix); - _daddr = daddr ? *(uint8_t *) daddr : 0; - } - else if (!daddr) { - /* - * if the dest addr isn't provided, we can't choose an encapsulation! - * Store the packet type (eg. ETH_P_IP) for now, and we'll push on a - * real header when we do rebuild_header. - */ - *(uint16_t *) skb_push(skb, 2) = type; - /* - * XXX: Why not use skb->mac_len? + arc_printk(D_DURING, dev, + "create header from %d to %d; protocol %d (%Xh); size %u.\n", + saddr ? *(uint8_t *)saddr : -1, + daddr ? *(uint8_t *)daddr : -1, + type, type, len); + + if (skb->len != 0 && len != skb->len) + arc_printk(D_NORMAL, dev, "arcnet_header: Yikes! skb->len(%d) != len(%d)!\n", + skb->len, len); + + /* Type is host order - ? */ + if (type == ETH_P_ARCNET) { + proto = arc_raw_proto; + arc_printk(D_DEBUG, dev, "arc_raw_proto used. proto='%c'\n", + proto->suffix); + _daddr = daddr ? *(uint8_t *)daddr : 0; + } else if (!daddr) { + /* if the dest addr isn't provided, we can't choose an + * encapsulation! Store the packet type (eg. ETH_P_IP) + * for now, and we'll push on a real header when we do + * rebuild_header. */ + *(uint16_t *)skb_push(skb, 2) = type; + /* XXX: Why not use skb->mac_len? */ if (skb->network_header - skb->mac_header != 2) - BUGMSG(D_NORMAL, "arcnet_header: Yikes! diff (%d) is not 2!\n", - (int)(skb->network_header - skb->mac_header)); + arc_printk(D_NORMAL, dev, "arcnet_header: Yikes! diff (%u) is not 2!\n", + skb->network_header - skb->mac_header); return -2; /* return error -- can't transmit yet! */ - } - else { + } else { /* otherwise, we can just add the header as usual. */ - _daddr = *(uint8_t *) daddr; + _daddr = *(uint8_t *)daddr; proto_num = lp->default_proto[_daddr]; proto = arc_proto_map[proto_num]; - BUGMSG(D_DURING, "building header for %02Xh using protocol '%c'\n", - proto_num, proto->suffix); + arc_printk(D_DURING, dev, "building header for %02Xh using protocol '%c'\n", + proto_num, proto->suffix); if (proto == &arc_proto_null && arc_bcast_proto != proto) { - BUGMSG(D_DURING, "actually, let's use '%c' instead.\n", - arc_bcast_proto->suffix); + arc_printk(D_DURING, dev, "actually, let's use '%c' instead.\n", + arc_bcast_proto->suffix); proto = arc_bcast_proto; } } @@ -538,7 +507,7 @@ static int arcnet_header(struct sk_buff *skb, struct net_device *dev, /* Called by the kernel in order to transmit a packet. */ netdev_tx_t arcnet_send_packet(struct sk_buff *skb, - struct net_device *dev) + struct net_device *dev) { struct arcnet_local *lp = netdev_priv(dev); struct archdr *pkt; @@ -548,21 +517,22 @@ netdev_tx_t arcnet_send_packet(struct sk_buff *skb, unsigned long flags; int freeskb, retval; - BUGMSG(D_DURING, - "transmit requested (status=%Xh, txbufs=%d/%d, len=%d, protocol %x)\n", - ASTATUS(), lp->cur_tx, lp->next_tx, skb->len,skb->protocol); + arc_printk(D_DURING, dev, + "transmit requested (status=%Xh, txbufs=%d/%d, len=%d, protocol %x)\n", + lp->hw.status(dev), lp->cur_tx, lp->next_tx, skb->len, skb->protocol); - pkt = (struct archdr *) skb->data; + pkt = (struct archdr *)skb->data; soft = &pkt->soft.rfc1201; proto = arc_proto_map[soft->proto]; - BUGMSG(D_SKB_SIZE, "skb: transmitting %d bytes to %02X\n", - skb->len, pkt->hard.dest); - BUGLVL(D_SKB) arcnet_dump_skb(dev, skb, "tx"); + arc_printk(D_SKB_SIZE, dev, "skb: transmitting %d bytes to %02X\n", + skb->len, pkt->hard.dest); + if (BUGLVL(D_SKB)) + arcnet_dump_skb(dev, skb, "tx"); /* fits in one packet? */ if (skb->len - ARC_HDR_SIZE > XMTU && !proto->continue_tx) { - BUGMSG(D_NORMAL, "fixme: packet too large: compensating badly!\n"); + arc_printk(D_NORMAL, dev, "fixme: packet too large: compensating badly!\n"); dev_kfree_skb(skb); return NETDEV_TX_OK; /* don't try again */ } @@ -571,17 +541,18 @@ netdev_tx_t arcnet_send_packet(struct sk_buff *skb, netif_stop_queue(dev); spin_lock_irqsave(&lp->lock, flags); - AINTMASK(0); - if(lp->next_tx == -1) + lp->hw.intmask(dev, 0); + if (lp->next_tx == -1) txbuf = get_arcbuf(dev); - else { + else txbuf = -1; - } + if (txbuf != -1) { if (proto->prepare_tx(dev, pkt, skb->len, txbuf) && !proto->ack_tx) { /* done right away and we don't want to acknowledge - the package later - forget about it now */ + * the package later - forget about it now + */ dev->stats.tx_bytes += skb->len; freeskb = 1; } else { @@ -594,9 +565,9 @@ netdev_tx_t arcnet_send_packet(struct sk_buff *skb, if (proto->continue_tx && proto->continue_tx(dev, txbuf)) { - BUGMSG(D_NORMAL, - "bug! continue_tx finished the first time! " - "(proto='%c')\n", proto->suffix); + arc_printk(D_NORMAL, dev, + "bug! continue_tx finished the first time! (proto='%c')\n", + proto->suffix); } } retval = NETDEV_TX_OK; @@ -606,61 +577,62 @@ netdev_tx_t arcnet_send_packet(struct sk_buff *skb, freeskb = 0; } - BUGMSG(D_DEBUG, "%s: %d: %s, status: %x\n",__FILE__,__LINE__,__func__,ASTATUS()); + arc_printk(D_DEBUG, dev, "%s: %d: %s, status: %x\n", + __FILE__, __LINE__, __func__, lp->hw.status(dev)); /* make sure we didn't ignore a TX IRQ while we were in here */ - AINTMASK(0); + lp->hw.intmask(dev, 0); - BUGMSG(D_DEBUG, "%s: %d: %s\n",__FILE__,__LINE__,__func__); - lp->intmask |= TXFREEflag|EXCNAKflag; - AINTMASK(lp->intmask); - BUGMSG(D_DEBUG, "%s: %d: %s, status: %x\n",__FILE__,__LINE__,__func__,ASTATUS()); + arc_printk(D_DEBUG, dev, "%s: %d: %s\n", __FILE__, __LINE__, __func__); + lp->intmask |= TXFREEflag | EXCNAKflag; + lp->hw.intmask(dev, lp->intmask); + arc_printk(D_DEBUG, dev, "%s: %d: %s, status: %x\n", + __FILE__, __LINE__, __func__, lp->hw.status(dev)); spin_unlock_irqrestore(&lp->lock, flags); - if (freeskb) { + if (freeskb) dev_kfree_skb(skb); - } + return retval; /* no need to try again */ } +EXPORT_SYMBOL(arcnet_send_packet); - -/* - * Actually start transmitting a packet that was loaded into a buffer +/* Actually start transmitting a packet that was loaded into a buffer * by prepare_tx. This should _only_ be called by the interrupt handler. */ static int go_tx(struct net_device *dev) { struct arcnet_local *lp = netdev_priv(dev); - BUGMSG(D_DURING, "go_tx: status=%Xh, intmask=%Xh, next_tx=%d, cur_tx=%d\n", - ASTATUS(), lp->intmask, lp->next_tx, lp->cur_tx); + arc_printk(D_DURING, dev, "go_tx: status=%Xh, intmask=%Xh, next_tx=%d, cur_tx=%d\n", + lp->hw.status(dev), lp->intmask, lp->next_tx, lp->cur_tx); if (lp->cur_tx != -1 || lp->next_tx == -1) return 0; - BUGLVL(D_TX) arcnet_dump_packet(dev, lp->next_tx, "go_tx", 0); + if (BUGLVL(D_TX)) + arcnet_dump_packet(dev, lp->next_tx, "go_tx", 0); lp->cur_tx = lp->next_tx; lp->next_tx = -1; /* start sending */ - ACOMMAND(TXcmd | (lp->cur_tx << 3)); + lp->hw.command(dev, TXcmd | (lp->cur_tx << 3)); dev->stats.tx_packets++; lp->lasttrans_dest = lp->lastload_dest; lp->lastload_dest = 0; lp->excnak_pending = 0; - lp->intmask |= TXFREEflag|EXCNAKflag; + lp->intmask |= TXFREEflag | EXCNAKflag; return 1; } - /* Called by the kernel when transmit times out */ void arcnet_timeout(struct net_device *dev) { unsigned long flags; struct arcnet_local *lp = netdev_priv(dev); - int status = ASTATUS(); + int status = lp->hw.status(dev); char *msg; spin_lock_irqsave(&lp->lock, flags); @@ -670,30 +642,29 @@ void arcnet_timeout(struct net_device *dev) msg = ""; dev->stats.tx_aborted_errors++; lp->timed_out = 1; - ACOMMAND(NOTXcmd | (lp->cur_tx << 3)); + lp->hw.command(dev, NOTXcmd | (lp->cur_tx << 3)); } dev->stats.tx_errors++; /* make sure we didn't miss a TX or a EXC NAK IRQ */ - AINTMASK(0); - lp->intmask |= TXFREEflag|EXCNAKflag; - AINTMASK(lp->intmask); - + lp->hw.intmask(dev, 0); + lp->intmask |= TXFREEflag | EXCNAKflag; + lp->hw.intmask(dev, lp->intmask); + spin_unlock_irqrestore(&lp->lock, flags); - if (time_after(jiffies, lp->last_timeout + 10*HZ)) { - BUGMSG(D_EXTRA, "tx timed out%s (status=%Xh, intmask=%Xh, dest=%02Xh)\n", - msg, status, lp->intmask, lp->lasttrans_dest); + if (time_after(jiffies, lp->last_timeout + 10 * HZ)) { + arc_printk(D_EXTRA, dev, "tx timed out%s (status=%Xh, intmask=%Xh, dest=%02Xh)\n", + msg, status, lp->intmask, lp->lasttrans_dest); lp->last_timeout = jiffies; } if (lp->cur_tx == -1) netif_wake_queue(dev); } +EXPORT_SYMBOL(arcnet_timeout); - -/* - * The typical workload of the driver: Handle the network interface +/* The typical workload of the driver: Handle the network interface * interrupts. Establish which device needs attention, and call the correct * chipset interrupt handler. */ @@ -704,125 +675,125 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) int recbuf, status, diagstatus, didsomething, boguscount; int retval = IRQ_NONE; - BUGMSG(D_DURING, "\n"); + arc_printk(D_DURING, dev, "\n"); - BUGMSG(D_DURING, "in arcnet_interrupt\n"); + arc_printk(D_DURING, dev, "in arcnet_interrupt\n"); lp = netdev_priv(dev); BUG_ON(!lp); - + spin_lock(&lp->lock); - /* - * RESET flag was enabled - if device is not running, we must clear it right - * away (but nothing else). + /* RESET flag was enabled - if device is not running, we must + * clear it right away (but nothing else). */ if (!netif_running(dev)) { - if (ASTATUS() & RESETflag) - ACOMMAND(CFLAGScmd | RESETclear); - AINTMASK(0); + if (lp->hw.status(dev) & RESETflag) + lp->hw.command(dev, CFLAGScmd | RESETclear); + lp->hw.intmask(dev, 0); spin_unlock(&lp->lock); return retval; } - BUGMSG(D_DURING, "in arcnet_inthandler (status=%Xh, intmask=%Xh)\n", - ASTATUS(), lp->intmask); + arc_printk(D_DURING, dev, "in arcnet_inthandler (status=%Xh, intmask=%Xh)\n", + lp->hw.status(dev), lp->intmask); boguscount = 5; do { - status = ASTATUS(); - diagstatus = (status >> 8) & 0xFF; + status = lp->hw.status(dev); + diagstatus = (status >> 8) & 0xFF; - BUGMSG(D_DEBUG, "%s: %d: %s: status=%x\n", - __FILE__,__LINE__,__func__,status); + arc_printk(D_DEBUG, dev, "%s: %d: %s: status=%x\n", + __FILE__, __LINE__, __func__, status); didsomething = 0; - /* - * RESET flag was enabled - card is resetting and if RX is + /* RESET flag was enabled - card is resetting and if RX is * disabled, it's NOT because we just got a packet. - * - * The card is in an undefined state. Clear it out and start over. + * + * The card is in an undefined state. + * Clear it out and start over. */ if (status & RESETflag) { - BUGMSG(D_NORMAL, "spurious reset (status=%Xh)\n", status); + arc_printk(D_NORMAL, dev, "spurious reset (status=%Xh)\n", + status); arcnet_close(dev); arcnet_open(dev); /* get out of the interrupt handler! */ break; } - /* - * RX is inhibited - we must have received something. Prepare to - * receive into the next buffer. - * - * We don't actually copy the received packet from the card until - * after the transmit handler runs (and possibly launches the next - * tx); this should improve latency slightly if we get both types - * of interrupts at once. + /* RX is inhibited - we must have received something. + * Prepare to receive into the next buffer. + * + * We don't actually copy the received packet from the card + * until after the transmit handler runs (and possibly + * launches the next tx); this should improve latency slightly + * if we get both types of interrupts at once. */ recbuf = -1; if (status & lp->intmask & NORXflag) { recbuf = lp->cur_rx; - BUGMSG(D_DURING, "Buffer #%d: receive irq (status=%Xh)\n", - recbuf, status); + arc_printk(D_DURING, dev, "Buffer #%d: receive irq (status=%Xh)\n", + recbuf, status); lp->cur_rx = get_arcbuf(dev); if (lp->cur_rx != -1) { - BUGMSG(D_DURING, "enabling receive to buffer #%d\n", - lp->cur_rx); - ACOMMAND(RXcmd | (lp->cur_rx << 3) | RXbcasts); + arc_printk(D_DURING, dev, "enabling receive to buffer #%d\n", + lp->cur_rx); + lp->hw.command(dev, RXcmd | (lp->cur_rx << 3) | RXbcasts); } didsomething++; } - if((diagstatus & EXCNAKflag)) { - BUGMSG(D_DURING, "EXCNAK IRQ (diagstat=%Xh)\n", - diagstatus); + if ((diagstatus & EXCNAKflag)) { + arc_printk(D_DURING, dev, "EXCNAK IRQ (diagstat=%Xh)\n", + diagstatus); - ACOMMAND(NOTXcmd); /* disable transmit */ - lp->excnak_pending = 1; + lp->hw.command(dev, NOTXcmd); /* disable transmit */ + lp->excnak_pending = 1; - ACOMMAND(EXCNAKclear); + lp->hw.command(dev, EXCNAKclear); lp->intmask &= ~(EXCNAKflag); - didsomething++; - } - + didsomething++; + } /* a transmit finished, and we're interested in it. */ if ((status & lp->intmask & TXFREEflag) || lp->timed_out) { - lp->intmask &= ~(TXFREEflag|EXCNAKflag); + lp->intmask &= ~(TXFREEflag | EXCNAKflag); - BUGMSG(D_DURING, "TX IRQ (stat=%Xh)\n", status); + arc_printk(D_DURING, dev, "TX IRQ (stat=%Xh)\n", + status); if (lp->cur_tx != -1 && !lp->timed_out) { - if(!(status & TXACKflag)) { + if (!(status & TXACKflag)) { if (lp->lasttrans_dest != 0) { - BUGMSG(D_EXTRA, - "transmit was not acknowledged! " - "(status=%Xh, dest=%02Xh)\n", - status, lp->lasttrans_dest); + arc_printk(D_EXTRA, dev, + "transmit was not acknowledged! (status=%Xh, dest=%02Xh)\n", + status, + lp->lasttrans_dest); dev->stats.tx_errors++; dev->stats.tx_carrier_errors++; } else { - BUGMSG(D_DURING, - "broadcast was not acknowledged; that's normal " - "(status=%Xh, dest=%02Xh)\n", - status, lp->lasttrans_dest); + arc_printk(D_DURING, dev, + "broadcast was not acknowledged; that's normal (status=%Xh, dest=%02Xh)\n", + status, + lp->lasttrans_dest); } } if (lp->outgoing.proto && lp->outgoing.proto->ack_tx) { - int ackstatus; - if(status & TXACKflag) - ackstatus=2; - else if(lp->excnak_pending) - ackstatus=1; - else - ackstatus=0; - - lp->outgoing.proto - ->ack_tx(dev, ackstatus); + int ackstatus; + + if (status & TXACKflag) + ackstatus = 2; + else if (lp->excnak_pending) + ackstatus = 1; + else + ackstatus = 0; + + lp->outgoing.proto + ->ack_tx(dev, ackstatus); } } if (lp->cur_tx != -1) @@ -836,17 +807,18 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) go_tx(dev); /* continue a split packet, if any */ - if (lp->outgoing.proto && lp->outgoing.proto->continue_tx) { + if (lp->outgoing.proto && + lp->outgoing.proto->continue_tx) { int txbuf = get_arcbuf(dev); + if (txbuf != -1) { if (lp->outgoing.proto->continue_tx(dev, txbuf)) { /* that was the last segment */ dev->stats.tx_bytes += lp->outgoing.skb->len; - if(!lp->outgoing.proto->ack_tx) - { - dev_kfree_skb_irq(lp->outgoing.skb); - lp->outgoing.proto = NULL; - } + if (!lp->outgoing.proto->ack_tx) { + dev_kfree_skb_irq(lp->outgoing.skb); + lp->outgoing.proto = NULL; + } } lp->next_tx = txbuf; } @@ -857,7 +829,8 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) } /* now process the received packet, if any */ if (recbuf != -1) { - BUGLVL(D_RX) arcnet_dump_packet(dev, recbuf, "rx irq", 0); + if (BUGLVL(D_RX)) + arcnet_dump_packet(dev, recbuf, "rx irq", 0); arcnet_rx(dev, recbuf); release_arcbuf(dev, recbuf); @@ -865,32 +838,32 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) didsomething++; } if (status & lp->intmask & RECONflag) { - ACOMMAND(CFLAGScmd | CONFIGclear); + lp->hw.command(dev, CFLAGScmd | CONFIGclear); dev->stats.tx_carrier_errors++; - BUGMSG(D_RECON, "Network reconfiguration detected (status=%Xh)\n", - status); + arc_printk(D_RECON, dev, "Network reconfiguration detected (status=%Xh)\n", + status); /* MYRECON bit is at bit 7 of diagstatus */ - if(diagstatus & 0x80) - BUGMSG(D_RECON,"Put out that recon myself\n"); + if (diagstatus & 0x80) + arc_printk(D_RECON, dev, "Put out that recon myself\n"); /* is the RECON info empty or old? */ if (!lp->first_recon || !lp->last_recon || time_after(jiffies, lp->last_recon + HZ * 10)) { if (lp->network_down) - BUGMSG(D_NORMAL, "reconfiguration detected: cabling restored?\n"); + arc_printk(D_NORMAL, dev, "reconfiguration detected: cabling restored?\n"); lp->first_recon = lp->last_recon = jiffies; lp->num_recons = lp->network_down = 0; - BUGMSG(D_DURING, "recon: clearing counters.\n"); + arc_printk(D_DURING, dev, "recon: clearing counters.\n"); } else { /* add to current RECON counter */ lp->last_recon = jiffies; lp->num_recons++; - BUGMSG(D_DURING, "recon: counter=%d, time=%lds, net=%d\n", - lp->num_recons, - (lp->last_recon - lp->first_recon) / HZ, - lp->network_down); + arc_printk(D_DURING, dev, "recon: counter=%d, time=%lds, net=%d\n", + lp->num_recons, + (lp->last_recon - lp->first_recon) / HZ, + lp->network_down); /* if network is marked up; * and first_recon and last_recon are 60+ apart; @@ -902,46 +875,44 @@ irqreturn_t arcnet_interrupt(int irq, void *dev_id) (lp->last_recon - lp->first_recon) <= HZ * 60 && lp->num_recons >= RECON_THRESHOLD) { lp->network_down = 1; - BUGMSG(D_NORMAL, "many reconfigurations detected: cabling problem?\n"); + arc_printk(D_NORMAL, dev, "many reconfigurations detected: cabling problem?\n"); } else if (!lp->network_down && lp->last_recon - lp->first_recon > HZ * 60) { - /* reset counters if we've gone for over a minute. */ + /* reset counters if we've gone for + * over a minute. + */ lp->first_recon = lp->last_recon; lp->num_recons = 1; } } } else if (lp->network_down && - time_after(jiffies, lp->last_recon + HZ * 10)) { + time_after(jiffies, lp->last_recon + HZ * 10)) { if (lp->network_down) - BUGMSG(D_NORMAL, "cabling restored?\n"); + arc_printk(D_NORMAL, dev, "cabling restored?\n"); lp->first_recon = lp->last_recon = 0; lp->num_recons = lp->network_down = 0; - BUGMSG(D_DURING, "not recon: clearing counters anyway.\n"); + arc_printk(D_DURING, dev, "not recon: clearing counters anyway.\n"); } - if(didsomething) { + if (didsomething) retval |= IRQ_HANDLED; - } - } - while (--boguscount && didsomething); - - BUGMSG(D_DURING, "arcnet_interrupt complete (status=%Xh, count=%d)\n", - ASTATUS(), boguscount); - BUGMSG(D_DURING, "\n"); + } while (--boguscount && didsomething); + arc_printk(D_DURING, dev, "arcnet_interrupt complete (status=%Xh, count=%d)\n", + lp->hw.status(dev), boguscount); + arc_printk(D_DURING, dev, "\n"); - AINTMASK(0); + lp->hw.intmask(dev, 0); udelay(1); - AINTMASK(lp->intmask); - + lp->hw.intmask(dev, lp->intmask); + spin_unlock(&lp->lock); return retval; } +EXPORT_SYMBOL(arcnet_interrupt); - -/* - * This is a generic packet receiver that calls arcnet??_rx depending on the +/* This is a generic packet receiver that calls arcnet??_rx depending on the * protocol ID found. */ static void arcnet_rx(struct net_device *dev, int bufnum) @@ -963,32 +934,31 @@ static void arcnet_rx(struct net_device *dev, int bufnum) } /* get the full header, if possible */ - if (sizeof(pkt.soft) <= length) + if (sizeof(pkt.soft) <= length) { lp->hw.copy_from_card(dev, bufnum, ofs, soft, sizeof(pkt.soft)); - else { + } else { memset(&pkt.soft, 0, sizeof(pkt.soft)); lp->hw.copy_from_card(dev, bufnum, ofs, soft, length); } - BUGMSG(D_DURING, "Buffer #%d: received packet from %02Xh to %02Xh " - "(%d+4 bytes)\n", - bufnum, pkt.hard.source, pkt.hard.dest, length); + arc_printk(D_DURING, dev, "Buffer #%d: received packet from %02Xh to %02Xh (%d+4 bytes)\n", + bufnum, pkt.hard.source, pkt.hard.dest, length); dev->stats.rx_packets++; dev->stats.rx_bytes += length + ARC_HDR_SIZE; /* call the right receiver for the protocol */ if (arc_proto_map[soft->proto]->is_ip) { - BUGLVL(D_PROTO) { + if (BUGLVL(D_PROTO)) { struct ArcProto *oldp = arc_proto_map[lp->default_proto[pkt.hard.source]], *newp = arc_proto_map[soft->proto]; if (oldp != newp) { - BUGMSG(D_PROTO, - "got protocol %02Xh; encap for host %02Xh is now '%c'" - " (was '%c')\n", soft->proto, pkt.hard.source, - newp->suffix, oldp->suffix); + arc_printk(D_PROTO, dev, + "got protocol %02Xh; encap for host %02Xh is now '%c' (was '%c')\n", + soft->proto, pkt.hard.source, + newp->suffix, oldp->suffix); } } @@ -1002,30 +972,27 @@ static void arcnet_rx(struct net_device *dev, int bufnum) arc_proto_map[soft->proto]->rx(dev, bufnum, &pkt, length); } - static void null_rx(struct net_device *dev, int bufnum, struct archdr *pkthdr, int length) { - BUGMSG(D_PROTO, - "rx: don't know how to deal with proto %02Xh from host %02Xh.\n", - pkthdr->soft.rfc1201.proto, pkthdr->hard.source); + arc_printk(D_PROTO, dev, + "rx: don't know how to deal with proto %02Xh from host %02Xh.\n", + pkthdr->soft.rfc1201.proto, pkthdr->hard.source); } - static int null_build_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, uint8_t daddr) { struct arcnet_local *lp = netdev_priv(dev); - BUGMSG(D_PROTO, - "tx: can't build header for encap %02Xh; load a protocol driver.\n", - lp->default_proto[daddr]); + arc_printk(D_PROTO, dev, + "tx: can't build header for encap %02Xh; load a protocol driver.\n", + lp->default_proto[daddr]); /* always fails */ return 0; } - /* the "do nothing" prepare_tx function warns that there's nothing to do. */ static int null_prepare_tx(struct net_device *dev, struct archdr *pkt, int length, int bufnum) @@ -1033,7 +1000,7 @@ static int null_prepare_tx(struct net_device *dev, struct archdr *pkt, struct arcnet_local *lp = netdev_priv(dev); struct arc_hardware newpkt; - BUGMSG(D_PROTO, "tx: no encap for this host; load a protocol driver.\n"); + arc_printk(D_PROTO, dev, "tx: no encap for this host; load a protocol driver.\n"); /* send a packet to myself -- will never get received, of course */ newpkt.source = newpkt.dest = dev->dev_addr[0]; diff --git a/drivers/net/arcnet/capmode.c b/drivers/net/arcnet/capmode.c index 42fce91b71fc..2056878fb087 100644 --- a/drivers/net/arcnet/capmode.c +++ b/drivers/net/arcnet/capmode.c @@ -26,6 +26,8 @@ * ********************** */ +#define pr_fmt(fmt) "arcnet:" KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/gfp.h> #include <linux/init.h> @@ -33,9 +35,8 @@ #include <net/arp.h> #include <linux/netdevice.h> #include <linux/skbuff.h> -#include <linux/arcdevice.h> -#define VERSION "arcnet: cap mode (`c') encapsulation support loaded.\n" +#include "arcdevice.h" /* packet receiver */ static void rx(struct net_device *dev, int bufnum, @@ -47,7 +48,8 @@ static void rx(struct net_device *dev, int bufnum, char *pktbuf, *pkthdrbuf; int ofs; - BUGMSG(D_DURING, "it's a raw(cap) packet (length=%d)\n", length); + arc_printk(D_DURING, dev, "it's a raw(cap) packet (length=%d)\n", + length); if (length >= MinTU) ofs = 512 - length; @@ -55,8 +57,7 @@ static void rx(struct net_device *dev, int bufnum, ofs = 256 - length; skb = alloc_skb(length + ARC_HDR_SIZE + sizeof(int), GFP_ATOMIC); - if (skb == NULL) { - BUGMSG(D_NORMAL, "Memory squeeze, dropping packet.\n"); + if (!skb) { dev->stats.rx_dropped++; return; } @@ -66,17 +67,17 @@ static void rx(struct net_device *dev, int bufnum, pkt = (struct archdr *)skb_mac_header(skb); skb_pull(skb, ARC_HDR_SIZE); - /* up to sizeof(pkt->soft) has already been copied from the card */ - /* squeeze in an int for the cap encapsulation */ - - /* use these variables to be sure we count in bytes, not in - sizeof(struct archdr) */ - pktbuf=(char*)pkt; - pkthdrbuf=(char*)pkthdr; - memcpy(pktbuf, pkthdrbuf, ARC_HDR_SIZE+sizeof(pkt->soft.cap.proto)); - memcpy(pktbuf+ARC_HDR_SIZE+sizeof(pkt->soft.cap.proto)+sizeof(int), - pkthdrbuf+ARC_HDR_SIZE+sizeof(pkt->soft.cap.proto), - sizeof(struct archdr)-ARC_HDR_SIZE-sizeof(pkt->soft.cap.proto)); + /* up to sizeof(pkt->soft) has already been copied from the card + * squeeze in an int for the cap encapsulation + * use these variables to be sure we count in bytes, not in + * sizeof(struct archdr) + */ + pktbuf = (char *)pkt; + pkthdrbuf = (char *)pkthdr; + memcpy(pktbuf, pkthdrbuf, ARC_HDR_SIZE + sizeof(pkt->soft.cap.proto)); + memcpy(pktbuf + ARC_HDR_SIZE + sizeof(pkt->soft.cap.proto) + sizeof(int), + pkthdrbuf + ARC_HDR_SIZE + sizeof(pkt->soft.cap.proto), + sizeof(struct archdr) - ARC_HDR_SIZE - sizeof(pkt->soft.cap.proto)); if (length > sizeof(pkt->soft)) lp->hw.copy_from_card(dev, bufnum, ofs + sizeof(pkt->soft), @@ -84,15 +85,14 @@ static void rx(struct net_device *dev, int bufnum, + sizeof(int), length - sizeof(pkt->soft)); - BUGLVL(D_SKB) arcnet_dump_skb(dev, skb, "rx"); + if (BUGLVL(D_SKB)) + arcnet_dump_skb(dev, skb, "rx"); skb->protocol = cpu_to_be16(ETH_P_ARCNET); netif_rx(skb); } - -/* - * Create the ARCnet hard/soft headers for cap mode. +/* Create the ARCnet hard/soft headers for cap mode. * There aren't any soft headers in cap mode - not even the protocol id. */ static int build_header(struct sk_buff *skb, @@ -101,12 +101,12 @@ static int build_header(struct sk_buff *skb, uint8_t daddr) { int hdr_size = ARC_HDR_SIZE; - struct archdr *pkt = (struct archdr *) skb_push(skb, hdr_size); + struct archdr *pkt = (struct archdr *)skb_push(skb, hdr_size); - BUGMSG(D_PROTO, "Preparing header for cap packet %x.\n", - *((int*)&pkt->soft.cap.cookie[0])); - /* - * Set the source hardware address. + arc_printk(D_PROTO, dev, "Preparing header for cap packet %x.\n", + *((int *)&pkt->soft.cap.cookie[0])); + + /* Set the source hardware address. * * This is pretty pointless for most purposes, but it can help in * debugging. ARCnet does not allow us to change the source address in @@ -117,9 +117,8 @@ static int build_header(struct sk_buff *skb, /* see linux/net/ethernet/eth.c to see where I got the following */ if (dev->flags & (IFF_LOOPBACK | IFF_NOARP)) { - /* - * FIXME: fill in the last byte of the dest ipaddr here to better - * comply with RFC1051 in "noarp" mode. + /* FIXME: fill in the last byte of the dest ipaddr here to + * better comply with RFC1051 in "noarp" mode. */ pkt->hard.dest = 0; return hdr_size; @@ -130,7 +129,6 @@ static int build_header(struct sk_buff *skb, return hdr_size; /* success */ } - static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, int bufnum) { @@ -138,22 +136,21 @@ static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, struct arc_hardware *hard = &pkt->hard; int ofs; - /* hard header is not included in packet length */ length -= ARC_HDR_SIZE; /* And neither is the cookie field */ length -= sizeof(int); - BUGMSG(D_DURING, "prepare_tx: txbufs=%d/%d/%d\n", - lp->next_tx, lp->cur_tx, bufnum); + arc_printk(D_DURING, dev, "prepare_tx: txbufs=%d/%d/%d\n", + lp->next_tx, lp->cur_tx, bufnum); - BUGMSG(D_PROTO, "Sending for cap packet %x.\n", - *((int*)&pkt->soft.cap.cookie[0])); + arc_printk(D_PROTO, dev, "Sending for cap packet %x.\n", + *((int *)&pkt->soft.cap.cookie[0])); if (length > XMTU) { /* should never happen! other people already check for this. */ - BUGMSG(D_NORMAL, "Bug! prepare_tx with size %d (> %d)\n", - length, XMTU); + arc_printk(D_NORMAL, dev, "Bug! prepare_tx with size %d (> %d)\n", + length, XMTU); length = XMTU; } if (length > MinTU) { @@ -162,11 +159,12 @@ static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, } else if (length > MTU) { hard->offset[0] = 0; hard->offset[1] = ofs = 512 - length - 3; - } else + } else { hard->offset[0] = ofs = 256 - length; + } - BUGMSG(D_DURING, "prepare_tx: length=%d ofs=%d\n", - length,ofs); + arc_printk(D_DURING, dev, "prepare_tx: length=%d ofs=%d\n", + length, ofs); /* Copy the arcnet-header + the protocol byte down: */ lp->hw.copy_to_card(dev, bufnum, 0, hard, ARC_HDR_SIZE); @@ -174,9 +172,10 @@ static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, sizeof(pkt->soft.cap.proto)); /* Skip the extra integer we have written into it as a cookie - but write the rest of the message: */ - lp->hw.copy_to_card(dev, bufnum, ofs+1, - ((unsigned char*)&pkt->soft.cap.mes),length-1); + * but write the rest of the message: + */ + lp->hw.copy_to_card(dev, bufnum, ofs + 1, + ((unsigned char *)&pkt->soft.cap.mes), length - 1); lp->lastload_dest = hard->dest; @@ -188,21 +187,20 @@ static int ack_tx(struct net_device *dev, int acked) struct arcnet_local *lp = netdev_priv(dev); struct sk_buff *ackskb; struct archdr *ackpkt; - int length=sizeof(struct arc_cap); + int length = sizeof(struct arc_cap); - BUGMSG(D_DURING, "capmode: ack_tx: protocol: %x: result: %d\n", - lp->outgoing.skb->protocol, acked); + arc_printk(D_DURING, dev, "capmode: ack_tx: protocol: %x: result: %d\n", + lp->outgoing.skb->protocol, acked); - BUGLVL(D_SKB) arcnet_dump_skb(dev, lp->outgoing.skb, "ack_tx"); + if (BUGLVL(D_SKB)) + arcnet_dump_skb(dev, lp->outgoing.skb, "ack_tx"); /* Now alloc a skb to send back up through the layers: */ - ackskb = alloc_skb(length + ARC_HDR_SIZE , GFP_ATOMIC); - if (ackskb == NULL) { - BUGMSG(D_NORMAL, "Memory squeeze, can't acknowledge.\n"); + ackskb = alloc_skb(length + ARC_HDR_SIZE, GFP_ATOMIC); + if (!ackskb) goto free_outskb; - } - skb_put(ackskb, length + ARC_HDR_SIZE ); + skb_put(ackskb, length + ARC_HDR_SIZE); ackskb->dev = dev; skb_reset_mac_header(ackskb); @@ -212,39 +210,40 @@ static int ack_tx(struct net_device *dev, int acked) skb_copy_from_linear_data(lp->outgoing.skb, ackpkt, ARC_HDR_SIZE + sizeof(struct arc_cap)); ackpkt->soft.cap.proto = 0; /* using protocol 0 for acknowledge */ - ackpkt->soft.cap.mes.ack=acked; + ackpkt->soft.cap.mes.ack = acked; - BUGMSG(D_PROTO, "Ackknowledge for cap packet %x.\n", - *((int*)&ackpkt->soft.cap.cookie[0])); + arc_printk(D_PROTO, dev, "Ackknowledge for cap packet %x.\n", + *((int *)&ackpkt->soft.cap.cookie[0])); ackskb->protocol = cpu_to_be16(ETH_P_ARCNET); - BUGLVL(D_SKB) arcnet_dump_skb(dev, ackskb, "ack_tx_recv"); + if (BUGLVL(D_SKB)) + arcnet_dump_skb(dev, ackskb, "ack_tx_recv"); netif_rx(ackskb); free_outskb: dev_kfree_skb_irq(lp->outgoing.skb); - lp->outgoing.proto = NULL; /* We are always finished when in this protocol */ + lp->outgoing.proto = NULL; + /* We are always finished when in this protocol */ return 0; } -static struct ArcProto capmode_proto = -{ - 'r', - XMTU, - 0, - rx, - build_header, - prepare_tx, - NULL, - ack_tx +static struct ArcProto capmode_proto = { + .suffix = 'r', + .mtu = XMTU, + .rx = rx, + .build_header = build_header, + .prepare_tx = prepare_tx, + .ack_tx = ack_tx }; -static void arcnet_cap_init(void) +static int __init capmode_module_init(void) { int count; + pr_info("cap mode (`c') encapsulation support loaded\n"); + for (count = 1; count <= 8; count++) if (arc_proto_map[count] == arc_proto_default) arc_proto_map[count] = &capmode_proto; @@ -255,12 +254,7 @@ static void arcnet_cap_init(void) arc_proto_default = &capmode_proto; arc_raw_proto = &capmode_proto; -} -static int __init capmode_module_init(void) -{ - printk(VERSION); - arcnet_cap_init(); return 0; } diff --git a/drivers/net/arcnet/com20020-isa.c b/drivers/net/arcnet/com20020-isa.c index 45c61a2c5fbd..b9e9931353b2 100644 --- a/drivers/net/arcnet/com20020-isa.c +++ b/drivers/net/arcnet/com20020-isa.c @@ -1,6 +1,6 @@ /* * Linux ARCnet driver - COM20020 chipset support - * + * * Written 1997 by David Woodhouse. * Written 1994-1999 by Avery Pennarun. * Written 1999-2000 by Martin Mares <mj@ucw.cz>. @@ -25,6 +25,9 @@ * * ********************** */ + +#define pr_fmt(fmt) "arcnet:" KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/kernel.h> @@ -36,16 +39,12 @@ #include <linux/init.h> #include <linux/interrupt.h> #include <linux/bootmem.h> -#include <linux/arcdevice.h> -#include <linux/com20020.h> - -#include <asm/io.h> +#include <linux/io.h> -#define VERSION "arcnet: COM20020 ISA support (by David Woodhouse et al.)\n" +#include "arcdevice.h" +#include "com20020.h" - -/* - * We cannot (yet) probe for an IO mapped card, although we can check that +/* We cannot (yet) probe for an IO mapped card, although we can check that * it's where we were told it was, and even do autoirq. */ static int __init com20020isa_probe(struct net_device *dev) @@ -55,21 +54,21 @@ static int __init com20020isa_probe(struct net_device *dev) struct arcnet_local *lp = netdev_priv(dev); int err; - BUGLVL(D_NORMAL) printk(VERSION); + if (BUGLVL(D_NORMAL)) + pr_info("%s\n", "COM20020 ISA support (by David Woodhouse et al.)"); ioaddr = dev->base_addr; if (!ioaddr) { - BUGMSG(D_NORMAL, "No autoprobe (yet) for IO mapped cards; you " - "must specify the base address!\n"); + arc_printk(D_NORMAL, dev, "No autoprobe (yet) for IO mapped cards; you must specify the base address!\n"); return -ENODEV; } if (!request_region(ioaddr, ARCNET_TOTAL_SIZE, "arcnet (COM20020)")) { - BUGMSG(D_NORMAL, "IO region %xh-%xh already allocated.\n", - ioaddr, ioaddr + ARCNET_TOTAL_SIZE - 1); + arc_printk(D_NORMAL, dev, "IO region %xh-%xh already allocated.\n", + ioaddr, ioaddr + ARCNET_TOTAL_SIZE - 1); return -ENXIO; } - if (ASTATUS() == 0xFF) { - BUGMSG(D_NORMAL, "IO address %x empty\n", ioaddr); + if (arcnet_inb(ioaddr, COM20020_REG_R_STATUS) == 0xFF) { + arc_printk(D_NORMAL, dev, "IO address %x empty\n", ioaddr); err = -ENODEV; goto out; } @@ -83,23 +82,24 @@ static int __init com20020isa_probe(struct net_device *dev) * card has just reset and the NORXflag is on until * we tell it to start receiving. */ - BUGMSG(D_INIT_REASONS, "intmask was %02Xh\n", inb(_INTMASK)); - outb(0, _INTMASK); + arc_printk(D_INIT_REASONS, dev, "intmask was %02Xh\n", + arcnet_inb(ioaddr, COM20020_REG_R_STATUS)); + arcnet_outb(0, ioaddr, COM20020_REG_W_INTMASK); airqmask = probe_irq_on(); - outb(NORXflag, _INTMASK); + arcnet_outb(NORXflag, ioaddr, COM20020_REG_W_INTMASK); udelay(1); - outb(0, _INTMASK); + arcnet_outb(0, ioaddr, COM20020_REG_W_INTMASK); dev->irq = probe_irq_off(airqmask); if ((int)dev->irq <= 0) { - BUGMSG(D_INIT_REASONS, "Autoprobe IRQ failed first time\n"); + arc_printk(D_INIT_REASONS, dev, "Autoprobe IRQ failed first time\n"); airqmask = probe_irq_on(); - outb(NORXflag, _INTMASK); + arcnet_outb(NORXflag, ioaddr, COM20020_REG_W_INTMASK); udelay(5); - outb(0, _INTMASK); + arcnet_outb(0, ioaddr, COM20020_REG_W_INTMASK); dev->irq = probe_irq_off(airqmask); if ((int)dev->irq <= 0) { - BUGMSG(D_NORMAL, "Autoprobe IRQ failed.\n"); + arc_printk(D_NORMAL, dev, "Autoprobe IRQ failed.\n"); err = -ENODEV; goto out; } @@ -107,7 +107,9 @@ static int __init com20020isa_probe(struct net_device *dev) } lp->card_name = "ISA COM20020"; - if ((err = com20020_found(dev, 0)) != 0) + + err = com20020_found(dev, 0); + if (err != 0) goto out; return 0; @@ -194,7 +196,7 @@ static int __init com20020isa_setup(char *s) switch (ints[0]) { default: /* ERROR */ - printk("com90xx: Too many arguments.\n"); + pr_info("Too many arguments\n"); case 6: /* Timeout */ timeout = ints[6]; case 5: /* CKP value */ diff --git a/drivers/net/arcnet/com20020-pci.c b/drivers/net/arcnet/com20020-pci.c index 96edc1346124..a12bf83be750 100644 --- a/drivers/net/arcnet/com20020-pci.c +++ b/drivers/net/arcnet/com20020-pci.c @@ -1,7 +1,7 @@ /* * Linux ARCnet driver - COM20020 PCI support * Contemporary Controls PCI20 and SOHARD SH-ARC PCI - * + * * Written 1994-1999 by Avery Pennarun, * based on an ISA version by David Woodhouse. * Written 1999-2000 by Martin Mares <mj@ucw.cz>. @@ -26,6 +26,9 @@ * * ********************** */ + +#define pr_fmt(fmt) "arcnet:" KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/kernel.h> @@ -36,14 +39,11 @@ #include <linux/init.h> #include <linux/interrupt.h> #include <linux/pci.h> -#include <linux/arcdevice.h> -#include <linux/com20020.h> #include <linux/list.h> +#include <linux/io.h> -#include <asm/io.h> - - -#define VERSION "arcnet: COM20020 PCI support\n" +#include "arcdevice.h" +#include "com20020.h" /* Module parameters */ @@ -64,7 +64,8 @@ MODULE_LICENSE("GPL"); static void com20020pci_remove(struct pci_dev *pdev); -static int com20020pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) +static int com20020pci_probe(struct pci_dev *pdev, + const struct pci_device_id *id) { struct com20020_pci_card_info *ci; struct net_device *dev; @@ -86,7 +87,6 @@ static int com20020pci_probe(struct pci_dev *pdev, const struct pci_device_id *i INIT_LIST_HEAD(&priv->list_dev); - for (i = 0; i < ci->devcount; i++) { struct com20020_pci_channel_map *cm = &ci->chan_map_tbl[i]; struct com20020_dev *card; @@ -101,13 +101,13 @@ static int com20020pci_probe(struct pci_dev *pdev, const struct pci_device_id *i lp = netdev_priv(dev); - BUGMSG(D_NORMAL, "%s Controls\n", ci->name); + arc_printk(D_NORMAL, dev, "%s Controls\n", ci->name); ioaddr = pci_resource_start(pdev, cm->bar) + cm->offset; r = devm_request_region(&pdev->dev, ioaddr, cm->size, "com20020-pci"); if (!r) { - pr_err("IO region %xh-%xh already allocated.\n", + pr_err("IO region %xh-%xh already allocated\n", ioaddr, ioaddr + cm->size - 1); ret = -EBUSY; goto out_port; @@ -117,8 +117,8 @@ static int com20020pci_probe(struct pci_dev *pdev, const struct pci_device_id *i * ARCNET controller needs * this access to detect bustype */ - outb(0x00, ioaddr + 1); - inb(ioaddr + 1); + arcnet_outb(0x00, ioaddr, COM20020_REG_W_COMMAND); + arcnet_inb(ioaddr, COM20020_REG_R_DIAGSTAT); dev->base_addr = ioaddr; dev->dev_addr[0] = node; @@ -131,7 +131,7 @@ static int com20020pci_probe(struct pci_dev *pdev, const struct pci_device_id *i lp->timeout = timeout; lp->hw.owner = THIS_MODULE; - if (ASTATUS() == 0xFF) { + if (arcnet_inb(ioaddr, COM20020_REG_R_STATUS) == 0xFF) { pr_err("IO address %Xh is empty!\n", ioaddr); ret = -EIO; goto out_port; @@ -143,10 +143,8 @@ static int com20020pci_probe(struct pci_dev *pdev, const struct pci_device_id *i card = devm_kzalloc(&pdev->dev, sizeof(struct com20020_dev), GFP_KERNEL); - if (!card) { - pr_err("%s out of memory!\n", __func__); + if (!card) return -ENOMEM; - } card->index = i; card->pci_priv = priv; @@ -190,7 +188,11 @@ static struct com20020_pci_card_info card_info_10mbit = { .name = "ARC-PCI", .devcount = 1, .chan_map_tbl = { - { 2, 0x00, 0x08 }, + { + .bar = 2, + .offset = 0x00, + .size = 0x08, + }, }, .flags = ARC_CAN_10MBIT, }; @@ -199,7 +201,11 @@ static struct com20020_pci_card_info card_info_5mbit = { .name = "ARC-PCI", .devcount = 1, .chan_map_tbl = { - { 2, 0x00, 0x08 }, + { + .bar = 2, + .offset = 0x00, + .size = 0x08, + }, }, .flags = ARC_IS_5MBIT, }; @@ -209,7 +215,11 @@ static struct com20020_pci_card_info card_info_sohard = { .devcount = 1, /* SOHARD needs PCI base addr 4 */ .chan_map_tbl = { - {4, 0x00, 0x08}, + { + .bar = 4, + .offset = 0x00, + .size = 0x08 + }, }, .flags = ARC_CAN_10MBIT, }; @@ -218,7 +228,11 @@ static struct com20020_pci_card_info card_info_eae_arc1 = { .name = "EAE PLX-PCI ARC1", .devcount = 1, .chan_map_tbl = { - { 2, 0x00, 0x08 }, + { + .bar = 2, + .offset = 0x00, + .size = 0x08, + }, }, .flags = ARC_CAN_10MBIT, }; @@ -227,8 +241,15 @@ static struct com20020_pci_card_info card_info_eae_ma1 = { .name = "EAE PLX-PCI MA1", .devcount = 2, .chan_map_tbl = { - { 2, 0x00, 0x08 }, - { 2, 0x08, 0x08 } + { + .bar = 2, + .offset = 0x00, + .size = 0x08, + }, { + .bar = 2, + .offset = 0x08, + .size = 0x08, + } }, .flags = ARC_CAN_10MBIT, }; @@ -404,7 +425,8 @@ static struct pci_driver com20020pci_driver = { static int __init com20020pci_init(void) { - BUGLVL(D_NORMAL) printk(VERSION); + if (BUGLVL(D_NORMAL)) + pr_info("%s\n", "COM20020 PCI support"); return pci_register_driver(&com20020pci_driver); } diff --git a/drivers/net/arcnet/com20020.c b/drivers/net/arcnet/com20020.c index 1a8437842fbc..c82f323a8c2b 100644 --- a/drivers/net/arcnet/com20020.c +++ b/drivers/net/arcnet/com20020.c @@ -1,6 +1,6 @@ /* * Linux ARCnet driver - COM20020 chipset support - * + * * Written 1997 by David Woodhouse. * Written 1994-1999 by Avery Pennarun. * Written 1999 by Martin Mares <mj@ucw.cz>. @@ -25,6 +25,9 @@ * * ********************** */ + +#define pr_fmt(fmt) "arcnet:" KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/kernel.h> #include <linux/types.h> @@ -34,17 +37,16 @@ #include <linux/netdevice.h> #include <linux/init.h> #include <linux/interrupt.h> -#include <linux/arcdevice.h> -#include <linux/com20020.h> +#include <linux/io.h> -#include <asm/io.h> +#include "arcdevice.h" +#include "com20020.h" -#define VERSION "arcnet: COM20020 chipset support (by David Woodhouse et al.)\n" - -static char *clockrates[] = -{"10 Mb/s", "Reserved", "5 Mb/s", - "2.5 Mb/s", "1.25Mb/s", "625 Kb/s", "312.5 Kb/s", - "156.25 Kb/s", "Reserved", "Reserved", "Reserved"}; +static const char * const clockrates[] = { + "XXXXXXX", "XXXXXXXX", "XXXXXX", "2.5 Mb/s", + "1.25Mb/s", "625 Kb/s", "312.5 Kb/s", "156.25 Kb/s", + "Reserved", "Reserved", "Reserved" +}; static void com20020_command(struct net_device *dev, int command); static int com20020_status(struct net_device *dev); @@ -63,35 +65,38 @@ static void com20020_copy_from_card(struct net_device *dev, int bufnum, int ioaddr = dev->base_addr, ofs = 512 * bufnum + offset; /* set up the address register */ - outb((ofs >> 8) | RDDATAflag | AUTOINCflag, _ADDR_HI); - outb(ofs & 0xff, _ADDR_LO); + arcnet_outb((ofs >> 8) | RDDATAflag | AUTOINCflag, + ioaddr, COM20020_REG_W_ADDR_HI); + arcnet_outb(ofs & 0xff, ioaddr, COM20020_REG_W_ADDR_LO); /* copy the data */ - TIME("insb", count, insb(_MEMDATA, buf, count)); + TIME(dev, "insb", count, + arcnet_insb(ioaddr, COM20020_REG_RW_MEMDATA, buf, count)); } - static void com20020_copy_to_card(struct net_device *dev, int bufnum, int offset, void *buf, int count) { int ioaddr = dev->base_addr, ofs = 512 * bufnum + offset; /* set up the address register */ - outb((ofs >> 8) | AUTOINCflag, _ADDR_HI); - outb(ofs & 0xff, _ADDR_LO); + arcnet_outb((ofs >> 8) | AUTOINCflag, ioaddr, COM20020_REG_W_ADDR_HI); + arcnet_outb(ofs & 0xff, ioaddr, COM20020_REG_W_ADDR_LO); /* copy the data */ - TIME("outsb", count, outsb(_MEMDATA, buf, count)); + TIME(dev, "outsb", count, + arcnet_outsb(ioaddr, COM20020_REG_RW_MEMDATA, buf, count)); } - /* Reset the card and check some basic stuff during the detection stage. */ int com20020_check(struct net_device *dev) { int ioaddr = dev->base_addr, status; struct arcnet_local *lp = netdev_priv(dev); - ARCRESET0; + arcnet_outb(XTOcfg(3) | RESETcfg, ioaddr, COM20020_REG_W_CONFIG); + udelay(5); + arcnet_outb(XTOcfg(3), ioaddr, COM20020_REG_W_CONFIG); mdelay(RESETtime); lp->setup = lp->clockm ? 0 : (lp->clockp << 1); @@ -101,49 +106,51 @@ int com20020_check(struct net_device *dev) /* Enable P1Mode for backplane mode */ lp->setup = lp->setup | P1MODE; - SET_SUBADR(SUB_SETUP1); - outb(lp->setup, _XREG); + com20020_set_subaddress(lp, ioaddr, SUB_SETUP1); + arcnet_outb(lp->setup, ioaddr, COM20020_REG_W_XREG); + + if (lp->clockm != 0) { + com20020_set_subaddress(lp, ioaddr, SUB_SETUP2); + arcnet_outb(lp->setup2, ioaddr, COM20020_REG_W_XREG); - if (lp->clockm != 0) - { - SET_SUBADR(SUB_SETUP2); - outb(lp->setup2, _XREG); - /* must now write the magic "restart operation" command */ mdelay(1); - outb(0x18, _COMMAND); + arcnet_outb(STARTIOcmd, ioaddr, COM20020_REG_W_COMMAND); } - lp->config = 0x21 | (lp->timeout << 3) | (lp->backplane << 2); + lp->config = TXENcfg | (lp->timeout << 3) | (lp->backplane << 2) | SUB_NODE; /* set node ID to 0x42 (but transmitter is disabled, so it's okay) */ - SETCONF; - outb(0x42, ioaddr + BUS_ALIGN*7); + arcnet_outb(lp->config, ioaddr, COM20020_REG_W_CONFIG); + arcnet_outb(0x42, ioaddr, COM20020_REG_W_XREG); - status = ASTATUS(); + status = arcnet_inb(ioaddr, COM20020_REG_R_STATUS); if ((status & 0x99) != (NORXflag | TXFREEflag | RESETflag)) { - BUGMSG(D_NORMAL, "status invalid (%Xh).\n", status); + arc_printk(D_NORMAL, dev, "status invalid (%Xh).\n", status); return -ENODEV; } - BUGMSG(D_INIT_REASONS, "status after reset: %X\n", status); + arc_printk(D_INIT_REASONS, dev, "status after reset: %X\n", status); /* Enable TX */ - outb(0x39, _CONFIG); - outb(inb(ioaddr + BUS_ALIGN*8), ioaddr + BUS_ALIGN*7); + lp->config |= TXENcfg; + arcnet_outb(lp->config, ioaddr, COM20020_REG_W_CONFIG); + arcnet_outb(arcnet_inb(ioaddr, 8), ioaddr, COM20020_REG_W_XREG); - ACOMMAND(CFLAGScmd | RESETclear | CONFIGclear); - - status = ASTATUS(); - BUGMSG(D_INIT_REASONS, "status after reset acknowledged: %X\n", - status); + arcnet_outb(CFLAGScmd | RESETclear | CONFIGclear, + ioaddr, COM20020_REG_W_COMMAND); + status = arcnet_inb(ioaddr, COM20020_REG_R_STATUS); + arc_printk(D_INIT_REASONS, dev, "status after reset acknowledged: %X\n", + status); /* Read first location of memory */ - outb(0 | RDDATAflag | AUTOINCflag, _ADDR_HI); - outb(0, _ADDR_LO); - - if ((status = inb(_MEMDATA)) != TESTvalue) { - BUGMSG(D_NORMAL, "Signature byte not found (%02Xh != D1h).\n", - status); + arcnet_outb(0 | RDDATAflag | AUTOINCflag, + ioaddr, COM20020_REG_W_ADDR_HI); + arcnet_outb(0, ioaddr, COM20020_REG_W_ADDR_LO); + + status = arcnet_inb(ioaddr, COM20020_REG_RW_MEMDATA); + if (status != TESTvalue) { + arc_printk(D_NORMAL, dev, "Signature byte not found (%02Xh != D1h).\n", + status); return -ENODEV; } return 0; @@ -156,8 +163,8 @@ static int com20020_set_hwaddr(struct net_device *dev, void *addr) struct sockaddr *hwaddr = addr; memcpy(dev->dev_addr, hwaddr->sa_data, 1); - SET_SUBADR(SUB_NODE); - outb(dev->dev_addr[0], _XREG); + com20020_set_subaddress(lp, ioaddr, SUB_NODE); + arcnet_outb(dev->dev_addr[0], ioaddr, COM20020_REG_W_XREG); return 0; } @@ -192,48 +199,54 @@ int com20020_found(struct net_device *dev, int shared) lp->hw.copy_from_card = com20020_copy_from_card; lp->hw.close = com20020_close; + /* FIXME: do this some other way! */ if (!dev->dev_addr[0]) - dev->dev_addr[0] = inb(ioaddr + BUS_ALIGN*8); /* FIXME: do this some other way! */ + dev->dev_addr[0] = arcnet_inb(ioaddr, 8); - SET_SUBADR(SUB_SETUP1); - outb(lp->setup, _XREG); + com20020_set_subaddress(lp, ioaddr, SUB_SETUP1); + arcnet_outb(lp->setup, ioaddr, COM20020_REG_W_XREG); + + if (lp->card_flags & ARC_CAN_10MBIT) { + com20020_set_subaddress(lp, ioaddr, SUB_SETUP2); + arcnet_outb(lp->setup2, ioaddr, COM20020_REG_W_XREG); - if (lp->card_flags & ARC_CAN_10MBIT) - { - SET_SUBADR(SUB_SETUP2); - outb(lp->setup2, _XREG); - /* must now write the magic "restart operation" command */ mdelay(1); - outb(0x18, _COMMAND); + arcnet_outb(STARTIOcmd, ioaddr, COM20020_REG_W_COMMAND); } - lp->config = 0x20 | (lp->timeout << 3) | (lp->backplane << 2) | 1; + lp->config = TXENcfg | (lp->timeout << 3) | (lp->backplane << 2) | SUB_NODE; /* Default 0x38 + register: Node ID */ - SETCONF; - outb(dev->dev_addr[0], _XREG); + arcnet_outb(lp->config, ioaddr, COM20020_REG_W_CONFIG); + arcnet_outb(dev->dev_addr[0], ioaddr, COM20020_REG_W_XREG); /* reserve the irq */ if (request_irq(dev->irq, arcnet_interrupt, shared, "arcnet (COM20020)", dev)) { - BUGMSG(D_NORMAL, "Can't get IRQ %d!\n", dev->irq); + arc_printk(D_NORMAL, dev, "Can't get IRQ %d!\n", dev->irq); return -ENODEV; } dev->base_addr = ioaddr; - BUGMSG(D_NORMAL, "%s: station %02Xh found at %03lXh, IRQ %d.\n", - lp->card_name, dev->dev_addr[0], dev->base_addr, dev->irq); + arc_printk(D_NORMAL, dev, "%s: station %02Xh found at %03lXh, IRQ %d.\n", + lp->card_name, dev->dev_addr[0], dev->base_addr, dev->irq); if (lp->backplane) - BUGMSG(D_NORMAL, "Using backplane mode.\n"); + arc_printk(D_NORMAL, dev, "Using backplane mode.\n"); if (lp->timeout != 3) - BUGMSG(D_NORMAL, "Using extended timeout value of %d.\n", lp->timeout); - - BUGMSG(D_NORMAL, "Using CKP %d - data rate %s.\n", - lp->setup >> 1, - clockrates[3 - ((lp->setup2 & 0xF0) >> 4) + ((lp->setup & 0x0F) >> 1)]); + arc_printk(D_NORMAL, dev, "Using extended timeout value of %d\n", + lp->timeout); + + arc_printk(D_NORMAL, dev, "Using CKP %d - data rate %s\n", + lp->setup >> 1, + clockrates[3 - + ((lp->setup2 & 0xF0) >> 4) + + ((lp->setup & 0x0F) >> 1)]); + /* The clockrates array index looks very fragile. + * It seems like it could have negative indexing. + */ if (register_netdev(dev)) { free_irq(dev->irq, dev); @@ -242,10 +255,8 @@ int com20020_found(struct net_device *dev, int shared) return 0; } - -/* - * Do a hardware reset on the card, and set up necessary registers. - * +/* Do a hardware reset on the card, and set up necessary registers. + * * This should be called as little as possible, because it disrupts the * token on the network (causes a RECON) and requires a significant delay. * @@ -257,65 +268,71 @@ static int com20020_reset(struct net_device *dev, int really_reset) u_int ioaddr = dev->base_addr; u_char inbyte; - BUGMSG(D_DEBUG, "%s: %d: %s: dev: %p, lp: %p, dev->name: %s\n", - __FILE__,__LINE__,__func__,dev,lp,dev->name); - BUGMSG(D_INIT, "Resetting %s (status=%02Xh)\n", - dev->name, ASTATUS()); + arc_printk(D_DEBUG, dev, "%s: %d: %s: dev: %p, lp: %p, dev->name: %s\n", + __FILE__, __LINE__, __func__, dev, lp, dev->name); + arc_printk(D_INIT, dev, "Resetting %s (status=%02Xh)\n", + dev->name, arcnet_inb(ioaddr, COM20020_REG_R_STATUS)); - BUGMSG(D_DEBUG, "%s: %d: %s\n",__FILE__,__LINE__,__func__); + arc_printk(D_DEBUG, dev, "%s: %d: %s\n", __FILE__, __LINE__, __func__); lp->config = TXENcfg | (lp->timeout << 3) | (lp->backplane << 2); /* power-up defaults */ - SETCONF; - BUGMSG(D_DEBUG, "%s: %d: %s\n",__FILE__,__LINE__,__func__); + arcnet_outb(lp->config, ioaddr, COM20020_REG_W_CONFIG); + arc_printk(D_DEBUG, dev, "%s: %d: %s\n", __FILE__, __LINE__, __func__); if (really_reset) { /* reset the card */ - ARCRESET; - mdelay(RESETtime * 2); /* COM20020 seems to be slower sometimes */ + arcnet_outb(lp->config | RESETcfg, ioaddr, COM20020_REG_W_CONFIG); + udelay(5); + arcnet_outb(lp->config, ioaddr, COM20020_REG_W_CONFIG); + mdelay(RESETtime * 2); + /* COM20020 seems to be slower sometimes */ } /* clear flags & end reset */ - BUGMSG(D_DEBUG, "%s: %d: %s\n",__FILE__,__LINE__,__func__); - ACOMMAND(CFLAGScmd | RESETclear | CONFIGclear); + arc_printk(D_DEBUG, dev, "%s: %d: %s\n", __FILE__, __LINE__, __func__); + arcnet_outb(CFLAGScmd | RESETclear | CONFIGclear, + ioaddr, COM20020_REG_W_COMMAND); /* verify that the ARCnet signature byte is present */ - BUGMSG(D_DEBUG, "%s: %d: %s\n",__FILE__,__LINE__,__func__); + arc_printk(D_DEBUG, dev, "%s: %d: %s\n", __FILE__, __LINE__, __func__); com20020_copy_from_card(dev, 0, 0, &inbyte, 1); - BUGMSG(D_DEBUG, "%s: %d: %s\n",__FILE__,__LINE__,__func__); + arc_printk(D_DEBUG, dev, "%s: %d: %s\n", __FILE__, __LINE__, __func__); if (inbyte != TESTvalue) { - BUGMSG(D_DEBUG, "%s: %d: %s\n",__FILE__,__LINE__,__func__); - BUGMSG(D_NORMAL, "reset failed: TESTvalue not present.\n"); + arc_printk(D_DEBUG, dev, "%s: %d: %s\n", + __FILE__, __LINE__, __func__); + arc_printk(D_NORMAL, dev, "reset failed: TESTvalue not present.\n"); return 1; } /* enable extended (512-byte) packets */ - ACOMMAND(CONFIGcmd | EXTconf); - BUGMSG(D_DEBUG, "%s: %d: %s\n",__FILE__,__LINE__,__func__); + arcnet_outb(CONFIGcmd | EXTconf, ioaddr, COM20020_REG_W_COMMAND); + + arc_printk(D_DEBUG, dev, "%s: %d: %s\n", __FILE__, __LINE__, __func__); /* done! return success. */ return 0; } - static void com20020_setmask(struct net_device *dev, int mask) { u_int ioaddr = dev->base_addr; - BUGMSG(D_DURING, "Setting mask to %x at %x\n",mask,ioaddr); - AINTMASK(mask); -} + arc_printk(D_DURING, dev, "Setting mask to %x at %x\n", mask, ioaddr); + arcnet_outb(mask, ioaddr, COM20020_REG_W_INTMASK); +} static void com20020_command(struct net_device *dev, int cmd) { u_int ioaddr = dev->base_addr; - ACOMMAND(cmd); -} + arcnet_outb(cmd, ioaddr, COM20020_REG_W_COMMAND); +} static int com20020_status(struct net_device *dev) { u_int ioaddr = dev->base_addr; - return ASTATUS() + (ADIAGSTATUS()<<8); + return arcnet_inb(ioaddr, COM20020_REG_R_STATUS) + + (arcnet_inb(ioaddr, COM20020_REG_R_DIAGSTAT) << 8); } static void com20020_close(struct net_device *dev) @@ -325,7 +342,7 @@ static void com20020_close(struct net_device *dev) /* disable transmitter */ lp->config &= ~TXENcfg; - SETCONF; + arcnet_outb(lp->config, ioaddr, COM20020_REG_W_CONFIG); } /* Set or clear the multicast filter for this adaptor. @@ -340,20 +357,20 @@ static void com20020_set_mc_list(struct net_device *dev) struct arcnet_local *lp = netdev_priv(dev); int ioaddr = dev->base_addr; - if ((dev->flags & IFF_PROMISC) && (dev->flags & IFF_UP)) { /* Enable promiscuous mode */ + if ((dev->flags & IFF_PROMISC) && (dev->flags & IFF_UP)) { + /* Enable promiscuous mode */ if (!(lp->setup & PROMISCset)) - BUGMSG(D_NORMAL, "Setting promiscuous flag...\n"); - SET_SUBADR(SUB_SETUP1); + arc_printk(D_NORMAL, dev, "Setting promiscuous flag...\n"); + com20020_set_subaddress(lp, ioaddr, SUB_SETUP1); lp->setup |= PROMISCset; - outb(lp->setup, _XREG); - } else + arcnet_outb(lp->setup, ioaddr, COM20020_REG_W_XREG); + } else { /* Disable promiscuous mode, use normal mode */ - { if ((lp->setup & PROMISCset)) - BUGMSG(D_NORMAL, "Resetting promiscuous flag...\n"); - SET_SUBADR(SUB_SETUP1); + arc_printk(D_NORMAL, dev, "Resetting promiscuous flag...\n"); + com20020_set_subaddress(lp, ioaddr, SUB_SETUP1); lp->setup &= ~PROMISCset; - outb(lp->setup, _XREG); + arcnet_outb(lp->setup, ioaddr, COM20020_REG_W_XREG); } } @@ -371,7 +388,8 @@ MODULE_LICENSE("GPL"); static int __init com20020_module_init(void) { - BUGLVL(D_NORMAL) printk(VERSION); + if (BUGLVL(D_NORMAL)) + pr_info("%s\n", "COM20020 chipset support (by David Woodhouse et al.)"); return 0; } diff --git a/include/linux/com20020.h b/drivers/net/arcnet/com20020.h index 85898995b234..22a460f39fb9 100644 --- a/include/linux/com20020.h +++ b/drivers/net/arcnet/com20020.h @@ -1,6 +1,6 @@ /* * Linux ARCnet driver - COM20020 chipset support - function declarations - * + * * Written 1997 by David Woodhouse. * Written 1994-1999 by Avery Pennarun. * Derived from skeleton.c by Donald Becker. @@ -34,13 +34,6 @@ extern const struct net_device_ops com20020_netdev_ops; /* The number of low I/O ports used by the card. */ #define ARCNET_TOTAL_SIZE 8 -/* various register addresses */ -#ifdef CONFIG_SA1100_CT6001 -#define BUS_ALIGN 2 /* 8 bit device on a 16 bit bus - needs padding */ -#else -#define BUS_ALIGN 1 -#endif - #define PLX_PCI_MAX_CARDS 2 struct com20020_pci_channel_map { @@ -71,17 +64,18 @@ struct com20020_dev { int index; }; -#define _INTMASK (ioaddr+BUS_ALIGN*0) /* writable */ -#define _STATUS (ioaddr+BUS_ALIGN*0) /* readable */ -#define _COMMAND (ioaddr+BUS_ALIGN*1) /* standard arcnet commands */ -#define _DIAGSTAT (ioaddr+BUS_ALIGN*1) /* diagnostic status register */ -#define _ADDR_HI (ioaddr+BUS_ALIGN*2) /* control registers for IO-mapped memory */ -#define _ADDR_LO (ioaddr+BUS_ALIGN*3) -#define _MEMDATA (ioaddr+BUS_ALIGN*4) /* data port for IO-mapped memory */ -#define _SUBADR (ioaddr+BUS_ALIGN*5) /* the extended port _XREG refers to */ -#define _CONFIG (ioaddr+BUS_ALIGN*6) /* configuration register */ -#define _XREG (ioaddr+BUS_ALIGN*7) /* extra registers (indexed by _CONFIG - or _SUBADR) */ +#define COM20020_REG_W_INTMASK 0 /* writable */ +#define COM20020_REG_R_STATUS 0 /* readable */ +#define COM20020_REG_W_COMMAND 1 /* standard arcnet commands */ +#define COM20020_REG_R_DIAGSTAT 1 /* diagnostic status */ +#define COM20020_REG_W_ADDR_HI 2 /* control for IO-mapped memory */ +#define COM20020_REG_W_ADDR_LO 3 +#define COM20020_REG_RW_MEMDATA 4 /* data port for IO-mapped memory */ +#define COM20020_REG_W_SUBADR 5 /* the extended port _XREG refers to */ +#define COM20020_REG_W_CONFIG 6 /* configuration */ +#define COM20020_REG_W_XREG 7 /* extra + * (indexed by _CONFIG or _SUBADDR) + */ /* in the ADDR_HI register */ #define RDDATAflag 0x80 /* next access is a read (not a write) */ @@ -92,6 +86,7 @@ struct com20020_dev { /* in the CONFIG register */ #define RESETcfg 0x80 /* put card in reset state */ #define TXENcfg 0x20 /* enable TX */ +#define XTOcfg(x) ((x) << 3) /* extended timeout */ /* in SETUP register */ #define PROMISCset 0x10 /* enable RCV_ALL */ @@ -109,37 +104,15 @@ struct com20020_dev { #define SUB_BUSCTL 5 /* bus control options */ #define SUB_DMACOUNT 6 /* DMA count options */ -#define SET_SUBADR(x) do { \ - if ((x) < 4) \ - { \ - lp->config = (lp->config & ~0x03) | (x); \ - SETCONF; \ - } \ - else \ - { \ - outb(x, _SUBADR); \ - } \ -} while (0) - -#undef ARCRESET -#undef ASTATUS -#undef ACOMMAND -#undef AINTMASK - -#define ARCRESET { outb(lp->config | 0x80, _CONFIG); \ - udelay(5); \ - outb(lp->config , _CONFIG); \ - } -#define ARCRESET0 { outb(0x18 | 0x80, _CONFIG); \ - udelay(5); \ - outb(0x18 , _CONFIG); \ - } - -#define ASTATUS() inb(_STATUS) -#define ADIAGSTATUS() inb(_DIAGSTAT) -#define ACOMMAND(cmd) outb((cmd),_COMMAND) -#define AINTMASK(msk) outb((msk),_INTMASK) - -#define SETCONF outb(lp->config, _CONFIG) +static inline void com20020_set_subaddress(struct arcnet_local *lp, + int ioaddr, int val) +{ + if (val < 4) { + lp->config = (lp->config & ~0x03) | val; + arcnet_outb(lp->config, ioaddr, COM20020_REG_W_CONFIG); + } else { + arcnet_outb(val, ioaddr, COM20020_REG_W_SUBADR); + } +} #endif /* __COM20020_H */ diff --git a/drivers/net/arcnet/com20020_cs.c b/drivers/net/arcnet/com20020_cs.c index 057d9582132a..cf607ffcf358 100644 --- a/drivers/net/arcnet/com20020_cs.c +++ b/drivers/net/arcnet/com20020_cs.c @@ -1,6 +1,6 @@ /* * Linux ARCnet driver - COM20020 PCMCIA support - * + * * Written 1994-1999 by Avery Pennarun, * based on an ISA version by David Woodhouse. * Derived from ibmtr_cs.c by Steve Kipisz (pcmcia-cs 3.1.4) @@ -19,18 +19,21 @@ * Director, National Security Agency. This software may only be used * and distributed according to the terms of the GNU General Public License as * modified by SRC, incorporated herein by reference. - * + * * ********************** * Changes: * Arnaldo Carvalho de Melo <acme@conectiva.com.br> - 08/08/2000 * - reorganize kmallocs in com20020_attach, checking all for failure * and releasing the previous allocations if one fails * ********************** - * + * * For more details, see drivers/net/arcnet.c * * ********************** */ + +#define pr_fmt(fmt) "arcnet:" KBUILD_MODNAME ": " fmt + #include <linux/kernel.h> #include <linux/ptrace.h> #include <linux/slab.h> @@ -39,51 +42,44 @@ #include <linux/delay.h> #include <linux/module.h> #include <linux/netdevice.h> -#include <linux/arcdevice.h> -#include <linux/com20020.h> - +#include <linux/io.h> #include <pcmcia/cistpl.h> #include <pcmcia/ds.h> -#include <asm/io.h> - -#define VERSION "arcnet: COM20020 PCMCIA support loaded.\n" - +#include "arcdevice.h" +#include "com20020.h" static void regdump(struct net_device *dev) { #ifdef DEBUG - int ioaddr = dev->base_addr; - int count; - - netdev_dbg(dev, "register dump:\n"); - for (count = ioaddr; count < ioaddr + 16; count++) - { - if (!(count % 16)) - pr_cont("%04X:", count); - pr_cont(" %02X", inb(count)); - } - pr_cont("\n"); - - netdev_dbg(dev, "buffer0 dump:\n"); + int ioaddr = dev->base_addr; + int count; + + netdev_dbg(dev, "register dump:\n"); + for (count = 0; count < 16; count++) { + if (!(count % 16)) + pr_cont("%04X:", ioaddr + count); + pr_cont(" %02X", arcnet_inb(ioaddr, count)); + } + pr_cont("\n"); + + netdev_dbg(dev, "buffer0 dump:\n"); /* set up the address register */ - count = 0; - outb((count >> 8) | RDDATAflag | AUTOINCflag, _ADDR_HI); - outb(count & 0xff, _ADDR_LO); - - for (count = 0; count < 256+32; count++) - { - if (!(count % 16)) - pr_cont("%04X:", count); - - /* copy the data */ - pr_cont(" %02X", inb(_MEMDATA)); - } - pr_cont("\n"); -#endif -} + count = 0; + arcnet_outb((count >> 8) | RDDATAflag | AUTOINCflag, + ioaddr, com20020_REG_W_ADDR_HI); + arcnet_outb(count & 0xff, ioaddr, COM20020_REG_W_ADDR_LO); + for (count = 0; count < 256 + 32; count++) { + if (!(count % 16)) + pr_cont("%04X:", count); + /* copy the data */ + pr_cont(" %02X", arcnet_inb(ioaddr, COM20020_REG_RW_MEMDATA)); + } + pr_cont("\n"); +#endif +} /*====================================================================*/ @@ -114,169 +110,161 @@ static void com20020_detach(struct pcmcia_device *p_dev); static int com20020_probe(struct pcmcia_device *p_dev) { - struct com20020_dev *info; - struct net_device *dev; - struct arcnet_local *lp; + struct com20020_dev *info; + struct net_device *dev; + struct arcnet_local *lp; - dev_dbg(&p_dev->dev, "com20020_attach()\n"); + dev_dbg(&p_dev->dev, "com20020_attach()\n"); - /* Create new network device */ - info = kzalloc(sizeof(*info), GFP_KERNEL); - if (!info) - goto fail_alloc_info; + /* Create new network device */ + info = kzalloc(sizeof(*info), GFP_KERNEL); + if (!info) + goto fail_alloc_info; - dev = alloc_arcdev(""); - if (!dev) - goto fail_alloc_dev; + dev = alloc_arcdev(""); + if (!dev) + goto fail_alloc_dev; - lp = netdev_priv(dev); - lp->timeout = timeout; - lp->backplane = backplane; - lp->clockp = clockp; - lp->clockm = clockm & 3; - lp->hw.owner = THIS_MODULE; + lp = netdev_priv(dev); + lp->timeout = timeout; + lp->backplane = backplane; + lp->clockp = clockp; + lp->clockm = clockm & 3; + lp->hw.owner = THIS_MODULE; - /* fill in our module parameters as defaults */ - dev->dev_addr[0] = node; + /* fill in our module parameters as defaults */ + dev->dev_addr[0] = node; - p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_8; - p_dev->resource[0]->end = 16; - p_dev->config_flags |= CONF_ENABLE_IRQ; + p_dev->resource[0]->flags |= IO_DATA_PATH_WIDTH_8; + p_dev->resource[0]->end = 16; + p_dev->config_flags |= CONF_ENABLE_IRQ; - info->dev = dev; - p_dev->priv = info; + info->dev = dev; + p_dev->priv = info; - return com20020_config(p_dev); + return com20020_config(p_dev); fail_alloc_dev: - kfree(info); + kfree(info); fail_alloc_info: - return -ENOMEM; + return -ENOMEM; } /* com20020_attach */ static void com20020_detach(struct pcmcia_device *link) { - struct com20020_dev *info = link->priv; - struct net_device *dev = info->dev; + struct com20020_dev *info = link->priv; + struct net_device *dev = info->dev; - dev_dbg(&link->dev, "detach...\n"); + dev_dbg(&link->dev, "detach...\n"); - dev_dbg(&link->dev, "com20020_detach\n"); + dev_dbg(&link->dev, "com20020_detach\n"); - dev_dbg(&link->dev, "unregister...\n"); + dev_dbg(&link->dev, "unregister...\n"); - unregister_netdev(dev); + unregister_netdev(dev); - /* - * this is necessary because we register our IRQ separately - * from card services. - */ - if (dev->irq) - free_irq(dev->irq, dev); + /* this is necessary because we register our IRQ separately + * from card services. + */ + if (dev->irq) + free_irq(dev->irq, dev); - com20020_release(link); + com20020_release(link); - /* Unlink device structure, free bits */ - dev_dbg(&link->dev, "unlinking...\n"); - if (link->priv) - { - dev = info->dev; - if (dev) - { - dev_dbg(&link->dev, "kfree...\n"); - free_netdev(dev); + /* Unlink device structure, free bits */ + dev_dbg(&link->dev, "unlinking...\n"); + if (link->priv) { + dev = info->dev; + if (dev) { + dev_dbg(&link->dev, "kfree...\n"); + free_netdev(dev); + } + dev_dbg(&link->dev, "kfree2...\n"); + kfree(info); } - dev_dbg(&link->dev, "kfree2...\n"); - kfree(info); - } } /* com20020_detach */ static int com20020_config(struct pcmcia_device *link) { - struct arcnet_local *lp; - struct com20020_dev *info; - struct net_device *dev; - int i, ret; - int ioaddr; + struct arcnet_local *lp; + struct com20020_dev *info; + struct net_device *dev; + int i, ret; + int ioaddr; + + info = link->priv; + dev = info->dev; + + dev_dbg(&link->dev, "config...\n"); + + dev_dbg(&link->dev, "com20020_config\n"); - info = link->priv; - dev = info->dev; + dev_dbg(&link->dev, "baseport1 is %Xh\n", + (unsigned int)link->resource[0]->start); - dev_dbg(&link->dev, "config...\n"); + i = -ENODEV; + link->io_lines = 16; - dev_dbg(&link->dev, "com20020_config\n"); + if (!link->resource[0]->start) { + for (ioaddr = 0x100; ioaddr < 0x400; ioaddr += 0x10) { + link->resource[0]->start = ioaddr; + i = pcmcia_request_io(link); + if (i == 0) + break; + } + } else { + i = pcmcia_request_io(link); + } - dev_dbg(&link->dev, "baseport1 is %Xh\n", - (unsigned int) link->resource[0]->start); + if (i != 0) { + dev_dbg(&link->dev, "requestIO failed totally!\n"); + goto failed; + } - i = -ENODEV; - link->io_lines = 16; + ioaddr = dev->base_addr = link->resource[0]->start; + dev_dbg(&link->dev, "got ioaddr %Xh\n", ioaddr); - if (!link->resource[0]->start) - { - for (ioaddr = 0x100; ioaddr < 0x400; ioaddr += 0x10) - { - link->resource[0]->start = ioaddr; - i = pcmcia_request_io(link); - if (i == 0) - break; + dev_dbg(&link->dev, "request IRQ %d\n", + link->irq); + if (!link->irq) { + dev_dbg(&link->dev, "requestIRQ failed totally!\n"); + goto failed; } - } - else - i = pcmcia_request_io(link); - - if (i != 0) - { - dev_dbg(&link->dev, "requestIO failed totally!\n"); - goto failed; - } - - ioaddr = dev->base_addr = link->resource[0]->start; - dev_dbg(&link->dev, "got ioaddr %Xh\n", ioaddr); - - dev_dbg(&link->dev, "request IRQ %d\n", - link->irq); - if (!link->irq) - { - dev_dbg(&link->dev, "requestIRQ failed totally!\n"); - goto failed; - } - - dev->irq = link->irq; - - ret = pcmcia_enable_device(link); - if (ret) - goto failed; - - if (com20020_check(dev)) - { - regdump(dev); - goto failed; - } - - lp = netdev_priv(dev); - lp->card_name = "PCMCIA COM20020"; - lp->card_flags = ARC_CAN_10MBIT; /* pretend all of them can 10Mbit */ - - SET_NETDEV_DEV(dev, &link->dev); - - i = com20020_found(dev, 0); /* calls register_netdev */ - - if (i != 0) { - dev_notice(&link->dev, - "com20020_found() failed\n"); - goto failed; - } - - netdev_dbg(dev, "port %#3lx, irq %d\n", - dev->base_addr, dev->irq); - return 0; + + dev->irq = link->irq; + + ret = pcmcia_enable_device(link); + if (ret) + goto failed; + + if (com20020_check(dev)) { + regdump(dev); + goto failed; + } + + lp = netdev_priv(dev); + lp->card_name = "PCMCIA COM20020"; + lp->card_flags = ARC_CAN_10MBIT; /* pretend all of them can 10Mbit */ + + SET_NETDEV_DEV(dev, &link->dev); + + i = com20020_found(dev, 0); /* calls register_netdev */ + + if (i != 0) { + dev_notice(&link->dev, + "com20020_found() failed\n"); + goto failed; + } + + netdev_dbg(dev, "port %#3lx, irq %d\n", + dev->base_addr, dev->irq); + return 0; failed: - dev_dbg(&link->dev, "com20020_config failed...\n"); - com20020_release(link); - return -ENODEV; + dev_dbg(&link->dev, "com20020_config failed...\n"); + com20020_release(link); + return -ENODEV; } /* com20020_config */ static void com20020_release(struct pcmcia_device *link) @@ -304,7 +292,10 @@ static int com20020_resume(struct pcmcia_device *link) if (link->open) { int ioaddr = dev->base_addr; struct arcnet_local *lp = netdev_priv(dev); - ARCRESET; + + arcnet_outb(lp->config | 0x80, ioaddr, COM20020_REG_W_CONFIG); + udelay(5); + arcnet_outb(lp->config, ioaddr, COM20020_REG_W_CONFIG); } return 0; @@ -312,9 +303,9 @@ static int com20020_resume(struct pcmcia_device *link) static const struct pcmcia_device_id com20020_ids[] = { PCMCIA_DEVICE_PROD_ID12("Contemporary Control Systems, Inc.", - "PCM20 Arcnet Adapter", 0x59991666, 0x95dfffaf), + "PCM20 Arcnet Adapter", 0x59991666, 0x95dfffaf), PCMCIA_DEVICE_PROD_ID12("SoHard AG", - "SH ARC PCMCIA", 0xf8991729, 0x69dff0c7), + "SH ARC PCMCIA", 0xf8991729, 0x69dff0c7), PCMCIA_DEVICE_NULL }; MODULE_DEVICE_TABLE(pcmcia, com20020_ids); diff --git a/drivers/net/arcnet/com9026.h b/drivers/net/arcnet/com9026.h new file mode 100644 index 000000000000..efcaf6707214 --- /dev/null +++ b/drivers/net/arcnet/com9026.h @@ -0,0 +1,17 @@ +#ifndef __COM9026_H +#define __COM9026_H + +/* COM 9026 controller chip --> ARCnet register addresses */ + +#define COM9026_REG_W_INTMASK 0 /* writable */ +#define COM9026_REG_R_STATUS 0 /* readable */ +#define COM9026_REG_W_COMMAND 1 /* writable, returns random vals on read (?) */ +#define COM9026_REG_RW_CONFIG 2 /* Configuration register */ +#define COM9026_REG_R_RESET 8 /* software reset (on read) */ +#define COM9026_REG_RW_MEMDATA 12 /* Data port for IO-mapped memory */ +#define COM9026_REG_W_ADDR_LO 14 /* Control registers for said */ +#define COM9026_REG_W_ADDR_HI 15 + +#define COM9026_REG_R_STATION 1 /* Station ID */ + +#endif diff --git a/drivers/net/arcnet/com90io.c b/drivers/net/arcnet/com90io.c index 487d780ebbdf..b57863df5bf5 100644 --- a/drivers/net/arcnet/com90io.c +++ b/drivers/net/arcnet/com90io.c @@ -1,6 +1,6 @@ /* * Linux ARCnet driver - COM90xx chipset (IO-mapped buffers) - * + * * Written 1997 by David Woodhouse. * Written 1994-1999 by Avery Pennarun. * Written 1999-2000 by Martin Mares <mj@ucw.cz>. @@ -25,6 +25,9 @@ * * ********************** */ + +#define pr_fmt(fmt) "arcnet:" KBUILD_MODNAME ": " fmt + #include <linux/kernel.h> #include <linux/module.h> #include <linux/moduleparam.h> @@ -34,12 +37,10 @@ #include <linux/bootmem.h> #include <linux/init.h> #include <linux/interrupt.h> -#include <asm/io.h> -#include <linux/arcdevice.h> - - -#define VERSION "arcnet: COM90xx IO-mapped mode support (by David Woodhouse et el.)\n" +#include <linux/io.h> +#include "arcdevice.h" +#include "com9026.h" /* Internal function declarations */ @@ -50,35 +51,14 @@ static void com90io_setmask(struct net_device *dev, int mask); static int com90io_reset(struct net_device *dev, int really_reset); static void com90io_copy_to_card(struct net_device *dev, int bufnum, int offset, void *buf, int count); -static void com90io_copy_from_card(struct net_device *dev, int bufnum, int offset, - void *buf, int count); - +static void com90io_copy_from_card(struct net_device *dev, int bufnum, + int offset, void *buf, int count); /* Handy defines for ARCnet specific stuff */ /* The number of low I/O ports used by the card. */ #define ARCNET_TOTAL_SIZE 16 -/* COM 9026 controller chip --> ARCnet register addresses */ -#define _INTMASK (ioaddr+0) /* writable */ -#define _STATUS (ioaddr+0) /* readable */ -#define _COMMAND (ioaddr+1) /* writable, returns random vals on read (?) */ -#define _RESET (ioaddr+8) /* software reset (on read) */ -#define _MEMDATA (ioaddr+12) /* Data port for IO-mapped memory */ -#define _ADDR_HI (ioaddr+15) /* Control registers for said */ -#define _ADDR_LO (ioaddr+14) -#define _CONFIG (ioaddr+2) /* Configuration register */ - -#undef ASTATUS -#undef ACOMMAND -#undef AINTMASK - -#define ASTATUS() inb(_STATUS) -#define ACOMMAND(cmd) outb((cmd),_COMMAND) -#define AINTMASK(msk) outb((msk),_INTMASK) -#define SETCONF() outb((lp->config),_CONFIG) - - /**************************************************************************** * * * IO-mapped operation routines * @@ -92,58 +72,59 @@ static u_char get_buffer_byte(struct net_device *dev, unsigned offset) { int ioaddr = dev->base_addr; - outb(offset >> 8, _ADDR_HI); - outb(offset & 0xff, _ADDR_LO); + arcnet_outb(offset >> 8, ioaddr, COM9026_REG_W_ADDR_HI); + arcnet_outb(offset & 0xff, ioaddr, COM9026_REG_W_ADDR_LO); - return inb(_MEMDATA); + return arcnet_inb(ioaddr, COM9026_REG_RW_MEMDATA); } #ifdef ONE_AT_A_TIME_TX -static void put_buffer_byte(struct net_device *dev, unsigned offset, u_char datum) +static void put_buffer_byte(struct net_device *dev, unsigned offset, + u_char datum) { int ioaddr = dev->base_addr; - outb(offset >> 8, _ADDR_HI); - outb(offset & 0xff, _ADDR_LO); + arcnet_outb(offset >> 8, ioaddr, COM9026_REG_W_ADDR_HI); + arcnet_outb(offset & 0xff, ioaddr, COM9026_REG_W_ADDR_LO); - outb(datum, _MEMDATA); + arcnet_outb(datum, ioaddr, COM9026_REG_RW_MEMDATA); } #endif - -static void get_whole_buffer(struct net_device *dev, unsigned offset, unsigned length, char *dest) +static void get_whole_buffer(struct net_device *dev, unsigned offset, + unsigned length, char *dest) { int ioaddr = dev->base_addr; - outb((offset >> 8) | AUTOINCflag, _ADDR_HI); - outb(offset & 0xff, _ADDR_LO); + arcnet_outb((offset >> 8) | AUTOINCflag, ioaddr, COM9026_REG_W_ADDR_HI); + arcnet_outb(offset & 0xff, ioaddr, COM9026_REG_W_ADDR_LO); while (length--) #ifdef ONE_AT_A_TIME_RX *(dest++) = get_buffer_byte(dev, offset++); #else - *(dest++) = inb(_MEMDATA); + *(dest++) = arcnet_inb(ioaddr, COM9026_REG_RW_MEMDATA); #endif } -static void put_whole_buffer(struct net_device *dev, unsigned offset, unsigned length, char *dest) +static void put_whole_buffer(struct net_device *dev, unsigned offset, + unsigned length, char *dest) { int ioaddr = dev->base_addr; - outb((offset >> 8) | AUTOINCflag, _ADDR_HI); - outb(offset & 0xff, _ADDR_LO); + arcnet_outb((offset >> 8) | AUTOINCflag, ioaddr, COM9026_REG_W_ADDR_HI); + arcnet_outb(offset & 0xff, ioaddr,COM9026_REG_W_ADDR_LO); while (length--) #ifdef ONE_AT_A_TIME_TX put_buffer_byte(dev, offset++, *(dest++)); #else - outb(*(dest++), _MEMDATA); + arcnet_outb(*(dest++), ioaddr, COM9026_REG_RW_MEMDATA); #endif } -/* - * We cannot probe for an IO mapped card either, although we can check that +/* We cannot probe for an IO mapped card either, although we can check that * it's where we were told it was, and even autoirq */ static int __init com90io_probe(struct net_device *dev) @@ -151,71 +132,78 @@ static int __init com90io_probe(struct net_device *dev) int ioaddr = dev->base_addr, status; unsigned long airqmask; - BUGLVL(D_NORMAL) printk(VERSION); - BUGLVL(D_NORMAL) printk("E-mail me if you actually test this driver, please!\n"); + if (BUGLVL(D_NORMAL)) { + pr_info("%s\n", "COM90xx IO-mapped mode support (by David Woodhouse et el.)"); + pr_info("E-mail me if you actually test this driver, please!\n"); + } if (!ioaddr) { - BUGMSG(D_NORMAL, "No autoprobe for IO mapped cards; you " - "must specify the base address!\n"); + arc_printk(D_NORMAL, dev, "No autoprobe for IO mapped cards; you must specify the base address!\n"); return -ENODEV; } if (!request_region(ioaddr, ARCNET_TOTAL_SIZE, "com90io probe")) { - BUGMSG(D_INIT_REASONS, "IO request_region %x-%x failed.\n", - ioaddr, ioaddr + ARCNET_TOTAL_SIZE - 1); + arc_printk(D_INIT_REASONS, dev, "IO request_region %x-%x failed\n", + ioaddr, ioaddr + ARCNET_TOTAL_SIZE - 1); return -ENXIO; } - if (ASTATUS() == 0xFF) { - BUGMSG(D_INIT_REASONS, "IO address %x empty\n", ioaddr); + if (arcnet_inb(ioaddr, COM9026_REG_R_STATUS) == 0xFF) { + arc_printk(D_INIT_REASONS, dev, "IO address %x empty\n", + ioaddr); goto err_out; } - inb(_RESET); + arcnet_inb(ioaddr, COM9026_REG_R_RESET); mdelay(RESETtime); - status = ASTATUS(); + status = arcnet_inb(ioaddr, COM9026_REG_R_STATUS); if ((status & 0x9D) != (NORXflag | RECONflag | TXFREEflag | RESETflag)) { - BUGMSG(D_INIT_REASONS, "Status invalid (%Xh).\n", status); + arc_printk(D_INIT_REASONS, dev, "Status invalid (%Xh)\n", + status); goto err_out; } - BUGMSG(D_INIT_REASONS, "Status after reset: %X\n", status); + arc_printk(D_INIT_REASONS, dev, "Status after reset: %X\n", status); - ACOMMAND(CFLAGScmd | RESETclear | CONFIGclear); + arcnet_outb(CFLAGScmd | RESETclear | CONFIGclear, + ioaddr, COM9026_REG_W_COMMAND); - BUGMSG(D_INIT_REASONS, "Status after reset acknowledged: %X\n", status); + arc_printk(D_INIT_REASONS, dev, "Status after reset acknowledged: %X\n", + status); - status = ASTATUS(); + status = arcnet_inb(ioaddr, COM9026_REG_R_STATUS); if (status & RESETflag) { - BUGMSG(D_INIT_REASONS, "Eternal reset (status=%Xh)\n", status); + arc_printk(D_INIT_REASONS, dev, "Eternal reset (status=%Xh)\n", + status); goto err_out; } - outb((0x16 | IOMAPflag) & ~ENABLE16flag, _CONFIG); + arcnet_outb((0x16 | IOMAPflag) & ~ENABLE16flag, + ioaddr, COM9026_REG_RW_CONFIG); /* Read first loc'n of memory */ - outb(AUTOINCflag, _ADDR_HI); - outb(0, _ADDR_LO); + arcnet_outb(AUTOINCflag, ioaddr, COM9026_REG_W_ADDR_HI); + arcnet_outb(0, ioaddr, COM9026_REG_W_ADDR_LO); - if ((status = inb(_MEMDATA)) != 0xd1) { - BUGMSG(D_INIT_REASONS, "Signature byte not found" - " (%Xh instead).\n", status); + status = arcnet_inb(ioaddr, COM9026_REG_RW_MEMDATA); + if (status != 0xd1) { + arc_printk(D_INIT_REASONS, dev, "Signature byte not found (%Xh instead).\n", + status); goto err_out; } if (!dev->irq) { - /* - * if we do this, we're sure to get an IRQ since the + /* if we do this, we're sure to get an IRQ since the * card has just reset and the NORXflag is on until * we tell it to start receiving. */ airqmask = probe_irq_on(); - outb(NORXflag, _INTMASK); + arcnet_outb(NORXflag, ioaddr, COM9026_REG_W_INTMASK); udelay(1); - outb(0, _INTMASK); + arcnet_outb(0, ioaddr, COM9026_REG_W_INTMASK); dev->irq = probe_irq_off(airqmask); if ((int)dev->irq <= 0) { - BUGMSG(D_INIT_REASONS, "Autoprobe IRQ failed\n"); + arc_printk(D_INIT_REASONS, dev, "Autoprobe IRQ failed\n"); goto err_out; } } @@ -227,7 +215,6 @@ err_out: return -ENODEV; } - /* Set up the struct net_device associated with this card. Called after * probing succeeds. */ @@ -238,12 +225,14 @@ static int __init com90io_found(struct net_device *dev) int err; /* Reserve the irq */ - if (request_irq(dev->irq, arcnet_interrupt, 0, "arcnet (COM90xx-IO)", dev)) { - BUGMSG(D_NORMAL, "Can't get IRQ %d!\n", dev->irq); + if (request_irq(dev->irq, arcnet_interrupt, 0, + "arcnet (COM90xx-IO)", dev)) { + arc_printk(D_NORMAL, dev, "Can't get IRQ %d!\n", dev->irq); return -ENODEV; } /* Reserve the I/O region */ - if (!request_region(dev->base_addr, ARCNET_TOTAL_SIZE, "arcnet (COM90xx-IO)")) { + if (!request_region(dev->base_addr, ARCNET_TOTAL_SIZE, + "arcnet (COM90xx-IO)")) { free_irq(dev->irq, dev); return -EBUSY; } @@ -259,7 +248,7 @@ static int __init com90io_found(struct net_device *dev) lp->hw.copy_from_card = com90io_copy_from_card; lp->config = (0x16 | IOMAPflag) & ~ENABLE16flag; - SETCONF(); + arcnet_outb(lp->config, ioaddr, COM9026_REG_RW_CONFIG); /* get and check the station ID from offset 1 in shmem */ @@ -267,21 +256,20 @@ static int __init com90io_found(struct net_device *dev) err = register_netdev(dev); if (err) { - outb((inb(_CONFIG) & ~IOMAPflag), _CONFIG); + arcnet_outb(arcnet_inb(ioaddr, COM9026_REG_RW_CONFIG) & ~IOMAPflag, + ioaddr, COM9026_REG_RW_CONFIG); free_irq(dev->irq, dev); release_region(dev->base_addr, ARCNET_TOTAL_SIZE); return err; } - BUGMSG(D_NORMAL, "COM90IO: station %02Xh found at %03lXh, IRQ %d.\n", - dev->dev_addr[0], dev->base_addr, dev->irq); + arc_printk(D_NORMAL, dev, "COM90IO: station %02Xh found at %03lXh, IRQ %d.\n", + dev->dev_addr[0], dev->base_addr, dev->irq); return 0; } - -/* - * Do a hardware reset on the card, and set up necessary registers. +/* Do a hardware reset on the card, and set up necessary registers. * * This should be called as little as possible, because it disrupts the * token on the network (causes a RECON) and requires a significant delay. @@ -293,67 +281,66 @@ static int com90io_reset(struct net_device *dev, int really_reset) struct arcnet_local *lp = netdev_priv(dev); short ioaddr = dev->base_addr; - BUGMSG(D_INIT, "Resetting %s (status=%02Xh)\n", dev->name, ASTATUS()); + arc_printk(D_INIT, dev, "Resetting %s (status=%02Xh)\n", + dev->name, arcnet_inb(ioaddr, COM9026_REG_R_STATUS)); if (really_reset) { /* reset the card */ - inb(_RESET); + arcnet_inb(ioaddr, COM9026_REG_R_RESET); mdelay(RESETtime); } /* Set the thing to IO-mapped, 8-bit mode */ lp->config = (0x1C | IOMAPflag) & ~ENABLE16flag; - SETCONF(); + arcnet_outb(lp->config, ioaddr, COM9026_REG_RW_CONFIG); - ACOMMAND(CFLAGScmd | RESETclear); /* clear flags & end reset */ - ACOMMAND(CFLAGScmd | CONFIGclear); + arcnet_outb(CFLAGScmd | RESETclear, ioaddr, COM9026_REG_W_COMMAND); + /* clear flags & end reset */ + arcnet_outb(CFLAGScmd | CONFIGclear, ioaddr, COM9026_REG_W_COMMAND); /* verify that the ARCnet signature byte is present */ if (get_buffer_byte(dev, 0) != TESTvalue) { - BUGMSG(D_NORMAL, "reset failed: TESTvalue not present.\n"); + arc_printk(D_NORMAL, dev, "reset failed: TESTvalue not present.\n"); return 1; } /* enable extended (512-byte) packets */ - ACOMMAND(CONFIGcmd | EXTconf); - + arcnet_outb(CONFIGcmd | EXTconf, ioaddr, COM9026_REG_W_COMMAND); /* done! return success. */ return 0; } - static void com90io_command(struct net_device *dev, int cmd) { short ioaddr = dev->base_addr; - ACOMMAND(cmd); + arcnet_outb(cmd, ioaddr, COM9026_REG_W_COMMAND); } - static int com90io_status(struct net_device *dev) { short ioaddr = dev->base_addr; - return ASTATUS(); + return arcnet_inb(ioaddr, COM9026_REG_R_STATUS); } - static void com90io_setmask(struct net_device *dev, int mask) { short ioaddr = dev->base_addr; - AINTMASK(mask); + arcnet_outb(mask, ioaddr, COM9026_REG_W_INTMASK); } -static void com90io_copy_to_card(struct net_device *dev, int bufnum, int offset, - void *buf, int count) +static void com90io_copy_to_card(struct net_device *dev, int bufnum, + int offset, void *buf, int count) { - TIME("put_whole_buffer", count, put_whole_buffer(dev, bufnum * 512 + offset, count, buf)); + TIME(dev, "put_whole_buffer", count, + put_whole_buffer(dev, bufnum * 512 + offset, count, buf)); } - -static void com90io_copy_from_card(struct net_device *dev, int bufnum, int offset, - void *buf, int count) +static void com90io_copy_from_card(struct net_device *dev, int bufnum, + int offset, void *buf, int count) { - TIME("get_whole_buffer", count, get_whole_buffer(dev, bufnum * 512 + offset, count, buf)); + TIME(dev, "get_whole_buffer", count, + get_whole_buffer(dev, bufnum * 512 + offset, count, buf)); } static int io; /* use the insmod io= irq= shmem= options */ @@ -369,12 +356,13 @@ MODULE_LICENSE("GPL"); static int __init com90io_setup(char *s) { int ints[4]; + s = get_options(s, 4, ints); if (!ints[0]) return 0; switch (ints[0]) { default: /* ERROR */ - printk("com90io: Too many arguments.\n"); + pr_err("Too many arguments\n"); case 2: /* IRQ */ irq = ints[2]; case 1: /* IO address */ @@ -421,8 +409,11 @@ static void __exit com90io_exit(void) unregister_netdev(dev); - /* Set the thing back to MMAP mode, in case the old driver is loaded later */ - outb((inb(_CONFIG) & ~IOMAPflag), _CONFIG); + /* In case the old driver is loaded later, + * set the thing back to MMAP mode + */ + arcnet_outb(arcnet_inb(ioaddr, COM9026_REG_RW_CONFIG) & ~IOMAPflag, + ioaddr, COM9026_REG_RW_CONFIG); free_irq(dev->irq, dev); release_region(dev->base_addr, ARCNET_TOTAL_SIZE); diff --git a/drivers/net/arcnet/com90xx.c b/drivers/net/arcnet/com90xx.c index b80fbe40aa0e..0d9b45ff1bb2 100644 --- a/drivers/net/arcnet/com90xx.c +++ b/drivers/net/arcnet/com90xx.c @@ -1,6 +1,6 @@ /* * Linux ARCnet driver - COM90xx chipset (memory-mapped buffers) - * + * * Written 1994-1999 by Avery Pennarun. * Written 1999 by Martin Mares <mj@ucw.cz>. * Derived from skeleton.c by Donald Becker. @@ -24,6 +24,9 @@ * * ********************** */ + +#define pr_fmt(fmt) "arcnet:" KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/init.h> @@ -32,12 +35,10 @@ #include <linux/delay.h> #include <linux/netdevice.h> #include <linux/slab.h> -#include <asm/io.h> -#include <linux/arcdevice.h> - - -#define VERSION "arcnet: COM90xx chipset support\n" +#include <linux/io.h> +#include "arcdevice.h" +#include "com9026.h" /* Define this to speed up the autoprobe by assuming if only one io port and * shmem are left in the list at Stage 5, they must correspond to each @@ -53,7 +54,6 @@ */ #undef FAST_PROBE - /* Internal function declarations */ static int com90xx_found(int ioaddr, int airq, u_long shmem, void __iomem *); static void com90xx_command(struct net_device *dev, int command); @@ -62,8 +62,8 @@ static void com90xx_setmask(struct net_device *dev, int mask); static int com90xx_reset(struct net_device *dev, int really_reset); static void com90xx_copy_to_card(struct net_device *dev, int bufnum, int offset, void *buf, int count); -static void com90xx_copy_from_card(struct net_device *dev, int bufnum, int offset, - void *buf, int count); +static void com90xx_copy_from_card(struct net_device *dev, int bufnum, + int offset, void *buf, int count); /* Known ARCnet cards */ @@ -77,26 +77,7 @@ static int numcards; /* Amount of I/O memory used by the card */ #define BUFFER_SIZE (512) -#define MIRROR_SIZE (BUFFER_SIZE*4) - -/* COM 9026 controller chip --> ARCnet register addresses */ -#define _INTMASK (ioaddr+0) /* writable */ -#define _STATUS (ioaddr+0) /* readable */ -#define _COMMAND (ioaddr+1) /* writable, returns random vals on read (?) */ -#define _CONFIG (ioaddr+2) /* Configuration register */ -#define _RESET (ioaddr+8) /* software reset (on read) */ -#define _MEMDATA (ioaddr+12) /* Data port for IO-mapped memory */ -#define _ADDR_HI (ioaddr+15) /* Control registers for said */ -#define _ADDR_LO (ioaddr+14) - -#undef ASTATUS -#undef ACOMMAND -#undef AINTMASK - -#define ASTATUS() inb(_STATUS) -#define ACOMMAND(cmd) outb((cmd),_COMMAND) -#define AINTMASK(msk) outb((msk),_INTMASK) - +#define MIRROR_SIZE (BUFFER_SIZE * 4) static int com90xx_skip_probe __initdata = 0; @@ -116,8 +97,7 @@ static void __init com90xx_probe(void) { int count, status, ioaddr, numprint, airq, openparen = 0; unsigned long airqmask; - int ports[(0x3f0 - 0x200) / 16 + 1] = - {0}; + int ports[(0x3f0 - 0x200) / 16 + 1] = { 0 }; unsigned long *shmems; void __iomem **iomem; int numports, numshmems, *port; @@ -127,18 +107,19 @@ static void __init com90xx_probe(void) if (!io && !irq && !shmem && !*device && com90xx_skip_probe) return; - shmems = kzalloc(((0x100000-0xa0000) / 0x800) * sizeof(unsigned long), + shmems = kzalloc(((0x100000 - 0xa0000) / 0x800) * sizeof(unsigned long), GFP_KERNEL); if (!shmems) return; - iomem = kzalloc(((0x100000-0xa0000) / 0x800) * sizeof(void __iomem *), - GFP_KERNEL); + iomem = kzalloc(((0x100000 - 0xa0000) / 0x800) * sizeof(void __iomem *), + GFP_KERNEL); if (!iomem) { kfree(shmems); return; } - BUGLVL(D_NORMAL) printk(VERSION); + if (BUGLVL(D_NORMAL)) + pr_info("%s\n", "COM90xx chipset support"); /* set up the arrays where we'll store the possible probe addresses */ numports = numshmems = 0; @@ -161,38 +142,43 @@ static void __init com90xx_probe(void) numprint++; numprint %= 8; if (!numprint) { - BUGMSG2(D_INIT, "\n"); - BUGMSG2(D_INIT, "S1: "); + arc_cont(D_INIT, "\n"); + arc_cont(D_INIT, "S1: "); } - BUGMSG2(D_INIT, "%Xh ", *port); + arc_cont(D_INIT, "%Xh ", *port); ioaddr = *port; - if (!request_region(*port, ARCNET_TOTAL_SIZE, "arcnet (90xx)")) { - BUGMSG2(D_INIT_REASONS, "(request_region)\n"); - BUGMSG2(D_INIT_REASONS, "S1: "); - BUGLVL(D_INIT_REASONS) numprint = 0; + if (!request_region(*port, ARCNET_TOTAL_SIZE, + "arcnet (90xx)")) { + arc_cont(D_INIT_REASONS, "(request_region)\n"); + arc_cont(D_INIT_REASONS, "S1: "); + if (BUGLVL(D_INIT_REASONS)) + numprint = 0; *port-- = ports[--numports]; continue; } - if (ASTATUS() == 0xFF) { - BUGMSG2(D_INIT_REASONS, "(empty)\n"); - BUGMSG2(D_INIT_REASONS, "S1: "); - BUGLVL(D_INIT_REASONS) numprint = 0; + if (arcnet_inb(ioaddr, COM9026_REG_R_STATUS) == 0xFF) { + arc_cont(D_INIT_REASONS, "(empty)\n"); + arc_cont(D_INIT_REASONS, "S1: "); + if (BUGLVL(D_INIT_REASONS)) + numprint = 0; release_region(*port, ARCNET_TOTAL_SIZE); *port-- = ports[--numports]; continue; } - inb(_RESET); /* begin resetting card */ + /* begin resetting card */ + arcnet_inb(ioaddr, COM9026_REG_R_RESET); - BUGMSG2(D_INIT_REASONS, "\n"); - BUGMSG2(D_INIT_REASONS, "S1: "); - BUGLVL(D_INIT_REASONS) numprint = 0; + arc_cont(D_INIT_REASONS, "\n"); + arc_cont(D_INIT_REASONS, "S1: "); + if (BUGLVL(D_INIT_REASONS)) + numprint = 0; } - BUGMSG2(D_INIT, "\n"); + arc_cont(D_INIT, "\n"); if (!numports) { - BUGMSG2(D_NORMAL, "S1: No ARCnet cards found.\n"); + arc_cont(D_NORMAL, "S1: No ARCnet cards found.\n"); kfree(shmems); kfree(iomem); return; @@ -206,12 +192,12 @@ static void __init com90xx_probe(void) numprint++; numprint %= 8; if (!numprint) { - BUGMSG2(D_INIT, "\n"); - BUGMSG2(D_INIT, "S2: "); + arc_cont(D_INIT, "\n"); + arc_cont(D_INIT, "S2: "); } - BUGMSG2(D_INIT, "%Xh ", *port); + arc_cont(D_INIT, "%Xh ", *port); } - BUGMSG2(D_INIT, "\n"); + arc_cont(D_INIT, "\n"); mdelay(RESETtime); /* Stage 3: abandon any shmem addresses that don't have the signature @@ -224,29 +210,33 @@ static void __init com90xx_probe(void) numprint++; numprint %= 8; if (!numprint) { - BUGMSG2(D_INIT, "\n"); - BUGMSG2(D_INIT, "S3: "); + arc_cont(D_INIT, "\n"); + arc_cont(D_INIT, "S3: "); } - BUGMSG2(D_INIT, "%lXh ", *p); + arc_cont(D_INIT, "%lXh ", *p); if (!request_mem_region(*p, MIRROR_SIZE, "arcnet (90xx)")) { - BUGMSG2(D_INIT_REASONS, "(request_mem_region)\n"); - BUGMSG2(D_INIT_REASONS, "Stage 3: "); - BUGLVL(D_INIT_REASONS) numprint = 0; + arc_cont(D_INIT_REASONS, "(request_mem_region)\n"); + arc_cont(D_INIT_REASONS, "Stage 3: "); + if (BUGLVL(D_INIT_REASONS)) + numprint = 0; goto out; } base = ioremap(*p, MIRROR_SIZE); if (!base) { - BUGMSG2(D_INIT_REASONS, "(ioremap)\n"); - BUGMSG2(D_INIT_REASONS, "Stage 3: "); - BUGLVL(D_INIT_REASONS) numprint = 0; + arc_cont(D_INIT_REASONS, "(ioremap)\n"); + arc_cont(D_INIT_REASONS, "Stage 3: "); + if (BUGLVL(D_INIT_REASONS)) + numprint = 0; goto out1; } - if (readb(base) != TESTvalue) { - BUGMSG2(D_INIT_REASONS, "(%02Xh != %02Xh)\n", - readb(base), TESTvalue); - BUGMSG2(D_INIT_REASONS, "S3: "); - BUGLVL(D_INIT_REASONS) numprint = 0; + if (arcnet_readb(base, COM9026_REG_R_STATUS) != TESTvalue) { + arc_cont(D_INIT_REASONS, "(%02Xh != %02Xh)\n", + arcnet_readb(base, COM9026_REG_R_STATUS), + TESTvalue); + arc_cont(D_INIT_REASONS, "S3: "); + if (BUGLVL(D_INIT_REASONS)) + numprint = 0; goto out2; } /* By writing 0x42 to the TESTvalue location, we also make @@ -254,15 +244,16 @@ static void __init com90xx_probe(void) * in another pass through this loop, they will be discarded * because *cptr != TESTvalue. */ - writeb(0x42, base); - if (readb(base) != 0x42) { - BUGMSG2(D_INIT_REASONS, "(read only)\n"); - BUGMSG2(D_INIT_REASONS, "S3: "); + arcnet_writeb(0x42, base, COM9026_REG_W_INTMASK); + if (arcnet_readb(base, COM9026_REG_R_STATUS) != 0x42) { + arc_cont(D_INIT_REASONS, "(read only)\n"); + arc_cont(D_INIT_REASONS, "S3: "); goto out2; } - BUGMSG2(D_INIT_REASONS, "\n"); - BUGMSG2(D_INIT_REASONS, "S3: "); - BUGLVL(D_INIT_REASONS) numprint = 0; + arc_cont(D_INIT_REASONS, "\n"); + arc_cont(D_INIT_REASONS, "S3: "); + if (BUGLVL(D_INIT_REASONS)) + numprint = 0; iomem[index] = base; continue; out2: @@ -273,10 +264,10 @@ static void __init com90xx_probe(void) *p-- = shmems[--numshmems]; index--; } - BUGMSG2(D_INIT, "\n"); + arc_cont(D_INIT, "\n"); if (!numshmems) { - BUGMSG2(D_NORMAL, "S3: No ARCnet cards found.\n"); + arc_cont(D_NORMAL, "S3: No ARCnet cards found.\n"); for (port = &ports[0]; port < ports + numports; port++) release_region(*port, ARCNET_TOTAL_SIZE); kfree(shmems); @@ -291,12 +282,12 @@ static void __init com90xx_probe(void) numprint++; numprint %= 8; if (!numprint) { - BUGMSG2(D_INIT, "\n"); - BUGMSG2(D_INIT, "S4: "); + arc_cont(D_INIT, "\n"); + arc_cont(D_INIT, "S4: "); } - BUGMSG2(D_INIT, "%lXh ", *p); + arc_cont(D_INIT, "%lXh ", *p); } - BUGMSG2(D_INIT, "\n"); + arc_cont(D_INIT, "\n"); /* Stage 5: for any ports that have the correct status, can disable * the RESET flag, and (if no irq is given) generate an autoirq, @@ -308,33 +299,37 @@ static void __init com90xx_probe(void) numprint = -1; for (port = &ports[0]; port < ports + numports; port++) { int found = 0; + numprint++; numprint %= 8; if (!numprint) { - BUGMSG2(D_INIT, "\n"); - BUGMSG2(D_INIT, "S5: "); + arc_cont(D_INIT, "\n"); + arc_cont(D_INIT, "S5: "); } - BUGMSG2(D_INIT, "%Xh ", *port); + arc_cont(D_INIT, "%Xh ", *port); ioaddr = *port; - status = ASTATUS(); + status = arcnet_inb(ioaddr, COM9026_REG_R_STATUS); if ((status & 0x9D) != (NORXflag | RECONflag | TXFREEflag | RESETflag)) { - BUGMSG2(D_INIT_REASONS, "(status=%Xh)\n", status); - BUGMSG2(D_INIT_REASONS, "S5: "); - BUGLVL(D_INIT_REASONS) numprint = 0; + arc_cont(D_INIT_REASONS, "(status=%Xh)\n", status); + arc_cont(D_INIT_REASONS, "S5: "); + if (BUGLVL(D_INIT_REASONS)) + numprint = 0; release_region(*port, ARCNET_TOTAL_SIZE); *port-- = ports[--numports]; continue; } - ACOMMAND(CFLAGScmd | RESETclear | CONFIGclear); - status = ASTATUS(); + arcnet_outb(CFLAGScmd | RESETclear | CONFIGclear, + ioaddr, COM9026_REG_W_COMMAND); + status = arcnet_inb(ioaddr, COM9026_REG_R_STATUS); if (status & RESETflag) { - BUGMSG2(D_INIT_REASONS, " (eternal reset, status=%Xh)\n", - status); - BUGMSG2(D_INIT_REASONS, "S5: "); - BUGLVL(D_INIT_REASONS) numprint = 0; + arc_cont(D_INIT_REASONS, " (eternal reset, status=%Xh)\n", + status); + arc_cont(D_INIT_REASONS, "S5: "); + if (BUGLVL(D_INIT_REASONS)) + numprint = 0; release_region(*port, ARCNET_TOTAL_SIZE); *port-- = ports[--numports]; continue; @@ -348,15 +343,16 @@ static void __init com90xx_probe(void) * we tell it to start receiving. */ airqmask = probe_irq_on(); - AINTMASK(NORXflag); + arcnet_outb(NORXflag, ioaddr, COM9026_REG_W_INTMASK); udelay(1); - AINTMASK(0); + arcnet_outb(0, ioaddr, COM9026_REG_W_INTMASK); airq = probe_irq_off(airqmask); if (airq <= 0) { - BUGMSG2(D_INIT_REASONS, "(airq=%d)\n", airq); - BUGMSG2(D_INIT_REASONS, "S5: "); - BUGLVL(D_INIT_REASONS) numprint = 0; + arc_cont(D_INIT_REASONS, "(airq=%d)\n", airq); + arc_cont(D_INIT_REASONS, "S5: "); + if (BUGLVL(D_INIT_REASONS)) + numprint = 0; release_region(*port, ARCNET_TOTAL_SIZE); *port-- = ports[--numports]; continue; @@ -365,7 +361,7 @@ static void __init com90xx_probe(void) airq = irq; } - BUGMSG2(D_INIT, "(%d,", airq); + arc_cont(D_INIT, "(%d,", airq); openparen = 1; /* Everything seems okay. But which shmem, if any, puts @@ -376,14 +372,15 @@ static void __init com90xx_probe(void) */ #ifdef FAST_PROBE if (numports > 1 || numshmems > 1) { - inb(_RESET); + arcnet_inb(ioaddr, COM9026_REG_R_RESET); mdelay(RESETtime); } else { /* just one shmem and port, assume they match */ - writeb(TESTvalue, iomem[0]); + arcnet_writeb(TESTvalue, iomem[0], + COM9026_REG_W_INTMASK); } #else - inb(_RESET); + arcnet_inb(ioaddr, COM9026_REG_R_RESET); mdelay(RESETtime); #endif @@ -391,8 +388,8 @@ static void __init com90xx_probe(void) u_long ptr = shmems[index]; void __iomem *base = iomem[index]; - if (readb(base) == TESTvalue) { /* found one */ - BUGMSG2(D_INIT, "%lXh)\n", *p); + if (arcnet_readb(base, COM9026_REG_R_STATUS) == TESTvalue) { /* found one */ + arc_cont(D_INIT, "%lXh)\n", *p); openparen = 0; /* register the card */ @@ -405,25 +402,30 @@ static void __init com90xx_probe(void) iomem[index] = iomem[numshmems]; break; /* go to the next I/O port */ } else { - BUGMSG2(D_INIT_REASONS, "%Xh-", readb(base)); + arc_cont(D_INIT_REASONS, "%Xh-", + arcnet_readb(base, COM9026_REG_R_STATUS)); } } if (openparen) { - BUGLVL(D_INIT) printk("no matching shmem)\n"); - BUGLVL(D_INIT_REASONS) printk("S5: "); - BUGLVL(D_INIT_REASONS) numprint = 0; + if (BUGLVL(D_INIT)) + pr_cont("no matching shmem)\n"); + if (BUGLVL(D_INIT_REASONS)) { + pr_cont("S5: "); + numprint = 0; + } } if (!found) release_region(*port, ARCNET_TOTAL_SIZE); *port-- = ports[--numports]; } - BUGLVL(D_INIT_REASONS) printk("\n"); + if (BUGLVL(D_INIT_REASONS)) + pr_cont("\n"); /* Now put back TESTvalue on all leftover shmems. */ for (index = 0; index < numshmems; index++) { - writeb(TESTvalue, iomem[index]); + arcnet_writeb(TESTvalue, iomem[index], COM9026_REG_W_INTMASK); iounmap(iomem[index]); release_mem_region(shmems[index], MIRROR_SIZE); } @@ -441,7 +443,7 @@ static int check_mirror(unsigned long addr, size_t size) p = ioremap(addr, size); if (p) { - if (readb(p) == TESTvalue) + if (arcnet_readb(p, COM9026_REG_R_STATUS) == TESTvalue) res = 1; else res = 0; @@ -455,7 +457,8 @@ static int check_mirror(unsigned long addr, size_t size) /* Set up the struct net_device associated with this card. Called after * probing succeeds. */ -static int __init com90xx_found(int ioaddr, int airq, u_long shmem, void __iomem *p) +static int __init com90xx_found(int ioaddr, int airq, u_long shmem, + void __iomem *p) { struct net_device *dev = NULL; struct arcnet_local *lp; @@ -465,7 +468,7 @@ static int __init com90xx_found(int ioaddr, int airq, u_long shmem, void __iomem /* allocate struct net_device */ dev = alloc_arcdev(device); if (!dev) { - BUGMSG2(D_NORMAL, "com90xx: Can't allocate device!\n"); + arc_cont(D_NORMAL, "com90xx: Can't allocate device!\n"); iounmap(p); release_mem_region(shmem, MIRROR_SIZE); return -ENOMEM; @@ -478,7 +481,7 @@ static int __init com90xx_found(int ioaddr, int airq, u_long shmem, void __iomem * 2k (or there are no mirrors at all) but on some, it's 4k. */ mirror_size = MIRROR_SIZE; - if (readb(p) == TESTvalue && + if (arcnet_readb(p, COM9026_REG_R_STATUS) == TESTvalue && check_mirror(shmem - MIRROR_SIZE, MIRROR_SIZE) == 0 && check_mirror(shmem - 2 * MIRROR_SIZE, MIRROR_SIZE) == 1) mirror_size = 2 * MIRROR_SIZE; @@ -499,12 +502,14 @@ static int __init com90xx_found(int ioaddr, int airq, u_long shmem, void __iomem iounmap(p); release_mem_region(shmem, MIRROR_SIZE); - if (!request_mem_region(dev->mem_start, dev->mem_end - dev->mem_start + 1, "arcnet (90xx)")) + if (!request_mem_region(dev->mem_start, + dev->mem_end - dev->mem_start + 1, + "arcnet (90xx)")) goto err_free_dev; /* reserve the irq */ if (request_irq(airq, arcnet_interrupt, 0, "arcnet (90xx)", dev)) { - BUGMSG(D_NORMAL, "Can't get IRQ %d!\n", airq); + arc_printk(D_NORMAL, dev, "Can't get IRQ %d!\n", airq); goto err_release_mem; } dev->irq = airq; @@ -518,22 +523,23 @@ static int __init com90xx_found(int ioaddr, int airq, u_long shmem, void __iomem lp->hw.owner = THIS_MODULE; lp->hw.copy_to_card = com90xx_copy_to_card; lp->hw.copy_from_card = com90xx_copy_from_card; - lp->mem_start = ioremap(dev->mem_start, dev->mem_end - dev->mem_start + 1); + lp->mem_start = ioremap(dev->mem_start, + dev->mem_end - dev->mem_start + 1); if (!lp->mem_start) { - BUGMSG(D_NORMAL, "Can't remap device memory!\n"); + arc_printk(D_NORMAL, dev, "Can't remap device memory!\n"); goto err_free_irq; } /* get and check the station ID from offset 1 in shmem */ - dev->dev_addr[0] = readb(lp->mem_start + 1); + dev->dev_addr[0] = arcnet_readb(lp->mem_start, COM9026_REG_R_STATION); dev->base_addr = ioaddr; - BUGMSG(D_NORMAL, "COM90xx station %02Xh found at %03lXh, IRQ %d, " - "ShMem %lXh (%ld*%xh).\n", - dev->dev_addr[0], - dev->base_addr, dev->irq, dev->mem_start, - (dev->mem_end - dev->mem_start + 1) / mirror_size, mirror_size); + arc_printk(D_NORMAL, dev, "COM90xx station %02Xh found at %03lXh, IRQ %d, ShMem %lXh (%ld*%xh).\n", + dev->dev_addr[0], + dev->base_addr, dev->irq, dev->mem_start, + (dev->mem_end - dev->mem_start + 1) / mirror_size, + mirror_size); if (register_netdev(dev)) goto err_unmap; @@ -552,34 +558,29 @@ err_free_dev: return -EIO; } - static void com90xx_command(struct net_device *dev, int cmd) { short ioaddr = dev->base_addr; - ACOMMAND(cmd); + arcnet_outb(cmd, ioaddr, COM9026_REG_W_COMMAND); } - static int com90xx_status(struct net_device *dev) { short ioaddr = dev->base_addr; - return ASTATUS(); + return arcnet_inb(ioaddr, COM9026_REG_R_STATUS); } - static void com90xx_setmask(struct net_device *dev, int mask) { short ioaddr = dev->base_addr; - AINTMASK(mask); + arcnet_outb(mask, ioaddr, COM9026_REG_W_INTMASK); } - -/* - * Do a hardware reset on the card, and set up necessary registers. - * +/* Do a hardware reset on the card, and set up necessary registers. + * * This should be called as little as possible, because it disrupts the * token on the network (causes a RECON) and requires a significant delay. * @@ -590,53 +591,58 @@ static int com90xx_reset(struct net_device *dev, int really_reset) struct arcnet_local *lp = netdev_priv(dev); short ioaddr = dev->base_addr; - BUGMSG(D_INIT, "Resetting (status=%02Xh)\n", ASTATUS()); + arc_printk(D_INIT, dev, "Resetting (status=%02Xh)\n", + arcnet_inb(ioaddr, COM9026_REG_R_STATUS)); if (really_reset) { /* reset the card */ - inb(_RESET); + arcnet_inb(ioaddr, COM9026_REG_R_RESET); mdelay(RESETtime); } - ACOMMAND(CFLAGScmd | RESETclear); /* clear flags & end reset */ - ACOMMAND(CFLAGScmd | CONFIGclear); + /* clear flags & end reset */ + arcnet_outb(CFLAGScmd | RESETclear, ioaddr, COM9026_REG_W_COMMAND); + arcnet_outb(CFLAGScmd | CONFIGclear, ioaddr, COM9026_REG_W_COMMAND); +#if 0 /* don't do this until we verify that it doesn't hurt older cards! */ - /* outb(inb(_CONFIG) | ENABLE16flag, _CONFIG); */ + arcnet_outb(arcnet_inb(ioaddr, COM9026_REG_RW_CONFIG) | ENABLE16flag, + ioaddr, COM9026_REG_RW_CONFIG); +#endif /* verify that the ARCnet signature byte is present */ - if (readb(lp->mem_start) != TESTvalue) { + if (arcnet_readb(lp->mem_start, COM9026_REG_R_STATUS) != TESTvalue) { if (really_reset) - BUGMSG(D_NORMAL, "reset failed: TESTvalue not present.\n"); + arc_printk(D_NORMAL, dev, "reset failed: TESTvalue not present.\n"); return 1; } /* enable extended (512-byte) packets */ - ACOMMAND(CONFIGcmd | EXTconf); + arcnet_outb(CONFIGcmd | EXTconf, ioaddr, COM9026_REG_W_COMMAND); /* clean out all the memory to make debugging make more sense :) */ - BUGLVL(D_DURING) - memset_io(lp->mem_start, 0x42, 2048); + if (BUGLVL(D_DURING)) + memset_io(lp->mem_start, 0x42, 2048); /* done! return success. */ return 0; } -static void com90xx_copy_to_card(struct net_device *dev, int bufnum, int offset, - void *buf, int count) +static void com90xx_copy_to_card(struct net_device *dev, int bufnum, + int offset, void *buf, int count) { struct arcnet_local *lp = netdev_priv(dev); void __iomem *memaddr = lp->mem_start + bufnum * 512 + offset; - TIME("memcpy_toio", count, memcpy_toio(memaddr, buf, count)); -} + TIME(dev, "memcpy_toio", count, memcpy_toio(memaddr, buf, count)); +} -static void com90xx_copy_from_card(struct net_device *dev, int bufnum, int offset, - void *buf, int count) +static void com90xx_copy_from_card(struct net_device *dev, int bufnum, + int offset, void *buf, int count) { struct arcnet_local *lp = netdev_priv(dev); void __iomem *memaddr = lp->mem_start + bufnum * 512 + offset; - TIME("memcpy_fromio", count, memcpy_fromio(buf, memaddr, count)); -} + TIME(dev, "memcpy_fromio", count, memcpy_fromio(buf, memaddr, count)); +} MODULE_LICENSE("GPL"); @@ -664,7 +670,8 @@ static void __exit com90xx_exit(void) free_irq(dev->irq, dev); iounmap(lp->mem_start); release_region(dev->base_addr, ARCNET_TOTAL_SIZE); - release_mem_region(dev->mem_start, dev->mem_end - dev->mem_start + 1); + release_mem_region(dev->mem_start, + dev->mem_end - dev->mem_start + 1); free_netdev(dev); } } @@ -679,13 +686,13 @@ static int __init com90xx_setup(char *s) s = get_options(s, 8, ints); if (!ints[0] && !*s) { - printk("com90xx: Disabled.\n"); + pr_notice("Disabled\n"); return 1; } switch (ints[0]) { default: /* ERROR */ - printk("com90xx: Too many arguments.\n"); + pr_err("Too many arguments\n"); case 3: /* Mem address */ shmem = ints[3]; case 2: /* IRQ */ diff --git a/drivers/net/arcnet/rfc1051.c b/drivers/net/arcnet/rfc1051.c index f81db4070a57..4b1a75469cb1 100644 --- a/drivers/net/arcnet/rfc1051.c +++ b/drivers/net/arcnet/rfc1051.c @@ -1,6 +1,6 @@ /* * Linux ARCnet driver - RFC1051 ("simple" standard) packet encapsulation - * + * * Written 1994-1999 by Avery Pennarun. * Derived from skeleton.c by Donald Becker. * @@ -23,6 +23,9 @@ * * ********************** */ + +#define pr_fmt(fmt) "arcnet:" KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/gfp.h> #include <linux/init.h> @@ -30,10 +33,8 @@ #include <net/arp.h> #include <linux/netdevice.h> #include <linux/skbuff.h> -#include <linux/arcdevice.h> - -#define VERSION "arcnet: RFC1051 \"simple standard\" (`s') encapsulation support loaded.\n" +#include "arcdevice.h" static __be16 type_trans(struct sk_buff *skb, struct net_device *dev); static void rx(struct net_device *dev, int bufnum, @@ -43,9 +44,7 @@ static int build_header(struct sk_buff *skb, struct net_device *dev, static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, int bufnum); - -static struct ArcProto rfc1051_proto = -{ +static struct ArcProto rfc1051_proto = { .suffix = 's', .mtu = XMTU - RFC1051_HDR_SIZE, .is_ip = 1, @@ -56,10 +55,9 @@ static struct ArcProto rfc1051_proto = .ack_tx = NULL }; - static int __init arcnet_rfc1051_init(void) { - printk(VERSION); + pr_info("%s\n", "RFC1051 \"simple standard\" (`s') encapsulation support loaded"); arc_proto_map[ARC_P_IP_RFC1051] = arc_proto_map[ARC_P_ARP_RFC1051] @@ -82,14 +80,13 @@ module_exit(arcnet_rfc1051_exit); MODULE_LICENSE("GPL"); -/* - * Determine a packet's protocol ID. - * +/* Determine a packet's protocol ID. + * * With ARCnet we have to convert everything to Ethernet-style stuff. */ static __be16 type_trans(struct sk_buff *skb, struct net_device *dev) { - struct archdr *pkt = (struct archdr *) skb->data; + struct archdr *pkt = (struct archdr *)skb->data; struct arc_rfc1051 *soft = &pkt->soft.rfc1051; int hdr_size = ARC_HDR_SIZE + RFC1051_HDR_SIZE; @@ -97,9 +94,9 @@ static __be16 type_trans(struct sk_buff *skb, struct net_device *dev) skb_reset_mac_header(skb); skb_pull(skb, hdr_size); - if (pkt->hard.dest == 0) + if (pkt->hard.dest == 0) { skb->pkt_type = PACKET_BROADCAST; - else if (dev->flags & IFF_PROMISC) { + } else if (dev->flags & IFF_PROMISC) { /* if we're not sending to ourselves :) */ if (pkt->hard.dest != dev->dev_addr[0]) skb->pkt_type = PACKET_OTHERHOST; @@ -120,7 +117,6 @@ static __be16 type_trans(struct sk_buff *skb, struct net_device *dev) return htons(ETH_P_IP); } - /* packet receiver */ static void rx(struct net_device *dev, int bufnum, struct archdr *pkthdr, int length) @@ -130,7 +126,7 @@ static void rx(struct net_device *dev, int bufnum, struct archdr *pkt = pkthdr; int ofs; - BUGMSG(D_DURING, "it's a raw packet (length=%d)\n", length); + arc_printk(D_DURING, dev, "it's a raw packet (length=%d)\n", length); if (length >= MinTU) ofs = 512 - length; @@ -138,15 +134,14 @@ static void rx(struct net_device *dev, int bufnum, ofs = 256 - length; skb = alloc_skb(length + ARC_HDR_SIZE, GFP_ATOMIC); - if (skb == NULL) { - BUGMSG(D_NORMAL, "Memory squeeze, dropping packet.\n"); + if (!skb) { dev->stats.rx_dropped++; return; } skb_put(skb, length + ARC_HDR_SIZE); skb->dev = dev; - pkt = (struct archdr *) skb->data; + pkt = (struct archdr *)skb->data; /* up to sizeof(pkt->soft) has already been copied from the card */ memcpy(pkt, pkthdr, sizeof(struct archdr)); @@ -155,21 +150,19 @@ static void rx(struct net_device *dev, int bufnum, pkt->soft.raw + sizeof(pkt->soft), length - sizeof(pkt->soft)); - BUGLVL(D_SKB) arcnet_dump_skb(dev, skb, "rx"); + if (BUGLVL(D_SKB)) + arcnet_dump_skb(dev, skb, "rx"); skb->protocol = type_trans(skb, dev); netif_rx(skb); } - -/* - * Create the ARCnet hard/soft headers for RFC1051. - */ +/* Create the ARCnet hard/soft headers for RFC1051 */ static int build_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, uint8_t daddr) { int hdr_size = ARC_HDR_SIZE + RFC1051_HDR_SIZE; - struct archdr *pkt = (struct archdr *) skb_push(skb, hdr_size); + struct archdr *pkt = (struct archdr *)skb_push(skb, hdr_size); struct arc_rfc1051 *soft = &pkt->soft.rfc1051; /* set the protocol ID according to RFC1051 */ @@ -181,29 +174,26 @@ static int build_header(struct sk_buff *skb, struct net_device *dev, soft->proto = ARC_P_ARP_RFC1051; break; default: - BUGMSG(D_NORMAL, "RFC1051: I don't understand protocol %d (%Xh)\n", - type, type); + arc_printk(D_NORMAL, dev, "RFC1051: I don't understand protocol %d (%Xh)\n", + type, type); dev->stats.tx_errors++; dev->stats.tx_aborted_errors++; return 0; } - - /* - * Set the source hardware address. + /* Set the source hardware address. * * This is pretty pointless for most purposes, but it can help in - * debugging. ARCnet does not allow us to change the source address in - * the actual packet sent) + * debugging. ARCnet does not allow us to change the source address + * in the actual packet sent. */ pkt->hard.source = *dev->dev_addr; /* see linux/net/ethernet/eth.c to see where I got the following */ if (dev->flags & (IFF_LOOPBACK | IFF_NOARP)) { - /* - * FIXME: fill in the last byte of the dest ipaddr here to better - * comply with RFC1051 in "noarp" mode. + /* FIXME: fill in the last byte of the dest ipaddr here to + * better comply with RFC1051 in "noarp" mode. */ pkt->hard.dest = 0; return hdr_size; @@ -214,7 +204,6 @@ static int build_header(struct sk_buff *skb, struct net_device *dev, return hdr_size; /* success */ } - static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, int bufnum) { @@ -222,15 +211,16 @@ static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, struct arc_hardware *hard = &pkt->hard; int ofs; - BUGMSG(D_DURING, "prepare_tx: txbufs=%d/%d/%d\n", - lp->next_tx, lp->cur_tx, bufnum); + arc_printk(D_DURING, dev, "prepare_tx: txbufs=%d/%d/%d\n", + lp->next_tx, lp->cur_tx, bufnum); - length -= ARC_HDR_SIZE; /* hard header is not included in packet length */ + /* hard header is not included in packet length */ + length -= ARC_HDR_SIZE; if (length > XMTU) { /* should never happen! other people already check for this. */ - BUGMSG(D_NORMAL, "Bug! prepare_tx with size %d (> %d)\n", - length, XMTU); + arc_printk(D_NORMAL, dev, "Bug! prepare_tx with size %d (> %d)\n", + length, XMTU); length = XMTU; } if (length > MinTU) { @@ -239,8 +229,9 @@ static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, } else if (length > MTU) { hard->offset[0] = 0; hard->offset[1] = ofs = 512 - length - 3; - } else + } else { hard->offset[0] = ofs = 256 - length; + } lp->hw.copy_to_card(dev, bufnum, 0, hard, ARC_HDR_SIZE); lp->hw.copy_to_card(dev, bufnum, ofs, &pkt->soft, length); diff --git a/drivers/net/arcnet/rfc1201.c b/drivers/net/arcnet/rfc1201.c index b71431aae084..566da5ecdc9d 100644 --- a/drivers/net/arcnet/rfc1201.c +++ b/drivers/net/arcnet/rfc1201.c @@ -1,6 +1,6 @@ /* * Linux ARCnet driver - RFC1201 (standard) packet encapsulation - * + * * Written 1994-1999 by Avery Pennarun. * Derived from skeleton.c by Donald Becker. * @@ -23,17 +23,19 @@ * * ********************** */ + +#define pr_fmt(fmt) "arcnet:" KBUILD_MODNAME ": " fmt + #include <linux/gfp.h> #include <linux/module.h> #include <linux/init.h> #include <linux/if_arp.h> #include <linux/netdevice.h> #include <linux/skbuff.h> -#include <linux/arcdevice.h> -MODULE_LICENSE("GPL"); -#define VERSION "arcnet: RFC1201 \"standard\" (`a') encapsulation support loaded.\n" +#include "arcdevice.h" +MODULE_LICENSE("GPL"); static __be16 type_trans(struct sk_buff *skb, struct net_device *dev); static void rx(struct net_device *dev, int bufnum, @@ -44,8 +46,7 @@ static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, int bufnum); static int continue_tx(struct net_device *dev, int bufnum); -static struct ArcProto rfc1201_proto = -{ +static struct ArcProto rfc1201_proto = { .suffix = 'a', .mtu = 1500, /* could be more, but some receivers can't handle it... */ .is_ip = 1, /* This is for sending IP and ARP packages */ @@ -56,10 +57,9 @@ static struct ArcProto rfc1201_proto = .ack_tx = NULL }; - static int __init arcnet_rfc1201_init(void) { - printk(VERSION); + pr_info("%s\n", "RFC1201 \"standard\" (`a') encapsulation support loaded"); arc_proto_map[ARC_P_IP] = arc_proto_map[ARC_P_IPV6] @@ -84,14 +84,13 @@ static void __exit arcnet_rfc1201_exit(void) module_init(arcnet_rfc1201_init); module_exit(arcnet_rfc1201_exit); -/* - * Determine a packet's protocol ID. - * +/* Determine a packet's protocol ID. + * * With ARCnet we have to convert everything to Ethernet-style stuff. */ static __be16 type_trans(struct sk_buff *skb, struct net_device *dev) { - struct archdr *pkt = (struct archdr *) skb->data; + struct archdr *pkt = (struct archdr *)skb->data; struct arc_rfc1201 *soft = &pkt->soft.rfc1201; int hdr_size = ARC_HDR_SIZE + RFC1201_HDR_SIZE; @@ -99,9 +98,9 @@ static __be16 type_trans(struct sk_buff *skb, struct net_device *dev) skb_reset_mac_header(skb); skb_pull(skb, hdr_size); - if (pkt->hard.dest == 0) + if (pkt->hard.dest == 0) { skb->pkt_type = PACKET_BROADCAST; - else if (dev->flags & IFF_PROMISC) { + } else if (dev->flags & IFF_PROMISC) { /* if we're not sending to ourselves :) */ if (pkt->hard.dest != dev->dev_addr[0]) skb->pkt_type = PACKET_OTHERHOST; @@ -129,7 +128,6 @@ static __be16 type_trans(struct sk_buff *skb, struct net_device *dev) return htons(ETH_P_IP); } - /* packet receiver */ static void rx(struct net_device *dev, int bufnum, struct archdr *pkthdr, int length) @@ -141,7 +139,8 @@ static void rx(struct net_device *dev, int bufnum, int saddr = pkt->hard.source, ofs; struct Incoming *in = &lp->rfc1201.incoming[saddr]; - BUGMSG(D_DURING, "it's an RFC1201 packet (length=%d)\n", length); + arc_printk(D_DURING, dev, "it's an RFC1201 packet (length=%d)\n", + length); if (length >= MinTU) ofs = 512 - length; @@ -149,11 +148,11 @@ static void rx(struct net_device *dev, int bufnum, ofs = 256 - length; if (soft->split_flag == 0xFF) { /* Exception Packet */ - if (length >= 4 + RFC1201_HDR_SIZE) - BUGMSG(D_DURING, "compensating for exception packet\n"); - else { - BUGMSG(D_EXTRA, "short RFC1201 exception packet from %02Xh", - saddr); + if (length >= 4 + RFC1201_HDR_SIZE) { + arc_printk(D_DURING, dev, "compensating for exception packet\n"); + } else { + arc_printk(D_EXTRA, dev, "short RFC1201 exception packet from %02Xh", + saddr); return; } @@ -164,12 +163,13 @@ static void rx(struct net_device *dev, int bufnum, soft, sizeof(pkt->soft)); } if (!soft->split_flag) { /* not split */ - BUGMSG(D_RX, "incoming is not split (splitflag=%d)\n", - soft->split_flag); + arc_printk(D_RX, dev, "incoming is not split (splitflag=%d)\n", + soft->split_flag); if (in->skb) { /* already assembling one! */ - BUGMSG(D_EXTRA, "aborting assembly (seq=%d) for unsplit packet (splitflag=%d, seq=%d)\n", - in->sequence, soft->split_flag, soft->sequence); + arc_printk(D_EXTRA, dev, "aborting assembly (seq=%d) for unsplit packet (splitflag=%d, seq=%d)\n", + in->sequence, soft->split_flag, + soft->sequence); lp->rfc1201.aborted_seq = soft->sequence; dev_kfree_skb_irq(in->skb); dev->stats.rx_errors++; @@ -179,82 +179,86 @@ static void rx(struct net_device *dev, int bufnum, in->sequence = soft->sequence; skb = alloc_skb(length + ARC_HDR_SIZE, GFP_ATOMIC); - if (skb == NULL) { - BUGMSG(D_NORMAL, "Memory squeeze, dropping packet.\n"); + if (!skb) { dev->stats.rx_dropped++; return; } skb_put(skb, length + ARC_HDR_SIZE); skb->dev = dev; - pkt = (struct archdr *) skb->data; + pkt = (struct archdr *)skb->data; soft = &pkt->soft.rfc1201; - /* up to sizeof(pkt->soft) has already been copied from the card */ + /* up to sizeof(pkt->soft) has already + * been copied from the card + */ memcpy(pkt, pkthdr, sizeof(struct archdr)); if (length > sizeof(pkt->soft)) - lp->hw.copy_from_card(dev, bufnum, ofs + sizeof(pkt->soft), - pkt->soft.raw + sizeof(pkt->soft), + lp->hw.copy_from_card(dev, bufnum, + ofs + sizeof(pkt->soft), + pkt->soft.raw + sizeof(pkt->soft), length - sizeof(pkt->soft)); - /* - * ARP packets have problems when sent from some DOS systems: the - * source address is always 0! So we take the hardware source addr - * (which is impossible to fumble) and insert it ourselves. + /* ARP packets have problems when sent from some DOS systems: + * the source address is always 0! + * So we take the hardware source addr (which is impossible + * to fumble) and insert it ourselves. */ if (soft->proto == ARC_P_ARP) { - struct arphdr *arp = (struct arphdr *) soft->payload; + struct arphdr *arp = (struct arphdr *)soft->payload; /* make sure addresses are the right length */ if (arp->ar_hln == 1 && arp->ar_pln == 4) { - uint8_t *cptr = (uint8_t *) arp + sizeof(struct arphdr); + uint8_t *cptr = (uint8_t *)arp + sizeof(struct arphdr); if (!*cptr) { /* is saddr = 00? */ - BUGMSG(D_EXTRA, - "ARP source address was 00h, set to %02Xh.\n", - saddr); + arc_printk(D_EXTRA, dev, + "ARP source address was 00h, set to %02Xh\n", + saddr); dev->stats.rx_crc_errors++; *cptr = saddr; } else { - BUGMSG(D_DURING, "ARP source address (%Xh) is fine.\n", - *cptr); + arc_printk(D_DURING, dev, "ARP source address (%Xh) is fine.\n", + *cptr); } } else { - BUGMSG(D_NORMAL, "funny-shaped ARP packet. (%Xh, %Xh)\n", - arp->ar_hln, arp->ar_pln); + arc_printk(D_NORMAL, dev, "funny-shaped ARP packet. (%Xh, %Xh)\n", + arp->ar_hln, arp->ar_pln); dev->stats.rx_errors++; dev->stats.rx_crc_errors++; } } - BUGLVL(D_SKB) arcnet_dump_skb(dev, skb, "rx"); + if (BUGLVL(D_SKB)) + arcnet_dump_skb(dev, skb, "rx"); skb->protocol = type_trans(skb, dev); netif_rx(skb); } else { /* split packet */ - /* - * NOTE: MSDOS ARP packet correction should only need to apply to - * unsplit packets, since ARP packets are so short. + /* NOTE: MSDOS ARP packet correction should only need to + * apply to unsplit packets, since ARP packets are so short. * - * My interpretation of the RFC1201 document is that if a packet is - * received out of order, the entire assembly process should be - * aborted. + * My interpretation of the RFC1201 document is that if a + * packet is received out of order, the entire assembly + * process should be aborted. * - * The RFC also mentions "it is possible for successfully received - * packets to be retransmitted." As of 0.40 all previously received - * packets are allowed, not just the most recent one. + * The RFC also mentions "it is possible for successfully + * received packets to be retransmitted." As of 0.40 all + * previously received packets are allowed, not just the + * most recent one. * - * We allow multiple assembly processes, one for each ARCnet card - * possible on the network. Seems rather like a waste of memory, - * but there's no other way to be reliable. + * We allow multiple assembly processes, one for each + * ARCnet card possible on the network. + * Seems rather like a waste of memory, but there's no + * other way to be reliable. */ - BUGMSG(D_RX, "packet is split (splitflag=%d, seq=%d)\n", - soft->split_flag, in->sequence); + arc_printk(D_RX, dev, "packet is split (splitflag=%d, seq=%d)\n", + soft->split_flag, in->sequence); if (in->skb && in->sequence != soft->sequence) { - BUGMSG(D_EXTRA, "wrong seq number (saddr=%d, expected=%d, seq=%d, splitflag=%d)\n", - saddr, in->sequence, soft->sequence, - soft->split_flag); + arc_printk(D_EXTRA, dev, "wrong seq number (saddr=%d, expected=%d, seq=%d, splitflag=%d)\n", + saddr, in->sequence, soft->sequence, + soft->split_flag); dev_kfree_skb_irq(in->skb); in->skb = NULL; dev->stats.rx_errors++; @@ -262,24 +266,23 @@ static void rx(struct net_device *dev, int bufnum, in->lastpacket = in->numpackets = 0; } if (soft->split_flag & 1) { /* first packet in split */ - BUGMSG(D_RX, "brand new splitpacket (splitflag=%d)\n", - soft->split_flag); + arc_printk(D_RX, dev, "brand new splitpacket (splitflag=%d)\n", + soft->split_flag); if (in->skb) { /* already assembling one! */ - BUGMSG(D_EXTRA, "aborting previous (seq=%d) assembly " - "(splitflag=%d, seq=%d)\n", - in->sequence, soft->split_flag, - soft->sequence); + arc_printk(D_EXTRA, dev, "aborting previous (seq=%d) assembly (splitflag=%d, seq=%d)\n", + in->sequence, soft->split_flag, + soft->sequence); dev->stats.rx_errors++; dev->stats.rx_missed_errors++; dev_kfree_skb_irq(in->skb); } in->sequence = soft->sequence; - in->numpackets = ((unsigned) soft->split_flag >> 1) + 2; + in->numpackets = ((unsigned)soft->split_flag >> 1) + 2; in->lastpacket = 1; if (in->numpackets > 16) { - BUGMSG(D_EXTRA, "incoming packet more than 16 segments; dropping. (splitflag=%d)\n", - soft->split_flag); + arc_printk(D_EXTRA, dev, "incoming packet more than 16 segments; dropping. (splitflag=%d)\n", + soft->split_flag); lp->rfc1201.aborted_seq = soft->sequence; dev->stats.rx_errors++; dev->stats.rx_length_errors++; @@ -287,14 +290,14 @@ static void rx(struct net_device *dev, int bufnum, } in->skb = skb = alloc_skb(508 * in->numpackets + ARC_HDR_SIZE, GFP_ATOMIC); - if (skb == NULL) { - BUGMSG(D_NORMAL, "(split) memory squeeze, dropping packet.\n"); + if (!skb) { + arc_printk(D_NORMAL, dev, "(split) memory squeeze, dropping packet.\n"); lp->rfc1201.aborted_seq = soft->sequence; dev->stats.rx_dropped++; return; } skb->dev = dev; - pkt = (struct archdr *) skb->data; + pkt = (struct archdr *)skb->data; soft = &pkt->soft.rfc1201; memcpy(pkt, pkthdr, ARC_HDR_SIZE + RFC1201_HDR_SIZE); @@ -302,37 +305,37 @@ static void rx(struct net_device *dev, int bufnum, soft->split_flag = 0; /* end result won't be split */ } else { /* not first packet */ - int packetnum = ((unsigned) soft->split_flag >> 1) + 1; + int packetnum = ((unsigned)soft->split_flag >> 1) + 1; - /* - * if we're not assembling, there's no point trying to + /* if we're not assembling, there's no point trying to * continue. */ if (!in->skb) { if (lp->rfc1201.aborted_seq != soft->sequence) { - BUGMSG(D_EXTRA, "can't continue split without starting " - "first! (splitflag=%d, seq=%d, aborted=%d)\n", - soft->split_flag, soft->sequence, - lp->rfc1201.aborted_seq); + arc_printk(D_EXTRA, dev, "can't continue split without starting first! (splitflag=%d, seq=%d, aborted=%d)\n", + soft->split_flag, + soft->sequence, + lp->rfc1201.aborted_seq); dev->stats.rx_errors++; dev->stats.rx_missed_errors++; } return; } in->lastpacket++; - if (packetnum != in->lastpacket) { /* not the right flag! */ + /* if not the right flag */ + if (packetnum != in->lastpacket) { /* harmless duplicate? ignore. */ if (packetnum <= in->lastpacket - 1) { - BUGMSG(D_EXTRA, "duplicate splitpacket ignored! (splitflag=%d)\n", - soft->split_flag); + arc_printk(D_EXTRA, dev, "duplicate splitpacket ignored! (splitflag=%d)\n", + soft->split_flag); dev->stats.rx_errors++; dev->stats.rx_frame_errors++; return; } /* "bad" duplicate, kill reassembly */ - BUGMSG(D_EXTRA, "out-of-order splitpacket, reassembly " - "(seq=%d) aborted (splitflag=%d, seq=%d)\n", - in->sequence, soft->split_flag, soft->sequence); + arc_printk(D_EXTRA, dev, "out-of-order splitpacket, reassembly (seq=%d) aborted (splitflag=%d, seq=%d)\n", + in->sequence, soft->split_flag, + soft->sequence); lp->rfc1201.aborted_seq = soft->sequence; dev_kfree_skb_irq(in->skb); in->skb = NULL; @@ -341,7 +344,7 @@ static void rx(struct net_device *dev, int bufnum, in->lastpacket = in->numpackets = 0; return; } - pkt = (struct archdr *) in->skb->data; + pkt = (struct archdr *)in->skb->data; soft = &pkt->soft.rfc1201; } @@ -357,11 +360,12 @@ static void rx(struct net_device *dev, int bufnum, in->skb = NULL; in->lastpacket = in->numpackets = 0; - BUGMSG(D_SKB_SIZE, "skb: received %d bytes from %02X (unsplit)\n", - skb->len, pkt->hard.source); - BUGMSG(D_SKB_SIZE, "skb: received %d bytes from %02X (split)\n", - skb->len, pkt->hard.source); - BUGLVL(D_SKB) arcnet_dump_skb(dev, skb, "rx"); + arc_printk(D_SKB_SIZE, dev, "skb: received %d bytes from %02X (unsplit)\n", + skb->len, pkt->hard.source); + arc_printk(D_SKB_SIZE, dev, "skb: received %d bytes from %02X (split)\n", + skb->len, pkt->hard.source); + if (BUGLVL(D_SKB)) + arcnet_dump_skb(dev, skb, "rx"); skb->protocol = type_trans(skb, dev); netif_rx(skb); @@ -369,14 +373,13 @@ static void rx(struct net_device *dev, int bufnum, } } - /* Create the ARCnet hard/soft headers for RFC1201. */ static int build_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, uint8_t daddr) { struct arcnet_local *lp = netdev_priv(dev); int hdr_size = ARC_HDR_SIZE + RFC1201_HDR_SIZE; - struct archdr *pkt = (struct archdr *) skb_push(skb, hdr_size); + struct archdr *pkt = (struct archdr *)skb_push(skb, hdr_size); struct arc_rfc1201 *soft = &pkt->soft.rfc1201; /* set the protocol ID according to RFC1201 */ @@ -402,19 +405,18 @@ static int build_header(struct sk_buff *skb, struct net_device *dev, soft->proto = ARC_P_ATALK; break; default: - BUGMSG(D_NORMAL, "RFC1201: I don't understand protocol %d (%Xh)\n", - type, type); + arc_printk(D_NORMAL, dev, "RFC1201: I don't understand protocol %d (%Xh)\n", + type, type); dev->stats.tx_errors++; dev->stats.tx_aborted_errors++; return 0; } - /* - * Set the source hardware address. + /* Set the source hardware address. * * This is pretty pointless for most purposes, but it can help in - * debugging. ARCnet does not allow us to change the source address in - * the actual packet sent) + * debugging. ARCnet does not allow us to change the source address + * in the actual packet sent. */ pkt->hard.source = *dev->dev_addr; @@ -424,10 +426,10 @@ static int build_header(struct sk_buff *skb, struct net_device *dev, /* see linux/net/ethernet/eth.c to see where I got the following */ if (dev->flags & (IFF_LOOPBACK | IFF_NOARP)) { - /* - * FIXME: fill in the last byte of the dest ipaddr here to better - * comply with RFC1051 in "noarp" mode. For now, always broadcasting - * will probably at least get packets sent out :) + /* FIXME: fill in the last byte of the dest ipaddr here + * to better comply with RFC1051 in "noarp" mode. + * For now, always broadcasting will probably at least get + * packets sent out :) */ pkt->hard.dest = 0; return hdr_size; @@ -437,7 +439,6 @@ static int build_header(struct sk_buff *skb, struct net_device *dev, return hdr_size; } - static void load_pkt(struct net_device *dev, struct arc_hardware *hard, struct arc_rfc1201 *soft, int softlen, int bufnum) { @@ -461,8 +462,9 @@ static void load_pkt(struct net_device *dev, struct arc_hardware *hard, hard->offset[1] = ofs - RFC1201_HDR_SIZE; lp->hw.copy_to_card(dev, bufnum, ofs - RFC1201_HDR_SIZE, &excsoft, RFC1201_HDR_SIZE); - } else + } else { hard->offset[0] = ofs = 256 - softlen; + } lp->hw.copy_to_card(dev, bufnum, 0, hard, ARC_HDR_SIZE); lp->hw.copy_to_card(dev, bufnum, ofs, soft, softlen); @@ -470,7 +472,6 @@ static void load_pkt(struct net_device *dev, struct arc_hardware *hard, lp->lastload_dest = hard->dest; } - static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, int bufnum) { @@ -478,11 +479,11 @@ static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, const int maxsegsize = XMTU - RFC1201_HDR_SIZE; struct Outgoing *out; + arc_printk(D_DURING, dev, "prepare_tx: txbufs=%d/%d/%d\n", + lp->next_tx, lp->cur_tx, bufnum); - BUGMSG(D_DURING, "prepare_tx: txbufs=%d/%d/%d\n", - lp->next_tx, lp->cur_tx, bufnum); - - length -= ARC_HDR_SIZE; /* hard header is not included in packet length */ + /* hard header is not included in packet length */ + length -= ARC_HDR_SIZE; pkt->soft.rfc1201.split_flag = 0; /* need to do a split packet? */ @@ -494,9 +495,9 @@ static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, out->numsegs = (out->dataleft + maxsegsize - 1) / maxsegsize; out->segnum = 0; - BUGMSG(D_DURING, "rfc1201 prep_tx: ready for %d-segment split " - "(%d bytes, seq=%d)\n", out->numsegs, out->length, - pkt->soft.rfc1201.sequence); + arc_printk(D_DURING, dev, "rfc1201 prep_tx: ready for %d-segment split (%d bytes, seq=%d)\n", + out->numsegs, out->length, + pkt->soft.rfc1201.sequence); return 0; /* not done */ } @@ -506,7 +507,6 @@ static int prepare_tx(struct net_device *dev, struct archdr *pkt, int length, return 1; /* done */ } - static int continue_tx(struct net_device *dev, int bufnum) { struct arcnet_local *lp = netdev_priv(dev); @@ -516,9 +516,9 @@ static int continue_tx(struct net_device *dev, int bufnum) int maxsegsize = XMTU - RFC1201_HDR_SIZE; int seglen; - BUGMSG(D_DURING, - "rfc1201 continue_tx: loading segment %d(+1) of %d (seq=%d)\n", - out->segnum, out->numsegs, soft->sequence); + arc_printk(D_DURING, dev, + "rfc1201 continue_tx: loading segment %d(+1) of %d (seq=%d)\n", + out->segnum, out->numsegs, soft->sequence); /* the "new" soft header comes right before the data chunk */ newsoft = (struct arc_rfc1201 *) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 771a449d2f56..90f2615428c0 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3136,6 +3136,10 @@ u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb) struct flow_keys flow; u32 hash; + if (bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP34 && + skb->l4_hash) + return skb->hash; + if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER2 || !bond_flow_dissect(bond, skb, &flow)) return bond_eth_hash(skb); diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig index e8c96b8e86f4..6d04183ed955 100644 --- a/drivers/net/can/Kconfig +++ b/drivers/net/can/Kconfig @@ -129,6 +129,16 @@ config CAN_RCAR To compile this driver as a module, choose M here: the module will be called rcar_can. +config CAN_SUN4I + tristate "Allwinner A10 CAN controller" + depends on MACH_SUN4I || MACH_SUN7I || COMPILE_TEST + ---help--- + Say Y here if you want to use CAN controller found on Allwinner + A10/A20 SoCs. + + To compile this driver as a module, choose M here: the module will + be called sun4i_can. + config CAN_XILINXCAN tristate "Xilinx CAN" depends on ARCH_ZYNQ || ARM64 || MICROBLAZE || COMPILE_TEST diff --git a/drivers/net/can/Makefile b/drivers/net/can/Makefile index c533c62b0f5e..1f21cef1d458 100644 --- a/drivers/net/can/Makefile +++ b/drivers/net/can/Makefile @@ -27,6 +27,7 @@ obj-$(CONFIG_CAN_FLEXCAN) += flexcan.o obj-$(CONFIG_PCH_CAN) += pch_can.o obj-$(CONFIG_CAN_GRCAN) += grcan.o obj-$(CONFIG_CAN_RCAR) += rcar_can.o +obj-$(CONFIG_CAN_SUN4I) += sun4i_can.o obj-$(CONFIG_CAN_XILINXCAN) += xilinx_can.o subdir-ccflags-y += -D__CHECK_ENDIAN__ diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index c83f0f03482b..868fe945e35a 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -26,12 +26,8 @@ #include <linux/can/led.h> #include <linux/clk.h> #include <linux/delay.h> -#include <linux/if_arp.h> -#include <linux/if_ether.h> #include <linux/interrupt.h> #include <linux/io.h> -#include <linux/kernel.h> -#include <linux/list.h> #include <linux/module.h> #include <linux/of.h> #include <linux/of_device.h> @@ -63,10 +59,10 @@ #define FLEXCAN_MCR_LPRIO_EN BIT(13) #define FLEXCAN_MCR_AEN BIT(12) #define FLEXCAN_MCR_MAXMB(x) ((x) & 0x7f) -#define FLEXCAN_MCR_IDAM_A (0 << 8) -#define FLEXCAN_MCR_IDAM_B (1 << 8) -#define FLEXCAN_MCR_IDAM_C (2 << 8) -#define FLEXCAN_MCR_IDAM_D (3 << 8) +#define FLEXCAN_MCR_IDAM_A (0x0 << 8) +#define FLEXCAN_MCR_IDAM_B (0x1 << 8) +#define FLEXCAN_MCR_IDAM_C (0x2 << 8) +#define FLEXCAN_MCR_IDAM_D (0x3 << 8) /* FLEXCAN control register (CANCTRL) bits */ #define FLEXCAN_CTRL_PRESDIV(x) (((x) & 0xff) << 24) @@ -161,7 +157,7 @@ #define FLEXCAN_MB_CODE_RX_INACTIVE (0x0 << 24) #define FLEXCAN_MB_CODE_RX_EMPTY (0x4 << 24) #define FLEXCAN_MB_CODE_RX_FULL (0x2 << 24) -#define FLEXCAN_MB_CODE_RX_OVERRRUN (0x6 << 24) +#define FLEXCAN_MB_CODE_RX_OVERRUN (0x6 << 24) #define FLEXCAN_MB_CODE_RX_RANSWER (0xa << 24) #define FLEXCAN_MB_CODE_TX_INACTIVE (0x8 << 24) @@ -175,12 +171,9 @@ #define FLEXCAN_MB_CNT_LENGTH(x) (((x) & 0xf) << 16) #define FLEXCAN_MB_CNT_TIMESTAMP(x) ((x) & 0xffff) -#define FLEXCAN_MB_CODE_MASK (0xf0ffffff) +#define FLEXCAN_TIMEOUT_US (50) -#define FLEXCAN_TIMEOUT_US (50) - -/* - * FLEXCAN hardware feature flags +/* FLEXCAN hardware feature flags * * Below is some version info we got: * SOC Version IP-Version Glitch- [TR]WRN_INT Memory err RTR re- @@ -194,9 +187,9 @@ * * Some SOCs do not have the RX_WARN & TX_WARN interrupt line connected. */ -#define FLEXCAN_HAS_V10_FEATURES BIT(1) /* For core version >= 10 */ -#define FLEXCAN_HAS_BROKEN_ERR_STATE BIT(2) /* [TR]WRN_INT not connected */ -#define FLEXCAN_HAS_MECR_FEATURES BIT(3) /* Memory error detection */ +#define FLEXCAN_QUIRK_BROKEN_ERR_STATE BIT(1) /* [TR]WRN_INT not connected */ +#define FLEXCAN_QUIRK_DISABLE_RXFG BIT(2) /* Disable RX FIFO Global mask */ +#define FLEXCAN_QUIRK_DISABLE_MECR BIT(3) /* Disble Memory error detection */ /* Structure of the message buffer */ struct flexcan_mb { @@ -228,7 +221,7 @@ struct flexcan_regs { u32 rxfgmask; /* 0x48 */ u32 rxfir; /* 0x4c */ u32 _reserved3[12]; /* 0x50 */ - struct flexcan_mb cantxfg[64]; /* 0x80 */ + struct flexcan_mb mb[64]; /* 0x80 */ /* FIFO-mode: * MB * 0x080...0x08f 0 RX message buffer @@ -236,7 +229,7 @@ struct flexcan_regs { * 0x0e0...0x0ff 6-7 8 entry ID table * (mx25, mx28, mx35, mx53) * 0x0e0...0x2df 6-7..37 8..128 entry ID table - * size conf'ed via ctrl2::RFFN + * size conf'ed via ctrl2::RFFN * (mx6, vf610) */ u32 _reserved4[408]; @@ -251,14 +244,14 @@ struct flexcan_regs { }; struct flexcan_devtype_data { - u32 features; /* hardware controller features */ + u32 quirks; /* quirks needed for different IP cores */ }; struct flexcan_priv { struct can_priv can; struct napi_struct napi; - void __iomem *base; + struct flexcan_regs __iomem *regs; u32 reg_esr; u32 reg_ctrl_default; @@ -270,14 +263,17 @@ struct flexcan_priv { }; static struct flexcan_devtype_data fsl_p1010_devtype_data = { - .features = FLEXCAN_HAS_BROKEN_ERR_STATE, + .quirks = FLEXCAN_QUIRK_BROKEN_ERR_STATE, }; + static struct flexcan_devtype_data fsl_imx28_devtype_data; + static struct flexcan_devtype_data fsl_imx6q_devtype_data = { - .features = FLEXCAN_HAS_V10_FEATURES, + .quirks = FLEXCAN_QUIRK_DISABLE_RXFG, }; + static struct flexcan_devtype_data fsl_vf610_devtype_data = { - .features = FLEXCAN_HAS_V10_FEATURES | FLEXCAN_HAS_MECR_FEATURES, + .quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_DISABLE_MECR, }; static const struct can_bittiming_const flexcan_bittiming_const = { @@ -292,11 +288,10 @@ static const struct can_bittiming_const flexcan_bittiming_const = { .brp_inc = 1, }; -/* - * Abstract off the read/write for arm versus ppc. This +/* Abstract off the read/write for arm versus ppc. This * assumes that PPC uses big-endian registers and everything * else uses little-endian registers, independent of CPU - * endianess. + * endianness. */ #if defined(CONFIG_PPC) static inline u32 flexcan_read(void __iomem *addr) @@ -345,7 +340,7 @@ static inline int flexcan_has_and_handle_berr(const struct flexcan_priv *priv, static int flexcan_chip_enable(struct flexcan_priv *priv) { - struct flexcan_regs __iomem *regs = priv->base; + struct flexcan_regs __iomem *regs = priv->regs; unsigned int timeout = FLEXCAN_TIMEOUT_US / 10; u32 reg; @@ -364,7 +359,7 @@ static int flexcan_chip_enable(struct flexcan_priv *priv) static int flexcan_chip_disable(struct flexcan_priv *priv) { - struct flexcan_regs __iomem *regs = priv->base; + struct flexcan_regs __iomem *regs = priv->regs; unsigned int timeout = FLEXCAN_TIMEOUT_US / 10; u32 reg; @@ -383,7 +378,7 @@ static int flexcan_chip_disable(struct flexcan_priv *priv) static int flexcan_chip_freeze(struct flexcan_priv *priv) { - struct flexcan_regs __iomem *regs = priv->base; + struct flexcan_regs __iomem *regs = priv->regs; unsigned int timeout = 1000 * 1000 * 10 / priv->can.bittiming.bitrate; u32 reg; @@ -402,7 +397,7 @@ static int flexcan_chip_freeze(struct flexcan_priv *priv) static int flexcan_chip_unfreeze(struct flexcan_priv *priv) { - struct flexcan_regs __iomem *regs = priv->base; + struct flexcan_regs __iomem *regs = priv->regs; unsigned int timeout = FLEXCAN_TIMEOUT_US / 10; u32 reg; @@ -421,7 +416,7 @@ static int flexcan_chip_unfreeze(struct flexcan_priv *priv) static int flexcan_chip_softreset(struct flexcan_priv *priv) { - struct flexcan_regs __iomem *regs = priv->base; + struct flexcan_regs __iomem *regs = priv->regs; unsigned int timeout = FLEXCAN_TIMEOUT_US / 10; flexcan_write(FLEXCAN_MCR_SOFTRST, ®s->mcr); @@ -434,12 +429,11 @@ static int flexcan_chip_softreset(struct flexcan_priv *priv) return 0; } - static int __flexcan_get_berr_counter(const struct net_device *dev, struct can_berr_counter *bec) { const struct flexcan_priv *priv = netdev_priv(dev); - struct flexcan_regs __iomem *regs = priv->base; + struct flexcan_regs __iomem *regs = priv->regs; u32 reg = flexcan_read(®s->ecr); bec->txerr = (reg >> 0) & 0xff; @@ -474,9 +468,10 @@ static int flexcan_get_berr_counter(const struct net_device *dev, static int flexcan_start_xmit(struct sk_buff *skb, struct net_device *dev) { const struct flexcan_priv *priv = netdev_priv(dev); - struct flexcan_regs __iomem *regs = priv->base; + struct flexcan_regs __iomem *regs = priv->regs; struct can_frame *cf = (struct can_frame *)skb->data; u32 can_id; + u32 data; u32 ctrl = FLEXCAN_MB_CODE_TX_DATA | (cf->can_dlc << 16); if (can_dropped_invalid_skb(dev, skb)) @@ -495,26 +490,26 @@ static int flexcan_start_xmit(struct sk_buff *skb, struct net_device *dev) ctrl |= FLEXCAN_MB_CNT_RTR; if (cf->can_dlc > 0) { - u32 data = be32_to_cpup((__be32 *)&cf->data[0]); - flexcan_write(data, ®s->cantxfg[FLEXCAN_TX_BUF_ID].data[0]); + data = be32_to_cpup((__be32 *)&cf->data[0]); + flexcan_write(data, ®s->mb[FLEXCAN_TX_BUF_ID].data[0]); } if (cf->can_dlc > 3) { - u32 data = be32_to_cpup((__be32 *)&cf->data[4]); - flexcan_write(data, ®s->cantxfg[FLEXCAN_TX_BUF_ID].data[1]); + data = be32_to_cpup((__be32 *)&cf->data[4]); + flexcan_write(data, ®s->mb[FLEXCAN_TX_BUF_ID].data[1]); } can_put_echo_skb(skb, dev, 0); - flexcan_write(can_id, ®s->cantxfg[FLEXCAN_TX_BUF_ID].can_id); - flexcan_write(ctrl, ®s->cantxfg[FLEXCAN_TX_BUF_ID].can_ctrl); + flexcan_write(can_id, ®s->mb[FLEXCAN_TX_BUF_ID].can_id); + flexcan_write(ctrl, ®s->mb[FLEXCAN_TX_BUF_ID].can_ctrl); /* Errata ERR005829 step8: * Write twice INACTIVE(0x8) code to first MB. */ flexcan_write(FLEXCAN_MB_CODE_TX_INACTIVE, - ®s->cantxfg[FLEXCAN_TX_BUF_RESERVED].can_ctrl); + ®s->mb[FLEXCAN_TX_BUF_RESERVED].can_ctrl); flexcan_write(FLEXCAN_MB_CODE_TX_INACTIVE, - ®s->cantxfg[FLEXCAN_TX_BUF_RESERVED].can_ctrl); + ®s->mb[FLEXCAN_TX_BUF_RESERVED].can_ctrl); return NETDEV_TX_OK; } @@ -597,14 +592,14 @@ static int flexcan_poll_state(struct net_device *dev, u32 reg_esr) flt = reg_esr & FLEXCAN_ESR_FLT_CONF_MASK; if (likely(flt == FLEXCAN_ESR_FLT_CONF_ACTIVE)) { tx_state = unlikely(reg_esr & FLEXCAN_ESR_TX_WRN) ? - CAN_STATE_ERROR_WARNING : CAN_STATE_ERROR_ACTIVE; + CAN_STATE_ERROR_WARNING : CAN_STATE_ERROR_ACTIVE; rx_state = unlikely(reg_esr & FLEXCAN_ESR_RX_WRN) ? - CAN_STATE_ERROR_WARNING : CAN_STATE_ERROR_ACTIVE; + CAN_STATE_ERROR_WARNING : CAN_STATE_ERROR_ACTIVE; new_state = max(tx_state, rx_state); } else { __flexcan_get_berr_counter(dev, &bec); new_state = flt == FLEXCAN_ESR_FLT_CONF_PASSIVE ? - CAN_STATE_ERROR_PASSIVE : CAN_STATE_BUS_OFF; + CAN_STATE_ERROR_PASSIVE : CAN_STATE_BUS_OFF; rx_state = bec.rxerr >= bec.txerr ? new_state : 0; tx_state = bec.rxerr <= bec.txerr ? new_state : 0; } @@ -633,8 +628,8 @@ static void flexcan_read_fifo(const struct net_device *dev, struct can_frame *cf) { const struct flexcan_priv *priv = netdev_priv(dev); - struct flexcan_regs __iomem *regs = priv->base; - struct flexcan_mb __iomem *mb = ®s->cantxfg[0]; + struct flexcan_regs __iomem *regs = priv->regs; + struct flexcan_mb __iomem *mb = ®s->mb[0]; u32 reg_ctrl, reg_id; reg_ctrl = flexcan_read(&mb->can_ctrl); @@ -683,12 +678,11 @@ static int flexcan_poll(struct napi_struct *napi, int quota) { struct net_device *dev = napi->dev; const struct flexcan_priv *priv = netdev_priv(dev); - struct flexcan_regs __iomem *regs = priv->base; + struct flexcan_regs __iomem *regs = priv->regs; u32 reg_iflag1, reg_esr; int work_done = 0; - /* - * The error bits are cleared on read, + /* The error bits are cleared on read, * use saved value from irq handler. */ reg_esr = flexcan_read(®s->esr) | priv->reg_esr; @@ -723,17 +717,17 @@ static irqreturn_t flexcan_irq(int irq, void *dev_id) struct net_device *dev = dev_id; struct net_device_stats *stats = &dev->stats; struct flexcan_priv *priv = netdev_priv(dev); - struct flexcan_regs __iomem *regs = priv->base; + struct flexcan_regs __iomem *regs = priv->regs; u32 reg_iflag1, reg_esr; reg_iflag1 = flexcan_read(®s->iflag1); reg_esr = flexcan_read(®s->esr); + /* ACK all bus error and state change IRQ sources */ if (reg_esr & FLEXCAN_ESR_ALL_INT) flexcan_write(reg_esr & FLEXCAN_ESR_ALL_INT, ®s->esr); - /* - * schedule NAPI in case of: + /* schedule NAPI in case of: * - rx IRQ * - state change IRQ * - bus error IRQ and bus error reporting is activated @@ -741,15 +735,14 @@ static irqreturn_t flexcan_irq(int irq, void *dev_id) if ((reg_iflag1 & FLEXCAN_IFLAG_RX_FIFO_AVAILABLE) || (reg_esr & FLEXCAN_ESR_ERR_STATE) || flexcan_has_and_handle_berr(priv, reg_esr)) { - /* - * The error bits are cleared on read, + /* The error bits are cleared on read, * save them for later use. */ priv->reg_esr = reg_esr & FLEXCAN_ESR_ERR_BUS; flexcan_write(FLEXCAN_IFLAG_DEFAULT & - ~FLEXCAN_IFLAG_RX_FIFO_AVAILABLE, ®s->imask1); + ~FLEXCAN_IFLAG_RX_FIFO_AVAILABLE, ®s->imask1); flexcan_write(priv->reg_ctrl_default & ~FLEXCAN_CTRL_ERR_ALL, - ®s->ctrl); + ®s->ctrl); napi_schedule(&priv->napi); } @@ -765,9 +758,10 @@ static irqreturn_t flexcan_irq(int irq, void *dev_id) stats->tx_bytes += can_get_echo_skb(dev, 0); stats->tx_packets++; can_led_event(dev, CAN_LED_EVENT_TX); - /* after sending a RTR frame mailbox is in RX mode */ + + /* after sending a RTR frame MB is in RX mode */ flexcan_write(FLEXCAN_MB_CODE_TX_INACTIVE, - ®s->cantxfg[FLEXCAN_TX_BUF_ID].can_ctrl); + ®s->mb[FLEXCAN_TX_BUF_ID].can_ctrl); flexcan_write((1 << FLEXCAN_TX_BUF_ID), ®s->iflag1); netif_wake_queue(dev); } @@ -779,7 +773,7 @@ static void flexcan_set_bittiming(struct net_device *dev) { const struct flexcan_priv *priv = netdev_priv(dev); const struct can_bittiming *bt = &priv->can.bittiming; - struct flexcan_regs __iomem *regs = priv->base; + struct flexcan_regs __iomem *regs = priv->regs; u32 reg; reg = flexcan_read(®s->ctrl); @@ -813,8 +807,7 @@ static void flexcan_set_bittiming(struct net_device *dev) flexcan_read(®s->mcr), flexcan_read(®s->ctrl)); } -/* - * flexcan_chip_start +/* flexcan_chip_start * * this functions is entered with clocks enabled * @@ -822,7 +815,7 @@ static void flexcan_set_bittiming(struct net_device *dev) static int flexcan_chip_start(struct net_device *dev) { struct flexcan_priv *priv = netdev_priv(dev); - struct flexcan_regs __iomem *regs = priv->base; + struct flexcan_regs __iomem *regs = priv->regs; u32 reg_mcr, reg_ctrl, reg_ctrl2, reg_mecr; int err, i; @@ -838,29 +831,26 @@ static int flexcan_chip_start(struct net_device *dev) flexcan_set_bittiming(dev); - /* - * MCR + /* MCR * * enable freeze * enable fifo * halt now * only supervisor access * enable warning int - * choose format C * disable local echo - * + * choose format C + * set max mailbox number */ reg_mcr = flexcan_read(®s->mcr); reg_mcr &= ~FLEXCAN_MCR_MAXMB(0xff); reg_mcr |= FLEXCAN_MCR_FRZ | FLEXCAN_MCR_FEN | FLEXCAN_MCR_HALT | - FLEXCAN_MCR_SUPV | FLEXCAN_MCR_WRN_EN | - FLEXCAN_MCR_IDAM_C | FLEXCAN_MCR_SRX_DIS | - FLEXCAN_MCR_MAXMB(FLEXCAN_TX_BUF_ID); + FLEXCAN_MCR_SUPV | FLEXCAN_MCR_WRN_EN | FLEXCAN_MCR_SRX_DIS | + FLEXCAN_MCR_IDAM_C | FLEXCAN_MCR_MAXMB(FLEXCAN_TX_BUF_ID); netdev_dbg(dev, "%s: writing mcr=0x%08x", __func__, reg_mcr); flexcan_write(reg_mcr, ®s->mcr); - /* - * CTRL + /* CTRL * * disable timer sync feature * @@ -875,12 +865,12 @@ static int flexcan_chip_start(struct net_device *dev) reg_ctrl &= ~FLEXCAN_CTRL_TSYN; reg_ctrl |= FLEXCAN_CTRL_BOFF_REC | FLEXCAN_CTRL_LBUF | FLEXCAN_CTRL_ERR_STATE; - /* - * enable the "error interrupt" (FLEXCAN_CTRL_ERR_MSK), + + /* enable the "error interrupt" (FLEXCAN_CTRL_ERR_MSK), * on most Flexcan cores, too. Otherwise we don't get * any error warning or passive interrupts. */ - if (priv->devtype_data->features & FLEXCAN_HAS_BROKEN_ERR_STATE || + if (priv->devtype_data->quirks & FLEXCAN_QUIRK_BROKEN_ERR_STATE || priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING) reg_ctrl |= FLEXCAN_CTRL_ERR_MSK; else @@ -888,41 +878,41 @@ static int flexcan_chip_start(struct net_device *dev) /* save for later use */ priv->reg_ctrl_default = reg_ctrl; + /* leave interrupts disabled for now */ + reg_ctrl &= ~FLEXCAN_CTRL_ERR_ALL; netdev_dbg(dev, "%s: writing ctrl=0x%08x", __func__, reg_ctrl); flexcan_write(reg_ctrl, ®s->ctrl); /* clear and invalidate all mailboxes first */ - for (i = FLEXCAN_TX_BUF_ID; i < ARRAY_SIZE(regs->cantxfg); i++) { + for (i = FLEXCAN_TX_BUF_ID; i < ARRAY_SIZE(regs->mb); i++) { flexcan_write(FLEXCAN_MB_CODE_RX_INACTIVE, - ®s->cantxfg[i].can_ctrl); + ®s->mb[i].can_ctrl); } /* Errata ERR005829: mark first TX mailbox as INACTIVE */ flexcan_write(FLEXCAN_MB_CODE_TX_INACTIVE, - ®s->cantxfg[FLEXCAN_TX_BUF_RESERVED].can_ctrl); + ®s->mb[FLEXCAN_TX_BUF_RESERVED].can_ctrl); /* mark TX mailbox as INACTIVE */ flexcan_write(FLEXCAN_MB_CODE_TX_INACTIVE, - ®s->cantxfg[FLEXCAN_TX_BUF_ID].can_ctrl); + ®s->mb[FLEXCAN_TX_BUF_ID].can_ctrl); /* acceptance mask/acceptance code (accept everything) */ flexcan_write(0x0, ®s->rxgmask); flexcan_write(0x0, ®s->rx14mask); flexcan_write(0x0, ®s->rx15mask); - if (priv->devtype_data->features & FLEXCAN_HAS_V10_FEATURES) + if (priv->devtype_data->quirks & FLEXCAN_QUIRK_DISABLE_RXFG) flexcan_write(0x0, ®s->rxfgmask); - /* - * On Vybrid, disable memory error detection interrupts + /* On Vybrid, disable memory error detection interrupts * and freeze mode. * This also works around errata e5295 which generates * false positive memory errors and put the device in * freeze mode. */ - if (priv->devtype_data->features & FLEXCAN_HAS_MECR_FEATURES) { - /* - * Follow the protocol as described in "Detection + if (priv->devtype_data->quirks & FLEXCAN_QUIRK_DISABLE_MECR) { + /* Follow the protocol as described in "Detection * and Correction of Memory Errors" to write to * MECR register */ @@ -934,7 +924,7 @@ static int flexcan_chip_start(struct net_device *dev) reg_mecr &= ~FLEXCAN_MECR_ECRWRDIS; flexcan_write(reg_mecr, ®s->mecr); reg_mecr &= ~(FLEXCAN_MECR_NCEFAFRZ | FLEXCAN_MECR_HANCEI_MSK | - FLEXCAN_MECR_FANCEI_MSK); + FLEXCAN_MECR_FANCEI_MSK); flexcan_write(reg_mecr, ®s->mecr); } @@ -949,8 +939,11 @@ static int flexcan_chip_start(struct net_device *dev) priv->can.state = CAN_STATE_ERROR_ACTIVE; - /* enable FIFO interrupts */ + /* enable interrupts atomically */ + disable_irq(dev->irq); + flexcan_write(priv->reg_ctrl_default, ®s->ctrl); flexcan_write(FLEXCAN_IFLAG_DEFAULT, ®s->imask1); + enable_irq(dev->irq); /* print chip status */ netdev_dbg(dev, "%s: reading mcr=0x%08x ctrl=0x%08x\n", __func__, @@ -965,16 +958,14 @@ static int flexcan_chip_start(struct net_device *dev) return err; } -/* - * flexcan_chip_stop +/* flexcan_chip_stop * * this functions is entered with clocks enabled - * */ static void flexcan_chip_stop(struct net_device *dev) { struct flexcan_priv *priv = netdev_priv(dev); - struct flexcan_regs __iomem *regs = priv->base; + struct flexcan_regs __iomem *regs = priv->regs; /* freeze + disable module */ flexcan_chip_freeze(priv); @@ -987,8 +978,6 @@ static void flexcan_chip_stop(struct net_device *dev) flexcan_transceiver_disable(priv); priv->can.state = CAN_STATE_STOPPED; - - return; } static int flexcan_open(struct net_device *dev) @@ -1085,7 +1074,7 @@ static const struct net_device_ops flexcan_netdev_ops = { static int register_flexcandev(struct net_device *dev) { struct flexcan_priv *priv = netdev_priv(dev); - struct flexcan_regs __iomem *regs = priv->base; + struct flexcan_regs __iomem *regs = priv->regs; u32 reg, err; err = clk_prepare_enable(priv->clk_ipg); @@ -1114,8 +1103,7 @@ static int register_flexcandev(struct net_device *dev) FLEXCAN_MCR_FEN | FLEXCAN_MCR_SUPV; flexcan_write(reg, ®s->mcr); - /* - * Currently we only support newer versions of this core + /* Currently we only support newer versions of this core * featuring a RX FIFO. Older cores found on some Coldfire * derivates are not yet supported. */ @@ -1168,7 +1156,7 @@ static int flexcan_probe(struct platform_device *pdev) struct regulator *reg_xceiver; struct resource *mem; struct clk *clk_ipg = NULL, *clk_per = NULL; - void __iomem *base; + struct flexcan_regs __iomem *regs; int err, irq; u32 clock_freq = 0; @@ -1180,7 +1168,7 @@ static int flexcan_probe(struct platform_device *pdev) if (pdev->dev.of_node) of_property_read_u32(pdev->dev.of_node, - "clock-frequency", &clock_freq); + "clock-frequency", &clock_freq); if (!clock_freq) { clk_ipg = devm_clk_get(&pdev->dev, "ipg"); @@ -1202,9 +1190,9 @@ static int flexcan_probe(struct platform_device *pdev) if (irq <= 0) return -ENODEV; - base = devm_ioremap_resource(&pdev->dev, mem); - if (IS_ERR(base)) - return PTR_ERR(base); + regs = devm_ioremap_resource(&pdev->dev, mem); + if (IS_ERR(regs)) + return PTR_ERR(regs); of_id = of_match_device(flexcan_of_match, &pdev->dev); if (of_id) { @@ -1232,12 +1220,11 @@ static int flexcan_probe(struct platform_device *pdev) priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK | CAN_CTRLMODE_LISTENONLY | CAN_CTRLMODE_3_SAMPLES | CAN_CTRLMODE_BERR_REPORTING; - priv->base = base; + priv->regs = regs; priv->clk_ipg = clk_ipg; priv->clk_per = clk_per; priv->pdata = dev_get_platdata(&pdev->dev); priv->devtype_data = devtype_data; - priv->reg_xceiver = reg_xceiver; netif_napi_add(dev, &priv->napi, flexcan_poll, FLEXCAN_NAPI_WEIGHT); @@ -1254,7 +1241,7 @@ static int flexcan_probe(struct platform_device *pdev) devm_can_led_init(dev); dev_info(&pdev->dev, "device registered (reg_base=%p, irq=%d)\n", - priv->base, dev->irq); + priv->regs, dev->irq); return 0; diff --git a/drivers/net/can/sun4i_can.c b/drivers/net/can/sun4i_can.c new file mode 100644 index 000000000000..10d8497635e8 --- /dev/null +++ b/drivers/net/can/sun4i_can.c @@ -0,0 +1,857 @@ +/* + * sun4i_can.c - CAN bus controller driver for Allwinner SUN4I&SUN7I based SoCs + * + * Copyright (C) 2013 Peter Chen + * Copyright (C) 2015 Gerhard Bertelsmann + * All rights reserved. + * + * Parts of this software are based on (derived from) the SJA1000 code by: + * Copyright (C) 2014 Oliver Hartkopp <oliver.hartkopp@volkswagen.de> + * Copyright (C) 2007 Wolfgang Grandegger <wg@grandegger.com> + * Copyright (C) 2002-2007 Volkswagen Group Electronic Research + * Copyright (C) 2003 Matthias Brukner, Trajet Gmbh, Rebenring 33, + * 38106 Braunschweig, GERMANY + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of Volkswagen nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * Alternatively, provided that this notice is retained in full, this + * software may be distributed under the terms of the GNU General + * Public License ("GPL") version 2, in which case the provisions of the + * GPL apply INSTEAD OF those given above. + * + * The provided data structures and external interfaces from this code + * are not restricted to be used by modules with a GPL compatible license. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH + * DAMAGE. + * + */ + +#include <linux/netdevice.h> +#include <linux/can.h> +#include <linux/can/dev.h> +#include <linux/can/error.h> +#include <linux/can/led.h> +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/interrupt.h> +#include <linux/init.h> +#include <linux/io.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <linux/platform_device.h> + +#define DRV_NAME "sun4i_can" + +/* Registers address (physical base address 0x01C2BC00) */ +#define SUN4I_REG_MSEL_ADDR 0x0000 /* CAN Mode Select */ +#define SUN4I_REG_CMD_ADDR 0x0004 /* CAN Command */ +#define SUN4I_REG_STA_ADDR 0x0008 /* CAN Status */ +#define SUN4I_REG_INT_ADDR 0x000c /* CAN Interrupt Flag */ +#define SUN4I_REG_INTEN_ADDR 0x0010 /* CAN Interrupt Enable */ +#define SUN4I_REG_BTIME_ADDR 0x0014 /* CAN Bus Timing 0 */ +#define SUN4I_REG_TEWL_ADDR 0x0018 /* CAN Tx Error Warning Limit */ +#define SUN4I_REG_ERRC_ADDR 0x001c /* CAN Error Counter */ +#define SUN4I_REG_RMCNT_ADDR 0x0020 /* CAN Receive Message Counter */ +#define SUN4I_REG_RBUFSA_ADDR 0x0024 /* CAN Receive Buffer Start Address */ +#define SUN4I_REG_BUF0_ADDR 0x0040 /* CAN Tx/Rx Buffer 0 */ +#define SUN4I_REG_BUF1_ADDR 0x0044 /* CAN Tx/Rx Buffer 1 */ +#define SUN4I_REG_BUF2_ADDR 0x0048 /* CAN Tx/Rx Buffer 2 */ +#define SUN4I_REG_BUF3_ADDR 0x004c /* CAN Tx/Rx Buffer 3 */ +#define SUN4I_REG_BUF4_ADDR 0x0050 /* CAN Tx/Rx Buffer 4 */ +#define SUN4I_REG_BUF5_ADDR 0x0054 /* CAN Tx/Rx Buffer 5 */ +#define SUN4I_REG_BUF6_ADDR 0x0058 /* CAN Tx/Rx Buffer 6 */ +#define SUN4I_REG_BUF7_ADDR 0x005c /* CAN Tx/Rx Buffer 7 */ +#define SUN4I_REG_BUF8_ADDR 0x0060 /* CAN Tx/Rx Buffer 8 */ +#define SUN4I_REG_BUF9_ADDR 0x0064 /* CAN Tx/Rx Buffer 9 */ +#define SUN4I_REG_BUF10_ADDR 0x0068 /* CAN Tx/Rx Buffer 10 */ +#define SUN4I_REG_BUF11_ADDR 0x006c /* CAN Tx/Rx Buffer 11 */ +#define SUN4I_REG_BUF12_ADDR 0x0070 /* CAN Tx/Rx Buffer 12 */ +#define SUN4I_REG_ACPC_ADDR 0x0040 /* CAN Acceptance Code 0 */ +#define SUN4I_REG_ACPM_ADDR 0x0044 /* CAN Acceptance Mask 0 */ +#define SUN4I_REG_RBUF_RBACK_START_ADDR 0x0180 /* CAN transmit buffer start */ +#define SUN4I_REG_RBUF_RBACK_END_ADDR 0x01b0 /* CAN transmit buffer end */ + +/* Controller Register Description */ + +/* mode select register (r/w) + * offset:0x0000 default:0x0000_0001 + */ +#define SUN4I_MSEL_SLEEP_MODE (0x01 << 4) /* write in reset mode */ +#define SUN4I_MSEL_WAKE_UP (0x00 << 4) +#define SUN4I_MSEL_SINGLE_FILTER (0x01 << 3) /* write in reset mode */ +#define SUN4I_MSEL_DUAL_FILTERS (0x00 << 3) +#define SUN4I_MSEL_LOOPBACK_MODE BIT(2) +#define SUN4I_MSEL_LISTEN_ONLY_MODE BIT(1) +#define SUN4I_MSEL_RESET_MODE BIT(0) + +/* command register (w) + * offset:0x0004 default:0x0000_0000 + */ +#define SUN4I_CMD_BUS_OFF_REQ BIT(5) +#define SUN4I_CMD_SELF_RCV_REQ BIT(4) +#define SUN4I_CMD_CLEAR_OR_FLAG BIT(3) +#define SUN4I_CMD_RELEASE_RBUF BIT(2) +#define SUN4I_CMD_ABORT_REQ BIT(1) +#define SUN4I_CMD_TRANS_REQ BIT(0) + +/* status register (r) + * offset:0x0008 default:0x0000_003c + */ +#define SUN4I_STA_BIT_ERR (0x00 << 22) +#define SUN4I_STA_FORM_ERR (0x01 << 22) +#define SUN4I_STA_STUFF_ERR (0x02 << 22) +#define SUN4I_STA_OTHER_ERR (0x03 << 22) +#define SUN4I_STA_MASK_ERR (0x03 << 22) +#define SUN4I_STA_ERR_DIR BIT(21) +#define SUN4I_STA_ERR_SEG_CODE (0x1f << 16) +#define SUN4I_STA_START (0x03 << 16) +#define SUN4I_STA_ID28_21 (0x02 << 16) +#define SUN4I_STA_ID20_18 (0x06 << 16) +#define SUN4I_STA_SRTR (0x04 << 16) +#define SUN4I_STA_IDE (0x05 << 16) +#define SUN4I_STA_ID17_13 (0x07 << 16) +#define SUN4I_STA_ID12_5 (0x0f << 16) +#define SUN4I_STA_ID4_0 (0x0e << 16) +#define SUN4I_STA_RTR (0x0c << 16) +#define SUN4I_STA_RB1 (0x0d << 16) +#define SUN4I_STA_RB0 (0x09 << 16) +#define SUN4I_STA_DLEN (0x0b << 16) +#define SUN4I_STA_DATA_FIELD (0x0a << 16) +#define SUN4I_STA_CRC_SEQUENCE (0x08 << 16) +#define SUN4I_STA_CRC_DELIMITER (0x18 << 16) +#define SUN4I_STA_ACK (0x19 << 16) +#define SUN4I_STA_ACK_DELIMITER (0x1b << 16) +#define SUN4I_STA_END (0x1a << 16) +#define SUN4I_STA_INTERMISSION (0x12 << 16) +#define SUN4I_STA_ACTIVE_ERROR (0x11 << 16) +#define SUN4I_STA_PASSIVE_ERROR (0x16 << 16) +#define SUN4I_STA_TOLERATE_DOMINANT_BITS (0x13 << 16) +#define SUN4I_STA_ERROR_DELIMITER (0x17 << 16) +#define SUN4I_STA_OVERLOAD (0x1c << 16) +#define SUN4I_STA_BUS_OFF BIT(7) +#define SUN4I_STA_ERR_STA BIT(6) +#define SUN4I_STA_TRANS_BUSY BIT(5) +#define SUN4I_STA_RCV_BUSY BIT(4) +#define SUN4I_STA_TRANS_OVER BIT(3) +#define SUN4I_STA_TBUF_RDY BIT(2) +#define SUN4I_STA_DATA_ORUN BIT(1) +#define SUN4I_STA_RBUF_RDY BIT(0) + +/* interrupt register (r) + * offset:0x000c default:0x0000_0000 + */ +#define SUN4I_INT_BUS_ERR BIT(7) +#define SUN4I_INT_ARB_LOST BIT(6) +#define SUN4I_INT_ERR_PASSIVE BIT(5) +#define SUN4I_INT_WAKEUP BIT(4) +#define SUN4I_INT_DATA_OR BIT(3) +#define SUN4I_INT_ERR_WRN BIT(2) +#define SUN4I_INT_TBUF_VLD BIT(1) +#define SUN4I_INT_RBUF_VLD BIT(0) + +/* interrupt enable register (r/w) + * offset:0x0010 default:0x0000_0000 + */ +#define SUN4I_INTEN_BERR BIT(7) +#define SUN4I_INTEN_ARB_LOST BIT(6) +#define SUN4I_INTEN_ERR_PASSIVE BIT(5) +#define SUN4I_INTEN_WAKEUP BIT(4) +#define SUN4I_INTEN_OR BIT(3) +#define SUN4I_INTEN_ERR_WRN BIT(2) +#define SUN4I_INTEN_TX BIT(1) +#define SUN4I_INTEN_RX BIT(0) + +/* error code */ +#define SUN4I_ERR_INRCV (0x1 << 5) +#define SUN4I_ERR_INTRANS (0x0 << 5) + +/* filter mode */ +#define SUN4I_FILTER_CLOSE 0 +#define SUN4I_SINGLE_FLTER_MODE 1 +#define SUN4I_DUAL_FILTER_MODE 2 + +/* message buffer flags */ +#define SUN4I_MSG_EFF_FLAG BIT(7) +#define SUN4I_MSG_RTR_FLAG BIT(6) + +/* max. number of interrupts handled in ISR */ +#define SUN4I_CAN_MAX_IRQ 20 +#define SUN4I_MODE_MAX_RETRIES 100 + +struct sun4ican_priv { + struct can_priv can; + void __iomem *base; + struct clk *clk; + spinlock_t cmdreg_lock; /* lock for concurrent cmd register writes */ +}; + +static const struct can_bittiming_const sun4ican_bittiming_const = { + .name = DRV_NAME, + .tseg1_min = 1, + .tseg1_max = 16, + .tseg2_min = 1, + .tseg2_max = 8, + .sjw_max = 4, + .brp_min = 1, + .brp_max = 64, + .brp_inc = 1, +}; + +static void sun4i_can_write_cmdreg(struct sun4ican_priv *priv, u8 val) +{ + unsigned long flags; + + spin_lock_irqsave(&priv->cmdreg_lock, flags); + writel(val, priv->base + SUN4I_REG_CMD_ADDR); + spin_unlock_irqrestore(&priv->cmdreg_lock, flags); +} + +static int set_normal_mode(struct net_device *dev) +{ + struct sun4ican_priv *priv = netdev_priv(dev); + int retry = SUN4I_MODE_MAX_RETRIES; + u32 mod_reg_val = 0; + + do { + mod_reg_val = readl(priv->base + SUN4I_REG_MSEL_ADDR); + mod_reg_val &= ~SUN4I_MSEL_RESET_MODE; + writel(mod_reg_val, priv->base + SUN4I_REG_MSEL_ADDR); + } while (retry-- && (mod_reg_val & SUN4I_MSEL_RESET_MODE)); + + if (readl(priv->base + SUN4I_REG_MSEL_ADDR) & SUN4I_MSEL_RESET_MODE) { + netdev_err(dev, + "setting controller into normal mode failed!\n"); + return -ETIMEDOUT; + } + + return 0; +} + +static int set_reset_mode(struct net_device *dev) +{ + struct sun4ican_priv *priv = netdev_priv(dev); + int retry = SUN4I_MODE_MAX_RETRIES; + u32 mod_reg_val = 0; + + do { + mod_reg_val = readl(priv->base + SUN4I_REG_MSEL_ADDR); + mod_reg_val |= SUN4I_MSEL_RESET_MODE; + writel(mod_reg_val, priv->base + SUN4I_REG_MSEL_ADDR); + } while (retry-- && !(mod_reg_val & SUN4I_MSEL_RESET_MODE)); + + if (!(readl(priv->base + SUN4I_REG_MSEL_ADDR) & + SUN4I_MSEL_RESET_MODE)) { + netdev_err(dev, "setting controller into reset mode failed!\n"); + return -ETIMEDOUT; + } + + return 0; +} + +/* bittiming is called in reset_mode only */ +static int sun4ican_set_bittiming(struct net_device *dev) +{ + struct sun4ican_priv *priv = netdev_priv(dev); + struct can_bittiming *bt = &priv->can.bittiming; + u32 cfg; + + cfg = ((bt->brp - 1) & 0x3FF) | + (((bt->sjw - 1) & 0x3) << 14) | + (((bt->prop_seg + bt->phase_seg1 - 1) & 0xf) << 16) | + (((bt->phase_seg2 - 1) & 0x7) << 20); + if (priv->can.ctrlmode & CAN_CTRLMODE_3_SAMPLES) + cfg |= 0x800000; + + netdev_dbg(dev, "setting BITTIMING=0x%08x\n", cfg); + writel(cfg, priv->base + SUN4I_REG_BTIME_ADDR); + + return 0; +} + +static int sun4ican_get_berr_counter(const struct net_device *dev, + struct can_berr_counter *bec) +{ + struct sun4ican_priv *priv = netdev_priv(dev); + u32 errors; + int err; + + err = clk_prepare_enable(priv->clk); + if (err) { + netdev_err(dev, "could not enable clock\n"); + return err; + } + + errors = readl(priv->base + SUN4I_REG_ERRC_ADDR); + + bec->txerr = errors & 0xFF; + bec->rxerr = (errors >> 16) & 0xFF; + + clk_disable_unprepare(priv->clk); + + return 0; +} + +static int sun4i_can_start(struct net_device *dev) +{ + struct sun4ican_priv *priv = netdev_priv(dev); + int err; + u32 mod_reg_val; + + /* we need to enter the reset mode */ + err = set_reset_mode(dev); + if (err) { + netdev_err(dev, "could not enter reset mode\n"); + return err; + } + + /* set filters - we accept all */ + writel(0x00000000, priv->base + SUN4I_REG_ACPC_ADDR); + writel(0xFFFFFFFF, priv->base + SUN4I_REG_ACPM_ADDR); + + /* clear error counters and error code capture */ + writel(0, priv->base + SUN4I_REG_ERRC_ADDR); + + /* enable interrupts */ + if (priv->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING) + writel(0xFF, priv->base + SUN4I_REG_INTEN_ADDR); + else + writel(0xFF & ~SUN4I_INTEN_BERR, + priv->base + SUN4I_REG_INTEN_ADDR); + + /* enter the selected mode */ + mod_reg_val = readl(priv->base + SUN4I_REG_MSEL_ADDR); + if (priv->can.ctrlmode & CAN_CTRLMODE_PRESUME_ACK) + mod_reg_val |= SUN4I_MSEL_LOOPBACK_MODE; + else if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY) + mod_reg_val |= SUN4I_MSEL_LISTEN_ONLY_MODE; + writel(mod_reg_val, priv->base + SUN4I_REG_MSEL_ADDR); + + err = sun4ican_set_bittiming(dev); + if (err) + return err; + + /* we are ready to enter the normal mode */ + err = set_normal_mode(dev); + if (err) { + netdev_err(dev, "could not enter normal mode\n"); + return err; + } + + priv->can.state = CAN_STATE_ERROR_ACTIVE; + + return 0; +} + +static int sun4i_can_stop(struct net_device *dev) +{ + struct sun4ican_priv *priv = netdev_priv(dev); + int err; + + priv->can.state = CAN_STATE_STOPPED; + /* we need to enter reset mode */ + err = set_reset_mode(dev); + if (err) { + netdev_err(dev, "could not enter reset mode\n"); + return err; + } + + /* disable all interrupts */ + writel(0, priv->base + SUN4I_REG_INTEN_ADDR); + + return 0; +} + +static int sun4ican_set_mode(struct net_device *dev, enum can_mode mode) +{ + int err; + + switch (mode) { + case CAN_MODE_START: + err = sun4i_can_start(dev); + if (err) { + netdev_err(dev, "starting CAN controller failed!\n"); + return err; + } + if (netif_queue_stopped(dev)) + netif_wake_queue(dev); + break; + + default: + return -EOPNOTSUPP; + } + return 0; +} + +/* transmit a CAN message + * message layout in the sk_buff should be like this: + * xx xx xx xx ff ll 00 11 22 33 44 55 66 77 + * [ can_id ] [flags] [len] [can data (up to 8 bytes] + */ +static int sun4ican_start_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct sun4ican_priv *priv = netdev_priv(dev); + struct can_frame *cf = (struct can_frame *)skb->data; + u8 dlc; + u32 dreg, msg_flag_n; + canid_t id; + int i; + + if (can_dropped_invalid_skb(dev, skb)) + return NETDEV_TX_OK; + + netif_stop_queue(dev); + + id = cf->can_id; + dlc = cf->can_dlc; + msg_flag_n = dlc; + + if (id & CAN_RTR_FLAG) + msg_flag_n |= SUN4I_MSG_RTR_FLAG; + + if (id & CAN_EFF_FLAG) { + msg_flag_n |= SUN4I_MSG_EFF_FLAG; + dreg = SUN4I_REG_BUF5_ADDR; + writel((id >> 21) & 0xFF, priv->base + SUN4I_REG_BUF1_ADDR); + writel((id >> 13) & 0xFF, priv->base + SUN4I_REG_BUF2_ADDR); + writel((id >> 5) & 0xFF, priv->base + SUN4I_REG_BUF3_ADDR); + writel((id << 3) & 0xF8, priv->base + SUN4I_REG_BUF4_ADDR); + } else { + dreg = SUN4I_REG_BUF3_ADDR; + writel((id >> 3) & 0xFF, priv->base + SUN4I_REG_BUF1_ADDR); + writel((id << 5) & 0xE0, priv->base + SUN4I_REG_BUF2_ADDR); + } + + for (i = 0; i < dlc; i++) + writel(cf->data[i], priv->base + (dreg + i * 4)); + + writel(msg_flag_n, priv->base + SUN4I_REG_BUF0_ADDR); + + can_put_echo_skb(skb, dev, 0); + + if (priv->can.ctrlmode & CAN_CTRLMODE_LOOPBACK) + sun4i_can_write_cmdreg(priv, SUN4I_CMD_SELF_RCV_REQ); + else + sun4i_can_write_cmdreg(priv, SUN4I_CMD_TRANS_REQ); + + return NETDEV_TX_OK; +} + +static void sun4i_can_rx(struct net_device *dev) +{ + struct sun4ican_priv *priv = netdev_priv(dev); + struct net_device_stats *stats = &dev->stats; + struct can_frame *cf; + struct sk_buff *skb; + u8 fi; + u32 dreg; + canid_t id; + int i; + + /* create zero'ed CAN frame buffer */ + skb = alloc_can_skb(dev, &cf); + if (!skb) + return; + + fi = readl(priv->base + SUN4I_REG_BUF0_ADDR); + cf->can_dlc = get_can_dlc(fi & 0x0F); + if (fi & SUN4I_MSG_EFF_FLAG) { + dreg = SUN4I_REG_BUF5_ADDR; + id = (readl(priv->base + SUN4I_REG_BUF1_ADDR) << 21) | + (readl(priv->base + SUN4I_REG_BUF2_ADDR) << 13) | + (readl(priv->base + SUN4I_REG_BUF3_ADDR) << 5) | + ((readl(priv->base + SUN4I_REG_BUF4_ADDR) >> 3) & 0x1f); + id |= CAN_EFF_FLAG; + } else { + dreg = SUN4I_REG_BUF3_ADDR; + id = (readl(priv->base + SUN4I_REG_BUF1_ADDR) << 3) | + ((readl(priv->base + SUN4I_REG_BUF2_ADDR) >> 5) & 0x7); + } + + /* remote frame ? */ + if (fi & SUN4I_MSG_RTR_FLAG) + id |= CAN_RTR_FLAG; + else + for (i = 0; i < cf->can_dlc; i++) + cf->data[i] = readl(priv->base + dreg + i * 4); + + cf->can_id = id; + + sun4i_can_write_cmdreg(priv, SUN4I_CMD_RELEASE_RBUF); + + stats->rx_packets++; + stats->rx_bytes += cf->can_dlc; + netif_rx(skb); + + can_led_event(dev, CAN_LED_EVENT_RX); +} + +static int sun4i_can_err(struct net_device *dev, u8 isrc, u8 status) +{ + struct sun4ican_priv *priv = netdev_priv(dev); + struct net_device_stats *stats = &dev->stats; + struct can_frame *cf; + struct sk_buff *skb; + enum can_state state = priv->can.state; + enum can_state rx_state, tx_state; + unsigned int rxerr, txerr, errc; + u32 ecc, alc; + + /* we don't skip if alloc fails because we want the stats anyhow */ + skb = alloc_can_err_skb(dev, &cf); + + errc = readl(priv->base + SUN4I_REG_ERRC_ADDR); + rxerr = (errc >> 16) & 0xFF; + txerr = errc & 0xFF; + + if (skb) { + cf->data[6] = txerr; + cf->data[7] = rxerr; + } + + if (isrc & SUN4I_INT_DATA_OR) { + /* data overrun interrupt */ + netdev_dbg(dev, "data overrun interrupt\n"); + if (likely(skb)) { + cf->can_id |= CAN_ERR_CRTL; + cf->data[1] = CAN_ERR_CRTL_RX_OVERFLOW; + } + stats->rx_over_errors++; + stats->rx_errors++; + /* clear bit */ + sun4i_can_write_cmdreg(priv, SUN4I_CMD_CLEAR_OR_FLAG); + } + if (isrc & SUN4I_INT_ERR_WRN) { + /* error warning interrupt */ + netdev_dbg(dev, "error warning interrupt\n"); + + if (status & SUN4I_STA_BUS_OFF) + state = CAN_STATE_BUS_OFF; + else if (status & SUN4I_STA_ERR_STA) + state = CAN_STATE_ERROR_WARNING; + else + state = CAN_STATE_ERROR_ACTIVE; + } + if (isrc & SUN4I_INT_BUS_ERR) { + /* bus error interrupt */ + netdev_dbg(dev, "bus error interrupt\n"); + priv->can.can_stats.bus_error++; + stats->rx_errors++; + + if (likely(skb)) { + ecc = readl(priv->base + SUN4I_REG_STA_ADDR); + + cf->can_id |= CAN_ERR_PROT | CAN_ERR_BUSERROR; + + switch (ecc & SUN4I_STA_MASK_ERR) { + case SUN4I_STA_BIT_ERR: + cf->data[2] |= CAN_ERR_PROT_BIT; + break; + case SUN4I_STA_FORM_ERR: + cf->data[2] |= CAN_ERR_PROT_FORM; + break; + case SUN4I_STA_STUFF_ERR: + cf->data[2] |= CAN_ERR_PROT_STUFF; + break; + default: + cf->data[2] |= CAN_ERR_PROT_UNSPEC; + cf->data[3] = (ecc & SUN4I_STA_ERR_SEG_CODE) + >> 16; + break; + } + /* error occurred during transmission? */ + if ((ecc & SUN4I_STA_ERR_DIR) == 0) + cf->data[2] |= CAN_ERR_PROT_TX; + } + } + if (isrc & SUN4I_INT_ERR_PASSIVE) { + /* error passive interrupt */ + netdev_dbg(dev, "error passive interrupt\n"); + if (state == CAN_STATE_ERROR_PASSIVE) + state = CAN_STATE_ERROR_WARNING; + else + state = CAN_STATE_ERROR_PASSIVE; + } + if (isrc & SUN4I_INT_ARB_LOST) { + /* arbitration lost interrupt */ + netdev_dbg(dev, "arbitration lost interrupt\n"); + alc = readl(priv->base + SUN4I_REG_STA_ADDR); + priv->can.can_stats.arbitration_lost++; + stats->tx_errors++; + if (likely(skb)) { + cf->can_id |= CAN_ERR_LOSTARB; + cf->data[0] = (alc & 0x1f) >> 8; + } + } + + if (state != priv->can.state) { + tx_state = txerr >= rxerr ? state : 0; + rx_state = txerr <= rxerr ? state : 0; + + if (likely(skb)) + can_change_state(dev, cf, tx_state, rx_state); + else + priv->can.state = state; + if (state == CAN_STATE_BUS_OFF) + can_bus_off(dev); + } + + if (likely(skb)) { + stats->rx_packets++; + stats->rx_bytes += cf->can_dlc; + netif_rx(skb); + } else { + return -ENOMEM; + } + + return 0; +} + +static irqreturn_t sun4i_can_interrupt(int irq, void *dev_id) +{ + struct net_device *dev = (struct net_device *)dev_id; + struct sun4ican_priv *priv = netdev_priv(dev); + struct net_device_stats *stats = &dev->stats; + u8 isrc, status; + int n = 0; + + while ((isrc = readl(priv->base + SUN4I_REG_INT_ADDR)) && + (n < SUN4I_CAN_MAX_IRQ)) { + n++; + status = readl(priv->base + SUN4I_REG_STA_ADDR); + + if (isrc & SUN4I_INT_WAKEUP) + netdev_warn(dev, "wakeup interrupt\n"); + + if (isrc & SUN4I_INT_TBUF_VLD) { + /* transmission complete interrupt */ + stats->tx_bytes += + readl(priv->base + + SUN4I_REG_RBUF_RBACK_START_ADDR) & 0xf; + stats->tx_packets++; + can_get_echo_skb(dev, 0); + netif_wake_queue(dev); + can_led_event(dev, CAN_LED_EVENT_TX); + } + if (isrc & SUN4I_INT_RBUF_VLD) { + /* receive interrupt */ + while (status & SUN4I_STA_RBUF_RDY) { + /* RX buffer is not empty */ + sun4i_can_rx(dev); + status = readl(priv->base + SUN4I_REG_STA_ADDR); + } + } + if (isrc & + (SUN4I_INT_DATA_OR | SUN4I_INT_ERR_WRN | SUN4I_INT_BUS_ERR | + SUN4I_INT_ERR_PASSIVE | SUN4I_INT_ARB_LOST)) { + /* error interrupt */ + if (sun4i_can_err(dev, isrc, status)) + netdev_err(dev, "can't allocate buffer - clearing pending interrupts\n"); + } + /* clear interrupts */ + writel(isrc, priv->base + SUN4I_REG_INT_ADDR); + readl(priv->base + SUN4I_REG_INT_ADDR); + } + if (n >= SUN4I_CAN_MAX_IRQ) + netdev_dbg(dev, "%d messages handled in ISR", n); + + return (n) ? IRQ_HANDLED : IRQ_NONE; +} + +static int sun4ican_open(struct net_device *dev) +{ + struct sun4ican_priv *priv = netdev_priv(dev); + int err; + + /* common open */ + err = open_candev(dev); + if (err) + return err; + + /* register interrupt handler */ + err = request_irq(dev->irq, sun4i_can_interrupt, 0, dev->name, dev); + if (err) { + netdev_err(dev, "request_irq err: %d\n", err); + goto exit_irq; + } + + /* turn on clocking for CAN peripheral block */ + err = clk_prepare_enable(priv->clk); + if (err) { + netdev_err(dev, "could not enable CAN peripheral clock\n"); + goto exit_clock; + } + + err = sun4i_can_start(dev); + if (err) { + netdev_err(dev, "could not start CAN peripheral\n"); + goto exit_can_start; + } + + can_led_event(dev, CAN_LED_EVENT_OPEN); + netif_start_queue(dev); + + return 0; + +exit_can_start: + clk_disable_unprepare(priv->clk); +exit_clock: + free_irq(dev->irq, dev); +exit_irq: + close_candev(dev); + return err; +} + +static int sun4ican_close(struct net_device *dev) +{ + struct sun4ican_priv *priv = netdev_priv(dev); + + netif_stop_queue(dev); + sun4i_can_stop(dev); + clk_disable_unprepare(priv->clk); + + free_irq(dev->irq, dev); + close_candev(dev); + can_led_event(dev, CAN_LED_EVENT_STOP); + + return 0; +} + +static const struct net_device_ops sun4ican_netdev_ops = { + .ndo_open = sun4ican_open, + .ndo_stop = sun4ican_close, + .ndo_start_xmit = sun4ican_start_xmit, +}; + +static const struct of_device_id sun4ican_of_match[] = { + {.compatible = "allwinner,sun4i-a10-can"}, + {}, +}; + +MODULE_DEVICE_TABLE(of, sun4ican_of_match); + +static int sun4ican_remove(struct platform_device *pdev) +{ + struct net_device *dev = platform_get_drvdata(pdev); + + unregister_netdev(dev); + free_candev(dev); + + return 0; +} + +static int sun4ican_probe(struct platform_device *pdev) +{ + struct device_node *np = pdev->dev.of_node; + struct resource *mem; + struct clk *clk; + void __iomem *addr; + int err, irq; + struct net_device *dev; + struct sun4ican_priv *priv; + + clk = of_clk_get(np, 0); + if (IS_ERR(clk)) { + dev_err(&pdev->dev, "unable to request clock\n"); + err = -ENODEV; + goto exit; + } + + irq = platform_get_irq(pdev, 0); + if (irq < 0) { + dev_err(&pdev->dev, "could not get a valid irq\n"); + err = -ENODEV; + goto exit; + } + + mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); + addr = devm_ioremap_resource(&pdev->dev, mem); + if (IS_ERR(addr)) { + err = -EBUSY; + goto exit; + } + + dev = alloc_candev(sizeof(struct sun4ican_priv), 1); + if (!dev) { + dev_err(&pdev->dev, + "could not allocate memory for CAN device\n"); + err = -ENOMEM; + goto exit; + } + + dev->netdev_ops = &sun4ican_netdev_ops; + dev->irq = irq; + dev->flags |= IFF_ECHO; + + priv = netdev_priv(dev); + priv->can.clock.freq = clk_get_rate(clk); + priv->can.bittiming_const = &sun4ican_bittiming_const; + priv->can.do_set_mode = sun4ican_set_mode; + priv->can.do_get_berr_counter = sun4ican_get_berr_counter; + priv->can.ctrlmode_supported = CAN_CTRLMODE_BERR_REPORTING | + CAN_CTRLMODE_LISTENONLY | + CAN_CTRLMODE_LOOPBACK | + CAN_CTRLMODE_PRESUME_ACK | + CAN_CTRLMODE_3_SAMPLES; + priv->base = addr; + priv->clk = clk; + spin_lock_init(&priv->cmdreg_lock); + + platform_set_drvdata(pdev, dev); + SET_NETDEV_DEV(dev, &pdev->dev); + + err = register_candev(dev); + if (err) { + dev_err(&pdev->dev, "registering %s failed (err=%d)\n", + DRV_NAME, err); + goto exit_free; + } + devm_can_led_init(dev); + + dev_info(&pdev->dev, "device registered (base=%p, irq=%d)\n", + priv->base, dev->irq); + + return 0; + +exit_free: + free_candev(dev); +exit: + return err; +} + +static struct platform_driver sun4i_can_driver = { + .driver = { + .name = DRV_NAME, + .of_match_table = sun4ican_of_match, + }, + .probe = sun4ican_probe, + .remove = sun4ican_remove, +}; + +module_platform_driver(sun4i_can_driver); + +MODULE_AUTHOR("Peter Chen <xingkongcp@gmail.com>"); +MODULE_AUTHOR("Gerhard Bertelsmann <info@gerhard-bertelsmann.de>"); +MODULE_LICENSE("Dual BSD/GPL"); +MODULE_DESCRIPTION(DRV_NAME "CAN driver for Allwinner SoCs (A10/A20)"); diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c index 1f7dd927cc5e..932fb720be24 100644 --- a/drivers/net/dsa/mv88e6xxx.c +++ b/drivers/net/dsa/mv88e6xxx.c @@ -574,7 +574,8 @@ void mv88e6xxx_adjust_link(struct dsa_switch *ds, int port, struct phy_device *phydev) { struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); - u32 ret, reg; + u32 reg; + int ret; if (!phy_is_pseudo_fixed_link(phydev)) return; @@ -1036,14 +1037,10 @@ out: return ret; } -static int _mv88e6xxx_atu_cmd(struct dsa_switch *ds, int fid, u16 cmd) +static int _mv88e6xxx_atu_cmd(struct dsa_switch *ds, u16 cmd) { int ret; - ret = _mv88e6xxx_reg_write(ds, REG_GLOBAL, GLOBAL_ATU_FID, fid); - if (ret < 0) - return ret; - ret = _mv88e6xxx_reg_write(ds, REG_GLOBAL, GLOBAL_ATU_OP, cmd); if (ret < 0) return ret; @@ -1051,15 +1048,98 @@ static int _mv88e6xxx_atu_cmd(struct dsa_switch *ds, int fid, u16 cmd) return _mv88e6xxx_atu_wait(ds); } +static int _mv88e6xxx_atu_data_write(struct dsa_switch *ds, + struct mv88e6xxx_atu_entry *entry) +{ + u16 data = entry->state & GLOBAL_ATU_DATA_STATE_MASK; + + if (entry->state != GLOBAL_ATU_DATA_STATE_UNUSED) { + unsigned int mask, shift; + + if (entry->trunk) { + data |= GLOBAL_ATU_DATA_TRUNK; + mask = GLOBAL_ATU_DATA_TRUNK_ID_MASK; + shift = GLOBAL_ATU_DATA_TRUNK_ID_SHIFT; + } else { + mask = GLOBAL_ATU_DATA_PORT_VECTOR_MASK; + shift = GLOBAL_ATU_DATA_PORT_VECTOR_SHIFT; + } + + data |= (entry->portv_trunkid << shift) & mask; + } + + return _mv88e6xxx_reg_write(ds, REG_GLOBAL, GLOBAL_ATU_DATA, data); +} + +static int _mv88e6xxx_atu_flush_move(struct dsa_switch *ds, + struct mv88e6xxx_atu_entry *entry, + bool static_too) +{ + int op; + int err; + + err = _mv88e6xxx_atu_wait(ds); + if (err) + return err; + + err = _mv88e6xxx_atu_data_write(ds, entry); + if (err) + return err; + + if (entry->fid) { + err = _mv88e6xxx_reg_write(ds, REG_GLOBAL, GLOBAL_ATU_FID, + entry->fid); + if (err) + return err; + + op = static_too ? GLOBAL_ATU_OP_FLUSH_MOVE_ALL_DB : + GLOBAL_ATU_OP_FLUSH_MOVE_NON_STATIC_DB; + } else { + op = static_too ? GLOBAL_ATU_OP_FLUSH_MOVE_ALL : + GLOBAL_ATU_OP_FLUSH_MOVE_NON_STATIC; + } + + return _mv88e6xxx_atu_cmd(ds, op); +} + +static int _mv88e6xxx_atu_flush(struct dsa_switch *ds, u16 fid, bool static_too) +{ + struct mv88e6xxx_atu_entry entry = { + .fid = fid, + .state = 0, /* EntryState bits must be 0 */ + }; + + return _mv88e6xxx_atu_flush_move(ds, &entry, static_too); +} + static int _mv88e6xxx_flush_fid(struct dsa_switch *ds, int fid) { - int ret; + return _mv88e6xxx_atu_flush(ds, fid, false); +} - ret = _mv88e6xxx_atu_wait(ds); - if (ret < 0) - return ret; +static int _mv88e6xxx_atu_move(struct dsa_switch *ds, u16 fid, int from_port, + int to_port, bool static_too) +{ + struct mv88e6xxx_atu_entry entry = { + .trunk = false, + .fid = fid, + }; + + /* EntryState bits must be 0xF */ + entry.state = GLOBAL_ATU_DATA_STATE_MASK; + + /* ToPort and FromPort are respectively in PortVec bits 7:4 and 3:0 */ + entry.portv_trunkid = (to_port & 0x0f) << 4; + entry.portv_trunkid |= from_port & 0x0f; + + return _mv88e6xxx_atu_flush_move(ds, &entry, static_too); +} - return _mv88e6xxx_atu_cmd(ds, fid, GLOBAL_ATU_OP_FLUSH_NON_STATIC_DB); +static int _mv88e6xxx_atu_remove(struct dsa_switch *ds, u16 fid, int port, + bool static_too) +{ + /* Destination port 0xF means remove the entries */ + return _mv88e6xxx_atu_move(ds, fid, port, 0x0f, static_too); } static int mv88e6xxx_set_port_state(struct dsa_switch *ds, int port, u8 state) @@ -1084,7 +1164,7 @@ static int mv88e6xxx_set_port_state(struct dsa_switch *ds, int port, u8 state) */ if (oldstate >= PORT_CONTROL_STATE_LEARNING && state <= PORT_CONTROL_STATE_BLOCKING) { - ret = _mv88e6xxx_flush_fid(ds, ps->fid[port]); + ret = _mv88e6xxx_atu_remove(ds, 0, port, false); if (ret) goto abort; } @@ -1576,7 +1656,8 @@ static int _mv88e6xxx_vlan_init(struct dsa_switch *ds, u16 vid, return -ENOSPC; } - err = _mv88e6xxx_flush_fid(ds, vlan.fid); + /* Clear all MAC addresses from the new database */ + err = _mv88e6xxx_atu_flush(ds, vlan.fid, true); if (err) return err; @@ -1653,6 +1734,10 @@ int mv88e6xxx_port_vlan_del(struct dsa_switch *ds, int port, u16 vid) if (err) goto unlock; + err = _mv88e6xxx_atu_remove(ds, vlan.fid, port, false); + if (err) + goto unlock; + if (!keep) clear_bit(vlan.fid, ps->fid_bitmap); @@ -1761,7 +1846,6 @@ static int _mv88e6xxx_atu_mac_read(struct dsa_switch *ds, unsigned char *addr) static int _mv88e6xxx_atu_load(struct dsa_switch *ds, struct mv88e6xxx_atu_entry *entry) { - u16 reg = 0; int ret; ret = _mv88e6xxx_atu_wait(ds); @@ -1772,28 +1856,15 @@ static int _mv88e6xxx_atu_load(struct dsa_switch *ds, if (ret < 0) return ret; - if (entry->state != GLOBAL_ATU_DATA_STATE_UNUSED) { - unsigned int mask, shift; - - if (entry->trunk) { - reg |= GLOBAL_ATU_DATA_TRUNK; - mask = GLOBAL_ATU_DATA_TRUNK_ID_MASK; - shift = GLOBAL_ATU_DATA_TRUNK_ID_SHIFT; - } else { - mask = GLOBAL_ATU_DATA_PORT_VECTOR_MASK; - shift = GLOBAL_ATU_DATA_PORT_VECTOR_SHIFT; - } - - reg |= (entry->portv_trunkid << shift) & mask; - } - - reg |= entry->state & GLOBAL_ATU_DATA_STATE_MASK; + ret = _mv88e6xxx_atu_data_write(ds, entry); + if (ret < 0) + return ret; - ret = _mv88e6xxx_reg_write(ds, REG_GLOBAL, GLOBAL_ATU_DATA, reg); + ret = _mv88e6xxx_reg_write(ds, REG_GLOBAL, GLOBAL_ATU_FID, entry->fid); if (ret < 0) return ret; - return _mv88e6xxx_atu_cmd(ds, entry->fid, GLOBAL_ATU_OP_LOAD_DB); + return _mv88e6xxx_atu_cmd(ds, GLOBAL_ATU_OP_LOAD_DB); } static int _mv88e6xxx_port_vid_to_fid(struct dsa_switch *ds, int port, u16 vid) @@ -1884,7 +1955,11 @@ static int _mv88e6xxx_atu_getnext(struct dsa_switch *ds, u16 fid, if (ret < 0) return ret; - ret = _mv88e6xxx_atu_cmd(ds, fid, GLOBAL_ATU_OP_GET_NEXT_DB); + ret = _mv88e6xxx_reg_write(ds, REG_GLOBAL, GLOBAL_ATU_FID, fid); + if (ret < 0) + return ret; + + ret = _mv88e6xxx_atu_cmd(ds, GLOBAL_ATU_OP_GET_NEXT_DB); if (ret < 0) return ret; @@ -2311,9 +2386,15 @@ static int mv88e6xxx_atu_show_db(struct seq_file *s, struct dsa_switch *ds, return ret; do { - ret = _mv88e6xxx_atu_cmd(ds, dbnum, GLOBAL_ATU_OP_GET_NEXT_DB); + ret = _mv88e6xxx_reg_write(ds, REG_GLOBAL, GLOBAL_ATU_FID, + dbnum); + if (ret < 0) + return ret; + + ret = _mv88e6xxx_atu_cmd(ds, GLOBAL_ATU_OP_GET_NEXT_DB); if (ret < 0) return ret; + data = _mv88e6xxx_reg_read(ds, REG_GLOBAL, GLOBAL_ATU_DATA); if (data < 0) return data; @@ -2638,6 +2719,11 @@ int mv88e6xxx_setup_global(struct dsa_switch *ds) if (ret < 0) goto unlock; + /* Clear all ATU entries */ + ret = _mv88e6xxx_atu_flush(ds, 0, true); + if (ret < 0) + goto unlock; + /* Clear all the VTU and STU entries */ ret = _mv88e6xxx_vtu_stu_flush(ds); unlock: diff --git a/drivers/net/dsa/mv88e6xxx.h b/drivers/net/dsa/mv88e6xxx.h index 9b6f3d9d5ae1..1cf3cf887902 100644 --- a/drivers/net/dsa/mv88e6xxx.h +++ b/drivers/net/dsa/mv88e6xxx.h @@ -226,12 +226,12 @@ #define GLOBAL_ATU_OP 0x0b #define GLOBAL_ATU_OP_BUSY BIT(15) #define GLOBAL_ATU_OP_NOP (0 << 12) -#define GLOBAL_ATU_OP_FLUSH_ALL ((1 << 12) | GLOBAL_ATU_OP_BUSY) -#define GLOBAL_ATU_OP_FLUSH_NON_STATIC ((2 << 12) | GLOBAL_ATU_OP_BUSY) +#define GLOBAL_ATU_OP_FLUSH_MOVE_ALL ((1 << 12) | GLOBAL_ATU_OP_BUSY) +#define GLOBAL_ATU_OP_FLUSH_MOVE_NON_STATIC ((2 << 12) | GLOBAL_ATU_OP_BUSY) #define GLOBAL_ATU_OP_LOAD_DB ((3 << 12) | GLOBAL_ATU_OP_BUSY) #define GLOBAL_ATU_OP_GET_NEXT_DB ((4 << 12) | GLOBAL_ATU_OP_BUSY) -#define GLOBAL_ATU_OP_FLUSH_DB ((5 << 12) | GLOBAL_ATU_OP_BUSY) -#define GLOBAL_ATU_OP_FLUSH_NON_STATIC_DB ((6 << 12) | GLOBAL_ATU_OP_BUSY) +#define GLOBAL_ATU_OP_FLUSH_MOVE_ALL_DB ((5 << 12) | GLOBAL_ATU_OP_BUSY) +#define GLOBAL_ATU_OP_FLUSH_MOVE_NON_STATIC_DB ((6 << 12) | GLOBAL_ATU_OP_BUSY) #define GLOBAL_ATU_OP_GET_CLR_VIOLATION ((7 << 12) | GLOBAL_ATU_OP_BUSY) #define GLOBAL_ATU_DATA 0x0c #define GLOBAL_ATU_DATA_TRUNK BIT(15) diff --git a/drivers/net/ethernet/8390/Kconfig b/drivers/net/ethernet/8390/Kconfig index edf72258ab1d..29c3075bfb05 100644 --- a/drivers/net/ethernet/8390/Kconfig +++ b/drivers/net/ethernet/8390/Kconfig @@ -64,7 +64,7 @@ config ARM_ETHERH should say Y to this option if you wish to use it with Linux. config MAC8390 - bool "Macintosh NS 8390 based ethernet cards" + tristate "Macintosh NS 8390 based ethernet cards" depends on MAC select CRC32 ---help--- diff --git a/drivers/net/ethernet/8390/mac8390.c b/drivers/net/ethernet/8390/mac8390.c index 65cf60f6718c..b9283901136e 100644 --- a/drivers/net/ethernet/8390/mac8390.c +++ b/drivers/net/ethernet/8390/mac8390.c @@ -454,34 +454,22 @@ MODULE_AUTHOR("David Huggins-Daines <dhd@debian.org> and others"); MODULE_DESCRIPTION("Macintosh NS8390-based Nubus Ethernet driver"); MODULE_LICENSE("GPL"); -/* overkill, of course */ -static struct net_device *dev_mac8390[15]; -int init_module(void) +static struct net_device *dev_mac8390; + +int __init init_module(void) { - int i; - for (i = 0; i < 15; i++) { - struct net_device *dev = mac8390_probe(-1); - if (IS_ERR(dev)) - break; - dev_mac890[i] = dev; - } - if (!i) { - pr_notice("No useable cards found, driver NOT installed.\n"); - return -ENODEV; + dev_mac8390 = mac8390_probe(-1); + if (IS_ERR(dev_mac8390)) { + pr_warn("mac8390: No card found\n"); + return PTR_ERR(dev_mac8390); } return 0; } -void cleanup_module(void) +void __exit cleanup_module(void) { - int i; - for (i = 0; i < 15; i++) { - struct net_device *dev = dev_mac890[i]; - if (dev) { - unregister_netdev(dev); - free_netdev(dev); - } - } + unregister_netdev(dev_mac8390); + free_netdev(dev_mac8390); } #endif /* MODULE */ diff --git a/drivers/net/ethernet/amd/7990.c b/drivers/net/ethernet/amd/7990.c index 98a10d555b79..66d0b73c39c0 100644 --- a/drivers/net/ethernet/amd/7990.c +++ b/drivers/net/ethernet/amd/7990.c @@ -661,6 +661,7 @@ void lance_poll(struct net_device *dev) spin_unlock(&lp->devlock); lance_interrupt(dev->irq, dev); } +EXPORT_SYMBOL_GPL(lance_poll); #endif MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/amd/Kconfig b/drivers/net/ethernet/amd/Kconfig index afc62ea804fc..0038709fd317 100644 --- a/drivers/net/ethernet/amd/Kconfig +++ b/drivers/net/ethernet/amd/Kconfig @@ -100,7 +100,7 @@ config DECLANCE DEPCA series. (This chipset is better known via the NE2100 cards.) config HPLANCE - bool "HP on-board LANCE support" + tristate "HP on-board LANCE support" depends on DIO select CRC32 ---help--- diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c index c4bb8027b3fb..652f21889a48 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c @@ -107,7 +107,8 @@ static void xgene_enet_set_ring_state(struct xgene_enet_desc_ring *ring) { xgene_enet_ring_set_type(ring); - if (xgene_enet_ring_owner(ring->id) == RING_OWNER_ETH0) + if (xgene_enet_ring_owner(ring->id) == RING_OWNER_ETH0 || + xgene_enet_ring_owner(ring->id) == RING_OWNER_ETH1) xgene_enet_ring_set_recombbuf(ring); xgene_enet_ring_init(ring); diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index e47298faf78d..6b1846df7b0c 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -1305,10 +1305,17 @@ static void xgene_enet_setup_ops(struct xgene_enet_pdata *pdata) pdata->ring_num = START_RING_NUM_0; break; case 1: - pdata->cpu_bufnum = START_CPU_BUFNUM_1; - pdata->eth_bufnum = START_ETH_BUFNUM_1; - pdata->bp_bufnum = START_BP_BUFNUM_1; - pdata->ring_num = START_RING_NUM_1; + if (pdata->phy_mode == PHY_INTERFACE_MODE_XGMII) { + pdata->cpu_bufnum = XG_START_CPU_BUFNUM_1; + pdata->eth_bufnum = XG_START_ETH_BUFNUM_1; + pdata->bp_bufnum = XG_START_BP_BUFNUM_1; + pdata->ring_num = XG_START_RING_NUM_1; + } else { + pdata->cpu_bufnum = START_CPU_BUFNUM_1; + pdata->eth_bufnum = START_ETH_BUFNUM_1; + pdata->bp_bufnum = START_BP_BUFNUM_1; + pdata->ring_num = START_RING_NUM_1; + } break; default: break; @@ -1478,6 +1485,7 @@ static const struct acpi_device_id xgene_enet_acpi_match[] = { { "APMC0D05", XGENE_ENET1}, { "APMC0D30", XGENE_ENET1}, { "APMC0D31", XGENE_ENET1}, + { "APMC0D3F", XGENE_ENET1}, { "APMC0D26", XGENE_ENET2}, { "APMC0D25", XGENE_ENET2}, { } diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h index 50f92c39ed2a..ff89a5d98d01 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.h +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.h @@ -56,6 +56,11 @@ #define START_BP_BUFNUM_1 0x2A #define START_RING_NUM_1 264 +#define XG_START_CPU_BUFNUM_1 12 +#define XG_START_ETH_BUFNUM_1 2 +#define XG_START_BP_BUFNUM_1 0x22 +#define XG_START_RING_NUM_1 264 + #define X2_START_CPU_BUFNUM_0 0 #define X2_START_ETH_BUFNUM_0 0 #define X2_START_BP_BUFNUM_0 0x20 diff --git a/drivers/net/ethernet/apple/Kconfig b/drivers/net/ethernet/apple/Kconfig index d19a41b0c6d2..31071297896c 100644 --- a/drivers/net/ethernet/apple/Kconfig +++ b/drivers/net/ethernet/apple/Kconfig @@ -51,7 +51,7 @@ config BMAC will be called bmac. config MACMACE - bool "Macintosh (AV) onboard MACE ethernet" + tristate "Macintosh (AV) onboard MACE ethernet" depends on MAC select CRC32 ---help--- diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 3bc701e4c59e..1a3988f51305 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -205,6 +205,23 @@ enum dma_reg { DMA_INDEX2RING_5, DMA_INDEX2RING_6, DMA_INDEX2RING_7, + DMA_RING0_TIMEOUT, + DMA_RING1_TIMEOUT, + DMA_RING2_TIMEOUT, + DMA_RING3_TIMEOUT, + DMA_RING4_TIMEOUT, + DMA_RING5_TIMEOUT, + DMA_RING6_TIMEOUT, + DMA_RING7_TIMEOUT, + DMA_RING8_TIMEOUT, + DMA_RING9_TIMEOUT, + DMA_RING10_TIMEOUT, + DMA_RING11_TIMEOUT, + DMA_RING12_TIMEOUT, + DMA_RING13_TIMEOUT, + DMA_RING14_TIMEOUT, + DMA_RING15_TIMEOUT, + DMA_RING16_TIMEOUT, }; static const u8 bcmgenet_dma_regs_v3plus[] = { @@ -216,6 +233,23 @@ static const u8 bcmgenet_dma_regs_v3plus[] = { [DMA_PRIORITY_0] = 0x30, [DMA_PRIORITY_1] = 0x34, [DMA_PRIORITY_2] = 0x38, + [DMA_RING0_TIMEOUT] = 0x2C, + [DMA_RING1_TIMEOUT] = 0x30, + [DMA_RING2_TIMEOUT] = 0x34, + [DMA_RING3_TIMEOUT] = 0x38, + [DMA_RING4_TIMEOUT] = 0x3c, + [DMA_RING5_TIMEOUT] = 0x40, + [DMA_RING6_TIMEOUT] = 0x44, + [DMA_RING7_TIMEOUT] = 0x48, + [DMA_RING8_TIMEOUT] = 0x4c, + [DMA_RING9_TIMEOUT] = 0x50, + [DMA_RING10_TIMEOUT] = 0x54, + [DMA_RING11_TIMEOUT] = 0x58, + [DMA_RING12_TIMEOUT] = 0x5c, + [DMA_RING13_TIMEOUT] = 0x60, + [DMA_RING14_TIMEOUT] = 0x64, + [DMA_RING15_TIMEOUT] = 0x68, + [DMA_RING16_TIMEOUT] = 0x6C, [DMA_INDEX2RING_0] = 0x70, [DMA_INDEX2RING_1] = 0x74, [DMA_INDEX2RING_2] = 0x78, @@ -235,6 +269,23 @@ static const u8 bcmgenet_dma_regs_v2[] = { [DMA_PRIORITY_0] = 0x34, [DMA_PRIORITY_1] = 0x38, [DMA_PRIORITY_2] = 0x3C, + [DMA_RING0_TIMEOUT] = 0x2C, + [DMA_RING1_TIMEOUT] = 0x30, + [DMA_RING2_TIMEOUT] = 0x34, + [DMA_RING3_TIMEOUT] = 0x38, + [DMA_RING4_TIMEOUT] = 0x3c, + [DMA_RING5_TIMEOUT] = 0x40, + [DMA_RING6_TIMEOUT] = 0x44, + [DMA_RING7_TIMEOUT] = 0x48, + [DMA_RING8_TIMEOUT] = 0x4c, + [DMA_RING9_TIMEOUT] = 0x50, + [DMA_RING10_TIMEOUT] = 0x54, + [DMA_RING11_TIMEOUT] = 0x58, + [DMA_RING12_TIMEOUT] = 0x5c, + [DMA_RING13_TIMEOUT] = 0x60, + [DMA_RING14_TIMEOUT] = 0x64, + [DMA_RING15_TIMEOUT] = 0x68, + [DMA_RING16_TIMEOUT] = 0x6C, }; static const u8 bcmgenet_dma_regs_v1[] = { @@ -245,6 +296,23 @@ static const u8 bcmgenet_dma_regs_v1[] = { [DMA_PRIORITY_0] = 0x34, [DMA_PRIORITY_1] = 0x38, [DMA_PRIORITY_2] = 0x3C, + [DMA_RING0_TIMEOUT] = 0x2C, + [DMA_RING1_TIMEOUT] = 0x30, + [DMA_RING2_TIMEOUT] = 0x34, + [DMA_RING3_TIMEOUT] = 0x38, + [DMA_RING4_TIMEOUT] = 0x3c, + [DMA_RING5_TIMEOUT] = 0x40, + [DMA_RING6_TIMEOUT] = 0x44, + [DMA_RING7_TIMEOUT] = 0x48, + [DMA_RING8_TIMEOUT] = 0x4c, + [DMA_RING9_TIMEOUT] = 0x50, + [DMA_RING10_TIMEOUT] = 0x54, + [DMA_RING11_TIMEOUT] = 0x58, + [DMA_RING12_TIMEOUT] = 0x5c, + [DMA_RING13_TIMEOUT] = 0x60, + [DMA_RING14_TIMEOUT] = 0x64, + [DMA_RING15_TIMEOUT] = 0x68, + [DMA_RING16_TIMEOUT] = 0x6C, }; /* Set at runtime once bcmgenet version is known */ @@ -498,6 +566,85 @@ static void bcmgenet_set_msglevel(struct net_device *dev, u32 level) priv->msg_enable = level; } +static int bcmgenet_get_coalesce(struct net_device *dev, + struct ethtool_coalesce *ec) +{ + struct bcmgenet_priv *priv = netdev_priv(dev); + + ec->tx_max_coalesced_frames = + bcmgenet_tdma_ring_readl(priv, DESC_INDEX, + DMA_MBUF_DONE_THRESH); + ec->rx_max_coalesced_frames = + bcmgenet_rdma_ring_readl(priv, DESC_INDEX, + DMA_MBUF_DONE_THRESH); + ec->rx_coalesce_usecs = + bcmgenet_rdma_readl(priv, DMA_RING16_TIMEOUT) * 8192 / 1000; + + return 0; +} + +static int bcmgenet_set_coalesce(struct net_device *dev, + struct ethtool_coalesce *ec) +{ + struct bcmgenet_priv *priv = netdev_priv(dev); + unsigned int i; + u32 reg; + + /* Base system clock is 125Mhz, DMA timeout is this reference clock + * divided by 1024, which yields roughly 8.192us, our maximum value + * has to fit in the DMA_TIMEOUT_MASK (16 bits) + */ + if (ec->tx_max_coalesced_frames > DMA_INTR_THRESHOLD_MASK || + ec->tx_max_coalesced_frames == 0 || + ec->rx_max_coalesced_frames > DMA_INTR_THRESHOLD_MASK || + ec->rx_coalesce_usecs > (DMA_TIMEOUT_MASK * 8) + 1) + return -EINVAL; + + if (ec->rx_coalesce_usecs == 0 && ec->rx_max_coalesced_frames == 0) + return -EINVAL; + + /* GENET TDMA hardware does not support a configurable timeout, but will + * always generate an interrupt either after MBDONE packets have been + * transmitted, or when the ring is emtpy. + */ + if (ec->tx_coalesce_usecs || ec->tx_coalesce_usecs_high || + ec->tx_coalesce_usecs_irq || ec->tx_coalesce_usecs_low) + return -EOPNOTSUPP; + + /* Program all TX queues with the same values, as there is no + * ethtool knob to do coalescing on a per-queue basis + */ + for (i = 0; i < priv->hw_params->tx_queues; i++) + bcmgenet_tdma_ring_writel(priv, i, + ec->tx_max_coalesced_frames, + DMA_MBUF_DONE_THRESH); + bcmgenet_tdma_ring_writel(priv, DESC_INDEX, + ec->tx_max_coalesced_frames, + DMA_MBUF_DONE_THRESH); + + for (i = 0; i < priv->hw_params->rx_queues; i++) { + bcmgenet_rdma_ring_writel(priv, i, + ec->rx_max_coalesced_frames, + DMA_MBUF_DONE_THRESH); + + reg = bcmgenet_rdma_readl(priv, DMA_RING0_TIMEOUT + i); + reg &= ~DMA_TIMEOUT_MASK; + reg |= DIV_ROUND_UP(ec->rx_coalesce_usecs * 1000, 8192); + bcmgenet_rdma_writel(priv, reg, DMA_RING0_TIMEOUT + i); + } + + bcmgenet_rdma_ring_writel(priv, DESC_INDEX, + ec->rx_max_coalesced_frames, + DMA_MBUF_DONE_THRESH); + + reg = bcmgenet_rdma_readl(priv, DMA_RING16_TIMEOUT); + reg &= ~DMA_TIMEOUT_MASK; + reg |= DIV_ROUND_UP(ec->rx_coalesce_usecs * 1000, 8192); + bcmgenet_rdma_writel(priv, reg, DMA_RING16_TIMEOUT); + + return 0; +} + /* standard ethtool support functions. */ enum bcmgenet_stat_type { BCMGENET_STAT_NETDEV = -1, @@ -844,6 +991,8 @@ static struct ethtool_ops bcmgenet_ethtool_ops = { .get_eee = bcmgenet_get_eee, .set_eee = bcmgenet_set_eee, .nway_reset = bcmgenet_nway_reset, + .get_coalesce = bcmgenet_get_coalesce, + .set_coalesce = bcmgenet_set_coalesce, }; /* Power down the unimac, based on mode. */ diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h index 7299d1075422..29dc2f1bbb19 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h @@ -304,13 +304,12 @@ struct bcmgenet_mib_counters { #define UMAC_IRQ_RXDMA_MBDONE (1 << 13) #define UMAC_IRQ_RXDMA_PDONE (1 << 14) #define UMAC_IRQ_RXDMA_BDONE (1 << 15) -#define UMAC_IRQ_RXDMA_DONE (UMAC_IRQ_RXDMA_PDONE | \ - UMAC_IRQ_RXDMA_BDONE) +#define UMAC_IRQ_RXDMA_DONE UMAC_IRQ_RXDMA_MBDONE #define UMAC_IRQ_TXDMA_MBDONE (1 << 16) #define UMAC_IRQ_TXDMA_PDONE (1 << 17) #define UMAC_IRQ_TXDMA_BDONE (1 << 18) -#define UMAC_IRQ_TXDMA_DONE (UMAC_IRQ_TXDMA_PDONE | \ - UMAC_IRQ_TXDMA_BDONE) +#define UMAC_IRQ_TXDMA_DONE UMAC_IRQ_TXDMA_MBDONE + /* Only valid for GENETv3+ */ #define UMAC_IRQ_MDIO_DONE (1 << 23) #define UMAC_IRQ_MDIO_ERROR (1 << 24) @@ -386,7 +385,7 @@ struct bcmgenet_mib_counters { #define DMA_RING_BUFFER_SIZE_MASK 0xFFFF /* DMA interrupt threshold register */ -#define DMA_INTR_THRESHOLD_MASK 0x00FF +#define DMA_INTR_THRESHOLD_MASK 0x01FF /* DMA XON/XOFF register */ #define DMA_XON_THREHOLD_MASK 0xFFFF diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index fa0c7b54ec7a..634e50c8c5ef 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -47,6 +47,7 @@ #include <linux/timer.h> #include <linux/vmalloc.h> #include <linux/etherdevice.h> +#include <linux/net_tstamp.h> #include <asm/io.h> #include "cxgb4_uld.h" @@ -478,6 +479,8 @@ struct port_info { #ifdef CONFIG_CHELSIO_T4_FCOE struct cxgb_fcoe fcoe; #endif /* CONFIG_CHELSIO_T4_FCOE */ + bool rxtstamp; /* Enable TS */ + struct hwtstamp_config tstamp_config; }; struct dentry; @@ -517,6 +520,7 @@ struct sge_fl { /* SGE free-buffer queue state */ /* A packet gather list */ struct pkt_gl { + u64 sgetstamp; /* SGE Time Stamp for Ingress Packet */ struct page_frag frags[MAX_SKB_FRAGS]; void *va; /* virtual address of first byte */ unsigned int nfrags; /* # of fragments */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c index 5eedb98ff581..02e4e028a647 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c @@ -961,6 +961,20 @@ static int set_flash(struct net_device *netdev, struct ethtool_flash *ef) return ret; } +static int get_ts_info(struct net_device *dev, struct ethtool_ts_info *ts_info) +{ + ts_info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE; + + ts_info->so_timestamping |= SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE; + + ts_info->phc_index = -1; + + return 0; +} + static u32 get_rss_table_size(struct net_device *dev) { const struct port_info *pi = netdev_priv(dev); @@ -1095,6 +1109,7 @@ static const struct ethtool_ops cxgb_ethtool_ops = { .get_rxfh = get_rss_table, .set_rxfh = set_rss_table, .flash_device = set_flash, + .get_ts_info = get_ts_info }; void cxgb4_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index f5dcde27e402..0b7570ddbe1a 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -2959,6 +2959,30 @@ static int cxgb_ioctl(struct net_device *dev, struct ifreq *req, int cmd) ret = t4_mdio_wr(pi->adapter, mbox, prtad, devad, data->reg_num, data->val_in); break; + case SIOCGHWTSTAMP: + return copy_to_user(req->ifr_data, &pi->tstamp_config, + sizeof(pi->tstamp_config)) ? + -EFAULT : 0; + case SIOCSHWTSTAMP: + if (copy_from_user(&pi->tstamp_config, req->ifr_data, + sizeof(pi->tstamp_config))) + return -EFAULT; + + switch (pi->tstamp_config.rx_filter) { + case HWTSTAMP_FILTER_NONE: + pi->rxtstamp = false; + break; + case HWTSTAMP_FILTER_ALL: + pi->rxtstamp = true; + break; + default: + pi->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; + return -ERANGE; + } + + return copy_to_user(req->ifr_data, &pi->tstamp_config, + sizeof(pi->tstamp_config)) ? + -EFAULT : 0; default: return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index 9162746d7729..b7b93e7a643d 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -1820,11 +1820,34 @@ static noinline int handle_trace_pkt(struct adapter *adap, return 0; } +/** + * cxgb4_sgetim_to_hwtstamp - convert sge time stamp to hw time stamp + * @adap: the adapter + * @hwtstamps: time stamp structure to update + * @sgetstamp: 60bit iqe timestamp + * + * Every ingress queue entry has the 60-bit timestamp, convert that timestamp + * which is in Core Clock ticks into ktime_t and assign it + **/ +static void cxgb4_sgetim_to_hwtstamp(struct adapter *adap, + struct skb_shared_hwtstamps *hwtstamps, + u64 sgetstamp) +{ + u64 ns; + u64 tmp = (sgetstamp * 1000 * 1000 + adap->params.vpd.cclk / 2); + + ns = div_u64(tmp, adap->params.vpd.cclk); + + memset(hwtstamps, 0, sizeof(*hwtstamps)); + hwtstamps->hwtstamp = ns_to_ktime(ns); +} + static void do_gro(struct sge_eth_rxq *rxq, const struct pkt_gl *gl, const struct cpl_rx_pkt *pkt) { struct adapter *adapter = rxq->rspq.adap; struct sge *s = &adapter->sge; + struct port_info *pi; int ret; struct sk_buff *skb; @@ -1842,6 +1865,10 @@ static void do_gro(struct sge_eth_rxq *rxq, const struct pkt_gl *gl, skb->ip_summed = CHECKSUM_UNNECESSARY; skb_record_rx_queue(skb, rxq->rspq.idx); skb_mark_napi_id(skb, &rxq->rspq.napi); + pi = netdev_priv(skb->dev); + if (pi->rxtstamp) + cxgb4_sgetim_to_hwtstamp(adapter, skb_hwtstamps(skb), + gl->sgetstamp); if (rxq->rspq.netdev->features & NETIF_F_RXHASH) skb_set_hash(skb, (__force u32)pkt->rsshdr.hash_val, PKT_HASH_TYPE_L3); @@ -1877,9 +1904,7 @@ int t4_ethrx_handler(struct sge_rspq *q, const __be64 *rsp, struct sge *s = &q->adap->sge; int cpl_trace_pkt = is_t4(q->adap->params.chip) ? CPL_TRACE_PKT : CPL_TRACE_PKT_T5; -#ifdef CONFIG_CHELSIO_T4_FCOE struct port_info *pi; -#endif if (unlikely(*(u8 *)rsp == cpl_trace_pkt)) return handle_trace_pkt(q->adap, si); @@ -1910,6 +1935,10 @@ int t4_ethrx_handler(struct sge_rspq *q, const __be64 *rsp, rxq->stats.pkts++; + pi = netdev_priv(skb->dev); + if (pi->rxtstamp) + cxgb4_sgetim_to_hwtstamp(q->adap, skb_hwtstamps(skb), + si->sgetstamp); if (csum_ok && (pkt->l2info & htonl(RXF_UDP_F | RXF_TCP_F))) { if (!pkt->ip_frag) { skb->ip_summed = CHECKSUM_UNNECESSARY; @@ -1926,7 +1955,6 @@ int t4_ethrx_handler(struct sge_rspq *q, const __be64 *rsp, #define CPL_RX_PKT_FLAGS (RXF_PSH_F | RXF_SYN_F | RXF_UDP_F | \ RXF_TCP_F | RXF_IP_F | RXF_IP6_F | RXF_LRO_F) - pi = netdev_priv(skb->dev); if (!(pkt->l2info & cpu_to_be32(CPL_RX_PKT_FLAGS))) { if ((pkt->l2info & cpu_to_be32(RXF_FCOE_F)) && (pi->fcoe.flags & CXGB_FCOE_ENABLED)) { @@ -2067,6 +2095,8 @@ static int process_responses(struct sge_rspq *q, int budget) unmap_rx_buf(q->adap, &rxq->fl); } + si.sgetstamp = SGE_TIMESTAMP_G( + be64_to_cpu(rc->last_flit)); /* * Last buffer remains mapped so explicitly make it * coherent for CPU access. diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h index 640369df8b3a..13708fde1668 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.h @@ -263,4 +263,9 @@ enum { #undef FLASH_START #undef FLASH_MAX_SIZE +#define SGE_TIMESTAMP_S 0 +#define SGE_TIMESTAMP_M 0xfffffffffffffffULL +#define SGE_TIMESTAMP_V(x) ((__u64)(x) << SGE_TIMESTAMP_S) +#define SGE_TIMESTAMP_G(x) (((__u64)(x) >> SGE_TIMESTAMP_S) & SGE_TIMESTAMP_M) + #endif /* __T4_HW_H */ diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c index a2c96fd88393..ff665493ca97 100644 --- a/drivers/net/ethernet/ethoc.c +++ b/drivers/net/ethernet/ethoc.c @@ -201,6 +201,7 @@ struct ethoc { void __iomem *membase; int dma_alloc; resource_size_t io_region_size; + bool big_endian; unsigned int num_bd; unsigned int num_tx; @@ -236,12 +237,18 @@ struct ethoc_bd { static inline u32 ethoc_read(struct ethoc *dev, loff_t offset) { - return ioread32(dev->iobase + offset); + if (dev->big_endian) + return ioread32be(dev->iobase + offset); + else + return ioread32(dev->iobase + offset); } static inline void ethoc_write(struct ethoc *dev, loff_t offset, u32 data) { - iowrite32(data, dev->iobase + offset); + if (dev->big_endian) + iowrite32be(data, dev->iobase + offset); + else + iowrite32(data, dev->iobase + offset); } static inline void ethoc_read_bd(struct ethoc *dev, int index, @@ -1106,6 +1113,9 @@ static int ethoc_probe(struct platform_device *pdev) priv->dma_alloc = buffer_size; } + priv->big_endian = pdata ? pdata->big_endian : + of_device_is_big_endian(pdev->dev.of_node); + /* calculate the number of TX/RX buffers, maximum 128 supported */ num_bd = min_t(unsigned int, 128, (netdev->mem_end - netdev->mem_start + 1) / ETHOC_BUFSIZ); diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index dd4ca39d5d8f..501e1438d153 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -3070,7 +3070,6 @@ static void fec_poll_controller(struct net_device *dev) } #endif -#define FEATURES_NEED_QUIESCE NETIF_F_RXCSUM static inline void fec_enet_set_netdev_features(struct net_device *netdev, netdev_features_t features) { @@ -3094,7 +3093,7 @@ static int fec_set_features(struct net_device *netdev, struct fec_enet_private *fep = netdev_priv(netdev); netdev_features_t changed = features ^ netdev->features; - if (netif_running(netdev) && changed & FEATURES_NEED_QUIESCE) { + if (netif_running(netdev) && changed & NETIF_F_RXCSUM) { napi_disable(&fep->napi); netif_tx_lock_bh(netdev); fec_stop(netdev); diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig index dead17b5d769..165b5a8aa2ea 100644 --- a/drivers/net/ethernet/hisilicon/Kconfig +++ b/drivers/net/ethernet/hisilicon/Kconfig @@ -5,7 +5,7 @@ config NET_VENDOR_HISILICON bool "Hisilicon devices" default y - depends on ARM + depends on ARM || ARM64 ---help--- If you have a network (Ethernet) card belonging to this class, say Y. @@ -27,8 +27,40 @@ config HIP04_ETH select PHYLIB select MARVELL_PHY select MFD_SYSCON + select HNS_MDIO ---help--- If you wish to compile a kernel for a hardware with hisilicon p04 SoC and want to use the internal ethernet then you should answer Y to this. +config HNS_MDIO + tristate "Hisilicon HNS MDIO device Support" + select MDIO + ---help--- + This selects the HNS MDIO support. It is needed by HNS_DSAF to access + the PHY + +config HNS + tristate "Hisilicon Network Subsystem Support (Framework)" + ---help--- + This selects the framework support for Hisilicon Network Subsystem. It + is needed by any driver which provides HNS acceleration engine or make + use of the engine + +config HNS_DSAF + tristate "Hisilicon HNS DSAF device Support" + select HNS + select HNS_MDIO + ---help--- + This selects the DSAF (Distributed System Area Frabric) network + acceleration engine support. The engine is used in Hisilicon hip05, + Hi1610 and further ICT SoC + +config HNS_ENET + tristate "Hisilicon HNS Ethernet Device Support" + select PHYLIB + select HNS + ---help--- + This selects the general ethernet driver for HNS. This module make + use of any HNS AE driver, such as HNS_DSAF + endif # NET_VENDOR_HISILICON diff --git a/drivers/net/ethernet/hisilicon/Makefile b/drivers/net/ethernet/hisilicon/Makefile index 6c14540a4dc5..390b71fb3000 100644 --- a/drivers/net/ethernet/hisilicon/Makefile +++ b/drivers/net/ethernet/hisilicon/Makefile @@ -3,4 +3,6 @@ # obj-$(CONFIG_HIX5HD2_GMAC) += hix5hd2_gmac.o -obj-$(CONFIG_HIP04_ETH) += hip04_mdio.o hip04_eth.o +obj-$(CONFIG_HIP04_ETH) += hip04_eth.o +obj-$(CONFIG_HNS_MDIO) += hns_mdio.o +obj-$(CONFIG_HNS) += hns/ diff --git a/drivers/net/ethernet/hisilicon/hip04_mdio.c b/drivers/net/ethernet/hisilicon/hip04_mdio.c deleted file mode 100644 index fca0a5be1f0f..000000000000 --- a/drivers/net/ethernet/hisilicon/hip04_mdio.c +++ /dev/null @@ -1,185 +0,0 @@ -/* Copyright (c) 2014 Linaro Ltd. - * Copyright (c) 2014 Hisilicon Limited. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ - -#include <linux/module.h> -#include <linux/platform_device.h> -#include <linux/io.h> -#include <linux/of_mdio.h> -#include <linux/delay.h> - -#define MDIO_CMD_REG 0x0 -#define MDIO_ADDR_REG 0x4 -#define MDIO_WDATA_REG 0x8 -#define MDIO_RDATA_REG 0xc -#define MDIO_STA_REG 0x10 - -#define MDIO_START BIT(14) -#define MDIO_R_VALID BIT(1) -#define MDIO_READ (BIT(12) | BIT(11) | MDIO_START) -#define MDIO_WRITE (BIT(12) | BIT(10) | MDIO_START) - -struct hip04_mdio_priv { - void __iomem *base; -}; - -#define WAIT_TIMEOUT 10 -static int hip04_mdio_wait_ready(struct mii_bus *bus) -{ - struct hip04_mdio_priv *priv = bus->priv; - int i; - - for (i = 0; readl_relaxed(priv->base + MDIO_CMD_REG) & MDIO_START; i++) { - if (i == WAIT_TIMEOUT) - return -ETIMEDOUT; - msleep(20); - } - - return 0; -} - -static int hip04_mdio_read(struct mii_bus *bus, int mii_id, int regnum) -{ - struct hip04_mdio_priv *priv = bus->priv; - u32 val; - int ret; - - ret = hip04_mdio_wait_ready(bus); - if (ret < 0) - goto out; - - val = regnum | (mii_id << 5) | MDIO_READ; - writel_relaxed(val, priv->base + MDIO_CMD_REG); - - ret = hip04_mdio_wait_ready(bus); - if (ret < 0) - goto out; - - val = readl_relaxed(priv->base + MDIO_STA_REG); - if (val & MDIO_R_VALID) { - dev_err(bus->parent, "SMI bus read not valid\n"); - ret = -ENODEV; - goto out; - } - - val = readl_relaxed(priv->base + MDIO_RDATA_REG); - ret = val & 0xFFFF; -out: - return ret; -} - -static int hip04_mdio_write(struct mii_bus *bus, int mii_id, - int regnum, u16 value) -{ - struct hip04_mdio_priv *priv = bus->priv; - u32 val; - int ret; - - ret = hip04_mdio_wait_ready(bus); - if (ret < 0) - goto out; - - writel_relaxed(value, priv->base + MDIO_WDATA_REG); - val = regnum | (mii_id << 5) | MDIO_WRITE; - writel_relaxed(val, priv->base + MDIO_CMD_REG); -out: - return ret; -} - -static int hip04_mdio_reset(struct mii_bus *bus) -{ - int temp, i; - - for (i = 0; i < PHY_MAX_ADDR; i++) { - hip04_mdio_write(bus, i, 22, 0); - temp = hip04_mdio_read(bus, i, MII_BMCR); - if (temp < 0) - continue; - - temp |= BMCR_RESET; - if (hip04_mdio_write(bus, i, MII_BMCR, temp) < 0) - continue; - } - - mdelay(500); - return 0; -} - -static int hip04_mdio_probe(struct platform_device *pdev) -{ - struct resource *r; - struct mii_bus *bus; - struct hip04_mdio_priv *priv; - int ret; - - bus = mdiobus_alloc_size(sizeof(struct hip04_mdio_priv)); - if (!bus) { - dev_err(&pdev->dev, "Cannot allocate MDIO bus\n"); - return -ENOMEM; - } - - bus->name = "hip04_mdio_bus"; - bus->read = hip04_mdio_read; - bus->write = hip04_mdio_write; - bus->reset = hip04_mdio_reset; - snprintf(bus->id, MII_BUS_ID_SIZE, "%s-mii", dev_name(&pdev->dev)); - bus->parent = &pdev->dev; - priv = bus->priv; - - r = platform_get_resource(pdev, IORESOURCE_MEM, 0); - priv->base = devm_ioremap_resource(&pdev->dev, r); - if (IS_ERR(priv->base)) { - ret = PTR_ERR(priv->base); - goto out_mdio; - } - - ret = of_mdiobus_register(bus, pdev->dev.of_node); - if (ret < 0) { - dev_err(&pdev->dev, "Cannot register MDIO bus (%d)\n", ret); - goto out_mdio; - } - - platform_set_drvdata(pdev, bus); - - return 0; - -out_mdio: - mdiobus_free(bus); - return ret; -} - -static int hip04_mdio_remove(struct platform_device *pdev) -{ - struct mii_bus *bus = platform_get_drvdata(pdev); - - mdiobus_unregister(bus); - mdiobus_free(bus); - - return 0; -} - -static const struct of_device_id hip04_mdio_match[] = { - { .compatible = "hisilicon,hip04-mdio" }, - { } -}; -MODULE_DEVICE_TABLE(of, hip04_mdio_match); - -static struct platform_driver hip04_mdio_driver = { - .probe = hip04_mdio_probe, - .remove = hip04_mdio_remove, - .driver = { - .name = "hip04-mdio", - .of_match_table = hip04_mdio_match, - }, -}; - -module_platform_driver(hip04_mdio_driver); - -MODULE_DESCRIPTION("HISILICON P04 MDIO interface driver"); -MODULE_LICENSE("GPL v2"); -MODULE_ALIAS("platform:hip04-mdio"); diff --git a/drivers/net/ethernet/hisilicon/hns/Makefile b/drivers/net/ethernet/hisilicon/hns/Makefile new file mode 100644 index 000000000000..6010c83e38d8 --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns/Makefile @@ -0,0 +1,12 @@ +# +# Makefile for the HISILICON network device drivers. +# + +obj-$(CONFIG_HNS) += hnae.o + +obj-$(CONFIG_HNS_DSAF) += hns_dsaf.o +hns_dsaf-objs = hns_ae_adapt.o hns_dsaf_gmac.o hns_dsaf_mac.o hns_dsaf_misc.o \ + hns_dsaf_main.o hns_dsaf_ppe.o hns_dsaf_rcb.o hns_dsaf_xgmac.o + +obj-$(CONFIG_HNS_ENET) += hns_enet_drv.o +hns_enet_drv-objs = hns_enet.o hns_ethtool.o diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.c b/drivers/net/ethernet/hisilicon/hns/hnae.c new file mode 100644 index 000000000000..0a0a9e80dcd7 --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns/hnae.c @@ -0,0 +1,507 @@ +/* + * Copyright (c) 2014-2015 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/dma-mapping.h> +#include <linux/interrupt.h> +#include <linux/skbuff.h> +#include <linux/slab.h> + +#include "hnae.h" + +#define cls_to_ae_dev(dev) container_of(dev, struct hnae_ae_dev, cls_dev) + +static struct class *hnae_class; + +static void +hnae_list_add(spinlock_t *lock, struct list_head *node, struct list_head *head) +{ + unsigned long flags; + + spin_lock_irqsave(lock, flags); + list_add_tail_rcu(node, head); + spin_unlock_irqrestore(lock, flags); +} + +static void hnae_list_del(spinlock_t *lock, struct list_head *node) +{ + unsigned long flags; + + spin_lock_irqsave(lock, flags); + list_del_rcu(node); + spin_unlock_irqrestore(lock, flags); +} + +static int hnae_alloc_buffer(struct hnae_ring *ring, struct hnae_desc_cb *cb) +{ + unsigned int order = hnae_page_order(ring); + struct page *p = dev_alloc_pages(order); + + if (!p) + return -ENOMEM; + + cb->priv = p; + cb->page_offset = 0; + cb->reuse_flag = 0; + cb->buf = page_address(p); + cb->length = hnae_page_size(ring); + cb->type = DESC_TYPE_PAGE; + + return 0; +} + +static void hnae_free_buffer(struct hnae_ring *ring, struct hnae_desc_cb *cb) +{ + if (cb->type == DESC_TYPE_SKB) + dev_kfree_skb_any((struct sk_buff *)cb->priv); + else if (unlikely(is_rx_ring(ring))) + put_page((struct page *)cb->priv); + memset(cb, 0, sizeof(*cb)); +} + +static int hnae_map_buffer(struct hnae_ring *ring, struct hnae_desc_cb *cb) +{ + cb->dma = dma_map_page(ring_to_dev(ring), cb->priv, 0, + cb->length, ring_to_dma_dir(ring)); + + if (dma_mapping_error(ring_to_dev(ring), cb->dma)) + return -EIO; + + return 0; +} + +static void hnae_unmap_buffer(struct hnae_ring *ring, struct hnae_desc_cb *cb) +{ + if (cb->type == DESC_TYPE_SKB) + dma_unmap_single(ring_to_dev(ring), cb->dma, cb->length, + ring_to_dma_dir(ring)); + else + dma_unmap_page(ring_to_dev(ring), cb->dma, cb->length, + ring_to_dma_dir(ring)); +} + +static struct hnae_buf_ops hnae_bops = { + .alloc_buffer = hnae_alloc_buffer, + .free_buffer = hnae_free_buffer, + .map_buffer = hnae_map_buffer, + .unmap_buffer = hnae_unmap_buffer, +}; + +static int __ae_match(struct device *dev, const void *data) +{ + struct hnae_ae_dev *hdev = cls_to_ae_dev(dev); + const char *ae_id = data; + + if (!strncmp(ae_id, hdev->name, AE_NAME_SIZE)) + return 1; + + return 0; +} + +static struct hnae_ae_dev *find_ae(const char *ae_id) +{ + struct device *dev; + + WARN_ON(!ae_id); + + dev = class_find_device(hnae_class, NULL, ae_id, __ae_match); + + return dev ? cls_to_ae_dev(dev) : NULL; +} + +static void hnae_free_buffers(struct hnae_ring *ring) +{ + int i; + + for (i = 0; i < ring->desc_num; i++) + hnae_free_buffer_detach(ring, i); +} + +/* Allocate memory for raw pkg, and map with dma */ +static int hnae_alloc_buffers(struct hnae_ring *ring) +{ + int i, j, ret; + + for (i = 0; i < ring->desc_num; i++) { + ret = hnae_alloc_buffer_attach(ring, i); + if (ret) + goto out_buffer_fail; + } + + return 0; + +out_buffer_fail: + for (j = i - 1; j >= 0; j--) + hnae_free_buffer_detach(ring, j); + return ret; +} + +/* free desc along with its attached buffer */ +static void hnae_free_desc(struct hnae_ring *ring) +{ + hnae_free_buffers(ring); + dma_unmap_single(ring_to_dev(ring), ring->desc_dma_addr, + ring->desc_num * sizeof(ring->desc[0]), + ring_to_dma_dir(ring)); + ring->desc_dma_addr = 0; + kfree(ring->desc); + ring->desc = NULL; +} + +/* alloc desc, without buffer attached */ +static int hnae_alloc_desc(struct hnae_ring *ring) +{ + int size = ring->desc_num * sizeof(ring->desc[0]); + + ring->desc = kzalloc(size, GFP_KERNEL); + if (!ring->desc) + return -ENOMEM; + + ring->desc_dma_addr = dma_map_single(ring_to_dev(ring), + ring->desc, size, ring_to_dma_dir(ring)); + if (dma_mapping_error(ring_to_dev(ring), ring->desc_dma_addr)) { + ring->desc_dma_addr = 0; + kfree(ring->desc); + ring->desc = NULL; + return -ENOMEM; + } + + return 0; +} + +/* fini ring, also free the buffer for the ring */ +static void hnae_fini_ring(struct hnae_ring *ring) +{ + hnae_free_desc(ring); + kfree(ring->desc_cb); + ring->desc_cb = NULL; + ring->next_to_clean = 0; + ring->next_to_use = 0; +} + +/* init ring, and with buffer for rx ring */ +static int +hnae_init_ring(struct hnae_queue *q, struct hnae_ring *ring, int flags) +{ + int ret; + + if (ring->desc_num <= 0 || ring->buf_size <= 0) + return -EINVAL; + + ring->q = q; + ring->flags = flags; + assert(!ring->desc && !ring->desc_cb && !ring->desc_dma_addr); + + /* not matter for tx or rx ring, the ntc and ntc start from 0 */ + assert(ring->next_to_use == 0); + assert(ring->next_to_clean == 0); + + ring->desc_cb = kcalloc(ring->desc_num, sizeof(ring->desc_cb[0]), + GFP_KERNEL); + if (!ring->desc_cb) { + ret = -ENOMEM; + goto out; + } + + ret = hnae_alloc_desc(ring); + if (ret) + goto out_with_desc_cb; + + if (is_rx_ring(ring)) { + ret = hnae_alloc_buffers(ring); + if (ret) + goto out_with_desc; + } + + return 0; + +out_with_desc: + hnae_free_desc(ring); +out_with_desc_cb: + kfree(ring->desc_cb); + ring->desc_cb = NULL; +out: + return ret; +} + +static int hnae_init_queue(struct hnae_handle *h, struct hnae_queue *q, + struct hnae_ae_dev *dev) +{ + int ret; + + q->dev = dev; + q->handle = h; + + ret = hnae_init_ring(q, &q->tx_ring, q->tx_ring.flags | RINGF_DIR); + if (ret) + goto out; + + ret = hnae_init_ring(q, &q->rx_ring, q->rx_ring.flags & ~RINGF_DIR); + if (ret) + goto out_with_tx_ring; + + if (dev->ops->init_queue) + dev->ops->init_queue(q); + + return 0; + +out_with_tx_ring: + hnae_fini_ring(&q->tx_ring); +out: + return ret; +} + +static void hnae_fini_queue(struct hnae_queue *q) +{ + if (q->dev->ops->fini_queue) + q->dev->ops->fini_queue(q); + + hnae_fini_ring(&q->tx_ring); + hnae_fini_ring(&q->rx_ring); +} + +/** + * ae_chain - define ae chain head + */ +static RAW_NOTIFIER_HEAD(ae_chain); + +int hnae_register_notifier(struct notifier_block *nb) +{ + return raw_notifier_chain_register(&ae_chain, nb); +} +EXPORT_SYMBOL(hnae_register_notifier); + +void hnae_unregister_notifier(struct notifier_block *nb) +{ + if (raw_notifier_chain_unregister(&ae_chain, nb)) + dev_err(NULL, "notifier chain unregister fail\n"); +} +EXPORT_SYMBOL(hnae_unregister_notifier); + +int hnae_reinit_handle(struct hnae_handle *handle) +{ + int i, j; + int ret; + + for (i = 0; i < handle->q_num; i++) /* free ring*/ + hnae_fini_queue(handle->qs[i]); + + if (handle->dev->ops->reset) + handle->dev->ops->reset(handle); + + for (i = 0; i < handle->q_num; i++) {/* reinit ring*/ + ret = hnae_init_queue(handle, handle->qs[i], handle->dev); + if (ret) + goto out_when_init_queue; + } + return 0; +out_when_init_queue: + for (j = i - 1; j >= 0; j--) + hnae_fini_queue(handle->qs[j]); + return ret; +} +EXPORT_SYMBOL(hnae_reinit_handle); + +/* hnae_get_handle - get a handle from the AE + * @owner_dev: the dev use this handle + * @ae_id: the id of the ae to be used + * @ae_opts: the options set for the handle + * @bops: the callbacks for buffer management + * + * return handle ptr or ERR_PTR + */ +struct hnae_handle *hnae_get_handle(struct device *owner_dev, + const char *ae_id, u32 port_id, + struct hnae_buf_ops *bops) +{ + struct hnae_ae_dev *dev; + struct hnae_handle *handle; + int i, j; + int ret; + + dev = find_ae(ae_id); + if (!dev) + return ERR_PTR(-ENODEV); + + handle = dev->ops->get_handle(dev, port_id); + if (IS_ERR(handle)) + return handle; + + handle->dev = dev; + handle->owner_dev = owner_dev; + handle->bops = bops ? bops : &hnae_bops; + handle->eport_id = port_id; + + for (i = 0; i < handle->q_num; i++) { + ret = hnae_init_queue(handle, handle->qs[i], dev); + if (ret) + goto out_when_init_queue; + } + + __module_get(dev->owner); + + hnae_list_add(&dev->lock, &handle->node, &dev->handle_list); + + return handle; + +out_when_init_queue: + for (j = i - 1; j >= 0; j--) + hnae_fini_queue(handle->qs[j]); + + return ERR_PTR(-ENOMEM); +} +EXPORT_SYMBOL(hnae_get_handle); + +void hnae_put_handle(struct hnae_handle *h) +{ + struct hnae_ae_dev *dev = h->dev; + int i; + + for (i = 0; i < h->q_num; i++) + hnae_fini_queue(h->qs[i]); + + if (h->dev->ops->reset) + h->dev->ops->reset(h); + + hnae_list_del(&dev->lock, &h->node); + + if (dev->ops->put_handle) + dev->ops->put_handle(h); + + module_put(dev->owner); +} +EXPORT_SYMBOL(hnae_put_handle); + +static void hnae_release(struct device *dev) +{ +} + +/** + * hnae_ae_register - register a AE engine to hnae framework + * @hdev: the hnae ae engine device + * @owner: the module who provides this dev + * NOTE: the duplicated name will not be checked + */ +int hnae_ae_register(struct hnae_ae_dev *hdev, struct module *owner) +{ + static atomic_t id = ATOMIC_INIT(-1); + int ret; + + if (!hdev->dev) + return -ENODEV; + + if (!hdev->ops || !hdev->ops->get_handle || + !hdev->ops->toggle_ring_irq || + !hdev->ops->toggle_queue_status || + !hdev->ops->get_status || !hdev->ops->adjust_link) + return -EINVAL; + + hdev->owner = owner; + hdev->id = (int)atomic_inc_return(&id); + hdev->cls_dev.parent = hdev->dev; + hdev->cls_dev.class = hnae_class; + hdev->cls_dev.release = hnae_release; + (void)dev_set_name(&hdev->cls_dev, "hnae%d", hdev->id); + ret = device_register(&hdev->cls_dev); + if (ret) + return ret; + + __module_get(THIS_MODULE); + + INIT_LIST_HEAD(&hdev->handle_list); + spin_lock_init(&hdev->lock); + + ret = raw_notifier_call_chain(&ae_chain, HNAE_AE_REGISTER, NULL); + if (ret) + dev_dbg(hdev->dev, + "has not notifier for AE: %s\n", hdev->name); + + return 0; +} +EXPORT_SYMBOL(hnae_ae_register); + +/** + * hnae_ae_unregister - unregisters a HNAE AE engine + * @cdev: the device to unregister + */ +void hnae_ae_unregister(struct hnae_ae_dev *hdev) +{ + device_unregister(&hdev->cls_dev); + module_put(THIS_MODULE); +} +EXPORT_SYMBOL(hnae_ae_unregister); + +static ssize_t handles_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + ssize_t s = 0; + struct hnae_ae_dev *hdev = cls_to_ae_dev(dev); + struct hnae_handle *h; + int i = 0, j; + + list_for_each_entry_rcu(h, &hdev->handle_list, node) { + s += sprintf(buf + s, "handle %d (eport_id=%u from %s):\n", + i++, h->eport_id, h->dev->name); + for (j = 0; j < h->q_num; j++) { + s += sprintf(buf + s, "\tqueue[%d] on 0x%llx\n", + j, (u64)h->qs[i]->io_base); +#define HANDEL_TX_MSG "\t\ttx_ring on 0x%llx:%u,%u,%u,%u,%u,%llu,%llu\n" + s += sprintf(buf + s, + HANDEL_TX_MSG, + (u64)h->qs[i]->tx_ring.io_base, + h->qs[i]->tx_ring.buf_size, + h->qs[i]->tx_ring.desc_num, + h->qs[i]->tx_ring.max_desc_num_per_pkt, + h->qs[i]->tx_ring.max_raw_data_sz_per_desc, + h->qs[i]->tx_ring.max_pkt_size, + h->qs[i]->tx_ring.stats.sw_err_cnt, + h->qs[i]->tx_ring.stats.io_err_cnt); + s += sprintf(buf + s, + "\t\trx_ring on 0x%llx:%u,%u,%llu,%llu,%llu\n", + (u64)h->qs[i]->rx_ring.io_base, + h->qs[i]->rx_ring.buf_size, + h->qs[i]->rx_ring.desc_num, + h->qs[i]->rx_ring.stats.sw_err_cnt, + h->qs[i]->rx_ring.stats.io_err_cnt, + h->qs[i]->rx_ring.stats.seg_pkt_cnt); + } + } + + return s; +} + +static DEVICE_ATTR_RO(handles); +static struct attribute *hnae_class_attrs[] = { + &dev_attr_handles.attr, + NULL, +}; +ATTRIBUTE_GROUPS(hnae_class); + +static int __init hnae_init(void) +{ + hnae_class = class_create(THIS_MODULE, "hnae"); + if (IS_ERR(hnae_class)) + return PTR_ERR(hnae_class); + + hnae_class->dev_groups = hnae_class_groups; + return 0; +} + +static void __exit hnae_exit(void) +{ + class_destroy(hnae_class); +} + +subsys_initcall(hnae_init); +module_exit(hnae_exit); + +MODULE_AUTHOR("Hisilicon, Inc."); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Hisilicon Network Acceleration Engine Framework"); + +/* vi: set tw=78 noet: */ diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.h b/drivers/net/ethernet/hisilicon/hns/hnae.h new file mode 100644 index 000000000000..5edd8cdc2485 --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns/hnae.h @@ -0,0 +1,583 @@ +/* + * Copyright (c) 2014-2015 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef __HNAE_H +#define __HNAE_H + +/* Names used in this framework: + * ae handle (handle): + * a set of queues provided by AE + * ring buffer queue (rbq): + * the channel between upper layer and the AE, can do tx and rx + * ring: + * a tx or rx channel within a rbq + * ring description (desc): + * an element in the ring with packet information + * buffer: + * a memory region referred by desc with the full packet payload + * + * "num" means a static number set as a parameter, "count" mean a dynamic + * number set while running + * "cb" means control block + */ + +#include <linux/delay.h> +#include <linux/device.h> +#include <linux/module.h> +#include <linux/netdevice.h> +#include <linux/notifier.h> +#include <linux/types.h> + +#define HNAE_DRIVER_VERSION "1.3.0" +#define HNAE_DRIVER_NAME "hns" +#define HNAE_COPYRIGHT "Copyright(c) 2015 Huawei Corporation." +#define HNAE_DRIVER_STRING "Hisilicon Network Subsystem Driver" +#define HNAE_DEFAULT_DEVICE_DESCR "Hisilicon Network Subsystem" + +#ifdef DEBUG + +#ifndef assert +#define assert(expr) \ +do { \ + if (!(expr)) { \ + pr_err("Assertion failed! %s, %s, %s, line %d\n", \ + #expr, __FILE__, __func__, __LINE__); \ + } \ +} while (0) +#endif + +#else + +#ifndef assert +#define assert(expr) +#endif + +#endif + +#define AE_VERSION_1 ('6' << 16 | '6' << 8 | '0') +#define AE_VERSION_2 ('1' << 24 | '6' << 16 | '1' << 8 | '0') +#define AE_NAME_SIZE 16 + +/* some said the RX and TX RCB format should not be the same in the future. But + * it is the same now... + */ +#define RCB_REG_BASEADDR_L 0x00 /* P660 support only 32bit accessing */ +#define RCB_REG_BASEADDR_H 0x04 +#define RCB_REG_BD_NUM 0x08 +#define RCB_REG_BD_LEN 0x0C +#define RCB_REG_PKTLINE 0x10 +#define RCB_REG_TAIL 0x18 +#define RCB_REG_HEAD 0x1C +#define RCB_REG_FBDNUM 0x20 +#define RCB_REG_OFFSET 0x24 /* pkt num to be handled */ +#define RCB_REG_PKTNUM_RECORD 0x2C /* total pkt received */ + +#define HNS_RX_HEAD_SIZE 256 + +#define HNAE_AE_REGISTER 0x1 + +#define RCB_RING_NAME_LEN 16 + +enum hnae_led_state { + HNAE_LED_INACTIVE, + HNAE_LED_ACTIVE, + HNAE_LED_ON, + HNAE_LED_OFF +}; + +#define HNS_RX_FLAG_VLAN_PRESENT 0x1 +#define HNS_RX_FLAG_L3ID_IPV4 0x0 +#define HNS_RX_FLAG_L3ID_IPV6 0x1 +#define HNS_RX_FLAG_L4ID_UDP 0x0 +#define HNS_RX_FLAG_L4ID_TCP 0x1 + +#define HNS_TXD_ASID_S 0 +#define HNS_TXD_ASID_M (0xff << HNS_TXD_ASID_S) +#define HNS_TXD_BUFNUM_S 8 +#define HNS_TXD_BUFNUM_M (0x3 << HNS_TXD_BUFNUM_S) +#define HNS_TXD_PORTID_S 10 +#define HNS_TXD_PORTID_M (0x7 << HNS_TXD_PORTID_S) + +#define HNS_TXD_RA_B 8 +#define HNS_TXD_RI_B 9 +#define HNS_TXD_L4CS_B 10 +#define HNS_TXD_L3CS_B 11 +#define HNS_TXD_FE_B 12 +#define HNS_TXD_VLD_B 13 +#define HNS_TXD_IPOFFSET_S 14 +#define HNS_TXD_IPOFFSET_M (0xff << HNS_TXD_IPOFFSET_S) + +#define HNS_RXD_IPOFFSET_S 0 +#define HNS_RXD_IPOFFSET_M (0xff << HNS_TXD_IPOFFSET_S) +#define HNS_RXD_BUFNUM_S 8 +#define HNS_RXD_BUFNUM_M (0x3 << HNS_RXD_BUFNUM_S) +#define HNS_RXD_PORTID_S 10 +#define HNS_RXD_PORTID_M (0x7 << HNS_RXD_PORTID_S) +#define HNS_RXD_DMAC_S 13 +#define HNS_RXD_DMAC_M (0x3 << HNS_RXD_DMAC_S) +#define HNS_RXD_VLAN_S 15 +#define HNS_RXD_VLAN_M (0x3 << HNS_RXD_VLAN_S) +#define HNS_RXD_L3ID_S 17 +#define HNS_RXD_L3ID_M (0xf << HNS_RXD_L3ID_S) +#define HNS_RXD_L4ID_S 21 +#define HNS_RXD_L4ID_M (0xf << HNS_RXD_L4ID_S) +#define HNS_RXD_FE_B 25 +#define HNS_RXD_FRAG_B 26 +#define HNS_RXD_VLD_B 27 +#define HNS_RXD_L2E_B 28 +#define HNS_RXD_L3E_B 29 +#define HNS_RXD_L4E_B 30 +#define HNS_RXD_DROP_B 31 + +#define HNS_RXD_VLANID_S 8 +#define HNS_RXD_VLANID_M (0xfff << HNS_RXD_VLANID_S) +#define HNS_RXD_CFI_B 20 +#define HNS_RXD_PRI_S 21 +#define HNS_RXD_PRI_M (0x7 << HNS_RXD_PRI_S) +#define HNS_RXD_ASID_S 24 +#define HNS_RXD_ASID_M (0xff << HNS_RXD_ASID_S) + +/* hardware spec ring buffer format */ +struct __packed hnae_desc { + __le64 addr; + union { + struct { + __le16 asid_bufnum_pid; + __le16 send_size; + __le32 flag_ipoffset; + __le32 reserved_3[4]; + } tx; + + struct { + __le32 ipoff_bnum_pid_flag; + __le16 pkt_len; + __le16 size; + __le32 vlan_pri_asid; + __le32 reserved_2[3]; + } rx; + }; +}; + +struct hnae_desc_cb { + dma_addr_t dma; /* dma address of this desc */ + void *buf; /* cpu addr for a desc */ + + /* priv data for the desc, e.g. skb when use with ip stack*/ + void *priv; + u16 page_offset; + u16 reuse_flag; + + u16 length; /* length of the buffer */ + + /* desc type, used by the ring user to mark the type of the priv data */ + u16 type; +}; + +#define setflags(flags, bits) ((flags) |= (bits)) +#define unsetflags(flags, bits) ((flags) &= ~(bits)) + +/* hnae_ring->flags fields */ +#define RINGF_DIR 0x1 /* TX or RX ring, set if TX */ +#define is_tx_ring(ring) ((ring)->flags & RINGF_DIR) +#define is_rx_ring(ring) (!is_tx_ring(ring)) +#define ring_to_dma_dir(ring) (is_tx_ring(ring) ? \ + DMA_TO_DEVICE : DMA_FROM_DEVICE) + +struct ring_stats { + u64 io_err_cnt; + u64 sw_err_cnt; + u64 seg_pkt_cnt; + union { + struct { + u64 tx_pkts; + u64 tx_bytes; + u64 tx_err_cnt; + u64 restart_queue; + u64 tx_busy; + }; + struct { + u64 rx_pkts; + u64 rx_bytes; + u64 rx_err_cnt; + u64 reuse_pg_cnt; + u64 err_pkt_len; + u64 non_vld_descs; + u64 err_bd_num; + u64 l2_err; + u64 l3l4_csum_err; + }; + }; +}; + +struct hnae_queue; + +struct hnae_ring { + u8 __iomem *io_base; /* base io address for the ring */ + struct hnae_desc *desc; /* dma map address space */ + struct hnae_desc_cb *desc_cb; + struct hnae_queue *q; + int irq; + char ring_name[RCB_RING_NAME_LEN]; + + /* statistic */ + struct ring_stats stats; + + dma_addr_t desc_dma_addr; + u32 buf_size; /* size for hnae_desc->addr, preset by AE */ + u16 desc_num; /* total number of desc */ + u16 max_desc_num_per_pkt; + u16 max_raw_data_sz_per_desc; + u16 max_pkt_size; + int next_to_use; /* idx of next spare desc */ + + /* idx of lastest sent desc, the ring is empty when equal to + * next_to_use + */ + int next_to_clean; + + int flags; /* ring attribute */ + int irq_init_flag; +}; + +#define ring_ptr_move_fw(ring, p) \ + ((ring)->p = ((ring)->p + 1) % (ring)->desc_num) +#define ring_ptr_move_bw(ring, p) \ + ((ring)->p = ((ring)->p - 1 + (ring)->desc_num) % (ring)->desc_num) + +enum hns_desc_type { + DESC_TYPE_SKB, + DESC_TYPE_PAGE, +}; + +#define assert_is_ring_idx(ring, idx) \ + assert((idx) >= 0 && (idx) < (ring)->desc_num) + +/* the distance between [begin, end) in a ring buffer + * note: there is a unuse slot between the begin and the end + */ +static inline int ring_dist(struct hnae_ring *ring, int begin, int end) +{ + assert_is_ring_idx(ring, begin); + assert_is_ring_idx(ring, end); + + return (end - begin + ring->desc_num) % ring->desc_num; +} + +static inline int ring_space(struct hnae_ring *ring) +{ + return ring->desc_num - + ring_dist(ring, ring->next_to_clean, ring->next_to_use) - 1; +} + +static inline int is_ring_empty(struct hnae_ring *ring) +{ + assert_is_ring_idx(ring, ring->next_to_use); + assert_is_ring_idx(ring, ring->next_to_clean); + + return ring->next_to_use == ring->next_to_clean; +} + +#define hnae_buf_size(_ring) ((_ring)->buf_size) +#define hnae_page_order(_ring) (get_order(hnae_buf_size(_ring))) +#define hnae_page_size(_ring) (PAGE_SIZE << hnae_page_order(_ring)) + +struct hnae_handle; + +/* allocate and dma map space for hnae desc */ +struct hnae_buf_ops { + int (*alloc_buffer)(struct hnae_ring *ring, struct hnae_desc_cb *cb); + void (*free_buffer)(struct hnae_ring *ring, struct hnae_desc_cb *cb); + int (*map_buffer)(struct hnae_ring *ring, struct hnae_desc_cb *cb); + void (*unmap_buffer)(struct hnae_ring *ring, struct hnae_desc_cb *cb); +}; + +struct hnae_queue { + void __iomem *io_base; + phys_addr_t phy_base; + struct hnae_ae_dev *dev; /* the device who use this queue */ + struct hnae_ring rx_ring, tx_ring; + struct hnae_handle *handle; +}; + +/*hnae loop mode*/ +enum hnae_loop { + MAC_INTERNALLOOP_MAC = 0, + MAC_INTERNALLOOP_SERDES, + MAC_INTERNALLOOP_PHY, + MAC_LOOP_NONE, +}; + +/*hnae port type*/ +enum hnae_port_type { + HNAE_PORT_SERVICE = 0, + HNAE_PORT_DEBUG +}; + +/* This struct defines the operation on the handle. + * + * get_handle(): (mandatory) + * Get a handle from AE according to its name and options. + * the AE driver should manage the space used by handle and its queues while + * the HNAE framework will allocate desc and desc_cb for all rings in the + * queues. + * put_handle(): + * Release the handle. + * start(): + * Enable the hardware, include all queues + * stop(): + * Disable the hardware + * set_opts(): (mandatory) + * Set options to the AE + * get_opts(): (mandatory) + * Get options from the AE + * get_status(): + * Get the carrier state of the back channel of the handle, 1 for ok, 0 for + * non-ok + * toggle_ring_irq(): (mandatory) + * Set the ring irq to be enabled(0) or disable(1) + * toggle_queue_status(): (mandatory) + * Set the queue to be enabled(1) or disable(0), this will not change the + * ring irq state + * adjust_link() + * adjust link status + * set_loopback() + * set loopback + * get_ring_bdnum_limit() + * get ring bd number limit + * get_pauseparam() + * get tx and rx of pause frame use + * set_autoneg() + * set auto autonegotiation of pause frame use + * get_autoneg() + * get auto autonegotiation of pause frame use + * set_pauseparam() + * set tx and rx of pause frame use + * get_coalesce_usecs() + * get usecs to delay a TX interrupt after a packet is sent + * get_rx_max_coalesced_frames() + * get Maximum number of packets to be sent before a TX interrupt. + * set_coalesce_usecs() + * set usecs to delay a TX interrupt after a packet is sent + * set_coalesce_frames() + * set Maximum number of packets to be sent before a TX interrupt. + * get_ringnum() + * get RX/TX ring number + * get_max_ringnum() + * get RX/TX ring maximum number + * get_mac_addr() + * get mac address + * set_mac_addr() + * set mac address + * set_mc_addr() + * set multicast mode + * set_mtu() + * set mtu + * update_stats() + * update Old network device statistics + * get_ethtool_stats() + * get ethtool network device statistics + * get_strings() + * get a set of strings that describe the requested objects + * get_sset_count() + * get number of strings that @get_strings will write + * update_led_status() + * update the led status + * set_led_id() + * set led id + * get_regs() + * get regs dump + * get_regs_len() + * get the len of the regs dump + */ +struct hnae_ae_ops { + struct hnae_handle *(*get_handle)(struct hnae_ae_dev *dev, + u32 port_id); + void (*put_handle)(struct hnae_handle *handle); + void (*init_queue)(struct hnae_queue *q); + void (*fini_queue)(struct hnae_queue *q); + int (*start)(struct hnae_handle *handle); + void (*stop)(struct hnae_handle *handle); + void (*reset)(struct hnae_handle *handle); + int (*set_opts)(struct hnae_handle *handle, int type, void *opts); + int (*get_opts)(struct hnae_handle *handle, int type, void **opts); + int (*get_status)(struct hnae_handle *handle); + int (*get_info)(struct hnae_handle *handle, + u8 *auto_neg, u16 *speed, u8 *duplex); + void (*toggle_ring_irq)(struct hnae_ring *ring, u32 val); + void (*toggle_queue_status)(struct hnae_queue *queue, u32 val); + void (*adjust_link)(struct hnae_handle *handle, int speed, int duplex); + int (*set_loopback)(struct hnae_handle *handle, + enum hnae_loop loop_mode, int en); + void (*get_ring_bdnum_limit)(struct hnae_queue *queue, + u32 *uplimit); + void (*get_pauseparam)(struct hnae_handle *handle, + u32 *auto_neg, u32 *rx_en, u32 *tx_en); + int (*set_autoneg)(struct hnae_handle *handle, u8 enable); + int (*get_autoneg)(struct hnae_handle *handle); + int (*set_pauseparam)(struct hnae_handle *handle, + u32 auto_neg, u32 rx_en, u32 tx_en); + void (*get_coalesce_usecs)(struct hnae_handle *handle, + u32 *tx_usecs, u32 *rx_usecs); + void (*get_rx_max_coalesced_frames)(struct hnae_handle *handle, + u32 *tx_frames, u32 *rx_frames); + void (*set_coalesce_usecs)(struct hnae_handle *handle, u32 timeout); + int (*set_coalesce_frames)(struct hnae_handle *handle, + u32 coalesce_frames); + int (*get_mac_addr)(struct hnae_handle *handle, void **p); + int (*set_mac_addr)(struct hnae_handle *handle, void *p); + int (*set_mc_addr)(struct hnae_handle *handle, void *addr); + int (*set_mtu)(struct hnae_handle *handle, int new_mtu); + void (*update_stats)(struct hnae_handle *handle, + struct net_device_stats *net_stats); + void (*get_stats)(struct hnae_handle *handle, u64 *data); + void (*get_strings)(struct hnae_handle *handle, + u32 stringset, u8 *data); + int (*get_sset_count)(struct hnae_handle *handle, int stringset); + void (*update_led_status)(struct hnae_handle *handle); + int (*set_led_id)(struct hnae_handle *handle, + enum hnae_led_state status); + void (*get_regs)(struct hnae_handle *handle, void *data); + int (*get_regs_len)(struct hnae_handle *handle); +}; + +struct hnae_ae_dev { + struct device cls_dev; /* the class dev */ + struct device *dev; /* the presented dev */ + struct hnae_ae_ops *ops; + struct list_head node; + struct module *owner; /* the module who provides this dev */ + int id; + char name[AE_NAME_SIZE]; + struct list_head handle_list; + spinlock_t lock; /* lock to protect the handle_list */ +}; + +struct hnae_handle { + struct device *owner_dev; /* the device which make use of this handle */ + struct hnae_ae_dev *dev; /* the device who provides this handle */ + struct device_node *phy_node; + phy_interface_t phy_if; + u32 if_support; + int q_num; + int vf_id; + u32 eport_id; + enum hnae_port_type port_type; + struct list_head node; /* list to hnae_ae_dev->handle_list */ + struct hnae_buf_ops *bops; /* operation for the buffer */ + struct hnae_queue **qs; /* array base of all queues */ +}; + +#define ring_to_dev(ring) ((ring)->q->dev->dev) + +struct hnae_handle *hnae_get_handle(struct device *owner_dev, const char *ae_id, + u32 port_id, struct hnae_buf_ops *bops); +void hnae_put_handle(struct hnae_handle *handle); +int hnae_ae_register(struct hnae_ae_dev *dev, struct module *owner); +void hnae_ae_unregister(struct hnae_ae_dev *dev); + +int hnae_register_notifier(struct notifier_block *nb); +void hnae_unregister_notifier(struct notifier_block *nb); +int hnae_reinit_handle(struct hnae_handle *handle); + +#define hnae_queue_xmit(q, buf_num) writel_relaxed(buf_num, \ + (q)->tx_ring.io_base + RCB_REG_TAIL) + +#ifndef assert +#define assert(cond) +#endif + +static inline int hnae_reserve_buffer_map(struct hnae_ring *ring, + struct hnae_desc_cb *cb) +{ + struct hnae_buf_ops *bops = ring->q->handle->bops; + int ret; + + ret = bops->alloc_buffer(ring, cb); + if (ret) + goto out; + + ret = bops->map_buffer(ring, cb); + if (ret) + goto out_with_buf; + + return 0; + +out_with_buf: + bops->free_buffer(ring, cb); +out: + return ret; +} + +static inline int hnae_alloc_buffer_attach(struct hnae_ring *ring, int i) +{ + int ret = hnae_reserve_buffer_map(ring, &ring->desc_cb[i]); + + if (ret) + return ret; + + ring->desc[i].addr = (__le64)ring->desc_cb[i].dma; + + return 0; +} + +static inline void hnae_buffer_detach(struct hnae_ring *ring, int i) +{ + ring->q->handle->bops->unmap_buffer(ring, &ring->desc_cb[i]); + ring->desc[i].addr = 0; +} + +static inline void hnae_free_buffer_detach(struct hnae_ring *ring, int i) +{ + struct hnae_buf_ops *bops = ring->q->handle->bops; + struct hnae_desc_cb *cb = &ring->desc_cb[i]; + + if (!ring->desc_cb[i].dma) + return; + + hnae_buffer_detach(ring, i); + bops->free_buffer(ring, cb); +} + +/* detach a in-used buffer and replace with a reserved one */ +static inline void hnae_replace_buffer(struct hnae_ring *ring, int i, + struct hnae_desc_cb *res_cb) +{ + struct hnae_buf_ops *bops = ring->q->handle->bops; + struct hnae_desc_cb tmp_cb = ring->desc_cb[i]; + + bops->unmap_buffer(ring, &ring->desc_cb[i]); + ring->desc_cb[i] = *res_cb; + *res_cb = tmp_cb; + ring->desc[i].addr = (__le64)ring->desc_cb[i].dma; + ring->desc[i].rx.ipoff_bnum_pid_flag = 0; +} + +static inline void hnae_reuse_buffer(struct hnae_ring *ring, int i) +{ + ring->desc_cb[i].reuse_flag = 0; + ring->desc[i].addr = (__le64)(ring->desc_cb[i].dma + + ring->desc_cb[i].page_offset); + ring->desc[i].rx.ipoff_bnum_pid_flag = 0; +} + +#define hnae_set_field(origin, mask, shift, val) \ + do { \ + (origin) &= (~(mask)); \ + (origin) |= ((val) << (shift)) & (mask); \ + } while (0) + +#define hnae_set_bit(origin, shift, val) \ + hnae_set_field((origin), (0x1 << (shift)), (shift), (val)) + +#define hnae_get_field(origin, mask, shift) (((origin) & (mask)) >> (shift)) + +#define hnae_get_bit(origin, shift) \ + hnae_get_field((origin), (0x1 << (shift)), (shift)) + +#endif diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c new file mode 100644 index 000000000000..a2c72f84e397 --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c @@ -0,0 +1,777 @@ +/* + * Copyright (c) 2014-2015 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/etherdevice.h> +#include <linux/netdevice.h> +#include <linux/spinlock.h> + +#include "hnae.h" +#include "hns_dsaf_mac.h" +#include "hns_dsaf_main.h" +#include "hns_dsaf_ppe.h" +#include "hns_dsaf_rcb.h" + +#define AE_NAME_PORT_ID_IDX 6 +#define ETH_STATIC_REG 1 +#define ETH_DUMP_REG 5 +#define ETH_GSTRING_LEN 32 + +static struct hns_mac_cb *hns_get_mac_cb(struct hnae_handle *handle) +{ + struct hnae_vf_cb *vf_cb = hns_ae_get_vf_cb(handle); + + return vf_cb->mac_cb; +} + +/** + * hns_ae_map_eport_to_dport - translate enet port id to dsaf port id + * @port_id: enet port id + *: debug port 0-1, service port 2 -7 (dsaf mode only 2) + * return: dsaf port id + *: service ports 0 - 5, debug port 6-7 + **/ +static int hns_ae_map_eport_to_dport(u32 port_id) +{ + int port_index; + + if (port_id < DSAF_DEBUG_NW_NUM) + port_index = port_id + DSAF_SERVICE_PORT_NUM_PER_DSAF; + else + port_index = port_id - DSAF_DEBUG_NW_NUM; + + return port_index; +} + +static struct dsaf_device *hns_ae_get_dsaf_dev(struct hnae_ae_dev *dev) +{ + return container_of(dev, struct dsaf_device, ae_dev); +} + +static struct hns_ppe_cb *hns_get_ppe_cb(struct hnae_handle *handle) +{ + int ppe_index; + int ppe_common_index; + struct ppe_common_cb *ppe_comm; + struct hnae_vf_cb *vf_cb = hns_ae_get_vf_cb(handle); + + if (vf_cb->port_index < DSAF_SERVICE_PORT_NUM_PER_DSAF) { + ppe_index = vf_cb->port_index; + ppe_common_index = 0; + } else { + ppe_index = 0; + ppe_common_index = + vf_cb->port_index - DSAF_SERVICE_PORT_NUM_PER_DSAF + 1; + } + ppe_comm = vf_cb->dsaf_dev->ppe_common[ppe_common_index]; + return &ppe_comm->ppe_cb[ppe_index]; +} + +static int hns_ae_get_q_num_per_vf( + struct dsaf_device *dsaf_dev, int port) +{ + int common_idx = hns_dsaf_get_comm_idx_by_port(port); + + return dsaf_dev->rcb_common[common_idx]->max_q_per_vf; +} + +static int hns_ae_get_vf_num_per_port( + struct dsaf_device *dsaf_dev, int port) +{ + int common_idx = hns_dsaf_get_comm_idx_by_port(port); + + return dsaf_dev->rcb_common[common_idx]->max_vfn; +} + +static struct ring_pair_cb *hns_ae_get_base_ring_pair( + struct dsaf_device *dsaf_dev, int port) +{ + int common_idx = hns_dsaf_get_comm_idx_by_port(port); + struct rcb_common_cb *rcb_comm = dsaf_dev->rcb_common[common_idx]; + int q_num = rcb_comm->max_q_per_vf; + int vf_num = rcb_comm->max_vfn; + + if (common_idx == HNS_DSAF_COMM_SERVICE_NW_IDX) + return &rcb_comm->ring_pair_cb[port * q_num * vf_num]; + else + return &rcb_comm->ring_pair_cb[0]; +} + +static struct ring_pair_cb *hns_ae_get_ring_pair(struct hnae_queue *q) +{ + return container_of(q, struct ring_pair_cb, q); +} + +struct hnae_handle *hns_ae_get_handle(struct hnae_ae_dev *dev, + u32 port_id) +{ + int port_idx; + int vfnum_per_port; + int qnum_per_vf; + int i; + struct dsaf_device *dsaf_dev; + struct hnae_handle *ae_handle; + struct ring_pair_cb *ring_pair_cb; + struct hnae_vf_cb *vf_cb; + + dsaf_dev = hns_ae_get_dsaf_dev(dev); + port_idx = hns_ae_map_eport_to_dport(port_id); + + ring_pair_cb = hns_ae_get_base_ring_pair(dsaf_dev, port_idx); + vfnum_per_port = hns_ae_get_vf_num_per_port(dsaf_dev, port_idx); + qnum_per_vf = hns_ae_get_q_num_per_vf(dsaf_dev, port_idx); + + vf_cb = kzalloc(sizeof(*vf_cb) + + qnum_per_vf * sizeof(struct hnae_queue *), GFP_KERNEL); + if (unlikely(!vf_cb)) { + dev_err(dsaf_dev->dev, "malloc vf_cb fail!\n"); + ae_handle = ERR_PTR(-ENOMEM); + goto handle_err; + } + ae_handle = &vf_cb->ae_handle; + /* ae_handle Init */ + ae_handle->owner_dev = dsaf_dev->dev; + ae_handle->dev = dev; + ae_handle->q_num = qnum_per_vf; + + /* find ring pair, and set vf id*/ + for (ae_handle->vf_id = 0; + ae_handle->vf_id < vfnum_per_port; ae_handle->vf_id++) { + if (!ring_pair_cb->used_by_vf) + break; + ring_pair_cb += qnum_per_vf; + } + if (ae_handle->vf_id >= vfnum_per_port) { + dev_err(dsaf_dev->dev, "malloc queue fail!\n"); + ae_handle = ERR_PTR(-EINVAL); + goto vf_id_err; + } + + ae_handle->qs = (struct hnae_queue **)(&ae_handle->qs + 1); + for (i = 0; i < qnum_per_vf; i++) { + ae_handle->qs[i] = &ring_pair_cb->q; + ae_handle->qs[i]->rx_ring.q = ae_handle->qs[i]; + ae_handle->qs[i]->tx_ring.q = ae_handle->qs[i]; + + ring_pair_cb->used_by_vf = 1; + if (port_idx < DSAF_SERVICE_PORT_NUM_PER_DSAF) + ring_pair_cb->port_id_in_dsa = port_idx; + else + ring_pair_cb->port_id_in_dsa = 0; + + ring_pair_cb++; + } + + vf_cb->dsaf_dev = dsaf_dev; + vf_cb->port_index = port_idx; + vf_cb->mac_cb = &dsaf_dev->mac_cb[port_idx]; + + ae_handle->phy_if = vf_cb->mac_cb->phy_if; + ae_handle->phy_node = vf_cb->mac_cb->phy_node; + ae_handle->if_support = vf_cb->mac_cb->if_support; + ae_handle->port_type = vf_cb->mac_cb->mac_type; + + return ae_handle; +vf_id_err: + kfree(vf_cb); +handle_err: + return ae_handle; +} + +static void hns_ae_put_handle(struct hnae_handle *handle) +{ + struct hnae_vf_cb *vf_cb = hns_ae_get_vf_cb(handle); + int i; + + vf_cb->mac_cb = NULL; + + kfree(vf_cb); + + for (i = 0; i < handle->q_num; i++) + hns_ae_get_ring_pair(handle->qs[i])->used_by_vf = 0; +} + +static void hns_ae_ring_enable_all(struct hnae_handle *handle, int val) +{ + int q_num = handle->q_num; + int i; + + for (i = 0; i < q_num; i++) + hns_rcb_ring_enable_hw(handle->qs[i], val); +} + +static void hns_ae_init_queue(struct hnae_queue *q) +{ + struct ring_pair_cb *ring = + container_of(q, struct ring_pair_cb, q); + + hns_rcb_init_hw(ring); +} + +static void hns_ae_fini_queue(struct hnae_queue *q) +{ + struct hnae_vf_cb *vf_cb = hns_ae_get_vf_cb(q->handle); + + if (vf_cb->mac_cb->mac_type == HNAE_PORT_SERVICE) + hns_rcb_reset_ring_hw(q); +} + +static int hns_ae_set_mac_address(struct hnae_handle *handle, void *p) +{ + int ret; + struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle); + + if (!p || !is_valid_ether_addr((const u8 *)p)) { + dev_err(handle->owner_dev, "is not valid ether addr !\n"); + return -EADDRNOTAVAIL; + } + + ret = hns_mac_change_vf_addr(mac_cb, handle->vf_id, p); + if (ret != 0) { + dev_err(handle->owner_dev, + "set_mac_address fail, ret=%d!\n", ret); + return ret; + } + + return 0; +} + +static int hns_ae_set_multicast_one(struct hnae_handle *handle, void *addr) +{ + int ret; + char *mac_addr = (char *)addr; + struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle); + + assert(mac_cb); + + if (mac_cb->mac_type != HNAE_PORT_SERVICE) + return 0; + + ret = hns_mac_set_multi(mac_cb, mac_cb->mac_id, mac_addr, ENABLE); + if (ret) { + dev_err(handle->owner_dev, + "mac add mul_mac:%pM port%d fail, ret = %#x!\n", + mac_addr, mac_cb->mac_id, ret); + return ret; + } + + ret = hns_mac_set_multi(mac_cb, DSAF_BASE_INNER_PORT_NUM, + mac_addr, ENABLE); + if (ret) + dev_err(handle->owner_dev, + "mac add mul_mac:%pM port%d fail, ret = %#x!\n", + mac_addr, DSAF_BASE_INNER_PORT_NUM, ret); + + return ret; +} + +static int hns_ae_set_mtu(struct hnae_handle *handle, int new_mtu) +{ + struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle); + + return hns_mac_set_mtu(mac_cb, new_mtu); +} + +static int hns_ae_start(struct hnae_handle *handle) +{ + int ret; + struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle); + + ret = hns_mac_vm_config_bc_en(mac_cb, 0, ENABLE); + if (ret) + return ret; + + hns_ae_ring_enable_all(handle, 1); + msleep(100); + + hns_mac_start(mac_cb); + + return 0; +} + +void hns_ae_stop(struct hnae_handle *handle) +{ + struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle); + + /* just clean tx fbd, neednot rx fbd*/ + hns_rcb_wait_fbd_clean(handle->qs, handle->q_num, RCB_INT_FLAG_TX); + + msleep(20); + + hns_mac_stop(mac_cb); + + usleep_range(10000, 20000); + + hns_ae_ring_enable_all(handle, 0); + + (void)hns_mac_vm_config_bc_en(mac_cb, 0, DISABLE); +} + +static void hns_ae_reset(struct hnae_handle *handle) +{ + struct hnae_vf_cb *vf_cb = hns_ae_get_vf_cb(handle); + + if (vf_cb->mac_cb->mac_type == HNAE_PORT_DEBUG) { + u8 ppe_common_index = + vf_cb->port_index - DSAF_SERVICE_PORT_NUM_PER_DSAF + 1; + + hns_mac_reset(vf_cb->mac_cb); + hns_ppe_reset_common(vf_cb->dsaf_dev, ppe_common_index); + } +} + +void hns_ae_toggle_ring_irq(struct hnae_ring *ring, u32 mask) +{ + u32 flag; + + if (is_tx_ring(ring)) + flag = RCB_INT_FLAG_TX; + else + flag = RCB_INT_FLAG_RX; + + hns_rcb_int_clr_hw(ring->q, flag); + hns_rcb_int_ctrl_hw(ring->q, flag, mask); +} + +static void hns_ae_toggle_queue_status(struct hnae_queue *queue, u32 val) +{ + hns_rcb_start(queue, val); +} + +static int hns_ae_get_link_status(struct hnae_handle *handle) +{ + u32 link_status; + struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle); + + hns_mac_get_link_status(mac_cb, &link_status); + + return !!link_status; +} + +static int hns_ae_get_mac_info(struct hnae_handle *handle, + u8 *auto_neg, u16 *speed, u8 *duplex) +{ + struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle); + + return hns_mac_get_port_info(mac_cb, auto_neg, speed, duplex); +} + +static void hns_ae_adjust_link(struct hnae_handle *handle, int speed, + int duplex) +{ + struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle); + + hns_mac_adjust_link(mac_cb, speed, duplex); +} + +static void hns_ae_get_ring_bdnum_limit(struct hnae_queue *queue, + u32 *uplimit) +{ + *uplimit = HNS_RCB_RING_MAX_PENDING_BD; +} + +static void hns_ae_get_pauseparam(struct hnae_handle *handle, + u32 *auto_neg, u32 *rx_en, u32 *tx_en) +{ + assert(handle); + + hns_mac_get_autoneg(hns_get_mac_cb(handle), auto_neg); + + hns_mac_get_pauseparam(hns_get_mac_cb(handle), rx_en, tx_en); +} + +static int hns_ae_set_autoneg(struct hnae_handle *handle, u8 enable) +{ + assert(handle); + + return hns_mac_set_autoneg(hns_get_mac_cb(handle), enable); +} + +static int hns_ae_get_autoneg(struct hnae_handle *handle) +{ + u32 auto_neg; + + assert(handle); + + hns_mac_get_autoneg(hns_get_mac_cb(handle), &auto_neg); + + return auto_neg; +} + +static int hns_ae_set_pauseparam(struct hnae_handle *handle, + u32 autoneg, u32 rx_en, u32 tx_en) +{ + struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle); + int ret; + + ret = hns_mac_set_autoneg(mac_cb, autoneg); + if (ret) + return ret; + + return hns_mac_set_pauseparam(mac_cb, rx_en, tx_en); +} + +static void hns_ae_get_coalesce_usecs(struct hnae_handle *handle, + u32 *tx_usecs, u32 *rx_usecs) +{ + int port; + + port = hns_ae_map_eport_to_dport(handle->eport_id); + + *tx_usecs = hns_rcb_get_coalesce_usecs( + hns_ae_get_dsaf_dev(handle->dev), + hns_dsaf_get_comm_idx_by_port(port)); + *rx_usecs = hns_rcb_get_coalesce_usecs( + hns_ae_get_dsaf_dev(handle->dev), + hns_dsaf_get_comm_idx_by_port(port)); +} + +static void hns_ae_get_rx_max_coalesced_frames(struct hnae_handle *handle, + u32 *tx_frames, u32 *rx_frames) +{ + int port; + + assert(handle); + + port = hns_ae_map_eport_to_dport(handle->eport_id); + + *tx_frames = hns_rcb_get_coalesced_frames( + hns_ae_get_dsaf_dev(handle->dev), port); + *rx_frames = hns_rcb_get_coalesced_frames( + hns_ae_get_dsaf_dev(handle->dev), port); +} + +static void hns_ae_set_coalesce_usecs(struct hnae_handle *handle, + u32 timeout) +{ + int port; + + assert(handle); + + port = hns_ae_map_eport_to_dport(handle->eport_id); + + hns_rcb_set_coalesce_usecs(hns_ae_get_dsaf_dev(handle->dev), + port, timeout); +} + +static int hns_ae_set_coalesce_frames(struct hnae_handle *handle, + u32 coalesce_frames) +{ + int port; + int ret; + + assert(handle); + + port = hns_ae_map_eport_to_dport(handle->eport_id); + + ret = hns_rcb_set_coalesced_frames(hns_ae_get_dsaf_dev(handle->dev), + port, coalesce_frames); + return ret; +} + +void hns_ae_update_stats(struct hnae_handle *handle, + struct net_device_stats *net_stats) +{ + int port; + int idx; + struct dsaf_device *dsaf_dev; + struct hns_mac_cb *mac_cb; + struct hns_ppe_cb *ppe_cb; + struct hnae_queue *queue; + struct hnae_vf_cb *vf_cb = hns_ae_get_vf_cb(handle); + u64 tx_bytes = 0, rx_bytes = 0, tx_packets = 0, rx_packets = 0; + u64 rx_errors = 0, tx_errors = 0, tx_dropped = 0; + u64 rx_missed_errors = 0; + + dsaf_dev = hns_ae_get_dsaf_dev(handle->dev); + if (!dsaf_dev) + return; + port = vf_cb->port_index; + ppe_cb = hns_get_ppe_cb(handle); + mac_cb = hns_get_mac_cb(handle); + + for (idx = 0; idx < handle->q_num; idx++) { + queue = handle->qs[idx]; + hns_rcb_update_stats(queue); + + tx_bytes += queue->tx_ring.stats.tx_bytes; + tx_packets += queue->tx_ring.stats.tx_pkts; + rx_bytes += queue->rx_ring.stats.rx_bytes; + rx_packets += queue->rx_ring.stats.rx_pkts; + + rx_errors += queue->rx_ring.stats.err_pkt_len + + queue->rx_ring.stats.l2_err + + queue->rx_ring.stats.l3l4_csum_err; + } + + hns_ppe_update_stats(ppe_cb); + rx_missed_errors = ppe_cb->hw_stats.rx_drop_no_buf; + tx_errors += ppe_cb->hw_stats.tx_err_checksum + + ppe_cb->hw_stats.tx_err_fifo_empty; + + if (mac_cb->mac_type == HNAE_PORT_SERVICE) { + hns_dsaf_update_stats(dsaf_dev, port); + /* for port upline direction, i.e., rx. */ + rx_missed_errors += dsaf_dev->hw_stats[port].bp_drop; + rx_missed_errors += dsaf_dev->hw_stats[port].pad_drop; + rx_missed_errors += dsaf_dev->hw_stats[port].crc_false; + + /* for port downline direction, i.e., tx. */ + port = port + DSAF_PPE_INODE_BASE; + hns_dsaf_update_stats(dsaf_dev, port); + tx_dropped += dsaf_dev->hw_stats[port].bp_drop; + tx_dropped += dsaf_dev->hw_stats[port].pad_drop; + tx_dropped += dsaf_dev->hw_stats[port].crc_false; + tx_dropped += dsaf_dev->hw_stats[port].rslt_drop; + tx_dropped += dsaf_dev->hw_stats[port].vlan_drop; + tx_dropped += dsaf_dev->hw_stats[port].stp_drop; + } + + hns_mac_update_stats(mac_cb); + rx_errors += mac_cb->hw_stats.rx_fifo_overrun_err; + + tx_errors += mac_cb->hw_stats.tx_bad_pkts + + mac_cb->hw_stats.tx_fragment_err + + mac_cb->hw_stats.tx_jabber_err + + mac_cb->hw_stats.tx_underrun_err + + mac_cb->hw_stats.tx_crc_err; + + net_stats->tx_bytes = tx_bytes; + net_stats->tx_packets = tx_packets; + net_stats->rx_bytes = rx_bytes; + net_stats->rx_dropped = 0; + net_stats->rx_packets = rx_packets; + net_stats->rx_errors = rx_errors; + net_stats->tx_errors = tx_errors; + net_stats->tx_dropped = tx_dropped; + net_stats->rx_missed_errors = rx_missed_errors; + net_stats->rx_crc_errors = mac_cb->hw_stats.rx_fcs_err; + net_stats->rx_frame_errors = mac_cb->hw_stats.rx_align_err; + net_stats->rx_fifo_errors = mac_cb->hw_stats.rx_fifo_overrun_err; + net_stats->rx_length_errors = mac_cb->hw_stats.rx_len_err; + net_stats->multicast = mac_cb->hw_stats.rx_mc_pkts; +} + +void hns_ae_get_stats(struct hnae_handle *handle, u64 *data) +{ + int idx; + struct hns_mac_cb *mac_cb; + struct hns_ppe_cb *ppe_cb; + u64 *p = data; + struct hnae_vf_cb *vf_cb; + + if (!handle || !data) { + pr_err("hns_ae_get_stats NULL handle or data pointer!\n"); + return; + } + + vf_cb = hns_ae_get_vf_cb(handle); + mac_cb = hns_get_mac_cb(handle); + ppe_cb = hns_get_ppe_cb(handle); + + for (idx = 0; idx < handle->q_num; idx++) { + hns_rcb_get_stats(handle->qs[idx], p); + p += hns_rcb_get_ring_sset_count((int)ETH_SS_STATS); + } + + hns_ppe_get_stats(ppe_cb, p); + p += hns_ppe_get_sset_count((int)ETH_SS_STATS); + + hns_mac_get_stats(mac_cb, p); + p += hns_mac_get_sset_count(mac_cb, (int)ETH_SS_STATS); + + if (mac_cb->mac_type == HNAE_PORT_SERVICE) + hns_dsaf_get_stats(vf_cb->dsaf_dev, p, vf_cb->port_index); +} + +void hns_ae_get_strings(struct hnae_handle *handle, + u32 stringset, u8 *data) +{ + int port; + int idx; + struct hns_mac_cb *mac_cb; + struct hns_ppe_cb *ppe_cb; + u8 *p = data; + struct hnae_vf_cb *vf_cb; + + assert(handle); + + vf_cb = hns_ae_get_vf_cb(handle); + port = vf_cb->port_index; + mac_cb = hns_get_mac_cb(handle); + ppe_cb = hns_get_ppe_cb(handle); + + for (idx = 0; idx < handle->q_num; idx++) { + hns_rcb_get_strings(stringset, p, idx); + p += ETH_GSTRING_LEN * hns_rcb_get_ring_sset_count(stringset); + } + + hns_ppe_get_strings(ppe_cb, stringset, p); + p += ETH_GSTRING_LEN * hns_ppe_get_sset_count(stringset); + + hns_mac_get_strings(mac_cb, stringset, p); + p += ETH_GSTRING_LEN * hns_mac_get_sset_count(mac_cb, stringset); + + if (mac_cb->mac_type == HNAE_PORT_SERVICE) + hns_dsaf_get_strings(stringset, p, port); +} + +int hns_ae_get_sset_count(struct hnae_handle *handle, int stringset) +{ + u32 sset_count = 0; + struct hns_mac_cb *mac_cb; + + assert(handle); + + mac_cb = hns_get_mac_cb(handle); + + sset_count += hns_rcb_get_ring_sset_count(stringset) * handle->q_num; + sset_count += hns_ppe_get_sset_count(stringset); + sset_count += hns_mac_get_sset_count(mac_cb, stringset); + + if (mac_cb->mac_type == HNAE_PORT_SERVICE) + sset_count += hns_dsaf_get_sset_count(stringset); + + return sset_count; +} + +static int hns_ae_config_loopback(struct hnae_handle *handle, + enum hnae_loop loop, int en) +{ + int ret; + struct hnae_vf_cb *vf_cb = hns_ae_get_vf_cb(handle); + + switch (loop) { + case MAC_INTERNALLOOP_SERDES: + ret = hns_mac_config_sds_loopback(vf_cb->mac_cb, en); + break; + case MAC_INTERNALLOOP_MAC: + ret = hns_mac_config_mac_loopback(vf_cb->mac_cb, loop, en); + break; + default: + ret = -EINVAL; + } + return ret; +} + +void hns_ae_update_led_status(struct hnae_handle *handle) +{ + struct hns_mac_cb *mac_cb; + + assert(handle); + mac_cb = hns_get_mac_cb(handle); + if (!mac_cb->cpld_vaddr) + return; + hns_set_led_opt(mac_cb); +} + +int hns_ae_cpld_set_led_id(struct hnae_handle *handle, + enum hnae_led_state status) +{ + struct hns_mac_cb *mac_cb; + + assert(handle); + + mac_cb = hns_get_mac_cb(handle); + + return hns_cpld_led_set_id(mac_cb, status); +} + +void hns_ae_get_regs(struct hnae_handle *handle, void *data) +{ + u32 *p = data; + u32 rcb_com_idx; + int i; + struct hnae_vf_cb *vf_cb = hns_ae_get_vf_cb(handle); + struct hns_ppe_cb *ppe_cb = hns_get_ppe_cb(handle); + + hns_ppe_get_regs(ppe_cb, p); + p += hns_ppe_get_regs_count(); + + rcb_com_idx = hns_dsaf_get_comm_idx_by_port(vf_cb->port_index); + hns_rcb_get_common_regs(vf_cb->dsaf_dev->rcb_common[rcb_com_idx], p); + p += hns_rcb_get_common_regs_count(); + + for (i = 0; i < handle->q_num; i++) { + hns_rcb_get_ring_regs(handle->qs[i], p); + p += hns_rcb_get_ring_regs_count(); + } + + hns_mac_get_regs(vf_cb->mac_cb, p); + p += hns_mac_get_regs_count(vf_cb->mac_cb); + + if (vf_cb->mac_cb->mac_type == HNAE_PORT_SERVICE) + hns_dsaf_get_regs(vf_cb->dsaf_dev, vf_cb->port_index, p); +} + +int hns_ae_get_regs_len(struct hnae_handle *handle) +{ + u32 total_num; + struct hnae_vf_cb *vf_cb = hns_ae_get_vf_cb(handle); + + total_num = hns_ppe_get_regs_count(); + total_num += hns_rcb_get_common_regs_count(); + total_num += hns_rcb_get_ring_regs_count() * handle->q_num; + total_num += hns_mac_get_regs_count(vf_cb->mac_cb); + + if (vf_cb->mac_cb->mac_type == HNAE_PORT_SERVICE) + total_num += hns_dsaf_get_regs_count(); + + return total_num; +} + +static struct hnae_ae_ops hns_dsaf_ops = { + .get_handle = hns_ae_get_handle, + .put_handle = hns_ae_put_handle, + .init_queue = hns_ae_init_queue, + .fini_queue = hns_ae_fini_queue, + .start = hns_ae_start, + .stop = hns_ae_stop, + .reset = hns_ae_reset, + .toggle_ring_irq = hns_ae_toggle_ring_irq, + .toggle_queue_status = hns_ae_toggle_queue_status, + .get_status = hns_ae_get_link_status, + .get_info = hns_ae_get_mac_info, + .adjust_link = hns_ae_adjust_link, + .set_loopback = hns_ae_config_loopback, + .get_ring_bdnum_limit = hns_ae_get_ring_bdnum_limit, + .get_pauseparam = hns_ae_get_pauseparam, + .set_autoneg = hns_ae_set_autoneg, + .get_autoneg = hns_ae_get_autoneg, + .set_pauseparam = hns_ae_set_pauseparam, + .get_coalesce_usecs = hns_ae_get_coalesce_usecs, + .get_rx_max_coalesced_frames = hns_ae_get_rx_max_coalesced_frames, + .set_coalesce_usecs = hns_ae_set_coalesce_usecs, + .set_coalesce_frames = hns_ae_set_coalesce_frames, + .set_mac_addr = hns_ae_set_mac_address, + .set_mc_addr = hns_ae_set_multicast_one, + .set_mtu = hns_ae_set_mtu, + .update_stats = hns_ae_update_stats, + .get_stats = hns_ae_get_stats, + .get_strings = hns_ae_get_strings, + .get_sset_count = hns_ae_get_sset_count, + .update_led_status = hns_ae_update_led_status, + .set_led_id = hns_ae_cpld_set_led_id, + .get_regs = hns_ae_get_regs, + .get_regs_len = hns_ae_get_regs_len +}; + +int hns_dsaf_ae_init(struct dsaf_device *dsaf_dev) +{ + struct hnae_ae_dev *ae_dev = &dsaf_dev->ae_dev; + + ae_dev->ops = &hns_dsaf_ops; + ae_dev->dev = dsaf_dev->dev; + + return hnae_ae_register(ae_dev, THIS_MODULE); +} + +void hns_dsaf_ae_uninit(struct dsaf_device *dsaf_dev) +{ + hnae_ae_unregister(&dsaf_dev->ae_dev); +} diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c new file mode 100644 index 000000000000..b8517b00e706 --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c @@ -0,0 +1,704 @@ +/* + * Copyright (c) 2014-2015 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/delay.h> +#include <linux/of_mdio.h> +#include "hns_dsaf_main.h" +#include "hns_dsaf_mac.h" +#include "hns_dsaf_gmac.h" + +static const struct mac_stats_string g_gmac_stats_string[] = { + {"gmac_rx_octets_total_ok", MAC_STATS_FIELD_OFF(rx_good_bytes)}, + {"gmac_rx_octets_bad", MAC_STATS_FIELD_OFF(rx_bad_bytes)}, + {"gmac_rx_uc_pkts", MAC_STATS_FIELD_OFF(rx_uc_pkts)}, + {"gamc_rx_mc_pkts", MAC_STATS_FIELD_OFF(rx_mc_pkts)}, + {"gmac_rx_bc_pkts", MAC_STATS_FIELD_OFF(rx_bc_pkts)}, + {"gmac_rx_pkts_64octets", MAC_STATS_FIELD_OFF(rx_64bytes)}, + {"gmac_rx_pkts_65to127", MAC_STATS_FIELD_OFF(rx_65to127)}, + {"gmac_rx_pkts_128to255", MAC_STATS_FIELD_OFF(rx_128to255)}, + {"gmac_rx_pkts_256to511", MAC_STATS_FIELD_OFF(rx_256to511)}, + {"gmac_rx_pkts_512to1023", MAC_STATS_FIELD_OFF(rx_512to1023)}, + {"gmac_rx_pkts_1024to1518", MAC_STATS_FIELD_OFF(rx_1024to1518)}, + {"gmac_rx_pkts_1519tomax", MAC_STATS_FIELD_OFF(rx_1519tomax)}, + {"gmac_rx_fcs_errors", MAC_STATS_FIELD_OFF(rx_fcs_err)}, + {"gmac_rx_tagged", MAC_STATS_FIELD_OFF(rx_vlan_pkts)}, + {"gmac_rx_data_err", MAC_STATS_FIELD_OFF(rx_data_err)}, + {"gmac_rx_align_errors", MAC_STATS_FIELD_OFF(rx_align_err)}, + {"gmac_rx_long_errors", MAC_STATS_FIELD_OFF(rx_oversize)}, + {"gmac_rx_jabber_errors", MAC_STATS_FIELD_OFF(rx_jabber_err)}, + {"gmac_rx_pause_maccontrol", MAC_STATS_FIELD_OFF(rx_pfc_tc0)}, + {"gmac_rx_unknown_maccontrol", MAC_STATS_FIELD_OFF(rx_unknown_ctrl)}, + {"gmac_rx_very_long_err", MAC_STATS_FIELD_OFF(rx_long_err)}, + {"gmac_rx_runt_err", MAC_STATS_FIELD_OFF(rx_minto64)}, + {"gmac_rx_short_err", MAC_STATS_FIELD_OFF(rx_under_min)}, + {"gmac_rx_filt_pkt", MAC_STATS_FIELD_OFF(rx_filter_bytes)}, + {"gmac_rx_octets_total_filt", MAC_STATS_FIELD_OFF(rx_filter_pkts)}, + {"gmac_rx_overrun_cnt", MAC_STATS_FIELD_OFF(rx_fifo_overrun_err)}, + {"gmac_rx_length_err", MAC_STATS_FIELD_OFF(rx_len_err)}, + {"gmac_rx_fail_comma", MAC_STATS_FIELD_OFF(rx_comma_err)}, + + {"gmac_tx_octets_ok", MAC_STATS_FIELD_OFF(tx_good_bytes)}, + {"gmac_tx_octets_bad", MAC_STATS_FIELD_OFF(tx_bad_bytes)}, + {"gmac_tx_uc_pkts", MAC_STATS_FIELD_OFF(tx_uc_pkts)}, + {"gmac_tx_mc_pkts", MAC_STATS_FIELD_OFF(tx_mc_pkts)}, + {"gmac_tx_bc_pkts", MAC_STATS_FIELD_OFF(tx_bc_pkts)}, + {"gmac_tx_pkts_64octets", MAC_STATS_FIELD_OFF(tx_64bytes)}, + {"gmac_tx_pkts_65to127", MAC_STATS_FIELD_OFF(tx_65to127)}, + {"gmac_tx_pkts_128to255", MAC_STATS_FIELD_OFF(tx_128to255)}, + {"gmac_tx_pkts_256to511", MAC_STATS_FIELD_OFF(tx_256to511)}, + {"gmac_tx_pkts_512to1023", MAC_STATS_FIELD_OFF(tx_512to1023)}, + {"gmac_tx_pkts_1024to1518", MAC_STATS_FIELD_OFF(tx_1024to1518)}, + {"gmac_tx_pkts_1519tomax", MAC_STATS_FIELD_OFF(tx_1519tomax)}, + {"gmac_tx_excessive_length_drop", MAC_STATS_FIELD_OFF(tx_jabber_err)}, + {"gmac_tx_underrun", MAC_STATS_FIELD_OFF(tx_underrun_err)}, + {"gmac_tx_tagged", MAC_STATS_FIELD_OFF(tx_vlan)}, + {"gmac_tx_crc_error", MAC_STATS_FIELD_OFF(tx_crc_err)}, + {"gmac_tx_pause_frames", MAC_STATS_FIELD_OFF(tx_pfc_tc0)} +}; + +static void hns_gmac_enable(void *mac_drv, enum mac_commom_mode mode) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + + /*enable GE rX/tX */ + if ((mode == MAC_COMM_MODE_TX) || (mode == MAC_COMM_MODE_RX_AND_TX)) + dsaf_set_dev_bit(drv, GMAC_PORT_EN_REG, GMAC_PORT_TX_EN_B, 1); + + if ((mode == MAC_COMM_MODE_RX) || (mode == MAC_COMM_MODE_RX_AND_TX)) + dsaf_set_dev_bit(drv, GMAC_PORT_EN_REG, GMAC_PORT_RX_EN_B, 1); +} + +static void hns_gmac_disable(void *mac_drv, enum mac_commom_mode mode) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + + /*disable GE rX/tX */ + if ((mode == MAC_COMM_MODE_TX) || (mode == MAC_COMM_MODE_RX_AND_TX)) + dsaf_set_dev_bit(drv, GMAC_PORT_EN_REG, GMAC_PORT_TX_EN_B, 0); + + if ((mode == MAC_COMM_MODE_RX) || (mode == MAC_COMM_MODE_RX_AND_TX)) + dsaf_set_dev_bit(drv, GMAC_PORT_EN_REG, GMAC_PORT_RX_EN_B, 0); +} + +/** +*hns_gmac_get_en - get port enable +*@mac_drv:mac device +*@rx:rx enable +*@tx:tx enable +*/ +static void hns_gmac_get_en(void *mac_drv, u32 *rx, u32 *tx) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + u32 porten; + + porten = dsaf_read_dev(drv, GMAC_PORT_EN_REG); + *tx = dsaf_get_bit(porten, GMAC_PORT_TX_EN_B); + *rx = dsaf_get_bit(porten, GMAC_PORT_RX_EN_B); +} + +static void hns_gmac_free(void *mac_drv) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + struct dsaf_device *dsaf_dev + = (struct dsaf_device *)dev_get_drvdata(drv->dev); + + u32 mac_id = drv->mac_id; + + hns_dsaf_ge_srst_by_port(dsaf_dev, mac_id, 0); +} + +static void hns_gmac_set_tx_auto_pause_frames(void *mac_drv, u16 newval) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + + dsaf_set_dev_field(drv, GMAC_FC_TX_TIMER_REG, GMAC_FC_TX_TIMER_M, + GMAC_FC_TX_TIMER_S, newval); +} + +static void hns_gmac_get_tx_auto_pause_frames(void *mac_drv, u16 *newval) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + + *newval = dsaf_get_dev_field(drv, GMAC_FC_TX_TIMER_REG, + GMAC_FC_TX_TIMER_M, GMAC_FC_TX_TIMER_S); +} + +static void hns_gmac_set_rx_auto_pause_frames(void *mac_drv, u32 newval) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + + dsaf_set_dev_bit(drv, GMAC_PAUSE_EN_REG, + GMAC_PAUSE_EN_RX_FDFC_B, !!newval); +} + +static void hns_gmac_config_max_frame_length(void *mac_drv, u16 newval) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + + dsaf_set_dev_field(drv, GMAC_MAX_FRM_SIZE_REG, GMAC_MAX_FRM_SIZE_M, + GMAC_MAX_FRM_SIZE_S, newval); + + dsaf_set_dev_field(drv, GAMC_RX_MAX_FRAME, GMAC_MAX_FRM_SIZE_M, + GMAC_MAX_FRM_SIZE_S, newval); +} + +static void hns_gmac_config_an_mode(void *mac_drv, u8 newval) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + + dsaf_set_dev_bit(drv, GMAC_TRANSMIT_CONTROL_REG, + GMAC_TX_AN_EN_B, !!newval); +} + +static void hns_gmac_tx_loop_pkt_dis(void *mac_drv) +{ + u32 tx_loop_pkt_pri; + struct mac_driver *drv = (struct mac_driver *)mac_drv; + + tx_loop_pkt_pri = dsaf_read_dev(drv, GMAC_TX_LOOP_PKT_PRI_REG); + dsaf_set_bit(tx_loop_pkt_pri, GMAC_TX_LOOP_PKT_EN_B, 1); + dsaf_set_bit(tx_loop_pkt_pri, GMAC_TX_LOOP_PKT_HIG_PRI_B, 0); + dsaf_write_dev(drv, GMAC_TX_LOOP_PKT_PRI_REG, tx_loop_pkt_pri); +} + +static void hns_gmac_set_duplex_type(void *mac_drv, u8 newval) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + + dsaf_set_dev_bit(drv, GMAC_DUPLEX_TYPE_REG, + GMAC_DUPLEX_TYPE_B, !!newval); +} + +static void hns_gmac_get_duplex_type(void *mac_drv, + enum hns_gmac_duplex_mdoe *duplex_mode) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + + *duplex_mode = (enum hns_gmac_duplex_mdoe)dsaf_get_dev_bit( + drv, GMAC_DUPLEX_TYPE_REG, GMAC_DUPLEX_TYPE_B); +} + +static void hns_gmac_get_port_mode(void *mac_drv, enum hns_port_mode *port_mode) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + + *port_mode = (enum hns_port_mode)dsaf_get_dev_field( + drv, GMAC_PORT_MODE_REG, GMAC_PORT_MODE_M, GMAC_PORT_MODE_S); +} + +static void hns_gmac_port_mode_get(void *mac_drv, + struct hns_gmac_port_mode_cfg *port_mode) +{ + u32 tx_ctrl; + u32 recv_ctrl; + struct mac_driver *drv = (struct mac_driver *)mac_drv; + + port_mode->port_mode = (enum hns_port_mode)dsaf_get_dev_field( + drv, GMAC_PORT_MODE_REG, GMAC_PORT_MODE_M, GMAC_PORT_MODE_S); + + tx_ctrl = dsaf_read_dev(drv, GMAC_TRANSMIT_CONTROL_REG); + recv_ctrl = dsaf_read_dev(drv, GMAC_RECV_CONTROL_REG); + + port_mode->max_frm_size = + dsaf_get_dev_field(drv, GMAC_MAX_FRM_SIZE_REG, + GMAC_MAX_FRM_SIZE_M, GMAC_MAX_FRM_SIZE_S); + port_mode->short_runts_thr = + dsaf_get_dev_field(drv, GMAC_SHORT_RUNTS_THR_REG, + GMAC_SHORT_RUNTS_THR_M, + GMAC_SHORT_RUNTS_THR_S); + + port_mode->pad_enable = dsaf_get_bit(tx_ctrl, GMAC_TX_PAD_EN_B); + port_mode->crc_add = dsaf_get_bit(tx_ctrl, GMAC_TX_CRC_ADD_B); + port_mode->an_enable = dsaf_get_bit(tx_ctrl, GMAC_TX_AN_EN_B); + + port_mode->runt_pkt_en = + dsaf_get_bit(recv_ctrl, GMAC_RECV_CTRL_RUNT_PKT_EN_B); + port_mode->strip_pad_en = + dsaf_get_bit(recv_ctrl, GMAC_RECV_CTRL_STRIP_PAD_EN_B); +} + +static void hns_gmac_pause_frm_cfg(void *mac_drv, u32 rx_pause_en, + u32 tx_pause_en) +{ + u32 pause_en; + struct mac_driver *drv = (struct mac_driver *)mac_drv; + + pause_en = dsaf_read_dev(drv, GMAC_PAUSE_EN_REG); + dsaf_set_bit(pause_en, GMAC_PAUSE_EN_RX_FDFC_B, !!rx_pause_en); + dsaf_set_bit(pause_en, GMAC_PAUSE_EN_TX_FDFC_B, !!tx_pause_en); + dsaf_write_dev(drv, GMAC_PAUSE_EN_REG, pause_en); +} + +static void hns_gmac_get_pausefrm_cfg(void *mac_drv, u32 *rx_pause_en, + u32 *tx_pause_en) +{ + u32 pause_en; + struct mac_driver *drv = (struct mac_driver *)mac_drv; + + pause_en = dsaf_read_dev(drv, GMAC_PAUSE_EN_REG); + + *rx_pause_en = dsaf_get_bit(pause_en, GMAC_PAUSE_EN_RX_FDFC_B); + *tx_pause_en = dsaf_get_bit(pause_en, GMAC_PAUSE_EN_TX_FDFC_B); +} + +static int hns_gmac_adjust_link(void *mac_drv, enum mac_speed speed, + u32 full_duplex) +{ + u32 tx_ctrl; + struct mac_driver *drv = (struct mac_driver *)mac_drv; + + dsaf_set_dev_bit(drv, GMAC_DUPLEX_TYPE_REG, + GMAC_DUPLEX_TYPE_B, !!full_duplex); + + switch (speed) { + case MAC_SPEED_10: + dsaf_set_dev_field( + drv, GMAC_PORT_MODE_REG, + GMAC_PORT_MODE_M, GMAC_PORT_MODE_S, 0x6); + break; + case MAC_SPEED_100: + dsaf_set_dev_field( + drv, GMAC_PORT_MODE_REG, + GMAC_PORT_MODE_M, GMAC_PORT_MODE_S, 0x7); + break; + case MAC_SPEED_1000: + dsaf_set_dev_field( + drv, GMAC_PORT_MODE_REG, + GMAC_PORT_MODE_M, GMAC_PORT_MODE_S, 0x8); + break; + default: + dev_err(drv->dev, + "hns_gmac_adjust_link fail, speed%d mac%d\n", + speed, drv->mac_id); + return -EINVAL; + } + + tx_ctrl = dsaf_read_dev(drv, GMAC_TRANSMIT_CONTROL_REG); + dsaf_set_bit(tx_ctrl, GMAC_TX_PAD_EN_B, 1); + dsaf_set_bit(tx_ctrl, GMAC_TX_CRC_ADD_B, 1); + dsaf_write_dev(drv, GMAC_TRANSMIT_CONTROL_REG, tx_ctrl); + + dsaf_set_dev_bit(drv, GMAC_MODE_CHANGE_EN_REG, + GMAC_MODE_CHANGE_EB_B, 1); + + return 0; +} + +static void hns_gmac_init(void *mac_drv) +{ + u32 port; + struct mac_driver *drv = (struct mac_driver *)mac_drv; + struct dsaf_device *dsaf_dev + = (struct dsaf_device *)dev_get_drvdata(drv->dev); + + port = drv->mac_id; + + hns_dsaf_ge_srst_by_port(dsaf_dev, port, 0); + mdelay(10); + hns_dsaf_ge_srst_by_port(dsaf_dev, port, 1); + mdelay(10); + hns_gmac_disable(mac_drv, MAC_COMM_MODE_RX_AND_TX); + hns_gmac_tx_loop_pkt_dis(mac_drv); +} + +void hns_gmac_update_stats(void *mac_drv) +{ + struct mac_hw_stats *hw_stats = NULL; + struct mac_driver *drv = (struct mac_driver *)mac_drv; + + hw_stats = &drv->mac_cb->hw_stats; + + /* RX */ + hw_stats->rx_good_bytes + += dsaf_read_dev(drv, GMAC_RX_OCTETS_TOTAL_OK_REG); + hw_stats->rx_bad_bytes + += dsaf_read_dev(drv, GMAC_RX_OCTETS_BAD_REG); + hw_stats->rx_uc_pkts += dsaf_read_dev(drv, GMAC_RX_UC_PKTS_REG); + hw_stats->rx_mc_pkts += dsaf_read_dev(drv, GMAC_RX_MC_PKTS_REG); + hw_stats->rx_bc_pkts += dsaf_read_dev(drv, GMAC_RX_BC_PKTS_REG); + hw_stats->rx_64bytes + += dsaf_read_dev(drv, GMAC_RX_PKTS_64OCTETS_REG); + hw_stats->rx_65to127 + += dsaf_read_dev(drv, GMAC_RX_PKTS_65TO127OCTETS_REG); + hw_stats->rx_128to255 + += dsaf_read_dev(drv, GMAC_RX_PKTS_128TO255OCTETS_REG); + hw_stats->rx_256to511 + += dsaf_read_dev(drv, GMAC_RX_PKTS_255TO511OCTETS_REG); + hw_stats->rx_512to1023 + += dsaf_read_dev(drv, GMAC_RX_PKTS_512TO1023OCTETS_REG); + hw_stats->rx_1024to1518 + += dsaf_read_dev(drv, GMAC_RX_PKTS_1024TO1518OCTETS_REG); + hw_stats->rx_1519tomax + += dsaf_read_dev(drv, GMAC_RX_PKTS_1519TOMAXOCTETS_REG); + hw_stats->rx_fcs_err += dsaf_read_dev(drv, GMAC_RX_FCS_ERRORS_REG); + hw_stats->rx_vlan_pkts += dsaf_read_dev(drv, GMAC_RX_TAGGED_REG); + hw_stats->rx_data_err += dsaf_read_dev(drv, GMAC_RX_DATA_ERR_REG); + hw_stats->rx_align_err + += dsaf_read_dev(drv, GMAC_RX_ALIGN_ERRORS_REG); + hw_stats->rx_oversize + += dsaf_read_dev(drv, GMAC_RX_LONG_ERRORS_REG); + hw_stats->rx_jabber_err + += dsaf_read_dev(drv, GMAC_RX_JABBER_ERRORS_REG); + hw_stats->rx_pfc_tc0 + += dsaf_read_dev(drv, GMAC_RX_PAUSE_MACCTRL_FRAM_REG); + hw_stats->rx_unknown_ctrl + += dsaf_read_dev(drv, GMAC_RX_UNKNOWN_MACCTRL_FRAM_REG); + hw_stats->rx_long_err + += dsaf_read_dev(drv, GMAC_RX_VERY_LONG_ERR_CNT_REG); + hw_stats->rx_minto64 + += dsaf_read_dev(drv, GMAC_RX_RUNT_ERR_CNT_REG); + hw_stats->rx_under_min + += dsaf_read_dev(drv, GMAC_RX_SHORT_ERR_CNT_REG); + hw_stats->rx_filter_pkts + += dsaf_read_dev(drv, GMAC_RX_FILT_PKT_CNT_REG); + hw_stats->rx_filter_bytes + += dsaf_read_dev(drv, GMAC_RX_OCTETS_TOTAL_FILT_REG); + hw_stats->rx_fifo_overrun_err + += dsaf_read_dev(drv, GMAC_RX_OVERRUN_CNT_REG); + hw_stats->rx_len_err + += dsaf_read_dev(drv, GMAC_RX_LENGTHFIELD_ERR_CNT_REG); + hw_stats->rx_comma_err + += dsaf_read_dev(drv, GMAC_RX_FAIL_COMMA_CNT_REG); + + /* TX */ + hw_stats->tx_good_bytes + += dsaf_read_dev(drv, GMAC_OCTETS_TRANSMITTED_OK_REG); + hw_stats->tx_bad_bytes + += dsaf_read_dev(drv, GMAC_OCTETS_TRANSMITTED_BAD_REG); + hw_stats->tx_uc_pkts += dsaf_read_dev(drv, GMAC_TX_UC_PKTS_REG); + hw_stats->tx_mc_pkts += dsaf_read_dev(drv, GMAC_TX_MC_PKTS_REG); + hw_stats->tx_bc_pkts += dsaf_read_dev(drv, GMAC_TX_BC_PKTS_REG); + hw_stats->tx_64bytes + += dsaf_read_dev(drv, GMAC_TX_PKTS_64OCTETS_REG); + hw_stats->tx_65to127 + += dsaf_read_dev(drv, GMAC_TX_PKTS_65TO127OCTETS_REG); + hw_stats->tx_128to255 + += dsaf_read_dev(drv, GMAC_TX_PKTS_128TO255OCTETS_REG); + hw_stats->tx_256to511 + += dsaf_read_dev(drv, GMAC_TX_PKTS_255TO511OCTETS_REG); + hw_stats->tx_512to1023 + += dsaf_read_dev(drv, GMAC_TX_PKTS_512TO1023OCTETS_REG); + hw_stats->tx_1024to1518 + += dsaf_read_dev(drv, GMAC_TX_PKTS_1024TO1518OCTETS_REG); + hw_stats->tx_1519tomax + += dsaf_read_dev(drv, GMAC_TX_PKTS_1519TOMAXOCTETS_REG); + hw_stats->tx_jabber_err + += dsaf_read_dev(drv, GMAC_TX_EXCESSIVE_LENGTH_DROP_REG); + hw_stats->tx_underrun_err + += dsaf_read_dev(drv, GMAC_TX_UNDERRUN_REG); + hw_stats->tx_vlan += dsaf_read_dev(drv, GMAC_TX_TAGGED_REG); + hw_stats->tx_crc_err += dsaf_read_dev(drv, GMAC_TX_CRC_ERROR_REG); + hw_stats->tx_pfc_tc0 + += dsaf_read_dev(drv, GMAC_TX_PAUSE_FRAMES_REG); +} + +static void hns_gmac_set_mac_addr(void *mac_drv, char *mac_addr) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + + if (drv->mac_id >= DSAF_SERVICE_NW_NUM) { + u32 high_val = mac_addr[1] | (mac_addr[0] << 8); + + u32 low_val = mac_addr[5] | (mac_addr[4] << 8) + | (mac_addr[3] << 16) | (mac_addr[2] << 24); + dsaf_write_dev(drv, GMAC_STATION_ADDR_LOW_2_REG, low_val); + dsaf_write_dev(drv, GMAC_STATION_ADDR_HIGH_2_REG, high_val); + } +} + +static int hns_gmac_config_loopback(void *mac_drv, enum hnae_loop loop_mode, + u8 enable) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + + switch (loop_mode) { + case MAC_INTERNALLOOP_MAC: + dsaf_set_dev_bit(drv, GMAC_LOOP_REG, GMAC_LP_REG_CF2MI_LP_EN_B, + !!enable); + break; + default: + dev_err(drv->dev, "loop_mode error\n"); + return -EINVAL; + } + + return 0; +} + +static void hns_gmac_config_pad_and_crc(void *mac_drv, u8 newval) +{ + u32 tx_ctrl; + struct mac_driver *drv = (struct mac_driver *)mac_drv; + + tx_ctrl = dsaf_read_dev(drv, GMAC_TRANSMIT_CONTROL_REG); + dsaf_set_bit(tx_ctrl, GMAC_TX_PAD_EN_B, !!newval); + dsaf_set_bit(tx_ctrl, GMAC_TX_CRC_ADD_B, !!newval); + dsaf_write_dev(drv, GMAC_TRANSMIT_CONTROL_REG, tx_ctrl); +} + +static void hns_gmac_get_id(void *mac_drv, u8 *mac_id) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + + *mac_id = drv->mac_id; +} + +static void hns_gmac_get_info(void *mac_drv, struct mac_info *mac_info) +{ + enum hns_gmac_duplex_mdoe duplex; + enum hns_port_mode speed; + u32 rx_pause; + u32 tx_pause; + u32 rx; + u32 tx; + u16 fc_tx_timer; + struct hns_gmac_port_mode_cfg port_mode = { GMAC_10M_MII, 0 }; + + hns_gmac_port_mode_get(mac_drv, &port_mode); + mac_info->pad_and_crc_en = port_mode.crc_add && port_mode.pad_enable; + mac_info->auto_neg = port_mode.an_enable; + + hns_gmac_get_tx_auto_pause_frames(mac_drv, &fc_tx_timer); + mac_info->tx_pause_time = fc_tx_timer; + + hns_gmac_get_en(mac_drv, &rx, &tx); + mac_info->port_en = rx && tx; + + hns_gmac_get_duplex_type(mac_drv, &duplex); + mac_info->duplex = duplex; + + hns_gmac_get_port_mode(mac_drv, &speed); + switch (speed) { + case GMAC_10M_SGMII: + mac_info->speed = MAC_SPEED_10; + break; + case GMAC_100M_SGMII: + mac_info->speed = MAC_SPEED_100; + break; + case GMAC_1000M_SGMII: + mac_info->speed = MAC_SPEED_1000; + break; + default: + mac_info->speed = 0; + break; + } + + hns_gmac_get_pausefrm_cfg(mac_drv, &rx_pause, &tx_pause); + mac_info->rx_pause_en = rx_pause; + mac_info->tx_pause_en = tx_pause; +} + +static void hns_gmac_autoneg_stat(void *mac_drv, u32 *enable) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + + *enable = dsaf_get_dev_bit(drv, GMAC_TRANSMIT_CONTROL_REG, + GMAC_TX_AN_EN_B); +} + +static void hns_gmac_get_link_status(void *mac_drv, u32 *link_stat) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + + *link_stat = dsaf_get_dev_bit(drv, GMAC_AN_NEG_STATE_REG, + GMAC_AN_NEG_STAT_RX_SYNC_OK_B); +} + +static void hns_gmac_get_regs(void *mac_drv, void *data) +{ + u32 *regs = data; + int i; + struct mac_driver *drv = (struct mac_driver *)mac_drv; + + /* base config registers */ + regs[0] = dsaf_read_dev(drv, GMAC_DUPLEX_TYPE_REG); + regs[1] = dsaf_read_dev(drv, GMAC_FD_FC_TYPE_REG); + regs[2] = dsaf_read_dev(drv, GMAC_FC_TX_TIMER_REG); + regs[3] = dsaf_read_dev(drv, GMAC_FD_FC_ADDR_LOW_REG); + regs[4] = dsaf_read_dev(drv, GMAC_FD_FC_ADDR_HIGH_REG); + regs[5] = dsaf_read_dev(drv, GMAC_IPG_TX_TIMER_REG); + regs[6] = dsaf_read_dev(drv, GMAC_PAUSE_THR_REG); + regs[7] = dsaf_read_dev(drv, GMAC_MAX_FRM_SIZE_REG); + regs[8] = dsaf_read_dev(drv, GMAC_PORT_MODE_REG); + regs[9] = dsaf_read_dev(drv, GMAC_PORT_EN_REG); + regs[10] = dsaf_read_dev(drv, GMAC_PAUSE_EN_REG); + regs[11] = dsaf_read_dev(drv, GMAC_SHORT_RUNTS_THR_REG); + regs[12] = dsaf_read_dev(drv, GMAC_AN_NEG_STATE_REG); + regs[13] = dsaf_read_dev(drv, GMAC_TX_LOCAL_PAGE_REG); + regs[14] = dsaf_read_dev(drv, GMAC_TRANSMIT_CONTROL_REG); + regs[15] = dsaf_read_dev(drv, GMAC_REC_FILT_CONTROL_REG); + regs[16] = dsaf_read_dev(drv, GMAC_PTP_CONFIG_REG); + + /* rx static registers */ + regs[17] = dsaf_read_dev(drv, GMAC_RX_OCTETS_TOTAL_OK_REG); + regs[18] = dsaf_read_dev(drv, GMAC_RX_OCTETS_BAD_REG); + regs[19] = dsaf_read_dev(drv, GMAC_RX_UC_PKTS_REG); + regs[20] = dsaf_read_dev(drv, GMAC_RX_MC_PKTS_REG); + regs[21] = dsaf_read_dev(drv, GMAC_RX_BC_PKTS_REG); + regs[22] = dsaf_read_dev(drv, GMAC_RX_PKTS_64OCTETS_REG); + regs[23] = dsaf_read_dev(drv, GMAC_RX_PKTS_65TO127OCTETS_REG); + regs[24] = dsaf_read_dev(drv, GMAC_RX_PKTS_128TO255OCTETS_REG); + regs[25] = dsaf_read_dev(drv, GMAC_RX_PKTS_255TO511OCTETS_REG); + regs[26] = dsaf_read_dev(drv, GMAC_RX_PKTS_512TO1023OCTETS_REG); + regs[27] = dsaf_read_dev(drv, GMAC_RX_PKTS_1024TO1518OCTETS_REG); + regs[28] = dsaf_read_dev(drv, GMAC_RX_PKTS_1519TOMAXOCTETS_REG); + regs[29] = dsaf_read_dev(drv, GMAC_RX_FCS_ERRORS_REG); + regs[30] = dsaf_read_dev(drv, GMAC_RX_TAGGED_REG); + regs[31] = dsaf_read_dev(drv, GMAC_RX_DATA_ERR_REG); + regs[32] = dsaf_read_dev(drv, GMAC_RX_ALIGN_ERRORS_REG); + regs[33] = dsaf_read_dev(drv, GMAC_RX_LONG_ERRORS_REG); + regs[34] = dsaf_read_dev(drv, GMAC_RX_JABBER_ERRORS_REG); + regs[35] = dsaf_read_dev(drv, GMAC_RX_PAUSE_MACCTRL_FRAM_REG); + regs[36] = dsaf_read_dev(drv, GMAC_RX_UNKNOWN_MACCTRL_FRAM_REG); + regs[37] = dsaf_read_dev(drv, GMAC_RX_VERY_LONG_ERR_CNT_REG); + regs[38] = dsaf_read_dev(drv, GMAC_RX_RUNT_ERR_CNT_REG); + regs[39] = dsaf_read_dev(drv, GMAC_RX_SHORT_ERR_CNT_REG); + regs[40] = dsaf_read_dev(drv, GMAC_RX_FILT_PKT_CNT_REG); + regs[41] = dsaf_read_dev(drv, GMAC_RX_OCTETS_TOTAL_FILT_REG); + + /* tx static registers */ + regs[42] = dsaf_read_dev(drv, GMAC_OCTETS_TRANSMITTED_OK_REG); + regs[43] = dsaf_read_dev(drv, GMAC_OCTETS_TRANSMITTED_BAD_REG); + regs[44] = dsaf_read_dev(drv, GMAC_TX_UC_PKTS_REG); + regs[45] = dsaf_read_dev(drv, GMAC_TX_MC_PKTS_REG); + regs[46] = dsaf_read_dev(drv, GMAC_TX_BC_PKTS_REG); + regs[47] = dsaf_read_dev(drv, GMAC_TX_PKTS_64OCTETS_REG); + regs[48] = dsaf_read_dev(drv, GMAC_TX_PKTS_65TO127OCTETS_REG); + regs[49] = dsaf_read_dev(drv, GMAC_TX_PKTS_128TO255OCTETS_REG); + regs[50] = dsaf_read_dev(drv, GMAC_TX_PKTS_255TO511OCTETS_REG); + regs[51] = dsaf_read_dev(drv, GMAC_TX_PKTS_512TO1023OCTETS_REG); + regs[52] = dsaf_read_dev(drv, GMAC_TX_PKTS_1024TO1518OCTETS_REG); + regs[53] = dsaf_read_dev(drv, GMAC_TX_PKTS_1519TOMAXOCTETS_REG); + regs[54] = dsaf_read_dev(drv, GMAC_TX_EXCESSIVE_LENGTH_DROP_REG); + regs[55] = dsaf_read_dev(drv, GMAC_TX_UNDERRUN_REG); + regs[56] = dsaf_read_dev(drv, GMAC_TX_TAGGED_REG); + regs[57] = dsaf_read_dev(drv, GMAC_TX_CRC_ERROR_REG); + regs[58] = dsaf_read_dev(drv, GMAC_TX_PAUSE_FRAMES_REG); + + regs[59] = dsaf_read_dev(drv, GAMC_RX_MAX_FRAME); + regs[60] = dsaf_read_dev(drv, GMAC_LINE_LOOP_BACK_REG); + regs[61] = dsaf_read_dev(drv, GMAC_CF_CRC_STRIP_REG); + regs[62] = dsaf_read_dev(drv, GMAC_MODE_CHANGE_EN_REG); + regs[63] = dsaf_read_dev(drv, GMAC_SIXTEEN_BIT_CNTR_REG); + regs[64] = dsaf_read_dev(drv, GMAC_LD_LINK_COUNTER_REG); + regs[65] = dsaf_read_dev(drv, GMAC_LOOP_REG); + regs[66] = dsaf_read_dev(drv, GMAC_RECV_CONTROL_REG); + regs[67] = dsaf_read_dev(drv, GMAC_VLAN_CODE_REG); + regs[68] = dsaf_read_dev(drv, GMAC_RX_OVERRUN_CNT_REG); + regs[69] = dsaf_read_dev(drv, GMAC_RX_LENGTHFIELD_ERR_CNT_REG); + regs[70] = dsaf_read_dev(drv, GMAC_RX_FAIL_COMMA_CNT_REG); + + regs[71] = dsaf_read_dev(drv, GMAC_STATION_ADDR_LOW_0_REG); + regs[72] = dsaf_read_dev(drv, GMAC_STATION_ADDR_HIGH_0_REG); + regs[73] = dsaf_read_dev(drv, GMAC_STATION_ADDR_LOW_1_REG); + regs[74] = dsaf_read_dev(drv, GMAC_STATION_ADDR_HIGH_1_REG); + regs[75] = dsaf_read_dev(drv, GMAC_STATION_ADDR_LOW_2_REG); + regs[76] = dsaf_read_dev(drv, GMAC_STATION_ADDR_HIGH_2_REG); + regs[77] = dsaf_read_dev(drv, GMAC_STATION_ADDR_LOW_3_REG); + regs[78] = dsaf_read_dev(drv, GMAC_STATION_ADDR_HIGH_3_REG); + regs[79] = dsaf_read_dev(drv, GMAC_STATION_ADDR_LOW_4_REG); + regs[80] = dsaf_read_dev(drv, GMAC_STATION_ADDR_HIGH_4_REG); + regs[81] = dsaf_read_dev(drv, GMAC_STATION_ADDR_LOW_5_REG); + regs[82] = dsaf_read_dev(drv, GMAC_STATION_ADDR_HIGH_5_REG); + regs[83] = dsaf_read_dev(drv, GMAC_STATION_ADDR_LOW_MSK_0_REG); + regs[84] = dsaf_read_dev(drv, GMAC_STATION_ADDR_HIGH_MSK_0_REG); + regs[85] = dsaf_read_dev(drv, GMAC_STATION_ADDR_LOW_MSK_1_REG); + regs[86] = dsaf_read_dev(drv, GMAC_STATION_ADDR_HIGH_MSK_1_REG); + regs[87] = dsaf_read_dev(drv, GMAC_MAC_SKIP_LEN_REG); + regs[88] = dsaf_read_dev(drv, GMAC_TX_LOOP_PKT_PRI_REG); + + /* mark end of mac regs */ + for (i = 89; i < 96; i++) + regs[i] = 0xaaaaaaaa; +} + +static void hns_gmac_get_stats(void *mac_drv, u64 *data) +{ + u32 i; + u64 *buf = data; + struct mac_driver *drv = (struct mac_driver *)mac_drv; + struct mac_hw_stats *hw_stats = NULL; + + hw_stats = &drv->mac_cb->hw_stats; + + for (i = 0; i < ARRAY_SIZE(g_gmac_stats_string); i++) { + buf[i] = DSAF_STATS_READ(hw_stats, + g_gmac_stats_string[i].offset); + } +} + +static void hns_gmac_get_strings(u32 stringset, u8 *data) +{ + char *buff = (char *)data; + u32 i; + + if (stringset != ETH_SS_STATS) + return; + + for (i = 0; i < ARRAY_SIZE(g_gmac_stats_string); i++) { + snprintf(buff, ETH_GSTRING_LEN, g_gmac_stats_string[i].desc); + buff = buff + ETH_GSTRING_LEN; + } +} + +static int hns_gmac_get_sset_count(int stringset) +{ + if (stringset == ETH_SS_STATS) + return ARRAY_SIZE(g_gmac_stats_string); + + return 0; +} + +static int hns_gmac_get_regs_count(void) +{ + return ETH_GMAC_DUMP_NUM; +} + +void *hns_gmac_config(struct hns_mac_cb *mac_cb, struct mac_params *mac_param) +{ + struct mac_driver *mac_drv; + + mac_drv = devm_kzalloc(mac_cb->dev, sizeof(*mac_drv), GFP_KERNEL); + if (!mac_drv) + return NULL; + + mac_drv->mac_init = hns_gmac_init; + mac_drv->mac_enable = hns_gmac_enable; + mac_drv->mac_disable = hns_gmac_disable; + mac_drv->mac_free = hns_gmac_free; + mac_drv->adjust_link = hns_gmac_adjust_link; + mac_drv->set_tx_auto_pause_frames = hns_gmac_set_tx_auto_pause_frames; + mac_drv->config_max_frame_length = hns_gmac_config_max_frame_length; + mac_drv->mac_pausefrm_cfg = hns_gmac_pause_frm_cfg; + + mac_drv->mac_id = mac_param->mac_id; + mac_drv->mac_mode = mac_param->mac_mode; + mac_drv->io_base = mac_param->vaddr; + mac_drv->dev = mac_param->dev; + mac_drv->mac_cb = mac_cb; + + mac_drv->set_mac_addr = hns_gmac_set_mac_addr; + mac_drv->set_an_mode = hns_gmac_config_an_mode; + mac_drv->config_loopback = hns_gmac_config_loopback; + mac_drv->config_pad_and_crc = hns_gmac_config_pad_and_crc; + mac_drv->config_half_duplex = hns_gmac_set_duplex_type; + mac_drv->set_rx_ignore_pause_frames = hns_gmac_set_rx_auto_pause_frames; + mac_drv->mac_get_id = hns_gmac_get_id; + mac_drv->get_info = hns_gmac_get_info; + mac_drv->autoneg_stat = hns_gmac_autoneg_stat; + mac_drv->get_pause_enable = hns_gmac_get_pausefrm_cfg; + mac_drv->get_link_status = hns_gmac_get_link_status; + mac_drv->get_regs = hns_gmac_get_regs; + mac_drv->get_regs_count = hns_gmac_get_regs_count; + mac_drv->get_ethtool_stats = hns_gmac_get_stats; + mac_drv->get_sset_count = hns_gmac_get_sset_count; + mac_drv->get_strings = hns_gmac_get_strings; + mac_drv->update_stats = hns_gmac_update_stats; + + return (void *)mac_drv; +} diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.h new file mode 100644 index 000000000000..44fe3010dc6d --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.h @@ -0,0 +1,45 @@ +/* + * Copyright (c) 2014-2015 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef _HNS_GMAC_H +#define _HNS_GMAC_H + +#include "hns_dsaf_mac.h" + +enum hns_port_mode { + GMAC_10M_MII = 0, + GMAC_100M_MII, + GMAC_1000M_GMII, + GMAC_10M_RGMII, + GMAC_100M_RGMII, + GMAC_1000M_RGMII, + GMAC_10M_SGMII, + GMAC_100M_SGMII, + GMAC_1000M_SGMII, + GMAC_10000M_SGMII /* 10GE */ +}; + +enum hns_gmac_duplex_mdoe { + GMAC_HALF_DUPLEX_MODE = 0, + GMAC_FULL_DUPLEX_MODE +}; + +struct hns_gmac_port_mode_cfg { + enum hns_port_mode port_mode; + u32 max_frm_size; + u32 short_runts_thr; + u32 pad_enable; + u32 crc_add; + u32 an_enable; /*auto-nego enable */ + u32 runt_pkt_en; + u32 strip_pad_en; +}; + +#define ETH_GMAC_DUMP_NUM 96 +#endif /* __HNS_GMAC_H__ */ diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c new file mode 100644 index 000000000000..95bf42aae24c --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c @@ -0,0 +1,900 @@ +/* + * Copyright (c) 2014-2015 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/netdevice.h> +#include <linux/phy_fixed.h> +#include <linux/interrupt.h> +#include <linux/platform_device.h> +#include <linux/of.h> +#include <linux/of_address.h> + +#include "hns_dsaf_misc.h" +#include "hns_dsaf_main.h" +#include "hns_dsaf_rcb.h" + +#define MAC_EN_FLAG_V 0xada0328 + +static const u16 mac_phy_to_speed[] = { + [PHY_INTERFACE_MODE_MII] = MAC_SPEED_100, + [PHY_INTERFACE_MODE_GMII] = MAC_SPEED_1000, + [PHY_INTERFACE_MODE_SGMII] = MAC_SPEED_1000, + [PHY_INTERFACE_MODE_TBI] = MAC_SPEED_1000, + [PHY_INTERFACE_MODE_RMII] = MAC_SPEED_100, + [PHY_INTERFACE_MODE_RGMII] = MAC_SPEED_1000, + [PHY_INTERFACE_MODE_RGMII_ID] = MAC_SPEED_1000, + [PHY_INTERFACE_MODE_RGMII_RXID] = MAC_SPEED_1000, + [PHY_INTERFACE_MODE_RGMII_TXID] = MAC_SPEED_1000, + [PHY_INTERFACE_MODE_RTBI] = MAC_SPEED_1000, + [PHY_INTERFACE_MODE_XGMII] = MAC_SPEED_10000 +}; + +static const enum mac_mode g_mac_mode_100[] = { + [PHY_INTERFACE_MODE_MII] = MAC_MODE_MII_100, + [PHY_INTERFACE_MODE_RMII] = MAC_MODE_RMII_100 +}; + +static const enum mac_mode g_mac_mode_1000[] = { + [PHY_INTERFACE_MODE_GMII] = MAC_MODE_GMII_1000, + [PHY_INTERFACE_MODE_SGMII] = MAC_MODE_SGMII_1000, + [PHY_INTERFACE_MODE_TBI] = MAC_MODE_TBI_1000, + [PHY_INTERFACE_MODE_RGMII] = MAC_MODE_RGMII_1000, + [PHY_INTERFACE_MODE_RGMII_ID] = MAC_MODE_RGMII_1000, + [PHY_INTERFACE_MODE_RGMII_RXID] = MAC_MODE_RGMII_1000, + [PHY_INTERFACE_MODE_RGMII_TXID] = MAC_MODE_RGMII_1000, + [PHY_INTERFACE_MODE_RTBI] = MAC_MODE_RTBI_1000 +}; + +static enum mac_mode hns_mac_dev_to_enet_if(const struct hns_mac_cb *mac_cb) +{ + switch (mac_cb->max_speed) { + case MAC_SPEED_100: + return g_mac_mode_100[mac_cb->phy_if]; + case MAC_SPEED_1000: + return g_mac_mode_1000[mac_cb->phy_if]; + case MAC_SPEED_10000: + return MAC_MODE_XGMII_10000; + default: + return MAC_MODE_MII_100; + } +} + +static enum mac_mode hns_get_enet_interface(const struct hns_mac_cb *mac_cb) +{ + switch (mac_cb->max_speed) { + case MAC_SPEED_100: + return g_mac_mode_100[mac_cb->phy_if]; + case MAC_SPEED_1000: + return g_mac_mode_1000[mac_cb->phy_if]; + case MAC_SPEED_10000: + return MAC_MODE_XGMII_10000; + default: + return MAC_MODE_MII_100; + } +} + +int hns_mac_get_sfp_prsnt(struct hns_mac_cb *mac_cb, int *sfp_prsnt) +{ + if (!mac_cb->cpld_vaddr) + return -ENODEV; + + *sfp_prsnt = !dsaf_read_b((u8 *)mac_cb->cpld_vaddr + + MAC_SFP_PORT_OFFSET); + + return 0; +} + +void hns_mac_get_link_status(struct hns_mac_cb *mac_cb, u32 *link_status) +{ + struct mac_driver *mac_ctrl_drv; + int ret, sfp_prsnt; + + mac_ctrl_drv = hns_mac_get_drv(mac_cb); + + if (mac_ctrl_drv->get_link_status) + mac_ctrl_drv->get_link_status(mac_ctrl_drv, link_status); + else + *link_status = 0; + + ret = hns_mac_get_sfp_prsnt(mac_cb, &sfp_prsnt); + if (!ret) + *link_status = *link_status && sfp_prsnt; + + mac_cb->link = *link_status; +} + +int hns_mac_get_port_info(struct hns_mac_cb *mac_cb, + u8 *auto_neg, u16 *speed, u8 *duplex) +{ + struct mac_driver *mac_ctrl_drv; + struct mac_info info; + + mac_ctrl_drv = hns_mac_get_drv(mac_cb); + + if (!mac_ctrl_drv->get_info) + return -ENODEV; + + mac_ctrl_drv->get_info(mac_ctrl_drv, &info); + if (auto_neg) + *auto_neg = info.auto_neg; + if (speed) + *speed = info.speed; + if (duplex) + *duplex = info.duplex; + + return 0; +} + +void hns_mac_adjust_link(struct hns_mac_cb *mac_cb, int speed, int duplex) +{ + int ret; + struct mac_driver *mac_ctrl_drv; + + mac_ctrl_drv = (struct mac_driver *)(mac_cb->priv.mac); + + mac_cb->speed = speed; + mac_cb->half_duplex = !duplex; + mac_ctrl_drv->mac_mode = hns_mac_dev_to_enet_if(mac_cb); + + if (mac_ctrl_drv->adjust_link) { + ret = mac_ctrl_drv->adjust_link(mac_ctrl_drv, + (enum mac_speed)speed, duplex); + if (ret) { + dev_err(mac_cb->dev, + "adjust_link failed,%s mac%d ret = %#x!\n", + mac_cb->dsaf_dev->ae_dev.name, + mac_cb->mac_id, ret); + return; + } + } +} + +/** + *hns_mac_get_inner_port_num - get mac table inner port number + *@mac_cb: mac device + *@vmid: vm id + *@port_num:port number + * + */ +static int hns_mac_get_inner_port_num(struct hns_mac_cb *mac_cb, + u8 vmid, u8 *port_num) +{ + u8 tmp_port; + u32 comm_idx; + + if (mac_cb->dsaf_dev->dsaf_mode <= DSAF_MODE_ENABLE) { + if (mac_cb->mac_id != DSAF_MAX_PORT_NUM_PER_CHIP) { + dev_err(mac_cb->dev, + "input invalid,%s mac%d vmid%d !\n", + mac_cb->dsaf_dev->ae_dev.name, + mac_cb->mac_id, vmid); + return -EINVAL; + } + } else if (mac_cb->dsaf_dev->dsaf_mode < DSAF_MODE_MAX) { + if (mac_cb->mac_id <= DSAF_MAX_PORT_NUM_PER_CHIP) { + dev_err(mac_cb->dev, + "input invalid,%s mac%d vmid%d!\n", + mac_cb->dsaf_dev->ae_dev.name, + mac_cb->mac_id, vmid); + return -EINVAL; + } + } else { + dev_err(mac_cb->dev, "dsaf mode invalid,%s mac%d!\n", + mac_cb->dsaf_dev->ae_dev.name, mac_cb->mac_id); + return -EINVAL; + } + + comm_idx = hns_dsaf_get_comm_idx_by_port(mac_cb->mac_id); + + if (vmid >= mac_cb->dsaf_dev->rcb_common[comm_idx]->max_vfn) { + dev_err(mac_cb->dev, "input invalid,%s mac%d vmid%d !\n", + mac_cb->dsaf_dev->ae_dev.name, mac_cb->mac_id, vmid); + return -EINVAL; + } + + switch (mac_cb->dsaf_dev->dsaf_mode) { + case DSAF_MODE_ENABLE_FIX: + tmp_port = 0; + break; + case DSAF_MODE_DISABLE_FIX: + tmp_port = 0; + break; + case DSAF_MODE_ENABLE_0VM: + case DSAF_MODE_ENABLE_8VM: + case DSAF_MODE_ENABLE_16VM: + case DSAF_MODE_ENABLE_32VM: + case DSAF_MODE_ENABLE_128VM: + case DSAF_MODE_DISABLE_2PORT_8VM: + case DSAF_MODE_DISABLE_2PORT_16VM: + case DSAF_MODE_DISABLE_2PORT_64VM: + case DSAF_MODE_DISABLE_6PORT_0VM: + case DSAF_MODE_DISABLE_6PORT_2VM: + case DSAF_MODE_DISABLE_6PORT_4VM: + case DSAF_MODE_DISABLE_6PORT_16VM: + tmp_port = vmid; + break; + default: + dev_err(mac_cb->dev, "dsaf mode invalid,%s mac%d!\n", + mac_cb->dsaf_dev->ae_dev.name, mac_cb->mac_id); + return -EINVAL; + } + tmp_port += DSAF_BASE_INNER_PORT_NUM; + + *port_num = tmp_port; + + return 0; +} + +/** + *hns_mac_get_inner_port_num - change vf mac address + *@mac_cb: mac device + *@vmid: vmid + *@addr:mac address + */ +int hns_mac_change_vf_addr(struct hns_mac_cb *mac_cb, + u32 vmid, char *addr) +{ + int ret; + struct mac_driver *mac_ctrl_drv = hns_mac_get_drv(mac_cb); + struct dsaf_device *dsaf_dev = mac_cb->dsaf_dev; + struct dsaf_drv_mac_single_dest_entry mac_entry; + struct mac_entry_idx *old_entry; + + old_entry = &mac_cb->addr_entry_idx[vmid]; + if (dsaf_dev) { + memcpy(mac_entry.addr, addr, sizeof(mac_entry.addr)); + mac_entry.in_vlan_id = old_entry->vlan_id; + mac_entry.in_port_num = mac_cb->mac_id; + ret = hns_mac_get_inner_port_num(mac_cb, (u8)vmid, + &mac_entry.port_num); + if (ret) + return ret; + + if ((old_entry->valid != 0) && + (memcmp(old_entry->addr, + addr, sizeof(mac_entry.addr)) != 0)) { + ret = hns_dsaf_del_mac_entry(dsaf_dev, + old_entry->vlan_id, + mac_cb->mac_id, + old_entry->addr); + if (ret) + return ret; + } + + ret = hns_dsaf_set_mac_uc_entry(dsaf_dev, &mac_entry); + if (ret) + return ret; + } + + if ((mac_ctrl_drv->set_mac_addr) && (vmid == 0)) + mac_ctrl_drv->set_mac_addr(mac_cb->priv.mac, addr); + + memcpy(old_entry->addr, addr, sizeof(old_entry->addr)); + old_entry->valid = 1; + return 0; +} + +int hns_mac_set_multi(struct hns_mac_cb *mac_cb, + u32 port_num, char *addr, u8 en) +{ + int ret; + struct dsaf_device *dsaf_dev = mac_cb->dsaf_dev; + struct dsaf_drv_mac_single_dest_entry mac_entry; + + if (dsaf_dev && addr) { + memcpy(mac_entry.addr, addr, sizeof(mac_entry.addr)); + mac_entry.in_vlan_id = 0;/*vlan_id;*/ + mac_entry.in_port_num = mac_cb->mac_id; + mac_entry.port_num = port_num; + + if (en == DISABLE) + ret = hns_dsaf_del_mac_mc_port(dsaf_dev, &mac_entry); + else + ret = hns_dsaf_add_mac_mc_port(dsaf_dev, &mac_entry); + if (ret) { + dev_err(dsaf_dev->dev, + "set mac mc port failed,%s mac%d ret = %#x!\n", + mac_cb->dsaf_dev->ae_dev.name, + mac_cb->mac_id, ret); + return ret; + } + } + + return 0; +} + +/** + *hns_mac_del_mac - delete mac address into dsaf table,can't delete the same + * address twice + *@net_dev: net device + *@vfn : vf lan + *@mac : mac address + *return status + */ +int hns_mac_del_mac(struct hns_mac_cb *mac_cb, u32 vfn, char *mac) +{ + struct mac_entry_idx *old_mac; + struct dsaf_device *dsaf_dev; + u32 ret; + + dsaf_dev = mac_cb->dsaf_dev; + + if (vfn < DSAF_MAX_VM_NUM) { + old_mac = &mac_cb->addr_entry_idx[vfn]; + } else { + dev_err(mac_cb->dev, + "vf queue is too large,%s mac%d queue = %#x!\n", + mac_cb->dsaf_dev->ae_dev.name, mac_cb->mac_id, vfn); + return -EINVAL; + } + + if (dsaf_dev) { + ret = hns_dsaf_del_mac_entry(dsaf_dev, old_mac->vlan_id, + mac_cb->mac_id, old_mac->addr); + if (ret) + return ret; + + if (memcmp(old_mac->addr, mac, sizeof(old_mac->addr)) == 0) + old_mac->valid = 0; + } + + return 0; +} + +static void hns_mac_param_get(struct mac_params *param, + struct hns_mac_cb *mac_cb) +{ + param->vaddr = (void *)mac_cb->vaddr; + param->mac_mode = hns_get_enet_interface(mac_cb); + memcpy(param->addr, mac_cb->addr_entry_idx[0].addr, + MAC_NUM_OCTETS_PER_ADDR); + param->mac_id = mac_cb->mac_id; + param->dev = mac_cb->dev; +} + +/** + *hns_mac_queue_config_bc_en - set broadcast rx&tx enable + *@mac_cb: mac device + *@queue: queue number + *@en:enable + *retuen 0 - success , negative --fail + */ +static int hns_mac_port_config_bc_en(struct hns_mac_cb *mac_cb, + u32 port_num, u16 vlan_id, u8 en) +{ + int ret; + struct dsaf_device *dsaf_dev = mac_cb->dsaf_dev; + u8 addr[MAC_NUM_OCTETS_PER_ADDR] + = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff}; + struct dsaf_drv_mac_single_dest_entry mac_entry; + + /* directy return ok in debug network mode */ + if (mac_cb->mac_type == HNAE_PORT_DEBUG) + return 0; + + if (dsaf_dev) { + memcpy(mac_entry.addr, addr, sizeof(mac_entry.addr)); + mac_entry.in_vlan_id = vlan_id; + mac_entry.in_port_num = mac_cb->mac_id; + mac_entry.port_num = port_num; + + if (en == DISABLE) + ret = hns_dsaf_del_mac_mc_port(dsaf_dev, &mac_entry); + else + ret = hns_dsaf_add_mac_mc_port(dsaf_dev, &mac_entry); + return ret; + } + + return 0; +} + +/** + *hns_mac_vm_config_bc_en - set broadcast rx&tx enable + *@mac_cb: mac device + *@vmid: vm id + *@en:enable + *retuen 0 - success , negative --fail + */ +int hns_mac_vm_config_bc_en(struct hns_mac_cb *mac_cb, u32 vmid, u8 en) +{ + int ret; + struct dsaf_device *dsaf_dev = mac_cb->dsaf_dev; + u8 port_num; + u8 addr[MAC_NUM_OCTETS_PER_ADDR] + = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff}; + struct mac_entry_idx *uc_mac_entry; + struct dsaf_drv_mac_single_dest_entry mac_entry; + + if (mac_cb->mac_type == HNAE_PORT_DEBUG) + return 0; + + uc_mac_entry = &mac_cb->addr_entry_idx[vmid]; + + if (dsaf_dev) { + memcpy(mac_entry.addr, addr, sizeof(mac_entry.addr)); + mac_entry.in_vlan_id = uc_mac_entry->vlan_id; + mac_entry.in_port_num = mac_cb->mac_id; + ret = hns_mac_get_inner_port_num(mac_cb, vmid, &port_num); + if (ret) + return ret; + mac_entry.port_num = port_num; + + if (en == DISABLE) + ret = hns_dsaf_del_mac_mc_port(dsaf_dev, &mac_entry); + else + ret = hns_dsaf_add_mac_mc_port(dsaf_dev, &mac_entry); + return ret; + } + + return 0; +} + +void hns_mac_reset(struct hns_mac_cb *mac_cb) +{ + struct mac_driver *drv; + + drv = hns_mac_get_drv(mac_cb); + + drv->mac_init(drv); + + if (drv->config_max_frame_length) + drv->config_max_frame_length(drv, mac_cb->max_frm); + + if (drv->set_tx_auto_pause_frames) + drv->set_tx_auto_pause_frames(drv, mac_cb->tx_pause_frm_time); + + if (drv->set_an_mode) + drv->set_an_mode(drv, 1); + + if (drv->mac_pausefrm_cfg) { + if (mac_cb->mac_type == HNAE_PORT_DEBUG) + drv->mac_pausefrm_cfg(drv, 0, 0); + else /* mac rx must disable, dsaf pfc close instead of it*/ + drv->mac_pausefrm_cfg(drv, 0, 1); + } +} + +int hns_mac_set_mtu(struct hns_mac_cb *mac_cb, u32 new_mtu) +{ + struct mac_driver *drv = hns_mac_get_drv(mac_cb); + u32 buf_size = mac_cb->dsaf_dev->buf_size; + u32 new_frm = new_mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; + + if ((new_mtu < MAC_MIN_MTU) || (new_frm > MAC_MAX_MTU) || + (new_frm > HNS_RCB_RING_MAX_BD_PER_PKT * buf_size)) + return -EINVAL; + + if (!drv->config_max_frame_length) + return -ECHILD; + + /* adjust max frame to be at least the size of a standard frame */ + if (new_frm < (ETH_FRAME_LEN + ETH_FCS_LEN + VLAN_HLEN)) + new_frm = (ETH_FRAME_LEN + ETH_FCS_LEN + VLAN_HLEN); + + drv->config_max_frame_length(drv, new_frm); + + mac_cb->max_frm = new_frm; + + return 0; +} + +void hns_mac_start(struct hns_mac_cb *mac_cb) +{ + struct mac_driver *mac_drv = hns_mac_get_drv(mac_cb); + + /* for virt */ + if (mac_drv->mac_en_flg == MAC_EN_FLAG_V) { + /*plus 1 when the virtual mac has been enabled */ + mac_drv->virt_dev_num += 1; + return; + } + + if (mac_drv->mac_enable) { + mac_drv->mac_enable(mac_cb->priv.mac, MAC_COMM_MODE_RX_AND_TX); + mac_drv->mac_en_flg = MAC_EN_FLAG_V; + } +} + +void hns_mac_stop(struct hns_mac_cb *mac_cb) +{ + struct mac_driver *mac_ctrl_drv = hns_mac_get_drv(mac_cb); + + /*modified for virtualization */ + if (mac_ctrl_drv->virt_dev_num > 0) { + mac_ctrl_drv->virt_dev_num -= 1; + if (mac_ctrl_drv->virt_dev_num > 0) + return; + } + + if (mac_ctrl_drv->mac_disable) + mac_ctrl_drv->mac_disable(mac_cb->priv.mac, + MAC_COMM_MODE_RX_AND_TX); + + mac_ctrl_drv->mac_en_flg = 0; + mac_cb->link = 0; + cpld_led_reset(mac_cb); +} + +/** + * hns_mac_get_autoneg - get auto autonegotiation + * @mac_cb: mac control block + * @enable: enable or not + * retuen 0 - success , negative --fail + */ +void hns_mac_get_autoneg(struct hns_mac_cb *mac_cb, u32 *auto_neg) +{ + struct mac_driver *mac_ctrl_drv = hns_mac_get_drv(mac_cb); + + if (mac_ctrl_drv->autoneg_stat) + mac_ctrl_drv->autoneg_stat(mac_ctrl_drv, auto_neg); + else + *auto_neg = 0; +} + +/** + * hns_mac_get_pauseparam - set rx & tx pause parameter + * @mac_cb: mac control block + * @rx_en: rx enable status + * @tx_en: tx enable status + * retuen 0 - success , negative --fail + */ +void hns_mac_get_pauseparam(struct hns_mac_cb *mac_cb, u32 *rx_en, u32 *tx_en) +{ + struct mac_driver *mac_ctrl_drv = hns_mac_get_drv(mac_cb); + + if (mac_ctrl_drv->get_pause_enable) { + mac_ctrl_drv->get_pause_enable(mac_ctrl_drv, rx_en, tx_en); + } else { + *rx_en = 0; + *tx_en = 0; + } + + /* Due to the chip defect, the service mac's rx pause CAN'T be enabled. + * We set the rx pause frm always be true (1), because DSAF deals with + * the rx pause frm instead of service mac. After all, we still support + * rx pause frm. + */ + if (mac_cb->mac_type == HNAE_PORT_SERVICE) + *rx_en = 1; +} + +/** + * hns_mac_set_autoneg - set auto autonegotiation + * @mac_cb: mac control block + * @enable: enable or not + * retuen 0 - success , negative --fail + */ +int hns_mac_set_autoneg(struct hns_mac_cb *mac_cb, u8 enable) +{ + struct mac_driver *mac_ctrl_drv = hns_mac_get_drv(mac_cb); + + if (mac_cb->phy_if == PHY_INTERFACE_MODE_XGMII && enable) { + dev_err(mac_cb->dev, "enable autoneg is not allowed!"); + return -ENOTSUPP; + } + + if (mac_ctrl_drv->set_an_mode) + mac_ctrl_drv->set_an_mode(mac_ctrl_drv, enable); + + return 0; +} + +/** + * hns_mac_set_autoneg - set rx & tx pause parameter + * @mac_cb: mac control block + * @rx_en: rx enable or not + * @tx_en: tx enable or not + * return 0 - success , negative --fail + */ +int hns_mac_set_pauseparam(struct hns_mac_cb *mac_cb, u32 rx_en, u32 tx_en) +{ + struct mac_driver *mac_ctrl_drv = hns_mac_get_drv(mac_cb); + + if (mac_cb->mac_type == HNAE_PORT_SERVICE) { + if (!rx_en) { + dev_err(mac_cb->dev, "disable rx_pause is not allowed!"); + return -EINVAL; + } + } else if (mac_cb->mac_type == HNAE_PORT_DEBUG) { + if (tx_en || rx_en) { + dev_err(mac_cb->dev, "enable tx_pause or enable rx_pause are not allowed!"); + return -EINVAL; + } + } else { + dev_err(mac_cb->dev, "Unsupport this operation!"); + return -EINVAL; + } + + if (mac_ctrl_drv->mac_pausefrm_cfg) + mac_ctrl_drv->mac_pausefrm_cfg(mac_ctrl_drv, rx_en, tx_en); + + return 0; +} + +/** + * hns_mac_init_ex - mac init + * @mac_cb: mac control block + * retuen 0 - success , negative --fail + */ +static int hns_mac_init_ex(struct hns_mac_cb *mac_cb) +{ + int ret; + struct mac_params param; + struct mac_driver *drv; + + hns_dsaf_fix_mac_mode(mac_cb); + + memset(¶m, 0, sizeof(struct mac_params)); + hns_mac_param_get(¶m, mac_cb); + + if (MAC_SPEED_FROM_MODE(param.mac_mode) < MAC_SPEED_10000) + drv = (struct mac_driver *)hns_gmac_config(mac_cb, ¶m); + else + drv = (struct mac_driver *)hns_xgmac_config(mac_cb, ¶m); + + if (!drv) + return -ENOMEM; + + mac_cb->priv.mac = (void *)drv; + hns_mac_reset(mac_cb); + + hns_mac_adjust_link(mac_cb, mac_cb->speed, !mac_cb->half_duplex); + + ret = hns_mac_port_config_bc_en(mac_cb, mac_cb->mac_id, 0, ENABLE); + if (ret) + goto free_mac_drv; + + return 0; + +free_mac_drv: + drv->mac_free(mac_cb->priv.mac); + mac_cb->priv.mac = NULL; + + return ret; +} + +/** + *mac_free_dev - get mac information from device node + *@mac_cb: mac device + *@np:device node + *@mac_mode_idx:mac mode index + */ +static void hns_mac_get_info(struct hns_mac_cb *mac_cb, + struct device_node *np, u32 mac_mode_idx) +{ + mac_cb->link = false; + mac_cb->half_duplex = false; + mac_cb->speed = mac_phy_to_speed[mac_cb->phy_if]; + mac_cb->max_speed = mac_cb->speed; + + if (mac_cb->phy_if == PHY_INTERFACE_MODE_SGMII) { + mac_cb->if_support = MAC_GMAC_SUPPORTED; + mac_cb->if_support |= SUPPORTED_1000baseT_Full; + } else if (mac_cb->phy_if == PHY_INTERFACE_MODE_XGMII) { + mac_cb->if_support = SUPPORTED_10000baseR_FEC; + mac_cb->if_support |= SUPPORTED_10000baseKR_Full; + } + + mac_cb->max_frm = MAC_DEFAULT_MTU; + mac_cb->tx_pause_frm_time = MAC_DEFAULT_PAUSE_TIME; + + /* Get the rest of the PHY information */ + mac_cb->phy_node = of_parse_phandle(np, "phy-handle", mac_cb->mac_id); + if (mac_cb->phy_node) + dev_dbg(mac_cb->dev, "mac%d phy_node: %s\n", + mac_cb->mac_id, mac_cb->phy_node->name); +} + +/** + * hns_mac_get_mode - get mac mode + * @phy_if: phy interface + * retuen 0 - gmac, 1 - xgmac , negative --fail + */ +static int hns_mac_get_mode(phy_interface_t phy_if) +{ + switch (phy_if) { + case PHY_INTERFACE_MODE_SGMII: + return MAC_GMAC_IDX; + case PHY_INTERFACE_MODE_XGMII: + return MAC_XGMAC_IDX; + default: + return -EINVAL; + } +} + +u8 __iomem *hns_mac_get_vaddr(struct dsaf_device *dsaf_dev, + struct hns_mac_cb *mac_cb, u32 mac_mode_idx) +{ + u8 __iomem *base = dsaf_dev->io_base; + int mac_id = mac_cb->mac_id; + + if (mac_cb->mac_type == HNAE_PORT_SERVICE) + return base + 0x40000 + mac_id * 0x4000 - + mac_mode_idx * 0x20000; + else + return mac_cb->serdes_vaddr + 0x1000 + + (mac_id - DSAF_SERVICE_PORT_NUM_PER_DSAF) * 0x100000; +} + +/** + * hns_mac_get_cfg - get mac cfg from dtb or acpi table + * @dsaf_dev: dsa fabric device struct pointer + * @mac_idx: mac index + * retuen 0 - success , negative --fail + */ +int hns_mac_get_cfg(struct dsaf_device *dsaf_dev, int mac_idx) +{ + int ret; + u32 mac_mode_idx; + struct hns_mac_cb *mac_cb = &dsaf_dev->mac_cb[mac_idx]; + + mac_cb->dsaf_dev = dsaf_dev; + mac_cb->dev = dsaf_dev->dev; + mac_cb->mac_id = mac_idx; + + mac_cb->sys_ctl_vaddr = dsaf_dev->sc_base; + mac_cb->serdes_vaddr = dsaf_dev->sds_base; + + if (dsaf_dev->cpld_base && + mac_idx < DSAF_SERVICE_PORT_NUM_PER_DSAF) + mac_cb->cpld_vaddr = dsaf_dev->cpld_base + + mac_cb->mac_id * CPLD_ADDR_PORT_OFFSET; + mac_cb->sfp_prsnt = 0; + mac_cb->txpkt_for_led = 0; + mac_cb->rxpkt_for_led = 0; + + if (mac_idx < DSAF_SERVICE_PORT_NUM_PER_DSAF) + mac_cb->mac_type = HNAE_PORT_SERVICE; + else + mac_cb->mac_type = HNAE_PORT_DEBUG; + + mac_cb->phy_if = hns_mac_get_phy_if(mac_cb); + + ret = hns_mac_get_mode(mac_cb->phy_if); + if (ret < 0) { + dev_err(dsaf_dev->dev, + "hns_mac_get_mode failed,mac%d ret = %#x!\n", + mac_cb->mac_id, ret); + return ret; + } + mac_mode_idx = (u32)ret; + + hns_mac_get_info(mac_cb, mac_cb->dev->of_node, mac_mode_idx); + + mac_cb->vaddr = hns_mac_get_vaddr(dsaf_dev, mac_cb, mac_mode_idx); + + return 0; +} + +/** + * hns_mac_init - init mac + * @dsaf_dev: dsa fabric device struct pointer + * retuen 0 - success , negative --fail + */ +int hns_mac_init(struct dsaf_device *dsaf_dev) +{ + int i; + int ret; + size_t size; + struct hns_mac_cb *mac_cb; + + size = sizeof(struct hns_mac_cb) * DSAF_MAX_PORT_NUM_PER_CHIP; + dsaf_dev->mac_cb = devm_kzalloc(dsaf_dev->dev, size, GFP_KERNEL); + if (!dsaf_dev->mac_cb) + return -ENOMEM; + + for (i = 0; i < DSAF_MAX_PORT_NUM_PER_CHIP; i++) { + ret = hns_mac_get_cfg(dsaf_dev, i); + if (ret) + goto free_mac_cb; + + mac_cb = &dsaf_dev->mac_cb[i]; + ret = hns_mac_init_ex(mac_cb); + if (ret) + goto free_mac_cb; + } + + return 0; + +free_mac_cb: + dsaf_dev->mac_cb = NULL; + + return ret; +} + +void hns_mac_uninit(struct dsaf_device *dsaf_dev) +{ + cpld_led_reset(dsaf_dev->mac_cb); + dsaf_dev->mac_cb = NULL; +} + +int hns_mac_config_mac_loopback(struct hns_mac_cb *mac_cb, + enum hnae_loop loop, int en) +{ + int ret; + struct mac_driver *drv = hns_mac_get_drv(mac_cb); + + if (drv->config_loopback) + ret = drv->config_loopback(drv, loop, en); + else + ret = -ENOTSUPP; + + return ret; +} + +void hns_mac_update_stats(struct hns_mac_cb *mac_cb) +{ + struct mac_driver *mac_ctrl_drv = hns_mac_get_drv(mac_cb); + + mac_ctrl_drv->update_stats(mac_ctrl_drv); +} + +void hns_mac_get_stats(struct hns_mac_cb *mac_cb, u64 *data) +{ + struct mac_driver *mac_ctrl_drv = hns_mac_get_drv(mac_cb); + + mac_ctrl_drv->get_ethtool_stats(mac_ctrl_drv, data); +} + +void hns_mac_get_strings(struct hns_mac_cb *mac_cb, + int stringset, u8 *data) +{ + struct mac_driver *mac_ctrl_drv = hns_mac_get_drv(mac_cb); + + mac_ctrl_drv->get_strings(stringset, data); +} + +int hns_mac_get_sset_count(struct hns_mac_cb *mac_cb, int stringset) +{ + struct mac_driver *mac_ctrl_drv = hns_mac_get_drv(mac_cb); + + return mac_ctrl_drv->get_sset_count(stringset); +} + +int hns_mac_get_regs_count(struct hns_mac_cb *mac_cb) +{ + struct mac_driver *mac_ctrl_drv = hns_mac_get_drv(mac_cb); + + return mac_ctrl_drv->get_regs_count(); +} + +void hns_mac_get_regs(struct hns_mac_cb *mac_cb, void *data) +{ + struct mac_driver *mac_ctrl_drv = hns_mac_get_drv(mac_cb); + + mac_ctrl_drv->get_regs(mac_ctrl_drv, data); +} + +void hns_set_led_opt(struct hns_mac_cb *mac_cb) +{ + int nic_data = 0; + int txpkts, rxpkts; + + txpkts = mac_cb->txpkt_for_led - mac_cb->hw_stats.tx_good_pkts; + rxpkts = mac_cb->rxpkt_for_led - mac_cb->hw_stats.rx_good_pkts; + if (txpkts || rxpkts) + nic_data = 1; + else + nic_data = 0; + mac_cb->txpkt_for_led = mac_cb->hw_stats.tx_good_pkts; + mac_cb->rxpkt_for_led = mac_cb->hw_stats.rx_good_pkts; + hns_cpld_set_led(mac_cb, (int)mac_cb->link, + mac_cb->speed, nic_data); +} + +int hns_cpld_led_set_id(struct hns_mac_cb *mac_cb, + enum hnae_led_state status) +{ + if (!mac_cb || !mac_cb->cpld_vaddr) + return 0; + + return cpld_set_led_id(mac_cb, status); +} diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h new file mode 100644 index 000000000000..7da95a7581f9 --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h @@ -0,0 +1,456 @@ +/* + * Copyright (c) 2014-2015 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef _HNS_DSAF_MAC_H +#define _HNS_DSAF_MAC_H + +#include <linux/phy.h> +#include <linux/kernel.h> +#include <linux/if_vlan.h> +#include "hns_dsaf_main.h" + +struct dsaf_device; + +#define MAC_GMAC_SUPPORTED \ + (SUPPORTED_10baseT_Half \ + | SUPPORTED_10baseT_Full \ + | SUPPORTED_100baseT_Half \ + | SUPPORTED_100baseT_Full \ + | SUPPORTED_Autoneg) + +#define MAC_DEFAULT_MTU (ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN + ETH_DATA_LEN) +#define MAC_MAX_MTU 9600 +#define MAC_MIN_MTU 68 + +#define MAC_DEFAULT_PAUSE_TIME 0xff + +#define MAC_GMAC_IDX 0 +#define MAC_XGMAC_IDX 1 + +#define ETH_STATIC_REG 1 +#define ETH_DUMP_REG 5 +/* check mac addr broadcast */ +#define MAC_IS_BROADCAST(p) ((*(p) == 0xff) && (*((p) + 1) == 0xff) && \ + (*((p) + 2) == 0xff) && (*((p) + 3) == 0xff) && \ + (*((p) + 4) == 0xff) && (*((p) + 5) == 0xff)) + +/* check mac addr is 01-00-5e-xx-xx-xx*/ +#define MAC_IS_L3_MULTICAST(p) ((*((p) + 0) == 0x01) && \ + (*((p) + 1) == 0x00) && \ + (*((p) + 2) == 0x5e)) + +/*check the mac addr is 0 in all bit*/ +#define MAC_IS_ALL_ZEROS(p) ((*(p) == 0) && (*((p) + 1) == 0) && \ + (*((p) + 2) == 0) && (*((p) + 3) == 0) && \ + (*((p) + 4) == 0) && (*((p) + 5) == 0)) + +/*check mac addr multicast*/ +#define MAC_IS_MULTICAST(p) ((*((u8 *)((p) + 0)) & 0x01) ? (1) : (0)) + +/**< Number of octets (8-bit bytes) in an ethernet address */ +#define MAC_NUM_OCTETS_PER_ADDR 6 + +struct mac_priv { + void *mac; +}; + +/* net speed */ +enum mac_speed { + MAC_SPEED_10 = 10, /**< 10 Mbps */ + MAC_SPEED_100 = 100, /**< 100 Mbps */ + MAC_SPEED_1000 = 1000, /**< 1000 Mbps = 1 Gbps */ + MAC_SPEED_10000 = 10000 /**< 10000 Mbps = 10 Gbps */ +}; + +/*mac interface keyword */ +enum mac_intf { + MAC_IF_NONE = 0x00000000, /**< interface not invalid */ + MAC_IF_MII = 0x00010000, /**< MII interface */ + MAC_IF_RMII = 0x00020000, /**< RMII interface */ + MAC_IF_SMII = 0x00030000, /**< SMII interface */ + MAC_IF_GMII = 0x00040000, /**< GMII interface */ + MAC_IF_RGMII = 0x00050000, /**< RGMII interface */ + MAC_IF_TBI = 0x00060000, /**< TBI interface */ + MAC_IF_RTBI = 0x00070000, /**< RTBI interface */ + MAC_IF_SGMII = 0x00080000, /**< SGMII interface */ + MAC_IF_XGMII = 0x00090000, /**< XGMII interface */ + MAC_IF_QSGMII = 0x000a0000 /**< QSGMII interface */ +}; + +/*mac mode */ +enum mac_mode { + /**< Invalid Ethernet mode */ + MAC_MODE_INVALID = 0, + /**< 10 Mbps MII */ + MAC_MODE_MII_10 = (MAC_IF_MII | MAC_SPEED_10), + /**< 100 Mbps MII */ + MAC_MODE_MII_100 = (MAC_IF_MII | MAC_SPEED_100), + /**< 10 Mbps RMII */ + MAC_MODE_RMII_10 = (MAC_IF_RMII | MAC_SPEED_10), + /**< 100 Mbps RMII */ + MAC_MODE_RMII_100 = (MAC_IF_RMII | MAC_SPEED_100), + /**< 10 Mbps SMII */ + MAC_MODE_SMII_10 = (MAC_IF_SMII | MAC_SPEED_10), + /**< 100 Mbps SMII */ + MAC_MODE_SMII_100 = (MAC_IF_SMII | MAC_SPEED_100), + /**< 1000 Mbps GMII */ + MAC_MODE_GMII_1000 = (MAC_IF_GMII | MAC_SPEED_1000), + /**< 10 Mbps RGMII */ + MAC_MODE_RGMII_10 = (MAC_IF_RGMII | MAC_SPEED_10), + /**< 100 Mbps RGMII */ + MAC_MODE_RGMII_100 = (MAC_IF_RGMII | MAC_SPEED_100), + /**< 1000 Mbps RGMII */ + MAC_MODE_RGMII_1000 = (MAC_IF_RGMII | MAC_SPEED_1000), + /**< 1000 Mbps TBI */ + MAC_MODE_TBI_1000 = (MAC_IF_TBI | MAC_SPEED_1000), + /**< 1000 Mbps RTBI */ + MAC_MODE_RTBI_1000 = (MAC_IF_RTBI | MAC_SPEED_1000), + /**< 10 Mbps SGMII */ + MAC_MODE_SGMII_10 = (MAC_IF_SGMII | MAC_SPEED_10), + /**< 100 Mbps SGMII */ + MAC_MODE_SGMII_100 = (MAC_IF_SGMII | MAC_SPEED_100), + /**< 1000 Mbps SGMII */ + MAC_MODE_SGMII_1000 = (MAC_IF_SGMII | MAC_SPEED_1000), + /**< 10000 Mbps XGMII */ + MAC_MODE_XGMII_10000 = (MAC_IF_XGMII | MAC_SPEED_10000), + /**< 1000 Mbps QSGMII */ + MAC_MODE_QSGMII_1000 = (MAC_IF_QSGMII | MAC_SPEED_1000) +}; + +/*mac communicate mode*/ +enum mac_commom_mode { + MAC_COMM_MODE_NONE = 0, /**< No transmit/receive communication */ + MAC_COMM_MODE_RX = 1, /**< Only receive communication */ + MAC_COMM_MODE_TX = 2, /**< Only transmit communication */ + MAC_COMM_MODE_RX_AND_TX = 3 /**< Both tx and rx communication */ +}; + +/*mac statistics */ +struct mac_statistics { + u64 stat_pkts64; /* r-10G tr-DT 64 byte frame counter */ + u64 stat_pkts65to127; /* r-10G 65 to 127 byte frame counter */ + u64 stat_pkts128to255; /* r-10G 128 to 255 byte frame counter */ + u64 stat_pkts256to511; /*r-10G 256 to 511 byte frame counter */ + u64 stat_pkts512to1023;/* r-10G 512 to 1023 byte frame counter */ + u64 stat_pkts1024to1518; /* r-10G 1024 to 1518 byte frame counter */ + u64 stat_pkts1519to1522; /* r-10G 1519 to 1522 byte good frame count*/ + /* Total number of packets that were less than 64 octets */ + /* long with a wrong CRC.*/ + u64 stat_fragments; + /* Total number of packets longer than valid maximum length octets */ + u64 stat_jabbers; + /* number of dropped packets due to internal errors of */ + /* the MAC Client. */ + u64 stat_drop_events; + /* Incremented when frames of correct length but with */ + /* CRC error are received.*/ + u64 stat_crc_align_errors; + /* Total number of packets that were less than 64 octets */ + /* long with a good CRC.*/ + u64 stat_undersize_pkts; + u64 stat_oversize_pkts; /**< T,B.D*/ + + u64 stat_rx_pause; /**< Pause MAC Control received */ + u64 stat_tx_pause; /**< Pause MAC Control sent */ + + u64 in_octets; /**< Total number of byte received. */ + u64 in_pkts; /* Total number of packets received.*/ + u64 in_mcast_pkts; /* Total number of multicast frame received */ + u64 in_bcast_pkts; /* Total number of broadcast frame received */ + /* Frames received, but discarded due to */ + /* problems within the MAC RX. */ + u64 in_discards; + u64 in_errors; /* Number of frames received with error: */ + /* - FIFO Overflow Error */ + /* - CRC Error */ + /* - Frame Too Long Error */ + /* - Alignment Error */ + u64 out_octets; /*Total number of byte sent. */ + u64 out_pkts; /**< Total number of packets sent .*/ + u64 out_mcast_pkts; /* Total number of multicast frame sent */ + u64 out_bcast_pkts; /* Total number of multicast frame sent */ + /* Frames received, but discarded due to problems within */ + /* the MAC TX N/A!.*/ + u64 out_discards; + u64 out_errors; /*Number of frames transmitted with error: */ + /* - FIFO Overflow Error */ + /* - FIFO Underflow Error */ + /* - Other */ +}; + +/*mac para struct ,mac get param from nic or dsaf when initialize*/ +struct mac_params { + char addr[MAC_NUM_OCTETS_PER_ADDR]; + void *vaddr; /*virtual address*/ + struct device *dev; + u8 mac_id; + /**< Ethernet operation mode (MAC-PHY interface and speed) */ + enum mac_mode mac_mode; +}; + +struct mac_info { + u16 speed;/* The forced speed (lower bits) in */ + /* *mbps. Please use */ + /* * ethtool_cmd_speed()/_set() to */ + /* * access it */ + u8 duplex; /* Duplex, half or full */ + u8 auto_neg; /* Enable or disable autonegotiation */ + enum hnae_loop loop_mode; + u8 tx_pause_en; + u8 tx_pause_time; + u8 rx_pause_en; + u8 pad_and_crc_en; + u8 promiscuous_en; + u8 port_en; /*port enable*/ +}; + +struct mac_entry_idx { + u8 addr[MAC_NUM_OCTETS_PER_ADDR]; + u16 vlan_id:12; + u16 valid:1; + u16 qos:3; +}; + +struct mac_hw_stats { + u64 rx_good_pkts; /* only for xgmac */ + u64 rx_good_bytes; + u64 rx_total_pkts; /* only for xgmac */ + u64 rx_total_bytes; /* only for xgmac */ + u64 rx_bad_bytes; /* only for gmac */ + u64 rx_uc_pkts; + u64 rx_mc_pkts; + u64 rx_bc_pkts; + u64 rx_fragment_err; /* only for xgmac */ + u64 rx_undersize; /* only for xgmac */ + u64 rx_under_min; + u64 rx_minto64; /* only for gmac */ + u64 rx_64bytes; + u64 rx_65to127; + u64 rx_128to255; + u64 rx_256to511; + u64 rx_512to1023; + u64 rx_1024to1518; + u64 rx_1519tomax; + u64 rx_1519tomax_good; /* only for xgmac */ + u64 rx_oversize; + u64 rx_jabber_err; + u64 rx_fcs_err; + u64 rx_vlan_pkts; /* only for gmac */ + u64 rx_data_err; /* only for gmac */ + u64 rx_align_err; /* only for gmac */ + u64 rx_long_err; /* only for gmac */ + u64 rx_pfc_tc0; + u64 rx_pfc_tc1; /* only for xgmac */ + u64 rx_pfc_tc2; /* only for xgmac */ + u64 rx_pfc_tc3; /* only for xgmac */ + u64 rx_pfc_tc4; /* only for xgmac */ + u64 rx_pfc_tc5; /* only for xgmac */ + u64 rx_pfc_tc6; /* only for xgmac */ + u64 rx_pfc_tc7; /* only for xgmac */ + u64 rx_unknown_ctrl; + u64 rx_filter_pkts; /* only for gmac */ + u64 rx_filter_bytes; /* only for gmac */ + u64 rx_fifo_overrun_err;/* only for gmac */ + u64 rx_len_err; /* only for gmac */ + u64 rx_comma_err; /* only for gmac */ + u64 rx_symbol_err; /* only for xgmac */ + u64 tx_good_to_sw; /* only for xgmac */ + u64 tx_bad_to_sw; /* only for xgmac */ + u64 rx_1731_pkts; /* only for xgmac */ + + u64 tx_good_bytes; + u64 tx_good_pkts; /* only for xgmac */ + u64 tx_total_bytes; /* only for xgmac */ + u64 tx_total_pkts; /* only for xgmac */ + u64 tx_bad_bytes; /* only for gmac */ + u64 tx_bad_pkts; /* only for xgmac */ + u64 tx_uc_pkts; + u64 tx_mc_pkts; + u64 tx_bc_pkts; + u64 tx_undersize; /* only for xgmac */ + u64 tx_fragment_err; /* only for xgmac */ + u64 tx_under_min_pkts; /* only for gmac */ + u64 tx_64bytes; + u64 tx_65to127; + u64 tx_128to255; + u64 tx_256to511; + u64 tx_512to1023; + u64 tx_1024to1518; + u64 tx_1519tomax; + u64 tx_1519tomax_good; /* only for xgmac */ + u64 tx_oversize; /* only for xgmac */ + u64 tx_jabber_err; + u64 tx_underrun_err; /* only for gmac */ + u64 tx_vlan; /* only for gmac */ + u64 tx_crc_err; /* only for gmac */ + u64 tx_pfc_tc0; + u64 tx_pfc_tc1; /* only for xgmac */ + u64 tx_pfc_tc2; /* only for xgmac */ + u64 tx_pfc_tc3; /* only for xgmac */ + u64 tx_pfc_tc4; /* only for xgmac */ + u64 tx_pfc_tc5; /* only for xgmac */ + u64 tx_pfc_tc6; /* only for xgmac */ + u64 tx_pfc_tc7; /* only for xgmac */ + u64 tx_ctrl; /* only for xgmac */ + u64 tx_1731_pkts; /* only for xgmac */ + u64 tx_1588_pkts; /* only for xgmac */ + u64 rx_good_from_sw; /* only for xgmac */ + u64 rx_bad_from_sw; /* only for xgmac */ +}; + +struct hns_mac_cb { + struct device *dev; + struct dsaf_device *dsaf_dev; + struct mac_priv priv; + u8 __iomem *vaddr; + u8 __iomem *cpld_vaddr; + u8 __iomem *sys_ctl_vaddr; + u8 __iomem *serdes_vaddr; + struct mac_entry_idx addr_entry_idx[DSAF_MAX_VM_NUM]; + u8 sfp_prsnt; + u8 cpld_led_value; + u8 mac_id; + + u8 link; + u8 half_duplex; + u16 speed; + u16 max_speed; + u16 max_frm; + u16 tx_pause_frm_time; + u32 if_support; + u64 txpkt_for_led; + u64 rxpkt_for_led; + enum hnae_port_type mac_type; + phy_interface_t phy_if; + enum hnae_loop loop_mode; + + struct device_node *phy_node; + + struct mac_hw_stats hw_stats; +}; + +struct mac_driver { + /*init Mac when init nic or dsaf*/ + void (*mac_init)(void *mac_drv); + /*remove mac when remove nic or dsaf*/ + void (*mac_free)(void *mac_drv); + /*enable mac when enable nic or dsaf*/ + void (*mac_enable)(void *mac_drv, enum mac_commom_mode mode); + /*disable mac when disable nic or dsaf*/ + void (*mac_disable)(void *mac_drv, enum mac_commom_mode mode); + /* config mac address*/ + void (*set_mac_addr)(void *mac_drv, char *mac_addr); + /*adjust mac mode of port,include speed and duplex*/ + int (*adjust_link)(void *mac_drv, enum mac_speed speed, + u32 full_duplex); + /* config autoegotaite mode of port*/ + void (*set_an_mode)(void *mac_drv, u8 enable); + /* config loopbank mode */ + int (*config_loopback)(void *mac_drv, enum hnae_loop loop_mode, + u8 enable); + /* config mtu*/ + void (*config_max_frame_length)(void *mac_drv, u16 newval); + /*config PAD and CRC enable */ + void (*config_pad_and_crc)(void *mac_drv, u8 newval); + /* config duplex mode*/ + void (*config_half_duplex)(void *mac_drv, u8 newval); + /*config tx pause time,if pause_time is zero,disable tx pause enable*/ + void (*set_tx_auto_pause_frames)(void *mac_drv, u16 pause_time); + /*config rx pause enable*/ + void (*set_rx_ignore_pause_frames)(void *mac_drv, u32 enable); + /* config rx mode for promiscuous*/ + int (*set_promiscuous)(void *mac_drv, u8 enable); + /* get mac id */ + void (*mac_get_id)(void *mac_drv, u8 *mac_id); + void (*mac_pausefrm_cfg)(void *mac_drv, u32 rx_en, u32 tx_en); + + void (*autoneg_stat)(void *mac_drv, u32 *enable); + int (*set_pause_enable)(void *mac_drv, u32 rx_en, u32 tx_en); + void (*get_pause_enable)(void *mac_drv, u32 *rx_en, u32 *tx_en); + void (*get_link_status)(void *mac_drv, u32 *link_stat); + /* get the imporant regs*/ + void (*get_regs)(void *mac_drv, void *data); + int (*get_regs_count)(void); + /* get strings name for ethtool statistic */ + void (*get_strings)(u32 stringset, u8 *data); + /* get the number of strings*/ + int (*get_sset_count)(int stringset); + + /* get the statistic by ethtools*/ + void (*get_ethtool_stats)(void *mac_drv, u64 *data); + + /* get mac information */ + void (*get_info)(void *mac_drv, struct mac_info *mac_info); + + void (*update_stats)(void *mac_drv); + + enum mac_mode mac_mode; + u8 mac_id; + struct hns_mac_cb *mac_cb; + void __iomem *io_base; + unsigned int mac_en_flg;/*you'd better don't enable mac twice*/ + unsigned int virt_dev_num; + struct device *dev; +}; + +struct mac_stats_string { + char desc[64]; + unsigned long offset; +}; + +#define MAC_MAKE_MODE(interface, speed) (enum mac_mode)((interface) | (speed)) +#define MAC_INTERFACE_FROM_MODE(mode) (enum mac_intf)((mode) & 0xFFFF0000) +#define MAC_SPEED_FROM_MODE(mode) (enum mac_speed)((mode) & 0x0000FFFF) +#define MAC_STATS_FIELD_OFF(field) (offsetof(struct mac_hw_stats, field)) + +static inline struct mac_driver *hns_mac_get_drv( + const struct hns_mac_cb *mac_cb) +{ + return (struct mac_driver *)(mac_cb->priv.mac); +} + +void *hns_gmac_config(struct hns_mac_cb *mac_cb, + struct mac_params *mac_param); +void *hns_xgmac_config(struct hns_mac_cb *mac_cb, + struct mac_params *mac_param); + +int hns_mac_init(struct dsaf_device *dsaf_dev); +void mac_adjust_link(struct net_device *net_dev); +void hns_mac_get_link_status(struct hns_mac_cb *mac_cb, u32 *link_status); +int hns_mac_change_vf_addr(struct hns_mac_cb *mac_cb, u32 vmid, char *addr); +int hns_mac_set_multi(struct hns_mac_cb *mac_cb, + u32 port_num, char *addr, u8 en); +int hns_mac_vm_config_bc_en(struct hns_mac_cb *mac_cb, u32 vm, u8 en); +void hns_mac_start(struct hns_mac_cb *mac_cb); +void hns_mac_stop(struct hns_mac_cb *mac_cb); +int hns_mac_del_mac(struct hns_mac_cb *mac_cb, u32 vfn, char *mac); +void hns_mac_uninit(struct dsaf_device *dsaf_dev); +void hns_mac_adjust_link(struct hns_mac_cb *mac_cb, int speed, int duplex); +void hns_mac_reset(struct hns_mac_cb *mac_cb); +void hns_mac_get_autoneg(struct hns_mac_cb *mac_cb, u32 *auto_neg); +void hns_mac_get_pauseparam(struct hns_mac_cb *mac_cb, u32 *rx_en, u32 *tx_en); +int hns_mac_set_autoneg(struct hns_mac_cb *mac_cb, u8 enable); +int hns_mac_set_pauseparam(struct hns_mac_cb *mac_cb, u32 rx_en, u32 tx_en); +int hns_mac_set_mtu(struct hns_mac_cb *mac_cb, u32 new_mtu); +int hns_mac_get_port_info(struct hns_mac_cb *mac_cb, + u8 *auto_neg, u16 *speed, u8 *duplex); +phy_interface_t hns_mac_get_phy_if(struct hns_mac_cb *mac_cb); +int hns_mac_config_sds_loopback(struct hns_mac_cb *mac_cb, u8 en); +int hns_mac_config_mac_loopback(struct hns_mac_cb *mac_cb, + enum hnae_loop loop, int en); +void hns_mac_update_stats(struct hns_mac_cb *mac_cb); +void hns_mac_get_stats(struct hns_mac_cb *mac_cb, u64 *data); +void hns_mac_get_strings(struct hns_mac_cb *mac_cb, int stringset, u8 *data); +int hns_mac_get_sset_count(struct hns_mac_cb *mac_cb, int stringset); +void hns_mac_get_regs(struct hns_mac_cb *mac_cb, void *data); +int hns_mac_get_regs_count(struct hns_mac_cb *mac_cb); +void hns_set_led_opt(struct hns_mac_cb *mac_cb); +int hns_cpld_led_set_id(struct hns_mac_cb *mac_cb, + enum hnae_led_state status); +#endif /* _HNS_DSAF_MAC_H */ diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c new file mode 100644 index 000000000000..26ae6c64d74c --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c @@ -0,0 +1,2445 @@ +/* + * Copyright (c) 2014-2015 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/netdevice.h> +#include <linux/platform_device.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> +#include <linux/device.h> +#include "hns_dsaf_main.h" +#include "hns_dsaf_rcb.h" +#include "hns_dsaf_ppe.h" +#include "hns_dsaf_mac.h" + +const char *g_dsaf_mode_match[DSAF_MODE_MAX] = { + [DSAF_MODE_DISABLE_2PORT_64VM] = "2port-64vf", + [DSAF_MODE_DISABLE_6PORT_0VM] = "6port-16rss", + [DSAF_MODE_DISABLE_6PORT_16VM] = "6port-16vf", +}; + +int hns_dsaf_get_cfg(struct dsaf_device *dsaf_dev) +{ + int ret, i; + u32 desc_num; + u32 buf_size; + const char *name, *mode_str; + struct device_node *np = dsaf_dev->dev->of_node; + + if (of_device_is_compatible(np, "hisilicon,hns-dsaf-v2")) + dsaf_dev->dsaf_ver = AE_VERSION_2; + else + dsaf_dev->dsaf_ver = AE_VERSION_1; + + ret = of_property_read_string(np, "dsa_name", &name); + if (ret) { + dev_err(dsaf_dev->dev, "get dsaf name fail, ret=%d!\n", ret); + return ret; + } + strncpy(dsaf_dev->ae_dev.name, name, AE_NAME_SIZE); + dsaf_dev->ae_dev.name[AE_NAME_SIZE - 1] = '\0'; + + ret = of_property_read_string(np, "mode", &mode_str); + if (ret) { + dev_err(dsaf_dev->dev, "get dsaf mode fail, ret=%d!\n", ret); + return ret; + } + for (i = 0; i < DSAF_MODE_MAX; i++) { + if (g_dsaf_mode_match[i] && + !strcmp(mode_str, g_dsaf_mode_match[i])) + break; + } + if (i >= DSAF_MODE_MAX || + i == DSAF_MODE_INVALID || i == DSAF_MODE_ENABLE) { + dev_err(dsaf_dev->dev, + "%s prs mode str fail!\n", dsaf_dev->ae_dev.name); + return -EINVAL; + } + dsaf_dev->dsaf_mode = (enum dsaf_mode)i; + + if (dsaf_dev->dsaf_mode > DSAF_MODE_ENABLE) + dsaf_dev->dsaf_en = HRD_DSAF_NO_DSAF_MODE; + else + dsaf_dev->dsaf_en = HRD_DSAF_MODE; + + if ((i == DSAF_MODE_ENABLE_16VM) || + (i == DSAF_MODE_DISABLE_2PORT_8VM) || + (i == DSAF_MODE_DISABLE_6PORT_2VM)) + dsaf_dev->dsaf_tc_mode = HRD_DSAF_8TC_MODE; + else + dsaf_dev->dsaf_tc_mode = HRD_DSAF_4TC_MODE; + + dsaf_dev->sc_base = of_iomap(np, 0); + if (!dsaf_dev->sc_base) { + dev_err(dsaf_dev->dev, + "%s of_iomap 0 fail!\n", dsaf_dev->ae_dev.name); + ret = -ENOMEM; + goto unmap_base_addr; + } + + dsaf_dev->sds_base = of_iomap(np, 1); + if (!dsaf_dev->sds_base) { + dev_err(dsaf_dev->dev, + "%s of_iomap 1 fail!\n", dsaf_dev->ae_dev.name); + ret = -ENOMEM; + goto unmap_base_addr; + } + + dsaf_dev->ppe_base = of_iomap(np, 2); + if (!dsaf_dev->ppe_base) { + dev_err(dsaf_dev->dev, + "%s of_iomap 2 fail!\n", dsaf_dev->ae_dev.name); + ret = -ENOMEM; + goto unmap_base_addr; + } + + dsaf_dev->io_base = of_iomap(np, 3); + if (!dsaf_dev->io_base) { + dev_err(dsaf_dev->dev, + "%s of_iomap 3 fail!\n", dsaf_dev->ae_dev.name); + ret = -ENOMEM; + goto unmap_base_addr; + } + + dsaf_dev->cpld_base = of_iomap(np, 4); + if (!dsaf_dev->cpld_base) + dev_dbg(dsaf_dev->dev, "NO CPLD ADDR"); + + ret = of_property_read_u32(np, "desc-num", &desc_num); + if (ret < 0 || desc_num < HNS_DSAF_MIN_DESC_CNT || + desc_num > HNS_DSAF_MAX_DESC_CNT) { + dev_err(dsaf_dev->dev, "get desc-num(%d) fail, ret=%d!\n", + desc_num, ret); + goto unmap_base_addr; + } + dsaf_dev->desc_num = desc_num; + + ret = of_property_read_u32(np, "buf-size", &buf_size); + if (ret < 0) { + dev_err(dsaf_dev->dev, + "get buf-size fail, ret=%d!\r\n", ret); + goto unmap_base_addr; + } + dsaf_dev->buf_size = buf_size; + + dsaf_dev->buf_size_type = hns_rcb_buf_size2type(buf_size); + if (dsaf_dev->buf_size_type < 0) { + dev_err(dsaf_dev->dev, + "buf_size(%d) is wrong!\n", buf_size); + goto unmap_base_addr; + } + + if (!dma_set_mask_and_coherent(dsaf_dev->dev, DMA_BIT_MASK(64ULL))) + dev_dbg(dsaf_dev->dev, "set mask to 64bit\n"); + else + dev_err(dsaf_dev->dev, "set mask to 64bit fail!\n"); + + return 0; + +unmap_base_addr: + if (dsaf_dev->io_base) + iounmap(dsaf_dev->io_base); + if (dsaf_dev->ppe_base) + iounmap(dsaf_dev->ppe_base); + if (dsaf_dev->sds_base) + iounmap(dsaf_dev->sds_base); + if (dsaf_dev->sc_base) + iounmap(dsaf_dev->sc_base); + if (dsaf_dev->cpld_base) + iounmap(dsaf_dev->cpld_base); + return ret; +} + +static void hns_dsaf_free_cfg(struct dsaf_device *dsaf_dev) +{ + if (dsaf_dev->io_base) + iounmap(dsaf_dev->io_base); + + if (dsaf_dev->ppe_base) + iounmap(dsaf_dev->ppe_base); + + if (dsaf_dev->sds_base) + iounmap(dsaf_dev->sds_base); + + if (dsaf_dev->sc_base) + iounmap(dsaf_dev->sc_base); + + if (dsaf_dev->cpld_base) + iounmap(dsaf_dev->cpld_base); +} + +/** + * hns_dsaf_sbm_link_sram_init_en - config dsaf_sbm_init_en + * @dsaf_id: dsa fabric id + */ +static void hns_dsaf_sbm_link_sram_init_en(struct dsaf_device *dsaf_dev) +{ + dsaf_set_dev_bit(dsaf_dev, DSAF_CFG_0_REG, DSAF_CFG_SBM_INIT_S, 1); +} + +/** + * hns_dsaf_reg_cnt_clr_ce - config hns_dsaf_reg_cnt_clr_ce + * @dsaf_id: dsa fabric id + * @hns_dsaf_reg_cnt_clr_ce: config value + */ +static void +hns_dsaf_reg_cnt_clr_ce(struct dsaf_device *dsaf_dev, u32 reg_cnt_clr_ce) +{ + dsaf_set_dev_bit(dsaf_dev, DSAF_DSA_REG_CNT_CLR_CE_REG, + DSAF_CNT_CLR_CE_S, reg_cnt_clr_ce); +} + +/** + * hns_ppe_qid_cfg - config ppe qid + * @dsaf_id: dsa fabric id + * @pppe_qid_cfg: value array + */ +static void +hns_dsaf_ppe_qid_cfg(struct dsaf_device *dsaf_dev, u32 qid_cfg) +{ + u32 i; + + for (i = 0; i < DSAF_COMM_CHN; i++) { + dsaf_set_dev_field(dsaf_dev, + DSAF_PPE_QID_CFG_0_REG + 0x0004 * i, + DSAF_PPE_QID_CFG_M, DSAF_PPE_QID_CFG_S, + qid_cfg); + } +} + +/** + * hns_dsaf_sw_port_type_cfg - cfg sw type + * @dsaf_id: dsa fabric id + * @psw_port_type: array + */ +static void hns_dsaf_sw_port_type_cfg(struct dsaf_device *dsaf_dev, + enum dsaf_sw_port_type port_type) +{ + u32 i; + + for (i = 0; i < DSAF_SW_PORT_NUM; i++) { + dsaf_set_dev_field(dsaf_dev, + DSAF_SW_PORT_TYPE_0_REG + 0x0004 * i, + DSAF_SW_PORT_TYPE_M, DSAF_SW_PORT_TYPE_S, + port_type); + } +} + +/** + * hns_dsaf_stp_port_type_cfg - cfg stp type + * @dsaf_id: dsa fabric id + * @pstp_port_type: array + */ +static void hns_dsaf_stp_port_type_cfg(struct dsaf_device *dsaf_dev, + enum dsaf_stp_port_type port_type) +{ + u32 i; + + for (i = 0; i < DSAF_COMM_CHN; i++) { + dsaf_set_dev_field(dsaf_dev, + DSAF_STP_PORT_TYPE_0_REG + 0x0004 * i, + DSAF_STP_PORT_TYPE_M, DSAF_STP_PORT_TYPE_S, + port_type); + } +} + +/** + * hns_dsaf_sbm_cfg - config sbm + * @dsaf_id: dsa fabric id + */ +static void hns_dsaf_sbm_cfg(struct dsaf_device *dsaf_dev) +{ + u32 o_sbm_cfg; + u32 i; + + for (i = 0; i < DSAF_SBM_NUM; i++) { + o_sbm_cfg = dsaf_read_dev(dsaf_dev, + DSAF_SBM_CFG_REG_0_REG + 0x80 * i); + dsaf_set_bit(o_sbm_cfg, DSAF_SBM_CFG_EN_S, 1); + dsaf_set_bit(o_sbm_cfg, DSAF_SBM_CFG_SHCUT_EN_S, 0); + dsaf_write_dev(dsaf_dev, + DSAF_SBM_CFG_REG_0_REG + 0x80 * i, o_sbm_cfg); + } +} + +/** + * hns_dsaf_sbm_cfg_mib_en - config sbm + * @dsaf_id: dsa fabric id + */ +static int hns_dsaf_sbm_cfg_mib_en(struct dsaf_device *dsaf_dev) +{ + u32 sbm_cfg_mib_en; + u32 i; + u32 reg; + u32 read_cnt; + + for (i = 0; i < DSAF_SBM_NUM; i++) { + reg = DSAF_SBM_CFG_REG_0_REG + 0x80 * i; + dsaf_set_dev_bit(dsaf_dev, reg, DSAF_SBM_CFG_MIB_EN_S, 1); + } + + /* waitint for all sbm enable finished */ + for (i = 0; i < DSAF_SBM_NUM; i++) { + read_cnt = 0; + reg = DSAF_SBM_CFG_REG_0_REG + 0x80 * i; + do { + udelay(1); + sbm_cfg_mib_en = dsaf_get_dev_bit( + dsaf_dev, reg, DSAF_SBM_CFG_MIB_EN_S); + read_cnt++; + } while (sbm_cfg_mib_en == 0 && + read_cnt < DSAF_CFG_READ_CNT); + + if (sbm_cfg_mib_en == 0) { + dev_err(dsaf_dev->dev, + "sbm_cfg_mib_en fail,%s,sbm_num=%d\n", + dsaf_dev->ae_dev.name, i); + return -ENODEV; + } + } + + return 0; +} + +/** + * hns_dsaf_sbm_bp_wl_cfg - config sbm + * @dsaf_id: dsa fabric id + */ +static void hns_dsaf_sbm_bp_wl_cfg(struct dsaf_device *dsaf_dev) +{ + u32 o_sbm_bp_cfg0; + u32 o_sbm_bp_cfg1; + u32 o_sbm_bp_cfg2; + u32 o_sbm_bp_cfg3; + u32 reg; + u32 i; + + /* XGE */ + for (i = 0; i < DSAF_XGE_NUM; i++) { + reg = DSAF_SBM_BP_CFG_0_XGE_REG_0_REG + 0x80 * i; + o_sbm_bp_cfg0 = dsaf_read_dev(dsaf_dev, reg); + dsaf_set_field(o_sbm_bp_cfg0, DSAF_SBM_CFG0_COM_MAX_BUF_NUM_M, + DSAF_SBM_CFG0_COM_MAX_BUF_NUM_S, 512); + dsaf_set_field(o_sbm_bp_cfg0, DSAF_SBM_CFG0_VC0_MAX_BUF_NUM_M, + DSAF_SBM_CFG0_VC0_MAX_BUF_NUM_S, 0); + dsaf_set_field(o_sbm_bp_cfg0, DSAF_SBM_CFG0_VC1_MAX_BUF_NUM_M, + DSAF_SBM_CFG0_VC1_MAX_BUF_NUM_S, 0); + dsaf_write_dev(dsaf_dev, reg, o_sbm_bp_cfg0); + + reg = DSAF_SBM_BP_CFG_1_REG_0_REG + 0x80 * i; + o_sbm_bp_cfg1 = dsaf_read_dev(dsaf_dev, reg); + dsaf_set_field(o_sbm_bp_cfg1, DSAF_SBM_CFG1_TC4_MAX_BUF_NUM_M, + DSAF_SBM_CFG1_TC4_MAX_BUF_NUM_S, 0); + dsaf_set_field(o_sbm_bp_cfg1, DSAF_SBM_CFG1_TC0_MAX_BUF_NUM_M, + DSAF_SBM_CFG1_TC0_MAX_BUF_NUM_S, 0); + dsaf_write_dev(dsaf_dev, reg, o_sbm_bp_cfg1); + + reg = DSAF_SBM_BP_CFG_2_XGE_REG_0_REG + 0x80 * i; + o_sbm_bp_cfg2 = dsaf_read_dev(dsaf_dev, reg); + dsaf_set_field(o_sbm_bp_cfg2, DSAF_SBM_CFG2_SET_BUF_NUM_M, + DSAF_SBM_CFG2_SET_BUF_NUM_S, 104); + dsaf_set_field(o_sbm_bp_cfg2, DSAF_SBM_CFG2_RESET_BUF_NUM_M, + DSAF_SBM_CFG2_RESET_BUF_NUM_S, 128); + dsaf_write_dev(dsaf_dev, reg, o_sbm_bp_cfg2); + + reg = DSAF_SBM_BP_CFG_3_REG_0_REG + 0x80 * i; + o_sbm_bp_cfg3 = dsaf_read_dev(dsaf_dev, reg); + dsaf_set_field(o_sbm_bp_cfg3, + DSAF_SBM_CFG3_SET_BUF_NUM_NO_PFC_M, + DSAF_SBM_CFG3_SET_BUF_NUM_NO_PFC_S, 110); + dsaf_set_field(o_sbm_bp_cfg3, + DSAF_SBM_CFG3_RESET_BUF_NUM_NO_PFC_M, + DSAF_SBM_CFG3_RESET_BUF_NUM_NO_PFC_S, 160); + dsaf_write_dev(dsaf_dev, reg, o_sbm_bp_cfg3); + + /* for no enable pfc mode */ + reg = DSAF_SBM_BP_CFG_4_REG_0_REG + 0x80 * i; + o_sbm_bp_cfg3 = dsaf_read_dev(dsaf_dev, reg); + dsaf_set_field(o_sbm_bp_cfg3, + DSAF_SBM_CFG3_SET_BUF_NUM_NO_PFC_M, + DSAF_SBM_CFG3_SET_BUF_NUM_NO_PFC_S, 128); + dsaf_set_field(o_sbm_bp_cfg3, + DSAF_SBM_CFG3_RESET_BUF_NUM_NO_PFC_M, + DSAF_SBM_CFG3_RESET_BUF_NUM_NO_PFC_S, 192); + dsaf_write_dev(dsaf_dev, reg, o_sbm_bp_cfg3); + } + + /* PPE */ + for (i = 0; i < DSAF_COMM_CHN; i++) { + reg = DSAF_SBM_BP_CFG_2_PPE_REG_0_REG + 0x80 * i; + o_sbm_bp_cfg2 = dsaf_read_dev(dsaf_dev, reg); + dsaf_set_field(o_sbm_bp_cfg2, DSAF_SBM_CFG2_SET_BUF_NUM_M, + DSAF_SBM_CFG2_SET_BUF_NUM_S, 10); + dsaf_set_field(o_sbm_bp_cfg2, DSAF_SBM_CFG2_RESET_BUF_NUM_M, + DSAF_SBM_CFG2_RESET_BUF_NUM_S, 12); + dsaf_write_dev(dsaf_dev, reg, o_sbm_bp_cfg2); + } + + /* RoCEE */ + for (i = 0; i < DSAF_COMM_CHN; i++) { + reg = DSAF_SBM_BP_CFG_2_ROCEE_REG_0_REG + 0x80 * i; + o_sbm_bp_cfg2 = dsaf_read_dev(dsaf_dev, reg); + dsaf_set_field(o_sbm_bp_cfg2, DSAF_SBM_CFG2_SET_BUF_NUM_M, + DSAF_SBM_CFG2_SET_BUF_NUM_S, 2); + dsaf_set_field(o_sbm_bp_cfg2, DSAF_SBM_CFG2_RESET_BUF_NUM_M, + DSAF_SBM_CFG2_RESET_BUF_NUM_S, 4); + dsaf_write_dev(dsaf_dev, reg, o_sbm_bp_cfg2); + } +} + +/** + * hns_dsaf_voq_bp_all_thrd_cfg - voq + * @dsaf_id: dsa fabric id + */ +static void hns_dsaf_voq_bp_all_thrd_cfg(struct dsaf_device *dsaf_dev) +{ + u32 voq_bp_all_thrd; + u32 i; + + for (i = 0; i < DSAF_VOQ_NUM; i++) { + voq_bp_all_thrd = dsaf_read_dev( + dsaf_dev, DSAF_VOQ_BP_ALL_THRD_0_REG + 0x40 * i); + if (i < DSAF_XGE_NUM) { + dsaf_set_field(voq_bp_all_thrd, + DSAF_VOQ_BP_ALL_DOWNTHRD_M, + DSAF_VOQ_BP_ALL_DOWNTHRD_S, 930); + dsaf_set_field(voq_bp_all_thrd, + DSAF_VOQ_BP_ALL_UPTHRD_M, + DSAF_VOQ_BP_ALL_UPTHRD_S, 950); + } else { + dsaf_set_field(voq_bp_all_thrd, + DSAF_VOQ_BP_ALL_DOWNTHRD_M, + DSAF_VOQ_BP_ALL_DOWNTHRD_S, 220); + dsaf_set_field(voq_bp_all_thrd, + DSAF_VOQ_BP_ALL_UPTHRD_M, + DSAF_VOQ_BP_ALL_UPTHRD_S, 230); + } + dsaf_write_dev( + dsaf_dev, DSAF_VOQ_BP_ALL_THRD_0_REG + 0x40 * i, + voq_bp_all_thrd); + } +} + +/** + * hns_dsaf_tbl_tcam_data_cfg - tbl + * @dsaf_id: dsa fabric id + * @ptbl_tcam_data: addr + */ +static void hns_dsaf_tbl_tcam_data_cfg( + struct dsaf_device *dsaf_dev, + struct dsaf_tbl_tcam_data *ptbl_tcam_data) +{ + dsaf_write_dev(dsaf_dev, DSAF_TBL_TCAM_LOW_0_REG, + ptbl_tcam_data->tbl_tcam_data_low); + dsaf_write_dev(dsaf_dev, DSAF_TBL_TCAM_HIGH_0_REG, + ptbl_tcam_data->tbl_tcam_data_high); +} + +/** + * dsaf_tbl_tcam_mcast_cfg - tbl + * @dsaf_id: dsa fabric id + * @ptbl_tcam_mcast: addr + */ +static void hns_dsaf_tbl_tcam_mcast_cfg( + struct dsaf_device *dsaf_dev, + struct dsaf_tbl_tcam_mcast_cfg *mcast) +{ + u32 mcast_cfg4; + + mcast_cfg4 = dsaf_read_dev(dsaf_dev, DSAF_TBL_TCAM_MCAST_CFG_4_0_REG); + dsaf_set_bit(mcast_cfg4, DSAF_TBL_MCAST_CFG4_ITEM_VLD_S, + mcast->tbl_mcast_item_vld); + dsaf_set_bit(mcast_cfg4, DSAF_TBL_MCAST_CFG4_OLD_EN_S, + mcast->tbl_mcast_old_en); + dsaf_set_field(mcast_cfg4, DSAF_TBL_MCAST_CFG4_VM128_112_M, + DSAF_TBL_MCAST_CFG4_VM128_112_S, + mcast->tbl_mcast_port_msk[4]); + dsaf_write_dev(dsaf_dev, DSAF_TBL_TCAM_MCAST_CFG_4_0_REG, mcast_cfg4); + + dsaf_write_dev(dsaf_dev, DSAF_TBL_TCAM_MCAST_CFG_3_0_REG, + mcast->tbl_mcast_port_msk[3]); + + dsaf_write_dev(dsaf_dev, DSAF_TBL_TCAM_MCAST_CFG_2_0_REG, + mcast->tbl_mcast_port_msk[2]); + + dsaf_write_dev(dsaf_dev, DSAF_TBL_TCAM_MCAST_CFG_1_0_REG, + mcast->tbl_mcast_port_msk[1]); + + dsaf_write_dev(dsaf_dev, DSAF_TBL_TCAM_MCAST_CFG_0_0_REG, + mcast->tbl_mcast_port_msk[0]); +} + +/** + * hns_dsaf_tbl_tcam_ucast_cfg - tbl + * @dsaf_id: dsa fabric id + * @ptbl_tcam_ucast: addr + */ +static void hns_dsaf_tbl_tcam_ucast_cfg( + struct dsaf_device *dsaf_dev, + struct dsaf_tbl_tcam_ucast_cfg *tbl_tcam_ucast) +{ + u32 ucast_cfg1; + + ucast_cfg1 = dsaf_read_dev(dsaf_dev, DSAF_TBL_TCAM_UCAST_CFG_0_REG); + dsaf_set_bit(ucast_cfg1, DSAF_TBL_UCAST_CFG1_MAC_DISCARD_S, + tbl_tcam_ucast->tbl_ucast_mac_discard); + dsaf_set_bit(ucast_cfg1, DSAF_TBL_UCAST_CFG1_ITEM_VLD_S, + tbl_tcam_ucast->tbl_ucast_item_vld); + dsaf_set_bit(ucast_cfg1, DSAF_TBL_UCAST_CFG1_OLD_EN_S, + tbl_tcam_ucast->tbl_ucast_old_en); + dsaf_set_bit(ucast_cfg1, DSAF_TBL_UCAST_CFG1_DVC_S, + tbl_tcam_ucast->tbl_ucast_dvc); + dsaf_set_field(ucast_cfg1, DSAF_TBL_UCAST_CFG1_OUT_PORT_M, + DSAF_TBL_UCAST_CFG1_OUT_PORT_S, + tbl_tcam_ucast->tbl_ucast_out_port); + dsaf_write_dev(dsaf_dev, DSAF_TBL_TCAM_UCAST_CFG_0_REG, ucast_cfg1); +} + +/** + * hns_dsaf_tbl_line_cfg - tbl + * @dsaf_id: dsa fabric id + * @ptbl_lin: addr + */ +static void hns_dsaf_tbl_line_cfg(struct dsaf_device *dsaf_dev, + struct dsaf_tbl_line_cfg *tbl_lin) +{ + u32 tbl_line; + + tbl_line = dsaf_read_dev(dsaf_dev, DSAF_TBL_LIN_CFG_0_REG); + dsaf_set_bit(tbl_line, DSAF_TBL_LINE_CFG_MAC_DISCARD_S, + tbl_lin->tbl_line_mac_discard); + dsaf_set_bit(tbl_line, DSAF_TBL_LINE_CFG_DVC_S, + tbl_lin->tbl_line_dvc); + dsaf_set_field(tbl_line, DSAF_TBL_LINE_CFG_OUT_PORT_M, + DSAF_TBL_LINE_CFG_OUT_PORT_S, + tbl_lin->tbl_line_out_port); + dsaf_write_dev(dsaf_dev, DSAF_TBL_LIN_CFG_0_REG, tbl_line); +} + +/** + * hns_dsaf_tbl_tcam_mcast_pul - tbl + * @dsaf_id: dsa fabric id + */ +static void hns_dsaf_tbl_tcam_mcast_pul(struct dsaf_device *dsaf_dev) +{ + u32 o_tbl_pul; + + o_tbl_pul = dsaf_read_dev(dsaf_dev, DSAF_TBL_PUL_0_REG); + dsaf_set_bit(o_tbl_pul, DSAF_TBL_PUL_MCAST_VLD_S, 1); + dsaf_write_dev(dsaf_dev, DSAF_TBL_PUL_0_REG, o_tbl_pul); + dsaf_set_bit(o_tbl_pul, DSAF_TBL_PUL_MCAST_VLD_S, 0); + dsaf_write_dev(dsaf_dev, DSAF_TBL_PUL_0_REG, o_tbl_pul); +} + +/** + * hns_dsaf_tbl_line_pul - tbl + * @dsaf_id: dsa fabric id + */ +static void hns_dsaf_tbl_line_pul(struct dsaf_device *dsaf_dev) +{ + u32 tbl_pul; + + tbl_pul = dsaf_read_dev(dsaf_dev, DSAF_TBL_PUL_0_REG); + dsaf_set_bit(tbl_pul, DSAF_TBL_PUL_LINE_VLD_S, 1); + dsaf_write_dev(dsaf_dev, DSAF_TBL_PUL_0_REG, tbl_pul); + dsaf_set_bit(tbl_pul, DSAF_TBL_PUL_LINE_VLD_S, 0); + dsaf_write_dev(dsaf_dev, DSAF_TBL_PUL_0_REG, tbl_pul); +} + +/** + * hns_dsaf_tbl_tcam_data_mcast_pul - tbl + * @dsaf_id: dsa fabric id + */ +static void hns_dsaf_tbl_tcam_data_mcast_pul( + struct dsaf_device *dsaf_dev) +{ + u32 o_tbl_pul; + + o_tbl_pul = dsaf_read_dev(dsaf_dev, DSAF_TBL_PUL_0_REG); + dsaf_set_bit(o_tbl_pul, DSAF_TBL_PUL_TCAM_DATA_VLD_S, 1); + dsaf_set_bit(o_tbl_pul, DSAF_TBL_PUL_MCAST_VLD_S, 1); + dsaf_write_dev(dsaf_dev, DSAF_TBL_PUL_0_REG, o_tbl_pul); + dsaf_set_bit(o_tbl_pul, DSAF_TBL_PUL_TCAM_DATA_VLD_S, 0); + dsaf_set_bit(o_tbl_pul, DSAF_TBL_PUL_MCAST_VLD_S, 0); + dsaf_write_dev(dsaf_dev, DSAF_TBL_PUL_0_REG, o_tbl_pul); +} + +/** + * hns_dsaf_tbl_tcam_data_ucast_pul - tbl + * @dsaf_id: dsa fabric id + */ +static void hns_dsaf_tbl_tcam_data_ucast_pul( + struct dsaf_device *dsaf_dev) +{ + u32 o_tbl_pul; + + o_tbl_pul = dsaf_read_dev(dsaf_dev, DSAF_TBL_PUL_0_REG); + dsaf_set_bit(o_tbl_pul, DSAF_TBL_PUL_TCAM_DATA_VLD_S, 1); + dsaf_set_bit(o_tbl_pul, DSAF_TBL_PUL_UCAST_VLD_S, 1); + dsaf_write_dev(dsaf_dev, DSAF_TBL_PUL_0_REG, o_tbl_pul); + dsaf_set_bit(o_tbl_pul, DSAF_TBL_PUL_TCAM_DATA_VLD_S, 0); + dsaf_set_bit(o_tbl_pul, DSAF_TBL_PUL_UCAST_VLD_S, 0); + dsaf_write_dev(dsaf_dev, DSAF_TBL_PUL_0_REG, o_tbl_pul); +} + +/** + * hns_dsaf_tbl_stat_en - tbl + * @dsaf_id: dsa fabric id + * @ptbl_stat_en: addr + */ +static void hns_dsaf_tbl_stat_en(struct dsaf_device *dsaf_dev) +{ + u32 o_tbl_ctrl; + + o_tbl_ctrl = dsaf_read_dev(dsaf_dev, DSAF_TBL_DFX_CTRL_0_REG); + dsaf_set_bit(o_tbl_ctrl, DSAF_TBL_DFX_LINE_LKUP_NUM_EN_S, 1); + dsaf_set_bit(o_tbl_ctrl, DSAF_TBL_DFX_UC_LKUP_NUM_EN_S, 1); + dsaf_set_bit(o_tbl_ctrl, DSAF_TBL_DFX_MC_LKUP_NUM_EN_S, 1); + dsaf_set_bit(o_tbl_ctrl, DSAF_TBL_DFX_BC_LKUP_NUM_EN_S, 1); + dsaf_write_dev(dsaf_dev, DSAF_TBL_DFX_CTRL_0_REG, o_tbl_ctrl); +} + +/** + * hns_dsaf_rocee_bp_en - rocee back press enable + * @dsaf_id: dsa fabric id + */ +static void hns_dsaf_rocee_bp_en(struct dsaf_device *dsaf_dev) +{ + dsaf_set_dev_bit(dsaf_dev, DSAF_XGE_CTRL_SIG_CFG_0_REG, + DSAF_FC_XGE_TX_PAUSE_S, 1); +} + +/* set msk for dsaf exception irq*/ +static void hns_dsaf_int_xge_msk_set(struct dsaf_device *dsaf_dev, + u32 chnn_num, u32 mask_set) +{ + dsaf_write_dev(dsaf_dev, + DSAF_XGE_INT_MSK_0_REG + 0x4 * chnn_num, mask_set); +} + +static void hns_dsaf_int_ppe_msk_set(struct dsaf_device *dsaf_dev, + u32 chnn_num, u32 msk_set) +{ + dsaf_write_dev(dsaf_dev, + DSAF_PPE_INT_MSK_0_REG + 0x4 * chnn_num, msk_set); +} + +static void hns_dsaf_int_rocee_msk_set(struct dsaf_device *dsaf_dev, + u32 chnn, u32 msk_set) +{ + dsaf_write_dev(dsaf_dev, + DSAF_ROCEE_INT_MSK_0_REG + 0x4 * chnn, msk_set); +} + +static void +hns_dsaf_int_tbl_msk_set(struct dsaf_device *dsaf_dev, u32 msk_set) +{ + dsaf_write_dev(dsaf_dev, DSAF_TBL_INT_MSK_0_REG, msk_set); +} + +/* clr dsaf exception irq*/ +static void hns_dsaf_int_xge_src_clr(struct dsaf_device *dsaf_dev, + u32 chnn_num, u32 int_src) +{ + dsaf_write_dev(dsaf_dev, + DSAF_XGE_INT_SRC_0_REG + 0x4 * chnn_num, int_src); +} + +static void hns_dsaf_int_ppe_src_clr(struct dsaf_device *dsaf_dev, + u32 chnn, u32 int_src) +{ + dsaf_write_dev(dsaf_dev, + DSAF_PPE_INT_SRC_0_REG + 0x4 * chnn, int_src); +} + +static void hns_dsaf_int_rocee_src_clr(struct dsaf_device *dsaf_dev, + u32 chnn, u32 int_src) +{ + dsaf_write_dev(dsaf_dev, + DSAF_ROCEE_INT_SRC_0_REG + 0x4 * chnn, int_src); +} + +static void hns_dsaf_int_tbl_src_clr(struct dsaf_device *dsaf_dev, + u32 int_src) +{ + dsaf_write_dev(dsaf_dev, DSAF_TBL_INT_SRC_0_REG, int_src); +} + +/** + * hns_dsaf_single_line_tbl_cfg - INT + * @dsaf_id: dsa fabric id + * @address: + * @ptbl_line: + */ +static void hns_dsaf_single_line_tbl_cfg( + struct dsaf_device *dsaf_dev, + u32 address, struct dsaf_tbl_line_cfg *ptbl_line) +{ + /*Write Addr*/ + hns_dsaf_tbl_line_addr_cfg(dsaf_dev, address); + + /*Write Line*/ + hns_dsaf_tbl_line_cfg(dsaf_dev, ptbl_line); + + /*Write Plus*/ + hns_dsaf_tbl_line_pul(dsaf_dev); +} + +/** + * hns_dsaf_tcam_uc_cfg - INT + * @dsaf_id: dsa fabric id + * @address, + * @ptbl_tcam_data, + */ +static void hns_dsaf_tcam_uc_cfg( + struct dsaf_device *dsaf_dev, u32 address, + struct dsaf_tbl_tcam_data *ptbl_tcam_data, + struct dsaf_tbl_tcam_ucast_cfg *ptbl_tcam_ucast) +{ + /*Write Addr*/ + hns_dsaf_tbl_tcam_addr_cfg(dsaf_dev, address); + /*Write Tcam Data*/ + hns_dsaf_tbl_tcam_data_cfg(dsaf_dev, ptbl_tcam_data); + /*Write Tcam Ucast*/ + hns_dsaf_tbl_tcam_ucast_cfg(dsaf_dev, ptbl_tcam_ucast); + /*Write Plus*/ + hns_dsaf_tbl_tcam_data_ucast_pul(dsaf_dev); +} + +/** + * hns_dsaf_tcam_mc_cfg - INT + * @dsaf_id: dsa fabric id + * @address, + * @ptbl_tcam_data, + * @ptbl_tcam_mcast, + */ +static void hns_dsaf_tcam_mc_cfg( + struct dsaf_device *dsaf_dev, u32 address, + struct dsaf_tbl_tcam_data *ptbl_tcam_data, + struct dsaf_tbl_tcam_mcast_cfg *ptbl_tcam_mcast) +{ + /*Write Addr*/ + hns_dsaf_tbl_tcam_addr_cfg(dsaf_dev, address); + /*Write Tcam Data*/ + hns_dsaf_tbl_tcam_data_cfg(dsaf_dev, ptbl_tcam_data); + /*Write Tcam Mcast*/ + hns_dsaf_tbl_tcam_mcast_cfg(dsaf_dev, ptbl_tcam_mcast); + /*Write Plus*/ + hns_dsaf_tbl_tcam_data_mcast_pul(dsaf_dev); +} + +/** + * hns_dsaf_tcam_mc_invld - INT + * @dsaf_id: dsa fabric id + * @address + */ +static void hns_dsaf_tcam_mc_invld(struct dsaf_device *dsaf_dev, u32 address) +{ + /*Write Addr*/ + hns_dsaf_tbl_tcam_addr_cfg(dsaf_dev, address); + + /*write tcam mcast*/ + dsaf_write_dev(dsaf_dev, DSAF_TBL_TCAM_MCAST_CFG_0_0_REG, 0); + dsaf_write_dev(dsaf_dev, DSAF_TBL_TCAM_MCAST_CFG_1_0_REG, 0); + dsaf_write_dev(dsaf_dev, DSAF_TBL_TCAM_MCAST_CFG_2_0_REG, 0); + dsaf_write_dev(dsaf_dev, DSAF_TBL_TCAM_MCAST_CFG_3_0_REG, 0); + dsaf_write_dev(dsaf_dev, DSAF_TBL_TCAM_MCAST_CFG_4_0_REG, 0); + + /*Write Plus*/ + hns_dsaf_tbl_tcam_mcast_pul(dsaf_dev); +} + +/** + * hns_dsaf_tcam_uc_get - INT + * @dsaf_id: dsa fabric id + * @address + * @ptbl_tcam_data + * @ptbl_tcam_ucast + */ +static void hns_dsaf_tcam_uc_get( + struct dsaf_device *dsaf_dev, u32 address, + struct dsaf_tbl_tcam_data *ptbl_tcam_data, + struct dsaf_tbl_tcam_ucast_cfg *ptbl_tcam_ucast) +{ + u32 tcam_read_data0; + u32 tcam_read_data4; + + /*Write Addr*/ + hns_dsaf_tbl_tcam_addr_cfg(dsaf_dev, address); + + /*read tcam item puls*/ + hns_dsaf_tbl_tcam_load_pul(dsaf_dev); + + /*read tcam data*/ + ptbl_tcam_data->tbl_tcam_data_high + = dsaf_read_dev(dsaf_dev, DSAF_TBL_TCAM_RDATA_LOW_0_REG); + ptbl_tcam_data->tbl_tcam_data_low + = dsaf_read_dev(dsaf_dev, DSAF_TBL_TCAM_RDATA_HIGH_0_REG); + + /*read tcam mcast*/ + tcam_read_data0 = dsaf_read_dev(dsaf_dev, + DSAF_TBL_TCAM_RAM_RDATA0_0_REG); + tcam_read_data4 = dsaf_read_dev(dsaf_dev, + DSAF_TBL_TCAM_RAM_RDATA4_0_REG); + + ptbl_tcam_ucast->tbl_ucast_item_vld + = dsaf_get_bit(tcam_read_data4, + DSAF_TBL_MCAST_CFG4_ITEM_VLD_S); + ptbl_tcam_ucast->tbl_ucast_old_en + = dsaf_get_bit(tcam_read_data4, DSAF_TBL_MCAST_CFG4_OLD_EN_S); + ptbl_tcam_ucast->tbl_ucast_mac_discard + = dsaf_get_bit(tcam_read_data0, + DSAF_TBL_UCAST_CFG1_MAC_DISCARD_S); + ptbl_tcam_ucast->tbl_ucast_out_port + = dsaf_get_field(tcam_read_data0, + DSAF_TBL_UCAST_CFG1_OUT_PORT_M, + DSAF_TBL_UCAST_CFG1_OUT_PORT_S); + ptbl_tcam_ucast->tbl_ucast_dvc + = dsaf_get_bit(tcam_read_data0, DSAF_TBL_UCAST_CFG1_DVC_S); +} + +/** + * hns_dsaf_tcam_mc_get - INT + * @dsaf_id: dsa fabric id + * @address + * @ptbl_tcam_data + * @ptbl_tcam_ucast + */ +static void hns_dsaf_tcam_mc_get( + struct dsaf_device *dsaf_dev, u32 address, + struct dsaf_tbl_tcam_data *ptbl_tcam_data, + struct dsaf_tbl_tcam_mcast_cfg *ptbl_tcam_mcast) +{ + u32 data_tmp; + + /*Write Addr*/ + hns_dsaf_tbl_tcam_addr_cfg(dsaf_dev, address); + + /*read tcam item puls*/ + hns_dsaf_tbl_tcam_load_pul(dsaf_dev); + + /*read tcam data*/ + ptbl_tcam_data->tbl_tcam_data_high = + dsaf_read_dev(dsaf_dev, DSAF_TBL_TCAM_RDATA_LOW_0_REG); + ptbl_tcam_data->tbl_tcam_data_low = + dsaf_read_dev(dsaf_dev, DSAF_TBL_TCAM_RDATA_HIGH_0_REG); + + /*read tcam mcast*/ + ptbl_tcam_mcast->tbl_mcast_port_msk[0] = + dsaf_read_dev(dsaf_dev, DSAF_TBL_TCAM_RAM_RDATA0_0_REG); + ptbl_tcam_mcast->tbl_mcast_port_msk[1] = + dsaf_read_dev(dsaf_dev, DSAF_TBL_TCAM_RAM_RDATA1_0_REG); + ptbl_tcam_mcast->tbl_mcast_port_msk[2] = + dsaf_read_dev(dsaf_dev, DSAF_TBL_TCAM_RAM_RDATA2_0_REG); + ptbl_tcam_mcast->tbl_mcast_port_msk[3] = + dsaf_read_dev(dsaf_dev, DSAF_TBL_TCAM_RAM_RDATA3_0_REG); + + data_tmp = dsaf_read_dev(dsaf_dev, DSAF_TBL_TCAM_RAM_RDATA4_0_REG); + ptbl_tcam_mcast->tbl_mcast_item_vld = + dsaf_get_bit(data_tmp, DSAF_TBL_MCAST_CFG4_ITEM_VLD_S); + ptbl_tcam_mcast->tbl_mcast_old_en = + dsaf_get_bit(data_tmp, DSAF_TBL_MCAST_CFG4_OLD_EN_S); + ptbl_tcam_mcast->tbl_mcast_port_msk[4] = + dsaf_get_field(data_tmp, DSAF_TBL_MCAST_CFG4_VM128_112_M, + DSAF_TBL_MCAST_CFG4_VM128_112_S); +} + +/** + * hns_dsaf_tbl_line_init - INT + * @dsaf_id: dsa fabric id + */ +static void hns_dsaf_tbl_line_init(struct dsaf_device *dsaf_dev) +{ + u32 i; + /* defaultly set all lineal mac table entry resulting discard */ + struct dsaf_tbl_line_cfg tbl_line[] = {{1, 0, 0} }; + + for (i = 0; i < DSAF_LINE_SUM; i++) + hns_dsaf_single_line_tbl_cfg(dsaf_dev, i, tbl_line); +} + +/** + * hns_dsaf_tbl_tcam_init - INT + * @dsaf_id: dsa fabric id + */ +static void hns_dsaf_tbl_tcam_init(struct dsaf_device *dsaf_dev) +{ + u32 i; + struct dsaf_tbl_tcam_data tcam_data[] = {{0, 0} }; + struct dsaf_tbl_tcam_ucast_cfg tcam_ucast[] = {{0, 0, 0, 0, 0} }; + + /*tcam tbl*/ + for (i = 0; i < DSAF_TCAM_SUM; i++) + hns_dsaf_tcam_uc_cfg(dsaf_dev, i, tcam_data, tcam_ucast); +} + +/** + * hns_dsaf_pfc_en_cfg - dsaf pfc pause cfg + * @mac_cb: mac contrl block + */ +static void hns_dsaf_pfc_en_cfg(struct dsaf_device *dsaf_dev, + int mac_id, int en) +{ + if (!en) + dsaf_write_dev(dsaf_dev, DSAF_PFC_EN_0_REG + mac_id * 4, 0); + else + dsaf_write_dev(dsaf_dev, DSAF_PFC_EN_0_REG + mac_id * 4, 0xff); +} + +/** + * hns_dsaf_tbl_tcam_init - INT + * @dsaf_id: dsa fabric id + * @dsaf_mode + */ +static void hns_dsaf_comm_init(struct dsaf_device *dsaf_dev) +{ + u32 i; + u32 o_dsaf_cfg; + + o_dsaf_cfg = dsaf_read_dev(dsaf_dev, DSAF_CFG_0_REG); + dsaf_set_bit(o_dsaf_cfg, DSAF_CFG_EN_S, dsaf_dev->dsaf_en); + dsaf_set_bit(o_dsaf_cfg, DSAF_CFG_TC_MODE_S, dsaf_dev->dsaf_tc_mode); + dsaf_set_bit(o_dsaf_cfg, DSAF_CFG_CRC_EN_S, 0); + dsaf_set_bit(o_dsaf_cfg, DSAF_CFG_MIX_MODE_S, 0); + dsaf_set_bit(o_dsaf_cfg, DSAF_CFG_LOCA_ADDR_EN_S, 0); + dsaf_write_dev(dsaf_dev, DSAF_CFG_0_REG, o_dsaf_cfg); + + hns_dsaf_reg_cnt_clr_ce(dsaf_dev, 1); + hns_dsaf_stp_port_type_cfg(dsaf_dev, DSAF_STP_PORT_TYPE_FORWARD); + + /* set 22 queue per tx ppe engine, only used in switch mode */ + hns_dsaf_ppe_qid_cfg(dsaf_dev, DSAF_DEFAUTL_QUEUE_NUM_PER_PPE); + + /* in non switch mode, set all port to access mode */ + hns_dsaf_sw_port_type_cfg(dsaf_dev, DSAF_SW_PORT_TYPE_NON_VLAN); + + /*set dsaf pfc to 0 for parseing rx pause*/ + for (i = 0; i < DSAF_COMM_CHN; i++) + hns_dsaf_pfc_en_cfg(dsaf_dev, i, 0); + + /*msk and clr exception irqs */ + for (i = 0; i < DSAF_COMM_CHN; i++) { + hns_dsaf_int_xge_src_clr(dsaf_dev, i, 0xfffffffful); + hns_dsaf_int_ppe_src_clr(dsaf_dev, i, 0xfffffffful); + hns_dsaf_int_rocee_src_clr(dsaf_dev, i, 0xfffffffful); + + hns_dsaf_int_xge_msk_set(dsaf_dev, i, 0xfffffffful); + hns_dsaf_int_ppe_msk_set(dsaf_dev, i, 0xfffffffful); + hns_dsaf_int_rocee_msk_set(dsaf_dev, i, 0xfffffffful); + } + hns_dsaf_int_tbl_src_clr(dsaf_dev, 0xfffffffful); + hns_dsaf_int_tbl_msk_set(dsaf_dev, 0xfffffffful); +} + +/** + * hns_dsaf_inode_init - INT + * @dsaf_id: dsa fabric id + */ +static void hns_dsaf_inode_init(struct dsaf_device *dsaf_dev) +{ + u32 reg; + u32 tc_cfg; + u32 i; + + if (dsaf_dev->dsaf_tc_mode == HRD_DSAF_4TC_MODE) + tc_cfg = HNS_DSAF_I4TC_CFG; + else + tc_cfg = HNS_DSAF_I8TC_CFG; + + for (i = 0; i < DSAF_INODE_NUM; i++) { + reg = DSAF_INODE_IN_PORT_NUM_0_REG + 0x80 * i; + dsaf_set_dev_field(dsaf_dev, reg, DSAF_INODE_IN_PORT_NUM_M, + DSAF_INODE_IN_PORT_NUM_S, i % DSAF_XGE_NUM); + + reg = DSAF_INODE_PRI_TC_CFG_0_REG + 0x80 * i; + dsaf_write_dev(dsaf_dev, reg, tc_cfg); + } +} + +/** + * hns_dsaf_sbm_init - INT + * @dsaf_id: dsa fabric id + */ +static int hns_dsaf_sbm_init(struct dsaf_device *dsaf_dev) +{ + u32 flag; + u32 cnt = 0; + int ret; + + hns_dsaf_sbm_bp_wl_cfg(dsaf_dev); + + /* enable sbm chanel, disable sbm chanel shcut function*/ + hns_dsaf_sbm_cfg(dsaf_dev); + + /* enable sbm mib */ + ret = hns_dsaf_sbm_cfg_mib_en(dsaf_dev); + if (ret) { + dev_err(dsaf_dev->dev, + "hns_dsaf_sbm_cfg_mib_en fail,%s, ret=%d\n", + dsaf_dev->ae_dev.name, ret); + return ret; + } + + /* enable sbm initial link sram */ + hns_dsaf_sbm_link_sram_init_en(dsaf_dev); + + do { + usleep_range(200, 210);/*udelay(200);*/ + flag = dsaf_read_dev(dsaf_dev, DSAF_SRAM_INIT_OVER_0_REG); + cnt++; + } while (flag != DSAF_SRAM_INIT_FINISH_FLAG && cnt < DSAF_CFG_READ_CNT); + + if (flag != DSAF_SRAM_INIT_FINISH_FLAG) { + dev_err(dsaf_dev->dev, + "hns_dsaf_sbm_init fail %s, flag=%d, cnt=%d\n", + dsaf_dev->ae_dev.name, flag, cnt); + return -ENODEV; + } + + hns_dsaf_rocee_bp_en(dsaf_dev); + + return 0; +} + +/** + * hns_dsaf_tbl_init - INT + * @dsaf_id: dsa fabric id + */ +static void hns_dsaf_tbl_init(struct dsaf_device *dsaf_dev) +{ + hns_dsaf_tbl_stat_en(dsaf_dev); + + hns_dsaf_tbl_tcam_init(dsaf_dev); + hns_dsaf_tbl_line_init(dsaf_dev); +} + +/** + * hns_dsaf_voq_init - INT + * @dsaf_id: dsa fabric id + */ +static void hns_dsaf_voq_init(struct dsaf_device *dsaf_dev) +{ + hns_dsaf_voq_bp_all_thrd_cfg(dsaf_dev); +} + +/** + * hns_dsaf_init_hw - init dsa fabric hardware + * @dsaf_dev: dsa fabric device struct pointer + */ +static int hns_dsaf_init_hw(struct dsaf_device *dsaf_dev) +{ + int ret; + + dev_dbg(dsaf_dev->dev, + "hns_dsaf_init_hw begin %s !\n", dsaf_dev->ae_dev.name); + + hns_dsaf_rst(dsaf_dev, 0); + mdelay(10); + hns_dsaf_rst(dsaf_dev, 1); + + hns_dsaf_comm_init(dsaf_dev); + + /*init XBAR_INODE*/ + hns_dsaf_inode_init(dsaf_dev); + + /*init SBM*/ + ret = hns_dsaf_sbm_init(dsaf_dev); + if (ret) + return ret; + + /*init TBL*/ + hns_dsaf_tbl_init(dsaf_dev); + + /*init VOQ*/ + hns_dsaf_voq_init(dsaf_dev); + + return 0; +} + +/** + * hns_dsaf_remove_hw - uninit dsa fabric hardware + * @dsaf_dev: dsa fabric device struct pointer + */ +static void hns_dsaf_remove_hw(struct dsaf_device *dsaf_dev) +{ + /*reset*/ + hns_dsaf_rst(dsaf_dev, 0); +} + +/** + * hns_dsaf_init - init dsa fabric + * @dsaf_dev: dsa fabric device struct pointer + * retuen 0 - success , negative --fail + */ +static int hns_dsaf_init(struct dsaf_device *dsaf_dev) +{ + struct dsaf_drv_priv *priv = + (struct dsaf_drv_priv *)hns_dsaf_dev_priv(dsaf_dev); + u32 i; + int ret; + + ret = hns_dsaf_init_hw(dsaf_dev); + if (ret) + return ret; + + /* malloc mem for tcam mac key(vlan+mac) */ + priv->soft_mac_tbl = vzalloc(sizeof(*priv->soft_mac_tbl) + * DSAF_TCAM_SUM); + if (!priv->soft_mac_tbl) { + ret = -ENOMEM; + goto remove_hw; + } + + /*all entry invall */ + for (i = 0; i < DSAF_TCAM_SUM; i++) + (priv->soft_mac_tbl + i)->index = DSAF_INVALID_ENTRY_IDX; + + return 0; + +remove_hw: + hns_dsaf_remove_hw(dsaf_dev); + return ret; +} + +/** + * hns_dsaf_free - free dsa fabric + * @dsaf_dev: dsa fabric device struct pointer + */ +static void hns_dsaf_free(struct dsaf_device *dsaf_dev) +{ + struct dsaf_drv_priv *priv = + (struct dsaf_drv_priv *)hns_dsaf_dev_priv(dsaf_dev); + + hns_dsaf_remove_hw(dsaf_dev); + + /* free all mac mem */ + vfree(priv->soft_mac_tbl); + priv->soft_mac_tbl = NULL; +} + +/** + * hns_dsaf_find_soft_mac_entry - find dsa fabric soft entry + * @dsaf_dev: dsa fabric device struct pointer + * @mac_key: mac entry struct pointer + */ +static u16 hns_dsaf_find_soft_mac_entry( + struct dsaf_device *dsaf_dev, + struct dsaf_drv_tbl_tcam_key *mac_key) +{ + struct dsaf_drv_priv *priv = + (struct dsaf_drv_priv *)hns_dsaf_dev_priv(dsaf_dev); + struct dsaf_drv_soft_mac_tbl *soft_mac_entry; + u32 i; + + soft_mac_entry = priv->soft_mac_tbl; + for (i = 0; i < DSAF_TCAM_SUM; i++) { + /* invall tab entry */ + if ((soft_mac_entry->index != DSAF_INVALID_ENTRY_IDX) && + (soft_mac_entry->tcam_key.high.val == mac_key->high.val) && + (soft_mac_entry->tcam_key.low.val == mac_key->low.val)) + /* return find result --soft index */ + return soft_mac_entry->index; + + soft_mac_entry++; + } + return DSAF_INVALID_ENTRY_IDX; +} + +/** + * hns_dsaf_find_empty_mac_entry - search dsa fabric soft empty-entry + * @dsaf_dev: dsa fabric device struct pointer + */ +static u16 hns_dsaf_find_empty_mac_entry(struct dsaf_device *dsaf_dev) +{ + struct dsaf_drv_priv *priv = + (struct dsaf_drv_priv *)hns_dsaf_dev_priv(dsaf_dev); + struct dsaf_drv_soft_mac_tbl *soft_mac_entry; + u32 i; + + soft_mac_entry = priv->soft_mac_tbl; + for (i = 0; i < DSAF_TCAM_SUM; i++) { + /* inv all entry */ + if (soft_mac_entry->index == DSAF_INVALID_ENTRY_IDX) + /* return find result --soft index */ + return i; + + soft_mac_entry++; + } + return DSAF_INVALID_ENTRY_IDX; +} + +/** + * hns_dsaf_set_mac_key - set mac key + * @dsaf_dev: dsa fabric device struct pointer + * @mac_key: tcam key pointer + * @vlan_id: vlan id + * @in_port_num: input port num + * @addr: mac addr + */ +static void hns_dsaf_set_mac_key( + struct dsaf_device *dsaf_dev, + struct dsaf_drv_tbl_tcam_key *mac_key, u16 vlan_id, u8 in_port_num, + u8 *addr) +{ + u8 port; + + if (dsaf_dev->dsaf_mode <= DSAF_MODE_ENABLE) + /*DSAF mode : in port id fixed 0*/ + port = 0; + else + /*non-dsaf mode*/ + port = in_port_num; + + mac_key->high.bits.mac_0 = addr[0]; + mac_key->high.bits.mac_1 = addr[1]; + mac_key->high.bits.mac_2 = addr[2]; + mac_key->high.bits.mac_3 = addr[3]; + mac_key->low.bits.mac_4 = addr[4]; + mac_key->low.bits.mac_5 = addr[5]; + mac_key->low.bits.vlan = vlan_id; + mac_key->low.bits.port = port; +} + +/** + * hns_dsaf_set_mac_uc_entry - set mac uc-entry + * @dsaf_dev: dsa fabric device struct pointer + * @mac_entry: uc-mac entry + */ +int hns_dsaf_set_mac_uc_entry( + struct dsaf_device *dsaf_dev, + struct dsaf_drv_mac_single_dest_entry *mac_entry) +{ + u16 entry_index = DSAF_INVALID_ENTRY_IDX; + struct dsaf_drv_tbl_tcam_key mac_key; + struct dsaf_tbl_tcam_ucast_cfg mac_data; + struct dsaf_drv_priv *priv = + (struct dsaf_drv_priv *)hns_dsaf_dev_priv(dsaf_dev); + struct dsaf_drv_soft_mac_tbl *soft_mac_entry = priv->soft_mac_tbl; + + /* mac addr check */ + if (MAC_IS_ALL_ZEROS(mac_entry->addr) || + MAC_IS_BROADCAST(mac_entry->addr) || + MAC_IS_MULTICAST(mac_entry->addr)) { + dev_err(dsaf_dev->dev, + "set_uc %s Mac %02x:%02x:%02x:%02x:%02x:%02x err!\n", + dsaf_dev->ae_dev.name, mac_entry->addr[0], + mac_entry->addr[1], mac_entry->addr[2], + mac_entry->addr[3], mac_entry->addr[4], + mac_entry->addr[5]); + return -EINVAL; + } + + /* config key */ + hns_dsaf_set_mac_key(dsaf_dev, &mac_key, mac_entry->in_vlan_id, + mac_entry->in_port_num, mac_entry->addr); + + /* entry ie exist? */ + entry_index = hns_dsaf_find_soft_mac_entry(dsaf_dev, &mac_key); + if (entry_index == DSAF_INVALID_ENTRY_IDX) { + /*if has not inv entry,find a empty entry */ + entry_index = hns_dsaf_find_empty_mac_entry(dsaf_dev); + if (entry_index == DSAF_INVALID_ENTRY_IDX) { + /* has not empty,return error */ + dev_err(dsaf_dev->dev, + "set_uc_entry failed, %s Mac key(%#x:%#x)\n", + dsaf_dev->ae_dev.name, + mac_key.high.val, mac_key.low.val); + return -EINVAL; + } + } + + dev_dbg(dsaf_dev->dev, + "set_uc_entry, %s Mac key(%#x:%#x) entry_index%d\n", + dsaf_dev->ae_dev.name, mac_key.high.val, + mac_key.low.val, entry_index); + + /* config hardware entry */ + mac_data.tbl_ucast_item_vld = 1; + mac_data.tbl_ucast_mac_discard = 0; + mac_data.tbl_ucast_old_en = 0; + /* default config dvc to 0 */ + mac_data.tbl_ucast_dvc = 0; + mac_data.tbl_ucast_out_port = mac_entry->port_num; + hns_dsaf_tcam_uc_cfg( + dsaf_dev, entry_index, + (struct dsaf_tbl_tcam_data *)(&mac_key), &mac_data); + + /* config software entry */ + soft_mac_entry += entry_index; + soft_mac_entry->index = entry_index; + soft_mac_entry->tcam_key.high.val = mac_key.high.val; + soft_mac_entry->tcam_key.low.val = mac_key.low.val; + + return 0; +} + +/** + * hns_dsaf_set_mac_mc_entry - set mac mc-entry + * @dsaf_dev: dsa fabric device struct pointer + * @mac_entry: mc-mac entry + */ +int hns_dsaf_set_mac_mc_entry( + struct dsaf_device *dsaf_dev, + struct dsaf_drv_mac_multi_dest_entry *mac_entry) +{ + u16 entry_index = DSAF_INVALID_ENTRY_IDX; + struct dsaf_drv_tbl_tcam_key mac_key; + struct dsaf_tbl_tcam_mcast_cfg mac_data; + struct dsaf_drv_priv *priv = + (struct dsaf_drv_priv *)hns_dsaf_dev_priv(dsaf_dev); + struct dsaf_drv_soft_mac_tbl *soft_mac_entry = priv->soft_mac_tbl; + struct dsaf_drv_tbl_tcam_key tmp_mac_key; + + /* mac addr check */ + if (MAC_IS_ALL_ZEROS(mac_entry->addr)) { + dev_err(dsaf_dev->dev, + "set uc %s Mac %02x:%02x:%02x:%02x:%02x:%02x err!\n", + dsaf_dev->ae_dev.name, mac_entry->addr[0], + mac_entry->addr[1], mac_entry->addr[2], + mac_entry->addr[3], + mac_entry->addr[4], mac_entry->addr[5]); + return -EINVAL; + } + + /*config key */ + hns_dsaf_set_mac_key(dsaf_dev, &mac_key, + mac_entry->in_vlan_id, + mac_entry->in_port_num, mac_entry->addr); + + /* entry ie exist? */ + entry_index = hns_dsaf_find_soft_mac_entry(dsaf_dev, &mac_key); + if (entry_index == DSAF_INVALID_ENTRY_IDX) { + /*if hasnot, find enpty entry*/ + entry_index = hns_dsaf_find_empty_mac_entry(dsaf_dev); + if (entry_index == DSAF_INVALID_ENTRY_IDX) { + /*if hasnot empty, error*/ + dev_err(dsaf_dev->dev, + "set_uc_entry failed, %s Mac key(%#x:%#x)\n", + dsaf_dev->ae_dev.name, + mac_key.high.val, mac_key.low.val); + return -EINVAL; + } + + /* config hardware entry */ + memset(mac_data.tbl_mcast_port_msk, + 0, sizeof(mac_data.tbl_mcast_port_msk)); + } else { + /* config hardware entry */ + hns_dsaf_tcam_mc_get( + dsaf_dev, entry_index, + (struct dsaf_tbl_tcam_data *)(&tmp_mac_key), &mac_data); + } + mac_data.tbl_mcast_old_en = 0; + mac_data.tbl_mcast_item_vld = 1; + dsaf_set_field(mac_data.tbl_mcast_port_msk[0], + 0x3F, 0, mac_entry->port_mask[0]); + + dev_dbg(dsaf_dev->dev, + "set_uc_entry, %s key(%#x:%#x) entry_index%d\n", + dsaf_dev->ae_dev.name, mac_key.high.val, + mac_key.low.val, entry_index); + + hns_dsaf_tcam_mc_cfg( + dsaf_dev, entry_index, + (struct dsaf_tbl_tcam_data *)(&mac_key), &mac_data); + + /* config software entry */ + soft_mac_entry += entry_index; + soft_mac_entry->index = entry_index; + soft_mac_entry->tcam_key.high.val = mac_key.high.val; + soft_mac_entry->tcam_key.low.val = mac_key.low.val; + + return 0; +} + +/** + * hns_dsaf_add_mac_mc_port - add mac mc-port + * @dsaf_dev: dsa fabric device struct pointer + * @mac_entry: mc-mac entry + */ +int hns_dsaf_add_mac_mc_port(struct dsaf_device *dsaf_dev, + struct dsaf_drv_mac_single_dest_entry *mac_entry) +{ + u16 entry_index = DSAF_INVALID_ENTRY_IDX; + struct dsaf_drv_tbl_tcam_key mac_key; + struct dsaf_tbl_tcam_mcast_cfg mac_data; + struct dsaf_drv_priv *priv = + (struct dsaf_drv_priv *)hns_dsaf_dev_priv(dsaf_dev); + struct dsaf_drv_soft_mac_tbl *soft_mac_entry = priv->soft_mac_tbl; + struct dsaf_drv_tbl_tcam_key tmp_mac_key; + int mskid; + + /*chechk mac addr */ + if (MAC_IS_ALL_ZEROS(mac_entry->addr)) { + dev_err(dsaf_dev->dev, + "set_entry failed,addr %02x:%02x:%02x:%02x:%02x:%02x!\n", + mac_entry->addr[0], mac_entry->addr[1], + mac_entry->addr[2], mac_entry->addr[3], + mac_entry->addr[4], mac_entry->addr[5]); + return -EINVAL; + } + + /*config key */ + hns_dsaf_set_mac_key( + dsaf_dev, &mac_key, mac_entry->in_vlan_id, + mac_entry->in_port_num, mac_entry->addr); + + memset(&mac_data, 0, sizeof(struct dsaf_tbl_tcam_mcast_cfg)); + + /*check exist? */ + entry_index = hns_dsaf_find_soft_mac_entry(dsaf_dev, &mac_key); + if (entry_index == DSAF_INVALID_ENTRY_IDX) { + /*if hasnot , find a empty*/ + entry_index = hns_dsaf_find_empty_mac_entry(dsaf_dev); + if (entry_index == DSAF_INVALID_ENTRY_IDX) { + /*if hasnot empty, error*/ + dev_err(dsaf_dev->dev, + "set_uc_entry failed, %s Mac key(%#x:%#x)\n", + dsaf_dev->ae_dev.name, mac_key.high.val, + mac_key.low.val); + return -EINVAL; + } + } else { + /*if exist, add in */ + hns_dsaf_tcam_mc_get( + dsaf_dev, entry_index, + (struct dsaf_tbl_tcam_data *)(&tmp_mac_key), &mac_data); + } + /* config hardware entry */ + if (mac_entry->port_num < DSAF_SERVICE_NW_NUM) { + mskid = mac_entry->port_num; + } else if (mac_entry->port_num >= DSAF_BASE_INNER_PORT_NUM) { + mskid = mac_entry->port_num - + DSAF_BASE_INNER_PORT_NUM + DSAF_SERVICE_NW_NUM; + } else { + dev_err(dsaf_dev->dev, + "%s,pnum(%d)error,key(%#x:%#x)\n", + dsaf_dev->ae_dev.name, mac_entry->port_num, + mac_key.high.val, mac_key.low.val); + return -EINVAL; + } + dsaf_set_bit(mac_data.tbl_mcast_port_msk[mskid / 32], mskid % 32, 1); + mac_data.tbl_mcast_old_en = 0; + mac_data.tbl_mcast_item_vld = 1; + + dev_dbg(dsaf_dev->dev, + "set_uc_entry, %s Mac key(%#x:%#x) entry_index%d\n", + dsaf_dev->ae_dev.name, mac_key.high.val, + mac_key.low.val, entry_index); + + hns_dsaf_tcam_mc_cfg( + dsaf_dev, entry_index, + (struct dsaf_tbl_tcam_data *)(&mac_key), &mac_data); + + /*config software entry */ + soft_mac_entry += entry_index; + soft_mac_entry->index = entry_index; + soft_mac_entry->tcam_key.high.val = mac_key.high.val; + soft_mac_entry->tcam_key.low.val = mac_key.low.val; + + return 0; +} + +/** + * hns_dsaf_del_mac_entry - del mac mc-port + * @dsaf_dev: dsa fabric device struct pointer + * @vlan_id: vlian id + * @in_port_num: input port num + * @addr : mac addr + */ +int hns_dsaf_del_mac_entry(struct dsaf_device *dsaf_dev, u16 vlan_id, + u8 in_port_num, u8 *addr) +{ + u16 entry_index = DSAF_INVALID_ENTRY_IDX; + struct dsaf_drv_tbl_tcam_key mac_key; + struct dsaf_drv_priv *priv = + (struct dsaf_drv_priv *)hns_dsaf_dev_priv(dsaf_dev); + struct dsaf_drv_soft_mac_tbl *soft_mac_entry = priv->soft_mac_tbl; + + /*check mac addr */ + if (MAC_IS_ALL_ZEROS(addr) || MAC_IS_BROADCAST(addr)) { + dev_err(dsaf_dev->dev, + "del_entry failed,addr %02x:%02x:%02x:%02x:%02x:%02x!\n", + addr[0], addr[1], addr[2], addr[3], addr[4], addr[5]); + return -EINVAL; + } + + /*config key */ + hns_dsaf_set_mac_key(dsaf_dev, &mac_key, vlan_id, in_port_num, addr); + + /*exist ?*/ + entry_index = hns_dsaf_find_soft_mac_entry(dsaf_dev, &mac_key); + if (entry_index == DSAF_INVALID_ENTRY_IDX) { + /*not exist, error */ + dev_err(dsaf_dev->dev, + "del_mac_entry failed, %s Mac key(%#x:%#x)\n", + dsaf_dev->ae_dev.name, + mac_key.high.val, mac_key.low.val); + return -EINVAL; + } + dev_dbg(dsaf_dev->dev, + "del_mac_entry, %s Mac key(%#x:%#x) entry_index%d\n", + dsaf_dev->ae_dev.name, mac_key.high.val, + mac_key.low.val, entry_index); + + /*do del opt*/ + hns_dsaf_tcam_mc_invld(dsaf_dev, entry_index); + + /*del soft emtry */ + soft_mac_entry += entry_index; + soft_mac_entry->index = DSAF_INVALID_ENTRY_IDX; + + return 0; +} + +/** + * hns_dsaf_del_mac_mc_port - del mac mc- port + * @dsaf_dev: dsa fabric device struct pointer + * @mac_entry: mac entry + */ +int hns_dsaf_del_mac_mc_port(struct dsaf_device *dsaf_dev, + struct dsaf_drv_mac_single_dest_entry *mac_entry) +{ + u16 entry_index = DSAF_INVALID_ENTRY_IDX; + struct dsaf_drv_tbl_tcam_key mac_key; + struct dsaf_drv_priv *priv = + (struct dsaf_drv_priv *)hns_dsaf_dev_priv(dsaf_dev); + struct dsaf_drv_soft_mac_tbl *soft_mac_entry = priv->soft_mac_tbl; + u16 vlan_id; + u8 in_port_num; + struct dsaf_tbl_tcam_mcast_cfg mac_data; + struct dsaf_drv_tbl_tcam_key tmp_mac_key; + int mskid; + const u8 empty_msk[sizeof(mac_data.tbl_mcast_port_msk)] = {0}; + + if (!(void *)mac_entry) { + dev_err(dsaf_dev->dev, + "hns_dsaf_del_mac_mc_port mac_entry is NULL\n"); + return -EINVAL; + } + + /*get key info*/ + vlan_id = mac_entry->in_vlan_id; + in_port_num = mac_entry->in_port_num; + + /*check mac addr */ + if (MAC_IS_ALL_ZEROS(mac_entry->addr)) { + dev_err(dsaf_dev->dev, + "del_port failed, addr %02x:%02x:%02x:%02x:%02x:%02x!\n", + mac_entry->addr[0], mac_entry->addr[1], + mac_entry->addr[2], mac_entry->addr[3], + mac_entry->addr[4], mac_entry->addr[5]); + return -EINVAL; + } + + /*config key */ + hns_dsaf_set_mac_key(dsaf_dev, &mac_key, vlan_id, in_port_num, + mac_entry->addr); + + /*check is exist? */ + entry_index = hns_dsaf_find_soft_mac_entry(dsaf_dev, &mac_key); + if (entry_index == DSAF_INVALID_ENTRY_IDX) { + /*find none */ + dev_err(dsaf_dev->dev, + "find_soft_mac_entry failed, %s Mac key(%#x:%#x)\n", + dsaf_dev->ae_dev.name, + mac_key.high.val, mac_key.low.val); + return -EINVAL; + } + + dev_dbg(dsaf_dev->dev, + "del_mac_mc_port, %s key(%#x:%#x) index%d\n", + dsaf_dev->ae_dev.name, mac_key.high.val, + mac_key.low.val, entry_index); + + /*read entry*/ + hns_dsaf_tcam_mc_get( + dsaf_dev, entry_index, + (struct dsaf_tbl_tcam_data *)(&tmp_mac_key), &mac_data); + + /*del the port*/ + if (mac_entry->port_num < DSAF_SERVICE_NW_NUM) { + mskid = mac_entry->port_num; + } else if (mac_entry->port_num >= DSAF_BASE_INNER_PORT_NUM) { + mskid = mac_entry->port_num - + DSAF_BASE_INNER_PORT_NUM + DSAF_SERVICE_NW_NUM; + } else { + dev_err(dsaf_dev->dev, + "%s,pnum(%d)error,key(%#x:%#x)\n", + dsaf_dev->ae_dev.name, mac_entry->port_num, + mac_key.high.val, mac_key.low.val); + return -EINVAL; + } + dsaf_set_bit(mac_data.tbl_mcast_port_msk[mskid / 32], mskid % 32, 0); + + /*check non port, do del entry */ + if (!memcmp(mac_data.tbl_mcast_port_msk, empty_msk, + sizeof(mac_data.tbl_mcast_port_msk))) { + hns_dsaf_tcam_mc_invld(dsaf_dev, entry_index); + + /* del soft entry */ + soft_mac_entry += entry_index; + soft_mac_entry->index = DSAF_INVALID_ENTRY_IDX; + } else { /* not zer, just del port, updata*/ + hns_dsaf_tcam_mc_cfg( + dsaf_dev, entry_index, + (struct dsaf_tbl_tcam_data *)(&mac_key), &mac_data); + } + + return 0; +} + +/** + * hns_dsaf_get_mac_uc_entry - get mac uc entry + * @dsaf_dev: dsa fabric device struct pointer + * @mac_entry: mac entry + */ +int hns_dsaf_get_mac_uc_entry(struct dsaf_device *dsaf_dev, + struct dsaf_drv_mac_single_dest_entry *mac_entry) +{ + u16 entry_index = DSAF_INVALID_ENTRY_IDX; + struct dsaf_drv_tbl_tcam_key mac_key; + + struct dsaf_tbl_tcam_ucast_cfg mac_data; + + /* check macaddr */ + if (MAC_IS_ALL_ZEROS(mac_entry->addr) || + MAC_IS_BROADCAST(mac_entry->addr)) { + dev_err(dsaf_dev->dev, + "get_entry failed,addr %02x:%02x:%02x:%02x:%02x:%02x\n", + mac_entry->addr[0], mac_entry->addr[1], + mac_entry->addr[2], mac_entry->addr[3], + mac_entry->addr[4], mac_entry->addr[5]); + return -EINVAL; + } + + /*config key */ + hns_dsaf_set_mac_key(dsaf_dev, &mac_key, mac_entry->in_vlan_id, + mac_entry->in_port_num, mac_entry->addr); + + /*check exist? */ + entry_index = hns_dsaf_find_soft_mac_entry(dsaf_dev, &mac_key); + if (entry_index == DSAF_INVALID_ENTRY_IDX) { + /*find none, error */ + dev_err(dsaf_dev->dev, + "get_uc_entry failed, %s Mac key(%#x:%#x)\n", + dsaf_dev->ae_dev.name, + mac_key.high.val, mac_key.low.val); + return -EINVAL; + } + dev_dbg(dsaf_dev->dev, + "get_uc_entry, %s Mac key(%#x:%#x) entry_index%d\n", + dsaf_dev->ae_dev.name, mac_key.high.val, + mac_key.low.val, entry_index); + + /*read entry*/ + hns_dsaf_tcam_uc_get(dsaf_dev, entry_index, + (struct dsaf_tbl_tcam_data *)&mac_key, &mac_data); + mac_entry->port_num = mac_data.tbl_ucast_out_port; + + return 0; +} + +/** + * hns_dsaf_get_mac_mc_entry - get mac mc entry + * @dsaf_dev: dsa fabric device struct pointer + * @mac_entry: mac entry + */ +int hns_dsaf_get_mac_mc_entry(struct dsaf_device *dsaf_dev, + struct dsaf_drv_mac_multi_dest_entry *mac_entry) +{ + u16 entry_index = DSAF_INVALID_ENTRY_IDX; + struct dsaf_drv_tbl_tcam_key mac_key; + + struct dsaf_tbl_tcam_mcast_cfg mac_data; + + /*check mac addr */ + if (MAC_IS_ALL_ZEROS(mac_entry->addr) || + MAC_IS_BROADCAST(mac_entry->addr)) { + dev_err(dsaf_dev->dev, + "get_entry failed,addr %02x:%02x:%02x:%02x:%02x:%02x\n", + mac_entry->addr[0], mac_entry->addr[1], + mac_entry->addr[2], mac_entry->addr[3], + mac_entry->addr[4], mac_entry->addr[5]); + return -EINVAL; + } + + /*config key */ + hns_dsaf_set_mac_key(dsaf_dev, &mac_key, mac_entry->in_vlan_id, + mac_entry->in_port_num, mac_entry->addr); + + /*check exist? */ + entry_index = hns_dsaf_find_soft_mac_entry(dsaf_dev, &mac_key); + if (entry_index == DSAF_INVALID_ENTRY_IDX) { + /* find none, error */ + dev_err(dsaf_dev->dev, + "get_mac_uc_entry failed, %s Mac key(%#x:%#x)\n", + dsaf_dev->ae_dev.name, mac_key.high.val, + mac_key.low.val); + return -EINVAL; + } + dev_dbg(dsaf_dev->dev, + "get_mac_uc_entry, %s Mac key(%#x:%#x) entry_index%d\n", + dsaf_dev->ae_dev.name, mac_key.high.val, + mac_key.low.val, entry_index); + + /*read entry */ + hns_dsaf_tcam_mc_get(dsaf_dev, entry_index, + (struct dsaf_tbl_tcam_data *)&mac_key, &mac_data); + + mac_entry->port_mask[0] = mac_data.tbl_mcast_port_msk[0] & 0x3F; + return 0; +} + +/** + * hns_dsaf_get_mac_entry_by_index - get mac entry by tab index + * @dsaf_dev: dsa fabric device struct pointer + * @entry_index: tab entry index + * @mac_entry: mac entry + */ +int hns_dsaf_get_mac_entry_by_index( + struct dsaf_device *dsaf_dev, + u16 entry_index, struct dsaf_drv_mac_multi_dest_entry *mac_entry) +{ + struct dsaf_drv_tbl_tcam_key mac_key; + + struct dsaf_tbl_tcam_mcast_cfg mac_data; + struct dsaf_tbl_tcam_ucast_cfg mac_uc_data; + char mac_addr[MAC_NUM_OCTETS_PER_ADDR] = {0}; + + if (entry_index >= DSAF_TCAM_SUM) { + /* find none, del error */ + dev_err(dsaf_dev->dev, "get_uc_entry failed, %s\n", + dsaf_dev->ae_dev.name); + return -EINVAL; + } + + /* mc entry, do read opt */ + hns_dsaf_tcam_mc_get(dsaf_dev, entry_index, + (struct dsaf_tbl_tcam_data *)&mac_key, &mac_data); + + mac_entry->port_mask[0] = mac_data.tbl_mcast_port_msk[0] & 0x3F; + + /***get mac addr*/ + mac_addr[0] = mac_key.high.bits.mac_0; + mac_addr[1] = mac_key.high.bits.mac_1; + mac_addr[2] = mac_key.high.bits.mac_2; + mac_addr[3] = mac_key.high.bits.mac_3; + mac_addr[4] = mac_key.low.bits.mac_4; + mac_addr[5] = mac_key.low.bits.mac_5; + /**is mc or uc*/ + if (MAC_IS_MULTICAST((u8 *)mac_addr) || + MAC_IS_L3_MULTICAST((u8 *)mac_addr)) { + /**mc donot do*/ + } else { + /*is not mc, just uc... */ + hns_dsaf_tcam_uc_get(dsaf_dev, entry_index, + (struct dsaf_tbl_tcam_data *)&mac_key, + &mac_uc_data); + mac_entry->port_mask[0] = (1 << mac_uc_data.tbl_ucast_out_port); + } + + return 0; +} + +static struct dsaf_device *hns_dsaf_alloc_dev(struct device *dev, + size_t sizeof_priv) +{ + struct dsaf_device *dsaf_dev; + + dsaf_dev = devm_kzalloc(dev, + sizeof(*dsaf_dev) + sizeof_priv, GFP_KERNEL); + if (unlikely(!dsaf_dev)) { + dsaf_dev = ERR_PTR(-ENOMEM); + } else { + dsaf_dev->dev = dev; + dev_set_drvdata(dev, dsaf_dev); + } + + return dsaf_dev; +} + +/** + * hns_dsaf_free_dev - free dev mem + * @dev: struct device pointer + */ +static void hns_dsaf_free_dev(struct dsaf_device *dsaf_dev) +{ + (void)dev_set_drvdata(dsaf_dev->dev, NULL); +} + +/** + * dsaf_pfc_unit_cnt - set pfc unit count + * @dsaf_id: dsa fabric id + * @pport_rate: value array + * @pdsaf_pfc_unit_cnt: value array + */ +static void hns_dsaf_pfc_unit_cnt(struct dsaf_device *dsaf_dev, int mac_id, + enum dsaf_port_rate_mode rate) +{ + u32 unit_cnt; + + switch (rate) { + case DSAF_PORT_RATE_10000: + unit_cnt = HNS_DSAF_PFC_UNIT_CNT_FOR_XGE; + break; + case DSAF_PORT_RATE_1000: + unit_cnt = HNS_DSAF_PFC_UNIT_CNT_FOR_GE_1000; + break; + case DSAF_PORT_RATE_2500: + unit_cnt = HNS_DSAF_PFC_UNIT_CNT_FOR_GE_1000; + break; + default: + unit_cnt = HNS_DSAF_PFC_UNIT_CNT_FOR_XGE; + } + + dsaf_set_dev_field(dsaf_dev, + (DSAF_PFC_UNIT_CNT_0_REG + 0x4 * (u64)mac_id), + DSAF_PFC_UNINT_CNT_M, DSAF_PFC_UNINT_CNT_S, + unit_cnt); +} + +/** + * dsaf_port_work_rate_cfg - fifo + * @dsaf_id: dsa fabric id + * @xge_ge_work_mode + */ +void hns_dsaf_port_work_rate_cfg(struct dsaf_device *dsaf_dev, int mac_id, + enum dsaf_port_rate_mode rate_mode) +{ + u32 port_work_mode; + + port_work_mode = dsaf_read_dev( + dsaf_dev, DSAF_XGE_GE_WORK_MODE_0_REG + 0x4 * (u64)mac_id); + + if (rate_mode == DSAF_PORT_RATE_10000) + dsaf_set_bit(port_work_mode, DSAF_XGE_GE_WORK_MODE_S, 1); + else + dsaf_set_bit(port_work_mode, DSAF_XGE_GE_WORK_MODE_S, 0); + + dsaf_write_dev(dsaf_dev, + DSAF_XGE_GE_WORK_MODE_0_REG + 0x4 * (u64)mac_id, + port_work_mode); + + hns_dsaf_pfc_unit_cnt(dsaf_dev, mac_id, rate_mode); +} + +/** + * hns_dsaf_fix_mac_mode - dsaf modify mac mode + * @mac_cb: mac contrl block + */ +void hns_dsaf_fix_mac_mode(struct hns_mac_cb *mac_cb) +{ + enum dsaf_port_rate_mode mode; + struct dsaf_device *dsaf_dev = mac_cb->dsaf_dev; + int mac_id = mac_cb->mac_id; + + if (mac_cb->mac_type != HNAE_PORT_SERVICE) + return; + if (mac_cb->phy_if == PHY_INTERFACE_MODE_XGMII) + mode = DSAF_PORT_RATE_10000; + else + mode = DSAF_PORT_RATE_1000; + + hns_dsaf_port_work_rate_cfg(dsaf_dev, mac_id, mode); +} + +void hns_dsaf_update_stats(struct dsaf_device *dsaf_dev, u32 node_num) +{ + struct dsaf_hw_stats *hw_stats + = &dsaf_dev->hw_stats[node_num]; + + hw_stats->pad_drop += dsaf_read_dev(dsaf_dev, + DSAF_INODE_PAD_DISCARD_NUM_0_REG + 0x80 * (u64)node_num); + hw_stats->man_pkts += dsaf_read_dev(dsaf_dev, + DSAF_INODE_FINAL_IN_MAN_NUM_0_REG + 0x80 * (u64)node_num); + hw_stats->rx_pkts += dsaf_read_dev(dsaf_dev, + DSAF_INODE_FINAL_IN_PKT_NUM_0_REG + 0x80 * (u64)node_num); + hw_stats->rx_pkt_id += dsaf_read_dev(dsaf_dev, + DSAF_INODE_SBM_PID_NUM_0_REG + 0x80 * (u64)node_num); + hw_stats->rx_pause_frame += dsaf_read_dev(dsaf_dev, + DSAF_INODE_FINAL_IN_PAUSE_NUM_0_REG + 0x80 * (u64)node_num); + hw_stats->release_buf_num += dsaf_read_dev(dsaf_dev, + DSAF_INODE_SBM_RELS_NUM_0_REG + 0x80 * (u64)node_num); + hw_stats->sbm_drop += dsaf_read_dev(dsaf_dev, + DSAF_INODE_SBM_DROP_NUM_0_REG + 0x80 * (u64)node_num); + hw_stats->crc_false += dsaf_read_dev(dsaf_dev, + DSAF_INODE_CRC_FALSE_NUM_0_REG + 0x80 * (u64)node_num); + hw_stats->bp_drop += dsaf_read_dev(dsaf_dev, + DSAF_INODE_BP_DISCARD_NUM_0_REG + 0x80 * (u64)node_num); + hw_stats->rslt_drop += dsaf_read_dev(dsaf_dev, + DSAF_INODE_RSLT_DISCARD_NUM_0_REG + 0x80 * (u64)node_num); + hw_stats->local_addr_false += dsaf_read_dev(dsaf_dev, + DSAF_INODE_LOCAL_ADDR_FALSE_NUM_0_REG + 0x80 * (u64)node_num); + + hw_stats->vlan_drop += dsaf_read_dev(dsaf_dev, + DSAF_INODE_SW_VLAN_TAG_DISC_0_REG + 0x80 * (u64)node_num); + hw_stats->stp_drop += dsaf_read_dev(dsaf_dev, + DSAF_INODE_IN_DATA_STP_DISC_0_REG + 0x80 * (u64)node_num); + + hw_stats->tx_pkts += dsaf_read_dev(dsaf_dev, + DSAF_XOD_RCVPKT_CNT_0_REG + 0x90 * (u64)node_num); +} + +/** + *hns_dsaf_get_regs - dump dsaf regs + *@dsaf_dev: dsaf device + *@data:data for value of regs + */ +void hns_dsaf_get_regs(struct dsaf_device *ddev, u32 port, void *data) +{ + u32 i = 0; + u32 j; + u32 *p = data; + + /* dsaf common registers */ + p[0] = dsaf_read_dev(ddev, DSAF_SRAM_INIT_OVER_0_REG); + p[1] = dsaf_read_dev(ddev, DSAF_CFG_0_REG); + p[2] = dsaf_read_dev(ddev, DSAF_ECC_ERR_INVERT_0_REG); + p[3] = dsaf_read_dev(ddev, DSAF_ABNORMAL_TIMEOUT_0_REG); + p[4] = dsaf_read_dev(ddev, DSAF_FSM_TIMEOUT_0_REG); + p[5] = dsaf_read_dev(ddev, DSAF_DSA_REG_CNT_CLR_CE_REG); + p[6] = dsaf_read_dev(ddev, DSAF_DSA_SBM_INF_FIFO_THRD_REG); + p[7] = dsaf_read_dev(ddev, DSAF_DSA_SRAM_1BIT_ECC_SEL_REG); + p[8] = dsaf_read_dev(ddev, DSAF_DSA_SRAM_1BIT_ECC_CNT_REG); + + p[9] = dsaf_read_dev(ddev, DSAF_PFC_EN_0_REG + port * 4); + p[10] = dsaf_read_dev(ddev, DSAF_PFC_UNIT_CNT_0_REG + port * 4); + p[11] = dsaf_read_dev(ddev, DSAF_XGE_INT_MSK_0_REG + port * 4); + p[12] = dsaf_read_dev(ddev, DSAF_XGE_INT_SRC_0_REG + port * 4); + p[13] = dsaf_read_dev(ddev, DSAF_XGE_INT_STS_0_REG + port * 4); + p[14] = dsaf_read_dev(ddev, DSAF_XGE_INT_MSK_0_REG + port * 4); + p[15] = dsaf_read_dev(ddev, DSAF_PPE_INT_MSK_0_REG + port * 4); + p[16] = dsaf_read_dev(ddev, DSAF_ROCEE_INT_MSK_0_REG + port * 4); + p[17] = dsaf_read_dev(ddev, DSAF_XGE_INT_SRC_0_REG + port * 4); + p[18] = dsaf_read_dev(ddev, DSAF_PPE_INT_SRC_0_REG + port * 4); + p[19] = dsaf_read_dev(ddev, DSAF_ROCEE_INT_SRC_0_REG + port * 4); + p[20] = dsaf_read_dev(ddev, DSAF_XGE_INT_STS_0_REG + port * 4); + p[21] = dsaf_read_dev(ddev, DSAF_PPE_INT_STS_0_REG + port * 4); + p[22] = dsaf_read_dev(ddev, DSAF_ROCEE_INT_STS_0_REG + port * 4); + p[23] = dsaf_read_dev(ddev, DSAF_PPE_QID_CFG_0_REG + port * 4); + + for (i = 0; i < DSAF_SW_PORT_NUM; i++) + p[24 + i] = dsaf_read_dev(ddev, + DSAF_SW_PORT_TYPE_0_REG + i * 4); + + p[32] = dsaf_read_dev(ddev, DSAF_MIX_DEF_QID_0_REG + port * 4); + + for (i = 0; i < DSAF_SW_PORT_NUM; i++) + p[33 + i] = dsaf_read_dev(ddev, + DSAF_PORT_DEF_VLAN_0_REG + i * 4); + + for (i = 0; i < DSAF_TOTAL_QUEUE_NUM; i++) + p[41 + i] = dsaf_read_dev(ddev, + DSAF_VM_DEF_VLAN_0_REG + i * 4); + + /* dsaf inode registers */ + p[170] = dsaf_read_dev(ddev, DSAF_INODE_CUT_THROUGH_CFG_0_REG); + + p[171] = dsaf_read_dev(ddev, + DSAF_INODE_ECC_ERR_ADDR_0_REG + port * 0x80); + + for (i = 0; i < DSAF_INODE_NUM / DSAF_COMM_CHN; i++) { + j = i * DSAF_COMM_CHN + port; + p[172 + i] = dsaf_read_dev(ddev, + DSAF_INODE_IN_PORT_NUM_0_REG + j * 0x80); + p[175 + i] = dsaf_read_dev(ddev, + DSAF_INODE_PRI_TC_CFG_0_REG + j * 0x80); + p[178 + i] = dsaf_read_dev(ddev, + DSAF_INODE_BP_STATUS_0_REG + j * 0x80); + p[181 + i] = dsaf_read_dev(ddev, + DSAF_INODE_PAD_DISCARD_NUM_0_REG + j * 0x80); + p[184 + i] = dsaf_read_dev(ddev, + DSAF_INODE_FINAL_IN_MAN_NUM_0_REG + j * 0x80); + p[187 + i] = dsaf_read_dev(ddev, + DSAF_INODE_FINAL_IN_PKT_NUM_0_REG + j * 0x80); + p[190 + i] = dsaf_read_dev(ddev, + DSAF_INODE_SBM_PID_NUM_0_REG + j * 0x80); + p[193 + i] = dsaf_read_dev(ddev, + DSAF_INODE_FINAL_IN_PAUSE_NUM_0_REG + j * 0x80); + p[196 + i] = dsaf_read_dev(ddev, + DSAF_INODE_SBM_RELS_NUM_0_REG + j * 0x80); + p[199 + i] = dsaf_read_dev(ddev, + DSAF_INODE_SBM_DROP_NUM_0_REG + j * 0x80); + p[202 + i] = dsaf_read_dev(ddev, + DSAF_INODE_CRC_FALSE_NUM_0_REG + j * 0x80); + p[205 + i] = dsaf_read_dev(ddev, + DSAF_INODE_BP_DISCARD_NUM_0_REG + j * 0x80); + p[208 + i] = dsaf_read_dev(ddev, + DSAF_INODE_RSLT_DISCARD_NUM_0_REG + j * 0x80); + p[211 + i] = dsaf_read_dev(ddev, + DSAF_INODE_LOCAL_ADDR_FALSE_NUM_0_REG + j * 0x80); + p[214 + i] = dsaf_read_dev(ddev, + DSAF_INODE_VOQ_OVER_NUM_0_REG + j * 0x80); + p[217 + i] = dsaf_read_dev(ddev, + DSAF_INODE_BD_SAVE_STATUS_0_REG + j * 4); + p[220 + i] = dsaf_read_dev(ddev, + DSAF_INODE_BD_ORDER_STATUS_0_REG + j * 4); + p[223 + i] = dsaf_read_dev(ddev, + DSAF_INODE_SW_VLAN_TAG_DISC_0_REG + j * 4); + p[224 + i] = dsaf_read_dev(ddev, + DSAF_INODE_IN_DATA_STP_DISC_0_REG + j * 4); + } + + p[227] = dsaf_read_dev(ddev, DSAF_INODE_GE_FC_EN_0_REG + port * 4); + + for (i = 0; i < DSAF_INODE_NUM / DSAF_COMM_CHN; i++) { + j = i * DSAF_COMM_CHN + port; + p[228 + i] = dsaf_read_dev(ddev, + DSAF_INODE_VC0_IN_PKT_NUM_0_REG + j * 4); + } + + p[231] = dsaf_read_dev(ddev, + DSAF_INODE_VC1_IN_PKT_NUM_0_REG + port * 4); + + /* dsaf inode registers */ + for (i = 0; i < DSAF_SBM_NUM / DSAF_COMM_CHN; i++) { + j = i * DSAF_COMM_CHN + port; + p[232 + i] = dsaf_read_dev(ddev, + DSAF_SBM_CFG_REG_0_REG + j * 0x80); + p[235 + i] = dsaf_read_dev(ddev, + DSAF_SBM_BP_CFG_0_XGE_REG_0_REG + j * 0x80); + p[238 + i] = dsaf_read_dev(ddev, + DSAF_SBM_BP_CFG_1_REG_0_REG + j * 0x80); + p[241 + i] = dsaf_read_dev(ddev, + DSAF_SBM_BP_CFG_2_XGE_REG_0_REG + j * 0x80); + p[244 + i] = dsaf_read_dev(ddev, + DSAF_SBM_FREE_CNT_0_0_REG + j * 0x80); + p[245 + i] = dsaf_read_dev(ddev, + DSAF_SBM_FREE_CNT_1_0_REG + j * 0x80); + p[248 + i] = dsaf_read_dev(ddev, + DSAF_SBM_BP_CNT_0_0_REG + j * 0x80); + p[251 + i] = dsaf_read_dev(ddev, + DSAF_SBM_BP_CNT_1_0_REG + j * 0x80); + p[254 + i] = dsaf_read_dev(ddev, + DSAF_SBM_BP_CNT_2_0_REG + j * 0x80); + p[257 + i] = dsaf_read_dev(ddev, + DSAF_SBM_BP_CNT_3_0_REG + j * 0x80); + p[260 + i] = dsaf_read_dev(ddev, + DSAF_SBM_INER_ST_0_REG + j * 0x80); + p[263 + i] = dsaf_read_dev(ddev, + DSAF_SBM_MIB_REQ_FAILED_TC_0_REG + j * 0x80); + p[266 + i] = dsaf_read_dev(ddev, + DSAF_SBM_LNK_INPORT_CNT_0_REG + j * 0x80); + p[269 + i] = dsaf_read_dev(ddev, + DSAF_SBM_LNK_DROP_CNT_0_REG + j * 0x80); + p[272 + i] = dsaf_read_dev(ddev, + DSAF_SBM_INF_OUTPORT_CNT_0_REG + j * 0x80); + p[275 + i] = dsaf_read_dev(ddev, + DSAF_SBM_LNK_INPORT_TC0_CNT_0_REG + j * 0x80); + p[278 + i] = dsaf_read_dev(ddev, + DSAF_SBM_LNK_INPORT_TC1_CNT_0_REG + j * 0x80); + p[281 + i] = dsaf_read_dev(ddev, + DSAF_SBM_LNK_INPORT_TC2_CNT_0_REG + j * 0x80); + p[284 + i] = dsaf_read_dev(ddev, + DSAF_SBM_LNK_INPORT_TC3_CNT_0_REG + j * 0x80); + p[287 + i] = dsaf_read_dev(ddev, + DSAF_SBM_LNK_INPORT_TC4_CNT_0_REG + j * 0x80); + p[290 + i] = dsaf_read_dev(ddev, + DSAF_SBM_LNK_INPORT_TC5_CNT_0_REG + j * 0x80); + p[293 + i] = dsaf_read_dev(ddev, + DSAF_SBM_LNK_INPORT_TC6_CNT_0_REG + j * 0x80); + p[296 + i] = dsaf_read_dev(ddev, + DSAF_SBM_LNK_INPORT_TC7_CNT_0_REG + j * 0x80); + p[299 + i] = dsaf_read_dev(ddev, + DSAF_SBM_LNK_REQ_CNT_0_REG + j * 0x80); + p[302 + i] = dsaf_read_dev(ddev, + DSAF_SBM_LNK_RELS_CNT_0_REG + j * 0x80); + p[305 + i] = dsaf_read_dev(ddev, + DSAF_SBM_BP_CFG_3_REG_0_REG + j * 0x80); + p[308 + i] = dsaf_read_dev(ddev, + DSAF_SBM_BP_CFG_4_REG_0_REG + j * 0x80); + } + + /* dsaf onode registers */ + for (i = 0; i < DSAF_XOD_NUM; i++) { + p[311 + i] = dsaf_read_dev(ddev, + DSAF_XOD_ETS_TSA_TC0_TC3_CFG_0_REG + j * 0x90); + p[319 + i] = dsaf_read_dev(ddev, + DSAF_XOD_ETS_TSA_TC4_TC7_CFG_0_REG + j * 0x90); + p[327 + i] = dsaf_read_dev(ddev, + DSAF_XOD_ETS_BW_TC0_TC3_CFG_0_REG + j * 0x90); + p[335 + i] = dsaf_read_dev(ddev, + DSAF_XOD_ETS_BW_TC4_TC7_CFG_0_REG + j * 0x90); + p[343 + i] = dsaf_read_dev(ddev, + DSAF_XOD_ETS_BW_OFFSET_CFG_0_REG + j * 0x90); + p[351 + i] = dsaf_read_dev(ddev, + DSAF_XOD_ETS_TOKEN_CFG_0_REG + j * 0x90); + } + + p[359] = dsaf_read_dev(ddev, DSAF_XOD_PFS_CFG_0_0_REG + port * 0x90); + p[360] = dsaf_read_dev(ddev, DSAF_XOD_PFS_CFG_1_0_REG + port * 0x90); + p[361] = dsaf_read_dev(ddev, DSAF_XOD_PFS_CFG_2_0_REG + port * 0x90); + + for (i = 0; i < DSAF_XOD_BIG_NUM / DSAF_COMM_CHN; i++) { + j = i * DSAF_COMM_CHN + port; + p[362 + i] = dsaf_read_dev(ddev, + DSAF_XOD_GNT_L_0_REG + j * 0x90); + p[365 + i] = dsaf_read_dev(ddev, + DSAF_XOD_GNT_H_0_REG + j * 0x90); + p[368 + i] = dsaf_read_dev(ddev, + DSAF_XOD_CONNECT_STATE_0_REG + j * 0x90); + p[371 + i] = dsaf_read_dev(ddev, + DSAF_XOD_RCVPKT_CNT_0_REG + j * 0x90); + p[374 + i] = dsaf_read_dev(ddev, + DSAF_XOD_RCVTC0_CNT_0_REG + j * 0x90); + p[377 + i] = dsaf_read_dev(ddev, + DSAF_XOD_RCVTC1_CNT_0_REG + j * 0x90); + p[380 + i] = dsaf_read_dev(ddev, + DSAF_XOD_RCVTC2_CNT_0_REG + j * 0x90); + p[383 + i] = dsaf_read_dev(ddev, + DSAF_XOD_RCVTC3_CNT_0_REG + j * 0x90); + p[386 + i] = dsaf_read_dev(ddev, + DSAF_XOD_RCVVC0_CNT_0_REG + j * 0x90); + p[389 + i] = dsaf_read_dev(ddev, + DSAF_XOD_RCVVC1_CNT_0_REG + j * 0x90); + } + + p[392] = dsaf_read_dev(ddev, + DSAF_XOD_XGE_RCVIN0_CNT_0_REG + port * 0x90); + p[393] = dsaf_read_dev(ddev, + DSAF_XOD_XGE_RCVIN1_CNT_0_REG + port * 0x90); + p[394] = dsaf_read_dev(ddev, + DSAF_XOD_XGE_RCVIN2_CNT_0_REG + port * 0x90); + p[395] = dsaf_read_dev(ddev, + DSAF_XOD_XGE_RCVIN3_CNT_0_REG + port * 0x90); + p[396] = dsaf_read_dev(ddev, + DSAF_XOD_XGE_RCVIN4_CNT_0_REG + port * 0x90); + p[397] = dsaf_read_dev(ddev, + DSAF_XOD_XGE_RCVIN5_CNT_0_REG + port * 0x90); + p[398] = dsaf_read_dev(ddev, + DSAF_XOD_XGE_RCVIN6_CNT_0_REG + port * 0x90); + p[399] = dsaf_read_dev(ddev, + DSAF_XOD_XGE_RCVIN7_CNT_0_REG + port * 0x90); + p[400] = dsaf_read_dev(ddev, + DSAF_XOD_PPE_RCVIN0_CNT_0_REG + port * 0x90); + p[401] = dsaf_read_dev(ddev, + DSAF_XOD_PPE_RCVIN1_CNT_0_REG + port * 0x90); + p[402] = dsaf_read_dev(ddev, + DSAF_XOD_ROCEE_RCVIN0_CNT_0_REG + port * 0x90); + p[403] = dsaf_read_dev(ddev, + DSAF_XOD_ROCEE_RCVIN1_CNT_0_REG + port * 0x90); + p[404] = dsaf_read_dev(ddev, + DSAF_XOD_FIFO_STATUS_0_REG + port * 0x90); + + /* dsaf voq registers */ + for (i = 0; i < DSAF_VOQ_NUM / DSAF_COMM_CHN; i++) { + j = (i * DSAF_COMM_CHN + port) * 0x90; + p[405 + i] = dsaf_read_dev(ddev, + DSAF_VOQ_ECC_INVERT_EN_0_REG + j); + p[408 + i] = dsaf_read_dev(ddev, + DSAF_VOQ_SRAM_PKT_NUM_0_REG + j); + p[411 + i] = dsaf_read_dev(ddev, DSAF_VOQ_IN_PKT_NUM_0_REG + j); + p[414 + i] = dsaf_read_dev(ddev, + DSAF_VOQ_OUT_PKT_NUM_0_REG + j); + p[417 + i] = dsaf_read_dev(ddev, + DSAF_VOQ_ECC_ERR_ADDR_0_REG + j); + p[420 + i] = dsaf_read_dev(ddev, DSAF_VOQ_BP_STATUS_0_REG + j); + p[423 + i] = dsaf_read_dev(ddev, DSAF_VOQ_SPUP_IDLE_0_REG + j); + p[426 + i] = dsaf_read_dev(ddev, + DSAF_VOQ_XGE_XOD_REQ_0_0_REG + j); + p[429 + i] = dsaf_read_dev(ddev, + DSAF_VOQ_XGE_XOD_REQ_1_0_REG + j); + p[432 + i] = dsaf_read_dev(ddev, + DSAF_VOQ_PPE_XOD_REQ_0_REG + j); + p[435 + i] = dsaf_read_dev(ddev, + DSAF_VOQ_ROCEE_XOD_REQ_0_REG + j); + p[438 + i] = dsaf_read_dev(ddev, + DSAF_VOQ_BP_ALL_THRD_0_REG + j); + } + + /* dsaf tbl registers */ + p[441] = dsaf_read_dev(ddev, DSAF_TBL_CTRL_0_REG); + p[442] = dsaf_read_dev(ddev, DSAF_TBL_INT_MSK_0_REG); + p[443] = dsaf_read_dev(ddev, DSAF_TBL_INT_SRC_0_REG); + p[444] = dsaf_read_dev(ddev, DSAF_TBL_INT_STS_0_REG); + p[445] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_ADDR_0_REG); + p[446] = dsaf_read_dev(ddev, DSAF_TBL_LINE_ADDR_0_REG); + p[447] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_HIGH_0_REG); + p[448] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_LOW_0_REG); + p[449] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_MCAST_CFG_4_0_REG); + p[450] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_MCAST_CFG_3_0_REG); + p[451] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_MCAST_CFG_2_0_REG); + p[452] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_MCAST_CFG_1_0_REG); + p[453] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_MCAST_CFG_0_0_REG); + p[454] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_UCAST_CFG_0_REG); + p[455] = dsaf_read_dev(ddev, DSAF_TBL_LIN_CFG_0_REG); + p[456] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_RDATA_HIGH_0_REG); + p[457] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_RDATA_LOW_0_REG); + p[458] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_RAM_RDATA4_0_REG); + p[459] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_RAM_RDATA3_0_REG); + p[460] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_RAM_RDATA2_0_REG); + p[461] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_RAM_RDATA1_0_REG); + p[462] = dsaf_read_dev(ddev, DSAF_TBL_TCAM_RAM_RDATA0_0_REG); + p[463] = dsaf_read_dev(ddev, DSAF_TBL_LIN_RDATA_0_REG); + + for (i = 0; i < DSAF_SW_PORT_NUM; i++) { + j = i * 0x8; + p[464 + 2 * i] = dsaf_read_dev(ddev, + DSAF_TBL_DA0_MIS_INFO1_0_REG + j); + p[465 + 2 * i] = dsaf_read_dev(ddev, + DSAF_TBL_DA0_MIS_INFO0_0_REG + j); + } + + p[480] = dsaf_read_dev(ddev, DSAF_TBL_SA_MIS_INFO2_0_REG); + p[481] = dsaf_read_dev(ddev, DSAF_TBL_SA_MIS_INFO1_0_REG); + p[482] = dsaf_read_dev(ddev, DSAF_TBL_SA_MIS_INFO0_0_REG); + p[483] = dsaf_read_dev(ddev, DSAF_TBL_PUL_0_REG); + p[484] = dsaf_read_dev(ddev, DSAF_TBL_OLD_RSLT_0_REG); + p[485] = dsaf_read_dev(ddev, DSAF_TBL_OLD_SCAN_VAL_0_REG); + p[486] = dsaf_read_dev(ddev, DSAF_TBL_DFX_CTRL_0_REG); + p[487] = dsaf_read_dev(ddev, DSAF_TBL_DFX_STAT_0_REG); + p[488] = dsaf_read_dev(ddev, DSAF_TBL_DFX_STAT_2_0_REG); + p[489] = dsaf_read_dev(ddev, DSAF_TBL_LKUP_NUM_I_0_REG); + p[490] = dsaf_read_dev(ddev, DSAF_TBL_LKUP_NUM_O_0_REG); + p[491] = dsaf_read_dev(ddev, DSAF_TBL_UCAST_BCAST_MIS_INFO_0_0_REG); + + /* dsaf other registers */ + p[492] = dsaf_read_dev(ddev, DSAF_INODE_FIFO_WL_0_REG + port * 0x4); + p[493] = dsaf_read_dev(ddev, DSAF_ONODE_FIFO_WL_0_REG + port * 0x4); + p[494] = dsaf_read_dev(ddev, DSAF_XGE_GE_WORK_MODE_0_REG + port * 0x4); + p[495] = dsaf_read_dev(ddev, + DSAF_XGE_APP_RX_LINK_UP_0_REG + port * 0x4); + p[496] = dsaf_read_dev(ddev, DSAF_NETPORT_CTRL_SIG_0_REG + port * 0x4); + p[497] = dsaf_read_dev(ddev, DSAF_XGE_CTRL_SIG_CFG_0_REG + port * 0x4); + + /* mark end of dsaf regs */ + for (i = 498; i < 504; i++) + p[i] = 0xdddddddd; +} + +static char *hns_dsaf_get_node_stats_strings(char *data, int node) +{ + char *buff = data; + + snprintf(buff, ETH_GSTRING_LEN, "innod%d_pad_drop_pkts", node); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "innod%d_manage_pkts", node); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "innod%d_rx_pkts", node); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "innod%d_rx_pkt_id", node); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "innod%d_rx_pause_frame", node); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "innod%d_release_buf_num", node); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "innod%d_sbm_drop_pkts", node); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "innod%d_crc_false_pkts", node); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "innod%d_bp_drop_pkts", node); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "innod%d_lookup_rslt_drop_pkts", node); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "innod%d_local_rslt_fail_pkts", node); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "innod%d_vlan_drop_pkts", node); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "innod%d_stp_drop_pkts", node); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "onnod%d_tx_pkts", node); + buff = buff + ETH_GSTRING_LEN; + + return buff; +} + +static u64 *hns_dsaf_get_node_stats(struct dsaf_device *ddev, u64 *data, + int node_num) +{ + u64 *p = data; + struct dsaf_hw_stats *hw_stats = &ddev->hw_stats[node_num]; + + p[0] = hw_stats->pad_drop; + p[1] = hw_stats->man_pkts; + p[2] = hw_stats->rx_pkts; + p[3] = hw_stats->rx_pkt_id; + p[4] = hw_stats->rx_pause_frame; + p[5] = hw_stats->release_buf_num; + p[6] = hw_stats->sbm_drop; + p[7] = hw_stats->crc_false; + p[8] = hw_stats->bp_drop; + p[9] = hw_stats->rslt_drop; + p[10] = hw_stats->local_addr_false; + p[11] = hw_stats->vlan_drop; + p[12] = hw_stats->stp_drop; + p[13] = hw_stats->tx_pkts; + + return &p[14]; +} + +/** + *hns_dsaf_get_stats - get dsaf statistic + *@ddev: dsaf device + *@data:statistic value + *@port: port num + */ +void hns_dsaf_get_stats(struct dsaf_device *ddev, u64 *data, int port) +{ + u64 *p = data; + int node_num = port; + + /* for ge/xge node info */ + p = hns_dsaf_get_node_stats(ddev, p, node_num); + + /* for ppe node info */ + node_num = port + DSAF_PPE_INODE_BASE; + (void)hns_dsaf_get_node_stats(ddev, p, node_num); +} + +/** + *hns_dsaf_get_sset_count - get dsaf string set count + *@stringset: type of values in data + *return dsaf string name count + */ +int hns_dsaf_get_sset_count(int stringset) +{ + if (stringset == ETH_SS_STATS) + return DSAF_STATIC_NUM; + + return 0; +} + +/** + *hns_dsaf_get_strings - get dsaf string set + *@stringset:srting set index + *@data:strings name value + *@port:port index + */ +void hns_dsaf_get_strings(int stringset, u8 *data, int port) +{ + char *buff = (char *)data; + int node = port; + + if (stringset != ETH_SS_STATS) + return; + + /* for ge/xge node info */ + buff = hns_dsaf_get_node_stats_strings(buff, node); + + /* for ppe node info */ + node = port + DSAF_PPE_INODE_BASE; + (void)hns_dsaf_get_node_stats_strings(buff, node); +} + +/** + *hns_dsaf_get_sset_count - get dsaf regs count + *return dsaf regs count + */ +int hns_dsaf_get_regs_count(void) +{ + return DSAF_DUMP_REGS_NUM; +} + +/** + * dsaf_probe - probo dsaf dev + * @pdev: dasf platform device + * retuen 0 - success , negative --fail + */ +static int hns_dsaf_probe(struct platform_device *pdev) +{ + struct dsaf_device *dsaf_dev; + int ret; + + dsaf_dev = hns_dsaf_alloc_dev(&pdev->dev, sizeof(struct dsaf_drv_priv)); + if (IS_ERR(dsaf_dev)) { + ret = PTR_ERR(dsaf_dev); + dev_err(&pdev->dev, + "dsaf_probe dsaf_alloc_dev failed, ret = %#x!\n", ret); + return ret; + } + + ret = hns_dsaf_get_cfg(dsaf_dev); + if (ret) + goto free_dev; + + ret = hns_dsaf_init(dsaf_dev); + if (ret) + goto free_cfg; + + ret = hns_mac_init(dsaf_dev); + if (ret) + goto uninit_dsaf; + + ret = hns_ppe_init(dsaf_dev); + if (ret) + goto uninit_mac; + + ret = hns_dsaf_ae_init(dsaf_dev); + if (ret) + goto uninit_ppe; + + return 0; + +uninit_ppe: + hns_ppe_uninit(dsaf_dev); + +uninit_mac: + hns_mac_uninit(dsaf_dev); + +uninit_dsaf: + hns_dsaf_free(dsaf_dev); + +free_cfg: + hns_dsaf_free_cfg(dsaf_dev); + +free_dev: + hns_dsaf_free_dev(dsaf_dev); + + return ret; +} + +/** + * dsaf_remove - remove dsaf dev + * @pdev: dasf platform device + */ +static int hns_dsaf_remove(struct platform_device *pdev) +{ + struct dsaf_device *dsaf_dev = dev_get_drvdata(&pdev->dev); + + hns_dsaf_ae_uninit(dsaf_dev); + + hns_ppe_uninit(dsaf_dev); + + hns_mac_uninit(dsaf_dev); + + hns_dsaf_free(dsaf_dev); + + hns_dsaf_free_cfg(dsaf_dev); + + hns_dsaf_free_dev(dsaf_dev); + + return 0; +} + +static const struct of_device_id g_dsaf_match[] = { + {.compatible = "hisilicon,hns-dsaf-v1"}, + {.compatible = "hisilicon,hns-dsaf-v2"}, + {} +}; + +static struct platform_driver g_dsaf_driver = { + .probe = hns_dsaf_probe, + .remove = hns_dsaf_remove, + .driver = { + .name = DSAF_DRV_NAME, + .of_match_table = g_dsaf_match, + }, +}; + +module_platform_driver(g_dsaf_driver); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Huawei Tech. Co., Ltd."); +MODULE_DESCRIPTION("HNS DSAF driver"); +MODULE_VERSION(DSAF_MOD_VERSION); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h new file mode 100644 index 000000000000..315b07ecd291 --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h @@ -0,0 +1,427 @@ +/* + * Copyright (c) 2014-2015 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef __HNS_DSAF_MAIN_H +#define __HNS_DSAF_MAIN_H +#include "hnae.h" + +#include "hns_dsaf_reg.h" +#include "hns_dsaf_mac.h" + +struct hns_mac_cb; + +#define DSAF_DRV_NAME "hns_dsaf" +#define DSAF_MOD_VERSION "v1.0" + +#define ENABLE (0x1) +#define DISABLE (0x0) + +#define HNS_DSAF_DEBUG_NW_REG_OFFSET (0x100000) + +#define DSAF_BASE_INNER_PORT_NUM (127) /* mac tbl qid*/ + +#define DSAF_MAX_CHIP_NUM (2) /*max 2 chips */ + +#define DSAF_DEFAUTL_QUEUE_NUM_PER_PPE (22) + +#define HNS_DSAF_MAX_DESC_CNT (1024) +#define HNS_DSAF_MIN_DESC_CNT (16) + +#define DSAF_INVALID_ENTRY_IDX (0xffff) + +#define DSAF_CFG_READ_CNT (30) +#define DSAF_SRAM_INIT_FINISH_FLAG (0xff) + +#define MAC_NUM_OCTETS_PER_ADDR 6 + +#define DSAF_DUMP_REGS_NUM 504 +#define DSAF_STATIC_NUM 28 + +#define DSAF_STATS_READ(p, offset) (*((u64 *)((u8 *)(p) + (offset)))) + +enum hal_dsaf_mode { + HRD_DSAF_NO_DSAF_MODE = 0x0, + HRD_DSAF_MODE = 0x1, +}; + +enum hal_dsaf_tc_mode { + HRD_DSAF_4TC_MODE = 0X0, + HRD_DSAF_8TC_MODE = 0X1, +}; + +struct dsaf_vm_def_vlan { + u32 vm_def_vlan_id; + u32 vm_def_vlan_cfi; + u32 vm_def_vlan_pri; +}; + +struct dsaf_tbl_tcam_data { + u32 tbl_tcam_data_high; + u32 tbl_tcam_data_low; +}; + +#define DSAF_PORT_MSK_NUM \ + ((DSAF_TOTAL_QUEUE_NUM + DSAF_SERVICE_NW_NUM - 1) / 32 + 1) +struct dsaf_tbl_tcam_mcast_cfg { + u8 tbl_mcast_old_en; + u8 tbl_mcast_item_vld; + u32 tbl_mcast_port_msk[DSAF_PORT_MSK_NUM]; +}; + +struct dsaf_tbl_tcam_ucast_cfg { + u32 tbl_ucast_old_en; + u32 tbl_ucast_item_vld; + u32 tbl_ucast_mac_discard; + u32 tbl_ucast_dvc; + u32 tbl_ucast_out_port; +}; + +struct dsaf_tbl_line_cfg { + u32 tbl_line_mac_discard; + u32 tbl_line_dvc; + u32 tbl_line_out_port; +}; + +enum dsaf_port_rate_mode { + DSAF_PORT_RATE_1000 = 0, + DSAF_PORT_RATE_2500, + DSAF_PORT_RATE_10000 +}; + +enum dsaf_stp_port_type { + DSAF_STP_PORT_TYPE_DISCARD = 0, + DSAF_STP_PORT_TYPE_BLOCK = 1, + DSAF_STP_PORT_TYPE_LISTEN = 2, + DSAF_STP_PORT_TYPE_LEARN = 3, + DSAF_STP_PORT_TYPE_FORWARD = 4 +}; + +enum dsaf_sw_port_type { + DSAF_SW_PORT_TYPE_NON_VLAN = 0, + DSAF_SW_PORT_TYPE_ACCESS = 1, + DSAF_SW_PORT_TYPE_TRUNK = 2, +}; + +#define DSAF_SUB_BASE_SIZE (0x10000) + +/* dsaf mode define */ +enum dsaf_mode { + DSAF_MODE_INVALID = 0, /**< Invalid dsaf mode */ + DSAF_MODE_ENABLE_FIX, /**< en DSAF-mode, fixed to queue*/ + DSAF_MODE_ENABLE_0VM, /**< en DSAF-mode, support 0 VM */ + DSAF_MODE_ENABLE_8VM, /**< en DSAF-mode, support 8 VM */ + DSAF_MODE_ENABLE_16VM, /**< en DSAF-mode, support 16 VM */ + DSAF_MODE_ENABLE_32VM, /**< en DSAF-mode, support 32 VM */ + DSAF_MODE_ENABLE_128VM, /**< en DSAF-mode, support 128 VM */ + DSAF_MODE_ENABLE, /**< before is enable DSAF mode*/ + DSAF_MODE_DISABLE_FIX, /**< non-dasf, fixed to queue*/ + DSAF_MODE_DISABLE_2PORT_8VM, /**< non-dasf, 2port 8VM */ + DSAF_MODE_DISABLE_2PORT_16VM, /**< non-dasf, 2port 16VM */ + DSAF_MODE_DISABLE_2PORT_64VM, /**< non-dasf, 2port 64VM */ + DSAF_MODE_DISABLE_6PORT_0VM, /**< non-dasf, 6port 0VM */ + DSAF_MODE_DISABLE_6PORT_2VM, /**< non-dasf, 6port 2VM */ + DSAF_MODE_DISABLE_6PORT_4VM, /**< non-dasf, 6port 4VM */ + DSAF_MODE_DISABLE_6PORT_16VM, /**< non-dasf, 6port 16VM */ + DSAF_MODE_MAX /**< the last one, use as the num */ +}; + +#define DSAF_DEST_PORT_NUM 256 /* DSAF max port num */ +#define DSAF_WORD_BIT_CNT 32 /* the num bit of word */ + +/*mac entry, mc or uc entry*/ +struct dsaf_drv_mac_single_dest_entry { + /* mac addr, match the entry*/ + u8 addr[MAC_NUM_OCTETS_PER_ADDR]; + u16 in_vlan_id; /* value of VlanId */ + + /* the vld input port num, dsaf-mode fix 0, */ + /* non-dasf is the entry whitch port vld*/ + u8 in_port_num; + + u8 port_num; /*output port num*/ + u8 rsv[6]; +}; + +/*only mc entry*/ +struct dsaf_drv_mac_multi_dest_entry { + /* mac addr, match the entry*/ + u8 addr[MAC_NUM_OCTETS_PER_ADDR]; + u16 in_vlan_id; + /* this mac addr output port,*/ + /* bit0-bit5 means Port0-Port5(1bit is vld)**/ + u32 port_mask[DSAF_DEST_PORT_NUM / DSAF_WORD_BIT_CNT]; + + /* the vld input port num, dsaf-mode fix 0,*/ + /* non-dasf is the entry whitch port vld*/ + u8 in_port_num; + u8 rsv[7]; +}; + +struct dsaf_hw_stats { + u64 pad_drop; + u64 man_pkts; + u64 rx_pkts; + u64 rx_pkt_id; + u64 rx_pause_frame; + u64 release_buf_num; + u64 sbm_drop; + u64 crc_false; + u64 bp_drop; + u64 rslt_drop; + u64 local_addr_false; + u64 vlan_drop; + u64 stp_drop; + u64 tx_pkts; +}; + +struct hnae_vf_cb { + u8 port_index; + struct hns_mac_cb *mac_cb; + struct dsaf_device *dsaf_dev; + struct hnae_handle ae_handle; /* must be the last number */ +}; + +struct dsaf_int_xge_src { + u32 xid_xge_ecc_err_int_src; + u32 xid_xge_fsm_timout_int_src; + u32 sbm_xge_lnk_fsm_timout_int_src; + u32 sbm_xge_lnk_ecc_2bit_int_src; + u32 sbm_xge_mib_req_failed_int_src; + u32 sbm_xge_mib_req_fsm_timout_int_src; + u32 sbm_xge_mib_rels_fsm_timout_int_src; + u32 sbm_xge_sram_ecc_2bit_int_src; + u32 sbm_xge_mib_buf_sum_err_int_src; + u32 sbm_xge_mib_req_extra_int_src; + u32 sbm_xge_mib_rels_extra_int_src; + u32 voq_xge_start_to_over_0_int_src; + u32 voq_xge_start_to_over_1_int_src; + u32 voq_xge_ecc_err_int_src; +}; + +struct dsaf_int_ppe_src { + u32 xid_ppe_fsm_timout_int_src; + u32 sbm_ppe_lnk_fsm_timout_int_src; + u32 sbm_ppe_lnk_ecc_2bit_int_src; + u32 sbm_ppe_mib_req_failed_int_src; + u32 sbm_ppe_mib_req_fsm_timout_int_src; + u32 sbm_ppe_mib_rels_fsm_timout_int_src; + u32 sbm_ppe_sram_ecc_2bit_int_src; + u32 sbm_ppe_mib_buf_sum_err_int_src; + u32 sbm_ppe_mib_req_extra_int_src; + u32 sbm_ppe_mib_rels_extra_int_src; + u32 voq_ppe_start_to_over_0_int_src; + u32 voq_ppe_ecc_err_int_src; + u32 xod_ppe_fifo_rd_empty_int_src; + u32 xod_ppe_fifo_wr_full_int_src; +}; + +struct dsaf_int_rocee_src { + u32 xid_rocee_fsm_timout_int_src; + u32 sbm_rocee_lnk_fsm_timout_int_src; + u32 sbm_rocee_lnk_ecc_2bit_int_src; + u32 sbm_rocee_mib_req_failed_int_src; + u32 sbm_rocee_mib_req_fsm_timout_int_src; + u32 sbm_rocee_mib_rels_fsm_timout_int_src; + u32 sbm_rocee_sram_ecc_2bit_int_src; + u32 sbm_rocee_mib_buf_sum_err_int_src; + u32 sbm_rocee_mib_req_extra_int_src; + u32 sbm_rocee_mib_rels_extra_int_src; + u32 voq_rocee_start_to_over_0_int_src; + u32 voq_rocee_ecc_err_int_src; +}; + +struct dsaf_int_tbl_src { + u32 tbl_da0_mis_src; + u32 tbl_da1_mis_src; + u32 tbl_da2_mis_src; + u32 tbl_da3_mis_src; + u32 tbl_da4_mis_src; + u32 tbl_da5_mis_src; + u32 tbl_da6_mis_src; + u32 tbl_da7_mis_src; + u32 tbl_sa_mis_src; + u32 tbl_old_sech_end_src; + u32 lram_ecc_err1_src; + u32 lram_ecc_err2_src; + u32 tram_ecc_err1_src; + u32 tram_ecc_err2_src; + u32 tbl_ucast_bcast_xge0_src; + u32 tbl_ucast_bcast_xge1_src; + u32 tbl_ucast_bcast_xge2_src; + u32 tbl_ucast_bcast_xge3_src; + u32 tbl_ucast_bcast_xge4_src; + u32 tbl_ucast_bcast_xge5_src; + u32 tbl_ucast_bcast_ppe_src; + u32 tbl_ucast_bcast_rocee_src; +}; + +struct dsaf_int_stat { + struct dsaf_int_xge_src dsaf_int_xge_stat[DSAF_COMM_CHN]; + struct dsaf_int_ppe_src dsaf_int_ppe_stat[DSAF_COMM_CHN]; + struct dsaf_int_rocee_src dsaf_int_rocee_stat[DSAF_COMM_CHN]; + struct dsaf_int_tbl_src dsaf_int_tbl_stat[1]; + +}; + +/* Dsaf device struct define ,and mac -> dsaf */ +struct dsaf_device { + struct device *dev; + struct hnae_ae_dev ae_dev; + + void *priv; + + int virq[DSAF_IRQ_NUM]; + + u8 __iomem *sc_base; + u8 __iomem *sds_base; + u8 __iomem *ppe_base; + u8 __iomem *io_base; + u8 __iomem *cpld_base; + + u32 desc_num; /* desc num per queue*/ + u32 buf_size; /* ring buffer size */ + int buf_size_type; /* ring buffer size-type */ + enum dsaf_mode dsaf_mode; /* dsaf mode */ + enum hal_dsaf_mode dsaf_en; + enum hal_dsaf_tc_mode dsaf_tc_mode; + u32 dsaf_ver; + + struct ppe_common_cb *ppe_common[DSAF_COMM_DEV_NUM]; + struct rcb_common_cb *rcb_common[DSAF_COMM_DEV_NUM]; + struct hns_mac_cb *mac_cb; + + struct dsaf_hw_stats hw_stats[DSAF_NODE_NUM]; + struct dsaf_int_stat int_stat; +}; + +static inline void *hns_dsaf_dev_priv(const struct dsaf_device *dsaf_dev) +{ + return (void *)((u8 *)dsaf_dev + sizeof(*dsaf_dev)); +} + +struct dsaf_drv_tbl_tcam_key { + union { + struct { + u8 mac_3; + u8 mac_2; + u8 mac_1; + u8 mac_0; + } bits; + + u32 val; + } high; + union { + struct { + u32 port:4; /* port id, */ + /* dsaf-mode fixed 0, non-dsaf-mode port id*/ + u32 vlan:12; /* vlan id */ + u32 mac_5:8; + u32 mac_4:8; + } bits; + + u32 val; + } low; +}; + +struct dsaf_drv_soft_mac_tbl { + struct dsaf_drv_tbl_tcam_key tcam_key; + u16 index; /*the entry's index in tcam tab*/ +}; + +struct dsaf_drv_priv { + /* soft tab Mac key, for hardware tab*/ + struct dsaf_drv_soft_mac_tbl *soft_mac_tbl; +}; + +static inline void hns_dsaf_tbl_tcam_addr_cfg(struct dsaf_device *dsaf_dev, + u32 tab_tcam_addr) +{ + dsaf_set_dev_field(dsaf_dev, DSAF_TBL_TCAM_ADDR_0_REG, + DSAF_TBL_TCAM_ADDR_M, DSAF_TBL_TCAM_ADDR_S, + tab_tcam_addr); +} + +static inline void hns_dsaf_tbl_tcam_load_pul(struct dsaf_device *dsaf_dev) +{ + u32 o_tbl_pul; + + o_tbl_pul = dsaf_read_dev(dsaf_dev, DSAF_TBL_PUL_0_REG); + dsaf_set_bit(o_tbl_pul, DSAF_TBL_PUL_TCAM_LOAD_S, 1); + dsaf_write_dev(dsaf_dev, DSAF_TBL_PUL_0_REG, o_tbl_pul); + dsaf_set_bit(o_tbl_pul, DSAF_TBL_PUL_TCAM_LOAD_S, 0); + dsaf_write_dev(dsaf_dev, DSAF_TBL_PUL_0_REG, o_tbl_pul); +} + +static inline void hns_dsaf_tbl_line_addr_cfg(struct dsaf_device *dsaf_dev, + u32 tab_line_addr) +{ + dsaf_set_dev_field(dsaf_dev, DSAF_TBL_LINE_ADDR_0_REG, + DSAF_TBL_LINE_ADDR_M, DSAF_TBL_LINE_ADDR_S, + tab_line_addr); +} + +static inline int hns_dsaf_get_comm_idx_by_port(int port) +{ + if ((port < DSAF_COMM_CHN) || (port == DSAF_MAX_PORT_NUM_PER_CHIP)) + return 0; + else + return (port - DSAF_COMM_CHN + 1); +} + +static inline struct hnae_vf_cb *hns_ae_get_vf_cb( + struct hnae_handle *handle) +{ + return container_of(handle, struct hnae_vf_cb, ae_handle); +} + +int hns_dsaf_set_mac_uc_entry(struct dsaf_device *dsaf_dev, + struct dsaf_drv_mac_single_dest_entry *mac_entry); +int hns_dsaf_set_mac_mc_entry(struct dsaf_device *dsaf_dev, + struct dsaf_drv_mac_multi_dest_entry *mac_entry); +int hns_dsaf_add_mac_mc_port(struct dsaf_device *dsaf_dev, + struct dsaf_drv_mac_single_dest_entry *mac_entry); +int hns_dsaf_del_mac_entry(struct dsaf_device *dsaf_dev, u16 vlan_id, + u8 in_port_num, u8 *addr); +int hns_dsaf_del_mac_mc_port(struct dsaf_device *dsaf_dev, + struct dsaf_drv_mac_single_dest_entry *mac_entry); +int hns_dsaf_get_mac_uc_entry(struct dsaf_device *dsaf_dev, + struct dsaf_drv_mac_single_dest_entry *mac_entry); +int hns_dsaf_get_mac_mc_entry(struct dsaf_device *dsaf_dev, + struct dsaf_drv_mac_multi_dest_entry *mac_entry); +int hns_dsaf_get_mac_entry_by_index( + struct dsaf_device *dsaf_dev, + u16 entry_index, + struct dsaf_drv_mac_multi_dest_entry *mac_entry); + +void hns_dsaf_rst(struct dsaf_device *dsaf_dev, u32 val); + +void hns_ppe_srst_by_port(struct dsaf_device *dsaf_dev, u32 port, u32 val); + +void hns_ppe_com_srst(struct ppe_common_cb *ppe_common, u32 val); + +void hns_dsaf_fix_mac_mode(struct hns_mac_cb *mac_cb); + +int hns_dsaf_ae_init(struct dsaf_device *dsaf_dev); +void hns_dsaf_ae_uninit(struct dsaf_device *dsaf_dev); + +void hns_dsaf_xge_srst_by_port(struct dsaf_device *dsaf_dev, u32 port, u32 val); +void hns_dsaf_ge_srst_by_port(struct dsaf_device *dsaf_dev, u32 port, u32 val); +void hns_dsaf_xge_core_srst_by_port(struct dsaf_device *dsaf_dev, + u32 port, u32 val); + +void hns_dsaf_update_stats(struct dsaf_device *dsaf_dev, u32 inode_num); + +int hns_dsaf_get_sset_count(int stringset); +void hns_dsaf_get_stats(struct dsaf_device *ddev, u64 *data, int port); +void hns_dsaf_get_strings(int stringset, u8 *data, int port); + +void hns_dsaf_get_regs(struct dsaf_device *ddev, u32 port, void *data); +int hns_dsaf_get_regs_count(void); + +#endif /* __HNS_DSAF_MAIN_H__ */ diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c new file mode 100644 index 000000000000..d611388aecef --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c @@ -0,0 +1,317 @@ +/* + * Copyright (c) 2014-2015 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include "hns_dsaf_misc.h" +#include "hns_dsaf_mac.h" +#include "hns_dsaf_reg.h" +#include "hns_dsaf_ppe.h" + +void hns_cpld_set_led(struct hns_mac_cb *mac_cb, int link_status, + u16 speed, int data) +{ + int speed_reg = 0; + u8 value; + + if (!mac_cb) { + pr_err("sfp_led_opt mac_dev is null!\n"); + return; + } + if (!mac_cb->cpld_vaddr) { + dev_err(mac_cb->dev, "mac_id=%d, cpld_vaddr is null !\n", + mac_cb->mac_id); + return; + } + + if (speed == MAC_SPEED_10000) + speed_reg = 1; + + value = mac_cb->cpld_led_value; + + if (link_status) { + dsaf_set_bit(value, DSAF_LED_LINK_B, link_status); + dsaf_set_field(value, DSAF_LED_SPEED_M, + DSAF_LED_SPEED_S, speed_reg); + dsaf_set_bit(value, DSAF_LED_DATA_B, data); + + if (value != mac_cb->cpld_led_value) { + dsaf_write_b(mac_cb->cpld_vaddr, value); + mac_cb->cpld_led_value = value; + } + } else { + dsaf_write_b(mac_cb->cpld_vaddr, CPLD_LED_DEFAULT_VALUE); + mac_cb->cpld_led_value = CPLD_LED_DEFAULT_VALUE; + } +} + +void cpld_led_reset(struct hns_mac_cb *mac_cb) +{ + if (!mac_cb || !mac_cb->cpld_vaddr) + return; + + dsaf_write_b(mac_cb->cpld_vaddr, CPLD_LED_DEFAULT_VALUE); + mac_cb->cpld_led_value = CPLD_LED_DEFAULT_VALUE; +} + +int cpld_set_led_id(struct hns_mac_cb *mac_cb, + enum hnae_led_state status) +{ + switch (status) { + case HNAE_LED_ACTIVE: + mac_cb->cpld_led_value = dsaf_read_b(mac_cb->cpld_vaddr); + return 2; + case HNAE_LED_ON: + dsaf_set_bit(mac_cb->cpld_led_value, DSAF_LED_ANCHOR_B, + CPLD_LED_ON_VALUE); + dsaf_write_b(mac_cb->cpld_vaddr, mac_cb->cpld_led_value); + break; + case HNAE_LED_OFF: + dsaf_set_bit(mac_cb->cpld_led_value, DSAF_LED_ANCHOR_B, + CPLD_LED_DEFAULT_VALUE); + dsaf_write_b(mac_cb->cpld_vaddr, mac_cb->cpld_led_value); + break; + case HNAE_LED_INACTIVE: + dsaf_set_bit(mac_cb->cpld_led_value, DSAF_LED_ANCHOR_B, + CPLD_LED_DEFAULT_VALUE); + dsaf_write_b(mac_cb->cpld_vaddr, mac_cb->cpld_led_value); + break; + default: + break; + } + + return 0; +} + +#define RESET_REQ_OR_DREQ 1 + +void hns_dsaf_rst(struct dsaf_device *dsaf_dev, u32 val) +{ + u32 xbar_reg_addr; + u32 nt_reg_addr; + + if (!val) { + xbar_reg_addr = DSAF_SUB_SC_XBAR_RESET_REQ_REG; + nt_reg_addr = DSAF_SUB_SC_NT_RESET_REQ_REG; + } else { + xbar_reg_addr = DSAF_SUB_SC_XBAR_RESET_DREQ_REG; + nt_reg_addr = DSAF_SUB_SC_NT_RESET_DREQ_REG; + } + + dsaf_write_reg(dsaf_dev->sc_base, xbar_reg_addr, + RESET_REQ_OR_DREQ); + dsaf_write_reg(dsaf_dev->sc_base, nt_reg_addr, + RESET_REQ_OR_DREQ); +} + +void hns_dsaf_xge_srst_by_port(struct dsaf_device *dsaf_dev, u32 port, u32 val) +{ + u32 reg_val = 0; + u32 reg_addr; + + if (port >= DSAF_XGE_NUM) + return; + + reg_val |= RESET_REQ_OR_DREQ; + reg_val |= 0x2082082 << port; + + if (val == 0) + reg_addr = DSAF_SUB_SC_XGE_RESET_REQ_REG; + else + reg_addr = DSAF_SUB_SC_XGE_RESET_DREQ_REG; + + dsaf_write_reg(dsaf_dev->sc_base, reg_addr, reg_val); +} + +void hns_dsaf_xge_core_srst_by_port(struct dsaf_device *dsaf_dev, + u32 port, u32 val) +{ + u32 reg_val = 0; + u32 reg_addr; + + if (port >= DSAF_XGE_NUM) + return; + + reg_val |= XGMAC_TRX_CORE_SRST_M << port; + + if (val == 0) + reg_addr = DSAF_SUB_SC_XGE_RESET_REQ_REG; + else + reg_addr = DSAF_SUB_SC_XGE_RESET_DREQ_REG; + + dsaf_write_reg(dsaf_dev->sc_base, reg_addr, reg_val); +} + +void hns_dsaf_ge_srst_by_port(struct dsaf_device *dsaf_dev, u32 port, u32 val) +{ + u32 reg_val_1; + u32 reg_val_2; + + if (port >= DSAF_GE_NUM) + return; + + if (port < DSAF_SERVICE_NW_NUM) { + reg_val_1 = 0x1 << port; + reg_val_2 = 0x1041041 << port; + + if (val == 0) { + dsaf_write_reg(dsaf_dev->sc_base, + DSAF_SUB_SC_GE_RESET_REQ1_REG, + reg_val_1); + + dsaf_write_reg(dsaf_dev->sc_base, + DSAF_SUB_SC_GE_RESET_REQ0_REG, + reg_val_2); + } else { + dsaf_write_reg(dsaf_dev->sc_base, + DSAF_SUB_SC_GE_RESET_DREQ0_REG, + reg_val_2); + + dsaf_write_reg(dsaf_dev->sc_base, + DSAF_SUB_SC_GE_RESET_DREQ1_REG, + reg_val_1); + } + } else { + reg_val_1 = 0x15540 << (port - 6); + reg_val_2 = 0x100 << (port - 6); + + if (val == 0) { + dsaf_write_reg(dsaf_dev->sc_base, + DSAF_SUB_SC_GE_RESET_REQ1_REG, + reg_val_1); + + dsaf_write_reg(dsaf_dev->sc_base, + DSAF_SUB_SC_PPE_RESET_REQ_REG, + reg_val_2); + } else { + dsaf_write_reg(dsaf_dev->sc_base, + DSAF_SUB_SC_GE_RESET_DREQ1_REG, + reg_val_1); + + dsaf_write_reg(dsaf_dev->sc_base, + DSAF_SUB_SC_PPE_RESET_DREQ_REG, + reg_val_2); + } + } +} + +void hns_ppe_srst_by_port(struct dsaf_device *dsaf_dev, u32 port, u32 val) +{ + u32 reg_val = 0; + u32 reg_addr; + + reg_val |= RESET_REQ_OR_DREQ << port; + + if (val == 0) + reg_addr = DSAF_SUB_SC_PPE_RESET_REQ_REG; + else + reg_addr = DSAF_SUB_SC_PPE_RESET_DREQ_REG; + + dsaf_write_reg(dsaf_dev->sc_base, reg_addr, reg_val); +} + +void hns_ppe_com_srst(struct ppe_common_cb *ppe_common, u32 val) +{ + int comm_index = ppe_common->comm_index; + struct dsaf_device *dsaf_dev = ppe_common->dsaf_dev; + u32 reg_val; + u32 reg_addr; + + if (comm_index == HNS_DSAF_COMM_SERVICE_NW_IDX) { + reg_val = RESET_REQ_OR_DREQ; + if (val == 0) + reg_addr = DSAF_SUB_SC_RCB_PPE_COM_RESET_REQ_REG; + else + reg_addr = DSAF_SUB_SC_RCB_PPE_COM_RESET_DREQ_REG; + + } else { + reg_val = 0x100 << (comm_index - 1); + + if (val == 0) + reg_addr = DSAF_SUB_SC_PPE_RESET_REQ_REG; + else + reg_addr = DSAF_SUB_SC_PPE_RESET_DREQ_REG; + } + + dsaf_write_reg(dsaf_dev->sc_base, reg_addr, reg_val); +} + +/** + * hns_mac_get_sds_mode - get phy ifterface form serdes mode + * @mac_cb: mac control block + * retuen phy interface + */ +phy_interface_t hns_mac_get_phy_if(struct hns_mac_cb *mac_cb) +{ + u32 hilink3_mode; + u32 hilink4_mode; + void __iomem *sys_ctl_vaddr = mac_cb->sys_ctl_vaddr; + int dev_id = mac_cb->mac_id; + phy_interface_t phy_if = PHY_INTERFACE_MODE_NA; + + hilink3_mode = dsaf_read_reg(sys_ctl_vaddr, HNS_MAC_HILINK3_REG); + hilink4_mode = dsaf_read_reg(sys_ctl_vaddr, HNS_MAC_HILINK4_REG); + if (dev_id >= 0 && dev_id <= 3) { + if (hilink4_mode == 0) + phy_if = PHY_INTERFACE_MODE_SGMII; + else + phy_if = PHY_INTERFACE_MODE_XGMII; + } else if (dev_id >= 4 && dev_id <= 5) { + if (hilink3_mode == 0) + phy_if = PHY_INTERFACE_MODE_SGMII; + else + phy_if = PHY_INTERFACE_MODE_XGMII; + } else { + phy_if = PHY_INTERFACE_MODE_SGMII; + } + + dev_dbg(mac_cb->dev, + "hilink3_mode=%d, hilink4_mode=%d dev_id=%d, phy_if=%d\n", + hilink3_mode, hilink4_mode, dev_id, phy_if); + return phy_if; +} + +/** + * hns_mac_config_sds_loopback - set loop back for serdes + * @mac_cb: mac control block + * retuen 0 == success + */ +int hns_mac_config_sds_loopback(struct hns_mac_cb *mac_cb, u8 en) +{ + /* port 0-3 hilink4 base is serdes_vaddr + 0x00280000 + * port 4-7 hilink3 base is serdes_vaddr + 0x00200000 + */ + u8 *base_addr = (u8 *)mac_cb->serdes_vaddr + + (mac_cb->mac_id <= 3 ? 0x00280000 : 0x00200000); + const u8 lane_id[] = { + 0, /* mac 0 -> lane 0 */ + 1, /* mac 1 -> lane 1 */ + 2, /* mac 2 -> lane 2 */ + 3, /* mac 3 -> lane 3 */ + 2, /* mac 4 -> lane 2 */ + 3, /* mac 5 -> lane 3 */ + 0, /* mac 6 -> lane 0 */ + 1 /* mac 7 -> lane 1 */ + }; +#define RX_CSR(lane, reg) ((0x4080 + (reg) * 0x0002 + (lane) * 0x0200) * 2) + u64 reg_offset = RX_CSR(lane_id[mac_cb->mac_id], 0); + + int sfp_prsnt; + int ret = hns_mac_get_sfp_prsnt(mac_cb, &sfp_prsnt); + + if (!mac_cb->phy_node) { + if (ret) + pr_info("please confirm sfp is present or not\n"); + else + if (!sfp_prsnt) + pr_info("no sfp in this eth\n"); + } + + dsaf_set_reg_field(base_addr, reg_offset, 1ull << 10, 10, !!en); + + return 0; +} diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.h new file mode 100644 index 000000000000..419f07aa9734 --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.h @@ -0,0 +1,43 @@ +/* + * Copyright (c) 2014-2015 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef _HNS_DSAF_MISC_H +#define _HNS_DSAF_MISC_H + +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/platform_device.h> + +#include "hns_dsaf_mac.h" + +#define CPLD_ADDR_PORT_OFFSET 0x4 + +#define HS_LED_ON 0xE +#define HS_LED_OFF 0xF + +#define CPLD_LED_ON_VALUE 1 +#define CPLD_LED_DEFAULT_VALUE 0 + +#define MAC_SFP_PORT_OFFSET 0x2 + +#define DSAF_LED_SPEED_S 0 +#define DSAF_LED_SPEED_M (0x3 << DSAF_LED_SPEED_S) + +#define DSAF_LED_LINK_B 2 +#define DSAF_LED_DATA_B 4 +#define DSAF_LED_ANCHOR_B 5 + +void hns_cpld_set_led(struct hns_mac_cb *mac_cb, int link_status, + u16 speed, int data); +void cpld_led_reset(struct hns_mac_cb *mac_cb); +int cpld_set_led_id(struct hns_mac_cb *mac_cb, + enum hnae_led_state status); +int hns_mac_get_sfp_prsnt(struct hns_mac_cb *mac_cb, int *sfp_prsnt); + +#endif diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c new file mode 100644 index 000000000000..67f33f185a44 --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c @@ -0,0 +1,583 @@ +/* + * Copyright (c) 2014-2015 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <linux/platform_device.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/of_platform.h> + +#include "hns_dsaf_ppe.h" + +static void __iomem *hns_ppe_common_get_ioaddr( + struct ppe_common_cb *ppe_common) +{ + void __iomem *base_addr; + + int idx = ppe_common->comm_index; + + if (idx == HNS_DSAF_COMM_SERVICE_NW_IDX) + base_addr = ppe_common->dsaf_dev->ppe_base + + PPE_COMMON_REG_OFFSET; + else + base_addr = ppe_common->dsaf_dev->sds_base + + (idx - 1) * HNS_DSAF_DEBUG_NW_REG_OFFSET + + PPE_COMMON_REG_OFFSET; + + return base_addr; +} + +/** + * hns_ppe_common_get_cfg - get ppe common config + * @dsaf_dev: dasf device + * comm_index: common index + * retuen 0 - success , negative --fail + */ +int hns_ppe_common_get_cfg(struct dsaf_device *dsaf_dev, int comm_index) +{ + struct ppe_common_cb *ppe_common; + int ppe_num; + + if (comm_index == HNS_DSAF_COMM_SERVICE_NW_IDX) + ppe_num = HNS_PPE_SERVICE_NW_ENGINE_NUM; + else + ppe_num = HNS_PPE_DEBUG_NW_ENGINE_NUM; + + ppe_common = devm_kzalloc(dsaf_dev->dev, sizeof(*ppe_common) + + ppe_num * sizeof(struct hns_ppe_cb), GFP_KERNEL); + if (!ppe_common) + return -ENOMEM; + + ppe_common->ppe_num = ppe_num; + ppe_common->dsaf_dev = dsaf_dev; + ppe_common->comm_index = comm_index; + if (comm_index == HNS_DSAF_COMM_SERVICE_NW_IDX) + ppe_common->ppe_mode = PPE_COMMON_MODE_SERVICE; + else + ppe_common->ppe_mode = PPE_COMMON_MODE_DEBUG; + ppe_common->dev = dsaf_dev->dev; + + ppe_common->io_base = hns_ppe_common_get_ioaddr(ppe_common); + + dsaf_dev->ppe_common[comm_index] = ppe_common; + + return 0; +} + +void hns_ppe_common_free_cfg(struct dsaf_device *dsaf_dev, u32 comm_index) +{ + dsaf_dev->ppe_common[comm_index] = NULL; +} + +static void __iomem *hns_ppe_get_iobase(struct ppe_common_cb *ppe_common, + int ppe_idx) +{ + void __iomem *base_addr; + int common_idx = ppe_common->comm_index; + + if (ppe_common->ppe_mode == PPE_COMMON_MODE_SERVICE) { + base_addr = ppe_common->dsaf_dev->ppe_base + + ppe_idx * PPE_REG_OFFSET; + + } else { + base_addr = ppe_common->dsaf_dev->sds_base + + (common_idx - 1) * HNS_DSAF_DEBUG_NW_REG_OFFSET; + } + + return base_addr; +} + +static int hns_ppe_get_port(struct ppe_common_cb *ppe_common, int idx) +{ + int port; + + if (ppe_common->ppe_mode == PPE_COMMON_MODE_SERVICE) + port = idx; + else + port = HNS_PPE_SERVICE_NW_ENGINE_NUM + + ppe_common->comm_index - 1; + + return port; +} + +static void hns_ppe_get_cfg(struct ppe_common_cb *ppe_common) +{ + u32 i; + struct hns_ppe_cb *ppe_cb; + u32 ppe_num = ppe_common->ppe_num; + + for (i = 0; i < ppe_num; i++) { + ppe_cb = &ppe_common->ppe_cb[i]; + ppe_cb->dev = ppe_common->dev; + ppe_cb->next = NULL; + ppe_cb->ppe_common_cb = ppe_common; + ppe_cb->index = i; + ppe_cb->port = hns_ppe_get_port(ppe_common, i); + ppe_cb->io_base = hns_ppe_get_iobase(ppe_common, i); + ppe_cb->virq = 0; + } +} + +static void hns_ppe_cnt_clr_ce(struct hns_ppe_cb *ppe_cb) +{ + dsaf_set_dev_bit(ppe_cb, PPE_TNL_0_5_CNT_CLR_CE_REG, + PPE_CNT_CLR_CE_B, 1); +} + +/** + * hns_ppe_checksum_hw - set ppe checksum caculate + * @ppe_device: ppe device + * @value: value + */ +static void hns_ppe_checksum_hw(struct hns_ppe_cb *ppe_cb, u32 value) +{ + dsaf_set_dev_field(ppe_cb, PPE_CFG_PRO_CHECK_EN_REG, + 0xfffffff, 0, value); +} + +static void hns_ppe_set_qid_mode(struct ppe_common_cb *ppe_common, + enum ppe_qid_mode qid_mdoe) +{ + dsaf_set_dev_field(ppe_common, PPE_COM_CFG_QID_MODE_REG, + PPE_CFG_QID_MODE_CF_QID_MODE_M, + PPE_CFG_QID_MODE_CF_QID_MODE_S, qid_mdoe); +} + +/** + * hns_ppe_set_qid - set ppe qid + * @ppe_common: ppe common device + * @qid: queue id + */ +static void hns_ppe_set_qid(struct ppe_common_cb *ppe_common, u32 qid) +{ + u32 qid_mod = dsaf_read_dev(ppe_common, PPE_COM_CFG_QID_MODE_REG); + + if (!dsaf_get_field(qid_mod, PPE_CFG_QID_MODE_DEF_QID_M, + PPE_CFG_QID_MODE_DEF_QID_S)) { + dsaf_set_field(qid_mod, PPE_CFG_QID_MODE_DEF_QID_M, + PPE_CFG_QID_MODE_DEF_QID_S, qid); + dsaf_write_dev(ppe_common, PPE_COM_CFG_QID_MODE_REG, qid_mod); + } +} + +/** + * hns_ppe_set_port_mode - set port mode + * @ppe_device: ppe device + * @mode: port mode + */ +static void hns_ppe_set_port_mode(struct hns_ppe_cb *ppe_cb, + enum ppe_port_mode mode) +{ + dsaf_write_dev(ppe_cb, PPE_CFG_XGE_MODE_REG, mode); +} + +/** + * hns_ppe_common_init_hw - init ppe common device + * @ppe_common: ppe common device + * + * Return 0 on success, negative on failure + */ +static int hns_ppe_common_init_hw(struct ppe_common_cb *ppe_common) +{ + enum ppe_qid_mode qid_mode; + enum dsaf_mode dsaf_mode = ppe_common->dsaf_dev->dsaf_mode; + + hns_ppe_com_srst(ppe_common, 0); + mdelay(100); + hns_ppe_com_srst(ppe_common, 1); + mdelay(100); + + if (ppe_common->ppe_mode == PPE_COMMON_MODE_SERVICE) { + switch (dsaf_mode) { + case DSAF_MODE_ENABLE_FIX: + case DSAF_MODE_DISABLE_FIX: + qid_mode = PPE_QID_MODE0; + hns_ppe_set_qid(ppe_common, 0); + break; + case DSAF_MODE_ENABLE_0VM: + case DSAF_MODE_DISABLE_2PORT_64VM: + qid_mode = PPE_QID_MODE3; + break; + case DSAF_MODE_ENABLE_8VM: + case DSAF_MODE_DISABLE_2PORT_16VM: + qid_mode = PPE_QID_MODE4; + break; + case DSAF_MODE_ENABLE_16VM: + case DSAF_MODE_DISABLE_6PORT_0VM: + qid_mode = PPE_QID_MODE5; + break; + case DSAF_MODE_ENABLE_32VM: + case DSAF_MODE_DISABLE_6PORT_16VM: + qid_mode = PPE_QID_MODE2; + break; + case DSAF_MODE_ENABLE_128VM: + case DSAF_MODE_DISABLE_6PORT_4VM: + qid_mode = PPE_QID_MODE1; + break; + case DSAF_MODE_DISABLE_2PORT_8VM: + qid_mode = PPE_QID_MODE7; + break; + case DSAF_MODE_DISABLE_6PORT_2VM: + qid_mode = PPE_QID_MODE6; + break; + default: + dev_err(ppe_common->dev, + "get ppe queue mode failed! dsaf_mode=%d\n", + dsaf_mode); + return -EINVAL; + } + hns_ppe_set_qid_mode(ppe_common, qid_mode); + } + + dsaf_set_dev_bit(ppe_common, PPE_COM_COMMON_CNT_CLR_CE_REG, + PPE_COMMON_CNT_CLR_CE_B, 1); + + return 0; +} + +/*clr ppe exception irq*/ +static void hns_ppe_exc_irq_en(struct hns_ppe_cb *ppe_cb, int en) +{ + u32 clr_vlue = 0xfffffffful; + u32 msk_vlue = en ? 0xfffffffful : 0; /*1 is en, 0 is dis*/ + u32 vld_msk = 0; + + /*only care bit 0,1,7*/ + dsaf_set_bit(vld_msk, 0, 1); + dsaf_set_bit(vld_msk, 1, 1); + dsaf_set_bit(vld_msk, 7, 1); + + /*clr sts**/ + dsaf_write_dev(ppe_cb, PPE_RINT_REG, clr_vlue); + + /*for some reserved bits, so set 0**/ + dsaf_write_dev(ppe_cb, PPE_INTEN_REG, msk_vlue & vld_msk); +} + +/** + * ppe_init_hw - init ppe + * @ppe_device: ppe device + */ +static void hns_ppe_init_hw(struct hns_ppe_cb *ppe_cb) +{ + struct ppe_common_cb *ppe_common_cb = ppe_cb->ppe_common_cb; + u32 port = ppe_cb->port; + struct dsaf_device *dsaf_dev = ppe_common_cb->dsaf_dev; + + hns_ppe_srst_by_port(dsaf_dev, port, 0); + mdelay(10); + hns_ppe_srst_by_port(dsaf_dev, port, 1); + + /* clr and msk except irq*/ + hns_ppe_exc_irq_en(ppe_cb, 0); + + if (ppe_common_cb->ppe_mode == PPE_COMMON_MODE_DEBUG) + hns_ppe_set_port_mode(ppe_cb, PPE_MODE_GE); + else + hns_ppe_set_port_mode(ppe_cb, PPE_MODE_XGE); + hns_ppe_checksum_hw(ppe_cb, 0xffffffff); + hns_ppe_cnt_clr_ce(ppe_cb); +} + +/** + * ppe_uninit_hw - uninit ppe + * @ppe_device: ppe device + */ +static void hns_ppe_uninit_hw(struct hns_ppe_cb *ppe_cb) +{ + u32 port; + + if (ppe_cb->ppe_common_cb) { + port = ppe_cb->index; + hns_ppe_srst_by_port(ppe_cb->ppe_common_cb->dsaf_dev, port, 0); + } +} + +void hns_ppe_uninit_ex(struct ppe_common_cb *ppe_common) +{ + u32 i; + + for (i = 0; i < ppe_common->ppe_num; i++) { + hns_ppe_uninit_hw(&ppe_common->ppe_cb[i]); + memset(&ppe_common->ppe_cb[i], 0, sizeof(struct hns_ppe_cb)); + } +} + +void hns_ppe_uninit(struct dsaf_device *dsaf_dev) +{ + u32 i; + + for (i = 0; i < HNS_PPE_COM_NUM; i++) { + if (dsaf_dev->ppe_common[i]) + hns_ppe_uninit_ex(dsaf_dev->ppe_common[i]); + hns_rcb_common_free_cfg(dsaf_dev, i); + hns_ppe_common_free_cfg(dsaf_dev, i); + } +} + +/** + * hns_ppe_reset - reinit ppe/rcb hw + * @dsaf_dev: dasf device + * retuen void + */ +void hns_ppe_reset_common(struct dsaf_device *dsaf_dev, u8 ppe_common_index) +{ + u32 i; + int ret; + struct ppe_common_cb *ppe_common; + + ppe_common = dsaf_dev->ppe_common[ppe_common_index]; + ret = hns_ppe_common_init_hw(ppe_common); + if (ret) + return; + + ret = hns_rcb_common_init_hw(dsaf_dev->rcb_common[ppe_common_index]); + if (ret) + return; + + for (i = 0; i < ppe_common->ppe_num; i++) + hns_ppe_init_hw(&ppe_common->ppe_cb[i]); + + hns_rcb_common_init_commit_hw(dsaf_dev->rcb_common[ppe_common_index]); +} + +void hns_ppe_update_stats(struct hns_ppe_cb *ppe_cb) +{ + struct hns_ppe_hw_stats *hw_stats = &ppe_cb->hw_stats; + + hw_stats->rx_pkts_from_sw + += dsaf_read_dev(ppe_cb, PPE_HIS_RX_SW_PKT_CNT_REG); + hw_stats->rx_pkts + += dsaf_read_dev(ppe_cb, PPE_HIS_RX_WR_BD_OK_PKT_CNT_REG); + hw_stats->rx_drop_no_bd + += dsaf_read_dev(ppe_cb, PPE_HIS_RX_PKT_NO_BUF_CNT_REG); + hw_stats->rx_alloc_buf_fail + += dsaf_read_dev(ppe_cb, PPE_HIS_RX_APP_BUF_FAIL_CNT_REG); + hw_stats->rx_alloc_buf_wait + += dsaf_read_dev(ppe_cb, PPE_HIS_RX_APP_BUF_WAIT_CNT_REG); + hw_stats->rx_drop_no_buf + += dsaf_read_dev(ppe_cb, PPE_HIS_RX_PKT_DROP_FUL_CNT_REG); + hw_stats->rx_err_fifo_full + += dsaf_read_dev(ppe_cb, PPE_HIS_RX_PKT_DROP_PRT_CNT_REG); + + hw_stats->tx_bd_form_rcb + += dsaf_read_dev(ppe_cb, PPE_HIS_TX_BD_CNT_REG); + hw_stats->tx_pkts_from_rcb + += dsaf_read_dev(ppe_cb, PPE_HIS_TX_PKT_CNT_REG); + hw_stats->tx_pkts + += dsaf_read_dev(ppe_cb, PPE_HIS_TX_PKT_OK_CNT_REG); + hw_stats->tx_err_fifo_empty + += dsaf_read_dev(ppe_cb, PPE_HIS_TX_PKT_EPT_CNT_REG); + hw_stats->tx_err_checksum + += dsaf_read_dev(ppe_cb, PPE_HIS_TX_PKT_CS_FAIL_CNT_REG); +} + +int hns_ppe_get_sset_count(int stringset) +{ + if (stringset == ETH_SS_STATS) + return ETH_PPE_STATIC_NUM; + return 0; +} + +int hns_ppe_get_regs_count(void) +{ + return ETH_PPE_DUMP_NUM; +} + +/** + * ppe_get_strings - get ppe srting + * @ppe_device: ppe device + * @stringset: string set type + * @data: output string + */ +void hns_ppe_get_strings(struct hns_ppe_cb *ppe_cb, int stringset, u8 *data) +{ + char *buff = (char *)data; + int index = ppe_cb->index; + + snprintf(buff, ETH_GSTRING_LEN, "ppe%d_rx_sw_pkt", index); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "ppe%d_rx_pkt_ok", index); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "ppe%d_rx_drop_pkt_no_bd", index); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "ppe%d_rx_alloc_buf_fail", index); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "ppe%d_rx_alloc_buf_wait", index); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "ppe%d_rx_pkt_drop_no_buf", index); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "ppe%d_rx_pkt_err_fifo_full", index); + buff = buff + ETH_GSTRING_LEN; + + snprintf(buff, ETH_GSTRING_LEN, "ppe%d_tx_bd", index); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "ppe%d_tx_pkt", index); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "ppe%d_tx_pkt_ok", index); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "ppe%d_tx_pkt_err_fifo_empty", index); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "ppe%d_tx_pkt_err_csum_fail", index); +} + +void hns_ppe_get_stats(struct hns_ppe_cb *ppe_cb, u64 *data) +{ + u64 *regs_buff = data; + struct hns_ppe_hw_stats *hw_stats = &ppe_cb->hw_stats; + + regs_buff[0] = hw_stats->rx_pkts_from_sw; + regs_buff[1] = hw_stats->rx_pkts; + regs_buff[2] = hw_stats->rx_drop_no_bd; + regs_buff[3] = hw_stats->rx_alloc_buf_fail; + regs_buff[4] = hw_stats->rx_alloc_buf_wait; + regs_buff[5] = hw_stats->rx_drop_no_buf; + regs_buff[6] = hw_stats->rx_err_fifo_full; + + regs_buff[7] = hw_stats->tx_bd_form_rcb; + regs_buff[8] = hw_stats->tx_pkts_from_rcb; + regs_buff[9] = hw_stats->tx_pkts; + regs_buff[10] = hw_stats->tx_err_fifo_empty; + regs_buff[11] = hw_stats->tx_err_checksum; +} + +/** + * hns_ppe_init - init ppe device + * @dsaf_dev: dasf device + * retuen 0 - success , negative --fail + */ +int hns_ppe_init(struct dsaf_device *dsaf_dev) +{ + int i, k; + int ret; + + for (i = 0; i < HNS_PPE_COM_NUM; i++) { + ret = hns_ppe_common_get_cfg(dsaf_dev, i); + if (ret) + goto get_ppe_cfg_fail; + + ret = hns_rcb_common_get_cfg(dsaf_dev, i); + if (ret) + goto get_rcb_cfg_fail; + + hns_ppe_get_cfg(dsaf_dev->ppe_common[i]); + + hns_rcb_get_cfg(dsaf_dev->rcb_common[i]); + } + + for (i = 0; i < HNS_PPE_COM_NUM; i++) + hns_ppe_reset_common(dsaf_dev, i); + + return 0; + +get_rcb_cfg_fail: + hns_ppe_common_free_cfg(dsaf_dev, i); +get_ppe_cfg_fail: + for (k = i - 1; k >= 0; k--) { + hns_rcb_common_free_cfg(dsaf_dev, k); + hns_ppe_common_free_cfg(dsaf_dev, k); + } + return ret; +} + +void hns_ppe_get_regs(struct hns_ppe_cb *ppe_cb, void *data) +{ + struct ppe_common_cb *ppe_common = ppe_cb->ppe_common_cb; + u32 *regs = data; + u32 i; + u32 offset; + + /* ppe common registers */ + regs[0] = dsaf_read_dev(ppe_common, PPE_COM_CFG_QID_MODE_REG); + regs[1] = dsaf_read_dev(ppe_common, PPE_COM_INTEN_REG); + regs[2] = dsaf_read_dev(ppe_common, PPE_COM_RINT_REG); + regs[3] = dsaf_read_dev(ppe_common, PPE_COM_INTSTS_REG); + regs[4] = dsaf_read_dev(ppe_common, PPE_COM_COMMON_CNT_CLR_CE_REG); + + for (i = 0; i < DSAF_TOTAL_QUEUE_NUM; i++) { + offset = PPE_COM_HIS_RX_PKT_QID_DROP_CNT_REG + 0x4 * i; + regs[5 + i] = dsaf_read_dev(ppe_common, offset); + offset = PPE_COM_HIS_RX_PKT_QID_OK_CNT_REG + 0x4 * i; + regs[5 + i + DSAF_TOTAL_QUEUE_NUM] + = dsaf_read_dev(ppe_common, offset); + offset = PPE_COM_HIS_TX_PKT_QID_ERR_CNT_REG + 0x4 * i; + regs[5 + i + DSAF_TOTAL_QUEUE_NUM * 2] + = dsaf_read_dev(ppe_common, offset); + offset = PPE_COM_HIS_TX_PKT_QID_OK_CNT_REG + 0x4 * i; + regs[5 + i + DSAF_TOTAL_QUEUE_NUM * 3] + = dsaf_read_dev(ppe_common, offset); + } + + /* mark end of ppe regs */ + for (i = 521; i < 524; i++) + regs[i] = 0xeeeeeeee; + + /* ppe channel registers */ + regs[525] = dsaf_read_dev(ppe_cb, PPE_CFG_TX_FIFO_THRSLD_REG); + regs[526] = dsaf_read_dev(ppe_cb, PPE_CFG_RX_FIFO_THRSLD_REG); + regs[527] = dsaf_read_dev(ppe_cb, PPE_CFG_RX_FIFO_PAUSE_THRSLD_REG); + regs[528] = dsaf_read_dev(ppe_cb, PPE_CFG_RX_FIFO_SW_BP_THRSLD_REG); + regs[529] = dsaf_read_dev(ppe_cb, PPE_CFG_PAUSE_IDLE_CNT_REG); + regs[530] = dsaf_read_dev(ppe_cb, PPE_CFG_BUS_CTRL_REG); + regs[531] = dsaf_read_dev(ppe_cb, PPE_CFG_TNL_TO_BE_RST_REG); + regs[532] = dsaf_read_dev(ppe_cb, PPE_CURR_TNL_CAN_RST_REG); + + regs[533] = dsaf_read_dev(ppe_cb, PPE_CFG_XGE_MODE_REG); + regs[534] = dsaf_read_dev(ppe_cb, PPE_CFG_MAX_FRAME_LEN_REG); + regs[535] = dsaf_read_dev(ppe_cb, PPE_CFG_RX_PKT_MODE_REG); + regs[536] = dsaf_read_dev(ppe_cb, PPE_CFG_RX_VLAN_TAG_REG); + regs[537] = dsaf_read_dev(ppe_cb, PPE_CFG_TAG_GEN_REG); + regs[538] = dsaf_read_dev(ppe_cb, PPE_CFG_PARSE_TAG_REG); + regs[539] = dsaf_read_dev(ppe_cb, PPE_CFG_PRO_CHECK_EN_REG); + + regs[540] = dsaf_read_dev(ppe_cb, PPE_INTEN_REG); + regs[541] = dsaf_read_dev(ppe_cb, PPE_RINT_REG); + regs[542] = dsaf_read_dev(ppe_cb, PPE_INTSTS_REG); + regs[543] = dsaf_read_dev(ppe_cb, PPE_CFG_RX_PKT_INT_REG); + + regs[544] = dsaf_read_dev(ppe_cb, PPE_CFG_HEAT_DECT_TIME0_REG); + regs[545] = dsaf_read_dev(ppe_cb, PPE_CFG_HEAT_DECT_TIME1_REG); + + /* ppe static */ + regs[546] = dsaf_read_dev(ppe_cb, PPE_HIS_RX_SW_PKT_CNT_REG); + regs[547] = dsaf_read_dev(ppe_cb, PPE_HIS_RX_WR_BD_OK_PKT_CNT_REG); + regs[548] = dsaf_read_dev(ppe_cb, PPE_HIS_RX_PKT_NO_BUF_CNT_REG); + regs[549] = dsaf_read_dev(ppe_cb, PPE_HIS_TX_BD_CNT_REG); + regs[550] = dsaf_read_dev(ppe_cb, PPE_HIS_TX_PKT_CNT_REG); + regs[551] = dsaf_read_dev(ppe_cb, PPE_HIS_TX_PKT_OK_CNT_REG); + regs[552] = dsaf_read_dev(ppe_cb, PPE_HIS_TX_PKT_EPT_CNT_REG); + regs[553] = dsaf_read_dev(ppe_cb, PPE_HIS_TX_PKT_CS_FAIL_CNT_REG); + regs[554] = dsaf_read_dev(ppe_cb, PPE_HIS_RX_APP_BUF_FAIL_CNT_REG); + regs[555] = dsaf_read_dev(ppe_cb, PPE_HIS_RX_APP_BUF_WAIT_CNT_REG); + regs[556] = dsaf_read_dev(ppe_cb, PPE_HIS_RX_PKT_DROP_FUL_CNT_REG); + regs[557] = dsaf_read_dev(ppe_cb, PPE_HIS_RX_PKT_DROP_PRT_CNT_REG); + + regs[558] = dsaf_read_dev(ppe_cb, PPE_TNL_0_5_CNT_CLR_CE_REG); + regs[559] = dsaf_read_dev(ppe_cb, PPE_CFG_AXI_DBG_REG); + regs[560] = dsaf_read_dev(ppe_cb, PPE_HIS_PRO_ERR_REG); + regs[561] = dsaf_read_dev(ppe_cb, PPE_HIS_TNL_FIFO_ERR_REG); + regs[562] = dsaf_read_dev(ppe_cb, PPE_CURR_CFF_DATA_NUM_REG); + regs[563] = dsaf_read_dev(ppe_cb, PPE_CURR_RX_ST_REG); + regs[564] = dsaf_read_dev(ppe_cb, PPE_CURR_TX_ST_REG); + regs[565] = dsaf_read_dev(ppe_cb, PPE_CURR_RX_FIFO0_REG); + regs[566] = dsaf_read_dev(ppe_cb, PPE_CURR_RX_FIFO1_REG); + regs[567] = dsaf_read_dev(ppe_cb, PPE_CURR_TX_FIFO0_REG); + regs[568] = dsaf_read_dev(ppe_cb, PPE_CURR_TX_FIFO1_REG); + regs[569] = dsaf_read_dev(ppe_cb, PPE_ECO0_REG); + regs[570] = dsaf_read_dev(ppe_cb, PPE_ECO1_REG); + regs[571] = dsaf_read_dev(ppe_cb, PPE_ECO2_REG); + + /* mark end of ppe regs */ + for (i = 572; i < 576; i++) + regs[i] = 0xeeeeeeee; +} diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h new file mode 100644 index 000000000000..4894f9a0d39f --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h @@ -0,0 +1,105 @@ +/* + * Copyright (c) 2014-2015 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef _HNS_DSAF_PPE_H +#define _HNS_DSAF_PPE_H + +#include <linux/platform_device.h> + +#include "hns_dsaf_main.h" +#include "hns_dsaf_mac.h" +#include "hns_dsaf_rcb.h" + +#define HNS_PPE_SERVICE_NW_ENGINE_NUM DSAF_COMM_CHN +#define HNS_PPE_DEBUG_NW_ENGINE_NUM 1 +#define HNS_PPE_COM_NUM DSAF_COMM_DEV_NUM + +#define PPE_COMMON_REG_OFFSET 0x70000 +#define PPE_REG_OFFSET 0x10000 + +#define ETH_PPE_DUMP_NUM 576 +#define ETH_PPE_STATIC_NUM 12 +enum ppe_qid_mode { + PPE_QID_MODE0 = 0, /* fixed queue id mode */ + PPE_QID_MODE1, /* switch:128VM non switch:6Port/4VM/4TC */ + PPE_QID_MODE2, /* switch:32VM/4TC non switch:6Port/16VM */ + PPE_QID_MODE3, /* switch:4TC/8TAG non switch:2Port/64VM */ + PPE_QID_MODE4, /* switch:8VM/16TAG non switch:2Port/16VM/4TC */ + PPE_QID_MODE5, /* non switch:6Port/16TAG */ + PPE_QID_MODE6, /* non switch:6Port/2VM/8TC */ + PPE_QID_MODE7, /* non switch:2Port/8VM/8TC */ +}; + +enum ppe_port_mode { + PPE_MODE_GE = 0, + PPE_MODE_XGE, +}; + +enum ppe_common_mode { + PPE_COMMON_MODE_DEBUG = 0, + PPE_COMMON_MODE_SERVICE, + PPE_COMMON_MODE_MAX +}; + +struct hns_ppe_hw_stats { + u64 rx_pkts_from_sw; + u64 rx_pkts; + u64 rx_drop_no_bd; + u64 rx_alloc_buf_fail; + u64 rx_alloc_buf_wait; + u64 rx_drop_no_buf; + u64 rx_err_fifo_full; + u64 tx_bd_form_rcb; + u64 tx_pkts_from_rcb; + u64 tx_pkts; + u64 tx_err_fifo_empty; + u64 tx_err_checksum; +}; + +struct hns_ppe_cb { + struct device *dev; + struct hns_ppe_cb *next; /* pointer to next ppe device */ + struct ppe_common_cb *ppe_common_cb; /* belong to */ + struct hns_ppe_hw_stats hw_stats; + + u8 index; /* index in a ppe common device */ + u8 port; /* port id in dsaf */ + void __iomem *io_base; + int virq; +}; + +struct ppe_common_cb { + struct device *dev; + struct dsaf_device *dsaf_dev; + void __iomem *io_base; + + enum ppe_common_mode ppe_mode; + + u8 comm_index; /*ppe_common index*/ + + u32 ppe_num; + struct hns_ppe_cb ppe_cb[0]; + +}; + +int hns_ppe_init(struct dsaf_device *dsaf_dev); + +void hns_ppe_uninit(struct dsaf_device *dsaf_dev); + +void hns_ppe_reset_common(struct dsaf_device *dsaf_dev, u8 ppe_common_index); + +void hns_ppe_update_stats(struct hns_ppe_cb *ppe_cb); + +int hns_ppe_get_sset_count(int stringset); +int hns_ppe_get_regs_count(void); +void hns_ppe_get_regs(struct hns_ppe_cb *ppe_cb, void *data); + +void hns_ppe_get_strings(struct hns_ppe_cb *ppe_cb, int stringset, u8 *data); +void hns_ppe_get_stats(struct hns_ppe_cb *ppe_cb, u64 *data); +#endif /* _HNS_DSAF_PPE_H */ diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c new file mode 100644 index 000000000000..05ea244d999c --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c @@ -0,0 +1,1021 @@ +/* + * Copyright (c) 2014-2015 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/cdev.h> +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <asm/cacheflush.h> +#include <linux/platform_device.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/of_platform.h> +#include <linux/of_irq.h> +#include <linux/spinlock.h> + +#include "hns_dsaf_main.h" +#include "hns_dsaf_ppe.h" +#include "hns_dsaf_rcb.h" + +#define RCB_COMMON_REG_OFFSET 0x80000 +#define TX_RING 0 +#define RX_RING 1 + +#define RCB_RESET_WAIT_TIMES 30 +#define RCB_RESET_TRY_TIMES 10 + +/** + *hns_rcb_wait_fbd_clean - clean fbd + *@qs: ring struct pointer array + *@qnum: num of array + *@flag: tx or rx flag + */ +void hns_rcb_wait_fbd_clean(struct hnae_queue **qs, int q_num, u32 flag) +{ + int i, wait_cnt; + u32 fbd_num; + + for (wait_cnt = i = 0; i < q_num; wait_cnt++) { + usleep_range(200, 300); + fbd_num = 0; + if (flag & RCB_INT_FLAG_TX) + fbd_num += dsaf_read_dev(qs[i], + RCB_RING_TX_RING_FBDNUM_REG); + if (flag & RCB_INT_FLAG_RX) + fbd_num += dsaf_read_dev(qs[i], + RCB_RING_RX_RING_FBDNUM_REG); + if (!fbd_num) + i++; + if (wait_cnt >= 10000) + break; + } + + if (i < q_num) + dev_err(qs[i]->handle->owner_dev, + "queue(%d) wait fbd(%d) clean fail!!\n", i, fbd_num); +} + +/** + *hns_rcb_reset_ring_hw - ring reset + *@q: ring struct pointer + */ +void hns_rcb_reset_ring_hw(struct hnae_queue *q) +{ + u32 wait_cnt; + u32 try_cnt = 0; + u32 could_ret; + + u32 tx_fbd_num; + + while (try_cnt++ < RCB_RESET_TRY_TIMES) { + usleep_range(100, 200); + tx_fbd_num = dsaf_read_dev(q, RCB_RING_TX_RING_FBDNUM_REG); + if (tx_fbd_num) + continue; + + dsaf_write_dev(q, RCB_RING_PREFETCH_EN_REG, 0); + + dsaf_write_dev(q, RCB_RING_T0_BE_RST, 1); + + msleep(20); + could_ret = dsaf_read_dev(q, RCB_RING_COULD_BE_RST); + + wait_cnt = 0; + while (!could_ret && (wait_cnt < RCB_RESET_WAIT_TIMES)) { + dsaf_write_dev(q, RCB_RING_T0_BE_RST, 0); + + dsaf_write_dev(q, RCB_RING_T0_BE_RST, 1); + + msleep(20); + could_ret = dsaf_read_dev(q, RCB_RING_COULD_BE_RST); + + wait_cnt++; + } + + dsaf_write_dev(q, RCB_RING_T0_BE_RST, 0); + + if (could_ret) + break; + } + + if (try_cnt >= RCB_RESET_TRY_TIMES) + dev_err(q->dev->dev, "port%d reset ring fail\n", + hns_ae_get_vf_cb(q->handle)->port_index); +} + +/** + *hns_rcb_int_ctrl_hw - rcb irq enable control + *@q: hnae queue struct pointer + *@flag:ring flag tx or rx + *@mask:mask + */ +void hns_rcb_int_ctrl_hw(struct hnae_queue *q, u32 flag, u32 mask) +{ + u32 int_mask_en = !!mask; + + if (flag & RCB_INT_FLAG_TX) { + dsaf_write_dev(q, RCB_RING_INTMSK_TXWL_REG, int_mask_en); + dsaf_write_dev(q, RCB_RING_INTMSK_TX_OVERTIME_REG, + int_mask_en); + } + + if (flag & RCB_INT_FLAG_RX) { + dsaf_write_dev(q, RCB_RING_INTMSK_RXWL_REG, int_mask_en); + dsaf_write_dev(q, RCB_RING_INTMSK_RX_OVERTIME_REG, + int_mask_en); + } +} + +void hns_rcb_int_clr_hw(struct hnae_queue *q, u32 flag) +{ + u32 clr = 1; + + if (flag & RCB_INT_FLAG_TX) { + dsaf_write_dev(q, RCB_RING_INTSTS_TX_RING_REG, clr); + dsaf_write_dev(q, RCB_RING_INTSTS_TX_OVERTIME_REG, clr); + } + + if (flag & RCB_INT_FLAG_RX) { + dsaf_write_dev(q, RCB_RING_INTSTS_RX_RING_REG, clr); + dsaf_write_dev(q, RCB_RING_INTSTS_RX_OVERTIME_REG, clr); + } +} + +/** + *hns_rcb_ring_enable_hw - enable ring + *@ring: rcb ring + */ +void hns_rcb_ring_enable_hw(struct hnae_queue *q, u32 val) +{ + dsaf_write_dev(q, RCB_RING_PREFETCH_EN_REG, !!val); +} + +void hns_rcb_start(struct hnae_queue *q, u32 val) +{ + hns_rcb_ring_enable_hw(q, val); +} + +/** + *hns_rcb_common_init_commit_hw - make rcb common init completed + *@rcb_common: rcb common device + */ +void hns_rcb_common_init_commit_hw(struct rcb_common_cb *rcb_common) +{ + wmb(); /* Sync point before breakpoint */ + dsaf_write_dev(rcb_common, RCB_COM_CFG_SYS_FSH_REG, 1); + wmb(); /* Sync point after breakpoint */ +} + +/** + *hns_rcb_ring_init - init rcb ring + *@ring_pair: ring pair control block + *@ring_type: ring type, RX_RING or TX_RING + */ +static void hns_rcb_ring_init(struct ring_pair_cb *ring_pair, int ring_type) +{ + struct hnae_queue *q = &ring_pair->q; + struct rcb_common_cb *rcb_common = ring_pair->rcb_common; + u32 bd_size_type = rcb_common->dsaf_dev->buf_size_type; + struct hnae_ring *ring = + (ring_type == RX_RING) ? &q->rx_ring : &q->tx_ring; + dma_addr_t dma = ring->desc_dma_addr; + + if (ring_type == RX_RING) { + dsaf_write_dev(q, RCB_RING_RX_RING_BASEADDR_L_REG, + (u32)dma); + dsaf_write_dev(q, RCB_RING_RX_RING_BASEADDR_H_REG, + (u32)((dma >> 31) >> 1)); + dsaf_write_dev(q, RCB_RING_RX_RING_BD_LEN_REG, + bd_size_type); + dsaf_write_dev(q, RCB_RING_RX_RING_BD_NUM_REG, + ring_pair->port_id_in_dsa); + dsaf_write_dev(q, RCB_RING_RX_RING_PKTLINE_REG, + ring_pair->port_id_in_dsa); + } else { + dsaf_write_dev(q, RCB_RING_TX_RING_BASEADDR_L_REG, + (u32)dma); + dsaf_write_dev(q, RCB_RING_TX_RING_BASEADDR_H_REG, + (u32)((dma >> 31) >> 1)); + dsaf_write_dev(q, RCB_RING_TX_RING_BD_LEN_REG, + bd_size_type); + dsaf_write_dev(q, RCB_RING_TX_RING_BD_NUM_REG, + ring_pair->port_id_in_dsa); + dsaf_write_dev(q, RCB_RING_TX_RING_PKTLINE_REG, + ring_pair->port_id_in_dsa); + } +} + +/** + *hns_rcb_init_hw - init rcb hardware + *@ring: rcb ring + */ +void hns_rcb_init_hw(struct ring_pair_cb *ring) +{ + hns_rcb_ring_init(ring, RX_RING); + hns_rcb_ring_init(ring, TX_RING); +} + +/** + *hns_rcb_set_port_desc_cnt - set rcb port description num + *@rcb_common: rcb_common device + *@port_idx:port index + *@desc_cnt:BD num + */ +static void hns_rcb_set_port_desc_cnt(struct rcb_common_cb *rcb_common, + u32 port_idx, u32 desc_cnt) +{ + if (port_idx >= HNS_RCB_SERVICE_NW_ENGINE_NUM) + port_idx = 0; + + dsaf_write_dev(rcb_common, RCB_CFG_BD_NUM_REG + port_idx * 4, + desc_cnt); +} + +/** + *hns_rcb_set_port_coalesced_frames - set rcb port coalesced frames + *@rcb_common: rcb_common device + *@port_idx:port index + *@coalesced_frames:BD num for coalesced frames + */ +static int hns_rcb_set_port_coalesced_frames(struct rcb_common_cb *rcb_common, + u32 port_idx, + u32 coalesced_frames) +{ + if (port_idx >= HNS_RCB_SERVICE_NW_ENGINE_NUM) + port_idx = 0; + if (coalesced_frames >= rcb_common->desc_num || + coalesced_frames > HNS_RCB_MAX_COALESCED_FRAMES) + return -EINVAL; + + dsaf_write_dev(rcb_common, RCB_CFG_PKTLINE_REG + port_idx * 4, + coalesced_frames); + return 0; +} + +/** + *hns_rcb_get_port_coalesced_frames - set rcb port coalesced frames + *@rcb_common: rcb_common device + *@port_idx:port index + * return coaleseced frames value + */ +static u32 hns_rcb_get_port_coalesced_frames(struct rcb_common_cb *rcb_common, + u32 port_idx) +{ + if (port_idx >= HNS_RCB_SERVICE_NW_ENGINE_NUM) + port_idx = 0; + + return dsaf_read_dev(rcb_common, + RCB_CFG_PKTLINE_REG + port_idx * 4); +} + +/** + *hns_rcb_set_timeout - set rcb port coalesced time_out + *@rcb_common: rcb_common device + *@time_out:time for coalesced time_out + */ +static void hns_rcb_set_timeout(struct rcb_common_cb *rcb_common, + u32 timeout) +{ + dsaf_write_dev(rcb_common, RCB_CFG_OVERTIME_REG, timeout); +} + +static int hns_rcb_common_get_port_num(struct rcb_common_cb *rcb_common) +{ + if (rcb_common->comm_index == HNS_DSAF_COMM_SERVICE_NW_IDX) + return HNS_RCB_SERVICE_NW_ENGINE_NUM; + else + return HNS_RCB_DEBUG_NW_ENGINE_NUM; +} + +/*clr rcb comm exception irq**/ +static void hns_rcb_comm_exc_irq_en( + struct rcb_common_cb *rcb_common, int en) +{ + u32 clr_vlue = 0xfffffffful; + u32 msk_vlue = en ? 0 : 0xfffffffful; + + /* clr int*/ + dsaf_write_dev(rcb_common, RCB_COM_INTSTS_ECC_ERR_REG, clr_vlue); + + dsaf_write_dev(rcb_common, RCB_COM_SF_CFG_RING_STS, clr_vlue); + + dsaf_write_dev(rcb_common, RCB_COM_SF_CFG_BD_RINT_STS, clr_vlue); + + dsaf_write_dev(rcb_common, RCB_COM_RINT_TX_PKT_REG, clr_vlue); + dsaf_write_dev(rcb_common, RCB_COM_AXI_ERR_STS, clr_vlue); + + /*en msk*/ + dsaf_write_dev(rcb_common, RCB_COM_INTMASK_ECC_ERR_REG, msk_vlue); + + dsaf_write_dev(rcb_common, RCB_COM_SF_CFG_INTMASK_RING, msk_vlue); + + /*for tx bd neednot cacheline, so msk sf_txring_fbd_intmask (bit 1)**/ + dsaf_write_dev(rcb_common, RCB_COM_SF_CFG_INTMASK_BD, msk_vlue | 2); + + dsaf_write_dev(rcb_common, RCB_COM_INTMSK_TX_PKT_REG, msk_vlue); + dsaf_write_dev(rcb_common, RCB_COM_AXI_WR_ERR_INTMASK, msk_vlue); +} + +/** + *hns_rcb_common_init_hw - init rcb common hardware + *@rcb_common: rcb_common device + *retuen 0 - success , negative --fail + */ +int hns_rcb_common_init_hw(struct rcb_common_cb *rcb_common) +{ + u32 reg_val; + int i; + int port_num = hns_rcb_common_get_port_num(rcb_common); + + hns_rcb_comm_exc_irq_en(rcb_common, 0); + + reg_val = dsaf_read_dev(rcb_common, RCB_COM_CFG_INIT_FLAG_REG); + if (0x1 != (reg_val & 0x1)) { + dev_err(rcb_common->dsaf_dev->dev, + "RCB_COM_CFG_INIT_FLAG_REG reg = 0x%x\n", reg_val); + return -EBUSY; + } + + for (i = 0; i < port_num; i++) { + hns_rcb_set_port_desc_cnt(rcb_common, i, rcb_common->desc_num); + (void)hns_rcb_set_port_coalesced_frames( + rcb_common, i, rcb_common->coalesced_frames); + } + hns_rcb_set_timeout(rcb_common, rcb_common->timeout); + + dsaf_write_dev(rcb_common, RCB_COM_CFG_ENDIAN_REG, + HNS_RCB_COMMON_ENDIAN); + + return 0; +} + +int hns_rcb_buf_size2type(u32 buf_size) +{ + int bd_size_type; + + switch (buf_size) { + case 512: + bd_size_type = HNS_BD_SIZE_512_TYPE; + break; + case 1024: + bd_size_type = HNS_BD_SIZE_1024_TYPE; + break; + case 2048: + bd_size_type = HNS_BD_SIZE_2048_TYPE; + break; + case 4096: + bd_size_type = HNS_BD_SIZE_4096_TYPE; + break; + default: + bd_size_type = -EINVAL; + } + + return bd_size_type; +} + +static void hns_rcb_ring_get_cfg(struct hnae_queue *q, int ring_type) +{ + struct hnae_ring *ring; + struct rcb_common_cb *rcb_common; + struct ring_pair_cb *ring_pair_cb; + u32 buf_size; + u16 desc_num; + int irq_idx; + + ring_pair_cb = container_of(q, struct ring_pair_cb, q); + if (ring_type == RX_RING) { + ring = &q->rx_ring; + ring->io_base = ring_pair_cb->q.io_base; + irq_idx = HNS_RCB_IRQ_IDX_RX; + } else { + ring = &q->tx_ring; + ring->io_base = (u8 __iomem *)ring_pair_cb->q.io_base + + HNS_RCB_TX_REG_OFFSET; + irq_idx = HNS_RCB_IRQ_IDX_TX; + } + + rcb_common = ring_pair_cb->rcb_common; + buf_size = rcb_common->dsaf_dev->buf_size; + desc_num = rcb_common->dsaf_dev->desc_num; + + ring->desc = NULL; + ring->desc_cb = NULL; + + ring->irq = ring_pair_cb->virq[irq_idx]; + ring->desc_dma_addr = 0; + + ring->buf_size = buf_size; + ring->desc_num = desc_num; + ring->max_desc_num_per_pkt = HNS_RCB_RING_MAX_BD_PER_PKT; + ring->max_raw_data_sz_per_desc = HNS_RCB_MAX_PKT_SIZE; + ring->max_pkt_size = HNS_RCB_MAX_PKT_SIZE; + ring->next_to_use = 0; + ring->next_to_clean = 0; +} + +static void hns_rcb_ring_pair_get_cfg(struct ring_pair_cb *ring_pair_cb) +{ + ring_pair_cb->q.handle = NULL; + + hns_rcb_ring_get_cfg(&ring_pair_cb->q, RX_RING); + hns_rcb_ring_get_cfg(&ring_pair_cb->q, TX_RING); +} + +static int hns_rcb_get_port(struct rcb_common_cb *rcb_common, int ring_idx) +{ + int comm_index = rcb_common->comm_index; + int port; + int q_num; + + if (comm_index == HNS_DSAF_COMM_SERVICE_NW_IDX) { + q_num = (int)rcb_common->max_q_per_vf * rcb_common->max_vfn; + port = ring_idx / q_num; + } else { + port = HNS_RCB_SERVICE_NW_ENGINE_NUM + comm_index - 1; + } + + return port; +} + +static int hns_rcb_get_base_irq_idx(struct rcb_common_cb *rcb_common) +{ + int comm_index = rcb_common->comm_index; + + if (comm_index == HNS_DSAF_COMM_SERVICE_NW_IDX) + return HNS_SERVICE_RING_IRQ_IDX; + else + return HNS_DEBUG_RING_IRQ_IDX + (comm_index - 1) * 2; +} + +#define RCB_COMM_BASE_TO_RING_BASE(base, ringid)\ + ((base) + 0x10000 + HNS_RCB_REG_OFFSET * (ringid)) +/** + *hns_rcb_get_cfg - get rcb config + *@rcb_common: rcb common device + */ +void hns_rcb_get_cfg(struct rcb_common_cb *rcb_common) +{ + struct ring_pair_cb *ring_pair_cb; + u32 i; + u32 ring_num = rcb_common->ring_num; + int base_irq_idx = hns_rcb_get_base_irq_idx(rcb_common); + struct device_node *np = rcb_common->dsaf_dev->dev->of_node; + + for (i = 0; i < ring_num; i++) { + ring_pair_cb = &rcb_common->ring_pair_cb[i]; + ring_pair_cb->rcb_common = rcb_common; + ring_pair_cb->dev = rcb_common->dsaf_dev->dev; + ring_pair_cb->index = i; + ring_pair_cb->q.io_base = + RCB_COMM_BASE_TO_RING_BASE(rcb_common->io_base, i); + ring_pair_cb->port_id_in_dsa = hns_rcb_get_port(rcb_common, i); + ring_pair_cb->virq[HNS_RCB_IRQ_IDX_TX] + = irq_of_parse_and_map(np, base_irq_idx + i * 2); + ring_pair_cb->virq[HNS_RCB_IRQ_IDX_RX] + = irq_of_parse_and_map(np, base_irq_idx + i * 2 + 1); + ring_pair_cb->q.phy_base = + RCB_COMM_BASE_TO_RING_BASE(rcb_common->phy_base, i); + hns_rcb_ring_pair_get_cfg(ring_pair_cb); + } +} + +/** + *hns_rcb_get_coalesced_frames - get rcb port coalesced frames + *@rcb_common: rcb_common device + *@comm_index:port index + *return coalesced_frames + */ +u32 hns_rcb_get_coalesced_frames(struct dsaf_device *dsaf_dev, int port) +{ + int comm_index = hns_dsaf_get_comm_idx_by_port(port); + struct rcb_common_cb *rcb_comm = dsaf_dev->rcb_common[comm_index]; + + return hns_rcb_get_port_coalesced_frames(rcb_comm, port); +} + +/** + *hns_rcb_get_coalesce_usecs - get rcb port coalesced time_out + *@rcb_common: rcb_common device + *@comm_index:port index + *return time_out + */ +u32 hns_rcb_get_coalesce_usecs(struct dsaf_device *dsaf_dev, int comm_index) +{ + struct rcb_common_cb *rcb_comm = dsaf_dev->rcb_common[comm_index]; + + return rcb_comm->timeout; +} + +/** + *hns_rcb_set_coalesce_usecs - set rcb port coalesced time_out + *@rcb_common: rcb_common device + *@comm_index: comm :index + *@etx_usecs:tx time for coalesced time_out + *@rx_usecs:rx time for coalesced time_out + */ +void hns_rcb_set_coalesce_usecs(struct dsaf_device *dsaf_dev, + int port, u32 timeout) +{ + int comm_index = hns_dsaf_get_comm_idx_by_port(port); + struct rcb_common_cb *rcb_comm = dsaf_dev->rcb_common[comm_index]; + + if (rcb_comm->timeout == timeout) + return; + + if (comm_index == HNS_DSAF_COMM_SERVICE_NW_IDX) { + dev_err(dsaf_dev->dev, + "error: not support coalesce_usecs setting!\n"); + return; + } + rcb_comm->timeout = timeout; + hns_rcb_set_timeout(rcb_comm, rcb_comm->timeout); +} + +/** + *hns_rcb_set_coalesced_frames - set rcb coalesced frames + *@rcb_common: rcb_common device + *@tx_frames:tx BD num for coalesced frames + *@rx_frames:rx BD num for coalesced frames + *Return 0 on success, negative on failure + */ +int hns_rcb_set_coalesced_frames(struct dsaf_device *dsaf_dev, + int port, u32 coalesced_frames) +{ + int comm_index = hns_dsaf_get_comm_idx_by_port(port); + struct rcb_common_cb *rcb_comm = dsaf_dev->rcb_common[comm_index]; + u32 coalesced_reg_val; + int ret; + + coalesced_reg_val = hns_rcb_get_port_coalesced_frames(rcb_comm, port); + + if (coalesced_reg_val == coalesced_frames) + return 0; + + if (coalesced_frames >= HNS_RCB_MIN_COALESCED_FRAMES) { + ret = hns_rcb_set_port_coalesced_frames(rcb_comm, port, + coalesced_frames); + return ret; + } else { + return -EINVAL; + } +} + +/** + *hns_rcb_get_queue_mode - get max VM number and max ring number per VM + * accordding to dsaf mode + *@dsaf_mode: dsaf mode + *@max_vfn : max vfn number + *@max_q_per_vf:max ring number per vm + */ +static void hns_rcb_get_queue_mode(enum dsaf_mode dsaf_mode, int comm_index, + u16 *max_vfn, u16 *max_q_per_vf) +{ + if (comm_index == HNS_DSAF_COMM_SERVICE_NW_IDX) { + switch (dsaf_mode) { + case DSAF_MODE_DISABLE_6PORT_0VM: + *max_vfn = 1; + *max_q_per_vf = 16; + break; + case DSAF_MODE_DISABLE_FIX: + *max_vfn = 1; + *max_q_per_vf = 1; + break; + case DSAF_MODE_DISABLE_2PORT_64VM: + *max_vfn = 64; + *max_q_per_vf = 1; + break; + case DSAF_MODE_DISABLE_6PORT_16VM: + *max_vfn = 16; + *max_q_per_vf = 1; + break; + default: + *max_vfn = 1; + *max_q_per_vf = 16; + break; + } + } else { + *max_vfn = 1; + *max_q_per_vf = 1; + } +} + +int hns_rcb_get_ring_num(struct dsaf_device *dsaf_dev, int comm_index) +{ + if (comm_index == HNS_DSAF_COMM_SERVICE_NW_IDX) { + switch (dsaf_dev->dsaf_mode) { + case DSAF_MODE_ENABLE_FIX: + return 1; + + case DSAF_MODE_DISABLE_FIX: + return 6; + + case DSAF_MODE_ENABLE_0VM: + return 32; + + case DSAF_MODE_DISABLE_6PORT_0VM: + case DSAF_MODE_ENABLE_16VM: + case DSAF_MODE_DISABLE_6PORT_2VM: + case DSAF_MODE_DISABLE_6PORT_16VM: + case DSAF_MODE_DISABLE_6PORT_4VM: + case DSAF_MODE_ENABLE_8VM: + return 96; + + case DSAF_MODE_DISABLE_2PORT_16VM: + case DSAF_MODE_DISABLE_2PORT_8VM: + case DSAF_MODE_ENABLE_32VM: + case DSAF_MODE_DISABLE_2PORT_64VM: + case DSAF_MODE_ENABLE_128VM: + return 128; + + default: + dev_warn(dsaf_dev->dev, + "get ring num fail,use default!dsaf_mode=%d\n", + dsaf_dev->dsaf_mode); + return 128; + } + } else { + return 1; + } +} + +void __iomem *hns_rcb_common_get_vaddr(struct dsaf_device *dsaf_dev, + int comm_index) +{ + void __iomem *base_addr; + + if (comm_index == HNS_DSAF_COMM_SERVICE_NW_IDX) + base_addr = dsaf_dev->ppe_base + RCB_COMMON_REG_OFFSET; + else + base_addr = dsaf_dev->sds_base + + (comm_index - 1) * HNS_DSAF_DEBUG_NW_REG_OFFSET + + RCB_COMMON_REG_OFFSET; + + return base_addr; +} + +static phys_addr_t hns_rcb_common_get_paddr(struct dsaf_device *dsaf_dev, + int comm_index) +{ + struct device_node *np = dsaf_dev->dev->of_node; + phys_addr_t phy_addr; + const __be32 *tmp_addr; + u64 addr_offset = 0; + u64 size = 0; + int index = 0; + + if (comm_index == HNS_DSAF_COMM_SERVICE_NW_IDX) { + index = 2; + addr_offset = RCB_COMMON_REG_OFFSET; + } else { + index = 1; + addr_offset = (comm_index - 1) * HNS_DSAF_DEBUG_NW_REG_OFFSET + + RCB_COMMON_REG_OFFSET; + } + tmp_addr = of_get_address(np, index, &size, NULL); + phy_addr = of_translate_address(np, tmp_addr); + return phy_addr + addr_offset; +} + +int hns_rcb_common_get_cfg(struct dsaf_device *dsaf_dev, + int comm_index) +{ + struct rcb_common_cb *rcb_common; + enum dsaf_mode dsaf_mode = dsaf_dev->dsaf_mode; + u16 max_vfn; + u16 max_q_per_vf; + int ring_num = hns_rcb_get_ring_num(dsaf_dev, comm_index); + + rcb_common = + devm_kzalloc(dsaf_dev->dev, sizeof(*rcb_common) + + ring_num * sizeof(struct ring_pair_cb), GFP_KERNEL); + if (!rcb_common) { + dev_err(dsaf_dev->dev, "rcb common devm_kzalloc fail!\n"); + return -ENOMEM; + } + rcb_common->comm_index = comm_index; + rcb_common->ring_num = ring_num; + rcb_common->dsaf_dev = dsaf_dev; + + rcb_common->desc_num = dsaf_dev->desc_num; + rcb_common->coalesced_frames = HNS_RCB_DEF_COALESCED_FRAMES; + rcb_common->timeout = HNS_RCB_MAX_TIME_OUT; + + hns_rcb_get_queue_mode(dsaf_mode, comm_index, &max_vfn, &max_q_per_vf); + rcb_common->max_vfn = max_vfn; + rcb_common->max_q_per_vf = max_q_per_vf; + + rcb_common->io_base = hns_rcb_common_get_vaddr(dsaf_dev, comm_index); + rcb_common->phy_base = hns_rcb_common_get_paddr(dsaf_dev, comm_index); + + dsaf_dev->rcb_common[comm_index] = rcb_common; + return 0; +} + +void hns_rcb_common_free_cfg(struct dsaf_device *dsaf_dev, + u32 comm_index) +{ + dsaf_dev->rcb_common[comm_index] = NULL; +} + +void hns_rcb_update_stats(struct hnae_queue *queue) +{ + struct ring_pair_cb *ring = + container_of(queue, struct ring_pair_cb, q); + struct dsaf_device *dsaf_dev = ring->rcb_common->dsaf_dev; + struct ppe_common_cb *ppe_common + = dsaf_dev->ppe_common[ring->rcb_common->comm_index]; + struct hns_ring_hw_stats *hw_stats = &ring->hw_stats; + + hw_stats->rx_pkts += dsaf_read_dev(queue, + RCB_RING_RX_RING_PKTNUM_RECORD_REG); + dsaf_write_dev(queue, RCB_RING_RX_RING_PKTNUM_RECORD_REG, 0x1); + + hw_stats->ppe_rx_ok_pkts += dsaf_read_dev(ppe_common, + PPE_COM_HIS_RX_PKT_QID_OK_CNT_REG + 4 * ring->index); + hw_stats->ppe_rx_drop_pkts += dsaf_read_dev(ppe_common, + PPE_COM_HIS_RX_PKT_QID_DROP_CNT_REG + 4 * ring->index); + + hw_stats->tx_pkts += dsaf_read_dev(queue, + RCB_RING_TX_RING_PKTNUM_RECORD_REG); + dsaf_write_dev(queue, RCB_RING_TX_RING_PKTNUM_RECORD_REG, 0x1); + + hw_stats->ppe_tx_ok_pkts += dsaf_read_dev(ppe_common, + PPE_COM_HIS_TX_PKT_QID_OK_CNT_REG + 4 * ring->index); + hw_stats->ppe_tx_drop_pkts += dsaf_read_dev(ppe_common, + PPE_COM_HIS_TX_PKT_QID_ERR_CNT_REG + 4 * ring->index); +} + +/** + *hns_rcb_get_stats - get rcb statistic + *@ring: rcb ring + *@data:statistic value + */ +void hns_rcb_get_stats(struct hnae_queue *queue, u64 *data) +{ + u64 *regs_buff = data; + struct ring_pair_cb *ring = + container_of(queue, struct ring_pair_cb, q); + struct hns_ring_hw_stats *hw_stats = &ring->hw_stats; + + regs_buff[0] = hw_stats->tx_pkts; + regs_buff[1] = hw_stats->ppe_tx_ok_pkts; + regs_buff[2] = hw_stats->ppe_tx_drop_pkts; + regs_buff[3] = + dsaf_read_dev(queue, RCB_RING_TX_RING_FBDNUM_REG); + + regs_buff[4] = queue->tx_ring.stats.tx_pkts; + regs_buff[5] = queue->tx_ring.stats.tx_bytes; + regs_buff[6] = queue->tx_ring.stats.tx_err_cnt; + regs_buff[7] = queue->tx_ring.stats.io_err_cnt; + regs_buff[8] = queue->tx_ring.stats.sw_err_cnt; + regs_buff[9] = queue->tx_ring.stats.seg_pkt_cnt; + regs_buff[10] = queue->tx_ring.stats.restart_queue; + regs_buff[11] = queue->tx_ring.stats.tx_busy; + + regs_buff[12] = hw_stats->rx_pkts; + regs_buff[13] = hw_stats->ppe_rx_ok_pkts; + regs_buff[14] = hw_stats->ppe_rx_drop_pkts; + regs_buff[15] = + dsaf_read_dev(queue, RCB_RING_RX_RING_FBDNUM_REG); + + regs_buff[16] = queue->rx_ring.stats.rx_pkts; + regs_buff[17] = queue->rx_ring.stats.rx_bytes; + regs_buff[18] = queue->rx_ring.stats.rx_err_cnt; + regs_buff[19] = queue->rx_ring.stats.io_err_cnt; + regs_buff[20] = queue->rx_ring.stats.sw_err_cnt; + regs_buff[21] = queue->rx_ring.stats.seg_pkt_cnt; + regs_buff[22] = queue->rx_ring.stats.reuse_pg_cnt; + regs_buff[23] = queue->rx_ring.stats.err_pkt_len; + regs_buff[24] = queue->rx_ring.stats.non_vld_descs; + regs_buff[25] = queue->rx_ring.stats.err_bd_num; + regs_buff[26] = queue->rx_ring.stats.l2_err; + regs_buff[27] = queue->rx_ring.stats.l3l4_csum_err; +} + +/** + *hns_rcb_get_ring_sset_count - rcb string set count + *@stringset:ethtool cmd + *return rcb ring string set count + */ +int hns_rcb_get_ring_sset_count(int stringset) +{ + if (stringset == ETH_SS_STATS) + return HNS_RING_STATIC_REG_NUM; + + return 0; +} + +/** + *hns_rcb_get_common_regs_count - rcb common regs count + *return regs count + */ +int hns_rcb_get_common_regs_count(void) +{ + return HNS_RCB_COMMON_DUMP_REG_NUM; +} + +/** + *rcb_get_sset_count - rcb ring regs count + *return regs count + */ +int hns_rcb_get_ring_regs_count(void) +{ + return HNS_RCB_RING_DUMP_REG_NUM; +} + +/** + *hns_rcb_get_strings - get rcb string set + *@stringset:string set index + *@data:strings name value + *@index:queue index + */ +void hns_rcb_get_strings(int stringset, u8 *data, int index) +{ + char *buff = (char *)data; + + if (stringset != ETH_SS_STATS) + return; + + snprintf(buff, ETH_GSTRING_LEN, "tx_ring%d_rcb_pkt_num", index); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "tx_ring%d_ppe_tx_pkt_num", index); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "tx_ring%d_ppe_drop_pkt_num", index); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "tx_ring%d_fbd_num", index); + buff = buff + ETH_GSTRING_LEN; + + snprintf(buff, ETH_GSTRING_LEN, "tx_ring%d_pkt_num", index); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "tx_ring%d_bytes", index); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "tx_ring%d_err_cnt", index); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "tx_ring%d_io_err", index); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "tx_ring%d_sw_err", index); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "tx_ring%d_seg_pkt", index); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "tx_ring%d_restart_queue", index); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "tx_ring%d_tx_busy", index); + buff = buff + ETH_GSTRING_LEN; + + snprintf(buff, ETH_GSTRING_LEN, "rx_ring%d_rcb_pkt_num", index); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "rx_ring%d_ppe_pkt_num", index); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "rx_ring%d_ppe_drop_pkt_num", index); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "rx_ring%d_fbd_num", index); + buff = buff + ETH_GSTRING_LEN; + + snprintf(buff, ETH_GSTRING_LEN, "rx_ring%d_pkt_num", index); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "rx_ring%d_bytes", index); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "rx_ring%d_err_cnt", index); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "rx_ring%d_io_err", index); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "rx_ring%d_sw_err", index); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "rx_ring%d_seg_pkt", index); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "rx_ring%d_reuse_pg", index); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "rx_ring%d_len_err", index); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "rx_ring%d_non_vld_desc_err", index); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "rx_ring%d_bd_num_err", index); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "rx_ring%d_l2_err", index); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "rx_ring%d_l3l4csum_err", index); +} + +void hns_rcb_get_common_regs(struct rcb_common_cb *rcb_com, void *data) +{ + u32 *regs = data; + u32 i = 0; + + /*rcb common registers */ + regs[0] = dsaf_read_dev(rcb_com, RCB_COM_CFG_ENDIAN_REG); + regs[1] = dsaf_read_dev(rcb_com, RCB_COM_CFG_SYS_FSH_REG); + regs[2] = dsaf_read_dev(rcb_com, RCB_COM_CFG_INIT_FLAG_REG); + + regs[3] = dsaf_read_dev(rcb_com, RCB_COM_CFG_PKT_REG); + regs[4] = dsaf_read_dev(rcb_com, RCB_COM_CFG_RINVLD_REG); + regs[5] = dsaf_read_dev(rcb_com, RCB_COM_CFG_FNA_REG); + regs[6] = dsaf_read_dev(rcb_com, RCB_COM_CFG_FA_REG); + regs[7] = dsaf_read_dev(rcb_com, RCB_COM_CFG_PKT_TC_BP_REG); + regs[8] = dsaf_read_dev(rcb_com, RCB_COM_CFG_PPE_TNL_CLKEN_REG); + + regs[9] = dsaf_read_dev(rcb_com, RCB_COM_INTMSK_TX_PKT_REG); + regs[10] = dsaf_read_dev(rcb_com, RCB_COM_RINT_TX_PKT_REG); + regs[11] = dsaf_read_dev(rcb_com, RCB_COM_INTMASK_ECC_ERR_REG); + regs[12] = dsaf_read_dev(rcb_com, RCB_COM_INTSTS_ECC_ERR_REG); + regs[13] = dsaf_read_dev(rcb_com, RCB_COM_EBD_SRAM_ERR_REG); + regs[14] = dsaf_read_dev(rcb_com, RCB_COM_RXRING_ERR_REG); + regs[15] = dsaf_read_dev(rcb_com, RCB_COM_TXRING_ERR_REG); + regs[16] = dsaf_read_dev(rcb_com, RCB_COM_TX_FBD_ERR_REG); + regs[17] = dsaf_read_dev(rcb_com, RCB_SRAM_ECC_CHK_EN_REG); + regs[18] = dsaf_read_dev(rcb_com, RCB_SRAM_ECC_CHK0_REG); + regs[19] = dsaf_read_dev(rcb_com, RCB_SRAM_ECC_CHK1_REG); + regs[20] = dsaf_read_dev(rcb_com, RCB_SRAM_ECC_CHK2_REG); + regs[21] = dsaf_read_dev(rcb_com, RCB_SRAM_ECC_CHK3_REG); + regs[22] = dsaf_read_dev(rcb_com, RCB_SRAM_ECC_CHK4_REG); + regs[23] = dsaf_read_dev(rcb_com, RCB_SRAM_ECC_CHK5_REG); + regs[24] = dsaf_read_dev(rcb_com, RCB_ECC_ERR_ADDR0_REG); + regs[25] = dsaf_read_dev(rcb_com, RCB_ECC_ERR_ADDR3_REG); + regs[26] = dsaf_read_dev(rcb_com, RCB_ECC_ERR_ADDR4_REG); + regs[27] = dsaf_read_dev(rcb_com, RCB_ECC_ERR_ADDR5_REG); + + regs[28] = dsaf_read_dev(rcb_com, RCB_COM_SF_CFG_INTMASK_RING); + regs[29] = dsaf_read_dev(rcb_com, RCB_COM_SF_CFG_RING_STS); + regs[30] = dsaf_read_dev(rcb_com, RCB_COM_SF_CFG_RING); + regs[31] = dsaf_read_dev(rcb_com, RCB_COM_SF_CFG_INTMASK_BD); + regs[32] = dsaf_read_dev(rcb_com, RCB_COM_SF_CFG_BD_RINT_STS); + regs[33] = dsaf_read_dev(rcb_com, RCB_COM_RCB_RD_BD_BUSY); + regs[34] = dsaf_read_dev(rcb_com, RCB_COM_RCB_FBD_CRT_EN); + regs[35] = dsaf_read_dev(rcb_com, RCB_COM_AXI_WR_ERR_INTMASK); + regs[36] = dsaf_read_dev(rcb_com, RCB_COM_AXI_ERR_STS); + regs[37] = dsaf_read_dev(rcb_com, RCB_COM_CHK_TX_FBD_NUM_REG); + + /* rcb common entry registers */ + for (i = 0; i < 16; i++) { /* total 16 model registers */ + regs[38 + i] + = dsaf_read_dev(rcb_com, RCB_CFG_BD_NUM_REG + 4 * i); + regs[54 + i] + = dsaf_read_dev(rcb_com, RCB_CFG_PKTLINE_REG + 4 * i); + } + + regs[70] = dsaf_read_dev(rcb_com, RCB_CFG_OVERTIME_REG); + regs[71] = dsaf_read_dev(rcb_com, RCB_CFG_PKTLINE_INT_NUM_REG); + regs[72] = dsaf_read_dev(rcb_com, RCB_CFG_OVERTIME_INT_NUM_REG); + + /* mark end of rcb common regs */ + for (i = 73; i < 80; i++) + regs[i] = 0xcccccccc; +} + +void hns_rcb_get_ring_regs(struct hnae_queue *queue, void *data) +{ + u32 *regs = data; + struct ring_pair_cb *ring_pair + = container_of(queue, struct ring_pair_cb, q); + u32 i = 0; + + /*rcb ring registers */ + regs[0] = dsaf_read_dev(queue, RCB_RING_RX_RING_BASEADDR_L_REG); + regs[1] = dsaf_read_dev(queue, RCB_RING_RX_RING_BASEADDR_H_REG); + regs[2] = dsaf_read_dev(queue, RCB_RING_RX_RING_BD_NUM_REG); + regs[3] = dsaf_read_dev(queue, RCB_RING_RX_RING_BD_LEN_REG); + regs[4] = dsaf_read_dev(queue, RCB_RING_RX_RING_PKTLINE_REG); + regs[5] = dsaf_read_dev(queue, RCB_RING_RX_RING_TAIL_REG); + regs[6] = dsaf_read_dev(queue, RCB_RING_RX_RING_HEAD_REG); + regs[7] = dsaf_read_dev(queue, RCB_RING_RX_RING_FBDNUM_REG); + regs[8] = dsaf_read_dev(queue, RCB_RING_RX_RING_PKTNUM_RECORD_REG); + + regs[9] = dsaf_read_dev(queue, RCB_RING_TX_RING_BASEADDR_L_REG); + regs[10] = dsaf_read_dev(queue, RCB_RING_TX_RING_BASEADDR_H_REG); + regs[11] = dsaf_read_dev(queue, RCB_RING_TX_RING_BD_NUM_REG); + regs[12] = dsaf_read_dev(queue, RCB_RING_TX_RING_BD_LEN_REG); + regs[13] = dsaf_read_dev(queue, RCB_RING_TX_RING_PKTLINE_REG); + regs[15] = dsaf_read_dev(queue, RCB_RING_TX_RING_TAIL_REG); + regs[16] = dsaf_read_dev(queue, RCB_RING_TX_RING_HEAD_REG); + regs[17] = dsaf_read_dev(queue, RCB_RING_TX_RING_FBDNUM_REG); + regs[18] = dsaf_read_dev(queue, RCB_RING_TX_RING_OFFSET_REG); + regs[19] = dsaf_read_dev(queue, RCB_RING_TX_RING_PKTNUM_RECORD_REG); + + regs[20] = dsaf_read_dev(queue, RCB_RING_PREFETCH_EN_REG); + regs[21] = dsaf_read_dev(queue, RCB_RING_CFG_VF_NUM_REG); + regs[22] = dsaf_read_dev(queue, RCB_RING_ASID_REG); + regs[23] = dsaf_read_dev(queue, RCB_RING_RX_VM_REG); + regs[24] = dsaf_read_dev(queue, RCB_RING_T0_BE_RST); + regs[25] = dsaf_read_dev(queue, RCB_RING_COULD_BE_RST); + regs[26] = dsaf_read_dev(queue, RCB_RING_WRR_WEIGHT_REG); + + regs[27] = dsaf_read_dev(queue, RCB_RING_INTMSK_RXWL_REG); + regs[28] = dsaf_read_dev(queue, RCB_RING_INTSTS_RX_RING_REG); + regs[29] = dsaf_read_dev(queue, RCB_RING_INTMSK_TXWL_REG); + regs[30] = dsaf_read_dev(queue, RCB_RING_INTSTS_TX_RING_REG); + regs[31] = dsaf_read_dev(queue, RCB_RING_INTMSK_RX_OVERTIME_REG); + regs[32] = dsaf_read_dev(queue, RCB_RING_INTSTS_RX_OVERTIME_REG); + regs[33] = dsaf_read_dev(queue, RCB_RING_INTMSK_TX_OVERTIME_REG); + regs[34] = dsaf_read_dev(queue, RCB_RING_INTSTS_TX_OVERTIME_REG); + + /* mark end of ring regs */ + for (i = 35; i < 40; i++) + regs[i] = 0xcccccc00 + ring_pair->index; +} diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h new file mode 100644 index 000000000000..c7db6130a3cf --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h @@ -0,0 +1,137 @@ +/* + * Copyright (c) 2014-2015 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef _HNS_DSAF_RCB_H +#define _HNS_DSAF_RCB_H + +#include <linux/netdevice.h> +#include <linux/platform_device.h> + +#include "hnae.h" +#include "hns_dsaf_main.h" + +struct rcb_common_cb; + +#define HNS_RCB_IRQ_NUM_PER_QUEUE 2 +#define HNS_RCB_IRQ_IDX_TX 0 +#define HNS_RCB_IRQ_IDX_RX 1 +#define HNS_RCB_TX_REG_OFFSET 0x40 + +#define HNS_RCB_SERVICE_NW_ENGINE_NUM DSAF_COMM_CHN +#define HNS_RCB_DEBUG_NW_ENGINE_NUM 1 +#define HNS_RCB_RING_MAX_BD_PER_PKT 3 +#define HNS_RCB_MAX_PKT_SIZE MAC_MAX_MTU + +#define HNS_RCB_RING_MAX_PENDING_BD 1024 +#define HNS_RCB_RING_MIN_PENDING_BD 16 + +#define HNS_RCB_REG_OFFSET 0x10000 + +#define HNS_RCB_MAX_COALESCED_FRAMES 1023 +#define HNS_RCB_MIN_COALESCED_FRAMES 1 +#define HNS_RCB_DEF_COALESCED_FRAMES 50 +#define HNS_RCB_MAX_TIME_OUT 0x500 + +#define HNS_RCB_COMMON_ENDIAN 1 + +#define HNS_BD_SIZE_512_TYPE 0 +#define HNS_BD_SIZE_1024_TYPE 1 +#define HNS_BD_SIZE_2048_TYPE 2 +#define HNS_BD_SIZE_4096_TYPE 3 + +#define HNS_RCB_COMMON_DUMP_REG_NUM 80 +#define HNS_RCB_RING_DUMP_REG_NUM 40 +#define HNS_RING_STATIC_REG_NUM 28 + +#define HNS_DUMP_REG_NUM 500 +#define HNS_STATIC_REG_NUM 12 + +enum rcb_int_flag { + RCB_INT_FLAG_TX = 0x1, + RCB_INT_FLAG_RX = (0x1 << 1), + RCB_INT_FLAG_MAX = (0x1 << 2), /*must be the last element */ +}; + +struct hns_ring_hw_stats { + u64 tx_pkts; + u64 ppe_tx_ok_pkts; + u64 ppe_tx_drop_pkts; + u64 rx_pkts; + u64 ppe_rx_ok_pkts; + u64 ppe_rx_drop_pkts; +}; + +struct ring_pair_cb { + struct rcb_common_cb *rcb_common; /* ring belongs to */ + struct device *dev; /*device for DMA mapping */ + struct hnae_queue q; + + u16 index; /* global index in a rcb common device */ + u16 buf_size; + + int virq[HNS_RCB_IRQ_NUM_PER_QUEUE]; + + u8 port_id_in_dsa; + u8 used_by_vf; + + struct hns_ring_hw_stats hw_stats; +}; + +struct rcb_common_cb { + u8 __iomem *io_base; + phys_addr_t phy_base; + struct dsaf_device *dsaf_dev; + u16 max_vfn; + u16 max_q_per_vf; + + u8 comm_index; + u32 ring_num; + u32 coalesced_frames; /* frames threshold of rx interrupt */ + u32 timeout; /* time threshold of rx interrupt */ + u32 desc_num; /* desc num per queue*/ + + struct ring_pair_cb ring_pair_cb[0]; +}; + +int hns_rcb_buf_size2type(u32 buf_size); + +int hns_rcb_common_get_cfg(struct dsaf_device *dsaf_dev, int comm_index); +void hns_rcb_common_free_cfg(struct dsaf_device *dsaf_dev, u32 comm_index); +int hns_rcb_common_init_hw(struct rcb_common_cb *rcb_common); +void hns_rcb_start(struct hnae_queue *q, u32 val); +void hns_rcb_get_cfg(struct rcb_common_cb *rcb_common); +void hns_rcb_common_init_commit_hw(struct rcb_common_cb *rcb_common); + +void hns_rcb_ring_enable_hw(struct hnae_queue *q, u32 val); +void hns_rcb_int_clr_hw(struct hnae_queue *q, u32 flag); +void hns_rcb_int_ctrl_hw(struct hnae_queue *q, u32 flag, u32 enable); +void hns_rcb_init_hw(struct ring_pair_cb *ring); +void hns_rcb_reset_ring_hw(struct hnae_queue *q); +void hns_rcb_wait_fbd_clean(struct hnae_queue **qs, int q_num, u32 flag); + +u32 hns_rcb_get_coalesced_frames(struct dsaf_device *dsaf_dev, int comm_index); +u32 hns_rcb_get_coalesce_usecs(struct dsaf_device *dsaf_dev, int comm_index); +void hns_rcb_set_coalesce_usecs(struct dsaf_device *dsaf_dev, + int comm_index, u32 timeout); +int hns_rcb_set_coalesced_frames(struct dsaf_device *dsaf_dev, + int comm_index, u32 coalesce_frames); +void hns_rcb_update_stats(struct hnae_queue *queue); + +void hns_rcb_get_stats(struct hnae_queue *queue, u64 *data); + +void hns_rcb_get_common_regs(struct rcb_common_cb *rcb_common, void *data); + +int hns_rcb_get_ring_sset_count(int stringset); +int hns_rcb_get_common_regs_count(void); +int hns_rcb_get_ring_regs_count(void); + +void hns_rcb_get_ring_regs(struct hnae_queue *queue, void *data); + +void hns_rcb_get_strings(int stringset, u8 *data, int index); +#endif /* _HNS_DSAF_RCB_H */ diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h new file mode 100644 index 000000000000..b475e1bf2e6f --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h @@ -0,0 +1,972 @@ +/* + * Copyright (c) 2014-2015 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef _DSAF_REG_H_ +#define _DSAF_REG_H_ + +#define HNS_GE_FIFO_ERR_INTNUM 8 +#define HNS_XGE_ERR_INTNUM 6 +#define HNS_RCB_COMM_ERR_INTNUM 12 +#define HNS_PPE_TNL_ERR_INTNUM 8 +#define HNS_DSAF_EVENT_INTNUM 21 +#define HNS_DEBUG_RING_INTNUM 4 +#define HNS_SERVICE_RING_INTNUM 256 + +#define HNS_DEBUG_RING_IRQ_IDX (HNS_GE_FIFO_ERR_INTNUM + HNS_XGE_ERR_INTNUM +\ + HNS_RCB_COMM_ERR_INTNUM + HNS_PPE_TNL_ERR_INTNUM +\ + HNS_DSAF_EVENT_INTNUM) +#define HNS_SERVICE_RING_IRQ_IDX (HNS_DEBUG_RING_IRQ_IDX +\ + HNS_DEBUG_RING_INTNUM) + +#define DSAF_IRQ_NUM 18 + +#define DSAF_MAX_PORT_NUM_PER_CHIP 8 +#define DSAF_SERVICE_PORT_NUM_PER_DSAF 6 +#define DSAF_MAX_VM_NUM 128 + +#define DSAF_COMM_DEV_NUM 3 +#define DSAF_PPE_INODE_BASE 6 +#define HNS_DSAF_COMM_SERVICE_NW_IDX 0 +#define DSAF_DEBUG_NW_NUM 2 +#define DSAF_SERVICE_NW_NUM 6 +#define DSAF_COMM_CHN DSAF_SERVICE_NW_NUM +#define DSAF_GE_NUM ((DSAF_SERVICE_NW_NUM) + (DSAF_DEBUG_NW_NUM)) +#define DSAF_PORT_NUM ((DSAF_SERVICE_NW_NUM) + (DSAF_DEBUG_NW_NUM)) +#define DSAF_XGE_NUM DSAF_SERVICE_NW_NUM +#define DSAF_NODE_NUM 18 +#define DSAF_XOD_BIG_NUM DSAF_NODE_NUM +#define DSAF_SBM_NUM DSAF_NODE_NUM +#define DSAF_VOQ_NUM DSAF_NODE_NUM +#define DSAF_INODE_NUM DSAF_NODE_NUM +#define DSAF_XOD_NUM 8 +#define DSAF_TBL_NUM 8 +#define DSAF_SW_PORT_NUM 8 +#define DSAF_TOTAL_QUEUE_NUM 129 + +#define DSAF_TCAM_SUM 512 +#define DSAF_LINE_SUM (2048 * 14) + +#define DSAF_SUB_SC_NT_SRAM_CLK_SEL_REG 0x100 +#define DSAF_SUB_SC_HILINK3_CRG_CTRL0_REG 0x180 +#define DSAF_SUB_SC_HILINK3_CRG_CTRL1_REG 0x184 +#define DSAF_SUB_SC_HILINK3_CRG_CTRL2_REG 0x188 +#define DSAF_SUB_SC_HILINK3_CRG_CTRL3_REG 0x18C +#define DSAF_SUB_SC_HILINK4_CRG_CTRL0_REG 0x190 +#define DSAF_SUB_SC_HILINK4_CRG_CTRL1_REG 0x194 +#define DSAF_SUB_SC_DSAF_CLK_EN_REG 0x300 +#define DSAF_SUB_SC_DSAF_CLK_DIS_REG 0x304 +#define DSAF_SUB_SC_NT_CLK_EN_REG 0x308 +#define DSAF_SUB_SC_NT_CLK_DIS_REG 0x30C +#define DSAF_SUB_SC_XGE_CLK_EN_REG 0x310 +#define DSAF_SUB_SC_XGE_CLK_DIS_REG 0x314 +#define DSAF_SUB_SC_GE_CLK_EN_REG 0x318 +#define DSAF_SUB_SC_GE_CLK_DIS_REG 0x31C +#define DSAF_SUB_SC_PPE_CLK_EN_REG 0x320 +#define DSAF_SUB_SC_PPE_CLK_DIS_REG 0x324 +#define DSAF_SUB_SC_RCB_PPE_COM_CLK_EN_REG 0x350 +#define DSAF_SUB_SC_RCB_PPE_COM_CLK_DIS_REG 0x354 +#define DSAF_SUB_SC_XBAR_RESET_REQ_REG 0xA00 +#define DSAF_SUB_SC_XBAR_RESET_DREQ_REG 0xA04 +#define DSAF_SUB_SC_NT_RESET_REQ_REG 0xA08 +#define DSAF_SUB_SC_NT_RESET_DREQ_REG 0xA0C +#define DSAF_SUB_SC_XGE_RESET_REQ_REG 0xA10 +#define DSAF_SUB_SC_XGE_RESET_DREQ_REG 0xA14 +#define DSAF_SUB_SC_GE_RESET_REQ0_REG 0xA18 +#define DSAF_SUB_SC_GE_RESET_DREQ0_REG 0xA1C +#define DSAF_SUB_SC_GE_RESET_REQ1_REG 0xA20 +#define DSAF_SUB_SC_GE_RESET_DREQ1_REG 0xA24 +#define DSAF_SUB_SC_PPE_RESET_REQ_REG 0xA48 +#define DSAF_SUB_SC_PPE_RESET_DREQ_REG 0xA4C +#define DSAF_SUB_SC_RCB_PPE_COM_RESET_REQ_REG 0xA88 +#define DSAF_SUB_SC_RCB_PPE_COM_RESET_DREQ_REG 0xA8C +#define DSAF_SUB_SC_LIGHT_MODULE_DETECT_EN_REG 0x2060 +#define DSAF_SUB_SC_TCAM_MBIST_EN_REG 0x2300 +#define DSAF_SUB_SC_DSAF_CLK_ST_REG 0x5300 +#define DSAF_SUB_SC_NT_CLK_ST_REG 0x5304 +#define DSAF_SUB_SC_XGE_CLK_ST_REG 0x5308 +#define DSAF_SUB_SC_GE_CLK_ST_REG 0x530C +#define DSAF_SUB_SC_PPE_CLK_ST_REG 0x5310 +#define DSAF_SUB_SC_ROCEE_CLK_ST_REG 0x5314 +#define DSAF_SUB_SC_CPU_CLK_ST_REG 0x5318 +#define DSAF_SUB_SC_RCB_PPE_COM_CLK_ST_REG 0x5328 +#define DSAF_SUB_SC_XBAR_RESET_ST_REG 0x5A00 +#define DSAF_SUB_SC_NT_RESET_ST_REG 0x5A04 +#define DSAF_SUB_SC_XGE_RESET_ST_REG 0x5A08 +#define DSAF_SUB_SC_GE_RESET_ST0_REG 0x5A0C +#define DSAF_SUB_SC_GE_RESET_ST1_REG 0x5A10 +#define DSAF_SUB_SC_PPE_RESET_ST_REG 0x5A24 +#define DSAF_SUB_SC_RCB_PPE_COM_RESET_ST_REG 0x5A44 + +/*serdes offset**/ +#define HNS_MAC_HILINK3_REG DSAF_SUB_SC_HILINK3_CRG_CTRL0_REG +#define HNS_MAC_HILINK4_REG DSAF_SUB_SC_HILINK4_CRG_CTRL0_REG +#define HNS_MAC_LANE0_CTLEDFE_REG 0x000BFFCCULL +#define HNS_MAC_LANE1_CTLEDFE_REG 0x000BFFBCULL +#define HNS_MAC_LANE2_CTLEDFE_REG 0x000BFFACULL +#define HNS_MAC_LANE3_CTLEDFE_REG 0x000BFF9CULL +#define HNS_MAC_LANE0_STATE_REG 0x000BFFD4ULL +#define HNS_MAC_LANE1_STATE_REG 0x000BFFC4ULL +#define HNS_MAC_LANE2_STATE_REG 0x000BFFB4ULL +#define HNS_MAC_LANE3_STATE_REG 0x000BFFA4ULL + +#define HILINK_RESET_TIMOUT 10000 + +#define DSAF_SRAM_INIT_OVER_0_REG 0x0 +#define DSAF_CFG_0_REG 0x4 +#define DSAF_ECC_ERR_INVERT_0_REG 0x8 +#define DSAF_ABNORMAL_TIMEOUT_0_REG 0x1C +#define DSAF_FSM_TIMEOUT_0_REG 0x20 +#define DSAF_DSA_REG_CNT_CLR_CE_REG 0x2C +#define DSAF_DSA_SBM_INF_FIFO_THRD_REG 0x30 +#define DSAF_DSA_SRAM_1BIT_ECC_SEL_REG 0x34 +#define DSAF_DSA_SRAM_1BIT_ECC_CNT_REG 0x38 +#define DSAF_PFC_EN_0_REG 0x50 +#define DSAF_PFC_UNIT_CNT_0_REG 0x70 +#define DSAF_XGE_INT_MSK_0_REG 0x100 +#define DSAF_PPE_INT_MSK_0_REG 0x120 +#define DSAF_ROCEE_INT_MSK_0_REG 0x140 +#define DSAF_XGE_INT_SRC_0_REG 0x160 +#define DSAF_PPE_INT_SRC_0_REG 0x180 +#define DSAF_ROCEE_INT_SRC_0_REG 0x1A0 +#define DSAF_XGE_INT_STS_0_REG 0x1C0 +#define DSAF_PPE_INT_STS_0_REG 0x1E0 +#define DSAF_ROCEE_INT_STS_0_REG 0x200 +#define DSAF_PPE_QID_CFG_0_REG 0x300 +#define DSAF_SW_PORT_TYPE_0_REG 0x320 +#define DSAF_STP_PORT_TYPE_0_REG 0x340 +#define DSAF_MIX_DEF_QID_0_REG 0x360 +#define DSAF_PORT_DEF_VLAN_0_REG 0x380 +#define DSAF_VM_DEF_VLAN_0_REG 0x400 + +#define DSAF_INODE_CUT_THROUGH_CFG_0_REG 0x1000 +#define DSAF_INODE_ECC_INVERT_EN_0_REG 0x1008 +#define DSAF_INODE_ECC_ERR_ADDR_0_REG 0x100C +#define DSAF_INODE_IN_PORT_NUM_0_REG 0x1018 +#define DSAF_INODE_PRI_TC_CFG_0_REG 0x101C +#define DSAF_INODE_BP_STATUS_0_REG 0x1020 +#define DSAF_INODE_PAD_DISCARD_NUM_0_REG 0x1028 +#define DSAF_INODE_FINAL_IN_MAN_NUM_0_REG 0x102C +#define DSAF_INODE_FINAL_IN_PKT_NUM_0_REG 0x1030 +#define DSAF_INODE_SBM_PID_NUM_0_REG 0x1038 +#define DSAF_INODE_FINAL_IN_PAUSE_NUM_0_REG 0x103C +#define DSAF_INODE_SBM_RELS_NUM_0_REG 0x104C +#define DSAF_INODE_SBM_DROP_NUM_0_REG 0x1050 +#define DSAF_INODE_CRC_FALSE_NUM_0_REG 0x1054 +#define DSAF_INODE_BP_DISCARD_NUM_0_REG 0x1058 +#define DSAF_INODE_RSLT_DISCARD_NUM_0_REG 0x105C +#define DSAF_INODE_LOCAL_ADDR_FALSE_NUM_0_REG 0x1060 +#define DSAF_INODE_VOQ_OVER_NUM_0_REG 0x1068 +#define DSAF_INODE_BD_SAVE_STATUS_0_REG 0x1900 +#define DSAF_INODE_BD_ORDER_STATUS_0_REG 0x1950 +#define DSAF_INODE_SW_VLAN_TAG_DISC_0_REG 0x1A00 +#define DSAF_INODE_IN_DATA_STP_DISC_0_REG 0x1A50 +#define DSAF_INODE_GE_FC_EN_0_REG 0x1B00 +#define DSAF_INODE_VC0_IN_PKT_NUM_0_REG 0x1B50 +#define DSAF_INODE_VC1_IN_PKT_NUM_0_REG 0x1C00 + +#define DSAF_SBM_CFG_REG_0_REG 0x2000 +#define DSAF_SBM_BP_CFG_0_XGE_REG_0_REG 0x2004 +#define DSAF_SBM_BP_CFG_0_PPE_REG_0_REG 0x2304 +#define DSAF_SBM_BP_CFG_0_ROCEE_REG_0_REG 0x2604 +#define DSAF_SBM_BP_CFG_1_REG_0_REG 0x2008 +#define DSAF_SBM_BP_CFG_2_XGE_REG_0_REG 0x200C +#define DSAF_SBM_BP_CFG_2_PPE_REG_0_REG 0x230C +#define DSAF_SBM_BP_CFG_2_ROCEE_REG_0_REG 0x260C +#define DSAF_SBM_FREE_CNT_0_0_REG 0x2010 +#define DSAF_SBM_FREE_CNT_1_0_REG 0x2014 +#define DSAF_SBM_BP_CNT_0_0_REG 0x2018 +#define DSAF_SBM_BP_CNT_1_0_REG 0x201C +#define DSAF_SBM_BP_CNT_2_0_REG 0x2020 +#define DSAF_SBM_BP_CNT_3_0_REG 0x2024 +#define DSAF_SBM_INER_ST_0_REG 0x2028 +#define DSAF_SBM_MIB_REQ_FAILED_TC_0_REG 0x202C +#define DSAF_SBM_LNK_INPORT_CNT_0_REG 0x2030 +#define DSAF_SBM_LNK_DROP_CNT_0_REG 0x2034 +#define DSAF_SBM_INF_OUTPORT_CNT_0_REG 0x2038 +#define DSAF_SBM_LNK_INPORT_TC0_CNT_0_REG 0x203C +#define DSAF_SBM_LNK_INPORT_TC1_CNT_0_REG 0x2040 +#define DSAF_SBM_LNK_INPORT_TC2_CNT_0_REG 0x2044 +#define DSAF_SBM_LNK_INPORT_TC3_CNT_0_REG 0x2048 +#define DSAF_SBM_LNK_INPORT_TC4_CNT_0_REG 0x204C +#define DSAF_SBM_LNK_INPORT_TC5_CNT_0_REG 0x2050 +#define DSAF_SBM_LNK_INPORT_TC6_CNT_0_REG 0x2054 +#define DSAF_SBM_LNK_INPORT_TC7_CNT_0_REG 0x2058 +#define DSAF_SBM_LNK_REQ_CNT_0_REG 0x205C +#define DSAF_SBM_LNK_RELS_CNT_0_REG 0x2060 +#define DSAF_SBM_BP_CFG_3_REG_0_REG 0x2068 +#define DSAF_SBM_BP_CFG_4_REG_0_REG 0x206C + +#define DSAF_XOD_ETS_TSA_TC0_TC3_CFG_0_REG 0x3000 +#define DSAF_XOD_ETS_TSA_TC4_TC7_CFG_0_REG 0x3004 +#define DSAF_XOD_ETS_BW_TC0_TC3_CFG_0_REG 0x3008 +#define DSAF_XOD_ETS_BW_TC4_TC7_CFG_0_REG 0x300C +#define DSAF_XOD_ETS_BW_OFFSET_CFG_0_REG 0x3010 +#define DSAF_XOD_ETS_TOKEN_CFG_0_REG 0x3014 +#define DSAF_XOD_PFS_CFG_0_0_REG 0x3018 +#define DSAF_XOD_PFS_CFG_1_0_REG 0x301C +#define DSAF_XOD_PFS_CFG_2_0_REG 0x3020 +#define DSAF_XOD_GNT_L_0_REG 0x3024 +#define DSAF_XOD_GNT_H_0_REG 0x3028 +#define DSAF_XOD_CONNECT_STATE_0_REG 0x302C +#define DSAF_XOD_RCVPKT_CNT_0_REG 0x3030 +#define DSAF_XOD_RCVTC0_CNT_0_REG 0x3034 +#define DSAF_XOD_RCVTC1_CNT_0_REG 0x3038 +#define DSAF_XOD_RCVTC2_CNT_0_REG 0x303C +#define DSAF_XOD_RCVTC3_CNT_0_REG 0x3040 +#define DSAF_XOD_RCVVC0_CNT_0_REG 0x3044 +#define DSAF_XOD_RCVVC1_CNT_0_REG 0x3048 +#define DSAF_XOD_XGE_RCVIN0_CNT_0_REG 0x304C +#define DSAF_XOD_XGE_RCVIN1_CNT_0_REG 0x3050 +#define DSAF_XOD_XGE_RCVIN2_CNT_0_REG 0x3054 +#define DSAF_XOD_XGE_RCVIN3_CNT_0_REG 0x3058 +#define DSAF_XOD_XGE_RCVIN4_CNT_0_REG 0x305C +#define DSAF_XOD_XGE_RCVIN5_CNT_0_REG 0x3060 +#define DSAF_XOD_XGE_RCVIN6_CNT_0_REG 0x3064 +#define DSAF_XOD_XGE_RCVIN7_CNT_0_REG 0x3068 +#define DSAF_XOD_PPE_RCVIN0_CNT_0_REG 0x306C +#define DSAF_XOD_PPE_RCVIN1_CNT_0_REG 0x3070 +#define DSAF_XOD_ROCEE_RCVIN0_CNT_0_REG 0x3074 +#define DSAF_XOD_ROCEE_RCVIN1_CNT_0_REG 0x3078 +#define DSAF_XOD_FIFO_STATUS_0_REG 0x307C + +#define DSAF_VOQ_ECC_INVERT_EN_0_REG 0x4004 +#define DSAF_VOQ_SRAM_PKT_NUM_0_REG 0x4008 +#define DSAF_VOQ_IN_PKT_NUM_0_REG 0x400C +#define DSAF_VOQ_OUT_PKT_NUM_0_REG 0x4010 +#define DSAF_VOQ_ECC_ERR_ADDR_0_REG 0x4014 +#define DSAF_VOQ_BP_STATUS_0_REG 0x4018 +#define DSAF_VOQ_SPUP_IDLE_0_REG 0x401C +#define DSAF_VOQ_XGE_XOD_REQ_0_0_REG 0x4024 +#define DSAF_VOQ_XGE_XOD_REQ_1_0_REG 0x4028 +#define DSAF_VOQ_PPE_XOD_REQ_0_REG 0x402C +#define DSAF_VOQ_ROCEE_XOD_REQ_0_REG 0x4030 +#define DSAF_VOQ_BP_ALL_THRD_0_REG 0x4034 + +#define DSAF_TBL_CTRL_0_REG 0x5000 +#define DSAF_TBL_INT_MSK_0_REG 0x5004 +#define DSAF_TBL_INT_SRC_0_REG 0x5008 +#define DSAF_TBL_INT_STS_0_REG 0x5100 +#define DSAF_TBL_TCAM_ADDR_0_REG 0x500C +#define DSAF_TBL_LINE_ADDR_0_REG 0x5010 +#define DSAF_TBL_TCAM_HIGH_0_REG 0x5014 +#define DSAF_TBL_TCAM_LOW_0_REG 0x5018 +#define DSAF_TBL_TCAM_MCAST_CFG_4_0_REG 0x501C +#define DSAF_TBL_TCAM_MCAST_CFG_3_0_REG 0x5020 +#define DSAF_TBL_TCAM_MCAST_CFG_2_0_REG 0x5024 +#define DSAF_TBL_TCAM_MCAST_CFG_1_0_REG 0x5028 +#define DSAF_TBL_TCAM_MCAST_CFG_0_0_REG 0x502C +#define DSAF_TBL_TCAM_UCAST_CFG_0_REG 0x5030 +#define DSAF_TBL_LIN_CFG_0_REG 0x5034 +#define DSAF_TBL_TCAM_RDATA_HIGH_0_REG 0x5038 +#define DSAF_TBL_TCAM_RDATA_LOW_0_REG 0x503C +#define DSAF_TBL_TCAM_RAM_RDATA4_0_REG 0x5040 +#define DSAF_TBL_TCAM_RAM_RDATA3_0_REG 0x5044 +#define DSAF_TBL_TCAM_RAM_RDATA2_0_REG 0x5048 +#define DSAF_TBL_TCAM_RAM_RDATA1_0_REG 0x504C +#define DSAF_TBL_TCAM_RAM_RDATA0_0_REG 0x5050 +#define DSAF_TBL_LIN_RDATA_0_REG 0x5054 +#define DSAF_TBL_DA0_MIS_INFO1_0_REG 0x5058 +#define DSAF_TBL_DA0_MIS_INFO0_0_REG 0x505C +#define DSAF_TBL_SA_MIS_INFO2_0_REG 0x5104 +#define DSAF_TBL_SA_MIS_INFO1_0_REG 0x5098 +#define DSAF_TBL_SA_MIS_INFO0_0_REG 0x509C +#define DSAF_TBL_PUL_0_REG 0x50A0 +#define DSAF_TBL_OLD_RSLT_0_REG 0x50A4 +#define DSAF_TBL_OLD_SCAN_VAL_0_REG 0x50A8 +#define DSAF_TBL_DFX_CTRL_0_REG 0x50AC +#define DSAF_TBL_DFX_STAT_0_REG 0x50B0 +#define DSAF_TBL_DFX_STAT_2_0_REG 0x5108 +#define DSAF_TBL_LKUP_NUM_I_0_REG 0x50C0 +#define DSAF_TBL_LKUP_NUM_O_0_REG 0x50E0 +#define DSAF_TBL_UCAST_BCAST_MIS_INFO_0_0_REG 0x510C + +#define DSAF_INODE_FIFO_WL_0_REG 0x6000 +#define DSAF_ONODE_FIFO_WL_0_REG 0x6020 +#define DSAF_XGE_GE_WORK_MODE_0_REG 0x6040 +#define DSAF_XGE_APP_RX_LINK_UP_0_REG 0x6080 +#define DSAF_NETPORT_CTRL_SIG_0_REG 0x60A0 +#define DSAF_XGE_CTRL_SIG_CFG_0_REG 0x60C0 + +#define PPE_COM_CFG_QID_MODE_REG 0x0 +#define PPE_COM_INTEN_REG 0x110 +#define PPE_COM_RINT_REG 0x114 +#define PPE_COM_INTSTS_REG 0x118 +#define PPE_COM_COMMON_CNT_CLR_CE_REG 0x1120 +#define PPE_COM_HIS_RX_PKT_QID_DROP_CNT_REG 0x300 +#define PPE_COM_HIS_RX_PKT_QID_OK_CNT_REG 0x600 +#define PPE_COM_HIS_TX_PKT_QID_ERR_CNT_REG 0x900 +#define PPE_COM_HIS_TX_PKT_QID_OK_CNT_REG 0xC00 +#define PPE_COM_COMMON_CNT_CLR_CE_REG 0x1120 + +#define PPE_CFG_TX_FIFO_THRSLD_REG 0x0 +#define PPE_CFG_RX_FIFO_THRSLD_REG 0x4 +#define PPE_CFG_RX_FIFO_PAUSE_THRSLD_REG 0x8 +#define PPE_CFG_RX_FIFO_SW_BP_THRSLD_REG 0xC +#define PPE_CFG_PAUSE_IDLE_CNT_REG 0x10 +#define PPE_CFG_BUS_CTRL_REG 0x40 +#define PPE_CFG_TNL_TO_BE_RST_REG 0x48 +#define PPE_CURR_TNL_CAN_RST_REG 0x4C +#define PPE_CFG_XGE_MODE_REG 0x80 +#define PPE_CFG_MAX_FRAME_LEN_REG 0x84 +#define PPE_CFG_RX_PKT_MODE_REG 0x88 +#define PPE_CFG_RX_VLAN_TAG_REG 0x8C +#define PPE_CFG_TAG_GEN_REG 0x90 +#define PPE_CFG_PARSE_TAG_REG 0x94 +#define PPE_CFG_PRO_CHECK_EN_REG 0x98 +#define PPE_INTEN_REG 0x100 +#define PPE_RINT_REG 0x104 +#define PPE_INTSTS_REG 0x108 +#define PPE_CFG_RX_PKT_INT_REG 0x140 +#define PPE_CFG_HEAT_DECT_TIME0_REG 0x144 +#define PPE_CFG_HEAT_DECT_TIME1_REG 0x148 +#define PPE_HIS_RX_SW_PKT_CNT_REG 0x200 +#define PPE_HIS_RX_WR_BD_OK_PKT_CNT_REG 0x204 +#define PPE_HIS_RX_PKT_NO_BUF_CNT_REG 0x208 +#define PPE_HIS_TX_BD_CNT_REG 0x20C +#define PPE_HIS_TX_PKT_CNT_REG 0x210 +#define PPE_HIS_TX_PKT_OK_CNT_REG 0x214 +#define PPE_HIS_TX_PKT_EPT_CNT_REG 0x218 +#define PPE_HIS_TX_PKT_CS_FAIL_CNT_REG 0x21C +#define PPE_HIS_RX_APP_BUF_FAIL_CNT_REG 0x220 +#define PPE_HIS_RX_APP_BUF_WAIT_CNT_REG 0x224 +#define PPE_HIS_RX_PKT_DROP_FUL_CNT_REG 0x228 +#define PPE_HIS_RX_PKT_DROP_PRT_CNT_REG 0x22C +#define PPE_TNL_0_5_CNT_CLR_CE_REG 0x300 +#define PPE_CFG_AXI_DBG_REG 0x304 +#define PPE_HIS_PRO_ERR_REG 0x308 +#define PPE_HIS_TNL_FIFO_ERR_REG 0x30C +#define PPE_CURR_CFF_DATA_NUM_REG 0x310 +#define PPE_CURR_RX_ST_REG 0x314 +#define PPE_CURR_TX_ST_REG 0x318 +#define PPE_CURR_RX_FIFO0_REG 0x31C +#define PPE_CURR_RX_FIFO1_REG 0x320 +#define PPE_CURR_TX_FIFO0_REG 0x324 +#define PPE_CURR_TX_FIFO1_REG 0x328 +#define PPE_ECO0_REG 0x32C +#define PPE_ECO1_REG 0x330 +#define PPE_ECO2_REG 0x334 + +#define RCB_COM_CFG_ENDIAN_REG 0x0 +#define RCB_COM_CFG_SYS_FSH_REG 0xC +#define RCB_COM_CFG_INIT_FLAG_REG 0x10 +#define RCB_COM_CFG_PKT_REG 0x30 +#define RCB_COM_CFG_RINVLD_REG 0x34 +#define RCB_COM_CFG_FNA_REG 0x38 +#define RCB_COM_CFG_FA_REG 0x3C +#define RCB_COM_CFG_PKT_TC_BP_REG 0x40 +#define RCB_COM_CFG_PPE_TNL_CLKEN_REG 0x44 + +#define RCB_COM_INTMSK_TX_PKT_REG 0x3A0 +#define RCB_COM_RINT_TX_PKT_REG 0x3A8 +#define RCB_COM_INTMASK_ECC_ERR_REG 0x400 +#define RCB_COM_INTSTS_ECC_ERR_REG 0x408 +#define RCB_COM_EBD_SRAM_ERR_REG 0x410 +#define RCB_COM_RXRING_ERR_REG 0x41C +#define RCB_COM_TXRING_ERR_REG 0x420 +#define RCB_COM_TX_FBD_ERR_REG 0x424 +#define RCB_SRAM_ECC_CHK_EN_REG 0x428 +#define RCB_SRAM_ECC_CHK0_REG 0x42C +#define RCB_SRAM_ECC_CHK1_REG 0x430 +#define RCB_SRAM_ECC_CHK2_REG 0x434 +#define RCB_SRAM_ECC_CHK3_REG 0x438 +#define RCB_SRAM_ECC_CHK4_REG 0x43c +#define RCB_SRAM_ECC_CHK5_REG 0x440 +#define RCB_ECC_ERR_ADDR0_REG 0x450 +#define RCB_ECC_ERR_ADDR3_REG 0x45C +#define RCB_ECC_ERR_ADDR4_REG 0x460 +#define RCB_ECC_ERR_ADDR5_REG 0x464 + +#define RCB_COM_SF_CFG_INTMASK_RING 0x480 +#define RCB_COM_SF_CFG_RING_STS 0x484 +#define RCB_COM_SF_CFG_RING 0x488 +#define RCB_COM_SF_CFG_INTMASK_BD 0x48C +#define RCB_COM_SF_CFG_BD_RINT_STS 0x470 +#define RCB_COM_RCB_RD_BD_BUSY 0x490 +#define RCB_COM_RCB_FBD_CRT_EN 0x494 +#define RCB_COM_AXI_WR_ERR_INTMASK 0x498 +#define RCB_COM_AXI_ERR_STS 0x49C +#define RCB_COM_CHK_TX_FBD_NUM_REG 0x4a0 + +#define RCB_CFG_BD_NUM_REG 0x9000 +#define RCB_CFG_PKTLINE_REG 0x9050 + +#define RCB_CFG_OVERTIME_REG 0x9300 +#define RCB_CFG_PKTLINE_INT_NUM_REG 0x9304 +#define RCB_CFG_OVERTIME_INT_NUM_REG 0x9308 + +#define RCB_RING_RX_RING_BASEADDR_L_REG 0x00000 +#define RCB_RING_RX_RING_BASEADDR_H_REG 0x00004 +#define RCB_RING_RX_RING_BD_NUM_REG 0x00008 +#define RCB_RING_RX_RING_BD_LEN_REG 0x0000C +#define RCB_RING_RX_RING_PKTLINE_REG 0x00010 +#define RCB_RING_RX_RING_TAIL_REG 0x00018 +#define RCB_RING_RX_RING_HEAD_REG 0x0001C +#define RCB_RING_RX_RING_FBDNUM_REG 0x00020 +#define RCB_RING_RX_RING_PKTNUM_RECORD_REG 0x0002C + +#define RCB_RING_TX_RING_BASEADDR_L_REG 0x00040 +#define RCB_RING_TX_RING_BASEADDR_H_REG 0x00044 +#define RCB_RING_TX_RING_BD_NUM_REG 0x00048 +#define RCB_RING_TX_RING_BD_LEN_REG 0x0004C +#define RCB_RING_TX_RING_PKTLINE_REG 0x00050 +#define RCB_RING_TX_RING_TAIL_REG 0x00058 +#define RCB_RING_TX_RING_HEAD_REG 0x0005C +#define RCB_RING_TX_RING_FBDNUM_REG 0x00060 +#define RCB_RING_TX_RING_OFFSET_REG 0x00064 +#define RCB_RING_TX_RING_PKTNUM_RECORD_REG 0x0006C + +#define RCB_RING_PREFETCH_EN_REG 0x0007C +#define RCB_RING_CFG_VF_NUM_REG 0x00080 +#define RCB_RING_ASID_REG 0x0008C +#define RCB_RING_RX_VM_REG 0x00090 +#define RCB_RING_T0_BE_RST 0x00094 +#define RCB_RING_COULD_BE_RST 0x00098 +#define RCB_RING_WRR_WEIGHT_REG 0x0009c + +#define RCB_RING_INTMSK_RXWL_REG 0x000A0 +#define RCB_RING_INTSTS_RX_RING_REG 0x000A4 +#define RCB_RING_INTMSK_TXWL_REG 0x000AC +#define RCB_RING_INTSTS_TX_RING_REG 0x000B0 +#define RCB_RING_INTMSK_RX_OVERTIME_REG 0x000B8 +#define RCB_RING_INTSTS_RX_OVERTIME_REG 0x000BC +#define RCB_RING_INTMSK_TX_OVERTIME_REG 0x000C4 +#define RCB_RING_INTSTS_TX_OVERTIME_REG 0x000C8 + +#define GMAC_DUPLEX_TYPE_REG 0x0008UL +#define GMAC_FD_FC_TYPE_REG 0x000CUL +#define GMAC_FC_TX_TIMER_REG 0x001CUL +#define GMAC_FD_FC_ADDR_LOW_REG 0x0020UL +#define GMAC_FD_FC_ADDR_HIGH_REG 0x0024UL +#define GMAC_IPG_TX_TIMER_REG 0x0030UL +#define GMAC_PAUSE_THR_REG 0x0038UL +#define GMAC_MAX_FRM_SIZE_REG 0x003CUL +#define GMAC_PORT_MODE_REG 0x0040UL +#define GMAC_PORT_EN_REG 0x0044UL +#define GMAC_PAUSE_EN_REG 0x0048UL +#define GMAC_SHORT_RUNTS_THR_REG 0x0050UL +#define GMAC_AN_NEG_STATE_REG 0x0058UL +#define GMAC_TX_LOCAL_PAGE_REG 0x005CUL +#define GMAC_TRANSMIT_CONTROL_REG 0x0060UL +#define GMAC_REC_FILT_CONTROL_REG 0x0064UL +#define GMAC_PTP_CONFIG_REG 0x0074UL + +#define GMAC_RX_OCTETS_TOTAL_OK_REG 0x0080UL +#define GMAC_RX_OCTETS_BAD_REG 0x0084UL +#define GMAC_RX_UC_PKTS_REG 0x0088UL +#define GMAC_RX_MC_PKTS_REG 0x008CUL +#define GMAC_RX_BC_PKTS_REG 0x0090UL +#define GMAC_RX_PKTS_64OCTETS_REG 0x0094UL +#define GMAC_RX_PKTS_65TO127OCTETS_REG 0x0098UL +#define GMAC_RX_PKTS_128TO255OCTETS_REG 0x009CUL +#define GMAC_RX_PKTS_255TO511OCTETS_REG 0x00A0UL +#define GMAC_RX_PKTS_512TO1023OCTETS_REG 0x00A4UL +#define GMAC_RX_PKTS_1024TO1518OCTETS_REG 0x00A8UL +#define GMAC_RX_PKTS_1519TOMAXOCTETS_REG 0x00ACUL +#define GMAC_RX_FCS_ERRORS_REG 0x00B0UL +#define GMAC_RX_TAGGED_REG 0x00B4UL +#define GMAC_RX_DATA_ERR_REG 0x00B8UL +#define GMAC_RX_ALIGN_ERRORS_REG 0x00BCUL +#define GMAC_RX_LONG_ERRORS_REG 0x00C0UL +#define GMAC_RX_JABBER_ERRORS_REG 0x00C4UL +#define GMAC_RX_PAUSE_MACCTRL_FRAM_REG 0x00C8UL +#define GMAC_RX_UNKNOWN_MACCTRL_FRAM_REG 0x00CCUL +#define GMAC_RX_VERY_LONG_ERR_CNT_REG 0x00D0UL +#define GMAC_RX_RUNT_ERR_CNT_REG 0x00D4UL +#define GMAC_RX_SHORT_ERR_CNT_REG 0x00D8UL +#define GMAC_RX_FILT_PKT_CNT_REG 0x00E8UL +#define GMAC_RX_OCTETS_TOTAL_FILT_REG 0x00ECUL +#define GMAC_OCTETS_TRANSMITTED_OK_REG 0x0100UL +#define GMAC_OCTETS_TRANSMITTED_BAD_REG 0x0104UL +#define GMAC_TX_UC_PKTS_REG 0x0108UL +#define GMAC_TX_MC_PKTS_REG 0x010CUL +#define GMAC_TX_BC_PKTS_REG 0x0110UL +#define GMAC_TX_PKTS_64OCTETS_REG 0x0114UL +#define GMAC_TX_PKTS_65TO127OCTETS_REG 0x0118UL +#define GMAC_TX_PKTS_128TO255OCTETS_REG 0x011CUL +#define GMAC_TX_PKTS_255TO511OCTETS_REG 0x0120UL +#define GMAC_TX_PKTS_512TO1023OCTETS_REG 0x0124UL +#define GMAC_TX_PKTS_1024TO1518OCTETS_REG 0x0128UL +#define GMAC_TX_PKTS_1519TOMAXOCTETS_REG 0x012CUL +#define GMAC_TX_EXCESSIVE_LENGTH_DROP_REG 0x014CUL +#define GMAC_TX_UNDERRUN_REG 0x0150UL +#define GMAC_TX_TAGGED_REG 0x0154UL +#define GMAC_TX_CRC_ERROR_REG 0x0158UL +#define GMAC_TX_PAUSE_FRAMES_REG 0x015CUL +#define GAMC_RX_MAX_FRAME 0x0170UL +#define GMAC_LINE_LOOP_BACK_REG 0x01A8UL +#define GMAC_CF_CRC_STRIP_REG 0x01B0UL +#define GMAC_MODE_CHANGE_EN_REG 0x01B4UL +#define GMAC_SIXTEEN_BIT_CNTR_REG 0x01CCUL +#define GMAC_LD_LINK_COUNTER_REG 0x01D0UL +#define GMAC_LOOP_REG 0x01DCUL +#define GMAC_RECV_CONTROL_REG 0x01E0UL +#define GMAC_VLAN_CODE_REG 0x01E8UL +#define GMAC_RX_OVERRUN_CNT_REG 0x01ECUL +#define GMAC_RX_LENGTHFIELD_ERR_CNT_REG 0x01F4UL +#define GMAC_RX_FAIL_COMMA_CNT_REG 0x01F8UL +#define GMAC_STATION_ADDR_LOW_0_REG 0x0200UL +#define GMAC_STATION_ADDR_HIGH_0_REG 0x0204UL +#define GMAC_STATION_ADDR_LOW_1_REG 0x0208UL +#define GMAC_STATION_ADDR_HIGH_1_REG 0x020CUL +#define GMAC_STATION_ADDR_LOW_2_REG 0x0210UL +#define GMAC_STATION_ADDR_HIGH_2_REG 0x0214UL +#define GMAC_STATION_ADDR_LOW_3_REG 0x0218UL +#define GMAC_STATION_ADDR_HIGH_3_REG 0x021CUL +#define GMAC_STATION_ADDR_LOW_4_REG 0x0220UL +#define GMAC_STATION_ADDR_HIGH_4_REG 0x0224UL +#define GMAC_STATION_ADDR_LOW_5_REG 0x0228UL +#define GMAC_STATION_ADDR_HIGH_5_REG 0x022CUL +#define GMAC_STATION_ADDR_LOW_MSK_0_REG 0x0230UL +#define GMAC_STATION_ADDR_HIGH_MSK_0_REG 0x0234UL +#define GMAC_STATION_ADDR_LOW_MSK_1_REG 0x0238UL +#define GMAC_STATION_ADDR_HIGH_MSK_1_REG 0x023CUL +#define GMAC_MAC_SKIP_LEN_REG 0x0240UL +#define GMAC_TX_LOOP_PKT_PRI_REG 0x0378UL + +#define XGMAC_INT_STATUS_REG 0x0 +#define XGMAC_INT_ENABLE_REG 0x4 +#define XGMAC_INT_SET_REG 0x8 +#define XGMAC_IERR_U_INFO_REG 0xC +#define XGMAC_OVF_INFO_REG 0x10 +#define XGMAC_OVF_CNT_REG 0x14 +#define XGMAC_PORT_MODE_REG 0x40 +#define XGMAC_CLK_ENABLE_REG 0x44 +#define XGMAC_RESET_REG 0x48 +#define XGMAC_LINK_CONTROL_REG 0x50 +#define XGMAC_LINK_STATUS_REG 0x54 +#define XGMAC_SPARE_REG 0xC0 +#define XGMAC_SPARE_CNT_REG 0xC4 + +#define XGMAC_MAC_ENABLE_REG 0x100 +#define XGMAC_MAC_CONTROL_REG 0x104 +#define XGMAC_MAC_IPG_REG 0x120 +#define XGMAC_MAC_MSG_CRC_EN_REG 0x124 +#define XGMAC_MAC_MSG_IMG_REG 0x128 +#define XGMAC_MAC_MSG_FC_CFG_REG 0x12C +#define XGMAC_MAC_MSG_TC_CFG_REG 0x130 +#define XGMAC_MAC_PAD_SIZE_REG 0x134 +#define XGMAC_MAC_MIN_PKT_SIZE_REG 0x138 +#define XGMAC_MAC_MAX_PKT_SIZE_REG 0x13C +#define XGMAC_MAC_PAUSE_CTRL_REG 0x160 +#define XGMAC_MAC_PAUSE_TIME_REG 0x164 +#define XGMAC_MAC_PAUSE_GAP_REG 0x168 +#define XGMAC_MAC_PAUSE_LOCAL_MAC_H_REG 0x16C +#define XGMAC_MAC_PAUSE_LOCAL_MAC_L_REG 0x170 +#define XGMAC_MAC_PAUSE_PEER_MAC_H_REG 0x174 +#define XGMAC_MAC_PAUSE_PEER_MAC_L_REG 0x178 +#define XGMAC_MAC_PFC_PRI_EN_REG 0x17C +#define XGMAC_MAC_1588_CTRL_REG 0x180 +#define XGMAC_MAC_1588_TX_PORT_DLY_REG 0x184 +#define XGMAC_MAC_1588_RX_PORT_DLY_REG 0x188 +#define XGMAC_MAC_1588_ASYM_DLY_REG 0x18C +#define XGMAC_MAC_1588_ADJUST_CFG_REG 0x190 +#define XGMAC_MAC_Y1731_ETH_TYPE_REG 0x194 +#define XGMAC_MAC_MIB_CONTROL_REG 0x198 +#define XGMAC_MAC_WAN_RATE_ADJUST_REG 0x19C +#define XGMAC_MAC_TX_ERR_MARK_REG 0x1A0 +#define XGMAC_MAC_TX_LF_RF_CONTROL_REG 0x1A4 +#define XGMAC_MAC_RX_LF_RF_STATUS_REG 0x1A8 +#define XGMAC_MAC_TX_RUNT_PKT_CNT_REG 0x1C0 +#define XGMAC_MAC_RX_RUNT_PKT_CNT_REG 0x1C4 +#define XGMAC_MAC_RX_PREAM_ERR_PKT_CNT_REG 0x1C8 +#define XGMAC_MAC_TX_LF_RF_TERM_PKT_CNT_REG 0x1CC +#define XGMAC_MAC_TX_SN_MISMATCH_PKT_CNT_REG 0x1D0 +#define XGMAC_MAC_RX_ERR_MSG_CNT_REG 0x1D4 +#define XGMAC_MAC_RX_ERR_EFD_CNT_REG 0x1D8 +#define XGMAC_MAC_ERR_INFO_REG 0x1DC +#define XGMAC_MAC_DBG_INFO_REG 0x1E0 + +#define XGMAC_PCS_BASER_SYNC_THD_REG 0x330 +#define XGMAC_PCS_STATUS1_REG 0x404 +#define XGMAC_PCS_BASER_STATUS1_REG 0x410 +#define XGMAC_PCS_BASER_STATUS2_REG 0x414 +#define XGMAC_PCS_BASER_SEEDA_0_REG 0x420 +#define XGMAC_PCS_BASER_SEEDA_1_REG 0x424 +#define XGMAC_PCS_BASER_SEEDB_0_REG 0x428 +#define XGMAC_PCS_BASER_SEEDB_1_REG 0x42C +#define XGMAC_PCS_BASER_TEST_CONTROL_REG 0x430 +#define XGMAC_PCS_BASER_TEST_ERR_CNT_REG 0x434 +#define XGMAC_PCS_DBG_INFO_REG 0x4C0 +#define XGMAC_PCS_DBG_INFO1_REG 0x4C4 +#define XGMAC_PCS_DBG_INFO2_REG 0x4C8 +#define XGMAC_PCS_DBG_INFO3_REG 0x4CC + +#define XGMAC_PMA_ENABLE_REG 0x700 +#define XGMAC_PMA_CONTROL_REG 0x704 +#define XGMAC_PMA_SIGNAL_STATUS_REG 0x708 +#define XGMAC_PMA_DBG_INFO_REG 0x70C +#define XGMAC_PMA_FEC_ABILITY_REG 0x740 +#define XGMAC_PMA_FEC_CONTROL_REG 0x744 +#define XGMAC_PMA_FEC_CORR_BLOCK_CNT__REG 0x750 +#define XGMAC_PMA_FEC_UNCORR_BLOCK_CNT__REG 0x760 + +#define XGMAC_TX_PKTS_FRAGMENT 0x0000 +#define XGMAC_TX_PKTS_UNDERSIZE 0x0008 +#define XGMAC_TX_PKTS_UNDERMIN 0x0010 +#define XGMAC_TX_PKTS_64OCTETS 0x0018 +#define XGMAC_TX_PKTS_65TO127OCTETS 0x0020 +#define XGMAC_TX_PKTS_128TO255OCTETS 0x0028 +#define XGMAC_TX_PKTS_256TO511OCTETS 0x0030 +#define XGMAC_TX_PKTS_512TO1023OCTETS 0x0038 +#define XGMAC_TX_PKTS_1024TO1518OCTETS 0x0040 +#define XGMAC_TX_PKTS_1519TOMAXOCTETS 0x0048 +#define XGMAC_TX_PKTS_1519TOMAXOCTETSOK 0x0050 +#define XGMAC_TX_PKTS_OVERSIZE 0x0058 +#define XGMAC_TX_PKTS_JABBER 0x0060 +#define XGMAC_TX_GOODPKTS 0x0068 +#define XGMAC_TX_GOODOCTETS 0x0070 +#define XGMAC_TX_TOTAL_PKTS 0x0078 +#define XGMAC_TX_TOTALOCTETS 0x0080 +#define XGMAC_TX_UNICASTPKTS 0x0088 +#define XGMAC_TX_MULTICASTPKTS 0x0090 +#define XGMAC_TX_BROADCASTPKTS 0x0098 +#define XGMAC_TX_PRI0PAUSEPKTS 0x00a0 +#define XGMAC_TX_PRI1PAUSEPKTS 0x00a8 +#define XGMAC_TX_PRI2PAUSEPKTS 0x00b0 +#define XGMAC_TX_PRI3PAUSEPKTS 0x00b8 +#define XGMAC_TX_PRI4PAUSEPKTS 0x00c0 +#define XGMAC_TX_PRI5PAUSEPKTS 0x00c8 +#define XGMAC_TX_PRI6PAUSEPKTS 0x00d0 +#define XGMAC_TX_PRI7PAUSEPKTS 0x00d8 +#define XGMAC_TX_MACCTRLPKTS 0x00e0 +#define XGMAC_TX_1731PKTS 0x00e8 +#define XGMAC_TX_1588PKTS 0x00f0 +#define XGMAC_RX_FROMAPPGOODPKTS 0x00f8 +#define XGMAC_RX_FROMAPPBADPKTS 0x0100 +#define XGMAC_TX_ERRALLPKTS 0x0108 + +#define XGMAC_RX_PKTS_FRAGMENT 0x0110 +#define XGMAC_RX_PKTSUNDERSIZE 0x0118 +#define XGMAC_RX_PKTS_UNDERMIN 0x0120 +#define XGMAC_RX_PKTS_64OCTETS 0x0128 +#define XGMAC_RX_PKTS_65TO127OCTETS 0x0130 +#define XGMAC_RX_PKTS_128TO255OCTETS 0x0138 +#define XGMAC_RX_PKTS_256TO511OCTETS 0x0140 +#define XGMAC_RX_PKTS_512TO1023OCTETS 0x0148 +#define XGMAC_RX_PKTS_1024TO1518OCTETS 0x0150 +#define XGMAC_RX_PKTS_1519TOMAXOCTETS 0x0158 +#define XGMAC_RX_PKTS_1519TOMAXOCTETSOK 0x0160 +#define XGMAC_RX_PKTS_OVERSIZE 0x0168 +#define XGMAC_RX_PKTS_JABBER 0x0170 +#define XGMAC_RX_GOODPKTS 0x0178 +#define XGMAC_RX_GOODOCTETS 0x0180 +#define XGMAC_RX_TOTAL_PKTS 0x0188 +#define XGMAC_RX_TOTALOCTETS 0x0190 +#define XGMAC_RX_UNICASTPKTS 0x0198 +#define XGMAC_RX_MULTICASTPKTS 0x01a0 +#define XGMAC_RX_BROADCASTPKTS 0x01a8 +#define XGMAC_RX_PRI0PAUSEPKTS 0x01b0 +#define XGMAC_RX_PRI1PAUSEPKTS 0x01b8 +#define XGMAC_RX_PRI2PAUSEPKTS 0x01c0 +#define XGMAC_RX_PRI3PAUSEPKTS 0x01c8 +#define XGMAC_RX_PRI4PAUSEPKTS 0x01d0 +#define XGMAC_RX_PRI5PAUSEPKTS 0x01d8 +#define XGMAC_RX_PRI6PAUSEPKTS 0x01e0 +#define XGMAC_RX_PRI7PAUSEPKTS 0x01e8 +#define XGMAC_RX_MACCTRLPKTS 0x01f0 +#define XGMAC_TX_SENDAPPGOODPKTS 0x01f8 +#define XGMAC_TX_SENDAPPBADPKTS 0x0200 +#define XGMAC_RX_1731PKTS 0x0208 +#define XGMAC_RX_SYMBOLERRPKTS 0x0210 +#define XGMAC_RX_FCSERRPKTS 0x0218 + +#define XGMAC_TRX_CORE_SRST_M 0x2080 + +#define DSAF_CFG_EN_S 0 +#define DSAF_CFG_TC_MODE_S 1 +#define DSAF_CFG_CRC_EN_S 2 +#define DSAF_CFG_SBM_INIT_S 3 +#define DSAF_CFG_MIX_MODE_S 4 +#define DSAF_CFG_STP_MODE_S 5 +#define DSAF_CFG_LOCA_ADDR_EN_S 6 + +#define DSAF_CNT_CLR_CE_S 0 +#define DSAF_SNAP_EN_S 1 + +#define HNS_DSAF_PFC_UNIT_CNT_FOR_XGE 41 +#define HNS_DSAF_PFC_UNIT_CNT_FOR_GE_1000 410 +#define HNS_DSAF_PFC_UNIT_CNT_FOR_GE_2500 103 + +#define DSAF_PFC_UNINT_CNT_M ((1ULL << 9) - 1) +#define DSAF_PFC_UNINT_CNT_S 0 + +#define DSAF_PPE_QID_CFG_M 0xFF +#define DSAF_PPE_QID_CFG_S 0 + +#define DSAF_SW_PORT_TYPE_M 3 +#define DSAF_SW_PORT_TYPE_S 0 + +#define DSAF_STP_PORT_TYPE_M 7 +#define DSAF_STP_PORT_TYPE_S 0 + +#define DSAF_INODE_IN_PORT_NUM_M 7 +#define DSAF_INODE_IN_PORT_NUM_S 0 + +#define HNS_DSAF_I4TC_CFG 0x18688688 +#define HNS_DSAF_I8TC_CFG 0x18FAC688 + +#define DSAF_SBM_CFG_SHCUT_EN_S 0 +#define DSAF_SBM_CFG_EN_S 1 +#define DSAF_SBM_CFG_MIB_EN_S 2 +#define DSAF_SBM_CFG_ECC_INVERT_EN_S 3 + +#define DSAF_SBM_CFG0_VC1_MAX_BUF_NUM_S 0 +#define DSAF_SBM_CFG0_VC1_MAX_BUF_NUM_M (((1ULL << 10) - 1) << 0) +#define DSAF_SBM_CFG0_VC0_MAX_BUF_NUM_S 10 +#define DSAF_SBM_CFG0_VC0_MAX_BUF_NUM_M (((1ULL << 10) - 1) << 10) +#define DSAF_SBM_CFG0_COM_MAX_BUF_NUM_S 20 +#define DSAF_SBM_CFG0_COM_MAX_BUF_NUM_M (((1ULL << 11) - 1) << 20) + +#define DSAF_SBM_CFG1_TC4_MAX_BUF_NUM_S 0 +#define DSAF_SBM_CFG1_TC4_MAX_BUF_NUM_M (((1ULL << 10) - 1) << 0) +#define DSAF_SBM_CFG1_TC0_MAX_BUF_NUM_S 10 +#define DSAF_SBM_CFG1_TC0_MAX_BUF_NUM_M (((1ULL << 10) - 1) << 10) + +#define DSAF_SBM_CFG2_SET_BUF_NUM_S 0 +#define DSAF_SBM_CFG2_SET_BUF_NUM_M (((1ULL << 10) - 1) << 0) +#define DSAF_SBM_CFG2_RESET_BUF_NUM_S 10 +#define DSAF_SBM_CFG2_RESET_BUF_NUM_M (((1ULL << 10) - 1) << 10) + +#define DSAF_SBM_CFG3_SET_BUF_NUM_NO_PFC_S 0 +#define DSAF_SBM_CFG3_SET_BUF_NUM_NO_PFC_M (((1ULL << 10) - 1) << 0) +#define DSAF_SBM_CFG3_RESET_BUF_NUM_NO_PFC_S 10 +#define DSAF_SBM_CFG3_RESET_BUF_NUM_NO_PFC_M (((1ULL << 10) - 1) << 10) + +#define DSAF_TBL_TCAM_ADDR_S 0 +#define DSAF_TBL_TCAM_ADDR_M ((1ULL << 9) - 1) + +#define DSAF_TBL_LINE_ADDR_S 0 +#define DSAF_TBL_LINE_ADDR_M ((1ULL << 15) - 1) + +#define DSAF_TBL_MCAST_CFG4_VM128_112_S 0 +#define DSAF_TBL_MCAST_CFG4_VM128_112_M (((1ULL << 7) - 1) << 0) +#define DSAF_TBL_MCAST_CFG4_ITEM_VLD_S 7 +#define DSAF_TBL_MCAST_CFG4_OLD_EN_S 8 + +#define DSAF_TBL_MCAST_CFG0_XGE5_0_S 0 +#define DSAF_TBL_MCAST_CFG0_XGE5_0_M (((1ULL << 6) - 1) << 0) +#define DSAF_TBL_MCAST_CFG0_VM25_0_S 6 +#define DSAF_TBL_MCAST_CFG0_VM25_0_M (((1ULL << 26) - 1) << 6) + +#define DSAF_TBL_UCAST_CFG1_OUT_PORT_S 0 +#define DSAF_TBL_UCAST_CFG1_OUT_PORT_M (((1ULL << 8) - 1) << 0) +#define DSAF_TBL_UCAST_CFG1_DVC_S 8 +#define DSAF_TBL_UCAST_CFG1_MAC_DISCARD_S 9 +#define DSAF_TBL_UCAST_CFG1_ITEM_VLD_S 10 +#define DSAF_TBL_UCAST_CFG1_OLD_EN_S 11 + +#define DSAF_TBL_LINE_CFG_OUT_PORT_S 0 +#define DSAF_TBL_LINE_CFG_OUT_PORT_M (((1ULL << 8) - 1) << 0) +#define DSAF_TBL_LINE_CFG_DVC_S 8 +#define DSAF_TBL_LINE_CFG_MAC_DISCARD_S 9 + +#define DSAF_TBL_PUL_OLD_RSLT_RE_S 0 +#define DSAF_TBL_PUL_MCAST_VLD_S 1 +#define DSAF_TBL_PUL_TCAM_DATA_VLD_S 2 +#define DSAF_TBL_PUL_UCAST_VLD_S 3 +#define DSAF_TBL_PUL_LINE_VLD_S 4 +#define DSAF_TBL_PUL_TCAM_LOAD_S 5 +#define DSAF_TBL_PUL_LINE_LOAD_S 6 + +#define DSAF_TBL_DFX_LINE_LKUP_NUM_EN_S 0 +#define DSAF_TBL_DFX_UC_LKUP_NUM_EN_S 1 +#define DSAF_TBL_DFX_MC_LKUP_NUM_EN_S 2 +#define DSAF_TBL_DFX_BC_LKUP_NUM_EN_S 3 +#define DSAF_TBL_DFX_RAM_ERR_INJECT_EN_S 4 + +#define DSAF_VOQ_BP_ALL_DOWNTHRD_S 0 +#define DSAF_VOQ_BP_ALL_DOWNTHRD_M (((1ULL << 10) - 1) << 0) +#define DSAF_VOQ_BP_ALL_UPTHRD_S 10 +#define DSAF_VOQ_BP_ALL_UPTHRD_M (((1ULL << 10) - 1) << 10) + +#define DSAF_XGE_GE_WORK_MODE_S 0 +#define DSAF_XGE_GE_LOOPBACK_S 1 + +#define DSAF_FC_XGE_TX_PAUSE_S 0 +#define DSAF_REGS_XGE_CNT_CAR_S 1 + +#define PPE_CFG_QID_MODE_DEF_QID_S 0 +#define PPE_CFG_QID_MODE_DEF_QID_M (0xff << PPE_CFG_QID_MODE_DEF_QID_S) + +#define PPE_CFG_QID_MODE_CF_QID_MODE_S 8 +#define PPE_CFG_QID_MODE_CF_QID_MODE_M (0x7 << PPE_CFG_QID_MODE_CF_QID_MODE_S) + +#define PPE_CNT_CLR_CE_B 0 +#define PPE_CNT_CLR_SNAP_EN_B 1 + +#define PPE_COMMON_CNT_CLR_CE_B 0 +#define PPE_COMMON_CNT_CLR_SNAP_EN_B 1 + +#define GMAC_DUPLEX_TYPE_B 0 + +#define GMAC_FC_TX_TIMER_S 0 +#define GMAC_FC_TX_TIMER_M 0xffff + +#define GMAC_MAX_FRM_SIZE_S 0 +#define GMAC_MAX_FRM_SIZE_M 0xffff + +#define GMAC_PORT_MODE_S 0 +#define GMAC_PORT_MODE_M 0xf + +#define GMAC_RGMII_1000M_DELAY_B 4 +#define GMAC_MII_TX_EDGE_SEL_B 5 +#define GMAC_FIFO_ERR_AUTO_RST_B 6 +#define GMAC_DBG_CLK_LOS_MSK_B 7 + +#define GMAC_PORT_RX_EN_B 1 +#define GMAC_PORT_TX_EN_B 2 + +#define GMAC_PAUSE_EN_RX_FDFC_B 0 +#define GMAC_PAUSE_EN_TX_FDFC_B 1 +#define GMAC_PAUSE_EN_TX_HDFC_B 2 + +#define GMAC_SHORT_RUNTS_THR_S 0 +#define GMAC_SHORT_RUNTS_THR_M 0x1f + +#define GMAC_AN_NEG_STAT_FD_B 5 +#define GMAC_AN_NEG_STAT_HD_B 6 +#define GMAC_AN_NEG_STAT_RF1_DUPLIEX_B 12 +#define GMAC_AN_NEG_STAT_RF2_B 13 + +#define GMAC_AN_NEG_STAT_NP_LNK_OK_B 15 +#define GMAC_AN_NEG_STAT_RX_SYNC_OK_B 20 +#define GMAC_AN_NEG_STAT_AN_DONE_B 21 + +#define GMAC_AN_NEG_STAT_PS_S 7 +#define GMAC_AN_NEG_STAT_PS_M (0x3 << GMAC_AN_NEG_STAT_PS_S) + +#define GMAC_AN_NEG_STAT_SPEED_S 10 +#define GMAC_AN_NEG_STAT_SPEED_M (0x3 << GMAC_AN_NEG_STAT_SPEED_S) + +#define GMAC_TX_AN_EN_B 5 +#define GMAC_TX_CRC_ADD_B 6 +#define GMAC_TX_PAD_EN_B 7 + +#define GMAC_LINE_LOOPBACK_B 0 + +#define GMAC_LP_REG_CF_EXT_DRV_LP_B 1 +#define GMAC_LP_REG_CF2MI_LP_EN_B 2 + +#define GMAC_MODE_CHANGE_EB_B 0 + +#define GMAC_RECV_CTRL_STRIP_PAD_EN_B 3 +#define GMAC_RECV_CTRL_RUNT_PKT_EN_B 4 + +#define GMAC_TX_LOOP_PKT_HIG_PRI_B 0 +#define GMAC_TX_LOOP_PKT_EN_B 1 + +#define XGMAC_PORT_MODE_TX_S 0x0 +#define XGMAC_PORT_MODE_TX_M (0x3 << XGMAC_PORT_MODE_TX_S) +#define XGMAC_PORT_MODE_TX_40G_B 0x3 +#define XGMAC_PORT_MODE_RX_S 0x4 +#define XGMAC_PORT_MODE_RX_M (0x3 << XGMAC_PORT_MODE_RX_S) +#define XGMAC_PORT_MODE_RX_40G_B 0x7 + +#define XGMAC_ENABLE_TX_B 0 +#define XGMAC_ENABLE_RX_B 1 + +#define XGMAC_CTL_TX_FCS_B 0 +#define XGMAC_CTL_TX_PAD_B 1 +#define XGMAC_CTL_TX_PREAMBLE_TRANS_B 3 +#define XGMAC_CTL_TX_UNDER_MIN_ERR_B 4 +#define XGMAC_CTL_TX_TRUNCATE_B 5 +#define XGMAC_CTL_TX_1588_B 8 +#define XGMAC_CTL_TX_1731_B 9 +#define XGMAC_CTL_TX_PFC_B 10 +#define XGMAC_CTL_RX_FCS_B 16 +#define XGMAC_CTL_RX_FCS_STRIP_B 17 +#define XGMAC_CTL_RX_PREAMBLE_TRANS_B 19 +#define XGMAC_CTL_RX_UNDER_MIN_ERR_B 20 +#define XGMAC_CTL_RX_TRUNCATE_B 21 +#define XGMAC_CTL_RX_1588_B 24 +#define XGMAC_CTL_RX_1731_B 25 +#define XGMAC_CTL_RX_PFC_B 26 + +#define XGMAC_PMA_FEC_CTL_TX_B 0 +#define XGMAC_PMA_FEC_CTL_RX_B 1 +#define XGMAC_PMA_FEC_CTL_ERR_EN 2 +#define XGMAC_PMA_FEC_CTL_ERR_SH 3 + +#define XGMAC_PAUSE_CTL_TX_B 0 +#define XGMAC_PAUSE_CTL_RX_B 1 +#define XGMAC_PAUSE_CTL_RSP_MODE_B 2 +#define XGMAC_PAUSE_CTL_TX_XOFF_B 3 + +static inline void dsaf_write_reg(void *base, u32 reg, u32 value) +{ + u8 __iomem *reg_addr = ACCESS_ONCE(base); + + writel(value, reg_addr + reg); +} + +#define dsaf_write_dev(a, reg, value) \ + dsaf_write_reg((a)->io_base, (reg), (value)) + +static inline u32 dsaf_read_reg(u8 *base, u32 reg) +{ + u8 __iomem *reg_addr = ACCESS_ONCE(base); + + return readl(reg_addr + reg); +} + +#define dsaf_read_dev(a, reg) \ + dsaf_read_reg((a)->io_base, (reg)) + +#define dsaf_set_field(origin, mask, shift, val) \ + do { \ + (origin) &= (~(mask)); \ + (origin) |= (((val) << (shift)) & (mask)); \ + } while (0) + +#define dsaf_set_bit(origin, shift, val) \ + dsaf_set_field((origin), (1ull << (shift)), (shift), (val)) + +static inline void dsaf_set_reg_field(void *base, u32 reg, u32 mask, u32 shift, + u32 val) +{ + u32 origin = dsaf_read_reg(base, reg); + + dsaf_set_field(origin, mask, shift, val); + dsaf_write_reg(base, reg, origin); +} + +#define dsaf_set_dev_field(dev, reg, mask, shift, val) \ + dsaf_set_reg_field((dev)->io_base, (reg), (mask), (shift), (val)) + +#define dsaf_set_dev_bit(dev, reg, bit, val) \ + dsaf_set_reg_field((dev)->io_base, (reg), (1ull << (bit)), (bit), (val)) + +#define dsaf_get_field(origin, mask, shift) (((origin) & (mask)) >> (shift)) + +#define dsaf_get_bit(origin, shift) \ + dsaf_get_field((origin), (1ull << (shift)), (shift)) + +static inline u32 dsaf_get_reg_field(void *base, u32 reg, u32 mask, u32 shift) +{ + u32 origin; + + origin = dsaf_read_reg(base, reg); + return dsaf_get_field(origin, mask, shift); +} + +#define dsaf_get_dev_field(dev, reg, mask, shift) \ + dsaf_get_reg_field((dev)->io_base, (reg), (mask), (shift)) + +#define dsaf_get_dev_bit(dev, reg, bit) \ + dsaf_get_reg_field((dev)->io_base, (reg), (1ull << (bit)), (bit)) + +#define dsaf_write_b(addr, data)\ + writeb((data), (__iomem unsigned char *)(addr)) +#define dsaf_read_b(addr)\ + readb((__iomem unsigned char *)(addr)) + +#define hns_mac_reg_read64(drv, offset) \ + readq((__iomem void *)(((u8 *)(drv)->io_base + 0xc00 + (offset)))) + +#endif /* _DSAF_REG_H */ diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c new file mode 100644 index 000000000000..dab5ecf382a0 --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c @@ -0,0 +1,837 @@ +/* + * Copyright (c) 2014-2015 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <asm-generic/io-64-nonatomic-hi-lo.h> +#include <linux/of_mdio.h> +#include "hns_dsaf_main.h" +#include "hns_dsaf_mac.h" +#include "hns_dsaf_xgmac.h" +#include "hns_dsaf_reg.h" + +static const struct mac_stats_string g_xgmac_stats_string[] = { + {"xgmac_tx_bad_pkts_minto64", MAC_STATS_FIELD_OFF(tx_fragment_err)}, + {"xgmac_tx_good_pkts_minto64", MAC_STATS_FIELD_OFF(tx_undersize)}, + {"xgmac_tx_total_pkts_minto64", MAC_STATS_FIELD_OFF(tx_under_min_pkts)}, + {"xgmac_tx_pkts_64", MAC_STATS_FIELD_OFF(tx_64bytes)}, + {"xgmac_tx_pkts_65to127", MAC_STATS_FIELD_OFF(tx_65to127)}, + {"xgmac_tx_pkts_128to255", MAC_STATS_FIELD_OFF(tx_128to255)}, + {"xgmac_tx_pkts_256to511", MAC_STATS_FIELD_OFF(tx_256to511)}, + {"xgmac_tx_pkts_512to1023", MAC_STATS_FIELD_OFF(tx_512to1023)}, + {"xgmac_tx_pkts_1024to1518", MAC_STATS_FIELD_OFF(tx_1024to1518)}, + {"xgmac_tx_pkts_1519tomax", MAC_STATS_FIELD_OFF(tx_1519tomax)}, + {"xgmac_tx_good_pkts_1519tomax", + MAC_STATS_FIELD_OFF(tx_1519tomax_good)}, + {"xgmac_tx_good_pkts_untralmax", MAC_STATS_FIELD_OFF(tx_oversize)}, + {"xgmac_tx_bad_pkts_untralmax", MAC_STATS_FIELD_OFF(tx_jabber_err)}, + {"xgmac_tx_good_pkts_all", MAC_STATS_FIELD_OFF(tx_good_pkts)}, + {"xgmac_tx_good_byte_all", MAC_STATS_FIELD_OFF(tx_good_bytes)}, + {"xgmac_tx_total_pkt", MAC_STATS_FIELD_OFF(tx_total_pkts)}, + {"xgmac_tx_total_byt", MAC_STATS_FIELD_OFF(tx_total_bytes)}, + {"xgmac_tx_uc_pkt", MAC_STATS_FIELD_OFF(tx_uc_pkts)}, + {"xgmac_tx_mc_pkt", MAC_STATS_FIELD_OFF(tx_mc_pkts)}, + {"xgmac_tx_bc_pkt", MAC_STATS_FIELD_OFF(tx_bc_pkts)}, + {"xgmac_tx_pause_frame_num", MAC_STATS_FIELD_OFF(tx_pfc_tc0)}, + {"xgmac_tx_pfc_per_1pause_framer", MAC_STATS_FIELD_OFF(tx_pfc_tc1)}, + {"xgmac_tx_pfc_per_2pause_framer", MAC_STATS_FIELD_OFF(tx_pfc_tc2)}, + {"xgmac_tx_pfc_per_3pause_framer", MAC_STATS_FIELD_OFF(tx_pfc_tc3)}, + {"xgmac_tx_pfc_per_4pause_framer", MAC_STATS_FIELD_OFF(tx_pfc_tc4)}, + {"xgmac_tx_pfc_per_5pause_framer", MAC_STATS_FIELD_OFF(tx_pfc_tc5)}, + {"xgmac_tx_pfc_per_6pause_framer", MAC_STATS_FIELD_OFF(tx_pfc_tc6)}, + {"xgmac_tx_pfc_per_7pause_framer", MAC_STATS_FIELD_OFF(tx_pfc_tc7)}, + {"xgmac_tx_mac_ctrol_frame", MAC_STATS_FIELD_OFF(tx_ctrl)}, + {"xgmac_tx_1731_pkts", MAC_STATS_FIELD_OFF(tx_1731_pkts)}, + {"xgmac_tx_1588_pkts", MAC_STATS_FIELD_OFF(tx_1588_pkts)}, + {"xgmac_rx_good_pkt_from_dsaf", MAC_STATS_FIELD_OFF(rx_good_from_sw)}, + {"xgmac_rx_bad_pkt_from_dsaf", MAC_STATS_FIELD_OFF(rx_bad_from_sw)}, + {"xgmac_tx_bad_pkt_64tomax", MAC_STATS_FIELD_OFF(tx_bad_pkts)}, + + {"xgmac_rx_not_well_pkt", MAC_STATS_FIELD_OFF(rx_fragment_err)}, + {"xgmac_rx_good_well_pkt", MAC_STATS_FIELD_OFF(rx_undersize)}, + {"xgmac_rx_total_pkt", MAC_STATS_FIELD_OFF(rx_under_min)}, + {"xgmac_rx_pkt_64", MAC_STATS_FIELD_OFF(rx_64bytes)}, + {"xgmac_rx_pkt_65to127", MAC_STATS_FIELD_OFF(rx_65to127)}, + {"xgmac_rx_pkt_128to255", MAC_STATS_FIELD_OFF(rx_128to255)}, + {"xgmac_rx_pkt_256to511", MAC_STATS_FIELD_OFF(rx_256to511)}, + {"xgmac_rx_pkt_512to1023", MAC_STATS_FIELD_OFF(rx_512to1023)}, + {"xgmac_rx_pkt_1024to1518", MAC_STATS_FIELD_OFF(rx_1024to1518)}, + {"xgmac_rx_pkt_1519tomax", MAC_STATS_FIELD_OFF(rx_1519tomax)}, + {"xgmac_rx_good_pkt_1519tomax", MAC_STATS_FIELD_OFF(rx_1519tomax_good)}, + {"xgmac_rx_good_pkt_untramax", MAC_STATS_FIELD_OFF(rx_oversize)}, + {"xgmac_rx_bad_pkt_untramax", MAC_STATS_FIELD_OFF(rx_jabber_err)}, + {"xgmac_rx_good_pkt", MAC_STATS_FIELD_OFF(rx_good_pkts)}, + {"xgmac_rx_good_byt", MAC_STATS_FIELD_OFF(rx_good_bytes)}, + {"xgmac_rx_pkt", MAC_STATS_FIELD_OFF(rx_total_pkts)}, + {"xgmac_rx_byt", MAC_STATS_FIELD_OFF(rx_total_bytes)}, + {"xgmac_rx_uc_pkt", MAC_STATS_FIELD_OFF(rx_uc_pkts)}, + {"xgmac_rx_mc_pkt", MAC_STATS_FIELD_OFF(rx_mc_pkts)}, + {"xgmac_rx_bc_pkt", MAC_STATS_FIELD_OFF(rx_bc_pkts)}, + {"xgmac_rx_pause_frame_num", MAC_STATS_FIELD_OFF(rx_pfc_tc0)}, + {"xgmac_rx_pfc_per_1pause_frame", MAC_STATS_FIELD_OFF(rx_pfc_tc1)}, + {"xgmac_rx_pfc_per_2pause_frame", MAC_STATS_FIELD_OFF(rx_pfc_tc2)}, + {"xgmac_rx_pfc_per_3pause_frame", MAC_STATS_FIELD_OFF(rx_pfc_tc3)}, + {"xgmac_rx_pfc_per_4pause_frame", MAC_STATS_FIELD_OFF(rx_pfc_tc4)}, + {"xgmac_rx_pfc_per_5pause_frame", MAC_STATS_FIELD_OFF(rx_pfc_tc5)}, + {"xgmac_rx_pfc_per_6pause_frame", MAC_STATS_FIELD_OFF(rx_pfc_tc6)}, + {"xgmac_rx_pfc_per_7pause_frame", MAC_STATS_FIELD_OFF(rx_pfc_tc7)}, + {"xgmac_rx_mac_control", MAC_STATS_FIELD_OFF(rx_unknown_ctrl)}, + {"xgmac_tx_good_pkt_todsaf", MAC_STATS_FIELD_OFF(tx_good_to_sw)}, + {"xgmac_tx_bad_pkt_todsaf", MAC_STATS_FIELD_OFF(tx_bad_to_sw)}, + {"xgmac_rx_1731_pkt", MAC_STATS_FIELD_OFF(rx_1731_pkts)}, + {"xgmac_rx_symbol_err_pkt", MAC_STATS_FIELD_OFF(rx_symbol_err)}, + {"xgmac_rx_fcs_pkt", MAC_STATS_FIELD_OFF(rx_fcs_err)} +}; + +/** + *hns_xgmac_tx_enable - xgmac port tx enable + *@drv: mac driver + *@value: value of enable + */ +static void hns_xgmac_tx_enable(struct mac_driver *drv, u32 value) +{ + dsaf_set_dev_bit(drv, XGMAC_MAC_ENABLE_REG, XGMAC_ENABLE_TX_B, !!value); +} + +/** + *hns_xgmac_rx_enable - xgmac port rx enable + *@drv: mac driver + *@value: value of enable + */ +static void hns_xgmac_rx_enable(struct mac_driver *drv, u32 value) +{ + dsaf_set_dev_bit(drv, XGMAC_MAC_ENABLE_REG, XGMAC_ENABLE_RX_B, !!value); +} + +/** + *hns_xgmac_enable - enable xgmac port + *@drv: mac driver + *@mode: mode of mac port + */ +static void hns_xgmac_enable(void *mac_drv, enum mac_commom_mode mode) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + struct dsaf_device *dsaf_dev + = (struct dsaf_device *)dev_get_drvdata(drv->dev); + u32 port = drv->mac_id; + + hns_dsaf_xge_core_srst_by_port(dsaf_dev, port, 1); + mdelay(10); + + /*enable XGE rX/tX */ + if (mode == MAC_COMM_MODE_TX) { + hns_xgmac_tx_enable(drv, 1); + } else if (mode == MAC_COMM_MODE_RX) { + hns_xgmac_rx_enable(drv, 1); + } else if (mode == MAC_COMM_MODE_RX_AND_TX) { + hns_xgmac_tx_enable(drv, 1); + hns_xgmac_rx_enable(drv, 1); + } else { + dev_err(drv->dev, "error mac mode:%d\n", mode); + } +} + +/** + *hns_xgmac_disable - disable xgmac port + *@mac_drv: mac driver + *@mode: mode of mac port + */ +static void hns_xgmac_disable(void *mac_drv, enum mac_commom_mode mode) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + struct dsaf_device *dsaf_dev + = (struct dsaf_device *)dev_get_drvdata(drv->dev); + u32 port = drv->mac_id; + + if (mode == MAC_COMM_MODE_TX) { + hns_xgmac_tx_enable(drv, 0); + } else if (mode == MAC_COMM_MODE_RX) { + hns_xgmac_rx_enable(drv, 0); + } else if (mode == MAC_COMM_MODE_RX_AND_TX) { + hns_xgmac_tx_enable(drv, 0); + hns_xgmac_rx_enable(drv, 0); + } + + mdelay(10); + hns_dsaf_xge_core_srst_by_port(dsaf_dev, port, 0); +} + +/** + *hns_xgmac_pma_fec_enable - xgmac PMA FEC enable + *@drv: mac driver + *@tx_value: tx value + *@rx_value: rx value + *return status + */ +static void hns_xgmac_pma_fec_enable(struct mac_driver *drv, u32 tx_value, + u32 rx_value) +{ + u32 origin = dsaf_read_dev(drv, XGMAC_PMA_FEC_CONTROL_REG); + + dsaf_set_bit(origin, XGMAC_PMA_FEC_CTL_TX_B, !!tx_value); + dsaf_set_bit(origin, XGMAC_PMA_FEC_CTL_RX_B, !!rx_value); + dsaf_write_dev(drv, XGMAC_PMA_FEC_CONTROL_REG, origin); +} + +/* clr exc irq for xge*/ +static void hns_xgmac_exc_irq_en(struct mac_driver *drv, u32 en) +{ + u32 clr_vlue = 0xfffffffful; + u32 msk_vlue = en ? 0xfffffffful : 0; /*1 is en, 0 is dis*/ + + dsaf_write_dev(drv, XGMAC_INT_STATUS_REG, clr_vlue); + dsaf_write_dev(drv, XGMAC_INT_ENABLE_REG, msk_vlue); +} + +/** + *hns_xgmac_init - initialize XGE + *@mac_drv: mac driver + */ +static void hns_xgmac_init(void *mac_drv) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + struct dsaf_device *dsaf_dev + = (struct dsaf_device *)dev_get_drvdata(drv->dev); + u32 port = drv->mac_id; + + hns_dsaf_xge_srst_by_port(dsaf_dev, port, 0); + mdelay(100); + hns_dsaf_xge_srst_by_port(dsaf_dev, port, 1); + + mdelay(100); + hns_xgmac_exc_irq_en(drv, 0); + + hns_xgmac_pma_fec_enable(drv, 0x0, 0x0); + + hns_xgmac_disable(mac_drv, MAC_COMM_MODE_RX_AND_TX); +} + +/** + *hns_xgmac_config_pad_and_crc - set xgmac pad and crc enable the same time + *@mac_drv: mac driver + *@newval:enable of pad and crc + */ +static void hns_xgmac_config_pad_and_crc(void *mac_drv, u8 newval) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + u32 origin = dsaf_read_dev(drv, XGMAC_MAC_CONTROL_REG); + + dsaf_set_bit(origin, XGMAC_CTL_TX_PAD_B, !!newval); + dsaf_set_bit(origin, XGMAC_CTL_TX_FCS_B, !!newval); + dsaf_set_bit(origin, XGMAC_CTL_RX_FCS_B, !!newval); + dsaf_write_dev(drv, XGMAC_MAC_CONTROL_REG, origin); +} + +/** + *hns_xgmac_pausefrm_cfg - set pause param about xgmac + *@mac_drv: mac driver + *@newval:enable of pad and crc + */ +static void hns_xgmac_pausefrm_cfg(void *mac_drv, u32 rx_en, u32 tx_en) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + u32 origin = dsaf_read_dev(drv, XGMAC_MAC_PAUSE_CTRL_REG); + + dsaf_set_bit(origin, XGMAC_PAUSE_CTL_TX_B, !!tx_en); + dsaf_set_bit(origin, XGMAC_PAUSE_CTL_RX_B, !!rx_en); + dsaf_write_dev(drv, XGMAC_MAC_PAUSE_CTRL_REG, origin); +} + +static void hns_xgmac_set_pausefrm_mac_addr(void *mac_drv, char *mac_addr) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + + u32 high_val = mac_addr[1] | (mac_addr[0] << 8); + u32 low_val = mac_addr[5] | (mac_addr[4] << 8) + | (mac_addr[3] << 16) | (mac_addr[2] << 24); + dsaf_write_dev(drv, XGMAC_MAC_PAUSE_LOCAL_MAC_L_REG, low_val); + dsaf_write_dev(drv, XGMAC_MAC_PAUSE_LOCAL_MAC_H_REG, high_val); +} + +/** + *hns_xgmac_set_rx_ignore_pause_frames - set rx pause param about xgmac + *@mac_drv: mac driver + *@enable:enable rx pause param + */ +static void hns_xgmac_set_rx_ignore_pause_frames(void *mac_drv, u32 enable) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + + dsaf_set_dev_bit(drv, XGMAC_MAC_PAUSE_CTRL_REG, + XGMAC_PAUSE_CTL_RX_B, !!enable); +} + +/** + *hns_xgmac_set_tx_auto_pause_frames - set tx pause param about xgmac + *@mac_drv: mac driver + *@enable:enable tx pause param + */ +static void hns_xgmac_set_tx_auto_pause_frames(void *mac_drv, u16 enable) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + + dsaf_set_dev_bit(drv, XGMAC_MAC_PAUSE_CTRL_REG, + XGMAC_PAUSE_CTL_TX_B, !!enable); + + /*if enable is not zero ,set tx pause time */ + if (enable) + dsaf_write_dev(drv, XGMAC_MAC_PAUSE_TIME_REG, enable); +} + +/** + *hns_xgmac_get_id - get xgmac port id + *@mac_drv: mac driver + *@newval:xgmac max frame length + */ +static void hns_xgmac_get_id(void *mac_drv, u8 *mac_id) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + + *mac_id = drv->mac_id; +} + +/** + *hns_xgmac_config_max_frame_length - set xgmac max frame length + *@mac_drv: mac driver + *@newval:xgmac max frame length + */ +static void hns_xgmac_config_max_frame_length(void *mac_drv, u16 newval) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + + dsaf_write_dev(drv, XGMAC_MAC_MAX_PKT_SIZE_REG, newval); +} + +void hns_xgmac_update_stats(void *mac_drv) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + struct mac_hw_stats *hw_stats = &drv->mac_cb->hw_stats; + + /* TX */ + hw_stats->tx_fragment_err + = hns_mac_reg_read64(drv, XGMAC_TX_PKTS_FRAGMENT); + hw_stats->tx_undersize + = hns_mac_reg_read64(drv, XGMAC_TX_PKTS_UNDERSIZE); + hw_stats->tx_under_min_pkts + = hns_mac_reg_read64(drv, XGMAC_TX_PKTS_UNDERMIN); + hw_stats->tx_64bytes = hns_mac_reg_read64(drv, XGMAC_TX_PKTS_64OCTETS); + hw_stats->tx_65to127 + = hns_mac_reg_read64(drv, XGMAC_TX_PKTS_65TO127OCTETS); + hw_stats->tx_128to255 + = hns_mac_reg_read64(drv, XGMAC_TX_PKTS_128TO255OCTETS); + hw_stats->tx_256to511 + = hns_mac_reg_read64(drv, XGMAC_TX_PKTS_256TO511OCTETS); + hw_stats->tx_512to1023 + = hns_mac_reg_read64(drv, XGMAC_TX_PKTS_512TO1023OCTETS); + hw_stats->tx_1024to1518 + = hns_mac_reg_read64(drv, XGMAC_TX_PKTS_1024TO1518OCTETS); + hw_stats->tx_1519tomax + = hns_mac_reg_read64(drv, XGMAC_TX_PKTS_1519TOMAXOCTETS); + hw_stats->tx_1519tomax_good + = hns_mac_reg_read64(drv, XGMAC_TX_PKTS_1519TOMAXOCTETSOK); + hw_stats->tx_oversize = hns_mac_reg_read64(drv, XGMAC_TX_PKTS_OVERSIZE); + hw_stats->tx_jabber_err = hns_mac_reg_read64(drv, XGMAC_TX_PKTS_JABBER); + hw_stats->tx_good_pkts = hns_mac_reg_read64(drv, XGMAC_TX_GOODPKTS); + hw_stats->tx_good_bytes = hns_mac_reg_read64(drv, XGMAC_TX_GOODOCTETS); + hw_stats->tx_total_pkts = hns_mac_reg_read64(drv, XGMAC_TX_TOTAL_PKTS); + hw_stats->tx_total_bytes + = hns_mac_reg_read64(drv, XGMAC_TX_TOTALOCTETS); + hw_stats->tx_uc_pkts = hns_mac_reg_read64(drv, XGMAC_TX_UNICASTPKTS); + hw_stats->tx_mc_pkts = hns_mac_reg_read64(drv, XGMAC_TX_MULTICASTPKTS); + hw_stats->tx_bc_pkts = hns_mac_reg_read64(drv, XGMAC_TX_BROADCASTPKTS); + hw_stats->tx_pfc_tc0 = hns_mac_reg_read64(drv, XGMAC_TX_PRI0PAUSEPKTS); + hw_stats->tx_pfc_tc1 = hns_mac_reg_read64(drv, XGMAC_TX_PRI1PAUSEPKTS); + hw_stats->tx_pfc_tc2 = hns_mac_reg_read64(drv, XGMAC_TX_PRI2PAUSEPKTS); + hw_stats->tx_pfc_tc3 = hns_mac_reg_read64(drv, XGMAC_TX_PRI3PAUSEPKTS); + hw_stats->tx_pfc_tc4 = hns_mac_reg_read64(drv, XGMAC_TX_PRI4PAUSEPKTS); + hw_stats->tx_pfc_tc5 = hns_mac_reg_read64(drv, XGMAC_TX_PRI5PAUSEPKTS); + hw_stats->tx_pfc_tc6 = hns_mac_reg_read64(drv, XGMAC_TX_PRI6PAUSEPKTS); + hw_stats->tx_pfc_tc7 = hns_mac_reg_read64(drv, XGMAC_TX_PRI7PAUSEPKTS); + hw_stats->tx_ctrl = hns_mac_reg_read64(drv, XGMAC_TX_MACCTRLPKTS); + hw_stats->tx_1731_pkts = hns_mac_reg_read64(drv, XGMAC_TX_1731PKTS); + hw_stats->tx_1588_pkts = hns_mac_reg_read64(drv, XGMAC_TX_1588PKTS); + hw_stats->rx_good_from_sw + = hns_mac_reg_read64(drv, XGMAC_RX_FROMAPPGOODPKTS); + hw_stats->rx_bad_from_sw + = hns_mac_reg_read64(drv, XGMAC_RX_FROMAPPBADPKTS); + hw_stats->tx_bad_pkts = hns_mac_reg_read64(drv, XGMAC_TX_ERRALLPKTS); + + /* RX */ + hw_stats->rx_fragment_err + = hns_mac_reg_read64(drv, XGMAC_RX_PKTS_FRAGMENT); + hw_stats->rx_undersize + = hns_mac_reg_read64(drv, XGMAC_RX_PKTSUNDERSIZE); + hw_stats->rx_under_min + = hns_mac_reg_read64(drv, XGMAC_RX_PKTS_UNDERMIN); + hw_stats->rx_64bytes = hns_mac_reg_read64(drv, XGMAC_RX_PKTS_64OCTETS); + hw_stats->rx_65to127 + = hns_mac_reg_read64(drv, XGMAC_RX_PKTS_65TO127OCTETS); + hw_stats->rx_128to255 + = hns_mac_reg_read64(drv, XGMAC_RX_PKTS_128TO255OCTETS); + hw_stats->rx_256to511 + = hns_mac_reg_read64(drv, XGMAC_RX_PKTS_256TO511OCTETS); + hw_stats->rx_512to1023 + = hns_mac_reg_read64(drv, XGMAC_RX_PKTS_512TO1023OCTETS); + hw_stats->rx_1024to1518 + = hns_mac_reg_read64(drv, XGMAC_RX_PKTS_1024TO1518OCTETS); + hw_stats->rx_1519tomax + = hns_mac_reg_read64(drv, XGMAC_RX_PKTS_1519TOMAXOCTETS); + hw_stats->rx_1519tomax_good + = hns_mac_reg_read64(drv, XGMAC_RX_PKTS_1519TOMAXOCTETSOK); + hw_stats->rx_oversize = hns_mac_reg_read64(drv, XGMAC_RX_PKTS_OVERSIZE); + hw_stats->rx_jabber_err = hns_mac_reg_read64(drv, XGMAC_RX_PKTS_JABBER); + hw_stats->rx_good_pkts = hns_mac_reg_read64(drv, XGMAC_RX_GOODPKTS); + hw_stats->rx_good_bytes = hns_mac_reg_read64(drv, XGMAC_RX_GOODOCTETS); + hw_stats->rx_total_pkts = hns_mac_reg_read64(drv, XGMAC_RX_TOTAL_PKTS); + hw_stats->rx_total_bytes + = hns_mac_reg_read64(drv, XGMAC_RX_TOTALOCTETS); + hw_stats->rx_uc_pkts = hns_mac_reg_read64(drv, XGMAC_RX_UNICASTPKTS); + hw_stats->rx_mc_pkts = hns_mac_reg_read64(drv, XGMAC_RX_MULTICASTPKTS); + hw_stats->rx_bc_pkts = hns_mac_reg_read64(drv, XGMAC_RX_BROADCASTPKTS); + hw_stats->rx_pfc_tc0 = hns_mac_reg_read64(drv, XGMAC_RX_PRI0PAUSEPKTS); + hw_stats->rx_pfc_tc1 = hns_mac_reg_read64(drv, XGMAC_RX_PRI1PAUSEPKTS); + hw_stats->rx_pfc_tc2 = hns_mac_reg_read64(drv, XGMAC_RX_PRI2PAUSEPKTS); + hw_stats->rx_pfc_tc3 = hns_mac_reg_read64(drv, XGMAC_RX_PRI3PAUSEPKTS); + hw_stats->rx_pfc_tc4 = hns_mac_reg_read64(drv, XGMAC_RX_PRI4PAUSEPKTS); + hw_stats->rx_pfc_tc5 = hns_mac_reg_read64(drv, XGMAC_RX_PRI5PAUSEPKTS); + hw_stats->rx_pfc_tc6 = hns_mac_reg_read64(drv, XGMAC_RX_PRI6PAUSEPKTS); + hw_stats->rx_pfc_tc7 = hns_mac_reg_read64(drv, XGMAC_RX_PRI7PAUSEPKTS); + + hw_stats->rx_unknown_ctrl + = hns_mac_reg_read64(drv, XGMAC_RX_MACCTRLPKTS); + hw_stats->tx_good_to_sw + = hns_mac_reg_read64(drv, XGMAC_TX_SENDAPPGOODPKTS); + hw_stats->tx_bad_to_sw + = hns_mac_reg_read64(drv, XGMAC_TX_SENDAPPBADPKTS); + hw_stats->rx_1731_pkts = hns_mac_reg_read64(drv, XGMAC_RX_1731PKTS); + hw_stats->rx_symbol_err + = hns_mac_reg_read64(drv, XGMAC_RX_SYMBOLERRPKTS); + hw_stats->rx_fcs_err = hns_mac_reg_read64(drv, XGMAC_RX_FCSERRPKTS); +} + +/** + *hns_xgmac_free - free xgmac driver + *@mac_drv: mac driver + */ +static void hns_xgmac_free(void *mac_drv) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + struct dsaf_device *dsaf_dev + = (struct dsaf_device *)dev_get_drvdata(drv->dev); + + u32 mac_id = drv->mac_id; + + hns_dsaf_xge_srst_by_port(dsaf_dev, mac_id, 0); +} + +/** + *hns_xgmac_get_info - get xgmac information + *@mac_drv: mac driver + *@mac_info:mac information + */ +static void hns_xgmac_get_info(void *mac_drv, struct mac_info *mac_info) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + u32 pause_time, pause_ctrl, port_mode, ctrl_val; + + ctrl_val = dsaf_read_dev(drv, XGMAC_MAC_CONTROL_REG); + mac_info->pad_and_crc_en = dsaf_get_bit(ctrl_val, XGMAC_CTL_TX_PAD_B); + mac_info->auto_neg = 0; + + pause_time = dsaf_read_dev(drv, XGMAC_MAC_PAUSE_TIME_REG); + mac_info->tx_pause_time = pause_time; + + port_mode = dsaf_read_dev(drv, XGMAC_PORT_MODE_REG); + mac_info->port_en = dsaf_get_field(port_mode, XGMAC_PORT_MODE_TX_M, + XGMAC_PORT_MODE_TX_S) && + dsaf_get_field(port_mode, XGMAC_PORT_MODE_RX_M, + XGMAC_PORT_MODE_RX_S); + mac_info->duplex = 1; + mac_info->speed = MAC_SPEED_10000; + + pause_ctrl = dsaf_read_dev(drv, XGMAC_MAC_PAUSE_CTRL_REG); + mac_info->rx_pause_en = dsaf_get_bit(pause_ctrl, XGMAC_PAUSE_CTL_RX_B); + mac_info->tx_pause_en = dsaf_get_bit(pause_ctrl, XGMAC_PAUSE_CTL_TX_B); +} + +/** + *hns_xgmac_get_pausefrm_cfg - get xgmac pause param + *@mac_drv: mac driver + *@rx_en:xgmac rx pause enable + *@tx_en:xgmac tx pause enable + */ +static void hns_xgmac_get_pausefrm_cfg(void *mac_drv, u32 *rx_en, u32 *tx_en) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + u32 pause_ctrl; + + pause_ctrl = dsaf_read_dev(drv, XGMAC_MAC_PAUSE_CTRL_REG); + *rx_en = dsaf_get_bit(pause_ctrl, XGMAC_PAUSE_CTL_RX_B); + *tx_en = dsaf_get_bit(pause_ctrl, XGMAC_PAUSE_CTL_TX_B); +} + +/** + *hns_xgmac_get_link_status - get xgmac link status + *@mac_drv: mac driver + *@link_stat: xgmac link stat + */ +static void hns_xgmac_get_link_status(void *mac_drv, u32 *link_stat) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + + *link_stat = dsaf_read_dev(drv, XGMAC_LINK_STATUS_REG); +} + +/** + *hns_xgmac_get_regs - dump xgmac regs + *@mac_drv: mac driver + *@cmd:ethtool cmd + *@data:data for value of regs + */ +static void hns_xgmac_get_regs(void *mac_drv, void *data) +{ + u32 i = 0; + struct mac_driver *drv = (struct mac_driver *)mac_drv; + u32 *regs = data; + u64 qtmp; + + /* base config registers */ + regs[0] = dsaf_read_dev(drv, XGMAC_INT_STATUS_REG); + regs[1] = dsaf_read_dev(drv, XGMAC_INT_ENABLE_REG); + regs[2] = dsaf_read_dev(drv, XGMAC_INT_SET_REG); + regs[3] = dsaf_read_dev(drv, XGMAC_IERR_U_INFO_REG); + regs[4] = dsaf_read_dev(drv, XGMAC_OVF_INFO_REG); + regs[5] = dsaf_read_dev(drv, XGMAC_OVF_CNT_REG); + regs[6] = dsaf_read_dev(drv, XGMAC_PORT_MODE_REG); + regs[7] = dsaf_read_dev(drv, XGMAC_CLK_ENABLE_REG); + regs[8] = dsaf_read_dev(drv, XGMAC_RESET_REG); + regs[9] = dsaf_read_dev(drv, XGMAC_LINK_CONTROL_REG); + regs[10] = dsaf_read_dev(drv, XGMAC_LINK_STATUS_REG); + + regs[11] = dsaf_read_dev(drv, XGMAC_SPARE_REG); + regs[12] = dsaf_read_dev(drv, XGMAC_SPARE_CNT_REG); + regs[13] = dsaf_read_dev(drv, XGMAC_MAC_ENABLE_REG); + regs[14] = dsaf_read_dev(drv, XGMAC_MAC_CONTROL_REG); + regs[15] = dsaf_read_dev(drv, XGMAC_MAC_IPG_REG); + regs[16] = dsaf_read_dev(drv, XGMAC_MAC_MSG_CRC_EN_REG); + regs[17] = dsaf_read_dev(drv, XGMAC_MAC_MSG_IMG_REG); + regs[18] = dsaf_read_dev(drv, XGMAC_MAC_MSG_FC_CFG_REG); + regs[19] = dsaf_read_dev(drv, XGMAC_MAC_MSG_TC_CFG_REG); + regs[20] = dsaf_read_dev(drv, XGMAC_MAC_PAD_SIZE_REG); + regs[21] = dsaf_read_dev(drv, XGMAC_MAC_MIN_PKT_SIZE_REG); + regs[22] = dsaf_read_dev(drv, XGMAC_MAC_MAX_PKT_SIZE_REG); + regs[23] = dsaf_read_dev(drv, XGMAC_MAC_PAUSE_CTRL_REG); + regs[24] = dsaf_read_dev(drv, XGMAC_MAC_PAUSE_TIME_REG); + regs[25] = dsaf_read_dev(drv, XGMAC_MAC_PAUSE_GAP_REG); + regs[26] = dsaf_read_dev(drv, XGMAC_MAC_PAUSE_LOCAL_MAC_H_REG); + regs[27] = dsaf_read_dev(drv, XGMAC_MAC_PAUSE_LOCAL_MAC_L_REG); + regs[28] = dsaf_read_dev(drv, XGMAC_MAC_PAUSE_PEER_MAC_H_REG); + regs[29] = dsaf_read_dev(drv, XGMAC_MAC_PAUSE_PEER_MAC_L_REG); + regs[30] = dsaf_read_dev(drv, XGMAC_MAC_PFC_PRI_EN_REG); + regs[31] = dsaf_read_dev(drv, XGMAC_MAC_1588_CTRL_REG); + regs[32] = dsaf_read_dev(drv, XGMAC_MAC_1588_TX_PORT_DLY_REG); + regs[33] = dsaf_read_dev(drv, XGMAC_MAC_1588_RX_PORT_DLY_REG); + regs[34] = dsaf_read_dev(drv, XGMAC_MAC_1588_ASYM_DLY_REG); + regs[35] = dsaf_read_dev(drv, XGMAC_MAC_1588_ADJUST_CFG_REG); + + regs[36] = dsaf_read_dev(drv, XGMAC_MAC_Y1731_ETH_TYPE_REG); + regs[37] = dsaf_read_dev(drv, XGMAC_MAC_MIB_CONTROL_REG); + regs[38] = dsaf_read_dev(drv, XGMAC_MAC_WAN_RATE_ADJUST_REG); + regs[39] = dsaf_read_dev(drv, XGMAC_MAC_TX_ERR_MARK_REG); + regs[40] = dsaf_read_dev(drv, XGMAC_MAC_TX_LF_RF_CONTROL_REG); + regs[41] = dsaf_read_dev(drv, XGMAC_MAC_RX_LF_RF_STATUS_REG); + regs[42] = dsaf_read_dev(drv, XGMAC_MAC_TX_RUNT_PKT_CNT_REG); + regs[43] = dsaf_read_dev(drv, XGMAC_MAC_RX_RUNT_PKT_CNT_REG); + regs[44] = dsaf_read_dev(drv, XGMAC_MAC_RX_PREAM_ERR_PKT_CNT_REG); + regs[45] = dsaf_read_dev(drv, XGMAC_MAC_TX_LF_RF_TERM_PKT_CNT_REG); + regs[46] = dsaf_read_dev(drv, XGMAC_MAC_TX_SN_MISMATCH_PKT_CNT_REG); + regs[47] = dsaf_read_dev(drv, XGMAC_MAC_RX_ERR_MSG_CNT_REG); + regs[48] = dsaf_read_dev(drv, XGMAC_MAC_RX_ERR_EFD_CNT_REG); + regs[49] = dsaf_read_dev(drv, XGMAC_MAC_ERR_INFO_REG); + regs[50] = dsaf_read_dev(drv, XGMAC_MAC_DBG_INFO_REG); + + regs[51] = dsaf_read_dev(drv, XGMAC_PCS_BASER_SYNC_THD_REG); + regs[52] = dsaf_read_dev(drv, XGMAC_PCS_STATUS1_REG); + regs[53] = dsaf_read_dev(drv, XGMAC_PCS_BASER_STATUS1_REG); + regs[54] = dsaf_read_dev(drv, XGMAC_PCS_BASER_STATUS2_REG); + regs[55] = dsaf_read_dev(drv, XGMAC_PCS_BASER_SEEDA_0_REG); + regs[56] = dsaf_read_dev(drv, XGMAC_PCS_BASER_SEEDA_1_REG); + regs[57] = dsaf_read_dev(drv, XGMAC_PCS_BASER_SEEDB_0_REG); + regs[58] = dsaf_read_dev(drv, XGMAC_PCS_BASER_SEEDB_1_REG); + regs[59] = dsaf_read_dev(drv, XGMAC_PCS_BASER_TEST_CONTROL_REG); + regs[60] = dsaf_read_dev(drv, XGMAC_PCS_BASER_TEST_ERR_CNT_REG); + regs[61] = dsaf_read_dev(drv, XGMAC_PCS_DBG_INFO_REG); + regs[62] = dsaf_read_dev(drv, XGMAC_PCS_DBG_INFO1_REG); + regs[63] = dsaf_read_dev(drv, XGMAC_PCS_DBG_INFO2_REG); + regs[64] = dsaf_read_dev(drv, XGMAC_PCS_DBG_INFO3_REG); + + regs[65] = dsaf_read_dev(drv, XGMAC_PMA_ENABLE_REG); + regs[66] = dsaf_read_dev(drv, XGMAC_PMA_CONTROL_REG); + regs[67] = dsaf_read_dev(drv, XGMAC_PMA_SIGNAL_STATUS_REG); + regs[68] = dsaf_read_dev(drv, XGMAC_PMA_DBG_INFO_REG); + regs[69] = dsaf_read_dev(drv, XGMAC_PMA_FEC_ABILITY_REG); + regs[70] = dsaf_read_dev(drv, XGMAC_PMA_FEC_CONTROL_REG); + regs[71] = dsaf_read_dev(drv, XGMAC_PMA_FEC_CORR_BLOCK_CNT__REG); + regs[72] = dsaf_read_dev(drv, XGMAC_PMA_FEC_UNCORR_BLOCK_CNT__REG); + + /* status registers */ +#define hns_xgmac_cpy_q(p, q) \ + do {\ + *(p) = (u32)(q);\ + *((p) + 1) = (u32)((q) >> 32);\ + } while (0) + + qtmp = hns_mac_reg_read64(drv, XGMAC_TX_PKTS_FRAGMENT); + hns_xgmac_cpy_q(®s[73], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_TX_PKTS_UNDERSIZE); + hns_xgmac_cpy_q(®s[75], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_TX_PKTS_UNDERMIN); + hns_xgmac_cpy_q(®s[77], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_TX_PKTS_64OCTETS); + hns_xgmac_cpy_q(®s[79], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_TX_PKTS_65TO127OCTETS); + hns_xgmac_cpy_q(®s[81], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_TX_PKTS_128TO255OCTETS); + hns_xgmac_cpy_q(®s[83], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_TX_PKTS_256TO511OCTETS); + hns_xgmac_cpy_q(®s[85], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_TX_PKTS_512TO1023OCTETS); + hns_xgmac_cpy_q(®s[87], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_TX_PKTS_1024TO1518OCTETS); + hns_xgmac_cpy_q(®s[89], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_TX_PKTS_1519TOMAXOCTETS); + hns_xgmac_cpy_q(®s[91], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_TX_PKTS_1519TOMAXOCTETSOK); + hns_xgmac_cpy_q(®s[93], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_TX_PKTS_OVERSIZE); + hns_xgmac_cpy_q(®s[95], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_TX_PKTS_JABBER); + hns_xgmac_cpy_q(®s[97], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_TX_GOODPKTS); + hns_xgmac_cpy_q(®s[99], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_TX_GOODOCTETS); + hns_xgmac_cpy_q(®s[101], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_TX_TOTAL_PKTS); + hns_xgmac_cpy_q(®s[103], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_TX_TOTALOCTETS); + hns_xgmac_cpy_q(®s[105], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_TX_UNICASTPKTS); + hns_xgmac_cpy_q(®s[107], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_TX_MULTICASTPKTS); + hns_xgmac_cpy_q(®s[109], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_TX_BROADCASTPKTS); + hns_xgmac_cpy_q(®s[111], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_TX_PRI0PAUSEPKTS); + hns_xgmac_cpy_q(®s[113], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_TX_PRI1PAUSEPKTS); + hns_xgmac_cpy_q(®s[115], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_TX_PRI2PAUSEPKTS); + hns_xgmac_cpy_q(®s[117], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_TX_PRI3PAUSEPKTS); + hns_xgmac_cpy_q(®s[119], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_TX_PRI4PAUSEPKTS); + hns_xgmac_cpy_q(®s[121], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_TX_PRI5PAUSEPKTS); + hns_xgmac_cpy_q(®s[123], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_TX_PRI6PAUSEPKTS); + hns_xgmac_cpy_q(®s[125], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_TX_PRI7PAUSEPKTS); + hns_xgmac_cpy_q(®s[127], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_TX_MACCTRLPKTS); + hns_xgmac_cpy_q(®s[129], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_TX_1731PKTS); + hns_xgmac_cpy_q(®s[131], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_TX_1588PKTS); + hns_xgmac_cpy_q(®s[133], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_RX_FROMAPPGOODPKTS); + hns_xgmac_cpy_q(®s[135], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_RX_FROMAPPBADPKTS); + hns_xgmac_cpy_q(®s[137], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_TX_ERRALLPKTS); + hns_xgmac_cpy_q(®s[139], qtmp); + + /* RX */ + qtmp = hns_mac_reg_read64(drv, XGMAC_RX_PKTS_FRAGMENT); + hns_xgmac_cpy_q(®s[141], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_RX_PKTSUNDERSIZE); + hns_xgmac_cpy_q(®s[143], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_RX_PKTS_UNDERMIN); + hns_xgmac_cpy_q(®s[145], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_RX_PKTS_64OCTETS); + hns_xgmac_cpy_q(®s[147], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_RX_PKTS_65TO127OCTETS); + hns_xgmac_cpy_q(®s[149], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_RX_PKTS_128TO255OCTETS); + hns_xgmac_cpy_q(®s[151], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_RX_PKTS_256TO511OCTETS); + hns_xgmac_cpy_q(®s[153], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_RX_PKTS_512TO1023OCTETS); + hns_xgmac_cpy_q(®s[155], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_RX_PKTS_1024TO1518OCTETS); + hns_xgmac_cpy_q(®s[157], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_RX_PKTS_1519TOMAXOCTETS); + hns_xgmac_cpy_q(®s[159], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_RX_PKTS_1519TOMAXOCTETSOK); + hns_xgmac_cpy_q(®s[161], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_RX_PKTS_OVERSIZE); + hns_xgmac_cpy_q(®s[163], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_RX_PKTS_JABBER); + hns_xgmac_cpy_q(®s[165], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_RX_GOODPKTS); + hns_xgmac_cpy_q(®s[167], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_RX_GOODOCTETS); + hns_xgmac_cpy_q(®s[169], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_RX_TOTAL_PKTS); + hns_xgmac_cpy_q(®s[171], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_RX_TOTALOCTETS); + hns_xgmac_cpy_q(®s[173], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_RX_UNICASTPKTS); + hns_xgmac_cpy_q(®s[175], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_RX_MULTICASTPKTS); + hns_xgmac_cpy_q(®s[177], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_RX_BROADCASTPKTS); + hns_xgmac_cpy_q(®s[179], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_RX_PRI0PAUSEPKTS); + hns_xgmac_cpy_q(®s[181], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_RX_PRI1PAUSEPKTS); + hns_xgmac_cpy_q(®s[183], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_RX_PRI2PAUSEPKTS); + hns_xgmac_cpy_q(®s[185], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_RX_PRI3PAUSEPKTS); + hns_xgmac_cpy_q(®s[187], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_RX_PRI4PAUSEPKTS); + hns_xgmac_cpy_q(®s[189], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_RX_PRI5PAUSEPKTS); + hns_xgmac_cpy_q(®s[191], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_RX_PRI6PAUSEPKTS); + hns_xgmac_cpy_q(®s[193], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_RX_PRI7PAUSEPKTS); + hns_xgmac_cpy_q(®s[195], qtmp); + + qtmp = hns_mac_reg_read64(drv, XGMAC_RX_MACCTRLPKTS); + hns_xgmac_cpy_q(®s[197], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_TX_SENDAPPGOODPKTS); + hns_xgmac_cpy_q(®s[199], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_TX_SENDAPPBADPKTS); + hns_xgmac_cpy_q(®s[201], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_RX_1731PKTS); + hns_xgmac_cpy_q(®s[203], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_RX_SYMBOLERRPKTS); + hns_xgmac_cpy_q(®s[205], qtmp); + qtmp = hns_mac_reg_read64(drv, XGMAC_RX_FCSERRPKTS); + hns_xgmac_cpy_q(®s[207], qtmp); + + /* mark end of mac regs */ + for (i = 208; i < 214; i++) + regs[i] = 0xaaaaaaaa; +} + +/** + *hns_xgmac_get_stats - get xgmac statistic + *@mac_drv: mac driver + *@data:data for value of stats regs + */ +static void hns_xgmac_get_stats(void *mac_drv, u64 *data) +{ + u32 i; + u64 *buf = data; + struct mac_driver *drv = (struct mac_driver *)mac_drv; + struct mac_hw_stats *hw_stats = NULL; + + hw_stats = &drv->mac_cb->hw_stats; + + for (i = 0; i < ARRAY_SIZE(g_xgmac_stats_string); i++) { + buf[i] = DSAF_STATS_READ(hw_stats, + g_xgmac_stats_string[i].offset); + } +} + +/** + *hns_xgmac_get_strings - get xgmac strings name + *@stringset: type of values in data + *@data:data for value of string name + */ +static void hns_xgmac_get_strings(u32 stringset, u8 *data) +{ + char *buff = (char *)data; + u32 i; + + if (stringset != ETH_SS_STATS) + return; + + for (i = 0; i < ARRAY_SIZE(g_xgmac_stats_string); i++) { + snprintf(buff, ETH_GSTRING_LEN, g_xgmac_stats_string[i].desc); + buff = buff + ETH_GSTRING_LEN; + } +} + +/** + *hns_xgmac_get_sset_count - get xgmac string set count + *@stringset: type of values in data + *return xgmac string set count + */ +static int hns_xgmac_get_sset_count(int stringset) +{ + if (stringset == ETH_SS_STATS) + return ARRAY_SIZE(g_xgmac_stats_string); + + return 0; +} + +/** + *hns_xgmac_get_regs_count - get xgmac regs count + *return xgmac regs count + */ +static int hns_xgmac_get_regs_count(void) +{ + return ETH_XGMAC_DUMP_NUM; +} + +void *hns_xgmac_config(struct hns_mac_cb *mac_cb, struct mac_params *mac_param) +{ + struct mac_driver *mac_drv; + + mac_drv = devm_kzalloc(mac_cb->dev, sizeof(*mac_drv), GFP_KERNEL); + if (!mac_drv) + return NULL; + + mac_drv->mac_init = hns_xgmac_init; + mac_drv->mac_enable = hns_xgmac_enable; + mac_drv->mac_disable = hns_xgmac_disable; + + mac_drv->mac_id = mac_param->mac_id; + mac_drv->mac_mode = mac_param->mac_mode; + mac_drv->io_base = mac_param->vaddr; + mac_drv->dev = mac_param->dev; + mac_drv->mac_cb = mac_cb; + + mac_drv->set_mac_addr = hns_xgmac_set_pausefrm_mac_addr; + mac_drv->set_an_mode = NULL; + mac_drv->config_loopback = NULL; + mac_drv->config_pad_and_crc = hns_xgmac_config_pad_and_crc; + mac_drv->config_half_duplex = NULL; + mac_drv->set_rx_ignore_pause_frames = + hns_xgmac_set_rx_ignore_pause_frames; + mac_drv->mac_get_id = hns_xgmac_get_id; + mac_drv->mac_free = hns_xgmac_free; + mac_drv->adjust_link = NULL; + mac_drv->set_tx_auto_pause_frames = hns_xgmac_set_tx_auto_pause_frames; + mac_drv->config_max_frame_length = hns_xgmac_config_max_frame_length; + mac_drv->mac_pausefrm_cfg = hns_xgmac_pausefrm_cfg; + mac_drv->autoneg_stat = NULL; + mac_drv->get_info = hns_xgmac_get_info; + mac_drv->get_pause_enable = hns_xgmac_get_pausefrm_cfg; + mac_drv->get_link_status = hns_xgmac_get_link_status; + mac_drv->get_regs = hns_xgmac_get_regs; + mac_drv->get_ethtool_stats = hns_xgmac_get_stats; + mac_drv->get_sset_count = hns_xgmac_get_sset_count; + mac_drv->get_regs_count = hns_xgmac_get_regs_count; + mac_drv->get_strings = hns_xgmac_get_strings; + mac_drv->update_stats = hns_xgmac_update_stats; + + return (void *)mac_drv; +} diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.h new file mode 100644 index 000000000000..139f7297c7b4 --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.h @@ -0,0 +1,15 @@ +/* + * Copyright (c) 2014-2015 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef _HNS_XGMAC_H +#define _HNS_XGMAC_H + +#define ETH_XGMAC_DUMP_NUM (214) + +#endif diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c new file mode 100644 index 000000000000..ce7f2e0e3fd1 --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -0,0 +1,1629 @@ +/* + * Copyright (c) 2014-2015 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/clk.h> +#include <linux/cpumask.h> +#include <linux/etherdevice.h> +#include <linux/if_vlan.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/module.h> +#include <linux/phy.h> +#include <linux/platform_device.h> +#include <linux/skbuff.h> + +#include "hnae.h" +#include "hns_enet.h" + +#define NIC_MAX_Q_PER_VF 16 +#define HNS_NIC_TX_TIMEOUT (5 * HZ) + +#define SERVICE_TIMER_HZ (1 * HZ) + +#define NIC_TX_CLEAN_MAX_NUM 256 +#define NIC_RX_CLEAN_MAX_NUM 64 + +#define RCB_IRQ_NOT_INITED 0 +#define RCB_IRQ_INITED 1 + +static void fill_desc(struct hnae_ring *ring, void *priv, + int size, dma_addr_t dma, int frag_end, + int buf_num, enum hns_desc_type type) +{ + struct hnae_desc *desc = &ring->desc[ring->next_to_use]; + struct hnae_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_use]; + struct sk_buff *skb; + __be16 protocol; + u32 ip_offset; + u32 asid_bufnum_pid = 0; + u32 flag_ipoffset = 0; + + desc_cb->priv = priv; + desc_cb->length = size; + desc_cb->dma = dma; + desc_cb->type = type; + + desc->addr = cpu_to_le64(dma); + desc->tx.send_size = cpu_to_le16((u16)size); + + /*config bd buffer end */ + flag_ipoffset |= 1 << HNS_TXD_VLD_B; + + asid_bufnum_pid |= buf_num << HNS_TXD_BUFNUM_S; + + if (type == DESC_TYPE_SKB) { + skb = (struct sk_buff *)priv; + + if (skb->ip_summed == CHECKSUM_PARTIAL) { + protocol = skb->protocol; + ip_offset = ETH_HLEN; + + /*if it is a SW VLAN check the next protocol*/ + if (protocol == htons(ETH_P_8021Q)) { + ip_offset += VLAN_HLEN; + protocol = vlan_get_protocol(skb); + skb->protocol = protocol; + } + + if (skb->protocol == htons(ETH_P_IP)) { + flag_ipoffset |= 1 << HNS_TXD_L3CS_B; + /* check for tcp/udp header */ + flag_ipoffset |= 1 << HNS_TXD_L4CS_B; + + } else if (skb->protocol == htons(ETH_P_IPV6)) { + /* ipv6 has not l3 cs, check for L4 header */ + flag_ipoffset |= 1 << HNS_TXD_L4CS_B; + } + + flag_ipoffset |= ip_offset << HNS_TXD_IPOFFSET_S; + } + } + + flag_ipoffset |= frag_end << HNS_TXD_FE_B; + + desc->tx.asid_bufnum_pid = cpu_to_le16(asid_bufnum_pid); + desc->tx.flag_ipoffset = cpu_to_le32(flag_ipoffset); + + ring_ptr_move_fw(ring, next_to_use); +} + +static void unfill_desc(struct hnae_ring *ring) +{ + ring_ptr_move_bw(ring, next_to_use); +} + +int hns_nic_net_xmit_hw(struct net_device *ndev, + struct sk_buff *skb, + struct hns_nic_ring_data *ring_data) +{ + struct hns_nic_priv *priv = netdev_priv(ndev); + struct device *dev = priv->dev; + struct hnae_ring *ring = ring_data->ring; + struct netdev_queue *dev_queue; + struct skb_frag_struct *frag; + int buf_num; + dma_addr_t dma; + int size, next_to_use; + int i, j; + struct sk_buff *new_skb; + + assert(ring->max_desc_num_per_pkt <= ring->desc_num); + + /* no. of segments (plus a header) */ + buf_num = skb_shinfo(skb)->nr_frags + 1; + + if (unlikely(buf_num > ring->max_desc_num_per_pkt)) { + if (ring_space(ring) < 1) { + ring->stats.tx_busy++; + goto out_net_tx_busy; + } + + new_skb = skb_copy(skb, GFP_ATOMIC); + if (!new_skb) { + ring->stats.sw_err_cnt++; + netdev_err(ndev, "no memory to xmit!\n"); + goto out_err_tx_ok; + } + + dev_kfree_skb_any(skb); + skb = new_skb; + buf_num = 1; + assert(skb_shinfo(skb)->nr_frags == 1); + } else if (buf_num > ring_space(ring)) { + ring->stats.tx_busy++; + goto out_net_tx_busy; + } + next_to_use = ring->next_to_use; + + /* fill the first part */ + size = skb_headlen(skb); + dma = dma_map_single(dev, skb->data, size, DMA_TO_DEVICE); + if (dma_mapping_error(dev, dma)) { + netdev_err(ndev, "TX head DMA map failed\n"); + ring->stats.sw_err_cnt++; + goto out_err_tx_ok; + } + fill_desc(ring, skb, size, dma, buf_num == 1 ? 1 : 0, buf_num, + DESC_TYPE_SKB); + + /* fill the fragments */ + for (i = 1; i < buf_num; i++) { + frag = &skb_shinfo(skb)->frags[i - 1]; + size = skb_frag_size(frag); + dma = skb_frag_dma_map(dev, frag, 0, size, DMA_TO_DEVICE); + if (dma_mapping_error(dev, dma)) { + netdev_err(ndev, "TX frag(%d) DMA map failed\n", i); + ring->stats.sw_err_cnt++; + goto out_map_frag_fail; + } + fill_desc(ring, skb_frag_page(frag), size, dma, + buf_num - 1 == i ? 1 : 0, buf_num, DESC_TYPE_PAGE); + } + + /*complete translate all packets*/ + dev_queue = netdev_get_tx_queue(ndev, skb->queue_mapping); + netdev_tx_sent_queue(dev_queue, skb->len); + + wmb(); /* commit all data before submit */ + assert(skb->queue_mapping < priv->ae_handle->q_num); + hnae_queue_xmit(priv->ae_handle->qs[skb->queue_mapping], buf_num); + ring->stats.tx_pkts++; + ring->stats.tx_bytes += skb->len; + + return NETDEV_TX_OK; + +out_map_frag_fail: + + for (j = i - 1; j > 0; j--) { + unfill_desc(ring); + next_to_use = ring->next_to_use; + dma_unmap_page(dev, ring->desc_cb[next_to_use].dma, + ring->desc_cb[next_to_use].length, + DMA_TO_DEVICE); + } + + unfill_desc(ring); + next_to_use = ring->next_to_use; + dma_unmap_single(dev, ring->desc_cb[next_to_use].dma, + ring->desc_cb[next_to_use].length, DMA_TO_DEVICE); + +out_err_tx_ok: + + dev_kfree_skb_any(skb); + return NETDEV_TX_OK; + +out_net_tx_busy: + + netif_stop_subqueue(ndev, skb->queue_mapping); + + /* Herbert's original patch had: + * smp_mb__after_netif_stop_queue(); + * but since that doesn't exist yet, just open code it. + */ + smp_mb(); + return NETDEV_TX_BUSY; +} + +/** + * hns_nic_get_headlen - determine size of header for RSC/LRO/GRO/FCOE + * @data: pointer to the start of the headers + * @max: total length of section to find headers in + * + * This function is meant to determine the length of headers that will + * be recognized by hardware for LRO, GRO, and RSC offloads. The main + * motivation of doing this is to only perform one pull for IPv4 TCP + * packets so that we can do basic things like calculating the gso_size + * based on the average data per packet. + **/ +static unsigned int hns_nic_get_headlen(unsigned char *data, u32 flag, + unsigned int max_size) +{ + unsigned char *network; + u8 hlen; + + /* this should never happen, but better safe than sorry */ + if (max_size < ETH_HLEN) + return max_size; + + /* initialize network frame pointer */ + network = data; + + /* set first protocol and move network header forward */ + network += ETH_HLEN; + + /* handle any vlan tag if present */ + if (hnae_get_field(flag, HNS_RXD_VLAN_M, HNS_RXD_VLAN_S) + == HNS_RX_FLAG_VLAN_PRESENT) { + if ((typeof(max_size))(network - data) > (max_size - VLAN_HLEN)) + return max_size; + + network += VLAN_HLEN; + } + + /* handle L3 protocols */ + if (hnae_get_field(flag, HNS_RXD_L3ID_M, HNS_RXD_L3ID_S) + == HNS_RX_FLAG_L3ID_IPV4) { + if ((typeof(max_size))(network - data) > + (max_size - sizeof(struct iphdr))) + return max_size; + + /* access ihl as a u8 to avoid unaligned access on ia64 */ + hlen = (network[0] & 0x0F) << 2; + + /* verify hlen meets minimum size requirements */ + if (hlen < sizeof(struct iphdr)) + return network - data; + + /* record next protocol if header is present */ + } else if (hnae_get_field(flag, HNS_RXD_L3ID_M, HNS_RXD_L3ID_S) + == HNS_RX_FLAG_L3ID_IPV6) { + if ((typeof(max_size))(network - data) > + (max_size - sizeof(struct ipv6hdr))) + return max_size; + + /* record next protocol */ + hlen = sizeof(struct ipv6hdr); + } else { + return network - data; + } + + /* relocate pointer to start of L4 header */ + network += hlen; + + /* finally sort out TCP/UDP */ + if (hnae_get_field(flag, HNS_RXD_L4ID_M, HNS_RXD_L4ID_S) + == HNS_RX_FLAG_L4ID_TCP) { + if ((typeof(max_size))(network - data) > + (max_size - sizeof(struct tcphdr))) + return max_size; + + /* access doff as a u8 to avoid unaligned access on ia64 */ + hlen = (network[12] & 0xF0) >> 2; + + /* verify hlen meets minimum size requirements */ + if (hlen < sizeof(struct tcphdr)) + return network - data; + + network += hlen; + } else if (hnae_get_field(flag, HNS_RXD_L4ID_M, HNS_RXD_L4ID_S) + == HNS_RX_FLAG_L4ID_UDP) { + if ((typeof(max_size))(network - data) > + (max_size - sizeof(struct udphdr))) + return max_size; + + network += sizeof(struct udphdr); + } + + /* If everything has gone correctly network should be the + * data section of the packet and will be the end of the header. + * If not then it probably represents the end of the last recognized + * header. + */ + if ((typeof(max_size))(network - data) < max_size) + return network - data; + else + return max_size; +} + +static void +hns_nic_reuse_page(struct hnae_desc_cb *desc_cb, int tsize, int last_offset) +{ + /* avoid re-using remote pages,flag default unreuse */ + if (likely(page_to_nid(desc_cb->priv) == numa_node_id())) { + /* move offset up to the next cache line */ + desc_cb->page_offset += tsize; + + if (desc_cb->page_offset <= last_offset) { + desc_cb->reuse_flag = 1; + /* bump ref count on page before it is given*/ + get_page(desc_cb->priv); + } + } +} + +static int hns_nic_poll_rx_skb(struct hns_nic_ring_data *ring_data, + struct sk_buff **out_skb, int *out_bnum) +{ + struct hnae_ring *ring = ring_data->ring; + struct net_device *ndev = ring_data->napi.dev; + struct sk_buff *skb; + struct hnae_desc *desc; + struct hnae_desc_cb *desc_cb; + unsigned char *va; + int bnum, length, size, i, truesize, last_offset; + int pull_len; + u32 bnum_flag; + + last_offset = hnae_page_size(ring) - hnae_buf_size(ring); + desc = &ring->desc[ring->next_to_clean]; + desc_cb = &ring->desc_cb[ring->next_to_clean]; + length = le16_to_cpu(desc->rx.pkt_len); + bnum_flag = le32_to_cpu(desc->rx.ipoff_bnum_pid_flag); + bnum = hnae_get_field(bnum_flag, HNS_RXD_BUFNUM_M, HNS_RXD_BUFNUM_S); + *out_bnum = bnum; + va = (unsigned char *)desc_cb->buf + desc_cb->page_offset; + + skb = *out_skb = napi_alloc_skb(&ring_data->napi, HNS_RX_HEAD_SIZE); + if (unlikely(!skb)) { + netdev_err(ndev, "alloc rx skb fail\n"); + ring->stats.sw_err_cnt++; + return -ENOMEM; + } + + if (length <= HNS_RX_HEAD_SIZE) { + memcpy(__skb_put(skb, length), va, ALIGN(length, sizeof(long))); + + /* we can reuse buffer as-is, just make sure it is local */ + if (likely(page_to_nid(desc_cb->priv) == numa_node_id())) + desc_cb->reuse_flag = 1; + else /* this page cannot be reused so discard it */ + put_page(desc_cb->priv); + + ring_ptr_move_fw(ring, next_to_clean); + + if (unlikely(bnum != 1)) { /* check err*/ + *out_bnum = 1; + goto out_bnum_err; + } + } else { + ring->stats.seg_pkt_cnt++; + + pull_len = hns_nic_get_headlen(va, bnum_flag, HNS_RX_HEAD_SIZE); + memcpy(__skb_put(skb, pull_len), va, + ALIGN(pull_len, sizeof(long))); + + size = le16_to_cpu(desc->rx.size); + truesize = ALIGN(size, L1_CACHE_BYTES); + skb_add_rx_frag(skb, 0, desc_cb->priv, + desc_cb->page_offset + pull_len, + size - pull_len, truesize - pull_len); + + hns_nic_reuse_page(desc_cb, truesize, last_offset); + ring_ptr_move_fw(ring, next_to_clean); + + if (unlikely(bnum >= (int)MAX_SKB_FRAGS)) { /* check err*/ + *out_bnum = 1; + goto out_bnum_err; + } + for (i = 1; i < bnum; i++) { + desc = &ring->desc[ring->next_to_clean]; + desc_cb = &ring->desc_cb[ring->next_to_clean]; + size = le16_to_cpu(desc->rx.size); + truesize = ALIGN(size, L1_CACHE_BYTES); + skb_add_rx_frag(skb, i, desc_cb->priv, + desc_cb->page_offset, + size, truesize); + + hns_nic_reuse_page(desc_cb, truesize, last_offset); + ring_ptr_move_fw(ring, next_to_clean); + } + } + + /* check except process, free skb and jump the desc */ + if (unlikely((!bnum) || (bnum > ring->max_desc_num_per_pkt))) { +out_bnum_err: + *out_bnum = *out_bnum ? *out_bnum : 1; /* ntc moved,cannot 0*/ + netdev_err(ndev, "invalid bnum(%d,%d,%d,%d),%016llx,%016llx\n", + bnum, ring->max_desc_num_per_pkt, + length, (int)MAX_SKB_FRAGS, + ((u64 *)desc)[0], ((u64 *)desc)[1]); + ring->stats.err_bd_num++; + dev_kfree_skb_any(skb); + return -EDOM; + } + + bnum_flag = le32_to_cpu(desc->rx.ipoff_bnum_pid_flag); + + if (unlikely(!hnae_get_bit(bnum_flag, HNS_RXD_VLD_B))) { + netdev_err(ndev, "no valid bd,%016llx,%016llx\n", + ((u64 *)desc)[0], ((u64 *)desc)[1]); + ring->stats.non_vld_descs++; + dev_kfree_skb_any(skb); + return -EINVAL; + } + + if (unlikely((!desc->rx.pkt_len) || + hnae_get_bit(bnum_flag, HNS_RXD_DROP_B))) { + ring->stats.err_pkt_len++; + dev_kfree_skb_any(skb); + return -EFAULT; + } + + if (unlikely(hnae_get_bit(bnum_flag, HNS_RXD_L2E_B))) { + ring->stats.l2_err++; + dev_kfree_skb_any(skb); + return -EFAULT; + } + + ring->stats.rx_pkts++; + ring->stats.rx_bytes += skb->len; + + if (unlikely(hnae_get_bit(bnum_flag, HNS_RXD_L3E_B) || + hnae_get_bit(bnum_flag, HNS_RXD_L4E_B))) { + ring->stats.l3l4_csum_err++; + return 0; + } + + skb->ip_summed = CHECKSUM_UNNECESSARY; + + return 0; +} + +static void +hns_nic_alloc_rx_buffers(struct hns_nic_ring_data *ring_data, int cleand_count) +{ + int i, ret; + struct hnae_desc_cb res_cbs; + struct hnae_desc_cb *desc_cb; + struct hnae_ring *ring = ring_data->ring; + struct net_device *ndev = ring_data->napi.dev; + + for (i = 0; i < cleand_count; i++) { + desc_cb = &ring->desc_cb[ring->next_to_use]; + if (desc_cb->reuse_flag) { + ring->stats.reuse_pg_cnt++; + hnae_reuse_buffer(ring, ring->next_to_use); + } else { + ret = hnae_reserve_buffer_map(ring, &res_cbs); + if (ret) { + ring->stats.sw_err_cnt++; + netdev_err(ndev, "hnae reserve buffer map failed.\n"); + break; + } + hnae_replace_buffer(ring, ring->next_to_use, &res_cbs); + } + + ring_ptr_move_fw(ring, next_to_use); + } + + wmb(); /* make all data has been write before submit */ + writel_relaxed(i, ring->io_base + RCB_REG_HEAD); +} + +/* return error number for error or number of desc left to take + */ +static void hns_nic_rx_up_pro(struct hns_nic_ring_data *ring_data, + struct sk_buff *skb) +{ + struct net_device *ndev = ring_data->napi.dev; + + skb->protocol = eth_type_trans(skb, ndev); + (void)napi_gro_receive(&ring_data->napi, skb); + ndev->last_rx = jiffies; +} + +static int hns_nic_rx_poll_one(struct hns_nic_ring_data *ring_data, + int budget, void *v) +{ + struct hnae_ring *ring = ring_data->ring; + struct sk_buff *skb; + int num, bnum, ex_num; +#define RCB_NOF_ALLOC_RX_BUFF_ONCE 16 + int recv_pkts, recv_bds, clean_count, err; + + num = readl_relaxed(ring->io_base + RCB_REG_FBDNUM); + rmb(); /* make sure num taken effect before the other data is touched */ + + recv_pkts = 0, recv_bds = 0, clean_count = 0; +recv: + while (recv_pkts < budget && recv_bds < num) { + /* reuse or realloc buffers*/ + if (clean_count >= RCB_NOF_ALLOC_RX_BUFF_ONCE) { + hns_nic_alloc_rx_buffers(ring_data, clean_count); + clean_count = 0; + } + + /* poll one pkg*/ + err = hns_nic_poll_rx_skb(ring_data, &skb, &bnum); + if (unlikely(!skb)) /* this fault cannot be repaired */ + break; + + recv_bds += bnum; + clean_count += bnum; + if (unlikely(err)) { /* do jump the err */ + recv_pkts++; + continue; + } + + /* do update ip stack process*/ + ((void (*)(struct hns_nic_ring_data *, struct sk_buff *))v)( + ring_data, skb); + recv_pkts++; + } + + /* make all data has been write before submit */ + if (clean_count > 0) { + hns_nic_alloc_rx_buffers(ring_data, clean_count); + clean_count = 0; + } + + if (recv_pkts < budget) { + ex_num = readl_relaxed(ring->io_base + RCB_REG_FBDNUM); + rmb(); /*complete read rx ring bd number*/ + if (ex_num > 0) { + num += ex_num; + goto recv; + } + } + + return recv_pkts; +} + +static void hns_nic_rx_fini_pro(struct hns_nic_ring_data *ring_data) +{ + struct hnae_ring *ring = ring_data->ring; + int num = 0; + + /* for hardware bug fixed */ + num = readl_relaxed(ring->io_base + RCB_REG_FBDNUM); + + if (num > 0) { + ring_data->ring->q->handle->dev->ops->toggle_ring_irq( + ring_data->ring, 1); + + napi_schedule(&ring_data->napi); + } +} + +static inline void hns_nic_reclaim_one_desc(struct hnae_ring *ring, + int *bytes, int *pkts) +{ + struct hnae_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_clean]; + + (*pkts) += (desc_cb->type == DESC_TYPE_SKB); + (*bytes) += desc_cb->length; + /* desc_cb will be cleaned, after hnae_free_buffer_detach*/ + hnae_free_buffer_detach(ring, ring->next_to_clean); + + ring_ptr_move_fw(ring, next_to_clean); +} + +static int is_valid_clean_head(struct hnae_ring *ring, int h) +{ + int u = ring->next_to_use; + int c = ring->next_to_clean; + + if (unlikely(h > ring->desc_num)) + return 0; + + assert(u > 0 && u < ring->desc_num); + assert(c > 0 && c < ring->desc_num); + assert(u != c && h != c); /* must be checked before call this func */ + + return u > c ? (h > c && h <= u) : (h > c || h <= u); +} + +/* netif_tx_lock will turn down the performance, set only when necessary */ +#ifdef CONFIG_NET_POLL_CONTROLLER +#define NETIF_TX_LOCK(ndev) netif_tx_lock(ndev) +#define NETIF_TX_UNLOCK(ndev) netif_tx_unlock(ndev) +#else +#define NETIF_TX_LOCK(ndev) +#define NETIF_TX_UNLOCK(ndev) +#endif +/* reclaim all desc in one budget + * return error or number of desc left + */ +static int hns_nic_tx_poll_one(struct hns_nic_ring_data *ring_data, + int budget, void *v) +{ + struct hnae_ring *ring = ring_data->ring; + struct net_device *ndev = ring_data->napi.dev; + struct netdev_queue *dev_queue; + struct hns_nic_priv *priv = netdev_priv(ndev); + int head; + int bytes, pkts; + + NETIF_TX_LOCK(ndev); + + head = readl_relaxed(ring->io_base + RCB_REG_HEAD); + rmb(); /* make sure head is ready before touch any data */ + + if (is_ring_empty(ring) || head == ring->next_to_clean) { + NETIF_TX_UNLOCK(ndev); + return 0; /* no data to poll */ + } + + if (!is_valid_clean_head(ring, head)) { + netdev_err(ndev, "wrong head (%d, %d-%d)\n", head, + ring->next_to_use, ring->next_to_clean); + ring->stats.io_err_cnt++; + NETIF_TX_UNLOCK(ndev); + return -EIO; + } + + bytes = 0; + pkts = 0; + while (head != ring->next_to_clean) + hns_nic_reclaim_one_desc(ring, &bytes, &pkts); + + NETIF_TX_UNLOCK(ndev); + + dev_queue = netdev_get_tx_queue(ndev, ring_data->queue_index); + netdev_tx_completed_queue(dev_queue, pkts, bytes); + + if (unlikely(pkts && netif_carrier_ok(ndev) && + (ring_space(ring) >= ring->max_desc_num_per_pkt * 2))) { + /* Make sure that anybody stopping the queue after this + * sees the new next_to_clean. + */ + smp_mb(); + if (netif_tx_queue_stopped(dev_queue) && + !test_bit(NIC_STATE_DOWN, &priv->state)) { + netif_tx_wake_queue(dev_queue); + ring->stats.restart_queue++; + } + } + return 0; +} + +static void hns_nic_tx_fini_pro(struct hns_nic_ring_data *ring_data) +{ + struct hnae_ring *ring = ring_data->ring; + int head = ring->next_to_clean; + + /* for hardware bug fixed */ + head = readl_relaxed(ring->io_base + RCB_REG_HEAD); + + if (head != ring->next_to_clean) { + ring_data->ring->q->handle->dev->ops->toggle_ring_irq( + ring_data->ring, 1); + + napi_schedule(&ring_data->napi); + } +} + +static void hns_nic_tx_clr_all_bufs(struct hns_nic_ring_data *ring_data) +{ + struct hnae_ring *ring = ring_data->ring; + struct net_device *ndev = ring_data->napi.dev; + struct netdev_queue *dev_queue; + int head; + int bytes, pkts; + + NETIF_TX_LOCK(ndev); + + head = ring->next_to_use; /* ntu :soft setted ring position*/ + bytes = 0; + pkts = 0; + while (head != ring->next_to_clean) + hns_nic_reclaim_one_desc(ring, &bytes, &pkts); + + NETIF_TX_UNLOCK(ndev); + + dev_queue = netdev_get_tx_queue(ndev, ring_data->queue_index); + netdev_tx_reset_queue(dev_queue); +} + +static int hns_nic_common_poll(struct napi_struct *napi, int budget) +{ + struct hns_nic_ring_data *ring_data = + container_of(napi, struct hns_nic_ring_data, napi); + int clean_complete = ring_data->poll_one( + ring_data, budget, ring_data->ex_process); + + if (clean_complete >= 0 && clean_complete < budget) { + napi_complete(napi); + ring_data->ring->q->handle->dev->ops->toggle_ring_irq( + ring_data->ring, 0); + + ring_data->fini_process(ring_data); + } + + return clean_complete; +} + +static irqreturn_t hns_irq_handle(int irq, void *dev) +{ + struct hns_nic_ring_data *ring_data = (struct hns_nic_ring_data *)dev; + + ring_data->ring->q->handle->dev->ops->toggle_ring_irq( + ring_data->ring, 1); + napi_schedule(&ring_data->napi); + + return IRQ_HANDLED; +} + +/** + *hns_nic_adjust_link - adjust net work mode by the phy stat or new param + *@ndev: net device + */ +static void hns_nic_adjust_link(struct net_device *ndev) +{ + struct hns_nic_priv *priv = netdev_priv(ndev); + struct hnae_handle *h = priv->ae_handle; + + h->dev->ops->adjust_link(h, ndev->phydev->speed, ndev->phydev->duplex); +} + +/** + *hns_nic_init_phy - init phy + *@ndev: net device + *@h: ae handle + * Return 0 on success, negative on failure + */ +int hns_nic_init_phy(struct net_device *ndev, struct hnae_handle *h) +{ + struct hns_nic_priv *priv = netdev_priv(ndev); + struct phy_device *phy_dev = NULL; + + if (!h->phy_node) + return 0; + + if (h->phy_if != PHY_INTERFACE_MODE_XGMII) + phy_dev = of_phy_connect(ndev, h->phy_node, + hns_nic_adjust_link, 0, h->phy_if); + else + phy_dev = of_phy_attach(ndev, h->phy_node, 0, h->phy_if); + + if (unlikely(!phy_dev) || IS_ERR(phy_dev)) + return !phy_dev ? -ENODEV : PTR_ERR(phy_dev); + + phy_dev->supported &= h->if_support; + phy_dev->advertising = phy_dev->supported; + + if (h->phy_if == PHY_INTERFACE_MODE_XGMII) + phy_dev->autoneg = false; + + priv->phy = phy_dev; + + return 0; +} + +static int hns_nic_ring_open(struct net_device *netdev, int idx) +{ + struct hns_nic_priv *priv = netdev_priv(netdev); + struct hnae_handle *h = priv->ae_handle; + + napi_enable(&priv->ring_data[idx].napi); + + enable_irq(priv->ring_data[idx].ring->irq); + h->dev->ops->toggle_ring_irq(priv->ring_data[idx].ring, 0); + + return 0; +} + +static int hns_nic_net_set_mac_address(struct net_device *ndev, void *p) +{ + struct hns_nic_priv *priv = netdev_priv(ndev); + struct hnae_handle *h = priv->ae_handle; + struct sockaddr *mac_addr = p; + int ret; + + if (!mac_addr || !is_valid_ether_addr((const u8 *)mac_addr->sa_data)) + return -EADDRNOTAVAIL; + + ret = h->dev->ops->set_mac_addr(h, mac_addr->sa_data); + if (ret) { + netdev_err(ndev, "set_mac_address fail, ret=%d!\n", ret); + return ret; + } + + memcpy(ndev->dev_addr, mac_addr->sa_data, ndev->addr_len); + + return 0; +} + +void hns_nic_update_stats(struct net_device *netdev) +{ + struct hns_nic_priv *priv = netdev_priv(netdev); + struct hnae_handle *h = priv->ae_handle; + + h->dev->ops->update_stats(h, &netdev->stats); +} + +/* set mac addr if it is configed. or leave it to the AE driver */ +static void hns_init_mac_addr(struct net_device *ndev) +{ + struct hns_nic_priv *priv = netdev_priv(ndev); + struct device_node *node = priv->dev->of_node; + const void *mac_addr_temp; + + mac_addr_temp = of_get_mac_address(node); + if (mac_addr_temp && is_valid_ether_addr(mac_addr_temp)) { + memcpy(ndev->dev_addr, mac_addr_temp, ndev->addr_len); + } else { + eth_hw_addr_random(ndev); + dev_warn(priv->dev, "No valid mac, use random mac %pM", + ndev->dev_addr); + } +} + +static void hns_nic_ring_close(struct net_device *netdev, int idx) +{ + struct hns_nic_priv *priv = netdev_priv(netdev); + struct hnae_handle *h = priv->ae_handle; + + h->dev->ops->toggle_ring_irq(priv->ring_data[idx].ring, 1); + disable_irq(priv->ring_data[idx].ring->irq); + + napi_disable(&priv->ring_data[idx].napi); +} + +static int hns_nic_init_irq(struct hns_nic_priv *priv) +{ + struct hnae_handle *h = priv->ae_handle; + struct hns_nic_ring_data *rd; + int i; + int ret; + int cpu; + cpumask_t mask; + + for (i = 0; i < h->q_num * 2; i++) { + rd = &priv->ring_data[i]; + + if (rd->ring->irq_init_flag == RCB_IRQ_INITED) + break; + + snprintf(rd->ring->ring_name, RCB_RING_NAME_LEN, + "%s-%s%d", priv->netdev->name, + (i < h->q_num ? "tx" : "rx"), rd->queue_index); + + rd->ring->ring_name[RCB_RING_NAME_LEN - 1] = '\0'; + + ret = request_irq(rd->ring->irq, + hns_irq_handle, 0, rd->ring->ring_name, rd); + if (ret) { + netdev_err(priv->netdev, "request irq(%d) fail\n", + rd->ring->irq); + return ret; + } + disable_irq(rd->ring->irq); + rd->ring->irq_init_flag = RCB_IRQ_INITED; + + /*set cpu affinity*/ + if (cpu_online(rd->queue_index)) { + cpumask_clear(&mask); + cpu = rd->queue_index; + cpumask_set_cpu(cpu, &mask); + irq_set_affinity_hint(rd->ring->irq, &mask); + } + } + + return 0; +} + +static int hns_nic_net_up(struct net_device *ndev) +{ + struct hns_nic_priv *priv = netdev_priv(ndev); + struct hnae_handle *h = priv->ae_handle; + int i, j, k; + int ret; + + ret = hns_nic_init_irq(priv); + if (ret != 0) { + netdev_err(ndev, "hns init irq failed! ret=%d\n", ret); + return ret; + } + + for (i = 0; i < h->q_num * 2; i++) { + ret = hns_nic_ring_open(ndev, i); + if (ret) + goto out_has_some_queues; + } + + for (k = 0; k < h->q_num; k++) + h->dev->ops->toggle_queue_status(h->qs[k], 1); + + ret = h->dev->ops->set_mac_addr(h, ndev->dev_addr); + if (ret) + goto out_set_mac_addr_err; + + ret = h->dev->ops->start ? h->dev->ops->start(h) : 0; + if (ret) + goto out_start_err; + + if (priv->phy) + phy_start(priv->phy); + + clear_bit(NIC_STATE_DOWN, &priv->state); + (void)mod_timer(&priv->service_timer, jiffies + SERVICE_TIMER_HZ); + + return 0; + +out_start_err: + netif_stop_queue(ndev); +out_set_mac_addr_err: + for (k = 0; k < h->q_num; k++) + h->dev->ops->toggle_queue_status(h->qs[k], 0); +out_has_some_queues: + for (j = i - 1; j >= 0; j--) + hns_nic_ring_close(ndev, j); + + set_bit(NIC_STATE_DOWN, &priv->state); + + return ret; +} + +static void hns_nic_net_down(struct net_device *ndev) +{ + int i; + struct hnae_ae_ops *ops; + struct hns_nic_priv *priv = netdev_priv(ndev); + + if (test_and_set_bit(NIC_STATE_DOWN, &priv->state)) + return; + + (void)del_timer_sync(&priv->service_timer); + netif_tx_stop_all_queues(ndev); + netif_carrier_off(ndev); + netif_tx_disable(ndev); + priv->link = 0; + + if (priv->phy) + phy_stop(priv->phy); + + ops = priv->ae_handle->dev->ops; + + if (ops->stop) + ops->stop(priv->ae_handle); + + netif_tx_stop_all_queues(ndev); + + for (i = priv->ae_handle->q_num - 1; i >= 0; i--) { + hns_nic_ring_close(ndev, i); + hns_nic_ring_close(ndev, i + priv->ae_handle->q_num); + + /* clean tx buffers*/ + hns_nic_tx_clr_all_bufs(priv->ring_data + i); + } +} + +void hns_nic_net_reset(struct net_device *ndev) +{ + struct hns_nic_priv *priv = netdev_priv(ndev); + struct hnae_handle *handle = priv->ae_handle; + + while (test_and_set_bit(NIC_STATE_RESETTING, &priv->state)) + usleep_range(1000, 2000); + + (void)hnae_reinit_handle(handle); + + clear_bit(NIC_STATE_RESETTING, &priv->state); +} + +void hns_nic_net_reinit(struct net_device *netdev) +{ + struct hns_nic_priv *priv = netdev_priv(netdev); + + priv->netdev->trans_start = jiffies; + while (test_and_set_bit(NIC_STATE_REINITING, &priv->state)) + usleep_range(1000, 2000); + + hns_nic_net_down(netdev); + hns_nic_net_reset(netdev); + (void)hns_nic_net_up(netdev); + clear_bit(NIC_STATE_REINITING, &priv->state); +} + +static int hns_nic_net_open(struct net_device *ndev) +{ + struct hns_nic_priv *priv = netdev_priv(ndev); + struct hnae_handle *h = priv->ae_handle; + int ret; + + if (test_bit(NIC_STATE_TESTING, &priv->state)) + return -EBUSY; + + priv->link = 0; + netif_carrier_off(ndev); + + ret = netif_set_real_num_tx_queues(ndev, h->q_num); + if (ret < 0) { + netdev_err(ndev, "netif_set_real_num_tx_queues fail, ret=%d!\n", + ret); + return ret; + } + + ret = netif_set_real_num_rx_queues(ndev, h->q_num); + if (ret < 0) { + netdev_err(ndev, + "netif_set_real_num_rx_queues fail, ret=%d!\n", ret); + return ret; + } + + ret = hns_nic_net_up(ndev); + if (ret) { + netdev_err(ndev, + "hns net up fail, ret=%d!\n", ret); + return ret; + } + + return 0; +} + +static int hns_nic_net_stop(struct net_device *ndev) +{ + hns_nic_net_down(ndev); + + return 0; +} + +static void hns_tx_timeout_reset(struct hns_nic_priv *priv); +static void hns_nic_net_timeout(struct net_device *ndev) +{ + struct hns_nic_priv *priv = netdev_priv(ndev); + + hns_tx_timeout_reset(priv); +} + +static int hns_nic_do_ioctl(struct net_device *netdev, struct ifreq *ifr, + int cmd) +{ + struct hns_nic_priv *priv = netdev_priv(netdev); + struct phy_device *phy_dev = priv->phy; + + if (!netif_running(netdev)) + return -EINVAL; + + if (!phy_dev) + return -ENOTSUPP; + + return phy_mii_ioctl(phy_dev, ifr, cmd); +} + +/* use only for netconsole to poll with the device without interrupt */ +#ifdef CONFIG_NET_POLL_CONTROLLER +void hns_nic_poll_controller(struct net_device *ndev) +{ + struct hns_nic_priv *priv = netdev_priv(ndev); + unsigned long flags; + int i; + + local_irq_save(flags); + for (i = 0; i < priv->ae_handle->q_num * 2; i++) + napi_schedule(&priv->ring_data[i].napi); + local_irq_restore(flags); +} +#endif + +static netdev_tx_t hns_nic_net_xmit(struct sk_buff *skb, + struct net_device *ndev) +{ + struct hns_nic_priv *priv = netdev_priv(ndev); + int ret; + + assert(skb->queue_mapping < ndev->ae_handle->q_num); + ret = hns_nic_net_xmit_hw(ndev, skb, + &tx_ring_data(priv, skb->queue_mapping)); + if (ret == NETDEV_TX_OK) { + ndev->trans_start = jiffies; + ndev->stats.tx_bytes += skb->len; + ndev->stats.tx_packets++; + } + return (netdev_tx_t)ret; +} + +static int hns_nic_change_mtu(struct net_device *ndev, int new_mtu) +{ + struct hns_nic_priv *priv = netdev_priv(ndev); + struct hnae_handle *h = priv->ae_handle; + int ret; + + /* MTU < 68 is an error and causes problems on some kernels */ + if (new_mtu < 68) + return -EINVAL; + + if (!h->dev->ops->set_mtu) + return -ENOTSUPP; + + if (netif_running(ndev)) { + (void)hns_nic_net_stop(ndev); + msleep(100); + + ret = h->dev->ops->set_mtu(h, new_mtu); + if (ret) + netdev_err(ndev, "set mtu fail, return value %d\n", + ret); + + if (hns_nic_net_open(ndev)) + netdev_err(ndev, "hns net open fail\n"); + } else { + ret = h->dev->ops->set_mtu(h, new_mtu); + } + + if (!ret) + ndev->mtu = new_mtu; + + return ret; +} + +/** + * nic_set_multicast_list - set mutl mac address + * @netdev: net device + * @p: mac address + * + * return void + */ +void hns_set_multicast_list(struct net_device *ndev) +{ + struct hns_nic_priv *priv = netdev_priv(ndev); + struct hnae_handle *h = priv->ae_handle; + struct netdev_hw_addr *ha = NULL; + + if (!h) { + netdev_err(ndev, "hnae handle is null\n"); + return; + } + + if (h->dev->ops->set_mc_addr) { + netdev_for_each_mc_addr(ha, ndev) + if (h->dev->ops->set_mc_addr(h, ha->addr)) + netdev_err(ndev, "set multicast fail\n"); + } +} + +struct rtnl_link_stats64 *hns_nic_get_stats64(struct net_device *ndev, + struct rtnl_link_stats64 *stats) +{ + int idx = 0; + u64 tx_bytes = 0; + u64 rx_bytes = 0; + u64 tx_pkts = 0; + u64 rx_pkts = 0; + struct hns_nic_priv *priv = netdev_priv(ndev); + struct hnae_handle *h = priv->ae_handle; + + for (idx = 0; idx < h->q_num; idx++) { + tx_bytes += h->qs[idx]->tx_ring.stats.tx_bytes; + tx_pkts += h->qs[idx]->tx_ring.stats.tx_pkts; + rx_bytes += h->qs[idx]->rx_ring.stats.rx_bytes; + rx_pkts += h->qs[idx]->rx_ring.stats.rx_pkts; + } + + stats->tx_bytes = tx_bytes; + stats->tx_packets = tx_pkts; + stats->rx_bytes = rx_bytes; + stats->rx_packets = rx_pkts; + + stats->rx_errors = ndev->stats.rx_errors; + stats->multicast = ndev->stats.multicast; + stats->rx_length_errors = ndev->stats.rx_length_errors; + stats->rx_crc_errors = ndev->stats.rx_crc_errors; + stats->rx_missed_errors = ndev->stats.rx_missed_errors; + + stats->tx_errors = ndev->stats.tx_errors; + stats->rx_dropped = ndev->stats.rx_dropped; + stats->tx_dropped = ndev->stats.tx_dropped; + stats->collisions = ndev->stats.collisions; + stats->rx_over_errors = ndev->stats.rx_over_errors; + stats->rx_frame_errors = ndev->stats.rx_frame_errors; + stats->rx_fifo_errors = ndev->stats.rx_fifo_errors; + stats->tx_aborted_errors = ndev->stats.tx_aborted_errors; + stats->tx_carrier_errors = ndev->stats.tx_carrier_errors; + stats->tx_fifo_errors = ndev->stats.tx_fifo_errors; + stats->tx_heartbeat_errors = ndev->stats.tx_heartbeat_errors; + stats->tx_window_errors = ndev->stats.tx_window_errors; + stats->rx_compressed = ndev->stats.rx_compressed; + stats->tx_compressed = ndev->stats.tx_compressed; + + return stats; +} + +static const struct net_device_ops hns_nic_netdev_ops = { + .ndo_open = hns_nic_net_open, + .ndo_stop = hns_nic_net_stop, + .ndo_start_xmit = hns_nic_net_xmit, + .ndo_tx_timeout = hns_nic_net_timeout, + .ndo_set_mac_address = hns_nic_net_set_mac_address, + .ndo_change_mtu = hns_nic_change_mtu, + .ndo_do_ioctl = hns_nic_do_ioctl, + .ndo_get_stats64 = hns_nic_get_stats64, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = hns_nic_poll_controller, +#endif + .ndo_set_rx_mode = hns_set_multicast_list, +}; + +static void hns_nic_update_link_status(struct net_device *netdev) +{ + struct hns_nic_priv *priv = netdev_priv(netdev); + + struct hnae_handle *h = priv->ae_handle; + int state = 1; + + if (priv->phy) { + if (!genphy_update_link(priv->phy)) + state = priv->phy->link; + else + state = 0; + } + state = state && h->dev->ops->get_status(h); + + if (state != priv->link) { + if (state) { + netif_carrier_on(netdev); + netif_tx_wake_all_queues(netdev); + netdev_info(netdev, "link up\n"); + } else { + netif_carrier_off(netdev); + netdev_info(netdev, "link down\n"); + } + priv->link = state; + } +} + +/* for dumping key regs*/ +static void hns_nic_dump(struct hns_nic_priv *priv) +{ + struct hnae_handle *h = priv->ae_handle; + struct hnae_ae_ops *ops = h->dev->ops; + u32 *data, reg_num, i; + + if (ops->get_regs_len && ops->get_regs) { + reg_num = ops->get_regs_len(priv->ae_handle); + reg_num = (reg_num + 3ul) & ~3ul; + data = kcalloc(reg_num, sizeof(u32), GFP_KERNEL); + if (data) { + ops->get_regs(priv->ae_handle, data); + for (i = 0; i < reg_num; i += 4) + pr_info("0x%08x: 0x%08x 0x%08x 0x%08x 0x%08x\n", + i, data[i], data[i + 1], + data[i + 2], data[i + 3]); + kfree(data); + } + } + + for (i = 0; i < h->q_num; i++) { + pr_info("tx_queue%d_next_to_clean:%d\n", + i, h->qs[i]->tx_ring.next_to_clean); + pr_info("tx_queue%d_next_to_use:%d\n", + i, h->qs[i]->tx_ring.next_to_use); + pr_info("rx_queue%d_next_to_clean:%d\n", + i, h->qs[i]->rx_ring.next_to_clean); + pr_info("rx_queue%d_next_to_use:%d\n", + i, h->qs[i]->rx_ring.next_to_use); + } +} + +/* for resetting suntask*/ +static void hns_nic_reset_subtask(struct hns_nic_priv *priv) +{ + enum hnae_port_type type = priv->ae_handle->port_type; + + if (!test_bit(NIC_STATE2_RESET_REQUESTED, &priv->state)) + return; + clear_bit(NIC_STATE2_RESET_REQUESTED, &priv->state); + + /* If we're already down, removing or resetting, just bail */ + if (test_bit(NIC_STATE_DOWN, &priv->state) || + test_bit(NIC_STATE_REMOVING, &priv->state) || + test_bit(NIC_STATE_RESETTING, &priv->state)) + return; + + hns_nic_dump(priv); + netdev_err(priv->netdev, "Reset %s port\n", + (type == HNAE_PORT_DEBUG ? "debug" : "business")); + + rtnl_lock(); + if (type == HNAE_PORT_DEBUG) { + hns_nic_net_reinit(priv->netdev); + } else { + hns_nic_net_down(priv->netdev); + hns_nic_net_reset(priv->netdev); + } + rtnl_unlock(); +} + +/* for doing service complete*/ +static void hns_nic_service_event_complete(struct hns_nic_priv *priv) +{ + assert(!test_bit(NIC_STATE_SERVICE_SCHED, &priv->state)); + + smp_mb__before_atomic(); + clear_bit(NIC_STATE_SERVICE_SCHED, &priv->state); +} + +static void hns_nic_service_task(struct work_struct *work) +{ + struct hns_nic_priv *priv + = container_of(work, struct hns_nic_priv, service_task); + struct hnae_handle *h = priv->ae_handle; + + hns_nic_update_link_status(priv->netdev); + h->dev->ops->update_led_status(h); + hns_nic_update_stats(priv->netdev); + + hns_nic_reset_subtask(priv); + hns_nic_service_event_complete(priv); +} + +static void hns_nic_task_schedule(struct hns_nic_priv *priv) +{ + if (!test_bit(NIC_STATE_DOWN, &priv->state) && + !test_bit(NIC_STATE_REMOVING, &priv->state) && + !test_and_set_bit(NIC_STATE_SERVICE_SCHED, &priv->state)) + (void)schedule_work(&priv->service_task); +} + +static void hns_nic_service_timer(unsigned long data) +{ + struct hns_nic_priv *priv = (struct hns_nic_priv *)data; + + (void)mod_timer(&priv->service_timer, jiffies + SERVICE_TIMER_HZ); + + hns_nic_task_schedule(priv); +} + +/** + * hns_tx_timeout_reset - initiate reset due to Tx timeout + * @priv: driver private struct + **/ +static void hns_tx_timeout_reset(struct hns_nic_priv *priv) +{ + /* Do the reset outside of interrupt context */ + if (!test_bit(NIC_STATE_DOWN, &priv->state)) { + set_bit(NIC_STATE2_RESET_REQUESTED, &priv->state); + netdev_warn(priv->netdev, + "initiating reset due to tx timeout(%llu,0x%lx)\n", + priv->tx_timeout_count, priv->state); + priv->tx_timeout_count++; + hns_nic_task_schedule(priv); + } +} + +static int hns_nic_init_ring_data(struct hns_nic_priv *priv) +{ + struct hnae_handle *h = priv->ae_handle; + struct hns_nic_ring_data *rd; + int i; + + if (h->q_num > NIC_MAX_Q_PER_VF) { + netdev_err(priv->netdev, "too much queue (%d)\n", h->q_num); + return -EINVAL; + } + + priv->ring_data = kzalloc(h->q_num * sizeof(*priv->ring_data) * 2, + GFP_KERNEL); + if (!priv->ring_data) + return -ENOMEM; + + for (i = 0; i < h->q_num; i++) { + rd = &priv->ring_data[i]; + rd->queue_index = i; + rd->ring = &h->qs[i]->tx_ring; + rd->poll_one = hns_nic_tx_poll_one; + rd->fini_process = hns_nic_tx_fini_pro; + + netif_napi_add(priv->netdev, &rd->napi, + hns_nic_common_poll, NIC_TX_CLEAN_MAX_NUM); + rd->ring->irq_init_flag = RCB_IRQ_NOT_INITED; + } + for (i = h->q_num; i < h->q_num * 2; i++) { + rd = &priv->ring_data[i]; + rd->queue_index = i - h->q_num; + rd->ring = &h->qs[i - h->q_num]->rx_ring; + rd->poll_one = hns_nic_rx_poll_one; + rd->ex_process = hns_nic_rx_up_pro; + rd->fini_process = hns_nic_rx_fini_pro; + + netif_napi_add(priv->netdev, &rd->napi, + hns_nic_common_poll, NIC_RX_CLEAN_MAX_NUM); + rd->ring->irq_init_flag = RCB_IRQ_NOT_INITED; + } + + return 0; +} + +static void hns_nic_uninit_ring_data(struct hns_nic_priv *priv) +{ + struct hnae_handle *h = priv->ae_handle; + int i; + + for (i = 0; i < h->q_num * 2; i++) { + netif_napi_del(&priv->ring_data[i].napi); + if (priv->ring_data[i].ring->irq_init_flag == RCB_IRQ_INITED) { + irq_set_affinity_hint(priv->ring_data[i].ring->irq, + NULL); + free_irq(priv->ring_data[i].ring->irq, + &priv->ring_data[i]); + } + + priv->ring_data[i].ring->irq_init_flag = RCB_IRQ_NOT_INITED; + } + kfree(priv->ring_data); +} + +static int hns_nic_try_get_ae(struct net_device *ndev) +{ + struct hns_nic_priv *priv = netdev_priv(ndev); + struct hnae_handle *h; + int ret; + + h = hnae_get_handle(&priv->netdev->dev, + priv->ae_name, priv->port_id, NULL); + if (IS_ERR_OR_NULL(h)) { + ret = PTR_ERR(h); + dev_dbg(priv->dev, "has not handle, register notifier!\n"); + goto out; + } + priv->ae_handle = h; + + ret = hns_nic_init_phy(ndev, h); + if (ret) { + dev_err(priv->dev, "probe phy device fail!\n"); + goto out_init_phy; + } + + ret = hns_nic_init_ring_data(priv); + if (ret) { + ret = -ENOMEM; + goto out_init_ring_data; + } + + ret = register_netdev(ndev); + if (ret) { + dev_err(priv->dev, "probe register netdev fail!\n"); + goto out_reg_ndev_fail; + } + return 0; + +out_reg_ndev_fail: + hns_nic_uninit_ring_data(priv); + priv->ring_data = NULL; +out_init_phy: +out_init_ring_data: + hnae_put_handle(priv->ae_handle); + priv->ae_handle = NULL; +out: + return ret; +} + +static int hns_nic_notifier_action(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct hns_nic_priv *priv = + container_of(nb, struct hns_nic_priv, notifier_block); + + assert(action == HNAE_AE_REGISTER); + + if (!hns_nic_try_get_ae(priv->netdev)) { + hnae_unregister_notifier(&priv->notifier_block); + priv->notifier_block.notifier_call = NULL; + } + return 0; +} + +static int hns_nic_dev_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct net_device *ndev; + struct hns_nic_priv *priv; + struct device_node *node = dev->of_node; + int ret; + + ndev = alloc_etherdev_mq(sizeof(struct hns_nic_priv), NIC_MAX_Q_PER_VF); + if (!ndev) + return -ENOMEM; + + platform_set_drvdata(pdev, ndev); + + priv = netdev_priv(ndev); + priv->dev = dev; + priv->netdev = ndev; + + if (of_device_is_compatible(node, "hisilicon,hns-nic-v2")) + priv->enet_ver = AE_VERSION_2; + else + priv->enet_ver = AE_VERSION_1; + + ret = of_property_read_string(node, "ae-name", &priv->ae_name); + if (ret) + goto out_read_string_fail; + + ret = of_property_read_u32(node, "port-id", &priv->port_id); + if (ret) + goto out_read_string_fail; + + hns_init_mac_addr(ndev); + + ndev->watchdog_timeo = HNS_NIC_TX_TIMEOUT; + ndev->priv_flags |= IFF_UNICAST_FLT; + ndev->netdev_ops = &hns_nic_netdev_ops; + hns_ethtool_set_ops(ndev); + ndev->features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | + NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO | + NETIF_F_GRO; + ndev->vlan_features |= + NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM; + ndev->vlan_features |= NETIF_F_SG | NETIF_F_GSO | NETIF_F_GRO; + + SET_NETDEV_DEV(ndev, dev); + + if (!dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64))) + dev_dbg(dev, "set mask to 64bit\n"); + else + dev_err(dev, "set mask to 32bit fail!\n"); + + /* carrier off reporting is important to ethtool even BEFORE open */ + netif_carrier_off(ndev); + + setup_timer(&priv->service_timer, hns_nic_service_timer, + (unsigned long)priv); + INIT_WORK(&priv->service_task, hns_nic_service_task); + + set_bit(NIC_STATE_SERVICE_INITED, &priv->state); + clear_bit(NIC_STATE_SERVICE_SCHED, &priv->state); + set_bit(NIC_STATE_DOWN, &priv->state); + + if (hns_nic_try_get_ae(priv->netdev)) { + priv->notifier_block.notifier_call = hns_nic_notifier_action; + ret = hnae_register_notifier(&priv->notifier_block); + if (ret) { + dev_err(dev, "register notifier fail!\n"); + goto out_notify_fail; + } + dev_dbg(dev, "has not handle, register notifier!\n"); + } + + return 0; + +out_notify_fail: + (void)cancel_work_sync(&priv->service_task); +out_read_string_fail: + free_netdev(ndev); + return ret; +} + +static int hns_nic_dev_remove(struct platform_device *pdev) +{ + struct net_device *ndev = platform_get_drvdata(pdev); + struct hns_nic_priv *priv = netdev_priv(ndev); + + if (ndev->reg_state != NETREG_UNINITIALIZED) + unregister_netdev(ndev); + + if (priv->ring_data) + hns_nic_uninit_ring_data(priv); + priv->ring_data = NULL; + + if (priv->phy) + phy_disconnect(priv->phy); + priv->phy = NULL; + + if (!IS_ERR_OR_NULL(priv->ae_handle)) + hnae_put_handle(priv->ae_handle); + priv->ae_handle = NULL; + if (priv->notifier_block.notifier_call) + hnae_unregister_notifier(&priv->notifier_block); + priv->notifier_block.notifier_call = NULL; + + set_bit(NIC_STATE_REMOVING, &priv->state); + (void)cancel_work_sync(&priv->service_task); + + free_netdev(ndev); + return 0; +} + +static const struct of_device_id hns_enet_of_match[] = { + {.compatible = "hisilicon,hns-nic-v1",}, + {.compatible = "hisilicon,hns-nic-v2",}, + {}, +}; + +MODULE_DEVICE_TABLE(of, hns_enet_of_match); + +static struct platform_driver hns_nic_dev_driver = { + .driver = { + .name = "hns-nic", + .owner = THIS_MODULE, + .of_match_table = hns_enet_of_match, + }, + .probe = hns_nic_dev_probe, + .remove = hns_nic_dev_remove, +}; + +module_platform_driver(hns_nic_dev_driver); + +MODULE_DESCRIPTION("HISILICON HNS Ethernet driver"); +MODULE_AUTHOR("Hisilicon, Inc."); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:hns-nic"); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.h b/drivers/net/ethernet/hisilicon/hns/hns_enet.h new file mode 100644 index 000000000000..dae0ed19ac6d --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.h @@ -0,0 +1,84 @@ +/* + * Copyright (c) 2014-2015 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef __HNS_ENET_H +#define __HNS_ENET_H + +#include <linux/netdevice.h> +#include <linux/of_net.h> +#include <linux/of_mdio.h> +#include <linux/timer.h> +#include <linux/workqueue.h> + +#include "hnae.h" + +enum hns_nic_state { + NIC_STATE_TESTING = 0, + NIC_STATE_RESETTING, + NIC_STATE_REINITING, + NIC_STATE_DOWN, + NIC_STATE_DISABLED, + NIC_STATE_REMOVING, + NIC_STATE_SERVICE_INITED, + NIC_STATE_SERVICE_SCHED, + NIC_STATE2_RESET_REQUESTED, + NIC_STATE_MAX +}; + +struct hns_nic_ring_data { + struct hnae_ring *ring; + struct napi_struct napi; + int queue_index; + int (*poll_one)(struct hns_nic_ring_data *, int, void *); + void (*ex_process)(struct hns_nic_ring_data *, struct sk_buff *); + void (*fini_process)(struct hns_nic_ring_data *); +}; + +struct hns_nic_priv { + const char *ae_name; + u32 enet_ver; + u32 port_id; + int phy_mode; + int phy_led_val; + struct phy_device *phy; + struct net_device *netdev; + struct device *dev; + struct hnae_handle *ae_handle; + + /* the cb for nic to manage the ring buffer, the first half of the + * array is for tx_ring and vice versa for the second half + */ + struct hns_nic_ring_data *ring_data; + + /* The most recently read link state */ + int link; + u64 tx_timeout_count; + + unsigned long state; + + struct timer_list service_timer; + + struct work_struct service_task; + + struct notifier_block notifier_block; +}; + +#define tx_ring_data(priv, idx) ((priv)->ring_data[idx]) +#define rx_ring_data(priv, idx) \ + ((priv)->ring_data[(priv)->ae_handle->q_num + (idx)]) + +void hns_ethtool_set_ops(struct net_device *ndev); +void hns_nic_net_reset(struct net_device *ndev); +void hns_nic_net_reinit(struct net_device *netdev); +int hns_nic_init_phy(struct net_device *ndev, struct hnae_handle *h); +int hns_nic_net_xmit_hw(struct net_device *ndev, + struct sk_buff *skb, + struct hns_nic_ring_data *ring_data); + +#endif /**__HNS_ENET_H */ diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c new file mode 100644 index 000000000000..2550208cb22e --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c @@ -0,0 +1,1230 @@ +/* + * Copyright (c) 2014-2015 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/etherdevice.h> +#include <linux/interrupt.h> +#include <linux/module.h> +#include <linux/platform_device.h> + +#include "hns_enet.h" + +#define HNS_PHY_PAGE_MDIX 0 +#define HNS_PHY_PAGE_LED 3 +#define HNS_PHY_PAGE_COPPER 0 + +#define HNS_PHY_PAGE_REG 22 /* Page Selection Reg. */ +#define HNS_PHY_CSC_REG 16 /* Copper Specific Control Register */ +#define HNS_PHY_CSS_REG 17 /* Copper Specific Status Register */ +#define HNS_LED_FC_REG 16 /* LED Function Control Reg. */ +#define HNS_LED_PC_REG 17 /* LED Polarity Control Reg. */ + +#define HNS_LED_FORCE_ON 9 +#define HNS_LED_FORCE_OFF 8 + +#define HNS_CHIP_VERSION 660 +#define HNS_NET_STATS_CNT 26 + +#define PHY_MDIX_CTRL_S (5) +#define PHY_MDIX_CTRL_M (3 << PHY_MDIX_CTRL_S) + +#define PHY_MDIX_STATUS_B (6) +#define PHY_SPEED_DUP_RESOLVE_B (11) + +/** + *hns_nic_get_link - get current link status + *@net_dev: net_device + *retuen 0 - success , negative --fail + */ +static u32 hns_nic_get_link(struct net_device *net_dev) +{ + struct hns_nic_priv *priv = netdev_priv(net_dev); + u32 link_stat = priv->link; + struct hnae_handle *h; + + assert(priv && priv->ae_handle); + h = priv->ae_handle; + + if (priv->phy) { + if (!genphy_update_link(priv->phy)) + link_stat = priv->phy->link; + else + link_stat = 0; + } + + if (h->dev && h->dev->ops && h->dev->ops->get_status) + link_stat = link_stat && h->dev->ops->get_status(h); + else + link_stat = 0; + + return link_stat; +} + +static void hns_get_mdix_mode(struct net_device *net_dev, + struct ethtool_cmd *cmd) +{ + int mdix_ctrl, mdix, retval, is_resolved; + struct hns_nic_priv *priv = netdev_priv(net_dev); + struct phy_device *phy_dev = priv->phy; + + if (!phy_dev || !phy_dev->bus) { + cmd->eth_tp_mdix_ctrl = ETH_TP_MDI_INVALID; + cmd->eth_tp_mdix = ETH_TP_MDI_INVALID; + return; + } + + (void)mdiobus_write(phy_dev->bus, phy_dev->addr, HNS_PHY_PAGE_REG, + HNS_PHY_PAGE_MDIX); + + retval = mdiobus_read(phy_dev->bus, phy_dev->addr, HNS_PHY_CSC_REG); + mdix_ctrl = hnae_get_field(retval, PHY_MDIX_CTRL_M, PHY_MDIX_CTRL_S); + + retval = mdiobus_read(phy_dev->bus, phy_dev->addr, HNS_PHY_CSS_REG); + mdix = hnae_get_bit(retval, PHY_MDIX_STATUS_B); + is_resolved = hnae_get_bit(retval, PHY_SPEED_DUP_RESOLVE_B); + + (void)mdiobus_write(phy_dev->bus, phy_dev->addr, HNS_PHY_PAGE_REG, + HNS_PHY_PAGE_COPPER); + + switch (mdix_ctrl) { + case 0x0: + cmd->eth_tp_mdix_ctrl = ETH_TP_MDI; + break; + case 0x1: + cmd->eth_tp_mdix_ctrl = ETH_TP_MDI_X; + break; + case 0x3: + cmd->eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO; + break; + default: + cmd->eth_tp_mdix_ctrl = ETH_TP_MDI_INVALID; + break; + } + + if (!is_resolved) + cmd->eth_tp_mdix = ETH_TP_MDI_INVALID; + else if (mdix) + cmd->eth_tp_mdix = ETH_TP_MDI_X; + else + cmd->eth_tp_mdix = ETH_TP_MDI; +} + +/** + *hns_nic_get_settings - implement ethtool get settings + *@net_dev: net_device + *@cmd: ethtool_cmd + *retuen 0 - success , negative --fail + */ +static int hns_nic_get_settings(struct net_device *net_dev, + struct ethtool_cmd *cmd) +{ + struct hns_nic_priv *priv = netdev_priv(net_dev); + struct hnae_handle *h; + u32 link_stat; + int ret; + u8 duplex; + u16 speed; + + if (!priv || !priv->ae_handle) + return -ESRCH; + + h = priv->ae_handle; + if (!h->dev || !h->dev->ops || !h->dev->ops->get_info) + return -ESRCH; + + ret = h->dev->ops->get_info(h, NULL, &speed, &duplex); + if (ret < 0) { + netdev_err(net_dev, "%s get_info error!\n", __func__); + return -EINVAL; + } + + /* When there is no phy, autoneg is off. */ + cmd->autoneg = false; + ethtool_cmd_speed_set(cmd, speed); + cmd->duplex = duplex; + + if (priv->phy) + (void)phy_ethtool_gset(priv->phy, cmd); + + link_stat = hns_nic_get_link(net_dev); + if (!link_stat) { + ethtool_cmd_speed_set(cmd, (u32)SPEED_UNKNOWN); + cmd->duplex = DUPLEX_UNKNOWN; + } + + if (cmd->autoneg) + cmd->advertising |= ADVERTISED_Autoneg; + + cmd->supported |= h->if_support; + if (h->phy_if == PHY_INTERFACE_MODE_SGMII) { + cmd->supported |= SUPPORTED_TP; + cmd->advertising |= ADVERTISED_1000baseT_Full; + } else if (h->phy_if == PHY_INTERFACE_MODE_XGMII) { + cmd->supported |= SUPPORTED_FIBRE; + cmd->advertising |= ADVERTISED_10000baseKR_Full; + } + + if (h->port_type == HNAE_PORT_SERVICE) { + cmd->port = PORT_FIBRE; + cmd->supported |= SUPPORTED_Pause; + } else { + cmd->port = PORT_TP; + } + + cmd->transceiver = XCVR_EXTERNAL; + cmd->mdio_support = (ETH_MDIO_SUPPORTS_C45 | ETH_MDIO_SUPPORTS_C22); + hns_get_mdix_mode(net_dev, cmd); + + return 0; +} + +/** + *hns_nic_set_settings - implement ethtool set settings + *@net_dev: net_device + *@cmd: ethtool_cmd + *retuen 0 - success , negative --fail + */ +static int hns_nic_set_settings(struct net_device *net_dev, + struct ethtool_cmd *cmd) +{ + struct hns_nic_priv *priv = netdev_priv(net_dev); + struct hnae_handle *h; + int link_stat; + u32 speed; + u8 duplex, autoneg; + + if (!netif_running(net_dev)) + return -ESRCH; + + if (!priv || !priv->ae_handle || !priv->ae_handle->dev || + !priv->ae_handle->dev->ops) + return -ENODEV; + + h = priv->ae_handle; + link_stat = hns_nic_get_link(net_dev); + duplex = cmd->duplex; + speed = ethtool_cmd_speed(cmd); + autoneg = cmd->autoneg; + + if (!link_stat) { + if (duplex != (u8)DUPLEX_UNKNOWN || speed != (u32)SPEED_UNKNOWN) + return -EINVAL; + + if (h->phy_if == PHY_INTERFACE_MODE_SGMII && h->phy_node) { + priv->phy->autoneg = autoneg; + return phy_start_aneg(priv->phy); + } + } + + if (h->phy_if == PHY_INTERFACE_MODE_XGMII) { + if (autoneg != AUTONEG_DISABLE) + return -EINVAL; + + if (speed != SPEED_10000 || duplex != DUPLEX_FULL) + return -EINVAL; + } else if (h->phy_if == PHY_INTERFACE_MODE_SGMII) { + if (!h->phy_node && autoneg != AUTONEG_DISABLE) + return -EINVAL; + + if (speed == SPEED_1000 && duplex == DUPLEX_HALF) + return -EINVAL; + + if (speed != SPEED_10 && speed != SPEED_100 && + speed != SPEED_1000) + return -EINVAL; + } else { + netdev_err(net_dev, "Not supported!"); + return -ENOTSUPP; + } + + if (priv->phy) { + return phy_ethtool_sset(priv->phy, cmd); + } else if (h->dev->ops->adjust_link && link_stat) { + h->dev->ops->adjust_link(h, speed, duplex); + return 0; + } + netdev_err(net_dev, "Not supported!"); + return -ENOTSUPP; +} + +static const char hns_nic_test_strs[][ETH_GSTRING_LEN] = { + "Mac Loopback test", + "Serdes Loopback test", + "Phy Loopback test" +}; + +static int hns_nic_config_phy_loopback(struct phy_device *phy_dev, u8 en) +{ +#define COPPER_CONTROL_REG 0 +#define PHY_LOOP_BACK BIT(14) + u16 val = 0; + + if (phy_dev->is_c45) /* c45 branch adding for XGE PHY */ + return -ENOTSUPP; + + if (en) { + /* speed : 1000M */ + (void)mdiobus_write(phy_dev->bus, phy_dev->addr, + HNS_PHY_PAGE_REG, 2); + (void)mdiobus_write(phy_dev->bus, phy_dev->addr, + 21, 0x1046); + /* Force Master */ + (void)mdiobus_write(phy_dev->bus, phy_dev->addr, + 9, 0x1F00); + /* Soft-reset */ + (void)mdiobus_write(phy_dev->bus, phy_dev->addr, + 0, 0x9140); + /* If autoneg disabled,two soft-reset operations */ + (void)mdiobus_write(phy_dev->bus, phy_dev->addr, + 0, 0x9140); + (void)mdiobus_write(phy_dev->bus, phy_dev->addr, + 22, 0xFA); + + /* Default is 0x0400 */ + (void)mdiobus_write(phy_dev->bus, phy_dev->addr, + 1, 0x418); + + /* Force 1000M Link, Default is 0x0200 */ + (void)mdiobus_write(phy_dev->bus, phy_dev->addr, + 7, 0x20C); + (void)mdiobus_write(phy_dev->bus, phy_dev->addr, + 22, 0); + + /* Enable MAC loop-back */ + val = (u16)mdiobus_read(phy_dev->bus, phy_dev->addr, + COPPER_CONTROL_REG); + val |= PHY_LOOP_BACK; + (void)mdiobus_write(phy_dev->bus, phy_dev->addr, + COPPER_CONTROL_REG, val); + } else { + (void)mdiobus_write(phy_dev->bus, phy_dev->addr, + 22, 0xFA); + (void)mdiobus_write(phy_dev->bus, phy_dev->addr, + 1, 0x400); + (void)mdiobus_write(phy_dev->bus, phy_dev->addr, + 7, 0x200); + (void)mdiobus_write(phy_dev->bus, phy_dev->addr, + 22, 0); + + val = (u16)mdiobus_read(phy_dev->bus, phy_dev->addr, + COPPER_CONTROL_REG); + val &= ~PHY_LOOP_BACK; + (void)mdiobus_write(phy_dev->bus, phy_dev->addr, + COPPER_CONTROL_REG, val); + } + return 0; +} + +static int __lb_setup(struct net_device *ndev, + enum hnae_loop loop) +{ + int ret = 0; + struct hns_nic_priv *priv = netdev_priv(ndev); + struct phy_device *phy_dev = priv->phy; + struct hnae_handle *h = priv->ae_handle; + + switch (loop) { + case MAC_INTERNALLOOP_PHY: + if ((phy_dev) && (!phy_dev->is_c45)) + ret = hns_nic_config_phy_loopback(phy_dev, 0x1); + break; + case MAC_INTERNALLOOP_MAC: + if ((h->dev->ops->set_loopback) && + (priv->ae_handle->phy_if != PHY_INTERFACE_MODE_XGMII)) + ret = h->dev->ops->set_loopback(h, loop, 0x1); + break; + case MAC_INTERNALLOOP_SERDES: + if (h->dev->ops->set_loopback) + ret = h->dev->ops->set_loopback(h, loop, 0x1); + break; + case MAC_LOOP_NONE: + if ((phy_dev) && (!phy_dev->is_c45)) + ret |= hns_nic_config_phy_loopback(phy_dev, 0x0); + + if (h->dev->ops->set_loopback) { + if (priv->ae_handle->phy_if != PHY_INTERFACE_MODE_XGMII) + ret |= h->dev->ops->set_loopback(h, + MAC_INTERNALLOOP_MAC, 0x0); + + ret |= h->dev->ops->set_loopback(h, + MAC_INTERNALLOOP_SERDES, 0x0); + } + break; + default: + ret = -EINVAL; + break; + } + + return ret; +} + +static int __lb_up(struct net_device *ndev, + enum hnae_loop loop_mode) +{ + struct hns_nic_priv *priv = netdev_priv(ndev); + struct hnae_handle *h = priv->ae_handle; + int speed, duplex; + int ret; + + hns_nic_net_reset(ndev); + + if (priv->phy) { + phy_disconnect(priv->phy); + msleep(100); + + ret = hns_nic_init_phy(ndev, h); + if (ret) + return ret; + } + + ret = __lb_setup(ndev, loop_mode); + if (ret) + return ret; + + msleep(100); + + ret = h->dev->ops->start ? h->dev->ops->start(h) : 0; + if (ret) + return ret; + + if (priv->phy) + phy_start(priv->phy); + + /* link adjust duplex*/ + if (priv->ae_handle->phy_if != PHY_INTERFACE_MODE_XGMII) + speed = 1000; + else + speed = 10000; + duplex = 1; + + h->dev->ops->adjust_link(h, speed, duplex); + + return 0; +} + +static void __lb_other_process(struct hns_nic_ring_data *ring_data, + struct sk_buff *skb) +{ + struct net_device *ndev; + struct hnae_ring *ring; + struct netdev_queue *dev_queue; + struct sk_buff *new_skb; + unsigned int frame_size; + int check_ok; + u32 i; + char buff[33]; /* 32B data and the last character '\0' */ + + if (!ring_data) { /* Just for doing create frame*/ + frame_size = skb->len; + memset(skb->data, 0xFF, frame_size); + frame_size &= ~1ul; + memset(&skb->data[frame_size / 2], 0xAA, frame_size / 2 - 1); + memset(&skb->data[frame_size / 2 + 10], 0xBE, + frame_size / 2 - 11); + memset(&skb->data[frame_size / 2 + 12], 0xAF, + frame_size / 2 - 13); + return; + } + + ring = ring_data->ring; + ndev = ring_data->napi.dev; + if (is_tx_ring(ring)) { /* for tx queue reset*/ + dev_queue = netdev_get_tx_queue(ndev, ring_data->queue_index); + netdev_tx_reset_queue(dev_queue); + return; + } + + frame_size = skb->len; + frame_size &= ~1ul; + /* for mutl buffer*/ + new_skb = skb_copy(skb, GFP_ATOMIC); + dev_kfree_skb_any(skb); + skb = new_skb; + + check_ok = 0; + if (*(skb->data + 10) == 0xFF) { /* for rx check frame*/ + if ((*(skb->data + frame_size / 2 + 10) == 0xBE) && + (*(skb->data + frame_size / 2 + 12) == 0xAF)) + check_ok = 1; + } + + if (check_ok) { + ndev->stats.rx_packets++; + ndev->stats.rx_bytes += skb->len; + } else { + ndev->stats.rx_frame_errors++; + for (i = 0; i < skb->len; i++) { + snprintf(buff + i % 16 * 2, 3, /* tailing \0*/ + "%02x", *(skb->data + i)); + if ((i % 16 == 15) || (i == skb->len - 1)) + pr_info("%s\n", buff); + } + } + dev_kfree_skb_any(skb); +} + +static int __lb_clean_rings(struct hns_nic_priv *priv, + int ringid0, int ringid1, int budget) +{ + int i, ret; + struct hns_nic_ring_data *ring_data; + struct net_device *ndev = priv->netdev; + unsigned long rx_packets = ndev->stats.rx_packets; + unsigned long rx_bytes = ndev->stats.rx_bytes; + unsigned long rx_frame_errors = ndev->stats.rx_frame_errors; + + for (i = ringid0; i <= ringid1; i++) { + ring_data = &priv->ring_data[i]; + (void)ring_data->poll_one(ring_data, + budget, __lb_other_process); + } + ret = (int)(ndev->stats.rx_packets - rx_packets); + ndev->stats.rx_packets = rx_packets; + ndev->stats.rx_bytes = rx_bytes; + ndev->stats.rx_frame_errors = rx_frame_errors; + return ret; +} + +/** + * nic_run_loopback_test - run loopback test + * @nic_dev: net device + * @loopback_type: loopback type + */ +static int __lb_run_test(struct net_device *ndev, + enum hnae_loop loop_mode) +{ +#define NIC_LB_TEST_PKT_NUM_PER_CYCLE 1 +#define NIC_LB_TEST_RING_ID 0 +#define NIC_LB_TEST_FRAME_SIZE 128 +/* nic loopback test err */ +#define NIC_LB_TEST_NO_MEM_ERR 1 +#define NIC_LB_TEST_TX_CNT_ERR 2 +#define NIC_LB_TEST_RX_CNT_ERR 3 +#define NIC_LB_TEST_RX_PKG_ERR 4 + struct hns_nic_priv *priv = netdev_priv(ndev); + struct hnae_handle *h = priv->ae_handle; + int i, j, lc, good_cnt, ret_val = 0; + unsigned int size; + netdev_tx_t tx_ret_val; + struct sk_buff *skb; + + size = NIC_LB_TEST_FRAME_SIZE; + /* allocate test skb */ + skb = alloc_skb(size, GFP_KERNEL); + if (!skb) + return NIC_LB_TEST_NO_MEM_ERR; + + /* place data into test skb */ + (void)skb_put(skb, size); + __lb_other_process(NULL, skb); + skb->queue_mapping = NIC_LB_TEST_RING_ID; + + lc = 1; + for (j = 0; j < lc; j++) { + /* reset count of good packets */ + good_cnt = 0; + /* place 64 packets on the transmit queue*/ + for (i = 0; i < NIC_LB_TEST_PKT_NUM_PER_CYCLE; i++) { + (void)skb_get(skb); + + tx_ret_val = (netdev_tx_t)hns_nic_net_xmit_hw( + ndev, skb, + &tx_ring_data(priv, skb->queue_mapping)); + if (tx_ret_val == NETDEV_TX_OK) + good_cnt++; + else + break; + } + if (good_cnt != NIC_LB_TEST_PKT_NUM_PER_CYCLE) { + ret_val = NIC_LB_TEST_TX_CNT_ERR; + dev_err(priv->dev, "%s sent fail, cnt=0x%x, budget=0x%x\n", + hns_nic_test_strs[loop_mode], good_cnt, + NIC_LB_TEST_PKT_NUM_PER_CYCLE); + break; + } + + /* allow 100 milliseconds for packets to go from Tx to Rx */ + msleep(100); + + good_cnt = __lb_clean_rings(priv, + h->q_num, h->q_num * 2 - 1, + NIC_LB_TEST_PKT_NUM_PER_CYCLE); + if (good_cnt != NIC_LB_TEST_PKT_NUM_PER_CYCLE) { + ret_val = NIC_LB_TEST_RX_CNT_ERR; + dev_err(priv->dev, "%s recv fail, cnt=0x%x, budget=0x%x\n", + hns_nic_test_strs[loop_mode], good_cnt, + NIC_LB_TEST_PKT_NUM_PER_CYCLE); + break; + } + (void)__lb_clean_rings(priv, + NIC_LB_TEST_RING_ID, NIC_LB_TEST_RING_ID, + NIC_LB_TEST_PKT_NUM_PER_CYCLE); + } + + /* free the original skb */ + kfree_skb(skb); + + return ret_val; +} + +static int __lb_down(struct net_device *ndev) +{ + struct hns_nic_priv *priv = netdev_priv(ndev); + struct hnae_handle *h = priv->ae_handle; + int ret; + + ret = __lb_setup(ndev, MAC_LOOP_NONE); + if (ret) + netdev_err(ndev, "%s: __lb_setup return error(%d)!\n", + __func__, + ret); + + if (priv->phy) + phy_stop(priv->phy); + + if (h->dev->ops->stop) + h->dev->ops->stop(h); + + usleep_range(10000, 20000); + (void)__lb_clean_rings(priv, 0, h->q_num - 1, 256); + + hns_nic_net_reset(ndev); + + return 0; +} + +/** + * hns_nic_self_test - self test + * @dev: net device + * @eth_test: test cmd + * @data: test result + */ +static void hns_nic_self_test(struct net_device *ndev, + struct ethtool_test *eth_test, u64 *data) +{ + struct hns_nic_priv *priv = netdev_priv(ndev); + bool if_running = netif_running(ndev); +#define SELF_TEST_TPYE_NUM 3 + int st_param[SELF_TEST_TPYE_NUM][2]; + int i; + int test_index = 0; + + st_param[0][0] = MAC_INTERNALLOOP_MAC; /* XGE not supported lb */ + st_param[0][1] = (priv->ae_handle->phy_if != PHY_INTERFACE_MODE_XGMII); + st_param[1][0] = MAC_INTERNALLOOP_SERDES; + st_param[1][1] = 1; /*serdes must exist*/ + st_param[2][0] = MAC_INTERNALLOOP_PHY; /* only supporte phy node*/ + st_param[2][1] = ((!!(priv->ae_handle->phy_node)) && + (priv->ae_handle->phy_if != PHY_INTERFACE_MODE_XGMII)); + + if (eth_test->flags == ETH_TEST_FL_OFFLINE) { + set_bit(NIC_STATE_TESTING, &priv->state); + + if (if_running) + (void)dev_close(ndev); + + for (i = 0; i < SELF_TEST_TPYE_NUM; i++) { + if (!st_param[i][1]) + continue; /* NEXT testing */ + + data[test_index] = __lb_up(ndev, + (enum hnae_loop)st_param[i][0]); + if (!data[test_index]) { + data[test_index] = __lb_run_test( + ndev, (enum hnae_loop)st_param[i][0]); + (void)__lb_down(ndev); + } + + if (data[test_index]) + eth_test->flags |= ETH_TEST_FL_FAILED; + + test_index++; + } + + hns_nic_net_reset(priv->netdev); + + clear_bit(NIC_STATE_TESTING, &priv->state); + + if (if_running) + (void)dev_open(ndev); + } + /* Online tests aren't run; pass by default */ + + (void)msleep_interruptible(4 * 1000); +} + +/** + * hns_nic_get_drvinfo - get net driver info + * @dev: net device + * @drvinfo: driver info + */ +static void hns_nic_get_drvinfo(struct net_device *net_dev, + struct ethtool_drvinfo *drvinfo) +{ + struct hns_nic_priv *priv = netdev_priv(net_dev); + + assert(priv); + + strncpy(drvinfo->version, HNAE_DRIVER_VERSION, + sizeof(drvinfo->version)); + drvinfo->version[sizeof(drvinfo->version) - 1] = '\0'; + + strncpy(drvinfo->driver, HNAE_DRIVER_NAME, sizeof(drvinfo->driver)); + drvinfo->driver[sizeof(drvinfo->driver) - 1] = '\0'; + + strncpy(drvinfo->bus_info, priv->dev->bus->name, + sizeof(drvinfo->bus_info)); + drvinfo->bus_info[ETHTOOL_BUSINFO_LEN - 1] = '\0'; + + strncpy(drvinfo->fw_version, "N/A", ETHTOOL_FWVERS_LEN); + drvinfo->eedump_len = 0; +} + +/** + * hns_get_ringparam - get ring parameter + * @dev: net device + * @param: ethtool parameter + */ +void hns_get_ringparam(struct net_device *net_dev, + struct ethtool_ringparam *param) +{ + struct hns_nic_priv *priv = netdev_priv(net_dev); + struct hnae_ae_ops *ops; + struct hnae_queue *queue; + u32 uplimit = 0; + + queue = priv->ae_handle->qs[0]; + ops = priv->ae_handle->dev->ops; + + if (ops->get_ring_bdnum_limit) + ops->get_ring_bdnum_limit(queue, &uplimit); + + param->rx_max_pending = uplimit; + param->tx_max_pending = uplimit; + param->rx_pending = queue->rx_ring.desc_num; + param->tx_pending = queue->tx_ring.desc_num; +} + +/** + * hns_get_pauseparam - get pause parameter + * @dev: net device + * @param: pause parameter + */ +static void hns_get_pauseparam(struct net_device *net_dev, + struct ethtool_pauseparam *param) +{ + struct hns_nic_priv *priv = netdev_priv(net_dev); + struct hnae_ae_ops *ops; + + ops = priv->ae_handle->dev->ops; + + if (ops->get_pauseparam) + ops->get_pauseparam(priv->ae_handle, ¶m->autoneg, + ¶m->rx_pause, ¶m->tx_pause); +} + +/** + * hns_set_pauseparam - set pause parameter + * @dev: net device + * @param: pause parameter + * + * Return 0 on success, negative on failure + */ +static int hns_set_pauseparam(struct net_device *net_dev, + struct ethtool_pauseparam *param) +{ + struct hns_nic_priv *priv = netdev_priv(net_dev); + struct hnae_handle *h; + struct hnae_ae_ops *ops; + + assert(priv || priv->ae_handle); + + h = priv->ae_handle; + ops = h->dev->ops; + + if (!ops->set_pauseparam) + return -ESRCH; + + return ops->set_pauseparam(priv->ae_handle, param->autoneg, + param->rx_pause, param->tx_pause); +} + +/** + * hns_get_coalesce - get coalesce info. + * @dev: net device + * @ec: coalesce info. + * + * Return 0 on success, negative on failure. + */ +static int hns_get_coalesce(struct net_device *net_dev, + struct ethtool_coalesce *ec) +{ + struct hns_nic_priv *priv = netdev_priv(net_dev); + struct hnae_ae_ops *ops; + + ops = priv->ae_handle->dev->ops; + + ec->use_adaptive_rx_coalesce = 1; + ec->use_adaptive_tx_coalesce = 1; + + if ((!ops->get_coalesce_usecs) || + (!ops->get_rx_max_coalesced_frames)) + return -ESRCH; + + ops->get_coalesce_usecs(priv->ae_handle, + &ec->tx_coalesce_usecs, + &ec->rx_coalesce_usecs); + + ops->get_rx_max_coalesced_frames( + priv->ae_handle, + &ec->tx_max_coalesced_frames, + &ec->rx_max_coalesced_frames); + + return 0; +} + +/** + * hns_set_coalesce - set coalesce info. + * @dev: net device + * @ec: coalesce info. + * + * Return 0 on success, negative on failure. + */ +static int hns_set_coalesce(struct net_device *net_dev, + struct ethtool_coalesce *ec) +{ + struct hns_nic_priv *priv = netdev_priv(net_dev); + struct hnae_ae_ops *ops; + int ret; + + assert(priv || priv->ae_handle); + + ops = priv->ae_handle->dev->ops; + + if (ec->tx_coalesce_usecs != ec->rx_coalesce_usecs) + return -EINVAL; + + if (ec->rx_max_coalesced_frames != ec->tx_max_coalesced_frames) + return -EINVAL; + + if ((!ops->set_coalesce_usecs) || + (!ops->set_coalesce_frames)) + return -ESRCH; + + ops->set_coalesce_usecs(priv->ae_handle, + ec->rx_coalesce_usecs); + + ret = ops->set_coalesce_frames( + priv->ae_handle, + ec->rx_max_coalesced_frames); + + return ret; +} + +/** + * hns_get_channels - get channel info. + * @dev: net device + * @ch: channel info. + */ +void hns_get_channels(struct net_device *net_dev, struct ethtool_channels *ch) +{ + struct hns_nic_priv *priv = netdev_priv(net_dev); + + ch->max_rx = priv->ae_handle->q_num; + ch->max_tx = priv->ae_handle->q_num; + + ch->rx_count = priv->ae_handle->q_num; + ch->tx_count = priv->ae_handle->q_num; +} + +/** + * get_ethtool_stats - get detail statistics. + * @dev: net device + * @stats: statistics info. + * @data: statistics data. + */ +void hns_get_ethtool_stats(struct net_device *netdev, + struct ethtool_stats *stats, u64 *data) +{ + u64 *p = data; + struct hns_nic_priv *priv = netdev_priv(netdev); + struct hnae_handle *h = priv->ae_handle; + const struct rtnl_link_stats64 *net_stats; + struct rtnl_link_stats64 temp; + + if (!h->dev->ops->get_stats || !h->dev->ops->update_stats) { + netdev_err(netdev, "get_stats or update_stats is null!\n"); + return; + } + + h->dev->ops->update_stats(h, &netdev->stats); + + net_stats = dev_get_stats(netdev, &temp); + + /* get netdev statistics */ + p[0] = net_stats->rx_packets; + p[1] = net_stats->tx_packets; + p[2] = net_stats->rx_bytes; + p[3] = net_stats->tx_bytes; + p[4] = net_stats->rx_errors; + p[5] = net_stats->tx_errors; + p[6] = net_stats->rx_dropped; + p[7] = net_stats->tx_dropped; + p[8] = net_stats->multicast; + p[9] = net_stats->collisions; + p[10] = net_stats->rx_over_errors; + p[11] = net_stats->rx_crc_errors; + p[12] = net_stats->rx_frame_errors; + p[13] = net_stats->rx_fifo_errors; + p[14] = net_stats->rx_missed_errors; + p[15] = net_stats->tx_aborted_errors; + p[16] = net_stats->tx_carrier_errors; + p[17] = net_stats->tx_fifo_errors; + p[18] = net_stats->tx_heartbeat_errors; + p[19] = net_stats->rx_length_errors; + p[20] = net_stats->tx_window_errors; + p[21] = net_stats->rx_compressed; + p[22] = net_stats->tx_compressed; + + p[23] = netdev->rx_dropped.counter; + p[24] = netdev->tx_dropped.counter; + + p[25] = priv->tx_timeout_count; + + /* get driver statistics */ + h->dev->ops->get_stats(h, &p[26]); +} + +/** + * get_strings: Return a set of strings that describe the requested objects + * @dev: net device + * @stats: string set ID. + * @data: objects data. + */ +void hns_get_strings(struct net_device *netdev, u32 stringset, u8 *data) +{ + struct hns_nic_priv *priv = netdev_priv(netdev); + struct hnae_handle *h = priv->ae_handle; + char *buff = (char *)data; + + if (!h->dev->ops->get_strings) { + netdev_err(netdev, "h->dev->ops->get_strings is null!\n"); + return; + } + + if (stringset == ETH_SS_TEST) { + if (priv->ae_handle->phy_if != PHY_INTERFACE_MODE_XGMII) { + memcpy(buff, hns_nic_test_strs[MAC_INTERNALLOOP_MAC], + ETH_GSTRING_LEN); + buff += ETH_GSTRING_LEN; + } + memcpy(buff, hns_nic_test_strs[MAC_INTERNALLOOP_SERDES], + ETH_GSTRING_LEN); + buff += ETH_GSTRING_LEN; + if ((priv->phy) && (!priv->phy->is_c45)) + memcpy(buff, hns_nic_test_strs[MAC_INTERNALLOOP_PHY], + ETH_GSTRING_LEN); + + } else { + snprintf(buff, ETH_GSTRING_LEN, "rx_packets"); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "tx_packets"); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "rx_bytes"); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "tx_bytes"); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "rx_errors"); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "tx_errors"); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "rx_dropped"); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "tx_dropped"); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "multicast"); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "collisions"); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "rx_over_errors"); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "rx_crc_errors"); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "rx_frame_errors"); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "rx_fifo_errors"); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "rx_missed_errors"); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "tx_aborted_errors"); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "tx_carrier_errors"); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "tx_fifo_errors"); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "tx_heartbeat_errors"); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "rx_length_errors"); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "tx_window_errors"); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "rx_compressed"); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "tx_compressed"); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "netdev_rx_dropped"); + buff = buff + ETH_GSTRING_LEN; + snprintf(buff, ETH_GSTRING_LEN, "netdev_tx_dropped"); + buff = buff + ETH_GSTRING_LEN; + + snprintf(buff, ETH_GSTRING_LEN, "netdev_tx_timeout"); + buff = buff + ETH_GSTRING_LEN; + + h->dev->ops->get_strings(h, stringset, (u8 *)buff); + } +} + +/** + * nic_get_sset_count - get string set count witch returned by nic_get_strings. + * @dev: net device + * @stringset: string set index, 0: self test string; 1: statistics string. + * + * Return string set count. + */ +int hns_get_sset_count(struct net_device *netdev, int stringset) +{ + struct hns_nic_priv *priv = netdev_priv(netdev); + struct hnae_handle *h = priv->ae_handle; + struct hnae_ae_ops *ops = h->dev->ops; + + if (!ops->get_sset_count) { + netdev_err(netdev, "get_sset_count is null!\n"); + return -EOPNOTSUPP; + } + if (stringset == ETH_SS_TEST) { + u32 cnt = (sizeof(hns_nic_test_strs) / ETH_GSTRING_LEN); + + if (priv->ae_handle->phy_if == PHY_INTERFACE_MODE_XGMII) + cnt--; + + if ((!priv->phy) || (priv->phy->is_c45)) + cnt--; + + return cnt; + } else { + return (HNS_NET_STATS_CNT + ops->get_sset_count(h, stringset)); + } +} + +/** + * hns_phy_led_set - set phy LED status. + * @dev: net device + * @value: LED state. + * + * Return 0 on success, negative on failure. + */ +int hns_phy_led_set(struct net_device *netdev, int value) +{ + int retval; + struct hns_nic_priv *priv = netdev_priv(netdev); + struct phy_device *phy_dev = priv->phy; + + if (!phy_dev->bus) { + netdev_err(netdev, "phy_dev->bus is null!\n"); + return -EINVAL; + } + retval = mdiobus_write(phy_dev->bus, phy_dev->addr, + HNS_PHY_PAGE_REG, HNS_PHY_PAGE_LED); + retval = mdiobus_write(phy_dev->bus, phy_dev->addr, HNS_LED_FC_REG, + value); + retval = mdiobus_write(phy_dev->bus, phy_dev->addr, + HNS_PHY_PAGE_REG, HNS_PHY_PAGE_COPPER); + if (retval) { + netdev_err(netdev, "mdiobus_write fail !\n"); + return retval; + } + return 0; +} + +/** + * nic_set_phys_id - set phy identify LED. + * @dev: net device + * @state: LED state. + * + * Return 0 on success, negative on failure. + */ +int hns_set_phys_id(struct net_device *netdev, enum ethtool_phys_id_state state) +{ + struct hns_nic_priv *priv = netdev_priv(netdev); + struct hnae_handle *h = priv->ae_handle; + struct phy_device *phy_dev = priv->phy; + int ret; + + if (phy_dev) + switch (state) { + case ETHTOOL_ID_ACTIVE: + ret = mdiobus_write(phy_dev->bus, phy_dev->addr, + HNS_PHY_PAGE_REG, + HNS_PHY_PAGE_LED); + if (ret) + return ret; + + priv->phy_led_val = (u16)mdiobus_read(phy_dev->bus, + phy_dev->addr, + HNS_LED_FC_REG); + + ret = mdiobus_write(phy_dev->bus, phy_dev->addr, + HNS_PHY_PAGE_REG, + HNS_PHY_PAGE_COPPER); + if (ret) + return ret; + return 2; + case ETHTOOL_ID_ON: + ret = hns_phy_led_set(netdev, HNS_LED_FORCE_ON); + if (ret) + return ret; + break; + case ETHTOOL_ID_OFF: + ret = hns_phy_led_set(netdev, HNS_LED_FORCE_OFF); + if (ret) + return ret; + break; + case ETHTOOL_ID_INACTIVE: + ret = mdiobus_write(phy_dev->bus, phy_dev->addr, + HNS_PHY_PAGE_REG, + HNS_PHY_PAGE_LED); + if (ret) + return ret; + + ret = mdiobus_write(phy_dev->bus, phy_dev->addr, + HNS_LED_FC_REG, priv->phy_led_val); + if (ret) + return ret; + + ret = mdiobus_write(phy_dev->bus, phy_dev->addr, + HNS_PHY_PAGE_REG, + HNS_PHY_PAGE_COPPER); + if (ret) + return ret; + break; + default: + return -EINVAL; + } + else + switch (state) { + case ETHTOOL_ID_ACTIVE: + return h->dev->ops->set_led_id(h, HNAE_LED_ACTIVE); + case ETHTOOL_ID_ON: + return h->dev->ops->set_led_id(h, HNAE_LED_ON); + case ETHTOOL_ID_OFF: + return h->dev->ops->set_led_id(h, HNAE_LED_OFF); + case ETHTOOL_ID_INACTIVE: + return h->dev->ops->set_led_id(h, HNAE_LED_INACTIVE); + default: + return -EINVAL; + } + + return 0; +} + +/** + * hns_get_regs - get net device register + * @dev: net device + * @cmd: ethtool cmd + * @date: register data + */ +void hns_get_regs(struct net_device *net_dev, struct ethtool_regs *cmd, + void *data) +{ + struct hns_nic_priv *priv = netdev_priv(net_dev); + struct hnae_ae_ops *ops; + + assert(priv || priv->ae_handle); + + ops = priv->ae_handle->dev->ops; + + cmd->version = HNS_CHIP_VERSION; + if (!ops->get_regs) { + netdev_err(net_dev, "ops->get_regs is null!\n"); + return; + } + ops->get_regs(priv->ae_handle, data); +} + +/** + * nic_get_regs_len - get total register len. + * @dev: net device + * + * Return total register len. + */ +static int hns_get_regs_len(struct net_device *net_dev) +{ + u32 reg_num; + struct hns_nic_priv *priv = netdev_priv(net_dev); + struct hnae_ae_ops *ops; + + assert(priv || priv->ae_handle); + + ops = priv->ae_handle->dev->ops; + if (!ops->get_regs_len) { + netdev_err(net_dev, "ops->get_regs_len is null!\n"); + return -EOPNOTSUPP; + } + + reg_num = ops->get_regs_len(priv->ae_handle); + if (reg_num > 0) + return reg_num * sizeof(u32); + else + return reg_num; /* error code */ +} + +/** + * hns_nic_nway_reset - nway reset + * @dev: net device + * + * Return 0 on success, negative on failure + */ +static int hns_nic_nway_reset(struct net_device *netdev) +{ + int ret = 0; + struct hns_nic_priv *priv = netdev_priv(netdev); + struct phy_device *phy = priv->phy; + + if (netif_running(netdev)) { + if (phy) + ret = genphy_restart_aneg(phy); + } + + return ret; +} + +static struct ethtool_ops hns_ethtool_ops = { + .get_drvinfo = hns_nic_get_drvinfo, + .get_link = hns_nic_get_link, + .get_settings = hns_nic_get_settings, + .set_settings = hns_nic_set_settings, + .get_ringparam = hns_get_ringparam, + .get_pauseparam = hns_get_pauseparam, + .set_pauseparam = hns_set_pauseparam, + .get_coalesce = hns_get_coalesce, + .set_coalesce = hns_set_coalesce, + .get_channels = hns_get_channels, + .self_test = hns_nic_self_test, + .get_strings = hns_get_strings, + .get_sset_count = hns_get_sset_count, + .get_ethtool_stats = hns_get_ethtool_stats, + .set_phys_id = hns_set_phys_id, + .get_regs_len = hns_get_regs_len, + .get_regs = hns_get_regs, + .nway_reset = hns_nic_nway_reset, +}; + +void hns_ethtool_set_ops(struct net_device *ndev) +{ + ndev->ethtool_ops = &hns_ethtool_ops; +} diff --git a/drivers/net/ethernet/hisilicon/hns_mdio.c b/drivers/net/ethernet/hisilicon/hns_mdio.c new file mode 100644 index 000000000000..e4ec52ae61ff --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns_mdio.c @@ -0,0 +1,520 @@ +/* + * Copyright (c) 2014-2015 Hisilicon Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/errno.h> +#include <linux/etherdevice.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/mutex.h> +#include <linux/netdevice.h> +#include <linux/of_address.h> +#include <linux/of.h> +#include <linux/of_mdio.h> +#include <linux/of_platform.h> +#include <linux/phy.h> +#include <linux/platform_device.h> +#include <linux/spinlock_types.h> + +#define MDIO_DRV_NAME "Hi-HNS_MDIO" +#define MDIO_BUS_NAME "Hisilicon MII Bus" +#define MDIO_DRV_VERSION "1.3.0" +#define MDIO_COPYRIGHT "Copyright(c) 2015 Huawei Corporation." +#define MDIO_DRV_STRING MDIO_BUS_NAME +#define MDIO_DEFAULT_DEVICE_DESCR MDIO_BUS_NAME + +#define MDIO_CTL_DEV_ADDR(x) (x & 0x1f) +#define MDIO_CTL_PORT_ADDR(x) ((x & 0x1f) << 5) + +#define MDIO_TIMEOUT 1000000 + +struct hns_mdio_device { + void *vbase; /* mdio reg base address */ + void *sys_vbase; +}; + +/* mdio reg */ +#define MDIO_COMMAND_REG 0x0 +#define MDIO_ADDR_REG 0x4 +#define MDIO_WDATA_REG 0x8 +#define MDIO_RDATA_REG 0xc +#define MDIO_STA_REG 0x10 + +/* cfg phy bit map */ +#define MDIO_CMD_DEVAD_M 0x1f +#define MDIO_CMD_DEVAD_S 0 +#define MDIO_CMD_PRTAD_M 0x1f +#define MDIO_CMD_PRTAD_S 5 +#define MDIO_CMD_OP_M 0x3 +#define MDIO_CMD_OP_S 10 +#define MDIO_CMD_ST_M 0x3 +#define MDIO_CMD_ST_S 12 +#define MDIO_CMD_START_B 14 + +#define MDIO_ADDR_DATA_M 0xffff +#define MDIO_ADDR_DATA_S 0 + +#define MDIO_WDATA_DATA_M 0xffff +#define MDIO_WDATA_DATA_S 0 + +#define MDIO_RDATA_DATA_M 0xffff +#define MDIO_RDATA_DATA_S 0 + +#define MDIO_STATE_STA_B 0 + +enum mdio_st_clause { + MDIO_ST_CLAUSE_45 = 0, + MDIO_ST_CLAUSE_22 +}; + +enum mdio_c22_op_seq { + MDIO_C22_WRITE = 1, + MDIO_C22_READ = 2 +}; + +enum mdio_c45_op_seq { + MDIO_C45_WRITE_ADDR = 0, + MDIO_C45_WRITE_DATA, + MDIO_C45_READ_INCREMENT, + MDIO_C45_READ +}; + +/* peri subctrl reg */ +#define MDIO_SC_CLK_EN 0x338 +#define MDIO_SC_CLK_DIS 0x33C +#define MDIO_SC_RESET_REQ 0xA38 +#define MDIO_SC_RESET_DREQ 0xA3C +#define MDIO_SC_CTRL 0x2010 +#define MDIO_SC_CLK_ST 0x531C +#define MDIO_SC_RESET_ST 0x5A1C + +static void mdio_write_reg(void *base, u32 reg, u32 value) +{ + u8 __iomem *reg_addr = (u8 __iomem *)base; + + writel_relaxed(value, reg_addr + reg); +} + +#define MDIO_WRITE_REG(a, reg, value) \ + mdio_write_reg((a)->vbase, (reg), (value)) + +static u32 mdio_read_reg(void *base, u32 reg) +{ + u8 __iomem *reg_addr = (u8 __iomem *)base; + + return readl_relaxed(reg_addr + reg); +} + +#define mdio_set_field(origin, mask, shift, val) \ + do { \ + (origin) &= (~((mask) << (shift))); \ + (origin) |= (((val) & (mask)) << (shift)); \ + } while (0) + +#define mdio_get_field(origin, mask, shift) (((origin) >> (shift)) & (mask)) + +static void mdio_set_reg_field(void *base, u32 reg, u32 mask, u32 shift, + u32 val) +{ + u32 origin = mdio_read_reg(base, reg); + + mdio_set_field(origin, mask, shift, val); + mdio_write_reg(base, reg, origin); +} + +#define MDIO_SET_REG_FIELD(dev, reg, mask, shift, val) \ + mdio_set_reg_field((dev)->vbase, (reg), (mask), (shift), (val)) + +static u32 mdio_get_reg_field(void *base, u32 reg, u32 mask, u32 shift) +{ + u32 origin; + + origin = mdio_read_reg(base, reg); + return mdio_get_field(origin, mask, shift); +} + +#define MDIO_GET_REG_FIELD(dev, reg, mask, shift) \ + mdio_get_reg_field((dev)->vbase, (reg), (mask), (shift)) + +#define MDIO_GET_REG_BIT(dev, reg, bit) \ + mdio_get_reg_field((dev)->vbase, (reg), 0x1ull, (bit)) + +#define MDIO_CHECK_SET_ST 1 +#define MDIO_CHECK_CLR_ST 0 + +static int mdio_sc_cfg_reg_write(struct hns_mdio_device *mdio_dev, + u32 cfg_reg, u32 set_val, + u32 st_reg, u32 st_msk, u8 check_st) +{ + u32 time_cnt; + u32 reg_value; + + mdio_write_reg((void *)mdio_dev->sys_vbase, cfg_reg, set_val); + + for (time_cnt = MDIO_TIMEOUT; time_cnt; time_cnt--) { + reg_value = mdio_read_reg((void *)mdio_dev->sys_vbase, st_reg); + reg_value &= st_msk; + if ((!!check_st) == (!!reg_value)) + break; + } + + if ((!!check_st) != (!!reg_value)) + return -EBUSY; + + return 0; +} + +static int hns_mdio_wait_ready(struct mii_bus *bus) +{ + struct hns_mdio_device *mdio_dev = bus->priv; + int i; + u32 cmd_reg_value = 1; + + /* waitting for MDIO_COMMAND_REG 's mdio_start==0 */ + /* after that can do read or write*/ + for (i = 0; cmd_reg_value; i++) { + cmd_reg_value = MDIO_GET_REG_BIT(mdio_dev, + MDIO_COMMAND_REG, + MDIO_CMD_START_B); + if (i == MDIO_TIMEOUT) + return -ETIMEDOUT; + } + + return 0; +} + +static void hns_mdio_cmd_write(struct hns_mdio_device *mdio_dev, + u8 is_c45, u8 op, u8 phy_id, u16 cmd) +{ + u32 cmd_reg_value; + u8 st = is_c45 ? MDIO_ST_CLAUSE_45 : MDIO_ST_CLAUSE_22; + + cmd_reg_value = st << MDIO_CMD_ST_S; + cmd_reg_value |= op << MDIO_CMD_OP_S; + cmd_reg_value |= + (phy_id & MDIO_CMD_PRTAD_M) << MDIO_CMD_PRTAD_S; + cmd_reg_value |= (cmd & MDIO_CMD_DEVAD_M) << MDIO_CMD_DEVAD_S; + cmd_reg_value |= 1 << MDIO_CMD_START_B; + + MDIO_WRITE_REG(mdio_dev, MDIO_COMMAND_REG, cmd_reg_value); +} + +/** + * hns_mdio_write - access phy register + * @bus: mdio bus + * @phy_id: phy id + * @regnum: register num + * @value: register value + * + * Return 0 on success, negative on failure + */ +static int hns_mdio_write(struct mii_bus *bus, + int phy_id, int regnum, u16 data) +{ + int ret; + struct hns_mdio_device *mdio_dev = (struct hns_mdio_device *)bus->priv; + u8 devad = ((regnum >> 16) & 0x1f); + u8 is_c45 = !!(regnum & MII_ADDR_C45); + u16 reg = (u16)(regnum & 0xffff); + u8 op; + u16 cmd_reg_cfg; + + dev_dbg(&bus->dev, "mdio write %s,base is %p\n", + bus->id, mdio_dev->vbase); + dev_dbg(&bus->dev, "phy id=%d, is_c45=%d, devad=%d, reg=%#x, write data=%d\n", + phy_id, is_c45, devad, reg, data); + + /* wait for ready */ + ret = hns_mdio_wait_ready(bus); + if (ret) { + dev_err(&bus->dev, "MDIO bus is busy\n"); + return ret; + } + + if (!is_c45) { + cmd_reg_cfg = reg; + op = MDIO_C22_WRITE; + } else { + /* config the cmd-reg to write addr*/ + MDIO_SET_REG_FIELD(mdio_dev, MDIO_ADDR_REG, MDIO_ADDR_DATA_M, + MDIO_ADDR_DATA_S, reg); + + hns_mdio_cmd_write(mdio_dev, is_c45, + MDIO_C45_WRITE_ADDR, phy_id, devad); + + /* check for read or write opt is finished */ + ret = hns_mdio_wait_ready(bus); + if (ret) { + dev_err(&bus->dev, "MDIO bus is busy\n"); + return ret; + } + + /* config the data needed writing */ + cmd_reg_cfg = devad; + op = MDIO_C45_WRITE_ADDR; + } + + MDIO_SET_REG_FIELD(mdio_dev, MDIO_WDATA_REG, MDIO_WDATA_DATA_M, + MDIO_WDATA_DATA_S, data); + + hns_mdio_cmd_write(mdio_dev, is_c45, op, phy_id, cmd_reg_cfg); + + return 0; +} + +/** + * hns_mdio_read - access phy register + * @bus: mdio bus + * @phy_id: phy id + * @regnum: register num + * @value: register value + * + * Return phy register value + */ +static int hns_mdio_read(struct mii_bus *bus, int phy_id, int regnum) +{ + int ret; + u16 reg_val = 0; + u8 devad = ((regnum >> 16) & 0x1f); + u8 is_c45 = !!(regnum & MII_ADDR_C45); + u16 reg = (u16)(regnum & 0xffff); + struct hns_mdio_device *mdio_dev = (struct hns_mdio_device *)bus->priv; + + dev_dbg(&bus->dev, "mdio read %s,base is %p\n", + bus->id, mdio_dev->vbase); + dev_dbg(&bus->dev, "phy id=%d, is_c45=%d, devad=%d, reg=%#x!\n", + phy_id, is_c45, devad, reg); + + /* Step 1: wait for ready */ + ret = hns_mdio_wait_ready(bus); + if (ret) { + dev_err(&bus->dev, "MDIO bus is busy\n"); + return ret; + } + + if (!is_c45) { + hns_mdio_cmd_write(mdio_dev, is_c45, + MDIO_C22_READ, phy_id, reg); + } else { + MDIO_SET_REG_FIELD(mdio_dev, MDIO_ADDR_REG, MDIO_ADDR_DATA_M, + MDIO_ADDR_DATA_S, reg); + + /* Step 2; config the cmd-reg to write addr*/ + hns_mdio_cmd_write(mdio_dev, is_c45, + MDIO_C45_WRITE_ADDR, phy_id, devad); + + /* Step 3: check for read or write opt is finished */ + ret = hns_mdio_wait_ready(bus); + if (ret) { + dev_err(&bus->dev, "MDIO bus is busy\n"); + return ret; + } + + hns_mdio_cmd_write(mdio_dev, is_c45, + MDIO_C45_WRITE_ADDR, phy_id, devad); + } + + /* Step 5: waitting for MDIO_COMMAND_REG 's mdio_start==0,*/ + /* check for read or write opt is finished */ + ret = hns_mdio_wait_ready(bus); + if (ret) { + dev_err(&bus->dev, "MDIO bus is busy\n"); + return ret; + } + + reg_val = MDIO_GET_REG_BIT(mdio_dev, MDIO_STA_REG, MDIO_STATE_STA_B); + if (reg_val) { + dev_err(&bus->dev, " ERROR! MDIO Read failed!\n"); + return -EBUSY; + } + + /* Step 6; get out data*/ + reg_val = (u16)MDIO_GET_REG_FIELD(mdio_dev, MDIO_RDATA_REG, + MDIO_RDATA_DATA_M, MDIO_RDATA_DATA_S); + + return reg_val; +} + +/** + * hns_mdio_reset - reset mdio bus + * @bus: mdio bus + * + * Return 0 on success, negative on failure + */ +static int hns_mdio_reset(struct mii_bus *bus) +{ + struct hns_mdio_device *mdio_dev = (struct hns_mdio_device *)bus->priv; + int ret; + + if (!mdio_dev->sys_vbase) { + dev_err(&bus->dev, "mdio sys ctl reg has not maped\n"); + return -ENODEV; + } + + /*1. reset req, and read reset st check*/ + ret = mdio_sc_cfg_reg_write(mdio_dev, MDIO_SC_RESET_REQ, 0x1, + MDIO_SC_RESET_ST, 0x1, + MDIO_CHECK_SET_ST); + if (ret) { + dev_err(&bus->dev, "MDIO reset fail\n"); + return ret; + } + + /*2. dis clk, and read clk st check*/ + ret = mdio_sc_cfg_reg_write(mdio_dev, MDIO_SC_CLK_DIS, + 0x1, MDIO_SC_CLK_ST, 0x1, + MDIO_CHECK_CLR_ST); + if (ret) { + dev_err(&bus->dev, "MDIO dis clk fail\n"); + return ret; + } + + /*3. reset dreq, and read reset st check*/ + ret = mdio_sc_cfg_reg_write(mdio_dev, MDIO_SC_RESET_DREQ, 0x1, + MDIO_SC_RESET_ST, 0x1, + MDIO_CHECK_CLR_ST); + if (ret) { + dev_err(&bus->dev, "MDIO dis clk fail\n"); + return ret; + } + + /*4. en clk, and read clk st check*/ + ret = mdio_sc_cfg_reg_write(mdio_dev, MDIO_SC_CLK_EN, + 0x1, MDIO_SC_CLK_ST, 0x1, + MDIO_CHECK_SET_ST); + if (ret) + dev_err(&bus->dev, "MDIO en clk fail\n"); + + return ret; +} + +/** + * hns_mdio_bus_name - get mdio bus name + * @name: mdio bus name + * @np: mdio device node pointer + */ +static void hns_mdio_bus_name(char *name, struct device_node *np) +{ + const u32 *addr; + u64 taddr = OF_BAD_ADDR; + + addr = of_get_address(np, 0, NULL, NULL); + if (addr) + taddr = of_translate_address(np, addr); + + snprintf(name, MII_BUS_ID_SIZE, "%s@%llx", np->name, + (unsigned long long)taddr); +} + +/** + * hns_mdio_probe - probe mdio device + * @pdev: mdio platform device + * + * Return 0 on success, negative on failure + */ +static int hns_mdio_probe(struct platform_device *pdev) +{ + struct device_node *np; + struct hns_mdio_device *mdio_dev; + struct mii_bus *new_bus; + struct resource *res; + int ret; + + if (!pdev) { + dev_err(NULL, "pdev is NULL!\r\n"); + return -ENODEV; + } + np = pdev->dev.of_node; + mdio_dev = devm_kzalloc(&pdev->dev, sizeof(*mdio_dev), GFP_KERNEL); + if (!mdio_dev) + return -ENOMEM; + + new_bus = devm_mdiobus_alloc(&pdev->dev); + if (!new_bus) { + dev_err(&pdev->dev, "mdiobus_alloc fail!\n"); + return -ENOMEM; + } + + new_bus->name = MDIO_BUS_NAME; + new_bus->read = hns_mdio_read; + new_bus->write = hns_mdio_write; + new_bus->reset = hns_mdio_reset; + new_bus->priv = mdio_dev; + hns_mdio_bus_name(new_bus->id, np); + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + mdio_dev->vbase = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(mdio_dev->vbase)) { + ret = PTR_ERR(mdio_dev->vbase); + return ret; + } + + res = platform_get_resource(pdev, IORESOURCE_MEM, 1); + mdio_dev->sys_vbase = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(mdio_dev->sys_vbase)) { + ret = PTR_ERR(mdio_dev->sys_vbase); + return ret; + } + + new_bus->irq = devm_kcalloc(&pdev->dev, PHY_MAX_ADDR, + sizeof(int), GFP_KERNEL); + if (!new_bus->irq) + return -ENOMEM; + + new_bus->parent = &pdev->dev; + platform_set_drvdata(pdev, new_bus); + + ret = of_mdiobus_register(new_bus, np); + if (ret) { + dev_err(&pdev->dev, "Cannot register as MDIO bus!\n"); + platform_set_drvdata(pdev, NULL); + return ret; + } + + return 0; +} + +/** + * hns_mdio_remove - remove mdio device + * @pdev: mdio platform device + * + * Return 0 on success, negative on failure + */ +static int hns_mdio_remove(struct platform_device *pdev) +{ + struct mii_bus *bus; + + bus = platform_get_drvdata(pdev); + + mdiobus_unregister(bus); + platform_set_drvdata(pdev, NULL); + return 0; +} + +static const struct of_device_id hns_mdio_match[] = { + {.compatible = "hisilicon,mdio"}, + {.compatible = "hisilicon,hns-mdio"}, + {} +}; + +static struct platform_driver hns_mdio_driver = { + .probe = hns_mdio_probe, + .remove = hns_mdio_remove, + .driver = { + .name = MDIO_DRV_NAME, + .of_match_table = hns_mdio_match, + }, +}; + +module_platform_driver(hns_mdio_driver); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Huawei Tech. Co., Ltd."); +MODULE_DESCRIPTION("Hisilicon HNS MDIO driver"); +MODULE_ALIAS("platform:" MDIO_DRV_NAME); diff --git a/drivers/net/ethernet/ibm/emac/core.h b/drivers/net/ethernet/ibm/emac/core.h index ac02c675c59c..93ae11494810 100644 --- a/drivers/net/ethernet/ibm/emac/core.h +++ b/drivers/net/ethernet/ibm/emac/core.h @@ -181,7 +181,7 @@ struct emac_instance { struct mal_commac commac; /* PHY infos */ - u32 phy_mode; + int phy_mode; u32 phy_map; u32 phy_address; u32 phy_feat_exc; diff --git a/drivers/net/ethernet/intel/e1000/e1000_hw.c b/drivers/net/ethernet/intel/e1000/e1000_hw.c index 45c8c864104e..b1af0d613caa 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_hw.c +++ b/drivers/net/ethernet/intel/e1000/e1000_hw.c @@ -3900,10 +3900,6 @@ static s32 e1000_do_read_eeprom(struct e1000_hw *hw, u16 offset, u16 words, return E1000_SUCCESS; } - /* If eeprom is not yet detected, do so now */ - if (eeprom->word_size == 0) - e1000_init_eeprom_params(hw); - /* A check for invalid values: offset too large, too many words, and * not enough words. */ @@ -4074,10 +4070,6 @@ static s32 e1000_do_write_eeprom(struct e1000_hw *hw, u16 offset, u16 words, return E1000_SUCCESS; } - /* If eeprom is not yet detected, do so now */ - if (eeprom->word_size == 0) - e1000_init_eeprom_params(hw); - /* A check for invalid values: offset too large, too many words, and * not enough words. */ diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index faf4b3f3d0b5..2e2ddec04a50 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -6952,6 +6952,7 @@ static const struct net_device_ops e1000e_netdev_ops = { #endif .ndo_set_features = e1000_set_features, .ndo_fix_features = e1000_fix_features, + .ndo_features_check = passthru_features_check, }; /** diff --git a/drivers/net/ethernet/intel/fm10k/fm10k.h b/drivers/net/ethernet/intel/fm10k/fm10k.h index c8c8c5baefda..14440200499b 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k.h @@ -101,12 +101,19 @@ struct fm10k_tx_queue_stats { u64 csum_err; u64 tx_busy; u64 tx_done_old; + u64 csum_good; }; struct fm10k_rx_queue_stats { u64 alloc_failed; u64 csum_err; u64 errors; + u64 csum_good; + u64 switch_errors; + u64 drops; + u64 pp_errors; + u64 link_errors; + u64 length_errors; }; struct fm10k_ring { @@ -251,6 +258,7 @@ struct fm10k_intfc { #define FM10K_FLAG_RSS_FIELD_IPV6_UDP (u32)(1 << 2) #define FM10K_FLAG_RX_TS_ENABLED (u32)(1 << 3) #define FM10K_FLAG_SWPRI_CONFIG (u32)(1 << 4) +#define FM10K_FLAG_DEBUG_STATS (u32)(1 << 5) int xcast_mode; /* Tx fast path data */ @@ -277,6 +285,17 @@ struct fm10k_intfc { u64 rx_drops_nic; u64 rx_overrun_pf; u64 rx_overrun_vf; + + /* Debug Statistics */ + u64 hw_sm_mbx_full; + u64 hw_csum_tx_good; + u64 hw_csum_rx_good; + u64 rx_switch_errors; + u64 rx_drops; + u64 rx_pp_errors; + u64 rx_link_errors; + u64 rx_length_errors; + u32 tx_timeout_count; /* RX */ diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c b/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c index f45b4d71adb8..08ecf43dffc7 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c @@ -37,7 +37,8 @@ static void *fm10k_dbg_desc_seq_start(struct seq_file *s, loff_t *pos) } static void *fm10k_dbg_desc_seq_next(struct seq_file *s, - void __always_unused *v, loff_t *pos) + void __always_unused *v, + loff_t *pos) { struct fm10k_ring *ring = s->private; @@ -45,7 +46,7 @@ static void *fm10k_dbg_desc_seq_next(struct seq_file *s, } static void fm10k_dbg_desc_seq_stop(struct seq_file __always_unused *s, - __always_unused void *v) + void __always_unused *v) { /* Do nothing. */ } diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c index c6dc9683429e..4ef2fbd22911 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c @@ -76,19 +76,22 @@ static const struct fm10k_stats fm10k_gstrings_global_stats[] = { FM10K_STAT("mac_rules_used", hw.swapi.mac.used), FM10K_STAT("mac_rules_avail", hw.swapi.mac.avail), - FM10K_STAT("mbx_tx_busy", hw.mbx.tx_busy), - FM10K_STAT("mbx_tx_oversized", hw.mbx.tx_dropped), - FM10K_STAT("mbx_tx_messages", hw.mbx.tx_messages), - FM10K_STAT("mbx_tx_dwords", hw.mbx.tx_dwords), - FM10K_STAT("mbx_rx_messages", hw.mbx.rx_messages), - FM10K_STAT("mbx_rx_dwords", hw.mbx.rx_dwords), - FM10K_STAT("mbx_rx_parse_err", hw.mbx.rx_parse_err), - FM10K_STAT("tx_hang_count", tx_timeout_count), FM10K_STAT("tx_hwtstamp_timeouts", tx_hwtstamp_timeouts), }; +static const struct fm10k_stats fm10k_gstrings_debug_stats[] = { + FM10K_STAT("hw_sm_mbx_full", hw_sm_mbx_full), + FM10K_STAT("hw_csum_tx_good", hw_csum_tx_good), + FM10K_STAT("hw_csum_rx_good", hw_csum_rx_good), + FM10K_STAT("rx_switch_errors", rx_switch_errors), + FM10K_STAT("rx_drops", rx_drops), + FM10K_STAT("rx_pp_errors", rx_pp_errors), + FM10K_STAT("rx_link_errors", rx_link_errors), + FM10K_STAT("rx_length_errors", rx_length_errors), +}; + static const struct fm10k_stats fm10k_gstrings_pf_stats[] = { FM10K_STAT("timeout", stats.timeout.count), FM10K_STAT("ur", stats.ur.count), @@ -100,14 +103,33 @@ static const struct fm10k_stats fm10k_gstrings_pf_stats[] = { FM10K_STAT("nodesc_drop", stats.nodesc_drop.count), }; +#define FM10K_MBX_STAT(_name, _stat) { \ + .stat_string = _name, \ + .sizeof_stat = FIELD_SIZEOF(struct fm10k_mbx_info, _stat), \ + .stat_offset = offsetof(struct fm10k_mbx_info, _stat) \ +} + +static const struct fm10k_stats fm10k_gstrings_mbx_stats[] = { + FM10K_MBX_STAT("mbx_tx_busy", tx_busy), + FM10K_MBX_STAT("mbx_tx_oversized", tx_dropped), + FM10K_MBX_STAT("mbx_tx_messages", tx_messages), + FM10K_MBX_STAT("mbx_tx_dwords", tx_dwords), + FM10K_MBX_STAT("mbx_rx_messages", rx_messages), + FM10K_MBX_STAT("mbx_rx_dwords", rx_dwords), + FM10K_MBX_STAT("mbx_rx_parse_err", rx_parse_err), +}; + #define FM10K_GLOBAL_STATS_LEN ARRAY_SIZE(fm10k_gstrings_global_stats) +#define FM10K_DEBUG_STATS_LEN ARRAY_SIZE(fm10k_gstrings_debug_stats) #define FM10K_PF_STATS_LEN ARRAY_SIZE(fm10k_gstrings_pf_stats) +#define FM10K_MBX_STATS_LEN ARRAY_SIZE(fm10k_gstrings_mbx_stats) #define FM10K_QUEUE_STATS_LEN(_n) \ ( (_n) * 2 * (sizeof(struct fm10k_queue_stats) / sizeof(u64))) #define FM10K_STATIC_STATS_LEN (FM10K_GLOBAL_STATS_LEN + \ - FM10K_NETDEV_STATS_LEN) + FM10K_NETDEV_STATS_LEN + \ + FM10K_MBX_STATS_LEN) static const char fm10k_gstrings_test[][ETH_GSTRING_LEN] = { "Mailbox test (on/offline)" @@ -120,47 +142,97 @@ enum fm10k_self_test_types { FM10K_TEST_MAX = FM10K_TEST_LEN }; -static void fm10k_get_strings(struct net_device *dev, u32 stringset, u8 *data) +enum { + FM10K_PRV_FLAG_DEBUG_STATS, + FM10K_PRV_FLAG_LEN, +}; + +static const char fm10k_prv_flags[FM10K_PRV_FLAG_LEN][ETH_GSTRING_LEN] = { + "debug-statistics", +}; + +static void fm10k_get_stat_strings(struct net_device *dev, u8 *data) { struct fm10k_intfc *interface = netdev_priv(dev); + struct fm10k_iov_data *iov_data = interface->iov_data; char *p = (char *)data; unsigned int i; + unsigned int j; - switch (stringset) { - case ETH_SS_TEST: - memcpy(data, *fm10k_gstrings_test, - FM10K_TEST_LEN * ETH_GSTRING_LEN); - break; - case ETH_SS_STATS: - for (i = 0; i < FM10K_NETDEV_STATS_LEN; i++) { - memcpy(p, fm10k_gstrings_net_stats[i].stat_string, + for (i = 0; i < FM10K_NETDEV_STATS_LEN; i++) { + memcpy(p, fm10k_gstrings_net_stats[i].stat_string, + ETH_GSTRING_LEN); + p += ETH_GSTRING_LEN; + } + + for (i = 0; i < FM10K_GLOBAL_STATS_LEN; i++) { + memcpy(p, fm10k_gstrings_global_stats[i].stat_string, + ETH_GSTRING_LEN); + p += ETH_GSTRING_LEN; + } + + if (interface->flags & FM10K_FLAG_DEBUG_STATS) { + for (i = 0; i < FM10K_DEBUG_STATS_LEN; i++) { + memcpy(p, fm10k_gstrings_debug_stats[i].stat_string, ETH_GSTRING_LEN); p += ETH_GSTRING_LEN; } - for (i = 0; i < FM10K_GLOBAL_STATS_LEN; i++) { - memcpy(p, fm10k_gstrings_global_stats[i].stat_string, + } + + for (i = 0; i < FM10K_MBX_STATS_LEN; i++) { + memcpy(p, fm10k_gstrings_mbx_stats[i].stat_string, + ETH_GSTRING_LEN); + p += ETH_GSTRING_LEN; + } + + if (interface->hw.mac.type != fm10k_mac_vf) { + for (i = 0; i < FM10K_PF_STATS_LEN; i++) { + memcpy(p, fm10k_gstrings_pf_stats[i].stat_string, ETH_GSTRING_LEN); p += ETH_GSTRING_LEN; } + } - if (interface->hw.mac.type != fm10k_mac_vf) { - for (i = 0; i < FM10K_PF_STATS_LEN; i++) { - memcpy(p, fm10k_gstrings_pf_stats[i].stat_string, - ETH_GSTRING_LEN); + if ((interface->flags & FM10K_FLAG_DEBUG_STATS) && iov_data) { + for (i = 0; i < iov_data->num_vfs; i++) { + for (j = 0; j < FM10K_MBX_STATS_LEN; j++) { + snprintf(p, + ETH_GSTRING_LEN, + "vf_%u_%s", i, + fm10k_gstrings_mbx_stats[j].stat_string); p += ETH_GSTRING_LEN; } } + } - for (i = 0; i < interface->hw.mac.max_queues; i++) { - sprintf(p, "tx_queue_%u_packets", i); - p += ETH_GSTRING_LEN; - sprintf(p, "tx_queue_%u_bytes", i); - p += ETH_GSTRING_LEN; - sprintf(p, "rx_queue_%u_packets", i); - p += ETH_GSTRING_LEN; - sprintf(p, "rx_queue_%u_bytes", i); - p += ETH_GSTRING_LEN; - } + for (i = 0; i < interface->hw.mac.max_queues; i++) { + sprintf(p, "tx_queue_%u_packets", i); + p += ETH_GSTRING_LEN; + sprintf(p, "tx_queue_%u_bytes", i); + p += ETH_GSTRING_LEN; + sprintf(p, "rx_queue_%u_packets", i); + p += ETH_GSTRING_LEN; + sprintf(p, "rx_queue_%u_bytes", i); + p += ETH_GSTRING_LEN; + } +} + +static void fm10k_get_strings(struct net_device *dev, + u32 stringset, u8 *data) +{ + char *p = (char *)data; + + switch (stringset) { + case ETH_SS_TEST: + memcpy(data, *fm10k_gstrings_test, + FM10K_TEST_LEN * ETH_GSTRING_LEN); + break; + case ETH_SS_STATS: + fm10k_get_stat_strings(dev, data); + break; + case ETH_SS_PRIV_FLAGS: + memcpy(p, fm10k_prv_flags, + FM10K_PRV_FLAG_LEN * ETH_GSTRING_LEN); break; } } @@ -168,6 +240,7 @@ static void fm10k_get_strings(struct net_device *dev, u32 stringset, u8 *data) static int fm10k_get_sset_count(struct net_device *dev, int sset) { struct fm10k_intfc *interface = netdev_priv(dev); + struct fm10k_iov_data *iov_data = interface->iov_data; struct fm10k_hw *hw = &interface->hw; int stats_len = FM10K_STATIC_STATS_LEN; @@ -180,7 +253,16 @@ static int fm10k_get_sset_count(struct net_device *dev, int sset) if (hw->mac.type != fm10k_mac_vf) stats_len += FM10K_PF_STATS_LEN; + if (interface->flags & FM10K_FLAG_DEBUG_STATS) { + stats_len += FM10K_DEBUG_STATS_LEN; + + if (iov_data) + stats_len += FM10K_MBX_STATS_LEN * iov_data->num_vfs; + } + return stats_len; + case ETH_SS_PRIV_FLAGS: + return FM10K_PRV_FLAG_LEN; default: return -EOPNOTSUPP; } @@ -192,6 +274,7 @@ static void fm10k_get_ethtool_stats(struct net_device *netdev, { const int stat_count = sizeof(struct fm10k_queue_stats) / sizeof(u64); struct fm10k_intfc *interface = netdev_priv(netdev); + struct fm10k_iov_data *iov_data = interface->iov_data; struct net_device_stats *net_stats = &netdev->stats; char *p; int i, j; @@ -211,13 +294,47 @@ static void fm10k_get_ethtool_stats(struct net_device *netdev, sizeof(u64)) ? *(u64 *)p : *(u32 *)p; } - if (interface->hw.mac.type != fm10k_mac_vf) + if (interface->flags & FM10K_FLAG_DEBUG_STATS) { + for (i = 0; i < FM10K_DEBUG_STATS_LEN; i++) { + p = (char *)interface + fm10k_gstrings_debug_stats[i].stat_offset; + *(data++) = (fm10k_gstrings_debug_stats[i].sizeof_stat == + sizeof(u64)) ? *(u64 *)p : *(u32 *)p; + } + } + + for (i = 0; i < FM10K_MBX_STATS_LEN; i++) { + p = (char *)&interface->hw.mbx + fm10k_gstrings_mbx_stats[i].stat_offset; + *(data++) = (fm10k_gstrings_mbx_stats[i].sizeof_stat == + sizeof(u64)) ? *(u64 *)p : *(u32 *)p; + } + + if (interface->hw.mac.type != fm10k_mac_vf) { for (i = 0; i < FM10K_PF_STATS_LEN; i++) { p = (char *)interface + fm10k_gstrings_pf_stats[i].stat_offset; *(data++) = (fm10k_gstrings_pf_stats[i].sizeof_stat == sizeof(u64)) ? *(u64 *)p : *(u32 *)p; } + } + + if ((interface->flags & FM10K_FLAG_DEBUG_STATS) && iov_data) { + for (i = 0; i < iov_data->num_vfs; i++) { + struct fm10k_vf_info *vf_info; + vf_info = &iov_data->vf_info[i]; + + /* skip stats if we don't have a vf info */ + if (!vf_info) { + data += FM10K_MBX_STATS_LEN; + continue; + } + + for (j = 0; j < FM10K_MBX_STATS_LEN; j++) { + p = (char *)&vf_info->mbx + fm10k_gstrings_mbx_stats[j].stat_offset; + *(data++) = (fm10k_gstrings_mbx_stats[j].sizeof_stat == + sizeof(u64)) ? *(u64 *)p : *(u32 *)p; + } + } + } for (i = 0; i < interface->hw.mac.max_queues; i++) { struct fm10k_ring *ring; @@ -881,6 +998,33 @@ static void fm10k_self_test(struct net_device *dev, eth_test->flags |= ETH_TEST_FL_FAILED; } +static u32 fm10k_get_priv_flags(struct net_device *netdev) +{ + struct fm10k_intfc *interface = netdev_priv(netdev); + u32 priv_flags = 0; + + if (interface->flags & FM10K_FLAG_DEBUG_STATS) + priv_flags |= 1 << FM10K_PRV_FLAG_DEBUG_STATS; + + return priv_flags; +} + +static int fm10k_set_priv_flags(struct net_device *netdev, u32 priv_flags) +{ + struct fm10k_intfc *interface = netdev_priv(netdev); + + if (priv_flags >= (1 << FM10K_PRV_FLAG_LEN)) + return -EINVAL; + + if (priv_flags & (1 << FM10K_PRV_FLAG_DEBUG_STATS)) + interface->flags |= FM10K_FLAG_DEBUG_STATS; + else + interface->flags &= ~FM10K_FLAG_DEBUG_STATS; + + return 0; +} + + static u32 fm10k_get_reta_size(struct net_device __always_unused *netdev) { return FM10K_RETA_SIZE * FM10K_RETA_ENTRIES_PER_REG; @@ -1094,6 +1238,8 @@ static const struct ethtool_ops fm10k_ethtool_ops = { .get_regs = fm10k_get_regs, .get_regs_len = fm10k_get_regs_len, .self_test = fm10k_self_test, + .get_priv_flags = fm10k_get_priv_flags, + .set_priv_flags = fm10k_set_priv_flags, .get_rxfh_indir_size = fm10k_get_reta_size, .get_rxfh_key_size = fm10k_get_rssrk_size, .get_rxfh = fm10k_get_rssh, diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c index 94571e6e790c..acfb8b1f88a7 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c @@ -137,8 +137,11 @@ process_mbx: } /* guarantee we have free space in the SM mailbox */ - if (!hw->mbx.ops.tx_ready(&hw->mbx, FM10K_VFMBX_MSG_MTU)) + if (!hw->mbx.ops.tx_ready(&hw->mbx, FM10K_VFMBX_MSG_MTU)) { + /* keep track of how many times this occurs */ + interface->hw_sm_mbx_full++; break; + } /* cleanup mailbox and process received messages */ mbx->ops.process(hw, mbx); @@ -228,9 +231,6 @@ int fm10k_iov_resume(struct pci_dev *pdev) hw->iov.ops.set_lport(hw, vf_info, i, FM10K_VF_FLAG_MULTI_CAPABLE); - /* assign our default vid to the VF following reset */ - vf_info->sw_vid = hw->mac.default_vid; - /* mailbox is disconnected so we don't send a message */ hw->iov.ops.assign_default_mac_vlan(hw, vf_info); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index b5b2925103ec..2f47bfe6cc90 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -398,6 +398,8 @@ static inline void fm10k_rx_checksum(struct fm10k_ring *ring, return; skb->ip_summed = CHECKSUM_UNNECESSARY; + + ring->rx_stats.csum_good++; } #define FM10K_RSS_L4_TYPES_MASK \ @@ -497,8 +499,11 @@ static unsigned int fm10k_process_skb_fields(struct fm10k_ring *rx_ring, if (rx_desc->w.vlan) { u16 vid = le16_to_cpu(rx_desc->w.vlan); - if (vid != rx_ring->vid) + if ((vid & VLAN_VID_MASK) != rx_ring->vid) __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vid); + else if (vid & VLAN_PRIO_MASK) + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), + vid & VLAN_PRIO_MASK); } fm10k_type_trans(rx_ring, rx_desc, skb); @@ -553,6 +558,18 @@ static bool fm10k_cleanup_headers(struct fm10k_ring *rx_ring, { if (unlikely((fm10k_test_staterr(rx_desc, FM10K_RXD_STATUS_RXE)))) { +#define FM10K_TEST_RXD_BIT(rxd, bit) \ + ((rxd)->w.csum_err & cpu_to_le16(bit)) + if (FM10K_TEST_RXD_BIT(rx_desc, FM10K_RXD_ERR_SWITCH_ERROR)) + rx_ring->rx_stats.switch_errors++; + if (FM10K_TEST_RXD_BIT(rx_desc, FM10K_RXD_ERR_NO_DESCRIPTOR)) + rx_ring->rx_stats.drops++; + if (FM10K_TEST_RXD_BIT(rx_desc, FM10K_RXD_ERR_PP_ERROR)) + rx_ring->rx_stats.pp_errors++; + if (FM10K_TEST_RXD_BIT(rx_desc, FM10K_RXD_ERR_SWITCH_READY)) + rx_ring->rx_stats.link_errors++; + if (FM10K_TEST_RXD_BIT(rx_desc, FM10K_RXD_ERR_TOO_BIG)) + rx_ring->rx_stats.length_errors++; dev_kfree_skb_any(skb); rx_ring->rx_stats.errors++; return true; @@ -878,6 +895,7 @@ static void fm10k_tx_csum(struct fm10k_ring *tx_ring, /* update TX checksum flag */ first->tx_flags |= FM10K_TX_FLAGS_CSUM; + tx_ring->tx_stats.csum_good++; no_csum: /* populate Tx descriptor header size and mss */ @@ -1079,9 +1097,7 @@ netdev_tx_t fm10k_xmit_frame_ring(struct sk_buff *skb, struct fm10k_tx_buffer *first; int tso; u32 tx_flags = 0; -#if PAGE_SIZE > FM10K_MAX_DATA_PER_TXD unsigned short f; -#endif u16 count = TXD_USE_COUNT(skb_headlen(skb)); /* need: 1 descriptor per page * PAGE_SIZE/FM10K_MAX_DATA_PER_TXD, @@ -1089,12 +1105,9 @@ netdev_tx_t fm10k_xmit_frame_ring(struct sk_buff *skb, * + 2 desc gap to keep tail from touching head * otherwise try next time */ -#if PAGE_SIZE > FM10K_MAX_DATA_PER_TXD for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size); -#else - count += skb_shinfo(skb)->nr_frags; -#endif + if (fm10k_maybe_stop_tx(tx_ring, count + 3)) { tx_ring->tx_stats.tx_busy++; return NETDEV_TX_BUSY; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c index 1a4b52637de9..af09a1b272e6 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c @@ -129,8 +129,8 @@ static u16 fm10k_fifo_head_drop(struct fm10k_mbx_fifo *fifo) * fm10k_fifo_drop_all - Drop all messages in FIFO * @fifo: pointer to FIFO * - * This function resets the head pointer to drop all messages in the FIFO, - * and ensure the FIFO is empty. + * This function resets the head pointer to drop all messages in the FIFO and + * ensure the FIFO is empty. **/ static void fm10k_fifo_drop_all(struct fm10k_mbx_fifo *fifo) { @@ -899,6 +899,27 @@ static void fm10k_mbx_create_disconnect_hdr(struct fm10k_mbx_info *mbx) } /** + * fm10k_mbx_create_fake_disconnect_hdr - Generate a false disconnect mailbox header + * @mbx: pointer to mailbox + * + * This function creates a fake disconnect header for loading into remote + * mailbox header. The primary purpose is to prevent errors on immediate + * start up after mbx->connect. + **/ +static void fm10k_mbx_create_fake_disconnect_hdr(struct fm10k_mbx_info *mbx) +{ + u32 hdr = FM10K_MSG_HDR_FIELD_SET(FM10K_MSG_DISCONNECT, TYPE) | + FM10K_MSG_HDR_FIELD_SET(mbx->head, TAIL) | + FM10K_MSG_HDR_FIELD_SET(mbx->tail, HEAD); + u16 crc = fm10k_crc_16b(&hdr, mbx->local, 1); + + mbx->mbx_lock |= FM10K_MBX_ACK; + + /* load header to memory to be written */ + mbx->mbx_hdr = hdr | FM10K_MSG_HDR_FIELD_SET(crc, CRC); +} + +/** * fm10k_mbx_create_error_msg - Generate a error message * @mbx: pointer to mailbox * @err: local error encountered @@ -1046,9 +1067,26 @@ static s32 fm10k_mbx_create_reply(struct fm10k_hw *hw, **/ static void fm10k_mbx_reset_work(struct fm10k_mbx_info *mbx) { + u16 len, head, ack; + /* reset our outgoing max size back to Rx limits */ mbx->max_size = mbx->rx.size - 1; + /* update mbx->pulled to account for tail_len and ack */ + head = FM10K_MSG_HDR_FIELD_GET(mbx->mbx_hdr, HEAD); + ack = fm10k_mbx_index_len(mbx, head, mbx->tail); + mbx->pulled += mbx->tail_len - ack; + + /* now drop any messages which have started or finished transmitting */ + while (fm10k_fifo_head_len(&mbx->tx) && mbx->pulled) { + len = fm10k_fifo_head_drop(&mbx->tx); + mbx->tx_dropped++; + if (mbx->pulled >= len) + mbx->pulled -= len; + else + mbx->pulled = 0; + } + /* just do a quick resysnc to start of message */ mbx->pushed = 0; mbx->pulled = 0; @@ -1418,8 +1456,10 @@ static s32 fm10k_mbx_connect(struct fm10k_hw *hw, struct fm10k_mbx_info *mbx) /* Place mbx in ready to connect state */ mbx->state = FM10K_STATE_CONNECT; + fm10k_mbx_reset_work(mbx); + /* initialize header of remote mailbox */ - fm10k_mbx_create_disconnect_hdr(mbx); + fm10k_mbx_create_fake_disconnect_hdr(mbx); fm10k_write_reg(hw, mbx->mbmem_reg ^ mbx->mbmem_len, mbx->mbx_hdr); /* enable interrupt and notify other party of new message */ @@ -1725,7 +1765,7 @@ static void fm10k_sm_mbx_disconnect(struct fm10k_hw *hw, mbx->state = FM10K_STATE_CLOSED; mbx->remote = 0; fm10k_mbx_reset_work(mbx); - fm10k_mbx_update_max_size(mbx, 0); + fm10k_fifo_drop_all(&mbx->tx); fm10k_write_reg(hw, mbx->mbmem_reg, 0); } diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c index 99228bf46c12..639263d5e833 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c @@ -758,6 +758,7 @@ static int fm10k_update_vid(struct net_device *netdev, u16 vid, bool set) struct fm10k_intfc *interface = netdev_priv(netdev); struct fm10k_hw *hw = &interface->hw; s32 err; + int i; /* updates do not apply to VLAN 0 */ if (!vid) @@ -775,8 +776,25 @@ static int fm10k_update_vid(struct net_device *netdev, u16 vid, bool set) if (!set) clear_bit(vid, interface->active_vlans); - /* if default VLAN is already present do nothing */ - if (vid == hw->mac.default_vid) + /* disable the default VID on ring if we have an active VLAN */ + for (i = 0; i < interface->num_rx_queues; i++) { + struct fm10k_ring *rx_ring = interface->rx_ring[i]; + u16 rx_vid = rx_ring->vid & (VLAN_N_VID - 1); + + if (test_bit(rx_vid, interface->active_vlans)) + rx_ring->vid |= FM10K_VLAN_CLEAR; + else + rx_ring->vid &= ~FM10K_VLAN_CLEAR; + } + + /* Do not remove default VID related entries from VLAN and MAC tables */ + if (!set && vid == hw->mac.default_vid) + return 0; + + /* Do not throw an error if the interface is down. We will sync once + * we come up + */ + if (test_bit(__FM10K_DOWN, &interface->state)) return 0; fm10k_mbx_lock(interface); @@ -996,21 +1014,6 @@ void fm10k_restore_rx_state(struct fm10k_intfc *interface) int xcast_mode; u16 vid, glort; - /* restore our address if perm_addr is set */ - if (hw->mac.type == fm10k_mac_vf) { - if (is_valid_ether_addr(hw->mac.perm_addr)) { - ether_addr_copy(hw->mac.addr, hw->mac.perm_addr); - ether_addr_copy(netdev->perm_addr, hw->mac.perm_addr); - ether_addr_copy(netdev->dev_addr, hw->mac.perm_addr); - netdev->addr_assign_type &= ~NET_ADDR_RANDOM; - } - - if (hw->mac.vlan_override) - netdev->features &= ~NETIF_F_HW_VLAN_CTAG_RX; - else - netdev->features |= NETIF_F_HW_VLAN_CTAG_RX; - } - /* record glort for this interface */ glort = interface->glort; @@ -1045,7 +1048,7 @@ void fm10k_restore_rx_state(struct fm10k_intfc *interface) vid, true, 0); } - /* update xcast mode before syncronizing addresses */ + /* update xcast mode before synchronizing addresses */ hw->mac.ops.update_xcast_mode(hw, glort, xcast_mode); /* synchronize all of the addresses */ diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index ce53ff25f88d..74be792f3f1b 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -170,6 +170,21 @@ static void fm10k_reinit(struct fm10k_intfc *interface) /* reassociate interrupts */ fm10k_mbx_request_irq(interface); + /* update hardware address for VFs if perm_addr has changed */ + if (hw->mac.type == fm10k_mac_vf) { + if (is_valid_ether_addr(hw->mac.perm_addr)) { + ether_addr_copy(hw->mac.addr, hw->mac.perm_addr); + ether_addr_copy(netdev->perm_addr, hw->mac.perm_addr); + ether_addr_copy(netdev->dev_addr, hw->mac.perm_addr); + netdev->addr_assign_type &= ~NET_ADDR_RANDOM; + } + + if (hw->mac.vlan_override) + netdev->features &= ~NETIF_F_HW_VLAN_CTAG_RX; + else + netdev->features |= NETIF_F_HW_VLAN_CTAG_RX; + } + /* reset clock */ fm10k_ts_reset(interface); @@ -259,8 +274,6 @@ static void fm10k_watchdog_update_host_state(struct fm10k_intfc *interface) * @interface: board private structure * * This function will process both the upstream and downstream mailboxes. - * It is necessary for us to hold the rtnl_lock while doing this as the - * mailbox accesses are protected by this lock. **/ static void fm10k_mbx_subtask(struct fm10k_intfc *interface) { @@ -315,6 +328,9 @@ void fm10k_update_stats(struct fm10k_intfc *interface) { struct net_device_stats *net_stats = &interface->netdev->stats; struct fm10k_hw *hw = &interface->hw; + u64 hw_csum_tx_good = 0, hw_csum_rx_good = 0, rx_length_errors = 0; + u64 rx_switch_errors = 0, rx_drops = 0, rx_pp_errors = 0; + u64 rx_link_errors = 0; u64 rx_errors = 0, rx_csum_errors = 0, tx_csum_errors = 0; u64 restart_queue = 0, tx_busy = 0, alloc_failed = 0; u64 rx_bytes_nic = 0, rx_pkts_nic = 0, rx_drops_nic = 0; @@ -334,6 +350,7 @@ void fm10k_update_stats(struct fm10k_intfc *interface) tx_csum_errors += tx_ring->tx_stats.csum_err; bytes += tx_ring->stats.bytes; pkts += tx_ring->stats.packets; + hw_csum_tx_good += tx_ring->tx_stats.csum_good; } interface->restart_queue = restart_queue; @@ -341,6 +358,8 @@ void fm10k_update_stats(struct fm10k_intfc *interface) net_stats->tx_bytes = bytes; net_stats->tx_packets = pkts; interface->tx_csum_errors = tx_csum_errors; + interface->hw_csum_tx_good = hw_csum_tx_good; + /* gather some stats to the interface struct that are per queue */ for (bytes = 0, pkts = 0, i = 0; i < interface->num_rx_queues; i++) { struct fm10k_ring *rx_ring = interface->rx_ring[i]; @@ -350,12 +369,24 @@ void fm10k_update_stats(struct fm10k_intfc *interface) alloc_failed += rx_ring->rx_stats.alloc_failed; rx_csum_errors += rx_ring->rx_stats.csum_err; rx_errors += rx_ring->rx_stats.errors; + hw_csum_rx_good += rx_ring->rx_stats.csum_good; + rx_switch_errors += rx_ring->rx_stats.switch_errors; + rx_drops += rx_ring->rx_stats.drops; + rx_pp_errors += rx_ring->rx_stats.pp_errors; + rx_link_errors += rx_ring->rx_stats.link_errors; + rx_length_errors += rx_ring->rx_stats.length_errors; } net_stats->rx_bytes = bytes; net_stats->rx_packets = pkts; interface->alloc_failed = alloc_failed; interface->rx_csum_errors = rx_csum_errors; + interface->hw_csum_rx_good = hw_csum_rx_good; + interface->rx_switch_errors = rx_switch_errors; + interface->rx_drops = rx_drops; + interface->rx_pp_errors = rx_pp_errors; + interface->rx_link_errors = rx_link_errors; + interface->rx_length_errors = rx_length_errors; hw->mac.ops.update_hw_stats(hw, &interface->stats); @@ -483,7 +514,7 @@ static void fm10k_service_task(struct work_struct *work) interface = container_of(work, struct fm10k_intfc, service_task); - /* tasks always capable of running, but must be rtnl protected */ + /* tasks run even when interface is down */ fm10k_mbx_subtask(interface); fm10k_detach_subtask(interface); fm10k_reset_subtask(interface); @@ -663,6 +694,10 @@ static void fm10k_configure_rx_ring(struct fm10k_intfc *interface, /* assign default VLAN to queue */ ring->vid = hw->mac.default_vid; + /* if we have an active VLAN, disable default VID */ + if (test_bit(hw->mac.default_vid, interface->active_vlans)) + ring->vid |= FM10K_VLAN_CLEAR; + /* Map interrupt */ if (ring->q_vector) { rxint = ring->q_vector->v_idx + NON_Q_VECTORS(hw); @@ -861,10 +896,12 @@ void fm10k_netpoll(struct net_device *netdev) #endif #define FM10K_ERR_MSG(type) case (type): error = #type; break -static void fm10k_print_fault(struct fm10k_intfc *interface, int type, +static void fm10k_handle_fault(struct fm10k_intfc *interface, int type, struct fm10k_fault *fault) { struct pci_dev *pdev = interface->pdev; + struct fm10k_hw *hw = &interface->hw; + struct fm10k_iov_data *iov_data = interface->iov_data; char *error; switch (type) { @@ -918,6 +955,30 @@ static void fm10k_print_fault(struct fm10k_intfc *interface, int type, "%s Address: 0x%llx SpecInfo: 0x%x Func: %02x.%0x\n", error, fault->address, fault->specinfo, PCI_SLOT(fault->func), PCI_FUNC(fault->func)); + + /* For VF faults, clear out the respective LPORT, reset the queue + * resources, and then reconnect to the mailbox. This allows the + * VF in question to resume behavior. For transient faults that are + * the result of non-malicious behavior this will log the fault and + * allow the VF to resume functionality. Obviously for malicious VFs + * they will be able to attempt malicious behavior again. In this + * case, the system administrator will need to step in and manually + * remove or disable the VF in question. + */ + if (fault->func && iov_data) { + int vf = fault->func - 1; + struct fm10k_vf_info *vf_info = &iov_data->vf_info[vf]; + + hw->iov.ops.reset_lport(hw, vf_info); + hw->iov.ops.reset_resources(hw, vf_info); + + /* reset_lport disables the VF, so re-enable it */ + hw->iov.ops.set_lport(hw, vf_info, vf, + FM10K_VF_FLAG_MULTI_CAPABLE); + + /* reset_resources will disconnect from the mbx */ + vf_info->mbx.ops.connect(hw, &vf_info->mbx); + } } static void fm10k_report_fault(struct fm10k_intfc *interface, u32 eicr) @@ -941,7 +1002,7 @@ static void fm10k_report_fault(struct fm10k_intfc *interface, u32 eicr) continue; } - fm10k_print_fault(interface, type, &fault); + fm10k_handle_fault(interface, type, &fault); } } @@ -1705,22 +1766,86 @@ static int fm10k_sw_init(struct fm10k_intfc *interface, static void fm10k_slot_warn(struct fm10k_intfc *interface) { - struct device *dev = &interface->pdev->dev; + enum pcie_link_width width = PCIE_LNK_WIDTH_UNKNOWN; + enum pci_bus_speed speed = PCI_SPEED_UNKNOWN; struct fm10k_hw *hw = &interface->hw; + int max_gts = 0, expected_gts = 0; + + if (pcie_get_minimum_link(interface->pdev, &speed, &width) || + speed == PCI_SPEED_UNKNOWN || width == PCIE_LNK_WIDTH_UNKNOWN) { + dev_warn(&interface->pdev->dev, + "Unable to determine PCI Express bandwidth.\n"); + return; + } + + switch (speed) { + case PCIE_SPEED_2_5GT: + /* 8b/10b encoding reduces max throughput by 20% */ + max_gts = 2 * width; + break; + case PCIE_SPEED_5_0GT: + /* 8b/10b encoding reduces max throughput by 20% */ + max_gts = 4 * width; + break; + case PCIE_SPEED_8_0GT: + /* 128b/130b encoding has less than 2% impact on throughput */ + max_gts = 8 * width; + break; + default: + dev_warn(&interface->pdev->dev, + "Unable to determine PCI Express bandwidth.\n"); + return; + } + + dev_info(&interface->pdev->dev, + "PCI Express bandwidth of %dGT/s available\n", + max_gts); + dev_info(&interface->pdev->dev, + "(Speed:%s, Width: x%d, Encoding Loss:%s, Payload:%s)\n", + (speed == PCIE_SPEED_8_0GT ? "8.0GT/s" : + speed == PCIE_SPEED_5_0GT ? "5.0GT/s" : + speed == PCIE_SPEED_2_5GT ? "2.5GT/s" : + "Unknown"), + hw->bus.width, + (speed == PCIE_SPEED_2_5GT ? "20%" : + speed == PCIE_SPEED_5_0GT ? "20%" : + speed == PCIE_SPEED_8_0GT ? "<2%" : + "Unknown"), + (hw->bus.payload == fm10k_bus_payload_128 ? "128B" : + hw->bus.payload == fm10k_bus_payload_256 ? "256B" : + hw->bus.payload == fm10k_bus_payload_512 ? "512B" : + "Unknown")); - if (hw->mac.ops.is_slot_appropriate(hw)) + switch (hw->bus_caps.speed) { + case fm10k_bus_speed_2500: + /* 8b/10b encoding reduces max throughput by 20% */ + expected_gts = 2 * hw->bus_caps.width; + break; + case fm10k_bus_speed_5000: + /* 8b/10b encoding reduces max throughput by 20% */ + expected_gts = 4 * hw->bus_caps.width; + break; + case fm10k_bus_speed_8000: + /* 128b/130b encoding has less than 2% impact on throughput */ + expected_gts = 8 * hw->bus_caps.width; + break; + default: + dev_warn(&interface->pdev->dev, + "Unable to determine expected PCI Express bandwidth.\n"); return; + } - dev_warn(dev, - "For optimal performance, a %s %s slot is recommended.\n", - (hw->bus_caps.width == fm10k_bus_width_pcie_x1 ? "x1" : - hw->bus_caps.width == fm10k_bus_width_pcie_x4 ? "x4" : - "x8"), - (hw->bus_caps.speed == fm10k_bus_speed_2500 ? "2.5GT/s" : - hw->bus_caps.speed == fm10k_bus_speed_5000 ? "5.0GT/s" : - "8.0GT/s")); - dev_warn(dev, - "A slot with more lanes and/or higher speed is suggested.\n"); + if (max_gts < expected_gts) { + dev_warn(&interface->pdev->dev, + "This device requires %dGT/s of bandwidth for optimal performance.\n", + expected_gts); + dev_warn(&interface->pdev->dev, + "A %sslot with x%d lanes is suggested.\n", + (hw->bus_caps.speed == fm10k_bus_speed_2500 ? "2.5GT/s " : + hw->bus_caps.speed == fm10k_bus_speed_5000 ? "5.0GT/s " : + hw->bus_caps.speed == fm10k_bus_speed_8000 ? "8.0GT/s " : ""), + hw->bus_caps.width); + } } /** @@ -1739,7 +1864,6 @@ static int fm10k_probe(struct pci_dev *pdev, { struct net_device *netdev; struct fm10k_intfc *interface; - struct fm10k_hw *hw; int err; err = pci_enable_device_mem(pdev); @@ -1783,7 +1907,6 @@ static int fm10k_probe(struct pci_dev *pdev, interface->netdev = netdev; interface->pdev = pdev; - hw = &interface->hw; interface->uc_addr = ioremap(pci_resource_start(pdev, 0), FM10K_UC_ADDR_SIZE); @@ -1825,24 +1948,12 @@ static int fm10k_probe(struct pci_dev *pdev, /* Register PTP interface */ fm10k_ptp_register(interface); - /* print bus type/speed/width info */ - dev_info(&pdev->dev, "(PCI Express:%s Width: %s Payload: %s)\n", - (hw->bus.speed == fm10k_bus_speed_8000 ? "8.0GT/s" : - hw->bus.speed == fm10k_bus_speed_5000 ? "5.0GT/s" : - hw->bus.speed == fm10k_bus_speed_2500 ? "2.5GT/s" : - "Unknown"), - (hw->bus.width == fm10k_bus_width_pcie_x8 ? "x8" : - hw->bus.width == fm10k_bus_width_pcie_x4 ? "x4" : - hw->bus.width == fm10k_bus_width_pcie_x1 ? "x1" : - "Unknown"), - (hw->bus.payload == fm10k_bus_payload_128 ? "128B" : - hw->bus.payload == fm10k_bus_payload_256 ? "256B" : - hw->bus.payload == fm10k_bus_payload_512 ? "512B" : - "Unknown")); - /* print warning for non-optimal configurations */ fm10k_slot_warn(interface); + /* report MAC address for logging */ + dev_info(&pdev->dev, "%pM\n", netdev->dev_addr); + /* enable SR-IOV after registering netdev to enforce PF/VF ordering */ fm10k_iov_configure(pdev, 0); @@ -1983,6 +2094,16 @@ static int fm10k_resume(struct pci_dev *pdev) if (err) return err; + /* assume host is not ready, to prevent race with watchdog in case we + * actually don't have connection to the switch + */ + interface->host_ready = false; + fm10k_watchdog_host_not_ready(interface); + + /* clear the service task disable bit to allow service task to start */ + clear_bit(__FM10K_SERVICE_DISABLE, &interface->state); + fm10k_service_event_schedule(interface); + /* restore SR-IOV interface */ fm10k_iov_resume(pdev); @@ -2010,6 +2131,15 @@ static int fm10k_suspend(struct pci_dev *pdev, fm10k_iov_suspend(pdev); + /* the watchdog tasks may read registers, which will appear like a + * surprise-remove event once the PCI device is disabled. This will + * cause us to close the netdevice, so we don't retain the open/closed + * state post-resume. Prevent this by disabling the service task while + * suspended, until we actually resume. + */ + set_bit(__FM10K_SERVICE_DISABLE, &interface->state); + cancel_work_sync(&interface->service_task); + rtnl_lock(); if (netif_running(netdev)) diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c index 3ca0233b3ea2..8c0bdc4e4edd 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c @@ -59,6 +59,11 @@ static s32 fm10k_reset_hw_pf(struct fm10k_hw *hw) if (reg & (FM10K_DMA_CTRL_TX_ACTIVE | FM10K_DMA_CTRL_RX_ACTIVE)) return FM10K_ERR_DMA_PENDING; + /* verify the switch is ready for reset */ + reg = fm10k_read_reg(hw, FM10K_DMA_CTRL2); + if (!(reg & FM10K_DMA_CTRL2_SWITCH_READY)) + goto out; + /* Inititate data path reset */ reg |= FM10K_DMA_CTRL_DATAPATH_RESET; fm10k_write_reg(hw, FM10K_DMA_CTRL, reg); @@ -72,6 +77,7 @@ static s32 fm10k_reset_hw_pf(struct fm10k_hw *hw) if (!(reg & FM10K_IP_NOTINRESET)) err = FM10K_ERR_RESET_FAILED; +out: return err; } @@ -185,19 +191,6 @@ static s32 fm10k_init_hw_pf(struct fm10k_hw *hw) } /** - * fm10k_is_slot_appropriate_pf - Indicate appropriate slot for this SKU - * @hw: pointer to hardware structure - * - * Looks at the PCIe bus info to confirm whether or not this slot can support - * the necessary bandwidth for this device. - **/ -static bool fm10k_is_slot_appropriate_pf(struct fm10k_hw *hw) -{ - return (hw->bus.speed == hw->bus_caps.speed) && - (hw->bus.width == hw->bus_caps.width); -} - -/** * fm10k_update_vlan_pf - Update status of VLAN ID in VLAN filter table * @hw: pointer to hardware structure * @vid: VLAN ID to add to table @@ -1162,6 +1155,24 @@ s32 fm10k_iov_msg_msix_pf(struct fm10k_hw *hw, u32 **results, } /** + * fm10k_iov_select_vid - Select correct default VID + * @hw: Pointer to hardware structure + * @vid: VID to correct + * + * Will report an error if VID is out of range. For VID = 0, it will return + * either the pf_vid or sw_vid depending on which one is set. + */ +static inline s32 fm10k_iov_select_vid(struct fm10k_vf_info *vf_info, u16 vid) +{ + if (!vid) + return vf_info->pf_vid ? vf_info->pf_vid : vf_info->sw_vid; + else if (vf_info->pf_vid && vid != vf_info->pf_vid) + return FM10K_ERR_PARAM; + else + return vid; +} + +/** * fm10k_iov_msg_mac_vlan_pf - Message handler for MAC/VLAN request from VF * @hw: Pointer to hardware structure * @results: Pointer array to message, results[0] is pointer to message @@ -1175,9 +1186,10 @@ s32 fm10k_iov_msg_mac_vlan_pf(struct fm10k_hw *hw, u32 **results, struct fm10k_mbx_info *mbx) { struct fm10k_vf_info *vf_info = (struct fm10k_vf_info *)mbx; - int err = 0; u8 mac[ETH_ALEN]; u32 *result; + int err = 0; + bool set; u16 vlan; u32 vid; @@ -1193,19 +1205,21 @@ s32 fm10k_iov_msg_mac_vlan_pf(struct fm10k_hw *hw, u32 **results, if (err) return err; - /* if VLAN ID is 0, set the default VLAN ID instead of 0 */ - if (!vid || (vid == FM10K_VLAN_CLEAR)) { - if (vf_info->pf_vid) - vid |= vf_info->pf_vid; - else - vid |= vf_info->sw_vid; - } else if (vid != vf_info->pf_vid) { + /* verify upper 16 bits are zero */ + if (vid >> 16) return FM10K_ERR_PARAM; - } + + set = !(vid & FM10K_VLAN_CLEAR); + vid &= ~FM10K_VLAN_CLEAR; + + err = fm10k_iov_select_vid(vf_info, vid); + if (err < 0) + return err; + else + vid = err; /* update VSI info for VF in regards to VLAN table */ - err = hw->mac.ops.update_vlan(hw, vid, vf_info->vsi, - !(vid & FM10K_VLAN_CLEAR)); + err = hw->mac.ops.update_vlan(hw, vid, vf_info->vsi, set); } if (!err && !!results[FM10K_MAC_VLAN_MSG_MAC]) { @@ -1221,19 +1235,18 @@ s32 fm10k_iov_msg_mac_vlan_pf(struct fm10k_hw *hw, u32 **results, memcmp(mac, vf_info->mac, ETH_ALEN)) return FM10K_ERR_PARAM; - /* if VLAN ID is 0, set the default VLAN ID instead of 0 */ - if (!vlan || (vlan == FM10K_VLAN_CLEAR)) { - if (vf_info->pf_vid) - vlan |= vf_info->pf_vid; - else - vlan |= vf_info->sw_vid; - } else if (vf_info->pf_vid) { - return FM10K_ERR_PARAM; - } + set = !(vlan & FM10K_VLAN_CLEAR); + vlan &= ~FM10K_VLAN_CLEAR; + + err = fm10k_iov_select_vid(vf_info, vlan); + if (err < 0) + return err; + else + vlan = err; /* notify switch of request for new unicast address */ - err = hw->mac.ops.update_uc_addr(hw, vf_info->glort, mac, vlan, - !(vlan & FM10K_VLAN_CLEAR), 0); + err = hw->mac.ops.update_uc_addr(hw, vf_info->glort, + mac, vlan, set, 0); } if (!err && !!results[FM10K_MAC_VLAN_MSG_MULTICAST]) { @@ -1248,19 +1261,18 @@ s32 fm10k_iov_msg_mac_vlan_pf(struct fm10k_hw *hw, u32 **results, if (!(vf_info->vf_flags & FM10K_VF_FLAG_MULTI_ENABLED)) return FM10K_ERR_PARAM; - /* if VLAN ID is 0, set the default VLAN ID instead of 0 */ - if (!vlan || (vlan == FM10K_VLAN_CLEAR)) { - if (vf_info->pf_vid) - vlan |= vf_info->pf_vid; - else - vlan |= vf_info->sw_vid; - } else if (vf_info->pf_vid) { - return FM10K_ERR_PARAM; - } + set = !(vlan & FM10K_VLAN_CLEAR); + vlan &= ~FM10K_VLAN_CLEAR; + + err = fm10k_iov_select_vid(vf_info, vlan); + if (err < 0) + return err; + else + vlan = err; /* notify switch of request for new multicast address */ - err = hw->mac.ops.update_mc_addr(hw, vf_info->glort, mac, vlan, - !(vlan & FM10K_VLAN_CLEAR)); + err = hw->mac.ops.update_mc_addr(hw, vf_info->glort, + mac, vlan, set); } return err; @@ -1849,7 +1861,6 @@ static struct fm10k_mac_ops mac_ops_pf = { .init_hw = &fm10k_init_hw_pf, .start_hw = &fm10k_start_hw_generic, .stop_hw = &fm10k_stop_hw_generic, - .is_slot_appropriate = &fm10k_is_slot_appropriate_pf, .update_vlan = &fm10k_update_vlan_pf, .read_mac_addr = &fm10k_read_mac_addr_pf, .update_uc_addr = &fm10k_update_uc_addr_pf, diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_type.h b/drivers/net/ethernet/intel/fm10k/fm10k_type.h index 2a17d82fa37d..318a212f0a78 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_type.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k_type.h @@ -521,7 +521,6 @@ struct fm10k_mac_ops { s32 (*stop_hw)(struct fm10k_hw *); s32 (*get_bus_info)(struct fm10k_hw *); s32 (*get_host_state)(struct fm10k_hw *, bool *); - bool (*is_slot_appropriate)(struct fm10k_hw *); s32 (*update_vlan)(struct fm10k_hw *, u32, u8, bool); s32 (*read_mac_addr)(struct fm10k_hw *); s32 (*update_uc_addr)(struct fm10k_hw *, u16, const u8 *, @@ -763,6 +762,12 @@ enum fm10k_rxdesc_xc { #define FM10K_RXD_STATUS_L4E 0x4000 /* L4 csum error */ #define FM10K_RXD_STATUS_IPE 0x8000 /* IPv4 csum error */ +#define FM10K_RXD_ERR_SWITCH_ERROR 0x0001 /* Switch found bad packet */ +#define FM10K_RXD_ERR_NO_DESCRIPTOR 0x0002 /* No descriptor available */ +#define FM10K_RXD_ERR_PP_ERROR 0x0004 /* RAM error during processing */ +#define FM10K_RXD_ERR_SWITCH_READY 0x0008 /* Link transition mid-packet */ +#define FM10K_RXD_ERR_TOO_BIG 0x0010 /* Pkt too big for single buf */ + struct fm10k_ftag { __be16 swpri_type_user; __be16 vlan; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_vf.c b/drivers/net/ethernet/intel/fm10k/fm10k_vf.c index 94f0f6a146d9..36c8b0aa08fd 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_vf.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_vf.c @@ -131,19 +131,6 @@ static s32 fm10k_init_hw_vf(struct fm10k_hw *hw) return 0; } -/** - * fm10k_is_slot_appropriate_vf - Indicate appropriate slot for this SKU - * @hw: pointer to hardware structure - * - * Looks at the PCIe bus info to confirm whether or not this slot can support - * the necessary bandwidth for this device. Since the VF has no control over - * the "slot" it is in, always indicate that the slot is appropriate. - **/ -static bool fm10k_is_slot_appropriate_vf(struct fm10k_hw *hw) -{ - return true; -} - /* This structure defines the attibutes to be parsed below */ const struct fm10k_tlv_attr fm10k_mac_vlan_msg_attr[] = { FM10K_TLV_ATTR_U32(FM10K_MAC_VLAN_MSG_VLAN), @@ -552,7 +539,6 @@ static struct fm10k_mac_ops mac_ops_vf = { .init_hw = &fm10k_init_hw_vf, .start_hw = &fm10k_start_hw_generic, .stop_hw = &fm10k_stop_hw_vf, - .is_slot_appropriate = &fm10k_is_slot_appropriate_vf, .update_vlan = &fm10k_update_vlan_vf, .read_mac_addr = &fm10k_read_mac_addr_vf, .update_uc_addr = &fm10k_update_uc_addr_vf, diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index e7462793d48d..c64d18d4cb2d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -243,7 +243,6 @@ struct i40e_pf { struct pci_dev *pdev; struct i40e_hw hw; unsigned long state; - unsigned long link_check_timeout; struct msix_entry *msix_entries; bool fc_autoneg_status; @@ -667,7 +666,7 @@ struct i40e_mac_filter *i40e_add_filter(struct i40e_vsi *vsi, bool is_vf, bool is_netdev); void i40e_del_filter(struct i40e_vsi *vsi, u8 *macaddr, s16 vlan, bool is_vf, bool is_netdev); -int i40e_sync_vsi_filters(struct i40e_vsi *vsi); +int i40e_sync_vsi_filters(struct i40e_vsi *vsi, bool grab_rtnl); struct i40e_vsi *i40e_vsi_setup(struct i40e_pf *pf, u8 type, u16 uplink, u32 param1); int i40e_vsi_release(struct i40e_vsi *vsi); diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c index 62488a67149d..e59ffb2e7b4c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c @@ -657,6 +657,9 @@ i40e_status i40e_shutdown_adminq(struct i40e_hw *hw) /* destroy the locks */ + if (hw->nvm_buff.va) + i40e_free_virt_mem(hw, &hw->nvm_buff); + return ret_code; } @@ -889,6 +892,10 @@ i40e_status i40e_asq_send_command(struct i40e_hw *hw, "AQTX: desc and buffer writeback:\n"); i40e_debug_aq(hw, I40E_DEBUG_AQ_COMMAND, (void *)desc, buff, buff_size); + /* save writeback aq if requested */ + if (details->wb_desc) + *details->wb_desc = *desc_on_ring; + /* update the error if time out occurred */ if ((!cmd_completed) && (!details->async && !details->postpone)) { @@ -1023,6 +1030,19 @@ clean_arq_element_err: i40e_release_nvm(hw); hw->aq.nvm_release_on_done = false; } + + switch (hw->nvmupd_state) { + case I40E_NVMUPD_STATE_INIT_WAIT: + hw->nvmupd_state = I40E_NVMUPD_STATE_INIT; + break; + + case I40E_NVMUPD_STATE_WRITE_WAIT: + hw->nvmupd_state = I40E_NVMUPD_STATE_WRITING; + break; + + default: + break; + } } return ret_code; diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.h b/drivers/net/ethernet/intel/i40e/i40e_adminq.h index 28e519a50de4..b67b34c35533 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.h @@ -69,6 +69,7 @@ struct i40e_asq_cmd_details { u16 flags_dis; bool async; bool postpone; + struct i40e_aq_desc *wb_desc; }; #define I40E_ADMINQ_DETAILS(R, i) \ diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index d7c15d17faa6..508efb034e87 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -1146,7 +1146,7 @@ static ssize_t i40e_dbg_command_write(struct file *filp, } f = i40e_add_filter(vsi, ma, vlan, false, false); - ret = i40e_sync_vsi_filters(vsi); + ret = i40e_sync_vsi_filters(vsi, true); if (f && !ret) dev_info(&pf->pdev->dev, "add macaddr: %pM vlan=%d added to VSI %d\n", @@ -1183,7 +1183,7 @@ static ssize_t i40e_dbg_command_write(struct file *filp, } i40e_del_filter(vsi, ma, vlan, false, false); - ret = i40e_sync_vsi_filters(vsi); + ret = i40e_sync_vsi_filters(vsi, true); if (!ret) dev_info(&pf->pdev->dev, "del macaddr: %pM vlan=%d removed from VSI %d\n", diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 2fdf978ae6a5..efd5335631d8 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -39,7 +39,7 @@ static const char i40e_driver_string[] = #define DRV_VERSION_MAJOR 1 #define DRV_VERSION_MINOR 3 -#define DRV_VERSION_BUILD 9 +#define DRV_VERSION_BUILD 21 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \ __stringify(DRV_VERSION_MINOR) "." \ __stringify(DRV_VERSION_BUILD) DRV_KERN @@ -299,25 +299,69 @@ static void i40e_tx_timeout(struct net_device *netdev) struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; + struct i40e_ring *tx_ring = NULL; + unsigned int i, hung_queue = 0; + u32 head, val; pf->tx_timeout_count++; + /* find the stopped queue the same way the stack does */ + for (i = 0; i < netdev->num_tx_queues; i++) { + struct netdev_queue *q; + unsigned long trans_start; + + q = netdev_get_tx_queue(netdev, i); + trans_start = q->trans_start ? : netdev->trans_start; + if (netif_xmit_stopped(q) && + time_after(jiffies, + (trans_start + netdev->watchdog_timeo))) { + hung_queue = i; + break; + } + } + + if (i == netdev->num_tx_queues) { + netdev_info(netdev, "tx_timeout: no netdev hung queue found\n"); + } else { + /* now that we have an index, find the tx_ring struct */ + for (i = 0; i < vsi->num_queue_pairs; i++) { + if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc) { + if (hung_queue == + vsi->tx_rings[i]->queue_index) { + tx_ring = vsi->tx_rings[i]; + break; + } + } + } + } + if (time_after(jiffies, (pf->tx_timeout_last_recovery + HZ*20))) - pf->tx_timeout_recovery_level = 1; + pf->tx_timeout_recovery_level = 1; /* reset after some time */ + else if (time_before(jiffies, + (pf->tx_timeout_last_recovery + netdev->watchdog_timeo))) + return; /* don't do any new action before the next timeout */ + + if (tx_ring) { + head = i40e_get_head(tx_ring); + /* Read interrupt register */ + if (pf->flags & I40E_FLAG_MSIX_ENABLED) + val = rd32(&pf->hw, + I40E_PFINT_DYN_CTLN(tx_ring->q_vector->v_idx + + tx_ring->vsi->base_vector - 1)); + else + val = rd32(&pf->hw, I40E_PFINT_DYN_CTL0); + + netdev_info(netdev, "tx_timeout: VSI_seid: %d, Q %d, NTC: 0x%x, HWB: 0x%x, NTU: 0x%x, TAIL: 0x%x, INT: 0x%x\n", + vsi->seid, hung_queue, tx_ring->next_to_clean, + head, tx_ring->next_to_use, + readl(tx_ring->tail), val); + } + pf->tx_timeout_last_recovery = jiffies; - netdev_info(netdev, "tx_timeout recovery level %d\n", - pf->tx_timeout_recovery_level); + netdev_info(netdev, "tx_timeout recovery level %d, hung_queue %d\n", + pf->tx_timeout_recovery_level, hung_queue); switch (pf->tx_timeout_recovery_level) { - case 0: - /* disable and re-enable queues for the VSI */ - if (in_interrupt()) { - set_bit(__I40E_REINIT_REQUESTED, &pf->state); - set_bit(__I40E_REINIT_REQUESTED, &vsi->state); - } else { - i40e_vsi_reinit_locked(vsi); - } - break; case 1: set_bit(__I40E_PF_RESET_REQUESTED, &pf->state); break; @@ -329,10 +373,9 @@ static void i40e_tx_timeout(struct net_device *netdev) break; default: netdev_err(netdev, "tx_timeout recovery unsuccessful\n"); - set_bit(__I40E_DOWN_REQUESTED, &pf->state); - set_bit(__I40E_DOWN_REQUESTED, &vsi->state); break; } + i40e_service_event_schedule(pf); pf->tx_timeout_recovery_level++; } @@ -754,7 +797,6 @@ static void i40e_update_link_xoff_rx(struct i40e_pf *pf) struct i40e_hw_port_stats *nsd = &pf->stats; struct i40e_hw *hw = &pf->hw; u64 xoff = 0; - u16 i, v; if ((hw->fc.current_mode != I40E_FC_FULL) && (hw->fc.current_mode != I40E_FC_RX_PAUSE)) @@ -769,18 +811,6 @@ static void i40e_update_link_xoff_rx(struct i40e_pf *pf) if (!(nsd->link_xoff_rx - xoff)) return; - /* Clear the __I40E_HANG_CHECK_ARMED bit for all Tx rings */ - for (v = 0; v < pf->num_alloc_vsi; v++) { - struct i40e_vsi *vsi = pf->vsi[v]; - - if (!vsi || !vsi->tx_rings[0]) - continue; - - for (i = 0; i < vsi->num_queue_pairs; i++) { - struct i40e_ring *ring = vsi->tx_rings[i]; - clear_bit(__I40E_HANG_CHECK_ARMED, &ring->state); - } - } } /** @@ -796,7 +826,7 @@ static void i40e_update_prio_xoff_rx(struct i40e_pf *pf) bool xoff[I40E_MAX_TRAFFIC_CLASS] = {false}; struct i40e_dcbx_config *dcb_cfg; struct i40e_hw *hw = &pf->hw; - u16 i, v; + u16 i; u8 tc; dcb_cfg = &hw->local_dcbx_config; @@ -821,23 +851,6 @@ static void i40e_update_prio_xoff_rx(struct i40e_pf *pf) tc = dcb_cfg->etscfg.prioritytable[i]; xoff[tc] = true; } - - /* Clear the __I40E_HANG_CHECK_ARMED bit for Tx rings */ - for (v = 0; v < pf->num_alloc_vsi; v++) { - struct i40e_vsi *vsi = pf->vsi[v]; - - if (!vsi || !vsi->tx_rings[0]) - continue; - - for (i = 0; i < vsi->num_queue_pairs; i++) { - struct i40e_ring *ring = vsi->tx_rings[i]; - - tc = ring->dcb_tc; - if (xoff[tc]) - clear_bit(__I40E_HANG_CHECK_ARMED, - &ring->state); - } - } } /** @@ -1514,7 +1527,7 @@ static int i40e_set_mac(struct net_device *netdev, void *p) f->is_laa = true; } - i40e_sync_vsi_filters(vsi); + i40e_sync_vsi_filters(vsi, false); ether_addr_copy(netdev->dev_addr, addr->sa_data); return 0; @@ -1751,12 +1764,13 @@ static void i40e_set_rx_mode(struct net_device *netdev) /** * i40e_sync_vsi_filters - Update the VSI filter list to the HW * @vsi: ptr to the VSI + * @grab_rtnl: whether RTNL needs to be grabbed * * Push any outstanding VSI filter changes through the AdminQ. * * Returns 0 or error value **/ -int i40e_sync_vsi_filters(struct i40e_vsi *vsi) +int i40e_sync_vsi_filters(struct i40e_vsi *vsi, bool grab_rtnl) { struct i40e_mac_filter *f, *ftmp; bool promisc_forced_on = false; @@ -1945,7 +1959,11 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) */ if (pf->cur_promisc != cur_promisc) { pf->cur_promisc = cur_promisc; - i40e_do_reset_safe(pf, + if (grab_rtnl) + i40e_do_reset_safe(pf, + BIT(__I40E_PF_RESET_REQUESTED)); + else + i40e_do_reset(pf, BIT(__I40E_PF_RESET_REQUESTED)); } } else { @@ -1996,7 +2014,7 @@ static void i40e_sync_filters_subtask(struct i40e_pf *pf) for (v = 0; v < pf->num_alloc_vsi; v++) { if (pf->vsi[v] && (pf->vsi[v]->flags & I40E_VSI_FLAG_FILTER_CHANGED)) - i40e_sync_vsi_filters(pf->vsi[v]); + i40e_sync_vsi_filters(pf->vsi[v], true); } } @@ -2203,7 +2221,7 @@ int i40e_vsi_add_vlan(struct i40e_vsi *vsi, s16 vid) test_bit(__I40E_RESET_RECOVERY_PENDING, &vsi->back->state)) return 0; - return i40e_sync_vsi_filters(vsi); + return i40e_sync_vsi_filters(vsi, false); } /** @@ -2275,7 +2293,7 @@ int i40e_vsi_kill_vlan(struct i40e_vsi *vsi, s16 vid) test_bit(__I40E_RESET_RECOVERY_PENDING, &vsi->back->state)) return 0; - return i40e_sync_vsi_filters(vsi); + return i40e_sync_vsi_filters(vsi, false); } /** @@ -2609,8 +2627,6 @@ static int i40e_configure_tx_ring(struct i40e_ring *ring) wr32(hw, I40E_QTX_CTL(pf_q), qtx_ctl); i40e_flush(hw); - clear_bit(__I40E_HANG_CHECK_ARMED, &ring->state); - /* cache tail off for easier writes later */ ring->tail = hw->hw_addr + I40E_QTX_TAIL(pf_q); @@ -4146,6 +4162,108 @@ static int i40e_pf_wait_txq_disabled(struct i40e_pf *pf) } #endif + +/** + * i40e_detect_recover_hung_queue - Function to detect and recover hung_queue + * @q_idx: TX queue number + * @vsi: Pointer to VSI struct + * + * This function checks specified queue for given VSI. Detects hung condition. + * Sets hung bit since it is two step process. Before next run of service task + * if napi_poll runs, it reset 'hung' bit for respective q_vector. If not, + * hung condition remain unchanged and during subsequent run, this function + * issues SW interrupt to recover from hung condition. + **/ +static void i40e_detect_recover_hung_queue(int q_idx, struct i40e_vsi *vsi) +{ + struct i40e_ring *tx_ring = NULL; + struct i40e_pf *pf; + u32 head, val, tx_pending; + int i; + + pf = vsi->back; + + /* now that we have an index, find the tx_ring struct */ + for (i = 0; i < vsi->num_queue_pairs; i++) { + if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc) { + if (q_idx == vsi->tx_rings[i]->queue_index) { + tx_ring = vsi->tx_rings[i]; + break; + } + } + } + + if (!tx_ring) + return; + + /* Read interrupt register */ + if (pf->flags & I40E_FLAG_MSIX_ENABLED) + val = rd32(&pf->hw, + I40E_PFINT_DYN_CTLN(tx_ring->q_vector->v_idx + + tx_ring->vsi->base_vector - 1)); + else + val = rd32(&pf->hw, I40E_PFINT_DYN_CTL0); + + head = i40e_get_head(tx_ring); + + tx_pending = i40e_get_tx_pending(tx_ring); + + /* Interrupts are disabled and TX pending is non-zero, + * trigger the SW interrupt (don't wait). Worst case + * there will be one extra interrupt which may result + * into not cleaning any queues because queues are cleaned. + */ + if (tx_pending && (!(val & I40E_PFINT_DYN_CTLN_INTENA_MASK))) + i40e_force_wb(vsi, tx_ring->q_vector); +} + +/** + * i40e_detect_recover_hung - Function to detect and recover hung_queues + * @pf: pointer to PF struct + * + * LAN VSI has netdev and netdev has TX queues. This function is to check + * each of those TX queues if they are hung, trigger recovery by issuing + * SW interrupt. + **/ +static void i40e_detect_recover_hung(struct i40e_pf *pf) +{ + struct net_device *netdev; + struct i40e_vsi *vsi; + int i; + + /* Only for LAN VSI */ + vsi = pf->vsi[pf->lan_vsi]; + + if (!vsi) + return; + + /* Make sure, VSI state is not DOWN/RECOVERY_PENDING */ + if (test_bit(__I40E_DOWN, &vsi->back->state) || + test_bit(__I40E_RESET_RECOVERY_PENDING, &vsi->back->state)) + return; + + /* Make sure type is MAIN VSI */ + if (vsi->type != I40E_VSI_MAIN) + return; + + netdev = vsi->netdev; + if (!netdev) + return; + + /* Bail out if netif_carrier is not OK */ + if (!netif_carrier_ok(netdev)) + return; + + /* Go thru' TX queues for netdev */ + for (i = 0; i < netdev->num_tx_queues; i++) { + struct netdev_queue *q; + + q = netdev_get_tx_queue(netdev, i); + if (q) + i40e_detect_recover_hung_queue(i, vsi); + } +} + /** * i40e_get_iscsi_tc_map - Return TC map for iSCSI APP * @pf: pointer to PF @@ -5760,68 +5878,6 @@ static void i40e_link_event(struct i40e_pf *pf) } /** - * i40e_check_hang_subtask - Check for hung queues and dropped interrupts - * @pf: board private structure - * - * Set the per-queue flags to request a check for stuck queues in the irq - * clean functions, then force interrupts to be sure the irq clean is called. - **/ -static void i40e_check_hang_subtask(struct i40e_pf *pf) -{ - int i, v; - - /* If we're down or resetting, just bail */ - if (test_bit(__I40E_DOWN, &pf->state) || - test_bit(__I40E_CONFIG_BUSY, &pf->state)) - return; - - /* for each VSI/netdev - * for each Tx queue - * set the check flag - * for each q_vector - * force an interrupt - */ - for (v = 0; v < pf->num_alloc_vsi; v++) { - struct i40e_vsi *vsi = pf->vsi[v]; - int armed = 0; - - if (!pf->vsi[v] || - test_bit(__I40E_DOWN, &vsi->state) || - (vsi->netdev && !netif_carrier_ok(vsi->netdev))) - continue; - - for (i = 0; i < vsi->num_queue_pairs; i++) { - set_check_for_tx_hang(vsi->tx_rings[i]); - if (test_bit(__I40E_HANG_CHECK_ARMED, - &vsi->tx_rings[i]->state)) - armed++; - } - - if (armed) { - if (!(pf->flags & I40E_FLAG_MSIX_ENABLED)) { - wr32(&vsi->back->hw, I40E_PFINT_DYN_CTL0, - (I40E_PFINT_DYN_CTL0_INTENA_MASK | - I40E_PFINT_DYN_CTL0_SWINT_TRIG_MASK | - I40E_PFINT_DYN_CTL0_ITR_INDX_MASK | - I40E_PFINT_DYN_CTL0_SW_ITR_INDX_ENA_MASK | - I40E_PFINT_DYN_CTL0_SW_ITR_INDX_MASK)); - } else { - u16 vec = vsi->base_vector - 1; - u32 val = (I40E_PFINT_DYN_CTLN_INTENA_MASK | - I40E_PFINT_DYN_CTLN_SWINT_TRIG_MASK | - I40E_PFINT_DYN_CTLN_ITR_INDX_MASK | - I40E_PFINT_DYN_CTLN_SW_ITR_INDX_ENA_MASK | - I40E_PFINT_DYN_CTLN_SW_ITR_INDX_MASK); - for (i = 0; i < vsi->num_q_vectors; i++, vec++) - wr32(&vsi->back->hw, - I40E_PFINT_DYN_CTLN(vec), val); - } - i40e_flush(&vsi->back->hw); - } - } -} - -/** * i40e_watchdog_subtask - periodic checks not using event driven response * @pf: board private structure **/ @@ -5840,7 +5896,6 @@ static void i40e_watchdog_subtask(struct i40e_pf *pf) return; pf->service_timer_previous = jiffies; - i40e_check_hang_subtask(pf); i40e_link_event(pf); /* Update the stats for active netdevs so the network stack @@ -6808,6 +6863,7 @@ static void i40e_service_task(struct work_struct *work) return; } + i40e_detect_recover_hung(pf); i40e_reset_subtask(pf); i40e_handle_mdd_event(pf); i40e_vc_process_vflr_event(pf); @@ -8771,7 +8827,7 @@ int i40e_vsi_release(struct i40e_vsi *vsi) list_for_each_entry_safe(f, ftmp, &vsi->mac_filter_list, list) i40e_del_filter(vsi, f->macaddr, f->vlan, f->is_vf, f->is_netdev); - i40e_sync_vsi_filters(vsi); + i40e_sync_vsi_filters(vsi, false); i40e_vsi_delete(vsi); i40e_vsi_free_q_vectors(vsi); @@ -10102,7 +10158,6 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) INIT_WORK(&pf->service_task, i40e_service_task); clear_bit(__I40E_SERVICE_SCHED, &pf->state); pf->flags |= I40E_FLAG_NEED_LINK_UPDATE; - pf->link_check_timeout = jiffies; /* WoL defaults to disabled */ pf->wol_en = false; diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c index 9b83abc0e774..d0288ad4e9b2 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c +++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c @@ -418,6 +418,10 @@ static i40e_status i40e_write_nvm_aq(struct i40e_hw *hw, u8 module_pointer, bool last_command) { i40e_status ret_code = I40E_ERR_NVM; + struct i40e_asq_cmd_details cmd_details; + + memset(&cmd_details, 0, sizeof(cmd_details)); + cmd_details.wb_desc = &hw->nvm_wb_desc; /* Here we are checking the SR limit only for the flat memory model. * We cannot do it for the module-based model, as we did not acquire @@ -443,7 +447,7 @@ static i40e_status i40e_write_nvm_aq(struct i40e_hw *hw, u8 module_pointer, ret_code = i40e_aq_update_nvm(hw, module_pointer, 2 * offset, /*bytes*/ 2 * words, /*bytes*/ - data, last_command, NULL); + data, last_command, &cmd_details); return ret_code; } @@ -592,25 +596,31 @@ i40e_validate_nvm_checksum_exit: static i40e_status i40e_nvmupd_state_init(struct i40e_hw *hw, struct i40e_nvm_access *cmd, - u8 *bytes, int *errno); + u8 *bytes, int *perrno); static i40e_status i40e_nvmupd_state_reading(struct i40e_hw *hw, struct i40e_nvm_access *cmd, - u8 *bytes, int *errno); + u8 *bytes, int *perrno); static i40e_status i40e_nvmupd_state_writing(struct i40e_hw *hw, struct i40e_nvm_access *cmd, u8 *bytes, int *errno); static enum i40e_nvmupd_cmd i40e_nvmupd_validate_command(struct i40e_hw *hw, struct i40e_nvm_access *cmd, - int *errno); + int *perrno); static i40e_status i40e_nvmupd_nvm_erase(struct i40e_hw *hw, struct i40e_nvm_access *cmd, - int *errno); + int *perrno); static i40e_status i40e_nvmupd_nvm_write(struct i40e_hw *hw, struct i40e_nvm_access *cmd, - u8 *bytes, int *errno); + u8 *bytes, int *perrno); static i40e_status i40e_nvmupd_nvm_read(struct i40e_hw *hw, struct i40e_nvm_access *cmd, - u8 *bytes, int *errno); + u8 *bytes, int *perrno); +static i40e_status i40e_nvmupd_exec_aq(struct i40e_hw *hw, + struct i40e_nvm_access *cmd, + u8 *bytes, int *perrno); +static i40e_status i40e_nvmupd_get_aq_result(struct i40e_hw *hw, + struct i40e_nvm_access *cmd, + u8 *bytes, int *perrno); static inline u8 i40e_nvmupd_get_module(u32 val) { return (u8)(val & I40E_NVM_MOD_PNT_MASK); @@ -634,6 +644,9 @@ static char *i40e_nvm_update_state_str[] = { "I40E_NVMUPD_CSUM_CON", "I40E_NVMUPD_CSUM_SA", "I40E_NVMUPD_CSUM_LCB", + "I40E_NVMUPD_STATUS", + "I40E_NVMUPD_EXEC_AQ", + "I40E_NVMUPD_GET_AQ_RESULT", }; /** @@ -641,30 +654,60 @@ static char *i40e_nvm_update_state_str[] = { * @hw: pointer to hardware structure * @cmd: pointer to nvm update command * @bytes: pointer to the data buffer - * @errno: pointer to return error code + * @perrno: pointer to return error code * * Dispatches command depending on what update state is current **/ i40e_status i40e_nvmupd_command(struct i40e_hw *hw, struct i40e_nvm_access *cmd, - u8 *bytes, int *errno) + u8 *bytes, int *perrno) { i40e_status status; + enum i40e_nvmupd_cmd upd_cmd; /* assume success */ - *errno = 0; + *perrno = 0; + + /* early check for status command and debug msgs */ + upd_cmd = i40e_nvmupd_validate_command(hw, cmd, perrno); + + i40e_debug(hw, I40E_DEBUG_NVM, "%s state %d nvm_release_on_hold %d\n", + i40e_nvm_update_state_str[upd_cmd], + hw->nvmupd_state, + hw->aq.nvm_release_on_done); + + if (upd_cmd == I40E_NVMUPD_INVALID) { + *perrno = -EFAULT; + i40e_debug(hw, I40E_DEBUG_NVM, + "i40e_nvmupd_validate_command returns %d errno %d\n", + upd_cmd, *perrno); + } + + /* a status request returns immediately rather than + * going into the state machine + */ + if (upd_cmd == I40E_NVMUPD_STATUS) { + bytes[0] = hw->nvmupd_state; + return 0; + } switch (hw->nvmupd_state) { case I40E_NVMUPD_STATE_INIT: - status = i40e_nvmupd_state_init(hw, cmd, bytes, errno); + status = i40e_nvmupd_state_init(hw, cmd, bytes, perrno); break; case I40E_NVMUPD_STATE_READING: - status = i40e_nvmupd_state_reading(hw, cmd, bytes, errno); + status = i40e_nvmupd_state_reading(hw, cmd, bytes, perrno); break; case I40E_NVMUPD_STATE_WRITING: - status = i40e_nvmupd_state_writing(hw, cmd, bytes, errno); + status = i40e_nvmupd_state_writing(hw, cmd, bytes, perrno); + break; + + case I40E_NVMUPD_STATE_INIT_WAIT: + case I40E_NVMUPD_STATE_WRITE_WAIT: + status = I40E_ERR_NOT_READY; + *perrno = -EBUSY; break; default: @@ -672,7 +715,7 @@ i40e_status i40e_nvmupd_command(struct i40e_hw *hw, i40e_debug(hw, I40E_DEBUG_NVM, "NVMUPD: no such state %d\n", hw->nvmupd_state); status = I40E_NOT_SUPPORTED; - *errno = -ESRCH; + *perrno = -ESRCH; break; } return status; @@ -683,28 +726,28 @@ i40e_status i40e_nvmupd_command(struct i40e_hw *hw, * @hw: pointer to hardware structure * @cmd: pointer to nvm update command buffer * @bytes: pointer to the data buffer - * @errno: pointer to return error code + * @perrno: pointer to return error code * * Process legitimate commands of the Init state and conditionally set next * state. Reject all other commands. **/ static i40e_status i40e_nvmupd_state_init(struct i40e_hw *hw, struct i40e_nvm_access *cmd, - u8 *bytes, int *errno) + u8 *bytes, int *perrno) { i40e_status status = 0; enum i40e_nvmupd_cmd upd_cmd; - upd_cmd = i40e_nvmupd_validate_command(hw, cmd, errno); + upd_cmd = i40e_nvmupd_validate_command(hw, cmd, perrno); switch (upd_cmd) { case I40E_NVMUPD_READ_SA: status = i40e_acquire_nvm(hw, I40E_RESOURCE_READ); if (status) { - *errno = i40e_aq_rc_to_posix(status, + *perrno = i40e_aq_rc_to_posix(status, hw->aq.asq_last_status); } else { - status = i40e_nvmupd_nvm_read(hw, cmd, bytes, errno); + status = i40e_nvmupd_nvm_read(hw, cmd, bytes, perrno); i40e_release_nvm(hw); } break; @@ -712,10 +755,10 @@ static i40e_status i40e_nvmupd_state_init(struct i40e_hw *hw, case I40E_NVMUPD_READ_SNT: status = i40e_acquire_nvm(hw, I40E_RESOURCE_READ); if (status) { - *errno = i40e_aq_rc_to_posix(status, + *perrno = i40e_aq_rc_to_posix(status, hw->aq.asq_last_status); } else { - status = i40e_nvmupd_nvm_read(hw, cmd, bytes, errno); + status = i40e_nvmupd_nvm_read(hw, cmd, bytes, perrno); if (status) i40e_release_nvm(hw); else @@ -726,70 +769,83 @@ static i40e_status i40e_nvmupd_state_init(struct i40e_hw *hw, case I40E_NVMUPD_WRITE_ERA: status = i40e_acquire_nvm(hw, I40E_RESOURCE_WRITE); if (status) { - *errno = i40e_aq_rc_to_posix(status, + *perrno = i40e_aq_rc_to_posix(status, hw->aq.asq_last_status); } else { - status = i40e_nvmupd_nvm_erase(hw, cmd, errno); - if (status) + status = i40e_nvmupd_nvm_erase(hw, cmd, perrno); + if (status) { i40e_release_nvm(hw); - else + } else { hw->aq.nvm_release_on_done = true; + hw->nvmupd_state = I40E_NVMUPD_STATE_INIT_WAIT; + } } break; case I40E_NVMUPD_WRITE_SA: status = i40e_acquire_nvm(hw, I40E_RESOURCE_WRITE); if (status) { - *errno = i40e_aq_rc_to_posix(status, + *perrno = i40e_aq_rc_to_posix(status, hw->aq.asq_last_status); } else { - status = i40e_nvmupd_nvm_write(hw, cmd, bytes, errno); - if (status) + status = i40e_nvmupd_nvm_write(hw, cmd, bytes, perrno); + if (status) { i40e_release_nvm(hw); - else + } else { hw->aq.nvm_release_on_done = true; + hw->nvmupd_state = I40E_NVMUPD_STATE_INIT_WAIT; + } } break; case I40E_NVMUPD_WRITE_SNT: status = i40e_acquire_nvm(hw, I40E_RESOURCE_WRITE); if (status) { - *errno = i40e_aq_rc_to_posix(status, + *perrno = i40e_aq_rc_to_posix(status, hw->aq.asq_last_status); } else { - status = i40e_nvmupd_nvm_write(hw, cmd, bytes, errno); + status = i40e_nvmupd_nvm_write(hw, cmd, bytes, perrno); if (status) i40e_release_nvm(hw); else - hw->nvmupd_state = I40E_NVMUPD_STATE_WRITING; + hw->nvmupd_state = I40E_NVMUPD_STATE_WRITE_WAIT; } break; case I40E_NVMUPD_CSUM_SA: status = i40e_acquire_nvm(hw, I40E_RESOURCE_WRITE); if (status) { - *errno = i40e_aq_rc_to_posix(status, + *perrno = i40e_aq_rc_to_posix(status, hw->aq.asq_last_status); } else { status = i40e_update_nvm_checksum(hw); if (status) { - *errno = hw->aq.asq_last_status ? + *perrno = hw->aq.asq_last_status ? i40e_aq_rc_to_posix(status, hw->aq.asq_last_status) : -EIO; i40e_release_nvm(hw); } else { hw->aq.nvm_release_on_done = true; + hw->nvmupd_state = I40E_NVMUPD_STATE_INIT_WAIT; } } break; + case I40E_NVMUPD_EXEC_AQ: + status = i40e_nvmupd_exec_aq(hw, cmd, bytes, perrno); + break; + + case I40E_NVMUPD_GET_AQ_RESULT: + status = i40e_nvmupd_get_aq_result(hw, cmd, bytes, perrno); + break; + default: i40e_debug(hw, I40E_DEBUG_NVM, "NVMUPD: bad cmd %s in init state\n", i40e_nvm_update_state_str[upd_cmd]); status = I40E_ERR_NVM; - *errno = -ESRCH; + *perrno = -ESRCH; break; } return status; @@ -800,28 +856,28 @@ static i40e_status i40e_nvmupd_state_init(struct i40e_hw *hw, * @hw: pointer to hardware structure * @cmd: pointer to nvm update command buffer * @bytes: pointer to the data buffer - * @errno: pointer to return error code + * @perrno: pointer to return error code * * NVM ownership is already held. Process legitimate commands and set any * change in state; reject all other commands. **/ static i40e_status i40e_nvmupd_state_reading(struct i40e_hw *hw, struct i40e_nvm_access *cmd, - u8 *bytes, int *errno) + u8 *bytes, int *perrno) { - i40e_status status; + i40e_status status = 0; enum i40e_nvmupd_cmd upd_cmd; - upd_cmd = i40e_nvmupd_validate_command(hw, cmd, errno); + upd_cmd = i40e_nvmupd_validate_command(hw, cmd, perrno); switch (upd_cmd) { case I40E_NVMUPD_READ_SA: case I40E_NVMUPD_READ_CON: - status = i40e_nvmupd_nvm_read(hw, cmd, bytes, errno); + status = i40e_nvmupd_nvm_read(hw, cmd, bytes, perrno); break; case I40E_NVMUPD_READ_LCB: - status = i40e_nvmupd_nvm_read(hw, cmd, bytes, errno); + status = i40e_nvmupd_nvm_read(hw, cmd, bytes, perrno); i40e_release_nvm(hw); hw->nvmupd_state = I40E_NVMUPD_STATE_INIT; break; @@ -831,7 +887,7 @@ static i40e_status i40e_nvmupd_state_reading(struct i40e_hw *hw, "NVMUPD: bad cmd %s in reading state.\n", i40e_nvm_update_state_str[upd_cmd]); status = I40E_NOT_SUPPORTED; - *errno = -ESRCH; + *perrno = -ESRCH; break; } return status; @@ -842,55 +898,68 @@ static i40e_status i40e_nvmupd_state_reading(struct i40e_hw *hw, * @hw: pointer to hardware structure * @cmd: pointer to nvm update command buffer * @bytes: pointer to the data buffer - * @errno: pointer to return error code + * @perrno: pointer to return error code * * NVM ownership is already held. Process legitimate commands and set any * change in state; reject all other commands **/ static i40e_status i40e_nvmupd_state_writing(struct i40e_hw *hw, struct i40e_nvm_access *cmd, - u8 *bytes, int *errno) + u8 *bytes, int *perrno) { - i40e_status status; + i40e_status status = 0; enum i40e_nvmupd_cmd upd_cmd; bool retry_attempt = false; - upd_cmd = i40e_nvmupd_validate_command(hw, cmd, errno); + upd_cmd = i40e_nvmupd_validate_command(hw, cmd, perrno); retry: switch (upd_cmd) { case I40E_NVMUPD_WRITE_CON: - status = i40e_nvmupd_nvm_write(hw, cmd, bytes, errno); + status = i40e_nvmupd_nvm_write(hw, cmd, bytes, perrno); + if (!status) + hw->nvmupd_state = I40E_NVMUPD_STATE_WRITE_WAIT; break; case I40E_NVMUPD_WRITE_LCB: - status = i40e_nvmupd_nvm_write(hw, cmd, bytes, errno); - if (!status) + status = i40e_nvmupd_nvm_write(hw, cmd, bytes, perrno); + if (status) { + *perrno = hw->aq.asq_last_status ? + i40e_aq_rc_to_posix(status, + hw->aq.asq_last_status) : + -EIO; + hw->nvmupd_state = I40E_NVMUPD_STATE_INIT; + } else { hw->aq.nvm_release_on_done = true; - hw->nvmupd_state = I40E_NVMUPD_STATE_INIT; + hw->nvmupd_state = I40E_NVMUPD_STATE_INIT_WAIT; + } break; case I40E_NVMUPD_CSUM_CON: status = i40e_update_nvm_checksum(hw); if (status) { - *errno = hw->aq.asq_last_status ? + *perrno = hw->aq.asq_last_status ? i40e_aq_rc_to_posix(status, hw->aq.asq_last_status) : -EIO; hw->nvmupd_state = I40E_NVMUPD_STATE_INIT; + } else { + hw->nvmupd_state = I40E_NVMUPD_STATE_WRITE_WAIT; } break; case I40E_NVMUPD_CSUM_LCB: status = i40e_update_nvm_checksum(hw); - if (status) - *errno = hw->aq.asq_last_status ? + if (status) { + *perrno = hw->aq.asq_last_status ? i40e_aq_rc_to_posix(status, hw->aq.asq_last_status) : -EIO; - else + hw->nvmupd_state = I40E_NVMUPD_STATE_INIT; + } else { hw->aq.nvm_release_on_done = true; - hw->nvmupd_state = I40E_NVMUPD_STATE_INIT; + hw->nvmupd_state = I40E_NVMUPD_STATE_INIT_WAIT; + } break; default: @@ -898,7 +967,7 @@ retry: "NVMUPD: bad cmd %s in writing state.\n", i40e_nvm_update_state_str[upd_cmd]); status = I40E_NOT_SUPPORTED; - *errno = -ESRCH; + *perrno = -ESRCH; break; } @@ -941,21 +1010,22 @@ retry: * i40e_nvmupd_validate_command - Validate given command * @hw: pointer to hardware structure * @cmd: pointer to nvm update command buffer - * @errno: pointer to return error code + * @perrno: pointer to return error code * * Return one of the valid command types or I40E_NVMUPD_INVALID **/ static enum i40e_nvmupd_cmd i40e_nvmupd_validate_command(struct i40e_hw *hw, struct i40e_nvm_access *cmd, - int *errno) + int *perrno) { enum i40e_nvmupd_cmd upd_cmd; - u8 transaction; + u8 module, transaction; /* anything that doesn't match a recognized case is an error */ upd_cmd = I40E_NVMUPD_INVALID; transaction = i40e_nvmupd_get_transaction(cmd->config); + module = i40e_nvmupd_get_module(cmd->config); /* limits on data size */ if ((cmd->data_size < 1) || @@ -963,7 +1033,7 @@ static enum i40e_nvmupd_cmd i40e_nvmupd_validate_command(struct i40e_hw *hw, i40e_debug(hw, I40E_DEBUG_NVM, "i40e_nvmupd_validate_command data_size %d\n", cmd->data_size); - *errno = -EFAULT; + *perrno = -EFAULT; return I40E_NVMUPD_INVALID; } @@ -982,6 +1052,12 @@ static enum i40e_nvmupd_cmd i40e_nvmupd_validate_command(struct i40e_hw *hw, case I40E_NVM_SA: upd_cmd = I40E_NVMUPD_READ_SA; break; + case I40E_NVM_EXEC: + if (module == 0xf) + upd_cmd = I40E_NVMUPD_STATUS; + else if (module == 0) + upd_cmd = I40E_NVMUPD_GET_AQ_RESULT; + break; } break; @@ -1011,21 +1087,155 @@ static enum i40e_nvmupd_cmd i40e_nvmupd_validate_command(struct i40e_hw *hw, case (I40E_NVM_CSUM|I40E_NVM_LCB): upd_cmd = I40E_NVMUPD_CSUM_LCB; break; + case I40E_NVM_EXEC: + if (module == 0) + upd_cmd = I40E_NVMUPD_EXEC_AQ; + break; } break; } - i40e_debug(hw, I40E_DEBUG_NVM, "%s state %d nvm_release_on_hold %d\n", - i40e_nvm_update_state_str[upd_cmd], - hw->nvmupd_state, - hw->aq.nvm_release_on_done); - if (upd_cmd == I40E_NVMUPD_INVALID) { - *errno = -EFAULT; + return upd_cmd; +} + +/** + * i40e_nvmupd_exec_aq - Run an AQ command + * @hw: pointer to hardware structure + * @cmd: pointer to nvm update command buffer + * @bytes: pointer to the data buffer + * @perrno: pointer to return error code + * + * cmd structure contains identifiers and data buffer + **/ +static i40e_status i40e_nvmupd_exec_aq(struct i40e_hw *hw, + struct i40e_nvm_access *cmd, + u8 *bytes, int *perrno) +{ + struct i40e_asq_cmd_details cmd_details; + i40e_status status; + struct i40e_aq_desc *aq_desc; + u32 buff_size = 0; + u8 *buff = NULL; + u32 aq_desc_len; + u32 aq_data_len; + + i40e_debug(hw, I40E_DEBUG_NVM, "NVMUPD: %s\n", __func__); + memset(&cmd_details, 0, sizeof(cmd_details)); + cmd_details.wb_desc = &hw->nvm_wb_desc; + + aq_desc_len = sizeof(struct i40e_aq_desc); + memset(&hw->nvm_wb_desc, 0, aq_desc_len); + + /* get the aq descriptor */ + if (cmd->data_size < aq_desc_len) { i40e_debug(hw, I40E_DEBUG_NVM, - "i40e_nvmupd_validate_command returns %d errno %d\n", - upd_cmd, *errno); + "NVMUPD: not enough aq desc bytes for exec, size %d < %d\n", + cmd->data_size, aq_desc_len); + *perrno = -EINVAL; + return I40E_ERR_PARAM; } - return upd_cmd; + aq_desc = (struct i40e_aq_desc *)bytes; + + /* if data buffer needed, make sure it's ready */ + aq_data_len = cmd->data_size - aq_desc_len; + buff_size = max_t(u32, aq_data_len, le16_to_cpu(aq_desc->datalen)); + if (buff_size) { + if (!hw->nvm_buff.va) { + status = i40e_allocate_virt_mem(hw, &hw->nvm_buff, + hw->aq.asq_buf_size); + if (status) + i40e_debug(hw, I40E_DEBUG_NVM, + "NVMUPD: i40e_allocate_virt_mem for exec buff failed, %d\n", + status); + } + + if (hw->nvm_buff.va) { + buff = hw->nvm_buff.va; + memcpy(buff, &bytes[aq_desc_len], aq_data_len); + } + } + + /* and away we go! */ + status = i40e_asq_send_command(hw, aq_desc, buff, + buff_size, &cmd_details); + if (status) { + i40e_debug(hw, I40E_DEBUG_NVM, + "i40e_nvmupd_exec_aq err %s aq_err %s\n", + i40e_stat_str(hw, status), + i40e_aq_str(hw, hw->aq.asq_last_status)); + *perrno = i40e_aq_rc_to_posix(status, hw->aq.asq_last_status); + } + + return status; +} + +/** + * i40e_nvmupd_get_aq_result - Get the results from the previous exec_aq + * @hw: pointer to hardware structure + * @cmd: pointer to nvm update command buffer + * @bytes: pointer to the data buffer + * @perrno: pointer to return error code + * + * cmd structure contains identifiers and data buffer + **/ +static i40e_status i40e_nvmupd_get_aq_result(struct i40e_hw *hw, + struct i40e_nvm_access *cmd, + u8 *bytes, int *perrno) +{ + u32 aq_total_len; + u32 aq_desc_len; + int remainder; + u8 *buff; + + i40e_debug(hw, I40E_DEBUG_NVM, "NVMUPD: %s\n", __func__); + + aq_desc_len = sizeof(struct i40e_aq_desc); + aq_total_len = aq_desc_len + le16_to_cpu(hw->nvm_wb_desc.datalen); + + /* check offset range */ + if (cmd->offset > aq_total_len) { + i40e_debug(hw, I40E_DEBUG_NVM, "%s: offset too big %d > %d\n", + __func__, cmd->offset, aq_total_len); + *perrno = -EINVAL; + return I40E_ERR_PARAM; + } + + /* check copylength range */ + if (cmd->data_size > (aq_total_len - cmd->offset)) { + int new_len = aq_total_len - cmd->offset; + + i40e_debug(hw, I40E_DEBUG_NVM, "%s: copy length %d too big, trimming to %d\n", + __func__, cmd->data_size, new_len); + cmd->data_size = new_len; + } + + remainder = cmd->data_size; + if (cmd->offset < aq_desc_len) { + u32 len = aq_desc_len - cmd->offset; + + len = min(len, cmd->data_size); + i40e_debug(hw, I40E_DEBUG_NVM, "%s: aq_desc bytes %d to %d\n", + __func__, cmd->offset, cmd->offset + len); + + buff = ((u8 *)&hw->nvm_wb_desc) + cmd->offset; + memcpy(bytes, buff, len); + + bytes += len; + remainder -= len; + buff = hw->nvm_buff.va; + } else { + buff = hw->nvm_buff.va + (cmd->offset - aq_desc_len); + } + + if (remainder > 0) { + int start_byte = buff - (u8 *)hw->nvm_buff.va; + + i40e_debug(hw, I40E_DEBUG_NVM, "%s: databuf bytes %d to %d\n", + __func__, start_byte, start_byte + remainder); + memcpy(bytes, buff, remainder); + } + + return 0; } /** @@ -1033,14 +1243,15 @@ static enum i40e_nvmupd_cmd i40e_nvmupd_validate_command(struct i40e_hw *hw, * @hw: pointer to hardware structure * @cmd: pointer to nvm update command buffer * @bytes: pointer to the data buffer - * @errno: pointer to return error code + * @perrno: pointer to return error code * * cmd structure contains identifiers and data buffer **/ static i40e_status i40e_nvmupd_nvm_read(struct i40e_hw *hw, struct i40e_nvm_access *cmd, - u8 *bytes, int *errno) + u8 *bytes, int *perrno) { + struct i40e_asq_cmd_details cmd_details; i40e_status status; u8 module, transaction; bool last; @@ -1049,8 +1260,11 @@ static i40e_status i40e_nvmupd_nvm_read(struct i40e_hw *hw, module = i40e_nvmupd_get_module(cmd->config); last = (transaction == I40E_NVM_LCB) || (transaction == I40E_NVM_SA); + memset(&cmd_details, 0, sizeof(cmd_details)); + cmd_details.wb_desc = &hw->nvm_wb_desc; + status = i40e_aq_read_nvm(hw, module, cmd->offset, (u16)cmd->data_size, - bytes, last, NULL); + bytes, last, &cmd_details); if (status) { i40e_debug(hw, I40E_DEBUG_NVM, "i40e_nvmupd_nvm_read mod 0x%x off 0x%x len 0x%x\n", @@ -1058,7 +1272,7 @@ static i40e_status i40e_nvmupd_nvm_read(struct i40e_hw *hw, i40e_debug(hw, I40E_DEBUG_NVM, "i40e_nvmupd_nvm_read status %d aq %d\n", status, hw->aq.asq_last_status); - *errno = i40e_aq_rc_to_posix(status, hw->aq.asq_last_status); + *perrno = i40e_aq_rc_to_posix(status, hw->aq.asq_last_status); } return status; @@ -1068,23 +1282,28 @@ static i40e_status i40e_nvmupd_nvm_read(struct i40e_hw *hw, * i40e_nvmupd_nvm_erase - Erase an NVM module * @hw: pointer to hardware structure * @cmd: pointer to nvm update command buffer - * @errno: pointer to return error code + * @perrno: pointer to return error code * * module, offset, data_size and data are in cmd structure **/ static i40e_status i40e_nvmupd_nvm_erase(struct i40e_hw *hw, struct i40e_nvm_access *cmd, - int *errno) + int *perrno) { i40e_status status = 0; + struct i40e_asq_cmd_details cmd_details; u8 module, transaction; bool last; transaction = i40e_nvmupd_get_transaction(cmd->config); module = i40e_nvmupd_get_module(cmd->config); last = (transaction & I40E_NVM_LCB); + + memset(&cmd_details, 0, sizeof(cmd_details)); + cmd_details.wb_desc = &hw->nvm_wb_desc; + status = i40e_aq_erase_nvm(hw, module, cmd->offset, (u16)cmd->data_size, - last, NULL); + last, &cmd_details); if (status) { i40e_debug(hw, I40E_DEBUG_NVM, "i40e_nvmupd_nvm_erase mod 0x%x off 0x%x len 0x%x\n", @@ -1092,7 +1311,7 @@ static i40e_status i40e_nvmupd_nvm_erase(struct i40e_hw *hw, i40e_debug(hw, I40E_DEBUG_NVM, "i40e_nvmupd_nvm_erase status %d aq %d\n", status, hw->aq.asq_last_status); - *errno = i40e_aq_rc_to_posix(status, hw->aq.asq_last_status); + *perrno = i40e_aq_rc_to_posix(status, hw->aq.asq_last_status); } return status; @@ -1103,15 +1322,16 @@ static i40e_status i40e_nvmupd_nvm_erase(struct i40e_hw *hw, * @hw: pointer to hardware structure * @cmd: pointer to nvm update command buffer * @bytes: pointer to the data buffer - * @errno: pointer to return error code + * @perrno: pointer to return error code * * module, offset, data_size and data are in cmd structure **/ static i40e_status i40e_nvmupd_nvm_write(struct i40e_hw *hw, struct i40e_nvm_access *cmd, - u8 *bytes, int *errno) + u8 *bytes, int *perrno) { i40e_status status = 0; + struct i40e_asq_cmd_details cmd_details; u8 module, transaction; bool last; @@ -1119,8 +1339,12 @@ static i40e_status i40e_nvmupd_nvm_write(struct i40e_hw *hw, module = i40e_nvmupd_get_module(cmd->config); last = (transaction & I40E_NVM_LCB); + memset(&cmd_details, 0, sizeof(cmd_details)); + cmd_details.wb_desc = &hw->nvm_wb_desc; + status = i40e_aq_update_nvm(hw, module, cmd->offset, - (u16)cmd->data_size, bytes, last, NULL); + (u16)cmd->data_size, bytes, last, + &cmd_details); if (status) { i40e_debug(hw, I40E_DEBUG_NVM, "i40e_nvmupd_nvm_write mod 0x%x off 0x%x len 0x%x\n", @@ -1128,7 +1352,7 @@ static i40e_status i40e_nvmupd_nvm_write(struct i40e_hw *hw, i40e_debug(hw, I40E_DEBUG_NVM, "i40e_nvmupd_nvm_write status %d aq %d\n", status, hw->aq.asq_last_status); - *errno = i40e_aq_rc_to_posix(status, hw->aq.asq_last_status); + *perrno = i40e_aq_rc_to_posix(status, hw->aq.asq_last_status); } return status; diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 738aca68f665..3ce4900c0c43 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -601,27 +601,13 @@ void i40e_free_tx_resources(struct i40e_ring *tx_ring) } /** - * i40e_get_head - Retrieve head from head writeback - * @tx_ring: tx ring to fetch head of - * - * Returns value of Tx ring head based on value stored - * in head write-back location - **/ -static inline u32 i40e_get_head(struct i40e_ring *tx_ring) -{ - void *head = (struct i40e_tx_desc *)tx_ring->desc + tx_ring->count; - - return le32_to_cpu(*(volatile __le32 *)head); -} - -/** * i40e_get_tx_pending - how many tx descriptors not processed * @tx_ring: the ring of descriptors * * Since there is no access to the ring head register * in XL710, we need to use our local copies **/ -static u32 i40e_get_tx_pending(struct i40e_ring *ring) +u32 i40e_get_tx_pending(struct i40e_ring *ring) { u32 head, tail; @@ -635,50 +621,6 @@ static u32 i40e_get_tx_pending(struct i40e_ring *ring) return 0; } -/** - * i40e_check_tx_hang - Is there a hang in the Tx queue - * @tx_ring: the ring of descriptors - **/ -static bool i40e_check_tx_hang(struct i40e_ring *tx_ring) -{ - u32 tx_done = tx_ring->stats.packets; - u32 tx_done_old = tx_ring->tx_stats.tx_done_old; - u32 tx_pending = i40e_get_tx_pending(tx_ring); - struct i40e_pf *pf = tx_ring->vsi->back; - bool ret = false; - - clear_check_for_tx_hang(tx_ring); - - /* Check for a hung queue, but be thorough. This verifies - * that a transmit has been completed since the previous - * check AND there is at least one packet pending. The - * ARMED bit is set to indicate a potential hang. The - * bit is cleared if a pause frame is received to remove - * false hang detection due to PFC or 802.3x frames. By - * requiring this to fail twice we avoid races with - * PFC clearing the ARMED bit and conditions where we - * run the check_tx_hang logic with a transmit completion - * pending but without time to complete it yet. - */ - if ((tx_done_old == tx_done) && tx_pending) { - /* make sure it is true for two checks in a row */ - ret = test_and_set_bit(__I40E_HANG_CHECK_ARMED, - &tx_ring->state); - } else if (tx_done_old == tx_done && - (tx_pending < I40E_MIN_DESC_PENDING) && (tx_pending > 0)) { - if (I40E_DEBUG_FLOW & pf->hw.debug_mask) - dev_info(tx_ring->dev, "HW needs some more descs to do a cacheline flush. tx_pending %d, queue %d", - tx_pending, tx_ring->queue_index); - pf->tx_sluggish_count++; - } else { - /* update completed stats and disarm the hang check */ - tx_ring->tx_stats.tx_done_old = tx_done; - clear_bit(__I40E_HANG_CHECK_ARMED, &tx_ring->state); - } - - return ret; -} - #define WB_STRIDE 0x3 /** @@ -784,42 +726,21 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget) tx_ring->q_vector->tx.total_bytes += total_bytes; tx_ring->q_vector->tx.total_packets += total_packets; - /* check to see if there are any non-cache aligned descriptors - * waiting to be written back, and kick the hardware to force - * them to be written back in case of napi polling - */ - if (budget && - !((i & WB_STRIDE) == WB_STRIDE) && - !test_bit(__I40E_DOWN, &tx_ring->vsi->state) && - (I40E_DESC_UNUSED(tx_ring) != tx_ring->count)) - tx_ring->arm_wb = true; - else - tx_ring->arm_wb = false; - - if (check_for_tx_hang(tx_ring) && i40e_check_tx_hang(tx_ring)) { - /* schedule immediate reset if we believe we hung */ - dev_info(tx_ring->dev, "Detected Tx Unit Hang\n" - " VSI <%d>\n" - " Tx Queue <%d>\n" - " next_to_use <%x>\n" - " next_to_clean <%x>\n", - tx_ring->vsi->seid, - tx_ring->queue_index, - tx_ring->next_to_use, i); - - netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index); - - dev_info(tx_ring->dev, - "tx hang detected on queue %d, reset requested\n", - tx_ring->queue_index); - - /* do not fire the reset immediately, wait for the stack to - * decide we are truly stuck, also prevents every queue from - * simultaneously requesting a reset + if (tx_ring->flags & I40E_TXR_FLAGS_WB_ON_ITR) { + unsigned int j = 0; + + /* check to see if there are < 4 descriptors + * waiting to be written back, then kick the hardware to force + * them to be written back in case we stay in NAPI. + * In this mode on X722 we do not enable Interrupt. */ + j = i40e_get_tx_pending(tx_ring); - /* the adapter is about to reset, no point in enabling polling */ - budget = 1; + if (budget && + ((j / (WB_STRIDE + 1)) == 0) && (j != 0) && + !test_bit(__I40E_DOWN, &tx_ring->vsi->state) && + (I40E_DESC_UNUSED(tx_ring) != tx_ring->count)) + tx_ring->arm_wb = true; } netdev_tx_completed_queue(netdev_get_tx_queue(tx_ring->netdev, @@ -851,7 +772,7 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget) * @q_vector: the vector on which to force writeback * **/ -static void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) +void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) { u16 flags = q_vector->tx.ring[0].flags; @@ -2324,6 +2245,9 @@ static void i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags, l4_tunnel = I40E_TXD_CTX_UDP_TUNNELING; *tx_flags |= I40E_TX_FLAGS_VXLAN_TUNNEL; break; + case IPPROTO_GRE: + l4_tunnel = I40E_TXD_CTX_GRE_TUNNELING; + break; default: return; } @@ -2581,6 +2505,9 @@ static inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, u32 td_tag = 0; dma_addr_t dma; u16 gso_segs; + u16 desc_count = 0; + bool tail_bump = true; + bool do_rs = false; if (tx_flags & I40E_TX_FLAGS_HW_VLAN) { td_cmd |= I40E_TX_DESC_CMD_IL2TAG1; @@ -2621,6 +2548,8 @@ static inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, tx_desc++; i++; + desc_count++; + if (i == tx_ring->count) { tx_desc = I40E_TX_DESC(tx_ring, 0); i = 0; @@ -2640,6 +2569,8 @@ static inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, tx_desc++; i++; + desc_count++; + if (i == tx_ring->count) { tx_desc = I40E_TX_DESC(tx_ring, 0); i = 0; @@ -2654,34 +2585,6 @@ static inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, tx_bi = &tx_ring->tx_bi[i]; } - /* Place RS bit on last descriptor of any packet that spans across the - * 4th descriptor (WB_STRIDE aka 0x3) in a 64B cacheline. - */ - if (((i & WB_STRIDE) != WB_STRIDE) && - (first <= &tx_ring->tx_bi[i]) && - (first >= &tx_ring->tx_bi[i & ~WB_STRIDE])) { - tx_desc->cmd_type_offset_bsz = - build_ctob(td_cmd, td_offset, size, td_tag) | - cpu_to_le64((u64)I40E_TX_DESC_CMD_EOP << - I40E_TXD_QW1_CMD_SHIFT); - } else { - tx_desc->cmd_type_offset_bsz = - build_ctob(td_cmd, td_offset, size, td_tag) | - cpu_to_le64((u64)I40E_TXD_CMD << - I40E_TXD_QW1_CMD_SHIFT); - } - - netdev_tx_sent_queue(netdev_get_tx_queue(tx_ring->netdev, - tx_ring->queue_index), - first->bytecount); - - /* Force memory writes to complete before letting h/w - * know there are new descriptors to fetch. (Only - * applicable for weak-ordered memory model archs, - * such as IA-64). - */ - wmb(); - /* set next_to_watch value indicating a packet is present */ first->next_to_watch = tx_desc; @@ -2691,15 +2594,72 @@ static inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, tx_ring->next_to_use = i; + netdev_tx_sent_queue(netdev_get_tx_queue(tx_ring->netdev, + tx_ring->queue_index), + first->bytecount); i40e_maybe_stop_tx(tx_ring, DESC_NEEDED); + + /* Algorithm to optimize tail and RS bit setting: + * if xmit_more is supported + * if xmit_more is true + * do not update tail and do not mark RS bit. + * if xmit_more is false and last xmit_more was false + * if every packet spanned less than 4 desc + * then set RS bit on 4th packet and update tail + * on every packet + * else + * update tail and set RS bit on every packet. + * if xmit_more is false and last_xmit_more was true + * update tail and set RS bit. + * + * Optimization: wmb to be issued only in case of tail update. + * Also optimize the Descriptor WB path for RS bit with the same + * algorithm. + * + * Note: If there are less than 4 packets + * pending and interrupts were disabled the service task will + * trigger a force WB. + */ + if (skb->xmit_more && + !netif_xmit_stopped(netdev_get_tx_queue(tx_ring->netdev, + tx_ring->queue_index))) { + tx_ring->flags |= I40E_TXR_FLAGS_LAST_XMIT_MORE_SET; + tail_bump = false; + } else if (!skb->xmit_more && + !netif_xmit_stopped(netdev_get_tx_queue(tx_ring->netdev, + tx_ring->queue_index)) && + (!(tx_ring->flags & I40E_TXR_FLAGS_LAST_XMIT_MORE_SET)) && + (tx_ring->packet_stride < WB_STRIDE) && + (desc_count < WB_STRIDE)) { + tx_ring->packet_stride++; + } else { + tx_ring->packet_stride = 0; + tx_ring->flags &= ~I40E_TXR_FLAGS_LAST_XMIT_MORE_SET; + do_rs = true; + } + if (do_rs) + tx_ring->packet_stride = 0; + + tx_desc->cmd_type_offset_bsz = + build_ctob(td_cmd, td_offset, size, td_tag) | + cpu_to_le64((u64)(do_rs ? I40E_TXD_CMD : + I40E_TX_DESC_CMD_EOP) << + I40E_TXD_QW1_CMD_SHIFT); + /* notify HW of packet */ - if (!skb->xmit_more || - netif_xmit_stopped(netdev_get_tx_queue(tx_ring->netdev, - tx_ring->queue_index))) - writel(i, tx_ring->tail); - else + if (!tail_bump) prefetchw(tx_desc + 1); + if (tail_bump) { + /* Force memory writes to complete before letting h/w + * know there are new descriptors to fetch. (Only + * applicable for weak-ordered memory model archs, + * such as IA-64). + */ + wmb(); + writel(i, tx_ring->tail); + } + return; dma_error: diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index f1385a1989fa..a3978c2b5fc9 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -199,8 +199,6 @@ struct i40e_rx_queue_stats { enum i40e_ring_state_t { __I40E_TX_FDIR_INIT_DONE, __I40E_TX_XPS_INIT_DONE, - __I40E_TX_DETECT_HANG, - __I40E_HANG_CHECK_ARMED, __I40E_RX_PS_ENABLED, __I40E_RX_16BYTE_DESC_ENABLED, }; @@ -211,12 +209,6 @@ enum i40e_ring_state_t { set_bit(__I40E_RX_PS_ENABLED, &(ring)->state) #define clear_ring_ps_enabled(ring) \ clear_bit(__I40E_RX_PS_ENABLED, &(ring)->state) -#define check_for_tx_hang(ring) \ - test_bit(__I40E_TX_DETECT_HANG, &(ring)->state) -#define set_check_for_tx_hang(ring) \ - set_bit(__I40E_TX_DETECT_HANG, &(ring)->state) -#define clear_check_for_tx_hang(ring) \ - clear_bit(__I40E_TX_DETECT_HANG, &(ring)->state) #define ring_is_16byte_desc_enabled(ring) \ test_bit(__I40E_RX_16BYTE_DESC_ENABLED, &(ring)->state) #define set_ring_16byte_desc_enabled(ring) \ @@ -264,10 +256,12 @@ struct i40e_ring { bool ring_active; /* is ring online or not */ bool arm_wb; /* do something to arm write back */ + u8 packet_stride; u16 flags; #define I40E_TXR_FLAGS_WB_ON_ITR BIT(0) #define I40E_TXR_FLAGS_OUTER_UDP_CSUM BIT(1) +#define I40E_TXR_FLAGS_LAST_XMIT_MORE_SET BIT(2) /* stats structs */ struct i40e_queue_stats stats; @@ -326,4 +320,20 @@ int i40e_xmit_descriptor_count(struct sk_buff *skb, struct i40e_ring *tx_ring); int i40e_tx_prepare_vlan_flags(struct sk_buff *skb, struct i40e_ring *tx_ring, u32 *flags); #endif +void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector); +u32 i40e_get_tx_pending(struct i40e_ring *ring); + +/** + * i40e_get_head - Retrieve head from head writeback + * @tx_ring: tx ring to fetch head of + * + * Returns value of Tx ring head based on value stored + * in head write-back location + **/ +static inline u32 i40e_get_head(struct i40e_ring *tx_ring) +{ + void *head = (struct i40e_tx_desc *)tx_ring->desc + tx_ring->count; + + return le32_to_cpu(*(volatile __le32 *)head); +} #endif /* _I40E_TXRX_H_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h index 4842239ee777..af4829065af6 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_type.h +++ b/drivers/net/ethernet/intel/i40e/i40e_type.h @@ -305,12 +305,17 @@ enum i40e_nvmupd_cmd { I40E_NVMUPD_CSUM_CON, I40E_NVMUPD_CSUM_SA, I40E_NVMUPD_CSUM_LCB, + I40E_NVMUPD_STATUS, + I40E_NVMUPD_EXEC_AQ, + I40E_NVMUPD_GET_AQ_RESULT, }; enum i40e_nvmupd_state { I40E_NVMUPD_STATE_INIT, I40E_NVMUPD_STATE_READING, - I40E_NVMUPD_STATE_WRITING + I40E_NVMUPD_STATE_WRITING, + I40E_NVMUPD_STATE_INIT_WAIT, + I40E_NVMUPD_STATE_WRITE_WAIT, }; /* nvm_access definition and its masks/shifts need to be accessible to @@ -329,6 +334,7 @@ enum i40e_nvmupd_state { #define I40E_NVM_SA (I40E_NVM_SNT | I40E_NVM_LCB) #define I40E_NVM_ERA 0x4 #define I40E_NVM_CSUM 0x8 +#define I40E_NVM_EXEC 0xf #define I40E_NVM_ADAPT_SHIFT 16 #define I40E_NVM_ADAPT_MASK (0xffff << I40E_NVM_ADAPT_SHIFT) @@ -492,6 +498,8 @@ struct i40e_hw { /* state of nvm update process */ enum i40e_nvmupd_state nvmupd_state; + struct i40e_aq_desc nvm_wb_desc; + struct i40e_virt_mem nvm_buff; /* HMC info */ struct i40e_hmc_info hmc; /* HMC info struct */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index d99c116032f3..eacce9389962 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -561,7 +561,7 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, enum i40e_vsi_type type) } /* program mac filter */ - ret = i40e_sync_vsi_filters(vsi); + ret = i40e_sync_vsi_filters(vsi, false); if (ret) dev_err(&pf->pdev->dev, "Unable to program ucast filters\n"); @@ -1605,7 +1605,7 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) } /* program the updated filter list */ - if (i40e_sync_vsi_filters(vsi)) + if (i40e_sync_vsi_filters(vsi, false)) dev_err(&pf->pdev->dev, "Unable to program VF MAC filters\n"); error_param: @@ -1656,7 +1656,7 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) I40E_VLAN_ANY, true, false); /* program the updated filter list */ - if (i40e_sync_vsi_filters(vsi)) + if (i40e_sync_vsi_filters(vsi, false)) dev_err(&pf->pdev->dev, "Unable to program VF MAC filters\n"); error_param: @@ -2062,7 +2062,7 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) dev_info(&pf->pdev->dev, "Setting MAC %pM on VF %d\n", mac, vf_id); /* program mac filter */ - if (i40e_sync_vsi_filters(vsi)) { + if (i40e_sync_vsi_filters(vsi, false)) { dev_err(&pf->pdev->dev, "Unable to program ucast filters\n"); ret = -EIO; goto error_param; diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c index 929d47152bf2..5026773a7c26 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c @@ -596,6 +596,9 @@ i40e_status i40evf_shutdown_adminq(struct i40e_hw *hw) /* destroy the locks */ + if (hw->nvm_buff.va) + i40e_free_virt_mem(hw, &hw->nvm_buff); + return ret_code; } @@ -830,6 +833,10 @@ i40e_status i40evf_asq_send_command(struct i40e_hw *hw, i40evf_debug_aq(hw, I40E_DEBUG_AQ_COMMAND, (void *)desc, buff, buff_size); + /* save writeback aq if requested */ + if (details->wb_desc) + *details->wb_desc = *desc_on_ring; + /* update the error if time out occurred */ if ((!cmd_completed) && (!details->async && !details->postpone)) { diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq.h index ef43d68f67b3..547b79b81ffe 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq.h @@ -69,6 +69,7 @@ struct i40e_asq_cmd_details { u16 flags_dis; bool async; bool postpone; + struct i40e_aq_desc *wb_desc; }; #define I40E_ADMINQ_DETAILS(R, i) \ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index 7e91d825c760..830979380466 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -140,65 +140,6 @@ static inline u32 i40e_get_head(struct i40e_ring *tx_ring) return le32_to_cpu(*(volatile __le32 *)head); } -/** - * i40e_get_tx_pending - how many tx descriptors not processed - * @tx_ring: the ring of descriptors - * - * Since there is no access to the ring head register - * in XL710, we need to use our local copies - **/ -static u32 i40e_get_tx_pending(struct i40e_ring *ring) -{ - u32 head, tail; - - head = i40e_get_head(ring); - tail = readl(ring->tail); - - if (head != tail) - return (head < tail) ? - tail - head : (tail + ring->count - head); - - return 0; -} - -/** - * i40e_check_tx_hang - Is there a hang in the Tx queue - * @tx_ring: the ring of descriptors - **/ -static bool i40e_check_tx_hang(struct i40e_ring *tx_ring) -{ - u32 tx_done = tx_ring->stats.packets; - u32 tx_done_old = tx_ring->tx_stats.tx_done_old; - u32 tx_pending = i40e_get_tx_pending(tx_ring); - bool ret = false; - - clear_check_for_tx_hang(tx_ring); - - /* Check for a hung queue, but be thorough. This verifies - * that a transmit has been completed since the previous - * check AND there is at least one packet pending. The - * ARMED bit is set to indicate a potential hang. The - * bit is cleared if a pause frame is received to remove - * false hang detection due to PFC or 802.3x frames. By - * requiring this to fail twice we avoid races with - * PFC clearing the ARMED bit and conditions where we - * run the check_tx_hang logic with a transmit completion - * pending but without time to complete it yet. - */ - if ((tx_done_old == tx_done) && tx_pending) { - /* make sure it is true for two checks in a row */ - ret = test_and_set_bit(__I40E_HANG_CHECK_ARMED, - &tx_ring->state); - } else if (tx_done_old == tx_done && - (tx_pending < I40E_MIN_DESC_PENDING) && (tx_pending > 0)) { - /* update completed stats and disarm the hang check */ - tx_ring->tx_stats.tx_done_old = tx_done; - clear_bit(__I40E_HANG_CHECK_ARMED, &tx_ring->state); - } - - return ret; -} - #define WB_STRIDE 0x3 /** @@ -304,6 +245,10 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget) tx_ring->q_vector->tx.total_bytes += total_bytes; tx_ring->q_vector->tx.total_packets += total_packets; + /* check to see if there are any non-cache aligned descriptors + * waiting to be written back, and kick the hardware to force + * them to be written back in case of napi polling + */ if (budget && !((i & WB_STRIDE) == WB_STRIDE) && !test_bit(__I40E_DOWN, &tx_ring->vsi->state) && @@ -312,29 +257,6 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget) else tx_ring->arm_wb = false; - if (check_for_tx_hang(tx_ring) && i40e_check_tx_hang(tx_ring)) { - /* schedule immediate reset if we believe we hung */ - dev_info(tx_ring->dev, "Detected Tx Unit Hang\n" - " VSI <%d>\n" - " Tx Queue <%d>\n" - " next_to_use <%x>\n" - " next_to_clean <%x>\n", - tx_ring->vsi->seid, - tx_ring->queue_index, - tx_ring->next_to_use, i); - - netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index); - - dev_info(tx_ring->dev, - "tx hang detected on queue %d, resetting adapter\n", - tx_ring->queue_index); - - tx_ring->netdev->netdev_ops->ndo_tx_timeout(tx_ring->netdev); - - /* the adapter is about to reset, no point in enabling stuff */ - return true; - } - netdev_tx_completed_queue(netdev_get_tx_queue(tx_ring->netdev, tx_ring->queue_index), total_packets, total_bytes); @@ -355,16 +277,16 @@ static bool i40e_clean_tx_irq(struct i40e_ring *tx_ring, int budget) } } - return budget > 0; + return !!budget; } /** - * i40e_force_wb -Arm hardware to do a wb on noncache aligned descriptors + * i40evf_force_wb -Arm hardware to do a wb on noncache aligned descriptors * @vsi: the VSI we care about * @q_vector: the vector on which to force writeback * **/ -static void i40e_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) +static void i40evf_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) { u16 flags = q_vector->tx.ring[0].flags; @@ -1385,7 +1307,7 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget) /* If work not completed, return budget and polling will return */ if (!clean_complete) { if (arm_wb) - i40e_force_wb(vsi, q_vector); + i40evf_force_wb(vsi, q_vector); return budget; } diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h index 9a30f5d8c089..d5cb7aca87b4 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h @@ -198,8 +198,6 @@ struct i40e_rx_queue_stats { enum i40e_ring_state_t { __I40E_TX_FDIR_INIT_DONE, __I40E_TX_XPS_INIT_DONE, - __I40E_TX_DETECT_HANG, - __I40E_HANG_CHECK_ARMED, __I40E_RX_PS_ENABLED, __I40E_RX_16BYTE_DESC_ENABLED, }; @@ -210,12 +208,6 @@ enum i40e_ring_state_t { set_bit(__I40E_RX_PS_ENABLED, &(ring)->state) #define clear_ring_ps_enabled(ring) \ clear_bit(__I40E_RX_PS_ENABLED, &(ring)->state) -#define check_for_tx_hang(ring) \ - test_bit(__I40E_TX_DETECT_HANG, &(ring)->state) -#define set_check_for_tx_hang(ring) \ - set_bit(__I40E_TX_DETECT_HANG, &(ring)->state) -#define clear_check_for_tx_hang(ring) \ - clear_bit(__I40E_TX_DETECT_HANG, &(ring)->state) #define ring_is_16byte_desc_enabled(ring) \ test_bit(__I40E_RX_16BYTE_DESC_ENABLED, &(ring)->state) #define set_ring_16byte_desc_enabled(ring) \ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h index 24a2693869a1..ed7166693e5f 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_type.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_type.h @@ -304,12 +304,17 @@ enum i40e_nvmupd_cmd { I40E_NVMUPD_CSUM_CON, I40E_NVMUPD_CSUM_SA, I40E_NVMUPD_CSUM_LCB, + I40E_NVMUPD_STATUS, + I40E_NVMUPD_EXEC_AQ, + I40E_NVMUPD_GET_AQ_RESULT, }; enum i40e_nvmupd_state { I40E_NVMUPD_STATE_INIT, I40E_NVMUPD_STATE_READING, - I40E_NVMUPD_STATE_WRITING + I40E_NVMUPD_STATE_WRITING, + I40E_NVMUPD_STATE_INIT_WAIT, + I40E_NVMUPD_STATE_WRITE_WAIT, }; /* nvm_access definition and its masks/shifts need to be accessible to @@ -328,6 +333,7 @@ enum i40e_nvmupd_state { #define I40E_NVM_SA (I40E_NVM_SNT | I40E_NVM_LCB) #define I40E_NVM_ERA 0x4 #define I40E_NVM_CSUM 0x8 +#define I40E_NVM_EXEC 0xf #define I40E_NVM_ADAPT_SHIFT 16 #define I40E_NVM_ADAPT_MASK (0xffff << I40E_NVM_ADAPT_SHIFT) @@ -486,6 +492,8 @@ struct i40e_hw { /* state of nvm update process */ enum i40e_nvmupd_state nvmupd_state; + struct i40e_aq_desc nvm_wb_desc; + struct i40e_virt_mem nvm_buff; /* HMC info */ struct i40e_hmc_info hmc; /* HMC info struct */ diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index e85849b9ff98..5fc820412fca 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -34,7 +34,7 @@ char i40evf_driver_name[] = "i40evf"; static const char i40evf_driver_string[] = "Intel(R) XL710/X710 Virtual Function Network Driver"; -#define DRV_VERSION "1.3.5" +#define DRV_VERSION "1.3.13" const char i40evf_driver_version[] = DRV_VERSION; static const char i40evf_copyright[] = "Copyright (c) 2013 - 2015 Intel Corporation."; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index e174fbbdba40..ba019fc87fd1 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -2986,6 +2986,9 @@ static int igb_sw_init(struct igb_adapter *adapter) } #endif /* CONFIG_PCI_IOV */ + /* Assume MSI-X interrupts, will be checked during IRQ allocation */ + adapter->flags |= IGB_FLAG_HAS_MSIX; + igb_probe_vfs(adapter); igb_init_queue_configuration(adapter); diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index 686fa7184179..e86d41ed9260 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -2615,6 +2615,7 @@ static const struct net_device_ops igbvf_netdev_ops = { .ndo_poll_controller = igbvf_netpoll, #endif .ndo_set_features = igbvf_set_features, + .ndo_features_check = passthru_features_check, }; /** diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index edf1fb913209..dda0f678339a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -539,8 +539,7 @@ struct hwmon_buff { #define IXGBE_MIN_RSC_ITR 24 #define IXGBE_100K_ITR 40 #define IXGBE_20K_ITR 200 -#define IXGBE_10K_ITR 400 -#define IXGBE_8K_ITR 500 +#define IXGBE_12K_ITR 336 /* ixgbe_test_staterr - tests bits in Rx descriptor status and error fields */ static inline __le32 ixgbe_test_staterr(union ixgbe_adv_rx_desc *rx_desc, @@ -595,6 +594,7 @@ struct ixgbe_mac_addr { /* default to trying for four seconds */ #define IXGBE_TRY_LINK_TIMEOUT (4 * HZ) +#define IXGBE_SFP_POLL_JIFFIES (2 * HZ) /* SFP poll every 2 seconds */ /* board specific private data structure */ struct ixgbe_adapter { @@ -708,6 +708,7 @@ struct ixgbe_adapter { u32 link_speed; bool link_up; + unsigned long sfp_poll_time; unsigned long link_check_timeout; struct timer_list service_timer; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c index dd7062fed61a..a39afcf03e2c 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c @@ -44,9 +44,8 @@ static void ixgbe_disable_tx_laser_multispeed_fiber(struct ixgbe_hw *hw); static void ixgbe_enable_tx_laser_multispeed_fiber(struct ixgbe_hw *hw); static void ixgbe_flap_tx_laser_multispeed_fiber(struct ixgbe_hw *hw); -static s32 ixgbe_setup_mac_link_multispeed_fiber(struct ixgbe_hw *hw, - ixgbe_link_speed speed, - bool autoneg_wait_to_complete); +static void +ixgbe_set_hard_rate_select_speed(struct ixgbe_hw *, ixgbe_link_speed); static s32 ixgbe_setup_mac_link_smartspeed(struct ixgbe_hw *hw, ixgbe_link_speed speed, bool autoneg_wait_to_complete); @@ -109,6 +108,9 @@ static void ixgbe_init_mac_link_ops_82599(struct ixgbe_hw *hw) if (hw->phy.multispeed_fiber) { /* Set up dual speed SFP+ support */ mac->ops.setup_link = &ixgbe_setup_mac_link_multispeed_fiber; + mac->ops.setup_mac_link = ixgbe_setup_mac_link_82599; + mac->ops.set_rate_select_speed = + ixgbe_set_hard_rate_select_speed; } else { if ((mac->ops.get_media_type(hw) == ixgbe_media_type_backplane) && @@ -646,176 +648,32 @@ static void ixgbe_flap_tx_laser_multispeed_fiber(struct ixgbe_hw *hw) } /** - * ixgbe_setup_mac_link_multispeed_fiber - Set MAC link speed - * @hw: pointer to hardware structure - * @speed: new link speed - * @autoneg_wait_to_complete: true when waiting for completion is needed + * ixgbe_set_hard_rate_select_speed - Set module link speed + * @hw: pointer to hardware structure + * @speed: link speed to set * - * Set the link speed in the AUTOC register and restarts link. - **/ -static s32 ixgbe_setup_mac_link_multispeed_fiber(struct ixgbe_hw *hw, - ixgbe_link_speed speed, - bool autoneg_wait_to_complete) + * Set module link speed via RS0/RS1 rate select pins. + */ +static void +ixgbe_set_hard_rate_select_speed(struct ixgbe_hw *hw, ixgbe_link_speed speed) { - s32 status = 0; - ixgbe_link_speed link_speed = IXGBE_LINK_SPEED_UNKNOWN; - ixgbe_link_speed highest_link_speed = IXGBE_LINK_SPEED_UNKNOWN; - u32 speedcnt = 0; u32 esdp_reg = IXGBE_READ_REG(hw, IXGBE_ESDP); - u32 i = 0; - bool link_up = false; - bool autoneg = false; - - /* Mask off requested but non-supported speeds */ - status = hw->mac.ops.get_link_capabilities(hw, &link_speed, - &autoneg); - if (status != 0) - return status; - - speed &= link_speed; - - /* - * Try each speed one by one, highest priority first. We do this in - * software because 10gb fiber doesn't support speed autonegotiation. - */ - if (speed & IXGBE_LINK_SPEED_10GB_FULL) { - speedcnt++; - highest_link_speed = IXGBE_LINK_SPEED_10GB_FULL; - - /* If we already have link at this speed, just jump out */ - status = hw->mac.ops.check_link(hw, &link_speed, &link_up, - false); - if (status != 0) - return status; - - if ((link_speed == IXGBE_LINK_SPEED_10GB_FULL) && link_up) - goto out; - - /* Set the module link speed */ - switch (hw->phy.media_type) { - case ixgbe_media_type_fiber: - esdp_reg |= (IXGBE_ESDP_SDP5_DIR | IXGBE_ESDP_SDP5); - IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp_reg); - IXGBE_WRITE_FLUSH(hw); - break; - case ixgbe_media_type_fiber_qsfp: - /* QSFP module automatically detects MAC link speed */ - break; - default: - hw_dbg(hw, "Unexpected media type.\n"); - break; - } - - /* Allow module to change analog characteristics (1G->10G) */ - msleep(40); - - status = ixgbe_setup_mac_link_82599(hw, - IXGBE_LINK_SPEED_10GB_FULL, - autoneg_wait_to_complete); - if (status != 0) - return status; - - /* Flap the tx laser if it has not already been done */ - if (hw->mac.ops.flap_tx_laser) - hw->mac.ops.flap_tx_laser(hw); - - /* - * Wait for the controller to acquire link. Per IEEE 802.3ap, - * Section 73.10.2, we may have to wait up to 500ms if KR is - * attempted. 82599 uses the same timing for 10g SFI. - */ - for (i = 0; i < 5; i++) { - /* Wait for the link partner to also set speed */ - msleep(100); - - /* If we have link, just jump out */ - status = hw->mac.ops.check_link(hw, &link_speed, - &link_up, false); - if (status != 0) - return status; - - if (link_up) - goto out; - } - } - - if (speed & IXGBE_LINK_SPEED_1GB_FULL) { - speedcnt++; - if (highest_link_speed == IXGBE_LINK_SPEED_UNKNOWN) - highest_link_speed = IXGBE_LINK_SPEED_1GB_FULL; - - /* If we already have link at this speed, just jump out */ - status = hw->mac.ops.check_link(hw, &link_speed, &link_up, - false); - if (status != 0) - return status; - - if ((link_speed == IXGBE_LINK_SPEED_1GB_FULL) && link_up) - goto out; - - /* Set the module link speed */ - switch (hw->phy.media_type) { - case ixgbe_media_type_fiber: - esdp_reg &= ~IXGBE_ESDP_SDP5; - esdp_reg |= IXGBE_ESDP_SDP5_DIR; - IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp_reg); - IXGBE_WRITE_FLUSH(hw); - break; - case ixgbe_media_type_fiber_qsfp: - /* QSFP module automatically detects MAC link speed */ - break; - default: - hw_dbg(hw, "Unexpected media type.\n"); - break; - } - - /* Allow module to change analog characteristics (10G->1G) */ - msleep(40); - - status = ixgbe_setup_mac_link_82599(hw, - IXGBE_LINK_SPEED_1GB_FULL, - autoneg_wait_to_complete); - if (status != 0) - return status; - - /* Flap the tx laser if it has not already been done */ - if (hw->mac.ops.flap_tx_laser) - hw->mac.ops.flap_tx_laser(hw); - /* Wait for the link partner to also set speed */ - msleep(100); - - /* If we have link, just jump out */ - status = hw->mac.ops.check_link(hw, &link_speed, &link_up, - false); - if (status != 0) - return status; - - if (link_up) - goto out; + switch (speed) { + case IXGBE_LINK_SPEED_10GB_FULL: + esdp_reg |= (IXGBE_ESDP_SDP5_DIR | IXGBE_ESDP_SDP5); + break; + case IXGBE_LINK_SPEED_1GB_FULL: + esdp_reg &= ~IXGBE_ESDP_SDP5; + esdp_reg |= IXGBE_ESDP_SDP5_DIR; + break; + default: + hw_dbg(hw, "Invalid fixed module speed\n"); + return; } - /* - * We didn't get link. Configure back to the highest speed we tried, - * (if there was more than one). We call ourselves back with just the - * single highest speed that the user requested. - */ - if (speedcnt > 1) - status = ixgbe_setup_mac_link_multispeed_fiber(hw, - highest_link_speed, - autoneg_wait_to_complete); - -out: - /* Set autoneg_advertised value based on input link speed */ - hw->phy.autoneg_advertised = 0; - - if (speed & IXGBE_LINK_SPEED_10GB_FULL) - hw->phy.autoneg_advertised |= IXGBE_LINK_SPEED_10GB_FULL; - - if (speed & IXGBE_LINK_SPEED_1GB_FULL) - hw->phy.autoneg_advertised |= IXGBE_LINK_SPEED_1GB_FULL; - - return status; + IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp_reg); + IXGBE_WRITE_FLUSH(hw); } /** @@ -1766,6 +1624,16 @@ s32 ixgbe_fdir_set_input_mask_82599(struct ixgbe_hw *hw, IXGBE_WRITE_REG(hw, IXGBE_FDIRTCPM, ~fdirtcpm); IXGBE_WRITE_REG(hw, IXGBE_FDIRUDPM, ~fdirtcpm); + /* also use it for SCTP */ + switch (hw->mac.type) { + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + IXGBE_WRITE_REG(hw, IXGBE_FDIRSCTPM, ~fdirtcpm); + break; + default: + break; + } + /* store source and destination IP masks (big-enian) */ IXGBE_WRITE_REG_BE32(hw, IXGBE_FDIRSIP4M, ~input_mask->formatted.src_ip[0]); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index 3f56a8080118..ce61b36b94f1 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -297,13 +297,13 @@ s32 ixgbe_start_hw_generic(struct ixgbe_hw *hw) /* Setup flow control */ ret_val = ixgbe_setup_fc(hw); - if (!ret_val) - return 0; + if (ret_val) + return ret_val; /* Clear adapter stopped flag */ hw->adapter_stopped = false; - return ret_val; + return 0; } /** @@ -2164,10 +2164,11 @@ s32 ixgbe_fc_enable_generic(struct ixgbe_hw *hw) /* * In order to prevent Tx hangs when the internal Tx * switch is enabled we must set the high water mark - * to the maximum FCRTH value. This allows the Tx - * switch to function even under heavy Rx workloads. + * to the Rx packet buffer size - 24KB. This allows + * the Tx switch to function even under heavy Rx + * workloads. */ - fcrth = IXGBE_READ_REG(hw, IXGBE_RXPBSIZE(i)) - 32; + fcrth = IXGBE_READ_REG(hw, IXGBE_RXPBSIZE(i)) - 24576; } IXGBE_WRITE_REG(hw, IXGBE_FCRTH_82599(i), fcrth); @@ -2476,6 +2477,9 @@ static s32 ixgbe_disable_pcie_master(struct ixgbe_hw *hw) hw_dbg(hw, "GIO Master Disable bit didn't clear - requesting resets\n"); hw->mac.flags |= IXGBE_FLAGS_DOUBLE_RESET_REQUIRED; + if (hw->mac.type >= ixgbe_mac_X550) + return 0; + /* * Before proceeding, make sure that the PCIe block does not have * transactions pending. @@ -3920,3 +3924,213 @@ bool ixgbe_mng_present(struct ixgbe_hw *hw) fwsm &= IXGBE_FWSM_MODE_MASK; return fwsm == IXGBE_FWSM_FW_MODE_PT; } + +/** + * ixgbe_setup_mac_link_multispeed_fiber - Set MAC link speed + * @hw: pointer to hardware structure + * @speed: new link speed + * @autoneg_wait_to_complete: true when waiting for completion is needed + * + * Set the link speed in the MAC and/or PHY register and restarts link. + */ +s32 ixgbe_setup_mac_link_multispeed_fiber(struct ixgbe_hw *hw, + ixgbe_link_speed speed, + bool autoneg_wait_to_complete) +{ + ixgbe_link_speed link_speed = IXGBE_LINK_SPEED_UNKNOWN; + ixgbe_link_speed highest_link_speed = IXGBE_LINK_SPEED_UNKNOWN; + s32 status = 0; + u32 speedcnt = 0; + u32 i = 0; + bool autoneg, link_up = false; + + /* Mask off requested but non-supported speeds */ + status = hw->mac.ops.get_link_capabilities(hw, &link_speed, &autoneg); + if (status) + return status; + + speed &= link_speed; + + /* Try each speed one by one, highest priority first. We do this in + * software because 10Gb fiber doesn't support speed autonegotiation. + */ + if (speed & IXGBE_LINK_SPEED_10GB_FULL) { + speedcnt++; + highest_link_speed = IXGBE_LINK_SPEED_10GB_FULL; + + /* If we already have link at this speed, just jump out */ + status = hw->mac.ops.check_link(hw, &link_speed, &link_up, + false); + if (status) + return status; + + if (link_speed == IXGBE_LINK_SPEED_10GB_FULL && link_up) + goto out; + + /* Set the module link speed */ + switch (hw->phy.media_type) { + case ixgbe_media_type_fiber: + hw->mac.ops.set_rate_select_speed(hw, + IXGBE_LINK_SPEED_10GB_FULL); + break; + case ixgbe_media_type_fiber_qsfp: + /* QSFP module automatically detects MAC link speed */ + break; + default: + hw_dbg(hw, "Unexpected media type\n"); + break; + } + + /* Allow module to change analog characteristics (1G->10G) */ + msleep(40); + + status = hw->mac.ops.setup_mac_link(hw, + IXGBE_LINK_SPEED_10GB_FULL, + autoneg_wait_to_complete); + if (status) + return status; + + /* Flap the Tx laser if it has not already been done */ + if (hw->mac.ops.flap_tx_laser) + hw->mac.ops.flap_tx_laser(hw); + + /* Wait for the controller to acquire link. Per IEEE 802.3ap, + * Section 73.10.2, we may have to wait up to 500ms if KR is + * attempted. 82599 uses the same timing for 10g SFI. + */ + for (i = 0; i < 5; i++) { + /* Wait for the link partner to also set speed */ + msleep(100); + + /* If we have link, just jump out */ + status = hw->mac.ops.check_link(hw, &link_speed, + &link_up, false); + if (status) + return status; + + if (link_up) + goto out; + } + } + + if (speed & IXGBE_LINK_SPEED_1GB_FULL) { + speedcnt++; + if (highest_link_speed == IXGBE_LINK_SPEED_UNKNOWN) + highest_link_speed = IXGBE_LINK_SPEED_1GB_FULL; + + /* If we already have link at this speed, just jump out */ + status = hw->mac.ops.check_link(hw, &link_speed, &link_up, + false); + if (status) + return status; + + if (link_speed == IXGBE_LINK_SPEED_1GB_FULL && link_up) + goto out; + + /* Set the module link speed */ + switch (hw->phy.media_type) { + case ixgbe_media_type_fiber: + hw->mac.ops.set_rate_select_speed(hw, + IXGBE_LINK_SPEED_1GB_FULL); + break; + case ixgbe_media_type_fiber_qsfp: + /* QSFP module automatically detects link speed */ + break; + default: + hw_dbg(hw, "Unexpected media type\n"); + break; + } + + /* Allow module to change analog characteristics (10G->1G) */ + msleep(40); + + status = hw->mac.ops.setup_mac_link(hw, + IXGBE_LINK_SPEED_1GB_FULL, + autoneg_wait_to_complete); + if (status) + return status; + + /* Flap the Tx laser if it has not already been done */ + if (hw->mac.ops.flap_tx_laser) + hw->mac.ops.flap_tx_laser(hw); + + /* Wait for the link partner to also set speed */ + msleep(100); + + /* If we have link, just jump out */ + status = hw->mac.ops.check_link(hw, &link_speed, &link_up, + false); + if (status) + return status; + + if (link_up) + goto out; + } + + /* We didn't get link. Configure back to the highest speed we tried, + * (if there was more than one). We call ourselves back with just the + * single highest speed that the user requested. + */ + if (speedcnt > 1) + status = ixgbe_setup_mac_link_multispeed_fiber(hw, + highest_link_speed, + autoneg_wait_to_complete); + +out: + /* Set autoneg_advertised value based on input link speed */ + hw->phy.autoneg_advertised = 0; + + if (speed & IXGBE_LINK_SPEED_10GB_FULL) + hw->phy.autoneg_advertised |= IXGBE_LINK_SPEED_10GB_FULL; + + if (speed & IXGBE_LINK_SPEED_1GB_FULL) + hw->phy.autoneg_advertised |= IXGBE_LINK_SPEED_1GB_FULL; + + return status; +} + +/** + * ixgbe_set_soft_rate_select_speed - Set module link speed + * @hw: pointer to hardware structure + * @speed: link speed to set + * + * Set module link speed via the soft rate select. + */ +void ixgbe_set_soft_rate_select_speed(struct ixgbe_hw *hw, + ixgbe_link_speed speed) +{ + s32 status; + u8 rs, eeprom_data; + + switch (speed) { + case IXGBE_LINK_SPEED_10GB_FULL: + /* one bit mask same as setting on */ + rs = IXGBE_SFF_SOFT_RS_SELECT_10G; + break; + case IXGBE_LINK_SPEED_1GB_FULL: + rs = IXGBE_SFF_SOFT_RS_SELECT_1G; + break; + default: + hw_dbg(hw, "Invalid fixed module speed\n"); + return; + } + + /* Set RS0 */ + status = hw->phy.ops.read_i2c_byte(hw, IXGBE_SFF_SFF_8472_OSCB, + IXGBE_I2C_EEPROM_DEV_ADDR2, + &eeprom_data); + if (status) { + hw_dbg(hw, "Failed to read Rx Rate Select RS0\n"); + return; + } + + eeprom_data = (eeprom_data & ~IXGBE_SFF_SOFT_RS_SELECT_MASK) | rs; + + status = hw->phy.ops.write_i2c_byte(hw, IXGBE_SFF_SFF_8472_OSCB, + IXGBE_I2C_EEPROM_DEV_ADDR2, + eeprom_data); + if (status) { + hw_dbg(hw, "Failed to write Rx Rate Select RS0\n"); + return; + } +} diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h index 2f779f35dc4f..a0044e4a8b90 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h @@ -135,6 +135,11 @@ s32 ixgbe_get_thermal_sensor_data_generic(struct ixgbe_hw *hw); s32 ixgbe_init_thermal_sensor_thresh_generic(struct ixgbe_hw *hw); void ixgbe_disable_rx_generic(struct ixgbe_hw *hw); void ixgbe_enable_rx_generic(struct ixgbe_hw *hw); +s32 ixgbe_setup_mac_link_multispeed_fiber(struct ixgbe_hw *hw, + ixgbe_link_speed speed, + bool autoneg_wait_to_complete); +void ixgbe_set_soft_rate_select_speed(struct ixgbe_hw *hw, + ixgbe_link_speed speed); #define IXGBE_FAILED_READ_REG 0xffffffffU #define IXGBE_FAILED_READ_CFG_DWORD 0xffffffffU diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.c index 3b932fe64ab6..23277ab153b6 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.c @@ -259,7 +259,13 @@ s32 ixgbe_dcb_config_pfc_82599(struct ixgbe_hw *hw, u8 pfc_en, u8 *prio_tc) fcrtl = (hw->fc.low_water[i] << 10) | IXGBE_FCRTL_XONE; IXGBE_WRITE_REG(hw, IXGBE_FCRTL_82599(i), fcrtl); } else { - reg = IXGBE_READ_REG(hw, IXGBE_RXPBSIZE(i)) - 32; + /* In order to prevent Tx hangs when the internal Tx + * switch is enabled we must set the high water mark + * to the Rx packet buffer size - 24KB. This allows + * the Tx switch to function even under heavy Rx + * workloads. + */ + reg = IXGBE_READ_REG(hw, IXGBE_RXPBSIZE(i)) - 24576; IXGBE_WRITE_REG(hw, IXGBE_FCRTL_82599(i), 0); } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index ab2edc8e7703..94c4912b2330 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -2286,7 +2286,7 @@ static int ixgbe_set_coalesce(struct net_device *netdev, adapter->tx_itr_setting = ec->tx_coalesce_usecs; if (adapter->tx_itr_setting == 1) - tx_itr_param = IXGBE_10K_ITR; + tx_itr_param = IXGBE_12K_ITR; else tx_itr_param = adapter->tx_itr_setting; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c index 68e1e757ecef..f3168bcc7d87 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c @@ -866,7 +866,7 @@ static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter, if (txr_count && !rxr_count) { /* tx only vector */ if (adapter->tx_itr_setting == 1) - q_vector->itr = IXGBE_10K_ITR; + q_vector->itr = IXGBE_12K_ITR; else q_vector->itr = adapter->tx_itr_setting; } else { diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 63b2cfe9416b..191003901adb 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -79,7 +79,7 @@ char ixgbe_default_device_descr[] = static char ixgbe_default_device_descr[] = "Intel(R) 10 Gigabit Network Connection"; #endif -#define DRV_VERSION "4.0.1-k" +#define DRV_VERSION "4.2.1-k" const char ixgbe_driver_version[] = DRV_VERSION; static const char ixgbe_copyright[] = "Copyright (c) 1999-2015 Intel Corporation."; @@ -137,6 +137,7 @@ static const struct pci_device_id ixgbe_pci_tbl[] = { {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_KX4), board_X550EM_x}, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_KR), board_X550EM_x}, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_10G_T), board_X550EM_x}, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_SFP), board_X550EM_x}, /* required last entry */ {0, } }; @@ -1244,9 +1245,12 @@ static void ixgbe_update_tx_dca(struct ixgbe_adapter *adapter, int cpu) { struct ixgbe_hw *hw = &adapter->hw; - u32 txctrl = dca3_get_tag(tx_ring->dev, cpu); + u32 txctrl = 0; u16 reg_offset; + if (adapter->flags & IXGBE_FLAG_DCA_ENABLED) + txctrl = dca3_get_tag(tx_ring->dev, cpu); + switch (hw->mac.type) { case ixgbe_mac_82598EB: reg_offset = IXGBE_DCA_TXCTRL(tx_ring->reg_idx); @@ -1278,9 +1282,11 @@ static void ixgbe_update_rx_dca(struct ixgbe_adapter *adapter, int cpu) { struct ixgbe_hw *hw = &adapter->hw; - u32 rxctrl = dca3_get_tag(rx_ring->dev, cpu); + u32 rxctrl = 0; u8 reg_idx = rx_ring->reg_idx; + if (adapter->flags & IXGBE_FLAG_DCA_ENABLED) + rxctrl = dca3_get_tag(rx_ring->dev, cpu); switch (hw->mac.type) { case ixgbe_mac_82599EB: @@ -1297,6 +1303,7 @@ static void ixgbe_update_rx_dca(struct ixgbe_adapter *adapter, * which will cause the DCA tag to be cleared. */ rxctrl |= IXGBE_DCA_RXCTRL_DESC_RRO_EN | + IXGBE_DCA_RXCTRL_DATA_DCA_EN | IXGBE_DCA_RXCTRL_DESC_DCA_EN; IXGBE_WRITE_REG(hw, IXGBE_DCA_RXCTRL(reg_idx), rxctrl); @@ -1326,11 +1333,13 @@ static void ixgbe_setup_dca(struct ixgbe_adapter *adapter) { int i; - if (!(adapter->flags & IXGBE_FLAG_DCA_ENABLED)) - return; - /* always use CB2 mode, difference is masked in the CB driver */ - IXGBE_WRITE_REG(&adapter->hw, IXGBE_DCA_CTRL, 2); + if (adapter->flags & IXGBE_FLAG_DCA_ENABLED) + IXGBE_WRITE_REG(&adapter->hw, IXGBE_DCA_CTRL, + IXGBE_DCA_CTRL_DCA_MODE_CB2); + else + IXGBE_WRITE_REG(&adapter->hw, IXGBE_DCA_CTRL, + IXGBE_DCA_CTRL_DCA_DISABLE); for (i = 0; i < adapter->num_q_vectors; i++) { adapter->q_vector[i]->cpu = -1; @@ -1353,7 +1362,8 @@ static int __ixgbe_notify_dca(struct device *dev, void *data) break; if (dca_add_requester(dev) == 0) { adapter->flags |= IXGBE_FLAG_DCA_ENABLED; - ixgbe_setup_dca(adapter); + IXGBE_WRITE_REG(&adapter->hw, IXGBE_DCA_CTRL, + IXGBE_DCA_CTRL_DCA_MODE_CB2); break; } /* Fall Through since DCA is disabled. */ @@ -1361,7 +1371,8 @@ static int __ixgbe_notify_dca(struct device *dev, void *data) if (adapter->flags & IXGBE_FLAG_DCA_ENABLED) { dca_remove_requester(dev); adapter->flags &= ~IXGBE_FLAG_DCA_ENABLED; - IXGBE_WRITE_REG(&adapter->hw, IXGBE_DCA_CTRL, 1); + IXGBE_WRITE_REG(&adapter->hw, IXGBE_DCA_CTRL, + IXGBE_DCA_CTRL_DCA_DISABLE); } break; } @@ -2261,7 +2272,7 @@ static void ixgbe_update_itr(struct ixgbe_q_vector *q_vector, /* simple throttlerate management * 0-10MB/s lowest (100000 ints/s) * 10-20MB/s low (20000 ints/s) - * 20-1249MB/s bulk (8000 ints/s) + * 20-1249MB/s bulk (12000 ints/s) */ /* what was last interrupt timeslice? */ timepassed_us = q_vector->itr >> 2; @@ -2350,7 +2361,7 @@ static void ixgbe_set_itr(struct ixgbe_q_vector *q_vector) new_itr = IXGBE_20K_ITR; break; case bulk_latency: - new_itr = IXGBE_8K_ITR; + new_itr = IXGBE_12K_ITR; break; default: break; @@ -2495,17 +2506,27 @@ static inline bool ixgbe_is_sfp(struct ixgbe_hw *hw) static void ixgbe_check_sfp_event(struct ixgbe_adapter *adapter, u32 eicr) { struct ixgbe_hw *hw = &adapter->hw; + u32 eicr_mask = IXGBE_EICR_GPI_SDP2(hw); + + if (!ixgbe_is_sfp(hw)) + return; + + /* Later MAC's use different SDP */ + if (hw->mac.type >= ixgbe_mac_X540) + eicr_mask = IXGBE_EICR_GPI_SDP0_X540; - if (eicr & IXGBE_EICR_GPI_SDP2(hw)) { + if (eicr & eicr_mask) { /* Clear the interrupt */ - IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_GPI_SDP2(hw)); + IXGBE_WRITE_REG(hw, IXGBE_EICR, eicr_mask); if (!test_bit(__IXGBE_DOWN, &adapter->state)) { adapter->flags2 |= IXGBE_FLAG2_SFP_NEEDS_RESET; + adapter->sfp_poll_time = 0; ixgbe_service_event_schedule(adapter); } } - if (eicr & IXGBE_EICR_GPI_SDP1(hw)) { + if (adapter->hw.mac.type == ixgbe_mac_82599EB && + (eicr & IXGBE_EICR_GPI_SDP1(hw))) { /* Clear the interrupt */ IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_GPI_SDP1(hw)); if (!test_bit(__IXGBE_DOWN, &adapter->state)) { @@ -2622,6 +2643,8 @@ static inline void ixgbe_irq_enable(struct ixgbe_adapter *adapter, bool queues, case ixgbe_mac_X540: case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: + if (adapter->hw.device_id == IXGBE_DEV_ID_X550EM_X_SFP) + mask |= IXGBE_EIMS_GPI_SDP0(&adapter->hw); if (adapter->hw.phy.type == ixgbe_phy_x550em_ext_t) mask |= IXGBE_EICR_GPI_SDP0_X540; mask |= IXGBE_EIMS_ECC; @@ -3777,8 +3800,6 @@ static void ixgbe_setup_rdrxctl(struct ixgbe_adapter *adapter) u32 rdrxctl = IXGBE_READ_REG(hw, IXGBE_RDRXCTL); switch (hw->mac.type) { - case ixgbe_mac_X550: - case ixgbe_mac_X550EM_x: case ixgbe_mac_82598EB: /* * For VMDq support of different descriptor types or @@ -3792,6 +3813,11 @@ static void ixgbe_setup_rdrxctl(struct ixgbe_adapter *adapter) */ rdrxctl |= IXGBE_RDRXCTL_MVMEN; break; + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + if (adapter->num_vfs) + rdrxctl |= IXGBE_RDRXCTL_PSP; + /* fall through for older HW */ case ixgbe_mac_82599EB: case ixgbe_mac_X540: /* Disable RSC for ACK packets */ @@ -4767,6 +4793,12 @@ static void ixgbe_configure(struct ixgbe_adapter *adapter) break; } +#ifdef CONFIG_IXGBE_DCA + /* configure DCA */ + if (adapter->flags & IXGBE_FLAG_DCA_CAPABLE) + ixgbe_setup_dca(adapter); +#endif /* CONFIG_IXGBE_DCA */ + #ifdef IXGBE_FCOE /* configure FCoE L2 filters, redirection table, and Rx control */ ixgbe_configure_fcoe(adapter); @@ -4793,6 +4825,7 @@ static void ixgbe_sfp_link_config(struct ixgbe_adapter *adapter) adapter->flags2 |= IXGBE_FLAG2_SEARCH_FOR_SFP; adapter->flags2 |= IXGBE_FLAG2_SFP_NEEDS_RESET; + adapter->sfp_poll_time = 0; } /** @@ -4883,9 +4916,6 @@ static void ixgbe_setup_gpie(struct ixgbe_adapter *adapter) case ixgbe_mac_82599EB: gpie |= IXGBE_SDP0_GPIEN_8259X; break; - case ixgbe_mac_X540: - gpie |= IXGBE_EIMS_TS; - break; default: break; } @@ -4895,9 +4925,15 @@ static void ixgbe_setup_gpie(struct ixgbe_adapter *adapter) if (adapter->flags & IXGBE_FLAG_FAN_FAIL_CAPABLE) gpie |= IXGBE_SDP1_GPIEN(hw); - if (hw->mac.type == ixgbe_mac_82599EB) { - gpie |= IXGBE_SDP1_GPIEN_8259X; - gpie |= IXGBE_SDP2_GPIEN_8259X; + switch (hw->mac.type) { + case ixgbe_mac_82599EB: + gpie |= IXGBE_SDP1_GPIEN_8259X | IXGBE_SDP2_GPIEN_8259X; + break; + case ixgbe_mac_X550EM_x: + gpie |= IXGBE_SDP0_GPIEN_X540; + break; + default: + break; } IXGBE_WRITE_REG(hw, IXGBE_GPIE, gpie); @@ -5220,11 +5256,6 @@ void ixgbe_down(struct ixgbe_adapter *adapter) ixgbe_clean_all_tx_rings(adapter); ixgbe_clean_all_rx_rings(adapter); - -#ifdef CONFIG_IXGBE_DCA - /* since we reset the hardware DCA settings were cleared */ - ixgbe_setup_dca(adapter); -#endif } /** @@ -6692,10 +6723,16 @@ static void ixgbe_sfp_detection_subtask(struct ixgbe_adapter *adapter) !(adapter->flags2 & IXGBE_FLAG2_SFP_NEEDS_RESET)) return; + if (adapter->sfp_poll_time && + time_after(adapter->sfp_poll_time, jiffies)) + return; /* If not yet time to poll for SFP */ + /* someone else is in init, wait until next service event */ if (test_and_set_bit(__IXGBE_IN_SFP_INIT, &adapter->state)) return; + adapter->sfp_poll_time = jiffies + IXGBE_SFP_POLL_JIFFIES - 1; + err = hw->phy.ops.identify_sfp(hw); if (err == IXGBE_ERR_SFP_NOT_SUPPORTED) goto sfp_out; @@ -8695,8 +8732,7 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) hw->phy.reset_if_overtemp = true; err = hw->mac.ops.reset_hw(hw); hw->phy.reset_if_overtemp = false; - if (err == IXGBE_ERR_SFP_NOT_PRESENT && - hw->mac.type == ixgbe_mac_82598EB) { + if (err == IXGBE_ERR_SFP_NOT_PRESENT) { err = 0; } else if (err == IXGBE_ERR_SFP_NOT_SUPPORTED) { e_dev_err("failed to load because an unsupported SFP+ or QSFP module type was detected.\n"); @@ -9008,7 +9044,8 @@ static void ixgbe_remove(struct pci_dev *pdev) if (adapter->flags & IXGBE_FLAG_DCA_ENABLED) { adapter->flags &= ~IXGBE_FLAG_DCA_ENABLED; dca_remove_requester(&pdev->dev); - IXGBE_WRITE_REG(&adapter->hw, IXGBE_DCA_CTRL, 1); + IXGBE_WRITE_REG(&adapter->hw, IXGBE_DCA_CTRL, + IXGBE_DCA_CTRL_DCA_DISABLE); } #endif @@ -9019,12 +9056,12 @@ static void ixgbe_remove(struct pci_dev *pdev) /* remove the added san mac */ ixgbe_del_sanmac_netdev(netdev); - if (netdev->reg_state == NETREG_REGISTERED) - unregister_netdev(netdev); - #ifdef CONFIG_PCI_IOV ixgbe_disable_sriov(adapter); #endif + if (netdev->reg_state == NETREG_REGISTERED) + unregister_netdev(netdev); + ixgbe_clear_interrupt_scheme(adapter); ixgbe_release_hw_control(adapter); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c index 597d0b1c2370..fb8673d63806 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c @@ -100,16 +100,17 @@ static u8 ixgbe_ones_comp_byte_add(u8 add1, u8 add2) } /** - * ixgbe_read_i2c_combined_generic - Perform I2C read combined operation + * ixgbe_read_i2c_combined_generic_int - Perform I2C read combined operation * @hw: pointer to the hardware structure * @addr: I2C bus address to read from * @reg: I2C device register to read from * @val: pointer to location to receive read value + * @lock: true if to take and release semaphore * * Returns an error code on error. - **/ -s32 ixgbe_read_i2c_combined_generic(struct ixgbe_hw *hw, u8 addr, - u16 reg, u16 *val) + */ +static s32 ixgbe_read_i2c_combined_generic_int(struct ixgbe_hw *hw, u8 addr, + u16 reg, u16 *val, bool lock) { u32 swfw_mask = hw->phy.phy_semaphore_mask; int max_retry = 10; @@ -124,7 +125,7 @@ s32 ixgbe_read_i2c_combined_generic(struct ixgbe_hw *hw, u8 addr, csum = ixgbe_ones_comp_byte_add(reg_high, reg & 0xFF); csum = ~csum; do { - if (hw->mac.ops.acquire_swfw_sync(hw, swfw_mask)) + if (lock && hw->mac.ops.acquire_swfw_sync(hw, swfw_mask)) return IXGBE_ERR_SWFW_SYNC; ixgbe_i2c_start(hw); /* Device Address and write indication */ @@ -157,13 +158,15 @@ s32 ixgbe_read_i2c_combined_generic(struct ixgbe_hw *hw, u8 addr, if (ixgbe_clock_out_i2c_bit(hw, false)) goto fail; ixgbe_i2c_stop(hw); - hw->mac.ops.release_swfw_sync(hw, swfw_mask); + if (lock) + hw->mac.ops.release_swfw_sync(hw, swfw_mask); *val = (high_bits << 8) | low_bits; return 0; fail: ixgbe_i2c_bus_clear(hw); - hw->mac.ops.release_swfw_sync(hw, swfw_mask); + if (lock) + hw->mac.ops.release_swfw_sync(hw, swfw_mask); retry++; if (retry < max_retry) hw_dbg(hw, "I2C byte read combined error - Retry.\n"); @@ -175,17 +178,49 @@ fail: } /** - * ixgbe_write_i2c_combined_generic - Perform I2C write combined operation + * ixgbe_read_i2c_combined_generic - Perform I2C read combined operation + * @hw: pointer to the hardware structure + * @addr: I2C bus address to read from + * @reg: I2C device register to read from + * @val: pointer to location to receive read value + * + * Returns an error code on error. + */ +s32 ixgbe_read_i2c_combined_generic(struct ixgbe_hw *hw, u8 addr, + u16 reg, u16 *val) +{ + return ixgbe_read_i2c_combined_generic_int(hw, addr, reg, val, true); +} + +/** + * ixgbe_read_i2c_combined_generic_unlocked - Unlocked I2C read combined + * @hw: pointer to the hardware structure + * @addr: I2C bus address to read from + * @reg: I2C device register to read from + * @val: pointer to location to receive read value + * + * Returns an error code on error. + */ +s32 ixgbe_read_i2c_combined_generic_unlocked(struct ixgbe_hw *hw, u8 addr, + u16 reg, u16 *val) +{ + return ixgbe_read_i2c_combined_generic_int(hw, addr, reg, val, false); +} + +/** + * ixgbe_write_i2c_combined_generic_int - Perform I2C write combined operation * @hw: pointer to the hardware structure * @addr: I2C bus address to write to * @reg: I2C device register to write to * @val: value to write + * @lock: true if to take and release semaphore * * Returns an error code on error. - **/ -s32 ixgbe_write_i2c_combined_generic(struct ixgbe_hw *hw, - u8 addr, u16 reg, u16 val) + */ +static s32 ixgbe_write_i2c_combined_generic_int(struct ixgbe_hw *hw, u8 addr, + u16 reg, u16 val, bool lock) { + u32 swfw_mask = hw->phy.phy_semaphore_mask; int max_retry = 1; int retry = 0; u8 reg_high; @@ -197,6 +232,8 @@ s32 ixgbe_write_i2c_combined_generic(struct ixgbe_hw *hw, csum = ixgbe_ones_comp_byte_add(csum, val & 0xFF); csum = ~csum; do { + if (lock && hw->mac.ops.acquire_swfw_sync(hw, swfw_mask)) + return IXGBE_ERR_SWFW_SYNC; ixgbe_i2c_start(hw); /* Device Address and write indication */ if (ixgbe_out_i2c_byte_ack(hw, addr)) @@ -217,10 +254,14 @@ s32 ixgbe_write_i2c_combined_generic(struct ixgbe_hw *hw, if (ixgbe_out_i2c_byte_ack(hw, csum)) goto fail; ixgbe_i2c_stop(hw); + if (lock) + hw->mac.ops.release_swfw_sync(hw, swfw_mask); return 0; fail: ixgbe_i2c_bus_clear(hw); + if (lock) + hw->mac.ops.release_swfw_sync(hw, swfw_mask); retry++; if (retry < max_retry) hw_dbg(hw, "I2C byte write combined error - Retry.\n"); @@ -232,6 +273,36 @@ fail: } /** + * ixgbe_write_i2c_combined_generic - Perform I2C write combined operation + * @hw: pointer to the hardware structure + * @addr: I2C bus address to write to + * @reg: I2C device register to write to + * @val: value to write + * + * Returns an error code on error. + */ +s32 ixgbe_write_i2c_combined_generic(struct ixgbe_hw *hw, + u8 addr, u16 reg, u16 val) +{ + return ixgbe_write_i2c_combined_generic_int(hw, addr, reg, val, true); +} + +/** + * ixgbe_write_i2c_combined_generic_unlocked - Unlocked I2C write combined + * @hw: pointer to the hardware structure + * @addr: I2C bus address to write to + * @reg: I2C device register to write to + * @val: value to write + * + * Returns an error code on error. + */ +s32 ixgbe_write_i2c_combined_generic_unlocked(struct ixgbe_hw *hw, + u8 addr, u16 reg, u16 val) +{ + return ixgbe_write_i2c_combined_generic_int(hw, addr, reg, val, false); +} + +/** * ixgbe_identify_phy_generic - Get physical layer module * @hw: pointer to hardware structure * @@ -1100,6 +1171,9 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) return IXGBE_ERR_SFP_NOT_PRESENT; } + /* LAN ID is needed for sfp_type determination */ + hw->mac.ops.set_lan_id(hw); + status = hw->phy.ops.read_i2c_eeprom(hw, IXGBE_SFF_IDENTIFIER, &identifier); @@ -1107,9 +1181,6 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) if (status) goto err_read_i2c_eeprom; - /* LAN ID is needed for sfp_type determination */ - hw->mac.ops.set_lan_id(hw); - if (identifier != IXGBE_SFF_IDENTIFIER_SFP) { hw->phy.type = ixgbe_phy_sfp_unsupported; return IXGBE_ERR_SFP_NOT_SUPPORTED; @@ -1159,7 +1230,7 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) hw->phy.sfp_type = ixgbe_sfp_type_lr; else hw->phy.sfp_type = ixgbe_sfp_type_unknown; - } else if (hw->mac.type == ixgbe_mac_82599EB) { + } else { if (cable_tech & IXGBE_SFF_DA_PASSIVE_CABLE) { if (hw->bus.lan_id == 0) hw->phy.sfp_type = @@ -1660,26 +1731,46 @@ s32 ixgbe_write_i2c_eeprom_generic(struct ixgbe_hw *hw, u8 byte_offset, } /** - * ixgbe_read_i2c_byte_generic - Reads 8 bit word over I2C + * ixgbe_is_sfp_probe - Returns true if SFP is being detected + * @hw: pointer to hardware structure + * @offset: eeprom offset to be read + * @addr: I2C address to be read + */ +static bool ixgbe_is_sfp_probe(struct ixgbe_hw *hw, u8 offset, u8 addr) +{ + if (addr == IXGBE_I2C_EEPROM_DEV_ADDR && + offset == IXGBE_SFF_IDENTIFIER && + hw->phy.sfp_type == ixgbe_sfp_type_not_present) + return true; + return false; +} + +/** + * ixgbe_read_i2c_byte_generic_int - Reads 8 bit word over I2C * @hw: pointer to hardware structure * @byte_offset: byte offset to read * @data: value read + * @lock: true if to take and release semaphore * * Performs byte read operation to SFP module's EEPROM over I2C interface at * a specified device address. - **/ -s32 ixgbe_read_i2c_byte_generic(struct ixgbe_hw *hw, u8 byte_offset, - u8 dev_addr, u8 *data) + */ +static s32 ixgbe_read_i2c_byte_generic_int(struct ixgbe_hw *hw, u8 byte_offset, + u8 dev_addr, u8 *data, bool lock) { s32 status; u32 max_retry = 10; u32 retry = 0; u32 swfw_mask = hw->phy.phy_semaphore_mask; bool nack = true; + + if (ixgbe_is_sfp_probe(hw, byte_offset, dev_addr)) + max_retry = IXGBE_SFP_DETECT_RETRIES; + *data = 0; do { - if (hw->mac.ops.acquire_swfw_sync(hw, swfw_mask)) + if (lock && hw->mac.ops.acquire_swfw_sync(hw, swfw_mask)) return IXGBE_ERR_SWFW_SYNC; ixgbe_i2c_start(hw); @@ -1721,12 +1812,16 @@ s32 ixgbe_read_i2c_byte_generic(struct ixgbe_hw *hw, u8 byte_offset, goto fail; ixgbe_i2c_stop(hw); - break; + if (lock) + hw->mac.ops.release_swfw_sync(hw, swfw_mask); + return 0; fail: ixgbe_i2c_bus_clear(hw); - hw->mac.ops.release_swfw_sync(hw, swfw_mask); - msleep(100); + if (lock) { + hw->mac.ops.release_swfw_sync(hw, swfw_mask); + msleep(100); + } retry++; if (retry < max_retry) hw_dbg(hw, "I2C byte read error - Retrying.\n"); @@ -1735,29 +1830,60 @@ fail: } while (retry < max_retry); - hw->mac.ops.release_swfw_sync(hw, swfw_mask); - return status; } /** - * ixgbe_write_i2c_byte_generic - Writes 8 bit word over I2C + * ixgbe_read_i2c_byte_generic - Reads 8 bit word over I2C + * @hw: pointer to hardware structure + * @byte_offset: byte offset to read + * @data: value read + * + * Performs byte read operation to SFP module's EEPROM over I2C interface at + * a specified device address. + */ +s32 ixgbe_read_i2c_byte_generic(struct ixgbe_hw *hw, u8 byte_offset, + u8 dev_addr, u8 *data) +{ + return ixgbe_read_i2c_byte_generic_int(hw, byte_offset, dev_addr, + data, true); +} + +/** + * ixgbe_read_i2c_byte_generic_unlocked - Reads 8 bit word over I2C + * @hw: pointer to hardware structure + * @byte_offset: byte offset to read + * @data: value read + * + * Performs byte read operation to SFP module's EEPROM over I2C interface at + * a specified device address. + */ +s32 ixgbe_read_i2c_byte_generic_unlocked(struct ixgbe_hw *hw, u8 byte_offset, + u8 dev_addr, u8 *data) +{ + return ixgbe_read_i2c_byte_generic_int(hw, byte_offset, dev_addr, + data, false); +} + +/** + * ixgbe_write_i2c_byte_generic_int - Writes 8 bit word over I2C * @hw: pointer to hardware structure * @byte_offset: byte offset to write * @data: value to write + * @lock: true if to take and release semaphore * * Performs byte write operation to SFP module's EEPROM over I2C interface at * a specified device address. - **/ -s32 ixgbe_write_i2c_byte_generic(struct ixgbe_hw *hw, u8 byte_offset, - u8 dev_addr, u8 data) + */ +static s32 ixgbe_write_i2c_byte_generic_int(struct ixgbe_hw *hw, u8 byte_offset, + u8 dev_addr, u8 data, bool lock) { s32 status; u32 max_retry = 1; u32 retry = 0; u32 swfw_mask = hw->phy.phy_semaphore_mask; - if (hw->mac.ops.acquire_swfw_sync(hw, swfw_mask)) + if (lock && hw->mac.ops.acquire_swfw_sync(hw, swfw_mask)) return IXGBE_ERR_SWFW_SYNC; do { @@ -1788,7 +1914,9 @@ s32 ixgbe_write_i2c_byte_generic(struct ixgbe_hw *hw, u8 byte_offset, goto fail; ixgbe_i2c_stop(hw); - break; + if (lock) + hw->mac.ops.release_swfw_sync(hw, swfw_mask); + return 0; fail: ixgbe_i2c_bus_clear(hw); @@ -1799,21 +1927,57 @@ fail: hw_dbg(hw, "I2C byte write error.\n"); } while (retry < max_retry); - hw->mac.ops.release_swfw_sync(hw, swfw_mask); + if (lock) + hw->mac.ops.release_swfw_sync(hw, swfw_mask); return status; } /** + * ixgbe_write_i2c_byte_generic - Writes 8 bit word over I2C + * @hw: pointer to hardware structure + * @byte_offset: byte offset to write + * @data: value to write + * + * Performs byte write operation to SFP module's EEPROM over I2C interface at + * a specified device address. + */ +s32 ixgbe_write_i2c_byte_generic(struct ixgbe_hw *hw, u8 byte_offset, + u8 dev_addr, u8 data) +{ + return ixgbe_write_i2c_byte_generic_int(hw, byte_offset, dev_addr, + data, true); +} + +/** + * ixgbe_write_i2c_byte_generic_unlocked - Writes 8 bit word over I2C + * @hw: pointer to hardware structure + * @byte_offset: byte offset to write + * @data: value to write + * + * Performs byte write operation to SFP module's EEPROM over I2C interface at + * a specified device address. + */ +s32 ixgbe_write_i2c_byte_generic_unlocked(struct ixgbe_hw *hw, u8 byte_offset, + u8 dev_addr, u8 data) +{ + return ixgbe_write_i2c_byte_generic_int(hw, byte_offset, dev_addr, + data, false); +} + +/** * ixgbe_i2c_start - Sets I2C start condition * @hw: pointer to hardware structure * * Sets I2C start condition (High -> Low on SDA while SCL is High) + * Set bit-bang mode on X550 hardware. **/ static void ixgbe_i2c_start(struct ixgbe_hw *hw) { u32 i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL(hw)); + i2cctl |= IXGBE_I2C_BB_EN(hw); + /* Start condition must begin with data and clock high */ ixgbe_set_i2c_data(hw, &i2cctl, 1); ixgbe_raise_i2c_clk(hw, &i2cctl); @@ -1838,10 +2002,15 @@ static void ixgbe_i2c_start(struct ixgbe_hw *hw) * @hw: pointer to hardware structure * * Sets I2C stop condition (Low -> High on SDA while SCL is High) + * Disables bit-bang mode and negates data output enable on X550 + * hardware. **/ static void ixgbe_i2c_stop(struct ixgbe_hw *hw) { u32 i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL(hw)); + u32 data_oe_bit = IXGBE_I2C_DATA_OE_N_EN(hw); + u32 clk_oe_bit = IXGBE_I2C_CLK_OE_N_EN(hw); + u32 bb_en_bit = IXGBE_I2C_BB_EN(hw); /* Stop condition must begin with data low and clock high */ ixgbe_set_i2c_data(hw, &i2cctl, 0); @@ -1854,6 +2023,13 @@ static void ixgbe_i2c_stop(struct ixgbe_hw *hw) /* bus free time between stop and start (4.7us)*/ udelay(IXGBE_I2C_T_BUF); + + if (bb_en_bit || data_oe_bit || clk_oe_bit) { + i2cctl &= ~bb_en_bit; + i2cctl |= data_oe_bit | clk_oe_bit; + IXGBE_WRITE_REG(hw, IXGBE_I2CCTL(hw), i2cctl); + IXGBE_WRITE_FLUSH(hw); + } } /** @@ -1868,6 +2044,7 @@ static s32 ixgbe_clock_in_i2c_byte(struct ixgbe_hw *hw, u8 *data) s32 i; bool bit = false; + *data = 0; for (i = 7; i >= 0; i--) { ixgbe_clock_in_i2c_bit(hw, &bit); *data |= bit << i; @@ -1901,6 +2078,7 @@ static s32 ixgbe_clock_out_i2c_byte(struct ixgbe_hw *hw, u8 data) /* Release SDA line (set high) */ i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL(hw)); i2cctl |= IXGBE_I2C_DATA_OUT(hw); + i2cctl |= IXGBE_I2C_DATA_OE_N_EN(hw); IXGBE_WRITE_REG(hw, IXGBE_I2CCTL(hw), i2cctl); IXGBE_WRITE_FLUSH(hw); @@ -1915,15 +2093,21 @@ static s32 ixgbe_clock_out_i2c_byte(struct ixgbe_hw *hw, u8 data) **/ static s32 ixgbe_get_i2c_ack(struct ixgbe_hw *hw) { + u32 data_oe_bit = IXGBE_I2C_DATA_OE_N_EN(hw); s32 status = 0; u32 i = 0; u32 i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL(hw)); u32 timeout = 10; bool ack = true; + if (data_oe_bit) { + i2cctl |= IXGBE_I2C_DATA_OUT(hw); + i2cctl |= data_oe_bit; + IXGBE_WRITE_REG(hw, IXGBE_I2CCTL(hw), i2cctl); + IXGBE_WRITE_FLUSH(hw); + } ixgbe_raise_i2c_clk(hw, &i2cctl); - /* Minimum high period of clock is 4us */ udelay(IXGBE_I2C_T_HIGH); @@ -1961,7 +2145,14 @@ static s32 ixgbe_get_i2c_ack(struct ixgbe_hw *hw) static s32 ixgbe_clock_in_i2c_bit(struct ixgbe_hw *hw, bool *data) { u32 i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL(hw)); + u32 data_oe_bit = IXGBE_I2C_DATA_OE_N_EN(hw); + if (data_oe_bit) { + i2cctl |= IXGBE_I2C_DATA_OUT(hw); + i2cctl |= data_oe_bit; + IXGBE_WRITE_REG(hw, IXGBE_I2CCTL(hw), i2cctl); + IXGBE_WRITE_FLUSH(hw); + } ixgbe_raise_i2c_clk(hw, &i2cctl); /* Minimum high period of clock is 4us */ @@ -2016,13 +2207,20 @@ static s32 ixgbe_clock_out_i2c_bit(struct ixgbe_hw *hw, bool data) * @i2cctl: Current value of I2CCTL register * * Raises the I2C clock line '0'->'1' + * Negates the I2C clock output enable on X550 hardware. **/ static void ixgbe_raise_i2c_clk(struct ixgbe_hw *hw, u32 *i2cctl) { + u32 clk_oe_bit = IXGBE_I2C_CLK_OE_N_EN(hw); u32 i = 0; u32 timeout = IXGBE_I2C_CLOCK_STRETCHING_TIMEOUT; u32 i2cctl_r = 0; + if (clk_oe_bit) { + *i2cctl |= clk_oe_bit; + IXGBE_WRITE_REG(hw, IXGBE_I2CCTL(hw), *i2cctl); + } + for (i = 0; i < timeout; i++) { *i2cctl |= IXGBE_I2C_CLK_OUT(hw); IXGBE_WRITE_REG(hw, IXGBE_I2CCTL(hw), *i2cctl); @@ -2042,11 +2240,13 @@ static void ixgbe_raise_i2c_clk(struct ixgbe_hw *hw, u32 *i2cctl) * @i2cctl: Current value of I2CCTL register * * Lowers the I2C clock line '1'->'0' + * Asserts the I2C clock output enable on X550 hardware. **/ static void ixgbe_lower_i2c_clk(struct ixgbe_hw *hw, u32 *i2cctl) { *i2cctl &= ~IXGBE_I2C_CLK_OUT(hw); + *i2cctl &= ~IXGBE_I2C_CLK_OE_N_EN(hw); IXGBE_WRITE_REG(hw, IXGBE_I2CCTL(hw), *i2cctl); IXGBE_WRITE_FLUSH(hw); @@ -2062,13 +2262,17 @@ static void ixgbe_lower_i2c_clk(struct ixgbe_hw *hw, u32 *i2cctl) * @data: I2C data value (0 or 1) to set * * Sets the I2C data bit + * Asserts the I2C data output enable on X550 hardware. **/ static s32 ixgbe_set_i2c_data(struct ixgbe_hw *hw, u32 *i2cctl, bool data) { + u32 data_oe_bit = IXGBE_I2C_DATA_OE_N_EN(hw); + if (data) *i2cctl |= IXGBE_I2C_DATA_OUT(hw); else *i2cctl &= ~IXGBE_I2C_DATA_OUT(hw); + *i2cctl &= ~data_oe_bit; IXGBE_WRITE_REG(hw, IXGBE_I2CCTL(hw), *i2cctl); IXGBE_WRITE_FLUSH(hw); @@ -2076,6 +2280,14 @@ static s32 ixgbe_set_i2c_data(struct ixgbe_hw *hw, u32 *i2cctl, bool data) /* Data rise/fall (1000ns/300ns) and set-up time (250ns) */ udelay(IXGBE_I2C_T_RISE + IXGBE_I2C_T_FALL + IXGBE_I2C_T_SU_DATA); + if (!data) /* Can't verify data in this case */ + return 0; + if (data_oe_bit) { + *i2cctl |= data_oe_bit; + IXGBE_WRITE_REG(hw, IXGBE_I2CCTL(hw), *i2cctl); + IXGBE_WRITE_FLUSH(hw); + } + /* Verify data was set correctly */ *i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL(hw)); if (data != ixgbe_get_i2c_data(hw, i2cctl)) { @@ -2092,9 +2304,19 @@ static s32 ixgbe_set_i2c_data(struct ixgbe_hw *hw, u32 *i2cctl, bool data) * @i2cctl: Current value of I2CCTL register * * Returns the I2C data bit value + * Negates the I2C data output enable on X550 hardware. **/ static bool ixgbe_get_i2c_data(struct ixgbe_hw *hw, u32 *i2cctl) { + u32 data_oe_bit = IXGBE_I2C_DATA_OE_N_EN(hw); + + if (data_oe_bit) { + *i2cctl |= data_oe_bit; + IXGBE_WRITE_REG(hw, IXGBE_I2CCTL(hw), *i2cctl); + IXGBE_WRITE_FLUSH(hw); + udelay(IXGBE_I2C_T_FALL); + } + if (*i2cctl & IXGBE_I2C_DATA_IN(hw)) return true; return false; @@ -2109,10 +2331,11 @@ static bool ixgbe_get_i2c_data(struct ixgbe_hw *hw, u32 *i2cctl) **/ static void ixgbe_i2c_bus_clear(struct ixgbe_hw *hw) { - u32 i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL(hw)); + u32 i2cctl; u32 i; ixgbe_i2c_start(hw); + i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL(hw)); ixgbe_set_i2c_data(hw, &i2cctl, 1); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h index e45988c4dad5..5abd66c84d00 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h @@ -66,6 +66,9 @@ #define IXGBE_SFF_1GBASET_CAPABLE 0x8 #define IXGBE_SFF_10GBASESR_CAPABLE 0x10 #define IXGBE_SFF_10GBASELR_CAPABLE 0x20 +#define IXGBE_SFF_SOFT_RS_SELECT_MASK 0x8 +#define IXGBE_SFF_SOFT_RS_SELECT_10G 0x8 +#define IXGBE_SFF_SOFT_RS_SELECT_1G 0x0 #define IXGBE_SFF_ADDRESSING_MODE 0x4 #define IXGBE_SFF_QSFP_DA_ACTIVE_CABLE 0x1 #define IXGBE_SFF_QSFP_DA_PASSIVE_CABLE 0x8 @@ -78,9 +81,29 @@ #define IXGBE_I2C_EEPROM_STATUS_FAIL 0x2 #define IXGBE_I2C_EEPROM_STATUS_IN_PROGRESS 0x3 #define IXGBE_CS4227 0xBE /* CS4227 address */ -#define IXGBE_CS4227_SPARE24_LSB 0x12B0 /* Reg to program EDC */ +#define IXGBE_CS4227_SCRATCH 2 +#define IXGBE_CS4227_RESET_PENDING 0x1357 +#define IXGBE_CS4227_RESET_COMPLETE 0x5AA5 +#define IXGBE_CS4227_RETRIES 15 +#define IXGBE_CS4227_EFUSE_STATUS 0x0181 +#define IXGBE_CS4227_LINE_SPARE22_MSB 0x12AD /* Reg to set speed */ +#define IXGBE_CS4227_LINE_SPARE24_LSB 0x12B0 /* Reg to set EDC */ +#define IXGBE_CS4227_HOST_SPARE22_MSB 0x1AAD /* Reg to set speed */ +#define IXGBE_CS4227_HOST_SPARE24_LSB 0x1AB0 /* Reg to program EDC */ +#define IXGBE_CS4227_EEPROM_STATUS 0x5001 +#define IXGBE_CS4227_EEPROM_LOAD_OK 0x0001 +#define IXGBE_CS4227_SPEED_1G 0x8000 +#define IXGBE_CS4227_SPEED_10G 0 #define IXGBE_CS4227_EDC_MODE_CX1 0x0002 #define IXGBE_CS4227_EDC_MODE_SR 0x0004 +#define IXGBE_CS4227_EDC_MODE_DIAG 0x0008 +#define IXGBE_CS4227_RESET_HOLD 500 /* microseconds */ +#define IXGBE_CS4227_RESET_DELAY 500 /* milliseconds */ +#define IXGBE_CS4227_CHECK_DELAY 30 /* milliseconds */ +#define IXGBE_PE 0xE0 /* Port expander addr */ +#define IXGBE_PE_OUTPUT 1 /* Output reg offset */ +#define IXGBE_PE_CONFIG 3 /* Config reg offset */ +#define IXGBE_PE_BIT1 (1 << 1) /* Flow control defines */ #define IXGBE_TAF_SYM_PAUSE 0x400 @@ -109,6 +132,8 @@ #define IXGBE_I2C_T_SU_STO 4 #define IXGBE_I2C_T_BUF 5 +#define IXGBE_SFP_DETECT_RETRIES 2 + #define IXGBE_TN_LASI_STATUS_REG 0x9005 #define IXGBE_TN_LASI_STATUS_TEMP_ALARM 0x0008 @@ -154,8 +179,12 @@ s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw, s32 ixgbe_tn_check_overtemp(struct ixgbe_hw *hw); s32 ixgbe_read_i2c_byte_generic(struct ixgbe_hw *hw, u8 byte_offset, u8 dev_addr, u8 *data); +s32 ixgbe_read_i2c_byte_generic_unlocked(struct ixgbe_hw *hw, u8 byte_offset, + u8 dev_addr, u8 *data); s32 ixgbe_write_i2c_byte_generic(struct ixgbe_hw *hw, u8 byte_offset, u8 dev_addr, u8 data); +s32 ixgbe_write_i2c_byte_generic_unlocked(struct ixgbe_hw *hw, u8 byte_offset, + u8 dev_addr, u8 data); s32 ixgbe_read_i2c_eeprom_generic(struct ixgbe_hw *hw, u8 byte_offset, u8 *eeprom_data); s32 ixgbe_read_i2c_sff8472_generic(struct ixgbe_hw *hw, u8 byte_offset, @@ -164,6 +193,10 @@ s32 ixgbe_write_i2c_eeprom_generic(struct ixgbe_hw *hw, u8 byte_offset, u8 eeprom_data); s32 ixgbe_read_i2c_combined_generic(struct ixgbe_hw *hw, u8 addr, u16 reg, u16 *val); +s32 ixgbe_read_i2c_combined_generic_unlocked(struct ixgbe_hw *hw, u8 addr, + u16 reg, u16 *val); s32 ixgbe_write_i2c_combined_generic(struct ixgbe_hw *hw, u8 addr, u16 reg, u16 val); +s32 ixgbe_write_i2c_combined_generic_unlocked(struct ixgbe_hw *hw, u8 addr, + u16 reg, u16 val); #endif /* _IXGBE_PHY_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h index 63689192b149..939c90c4ff39 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h @@ -402,6 +402,7 @@ struct ixgbe_thermal_sensor_data { #define IXGBE_FDIRSIP4M 0x0EE40 #define IXGBE_FDIRTCPM 0x0EE44 #define IXGBE_FDIRUDPM 0x0EE48 +#define IXGBE_FDIRSCTPM 0x0EE78 #define IXGBE_FDIRIP6M 0x0EE74 #define IXGBE_FDIRM 0x0EE70 @@ -1192,6 +1193,7 @@ struct ixgbe_thermal_sensor_data { /* RDRXCTL Bit Masks */ #define IXGBE_RDRXCTL_RDMTS_1_2 0x00000000 /* Rx Desc Min Threshold Size */ #define IXGBE_RDRXCTL_CRCSTRIP 0x00000002 /* CRC Strip */ +#define IXGBE_RDRXCTL_PSP 0x00000004 /* Pad small packet */ #define IXGBE_RDRXCTL_MVMEN 0x00000020 #define IXGBE_RDRXCTL_DMAIDONE 0x00000008 /* DMA init cycle done */ #define IXGBE_RDRXCTL_AGGDIS 0x00010000 /* Aggregation disable */ @@ -1948,6 +1950,7 @@ enum { #define IXGBE_GSSR_SW_MNG_SM 0x0400 #define IXGBE_GSSR_SHARED_I2C_SM 0x1806 /* Wait for both phys & I2Cs */ #define IXGBE_GSSR_I2C_MASK 0x1800 +#define IXGBE_GSSR_NVM_PHY_MASK 0xF /* FW Status register bitmask */ #define IXGBE_FWSTS_FWRI 0x00000200 /* Firmware Reset Indication */ @@ -3255,9 +3258,11 @@ struct ixgbe_mac_operations { void (*flap_tx_laser)(struct ixgbe_hw *); void (*stop_link_on_d3)(struct ixgbe_hw *); s32 (*setup_link)(struct ixgbe_hw *, ixgbe_link_speed, bool); + s32 (*setup_mac_link)(struct ixgbe_hw *, ixgbe_link_speed, bool); s32 (*check_link)(struct ixgbe_hw *, ixgbe_link_speed *, bool *, bool); s32 (*get_link_capabilities)(struct ixgbe_hw *, ixgbe_link_speed *, bool *); + void (*set_rate_select_speed)(struct ixgbe_hw *, ixgbe_link_speed); /* Packet Buffer Manipulation */ void (*set_rxpba)(struct ixgbe_hw *, int, u32, int); @@ -3328,6 +3333,10 @@ struct ixgbe_phy_operations { s32 (*set_phy_power)(struct ixgbe_hw *, bool on); s32 (*enter_lplu)(struct ixgbe_hw *); s32 (*handle_lasi)(struct ixgbe_hw *hw); + s32 (*read_i2c_combined_unlocked)(struct ixgbe_hw *, u8 addr, u16 reg, + u16 *value); + s32 (*write_i2c_combined_unlocked)(struct ixgbe_hw *, u8 addr, u16 reg, + u16 value); }; struct ixgbe_eeprom_info { diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c index 4e758435ece8..c1d4584f6469 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c @@ -567,19 +567,25 @@ static s32 ixgbe_poll_flash_update_done_X540(struct ixgbe_hw *hw) **/ s32 ixgbe_acquire_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask) { - u32 swfw_sync; - u32 swmask = mask; - u32 fwmask = mask << 5; - u32 hwmask = 0; + u32 swmask = mask & IXGBE_GSSR_NVM_PHY_MASK; + u32 swi2c_mask = mask & IXGBE_GSSR_I2C_MASK; + u32 fwmask = swmask << 5; u32 timeout = 200; + u32 hwmask = 0; + u32 swfw_sync; u32 i; - if (swmask == IXGBE_GSSR_EEP_SM) + if (swmask & IXGBE_GSSR_EEP_SM) hwmask = IXGBE_GSSR_FLASH_SM; + /* SW only mask does not have FW bit pair */ + if (mask & IXGBE_GSSR_SW_MNG_SM) + swmask |= IXGBE_GSSR_SW_MNG_SM; + + swmask |= swi2c_mask; + fwmask |= swi2c_mask << 2; for (i = 0; i < timeout; i++) { - /* - * SW NVM semaphore bit is used for access to all + /* SW NVM semaphore bit is used for access to all * SW_FW_SYNC bits (not just NVM) */ if (ixgbe_get_swfw_sync_semaphore(hw)) @@ -590,39 +596,56 @@ s32 ixgbe_acquire_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask) swfw_sync |= swmask; IXGBE_WRITE_REG(hw, IXGBE_SWFW_SYNC(hw), swfw_sync); ixgbe_release_swfw_sync_semaphore(hw); - break; - } else { - /* - * Firmware currently using resource (fwmask), - * hardware currently using resource (hwmask), - * or other software thread currently using - * resource (swmask) - */ - ixgbe_release_swfw_sync_semaphore(hw); - usleep_range(5000, 10000); + usleep_range(5000, 6000); + return 0; } + /* Firmware currently using resource (fwmask), hardware + * currently using resource (hwmask), or other software + * thread currently using resource (swmask) + */ + ixgbe_release_swfw_sync_semaphore(hw); + usleep_range(5000, 10000); } - /* - * If the resource is not released by the FW/HW the SW can assume that - * the FW/HW malfunctions. In that case the SW should sets the - * SW bit(s) of the requested resource(s) while ignoring the - * corresponding FW/HW bits in the SW_FW_SYNC register. - */ - if (i >= timeout) { - swfw_sync = IXGBE_READ_REG(hw, IXGBE_SWFW_SYNC(hw)); - if (swfw_sync & (fwmask | hwmask)) { - if (ixgbe_get_swfw_sync_semaphore(hw)) - return IXGBE_ERR_SWFW_SYNC; + /* Failed to get SW only semaphore */ + if (swmask == IXGBE_GSSR_SW_MNG_SM) { + hw_dbg(hw, "Failed to get SW only semaphore\n"); + return IXGBE_ERR_SWFW_SYNC; + } - swfw_sync |= swmask; - IXGBE_WRITE_REG(hw, IXGBE_SWFW_SYNC(hw), swfw_sync); - ixgbe_release_swfw_sync_semaphore(hw); - } + /* If the resource is not released by the FW/HW the SW can assume that + * the FW/HW malfunctions. In that case the SW should set the SW bit(s) + * of the requested resource(s) while ignoring the corresponding FW/HW + * bits in the SW_FW_SYNC register. + */ + if (ixgbe_get_swfw_sync_semaphore(hw)) + return IXGBE_ERR_SWFW_SYNC; + swfw_sync = IXGBE_READ_REG(hw, IXGBE_SWFW_SYNC(hw)); + if (swfw_sync & (fwmask | hwmask)) { + swfw_sync |= swmask; + IXGBE_WRITE_REG(hw, IXGBE_SWFW_SYNC(hw), swfw_sync); + ixgbe_release_swfw_sync_semaphore(hw); + usleep_range(5000, 6000); + return 0; } + /* If the resource is not released by other SW the SW can assume that + * the other SW malfunctions. In that case the SW should clear all SW + * flags that it does not own and then repeat the whole process once + * again. + */ + if (swfw_sync & swmask) { + u32 rmask = IXGBE_GSSR_EEP_SM | IXGBE_GSSR_PHY0_SM | + IXGBE_GSSR_PHY1_SM | IXGBE_GSSR_MAC_CSR_SM; + + if (swi2c_mask) + rmask |= IXGBE_GSSR_I2C_MASK; + ixgbe_release_swfw_sync_X540(hw, rmask); + ixgbe_release_swfw_sync_semaphore(hw); + return IXGBE_ERR_SWFW_SYNC; + } + ixgbe_release_swfw_sync_semaphore(hw); - usleep_range(5000, 10000); - return 0; + return IXGBE_ERR_SWFW_SYNC; } /** @@ -635,9 +658,11 @@ s32 ixgbe_acquire_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask) **/ void ixgbe_release_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask) { + u32 swmask = mask & (IXGBE_GSSR_NVM_PHY_MASK | IXGBE_GSSR_SW_MNG_SM); u32 swfw_sync; - u32 swmask = mask; + if (mask & IXGBE_GSSR_I2C_MASK) + swmask |= mask & IXGBE_GSSR_I2C_MASK; ixgbe_get_swfw_sync_semaphore(hw); swfw_sync = IXGBE_READ_REG(hw, IXGBE_SWFW_SYNC(hw)); @@ -645,7 +670,7 @@ void ixgbe_release_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask) IXGBE_WRITE_REG(hw, IXGBE_SWFW_SYNC(hw), swfw_sync); ixgbe_release_swfw_sync_semaphore(hw); - usleep_range(5000, 10000); + usleep_range(5000, 6000); } /** @@ -686,6 +711,11 @@ static s32 ixgbe_get_swfw_sync_semaphore(struct ixgbe_hw *hw) usleep_range(50, 100); } + /* Release semaphores and return error if SW NVM semaphore + * was not granted because we do not have access to the EEPROM + */ + hw_dbg(hw, "REGSMP Software NVM semaphore not granted\n"); + ixgbe_release_swfw_sync_semaphore(hw); return IXGBE_ERR_EEPROM; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c index 9fe9445cd73b..ed7b2899affe 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c @@ -56,6 +56,283 @@ static void ixgbe_setup_mux_ctl(struct ixgbe_hw *hw) IXGBE_WRITE_FLUSH(hw); } +/** + * ixgbe_read_cs4227 - Read CS4227 register + * @hw: pointer to hardware structure + * @reg: register number to write + * @value: pointer to receive value read + * + * Returns status code + */ +static s32 ixgbe_read_cs4227(struct ixgbe_hw *hw, u16 reg, u16 *value) +{ + return hw->phy.ops.read_i2c_combined_unlocked(hw, IXGBE_CS4227, reg, + value); +} + +/** + * ixgbe_write_cs4227 - Write CS4227 register + * @hw: pointer to hardware structure + * @reg: register number to write + * @value: value to write to register + * + * Returns status code + */ +static s32 ixgbe_write_cs4227(struct ixgbe_hw *hw, u16 reg, u16 value) +{ + return hw->phy.ops.write_i2c_combined_unlocked(hw, IXGBE_CS4227, reg, + value); +} + +/** + * ixgbe_check_cs4227_reg - Perform diag on a CS4227 register + * @hw: pointer to hardware structure + * @reg: the register to check + * + * Performs a diagnostic on a register in the CS4227 chip. Returns an error + * if it is not operating correctly. + * This function assumes that the caller has acquired the proper semaphore. + */ +static s32 ixgbe_check_cs4227_reg(struct ixgbe_hw *hw, u16 reg) +{ + s32 status; + u32 retry; + u16 reg_val; + + reg_val = (IXGBE_CS4227_EDC_MODE_DIAG << 1) | 1; + status = ixgbe_write_cs4227(hw, reg, reg_val); + if (status) + return status; + for (retry = 0; retry < IXGBE_CS4227_RETRIES; retry++) { + msleep(IXGBE_CS4227_CHECK_DELAY); + reg_val = 0xFFFF; + ixgbe_read_cs4227(hw, reg, ®_val); + if (!reg_val) + break; + } + if (reg_val) { + hw_err(hw, "CS4227 reg 0x%04X failed diagnostic\n", reg); + return status; + } + + return 0; +} + +/** + * ixgbe_get_cs4227_status - Return CS4227 status + * @hw: pointer to hardware structure + * + * Performs a diagnostic on the CS4227 chip. Returns an error if it is + * not operating correctly. + * This function assumes that the caller has acquired the proper semaphore. + */ +static s32 ixgbe_get_cs4227_status(struct ixgbe_hw *hw) +{ + s32 status; + u16 value = 0; + + /* Exit if the diagnostic has already been performed. */ + status = ixgbe_read_cs4227(hw, IXGBE_CS4227_SCRATCH, &value); + if (status) + return status; + if (value == IXGBE_CS4227_RESET_COMPLETE) + return 0; + + /* Check port 0. */ + status = ixgbe_check_cs4227_reg(hw, IXGBE_CS4227_LINE_SPARE24_LSB); + if (status) + return status; + + status = ixgbe_check_cs4227_reg(hw, IXGBE_CS4227_HOST_SPARE24_LSB); + if (status) + return status; + + /* Check port 1. */ + status = ixgbe_check_cs4227_reg(hw, IXGBE_CS4227_LINE_SPARE24_LSB + + (1 << 12)); + if (status) + return status; + + return ixgbe_check_cs4227_reg(hw, IXGBE_CS4227_HOST_SPARE24_LSB + + (1 << 12)); +} + +/** + * ixgbe_read_pe - Read register from port expander + * @hw: pointer to hardware structure + * @reg: register number to read + * @value: pointer to receive read value + * + * Returns status code + */ +static s32 ixgbe_read_pe(struct ixgbe_hw *hw, u8 reg, u8 *value) +{ + s32 status; + + status = ixgbe_read_i2c_byte_generic_unlocked(hw, reg, IXGBE_PE, value); + if (status) + hw_err(hw, "port expander access failed with %d\n", status); + return status; +} + +/** + * ixgbe_write_pe - Write register to port expander + * @hw: pointer to hardware structure + * @reg: register number to write + * @value: value to write + * + * Returns status code + */ +static s32 ixgbe_write_pe(struct ixgbe_hw *hw, u8 reg, u8 value) +{ + s32 status; + + status = ixgbe_write_i2c_byte_generic_unlocked(hw, reg, IXGBE_PE, + value); + if (status) + hw_err(hw, "port expander access failed with %d\n", status); + return status; +} + +/** + * ixgbe_reset_cs4227 - Reset CS4227 using port expander + * @hw: pointer to hardware structure + * + * Returns error code + */ +static s32 ixgbe_reset_cs4227(struct ixgbe_hw *hw) +{ + s32 status; + u32 retry; + u16 value; + u8 reg; + + /* Trigger hard reset. */ + status = ixgbe_read_pe(hw, IXGBE_PE_OUTPUT, ®); + if (status) + return status; + reg |= IXGBE_PE_BIT1; + status = ixgbe_write_pe(hw, IXGBE_PE_OUTPUT, reg); + if (status) + return status; + + status = ixgbe_read_pe(hw, IXGBE_PE_CONFIG, ®); + if (status) + return status; + reg &= ~IXGBE_PE_BIT1; + status = ixgbe_write_pe(hw, IXGBE_PE_CONFIG, reg); + if (status) + return status; + + status = ixgbe_read_pe(hw, IXGBE_PE_OUTPUT, ®); + if (status) + return status; + reg &= ~IXGBE_PE_BIT1; + status = ixgbe_write_pe(hw, IXGBE_PE_OUTPUT, reg); + if (status) + return status; + + usleep_range(IXGBE_CS4227_RESET_HOLD, IXGBE_CS4227_RESET_HOLD + 100); + + status = ixgbe_read_pe(hw, IXGBE_PE_OUTPUT, ®); + if (status) + return status; + reg |= IXGBE_PE_BIT1; + status = ixgbe_write_pe(hw, IXGBE_PE_OUTPUT, reg); + if (status) + return status; + + /* Wait for the reset to complete. */ + msleep(IXGBE_CS4227_RESET_DELAY); + for (retry = 0; retry < IXGBE_CS4227_RETRIES; retry++) { + status = ixgbe_read_cs4227(hw, IXGBE_CS4227_EFUSE_STATUS, + &value); + if (!status && value == IXGBE_CS4227_EEPROM_LOAD_OK) + break; + msleep(IXGBE_CS4227_CHECK_DELAY); + } + if (retry == IXGBE_CS4227_RETRIES) { + hw_err(hw, "CS4227 reset did not complete\n"); + return IXGBE_ERR_PHY; + } + + status = ixgbe_read_cs4227(hw, IXGBE_CS4227_EEPROM_STATUS, &value); + if (status || !(value & IXGBE_CS4227_EEPROM_LOAD_OK)) { + hw_err(hw, "CS4227 EEPROM did not load successfully\n"); + return IXGBE_ERR_PHY; + } + + return 0; +} + +/** + * ixgbe_check_cs4227 - Check CS4227 and reset as needed + * @hw: pointer to hardware structure + */ +static void ixgbe_check_cs4227(struct ixgbe_hw *hw) +{ + u32 swfw_mask = hw->phy.phy_semaphore_mask; + s32 status; + u16 value; + u8 retry; + + for (retry = 0; retry < IXGBE_CS4227_RETRIES; retry++) { + status = hw->mac.ops.acquire_swfw_sync(hw, swfw_mask); + if (status) { + hw_err(hw, "semaphore failed with %d\n", status); + msleep(IXGBE_CS4227_CHECK_DELAY); + continue; + } + + /* Get status of reset flow. */ + status = ixgbe_read_cs4227(hw, IXGBE_CS4227_SCRATCH, &value); + if (!status && value == IXGBE_CS4227_RESET_COMPLETE) + goto out; + + if (status || value != IXGBE_CS4227_RESET_PENDING) + break; + + /* Reset is pending. Wait and check again. */ + hw->mac.ops.release_swfw_sync(hw, swfw_mask); + msleep(IXGBE_CS4227_CHECK_DELAY); + } + + /* Reset the CS4227. */ + status = ixgbe_reset_cs4227(hw); + if (status) { + hw_err(hw, "CS4227 reset failed: %d", status); + goto out; + } + + /* Reset takes so long, temporarily release semaphore in case the + * other driver instance is waiting for the reset indication. + */ + ixgbe_write_cs4227(hw, IXGBE_CS4227_SCRATCH, + IXGBE_CS4227_RESET_PENDING); + hw->mac.ops.release_swfw_sync(hw, swfw_mask); + usleep_range(10000, 12000); + status = hw->mac.ops.acquire_swfw_sync(hw, swfw_mask); + if (status) { + hw_err(hw, "semaphore failed with %d", status); + return; + } + + /* Is the CS4227 working correctly? */ + status = ixgbe_get_cs4227_status(hw); + if (status) { + hw_err(hw, "CS4227 status failed: %d", status); + goto out; + } + + /* Record completion for next time. */ + status = ixgbe_write_cs4227(hw, IXGBE_CS4227_SCRATCH, + IXGBE_CS4227_RESET_COMPLETE); + +out: + hw->mac.ops.release_swfw_sync(hw, swfw_mask); + msleep(hw->eeprom.semaphore_delay); +} + /** ixgbe_identify_phy_x550em - Get PHY type based on device id * @hw: pointer to hardware structure * @@ -68,7 +345,7 @@ static s32 ixgbe_identify_phy_x550em(struct ixgbe_hw *hw) /* set up for CS4227 usage */ hw->phy.phy_semaphore_mask = IXGBE_GSSR_SHARED_I2C_SM; ixgbe_setup_mux_ctl(hw); - + ixgbe_check_cs4227(hw); return ixgbe_identify_module_generic(hw); case IXGBE_DEV_ID_X550EM_X_KX4: hw->phy.type = ixgbe_phy_x550em_kx4; @@ -910,6 +1187,96 @@ static s32 ixgbe_setup_ixfi_x550em(struct ixgbe_hw *hw, ixgbe_link_speed *speed) } /** + * ixgbe_supported_sfp_modules_X550em - Check if SFP module type is supported + * @hw: pointer to hardware structure + * @linear: true if SFP module is linear + */ +static s32 ixgbe_supported_sfp_modules_X550em(struct ixgbe_hw *hw, bool *linear) +{ + switch (hw->phy.sfp_type) { + case ixgbe_sfp_type_not_present: + return IXGBE_ERR_SFP_NOT_PRESENT; + case ixgbe_sfp_type_da_cu_core0: + case ixgbe_sfp_type_da_cu_core1: + *linear = true; + break; + case ixgbe_sfp_type_srlr_core0: + case ixgbe_sfp_type_srlr_core1: + case ixgbe_sfp_type_da_act_lmt_core0: + case ixgbe_sfp_type_da_act_lmt_core1: + case ixgbe_sfp_type_1g_sx_core0: + case ixgbe_sfp_type_1g_sx_core1: + case ixgbe_sfp_type_1g_lx_core0: + case ixgbe_sfp_type_1g_lx_core1: + *linear = false; + break; + case ixgbe_sfp_type_unknown: + case ixgbe_sfp_type_1g_cu_core0: + case ixgbe_sfp_type_1g_cu_core1: + default: + return IXGBE_ERR_SFP_NOT_SUPPORTED; + } + + return 0; +} + +/** + * ixgbe_setup_mac_link_sfp_x550em - Configure the KR PHY for SFP. + * @hw: pointer to hardware structure + * + * Configures the extern PHY and the integrated KR PHY for SFP support. + */ +static s32 +ixgbe_setup_mac_link_sfp_x550em(struct ixgbe_hw *hw, + ixgbe_link_speed speed, + __always_unused bool autoneg_wait_to_complete) +{ + s32 status; + u16 slice, value; + bool setup_linear = false; + + /* Check if SFP module is supported and linear */ + status = ixgbe_supported_sfp_modules_X550em(hw, &setup_linear); + + /* If no SFP module present, then return success. Return success since + * there is no reason to configure CS4227 and SFP not present error is + * not accepted in the setup MAC link flow. + */ + if (status == IXGBE_ERR_SFP_NOT_PRESENT) + return 0; + + if (status) + return status; + + /* Configure CS4227 LINE side to 10G SR. */ + slice = IXGBE_CS4227_LINE_SPARE22_MSB + (hw->bus.lan_id << 12); + value = IXGBE_CS4227_SPEED_10G; + status = ixgbe_write_i2c_combined_generic(hw, IXGBE_CS4227, slice, + value); + + /* Configure CS4227 for HOST connection rate then type. */ + slice = IXGBE_CS4227_HOST_SPARE22_MSB + (hw->bus.lan_id << 12); + value = speed & IXGBE_LINK_SPEED_10GB_FULL ? + IXGBE_CS4227_SPEED_10G : IXGBE_CS4227_SPEED_1G; + status = ixgbe_write_i2c_combined_generic(hw, IXGBE_CS4227, slice, + value); + + slice = IXGBE_CS4227_HOST_SPARE24_LSB + (hw->bus.lan_id << 12); + if (setup_linear) + value = (IXGBE_CS4227_EDC_MODE_CX1 << 1) | 1; + else + value = (IXGBE_CS4227_EDC_MODE_SR << 1) | 1; + status = ixgbe_write_i2c_combined_generic(hw, IXGBE_CS4227, slice, + value); + + /* If internal link mode is XFI, then setup XFI internal link. */ + if (!(hw->phy.nw_mng_if_sel & IXGBE_NW_MNG_IF_SEL_INT_PHY_MODE)) + status = ixgbe_setup_ixfi_x550em(hw, &speed); + + return status; +} + +/** * ixgbe_setup_mac_link_t_X550em - Sets the auto advertised link speed * @hw: pointer to hardware structure * @speed: new link speed @@ -1003,6 +1370,10 @@ static void ixgbe_init_mac_link_ops_X550em(struct ixgbe_hw *hw) mac->ops.disable_tx_laser = NULL; mac->ops.enable_tx_laser = NULL; mac->ops.flap_tx_laser = NULL; + mac->ops.setup_link = ixgbe_setup_mac_link_multispeed_fiber; + mac->ops.setup_mac_link = ixgbe_setup_mac_link_sfp_x550em; + mac->ops.set_rate_select_speed = + ixgbe_set_soft_rate_select_speed; break; case ixgbe_media_type_copper: mac->ops.setup_link = ixgbe_setup_mac_link_t_X550em; @@ -1018,53 +1389,18 @@ static void ixgbe_init_mac_link_ops_X550em(struct ixgbe_hw *hw) */ static s32 ixgbe_setup_sfp_modules_X550em(struct ixgbe_hw *hw) { - bool setup_linear; - u16 reg_slice, edc_mode; - s32 ret_val; + s32 status; + bool linear; - switch (hw->phy.sfp_type) { - case ixgbe_sfp_type_unknown: - return 0; - case ixgbe_sfp_type_not_present: - return IXGBE_ERR_SFP_NOT_PRESENT; - case ixgbe_sfp_type_da_cu_core0: - case ixgbe_sfp_type_da_cu_core1: - setup_linear = true; - break; - case ixgbe_sfp_type_srlr_core0: - case ixgbe_sfp_type_srlr_core1: - case ixgbe_sfp_type_da_act_lmt_core0: - case ixgbe_sfp_type_da_act_lmt_core1: - case ixgbe_sfp_type_1g_sx_core0: - case ixgbe_sfp_type_1g_sx_core1: - setup_linear = false; - break; - default: - return IXGBE_ERR_SFP_NOT_SUPPORTED; - } + /* Check if SFP module is supported */ + status = ixgbe_supported_sfp_modules_X550em(hw, &linear); + if (status) + return status; ixgbe_init_mac_link_ops_X550em(hw); hw->phy.ops.reset = NULL; - /* The CS4227 slice address is the base address + the port-pair reg - * offset. I.e. Slice 0 = 0x12B0 and slice 1 = 0x22B0. - */ - reg_slice = IXGBE_CS4227_SPARE24_LSB + (hw->bus.lan_id << 12); - - if (setup_linear) - edc_mode = (IXGBE_CS4227_EDC_MODE_CX1 << 1) | 0x1; - else - edc_mode = (IXGBE_CS4227_EDC_MODE_SR << 1) | 0x1; - - /* Configure CS4227 for connection type. */ - ret_val = hw->phy.ops.write_i2c_combined(hw, IXGBE_CS4227, reg_slice, - edc_mode); - - if (ret_val) - ret_val = hw->phy.ops.write_i2c_combined(hw, 0x80, reg_slice, - edc_mode); - - return ret_val; + return 0; } /** ixgbe_get_link_capabilities_x550em - Determines link capabilities @@ -1927,6 +2263,62 @@ static void ixgbe_set_source_address_pruning_X550(struct ixgbe_hw *hw, IXGBE_WRITE_REG(hw, IXGBE_PFFLPH, (u32)(pfflp >> 32)); } +/** + * ixgbe_set_mux - Set mux for port 1 access with CS4227 + * @hw: pointer to hardware structure + * @state: set mux if 1, clear if 0 + */ +static void ixgbe_set_mux(struct ixgbe_hw *hw, u8 state) +{ + u32 esdp; + + if (!hw->bus.lan_id) + return; + esdp = IXGBE_READ_REG(hw, IXGBE_ESDP); + if (state) + esdp |= IXGBE_ESDP_SDP1; + else + esdp &= ~IXGBE_ESDP_SDP1; + IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp); + IXGBE_WRITE_FLUSH(hw); +} + +/** + * ixgbe_acquire_swfw_sync_X550em - Acquire SWFW semaphore + * @hw: pointer to hardware structure + * @mask: Mask to specify which semaphore to acquire + * + * Acquires the SWFW semaphore and sets the I2C MUX + */ +static s32 ixgbe_acquire_swfw_sync_X550em(struct ixgbe_hw *hw, u32 mask) +{ + s32 status; + + status = ixgbe_acquire_swfw_sync_X540(hw, mask); + if (status) + return status; + + if (mask & IXGBE_GSSR_I2C_MASK) + ixgbe_set_mux(hw, 1); + + return 0; +} + +/** + * ixgbe_release_swfw_sync_X550em - Release SWFW semaphore + * @hw: pointer to hardware structure + * @mask: Mask to specify which semaphore to release + * + * Releases the SWFW semaphore and sets the I2C MUX + */ +static void ixgbe_release_swfw_sync_X550em(struct ixgbe_hw *hw, u32 mask) +{ + if (mask & IXGBE_GSSR_I2C_MASK) + ixgbe_set_mux(hw, 0); + + ixgbe_release_swfw_sync_X540(hw, mask); +} + #define X550_COMMON_MAC \ .init_hw = &ixgbe_init_hw_generic, \ .start_hw = &ixgbe_start_hw_X540, \ @@ -1964,8 +2356,6 @@ static void ixgbe_set_source_address_pruning_X550(struct ixgbe_hw *hw, &ixgbe_set_source_address_pruning_X550, \ .set_ethertype_anti_spoofing = \ &ixgbe_set_ethertype_anti_spoofing_X550, \ - .acquire_swfw_sync = &ixgbe_acquire_swfw_sync_X540, \ - .release_swfw_sync = &ixgbe_release_swfw_sync_X540, \ .disable_rx_buff = &ixgbe_disable_rx_buff_generic, \ .enable_rx_buff = &ixgbe_enable_rx_buff_generic, \ .get_thermal_sensor_data = NULL, \ @@ -1985,6 +2375,8 @@ static struct ixgbe_mac_operations mac_ops_X550 = { .get_link_capabilities = &ixgbe_get_copper_link_capabilities_generic, .get_bus_info = &ixgbe_get_bus_info_generic, .setup_sfp = NULL, + .acquire_swfw_sync = &ixgbe_acquire_swfw_sync_X540, + .release_swfw_sync = &ixgbe_release_swfw_sync_X540, }; static struct ixgbe_mac_operations mac_ops_X550EM_x = { @@ -1997,7 +2389,8 @@ static struct ixgbe_mac_operations mac_ops_X550EM_x = { .get_link_capabilities = &ixgbe_get_link_capabilities_X550em, .get_bus_info = &ixgbe_get_bus_info_X550em, .setup_sfp = ixgbe_setup_sfp_modules_X550em, - + .acquire_swfw_sync = &ixgbe_acquire_swfw_sync_X550em, + .release_swfw_sync = &ixgbe_release_swfw_sync_X550em, }; #define X550_COMMON_EEP \ @@ -2039,14 +2432,17 @@ static struct ixgbe_phy_operations phy_ops_X550 = { X550_COMMON_PHY .init = NULL, .identify = &ixgbe_identify_phy_generic, - .read_i2c_combined = &ixgbe_read_i2c_combined_generic, - .write_i2c_combined = &ixgbe_write_i2c_combined_generic, }; static struct ixgbe_phy_operations phy_ops_X550EM_x = { X550_COMMON_PHY .init = &ixgbe_init_phy_ops_X550em, .identify = &ixgbe_identify_phy_x550em, + .read_i2c_combined = &ixgbe_read_i2c_combined_generic, + .write_i2c_combined = &ixgbe_write_i2c_combined_generic, + .read_i2c_combined_unlocked = &ixgbe_read_i2c_combined_generic_unlocked, + .write_i2c_combined_unlocked = + &ixgbe_write_i2c_combined_generic_unlocked, }; static const u32 ixgbe_mvals_X550[IXGBE_MVALS_IDX_LIMIT] = { diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 149a0b4489be..35da2d74e73e 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -3896,6 +3896,7 @@ static const struct net_device_ops ixgbevf_netdev_ops = { #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = ixgbevf_netpoll, #endif + .ndo_features_check = passthru_features_check, }; static void ixgbevf_assign_netdev_ops(struct net_device *dev) diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 960169efe636..c78ae1868097 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -1845,29 +1845,19 @@ static void mv643xx_eth_program_multicast_filter(struct net_device *dev) struct netdev_hw_addr *ha; int i; - if (dev->flags & (IFF_PROMISC | IFF_ALLMULTI)) { - int port_num; - u32 accept; + if (dev->flags & (IFF_PROMISC | IFF_ALLMULTI)) + goto promiscuous; -oom: - port_num = mp->port_num; - accept = 0x01010101; - for (i = 0; i < 0x100; i += 4) { - wrl(mp, SPECIAL_MCAST_TABLE(port_num) + i, accept); - wrl(mp, OTHER_MCAST_TABLE(port_num) + i, accept); - } - return; - } - - mc_spec = kzalloc(0x200, GFP_ATOMIC); - if (mc_spec == NULL) - goto oom; - mc_other = mc_spec + (0x100 >> 2); + /* Allocate both mc_spec and mc_other tables */ + mc_spec = kcalloc(128, sizeof(u32), GFP_ATOMIC); + if (!mc_spec) + goto promiscuous; + mc_other = &mc_spec[64]; netdev_for_each_mc_addr(ha, dev) { u8 *a = ha->addr; u32 *table; - int entry; + u8 entry; if (memcmp(a, "\x01\x00\x5e\x00\x00", 5) == 0) { table = mc_spec; @@ -1880,12 +1870,23 @@ oom: table[entry >> 2] |= 1 << (8 * (entry & 3)); } - for (i = 0; i < 0x100; i += 4) { - wrl(mp, SPECIAL_MCAST_TABLE(mp->port_num) + i, mc_spec[i >> 2]); - wrl(mp, OTHER_MCAST_TABLE(mp->port_num) + i, mc_other[i >> 2]); + for (i = 0; i < 64; i++) { + wrl(mp, SPECIAL_MCAST_TABLE(mp->port_num) + i * sizeof(u32), + mc_spec[i]); + wrl(mp, OTHER_MCAST_TABLE(mp->port_num) + i * sizeof(u32), + mc_other[i]); } kfree(mc_spec); + return; + +promiscuous: + for (i = 0; i < 64; i++) { + wrl(mp, SPECIAL_MCAST_TABLE(mp->port_num) + i * sizeof(u32), + 0x01010101u); + wrl(mp, OTHER_MCAST_TABLE(mp->port_num) + i * sizeof(u32), + 0x01010101u); + } } static void mv643xx_eth_set_rx_mode(struct net_device *dev) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 514df76fc70f..dd6fe942acf9 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -32,6 +32,7 @@ #include <linux/of_address.h> #include <linux/phy.h> #include <linux/clk.h> +#include <linux/cpu.h> /* Registers */ #define MVNETA_RXQ_CONFIG_REG(q) (0x1400 + ((q) << 2)) @@ -285,23 +286,34 @@ struct mvneta_pcpu_stats { u64 tx_bytes; }; +struct mvneta_pcpu_port { + /* Pointer to the shared port */ + struct mvneta_port *pp; + + /* Pointer to the CPU-local NAPI struct */ + struct napi_struct napi; + + /* Cause of the previous interrupt */ + u32 cause_rx_tx; +}; + struct mvneta_port { + struct mvneta_pcpu_port __percpu *ports; + struct mvneta_pcpu_stats __percpu *stats; + int pkt_size; unsigned int frag_size; void __iomem *base; struct mvneta_rx_queue *rxqs; struct mvneta_tx_queue *txqs; struct net_device *dev; - - u32 cause_rx_tx; - struct napi_struct napi; + struct notifier_block cpu_notifier; /* Core clock */ struct clk *clk; u8 mcast_count[256]; u16 tx_ring_size; u16 rx_ring_size; - struct mvneta_pcpu_stats *stats; struct mii_bus *mii_bus; struct phy_device *phy_dev; @@ -468,7 +480,7 @@ struct mvneta_rx_queue { /* The hardware supports eight (8) rx queues, but we are only allowing * the first one to be used. Therefore, let's just allocate one queue. */ -static int rxq_number = 1; +static int rxq_number = 8; static int txq_number = 8; static int rxq_def; @@ -756,14 +768,7 @@ static void mvneta_port_up(struct mvneta_port *pp) mvreg_write(pp, MVNETA_TXQ_CMD, q_map); /* Enable all initialized RXQs. */ - q_map = 0; - for (queue = 0; queue < rxq_number; queue++) { - struct mvneta_rx_queue *rxq = &pp->rxqs[queue]; - if (rxq->descs != NULL) - q_map |= (1 << queue); - } - - mvreg_write(pp, MVNETA_RXQ_CMD, q_map); + mvreg_write(pp, MVNETA_RXQ_CMD, BIT(rxq_def)); } /* Stop the Ethernet port activity */ @@ -949,7 +954,7 @@ static void mvneta_defaults_set(struct mvneta_port *pp) /* Set CPU queue access map - all CPUs have access to all RX * queues and to all TX queues */ - for (cpu = 0; cpu < CONFIG_NR_CPUS; cpu++) + for_each_present_cpu(cpu) mvreg_write(pp, MVNETA_CPU_MAP(cpu), (MVNETA_CPU_RXQ_ACCESS_ALL_MASK | MVNETA_CPU_TXQ_ACCESS_ALL_MASK)); @@ -1426,17 +1431,6 @@ static u32 mvneta_skb_tx_csum(struct mvneta_port *pp, struct sk_buff *skb) return MVNETA_TX_L4_CSUM_NOT; } -/* Returns rx queue pointer (find last set bit) according to causeRxTx - * value - */ -static struct mvneta_rx_queue *mvneta_rx_policy(struct mvneta_port *pp, - u32 cause) -{ - int queue = fls(cause >> 8) - 1; - - return (queue < 0 || queue >= rxq_number) ? NULL : &pp->rxqs[queue]; -} - /* Drop packets received by the RXQ and free buffers */ static void mvneta_rxq_drop_pkts(struct mvneta_port *pp, struct mvneta_rx_queue *rxq) @@ -1461,6 +1455,7 @@ static void mvneta_rxq_drop_pkts(struct mvneta_port *pp, static int mvneta_rx(struct mvneta_port *pp, int rx_todo, struct mvneta_rx_queue *rxq) { + struct mvneta_pcpu_port *port = this_cpu_ptr(pp->ports); struct net_device *dev = pp->dev; int rx_done; u32 rcvd_pkts = 0; @@ -1515,7 +1510,7 @@ static int mvneta_rx(struct mvneta_port *pp, int rx_todo, skb->protocol = eth_type_trans(skb, dev); mvneta_rx_csum(pp, rx_status, skb); - napi_gro_receive(&pp->napi, skb); + napi_gro_receive(&port->napi, skb); rcvd_pkts++; rcvd_bytes += rx_bytes; @@ -1550,7 +1545,7 @@ static int mvneta_rx(struct mvneta_port *pp, int rx_todo, mvneta_rx_csum(pp, rx_status, skb); - napi_gro_receive(&pp->napi, skb); + napi_gro_receive(&port->napi, skb); } if (rcvd_pkts) { @@ -2061,12 +2056,10 @@ static void mvneta_set_rx_mode(struct net_device *dev) /* Interrupt handling - the callback for request_irq() */ static irqreturn_t mvneta_isr(int irq, void *dev_id) { - struct mvneta_port *pp = (struct mvneta_port *)dev_id; + struct mvneta_pcpu_port *port = (struct mvneta_pcpu_port *)dev_id; - /* Mask all interrupts */ - mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0); - - napi_schedule(&pp->napi); + disable_percpu_irq(port->pp->dev->irq); + napi_schedule(&port->napi); return IRQ_HANDLED; } @@ -2104,11 +2097,11 @@ static int mvneta_poll(struct napi_struct *napi, int budget) { int rx_done = 0; u32 cause_rx_tx; - unsigned long flags; struct mvneta_port *pp = netdev_priv(napi->dev); + struct mvneta_pcpu_port *port = this_cpu_ptr(pp->ports); if (!netif_running(pp->dev)) { - napi_complete(napi); + napi_complete(&port->napi); return rx_done; } @@ -2135,47 +2128,17 @@ static int mvneta_poll(struct napi_struct *napi, int budget) /* For the case where the last mvneta_poll did not process all * RX packets */ - cause_rx_tx |= pp->cause_rx_tx; - if (rxq_number > 1) { - while ((cause_rx_tx & MVNETA_RX_INTR_MASK_ALL) && (budget > 0)) { - int count; - struct mvneta_rx_queue *rxq; - /* get rx queue number from cause_rx_tx */ - rxq = mvneta_rx_policy(pp, cause_rx_tx); - if (!rxq) - break; - - /* process the packet in that rx queue */ - count = mvneta_rx(pp, budget, rxq); - rx_done += count; - budget -= count; - if (budget > 0) { - /* set off the rx bit of the - * corresponding bit in the cause rx - * tx register, so that next iteration - * will find the next rx queue where - * packets are received on - */ - cause_rx_tx &= ~((1 << rxq->id) << 8); - } - } - } else { - rx_done = mvneta_rx(pp, budget, &pp->rxqs[rxq_def]); - budget -= rx_done; - } + cause_rx_tx |= port->cause_rx_tx; + rx_done = mvneta_rx(pp, budget, &pp->rxqs[rxq_def]); + budget -= rx_done; if (budget > 0) { cause_rx_tx = 0; - napi_complete(napi); - local_irq_save(flags); - mvreg_write(pp, MVNETA_INTR_NEW_MASK, - MVNETA_RX_INTR_MASK(rxq_number) | - MVNETA_TX_INTR_MASK(txq_number) | - MVNETA_MISCINTR_INTR_MASK); - local_irq_restore(flags); + napi_complete(&port->napi); + enable_percpu_irq(pp->dev->irq, 0); } - pp->cause_rx_tx = cause_rx_tx; + port->cause_rx_tx = cause_rx_tx; return rx_done; } @@ -2379,26 +2342,19 @@ static void mvneta_cleanup_txqs(struct mvneta_port *pp) /* Cleanup all Rx queues */ static void mvneta_cleanup_rxqs(struct mvneta_port *pp) { - int queue; - - for (queue = 0; queue < rxq_number; queue++) - mvneta_rxq_deinit(pp, &pp->rxqs[queue]); + mvneta_rxq_deinit(pp, &pp->rxqs[rxq_def]); } /* Init all Rx queues */ static int mvneta_setup_rxqs(struct mvneta_port *pp) { - int queue; - - for (queue = 0; queue < rxq_number; queue++) { - int err = mvneta_rxq_init(pp, &pp->rxqs[queue]); - if (err) { - netdev_err(pp->dev, "%s: can't create rxq=%d\n", - __func__, queue); - mvneta_cleanup_rxqs(pp); - return err; - } + int err = mvneta_rxq_init(pp, &pp->rxqs[rxq_def]); + if (err) { + netdev_err(pp->dev, "%s: can't create rxq=%d\n", + __func__, rxq_def); + mvneta_cleanup_rxqs(pp); + return err; } return 0; @@ -2424,6 +2380,8 @@ static int mvneta_setup_txqs(struct mvneta_port *pp) static void mvneta_start_dev(struct mvneta_port *pp) { + unsigned int cpu; + mvneta_max_rx_size_set(pp, pp->pkt_size); mvneta_txq_max_tx_size_set(pp, pp->pkt_size); @@ -2431,7 +2389,11 @@ static void mvneta_start_dev(struct mvneta_port *pp) mvneta_port_enable(pp); /* Enable polling on the port */ - napi_enable(&pp->napi); + for_each_present_cpu(cpu) { + struct mvneta_pcpu_port *port = per_cpu_ptr(pp->ports, cpu); + + napi_enable(&port->napi); + } /* Unmask interrupts */ mvreg_write(pp, MVNETA_INTR_NEW_MASK, @@ -2449,9 +2411,15 @@ static void mvneta_start_dev(struct mvneta_port *pp) static void mvneta_stop_dev(struct mvneta_port *pp) { + unsigned int cpu; + phy_stop(pp->phy_dev); - napi_disable(&pp->napi); + for_each_present_cpu(cpu) { + struct mvneta_pcpu_port *port = per_cpu_ptr(pp->ports, cpu); + + napi_disable(&port->napi); + } netif_carrier_off(pp->dev); @@ -2691,6 +2659,125 @@ static void mvneta_mdio_remove(struct mvneta_port *pp) pp->phy_dev = NULL; } +static void mvneta_percpu_enable(void *arg) +{ + struct mvneta_port *pp = arg; + + enable_percpu_irq(pp->dev->irq, IRQ_TYPE_NONE); +} + +static void mvneta_percpu_disable(void *arg) +{ + struct mvneta_port *pp = arg; + + disable_percpu_irq(pp->dev->irq); +} + +static void mvneta_percpu_elect(struct mvneta_port *pp) +{ + int online_cpu_idx, cpu, i = 0; + + online_cpu_idx = rxq_def % num_online_cpus(); + + for_each_online_cpu(cpu) { + if (i == online_cpu_idx) + /* Enable per-CPU interrupt on the one CPU we + * just elected + */ + smp_call_function_single(cpu, mvneta_percpu_enable, + pp, true); + else + /* Disable per-CPU interrupt on all the other CPU */ + smp_call_function_single(cpu, mvneta_percpu_disable, + pp, true); + i++; + } +}; + +static int mvneta_percpu_notifier(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + struct mvneta_port *pp = container_of(nfb, struct mvneta_port, + cpu_notifier); + int cpu = (unsigned long)hcpu, other_cpu; + struct mvneta_pcpu_port *port = per_cpu_ptr(pp->ports, cpu); + + switch (action) { + case CPU_ONLINE: + case CPU_ONLINE_FROZEN: + netif_tx_stop_all_queues(pp->dev); + + /* We have to synchronise on tha napi of each CPU + * except the one just being waked up + */ + for_each_online_cpu(other_cpu) { + if (other_cpu != cpu) { + struct mvneta_pcpu_port *other_port = + per_cpu_ptr(pp->ports, other_cpu); + + napi_synchronize(&other_port->napi); + } + } + + /* Mask all ethernet port interrupts */ + mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0); + mvreg_write(pp, MVNETA_INTR_OLD_MASK, 0); + mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0); + napi_enable(&port->napi); + + /* Enable per-CPU interrupt on the one CPU we care + * about. + */ + mvneta_percpu_elect(pp); + + /* Unmask all ethernet port interrupts */ + mvreg_write(pp, MVNETA_INTR_NEW_MASK, + MVNETA_RX_INTR_MASK(rxq_number) | + MVNETA_TX_INTR_MASK(txq_number) | + MVNETA_MISCINTR_INTR_MASK); + mvreg_write(pp, MVNETA_INTR_MISC_MASK, + MVNETA_CAUSE_PHY_STATUS_CHANGE | + MVNETA_CAUSE_LINK_CHANGE | + MVNETA_CAUSE_PSC_SYNC_CHANGE); + netif_tx_start_all_queues(pp->dev); + break; + case CPU_DOWN_PREPARE: + case CPU_DOWN_PREPARE_FROZEN: + netif_tx_stop_all_queues(pp->dev); + /* Mask all ethernet port interrupts */ + mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0); + mvreg_write(pp, MVNETA_INTR_OLD_MASK, 0); + mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0); + + napi_synchronize(&port->napi); + napi_disable(&port->napi); + /* Disable per-CPU interrupts on the CPU that is + * brought down. + */ + smp_call_function_single(cpu, mvneta_percpu_disable, + pp, true); + + break; + case CPU_DEAD: + case CPU_DEAD_FROZEN: + /* Check if a new CPU must be elected now this on is down */ + mvneta_percpu_elect(pp); + /* Unmask all ethernet port interrupts */ + mvreg_write(pp, MVNETA_INTR_NEW_MASK, + MVNETA_RX_INTR_MASK(rxq_number) | + MVNETA_TX_INTR_MASK(txq_number) | + MVNETA_MISCINTR_INTR_MASK); + mvreg_write(pp, MVNETA_INTR_MISC_MASK, + MVNETA_CAUSE_PHY_STATUS_CHANGE | + MVNETA_CAUSE_LINK_CHANGE | + MVNETA_CAUSE_PSC_SYNC_CHANGE); + netif_tx_start_all_queues(pp->dev); + break; + } + + return NOTIFY_OK; +} + static int mvneta_open(struct net_device *dev) { struct mvneta_port *pp = netdev_priv(dev); @@ -2709,13 +2796,29 @@ static int mvneta_open(struct net_device *dev) goto err_cleanup_rxqs; /* Connect to port interrupt line */ - ret = request_irq(pp->dev->irq, mvneta_isr, 0, - MVNETA_DRIVER_NAME, pp); + ret = request_percpu_irq(pp->dev->irq, mvneta_isr, + MVNETA_DRIVER_NAME, pp->ports); if (ret) { netdev_err(pp->dev, "cannot request irq %d\n", pp->dev->irq); goto err_cleanup_txqs; } + /* Even though the documentation says that request_percpu_irq + * doesn't enable the interrupts automatically, it actually + * does so on the local CPU. + * + * Make sure it's disabled. + */ + mvneta_percpu_disable(pp); + + /* Elect a CPU to handle our RX queue interrupt */ + mvneta_percpu_elect(pp); + + /* Register a CPU notifier to handle the case where our CPU + * might be taken offline. + */ + register_cpu_notifier(&pp->cpu_notifier); + /* In default link is down */ netif_carrier_off(pp->dev); @@ -2730,7 +2833,7 @@ static int mvneta_open(struct net_device *dev) return 0; err_free_irq: - free_irq(pp->dev->irq, pp); + free_percpu_irq(pp->dev->irq, pp->ports); err_cleanup_txqs: mvneta_cleanup_txqs(pp); err_cleanup_rxqs: @@ -2742,10 +2845,14 @@ err_cleanup_rxqs: static int mvneta_stop(struct net_device *dev) { struct mvneta_port *pp = netdev_priv(dev); + int cpu; mvneta_stop_dev(pp); mvneta_mdio_remove(pp); - free_irq(dev->irq, pp); + unregister_cpu_notifier(&pp->cpu_notifier); + for_each_present_cpu(cpu) + smp_call_function_single(cpu, mvneta_percpu_disable, pp, true); + free_percpu_irq(dev->irq, pp->ports); mvneta_cleanup_rxqs(pp); mvneta_cleanup_txqs(pp); @@ -3032,14 +3139,7 @@ static int mvneta_probe(struct platform_device *pdev) const char *managed; int phy_mode; int err; - - /* Our multiqueue support is not complete, so for now, only - * allow the usage of the first RX queue - */ - if (rxq_def != 0) { - dev_err(&pdev->dev, "Invalid rxq_def argument: %d\n", rxq_def); - return -EINVAL; - } + int cpu; dev = alloc_etherdev_mqs(sizeof(struct mvneta_port), txq_number, rxq_number); if (!dev) @@ -3091,6 +3191,7 @@ static int mvneta_probe(struct platform_device *pdev) err = of_property_read_string(dn, "managed", &managed); pp->use_inband_status = (err == 0 && strcmp(managed, "in-band-status") == 0); + pp->cpu_notifier.notifier_call = mvneta_percpu_notifier; pp->clk = devm_clk_get(&pdev->dev, NULL); if (IS_ERR(pp->clk)) { @@ -3107,11 +3208,18 @@ static int mvneta_probe(struct platform_device *pdev) goto err_clk; } + /* Alloc per-cpu port structure */ + pp->ports = alloc_percpu(struct mvneta_pcpu_port); + if (!pp->ports) { + err = -ENOMEM; + goto err_clk; + } + /* Alloc per-cpu stats */ pp->stats = netdev_alloc_pcpu_stats(struct mvneta_pcpu_stats); if (!pp->stats) { err = -ENOMEM; - goto err_clk; + goto err_free_ports; } dt_mac_addr = of_get_mac_address(dn); @@ -3152,7 +3260,12 @@ static int mvneta_probe(struct platform_device *pdev) if (dram_target_info) mvneta_conf_mbus_windows(pp, dram_target_info); - netif_napi_add(dev, &pp->napi, mvneta_poll, NAPI_POLL_WEIGHT); + for_each_present_cpu(cpu) { + struct mvneta_pcpu_port *port = per_cpu_ptr(pp->ports, cpu); + + netif_napi_add(dev, &port->napi, mvneta_poll, NAPI_POLL_WEIGHT); + port->pp = pp; + } dev->features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO; dev->hw_features |= dev->features; @@ -3183,6 +3296,8 @@ static int mvneta_probe(struct platform_device *pdev) err_free_stats: free_percpu(pp->stats); +err_free_ports: + free_percpu(pp->ports); err_clk: clk_disable_unprepare(pp->clk); err_put_phy_node: @@ -3202,6 +3317,7 @@ static int mvneta_remove(struct platform_device *pdev) unregister_netdev(dev); clk_disable_unprepare(pp->clk); + free_percpu(pp->ports); free_percpu(pp->stats); irq_dispose_mapping(dev->irq); of_node_put(pp->phy_node); diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index d9f4498832a1..5606a043063e 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -4819,6 +4819,18 @@ static struct net_device *sky2_init_netdev(struct sky2_hw *hw, unsigned port, memcpy_fromio(dev->dev_addr, hw->regs + B2_MAC_1 + port * 8, ETH_ALEN); + /* if the address is invalid, use a random value */ + if (!is_valid_ether_addr(dev->dev_addr)) { + struct sockaddr sa = { AF_UNSPEC }; + + netdev_warn(dev, + "Invalid MAC address, defaulting to random\n"); + eth_hw_addr_random(dev); + memcpy(sa.sa_data, dev->dev_addr, ETH_ALEN); + if (sky2_set_mac_address(dev, &sa)) + netdev_warn(dev, "Failed to set MAC address.\n"); + } + return dev; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 75ff58dc1ff5..84838c2f528f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -1136,6 +1136,7 @@ void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, unsigned long vector) mlx5_free_cmd_msg(dev, ent->out); free_msg(dev, ent->in); + err = err ? err : ent->status; free_cmd(ent); callback(err, context); } else { @@ -1363,6 +1364,7 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev) int err; int i; + memset(cmd, 0, sizeof(*cmd)); cmd_if_rev = cmdif_rev(dev); if (cmd_if_rev != CMD_IF_REV) { dev_err(&dev->pdev->dev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c index 04ab7e445eae..b51e42d6fbec 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c @@ -242,6 +242,7 @@ int mlx5_init_cq_table(struct mlx5_core_dev *dev) struct mlx5_cq_table *table = &dev->priv.cq_table; int err; + memset(table, 0, sizeof(*table)); spin_lock_init(&table->lock); INIT_RADIX_TREE(&table->tree, GFP_ATOMIC); err = mlx5_cq_debugfs_init(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 59874d666cff..bb801a9bbd42 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -1367,13 +1367,13 @@ int mlx5e_open_locked(struct net_device *netdev) err = mlx5e_set_dev_port_mtu(netdev); if (err) - return err; + goto err_clear_state_opened_flag; err = mlx5e_open_channels(priv); if (err) { netdev_err(netdev, "%s: mlx5e_open_channels failed, %d\n", __func__, err); - return err; + goto err_clear_state_opened_flag; } mlx5e_update_carrier(priv); @@ -1382,6 +1382,10 @@ int mlx5e_open_locked(struct net_device *netdev) schedule_delayed_work(&priv->update_stats_work, 0); return 0; + +err_clear_state_opened_flag: + clear_bit(MLX5E_STATE_OPENED, &priv->state); + return err; } static int mlx5e_open(struct net_device *netdev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index a40b96d4c662..1f01fe8fde42 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -346,6 +346,7 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx, int inlen; eq->nent = roundup_pow_of_two(nent + MLX5_NUM_SPARE_EQE); + eq->cons_index = 0; err = mlx5_buf_alloc(dev, eq->nent * MLX5_EQE_SIZE, &eq->buf); if (err) return err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 292d76f2a904..1277c427242a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -46,12 +46,15 @@ enum { enum { MLX5_HEALTH_SYNDR_FW_ERR = 0x1, MLX5_HEALTH_SYNDR_IRISC_ERR = 0x7, + MLX5_HEALTH_SYNDR_HW_UNRECOVERABLE_ERR = 0x8, MLX5_HEALTH_SYNDR_CRC_ERR = 0x9, MLX5_HEALTH_SYNDR_FETCH_PCI_ERR = 0xa, MLX5_HEALTH_SYNDR_HW_FTL_ERR = 0xb, MLX5_HEALTH_SYNDR_ASYNC_EQ_OVERRUN_ERR = 0xc, MLX5_HEALTH_SYNDR_EQ_ERR = 0xd, + MLX5_HEALTH_SYNDR_EQ_INV = 0xe, MLX5_HEALTH_SYNDR_FFSER_ERR = 0xf, + MLX5_HEALTH_SYNDR_HIGH_TEMP = 0x10 }; static DEFINE_SPINLOCK(health_lock); @@ -88,6 +91,8 @@ static const char *hsynd_str(u8 synd) return "firmware internal error"; case MLX5_HEALTH_SYNDR_IRISC_ERR: return "irisc not responding"; + case MLX5_HEALTH_SYNDR_HW_UNRECOVERABLE_ERR: + return "unrecoverable hardware error"; case MLX5_HEALTH_SYNDR_CRC_ERR: return "firmware CRC error"; case MLX5_HEALTH_SYNDR_FETCH_PCI_ERR: @@ -98,8 +103,12 @@ static const char *hsynd_str(u8 synd) return "async EQ buffer overrun"; case MLX5_HEALTH_SYNDR_EQ_ERR: return "EQ error"; + case MLX5_HEALTH_SYNDR_EQ_INV: + return "Invalid EQ refrenced"; case MLX5_HEALTH_SYNDR_FFSER_ERR: return "FFSER error"; + case MLX5_HEALTH_SYNDR_HIGH_TEMP: + return "High temprature"; default: return "unrecognized error"; } @@ -130,7 +139,7 @@ static void print_health_info(struct mlx5_core_dev *dev) pr_info("hw_id 0x%08x\n", read_be32(&h->hw_id)); pr_info("irisc_index %d\n", readb(&h->irisc_index)); pr_info("synd 0x%x: %s\n", readb(&h->synd), hsynd_str(readb(&h->synd))); - pr_info("ext_sync 0x%04x\n", read_be16(&h->ext_sync)); + pr_info("ext_sync 0x%04x\n", read_be16(&h->ext_synd)); } static void poll_health(unsigned long data) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 03aabdd79abe..7718f6ac6214 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -672,12 +672,126 @@ static void unmap_bf_area(struct mlx5_core_dev *dev) io_mapping_free(dev->priv.bf_mapping); } -static int mlx5_dev_init(struct mlx5_core_dev *dev, struct pci_dev *pdev) +static void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv) +{ + struct mlx5_device_context *dev_ctx; + struct mlx5_core_dev *dev = container_of(priv, struct mlx5_core_dev, priv); + + dev_ctx = kmalloc(sizeof(*dev_ctx), GFP_KERNEL); + if (!dev_ctx) + return; + + dev_ctx->intf = intf; + dev_ctx->context = intf->add(dev); + + if (dev_ctx->context) { + spin_lock_irq(&priv->ctx_lock); + list_add_tail(&dev_ctx->list, &priv->ctx_list); + spin_unlock_irq(&priv->ctx_lock); + } else { + kfree(dev_ctx); + } +} + +static void mlx5_remove_device(struct mlx5_interface *intf, struct mlx5_priv *priv) +{ + struct mlx5_device_context *dev_ctx; + struct mlx5_core_dev *dev = container_of(priv, struct mlx5_core_dev, priv); + + list_for_each_entry(dev_ctx, &priv->ctx_list, list) + if (dev_ctx->intf == intf) { + spin_lock_irq(&priv->ctx_lock); + list_del(&dev_ctx->list); + spin_unlock_irq(&priv->ctx_lock); + + intf->remove(dev, dev_ctx->context); + kfree(dev_ctx); + return; + } +} + +static int mlx5_register_device(struct mlx5_core_dev *dev) { struct mlx5_priv *priv = &dev->priv; - int err; + struct mlx5_interface *intf; + + mutex_lock(&intf_mutex); + list_add_tail(&priv->dev_list, &dev_list); + list_for_each_entry(intf, &intf_list, list) + mlx5_add_device(intf, priv); + mutex_unlock(&intf_mutex); + + return 0; +} + +static void mlx5_unregister_device(struct mlx5_core_dev *dev) +{ + struct mlx5_priv *priv = &dev->priv; + struct mlx5_interface *intf; + + mutex_lock(&intf_mutex); + list_for_each_entry(intf, &intf_list, list) + mlx5_remove_device(intf, priv); + list_del(&priv->dev_list); + mutex_unlock(&intf_mutex); +} + +int mlx5_register_interface(struct mlx5_interface *intf) +{ + struct mlx5_priv *priv; + + if (!intf->add || !intf->remove) + return -EINVAL; + + mutex_lock(&intf_mutex); + list_add_tail(&intf->list, &intf_list); + list_for_each_entry(priv, &dev_list, dev_list) + mlx5_add_device(intf, priv); + mutex_unlock(&intf_mutex); + + return 0; +} +EXPORT_SYMBOL(mlx5_register_interface); + +void mlx5_unregister_interface(struct mlx5_interface *intf) +{ + struct mlx5_priv *priv; + + mutex_lock(&intf_mutex); + list_for_each_entry(priv, &dev_list, dev_list) + mlx5_remove_device(intf, priv); + list_del(&intf->list); + mutex_unlock(&intf_mutex); +} +EXPORT_SYMBOL(mlx5_unregister_interface); + +void *mlx5_get_protocol_dev(struct mlx5_core_dev *mdev, int protocol) +{ + struct mlx5_priv *priv = &mdev->priv; + struct mlx5_device_context *dev_ctx; + unsigned long flags; + void *result = NULL; + + spin_lock_irqsave(&priv->ctx_lock, flags); + + list_for_each_entry(dev_ctx, &mdev->priv.ctx_list, list) + if ((dev_ctx->intf->protocol == protocol) && + dev_ctx->intf->get_dev) { + result = dev_ctx->intf->get_dev(dev_ctx->context); + break; + } + + spin_unlock_irqrestore(&priv->ctx_lock, flags); + + return result; +} +EXPORT_SYMBOL(mlx5_get_protocol_dev); + +static int mlx5_pci_init(struct mlx5_core_dev *dev, struct mlx5_priv *priv) +{ + struct pci_dev *pdev = dev->pdev; + int err = 0; - dev->pdev = pdev; pci_set_drvdata(dev->pdev, dev); strncpy(priv->name, dev_name(&pdev->dev), MLX5_MAX_NAME_LEN); priv->name[MLX5_MAX_NAME_LEN - 1] = 0; @@ -721,13 +835,42 @@ static int mlx5_dev_init(struct mlx5_core_dev *dev, struct pci_dev *pdev) dev_err(&pdev->dev, "Failed mapping initialization segment, aborting\n"); goto err_clr_master; } + + return 0; + +err_clr_master: + pci_clear_master(dev->pdev); + release_bar(dev->pdev); +err_disable: + pci_disable_device(dev->pdev); + +err_dbg: + debugfs_remove(priv->dbg_root); + return err; +} + +static void mlx5_pci_close(struct mlx5_core_dev *dev, struct mlx5_priv *priv) +{ + iounmap(dev->iseg); + pci_clear_master(dev->pdev); + release_bar(dev->pdev); + pci_disable_device(dev->pdev); + debugfs_remove(priv->dbg_root); +} + +#define MLX5_IB_MOD "mlx5_ib" +static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv) +{ + struct pci_dev *pdev = dev->pdev; + int err; + dev_info(&pdev->dev, "firmware version: %d.%d.%d\n", fw_rev_maj(dev), fw_rev_min(dev), fw_rev_sub(dev)); err = mlx5_cmd_init(dev); if (err) { dev_err(&pdev->dev, "Failed initializing command interface, aborting\n"); - goto err_unmap; + return err; } mlx5_pagealloc_init(dev); @@ -842,8 +985,25 @@ static int mlx5_dev_init(struct mlx5_core_dev *dev, struct pci_dev *pdev) mlx5_init_srq_table(dev); mlx5_init_mr_table(dev); + err = mlx5_register_device(dev); + if (err) { + dev_err(&pdev->dev, "mlx5_register_device failed %d\n", err); + goto err_reg_dev; + } + + err = request_module_nowait(MLX5_IB_MOD); + if (err) + pr_info("failed request module on %s\n", MLX5_IB_MOD); + return 0; +err_reg_dev: + mlx5_cleanup_mr_table(dev); + mlx5_cleanup_srq_table(dev); + mlx5_cleanup_qp_table(dev); + mlx5_cleanup_cq_table(dev); + mlx5_irq_clear_affinity_hints(dev); + err_unmap_bf_area: unmap_bf_area(dev); @@ -881,25 +1041,14 @@ err_pagealloc_cleanup: mlx5_pagealloc_cleanup(dev); mlx5_cmd_cleanup(dev); -err_unmap: - iounmap(dev->iseg); - -err_clr_master: - pci_clear_master(dev->pdev); - release_bar(dev->pdev); - -err_disable: - pci_disable_device(dev->pdev); - -err_dbg: - debugfs_remove(priv->dbg_root); return err; } -static void mlx5_dev_cleanup(struct mlx5_core_dev *dev) +static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv) { - struct mlx5_priv *priv = &dev->priv; + mlx5_unregister_device(dev); + mlx5_cleanup_mr_table(dev); mlx5_cleanup_srq_table(dev); mlx5_cleanup_qp_table(dev); mlx5_cleanup_cq_table(dev); @@ -913,134 +1062,16 @@ static void mlx5_dev_cleanup(struct mlx5_core_dev *dev) mlx5_stop_health_poll(dev); if (mlx5_cmd_teardown_hca(dev)) { dev_err(&dev->pdev->dev, "tear_down_hca failed, skip cleanup\n"); - return; + return 1; } mlx5_pagealloc_stop(dev); mlx5_reclaim_startup_pages(dev); mlx5_core_disable_hca(dev); mlx5_pagealloc_cleanup(dev); mlx5_cmd_cleanup(dev); - iounmap(dev->iseg); - pci_clear_master(dev->pdev); - release_bar(dev->pdev); - pci_disable_device(dev->pdev); - debugfs_remove(priv->dbg_root); -} - -static void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv) -{ - struct mlx5_device_context *dev_ctx; - struct mlx5_core_dev *dev = container_of(priv, struct mlx5_core_dev, priv); - - dev_ctx = kmalloc(sizeof(*dev_ctx), GFP_KERNEL); - if (!dev_ctx) { - pr_warn("mlx5_add_device: alloc context failed\n"); - return; - } - - dev_ctx->intf = intf; - dev_ctx->context = intf->add(dev); - - if (dev_ctx->context) { - spin_lock_irq(&priv->ctx_lock); - list_add_tail(&dev_ctx->list, &priv->ctx_list); - spin_unlock_irq(&priv->ctx_lock); - } else { - kfree(dev_ctx); - } -} - -static void mlx5_remove_device(struct mlx5_interface *intf, struct mlx5_priv *priv) -{ - struct mlx5_device_context *dev_ctx; - struct mlx5_core_dev *dev = container_of(priv, struct mlx5_core_dev, priv); - - list_for_each_entry(dev_ctx, &priv->ctx_list, list) - if (dev_ctx->intf == intf) { - spin_lock_irq(&priv->ctx_lock); - list_del(&dev_ctx->list); - spin_unlock_irq(&priv->ctx_lock); - - intf->remove(dev, dev_ctx->context); - kfree(dev_ctx); - return; - } -} -static int mlx5_register_device(struct mlx5_core_dev *dev) -{ - struct mlx5_priv *priv = &dev->priv; - struct mlx5_interface *intf; - - mutex_lock(&intf_mutex); - list_add_tail(&priv->dev_list, &dev_list); - list_for_each_entry(intf, &intf_list, list) - mlx5_add_device(intf, priv); - mutex_unlock(&intf_mutex); return 0; } -static void mlx5_unregister_device(struct mlx5_core_dev *dev) -{ - struct mlx5_priv *priv = &dev->priv; - struct mlx5_interface *intf; - - mutex_lock(&intf_mutex); - list_for_each_entry(intf, &intf_list, list) - mlx5_remove_device(intf, priv); - list_del(&priv->dev_list); - mutex_unlock(&intf_mutex); -} - -int mlx5_register_interface(struct mlx5_interface *intf) -{ - struct mlx5_priv *priv; - - if (!intf->add || !intf->remove) - return -EINVAL; - - mutex_lock(&intf_mutex); - list_add_tail(&intf->list, &intf_list); - list_for_each_entry(priv, &dev_list, dev_list) - mlx5_add_device(intf, priv); - mutex_unlock(&intf_mutex); - - return 0; -} -EXPORT_SYMBOL(mlx5_register_interface); - -void mlx5_unregister_interface(struct mlx5_interface *intf) -{ - struct mlx5_priv *priv; - - mutex_lock(&intf_mutex); - list_for_each_entry(priv, &dev_list, dev_list) - mlx5_remove_device(intf, priv); - list_del(&intf->list); - mutex_unlock(&intf_mutex); -} -EXPORT_SYMBOL(mlx5_unregister_interface); - -void *mlx5_get_protocol_dev(struct mlx5_core_dev *mdev, int protocol) -{ - struct mlx5_priv *priv = &mdev->priv; - struct mlx5_device_context *dev_ctx; - unsigned long flags; - void *result = NULL; - - spin_lock_irqsave(&priv->ctx_lock, flags); - - list_for_each_entry(dev_ctx, &mdev->priv.ctx_list, list) - if ((dev_ctx->intf->protocol == protocol) && - dev_ctx->intf->get_dev) { - result = dev_ctx->intf->get_dev(dev_ctx->context); - break; - } - - spin_unlock_irqrestore(&priv->ctx_lock, flags); - - return result; -} -EXPORT_SYMBOL(mlx5_get_protocol_dev); static void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event, unsigned long param) @@ -1064,7 +1095,6 @@ struct mlx5_core_event_handler { void *data); }; -#define MLX5_IB_MOD "mlx5_ib" static int init_one(struct pci_dev *pdev, const struct pci_device_id *id) @@ -1088,40 +1118,45 @@ static int init_one(struct pci_dev *pdev, prof_sel = MLX5_DEFAULT_PROF; } dev->profile = &profile[prof_sel]; + dev->pdev = pdev; dev->event = mlx5_core_event; INIT_LIST_HEAD(&priv->ctx_list); spin_lock_init(&priv->ctx_lock); - err = mlx5_dev_init(dev, pdev); + err = mlx5_pci_init(dev, priv); if (err) { - dev_err(&pdev->dev, "mlx5_dev_init failed %d\n", err); - goto out; + dev_err(&pdev->dev, "mlx5_pci_init failed with error code %d\n", err); + goto clean_dev; } - err = mlx5_register_device(dev); + err = mlx5_load_one(dev, priv); if (err) { - dev_err(&pdev->dev, "mlx5_register_device failed %d\n", err); - goto out_init; + dev_err(&pdev->dev, "mlx5_load_one failed with error code %d\n", err); + goto close_pci; } - err = request_module_nowait(MLX5_IB_MOD); - if (err) - pr_info("failed request module on %s\n", MLX5_IB_MOD); - return 0; -out_init: - mlx5_dev_cleanup(dev); -out: +close_pci: + mlx5_pci_close(dev, priv); +clean_dev: + pci_set_drvdata(pdev, NULL); kfree(dev); + return err; } + static void remove_one(struct pci_dev *pdev) { struct mlx5_core_dev *dev = pci_get_drvdata(pdev); + struct mlx5_priv *priv = &dev->priv; - mlx5_unregister_device(dev); - mlx5_dev_cleanup(dev); + if (mlx5_unload_one(dev, priv)) { + dev_err(&dev->pdev->dev, "mlx5_unload_one failed\n"); + return; + } + mlx5_pci_close(dev, priv); + pci_set_drvdata(pdev, NULL); kfree(dev); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c index 1adb300dd850..6fa22b51e460 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c @@ -40,6 +40,7 @@ void mlx5_init_mr_table(struct mlx5_core_dev *dev) { struct mlx5_mr_table *table = &dev->priv.mr_table; + memset(table, 0, sizeof(*table)); rwlock_init(&table->lock); INIT_RADIX_TREE(&table->tree, GFP_ATOMIC); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c index 8a64542abc16..76432a510ac2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c @@ -275,12 +275,36 @@ out_alloc: return err; } + +static void page_notify_fail(struct mlx5_core_dev *dev, u16 func_id) +{ + struct mlx5_manage_pages_inbox *in; + struct mlx5_manage_pages_outbox out; + int err; + + in = kzalloc(sizeof(*in), GFP_KERNEL); + if (!in) + return; + + memset(&out, 0, sizeof(out)); + in->hdr.opcode = cpu_to_be16(MLX5_CMD_OP_MANAGE_PAGES); + in->hdr.opmod = cpu_to_be16(MLX5_PAGES_CANT_GIVE); + in->func_id = cpu_to_be16(func_id); + err = mlx5_cmd_exec(dev, in, sizeof(*in), &out, sizeof(out)); + if (!err) + err = mlx5_cmd_status_to_err(&out.hdr); + + if (err) + mlx5_core_warn(dev, "page notify failed\n"); + + kfree(in); +} + static int give_pages(struct mlx5_core_dev *dev, u16 func_id, int npages, int notify_fail) { struct mlx5_manage_pages_inbox *in; struct mlx5_manage_pages_outbox out; - struct mlx5_manage_pages_inbox *nin; int inlen; u64 addr; int err; @@ -289,8 +313,9 @@ static int give_pages(struct mlx5_core_dev *dev, u16 func_id, int npages, inlen = sizeof(*in) + npages * sizeof(in->pas[0]); in = mlx5_vzalloc(inlen); if (!in) { + err = -ENOMEM; mlx5_core_warn(dev, "vzalloc failed %d\n", inlen); - return -ENOMEM; + goto out_free; } memset(&out, 0, sizeof(out)); @@ -316,43 +341,29 @@ retry: if (err) { mlx5_core_warn(dev, "func_id 0x%x, npages %d, err %d\n", func_id, npages, err); - goto out_alloc; + goto out_4k; } dev->priv.fw_pages += npages; - if (out.hdr.status) { - err = mlx5_cmd_status_to_err(&out.hdr); - if (err) { - mlx5_core_warn(dev, "func_id 0x%x, npages %d, status %d\n", - func_id, npages, out.hdr.status); - goto out_alloc; - } + err = mlx5_cmd_status_to_err(&out.hdr); + if (err) { + mlx5_core_warn(dev, "func_id 0x%x, npages %d, status %d\n", + func_id, npages, out.hdr.status); + goto out_4k; } mlx5_core_dbg(dev, "err %d\n", err); - goto out_free; - -out_alloc: - if (notify_fail) { - nin = kzalloc(sizeof(*nin), GFP_KERNEL); - if (!nin) { - mlx5_core_warn(dev, "allocation failed\n"); - goto out_4k; - } - memset(&out, 0, sizeof(out)); - nin->hdr.opcode = cpu_to_be16(MLX5_CMD_OP_MANAGE_PAGES); - nin->hdr.opmod = cpu_to_be16(MLX5_PAGES_CANT_GIVE); - if (mlx5_cmd_exec(dev, nin, sizeof(*nin), &out, sizeof(out))) - mlx5_core_warn(dev, "page notify failed\n"); - kfree(nin); - } + kvfree(in); + return 0; out_4k: for (i--; i >= 0; i--) free_4k(dev, be64_to_cpu(in->pas[i])); out_free: kvfree(in); + if (notify_fail) + page_notify_fail(dev, func_id); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c index 821caaab9bfb..ae302614e74b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c @@ -90,16 +90,13 @@ int mlx5_set_port_caps(struct mlx5_core_dev *dev, u8 port_num, u32 caps) { struct mlx5_reg_pcap in; struct mlx5_reg_pcap out; - int err; memset(&in, 0, sizeof(in)); in.caps_127_96 = cpu_to_be32(caps); in.port_num = port_num; - err = mlx5_core_access_reg(dev, &in, sizeof(in), &out, - sizeof(out), MLX5_REG_PCAP, 0, 1); - - return err; + return mlx5_core_access_reg(dev, &in, sizeof(in), &out, + sizeof(out), MLX5_REG_PCAP, 0, 1); } EXPORT_SYMBOL_GPL(mlx5_set_port_caps); @@ -107,16 +104,13 @@ int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys, int ptys_size, int proto_mask, u8 local_port) { u32 in[MLX5_ST_SZ_DW(ptys_reg)]; - int err; memset(in, 0, sizeof(in)); MLX5_SET(ptys_reg, in, local_port, local_port); MLX5_SET(ptys_reg, in, proto_mask, proto_mask); - err = mlx5_core_access_reg(dev, in, sizeof(in), ptys, - ptys_size, MLX5_REG_PTYS, 0, 0); - - return err; + return mlx5_core_access_reg(dev, in, sizeof(in), ptys, + ptys_size, MLX5_REG_PTYS, 0, 0); } EXPORT_SYMBOL_GPL(mlx5_query_port_ptys); @@ -199,7 +193,6 @@ int mlx5_set_port_proto(struct mlx5_core_dev *dev, u32 proto_admin, { u32 in[MLX5_ST_SZ_DW(ptys_reg)]; u32 out[MLX5_ST_SZ_DW(ptys_reg)]; - int err; memset(in, 0, sizeof(in)); @@ -210,9 +203,8 @@ int mlx5_set_port_proto(struct mlx5_core_dev *dev, u32 proto_admin, else MLX5_SET(ptys_reg, in, ib_proto_admin, proto_admin); - err = mlx5_core_access_reg(dev, in, sizeof(in), out, - sizeof(out), MLX5_REG_PTYS, 0, 1); - return err; + return mlx5_core_access_reg(dev, in, sizeof(in), out, + sizeof(out), MLX5_REG_PTYS, 0, 1); } EXPORT_SYMBOL_GPL(mlx5_set_port_proto); @@ -250,7 +242,7 @@ int mlx5_query_port_admin_status(struct mlx5_core_dev *dev, return err; *status = MLX5_GET(paos_reg, out, admin_status); - return err; + return 0; } EXPORT_SYMBOL_GPL(mlx5_query_port_admin_status); @@ -308,15 +300,12 @@ static int mlx5_query_port_pvlc(struct mlx5_core_dev *dev, u32 *pvlc, int pvlc_size, u8 local_port) { u32 in[MLX5_ST_SZ_DW(pvlc_reg)]; - int err; memset(in, 0, sizeof(in)); MLX5_SET(ptys_reg, in, local_port, local_port); - err = mlx5_core_access_reg(dev, in, sizeof(in), pvlc, - pvlc_size, MLX5_REG_PVLC, 0, 0); - - return err; + return mlx5_core_access_reg(dev, in, sizeof(in), pvlc, + pvlc_size, MLX5_REG_PVLC, 0, 0); } int mlx5_query_port_vl_hw_cap(struct mlx5_core_dev *dev, @@ -339,16 +328,14 @@ int mlx5_set_port_pause(struct mlx5_core_dev *dev, u32 rx_pause, u32 tx_pause) { u32 in[MLX5_ST_SZ_DW(pfcc_reg)]; u32 out[MLX5_ST_SZ_DW(pfcc_reg)]; - int err; memset(in, 0, sizeof(in)); MLX5_SET(pfcc_reg, in, local_port, 1); MLX5_SET(pfcc_reg, in, pptx, tx_pause); MLX5_SET(pfcc_reg, in, pprx, rx_pause); - err = mlx5_core_access_reg(dev, in, sizeof(in), out, - sizeof(out), MLX5_REG_PFCC, 0, 1); - return err; + return mlx5_core_access_reg(dev, in, sizeof(in), out, + sizeof(out), MLX5_REG_PFCC, 0, 1); } EXPORT_SYMBOL_GPL(mlx5_set_port_pause); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c index 8b494b562263..30e2ba3f5f16 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c @@ -345,6 +345,7 @@ void mlx5_init_qp_table(struct mlx5_core_dev *dev) { struct mlx5_qp_table *table = &dev->priv.qp_table; + memset(table, 0, sizeof(*table)); spin_lock_init(&table->lock); INIT_RADIX_TREE(&table->tree, GFP_ATOMIC); mlx5_qp_debugfs_init(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/srq.c b/drivers/net/ethernet/mellanox/mlx5/core/srq.c index c48f504ccbeb..ffada801976b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/srq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/srq.c @@ -531,6 +531,7 @@ void mlx5_init_srq_table(struct mlx5_core_dev *dev) { struct mlx5_srq_table *table = &dev->priv.srq_table; + memset(table, 0, sizeof(*table)); spin_lock_init(&table->lock); INIT_RADIX_TREE(&table->tree, GFP_ATOMIC); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c index b4c87c7b0cf0..d7068f54e800 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/transobj.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/transobj.c @@ -177,7 +177,7 @@ int mlx5_core_modify_tir(struct mlx5_core_dev *dev, u32 tirn, u32 *in, void mlx5_core_destroy_tir(struct mlx5_core_dev *dev, u32 tirn) { - u32 in[MLX5_ST_SZ_DW(destroy_tir_out)]; + u32 in[MLX5_ST_SZ_DW(destroy_tir_in)]; u32 out[MLX5_ST_SZ_DW(destroy_tir_out)]; memset(in, 0, sizeof(in)); @@ -206,7 +206,7 @@ int mlx5_core_create_tis(struct mlx5_core_dev *dev, u32 *in, int inlen, void mlx5_core_destroy_tis(struct mlx5_core_dev *dev, u32 tisn) { - u32 in[MLX5_ST_SZ_DW(destroy_tis_out)]; + u32 in[MLX5_ST_SZ_DW(destroy_tis_in)]; u32 out[MLX5_ST_SZ_DW(destroy_tis_out)]; memset(in, 0, sizeof(in)); diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c index 686334f4588d..deae10d7426d 100644 --- a/drivers/net/ethernet/realtek/8139cp.c +++ b/drivers/net/ethernet/realtek/8139cp.c @@ -175,7 +175,7 @@ enum { LastFrag = (1 << 28), /* Final segment of a packet */ LargeSend = (1 << 27), /* TCP Large Send Offload (TSO) */ MSSShift = 16, /* MSS value position */ - MSSMask = 0xfff, /* MSS value: 11 bits */ + MSSMask = 0x7ff, /* MSS value: 11 bits */ TxError = (1 << 23), /* Tx error summary */ RxError = (1 << 20), /* Rx error summary */ IPCS = (1 << 18), /* Calculate IP checksum */ @@ -754,10 +754,16 @@ static netdev_tx_t cp_start_xmit (struct sk_buff *skb, eor = (entry == (CP_TX_RING_SIZE - 1)) ? RingEnd : 0; mss = skb_shinfo(skb)->gso_size; + if (mss > MSSMask) { + WARN_ONCE(1, "Net bug: GSO size %d too large for 8139CP\n", + mss); + goto out_dma_error; + } + opts2 = cpu_to_le32(cp_tx_vlan_tag(skb)); opts1 = DescOwn; if (mss) - opts1 |= LargeSend | ((mss & MSSMask) << MSSShift); + opts1 |= LargeSend | (mss << MSSShift); else if (skb->ip_summed == CHECKSUM_PARTIAL) { const struct iphdr *ip = ip_hdr(skb); if (ip->protocol == IPPROTO_TCP) @@ -1852,6 +1858,15 @@ static void cp_set_d3_state (struct cp_private *cp) pci_set_power_state (cp->pdev, PCI_D3hot); } +static netdev_features_t cp_features_check(struct sk_buff *skb, + struct net_device *dev, + netdev_features_t features) +{ + if (skb_shinfo(skb)->gso_size > MSSMask) + features &= ~NETIF_F_TSO; + + return vlan_features_check(skb, features); +} static const struct net_device_ops cp_netdev_ops = { .ndo_open = cp_open, .ndo_stop = cp_close, @@ -1864,6 +1879,7 @@ static const struct net_device_ops cp_netdev_ops = { .ndo_tx_timeout = cp_tx_timeout, .ndo_set_features = cp_set_features, .ndo_change_mtu = cp_change_mtu, + .ndo_features_check = cp_features_check, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = cp_poll_controller, @@ -1983,12 +1999,12 @@ static int cp_init_one (struct pci_dev *pdev, const struct pci_device_id *ent) dev->ethtool_ops = &cp_ethtool_ops; dev->watchdog_timeo = TX_TIMEOUT; - dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX; + dev->features |= NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO | + NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX; if (pci_using_dac) dev->features |= NETIF_F_HIGHDMA; - /* disabled by default until verified */ dev->hw_features |= NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX; dev->vlan_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO | diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index 34ac41ac9e61..9773f5b65296 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -152,8 +152,9 @@ struct rocker_fdb_tbl_entry { struct hlist_node entry; u32 key_crc32; /* key */ bool learned; + unsigned long touched; struct rocker_fdb_tbl_key { - u32 pport; + struct rocker_port *rocker_port; u8 addr[ETH_ALEN]; __be16 vlan_id; } key; @@ -220,13 +221,13 @@ struct rocker_port { __be16 internal_vlan_id; int stp_state; u32 brport_flags; + unsigned long ageing_time; bool ctrls[ROCKER_CTRL_MAX]; unsigned long vlan_bitmap[ROCKER_VLAN_BITMAP_LEN]; struct napi_struct napi_tx; struct napi_struct napi_rx; struct rocker_dma_ring_info tx_ring; struct rocker_dma_ring_info rx_ring; - struct list_head trans_mem; }; struct rocker { @@ -246,6 +247,7 @@ struct rocker { u64 flow_tbl_next_cookie; DECLARE_HASHTABLE(group_tbl, 16); spinlock_t group_tbl_lock; /* for group tbl accesses */ + struct timer_list fdb_cleanup_timer; DECLARE_HASHTABLE(fdb_tbl, 16); spinlock_t fdb_tbl_lock; /* for fdb tbl accesses */ unsigned long internal_vlan_bitmap[ROCKER_INTERNAL_VLAN_BITMAP_LEN]; @@ -340,74 +342,63 @@ static bool rocker_port_is_ovsed(const struct rocker_port *rocker_port) #define ROCKER_OP_FLAG_REFRESH BIT(3) static void *__rocker_port_mem_alloc(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + struct switchdev_trans *trans, int flags, size_t size) { - struct list_head *elem = NULL; + struct switchdev_trans_item *elem = NULL; gfp_t gfp_flags = (flags & ROCKER_OP_FLAG_NOWAIT) ? GFP_ATOMIC : GFP_KERNEL; /* If in transaction prepare phase, allocate the memory - * and enqueue it on a per-port list. If in transaction - * commit phase, dequeue the memory from the per-port list + * and enqueue it on a transaction. If in transaction + * commit phase, dequeue the memory from the transaction * rather than re-allocating the memory. The idea is the * driver code paths for prepare and commit are identical * so the memory allocated in the prepare phase is the * memory used in the commit phase. */ - switch (trans) { - case SWITCHDEV_TRANS_PREPARE: + if (!trans) { + elem = kzalloc(size + sizeof(*elem), gfp_flags); + } else if (switchdev_trans_ph_prepare(trans)) { elem = kzalloc(size + sizeof(*elem), gfp_flags); if (!elem) return NULL; - list_add_tail(elem, &rocker_port->trans_mem); - break; - case SWITCHDEV_TRANS_COMMIT: - BUG_ON(list_empty(&rocker_port->trans_mem)); - elem = rocker_port->trans_mem.next; - list_del_init(elem); - break; - case SWITCHDEV_TRANS_NONE: - elem = kzalloc(size + sizeof(*elem), gfp_flags); - if (elem) - INIT_LIST_HEAD(elem); - break; - default: - break; + switchdev_trans_item_enqueue(trans, elem, kfree, elem); + } else { + elem = switchdev_trans_item_dequeue(trans); } return elem ? elem + 1 : NULL; } static void *rocker_port_kzalloc(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + struct switchdev_trans *trans, int flags, size_t size) { return __rocker_port_mem_alloc(rocker_port, trans, flags, size); } static void *rocker_port_kcalloc(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + struct switchdev_trans *trans, int flags, size_t n, size_t size) { return __rocker_port_mem_alloc(rocker_port, trans, flags, n * size); } -static void rocker_port_kfree(enum switchdev_trans trans, const void *mem) +static void rocker_port_kfree(struct switchdev_trans *trans, const void *mem) { - struct list_head *elem; + struct switchdev_trans_item *elem; /* Frees are ignored if in transaction prepare phase. The * memory remains on the per-port list until freed in the * commit phase. */ - if (trans == SWITCHDEV_TRANS_PREPARE) + if (switchdev_trans_ph_prepare(trans)) return; - elem = (struct list_head *)mem - 1; - BUG_ON(!list_empty(elem)); + elem = (struct switchdev_trans_item *) mem - 1; kfree(elem); } @@ -430,7 +421,7 @@ static void rocker_wait_init(struct rocker_wait *wait) } static struct rocker_wait *rocker_wait_create(struct rocker_port *rocker_port, - enum switchdev_trans trans, + struct switchdev_trans *trans, int flags) { struct rocker_wait *wait; @@ -442,7 +433,7 @@ static struct rocker_wait *rocker_wait_create(struct rocker_port *rocker_port, return wait; } -static void rocker_wait_destroy(enum switchdev_trans trans, +static void rocker_wait_destroy(struct switchdev_trans *trans, struct rocker_wait *wait) { rocker_port_kfree(trans, wait); @@ -1408,7 +1399,7 @@ static irqreturn_t rocker_cmd_irq_handler(int irq, void *dev_id) wait = rocker_desc_cookie_ptr_get(desc_info); if (wait->nowait) { rocker_desc_gen_clear(desc_info); - rocker_wait_destroy(SWITCHDEV_TRANS_NONE, wait); + rocker_wait_destroy(NULL, wait); } else { rocker_wait_wake_up(wait); } @@ -1463,7 +1454,7 @@ static int rocker_event_link_change(const struct rocker *rocker, } static int rocker_port_fdb(struct rocker_port *rocker_port, - enum switchdev_trans trans, + struct switchdev_trans *trans, const unsigned char *addr, __be16 vlan_id, int flags); @@ -1496,8 +1487,7 @@ static int rocker_event_mac_vlan_seen(const struct rocker *rocker, rocker_port->stp_state != BR_STATE_FORWARDING) return 0; - return rocker_port_fdb(rocker_port, SWITCHDEV_TRANS_NONE, - addr, vlan_id, flags); + return rocker_port_fdb(rocker_port, NULL, addr, vlan_id, flags); } static int rocker_event_process(const struct rocker *rocker, @@ -1582,7 +1572,7 @@ typedef int (*rocker_cmd_proc_cb_t)(const struct rocker_port *rocker_port, void *priv); static int rocker_cmd_exec(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + struct switchdev_trans *trans, int flags, rocker_cmd_prep_cb_t prepare, void *prepare_priv, rocker_cmd_proc_cb_t process, void *process_priv) { @@ -1615,7 +1605,7 @@ static int rocker_cmd_exec(struct rocker_port *rocker_port, rocker_desc_cookie_ptr_set(desc_info, wait); - if (trans != SWITCHDEV_TRANS_PREPARE) + if (!switchdev_trans_ph_prepare(trans)) rocker_desc_head_set(rocker, &rocker->cmd_ring, desc_info); spin_unlock_irqrestore(&rocker->cmd_ring_lock, lock_flags); @@ -1623,7 +1613,7 @@ static int rocker_cmd_exec(struct rocker_port *rocker_port, if (nowait) return 0; - if (trans != SWITCHDEV_TRANS_PREPARE) + if (!switchdev_trans_ph_prepare(trans)) if (!rocker_wait_event_timeout(wait, HZ / 10)) return -EIO; @@ -1875,7 +1865,7 @@ rocker_cmd_set_port_learning_prep(const struct rocker_port *rocker_port, static int rocker_cmd_get_port_settings_ethtool(struct rocker_port *rocker_port, struct ethtool_cmd *ecmd) { - return rocker_cmd_exec(rocker_port, SWITCHDEV_TRANS_NONE, 0, + return rocker_cmd_exec(rocker_port, NULL, 0, rocker_cmd_get_port_settings_prep, NULL, rocker_cmd_get_port_settings_ethtool_proc, ecmd); @@ -1884,7 +1874,7 @@ static int rocker_cmd_get_port_settings_ethtool(struct rocker_port *rocker_port, static int rocker_cmd_get_port_settings_macaddr(struct rocker_port *rocker_port, unsigned char *macaddr) { - return rocker_cmd_exec(rocker_port, SWITCHDEV_TRANS_NONE, 0, + return rocker_cmd_exec(rocker_port, NULL, 0, rocker_cmd_get_port_settings_prep, NULL, rocker_cmd_get_port_settings_macaddr_proc, macaddr); @@ -1893,7 +1883,7 @@ static int rocker_cmd_get_port_settings_macaddr(struct rocker_port *rocker_port, static int rocker_cmd_set_port_settings_ethtool(struct rocker_port *rocker_port, struct ethtool_cmd *ecmd) { - return rocker_cmd_exec(rocker_port, SWITCHDEV_TRANS_NONE, 0, + return rocker_cmd_exec(rocker_port, NULL, 0, rocker_cmd_set_port_settings_ethtool_prep, ecmd, NULL, NULL); } @@ -1901,7 +1891,7 @@ static int rocker_cmd_set_port_settings_ethtool(struct rocker_port *rocker_port, static int rocker_cmd_set_port_settings_macaddr(struct rocker_port *rocker_port, unsigned char *macaddr) { - return rocker_cmd_exec(rocker_port, SWITCHDEV_TRANS_NONE, 0, + return rocker_cmd_exec(rocker_port, NULL, 0, rocker_cmd_set_port_settings_macaddr_prep, macaddr, NULL, NULL); } @@ -1909,13 +1899,13 @@ static int rocker_cmd_set_port_settings_macaddr(struct rocker_port *rocker_port, static int rocker_cmd_set_port_settings_mtu(struct rocker_port *rocker_port, int mtu) { - return rocker_cmd_exec(rocker_port, SWITCHDEV_TRANS_NONE, 0, + return rocker_cmd_exec(rocker_port, NULL, 0, rocker_cmd_set_port_settings_mtu_prep, &mtu, NULL, NULL); } static int rocker_port_set_learning(struct rocker_port *rocker_port, - enum switchdev_trans trans) + struct switchdev_trans *trans) { return rocker_cmd_exec(rocker_port, trans, 0, rocker_cmd_set_port_learning_prep, @@ -2433,7 +2423,7 @@ rocker_flow_tbl_find(const struct rocker *rocker, } static int rocker_flow_tbl_add(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + struct switchdev_trans *trans, int flags, struct rocker_flow_tbl_entry *match) { struct rocker *rocker = rocker_port->rocker; @@ -2449,7 +2439,7 @@ static int rocker_flow_tbl_add(struct rocker_port *rocker_port, if (found) { match->cookie = found->cookie; - if (trans != SWITCHDEV_TRANS_PREPARE) + if (!switchdev_trans_ph_prepare(trans)) hash_del(&found->entry); rocker_port_kfree(trans, found); found = match; @@ -2460,7 +2450,7 @@ static int rocker_flow_tbl_add(struct rocker_port *rocker_port, found->cmd = ROCKER_TLV_CMD_TYPE_OF_DPA_FLOW_ADD; } - if (trans != SWITCHDEV_TRANS_PREPARE) + if (!switchdev_trans_ph_prepare(trans)) hash_add(rocker->flow_tbl, &found->entry, found->key_crc32); spin_unlock_irqrestore(&rocker->flow_tbl_lock, lock_flags); @@ -2470,7 +2460,7 @@ static int rocker_flow_tbl_add(struct rocker_port *rocker_port, } static int rocker_flow_tbl_del(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + struct switchdev_trans *trans, int flags, struct rocker_flow_tbl_entry *match) { struct rocker *rocker = rocker_port->rocker; @@ -2486,7 +2476,7 @@ static int rocker_flow_tbl_del(struct rocker_port *rocker_port, found = rocker_flow_tbl_find(rocker, match); if (found) { - if (trans != SWITCHDEV_TRANS_PREPARE) + if (!switchdev_trans_ph_prepare(trans)) hash_del(&found->entry); found->cmd = ROCKER_TLV_CMD_TYPE_OF_DPA_FLOW_DEL; } @@ -2506,7 +2496,7 @@ static int rocker_flow_tbl_del(struct rocker_port *rocker_port, } static int rocker_flow_tbl_do(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + struct switchdev_trans *trans, int flags, struct rocker_flow_tbl_entry *entry) { if (flags & ROCKER_OP_FLAG_REMOVE) @@ -2516,7 +2506,7 @@ static int rocker_flow_tbl_do(struct rocker_port *rocker_port, } static int rocker_flow_tbl_ig_port(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + struct switchdev_trans *trans, int flags, u32 in_pport, u32 in_pport_mask, enum rocker_of_dpa_table_id goto_tbl) { @@ -2536,7 +2526,7 @@ static int rocker_flow_tbl_ig_port(struct rocker_port *rocker_port, } static int rocker_flow_tbl_vlan(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + struct switchdev_trans *trans, int flags, u32 in_pport, __be16 vlan_id, __be16 vlan_id_mask, enum rocker_of_dpa_table_id goto_tbl, @@ -2562,7 +2552,7 @@ static int rocker_flow_tbl_vlan(struct rocker_port *rocker_port, } static int rocker_flow_tbl_term_mac(struct rocker_port *rocker_port, - enum switchdev_trans trans, + struct switchdev_trans *trans, u32 in_pport, u32 in_pport_mask, __be16 eth_type, const u8 *eth_dst, const u8 *eth_dst_mask, __be16 vlan_id, @@ -2599,7 +2589,7 @@ static int rocker_flow_tbl_term_mac(struct rocker_port *rocker_port, } static int rocker_flow_tbl_bridge(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + struct switchdev_trans *trans, int flags, const u8 *eth_dst, const u8 *eth_dst_mask, __be16 vlan_id, u32 tunnel_id, enum rocker_of_dpa_table_id goto_tbl, @@ -2653,7 +2643,7 @@ static int rocker_flow_tbl_bridge(struct rocker_port *rocker_port, } static int rocker_flow_tbl_ucast4_routing(struct rocker_port *rocker_port, - enum switchdev_trans trans, + struct switchdev_trans *trans, __be16 eth_type, __be32 dst, __be32 dst_mask, u32 priority, enum rocker_of_dpa_table_id goto_tbl, @@ -2679,7 +2669,7 @@ static int rocker_flow_tbl_ucast4_routing(struct rocker_port *rocker_port, } static int rocker_flow_tbl_acl(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + struct switchdev_trans *trans, int flags, u32 in_pport, u32 in_pport_mask, const u8 *eth_src, const u8 *eth_src_mask, const u8 *eth_dst, const u8 *eth_dst_mask, @@ -2744,7 +2734,7 @@ rocker_group_tbl_find(const struct rocker *rocker, return NULL; } -static void rocker_group_tbl_entry_free(enum switchdev_trans trans, +static void rocker_group_tbl_entry_free(struct switchdev_trans *trans, struct rocker_group_tbl_entry *entry) { switch (ROCKER_GROUP_TYPE_GET(entry->group_id)) { @@ -2759,7 +2749,7 @@ static void rocker_group_tbl_entry_free(enum switchdev_trans trans, } static int rocker_group_tbl_add(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + struct switchdev_trans *trans, int flags, struct rocker_group_tbl_entry *match) { struct rocker *rocker = rocker_port->rocker; @@ -2771,7 +2761,7 @@ static int rocker_group_tbl_add(struct rocker_port *rocker_port, found = rocker_group_tbl_find(rocker, match); if (found) { - if (trans != SWITCHDEV_TRANS_PREPARE) + if (!switchdev_trans_ph_prepare(trans)) hash_del(&found->entry); rocker_group_tbl_entry_free(trans, found); found = match; @@ -2781,7 +2771,7 @@ static int rocker_group_tbl_add(struct rocker_port *rocker_port, found->cmd = ROCKER_TLV_CMD_TYPE_OF_DPA_GROUP_ADD; } - if (trans != SWITCHDEV_TRANS_PREPARE) + if (!switchdev_trans_ph_prepare(trans)) hash_add(rocker->group_tbl, &found->entry, found->group_id); spin_unlock_irqrestore(&rocker->group_tbl_lock, lock_flags); @@ -2791,7 +2781,7 @@ static int rocker_group_tbl_add(struct rocker_port *rocker_port, } static int rocker_group_tbl_del(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + struct switchdev_trans *trans, int flags, struct rocker_group_tbl_entry *match) { struct rocker *rocker = rocker_port->rocker; @@ -2804,7 +2794,7 @@ static int rocker_group_tbl_del(struct rocker_port *rocker_port, found = rocker_group_tbl_find(rocker, match); if (found) { - if (trans != SWITCHDEV_TRANS_PREPARE) + if (!switchdev_trans_ph_prepare(trans)) hash_del(&found->entry); found->cmd = ROCKER_TLV_CMD_TYPE_OF_DPA_GROUP_DEL; } @@ -2824,7 +2814,7 @@ static int rocker_group_tbl_del(struct rocker_port *rocker_port, } static int rocker_group_tbl_do(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + struct switchdev_trans *trans, int flags, struct rocker_group_tbl_entry *entry) { if (flags & ROCKER_OP_FLAG_REMOVE) @@ -2834,7 +2824,7 @@ static int rocker_group_tbl_do(struct rocker_port *rocker_port, } static int rocker_group_l2_interface(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + struct switchdev_trans *trans, int flags, __be16 vlan_id, u32 out_pport, int pop_vlan) { @@ -2851,7 +2841,7 @@ static int rocker_group_l2_interface(struct rocker_port *rocker_port, } static int rocker_group_l2_fan_out(struct rocker_port *rocker_port, - enum switchdev_trans trans, + struct switchdev_trans *trans, int flags, u8 group_count, const u32 *group_ids, u32 group_id) { @@ -2876,7 +2866,7 @@ static int rocker_group_l2_fan_out(struct rocker_port *rocker_port, } static int rocker_group_l2_flood(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + struct switchdev_trans *trans, int flags, __be16 vlan_id, u8 group_count, const u32 *group_ids, u32 group_id) { @@ -2886,7 +2876,7 @@ static int rocker_group_l2_flood(struct rocker_port *rocker_port, } static int rocker_group_l3_unicast(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + struct switchdev_trans *trans, int flags, u32 index, const u8 *src_mac, const u8 *dst_mac, __be16 vlan_id, bool ttl_check, u32 pport) { @@ -2922,22 +2912,22 @@ rocker_neigh_tbl_find(const struct rocker *rocker, __be32 ip_addr) } static void _rocker_neigh_add(struct rocker *rocker, - enum switchdev_trans trans, + struct switchdev_trans *trans, struct rocker_neigh_tbl_entry *entry) { - if (trans != SWITCHDEV_TRANS_COMMIT) + if (!switchdev_trans_ph_commit(trans)) entry->index = rocker->neigh_tbl_next_index++; - if (trans == SWITCHDEV_TRANS_PREPARE) + if (switchdev_trans_ph_prepare(trans)) return; entry->ref_count++; hash_add(rocker->neigh_tbl, &entry->entry, be32_to_cpu(entry->ip_addr)); } -static void _rocker_neigh_del(enum switchdev_trans trans, +static void _rocker_neigh_del(struct switchdev_trans *trans, struct rocker_neigh_tbl_entry *entry) { - if (trans == SWITCHDEV_TRANS_PREPARE) + if (switchdev_trans_ph_prepare(trans)) return; if (--entry->ref_count == 0) { hash_del(&entry->entry); @@ -2946,19 +2936,19 @@ static void _rocker_neigh_del(enum switchdev_trans trans, } static void _rocker_neigh_update(struct rocker_neigh_tbl_entry *entry, - enum switchdev_trans trans, + struct switchdev_trans *trans, const u8 *eth_dst, bool ttl_check) { if (eth_dst) { ether_addr_copy(entry->eth_dst, eth_dst); entry->ttl_check = ttl_check; - } else if (trans != SWITCHDEV_TRANS_PREPARE) { + } else if (!switchdev_trans_ph_prepare(trans)) { entry->ref_count++; } } static int rocker_port_ipv4_neigh(struct rocker_port *rocker_port, - enum switchdev_trans trans, + struct switchdev_trans *trans, int flags, __be32 ip_addr, const u8 *eth_dst) { struct rocker *rocker = rocker_port->rocker; @@ -3050,7 +3040,8 @@ err_out: } static int rocker_port_ipv4_resolve(struct rocker_port *rocker_port, - enum switchdev_trans trans, __be32 ip_addr) + struct switchdev_trans *trans, + __be32 ip_addr) { struct net_device *dev = rocker_port->dev; struct neighbour *n = __ipv4_neigh_lookup(dev, (__force u32)ip_addr); @@ -3078,7 +3069,7 @@ static int rocker_port_ipv4_resolve(struct rocker_port *rocker_port, } static int rocker_port_ipv4_nh(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + struct switchdev_trans *trans, int flags, __be32 ip_addr, u32 *index) { struct rocker *rocker = rocker_port->rocker; @@ -3137,7 +3128,7 @@ static int rocker_port_ipv4_nh(struct rocker_port *rocker_port, } static int rocker_port_vlan_flood_group(struct rocker_port *rocker_port, - enum switchdev_trans trans, + struct switchdev_trans *trans, int flags, __be16 vlan_id) { struct rocker_port *p; @@ -3186,7 +3177,7 @@ no_ports_in_vlan: } static int rocker_port_vlan_l2_groups(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + struct switchdev_trans *trans, int flags, __be16 vlan_id, bool pop_vlan) { const struct rocker *rocker = rocker_port->rocker; @@ -3292,7 +3283,7 @@ static struct rocker_ctrl { }; static int rocker_port_ctrl_vlan_acl(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + struct switchdev_trans *trans, int flags, const struct rocker_ctrl *ctrl, __be16 vlan_id) { u32 in_pport = rocker_port->pport; @@ -3325,7 +3316,8 @@ static int rocker_port_ctrl_vlan_acl(struct rocker_port *rocker_port, } static int rocker_port_ctrl_vlan_bridge(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + struct switchdev_trans *trans, + int flags, const struct rocker_ctrl *ctrl, __be16 vlan_id) { @@ -3350,7 +3342,7 @@ static int rocker_port_ctrl_vlan_bridge(struct rocker_port *rocker_port, } static int rocker_port_ctrl_vlan_term(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + struct switchdev_trans *trans, int flags, const struct rocker_ctrl *ctrl, __be16 vlan_id) { u32 in_pport_mask = 0xffffffff; @@ -3374,7 +3366,7 @@ static int rocker_port_ctrl_vlan_term(struct rocker_port *rocker_port, } static int rocker_port_ctrl_vlan(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + struct switchdev_trans *trans, int flags, const struct rocker_ctrl *ctrl, __be16 vlan_id) { if (ctrl->acl) @@ -3392,7 +3384,7 @@ static int rocker_port_ctrl_vlan(struct rocker_port *rocker_port, } static int rocker_port_ctrl_vlan_add(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + struct switchdev_trans *trans, int flags, __be16 vlan_id) { int err = 0; @@ -3411,7 +3403,7 @@ static int rocker_port_ctrl_vlan_add(struct rocker_port *rocker_port, } static int rocker_port_ctrl(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + struct switchdev_trans *trans, int flags, const struct rocker_ctrl *ctrl) { u16 vid; @@ -3430,7 +3422,7 @@ static int rocker_port_ctrl(struct rocker_port *rocker_port, } static int rocker_port_vlan(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, u16 vid) + struct switchdev_trans *trans, int flags, u16 vid) { enum rocker_of_dpa_table_id goto_tbl = ROCKER_OF_DPA_TABLE_ID_TERMINATION_MAC; @@ -3487,14 +3479,14 @@ static int rocker_port_vlan(struct rocker_port *rocker_port, "Error (%d) port VLAN table\n", err); err_out: - if (trans == SWITCHDEV_TRANS_PREPARE) + if (switchdev_trans_ph_prepare(trans)) change_bit(ntohs(internal_vlan_id), rocker_port->vlan_bitmap); return err; } static int rocker_port_ig_tbl(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags) + struct switchdev_trans *trans, int flags) { enum rocker_of_dpa_table_id goto_tbl; u32 in_pport; @@ -3522,7 +3514,7 @@ static int rocker_port_ig_tbl(struct rocker_port *rocker_port, struct rocker_fdb_learn_work { struct work_struct work; struct rocker_port *rocker_port; - enum switchdev_trans trans; + struct switchdev_trans *trans; int flags; u8 addr[ETH_ALEN]; u16 vid; @@ -3550,7 +3542,7 @@ static void rocker_port_fdb_learn_work(struct work_struct *work) } static int rocker_port_fdb_learn(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + struct switchdev_trans *trans, int flags, const u8 *addr, __be16 vlan_id) { struct rocker_fdb_learn_work *lw; @@ -3592,7 +3584,7 @@ static int rocker_port_fdb_learn(struct rocker_port *rocker_port, ether_addr_copy(lw->addr, addr); lw->vid = rocker_port_vlan_to_vid(rocker_port, vlan_id); - if (trans == SWITCHDEV_TRANS_PREPARE) + if (switchdev_trans_ph_prepare(trans)) rocker_port_kfree(trans, lw); else schedule_work(&lw->work); @@ -3614,7 +3606,7 @@ rocker_fdb_tbl_find(const struct rocker *rocker, } static int rocker_port_fdb(struct rocker_port *rocker_port, - enum switchdev_trans trans, + struct switchdev_trans *trans, const unsigned char *addr, __be16 vlan_id, int flags) { @@ -3629,7 +3621,8 @@ static int rocker_port_fdb(struct rocker_port *rocker_port, return -ENOMEM; fdb->learned = (flags & ROCKER_OP_FLAG_LEARNED); - fdb->key.pport = rocker_port->pport; + fdb->touched = jiffies; + fdb->key.rocker_port = rocker_port; ether_addr_copy(fdb->key.addr, addr); fdb->key.vlan_id = vlan_id; fdb->key_crc32 = crc32(~0, &fdb->key, sizeof(fdb->key)); @@ -3638,13 +3631,17 @@ static int rocker_port_fdb(struct rocker_port *rocker_port, found = rocker_fdb_tbl_find(rocker, fdb); - if (removing && found) { - rocker_port_kfree(trans, fdb); - if (trans != SWITCHDEV_TRANS_PREPARE) - hash_del(&found->entry); - } else if (!removing && !found) { - if (trans != SWITCHDEV_TRANS_PREPARE) - hash_add(rocker->fdb_tbl, &fdb->entry, fdb->key_crc32); + if (found) { + found->touched = jiffies; + if (removing) { + rocker_port_kfree(trans, fdb); + if (!switchdev_trans_ph_prepare(trans)) + hash_del(&found->entry); + } + } else if (!removing) { + if (!switchdev_trans_ph_prepare(trans)) + hash_add(rocker->fdb_tbl, &fdb->entry, + fdb->key_crc32); } spin_unlock_irqrestore(&rocker->fdb_tbl_lock, lock_flags); @@ -3662,7 +3659,7 @@ static int rocker_port_fdb(struct rocker_port *rocker_port, } static int rocker_port_fdb_flush(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags) + struct switchdev_trans *trans, int flags) { struct rocker *rocker = rocker_port->rocker; struct rocker_fdb_tbl_entry *found; @@ -3680,7 +3677,7 @@ static int rocker_port_fdb_flush(struct rocker_port *rocker_port, spin_lock_irqsave(&rocker->fdb_tbl_lock, lock_flags); hash_for_each_safe(rocker->fdb_tbl, bkt, tmp, found, entry) { - if (found->key.pport != rocker_port->pport) + if (found->key.rocker_port != rocker_port) continue; if (!found->learned) continue; @@ -3689,7 +3686,7 @@ static int rocker_port_fdb_flush(struct rocker_port *rocker_port, found->key.vlan_id); if (err) goto err_out; - if (trans != SWITCHDEV_TRANS_PREPARE) + if (!switchdev_trans_ph_prepare(trans)) hash_del(&found->entry); } @@ -3699,8 +3696,43 @@ err_out: return err; } +static void rocker_fdb_cleanup(unsigned long data) +{ + struct rocker *rocker = (struct rocker *)data; + struct rocker_port *rocker_port; + struct rocker_fdb_tbl_entry *entry; + struct hlist_node *tmp; + unsigned long next_timer = jiffies + BR_MIN_AGEING_TIME; + unsigned long expires; + unsigned long lock_flags; + int flags = ROCKER_OP_FLAG_NOWAIT | ROCKER_OP_FLAG_REMOVE | + ROCKER_OP_FLAG_LEARNED; + int bkt; + + spin_lock_irqsave(&rocker->fdb_tbl_lock, lock_flags); + + hash_for_each_safe(rocker->fdb_tbl, bkt, tmp, entry, entry) { + if (!entry->learned) + continue; + rocker_port = entry->key.rocker_port; + expires = entry->touched + rocker_port->ageing_time; + if (time_before_eq(expires, jiffies)) { + rocker_port_fdb_learn(rocker_port, NULL, + flags, entry->key.addr, + entry->key.vlan_id); + hash_del(&entry->entry); + } else if (time_before(expires, next_timer)) { + next_timer = expires; + } + } + + spin_unlock_irqrestore(&rocker->fdb_tbl_lock, lock_flags); + + mod_timer(&rocker->fdb_cleanup_timer, round_jiffies_up(next_timer)); +} + static int rocker_port_router_mac(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + struct switchdev_trans *trans, int flags, __be16 vlan_id) { u32 in_pport_mask = 0xffffffff; @@ -3733,7 +3765,7 @@ static int rocker_port_router_mac(struct rocker_port *rocker_port, } static int rocker_port_fwding(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags) + struct switchdev_trans *trans, int flags) { bool pop_vlan; u32 out_pport; @@ -3772,16 +3804,16 @@ static int rocker_port_fwding(struct rocker_port *rocker_port, } static int rocker_port_stp_update(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags, + struct switchdev_trans *trans, int flags, u8 state) { bool want[ROCKER_CTRL_MAX] = { 0, }; bool prev_ctrls[ROCKER_CTRL_MAX]; - u8 prev_state; + u8 uninitialized_var(prev_state); int err; int i; - if (trans == SWITCHDEV_TRANS_PREPARE) { + if (switchdev_trans_ph_prepare(trans)) { memcpy(prev_ctrls, rocker_port->ctrls, sizeof(prev_ctrls)); prev_state = rocker_port->stp_state; } @@ -3833,7 +3865,7 @@ static int rocker_port_stp_update(struct rocker_port *rocker_port, err = rocker_port_fwding(rocker_port, trans, flags); err_out: - if (trans == SWITCHDEV_TRANS_PREPARE) { + if (switchdev_trans_ph_prepare(trans)) { memcpy(rocker_port->ctrls, prev_ctrls, sizeof(prev_ctrls)); rocker_port->stp_state = prev_state; } @@ -3842,7 +3874,7 @@ err_out: } static int rocker_port_fwd_enable(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags) + struct switchdev_trans *trans, int flags) { if (rocker_port_is_bridged(rocker_port)) /* bridge STP will enable port */ @@ -3854,7 +3886,7 @@ static int rocker_port_fwd_enable(struct rocker_port *rocker_port, } static int rocker_port_fwd_disable(struct rocker_port *rocker_port, - enum switchdev_trans trans, int flags) + struct switchdev_trans *trans, int flags) { if (rocker_port_is_bridged(rocker_port)) /* bridge STP will disable port */ @@ -3952,7 +3984,7 @@ not_found: } static int rocker_port_fib_ipv4(struct rocker_port *rocker_port, - enum switchdev_trans trans, __be32 dst, + struct switchdev_trans *trans, __be32 dst, int dst_len, const struct fib_info *fi, u32 tb_id, int flags) { @@ -4026,7 +4058,7 @@ static int rocker_port_open(struct net_device *dev) goto err_request_rx_irq; } - err = rocker_port_fwd_enable(rocker_port, SWITCHDEV_TRANS_NONE, 0); + err = rocker_port_fwd_enable(rocker_port, NULL, 0); if (err) goto err_fwd_enable; @@ -4054,7 +4086,7 @@ static int rocker_port_stop(struct net_device *dev) rocker_port_set_enable(rocker_port, false); napi_disable(&rocker_port->napi_rx); napi_disable(&rocker_port->napi_tx); - rocker_port_fwd_disable(rocker_port, SWITCHDEV_TRANS_NONE, + rocker_port_fwd_disable(rocker_port, NULL, ROCKER_OP_FLAG_NOWAIT); free_irq(rocker_msix_rx_vector(rocker_port), rocker_port); free_irq(rocker_msix_tx_vector(rocker_port), rocker_port); @@ -4240,7 +4272,7 @@ static int rocker_port_get_phys_port_name(struct net_device *dev, struct port_name name = { .buf = buf, .len = len }; int err; - err = rocker_cmd_exec(rocker_port, SWITCHDEV_TRANS_NONE, 0, + err = rocker_cmd_exec(rocker_port, NULL, 0, rocker_cmd_get_port_settings_prep, NULL, rocker_cmd_get_port_settings_phys_name_proc, &name); @@ -4265,7 +4297,7 @@ static void rocker_port_neigh_destroy(struct neighbour *n) int flags = ROCKER_OP_FLAG_REMOVE | ROCKER_OP_FLAG_NOWAIT; __be32 ip_addr = *(__be32 *)n->primary_key; - rocker_port_ipv4_neigh(rocker_port, SWITCHDEV_TRANS_NONE, + rocker_port_ipv4_neigh(rocker_port, NULL, flags, ip_addr, n->ha); } @@ -4311,18 +4343,8 @@ static int rocker_port_attr_get(struct net_device *dev, return 0; } -static void rocker_port_trans_abort(const struct rocker_port *rocker_port) -{ - struct list_head *mem, *tmp; - - list_for_each_safe(mem, tmp, &rocker_port->trans_mem) { - list_del(mem); - kfree(mem); - } -} - static int rocker_port_brport_flags_set(struct rocker_port *rocker_port, - enum switchdev_trans trans, + struct switchdev_trans *trans, unsigned long brport_flags) { unsigned long orig_flags; @@ -4333,37 +4355,27 @@ static int rocker_port_brport_flags_set(struct rocker_port *rocker_port, if ((orig_flags ^ rocker_port->brport_flags) & BR_LEARNING) err = rocker_port_set_learning(rocker_port, trans); - if (trans == SWITCHDEV_TRANS_PREPARE) + if (switchdev_trans_ph_prepare(trans)) rocker_port->brport_flags = orig_flags; return err; } static int rocker_port_attr_set(struct net_device *dev, - struct switchdev_attr *attr) + struct switchdev_attr *attr, + struct switchdev_trans *trans) { struct rocker_port *rocker_port = netdev_priv(dev); int err = 0; - switch (attr->trans) { - case SWITCHDEV_TRANS_PREPARE: - BUG_ON(!list_empty(&rocker_port->trans_mem)); - break; - case SWITCHDEV_TRANS_ABORT: - rocker_port_trans_abort(rocker_port); - return 0; - default: - break; - } - switch (attr->id) { case SWITCHDEV_ATTR_PORT_STP_STATE: - err = rocker_port_stp_update(rocker_port, attr->trans, + err = rocker_port_stp_update(rocker_port, trans, ROCKER_OP_FLAG_NOWAIT, attr->u.stp_state); break; case SWITCHDEV_ATTR_PORT_BRIDGE_FLAGS: - err = rocker_port_brport_flags_set(rocker_port, attr->trans, + err = rocker_port_brport_flags_set(rocker_port, trans, attr->u.brport_flags); break; default: @@ -4375,7 +4387,8 @@ static int rocker_port_attr_set(struct net_device *dev, } static int rocker_port_vlan_add(struct rocker_port *rocker_port, - enum switchdev_trans trans, u16 vid, u16 flags) + struct switchdev_trans *trans, + u16 vid, u16 flags) { int err; @@ -4394,7 +4407,7 @@ static int rocker_port_vlan_add(struct rocker_port *rocker_port, } static int rocker_port_vlans_add(struct rocker_port *rocker_port, - enum switchdev_trans trans, + struct switchdev_trans *trans, const struct switchdev_obj_vlan *vlan) { u16 vid; @@ -4411,7 +4424,7 @@ static int rocker_port_vlans_add(struct rocker_port *rocker_port, } static int rocker_port_fdb_add(struct rocker_port *rocker_port, - enum switchdev_trans trans, + struct switchdev_trans *trans, const struct switchdev_obj_fdb *fdb) { __be16 vlan_id = rocker_port_vid_to_vlan(rocker_port, fdb->vid, NULL); @@ -4424,36 +4437,25 @@ static int rocker_port_fdb_add(struct rocker_port *rocker_port, } static int rocker_port_obj_add(struct net_device *dev, - struct switchdev_obj *obj) + enum switchdev_obj_id id, const void *obj, + struct switchdev_trans *trans) { struct rocker_port *rocker_port = netdev_priv(dev); const struct switchdev_obj_ipv4_fib *fib4; int err = 0; - switch (obj->trans) { - case SWITCHDEV_TRANS_PREPARE: - BUG_ON(!list_empty(&rocker_port->trans_mem)); - break; - case SWITCHDEV_TRANS_ABORT: - rocker_port_trans_abort(rocker_port); - return 0; - default: - break; - } - - switch (obj->id) { + switch (id) { case SWITCHDEV_OBJ_PORT_VLAN: - err = rocker_port_vlans_add(rocker_port, obj->trans, - &obj->u.vlan); + err = rocker_port_vlans_add(rocker_port, trans, obj); break; case SWITCHDEV_OBJ_IPV4_FIB: - fib4 = &obj->u.ipv4_fib; - err = rocker_port_fib_ipv4(rocker_port, obj->trans, + fib4 = obj; + err = rocker_port_fib_ipv4(rocker_port, trans, htonl(fib4->dst), fib4->dst_len, fib4->fi, fib4->tb_id, 0); break; case SWITCHDEV_OBJ_PORT_FDB: - err = rocker_port_fdb_add(rocker_port, obj->trans, &obj->u.fdb); + err = rocker_port_fdb_add(rocker_port, trans, obj); break; default: err = -EOPNOTSUPP; @@ -4468,12 +4470,12 @@ static int rocker_port_vlan_del(struct rocker_port *rocker_port, { int err; - err = rocker_port_router_mac(rocker_port, SWITCHDEV_TRANS_NONE, + err = rocker_port_router_mac(rocker_port, NULL, ROCKER_OP_FLAG_REMOVE, htons(vid)); if (err) return err; - return rocker_port_vlan(rocker_port, SWITCHDEV_TRANS_NONE, + return rocker_port_vlan(rocker_port, NULL, ROCKER_OP_FLAG_REMOVE, vid); } @@ -4493,7 +4495,7 @@ static int rocker_port_vlans_del(struct rocker_port *rocker_port, } static int rocker_port_fdb_del(struct rocker_port *rocker_port, - enum switchdev_trans trans, + struct switchdev_trans *trans, const struct switchdev_obj_fdb *fdb) { __be16 vlan_id = rocker_port_vid_to_vlan(rocker_port, fdb->vid, NULL); @@ -4506,25 +4508,25 @@ static int rocker_port_fdb_del(struct rocker_port *rocker_port, } static int rocker_port_obj_del(struct net_device *dev, - struct switchdev_obj *obj) + enum switchdev_obj_id id, const void *obj) { struct rocker_port *rocker_port = netdev_priv(dev); const struct switchdev_obj_ipv4_fib *fib4; int err = 0; - switch (obj->id) { + switch (id) { case SWITCHDEV_OBJ_PORT_VLAN: - err = rocker_port_vlans_del(rocker_port, &obj->u.vlan); + err = rocker_port_vlans_del(rocker_port, obj); break; case SWITCHDEV_OBJ_IPV4_FIB: - fib4 = &obj->u.ipv4_fib; - err = rocker_port_fib_ipv4(rocker_port, SWITCHDEV_TRANS_NONE, + fib4 = obj; + err = rocker_port_fib_ipv4(rocker_port, NULL, htonl(fib4->dst), fib4->dst_len, fib4->fi, fib4->tb_id, ROCKER_OP_FLAG_REMOVE); break; case SWITCHDEV_OBJ_PORT_FDB: - err = rocker_port_fdb_del(rocker_port, obj->trans, &obj->u.fdb); + err = rocker_port_fdb_del(rocker_port, NULL, obj); break; default: err = -EOPNOTSUPP; @@ -4535,10 +4537,10 @@ static int rocker_port_obj_del(struct net_device *dev, } static int rocker_port_fdb_dump(const struct rocker_port *rocker_port, - struct switchdev_obj *obj) + struct switchdev_obj_fdb *fdb, + int (*cb)(void *obj)) { struct rocker *rocker = rocker_port->rocker; - struct switchdev_obj_fdb *fdb = &obj->u.fdb; struct rocker_fdb_tbl_entry *found; struct hlist_node *tmp; unsigned long lock_flags; @@ -4547,13 +4549,13 @@ static int rocker_port_fdb_dump(const struct rocker_port *rocker_port, spin_lock_irqsave(&rocker->fdb_tbl_lock, lock_flags); hash_for_each_safe(rocker->fdb_tbl, bkt, tmp, found, entry) { - if (found->key.pport != rocker_port->pport) + if (found->key.rocker_port != rocker_port) continue; fdb->addr = found->key.addr; fdb->ndm_state = NUD_REACHABLE; fdb->vid = rocker_port_vlan_to_vid(rocker_port, found->key.vlan_id); - err = obj->cb(rocker_port->dev, obj); + err = cb(fdb); if (err) break; } @@ -4563,9 +4565,9 @@ static int rocker_port_fdb_dump(const struct rocker_port *rocker_port, } static int rocker_port_vlan_dump(const struct rocker_port *rocker_port, - struct switchdev_obj *obj) + struct switchdev_obj_vlan *vlan, + int (*cb)(void *obj)) { - struct switchdev_obj_vlan *vlan = &obj->u.vlan; u16 vid; int err = 0; @@ -4576,7 +4578,7 @@ static int rocker_port_vlan_dump(const struct rocker_port *rocker_port, if (rocker_vlan_id_is_internal(htons(vid))) vlan->flags |= BRIDGE_VLAN_INFO_PVID; vlan->vid_begin = vlan->vid_end = vid; - err = obj->cb(rocker_port->dev, obj); + err = cb(vlan); if (err) break; } @@ -4585,17 +4587,18 @@ static int rocker_port_vlan_dump(const struct rocker_port *rocker_port, } static int rocker_port_obj_dump(struct net_device *dev, - struct switchdev_obj *obj) + enum switchdev_obj_id id, void *obj, + int (*cb)(void *obj)) { const struct rocker_port *rocker_port = netdev_priv(dev); int err = 0; - switch (obj->id) { + switch (id) { case SWITCHDEV_OBJ_PORT_FDB: - err = rocker_port_fdb_dump(rocker_port, obj); + err = rocker_port_fdb_dump(rocker_port, obj, cb); break; case SWITCHDEV_OBJ_PORT_VLAN: - err = rocker_port_vlan_dump(rocker_port, obj); + err = rocker_port_vlan_dump(rocker_port, obj, cb); break; default: err = -EOPNOTSUPP; @@ -4738,7 +4741,7 @@ rocker_cmd_get_port_stats_ethtool_proc(const struct rocker_port *rocker_port, static int rocker_cmd_get_port_stats_ethtool(struct rocker_port *rocker_port, void *priv) { - return rocker_cmd_exec(rocker_port, SWITCHDEV_TRANS_NONE, 0, + return rocker_cmd_exec(rocker_port, NULL, 0, rocker_cmd_get_port_stats_prep, NULL, rocker_cmd_get_port_stats_ethtool_proc, priv); @@ -4930,8 +4933,7 @@ static void rocker_remove_ports(const struct rocker *rocker) rocker_port = rocker->ports[i]; if (!rocker_port) continue; - rocker_port_ig_tbl(rocker_port, SWITCHDEV_TRANS_NONE, - ROCKER_OP_FLAG_REMOVE); + rocker_port_ig_tbl(rocker_port, NULL, ROCKER_OP_FLAG_REMOVE); unregister_netdev(rocker_port->dev); free_netdev(rocker_port->dev); } @@ -4969,7 +4971,7 @@ static int rocker_probe_port(struct rocker *rocker, unsigned int port_number) rocker_port->port_number = port_number; rocker_port->pport = port_number + 1; rocker_port->brport_flags = BR_LEARNING | BR_LEARNING_SYNC; - INIT_LIST_HEAD(&rocker_port->trans_mem); + rocker_port->ageing_time = BR_DEFAULT_AGEING_TIME; rocker_port_dev_addr_init(rocker_port); dev->netdev_ops = &rocker_port_netdev_ops; @@ -4992,9 +4994,9 @@ static int rocker_probe_port(struct rocker *rocker, unsigned int port_number) switchdev_port_fwd_mark_set(rocker_port->dev, NULL, false); - rocker_port_set_learning(rocker_port, SWITCHDEV_TRANS_NONE); + rocker_port_set_learning(rocker_port, NULL); - err = rocker_port_ig_tbl(rocker_port, SWITCHDEV_TRANS_NONE, 0); + err = rocker_port_ig_tbl(rocker_port, NULL, 0); if (err) { netdev_err(rocker_port->dev, "install ig port table failed\n"); goto err_port_ig_tbl; @@ -5003,8 +5005,7 @@ static int rocker_probe_port(struct rocker *rocker, unsigned int port_number) rocker_port->internal_vlan_id = rocker_port_internal_vlan_id_get(rocker_port, dev->ifindex); - err = rocker_port_vlan_add(rocker_port, SWITCHDEV_TRANS_NONE, - untagged_vid, 0); + err = rocker_port_vlan_add(rocker_port, NULL, untagged_vid, 0); if (err) { netdev_err(rocker_port->dev, "install untagged VLAN failed\n"); goto err_untagged_vlan; @@ -5013,8 +5014,7 @@ static int rocker_probe_port(struct rocker *rocker, unsigned int port_number) return 0; err_untagged_vlan: - rocker_port_ig_tbl(rocker_port, SWITCHDEV_TRANS_NONE, - ROCKER_OP_FLAG_REMOVE); + rocker_port_ig_tbl(rocker_port, NULL, ROCKER_OP_FLAG_REMOVE); err_port_ig_tbl: rocker->ports[port_number] = NULL; unregister_netdev(dev); @@ -5183,6 +5183,10 @@ static int rocker_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto err_init_tbls; } + setup_timer(&rocker->fdb_cleanup_timer, rocker_fdb_cleanup, + (unsigned long) rocker); + mod_timer(&rocker->fdb_cleanup_timer, jiffies); + err = rocker_probe_ports(rocker); if (err) { dev_err(&pdev->dev, "failed to probe ports\n"); @@ -5195,6 +5199,7 @@ static int rocker_probe(struct pci_dev *pdev, const struct pci_device_id *id) return 0; err_probe_ports: + del_timer_sync(&rocker->fdb_cleanup_timer); rocker_free_tbls(rocker); err_init_tbls: free_irq(rocker_msix_vector(rocker, ROCKER_MSIX_VEC_EVENT), rocker); @@ -5222,6 +5227,7 @@ static void rocker_remove(struct pci_dev *pdev) { struct rocker *rocker = pci_get_drvdata(pdev); + del_timer_sync(&rocker->fdb_cleanup_timer); rocker_free_tbls(rocker); rocker_write32(rocker, CONTROL, ROCKER_CONTROL_RESET); rocker_remove_ports(rocker); @@ -5275,8 +5281,7 @@ static int rocker_port_bridge_join(struct rocker_port *rocker_port, rocker_port->bridge_dev = bridge; switchdev_port_fwd_mark_set(rocker_port->dev, bridge, true); - return rocker_port_vlan_add(rocker_port, SWITCHDEV_TRANS_NONE, - untagged_vid, 0); + return rocker_port_vlan_add(rocker_port, NULL, untagged_vid, 0); } static int rocker_port_bridge_leave(struct rocker_port *rocker_port) @@ -5298,14 +5303,12 @@ static int rocker_port_bridge_leave(struct rocker_port *rocker_port) false); rocker_port->bridge_dev = NULL; - err = rocker_port_vlan_add(rocker_port, SWITCHDEV_TRANS_NONE, - untagged_vid, 0); + err = rocker_port_vlan_add(rocker_port, NULL, untagged_vid, 0); if (err) return err; if (rocker_port->dev->flags & IFF_UP) - err = rocker_port_fwd_enable(rocker_port, - SWITCHDEV_TRANS_NONE, 0); + err = rocker_port_fwd_enable(rocker_port, NULL, 0); return err; } @@ -5318,10 +5321,10 @@ static int rocker_port_ovs_changed(struct rocker_port *rocker_port, rocker_port->bridge_dev = master; - err = rocker_port_fwd_disable(rocker_port, SWITCHDEV_TRANS_NONE, 0); + err = rocker_port_fwd_disable(rocker_port, NULL, 0); if (err) return err; - err = rocker_port_fwd_enable(rocker_port, SWITCHDEV_TRANS_NONE, 0); + err = rocker_port_fwd_enable(rocker_port, NULL, 0); return err; } @@ -5399,8 +5402,7 @@ static int rocker_neigh_update(struct net_device *dev, struct neighbour *n) ROCKER_OP_FLAG_NOWAIT; __be32 ip_addr = *(__be32 *)n->primary_key; - return rocker_port_ipv4_neigh(rocker_port, SWITCHDEV_TRANS_NONE, - flags, ip_addr, n->ha); + return rocker_port_ipv4_neigh(rocker_port, NULL, flags, ip_addr, n->ha); } static int rocker_netevent_event(struct notifier_block *unused, diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c index 630f0b7800e4..0e2fc1a844ab 100644 --- a/drivers/net/ethernet/smsc/smc91x.c +++ b/drivers/net/ethernet/smsc/smc91x.c @@ -2018,10 +2018,18 @@ static int smc_probe(struct net_device *dev, void __iomem *ioaddr, lp->cfg.flags |= SMC91X_USE_DMA; # endif if (lp->cfg.flags & SMC91X_USE_DMA) { - int dma = pxa_request_dma(dev->name, DMA_PRIO_LOW, - smc_pxa_dma_irq, NULL); - if (dma >= 0) - dev->dma = dma; + dma_cap_mask_t mask; + struct pxad_param param; + + dma_cap_zero(mask); + dma_cap_set(DMA_SLAVE, mask); + param.prio = PXAD_PRIO_LOWEST; + param.drcmr = -1UL; + + lp->dma_chan = + dma_request_slave_channel_compat(mask, pxad_filter_fn, + ¶m, &dev->dev, + "data"); } #endif @@ -2032,8 +2040,8 @@ static int smc_probe(struct net_device *dev, void __iomem *ioaddr, version_string, revision_register & 0x0f, lp->base, dev->irq); - if (dev->dma != (unsigned char)-1) - pr_cont(" DMA %d", dev->dma); + if (lp->dma_chan) + pr_cont(" DMA %p", lp->dma_chan); pr_cont("%s%s\n", lp->cfg.flags & SMC91X_NOWAIT ? " [nowait]" : "", @@ -2058,8 +2066,8 @@ static int smc_probe(struct net_device *dev, void __iomem *ioaddr, err_out: #ifdef CONFIG_ARCH_PXA - if (retval && dev->dma != (unsigned char)-1) - pxa_free_dma(dev->dma); + if (retval && lp->dma_chan) + dma_release_channel(lp->dma_chan); #endif return retval; } @@ -2370,6 +2378,7 @@ static int smc_drv_probe(struct platform_device *pdev) struct smc_local *lp = netdev_priv(ndev); lp->device = &pdev->dev; lp->physaddr = res->start; + } #endif @@ -2406,8 +2415,8 @@ static int smc_drv_remove(struct platform_device *pdev) free_irq(ndev->irq, ndev); #ifdef CONFIG_ARCH_PXA - if (ndev->dma != (unsigned char)-1) - pxa_free_dma(ndev->dma); + if (lp->dma_chan) + dma_release_channel(lp->dma_chan); #endif iounmap(lp->base); diff --git a/drivers/net/ethernet/smsc/smc91x.h b/drivers/net/ethernet/smsc/smc91x.h index 3a18501d1068..a3c129e1e40a 100644 --- a/drivers/net/ethernet/smsc/smc91x.h +++ b/drivers/net/ethernet/smsc/smc91x.h @@ -33,6 +33,7 @@ #ifndef _SMC91X_H_ #define _SMC91X_H_ +#include <linux/dmaengine.h> #include <linux/smc91x.h> /* @@ -244,6 +245,7 @@ struct smc_local { u_long physaddr; struct device *device; #endif + struct dma_chan *dma_chan; void __iomem *base; void __iomem *datacs; @@ -265,21 +267,47 @@ struct smc_local { * as RX which can overrun memory and lose packets. */ #include <linux/dma-mapping.h> -#include <mach/dma.h> +#include <linux/dma/pxa-dma.h> #ifdef SMC_insl #undef SMC_insl #define SMC_insl(a, r, p, l) \ smc_pxa_dma_insl(a, lp, r, dev->dma, p, l) static inline void +smc_pxa_dma_inpump(struct smc_local *lp, u_char *buf, int len) +{ + dma_addr_t dmabuf; + struct dma_async_tx_descriptor *tx; + dma_cookie_t cookie; + enum dma_status status; + struct dma_tx_state state; + + dmabuf = dma_map_single(lp->device, buf, len, DMA_FROM_DEVICE); + tx = dmaengine_prep_slave_single(lp->dma_chan, dmabuf, len, + DMA_DEV_TO_MEM, 0); + if (tx) { + cookie = dmaengine_submit(tx); + dma_async_issue_pending(lp->dma_chan); + do { + status = dmaengine_tx_status(lp->dma_chan, cookie, + &state); + cpu_relax(); + } while (status != DMA_COMPLETE && status != DMA_ERROR && + state.residue); + dmaengine_terminate_all(lp->dma_chan); + } + dma_unmap_single(lp->device, dmabuf, len, DMA_FROM_DEVICE); +} + +static inline void smc_pxa_dma_insl(void __iomem *ioaddr, struct smc_local *lp, int reg, int dma, u_char *buf, int len) { - u_long physaddr = lp->physaddr; - dma_addr_t dmabuf; + struct dma_slave_config config; + int ret; /* fallback if no DMA available */ - if (dma == (unsigned char)-1) { + if (!lp->dma_chan) { readsl(ioaddr + reg, buf, len); return; } @@ -291,18 +319,22 @@ smc_pxa_dma_insl(void __iomem *ioaddr, struct smc_local *lp, int reg, int dma, len--; } + memset(&config, 0, sizeof(config)); + config.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES; + config.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES; + config.src_addr = lp->physaddr + reg; + config.dst_addr = lp->physaddr + reg; + config.src_maxburst = 32; + config.dst_maxburst = 32; + ret = dmaengine_slave_config(lp->dma_chan, &config); + if (ret) { + dev_err(lp->device, "dma channel configuration failed: %d\n", + ret); + return; + } + len *= 4; - dmabuf = dma_map_single(lp->device, buf, len, DMA_FROM_DEVICE); - DCSR(dma) = DCSR_NODESC; - DTADR(dma) = dmabuf; - DSADR(dma) = physaddr + reg; - DCMD(dma) = (DCMD_INCTRGADDR | DCMD_BURST32 | - DCMD_WIDTH4 | (DCMD_LENGTH & len)); - DCSR(dma) = DCSR_NODESC | DCSR_RUN; - while (!(DCSR(dma) & DCSR_STOPSTATE)) - cpu_relax(); - DCSR(dma) = 0; - dma_unmap_single(lp->device, dmabuf, len, DMA_FROM_DEVICE); + smc_pxa_dma_inpump(lp, buf, len); } #endif @@ -314,11 +346,11 @@ static inline void smc_pxa_dma_insw(void __iomem *ioaddr, struct smc_local *lp, int reg, int dma, u_char *buf, int len) { - u_long physaddr = lp->physaddr; - dma_addr_t dmabuf; + struct dma_slave_config config; + int ret; /* fallback if no DMA available */ - if (dma == (unsigned char)-1) { + if (!lp->dma_chan) { readsw(ioaddr + reg, buf, len); return; } @@ -330,26 +362,25 @@ smc_pxa_dma_insw(void __iomem *ioaddr, struct smc_local *lp, int reg, int dma, len--; } + memset(&config, 0, sizeof(config)); + config.src_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES; + config.dst_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES; + config.src_addr = lp->physaddr + reg; + config.dst_addr = lp->physaddr + reg; + config.src_maxburst = 32; + config.dst_maxburst = 32; + ret = dmaengine_slave_config(lp->dma_chan, &config); + if (ret) { + dev_err(lp->device, "dma channel configuration failed: %d\n", + ret); + return; + } + len *= 2; - dmabuf = dma_map_single(lp->device, buf, len, DMA_FROM_DEVICE); - DCSR(dma) = DCSR_NODESC; - DTADR(dma) = dmabuf; - DSADR(dma) = physaddr + reg; - DCMD(dma) = (DCMD_INCTRGADDR | DCMD_BURST32 | - DCMD_WIDTH2 | (DCMD_LENGTH & len)); - DCSR(dma) = DCSR_NODESC | DCSR_RUN; - while (!(DCSR(dma) & DCSR_STOPSTATE)) - cpu_relax(); - DCSR(dma) = 0; - dma_unmap_single(lp->device, dmabuf, len, DMA_FROM_DEVICE); + smc_pxa_dma_inpump(lp, buf, len); } #endif -static void -smc_pxa_dma_irq(int dma, void *dummy) -{ - DCSR(dma) = 0; -} #endif /* CONFIG_ARCH_PXA */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 925f2f8659b8..934143e1193b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1945,7 +1945,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) { struct stmmac_priv *priv = netdev_priv(dev); unsigned int txsize = priv->dma_tx_size; - unsigned int entry; + int entry; int i, csum_insertion = 0, is_jumbo = 0; int nfrags = skb_shinfo(skb)->nr_frags; struct dma_desc *desc, *first; diff --git a/drivers/net/ethernet/ti/cpsw-common.c b/drivers/net/ethernet/ti/cpsw-common.c index f59509486113..c08be62bceba 100644 --- a/drivers/net/ethernet/ti/cpsw-common.c +++ b/drivers/net/ethernet/ti/cpsw-common.c @@ -19,11 +19,38 @@ #include "cpsw.h" -#define AM33XX_CTRL_MAC_LO_REG(offset, id) ((offset) + 0x8 * (id)) -#define AM33XX_CTRL_MAC_HI_REG(offset, id) ((offset) + 0x8 * (id) + 0x4) +#define CTRL_MAC_LO_REG(offset, id) ((offset) + 0x8 * (id)) +#define CTRL_MAC_HI_REG(offset, id) ((offset) + 0x8 * (id) + 0x4) -int cpsw_am33xx_cm_get_macid(struct device *dev, u16 offset, int slave, - u8 *mac_addr) +static int davinci_emac_3517_get_macid(struct device *dev, u16 offset, + int slave, u8 *mac_addr) +{ + u32 macid_lsb; + u32 macid_msb; + struct regmap *syscon; + + syscon = syscon_regmap_lookup_by_phandle(dev->of_node, "syscon"); + if (IS_ERR(syscon)) { + if (PTR_ERR(syscon) == -ENODEV) + return 0; + return PTR_ERR(syscon); + } + + regmap_read(syscon, CTRL_MAC_LO_REG(offset, slave), &macid_lsb); + regmap_read(syscon, CTRL_MAC_HI_REG(offset, slave), &macid_msb); + + mac_addr[0] = (macid_msb >> 16) & 0xff; + mac_addr[1] = (macid_msb >> 8) & 0xff; + mac_addr[2] = macid_msb & 0xff; + mac_addr[3] = (macid_lsb >> 16) & 0xff; + mac_addr[4] = (macid_lsb >> 8) & 0xff; + mac_addr[5] = macid_lsb & 0xff; + + return 0; +} + +static int cpsw_am33xx_cm_get_macid(struct device *dev, u16 offset, int slave, + u8 *mac_addr) { u32 macid_lo; u32 macid_hi; @@ -36,10 +63,8 @@ int cpsw_am33xx_cm_get_macid(struct device *dev, u16 offset, int slave, return PTR_ERR(syscon); } - regmap_read(syscon, AM33XX_CTRL_MAC_LO_REG(offset, slave), - &macid_lo); - regmap_read(syscon, AM33XX_CTRL_MAC_HI_REG(offset, slave), - &macid_hi); + regmap_read(syscon, CTRL_MAC_LO_REG(offset, slave), &macid_lo); + regmap_read(syscon, CTRL_MAC_HI_REG(offset, slave), &macid_hi); mac_addr[5] = (macid_lo >> 8) & 0xff; mac_addr[4] = macid_lo & 0xff; @@ -50,6 +75,27 @@ int cpsw_am33xx_cm_get_macid(struct device *dev, u16 offset, int slave, return 0; } -EXPORT_SYMBOL_GPL(cpsw_am33xx_cm_get_macid); + +int ti_cm_get_macid(struct device *dev, int slave, u8 *mac_addr) +{ + if (of_machine_is_compatible("ti,am33xx")) + return cpsw_am33xx_cm_get_macid(dev, 0x630, slave, mac_addr); + + if (of_device_is_compatible(dev->of_node, "ti,am3517-emac")) + return davinci_emac_3517_get_macid(dev, 0x110, slave, mac_addr); + + if (of_device_is_compatible(dev->of_node, "ti,dm816-emac")) + return cpsw_am33xx_cm_get_macid(dev, 0x30, slave, mac_addr); + + if (of_machine_is_compatible("ti,am4372")) + return cpsw_am33xx_cm_get_macid(dev, 0x630, slave, mac_addr); + + if (of_machine_is_compatible("ti,dra7")) + return davinci_emac_3517_get_macid(dev, 0x514, slave, mac_addr); + + dev_err(dev, "incompatible machine/device type for reading mac address\n"); + return -ENOENT; +} +EXPORT_SYMBOL_GPL(ti_cm_get_macid); MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 8fc90f1c872c..75584cc36339 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -29,6 +29,7 @@ #include <linux/workqueue.h> #include <linux/delay.h> #include <linux/pm_runtime.h> +#include <linux/gpio.h> #include <linux/of.h> #include <linux/of_net.h> #include <linux/of_device.h> @@ -2057,13 +2058,10 @@ no_phy_slave: if (mac_addr) { memcpy(slave_data->mac_addr, mac_addr, ETH_ALEN); } else { - if (of_machine_is_compatible("ti,am33xx")) { - ret = cpsw_am33xx_cm_get_macid(&pdev->dev, - 0x630, i, - slave_data->mac_addr); - if (ret) - return ret; - } + ret = ti_cm_get_macid(&pdev->dev, i, + slave_data->mac_addr); + if (ret) + return ret; } if (data->dual_emac) { if (of_property_read_u32(slave_node, "dual_emac_res_vlan", @@ -2207,6 +2205,7 @@ static int cpsw_probe(struct platform_device *pdev) void __iomem *ss_regs; struct resource *res, *ss_res; const struct of_device_id *of_id; + struct gpio_descs *mode; u32 slave_offset, sliver_offset, slave_size; int ret = 0, i; int irq; @@ -2232,6 +2231,13 @@ static int cpsw_probe(struct platform_device *pdev) goto clean_ndev_ret; } + mode = devm_gpiod_get_array_optional(&pdev->dev, "mode", GPIOD_OUT_LOW); + if (IS_ERR(mode)) { + ret = PTR_ERR(mode); + dev_err(&pdev->dev, "gpio request failed, ret %d\n", ret); + goto clean_ndev_ret; + } + /* * This may be required here for child devices. */ diff --git a/drivers/net/ethernet/ti/cpsw.h b/drivers/net/ethernet/ti/cpsw.h index ca90efafd156..442a7038e660 100644 --- a/drivers/net/ethernet/ti/cpsw.h +++ b/drivers/net/ethernet/ti/cpsw.h @@ -41,7 +41,6 @@ struct cpsw_platform_data { }; void cpsw_phy_sel(struct device *dev, phy_interface_t phy_mode, int slave); -int cpsw_am33xx_cm_get_macid(struct device *dev, u16 offset, int slave, - u8 *mac_addr); +int ti_cm_get_macid(struct device *dev, int slave, u8 *mac_addr); #endif /* __CPSW_H__ */ diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c index a21c77bc1b27..33bd3b902304 100644 --- a/drivers/net/ethernet/ti/davinci_emac.c +++ b/drivers/net/ethernet/ti/davinci_emac.c @@ -1861,8 +1861,12 @@ davinci_emac_of_get_pdata(struct platform_device *pdev, struct emac_priv *priv) pdata->no_bd_ram = of_property_read_bool(np, "ti,davinci-no-bd-ram"); priv->phy_node = of_parse_phandle(np, "phy-handle", 0); - if (!priv->phy_node) - pdata->phy_id = NULL; + if (!priv->phy_node) { + if (!of_phy_is_fixed_link(np)) + pdata->phy_id = NULL; + else if (of_phy_register_fixed_link(np) >= 0) + priv->phy_node = of_node_get(np); + } auxdata = pdev->dev.platform_data; if (auxdata) { @@ -1882,51 +1886,13 @@ davinci_emac_of_get_pdata(struct platform_device *pdev, struct emac_priv *priv) return pdata; } -static int davinci_emac_3517_get_macid(struct device *dev, u16 offset, - int slave, u8 *mac_addr) -{ - u32 macid_lsb; - u32 macid_msb; - struct regmap *syscon; - - syscon = syscon_regmap_lookup_by_phandle(dev->of_node, "syscon"); - if (IS_ERR(syscon)) { - if (PTR_ERR(syscon) == -ENODEV) - return 0; - return PTR_ERR(syscon); - } - - regmap_read(syscon, offset, &macid_lsb); - regmap_read(syscon, offset + 4, &macid_msb); - - mac_addr[0] = (macid_msb >> 16) & 0xff; - mac_addr[1] = (macid_msb >> 8) & 0xff; - mac_addr[2] = macid_msb & 0xff; - mac_addr[3] = (macid_lsb >> 16) & 0xff; - mac_addr[4] = (macid_lsb >> 8) & 0xff; - mac_addr[5] = macid_lsb & 0xff; - - return 0; -} - static int davinci_emac_try_get_mac(struct platform_device *pdev, int instance, u8 *mac_addr) { - int error = -EINVAL; - if (!pdev->dev.of_node) - return error; - - if (of_device_is_compatible(pdev->dev.of_node, "ti,am3517-emac")) - error = davinci_emac_3517_get_macid(&pdev->dev, 0x110, - 0, mac_addr); - else if (of_device_is_compatible(pdev->dev.of_node, - "ti,dm816-emac")) - error = cpsw_am33xx_cm_get_macid(&pdev->dev, 0x30, - instance, - mac_addr); - - return error; + return -EINVAL; + + return ti_cm_get_macid(&pdev->dev, instance, mac_addr); } /** diff --git a/drivers/net/ethernet/xilinx/ll_temac_mdio.c b/drivers/net/ethernet/xilinx/ll_temac_mdio.c index 8cf9d4f56bb2..415de1eaf641 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_mdio.c +++ b/drivers/net/ethernet/xilinx/ll_temac_mdio.c @@ -59,16 +59,15 @@ static int temac_mdio_write(struct mii_bus *bus, int phy_id, int reg, u16 val) int temac_mdio_setup(struct temac_local *lp, struct device_node *np) { struct mii_bus *bus; - const u32 *bus_hz; + u32 bus_hz; int clk_div; - int rc, size; + int rc; struct resource res; /* Calculate a reasonable divisor for the clock rate */ clk_div = 0x3f; /* worst-case default setting */ - bus_hz = of_get_property(np, "clock-frequency", &size); - if (bus_hz && size >= sizeof(*bus_hz)) { - clk_div = (*bus_hz) / (2500 * 1000 * 2) - 1; + if (of_property_read_u32(np, "clock-frequency", &bus_hz) == 0) { + clk_div = bus_hz / (2500 * 1000 * 2) - 1; if (clk_div < 1) clk_div = 1; if (clk_div > 0x3f) diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c b/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c index 2a5a16834c01..507bbb0355c2 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_mdio.c @@ -129,7 +129,6 @@ int axienet_mdio_setup(struct axienet_local *lp, struct device_node *np) { int ret; u32 clk_div, host_clock; - u32 *property_p; struct mii_bus *bus; struct resource res; struct device_node *np1; @@ -168,8 +167,7 @@ int axienet_mdio_setup(struct axienet_local *lp, struct device_node *np) clk_div = DEFAULT_CLOCK_DIVISOR; goto issue; } - property_p = (u32 *) of_get_property(np1, "clock-frequency", NULL); - if (!property_p) { + if (of_property_read_u32(np1, "clock-frequency", &host_clock)) { netdev_warn(lp->ndev, "clock-frequency property not found.\n"); netdev_warn(lp->ndev, "Setting MDIO clock divisor to default %d\n", @@ -179,7 +177,6 @@ int axienet_mdio_setup(struct axienet_local *lp, struct device_node *np) goto issue; } - host_clock = be32_to_cpup(property_p); clk_div = (host_clock / (MAX_MDIO_FREQ * 2)) - 1; /* If there is any remainder from the division of * fHOST / (MAX_MDIO_FREQ * 2), then we need to add diff --git a/drivers/net/ieee802154/Kconfig b/drivers/net/ieee802154/Kconfig index 1dd5ab8e5054..5a614b2d0767 100644 --- a/drivers/net/ieee802154/Kconfig +++ b/drivers/net/ieee802154/Kconfig @@ -32,6 +32,13 @@ config IEEE802154_AT86RF230 This driver can also be built as a module. To do so, say M here. the module will be called 'at86rf230'. +config IEEE802154_AT86RF230_DEBUGFS + depends on IEEE802154_AT86RF230 + bool "AT86RF230 debugfs interface" + depends on DEBUG_FS + ---help--- + This option compiles debugfs code for the at86rf230 driver. + config IEEE802154_MRF24J40 tristate "Microchip MRF24J40 transceiver driver" depends on IEEE802154_DRIVERS && MAC802154 diff --git a/drivers/net/ieee802154/at86rf230.c b/drivers/net/ieee802154/at86rf230.c index 6422caac8d40..9756e6451038 100644 --- a/drivers/net/ieee802154/at86rf230.c +++ b/drivers/net/ieee802154/at86rf230.c @@ -31,6 +31,7 @@ #include <linux/skbuff.h> #include <linux/of_gpio.h> #include <linux/ieee802154.h> +#include <linux/debugfs.h> #include <net/mac802154.h> #include <net/cfg802154.h> @@ -83,6 +84,15 @@ struct at86rf230_state_change { bool irq_enable; }; +struct at86rf230_trac { + u64 success; + u64 success_data_pending; + u64 success_wait_for_ack; + u64 channel_access_failure; + u64 no_ack; + u64 invalid; +}; + struct at86rf230_local { struct spi_device *spi; @@ -103,6 +113,8 @@ struct at86rf230_local { u8 tx_retry; struct sk_buff *tx_skb; struct at86rf230_state_change tx; + + struct at86rf230_trac trac; }; #define AT86RF2XX_NUMREGS 0x3F @@ -377,14 +389,6 @@ at86rf230_async_read_reg(struct at86rf230_local *lp, const u8 reg, } } -static inline u8 at86rf230_state_to_force(u8 state) -{ - if (state == STATE_TX_ON) - return STATE_FORCE_TX_ON; - else - return STATE_FORCE_TRX_OFF; -} - static void at86rf230_async_state_assert(void *context) { @@ -426,7 +430,7 @@ at86rf230_async_state_assert(void *context) u8 state = ctx->to_state; if (lp->tx_retry >= AT86RF2XX_MAX_TX_RETRIES) - state = at86rf230_state_to_force(state); + state = STATE_FORCE_TRX_OFF; lp->tx_retry++; at86rf230_async_state_change(lp, ctx, state, @@ -667,28 +671,34 @@ at86rf230_tx_trac_check(void *context) { struct at86rf230_state_change *ctx = context; struct at86rf230_local *lp = ctx->lp; - const u8 *buf = ctx->buf; - const u8 trac = (buf[1] & 0xe0) >> 5; - /* If trac status is different than zero we need to do a state change - * to STATE_FORCE_TRX_OFF then STATE_RX_AACK_ON to recover the - * transceiver. - */ - if (trac) - at86rf230_async_state_change(lp, ctx, STATE_FORCE_TRX_OFF, - at86rf230_tx_on, true); - else - at86rf230_tx_on(context); -} + if (IS_ENABLED(CONFIG_IEEE802154_AT86RF230_DEBUGFS)) { + u8 trac = TRAC_MASK(ctx->buf[1]); -static void -at86rf230_tx_trac_status(void *context) -{ - struct at86rf230_state_change *ctx = context; - struct at86rf230_local *lp = ctx->lp; + switch (trac) { + case TRAC_SUCCESS: + lp->trac.success++; + break; + case TRAC_SUCCESS_DATA_PENDING: + lp->trac.success_data_pending++; + break; + case TRAC_CHANNEL_ACCESS_FAILURE: + lp->trac.channel_access_failure++; + break; + case TRAC_NO_ACK: + lp->trac.no_ack++; + break; + case TRAC_INVALID: + lp->trac.invalid++; + break; + default: + WARN_ONCE(1, "received tx trac status %d\n", trac); + break; + } + } - at86rf230_async_read_reg(lp, RG_TRX_STATE, ctx, - at86rf230_tx_trac_check, true); + at86rf230_async_state_change(lp, &lp->irq, STATE_TX_ON, + at86rf230_tx_on, true); } static void @@ -723,13 +733,32 @@ at86rf230_rx_read_frame_complete(void *context) } static void -at86rf230_rx_read_frame(void *context) +at86rf230_rx_trac_check(void *context) { struct at86rf230_state_change *ctx = context; struct at86rf230_local *lp = ctx->lp; u8 *buf = ctx->buf; int rc; + if (IS_ENABLED(CONFIG_IEEE802154_AT86RF230_DEBUGFS)) { + u8 trac = TRAC_MASK(buf[1]); + + switch (trac) { + case TRAC_SUCCESS: + lp->trac.success++; + break; + case TRAC_SUCCESS_WAIT_FOR_ACK: + lp->trac.success_wait_for_ack++; + break; + case TRAC_INVALID: + lp->trac.invalid++; + break; + default: + WARN_ONCE(1, "received rx trac status %d\n", trac); + break; + } + } + buf[0] = CMD_FB; ctx->trx.len = AT86RF2XX_MAX_BUF; ctx->msg.complete = at86rf230_rx_read_frame_complete; @@ -742,26 +771,12 @@ at86rf230_rx_read_frame(void *context) } static void -at86rf230_rx_trac_check(void *context) -{ - /* Possible check on trac status here. This could be useful to make - * some stats why receive is failed. Not used at the moment, but it's - * maybe timing relevant. Datasheet doesn't say anything about this. - * The programming guide say do it so. - */ - - at86rf230_rx_read_frame(context); -} - -static void at86rf230_irq_trx_end(struct at86rf230_local *lp) { if (lp->is_tx) { lp->is_tx = 0; - at86rf230_async_state_change(lp, &lp->irq, - STATE_FORCE_TX_ON, - at86rf230_tx_trac_status, - true); + at86rf230_async_read_reg(lp, RG_TRX_STATE, &lp->irq, + at86rf230_tx_trac_check, true); } else { at86rf230_async_read_reg(lp, RG_TRX_STATE, &lp->irq, at86rf230_rx_trac_check, true); @@ -920,6 +935,10 @@ at86rf230_start(struct ieee802154_hw *hw) { struct at86rf230_local *lp = hw->priv; + /* reset trac stats on start */ + if (IS_ENABLED(CONFIG_IEEE802154_AT86RF230_DEBUGFS)) + memset(&lp->trac, 0, sizeof(struct at86rf230_trac)); + at86rf230_awake(lp); enable_irq(lp->spi->irq); @@ -1357,7 +1376,7 @@ static int at86rf230_hw_init(struct at86rf230_local *lp, u8 xtal_trim) if (irq_type == IRQ_TYPE_EDGE_RISING || irq_type == IRQ_TYPE_EDGE_FALLING) dev_warn(&lp->spi->dev, - "Using edge triggered irq's are not recommended!\n"); + "Using edge triggered irq's are not recommended, because it can cause races and result in a non-functional driver!\n"); if (irq_type == IRQ_TYPE_EDGE_FALLING || irq_type == IRQ_TYPE_LEVEL_LOW) irq_pol = IRQ_ACTIVE_LOW; @@ -1620,6 +1639,66 @@ at86rf230_setup_spi_messages(struct at86rf230_local *lp) lp->tx.timer.function = at86rf230_async_state_timer; } +#ifdef CONFIG_IEEE802154_AT86RF230_DEBUGFS +static struct dentry *at86rf230_debugfs_root; + +static int at86rf230_stats_show(struct seq_file *file, void *offset) +{ + struct at86rf230_local *lp = file->private; + + seq_printf(file, "SUCCESS:\t\t%8llu\n", lp->trac.success); + seq_printf(file, "SUCCESS_DATA_PENDING:\t%8llu\n", + lp->trac.success_data_pending); + seq_printf(file, "SUCCESS_WAIT_FOR_ACK:\t%8llu\n", + lp->trac.success_wait_for_ack); + seq_printf(file, "CHANNEL_ACCESS_FAILURE:\t%8llu\n", + lp->trac.channel_access_failure); + seq_printf(file, "NO_ACK:\t\t\t%8llu\n", lp->trac.no_ack); + seq_printf(file, "INVALID:\t\t%8llu\n", lp->trac.invalid); + return 0; +} + +static int at86rf230_stats_open(struct inode *inode, struct file *file) +{ + return single_open(file, at86rf230_stats_show, inode->i_private); +} + +static const struct file_operations at86rf230_stats_fops = { + .open = at86rf230_stats_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int at86rf230_debugfs_init(struct at86rf230_local *lp) +{ + char debugfs_dir_name[DNAME_INLINE_LEN + 1] = "at86rf230-"; + struct dentry *stats; + + strncat(debugfs_dir_name, dev_name(&lp->spi->dev), DNAME_INLINE_LEN); + + at86rf230_debugfs_root = debugfs_create_dir(debugfs_dir_name, NULL); + if (!at86rf230_debugfs_root) + return -ENOMEM; + + stats = debugfs_create_file("trac_stats", S_IRUGO, + at86rf230_debugfs_root, lp, + &at86rf230_stats_fops); + if (!stats) + return -ENOMEM; + + return 0; +} + +static void at86rf230_debugfs_remove(void) +{ + debugfs_remove_recursive(at86rf230_debugfs_root); +} +#else +static int at86rf230_debugfs_init(struct at86rf230_local *lp) { return 0; } +static void at86rf230_debugfs_remove(void) { } +#endif + static int at86rf230_probe(struct spi_device *spi) { struct ieee802154_hw *hw; @@ -1715,12 +1794,18 @@ static int at86rf230_probe(struct spi_device *spi) /* going into sleep by default */ at86rf230_sleep(lp); - rc = ieee802154_register_hw(lp->hw); + rc = at86rf230_debugfs_init(lp); if (rc) goto free_dev; + rc = ieee802154_register_hw(lp->hw); + if (rc) + goto free_debugfs; + return rc; +free_debugfs: + at86rf230_debugfs_remove(); free_dev: ieee802154_free_hw(lp->hw); @@ -1735,6 +1820,7 @@ static int at86rf230_remove(struct spi_device *spi) at86rf230_write_subreg(lp, SR_IRQ_MASK, 0); ieee802154_unregister_hw(lp->hw); ieee802154_free_hw(lp->hw); + at86rf230_debugfs_remove(); dev_dbg(&spi->dev, "unregistered at86rf230\n"); return 0; diff --git a/drivers/net/ieee802154/at86rf230.h b/drivers/net/ieee802154/at86rf230.h index 1e6d1cc677f6..fd9c1f467f63 100644 --- a/drivers/net/ieee802154/at86rf230.h +++ b/drivers/net/ieee802154/at86rf230.h @@ -216,5 +216,13 @@ #define STATE_TRANSITION_IN_PROGRESS 0x1F #define TRX_STATE_MASK (0x1F) +#define TRAC_MASK(x) ((x & 0xe0) >> 5) + +#define TRAC_SUCCESS 0 +#define TRAC_SUCCESS_DATA_PENDING 1 +#define TRAC_SUCCESS_WAIT_FOR_ACK 2 +#define TRAC_CHANNEL_ACCESS_FAILURE 3 +#define TRAC_NO_ACK 5 +#define TRAC_INVALID 7 #endif /* !_AT86RF230_H */ diff --git a/drivers/net/ieee802154/atusb.c b/drivers/net/ieee802154/atusb.c index 80dfc725b8dc..199a94a9c8bc 100644 --- a/drivers/net/ieee802154/atusb.c +++ b/drivers/net/ieee802154/atusb.c @@ -559,6 +559,7 @@ static int atusb_get_and_show_chip(struct atusb *atusb) { struct usb_device *usb_dev = atusb->usb_dev; uint8_t man_id_0, man_id_1, part_num, version_num; + const char *chip; man_id_0 = atusb_read_reg(atusb, RG_MAN_ID_0); man_id_1 = atusb_read_reg(atusb, RG_MAN_ID_1); @@ -574,14 +575,22 @@ static int atusb_get_and_show_chip(struct atusb *atusb) man_id_1, man_id_0); goto fail; } - if (part_num != 3 && part_num != 2) { + + switch (part_num) { + case 2: + chip = "AT86RF230"; + break; + case 3: + chip = "AT86RF231"; + break; + default: dev_err(&usb_dev->dev, "unexpected transceiver, part 0x%02x version 0x%02x\n", part_num, version_num); goto fail; } - dev_info(&usb_dev->dev, "ATUSB: AT86RF231 version %d\n", version_num); + dev_info(&usb_dev->dev, "ATUSB: %s version %d\n", chip, version_num); return 0; diff --git a/drivers/net/irda/pxaficp_ir.c b/drivers/net/irda/pxaficp_ir.c index 100454662e4b..6e8f616be48e 100644 --- a/drivers/net/irda/pxaficp_ir.c +++ b/drivers/net/irda/pxaficp_ir.c @@ -19,6 +19,9 @@ #include <linux/etherdevice.h> #include <linux/platform_device.h> #include <linux/clk.h> +#include <linux/dmaengine.h> +#include <linux/dma-mapping.h> +#include <linux/dma/pxa-dma.h> #include <linux/gpio.h> #include <linux/slab.h> @@ -27,18 +30,17 @@ #include <net/irda/wrapper.h> #include <net/irda/irda_device.h> -#include <mach/dma.h> #include <linux/platform_data/irda-pxaficp.h> -#include <mach/regs-ost.h> +#undef __REG +#define __REG(x) ((x) & 0xffff) #include <mach/regs-uart.h> -#define FICP __REG(0x40800000) /* Start of FICP area */ -#define ICCR0 __REG(0x40800000) /* ICP Control Register 0 */ -#define ICCR1 __REG(0x40800004) /* ICP Control Register 1 */ -#define ICCR2 __REG(0x40800008) /* ICP Control Register 2 */ -#define ICDR __REG(0x4080000c) /* ICP Data Register */ -#define ICSR0 __REG(0x40800014) /* ICP Status Register 0 */ -#define ICSR1 __REG(0x40800018) /* ICP Status Register 1 */ +#define ICCR0 0x0000 /* ICP Control Register 0 */ +#define ICCR1 0x0004 /* ICP Control Register 1 */ +#define ICCR2 0x0008 /* ICP Control Register 2 */ +#define ICDR 0x000c /* ICP Data Register */ +#define ICSR0 0x0014 /* ICP Status Register 0 */ +#define ICSR1 0x0018 /* ICP Status Register 1 */ #define ICCR0_AME (1 << 7) /* Address match enable */ #define ICCR0_TIE (1 << 6) /* Transmit FIFO interrupt enable */ @@ -56,9 +58,7 @@ #define ICCR2_TRIG_16 (1 << 0) /* >= 16 bytes */ #define ICCR2_TRIG_32 (2 << 0) /* >= 32 bytes */ -#ifdef CONFIG_PXA27x #define ICSR0_EOC (1 << 6) /* DMA End of Descriptor Chain */ -#endif #define ICSR0_FRE (1 << 5) /* Framing error */ #define ICSR0_RFS (1 << 4) /* Receive FIFO service request */ #define ICSR0_TFS (1 << 3) /* Transnit FIFO service request */ @@ -99,18 +99,61 @@ IrSR_RCVEIR_UART_MODE | \ IrSR_XMITIR_IR_MODE) +/* macros for registers read/write */ +#define ficp_writel(irda, val, off) \ + do { \ + dev_vdbg(irda->dev, \ + "%s():%d ficp_writel(0x%x, %s)\n", \ + __func__, __LINE__, (val), #off); \ + writel_relaxed((val), (irda)->irda_base + (off)); \ + } while (0) + +#define ficp_readl(irda, off) \ + ({ \ + unsigned int _v; \ + _v = readl_relaxed((irda)->irda_base + (off)); \ + dev_vdbg(irda->dev, \ + "%s():%d ficp_readl(%s): 0x%x\n", \ + __func__, __LINE__, #off, _v); \ + _v; \ + }) + +#define stuart_writel(irda, val, off) \ + do { \ + dev_vdbg(irda->dev, \ + "%s():%d stuart_writel(0x%x, %s)\n", \ + __func__, __LINE__, (val), #off); \ + writel_relaxed((val), (irda)->stuart_base + (off)); \ + } while (0) + +#define stuart_readl(irda, off) \ + ({ \ + unsigned int _v; \ + _v = readl_relaxed((irda)->stuart_base + (off)); \ + dev_vdbg(irda->dev, \ + "%s():%d stuart_readl(%s): 0x%x\n", \ + __func__, __LINE__, #off, _v); \ + _v; \ + }) + struct pxa_irda { int speed; int newspeed; - unsigned long last_oscr; + unsigned long long last_clk; + void __iomem *stuart_base; + void __iomem *irda_base; unsigned char *dma_rx_buff; unsigned char *dma_tx_buff; dma_addr_t dma_rx_buff_phy; dma_addr_t dma_tx_buff_phy; unsigned int dma_tx_buff_len; - int txdma; - int rxdma; + struct dma_chan *txdma; + struct dma_chan *rxdma; + dma_cookie_t rx_cookie; + dma_cookie_t tx_cookie; + int drcmr_rx; + int drcmr_tx; int uart_irq; int icp_irq; @@ -128,6 +171,8 @@ struct pxa_irda { struct clk *cur_clk; }; +static int pxa_irda_set_speed(struct pxa_irda *si, int speed); + static inline void pxa_irda_disable_clk(struct pxa_irda *si) { if (si->cur_clk) @@ -151,22 +196,41 @@ static inline void pxa_irda_enable_sirclk(struct pxa_irda *si) #define IS_FIR(si) ((si)->speed >= 4000000) #define IRDA_FRAME_SIZE_LIMIT 2047 +static void pxa_irda_fir_dma_rx_irq(void *data); +static void pxa_irda_fir_dma_tx_irq(void *data); + inline static void pxa_irda_fir_dma_rx_start(struct pxa_irda *si) { - DCSR(si->rxdma) = DCSR_NODESC; - DSADR(si->rxdma) = __PREG(ICDR); - DTADR(si->rxdma) = si->dma_rx_buff_phy; - DCMD(si->rxdma) = DCMD_INCTRGADDR | DCMD_FLOWSRC | DCMD_WIDTH1 | DCMD_BURST32 | IRDA_FRAME_SIZE_LIMIT; - DCSR(si->rxdma) |= DCSR_RUN; + struct dma_async_tx_descriptor *tx; + + tx = dmaengine_prep_slave_single(si->rxdma, si->dma_rx_buff_phy, + IRDA_FRAME_SIZE_LIMIT, DMA_FROM_DEVICE, + DMA_PREP_INTERRUPT); + if (!tx) { + dev_err(si->dev, "prep_slave_sg() failed\n"); + return; + } + tx->callback = pxa_irda_fir_dma_rx_irq; + tx->callback_param = si; + si->rx_cookie = dmaengine_submit(tx); + dma_async_issue_pending(si->rxdma); } inline static void pxa_irda_fir_dma_tx_start(struct pxa_irda *si) { - DCSR(si->txdma) = DCSR_NODESC; - DSADR(si->txdma) = si->dma_tx_buff_phy; - DTADR(si->txdma) = __PREG(ICDR); - DCMD(si->txdma) = DCMD_INCSRCADDR | DCMD_FLOWTRG | DCMD_ENDIRQEN | DCMD_WIDTH1 | DCMD_BURST32 | si->dma_tx_buff_len; - DCSR(si->txdma) |= DCSR_RUN; + struct dma_async_tx_descriptor *tx; + + tx = dmaengine_prep_slave_single(si->txdma, si->dma_tx_buff_phy, + si->dma_tx_buff_len, DMA_TO_DEVICE, + DMA_PREP_INTERRUPT); + if (!tx) { + dev_err(si->dev, "prep_slave_sg() failed\n"); + return; + } + tx->callback = pxa_irda_fir_dma_tx_irq; + tx->callback_param = si; + si->tx_cookie = dmaengine_submit(tx); + dma_async_issue_pending(si->rxdma); } /* @@ -205,9 +269,9 @@ static int pxa_irda_set_speed(struct pxa_irda *si, int speed) if (IS_FIR(si)) { /* stop RX DMA */ - DCSR(si->rxdma) &= ~DCSR_RUN; + dmaengine_terminate_all(si->rxdma); /* disable FICP */ - ICCR0 = 0; + ficp_writel(si, 0, ICCR0); pxa_irda_disable_clk(si); /* set board transceiver to SIR mode */ @@ -218,17 +282,19 @@ static int pxa_irda_set_speed(struct pxa_irda *si, int speed) } /* disable STUART first */ - STIER = 0; + stuart_writel(si, 0, STIER); /* access DLL & DLH */ - STLCR |= LCR_DLAB; - STDLL = divisor & 0xff; - STDLH = divisor >> 8; - STLCR &= ~LCR_DLAB; + stuart_writel(si, stuart_readl(si, STLCR) | LCR_DLAB, STLCR); + stuart_writel(si, divisor & 0xff, STDLL); + stuart_writel(si, divisor >> 8, STDLH); + stuart_writel(si, stuart_readl(si, STLCR) & ~LCR_DLAB, STLCR); si->speed = speed; - STISR = IrSR_IR_RECEIVE_ON | IrSR_XMODE_PULSE_1_6; - STIER = IER_UUE | IER_RLSE | IER_RAVIE | IER_RTIOE; + stuart_writel(si, IrSR_IR_RECEIVE_ON | IrSR_XMODE_PULSE_1_6, + STISR); + stuart_writel(si, IER_UUE | IER_RLSE | IER_RAVIE | IER_RTIOE, + STIER); local_irq_restore(flags); break; @@ -237,12 +303,12 @@ static int pxa_irda_set_speed(struct pxa_irda *si, int speed) local_irq_save(flags); /* disable STUART */ - STIER = 0; - STISR = 0; + stuart_writel(si, 0, STIER); + stuart_writel(si, 0, STISR); pxa_irda_disable_clk(si); /* disable FICP first */ - ICCR0 = 0; + ficp_writel(si, 0, ICCR0); /* set board transceiver to FIR mode */ pxa_irda_set_mode(si, IR_FIRMODE); @@ -252,7 +318,7 @@ static int pxa_irda_set_speed(struct pxa_irda *si, int speed) si->speed = speed; pxa_irda_fir_dma_rx_start(si); - ICCR0 = ICCR0_ITR | ICCR0_RXE; + ficp_writel(si, ICCR0_ITR | ICCR0_RXE, ICCR0); local_irq_restore(flags); break; @@ -271,13 +337,13 @@ static irqreturn_t pxa_irda_sir_irq(int irq, void *dev_id) struct pxa_irda *si = netdev_priv(dev); int iir, lsr, data; - iir = STIIR; + iir = stuart_readl(si, STIIR); switch (iir & 0x0F) { case 0x06: /* Receiver Line Status */ - lsr = STLSR; + lsr = stuart_readl(si, STLSR); while (lsr & LSR_FIFOE) { - data = STRBR; + data = stuart_readl(si, STRBR); if (lsr & (LSR_OE | LSR_PE | LSR_FE | LSR_BI)) { printk(KERN_DEBUG "pxa_ir: sir receiving error\n"); dev->stats.rx_errors++; @@ -290,9 +356,9 @@ static irqreturn_t pxa_irda_sir_irq(int irq, void *dev_id) async_unwrap_char(dev, &dev->stats, &si->rx_buff, data); } - lsr = STLSR; + lsr = stuart_readl(si, STLSR); } - si->last_oscr = readl_relaxed(OSCR); + si->last_clk = sched_clock(); break; case 0x04: /* Received Data Available */ @@ -301,14 +367,16 @@ static irqreturn_t pxa_irda_sir_irq(int irq, void *dev_id) case 0x0C: /* Character Timeout Indication */ do { dev->stats.rx_bytes++; - async_unwrap_char(dev, &dev->stats, &si->rx_buff, STRBR); - } while (STLSR & LSR_DR); - si->last_oscr = readl_relaxed(OSCR); + async_unwrap_char(dev, &dev->stats, &si->rx_buff, + stuart_readl(si, STRBR)); + } while (stuart_readl(si, STLSR) & LSR_DR); + si->last_clk = sched_clock(); break; case 0x02: /* Transmit FIFO Data Request */ - while ((si->tx_buff.len) && (STLSR & LSR_TDRQ)) { - STTHR = *si->tx_buff.data++; + while ((si->tx_buff.len) && + (stuart_readl(si, STLSR) & LSR_TDRQ)) { + stuart_writel(si, *si->tx_buff.data++, STTHR); si->tx_buff.len -= 1; } @@ -317,9 +385,9 @@ static irqreturn_t pxa_irda_sir_irq(int irq, void *dev_id) dev->stats.tx_bytes += si->tx_buff.data - si->tx_buff.head; /* We need to ensure that the transmitter has finished. */ - while ((STLSR & LSR_TEMT) == 0) + while ((stuart_readl(si, STLSR) & LSR_TEMT) == 0) cpu_relax(); - si->last_oscr = readl_relaxed(OSCR); + si->last_clk = sched_clock(); /* * Ok, we've finished transmitting. Now enable @@ -331,9 +399,11 @@ static irqreturn_t pxa_irda_sir_irq(int irq, void *dev_id) si->newspeed = 0; } else { /* enable IR Receiver, disable IR Transmitter */ - STISR = IrSR_IR_RECEIVE_ON | IrSR_XMODE_PULSE_1_6; + stuart_writel(si, IrSR_IR_RECEIVE_ON | + IrSR_XMODE_PULSE_1_6, STISR); /* enable STUART and receive interrupts */ - STIER = IER_UUE | IER_RLSE | IER_RAVIE | IER_RTIOE; + stuart_writel(si, IER_UUE | IER_RLSE | + IER_RAVIE | IER_RTIOE, STIER); } /* I'm hungry! */ netif_wake_queue(dev); @@ -345,35 +415,32 @@ static irqreturn_t pxa_irda_sir_irq(int irq, void *dev_id) } /* FIR Receive DMA interrupt handler */ -static void pxa_irda_fir_dma_rx_irq(int channel, void *data) +static void pxa_irda_fir_dma_rx_irq(void *data) { - int dcsr = DCSR(channel); - - DCSR(channel) = dcsr & ~DCSR_RUN; + struct net_device *dev = data; + struct pxa_irda *si = netdev_priv(dev); - printk(KERN_DEBUG "pxa_ir: fir rx dma bus error %#x\n", dcsr); + dmaengine_terminate_all(si->rxdma); + netdev_dbg(dev, "pxa_ir: fir rx dma bus error\n"); } /* FIR Transmit DMA interrupt handler */ -static void pxa_irda_fir_dma_tx_irq(int channel, void *data) +static void pxa_irda_fir_dma_tx_irq(void *data) { struct net_device *dev = data; struct pxa_irda *si = netdev_priv(dev); - int dcsr; - - dcsr = DCSR(channel); - DCSR(channel) = dcsr & ~DCSR_RUN; - if (dcsr & DCSR_ENDINTR) { + dmaengine_terminate_all(si->txdma); + if (dmaengine_tx_status(si->txdma, si->tx_cookie, NULL) == DMA_ERROR) { + dev->stats.tx_errors++; + } else { dev->stats.tx_packets++; dev->stats.tx_bytes += si->dma_tx_buff_len; - } else { - dev->stats.tx_errors++; } - while (ICSR1 & ICSR1_TBY) + while (ficp_readl(si, ICSR1) & ICSR1_TBY) cpu_relax(); - si->last_oscr = readl_relaxed(OSCR); + si->last_clk = sched_clock(); /* * HACK: It looks like the TBY bit is dropped too soon. @@ -387,11 +454,11 @@ static void pxa_irda_fir_dma_tx_irq(int channel, void *data) } else { int i = 64; - ICCR0 = 0; + ficp_writel(si, 0, ICCR0); pxa_irda_fir_dma_rx_start(si); - while ((ICSR1 & ICSR1_RNE) && i--) - (void)ICDR; - ICCR0 = ICCR0_ITR | ICCR0_RXE; + while ((ficp_readl(si, ICSR1) & ICSR1_RNE) && i--) + ficp_readl(si, ICDR); + ficp_writel(si, ICCR0_ITR | ICCR0_RXE, ICCR0); if (i < 0) printk(KERN_ERR "pxa_ir: cannot clear Rx FIFO!\n"); @@ -403,15 +470,18 @@ static void pxa_irda_fir_dma_tx_irq(int channel, void *data) static void pxa_irda_fir_irq_eif(struct pxa_irda *si, struct net_device *dev, int icsr0) { unsigned int len, stat, data; + struct dma_tx_state state; /* Get the current data position. */ - len = DTADR(si->rxdma) - si->dma_rx_buff_phy; + + dmaengine_tx_status(si->rxdma, si->rx_cookie, &state); + len = IRDA_FRAME_SIZE_LIMIT - state.residue; do { /* Read Status, and then Data. */ - stat = ICSR1; + stat = ficp_readl(si, ICSR1); rmb(); - data = ICDR; + data = ficp_readl(si, ICDR); if (stat & (ICSR1_CRE | ICSR1_ROR)) { dev->stats.rx_errors++; @@ -429,7 +499,7 @@ static void pxa_irda_fir_irq_eif(struct pxa_irda *si, struct net_device *dev, in /* If we hit the end of frame, there's no point in continuing. */ if (stat & ICSR1_EOF) break; - } while (ICSR0 & ICSR0_EIF); + } while (ficp_readl(si, ICSR0) & ICSR0_EIF); if (stat & ICSR1_EOF) { /* end of frame. */ @@ -472,9 +542,9 @@ static irqreturn_t pxa_irda_fir_irq(int irq, void *dev_id) int icsr0, i = 64; /* stop RX DMA */ - DCSR(si->rxdma) &= ~DCSR_RUN; - si->last_oscr = readl_relaxed(OSCR); - icsr0 = ICSR0; + dmaengine_terminate_all(si->rxdma); + si->last_clk = sched_clock(); + icsr0 = ficp_readl(si, ICSR0); if (icsr0 & (ICSR0_FRE | ICSR0_RAB)) { if (icsr0 & ICSR0_FRE) { @@ -484,7 +554,7 @@ static irqreturn_t pxa_irda_fir_irq(int irq, void *dev_id) printk(KERN_DEBUG "pxa_ir: fir receive abort\n"); dev->stats.rx_errors++; } - ICSR0 = icsr0 & (ICSR0_FRE | ICSR0_RAB); + ficp_writel(si, icsr0 & (ICSR0_FRE | ICSR0_RAB), ICSR0); } if (icsr0 & ICSR0_EIF) { @@ -492,11 +562,11 @@ static irqreturn_t pxa_irda_fir_irq(int irq, void *dev_id) pxa_irda_fir_irq_eif(si, dev, icsr0); } - ICCR0 = 0; + ficp_writel(si, 0, ICCR0); pxa_irda_fir_dma_rx_start(si); - while ((ICSR1 & ICSR1_RNE) && i--) - (void)ICDR; - ICCR0 = ICCR0_ITR | ICCR0_RXE; + while ((ficp_readl(si, ICSR1) & ICSR1_RNE) && i--) + ficp_readl(si, ICDR); + ficp_writel(si, ICCR0_ITR | ICCR0_RXE, ICCR0); if (i < 0) printk(KERN_ERR "pxa_ir: cannot clear Rx FIFO!\n"); @@ -537,11 +607,12 @@ static int pxa_irda_hard_xmit(struct sk_buff *skb, struct net_device *dev) si->tx_buff.len = async_wrap_skb(skb, si->tx_buff.data, si->tx_buff.truesize); /* Disable STUART interrupts and switch to transmit mode. */ - STIER = 0; - STISR = IrSR_IR_TRANSMIT_ON | IrSR_XMODE_PULSE_1_6; + stuart_writel(si, 0, STIER); + stuart_writel(si, IrSR_IR_TRANSMIT_ON | IrSR_XMODE_PULSE_1_6, + STISR); /* enable STUART and transmit interrupts */ - STIER = IER_UUE | IER_TIE; + stuart_writel(si, IER_UUE | IER_TIE, STIER); } else { unsigned long mtt = irda_get_mtt(skb); @@ -549,15 +620,15 @@ static int pxa_irda_hard_xmit(struct sk_buff *skb, struct net_device *dev) skb_copy_from_linear_data(skb, si->dma_tx_buff, skb->len); if (mtt) - while ((unsigned)(readl_relaxed(OSCR) - si->last_oscr)/4 < mtt) + while ((sched_clock() - si->last_clk) * 1000 < mtt) cpu_relax(); /* stop RX DMA, disable FICP */ - DCSR(si->rxdma) &= ~DCSR_RUN; - ICCR0 = 0; + dmaengine_terminate_all(si->rxdma); + ficp_writel(si, 0, ICCR0); pxa_irda_fir_dma_tx_start(si); - ICCR0 = ICCR0_ITR | ICCR0_TXE; + ficp_writel(si, ICCR0_ITR | ICCR0_TXE, ICCR0); } dev_kfree_skb(skb); @@ -613,22 +684,18 @@ static int pxa_irda_ioctl(struct net_device *dev, struct ifreq *ifreq, int cmd) static void pxa_irda_startup(struct pxa_irda *si) { /* Disable STUART interrupts */ - STIER = 0; + stuart_writel(si, 0, STIER); /* enable STUART interrupt to the processor */ - STMCR = MCR_OUT2; + stuart_writel(si, MCR_OUT2, STMCR); /* configure SIR frame format: StartBit - Data 7 ... Data 0 - Stop Bit */ - STLCR = LCR_WLS0 | LCR_WLS1; + stuart_writel(si, LCR_WLS0 | LCR_WLS1, STLCR); /* enable FIFO, we use FIFO to improve performance */ - STFCR = FCR_TRFIFOE | FCR_ITL_32; + stuart_writel(si, FCR_TRFIFOE | FCR_ITL_32, STFCR); /* disable FICP */ - ICCR0 = 0; + ficp_writel(si, 0, ICCR0); /* configure FICP ICCR2 */ - ICCR2 = ICCR2_TXP | ICCR2_TRIG_32; - - /* configure DMAC */ - DRCMR(17) = si->rxdma | DRCMR_MAPVLD; - DRCMR(18) = si->txdma | DRCMR_MAPVLD; + ficp_writel(si, ICCR2_TXP | ICCR2_TRIG_32, ICCR2); /* force SIR reinitialization */ si->speed = 4000000; @@ -644,22 +711,19 @@ static void pxa_irda_shutdown(struct pxa_irda *si) local_irq_save(flags); /* disable STUART and interrupt */ - STIER = 0; + stuart_writel(si, 0, STIER); /* disable STUART SIR mode */ - STISR = 0; + stuart_writel(si, 0, STISR); /* disable DMA */ - DCSR(si->txdma) &= ~DCSR_RUN; - DCSR(si->rxdma) &= ~DCSR_RUN; + dmaengine_terminate_all(si->rxdma); + dmaengine_terminate_all(si->txdma); /* disable FICP */ - ICCR0 = 0; + ficp_writel(si, 0, ICCR0); /* disable the STUART or FICP clocks */ pxa_irda_disable_clk(si); - DRCMR(17) = 0; - DRCMR(18) = 0; - local_irq_restore(flags); /* power off board transceiver */ @@ -671,6 +735,9 @@ static void pxa_irda_shutdown(struct pxa_irda *si) static int pxa_irda_start(struct net_device *dev) { struct pxa_irda *si = netdev_priv(dev); + dma_cap_mask_t mask; + struct dma_slave_config config; + struct pxad_param param; int err; si->speed = 9600; @@ -690,14 +757,37 @@ static int pxa_irda_start(struct net_device *dev) disable_irq(si->icp_irq); err = -EBUSY; - si->rxdma = pxa_request_dma("FICP_RX",DMA_PRIO_LOW, pxa_irda_fir_dma_rx_irq, dev); - if (si->rxdma < 0) + dma_cap_zero(mask); + dma_cap_set(DMA_SLAVE, mask); + param.prio = PXAD_PRIO_LOWEST; + + memset(&config, 0, sizeof(config)); + config.src_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE; + config.dst_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE; + config.src_addr = (dma_addr_t)si->irda_base + ICDR; + config.dst_addr = (dma_addr_t)si->irda_base + ICDR; + config.src_maxburst = 32; + config.dst_maxburst = 32; + + param.drcmr = si->drcmr_rx; + si->rxdma = dma_request_slave_channel_compat(mask, pxad_filter_fn, + ¶m, &dev->dev, "rx"); + if (!si->rxdma) goto err_rx_dma; - si->txdma = pxa_request_dma("FICP_TX",DMA_PRIO_LOW, pxa_irda_fir_dma_tx_irq, dev); - if (si->txdma < 0) + param.drcmr = si->drcmr_tx; + si->txdma = dma_request_slave_channel_compat(mask, pxad_filter_fn, + ¶m, &dev->dev, "tx"); + if (!si->txdma) goto err_tx_dma; + err = dmaengine_slave_config(si->rxdma, &config); + if (err) + goto err_dma_rx_buff; + err = dmaengine_slave_config(si->txdma, &config); + if (err) + goto err_dma_rx_buff; + err = -ENOMEM; si->dma_rx_buff = dma_alloc_coherent(si->dev, IRDA_FRAME_SIZE_LIMIT, &si->dma_rx_buff_phy, GFP_KERNEL); @@ -737,9 +827,9 @@ err_irlap: err_dma_tx_buff: dma_free_coherent(si->dev, IRDA_FRAME_SIZE_LIMIT, si->dma_rx_buff, si->dma_rx_buff_phy); err_dma_rx_buff: - pxa_free_dma(si->txdma); + dma_release_channel(si->txdma); err_tx_dma: - pxa_free_dma(si->rxdma); + dma_release_channel(si->rxdma); err_rx_dma: free_irq(si->icp_irq, dev); err_irq2: @@ -766,8 +856,10 @@ static int pxa_irda_stop(struct net_device *dev) free_irq(si->uart_irq, dev); free_irq(si->icp_irq, dev); - pxa_free_dma(si->rxdma); - pxa_free_dma(si->txdma); + dmaengine_terminate_all(si->rxdma); + dmaengine_terminate_all(si->txdma); + dma_release_channel(si->rxdma); + dma_release_channel(si->txdma); if (si->dma_rx_buff) dma_free_coherent(si->dev, IRDA_FRAME_SIZE_LIMIT, si->dma_tx_buff, si->dma_tx_buff_phy); @@ -830,25 +922,33 @@ static const struct net_device_ops pxa_irda_netdev_ops = { static int pxa_irda_probe(struct platform_device *pdev) { struct net_device *dev; + struct resource *res; struct pxa_irda *si; + void __iomem *ficp, *stuart; unsigned int baudrate_mask; int err; if (!pdev->dev.platform_data) return -ENODEV; - err = request_mem_region(__PREG(STUART), 0x24, "IrDA") ? 0 : -EBUSY; - if (err) - goto err_mem_1; + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + ficp = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(ficp)) { + dev_err(&pdev->dev, "resource ficp not defined\n"); + return PTR_ERR(ficp); + } - err = request_mem_region(__PREG(FICP), 0x1c, "IrDA") ? 0 : -EBUSY; - if (err) - goto err_mem_2; + res = platform_get_resource(pdev, IORESOURCE_MEM, 1); + stuart = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(stuart)) { + dev_err(&pdev->dev, "resource stuart not defined\n"); + return PTR_ERR(stuart); + } dev = alloc_irdadev(sizeof(struct pxa_irda)); if (!dev) { err = -ENOMEM; - goto err_mem_3; + goto err_mem_1; } SET_NETDEV_DEV(dev, &pdev->dev); @@ -856,16 +956,25 @@ static int pxa_irda_probe(struct platform_device *pdev) si->dev = &pdev->dev; si->pdata = pdev->dev.platform_data; + si->irda_base = ficp; + si->stuart_base = stuart; si->uart_irq = platform_get_irq(pdev, 0); si->icp_irq = platform_get_irq(pdev, 1); - si->sir_clk = clk_get(&pdev->dev, "UARTCLK"); - si->fir_clk = clk_get(&pdev->dev, "FICPCLK"); + si->sir_clk = devm_clk_get(&pdev->dev, "UARTCLK"); + si->fir_clk = devm_clk_get(&pdev->dev, "FICPCLK"); if (IS_ERR(si->sir_clk) || IS_ERR(si->fir_clk)) { err = PTR_ERR(IS_ERR(si->sir_clk) ? si->sir_clk : si->fir_clk); goto err_mem_4; } + res = platform_get_resource(pdev, IORESOURCE_DMA, 0); + if (res) + si->drcmr_rx = res->start; + res = platform_get_resource(pdev, IORESOURCE_DMA, 1); + if (res) + si->drcmr_tx = res->start; + /* * Initialise the SIR buffers */ @@ -925,15 +1034,7 @@ err_startup: err_mem_5: kfree(si->rx_buff.head); err_mem_4: - if (si->sir_clk && !IS_ERR(si->sir_clk)) - clk_put(si->sir_clk); - if (si->fir_clk && !IS_ERR(si->fir_clk)) - clk_put(si->fir_clk); free_netdev(dev); -err_mem_3: - release_mem_region(__PREG(FICP), 0x1c); -err_mem_2: - release_mem_region(__PREG(STUART), 0x24); } err_mem_1: return err; @@ -952,14 +1053,9 @@ static int pxa_irda_remove(struct platform_device *_dev) si->pdata->shutdown(si->dev); kfree(si->tx_buff.head); kfree(si->rx_buff.head); - clk_put(si->fir_clk); - clk_put(si->sir_clk); free_netdev(dev); } - release_mem_region(__PREG(STUART), 0x24); - release_mem_region(__PREG(FICP), 0x1c); - return 0; } diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig index fbb9325d1f6e..3a8a36c8ded1 100644 --- a/drivers/net/usb/Kconfig +++ b/drivers/net/usb/Kconfig @@ -109,6 +109,8 @@ config USB_RTL8152 config USB_LAN78XX tristate "Microchip LAN78XX Based USB Ethernet Adapters" select MII + select PHYLIB + select MICROCHIP_PHY help This option adds support for Microchip LAN78XX based USB 2 & USB 3 10/100/1000 Ethernet adapters. @@ -541,7 +543,7 @@ config USB_NET_INT51X1 config USB_CDC_PHONET tristate "CDC Phonet support" - depends on PHONET + depends on PHONET && USB_USBNET help Choose this option to support the Phonet interface to a Nokia cellular modem, as found on most Nokia handsets with the diff --git a/drivers/net/usb/cdc-phonet.c b/drivers/net/usb/cdc-phonet.c index 415ce8b882c6..ff2270ead2e6 100644 --- a/drivers/net/usb/cdc-phonet.c +++ b/drivers/net/usb/cdc-phonet.c @@ -340,32 +340,13 @@ static int usbpn_probe(struct usb_interface *intf, const struct usb_device_id *i u8 *data; int phonet = 0; int len, err; + struct usb_cdc_parsed_header hdr; data = intf->altsetting->extra; len = intf->altsetting->extralen; - while (len >= 3) { - u8 dlen = data[0]; - if (dlen < 3) - return -EINVAL; - - /* bDescriptorType */ - if (data[1] == USB_DT_CS_INTERFACE) { - /* bDescriptorSubType */ - switch (data[2]) { - case USB_CDC_UNION_TYPE: - if (union_header || dlen < 5) - break; - union_header = - (struct usb_cdc_union_desc *)data; - break; - case 0xAB: - phonet = 1; - break; - } - } - data += dlen; - len -= dlen; - } + cdc_parse_cdc_header(&hdr, intf, data, len); + union_header = hdr.usb_cdc_union_desc; + phonet = hdr.phonet_magic_present; if (!union_header || !phonet) return -EINVAL; diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index 35a2bffe848a..c78d3cb1b464 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -112,8 +112,7 @@ int usbnet_generic_cdc_bind(struct usbnet *dev, struct usb_interface *intf) int rndis; bool android_rndis_quirk = false; struct usb_driver *driver = driver_of(intf); - struct usb_cdc_mdlm_desc *desc = NULL; - struct usb_cdc_mdlm_detail_desc *detail = NULL; + struct usb_cdc_parsed_header header; if (sizeof(dev->data) < sizeof(*info)) return -EDOM; @@ -155,156 +154,89 @@ int usbnet_generic_cdc_bind(struct usbnet *dev, struct usb_interface *intf) memset(info, 0, sizeof(*info)); info->control = intf; - while (len > 3) { - if (buf[1] != USB_DT_CS_INTERFACE) - goto next_desc; - - /* use bDescriptorSubType to identify the CDC descriptors. - * We expect devices with CDC header and union descriptors. - * For CDC Ethernet we need the ethernet descriptor. - * For RNDIS, ignore two (pointless) CDC modem descriptors - * in favor of a complicated OID-based RPC scheme doing what - * CDC Ethernet achieves with a simple descriptor. - */ - switch (buf[2]) { - case USB_CDC_HEADER_TYPE: - if (info->header) { - dev_dbg(&intf->dev, "extra CDC header\n"); - goto bad_desc; - } - info->header = (void *) buf; - if (info->header->bLength != sizeof(*info->header)) { - dev_dbg(&intf->dev, "CDC header len %u\n", - info->header->bLength); - goto bad_desc; - } - break; - case USB_CDC_ACM_TYPE: - /* paranoia: disambiguate a "real" vendor-specific - * modem interface from an RNDIS non-modem. - */ - if (rndis) { - struct usb_cdc_acm_descriptor *acm; - - acm = (void *) buf; - if (acm->bmCapabilities) { - dev_dbg(&intf->dev, - "ACM capabilities %02x, " - "not really RNDIS?\n", - acm->bmCapabilities); - goto bad_desc; - } - } - break; - case USB_CDC_UNION_TYPE: - if (info->u) { - dev_dbg(&intf->dev, "extra CDC union\n"); - goto bad_desc; - } - info->u = (void *) buf; - if (info->u->bLength != sizeof(*info->u)) { - dev_dbg(&intf->dev, "CDC union len %u\n", - info->u->bLength); - goto bad_desc; - } - - /* we need a master/control interface (what we're - * probed with) and a slave/data interface; union - * descriptors sort this all out. - */ - info->control = usb_ifnum_to_if(dev->udev, - info->u->bMasterInterface0); - info->data = usb_ifnum_to_if(dev->udev, - info->u->bSlaveInterface0); - if (!info->control || !info->data) { - dev_dbg(&intf->dev, - "master #%u/%p slave #%u/%p\n", - info->u->bMasterInterface0, - info->control, - info->u->bSlaveInterface0, - info->data); - /* fall back to hard-wiring for RNDIS */ - if (rndis) { - android_rndis_quirk = true; - goto next_desc; - } - goto bad_desc; - } - if (info->control != intf) { - dev_dbg(&intf->dev, "bogus CDC Union\n"); - /* Ambit USB Cable Modem (and maybe others) - * interchanges master and slave interface. - */ - if (info->data == intf) { - info->data = info->control; - info->control = intf; - } else - goto bad_desc; - } - - /* some devices merge these - skip class check */ - if (info->control == info->data) - goto next_desc; - - /* a data interface altsetting does the real i/o */ - d = &info->data->cur_altsetting->desc; - if (d->bInterfaceClass != USB_CLASS_CDC_DATA) { - dev_dbg(&intf->dev, "slave class %u\n", - d->bInterfaceClass); - goto bad_desc; - } - break; - case USB_CDC_ETHERNET_TYPE: - if (info->ether) { - dev_dbg(&intf->dev, "extra CDC ether\n"); - goto bad_desc; - } - info->ether = (void *) buf; - if (info->ether->bLength != sizeof(*info->ether)) { - dev_dbg(&intf->dev, "CDC ether len %u\n", - info->ether->bLength); - goto bad_desc; - } - dev->hard_mtu = le16_to_cpu( - info->ether->wMaxSegmentSize); - /* because of Zaurus, we may be ignoring the host - * side link address we were given. - */ - break; - case USB_CDC_MDLM_TYPE: - if (desc) { - dev_dbg(&intf->dev, "extra MDLM descriptor\n"); - goto bad_desc; - } - - desc = (void *)buf; - - if (desc->bLength != sizeof(*desc)) - goto bad_desc; - - if (memcmp(&desc->bGUID, mbm_guid, 16)) - goto bad_desc; - break; - case USB_CDC_MDLM_DETAIL_TYPE: - if (detail) { - dev_dbg(&intf->dev, "extra MDLM detail descriptor\n"); - goto bad_desc; - } - - detail = (void *)buf; - - if (detail->bGuidDescriptorType == 0) { - if (detail->bLength < (sizeof(*detail) + 1)) - goto bad_desc; - } else - goto bad_desc; - break; + + cdc_parse_cdc_header(&header, intf, buf, len); + + info->u = header.usb_cdc_union_desc; + info->header = header.usb_cdc_header_desc; + info->ether = header.usb_cdc_ether_desc; + /* we need a master/control interface (what we're + * probed with) and a slave/data interface; union + * descriptors sort this all out. + */ + info->control = usb_ifnum_to_if(dev->udev, + info->u->bMasterInterface0); + info->data = usb_ifnum_to_if(dev->udev, + info->u->bSlaveInterface0); + if (!info->control || !info->data) { + dev_dbg(&intf->dev, + "master #%u/%p slave #%u/%p\n", + info->u->bMasterInterface0, + info->control, + info->u->bSlaveInterface0, + info->data); + /* fall back to hard-wiring for RNDIS */ + if (rndis) { + android_rndis_quirk = true; + goto skip; } -next_desc: - len -= buf[0]; /* bLength */ - buf += buf[0]; + goto bad_desc; + } + if (info->control != intf) { + dev_dbg(&intf->dev, "bogus CDC Union\n"); + /* Ambit USB Cable Modem (and maybe others) + * interchanges master and slave interface. + */ + if (info->data == intf) { + info->data = info->control; + info->control = intf; + } else + goto bad_desc; + } + + /* some devices merge these - skip class check */ + if (info->control == info->data) + goto skip; + + /* a data interface altsetting does the real i/o */ + d = &info->data->cur_altsetting->desc; + if (d->bInterfaceClass != USB_CLASS_CDC_DATA) { + dev_dbg(&intf->dev, "slave class %u\n", + d->bInterfaceClass); + goto bad_desc; + } +skip: + if ( rndis && + header.usb_cdc_acm_descriptor && + header.usb_cdc_acm_descriptor->bmCapabilities) { + dev_dbg(&intf->dev, + "ACM capabilities %02x, not really RNDIS?\n", + header.usb_cdc_acm_descriptor->bmCapabilities); + goto bad_desc; } + if (header.usb_cdc_ether_desc) { + dev->hard_mtu = le16_to_cpu(info->ether->wMaxSegmentSize); + /* because of Zaurus, we may be ignoring the host + * side link address we were given. + */ + } + + if (header.usb_cdc_mdlm_desc && + memcmp(header.usb_cdc_mdlm_desc->bGUID, mbm_guid, 16)) { + dev_dbg(&intf->dev, "GUID doesn't match\n"); + goto bad_desc; + } + + if (header.usb_cdc_mdlm_detail_desc && + header.usb_cdc_mdlm_detail_desc->bLength < + (sizeof(struct usb_cdc_mdlm_detail_desc) + 1)) { + dev_dbg(&intf->dev, "Descriptor too short\n"); + goto bad_desc; + } + + + /* Microsoft ActiveSync based and some regular RNDIS devices lack the * CDC descriptors, so we'll hard-wire the interfaces and not check * for descriptors. diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c index efc18e05af0a..bbde9884ab8a 100644 --- a/drivers/net/usb/cdc_mbim.c +++ b/drivers/net/usb/cdc_mbim.c @@ -342,7 +342,7 @@ static void do_neigh_solicit(struct usbnet *dev, u8 *buf, u16 tci) in6_dev_put(in6_dev); /* ipv6_stub != NULL if in6_dev_get returned an inet6_dev */ - ipv6_stub->ndisc_send_na(netdev, NULL, &iph->saddr, &msg->target, + ipv6_stub->ndisc_send_na(netdev, &iph->saddr, &msg->target, is_router /* router */, true /* solicited */, false /* override */, diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index db40175b1a0b..a187f08113ec 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -698,6 +698,7 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_ int len; int temp; u8 iface_no; + struct usb_cdc_parsed_header hdr; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) @@ -722,66 +723,14 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_ len = intf->cur_altsetting->extralen; /* parse through descriptors associated with control interface */ - while ((len > 0) && (buf[0] > 2) && (buf[0] <= len)) { - - if (buf[1] != USB_DT_CS_INTERFACE) - goto advance; - - switch (buf[2]) { - case USB_CDC_UNION_TYPE: - if (buf[0] < sizeof(*union_desc)) - break; - - union_desc = (const struct usb_cdc_union_desc *)buf; - /* the master must be the interface we are probing */ - if (intf->cur_altsetting->desc.bInterfaceNumber != - union_desc->bMasterInterface0) { - dev_dbg(&intf->dev, "bogus CDC Union\n"); - goto error; - } - ctx->data = usb_ifnum_to_if(dev->udev, - union_desc->bSlaveInterface0); - break; - - case USB_CDC_ETHERNET_TYPE: - if (buf[0] < sizeof(*(ctx->ether_desc))) - break; - - ctx->ether_desc = - (const struct usb_cdc_ether_desc *)buf; - break; - - case USB_CDC_NCM_TYPE: - if (buf[0] < sizeof(*(ctx->func_desc))) - break; - - ctx->func_desc = (const struct usb_cdc_ncm_desc *)buf; - break; - - case USB_CDC_MBIM_TYPE: - if (buf[0] < sizeof(*(ctx->mbim_desc))) - break; - - ctx->mbim_desc = (const struct usb_cdc_mbim_desc *)buf; - break; - - case USB_CDC_MBIM_EXTENDED_TYPE: - if (buf[0] < sizeof(*(ctx->mbim_extended_desc))) - break; - - ctx->mbim_extended_desc = - (const struct usb_cdc_mbim_extended_desc *)buf; - break; - - default: - break; - } -advance: - /* advance to next descriptor */ - temp = buf[0]; - buf += temp; - len -= temp; - } + cdc_parse_cdc_header(&hdr, intf, buf, len); + + ctx->data = usb_ifnum_to_if(dev->udev, + hdr.usb_cdc_union_desc->bSlaveInterface0); + ctx->ether_desc = hdr.usb_cdc_ether_desc; + ctx->func_desc = hdr.usb_cdc_ncm_desc; + ctx->mbim_desc = hdr.usb_cdc_mbim_desc; + ctx->mbim_extended_desc = hdr.usb_cdc_mbim_extended_desc; /* some buggy devices have an IAD but no CDC Union */ if (!union_desc && intf->intf_assoc && intf->intf_assoc->bInterfaceCount == 2) { diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index a39518fc93aa..226668ead0d8 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -19,7 +19,6 @@ #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/ethtool.h> -#include <linux/mii.h> #include <linux/usb.h> #include <linux/crc32.h> #include <linux/signal.h> @@ -31,12 +30,13 @@ #include <linux/ipv6.h> #include <linux/mdio.h> #include <net/ip6_checksum.h> +#include <linux/microchipphy.h> #include "lan78xx.h" #define DRIVER_AUTHOR "WOOJUNG HUH <woojung.huh@microchip.com>" #define DRIVER_DESC "LAN78XX USB 3.0 Gigabit Ethernet Devices" #define DRIVER_NAME "lan78xx" -#define DRIVER_VERSION "1.0.0" +#define DRIVER_VERSION "1.0.1" #define TX_TIMEOUT_JIFFIES (5 * HZ) #define THROTTLE_JIFFIES (HZ / 8) @@ -57,7 +57,6 @@ #define DEFAULT_RX_CSUM_ENABLE (true) #define DEFAULT_TSO_CSUM_ENABLE (true) #define DEFAULT_VLAN_FILTER_ENABLE (true) -#define INTERNAL_PHY_ID (2) /* 2: GMII */ #define TX_OVERHEAD (8) #define RXW_PADDING 2 @@ -275,10 +274,12 @@ struct lan78xx_net { struct timer_list delay; unsigned long data[5]; - struct mii_if_info mii; int link_on; u8 mdix_ctrl; + + u32 devid; + struct mii_bus *mdiobus; }; /* use ethtool to change the level for any given device */ @@ -411,222 +412,6 @@ static inline u32 mii_access(int id, int index, int read) return ret; } -static int lan78xx_mdio_read(struct net_device *netdev, int phy_id, int idx) -{ - struct lan78xx_net *dev = netdev_priv(netdev); - u32 val, addr; - int ret; - - ret = usb_autopm_get_interface(dev->intf); - if (ret < 0) - return ret; - - mutex_lock(&dev->phy_mutex); - - /* confirm MII not busy */ - ret = lan78xx_phy_wait_not_busy(dev); - if (ret < 0) - goto done; - - /* set the address, index & direction (read from PHY) */ - phy_id &= dev->mii.phy_id_mask; - idx &= dev->mii.reg_num_mask; - addr = mii_access(phy_id, idx, MII_READ); - ret = lan78xx_write_reg(dev, MII_ACC, addr); - - ret = lan78xx_phy_wait_not_busy(dev); - if (ret < 0) - goto done; - - ret = lan78xx_read_reg(dev, MII_DATA, &val); - - ret = (int)(val & 0xFFFF); - -done: - mutex_unlock(&dev->phy_mutex); - usb_autopm_put_interface(dev->intf); - return ret; -} - -static void lan78xx_mdio_write(struct net_device *netdev, int phy_id, - int idx, int regval) -{ - struct lan78xx_net *dev = netdev_priv(netdev); - u32 val, addr; - int ret; - - if (usb_autopm_get_interface(dev->intf) < 0) - return; - - mutex_lock(&dev->phy_mutex); - - /* confirm MII not busy */ - ret = lan78xx_phy_wait_not_busy(dev); - if (ret < 0) - goto done; - - val = regval; - ret = lan78xx_write_reg(dev, MII_DATA, val); - - /* set the address, index & direction (write to PHY) */ - phy_id &= dev->mii.phy_id_mask; - idx &= dev->mii.reg_num_mask; - addr = mii_access(phy_id, idx, MII_WRITE); - ret = lan78xx_write_reg(dev, MII_ACC, addr); - - ret = lan78xx_phy_wait_not_busy(dev); - if (ret < 0) - goto done; - -done: - mutex_unlock(&dev->phy_mutex); - usb_autopm_put_interface(dev->intf); -} - -static void lan78xx_mmd_write(struct net_device *netdev, int phy_id, - int mmddev, int mmdidx, int regval) -{ - struct lan78xx_net *dev = netdev_priv(netdev); - u32 val, addr; - int ret; - - if (usb_autopm_get_interface(dev->intf) < 0) - return; - - mutex_lock(&dev->phy_mutex); - - /* confirm MII not busy */ - ret = lan78xx_phy_wait_not_busy(dev); - if (ret < 0) - goto done; - - mmddev &= 0x1F; - - /* set up device address for MMD */ - ret = lan78xx_write_reg(dev, MII_DATA, mmddev); - - phy_id &= dev->mii.phy_id_mask; - addr = mii_access(phy_id, PHY_MMD_CTL, MII_WRITE); - ret = lan78xx_write_reg(dev, MII_ACC, addr); - - ret = lan78xx_phy_wait_not_busy(dev); - if (ret < 0) - goto done; - - /* select register of MMD */ - val = mmdidx; - ret = lan78xx_write_reg(dev, MII_DATA, val); - - phy_id &= dev->mii.phy_id_mask; - addr = mii_access(phy_id, PHY_MMD_REG_DATA, MII_WRITE); - ret = lan78xx_write_reg(dev, MII_ACC, addr); - - ret = lan78xx_phy_wait_not_busy(dev); - if (ret < 0) - goto done; - - /* select register data for MMD */ - val = PHY_MMD_CTRL_OP_DNI_ | mmddev; - ret = lan78xx_write_reg(dev, MII_DATA, val); - - phy_id &= dev->mii.phy_id_mask; - addr = mii_access(phy_id, PHY_MMD_CTL, MII_WRITE); - ret = lan78xx_write_reg(dev, MII_ACC, addr); - - ret = lan78xx_phy_wait_not_busy(dev); - if (ret < 0) - goto done; - - /* write to MMD */ - val = regval; - ret = lan78xx_write_reg(dev, MII_DATA, val); - - phy_id &= dev->mii.phy_id_mask; - addr = mii_access(phy_id, PHY_MMD_REG_DATA, MII_WRITE); - ret = lan78xx_write_reg(dev, MII_ACC, addr); - - ret = lan78xx_phy_wait_not_busy(dev); - if (ret < 0) - goto done; - -done: - mutex_unlock(&dev->phy_mutex); - usb_autopm_put_interface(dev->intf); -} - -static int lan78xx_mmd_read(struct net_device *netdev, int phy_id, - int mmddev, int mmdidx) -{ - struct lan78xx_net *dev = netdev_priv(netdev); - u32 val, addr; - int ret; - - ret = usb_autopm_get_interface(dev->intf); - if (ret < 0) - return ret; - - mutex_lock(&dev->phy_mutex); - - /* confirm MII not busy */ - ret = lan78xx_phy_wait_not_busy(dev); - if (ret < 0) - goto done; - - /* set up device address for MMD */ - ret = lan78xx_write_reg(dev, MII_DATA, mmddev); - - phy_id &= dev->mii.phy_id_mask; - addr = mii_access(phy_id, PHY_MMD_CTL, MII_WRITE); - ret = lan78xx_write_reg(dev, MII_ACC, addr); - - ret = lan78xx_phy_wait_not_busy(dev); - if (ret < 0) - goto done; - - /* select register of MMD */ - val = mmdidx; - ret = lan78xx_write_reg(dev, MII_DATA, val); - - phy_id &= dev->mii.phy_id_mask; - addr = mii_access(phy_id, PHY_MMD_REG_DATA, MII_WRITE); - ret = lan78xx_write_reg(dev, MII_ACC, addr); - - ret = lan78xx_phy_wait_not_busy(dev); - if (ret < 0) - goto done; - - /* select register data for MMD */ - val = PHY_MMD_CTRL_OP_DNI_ | mmddev; - ret = lan78xx_write_reg(dev, MII_DATA, val); - - phy_id &= dev->mii.phy_id_mask; - addr = mii_access(phy_id, PHY_MMD_CTL, MII_WRITE); - ret = lan78xx_write_reg(dev, MII_ACC, addr); - - ret = lan78xx_phy_wait_not_busy(dev); - if (ret < 0) - goto done; - - /* set the address, index & direction (read from PHY) */ - phy_id &= dev->mii.phy_id_mask; - addr = mii_access(phy_id, PHY_MMD_REG_DATA, MII_READ); - ret = lan78xx_write_reg(dev, MII_ACC, addr); - - ret = lan78xx_phy_wait_not_busy(dev); - if (ret < 0) - goto done; - - /* read from MMD */ - ret = lan78xx_read_reg(dev, MII_DATA, &val); - - ret = (int)(val & 0xFFFF); - -done: - mutex_unlock(&dev->phy_mutex); - usb_autopm_put_interface(dev->intf); - return ret; -} - static int lan78xx_wait_eeprom(struct lan78xx_net *dev) { unsigned long start_time = jiffies; @@ -1047,14 +832,13 @@ static int lan78xx_update_flowcontrol(struct lan78xx_net *dev, u8 duplex, static int lan78xx_link_reset(struct lan78xx_net *dev) { - struct mii_if_info *mii = &dev->mii; + struct phy_device *phydev = dev->net->phydev; struct ethtool_cmd ecmd = { .cmd = ETHTOOL_GSET }; int ladv, radv, ret; u32 buf; /* clear PHY interrupt status */ - /* VTSE PHY */ - ret = lan78xx_mdio_read(dev->net, mii->phy_id, PHY_VTSE_INT_STS); + ret = phy_read(phydev, LAN88XX_INT_STS); if (unlikely(ret < 0)) return -EIO; @@ -1063,7 +847,9 @@ static int lan78xx_link_reset(struct lan78xx_net *dev) if (unlikely(ret < 0)) return -EIO; - if (!mii_link_ok(mii) && dev->link_on) { + phy_read_status(phydev); + + if (!phydev->link && dev->link_on) { dev->link_on = false; netif_carrier_off(dev->net); @@ -1075,13 +861,12 @@ static int lan78xx_link_reset(struct lan78xx_net *dev) ret = lan78xx_write_reg(dev, MAC_CR, buf); if (unlikely(ret < 0)) return -EIO; - } else if (mii_link_ok(mii) && !dev->link_on) { + } else if (phydev->link && !dev->link_on) { dev->link_on = true; - mii_check_media(mii, 1, 1); - mii_ethtool_gset(&dev->mii, &ecmd); + phy_ethtool_gset(phydev, &ecmd); - mii->mdio_read(mii->dev, mii->phy_id, PHY_VTSE_INT_STS); + ret = phy_read(phydev, LAN88XX_INT_STS); if (dev->udev->speed == USB_SPEED_SUPER) { if (ethtool_cmd_speed(&ecmd) == 1000) { @@ -1102,11 +887,11 @@ static int lan78xx_link_reset(struct lan78xx_net *dev) } } - ladv = lan78xx_mdio_read(dev->net, mii->phy_id, MII_ADVERTISE); + ladv = phy_read(phydev, MII_ADVERTISE); if (ladv < 0) return ladv; - radv = lan78xx_mdio_read(dev->net, mii->phy_id, MII_LPA); + radv = phy_read(phydev, MII_LPA); if (radv < 0) return radv; @@ -1279,6 +1064,8 @@ static int lan78xx_set_wol(struct net_device *netdev, device_set_wakeup_enable(&dev->udev->dev, (bool)wol->wolopts); + phy_ethtool_set_wol(netdev->phydev, wol); + usb_autopm_put_interface(dev->intf); return ret; @@ -1287,49 +1074,39 @@ static int lan78xx_set_wol(struct net_device *netdev, static int lan78xx_get_eee(struct net_device *net, struct ethtool_eee *edata) { struct lan78xx_net *dev = netdev_priv(net); + struct phy_device *phydev = net->phydev; int ret; u32 buf; - u32 adv, lpadv; ret = usb_autopm_get_interface(dev->intf); if (ret < 0) return ret; + ret = phy_ethtool_get_eee(phydev, edata); + if (ret < 0) + goto exit; + ret = lan78xx_read_reg(dev, MAC_CR, &buf); if (buf & MAC_CR_EEE_EN_) { - buf = lan78xx_mmd_read(dev->net, dev->mii.phy_id, - PHY_MMD_DEV_7, PHY_EEE_ADVERTISEMENT); - adv = mmd_eee_adv_to_ethtool_adv_t(buf); - buf = lan78xx_mmd_read(dev->net, dev->mii.phy_id, - PHY_MMD_DEV_7, PHY_EEE_LP_ADVERTISEMENT); - lpadv = mmd_eee_adv_to_ethtool_adv_t(buf); - edata->eee_enabled = true; - edata->supported = true; - edata->eee_active = !!(adv & lpadv); - edata->advertised = adv; - edata->lp_advertised = lpadv; + edata->eee_active = !!(edata->advertised & + edata->lp_advertised); edata->tx_lpi_enabled = true; /* EEE_TX_LPI_REQ_DLY & tx_lpi_timer are same uSec unit */ ret = lan78xx_read_reg(dev, EEE_TX_LPI_REQ_DLY, &buf); edata->tx_lpi_timer = buf; } else { - buf = lan78xx_mmd_read(dev->net, dev->mii.phy_id, - PHY_MMD_DEV_7, PHY_EEE_LP_ADVERTISEMENT); - lpadv = mmd_eee_adv_to_ethtool_adv_t(buf); - edata->eee_enabled = false; edata->eee_active = false; - edata->supported = false; - edata->advertised = 0; - edata->lp_advertised = mmd_eee_adv_to_ethtool_adv_t(lpadv); edata->tx_lpi_enabled = false; edata->tx_lpi_timer = 0; } + ret = 0; +exit: usb_autopm_put_interface(dev->intf); - return 0; + return ret; } static int lan78xx_set_eee(struct net_device *net, struct ethtool_eee *edata) @@ -1347,9 +1124,10 @@ static int lan78xx_set_eee(struct net_device *net, struct ethtool_eee *edata) buf |= MAC_CR_EEE_EN_; ret = lan78xx_write_reg(dev, MAC_CR, buf); - buf = ethtool_adv_to_mmd_eee_adv_t(edata->advertised); - lan78xx_mmd_write(dev->net, dev->mii.phy_id, - PHY_MMD_DEV_7, PHY_EEE_ADVERTISEMENT, buf); + phy_ethtool_set_eee(net->phydev, edata); + + buf = (u32)edata->tx_lpi_timer; + ret = lan78xx_write_reg(dev, EEE_TX_LPI_REQ_DLY, buf); } else { ret = lan78xx_read_reg(dev, MAC_CR, &buf); buf &= ~MAC_CR_EEE_EN_; @@ -1363,19 +1141,14 @@ static int lan78xx_set_eee(struct net_device *net, struct ethtool_eee *edata) static u32 lan78xx_get_link(struct net_device *net) { - struct lan78xx_net *dev = netdev_priv(net); + phy_read_status(net->phydev); - return mii_link_ok(&dev->mii); + return net->phydev->link; } int lan78xx_nway_reset(struct net_device *net) { - struct lan78xx_net *dev = netdev_priv(net); - - if ((!dev->mii.mdio_read) || (!dev->mii.mdio_write)) - return -EOPNOTSUPP; - - return mii_nway_restart(&dev->mii); + return phy_start_aneg(net->phydev); } static void lan78xx_get_drvinfo(struct net_device *net, @@ -1402,36 +1175,78 @@ static void lan78xx_set_msglevel(struct net_device *net, u32 level) dev->msg_enable = level; } +static int lan78xx_get_mdix_status(struct net_device *net) +{ + struct phy_device *phydev = net->phydev; + int buf; + + phy_write(phydev, LAN88XX_EXT_PAGE_ACCESS, LAN88XX_EXT_PAGE_SPACE_1); + buf = phy_read(phydev, LAN88XX_EXT_MODE_CTRL); + phy_write(phydev, LAN88XX_EXT_PAGE_ACCESS, LAN88XX_EXT_PAGE_SPACE_0); + + return buf; +} + +static void lan78xx_set_mdix_status(struct net_device *net, __u8 mdix_ctrl) +{ + struct lan78xx_net *dev = netdev_priv(net); + struct phy_device *phydev = net->phydev; + int buf; + + if (mdix_ctrl == ETH_TP_MDI) { + phy_write(phydev, LAN88XX_EXT_PAGE_ACCESS, + LAN88XX_EXT_PAGE_SPACE_1); + buf = phy_read(phydev, LAN88XX_EXT_MODE_CTRL); + buf &= ~LAN88XX_EXT_MODE_CTRL_MDIX_MASK_; + phy_write(phydev, LAN88XX_EXT_MODE_CTRL, + buf | LAN88XX_EXT_MODE_CTRL_MDI_); + phy_write(phydev, LAN88XX_EXT_PAGE_ACCESS, + LAN88XX_EXT_PAGE_SPACE_0); + } else if (mdix_ctrl == ETH_TP_MDI_X) { + phy_write(phydev, LAN88XX_EXT_PAGE_ACCESS, + LAN88XX_EXT_PAGE_SPACE_1); + buf = phy_read(phydev, LAN88XX_EXT_MODE_CTRL); + buf &= ~LAN88XX_EXT_MODE_CTRL_MDIX_MASK_; + phy_write(phydev, LAN88XX_EXT_MODE_CTRL, + buf | LAN88XX_EXT_MODE_CTRL_MDI_X_); + phy_write(phydev, LAN88XX_EXT_PAGE_ACCESS, + LAN88XX_EXT_PAGE_SPACE_0); + } else if (mdix_ctrl == ETH_TP_MDI_AUTO) { + phy_write(phydev, LAN88XX_EXT_PAGE_ACCESS, + LAN88XX_EXT_PAGE_SPACE_1); + buf = phy_read(phydev, LAN88XX_EXT_MODE_CTRL); + buf &= ~LAN88XX_EXT_MODE_CTRL_MDIX_MASK_; + phy_write(phydev, LAN88XX_EXT_MODE_CTRL, + buf | LAN88XX_EXT_MODE_CTRL_AUTO_MDIX_); + phy_write(phydev, LAN88XX_EXT_PAGE_ACCESS, + LAN88XX_EXT_PAGE_SPACE_0); + } + dev->mdix_ctrl = mdix_ctrl; +} + static int lan78xx_get_settings(struct net_device *net, struct ethtool_cmd *cmd) { struct lan78xx_net *dev = netdev_priv(net); - struct mii_if_info *mii = &dev->mii; + struct phy_device *phydev = net->phydev; int ret; int buf; - if ((!dev->mii.mdio_read) || (!dev->mii.mdio_write)) - return -EOPNOTSUPP; - ret = usb_autopm_get_interface(dev->intf); if (ret < 0) return ret; - ret = mii_ethtool_gset(&dev->mii, cmd); + ret = phy_ethtool_gset(phydev, cmd); - mii->mdio_write(mii->dev, mii->phy_id, - PHY_EXT_GPIO_PAGE, PHY_EXT_GPIO_PAGE_SPACE_1); - buf = mii->mdio_read(mii->dev, mii->phy_id, PHY_EXT_MODE_CTRL); - mii->mdio_write(mii->dev, mii->phy_id, - PHY_EXT_GPIO_PAGE, PHY_EXT_GPIO_PAGE_SPACE_0); + buf = lan78xx_get_mdix_status(net); - buf &= PHY_EXT_MODE_CTRL_MDIX_MASK_; - if (buf == PHY_EXT_MODE_CTRL_AUTO_MDIX_) { + buf &= LAN88XX_EXT_MODE_CTRL_MDIX_MASK_; + if (buf == LAN88XX_EXT_MODE_CTRL_AUTO_MDIX_) { cmd->eth_tp_mdix = ETH_TP_MDI_AUTO; cmd->eth_tp_mdix_ctrl = ETH_TP_MDI_AUTO; - } else if (buf == PHY_EXT_MODE_CTRL_MDI_) { + } else if (buf == LAN88XX_EXT_MODE_CTRL_MDI_) { cmd->eth_tp_mdix = ETH_TP_MDI; cmd->eth_tp_mdix_ctrl = ETH_TP_MDI; - } else if (buf == PHY_EXT_MODE_CTRL_MDI_X_) { + } else if (buf == LAN88XX_EXT_MODE_CTRL_MDI_X_) { cmd->eth_tp_mdix = ETH_TP_MDI_X; cmd->eth_tp_mdix_ctrl = ETH_TP_MDI_X; } @@ -1444,70 +1259,27 @@ static int lan78xx_get_settings(struct net_device *net, struct ethtool_cmd *cmd) static int lan78xx_set_settings(struct net_device *net, struct ethtool_cmd *cmd) { struct lan78xx_net *dev = netdev_priv(net); - struct mii_if_info *mii = &dev->mii; + struct phy_device *phydev = net->phydev; int ret = 0; int temp; - if ((!dev->mii.mdio_read) || (!dev->mii.mdio_write)) - return -EOPNOTSUPP; - ret = usb_autopm_get_interface(dev->intf); if (ret < 0) return ret; if (dev->mdix_ctrl != cmd->eth_tp_mdix_ctrl) { - if (cmd->eth_tp_mdix_ctrl == ETH_TP_MDI) { - mii->mdio_write(mii->dev, mii->phy_id, - PHY_EXT_GPIO_PAGE, - PHY_EXT_GPIO_PAGE_SPACE_1); - temp = mii->mdio_read(mii->dev, mii->phy_id, - PHY_EXT_MODE_CTRL); - temp &= ~PHY_EXT_MODE_CTRL_MDIX_MASK_; - mii->mdio_write(mii->dev, mii->phy_id, - PHY_EXT_MODE_CTRL, - temp | PHY_EXT_MODE_CTRL_MDI_); - mii->mdio_write(mii->dev, mii->phy_id, - PHY_EXT_GPIO_PAGE, - PHY_EXT_GPIO_PAGE_SPACE_0); - } else if (cmd->eth_tp_mdix_ctrl == ETH_TP_MDI_X) { - mii->mdio_write(mii->dev, mii->phy_id, - PHY_EXT_GPIO_PAGE, - PHY_EXT_GPIO_PAGE_SPACE_1); - temp = mii->mdio_read(mii->dev, mii->phy_id, - PHY_EXT_MODE_CTRL); - temp &= ~PHY_EXT_MODE_CTRL_MDIX_MASK_; - mii->mdio_write(mii->dev, mii->phy_id, - PHY_EXT_MODE_CTRL, - temp | PHY_EXT_MODE_CTRL_MDI_X_); - mii->mdio_write(mii->dev, mii->phy_id, - PHY_EXT_GPIO_PAGE, - PHY_EXT_GPIO_PAGE_SPACE_0); - } else if (cmd->eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO) { - mii->mdio_write(mii->dev, mii->phy_id, - PHY_EXT_GPIO_PAGE, - PHY_EXT_GPIO_PAGE_SPACE_1); - temp = mii->mdio_read(mii->dev, mii->phy_id, - PHY_EXT_MODE_CTRL); - temp &= ~PHY_EXT_MODE_CTRL_MDIX_MASK_; - mii->mdio_write(mii->dev, mii->phy_id, - PHY_EXT_MODE_CTRL, - temp | PHY_EXT_MODE_CTRL_AUTO_MDIX_); - mii->mdio_write(mii->dev, mii->phy_id, - PHY_EXT_GPIO_PAGE, - PHY_EXT_GPIO_PAGE_SPACE_0); - } + lan78xx_set_mdix_status(net, cmd->eth_tp_mdix_ctrl); } /* change speed & duplex */ - ret = mii_ethtool_sset(&dev->mii, cmd); + ret = phy_ethtool_sset(phydev, cmd); if (!cmd->autoneg) { /* force link down */ - temp = mii->mdio_read(mii->dev, mii->phy_id, MII_BMCR); - mii->mdio_write(mii->dev, mii->phy_id, MII_BMCR, - temp | BMCR_LOOPBACK); + temp = phy_read(phydev, MII_BMCR); + phy_write(phydev, MII_BMCR, temp | BMCR_LOOPBACK); mdelay(1); - mii->mdio_write(mii->dev, mii->phy_id, MII_BMCR, temp); + phy_write(phydev, MII_BMCR, temp); } usb_autopm_put_interface(dev->intf); @@ -1537,12 +1309,10 @@ static const struct ethtool_ops lan78xx_ethtool_ops = { static int lan78xx_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) { - struct lan78xx_net *dev = netdev_priv(netdev); - if (!netif_running(netdev)) return -EINVAL; - return generic_mii_ioctl(&dev->mii, if_mii(rq), cmd, NULL); + return phy_mii_ioctl(netdev->phydev, rq, cmd); } static void lan78xx_init_mac_address(struct lan78xx_net *dev) @@ -1598,53 +1368,183 @@ static void lan78xx_init_mac_address(struct lan78xx_net *dev) ether_addr_copy(dev->net->dev_addr, addr); } -static void lan78xx_mii_init(struct lan78xx_net *dev) +/* MDIO read and write wrappers for phylib */ +static int lan78xx_mdiobus_read(struct mii_bus *bus, int phy_id, int idx) { - /* Initialize MII structure */ - dev->mii.dev = dev->net; - dev->mii.mdio_read = lan78xx_mdio_read; - dev->mii.mdio_write = lan78xx_mdio_write; - dev->mii.phy_id_mask = 0x1f; - dev->mii.reg_num_mask = 0x1f; - dev->mii.phy_id = INTERNAL_PHY_ID; - dev->mii.supports_gmii = true; + struct lan78xx_net *dev = bus->priv; + u32 val, addr; + int ret; + + ret = usb_autopm_get_interface(dev->intf); + if (ret < 0) + return ret; + + mutex_lock(&dev->phy_mutex); + + /* confirm MII not busy */ + ret = lan78xx_phy_wait_not_busy(dev); + if (ret < 0) + goto done; + + /* set the address, index & direction (read from PHY) */ + addr = mii_access(phy_id, idx, MII_READ); + ret = lan78xx_write_reg(dev, MII_ACC, addr); + + ret = lan78xx_phy_wait_not_busy(dev); + if (ret < 0) + goto done; + + ret = lan78xx_read_reg(dev, MII_DATA, &val); + + ret = (int)(val & 0xFFFF); + +done: + mutex_unlock(&dev->phy_mutex); + usb_autopm_put_interface(dev->intf); + return ret; +} + +static int lan78xx_mdiobus_write(struct mii_bus *bus, int phy_id, int idx, + u16 regval) +{ + struct lan78xx_net *dev = bus->priv; + u32 val, addr; + int ret; + + ret = usb_autopm_get_interface(dev->intf); + if (ret < 0) + return ret; + + mutex_lock(&dev->phy_mutex); + + /* confirm MII not busy */ + ret = lan78xx_phy_wait_not_busy(dev); + if (ret < 0) + goto done; + + val = (u32)regval; + ret = lan78xx_write_reg(dev, MII_DATA, val); + + /* set the address, index & direction (write to PHY) */ + addr = mii_access(phy_id, idx, MII_WRITE); + ret = lan78xx_write_reg(dev, MII_ACC, addr); + + ret = lan78xx_phy_wait_not_busy(dev); + if (ret < 0) + goto done; + +done: + mutex_unlock(&dev->phy_mutex); + usb_autopm_put_interface(dev->intf); + return 0; +} + +static int lan78xx_mdio_init(struct lan78xx_net *dev) +{ + int ret; + int i; + + dev->mdiobus = mdiobus_alloc(); + if (!dev->mdiobus) { + netdev_err(dev->net, "can't allocate MDIO bus\n"); + return -ENOMEM; + } + + dev->mdiobus->priv = (void *)dev; + dev->mdiobus->read = lan78xx_mdiobus_read; + dev->mdiobus->write = lan78xx_mdiobus_write; + dev->mdiobus->name = "lan78xx-mdiobus"; + + snprintf(dev->mdiobus->id, MII_BUS_ID_SIZE, "usb-%03d:%03d", + dev->udev->bus->busnum, dev->udev->devnum); + + dev->mdiobus->irq = kzalloc(sizeof(int) * PHY_MAX_ADDR, GFP_KERNEL); + if (!dev->mdiobus->irq) { + ret = -ENOMEM; + goto exit1; + } + + /* handle our own interrupt */ + for (i = 0; i < PHY_MAX_ADDR; i++) + dev->mdiobus->irq[i] = PHY_IGNORE_INTERRUPT; + + switch (dev->devid & ID_REV_CHIP_ID_MASK_) { + case 0x78000000: + case 0x78500000: + /* set to internal PHY id */ + dev->mdiobus->phy_mask = ~(1 << 1); + break; + } + + ret = mdiobus_register(dev->mdiobus); + if (ret) { + netdev_err(dev->net, "can't register MDIO bus\n"); + goto exit2; + } + + netdev_dbg(dev->net, "registered mdiobus bus %s\n", dev->mdiobus->id); + return 0; +exit2: + kfree(dev->mdiobus->irq); +exit1: + mdiobus_free(dev->mdiobus); + return ret; +} + +static void lan78xx_remove_mdio(struct lan78xx_net *dev) +{ + mdiobus_unregister(dev->mdiobus); + kfree(dev->mdiobus->irq); + mdiobus_free(dev->mdiobus); +} + +static void lan78xx_link_status_change(struct net_device *net) +{ + /* nothing to do */ } static int lan78xx_phy_init(struct lan78xx_net *dev) { - int temp; - struct mii_if_info *mii = &dev->mii; + int ret; + struct phy_device *phydev = dev->net->phydev; - if ((!mii->mdio_write) || (!mii->mdio_read)) - return -EOPNOTSUPP; + phydev = phy_find_first(dev->mdiobus); + if (!phydev) { + netdev_err(dev->net, "no PHY found\n"); + return -EIO; + } - temp = mii->mdio_read(mii->dev, mii->phy_id, MII_ADVERTISE); - temp |= ADVERTISE_ALL; - mii->mdio_write(mii->dev, mii->phy_id, MII_ADVERTISE, - temp | ADVERTISE_CSMA | - ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM); + ret = phy_connect_direct(dev->net, phydev, + lan78xx_link_status_change, + PHY_INTERFACE_MODE_GMII); + if (ret) { + netdev_err(dev->net, "can't attach PHY to %s\n", + dev->mdiobus->id); + return -EIO; + } /* set to AUTOMDIX */ - mii->mdio_write(mii->dev, mii->phy_id, - PHY_EXT_GPIO_PAGE, PHY_EXT_GPIO_PAGE_SPACE_1); - temp = mii->mdio_read(mii->dev, mii->phy_id, PHY_EXT_MODE_CTRL); - temp &= ~PHY_EXT_MODE_CTRL_MDIX_MASK_; - mii->mdio_write(mii->dev, mii->phy_id, PHY_EXT_MODE_CTRL, - temp | PHY_EXT_MODE_CTRL_AUTO_MDIX_); - mii->mdio_write(mii->dev, mii->phy_id, - PHY_EXT_GPIO_PAGE, PHY_EXT_GPIO_PAGE_SPACE_0); - dev->mdix_ctrl = ETH_TP_MDI_AUTO; - - /* MAC doesn't support 1000HD */ - temp = mii->mdio_read(mii->dev, mii->phy_id, MII_CTRL1000); - mii->mdio_write(mii->dev, mii->phy_id, MII_CTRL1000, - temp & ~ADVERTISE_1000HALF); - - /* clear interrupt */ - mii->mdio_read(mii->dev, mii->phy_id, PHY_VTSE_INT_STS); - mii->mdio_write(mii->dev, mii->phy_id, PHY_VTSE_INT_MASK, - PHY_VTSE_INT_MASK_MDINTPIN_EN_ | - PHY_VTSE_INT_MASK_LINK_CHANGE_); + lan78xx_set_mdix_status(dev->net, ETH_TP_MDI_AUTO); + + /* MAC doesn't support 1000T Half */ + phydev->supported &= ~SUPPORTED_1000baseT_Half; + phydev->supported |= (SUPPORTED_10baseT_Half | + SUPPORTED_10baseT_Full | + SUPPORTED_100baseT_Half | + SUPPORTED_100baseT_Full | + SUPPORTED_1000baseT_Full | + SUPPORTED_Pause | SUPPORTED_Asym_Pause); + genphy_config_aneg(phydev); + + /* Workaround to enable PHY interrupt. + * phy_start_interrupts() is API for requesting and enabling + * PHY interrupt. However, USB-to-Ethernet device can't use + * request_irq() called in phy_start_interrupts(). + * Set PHY to PHY_HALTED and call phy_start() + * to make a call to phy_enable_interrupts() + */ + phy_stop(phydev); + phy_start(phydev); netif_dbg(dev, ifup, dev->net, "phy initialised successfully"); @@ -1930,6 +1830,10 @@ static int lan78xx_reset(struct lan78xx_net *dev) lan78xx_init_mac_address(dev); + /* save DEVID for later usage */ + ret = lan78xx_read_reg(dev, ID_REV, &buf); + dev->devid = buf; + /* Respond to the IN token with a NAK */ ret = lan78xx_read_reg(dev, USB_CFG0, &buf); buf |= USB_CFG_BIR_; @@ -2002,23 +1906,12 @@ static int lan78xx_reset(struct lan78xx_net *dev) netdev_warn(dev->net, "timeout waiting for PHY Reset"); return -EIO; } - } while (buf & PMT_CTL_PHY_RST_); - - lan78xx_mii_init(dev); - - ret = lan78xx_phy_init(dev); + } while ((buf & PMT_CTL_PHY_RST_) || !(buf & PMT_CTL_READY_)); ret = lan78xx_read_reg(dev, MAC_CR, &buf); - - buf |= MAC_CR_GMII_EN_; buf |= MAC_CR_AUTO_DUPLEX_ | MAC_CR_AUTO_SPEED_; - ret = lan78xx_write_reg(dev, MAC_CR, buf); - /* enable on PHY */ - if (buf & MAC_CR_EEE_EN_) - lan78xx_mmd_write(dev->net, dev->mii.phy_id, 0x07, 0x3C, 0x06); - /* enable PHY interrupts */ ret = lan78xx_read_reg(dev, INT_EP_CTL, &buf); buf |= INT_ENP_PHY_INT; @@ -2042,9 +1935,6 @@ static int lan78xx_reset(struct lan78xx_net *dev) buf |= FCT_RX_CTL_EN_; ret = lan78xx_write_reg(dev, FCT_RX_CTL, buf); - if (!mii_nway_restart(&dev->mii)) - netif_dbg(dev, link, dev->net, "autoneg initiated"); - return 0; } @@ -2061,6 +1951,10 @@ static int lan78xx_open(struct net_device *net) if (ret < 0) goto done; + ret = lan78xx_phy_init(dev); + if (ret < 0) + goto done; + /* for Link Check */ if (dev->urb_intr) { ret = usb_submit_urb(dev->urb_intr, GFP_KERNEL); @@ -2115,6 +2009,10 @@ int lan78xx_stop(struct net_device *net) { struct lan78xx_net *dev = netdev_priv(net); + phy_stop(net->phydev); + phy_disconnect(net->phydev); + net->phydev = NULL; + clear_bit(EVENT_DEV_OPEN, &dev->flags); netif_stop_queue(net); @@ -2395,6 +2293,8 @@ static int lan78xx_bind(struct lan78xx_net *dev, struct usb_interface *intf) /* Init all registers */ ret = lan78xx_reset(dev); + lan78xx_mdio_init(dev); + dev->net->flags |= IFF_MULTICAST; pdata->wol = WAKE_MAGIC; @@ -2406,6 +2306,8 @@ static void lan78xx_unbind(struct lan78xx_net *dev, struct usb_interface *intf) { struct lan78xx_priv *pdata = (struct lan78xx_priv *)(dev->data[0]); + lan78xx_remove_mdio(dev); + if (pdata) { netif_dbg(dev, ifdown, dev->net, "free pdata"); kfree(pdata); @@ -2522,11 +2424,6 @@ static int lan78xx_rx(struct lan78xx_net *dev, struct sk_buff *skb) skb_pull(skb, align_count); } - if (unlikely(skb->len < 0)) { - netdev_warn(dev->net, "invalid rx length<0 %d", skb->len); - return 0; - } - return 1; } @@ -3307,7 +3204,6 @@ int lan78xx_suspend(struct usb_interface *intf, pm_message_t message) int ret; int event; - ret = 0; event = message.event; if (!dev->suspend_count++) { @@ -3389,6 +3285,7 @@ int lan78xx_suspend(struct usb_interface *intf, pm_message_t message) } } + ret = 0; out: return ret; } @@ -3459,6 +3356,9 @@ int lan78xx_reset_resume(struct usb_interface *intf) struct lan78xx_net *dev = usb_get_intfdata(intf); lan78xx_reset(dev); + + lan78xx_phy_init(dev); + return lan78xx_resume(intf); } diff --git a/drivers/net/usb/lan78xx.h b/drivers/net/usb/lan78xx.h index ae7562ee72ad..a93fb653e7c5 100644 --- a/drivers/net/usb/lan78xx.h +++ b/drivers/net/usb/lan78xx.h @@ -549,7 +549,6 @@ #define LTM_INACTIVE1_TIMER10_ (0x0000FFFF) #define MAC_CR (0x100) -#define MAC_CR_GMII_EN_ (0x00080000) #define MAC_CR_EEE_TX_CLK_STOP_EN_ (0x00040000) #define MAC_CR_EEE_EN_ (0x00020000) #define MAC_CR_EEE_TLAR_EN_ (0x00010000) @@ -874,196 +873,4 @@ #define OTP_TPVSR_VAL (OTP_BASE_ADDR + 4 * 0x3A) #define OTP_TPVHR_VAL (OTP_BASE_ADDR + 4 * 0x3B) #define OTP_TPVSA_VAL (OTP_BASE_ADDR + 4 * 0x3C) - -#define PHY_ID1 (0x02) -#define PHY_ID2 (0x03) - -#define PHY_DEV_ID_OUI_VTSE (0x04001C) -#define PHY_DEV_ID_MODEL_VTSE_8502 (0x23) - -#define PHY_AUTONEG_ADV (0x04) -#define NWAY_AR_NEXT_PAGE_ (0x8000) -#define NWAY_AR_REMOTE_FAULT_ (0x2000) -#define NWAY_AR_ASM_DIR_ (0x0800) -#define NWAY_AR_PAUSE_ (0x0400) -#define NWAY_AR_100T4_CAPS_ (0x0200) -#define NWAY_AR_100TX_FD_CAPS_ (0x0100) -#define NWAY_AR_SELECTOR_FIELD_ (0x001F) -#define NWAY_AR_100TX_HD_CAPS_ (0x0080) -#define NWAY_AR_10T_FD_CAPS_ (0x0040) -#define NWAY_AR_10T_HD_CAPS_ (0x0020) -#define NWAY_AR_ALL_CAPS_ (NWAY_AR_10T_HD_CAPS_ | \ - NWAY_AR_10T_FD_CAPS_ | \ - NWAY_AR_100TX_HD_CAPS_ | \ - NWAY_AR_100TX_FD_CAPS_) -#define NWAY_AR_PAUSE_MASK (NWAY_AR_PAUSE_ | NWAY_AR_ASM_DIR_) - -#define PHY_LP_ABILITY (0x05) -#define NWAY_LPAR_NEXT_PAGE_ (0x8000) -#define NWAY_LPAR_ACKNOWLEDGE_ (0x4000) -#define NWAY_LPAR_REMOTE_FAULT_ (0x2000) -#define NWAY_LPAR_ASM_DIR_ (0x0800) -#define NWAY_LPAR_PAUSE_ (0x0400) -#define NWAY_LPAR_100T4_CAPS_ (0x0200) -#define NWAY_LPAR_100TX_FD_CAPS_ (0x0100) -#define NWAY_LPAR_100TX_HD_CAPS_ (0x0080) -#define NWAY_LPAR_10T_FD_CAPS_ (0x0040) -#define NWAY_LPAR_10T_HD_CAPS_ (0x0020) -#define NWAY_LPAR_SELECTOR_FIELD_ (0x001F) - -#define PHY_AUTONEG_EXP (0x06) -#define NWAY_ER_PAR_DETECT_FAULT_ (0x0010) -#define NWAY_ER_LP_NEXT_PAGE_CAPS_ (0x0008) -#define NWAY_ER_NEXT_PAGE_CAPS_ (0x0004) -#define NWAY_ER_PAGE_RXD_ (0x0002) -#define NWAY_ER_LP_NWAY_CAPS_ (0x0001) - -#define PHY_NEXT_PAGE_TX (0x07) -#define NPTX_NEXT_PAGE_ (0x8000) -#define NPTX_MSG_PAGE_ (0x2000) -#define NPTX_ACKNOWLDGE2_ (0x1000) -#define NPTX_TOGGLE_ (0x0800) -#define NPTX_MSG_CODE_FIELD_ (0x0001) - -#define PHY_LP_NEXT_PAGE (0x08) -#define LP_RNPR_NEXT_PAGE_ (0x8000) -#define LP_RNPR_ACKNOWLDGE_ (0x4000) -#define LP_RNPR_MSG_PAGE_ (0x2000) -#define LP_RNPR_ACKNOWLDGE2_ (0x1000) -#define LP_RNPR_TOGGLE_ (0x0800) -#define LP_RNPR_MSG_CODE_FIELD_ (0x0001) - -#define PHY_1000T_CTRL (0x09) -#define CR_1000T_TEST_MODE_4_ (0x8000) -#define CR_1000T_TEST_MODE_3_ (0x6000) -#define CR_1000T_TEST_MODE_2_ (0x4000) -#define CR_1000T_TEST_MODE_1_ (0x2000) -#define CR_1000T_MS_ENABLE_ (0x1000) -#define CR_1000T_MS_VALUE_ (0x0800) -#define CR_1000T_REPEATER_DTE_ (0x0400) -#define CR_1000T_FD_CAPS_ (0x0200) -#define CR_1000T_HD_CAPS_ (0x0100) -#define CR_1000T_ASYM_PAUSE_ (0x0080) -#define CR_1000T_TEST_MODE_NORMAL_ (0x0000) - -#define PHY_1000T_STATUS (0x0A) -#define SR_1000T_MS_CONFIG_FAULT_ (0x8000) -#define SR_1000T_MS_CONFIG_RES_ (0x4000) -#define SR_1000T_LOCAL_RX_STATUS_ (0x2000) -#define SR_1000T_REMOTE_RX_STATUS_ (0x1000) -#define SR_1000T_LP_FD_CAPS_ (0x0800) -#define SR_1000T_LP_HD_CAPS_ (0x0400) -#define SR_1000T_ASYM_PAUSE_DIR_ (0x0100) -#define SR_1000T_IDLE_ERROR_CNT_ (0x00FF) -#define SR_1000T_REMOTE_RX_STATUS_SHIFT 12 -#define SR_1000T_LOCAL_RX_STATUS_SHIFT 13 -#define SR_1000T_PHY_EXCESSIVE_IDLE_ERR_COUNT 5 -#define FFE_IDLE_ERR_COUNT_TIMEOUT_20 20 -#define FFE_IDLE_ERR_COUNT_TIMEOUT_100 100 - -#define PHY_EXT_STATUS (0x0F) -#define IEEE_ESR_1000X_FD_CAPS_ (0x8000) -#define IEEE_ESR_1000X_HD_CAPS_ (0x4000) -#define IEEE_ESR_1000T_FD_CAPS_ (0x2000) -#define IEEE_ESR_1000T_HD_CAPS_ (0x1000) -#define PHY_TX_POLARITY_MASK_ (0x0100) -#define PHY_TX_NORMAL_POLARITY_ (0x0000) -#define AUTO_POLARITY_DISABLE_ (0x0010) - -#define PHY_MMD_CTL (0x0D) -#define PHY_MMD_CTRL_OP_MASK_ (0xC000) -#define PHY_MMD_CTRL_OP_REG_ (0x0000) -#define PHY_MMD_CTRL_OP_DNI_ (0x4000) -#define PHY_MMD_CTRL_OP_DPIRW_ (0x8000) -#define PHY_MMD_CTRL_OP_DPIWO_ (0xC000) -#define PHY_MMD_CTRL_DEV_ADDR_MASK_ (0x001F) - -#define PHY_MMD_REG_DATA (0x0E) - -/* VTSE Vendor Specific registers */ -#define PHY_VTSE_BYPASS (0x12) -#define PHY_VTSE_BYPASS_DISABLE_PAIR_SWAP_ (0x0020) - -#define PHY_VTSE_INT_MASK (0x19) -#define PHY_VTSE_INT_MASK_MDINTPIN_EN_ (0x8000) -#define PHY_VTSE_INT_MASK_SPEED_CHANGE_ (0x4000) -#define PHY_VTSE_INT_MASK_LINK_CHANGE_ (0x2000) -#define PHY_VTSE_INT_MASK_FDX_CHANGE_ (0x1000) -#define PHY_VTSE_INT_MASK_AUTONEG_ERR_ (0x0800) -#define PHY_VTSE_INT_MASK_AUTONEG_DONE_ (0x0400) -#define PHY_VTSE_INT_MASK_POE_DETECT_ (0x0200) -#define PHY_VTSE_INT_MASK_SYMBOL_ERR_ (0x0100) -#define PHY_VTSE_INT_MASK_FAST_LINK_FAIL_ (0x0080) -#define PHY_VTSE_INT_MASK_WOL_EVENT_ (0x0040) -#define PHY_VTSE_INT_MASK_EXTENDED_INT_ (0x0020) -#define PHY_VTSE_INT_MASK_RESERVED_ (0x0010) -#define PHY_VTSE_INT_MASK_FALSE_CARRIER_ (0x0008) -#define PHY_VTSE_INT_MASK_LINK_SPEED_DS_ (0x0004) -#define PHY_VTSE_INT_MASK_MASTER_SLAVE_DONE_ (0x0002) -#define PHY_VTSE_INT_MASK_RX__ER_ (0x0001) - -#define PHY_VTSE_INT_STS (0x1A) -#define PHY_VTSE_INT_STS_INT_ACTIVE_ (0x8000) -#define PHY_VTSE_INT_STS_SPEED_CHANGE_ (0x4000) -#define PHY_VTSE_INT_STS_LINK_CHANGE_ (0x2000) -#define PHY_VTSE_INT_STS_FDX_CHANGE_ (0x1000) -#define PHY_VTSE_INT_STS_AUTONEG_ERR_ (0x0800) -#define PHY_VTSE_INT_STS_AUTONEG_DONE_ (0x0400) -#define PHY_VTSE_INT_STS_POE_DETECT_ (0x0200) -#define PHY_VTSE_INT_STS_SYMBOL_ERR_ (0x0100) -#define PHY_VTSE_INT_STS_FAST_LINK_FAIL_ (0x0080) -#define PHY_VTSE_INT_STS_WOL_EVENT_ (0x0040) -#define PHY_VTSE_INT_STS_EXTENDED_INT_ (0x0020) -#define PHY_VTSE_INT_STS_RESERVED_ (0x0010) -#define PHY_VTSE_INT_STS_FALSE_CARRIER_ (0x0008) -#define PHY_VTSE_INT_STS_LINK_SPEED_DS_ (0x0004) -#define PHY_VTSE_INT_STS_MASTER_SLAVE_DONE_ (0x0002) -#define PHY_VTSE_INT_STS_RX_ER_ (0x0001) - -/* VTSE PHY registers */ -#define PHY_EXT_GPIO_PAGE (0x1F) -#define PHY_EXT_GPIO_PAGE_SPACE_0 (0x0000) -#define PHY_EXT_GPIO_PAGE_SPACE_1 (0x0001) -#define PHY_EXT_GPIO_PAGE_SPACE_2 (0x0002) - -/* Extended Register Page 1 space */ -#define PHY_EXT_MODE_CTRL (0x13) -#define PHY_EXT_MODE_CTRL_MDIX_MASK_ (0x000C) -#define PHY_EXT_MODE_CTRL_AUTO_MDIX_ (0x0000) -#define PHY_EXT_MODE_CTRL_MDI_ (0x0008) -#define PHY_EXT_MODE_CTRL_MDI_X_ (0x000C) - -#define PHY_ANA_10BASE_T_HD 0x01 -#define PHY_ANA_10BASE_T_FD 0x02 -#define PHY_ANA_100BASE_TX_HD 0x04 -#define PHY_ANA_100BASE_TX_FD 0x08 -#define PHY_ANA_1000BASE_T_FD 0x10 -#define PHY_ANA_ALL_SUPPORTED_MEDIA (PHY_ANA_10BASE_T_HD | \ - PHY_ANA_10BASE_T_FD | \ - PHY_ANA_100BASE_TX_HD | \ - PHY_ANA_100BASE_TX_FD | \ - PHY_ANA_1000BASE_T_FD) -/* PHY MMD registers */ -#define PHY_MMD_DEV_3 3 - -#define PHY_EEE_PCS_STATUS (0x1) -#define PHY_EEE_PCS_STATUS_TX_LPI_RCVD_ ((WORD)0x0800) -#define PHY_EEE_PCS_STATUS_RX_LPI_RCVD_ ((WORD)0x0400) -#define PHY_EEE_PCS_STATUS_TX_LPI_IND_ ((WORD)0x0200) -#define PHY_EEE_PCS_STATUS_RX_LPI_IND_ ((WORD)0x0100) -#define PHY_EEE_PCS_STATUS_PCS_RCV_LNK_STS_ ((WORD)0x0004) - -#define PHY_EEE_CAPABILITIES (0x14) -#define PHY_EEE_CAPABILITIES_1000BT_EEE_ ((WORD)0x0004) -#define PHY_EEE_CAPABILITIES_100BT_EEE_ ((WORD)0x0002) - -#define PHY_MMD_DEV_7 7 - -#define PHY_EEE_ADVERTISEMENT (0x3C) -#define PHY_EEE_ADVERTISEMENT_1000BT_EEE_ ((WORD)0x0004) -#define PHY_EEE_ADVERTISEMENT_100BT_EEE_ ((WORD)0x0002) - -#define PHY_EEE_LP_ADVERTISEMENT (0x3D) -#define PHY_EEE_1000BT_EEE_CAPABLE_ ((WORD)0x0004) -#define PHY_EEE_100BT_EEE_CAPABLE_ ((WORD)0x0002) #endif /* _LAN78XX_H */ diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 355842b85ee9..4752e69de00e 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -229,11 +229,11 @@ static int qmi_wwan_bind(struct usbnet *dev, struct usb_interface *intf) u8 *buf = intf->cur_altsetting->extra; int len = intf->cur_altsetting->extralen; struct usb_interface_descriptor *desc = &intf->cur_altsetting->desc; - struct usb_cdc_union_desc *cdc_union = NULL; - struct usb_cdc_ether_desc *cdc_ether = NULL; - u32 found = 0; + struct usb_cdc_union_desc *cdc_union; + struct usb_cdc_ether_desc *cdc_ether; struct usb_driver *driver = driver_of(intf); struct qmi_wwan_state *info = (void *)&dev->data; + struct usb_cdc_parsed_header hdr; BUILD_BUG_ON((sizeof(((struct usbnet *)0)->data) < sizeof(struct qmi_wwan_state))); @@ -243,63 +243,9 @@ static int qmi_wwan_bind(struct usbnet *dev, struct usb_interface *intf) info->data = intf; /* and a number of CDC descriptors */ - while (len > 3) { - struct usb_descriptor_header *h = (void *)buf; - - /* ignore any misplaced descriptors */ - if (h->bDescriptorType != USB_DT_CS_INTERFACE) - goto next_desc; - - /* buf[2] is CDC descriptor subtype */ - switch (buf[2]) { - case USB_CDC_HEADER_TYPE: - if (found & 1 << USB_CDC_HEADER_TYPE) { - dev_dbg(&intf->dev, "extra CDC header\n"); - goto err; - } - if (h->bLength != sizeof(struct usb_cdc_header_desc)) { - dev_dbg(&intf->dev, "CDC header len %u\n", - h->bLength); - goto err; - } - break; - case USB_CDC_UNION_TYPE: - if (found & 1 << USB_CDC_UNION_TYPE) { - dev_dbg(&intf->dev, "extra CDC union\n"); - goto err; - } - if (h->bLength != sizeof(struct usb_cdc_union_desc)) { - dev_dbg(&intf->dev, "CDC union len %u\n", - h->bLength); - goto err; - } - cdc_union = (struct usb_cdc_union_desc *)buf; - break; - case USB_CDC_ETHERNET_TYPE: - if (found & 1 << USB_CDC_ETHERNET_TYPE) { - dev_dbg(&intf->dev, "extra CDC ether\n"); - goto err; - } - if (h->bLength != sizeof(struct usb_cdc_ether_desc)) { - dev_dbg(&intf->dev, "CDC ether len %u\n", - h->bLength); - goto err; - } - cdc_ether = (struct usb_cdc_ether_desc *)buf; - break; - } - - /* Remember which CDC functional descriptors we've seen. Works - * for all types we care about, of which USB_CDC_ETHERNET_TYPE - * (0x0f) is the highest numbered - */ - if (buf[2] < 32) - found |= 1 << buf[2]; - -next_desc: - len -= h->bLength; - buf += h->bLength; - } + cdc_parse_cdc_header(&hdr, intf, buf, len); + cdc_union = hdr.usb_cdc_union_desc; + cdc_ether = hdr.usb_cdc_ether_desc; /* Use separate control and data interfaces if we found a CDC Union */ if (cdc_union) { diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c index d9e7892262fa..30033dbe6662 100644 --- a/drivers/net/usb/smsc75xx.c +++ b/drivers/net/usb/smsc75xx.c @@ -2185,11 +2185,6 @@ static int smsc75xx_rx_fixup(struct usbnet *dev, struct sk_buff *skb) skb_pull(skb, align_count); } - if (unlikely(skb->len < 0)) { - netdev_warn(dev->net, "invalid rx length<0 %d\n", skb->len); - return 0; - } - return 1; } diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 26423adc35ee..66b3ab9f614e 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -1815,11 +1815,6 @@ static int smsc95xx_rx_fixup(struct usbnet *dev, struct sk_buff *skb) skb_pull(skb, align_count); } - if (unlikely(skb->len < 0)) { - netdev_warn(dev->net, "invalid rx length<0 %d\n", skb->len); - return 0; - } - return 1; } diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index b4cf10781348..060918f49fea 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -42,6 +42,7 @@ #include <linux/mii.h> #include <linux/usb.h> #include <linux/usb/usbnet.h> +#include <linux/usb/cdc.h> #include <linux/slab.h> #include <linux/kernel.h> #include <linux/pm_runtime.h> @@ -1962,6 +1963,143 @@ out: return err; } +int cdc_parse_cdc_header(struct usb_cdc_parsed_header *hdr, + struct usb_interface *intf, + u8 *buffer, + int buflen) +{ + /* duplicates are ignored */ + struct usb_cdc_union_desc *union_header = NULL; + + /* duplicates are not tolerated */ + struct usb_cdc_header_desc *header = NULL; + struct usb_cdc_ether_desc *ether = NULL; + struct usb_cdc_mdlm_detail_desc *detail = NULL; + struct usb_cdc_mdlm_desc *desc = NULL; + + unsigned int elength; + int cnt = 0; + + memset(hdr, 0x00, sizeof(struct usb_cdc_parsed_header)); + hdr->phonet_magic_present = false; + while (buflen > 0) { + elength = buffer[0]; + if (!elength) { + dev_err(&intf->dev, "skipping garbage byte\n"); + elength = 1; + goto next_desc; + } + if (buffer[1] != USB_DT_CS_INTERFACE) { + dev_err(&intf->dev, "skipping garbage\n"); + goto next_desc; + } + + switch (buffer[2]) { + case USB_CDC_UNION_TYPE: /* we've found it */ + if (elength < sizeof(struct usb_cdc_union_desc)) + goto next_desc; + if (union_header) { + dev_err(&intf->dev, "More than one union descriptor, skipping ...\n"); + goto next_desc; + } + union_header = (struct usb_cdc_union_desc *)buffer; + break; + case USB_CDC_COUNTRY_TYPE: + if (elength < sizeof(struct usb_cdc_country_functional_desc)) + goto next_desc; + hdr->usb_cdc_country_functional_desc = + (struct usb_cdc_country_functional_desc *)buffer; + break; + case USB_CDC_HEADER_TYPE: + if (elength != sizeof(struct usb_cdc_header_desc)) + goto next_desc; + if (header) + return -EINVAL; + header = (struct usb_cdc_header_desc *)buffer; + break; + case USB_CDC_ACM_TYPE: + if (elength < sizeof(struct usb_cdc_acm_descriptor)) + goto next_desc; + hdr->usb_cdc_acm_descriptor = + (struct usb_cdc_acm_descriptor *)buffer; + break; + case USB_CDC_ETHERNET_TYPE: + if (elength != sizeof(struct usb_cdc_ether_desc)) + goto next_desc; + if (ether) + return -EINVAL; + ether = (struct usb_cdc_ether_desc *)buffer; + break; + case USB_CDC_CALL_MANAGEMENT_TYPE: + if (elength < sizeof(struct usb_cdc_call_mgmt_descriptor)) + goto next_desc; + hdr->usb_cdc_call_mgmt_descriptor = + (struct usb_cdc_call_mgmt_descriptor *)buffer; + break; + case USB_CDC_DMM_TYPE: + if (elength < sizeof(struct usb_cdc_dmm_desc)) + goto next_desc; + hdr->usb_cdc_dmm_desc = + (struct usb_cdc_dmm_desc *)buffer; + break; + case USB_CDC_MDLM_TYPE: + if (elength < sizeof(struct usb_cdc_mdlm_desc *)) + goto next_desc; + if (desc) + return -EINVAL; + desc = (struct usb_cdc_mdlm_desc *)buffer; + break; + case USB_CDC_MDLM_DETAIL_TYPE: + if (elength < sizeof(struct usb_cdc_mdlm_detail_desc *)) + goto next_desc; + if (detail) + return -EINVAL; + detail = (struct usb_cdc_mdlm_detail_desc *)buffer; + break; + case USB_CDC_NCM_TYPE: + if (elength < sizeof(struct usb_cdc_ncm_desc)) + goto next_desc; + hdr->usb_cdc_ncm_desc = (struct usb_cdc_ncm_desc *)buffer; + break; + case USB_CDC_MBIM_TYPE: + if (elength < sizeof(struct usb_cdc_mbim_desc)) + goto next_desc; + + hdr->usb_cdc_mbim_desc = (struct usb_cdc_mbim_desc *)buffer; + break; + case USB_CDC_MBIM_EXTENDED_TYPE: + if (elength < sizeof(struct usb_cdc_mbim_extended_desc)) + break; + hdr->usb_cdc_mbim_extended_desc = + (struct usb_cdc_mbim_extended_desc *)buffer; + break; + case CDC_PHONET_MAGIC_NUMBER: + hdr->phonet_magic_present = true; + break; + default: + /* + * there are LOTS more CDC descriptors that + * could legitimately be found here. + */ + dev_dbg(&intf->dev, "Ignoring descriptor: type %02x, length %ud\n", + buffer[2], elength); + goto next_desc; + } + cnt++; +next_desc: + buflen -= elength; + buffer += elength; + } + hdr->usb_cdc_union_desc = union_header; + hdr->usb_cdc_header_desc = header; + hdr->usb_cdc_mdlm_detail_desc = detail; + hdr->usb_cdc_mdlm_desc = desc; + hdr->usb_cdc_ether_desc = ether; + return cnt; +} + +EXPORT_SYMBOL(cdc_parse_cdc_header); + /* * The function can't be called inside suspend/resume callback, * otherwise deadlock will be caused. diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c index c1d0e7a9da04..a681569ae0b5 100644 --- a/drivers/net/vmxnet3/vmxnet3_ethtool.c +++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c @@ -183,16 +183,22 @@ vmxnet3_get_sset_count(struct net_device *netdev, int sset) } -/* Should be multiple of 4 */ -#define NUM_TX_REGS 8 -#define NUM_RX_REGS 12 - +/* This is a version 2 of the vmxnet3 ethtool_regs which goes hand in hand with + * the version 2 of the vmxnet3 support for ethtool(8) --register-dump. + * Therefore, if any registers are added, removed or modified, then a version + * bump and a corresponding change in the vmxnet3 support for ethtool(8) + * --register-dump would be required. + */ static int vmxnet3_get_regs_len(struct net_device *netdev) { struct vmxnet3_adapter *adapter = netdev_priv(netdev); - return (adapter->num_tx_queues * NUM_TX_REGS * sizeof(u32) + - adapter->num_rx_queues * NUM_RX_REGS * sizeof(u32)); + + return ((9 /* BAR1 registers */ + + (1 + adapter->intr.num_intrs) + + (1 + adapter->num_tx_queues * 17 /* Tx queue registers */) + + (1 + adapter->num_rx_queues * 23 /* Rx queue registers */)) * + sizeof(u32)); } @@ -342,6 +348,12 @@ vmxnet3_get_ethtool_stats(struct net_device *netdev, } +/* This is a version 2 of the vmxnet3 ethtool_regs which goes hand in hand with + * the version 2 of the vmxnet3 support for ethtool(8) --register-dump. + * Therefore, if any registers are added, removed or modified, then a version + * bump and a corresponding change in the vmxnet3 support for ethtool(8) + * --register-dump would be required. + */ static void vmxnet3_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *p) { @@ -351,40 +363,90 @@ vmxnet3_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *p) memset(p, 0, vmxnet3_get_regs_len(netdev)); - regs->version = 1; + regs->version = 2; /* Update vmxnet3_get_regs_len if we want to dump more registers */ - /* make each ring use multiple of 16 bytes */ - for (i = 0; i < adapter->num_tx_queues; i++) { - buf[j++] = adapter->tx_queue[i].tx_ring.next2fill; - buf[j++] = adapter->tx_queue[i].tx_ring.next2comp; - buf[j++] = adapter->tx_queue[i].tx_ring.gen; - buf[j++] = 0; + buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_VRRS); + buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_UVRS); + buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_DSAL); + buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_DSAH); + buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD); + buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_MACL); + buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_MACH); + buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_ICR); + buf[j++] = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_ECR); + + buf[j++] = adapter->intr.num_intrs; + for (i = 0; i < adapter->intr.num_intrs; i++) { + buf[j++] = VMXNET3_READ_BAR0_REG(adapter, VMXNET3_REG_IMR + + i * VMXNET3_REG_ALIGN); + } - buf[j++] = adapter->tx_queue[i].comp_ring.next2proc; - buf[j++] = adapter->tx_queue[i].comp_ring.gen; - buf[j++] = adapter->tx_queue[i].stopped; - buf[j++] = 0; + buf[j++] = adapter->num_tx_queues; + for (i = 0; i < adapter->num_tx_queues; i++) { + struct vmxnet3_tx_queue *tq = &adapter->tx_queue[i]; + + buf[j++] = VMXNET3_READ_BAR0_REG(adapter, VMXNET3_REG_TXPROD + + i * VMXNET3_REG_ALIGN); + + buf[j++] = VMXNET3_GET_ADDR_LO(tq->tx_ring.basePA); + buf[j++] = VMXNET3_GET_ADDR_HI(tq->tx_ring.basePA); + buf[j++] = tq->tx_ring.size; + buf[j++] = tq->tx_ring.next2fill; + buf[j++] = tq->tx_ring.next2comp; + buf[j++] = tq->tx_ring.gen; + + buf[j++] = VMXNET3_GET_ADDR_LO(tq->data_ring.basePA); + buf[j++] = VMXNET3_GET_ADDR_HI(tq->data_ring.basePA); + buf[j++] = tq->data_ring.size; + /* transmit data ring buffer size */ + buf[j++] = VMXNET3_HDR_COPY_SIZE; + + buf[j++] = VMXNET3_GET_ADDR_LO(tq->comp_ring.basePA); + buf[j++] = VMXNET3_GET_ADDR_HI(tq->comp_ring.basePA); + buf[j++] = tq->comp_ring.size; + buf[j++] = tq->comp_ring.next2proc; + buf[j++] = tq->comp_ring.gen; + + buf[j++] = tq->stopped; } + buf[j++] = adapter->num_rx_queues; for (i = 0; i < adapter->num_rx_queues; i++) { - buf[j++] = adapter->rx_queue[i].rx_ring[0].next2fill; - buf[j++] = adapter->rx_queue[i].rx_ring[0].next2comp; - buf[j++] = adapter->rx_queue[i].rx_ring[0].gen; + struct vmxnet3_rx_queue *rq = &adapter->rx_queue[i]; + + buf[j++] = VMXNET3_READ_BAR0_REG(adapter, VMXNET3_REG_RXPROD + + i * VMXNET3_REG_ALIGN); + buf[j++] = VMXNET3_READ_BAR0_REG(adapter, VMXNET3_REG_RXPROD2 + + i * VMXNET3_REG_ALIGN); + + buf[j++] = VMXNET3_GET_ADDR_LO(rq->rx_ring[0].basePA); + buf[j++] = VMXNET3_GET_ADDR_HI(rq->rx_ring[0].basePA); + buf[j++] = rq->rx_ring[0].size; + buf[j++] = rq->rx_ring[0].next2fill; + buf[j++] = rq->rx_ring[0].next2comp; + buf[j++] = rq->rx_ring[0].gen; + + buf[j++] = VMXNET3_GET_ADDR_LO(rq->rx_ring[1].basePA); + buf[j++] = VMXNET3_GET_ADDR_HI(rq->rx_ring[1].basePA); + buf[j++] = rq->rx_ring[1].size; + buf[j++] = rq->rx_ring[1].next2fill; + buf[j++] = rq->rx_ring[1].next2comp; + buf[j++] = rq->rx_ring[1].gen; + + /* receive data ring */ buf[j++] = 0; - - buf[j++] = adapter->rx_queue[i].rx_ring[1].next2fill; - buf[j++] = adapter->rx_queue[i].rx_ring[1].next2comp; - buf[j++] = adapter->rx_queue[i].rx_ring[1].gen; buf[j++] = 0; - - buf[j++] = adapter->rx_queue[i].comp_ring.next2proc; - buf[j++] = adapter->rx_queue[i].comp_ring.gen; buf[j++] = 0; buf[j++] = 0; - } + buf[j++] = VMXNET3_GET_ADDR_LO(rq->comp_ring.basePA); + buf[j++] = VMXNET3_GET_ADDR_HI(rq->comp_ring.basePA); + buf[j++] = rq->comp_ring.size; + buf[j++] = rq->comp_ring.next2proc; + buf[j++] = rq->comp_ring.gen; + } } diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h index 2652245631d1..3f859a55c035 100644 --- a/drivers/net/vmxnet3/vmxnet3_int.h +++ b/drivers/net/vmxnet3/vmxnet3_int.h @@ -69,10 +69,10 @@ /* * Version numbers */ -#define VMXNET3_DRIVER_VERSION_STRING "1.4.2.0-k" +#define VMXNET3_DRIVER_VERSION_STRING "1.4.3.0-k" /* a 32-bit int, each byte encode a verion number in VMXNET3_DRIVER_VERSION */ -#define VMXNET3_DRIVER_VERSION_NUM 0x01040200 +#define VMXNET3_DRIVER_VERSION_NUM 0x01040300 #if defined(CONFIG_PCI_MSI) /* RSS only makes sense if MSI-X is supported. */ diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 488c6f50df73..64f2ab663ffe 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -34,7 +34,7 @@ #include <net/rtnetlink.h> #include <net/route.h> #include <net/addrconf.h> -#include <net/vrf.h> +#include <net/l3mdev.h> #define DRV_NAME "vrf" #define DRV_VERSION "1.0" @@ -44,6 +44,21 @@ #define vrf_master_get_rcu(dev) \ ((struct net_device *)rcu_dereference(dev->rx_handler_data)) +struct slave { + struct list_head list; + struct net_device *dev; +}; + +struct slave_queue { + struct list_head all_slaves; +}; + +struct net_vrf { + struct slave_queue queue; + struct rtable *rth; + u32 tb_id; +}; + struct pcpu_dstats { u64 tx_pkts; u64 tx_bytes; @@ -254,7 +269,7 @@ static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev) } /* modelled after ip_finish_output2 */ -static int vrf_finish_output(struct sock *sk, struct sk_buff *skb) +static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct rtable *rt = (struct rtable *)dst; @@ -299,14 +314,15 @@ err: static int vrf_output(struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb_dst(skb)->dev; + struct net *net = dev_net(dev); - IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUT, skb->len); + IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len); skb->dev = dev; skb->protocol = htons(ETH_P_IP); - return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, sk, skb, - NULL, dev, + return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, + net, sk, skb, NULL, dev, vrf_finish_output, !(IPCB(skb)->flags & IPSKB_REROUTED)); } @@ -321,6 +337,7 @@ static void vrf_rtable_destroy(struct net_vrf *vrf) static struct rtable *vrf_rtable_create(struct net_device *dev) { + struct net_vrf *vrf = netdev_priv(dev); struct rtable *rth; rth = dst_alloc(&vrf_dst_ops, dev, 2, @@ -336,6 +353,7 @@ static struct rtable *vrf_rtable_create(struct net_device *dev) rth->rt_pmtu = 0; rth->rt_gateway = 0; rth->rt_uses_gateway = 0; + rth->rt_table_id = vrf->tb_id; INIT_LIST_HEAD(&rth->rt_uncached); rth->rt_uncached_list = NULL; } @@ -392,18 +410,15 @@ static void __vrf_insert_slave(struct slave_queue *queue, struct slave *slave) static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev) { - struct net_vrf_dev *vrf_ptr = kmalloc(sizeof(*vrf_ptr), GFP_KERNEL); struct slave *slave = kzalloc(sizeof(*slave), GFP_KERNEL); struct net_vrf *vrf = netdev_priv(dev); struct slave_queue *queue = &vrf->queue; int ret = -ENOMEM; - if (!slave || !vrf_ptr) + if (!slave) goto out_fail; slave->dev = port_dev; - vrf_ptr->ifindex = dev->ifindex; - vrf_ptr->tb_id = vrf->tb_id; /* register the packet handler for slave ports */ ret = netdev_rx_handler_register(port_dev, vrf_handle_frame, dev); @@ -420,7 +435,6 @@ static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev) port_dev->flags |= IFF_SLAVE; __vrf_insert_slave(queue, slave); - rcu_assign_pointer(port_dev->vrf_ptr, vrf_ptr); cycle_netdev(port_dev); return 0; @@ -428,14 +442,13 @@ static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev) out_unregister: netdev_rx_handler_unregister(port_dev); out_fail: - kfree(vrf_ptr); kfree(slave); return ret; } static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev) { - if (netif_is_vrf(port_dev) || vrf_is_slave(port_dev)) + if (netif_is_l3_master(port_dev) || vrf_is_slave(port_dev)) return -EINVAL; return do_vrf_add_slave(dev, port_dev); @@ -444,21 +457,15 @@ static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev) /* inverse of do_vrf_add_slave */ static int do_vrf_del_slave(struct net_device *dev, struct net_device *port_dev) { - struct net_vrf_dev *vrf_ptr = rtnl_dereference(port_dev->vrf_ptr); struct net_vrf *vrf = netdev_priv(dev); struct slave_queue *queue = &vrf->queue; struct slave *slave; - RCU_INIT_POINTER(port_dev->vrf_ptr, NULL); - netdev_upper_dev_unlink(port_dev, dev); port_dev->flags &= ~IFF_SLAVE; netdev_rx_handler_unregister(port_dev); - /* after netdev_rx_handler_unregister for synchronize_rcu */ - kfree(vrf_ptr); - cycle_netdev(port_dev); slave = __vrf_find_slave_dev(queue, port_dev); @@ -526,6 +533,33 @@ static const struct net_device_ops vrf_netdev_ops = { .ndo_del_slave = vrf_del_slave, }; +static u32 vrf_fib_table(const struct net_device *dev) +{ + struct net_vrf *vrf = netdev_priv(dev); + + return vrf->tb_id; +} + +static struct rtable *vrf_get_rtable(const struct net_device *dev, + const struct flowi4 *fl4) +{ + struct rtable *rth = NULL; + + if (!(fl4->flowi4_flags & FLOWI_FLAG_VRFSRC)) { + struct net_vrf *vrf = netdev_priv(dev); + + rth = vrf->rth; + atomic_inc(&rth->dst.__refcnt); + } + + return rth; +} + +static const struct l3mdev_ops vrf_l3mdev_ops = { + .l3mdev_fib_table = vrf_fib_table, + .l3mdev_get_rtable = vrf_get_rtable, +}; + static void vrf_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { @@ -543,6 +577,7 @@ static void vrf_setup(struct net_device *dev) /* Initialize the device structure. */ dev->netdev_ops = &vrf_netdev_ops; + dev->l3mdev_ops = &vrf_l3mdev_ops; dev->ethtool_ops = &vrf_ethtool_ops; dev->destructor = free_netdev; @@ -569,10 +604,6 @@ static int vrf_validate(struct nlattr *tb[], struct nlattr *data[]) static void vrf_dellink(struct net_device *dev, struct list_head *head) { - struct net_vrf_dev *vrf_ptr = rtnl_dereference(dev->vrf_ptr); - - RCU_INIT_POINTER(dev->vrf_ptr, NULL); - kfree_rcu(vrf_ptr, rcu); unregister_netdevice_queue(dev, head); } @@ -580,7 +611,6 @@ static int vrf_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { struct net_vrf *vrf = netdev_priv(dev); - struct net_vrf_dev *vrf_ptr; int err; if (!data || !data[IFLA_VRF_TABLE]) @@ -588,26 +618,15 @@ static int vrf_newlink(struct net *src_net, struct net_device *dev, vrf->tb_id = nla_get_u32(data[IFLA_VRF_TABLE]); - dev->priv_flags |= IFF_VRF_MASTER; - - err = -ENOMEM; - vrf_ptr = kmalloc(sizeof(*dev->vrf_ptr), GFP_KERNEL); - if (!vrf_ptr) - goto out_fail; - - vrf_ptr->ifindex = dev->ifindex; - vrf_ptr->tb_id = vrf->tb_id; + dev->priv_flags |= IFF_L3MDEV_MASTER; err = register_netdevice(dev); if (err < 0) goto out_fail; - rcu_assign_pointer(dev->vrf_ptr, vrf_ptr); - return 0; out_fail: - kfree(vrf_ptr); free_netdev(dev); return err; } @@ -651,10 +670,9 @@ static int vrf_device_event(struct notifier_block *unused, /* only care about unregister events to drop slave references */ if (event == NETDEV_UNREGISTER) { - struct net_vrf_dev *vrf_ptr = rtnl_dereference(dev->vrf_ptr); struct net_device *vrf_dev; - if (!vrf_ptr || netif_is_vrf(dev)) + if (netif_is_l3_master(dev)) goto out; vrf_dev = netdev_master_upper_dev_get(dev); diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index bbac1d35ed4e..ce704df7681b 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -75,8 +75,7 @@ static struct rtnl_link_ops vxlan_link_ops; static const u8 all_zeros_mac[ETH_ALEN]; -static struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port, - bool no_share, u32 flags); +static int vxlan_sock_add(struct vxlan_dev *vxlan); /* per-network namespace private data for this module */ struct vxlan_net { @@ -994,19 +993,30 @@ static bool vxlan_snoop(struct net_device *dev, static bool vxlan_group_used(struct vxlan_net *vn, struct vxlan_dev *dev) { struct vxlan_dev *vxlan; + unsigned short family = dev->default_dst.remote_ip.sa.sa_family; /* The vxlan_sock is only used by dev, leaving group has * no effect on other vxlan devices. */ - if (atomic_read(&dev->vn_sock->refcnt) == 1) + if (family == AF_INET && dev->vn4_sock && + atomic_read(&dev->vn4_sock->refcnt) == 1) return false; +#if IS_ENABLED(CONFIG_IPV6) + if (family == AF_INET6 && dev->vn6_sock && + atomic_read(&dev->vn6_sock->refcnt) == 1) + return false; +#endif list_for_each_entry(vxlan, &vn->vxlan_list, next) { if (!netif_running(vxlan->dev) || vxlan == dev) continue; - if (vxlan->vn_sock != dev->vn_sock) + if (family == AF_INET && vxlan->vn4_sock != dev->vn4_sock) continue; +#if IS_ENABLED(CONFIG_IPV6) + if (family == AF_INET6 && vxlan->vn6_sock != dev->vn6_sock) + continue; +#endif if (!vxlan_addr_equal(&vxlan->default_dst.remote_ip, &dev->default_dst.remote_ip)) @@ -1022,15 +1032,16 @@ static bool vxlan_group_used(struct vxlan_net *vn, struct vxlan_dev *dev) return false; } -static void vxlan_sock_release(struct vxlan_sock *vs) +static void __vxlan_sock_release(struct vxlan_sock *vs) { - struct sock *sk = vs->sock->sk; - struct net *net = sock_net(sk); - struct vxlan_net *vn = net_generic(net, vxlan_net_id); + struct vxlan_net *vn; + if (!vs) + return; if (!atomic_dec_and_test(&vs->refcnt)) return; + vn = net_generic(sock_net(vs->sock->sk), vxlan_net_id); spin_lock(&vn->sock_lock); hlist_del_rcu(&vs->hlist); vxlan_notify_del_rx_port(vs); @@ -1039,32 +1050,43 @@ static void vxlan_sock_release(struct vxlan_sock *vs) queue_work(vxlan_wq, &vs->del_work); } +static void vxlan_sock_release(struct vxlan_dev *vxlan) +{ + __vxlan_sock_release(vxlan->vn4_sock); +#if IS_ENABLED(CONFIG_IPV6) + __vxlan_sock_release(vxlan->vn6_sock); +#endif +} + /* Update multicast group membership when first VNI on * multicast address is brought up */ static int vxlan_igmp_join(struct vxlan_dev *vxlan) { - struct vxlan_sock *vs = vxlan->vn_sock; - struct sock *sk = vs->sock->sk; + struct sock *sk; union vxlan_addr *ip = &vxlan->default_dst.remote_ip; int ifindex = vxlan->default_dst.remote_ifindex; int ret = -EINVAL; - lock_sock(sk); if (ip->sa.sa_family == AF_INET) { struct ip_mreqn mreq = { .imr_multiaddr.s_addr = ip->sin.sin_addr.s_addr, .imr_ifindex = ifindex, }; + sk = vxlan->vn4_sock->sock->sk; + lock_sock(sk); ret = ip_mc_join_group(sk, &mreq); + release_sock(sk); #if IS_ENABLED(CONFIG_IPV6) } else { + sk = vxlan->vn6_sock->sock->sk; + lock_sock(sk); ret = ipv6_stub->ipv6_sock_mc_join(sk, ifindex, &ip->sin6.sin6_addr); + release_sock(sk); #endif } - release_sock(sk); return ret; } @@ -1072,27 +1094,30 @@ static int vxlan_igmp_join(struct vxlan_dev *vxlan) /* Inverse of vxlan_igmp_join when last VNI is brought down */ static int vxlan_igmp_leave(struct vxlan_dev *vxlan) { - struct vxlan_sock *vs = vxlan->vn_sock; - struct sock *sk = vs->sock->sk; + struct sock *sk; union vxlan_addr *ip = &vxlan->default_dst.remote_ip; int ifindex = vxlan->default_dst.remote_ifindex; int ret = -EINVAL; - lock_sock(sk); if (ip->sa.sa_family == AF_INET) { struct ip_mreqn mreq = { .imr_multiaddr.s_addr = ip->sin.sin_addr.s_addr, .imr_ifindex = ifindex, }; + sk = vxlan->vn4_sock->sock->sk; + lock_sock(sk); ret = ip_mc_leave_group(sk, &mreq); + release_sock(sk); #if IS_ENABLED(CONFIG_IPV6) } else { + sk = vxlan->vn6_sock->sock->sk; + lock_sock(sk); ret = ipv6_stub->ipv6_sock_mc_drop(sk, ifindex, &ip->sin6.sin6_addr); + release_sock(sk); #endif } - release_sock(sk); return ret; } @@ -1873,8 +1898,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, { struct ip_tunnel_info *info; struct vxlan_dev *vxlan = netdev_priv(dev); - struct sock *sk = vxlan->vn_sock->sock->sk; - unsigned short family = vxlan_get_sk_family(vxlan->vn_sock); + struct sock *sk; struct rtable *rt = NULL; const struct iphdr *old_iph; struct flowi4 fl4; @@ -1901,13 +1925,10 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, dev->name); goto drop; } - if (family != ip_tunnel_info_af(info)) - goto drop; - dst_port = info->key.tp_dst ? : vxlan->cfg.dst_port; vni = be64_to_cpu(info->key.tun_id); - remote_ip.sa.sa_family = family; - if (family == AF_INET) + remote_ip.sa.sa_family = ip_tunnel_info_af(info); + if (remote_ip.sa.sa_family == AF_INET) remote_ip.sin.sin_addr.s_addr = info->key.u.ipv4.dst; else remote_ip.sin6.sin6_addr = info->key.u.ipv6.dst; @@ -1952,6 +1973,10 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, } if (dst->sa.sa_family == AF_INET) { + if (!vxlan->vn4_sock) + goto drop; + sk = vxlan->vn4_sock->sock->sk; + if (info && (info->key.tun_flags & TUNNEL_DONT_FRAGMENT)) df = htons(IP_DF); @@ -2013,6 +2038,10 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, struct flowi6 fl6; u32 rt6i_flags; + if (!vxlan->vn6_sock) + goto drop; + sk = vxlan->vn6_sock->sock->sk; + memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_oif = rdst ? rdst->remote_ifindex : 0; fl6.daddr = dst->sin6.sin6_addr; @@ -2204,7 +2233,6 @@ static void vxlan_vs_add_dev(struct vxlan_sock *vs, struct vxlan_dev *vxlan) struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); __u32 vni = vxlan->default_dst.remote_vni; - vxlan->vn_sock = vs; spin_lock(&vn->sock_lock); hlist_add_head_rcu(&vxlan->hlist, vni_head(vs, vni)); spin_unlock(&vn->sock_lock); @@ -2244,22 +2272,18 @@ static void vxlan_uninit(struct net_device *dev) static int vxlan_open(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); - struct vxlan_sock *vs; - int ret = 0; + int ret; - vs = vxlan_sock_add(vxlan->net, vxlan->cfg.dst_port, - vxlan->cfg.no_share, vxlan->flags); - if (IS_ERR(vs)) - return PTR_ERR(vs); - - vxlan_vs_add_dev(vs, vxlan); + ret = vxlan_sock_add(vxlan); + if (ret < 0) + return ret; if (vxlan_addr_multicast(&vxlan->default_dst.remote_ip)) { ret = vxlan_igmp_join(vxlan); if (ret == -EADDRINUSE) ret = 0; if (ret) { - vxlan_sock_release(vs); + vxlan_sock_release(vxlan); return ret; } } @@ -2294,7 +2318,6 @@ static int vxlan_stop(struct net_device *dev) { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); - struct vxlan_sock *vs = vxlan->vn_sock; int ret = 0; if (vxlan_addr_multicast(&vxlan->default_dst.remote_ip) && @@ -2304,7 +2327,7 @@ static int vxlan_stop(struct net_device *dev) del_timer_sync(&vxlan->age_timer); vxlan_flush(vxlan); - vxlan_sock_release(vs); + vxlan_sock_release(vxlan); return ret; } @@ -2540,14 +2563,13 @@ static struct socket *vxlan_create_sock(struct net *net, bool ipv6, } /* Create new listen socket if needed */ -static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port, - u32 flags) +static struct vxlan_sock *vxlan_socket_create(struct net *net, bool ipv6, + __be16 port, u32 flags) { struct vxlan_net *vn = net_generic(net, vxlan_net_id); struct vxlan_sock *vs; struct socket *sock; unsigned int h; - bool ipv6 = !!(flags & VXLAN_F_IPV6); struct udp_tunnel_sock_cfg tunnel_cfg; vs = kzalloc(sizeof(*vs), GFP_KERNEL); @@ -2592,27 +2614,53 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port, return vs; } -static struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port, - bool no_share, u32 flags) +static int __vxlan_sock_add(struct vxlan_dev *vxlan, bool ipv6) { - struct vxlan_net *vn = net_generic(net, vxlan_net_id); - struct vxlan_sock *vs; - bool ipv6 = flags & VXLAN_F_IPV6; + struct vxlan_net *vn = net_generic(vxlan->net, vxlan_net_id); + struct vxlan_sock *vs = NULL; - if (!no_share) { + if (!vxlan->cfg.no_share) { spin_lock(&vn->sock_lock); - vs = vxlan_find_sock(net, ipv6 ? AF_INET6 : AF_INET, port, - flags); - if (vs) { - if (!atomic_add_unless(&vs->refcnt, 1, 0)) - vs = ERR_PTR(-EBUSY); + vs = vxlan_find_sock(vxlan->net, ipv6 ? AF_INET6 : AF_INET, + vxlan->cfg.dst_port, vxlan->flags); + if (vs && !atomic_add_unless(&vs->refcnt, 1, 0)) { spin_unlock(&vn->sock_lock); - return vs; + return -EBUSY; } spin_unlock(&vn->sock_lock); } + if (!vs) + vs = vxlan_socket_create(vxlan->net, ipv6, + vxlan->cfg.dst_port, vxlan->flags); + if (IS_ERR(vs)) + return PTR_ERR(vs); +#if IS_ENABLED(CONFIG_IPV6) + if (ipv6) + vxlan->vn6_sock = vs; + else +#endif + vxlan->vn4_sock = vs; + vxlan_vs_add_dev(vs, vxlan); + return 0; +} - return vxlan_socket_create(net, port, flags); +static int vxlan_sock_add(struct vxlan_dev *vxlan) +{ + bool ipv6 = vxlan->flags & VXLAN_F_IPV6; + bool metadata = vxlan->flags & VXLAN_F_COLLECT_METADATA; + int ret = 0; + + vxlan->vn4_sock = NULL; +#if IS_ENABLED(CONFIG_IPV6) + vxlan->vn6_sock = NULL; + if (ipv6 || metadata) + ret = __vxlan_sock_add(vxlan, true); +#endif + if (!ret && (!ipv6 || metadata)) + ret = __vxlan_sock_add(vxlan, false); + if (ret < 0) + vxlan_sock_release(vxlan); + return ret; } static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, @@ -2621,6 +2669,7 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, struct vxlan_net *vn = net_generic(src_net, vxlan_net_id); struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst *dst = &vxlan->default_dst; + unsigned short needed_headroom = ETH_HLEN; int err; bool use_ipv6 = false; __be16 default_port = vxlan->cfg.dst_port; @@ -2640,6 +2689,7 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, if (!IS_ENABLED(CONFIG_IPV6)) return -EPFNOSUPPORT; use_ipv6 = true; + vxlan->flags |= VXLAN_F_IPV6; } if (conf->remote_ifindex) { @@ -2660,22 +2710,21 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev, pr_info("IPv6 is disabled via sysctl\n"); return -EPERM; } - vxlan->flags |= VXLAN_F_IPV6; } #endif if (!conf->mtu) dev->mtu = lowerdev->mtu - (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM); - dev->needed_headroom = lowerdev->hard_header_len + - (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM); - } else if (use_ipv6) { - vxlan->flags |= VXLAN_F_IPV6; - dev->needed_headroom = ETH_HLEN + VXLAN6_HEADROOM; - } else { - dev->needed_headroom = ETH_HLEN + VXLAN_HEADROOM; + needed_headroom = lowerdev->hard_header_len; } + if (use_ipv6 || conf->flags & VXLAN_F_COLLECT_METADATA) + needed_headroom += VXLAN6_HEADROOM; + else + needed_headroom += VXLAN_HEADROOM; + dev->needed_headroom = needed_headroom; + memcpy(&vxlan->cfg, conf, sizeof(*conf)); if (!vxlan->cfg.dst_port) vxlan->cfg.dst_port = default_port; diff --git a/drivers/net/wireless/brcm80211/brcmsmac/main.c b/drivers/net/wireless/brcm80211/brcmsmac/main.c index 9728be0e704b..218cbc8bf3a7 100644 --- a/drivers/net/wireless/brcm80211/brcmsmac/main.c +++ b/drivers/net/wireless/brcm80211/brcmsmac/main.c @@ -4585,7 +4585,7 @@ static int brcms_b_attach(struct brcms_c_info *wlc, struct bcma_device *core, wlc_hw->machwcap_backup = wlc_hw->machwcap; /* init tx fifo size */ - WARN_ON((wlc_hw->corerev - XMTFIFOTBL_STARTREV) < 0 || + WARN_ON(wlc_hw->corerev < XMTFIFOTBL_STARTREV || (wlc_hw->corerev - XMTFIFOTBL_STARTREV) > ARRAY_SIZE(xmtfifo_sz)); wlc_hw->xmtfifo_sz = diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 520bef80747f..66c963dbc3fd 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -2190,9 +2190,8 @@ static void hwsim_mcast_config_msg(struct sk_buff *mcast_skb, struct genl_info *info) { if (info) - genl_notify(&hwsim_genl_family, mcast_skb, - genl_info_net(info), info->snd_portid, - HWSIM_MCGRP_CONFIG, info->nlhdr, GFP_KERNEL); + genl_notify(&hwsim_genl_family, mcast_skb, info, + HWSIM_MCGRP_CONFIG, GFP_KERNEL); else genlmsg_multicast(&hwsim_genl_family, mcast_skb, 0, HWSIM_MCGRP_CONFIG, GFP_KERNEL); diff --git a/drivers/net/wireless/mwifiex/11n_rxreorder.c b/drivers/net/wireless/mwifiex/11n_rxreorder.c index 2906cd543532..b3970a8c9e48 100644 --- a/drivers/net/wireless/mwifiex/11n_rxreorder.c +++ b/drivers/net/wireless/mwifiex/11n_rxreorder.c @@ -615,10 +615,10 @@ int mwifiex_11n_rx_reorder_pkt(struct mwifiex_private *priv, ((end_win > start_win) && ((seq_num > end_win) || (seq_num < start_win)))) { end_win = seq_num; - if (((seq_num - win_size) + 1) >= 0) + if (((end_win - win_size) + 1) >= 0) start_win = (end_win - win_size) + 1; else - start_win = (MAX_TID_VALUE - (win_size - seq_num)) + 1; + start_win = (MAX_TID_VALUE - (win_size - end_win)) + 1; mwifiex_11n_dispatch_pkt_until_start_win(priv, tbl, start_win); } diff --git a/drivers/net/wireless/orinoco/cfg.c b/drivers/net/wireless/orinoco/cfg.c index a9e94b6db5b7..0f6ea316e38e 100644 --- a/drivers/net/wireless/orinoco/cfg.c +++ b/drivers/net/wireless/orinoco/cfg.c @@ -220,7 +220,7 @@ static int orinoco_set_wiphy_params(struct wiphy *wiphy, u32 changed) if (changed & WIPHY_PARAM_FRAG_THRESHOLD) { /* Set fragmentation */ if (priv->has_mwo) { - if (wiphy->frag_threshold < 0) + if (wiphy->frag_threshold == -1) frag_value = 0; else { printk(KERN_WARNING "%s: Fixed fragmentation " @@ -230,7 +230,7 @@ static int orinoco_set_wiphy_params(struct wiphy *wiphy, u32 changed) frag_value = 1; } } else { - if (wiphy->frag_threshold < 0) + if (wiphy->frag_threshold == -1) frag_value = 2346; else if ((wiphy->frag_threshold < 257) || (wiphy->frag_threshold > 2347)) @@ -252,7 +252,7 @@ static int orinoco_set_wiphy_params(struct wiphy *wiphy, u32 changed) * the upper limit. */ - if (wiphy->rts_threshold < 0) + if (wiphy->rts_threshold == -1) rts_value = 2347; else if (wiphy->rts_threshold > 2347) err = -EINVAL; diff --git a/drivers/net/wireless/rndis_wlan.c b/drivers/net/wireless/rndis_wlan.c index 71a825c750cf..a13d1f2b5912 100644 --- a/drivers/net/wireless/rndis_wlan.c +++ b/drivers/net/wireless/rndis_wlan.c @@ -1236,7 +1236,7 @@ static int set_rts_threshold(struct usbnet *usbdev, u32 rts_threshold) netdev_dbg(usbdev->net, "%s(): %i\n", __func__, rts_threshold); - if (rts_threshold < 0 || rts_threshold > 2347) + if (rts_threshold == -1 || rts_threshold > 2347) rts_threshold = 2347; tmp = cpu_to_le32(rts_threshold); diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index f821a97d7827..9bf63c27a9b7 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -1819,19 +1819,22 @@ again: goto destroy_ring; } - if (num_queues == 1) { - err = write_queue_xenstore_keys(&info->queues[0], &xbt, 0); /* flat */ - if (err) - goto abort_transaction_no_dev_fatal; - } else { + if (xenbus_exists(XBT_NIL, + info->xbdev->otherend, "multi-queue-max-queues")) { /* Write the number of queues */ - err = xenbus_printf(xbt, dev->nodename, "multi-queue-num-queues", - "%u", num_queues); + err = xenbus_printf(xbt, dev->nodename, + "multi-queue-num-queues", "%u", num_queues); if (err) { message = "writing multi-queue-num-queues"; goto abort_transaction_no_dev_fatal; } + } + if (num_queues == 1) { + err = write_queue_xenstore_keys(&info->queues[0], &xbt, 0); /* flat */ + if (err) + goto abort_transaction_no_dev_fatal; + } else { /* Write the keys for each queue */ for (i = 0; i < num_queues; ++i) { queue = &info->queues[i]; diff --git a/drivers/s390/char/monreader.c b/drivers/s390/char/monreader.c index b7d60306b0bc..fc94bfdceb95 100644 --- a/drivers/s390/char/monreader.c +++ b/drivers/s390/char/monreader.c @@ -229,7 +229,7 @@ static struct mon_msg *mon_next_message(struct mon_private *monpriv) /****************************************************************************** * IUCV handler * *****************************************************************************/ -static void mon_iucv_path_complete(struct iucv_path *path, u8 ipuser[16]) +static void mon_iucv_path_complete(struct iucv_path *path, u8 *ipuser) { struct mon_private *monpriv = path->private; @@ -237,7 +237,7 @@ static void mon_iucv_path_complete(struct iucv_path *path, u8 ipuser[16]) wake_up(&mon_conn_wait_queue); } -static void mon_iucv_path_severed(struct iucv_path *path, u8 ipuser[16]) +static void mon_iucv_path_severed(struct iucv_path *path, u8 *ipuser) { struct mon_private *monpriv = path->private; diff --git a/drivers/s390/char/vmlogrdr.c b/drivers/s390/char/vmlogrdr.c index 9bb48d70957c..799c1524c779 100644 --- a/drivers/s390/char/vmlogrdr.c +++ b/drivers/s390/char/vmlogrdr.c @@ -99,8 +99,8 @@ static const struct file_operations vmlogrdr_fops = { }; -static void vmlogrdr_iucv_path_complete(struct iucv_path *, u8 ipuser[16]); -static void vmlogrdr_iucv_path_severed(struct iucv_path *, u8 ipuser[16]); +static void vmlogrdr_iucv_path_complete(struct iucv_path *, u8 *ipuser); +static void vmlogrdr_iucv_path_severed(struct iucv_path *, u8 *ipuser); static void vmlogrdr_iucv_message_pending(struct iucv_path *, struct iucv_message *); @@ -160,7 +160,7 @@ static struct cdev *vmlogrdr_cdev = NULL; static int recording_class_AB; -static void vmlogrdr_iucv_path_complete(struct iucv_path *path, u8 ipuser[16]) +static void vmlogrdr_iucv_path_complete(struct iucv_path *path, u8 *ipuser) { struct vmlogrdr_priv_t * logptr = path->private; @@ -171,7 +171,7 @@ static void vmlogrdr_iucv_path_complete(struct iucv_path *path, u8 ipuser[16]) } -static void vmlogrdr_iucv_path_severed(struct iucv_path *path, u8 ipuser[16]) +static void vmlogrdr_iucv_path_severed(struct iucv_path *path, u8 *ipuser) { struct vmlogrdr_priv_t * logptr = path->private; u8 reason = (u8) ipuser[8]; diff --git a/drivers/s390/net/netiucv.c b/drivers/s390/net/netiucv.c index 33f7040d711d..0ba3a2f81750 100644 --- a/drivers/s390/net/netiucv.c +++ b/drivers/s390/net/netiucv.c @@ -149,12 +149,11 @@ static struct device_driver netiucv_driver = { .pm = &netiucv_pm_ops, }; -static int netiucv_callback_connreq(struct iucv_path *, - u8 ipvmid[8], u8 ipuser[16]); -static void netiucv_callback_connack(struct iucv_path *, u8 ipuser[16]); -static void netiucv_callback_connrej(struct iucv_path *, u8 ipuser[16]); -static void netiucv_callback_connsusp(struct iucv_path *, u8 ipuser[16]); -static void netiucv_callback_connres(struct iucv_path *, u8 ipuser[16]); +static int netiucv_callback_connreq(struct iucv_path *, u8 *, u8 *); +static void netiucv_callback_connack(struct iucv_path *, u8 *); +static void netiucv_callback_connrej(struct iucv_path *, u8 *); +static void netiucv_callback_connsusp(struct iucv_path *, u8 *); +static void netiucv_callback_connres(struct iucv_path *, u8 *); static void netiucv_callback_rx(struct iucv_path *, struct iucv_message *); static void netiucv_callback_txdone(struct iucv_path *, struct iucv_message *); @@ -556,8 +555,8 @@ static void netiucv_callback_connack(struct iucv_path *path, u8 ipuser[16]) fsm_event(conn->fsm, CONN_EVENT_CONN_ACK, conn); } -static int netiucv_callback_connreq(struct iucv_path *path, - u8 ipvmid[8], u8 ipuser[16]) +static int netiucv_callback_connreq(struct iucv_path *path, u8 *ipvmid, + u8 *ipuser) { struct iucv_connection *conn = path->private; struct iucv_event ev; @@ -587,21 +586,21 @@ static int netiucv_callback_connreq(struct iucv_path *path, return rc; } -static void netiucv_callback_connrej(struct iucv_path *path, u8 ipuser[16]) +static void netiucv_callback_connrej(struct iucv_path *path, u8 *ipuser) { struct iucv_connection *conn = path->private; fsm_event(conn->fsm, CONN_EVENT_CONN_REJ, conn); } -static void netiucv_callback_connsusp(struct iucv_path *path, u8 ipuser[16]) +static void netiucv_callback_connsusp(struct iucv_path *path, u8 *ipuser) { struct iucv_connection *conn = path->private; fsm_event(conn->fsm, CONN_EVENT_CONN_SUS, conn); } -static void netiucv_callback_connres(struct iucv_path *path, u8 ipuser[16]) +static void netiucv_callback_connres(struct iucv_path *path, u8 *ipuser) { struct iucv_connection *conn = path->private; diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index ba974a2e409f..6719447d13f0 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -663,9 +663,7 @@ struct qeth_card_info { char mcl_level[QETH_MCL_LENGTH + 1]; int guestlan; int mac_bits; - int portname_required; int portno; - char portname[9]; enum qeth_card_types type; enum qeth_link_types link_type; int is_multicast_different; @@ -969,6 +967,15 @@ int qeth_hw_trap(struct qeth_card *, enum qeth_diags_trap_action); int qeth_query_ipassists(struct qeth_card *, enum qeth_prot_versions prot); void qeth_trace_features(struct qeth_card *); void qeth_close_dev(struct qeth_card *); +int qeth_send_simple_setassparms(struct qeth_card *, enum qeth_ipa_funcs, + __u16, long); +int qeth_send_setassparms(struct qeth_card *, struct qeth_cmd_buffer *, __u16, + long, + int (*reply_cb)(struct qeth_card *, + struct qeth_reply *, unsigned long), + void *); +int qeth_start_ipa_tx_checksum(struct qeth_card *); +int qeth_set_rx_csum(struct qeth_card *, int); /* exports for OSN */ int qeth_osn_assist(struct net_device *, void *, int); diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 5e20fba37bff..31ac53fa5cee 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -1982,14 +1982,6 @@ static void qeth_idx_read_cb(struct qeth_channel *channel, goto out; } -/** - * * temporary fix for microcode bug - * * to revert it,replace OR by AND - * */ - if ((!QETH_IDX_NO_PORTNAME_REQUIRED(iob->data)) || - (card->info.type == QETH_CARD_TYPE_OSD)) - card->info.portname_required = 1; - memcpy(&temp, QETH_IDX_ACT_FUNC_LEVEL(iob->data), 2); if (temp != qeth_peer_func_level(card->info.func_level)) { QETH_DBF_MESSAGE(2, "%s IDX_ACTIVATE on read channel: function " @@ -2360,8 +2352,6 @@ static int qeth_ulp_enable(struct qeth_card *card) &card->token.cm_connection_r, QETH_MPC_TOKEN_LENGTH); memcpy(QETH_ULP_ENABLE_FILTER_TOKEN(iob->data), &card->token.ulp_filter_w, QETH_MPC_TOKEN_LENGTH); - memcpy(QETH_ULP_ENABLE_PORTNAME_AND_LL(iob->data), - card->info.portname, 9); rc = qeth_send_control_data(card, ULP_ENABLE_SIZE, iob, qeth_ulp_enable_cb, NULL); return rc; @@ -2680,48 +2670,6 @@ out_qdio: return rc; } -static void qeth_print_status_with_portname(struct qeth_card *card) -{ - char dbf_text[15]; - int i; - - sprintf(dbf_text, "%s", card->info.portname + 1); - for (i = 0; i < 8; i++) - dbf_text[i] = - (char) _ebcasc[(__u8) dbf_text[i]]; - dbf_text[8] = 0; - dev_info(&card->gdev->dev, "Device is a%s card%s%s%s\n" - "with link type %s (portname: %s)\n", - qeth_get_cardname(card), - (card->info.mcl_level[0]) ? " (level: " : "", - (card->info.mcl_level[0]) ? card->info.mcl_level : "", - (card->info.mcl_level[0]) ? ")" : "", - qeth_get_cardname_short(card), - dbf_text); - -} - -static void qeth_print_status_no_portname(struct qeth_card *card) -{ - if (card->info.portname[0]) - dev_info(&card->gdev->dev, "Device is a%s " - "card%s%s%s\nwith link type %s " - "(no portname needed by interface).\n", - qeth_get_cardname(card), - (card->info.mcl_level[0]) ? " (level: " : "", - (card->info.mcl_level[0]) ? card->info.mcl_level : "", - (card->info.mcl_level[0]) ? ")" : "", - qeth_get_cardname_short(card)); - else - dev_info(&card->gdev->dev, "Device is a%s " - "card%s%s%s\nwith link type %s.\n", - qeth_get_cardname(card), - (card->info.mcl_level[0]) ? " (level: " : "", - (card->info.mcl_level[0]) ? card->info.mcl_level : "", - (card->info.mcl_level[0]) ? ")" : "", - qeth_get_cardname_short(card)); -} - void qeth_print_status_message(struct qeth_card *card) { switch (card->info.type) { @@ -2758,10 +2706,13 @@ void qeth_print_status_message(struct qeth_card *card) default: memset(&card->info.mcl_level[0], 0, QETH_MCL_LENGTH + 1); } - if (card->info.portname_required) - qeth_print_status_with_portname(card); - else - qeth_print_status_no_portname(card); + dev_info(&card->gdev->dev, + "Device is a%s card%s%s%s\nwith link type %s.\n", + qeth_get_cardname(card), + (card->info.mcl_level[0]) ? " (level: " : "", + (card->info.mcl_level[0]) ? card->info.mcl_level : "", + (card->info.mcl_level[0]) ? ")" : "", + qeth_get_cardname_short(card)); } EXPORT_SYMBOL_GPL(qeth_print_status_message); @@ -5027,13 +4978,11 @@ static void qeth_core_free_card(struct qeth_card *card) void qeth_trace_features(struct qeth_card *card) { QETH_CARD_TEXT(card, 2, "features"); - QETH_CARD_TEXT_(card, 2, "%x", card->options.ipa4.supported_funcs); - QETH_CARD_TEXT_(card, 2, "%x", card->options.ipa4.enabled_funcs); - QETH_CARD_TEXT_(card, 2, "%x", card->options.ipa6.supported_funcs); - QETH_CARD_TEXT_(card, 2, "%x", card->options.ipa6.enabled_funcs); - QETH_CARD_TEXT_(card, 2, "%x", card->options.adp.supported_funcs); - QETH_CARD_TEXT_(card, 2, "%x", card->options.adp.enabled_funcs); - QETH_CARD_TEXT_(card, 2, "%x", card->info.diagass_support); + QETH_CARD_HEX(card, 2, &card->options.ipa4, sizeof(card->options.ipa4)); + QETH_CARD_HEX(card, 2, &card->options.ipa6, sizeof(card->options.ipa6)); + QETH_CARD_HEX(card, 2, &card->options.adp, sizeof(card->options.adp)); + QETH_CARD_HEX(card, 2, &card->info.diagass_support, + sizeof(card->info.diagass_support)); } EXPORT_SYMBOL_GPL(qeth_trace_features); @@ -5132,6 +5081,7 @@ retriable: } card->options.ipa4.supported_funcs = 0; + card->options.ipa6.supported_funcs = 0; card->options.adp.supported_funcs = 0; card->options.sbp.supported_funcs = 0; card->info.diagass_support = 0; @@ -5317,6 +5267,102 @@ no_mem: } EXPORT_SYMBOL_GPL(qeth_core_get_next_skb); +static int qeth_setassparms_cb(struct qeth_card *card, + struct qeth_reply *reply, unsigned long data) +{ + struct qeth_ipa_cmd *cmd; + + QETH_CARD_TEXT(card, 4, "defadpcb"); + + cmd = (struct qeth_ipa_cmd *) data; + if (cmd->hdr.return_code == 0) { + cmd->hdr.return_code = cmd->data.setassparms.hdr.return_code; + if (cmd->hdr.prot_version == QETH_PROT_IPV4) + card->options.ipa4.enabled_funcs = cmd->hdr.ipa_enabled; + if (cmd->hdr.prot_version == QETH_PROT_IPV6) + card->options.ipa6.enabled_funcs = cmd->hdr.ipa_enabled; + } + if (cmd->data.setassparms.hdr.assist_no == IPA_INBOUND_CHECKSUM && + cmd->data.setassparms.hdr.command_code == IPA_CMD_ASS_START) { + card->info.csum_mask = cmd->data.setassparms.data.flags_32bit; + QETH_CARD_TEXT_(card, 3, "csum:%d", card->info.csum_mask); + } + if (cmd->data.setassparms.hdr.assist_no == IPA_OUTBOUND_CHECKSUM && + cmd->data.setassparms.hdr.command_code == IPA_CMD_ASS_START) { + card->info.tx_csum_mask = + cmd->data.setassparms.data.flags_32bit; + QETH_CARD_TEXT_(card, 3, "tcsu:%d", card->info.tx_csum_mask); + } + + return 0; +} + +static struct qeth_cmd_buffer *qeth_get_setassparms_cmd(struct qeth_card *card, + enum qeth_ipa_funcs ipa_func, + __u16 cmd_code, __u16 len, + enum qeth_prot_versions prot) +{ + struct qeth_cmd_buffer *iob; + struct qeth_ipa_cmd *cmd; + + QETH_CARD_TEXT(card, 4, "getasscm"); + iob = qeth_get_ipacmd_buffer(card, IPA_CMD_SETASSPARMS, prot); + + if (iob) { + cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE); + cmd->data.setassparms.hdr.assist_no = ipa_func; + cmd->data.setassparms.hdr.length = 8 + len; + cmd->data.setassparms.hdr.command_code = cmd_code; + cmd->data.setassparms.hdr.return_code = 0; + cmd->data.setassparms.hdr.seq_no = 0; + } + + return iob; +} + +int qeth_send_setassparms(struct qeth_card *card, + struct qeth_cmd_buffer *iob, __u16 len, long data, + int (*reply_cb)(struct qeth_card *, + struct qeth_reply *, unsigned long), + void *reply_param) +{ + int rc; + struct qeth_ipa_cmd *cmd; + + QETH_CARD_TEXT(card, 4, "sendassp"); + + cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE); + if (len <= sizeof(__u32)) + cmd->data.setassparms.data.flags_32bit = (__u32) data; + else /* (len > sizeof(__u32)) */ + memcpy(&cmd->data.setassparms.data, (void *) data, len); + + rc = qeth_send_ipa_cmd(card, iob, reply_cb, reply_param); + return rc; +} +EXPORT_SYMBOL_GPL(qeth_send_setassparms); + +int qeth_send_simple_setassparms(struct qeth_card *card, + enum qeth_ipa_funcs ipa_func, + __u16 cmd_code, long data) +{ + int rc; + int length = 0; + struct qeth_cmd_buffer *iob; + + QETH_CARD_TEXT(card, 4, "simassp4"); + if (data) + length = sizeof(__u32); + iob = qeth_get_setassparms_cmd(card, ipa_func, cmd_code, + length, QETH_PROT_IPV4); + if (!iob) + return -ENOMEM; + rc = qeth_send_setassparms(card, iob, length, data, + qeth_setassparms_cb, NULL); + return rc; +} +EXPORT_SYMBOL_GPL(qeth_send_simple_setassparms); + static void qeth_unregister_dbf_views(void) { int x; @@ -6003,6 +6049,75 @@ int qeth_core_ethtool_get_settings(struct net_device *netdev, } EXPORT_SYMBOL_GPL(qeth_core_ethtool_get_settings); +static int qeth_send_checksum_command(struct qeth_card *card) +{ + int rc; + + rc = qeth_send_simple_setassparms(card, IPA_INBOUND_CHECKSUM, + IPA_CMD_ASS_START, 0); + if (rc) { + dev_warn(&card->gdev->dev, "Starting HW checksumming for %s " + "failed, using SW checksumming\n", + QETH_CARD_IFNAME(card)); + return rc; + } + rc = qeth_send_simple_setassparms(card, IPA_INBOUND_CHECKSUM, + IPA_CMD_ASS_ENABLE, + card->info.csum_mask); + if (rc) { + dev_warn(&card->gdev->dev, "Enabling HW checksumming for %s " + "failed, using SW checksumming\n", + QETH_CARD_IFNAME(card)); + return rc; + } + return 0; +} + +int qeth_set_rx_csum(struct qeth_card *card, int on) +{ + int rc; + + if (on) { + rc = qeth_send_checksum_command(card); + if (rc) + return -EIO; + dev_info(&card->gdev->dev, + "HW Checksumming (inbound) enabled\n"); + } else { + rc = qeth_send_simple_setassparms(card, + IPA_INBOUND_CHECKSUM, IPA_CMD_ASS_STOP, 0); + if (rc) + return -EIO; + } + return 0; +} +EXPORT_SYMBOL_GPL(qeth_set_rx_csum); + +int qeth_start_ipa_tx_checksum(struct qeth_card *card) +{ + int rc = 0; + + if (!qeth_is_supported(card, IPA_OUTBOUND_CHECKSUM)) + return rc; + rc = qeth_send_simple_setassparms(card, IPA_OUTBOUND_CHECKSUM, + IPA_CMD_ASS_START, 0); + if (rc) + goto err_out; + rc = qeth_send_simple_setassparms(card, IPA_OUTBOUND_CHECKSUM, + IPA_CMD_ASS_ENABLE, + card->info.tx_csum_mask); + if (rc) + goto err_out; + + dev_info(&card->gdev->dev, "HW TX Checksumming enabled\n"); + return rc; +err_out: + dev_warn(&card->gdev->dev, "Enabling HW TX checksumming for %s " + "failed, using SW TX checksumming\n", QETH_CARD_IFNAME(card)); + return rc; +} +EXPORT_SYMBOL_GPL(qeth_start_ipa_tx_checksum); + static int __init qeth_core_init(void) { int rc; diff --git a/drivers/s390/net/qeth_core_sys.c b/drivers/s390/net/qeth_core_sys.c index 423bec56cffa..e6e5b9671bf2 100644 --- a/drivers/s390/net/qeth_core_sys.c +++ b/drivers/s390/net/qeth_core_sys.c @@ -153,52 +153,17 @@ static DEVICE_ATTR(portno, 0644, qeth_dev_portno_show, qeth_dev_portno_store); static ssize_t qeth_dev_portname_show(struct device *dev, struct device_attribute *attr, char *buf) { - struct qeth_card *card = dev_get_drvdata(dev); - char portname[9] = {0, }; - - if (!card) - return -EINVAL; - - if (card->info.portname_required) { - memcpy(portname, card->info.portname + 1, 8); - EBCASC(portname, 8); - return sprintf(buf, "%s\n", portname); - } else - return sprintf(buf, "no portname required\n"); + return sprintf(buf, "no portname required\n"); } static ssize_t qeth_dev_portname_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct qeth_card *card = dev_get_drvdata(dev); - char *tmp; - int i, rc = 0; - - if (!card) - return -EINVAL; - - mutex_lock(&card->conf_mutex); - if ((card->state != CARD_STATE_DOWN) && - (card->state != CARD_STATE_RECOVER)) { - rc = -EPERM; - goto out; - } - tmp = strsep((char **) &buf, "\n"); - if ((strlen(tmp) > 8) || (strlen(tmp) == 0)) { - rc = -EINVAL; - goto out; - } - - card->info.portname[0] = strlen(tmp); - /* for beauty reasons */ - for (i = 1; i < 9; i++) - card->info.portname[i] = ' '; - strcpy(card->info.portname + 1, tmp); - ASCEBC(card->info.portname + 1, 8); -out: - mutex_unlock(&card->conf_mutex); - return rc ? rc : count; + dev_warn_once(&card->gdev->dev, + "portname is deprecated and is ignored\n"); + return count; } static DEVICE_ATTR(portname, 0644, qeth_dev_portname_show, diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index a8556692f632..dc905b37aa12 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -252,6 +252,23 @@ static inline int qeth_l2_get_cast_type(struct qeth_card *card, return RTN_UNSPEC; } +static inline void qeth_l2_hdr_csum(struct qeth_card *card, + struct qeth_hdr *hdr, struct sk_buff *skb) +{ + struct iphdr *iph = ip_hdr(skb); + + /* tcph->check contains already the pseudo hdr checksum + * so just set the header flags + */ + if (iph->protocol == IPPROTO_UDP) + hdr->hdr.l2.flags[1] |= QETH_HDR_EXT_UDP; + hdr->hdr.l2.flags[1] |= QETH_HDR_EXT_CSUM_TRANSP_REQ | + QETH_HDR_EXT_CSUM_HDR_REQ; + iph->check = 0; + if (card->options.performance_stats) + card->perf_stats.tx_csum++; +} + static void qeth_l2_fill_header(struct qeth_card *card, struct qeth_hdr *hdr, struct sk_buff *skb, int cast_type) { @@ -390,6 +407,38 @@ static int qeth_l2_vlan_rx_kill_vid(struct net_device *dev, return rc; } +static netdev_features_t qeth_l2_fix_features(struct net_device *dev, + netdev_features_t features) +{ + struct qeth_card *card = dev->ml_priv; + + QETH_DBF_TEXT(SETUP, 2, "fixfeat"); + if (!qeth_is_supported(card, IPA_OUTBOUND_CHECKSUM)) + features &= ~NETIF_F_IP_CSUM; + if (!qeth_is_supported(card, IPA_INBOUND_CHECKSUM)) + features &= ~NETIF_F_RXCSUM; + QETH_DBF_HEX(SETUP, 2, &features, sizeof(features)); + return features; +} + +static int qeth_l2_set_features(struct net_device *dev, + netdev_features_t features) +{ + struct qeth_card *card = dev->ml_priv; + netdev_features_t changed = dev->features ^ features; + + QETH_DBF_TEXT(SETUP, 2, "setfeat"); + QETH_DBF_HEX(SETUP, 2, &features, sizeof(features)); + + if (card->state == CARD_STATE_DOWN || + card->state == CARD_STATE_RECOVER) + return 0; + + if (!(changed & NETIF_F_RXCSUM)) + return 0; + return qeth_set_rx_csum(card, features & NETIF_F_RXCSUM ? 1 : 0); +} + static void qeth_l2_stop_card(struct qeth_card *card, int recovery_mode) { QETH_DBF_TEXT(SETUP , 2, "stopcard"); @@ -450,7 +499,15 @@ static int qeth_l2_process_inbound_buffer(struct qeth_card *card, case QETH_HEADER_TYPE_LAYER2: skb->pkt_type = PACKET_HOST; skb->protocol = eth_type_trans(skb, skb->dev); - skb->ip_summed = CHECKSUM_NONE; + if ((card->dev->features & NETIF_F_RXCSUM) + && ((hdr->hdr.l2.flags[1] & + (QETH_HDR_EXT_CSUM_HDR_REQ | + QETH_HDR_EXT_CSUM_TRANSP_REQ)) == + (QETH_HDR_EXT_CSUM_HDR_REQ | + QETH_HDR_EXT_CSUM_TRANSP_REQ))) + skb->ip_summed = CHECKSUM_UNNECESSARY; + else + skb->ip_summed = CHECKSUM_NONE; if (skb->protocol == htons(ETH_P_802_2)) *((__u32 *)skb->cb) = ++card->seqno.pkt_seqno; len = skb->len; @@ -803,6 +860,8 @@ static int qeth_l2_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) sizeof(struct qeth_hdr)); skb_set_mac_header(new_skb, sizeof(struct qeth_hdr)); qeth_l2_fill_header(card, hdr, new_skb, cast_type); + if (new_skb->ip_summed == CHECKSUM_PARTIAL) + qeth_l2_hdr_csum(card, hdr, new_skb); } } @@ -968,6 +1027,8 @@ static const struct net_device_ops qeth_l2_netdev_ops = { .ndo_vlan_rx_add_vid = qeth_l2_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = qeth_l2_vlan_rx_kill_vid, .ndo_tx_timeout = qeth_tx_timeout, + .ndo_fix_features = qeth_l2_fix_features, + .ndo_set_features = qeth_l2_set_features }; static int qeth_l2_setup_netdev(struct qeth_card *card) @@ -997,6 +1058,11 @@ static int qeth_l2_setup_netdev(struct qeth_card *card) (card->info.type != QETH_CARD_TYPE_OSN) ? &qeth_l2_ethtool_ops : &qeth_l2_osn_ops; card->dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + if (card->info.type == QETH_CARD_TYPE_OSD && !card->info.guestlan) { + card->dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_RXCSUM; + /* Turn on RX offloading per default */ + card->dev->features |= NETIF_F_RXCSUM; + } card->info.broadcast_capable = 1; qeth_l2_request_initial_mac(card); SET_NETDEV_DEV(card->dev, &card->gdev->dev); @@ -1004,6 +1070,17 @@ static int qeth_l2_setup_netdev(struct qeth_card *card) return register_netdev(card->dev); } +static int qeth_l2_start_ipassists(struct qeth_card *card) +{ + /* configure isolation level */ + if (qeth_set_access_ctrl_online(card, 0)) + return -ENODEV; + if (qeth_is_supported(card, IPA_INBOUND_CHECKSUM)) + qeth_set_rx_csum(card, 1); + qeth_start_ipa_tx_checksum(card); + return 0; +} + static int __qeth_l2_set_online(struct ccwgroup_device *gdev, int recovery_mode) { struct qeth_card *card = dev_get_drvdata(&gdev->dev); @@ -1069,12 +1146,8 @@ static int __qeth_l2_set_online(struct ccwgroup_device *gdev, int recovery_mode) contin: if ((card->info.type == QETH_CARD_TYPE_OSD) || (card->info.type == QETH_CARD_TYPE_OSX)) { - /* configure isolation level */ - rc = qeth_set_access_ctrl_online(card, 0); - if (rc) { - rc = -ENODEV; + if (qeth_l2_start_ipassists(card)) goto out_remove; - } } if (card->info.type != QETH_CARD_TYPE_OSN && @@ -1452,8 +1525,8 @@ static void qeth_bridge_emit_host_event(struct qeth_card *card, env[i] = str[i]; i++; } if (code & IPA_ADDR_CHANGE_CODE_MACADDR) { - snprintf(str[i], sizeof(str[i]), "MAC=%pM6", - &addr_lnid->mac); + snprintf(str[i], sizeof(str[i]), "MAC=%pM", + addr_lnid->mac); env[i] = str[i]; i++; } snprintf(str[i], sizeof(str[i]), "NTOK_BUSID=%x.%x.%04x", diff --git a/drivers/s390/net/qeth_l2_sys.c b/drivers/s390/net/qeth_l2_sys.c index 52673cd1db99..692db49e3d2a 100644 --- a/drivers/s390/net/qeth_l2_sys.c +++ b/drivers/s390/net/qeth_l2_sys.c @@ -109,7 +109,7 @@ static ssize_t qeth_bridge_port_state_show(struct device *dev, return qeth_bridge_port_role_state_show(dev, attr, buf, 1); } -static DEVICE_ATTR(bridge_state, 0644, qeth_bridge_port_state_show, +static DEVICE_ATTR(bridge_state, 0444, qeth_bridge_port_state_show, NULL); static ssize_t qeth_bridgeport_hostnotification_show(struct device *dev, diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index a1aaa36e9ebb..543960e96b42 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -1065,27 +1065,6 @@ static struct qeth_cmd_buffer *qeth_l3_get_setassparms_cmd( return iob; } -static int qeth_l3_send_setassparms(struct qeth_card *card, - struct qeth_cmd_buffer *iob, __u16 len, long data, - int (*reply_cb)(struct qeth_card *, struct qeth_reply *, - unsigned long), - void *reply_param) -{ - int rc; - struct qeth_ipa_cmd *cmd; - - QETH_CARD_TEXT(card, 4, "sendassp"); - - cmd = (struct qeth_ipa_cmd *)(iob->data+IPA_PDU_HEADER_SIZE); - if (len <= sizeof(__u32)) - cmd->data.setassparms.data.flags_32bit = (__u32) data; - else /* (len > sizeof(__u32)) */ - memcpy(&cmd->data.setassparms.data, (void *) data, len); - - rc = qeth_send_ipa_cmd(card, iob, reply_cb, reply_param); - return rc; -} - #ifdef CONFIG_QETH_IPV6 static int qeth_l3_send_simple_setassparms_ipv6(struct qeth_card *card, enum qeth_ipa_funcs ipa_func, __u16 cmd_code) @@ -1098,31 +1077,12 @@ static int qeth_l3_send_simple_setassparms_ipv6(struct qeth_card *card, 0, QETH_PROT_IPV6); if (!iob) return -ENOMEM; - rc = qeth_l3_send_setassparms(card, iob, 0, 0, + rc = qeth_send_setassparms(card, iob, 0, 0, qeth_l3_default_setassparms_cb, NULL); return rc; } #endif -static int qeth_l3_send_simple_setassparms(struct qeth_card *card, - enum qeth_ipa_funcs ipa_func, __u16 cmd_code, long data) -{ - int rc; - int length = 0; - struct qeth_cmd_buffer *iob; - - QETH_CARD_TEXT(card, 4, "simassp4"); - if (data) - length = sizeof(__u32); - iob = qeth_l3_get_setassparms_cmd(card, ipa_func, cmd_code, - length, QETH_PROT_IPV4); - if (!iob) - return -ENOMEM; - rc = qeth_l3_send_setassparms(card, iob, length, data, - qeth_l3_default_setassparms_cb, NULL); - return rc; -} - static int qeth_l3_start_ipa_arp_processing(struct qeth_card *card) { int rc; @@ -1135,8 +1095,8 @@ static int qeth_l3_start_ipa_arp_processing(struct qeth_card *card) QETH_CARD_IFNAME(card)); return 0; } - rc = qeth_l3_send_simple_setassparms(card, IPA_ARP_PROCESSING, - IPA_CMD_ASS_START, 0); + rc = qeth_send_simple_setassparms(card, IPA_ARP_PROCESSING, + IPA_CMD_ASS_START, 0); if (rc) { dev_warn(&card->gdev->dev, "Starting ARP processing support for %s failed\n", @@ -1158,7 +1118,7 @@ static int qeth_l3_start_ipa_ip_fragmentation(struct qeth_card *card) return -EOPNOTSUPP; } - rc = qeth_l3_send_simple_setassparms(card, IPA_IP_FRAGMENTATION, + rc = qeth_send_simple_setassparms(card, IPA_IP_FRAGMENTATION, IPA_CMD_ASS_START, 0); if (rc) { dev_warn(&card->gdev->dev, @@ -1183,7 +1143,7 @@ static int qeth_l3_start_ipa_source_mac(struct qeth_card *card) return -EOPNOTSUPP; } - rc = qeth_l3_send_simple_setassparms(card, IPA_SOURCE_MAC, + rc = qeth_send_simple_setassparms(card, IPA_SOURCE_MAC, IPA_CMD_ASS_START, 0); if (rc) dev_warn(&card->gdev->dev, @@ -1204,7 +1164,7 @@ static int qeth_l3_start_ipa_vlan(struct qeth_card *card) return -EOPNOTSUPP; } - rc = qeth_l3_send_simple_setassparms(card, IPA_VLAN_PRIO, + rc = qeth_send_simple_setassparms(card, IPA_VLAN_PRIO, IPA_CMD_ASS_START, 0); if (rc) { dev_warn(&card->gdev->dev, @@ -1229,7 +1189,7 @@ static int qeth_l3_start_ipa_multicast(struct qeth_card *card) return -EOPNOTSUPP; } - rc = qeth_l3_send_simple_setassparms(card, IPA_MULTICASTING, + rc = qeth_send_simple_setassparms(card, IPA_MULTICASTING, IPA_CMD_ASS_START, 0); if (rc) { dev_warn(&card->gdev->dev, @@ -1259,7 +1219,7 @@ static int qeth_l3_softsetup_ipv6(struct qeth_card *card) QETH_CARD_IFNAME(card)); return rc; } - rc = qeth_l3_send_simple_setassparms(card, IPA_IPV6, + rc = qeth_send_simple_setassparms(card, IPA_IPV6, IPA_CMD_ASS_START, 3); if (rc) { dev_err(&card->gdev->dev, @@ -1319,7 +1279,7 @@ static int qeth_l3_start_ipa_broadcast(struct qeth_card *card) rc = -EOPNOTSUPP; goto out; } - rc = qeth_l3_send_simple_setassparms(card, IPA_FILTERING, + rc = qeth_send_simple_setassparms(card, IPA_FILTERING, IPA_CMD_ASS_START, 0); if (rc) { dev_warn(&card->gdev->dev, "Enabling broadcast filtering for " @@ -1327,7 +1287,7 @@ static int qeth_l3_start_ipa_broadcast(struct qeth_card *card) goto out; } - rc = qeth_l3_send_simple_setassparms(card, IPA_FILTERING, + rc = qeth_send_simple_setassparms(card, IPA_FILTERING, IPA_CMD_ASS_CONFIGURE, 1); if (rc) { dev_warn(&card->gdev->dev, @@ -1337,7 +1297,7 @@ static int qeth_l3_start_ipa_broadcast(struct qeth_card *card) } card->info.broadcast_capable = QETH_BROADCAST_WITH_ECHO; dev_info(&card->gdev->dev, "Broadcast enabled\n"); - rc = qeth_l3_send_simple_setassparms(card, IPA_FILTERING, + rc = qeth_send_simple_setassparms(card, IPA_FILTERING, IPA_CMD_ASS_ENABLE, 1); if (rc) { dev_warn(&card->gdev->dev, "Setting up broadcast echo " @@ -1353,84 +1313,18 @@ out: return rc; } -static int qeth_l3_send_checksum_command(struct qeth_card *card) -{ - int rc; - - rc = qeth_l3_send_simple_setassparms(card, IPA_INBOUND_CHECKSUM, - IPA_CMD_ASS_START, 0); - if (rc) { - dev_warn(&card->gdev->dev, "Starting HW checksumming for %s " - "failed, using SW checksumming\n", - QETH_CARD_IFNAME(card)); - return rc; - } - rc = qeth_l3_send_simple_setassparms(card, IPA_INBOUND_CHECKSUM, - IPA_CMD_ASS_ENABLE, - card->info.csum_mask); - if (rc) { - dev_warn(&card->gdev->dev, "Enabling HW checksumming for %s " - "failed, using SW checksumming\n", - QETH_CARD_IFNAME(card)); - return rc; - } - return 0; -} - -static int qeth_l3_set_rx_csum(struct qeth_card *card, int on) -{ - int rc = 0; - - if (on) { - rc = qeth_l3_send_checksum_command(card); - if (rc) - return -EIO; - dev_info(&card->gdev->dev, - "HW Checksumming (inbound) enabled\n"); - } else { - rc = qeth_l3_send_simple_setassparms(card, - IPA_INBOUND_CHECKSUM, IPA_CMD_ASS_STOP, 0); - if (rc) - return -EIO; - } - - return 0; -} - -static int qeth_l3_start_ipa_checksum(struct qeth_card *card) +static void qeth_l3_start_ipa_checksum(struct qeth_card *card) { QETH_CARD_TEXT(card, 3, "strtcsum"); - - if (card->dev->features & NETIF_F_RXCSUM) { - rtnl_lock(); - /* force set_features call */ - card->dev->features &= ~NETIF_F_RXCSUM; - netdev_update_features(card->dev); - rtnl_unlock(); - } - return 0; + if (qeth_is_supported(card, IPA_INBOUND_CHECKSUM) + && (card->dev->features & NETIF_F_RXCSUM)) + qeth_set_rx_csum(card, 1); } -static int qeth_l3_start_ipa_tx_checksum(struct qeth_card *card) +static void qeth_l3_start_ipa_tx_checksum(struct qeth_card *card) { - int rc = 0; - - if (!qeth_is_supported(card, IPA_OUTBOUND_CHECKSUM)) - return rc; - rc = qeth_l3_send_simple_setassparms(card, IPA_OUTBOUND_CHECKSUM, - IPA_CMD_ASS_START, 0); - if (rc) - goto err_out; - rc = qeth_l3_send_simple_setassparms(card, IPA_OUTBOUND_CHECKSUM, - IPA_CMD_ASS_ENABLE, card->info.tx_csum_mask); - if (rc) - goto err_out; - dev_info(&card->gdev->dev, "HW TX Checksumming enabled\n"); - return rc; -err_out: - dev_warn(&card->gdev->dev, "Enabling HW TX checksumming for %s " - "failed, using SW TX checksumming\n", QETH_CARD_IFNAME(card)); - return rc; + QETH_CARD_TEXT(card, 3, "strttxcs"); + qeth_start_ipa_tx_checksum(card); } static int qeth_l3_start_ipa_tso(struct qeth_card *card) @@ -1445,8 +1339,8 @@ static int qeth_l3_start_ipa_tso(struct qeth_card *card) QETH_CARD_IFNAME(card)); rc = -EOPNOTSUPP; } else { - rc = qeth_l3_send_simple_setassparms(card, IPA_OUTBOUND_TSO, - IPA_CMD_ASS_START, 0); + rc = qeth_send_simple_setassparms(card, IPA_OUTBOUND_TSO, + IPA_CMD_ASS_START, 0); if (rc) dev_warn(&card->gdev->dev, "Starting outbound TCP " "segmentation offload for %s failed\n", @@ -1950,7 +1844,6 @@ static inline int qeth_l3_rebuild_skb(struct qeth_card *card, skb->ip_summed = CHECKSUM_NONE; } else skb->ip_summed = CHECKSUM_NONE; - return is_vlan; } @@ -2287,7 +2180,7 @@ static int qeth_l3_arp_set_no_entries(struct qeth_card *card, int no_entries) if (!qeth_is_supported(card, IPA_ARP_PROCESSING)) { return -EOPNOTSUPP; } - rc = qeth_l3_send_simple_setassparms(card, IPA_ARP_PROCESSING, + rc = qeth_send_simple_setassparms(card, IPA_ARP_PROCESSING, IPA_CMD_ASS_ARP_SET_NO_ENTRIES, no_entries); if (rc) { @@ -2552,7 +2445,7 @@ static int qeth_l3_arp_add_entry(struct qeth_card *card, QETH_PROT_IPV4); if (!iob) return -ENOMEM; - rc = qeth_l3_send_setassparms(card, iob, + rc = qeth_send_setassparms(card, iob, sizeof(struct qeth_arp_cache_entry), (unsigned long) entry, qeth_l3_default_setassparms_cb, NULL); @@ -2593,7 +2486,7 @@ static int qeth_l3_arp_remove_entry(struct qeth_card *card, QETH_PROT_IPV4); if (!iob) return -ENOMEM; - rc = qeth_l3_send_setassparms(card, iob, + rc = qeth_send_setassparms(card, iob, 12, (unsigned long)buf, qeth_l3_default_setassparms_cb, NULL); if (rc) { @@ -2624,7 +2517,7 @@ static int qeth_l3_arp_flush_cache(struct qeth_card *card) if (!qeth_is_supported(card, IPA_ARP_PROCESSING)) { return -EOPNOTSUPP; } - rc = qeth_l3_send_simple_setassparms(card, IPA_ARP_PROCESSING, + rc = qeth_send_simple_setassparms(card, IPA_ARP_PROCESSING, IPA_CMD_ASS_ARP_FLUSH_CACHE, 0); if (rc) { tmp = rc; @@ -3187,7 +3080,6 @@ static netdev_features_t qeth_l3_fix_features(struct net_device *dev, features &= ~NETIF_F_TSO; if (!qeth_is_supported(card, IPA_INBOUND_CHECKSUM)) features &= ~NETIF_F_RXCSUM; - return features; } @@ -3204,7 +3096,7 @@ static int qeth_l3_set_features(struct net_device *dev, card->state == CARD_STATE_RECOVER) return 0; - return qeth_l3_set_rx_csum(card, features & NETIF_F_RXCSUM ? 1 : 0); + return qeth_set_rx_csum(card, features & NETIF_F_RXCSUM ? 1 : 0); } static const struct ethtool_ops qeth_l3_ethtool_ops = { diff --git a/drivers/s390/net/smsgiucv.c b/drivers/s390/net/smsgiucv.c index d8f990b6b332..a851d34c642b 100644 --- a/drivers/s390/net/smsgiucv.c +++ b/drivers/s390/net/smsgiucv.c @@ -49,7 +49,7 @@ static DEFINE_SPINLOCK(smsg_list_lock); static LIST_HEAD(smsg_list); static int iucv_path_connected; -static int smsg_path_pending(struct iucv_path *, u8 ipvmid[8], u8 ipuser[16]); +static int smsg_path_pending(struct iucv_path *, u8 *, u8 *); static void smsg_message_pending(struct iucv_path *, struct iucv_message *); static struct iucv_handler smsg_handler = { @@ -57,8 +57,7 @@ static struct iucv_handler smsg_handler = { .message_pending = smsg_message_pending, }; -static int smsg_path_pending(struct iucv_path *path, u8 ipvmid[8], - u8 ipuser[16]) +static int smsg_path_pending(struct iucv_path *path, u8 *ipvmid, u8 *ipuser) { if (strncmp(ipvmid, "*MSG ", 8) != 0) return -EINVAL; diff --git a/drivers/tty/hvc/hvc_iucv.c b/drivers/tty/hvc/hvc_iucv.c index bb809cf36617..8b70a1627356 100644 --- a/drivers/tty/hvc/hvc_iucv.c +++ b/drivers/tty/hvc/hvc_iucv.c @@ -88,8 +88,8 @@ struct iucv_tty_buffer { }; /* IUCV callback handler */ -static int hvc_iucv_path_pending(struct iucv_path *, u8[8], u8[16]); -static void hvc_iucv_path_severed(struct iucv_path *, u8[16]); +static int hvc_iucv_path_pending(struct iucv_path *, u8 *, u8 *); +static void hvc_iucv_path_severed(struct iucv_path *, u8 *); static void hvc_iucv_msg_pending(struct iucv_path *, struct iucv_message *); static void hvc_iucv_msg_complete(struct iucv_path *, struct iucv_message *); @@ -782,8 +782,8 @@ static int hvc_iucv_filter_connreq(u8 ipvmid[8]) * * Locking: struct hvc_iucv_private->lock */ -static int hvc_iucv_path_pending(struct iucv_path *path, - u8 ipvmid[8], u8 ipuser[16]) +static int hvc_iucv_path_pending(struct iucv_path *path, u8 *ipvmid, + u8 *ipuser) { struct hvc_iucv_private *priv, *tmp; u8 wildcard[9] = "lnxhvc "; @@ -881,7 +881,7 @@ out_path_handled: * * Locking: struct hvc_iucv_private->lock */ -static void hvc_iucv_path_severed(struct iucv_path *path, u8 ipuser[16]) +static void hvc_iucv_path_severed(struct iucv_path *path, u8 *ipuser) { struct hvc_iucv_private *priv = path->private; diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index c3a9c8fc60fa..56dcadd83716 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -14,9 +14,10 @@ #define _CAN_DEV_H #include <linux/can.h> -#include <linux/can/netlink.h> #include <linux/can/error.h> #include <linux/can/led.h> +#include <linux/can/netlink.h> +#include <linux/netdevice.h> /* * CAN mode diff --git a/include/linux/can/led.h b/include/linux/can/led.h index 146de4506d21..2746f7c2f87d 100644 --- a/include/linux/can/led.h +++ b/include/linux/can/led.h @@ -11,6 +11,7 @@ #include <linux/if.h> #include <linux/leds.h> +#include <linux/netdevice.h> enum can_led_event { CAN_LED_EVENT_OPEN, diff --git a/include/linux/ieee802154.h b/include/linux/ieee802154.h index 1dc1f4ed4001..db01492814d3 100644 --- a/include/linux/ieee802154.h +++ b/include/linux/ieee802154.h @@ -205,6 +205,31 @@ enum { IEEE802154_SCAN_IN_PROGRESS = 0xfc, }; +/* frame control handling */ +#define IEEE802154_FCTL_FTYPE 0x0003 +#define IEEE802154_FCTL_INTRA_PAN 0x0040 + +#define IEEE802154_FTYPE_DATA 0x0001 + +/* + * ieee802154_is_data - check if type is IEEE802154_FTYPE_DATA + * @fc: frame control bytes in little-endian byteorder + */ +static inline int ieee802154_is_data(__le16 fc) +{ + return (fc & cpu_to_le16(IEEE802154_FCTL_FTYPE)) == + cpu_to_le16(IEEE802154_FTYPE_DATA); +} + +/** + * ieee802154_is_intra_pan - check if intra pan id communication + * @fc: frame control bytes in little-endian byteorder + */ +static inline bool ieee802154_is_intra_pan(__le16 fc) +{ + return fc & cpu_to_le16(IEEE802154_FCTL_INTRA_PAN); +} + /** * ieee802154_is_valid_psdu_len - check if psdu len is valid * available lengths: diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index dad8b00beed2..a338a688ee4a 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -46,6 +46,12 @@ struct br_ip_list { #define BR_LEARNING_SYNC BIT(9) #define BR_PROXYARP_WIFI BIT(10) +/* values as per ieee8021QBridgeFdbAgingTime */ +#define BR_MIN_AGEING_TIME (10 * HZ) +#define BR_MAX_AGEING_TIME (1000000 * HZ) + +#define BR_DEFAULT_AGEING_TIME (300 * HZ) + extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __user *)); typedef int br_should_route_hook_t(struct sk_buff *skb); diff --git a/include/linux/igmp.h b/include/linux/igmp.h index 908429216d9f..9c9de11549a7 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -110,7 +110,7 @@ struct ip_mc_list { #define IGMPV3_QQIC(value) IGMPV3_EXP(0x80, 4, 3, value) #define IGMPV3_MRC(value) IGMPV3_EXP(0x80, 4, 3, value) -extern int ip_check_mc_rcu(struct in_device *dev, __be32 mc_addr, __be32 src_addr, u16 proto); +extern int ip_check_mc_rcu(struct in_device *dev, __be32 mc_addr, __be32 src_addr, u8 proto); extern int igmp_rcv(struct sk_buff *); extern int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr); extern int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr); diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 250b1ff8b48d..2a0b95662548 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -429,7 +429,7 @@ struct health_buffer { __be32 rsvd2; u8 irisc_index; u8 synd; - __be16 ext_sync; + __be16 ext_synd; }; struct mlx5_init_seg { diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2d15e3831440..b9450784ae06 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1258,7 +1258,7 @@ struct net_device_ops { * @IFF_LIVE_ADDR_CHANGE: device supports hardware address * change when it's running * @IFF_MACVLAN: Macvlan device - * @IFF_VRF_MASTER: device is a VRF master + * @IFF_L3MDEV_MASTER: device is an L3 master device * @IFF_NO_QUEUE: device can run without qdisc attached * @IFF_OPENVSWITCH: device is a Open vSwitch master */ @@ -1283,7 +1283,7 @@ enum netdev_priv_flags { IFF_XMIT_DST_RELEASE_PERM = 1<<17, IFF_IPVLAN_MASTER = 1<<18, IFF_IPVLAN_SLAVE = 1<<19, - IFF_VRF_MASTER = 1<<20, + IFF_L3MDEV_MASTER = 1<<20, IFF_NO_QUEUE = 1<<21, IFF_OPENVSWITCH = 1<<22, }; @@ -1308,7 +1308,7 @@ enum netdev_priv_flags { #define IFF_XMIT_DST_RELEASE_PERM IFF_XMIT_DST_RELEASE_PERM #define IFF_IPVLAN_MASTER IFF_IPVLAN_MASTER #define IFF_IPVLAN_SLAVE IFF_IPVLAN_SLAVE -#define IFF_VRF_MASTER IFF_VRF_MASTER +#define IFF_L3MDEV_MASTER IFF_L3MDEV_MASTER #define IFF_NO_QUEUE IFF_NO_QUEUE #define IFF_OPENVSWITCH IFF_OPENVSWITCH @@ -1427,7 +1427,6 @@ enum netdev_priv_flags { * @dn_ptr: DECnet specific data * @ip6_ptr: IPv6 specific data * @ax25_ptr: AX.25 specific data - * @vrf_ptr: VRF specific data * @ieee80211_ptr: IEEE 802.11 specific data, assign before registering * * @last_rx: Time of last Rx @@ -1587,6 +1586,9 @@ struct net_device { #ifdef CONFIG_NET_SWITCHDEV const struct switchdev_ops *switchdev_ops; #endif +#ifdef CONFIG_NET_L3_MASTER_DEV + const struct l3mdev_ops *l3mdev_ops; +#endif const struct header_ops *header_ops; @@ -1646,7 +1648,6 @@ struct net_device { struct dn_dev __rcu *dn_ptr; struct inet6_dev __rcu *ip6_ptr; void *ax25_ptr; - struct net_vrf_dev __rcu *vrf_ptr; struct wireless_dev *ieee80211_ptr; struct wpan_dev *ieee802154_ptr; #if IS_ENABLED(CONFIG_MPLS_ROUTING) @@ -2213,12 +2214,8 @@ int dev_open(struct net_device *dev); int dev_close(struct net_device *dev); int dev_close_many(struct list_head *head, bool unlink); void dev_disable_lro(struct net_device *dev); -int dev_loopback_xmit(struct sock *sk, struct sk_buff *newskb); -int dev_queue_xmit_sk(struct sock *sk, struct sk_buff *skb); -static inline int dev_queue_xmit(struct sk_buff *skb) -{ - return dev_queue_xmit_sk(skb->sk, skb); -} +int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb); +int dev_queue_xmit(struct sk_buff *skb); int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv); int register_netdevice(struct net_device *dev); void unregister_netdevice_queue(struct net_device *dev, struct list_head *head); @@ -2990,11 +2987,7 @@ static inline void dev_consume_skb_any(struct sk_buff *skb) int netif_rx(struct sk_buff *skb); int netif_rx_ni(struct sk_buff *skb); -int netif_receive_skb_sk(struct sock *sk, struct sk_buff *skb); -static inline int netif_receive_skb(struct sk_buff *skb) -{ - return netif_receive_skb_sk(skb->sk, skb); -} +int netif_receive_skb(struct sk_buff *skb); gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb); void napi_gro_flush(struct napi_struct *napi, bool flush_old); struct sk_buff *napi_get_frags(struct napi_struct *napi); @@ -3832,9 +3825,9 @@ static inline bool netif_supports_nofcs(struct net_device *dev) return dev->priv_flags & IFF_SUPP_NOFCS; } -static inline bool netif_is_vrf(const struct net_device *dev) +static inline bool netif_is_l3_master(const struct net_device *dev) { - return dev->priv_flags & IFF_VRF_MASTER; + return dev->priv_flags & IFF_L3MDEV_MASTER; } static inline bool netif_is_bridge_master(const struct net_device *dev) @@ -3847,27 +3840,6 @@ static inline bool netif_is_ovs_master(const struct net_device *dev) return dev->priv_flags & IFF_OPENVSWITCH; } -static inline bool netif_index_is_vrf(struct net *net, int ifindex) -{ - bool rc = false; - -#if IS_ENABLED(CONFIG_NET_VRF) - struct net_device *dev; - - if (ifindex == 0) - return false; - - rcu_read_lock(); - - dev = dev_get_by_index_rcu(net, ifindex); - if (dev) - rc = netif_is_vrf(dev); - - rcu_read_unlock(); -#endif - return rc; -} - /* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */ static inline void netif_keep_dst(struct net_device *dev) { diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 36a652531791..165ab2d14734 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -54,8 +54,9 @@ struct nf_hook_state { struct net_device *in; struct net_device *out; struct sock *sk; + struct net *net; struct list_head *hook_list; - int (*okfn)(struct sock *, struct sk_buff *); + int (*okfn)(struct net *, struct sock *, struct sk_buff *); }; static inline void nf_hook_state_init(struct nf_hook_state *p, @@ -65,7 +66,8 @@ static inline void nf_hook_state_init(struct nf_hook_state *p, struct net_device *indev, struct net_device *outdev, struct sock *sk, - int (*okfn)(struct sock *, struct sk_buff *)) + struct net *net, + int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { p->hook = hook; p->thresh = thresh; @@ -73,11 +75,12 @@ static inline void nf_hook_state_init(struct nf_hook_state *p, p->in = indev; p->out = outdev; p->sk = sk; + p->net = net; p->hook_list = hook_list; p->okfn = okfn; } -typedef unsigned int nf_hookfn(const struct nf_hook_ops *ops, +typedef unsigned int nf_hookfn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); @@ -167,32 +170,32 @@ int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state); * value indicates the packet has been consumed by the hook. */ static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook, + struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *indev, struct net_device *outdev, - int (*okfn)(struct sock *, struct sk_buff *), + int (*okfn)(struct net *, struct sock *, struct sk_buff *), int thresh) { - struct net *net = dev_net(indev ? indev : outdev); struct list_head *hook_list = &net->nf.hooks[pf][hook]; if (nf_hook_list_active(hook_list, pf, hook)) { struct nf_hook_state state; nf_hook_state_init(&state, hook_list, hook, thresh, - pf, indev, outdev, sk, okfn); + pf, indev, outdev, sk, net, okfn); return nf_hook_slow(skb, &state); } return 1; } -static inline int nf_hook(u_int8_t pf, unsigned int hook, struct sock *sk, - struct sk_buff *skb, struct net_device *indev, - struct net_device *outdev, - int (*okfn)(struct sock *, struct sk_buff *)) +static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, + struct sock *sk, struct sk_buff *skb, + struct net_device *indev, struct net_device *outdev, + int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { - return nf_hook_thresh(pf, hook, sk, skb, indev, outdev, okfn, INT_MIN); + return nf_hook_thresh(pf, hook, net, sk, skb, indev, outdev, okfn, INT_MIN); } /* Activate hook; either okfn or kfree_skb called, unless a hook @@ -213,36 +216,38 @@ static inline int nf_hook(u_int8_t pf, unsigned int hook, struct sock *sk, */ static inline int -NF_HOOK_THRESH(uint8_t pf, unsigned int hook, struct sock *sk, +NF_HOOK_THRESH(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *in, struct net_device *out, - int (*okfn)(struct sock *, struct sk_buff *), int thresh) + int (*okfn)(struct net *, struct sock *, struct sk_buff *), + int thresh) { - int ret = nf_hook_thresh(pf, hook, sk, skb, in, out, okfn, thresh); + int ret = nf_hook_thresh(pf, hook, net, sk, skb, in, out, okfn, thresh); if (ret == 1) - ret = okfn(sk, skb); + ret = okfn(net, sk, skb); return ret; } static inline int -NF_HOOK_COND(uint8_t pf, unsigned int hook, struct sock *sk, +NF_HOOK_COND(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *in, struct net_device *out, - int (*okfn)(struct sock *, struct sk_buff *), bool cond) + int (*okfn)(struct net *, struct sock *, struct sk_buff *), + bool cond) { int ret; if (!cond || - ((ret = nf_hook_thresh(pf, hook, sk, skb, in, out, okfn, INT_MIN)) == 1)) - ret = okfn(sk, skb); + ((ret = nf_hook_thresh(pf, hook, net, sk, skb, in, out, okfn, INT_MIN)) == 1)) + ret = okfn(net, sk, skb); return ret; } static inline int -NF_HOOK(uint8_t pf, unsigned int hook, struct sock *sk, struct sk_buff *skb, +NF_HOOK(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *in, struct net_device *out, - int (*okfn)(struct sock *, struct sk_buff *)) + int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { - return NF_HOOK_THRESH(pf, hook, sk, skb, in, out, okfn, INT_MIN); + return NF_HOOK_THRESH(pf, hook, net, sk, skb, in, out, okfn, INT_MIN); } /* Call setsockopt() */ @@ -278,7 +283,7 @@ struct nf_afinfo { struct flowi *fl, bool strict); void (*saveroute)(const struct sk_buff *skb, struct nf_queue_entry *entry); - int (*reroute)(struct sk_buff *skb, + int (*reroute)(struct net *net, struct sk_buff *skb, const struct nf_queue_entry *entry); int route_key_size; }; @@ -342,21 +347,12 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) } #else /* !CONFIG_NETFILTER */ -#define NF_HOOK(pf, hook, sk, skb, indev, outdev, okfn) (okfn)(sk, skb) -#define NF_HOOK_COND(pf, hook, sk, skb, indev, outdev, okfn, cond) (okfn)(sk, skb) -static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook, - struct sock *sk, - struct sk_buff *skb, - struct net_device *indev, - struct net_device *outdev, - int (*okfn)(struct sock *sk, struct sk_buff *), int thresh) -{ - return okfn(sk, skb); -} -static inline int nf_hook(u_int8_t pf, unsigned int hook, struct sock *sk, - struct sk_buff *skb, struct net_device *indev, - struct net_device *outdev, - int (*okfn)(struct sock *, struct sk_buff *)) +#define NF_HOOK(pf, hook, net, sk, skb, indev, outdev, okfn) (okfn)(net, sk, skb) +#define NF_HOOK_COND(pf, hook, net, sk, skb, indev, outdev, okfn, cond) (okfn)(net, sk, skb) +static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net, + struct sock *sk, struct sk_buff *skb, + struct net_device *indev, struct net_device *outdev, + int (*okfn)(struct net *, struct sock *, struct sk_buff *)) { return 1; } diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index b006b719183f..c5577410c25d 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -13,6 +13,7 @@ * @target: the target extension * @matchinfo: per-match data * @targetinfo: per-target data + * @net network namespace through which the action was invoked * @in: input netdevice * @out: output netdevice * @fragoff: packet is a fragment, this is the data offset @@ -24,7 +25,6 @@ * Fields written to by extensions: * * @hotdrop: drop packet if we had inspection problems - * Network namespace obtainable using dev_net(in/out) */ struct xt_action_param { union { @@ -34,6 +34,7 @@ struct xt_action_param { union { const void *matchinfo, *targinfo; }; + struct net *net; const struct net_device *in, *out; int fragoff; unsigned int thoff; diff --git a/include/linux/netfilter_arp/arp_tables.h b/include/linux/netfilter_arp/arp_tables.h index c22a7fb8d0df..6f074db2f23d 100644 --- a/include/linux/netfilter_arp/arp_tables.h +++ b/include/linux/netfilter_arp/arp_tables.h @@ -53,7 +53,6 @@ extern struct xt_table *arpt_register_table(struct net *net, const struct arpt_replace *repl); extern void arpt_unregister_table(struct xt_table *table); extern unsigned int arpt_do_table(struct sk_buff *skb, - unsigned int hook, const struct nf_hook_state *state, struct xt_table *table); diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h index 2437b8a5d7a9..2ed40c402b5e 100644 --- a/include/linux/netfilter_bridge.h +++ b/include/linux/netfilter_bridge.h @@ -17,7 +17,7 @@ enum nf_br_hook_priorities { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) -int br_handle_frame_finish(struct sock *sk, struct sk_buff *skb); +int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb); static inline void br_drop_fake_rtable(struct sk_buff *skb) { diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index 8ca6d6464ea3..2ea517c7c6b9 100644 --- a/include/linux/netfilter_bridge/ebtables.h +++ b/include/linux/netfilter_bridge/ebtables.h @@ -111,9 +111,9 @@ struct ebt_table { extern struct ebt_table *ebt_register_table(struct net *net, const struct ebt_table *table); extern void ebt_unregister_table(struct net *net, struct ebt_table *table); -extern unsigned int ebt_do_table(unsigned int hook, struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, - struct ebt_table *table); +extern unsigned int ebt_do_table(struct sk_buff *skb, + const struct nf_hook_state *state, + struct ebt_table *table); /* Used in the kernel match() functions */ #define FWINV(bool,invflg) ((bool) ^ !!(info->invflags & invflg)) diff --git a/include/linux/netfilter_ingress.h b/include/linux/netfilter_ingress.h index cb0727fe2b3d..187feabe557c 100644 --- a/include/linux/netfilter_ingress.h +++ b/include/linux/netfilter_ingress.h @@ -17,7 +17,7 @@ static inline int nf_hook_ingress(struct sk_buff *skb) nf_hook_state_init(&state, &skb->dev->nf_hooks_ingress, NF_NETDEV_INGRESS, INT_MIN, NFPROTO_NETDEV, NULL, - skb->dev, NULL, NULL); + skb->dev, NULL, dev_net(skb->dev), NULL); return nf_hook_slow(skb, &state); } diff --git a/include/linux/netfilter_ipv4.h b/include/linux/netfilter_ipv4.h index 6e4591bb54d4..98c03b2462b5 100644 --- a/include/linux/netfilter_ipv4.h +++ b/include/linux/netfilter_ipv4.h @@ -6,7 +6,7 @@ #include <uapi/linux/netfilter_ipv4.h> -int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type); +int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned addr_type); __sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol); #endif /*__LINUX_IP_NETFILTER_H*/ diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index 4073510da485..aa598f942c01 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -64,7 +64,6 @@ struct ipt_error { extern void *ipt_alloc_initial_table(const struct xt_table *); extern unsigned int ipt_do_table(struct sk_buff *skb, - unsigned int hook, const struct nf_hook_state *state, struct xt_table *table); diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index 771574677e83..2ac8369fa96c 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -22,7 +22,7 @@ struct nf_ipv6_ops { }; #ifdef CONFIG_NETFILTER -int ip6_route_me_harder(struct sk_buff *skb); +int ip6_route_me_harder(struct net *net, struct sk_buff *skb); __sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol); diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index b40d2b635778..0f76e5c674f9 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -30,7 +30,6 @@ extern struct xt_table *ip6t_register_table(struct net *net, const struct ip6t_replace *repl); extern void ip6t_unregister_table(struct net *net, struct xt_table *table); extern unsigned int ip6t_do_table(struct sk_buff *skb, - unsigned int hook, const struct nf_hook_state *state, struct xt_table *table); diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 48c3696e8645..e442e6e9a365 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -112,10 +112,11 @@ struct tcp_request_sock_ops; struct tcp_request_sock { struct inet_request_sock req; const struct tcp_request_sock_ops *af_specific; + struct skb_mstamp snt_synack; /* first SYNACK sent time */ bool tfo_listener; + u32 txhash; u32 rcv_isn; u32 snt_isn; - u32 snt_synack; /* synack sent time */ u32 last_oow_ack_time; /* last SYNACK */ u32 rcv_nxt; /* the ack # by SYNACK. For * FastOpen it's the seq# @@ -381,25 +382,11 @@ static inline bool tcp_passive_fastopen(const struct sock *sk) tcp_sk(sk)->fastopen_rsk != NULL); } -extern void tcp_sock_destruct(struct sock *sk); - -static inline int fastopen_init_queue(struct sock *sk, int backlog) +static inline void fastopen_queue_tune(struct sock *sk, int backlog) { - struct request_sock_queue *queue = - &inet_csk(sk)->icsk_accept_queue; - - if (queue->fastopenq == NULL) { - queue->fastopenq = kzalloc( - sizeof(struct fastopen_queue), - sk->sk_allocation); - if (queue->fastopenq == NULL) - return -ENOMEM; - - sk->sk_destruct = tcp_sock_destruct; - spin_lock_init(&queue->fastopenq->lock); - } - queue->fastopenq->max_qlen = backlog; - return 0; + struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; + + queue->fastopenq.max_qlen = backlog; } static inline void tcp_saved_syn_free(struct tcp_sock *tp) diff --git a/include/linux/usb/cdc.h b/include/linux/usb/cdc.h new file mode 100644 index 000000000000..b5706f94ee9e --- /dev/null +++ b/include/linux/usb/cdc.h @@ -0,0 +1,51 @@ +/* + * USB CDC common helpers + * + * Copyright (c) 2015 Oliver Neukum <oneukum@suse.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + */ +#ifndef __LINUX_USB_CDC_H +#define __LINUX_USB_CDC_H + +#include <uapi/linux/usb/cdc.h> + +/* + * inofficial magic numbers + */ + +#define CDC_PHONET_MAGIC_NUMBER 0xAB + +/* + * parsing CDC headers + */ + +struct usb_cdc_parsed_header { + struct usb_cdc_union_desc *usb_cdc_union_desc; + struct usb_cdc_header_desc *usb_cdc_header_desc; + + struct usb_cdc_call_mgmt_descriptor *usb_cdc_call_mgmt_descriptor; + struct usb_cdc_acm_descriptor *usb_cdc_acm_descriptor; + struct usb_cdc_country_functional_desc *usb_cdc_country_functional_desc; + struct usb_cdc_network_terminal_desc *usb_cdc_network_terminal_desc; + struct usb_cdc_ether_desc *usb_cdc_ether_desc; + struct usb_cdc_dmm_desc *usb_cdc_dmm_desc; + struct usb_cdc_mdlm_desc *usb_cdc_mdlm_desc; + struct usb_cdc_mdlm_detail_desc *usb_cdc_mdlm_detail_desc; + struct usb_cdc_obex_desc *usb_cdc_obex_desc; + struct usb_cdc_ncm_desc *usb_cdc_ncm_desc; + struct usb_cdc_mbim_desc *usb_cdc_mbim_desc; + struct usb_cdc_mbim_extended_desc *usb_cdc_mbim_extended_desc; + + bool phonet_magic_present; +}; + +struct usb_interface; +int cdc_parse_cdc_header(struct usb_cdc_parsed_header *hdr, + struct usb_interface *intf, + u8 *buffer, + int buflen); + +#endif /* __LINUX_USB_CDC_H */ diff --git a/include/net/6lowpan.h b/include/net/6lowpan.h index a2f59ec98d24..eeae5eb58754 100644 --- a/include/net/6lowpan.h +++ b/include/net/6lowpan.h @@ -126,13 +126,19 @@ (((a)[6]) == 0xFF) && \ (((a)[7]) == 0xFF)) -#define LOWPAN_DISPATCH_IPV6 0x41 /* 01000001 = 65 */ -#define LOWPAN_DISPATCH_HC1 0x42 /* 01000010 = 66 */ -#define LOWPAN_DISPATCH_IPHC 0x60 /* 011xxxxx = ... */ -#define LOWPAN_DISPATCH_FRAG1 0xc0 /* 11000xxx */ -#define LOWPAN_DISPATCH_FRAGN 0xe0 /* 11100xxx */ +#define LOWPAN_DISPATCH_IPV6 0x41 /* 01000001 = 65 */ +#define LOWPAN_DISPATCH_IPHC 0x60 /* 011xxxxx = ... */ +#define LOWPAN_DISPATCH_IPHC_MASK 0xe0 -#define LOWPAN_DISPATCH_MASK 0xf8 /* 11111000 */ +static inline bool lowpan_is_ipv6(u8 dispatch) +{ + return dispatch == LOWPAN_DISPATCH_IPV6; +} + +static inline bool lowpan_is_iphc(u8 dispatch) +{ + return (dispatch & LOWPAN_DISPATCH_IPHC_MASK) == LOWPAN_DISPATCH_IPHC; +} #define LOWPAN_FRAG_TIMEOUT (HZ * 60) /* time-out 60 sec */ @@ -218,6 +224,19 @@ struct lowpan_priv *lowpan_priv(const struct net_device *dev) return netdev_priv(dev); } +struct lowpan_802154_cb { + u16 d_tag; + unsigned int d_size; + u8 d_offset; +}; + +static inline +struct lowpan_802154_cb *lowpan_802154_cb(const struct sk_buff *skb) +{ + BUILD_BUG_ON(sizeof(struct lowpan_802154_cb) > sizeof(skb->cb)); + return (struct lowpan_802154_cb *)skb->cb; +} + #ifdef DEBUG /* print data in line */ static inline void raw_dump_inline(const char *caller, char *msg, @@ -280,119 +299,6 @@ static inline void lowpan_push_hc_data(u8 **hc_ptr, const void *data, *hc_ptr += len; } -static inline u8 lowpan_addr_mode_size(const u8 addr_mode) -{ - static const u8 addr_sizes[] = { - [LOWPAN_IPHC_ADDR_00] = 16, - [LOWPAN_IPHC_ADDR_01] = 8, - [LOWPAN_IPHC_ADDR_02] = 2, - [LOWPAN_IPHC_ADDR_03] = 0, - }; - return addr_sizes[addr_mode]; -} - -static inline u8 lowpan_next_hdr_size(const u8 h_enc, u16 *uncomp_header) -{ - u8 ret = 1; - - if ((h_enc & LOWPAN_NHC_UDP_MASK) == LOWPAN_NHC_UDP_ID) { - *uncomp_header += sizeof(struct udphdr); - - switch (h_enc & LOWPAN_NHC_UDP_CS_P_11) { - case LOWPAN_NHC_UDP_CS_P_00: - ret += 4; - break; - case LOWPAN_NHC_UDP_CS_P_01: - case LOWPAN_NHC_UDP_CS_P_10: - ret += 3; - break; - case LOWPAN_NHC_UDP_CS_P_11: - ret++; - break; - default: - break; - } - - if (!(h_enc & LOWPAN_NHC_UDP_CS_C)) - ret += 2; - } - - return ret; -} - -/** - * lowpan_uncompress_size - returns skb->len size with uncompressed header - * @skb: sk_buff with 6lowpan header inside - * @datagram_offset: optional to get the datagram_offset value - * - * Returns the skb->len with uncompressed header - */ -static inline u16 -lowpan_uncompress_size(const struct sk_buff *skb, u16 *dgram_offset) -{ - u16 ret = 2, uncomp_header = sizeof(struct ipv6hdr); - u8 iphc0, iphc1, h_enc; - - iphc0 = skb_network_header(skb)[0]; - iphc1 = skb_network_header(skb)[1]; - - switch ((iphc0 & LOWPAN_IPHC_TF) >> 3) { - case 0: - ret += 4; - break; - case 1: - ret += 3; - break; - case 2: - ret++; - break; - default: - break; - } - - if (!(iphc0 & LOWPAN_IPHC_NH_C)) - ret++; - - if (!(iphc0 & 0x03)) - ret++; - - ret += lowpan_addr_mode_size((iphc1 & LOWPAN_IPHC_SAM) >> - LOWPAN_IPHC_SAM_BIT); - - if (iphc1 & LOWPAN_IPHC_M) { - switch ((iphc1 & LOWPAN_IPHC_DAM_11) >> - LOWPAN_IPHC_DAM_BIT) { - case LOWPAN_IPHC_DAM_00: - ret += 16; - break; - case LOWPAN_IPHC_DAM_01: - ret += 6; - break; - case LOWPAN_IPHC_DAM_10: - ret += 4; - break; - case LOWPAN_IPHC_DAM_11: - ret++; - break; - default: - break; - } - } else { - ret += lowpan_addr_mode_size((iphc1 & LOWPAN_IPHC_DAM_11) >> - LOWPAN_IPHC_DAM_BIT); - } - - if (iphc0 & LOWPAN_IPHC_NH_C) { - h_enc = skb_network_header(skb)[ret]; - ret += lowpan_next_hdr_size(h_enc, &uncomp_header); - } - - if (dgram_offset) - *dgram_offset = uncomp_header; - - return skb->len + uncomp_header - ret; -} - void lowpan_netdev_setup(struct net_device *dev, enum lowpan_lltypes lltype); int diff --git a/include/net/addrconf.h b/include/net/addrconf.h index b5474b1fcd83..78003dfb8539 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -192,8 +192,7 @@ struct ipv6_stub { int (*ipv6_dst_lookup)(struct net *net, struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6); void (*udpv6_encap_enable)(void); - void (*ndisc_send_na)(struct net_device *dev, struct neighbour *neigh, - const struct in6_addr *daddr, + void (*ndisc_send_na)(struct net_device *dev, const struct in6_addr *daddr, const struct in6_addr *solicited_addr, bool router, bool solicited, bool override, bool inc_opt); struct neigh_table *nd_tbl; diff --git a/include/net/af_ieee802154.h b/include/net/af_ieee802154.h index 7d38e2ffd256..a5563d27a3eb 100644 --- a/include/net/af_ieee802154.h +++ b/include/net/af_ieee802154.h @@ -1,5 +1,5 @@ /* - * IEEE 802.15.4 inteface for userspace + * IEEE 802.15.4 interface for userspace * * Copyright 2007, 2008 Siemens AG * diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 38d8a34d3589..f5ade8573393 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -123,11 +123,22 @@ __printf(1, 2) void bt_info(const char *fmt, ...); __printf(1, 2) void bt_err(const char *fmt, ...); +__printf(1, 2) +void bt_err_ratelimited(const char *fmt, ...); #define BT_INFO(fmt, ...) bt_info(fmt "\n", ##__VA_ARGS__) #define BT_ERR(fmt, ...) bt_err(fmt "\n", ##__VA_ARGS__) #define BT_DBG(fmt, ...) pr_debug(fmt "\n", ##__VA_ARGS__) +#define BT_ERR_RATELIMITED(fmt, ...) bt_err_ratelimited(fmt "\n", ##__VA_ARGS__) + +#define bt_dev_info(hdev, fmt, ...) \ + BT_INFO("%s: " fmt, (hdev)->name, ##__VA_ARGS__) +#define bt_dev_err(hdev, fmt, ...) \ + BT_ERR("%s: " fmt, (hdev)->name, ##__VA_ARGS__) +#define bt_dev_dbg(hdev, fmt, ...) \ + BT_DBG("%s: " fmt, (hdev)->name, ##__VA_ARGS__) + /* Connection and socket states */ enum { BT_CONNECTED = 1, /* Equal to TCP_ESTABLISHED to make net code happy */ diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 9e1a59e01fa2..256e6734c1fb 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -987,6 +987,7 @@ int hci_resume_dev(struct hci_dev *hdev); int hci_reset_dev(struct hci_dev *hdev); int hci_dev_open(__u16 dev); int hci_dev_close(__u16 dev); +int hci_dev_do_close(struct hci_dev *hdev); int hci_dev_reset(__u16 dev); int hci_dev_reset_stat(__u16 dev); int hci_dev_cmd(unsigned int cmd, void __user *arg); diff --git a/include/net/dn_neigh.h b/include/net/dn_neigh.h index d0424269313f..5e902fc3f4eb 100644 --- a/include/net/dn_neigh.h +++ b/include/net/dn_neigh.h @@ -18,11 +18,11 @@ struct dn_neigh { void dn_neigh_init(void); void dn_neigh_cleanup(void); -int dn_neigh_router_hello(struct sock *sk, struct sk_buff *skb); -int dn_neigh_endnode_hello(struct sock *sk, struct sk_buff *skb); +int dn_neigh_router_hello(struct net *net, struct sock *sk, struct sk_buff *skb); +int dn_neigh_endnode_hello(struct net *net, struct sock *sk, struct sk_buff *skb); void dn_neigh_pointopoint_hello(struct sk_buff *skb); int dn_neigh_elist(struct net_device *dev, unsigned char *ptr, int n); -int dn_to_neigh_output(struct sock *sk, struct sk_buff *skb); +int dn_to_neigh_output(struct net *net, struct sock *sk, struct sk_buff *skb); extern struct neigh_table dn_neigh_table; diff --git a/include/net/dst.h b/include/net/dst.h index 9261d928303d..779206c15f8b 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -454,13 +454,13 @@ static inline void dst_set_expires(struct dst_entry *dst, int timeout) } /* Output packet to network from transport. */ -static inline int dst_output_sk(struct sock *sk, struct sk_buff *skb) +static inline int dst_output(struct sock *sk, struct sk_buff *skb) { return skb_dst(skb)->output(sk, skb); } -static inline int dst_output(struct sk_buff *skb) +static inline int dst_output_okfn(struct net *net, struct sock *sk, struct sk_buff *skb) { - return dst_output_sk(skb->sk, skb); + return dst_output(sk, skb); } /* Input packet from network to transport. */ @@ -489,7 +489,8 @@ struct flowi; #ifndef CONFIG_XFRM static inline struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, - const struct flowi *fl, struct sock *sk, + const struct flowi *fl, + const struct sock *sk, int flags) { return dst_orig; @@ -498,7 +499,7 @@ static inline struct dst_entry *xfrm_lookup(struct net *net, static inline struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, - struct sock *sk, + const struct sock *sk, int flags) { return dst_orig; @@ -511,11 +512,11 @@ static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst) #else struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, - const struct flowi *fl, struct sock *sk, + const struct flowi *fl, const struct sock *sk, int flags); struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, - const struct flowi *fl, struct sock *sk, + const struct flowi *fl, const struct sock *sk, int flags); /* skb attached with this dst needs transformation if dst->xfrm is valid */ diff --git a/include/net/ethoc.h b/include/net/ethoc.h index 2a2d6bb34eb8..bb7f467da7fc 100644 --- a/include/net/ethoc.h +++ b/include/net/ethoc.h @@ -17,6 +17,7 @@ struct ethoc_platform_data { u8 hwaddr[IFHWADDRLEN]; s8 phy_id; u32 eth_clkfreq; + bool big_endian; }; #endif /* !LINUX_NET_ETHOC_H */ diff --git a/include/net/genetlink.h b/include/net/genetlink.h index a9af1cc8c1bc..1b6b6dcb018d 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -183,9 +183,8 @@ _genl_register_family_with_ops_grps(struct genl_family *family, (grps), ARRAY_SIZE(grps)) int genl_unregister_family(struct genl_family *family); -void genl_notify(struct genl_family *family, - struct sk_buff *skb, struct net *net, u32 portid, - u32 group, struct nlmsghdr *nlh, gfp_t flags); +void genl_notify(struct genl_family *family, struct sk_buff *skb, + struct genl_info *info, u32 group, gfp_t flags); struct sk_buff *genlmsg_new_unicast(size_t payload, struct genl_info *info, gfp_t flags); diff --git a/include/net/inet6_connection_sock.h b/include/net/inet6_connection_sock.h index 6d539e4e5ba7..79b2a4c09ca6 100644 --- a/include/net/inet6_connection_sock.h +++ b/include/net/inet6_connection_sock.h @@ -25,8 +25,8 @@ struct sockaddr; int inet6_csk_bind_conflict(const struct sock *sk, const struct inet_bind_bucket *tb, bool relax); -struct dst_entry *inet6_csk_route_req(struct sock *sk, struct flowi6 *fl6, - const struct request_sock *req); +struct dst_entry *inet6_csk_route_req(const struct sock *sk, struct flowi6 *fl6, + const struct request_sock *req, u8 proto); struct request_sock *inet6_csk_search_req(struct sock *sk, const __be16 rport, diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 0320bbb7d7b5..ee54f21a8113 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -41,7 +41,7 @@ struct inet_connection_sock_af_ops { int (*rebuild_header)(struct sock *sk); void (*sk_rx_dst_set)(struct sock *sk, const struct sk_buff *skb); int (*conn_request)(struct sock *sk, struct sk_buff *skb); - struct sock *(*syn_recv_sock)(struct sock *sk, struct sk_buff *skb, + struct sock *(*syn_recv_sock)(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst); u16 net_header_len; @@ -266,9 +266,10 @@ int inet_csk_bind_conflict(const struct sock *sk, const struct inet_bind_bucket *tb, bool relax); int inet_csk_get_port(struct sock *sk, unsigned short snum); -struct dst_entry *inet_csk_route_req(struct sock *sk, struct flowi4 *fl4, +struct dst_entry *inet_csk_route_req(const struct sock *sk, struct flowi4 *fl4, const struct request_sock *req); -struct dst_entry *inet_csk_route_child_sock(struct sock *sk, struct sock *newsk, +struct dst_entry *inet_csk_route_child_sock(const struct sock *sk, + struct sock *newsk, const struct request_sock *req); static inline void inet_csk_reqsk_queue_add(struct sock *sk, diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index b07d126694a7..3fb778d7c875 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -199,7 +199,7 @@ static inline int inet_sk_listen_hashfn(const struct sock *sk) } /* Caller must disable local BH processing. */ -int __inet_inherit_port(struct sock *sk, struct sock *child); +int __inet_inherit_port(const struct sock *sk, struct sock *child); void inet_put_port(struct sock *sk); diff --git a/include/net/ip.h b/include/net/ip.h index 9b9ca2839399..91a6b2c88341 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -100,7 +100,7 @@ int igmp_mc_init(void); * Functions provided by ip.c */ -int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk, +int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, __be32 saddr, __be32 daddr, struct ip_options_rcu *opt); int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, @@ -282,10 +282,12 @@ int ip_decrease_ttl(struct iphdr *iph) } static inline -int ip_dont_fragment(struct sock *sk, struct dst_entry *dst) +int ip_dont_fragment(const struct sock *sk, const struct dst_entry *dst) { - return inet_sk(sk)->pmtudisc == IP_PMTUDISC_DO || - (inet_sk(sk)->pmtudisc == IP_PMTUDISC_WANT && + u8 pmtudisc = READ_ONCE(inet_sk(sk)->pmtudisc); + + return pmtudisc == IP_PMTUDISC_DO || + (pmtudisc == IP_PMTUDISC_WANT && !(dst_metric_locked(dst, RTAX_MTU))); } diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 9b9ca87a4210..0816c872b689 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -29,65 +29,15 @@ #endif #include <net/net_namespace.h> /* Netw namespace */ +#define IP_VS_HDR_INVERSE 1 +#define IP_VS_HDR_ICMP 2 + /* Generic access of ipvs struct */ static inline struct netns_ipvs *net_ipvs(struct net* net) { return net->ipvs; } -/* Get net ptr from skb in traffic cases - * use skb_sknet when call is from userland (ioctl or netlink) - */ -static inline struct net *skb_net(const struct sk_buff *skb) -{ -#ifdef CONFIG_NET_NS -#ifdef CONFIG_IP_VS_DEBUG - /* - * This is used for debug only. - * Start with the most likely hit - * End with BUG - */ - if (likely(skb->dev && dev_net(skb->dev))) - return dev_net(skb->dev); - if (skb_dst(skb) && skb_dst(skb)->dev) - return dev_net(skb_dst(skb)->dev); - WARN(skb->sk, "Maybe skb_sknet should be used in %s() at line:%d\n", - __func__, __LINE__); - if (likely(skb->sk && sock_net(skb->sk))) - return sock_net(skb->sk); - pr_err("There is no net ptr to find in the skb in %s() line:%d\n", - __func__, __LINE__); - BUG(); -#else - return dev_net(skb->dev ? : skb_dst(skb)->dev); -#endif -#else - return &init_net; -#endif -} - -static inline struct net *skb_sknet(const struct sk_buff *skb) -{ -#ifdef CONFIG_NET_NS -#ifdef CONFIG_IP_VS_DEBUG - /* Start with the most likely hit */ - if (likely(skb->sk && sock_net(skb->sk))) - return sock_net(skb->sk); - WARN(skb->dev, "Maybe skb_net should be used instead in %s() line:%d\n", - __func__, __LINE__); - if (likely(skb->dev && dev_net(skb->dev))) - return dev_net(skb->dev); - pr_err("There is no net ptr to find in the skb in %s() line:%d\n", - __func__, __LINE__); - BUG(); -#else - return sock_net(skb->sk); -#endif -#else - return &init_net; -#endif -} - /* This one needed for single_open_net since net is stored directly in * private not as a struct i.e. seq_file_net can't be used. */ @@ -104,6 +54,8 @@ static inline struct net *seq_file_single_net(struct seq_file *seq) extern int ip_vs_conn_tab_size; struct ip_vs_iphdr { + int hdr_flags; /* ipvs flags */ + __u32 off; /* Where IP or IPv4 header starts */ __u32 len; /* IPv4 simply where L4 starts * IPv6 where L4 Transport Header starts */ __u16 fragoffs; /* IPv6 fragment offset, 0 if first frag (or not frag)*/ @@ -120,48 +72,89 @@ static inline void *frag_safe_skb_hp(const struct sk_buff *skb, int offset, return skb_header_pointer(skb, offset, len, buffer); } -static inline void -ip_vs_fill_ip4hdr(const void *nh, struct ip_vs_iphdr *iphdr) -{ - const struct iphdr *iph = nh; - - iphdr->len = iph->ihl * 4; - iphdr->fragoffs = 0; - iphdr->protocol = iph->protocol; - iphdr->saddr.ip = iph->saddr; - iphdr->daddr.ip = iph->daddr; -} - /* This function handles filling *ip_vs_iphdr, both for IPv4 and IPv6. * IPv6 requires some extra work, as finding proper header position, * depend on the IPv6 extension headers. */ -static inline void -ip_vs_fill_iph_skb(int af, const struct sk_buff *skb, struct ip_vs_iphdr *iphdr) +static inline int +ip_vs_fill_iph_skb_off(int af, const struct sk_buff *skb, int offset, + int hdr_flags, struct ip_vs_iphdr *iphdr) { + iphdr->hdr_flags = hdr_flags; + iphdr->off = offset; + #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { - const struct ipv6hdr *iph = - (struct ipv6hdr *)skb_network_header(skb); + struct ipv6hdr _iph; + const struct ipv6hdr *iph = skb_header_pointer( + skb, offset, sizeof(_iph), &_iph); + if (!iph) + return 0; + iphdr->saddr.in6 = iph->saddr; iphdr->daddr.in6 = iph->daddr; /* ipv6_find_hdr() updates len, flags */ - iphdr->len = 0; + iphdr->len = offset; iphdr->flags = 0; iphdr->protocol = ipv6_find_hdr(skb, &iphdr->len, -1, &iphdr->fragoffs, &iphdr->flags); + if (iphdr->protocol < 0) + return 0; } else #endif { - const struct iphdr *iph = - (struct iphdr *)skb_network_header(skb); - iphdr->len = iph->ihl * 4; + struct iphdr _iph; + const struct iphdr *iph = skb_header_pointer( + skb, offset, sizeof(_iph), &_iph); + if (!iph) + return 0; + + iphdr->len = offset + iph->ihl * 4; iphdr->fragoffs = 0; iphdr->protocol = iph->protocol; iphdr->saddr.ip = iph->saddr; iphdr->daddr.ip = iph->daddr; } + + return 1; +} + +static inline int +ip_vs_fill_iph_skb_icmp(int af, const struct sk_buff *skb, int offset, + bool inverse, struct ip_vs_iphdr *iphdr) +{ + int hdr_flags = IP_VS_HDR_ICMP; + + if (inverse) + hdr_flags |= IP_VS_HDR_INVERSE; + + return ip_vs_fill_iph_skb_off(af, skb, offset, hdr_flags, iphdr); +} + +static inline int +ip_vs_fill_iph_skb(int af, const struct sk_buff *skb, bool inverse, + struct ip_vs_iphdr *iphdr) +{ + int hdr_flags = 0; + + if (inverse) + hdr_flags |= IP_VS_HDR_INVERSE; + + return ip_vs_fill_iph_skb_off(af, skb, skb_network_offset(skb), + hdr_flags, iphdr); +} + +static inline bool +ip_vs_iph_inverse(const struct ip_vs_iphdr *iph) +{ + return !!(iph->hdr_flags & IP_VS_HDR_INVERSE); +} + +static inline bool +ip_vs_iph_icmp(const struct ip_vs_iphdr *iph) +{ + return !!(iph->hdr_flags & IP_VS_HDR_ICMP); } static inline void ip_vs_addr_copy(int af, union nf_inet_addr *dst, @@ -437,26 +430,27 @@ struct ip_vs_protocol { void (*exit)(struct ip_vs_protocol *pp); - int (*init_netns)(struct net *net, struct ip_vs_proto_data *pd); + int (*init_netns)(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd); - void (*exit_netns)(struct net *net, struct ip_vs_proto_data *pd); + void (*exit_netns)(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd); - int (*conn_schedule)(int af, struct sk_buff *skb, + int (*conn_schedule)(struct netns_ipvs *ipvs, + int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp, struct ip_vs_iphdr *iph); struct ip_vs_conn * - (*conn_in_get)(int af, + (*conn_in_get)(struct netns_ipvs *ipvs, + int af, const struct sk_buff *skb, - const struct ip_vs_iphdr *iph, - int inverse); + const struct ip_vs_iphdr *iph); struct ip_vs_conn * - (*conn_out_get)(int af, + (*conn_out_get)(struct netns_ipvs *ipvs, + int af, const struct sk_buff *skb, - const struct ip_vs_iphdr *iph, - int inverse); + const struct ip_vs_iphdr *iph); int (*snat_handler)(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, struct ip_vs_iphdr *iph); @@ -473,9 +467,9 @@ struct ip_vs_protocol { const struct sk_buff *skb, struct ip_vs_proto_data *pd); - int (*register_app)(struct net *net, struct ip_vs_app *inc); + int (*register_app)(struct netns_ipvs *ipvs, struct ip_vs_app *inc); - void (*unregister_app)(struct net *net, struct ip_vs_app *inc); + void (*unregister_app)(struct netns_ipvs *ipvs, struct ip_vs_app *inc); int (*app_conn_bind)(struct ip_vs_conn *cp); @@ -497,11 +491,11 @@ struct ip_vs_proto_data { }; struct ip_vs_protocol *ip_vs_proto_get(unsigned short proto); -struct ip_vs_proto_data *ip_vs_proto_data_get(struct net *net, +struct ip_vs_proto_data *ip_vs_proto_data_get(struct netns_ipvs *ipvs, unsigned short proto); struct ip_vs_conn_param { - struct net *net; + struct netns_ipvs *ipvs; const union nf_inet_addr *caddr; const union nf_inet_addr *vaddr; __be16 cport; @@ -528,9 +522,7 @@ struct ip_vs_conn { volatile __u32 flags; /* status flags */ __u16 protocol; /* Which protocol (TCP/UDP) */ __u16 daf; /* Address family of the dest */ -#ifdef CONFIG_NET_NS - struct net *net; /* Name space */ -#endif + struct netns_ipvs *ipvs; /* counter and timer */ atomic_t refcnt; /* reference count */ @@ -577,33 +569,6 @@ struct ip_vs_conn { struct rcu_head rcu_head; }; -/* To save some memory in conn table when name space is disabled. */ -static inline struct net *ip_vs_conn_net(const struct ip_vs_conn *cp) -{ -#ifdef CONFIG_NET_NS - return cp->net; -#else - return &init_net; -#endif -} - -static inline void ip_vs_conn_net_set(struct ip_vs_conn *cp, struct net *net) -{ -#ifdef CONFIG_NET_NS - cp->net = net; -#endif -} - -static inline int ip_vs_conn_net_eq(const struct ip_vs_conn *cp, - struct net *net) -{ -#ifdef CONFIG_NET_NS - return cp->net == net; -#else - return 1; -#endif -} - /* Extended internal versions of struct ip_vs_service_user and ip_vs_dest_user * for IPv6 support. * @@ -663,7 +628,7 @@ struct ip_vs_service { unsigned int flags; /* service status flags */ unsigned int timeout; /* persistent timeout in ticks */ __be32 netmask; /* grouping granularity, mask/plen */ - struct net *net; + struct netns_ipvs *ipvs; struct list_head destinations; /* real server d-linked list */ __u32 num_dests; /* number of servers */ @@ -953,6 +918,8 @@ struct netns_ipvs { int sysctl_pmtu_disc; int sysctl_backup_only; int sysctl_conn_reuse_mode; + int sysctl_schedule_icmp; + int sysctl_ignore_tunneled; /* ip_vs_lblc */ int sysctl_lblc_expiration; @@ -1071,6 +1038,21 @@ static inline int sysctl_conn_reuse_mode(struct netns_ipvs *ipvs) return ipvs->sysctl_conn_reuse_mode; } +static inline int sysctl_schedule_icmp(struct netns_ipvs *ipvs) +{ + return ipvs->sysctl_schedule_icmp; +} + +static inline int sysctl_ignore_tunneled(struct netns_ipvs *ipvs) +{ + return ipvs->sysctl_ignore_tunneled; +} + +static inline int sysctl_cache_bypass(struct netns_ipvs *ipvs) +{ + return ipvs->sysctl_cache_bypass; +} + #else static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs) @@ -1143,6 +1125,21 @@ static inline int sysctl_conn_reuse_mode(struct netns_ipvs *ipvs) return 1; } +static inline int sysctl_schedule_icmp(struct netns_ipvs *ipvs) +{ + return 0; +} + +static inline int sysctl_ignore_tunneled(struct netns_ipvs *ipvs) +{ + return 0; +} + +static inline int sysctl_cache_bypass(struct netns_ipvs *ipvs) +{ + return 0; +} + #endif /* IPVS core functions @@ -1164,14 +1161,14 @@ enum { IP_VS_DIR_LAST, }; -static inline void ip_vs_conn_fill_param(struct net *net, int af, int protocol, +static inline void ip_vs_conn_fill_param(struct netns_ipvs *ipvs, int af, int protocol, const union nf_inet_addr *caddr, __be16 cport, const union nf_inet_addr *vaddr, __be16 vport, struct ip_vs_conn_param *p) { - p->net = net; + p->ipvs = ipvs; p->af = af; p->protocol = protocol; p->caddr = caddr; @@ -1185,15 +1182,15 @@ static inline void ip_vs_conn_fill_param(struct net *net, int af, int protocol, struct ip_vs_conn *ip_vs_conn_in_get(const struct ip_vs_conn_param *p); struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p); -struct ip_vs_conn * ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb, - const struct ip_vs_iphdr *iph, - int inverse); +struct ip_vs_conn * ip_vs_conn_in_get_proto(struct netns_ipvs *ipvs, int af, + const struct sk_buff *skb, + const struct ip_vs_iphdr *iph); struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p); -struct ip_vs_conn * ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb, - const struct ip_vs_iphdr *iph, - int inverse); +struct ip_vs_conn * ip_vs_conn_out_get_proto(struct netns_ipvs *ipvs, int af, + const struct sk_buff *skb, + const struct ip_vs_iphdr *iph); /* Get reference to gain full access to conn. * By default, RCU read-side critical sections have access only to @@ -1221,9 +1218,9 @@ void ip_vs_conn_expire_now(struct ip_vs_conn *cp); const char *ip_vs_state_name(__u16 proto, int state); -void ip_vs_tcp_conn_listen(struct net *net, struct ip_vs_conn *cp); +void ip_vs_tcp_conn_listen(struct ip_vs_conn *cp); int ip_vs_check_template(struct ip_vs_conn *ct); -void ip_vs_random_dropentry(struct net *net); +void ip_vs_random_dropentry(struct netns_ipvs *ipvs); int ip_vs_conn_init(void); void ip_vs_conn_cleanup(void); @@ -1288,29 +1285,29 @@ ip_vs_control_add(struct ip_vs_conn *cp, struct ip_vs_conn *ctl_cp) } /* IPVS netns init & cleanup functions */ -int ip_vs_estimator_net_init(struct net *net); -int ip_vs_control_net_init(struct net *net); -int ip_vs_protocol_net_init(struct net *net); -int ip_vs_app_net_init(struct net *net); -int ip_vs_conn_net_init(struct net *net); -int ip_vs_sync_net_init(struct net *net); -void ip_vs_conn_net_cleanup(struct net *net); -void ip_vs_app_net_cleanup(struct net *net); -void ip_vs_protocol_net_cleanup(struct net *net); -void ip_vs_control_net_cleanup(struct net *net); -void ip_vs_estimator_net_cleanup(struct net *net); -void ip_vs_sync_net_cleanup(struct net *net); -void ip_vs_service_net_cleanup(struct net *net); +int ip_vs_estimator_net_init(struct netns_ipvs *ipvs); +int ip_vs_control_net_init(struct netns_ipvs *ipvs); +int ip_vs_protocol_net_init(struct netns_ipvs *ipvs); +int ip_vs_app_net_init(struct netns_ipvs *ipvs); +int ip_vs_conn_net_init(struct netns_ipvs *ipvs); +int ip_vs_sync_net_init(struct netns_ipvs *ipvs); +void ip_vs_conn_net_cleanup(struct netns_ipvs *ipvs); +void ip_vs_app_net_cleanup(struct netns_ipvs *ipvs); +void ip_vs_protocol_net_cleanup(struct netns_ipvs *ipvs); +void ip_vs_control_net_cleanup(struct netns_ipvs *ipvs); +void ip_vs_estimator_net_cleanup(struct netns_ipvs *ipvs); +void ip_vs_sync_net_cleanup(struct netns_ipvs *ipvs); +void ip_vs_service_net_cleanup(struct netns_ipvs *ipvs); /* IPVS application functions * (from ip_vs_app.c) */ #define IP_VS_APP_MAX_PORTS 8 -struct ip_vs_app *register_ip_vs_app(struct net *net, struct ip_vs_app *app); -void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app); +struct ip_vs_app *register_ip_vs_app(struct netns_ipvs *ipvs, struct ip_vs_app *app); +void unregister_ip_vs_app(struct netns_ipvs *ipvs, struct ip_vs_app *app); int ip_vs_bind_app(struct ip_vs_conn *cp, struct ip_vs_protocol *pp); void ip_vs_unbind_app(struct ip_vs_conn *cp); -int register_ip_vs_app_inc(struct net *net, struct ip_vs_app *app, __u16 proto, +int register_ip_vs_app_inc(struct netns_ipvs *ipvs, struct ip_vs_app *app, __u16 proto, __u16 port); int ip_vs_app_inc_get(struct ip_vs_app *inc); void ip_vs_app_inc_put(struct ip_vs_app *inc); @@ -1375,10 +1372,10 @@ extern struct ip_vs_stats ip_vs_stats; extern int sysctl_ip_vs_sync_ver; struct ip_vs_service * -ip_vs_service_find(struct net *net, int af, __u32 fwmark, __u16 protocol, +ip_vs_service_find(struct netns_ipvs *ipvs, int af, __u32 fwmark, __u16 protocol, const union nf_inet_addr *vaddr, __be16 vport); -bool ip_vs_has_real_service(struct net *net, int af, __u16 protocol, +bool ip_vs_has_real_service(struct netns_ipvs *ipvs, int af, __u16 protocol, const union nf_inet_addr *daddr, __be16 dport); int ip_vs_use_count_inc(void); @@ -1388,7 +1385,7 @@ void ip_vs_unregister_nl_ioctl(void); int ip_vs_control_init(void); void ip_vs_control_cleanup(void); struct ip_vs_dest * -ip_vs_find_dest(struct net *net, int svc_af, int dest_af, +ip_vs_find_dest(struct netns_ipvs *ipvs, int svc_af, int dest_af, const union nf_inet_addr *daddr, __be16 dport, const union nf_inet_addr *vaddr, __be16 vport, __u16 protocol, __u32 fwmark, __u32 flags); @@ -1414,14 +1411,14 @@ static inline void ip_vs_dest_put_and_free(struct ip_vs_dest *dest) /* IPVS sync daemon data and function prototypes * (from ip_vs_sync.c) */ -int start_sync_thread(struct net *net, struct ipvs_sync_daemon_cfg *cfg, +int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *cfg, int state); -int stop_sync_thread(struct net *net, int state); -void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp, int pkts); +int stop_sync_thread(struct netns_ipvs *ipvs, int state); +void ip_vs_sync_conn(struct netns_ipvs *ipvs, struct ip_vs_conn *cp, int pkts); /* IPVS rate estimator prototypes (from ip_vs_est.c) */ -void ip_vs_start_estimator(struct net *net, struct ip_vs_stats *stats); -void ip_vs_stop_estimator(struct net *net, struct ip_vs_stats *stats); +void ip_vs_start_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats); +void ip_vs_stop_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats); void ip_vs_zero_estimator(struct ip_vs_stats *stats); void ip_vs_read_estimator(struct ip_vs_kstats *dst, struct ip_vs_stats *stats); diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 711cca428cc8..3dde042bcd3f 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -807,12 +807,12 @@ static inline u8 ip6_tclass(__be32 flowinfo) int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); -int ip6_rcv_finish(struct sock *sk, struct sk_buff *skb); +int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb); /* * upper-layer output functions */ -int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, +int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, struct ipv6_txoptions *opt, int tclass); int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr); @@ -849,7 +849,7 @@ static inline struct sk_buff *ip6_finish_skb(struct sock *sk) int ip6_dst_lookup(struct net *net, struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6); -struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, +struct dst_entry *ip6_dst_lookup_flow(const struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst); struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst); diff --git a/include/net/iucv/iucv.h b/include/net/iucv/iucv.h index 0894ced31957..b867b0cf79e8 100644 --- a/include/net/iucv/iucv.h +++ b/include/net/iucv/iucv.h @@ -141,14 +141,14 @@ struct iucv_handler { * called is the order of the registration of the iucv handlers * to the base code. */ - int (*path_pending)(struct iucv_path *, u8 ipvmid[8], u8 ipuser[16]); + int (*path_pending)(struct iucv_path *, u8 *ipvmid, u8 *ipuser); /* * The path_complete function is called after an iucv interrupt * type 0x02 has been received for a path that has been established * for this handler with iucv_path_connect and got accepted by the * peer with iucv_path_accept. */ - void (*path_complete)(struct iucv_path *, u8 ipuser[16]); + void (*path_complete)(struct iucv_path *, u8 *ipuser); /* * The path_severed function is called after an iucv interrupt * type 0x03 has been received. The communication peer shutdown @@ -156,20 +156,20 @@ struct iucv_handler { * remaining messages can be received until a iucv_path_sever * shuts down the other end of the path as well. */ - void (*path_severed)(struct iucv_path *, u8 ipuser[16]); + void (*path_severed)(struct iucv_path *, u8 *ipuser); /* * The path_quiesced function is called after an icuv interrupt * type 0x04 has been received. The communication peer has quiesced * the path. Delivery of messages is stopped until iucv_path_resume * has been called. */ - void (*path_quiesced)(struct iucv_path *, u8 ipuser[16]); + void (*path_quiesced)(struct iucv_path *, u8 *ipuser); /* * The path_resumed function is called after an icuv interrupt * type 0x05 has been received. The communication peer has resumed * the path. */ - void (*path_resumed)(struct iucv_path *, u8 ipuser[16]); + void (*path_resumed)(struct iucv_path *, u8 *ipuser); /* * The message_pending function is called after an icuv interrupt * type 0x06 or type 0x07 has been received. A new message is @@ -256,7 +256,7 @@ static inline void iucv_path_free(struct iucv_path *path) * Returns the result of the CP IUCV call. */ int iucv_path_accept(struct iucv_path *path, struct iucv_handler *handler, - u8 userdata[16], void *private); + u8 *userdata, void *private); /** * iucv_path_connect @@ -274,7 +274,7 @@ int iucv_path_accept(struct iucv_path *path, struct iucv_handler *handler, * Returns the result of the CP IUCV call. */ int iucv_path_connect(struct iucv_path *path, struct iucv_handler *handler, - u8 userid[8], u8 system[8], u8 userdata[16], + u8 *userid, u8 *system, u8 *userdata, void *private); /** @@ -287,7 +287,7 @@ int iucv_path_connect(struct iucv_path *path, struct iucv_handler *handler, * * Returns the result from the CP IUCV call. */ -int iucv_path_quiesce(struct iucv_path *path, u8 userdata[16]); +int iucv_path_quiesce(struct iucv_path *path, u8 *userdata); /** * iucv_path_resume: @@ -299,7 +299,7 @@ int iucv_path_quiesce(struct iucv_path *path, u8 userdata[16]); * * Returns the result from the CP IUCV call. */ -int iucv_path_resume(struct iucv_path *path, u8 userdata[16]); +int iucv_path_resume(struct iucv_path *path, u8 *userdata); /** * iucv_path_sever @@ -310,7 +310,7 @@ int iucv_path_resume(struct iucv_path *path, u8 userdata[16]); * * Returns the result from the CP IUCV call. */ -int iucv_path_sever(struct iucv_path *path, u8 userdata[16]); +int iucv_path_sever(struct iucv_path *path, u8 *userdata); /** * iucv_message_purge diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h new file mode 100644 index 000000000000..87cee05a0a17 --- /dev/null +++ b/include/net/l3mdev.h @@ -0,0 +1,149 @@ +/* + * include/net/l3mdev.h - L3 master device API + * Copyright (c) 2015 Cumulus Networks + * Copyright (c) 2015 David Ahern <dsa@cumulusnetworks.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ +#ifndef _NET_L3MDEV_H_ +#define _NET_L3MDEV_H_ + +/** + * struct l3mdev_ops - l3mdev operations + * + * @l3mdev_fib_table: Get FIB table id to use for lookups + * + * @l3mdev_get_rtable: Get cached IPv4 rtable (dst_entry) for device + */ + +struct l3mdev_ops { + u32 (*l3mdev_fib_table)(const struct net_device *dev); + struct rtable * (*l3mdev_get_rtable)(const struct net_device *dev, + const struct flowi4 *fl4); +}; + +#ifdef CONFIG_NET_L3_MASTER_DEV + +int l3mdev_master_ifindex_rcu(struct net_device *dev); +static inline int l3mdev_master_ifindex(struct net_device *dev) +{ + int ifindex; + + rcu_read_lock(); + ifindex = l3mdev_master_ifindex_rcu(dev); + rcu_read_unlock(); + + return ifindex; +} + +/* get index of an interface to use for FIB lookups. For devices + * enslaved to an L3 master device FIB lookups are based on the + * master index + */ +static inline int l3mdev_fib_oif_rcu(struct net_device *dev) +{ + return l3mdev_master_ifindex_rcu(dev) ? : dev->ifindex; +} + +static inline int l3mdev_fib_oif(struct net_device *dev) +{ + int oif; + + rcu_read_lock(); + oif = l3mdev_fib_oif_rcu(dev); + rcu_read_unlock(); + + return oif; +} + +u32 l3mdev_fib_table_rcu(const struct net_device *dev); +u32 l3mdev_fib_table_by_index(struct net *net, int ifindex); +static inline u32 l3mdev_fib_table(const struct net_device *dev) +{ + u32 tb_id; + + rcu_read_lock(); + tb_id = l3mdev_fib_table_rcu(dev); + rcu_read_unlock(); + + return tb_id; +} + +static inline struct rtable *l3mdev_get_rtable(const struct net_device *dev, + const struct flowi4 *fl4) +{ + if (netif_is_l3_master(dev) && dev->l3mdev_ops->l3mdev_get_rtable) + return dev->l3mdev_ops->l3mdev_get_rtable(dev, fl4); + + return NULL; +} + +static inline bool netif_index_is_l3_master(struct net *net, int ifindex) +{ + struct net_device *dev; + bool rc = false; + + if (ifindex == 0) + return false; + + rcu_read_lock(); + + dev = dev_get_by_index_rcu(net, ifindex); + if (dev) + rc = netif_is_l3_master(dev); + + rcu_read_unlock(); + + return rc; +} + +#else + +static inline int l3mdev_master_ifindex_rcu(struct net_device *dev) +{ + return 0; +} +static inline int l3mdev_master_ifindex(struct net_device *dev) +{ + return 0; +} + +static inline int l3mdev_fib_oif_rcu(struct net_device *dev) +{ + return dev ? dev->ifindex : 0; +} +static inline int l3mdev_fib_oif(struct net_device *dev) +{ + return dev ? dev->ifindex : 0; +} + +static inline u32 l3mdev_fib_table_rcu(const struct net_device *dev) +{ + return 0; +} +static inline u32 l3mdev_fib_table(const struct net_device *dev) +{ + return 0; +} +static inline u32 l3mdev_fib_table_by_index(struct net *net, int ifindex) +{ + return 0; +} + +static inline struct rtable *l3mdev_get_rtable(const struct net_device *dev, + const struct flowi4 *fl4) +{ + return NULL; +} + +static inline bool netif_index_is_l3_master(struct net *net, int ifindex) +{ + return false; +} + +#endif + +#endif /* _NET_L3MDEV_H_ */ diff --git a/include/net/mac802154.h b/include/net/mac802154.h index b7f99615224b..32bd7c0467d4 100644 --- a/include/net/mac802154.h +++ b/include/net/mac802154.h @@ -250,6 +250,21 @@ struct ieee802154_ops { }; /** + * ieee802154_get_fc_from_skb - get the frame control field from an skb + * @skb: skb where the frame control field will be get from + */ +static inline __le16 ieee802154_get_fc_from_skb(const struct sk_buff *skb) +{ + /* return some invalid fc on failure */ + if (unlikely(skb->mac_len < 2)) { + WARN_ON(1); + return cpu_to_le16(0); + } + + return (__force __le16)__get_unaligned_memmove16(skb_mac_header(skb)); +} + +/** * ieee802154_be64_to_le64 - copies and convert be64 to le64 * @le64_dst: le64 destination pointer * @be64_src: be64 source pointer diff --git a/include/net/ndisc.h b/include/net/ndisc.h index aba5695fadb0..bf3937431030 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -180,15 +180,13 @@ void ndisc_cleanup(void); int ndisc_rcv(struct sk_buff *skb); -void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh, - const struct in6_addr *solicit, +void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit, const struct in6_addr *daddr, const struct in6_addr *saddr, struct sk_buff *oskb); void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr, const struct in6_addr *daddr); -void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, - const struct in6_addr *daddr, +void ndisc_send_na(struct net_device *dev, const struct in6_addr *daddr, const struct in6_addr *solicited_addr, bool router, bool solicited, bool override, bool inc_opt); diff --git a/include/net/netfilter/br_netfilter.h b/include/net/netfilter/br_netfilter.h index d4c6b5f30acd..e8d1448425a7 100644 --- a/include/net/netfilter/br_netfilter.h +++ b/include/net/netfilter/br_netfilter.h @@ -31,7 +31,7 @@ static inline void nf_bridge_push_encap_header(struct sk_buff *skb) skb->network_header -= len; } -int br_nf_pre_routing_finish_bridge(struct sock *sk, struct sk_buff *skb); +int br_nf_pre_routing_finish_bridge(struct net *net, struct sock *sk, struct sk_buff *skb); static inline struct rtable *bridge_parent_rtable(const struct net_device *dev) { @@ -45,12 +45,12 @@ struct net_device *setup_pre_routing(struct sk_buff *skb); void br_netfilter_enable(void); #if IS_ENABLED(CONFIG_IPV6) -int br_validate_ipv6(struct sk_buff *skb); -unsigned int br_nf_pre_routing_ipv6(const struct nf_hook_ops *ops, +int br_validate_ipv6(struct net *net, struct sk_buff *skb); +unsigned int br_nf_pre_routing_ipv6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state); #else -static inline int br_validate_ipv6(struct sk_buff *skb) +static inline int br_validate_ipv6(struct net *net, struct sk_buff *skb) { return -1; } diff --git a/include/net/netfilter/ipv4/nf_dup_ipv4.h b/include/net/netfilter/ipv4/nf_dup_ipv4.h index 42008f10dfc4..0a14733e8b82 100644 --- a/include/net/netfilter/ipv4/nf_dup_ipv4.h +++ b/include/net/netfilter/ipv4/nf_dup_ipv4.h @@ -1,7 +1,7 @@ #ifndef _NF_DUP_IPV4_H_ #define _NF_DUP_IPV4_H_ -void nf_dup_ipv4(struct sk_buff *skb, unsigned int hooknum, +void nf_dup_ipv4(struct net *net, struct sk_buff *skb, unsigned int hooknum, const struct in_addr *gw, int oif); #endif /* _NF_DUP_IPV4_H_ */ diff --git a/include/net/netfilter/ipv4/nf_reject.h b/include/net/netfilter/ipv4/nf_reject.h index 77862c3645f0..df7ecd806aba 100644 --- a/include/net/netfilter/ipv4/nf_reject.h +++ b/include/net/netfilter/ipv4/nf_reject.h @@ -6,7 +6,7 @@ #include <net/icmp.h> void nf_send_unreach(struct sk_buff *skb_in, int code, int hook); -void nf_send_reset(struct sk_buff *oldskb, int hook); +void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook); const struct tcphdr *nf_reject_ip_tcphdr_get(struct sk_buff *oldskb, struct tcphdr *_oth, int hook); diff --git a/include/net/netfilter/ipv6/nf_dup_ipv6.h b/include/net/netfilter/ipv6/nf_dup_ipv6.h index ed6bd66fa5a0..fa6237b382a3 100644 --- a/include/net/netfilter/ipv6/nf_dup_ipv6.h +++ b/include/net/netfilter/ipv6/nf_dup_ipv6.h @@ -1,7 +1,7 @@ #ifndef _NF_DUP_IPV6_H_ #define _NF_DUP_IPV6_H_ -void nf_dup_ipv6(struct sk_buff *skb, unsigned int hooknum, +void nf_dup_ipv6(struct net *net, struct sk_buff *skb, unsigned int hooknum, const struct in6_addr *gw, int oif); #endif /* _NF_DUP_IPV6_H_ */ diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index e8ad46834df8..d642f68a7c73 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -191,7 +191,8 @@ int nf_conntrack_hash_check_insert(struct nf_conn *ct); bool nf_ct_delete(struct nf_conn *ct, u32 pid, int report); bool nf_ct_get_tuplepr(const struct sk_buff *skb, unsigned int nhoff, - u_int16_t l3num, struct nf_conntrack_tuple *tuple); + u_int16_t l3num, struct net *net, + struct nf_conntrack_tuple *tuple); bool nf_ct_invert_tuplepr(struct nf_conntrack_tuple *inverse, const struct nf_conntrack_tuple *orig); diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h index c03f9c42b3cd..788ef58a66b9 100644 --- a/include/net/netfilter/nf_conntrack_core.h +++ b/include/net/netfilter/nf_conntrack_core.h @@ -41,6 +41,7 @@ void nf_conntrack_cleanup_end(void); bool nf_ct_get_tuple(const struct sk_buff *skb, unsigned int nhoff, unsigned int dataoff, u_int16_t l3num, u_int8_t protonum, + struct net *net, struct nf_conntrack_tuple *tuple, const struct nf_conntrack_l3proto *l3proto, const struct nf_conntrack_l4proto *l4proto); diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 1f7061313d54..956d8a6ac069 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -26,7 +26,7 @@ struct nf_conntrack_l4proto { /* Try to fill in the third arg: dataoff is offset past network protocol hdr. Return true if possible. */ bool (*pkt_to_tuple)(const struct sk_buff *skb, unsigned int dataoff, - struct nf_conntrack_tuple *tuple); + struct net *net, struct nf_conntrack_tuple *tuple); /* Invert the per-proto part of the tuple: ie. turn xmit into reply. * Some packets can't be inverted: return 0 in that case. diff --git a/include/net/netfilter/nf_nat_core.h b/include/net/netfilter/nf_nat_core.h index fbfd1ba4254e..186c54138f35 100644 --- a/include/net/netfilter/nf_nat_core.h +++ b/include/net/netfilter/nf_nat_core.h @@ -10,7 +10,7 @@ unsigned int nf_nat_packet(struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned int hooknum, struct sk_buff *skb); -int nf_xfrm_me_harder(struct sk_buff *skb, unsigned int family); +int nf_xfrm_me_harder(struct net *net, struct sk_buff *skb, unsigned int family); static inline int nf_nat_initialized(struct nf_conn *ct, enum nf_nat_manip_type manip) diff --git a/include/net/netfilter/nf_nat_l3proto.h b/include/net/netfilter/nf_nat_l3proto.h index a3127325f624..aef3e5fc9fd9 100644 --- a/include/net/netfilter/nf_nat_l3proto.h +++ b/include/net/netfilter/nf_nat_l3proto.h @@ -43,31 +43,31 @@ int nf_nat_icmp_reply_translation(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned int hooknum); -unsigned int nf_nat_ipv4_in(const struct nf_hook_ops *ops, struct sk_buff *skb, +unsigned int nf_nat_ipv4_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)); -unsigned int nf_nat_ipv4_out(const struct nf_hook_ops *ops, struct sk_buff *skb, +unsigned int nf_nat_ipv4_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)); -unsigned int nf_nat_ipv4_local_fn(const struct nf_hook_ops *ops, +unsigned int nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)); -unsigned int nf_nat_ipv4_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, +unsigned int nf_nat_ipv4_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)); @@ -76,31 +76,31 @@ int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, unsigned int hooknum, unsigned int hdrlen); -unsigned int nf_nat_ipv6_in(const struct nf_hook_ops *ops, struct sk_buff *skb, +unsigned int nf_nat_ipv6_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)); -unsigned int nf_nat_ipv6_out(const struct nf_hook_ops *ops, struct sk_buff *skb, +unsigned int nf_nat_ipv6_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)); -unsigned int nf_nat_ipv6_local_fn(const struct nf_hook_ops *ops, +unsigned int nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)); -unsigned int nf_nat_ipv6_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, +unsigned int nf_nat_ipv6_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)); diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index aa8bee72c9d3..c9149cc0a02d 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -14,9 +14,11 @@ struct nft_pktinfo { struct sk_buff *skb; + struct net *net; const struct net_device *in; const struct net_device *out; - const struct nf_hook_ops *ops; + u8 pf; + u8 hook; u8 nhoff; u8 thoff; u8 tprot; @@ -25,16 +27,15 @@ struct nft_pktinfo { }; static inline void nft_set_pktinfo(struct nft_pktinfo *pkt, - const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { pkt->skb = skb; + pkt->net = pkt->xt.net = state->net; pkt->in = pkt->xt.in = state->in; pkt->out = pkt->xt.out = state->out; - pkt->ops = ops; - pkt->xt.hooknum = ops->hooknum; - pkt->xt.family = ops->pf; + pkt->hook = pkt->xt.hooknum = state->hook; + pkt->pf = pkt->xt.family = state->pf; } /** @@ -815,8 +816,7 @@ int nft_register_basechain(struct nft_base_chain *basechain, void nft_unregister_basechain(struct nft_base_chain *basechain, unsigned int hook_nops); -unsigned int nft_do_chain(struct nft_pktinfo *pkt, - const struct nf_hook_ops *ops); +unsigned int nft_do_chain(struct nft_pktinfo *pkt, void *priv); /** * struct nft_table - nf_tables table diff --git a/include/net/netfilter/nf_tables_ipv4.h b/include/net/netfilter/nf_tables_ipv4.h index 2df7f96902ee..ca6ef6bf775e 100644 --- a/include/net/netfilter/nf_tables_ipv4.h +++ b/include/net/netfilter/nf_tables_ipv4.h @@ -6,13 +6,12 @@ static inline void nft_set_pktinfo_ipv4(struct nft_pktinfo *pkt, - const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { struct iphdr *ip; - nft_set_pktinfo(pkt, ops, skb, state); + nft_set_pktinfo(pkt, skb, state); ip = ip_hdr(pkt->skb); pkt->tprot = ip->protocol; diff --git a/include/net/netfilter/nf_tables_ipv6.h b/include/net/netfilter/nf_tables_ipv6.h index 97db2e3a5e65..8ad39a6a5fe1 100644 --- a/include/net/netfilter/nf_tables_ipv6.h +++ b/include/net/netfilter/nf_tables_ipv6.h @@ -6,14 +6,13 @@ static inline int nft_set_pktinfo_ipv6(struct nft_pktinfo *pkt, - const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { int protohdr, thoff = 0; unsigned short frag_off; - nft_set_pktinfo(pkt, ops, skb, state); + nft_set_pktinfo(pkt, skb, state); protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, NULL); /* If malformed, drop it */ diff --git a/include/net/request_sock.h b/include/net/request_sock.h index 87935cad2f7b..d2544de329bd 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -32,17 +32,17 @@ struct request_sock_ops { int obj_size; struct kmem_cache *slab; char *slab_name; - int (*rtx_syn_ack)(struct sock *sk, + int (*rtx_syn_ack)(const struct sock *sk, struct request_sock *req); - void (*send_ack)(struct sock *sk, struct sk_buff *skb, + void (*send_ack)(const struct sock *sk, struct sk_buff *skb, struct request_sock *req); - void (*send_reset)(struct sock *sk, + void (*send_reset)(const struct sock *sk, struct sk_buff *skb); void (*destructor)(struct request_sock *req); void (*syn_ack_timeout)(const struct request_sock *req); }; -int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req); +int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req); /* struct request_sock - mini sock to represent a connection request */ @@ -129,9 +129,8 @@ struct listen_sock { atomic_t qlen_dec; /* qlen = qlen_inc - qlen_dec */ atomic_t young_dec; - u8 max_qlen_log ____cacheline_aligned_in_smp; - u8 synflood_warned; - /* 2 bytes hole, try to use */ + u32 max_qlen_log ____cacheline_aligned_in_smp; + u32 synflood_warned; u32 hash_rnd; u32 nr_table_entries; struct request_sock *syn_table[0]; @@ -181,11 +180,8 @@ struct request_sock_queue { struct request_sock *rskq_accept_tail; u8 rskq_defer_accept; struct listen_sock *listen_opt; - struct fastopen_queue *fastopenq; /* This is non-NULL iff TFO has been - * enabled on this listener. Check - * max_qlen != 0 in fastopen_queue - * to determine if TFO is enabled - * right at this moment. + struct fastopen_queue fastopenq; /* Check max_qlen != 0 to determine + * if TFO is enabled. */ /* temporary alignment, our goal is to get rid of this lock */ diff --git a/include/net/route.h b/include/net/route.h index f46af256880c..e211dc167db1 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -28,6 +28,7 @@ #include <net/inetpeer.h> #include <net/flow.h> #include <net/inet_sock.h> +#include <net/l3mdev.h> #include <linux/in_route.h> #include <linux/rtnetlink.h> #include <linux/rcupdate.h> @@ -64,6 +65,8 @@ struct rtable { /* Miscellaneous cached information */ u32 rt_pmtu; + u32 rt_table_id; + struct list_head rt_uncached; struct uncached_list *rt_uncached_list; }; @@ -112,7 +115,7 @@ void rt_cache_flush(struct net *net); void rt_flush_dev(struct net_device *dev); struct rtable *__ip_route_output_key(struct net *, struct flowi4 *flp); struct rtable *ip_route_output_flow(struct net *, struct flowi4 *flp, - struct sock *sk); + const struct sock *sk); struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig); @@ -254,7 +257,7 @@ static inline void ip_route_connect_init(struct flowi4 *fl4, __be32 dst, __be32 if (inet_sk(sk)->transparent) flow_flags |= FLOWI_FLAG_ANYSRC; - if (netif_index_is_vrf(sock_net(sk), oif)) + if (netif_index_is_l3_master(sock_net(sk), oif)) flow_flags |= FLOWI_FLAG_VRFSRC | FLOWI_FLAG_SKIP_NH_OIF; flowi4_init_output(fl4, oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 18fdb98185ab..aff6ceb891a9 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -122,7 +122,8 @@ struct rtnl_af_ops { int family; int (*fill_link_af)(struct sk_buff *skb, - const struct net_device *dev); + const struct net_device *dev, + u32 ext_filter_mask); size_t (*get_link_af_size)(const struct net_device *dev); int (*validate_link_af)(const struct net_device *dev, diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 444faa89a55f..4c79ce8c1f92 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -251,7 +251,7 @@ struct tcf_proto { struct qdisc_skb_cb { unsigned int pkt_len; u16 slave_dev_queue_mapping; - u16 _pad; + u16 tc_classid; #define QDISC_CB_PRIV_LEN 20 unsigned char data[QDISC_CB_PRIV_LEN]; }; @@ -402,6 +402,7 @@ void __qdisc_calculate_pkt_len(struct sk_buff *skb, const struct qdisc_size_table *stab); bool tcf_destroy(struct tcf_proto *tp, bool force); void tcf_destroy_chain(struct tcf_proto __rcu **fl); +int skb_do_redirect(struct sk_buff *); /* Reset all TX qdiscs greater then index of a device. */ static inline void qdisc_reset_all_tx_gt(struct net_device *dev, unsigned int i) diff --git a/include/net/sock.h b/include/net/sock.h index 7aa78440559a..dfe2eb8e1132 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -759,7 +759,7 @@ static inline int sk_memalloc_socks(void) #endif -static inline gfp_t sk_gfp_atomic(struct sock *sk, gfp_t gfp_mask) +static inline gfp_t sk_gfp_atomic(const struct sock *sk, gfp_t gfp_mask) { return GFP_ATOMIC | (sk->sk_allocation & __GFP_MEMALLOC); } @@ -1654,12 +1654,16 @@ static inline void sock_graft(struct sock *sk, struct socket *parent) kuid_t sock_i_uid(struct sock *sk); unsigned long sock_i_ino(struct sock *sk); -static inline void sk_set_txhash(struct sock *sk) +static inline u32 net_tx_rndhash(void) { - sk->sk_txhash = prandom_u32(); + u32 v = prandom_u32(); + + return v ?: 1; +} - if (unlikely(!sk->sk_txhash)) - sk->sk_txhash = 1; +static inline void sk_set_txhash(struct sock *sk) +{ + sk->sk_txhash = net_tx_rndhash(); } static inline void sk_rethink_txhash(struct sock *sk) diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 319baab3b48e..e11425eb0735 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -1,6 +1,6 @@ /* * include/net/switchdev.h - Switch device API - * Copyright (c) 2014 Jiri Pirko <jiri@resnulli.us> + * Copyright (c) 2014-2015 Jiri Pirko <jiri@resnulli.us> * Copyright (c) 2014-2015 Scott Feldman <sfeldma@gmail.com> * * This program is free software; you can redistribute it and/or modify @@ -13,16 +13,31 @@ #include <linux/netdevice.h> #include <linux/notifier.h> +#include <linux/list.h> #define SWITCHDEV_F_NO_RECURSE BIT(0) -enum switchdev_trans { - SWITCHDEV_TRANS_NONE, - SWITCHDEV_TRANS_PREPARE, - SWITCHDEV_TRANS_ABORT, - SWITCHDEV_TRANS_COMMIT, +struct switchdev_trans_item { + struct list_head list; + void *data; + void (*destructor)(const void *data); }; +struct switchdev_trans { + struct list_head item_list; + bool ph_prepare; +}; + +static inline bool switchdev_trans_ph_prepare(struct switchdev_trans *trans) +{ + return trans && trans->ph_prepare; +} + +static inline bool switchdev_trans_ph_commit(struct switchdev_trans *trans) +{ + return trans && !trans->ph_prepare; +} + enum switchdev_attr_id { SWITCHDEV_ATTR_UNDEFINED, SWITCHDEV_ATTR_PORT_PARENT_ID, @@ -32,7 +47,6 @@ enum switchdev_attr_id { struct switchdev_attr { enum switchdev_attr_id id; - enum switchdev_trans trans; u32 flags; union { struct netdev_phys_item_id ppid; /* PORT_PARENT_ID */ @@ -50,33 +64,36 @@ enum switchdev_obj_id { SWITCHDEV_OBJ_PORT_FDB, }; -struct switchdev_obj { - enum switchdev_obj_id id; - enum switchdev_trans trans; - int (*cb)(struct net_device *dev, struct switchdev_obj *obj); - union { - struct switchdev_obj_vlan { /* PORT_VLAN */ - u16 flags; - u16 vid_begin; - u16 vid_end; - } vlan; - struct switchdev_obj_ipv4_fib { /* IPV4_FIB */ - u32 dst; - int dst_len; - struct fib_info *fi; - u8 tos; - u8 type; - u32 nlflags; - u32 tb_id; - } ipv4_fib; - struct switchdev_obj_fdb { /* PORT_FDB */ - const unsigned char *addr; - u16 vid; - u16 ndm_state; - } fdb; - } u; +/* SWITCHDEV_OBJ_PORT_VLAN */ +struct switchdev_obj_vlan { + u16 flags; + u16 vid_begin; + u16 vid_end; +}; + +/* SWITCHDEV_OBJ_IPV4_FIB */ +struct switchdev_obj_ipv4_fib { + u32 dst; + int dst_len; + struct fib_info *fi; + u8 tos; + u8 type; + u32 nlflags; + u32 tb_id; }; +/* SWITCHDEV_OBJ_PORT_FDB */ +struct switchdev_obj_fdb { + const unsigned char *addr; + u16 vid; + u16 ndm_state; +}; + +void switchdev_trans_item_enqueue(struct switchdev_trans *trans, + void *data, void (*destructor)(void const *), + struct switchdev_trans_item *tritem); +void *switchdev_trans_item_dequeue(struct switchdev_trans *trans); + /** * struct switchdev_ops - switchdev operations * @@ -84,23 +101,28 @@ struct switchdev_obj { * * @switchdev_port_attr_set: Set a port attribute (see switchdev_attr). * - * @switchdev_port_obj_add: Add an object to port (see switchdev_obj). + * @switchdev_port_obj_add: Add an object to port (see switchdev_obj_*). * - * @switchdev_port_obj_del: Delete an object from port (see switchdev_obj). + * @switchdev_port_obj_del: Delete an object from port (see switchdev_obj_*). * - * @switchdev_port_obj_dump: Dump port objects (see switchdev_obj). + * @switchdev_port_obj_dump: Dump port objects (see switchdev_obj_*). */ struct switchdev_ops { int (*switchdev_port_attr_get)(struct net_device *dev, struct switchdev_attr *attr); int (*switchdev_port_attr_set)(struct net_device *dev, - struct switchdev_attr *attr); + struct switchdev_attr *attr, + struct switchdev_trans *trans); int (*switchdev_port_obj_add)(struct net_device *dev, - struct switchdev_obj *obj); + enum switchdev_obj_id id, + const void *obj, + struct switchdev_trans *trans); int (*switchdev_port_obj_del)(struct net_device *dev, - struct switchdev_obj *obj); + enum switchdev_obj_id id, + const void *obj); int (*switchdev_port_obj_dump)(struct net_device *dev, - struct switchdev_obj *obj); + enum switchdev_obj_id id, void *obj, + int (*cb)(void *obj)); }; enum switchdev_notifier_type { @@ -130,9 +152,12 @@ int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr); int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr); -int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj); -int switchdev_port_obj_del(struct net_device *dev, struct switchdev_obj *obj); -int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj); +int switchdev_port_obj_add(struct net_device *dev, enum switchdev_obj_id id, + const void *obj); +int switchdev_port_obj_del(struct net_device *dev, enum switchdev_obj_id id, + const void *obj); +int switchdev_port_obj_dump(struct net_device *dev, enum switchdev_obj_id id, + void *obj, int (*cb)(void *obj)); int register_switchdev_notifier(struct notifier_block *nb); int unregister_switchdev_notifier(struct notifier_block *nb); int call_switchdev_notifiers(unsigned long val, struct net_device *dev, @@ -177,19 +202,22 @@ static inline int switchdev_port_attr_set(struct net_device *dev, } static inline int switchdev_port_obj_add(struct net_device *dev, - struct switchdev_obj *obj) + enum switchdev_obj_id id, + const void *obj) { return -EOPNOTSUPP; } static inline int switchdev_port_obj_del(struct net_device *dev, - struct switchdev_obj *obj) + enum switchdev_obj_id id, + const void *obj) { return -EOPNOTSUPP; } static inline int switchdev_port_obj_dump(struct net_device *dev, - struct switchdev_obj *obj) + enum switchdev_obj_id id, void *obj, + int (*cb)(void *obj)) { return -EOPNOTSUPP; } diff --git a/include/net/tc_act/tc_connmark.h b/include/net/tc_act/tc_connmark.h index 5c1104c2e24f..02caa406611b 100644 --- a/include/net/tc_act/tc_connmark.h +++ b/include/net/tc_act/tc_connmark.h @@ -5,6 +5,7 @@ struct tcf_connmark_info { struct tcf_common common; + struct net *net; u16 zone; }; diff --git a/include/net/tcp.h b/include/net/tcp.h index 0cab28cd43a9..2c7dfe52f473 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -365,8 +365,7 @@ void tcp_wfree(struct sk_buff *skb); void tcp_write_timer_handler(struct sock *sk); void tcp_delack_timer_handler(struct sock *sk); int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg); -int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, - const struct tcphdr *th, unsigned int len); +int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb); void tcp_rcv_established(struct sock *sk, struct sk_buff *skb, const struct tcphdr *th, unsigned int len); void tcp_rcv_space_adjust(struct sock *sk); @@ -451,17 +450,17 @@ void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb); void tcp_v4_mtu_reduced(struct sock *sk); void tcp_req_err(struct sock *sk, u32 seq); int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb); -struct sock *tcp_create_openreq_child(struct sock *sk, +struct sock *tcp_create_openreq_child(const struct sock *sk, struct request_sock *req, struct sk_buff *skb); void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst); -struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, +struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst); int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb); int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); int tcp_connect(struct sock *sk); -struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, +struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, struct request_sock *req, struct tcp_fastopen_cookie *foc); int tcp_disconnect(struct sock *sk, int flags); @@ -492,8 +491,9 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb); /* syncookies: remember time of last synqueue overflow * But do not dirty this field too often (once per second is enough) + * It is racy as we do not hold a lock, but race is very minor. */ -static inline void tcp_synq_overflow(struct sock *sk) +static inline void tcp_synq_overflow(const struct sock *sk) { unsigned long last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp; unsigned long now = jiffies; @@ -520,8 +520,7 @@ static inline u32 tcp_cookie_time(void) u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th, u16 *mssp); -__u32 cookie_v4_init_sequence(struct sock *sk, const struct sk_buff *skb, - __u16 *mss); +__u32 cookie_v4_init_sequence(const struct sk_buff *skb, __u16 *mss); __u32 cookie_init_timestamp(struct request_sock *req); bool cookie_timestamp_decode(struct tcp_options_received *opt); bool cookie_ecn_ok(const struct tcp_options_received *opt, @@ -534,8 +533,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb); u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph, const struct tcphdr *th, u16 *mssp); -__u32 cookie_v6_init_sequence(struct sock *sk, const struct sk_buff *skb, - __u16 *mss); +__u32 cookie_v6_init_sequence(const struct sk_buff *skb, __u16 *mss); #endif /* tcp_output.c */ @@ -565,6 +563,7 @@ bool tcp_schedule_loss_probe(struct sock *sk); /* tcp_input.c */ void tcp_resume_early_retransmit(struct sock *sk); void tcp_rearm_rto(struct sock *sk); +void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req); void tcp_reset(struct sock *sk); /* tcp_timer.c */ @@ -1206,7 +1205,8 @@ static inline int tcp_full_space(const struct sock *sk) } extern void tcp_openreq_init_rwin(struct request_sock *req, - struct sock *sk, struct dst_entry *dst); + const struct sock *sk_listener, + const struct dst_entry *dst); void tcp_enter_memory_pressure(struct sock *sk); @@ -1370,16 +1370,16 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, int family, const u8 *newkey, u8 newkeylen, gfp_t gfp); int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family); -struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk, +struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, const struct sock *addr_sk); #ifdef CONFIG_TCP_MD5SIG -struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk, +struct tcp_md5sig_key *tcp_md5_do_lookup(const struct sock *sk, const union tcp_md5_addr *addr, int family); #define tcp_twsk_md5_key(twsk) ((twsk)->tw_md5_key) #else -static inline struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk, +static inline struct tcp_md5sig_key *tcp_md5_do_lookup(const struct sock *sk, const union tcp_md5_addr *addr, int family) { @@ -1420,10 +1420,10 @@ void tcp_free_fastopen_req(struct tcp_sock *tp); extern struct tcp_fastopen_context __rcu *tcp_fastopen_ctx; int tcp_fastopen_reset_cipher(void *key, unsigned int len); -bool tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, - struct request_sock *req, - struct tcp_fastopen_cookie *foc, - struct dst_entry *dst); +struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct tcp_fastopen_cookie *foc, + struct dst_entry *dst); void tcp_fastopen_init_key_once(bool publish); #define TCP_FASTOPEN_KEY_LENGTH 16 @@ -1674,7 +1674,7 @@ int tcp4_proc_init(void); void tcp4_proc_exit(void); #endif -int tcp_rtx_synack(struct sock *sk, struct request_sock *req); +int tcp_rtx_synack(const struct sock *sk, struct request_sock *req); int tcp_conn_request(struct request_sock_ops *rsk_ops, const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct sk_buff *skb); @@ -1682,7 +1682,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, /* TCP af-specific functions */ struct tcp_sock_af_ops { #ifdef CONFIG_TCP_MD5SIG - struct tcp_md5sig_key *(*md5_lookup) (struct sock *sk, + struct tcp_md5sig_key *(*md5_lookup) (const struct sock *sk, const struct sock *addr_sk); int (*calc_md5_hash)(char *location, const struct tcp_md5sig_key *md5, @@ -1697,24 +1697,25 @@ struct tcp_sock_af_ops { struct tcp_request_sock_ops { u16 mss_clamp; #ifdef CONFIG_TCP_MD5SIG - struct tcp_md5sig_key *(*req_md5_lookup)(struct sock *sk, + struct tcp_md5sig_key *(*req_md5_lookup)(const struct sock *sk, const struct sock *addr_sk); int (*calc_md5_hash) (char *location, const struct tcp_md5sig_key *md5, const struct sock *sk, const struct sk_buff *skb); #endif - void (*init_req)(struct request_sock *req, struct sock *sk, + void (*init_req)(struct request_sock *req, + const struct sock *sk_listener, struct sk_buff *skb); #ifdef CONFIG_SYN_COOKIES - __u32 (*cookie_init_seq)(struct sock *sk, const struct sk_buff *skb, + __u32 (*cookie_init_seq)(const struct sk_buff *skb, __u16 *mss); #endif - struct dst_entry *(*route_req)(struct sock *sk, struct flowi *fl, + struct dst_entry *(*route_req)(const struct sock *sk, struct flowi *fl, const struct request_sock *req, bool *strict); __u32 (*init_seq)(const struct sk_buff *skb); - int (*send_synack)(struct sock *sk, struct dst_entry *dst, + int (*send_synack)(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, u16 queue_mapping, struct tcp_fastopen_cookie *foc); void (*queue_hash_add)(struct sock *sk, struct request_sock *req, @@ -1723,14 +1724,16 @@ struct tcp_request_sock_ops { #ifdef CONFIG_SYN_COOKIES static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops, - struct sock *sk, struct sk_buff *skb, + const struct sock *sk, struct sk_buff *skb, __u16 *mss) { - return ops->cookie_init_seq(sk, skb, mss); + tcp_synq_overflow(sk); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESSENT); + return ops->cookie_init_seq(skb, mss); } #else static inline __u32 cookie_init_sequence(const struct tcp_request_sock_ops *ops, - struct sock *sk, struct sk_buff *skb, + const struct sock *sk, struct sk_buff *skb, __u16 *mss) { return 0; diff --git a/include/net/vrf.h b/include/net/vrf.h deleted file mode 100644 index 593e6094ddd4..000000000000 --- a/include/net/vrf.h +++ /dev/null @@ -1,178 +0,0 @@ -/* - * include/net/net_vrf.h - adds vrf dev structure definitions - * Copyright (c) 2015 Cumulus Networks - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - */ - -#ifndef __LINUX_NET_VRF_H -#define __LINUX_NET_VRF_H - -struct net_vrf_dev { - struct rcu_head rcu; - int ifindex; /* ifindex of master dev */ - u32 tb_id; /* table id for VRF */ -}; - -struct slave { - struct list_head list; - struct net_device *dev; -}; - -struct slave_queue { - struct list_head all_slaves; -}; - -struct net_vrf { - struct slave_queue queue; - struct rtable *rth; - u32 tb_id; -}; - - -#if IS_ENABLED(CONFIG_NET_VRF) -/* called with rcu_read_lock() */ -static inline int vrf_master_ifindex_rcu(const struct net_device *dev) -{ - struct net_vrf_dev *vrf_ptr; - int ifindex = 0; - - if (!dev) - return 0; - - if (netif_is_vrf(dev)) { - ifindex = dev->ifindex; - } else { - vrf_ptr = rcu_dereference(dev->vrf_ptr); - if (vrf_ptr) - ifindex = vrf_ptr->ifindex; - } - - return ifindex; -} - -static inline int vrf_master_ifindex(const struct net_device *dev) -{ - int ifindex; - - rcu_read_lock(); - ifindex = vrf_master_ifindex_rcu(dev); - rcu_read_unlock(); - - return ifindex; -} - -/* called with rcu_read_lock */ -static inline u32 vrf_dev_table_rcu(const struct net_device *dev) -{ - u32 tb_id = 0; - - if (dev) { - struct net_vrf_dev *vrf_ptr; - - vrf_ptr = rcu_dereference(dev->vrf_ptr); - if (vrf_ptr) - tb_id = vrf_ptr->tb_id; - } - return tb_id; -} - -static inline u32 vrf_dev_table(const struct net_device *dev) -{ - u32 tb_id; - - rcu_read_lock(); - tb_id = vrf_dev_table_rcu(dev); - rcu_read_unlock(); - - return tb_id; -} - -static inline u32 vrf_dev_table_ifindex(struct net *net, int ifindex) -{ - struct net_device *dev; - u32 tb_id = 0; - - if (!ifindex) - return 0; - - rcu_read_lock(); - - dev = dev_get_by_index_rcu(net, ifindex); - if (dev) - tb_id = vrf_dev_table_rcu(dev); - - rcu_read_unlock(); - - return tb_id; -} - -/* called with rtnl */ -static inline u32 vrf_dev_table_rtnl(const struct net_device *dev) -{ - u32 tb_id = 0; - - if (dev) { - struct net_vrf_dev *vrf_ptr; - - vrf_ptr = rtnl_dereference(dev->vrf_ptr); - if (vrf_ptr) - tb_id = vrf_ptr->tb_id; - } - return tb_id; -} - -/* caller has already checked netif_is_vrf(dev) */ -static inline struct rtable *vrf_dev_get_rth(const struct net_device *dev) -{ - struct rtable *rth = ERR_PTR(-ENETUNREACH); - struct net_vrf *vrf = netdev_priv(dev); - - if (vrf) { - rth = vrf->rth; - atomic_inc(&rth->dst.__refcnt); - } - return rth; -} - -#else -static inline int vrf_master_ifindex_rcu(const struct net_device *dev) -{ - return 0; -} - -static inline int vrf_master_ifindex(const struct net_device *dev) -{ - return 0; -} - -static inline u32 vrf_dev_table_rcu(const struct net_device *dev) -{ - return 0; -} - -static inline u32 vrf_dev_table(const struct net_device *dev) -{ - return 0; -} - -static inline u32 vrf_dev_table_ifindex(struct net *net, int ifindex) -{ - return 0; -} - -static inline u32 vrf_dev_table_rtnl(const struct net_device *dev) -{ - return 0; -} - -static inline struct rtable *vrf_dev_get_rth(const struct net_device *dev) -{ - return ERR_PTR(-ENETUNREACH); -} -#endif - -#endif /* __LINUX_NET_VRF_H */ diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 480a319b4c92..c1c899c3a51b 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -152,7 +152,10 @@ struct vxlan_config { struct vxlan_dev { struct hlist_node hlist; /* vni hash table */ struct list_head next; /* vxlan's per namespace list */ - struct vxlan_sock *vn_sock; /* listening socket */ + struct vxlan_sock *vn4_sock; /* listening socket for IPv4 */ +#if IS_ENABLED(CONFIG_IPV6) + struct vxlan_sock *vn6_sock; /* listening socket for IPv6 */ +#endif struct net_device *dev; struct net *net; /* netns for packet i/o */ struct vxlan_rdst default_dst; /* default destination */ @@ -195,9 +198,14 @@ struct vxlan_dev { struct net_device *vxlan_dev_create(struct net *net, const char *name, u8 name_assign_type, struct vxlan_config *conf); -static inline __be16 vxlan_dev_dst_port(struct vxlan_dev *vxlan) +static inline __be16 vxlan_dev_dst_port(struct vxlan_dev *vxlan, + unsigned short family) { - return inet_sk(vxlan->vn_sock->sock->sk)->inet_sport; +#if IS_ENABLED(CONFIG_IPV6) + if (family == AF_INET6) + return inet_sk(vxlan->vn6_sock->sock->sk)->inet_sport; +#endif + return inet_sk(vxlan->vn4_sock->sock->sk)->inet_sport; } static inline netdev_features_t vxlan_features_check(struct sk_buff *skb, diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 312e3fee9ccf..fd176106909a 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -296,8 +296,6 @@ struct xfrm_policy_afinfo { struct flowi *fl, int reverse); int (*get_tos)(const struct flowi *fl); - void (*init_dst)(struct net *net, - struct xfrm_dst *dst); int (*init_path)(struct xfrm_dst *path, struct dst_entry *dst, int nfheader_len); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 92a48e2d5461..4ec0b5488294 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -272,6 +272,14 @@ enum bpf_func_id { BPF_FUNC_skb_get_tunnel_key, BPF_FUNC_skb_set_tunnel_key, BPF_FUNC_perf_event_read, /* u64 bpf_perf_event_read(&map, index) */ + /** + * bpf_redirect(ifindex, flags) - redirect to another netdev + * @ifindex: ifindex of the net device + * @flags: bit 0 - if set, redirect to ingress instead of egress + * other bits - reserved + * Return: TC_ACT_REDIRECT + */ + BPF_FUNC_redirect, __BPF_FUNC_MAX_ID, }; @@ -293,6 +301,7 @@ struct __sk_buff { __u32 tc_index; __u32 cb[5]; __u32 hash; + __u32 tc_classid; }; struct bpf_tunnel_key { diff --git a/include/uapi/linux/if_arcnet.h b/include/uapi/linux/if_arcnet.h index 46e34bd0e783..cfb642f8e7bd 100644 --- a/include/uapi/linux/if_arcnet.h +++ b/include/uapi/linux/if_arcnet.h @@ -19,7 +19,6 @@ #include <linux/types.h> #include <linux/if_ether.h> - /* * These are the defined ARCnet Protocol ID's. */ @@ -57,42 +56,40 @@ * The RFC1201-specific components of an arcnet packet header. */ struct arc_rfc1201 { - __u8 proto; /* protocol ID field - varies */ - __u8 split_flag; /* for use with split packets */ - __be16 sequence; /* sequence number */ - __u8 payload[0]; /* space remaining in packet (504 bytes)*/ + __u8 proto; /* protocol ID field - varies */ + __u8 split_flag; /* for use with split packets */ + __be16 sequence; /* sequence number */ + __u8 payload[0]; /* space remaining in packet (504 bytes)*/ }; #define RFC1201_HDR_SIZE 4 - /* * The RFC1051-specific components. */ struct arc_rfc1051 { - __u8 proto; /* ARC_P_RFC1051_ARP/RFC1051_IP */ - __u8 payload[0]; /* 507 bytes */ + __u8 proto; /* ARC_P_RFC1051_ARP/RFC1051_IP */ + __u8 payload[0]; /* 507 bytes */ }; #define RFC1051_HDR_SIZE 1 - /* * The ethernet-encap-specific components. We have a real ethernet header * and some data. */ struct arc_eth_encap { - __u8 proto; /* Always ARC_P_ETHER */ - struct ethhdr eth; /* standard ethernet header (yuck!) */ - __u8 payload[0]; /* 493 bytes */ + __u8 proto; /* Always ARC_P_ETHER */ + struct ethhdr eth; /* standard ethernet header (yuck!) */ + __u8 payload[0]; /* 493 bytes */ }; #define ETH_ENCAP_HDR_SIZE 14 - struct arc_cap { __u8 proto; - __u8 cookie[sizeof(int)]; /* Actually NOT sent over the network */ + __u8 cookie[sizeof(int)]; + /* Actually NOT sent over the network */ union { __u8 ack; - __u8 raw[0]; /* 507 bytes */ + __u8 raw[0]; /* 507 bytes */ } mes; }; @@ -105,9 +102,9 @@ struct arc_cap { * driver. */ struct arc_hardware { - __u8 source, /* source ARCnet - filled in automagically */ - dest, /* destination ARCnet - 0 for broadcast */ - offset[2]; /* offset bytes (some weird semantics) */ + __u8 source; /* source ARCnet - filled in automagically */ + __u8 dest; /* destination ARCnet - 0 for broadcast */ + __u8 offset[2]; /* offset bytes (some weird semantics) */ }; #define ARC_HDR_SIZE 4 @@ -116,17 +113,17 @@ struct arc_hardware { * when you do a raw packet capture). */ struct archdr { - /* hardware requirements */ - struct arc_hardware hard; - - /* arcnet encapsulation-specific bits */ - union { - struct arc_rfc1201 rfc1201; - struct arc_rfc1051 rfc1051; - struct arc_eth_encap eth_encap; - struct arc_cap cap; - __u8 raw[0]; /* 508 bytes */ - } soft; + /* hardware requirements */ + struct arc_hardware hard; + + /* arcnet encapsulation-specific bits */ + union { + struct arc_rfc1201 rfc1201; + struct arc_rfc1051 rfc1051; + struct arc_eth_encap eth_encap; + struct arc_cap cap; + __u8 raw[0]; /* 508 bytes */ + } soft; }; #endif /* _LINUX_IF_ARCNET_H */ diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index 3635b7797508..18db14477bdd 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -127,6 +127,7 @@ enum { #define BRIDGE_VLAN_INFO_UNTAGGED (1<<2) /* VLAN egresses untagged */ #define BRIDGE_VLAN_INFO_RANGE_BEGIN (1<<3) /* VLAN is start of vlan range */ #define BRIDGE_VLAN_INFO_RANGE_END (1<<4) /* VLAN is end of vlan range */ +#define BRIDGE_VLAN_INFO_BRENTRY (1<<5) /* Global bridge VLAN entry */ struct bridge_vlan_info { __u16 flags; diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h index 6f3fe16cd22a..f095155d8749 100644 --- a/include/uapi/linux/netlink.h +++ b/include/uapi/linux/netlink.h @@ -54,6 +54,7 @@ struct nlmsghdr { #define NLM_F_ACK 4 /* Reply with ack, with zero or error code */ #define NLM_F_ECHO 8 /* Echo this request */ #define NLM_F_DUMP_INTR 16 /* Dump was inconsistent due to sequence change */ +#define NLM_F_DUMP_FILTERED 32 /* Dump was filtered as requested */ /* Modifiers to GET request */ #define NLM_F_ROOT 0x100 /* specify tree root */ diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 4f0d1bc3647d..439873775d49 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -87,6 +87,7 @@ enum { #define TC_ACT_STOLEN 4 #define TC_ACT_QUEUED 5 #define TC_ACT_REPEAT 6 +#define TC_ACT_REDIRECT 7 #define TC_ACT_JUMP 0x10000000 /* Action type identifiers*/ @@ -373,6 +374,8 @@ enum { /* BPF classifier */ +#define TCA_BPF_FLAG_ACT_DIRECT (1 << 0) + enum { TCA_BPF_UNSPEC, TCA_BPF_ACT, @@ -382,6 +385,7 @@ enum { TCA_BPF_OPS, TCA_BPF_FD, TCA_BPF_NAME, + TCA_BPF_FLAGS, __TCA_BPF_MAX, }; diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 702024769c74..4db0b3ccb497 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -270,6 +270,7 @@ enum rt_scope_t { #define RTM_F_CLONED 0x200 /* This route is cloned */ #define RTM_F_EQUALIZE 0x400 /* Multipath equalizer: NI */ #define RTM_F_PREFIX 0x800 /* Prefix addresses */ +#define RTM_F_LOOKUP_TABLE 0x1000 /* set rtm_table to FIB lookup result */ /* Reserved table identifiers */ @@ -666,6 +667,7 @@ struct tcamsg { #define RTEXT_FILTER_VF (1 << 0) #define RTEXT_FILTER_BRVLAN (1 << 1) #define RTEXT_FILTER_BRVLAN_COMPRESSED (1 << 2) +#define RTEXT_FILTER_SKIP_STATS (1 << 3) /* End of information exported to user level */ diff --git a/include/uapi/linux/usb/cdc.h b/include/uapi/linux/usb/cdc.h index b6a9cdd6e096..e2bc417b243b 100644 --- a/include/uapi/linux/usb/cdc.h +++ b/include/uapi/linux/usb/cdc.h @@ -6,8 +6,8 @@ * firmware based USB peripherals. */ -#ifndef __LINUX_USB_CDC_H -#define __LINUX_USB_CDC_H +#ifndef __UAPI_LINUX_USB_CDC_H +#define __UAPI_LINUX_USB_CDC_H #include <linux/types.h> @@ -444,4 +444,4 @@ struct usb_cdc_ncm_ndp_input_size { #define USB_CDC_NCM_CRC_NOT_APPENDED 0x00 #define USB_CDC_NCM_CRC_APPENDED 0x01 -#endif /* __LINUX_USB_CDC_H */ +#endif /* __UAPI_LINUX_USB_CDC_H */ diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index f9a59f6cabd2..4c213864ec45 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -1761,6 +1761,7 @@ void free_percpu_irq(unsigned int irq, void __percpu *dev_id) kfree(__free_percpu_irq(irq, dev_id)); chip_bus_sync_unlock(desc); } +EXPORT_SYMBOL_GPL(free_percpu_irq); /** * setup_percpu_irq - setup a per-cpu interrupt @@ -1790,9 +1791,10 @@ int setup_percpu_irq(unsigned int irq, struct irqaction *act) * @devname: An ascii name for the claiming device * @dev_id: A percpu cookie passed back to the handler function * - * This call allocates interrupt resources, but doesn't - * automatically enable the interrupt. It has to be done on each - * CPU using enable_percpu_irq(). + * This call allocates interrupt resources and enables the + * interrupt on the local CPU. If the interrupt is supposed to be + * enabled on other CPUs, it has to be done on each CPU using + * enable_percpu_irq(). * * Dev_id must be globally unique. It is a per-cpu variable, and * the handler gets called with the interrupted CPU's instance of @@ -1831,6 +1833,7 @@ int request_percpu_irq(unsigned int irq, irq_handler_t handler, return retval; } +EXPORT_SYMBOL_GPL(request_percpu_irq); /** * irq_get_irqchip_state - returns the irqchip state of a interrupt. diff --git a/net/6lowpan/iphc.c b/net/6lowpan/iphc.c index 1e0071fdcf72..78c8a495b571 100644 --- a/net/6lowpan/iphc.c +++ b/net/6lowpan/iphc.c @@ -366,7 +366,18 @@ lowpan_header_decompress(struct sk_buff *skb, struct net_device *dev, return err; } - hdr.payload_len = htons(skb->len); + switch (lowpan_priv(dev)->lltype) { + case LOWPAN_LLTYPE_IEEE802154: + if (lowpan_802154_cb(skb)->d_size) + hdr.payload_len = htons(lowpan_802154_cb(skb)->d_size - + sizeof(struct ipv6hdr)); + else + hdr.payload_len = htons(skb->len); + break; + default: + hdr.payload_len = htons(skb->len); + break; + } pr_debug("skb headroom size = %d, data length = %d\n", skb_headroom(skb), skb->len); diff --git a/net/6lowpan/nhc_udp.c b/net/6lowpan/nhc_udp.c index c6bcaeb428ae..72d0b57eb6e5 100644 --- a/net/6lowpan/nhc_udp.c +++ b/net/6lowpan/nhc_udp.c @@ -71,7 +71,18 @@ static int udp_uncompress(struct sk_buff *skb, size_t needed) * here, we obtain the hint from the remaining size of the * frame */ - uh.len = htons(skb->len + sizeof(struct udphdr)); + switch (lowpan_priv(skb->dev)->lltype) { + case LOWPAN_LLTYPE_IEEE802154: + if (lowpan_802154_cb(skb)->d_size) + uh.len = htons(lowpan_802154_cb(skb)->d_size - + sizeof(struct ipv6hdr)); + else + uh.len = htons(skb->len + sizeof(struct udphdr)); + break; + default: + uh.len = htons(skb->len + sizeof(struct udphdr)); + break; + } pr_debug("uncompressed UDP length: src = %d", ntohs(uh.len)); /* replace the compressed UDP head by the uncompressed UDP diff --git a/net/Kconfig b/net/Kconfig index 7021c1bf44d6..127da94ae25e 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -232,6 +232,7 @@ source "net/netlink/Kconfig" source "net/mpls/Kconfig" source "net/hsr/Kconfig" source "net/switchdev/Kconfig" +source "net/l3mdev/Kconfig" config RPS bool diff --git a/net/Makefile b/net/Makefile index 3995613e5510..a5d04098dfce 100644 --- a/net/Makefile +++ b/net/Makefile @@ -74,3 +74,6 @@ obj-$(CONFIG_HSR) += hsr/ ifneq ($(CONFIG_NET_SWITCHDEV),) obj-y += switchdev/ endif +ifneq ($(CONFIG_NET_L3_MASTER_DEV),) +obj-y += l3mdev/ +endif diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index adcbc74c2432..a7cdd99ec3f1 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -693,7 +693,8 @@ static void hci_init3_req(struct hci_request *req, unsigned long opt) hci_setup_event_mask(req); - if (hdev->commands[6] & 0x20) { + if (hdev->commands[6] & 0x20 && + !test_bit(HCI_QUIRK_BROKEN_STORED_LINK_KEY, &hdev->quirks)) { struct hci_cp_read_stored_link_key cp; bacpy(&cp.bdaddr, BDADDR_ANY); @@ -1548,7 +1549,7 @@ static void hci_pend_le_actions_clear(struct hci_dev *hdev) BT_DBG("All LE pending actions cleared"); } -static int hci_dev_do_close(struct hci_dev *hdev) +int hci_dev_do_close(struct hci_dev *hdev) { BT_DBG("%s %p", hdev->name, hdev); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 186041866315..8acec932123a 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -4719,6 +4719,27 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, struct hci_conn *conn; bool match; u32 flags; + u8 *ptr, real_len; + + /* Find the end of the data in case the report contains padded zero + * bytes at the end causing an invalid length value. + * + * When data is NULL, len is 0 so there is no need for extra ptr + * check as 'ptr < data + 0' is already false in such case. + */ + for (ptr = data; ptr < data + len && *ptr; ptr += *ptr + 1) { + if (ptr + 1 + *ptr > data + len) + break; + } + + real_len = ptr - data; + + /* Adjust for actual length */ + if (len != real_len) { + BT_ERR_RATELIMITED("%s advertising data length corrected", + hdev->name); + len = real_len; + } /* If the direct address is present, then this report is from * a LE Direct Advertising Report event. In that case it is diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index f2d30d1156c9..150556345263 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -503,7 +503,16 @@ static int hci_sock_release(struct socket *sock) if (hdev) { if (hci_pi(sk)->channel == HCI_CHANNEL_USER) { - hci_dev_close(hdev->id); + /* When releasing an user channel exclusive access, + * call hci_dev_do_close directly instead of calling + * hci_dev_close to ensure the exclusive access will + * be released and the controller brought back down. + * + * The checking of HCI_AUTO_OFF is not needed in this + * case since it will have been cleared already when + * opening the user channel. + */ + hci_dev_do_close(hdev); hci_dev_clear_flag(hdev, HCI_USER_CHANNEL); mgmt_index_added(hdev); } diff --git a/net/bluetooth/lib.c b/net/bluetooth/lib.c index b36bc0415854..8b4cdce3f62e 100644 --- a/net/bluetooth/lib.c +++ b/net/bluetooth/lib.c @@ -166,3 +166,19 @@ void bt_err(const char *format, ...) va_end(args); } EXPORT_SYMBOL(bt_err); + +void bt_err_ratelimited(const char *format, ...) +{ + struct va_format vaf; + va_list args; + + va_start(args, format); + + vaf.fmt = format; + vaf.va = &args; + + pr_err_ratelimited("%pV", &vaf); + + va_end(args); +} +EXPORT_SYMBOL(bt_err_ratelimited); diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 0510a577a7b5..25644e1bc479 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -495,7 +495,7 @@ static int smp_ah(struct crypto_blkcipher *tfm, const u8 irk[16], } /* The output of the random address function ah is: - * ah(h, r) = e(k, r') mod 2^24 + * ah(k, r) = e(k, r') mod 2^24 * The output of the security function e is then truncated to 24 bits * by taking the least significant 24 bits of the output of e as the * result of ah. diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 6ed2feb51e3c..bdfb9544ca03 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -56,7 +56,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) skb_reset_mac_header(skb); skb_pull(skb, ETH_HLEN); - if (!br_allowed_ingress(br, br_get_vlan_info(br), skb, &vid)) + if (!br_allowed_ingress(br, br_vlan_group(br), skb, &vid)) goto out; if (is_broadcast_ether_addr(dest)) @@ -391,7 +391,7 @@ void br_dev_setup(struct net_device *dev) br->bridge_max_age = br->max_age = 20 * HZ; br->bridge_hello_time = br->hello_time = 2 * HZ; br->bridge_forward_delay = br->forward_delay = 15 * HZ; - br->ageing_time = 300 * HZ; + br->ageing_time = BR_DEFAULT_AGEING_TIME; br_netfilter_rtable_init(br); br_stp_timer_init(br); diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 9e9875da0a4f..7826782d62ab 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -133,15 +133,12 @@ static void fdb_del_hw_addr(struct net_bridge *br, const unsigned char *addr) static void fdb_del_external_learn(struct net_bridge_fdb_entry *f) { - struct switchdev_obj obj = { - .id = SWITCHDEV_OBJ_PORT_FDB, - .u.fdb = { - .addr = f->addr.addr, - .vid = f->vlan_id, - }, + struct switchdev_obj_fdb fdb = { + .addr = f->addr.addr, + .vid = f->vlan_id, }; - switchdev_port_obj_del(f->dst->dev, &obj); + switchdev_port_obj_del(f->dst->dev, SWITCHDEV_OBJ_PORT_FDB, &fdb); } static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f) @@ -163,22 +160,27 @@ static void fdb_delete_local(struct net_bridge *br, struct net_bridge_fdb_entry *f) { const unsigned char *addr = f->addr.addr; - u16 vid = f->vlan_id; + struct net_bridge_vlan_group *vg; + const struct net_bridge_vlan *v; struct net_bridge_port *op; + u16 vid = f->vlan_id; /* Maybe another port has same hw addr? */ list_for_each_entry(op, &br->port_list, list) { + vg = nbp_vlan_group(op); if (op != p && ether_addr_equal(op->dev->dev_addr, addr) && - (!vid || nbp_vlan_find(op, vid))) { + (!vid || br_vlan_find(vg, vid))) { f->dst = op; f->added_by_user = 0; return; } } + vg = br_vlan_group(br); + v = br_vlan_find(vg, vid); /* Maybe bridge device has same hw addr? */ if (p && ether_addr_equal(br->dev->dev_addr, addr) && - (!vid || br_vlan_find(br, vid))) { + (!vid || (v && br_vlan_should_use(v)))) { f->dst = NULL; f->added_by_user = 0; return; @@ -203,14 +205,14 @@ void br_fdb_find_delete_local(struct net_bridge *br, void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr) { + struct net_bridge_vlan_group *vg; struct net_bridge *br = p->br; - struct net_port_vlans *pv = nbp_get_vlan_info(p); - bool no_vlan = !pv; + struct net_bridge_vlan *v; int i; - u16 vid; spin_lock_bh(&br->hash_lock); + vg = nbp_vlan_group(p); /* Search all chains since old address/hash is unknown */ for (i = 0; i < BR_HASH_SIZE; i++) { struct hlist_node *h; @@ -226,7 +228,7 @@ void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr) * configured, we can safely be done at * this point. */ - if (no_vlan) + if (!vg || !vg->num_vlans) goto insert; } } @@ -236,15 +238,15 @@ insert: /* insert new address, may fail if invalid address or dup. */ fdb_insert(br, p, newaddr, 0); - if (no_vlan) + if (!vg || !vg->num_vlans) goto done; /* Now add entries for every VLAN configured on the port. * This function runs under RTNL so the bitmap will not change * from under us. */ - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) - fdb_insert(br, p, newaddr, vid); + list_for_each_entry(v, &vg->vlan_list, vlist) + fdb_insert(br, p, newaddr, v->vid); done: spin_unlock_bh(&br->hash_lock); @@ -252,9 +254,9 @@ done: void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr) { + struct net_bridge_vlan_group *vg; struct net_bridge_fdb_entry *f; - struct net_port_vlans *pv; - u16 vid = 0; + struct net_bridge_vlan *v; spin_lock_bh(&br->hash_lock); @@ -264,20 +266,18 @@ void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr) fdb_delete_local(br, NULL, f); fdb_insert(br, NULL, newaddr, 0); - + vg = br_vlan_group(br); + if (!vg || !vg->num_vlans) + goto out; /* Now remove and add entries for every VLAN configured on the * bridge. This function runs under RTNL so the bitmap will not * change from under us. */ - pv = br_get_vlan_info(br); - if (!pv) - goto out; - - for_each_set_bit_from(vid, pv->vlan_bitmap, VLAN_N_VID) { - f = __br_fdb_get(br, br->dev->dev_addr, vid); + list_for_each_entry(v, &vg->vlan_list, vlist) { + f = __br_fdb_get(br, br->dev->dev_addr, v->vid); if (f && f->is_local && !f->dst) fdb_delete_local(br, NULL, f); - fdb_insert(br, NULL, newaddr, vid); + fdb_insert(br, NULL, newaddr, v->vid); } out: spin_unlock_bh(&br->hash_lock); @@ -299,6 +299,8 @@ void br_fdb_cleanup(unsigned long _data) unsigned long this_timer; if (f->is_static) continue; + if (f->added_by_external_learn) + continue; this_timer = f->updated + delay; if (time_before_eq(this_timer, jiffies)) fdb_delete(br, f); @@ -842,9 +844,10 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, u16 nlh_flags) { + struct net_bridge_vlan_group *vg; struct net_bridge_port *p; + struct net_bridge_vlan *v; int err = 0; - struct net_port_vlans *pv; if (!(ndm->ndm_state & (NUD_PERMANENT|NUD_NOARP|NUD_REACHABLE))) { pr_info("bridge: RTM_NEWNEIGH with invalid state %#x\n", ndm->ndm_state); @@ -863,9 +866,10 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], return -EINVAL; } - pv = nbp_get_vlan_info(p); + vg = nbp_vlan_group(p); if (vid) { - if (!pv || !test_bit(vid, pv->vlan_bitmap)) { + v = br_vlan_find(vg, vid); + if (!v) { pr_info("bridge: RTM_NEWNEIGH with unconfigured " "vlan %d on port %s\n", vid, dev->name); return -EINVAL; @@ -875,15 +879,15 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], err = __br_fdb_add(ndm, p, addr, nlh_flags, vid); } else { err = __br_fdb_add(ndm, p, addr, nlh_flags, 0); - if (err || !pv) + if (err || !vg || !vg->num_vlans) goto out; /* We have vlans configured on this port and user didn't * specify a VLAN. To be nice, add/update entry for every * vlan on this port. */ - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { - err = __br_fdb_add(ndm, p, addr, nlh_flags, vid); + list_for_each_entry(v, &vg->vlan_list, vlist) { + err = __br_fdb_add(ndm, p, addr, nlh_flags, v->vid); if (err) goto out; } @@ -925,9 +929,10 @@ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid) { + struct net_bridge_vlan_group *vg; struct net_bridge_port *p; + struct net_bridge_vlan *v; int err; - struct net_port_vlans *pv; p = br_port_get_rtnl(dev); if (p == NULL) { @@ -936,9 +941,10 @@ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], return -EINVAL; } - pv = nbp_get_vlan_info(p); + vg = nbp_vlan_group(p); if (vid) { - if (!pv || !test_bit(vid, pv->vlan_bitmap)) { + v = br_vlan_find(vg, vid); + if (!v) { pr_info("bridge: RTM_DELNEIGH with unconfigured " "vlan %d on port %s\n", vid, dev->name); return -EINVAL; @@ -948,16 +954,11 @@ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], } else { err = -ENOENT; err &= __br_fdb_delete(p, addr, 0); - if (!pv) + if (!vg || !vg->num_vlans) goto out; - /* We have vlans configured on this port and user didn't - * specify a VLAN. To be nice, add/update entry for every - * vlan on this port. - */ - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { - err &= __br_fdb_delete(p, addr, vid); - } + list_for_each_entry(v, &vg->vlan_list, vlist) + err &= __br_fdb_delete(p, addr, v->vid); } out: return err; diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index fa7bfced888e..6d5ed795c3e2 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -30,12 +30,14 @@ static int deliver_clone(const struct net_bridge_port *prev, static inline int should_deliver(const struct net_bridge_port *p, const struct sk_buff *skb) { + struct net_bridge_vlan_group *vg; + + vg = nbp_vlan_group(p); return ((p->flags & BR_HAIRPIN_MODE) || skb->dev != p->dev) && - br_allowed_egress(p->br, nbp_get_vlan_info(p), skb) && - p->state == BR_STATE_FORWARDING; + br_allowed_egress(vg, skb) && p->state == BR_STATE_FORWARDING; } -int br_dev_queue_push_xmit(struct sock *sk, struct sk_buff *skb) +int br_dev_queue_push_xmit(struct net *net, struct sock *sk, struct sk_buff *skb) { if (!is_skb_forwardable(skb->dev, skb)) goto drop; @@ -65,10 +67,10 @@ drop: } EXPORT_SYMBOL_GPL(br_dev_queue_push_xmit); -int br_forward_finish(struct sock *sk, struct sk_buff *skb) +int br_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { - return NF_HOOK(NFPROTO_BRIDGE, NF_BR_POST_ROUTING, sk, skb, - NULL, skb->dev, + return NF_HOOK(NFPROTO_BRIDGE, NF_BR_POST_ROUTING, + net, sk, skb, NULL, skb->dev, br_dev_queue_push_xmit); } @@ -76,7 +78,10 @@ EXPORT_SYMBOL_GPL(br_forward_finish); static void __br_deliver(const struct net_bridge_port *to, struct sk_buff *skb) { - skb = br_handle_vlan(to->br, nbp_get_vlan_info(to), skb); + struct net_bridge_vlan_group *vg; + + vg = nbp_vlan_group(to); + skb = br_handle_vlan(to->br, vg, skb); if (!skb) return; @@ -92,13 +97,14 @@ static void __br_deliver(const struct net_bridge_port *to, struct sk_buff *skb) return; } - NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, NULL, skb, - NULL, skb->dev, + NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, + dev_net(skb->dev), NULL, skb,NULL, skb->dev, br_forward_finish); } static void __br_forward(const struct net_bridge_port *to, struct sk_buff *skb) { + struct net_bridge_vlan_group *vg; struct net_device *indev; if (skb_warn_if_lro(skb)) { @@ -106,7 +112,8 @@ static void __br_forward(const struct net_bridge_port *to, struct sk_buff *skb) return; } - skb = br_handle_vlan(to->br, nbp_get_vlan_info(to), skb); + vg = nbp_vlan_group(to); + skb = br_handle_vlan(to->br, vg, skb); if (!skb) return; @@ -114,8 +121,8 @@ static void __br_forward(const struct net_bridge_port *to, struct sk_buff *skb) skb->dev = to->dev; skb_forward_csum(skb); - NF_HOOK(NFPROTO_BRIDGE, NF_BR_FORWARD, NULL, skb, - indev, skb->dev, + NF_HOOK(NFPROTO_BRIDGE, NF_BR_FORWARD, + dev_net(indev), NULL, skb, indev, skb->dev, br_forward_finish); } diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 45e4757c6fd2..934cae9fa317 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -248,7 +248,6 @@ static void del_nbp(struct net_bridge_port *p) list_del_rcu(&p->list); - nbp_vlan_flush(p); br_fdb_delete_by_port(br, p, 0, 1); nbp_update_port_count(br); @@ -257,6 +256,8 @@ static void del_nbp(struct net_bridge_port *p) dev->priv_flags &= ~IFF_BRIDGE_PORT; netdev_rx_handler_unregister(dev); + /* use the synchronize_rcu done by netdev_rx_handler_unregister */ + nbp_vlan_flush(p); br_multicast_del_port(p); diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index f921a5dce22d..f5c5a4500e2f 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -26,38 +26,44 @@ br_should_route_hook_t __rcu *br_should_route_hook __read_mostly; EXPORT_SYMBOL(br_should_route_hook); +static int +br_netif_receive_skb(struct net *net, struct sock *sk, struct sk_buff *skb) +{ + return netif_receive_skb(skb); +} + static int br_pass_frame_up(struct sk_buff *skb) { struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev; struct net_bridge *br = netdev_priv(brdev); + struct net_bridge_vlan_group *vg; struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats); - struct net_port_vlans *pv; u64_stats_update_begin(&brstats->syncp); brstats->rx_packets++; brstats->rx_bytes += skb->len; u64_stats_update_end(&brstats->syncp); + vg = br_vlan_group(br); /* Bridge is just like any other port. Make sure the * packet is allowed except in promisc modue when someone * may be running packet capture. */ - pv = br_get_vlan_info(br); if (!(brdev->flags & IFF_PROMISC) && - !br_allowed_egress(br, pv, skb)) { + !br_allowed_egress(vg, skb)) { kfree_skb(skb); return NET_RX_DROP; } indev = skb->dev; skb->dev = brdev; - skb = br_handle_vlan(br, pv, skb); + skb = br_handle_vlan(br, vg, skb); if (!skb) return NET_RX_DROP; - return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, NULL, skb, - indev, NULL, - netif_receive_skb_sk); + return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, + dev_net(indev), NULL, skb, indev, NULL, + br_netif_receive_skb); } static void br_do_proxy_arp(struct sk_buff *skb, struct net_bridge *br, @@ -120,7 +126,7 @@ static void br_do_proxy_arp(struct sk_buff *skb, struct net_bridge *br, } /* note: already called with rcu_read_lock */ -int br_handle_frame_finish(struct sock *sk, struct sk_buff *skb) +int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { const unsigned char *dest = eth_hdr(skb)->h_dest; struct net_bridge_port *p = br_port_get_rcu(skb->dev); @@ -134,7 +140,7 @@ int br_handle_frame_finish(struct sock *sk, struct sk_buff *skb) if (!p || p->state == BR_STATE_DISABLED) goto drop; - if (!br_allowed_ingress(p->br, nbp_get_vlan_info(p), skb, &vid)) + if (!br_allowed_ingress(p->br, nbp_vlan_group(p), skb, &vid)) goto out; /* insert into forwarding database after filtering to avoid spoofing */ @@ -208,7 +214,7 @@ drop: EXPORT_SYMBOL_GPL(br_handle_frame_finish); /* note: already called with rcu_read_lock */ -static int br_handle_local_finish(struct sock *sk, struct sk_buff *skb) +static int br_handle_local_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_bridge_port *p = br_port_get_rcu(skb->dev); u16 vid = 0; @@ -278,8 +284,9 @@ rx_handler_result_t br_handle_frame(struct sk_buff **pskb) } /* Deliver packet to local host only */ - if (NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, NULL, skb, - skb->dev, NULL, br_handle_local_finish)) { + if (NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, + dev_net(skb->dev), NULL, skb, skb->dev, NULL, + br_handle_local_finish)) { return RX_HANDLER_CONSUMED; /* consumed by filter */ } else { *pskb = skb; @@ -303,8 +310,8 @@ forward: if (ether_addr_equal(p->br->dev->dev_addr, dest)) skb->pkt_type = PACKET_HOST; - NF_HOOK(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, NULL, skb, - skb->dev, NULL, + NF_HOOK(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, + dev_net(skb->dev), NULL, skb, skb->dev, NULL, br_handle_frame_finish); break; default: diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index d747275fad18..cd8deea2d074 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -464,11 +464,11 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br, static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); - unsigned short vid = VLAN_N_VID; + struct net_bridge_vlan_group *vg; struct net_device *dev, *pdev; struct br_mdb_entry *entry; struct net_bridge_port *p; - struct net_port_vlans *pv; + struct net_bridge_vlan *v; struct net_bridge *br; int err; @@ -489,10 +489,10 @@ static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh) if (!p || p->br != br || p->state == BR_STATE_DISABLED) return -EINVAL; - pv = nbp_get_vlan_info(p); - if (br_vlan_enabled(br) && pv && entry->vid == 0) { - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { - entry->vid = vid; + vg = nbp_vlan_group(p); + if (br_vlan_enabled(br) && vg && entry->vid == 0) { + list_for_each_entry(v, &vg->vlan_list, vlist) { + entry->vid = v->vid; err = __br_mdb_add(net, br, entry); if (err) break; @@ -566,11 +566,11 @@ unlock: static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); - unsigned short vid = VLAN_N_VID; + struct net_bridge_vlan_group *vg; struct net_device *dev, *pdev; struct br_mdb_entry *entry; struct net_bridge_port *p; - struct net_port_vlans *pv; + struct net_bridge_vlan *v; struct net_bridge *br; int err; @@ -591,10 +591,10 @@ static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh) if (!p || p->br != br || p->state == BR_STATE_DISABLED) return -EINVAL; - pv = nbp_get_vlan_info(p); - if (br_vlan_enabled(br) && pv && entry->vid == 0) { - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { - entry->vid = vid; + vg = nbp_vlan_group(p); + if (br_vlan_enabled(br) && vg && entry->vid == 0) { + list_for_each_entry(v, &vg->vlan_list, vlist) { + entry->vid = v->vid; err = __br_mdb_del(br, entry); if (!err) __br_mdb_notify(dev, entry, RTM_DELMDB); diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 480b3de1a0e3..03661d97463c 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -829,8 +829,8 @@ static void __br_multicast_send_query(struct net_bridge *br, if (port) { skb->dev = port->dev; - NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, NULL, skb, - NULL, skb->dev, + NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, + dev_net(port->dev), NULL, skb, NULL, skb->dev, br_dev_queue_push_xmit); } else { br_multicast_select_own_querier(br, ip, skb); diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 0a6f095bb0c9..13f03671c88d 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -189,10 +189,9 @@ static inline void nf_bridge_pull_encap_header_rcsum(struct sk_buff *skb) * expected format */ -static int br_validate_ipv4(struct sk_buff *skb) +static int br_validate_ipv4(struct net *net, struct sk_buff *skb) { const struct iphdr *iph; - struct net_device *dev = skb->dev; u32 len; if (!pskb_may_pull(skb, sizeof(struct iphdr))) @@ -213,13 +212,13 @@ static int br_validate_ipv4(struct sk_buff *skb) len = ntohs(iph->tot_len); if (skb->len < len) { - IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INTRUNCATEDPKTS); + IP_INC_STATS_BH(net, IPSTATS_MIB_INTRUNCATEDPKTS); goto drop; } else if (len < (iph->ihl*4)) goto inhdr_error; if (pskb_trim_rcsum(skb, len)) { - IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INDISCARDS); + IP_INC_STATS_BH(net, IPSTATS_MIB_INDISCARDS); goto drop; } @@ -232,7 +231,7 @@ static int br_validate_ipv4(struct sk_buff *skb) return 0; inhdr_error: - IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INHDRERRORS); + IP_INC_STATS_BH(net, IPSTATS_MIB_INHDRERRORS); drop: return -1; } @@ -256,7 +255,7 @@ void nf_bridge_update_protocol(struct sk_buff *skb) * don't, we use the neighbour framework to find out. In both cases, we make * sure that br_handle_frame_finish() is called afterwards. */ -int br_nf_pre_routing_finish_bridge(struct sock *sk, struct sk_buff *skb) +int br_nf_pre_routing_finish_bridge(struct net *net, struct sock *sk, struct sk_buff *skb) { struct neighbour *neigh; struct dst_entry *dst; @@ -273,7 +272,7 @@ int br_nf_pre_routing_finish_bridge(struct sock *sk, struct sk_buff *skb) if (neigh->hh.hh_len) { neigh_hh_bridge(&neigh->hh, skb); skb->dev = nf_bridge->physindev; - ret = br_handle_frame_finish(sk, skb); + ret = br_handle_frame_finish(net, sk, skb); } else { /* the neighbour function below overwrites the complete * MAC header, so we save the Ethernet source address and @@ -342,7 +341,7 @@ br_nf_ipv4_daddr_was_changed(const struct sk_buff *skb, * device, we proceed as if ip_route_input() succeeded. If it differs from the * logical bridge port or if ip_route_output_key() fails we drop the packet. */ -static int br_nf_pre_routing_finish(struct sock *sk, struct sk_buff *skb) +static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb->dev; struct iphdr *iph = ip_hdr(skb); @@ -371,7 +370,7 @@ static int br_nf_pre_routing_finish(struct sock *sk, struct sk_buff *skb) if (err != -EHOSTUNREACH || !in_dev || IN_DEV_FORWARD(in_dev)) goto free_skb; - rt = ip_route_output(dev_net(dev), iph->daddr, 0, + rt = ip_route_output(net, iph->daddr, 0, RT_TOS(iph->tos), 0); if (!IS_ERR(rt)) { /* - Bridged-and-DNAT'ed traffic doesn't @@ -393,7 +392,7 @@ bridged_dnat: nf_bridge_push_encap_header(skb); NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, - sk, skb, skb->dev, NULL, + net, sk, skb, skb->dev, NULL, br_nf_pre_routing_finish_bridge, 1); return 0; @@ -413,7 +412,7 @@ bridged_dnat: skb->dev = nf_bridge->physindev; nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); - NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, sk, skb, + NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, net, sk, skb, skb->dev, NULL, br_handle_frame_finish, 1); @@ -464,7 +463,7 @@ struct net_device *setup_pre_routing(struct sk_buff *skb) * receiving device) to make netfilter happy, the REDIRECT * target in particular. Save the original destination IP * address to be able to detect DNAT afterwards. */ -static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops, +static unsigned int br_nf_pre_routing(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -486,7 +485,7 @@ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops, return NF_ACCEPT; nf_bridge_pull_encap_header_rcsum(skb); - return br_nf_pre_routing_ipv6(ops, skb, state); + return br_nf_pre_routing_ipv6(priv, skb, state); } if (!brnf_call_iptables && !br->nf_call_iptables) @@ -497,7 +496,7 @@ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops, nf_bridge_pull_encap_header_rcsum(skb); - if (br_validate_ipv4(skb)) + if (br_validate_ipv4(state->net, skb)) return NF_DROP; nf_bridge_put(skb->nf_bridge); @@ -511,7 +510,7 @@ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops, skb->protocol = htons(ETH_P_IP); - NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, state->sk, skb, + NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, state->net, state->sk, skb, skb->dev, NULL, br_nf_pre_routing_finish); @@ -526,7 +525,7 @@ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops, * took place when the packet entered the bridge), but we * register an IPv4 PRE_ROUTING 'sabotage' hook that will * prevent this from happening. */ -static unsigned int br_nf_local_in(const struct nf_hook_ops *ops, +static unsigned int br_nf_local_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -535,7 +534,7 @@ static unsigned int br_nf_local_in(const struct nf_hook_ops *ops, } /* PF_BRIDGE/FORWARD *************************************************/ -static int br_nf_forward_finish(struct sock *sk, struct sk_buff *skb) +static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); struct net_device *in; @@ -559,7 +558,7 @@ static int br_nf_forward_finish(struct sock *sk, struct sk_buff *skb) } nf_bridge_push_encap_header(skb); - NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_FORWARD, sk, skb, + NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_FORWARD, net, sk, skb, in, skb->dev, br_forward_finish, 1); return 0; } @@ -570,7 +569,7 @@ static int br_nf_forward_finish(struct sock *sk, struct sk_buff *skb) * but we are still able to filter on the 'real' indev/outdev * because of the physdev module. For ARP, indev and outdev are the * bridge ports. */ -static unsigned int br_nf_forward_ip(const struct nf_hook_ops *ops, +static unsigned int br_nf_forward_ip(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -609,13 +608,13 @@ static unsigned int br_nf_forward_ip(const struct nf_hook_ops *ops, } if (pf == NFPROTO_IPV4) { - if (br_validate_ipv4(skb)) + if (br_validate_ipv4(state->net, skb)) return NF_DROP; IPCB(skb)->frag_max_size = nf_bridge->frag_max_size; } if (pf == NFPROTO_IPV6) { - if (br_validate_ipv6(skb)) + if (br_validate_ipv6(state->net, skb)) return NF_DROP; IP6CB(skb)->frag_max_size = nf_bridge->frag_max_size; } @@ -626,14 +625,14 @@ static unsigned int br_nf_forward_ip(const struct nf_hook_ops *ops, else skb->protocol = htons(ETH_P_IPV6); - NF_HOOK(pf, NF_INET_FORWARD, NULL, skb, + NF_HOOK(pf, NF_INET_FORWARD, state->net, NULL, skb, brnf_get_logical_dev(skb, state->in), parent, br_nf_forward_finish); return NF_STOLEN; } -static unsigned int br_nf_forward_arp(const struct nf_hook_ops *ops, +static unsigned int br_nf_forward_arp(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -661,14 +660,14 @@ static unsigned int br_nf_forward_arp(const struct nf_hook_ops *ops, return NF_ACCEPT; } *d = state->in; - NF_HOOK(NFPROTO_ARP, NF_ARP_FORWARD, state->sk, skb, + NF_HOOK(NFPROTO_ARP, NF_ARP_FORWARD, state->net, state->sk, skb, state->in, state->out, br_nf_forward_finish); return NF_STOLEN; } #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) || IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) -static int br_nf_push_frag_xmit(struct sock *sk, struct sk_buff *skb) +static int br_nf_push_frag_xmit(struct net *net, struct sock *sk, struct sk_buff *skb) { struct brnf_frag_data *data; int err; @@ -690,23 +689,27 @@ static int br_nf_push_frag_xmit(struct sock *sk, struct sk_buff *skb) __skb_push(skb, data->encap_size); nf_bridge_info_free(skb); - return br_dev_queue_push_xmit(sk, skb); + return br_dev_queue_push_xmit(net, sk, skb); +} +static int br_nf_push_frag_xmit_sk(struct sock *sk, struct sk_buff *skb) +{ + struct net *net = dev_net(skb_dst(skb)->dev); + return br_nf_push_frag_xmit(net, sk, skb); } #endif #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) -static int br_nf_ip_fragment(struct sock *sk, struct sk_buff *skb, - int (*output)(struct sock *, struct sk_buff *)) +static int +br_nf_ip_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, + int (*output)(struct sock *, struct sk_buff *)) { unsigned int mtu = ip_skb_dst_mtu(skb); struct iphdr *iph = ip_hdr(skb); - struct rtable *rt = skb_rtable(skb); - struct net_device *dev = rt->dst.dev; if (unlikely(((iph->frag_off & htons(IP_DF)) && !skb->ignore_df) || (IPCB(skb)->frag_max_size && IPCB(skb)->frag_max_size > mtu))) { - IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS); + IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return -EMSGSIZE; } @@ -722,7 +725,7 @@ static unsigned int nf_bridge_mtu_reduction(const struct sk_buff *skb) return 0; } -static int br_nf_dev_queue_xmit(struct sock *sk, struct sk_buff *skb) +static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff *skb) { struct nf_bridge_info *nf_bridge; unsigned int mtu_reserved; @@ -731,7 +734,7 @@ static int br_nf_dev_queue_xmit(struct sock *sk, struct sk_buff *skb) if (skb_is_gso(skb) || skb->len + mtu_reserved <= skb->dev->mtu) { nf_bridge_info_free(skb); - return br_dev_queue_push_xmit(sk, skb); + return br_dev_queue_push_xmit(net, sk, skb); } nf_bridge = nf_bridge_info_get(skb); @@ -743,7 +746,7 @@ static int br_nf_dev_queue_xmit(struct sock *sk, struct sk_buff *skb) if (skb->protocol == htons(ETH_P_IP)) { struct brnf_frag_data *data; - if (br_validate_ipv4(skb)) + if (br_validate_ipv4(net, skb)) goto drop; IPCB(skb)->frag_max_size = nf_bridge->frag_max_size; @@ -760,7 +763,7 @@ static int br_nf_dev_queue_xmit(struct sock *sk, struct sk_buff *skb) skb_copy_from_linear_data_offset(skb, -data->size, data->mac, data->size); - return br_nf_ip_fragment(sk, skb, br_nf_push_frag_xmit); + return br_nf_ip_fragment(net, sk, skb, br_nf_push_frag_xmit_sk); } #endif #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) @@ -768,7 +771,7 @@ static int br_nf_dev_queue_xmit(struct sock *sk, struct sk_buff *skb) const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops(); struct brnf_frag_data *data; - if (br_validate_ipv6(skb)) + if (br_validate_ipv6(net, skb)) goto drop; IP6CB(skb)->frag_max_size = nf_bridge->frag_max_size; @@ -783,21 +786,21 @@ static int br_nf_dev_queue_xmit(struct sock *sk, struct sk_buff *skb) data->size); if (v6ops) - return v6ops->fragment(sk, skb, br_nf_push_frag_xmit); + return v6ops->fragment(sk, skb, br_nf_push_frag_xmit_sk); kfree_skb(skb); return -EMSGSIZE; } #endif nf_bridge_info_free(skb); - return br_dev_queue_push_xmit(sk, skb); + return br_dev_queue_push_xmit(net, sk, skb); drop: kfree_skb(skb); return 0; } /* PF_BRIDGE/POST_ROUTING ********************************************/ -static unsigned int br_nf_post_routing(const struct nf_hook_ops *ops, +static unsigned int br_nf_post_routing(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -836,7 +839,7 @@ static unsigned int br_nf_post_routing(const struct nf_hook_ops *ops, else skb->protocol = htons(ETH_P_IPV6); - NF_HOOK(pf, NF_INET_POST_ROUTING, state->sk, skb, + NF_HOOK(pf, NF_INET_POST_ROUTING, state->net, state->sk, skb, NULL, realoutdev, br_nf_dev_queue_xmit); @@ -846,7 +849,7 @@ static unsigned int br_nf_post_routing(const struct nf_hook_ops *ops, /* IP/SABOTAGE *****************************************************/ /* Don't hand locally destined packets to PF_INET(6)/PRE_ROUTING * for the second time. */ -static unsigned int ip_sabotage_in(const struct nf_hook_ops *ops, +static unsigned int ip_sabotage_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -880,7 +883,7 @@ static void br_nf_pre_routing_finish_bridge_slow(struct sk_buff *skb) skb->dev = nf_bridge->physindev; nf_bridge->physoutdev = NULL; - br_handle_frame_finish(NULL, skb); + br_handle_frame_finish(dev_net(skb->dev), NULL, skb); } static int br_nf_dev_xmit(struct sk_buff *skb) diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c index 77383bfe7ea3..d61f56efc8dc 100644 --- a/net/bridge/br_netfilter_ipv6.c +++ b/net/bridge/br_netfilter_ipv6.c @@ -100,10 +100,9 @@ bad: return -1; } -int br_validate_ipv6(struct sk_buff *skb) +int br_validate_ipv6(struct net *net, struct sk_buff *skb) { const struct ipv6hdr *hdr; - struct net_device *dev = skb->dev; struct inet6_dev *idev = __in6_dev_get(skb->dev); u32 pkt_len; u8 ip6h_len = sizeof(struct ipv6hdr); @@ -123,12 +122,12 @@ int br_validate_ipv6(struct sk_buff *skb) if (pkt_len || hdr->nexthdr != NEXTHDR_HOP) { if (pkt_len + ip6h_len > skb->len) { - IP6_INC_STATS_BH(dev_net(dev), idev, + IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INTRUNCATEDPKTS); goto drop; } if (pskb_trim_rcsum(skb, pkt_len + ip6h_len)) { - IP6_INC_STATS_BH(dev_net(dev), idev, + IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INDISCARDS); goto drop; } @@ -143,7 +142,7 @@ int br_validate_ipv6(struct sk_buff *skb) return 0; inhdr_error: - IP6_INC_STATS_BH(dev_net(dev), idev, IPSTATS_MIB_INHDRERRORS); + IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INHDRERRORS); drop: return -1; } @@ -161,7 +160,7 @@ br_nf_ipv6_daddr_was_changed(const struct sk_buff *skb, * for br_nf_pre_routing_finish(), same logic is used here but * equivalent IPv6 function ip6_route_input() called indirectly. */ -static int br_nf_pre_routing_finish_ipv6(struct sock *sk, struct sk_buff *skb) +static int br_nf_pre_routing_finish_ipv6(struct net *net, struct sock *sk, struct sk_buff *skb) { struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); struct rtable *rt; @@ -189,7 +188,7 @@ static int br_nf_pre_routing_finish_ipv6(struct sock *sk, struct sk_buff *skb) nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, - sk, skb, skb->dev, NULL, + net, sk, skb, skb->dev, NULL, br_nf_pre_routing_finish_bridge, 1); return 0; @@ -208,7 +207,7 @@ static int br_nf_pre_routing_finish_ipv6(struct sock *sk, struct sk_buff *skb) skb->dev = nf_bridge->physindev; nf_bridge_update_protocol(skb); nf_bridge_push_encap_header(skb); - NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, sk, skb, + NF_HOOK_THRESH(NFPROTO_BRIDGE, NF_BR_PRE_ROUTING, net, sk, skb, skb->dev, NULL, br_handle_frame_finish, 1); @@ -218,13 +217,13 @@ static int br_nf_pre_routing_finish_ipv6(struct sock *sk, struct sk_buff *skb) /* Replicate the checks that IPv6 does on packet reception and pass the packet * to ip6tables. */ -unsigned int br_nf_pre_routing_ipv6(const struct nf_hook_ops *ops, +unsigned int br_nf_pre_routing_ipv6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nf_bridge_info *nf_bridge; - if (br_validate_ipv6(skb)) + if (br_validate_ipv6(state->net, skb)) return NF_DROP; nf_bridge_put(skb->nf_bridge); @@ -237,7 +236,7 @@ unsigned int br_nf_pre_routing_ipv6(const struct nf_hook_ops *ops, nf_bridge->ipv6_daddr = ipv6_hdr(skb)->daddr; skb->protocol = htons(ETH_P_IPV6); - NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, state->sk, skb, + NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, state->net, state->sk, skb, skb->dev, NULL, br_nf_pre_routing_finish_ipv6); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index ea748c93a07f..c64dcad11662 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -21,36 +21,35 @@ #include "br_private.h" #include "br_private_stp.h" -static int br_get_num_vlan_infos(const struct net_port_vlans *pv, - u32 filter_mask) +static int __get_num_vlan_infos(struct net_bridge_vlan_group *vg, + u32 filter_mask) { - u16 vid_range_start = 0, vid_range_end = 0; - u16 vid_range_flags = 0; - u16 pvid, vid, flags; + struct net_bridge_vlan *v; + u16 vid_range_start = 0, vid_range_end = 0, vid_range_flags = 0; + u16 flags, pvid; int num_vlans = 0; - if (filter_mask & RTEXT_FILTER_BRVLAN) - return pv->num_vlans; - if (!(filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) return 0; - /* Count number of vlan info's - */ - pvid = br_get_pvid(pv); - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { + pvid = br_get_pvid(vg); + /* Count number of vlan infos */ + list_for_each_entry(v, &vg->vlan_list, vlist) { flags = 0; - if (vid == pvid) + /* only a context, bridge vlan not activated */ + if (!br_vlan_should_use(v)) + continue; + if (v->vid == pvid) flags |= BRIDGE_VLAN_INFO_PVID; - if (test_bit(vid, pv->untagged_bitmap)) + if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED) flags |= BRIDGE_VLAN_INFO_UNTAGGED; if (vid_range_start == 0) { goto initvars; - } else if ((vid - vid_range_end) == 1 && + } else if ((v->vid - vid_range_end) == 1 && flags == vid_range_flags) { - vid_range_end = vid; + vid_range_end = v->vid; continue; } else { if ((vid_range_end - vid_range_start) > 0) @@ -59,8 +58,8 @@ static int br_get_num_vlan_infos(const struct net_port_vlans *pv, num_vlans += 1; } initvars: - vid_range_start = vid; - vid_range_end = vid; + vid_range_start = v->vid; + vid_range_end = v->vid; vid_range_flags = flags; } @@ -74,28 +73,37 @@ initvars: return num_vlans; } +static int br_get_num_vlan_infos(struct net_bridge_vlan_group *vg, + u32 filter_mask) +{ + if (!vg) + return 0; + + if (filter_mask & RTEXT_FILTER_BRVLAN) + return vg->num_vlans; + + return __get_num_vlan_infos(vg, filter_mask); +} + static size_t br_get_link_af_size_filtered(const struct net_device *dev, u32 filter_mask) { - struct net_port_vlans *pv; + struct net_bridge_vlan_group *vg = NULL; + struct net_bridge_port *p; + struct net_bridge *br; int num_vlan_infos; rcu_read_lock(); - if (br_port_exists(dev)) - pv = nbp_get_vlan_info(br_port_get_rcu(dev)); - else if (dev->priv_flags & IFF_EBRIDGE) - pv = br_get_vlan_info((struct net_bridge *)netdev_priv(dev)); - else - pv = NULL; - if (pv) - num_vlan_infos = br_get_num_vlan_infos(pv, filter_mask); - else - num_vlan_infos = 0; + if (br_port_exists(dev)) { + p = br_port_get_rcu(dev); + vg = nbp_vlan_group(p); + } else if (dev->priv_flags & IFF_EBRIDGE) { + br = netdev_priv(dev); + vg = br_vlan_group(br); + } + num_vlan_infos = br_get_num_vlan_infos(vg, filter_mask); rcu_read_unlock(); - if (!num_vlan_infos) - return 0; - /* Each VLAN is returned in bridge_vlan_info along with flags */ return num_vlan_infos * nla_total_size(sizeof(struct bridge_vlan_info)); } @@ -185,31 +193,33 @@ nla_put_failure: } static int br_fill_ifvlaninfo_compressed(struct sk_buff *skb, - const struct net_port_vlans *pv) + struct net_bridge_vlan_group *vg) { - u16 vid_range_start = 0, vid_range_end = 0; - u16 vid_range_flags = 0; - u16 pvid, vid, flags; + struct net_bridge_vlan *v; + u16 vid_range_start = 0, vid_range_end = 0, vid_range_flags = 0; + u16 flags, pvid; int err = 0; /* Pack IFLA_BRIDGE_VLAN_INFO's for every vlan * and mark vlan info with begin and end flags * if vlaninfo represents a range */ - pvid = br_get_pvid(pv); - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { + pvid = br_get_pvid(vg); + list_for_each_entry(v, &vg->vlan_list, vlist) { flags = 0; - if (vid == pvid) + if (!br_vlan_should_use(v)) + continue; + if (v->vid == pvid) flags |= BRIDGE_VLAN_INFO_PVID; - if (test_bit(vid, pv->untagged_bitmap)) + if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED) flags |= BRIDGE_VLAN_INFO_UNTAGGED; if (vid_range_start == 0) { goto initvars; - } else if ((vid - vid_range_end) == 1 && + } else if ((v->vid - vid_range_end) == 1 && flags == vid_range_flags) { - vid_range_end = vid; + vid_range_end = v->vid; continue; } else { err = br_fill_ifvlaninfo_range(skb, vid_range_start, @@ -220,8 +230,8 @@ static int br_fill_ifvlaninfo_compressed(struct sk_buff *skb, } initvars: - vid_range_start = vid; - vid_range_end = vid; + vid_range_start = v->vid; + vid_range_end = v->vid; vid_range_flags = flags; } @@ -238,19 +248,23 @@ initvars: } static int br_fill_ifvlaninfo(struct sk_buff *skb, - const struct net_port_vlans *pv) + struct net_bridge_vlan_group *vg) { struct bridge_vlan_info vinfo; - u16 pvid, vid; + struct net_bridge_vlan *v; + u16 pvid; - pvid = br_get_pvid(pv); - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { - vinfo.vid = vid; + pvid = br_get_pvid(vg); + list_for_each_entry(v, &vg->vlan_list, vlist) { + if (!br_vlan_should_use(v)) + continue; + + vinfo.vid = v->vid; vinfo.flags = 0; - if (vid == pvid) + if (v->vid == pvid) vinfo.flags |= BRIDGE_VLAN_INFO_PVID; - if (test_bit(vid, pv->untagged_bitmap)) + if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED) vinfo.flags |= BRIDGE_VLAN_INFO_UNTAGGED; if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, @@ -269,11 +283,11 @@ nla_put_failure: * Contains port and master info as well as carrier and bridge state. */ static int br_fill_ifinfo(struct sk_buff *skb, - const struct net_bridge_port *port, + struct net_bridge_port *port, u32 pid, u32 seq, int event, unsigned int flags, u32 filter_mask, const struct net_device *dev) { - const struct net_bridge *br; + struct net_bridge *br; struct ifinfomsg *hdr; struct nlmsghdr *nlh; u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN; @@ -320,16 +334,16 @@ static int br_fill_ifinfo(struct sk_buff *skb, /* Check if the VID information is requested */ if ((filter_mask & RTEXT_FILTER_BRVLAN) || (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) { - const struct net_port_vlans *pv; + struct net_bridge_vlan_group *vg; struct nlattr *af; int err; if (port) - pv = nbp_get_vlan_info(port); + vg = nbp_vlan_group(port); else - pv = br_get_vlan_info(br); + vg = br_vlan_group(br); - if (!pv || bitmap_empty(pv->vlan_bitmap, VLAN_N_VID)) + if (!vg || !vg->num_vlans) goto done; af = nla_nest_start(skb, IFLA_AF_SPEC); @@ -337,9 +351,9 @@ static int br_fill_ifinfo(struct sk_buff *skb, goto nla_put_failure; if (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED) - err = br_fill_ifvlaninfo_compressed(skb, pv); + err = br_fill_ifvlaninfo_compressed(skb, vg); else - err = br_fill_ifvlaninfo(skb, pv); + err = br_fill_ifvlaninfo(skb, vg); if (err) goto nla_put_failure; nla_nest_end(skb, af); @@ -413,14 +427,14 @@ static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p, switch (cmd) { case RTM_SETLINK: if (p) { + /* if the MASTER flag is set this will act on the global + * per-VLAN entry as well + */ err = nbp_vlan_add(p, vinfo->vid, vinfo->flags); if (err) break; - - if (vinfo->flags & BRIDGE_VLAN_INFO_MASTER) - err = br_vlan_add(p->br, vinfo->vid, - vinfo->flags); } else { + vinfo->flags |= BRIDGE_VLAN_INFO_BRENTRY; err = br_vlan_add(br, vinfo->vid, vinfo->flags); } break; @@ -857,20 +871,22 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) static size_t br_get_link_af_size(const struct net_device *dev) { - struct net_port_vlans *pv; - - if (br_port_exists(dev)) - pv = nbp_get_vlan_info(br_port_get_rtnl(dev)); - else if (dev->priv_flags & IFF_EBRIDGE) - pv = br_get_vlan_info((struct net_bridge *)netdev_priv(dev)); - else - return 0; + struct net_bridge_port *p; + struct net_bridge *br; + int num_vlans = 0; - if (!pv) - return 0; + if (br_port_exists(dev)) { + p = br_port_get_rtnl(dev); + num_vlans = br_get_num_vlan_infos(nbp_vlan_group(p), + RTEXT_FILTER_BRVLAN); + } else if (dev->priv_flags & IFF_EBRIDGE) { + br = netdev_priv(dev); + num_vlans = br_get_num_vlan_infos(br_vlan_group(br), + RTEXT_FILTER_BRVLAN); + } /* Each VLAN is returned in bridge_vlan_info along with flags */ - return pv->num_vlans * nla_total_size(sizeof(struct bridge_vlan_info)); + return num_vlans * nla_total_size(sizeof(struct bridge_vlan_info)); } static struct rtnl_af_ops br_af_ops __read_mostly = { diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 213baf7aaa93..4ed8308db66e 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -20,6 +20,7 @@ #include <net/route.h> #include <net/ip6_fib.h> #include <linux/if_vlan.h> +#include <linux/rhashtable.h> #define BR_HASH_BITS 8 #define BR_HASH_SIZE (1 << BR_HASH_BITS) @@ -28,7 +29,6 @@ #define BR_PORT_BITS 10 #define BR_MAX_PORTS (1<<BR_PORT_BITS) -#define BR_VLAN_BITMAP_LEN BITS_TO_LONGS(VLAN_N_VID) #define BR_VERSION "2.3" @@ -77,17 +77,61 @@ struct bridge_mcast_querier { }; #endif -struct net_port_vlans { - u16 port_idx; - u16 pvid; +/** + * struct net_bridge_vlan - per-vlan entry + * + * @vnode: rhashtable member + * @vid: VLAN id + * @flags: bridge vlan flags + * @br: if MASTER flag set, this points to a bridge struct + * @port: if MASTER flag unset, this points to a port struct + * @refcnt: if MASTER flag set, this is bumped for each port referencing it + * @brvlan: if MASTER flag unset, this points to the global per-VLAN context + * for this VLAN entry + * @vlist: sorted list of VLAN entries + * @rcu: used for entry destruction + * + * This structure is shared between the global per-VLAN entries contained in + * the bridge rhashtable and the local per-port per-VLAN entries contained in + * the port's rhashtable. The union entries should be interpreted depending on + * the entry flags that are set. + */ +struct net_bridge_vlan { + struct rhash_head vnode; + u16 vid; + u16 flags; union { - struct net_bridge_port *port; - struct net_bridge *br; - } parent; + struct net_bridge *br; + struct net_bridge_port *port; + }; + union { + atomic_t refcnt; + struct net_bridge_vlan *brvlan; + }; + struct list_head vlist; + struct rcu_head rcu; - unsigned long vlan_bitmap[BR_VLAN_BITMAP_LEN]; - unsigned long untagged_bitmap[BR_VLAN_BITMAP_LEN]; +}; + +/** + * struct net_bridge_vlan_group + * + * @vlan_hash: VLAN entry rhashtable + * @vlan_list: sorted VLAN entry list + * @num_vlans: number of total VLAN entries + * @pvid: PVID VLAN id + * + * IMPORTANT: Be careful when checking if there're VLAN entries using list + * primitives because the bridge can have entries in its list which + * are just for global context but not for filtering, i.e. they have + * the master flag set but not the brentry flag. If you have to check + * if there're "real" entries in the bridge please test @num_vlans + */ +struct net_bridge_vlan_group { + struct rhashtable vlan_hash; + struct list_head vlan_list; u16 num_vlans; + u16 pvid; }; struct net_bridge_fdb_entry @@ -185,7 +229,7 @@ struct net_bridge_port struct netpoll *np; #endif #ifdef CONFIG_BRIDGE_VLAN_FILTERING - struct net_port_vlans __rcu *vlan_info; + struct net_bridge_vlan_group *vlgrp; #endif }; @@ -293,10 +337,10 @@ struct net_bridge struct kobject *ifobj; u32 auto_cnt; #ifdef CONFIG_BRIDGE_VLAN_FILTERING + struct net_bridge_vlan_group *vlgrp; u8 vlan_enabled; __be16 vlan_proto; u16 default_pvid; - struct net_port_vlans __rcu *vlan_info; #endif }; @@ -344,6 +388,31 @@ static inline int br_is_root_bridge(const struct net_bridge *br) return !memcmp(&br->bridge_id, &br->designated_root, 8); } +/* check if a VLAN entry is global */ +static inline bool br_vlan_is_master(const struct net_bridge_vlan *v) +{ + return v->flags & BRIDGE_VLAN_INFO_MASTER; +} + +/* check if a VLAN entry is used by the bridge */ +static inline bool br_vlan_is_brentry(const struct net_bridge_vlan *v) +{ + return v->flags & BRIDGE_VLAN_INFO_BRENTRY; +} + +/* check if we should use the vlan entry is usable */ +static inline bool br_vlan_should_use(const struct net_bridge_vlan *v) +{ + if (br_vlan_is_master(v)) { + if (br_vlan_is_brentry(v)) + return true; + else + return false; + } + + return true; +} + /* br_device.c */ void br_dev_setup(struct net_device *dev); void br_dev_delete(struct net_device *dev, struct list_head *list); @@ -413,10 +482,10 @@ int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p, /* br_forward.c */ void br_deliver(const struct net_bridge_port *to, struct sk_buff *skb); -int br_dev_queue_push_xmit(struct sock *sk, struct sk_buff *skb); +int br_dev_queue_push_xmit(struct net *net, struct sock *sk, struct sk_buff *skb); void br_forward(const struct net_bridge_port *to, struct sk_buff *skb, struct sk_buff *skb0); -int br_forward_finish(struct sock *sk, struct sk_buff *skb); +int br_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb); void br_flood_deliver(struct net_bridge *br, struct sk_buff *skb, bool unicast); void br_flood_forward(struct net_bridge *br, struct sk_buff *skb, struct sk_buff *skb2, bool unicast); @@ -434,7 +503,7 @@ void br_port_flags_change(struct net_bridge_port *port, unsigned long mask); void br_manage_promisc(struct net_bridge *br); /* br_input.c */ -int br_handle_frame_finish(struct sock *sk, struct sk_buff *skb); +int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb); rx_handler_result_t br_handle_frame(struct sk_buff **pskb); static inline bool br_rx_handler_check_rcu(const struct net_device *dev) @@ -601,18 +670,19 @@ static inline void br_mdb_uninit(void) /* br_vlan.c */ #ifdef CONFIG_BRIDGE_VLAN_FILTERING -bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, - struct sk_buff *skb, u16 *vid); -bool br_allowed_egress(struct net_bridge *br, const struct net_port_vlans *v, +bool br_allowed_ingress(const struct net_bridge *br, + struct net_bridge_vlan_group *vg, struct sk_buff *skb, + u16 *vid); +bool br_allowed_egress(struct net_bridge_vlan_group *vg, const struct sk_buff *skb); bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid); struct sk_buff *br_handle_vlan(struct net_bridge *br, - const struct net_port_vlans *v, + struct net_bridge_vlan_group *vg, struct sk_buff *skb); int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags); int br_vlan_delete(struct net_bridge *br, u16 vid); void br_vlan_flush(struct net_bridge *br); -bool br_vlan_find(struct net_bridge *br, u16 vid); +struct net_bridge_vlan *br_vlan_find(struct net_bridge_vlan_group *vg, u16 vid); void br_recalculate_fwd_mask(struct net_bridge *br); int __br_vlan_filter_toggle(struct net_bridge *br, unsigned long val); int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val); @@ -623,19 +693,19 @@ int br_vlan_set_default_pvid(struct net_bridge *br, unsigned long val); int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags); int nbp_vlan_delete(struct net_bridge_port *port, u16 vid); void nbp_vlan_flush(struct net_bridge_port *port); -bool nbp_vlan_find(struct net_bridge_port *port, u16 vid); int nbp_vlan_init(struct net_bridge_port *port); +int nbp_get_num_vlan_infos(struct net_bridge_port *p, u32 filter_mask); -static inline struct net_port_vlans *br_get_vlan_info( - const struct net_bridge *br) +static inline struct net_bridge_vlan_group *br_vlan_group( + const struct net_bridge *br) { - return rcu_dereference_rtnl(br->vlan_info); + return br->vlgrp; } -static inline struct net_port_vlans *nbp_get_vlan_info( - const struct net_bridge_port *p) +static inline struct net_bridge_vlan_group *nbp_vlan_group( + const struct net_bridge_port *p) { - return rcu_dereference_rtnl(p->vlan_info); + return p->vlgrp; } /* Since bridge now depends on 8021Q module, but the time bridge sees the @@ -645,9 +715,9 @@ static inline int br_vlan_get_tag(const struct sk_buff *skb, u16 *vid) { int err = 0; - if (skb_vlan_tag_present(skb)) + if (skb_vlan_tag_present(skb)) { *vid = skb_vlan_tag_get(skb) & VLAN_VID_MASK; - else { + } else { *vid = 0; err = -EINVAL; } @@ -655,13 +725,13 @@ static inline int br_vlan_get_tag(const struct sk_buff *skb, u16 *vid) return err; } -static inline u16 br_get_pvid(const struct net_port_vlans *v) +static inline u16 br_get_pvid(const struct net_bridge_vlan_group *vg) { - if (!v) + if (!vg) return 0; smp_rmb(); - return v->pvid; + return vg->pvid; } static inline int br_vlan_enabled(struct net_bridge *br) @@ -669,16 +739,15 @@ static inline int br_vlan_enabled(struct net_bridge *br) return br->vlan_enabled; } #else -static inline bool br_allowed_ingress(struct net_bridge *br, - struct net_port_vlans *v, +static inline bool br_allowed_ingress(const struct net_bridge *br, + struct net_bridge_vlan_group *vg, struct sk_buff *skb, u16 *vid) { return true; } -static inline bool br_allowed_egress(struct net_bridge *br, - const struct net_port_vlans *v, +static inline bool br_allowed_egress(struct net_bridge_vlan_group *vg, const struct sk_buff *skb) { return true; @@ -691,7 +760,7 @@ static inline bool br_should_learn(struct net_bridge_port *p, } static inline struct sk_buff *br_handle_vlan(struct net_bridge *br, - const struct net_port_vlans *v, + struct net_bridge_vlan_group *vg, struct sk_buff *skb) { return skb; @@ -711,11 +780,6 @@ static inline void br_vlan_flush(struct net_bridge *br) { } -static inline bool br_vlan_find(struct net_bridge *br, u16 vid) -{ - return false; -} - static inline void br_recalculate_fwd_mask(struct net_bridge *br) { } @@ -739,21 +803,11 @@ static inline void nbp_vlan_flush(struct net_bridge_port *port) { } -static inline struct net_port_vlans *br_get_vlan_info( - const struct net_bridge *br) +static inline struct net_bridge_vlan *br_vlan_find(struct net_bridge_vlan_group *vg, + u16 vid) { return NULL; } -static inline struct net_port_vlans *nbp_get_vlan_info( - const struct net_bridge_port *p) -{ - return NULL; -} - -static inline bool nbp_vlan_find(struct net_bridge_port *port, u16 vid) -{ - return false; -} static inline int nbp_vlan_init(struct net_bridge_port *port) { @@ -764,7 +818,8 @@ static inline u16 br_vlan_get_tag(const struct sk_buff *skb, u16 *tag) { return 0; } -static inline u16 br_get_pvid(const struct net_port_vlans *v) + +static inline u16 br_get_pvid(const struct net_bridge_vlan_group *vg) { return 0; } @@ -779,6 +834,24 @@ static inline int __br_vlan_filter_toggle(struct net_bridge *br, { return -EOPNOTSUPP; } + +static inline int nbp_get_num_vlan_infos(struct net_bridge_port *p, + u32 filter_mask) +{ + return 0; +} + +static inline struct net_bridge_vlan_group *br_vlan_group( + const struct net_bridge *br) +{ + return NULL; +} + +static inline struct net_bridge_vlan_group *nbp_vlan_group( + const struct net_bridge_port *p) +{ + return NULL; +} #endif struct nf_br_ops { diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index ed74ffaa851f..3a7392e6010e 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -576,17 +576,12 @@ void __br_set_forward_delay(struct net_bridge *br, unsigned long t) int br_set_forward_delay(struct net_bridge *br, unsigned long val) { unsigned long t = clock_t_to_jiffies(val); - int err = -ERANGE; - spin_lock_bh(&br->lock); - if (br->stp_enabled != BR_NO_STP && - (t < BR_MIN_FORWARD_DELAY || t > BR_MAX_FORWARD_DELAY)) - goto unlock; + if (t < BR_MIN_FORWARD_DELAY || t > BR_MAX_FORWARD_DELAY) + return -ERANGE; + spin_lock_bh(&br->lock); __br_set_forward_delay(br, t); - err = 0; - -unlock: spin_unlock_bh(&br->lock); - return err; + return 0; } diff --git a/net/bridge/br_stp_bpdu.c b/net/bridge/br_stp_bpdu.c index 534fc4cd263e..5881fbc114a9 100644 --- a/net/bridge/br_stp_bpdu.c +++ b/net/bridge/br_stp_bpdu.c @@ -30,6 +30,12 @@ #define LLC_RESERVE sizeof(struct llc_pdu_un) +static int br_send_bpdu_finish(struct net *net, struct sock *sk, + struct sk_buff *skb) +{ + return dev_queue_xmit(skb); +} + static void br_send_bpdu(struct net_bridge_port *p, const unsigned char *data, int length) { @@ -54,9 +60,9 @@ static void br_send_bpdu(struct net_bridge_port *p, skb_reset_mac_header(skb); - NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, NULL, skb, - NULL, skb->dev, - dev_queue_xmit_sk); + NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, + dev_net(p->dev), NULL, skb, NULL, skb->dev, + br_send_bpdu_finish); } static inline void br_set_ticks(unsigned char *dest, int j) diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 5f5a02b49a99..75214a51cf0e 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -6,35 +6,67 @@ #include "br_private.h" -static void __vlan_add_pvid(struct net_port_vlans *v, u16 vid) +static inline int br_vlan_cmp(struct rhashtable_compare_arg *arg, + const void *ptr) { - if (v->pvid == vid) + const struct net_bridge_vlan *vle = ptr; + u16 vid = *(u16 *)arg->key; + + return vle->vid != vid; +} + +static const struct rhashtable_params br_vlan_rht_params = { + .head_offset = offsetof(struct net_bridge_vlan, vnode), + .key_offset = offsetof(struct net_bridge_vlan, vid), + .key_len = sizeof(u16), + .nelem_hint = 3, + .locks_mul = 1, + .max_size = VLAN_N_VID, + .obj_cmpfn = br_vlan_cmp, + .automatic_shrinking = true, +}; + +static struct net_bridge_vlan *br_vlan_lookup(struct rhashtable *tbl, u16 vid) +{ + return rhashtable_lookup_fast(tbl, &vid, br_vlan_rht_params); +} + +static void __vlan_add_pvid(struct net_bridge_vlan_group *vg, u16 vid) +{ + if (vg->pvid == vid) return; smp_wmb(); - v->pvid = vid; + vg->pvid = vid; } -static void __vlan_delete_pvid(struct net_port_vlans *v, u16 vid) +static void __vlan_delete_pvid(struct net_bridge_vlan_group *vg, u16 vid) { - if (v->pvid != vid) + if (vg->pvid != vid) return; smp_wmb(); - v->pvid = 0; + vg->pvid = 0; } -static void __vlan_add_flags(struct net_port_vlans *v, u16 vid, u16 flags) +static void __vlan_add_flags(struct net_bridge_vlan *v, u16 flags) { + struct net_bridge_vlan_group *vg; + + if (br_vlan_is_master(v)) + vg = v->br->vlgrp; + else + vg = v->port->vlgrp; + if (flags & BRIDGE_VLAN_INFO_PVID) - __vlan_add_pvid(v, vid); + __vlan_add_pvid(vg, v->vid); else - __vlan_delete_pvid(v, vid); + __vlan_delete_pvid(vg, v->vid); if (flags & BRIDGE_VLAN_INFO_UNTAGGED) - set_bit(vid, v->untagged_bitmap); + v->flags |= BRIDGE_VLAN_INFO_UNTAGGED; else - clear_bit(vid, v->untagged_bitmap); + v->flags &= ~BRIDGE_VLAN_INFO_UNTAGGED; } static int __vlan_vid_add(struct net_device *dev, struct net_bridge *br, @@ -50,16 +82,13 @@ static int __vlan_vid_add(struct net_device *dev, struct net_bridge *br, if (ops->ndo_vlan_rx_add_vid) { err = vlan_vid_add(dev, br->vlan_proto, vid); } else { - struct switchdev_obj vlan_obj = { - .id = SWITCHDEV_OBJ_PORT_VLAN, - .u.vlan = { - .flags = flags, - .vid_begin = vid, - .vid_end = vid, - }, + struct switchdev_obj_vlan v = { + .flags = flags, + .vid_begin = vid, + .vid_end = vid, }; - err = switchdev_port_obj_add(dev, &vlan_obj); + err = switchdev_port_obj_add(dev, SWITCHDEV_OBJ_PORT_VLAN, &v); if (err == -EOPNOTSUPP) err = 0; } @@ -67,54 +96,26 @@ static int __vlan_vid_add(struct net_device *dev, struct net_bridge *br, return err; } -static int __vlan_add(struct net_port_vlans *v, u16 vid, u16 flags) +static void __vlan_add_list(struct net_bridge_vlan *v) { - struct net_bridge_port *p = NULL; - struct net_bridge *br; - struct net_device *dev; - int err; - - if (test_bit(vid, v->vlan_bitmap)) { - __vlan_add_flags(v, vid, flags); - return 0; - } - - if (v->port_idx) { - p = v->parent.port; - br = p->br; - dev = p->dev; - } else { - br = v->parent.br; - dev = br->dev; - } - - if (p) { - /* Add VLAN to the device filter if it is supported. - * This ensures tagged traffic enters the bridge when - * promiscuous mode is disabled by br_manage_promisc(). - */ - err = __vlan_vid_add(dev, br, vid, flags); - if (err) - return err; - } + struct list_head *headp, *hpos; + struct net_bridge_vlan *vent; - err = br_fdb_insert(br, p, dev->dev_addr, vid); - if (err) { - br_err(br, "failed insert local address into bridge " - "forwarding table\n"); - goto out_filt; + headp = br_vlan_is_master(v) ? &v->br->vlgrp->vlan_list : + &v->port->vlgrp->vlan_list; + list_for_each_prev(hpos, headp) { + vent = list_entry(hpos, struct net_bridge_vlan, vlist); + if (v->vid < vent->vid) + continue; + else + break; } + list_add(&v->vlist, hpos); +} - set_bit(vid, v->vlan_bitmap); - v->num_vlans++; - __vlan_add_flags(v, vid, flags); - - return 0; - -out_filt: - if (p) - vlan_vid_del(dev, br->vlan_proto, vid); - return err; +static void __vlan_del_list(struct net_bridge_vlan *v) +{ + list_del(&v->vlist); } static int __vlan_vid_del(struct net_device *dev, struct net_bridge *br, @@ -130,15 +131,12 @@ static int __vlan_vid_del(struct net_device *dev, struct net_bridge *br, if (ops->ndo_vlan_rx_kill_vid) { vlan_vid_del(dev, br->vlan_proto, vid); } else { - struct switchdev_obj vlan_obj = { - .id = SWITCHDEV_OBJ_PORT_VLAN, - .u.vlan = { - .vid_begin = vid, - .vid_end = vid, - }, + struct switchdev_obj_vlan v = { + .vid_begin = vid, + .vid_end = vid, }; - err = switchdev_port_obj_del(dev, &vlan_obj); + err = switchdev_port_obj_del(dev, SWITCHDEV_OBJ_PORT_VLAN, &v); if (err == -EOPNOTSUPP) err = 0; } @@ -146,63 +144,193 @@ static int __vlan_vid_del(struct net_device *dev, struct net_bridge *br, return err; } -static int __vlan_del(struct net_port_vlans *v, u16 vid) +/* This is the shared VLAN add function which works for both ports and bridge + * devices. There are four possible calls to this function in terms of the + * vlan entry type: + * 1. vlan is being added on a port (no master flags, global entry exists) + * 2. vlan is being added on a bridge (both master and brvlan flags) + * 3. vlan is being added on a port, but a global entry didn't exist which + * is being created right now (master flag set, brvlan flag unset), the + * global entry is used for global per-vlan features, but not for filtering + * 4. same as 3 but with both master and brvlan flags set so the entry + * will be used for filtering in both the port and the bridge + */ +static int __vlan_add(struct net_bridge_vlan *v, u16 flags) { - if (!test_bit(vid, v->vlan_bitmap)) - return -EINVAL; + struct net_bridge_vlan *masterv = NULL; + struct net_bridge_port *p = NULL; + struct rhashtable *tbl; + struct net_device *dev; + struct net_bridge *br; + int err; + + if (br_vlan_is_master(v)) { + br = v->br; + dev = br->dev; + tbl = &br->vlgrp->vlan_hash; + } else { + p = v->port; + br = p->br; + dev = p->dev; + tbl = &p->vlgrp->vlan_hash; + } + + if (p) { + u16 master_flags = flags; + + /* Add VLAN to the device filter if it is supported. + * This ensures tagged traffic enters the bridge when + * promiscuous mode is disabled by br_manage_promisc(). + */ + err = __vlan_vid_add(dev, br, v->vid, flags); + if (err) + goto out; + + /* need to work on the master vlan too */ + if (flags & BRIDGE_VLAN_INFO_MASTER) { + master_flags |= BRIDGE_VLAN_INFO_BRENTRY; + err = br_vlan_add(br, v->vid, master_flags); + if (err) + goto out_filt; + } + + masterv = br_vlan_find(br->vlgrp, v->vid); + if (!masterv) { + /* missing global ctx, create it now */ + err = br_vlan_add(br, v->vid, 0); + if (err) + goto out_filt; + masterv = br_vlan_find(br->vlgrp, v->vid); + WARN_ON(!masterv); + } + atomic_inc(&masterv->refcnt); + v->brvlan = masterv; + } + + /* Add the dev mac only if it's a usable vlan */ + if (br_vlan_should_use(v)) { + err = br_fdb_insert(br, p, dev->dev_addr, v->vid); + if (err) { + br_err(br, "failed insert local address into bridge forwarding table\n"); + goto out_filt; + } + } + + err = rhashtable_lookup_insert_fast(tbl, &v->vnode, br_vlan_rht_params); + if (err) + goto out_fdb_insert; + + __vlan_add_list(v); + __vlan_add_flags(v, flags); + if (br_vlan_is_master(v)) { + if (br_vlan_is_brentry(v)) + br->vlgrp->num_vlans++; + } else { + p->vlgrp->num_vlans++; + } +out: + return err; + +out_fdb_insert: + br_fdb_find_delete_local(br, p, br->dev->dev_addr, v->vid); + +out_filt: + if (p) { + __vlan_vid_del(dev, br, v->vid); + if (masterv) { + atomic_dec(&masterv->refcnt); + v->brvlan = NULL; + } + } + + goto out; +} - __vlan_delete_pvid(v, vid); - clear_bit(vid, v->untagged_bitmap); +static int __vlan_del(struct net_bridge_vlan *v) +{ + struct net_bridge_vlan *masterv = v; + struct net_bridge_vlan_group *vg; + struct net_bridge_port *p = NULL; + struct net_bridge *br; + int err = 0; - if (v->port_idx) { - struct net_bridge_port *p = v->parent.port; - int err; + if (br_vlan_is_master(v)) { + br = v->br; + vg = v->br->vlgrp; + } else { + p = v->port; + br = p->br; + vg = v->port->vlgrp; + masterv = v->brvlan; + } - err = __vlan_vid_del(p->dev, p->br, vid); + __vlan_delete_pvid(vg, v->vid); + if (p) { + err = __vlan_vid_del(p->dev, p->br, v->vid); if (err) - return err; + goto out; } - clear_bit(vid, v->vlan_bitmap); - v->num_vlans--; - if (bitmap_empty(v->vlan_bitmap, VLAN_N_VID)) { - if (v->port_idx) - RCU_INIT_POINTER(v->parent.port->vlan_info, NULL); - else - RCU_INIT_POINTER(v->parent.br->vlan_info, NULL); + if (br_vlan_is_master(v)) { + if (br_vlan_is_brentry(v)) { + v->flags &= ~BRIDGE_VLAN_INFO_BRENTRY; + br->vlgrp->num_vlans--; + } + } else { + p->vlgrp->num_vlans--; + } + + if (masterv != v) { + rhashtable_remove_fast(&vg->vlan_hash, &v->vnode, + br_vlan_rht_params); + __vlan_del_list(v); kfree_rcu(v, rcu); } - return 0; + + if (atomic_dec_and_test(&masterv->refcnt)) { + rhashtable_remove_fast(&masterv->br->vlgrp->vlan_hash, + &masterv->vnode, br_vlan_rht_params); + __vlan_del_list(masterv); + kfree_rcu(masterv, rcu); + } +out: + return err; } -static void __vlan_flush(struct net_port_vlans *v) +static void __vlan_flush(struct net_bridge_vlan_group *vlgrp) { - smp_wmb(); - v->pvid = 0; - bitmap_zero(v->vlan_bitmap, VLAN_N_VID); - if (v->port_idx) - RCU_INIT_POINTER(v->parent.port->vlan_info, NULL); - else - RCU_INIT_POINTER(v->parent.br->vlan_info, NULL); - kfree_rcu(v, rcu); + struct net_bridge_vlan *vlan, *tmp; + + __vlan_delete_pvid(vlgrp, vlgrp->pvid); + list_for_each_entry_safe(vlan, tmp, &vlgrp->vlan_list, vlist) + __vlan_del(vlan); + rhashtable_destroy(&vlgrp->vlan_hash); + kfree(vlgrp); } struct sk_buff *br_handle_vlan(struct net_bridge *br, - const struct net_port_vlans *pv, + struct net_bridge_vlan_group *vg, struct sk_buff *skb) { + struct net_bridge_vlan *v; u16 vid; /* If this packet was not filtered at input, let it pass */ if (!BR_INPUT_SKB_CB(skb)->vlan_filtered) goto out; - /* Vlan filter table must be configured at this point. The + /* At this point, we know that the frame was filtered and contains + * a valid vlan id. If the vlan id has untagged flag set, + * send untagged; otherwise, send tagged. + */ + br_vlan_get_tag(skb, &vid); + v = br_vlan_find(vg, vid); + /* Vlan entry must be configured at this point. The * only exception is the bridge is set in promisc mode and the * packet is destined for the bridge device. In this case * pass the packet as is. */ - if (!pv) { + if (!v || !br_vlan_should_use(v)) { if ((br->dev->flags & IFF_PROMISC) && skb->dev == br->dev) { goto out; } else { @@ -210,13 +338,7 @@ struct sk_buff *br_handle_vlan(struct net_bridge *br, return NULL; } } - - /* At this point, we know that the frame was filtered and contains - * a valid vlan id. If the vlan id is set in the untagged bitmap, - * send untagged; otherwise, send tagged. - */ - br_vlan_get_tag(skb, &vid); - if (test_bit(vid, pv->untagged_bitmap)) + if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED) skb->vlan_tci = 0; out: @@ -224,29 +346,13 @@ out: } /* Called under RCU */ -bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, - struct sk_buff *skb, u16 *vid) +static bool __allowed_ingress(struct net_bridge_vlan_group *vg, __be16 proto, + struct sk_buff *skb, u16 *vid) { + const struct net_bridge_vlan *v; bool tagged; - __be16 proto; - - /* If VLAN filtering is disabled on the bridge, all packets are - * permitted. - */ - if (!br->vlan_enabled) { - BR_INPUT_SKB_CB(skb)->vlan_filtered = false; - return true; - } - - /* If there are no vlan in the permitted list, all packets are - * rejected. - */ - if (!v) - goto drop; BR_INPUT_SKB_CB(skb)->vlan_filtered = true; - proto = br->vlan_proto; - /* If vlan tx offload is disabled on bridge device and frame was * sent from vlan device on the bridge device, it does not have * HW accelerated vlan tag. @@ -281,7 +387,7 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, } if (!*vid) { - u16 pvid = br_get_pvid(v); + u16 pvid = br_get_pvid(vg); /* Frame had a tag with VID 0 or did not have a tag. * See if pvid is set on this port. That tells us which @@ -309,29 +415,43 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, } /* Frame had a valid vlan tag. See if vlan is allowed */ - if (test_bit(*vid, v->vlan_bitmap)) + v = br_vlan_find(vg, *vid); + if (v && br_vlan_should_use(v)) return true; drop: kfree_skb(skb); return false; } +bool br_allowed_ingress(const struct net_bridge *br, + struct net_bridge_vlan_group *vg, struct sk_buff *skb, + u16 *vid) +{ + /* If VLAN filtering is disabled on the bridge, all packets are + * permitted. + */ + if (!br->vlan_enabled) { + BR_INPUT_SKB_CB(skb)->vlan_filtered = false; + return true; + } + + return __allowed_ingress(vg, br->vlan_proto, skb, vid); +} + /* Called under RCU. */ -bool br_allowed_egress(struct net_bridge *br, - const struct net_port_vlans *v, +bool br_allowed_egress(struct net_bridge_vlan_group *vg, const struct sk_buff *skb) { + const struct net_bridge_vlan *v; u16 vid; /* If this packet was not filtered at input, let it pass */ if (!BR_INPUT_SKB_CB(skb)->vlan_filtered) return true; - if (!v) - return false; - br_vlan_get_tag(skb, &vid); - if (test_bit(vid, v->vlan_bitmap)) + v = br_vlan_find(vg, vid); + if (v && br_vlan_should_use(v)) return true; return false; @@ -340,29 +460,29 @@ bool br_allowed_egress(struct net_bridge *br, /* Called under RCU */ bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid) { + struct net_bridge_vlan_group *vg; struct net_bridge *br = p->br; - struct net_port_vlans *v; /* If filtering was disabled at input, let it pass. */ if (!br->vlan_enabled) return true; - v = rcu_dereference(p->vlan_info); - if (!v) + vg = p->vlgrp; + if (!vg || !vg->num_vlans) return false; if (!br_vlan_get_tag(skb, vid) && skb->vlan_proto != br->vlan_proto) *vid = 0; if (!*vid) { - *vid = br_get_pvid(v); + *vid = br_get_pvid(vg); if (!*vid) return false; return true; } - if (test_bit(*vid, v->vlan_bitmap)) + if (br_vlan_find(vg, *vid)) return true; return false; @@ -373,31 +493,47 @@ bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid) */ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags) { - struct net_port_vlans *pv = NULL; - int err; + struct net_bridge_vlan *vlan; + int ret; ASSERT_RTNL(); - pv = rtnl_dereference(br->vlan_info); - if (pv) - return __vlan_add(pv, vid, flags); + vlan = br_vlan_find(br->vlgrp, vid); + if (vlan) { + if (!br_vlan_is_brentry(vlan)) { + /* Trying to change flags of non-existent bridge vlan */ + if (!(flags & BRIDGE_VLAN_INFO_BRENTRY)) + return -EINVAL; + /* It was only kept for port vlans, now make it real */ + ret = br_fdb_insert(br, NULL, br->dev->dev_addr, + vlan->vid); + if (ret) { + br_err(br, "failed insert local address into bridge forwarding table\n"); + return ret; + } + atomic_inc(&vlan->refcnt); + vlan->flags |= BRIDGE_VLAN_INFO_BRENTRY; + br->vlgrp->num_vlans++; + } + __vlan_add_flags(vlan, flags); + return 0; + } - /* Create port vlan infomration - */ - pv = kzalloc(sizeof(*pv), GFP_KERNEL); - if (!pv) + vlan = kzalloc(sizeof(*vlan), GFP_KERNEL); + if (!vlan) return -ENOMEM; - pv->parent.br = br; - err = __vlan_add(pv, vid, flags); - if (err) - goto out; + vlan->vid = vid; + vlan->flags = flags | BRIDGE_VLAN_INFO_MASTER; + vlan->flags &= ~BRIDGE_VLAN_INFO_PVID; + vlan->br = br; + if (flags & BRIDGE_VLAN_INFO_BRENTRY) + atomic_set(&vlan->refcnt, 1); + ret = __vlan_add(vlan, flags); + if (ret) + kfree(vlan); - rcu_assign_pointer(br->vlan_info, pv); - return 0; -out: - kfree(pv); - return err; + return ret; } /* Must be protected by RTNL. @@ -405,49 +541,32 @@ out: */ int br_vlan_delete(struct net_bridge *br, u16 vid) { - struct net_port_vlans *pv; + struct net_bridge_vlan *v; ASSERT_RTNL(); - pv = rtnl_dereference(br->vlan_info); - if (!pv) - return -EINVAL; + v = br_vlan_find(br->vlgrp, vid); + if (!v || !br_vlan_is_brentry(v)) + return -ENOENT; br_fdb_find_delete_local(br, NULL, br->dev->dev_addr, vid); - __vlan_del(pv, vid); - return 0; + return __vlan_del(v); } void br_vlan_flush(struct net_bridge *br) { - struct net_port_vlans *pv; - ASSERT_RTNL(); - pv = rtnl_dereference(br->vlan_info); - if (!pv) - return; - __vlan_flush(pv); + __vlan_flush(br_vlan_group(br)); } -bool br_vlan_find(struct net_bridge *br, u16 vid) +struct net_bridge_vlan *br_vlan_find(struct net_bridge_vlan_group *vg, u16 vid) { - struct net_port_vlans *pv; - bool found = false; - - rcu_read_lock(); - pv = rcu_dereference(br->vlan_info); - - if (!pv) - goto out; + if (!vg) + return NULL; - if (test_bit(vid, pv->vlan_bitmap)) - found = true; - -out: - rcu_read_unlock(); - return found; + return br_vlan_lookup(&vg->vlan_hash, vid); } /* Must be protected by RTNL. */ @@ -505,21 +624,16 @@ int __br_vlan_set_proto(struct net_bridge *br, __be16 proto) { int err = 0; struct net_bridge_port *p; - struct net_port_vlans *pv; + struct net_bridge_vlan *vlan; __be16 oldproto; - u16 vid, errvid; if (br->vlan_proto == proto) return 0; /* Add VLANs for the new proto to the device filter. */ list_for_each_entry(p, &br->port_list, list) { - pv = rtnl_dereference(p->vlan_info); - if (!pv) - continue; - - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { - err = vlan_vid_add(p->dev, proto, vid); + list_for_each_entry(vlan, &p->vlgrp->vlan_list, vlist) { + err = vlan_vid_add(p->dev, proto, vlan->vid); if (err) goto err_filt; } @@ -532,30 +646,19 @@ int __br_vlan_set_proto(struct net_bridge *br, __be16 proto) br_recalculate_fwd_mask(br); /* Delete VLANs for the old proto from the device filter. */ - list_for_each_entry(p, &br->port_list, list) { - pv = rtnl_dereference(p->vlan_info); - if (!pv) - continue; - - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) - vlan_vid_del(p->dev, oldproto, vid); - } + list_for_each_entry(p, &br->port_list, list) + list_for_each_entry(vlan, &p->vlgrp->vlan_list, vlist) + vlan_vid_del(p->dev, oldproto, vlan->vid); return 0; err_filt: - errvid = vid; - for_each_set_bit(vid, pv->vlan_bitmap, errvid) - vlan_vid_del(p->dev, proto, vid); - - list_for_each_entry_continue_reverse(p, &br->port_list, list) { - pv = rtnl_dereference(p->vlan_info); - if (!pv) - continue; + list_for_each_entry_continue_reverse(vlan, &p->vlgrp->vlan_list, vlist) + vlan_vid_del(p->dev, proto, vlan->vid); - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) - vlan_vid_del(p->dev, proto, vid); - } + list_for_each_entry_continue_reverse(p, &br->port_list, list) + list_for_each_entry(vlan, &p->vlgrp->vlan_list, vlist) + vlan_vid_del(p->dev, proto, vlan->vid); return err; } @@ -576,9 +679,19 @@ int br_vlan_set_proto(struct net_bridge *br, unsigned long val) return err; } -static bool vlan_default_pvid(struct net_port_vlans *pv, u16 vid) +static bool vlan_default_pvid(struct net_bridge_vlan_group *vg, u16 vid) { - return pv && vid == pv->pvid && test_bit(vid, pv->untagged_bitmap); + struct net_bridge_vlan *v; + + if (vid != vg->pvid) + return false; + + v = br_vlan_lookup(&vg->vlan_hash, vid); + if (v && br_vlan_should_use(v) && + (v->flags & BRIDGE_VLAN_INFO_UNTAGGED)) + return true; + + return false; } static void br_vlan_disable_default_pvid(struct net_bridge *br) @@ -589,11 +702,11 @@ static void br_vlan_disable_default_pvid(struct net_bridge *br) /* Disable default_pvid on all ports where it is still * configured. */ - if (vlan_default_pvid(br_get_vlan_info(br), pvid)) + if (vlan_default_pvid(br->vlgrp, pvid)) br_vlan_delete(br, pvid); list_for_each_entry(p, &br->port_list, list) { - if (vlan_default_pvid(nbp_get_vlan_info(p), pvid)) + if (vlan_default_pvid(p->vlgrp, pvid)) nbp_vlan_delete(p, pvid); } @@ -602,6 +715,7 @@ static void br_vlan_disable_default_pvid(struct net_bridge *br) static int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid) { + const struct net_bridge_vlan *pvent; struct net_bridge_port *p; u16 old_pvid; int err = 0; @@ -617,11 +731,13 @@ static int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid) /* Update default_pvid config only if we do not conflict with * user configuration. */ - if ((!old_pvid || vlan_default_pvid(br_get_vlan_info(br), old_pvid)) && - !br_vlan_find(br, pvid)) { + pvent = br_vlan_find(br->vlgrp, pvid); + if ((!old_pvid || vlan_default_pvid(br->vlgrp, old_pvid)) && + (!pvent || !br_vlan_should_use(pvent))) { err = br_vlan_add(br, pvid, BRIDGE_VLAN_INFO_PVID | - BRIDGE_VLAN_INFO_UNTAGGED); + BRIDGE_VLAN_INFO_UNTAGGED | + BRIDGE_VLAN_INFO_BRENTRY); if (err) goto out; br_vlan_delete(br, old_pvid); @@ -633,8 +749,8 @@ static int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid) * user configuration. */ if ((old_pvid && - !vlan_default_pvid(nbp_get_vlan_info(p), old_pvid)) || - nbp_vlan_find(p, pvid)) + !vlan_default_pvid(p->vlgrp, old_pvid)) || + br_vlan_find(p->vlgrp, pvid)) continue; err = nbp_vlan_add(p, pvid, @@ -668,7 +784,8 @@ err_port: if (old_pvid) br_vlan_add(br, old_pvid, BRIDGE_VLAN_INFO_PVID | - BRIDGE_VLAN_INFO_UNTAGGED); + BRIDGE_VLAN_INFO_UNTAGGED | + BRIDGE_VLAN_INFO_BRENTRY); br_vlan_delete(br, pvid); } goto out; @@ -707,10 +824,66 @@ unlock: int br_vlan_init(struct net_bridge *br) { + int ret = -ENOMEM; + + br->vlgrp = kzalloc(sizeof(struct net_bridge_vlan_group), GFP_KERNEL); + if (!br->vlgrp) + goto out; + ret = rhashtable_init(&br->vlgrp->vlan_hash, &br_vlan_rht_params); + if (ret) + goto err_rhtbl; + INIT_LIST_HEAD(&br->vlgrp->vlan_list); br->vlan_proto = htons(ETH_P_8021Q); br->default_pvid = 1; - return br_vlan_add(br, 1, - BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED); + ret = br_vlan_add(br, 1, + BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED | + BRIDGE_VLAN_INFO_BRENTRY); + if (ret) + goto err_vlan_add; + +out: + return ret; + +err_vlan_add: + rhashtable_destroy(&br->vlgrp->vlan_hash); +err_rhtbl: + kfree(br->vlgrp); + + goto out; +} + +int nbp_vlan_init(struct net_bridge_port *p) +{ + struct net_bridge_vlan_group *vg; + int ret = -ENOMEM; + + vg = kzalloc(sizeof(struct net_bridge_vlan_group), GFP_KERNEL); + if (!vg) + goto out; + + ret = rhashtable_init(&vg->vlan_hash, &br_vlan_rht_params); + if (ret) + goto err_rhtbl; + INIT_LIST_HEAD(&vg->vlan_list); + /* Make sure everything's committed before publishing vg */ + smp_wmb(); + p->vlgrp = vg; + if (p->br->default_pvid) { + ret = nbp_vlan_add(p, p->br->default_pvid, + BRIDGE_VLAN_INFO_PVID | + BRIDGE_VLAN_INFO_UNTAGGED); + if (ret) + goto err_vlan_add; + } +out: + return ret; + +err_vlan_add: + rhashtable_destroy(&vg->vlan_hash); +err_rhtbl: + kfree(vg); + + goto out; } /* Must be protected by RTNL. @@ -718,35 +891,28 @@ int br_vlan_init(struct net_bridge *br) */ int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags) { - struct net_port_vlans *pv = NULL; - int err; + struct net_bridge_vlan *vlan; + int ret; ASSERT_RTNL(); - pv = rtnl_dereference(port->vlan_info); - if (pv) - return __vlan_add(pv, vid, flags); - - /* Create port vlan infomration - */ - pv = kzalloc(sizeof(*pv), GFP_KERNEL); - if (!pv) { - err = -ENOMEM; - goto clean_up; + vlan = br_vlan_find(port->vlgrp, vid); + if (vlan) { + __vlan_add_flags(vlan, flags); + return 0; } - pv->port_idx = port->port_no; - pv->parent.port = port; - err = __vlan_add(pv, vid, flags); - if (err) - goto clean_up; + vlan = kzalloc(sizeof(*vlan), GFP_KERNEL); + if (!vlan) + return -ENOMEM; - rcu_assign_pointer(port->vlan_info, pv); - return 0; + vlan->vid = vid; + vlan->port = port; + ret = __vlan_add(vlan, flags); + if (ret) + kfree(vlan); -clean_up: - kfree(pv); - return err; + return ret; } /* Must be protected by RTNL. @@ -754,61 +920,27 @@ clean_up: */ int nbp_vlan_delete(struct net_bridge_port *port, u16 vid) { - struct net_port_vlans *pv; + struct net_bridge_vlan *v; ASSERT_RTNL(); - pv = rtnl_dereference(port->vlan_info); - if (!pv) - return -EINVAL; - + v = br_vlan_find(port->vlgrp, vid); + if (!v) + return -ENOENT; br_fdb_find_delete_local(port->br, port, port->dev->dev_addr, vid); br_fdb_delete_by_port(port->br, port, vid, 0); - return __vlan_del(pv, vid); + return __vlan_del(v); } void nbp_vlan_flush(struct net_bridge_port *port) { - struct net_port_vlans *pv; - u16 vid; + struct net_bridge_vlan *vlan; ASSERT_RTNL(); - pv = rtnl_dereference(port->vlan_info); - if (!pv) - return; - - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) - vlan_vid_del(port->dev, port->br->vlan_proto, vid); + list_for_each_entry(vlan, &port->vlgrp->vlan_list, vlist) + vlan_vid_del(port->dev, port->br->vlan_proto, vlan->vid); - __vlan_flush(pv); -} - -bool nbp_vlan_find(struct net_bridge_port *port, u16 vid) -{ - struct net_port_vlans *pv; - bool found = false; - - rcu_read_lock(); - pv = rcu_dereference(port->vlan_info); - - if (!pv) - goto out; - - if (test_bit(vid, pv->vlan_bitmap)) - found = true; - -out: - rcu_read_unlock(); - return found; -} - -int nbp_vlan_init(struct net_bridge_port *p) -{ - return p->br->default_pvid ? - nbp_vlan_add(p, p->br->default_pvid, - BRIDGE_VLAN_INFO_PVID | - BRIDGE_VLAN_INFO_UNTAGGED) : - 0; + __vlan_flush(nbp_vlan_group(port)); } diff --git a/net/bridge/netfilter/ebt_log.c b/net/bridge/netfilter/ebt_log.c index 17f2e4bc2a29..0ad639a96142 100644 --- a/net/bridge/netfilter/ebt_log.c +++ b/net/bridge/netfilter/ebt_log.c @@ -180,7 +180,7 @@ ebt_log_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ebt_log_info *info = par->targinfo; struct nf_loginfo li; - struct net *net = dev_net(par->in ? par->in : par->out); + struct net *net = par->net; li.type = NF_LOG_TYPE_LOG; li.u.log.level = info->loglevel; diff --git a/net/bridge/netfilter/ebt_nflog.c b/net/bridge/netfilter/ebt_nflog.c index 59ac7952010d..54816150608e 100644 --- a/net/bridge/netfilter/ebt_nflog.c +++ b/net/bridge/netfilter/ebt_nflog.c @@ -24,7 +24,7 @@ ebt_nflog_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ebt_nflog_info *info = par->targinfo; struct nf_loginfo li; - struct net *net = dev_net(par->in ? par->in : par->out); + struct net *net = par->net; li.type = NF_LOG_TYPE_ULOG; li.u.ulog.copy_len = info->len; diff --git a/net/bridge/netfilter/ebtable_broute.c b/net/bridge/netfilter/ebtable_broute.c index d2cdf5d6e98c..ec94c6f1ae88 100644 --- a/net/bridge/netfilter/ebtable_broute.c +++ b/net/bridge/netfilter/ebtable_broute.c @@ -50,10 +50,14 @@ static const struct ebt_table broute_table = { static int ebt_broute(struct sk_buff *skb) { + struct nf_hook_state state; int ret; - ret = ebt_do_table(NF_BR_BROUTING, skb, skb->dev, NULL, - dev_net(skb->dev)->xt.broute_table); + nf_hook_state_init(&state, NULL, NF_BR_BROUTING, INT_MIN, + NFPROTO_BRIDGE, skb->dev, NULL, NULL, + dev_net(skb->dev), NULL); + + ret = ebt_do_table(skb, &state, state.net->xt.broute_table); if (ret == NF_DROP) return 1; /* route it */ return 0; /* bridge it */ diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c index 8a3f63b2e807..f9242dffa65e 100644 --- a/net/bridge/netfilter/ebtable_filter.c +++ b/net/bridge/netfilter/ebtable_filter.c @@ -57,19 +57,17 @@ static const struct ebt_table frame_filter = { }; static unsigned int -ebt_in_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, +ebt_in_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return ebt_do_table(ops->hooknum, skb, state->in, state->out, - dev_net(state->in)->xt.frame_filter); + return ebt_do_table(skb, state, state->net->xt.frame_filter); } static unsigned int -ebt_out_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, +ebt_out_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return ebt_do_table(ops->hooknum, skb, state->in, state->out, - dev_net(state->out)->xt.frame_filter); + return ebt_do_table(skb, state, state->net->xt.frame_filter); } static struct nf_hook_ops ebt_ops_filter[] __read_mostly = { diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c index c5ef5b1ab678..4bbefe03ab58 100644 --- a/net/bridge/netfilter/ebtable_nat.c +++ b/net/bridge/netfilter/ebtable_nat.c @@ -57,19 +57,17 @@ static struct ebt_table frame_nat = { }; static unsigned int -ebt_nat_in(const struct nf_hook_ops *ops, struct sk_buff *skb, +ebt_nat_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return ebt_do_table(ops->hooknum, skb, state->in, state->out, - dev_net(state->in)->xt.frame_nat); + return ebt_do_table(skb, state, state->net->xt.frame_nat); } static unsigned int -ebt_nat_out(const struct nf_hook_ops *ops, struct sk_buff *skb, +ebt_nat_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return ebt_do_table(ops->hooknum, skb, state->in, state->out, - dev_net(state->out)->xt.frame_nat); + return ebt_do_table(skb, state, state->net->xt.frame_nat); } static struct nf_hook_ops ebt_ops_nat[] __read_mostly = { diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 48b6b01295de..f46ca417bf2d 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -183,10 +183,11 @@ struct ebt_entry *ebt_next_entry(const struct ebt_entry *entry) } /* Do some firewalling */ -unsigned int ebt_do_table (unsigned int hook, struct sk_buff *skb, - const struct net_device *in, const struct net_device *out, - struct ebt_table *table) +unsigned int ebt_do_table(struct sk_buff *skb, + const struct nf_hook_state *state, + struct ebt_table *table) { + unsigned int hook = state->hook; int i, nentries; struct ebt_entry *point; struct ebt_counter *counter_base, *cb_base; @@ -199,8 +200,9 @@ unsigned int ebt_do_table (unsigned int hook, struct sk_buff *skb, struct xt_action_param acpar; acpar.family = NFPROTO_BRIDGE; - acpar.in = in; - acpar.out = out; + acpar.net = state->net; + acpar.in = state->in; + acpar.out = state->out; acpar.hotdrop = false; acpar.hooknum = hook; @@ -220,7 +222,7 @@ unsigned int ebt_do_table (unsigned int hook, struct sk_buff *skb, base = private->entries; i = 0; while (i < nentries) { - if (ebt_basic_match(point, skb, in, out)) + if (ebt_basic_match(point, skb, state->in, state->out)) goto letscontinue; if (EBT_MATCH_ITERATE(point, ebt_do_match, skb, &acpar) != 0) diff --git a/net/bridge/netfilter/nf_tables_bridge.c b/net/bridge/netfilter/nf_tables_bridge.c index a343e62442b1..62f6b1b19589 100644 --- a/net/bridge/netfilter/nf_tables_bridge.c +++ b/net/bridge/netfilter/nf_tables_bridge.c @@ -65,31 +65,29 @@ int nft_bridge_ip6hdr_validate(struct sk_buff *skb) EXPORT_SYMBOL_GPL(nft_bridge_ip6hdr_validate); static inline void nft_bridge_set_pktinfo_ipv4(struct nft_pktinfo *pkt, - const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { if (nft_bridge_iphdr_validate(skb)) - nft_set_pktinfo_ipv4(pkt, ops, skb, state); + nft_set_pktinfo_ipv4(pkt, skb, state); else - nft_set_pktinfo(pkt, ops, skb, state); + nft_set_pktinfo(pkt, skb, state); } static inline void nft_bridge_set_pktinfo_ipv6(struct nft_pktinfo *pkt, - const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { #if IS_ENABLED(CONFIG_IPV6) if (nft_bridge_ip6hdr_validate(skb) && - nft_set_pktinfo_ipv6(pkt, ops, skb, state) == 0) + nft_set_pktinfo_ipv6(pkt, skb, state) == 0) return; #endif - nft_set_pktinfo(pkt, ops, skb, state); + nft_set_pktinfo(pkt, skb, state); } static unsigned int -nft_do_chain_bridge(const struct nf_hook_ops *ops, +nft_do_chain_bridge(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -97,17 +95,17 @@ nft_do_chain_bridge(const struct nf_hook_ops *ops, switch (eth_hdr(skb)->h_proto) { case htons(ETH_P_IP): - nft_bridge_set_pktinfo_ipv4(&pkt, ops, skb, state); + nft_bridge_set_pktinfo_ipv4(&pkt, skb, state); break; case htons(ETH_P_IPV6): - nft_bridge_set_pktinfo_ipv6(&pkt, ops, skb, state); + nft_bridge_set_pktinfo_ipv6(&pkt, skb, state); break; default: - nft_set_pktinfo(&pkt, ops, skb, state); + nft_set_pktinfo(&pkt, skb, state); break; } - return nft_do_chain(&pkt, ops); + return nft_do_chain(&pkt, priv); } static struct nft_af_info nft_af_bridge __read_mostly = { diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c index 858d848564ee..fdba3d9fbff3 100644 --- a/net/bridge/netfilter/nft_reject_bridge.c +++ b/net/bridge/netfilter/nft_reject_bridge.c @@ -261,7 +261,6 @@ static void nft_reject_bridge_eval(const struct nft_expr *expr, const struct nft_pktinfo *pkt) { struct nft_reject *priv = nft_expr_priv(expr); - struct net *net = dev_net((pkt->in != NULL) ? pkt->in : pkt->out); const unsigned char *dest = eth_hdr(pkt->skb)->h_dest; if (is_broadcast_ether_addr(dest) || @@ -273,16 +272,16 @@ static void nft_reject_bridge_eval(const struct nft_expr *expr, switch (priv->type) { case NFT_REJECT_ICMP_UNREACH: nft_reject_br_send_v4_unreach(pkt->skb, pkt->in, - pkt->ops->hooknum, + pkt->hook, priv->icmp_code); break; case NFT_REJECT_TCP_RST: nft_reject_br_send_v4_tcp_reset(pkt->skb, pkt->in, - pkt->ops->hooknum); + pkt->hook); break; case NFT_REJECT_ICMPX_UNREACH: nft_reject_br_send_v4_unreach(pkt->skb, pkt->in, - pkt->ops->hooknum, + pkt->hook, nft_reject_icmp_code(priv->icmp_code)); break; } @@ -290,17 +289,17 @@ static void nft_reject_bridge_eval(const struct nft_expr *expr, case htons(ETH_P_IPV6): switch (priv->type) { case NFT_REJECT_ICMP_UNREACH: - nft_reject_br_send_v6_unreach(net, pkt->skb, pkt->in, - pkt->ops->hooknum, + nft_reject_br_send_v6_unreach(pkt->net, pkt->skb, + pkt->in, pkt->hook, priv->icmp_code); break; case NFT_REJECT_TCP_RST: - nft_reject_br_send_v6_tcp_reset(net, pkt->skb, pkt->in, - pkt->ops->hooknum); + nft_reject_br_send_v6_tcp_reset(pkt->net, pkt->skb, + pkt->in, pkt->hook); break; case NFT_REJECT_ICMPX_UNREACH: - nft_reject_br_send_v6_unreach(net, pkt->skb, pkt->in, - pkt->ops->hooknum, + nft_reject_br_send_v6_unreach(pkt->net, pkt->skb, + pkt->in, pkt->hook, nft_reject_icmpv6_code(priv->icmp_code)); break; } diff --git a/net/core/dev.c b/net/core/dev.c index 6bb6470f5b7b..323c04edd779 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2915,9 +2915,11 @@ EXPORT_SYMBOL(xmit_recursion); /** * dev_loopback_xmit - loop back @skb + * @net: network namespace this loopback is happening in + * @sk: sk needed to be a netfilter okfn * @skb: buffer to transmit */ -int dev_loopback_xmit(struct sock *sk, struct sk_buff *skb) +int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *skb) { skb_reset_mac_header(skb); __skb_pull(skb, skb_network_offset(skb)); @@ -3143,11 +3145,11 @@ out: return rc; } -int dev_queue_xmit_sk(struct sock *sk, struct sk_buff *skb) +int dev_queue_xmit(struct sk_buff *skb) { return __dev_queue_xmit(skb, NULL); } -EXPORT_SYMBOL(dev_queue_xmit_sk); +EXPORT_SYMBOL(dev_queue_xmit); int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv) { @@ -3668,6 +3670,14 @@ static inline struct sk_buff *handle_ing(struct sk_buff *skb, case TC_ACT_QUEUED: kfree_skb(skb); return NULL; + case TC_ACT_REDIRECT: + /* skb_mac_header check was done by cls/act_bpf, so + * we can safely push the L2 header back before + * redirecting to another netdev + */ + __skb_push(skb, skb->mac_len); + skb_do_redirect(skb); + return NULL; default: break; } @@ -3982,13 +3992,13 @@ static int netif_receive_skb_internal(struct sk_buff *skb) * NET_RX_SUCCESS: no congestion * NET_RX_DROP: packet was dropped */ -int netif_receive_skb_sk(struct sock *sk, struct sk_buff *skb) +int netif_receive_skb(struct sk_buff *skb) { trace_netif_receive_skb_entry(skb); return netif_receive_skb_internal(skb); } -EXPORT_SYMBOL(netif_receive_skb_sk); +EXPORT_SYMBOL(netif_receive_skb); /* Network device is going away, flush any packets still pending * Called with irqs disabled. @@ -4857,8 +4867,7 @@ struct netdev_adjacent { struct rcu_head rcu; }; -static struct netdev_adjacent *__netdev_find_adj(struct net_device *dev, - struct net_device *adj_dev, +static struct netdev_adjacent *__netdev_find_adj(struct net_device *adj_dev, struct list_head *adj_list) { struct netdev_adjacent *adj; @@ -4884,7 +4893,7 @@ bool netdev_has_upper_dev(struct net_device *dev, { ASSERT_RTNL(); - return __netdev_find_adj(dev, upper_dev, &dev->all_adj_list.upper); + return __netdev_find_adj(upper_dev, &dev->all_adj_list.upper); } EXPORT_SYMBOL(netdev_has_upper_dev); @@ -5146,7 +5155,7 @@ static int __netdev_adjacent_dev_insert(struct net_device *dev, struct netdev_adjacent *adj; int ret; - adj = __netdev_find_adj(dev, adj_dev, dev_list); + adj = __netdev_find_adj(adj_dev, dev_list); if (adj) { adj->ref_nr++; @@ -5202,7 +5211,7 @@ static void __netdev_adjacent_dev_remove(struct net_device *dev, { struct netdev_adjacent *adj; - adj = __netdev_find_adj(dev, adj_dev, dev_list); + adj = __netdev_find_adj(adj_dev, dev_list); if (!adj) { pr_err("tried to remove device %s from %s\n", @@ -5323,10 +5332,10 @@ static int __netdev_upper_dev_link(struct net_device *dev, return -EBUSY; /* To prevent loops, check if dev is not upper device to upper_dev. */ - if (__netdev_find_adj(upper_dev, dev, &upper_dev->all_adj_list.upper)) + if (__netdev_find_adj(dev, &upper_dev->all_adj_list.upper)) return -EBUSY; - if (__netdev_find_adj(dev, upper_dev, &dev->adj_list.upper)) + if (__netdev_find_adj(upper_dev, &dev->adj_list.upper)) return -EEXIST; if (master && netdev_master_upper_dev_get(dev)) @@ -5604,7 +5613,7 @@ void *netdev_lower_dev_get_private(struct net_device *dev, if (!lower_dev) return NULL; - lower = __netdev_find_adj(dev, lower_dev, &dev->adj_list.lower); + lower = __netdev_find_adj(lower_dev, &dev->adj_list.lower); if (!lower) return NULL; diff --git a/net/core/filter.c b/net/core/filter.c index 05a04ea87172..60e3fe7c59c0 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1404,9 +1404,6 @@ static u64 bpf_clone_redirect(u64 r1, u64 ifindex, u64 flags, u64 r4, u64 r5) if (unlikely(!dev)) return -EINVAL; - if (unlikely(!(dev->flags & IFF_UP))) - return -EINVAL; - skb2 = skb_clone(skb, GFP_ATOMIC); if (unlikely(!skb2)) return -ENOMEM; @@ -1427,6 +1424,48 @@ const struct bpf_func_proto bpf_clone_redirect_proto = { .arg3_type = ARG_ANYTHING, }; +struct redirect_info { + u32 ifindex; + u32 flags; +}; + +static DEFINE_PER_CPU(struct redirect_info, redirect_info); +static u64 bpf_redirect(u64 ifindex, u64 flags, u64 r3, u64 r4, u64 r5) +{ + struct redirect_info *ri = this_cpu_ptr(&redirect_info); + + ri->ifindex = ifindex; + ri->flags = flags; + return TC_ACT_REDIRECT; +} + +int skb_do_redirect(struct sk_buff *skb) +{ + struct redirect_info *ri = this_cpu_ptr(&redirect_info); + struct net_device *dev; + + dev = dev_get_by_index_rcu(dev_net(skb->dev), ri->ifindex); + ri->ifindex = 0; + if (unlikely(!dev)) { + kfree_skb(skb); + return -EINVAL; + } + + if (BPF_IS_REDIRECT_INGRESS(ri->flags)) + return dev_forward_skb(dev, skb); + + skb->dev = dev; + return dev_queue_xmit(skb); +} + +const struct bpf_func_proto bpf_redirect_proto = { + .func = bpf_redirect, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, + .arg2_type = ARG_ANYTHING, +}; + static u64 bpf_get_cgroup_classid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) { return task_get_classid((struct sk_buff *) (unsigned long) r1); @@ -1607,6 +1646,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) return &bpf_skb_get_tunnel_key_proto; case BPF_FUNC_skb_set_tunnel_key: return bpf_get_skb_set_tunnel_key_proto(); + case BPF_FUNC_redirect: + return &bpf_redirect_proto; default: return sk_filter_func_proto(func_id); } @@ -1632,6 +1673,9 @@ static bool __is_valid_access(int off, int size, enum bpf_access_type type) static bool sk_filter_is_valid_access(int off, int size, enum bpf_access_type type) { + if (off == offsetof(struct __sk_buff, tc_classid)) + return false; + if (type == BPF_WRITE) { switch (off) { case offsetof(struct __sk_buff, cb[0]) ... @@ -1648,6 +1692,9 @@ static bool sk_filter_is_valid_access(int off, int size, static bool tc_cls_act_is_valid_access(int off, int size, enum bpf_access_type type) { + if (off == offsetof(struct __sk_buff, tc_classid)) + return type == BPF_WRITE ? true : false; + if (type == BPF_WRITE) { switch (off) { case offsetof(struct __sk_buff, mark): @@ -1760,6 +1807,14 @@ static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg, *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, ctx_off); break; + case offsetof(struct __sk_buff, tc_classid): + ctx_off -= offsetof(struct __sk_buff, tc_classid); + ctx_off += offsetof(struct sk_buff, cb); + ctx_off += offsetof(struct qdisc_skb_cb, tc_classid); + WARN_ON(type != BPF_WRITE); + *insn++ = BPF_STX_MEM(BPF_H, dst_reg, src_reg, ctx_off); + break; + case offsetof(struct __sk_buff, tc_index): #ifdef CONFIG_NET_SCHED BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, tc_index) != 2); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 2b515ba7e94f..8c57fdf4d68e 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2235,14 +2235,42 @@ static void neigh_update_notify(struct neighbour *neigh) __neigh_notify(neigh, RTM_NEWNEIGH, 0); } +static bool neigh_master_filtered(struct net_device *dev, int master_idx) +{ + struct net_device *master; + + if (!master_idx) + return false; + + master = netdev_master_upper_dev_get(dev); + if (!master || master->ifindex != master_idx) + return true; + + return false; +} + static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); + const struct nlmsghdr *nlh = cb->nlh; + struct nlattr *tb[NDA_MAX + 1]; struct neighbour *n; int rc, h, s_h = cb->args[1]; int idx, s_idx = idx = cb->args[2]; struct neigh_hash_table *nht; + int filter_master_idx = 0; + unsigned int flags = NLM_F_MULTI; + int err; + + err = nlmsg_parse(nlh, sizeof(struct ndmsg), tb, NDA_MAX, NULL); + if (!err) { + if (tb[NDA_MASTER]) + filter_master_idx = nla_get_u32(tb[NDA_MASTER]); + + if (filter_master_idx) + flags |= NLM_F_DUMP_FILTERED; + } rcu_read_lock_bh(); nht = rcu_dereference_bh(tbl->nht); @@ -2255,12 +2283,14 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, n = rcu_dereference_bh(n->next)) { if (!net_eq(dev_net(n->dev), net)) continue; + if (neigh_master_filtered(n->dev, filter_master_idx)) + continue; if (idx < s_idx) goto next; if (neigh_fill_info(skb, n, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, - NLM_F_MULTI) < 0) { + flags) < 0) { rc = -1; goto out; } diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 830f8a7c1cb1..410c6e42bf1f 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1003,15 +1003,12 @@ static ssize_t show_trans_timeout(struct netdev_queue *queue, } #ifdef CONFIG_XPS -static inline unsigned int get_netdev_queue_index(struct netdev_queue *queue) +static unsigned int get_netdev_queue_index(struct netdev_queue *queue) { struct net_device *dev = queue->dev; - int i; - - for (i = 0; i < dev->num_tx_queues; i++) - if (queue == &dev->_tx[i]) - break; + unsigned int i; + i = queue - dev->_tx; BUG_ON(i >= dev->num_tx_queues); return i; diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 8bdada242a7d..94acfc89ad97 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -140,7 +140,7 @@ static void queue_process(struct work_struct *work) * case. Further, we test the poll_owner to avoid recursion on UP * systems where the lock doesn't exist. */ -static int poll_one_napi(struct napi_struct *napi, int budget) +static void poll_one_napi(struct napi_struct *napi) { int work = 0; @@ -149,33 +149,33 @@ static int poll_one_napi(struct napi_struct *napi, int budget) * holding the napi->poll_lock. */ if (!test_bit(NAPI_STATE_SCHED, &napi->state)) - return budget; + return; /* If we set this bit but see that it has already been set, * that indicates that napi has been disabled and we need * to abort this operation */ if (test_and_set_bit(NAPI_STATE_NPSVC, &napi->state)) - goto out; + return; - work = napi->poll(napi, budget); - WARN_ONCE(work > budget, "%pF exceeded budget in poll\n", napi->poll); + /* We explicilty pass the polling call a budget of 0 to + * indicate that we are clearing the Tx path only. + */ + work = napi->poll(napi, 0); + WARN_ONCE(work, "%pF exceeded budget in poll\n", napi->poll); trace_napi_poll(napi); clear_bit(NAPI_STATE_NPSVC, &napi->state); - -out: - return budget - work; } -static void poll_napi(struct net_device *dev, int budget) +static void poll_napi(struct net_device *dev) { struct napi_struct *napi; list_for_each_entry(napi, &dev->napi_list, dev_list) { if (napi->poll_owner != smp_processor_id() && spin_trylock(&napi->poll_lock)) { - budget = poll_one_napi(napi, budget); + poll_one_napi(napi); spin_unlock(&napi->poll_lock); } } @@ -185,7 +185,6 @@ static void netpoll_poll_dev(struct net_device *dev) { const struct net_device_ops *ops; struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo); - int budget = 0; /* Don't do any rx activity if the dev_lock mutex is held * the dev_open/close paths use this to block netpoll activity @@ -208,7 +207,7 @@ static void netpoll_poll_dev(struct net_device *dev) /* Process pending work on NIC */ ops->ndo_poll_controller(dev); - poll_napi(dev, budget); + poll_napi(dev); up(&ni->dev_lock); diff --git a/net/core/request_sock.c b/net/core/request_sock.c index b42f0e26f89e..e22cfa4ed25f 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -59,6 +59,13 @@ int reqsk_queue_alloc(struct request_sock_queue *queue, get_random_bytes(&lopt->hash_rnd, sizeof(lopt->hash_rnd)); spin_lock_init(&queue->syn_wait_lock); + + spin_lock_init(&queue->fastopenq.lock); + queue->fastopenq.rskq_rst_head = NULL; + queue->fastopenq.rskq_rst_tail = NULL; + queue->fastopenq.qlen = 0; + queue->fastopenq.max_qlen = 0; + queue->rskq_accept_head = NULL; lopt->nr_table_entries = nr_table_entries; lopt->max_qlen_log = ilog2(nr_table_entries); @@ -174,7 +181,7 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, struct sock *lsk = req->rsk_listener; struct fastopen_queue *fastopenq; - fastopenq = inet_csk(lsk)->icsk_accept_queue.fastopenq; + fastopenq = &inet_csk(lsk)->icsk_accept_queue.fastopenq; tcp_sk(sk)->fastopen_rsk = NULL; spin_lock_bh(&fastopenq->lock); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 0ec48403ed68..474a6da3b51a 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1272,7 +1272,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, if (!(af = nla_nest_start(skb, af_ops->family))) goto nla_put_failure; - err = af_ops->fill_link_af(skb, dev); + err = af_ops->fill_link_af(skb, dev, ext_filter_mask); /* * Caller may return ENODATA to indicate that there diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index bebc735f5afc..e1f823451565 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -229,7 +229,7 @@ void dccp_v4_send_check(struct sock *sk, struct sk_buff *skb); int dccp_retransmit_skb(struct sock *sk); void dccp_send_ack(struct sock *sk); -void dccp_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, +void dccp_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, struct request_sock *rsk); void dccp_send_sync(struct sock *sk, const u64 seq, @@ -270,13 +270,13 @@ int dccp_reqsk_init(struct request_sock *rq, struct dccp_sock const *dp, int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb); -struct sock *dccp_create_openreq_child(struct sock *sk, +struct sock *dccp_create_openreq_child(const struct sock *sk, const struct request_sock *req, const struct sk_buff *skb); int dccp_v4_do_rcv(struct sock *sk, struct sk_buff *skb); -struct sock *dccp_v4_request_recv_sock(struct sock *sk, struct sk_buff *skb, +struct sock *dccp_v4_request_recv_sock(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst); struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, @@ -293,7 +293,7 @@ int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized); void dccp_destroy_sock(struct sock *sk); void dccp_close(struct sock *sk, long timeout); -struct sk_buff *dccp_make_response(struct sock *sk, struct dst_entry *dst, +struct sk_buff *dccp_make_response(const struct sock *sk, struct dst_entry *dst, struct request_sock *req); int dccp_connect(struct sock *sk); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index ccf4c5629b3c..5b7818c63cec 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -390,7 +390,8 @@ static inline u64 dccp_v4_init_sequence(const struct sk_buff *skb) * * This is the equivalent of TCP's tcp_v4_syn_recv_sock */ -struct sock *dccp_v4_request_recv_sock(struct sock *sk, struct sk_buff *skb, +struct sock *dccp_v4_request_recv_sock(const struct sock *sk, + struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst) { @@ -498,7 +499,7 @@ static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk, return &rt->dst; } -static int dccp_v4_send_response(struct sock *sk, struct request_sock *req) +static int dccp_v4_send_response(const struct sock *sk, struct request_sock *req) { int err = -1; struct sk_buff *skb; @@ -527,7 +528,7 @@ out: return err; } -static void dccp_v4_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb) +static void dccp_v4_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb) { int err; const struct iphdr *rxiph; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 5165571f397a..e8753aa3b7a4 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -181,7 +181,7 @@ out: } -static int dccp_v6_send_response(struct sock *sk, struct request_sock *req) +static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req) { struct inet_request_sock *ireq = inet_rsk(req); struct ipv6_pinfo *np = inet6_sk(sk); @@ -234,7 +234,7 @@ static void dccp_v6_reqsk_destructor(struct request_sock *req) kfree_skb(inet_rsk(req)->pktopts); } -static void dccp_v6_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb) +static void dccp_v6_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb) { const struct ipv6hdr *rxip6h; struct sk_buff *skb; @@ -408,13 +408,14 @@ drop: return -1; } -static struct sock *dccp_v6_request_recv_sock(struct sock *sk, +static struct sock *dccp_v6_request_recv_sock(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst) { struct inet_request_sock *ireq = inet_rsk(req); - struct ipv6_pinfo *newnp, *np = inet6_sk(sk); + struct ipv6_pinfo *newnp; + const struct ipv6_pinfo *np = inet6_sk(sk); struct inet_sock *newinet; struct dccp6_sock *newdp6; struct sock *newsk; @@ -462,22 +463,11 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, if (sk_acceptq_is_full(sk)) goto out_overflow; - if (dst == NULL) { - struct in6_addr *final_p, final; + if (!dst) { struct flowi6 fl6; - memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_proto = IPPROTO_DCCP; - fl6.daddr = ireq->ir_v6_rmt_addr; - final_p = fl6_update_dst(&fl6, np->opt, &final); - fl6.saddr = ireq->ir_v6_loc_addr; - fl6.flowi6_oif = sk->sk_bound_dev_if; - fl6.fl6_dport = ireq->ir_rmt_port; - fl6.fl6_sport = htons(ireq->ir_num); - security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); - - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); - if (IS_ERR(dst)) + dst = inet6_csk_route_req(sk, &fl6, req, IPPROTO_DCCP); + if (!dst) goto out; } diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 838f524cf11a..d10aace43672 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -72,7 +72,7 @@ void dccp_time_wait(struct sock *sk, int state, int timeo) dccp_done(sk); } -struct sock *dccp_create_openreq_child(struct sock *sk, +struct sock *dccp_create_openreq_child(const struct sock *sk, const struct request_sock *req, const struct sk_buff *skb) { @@ -236,7 +236,7 @@ int dccp_child_process(struct sock *parent, struct sock *child, EXPORT_SYMBOL_GPL(dccp_child_process); -void dccp_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, +void dccp_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, struct request_sock *rsk) { DCCP_BUG("DCCP-ACK packets are never sent in LISTEN/RESPOND state"); diff --git a/net/dccp/output.c b/net/dccp/output.c index 0248e8a3460c..4ce912e691d0 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -390,7 +390,7 @@ int dccp_retransmit_skb(struct sock *sk) return dccp_transmit_skb(sk, skb_clone(sk->sk_send_head, GFP_ATOMIC)); } -struct sk_buff *dccp_make_response(struct sock *sk, struct dst_entry *dst, +struct sk_buff *dccp_make_response(const struct sock *sk, struct dst_entry *dst, struct request_sock *req) { struct dccp_hdr *dh; @@ -398,13 +398,18 @@ struct sk_buff *dccp_make_response(struct sock *sk, struct dst_entry *dst, const u32 dccp_header_size = sizeof(struct dccp_hdr) + sizeof(struct dccp_hdr_ext) + sizeof(struct dccp_hdr_response); - struct sk_buff *skb = sock_wmalloc(sk, sk->sk_prot->max_header, 1, - GFP_ATOMIC); - if (skb == NULL) + struct sk_buff *skb; + + /* sk is marked const to clearly express we dont hold socket lock. + * sock_wmalloc() will atomically change sk->sk_wmem_alloc, + * it is safe to promote sk to non const. + */ + skb = sock_wmalloc((struct sock *)sk, MAX_DCCP_HEADER, 1, + GFP_ATOMIC); + if (!skb) return NULL; - /* Reserve space for headers. */ - skb_reserve(skb, sk->sk_prot->max_header); + skb_reserve(skb, MAX_DCCP_HEADER); skb_dst_set(skb, dst_clone(dst)); diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c index 4507b188fc51..482730cd8a56 100644 --- a/net/decnet/dn_neigh.c +++ b/net/decnet/dn_neigh.c @@ -194,7 +194,7 @@ static int dn_neigh_output(struct neighbour *neigh, struct sk_buff *skb) return err; } -static int dn_neigh_output_packet(struct sock *sk, struct sk_buff *skb) +static int dn_neigh_output_packet(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct dn_route *rt = (struct dn_route *)dst; @@ -246,8 +246,9 @@ static int dn_long_output(struct neighbour *neigh, struct sock *sk, skb_reset_network_header(skb); - return NF_HOOK(NFPROTO_DECNET, NF_DN_POST_ROUTING, sk, skb, - NULL, neigh->dev, dn_neigh_output_packet); + return NF_HOOK(NFPROTO_DECNET, NF_DN_POST_ROUTING, + &init_net, sk, skb, NULL, neigh->dev, + dn_neigh_output_packet); } /* @@ -286,8 +287,9 @@ static int dn_short_output(struct neighbour *neigh, struct sock *sk, skb_reset_network_header(skb); - return NF_HOOK(NFPROTO_DECNET, NF_DN_POST_ROUTING, sk, skb, - NULL, neigh->dev, dn_neigh_output_packet); + return NF_HOOK(NFPROTO_DECNET, NF_DN_POST_ROUTING, + &init_net, sk, skb, NULL, neigh->dev, + dn_neigh_output_packet); } /* @@ -327,11 +329,12 @@ static int dn_phase3_output(struct neighbour *neigh, struct sock *sk, skb_reset_network_header(skb); - return NF_HOOK(NFPROTO_DECNET, NF_DN_POST_ROUTING, sk, skb, - NULL, neigh->dev, dn_neigh_output_packet); + return NF_HOOK(NFPROTO_DECNET, NF_DN_POST_ROUTING, + &init_net, sk, skb, NULL, neigh->dev, + dn_neigh_output_packet); } -int dn_to_neigh_output(struct sock *sk, struct sk_buff *skb) +int dn_to_neigh_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct dn_route *rt = (struct dn_route *) dst; @@ -375,7 +378,7 @@ void dn_neigh_pointopoint_hello(struct sk_buff *skb) /* * Ethernet router hello message received */ -int dn_neigh_router_hello(struct sock *sk, struct sk_buff *skb) +int dn_neigh_router_hello(struct net *net, struct sock *sk, struct sk_buff *skb) { struct rtnode_hello_message *msg = (struct rtnode_hello_message *)skb->data; @@ -437,7 +440,7 @@ int dn_neigh_router_hello(struct sock *sk, struct sk_buff *skb) /* * Endnode hello message received */ -int dn_neigh_endnode_hello(struct sock *sk, struct sk_buff *skb) +int dn_neigh_endnode_hello(struct net *net, struct sock *sk, struct sk_buff *skb) { struct endnode_hello_message *msg = (struct endnode_hello_message *)skb->data; struct neighbour *neigh; diff --git a/net/decnet/dn_nsp_in.c b/net/decnet/dn_nsp_in.c index a321eac9fd0c..7ac086d5c0c0 100644 --- a/net/decnet/dn_nsp_in.c +++ b/net/decnet/dn_nsp_in.c @@ -714,7 +714,8 @@ out: return ret; } -static int dn_nsp_rx_packet(struct sock *sk2, struct sk_buff *skb) +static int dn_nsp_rx_packet(struct net *net, struct sock *sk2, + struct sk_buff *skb) { struct dn_skb_cb *cb = DN_SKB_CB(skb); struct sock *sk = NULL; @@ -814,8 +815,8 @@ free_out: int dn_nsp_rx(struct sk_buff *skb) { - return NF_HOOK(NFPROTO_DECNET, NF_DN_LOCAL_IN, NULL, skb, - skb->dev, NULL, + return NF_HOOK(NFPROTO_DECNET, NF_DN_LOCAL_IN, + &init_net, NULL, skb, skb->dev, NULL, dn_nsp_rx_packet); } diff --git a/net/decnet/dn_nsp_out.c b/net/decnet/dn_nsp_out.c index 1aaa51ebbda6..4b02dd300f50 100644 --- a/net/decnet/dn_nsp_out.c +++ b/net/decnet/dn_nsp_out.c @@ -85,7 +85,7 @@ static void dn_nsp_send(struct sk_buff *skb) if (dst) { try_again: skb_dst_set(skb, dst); - dst_output(skb); + dst_output(skb->sk, skb); return; } @@ -582,7 +582,7 @@ static __inline__ void dn_nsp_do_disc(struct sock *sk, unsigned char msgflg, * associations. */ skb_dst_set(skb, dst_clone(dst)); - dst_output(skb); + dst_output(skb->sk, skb); } diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 03227ffd19ce..e930321e2c1d 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -512,7 +512,7 @@ static int dn_return_long(struct sk_buff *skb) * * Returns: result of input function if route is found, error code otherwise */ -static int dn_route_rx_packet(struct sock *sk, struct sk_buff *skb) +static int dn_route_rx_packet(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dn_skb_cb *cb; int err; @@ -573,8 +573,8 @@ static int dn_route_rx_long(struct sk_buff *skb) ptr++; cb->hops = *ptr++; /* Visit Count */ - return NF_HOOK(NFPROTO_DECNET, NF_DN_PRE_ROUTING, NULL, skb, - skb->dev, NULL, + return NF_HOOK(NFPROTO_DECNET, NF_DN_PRE_ROUTING, + &init_net, NULL, skb, skb->dev, NULL, dn_route_rx_packet); drop_it: @@ -601,8 +601,8 @@ static int dn_route_rx_short(struct sk_buff *skb) ptr += 2; cb->hops = *ptr & 0x3f; - return NF_HOOK(NFPROTO_DECNET, NF_DN_PRE_ROUTING, NULL, skb, - skb->dev, NULL, + return NF_HOOK(NFPROTO_DECNET, NF_DN_PRE_ROUTING, + &init_net, NULL, skb, skb->dev, NULL, dn_route_rx_packet); drop_it: @@ -610,7 +610,7 @@ drop_it: return NET_RX_DROP; } -static int dn_route_discard(struct sock *sk, struct sk_buff *skb) +static int dn_route_discard(struct net *net, struct sock *sk, struct sk_buff *skb) { /* * I know we drop the packet here, but thats considered success in @@ -620,7 +620,7 @@ static int dn_route_discard(struct sock *sk, struct sk_buff *skb) return NET_RX_SUCCESS; } -static int dn_route_ptp_hello(struct sock *sk, struct sk_buff *skb) +static int dn_route_ptp_hello(struct net *net, struct sock *sk, struct sk_buff *skb) { dn_dev_hello(skb); dn_neigh_pointopoint_hello(skb); @@ -706,22 +706,22 @@ int dn_route_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type switch (flags & DN_RT_CNTL_MSK) { case DN_RT_PKT_HELO: return NF_HOOK(NFPROTO_DECNET, NF_DN_HELLO, - NULL, skb, skb->dev, NULL, + &init_net, NULL, skb, skb->dev, NULL, dn_route_ptp_hello); case DN_RT_PKT_L1RT: case DN_RT_PKT_L2RT: return NF_HOOK(NFPROTO_DECNET, NF_DN_ROUTE, - NULL, skb, skb->dev, NULL, + &init_net, NULL, skb, skb->dev, NULL, dn_route_discard); case DN_RT_PKT_ERTH: return NF_HOOK(NFPROTO_DECNET, NF_DN_HELLO, - NULL, skb, skb->dev, NULL, + &init_net, NULL, skb, skb->dev, NULL, dn_neigh_router_hello); case DN_RT_PKT_EEDH: return NF_HOOK(NFPROTO_DECNET, NF_DN_HELLO, - NULL, skb, skb->dev, NULL, + &init_net, NULL, skb, skb->dev, NULL, dn_neigh_endnode_hello); } } else { @@ -770,8 +770,8 @@ static int dn_output(struct sock *sk, struct sk_buff *skb) cb->rt_flags |= DN_RT_F_IE; cb->hops = 0; - return NF_HOOK(NFPROTO_DECNET, NF_DN_LOCAL_OUT, sk, skb, - NULL, dev, + return NF_HOOK(NFPROTO_DECNET, NF_DN_LOCAL_OUT, + &init_net, sk, skb, NULL, dev, dn_to_neigh_output); error: @@ -819,8 +819,8 @@ static int dn_forward(struct sk_buff *skb) if (rt->rt_flags & RTCF_DOREDIRECT) cb->rt_flags |= DN_RT_F_IE; - return NF_HOOK(NFPROTO_DECNET, NF_DN_FORWARD, NULL, skb, - dev, skb->dev, + return NF_HOOK(NFPROTO_DECNET, NF_DN_FORWARD, + &init_net, NULL, skb, dev, skb->dev, dn_to_neigh_output); drop: diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c index af34fc9bdf69..85f2fdc360c2 100644 --- a/net/decnet/netfilter/dn_rtmsg.c +++ b/net/decnet/netfilter/dn_rtmsg.c @@ -87,7 +87,7 @@ static void dnrmg_send_peer(struct sk_buff *skb) } -static unsigned int dnrmg_hook(const struct nf_hook_ops *ops, +static unsigned int dnrmg_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 7d91f4612ac0..7b1d9ec74e09 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -242,16 +242,15 @@ static int dsa_bridge_check_vlan_range(struct dsa_switch *ds, } static int dsa_slave_port_vlan_add(struct net_device *dev, - struct switchdev_obj *obj) + const struct switchdev_obj_vlan *vlan, + struct switchdev_trans *trans) { - struct switchdev_obj_vlan *vlan = &obj->u.vlan; struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; u16 vid; int err; - switch (obj->trans) { - case SWITCHDEV_TRANS_PREPARE: + if (switchdev_trans_ph_prepare(trans)) { if (!ds->drv->port_vlan_add || !ds->drv->port_pvid_set) return -EOPNOTSUPP; @@ -263,8 +262,7 @@ static int dsa_slave_port_vlan_add(struct net_device *dev, vlan->vid_end); if (err) return err; - break; - case SWITCHDEV_TRANS_COMMIT: + } else { for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) { err = ds->drv->port_vlan_add(ds, p->port, vid, vlan->flags & @@ -274,18 +272,14 @@ static int dsa_slave_port_vlan_add(struct net_device *dev, if (err) return err; } - break; - default: - return -EOPNOTSUPP; } return 0; } static int dsa_slave_port_vlan_del(struct net_device *dev, - struct switchdev_obj *obj) + const struct switchdev_obj_vlan *vlan) { - struct switchdev_obj_vlan *vlan = &obj->u.vlan; struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; u16 vid; @@ -304,9 +298,9 @@ static int dsa_slave_port_vlan_del(struct net_device *dev, } static int dsa_slave_port_vlan_dump(struct net_device *dev, - struct switchdev_obj *obj) + struct switchdev_obj_vlan *vlan, + int (*cb)(void *obj)) { - struct switchdev_obj_vlan *vlan = &obj->u.vlan; struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; DECLARE_BITMAP(members, DSA_MAX_PORTS); @@ -338,7 +332,7 @@ static int dsa_slave_port_vlan_dump(struct net_device *dev, if (test_bit(p->port, untagged)) vlan->flags |= BRIDGE_VLAN_INFO_UNTAGGED; - err = obj->cb(dev, obj); + err = cb(vlan); if (err) break; } @@ -347,25 +341,24 @@ static int dsa_slave_port_vlan_dump(struct net_device *dev, } static int dsa_slave_port_fdb_add(struct net_device *dev, - struct switchdev_obj *obj) + const struct switchdev_obj_fdb *fdb, + struct switchdev_trans *trans) { - struct switchdev_obj_fdb *fdb = &obj->u.fdb; struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; int ret = -EOPNOTSUPP; - if (obj->trans == SWITCHDEV_TRANS_PREPARE) + if (switchdev_trans_ph_prepare(trans)) ret = ds->drv->port_fdb_add ? 0 : -EOPNOTSUPP; - else if (obj->trans == SWITCHDEV_TRANS_COMMIT) + else ret = ds->drv->port_fdb_add(ds, p->port, fdb->addr, fdb->vid); return ret; } static int dsa_slave_port_fdb_del(struct net_device *dev, - struct switchdev_obj *obj) + const struct switchdev_obj_fdb *fdb) { - struct switchdev_obj_fdb *fdb = &obj->u.fdb; struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; int ret = -EOPNOTSUPP; @@ -377,7 +370,8 @@ static int dsa_slave_port_fdb_del(struct net_device *dev, } static int dsa_slave_port_fdb_dump(struct net_device *dev, - struct switchdev_obj *obj) + struct switchdev_obj_fdb *fdb, + int (*cb)(void *obj)) { struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; @@ -396,11 +390,11 @@ static int dsa_slave_port_fdb_dump(struct net_device *dev, if (ret < 0) break; - obj->u.fdb.addr = addr; - obj->u.fdb.vid = vid; - obj->u.fdb.ndm_state = is_static ? NUD_NOARP : NUD_REACHABLE; + fdb->addr = addr; + fdb->vid = vid; + fdb->ndm_state = is_static ? NUD_NOARP : NUD_REACHABLE; - ret = obj->cb(dev, obj); + ret = cb(fdb); if (ret < 0) break; } @@ -456,7 +450,8 @@ static int dsa_slave_stp_update(struct net_device *dev, u8 state) } static int dsa_slave_port_attr_set(struct net_device *dev, - struct switchdev_attr *attr) + struct switchdev_attr *attr, + struct switchdev_trans *trans) { struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->parent; @@ -464,7 +459,7 @@ static int dsa_slave_port_attr_set(struct net_device *dev, switch (attr->id) { case SWITCHDEV_ATTR_PORT_STP_STATE: - if (attr->trans == SWITCHDEV_TRANS_PREPARE) + if (switchdev_trans_ph_prepare(trans)) ret = ds->drv->port_stp_update ? 0 : -EOPNOTSUPP; else ret = ds->drv->port_stp_update(ds, p->port, @@ -479,7 +474,8 @@ static int dsa_slave_port_attr_set(struct net_device *dev, } static int dsa_slave_port_obj_add(struct net_device *dev, - struct switchdev_obj *obj) + enum switchdev_obj_id id, const void *obj, + struct switchdev_trans *trans) { int err; @@ -488,12 +484,12 @@ static int dsa_slave_port_obj_add(struct net_device *dev, * supported, return -EOPNOTSUPP. */ - switch (obj->id) { + switch (id) { case SWITCHDEV_OBJ_PORT_FDB: - err = dsa_slave_port_fdb_add(dev, obj); + err = dsa_slave_port_fdb_add(dev, obj, trans); break; case SWITCHDEV_OBJ_PORT_VLAN: - err = dsa_slave_port_vlan_add(dev, obj); + err = dsa_slave_port_vlan_add(dev, obj, trans); break; default: err = -EOPNOTSUPP; @@ -504,11 +500,11 @@ static int dsa_slave_port_obj_add(struct net_device *dev, } static int dsa_slave_port_obj_del(struct net_device *dev, - struct switchdev_obj *obj) + enum switchdev_obj_id id, const void *obj) { int err; - switch (obj->id) { + switch (id) { case SWITCHDEV_OBJ_PORT_FDB: err = dsa_slave_port_fdb_del(dev, obj); break; @@ -524,16 +520,17 @@ static int dsa_slave_port_obj_del(struct net_device *dev, } static int dsa_slave_port_obj_dump(struct net_device *dev, - struct switchdev_obj *obj) + enum switchdev_obj_id id, void *obj, + int (*cb)(void *obj)) { int err; - switch (obj->id) { + switch (id) { case SWITCHDEV_OBJ_PORT_FDB: - err = dsa_slave_port_fdb_dump(dev, obj); + err = dsa_slave_port_fdb_dump(dev, obj, cb); break; case SWITCHDEV_OBJ_PORT_VLAN: - err = dsa_slave_port_vlan_dump(dev, obj); + err = dsa_slave_port_vlan_dump(dev, obj, cb); break; default: err = -EOPNOTSUPP; @@ -967,6 +964,10 @@ static const struct switchdev_ops dsa_slave_switchdev_ops = { .switchdev_port_obj_dump = dsa_slave_port_obj_dump, }; +static struct device_type dsa_type = { + .name = "dsa", +}; + static void dsa_slave_adjust_link(struct net_device *dev) { struct dsa_slave_priv *p = netdev_priv(dev); @@ -1155,6 +1156,7 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent, slave_dev->priv_flags |= IFF_NO_QUEUE; slave_dev->netdev_ops = &dsa_slave_netdev_ops; slave_dev->switchdev_ops = &dsa_slave_switchdev_ops; + SET_NETDEV_DEVTYPE(slave_dev, &dsa_type); netdev_for_each_tx_queue(slave_dev, dsa_slave_set_lockdep_class_one, NULL); diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index d850fdc828f9..9e63f252a89e 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -127,7 +127,7 @@ u32 eth_get_headlen(void *data, unsigned int len) struct flow_keys keys; /* this should never happen, but better safe than sorry */ - if (len < sizeof(*eth)) + if (unlikely(len < sizeof(*eth))) return len; /* parse any remaining L2/L3 headers, check for L4 */ diff --git a/net/ieee802154/6lowpan/6lowpan_i.h b/net/ieee802154/6lowpan/6lowpan_i.h index ea339fa94c27..b4e17a7c0df0 100644 --- a/net/ieee802154/6lowpan/6lowpan_i.h +++ b/net/ieee802154/6lowpan/6lowpan_i.h @@ -7,6 +7,15 @@ #include <net/inet_frag.h> #include <net/6lowpan.h> +typedef unsigned __bitwise__ lowpan_rx_result; +#define RX_CONTINUE ((__force lowpan_rx_result) 0u) +#define RX_DROP_UNUSABLE ((__force lowpan_rx_result) 1u) +#define RX_DROP ((__force lowpan_rx_result) 2u) +#define RX_QUEUED ((__force lowpan_rx_result) 3u) + +#define LOWPAN_DISPATCH_FRAG1 0xc0 +#define LOWPAN_DISPATCH_FRAGN 0xe0 + struct lowpan_create_arg { u16 tag; u16 d_size; @@ -40,7 +49,7 @@ static inline u32 ieee802154_addr_hash(const struct ieee802154_addr *a) /* private device info */ struct lowpan_dev_info { - struct net_device *real_dev; /* real WPAN device ptr */ + struct net_device *wdev; /* wpan device ptr */ u16 fragment_tag; }; @@ -62,4 +71,7 @@ int lowpan_header_create(struct sk_buff *skb, struct net_device *dev, const void *_saddr, unsigned int len); netdev_tx_t lowpan_xmit(struct sk_buff *skb, struct net_device *dev); +int lowpan_iphc_decompress(struct sk_buff *skb); +lowpan_rx_result lowpan_rx_h_ipv6(struct sk_buff *skb); + #endif /* __IEEE802154_6LOWPAN_I_H__ */ diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c index 953b1c49f5d1..9f0cfa598e3a 100644 --- a/net/ieee802154/6lowpan/core.c +++ b/net/ieee802154/6lowpan/core.c @@ -61,7 +61,7 @@ static struct header_ops lowpan_header_ops = { static struct lock_class_key lowpan_tx_busylock; static struct lock_class_key lowpan_netdev_xmit_lock_key; -static void lowpan_set_lockdep_class_one(struct net_device *dev, +static void lowpan_set_lockdep_class_one(struct net_device *ldev, struct netdev_queue *txq, void *_unused) { @@ -69,35 +69,52 @@ static void lowpan_set_lockdep_class_one(struct net_device *dev, &lowpan_netdev_xmit_lock_key); } -static int lowpan_dev_init(struct net_device *dev) +static int lowpan_dev_init(struct net_device *ldev) { - netdev_for_each_tx_queue(dev, lowpan_set_lockdep_class_one, NULL); - dev->qdisc_tx_busylock = &lowpan_tx_busylock; + netdev_for_each_tx_queue(ldev, lowpan_set_lockdep_class_one, NULL); + ldev->qdisc_tx_busylock = &lowpan_tx_busylock; + return 0; +} + +static int lowpan_open(struct net_device *dev) +{ + if (!open_count) + lowpan_rx_init(); + open_count++; + return 0; +} + +static int lowpan_stop(struct net_device *dev) +{ + open_count--; + if (!open_count) + lowpan_rx_exit(); return 0; } static const struct net_device_ops lowpan_netdev_ops = { .ndo_init = lowpan_dev_init, .ndo_start_xmit = lowpan_xmit, + .ndo_open = lowpan_open, + .ndo_stop = lowpan_stop, }; -static void lowpan_setup(struct net_device *dev) +static void lowpan_setup(struct net_device *ldev) { - dev->addr_len = IEEE802154_ADDR_LEN; - memset(dev->broadcast, 0xff, IEEE802154_ADDR_LEN); - dev->type = ARPHRD_6LOWPAN; + ldev->addr_len = IEEE802154_ADDR_LEN; + memset(ldev->broadcast, 0xff, IEEE802154_ADDR_LEN); + ldev->type = ARPHRD_6LOWPAN; /* Frame Control + Sequence Number + Address fields + Security Header */ - dev->hard_header_len = 2 + 1 + 20 + 14; - dev->needed_tailroom = 2; /* FCS */ - dev->mtu = IPV6_MIN_MTU; - dev->priv_flags |= IFF_NO_QUEUE; - dev->flags = IFF_BROADCAST | IFF_MULTICAST; - dev->watchdog_timeo = 0; - - dev->netdev_ops = &lowpan_netdev_ops; - dev->header_ops = &lowpan_header_ops; - dev->destructor = free_netdev; - dev->features |= NETIF_F_NETNS_LOCAL; + ldev->hard_header_len = 2 + 1 + 20 + 14; + ldev->needed_tailroom = 2; /* FCS */ + ldev->mtu = IPV6_MIN_MTU; + ldev->priv_flags |= IFF_NO_QUEUE; + ldev->flags = IFF_BROADCAST | IFF_MULTICAST; + + ldev->netdev_ops = &lowpan_netdev_ops; + ldev->header_ops = &lowpan_header_ops; + ldev->destructor = free_netdev; + ldev->features |= NETIF_F_NETNS_LOCAL; } static int lowpan_validate(struct nlattr *tb[], struct nlattr *data[]) @@ -109,10 +126,10 @@ static int lowpan_validate(struct nlattr *tb[], struct nlattr *data[]) return 0; } -static int lowpan_newlink(struct net *src_net, struct net_device *dev, +static int lowpan_newlink(struct net *src_net, struct net_device *ldev, struct nlattr *tb[], struct nlattr *data[]) { - struct net_device *real_dev; + struct net_device *wdev; int ret; ASSERT_RTNL(); @@ -120,58 +137,47 @@ static int lowpan_newlink(struct net *src_net, struct net_device *dev, pr_debug("adding new link\n"); if (!tb[IFLA_LINK] || - !net_eq(dev_net(dev), &init_net)) + !net_eq(dev_net(ldev), &init_net)) return -EINVAL; - /* find and hold real wpan device */ - real_dev = dev_get_by_index(dev_net(dev), nla_get_u32(tb[IFLA_LINK])); - if (!real_dev) + /* find and hold wpan device */ + wdev = dev_get_by_index(dev_net(ldev), nla_get_u32(tb[IFLA_LINK])); + if (!wdev) return -ENODEV; - if (real_dev->type != ARPHRD_IEEE802154) { - dev_put(real_dev); + if (wdev->type != ARPHRD_IEEE802154) { + dev_put(wdev); return -EINVAL; } - if (real_dev->ieee802154_ptr->lowpan_dev) { - dev_put(real_dev); + if (wdev->ieee802154_ptr->lowpan_dev) { + dev_put(wdev); return -EBUSY; } - lowpan_dev_info(dev)->real_dev = real_dev; + lowpan_dev_info(ldev)->wdev = wdev; /* Set the lowpan hardware address to the wpan hardware address. */ - memcpy(dev->dev_addr, real_dev->dev_addr, IEEE802154_ADDR_LEN); + memcpy(ldev->dev_addr, wdev->dev_addr, IEEE802154_ADDR_LEN); - lowpan_netdev_setup(dev, LOWPAN_LLTYPE_IEEE802154); + lowpan_netdev_setup(ldev, LOWPAN_LLTYPE_IEEE802154); - ret = register_netdevice(dev); + ret = register_netdevice(ldev); if (ret < 0) { - dev_put(real_dev); + dev_put(wdev); return ret; } - real_dev->ieee802154_ptr->lowpan_dev = dev; - if (!open_count) - lowpan_rx_init(); - - open_count++; - + wdev->ieee802154_ptr->lowpan_dev = ldev; return 0; } -static void lowpan_dellink(struct net_device *dev, struct list_head *head) +static void lowpan_dellink(struct net_device *ldev, struct list_head *head) { - struct lowpan_dev_info *lowpan_dev = lowpan_dev_info(dev); - struct net_device *real_dev = lowpan_dev->real_dev; + struct net_device *wdev = lowpan_dev_info(ldev)->wdev; ASSERT_RTNL(); - open_count--; - - if (!open_count) - lowpan_rx_exit(); - - real_dev->ieee802154_ptr->lowpan_dev = NULL; - unregister_netdevice(dev); - dev_put(real_dev); + wdev->ieee802154_ptr->lowpan_dev = NULL; + unregister_netdevice(ldev); + dev_put(wdev); } static struct rtnl_link_ops lowpan_link_ops __read_mostly = { @@ -196,9 +202,9 @@ static inline void lowpan_netlink_fini(void) static int lowpan_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { - struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct net_device *wdev = netdev_notifier_info_to_dev(ptr); - if (dev->type != ARPHRD_IEEE802154) + if (wdev->type != ARPHRD_IEEE802154) goto out; switch (event) { @@ -207,8 +213,8 @@ static int lowpan_device_event(struct notifier_block *unused, * also delete possible lowpan interfaces which belongs * to the wpan interface. */ - if (dev->ieee802154_ptr && dev->ieee802154_ptr->lowpan_dev) - lowpan_dellink(dev->ieee802154_ptr->lowpan_dev, NULL); + if (wdev->ieee802154_ptr->lowpan_dev) + lowpan_dellink(wdev->ieee802154_ptr->lowpan_dev, NULL); break; default: break; diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c index 214d44aef35b..12e8cf4bda9f 100644 --- a/net/ieee802154/6lowpan/reassembly.c +++ b/net/ieee802154/6lowpan/reassembly.c @@ -32,21 +32,10 @@ static const char lowpan_frags_cache_name[] = "lowpan-frags"; -struct lowpan_frag_info { - u16 d_tag; - u16 d_size; - u8 d_offset; -}; - -static struct lowpan_frag_info *lowpan_cb(struct sk_buff *skb) -{ - return (struct lowpan_frag_info *)skb->cb; -} - static struct inet_frags lowpan_frags; static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, - struct sk_buff *prev, struct net_device *dev); + struct sk_buff *prev, struct net_device *ldev); static unsigned int lowpan_hash_frag(u16 tag, u16 d_size, const struct ieee802154_addr *saddr, @@ -111,7 +100,7 @@ out: } static inline struct lowpan_frag_queue * -fq_find(struct net *net, const struct lowpan_frag_info *frag_info, +fq_find(struct net *net, const struct lowpan_802154_cb *cb, const struct ieee802154_addr *src, const struct ieee802154_addr *dst) { @@ -121,12 +110,12 @@ fq_find(struct net *net, const struct lowpan_frag_info *frag_info, struct netns_ieee802154_lowpan *ieee802154_lowpan = net_ieee802154_lowpan(net); - arg.tag = frag_info->d_tag; - arg.d_size = frag_info->d_size; + arg.tag = cb->d_tag; + arg.d_size = cb->d_size; arg.src = src; arg.dst = dst; - hash = lowpan_hash_frag(frag_info->d_tag, frag_info->d_size, src, dst); + hash = lowpan_hash_frag(cb->d_tag, cb->d_size, src, dst); q = inet_frag_find(&ieee802154_lowpan->frags, &lowpan_frags, &arg, hash); @@ -138,17 +127,17 @@ fq_find(struct net *net, const struct lowpan_frag_info *frag_info, } static int lowpan_frag_queue(struct lowpan_frag_queue *fq, - struct sk_buff *skb, const u8 frag_type) + struct sk_buff *skb, u8 frag_type) { struct sk_buff *prev, *next; - struct net_device *dev; + struct net_device *ldev; int end, offset; if (fq->q.flags & INET_FRAG_COMPLETE) goto err; - offset = lowpan_cb(skb)->d_offset << 3; - end = lowpan_cb(skb)->d_size; + offset = lowpan_802154_cb(skb)->d_offset << 3; + end = lowpan_802154_cb(skb)->d_size; /* Is this the final fragment? */ if (offset + skb->len == end) { @@ -174,13 +163,16 @@ static int lowpan_frag_queue(struct lowpan_frag_queue *fq, * this fragment, right? */ prev = fq->q.fragments_tail; - if (!prev || lowpan_cb(prev)->d_offset < lowpan_cb(skb)->d_offset) { + if (!prev || + lowpan_802154_cb(prev)->d_offset < + lowpan_802154_cb(skb)->d_offset) { next = NULL; goto found; } prev = NULL; for (next = fq->q.fragments; next != NULL; next = next->next) { - if (lowpan_cb(next)->d_offset >= lowpan_cb(skb)->d_offset) + if (lowpan_802154_cb(next)->d_offset >= + lowpan_802154_cb(skb)->d_offset) break; /* bingo! */ prev = next; } @@ -195,18 +187,15 @@ found: else fq->q.fragments = skb; - dev = skb->dev; - if (dev) + ldev = skb->dev; + if (ldev) skb->dev = NULL; fq->q.stamp = skb->tstamp; - if (frag_type == LOWPAN_DISPATCH_FRAG1) { - /* Calculate uncomp. 6lowpan header to estimate full size */ - fq->q.meat += lowpan_uncompress_size(skb, NULL); + if (frag_type == LOWPAN_DISPATCH_FRAG1) fq->q.flags |= INET_FRAG_FIRST_IN; - } else { - fq->q.meat += skb->len; - } + + fq->q.meat += skb->len; add_frag_mem_limit(fq->q.net, skb->truesize); if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && @@ -215,7 +204,7 @@ found: unsigned long orefdst = skb->_skb_refdst; skb->_skb_refdst = 0UL; - res = lowpan_frag_reasm(fq, prev, dev); + res = lowpan_frag_reasm(fq, prev, ldev); skb->_skb_refdst = orefdst; return res; } @@ -235,7 +224,7 @@ err: * the last and the first frames arrived and all the bits are here. */ static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *prev, - struct net_device *dev) + struct net_device *ldev) { struct sk_buff *fp, *head = fq->q.fragments; int sum_truesize; @@ -313,7 +302,7 @@ static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *prev, sub_frag_mem_limit(fq->q.net, sum_truesize); head->next = NULL; - head->dev = dev; + head->dev = ldev; head->tstamp = fq->q.stamp; fq->q.fragments = NULL; @@ -325,24 +314,87 @@ out_oom: return -1; } -static int lowpan_get_frag_info(struct sk_buff *skb, const u8 frag_type, - struct lowpan_frag_info *frag_info) +static int lowpan_frag_rx_handlers_result(struct sk_buff *skb, + lowpan_rx_result res) +{ + switch (res) { + case RX_QUEUED: + return NET_RX_SUCCESS; + case RX_CONTINUE: + /* nobody cared about this packet */ + net_warn_ratelimited("%s: received unknown dispatch\n", + __func__); + + /* fall-through */ + default: + /* all others failure */ + return NET_RX_DROP; + } +} + +static lowpan_rx_result lowpan_frag_rx_h_iphc(struct sk_buff *skb) +{ + int ret; + + if (!lowpan_is_iphc(*skb_network_header(skb))) + return RX_CONTINUE; + + ret = lowpan_iphc_decompress(skb); + if (ret < 0) + return RX_DROP; + + return RX_QUEUED; +} + +static int lowpan_invoke_frag_rx_handlers(struct sk_buff *skb) +{ + lowpan_rx_result res; + +#define CALL_RXH(rxh) \ + do { \ + res = rxh(skb); \ + if (res != RX_CONTINUE) \ + goto rxh_next; \ + } while (0) + + /* likely at first */ + CALL_RXH(lowpan_frag_rx_h_iphc); + CALL_RXH(lowpan_rx_h_ipv6); + +rxh_next: + return lowpan_frag_rx_handlers_result(skb, res); +#undef CALL_RXH +} + +#define LOWPAN_FRAG_DGRAM_SIZE_HIGH_MASK 0x07 +#define LOWPAN_FRAG_DGRAM_SIZE_HIGH_SHIFT 8 + +static int lowpan_get_cb(struct sk_buff *skb, u8 frag_type, + struct lowpan_802154_cb *cb) { bool fail; - u8 pattern = 0, low = 0; + u8 high = 0, low = 0; __be16 d_tag = 0; - fail = lowpan_fetch_skb(skb, &pattern, 1); + fail = lowpan_fetch_skb(skb, &high, 1); fail |= lowpan_fetch_skb(skb, &low, 1); - frag_info->d_size = (pattern & 7) << 8 | low; + /* remove the dispatch value and use first three bits as high value + * for the datagram size + */ + cb->d_size = (high & LOWPAN_FRAG_DGRAM_SIZE_HIGH_MASK) << + LOWPAN_FRAG_DGRAM_SIZE_HIGH_SHIFT | low; fail |= lowpan_fetch_skb(skb, &d_tag, 2); - frag_info->d_tag = ntohs(d_tag); + cb->d_tag = ntohs(d_tag); if (frag_type == LOWPAN_DISPATCH_FRAGN) { - fail |= lowpan_fetch_skb(skb, &frag_info->d_offset, 1); + fail |= lowpan_fetch_skb(skb, &cb->d_offset, 1); } else { skb_reset_network_header(skb); - frag_info->d_offset = 0; + cb->d_offset = 0; + /* check if datagram_size has ipv6hdr on FRAG1 */ + fail |= cb->d_size < sizeof(struct ipv6hdr); + /* check if we can dereference the dispatch value */ + fail |= !skb->len; } if (unlikely(fail)) @@ -351,27 +403,33 @@ static int lowpan_get_frag_info(struct sk_buff *skb, const u8 frag_type, return 0; } -int lowpan_frag_rcv(struct sk_buff *skb, const u8 frag_type) +int lowpan_frag_rcv(struct sk_buff *skb, u8 frag_type) { struct lowpan_frag_queue *fq; struct net *net = dev_net(skb->dev); - struct lowpan_frag_info *frag_info = lowpan_cb(skb); - struct ieee802154_addr source, dest; + struct lowpan_802154_cb *cb = lowpan_802154_cb(skb); + struct ieee802154_hdr hdr; int err; - source = mac_cb(skb)->source; - dest = mac_cb(skb)->dest; + if (ieee802154_hdr_peek_addrs(skb, &hdr) < 0) + goto err; - err = lowpan_get_frag_info(skb, frag_type, frag_info); + err = lowpan_get_cb(skb, frag_type, cb); if (err < 0) goto err; - if (frag_info->d_size > IPV6_MIN_MTU) { + if (frag_type == LOWPAN_DISPATCH_FRAG1) { + err = lowpan_invoke_frag_rx_handlers(skb); + if (err == NET_RX_DROP) + goto err; + } + + if (cb->d_size > IPV6_MIN_MTU) { net_warn_ratelimited("lowpan_frag_rcv: datagram size exceeds MTU\n"); goto err; } - fq = fq_find(net, frag_info, &source, &dest); + fq = fq_find(net, cb, &hdr.source, &hdr.dest); if (fq != NULL) { int ret; @@ -387,7 +445,6 @@ err: kfree_skb(skb); return -1; } -EXPORT_SYMBOL(lowpan_frag_rcv); #ifdef CONFIG_SYSCTL static int zero; diff --git a/net/ieee802154/6lowpan/rx.c b/net/ieee802154/6lowpan/rx.c index 12e10201d263..b1fd47d2802b 100644 --- a/net/ieee802154/6lowpan/rx.c +++ b/net/ieee802154/6lowpan/rx.c @@ -11,40 +11,99 @@ #include <linux/if_arp.h> #include <net/6lowpan.h> +#include <net/mac802154.h> #include <net/ieee802154_netdev.h> #include "6lowpan_i.h" -static int lowpan_give_skb_to_device(struct sk_buff *skb, - struct net_device *dev) +#define LOWPAN_DISPATCH_FIRST 0xc0 +#define LOWPAN_DISPATCH_FRAG_MASK 0xf8 + +#define LOWPAN_DISPATCH_NALP 0x00 +#define LOWPAN_DISPATCH_ESC 0x40 +#define LOWPAN_DISPATCH_HC1 0x42 +#define LOWPAN_DISPATCH_DFF 0x43 +#define LOWPAN_DISPATCH_BC0 0x50 +#define LOWPAN_DISPATCH_MESH 0x80 + +static int lowpan_give_skb_to_device(struct sk_buff *skb) { - skb->dev = dev->ieee802154_ptr->lowpan_dev; skb->protocol = htons(ETH_P_IPV6); - skb->pkt_type = PACKET_HOST; return netif_rx(skb); } -static int -iphc_decompress(struct sk_buff *skb, const struct ieee802154_hdr *hdr) +static int lowpan_rx_handlers_result(struct sk_buff *skb, lowpan_rx_result res) +{ + switch (res) { + case RX_CONTINUE: + /* nobody cared about this packet */ + net_warn_ratelimited("%s: received unknown dispatch\n", + __func__); + + /* fall-through */ + case RX_DROP_UNUSABLE: + kfree_skb(skb); + + /* fall-through */ + case RX_DROP: + return NET_RX_DROP; + case RX_QUEUED: + return lowpan_give_skb_to_device(skb); + default: + break; + } + + return NET_RX_DROP; +} + +static inline bool lowpan_is_frag1(u8 dispatch) +{ + return (dispatch & LOWPAN_DISPATCH_FRAG_MASK) == LOWPAN_DISPATCH_FRAG1; +} + +static inline bool lowpan_is_fragn(u8 dispatch) +{ + return (dispatch & LOWPAN_DISPATCH_FRAG_MASK) == LOWPAN_DISPATCH_FRAGN; +} + +static lowpan_rx_result lowpan_rx_h_frag(struct sk_buff *skb) +{ + int ret; + + if (!(lowpan_is_frag1(*skb_network_header(skb)) || + lowpan_is_fragn(*skb_network_header(skb)))) + return RX_CONTINUE; + + ret = lowpan_frag_rcv(skb, *skb_network_header(skb) & + LOWPAN_DISPATCH_FRAG_MASK); + if (ret == 1) + return RX_QUEUED; + + /* Packet is freed by lowpan_frag_rcv on error or put into the frag + * bucket. + */ + return RX_DROP; +} + +int lowpan_iphc_decompress(struct sk_buff *skb) { - u8 iphc0, iphc1; struct ieee802154_addr_sa sa, da; + struct ieee802154_hdr hdr; + u8 iphc0, iphc1; void *sap, *dap; - raw_dump_table(__func__, "raw skb data dump", skb->data, skb->len); - /* at least two bytes will be used for the encoding */ - if (skb->len < 2) + if (ieee802154_hdr_peek_addrs(skb, &hdr) < 0) return -EINVAL; - if (lowpan_fetch_skb_u8(skb, &iphc0)) - return -EINVAL; + raw_dump_table(__func__, "raw skb data dump", skb->data, skb->len); - if (lowpan_fetch_skb_u8(skb, &iphc1)) + if (lowpan_fetch_skb_u8(skb, &iphc0) || + lowpan_fetch_skb_u8(skb, &iphc1)) return -EINVAL; - ieee802154_addr_to_sa(&sa, &hdr->source); - ieee802154_addr_to_sa(&da, &hdr->dest); + ieee802154_addr_to_sa(&sa, &hdr.source); + ieee802154_addr_to_sa(&da, &hdr.dest); if (sa.addr_type == IEEE802154_ADDR_SHORT) sap = &sa.short_addr; @@ -61,77 +120,216 @@ iphc_decompress(struct sk_buff *skb, const struct ieee802154_hdr *hdr) IEEE802154_ADDR_LEN, iphc0, iphc1); } -static int lowpan_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt, struct net_device *orig_dev) +static lowpan_rx_result lowpan_rx_h_iphc(struct sk_buff *skb) { - struct ieee802154_hdr hdr; int ret; - if (dev->type != ARPHRD_IEEE802154 || - !dev->ieee802154_ptr->lowpan_dev) - goto drop; + if (!lowpan_is_iphc(*skb_network_header(skb))) + return RX_CONTINUE; - skb = skb_share_check(skb, GFP_ATOMIC); - if (!skb) - goto drop; + /* Setting datagram_offset to zero indicates non frag handling + * while doing lowpan_header_decompress. + */ + lowpan_802154_cb(skb)->d_size = 0; - if (!netif_running(dev)) - goto drop_skb; + ret = lowpan_iphc_decompress(skb); + if (ret < 0) + return RX_DROP_UNUSABLE; - if (skb->pkt_type == PACKET_OTHERHOST) - goto drop_skb; + return RX_QUEUED; +} - if (ieee802154_hdr_peek_addrs(skb, &hdr) < 0) - goto drop_skb; - - /* check that it's our buffer */ - if (skb->data[0] == LOWPAN_DISPATCH_IPV6) { - /* Pull off the 1-byte of 6lowpan header. */ - skb_pull(skb, 1); - return lowpan_give_skb_to_device(skb, dev); - } else { - switch (skb->data[0] & 0xe0) { - case LOWPAN_DISPATCH_IPHC: /* ipv6 datagram */ - ret = iphc_decompress(skb, &hdr); - if (ret < 0) - goto drop_skb; - - return lowpan_give_skb_to_device(skb, dev); - case LOWPAN_DISPATCH_FRAG1: /* first fragment header */ - ret = lowpan_frag_rcv(skb, LOWPAN_DISPATCH_FRAG1); - if (ret == 1) { - ret = iphc_decompress(skb, &hdr); - if (ret < 0) - goto drop_skb; - - return lowpan_give_skb_to_device(skb, dev); - } else if (ret == -1) { - return NET_RX_DROP; - } else { - return NET_RX_SUCCESS; - } - case LOWPAN_DISPATCH_FRAGN: /* next fragments headers */ - ret = lowpan_frag_rcv(skb, LOWPAN_DISPATCH_FRAGN); - if (ret == 1) { - ret = iphc_decompress(skb, &hdr); - if (ret < 0) - goto drop_skb; - - return lowpan_give_skb_to_device(skb, dev); - } else if (ret == -1) { - return NET_RX_DROP; - } else { - return NET_RX_SUCCESS; - } - default: - break; - } +lowpan_rx_result lowpan_rx_h_ipv6(struct sk_buff *skb) +{ + if (!lowpan_is_ipv6(*skb_network_header(skb))) + return RX_CONTINUE; + + /* Pull off the 1-byte of 6lowpan header. */ + skb_pull(skb, 1); + return RX_QUEUED; +} + +static inline bool lowpan_is_esc(u8 dispatch) +{ + return dispatch == LOWPAN_DISPATCH_ESC; +} + +static lowpan_rx_result lowpan_rx_h_esc(struct sk_buff *skb) +{ + if (!lowpan_is_esc(*skb_network_header(skb))) + return RX_CONTINUE; + + net_warn_ratelimited("%s: %s\n", skb->dev->name, + "6LoWPAN ESC not supported\n"); + + return RX_DROP_UNUSABLE; +} + +static inline bool lowpan_is_hc1(u8 dispatch) +{ + return dispatch == LOWPAN_DISPATCH_HC1; +} + +static lowpan_rx_result lowpan_rx_h_hc1(struct sk_buff *skb) +{ + if (!lowpan_is_hc1(*skb_network_header(skb))) + return RX_CONTINUE; + + net_warn_ratelimited("%s: %s\n", skb->dev->name, + "6LoWPAN HC1 not supported\n"); + + return RX_DROP_UNUSABLE; +} + +static inline bool lowpan_is_dff(u8 dispatch) +{ + return dispatch == LOWPAN_DISPATCH_DFF; +} + +static lowpan_rx_result lowpan_rx_h_dff(struct sk_buff *skb) +{ + if (!lowpan_is_dff(*skb_network_header(skb))) + return RX_CONTINUE; + + net_warn_ratelimited("%s: %s\n", skb->dev->name, + "6LoWPAN DFF not supported\n"); + + return RX_DROP_UNUSABLE; +} + +static inline bool lowpan_is_bc0(u8 dispatch) +{ + return dispatch == LOWPAN_DISPATCH_BC0; +} + +static lowpan_rx_result lowpan_rx_h_bc0(struct sk_buff *skb) +{ + if (!lowpan_is_bc0(*skb_network_header(skb))) + return RX_CONTINUE; + + net_warn_ratelimited("%s: %s\n", skb->dev->name, + "6LoWPAN BC0 not supported\n"); + + return RX_DROP_UNUSABLE; +} + +static inline bool lowpan_is_mesh(u8 dispatch) +{ + return (dispatch & LOWPAN_DISPATCH_FIRST) == LOWPAN_DISPATCH_MESH; +} + +static lowpan_rx_result lowpan_rx_h_mesh(struct sk_buff *skb) +{ + if (!lowpan_is_mesh(*skb_network_header(skb))) + return RX_CONTINUE; + + net_warn_ratelimited("%s: %s\n", skb->dev->name, + "6LoWPAN MESH not supported\n"); + + return RX_DROP_UNUSABLE; +} + +static int lowpan_invoke_rx_handlers(struct sk_buff *skb) +{ + lowpan_rx_result res; + +#define CALL_RXH(rxh) \ + do { \ + res = rxh(skb); \ + if (res != RX_CONTINUE) \ + goto rxh_next; \ + } while (0) + + /* likely at first */ + CALL_RXH(lowpan_rx_h_iphc); + CALL_RXH(lowpan_rx_h_frag); + CALL_RXH(lowpan_rx_h_ipv6); + CALL_RXH(lowpan_rx_h_esc); + CALL_RXH(lowpan_rx_h_hc1); + CALL_RXH(lowpan_rx_h_dff); + CALL_RXH(lowpan_rx_h_bc0); + CALL_RXH(lowpan_rx_h_mesh); + +rxh_next: + return lowpan_rx_handlers_result(skb, res); +#undef CALL_RXH +} + +static inline bool lowpan_is_nalp(u8 dispatch) +{ + return (dispatch & LOWPAN_DISPATCH_FIRST) == LOWPAN_DISPATCH_NALP; +} + +/* Lookup for reserved dispatch values at: + * https://www.iana.org/assignments/_6lowpan-parameters/_6lowpan-parameters.xhtml#_6lowpan-parameters-1 + * + * Last Updated: 2015-01-22 + */ +static inline bool lowpan_is_reserved(u8 dispatch) +{ + return ((dispatch >= 0x44 && dispatch <= 0x4F) || + (dispatch >= 0x51 && dispatch <= 0x5F) || + (dispatch >= 0xc8 && dispatch <= 0xdf) || + (dispatch >= 0xe8 && dispatch <= 0xff)); +} + +/* lowpan_rx_h_check checks on generic 6LoWPAN requirements + * in MAC and 6LoWPAN header. + * + * Don't manipulate the skb here, it could be shared buffer. + */ +static inline bool lowpan_rx_h_check(struct sk_buff *skb) +{ + __le16 fc = ieee802154_get_fc_from_skb(skb); + + /* check on ieee802154 conform 6LoWPAN header */ + if (!ieee802154_is_data(fc) || + !ieee802154_is_intra_pan(fc)) + return false; + + /* check if we can dereference the dispatch */ + if (unlikely(!skb->len)) + return false; + + if (lowpan_is_nalp(*skb_network_header(skb)) || + lowpan_is_reserved(*skb_network_header(skb))) + return false; + + return true; +} + +static int lowpan_rcv(struct sk_buff *skb, struct net_device *wdev, + struct packet_type *pt, struct net_device *orig_wdev) +{ + struct net_device *ldev; + + if (wdev->type != ARPHRD_IEEE802154 || + skb->pkt_type == PACKET_OTHERHOST || + !lowpan_rx_h_check(skb)) + return NET_RX_DROP; + + ldev = wdev->ieee802154_ptr->lowpan_dev; + if (!ldev || !netif_running(ldev)) + return NET_RX_DROP; + + /* Replacing skb->dev and followed rx handlers will manipulate skb. */ + skb = skb_share_check(skb, GFP_ATOMIC); + if (!skb) + return NET_RX_DROP; + skb->dev = ldev; + + /* When receive frag1 it's likely that we manipulate the buffer. + * When recevie iphc we manipulate the data buffer. So we need + * to unshare the buffer. + */ + if (lowpan_is_frag1(*skb_network_header(skb)) || + lowpan_is_iphc(*skb_network_header(skb))) { + skb = skb_unshare(skb, GFP_ATOMIC); + if (!skb) + return NET_RX_DROP; } -drop_skb: - kfree_skb(skb); -drop: - return NET_RX_DROP; + return lowpan_invoke_rx_handlers(skb); } static struct packet_type lowpan_packet_type = { diff --git a/net/ieee802154/6lowpan/tx.c b/net/ieee802154/6lowpan/tx.c index f6263fc12340..54939d031ea5 100644 --- a/net/ieee802154/6lowpan/tx.c +++ b/net/ieee802154/6lowpan/tx.c @@ -36,7 +36,7 @@ lowpan_addr_info *lowpan_skb_priv(const struct sk_buff *skb) sizeof(struct lowpan_addr_info)); } -int lowpan_header_create(struct sk_buff *skb, struct net_device *dev, +int lowpan_header_create(struct sk_buff *skb, struct net_device *ldev, unsigned short type, const void *_daddr, const void *_saddr, unsigned int len) { @@ -51,7 +51,7 @@ int lowpan_header_create(struct sk_buff *skb, struct net_device *dev, return 0; if (!saddr) - saddr = dev->dev_addr; + saddr = ldev->dev_addr; raw_dump_inline(__func__, "saddr", (unsigned char *)saddr, 8); raw_dump_inline(__func__, "daddr", (unsigned char *)daddr, 8); @@ -73,22 +73,21 @@ static struct sk_buff* lowpan_alloc_frag(struct sk_buff *skb, int size, const struct ieee802154_hdr *master_hdr) { - struct net_device *real_dev = lowpan_dev_info(skb->dev)->real_dev; + struct net_device *wdev = lowpan_dev_info(skb->dev)->wdev; struct sk_buff *frag; int rc; - frag = alloc_skb(real_dev->hard_header_len + - real_dev->needed_tailroom + size, + frag = alloc_skb(wdev->hard_header_len + wdev->needed_tailroom + size, GFP_ATOMIC); if (likely(frag)) { - frag->dev = real_dev; + frag->dev = wdev; frag->priority = skb->priority; - skb_reserve(frag, real_dev->hard_header_len); + skb_reserve(frag, wdev->hard_header_len); skb_reset_network_header(frag); *mac_cb(frag) = *mac_cb(skb); - rc = dev_hard_header(frag, real_dev, 0, &master_hdr->dest, + rc = dev_hard_header(frag, wdev, 0, &master_hdr->dest, &master_hdr->source, size); if (rc < 0) { kfree_skb(frag); @@ -123,19 +122,17 @@ lowpan_xmit_fragment(struct sk_buff *skb, const struct ieee802154_hdr *wpan_hdr, } static int -lowpan_xmit_fragmented(struct sk_buff *skb, struct net_device *dev, - const struct ieee802154_hdr *wpan_hdr) +lowpan_xmit_fragmented(struct sk_buff *skb, struct net_device *ldev, + const struct ieee802154_hdr *wpan_hdr, u16 dgram_size, + u16 dgram_offset) { - u16 dgram_size, dgram_offset; __be16 frag_tag; u8 frag_hdr[5]; int frag_cap, frag_len, payload_cap, rc; int skb_unprocessed, skb_offset; - dgram_size = lowpan_uncompress_size(skb, &dgram_offset) - - skb->mac_len; - frag_tag = htons(lowpan_dev_info(dev)->fragment_tag); - lowpan_dev_info(dev)->fragment_tag++; + frag_tag = htons(lowpan_dev_info(ldev)->fragment_tag); + lowpan_dev_info(ldev)->fragment_tag++; frag_hdr[0] = LOWPAN_DISPATCH_FRAG1 | ((dgram_size >> 8) & 0x07); frag_hdr[1] = dgram_size & 0xff; @@ -188,9 +185,10 @@ err: return rc; } -static int lowpan_header(struct sk_buff *skb, struct net_device *dev) +static int lowpan_header(struct sk_buff *skb, struct net_device *ldev, + u16 *dgram_size, u16 *dgram_offset) { - struct wpan_dev *wpan_dev = lowpan_dev_info(dev)->real_dev->ieee802154_ptr; + struct wpan_dev *wpan_dev = lowpan_dev_info(ldev)->wdev->ieee802154_ptr; struct ieee802154_addr sa, da; struct ieee802154_mac_cb *cb = mac_cb_init(skb); struct lowpan_addr_info info; @@ -202,7 +200,10 @@ static int lowpan_header(struct sk_buff *skb, struct net_device *dev) daddr = &info.daddr.u.extended_addr; saddr = &info.saddr.u.extended_addr; - lowpan_header_compress(skb, dev, ETH_P_IPV6, daddr, saddr, skb->len); + *dgram_size = skb->len; + lowpan_header_compress(skb, ldev, ETH_P_IPV6, daddr, saddr, skb->len); + /* dgram_offset = (saved bytes after compression) + lowpan header len */ + *dgram_offset = (*dgram_size - skb->len) + skb_network_header_len(skb); cb->type = IEEE802154_FC_TYPE_DATA; @@ -227,14 +228,15 @@ static int lowpan_header(struct sk_buff *skb, struct net_device *dev) cb->ackreq = wpan_dev->ackreq; } - return dev_hard_header(skb, lowpan_dev_info(dev)->real_dev, - ETH_P_IPV6, (void *)&da, (void *)&sa, 0); + return dev_hard_header(skb, lowpan_dev_info(ldev)->wdev, ETH_P_IPV6, + (void *)&da, (void *)&sa, 0); } -netdev_tx_t lowpan_xmit(struct sk_buff *skb, struct net_device *dev) +netdev_tx_t lowpan_xmit(struct sk_buff *skb, struct net_device *ldev) { struct ieee802154_hdr wpan_hdr; int max_single, ret; + u16 dgram_size, dgram_offset; pr_debug("package xmit\n"); @@ -245,7 +247,7 @@ netdev_tx_t lowpan_xmit(struct sk_buff *skb, struct net_device *dev) if (!skb) return NET_XMIT_DROP; - ret = lowpan_header(skb, dev); + ret = lowpan_header(skb, ldev, &dgram_size, &dgram_offset); if (ret < 0) { kfree_skb(skb); return NET_XMIT_DROP; @@ -259,13 +261,14 @@ netdev_tx_t lowpan_xmit(struct sk_buff *skb, struct net_device *dev) max_single = ieee802154_max_payload(&wpan_hdr); if (skb_tail_pointer(skb) - skb_network_header(skb) <= max_single) { - skb->dev = lowpan_dev_info(dev)->real_dev; + skb->dev = lowpan_dev_info(ldev)->wdev; return dev_queue_xmit(skb); } else { netdev_tx_t rc; pr_debug("frame is too big, fragmentation is needed\n"); - rc = lowpan_xmit_fragmented(skb, dev, &wpan_hdr); + rc = lowpan_xmit_fragmented(skb, ldev, &wpan_hdr, dgram_size, + dgram_offset); return rc < 0 ? NET_XMIT_DROP : rc; } diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 1d0c3adb6f34..11c4ca13ec3b 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -119,7 +119,7 @@ #ifdef CONFIG_IP_MROUTE #include <linux/mroute.h> #endif -#include <net/vrf.h> +#include <net/l3mdev.h> /* The inetsw table contains everything that inet_create needs to @@ -219,17 +219,13 @@ int inet_listen(struct socket *sock, int backlog) * shutdown() (rather than close()). */ if ((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) != 0 && - !inet_csk(sk)->icsk_accept_queue.fastopenq) { + !inet_csk(sk)->icsk_accept_queue.fastopenq.max_qlen) { if ((sysctl_tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) != 0) - err = fastopen_init_queue(sk, backlog); + fastopen_queue_tune(sk, backlog); else if ((sysctl_tcp_fastopen & TFO_SERVER_WO_SOCKOPT2) != 0) - err = fastopen_init_queue(sk, + fastopen_queue_tune(sk, ((uint)sysctl_tcp_fastopen) >> 16); - else - err = 0; - if (err) - goto out; tcp_fastopen_init_key_once(true); } @@ -450,7 +446,7 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out; } - tb_id = vrf_dev_table_ifindex(net, sk->sk_bound_dev_if) ? : tb_id; + tb_id = l3mdev_fib_table_by_index(net, sk->sk_bound_dev_if) ? : tb_id; chk_addr_ret = inet_addr_type_table(net, addr->sin_addr.s_addr, tb_id); /* Not specified by any standard per-se, however it breaks too @@ -1043,22 +1039,16 @@ void inet_register_protosw(struct inet_protosw *p) goto out_illegal; /* If we are trying to override a permanent protocol, bail. */ - answer = NULL; last_perm = &inetsw[p->type]; list_for_each(lh, &inetsw[p->type]) { answer = list_entry(lh, struct inet_protosw, list); - /* Check only the non-wild match. */ - if (INET_PROTOSW_PERMANENT & answer->flags) { - if (protocol == answer->protocol) - break; - last_perm = lh; - } - - answer = NULL; + if ((INET_PROTOSW_PERMANENT & answer->flags) == 0) + break; + if (protocol == answer->protocol) + goto out_permanent; + last_perm = lh; } - if (answer) - goto out_permanent; /* Add the new entry after the last permanent entry if any, so that * the new entry does not override a permanent entry when matched with diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index f03db8b7abee..01308e6e6127 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -624,14 +624,20 @@ out: } EXPORT_SYMBOL(arp_create); +static int arp_xmit_finish(struct net *net, struct sock *sk, struct sk_buff *skb) +{ + return dev_queue_xmit(skb); +} + /* * Send an arp packet. */ void arp_xmit(struct sk_buff *skb) { /* Send it off, maybe filter it using firewalling first. */ - NF_HOOK(NFPROTO_ARP, NF_ARP_OUT, NULL, skb, - NULL, skb->dev, dev_queue_xmit_sk); + NF_HOOK(NFPROTO_ARP, NF_ARP_OUT, + dev_net(skb->dev), NULL, skb, NULL, skb->dev, + arp_xmit_finish); } EXPORT_SYMBOL(arp_xmit); @@ -639,7 +645,7 @@ EXPORT_SYMBOL(arp_xmit); * Process an arp request. */ -static int arp_process(struct sock *sk, struct sk_buff *skb) +static int arp_process(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb->dev; struct in_device *in_dev = __in_dev_get_rcu(dev); @@ -651,7 +657,6 @@ static int arp_process(struct sock *sk, struct sk_buff *skb) u16 dev_type = dev->type; int addr_type; struct neighbour *n; - struct net *net = dev_net(dev); struct dst_entry *reply_dst = NULL; bool is_garp = false; @@ -870,7 +875,7 @@ out: static void parp_redo(struct sk_buff *skb) { - arp_process(NULL, skb); + arp_process(dev_net(skb->dev), NULL, skb); } @@ -903,8 +908,9 @@ static int arp_rcv(struct sk_buff *skb, struct net_device *dev, memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb)); - return NF_HOOK(NFPROTO_ARP, NF_ARP_IN, NULL, skb, - dev, NULL, arp_process); + return NF_HOOK(NFPROTO_ARP, NF_ARP_IN, + dev_net(dev), NULL, skb, dev, NULL, + arp_process); consumeskb: consume_skb(skb); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 2d9cb1748f81..735008472844 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1654,7 +1654,8 @@ static size_t inet_get_link_af_size(const struct net_device *dev) return nla_total_size(IPV4_DEVCONF_MAX * 4); /* IFLA_INET_CONF */ } -static int inet_fill_link_af(struct sk_buff *skb, const struct net_device *dev) +static int inet_fill_link_af(struct sk_buff *skb, const struct net_device *dev, + u32 ext_filter_mask) { struct in_device *in_dev = rcu_dereference_rtnl(dev->ip_ptr); struct nlattr *nla; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 690bcbc59f26..d7c2bb0c4f65 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -45,7 +45,7 @@ #include <net/ip_fib.h> #include <net/rtnetlink.h> #include <net/xfrm.h> -#include <net/vrf.h> +#include <net/l3mdev.h> #include <trace/events/fib.h> #ifndef CONFIG_IP_MULTIPLE_TABLES @@ -255,7 +255,7 @@ EXPORT_SYMBOL(inet_addr_type); unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev, __be32 addr) { - u32 rt_table = vrf_dev_table(dev) ? : RT_TABLE_LOCAL; + u32 rt_table = l3mdev_fib_table(dev) ? : RT_TABLE_LOCAL; return __inet_dev_addr_type(net, dev, addr, rt_table); } @@ -268,7 +268,7 @@ unsigned int inet_addr_type_dev_table(struct net *net, const struct net_device *dev, __be32 addr) { - u32 rt_table = vrf_dev_table(dev) ? : RT_TABLE_LOCAL; + u32 rt_table = l3mdev_fib_table(dev) ? : RT_TABLE_LOCAL; return __inet_dev_addr_type(net, NULL, addr, rt_table); } @@ -332,7 +332,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, bool dev_match; fl4.flowi4_oif = 0; - fl4.flowi4_iif = vrf_master_ifindex_rcu(dev); + fl4.flowi4_iif = l3mdev_master_ifindex_rcu(dev); if (!fl4.flowi4_iif) fl4.flowi4_iif = oif ? : LOOPBACK_IFINDEX; fl4.daddr = src; @@ -367,7 +367,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, if (nh->nh_dev == dev) { dev_match = true; break; - } else if (vrf_master_ifindex_rcu(nh->nh_dev) == dev->ifindex) { + } else if (l3mdev_master_ifindex_rcu(nh->nh_dev) == dev->ifindex) { dev_match = true; break; } @@ -804,7 +804,7 @@ out: static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifaddr *ifa) { struct net *net = dev_net(ifa->ifa_dev->dev); - u32 tb_id = vrf_dev_table_rtnl(ifa->ifa_dev->dev); + u32 tb_id = l3mdev_fib_table(ifa->ifa_dev->dev); struct fib_table *tb; struct fib_config cfg = { .fc_protocol = RTPROT_KERNEL, diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index e5eb8ac4089d..6b96dee2800b 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -96,7 +96,7 @@ #include <net/xfrm.h> #include <net/inet_common.h> #include <net/ip_fib.h> -#include <net/vrf.h> +#include <net/l3mdev.h> /* * Build xmit assembly blocks @@ -309,7 +309,7 @@ static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt, rc = false; if (icmp_global_allow()) { - int vif = vrf_master_ifindex(dst->dev); + int vif = l3mdev_master_ifindex(dst->dev); struct inet_peer *peer; peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, vif, 1); @@ -427,7 +427,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) fl4.flowi4_mark = mark; fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos); fl4.flowi4_proto = IPPROTO_ICMP; - fl4.flowi4_oif = vrf_master_ifindex(skb->dev); + fl4.flowi4_oif = l3mdev_master_ifindex(skb->dev); security_skb_classify_flow(skb, flowi4_to_flowi(&fl4)); rt = ip_route_output_key(net, &fl4); if (IS_ERR(rt)) @@ -461,7 +461,7 @@ static struct rtable *icmp_route_lookup(struct net *net, fl4->flowi4_proto = IPPROTO_ICMP; fl4->fl4_icmp_type = type; fl4->fl4_icmp_code = code; - fl4->flowi4_oif = vrf_master_ifindex(skb_in->dev); + fl4->flowi4_oif = l3mdev_master_ifindex(skb_in->dev); security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4)); rt = __ip_route_output_key(net, fl4); diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index d38b8b61eaee..de6d4c8ba600 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -2569,7 +2569,7 @@ void ip_mc_drop_socket(struct sock *sk) } /* called with rcu_read_lock() */ -int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u16 proto) +int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u8 proto) { struct ip_mc_list *im; struct ip_mc_list __rcu **mc_hash; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 7bb9c39e0a4d..e1527882a578 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -335,9 +335,8 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err) sk_acceptq_removed(sk); if (sk->sk_protocol == IPPROTO_TCP && - tcp_rsk(req)->tfo_listener && - queue->fastopenq) { - spin_lock_bh(&queue->fastopenq->lock); + tcp_rsk(req)->tfo_listener) { + spin_lock_bh(&queue->fastopenq.lock); if (tcp_rsk(req)->tfo_listener) { /* We are still waiting for the final ACK from 3WHS * so can't free req now. Instead, we set req->sk to @@ -348,7 +347,7 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err) req->sk = NULL; req = NULL; } - spin_unlock_bh(&queue->fastopenq->lock); + spin_unlock_bh(&queue->fastopenq.lock); } out: release_sock(sk); @@ -408,7 +407,7 @@ void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long len) } EXPORT_SYMBOL(inet_csk_reset_keepalive_timer); -struct dst_entry *inet_csk_route_req(struct sock *sk, +struct dst_entry *inet_csk_route_req(const struct sock *sk, struct flowi4 *fl4, const struct request_sock *req) { @@ -439,7 +438,7 @@ no_route: } EXPORT_SYMBOL_GPL(inet_csk_route_req); -struct dst_entry *inet_csk_route_child_sock(struct sock *sk, +struct dst_entry *inet_csk_route_child_sock(const struct sock *sk, struct sock *newsk, const struct request_sock *req) { @@ -563,7 +562,7 @@ static inline void syn_ack_recalc(struct request_sock *req, const int thresh, req->num_timeout >= rskq_defer_accept - 1; } -int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req) +int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req) { int err = req->rsk_ops->rtx_syn_ack(parent, req); @@ -886,12 +885,12 @@ void inet_csk_listen_stop(struct sock *sk) sk_acceptq_removed(sk); reqsk_put(req); } - if (queue->fastopenq) { + if (queue->fastopenq.rskq_rst_head) { /* Free all the reqs queued in rskq_rst_head. */ - spin_lock_bh(&queue->fastopenq->lock); - acc_req = queue->fastopenq->rskq_rst_head; - queue->fastopenq->rskq_rst_head = NULL; - spin_unlock_bh(&queue->fastopenq->lock); + spin_lock_bh(&queue->fastopenq.lock); + acc_req = queue->fastopenq.rskq_rst_head; + queue->fastopenq.rskq_rst_head = NULL; + spin_unlock_bh(&queue->fastopenq.lock); while ((req = acc_req) != NULL) { acc_req = req->dl_next; reqsk_put(req); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 89120196a949..56742e995dd3 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -126,7 +126,7 @@ void inet_put_port(struct sock *sk) } EXPORT_SYMBOL(inet_put_port); -int __inet_inherit_port(struct sock *sk, struct sock *child) +int __inet_inherit_port(const struct sock *sk, struct sock *child) { struct inet_hashinfo *table = sk->sk_prot->h.hashinfo; unsigned short port = inet_sk(child)->inet_num; diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 2d3aa408fbdc..d66cfb35ba74 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -61,18 +61,18 @@ static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) } -static int ip_forward_finish(struct sock *sk, struct sk_buff *skb) +static int ip_forward_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { struct ip_options *opt = &(IPCB(skb)->opt); - IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS); - IP_ADD_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTOCTETS, skb->len); + IP_INC_STATS_BH(net, IPSTATS_MIB_OUTFORWDATAGRAMS); + IP_ADD_STATS_BH(net, IPSTATS_MIB_OUTOCTETS, skb->len); if (unlikely(opt->optlen)) ip_forward_options(skb); skb_sender_cpu_clear(skb); - return dst_output_sk(sk, skb); + return dst_output(sk, skb); } int ip_forward(struct sk_buff *skb) @@ -81,6 +81,7 @@ int ip_forward(struct sk_buff *skb) struct iphdr *iph; /* Our header */ struct rtable *rt; /* Route we use */ struct ip_options *opt = &(IPCB(skb)->opt); + struct net *net; /* that should never happen */ if (skb->pkt_type != PACKET_HOST) @@ -99,6 +100,7 @@ int ip_forward(struct sk_buff *skb) return NET_RX_SUCCESS; skb_forward_csum(skb); + net = dev_net(skb->dev); /* * According to the RFC, we must first decrease the TTL field. If @@ -119,7 +121,7 @@ int ip_forward(struct sk_buff *skb) IPCB(skb)->flags |= IPSKB_FORWARDED; mtu = ip_dst_mtu_maybe_forward(&rt->dst, true); if (ip_exceeds_mtu(skb, mtu)) { - IP_INC_STATS(dev_net(rt->dst.dev), IPSTATS_MIB_FRAGFAILS); + IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); goto drop; @@ -143,8 +145,9 @@ int ip_forward(struct sk_buff *skb) skb->priority = rt_tos2priority(iph->tos); - return NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD, NULL, skb, - skb->dev, rt->dst.dev, ip_forward_finish); + return NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD, + net, NULL, skb, skb->dev, rt->dst.dev, + ip_forward_finish); sr_failed: /* @@ -155,7 +158,7 @@ sr_failed: too_many_hops: /* Tell the sender its packet died... */ - IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_INHDRERRORS); + IP_INC_STATS_BH(net, IPSTATS_MIB_INHDRERRORS); icmp_send(skb, ICMP_TIME_EXCEEDED, ICMP_EXC_TTL, 0); drop: kfree_skb(skb); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index fa7f15305f9a..9772b789adf3 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -48,7 +48,7 @@ #include <linux/inet.h> #include <linux/netfilter_ipv4.h> #include <net/inet_ecn.h> -#include <net/vrf.h> +#include <net/l3mdev.h> /* NOTE. Logic of IP defragmentation is parallel to corresponding IPv6 * code now. If you change something here, _PLEASE_ update ipv6/reassembly.c @@ -78,7 +78,7 @@ struct ipq { u8 ecn; /* RFC3168 support */ u16 max_df_size; /* largest frag with DF set seen */ int iif; - int vif; /* VRF device index */ + int vif; /* L3 master device index */ unsigned int rid; struct inet_peer *peer; }; @@ -657,7 +657,7 @@ out_fail: int ip_defrag(struct sk_buff *skb, u32 user) { struct net_device *dev = skb->dev ? : skb_dst(skb)->dev; - int vif = vrf_master_ifindex_rcu(dev); + int vif = l3mdev_master_ifindex_rcu(dev); struct net *net = dev_net(dev); struct ipq *qp; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index f4fc8a77aaa7..7cc9f7bb7fb7 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -188,10 +188,8 @@ bool ip_call_ra_chain(struct sk_buff *skb) return false; } -static int ip_local_deliver_finish(struct sock *sk, struct sk_buff *skb) +static int ip_local_deliver_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct net *net = dev_net(skb->dev); - __skb_pull(skb, skb_network_header_len(skb)); rcu_read_lock(); @@ -254,8 +252,8 @@ int ip_local_deliver(struct sk_buff *skb) return 0; } - return NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_IN, NULL, skb, - skb->dev, NULL, + return NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_IN, + dev_net(skb->dev), NULL, skb, skb->dev, NULL, ip_local_deliver_finish); } @@ -311,7 +309,7 @@ drop: int sysctl_ip_early_demux __read_mostly = 1; EXPORT_SYMBOL(sysctl_ip_early_demux); -static int ip_rcv_finish(struct sock *sk, struct sk_buff *skb) +static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { const struct iphdr *iph = ip_hdr(skb); struct rtable *rt; @@ -337,8 +335,7 @@ static int ip_rcv_finish(struct sock *sk, struct sk_buff *skb) iph->tos, skb->dev); if (unlikely(err)) { if (err == -EXDEV) - NET_INC_STATS_BH(dev_net(skb->dev), - LINUX_MIB_IPRPFILTER); + NET_INC_STATS_BH(net, LINUX_MIB_IPRPFILTER); goto drop; } } @@ -359,11 +356,9 @@ static int ip_rcv_finish(struct sock *sk, struct sk_buff *skb) rt = skb_rtable(skb); if (rt->rt_type == RTN_MULTICAST) { - IP_UPD_PO_STATS_BH(dev_net(rt->dst.dev), IPSTATS_MIB_INMCAST, - skb->len); + IP_UPD_PO_STATS_BH(net, IPSTATS_MIB_INMCAST, skb->len); } else if (rt->rt_type == RTN_BROADCAST) - IP_UPD_PO_STATS_BH(dev_net(rt->dst.dev), IPSTATS_MIB_INBCAST, - skb->len); + IP_UPD_PO_STATS_BH(net, IPSTATS_MIB_INBCAST, skb->len); return dst_input(skb); @@ -378,6 +373,7 @@ drop: int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { const struct iphdr *iph; + struct net *net; u32 len; /* When the interface is in promisc. mode, drop all the crap @@ -387,11 +383,12 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, goto drop; - IP_UPD_PO_STATS_BH(dev_net(dev), IPSTATS_MIB_IN, skb->len); + net = dev_net(dev); + IP_UPD_PO_STATS_BH(net, IPSTATS_MIB_IN, skb->len); skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) { - IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INDISCARDS); + IP_INC_STATS_BH(net, IPSTATS_MIB_INDISCARDS); goto out; } @@ -417,7 +414,7 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, BUILD_BUG_ON(IPSTATS_MIB_ECT1PKTS != IPSTATS_MIB_NOECTPKTS + INET_ECN_ECT_1); BUILD_BUG_ON(IPSTATS_MIB_ECT0PKTS != IPSTATS_MIB_NOECTPKTS + INET_ECN_ECT_0); BUILD_BUG_ON(IPSTATS_MIB_CEPKTS != IPSTATS_MIB_NOECTPKTS + INET_ECN_CE); - IP_ADD_STATS_BH(dev_net(dev), + IP_ADD_STATS_BH(net, IPSTATS_MIB_NOECTPKTS + (iph->tos & INET_ECN_MASK), max_t(unsigned short, 1, skb_shinfo(skb)->gso_segs)); @@ -431,7 +428,7 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, len = ntohs(iph->tot_len); if (skb->len < len) { - IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INTRUNCATEDPKTS); + IP_INC_STATS_BH(net, IPSTATS_MIB_INTRUNCATEDPKTS); goto drop; } else if (len < (iph->ihl*4)) goto inhdr_error; @@ -441,7 +438,7 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, * Note this now means skb->len holds ntohs(iph->tot_len). */ if (pskb_trim_rcsum(skb, len)) { - IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INDISCARDS); + IP_INC_STATS_BH(net, IPSTATS_MIB_INDISCARDS); goto drop; } @@ -453,14 +450,14 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, /* Must drop socket now because of tproxy. */ skb_orphan(skb); - return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, NULL, skb, - dev, NULL, + return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, + net, NULL, skb, dev, NULL, ip_rcv_finish); csum_error: - IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_CSUMERRORS); + IP_INC_STATS_BH(net, IPSTATS_MIB_CSUMERRORS); inhdr_error: - IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_INHDRERRORS); + IP_INC_STATS_BH(net, IPSTATS_MIB_INHDRERRORS); drop: kfree_skb(skb); out: diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 0138fada0951..aff6766922e8 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -97,12 +97,14 @@ EXPORT_SYMBOL(ip_send_check); static int __ip_local_out_sk(struct sock *sk, struct sk_buff *skb) { + struct net *net = dev_net(skb_dst(skb)->dev); struct iphdr *iph = ip_hdr(skb); iph->tot_len = htons(skb->len); ip_send_check(iph); - return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, sk, skb, NULL, - skb_dst(skb)->dev, dst_output_sk); + return nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, + net, sk, skb, NULL, skb_dst(skb)->dev, + dst_output_okfn); } int __ip_local_out(struct sk_buff *skb) @@ -116,7 +118,7 @@ int ip_local_out_sk(struct sock *sk, struct sk_buff *skb) err = __ip_local_out(skb); if (likely(err == 1)) - err = dst_output_sk(sk, skb); + err = dst_output(sk, skb); return err; } @@ -135,7 +137,7 @@ static inline int ip_select_ttl(struct inet_sock *inet, struct dst_entry *dst) * Add an ip header to a skbuff and send it out. * */ -int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk, +int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk, __be32 saddr, __be32 daddr, struct ip_options_rcu *opt) { struct inet_sock *inet = inet_sk(sk); @@ -149,15 +151,17 @@ int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk, iph->version = 4; iph->ihl = 5; iph->tos = inet->tos; - if (ip_dont_fragment(sk, &rt->dst)) - iph->frag_off = htons(IP_DF); - else - iph->frag_off = 0; iph->ttl = ip_select_ttl(inet, &rt->dst); iph->daddr = (opt && opt->opt.srr ? opt->opt.faddr : daddr); iph->saddr = saddr; iph->protocol = sk->sk_protocol; - ip_select_ident(sock_net(sk), skb, sk); + if (ip_dont_fragment(sk, &rt->dst)) { + iph->frag_off = htons(IP_DF); + iph->id = 0; + } else { + iph->frag_off = 0; + __ip_select_ident(sock_net(sk), iph, 1); + } if (opt && opt->opt.optlen) { iph->ihl += opt->opt.optlen>>2; @@ -177,14 +181,15 @@ static int ip_finish_output2(struct sock *sk, struct sk_buff *skb) struct dst_entry *dst = skb_dst(skb); struct rtable *rt = (struct rtable *)dst; struct net_device *dev = dst->dev; + struct net *net = dev_net(dev); unsigned int hh_len = LL_RESERVED_SPACE(dev); struct neighbour *neigh; u32 nexthop; if (rt->rt_type == RTN_MULTICAST) { - IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUTMCAST, skb->len); + IP_UPD_PO_STATS(net, IPSTATS_MIB_OUTMCAST, skb->len); } else if (rt->rt_type == RTN_BROADCAST) - IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUTBCAST, skb->len); + IP_UPD_PO_STATS(net, IPSTATS_MIB_OUTBCAST, skb->len); /* Be paranoid, rather than too clever. */ if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { @@ -263,7 +268,7 @@ static int ip_finish_output_gso(struct sock *sk, struct sk_buff *skb, return ret; } -static int ip_finish_output(struct sock *sk, struct sk_buff *skb) +static int ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { unsigned int mtu; @@ -271,7 +276,7 @@ static int ip_finish_output(struct sock *sk, struct sk_buff *skb) /* Policy lookup after SNAT yielded a new policy */ if (skb_dst(skb)->xfrm) { IPCB(skb)->flags |= IPSKB_REROUTED; - return dst_output_sk(sk, skb); + return dst_output(sk, skb); } #endif mtu = ip_skb_dst_mtu(skb); @@ -288,11 +293,12 @@ int ip_mc_output(struct sock *sk, struct sk_buff *skb) { struct rtable *rt = skb_rtable(skb); struct net_device *dev = rt->dst.dev; + struct net *net = dev_net(dev); /* * If the indicated interface is up and running, send the packet. */ - IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUT, skb->len); + IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len); skb->dev = dev; skb->protocol = htons(ETH_P_IP); @@ -320,7 +326,7 @@ int ip_mc_output(struct sock *sk, struct sk_buff *skb) struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); if (newskb) NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, - sk, newskb, NULL, newskb->dev, + net, sk, newskb, NULL, newskb->dev, dev_loopback_xmit); } @@ -335,26 +341,29 @@ int ip_mc_output(struct sock *sk, struct sk_buff *skb) if (rt->rt_flags&RTCF_BROADCAST) { struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); if (newskb) - NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, sk, newskb, - NULL, newskb->dev, dev_loopback_xmit); + NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, + net, sk, newskb, NULL, newskb->dev, + dev_loopback_xmit); } - return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, sk, skb, NULL, - skb->dev, ip_finish_output, + return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, + net, sk, skb, NULL, skb->dev, + ip_finish_output, !(IPCB(skb)->flags & IPSKB_REROUTED)); } int ip_output(struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb_dst(skb)->dev; + struct net *net = dev_net(dev); - IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUT, skb->len); + IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len); skb->dev = dev; skb->protocol = htons(ETH_P_IP); - return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, sk, skb, - NULL, dev, + return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, + net, sk, skb, NULL, dev, ip_finish_output, !(IPCB(skb)->flags & IPSKB_REROUTED)); } @@ -498,10 +507,9 @@ static int ip_fragment(struct sock *sk, struct sk_buff *skb, if (unlikely(!skb->ignore_df || (IPCB(skb)->frag_max_size && IPCB(skb)->frag_max_size > mtu))) { - struct rtable *rt = skb_rtable(skb); - struct net_device *dev = rt->dst.dev; + struct net *net = dev_net(skb_rtable(skb)->dst.dev); - IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS); + IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); kfree_skb(skb); @@ -529,9 +537,11 @@ int ip_do_fragment(struct sock *sk, struct sk_buff *skb, int offset; __be16 not_last_frag; struct rtable *rt = skb_rtable(skb); + struct net *net; int err = 0; dev = rt->dst.dev; + net = dev_net(dev); /* * Point into the IP datagram header. @@ -624,7 +634,7 @@ int ip_do_fragment(struct sock *sk, struct sk_buff *skb, err = output(sk, skb); if (!err) - IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGCREATES); + IP_INC_STATS(net, IPSTATS_MIB_FRAGCREATES); if (err || !frag) break; @@ -634,7 +644,7 @@ int ip_do_fragment(struct sock *sk, struct sk_buff *skb, } if (err == 0) { - IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGOKS); + IP_INC_STATS(net, IPSTATS_MIB_FRAGOKS); return 0; } @@ -643,7 +653,7 @@ int ip_do_fragment(struct sock *sk, struct sk_buff *skb, kfree_skb(frag); frag = skb; } - IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS); + IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); return err; slow_path_clean: @@ -765,15 +775,15 @@ slow_path: if (err) goto fail; - IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGCREATES); + IP_INC_STATS(net, IPSTATS_MIB_FRAGCREATES); } consume_skb(skb); - IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGOKS); + IP_INC_STATS(net, IPSTATS_MIB_FRAGOKS); return err; fail: kfree_skb(skb); - IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS); + IP_INC_STATS(net, IPSTATS_MIB_FRAGFAILS); return err; } EXPORT_SYMBOL(ip_do_fragment); @@ -1561,7 +1571,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, } oif = arg->bound_dev_if; - if (!oif && netif_index_is_vrf(net, skb->skb_iif)) + if (!oif && netif_index_is_l3_master(net, skb->skb_iif)) oif = skb->skb_iif; flowi4_init_output(&fl4, oif, diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 0c152087ca15..3b87ec5178f9 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -197,7 +197,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, skb_dst_set(skb, dst); skb->dev = skb_dst(skb)->dev; - err = dst_output(skb); + err = dst_output(skb->sk, skb); if (net_xmit_eval(err) == 0) err = skb->len; iptunnel_xmit_stats(err, &dev->stats, dev->tstats); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 866ee89f5254..cfcb996ec51b 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1678,17 +1678,18 @@ static void ip_encap(struct net *net, struct sk_buff *skb, nf_reset(skb); } -static inline int ipmr_forward_finish(struct sock *sk, struct sk_buff *skb) +static inline int ipmr_forward_finish(struct net *net, struct sock *sk, + struct sk_buff *skb) { struct ip_options *opt = &(IPCB(skb)->opt); - IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS); - IP_ADD_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTOCTETS, skb->len); + IP_INC_STATS_BH(net, IPSTATS_MIB_OUTFORWDATAGRAMS); + IP_ADD_STATS_BH(net, IPSTATS_MIB_OUTOCTETS, skb->len); if (unlikely(opt->optlen)) ip_forward_options(skb); - return dst_output_sk(sk, skb); + return dst_output(sk, skb); } /* @@ -1745,7 +1746,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, * to blackhole. */ - IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_FRAGFAILS); + IP_INC_STATS_BH(net, IPSTATS_MIB_FRAGFAILS); ip_rt_put(rt); goto out_free; } @@ -1787,8 +1788,8 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, * not mrouter) cannot join to more than one interface - it will * result in receiving multiple packets. */ - NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD, NULL, skb, - skb->dev, dev, + NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD, + net, NULL, skb, skb->dev, dev, ipmr_forward_finish); return; diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index 61eafc9b4545..c3776ff6749f 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -17,9 +17,8 @@ #include <net/netfilter/nf_queue.h> /* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */ -int ip_route_me_harder(struct sk_buff *skb, unsigned int addr_type) +int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned int addr_type) { - struct net *net = dev_net(skb_dst(skb)->dev); const struct iphdr *iph = ip_hdr(skb); struct rtable *rt; struct flowi4 fl4 = {}; @@ -104,7 +103,7 @@ static void nf_ip_saveroute(const struct sk_buff *skb, } } -static int nf_ip_reroute(struct sk_buff *skb, +static int nf_ip_reroute(struct net *net, struct sk_buff *skb, const struct nf_queue_entry *entry) { const struct ip_rt_info *rt_info = nf_queue_entry_reroute(entry); @@ -116,7 +115,7 @@ static int nf_ip_reroute(struct sk_buff *skb, skb->mark == rt_info->mark && iph->daddr == rt_info->daddr && iph->saddr == rt_info->saddr)) - return ip_route_me_harder(skb, RTN_UNSPEC); + return ip_route_me_harder(net, skb, RTN_UNSPEC); } return 0; } diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 8f87fc38ccde..2dad3e1c5f11 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -247,10 +247,10 @@ struct arpt_entry *arpt_next_entry(const struct arpt_entry *entry) } unsigned int arpt_do_table(struct sk_buff *skb, - unsigned int hook, const struct nf_hook_state *state, struct xt_table *table) { + unsigned int hook = state->hook; static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); unsigned int verdict = NF_DROP; const struct arphdr *arp; @@ -285,6 +285,7 @@ unsigned int arpt_do_table(struct sk_buff *skb, */ e = get_entry(table_base, private->hook_entry[hook]); + acpar.net = state->net; acpar.in = state->in; acpar.out = state->out; acpar.hooknum = hook; diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c index 93876d03120c..1897ee160920 100644 --- a/net/ipv4/netfilter/arptable_filter.c +++ b/net/ipv4/netfilter/arptable_filter.c @@ -27,13 +27,10 @@ static const struct xt_table packet_filter = { /* The work comes in here from netfilter.c */ static unsigned int -arptable_filter_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, +arptable_filter_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - const struct net *net = dev_net(state->in ? state->in : state->out); - - return arpt_do_table(skb, ops->hooknum, state, - net->ipv4.arptable_filter); + return arpt_do_table(skb, state, state->net->ipv4.arptable_filter); } static struct nf_hook_ops *arpfilter_ops __read_mostly; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index b0a86e73451c..42d0946956db 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -246,7 +246,8 @@ get_chainname_rulenum(const struct ipt_entry *s, const struct ipt_entry *e, return 0; } -static void trace_packet(const struct sk_buff *skb, +static void trace_packet(struct net *net, + const struct sk_buff *skb, unsigned int hook, const struct net_device *in, const struct net_device *out, @@ -258,7 +259,6 @@ static void trace_packet(const struct sk_buff *skb, const char *hookname, *chainname, *comment; const struct ipt_entry *iter; unsigned int rulenum = 0; - struct net *net = dev_net(in ? in : out); root = get_entry(private->entries, private->hook_entry[hook]); @@ -285,10 +285,10 @@ struct ipt_entry *ipt_next_entry(const struct ipt_entry *entry) /* Returns one of the generic firewall policies, like NF_ACCEPT. */ unsigned int ipt_do_table(struct sk_buff *skb, - unsigned int hook, const struct nf_hook_state *state, struct xt_table *table) { + unsigned int hook = state->hook; static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); const struct iphdr *ip; /* Initializing verdict to NF_DROP keeps gcc happy. */ @@ -315,6 +315,7 @@ ipt_do_table(struct sk_buff *skb, acpar.fragoff = ntohs(ip->frag_off) & IP_OFFSET; acpar.thoff = ip_hdrlen(skb); acpar.hotdrop = false; + acpar.net = state->net; acpar.in = state->in; acpar.out = state->out; acpar.family = NFPROTO_IPV4; @@ -378,8 +379,8 @@ ipt_do_table(struct sk_buff *skb, #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) /* The packet is traced: log it */ if (unlikely(skb->nf_trace)) - trace_packet(skb, hook, state->in, state->out, - table->name, private, e); + trace_packet(state->net, skb, hook, state->in, + state->out, table->name, private, e); #endif /* Standard target? */ if (!t->u.kernel.target->target) { diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 45cb16a6a4a3..3f32c03e8b2e 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -507,14 +507,14 @@ static void arp_print(struct arp_payload *payload) #endif static unsigned int -arp_mangle(const struct nf_hook_ops *ops, +arp_mangle(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct arphdr *arp = arp_hdr(skb); struct arp_payload *payload; struct clusterip_config *c; - struct net *net = dev_net(state->in ? state->in : state->out); + struct net *net = state->net; /* we don't care about non-ethernet and non-ipv4 ARP */ if (arp->ar_hrd != htons(ARPHRD_ETHER) || diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c index 87907d4bd259..1d16c0f28df0 100644 --- a/net/ipv4/netfilter/ipt_REJECT.c +++ b/net/ipv4/netfilter/ipt_REJECT.c @@ -59,7 +59,7 @@ reject_tg(struct sk_buff *skb, const struct xt_action_param *par) nf_send_unreach(skb, ICMP_PKT_FILTERED, hook); break; case IPT_TCP_RESET: - nf_send_reset(skb, hook); + nf_send_reset(par->net, skb, hook); case IPT_ICMP_ECHOREPLY: /* Doesn't happen. */ break; diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c index 95ea633e8356..6a6e762ab27f 100644 --- a/net/ipv4/netfilter/ipt_SYNPROXY.c +++ b/net/ipv4/netfilter/ipt_SYNPROXY.c @@ -39,11 +39,14 @@ synproxy_build_ip(struct sk_buff *skb, __be32 saddr, __be32 daddr) } static void -synproxy_send_tcp(const struct sk_buff *skb, struct sk_buff *nskb, +synproxy_send_tcp(const struct synproxy_net *snet, + const struct sk_buff *skb, struct sk_buff *nskb, struct nf_conntrack *nfct, enum ip_conntrack_info ctinfo, struct iphdr *niph, struct tcphdr *nth, unsigned int tcp_hdr_size) { + struct net *net = nf_ct_net(snet->tmpl); + nth->check = ~tcp_v4_check(tcp_hdr_size, niph->saddr, niph->daddr, 0); nskb->ip_summed = CHECKSUM_PARTIAL; nskb->csum_start = (unsigned char *)nth - nskb->head; @@ -51,7 +54,7 @@ synproxy_send_tcp(const struct sk_buff *skb, struct sk_buff *nskb, skb_dst_set_noref(nskb, skb_dst(skb)); nskb->protocol = htons(ETH_P_IP); - if (ip_route_me_harder(nskb, RTN_UNSPEC)) + if (ip_route_me_harder(net, nskb, RTN_UNSPEC)) goto free_nskb; if (nfct) { @@ -68,7 +71,8 @@ free_nskb: } static void -synproxy_send_client_synack(const struct sk_buff *skb, const struct tcphdr *th, +synproxy_send_client_synack(const struct synproxy_net *snet, + const struct sk_buff *skb, const struct tcphdr *th, const struct synproxy_options *opts) { struct sk_buff *nskb; @@ -104,7 +108,7 @@ synproxy_send_client_synack(const struct sk_buff *skb, const struct tcphdr *th, synproxy_build_options(nth, opts); - synproxy_send_tcp(skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY, + synproxy_send_tcp(snet, skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY, niph, nth, tcp_hdr_size); } @@ -148,7 +152,7 @@ synproxy_send_server_syn(const struct synproxy_net *snet, synproxy_build_options(nth, opts); - synproxy_send_tcp(skb, nskb, &snet->tmpl->ct_general, IP_CT_NEW, + synproxy_send_tcp(snet, skb, nskb, &snet->tmpl->ct_general, IP_CT_NEW, niph, nth, tcp_hdr_size); } @@ -188,7 +192,7 @@ synproxy_send_server_ack(const struct synproxy_net *snet, synproxy_build_options(nth, opts); - synproxy_send_tcp(skb, nskb, NULL, 0, niph, nth, tcp_hdr_size); + synproxy_send_tcp(snet, skb, nskb, NULL, 0, niph, nth, tcp_hdr_size); } static void @@ -226,7 +230,7 @@ synproxy_send_client_ack(const struct synproxy_net *snet, synproxy_build_options(nth, opts); - synproxy_send_tcp(skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY, + synproxy_send_tcp(snet, skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY, niph, nth, tcp_hdr_size); } @@ -258,7 +262,7 @@ static unsigned int synproxy_tg4(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_synproxy_info *info = par->targinfo; - struct synproxy_net *snet = synproxy_pernet(dev_net(par->in)); + struct synproxy_net *snet = synproxy_pernet(par->net); struct synproxy_options opts = {}; struct tcphdr *th, _th; @@ -287,7 +291,7 @@ synproxy_tg4(struct sk_buff *skb, const struct xt_action_param *par) XT_SYNPROXY_OPT_SACK_PERM | XT_SYNPROXY_OPT_ECN); - synproxy_send_client_synack(skb, th, &opts); + synproxy_send_client_synack(snet, skb, th, &opts); return NF_DROP; } else if (th->ack && !(th->fin || th->rst || th->syn)) { @@ -299,11 +303,11 @@ synproxy_tg4(struct sk_buff *skb, const struct xt_action_param *par) return XT_CONTINUE; } -static unsigned int ipv4_synproxy_hook(const struct nf_hook_ops *ops, +static unsigned int ipv4_synproxy_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *nhs) { - struct synproxy_net *snet = synproxy_pernet(dev_net(nhs->in ? : nhs->out)); + struct synproxy_net *snet = synproxy_pernet(nhs->net); enum ip_conntrack_info ctinfo; struct nf_conn *ct; struct nf_conn_synproxy *synproxy; diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c index 8618fd150c96..74dd6671b66d 100644 --- a/net/ipv4/netfilter/ipt_rpfilter.c +++ b/net/ipv4/netfilter/ipt_rpfilter.c @@ -32,12 +32,11 @@ static __be32 rpfilter_get_saddr(__be32 addr) return addr; } -static bool rpfilter_lookup_reverse(struct flowi4 *fl4, +static bool rpfilter_lookup_reverse(struct net *net, struct flowi4 *fl4, const struct net_device *dev, u8 flags) { struct fib_result res; bool dev_match; - struct net *net = dev_net(dev); int ret __maybe_unused; if (fib_lookup(net, fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE)) @@ -98,7 +97,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) flow.flowi4_tos = RT_TOS(iph->tos); flow.flowi4_scope = RT_SCOPE_UNIVERSE; - return rpfilter_lookup_reverse(&flow, par->in, info->flags) ^ invert; + return rpfilter_lookup_reverse(par->net, &flow, par->in, info->flags) ^ invert; } static int rpfilter_check(const struct xt_mtchk_param *par) diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index a0f3beca52d2..397ef2dd133e 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -33,19 +33,16 @@ static const struct xt_table packet_filter = { }; static unsigned int -iptable_filter_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, +iptable_filter_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - const struct net *net; - - if (ops->hooknum == NF_INET_LOCAL_OUT && + if (state->hook == NF_INET_LOCAL_OUT && (skb->len < sizeof(struct iphdr) || ip_hdrlen(skb) < sizeof(struct iphdr))) /* root is playing with raw sockets. */ return NF_ACCEPT; - net = dev_net(state->in ? state->in : state->out); - return ipt_do_table(skb, ops->hooknum, state, net->ipv4.iptable_filter); + return ipt_do_table(skb, state, state->net->ipv4.iptable_filter); } static struct nf_hook_ops *filter_ops __read_mostly; diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index 62cbb8c5f4a8..ba5d392a13c4 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -39,7 +39,6 @@ static const struct xt_table packet_mangler = { static unsigned int ipt_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state) { - struct net_device *out = state->out; unsigned int ret; const struct iphdr *iph; u_int8_t tos; @@ -59,8 +58,7 @@ ipt_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state) daddr = iph->daddr; tos = iph->tos; - ret = ipt_do_table(skb, NF_INET_LOCAL_OUT, state, - dev_net(out)->ipv4.iptable_mangle); + ret = ipt_do_table(skb, state, state->net->ipv4.iptable_mangle); /* Reroute for ANY change. */ if (ret != NF_DROP && ret != NF_STOLEN) { iph = ip_hdr(skb); @@ -69,7 +67,7 @@ ipt_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state) iph->daddr != daddr || skb->mark != mark || iph->tos != tos) { - err = ip_route_me_harder(skb, RTN_UNSPEC); + err = ip_route_me_harder(state->net, skb, RTN_UNSPEC); if (err < 0) ret = NF_DROP_ERR(err); } @@ -80,18 +78,17 @@ ipt_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state) /* The work comes in here from netfilter.c. */ static unsigned int -iptable_mangle_hook(const struct nf_hook_ops *ops, +iptable_mangle_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - if (ops->hooknum == NF_INET_LOCAL_OUT) + if (state->hook == NF_INET_LOCAL_OUT) return ipt_mangle_out(skb, state); - if (ops->hooknum == NF_INET_POST_ROUTING) - return ipt_do_table(skb, ops->hooknum, state, - dev_net(state->out)->ipv4.iptable_mangle); + if (state->hook == NF_INET_POST_ROUTING) + return ipt_do_table(skb, state, + state->net->ipv4.iptable_mangle); /* PREROUTING/INPUT/FORWARD: */ - return ipt_do_table(skb, ops->hooknum, state, - dev_net(state->in)->ipv4.iptable_mangle); + return ipt_do_table(skb, state, state->net->ipv4.iptable_mangle); } static struct nf_hook_ops *mangle_ops __read_mostly; diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c index 0d4d9cdf98a4..3a2e4d830a0b 100644 --- a/net/ipv4/netfilter/iptable_nat.c +++ b/net/ipv4/netfilter/iptable_nat.c @@ -28,42 +28,40 @@ static const struct xt_table nf_nat_ipv4_table = { .af = NFPROTO_IPV4, }; -static unsigned int iptable_nat_do_chain(const struct nf_hook_ops *ops, +static unsigned int iptable_nat_do_chain(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct) { - struct net *net = nf_ct_net(ct); - - return ipt_do_table(skb, ops->hooknum, state, net->ipv4.nat_table); + return ipt_do_table(skb, state, state->net->ipv4.nat_table); } -static unsigned int iptable_nat_ipv4_fn(const struct nf_hook_ops *ops, +static unsigned int iptable_nat_ipv4_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_nat_ipv4_fn(ops, skb, state, iptable_nat_do_chain); + return nf_nat_ipv4_fn(priv, skb, state, iptable_nat_do_chain); } -static unsigned int iptable_nat_ipv4_in(const struct nf_hook_ops *ops, +static unsigned int iptable_nat_ipv4_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_nat_ipv4_in(ops, skb, state, iptable_nat_do_chain); + return nf_nat_ipv4_in(priv, skb, state, iptable_nat_do_chain); } -static unsigned int iptable_nat_ipv4_out(const struct nf_hook_ops *ops, +static unsigned int iptable_nat_ipv4_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_nat_ipv4_out(ops, skb, state, iptable_nat_do_chain); + return nf_nat_ipv4_out(priv, skb, state, iptable_nat_do_chain); } -static unsigned int iptable_nat_ipv4_local_fn(const struct nf_hook_ops *ops, +static unsigned int iptable_nat_ipv4_local_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_nat_ipv4_local_fn(ops, skb, state, iptable_nat_do_chain); + return nf_nat_ipv4_local_fn(priv, skb, state, iptable_nat_do_chain); } static struct nf_hook_ops nf_nat_ipv4_ops[] __read_mostly = { diff --git a/net/ipv4/netfilter/iptable_raw.c b/net/ipv4/netfilter/iptable_raw.c index 0356e6da4bb7..1ba02811acb0 100644 --- a/net/ipv4/netfilter/iptable_raw.c +++ b/net/ipv4/netfilter/iptable_raw.c @@ -20,19 +20,16 @@ static const struct xt_table packet_raw = { /* The work comes in here from netfilter.c. */ static unsigned int -iptable_raw_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, +iptable_raw_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - const struct net *net; - - if (ops->hooknum == NF_INET_LOCAL_OUT && + if (state->hook == NF_INET_LOCAL_OUT && (skb->len < sizeof(struct iphdr) || ip_hdrlen(skb) < sizeof(struct iphdr))) /* root is playing with raw sockets. */ return NF_ACCEPT; - net = dev_net(state->in ? state->in : state->out); - return ipt_do_table(skb, ops->hooknum, state, net->ipv4.iptable_raw); + return ipt_do_table(skb, state, state->net->ipv4.iptable_raw); } static struct nf_hook_ops *rawtable_ops __read_mostly; diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c index 4bce3980ccd9..f534e2f05bad 100644 --- a/net/ipv4/netfilter/iptable_security.c +++ b/net/ipv4/netfilter/iptable_security.c @@ -37,20 +37,16 @@ static const struct xt_table security_table = { }; static unsigned int -iptable_security_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, +iptable_security_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - const struct net *net; - - if (ops->hooknum == NF_INET_LOCAL_OUT && + if (state->hook == NF_INET_LOCAL_OUT && (skb->len < sizeof(struct iphdr) || ip_hdrlen(skb) < sizeof(struct iphdr))) /* Somebody is playing with raw sockets. */ return NF_ACCEPT; - net = dev_net(state->in ? state->in : state->out); - return ipt_do_table(skb, ops->hooknum, state, - net->ipv4.iptable_security); + return ipt_do_table(skb, state, state->net->ipv4.iptable_security); } static struct nf_hook_ops *sectbl_ops __read_mostly; diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 8a2caaf3940b..752fb40adcf8 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -92,7 +92,7 @@ static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, return NF_ACCEPT; } -static unsigned int ipv4_helper(const struct nf_hook_ops *ops, +static unsigned int ipv4_helper(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -119,7 +119,7 @@ static unsigned int ipv4_helper(const struct nf_hook_ops *ops, ct, ctinfo); } -static unsigned int ipv4_confirm(const struct nf_hook_ops *ops, +static unsigned int ipv4_confirm(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -143,14 +143,14 @@ out: return nf_conntrack_confirm(skb); } -static unsigned int ipv4_conntrack_in(const struct nf_hook_ops *ops, +static unsigned int ipv4_conntrack_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_conntrack_in(dev_net(state->in), PF_INET, ops->hooknum, skb); + return nf_conntrack_in(state->net, PF_INET, state->hook, skb); } -static unsigned int ipv4_conntrack_local(const struct nf_hook_ops *ops, +static unsigned int ipv4_conntrack_local(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -158,7 +158,7 @@ static unsigned int ipv4_conntrack_local(const struct nf_hook_ops *ops, if (skb->len < sizeof(struct iphdr) || ip_hdrlen(skb) < sizeof(struct iphdr)) return NF_ACCEPT; - return nf_conntrack_in(dev_net(state->out), PF_INET, ops->hooknum, skb); + return nf_conntrack_in(state->net, PF_INET, state->hook, skb); } /* Connection tracking may drop packets, but never alters them, so diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c index cdde3ec496e9..c567e1b5d799 100644 --- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c @@ -30,7 +30,7 @@ static inline struct nf_icmp_net *icmp_pernet(struct net *net) } static bool icmp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, - struct nf_conntrack_tuple *tuple) + struct net *net, struct nf_conntrack_tuple *tuple) { const struct icmphdr *hp; struct icmphdr _hdr; @@ -144,7 +144,7 @@ icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb) + ip_hdrlen(skb) + sizeof(struct icmphdr), - PF_INET, &origtuple)) { + PF_INET, net, &origtuple)) { pr_debug("icmp_error_message: failed to get tuple\n"); return -NF_ACCEPT; } diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index 9306ec4fab41..b246346ee849 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -61,7 +61,7 @@ static enum ip_defrag_users nf_ct_defrag_user(unsigned int hooknum, return IP_DEFRAG_CONNTRACK_OUT + zone_id; } -static unsigned int ipv4_conntrack_defrag(const struct nf_hook_ops *ops, +static unsigned int ipv4_conntrack_defrag(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -83,7 +83,7 @@ static unsigned int ipv4_conntrack_defrag(const struct nf_hook_ops *ops, /* Gather fragments. */ if (ip_is_fragment(ip_hdr(skb))) { enum ip_defrag_users user = - nf_ct_defrag_user(ops->hooknum, skb); + nf_ct_defrag_user(state->hook, skb); if (nf_ct_ipv4_gather_frags(skb, user)) return NF_STOLEN; diff --git a/net/ipv4/netfilter/nf_dup_ipv4.c b/net/ipv4/netfilter/nf_dup_ipv4.c index 2d79e6e8d934..ce2a59e5c665 100644 --- a/net/ipv4/netfilter/nf_dup_ipv4.c +++ b/net/ipv4/netfilter/nf_dup_ipv4.c @@ -23,25 +23,10 @@ #include <net/netfilter/nf_conntrack.h> #endif -static struct net *pick_net(struct sk_buff *skb) -{ -#ifdef CONFIG_NET_NS - const struct dst_entry *dst; - - if (skb->dev != NULL) - return dev_net(skb->dev); - dst = skb_dst(skb); - if (dst != NULL && dst->dev != NULL) - return dev_net(dst->dev); -#endif - return &init_net; -} - -static bool nf_dup_ipv4_route(struct sk_buff *skb, const struct in_addr *gw, - int oif) +static bool nf_dup_ipv4_route(struct net *net, struct sk_buff *skb, + const struct in_addr *gw, int oif) { const struct iphdr *iph = ip_hdr(skb); - struct net *net = pick_net(skb); struct rtable *rt; struct flowi4 fl4; @@ -65,7 +50,7 @@ static bool nf_dup_ipv4_route(struct sk_buff *skb, const struct in_addr *gw, return true; } -void nf_dup_ipv4(struct sk_buff *skb, unsigned int hooknum, +void nf_dup_ipv4(struct net *net, struct sk_buff *skb, unsigned int hooknum, const struct in_addr *gw, int oif) { struct iphdr *iph; @@ -105,7 +90,7 @@ void nf_dup_ipv4(struct sk_buff *skb, unsigned int hooknum, --iph->ttl; ip_send_check(iph); - if (nf_dup_ipv4_route(skb, gw, oif)) { + if (nf_dup_ipv4_route(net, skb, gw, oif)) { __this_cpu_write(nf_skb_duplicated, true); ip_local_out(skb); __this_cpu_write(nf_skb_duplicated, false); diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c index 22f4579b0c2a..5075b7ecd26d 100644 --- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c @@ -255,9 +255,9 @@ int nf_nat_icmp_reply_translation(struct sk_buff *skb, EXPORT_SYMBOL_GPL(nf_nat_icmp_reply_translation); unsigned int -nf_nat_ipv4_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, +nf_nat_ipv4_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)) @@ -266,7 +266,7 @@ nf_nat_ipv4_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, enum ip_conntrack_info ctinfo; struct nf_conn_nat *nat; /* maniptype == SRC for postrouting. */ - enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum); + enum nf_nat_manip_type maniptype = HOOK2MANIP(state->hook); /* We never see fragments: conntrack defrags on pre-routing * and local-out, and nf_nat_out protects post-routing. @@ -295,7 +295,7 @@ nf_nat_ipv4_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, case IP_CT_RELATED_REPLY: if (ip_hdr(skb)->protocol == IPPROTO_ICMP) { if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo, - ops->hooknum)) + state->hook)) return NF_DROP; else return NF_ACCEPT; @@ -308,21 +308,21 @@ nf_nat_ipv4_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, if (!nf_nat_initialized(ct, maniptype)) { unsigned int ret; - ret = do_chain(ops, skb, state, ct); + ret = do_chain(priv, skb, state, ct); if (ret != NF_ACCEPT) return ret; - if (nf_nat_initialized(ct, HOOK2MANIP(ops->hooknum))) + if (nf_nat_initialized(ct, HOOK2MANIP(state->hook))) break; - ret = nf_nat_alloc_null_binding(ct, ops->hooknum); + ret = nf_nat_alloc_null_binding(ct, state->hook); if (ret != NF_ACCEPT) return ret; } else { pr_debug("Already setup manip %s for ct %p\n", maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST", ct); - if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, + if (nf_nat_oif_changed(state->hook, ctinfo, nat, state->out)) goto oif_changed; } @@ -332,11 +332,11 @@ nf_nat_ipv4_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, /* ESTABLISHED */ NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED || ctinfo == IP_CT_ESTABLISHED_REPLY); - if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, state->out)) + if (nf_nat_oif_changed(state->hook, ctinfo, nat, state->out)) goto oif_changed; } - return nf_nat_packet(ct, ctinfo, ops->hooknum, skb); + return nf_nat_packet(ct, ctinfo, state->hook, skb); oif_changed: nf_ct_kill_acct(ct, ctinfo, skb); @@ -345,9 +345,9 @@ oif_changed: EXPORT_SYMBOL_GPL(nf_nat_ipv4_fn); unsigned int -nf_nat_ipv4_in(const struct nf_hook_ops *ops, struct sk_buff *skb, +nf_nat_ipv4_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)) @@ -355,7 +355,7 @@ nf_nat_ipv4_in(const struct nf_hook_ops *ops, struct sk_buff *skb, unsigned int ret; __be32 daddr = ip_hdr(skb)->daddr; - ret = nf_nat_ipv4_fn(ops, skb, state, do_chain); + ret = nf_nat_ipv4_fn(priv, skb, state, do_chain); if (ret != NF_DROP && ret != NF_STOLEN && daddr != ip_hdr(skb)->daddr) skb_dst_drop(skb); @@ -365,9 +365,9 @@ nf_nat_ipv4_in(const struct nf_hook_ops *ops, struct sk_buff *skb, EXPORT_SYMBOL_GPL(nf_nat_ipv4_in); unsigned int -nf_nat_ipv4_out(const struct nf_hook_ops *ops, struct sk_buff *skb, +nf_nat_ipv4_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)) @@ -384,7 +384,7 @@ nf_nat_ipv4_out(const struct nf_hook_ops *ops, struct sk_buff *skb, ip_hdrlen(skb) < sizeof(struct iphdr)) return NF_ACCEPT; - ret = nf_nat_ipv4_fn(ops, skb, state, do_chain); + ret = nf_nat_ipv4_fn(priv, skb, state, do_chain); #ifdef CONFIG_XFRM if (ret != NF_DROP && ret != NF_STOLEN && !(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) && @@ -396,7 +396,7 @@ nf_nat_ipv4_out(const struct nf_hook_ops *ops, struct sk_buff *skb, (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP && ct->tuplehash[dir].tuple.src.u.all != ct->tuplehash[!dir].tuple.dst.u.all)) { - err = nf_xfrm_me_harder(skb, AF_INET); + err = nf_xfrm_me_harder(state->net, skb, AF_INET); if (err < 0) ret = NF_DROP_ERR(err); } @@ -407,9 +407,9 @@ nf_nat_ipv4_out(const struct nf_hook_ops *ops, struct sk_buff *skb, EXPORT_SYMBOL_GPL(nf_nat_ipv4_out); unsigned int -nf_nat_ipv4_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, +nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)) @@ -424,14 +424,14 @@ nf_nat_ipv4_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, ip_hdrlen(skb) < sizeof(struct iphdr)) return NF_ACCEPT; - ret = nf_nat_ipv4_fn(ops, skb, state, do_chain); + ret = nf_nat_ipv4_fn(priv, skb, state, do_chain); if (ret != NF_DROP && ret != NF_STOLEN && (ct = nf_ct_get(skb, &ctinfo)) != NULL) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); if (ct->tuplehash[dir].tuple.dst.u3.ip != ct->tuplehash[!dir].tuple.src.u3.ip) { - err = ip_route_me_harder(skb, RTN_UNSPEC); + err = ip_route_me_harder(state->net, skb, RTN_UNSPEC); if (err < 0) ret = NF_DROP_ERR(err); } @@ -440,7 +440,7 @@ nf_nat_ipv4_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP && ct->tuplehash[dir].tuple.dst.u.all != ct->tuplehash[!dir].tuple.src.u.all) { - err = nf_xfrm_me_harder(skb, AF_INET); + err = nf_xfrm_me_harder(state->net, skb, AF_INET); if (err < 0) ret = NF_DROP_ERR(err); } diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index 3262e41ff76f..2f5e925d3264 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -99,7 +99,7 @@ void nf_reject_ip_tcphdr_put(struct sk_buff *nskb, const struct sk_buff *oldskb, EXPORT_SYMBOL_GPL(nf_reject_ip_tcphdr_put); /* Send RST reply */ -void nf_send_reset(struct sk_buff *oldskb, int hook) +void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook) { struct sk_buff *nskb; const struct iphdr *oiph; @@ -129,7 +129,7 @@ void nf_send_reset(struct sk_buff *oldskb, int hook) ip4_dst_hoplimit(skb_dst(nskb))); nf_reject_ip_tcphdr_put(nskb, oldskb, oth); - if (ip_route_me_harder(nskb, RTN_UNSPEC)) + if (ip_route_me_harder(net, nskb, RTN_UNSPEC)) goto free_nskb; /* "Never happens" */ diff --git a/net/ipv4/netfilter/nf_tables_arp.c b/net/ipv4/netfilter/nf_tables_arp.c index 8412268bbad1..9d09d4f59545 100644 --- a/net/ipv4/netfilter/nf_tables_arp.c +++ b/net/ipv4/netfilter/nf_tables_arp.c @@ -15,15 +15,15 @@ #include <net/netfilter/nf_tables.h> static unsigned int -nft_do_chain_arp(const struct nf_hook_ops *ops, +nft_do_chain_arp(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nft_pktinfo pkt; - nft_set_pktinfo(&pkt, ops, skb, state); + nft_set_pktinfo(&pkt, skb, state); - return nft_do_chain(&pkt, ops); + return nft_do_chain(&pkt, priv); } static struct nft_af_info nft_af_arp __read_mostly = { diff --git a/net/ipv4/netfilter/nf_tables_ipv4.c b/net/ipv4/netfilter/nf_tables_ipv4.c index aa180d3a69a5..ca9dc3c46c4f 100644 --- a/net/ipv4/netfilter/nf_tables_ipv4.c +++ b/net/ipv4/netfilter/nf_tables_ipv4.c @@ -18,18 +18,18 @@ #include <net/ip.h> #include <net/netfilter/nf_tables_ipv4.h> -static unsigned int nft_do_chain_ipv4(const struct nf_hook_ops *ops, +static unsigned int nft_do_chain_ipv4(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nft_pktinfo pkt; - nft_set_pktinfo_ipv4(&pkt, ops, skb, state); + nft_set_pktinfo_ipv4(&pkt, skb, state); - return nft_do_chain(&pkt, ops); + return nft_do_chain(&pkt, priv); } -static unsigned int nft_ipv4_output(const struct nf_hook_ops *ops, +static unsigned int nft_ipv4_output(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -41,7 +41,7 @@ static unsigned int nft_ipv4_output(const struct nf_hook_ops *ops, return NF_ACCEPT; } - return nft_do_chain_ipv4(ops, skb, state); + return nft_do_chain_ipv4(priv, skb, state); } struct nft_af_info nft_af_ipv4 __read_mostly = { diff --git a/net/ipv4/netfilter/nft_chain_nat_ipv4.c b/net/ipv4/netfilter/nft_chain_nat_ipv4.c index bf5c30ae14e4..f5c66a7a4bf2 100644 --- a/net/ipv4/netfilter/nft_chain_nat_ipv4.c +++ b/net/ipv4/netfilter/nft_chain_nat_ipv4.c @@ -26,44 +26,44 @@ #include <net/netfilter/nf_nat_l3proto.h> #include <net/ip.h> -static unsigned int nft_nat_do_chain(const struct nf_hook_ops *ops, +static unsigned int nft_nat_do_chain(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct) { struct nft_pktinfo pkt; - nft_set_pktinfo_ipv4(&pkt, ops, skb, state); + nft_set_pktinfo_ipv4(&pkt, skb, state); - return nft_do_chain(&pkt, ops); + return nft_do_chain(&pkt, priv); } -static unsigned int nft_nat_ipv4_fn(const struct nf_hook_ops *ops, +static unsigned int nft_nat_ipv4_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_nat_ipv4_fn(ops, skb, state, nft_nat_do_chain); + return nf_nat_ipv4_fn(priv, skb, state, nft_nat_do_chain); } -static unsigned int nft_nat_ipv4_in(const struct nf_hook_ops *ops, +static unsigned int nft_nat_ipv4_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_nat_ipv4_in(ops, skb, state, nft_nat_do_chain); + return nf_nat_ipv4_in(priv, skb, state, nft_nat_do_chain); } -static unsigned int nft_nat_ipv4_out(const struct nf_hook_ops *ops, +static unsigned int nft_nat_ipv4_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_nat_ipv4_out(ops, skb, state, nft_nat_do_chain); + return nf_nat_ipv4_out(priv, skb, state, nft_nat_do_chain); } -static unsigned int nft_nat_ipv4_local_fn(const struct nf_hook_ops *ops, +static unsigned int nft_nat_ipv4_local_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_nat_ipv4_local_fn(ops, skb, state, nft_nat_do_chain); + return nf_nat_ipv4_local_fn(priv, skb, state, nft_nat_do_chain); } static const struct nf_chain_type nft_chain_nat_ipv4 = { diff --git a/net/ipv4/netfilter/nft_chain_route_ipv4.c b/net/ipv4/netfilter/nft_chain_route_ipv4.c index e335b0afdaf3..2375b0a8be46 100644 --- a/net/ipv4/netfilter/nft_chain_route_ipv4.c +++ b/net/ipv4/netfilter/nft_chain_route_ipv4.c @@ -21,7 +21,7 @@ #include <net/route.h> #include <net/ip.h> -static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops, +static unsigned int nf_route_table_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -37,7 +37,7 @@ static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops, ip_hdrlen(skb) < sizeof(struct iphdr)) return NF_ACCEPT; - nft_set_pktinfo_ipv4(&pkt, ops, skb, state); + nft_set_pktinfo_ipv4(&pkt, skb, state); mark = skb->mark; iph = ip_hdr(skb); @@ -45,7 +45,7 @@ static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops, daddr = iph->daddr; tos = iph->tos; - ret = nft_do_chain(&pkt, ops); + ret = nft_do_chain(&pkt, priv); if (ret != NF_DROP && ret != NF_QUEUE) { iph = ip_hdr(skb); @@ -53,7 +53,7 @@ static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops, iph->daddr != daddr || skb->mark != mark || iph->tos != tos) - if (ip_route_me_harder(skb, RTN_UNSPEC)) + if (ip_route_me_harder(state->net, skb, RTN_UNSPEC)) ret = NF_DROP; } return ret; diff --git a/net/ipv4/netfilter/nft_dup_ipv4.c b/net/ipv4/netfilter/nft_dup_ipv4.c index b45932d43b69..bf855e64fc45 100644 --- a/net/ipv4/netfilter/nft_dup_ipv4.c +++ b/net/ipv4/netfilter/nft_dup_ipv4.c @@ -30,7 +30,7 @@ static void nft_dup_ipv4_eval(const struct nft_expr *expr, }; int oif = regs->data[priv->sreg_dev]; - nf_dup_ipv4(pkt->skb, pkt->ops->hooknum, &gw, oif); + nf_dup_ipv4(pkt->net, pkt->skb, pkt->hook, &gw, oif); } static int nft_dup_ipv4_init(const struct nft_ctx *ctx, diff --git a/net/ipv4/netfilter/nft_masq_ipv4.c b/net/ipv4/netfilter/nft_masq_ipv4.c index 40e414c4ca56..b72ffc58e255 100644 --- a/net/ipv4/netfilter/nft_masq_ipv4.c +++ b/net/ipv4/netfilter/nft_masq_ipv4.c @@ -26,7 +26,7 @@ static void nft_masq_ipv4_eval(const struct nft_expr *expr, memset(&range, 0, sizeof(range)); range.flags = priv->flags; - regs->verdict.code = nf_nat_masquerade_ipv4(pkt->skb, pkt->ops->hooknum, + regs->verdict.code = nf_nat_masquerade_ipv4(pkt->skb, pkt->hook, &range, pkt->out); } diff --git a/net/ipv4/netfilter/nft_redir_ipv4.c b/net/ipv4/netfilter/nft_redir_ipv4.c index d8d795df9c13..c09d4381427e 100644 --- a/net/ipv4/netfilter/nft_redir_ipv4.c +++ b/net/ipv4/netfilter/nft_redir_ipv4.c @@ -36,7 +36,7 @@ static void nft_redir_ipv4_eval(const struct nft_expr *expr, mr.range[0].flags |= priv->flags; regs->verdict.code = nf_nat_redirect_ipv4(pkt->skb, &mr, - pkt->ops->hooknum); + pkt->hook); } static struct nft_expr_type nft_redir_ipv4_type; diff --git a/net/ipv4/netfilter/nft_reject_ipv4.c b/net/ipv4/netfilter/nft_reject_ipv4.c index b07e58b51158..c24f41c816b3 100644 --- a/net/ipv4/netfilter/nft_reject_ipv4.c +++ b/net/ipv4/netfilter/nft_reject_ipv4.c @@ -27,11 +27,10 @@ static void nft_reject_ipv4_eval(const struct nft_expr *expr, switch (priv->type) { case NFT_REJECT_ICMP_UNREACH: - nf_send_unreach(pkt->skb, priv->icmp_code, - pkt->ops->hooknum); + nf_send_unreach(pkt->skb, priv->icmp_code, pkt->hook); break; case NFT_REJECT_TCP_RST: - nf_send_reset(pkt->skb, pkt->ops->hooknum); + nf_send_reset(pkt->net, pkt->skb, pkt->hook); break; default: break; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 561cd4b8fc6e..28ef8a913130 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -411,8 +411,9 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, icmp_out_count(net, ((struct icmphdr *) skb_transport_header(skb))->type); - err = NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_OUT, sk, skb, - NULL, rt->dst.dev, dst_output_sk); + err = NF_HOOK(NFPROTO_IPV4, NF_INET_LOCAL_OUT, + net, sk, skb, NULL, rt->dst.dev, + dst_output_okfn); if (err > 0) err = net_xmit_errno(err); if (err) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index c81deb85acb4..76ca4e75f785 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -112,7 +112,7 @@ #endif #include <net/secure_seq.h> #include <net/ip_tunnels.h> -#include <net/vrf.h> +#include <net/l3mdev.h> #define RT_FL_TOS(oldflp4) \ ((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK)) @@ -847,7 +847,7 @@ void ip_rt_send_redirect(struct sk_buff *skb) return; } log_martians = IN_DEV_LOG_MARTIANS(in_dev); - vif = vrf_master_ifindex_rcu(rt->dst.dev); + vif = l3mdev_master_ifindex_rcu(rt->dst.dev); rcu_read_unlock(); net = dev_net(rt->dst.dev); @@ -941,7 +941,7 @@ static int ip_error(struct sk_buff *skb) } peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, - vrf_master_ifindex(skb->dev), 1); + l3mdev_master_ifindex(skb->dev), 1); send = true; if (peer) { @@ -1438,12 +1438,34 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr, } static struct rtable *rt_dst_alloc(struct net_device *dev, + unsigned int flags, u16 type, bool nopolicy, bool noxfrm, bool will_cache) { - return dst_alloc(&ipv4_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK, - (will_cache ? 0 : (DST_HOST | DST_NOCACHE)) | - (nopolicy ? DST_NOPOLICY : 0) | - (noxfrm ? DST_NOXFRM : 0)); + struct rtable *rt; + + rt = dst_alloc(&ipv4_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK, + (will_cache ? 0 : (DST_HOST | DST_NOCACHE)) | + (nopolicy ? DST_NOPOLICY : 0) | + (noxfrm ? DST_NOXFRM : 0)); + + if (rt) { + rt->rt_genid = rt_genid_ipv4(dev_net(dev)); + rt->rt_flags = flags; + rt->rt_type = type; + rt->rt_is_input = 0; + rt->rt_iif = 0; + rt->rt_pmtu = 0; + rt->rt_gateway = 0; + rt->rt_uses_gateway = 0; + rt->rt_table_id = 0; + INIT_LIST_HEAD(&rt->rt_uncached); + + rt->dst.output = ip_output; + if (flags & RTCF_LOCAL) + rt->dst.input = ip_local_deliver; + } + + return rt; } /* called in rcu_read_lock() section */ @@ -1452,6 +1474,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, { struct rtable *rth; struct in_device *in_dev = __in_dev_get_rcu(dev); + unsigned int flags = RTCF_MULTICAST; u32 itag = 0; int err; @@ -1464,9 +1487,8 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, skb->protocol != htons(ETH_P_IP)) goto e_inval; - if (likely(!IN_DEV_ROUTE_LOCALNET(in_dev))) - if (ipv4_is_loopback(saddr)) - goto e_inval; + if (ipv4_is_loopback(saddr) && !IN_DEV_ROUTE_LOCALNET(in_dev)) + goto e_inval; if (ipv4_is_zeronet(saddr)) { if (!ipv4_is_local_multicast(daddr)) @@ -1477,7 +1499,10 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (err < 0) goto e_err; } - rth = rt_dst_alloc(dev_net(dev)->loopback_dev, + if (our) + flags |= RTCF_LOCAL; + + rth = rt_dst_alloc(dev_net(dev)->loopback_dev, flags, RTN_MULTICAST, IN_DEV_CONF_GET(in_dev, NOPOLICY), false, false); if (!rth) goto e_nobufs; @@ -1486,20 +1511,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, rth->dst.tclassid = itag; #endif rth->dst.output = ip_rt_bug; - - rth->rt_genid = rt_genid_ipv4(dev_net(dev)); - rth->rt_flags = RTCF_MULTICAST; - rth->rt_type = RTN_MULTICAST; rth->rt_is_input= 1; - rth->rt_iif = 0; - rth->rt_pmtu = 0; - rth->rt_gateway = 0; - rth->rt_uses_gateway = 0; - INIT_LIST_HEAD(&rth->rt_uncached); - if (our) { - rth->dst.input= ip_local_deliver; - rth->rt_flags |= RTCF_LOCAL; - } #ifdef CONFIG_IP_MROUTE if (!ipv4_is_local_multicast(daddr) && IN_DEV_MFORWARD(in_dev)) @@ -1608,7 +1620,7 @@ static int __mkroute_input(struct sk_buff *skb, } } - rth = rt_dst_alloc(out_dev->dev, + rth = rt_dst_alloc(out_dev->dev, 0, res->type, IN_DEV_CONF_GET(in_dev, NOPOLICY), IN_DEV_CONF_GET(out_dev, NOXFRM), do_cache); if (!rth) { @@ -1616,19 +1628,12 @@ static int __mkroute_input(struct sk_buff *skb, goto cleanup; } - rth->rt_genid = rt_genid_ipv4(dev_net(rth->dst.dev)); - rth->rt_flags = 0; - rth->rt_type = res->type; rth->rt_is_input = 1; - rth->rt_iif = 0; - rth->rt_pmtu = 0; - rth->rt_gateway = 0; - rth->rt_uses_gateway = 0; - INIT_LIST_HEAD(&rth->rt_uncached); + if (res->table) + rth->rt_table_id = res->table->tb_id; RT_CACHE_STAT_INC(in_slow_tot); rth->dst.input = ip_forward; - rth->dst.output = ip_output; rt_set_nexthop(rth, daddr, res, fnhe, res->fi, res->type, itag); if (lwtunnel_output_redirect(rth->dst.lwtstate)) { @@ -1706,6 +1711,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, goto martian_source; res.fi = NULL; + res.table = NULL; if (ipv4_is_lbcast(daddr) || (saddr == 0 && daddr == 0)) goto brd_input; @@ -1733,7 +1739,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, * Now we are ready to route packet. */ fl4.flowi4_oif = 0; - fl4.flowi4_iif = vrf_master_ifindex_rcu(dev) ? : dev->ifindex; + fl4.flowi4_iif = l3mdev_fib_oif_rcu(dev); fl4.flowi4_mark = skb->mark; fl4.flowi4_tos = tos; fl4.flowi4_scope = RT_SCOPE_UNIVERSE; @@ -1754,7 +1760,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, err = fib_validate_source(skb, saddr, daddr, tos, 0, dev, in_dev, &itag); if (err < 0) - goto martian_source_keep_err; + goto martian_source; goto local_input; } @@ -1776,7 +1782,7 @@ brd_input: err = fib_validate_source(skb, saddr, 0, tos, 0, dev, in_dev, &itag); if (err < 0) - goto martian_source_keep_err; + goto martian_source; } flags |= RTCF_BROADCAST; res.type = RTN_BROADCAST; @@ -1796,26 +1802,18 @@ local_input: } } - rth = rt_dst_alloc(net->loopback_dev, + rth = rt_dst_alloc(net->loopback_dev, flags | RTCF_LOCAL, res.type, IN_DEV_CONF_GET(in_dev, NOPOLICY), false, do_cache); if (!rth) goto e_nobufs; - rth->dst.input= ip_local_deliver; rth->dst.output= ip_rt_bug; #ifdef CONFIG_IP_ROUTE_CLASSID rth->dst.tclassid = itag; #endif - - rth->rt_genid = rt_genid_ipv4(net); - rth->rt_flags = flags|RTCF_LOCAL; - rth->rt_type = res.type; rth->rt_is_input = 1; - rth->rt_iif = 0; - rth->rt_pmtu = 0; - rth->rt_gateway = 0; - rth->rt_uses_gateway = 0; - INIT_LIST_HEAD(&rth->rt_uncached); + if (res.table) + rth->rt_table_id = res.table->tb_id; RT_CACHE_STAT_INC(in_slow_tot); if (res.type == RTN_UNREACHABLE) { @@ -1837,6 +1835,7 @@ no_route: RT_CACHE_STAT_INC(in_no_route); res.type = RTN_UNREACHABLE; res.fi = NULL; + res.table = NULL; goto local_input; /* @@ -1859,8 +1858,6 @@ e_nobufs: goto out; martian_source: - err = -EINVAL; -martian_source_keep_err: ip_handle_martian_source(dev, in_dev, skb, daddr, saddr); goto out; } @@ -1988,28 +1985,19 @@ static struct rtable *__mkroute_output(const struct fib_result *res, } add: - rth = rt_dst_alloc(dev_out, + rth = rt_dst_alloc(dev_out, flags, type, IN_DEV_CONF_GET(in_dev, NOPOLICY), IN_DEV_CONF_GET(in_dev, NOXFRM), do_cache); if (!rth) return ERR_PTR(-ENOBUFS); - rth->dst.output = ip_output; - - rth->rt_genid = rt_genid_ipv4(dev_net(dev_out)); - rth->rt_flags = flags; - rth->rt_type = type; - rth->rt_is_input = 0; rth->rt_iif = orig_oif ? : 0; - rth->rt_pmtu = 0; - rth->rt_gateway = 0; - rth->rt_uses_gateway = 0; - INIT_LIST_HEAD(&rth->rt_uncached); + if (res->table) + rth->rt_table_id = res->table->tb_id; + RT_CACHE_STAT_INC(out_slow_tot); - if (flags & RTCF_LOCAL) - rth->dst.input = ip_local_deliver; if (flags & (RTCF_BROADCAST | RTCF_MULTICAST)) { if (flags & RTCF_LOCAL && !(dev_out->flags & IFF_LOOPBACK)) { @@ -2137,11 +2125,10 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) fl4->saddr = inet_select_addr(dev_out, 0, RT_SCOPE_HOST); } - if (netif_is_vrf(dev_out) && - !(fl4->flowi4_flags & FLOWI_FLAG_VRFSRC)) { - rth = vrf_dev_get_rth(dev_out); + + rth = l3mdev_get_rtable(dev_out, fl4); + if (rth) goto out; - } } if (!fl4->daddr) { @@ -2303,7 +2290,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or } struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4, - struct sock *sk) + const struct sock *sk) { struct rtable *rt = __ip_route_output_key(net, flp4); @@ -2319,7 +2306,7 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4, } EXPORT_SYMBOL_GPL(ip_route_output_flow); -static int rt_fill_info(struct net *net, __be32 dst, __be32 src, +static int rt_fill_info(struct net *net, __be32 dst, __be32 src, u32 table_id, struct flowi4 *fl4, struct sk_buff *skb, u32 portid, u32 seq, int event, int nowait, unsigned int flags) { @@ -2339,8 +2326,8 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, r->rtm_dst_len = 32; r->rtm_src_len = 0; r->rtm_tos = fl4->flowi4_tos; - r->rtm_table = RT_TABLE_MAIN; - if (nla_put_u32(skb, RTA_TABLE, RT_TABLE_MAIN)) + r->rtm_table = table_id; + if (nla_put_u32(skb, RTA_TABLE, table_id)) goto nla_put_failure; r->rtm_type = rt->rt_type; r->rtm_scope = RT_SCOPE_UNIVERSE; @@ -2445,6 +2432,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh) int err; int mark; struct sk_buff *skb; + u32 table_id = RT_TABLE_MAIN; err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy); if (err < 0) @@ -2514,7 +2502,10 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh) if (rtm->rtm_flags & RTM_F_NOTIFY) rt->rt_flags |= RTCF_NOTIFY; - err = rt_fill_info(net, dst, src, &fl4, skb, + if (rtm->rtm_flags & RTM_F_LOOKUP_TABLE) + table_id = rt->rt_table_id; + + err = rt_fill_info(net, dst, src, table_id, &fl4, skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, RTM_NEWROUTE, 0, 0); if (err < 0) diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index d70b1f603692..6b97b5f6457c 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -192,15 +192,11 @@ u32 __cookie_v4_init_sequence(const struct iphdr *iph, const struct tcphdr *th, } EXPORT_SYMBOL_GPL(__cookie_v4_init_sequence); -__u32 cookie_v4_init_sequence(struct sock *sk, const struct sk_buff *skb, - __u16 *mssp) +__u32 cookie_v4_init_sequence(const struct sk_buff *skb, __u16 *mssp) { const struct iphdr *iph = ip_hdr(skb); const struct tcphdr *th = tcp_hdr(skb); - tcp_synq_overflow(sk); - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESSENT); - return __cookie_v4_init_sequence(iph, th, mssp); } @@ -345,7 +341,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) ireq->wscale_ok = tcp_opt.wscale_ok; ireq->tstamp_ok = tcp_opt.saw_tstamp; req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; - treq->snt_synack = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsecr : 0; + treq->snt_synack.v64 = 0; treq->tfo_listener = false; ireq->ir_iif = sk->sk_bound_dev_if; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b8b8fa184f75..3c96fa87ff9e 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2253,13 +2253,6 @@ int tcp_disconnect(struct sock *sk, int flags) } EXPORT_SYMBOL(tcp_disconnect); -void tcp_sock_destruct(struct sock *sk) -{ - inet_sock_destruct(sk); - - kfree(inet_csk(sk)->icsk_accept_queue.fastopenq); -} - static inline bool tcp_can_repair_sock(const struct sock *sk) { return ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN) && @@ -2581,7 +2574,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, TCPF_LISTEN))) { tcp_fastopen_init_key_once(true); - err = fastopen_init_queue(sk, val); + fastopen_queue_tune(sk, val); } else { err = -EINVAL; } @@ -2849,10 +2842,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level, break; case TCP_FASTOPEN: - if (icsk->icsk_accept_queue.fastopenq) - val = icsk->icsk_accept_queue.fastopenq->max_qlen; - else - val = 0; + val = icsk->icsk_accept_queue.fastopenq.max_qlen; break; case TCP_TIMESTAMP: diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 93c4dc3ab23f..882caa4e72bc 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -173,6 +173,10 @@ out: */ if (ca->get_info) memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); + if (ca->flags & TCP_CONG_NEEDS_ECN) + INET_ECN_xmit(sk); + else + INET_ECN_dontxmit(sk); } void tcp_init_congestion_control(struct sock *sk) @@ -181,6 +185,10 @@ void tcp_init_congestion_control(struct sock *sk) if (icsk->icsk_ca_ops->init) icsk->icsk_ca_ops->init(sk); + if (tcp_ca_needs_ecn(sk)) + INET_ECN_xmit(sk); + else + INET_ECN_dontxmit(sk); } static void tcp_reinit_congestion_control(struct sock *sk, @@ -192,8 +200,8 @@ static void tcp_reinit_congestion_control(struct sock *sk, icsk->icsk_ca_ops = ca; icsk->icsk_ca_setsockopt = 1; - if (sk->sk_state != TCP_CLOSE && icsk->icsk_ca_ops->init) - icsk->icsk_ca_ops->init(sk); + if (sk->sk_state != TCP_CLOSE) + tcp_init_congestion_control(sk); } /* Manage refcounts on socket close. */ diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index f9c0fb84e435..f69f436fcbcc 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -124,10 +124,10 @@ static bool tcp_fastopen_cookie_gen(struct request_sock *req, return false; } -static bool tcp_fastopen_create_child(struct sock *sk, - struct sk_buff *skb, - struct dst_entry *dst, - struct request_sock *req) +static struct sock *tcp_fastopen_create_child(struct sock *sk, + struct sk_buff *skb, + struct dst_entry *dst, + struct request_sock *req) { struct tcp_sock *tp; struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; @@ -140,11 +140,11 @@ static bool tcp_fastopen_create_child(struct sock *sk, child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL); if (!child) - return false; + return NULL; - spin_lock(&queue->fastopenq->lock); - queue->fastopenq->qlen++; - spin_unlock(&queue->fastopenq->lock); + spin_lock(&queue->fastopenq.lock); + queue->fastopenq.qlen++; + spin_unlock(&queue->fastopenq.lock); /* Initialize the child socket. Have to fix some values to take * into account the child is a Fast Open socket and is created @@ -216,9 +216,11 @@ static bool tcp_fastopen_create_child(struct sock *sk, tcp_rsk(req)->rcv_nxt = tp->rcv_nxt = end_seq; sk->sk_data_ready(sk); bh_unlock_sock(child); - sock_put(child); + /* Note: sock_put(child) will be done by tcp_conn_request() + * after SYNACK packet is sent. + */ WARN_ON(!req->sk); - return true; + return child; } static bool tcp_fastopen_queue_check(struct sock *sk) @@ -235,8 +237,8 @@ static bool tcp_fastopen_queue_check(struct sock *sk) * between qlen overflow causing Fast Open to be disabled * temporarily vs a server not supporting Fast Open at all. */ - fastopenq = inet_csk(sk)->icsk_accept_queue.fastopenq; - if (!fastopenq || fastopenq->max_qlen == 0) + fastopenq = &inet_csk(sk)->icsk_accept_queue.fastopenq; + if (fastopenq->max_qlen == 0) return false; if (fastopenq->qlen >= fastopenq->max_qlen) { @@ -261,13 +263,14 @@ static bool tcp_fastopen_queue_check(struct sock *sk) * may be updated and return the client in the SYN-ACK later. E.g., Fast Open * cookie request (foc->len == 0). */ -bool tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, - struct request_sock *req, - struct tcp_fastopen_cookie *foc, - struct dst_entry *dst) +struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct tcp_fastopen_cookie *foc, + struct dst_entry *dst) { struct tcp_fastopen_cookie valid_foc = { .len = -1 }; bool syn_data = TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1; + struct sock *child; if (foc->len == 0) /* Client requests a cookie */ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENCOOKIEREQD); @@ -276,7 +279,7 @@ bool tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, (syn_data || foc->len >= 0) && tcp_fastopen_queue_check(sk))) { foc->len = -1; - return false; + return NULL; } if (syn_data && (sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD)) @@ -296,11 +299,12 @@ bool tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, * data in SYN_RECV state. */ fastopen: - if (tcp_fastopen_create_child(sk, skb, dst, req)) { + child = tcp_fastopen_create_child(sk, skb, dst, req); + if (child) { foc->len = -1; NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVE); - return true; + return child; } NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVEFAIL); } else if (foc->len > 0) /* Client presents an invalid cookie */ @@ -308,6 +312,5 @@ fastopen: valid_foc.exp = foc->exp; *foc = valid_foc; - return false; + return NULL; } -EXPORT_SYMBOL(tcp_try_fastopen); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index a8f515bb19c4..e58cbcd2f07e 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2953,21 +2953,21 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, } /* Compute time elapsed between (last) SYNACK and the ACK completing 3WHS. */ -static void tcp_synack_rtt_meas(struct sock *sk, const u32 synack_stamp) +void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req) { - struct tcp_sock *tp = tcp_sk(sk); - long seq_rtt_us = -1L; + long rtt_us = -1L; - if (synack_stamp && !tp->total_retrans) - seq_rtt_us = jiffies_to_usecs(tcp_time_stamp - synack_stamp); + if (req && !req->num_retrans && tcp_rsk(req)->snt_synack.v64) { + struct skb_mstamp now; - /* If the ACK acks both the SYNACK and the (Fast Open'd) data packets - * sent in SYN_RECV, SYNACK RTT is the smooth RTT computed in tcp_ack() - */ - if (!tp->srtt_us) - tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, seq_rtt_us, -1L); + skb_mstamp_get(&now); + rtt_us = skb_mstamp_us_delta(&now, &tcp_rsk(req)->snt_synack); + } + + tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, rtt_us, -1L); } + static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) { const struct inet_connection_sock *icsk = inet_csk(sk); @@ -5472,7 +5472,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, } static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, - const struct tcphdr *th, unsigned int len) + const struct tcphdr *th) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); @@ -5698,15 +5698,14 @@ reset_and_undo: * address independent. */ -int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, - const struct tcphdr *th, unsigned int len) +int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); + const struct tcphdr *th = tcp_hdr(skb); struct request_sock *req; int queued = 0; bool acceptable; - u32 synack_stamp; tp->rx_opt.saw_tstamp = 0; @@ -5750,7 +5749,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, goto discard; case TCP_SYN_SENT: - queued = tcp_rcv_synsent_state_process(sk, skb, th, len); + queued = tcp_rcv_synsent_state_process(sk, skb, th); if (queued >= 0) return queued; @@ -5785,15 +5784,16 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, if (!acceptable) return 1; + if (!tp->srtt_us) + tcp_synack_rtt_meas(sk, req); + /* Once we leave TCP_SYN_RECV, we no longer need req * so release it. */ if (req) { - synack_stamp = tcp_rsk(req)->snt_synack; tp->total_retrans = req->num_retrans; reqsk_fastopen_remove(sk, req, false); } else { - synack_stamp = tp->lsndtime; /* Make sure socket is routed, for correct metrics. */ icsk->icsk_af_ops->rebuild_header(sk); tcp_init_congestion_control(sk); @@ -5816,7 +5816,6 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, tp->snd_una = TCP_SKB_CB(skb)->ack_seq; tp->snd_wnd = ntohs(th->window) << tp->rx_opt.snd_wscale; tcp_init_wl(tp, TCP_SKB_CB(skb)->seq); - tcp_synack_rtt_meas(sk, synack_stamp); if (tp->rx_opt.tstamp_ok) tp->advmss -= TCPOLEN_TSTAMP_ALIGNED; @@ -6027,7 +6026,7 @@ static void tcp_openreq_init(struct request_sock *req, req->cookie_ts = 0; tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq; tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; - tcp_rsk(req)->snt_synack = tcp_time_stamp; + skb_mstamp_get(&tcp_rsk(req)->snt_synack); tcp_rsk(req)->last_oow_ack_time = 0; req->mss = rx_opt->mss_clamp; req->ts_recent = rx_opt->saw_tstamp ? rx_opt->rcv_tsval : 0; @@ -6065,7 +6064,7 @@ EXPORT_SYMBOL(inet_reqsk_alloc); /* * Return true if a syncookie should be sent */ -static bool tcp_syn_flood_action(struct sock *sk, +static bool tcp_syn_flood_action(const struct sock *sk, const struct sk_buff *skb, const char *proto) { @@ -6083,11 +6082,12 @@ static bool tcp_syn_flood_action(struct sock *sk, NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDROP); lopt = inet_csk(sk)->icsk_accept_queue.listen_opt; - if (!lopt->synflood_warned && sysctl_tcp_syncookies != 2) { - lopt->synflood_warned = 1; + if (!lopt->synflood_warned && + sysctl_tcp_syncookies != 2 && + xchg(&lopt->synflood_warned, 1) == 0) pr_info("%s: Possible SYN flooding on port %d. %s. Check SNMP counters.\n", proto, ntohs(tcp_hdr(skb)->dest), msg); - } + return want_cookie; } @@ -6112,14 +6112,15 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct sk_buff *skb) { + struct tcp_fastopen_cookie foc = { .len = -1 }; + __u32 isn = TCP_SKB_CB(skb)->tcp_tw_isn; struct tcp_options_received tmp_opt; - struct request_sock *req; struct tcp_sock *tp = tcp_sk(sk); + struct sock *fastopen_sk = NULL; struct dst_entry *dst = NULL; - __u32 isn = TCP_SKB_CB(skb)->tcp_tw_isn; - bool want_cookie = false, fastopen; + struct request_sock *req; + bool want_cookie = false; struct flowi fl; - struct tcp_fastopen_cookie foc = { .len = -1 }; int err; @@ -6228,12 +6229,15 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, } tcp_rsk(req)->snt_isn = isn; + tcp_rsk(req)->txhash = net_tx_rndhash(); tcp_openreq_init_rwin(req, sk, dst); - fastopen = !want_cookie && - tcp_try_fastopen(sk, skb, req, &foc, dst); - err = af_ops->send_synack(sk, dst, &fl, req, + if (!want_cookie) + fastopen_sk = tcp_try_fastopen(sk, skb, req, &foc, dst); + err = af_ops->send_synack(fastopen_sk ?: sk, dst, &fl, req, skb_get_queue_mapping(skb), &foc); - if (!fastopen) { + if (fastopen_sk) { + sock_put(fastopen_sk); + } else { if (err || want_cookie) goto drop_and_free; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 93898e093d4e..64ece718d66c 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -576,7 +576,7 @@ EXPORT_SYMBOL(tcp_v4_send_check); * Exception: precedence violation. We do not implement it in any case. */ -static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb) +static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) { const struct tcphdr *th = tcp_hdr(skb); struct { @@ -795,7 +795,7 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) inet_twsk_put(tw); } -static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, +static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, struct request_sock *req) { /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV @@ -818,7 +818,7 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, * This still operates on a request_sock only, not on a big * socket. */ -static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, +static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, u16 queue_mapping, @@ -865,7 +865,7 @@ static void tcp_v4_reqsk_destructor(struct request_sock *req) */ /* Find the Key structure for an address. */ -struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk, +struct tcp_md5sig_key *tcp_md5_do_lookup(const struct sock *sk, const union tcp_md5_addr *addr, int family) { @@ -877,7 +877,7 @@ struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk, /* caller either holds rcu_read_lock() or socket lock */ md5sig = rcu_dereference_check(tp->md5sig_info, sock_owned_by_user(sk) || - lockdep_is_held(&sk->sk_lock.slock)); + lockdep_is_held((spinlock_t *)&sk->sk_lock.slock)); if (!md5sig) return NULL; #if IS_ENABLED(CONFIG_IPV6) @@ -894,7 +894,7 @@ struct tcp_md5sig_key *tcp_md5_do_lookup(struct sock *sk, } EXPORT_SYMBOL(tcp_md5_do_lookup); -struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk, +struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, const struct sock *addr_sk) { const union tcp_md5_addr *addr; @@ -1168,7 +1168,8 @@ static bool tcp_v4_inbound_md5_hash(struct sock *sk, } #endif -static void tcp_v4_init_req(struct request_sock *req, struct sock *sk_listener, +static void tcp_v4_init_req(struct request_sock *req, + const struct sock *sk_listener, struct sk_buff *skb) { struct inet_request_sock *ireq = inet_rsk(req); @@ -1179,7 +1180,8 @@ static void tcp_v4_init_req(struct request_sock *req, struct sock *sk_listener, ireq->opt = tcp_v4_save_options(skb); } -static struct dst_entry *tcp_v4_route_req(struct sock *sk, struct flowi *fl, +static struct dst_entry *tcp_v4_route_req(const struct sock *sk, + struct flowi *fl, const struct request_sock *req, bool *strict) { @@ -1241,7 +1243,7 @@ EXPORT_SYMBOL(tcp_v4_conn_request); * The three way handshake has completed - we got a valid synack - * now create the new socket. */ -struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, +struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst) { @@ -1277,7 +1279,6 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newinet->mc_ttl = ip_hdr(skb)->ttl; newinet->rcv_tos = ip_hdr(skb)->tos; inet_csk(newsk)->icsk_ext_hdr_len = 0; - sk_set_txhash(newsk); if (inet_opt) inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; newinet->inet_id = newtp->write_seq ^ jiffies; @@ -1420,7 +1421,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) } else sock_rps_save_rxhash(sk, skb); - if (tcp_rcv_state_process(sk, skb, tcp_hdr(skb), skb->len)) { + if (tcp_rcv_state_process(sk, skb)) { rsk = sk; goto reset; } @@ -2185,7 +2186,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i) const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); const struct inet_sock *inet = inet_sk(sk); - struct fastopen_queue *fastopenq = icsk->icsk_accept_queue.fastopenq; + const struct fastopen_queue *fastopenq = &icsk->icsk_accept_queue.fastopenq; __be32 dest = inet->inet_daddr; __be32 src = inet->inet_rcv_saddr; __u16 destp = ntohs(inet->inet_dport); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index def765911ff8..897e34273ba3 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -361,27 +361,35 @@ void tcp_twsk_destructor(struct sock *sk) } EXPORT_SYMBOL_GPL(tcp_twsk_destructor); +/* Warning : This function is called without sk_listener being locked. + * Be sure to read socket fields once, as their value could change under us. + */ void tcp_openreq_init_rwin(struct request_sock *req, - struct sock *sk, struct dst_entry *dst) + const struct sock *sk_listener, + const struct dst_entry *dst) { struct inet_request_sock *ireq = inet_rsk(req); - struct tcp_sock *tp = tcp_sk(sk); - __u8 rcv_wscale; + const struct tcp_sock *tp = tcp_sk(sk_listener); + u16 user_mss = READ_ONCE(tp->rx_opt.user_mss); + int full_space = tcp_full_space(sk_listener); int mss = dst_metric_advmss(dst); + u32 window_clamp; + __u8 rcv_wscale; - if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss) - mss = tp->rx_opt.user_mss; + if (user_mss && user_mss < mss) + mss = user_mss; + window_clamp = READ_ONCE(tp->window_clamp); /* Set this up on the first call only */ - req->window_clamp = tp->window_clamp ? : dst_metric(dst, RTAX_WINDOW); + req->window_clamp = window_clamp ? : dst_metric(dst, RTAX_WINDOW); /* limit the window selection if the user enforce a smaller rx buffer */ - if (sk->sk_userlocks & SOCK_RCVBUF_LOCK && - (req->window_clamp > tcp_full_space(sk) || req->window_clamp == 0)) - req->window_clamp = tcp_full_space(sk); + if (sk_listener->sk_userlocks & SOCK_RCVBUF_LOCK && + (req->window_clamp > full_space || req->window_clamp == 0)) + req->window_clamp = full_space; /* tcp_full_space because it is guaranteed to be the first packet */ - tcp_select_initial_window(tcp_full_space(sk), + tcp_select_initial_window(full_space, mss - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0), &req->rcv_wnd, &req->window_clamp, @@ -433,7 +441,9 @@ EXPORT_SYMBOL_GPL(tcp_ca_openreq_child); * Actually, we could lots of memory writes here. tp of listening * socket contains all necessary default parameters. */ -struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, struct sk_buff *skb) +struct sock *tcp_create_openreq_child(const struct sock *sk, + struct request_sock *req, + struct sk_buff *skb) { struct sock *newsk = inet_csk_clone_lock(sk, req, GFP_ATOMIC); @@ -469,7 +479,8 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, newtp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tcp_enable_early_retrans(newtp); newtp->tlp_high_seq = 0; - newtp->lsndtime = treq->snt_synack; + newtp->lsndtime = treq->snt_synack.stamp_jiffies; + newsk->sk_txhash = treq->txhash; newtp->last_oow_ack_time = 0; newtp->total_retrans = req->num_retrans; @@ -759,6 +770,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, if (!child) goto listen_overflow; + tcp_synack_rtt_meas(child, req); inet_csk_reqsk_queue_drop(sk, req); inet_csk_reqsk_queue_add(sk, req, child); /* Warning: caller must not call reqsk_put(req); @@ -811,8 +823,7 @@ int tcp_child_process(struct sock *parent, struct sock *child, int state = child->sk_state; if (!sock_owned_by_user(child)) { - ret = tcp_rcv_state_process(child, skb, tcp_hdr(skb), - skb->len); + ret = tcp_rcv_state_process(child, skb); /* Wakeup parent, send SIGIO */ if (state == TCP_SYN_RECV && child->sk_state != state) parent->sk_data_ready(parent); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 1100ffe4a722..09bb082ca1a7 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -357,14 +357,10 @@ static void tcp_ecn_clear_syn(struct sock *sk, struct sk_buff *skb) } static void -tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th, - struct sock *sk) +tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th) { - if (inet_rsk(req)->ecn_ok) { + if (inet_rsk(req)->ecn_ok) th->ece = 1; - if (tcp_ca_needs_ecn(sk)) - INET_ECN_xmit(sk); - } } /* Set up ECN state for a packet on a ESTABLISHED socket that is about to @@ -612,12 +608,11 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, } /* Set up TCP options for SYN-ACKs. */ -static unsigned int tcp_synack_options(struct sock *sk, - struct request_sock *req, - unsigned int mss, struct sk_buff *skb, - struct tcp_out_options *opts, - const struct tcp_md5sig_key *md5, - struct tcp_fastopen_cookie *foc) +static unsigned int tcp_synack_options(struct request_sock *req, + unsigned int mss, struct sk_buff *skb, + struct tcp_out_options *opts, + const struct tcp_md5sig_key *md5, + struct tcp_fastopen_cookie *foc) { struct inet_request_sock *ireq = inet_rsk(req); unsigned int remaining = MAX_TCP_OPTION_SPACE; @@ -1827,7 +1822,7 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, /* Ok, it looks like it is advisable to defer. */ - if (cong_win < send_win && cong_win < skb->len) + if (cong_win < send_win && cong_win <= skb->len) *is_cwnd_limited = true; return true; @@ -2060,7 +2055,6 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, cwnd_quota = tcp_cwnd_test(tp, skb); if (!cwnd_quota) { - is_cwnd_limited = true; if (push_one == 2) /* Force out a loss probe pkt. */ cwnd_quota = 1; @@ -2142,6 +2136,7 @@ repair: /* Send one loss probe per tail loss episode. */ if (push_one != 2) tcp_schedule_loss_probe(sk); + is_cwnd_limited |= (tcp_packets_in_flight(tp) >= tp->snd_cwnd); tcp_cwnd_validate(sk, is_cwnd_limited); return false; } @@ -2165,7 +2160,7 @@ bool tcp_schedule_loss_probe(struct sock *sk) /* Don't do any loss probe on a Fast Open connection before 3WHS * finishes. */ - if (sk->sk_state == TCP_SYN_RECV) + if (tp->fastopen_rsk) return false; /* TLP is only scheduled when next timer event is RTO. */ @@ -2175,7 +2170,7 @@ bool tcp_schedule_loss_probe(struct sock *sk) /* Schedule a loss probe in 2*RTT for SACK capable connections * in Open state, that are either limited by cwnd or application. */ - if (sysctl_tcp_early_retrans < 3 || !tp->srtt_us || !tp->packets_out || + if (sysctl_tcp_early_retrans < 3 || !tp->packets_out || !tcp_is_sack(tp) || inet_csk(sk)->icsk_ca_state != TCP_CA_Open) return false; @@ -2184,9 +2179,10 @@ bool tcp_schedule_loss_probe(struct sock *sk) return false; /* Probe timeout is at least 1.5*rtt + TCP_DELACK_MAX to account - * for delayed ack when there's one outstanding packet. + * for delayed ack when there's one outstanding packet. If no RTT + * sample is available then probe after TCP_TIMEOUT_INIT. */ - timeout = rtt << 1; + timeout = rtt << 1 ? : TCP_TIMEOUT_INIT; if (tp->packets_out == 1) timeout = max_t(u32, timeout, (rtt + (rtt >> 1) + TCP_DELACK_MAX)); @@ -2949,20 +2945,25 @@ int tcp_send_synack(struct sock *sk) * Allocate one skb and build a SYNACK packet. * @dst is consumed : Caller should not use it again. */ -struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, +struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, struct request_sock *req, struct tcp_fastopen_cookie *foc) { - struct tcp_out_options opts; struct inet_request_sock *ireq = inet_rsk(req); - struct tcp_sock *tp = tcp_sk(sk); - struct tcphdr *th; - struct sk_buff *skb; + const struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *md5 = NULL; + struct tcp_out_options opts; + struct sk_buff *skb; int tcp_header_size; + struct tcphdr *th; + u16 user_mss; int mss; - skb = sock_wmalloc(sk, MAX_TCP_HEADER, 1, GFP_ATOMIC); + /* sk is a const pointer, because we want to express multiple cpus + * might call us concurrently. + * sock_wmalloc() will change sk->sk_wmem_alloc in an atomic way. + */ + skb = sock_wmalloc((struct sock *)sk, MAX_TCP_HEADER, 1, GFP_ATOMIC); if (unlikely(!skb)) { dst_release(dst); return NULL; @@ -2973,8 +2974,9 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, skb_dst_set(skb, dst); mss = dst_metric_advmss(dst); - if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss) - mss = tp->rx_opt.user_mss; + user_mss = READ_ONCE(tp->rx_opt.user_mss); + if (user_mss && user_mss < mss) + mss = user_mss; memset(&opts, 0, sizeof(opts)); #ifdef CONFIG_SYN_COOKIES @@ -2988,8 +2990,9 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, rcu_read_lock(); md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req)); #endif - tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5, - foc) + sizeof(*th); + skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4); + tcp_header_size = tcp_synack_options(req, mss, skb, &opts, md5, foc) + + sizeof(*th); skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); @@ -2998,7 +3001,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, memset(th, 0, sizeof(struct tcphdr)); th->syn = 1; th->ack = 1; - tcp_ecn_make_synack(req, th, sk); + tcp_ecn_make_synack(req, th); th->source = htons(ireq->ir_num); th->dest = ireq->ir_rmt_port; /* Setting of flags are superfluous here for callers (and ECE is @@ -3013,7 +3016,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, /* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */ th->window = htons(min(req->rcv_wnd, 65535U)); - tcp_options_write((__be32 *)(th + 1), tp, &opts); + tcp_options_write((__be32 *)(th + 1), NULL, &opts); th->doff = (tcp_header_size >> 2); TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_OUTSEGS); @@ -3500,12 +3503,13 @@ void tcp_send_probe0(struct sock *sk) TCP_RTO_MAX); } -int tcp_rtx_synack(struct sock *sk, struct request_sock *req) +int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) { const struct tcp_request_sock_ops *af_ops = tcp_rsk(req)->af_specific; struct flowi fl; int res; + tcp_rsk(req)->txhash = net_tx_rndhash(); res = af_ops->send_synack(sk, NULL, &fl, req, 0, NULL); if (!res) { TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index f7d1d5e19e95..156ba75b6000 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1021,7 +1021,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) * device lookup source address from VRF table. This mimics * behavior of ip_route_connect{_init}. */ - if (netif_index_is_vrf(net, ipc.oif)) { + if (netif_index_is_l3_master(net, ipc.oif)) { flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, sk->sk_protocol, (flow_flags | FLOWI_FLAG_VRFSRC | diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index 60b032f58ccc..62e1e72db461 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -22,7 +22,8 @@ int xfrm4_extract_input(struct xfrm_state *x, struct sk_buff *skb) return xfrm4_extract_header(skb); } -static inline int xfrm4_rcv_encap_finish(struct sock *sk, struct sk_buff *skb) +static inline int xfrm4_rcv_encap_finish(struct net *net, struct sock *sk, + struct sk_buff *skb) { if (!skb_dst(skb)) { const struct iphdr *iph = ip_hdr(skb); @@ -52,8 +53,8 @@ int xfrm4_transport_finish(struct sk_buff *skb, int async) iph->tot_len = htons(skb->len); ip_send_check(iph); - NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, NULL, skb, - skb->dev, NULL, + NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, + dev_net(skb->dev), NULL, skb, skb->dev, NULL, xfrm4_rcv_encap_finish); return 0; } diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index 2878dbfffeb7..cd6be736e19f 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -80,14 +80,14 @@ int xfrm4_output_finish(struct sock *sk, struct sk_buff *skb) return xfrm_output(sk, skb); } -static int __xfrm4_output(struct sock *sk, struct sk_buff *skb) +static int __xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct xfrm_state *x = skb_dst(skb)->xfrm; #ifdef CONFIG_NETFILTER if (!x) { IPCB(skb)->flags |= IPSKB_REROUTED; - return dst_output_sk(sk, skb); + return dst_output(sk, skb); } #endif @@ -96,8 +96,11 @@ static int __xfrm4_output(struct sock *sk, struct sk_buff *skb) int xfrm4_output(struct sock *sk, struct sk_buff *skb) { - return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, sk, skb, - NULL, skb_dst(skb)->dev, __xfrm4_output, + struct net *net = dev_net(skb_dst(skb)->dev); + + return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, + net, sk, skb, NULL, skb_dst(skb)->dev, + __xfrm4_output, !(IPCB(skb)->flags & IPSKB_REROUTED)); } diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index c10a9ee68433..f2606b9056bb 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -15,7 +15,7 @@ #include <net/dst.h> #include <net/xfrm.h> #include <net/ip.h> -#include <net/vrf.h> +#include <net/l3mdev.h> static struct xfrm_policy_afinfo xfrm4_policy_afinfo; @@ -97,6 +97,7 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, xdst->u.rt.rt_gateway = rt->rt_gateway; xdst->u.rt.rt_uses_gateway = rt->rt_uses_gateway; xdst->u.rt.rt_pmtu = rt->rt_pmtu; + xdst->u.rt.rt_table_id = rt->rt_table_id; INIT_LIST_HEAD(&xdst->u.rt.rt_uncached); return 0; @@ -110,10 +111,8 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) struct flowi4 *fl4 = &fl->u.ip4; int oif = 0; - if (skb_dst(skb)) { - oif = vrf_master_ifindex(skb_dst(skb)->dev) ? - : skb_dst(skb)->dev->ifindex; - } + if (skb_dst(skb)) + oif = l3mdev_fib_oif(skb_dst(skb)->dev); memset(fl4, 0, sizeof(struct flowi4)); fl4->flowi4_mark = skb->mark; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 900113376d4e..c8380f1876f1 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3625,7 +3625,7 @@ static void addrconf_dad_work(struct work_struct *w) /* send a neighbour solicitation for our addr */ addrconf_addr_solict_mult(&ifp->addr, &mcaddr); - ndisc_send_ns(ifp->idev->dev, NULL, &ifp->addr, &mcaddr, &in6addr_any, NULL); + ndisc_send_ns(ifp->idev->dev, &ifp->addr, &mcaddr, &in6addr_any, NULL); out: in6_ifa_put(ifp); rtnl_unlock(); @@ -4729,7 +4729,8 @@ static void snmp6_fill_stats(u64 *stats, struct inet6_dev *idev, int attrtype, } } -static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev) +static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev, + u32 ext_filter_mask) { struct nlattr *nla; struct ifla_cacheinfo ci; @@ -4749,6 +4750,9 @@ static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev) /* XXX - MC not implemented */ + if (ext_filter_mask & RTEXT_FILTER_SKIP_STATS) + return 0; + nla = nla_reserve(skb, IFLA_INET6_STATS, IPSTATS_MIB_MAX * sizeof(u64)); if (!nla) goto nla_put_failure; @@ -4784,14 +4788,15 @@ static size_t inet6_get_link_af_size(const struct net_device *dev) return inet6_ifla6_size(); } -static int inet6_fill_link_af(struct sk_buff *skb, const struct net_device *dev) +static int inet6_fill_link_af(struct sk_buff *skb, const struct net_device *dev, + u32 ext_filter_mask) { struct inet6_dev *idev = __in6_dev_get(dev); if (!idev) return -ENODATA; - if (inet6_fill_ifla6_attrs(skb, idev) < 0) + if (inet6_fill_ifla6_attrs(skb, idev, ext_filter_mask) < 0) return -EMSGSIZE; return 0; @@ -4946,7 +4951,7 @@ static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev, if (!protoinfo) goto nla_put_failure; - if (inet6_fill_ifla6_attrs(skb, idev) < 0) + if (inet6_fill_ifla6_attrs(skb, idev, 0) < 0) goto nla_put_failure; nla_nest_end(skb, protoinfo); diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 9aadd57808a5..d70b0238f468 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -263,7 +263,7 @@ void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info) { - struct ipv6_pinfo *np = inet6_sk(sk); + const struct ipv6_pinfo *np = inet6_sk(sk); struct sock_exterr_skb *serr; struct ipv6hdr *iph; struct sk_buff *skb; diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 6927f3fb5597..163bfef3e5db 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -65,17 +65,18 @@ int inet6_csk_bind_conflict(const struct sock *sk, } EXPORT_SYMBOL_GPL(inet6_csk_bind_conflict); -struct dst_entry *inet6_csk_route_req(struct sock *sk, +struct dst_entry *inet6_csk_route_req(const struct sock *sk, struct flowi6 *fl6, - const struct request_sock *req) + const struct request_sock *req, + u8 proto) { struct inet_request_sock *ireq = inet_rsk(req); - struct ipv6_pinfo *np = inet6_sk(sk); + const struct ipv6_pinfo *np = inet6_sk(sk); struct in6_addr *final_p, final; struct dst_entry *dst; memset(fl6, 0, sizeof(*fl6)); - fl6->flowi6_proto = IPPROTO_TCP; + fl6->flowi6_proto = proto; fl6->daddr = ireq->ir_v6_rmt_addr; final_p = fl6_update_dst(fl6, np->opt, &final); fl6->saddr = ireq->ir_v6_loc_addr; @@ -91,6 +92,7 @@ struct dst_entry *inet6_csk_route_req(struct sock *sk, return dst; } +EXPORT_SYMBOL(inet6_csk_route_req); /* * request_sock (formerly open request) hash tables. diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index adba03ac7ce9..9075acf081dd 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -47,7 +47,7 @@ #include <net/inet_ecn.h> #include <net/dst_metadata.h> -int ip6_rcv_finish(struct sock *sk, struct sk_buff *skb) +int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { if (sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) { const struct inet6_protocol *ipprot; @@ -109,7 +109,7 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt if (hdr->version != 6) goto err; - IP6_ADD_STATS_BH(dev_net(dev), idev, + IP6_ADD_STATS_BH(net, idev, IPSTATS_MIB_NOECTPKTS + (ipv6_get_dsfield(hdr) & INET_ECN_MASK), max_t(unsigned short, 1, skb_shinfo(skb)->gso_segs)); @@ -183,8 +183,8 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt /* Must drop socket now because of tproxy. */ skb_orphan(skb); - return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, NULL, skb, - dev, NULL, + return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, + net, NULL, skb, dev, NULL, ip6_rcv_finish); err: IP6_INC_STATS_BH(net, idev, IPSTATS_MIB_INHDRERRORS); @@ -199,9 +199,8 @@ drop: */ -static int ip6_input_finish(struct sock *sk, struct sk_buff *skb) +static int ip6_input_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct net *net = dev_net(skb_dst(skb)->dev); const struct inet6_protocol *ipprot; struct inet6_dev *idev; unsigned int nhoff; @@ -278,8 +277,8 @@ discard: int ip6_input(struct sk_buff *skb) { - return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_IN, NULL, skb, - skb->dev, NULL, + return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_IN, + dev_net(skb->dev), NULL, skb, skb->dev, NULL, ip6_input_finish); } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 92b1aa38f121..a598fe2c0849 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -60,6 +60,7 @@ static int ip6_finish_output2(struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst->dev; + struct net *net = dev_net(dev); struct neighbour *neigh; struct in6_addr *nexthop; int ret; @@ -71,7 +72,7 @@ static int ip6_finish_output2(struct sock *sk, struct sk_buff *skb) struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(sk) && - ((mroute6_socket(dev_net(dev), skb) && + ((mroute6_socket(net, skb) && !(IP6CB(skb)->flags & IP6SKB_FORWARDED)) || ipv6_chk_mcast_addr(dev, &ipv6_hdr(skb)->daddr, &ipv6_hdr(skb)->saddr))) { @@ -82,19 +83,18 @@ static int ip6_finish_output2(struct sock *sk, struct sk_buff *skb) */ if (newskb) NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, - sk, newskb, NULL, newskb->dev, + net, sk, newskb, NULL, newskb->dev, dev_loopback_xmit); if (ipv6_hdr(skb)->hop_limit == 0) { - IP6_INC_STATS(dev_net(dev), idev, + IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); return 0; } } - IP6_UPD_PO_STATS(dev_net(dev), idev, IPSTATS_MIB_OUTMCAST, - skb->len); + IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUTMCAST, skb->len); if (IPV6_ADDR_MC_SCOPE(&ipv6_hdr(skb)->daddr) <= IPV6_ADDR_SCOPE_NODELOCAL && @@ -116,13 +116,12 @@ static int ip6_finish_output2(struct sock *sk, struct sk_buff *skb) } rcu_read_unlock_bh(); - IP6_INC_STATS(dev_net(dst->dev), - ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); + IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); kfree_skb(skb); return -EINVAL; } -static int ip6_finish_output(struct sock *sk, struct sk_buff *skb) +static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) || dst_allfrag(skb_dst(skb)) || @@ -136,28 +135,31 @@ int ip6_output(struct sock *sk, struct sk_buff *skb) { struct net_device *dev = skb_dst(skb)->dev; struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); + struct net *net = dev_net(dev); + if (unlikely(idev->cnf.disable_ipv6)) { - IP6_INC_STATS(dev_net(dev), idev, - IPSTATS_MIB_OUTDISCARDS); + IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS); kfree_skb(skb); return 0; } - return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, sk, skb, - NULL, dev, + return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, + net, sk, skb, NULL, dev, ip6_finish_output, !(IP6CB(skb)->flags & IP6SKB_REROUTED)); } /* - * xmit an sk_buff (used by TCP, SCTP and DCCP) + * xmit an sk_buff (used by TCP, SCTP and DCCP) + * Note : socket lock is not held for SYNACK packets, but might be modified + * by calls to skb_set_owner_w() and ipv6_local_error(), + * which are using proper atomic operations or spinlocks. */ - -int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, +int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, struct ipv6_txoptions *opt, int tclass) { struct net *net = sock_net(sk); - struct ipv6_pinfo *np = inet6_sk(sk); + const struct ipv6_pinfo *np = inet6_sk(sk); struct in6_addr *first_hop = &fl6->daddr; struct dst_entry *dst = skb_dst(skb); struct ipv6hdr *hdr; @@ -186,7 +188,10 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, } consume_skb(skb); skb = skb2; - skb_set_owner_w(skb, sk); + /* skb_set_owner_w() changes sk->sk_wmem_alloc atomically, + * it is safe to call in our context (socket lock not held) + */ + skb_set_owner_w(skb, (struct sock *)sk); } if (opt->opt_flen) ipv6_push_frag_opts(skb, opt, &proto); @@ -224,12 +229,20 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) { IP6_UPD_PO_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUT, skb->len); - return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, sk, skb, - NULL, dst->dev, dst_output_sk); + /* hooks should never assume socket lock is held. + * we promote our socket to non const + */ + return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, + net, (struct sock *)sk, skb, NULL, dst->dev, + dst_output_okfn); } skb->dev = dst->dev; - ipv6_local_error(sk, EMSGSIZE, fl6, mtu); + /* ipv6_local_error() does not require socket lock, + * we promote our socket to non const + */ + ipv6_local_error((struct sock *)sk, EMSGSIZE, fl6, mtu); + IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); return -EMSGSIZE; @@ -317,10 +330,11 @@ static int ip6_forward_proxy_check(struct sk_buff *skb) return 0; } -static inline int ip6_forward_finish(struct sock *sk, struct sk_buff *skb) +static inline int ip6_forward_finish(struct net *net, struct sock *sk, + struct sk_buff *skb) { skb_sender_cpu_clear(skb); - return dst_output_sk(sk, skb); + return dst_output(sk, skb); } static unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst) @@ -512,8 +526,8 @@ int ip6_forward(struct sk_buff *skb) IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS); IP6_ADD_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTOCTETS, skb->len); - return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, NULL, skb, - skb->dev, dst->dev, + return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, + net, NULL, skb, skb->dev, dst->dev, ip6_forward_finish); error: @@ -883,7 +897,7 @@ out: return dst; } -static int ip6_dst_lookup_tail(struct net *net, struct sock *sk, +static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6) { #ifdef CONFIG_IPV6_OPTIMISTIC_DAD @@ -1014,7 +1028,7 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup); * It returns a valid dst pointer on success, or a pointer encoded * error code. */ -struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, +struct dst_entry *ip6_dst_lookup_flow(const struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst) { struct dst_entry *dst = NULL; diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 0224c032dca5..f96f1c19b4a8 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -482,7 +482,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) return -EMSGSIZE; } - err = dst_output(skb); + err = dst_output(skb->sk, skb); if (net_xmit_eval(err) == 0) { struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 0e004cc42a22..5e5d16e7ce85 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1985,13 +1985,13 @@ int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) } #endif -static inline int ip6mr_forward2_finish(struct sock *sk, struct sk_buff *skb) +static inline int ip6mr_forward2_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { - IP6_INC_STATS_BH(dev_net(skb_dst(skb)->dev), ip6_dst_idev(skb_dst(skb)), + IP6_INC_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTFORWDATAGRAMS); - IP6_ADD_STATS_BH(dev_net(skb_dst(skb)->dev), ip6_dst_idev(skb_dst(skb)), + IP6_ADD_STATS_BH(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTOCTETS, skb->len); - return dst_output_sk(sk, skb); + return dst_output(sk, skb); } /* @@ -2063,8 +2063,8 @@ static int ip6mr_forward2(struct net *net, struct mr6_table *mrt, IP6CB(skb)->flags |= IP6SKB_FORWARDED; - return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, NULL, skb, - skb->dev, dev, + return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, + net, NULL, skb, skb->dev, dev, ip6mr_forward2_finish); out_free: diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 083b2927fc67..a8bf57ca74d3 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1645,8 +1645,8 @@ static void mld_sendpack(struct sk_buff *skb) payload_len = skb->len; err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, - net->ipv6.igmp_sk, skb, NULL, skb->dev, - dst_output_sk); + net, net->ipv6.igmp_sk, skb, NULL, skb->dev, + dst_output_okfn); out: if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, ICMPV6_MLD2_REPORT); @@ -2008,8 +2008,9 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) } skb_dst_set(skb, dst); - err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, sk, skb, - NULL, skb->dev, dst_output_sk); + err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, + net, sk, skb, NULL, skb->dev, + dst_output_okfn); out: if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, type); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 64a71354b069..7089c305245c 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -463,9 +463,9 @@ static void ndisc_send_skb(struct sk_buff *skb, idev = __in6_dev_get(dst->dev); IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); - err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, sk, skb, - NULL, dst->dev, - dst_output_sk); + err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, + net, sk, skb, NULL, dst->dev, + dst_output_okfn); if (!err) { ICMP6MSGOUT_INC_STATS(net, idev, type); ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS); @@ -474,8 +474,7 @@ static void ndisc_send_skb(struct sk_buff *skb, rcu_read_unlock(); } -void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, - const struct in6_addr *daddr, +void ndisc_send_na(struct net_device *dev, const struct in6_addr *daddr, const struct in6_addr *solicited_addr, bool router, bool solicited, bool override, bool inc_opt) { @@ -541,7 +540,7 @@ static void ndisc_send_unsol_na(struct net_device *dev) read_lock_bh(&idev->lock); list_for_each_entry(ifa, &idev->addr_list, if_list) { - ndisc_send_na(dev, NULL, &in6addr_linklocal_allnodes, &ifa->addr, + ndisc_send_na(dev, &in6addr_linklocal_allnodes, &ifa->addr, /*router=*/ !!idev->cnf.forwarding, /*solicited=*/ false, /*override=*/ true, /*inc_opt=*/ true); @@ -551,8 +550,7 @@ static void ndisc_send_unsol_na(struct net_device *dev) in6_dev_put(idev); } -void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh, - const struct in6_addr *solicit, +void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit, const struct in6_addr *daddr, const struct in6_addr *saddr, struct sk_buff *oskb) { @@ -679,12 +677,12 @@ static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb) "%s: trying to ucast probe in NUD_INVALID: %pI6\n", __func__, target); } - ndisc_send_ns(dev, neigh, target, target, saddr, skb); + ndisc_send_ns(dev, target, target, saddr, skb); } else if ((probes -= NEIGH_VAR(neigh->parms, APP_PROBES)) < 0) { neigh_app_ns(neigh); } else { addrconf_addr_solict_mult(target, &mcaddr); - ndisc_send_ns(dev, NULL, target, &mcaddr, saddr, skb); + ndisc_send_ns(dev, target, &mcaddr, saddr, skb); } } @@ -828,7 +826,7 @@ static void ndisc_recv_ns(struct sk_buff *skb) is_router = idev->cnf.forwarding; if (dad) { - ndisc_send_na(dev, NULL, &in6addr_linklocal_allnodes, &msg->target, + ndisc_send_na(dev, &in6addr_linklocal_allnodes, &msg->target, !!is_router, false, (ifp != NULL), true); goto out; } @@ -849,8 +847,7 @@ static void ndisc_recv_ns(struct sk_buff *skb) NEIGH_UPDATE_F_WEAK_OVERRIDE| NEIGH_UPDATE_F_OVERRIDE); if (neigh || !dev->header_ops) { - ndisc_send_na(dev, neigh, saddr, &msg->target, - !!is_router, + ndisc_send_na(dev, saddr, &msg->target, !!is_router, true, (ifp != NULL && inc), inc); if (neigh) neigh_release(neigh); diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index b4de08a83e0b..d11c46833d61 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -18,9 +18,8 @@ #include <net/ip6_checksum.h> #include <net/netfilter/nf_queue.h> -int ip6_route_me_harder(struct sk_buff *skb) +int ip6_route_me_harder(struct net *net, struct sk_buff *skb) { - struct net *net = dev_net(skb_dst(skb)->dev); const struct ipv6hdr *iph = ipv6_hdr(skb); unsigned int hh_len; struct dst_entry *dst; @@ -93,7 +92,7 @@ static void nf_ip6_saveroute(const struct sk_buff *skb, } } -static int nf_ip6_reroute(struct sk_buff *skb, +static int nf_ip6_reroute(struct net *net, struct sk_buff *skb, const struct nf_queue_entry *entry) { struct ip6_rt_info *rt_info = nf_queue_entry_reroute(entry); @@ -103,7 +102,7 @@ static int nf_ip6_reroute(struct sk_buff *skb, if (!ipv6_addr_equal(&iph->daddr, &rt_info->daddr) || !ipv6_addr_equal(&iph->saddr, &rt_info->saddr) || skb->mark != rt_info->mark) - return ip6_route_me_harder(skb); + return ip6_route_me_harder(net, skb); } return 0; } diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 0771991ed812..80e3bd72b715 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -275,7 +275,8 @@ get_chainname_rulenum(const struct ip6t_entry *s, const struct ip6t_entry *e, return 0; } -static void trace_packet(const struct sk_buff *skb, +static void trace_packet(struct net *net, + const struct sk_buff *skb, unsigned int hook, const struct net_device *in, const struct net_device *out, @@ -287,7 +288,6 @@ static void trace_packet(const struct sk_buff *skb, const char *hookname, *chainname, *comment; const struct ip6t_entry *iter; unsigned int rulenum = 0; - struct net *net = dev_net(in ? in : out); root = get_entry(private->entries, private->hook_entry[hook]); @@ -314,10 +314,10 @@ ip6t_next_entry(const struct ip6t_entry *entry) /* Returns one of the generic firewall policies, like NF_ACCEPT. */ unsigned int ip6t_do_table(struct sk_buff *skb, - unsigned int hook, const struct nf_hook_state *state, struct xt_table *table) { + unsigned int hook = state->hook; static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long)))); /* Initializing verdict to NF_DROP keeps gcc happy. */ unsigned int verdict = NF_DROP; @@ -340,6 +340,7 @@ ip6t_do_table(struct sk_buff *skb, * rule is also a fragment-specific rule, non-fragments won't * match it. */ acpar.hotdrop = false; + acpar.net = state->net; acpar.in = state->in; acpar.out = state->out; acpar.family = NFPROTO_IPV6; @@ -401,8 +402,8 @@ ip6t_do_table(struct sk_buff *skb, #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) /* The packet is traced: log it */ if (unlikely(skb->nf_trace)) - trace_packet(skb, hook, state->in, state->out, - table->name, private, e); + trace_packet(state->net, skb, hook, state->in, + state->out, table->name, private, e); #endif /* Standard target? */ if (!t->u.kernel.target->target) { diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index 0ed841a3fa33..db29bbf41b59 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -39,7 +39,7 @@ static unsigned int reject_tg6(struct sk_buff *skb, const struct xt_action_param *par) { const struct ip6t_reject_info *reject = par->targinfo; - struct net *net = dev_net((par->in != NULL) ? par->in : par->out); + struct net *net = par->net; switch (reject->with) { case IP6T_ICMP6_NO_ROUTE: diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c index 1e4bf99ed16e..c2356602158a 100644 --- a/net/ipv6/netfilter/ip6t_SYNPROXY.c +++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c @@ -275,7 +275,7 @@ static unsigned int synproxy_tg6(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_synproxy_info *info = par->targinfo; - struct synproxy_net *snet = synproxy_pernet(dev_net(par->in)); + struct synproxy_net *snet = synproxy_pernet(par->net); struct synproxy_options opts = {}; struct tcphdr *th, _th; @@ -316,11 +316,11 @@ synproxy_tg6(struct sk_buff *skb, const struct xt_action_param *par) return XT_CONTINUE; } -static unsigned int ipv6_synproxy_hook(const struct nf_hook_ops *ops, +static unsigned int ipv6_synproxy_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *nhs) { - struct synproxy_net *snet = synproxy_pernet(dev_net(nhs->in ? : nhs->out)); + struct synproxy_net *snet = synproxy_pernet(nhs->net); enum ip_conntrack_info ctinfo; struct nf_conn *ct; struct nf_conn_synproxy *synproxy; diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c index 790e0c6b19e1..1ee1b25df096 100644 --- a/net/ipv6/netfilter/ip6t_rpfilter.c +++ b/net/ipv6/netfilter/ip6t_rpfilter.c @@ -26,7 +26,7 @@ static bool rpfilter_addr_unicast(const struct in6_addr *addr) return addr_type & IPV6_ADDR_UNICAST; } -static bool rpfilter_lookup_reverse6(const struct sk_buff *skb, +static bool rpfilter_lookup_reverse6(struct net *net, const struct sk_buff *skb, const struct net_device *dev, u8 flags) { struct rt6_info *rt; @@ -53,7 +53,7 @@ static bool rpfilter_lookup_reverse6(const struct sk_buff *skb, lookup_flags |= RT6_LOOKUP_F_IFACE; } - rt = (void *) ip6_route_lookup(dev_net(dev), &fl6, lookup_flags); + rt = (void *) ip6_route_lookup(net, &fl6, lookup_flags); if (rt->dst.error) goto out; @@ -93,7 +93,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) if (unlikely(saddrtype == IPV6_ADDR_ANY)) return true ^ invert; /* not routable: forward path will drop it */ - return rpfilter_lookup_reverse6(skb, par->in, info->flags) ^ invert; + return rpfilter_lookup_reverse6(par->net, skb, par->in, info->flags) ^ invert; } static int rpfilter_check(const struct xt_mtchk_param *par) diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index 5c33d8abc077..8b277b983ca5 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -32,12 +32,10 @@ static const struct xt_table packet_filter = { /* The work comes in here from netfilter.c. */ static unsigned int -ip6table_filter_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, +ip6table_filter_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - const struct net *net = dev_net(state->in ? state->in : state->out); - - return ip6t_do_table(skb, ops->hooknum, state, net->ipv6.ip6table_filter); + return ip6t_do_table(skb, state, state->net->ipv6.ip6table_filter); } static struct nf_hook_ops *filter_ops __read_mostly; diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index b551f5b79fe2..abe278b07932 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -57,8 +57,7 @@ ip6t_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state) /* flowlabel and prio (includes version, which shouldn't change either */ flowlabel = *((u_int32_t *)ipv6_hdr(skb)); - ret = ip6t_do_table(skb, NF_INET_LOCAL_OUT, state, - dev_net(state->out)->ipv6.ip6table_mangle); + ret = ip6t_do_table(skb, state, state->net->ipv6.ip6table_mangle); if (ret != NF_DROP && ret != NF_STOLEN && (!ipv6_addr_equal(&ipv6_hdr(skb)->saddr, &saddr) || @@ -66,7 +65,7 @@ ip6t_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state) skb->mark != mark || ipv6_hdr(skb)->hop_limit != hop_limit || flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) { - err = ip6_route_me_harder(skb); + err = ip6_route_me_harder(state->net, skb); if (err < 0) ret = NF_DROP_ERR(err); } @@ -76,17 +75,16 @@ ip6t_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state) /* The work comes in here from netfilter.c. */ static unsigned int -ip6table_mangle_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, +ip6table_mangle_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - if (ops->hooknum == NF_INET_LOCAL_OUT) + if (state->hook == NF_INET_LOCAL_OUT) return ip6t_mangle_out(skb, state); - if (ops->hooknum == NF_INET_POST_ROUTING) - return ip6t_do_table(skb, ops->hooknum, state, - dev_net(state->out)->ipv6.ip6table_mangle); + if (state->hook == NF_INET_POST_ROUTING) + return ip6t_do_table(skb, state, + state->net->ipv6.ip6table_mangle); /* INPUT/FORWARD */ - return ip6t_do_table(skb, ops->hooknum, state, - dev_net(state->in)->ipv6.ip6table_mangle); + return ip6t_do_table(skb, state, state->net->ipv6.ip6table_mangle); } static struct nf_hook_ops *mangle_ops __read_mostly; diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index c3a7f7af0ed4..abea175d5853 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -30,42 +30,40 @@ static const struct xt_table nf_nat_ipv6_table = { .af = NFPROTO_IPV6, }; -static unsigned int ip6table_nat_do_chain(const struct nf_hook_ops *ops, +static unsigned int ip6table_nat_do_chain(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct) { - struct net *net = nf_ct_net(ct); - - return ip6t_do_table(skb, ops->hooknum, state, net->ipv6.ip6table_nat); + return ip6t_do_table(skb, state, state->net->ipv6.ip6table_nat); } -static unsigned int ip6table_nat_fn(const struct nf_hook_ops *ops, +static unsigned int ip6table_nat_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_nat_ipv6_fn(ops, skb, state, ip6table_nat_do_chain); + return nf_nat_ipv6_fn(priv, skb, state, ip6table_nat_do_chain); } -static unsigned int ip6table_nat_in(const struct nf_hook_ops *ops, +static unsigned int ip6table_nat_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_nat_ipv6_in(ops, skb, state, ip6table_nat_do_chain); + return nf_nat_ipv6_in(priv, skb, state, ip6table_nat_do_chain); } -static unsigned int ip6table_nat_out(const struct nf_hook_ops *ops, +static unsigned int ip6table_nat_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_nat_ipv6_out(ops, skb, state, ip6table_nat_do_chain); + return nf_nat_ipv6_out(priv, skb, state, ip6table_nat_do_chain); } -static unsigned int ip6table_nat_local_fn(const struct nf_hook_ops *ops, +static unsigned int ip6table_nat_local_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_nat_ipv6_local_fn(ops, skb, state, ip6table_nat_do_chain); + return nf_nat_ipv6_local_fn(priv, skb, state, ip6table_nat_do_chain); } static struct nf_hook_ops nf_nat_ipv6_ops[] __read_mostly = { diff --git a/net/ipv6/netfilter/ip6table_raw.c b/net/ipv6/netfilter/ip6table_raw.c index 0b33caad2b69..9021963565c3 100644 --- a/net/ipv6/netfilter/ip6table_raw.c +++ b/net/ipv6/netfilter/ip6table_raw.c @@ -19,12 +19,10 @@ static const struct xt_table packet_raw = { /* The work comes in here from netfilter.c. */ static unsigned int -ip6table_raw_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, +ip6table_raw_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - const struct net *net = dev_net(state->in ? state->in : state->out); - - return ip6t_do_table(skb, ops->hooknum, state, net->ipv6.ip6table_raw); + return ip6t_do_table(skb, state, state->net->ipv6.ip6table_raw); } static struct nf_hook_ops *rawtable_ops __read_mostly; diff --git a/net/ipv6/netfilter/ip6table_security.c b/net/ipv6/netfilter/ip6table_security.c index fcef83c25f7b..0d856fedfeb0 100644 --- a/net/ipv6/netfilter/ip6table_security.c +++ b/net/ipv6/netfilter/ip6table_security.c @@ -36,13 +36,10 @@ static const struct xt_table security_table = { }; static unsigned int -ip6table_security_hook(const struct nf_hook_ops *ops, struct sk_buff *skb, +ip6table_security_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - const struct net *net = dev_net(state->in ? state->in : state->out); - - return ip6t_do_table(skb, ops->hooknum, state, - net->ipv6.ip6table_security); + return ip6t_do_table(skb, state, state->net->ipv6.ip6table_security); } static struct nf_hook_ops *sectbl_ops __read_mostly; diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index 7302900c321a..dd83ad42f8f6 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -95,7 +95,7 @@ static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, return NF_ACCEPT; } -static unsigned int ipv6_helper(const struct nf_hook_ops *ops, +static unsigned int ipv6_helper(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -131,7 +131,7 @@ static unsigned int ipv6_helper(const struct nf_hook_ops *ops, return helper->help(skb, protoff, ct, ctinfo); } -static unsigned int ipv6_confirm(const struct nf_hook_ops *ops, +static unsigned int ipv6_confirm(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -165,14 +165,14 @@ out: return nf_conntrack_confirm(skb); } -static unsigned int ipv6_conntrack_in(const struct nf_hook_ops *ops, +static unsigned int ipv6_conntrack_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_conntrack_in(dev_net(state->in), PF_INET6, ops->hooknum, skb); + return nf_conntrack_in(state->net, PF_INET6, state->hook, skb); } -static unsigned int ipv6_conntrack_local(const struct nf_hook_ops *ops, +static unsigned int ipv6_conntrack_local(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -181,7 +181,7 @@ static unsigned int ipv6_conntrack_local(const struct nf_hook_ops *ops, net_notice_ratelimited("ipv6_conntrack_local: packet too short\n"); return NF_ACCEPT; } - return nf_conntrack_in(dev_net(state->out), PF_INET6, ops->hooknum, skb); + return nf_conntrack_in(state->net, PF_INET6, state->hook, skb); } static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = { diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index 0e6fae103d33..d3b797446cea 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -36,6 +36,7 @@ static inline struct nf_icmp_net *icmpv6_pernet(struct net *net) static bool icmpv6_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, + struct net *net, struct nf_conntrack_tuple *tuple) { const struct icmp6hdr *hp; @@ -159,7 +160,7 @@ icmpv6_error_message(struct net *net, struct nf_conn *tmpl, skb_network_offset(skb) + sizeof(struct ipv6hdr) + sizeof(struct icmp6hdr), - PF_INET6, &origtuple)) { + PF_INET6, net, &origtuple)) { pr_debug("icmpv6_error: Can't get tuple\n"); return -NF_ACCEPT; } diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c index 6d9c0b3d5b8c..a99baf63eccf 100644 --- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -51,7 +51,7 @@ static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum, return IP6_DEFRAG_CONNTRACK_OUT + zone_id; } -static unsigned int ipv6_defrag(const struct nf_hook_ops *ops, +static unsigned int ipv6_defrag(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -63,7 +63,7 @@ static unsigned int ipv6_defrag(const struct nf_hook_ops *ops, return NF_ACCEPT; #endif - reasm = nf_ct_frag6_gather(skb, nf_ct6_defrag_user(ops->hooknum, skb)); + reasm = nf_ct_frag6_gather(skb, nf_ct6_defrag_user(state->hook, skb)); /* queued */ if (reasm == NULL) return NF_STOLEN; @@ -74,7 +74,7 @@ static unsigned int ipv6_defrag(const struct nf_hook_ops *ops, nf_ct_frag6_consume_orig(reasm); - NF_HOOK_THRESH(NFPROTO_IPV6, ops->hooknum, state->sk, reasm, + NF_HOOK_THRESH(NFPROTO_IPV6, state->hook, state->net, state->sk, reasm, state->in, state->out, state->okfn, NF_IP6_PRI_CONNTRACK_DEFRAG + 1); diff --git a/net/ipv6/netfilter/nf_dup_ipv6.c b/net/ipv6/netfilter/nf_dup_ipv6.c index c8ab626556a0..ee0d9a5b16c3 100644 --- a/net/ipv6/netfilter/nf_dup_ipv6.c +++ b/net/ipv6/netfilter/nf_dup_ipv6.c @@ -19,25 +19,10 @@ #include <net/netfilter/nf_conntrack.h> #endif -static struct net *pick_net(struct sk_buff *skb) -{ -#ifdef CONFIG_NET_NS - const struct dst_entry *dst; - - if (skb->dev != NULL) - return dev_net(skb->dev); - dst = skb_dst(skb); - if (dst != NULL && dst->dev != NULL) - return dev_net(dst->dev); -#endif - return &init_net; -} - -static bool nf_dup_ipv6_route(struct sk_buff *skb, const struct in6_addr *gw, - int oif) +static bool nf_dup_ipv6_route(struct net *net, struct sk_buff *skb, + const struct in6_addr *gw, int oif) { const struct ipv6hdr *iph = ipv6_hdr(skb); - struct net *net = pick_net(skb); struct dst_entry *dst; struct flowi6 fl6; @@ -61,7 +46,7 @@ static bool nf_dup_ipv6_route(struct sk_buff *skb, const struct in6_addr *gw, return true; } -void nf_dup_ipv6(struct sk_buff *skb, unsigned int hooknum, +void nf_dup_ipv6(struct net *net, struct sk_buff *skb, unsigned int hooknum, const struct in6_addr *gw, int oif) { if (this_cpu_read(nf_skb_duplicated)) @@ -81,7 +66,7 @@ void nf_dup_ipv6(struct sk_buff *skb, unsigned int hooknum, struct ipv6hdr *iph = ipv6_hdr(skb); --iph->hop_limit; } - if (nf_dup_ipv6_route(skb, gw, oif)) { + if (nf_dup_ipv6_route(net, skb, gw, oif)) { __this_cpu_write(nf_skb_duplicated, true); ip6_local_out(skb); __this_cpu_write(nf_skb_duplicated, false); diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c index 70fbaed49edb..238e70c3f7b7 100644 --- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c @@ -262,9 +262,9 @@ int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, EXPORT_SYMBOL_GPL(nf_nat_icmpv6_reply_translation); unsigned int -nf_nat_ipv6_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, +nf_nat_ipv6_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)) @@ -272,7 +272,7 @@ nf_nat_ipv6_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, struct nf_conn *ct; enum ip_conntrack_info ctinfo; struct nf_conn_nat *nat; - enum nf_nat_manip_type maniptype = HOOK2MANIP(ops->hooknum); + enum nf_nat_manip_type maniptype = HOOK2MANIP(state->hook); __be16 frag_off; int hdrlen; u8 nexthdr; @@ -303,7 +303,7 @@ nf_nat_ipv6_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) { if (!nf_nat_icmpv6_reply_translation(skb, ct, ctinfo, - ops->hooknum, + state->hook, hdrlen)) return NF_DROP; else @@ -317,21 +317,21 @@ nf_nat_ipv6_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, if (!nf_nat_initialized(ct, maniptype)) { unsigned int ret; - ret = do_chain(ops, skb, state, ct); + ret = do_chain(priv, skb, state, ct); if (ret != NF_ACCEPT) return ret; - if (nf_nat_initialized(ct, HOOK2MANIP(ops->hooknum))) + if (nf_nat_initialized(ct, HOOK2MANIP(state->hook))) break; - ret = nf_nat_alloc_null_binding(ct, ops->hooknum); + ret = nf_nat_alloc_null_binding(ct, state->hook); if (ret != NF_ACCEPT) return ret; } else { pr_debug("Already setup manip %s for ct %p\n", maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST", ct); - if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, state->out)) + if (nf_nat_oif_changed(state->hook, ctinfo, nat, state->out)) goto oif_changed; } break; @@ -340,11 +340,11 @@ nf_nat_ipv6_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, /* ESTABLISHED */ NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED || ctinfo == IP_CT_ESTABLISHED_REPLY); - if (nf_nat_oif_changed(ops->hooknum, ctinfo, nat, state->out)) + if (nf_nat_oif_changed(state->hook, ctinfo, nat, state->out)) goto oif_changed; } - return nf_nat_packet(ct, ctinfo, ops->hooknum, skb); + return nf_nat_packet(ct, ctinfo, state->hook, skb); oif_changed: nf_ct_kill_acct(ct, ctinfo, skb); @@ -353,9 +353,9 @@ oif_changed: EXPORT_SYMBOL_GPL(nf_nat_ipv6_fn); unsigned int -nf_nat_ipv6_in(const struct nf_hook_ops *ops, struct sk_buff *skb, +nf_nat_ipv6_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)) @@ -363,7 +363,7 @@ nf_nat_ipv6_in(const struct nf_hook_ops *ops, struct sk_buff *skb, unsigned int ret; struct in6_addr daddr = ipv6_hdr(skb)->daddr; - ret = nf_nat_ipv6_fn(ops, skb, state, do_chain); + ret = nf_nat_ipv6_fn(priv, skb, state, do_chain); if (ret != NF_DROP && ret != NF_STOLEN && ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr)) skb_dst_drop(skb); @@ -373,9 +373,9 @@ nf_nat_ipv6_in(const struct nf_hook_ops *ops, struct sk_buff *skb, EXPORT_SYMBOL_GPL(nf_nat_ipv6_in); unsigned int -nf_nat_ipv6_out(const struct nf_hook_ops *ops, struct sk_buff *skb, +nf_nat_ipv6_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)) @@ -391,7 +391,7 @@ nf_nat_ipv6_out(const struct nf_hook_ops *ops, struct sk_buff *skb, if (skb->len < sizeof(struct ipv6hdr)) return NF_ACCEPT; - ret = nf_nat_ipv6_fn(ops, skb, state, do_chain); + ret = nf_nat_ipv6_fn(priv, skb, state, do_chain); #ifdef CONFIG_XFRM if (ret != NF_DROP && ret != NF_STOLEN && !(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) && @@ -403,7 +403,7 @@ nf_nat_ipv6_out(const struct nf_hook_ops *ops, struct sk_buff *skb, (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 && ct->tuplehash[dir].tuple.src.u.all != ct->tuplehash[!dir].tuple.dst.u.all)) { - err = nf_xfrm_me_harder(skb, AF_INET6); + err = nf_xfrm_me_harder(state->net, skb, AF_INET6); if (err < 0) ret = NF_DROP_ERR(err); } @@ -414,9 +414,9 @@ nf_nat_ipv6_out(const struct nf_hook_ops *ops, struct sk_buff *skb, EXPORT_SYMBOL_GPL(nf_nat_ipv6_out); unsigned int -nf_nat_ipv6_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, +nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, - unsigned int (*do_chain)(const struct nf_hook_ops *ops, + unsigned int (*do_chain)(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct)) @@ -430,14 +430,14 @@ nf_nat_ipv6_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, if (skb->len < sizeof(struct ipv6hdr)) return NF_ACCEPT; - ret = nf_nat_ipv6_fn(ops, skb, state, do_chain); + ret = nf_nat_ipv6_fn(priv, skb, state, do_chain); if (ret != NF_DROP && ret != NF_STOLEN && (ct = nf_ct_get(skb, &ctinfo)) != NULL) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3, &ct->tuplehash[!dir].tuple.src.u3)) { - err = ip6_route_me_harder(skb); + err = ip6_route_me_harder(state->net, skb); if (err < 0) ret = NF_DROP_ERR(err); } @@ -446,7 +446,7 @@ nf_nat_ipv6_local_fn(const struct nf_hook_ops *ops, struct sk_buff *skb, ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 && ct->tuplehash[dir].tuple.dst.u.all != ct->tuplehash[!dir].tuple.src.u.all) { - err = nf_xfrm_me_harder(skb, AF_INET6); + err = nf_xfrm_me_harder(state->net, skb, AF_INET6); if (err < 0) ret = NF_DROP_ERR(err); } diff --git a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c index 7745609665cd..31ba7ca19757 100644 --- a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c @@ -34,7 +34,7 @@ nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range *range, NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY)); - if (ipv6_dev_get_saddr(dev_net(out), out, + if (ipv6_dev_get_saddr(nf_ct_net(ct), out, &ipv6_hdr(skb)->daddr, 0, &src) < 0) return NF_DROP; diff --git a/net/ipv6/netfilter/nf_tables_ipv6.c b/net/ipv6/netfilter/nf_tables_ipv6.c index c8148ba76d1a..120ea9131be0 100644 --- a/net/ipv6/netfilter/nf_tables_ipv6.c +++ b/net/ipv6/netfilter/nf_tables_ipv6.c @@ -16,20 +16,20 @@ #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_ipv6.h> -static unsigned int nft_do_chain_ipv6(const struct nf_hook_ops *ops, +static unsigned int nft_do_chain_ipv6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nft_pktinfo pkt; /* malformed packet, drop it */ - if (nft_set_pktinfo_ipv6(&pkt, ops, skb, state) < 0) + if (nft_set_pktinfo_ipv6(&pkt, skb, state) < 0) return NF_DROP; - return nft_do_chain(&pkt, ops); + return nft_do_chain(&pkt, priv); } -static unsigned int nft_ipv6_output(const struct nf_hook_ops *ops, +static unsigned int nft_ipv6_output(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -40,7 +40,7 @@ static unsigned int nft_ipv6_output(const struct nf_hook_ops *ops, return NF_ACCEPT; } - return nft_do_chain_ipv6(ops, skb, state); + return nft_do_chain_ipv6(priv, skb, state); } struct nft_af_info nft_af_ipv6 __read_mostly = { diff --git a/net/ipv6/netfilter/nft_chain_nat_ipv6.c b/net/ipv6/netfilter/nft_chain_nat_ipv6.c index 951bb458b7bd..443cd306c0b0 100644 --- a/net/ipv6/netfilter/nft_chain_nat_ipv6.c +++ b/net/ipv6/netfilter/nft_chain_nat_ipv6.c @@ -24,44 +24,44 @@ #include <net/netfilter/nf_nat_l3proto.h> #include <net/ipv6.h> -static unsigned int nft_nat_do_chain(const struct nf_hook_ops *ops, +static unsigned int nft_nat_do_chain(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, struct nf_conn *ct) { struct nft_pktinfo pkt; - nft_set_pktinfo_ipv6(&pkt, ops, skb, state); + nft_set_pktinfo_ipv6(&pkt, skb, state); - return nft_do_chain(&pkt, ops); + return nft_do_chain(&pkt, priv); } -static unsigned int nft_nat_ipv6_fn(const struct nf_hook_ops *ops, +static unsigned int nft_nat_ipv6_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_nat_ipv6_fn(ops, skb, state, nft_nat_do_chain); + return nf_nat_ipv6_fn(priv, skb, state, nft_nat_do_chain); } -static unsigned int nft_nat_ipv6_in(const struct nf_hook_ops *ops, +static unsigned int nft_nat_ipv6_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_nat_ipv6_in(ops, skb, state, nft_nat_do_chain); + return nf_nat_ipv6_in(priv, skb, state, nft_nat_do_chain); } -static unsigned int nft_nat_ipv6_out(const struct nf_hook_ops *ops, +static unsigned int nft_nat_ipv6_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_nat_ipv6_out(ops, skb, state, nft_nat_do_chain); + return nf_nat_ipv6_out(priv, skb, state, nft_nat_do_chain); } -static unsigned int nft_nat_ipv6_local_fn(const struct nf_hook_ops *ops, +static unsigned int nft_nat_ipv6_local_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return nf_nat_ipv6_local_fn(ops, skb, state, nft_nat_do_chain); + return nf_nat_ipv6_local_fn(priv, skb, state, nft_nat_do_chain); } static const struct nf_chain_type nft_chain_nat_ipv6 = { diff --git a/net/ipv6/netfilter/nft_chain_route_ipv6.c b/net/ipv6/netfilter/nft_chain_route_ipv6.c index 0dafdaac5e17..9df75bd7c94a 100644 --- a/net/ipv6/netfilter/nft_chain_route_ipv6.c +++ b/net/ipv6/netfilter/nft_chain_route_ipv6.c @@ -22,7 +22,7 @@ #include <net/netfilter/nf_tables_ipv6.h> #include <net/route.h> -static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops, +static unsigned int nf_route_table_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -33,7 +33,7 @@ static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops, u32 mark, flowlabel; /* malformed packet, drop it */ - if (nft_set_pktinfo_ipv6(&pkt, ops, skb, state) < 0) + if (nft_set_pktinfo_ipv6(&pkt, skb, state) < 0) return NF_DROP; /* save source/dest address, mark, hoplimit, flowlabel, priority */ @@ -45,14 +45,14 @@ static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops, /* flowlabel and prio (includes version, which shouldn't change either */ flowlabel = *((u32 *)ipv6_hdr(skb)); - ret = nft_do_chain(&pkt, ops); + ret = nft_do_chain(&pkt, priv); if (ret != NF_DROP && ret != NF_QUEUE && (memcmp(&ipv6_hdr(skb)->saddr, &saddr, sizeof(saddr)) || memcmp(&ipv6_hdr(skb)->daddr, &daddr, sizeof(daddr)) || skb->mark != mark || ipv6_hdr(skb)->hop_limit != hop_limit || flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) - return ip6_route_me_harder(skb) == 0 ? ret : NF_DROP; + return ip6_route_me_harder(state->net, skb) == 0 ? ret : NF_DROP; return ret; } diff --git a/net/ipv6/netfilter/nft_dup_ipv6.c b/net/ipv6/netfilter/nft_dup_ipv6.c index 0eaa4f65fdea..8bfd470cbe72 100644 --- a/net/ipv6/netfilter/nft_dup_ipv6.c +++ b/net/ipv6/netfilter/nft_dup_ipv6.c @@ -28,7 +28,7 @@ static void nft_dup_ipv6_eval(const struct nft_expr *expr, struct in6_addr *gw = (struct in6_addr *)®s->data[priv->sreg_addr]; int oif = regs->data[priv->sreg_dev]; - nf_dup_ipv6(pkt->skb, pkt->ops->hooknum, gw, oif); + nf_dup_ipv6(pkt->net, pkt->skb, pkt->hook, gw, oif); } static int nft_dup_ipv6_init(const struct nft_ctx *ctx, diff --git a/net/ipv6/netfilter/nft_redir_ipv6.c b/net/ipv6/netfilter/nft_redir_ipv6.c index effd393bd517..aca44e89a881 100644 --- a/net/ipv6/netfilter/nft_redir_ipv6.c +++ b/net/ipv6/netfilter/nft_redir_ipv6.c @@ -35,8 +35,7 @@ static void nft_redir_ipv6_eval(const struct nft_expr *expr, range.flags |= priv->flags; - regs->verdict.code = nf_nat_redirect_ipv6(pkt->skb, &range, - pkt->ops->hooknum); + regs->verdict.code = nf_nat_redirect_ipv6(pkt->skb, &range, pkt->hook); } static struct nft_expr_type nft_redir_ipv6_type; diff --git a/net/ipv6/netfilter/nft_reject_ipv6.c b/net/ipv6/netfilter/nft_reject_ipv6.c index d0d1540ecf87..533cd5719c59 100644 --- a/net/ipv6/netfilter/nft_reject_ipv6.c +++ b/net/ipv6/netfilter/nft_reject_ipv6.c @@ -24,15 +24,14 @@ static void nft_reject_ipv6_eval(const struct nft_expr *expr, const struct nft_pktinfo *pkt) { struct nft_reject *priv = nft_expr_priv(expr); - struct net *net = dev_net((pkt->in != NULL) ? pkt->in : pkt->out); switch (priv->type) { case NFT_REJECT_ICMP_UNREACH: - nf_send_unreach6(net, pkt->skb, priv->icmp_code, - pkt->ops->hooknum); + nf_send_unreach6(pkt->net, pkt->skb, priv->icmp_code, + pkt->hook); break; case NFT_REJECT_TCP_RST: - nf_send_reset6(net, pkt->skb, pkt->ops->hooknum); + nf_send_reset6(pkt->net, pkt->skb, pkt->hook); break; default: break; diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c index 928a0fb0b744..e77102c4f804 100644 --- a/net/ipv6/output_core.c +++ b/net/ipv6/output_core.c @@ -140,6 +140,7 @@ EXPORT_SYMBOL(ip6_dst_hoplimit); static int __ip6_local_out_sk(struct sock *sk, struct sk_buff *skb) { + struct net *net = dev_net(skb_dst(skb)->dev); int len; len = skb->len - sizeof(struct ipv6hdr); @@ -148,8 +149,9 @@ static int __ip6_local_out_sk(struct sock *sk, struct sk_buff *skb) ipv6_hdr(skb)->payload_len = htons(len); IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr); - return nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, sk, skb, - NULL, skb_dst(skb)->dev, dst_output_sk); + return nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, + net, sk, skb, NULL, skb_dst(skb)->dev, + dst_output_okfn); } int __ip6_local_out(struct sk_buff *skb) @@ -164,7 +166,7 @@ int ip6_local_out_sk(struct sock *sk, struct sk_buff *skb) err = __ip6_local_out_sk(sk, skb); if (likely(err == 1)) - err = dst_output_sk(sk, skb); + err = dst_output(sk, skb); return err; } diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index fdbada1569a3..fec0151522a2 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -614,6 +614,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, unsigned int flags) { struct ipv6_pinfo *np = inet6_sk(sk); + struct net *net = sock_net(sk); struct ipv6hdr *iph; struct sk_buff *skb; int err; @@ -652,9 +653,9 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, if (err) goto error_fault; - IP6_UPD_PO_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); - err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, sk, skb, - NULL, rt->dst.dev, dst_output_sk); + IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); + err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, + NULL, rt->dst.dev, dst_output_okfn); if (err > 0) err = net_xmit_errno(err); if (err) @@ -666,7 +667,7 @@ error_fault: err = -EFAULT; kfree_skb(skb); error: - IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); + IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); if (err == -ENOBUFS && !np->recverr) err = 0; return err; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index cb32ce250db0..d3d946773a3e 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -421,31 +421,7 @@ static bool rt6_check_expired(const struct rt6_info *rt) static int rt6_info_hash_nhsfn(unsigned int candidate_count, const struct flowi6 *fl6) { - unsigned int val = fl6->flowi6_proto; - - val ^= ipv6_addr_hash(&fl6->daddr); - val ^= ipv6_addr_hash(&fl6->saddr); - - /* Work only if this not encapsulated */ - switch (fl6->flowi6_proto) { - case IPPROTO_UDP: - case IPPROTO_TCP: - case IPPROTO_SCTP: - val ^= (__force u16)fl6->fl6_sport; - val ^= (__force u16)fl6->fl6_dport; - break; - - case IPPROTO_ICMPV6: - val ^= (__force u16)fl6->fl6_icmp_type; - val ^= (__force u16)fl6->fl6_icmp_code; - break; - } - /* RFC6438 recommands to use flowlabel */ - val ^= (__force u32)fl6->flowlabel; - - /* Perhaps, we need to tune, this function? */ - val = val ^ (val >> 7) ^ (val >> 12); - return val % candidate_count; + return get_hash_from_flowi6(fl6) % candidate_count; } static struct rt6_info *rt6_multipath_select(struct rt6_info *match, @@ -498,10 +474,10 @@ static inline struct rt6_info *rt6_device_match(struct net *net, if (dev->flags & IFF_LOOPBACK) { if (!sprt->rt6i_idev || sprt->rt6i_idev->dev->ifindex != oif) { - if (flags & RT6_LOOKUP_F_IFACE && oif) + if (flags & RT6_LOOKUP_F_IFACE) continue; - if (local && (!oif || - local->rt6i_idev->dev->ifindex == oif)) + if (local && + local->rt6i_idev->dev->ifindex == oif) continue; } local = sprt; @@ -538,7 +514,7 @@ static void rt6_probe_deferred(struct work_struct *w) container_of(w, struct __rt6_probe_work, work); addrconf_addr_solict_mult(&work->target, &mcaddr); - ndisc_send_ns(work->dev, NULL, &work->target, &mcaddr, NULL, NULL); + ndisc_send_ns(work->dev, &work->target, &mcaddr, NULL, NULL); dev_put(work->dev); kfree(work); } diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 0909f4e0d53c..7606eba83e7b 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -114,14 +114,11 @@ u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph, } EXPORT_SYMBOL_GPL(__cookie_v6_init_sequence); -__u32 cookie_v6_init_sequence(struct sock *sk, const struct sk_buff *skb, __u16 *mssp) +__u32 cookie_v6_init_sequence(const struct sk_buff *skb, __u16 *mssp) { const struct ipv6hdr *iph = ipv6_hdr(skb); const struct tcphdr *th = tcp_hdr(skb); - tcp_synq_overflow(sk); - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESSENT); - return __cookie_v6_init_sequence(iph, th, mssp); } @@ -210,7 +207,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ireq->wscale_ok = tcp_opt.wscale_ok; ireq->tstamp_ok = tcp_opt.saw_tstamp; req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; - treq->snt_synack = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsecr : 0; + treq->snt_synack.v64 = 0; treq->rcv_isn = ntohl(th->seq) - 1; treq->snt_isn = cookie; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 97d9314ea361..2ae95e1d03e1 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -70,8 +70,8 @@ #include <linux/crypto.h> #include <linux/scatterlist.h> -static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb); -static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, +static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb); +static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, struct request_sock *req); static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb); @@ -82,7 +82,7 @@ static const struct inet_connection_sock_af_ops ipv6_specific; static const struct tcp_sock_af_ops tcp_sock_ipv6_specific; static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific; #else -static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk, +static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(const struct sock *sk, const struct in6_addr *addr) { return NULL; @@ -434,7 +434,7 @@ out: } -static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst, +static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, u16 queue_mapping, @@ -447,7 +447,8 @@ static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst, int err = -ENOMEM; /* First, grab a route. */ - if (!dst && (dst = inet6_csk_route_req(sk, fl6, req)) == NULL) + if (!dst && (dst = inet6_csk_route_req(sk, fl6, req, + IPPROTO_TCP)) == NULL) goto done; skb = tcp_make_synack(sk, dst, req, foc); @@ -476,13 +477,13 @@ static void tcp_v6_reqsk_destructor(struct request_sock *req) } #ifdef CONFIG_TCP_MD5SIG -static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk, +static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(const struct sock *sk, const struct in6_addr *addr) { return tcp_md5_do_lookup(sk, (union tcp_md5_addr *)addr, AF_INET6); } -static struct tcp_md5sig_key *tcp_v6_md5_lookup(struct sock *sk, +static struct tcp_md5sig_key *tcp_v6_md5_lookup(const struct sock *sk, const struct sock *addr_sk) { return tcp_v6_md5_do_lookup(sk, &addr_sk->sk_v6_daddr); @@ -663,22 +664,23 @@ static bool tcp_v6_inbound_md5_hash(struct sock *sk, const struct sk_buff *skb) } #endif -static void tcp_v6_init_req(struct request_sock *req, struct sock *sk, +static void tcp_v6_init_req(struct request_sock *req, + const struct sock *sk_listener, struct sk_buff *skb) { struct inet_request_sock *ireq = inet_rsk(req); - struct ipv6_pinfo *np = inet6_sk(sk); + const struct ipv6_pinfo *np = inet6_sk(sk_listener); ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; /* So that link locals have meaning */ - if (!sk->sk_bound_dev_if && + if (!sk_listener->sk_bound_dev_if && ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL) ireq->ir_iif = tcp_v6_iif(skb); if (!TCP_SKB_CB(skb)->tcp_tw_isn && - (ipv6_opt_accepted(sk, skb, &TCP_SKB_CB(skb)->header.h6) || + (ipv6_opt_accepted(sk_listener, skb, &TCP_SKB_CB(skb)->header.h6) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim || np->repflow)) { @@ -687,13 +689,14 @@ static void tcp_v6_init_req(struct request_sock *req, struct sock *sk, } } -static struct dst_entry *tcp_v6_route_req(struct sock *sk, struct flowi *fl, +static struct dst_entry *tcp_v6_route_req(const struct sock *sk, + struct flowi *fl, const struct request_sock *req, bool *strict) { if (strict) *strict = true; - return inet6_csk_route_req(sk, &fl->u.ip6, req); + return inet6_csk_route_req(sk, &fl->u.ip6, req, IPPROTO_TCP); } struct request_sock_ops tcp6_request_sock_ops __read_mostly = { @@ -723,7 +726,7 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { .queue_hash_add = inet6_csk_reqsk_queue_hash_add, }; -static void tcp_v6_send_response(struct sock *sk, struct sk_buff *skb, u32 seq, +static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 tsval, u32 tsecr, int oif, struct tcp_md5sig_key *key, int rst, u8 tclass, u32 label) @@ -822,7 +825,7 @@ static void tcp_v6_send_response(struct sock *sk, struct sk_buff *skb, u32 seq, kfree_skb(buff); } -static void tcp_v6_send_reset(struct sock *sk, struct sk_buff *skb) +static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) { const struct tcphdr *th = tcp_hdr(skb); u32 seq = 0, ack_seq = 0; @@ -893,7 +896,7 @@ release_sk1: #endif } -static void tcp_v6_send_ack(struct sock *sk, struct sk_buff *skb, u32 seq, +static void tcp_v6_send_ack(const struct sock *sk, struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 tsval, u32 tsecr, int oif, struct tcp_md5sig_key *key, u8 tclass, u32 label) @@ -916,7 +919,7 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) inet_twsk_put(tw); } -static void tcp_v6_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, +static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, struct request_sock *req) { /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV @@ -984,12 +987,13 @@ drop: return 0; /* don't send reset */ } -static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, +static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst) { struct inet_request_sock *ireq; - struct ipv6_pinfo *newnp, *np = inet6_sk(sk); + struct ipv6_pinfo *newnp; + const struct ipv6_pinfo *np = inet6_sk(sk); struct tcp6_sock *newtcp6sk; struct inet_sock *newinet; struct tcp_sock *newtp; @@ -1057,7 +1061,7 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, goto out_overflow; if (!dst) { - dst = inet6_csk_route_req(sk, &fl6, req); + dst = inet6_csk_route_req(sk, &fl6, req, IPPROTO_TCP); if (!dst) goto out; } @@ -1090,8 +1094,6 @@ static struct sock *tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr; newsk->sk_bound_dev_if = ireq->ir_iif; - sk_set_txhash(newsk); - /* Now IPv6 options... First: no IPv4 options. @@ -1273,7 +1275,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) } else sock_rps_save_rxhash(sk, skb); - if (tcp_rcv_state_process(sk, skb, tcp_hdr(skb), skb->len)) + if (tcp_rcv_state_process(sk, skb)) goto reset; if (opt_skb) goto ipv6_pktoptions; @@ -1670,7 +1672,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) const struct inet_sock *inet = inet_sk(sp); const struct tcp_sock *tp = tcp_sk(sp); const struct inet_connection_sock *icsk = inet_csk(sp); - struct fastopen_queue *fastopenq = icsk->icsk_accept_queue.fastopenq; + const struct fastopen_queue *fastopenq = &icsk->icsk_accept_queue.fastopenq; dest = &sp->sk_v6_daddr; src = &sp->sk_v6_rcv_saddr; @@ -1714,7 +1716,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) (icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong, tp->snd_cwnd, sp->sk_state == TCP_LISTEN ? - (fastopenq ? fastopenq->max_qlen : 0) : + fastopenq->max_qlen : (tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh) ); } diff --git a/net/ipv6/xfrm6_input.c b/net/ipv6/xfrm6_input.c index 74bd17882a2f..0eaab1fa6be5 100644 --- a/net/ipv6/xfrm6_input.c +++ b/net/ipv6/xfrm6_input.c @@ -42,8 +42,8 @@ int xfrm6_transport_finish(struct sk_buff *skb, int async) ipv6_hdr(skb)->payload_len = htons(skb->len); __skb_push(skb, skb->data - skb_network_header(skb)); - NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, NULL, skb, - skb->dev, NULL, + NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING, + dev_net(skb->dev), NULL, skb, skb->dev, NULL, ip6_rcv_finish); return -1; } diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 09c76a7b474d..0c3e9ffcf231 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -131,7 +131,7 @@ int xfrm6_output_finish(struct sock *sk, struct sk_buff *skb) return xfrm_output(sk, skb); } -static int __xfrm6_output(struct sock *sk, struct sk_buff *skb) +static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct xfrm_state *x = dst->xfrm; @@ -140,7 +140,7 @@ static int __xfrm6_output(struct sock *sk, struct sk_buff *skb) #ifdef CONFIG_NETFILTER if (!x) { IP6CB(skb)->flags |= IP6SKB_REROUTED; - return dst_output_sk(sk, skb); + return dst_output(sk, skb); } #endif @@ -168,7 +168,10 @@ static int __xfrm6_output(struct sock *sk, struct sk_buff *skb) int xfrm6_output(struct sock *sk, struct sk_buff *skb) { - return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, sk, skb, - NULL, skb_dst(skb)->dev, __xfrm6_output, + struct net *net = dev_net(skb_dst(skb)->dev); + + return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING, + net, sk, skb, NULL, skb_dst(skb)->dev, + __xfrm6_output, !(IP6CB(skb)->flags & IP6SKB_REROUTED)); } diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 30caa289c5db..69cee4e0d728 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -20,7 +20,7 @@ #include <net/ip.h> #include <net/ipv6.h> #include <net/ip6_route.h> -#include <net/vrf.h> +#include <net/l3mdev.h> #if IS_ENABLED(CONFIG_IPV6_MIP6) #include <net/mip6.h> #endif @@ -132,10 +132,8 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) nexthdr = nh[nhoff]; - if (skb_dst(skb)) { - oif = vrf_master_ifindex(skb_dst(skb)->dev) ? - : skb_dst(skb)->dev->ifindex; - } + if (skb_dst(skb)) + oif = l3mdev_fib_oif(skb_dst(skb)->dev); memset(fl6, 0, sizeof(struct flowi6)); fl6->flowi6_mark = skb->mark; diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 918151c11348..fcb2752419c6 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -95,11 +95,10 @@ static void afiucv_hs_callback_txnotify(struct sk_buff *, enum iucv_tx_notify); /* Call Back functions */ static void iucv_callback_rx(struct iucv_path *, struct iucv_message *); static void iucv_callback_txdone(struct iucv_path *, struct iucv_message *); -static void iucv_callback_connack(struct iucv_path *, u8 ipuser[16]); -static int iucv_callback_connreq(struct iucv_path *, u8 ipvmid[8], - u8 ipuser[16]); -static void iucv_callback_connrej(struct iucv_path *, u8 ipuser[16]); -static void iucv_callback_shutdown(struct iucv_path *, u8 ipuser[16]); +static void iucv_callback_connack(struct iucv_path *, u8 *); +static int iucv_callback_connreq(struct iucv_path *, u8 *, u8 *); +static void iucv_callback_connrej(struct iucv_path *, u8 *); +static void iucv_callback_shutdown(struct iucv_path *, u8 *); static struct iucv_sock_list iucv_sk_list = { .lock = __RW_LOCK_UNLOCKED(iucv_sk_list.lock), diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index 2a6a1fdd62c0..7eaa000c9258 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -713,7 +713,7 @@ static struct notifier_block __refdata iucv_cpu_notifier = { * * Sever an iucv path to free up the pathid. Used internally. */ -static int iucv_sever_pathid(u16 pathid, u8 userdata[16]) +static int iucv_sever_pathid(u16 pathid, u8 *userdata) { union iucv_param *parm; @@ -876,7 +876,7 @@ static struct notifier_block iucv_reboot_notifier = { * Returns the result of the CP IUCV call. */ int iucv_path_accept(struct iucv_path *path, struct iucv_handler *handler, - u8 userdata[16], void *private) + u8 *userdata, void *private) { union iucv_param *parm; int rc; @@ -923,7 +923,7 @@ EXPORT_SYMBOL(iucv_path_accept); * Returns the result of the CP IUCV call. */ int iucv_path_connect(struct iucv_path *path, struct iucv_handler *handler, - u8 userid[8], u8 system[8], u8 userdata[16], + u8 *userid, u8 *system, u8 *userdata, void *private) { union iucv_param *parm; @@ -985,7 +985,7 @@ EXPORT_SYMBOL(iucv_path_connect); * * Returns the result from the CP IUCV call. */ -int iucv_path_quiesce(struct iucv_path *path, u8 userdata[16]) +int iucv_path_quiesce(struct iucv_path *path, u8 *userdata) { union iucv_param *parm; int rc; @@ -1017,7 +1017,7 @@ EXPORT_SYMBOL(iucv_path_quiesce); * * Returns the result from the CP IUCV call. */ -int iucv_path_resume(struct iucv_path *path, u8 userdata[16]) +int iucv_path_resume(struct iucv_path *path, u8 *userdata) { union iucv_param *parm; int rc; @@ -1047,7 +1047,7 @@ out: * * Returns the result from the CP IUCV call. */ -int iucv_path_sever(struct iucv_path *path, u8 userdata[16]) +int iucv_path_sever(struct iucv_path *path, u8 *userdata) { int rc; diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index 68aa9ffd4ae4..5871537af387 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -321,4 +321,7 @@ do { \ #define l2tp_dbg(ptr, type, fmt, ...) \ l2tp_printk(ptr, type, pr_debug, fmt, ##__VA_ARGS__) +#define MODULE_ALIAS_L2TP_PWTYPE(type) \ + MODULE_ALIAS("net-l2tp-type-" __stringify(type)) + #endif /* _L2TP_CORE_H_ */ diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index 4b552873b556..e253c26f31ac 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -358,3 +358,4 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("James Chapman <jchapman@katalix.com>"); MODULE_DESCRIPTION("L2TP ethernet pseudowire driver"); MODULE_VERSION("1.0"); +MODULE_ALIAS_L2TP_PWTYPE(5); diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 79649937ec71..ec22078b0914 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -655,3 +655,4 @@ MODULE_VERSION("1.0"); * enums */ MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET, 2, IPPROTO_L2TP); +MODULE_ALIAS_NET_PF_PROTO(PF_INET, IPPROTO_L2TP); diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index d1ded3777815..aca38d8aed8e 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -801,3 +801,4 @@ MODULE_VERSION("1.0"); * enums */ MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 2, IPPROTO_L2TP); +MODULE_ALIAS_NET_PF_PROTO(PF_INET6, IPPROTO_L2TP); diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index 9e13c2ff8789..f93c5be612a7 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -576,6 +576,13 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf if (info->attrs[L2TP_ATTR_MRU]) cfg.mru = nla_get_u16(info->attrs[L2TP_ATTR_MRU]); +#ifdef CONFIG_MODULES + if (l2tp_nl_cmd_ops[cfg.pw_type] == NULL) { + genl_unlock(); + request_module("net-l2tp-type-%u", cfg.pw_type); + genl_lock(); + } +#endif if ((l2tp_nl_cmd_ops[cfg.pw_type] == NULL) || (l2tp_nl_cmd_ops[cfg.pw_type]->session_create == NULL)) { ret = -EPROTONOSUPPORT; diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index f56c9f69e9f2..1ad18c55064c 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -1863,3 +1863,4 @@ MODULE_DESCRIPTION("PPP over L2TP over UDP"); MODULE_LICENSE("GPL"); MODULE_VERSION(PPPOL2TP_DRV_VERSION); MODULE_ALIAS("pppox-proto-" __stringify(PX_PROTO_OL2TP)); +MODULE_ALIAS_L2TP_PWTYPE(11); diff --git a/net/l3mdev/Kconfig b/net/l3mdev/Kconfig new file mode 100644 index 000000000000..5d47325037bc --- /dev/null +++ b/net/l3mdev/Kconfig @@ -0,0 +1,10 @@ +# +# Configuration for L3 master device support +# + +config NET_L3_MASTER_DEV + bool "L3 Master device support" + depends on INET || IPV6 + ---help--- + This module provides glue between core networking code and device + drivers to support L3 master devices like VRF. diff --git a/net/l3mdev/Makefile b/net/l3mdev/Makefile new file mode 100644 index 000000000000..84a53a6f609a --- /dev/null +++ b/net/l3mdev/Makefile @@ -0,0 +1,5 @@ +# +# Makefile for the L3 device API +# + +obj-$(CONFIG_NET_L3_MASTER_DEV) += l3mdev.o diff --git a/net/l3mdev/l3mdev.c b/net/l3mdev/l3mdev.c new file mode 100644 index 000000000000..ddf75ad41713 --- /dev/null +++ b/net/l3mdev/l3mdev.c @@ -0,0 +1,92 @@ +/* + * net/l3mdev/l3mdev.c - L3 master device implementation + * Copyright (c) 2015 Cumulus Networks + * Copyright (c) 2015 David Ahern <dsa@cumulusnetworks.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/netdevice.h> +#include <net/l3mdev.h> + +/** + * l3mdev_master_ifindex - get index of L3 master device + * @dev: targeted interface + */ + +int l3mdev_master_ifindex_rcu(struct net_device *dev) +{ + int ifindex = 0; + + if (!dev) + return 0; + + if (netif_is_l3_master(dev)) { + ifindex = dev->ifindex; + } else if (dev->flags & IFF_SLAVE) { + struct net_device *master; + + master = netdev_master_upper_dev_get_rcu(dev); + if (master && netif_is_l3_master(master)) + ifindex = master->ifindex; + } + + return ifindex; +} +EXPORT_SYMBOL_GPL(l3mdev_master_ifindex_rcu); + +/** + * l3mdev_fib_table - get FIB table id associated with an L3 + * master interface + * @dev: targeted interface + */ + +u32 l3mdev_fib_table_rcu(const struct net_device *dev) +{ + u32 tb_id = 0; + + if (!dev) + return 0; + + if (netif_is_l3_master(dev)) { + if (dev->l3mdev_ops->l3mdev_fib_table) + tb_id = dev->l3mdev_ops->l3mdev_fib_table(dev); + } else if (dev->flags & IFF_SLAVE) { + /* Users of netdev_master_upper_dev_get_rcu need non-const, + * but current inet_*type functions take a const + */ + struct net_device *_dev = (struct net_device *) dev; + const struct net_device *master; + + master = netdev_master_upper_dev_get_rcu(_dev); + if (master && netif_is_l3_master(master) && + master->l3mdev_ops->l3mdev_fib_table) + tb_id = master->l3mdev_ops->l3mdev_fib_table(master); + } + + return tb_id; +} +EXPORT_SYMBOL_GPL(l3mdev_fib_table_rcu); + +u32 l3mdev_fib_table_by_index(struct net *net, int ifindex) +{ + struct net_device *dev; + u32 tb_id = 0; + + if (!ifindex) + return 0; + + rcu_read_lock(); + + dev = dev_get_by_index_rcu(net, ifindex); + if (dev) + tb_id = l3mdev_fib_table_rcu(dev); + + rcu_read_unlock(); + + return tb_id; +} +EXPORT_SYMBOL_GPL(l3mdev_fib_table_by_index); diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 8e47f8113495..2e907335ee81 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -269,7 +269,7 @@ unsigned int nf_iterate(struct list_head *head, /* Optimization: we don't need to hold module reference here, since function can't sleep. --RR */ repeat: - verdict = (*elemp)->hook(*elemp, skb, state); + verdict = (*elemp)->hook((*elemp)->priv, skb, state); if (verdict != NF_ACCEPT) { #ifdef CONFIG_NETFILTER_DEBUG if (unlikely((verdict & NF_VERDICT_MASK) diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 338b4047776f..69ab9c2634e1 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -519,8 +519,7 @@ int ip_set_test(ip_set_id_t index, const struct sk_buff *skb, const struct xt_action_param *par, struct ip_set_adt_opt *opt) { - struct ip_set *set = ip_set_rcu_get( - dev_net(par->in ? par->in : par->out), index); + struct ip_set *set = ip_set_rcu_get(par->net, index); int ret = 0; BUG_ON(!set); @@ -558,8 +557,7 @@ int ip_set_add(ip_set_id_t index, const struct sk_buff *skb, const struct xt_action_param *par, struct ip_set_adt_opt *opt) { - struct ip_set *set = ip_set_rcu_get( - dev_net(par->in ? par->in : par->out), index); + struct ip_set *set = ip_set_rcu_get(par->net, index); int ret; BUG_ON(!set); @@ -581,8 +579,7 @@ int ip_set_del(ip_set_id_t index, const struct sk_buff *skb, const struct xt_action_param *par, struct ip_set_adt_opt *opt) { - struct ip_set *set = ip_set_rcu_get( - dev_net(par->in ? par->in : par->out), index); + struct ip_set *set = ip_set_rcu_get(par->net, index); int ret = 0; BUG_ON(!set); diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index dfd7b65b3d2a..0328f7250693 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -75,7 +75,7 @@ static void ip_vs_app_inc_rcu_free(struct rcu_head *head) * Allocate/initialize app incarnation and register it in proto apps. */ static int -ip_vs_app_inc_new(struct net *net, struct ip_vs_app *app, __u16 proto, +ip_vs_app_inc_new(struct netns_ipvs *ipvs, struct ip_vs_app *app, __u16 proto, __u16 port) { struct ip_vs_protocol *pp; @@ -107,7 +107,7 @@ ip_vs_app_inc_new(struct net *net, struct ip_vs_app *app, __u16 proto, } } - ret = pp->register_app(net, inc); + ret = pp->register_app(ipvs, inc); if (ret) goto out; @@ -127,7 +127,7 @@ ip_vs_app_inc_new(struct net *net, struct ip_vs_app *app, __u16 proto, * Release app incarnation */ static void -ip_vs_app_inc_release(struct net *net, struct ip_vs_app *inc) +ip_vs_app_inc_release(struct netns_ipvs *ipvs, struct ip_vs_app *inc) { struct ip_vs_protocol *pp; @@ -135,7 +135,7 @@ ip_vs_app_inc_release(struct net *net, struct ip_vs_app *inc) return; if (pp->unregister_app) - pp->unregister_app(net, inc); + pp->unregister_app(ipvs, inc); IP_VS_DBG(9, "%s App %s:%u unregistered\n", pp->name, inc->name, ntohs(inc->port)); @@ -175,14 +175,14 @@ void ip_vs_app_inc_put(struct ip_vs_app *inc) * Register an application incarnation in protocol applications */ int -register_ip_vs_app_inc(struct net *net, struct ip_vs_app *app, __u16 proto, +register_ip_vs_app_inc(struct netns_ipvs *ipvs, struct ip_vs_app *app, __u16 proto, __u16 port) { int result; mutex_lock(&__ip_vs_app_mutex); - result = ip_vs_app_inc_new(net, app, proto, port); + result = ip_vs_app_inc_new(ipvs, app, proto, port); mutex_unlock(&__ip_vs_app_mutex); @@ -191,15 +191,11 @@ register_ip_vs_app_inc(struct net *net, struct ip_vs_app *app, __u16 proto, /* Register application for netns */ -struct ip_vs_app *register_ip_vs_app(struct net *net, struct ip_vs_app *app) +struct ip_vs_app *register_ip_vs_app(struct netns_ipvs *ipvs, struct ip_vs_app *app) { - struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_app *a; int err = 0; - if (!ipvs) - return ERR_PTR(-ENOENT); - mutex_lock(&__ip_vs_app_mutex); list_for_each_entry(a, &ipvs->app_list, a_list) { @@ -230,21 +226,17 @@ out_unlock: * We are sure there are no app incarnations attached to services * Caller should use synchronize_rcu() or rcu_barrier() */ -void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app) +void unregister_ip_vs_app(struct netns_ipvs *ipvs, struct ip_vs_app *app) { - struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_app *a, *anxt, *inc, *nxt; - if (!ipvs) - return; - mutex_lock(&__ip_vs_app_mutex); list_for_each_entry_safe(a, anxt, &ipvs->app_list, a_list) { if (app && strcmp(app->name, a->name)) continue; list_for_each_entry_safe(inc, nxt, &a->incs_list, a_list) { - ip_vs_app_inc_release(net, inc); + ip_vs_app_inc_release(ipvs, inc); } list_del(&a->a_list); @@ -611,17 +603,19 @@ static const struct file_operations ip_vs_app_fops = { }; #endif -int __net_init ip_vs_app_net_init(struct net *net) +int __net_init ip_vs_app_net_init(struct netns_ipvs *ipvs) { - struct netns_ipvs *ipvs = net_ipvs(net); + struct net *net = ipvs->net; INIT_LIST_HEAD(&ipvs->app_list); proc_create("ip_vs_app", 0, net->proc_net, &ip_vs_app_fops); return 0; } -void __net_exit ip_vs_app_net_cleanup(struct net *net) +void __net_exit ip_vs_app_net_cleanup(struct netns_ipvs *ipvs) { - unregister_ip_vs_app(net, NULL /* all */); + struct net *net = ipvs->net; + + unregister_ip_vs_app(ipvs, NULL /* all */); remove_proc_entry("ip_vs_app", net->proc_net); } diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index b0f7b626b56d..d1d168c7fc68 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -108,7 +108,7 @@ static inline void ct_write_unlock_bh(unsigned int key) /* * Returns hash value for IPVS connection entry */ -static unsigned int ip_vs_conn_hashkey(struct net *net, int af, unsigned int proto, +static unsigned int ip_vs_conn_hashkey(struct netns_ipvs *ipvs, int af, unsigned int proto, const union nf_inet_addr *addr, __be16 port) { @@ -116,11 +116,11 @@ static unsigned int ip_vs_conn_hashkey(struct net *net, int af, unsigned int pro if (af == AF_INET6) return (jhash_3words(jhash(addr, 16, ip_vs_conn_rnd), (__force u32)port, proto, ip_vs_conn_rnd) ^ - ((size_t)net>>8)) & ip_vs_conn_tab_mask; + ((size_t)ipvs>>8)) & ip_vs_conn_tab_mask; #endif return (jhash_3words((__force u32)addr->ip, (__force u32)port, proto, ip_vs_conn_rnd) ^ - ((size_t)net>>8)) & ip_vs_conn_tab_mask; + ((size_t)ipvs>>8)) & ip_vs_conn_tab_mask; } static unsigned int ip_vs_conn_hashkey_param(const struct ip_vs_conn_param *p, @@ -141,14 +141,14 @@ static unsigned int ip_vs_conn_hashkey_param(const struct ip_vs_conn_param *p, port = p->vport; } - return ip_vs_conn_hashkey(p->net, p->af, p->protocol, addr, port); + return ip_vs_conn_hashkey(p->ipvs, p->af, p->protocol, addr, port); } static unsigned int ip_vs_conn_hashkey_conn(const struct ip_vs_conn *cp) { struct ip_vs_conn_param p; - ip_vs_conn_fill_param(ip_vs_conn_net(cp), cp->af, cp->protocol, + ip_vs_conn_fill_param(cp->ipvs, cp->af, cp->protocol, &cp->caddr, cp->cport, NULL, 0, &p); if (cp->pe) { @@ -279,7 +279,7 @@ __ip_vs_conn_in_get(const struct ip_vs_conn_param *p) ip_vs_addr_equal(p->af, p->vaddr, &cp->vaddr) && ((!p->cport) ^ (!(cp->flags & IP_VS_CONN_F_NO_CPORT))) && p->protocol == cp->protocol && - ip_vs_conn_net_eq(cp, p->net)) { + cp->ipvs == p->ipvs) { if (!__ip_vs_conn_get(cp)) continue; /* HIT */ @@ -314,33 +314,34 @@ struct ip_vs_conn *ip_vs_conn_in_get(const struct ip_vs_conn_param *p) } static int -ip_vs_conn_fill_param_proto(int af, const struct sk_buff *skb, +ip_vs_conn_fill_param_proto(struct netns_ipvs *ipvs, + int af, const struct sk_buff *skb, const struct ip_vs_iphdr *iph, - int inverse, struct ip_vs_conn_param *p) + struct ip_vs_conn_param *p) { __be16 _ports[2], *pptr; - struct net *net = skb_net(skb); pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports, iph); if (pptr == NULL) return 1; - if (likely(!inverse)) - ip_vs_conn_fill_param(net, af, iph->protocol, &iph->saddr, + if (likely(!ip_vs_iph_inverse(iph))) + ip_vs_conn_fill_param(ipvs, af, iph->protocol, &iph->saddr, pptr[0], &iph->daddr, pptr[1], p); else - ip_vs_conn_fill_param(net, af, iph->protocol, &iph->daddr, + ip_vs_conn_fill_param(ipvs, af, iph->protocol, &iph->daddr, pptr[1], &iph->saddr, pptr[0], p); return 0; } struct ip_vs_conn * -ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb, - const struct ip_vs_iphdr *iph, int inverse) +ip_vs_conn_in_get_proto(struct netns_ipvs *ipvs, int af, + const struct sk_buff *skb, + const struct ip_vs_iphdr *iph) { struct ip_vs_conn_param p; - if (ip_vs_conn_fill_param_proto(af, skb, iph, inverse, &p)) + if (ip_vs_conn_fill_param_proto(ipvs, af, skb, iph, &p)) return NULL; return ip_vs_conn_in_get(&p); @@ -359,7 +360,7 @@ struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p) hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[hash], c_list) { if (unlikely(p->pe_data && p->pe->ct_match)) { - if (!ip_vs_conn_net_eq(cp, p->net)) + if (cp->ipvs != p->ipvs) continue; if (p->pe == cp->pe && p->pe->ct_match(p, cp)) { if (__ip_vs_conn_get(cp)) @@ -377,7 +378,7 @@ struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p) p->vport == cp->vport && p->cport == cp->cport && cp->flags & IP_VS_CONN_F_TEMPLATE && p->protocol == cp->protocol && - ip_vs_conn_net_eq(cp, p->net)) { + cp->ipvs == p->ipvs) { if (__ip_vs_conn_get(cp)) goto out; } @@ -418,7 +419,7 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p) ip_vs_addr_equal(p->af, p->vaddr, &cp->caddr) && ip_vs_addr_equal(p->af, p->caddr, &cp->daddr) && p->protocol == cp->protocol && - ip_vs_conn_net_eq(cp, p->net)) { + cp->ipvs == p->ipvs) { if (!__ip_vs_conn_get(cp)) continue; /* HIT */ @@ -439,12 +440,13 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p) } struct ip_vs_conn * -ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb, - const struct ip_vs_iphdr *iph, int inverse) +ip_vs_conn_out_get_proto(struct netns_ipvs *ipvs, int af, + const struct sk_buff *skb, + const struct ip_vs_iphdr *iph) { struct ip_vs_conn_param p; - if (ip_vs_conn_fill_param_proto(af, skb, iph, inverse, &p)) + if (ip_vs_conn_fill_param_proto(ipvs, af, skb, iph, &p)) return NULL; return ip_vs_conn_out_get(&p); @@ -638,7 +640,7 @@ void ip_vs_try_bind_dest(struct ip_vs_conn *cp) * so we can make the assumption that the svc_af is the same as the * dest_af */ - dest = ip_vs_find_dest(ip_vs_conn_net(cp), cp->af, cp->af, &cp->daddr, + dest = ip_vs_find_dest(cp->ipvs, cp->af, cp->af, &cp->daddr, cp->dport, &cp->vaddr, cp->vport, cp->protocol, cp->fwmark, cp->flags); if (dest) { @@ -668,7 +670,7 @@ void ip_vs_try_bind_dest(struct ip_vs_conn *cp) #endif ip_vs_bind_xmit(cp); - pd = ip_vs_proto_data_get(ip_vs_conn_net(cp), cp->protocol); + pd = ip_vs_proto_data_get(cp->ipvs, cp->protocol); if (pd && atomic_read(&pd->appcnt)) ip_vs_bind_app(cp, pd->pp); } @@ -746,7 +748,7 @@ static int expire_quiescent_template(struct netns_ipvs *ipvs, int ip_vs_check_template(struct ip_vs_conn *ct) { struct ip_vs_dest *dest = ct->dest; - struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(ct)); + struct netns_ipvs *ipvs = ct->ipvs; /* * Checking the dest server status. @@ -800,8 +802,7 @@ static void ip_vs_conn_rcu_free(struct rcu_head *head) static void ip_vs_conn_expire(unsigned long data) { struct ip_vs_conn *cp = (struct ip_vs_conn *)data; - struct net *net = ip_vs_conn_net(cp); - struct netns_ipvs *ipvs = net_ipvs(net); + struct netns_ipvs *ipvs = cp->ipvs; /* * do I control anybody? @@ -847,7 +848,7 @@ static void ip_vs_conn_expire(unsigned long data) cp->timeout = 60*HZ; if (ipvs->sync_state & IP_VS_STATE_MASTER) - ip_vs_sync_conn(net, cp, sysctl_sync_threshold(ipvs)); + ip_vs_sync_conn(ipvs, cp, sysctl_sync_threshold(ipvs)); ip_vs_conn_put(cp); } @@ -875,8 +876,8 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, int dest_af, struct ip_vs_dest *dest, __u32 fwmark) { struct ip_vs_conn *cp; - struct netns_ipvs *ipvs = net_ipvs(p->net); - struct ip_vs_proto_data *pd = ip_vs_proto_data_get(p->net, + struct netns_ipvs *ipvs = p->ipvs; + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(p->ipvs, p->protocol); cp = kmem_cache_alloc(ip_vs_conn_cachep, GFP_ATOMIC); @@ -887,7 +888,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, int dest_af, INIT_HLIST_NODE(&cp->c_list); setup_timer(&cp->timer, ip_vs_conn_expire, (unsigned long)cp); - ip_vs_conn_net_set(cp, p->net); + cp->ipvs = ipvs; cp->af = p->af; cp->daf = dest_af; cp->protocol = p->protocol; @@ -1061,7 +1062,7 @@ static int ip_vs_conn_seq_show(struct seq_file *seq, void *v) size_t len = 0; char dbuf[IP_VS_ADDRSTRLEN]; - if (!ip_vs_conn_net_eq(cp, net)) + if (!net_eq(cp->ipvs->net, net)) return 0; if (cp->pe_data) { pe_data[0] = ' '; @@ -1146,7 +1147,7 @@ static int ip_vs_conn_sync_seq_show(struct seq_file *seq, void *v) const struct ip_vs_conn *cp = v; struct net *net = seq_file_net(seq); - if (!ip_vs_conn_net_eq(cp, net)) + if (!net_eq(cp->ipvs->net, net)) return 0; #ifdef CONFIG_IP_VS_IPV6 @@ -1240,7 +1241,7 @@ static inline int todrop_entry(struct ip_vs_conn *cp) } /* Called from keventd and must protect itself from softirqs */ -void ip_vs_random_dropentry(struct net *net) +void ip_vs_random_dropentry(struct netns_ipvs *ipvs) { int idx; struct ip_vs_conn *cp, *cp_c; @@ -1256,7 +1257,7 @@ void ip_vs_random_dropentry(struct net *net) if (cp->flags & IP_VS_CONN_F_TEMPLATE) /* connection template */ continue; - if (!ip_vs_conn_net_eq(cp, net)) + if (cp->ipvs != ipvs) continue; if (cp->protocol == IPPROTO_TCP) { switch(cp->state) { @@ -1308,18 +1309,17 @@ void ip_vs_random_dropentry(struct net *net) /* * Flush all the connection entries in the ip_vs_conn_tab */ -static void ip_vs_conn_flush(struct net *net) +static void ip_vs_conn_flush(struct netns_ipvs *ipvs) { int idx; struct ip_vs_conn *cp, *cp_c; - struct netns_ipvs *ipvs = net_ipvs(net); flush_again: rcu_read_lock(); for (idx = 0; idx < ip_vs_conn_tab_size; idx++) { hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[idx], c_list) { - if (!ip_vs_conn_net_eq(cp, net)) + if (cp->ipvs != ipvs) continue; IP_VS_DBG(4, "del connection\n"); ip_vs_conn_expire_now(cp); @@ -1345,9 +1345,9 @@ flush_again: /* * per netns init and exit */ -int __net_init ip_vs_conn_net_init(struct net *net) +int __net_init ip_vs_conn_net_init(struct netns_ipvs *ipvs) { - struct netns_ipvs *ipvs = net_ipvs(net); + struct net *net = ipvs->net; atomic_set(&ipvs->conn_count, 0); @@ -1356,10 +1356,12 @@ int __net_init ip_vs_conn_net_init(struct net *net) return 0; } -void __net_exit ip_vs_conn_net_cleanup(struct net *net) +void __net_exit ip_vs_conn_net_cleanup(struct netns_ipvs *ipvs) { + struct net *net = ipvs->net; + /* flush all the connection entries first */ - ip_vs_conn_flush(net); + ip_vs_conn_flush(ipvs); remove_proc_entry("ip_vs_conn", net->proc_net); remove_proc_entry("ip_vs_conn_sync", net->proc_net); } diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 38fbc194b9cb..37dd77a3d0fb 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -112,7 +112,7 @@ static inline void ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb) { struct ip_vs_dest *dest = cp->dest; - struct netns_ipvs *ipvs = net_ipvs(skb_net(skb)); + struct netns_ipvs *ipvs = cp->ipvs; if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { struct ip_vs_cpu_stats *s; @@ -146,7 +146,7 @@ static inline void ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb) { struct ip_vs_dest *dest = cp->dest; - struct netns_ipvs *ipvs = net_ipvs(skb_net(skb)); + struct netns_ipvs *ipvs = cp->ipvs; if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { struct ip_vs_cpu_stats *s; @@ -179,7 +179,7 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb) static inline void ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc) { - struct netns_ipvs *ipvs = net_ipvs(svc->net); + struct netns_ipvs *ipvs = svc->ipvs; struct ip_vs_cpu_stats *s; s = this_cpu_ptr(cp->dest->stats.cpustats); @@ -215,7 +215,7 @@ ip_vs_conn_fill_param_persist(const struct ip_vs_service *svc, const union nf_inet_addr *vaddr, __be16 vport, struct ip_vs_conn_param *p) { - ip_vs_conn_fill_param(svc->net, svc->af, protocol, caddr, cport, vaddr, + ip_vs_conn_fill_param(svc->ipvs, svc->af, protocol, caddr, cport, vaddr, vport, p); p->pe = rcu_dereference(svc->pe); if (p->pe && p->pe->fill_param) @@ -245,20 +245,30 @@ ip_vs_sched_persist(struct ip_vs_service *svc, const union nf_inet_addr fwmark = { .ip = htonl(svc->fwmark) }; union nf_inet_addr snet; /* source network of the client, after masking */ + const union nf_inet_addr *src_addr, *dst_addr; + + if (likely(!ip_vs_iph_inverse(iph))) { + src_addr = &iph->saddr; + dst_addr = &iph->daddr; + } else { + src_addr = &iph->daddr; + dst_addr = &iph->saddr; + } + /* Mask saddr with the netmask to adjust template granularity */ #ifdef CONFIG_IP_VS_IPV6 if (svc->af == AF_INET6) - ipv6_addr_prefix(&snet.in6, &iph->saddr.in6, + ipv6_addr_prefix(&snet.in6, &src_addr->in6, (__force __u32) svc->netmask); else #endif - snet.ip = iph->saddr.ip & svc->netmask; + snet.ip = src_addr->ip & svc->netmask; IP_VS_DBG_BUF(6, "p-schedule: src %s:%u dest %s:%u " "mnet %s\n", - IP_VS_DBG_ADDR(svc->af, &iph->saddr), ntohs(src_port), - IP_VS_DBG_ADDR(svc->af, &iph->daddr), ntohs(dst_port), + IP_VS_DBG_ADDR(svc->af, src_addr), ntohs(src_port), + IP_VS_DBG_ADDR(svc->af, dst_addr), ntohs(dst_port), IP_VS_DBG_ADDR(svc->af, &snet)); /* @@ -276,7 +286,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc, */ { int protocol = iph->protocol; - const union nf_inet_addr *vaddr = &iph->daddr; + const union nf_inet_addr *vaddr = dst_addr; __be16 vport = 0; if (dst_port == svc->port) { @@ -366,8 +376,8 @@ ip_vs_sched_persist(struct ip_vs_service *svc, /* * Create a new connection according to the template */ - ip_vs_conn_fill_param(svc->net, svc->af, iph->protocol, &iph->saddr, - src_port, &iph->daddr, dst_port, ¶m); + ip_vs_conn_fill_param(svc->ipvs, svc->af, iph->protocol, src_addr, + src_port, dst_addr, dst_port, ¶m); cp = ip_vs_conn_new(¶m, dest->af, &dest->addr, dport, flags, dest, skb->mark); @@ -418,7 +428,8 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, struct ip_vs_conn *cp = NULL; struct ip_vs_scheduler *sched; struct ip_vs_dest *dest; - __be16 _ports[2], *pptr; + __be16 _ports[2], *pptr, cport, vport; + const void *caddr, *vaddr; unsigned int flags; *ignored = 1; @@ -429,14 +440,26 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, if (pptr == NULL) return NULL; + if (likely(!ip_vs_iph_inverse(iph))) { + cport = pptr[0]; + caddr = &iph->saddr; + vport = pptr[1]; + vaddr = &iph->daddr; + } else { + cport = pptr[1]; + caddr = &iph->daddr; + vport = pptr[0]; + vaddr = &iph->saddr; + } + /* * FTPDATA needs this check when using local real server. * Never schedule Active FTPDATA connections from real server. * For LVS-NAT they must be already created. For other methods * with persistence the connection is created on SYN+ACK. */ - if (pptr[0] == FTPDATA) { - IP_VS_DBG_PKT(12, svc->af, pp, skb, 0, + if (cport == FTPDATA) { + IP_VS_DBG_PKT(12, svc->af, pp, skb, iph->off, "Not scheduling FTPDATA"); return NULL; } @@ -444,19 +467,25 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, /* * Do not schedule replies from local real server. */ - if ((!skb->dev || skb->dev->flags & IFF_LOOPBACK) && - (cp = pp->conn_in_get(svc->af, skb, iph, 1))) { - IP_VS_DBG_PKT(12, svc->af, pp, skb, 0, - "Not scheduling reply for existing connection"); - __ip_vs_conn_put(cp); - return NULL; + if ((!skb->dev || skb->dev->flags & IFF_LOOPBACK)) { + iph->hdr_flags ^= IP_VS_HDR_INVERSE; + cp = pp->conn_in_get(svc->ipvs, svc->af, skb, iph); + iph->hdr_flags ^= IP_VS_HDR_INVERSE; + + if (cp) { + IP_VS_DBG_PKT(12, svc->af, pp, skb, iph->off, + "Not scheduling reply for existing" + " connection"); + __ip_vs_conn_put(cp); + return NULL; + } } /* * Persistent service */ if (svc->flags & IP_VS_SVC_F_PERSISTENT) - return ip_vs_sched_persist(svc, skb, pptr[0], pptr[1], ignored, + return ip_vs_sched_persist(svc, skb, cport, vport, ignored, iph); *ignored = 0; @@ -464,7 +493,7 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, /* * Non-persistent service */ - if (!svc->fwmark && pptr[1] != svc->port) { + if (!svc->fwmark && vport != svc->port) { if (!svc->port) pr_err("Schedule: port zero only supported " "in persistent services, " @@ -495,11 +524,10 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, { struct ip_vs_conn_param p; - ip_vs_conn_fill_param(svc->net, svc->af, iph->protocol, - &iph->saddr, pptr[0], &iph->daddr, - pptr[1], &p); + ip_vs_conn_fill_param(svc->ipvs, svc->af, iph->protocol, + caddr, cport, vaddr, vport, &p); cp = ip_vs_conn_new(&p, dest->af, &dest->addr, - dest->port ? dest->port : pptr[1], + dest->port ? dest->port : vport, flags, dest, skb->mark); if (!cp) { *ignored = -1; @@ -519,6 +547,17 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, return cp; } +#ifdef CONFIG_SYSCTL +static inline int ip_vs_addr_is_unicast(struct net *net, int af, + union nf_inet_addr *addr) +{ +#ifdef CONFIG_IP_VS_IPV6 + if (af == AF_INET6) + return ipv6_addr_type(&addr->in6) & IPV6_ADDR_UNICAST; +#endif + return (inet_addr_type(net, addr->ip) == RTN_UNICAST); +} +#endif /* * Pass or drop the packet. @@ -528,33 +567,21 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, struct ip_vs_proto_data *pd, struct ip_vs_iphdr *iph) { - __be16 _ports[2], *pptr; -#ifdef CONFIG_SYSCTL - struct net *net; - struct netns_ipvs *ipvs; - int unicast; -#endif + __be16 _ports[2], *pptr, dport; + struct netns_ipvs *ipvs = svc->ipvs; + struct net *net = ipvs->net; pptr = frag_safe_skb_hp(skb, iph->len, sizeof(_ports), _ports, iph); - if (pptr == NULL) { + if (!pptr) return NF_DROP; - } - -#ifdef CONFIG_SYSCTL - net = skb_net(skb); - -#ifdef CONFIG_IP_VS_IPV6 - if (svc->af == AF_INET6) - unicast = ipv6_addr_type(&iph->daddr.in6) & IPV6_ADDR_UNICAST; - else -#endif - unicast = (inet_addr_type(net, iph->daddr.ip) == RTN_UNICAST); + dport = likely(!ip_vs_iph_inverse(iph)) ? pptr[1] : pptr[0]; /* if it is fwmark-based service, the cache_bypass sysctl is up and the destination is a non-local unicast, then create a cache_bypass connection entry */ - ipvs = net_ipvs(net); - if (ipvs->sysctl_cache_bypass && svc->fwmark && unicast) { + if (sysctl_cache_bypass(ipvs) && svc->fwmark && + !(iph->hdr_flags & (IP_VS_HDR_INVERSE | IP_VS_HDR_ICMP)) && + ip_vs_addr_is_unicast(net, svc->af, &iph->daddr)) { int ret; struct ip_vs_conn *cp; unsigned int flags = (svc->flags & IP_VS_SVC_F_ONEPACKET && @@ -566,7 +593,7 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, IP_VS_DBG(6, "%s(): create a cache_bypass entry\n", __func__); { struct ip_vs_conn_param p; - ip_vs_conn_fill_param(svc->net, svc->af, iph->protocol, + ip_vs_conn_fill_param(svc->ipvs, svc->af, iph->protocol, &iph->saddr, pptr[0], &iph->daddr, pptr[1], &p); cp = ip_vs_conn_new(&p, svc->af, &daddr, 0, @@ -590,7 +617,6 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, ip_vs_conn_put(cp); return ret; } -#endif /* * When the virtual ftp service is presented, packets destined @@ -598,9 +624,12 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, * listed in the ipvs table), pass the packets, because it is * not ipvs job to decide to drop the packets. */ - if ((svc->port == FTPPORT) && (pptr[1] != FTPPORT)) + if (svc->port == FTPPORT && dport != FTPPORT) return NF_ACCEPT; + if (unlikely(ip_vs_iph_icmp(iph))) + return NF_DROP; + /* * Notify the client that the destination is unreachable, and * release the socket buffer. @@ -610,11 +639,8 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, */ #ifdef CONFIG_IP_VS_IPV6 if (svc->af == AF_INET6) { - if (!skb->dev) { - struct net *net_ = dev_net(skb_dst(skb)->dev); - - skb->dev = net_->loopback_dev; - } + if (!skb->dev) + skb->dev = net->loopback_dev; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); } else #endif @@ -625,15 +651,13 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, #ifdef CONFIG_SYSCTL -static int sysctl_snat_reroute(struct sk_buff *skb) +static int sysctl_snat_reroute(struct netns_ipvs *ipvs) { - struct netns_ipvs *ipvs = net_ipvs(skb_net(skb)); return ipvs->sysctl_snat_reroute; } -static int sysctl_nat_icmp_send(struct net *net) +static int sysctl_nat_icmp_send(struct netns_ipvs *ipvs) { - struct netns_ipvs *ipvs = net_ipvs(net); return ipvs->sysctl_nat_icmp_send; } @@ -644,8 +668,8 @@ static int sysctl_expire_nodest_conn(struct netns_ipvs *ipvs) #else -static int sysctl_snat_reroute(struct sk_buff *skb) { return 0; } -static int sysctl_nat_icmp_send(struct net *net) { return 0; } +static int sysctl_snat_reroute(struct netns_ipvs *ipvs) { return 0; } +static int sysctl_nat_icmp_send(struct netns_ipvs *ipvs) { return 0; } static int sysctl_expire_nodest_conn(struct netns_ipvs *ipvs) { return 0; } #endif @@ -664,7 +688,8 @@ static inline enum ip_defrag_users ip_vs_defrag_user(unsigned int hooknum) return IP_DEFRAG_VS_OUT; } -static inline int ip_vs_gather_frags(struct sk_buff *skb, u_int32_t user) +static inline int ip_vs_gather_frags(struct netns_ipvs *ipvs, + struct sk_buff *skb, u_int32_t user) { int err; @@ -677,10 +702,10 @@ static inline int ip_vs_gather_frags(struct sk_buff *skb, u_int32_t user) return err; } -static int ip_vs_route_me_harder(int af, struct sk_buff *skb, - unsigned int hooknum) +static int ip_vs_route_me_harder(struct netns_ipvs *ipvs, int af, + struct sk_buff *skb, unsigned int hooknum) { - if (!sysctl_snat_reroute(skb)) + if (!sysctl_snat_reroute(ipvs)) return 0; /* Reroute replies only to remote clients (FORWARD and LOCAL_OUT) */ if (NF_INET_LOCAL_IN == hooknum) @@ -690,12 +715,12 @@ static int ip_vs_route_me_harder(int af, struct sk_buff *skb, struct dst_entry *dst = skb_dst(skb); if (dst->dev && !(dst->dev->flags & IFF_LOOPBACK) && - ip6_route_me_harder(skb) != 0) + ip6_route_me_harder(ipvs->net, skb) != 0) return 1; } else #endif if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL) && - ip_route_me_harder(skb, RTN_LOCAL) != 0) + ip_route_me_harder(ipvs->net, skb, RTN_LOCAL) != 0) return 1; return 0; @@ -848,7 +873,7 @@ static int handle_response_icmp(int af, struct sk_buff *skb, #endif ip_vs_nat_icmp(skb, pp, cp, 1); - if (ip_vs_route_me_harder(af, skb, hooknum)) + if (ip_vs_route_me_harder(cp->ipvs, af, skb, hooknum)) goto out; /* do the statistics and put it back */ @@ -872,8 +897,8 @@ out: * Find any that might be relevant, check against existing connections. * Currently handles error types - unreachable, quench, ttl exceeded. */ -static int ip_vs_out_icmp(struct sk_buff *skb, int *related, - unsigned int hooknum) +static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, + int *related, unsigned int hooknum) { struct iphdr *iph; struct icmphdr _icmph, *ic; @@ -888,7 +913,7 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related, /* reassemble IP fragments */ if (ip_is_fragment(ip_hdr(skb))) { - if (ip_vs_gather_frags(skb, ip_vs_defrag_user(hooknum))) + if (ip_vs_gather_frags(ipvs, skb, ip_vs_defrag_user(hooknum))) return NF_STOLEN; } @@ -934,10 +959,10 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related, IP_VS_DBG_PKT(11, AF_INET, pp, skb, offset, "Checking outgoing ICMP for"); - ip_vs_fill_ip4hdr(cih, &ciph); - ciph.len += offset; + ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, true, &ciph); + /* The embedded headers contain source and dest in reverse order */ - cp = pp->conn_out_get(AF_INET, skb, &ciph, 1); + cp = pp->conn_out_get(ipvs, AF_INET, skb, &ciph); if (!cp) return NF_ACCEPT; @@ -947,16 +972,16 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related, } #ifdef CONFIG_IP_VS_IPV6 -static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related, - unsigned int hooknum, struct ip_vs_iphdr *ipvsh) +static int ip_vs_out_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, + int *related, unsigned int hooknum, + struct ip_vs_iphdr *ipvsh) { struct icmp6hdr _icmph, *ic; - struct ipv6hdr _ip6h, *ip6h; /* The ip header contained within ICMP */ struct ip_vs_iphdr ciph = {.flags = 0, .fragoffs = 0};/*Contained IP */ struct ip_vs_conn *cp; struct ip_vs_protocol *pp; union nf_inet_addr snet; - unsigned int writable; + unsigned int offset; *related = 1; ic = frag_safe_skb_hp(skb, ipvsh->len, sizeof(_icmph), &_icmph, ipvsh); @@ -984,31 +1009,23 @@ static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related, ic->icmp6_type, ntohs(icmpv6_id(ic)), &ipvsh->saddr, &ipvsh->daddr); - /* Now find the contained IP header */ - ciph.len = ipvsh->len + sizeof(_icmph); - ip6h = skb_header_pointer(skb, ciph.len, sizeof(_ip6h), &_ip6h); - if (ip6h == NULL) + if (!ip_vs_fill_iph_skb_icmp(AF_INET6, skb, ipvsh->len + sizeof(_icmph), + true, &ciph)) return NF_ACCEPT; /* The packet looks wrong, ignore */ - ciph.saddr.in6 = ip6h->saddr; /* conn_out_get() handles reverse order */ - ciph.daddr.in6 = ip6h->daddr; - /* skip possible IPv6 exthdrs of contained IPv6 packet */ - ciph.protocol = ipv6_find_hdr(skb, &ciph.len, -1, &ciph.fragoffs, NULL); - if (ciph.protocol < 0) - return NF_ACCEPT; /* Contained IPv6 hdr looks wrong, ignore */ pp = ip_vs_proto_get(ciph.protocol); if (!pp) return NF_ACCEPT; /* The embedded headers contain source and dest in reverse order */ - cp = pp->conn_out_get(AF_INET6, skb, &ciph, 1); + cp = pp->conn_out_get(ipvs, AF_INET6, skb, &ciph); if (!cp) return NF_ACCEPT; snet.in6 = ciph.saddr.in6; - writable = ciph.len; + offset = ciph.len; return handle_response_icmp(AF_INET6, skb, &snet, ciph.protocol, cp, - pp, writable, sizeof(struct ipv6hdr), + pp, offset, sizeof(struct ipv6hdr), hooknum); } #endif @@ -1093,7 +1110,7 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, { struct ip_vs_protocol *pp = pd->pp; - IP_VS_DBG_PKT(11, af, pp, skb, 0, "Outgoing packet"); + IP_VS_DBG_PKT(11, af, pp, skb, iph->off, "Outgoing packet"); if (!skb_make_writable(skb, iph->len)) goto drop; @@ -1127,10 +1144,10 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, * if it came from this machine itself. So re-compute * the routing information. */ - if (ip_vs_route_me_harder(af, skb, hooknum)) + if (ip_vs_route_me_harder(cp->ipvs, af, skb, hooknum)) goto drop; - IP_VS_DBG_PKT(10, af, pp, skb, 0, "After SNAT"); + IP_VS_DBG_PKT(10, af, pp, skb, iph->off, "After SNAT"); ip_vs_out_stats(cp, skb); ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pd); @@ -1155,9 +1172,9 @@ drop: * Check if outgoing packet belongs to the established ip_vs_conn. */ static unsigned int -ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) +ip_vs_out(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int af) { - struct net *net = NULL; + struct net *net = ipvs->net; struct ip_vs_iphdr iph; struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; @@ -1182,16 +1199,15 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) if (unlikely(!skb_dst(skb))) return NF_ACCEPT; - net = skb_net(skb); - if (!net_ipvs(net)->enable) + if (!ipvs->enable) return NF_ACCEPT; - ip_vs_fill_iph_skb(af, skb, &iph); + ip_vs_fill_iph_skb(af, skb, false, &iph); #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { if (unlikely(iph.protocol == IPPROTO_ICMPV6)) { int related; - int verdict = ip_vs_out_icmp_v6(skb, &related, + int verdict = ip_vs_out_icmp_v6(ipvs, skb, &related, hooknum, &iph); if (related) @@ -1201,13 +1217,13 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) #endif if (unlikely(iph.protocol == IPPROTO_ICMP)) { int related; - int verdict = ip_vs_out_icmp(skb, &related, hooknum); + int verdict = ip_vs_out_icmp(ipvs, skb, &related, hooknum); if (related) return verdict; } - pd = ip_vs_proto_data_get(net, iph.protocol); + pd = ip_vs_proto_data_get(ipvs, iph.protocol); if (unlikely(!pd)) return NF_ACCEPT; pp = pd->pp; @@ -1217,21 +1233,21 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) if (af == AF_INET) #endif if (unlikely(ip_is_fragment(ip_hdr(skb)) && !pp->dont_defrag)) { - if (ip_vs_gather_frags(skb, + if (ip_vs_gather_frags(ipvs, skb, ip_vs_defrag_user(hooknum))) return NF_STOLEN; - ip_vs_fill_ip4hdr(skb_network_header(skb), &iph); + ip_vs_fill_iph_skb(AF_INET, skb, false, &iph); } /* * Check if the packet belongs to an existing entry */ - cp = pp->conn_out_get(af, skb, &iph, 0); + cp = pp->conn_out_get(ipvs, af, skb, &iph); if (likely(cp)) return handle_response(af, skb, pd, cp, &iph, hooknum); - if (sysctl_nat_icmp_send(net) && + if (sysctl_nat_icmp_send(ipvs) && (pp->protocol == IPPROTO_TCP || pp->protocol == IPPROTO_UDP || pp->protocol == IPPROTO_SCTP)) { @@ -1241,7 +1257,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) sizeof(_ports), _ports, &iph); if (pptr == NULL) return NF_ACCEPT; /* Not for me */ - if (ip_vs_has_real_service(net, af, iph.protocol, &iph.saddr, + if (ip_vs_has_real_service(ipvs, af, iph.protocol, &iph.saddr, pptr[0])) { /* * Notify the real server: there is no @@ -1272,7 +1288,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) } } } - IP_VS_DBG_PKT(12, af, pp, skb, 0, + IP_VS_DBG_PKT(12, af, pp, skb, iph.off, "ip_vs_out: packet continues traversal as normal"); return NF_ACCEPT; } @@ -1283,10 +1299,10 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) * Check if packet is reply for established ip_vs_conn. */ static unsigned int -ip_vs_reply4(const struct nf_hook_ops *ops, struct sk_buff *skb, +ip_vs_reply4(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return ip_vs_out(ops->hooknum, skb, AF_INET); + return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET); } /* @@ -1294,10 +1310,10 @@ ip_vs_reply4(const struct nf_hook_ops *ops, struct sk_buff *skb, * Check if packet is reply for established ip_vs_conn. */ static unsigned int -ip_vs_local_reply4(const struct nf_hook_ops *ops, struct sk_buff *skb, +ip_vs_local_reply4(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return ip_vs_out(ops->hooknum, skb, AF_INET); + return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET); } #ifdef CONFIG_IP_VS_IPV6 @@ -1308,10 +1324,10 @@ ip_vs_local_reply4(const struct nf_hook_ops *ops, struct sk_buff *skb, * Check if packet is reply for established ip_vs_conn. */ static unsigned int -ip_vs_reply6(const struct nf_hook_ops *ops, struct sk_buff *skb, +ip_vs_reply6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return ip_vs_out(ops->hooknum, skb, AF_INET6); + return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET6); } /* @@ -1319,14 +1335,51 @@ ip_vs_reply6(const struct nf_hook_ops *ops, struct sk_buff *skb, * Check if packet is reply for established ip_vs_conn. */ static unsigned int -ip_vs_local_reply6(const struct nf_hook_ops *ops, struct sk_buff *skb, +ip_vs_local_reply6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return ip_vs_out(ops->hooknum, skb, AF_INET6); + return ip_vs_out(net_ipvs(state->net), state->hook, skb, AF_INET6); } #endif +static unsigned int +ip_vs_try_to_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, + struct ip_vs_proto_data *pd, + int *verdict, struct ip_vs_conn **cpp, + struct ip_vs_iphdr *iph) +{ + struct ip_vs_protocol *pp = pd->pp; + + if (!iph->fragoffs) { + /* No (second) fragments need to enter here, as nf_defrag_ipv6 + * replayed fragment zero will already have created the cp + */ + + /* Schedule and create new connection entry into cpp */ + if (!pp->conn_schedule(ipvs, af, skb, pd, verdict, cpp, iph)) + return 0; + } + + if (unlikely(!*cpp)) { + /* sorry, all this trouble for a no-hit :) */ + IP_VS_DBG_PKT(12, af, pp, skb, iph->off, + "ip_vs_in: packet continues traversal as normal"); + if (iph->fragoffs) { + /* Fragment that couldn't be mapped to a conn entry + * is missing module nf_defrag_ipv6 + */ + IP_VS_DBG_RL("Unhandled frag, load nf_defrag_ipv6\n"); + IP_VS_DBG_PKT(7, af, pp, skb, iph->off, + "unhandled fragment"); + } + *verdict = NF_ACCEPT; + return 0; + } + + return 1; +} + /* * Handle ICMP messages in the outside-to-inside direction (incoming). * Find any that might be relevant, check against existing connections, @@ -1334,9 +1387,9 @@ ip_vs_local_reply6(const struct nf_hook_ops *ops, struct sk_buff *skb, * Currently handles error types - unreachable, quench, ttl exceeded. */ static int -ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) +ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, + unsigned int hooknum) { - struct net *net = NULL; struct iphdr *iph; struct icmphdr _icmph, *ic; struct iphdr _ciph, *cih; /* The ip header contained within the ICMP */ @@ -1345,13 +1398,13 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; unsigned int offset, offset2, ihl, verdict; - bool ipip; + bool ipip, new_cp = false; *related = 1; /* reassemble IP fragments */ if (ip_is_fragment(ip_hdr(skb))) { - if (ip_vs_gather_frags(skb, ip_vs_defrag_user(hooknum))) + if (ip_vs_gather_frags(ipvs, skb, ip_vs_defrag_user(hooknum))) return NF_STOLEN; } @@ -1385,8 +1438,6 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) if (cih == NULL) return NF_ACCEPT; /* The packet looks wrong, ignore */ - net = skb_net(skb); - /* Special case for errors for IPIP packets */ ipip = false; if (cih->protocol == IPPROTO_IPIP) { @@ -1402,7 +1453,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) ipip = true; } - pd = ip_vs_proto_data_get(net, cih->protocol); + pd = ip_vs_proto_data_get(ipvs, cih->protocol); if (!pd) return NF_ACCEPT; pp = pd->pp; @@ -1416,15 +1467,24 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) "Checking incoming ICMP for"); offset2 = offset; - ip_vs_fill_ip4hdr(cih, &ciph); - ciph.len += offset; + ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, !ipip, &ciph); offset = ciph.len; + /* The embedded headers contain source and dest in reverse order. * For IPIP this is error for request, not for reply. */ - cp = pp->conn_in_get(AF_INET, skb, &ciph, ipip ? 0 : 1); - if (!cp) - return NF_ACCEPT; + cp = pp->conn_in_get(ipvs, AF_INET, skb, &ciph); + + if (!cp) { + int v; + + if (!sysctl_schedule_icmp(ipvs)) + return NF_ACCEPT; + + if (!ip_vs_try_to_schedule(ipvs, AF_INET, skb, pd, &v, &cp, &ciph)) + return v; + new_cp = true; + } verdict = NF_DROP; @@ -1455,7 +1515,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) skb_reset_network_header(skb); IP_VS_DBG(12, "ICMP for IPIP %pI4->%pI4: mtu=%u\n", &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, mtu); - ipv4_update_pmtu(skb, dev_net(skb->dev), + ipv4_update_pmtu(skb, ipvs->net, mtu, 0, 0, 0, 0); /* Client uses PMTUD? */ if (!(frag_off & htons(IP_DF))) @@ -1501,23 +1561,26 @@ ignore_ipip: verdict = ip_vs_icmp_xmit(skb, cp, pp, offset, hooknum, &ciph); out: - __ip_vs_conn_put(cp); + if (likely(!new_cp)) + __ip_vs_conn_put(cp); + else + ip_vs_conn_put(cp); return verdict; } #ifdef CONFIG_IP_VS_IPV6 -static int ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, - unsigned int hooknum, struct ip_vs_iphdr *iph) +static int ip_vs_in_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, + int *related, unsigned int hooknum, + struct ip_vs_iphdr *iph) { - struct net *net = NULL; - struct ipv6hdr _ip6h, *ip6h; struct icmp6hdr _icmph, *ic; struct ip_vs_iphdr ciph = {.flags = 0, .fragoffs = 0};/*Contained IP */ struct ip_vs_conn *cp; struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; - unsigned int offs_ciph, writable, verdict; + unsigned int offset, verdict; + bool new_cp = false; *related = 1; @@ -1546,21 +1609,11 @@ static int ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, ic->icmp6_type, ntohs(icmpv6_id(ic)), &iph->saddr, &iph->daddr); - /* Now find the contained IP header */ - ciph.len = iph->len + sizeof(_icmph); - offs_ciph = ciph.len; /* Save ip header offset */ - ip6h = skb_header_pointer(skb, ciph.len, sizeof(_ip6h), &_ip6h); - if (ip6h == NULL) - return NF_ACCEPT; /* The packet looks wrong, ignore */ - ciph.saddr.in6 = ip6h->saddr; /* conn_in_get() handles reverse order */ - ciph.daddr.in6 = ip6h->daddr; - /* skip possible IPv6 exthdrs of contained IPv6 packet */ - ciph.protocol = ipv6_find_hdr(skb, &ciph.len, -1, &ciph.fragoffs, NULL); - if (ciph.protocol < 0) - return NF_ACCEPT; /* Contained IPv6 hdr looks wrong, ignore */ - - net = skb_net(skb); - pd = ip_vs_proto_data_get(net, ciph.protocol); + offset = iph->len + sizeof(_icmph); + if (!ip_vs_fill_iph_skb_icmp(AF_INET6, skb, offset, true, &ciph)) + return NF_ACCEPT; + + pd = ip_vs_proto_data_get(ipvs, ciph.protocol); if (!pd) return NF_ACCEPT; pp = pd->pp; @@ -1569,36 +1622,49 @@ static int ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, if (ciph.fragoffs) return NF_ACCEPT; - IP_VS_DBG_PKT(11, AF_INET6, pp, skb, offs_ciph, + IP_VS_DBG_PKT(11, AF_INET6, pp, skb, offset, "Checking incoming ICMPv6 for"); /* The embedded headers contain source and dest in reverse order * if not from localhost */ - cp = pp->conn_in_get(AF_INET6, skb, &ciph, - (hooknum == NF_INET_LOCAL_OUT) ? 0 : 1); + cp = pp->conn_in_get(ipvs, AF_INET6, skb, &ciph); + + if (!cp) { + int v; + + if (!sysctl_schedule_icmp(ipvs)) + return NF_ACCEPT; + + if (!ip_vs_try_to_schedule(ipvs, AF_INET6, skb, pd, &v, &cp, &ciph)) + return v; + + new_cp = true; + } - if (!cp) - return NF_ACCEPT; /* VS/TUN, VS/DR and LOCALNODE just let it go */ if ((hooknum == NF_INET_LOCAL_OUT) && (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ)) { - __ip_vs_conn_put(cp); - return NF_ACCEPT; + verdict = NF_ACCEPT; + goto out; } /* do the statistics and put it back */ ip_vs_in_stats(cp, skb); /* Need to mangle contained IPv6 header in ICMPv6 packet */ - writable = ciph.len; + offset = ciph.len; if (IPPROTO_TCP == ciph.protocol || IPPROTO_UDP == ciph.protocol || IPPROTO_SCTP == ciph.protocol) - writable += 2 * sizeof(__u16); /* Also mangle ports */ + offset += 2 * sizeof(__u16); /* Also mangle ports */ - verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, writable, hooknum, &ciph); + verdict = ip_vs_icmp_xmit_v6(skb, cp, pp, offset, hooknum, &ciph); - __ip_vs_conn_put(cp); +out: + if (likely(!new_cp)) + __ip_vs_conn_put(cp); + else + ip_vs_conn_put(cp); return verdict; } @@ -1610,15 +1676,13 @@ static int ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, * and send it on its way... */ static unsigned int -ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) +ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int af) { - struct net *net; struct ip_vs_iphdr iph; struct ip_vs_protocol *pp; struct ip_vs_proto_data *pd; struct ip_vs_conn *cp; int ret, pkts; - struct netns_ipvs *ipvs; int conn_reuse_mode; /* Already marked as IPVS request or reply? */ @@ -1633,7 +1697,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) if (unlikely((skb->pkt_type != PACKET_HOST && hooknum != NF_INET_LOCAL_OUT) || !skb_dst(skb))) { - ip_vs_fill_iph_skb(af, skb, &iph); + ip_vs_fill_iph_skb(af, skb, false, &iph); IP_VS_DBG_BUF(12, "packet type=%d proto=%d daddr=%s" " ignored in hook %u\n", skb->pkt_type, iph.protocol, @@ -1641,12 +1705,10 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) return NF_ACCEPT; } /* ipvs enabled in this netns ? */ - net = skb_net(skb); - ipvs = net_ipvs(net); if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) return NF_ACCEPT; - ip_vs_fill_iph_skb(af, skb, &iph); + ip_vs_fill_iph_skb(af, skb, false, &iph); /* Bad... Do not break raw sockets */ if (unlikely(skb->sk != NULL && hooknum == NF_INET_LOCAL_OUT && @@ -1662,8 +1724,8 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) if (af == AF_INET6) { if (unlikely(iph.protocol == IPPROTO_ICMPV6)) { int related; - int verdict = ip_vs_in_icmp_v6(skb, &related, hooknum, - &iph); + int verdict = ip_vs_in_icmp_v6(ipvs, skb, &related, + hooknum, &iph); if (related) return verdict; @@ -1672,21 +1734,30 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) #endif if (unlikely(iph.protocol == IPPROTO_ICMP)) { int related; - int verdict = ip_vs_in_icmp(skb, &related, hooknum); + int verdict = ip_vs_in_icmp(ipvs, skb, &related, + hooknum); if (related) return verdict; } /* Protocol supported? */ - pd = ip_vs_proto_data_get(net, iph.protocol); - if (unlikely(!pd)) + pd = ip_vs_proto_data_get(ipvs, iph.protocol); + if (unlikely(!pd)) { + /* The only way we'll see this packet again is if it's + * encapsulated, so mark it with ipvs_property=1 so we + * skip it if we're ignoring tunneled packets + */ + if (sysctl_ignore_tunneled(ipvs)) + skb->ipvs_property = 1; + return NF_ACCEPT; + } pp = pd->pp; /* * Check if the packet belongs to an existing connection entry */ - cp = pp->conn_in_get(af, skb, &iph, 0); + cp = pp->conn_in_get(ipvs, af, skb, &iph); conn_reuse_mode = sysctl_conn_reuse_mode(ipvs); if (conn_reuse_mode && !iph.fragoffs && @@ -1700,32 +1771,15 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) cp = NULL; } - if (unlikely(!cp) && !iph.fragoffs) { - /* No (second) fragments need to enter here, as nf_defrag_ipv6 - * replayed fragment zero will already have created the cp - */ + if (unlikely(!cp)) { int v; - /* Schedule and create new connection entry into &cp */ - if (!pp->conn_schedule(af, skb, pd, &v, &cp, &iph)) + if (!ip_vs_try_to_schedule(ipvs, af, skb, pd, &v, &cp, &iph)) return v; } - if (unlikely(!cp)) { - /* sorry, all this trouble for a no-hit :) */ - IP_VS_DBG_PKT(12, af, pp, skb, 0, - "ip_vs_in: packet continues traversal as normal"); - if (iph.fragoffs) { - /* Fragment that couldn't be mapped to a conn entry - * is missing module nf_defrag_ipv6 - */ - IP_VS_DBG_RL("Unhandled frag, load nf_defrag_ipv6\n"); - IP_VS_DBG_PKT(7, af, pp, skb, 0, "unhandled fragment"); - } - return NF_ACCEPT; - } + IP_VS_DBG_PKT(11, af, pp, skb, iph.off, "Incoming packet"); - IP_VS_DBG_PKT(11, af, pp, skb, 0, "Incoming packet"); /* Check the server status */ if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) { /* the destination server is not available */ @@ -1765,7 +1819,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) pkts = atomic_add_return(1, &cp->in_pkts); if (ipvs->sync_state & IP_VS_STATE_MASTER) - ip_vs_sync_conn(net, cp, pkts); + ip_vs_sync_conn(ipvs, cp, pkts); ip_vs_conn_put(cp); return ret; @@ -1776,10 +1830,10 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) * Schedule and forward packets from remote clients */ static unsigned int -ip_vs_remote_request4(const struct nf_hook_ops *ops, struct sk_buff *skb, +ip_vs_remote_request4(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return ip_vs_in(ops->hooknum, skb, AF_INET); + return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET); } /* @@ -1787,10 +1841,10 @@ ip_vs_remote_request4(const struct nf_hook_ops *ops, struct sk_buff *skb, * Schedule and forward packets from local clients */ static unsigned int -ip_vs_local_request4(const struct nf_hook_ops *ops, struct sk_buff *skb, +ip_vs_local_request4(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return ip_vs_in(ops->hooknum, skb, AF_INET); + return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET); } #ifdef CONFIG_IP_VS_IPV6 @@ -1800,10 +1854,10 @@ ip_vs_local_request4(const struct nf_hook_ops *ops, struct sk_buff *skb, * Schedule and forward packets from remote clients */ static unsigned int -ip_vs_remote_request6(const struct nf_hook_ops *ops, struct sk_buff *skb, +ip_vs_remote_request6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return ip_vs_in(ops->hooknum, skb, AF_INET6); + return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET6); } /* @@ -1811,10 +1865,10 @@ ip_vs_remote_request6(const struct nf_hook_ops *ops, struct sk_buff *skb, * Schedule and forward packets from local clients */ static unsigned int -ip_vs_local_request6(const struct nf_hook_ops *ops, struct sk_buff *skb, +ip_vs_local_request6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - return ip_vs_in(ops->hooknum, skb, AF_INET6); + return ip_vs_in(net_ipvs(state->net), state->hook, skb, AF_INET6); } #endif @@ -1830,46 +1884,40 @@ ip_vs_local_request6(const struct nf_hook_ops *ops, struct sk_buff *skb, * and send them to ip_vs_in_icmp. */ static unsigned int -ip_vs_forward_icmp(const struct nf_hook_ops *ops, struct sk_buff *skb, +ip_vs_forward_icmp(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { int r; - struct net *net; - struct netns_ipvs *ipvs; + struct netns_ipvs *ipvs = net_ipvs(state->net); if (ip_hdr(skb)->protocol != IPPROTO_ICMP) return NF_ACCEPT; /* ipvs enabled in this netns ? */ - net = skb_net(skb); - ipvs = net_ipvs(net); if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) return NF_ACCEPT; - return ip_vs_in_icmp(skb, &r, ops->hooknum); + return ip_vs_in_icmp(ipvs, skb, &r, state->hook); } #ifdef CONFIG_IP_VS_IPV6 static unsigned int -ip_vs_forward_icmp_v6(const struct nf_hook_ops *ops, struct sk_buff *skb, +ip_vs_forward_icmp_v6(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { int r; - struct net *net; - struct netns_ipvs *ipvs; + struct netns_ipvs *ipvs = net_ipvs(state->net); struct ip_vs_iphdr iphdr; - ip_vs_fill_iph_skb(AF_INET6, skb, &iphdr); + ip_vs_fill_iph_skb(AF_INET6, skb, false, &iphdr); if (iphdr.protocol != IPPROTO_ICMPV6) return NF_ACCEPT; /* ipvs enabled in this netns ? */ - net = skb_net(skb); - ipvs = net_ipvs(net); if (unlikely(sysctl_backup_only(ipvs) || !ipvs->enable)) return NF_ACCEPT; - return ip_vs_in_icmp_v6(skb, &r, ops->hooknum, &iphdr); + return ip_vs_in_icmp_v6(ipvs, skb, &r, state->hook, &iphdr); } #endif @@ -1999,22 +2047,22 @@ static int __net_init __ip_vs_init(struct net *net) atomic_inc(&ipvs_netns_cnt); net->ipvs = ipvs; - if (ip_vs_estimator_net_init(net) < 0) + if (ip_vs_estimator_net_init(ipvs) < 0) goto estimator_fail; - if (ip_vs_control_net_init(net) < 0) + if (ip_vs_control_net_init(ipvs) < 0) goto control_fail; - if (ip_vs_protocol_net_init(net) < 0) + if (ip_vs_protocol_net_init(ipvs) < 0) goto protocol_fail; - if (ip_vs_app_net_init(net) < 0) + if (ip_vs_app_net_init(ipvs) < 0) goto app_fail; - if (ip_vs_conn_net_init(net) < 0) + if (ip_vs_conn_net_init(ipvs) < 0) goto conn_fail; - if (ip_vs_sync_net_init(net) < 0) + if (ip_vs_sync_net_init(ipvs) < 0) goto sync_fail; printk(KERN_INFO "IPVS: Creating netns size=%zu id=%d\n", @@ -2025,15 +2073,15 @@ static int __net_init __ip_vs_init(struct net *net) */ sync_fail: - ip_vs_conn_net_cleanup(net); + ip_vs_conn_net_cleanup(ipvs); conn_fail: - ip_vs_app_net_cleanup(net); + ip_vs_app_net_cleanup(ipvs); app_fail: - ip_vs_protocol_net_cleanup(net); + ip_vs_protocol_net_cleanup(ipvs); protocol_fail: - ip_vs_control_net_cleanup(net); + ip_vs_control_net_cleanup(ipvs); control_fail: - ip_vs_estimator_net_cleanup(net); + ip_vs_estimator_net_cleanup(ipvs); estimator_fail: net->ipvs = NULL; return -ENOMEM; @@ -2041,22 +2089,25 @@ estimator_fail: static void __net_exit __ip_vs_cleanup(struct net *net) { - ip_vs_service_net_cleanup(net); /* ip_vs_flush() with locks */ - ip_vs_conn_net_cleanup(net); - ip_vs_app_net_cleanup(net); - ip_vs_protocol_net_cleanup(net); - ip_vs_control_net_cleanup(net); - ip_vs_estimator_net_cleanup(net); - IP_VS_DBG(2, "ipvs netns %d released\n", net_ipvs(net)->gen); + struct netns_ipvs *ipvs = net_ipvs(net); + + ip_vs_service_net_cleanup(ipvs); /* ip_vs_flush() with locks */ + ip_vs_conn_net_cleanup(ipvs); + ip_vs_app_net_cleanup(ipvs); + ip_vs_protocol_net_cleanup(ipvs); + ip_vs_control_net_cleanup(ipvs); + ip_vs_estimator_net_cleanup(ipvs); + IP_VS_DBG(2, "ipvs netns %d released\n", ipvs->gen); net->ipvs = NULL; } static void __net_exit __ip_vs_dev_cleanup(struct net *net) { + struct netns_ipvs *ipvs = net_ipvs(net); EnterFunction(2); - net_ipvs(net)->enable = 0; /* Disable packet reception */ + ipvs->enable = 0; /* Disable packet reception */ smp_wmb(); - ip_vs_sync_net_cleanup(net); + ip_vs_sync_net_cleanup(ipvs); LeaveFunction(2); } diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 1a23e91d50d8..e7c1b052c2a3 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -228,7 +228,7 @@ static void defense_work_handler(struct work_struct *work) update_defense_level(ipvs); if (atomic_read(&ipvs->dropentry)) - ip_vs_random_dropentry(ipvs->net); + ip_vs_random_dropentry(ipvs); schedule_delayed_work(&ipvs->defense_work, DEFENSE_TIMER_PERIOD); } #endif @@ -263,7 +263,7 @@ static struct hlist_head ip_vs_svc_fwm_table[IP_VS_SVC_TAB_SIZE]; * Returns hash value for virtual service */ static inline unsigned int -ip_vs_svc_hashkey(struct net *net, int af, unsigned int proto, +ip_vs_svc_hashkey(struct netns_ipvs *ipvs, int af, unsigned int proto, const union nf_inet_addr *addr, __be16 port) { register unsigned int porth = ntohs(port); @@ -276,7 +276,7 @@ ip_vs_svc_hashkey(struct net *net, int af, unsigned int proto, addr->ip6[2]^addr->ip6[3]; #endif ahash = ntohl(addr_fold); - ahash ^= ((size_t) net >> 8); + ahash ^= ((size_t) ipvs >> 8); return (proto ^ ahash ^ (porth >> IP_VS_SVC_TAB_BITS) ^ porth) & IP_VS_SVC_TAB_MASK; @@ -285,9 +285,9 @@ ip_vs_svc_hashkey(struct net *net, int af, unsigned int proto, /* * Returns hash value of fwmark for virtual service lookup */ -static inline unsigned int ip_vs_svc_fwm_hashkey(struct net *net, __u32 fwmark) +static inline unsigned int ip_vs_svc_fwm_hashkey(struct netns_ipvs *ipvs, __u32 fwmark) { - return (((size_t)net>>8) ^ fwmark) & IP_VS_SVC_TAB_MASK; + return (((size_t)ipvs>>8) ^ fwmark) & IP_VS_SVC_TAB_MASK; } /* @@ -309,14 +309,14 @@ static int ip_vs_svc_hash(struct ip_vs_service *svc) /* * Hash it by <netns,protocol,addr,port> in ip_vs_svc_table */ - hash = ip_vs_svc_hashkey(svc->net, svc->af, svc->protocol, + hash = ip_vs_svc_hashkey(svc->ipvs, svc->af, svc->protocol, &svc->addr, svc->port); hlist_add_head_rcu(&svc->s_list, &ip_vs_svc_table[hash]); } else { /* * Hash it by fwmark in svc_fwm_table */ - hash = ip_vs_svc_fwm_hashkey(svc->net, svc->fwmark); + hash = ip_vs_svc_fwm_hashkey(svc->ipvs, svc->fwmark); hlist_add_head_rcu(&svc->f_list, &ip_vs_svc_fwm_table[hash]); } @@ -357,21 +357,21 @@ static int ip_vs_svc_unhash(struct ip_vs_service *svc) * Get service by {netns, proto,addr,port} in the service table. */ static inline struct ip_vs_service * -__ip_vs_service_find(struct net *net, int af, __u16 protocol, +__ip_vs_service_find(struct netns_ipvs *ipvs, int af, __u16 protocol, const union nf_inet_addr *vaddr, __be16 vport) { unsigned int hash; struct ip_vs_service *svc; /* Check for "full" addressed entries */ - hash = ip_vs_svc_hashkey(net, af, protocol, vaddr, vport); + hash = ip_vs_svc_hashkey(ipvs, af, protocol, vaddr, vport); hlist_for_each_entry_rcu(svc, &ip_vs_svc_table[hash], s_list) { if ((svc->af == af) && ip_vs_addr_equal(af, &svc->addr, vaddr) && (svc->port == vport) && (svc->protocol == protocol) - && net_eq(svc->net, net)) { + && (svc->ipvs == ipvs)) { /* HIT */ return svc; } @@ -385,17 +385,17 @@ __ip_vs_service_find(struct net *net, int af, __u16 protocol, * Get service by {fwmark} in the service table. */ static inline struct ip_vs_service * -__ip_vs_svc_fwm_find(struct net *net, int af, __u32 fwmark) +__ip_vs_svc_fwm_find(struct netns_ipvs *ipvs, int af, __u32 fwmark) { unsigned int hash; struct ip_vs_service *svc; /* Check for fwmark addressed entries */ - hash = ip_vs_svc_fwm_hashkey(net, fwmark); + hash = ip_vs_svc_fwm_hashkey(ipvs, fwmark); hlist_for_each_entry_rcu(svc, &ip_vs_svc_fwm_table[hash], f_list) { if (svc->fwmark == fwmark && svc->af == af - && net_eq(svc->net, net)) { + && (svc->ipvs == ipvs)) { /* HIT */ return svc; } @@ -406,17 +406,16 @@ __ip_vs_svc_fwm_find(struct net *net, int af, __u32 fwmark) /* Find service, called under RCU lock */ struct ip_vs_service * -ip_vs_service_find(struct net *net, int af, __u32 fwmark, __u16 protocol, +ip_vs_service_find(struct netns_ipvs *ipvs, int af, __u32 fwmark, __u16 protocol, const union nf_inet_addr *vaddr, __be16 vport) { struct ip_vs_service *svc; - struct netns_ipvs *ipvs = net_ipvs(net); /* * Check the table hashed by fwmark first */ if (fwmark) { - svc = __ip_vs_svc_fwm_find(net, af, fwmark); + svc = __ip_vs_svc_fwm_find(ipvs, af, fwmark); if (svc) goto out; } @@ -425,7 +424,7 @@ ip_vs_service_find(struct net *net, int af, __u32 fwmark, __u16 protocol, * Check the table hashed by <protocol,addr,port> * for "full" addressed entries */ - svc = __ip_vs_service_find(net, af, protocol, vaddr, vport); + svc = __ip_vs_service_find(ipvs, af, protocol, vaddr, vport); if (svc == NULL && protocol == IPPROTO_TCP @@ -435,7 +434,7 @@ ip_vs_service_find(struct net *net, int af, __u32 fwmark, __u16 protocol, * Check if ftp service entry exists, the packet * might belong to FTP data connections. */ - svc = __ip_vs_service_find(net, af, protocol, vaddr, FTPPORT); + svc = __ip_vs_service_find(ipvs, af, protocol, vaddr, FTPPORT); } if (svc == NULL @@ -443,7 +442,7 @@ ip_vs_service_find(struct net *net, int af, __u32 fwmark, __u16 protocol, /* * Check if the catch-all port (port zero) exists */ - svc = __ip_vs_service_find(net, af, protocol, vaddr, 0); + svc = __ip_vs_service_find(ipvs, af, protocol, vaddr, 0); } out: @@ -543,10 +542,9 @@ static void ip_vs_rs_unhash(struct ip_vs_dest *dest) } /* Check if real service by <proto,addr,port> is present */ -bool ip_vs_has_real_service(struct net *net, int af, __u16 protocol, +bool ip_vs_has_real_service(struct netns_ipvs *ipvs, int af, __u16 protocol, const union nf_inet_addr *daddr, __be16 dport) { - struct netns_ipvs *ipvs = net_ipvs(net); unsigned int hash; struct ip_vs_dest *dest; @@ -601,7 +599,7 @@ ip_vs_lookup_dest(struct ip_vs_service *svc, int dest_af, * on the backup. * Called under RCU lock, no refcnt is returned. */ -struct ip_vs_dest *ip_vs_find_dest(struct net *net, int svc_af, int dest_af, +struct ip_vs_dest *ip_vs_find_dest(struct netns_ipvs *ipvs, int svc_af, int dest_af, const union nf_inet_addr *daddr, __be16 dport, const union nf_inet_addr *vaddr, @@ -612,7 +610,7 @@ struct ip_vs_dest *ip_vs_find_dest(struct net *net, int svc_af, int dest_af, struct ip_vs_service *svc; __be16 port = dport; - svc = ip_vs_service_find(net, svc_af, fwmark, protocol, vaddr, vport); + svc = ip_vs_service_find(ipvs, svc_af, fwmark, protocol, vaddr, vport); if (!svc) return NULL; if (fwmark && (flags & IP_VS_CONN_F_FWD_MASK) != IP_VS_CONN_F_MASQ) @@ -660,7 +658,7 @@ ip_vs_trash_get_dest(struct ip_vs_service *svc, int dest_af, const union nf_inet_addr *daddr, __be16 dport) { struct ip_vs_dest *dest; - struct netns_ipvs *ipvs = net_ipvs(svc->net); + struct netns_ipvs *ipvs = svc->ipvs; /* * Find the destination in trash @@ -715,10 +713,9 @@ static void ip_vs_dest_free(struct ip_vs_dest *dest) * are expired, and the refcnt of each destination in the trash must * be 0, so we simply release them here. */ -static void ip_vs_trash_cleanup(struct net *net) +static void ip_vs_trash_cleanup(struct netns_ipvs *ipvs) { struct ip_vs_dest *dest, *nxt; - struct netns_ipvs *ipvs = net_ipvs(net); del_timer_sync(&ipvs->dest_trash_timer); /* No need to use dest_trash_lock */ @@ -788,7 +785,7 @@ static void __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, struct ip_vs_dest_user_kern *udest, int add) { - struct netns_ipvs *ipvs = net_ipvs(svc->net); + struct netns_ipvs *ipvs = svc->ipvs; struct ip_vs_service *old_svc; struct ip_vs_scheduler *sched; int conn_flags; @@ -843,7 +840,7 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, spin_unlock_bh(&dest->dst_lock); if (add) { - ip_vs_start_estimator(svc->net, &dest->stats); + ip_vs_start_estimator(svc->ipvs, &dest->stats); list_add_rcu(&dest->n_list, &svc->destinations); svc->num_dests++; sched = rcu_dereference_protected(svc->scheduler, 1); @@ -874,12 +871,12 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest, atype = ipv6_addr_type(&udest->addr.in6); if ((!(atype & IPV6_ADDR_UNICAST) || atype & IPV6_ADDR_LINKLOCAL) && - !__ip_vs_addr_is_local_v6(svc->net, &udest->addr.in6)) + !__ip_vs_addr_is_local_v6(svc->ipvs->net, &udest->addr.in6)) return -EINVAL; } else #endif { - atype = inet_addr_type(svc->net, udest->addr.ip); + atype = inet_addr_type(svc->ipvs->net, udest->addr.ip); if (atype != RTN_LOCAL && atype != RTN_UNICAST) return -EINVAL; } @@ -1036,12 +1033,10 @@ ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) /* * Delete a destination (must be already unlinked from the service) */ -static void __ip_vs_del_dest(struct net *net, struct ip_vs_dest *dest, +static void __ip_vs_del_dest(struct netns_ipvs *ipvs, struct ip_vs_dest *dest, bool cleanup) { - struct netns_ipvs *ipvs = net_ipvs(net); - - ip_vs_stop_estimator(net, &dest->stats); + ip_vs_stop_estimator(ipvs, &dest->stats); /* * Remove it from the d-linked list with the real services. @@ -1079,7 +1074,7 @@ static void __ip_vs_unlink_dest(struct ip_vs_service *svc, svc->num_dests--; if (dest->af != svc->af) - net_ipvs(svc->net)->mixed_address_family_dests--; + svc->ipvs->mixed_address_family_dests--; if (svcupd) { struct ip_vs_scheduler *sched; @@ -1120,7 +1115,7 @@ ip_vs_del_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) /* * Delete the destination */ - __ip_vs_del_dest(svc->net, dest, false); + __ip_vs_del_dest(svc->ipvs, dest, false); LeaveFunction(2); @@ -1129,8 +1124,7 @@ ip_vs_del_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) static void ip_vs_dest_trash_expire(unsigned long data) { - struct net *net = (struct net *) data; - struct netns_ipvs *ipvs = net_ipvs(net); + struct netns_ipvs *ipvs = (struct netns_ipvs *)data; struct ip_vs_dest *dest, *next; unsigned long now = jiffies; @@ -1163,14 +1157,13 @@ static void ip_vs_dest_trash_expire(unsigned long data) * Add a service into the service hash table */ static int -ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u, +ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u, struct ip_vs_service **svc_p) { int ret = 0, i; struct ip_vs_scheduler *sched = NULL; struct ip_vs_pe *pe = NULL; struct ip_vs_service *svc = NULL; - struct netns_ipvs *ipvs = net_ipvs(net); /* increase the module use count */ ip_vs_use_count_inc(); @@ -1237,7 +1230,7 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u, svc->flags = u->flags; svc->timeout = u->timeout * HZ; svc->netmask = u->netmask; - svc->net = net; + svc->ipvs = ipvs; INIT_LIST_HEAD(&svc->destinations); spin_lock_init(&svc->sched_lock); @@ -1261,7 +1254,7 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u, else if (svc->port == 0) atomic_inc(&ipvs->nullsvc_counter); - ip_vs_start_estimator(net, &svc->stats); + ip_vs_start_estimator(ipvs, &svc->stats); /* Count only IPv4 services for old get/setsockopt interface */ if (svc->af == AF_INET) @@ -1381,7 +1374,7 @@ static void __ip_vs_del_service(struct ip_vs_service *svc, bool cleanup) struct ip_vs_dest *dest, *nxt; struct ip_vs_scheduler *old_sched; struct ip_vs_pe *old_pe; - struct netns_ipvs *ipvs = net_ipvs(svc->net); + struct netns_ipvs *ipvs = svc->ipvs; pr_info("%s: enter\n", __func__); @@ -1389,7 +1382,7 @@ static void __ip_vs_del_service(struct ip_vs_service *svc, bool cleanup) if (svc->af == AF_INET) ipvs->num_services--; - ip_vs_stop_estimator(svc->net, &svc->stats); + ip_vs_stop_estimator(svc->ipvs, &svc->stats); /* Unbind scheduler */ old_sched = rcu_dereference_protected(svc->scheduler, 1); @@ -1405,7 +1398,7 @@ static void __ip_vs_del_service(struct ip_vs_service *svc, bool cleanup) */ list_for_each_entry_safe(dest, nxt, &svc->destinations, n_list) { __ip_vs_unlink_dest(svc, dest, 0); - __ip_vs_del_dest(svc->net, dest, cleanup); + __ip_vs_del_dest(svc->ipvs, dest, cleanup); } /* @@ -1456,7 +1449,7 @@ static int ip_vs_del_service(struct ip_vs_service *svc) /* * Flush all the virtual services */ -static int ip_vs_flush(struct net *net, bool cleanup) +static int ip_vs_flush(struct netns_ipvs *ipvs, bool cleanup) { int idx; struct ip_vs_service *svc; @@ -1468,7 +1461,7 @@ static int ip_vs_flush(struct net *net, bool cleanup) for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { hlist_for_each_entry_safe(svc, n, &ip_vs_svc_table[idx], s_list) { - if (net_eq(svc->net, net)) + if (svc->ipvs == ipvs) ip_vs_unlink_service(svc, cleanup); } } @@ -1479,7 +1472,7 @@ static int ip_vs_flush(struct net *net, bool cleanup) for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { hlist_for_each_entry_safe(svc, n, &ip_vs_svc_fwm_table[idx], f_list) { - if (net_eq(svc->net, net)) + if (svc->ipvs == ipvs) ip_vs_unlink_service(svc, cleanup); } } @@ -1491,12 +1484,12 @@ static int ip_vs_flush(struct net *net, bool cleanup) * Delete service by {netns} in the service table. * Called by __ip_vs_cleanup() */ -void ip_vs_service_net_cleanup(struct net *net) +void ip_vs_service_net_cleanup(struct netns_ipvs *ipvs) { EnterFunction(2); /* Check for "full" addressed entries */ mutex_lock(&__ip_vs_mutex); - ip_vs_flush(net, true); + ip_vs_flush(ipvs, true); mutex_unlock(&__ip_vs_mutex); LeaveFunction(2); } @@ -1540,7 +1533,7 @@ static int ip_vs_dst_event(struct notifier_block *this, unsigned long event, mutex_lock(&__ip_vs_mutex); for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { hlist_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) { - if (net_eq(svc->net, net)) { + if (svc->ipvs == ipvs) { list_for_each_entry(dest, &svc->destinations, n_list) { ip_vs_forget_dev(dest, dev); @@ -1549,7 +1542,7 @@ static int ip_vs_dst_event(struct notifier_block *this, unsigned long event, } hlist_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) { - if (net_eq(svc->net, net)) { + if (svc->ipvs == ipvs) { list_for_each_entry(dest, &svc->destinations, n_list) { ip_vs_forget_dev(dest, dev); @@ -1583,26 +1576,26 @@ static int ip_vs_zero_service(struct ip_vs_service *svc) return 0; } -static int ip_vs_zero_all(struct net *net) +static int ip_vs_zero_all(struct netns_ipvs *ipvs) { int idx; struct ip_vs_service *svc; for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { hlist_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) { - if (net_eq(svc->net, net)) + if (svc->ipvs == ipvs) ip_vs_zero_service(svc); } } for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { hlist_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) { - if (net_eq(svc->net, net)) + if (svc->ipvs == ipvs) ip_vs_zero_service(svc); } } - ip_vs_zero_stats(&net_ipvs(net)->tot_stats); + ip_vs_zero_stats(&ipvs->tot_stats); return 0; } @@ -1615,7 +1608,7 @@ static int proc_do_defense_mode(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - struct net *net = current->nsproxy->net_ns; + struct netns_ipvs *ipvs = table->extra2; int *valp = table->data; int val = *valp; int rc; @@ -1626,7 +1619,7 @@ proc_do_defense_mode(struct ctl_table *table, int write, /* Restore the correct value */ *valp = val; } else { - update_defense_level(net_ipvs(net)); + update_defense_level(ipvs); } } return rc; @@ -1844,6 +1837,18 @@ static struct ctl_table vs_vars[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "schedule_icmp", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "ignore_tunneled", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, #ifdef CONFIG_IP_VS_DEBUG { .procname = "debug_level", @@ -1889,6 +1894,7 @@ static inline const char *ip_vs_fwd_name(unsigned int flags) static struct ip_vs_service *ip_vs_info_array(struct seq_file *seq, loff_t pos) { struct net *net = seq_file_net(seq); + struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_iter *iter = seq->private; int idx; struct ip_vs_service *svc; @@ -1896,7 +1902,7 @@ static struct ip_vs_service *ip_vs_info_array(struct seq_file *seq, loff_t pos) /* look in hash by protocol */ for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { hlist_for_each_entry_rcu(svc, &ip_vs_svc_table[idx], s_list) { - if (net_eq(svc->net, net) && pos-- == 0) { + if ((svc->ipvs == ipvs) && pos-- == 0) { iter->table = ip_vs_svc_table; iter->bucket = idx; return svc; @@ -1908,7 +1914,7 @@ static struct ip_vs_service *ip_vs_info_array(struct seq_file *seq, loff_t pos) for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { hlist_for_each_entry_rcu(svc, &ip_vs_svc_fwm_table[idx], f_list) { - if (net_eq(svc->net, net) && pos-- == 0) { + if ((svc->ipvs == ipvs) && pos-- == 0) { iter->table = ip_vs_svc_fwm_table; iter->bucket = idx; return svc; @@ -2196,7 +2202,7 @@ static const struct file_operations ip_vs_stats_percpu_fops = { /* * Set timeout values for tcp tcpfin udp in the timeout_table. */ -static int ip_vs_set_timeout(struct net *net, struct ip_vs_timeout_user *u) +static int ip_vs_set_timeout(struct netns_ipvs *ipvs, struct ip_vs_timeout_user *u) { #if defined(CONFIG_IP_VS_PROTO_TCP) || defined(CONFIG_IP_VS_PROTO_UDP) struct ip_vs_proto_data *pd; @@ -2209,13 +2215,13 @@ static int ip_vs_set_timeout(struct net *net, struct ip_vs_timeout_user *u) #ifdef CONFIG_IP_VS_PROTO_TCP if (u->tcp_timeout) { - pd = ip_vs_proto_data_get(net, IPPROTO_TCP); + pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP); pd->timeout_table[IP_VS_TCP_S_ESTABLISHED] = u->tcp_timeout * HZ; } if (u->tcp_fin_timeout) { - pd = ip_vs_proto_data_get(net, IPPROTO_TCP); + pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP); pd->timeout_table[IP_VS_TCP_S_FIN_WAIT] = u->tcp_fin_timeout * HZ; } @@ -2223,7 +2229,7 @@ static int ip_vs_set_timeout(struct net *net, struct ip_vs_timeout_user *u) #ifdef CONFIG_IP_VS_PROTO_UDP if (u->udp_timeout) { - pd = ip_vs_proto_data_get(net, IPPROTO_UDP); + pd = ip_vs_proto_data_get(ipvs, IPPROTO_UDP); pd->timeout_table[IP_VS_UDP_S_NORMAL] = u->udp_timeout * HZ; } @@ -2344,12 +2350,12 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) cfg.syncid = dm->syncid; rtnl_lock(); mutex_lock(&ipvs->sync_mutex); - ret = start_sync_thread(net, &cfg, dm->state); + ret = start_sync_thread(ipvs, &cfg, dm->state); mutex_unlock(&ipvs->sync_mutex); rtnl_unlock(); } else { mutex_lock(&ipvs->sync_mutex); - ret = stop_sync_thread(net, dm->state); + ret = stop_sync_thread(ipvs, dm->state); mutex_unlock(&ipvs->sync_mutex); } goto out_dec; @@ -2358,11 +2364,11 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) mutex_lock(&__ip_vs_mutex); if (cmd == IP_VS_SO_SET_FLUSH) { /* Flush the virtual service */ - ret = ip_vs_flush(net, false); + ret = ip_vs_flush(ipvs, false); goto out_unlock; } else if (cmd == IP_VS_SO_SET_TIMEOUT) { /* Set timeout values for (tcp tcpfin udp) */ - ret = ip_vs_set_timeout(net, (struct ip_vs_timeout_user *)arg); + ret = ip_vs_set_timeout(ipvs, (struct ip_vs_timeout_user *)arg); goto out_unlock; } @@ -2377,7 +2383,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) if (cmd == IP_VS_SO_SET_ZERO) { /* if no service address is set, zero counters in all */ if (!usvc.fwmark && !usvc.addr.ip && !usvc.port) { - ret = ip_vs_zero_all(net); + ret = ip_vs_zero_all(ipvs); goto out_unlock; } } @@ -2395,10 +2401,10 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) /* Lookup the exact service by <protocol, addr, port> or fwmark */ rcu_read_lock(); if (usvc.fwmark == 0) - svc = __ip_vs_service_find(net, usvc.af, usvc.protocol, + svc = __ip_vs_service_find(ipvs, usvc.af, usvc.protocol, &usvc.addr, usvc.port); else - svc = __ip_vs_svc_fwm_find(net, usvc.af, usvc.fwmark); + svc = __ip_vs_svc_fwm_find(ipvs, usvc.af, usvc.fwmark); rcu_read_unlock(); if (cmd != IP_VS_SO_SET_ADD @@ -2412,7 +2418,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) if (svc != NULL) ret = -EEXIST; else - ret = ip_vs_add_service(net, &usvc, &svc); + ret = ip_vs_add_service(ipvs, &usvc, &svc); break; case IP_VS_SO_SET_EDIT: ret = ip_vs_edit_service(svc, &usvc); @@ -2471,7 +2477,7 @@ ip_vs_copy_service(struct ip_vs_service_entry *dst, struct ip_vs_service *src) } static inline int -__ip_vs_get_service_entries(struct net *net, +__ip_vs_get_service_entries(struct netns_ipvs *ipvs, const struct ip_vs_get_services *get, struct ip_vs_get_services __user *uptr) { @@ -2483,7 +2489,7 @@ __ip_vs_get_service_entries(struct net *net, for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { hlist_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) { /* Only expose IPv4 entries to old interface */ - if (svc->af != AF_INET || !net_eq(svc->net, net)) + if (svc->af != AF_INET || (svc->ipvs != ipvs)) continue; if (count >= get->num_services) @@ -2502,7 +2508,7 @@ __ip_vs_get_service_entries(struct net *net, for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { hlist_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) { /* Only expose IPv4 entries to old interface */ - if (svc->af != AF_INET || !net_eq(svc->net, net)) + if (svc->af != AF_INET || (svc->ipvs != ipvs)) continue; if (count >= get->num_services) @@ -2522,7 +2528,7 @@ out: } static inline int -__ip_vs_get_dest_entries(struct net *net, const struct ip_vs_get_dests *get, +__ip_vs_get_dest_entries(struct netns_ipvs *ipvs, const struct ip_vs_get_dests *get, struct ip_vs_get_dests __user *uptr) { struct ip_vs_service *svc; @@ -2531,9 +2537,9 @@ __ip_vs_get_dest_entries(struct net *net, const struct ip_vs_get_dests *get, rcu_read_lock(); if (get->fwmark) - svc = __ip_vs_svc_fwm_find(net, AF_INET, get->fwmark); + svc = __ip_vs_svc_fwm_find(ipvs, AF_INET, get->fwmark); else - svc = __ip_vs_service_find(net, AF_INET, get->protocol, &addr, + svc = __ip_vs_service_find(ipvs, AF_INET, get->protocol, &addr, get->port); rcu_read_unlock(); @@ -2578,7 +2584,7 @@ __ip_vs_get_dest_entries(struct net *net, const struct ip_vs_get_dests *get, } static inline void -__ip_vs_get_timeouts(struct net *net, struct ip_vs_timeout_user *u) +__ip_vs_get_timeouts(struct netns_ipvs *ipvs, struct ip_vs_timeout_user *u) { #if defined(CONFIG_IP_VS_PROTO_TCP) || defined(CONFIG_IP_VS_PROTO_UDP) struct ip_vs_proto_data *pd; @@ -2587,12 +2593,12 @@ __ip_vs_get_timeouts(struct net *net, struct ip_vs_timeout_user *u) memset(u, 0, sizeof (*u)); #ifdef CONFIG_IP_VS_PROTO_TCP - pd = ip_vs_proto_data_get(net, IPPROTO_TCP); + pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP); u->tcp_timeout = pd->timeout_table[IP_VS_TCP_S_ESTABLISHED] / HZ; u->tcp_fin_timeout = pd->timeout_table[IP_VS_TCP_S_FIN_WAIT] / HZ; #endif #ifdef CONFIG_IP_VS_PROTO_UDP - pd = ip_vs_proto_data_get(net, IPPROTO_UDP); + pd = ip_vs_proto_data_get(ipvs, IPPROTO_UDP); u->udp_timeout = pd->timeout_table[IP_VS_UDP_S_NORMAL] / HZ; #endif @@ -2711,7 +2717,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) ret = -EINVAL; goto out; } - ret = __ip_vs_get_service_entries(net, get, user); + ret = __ip_vs_get_service_entries(ipvs, get, user); } break; @@ -2725,9 +2731,9 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) addr.ip = entry->addr; rcu_read_lock(); if (entry->fwmark) - svc = __ip_vs_svc_fwm_find(net, AF_INET, entry->fwmark); + svc = __ip_vs_svc_fwm_find(ipvs, AF_INET, entry->fwmark); else - svc = __ip_vs_service_find(net, AF_INET, + svc = __ip_vs_service_find(ipvs, AF_INET, entry->protocol, &addr, entry->port); rcu_read_unlock(); @@ -2753,7 +2759,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) ret = -EINVAL; goto out; } - ret = __ip_vs_get_dest_entries(net, get, user); + ret = __ip_vs_get_dest_entries(ipvs, get, user); } break; @@ -2761,7 +2767,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) { struct ip_vs_timeout_user t; - __ip_vs_get_timeouts(net, &t); + __ip_vs_get_timeouts(ipvs, &t); if (copy_to_user(user, &t, sizeof(t)) != 0) ret = -EFAULT; } @@ -2996,12 +3002,13 @@ static int ip_vs_genl_dump_services(struct sk_buff *skb, int idx = 0, i; int start = cb->args[0]; struct ip_vs_service *svc; - struct net *net = skb_sknet(skb); + struct net *net = sock_net(skb->sk); + struct netns_ipvs *ipvs = net_ipvs(net); mutex_lock(&__ip_vs_mutex); for (i = 0; i < IP_VS_SVC_TAB_SIZE; i++) { hlist_for_each_entry(svc, &ip_vs_svc_table[i], s_list) { - if (++idx <= start || !net_eq(svc->net, net)) + if (++idx <= start || (svc->ipvs != ipvs)) continue; if (ip_vs_genl_dump_service(skb, svc, cb) < 0) { idx--; @@ -3012,7 +3019,7 @@ static int ip_vs_genl_dump_services(struct sk_buff *skb, for (i = 0; i < IP_VS_SVC_TAB_SIZE; i++) { hlist_for_each_entry(svc, &ip_vs_svc_fwm_table[i], f_list) { - if (++idx <= start || !net_eq(svc->net, net)) + if (++idx <= start || (svc->ipvs != ipvs)) continue; if (ip_vs_genl_dump_service(skb, svc, cb) < 0) { idx--; @@ -3028,7 +3035,7 @@ nla_put_failure: return skb->len; } -static int ip_vs_genl_parse_service(struct net *net, +static int ip_vs_genl_parse_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *usvc, struct nlattr *nla, int full_entry, struct ip_vs_service **ret_svc) @@ -3073,9 +3080,9 @@ static int ip_vs_genl_parse_service(struct net *net, rcu_read_lock(); if (usvc->fwmark) - svc = __ip_vs_svc_fwm_find(net, usvc->af, usvc->fwmark); + svc = __ip_vs_svc_fwm_find(ipvs, usvc->af, usvc->fwmark); else - svc = __ip_vs_service_find(net, usvc->af, usvc->protocol, + svc = __ip_vs_service_find(ipvs, usvc->af, usvc->protocol, &usvc->addr, usvc->port); rcu_read_unlock(); *ret_svc = svc; @@ -3113,14 +3120,14 @@ static int ip_vs_genl_parse_service(struct net *net, return 0; } -static struct ip_vs_service *ip_vs_genl_find_service(struct net *net, +static struct ip_vs_service *ip_vs_genl_find_service(struct netns_ipvs *ipvs, struct nlattr *nla) { struct ip_vs_service_user_kern usvc; struct ip_vs_service *svc; int ret; - ret = ip_vs_genl_parse_service(net, &usvc, nla, 0, &svc); + ret = ip_vs_genl_parse_service(ipvs, &usvc, nla, 0, &svc); return ret ? ERR_PTR(ret) : svc; } @@ -3195,7 +3202,8 @@ static int ip_vs_genl_dump_dests(struct sk_buff *skb, struct ip_vs_service *svc; struct ip_vs_dest *dest; struct nlattr *attrs[IPVS_CMD_ATTR_MAX + 1]; - struct net *net = skb_sknet(skb); + struct net *net = sock_net(skb->sk); + struct netns_ipvs *ipvs = net_ipvs(net); mutex_lock(&__ip_vs_mutex); @@ -3205,7 +3213,7 @@ static int ip_vs_genl_dump_dests(struct sk_buff *skb, goto out_err; - svc = ip_vs_genl_find_service(net, attrs[IPVS_CMD_ATTR_SERVICE]); + svc = ip_vs_genl_find_service(ipvs, attrs[IPVS_CMD_ATTR_SERVICE]); if (IS_ERR(svc) || svc == NULL) goto out_err; @@ -3341,7 +3349,7 @@ nla_put_failure: static int ip_vs_genl_dump_daemons(struct sk_buff *skb, struct netlink_callback *cb) { - struct net *net = skb_sknet(skb); + struct net *net = sock_net(skb->sk); struct netns_ipvs *ipvs = net_ipvs(net); mutex_lock(&ipvs->sync_mutex); @@ -3367,9 +3375,8 @@ nla_put_failure: return skb->len; } -static int ip_vs_genl_new_daemon(struct net *net, struct nlattr **attrs) +static int ip_vs_genl_new_daemon(struct netns_ipvs *ipvs, struct nlattr **attrs) { - struct netns_ipvs *ipvs = net_ipvs(net); struct ipvs_sync_daemon_cfg c; struct nlattr *a; int ret; @@ -3426,33 +3433,32 @@ static int ip_vs_genl_new_daemon(struct net *net, struct nlattr **attrs) rtnl_lock(); mutex_lock(&ipvs->sync_mutex); - ret = start_sync_thread(net, &c, + ret = start_sync_thread(ipvs, &c, nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE])); mutex_unlock(&ipvs->sync_mutex); rtnl_unlock(); return ret; } -static int ip_vs_genl_del_daemon(struct net *net, struct nlattr **attrs) +static int ip_vs_genl_del_daemon(struct netns_ipvs *ipvs, struct nlattr **attrs) { - struct netns_ipvs *ipvs = net_ipvs(net); int ret; if (!attrs[IPVS_DAEMON_ATTR_STATE]) return -EINVAL; mutex_lock(&ipvs->sync_mutex); - ret = stop_sync_thread(net, + ret = stop_sync_thread(ipvs, nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE])); mutex_unlock(&ipvs->sync_mutex); return ret; } -static int ip_vs_genl_set_config(struct net *net, struct nlattr **attrs) +static int ip_vs_genl_set_config(struct netns_ipvs *ipvs, struct nlattr **attrs) { struct ip_vs_timeout_user t; - __ip_vs_get_timeouts(net, &t); + __ip_vs_get_timeouts(ipvs, &t); if (attrs[IPVS_CMD_ATTR_TIMEOUT_TCP]) t.tcp_timeout = nla_get_u32(attrs[IPVS_CMD_ATTR_TIMEOUT_TCP]); @@ -3464,17 +3470,15 @@ static int ip_vs_genl_set_config(struct net *net, struct nlattr **attrs) if (attrs[IPVS_CMD_ATTR_TIMEOUT_UDP]) t.udp_timeout = nla_get_u32(attrs[IPVS_CMD_ATTR_TIMEOUT_UDP]); - return ip_vs_set_timeout(net, &t); + return ip_vs_set_timeout(ipvs, &t); } static int ip_vs_genl_set_daemon(struct sk_buff *skb, struct genl_info *info) { int ret = -EINVAL, cmd; - struct net *net; - struct netns_ipvs *ipvs; + struct net *net = sock_net(skb->sk); + struct netns_ipvs *ipvs = net_ipvs(net); - net = skb_sknet(skb); - ipvs = net_ipvs(net); cmd = info->genlhdr->cmd; if (cmd == IPVS_CMD_NEW_DAEMON || cmd == IPVS_CMD_DEL_DAEMON) { @@ -3487,9 +3491,9 @@ static int ip_vs_genl_set_daemon(struct sk_buff *skb, struct genl_info *info) goto out; if (cmd == IPVS_CMD_NEW_DAEMON) - ret = ip_vs_genl_new_daemon(net, daemon_attrs); + ret = ip_vs_genl_new_daemon(ipvs, daemon_attrs); else - ret = ip_vs_genl_del_daemon(net, daemon_attrs); + ret = ip_vs_genl_del_daemon(ipvs, daemon_attrs); } out: @@ -3503,22 +3507,22 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) struct ip_vs_dest_user_kern udest; int ret = 0, cmd; int need_full_svc = 0, need_full_dest = 0; - struct net *net; + struct net *net = sock_net(skb->sk); + struct netns_ipvs *ipvs = net_ipvs(net); - net = skb_sknet(skb); cmd = info->genlhdr->cmd; mutex_lock(&__ip_vs_mutex); if (cmd == IPVS_CMD_FLUSH) { - ret = ip_vs_flush(net, false); + ret = ip_vs_flush(ipvs, false); goto out; } else if (cmd == IPVS_CMD_SET_CONFIG) { - ret = ip_vs_genl_set_config(net, info->attrs); + ret = ip_vs_genl_set_config(ipvs, info->attrs); goto out; } else if (cmd == IPVS_CMD_ZERO && !info->attrs[IPVS_CMD_ATTR_SERVICE]) { - ret = ip_vs_zero_all(net); + ret = ip_vs_zero_all(ipvs); goto out; } @@ -3528,7 +3532,7 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) if (cmd == IPVS_CMD_NEW_SERVICE || cmd == IPVS_CMD_SET_SERVICE) need_full_svc = 1; - ret = ip_vs_genl_parse_service(net, &usvc, + ret = ip_vs_genl_parse_service(ipvs, &usvc, info->attrs[IPVS_CMD_ATTR_SERVICE], need_full_svc, &svc); if (ret) @@ -3567,7 +3571,7 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) /* The synchronization protocol is incompatible * with mixed family services */ - if (net_ipvs(net)->sync_state) { + if (ipvs->sync_state) { ret = -EINVAL; goto out; } @@ -3587,7 +3591,7 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) switch (cmd) { case IPVS_CMD_NEW_SERVICE: if (svc == NULL) - ret = ip_vs_add_service(net, &usvc, &svc); + ret = ip_vs_add_service(ipvs, &usvc, &svc); else ret = -EEXIST; break; @@ -3625,9 +3629,9 @@ static int ip_vs_genl_get_cmd(struct sk_buff *skb, struct genl_info *info) struct sk_buff *msg; void *reply; int ret, cmd, reply_cmd; - struct net *net; + struct net *net = sock_net(skb->sk); + struct netns_ipvs *ipvs = net_ipvs(net); - net = skb_sknet(skb); cmd = info->genlhdr->cmd; if (cmd == IPVS_CMD_GET_SERVICE) @@ -3656,7 +3660,7 @@ static int ip_vs_genl_get_cmd(struct sk_buff *skb, struct genl_info *info) { struct ip_vs_service *svc; - svc = ip_vs_genl_find_service(net, + svc = ip_vs_genl_find_service(ipvs, info->attrs[IPVS_CMD_ATTR_SERVICE]); if (IS_ERR(svc)) { ret = PTR_ERR(svc); @@ -3677,7 +3681,7 @@ static int ip_vs_genl_get_cmd(struct sk_buff *skb, struct genl_info *info) { struct ip_vs_timeout_user t; - __ip_vs_get_timeouts(net, &t); + __ip_vs_get_timeouts(ipvs, &t); #ifdef CONFIG_IP_VS_PROTO_TCP if (nla_put_u32(msg, IPVS_CMD_ATTR_TIMEOUT_TCP, t.tcp_timeout) || @@ -3832,10 +3836,10 @@ static void ip_vs_genl_unregister(void) * per netns intit/exit func. */ #ifdef CONFIG_SYSCTL -static int __net_init ip_vs_control_net_init_sysctl(struct net *net) +static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs) { + struct net *net = ipvs->net; int idx; - struct netns_ipvs *ipvs = net_ipvs(net); struct ctl_table *tbl; atomic_set(&ipvs->dropentry, 0); @@ -3854,6 +3858,10 @@ static int __net_init ip_vs_control_net_init_sysctl(struct net *net) } else tbl = vs_vars; /* Initialize sysctl defaults */ + for (idx = 0; idx < ARRAY_SIZE(vs_vars); idx++) { + if (tbl[idx].proc_handler == proc_do_defense_mode) + tbl[idx].extra2 = ipvs; + } idx = 0; ipvs->sysctl_amemthresh = 1024; tbl[idx++].data = &ipvs->sysctl_amemthresh; @@ -3895,7 +3903,8 @@ static int __net_init ip_vs_control_net_init_sysctl(struct net *net) tbl[idx++].data = &ipvs->sysctl_backup_only; ipvs->sysctl_conn_reuse_mode = 1; tbl[idx++].data = &ipvs->sysctl_conn_reuse_mode; - + tbl[idx++].data = &ipvs->sysctl_schedule_icmp; + tbl[idx++].data = &ipvs->sysctl_ignore_tunneled; ipvs->sysctl_hdr = register_net_sysctl(net, "net/ipv4/vs", tbl); if (ipvs->sysctl_hdr == NULL) { @@ -3903,7 +3912,7 @@ static int __net_init ip_vs_control_net_init_sysctl(struct net *net) kfree(tbl); return -ENOMEM; } - ip_vs_start_estimator(net, &ipvs->tot_stats); + ip_vs_start_estimator(ipvs, &ipvs->tot_stats); ipvs->sysctl_tbl = tbl; /* Schedule defense work */ INIT_DELAYED_WORK(&ipvs->defense_work, defense_work_handler); @@ -3912,14 +3921,14 @@ static int __net_init ip_vs_control_net_init_sysctl(struct net *net) return 0; } -static void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net) +static void __net_exit ip_vs_control_net_cleanup_sysctl(struct netns_ipvs *ipvs) { - struct netns_ipvs *ipvs = net_ipvs(net); + struct net *net = ipvs->net; cancel_delayed_work_sync(&ipvs->defense_work); cancel_work_sync(&ipvs->defense_work.work); unregister_net_sysctl_table(ipvs->sysctl_hdr); - ip_vs_stop_estimator(net, &ipvs->tot_stats); + ip_vs_stop_estimator(ipvs, &ipvs->tot_stats); if (!net_eq(net, &init_net)) kfree(ipvs->sysctl_tbl); @@ -3927,8 +3936,8 @@ static void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net) #else -static int __net_init ip_vs_control_net_init_sysctl(struct net *net) { return 0; } -static void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net) { } +static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs) { return 0; } +static void __net_exit ip_vs_control_net_cleanup_sysctl(struct netns_ipvs *ipvs) { } #endif @@ -3936,10 +3945,10 @@ static struct notifier_block ip_vs_dst_notifier = { .notifier_call = ip_vs_dst_event, }; -int __net_init ip_vs_control_net_init(struct net *net) +int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs) { + struct net *net = ipvs->net; int i, idx; - struct netns_ipvs *ipvs = net_ipvs(net); /* Initialize rs_table */ for (idx = 0; idx < IP_VS_RTAB_SIZE; idx++) @@ -3948,7 +3957,7 @@ int __net_init ip_vs_control_net_init(struct net *net) INIT_LIST_HEAD(&ipvs->dest_trash); spin_lock_init(&ipvs->dest_trash_lock); setup_timer(&ipvs->dest_trash_timer, ip_vs_dest_trash_expire, - (unsigned long) net); + (unsigned long) ipvs); atomic_set(&ipvs->ftpsvc_counter, 0); atomic_set(&ipvs->nullsvc_counter, 0); @@ -3970,7 +3979,7 @@ int __net_init ip_vs_control_net_init(struct net *net) proc_create("ip_vs_stats_percpu", 0, net->proc_net, &ip_vs_stats_percpu_fops); - if (ip_vs_control_net_init_sysctl(net)) + if (ip_vs_control_net_init_sysctl(ipvs)) goto err; return 0; @@ -3980,12 +3989,12 @@ err: return -ENOMEM; } -void __net_exit ip_vs_control_net_cleanup(struct net *net) +void __net_exit ip_vs_control_net_cleanup(struct netns_ipvs *ipvs) { - struct netns_ipvs *ipvs = net_ipvs(net); + struct net *net = ipvs->net; - ip_vs_trash_cleanup(net); - ip_vs_control_net_cleanup_sysctl(net); + ip_vs_trash_cleanup(ipvs); + ip_vs_control_net_cleanup_sysctl(ipvs); remove_proc_entry("ip_vs_stats_percpu", net->proc_net); remove_proc_entry("ip_vs_stats", net->proc_net); remove_proc_entry("ip_vs", net->proc_net); diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index ef0eb0a8d552..457c6c193e13 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -102,10 +102,8 @@ static void estimation_timer(unsigned long arg) struct ip_vs_estimator *e; struct ip_vs_stats *s; u64 rate; - struct net *net = (struct net *)arg; - struct netns_ipvs *ipvs; + struct netns_ipvs *ipvs = (struct netns_ipvs *)arg; - ipvs = net_ipvs(net); spin_lock(&ipvs->est_lock); list_for_each_entry(e, &ipvs->est_list, list) { s = container_of(e, struct ip_vs_stats, est); @@ -140,9 +138,8 @@ static void estimation_timer(unsigned long arg) mod_timer(&ipvs->est_timer, jiffies + 2*HZ); } -void ip_vs_start_estimator(struct net *net, struct ip_vs_stats *stats) +void ip_vs_start_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats) { - struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_estimator *est = &stats->est; INIT_LIST_HEAD(&est->list); @@ -152,9 +149,8 @@ void ip_vs_start_estimator(struct net *net, struct ip_vs_stats *stats) spin_unlock_bh(&ipvs->est_lock); } -void ip_vs_stop_estimator(struct net *net, struct ip_vs_stats *stats) +void ip_vs_stop_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats) { - struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_estimator *est = &stats->est; spin_lock_bh(&ipvs->est_lock); @@ -192,18 +188,16 @@ void ip_vs_read_estimator(struct ip_vs_kstats *dst, struct ip_vs_stats *stats) dst->outbps = (e->outbps + 0xF) >> 5; } -int __net_init ip_vs_estimator_net_init(struct net *net) +int __net_init ip_vs_estimator_net_init(struct netns_ipvs *ipvs) { - struct netns_ipvs *ipvs = net_ipvs(net); - INIT_LIST_HEAD(&ipvs->est_list); spin_lock_init(&ipvs->est_lock); - setup_timer(&ipvs->est_timer, estimation_timer, (unsigned long)net); + setup_timer(&ipvs->est_timer, estimation_timer, (unsigned long)ipvs); mod_timer(&ipvs->est_timer, jiffies + 2 * HZ); return 0; } -void __net_exit ip_vs_estimator_net_cleanup(struct net *net) +void __net_exit ip_vs_estimator_net_cleanup(struct netns_ipvs *ipvs) { - del_timer_sync(&net_ipvs(net)->est_timer); + del_timer_sync(&ipvs->est_timer); } diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index 5d3daae98bf0..d30c327bb578 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -181,7 +181,6 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, int ret = 0; enum ip_conntrack_info ctinfo; struct nf_conn *ct; - struct net *net; *diff = 0; @@ -223,14 +222,14 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, */ { struct ip_vs_conn_param p; - ip_vs_conn_fill_param(ip_vs_conn_net(cp), AF_INET, + ip_vs_conn_fill_param(cp->ipvs, AF_INET, iph->protocol, &from, port, &cp->caddr, 0, &p); n_cp = ip_vs_conn_out_get(&p); } if (!n_cp) { struct ip_vs_conn_param p; - ip_vs_conn_fill_param(ip_vs_conn_net(cp), + ip_vs_conn_fill_param(cp->ipvs, AF_INET, IPPROTO_TCP, &cp->caddr, 0, &cp->vaddr, port, &p); /* As above, this is ipv4 only */ @@ -289,9 +288,8 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, * would be adjusted twice. */ - net = skb_net(skb); cp->app_data = NULL; - ip_vs_tcp_conn_listen(net, n_cp); + ip_vs_tcp_conn_listen(n_cp); ip_vs_conn_put(n_cp); return ret; } @@ -320,7 +318,6 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, union nf_inet_addr to; __be16 port; struct ip_vs_conn *n_cp; - struct net *net; /* no diff required for incoming packets */ *diff = 0; @@ -392,7 +389,7 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, { struct ip_vs_conn_param p; - ip_vs_conn_fill_param(ip_vs_conn_net(cp), AF_INET, + ip_vs_conn_fill_param(cp->ipvs, AF_INET, iph->protocol, &to, port, &cp->vaddr, htons(ntohs(cp->vport)-1), &p); n_cp = ip_vs_conn_in_get(&p); @@ -413,8 +410,7 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, /* * Move tunnel to listen state */ - net = skb_net(skb); - ip_vs_tcp_conn_listen(net, n_cp); + ip_vs_tcp_conn_listen(n_cp); ip_vs_conn_put(n_cp); return 1; @@ -447,14 +443,14 @@ static int __net_init __ip_vs_ftp_init(struct net *net) if (!ipvs) return -ENOENT; - app = register_ip_vs_app(net, &ip_vs_ftp); + app = register_ip_vs_app(ipvs, &ip_vs_ftp); if (IS_ERR(app)) return PTR_ERR(app); for (i = 0; i < ports_count; i++) { if (!ports[i]) continue; - ret = register_ip_vs_app_inc(net, app, app->protocol, ports[i]); + ret = register_ip_vs_app_inc(ipvs, app, app->protocol, ports[i]); if (ret) goto err_unreg; pr_info("%s: loaded support on port[%d] = %d\n", @@ -463,7 +459,7 @@ static int __net_init __ip_vs_ftp_init(struct net *net) return 0; err_unreg: - unregister_ip_vs_app(net, &ip_vs_ftp); + unregister_ip_vs_app(ipvs, &ip_vs_ftp); return ret; } /* @@ -471,7 +467,12 @@ err_unreg: */ static void __ip_vs_ftp_exit(struct net *net) { - unregister_ip_vs_app(net, &ip_vs_ftp); + struct netns_ipvs *ipvs = net_ipvs(net); + + if (!ipvs) + return; + + unregister_ip_vs_app(ipvs, &ip_vs_ftp); } static struct pernet_operations ip_vs_ftp_ops = { diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c index 127f14046c51..cccf4d637412 100644 --- a/net/netfilter/ipvs/ip_vs_lblc.c +++ b/net/netfilter/ipvs/ip_vs_lblc.c @@ -250,8 +250,7 @@ static void ip_vs_lblc_flush(struct ip_vs_service *svc) static int sysctl_lblc_expiration(struct ip_vs_service *svc) { #ifdef CONFIG_SYSCTL - struct netns_ipvs *ipvs = net_ipvs(svc->net); - return ipvs->sysctl_lblc_expiration; + return svc->ipvs->sysctl_lblc_expiration; #else return DEFAULT_EXPIRATION; #endif diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index 2229d2d8bbe0..796d70e47ddd 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -415,8 +415,7 @@ static void ip_vs_lblcr_flush(struct ip_vs_service *svc) static int sysctl_lblcr_expiration(struct ip_vs_service *svc) { #ifdef CONFIG_SYSCTL - struct netns_ipvs *ipvs = net_ipvs(svc->net); - return ipvs->sysctl_lblcr_expiration; + return svc->ipvs->sysctl_lblcr_expiration; #else return DEFAULT_EXPIRATION; #endif diff --git a/net/netfilter/ipvs/ip_vs_nfct.c b/net/netfilter/ipvs/ip_vs_nfct.c index 136184572fc9..30434fb133df 100644 --- a/net/netfilter/ipvs/ip_vs_nfct.c +++ b/net/netfilter/ipvs/ip_vs_nfct.c @@ -161,7 +161,7 @@ static void ip_vs_nfct_expect_callback(struct nf_conn *ct, /* RS->CLIENT */ orig = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; - ip_vs_conn_fill_param(net, exp->tuple.src.l3num, orig->dst.protonum, + ip_vs_conn_fill_param(net_ipvs(net), exp->tuple.src.l3num, orig->dst.protonum, &orig->src.u3, orig->src.u.tcp.port, &orig->dst.u3, orig->dst.u.tcp.port, &p); cp = ip_vs_conn_out_get(&p); @@ -274,8 +274,7 @@ void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp) " for conn " FMT_CONN "\n", __func__, ARG_TUPLE(&tuple), ARG_CONN(cp)); - h = nf_conntrack_find_get(ip_vs_conn_net(cp), &nf_ct_zone_dflt, - &tuple); + h = nf_conntrack_find_get(cp->ipvs->net, &nf_ct_zone_dflt, &tuple); if (h) { ct = nf_ct_tuplehash_to_ctrack(h); /* Show what happens instead of calling nf_ct_kill() */ diff --git a/net/netfilter/ipvs/ip_vs_pe_sip.c b/net/netfilter/ipvs/ip_vs_pe_sip.c index bed5f7042529..1b8d594e493a 100644 --- a/net/netfilter/ipvs/ip_vs_pe_sip.c +++ b/net/netfilter/ipvs/ip_vs_pe_sip.c @@ -70,7 +70,7 @@ ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb) const char *dptr; int retc; - ip_vs_fill_iph_skb(p->af, skb, &iph); + ip_vs_fill_iph_skb(p->af, skb, false, &iph); /* Only useful with UDP */ if (iph.protocol != IPPROTO_UDP) diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c index 939f7fbe9b46..8ae480715cea 100644 --- a/net/netfilter/ipvs/ip_vs_proto.c +++ b/net/netfilter/ipvs/ip_vs_proto.c @@ -63,9 +63,8 @@ static int __used __init register_ip_vs_protocol(struct ip_vs_protocol *pp) * register an ipvs protocols netns related data */ static int -register_ip_vs_proto_netns(struct net *net, struct ip_vs_protocol *pp) +register_ip_vs_proto_netns(struct netns_ipvs *ipvs, struct ip_vs_protocol *pp) { - struct netns_ipvs *ipvs = net_ipvs(net); unsigned int hash = IP_VS_PROTO_HASH(pp->protocol); struct ip_vs_proto_data *pd = kzalloc(sizeof(struct ip_vs_proto_data), GFP_KERNEL); @@ -79,7 +78,7 @@ register_ip_vs_proto_netns(struct net *net, struct ip_vs_protocol *pp) atomic_set(&pd->appcnt, 0); /* Init app counter */ if (pp->init_netns != NULL) { - int ret = pp->init_netns(net, pd); + int ret = pp->init_netns(ipvs, pd); if (ret) { /* unlink an free proto data */ ipvs->proto_data_table[hash] = pd->next; @@ -116,9 +115,8 @@ static int unregister_ip_vs_protocol(struct ip_vs_protocol *pp) * unregister an ipvs protocols netns data */ static int -unregister_ip_vs_proto_netns(struct net *net, struct ip_vs_proto_data *pd) +unregister_ip_vs_proto_netns(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd) { - struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_proto_data **pd_p; unsigned int hash = IP_VS_PROTO_HASH(pd->pp->protocol); @@ -127,7 +125,7 @@ unregister_ip_vs_proto_netns(struct net *net, struct ip_vs_proto_data *pd) if (*pd_p == pd) { *pd_p = pd->next; if (pd->pp->exit_netns != NULL) - pd->pp->exit_netns(net, pd); + pd->pp->exit_netns(ipvs, pd); kfree(pd); return 0; } @@ -156,8 +154,8 @@ EXPORT_SYMBOL(ip_vs_proto_get); /* * get ip_vs_protocol object data by netns and proto */ -static struct ip_vs_proto_data * -__ipvs_proto_data_get(struct netns_ipvs *ipvs, unsigned short proto) +struct ip_vs_proto_data * +ip_vs_proto_data_get(struct netns_ipvs *ipvs, unsigned short proto) { struct ip_vs_proto_data *pd; unsigned int hash = IP_VS_PROTO_HASH(proto); @@ -169,14 +167,6 @@ __ipvs_proto_data_get(struct netns_ipvs *ipvs, unsigned short proto) return NULL; } - -struct ip_vs_proto_data * -ip_vs_proto_data_get(struct net *net, unsigned short proto) -{ - struct netns_ipvs *ipvs = net_ipvs(net); - - return __ipvs_proto_data_get(ipvs, proto); -} EXPORT_SYMBOL(ip_vs_proto_data_get); /* @@ -317,7 +307,7 @@ ip_vs_tcpudp_debug_packet(int af, struct ip_vs_protocol *pp, /* * per network name-space init */ -int __net_init ip_vs_protocol_net_init(struct net *net) +int __net_init ip_vs_protocol_net_init(struct netns_ipvs *ipvs) { int i, ret; static struct ip_vs_protocol *protos[] = { @@ -339,27 +329,26 @@ int __net_init ip_vs_protocol_net_init(struct net *net) }; for (i = 0; i < ARRAY_SIZE(protos); i++) { - ret = register_ip_vs_proto_netns(net, protos[i]); + ret = register_ip_vs_proto_netns(ipvs, protos[i]); if (ret < 0) goto cleanup; } return 0; cleanup: - ip_vs_protocol_net_cleanup(net); + ip_vs_protocol_net_cleanup(ipvs); return ret; } -void __net_exit ip_vs_protocol_net_cleanup(struct net *net) +void __net_exit ip_vs_protocol_net_cleanup(struct netns_ipvs *ipvs) { - struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_proto_data *pd; int i; /* unregister all the ipvs proto data for this netns */ for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) { while ((pd = ipvs->proto_data_table[i]) != NULL) - unregister_ip_vs_proto_netns(net, pd); + unregister_ip_vs_proto_netns(ipvs, pd); } } diff --git a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c index 5de3dd312c0f..5320d39976e1 100644 --- a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c +++ b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c @@ -41,30 +41,28 @@ struct isakmp_hdr { #define PORT_ISAKMP 500 static void -ah_esp_conn_fill_param_proto(struct net *net, int af, - const struct ip_vs_iphdr *iph, int inverse, +ah_esp_conn_fill_param_proto(struct netns_ipvs *ipvs, int af, + const struct ip_vs_iphdr *iph, struct ip_vs_conn_param *p) { - if (likely(!inverse)) - ip_vs_conn_fill_param(net, af, IPPROTO_UDP, + if (likely(!ip_vs_iph_inverse(iph))) + ip_vs_conn_fill_param(ipvs, af, IPPROTO_UDP, &iph->saddr, htons(PORT_ISAKMP), &iph->daddr, htons(PORT_ISAKMP), p); else - ip_vs_conn_fill_param(net, af, IPPROTO_UDP, + ip_vs_conn_fill_param(ipvs, af, IPPROTO_UDP, &iph->daddr, htons(PORT_ISAKMP), &iph->saddr, htons(PORT_ISAKMP), p); } static struct ip_vs_conn * -ah_esp_conn_in_get(int af, const struct sk_buff *skb, - const struct ip_vs_iphdr *iph, - int inverse) +ah_esp_conn_in_get(struct netns_ipvs *ipvs, int af, const struct sk_buff *skb, + const struct ip_vs_iphdr *iph) { struct ip_vs_conn *cp; struct ip_vs_conn_param p; - struct net *net = skb_net(skb); - ah_esp_conn_fill_param_proto(net, af, iph, inverse, &p); + ah_esp_conn_fill_param_proto(ipvs, af, iph, &p); cp = ip_vs_conn_in_get(&p); if (!cp) { /* @@ -73,7 +71,7 @@ ah_esp_conn_in_get(int af, const struct sk_buff *skb, */ IP_VS_DBG_BUF(12, "Unknown ISAKMP entry for outin packet " "%s%s %s->%s\n", - inverse ? "ICMP+" : "", + ip_vs_iph_icmp(iph) ? "ICMP+" : "", ip_vs_proto_get(iph->protocol)->name, IP_VS_DBG_ADDR(af, &iph->saddr), IP_VS_DBG_ADDR(af, &iph->daddr)); @@ -84,19 +82,18 @@ ah_esp_conn_in_get(int af, const struct sk_buff *skb, static struct ip_vs_conn * -ah_esp_conn_out_get(int af, const struct sk_buff *skb, - const struct ip_vs_iphdr *iph, int inverse) +ah_esp_conn_out_get(struct netns_ipvs *ipvs, int af, const struct sk_buff *skb, + const struct ip_vs_iphdr *iph) { struct ip_vs_conn *cp; struct ip_vs_conn_param p; - struct net *net = skb_net(skb); - ah_esp_conn_fill_param_proto(net, af, iph, inverse, &p); + ah_esp_conn_fill_param_proto(ipvs, af, iph, &p); cp = ip_vs_conn_out_get(&p); if (!cp) { IP_VS_DBG_BUF(12, "Unknown ISAKMP entry for inout packet " "%s%s %s->%s\n", - inverse ? "ICMP+" : "", + ip_vs_iph_icmp(iph) ? "ICMP+" : "", ip_vs_proto_get(iph->protocol)->name, IP_VS_DBG_ADDR(af, &iph->saddr), IP_VS_DBG_ADDR(af, &iph->daddr)); @@ -107,7 +104,8 @@ ah_esp_conn_out_get(int af, const struct sk_buff *skb, static int -ah_esp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, +ah_esp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, + struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp, struct ip_vs_iphdr *iph) { diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 5b84c0b56642..010ddeec135f 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -9,35 +9,44 @@ #include <net/ip_vs.h> static int -sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, +sctp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, + struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp, struct ip_vs_iphdr *iph) { - struct net *net; struct ip_vs_service *svc; - struct netns_ipvs *ipvs; sctp_chunkhdr_t _schunkh, *sch; sctp_sctphdr_t *sh, _sctph; - - sh = skb_header_pointer(skb, iph->len, sizeof(_sctph), &_sctph); - if (sh == NULL) { - *verdict = NF_DROP; - return 0; + __be16 _ports[2], *ports = NULL; + + if (likely(!ip_vs_iph_icmp(iph))) { + sh = skb_header_pointer(skb, iph->len, sizeof(_sctph), &_sctph); + if (sh) { + sch = skb_header_pointer( + skb, iph->len + sizeof(sctp_sctphdr_t), + sizeof(_schunkh), &_schunkh); + if (sch && (sch->type == SCTP_CID_INIT || + sysctl_sloppy_sctp(ipvs))) + ports = &sh->source; + } + } else { + ports = skb_header_pointer( + skb, iph->len, sizeof(_ports), &_ports); } - sch = skb_header_pointer(skb, iph->len + sizeof(sctp_sctphdr_t), - sizeof(_schunkh), &_schunkh); - if (sch == NULL) { + if (!ports) { *verdict = NF_DROP; return 0; } - net = skb_net(skb); - ipvs = net_ipvs(net); rcu_read_lock(); - if ((sch->type == SCTP_CID_INIT || sysctl_sloppy_sctp(ipvs)) && - (svc = ip_vs_service_find(net, af, skb->mark, iph->protocol, - &iph->daddr, sh->dest))) { + if (likely(!ip_vs_iph_inverse(iph))) + svc = ip_vs_service_find(ipvs, af, skb->mark, iph->protocol, + &iph->daddr, ports[1]); + else + svc = ip_vs_service_find(ipvs, af, skb->mark, iph->protocol, + &iph->saddr, ports[0]); + if (svc) { int ignored; if (ip_vs_todrop(ipvs)) { @@ -474,14 +483,13 @@ static inline __u16 sctp_app_hashkey(__be16 port) & SCTP_APP_TAB_MASK; } -static int sctp_register_app(struct net *net, struct ip_vs_app *inc) +static int sctp_register_app(struct netns_ipvs *ipvs, struct ip_vs_app *inc) { struct ip_vs_app *i; __u16 hash; __be16 port = inc->port; int ret = 0; - struct netns_ipvs *ipvs = net_ipvs(net); - struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_SCTP); + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(ipvs, IPPROTO_SCTP); hash = sctp_app_hashkey(port); @@ -498,9 +506,9 @@ out: return ret; } -static void sctp_unregister_app(struct net *net, struct ip_vs_app *inc) +static void sctp_unregister_app(struct netns_ipvs *ipvs, struct ip_vs_app *inc) { - struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_SCTP); + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(ipvs, IPPROTO_SCTP); atomic_dec(&pd->appcnt); list_del_rcu(&inc->p_list); @@ -508,7 +516,7 @@ static void sctp_unregister_app(struct net *net, struct ip_vs_app *inc) static int sctp_app_conn_bind(struct ip_vs_conn *cp) { - struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(cp)); + struct netns_ipvs *ipvs = cp->ipvs; int hash; struct ip_vs_app *inc; int result = 0; @@ -549,10 +557,8 @@ out: * timeouts is netns related now. * --------------------------------------------- */ -static int __ip_vs_sctp_init(struct net *net, struct ip_vs_proto_data *pd) +static int __ip_vs_sctp_init(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd) { - struct netns_ipvs *ipvs = net_ipvs(net); - ip_vs_init_hash_table(ipvs->sctp_apps, SCTP_APP_TAB_SIZE); pd->timeout_table = ip_vs_create_timeout_table((int *)sctp_timeouts, sizeof(sctp_timeouts)); @@ -561,7 +567,7 @@ static int __ip_vs_sctp_init(struct net *net, struct ip_vs_proto_data *pd) return 0; } -static void __ip_vs_sctp_exit(struct net *net, struct ip_vs_proto_data *pd) +static void __ip_vs_sctp_exit(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd) { kfree(pd->timeout_table); } diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index 8e92beb0cca9..d7024b2ed769 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -32,27 +32,47 @@ #include <net/ip_vs.h> static int -tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, +tcp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, + struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp, struct ip_vs_iphdr *iph) { - struct net *net; struct ip_vs_service *svc; struct tcphdr _tcph, *th; - struct netns_ipvs *ipvs; + __be16 _ports[2], *ports = NULL; - th = skb_header_pointer(skb, iph->len, sizeof(_tcph), &_tcph); - if (th == NULL) { + /* In the event of icmp, we're only guaranteed to have the first 8 + * bytes of the transport header, so we only check the rest of the + * TCP packet for non-ICMP packets + */ + if (likely(!ip_vs_iph_icmp(iph))) { + th = skb_header_pointer(skb, iph->len, sizeof(_tcph), &_tcph); + if (th) { + if (th->rst || !(sysctl_sloppy_tcp(ipvs) || th->syn)) + return 1; + ports = &th->source; + } + } else { + ports = skb_header_pointer( + skb, iph->len, sizeof(_ports), &_ports); + } + + if (!ports) { *verdict = NF_DROP; return 0; } - net = skb_net(skb); - ipvs = net_ipvs(net); + /* No !th->ack check to allow scheduling on SYN+ACK for Active FTP */ rcu_read_lock(); - if ((th->syn || sysctl_sloppy_tcp(ipvs)) && !th->rst && - (svc = ip_vs_service_find(net, af, skb->mark, iph->protocol, - &iph->daddr, th->dest))) { + + if (likely(!ip_vs_iph_inverse(iph))) + svc = ip_vs_service_find(ipvs, af, skb->mark, iph->protocol, + &iph->daddr, ports[1]); + else + svc = ip_vs_service_find(ipvs, af, skb->mark, iph->protocol, + &iph->saddr, ports[0]); + + if (svc) { int ignored; if (ip_vs_todrop(ipvs)) { @@ -571,14 +591,13 @@ static inline __u16 tcp_app_hashkey(__be16 port) } -static int tcp_register_app(struct net *net, struct ip_vs_app *inc) +static int tcp_register_app(struct netns_ipvs *ipvs, struct ip_vs_app *inc) { struct ip_vs_app *i; __u16 hash; __be16 port = inc->port; int ret = 0; - struct netns_ipvs *ipvs = net_ipvs(net); - struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_TCP); + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP); hash = tcp_app_hashkey(port); @@ -597,9 +616,9 @@ static int tcp_register_app(struct net *net, struct ip_vs_app *inc) static void -tcp_unregister_app(struct net *net, struct ip_vs_app *inc) +tcp_unregister_app(struct netns_ipvs *ipvs, struct ip_vs_app *inc) { - struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_TCP); + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP); atomic_dec(&pd->appcnt); list_del_rcu(&inc->p_list); @@ -609,7 +628,7 @@ tcp_unregister_app(struct net *net, struct ip_vs_app *inc) static int tcp_app_conn_bind(struct ip_vs_conn *cp) { - struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(cp)); + struct netns_ipvs *ipvs = cp->ipvs; int hash; struct ip_vs_app *inc; int result = 0; @@ -653,9 +672,9 @@ tcp_app_conn_bind(struct ip_vs_conn *cp) /* * Set LISTEN timeout. (ip_vs_conn_put will setup timer) */ -void ip_vs_tcp_conn_listen(struct net *net, struct ip_vs_conn *cp) +void ip_vs_tcp_conn_listen(struct ip_vs_conn *cp) { - struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_TCP); + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(cp->ipvs, IPPROTO_TCP); spin_lock_bh(&cp->lock); cp->state = IP_VS_TCP_S_LISTEN; @@ -668,10 +687,8 @@ void ip_vs_tcp_conn_listen(struct net *net, struct ip_vs_conn *cp) * timeouts is netns related now. * --------------------------------------------- */ -static int __ip_vs_tcp_init(struct net *net, struct ip_vs_proto_data *pd) +static int __ip_vs_tcp_init(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd) { - struct netns_ipvs *ipvs = net_ipvs(net); - ip_vs_init_hash_table(ipvs->tcp_apps, TCP_APP_TAB_SIZE); pd->timeout_table = ip_vs_create_timeout_table((int *)tcp_timeouts, sizeof(tcp_timeouts)); @@ -681,7 +698,7 @@ static int __ip_vs_tcp_init(struct net *net, struct ip_vs_proto_data *pd) return 0; } -static void __ip_vs_tcp_exit(struct net *net, struct ip_vs_proto_data *pd) +static void __ip_vs_tcp_exit(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd) { kfree(pd->timeout_table); } diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c index b62a3c0ff9bf..e494e9a88c7f 100644 --- a/net/netfilter/ipvs/ip_vs_proto_udp.c +++ b/net/netfilter/ipvs/ip_vs_proto_udp.c @@ -29,28 +29,42 @@ #include <net/ip6_checksum.h> static int -udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, +udp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, + struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp, struct ip_vs_iphdr *iph) { - struct net *net; struct ip_vs_service *svc; struct udphdr _udph, *uh; + __be16 _ports[2], *ports = NULL; - /* IPv6 fragments, only first fragment will hit this */ - uh = skb_header_pointer(skb, iph->len, sizeof(_udph), &_udph); - if (uh == NULL) { + if (likely(!ip_vs_iph_icmp(iph))) { + /* IPv6 fragments, only first fragment will hit this */ + uh = skb_header_pointer(skb, iph->len, sizeof(_udph), &_udph); + if (uh) + ports = &uh->source; + } else { + ports = skb_header_pointer( + skb, iph->len, sizeof(_ports), &_ports); + } + + if (!ports) { *verdict = NF_DROP; return 0; } - net = skb_net(skb); + rcu_read_lock(); - svc = ip_vs_service_find(net, af, skb->mark, iph->protocol, - &iph->daddr, uh->dest); + if (likely(!ip_vs_iph_inverse(iph))) + svc = ip_vs_service_find(ipvs, af, skb->mark, iph->protocol, + &iph->daddr, ports[1]); + else + svc = ip_vs_service_find(ipvs, af, skb->mark, iph->protocol, + &iph->saddr, ports[0]); + if (svc) { int ignored; - if (ip_vs_todrop(net_ipvs(net))) { + if (ip_vs_todrop(ipvs)) { /* * It seems that we are very loaded. * We have to drop this packet :( @@ -348,14 +362,13 @@ static inline __u16 udp_app_hashkey(__be16 port) } -static int udp_register_app(struct net *net, struct ip_vs_app *inc) +static int udp_register_app(struct netns_ipvs *ipvs, struct ip_vs_app *inc) { struct ip_vs_app *i; __u16 hash; __be16 port = inc->port; int ret = 0; - struct netns_ipvs *ipvs = net_ipvs(net); - struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_UDP); + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(ipvs, IPPROTO_UDP); hash = udp_app_hashkey(port); @@ -374,9 +387,9 @@ static int udp_register_app(struct net *net, struct ip_vs_app *inc) static void -udp_unregister_app(struct net *net, struct ip_vs_app *inc) +udp_unregister_app(struct netns_ipvs *ipvs, struct ip_vs_app *inc) { - struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_UDP); + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(ipvs, IPPROTO_UDP); atomic_dec(&pd->appcnt); list_del_rcu(&inc->p_list); @@ -385,7 +398,7 @@ udp_unregister_app(struct net *net, struct ip_vs_app *inc) static int udp_app_conn_bind(struct ip_vs_conn *cp) { - struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(cp)); + struct netns_ipvs *ipvs = cp->ipvs; int hash; struct ip_vs_app *inc; int result = 0; @@ -456,10 +469,8 @@ udp_state_transition(struct ip_vs_conn *cp, int direction, cp->timeout = pd->timeout_table[IP_VS_UDP_S_NORMAL]; } -static int __udp_init(struct net *net, struct ip_vs_proto_data *pd) +static int __udp_init(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd) { - struct netns_ipvs *ipvs = net_ipvs(net); - ip_vs_init_hash_table(ipvs->udp_apps, UDP_APP_TAB_SIZE); pd->timeout_table = ip_vs_create_timeout_table((int *)udp_timeouts, sizeof(udp_timeouts)); @@ -468,7 +479,7 @@ static int __udp_init(struct net *net, struct ip_vs_proto_data *pd) return 0; } -static void __udp_exit(struct net *net, struct ip_vs_proto_data *pd) +static void __udp_exit(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd) { kfree(pd->timeout_table); } diff --git a/net/netfilter/ipvs/ip_vs_sh.c b/net/netfilter/ipvs/ip_vs_sh.c index 98a13433b68c..1e373a5e44e3 100644 --- a/net/netfilter/ipvs/ip_vs_sh.c +++ b/net/netfilter/ipvs/ip_vs_sh.c @@ -280,35 +280,29 @@ static int ip_vs_sh_dest_changed(struct ip_vs_service *svc, static inline __be16 ip_vs_sh_get_port(const struct sk_buff *skb, struct ip_vs_iphdr *iph) { - __be16 port; - struct tcphdr _tcph, *th; - struct udphdr _udph, *uh; - sctp_sctphdr_t _sctph, *sh; + __be16 _ports[2], *ports; + /* At this point we know that we have a valid packet of some kind. + * Because ICMP packets are only guaranteed to have the first 8 + * bytes, let's just grab the ports. Fortunately they're in the + * same position for all three of the protocols we care about. + */ switch (iph->protocol) { case IPPROTO_TCP: - th = skb_header_pointer(skb, iph->len, sizeof(_tcph), &_tcph); - if (unlikely(th == NULL)) - return 0; - port = th->source; - break; case IPPROTO_UDP: - uh = skb_header_pointer(skb, iph->len, sizeof(_udph), &_udph); - if (unlikely(uh == NULL)) - return 0; - port = uh->source; - break; case IPPROTO_SCTP: - sh = skb_header_pointer(skb, iph->len, sizeof(_sctph), &_sctph); - if (unlikely(sh == NULL)) + ports = skb_header_pointer(skb, iph->len, sizeof(_ports), + &_ports); + if (unlikely(!ports)) return 0; - port = sh->source; - break; + + if (likely(!ip_vs_iph_inverse(iph))) + return ports[0]; + else + return ports[1]; default: - port = 0; + return 0; } - - return port; } @@ -322,6 +316,9 @@ ip_vs_sh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, struct ip_vs_dest *dest; struct ip_vs_sh_state *s; __be16 port = 0; + const union nf_inet_addr *hash_addr; + + hash_addr = ip_vs_iph_inverse(iph) ? &iph->daddr : &iph->saddr; IP_VS_DBG(6, "ip_vs_sh_schedule(): Scheduling...\n"); @@ -331,9 +328,9 @@ ip_vs_sh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, s = (struct ip_vs_sh_state *) svc->sched_data; if (svc->flags & IP_VS_SVC_F_SCHED_SH_FALLBACK) - dest = ip_vs_sh_get_fallback(svc, s, &iph->saddr, port); + dest = ip_vs_sh_get_fallback(svc, s, hash_addr, port); else - dest = ip_vs_sh_get(svc, s, &iph->saddr, port); + dest = ip_vs_sh_get(svc, s, hash_addr, port); if (!dest) { ip_vs_scheduler_err(svc, "no destination available"); @@ -341,7 +338,7 @@ ip_vs_sh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, } IP_VS_DBG_BUF(6, "SH: source IP address %s --> server %s:%d\n", - IP_VS_DBG_ADDR(svc->af, &iph->saddr), + IP_VS_DBG_ADDR(svc->af, hash_addr), IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port)); diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 43f140950075..803001a45aa1 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -193,7 +193,7 @@ union ip_vs_sync_conn { #define IPVS_OPT_F_PARAM (1 << (IPVS_OPT_PARAM-1)) struct ip_vs_sync_thread_data { - struct net *net; + struct netns_ipvs *ipvs; struct socket *sock; char *buf; int id; @@ -533,10 +533,9 @@ set: * Version 0 , could be switched in by sys_ctl. * Add an ip_vs_conn information into the current sync_buff. */ -static void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp, +static void ip_vs_sync_conn_v0(struct netns_ipvs *ipvs, struct ip_vs_conn *cp, int pkts) { - struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_sync_mesg_v0 *m; struct ip_vs_sync_conn_v0 *s; struct ip_vs_sync_buff *buff; @@ -615,7 +614,7 @@ static void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp, pkts = atomic_add_return(1, &cp->in_pkts); else pkts = sysctl_sync_threshold(ipvs); - ip_vs_sync_conn(net, cp, pkts); + ip_vs_sync_conn(ipvs, cp, pkts); } } @@ -624,9 +623,8 @@ static void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp, * Called by ip_vs_in. * Sending Version 1 messages */ -void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp, int pkts) +void ip_vs_sync_conn(struct netns_ipvs *ipvs, struct ip_vs_conn *cp, int pkts) { - struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_sync_mesg *m; union ip_vs_sync_conn *s; struct ip_vs_sync_buff *buff; @@ -637,7 +635,7 @@ void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp, int pkts) /* Handle old version of the protocol */ if (sysctl_sync_ver(ipvs) == 0) { - ip_vs_sync_conn_v0(net, cp, pkts); + ip_vs_sync_conn_v0(ipvs, cp, pkts); return; } /* Do not sync ONE PACKET */ @@ -784,21 +782,21 @@ control: * fill_param used by version 1 */ static inline int -ip_vs_conn_fill_param_sync(struct net *net, int af, union ip_vs_sync_conn *sc, +ip_vs_conn_fill_param_sync(struct netns_ipvs *ipvs, int af, union ip_vs_sync_conn *sc, struct ip_vs_conn_param *p, __u8 *pe_data, unsigned int pe_data_len, __u8 *pe_name, unsigned int pe_name_len) { #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) - ip_vs_conn_fill_param(net, af, sc->v6.protocol, + ip_vs_conn_fill_param(ipvs, af, sc->v6.protocol, (const union nf_inet_addr *)&sc->v6.caddr, sc->v6.cport, (const union nf_inet_addr *)&sc->v6.vaddr, sc->v6.vport, p); else #endif - ip_vs_conn_fill_param(net, af, sc->v4.protocol, + ip_vs_conn_fill_param(ipvs, af, sc->v4.protocol, (const union nf_inet_addr *)&sc->v4.caddr, sc->v4.cport, (const union nf_inet_addr *)&sc->v4.vaddr, @@ -837,7 +835,7 @@ ip_vs_conn_fill_param_sync(struct net *net, int af, union ip_vs_sync_conn *sc, * Param: ... * timeout is in sec. */ -static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param, +static void ip_vs_proc_conn(struct netns_ipvs *ipvs, struct ip_vs_conn_param *param, unsigned int flags, unsigned int state, unsigned int protocol, unsigned int type, const union nf_inet_addr *daddr, __be16 dport, @@ -846,7 +844,6 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param, { struct ip_vs_dest *dest; struct ip_vs_conn *cp; - struct netns_ipvs *ipvs = net_ipvs(net); if (!(flags & IP_VS_CONN_F_TEMPLATE)) { cp = ip_vs_conn_in_get(param); @@ -904,7 +901,7 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param, * with synchronization, so we can make the assumption that * the svc_af is the same as the dest_af */ - dest = ip_vs_find_dest(net, type, type, daddr, dport, + dest = ip_vs_find_dest(ipvs, type, type, daddr, dport, param->vaddr, param->vport, protocol, fwmark, flags); @@ -941,7 +938,7 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param, } else { struct ip_vs_proto_data *pd; - pd = ip_vs_proto_data_get(net, protocol); + pd = ip_vs_proto_data_get(ipvs, protocol); if (!(flags & IP_VS_CONN_F_TEMPLATE) && pd && pd->timeout_table) cp->timeout = pd->timeout_table[state]; else @@ -953,7 +950,7 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param, /* * Process received multicast message for Version 0 */ -static void ip_vs_process_message_v0(struct net *net, const char *buffer, +static void ip_vs_process_message_v0(struct netns_ipvs *ipvs, const char *buffer, const size_t buflen) { struct ip_vs_sync_mesg_v0 *m = (struct ip_vs_sync_mesg_v0 *)buffer; @@ -1009,14 +1006,14 @@ static void ip_vs_process_message_v0(struct net *net, const char *buffer, } } - ip_vs_conn_fill_param(net, AF_INET, s->protocol, + ip_vs_conn_fill_param(ipvs, AF_INET, s->protocol, (const union nf_inet_addr *)&s->caddr, s->cport, (const union nf_inet_addr *)&s->vaddr, s->vport, ¶m); /* Send timeout as Zero */ - ip_vs_proc_conn(net, ¶m, flags, state, s->protocol, AF_INET, + ip_vs_proc_conn(ipvs, ¶m, flags, state, s->protocol, AF_INET, (union nf_inet_addr *)&s->daddr, s->dport, 0, 0, opt); } @@ -1067,7 +1064,7 @@ static int ip_vs_proc_str(__u8 *p, unsigned int plen, unsigned int *data_len, /* * Process a Version 1 sync. connection */ -static inline int ip_vs_proc_sync_conn(struct net *net, __u8 *p, __u8 *msg_end) +static inline int ip_vs_proc_sync_conn(struct netns_ipvs *ipvs, __u8 *p, __u8 *msg_end) { struct ip_vs_sync_conn_options opt; union ip_vs_sync_conn *s; @@ -1171,21 +1168,21 @@ static inline int ip_vs_proc_sync_conn(struct net *net, __u8 *p, __u8 *msg_end) state = 0; } } - if (ip_vs_conn_fill_param_sync(net, af, s, ¶m, pe_data, + if (ip_vs_conn_fill_param_sync(ipvs, af, s, ¶m, pe_data, pe_data_len, pe_name, pe_name_len)) { retc = 50; goto out; } /* If only IPv4, just silent skip IPv6 */ if (af == AF_INET) - ip_vs_proc_conn(net, ¶m, flags, state, s->v4.protocol, af, + ip_vs_proc_conn(ipvs, ¶m, flags, state, s->v4.protocol, af, (union nf_inet_addr *)&s->v4.daddr, s->v4.dport, ntohl(s->v4.timeout), ntohl(s->v4.fwmark), (opt_flags & IPVS_OPT_F_SEQ_DATA ? &opt : NULL) ); #ifdef CONFIG_IP_VS_IPV6 else - ip_vs_proc_conn(net, ¶m, flags, state, s->v6.protocol, af, + ip_vs_proc_conn(ipvs, ¶m, flags, state, s->v6.protocol, af, (union nf_inet_addr *)&s->v6.daddr, s->v6.dport, ntohl(s->v6.timeout), ntohl(s->v6.fwmark), (opt_flags & IPVS_OPT_F_SEQ_DATA ? &opt : NULL) @@ -1204,10 +1201,9 @@ out: * ip_vs_conn entries. * Handles Version 0 & 1 */ -static void ip_vs_process_message(struct net *net, __u8 *buffer, +static void ip_vs_process_message(struct netns_ipvs *ipvs, __u8 *buffer, const size_t buflen) { - struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_sync_mesg *m2 = (struct ip_vs_sync_mesg *)buffer; __u8 *p, *msg_end; int i, nr_conns; @@ -1257,7 +1253,7 @@ static void ip_vs_process_message(struct net *net, __u8 *buffer, return; } /* Process a single sync_conn */ - retc = ip_vs_proc_sync_conn(net, p, msg_end); + retc = ip_vs_proc_sync_conn(ipvs, p, msg_end); if (retc < 0) { IP_VS_ERR_RL("BACKUP, Dropping buffer, Err: %d in decoding\n", retc); @@ -1268,7 +1264,7 @@ static void ip_vs_process_message(struct net *net, __u8 *buffer, } } else { /* Old type of message */ - ip_vs_process_message_v0(net, buffer, buflen); + ip_vs_process_message_v0(ipvs, buffer, buflen); return; } } @@ -1493,16 +1489,15 @@ static void get_mcast_sockaddr(union ipvs_sockaddr *sa, int *salen, /* * Set up sending multicast socket over UDP */ -static struct socket *make_send_sock(struct net *net, int id) +static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id) { - struct netns_ipvs *ipvs = net_ipvs(net); /* multicast addr */ union ipvs_sockaddr mcast_addr; struct socket *sock; int result, salen; /* First create a socket */ - result = sock_create_kern(net, ipvs->mcfg.mcast_af, SOCK_DGRAM, + result = sock_create_kern(ipvs->net, ipvs->mcfg.mcast_af, SOCK_DGRAM, IPPROTO_UDP, &sock); if (result < 0) { pr_err("Error during creation of socket; terminating\n"); @@ -1550,16 +1545,15 @@ error: /* * Set up receiving multicast socket over UDP */ -static struct socket *make_receive_sock(struct net *net, int id) +static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id) { - struct netns_ipvs *ipvs = net_ipvs(net); /* multicast addr */ union ipvs_sockaddr mcast_addr; struct socket *sock; int result, salen; /* First create a socket */ - result = sock_create_kern(net, ipvs->bcfg.mcast_af, SOCK_DGRAM, + result = sock_create_kern(ipvs->net, ipvs->bcfg.mcast_af, SOCK_DGRAM, IPPROTO_UDP, &sock); if (result < 0) { pr_err("Error during creation of socket; terminating\n"); @@ -1687,7 +1681,7 @@ next_sync_buff(struct netns_ipvs *ipvs, struct ipvs_master_sync_state *ms) static int sync_thread_master(void *data) { struct ip_vs_sync_thread_data *tinfo = data; - struct netns_ipvs *ipvs = net_ipvs(tinfo->net); + struct netns_ipvs *ipvs = tinfo->ipvs; struct ipvs_master_sync_state *ms = &ipvs->ms[tinfo->id]; struct sock *sk = tinfo->sock->sk; struct ip_vs_sync_buff *sb; @@ -1743,7 +1737,7 @@ done: static int sync_thread_backup(void *data) { struct ip_vs_sync_thread_data *tinfo = data; - struct netns_ipvs *ipvs = net_ipvs(tinfo->net); + struct netns_ipvs *ipvs = tinfo->ipvs; int len; pr_info("sync thread started: state = BACKUP, mcast_ifn = %s, " @@ -1765,7 +1759,7 @@ static int sync_thread_backup(void *data) break; } - ip_vs_process_message(tinfo->net, tinfo->buf, len); + ip_vs_process_message(ipvs, tinfo->buf, len); } } @@ -1778,13 +1772,12 @@ static int sync_thread_backup(void *data) } -int start_sync_thread(struct net *net, struct ipvs_sync_daemon_cfg *c, +int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c, int state) { struct ip_vs_sync_thread_data *tinfo; struct task_struct **array = NULL, *task; struct socket *sock; - struct netns_ipvs *ipvs = net_ipvs(net); struct net_device *dev; char *name; int (*threadfn)(void *data); @@ -1811,7 +1804,7 @@ int start_sync_thread(struct net *net, struct ipvs_sync_daemon_cfg *c, if (!c->mcast_ttl) c->mcast_ttl = 1; - dev = __dev_get_by_name(net, c->mcast_ifn); + dev = __dev_get_by_name(ipvs->net, c->mcast_ifn); if (!dev) { pr_err("Unknown mcast interface: %s\n", c->mcast_ifn); return -ENODEV; @@ -1873,9 +1866,9 @@ int start_sync_thread(struct net *net, struct ipvs_sync_daemon_cfg *c, tinfo = NULL; for (id = 0; id < count; id++) { if (state == IP_VS_STATE_MASTER) - sock = make_send_sock(net, id); + sock = make_send_sock(ipvs, id); else - sock = make_receive_sock(net, id); + sock = make_receive_sock(ipvs, id); if (IS_ERR(sock)) { result = PTR_ERR(sock); goto outtinfo; @@ -1883,7 +1876,7 @@ int start_sync_thread(struct net *net, struct ipvs_sync_daemon_cfg *c, tinfo = kmalloc(sizeof(*tinfo), GFP_KERNEL); if (!tinfo) goto outsocket; - tinfo->net = net; + tinfo->ipvs = ipvs; tinfo->sock = sock; if (state == IP_VS_STATE_BACKUP) { tinfo->buf = kmalloc(ipvs->bcfg.sync_maxlen, @@ -1947,9 +1940,8 @@ out: } -int stop_sync_thread(struct net *net, int state) +int stop_sync_thread(struct netns_ipvs *ipvs, int state) { - struct netns_ipvs *ipvs = net_ipvs(net); struct task_struct **array; int id; int retc = -EINVAL; @@ -2015,27 +2007,24 @@ int stop_sync_thread(struct net *net, int state) /* * Initialize data struct for each netns */ -int __net_init ip_vs_sync_net_init(struct net *net) +int __net_init ip_vs_sync_net_init(struct netns_ipvs *ipvs) { - struct netns_ipvs *ipvs = net_ipvs(net); - __mutex_init(&ipvs->sync_mutex, "ipvs->sync_mutex", &__ipvs_sync_key); spin_lock_init(&ipvs->sync_lock); spin_lock_init(&ipvs->sync_buff_lock); return 0; } -void ip_vs_sync_net_cleanup(struct net *net) +void ip_vs_sync_net_cleanup(struct netns_ipvs *ipvs) { int retc; - struct netns_ipvs *ipvs = net_ipvs(net); mutex_lock(&ipvs->sync_mutex); - retc = stop_sync_thread(net, IP_VS_STATE_MASTER); + retc = stop_sync_thread(ipvs, IP_VS_STATE_MASTER); if (retc && retc != -ESRCH) pr_err("Failed to stop Master Daemon\n"); - retc = stop_sync_thread(net, IP_VS_STATE_BACKUP); + retc = stop_sync_thread(ipvs, IP_VS_STATE_BACKUP); if (retc && retc != -ESRCH) pr_err("Failed to stop Backup Daemon\n"); mutex_unlock(&ipvs->sync_mutex); diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 258a0b0e82a2..77182b9750cd 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -212,19 +212,20 @@ static inline void maybe_update_pmtu(int skb_af, struct sk_buff *skb, int mtu) ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu); } -static inline bool ensure_mtu_is_adequate(int skb_af, int rt_mode, +static inline bool ensure_mtu_is_adequate(struct netns_ipvs *ipvs, int skb_af, + int rt_mode, struct ip_vs_iphdr *ipvsh, struct sk_buff *skb, int mtu) { #ifdef CONFIG_IP_VS_IPV6 if (skb_af == AF_INET6) { - struct net *net = dev_net(skb_dst(skb)->dev); + struct net *net = ipvs->net; if (unlikely(__mtu_check_toobig_v6(skb, mtu))) { if (!skb->dev) skb->dev = net->loopback_dev; /* only send ICMP too big on first fragment */ - if (!ipvsh->fragoffs) + if (!ipvsh->fragoffs && !ip_vs_iph_icmp(ipvsh)) icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); IP_VS_DBG(1, "frag needed for %pI6c\n", &ipv6_hdr(skb)->saddr); @@ -233,8 +234,6 @@ static inline bool ensure_mtu_is_adequate(int skb_af, int rt_mode, } else #endif { - struct netns_ipvs *ipvs = net_ipvs(skb_net(skb)); - /* If we're going to tunnel the packet and pmtu discovery * is disabled, we'll just fragment it anyway */ @@ -242,7 +241,8 @@ static inline bool ensure_mtu_is_adequate(int skb_af, int rt_mode, return true; if (unlikely(ip_hdr(skb)->frag_off & htons(IP_DF) && - skb->len > mtu && !skb_is_gso(skb))) { + skb->len > mtu && !skb_is_gso(skb) && + !ip_vs_iph_icmp(ipvsh))) { icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); IP_VS_DBG(1, "frag needed for %pI4\n", @@ -256,11 +256,12 @@ static inline bool ensure_mtu_is_adequate(int skb_af, int rt_mode, /* Get route to destination or remote server */ static int -__ip_vs_get_out_rt(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest, +__ip_vs_get_out_rt(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb, + struct ip_vs_dest *dest, __be32 daddr, int rt_mode, __be32 *ret_saddr, struct ip_vs_iphdr *ipvsh) { - struct net *net = dev_net(skb_dst(skb)->dev); + struct net *net = ipvs->net; struct ip_vs_dest_dst *dest_dst; struct rtable *rt; /* Route to the other host */ int mtu; @@ -336,7 +337,7 @@ __ip_vs_get_out_rt(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest, maybe_update_pmtu(skb_af, skb, mtu); } - if (!ensure_mtu_is_adequate(skb_af, rt_mode, ipvsh, skb, mtu)) + if (!ensure_mtu_is_adequate(ipvs, skb_af, rt_mode, ipvsh, skb, mtu)) goto err_put; skb_dst_drop(skb); @@ -402,11 +403,12 @@ out_err: * Get route to destination or remote server */ static int -__ip_vs_get_out_rt_v6(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest, +__ip_vs_get_out_rt_v6(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb, + struct ip_vs_dest *dest, struct in6_addr *daddr, struct in6_addr *ret_saddr, struct ip_vs_iphdr *ipvsh, int do_xfrm, int rt_mode) { - struct net *net = dev_net(skb_dst(skb)->dev); + struct net *net = ipvs->net; struct ip_vs_dest_dst *dest_dst; struct rt6_info *rt; /* Route to the other host */ struct dst_entry *dst; @@ -484,7 +486,7 @@ __ip_vs_get_out_rt_v6(int skb_af, struct sk_buff *skb, struct ip_vs_dest *dest, maybe_update_pmtu(skb_af, skb, mtu); } - if (!ensure_mtu_is_adequate(skb_af, rt_mode, ipvsh, skb, mtu)) + if (!ensure_mtu_is_adequate(ipvs, skb_af, rt_mode, ipvsh, skb, mtu)) goto err_put; skb_dst_drop(skb); @@ -573,8 +575,8 @@ static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb, skb_forward_csum(skb); if (!skb->sk) skb_sender_cpu_clear(skb); - NF_HOOK(pf, NF_INET_LOCAL_OUT, NULL, skb, - NULL, skb_dst(skb)->dev, dst_output_sk); + NF_HOOK(pf, NF_INET_LOCAL_OUT, cp->ipvs->net, NULL, skb, + NULL, skb_dst(skb)->dev, dst_output_okfn); } else ret = NF_ACCEPT; @@ -595,8 +597,8 @@ static inline int ip_vs_send_or_cont(int pf, struct sk_buff *skb, skb_forward_csum(skb); if (!skb->sk) skb_sender_cpu_clear(skb); - NF_HOOK(pf, NF_INET_LOCAL_OUT, NULL, skb, - NULL, skb_dst(skb)->dev, dst_output_sk); + NF_HOOK(pf, NF_INET_LOCAL_OUT, cp->ipvs->net, NULL, skb, + NULL, skb_dst(skb)->dev, dst_output_okfn); } else ret = NF_ACCEPT; return ret; @@ -629,7 +631,7 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, EnterFunction(10); rcu_read_lock(); - if (__ip_vs_get_out_rt(cp->af, skb, NULL, iph->daddr, + if (__ip_vs_get_out_rt(cp->ipvs, cp->af, skb, NULL, iph->daddr, IP_VS_RT_MODE_NON_LOCAL, NULL, ipvsh) < 0) goto tx_error; @@ -656,10 +658,13 @@ int ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh) { + struct ipv6hdr *iph = ipv6_hdr(skb); + EnterFunction(10); rcu_read_lock(); - if (__ip_vs_get_out_rt_v6(cp->af, skb, NULL, &ipvsh->daddr.in6, NULL, + if (__ip_vs_get_out_rt_v6(cp->ipvs, cp->af, skb, NULL, + &iph->daddr, NULL, ipvsh, 0, IP_VS_RT_MODE_NON_LOCAL) < 0) goto tx_error; @@ -706,7 +711,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, } was_input = rt_is_input_route(skb_rtable(skb)); - local = __ip_vs_get_out_rt(cp->af, skb, cp->dest, cp->daddr.ip, + local = __ip_vs_get_out_rt(cp->ipvs, cp->af, skb, cp->dest, cp->daddr.ip, IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL | IP_VS_RT_MODE_RDR, NULL, ipvsh); @@ -723,7 +728,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, struct nf_conn *ct = nf_ct_get(skb, &ctinfo); if (ct && !nf_ct_is_untracked(ct)) { - IP_VS_DBG_RL_PKT(10, AF_INET, pp, skb, 0, + IP_VS_DBG_RL_PKT(10, AF_INET, pp, skb, ipvsh->off, "ip_vs_nat_xmit(): " "stopping DNAT to local address"); goto tx_error; @@ -733,8 +738,9 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, /* From world but DNAT to loopback address? */ if (local && ipv4_is_loopback(cp->daddr.ip) && was_input) { - IP_VS_DBG_RL_PKT(1, AF_INET, pp, skb, 0, "ip_vs_nat_xmit(): " - "stopping DNAT to loopback address"); + IP_VS_DBG_RL_PKT(1, AF_INET, pp, skb, ipvsh->off, + "ip_vs_nat_xmit(): stopping DNAT to loopback " + "address"); goto tx_error; } @@ -751,7 +757,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, ip_hdr(skb)->daddr = cp->daddr.ip; ip_send_check(ip_hdr(skb)); - IP_VS_DBG_PKT(10, AF_INET, pp, skb, 0, "After DNAT"); + IP_VS_DBG_PKT(10, AF_INET, pp, skb, ipvsh->off, "After DNAT"); /* FIXME: when application helper enlarges the packet and the length is larger than the MTU of outgoing device, there will be still @@ -794,7 +800,8 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, IP_VS_DBG(10, "filled cport=%d\n", ntohs(*p)); } - local = __ip_vs_get_out_rt_v6(cp->af, skb, cp->dest, &cp->daddr.in6, + local = __ip_vs_get_out_rt_v6(cp->ipvs, cp->af, skb, cp->dest, + &cp->daddr.in6, NULL, ipvsh, 0, IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL | @@ -812,7 +819,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, struct nf_conn *ct = nf_ct_get(skb, &ctinfo); if (ct && !nf_ct_is_untracked(ct)) { - IP_VS_DBG_RL_PKT(10, AF_INET6, pp, skb, 0, + IP_VS_DBG_RL_PKT(10, AF_INET6, pp, skb, ipvsh->off, "ip_vs_nat_xmit_v6(): " "stopping DNAT to local address"); goto tx_error; @@ -823,7 +830,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, /* From world but DNAT to loopback address? */ if (local && skb->dev && !(skb->dev->flags & IFF_LOOPBACK) && ipv6_addr_type(&cp->daddr.in6) & IPV6_ADDR_LOOPBACK) { - IP_VS_DBG_RL_PKT(1, AF_INET6, pp, skb, 0, + IP_VS_DBG_RL_PKT(1, AF_INET6, pp, skb, ipvsh->off, "ip_vs_nat_xmit_v6(): " "stopping DNAT to loopback address"); goto tx_error; @@ -841,7 +848,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, goto tx_error; ipv6_hdr(skb)->daddr = cp->daddr.in6; - IP_VS_DBG_PKT(10, AF_INET6, pp, skb, 0, "After DNAT"); + IP_VS_DBG_PKT(10, AF_INET6, pp, skb, ipvsh->off, "After DNAT"); /* FIXME: when application helper enlarges the packet and the length is larger than the MTU of outgoing device, there will be still @@ -967,8 +974,8 @@ int ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, struct ip_vs_protocol *pp, struct ip_vs_iphdr *ipvsh) { - struct net *net = skb_net(skb); - struct netns_ipvs *ipvs = net_ipvs(net); + struct netns_ipvs *ipvs = cp->ipvs; + struct net *net = ipvs->net; struct rtable *rt; /* Route to the other host */ __be32 saddr; /* Source for tunnel */ struct net_device *tdev; /* Device to other host */ @@ -984,7 +991,7 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, EnterFunction(10); rcu_read_lock(); - local = __ip_vs_get_out_rt(cp->af, skb, cp->dest, cp->daddr.ip, + local = __ip_vs_get_out_rt(ipvs, cp->af, skb, cp->dest, cp->daddr.ip, IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL | IP_VS_RT_MODE_CONNECT | @@ -1078,7 +1085,8 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, EnterFunction(10); rcu_read_lock(); - local = __ip_vs_get_out_rt_v6(cp->af, skb, cp->dest, &cp->daddr.in6, + local = __ip_vs_get_out_rt_v6(cp->ipvs, cp->af, skb, cp->dest, + &cp->daddr.in6, &saddr, ipvsh, 1, IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL | @@ -1165,7 +1173,7 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, EnterFunction(10); rcu_read_lock(); - local = __ip_vs_get_out_rt(cp->af, skb, cp->dest, cp->daddr.ip, + local = __ip_vs_get_out_rt(cp->ipvs, cp->af, skb, cp->dest, cp->daddr.ip, IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL | IP_VS_RT_MODE_KNOWN_NH, NULL, ipvsh); @@ -1204,7 +1212,8 @@ ip_vs_dr_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, EnterFunction(10); rcu_read_lock(); - local = __ip_vs_get_out_rt_v6(cp->af, skb, cp->dest, &cp->daddr.in6, + local = __ip_vs_get_out_rt_v6(cp->ipvs, cp->af, skb, cp->dest, + &cp->daddr.in6, NULL, ipvsh, 0, IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL | @@ -1273,7 +1282,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL | IP_VS_RT_MODE_RDR : IP_VS_RT_MODE_NON_LOCAL; rcu_read_lock(); - local = __ip_vs_get_out_rt(cp->af, skb, cp->dest, cp->daddr.ip, rt_mode, + local = __ip_vs_get_out_rt(cp->ipvs, cp->af, skb, cp->dest, cp->daddr.ip, rt_mode, NULL, iph); if (local < 0) goto tx_error; @@ -1365,8 +1374,8 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL | IP_VS_RT_MODE_RDR : IP_VS_RT_MODE_NON_LOCAL; rcu_read_lock(); - local = __ip_vs_get_out_rt_v6(cp->af, skb, cp->dest, &cp->daddr.in6, - NULL, ipvsh, 0, rt_mode); + local = __ip_vs_get_out_rt_v6(cp->ipvs, cp->af, skb, cp->dest, + &cp->daddr.in6, NULL, ipvsh, 0, rt_mode); if (local < 0) goto tx_error; rt = (struct rt6_info *) skb_dst(skb); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index c09d6c7198f6..09d1d19b2ab9 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -168,6 +168,7 @@ nf_ct_get_tuple(const struct sk_buff *skb, unsigned int dataoff, u_int16_t l3num, u_int8_t protonum, + struct net *net, struct nf_conntrack_tuple *tuple, const struct nf_conntrack_l3proto *l3proto, const struct nf_conntrack_l4proto *l4proto) @@ -181,12 +182,13 @@ nf_ct_get_tuple(const struct sk_buff *skb, tuple->dst.protonum = protonum; tuple->dst.dir = IP_CT_DIR_ORIGINAL; - return l4proto->pkt_to_tuple(skb, dataoff, tuple); + return l4proto->pkt_to_tuple(skb, dataoff, net, tuple); } EXPORT_SYMBOL_GPL(nf_ct_get_tuple); bool nf_ct_get_tuplepr(const struct sk_buff *skb, unsigned int nhoff, - u_int16_t l3num, struct nf_conntrack_tuple *tuple) + u_int16_t l3num, + struct net *net, struct nf_conntrack_tuple *tuple) { struct nf_conntrack_l3proto *l3proto; struct nf_conntrack_l4proto *l4proto; @@ -205,7 +207,7 @@ bool nf_ct_get_tuplepr(const struct sk_buff *skb, unsigned int nhoff, l4proto = __nf_ct_l4proto_find(l3num, protonum); - ret = nf_ct_get_tuple(skb, nhoff, protoff, l3num, protonum, tuple, + ret = nf_ct_get_tuple(skb, nhoff, protoff, l3num, protonum, net, tuple, l3proto, l4proto); rcu_read_unlock(); @@ -1029,7 +1031,7 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl, u32 hash; if (!nf_ct_get_tuple(skb, skb_network_offset(skb), - dataoff, l3num, protonum, &tuple, l3proto, + dataoff, l3num, protonum, net, &tuple, l3proto, l4proto)) { pr_debug("resolve_normal_ct: Can't get tuple\n"); return NULL; diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 6dd995c7c72b..fce1b1cca32d 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -398,7 +398,7 @@ static inline struct dccp_net *dccp_pernet(struct net *net) } static bool dccp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, - struct nf_conntrack_tuple *tuple) + struct net *net, struct nf_conntrack_tuple *tuple) { struct dccp_hdr _hdr, *dh; diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c index 2281be419a74..86dc752e5349 100644 --- a/net/netfilter/nf_conntrack_proto_generic.c +++ b/net/netfilter/nf_conntrack_proto_generic.c @@ -45,7 +45,7 @@ static inline struct nf_generic_net *generic_pernet(struct net *net) static bool generic_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, - struct nf_conntrack_tuple *tuple) + struct net *net, struct nf_conntrack_tuple *tuple) { tuple->src.u.all = 0; tuple->dst.u.all = 0; diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index 7648674f29c3..a96451a7af20 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -190,9 +190,8 @@ static bool gre_invert_tuple(struct nf_conntrack_tuple *tuple, /* gre hdr info to tuple */ static bool gre_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, - struct nf_conntrack_tuple *tuple) + struct net *net, struct nf_conntrack_tuple *tuple) { - struct net *net = dev_net(skb->dev ? skb->dev : skb_dst(skb)->dev); const struct gre_hdr_pptp *pgrehdr; struct gre_hdr_pptp _pgrehdr; __be16 srckey; diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 67197731eb68..9578a7c371ef 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -156,7 +156,7 @@ static inline struct sctp_net *sctp_pernet(struct net *net) } static bool sctp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, - struct nf_conntrack_tuple *tuple) + struct net *net, struct nf_conntrack_tuple *tuple) { const struct sctphdr *hp; struct sctphdr _hdr; diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 70383de72054..278f3b9356ef 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -277,7 +277,7 @@ static inline struct nf_tcp_net *tcp_pernet(struct net *net) } static bool tcp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, - struct nf_conntrack_tuple *tuple) + struct net *net, struct nf_conntrack_tuple *tuple) { const struct tcphdr *hp; struct tcphdr _hdr; diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 6957281ffee5..478f92f834b6 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -38,6 +38,7 @@ static inline struct nf_udp_net *udp_pernet(struct net *net) static bool udp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, + struct net *net, struct nf_conntrack_tuple *tuple) { const struct udphdr *hp; diff --git a/net/netfilter/nf_conntrack_proto_udplite.c b/net/netfilter/nf_conntrack_proto_udplite.c index c5903d1649f9..1ac8ee13a873 100644 --- a/net/netfilter/nf_conntrack_proto_udplite.c +++ b/net/netfilter/nf_conntrack_proto_udplite.c @@ -48,6 +48,7 @@ static inline struct udplite_net *udplite_pernet(struct net *net) static bool udplite_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, + struct net *net, struct nf_conntrack_tuple *tuple) { const struct udphdr *hp; diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 5113dfd39df9..06a9f45771ab 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -83,7 +83,7 @@ out: rcu_read_unlock(); } -int nf_xfrm_me_harder(struct sk_buff *skb, unsigned int family) +int nf_xfrm_me_harder(struct net *net, struct sk_buff *skb, unsigned int family) { struct flowi fl; unsigned int hh_len; @@ -99,7 +99,7 @@ int nf_xfrm_me_harder(struct sk_buff *skb, unsigned int family) dst = ((struct xfrm_dst *)dst)->route; dst_hold(dst); - dst = xfrm_lookup(dev_net(dst->dev), dst, &fl, skb->sk, 0); + dst = xfrm_lookup(net, dst, &fl, skb->sk, 0); if (IS_ERR(dst)) return PTR_ERR(dst); diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index 96777f9a9350..34f628e16a4c 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -199,7 +199,7 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) if (verdict == NF_ACCEPT) { afinfo = nf_get_afinfo(entry->state.pf); - if (!afinfo || afinfo->reroute(skb, entry) < 0) + if (!afinfo || afinfo->reroute(entry->state.net, skb, entry) < 0) verdict = NF_DROP; } @@ -215,7 +215,7 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) case NF_ACCEPT: case NF_STOP: local_bh_disable(); - entry->state.okfn(entry->state.sk, skb); + entry->state.okfn(entry->state.net, entry->state.sk, skb); local_bh_enable(); break; case NF_QUEUE: diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 05d0b03530f6..f3695a497408 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -48,9 +48,7 @@ static void __nft_trace_packet(const struct nft_pktinfo *pkt, const struct nft_chain *chain, int rulenum, enum nft_trace type) { - struct net *net = dev_net(pkt->in ? pkt->in : pkt->out); - - nf_log_trace(net, pkt->xt.family, pkt->ops->hooknum, pkt->skb, pkt->in, + nf_log_trace(pkt->net, pkt->pf, pkt->hook, pkt->skb, pkt->in, pkt->out, &trace_loginfo, "TRACE: %s:%s:%s:%u ", chain->table->name, chain->name, comments[type], rulenum); @@ -111,10 +109,10 @@ struct nft_jumpstack { }; unsigned int -nft_do_chain(struct nft_pktinfo *pkt, const struct nf_hook_ops *ops) +nft_do_chain(struct nft_pktinfo *pkt, void *priv) { - const struct nft_chain *chain = ops->priv, *basechain = chain; - const struct net *net = dev_net(pkt->in ? pkt->in : pkt->out); + const struct nft_chain *chain = priv, *basechain = chain; + const struct net *net = pkt->net; const struct nft_rule *rule; const struct nft_expr *expr, *last; struct nft_regs regs; diff --git a/net/netfilter/nf_tables_netdev.c b/net/netfilter/nf_tables_netdev.c index 2cae4d4a03b7..7b9c053ba750 100644 --- a/net/netfilter/nf_tables_netdev.c +++ b/net/netfilter/nf_tables_netdev.c @@ -17,13 +17,13 @@ static inline void nft_netdev_set_pktinfo_ipv4(struct nft_pktinfo *pkt, - const struct nf_hook_ops *ops, struct sk_buff *skb, + struct sk_buff *skb, const struct nf_hook_state *state) { struct iphdr *iph, _iph; u32 len, thoff; - nft_set_pktinfo(pkt, ops, skb, state); + nft_set_pktinfo(pkt, skb, state); iph = skb_header_pointer(skb, skb_network_offset(skb), sizeof(*iph), &_iph); @@ -48,7 +48,6 @@ nft_netdev_set_pktinfo_ipv4(struct nft_pktinfo *pkt, static inline void __nft_netdev_set_pktinfo_ipv6(struct nft_pktinfo *pkt, - const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -82,33 +81,32 @@ __nft_netdev_set_pktinfo_ipv6(struct nft_pktinfo *pkt, } static inline void nft_netdev_set_pktinfo_ipv6(struct nft_pktinfo *pkt, - const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { - nft_set_pktinfo(pkt, ops, skb, state); - __nft_netdev_set_pktinfo_ipv6(pkt, ops, skb, state); + nft_set_pktinfo(pkt, skb, state); + __nft_netdev_set_pktinfo_ipv6(pkt, skb, state); } static unsigned int -nft_do_chain_netdev(const struct nf_hook_ops *ops, struct sk_buff *skb, +nft_do_chain_netdev(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { struct nft_pktinfo pkt; switch (eth_hdr(skb)->h_proto) { case htons(ETH_P_IP): - nft_netdev_set_pktinfo_ipv4(&pkt, ops, skb, state); + nft_netdev_set_pktinfo_ipv4(&pkt, skb, state); break; case htons(ETH_P_IPV6): - nft_netdev_set_pktinfo_ipv6(&pkt, ops, skb, state); + nft_netdev_set_pktinfo_ipv6(&pkt, skb, state); break; default: - nft_set_pktinfo(&pkt, ops, skb, state); + nft_set_pktinfo(&pkt, skb, state); break; } - return nft_do_chain(&pkt, ops); + return nft_do_chain(&pkt, priv); } static struct nft_af_info nft_af_netdev __read_mostly = { diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index a5cd6d90b78b..41583e30051b 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -670,8 +670,7 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) struct nfqnl_instance *queue; struct sk_buff *skb, *segs; int err = -ENOBUFS; - struct net *net = dev_net(entry->state.in ? - entry->state.in : entry->state.out); + struct net *net = entry->state.net; struct nfnl_queue_net *q = nfnl_queue_pernet(net); /* rcu_read_lock()ed by nf_hook_slow() */ diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c index a13d6a386d63..319c22b4bca2 100644 --- a/net/netfilter/nft_log.c +++ b/net/netfilter/nft_log.c @@ -31,9 +31,8 @@ static void nft_log_eval(const struct nft_expr *expr, const struct nft_pktinfo *pkt) { const struct nft_log *priv = nft_expr_priv(expr); - struct net *net = dev_net(pkt->in ? pkt->in : pkt->out); - nf_log_packet(net, pkt->ops->pf, pkt->ops->hooknum, pkt->skb, pkt->in, + nf_log_packet(pkt->net, pkt->pf, pkt->hook, pkt->skb, pkt->in, pkt->out, &priv->loginfo, "%s", priv->prefix); } diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index cb2f13ebb5a6..e4ad2c24bc41 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -42,7 +42,7 @@ void nft_meta_get_eval(const struct nft_expr *expr, *(__be16 *)dest = skb->protocol; break; case NFT_META_NFPROTO: - *dest = pkt->ops->pf; + *dest = pkt->pf; break; case NFT_META_L4PROTO: *dest = pkt->tprot; @@ -135,7 +135,7 @@ void nft_meta_get_eval(const struct nft_expr *expr, break; } - switch (pkt->ops->pf) { + switch (pkt->pf) { case NFPROTO_IPV4: if (ipv4_is_multicast(ip_hdr(skb)->daddr)) *dest = PACKET_MULTICAST; diff --git a/net/netfilter/nft_queue.c b/net/netfilter/nft_queue.c index 96805d21d618..61d216eb7917 100644 --- a/net/netfilter/nft_queue.c +++ b/net/netfilter/nft_queue.c @@ -42,7 +42,7 @@ static void nft_queue_eval(const struct nft_expr *expr, queue = priv->queuenum + cpu % priv->queues_total; } else { queue = nfqueue_hash(pkt->skb, queue, - priv->queues_total, pkt->ops->pf, + priv->queues_total, pkt->pf, jhash_initval); } } diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c index 635dbba93d01..759ca5248a3d 100644 --- a/net/netfilter/nft_reject_inet.c +++ b/net/netfilter/nft_reject_inet.c @@ -22,38 +22,37 @@ static void nft_reject_inet_eval(const struct nft_expr *expr, const struct nft_pktinfo *pkt) { struct nft_reject *priv = nft_expr_priv(expr); - struct net *net = dev_net((pkt->in != NULL) ? pkt->in : pkt->out); - switch (pkt->ops->pf) { + switch (pkt->pf) { case NFPROTO_IPV4: switch (priv->type) { case NFT_REJECT_ICMP_UNREACH: nf_send_unreach(pkt->skb, priv->icmp_code, - pkt->ops->hooknum); + pkt->hook); break; case NFT_REJECT_TCP_RST: - nf_send_reset(pkt->skb, pkt->ops->hooknum); + nf_send_reset(pkt->net, pkt->skb, pkt->hook); break; case NFT_REJECT_ICMPX_UNREACH: nf_send_unreach(pkt->skb, nft_reject_icmp_code(priv->icmp_code), - pkt->ops->hooknum); + pkt->hook); break; } break; case NFPROTO_IPV6: switch (priv->type) { case NFT_REJECT_ICMP_UNREACH: - nf_send_unreach6(net, pkt->skb, priv->icmp_code, - pkt->ops->hooknum); + nf_send_unreach6(pkt->net, pkt->skb, priv->icmp_code, + pkt->hook); break; case NFT_REJECT_TCP_RST: - nf_send_reset6(net, pkt->skb, pkt->ops->hooknum); + nf_send_reset6(pkt->net, pkt->skb, pkt->hook); break; case NFT_REJECT_ICMPX_UNREACH: - nf_send_unreach6(net, pkt->skb, + nf_send_unreach6(pkt->net, pkt->skb, nft_reject_icmpv6_code(priv->icmp_code), - pkt->ops->hooknum); + pkt->hook); break; } break; diff --git a/net/netfilter/xt_LOG.c b/net/netfilter/xt_LOG.c index c13b79440ede..1763ab82bcd7 100644 --- a/net/netfilter/xt_LOG.c +++ b/net/netfilter/xt_LOG.c @@ -33,7 +33,7 @@ log_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_log_info *loginfo = par->targinfo; struct nf_loginfo li; - struct net *net = dev_net(par->in ? par->in : par->out); + struct net *net = par->net; li.type = NF_LOG_TYPE_LOG; li.u.log.level = loginfo->level; diff --git a/net/netfilter/xt_NFLOG.c b/net/netfilter/xt_NFLOG.c index fb7497c928a0..a1fa2c800cb9 100644 --- a/net/netfilter/xt_NFLOG.c +++ b/net/netfilter/xt_NFLOG.c @@ -26,7 +26,7 @@ nflog_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_nflog_info *info = par->targinfo; struct nf_loginfo li; - struct net *net = dev_net(par->in ? par->in : par->out); + struct net *net = par->net; li.type = NF_LOG_TYPE_ULOG; li.u.ulog.copy_len = info->len; diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c index 8c02501a530f..b7c43def0dc6 100644 --- a/net/netfilter/xt_TCPMSS.c +++ b/net/netfilter/xt_TCPMSS.c @@ -108,7 +108,7 @@ tcpmss_mangle_packet(struct sk_buff *skb, return -1; if (info->mss == XT_TCPMSS_CLAMP_PMTU) { - struct net *net = dev_net(par->in ? par->in : par->out); + struct net *net = par->net; unsigned int in_mtu = tcpmss_reverse_mtu(net, skb, family); if (dst_mtu(skb_dst(skb)) <= minlen) { diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c index fd980aa7715d..899b06115fc5 100644 --- a/net/netfilter/xt_TEE.c +++ b/net/netfilter/xt_TEE.c @@ -32,7 +32,7 @@ tee_tg4(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_tee_tginfo *info = par->targinfo; - nf_dup_ipv4(skb, par->hooknum, &info->gw.in, info->priv->oif); + nf_dup_ipv4(par->net, skb, par->hooknum, &info->gw.in, info->priv->oif); return XT_CONTINUE; } @@ -43,7 +43,7 @@ tee_tg6(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_tee_tginfo *info = par->targinfo; - nf_dup_ipv6(skb, par->hooknum, &info->gw.in6, info->priv->oif); + nf_dup_ipv6(par->net, skb, par->hooknum, &info->gw.in6, info->priv->oif); return XT_CONTINUE; } diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index d0c96c5ae29a..3ab591e73ec0 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -250,8 +250,8 @@ nf_tproxy_get_sock_v6(struct net *net, const u8 protocol, * no such listener is found, or NULL if the TCP header is incomplete. */ static struct sock * -tproxy_handle_time_wait4(struct sk_buff *skb, __be32 laddr, __be16 lport, - struct sock *sk) +tproxy_handle_time_wait4(struct net *net, struct sk_buff *skb, + __be32 laddr, __be16 lport, struct sock *sk) { const struct iphdr *iph = ip_hdr(skb); struct tcphdr _hdr, *hp; @@ -267,7 +267,7 @@ tproxy_handle_time_wait4(struct sk_buff *skb, __be32 laddr, __be16 lport, * to a listener socket if there's one */ struct sock *sk2; - sk2 = nf_tproxy_get_sock_v4(dev_net(skb->dev), iph->protocol, + sk2 = nf_tproxy_get_sock_v4(net, iph->protocol, iph->saddr, laddr ? laddr : iph->daddr, hp->source, lport ? lport : hp->dest, skb->dev, NFT_LOOKUP_LISTENER); @@ -290,7 +290,7 @@ nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk) } static unsigned int -tproxy_tg4(struct sk_buff *skb, __be32 laddr, __be16 lport, +tproxy_tg4(struct net *net, struct sk_buff *skb, __be32 laddr, __be16 lport, u_int32_t mark_mask, u_int32_t mark_value) { const struct iphdr *iph = ip_hdr(skb); @@ -305,7 +305,7 @@ tproxy_tg4(struct sk_buff *skb, __be32 laddr, __be16 lport, * addresses, this happens if the redirect already happened * and the current packet belongs to an already established * connection */ - sk = nf_tproxy_get_sock_v4(dev_net(skb->dev), iph->protocol, + sk = nf_tproxy_get_sock_v4(net, iph->protocol, iph->saddr, iph->daddr, hp->source, hp->dest, skb->dev, NFT_LOOKUP_ESTABLISHED); @@ -317,11 +317,11 @@ tproxy_tg4(struct sk_buff *skb, __be32 laddr, __be16 lport, /* UDP has no TCP_TIME_WAIT state, so we never enter here */ if (sk && sk->sk_state == TCP_TIME_WAIT) /* reopening a TIME_WAIT connection needs special handling */ - sk = tproxy_handle_time_wait4(skb, laddr, lport, sk); + sk = tproxy_handle_time_wait4(net, skb, laddr, lport, sk); else if (!sk) /* no, there's no established connection, check if * there's a listener on the redirected addr/port */ - sk = nf_tproxy_get_sock_v4(dev_net(skb->dev), iph->protocol, + sk = nf_tproxy_get_sock_v4(net, iph->protocol, iph->saddr, laddr, hp->source, lport, skb->dev, NFT_LOOKUP_LISTENER); @@ -351,7 +351,7 @@ tproxy_tg4_v0(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_tproxy_target_info *tgi = par->targinfo; - return tproxy_tg4(skb, tgi->laddr, tgi->lport, tgi->mark_mask, tgi->mark_value); + return tproxy_tg4(par->net, skb, tgi->laddr, tgi->lport, tgi->mark_mask, tgi->mark_value); } static unsigned int @@ -359,7 +359,7 @@ tproxy_tg4_v1(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_tproxy_target_info_v1 *tgi = par->targinfo; - return tproxy_tg4(skb, tgi->laddr.ip, tgi->lport, tgi->mark_mask, tgi->mark_value); + return tproxy_tg4(par->net, skb, tgi->laddr.ip, tgi->lport, tgi->mark_mask, tgi->mark_value); } #ifdef XT_TPROXY_HAVE_IPV6 @@ -429,7 +429,7 @@ tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff, * to a listener socket if there's one */ struct sock *sk2; - sk2 = nf_tproxy_get_sock_v6(dev_net(skb->dev), tproto, + sk2 = nf_tproxy_get_sock_v6(par->net, tproto, &iph->saddr, tproxy_laddr6(skb, &tgi->laddr.in6, &iph->daddr), hp->source, @@ -472,7 +472,7 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par) * addresses, this happens if the redirect already happened * and the current packet belongs to an already established * connection */ - sk = nf_tproxy_get_sock_v6(dev_net(skb->dev), tproto, + sk = nf_tproxy_get_sock_v6(par->net, tproto, &iph->saddr, &iph->daddr, hp->source, hp->dest, par->in, NFT_LOOKUP_ESTABLISHED); @@ -487,7 +487,7 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par) else if (!sk) /* no there's no established connection, check if * there's a listener on the redirected addr/port */ - sk = nf_tproxy_get_sock_v6(dev_net(skb->dev), tproto, + sk = nf_tproxy_get_sock_v6(par->net, tproto, &iph->saddr, laddr, hp->source, lport, par->in, NFT_LOOKUP_LISTENER); diff --git a/net/netfilter/xt_addrtype.c b/net/netfilter/xt_addrtype.c index 5b4743cc0436..11d6091991a4 100644 --- a/net/netfilter/xt_addrtype.c +++ b/net/netfilter/xt_addrtype.c @@ -125,7 +125,7 @@ static inline bool match_type(struct net *net, const struct net_device *dev, static bool addrtype_mt_v0(const struct sk_buff *skb, struct xt_action_param *par) { - struct net *net = dev_net(par->in ? par->in : par->out); + struct net *net = par->net; const struct xt_addrtype_info *info = par->matchinfo; const struct iphdr *iph = ip_hdr(skb); bool ret = true; @@ -143,7 +143,7 @@ addrtype_mt_v0(const struct sk_buff *skb, struct xt_action_param *par) static bool addrtype_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) { - struct net *net = dev_net(par->in ? par->in : par->out); + struct net *net = par->net; const struct xt_addrtype_info_v1 *info = par->matchinfo; const struct iphdr *iph; const struct net_device *dev = NULL; diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c index 075d89d94d28..99bbc829868d 100644 --- a/net/netfilter/xt_connlimit.c +++ b/net/netfilter/xt_connlimit.c @@ -317,7 +317,7 @@ static int count_them(struct net *net, static bool connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) { - struct net *net = dev_net(par->in ? par->in : par->out); + struct net *net = par->net; const struct xt_connlimit_info *info = par->matchinfo; union nf_inet_addr addr; struct nf_conntrack_tuple tuple; @@ -332,7 +332,7 @@ connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) tuple_ptr = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; zone = nf_ct_zone(ct); } else if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), - par->family, &tuple)) { + par->family, net, &tuple)) { goto hotdrop; } diff --git a/net/netfilter/xt_ipvs.c b/net/netfilter/xt_ipvs.c index 8d47c3780fda..71a9d95e0a81 100644 --- a/net/netfilter/xt_ipvs.c +++ b/net/netfilter/xt_ipvs.c @@ -48,6 +48,7 @@ static bool ipvs_mt(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_ipvs_mtinfo *data = par->matchinfo; + struct netns_ipvs *ipvs = net_ipvs(par->net); /* ipvs_mt_check ensures that family is only NFPROTO_IPV[46]. */ const u_int8_t family = par->family; struct ip_vs_iphdr iph; @@ -67,7 +68,7 @@ ipvs_mt(const struct sk_buff *skb, struct xt_action_param *par) goto out; } - ip_vs_fill_iph_skb(family, skb, &iph); + ip_vs_fill_iph_skb(family, skb, true, &iph); if (data->bitmask & XT_IPVS_PROTO) if ((iph.protocol == data->l4proto) ^ @@ -85,7 +86,7 @@ ipvs_mt(const struct sk_buff *skb, struct xt_action_param *par) /* * Check if the packet belongs to an existing entry */ - cp = pp->conn_out_get(family, skb, &iph, 1 /* inverse */); + cp = pp->conn_out_get(ipvs, family, skb, &iph); if (unlikely(cp == NULL)) { match = false; goto out; diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c index 0778855ea5e7..df8801e02a32 100644 --- a/net/netfilter/xt_osf.c +++ b/net/netfilter/xt_osf.c @@ -200,7 +200,7 @@ xt_osf_match_packet(const struct sk_buff *skb, struct xt_action_param *p) unsigned char opts[MAX_IPOPTLEN]; const struct xt_osf_finger *kf; const struct xt_osf_user_finger *f; - struct net *net = dev_net(p->in ? p->in : p->out); + struct net *net = p->net; if (!info) return false; diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index 45e1b30e4fb2..d725a27743a1 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -237,7 +237,7 @@ static void recent_table_flush(struct recent_table *t) static bool recent_mt(const struct sk_buff *skb, struct xt_action_param *par) { - struct net *net = dev_net(par->in ? par->in : par->out); + struct net *net = par->net; struct recent_net *recent_net = recent_pernet(net); const struct xt_recent_mtinfo_v1 *info = par->matchinfo; struct recent_table *t; diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 43e26c881100..2ec08f04b816 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -143,7 +143,8 @@ static bool xt_socket_sk_is_transparent(struct sock *sk) } } -static struct sock *xt_socket_lookup_slow_v4(const struct sk_buff *skb, +static struct sock *xt_socket_lookup_slow_v4(struct net *net, + const struct sk_buff *skb, const struct net_device *indev) { const struct iphdr *iph = ip_hdr(skb); @@ -197,7 +198,7 @@ static struct sock *xt_socket_lookup_slow_v4(const struct sk_buff *skb, } #endif - return xt_socket_get_sock_v4(dev_net(skb->dev), protocol, saddr, daddr, + return xt_socket_get_sock_v4(net, protocol, saddr, daddr, sport, dport, indev); } @@ -209,7 +210,7 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, struct sock *sk = skb->sk; if (!sk) - sk = xt_socket_lookup_slow_v4(skb, par->in); + sk = xt_socket_lookup_slow_v4(par->net, skb, par->in); if (sk) { bool wildcard; bool transparent = true; @@ -335,7 +336,8 @@ xt_socket_get_sock_v6(struct net *net, const u8 protocol, return NULL; } -static struct sock *xt_socket_lookup_slow_v6(const struct sk_buff *skb, +static struct sock *xt_socket_lookup_slow_v6(struct net *net, + const struct sk_buff *skb, const struct net_device *indev) { __be16 uninitialized_var(dport), uninitialized_var(sport); @@ -371,7 +373,7 @@ static struct sock *xt_socket_lookup_slow_v6(const struct sk_buff *skb, return NULL; } - return xt_socket_get_sock_v6(dev_net(skb->dev), tproto, saddr, daddr, + return xt_socket_get_sock_v6(net, tproto, saddr, daddr, sport, dport, indev); } @@ -383,7 +385,7 @@ socket_mt6_v1_v2_v3(const struct sk_buff *skb, struct xt_action_param *par) struct sock *sk = skb->sk; if (!sk) - sk = xt_socket_lookup_slow_v6(skb, par->in); + sk = xt_socket_lookup_slow_v6(par->net, skb, par->in); if (sk) { bool wildcard; bool transparent = true; diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 2ed5f964772e..75724a96aef2 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -1136,19 +1136,19 @@ int genlmsg_multicast_allns(struct genl_family *family, struct sk_buff *skb, } EXPORT_SYMBOL(genlmsg_multicast_allns); -void genl_notify(struct genl_family *family, - struct sk_buff *skb, struct net *net, u32 portid, u32 group, - struct nlmsghdr *nlh, gfp_t flags) +void genl_notify(struct genl_family *family, struct sk_buff *skb, + struct genl_info *info, u32 group, gfp_t flags) { + struct net *net = genl_info_net(info); struct sock *sk = net->genl_sock; int report = 0; - if (nlh) - report = nlmsg_report(nlh); + if (info->nlhdr) + report = nlmsg_report(info->nlhdr); if (WARN_ON_ONCE(group >= family->n_mcgrps)) return; group = family->mcgrp_offset + group; - nlmsg_notify(sk, skb, portid, group, report, flags); + nlmsg_notify(sk, skb, info->snd_portid, group, report, flags); } EXPORT_SYMBOL(genl_notify); diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 002a755fa07e..eb759e3a88ca 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -347,7 +347,7 @@ ovs_ct_expect_find(struct net *net, const struct nf_conntrack_zone *zone, { struct nf_conntrack_tuple tuple; - if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), proto, &tuple)) + if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), proto, net, &tuple)) return NULL; return __nf_ct_expect_find(net, zone, &tuple); } diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index b816ff871528..a75828091e21 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -91,8 +91,7 @@ static bool ovs_must_notify(struct genl_family *family, struct genl_info *info, static void ovs_notify(struct genl_family *family, struct sk_buff *skb, struct genl_info *info) { - genl_notify(family, skb, genl_info_net(info), info->snd_portid, - 0, info->nlhdr, GFP_KERNEL); + genl_notify(family, skb, info, 0, GFP_KERNEL); } /** diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c index c11413d5075f..fb3cdb85905d 100644 --- a/net/openvswitch/vport-vxlan.c +++ b/net/openvswitch/vport-vxlan.c @@ -151,7 +151,8 @@ static int vxlan_get_egress_tun_info(struct vport *vport, struct sk_buff *skb, { struct vxlan_dev *vxlan = netdev_priv(vport->dev); struct net *net = ovs_dp_get_net(vport->dp); - __be16 dst_port = vxlan_dev_dst_port(vxlan); + unsigned short family = ip_tunnel_info_af(upcall->egress_tun_info); + __be16 dst_port = vxlan_dev_dst_port(vxlan, family); __be16 src_port; int port_min; int port_max; diff --git a/net/rxrpc/ar-connection.c b/net/rxrpc/ar-connection.c index 6631f4f1e39b..692b3e67fb54 100644 --- a/net/rxrpc/ar-connection.c +++ b/net/rxrpc/ar-connection.c @@ -808,7 +808,7 @@ void rxrpc_put_connection(struct rxrpc_connection *conn) ASSERTCMP(atomic_read(&conn->usage), >, 0); - conn->put_time = get_seconds(); + conn->put_time = ktime_get_seconds(); if (atomic_dec_and_test(&conn->usage)) { _debug("zombie"); rxrpc_queue_delayed_work(&rxrpc_connection_reap, 0); @@ -852,7 +852,7 @@ static void rxrpc_connection_reaper(struct work_struct *work) _enter(""); - now = get_seconds(); + now = ktime_get_seconds(); earliest = ULONG_MAX; write_lock_bh(&rxrpc_connection_lock); diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index aef1bd294e17..2934a73a5981 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -208,7 +208,7 @@ struct rxrpc_transport { struct rb_root server_conns; /* server connections on this transport */ struct list_head link; /* link in master session list */ struct sk_buff_head error_queue; /* error packets awaiting processing */ - time_t put_time; /* time at which to reap */ + unsigned long put_time; /* time at which to reap */ spinlock_t client_lock; /* client connection allocation lock */ rwlock_t conn_lock; /* lock for active/dead connections */ atomic_t usage; @@ -256,7 +256,7 @@ struct rxrpc_connection { struct rxrpc_crypt csum_iv; /* packet checksum base */ unsigned long events; #define RXRPC_CONN_CHALLENGE 0 /* send challenge packet */ - time_t put_time; /* time at which to reap */ + unsigned long put_time; /* time at which to reap */ rwlock_t lock; /* access lock */ spinlock_t state_lock; /* state-change lock */ atomic_t usage; diff --git a/net/rxrpc/ar-transport.c b/net/rxrpc/ar-transport.c index 1976dec84f29..9946467f16b4 100644 --- a/net/rxrpc/ar-transport.c +++ b/net/rxrpc/ar-transport.c @@ -189,7 +189,7 @@ void rxrpc_put_transport(struct rxrpc_transport *trans) ASSERTCMP(atomic_read(&trans->usage), >, 0); - trans->put_time = get_seconds(); + trans->put_time = ktime_get_seconds(); if (unlikely(atomic_dec_and_test(&trans->usage))) { _debug("zombie"); /* let the reaper determine the timeout to avoid a race with @@ -226,7 +226,7 @@ static void rxrpc_transport_reaper(struct work_struct *work) _enter(""); - now = get_seconds(); + now = ktime_get_seconds(); earliest = ULONG_MAX; /* extract all the transports that have been dead too long */ diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 559bfa011bda..0bc6f912f870 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -72,6 +72,7 @@ static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act, case TC_ACT_PIPE: case TC_ACT_RECLASSIFY: case TC_ACT_OK: + case TC_ACT_REDIRECT: action = filter_res; break; case TC_ACT_SHOT: diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 5019a47b9270..bb41699c6c49 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -68,13 +68,13 @@ static int tcf_connmark(struct sk_buff *skb, const struct tc_action *a, } if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), - proto, &tuple)) + proto, ca->net, &tuple)) goto out; zone.id = ca->zone; zone.dir = NF_CT_DEFAULT_ZONE_DIR; - thash = nf_conntrack_find_get(dev_net(skb->dev), &zone, &tuple); + thash = nf_conntrack_find_get(ca->net, &zone, &tuple); if (!thash) goto out; @@ -119,6 +119,7 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla, ci = to_connmark(a); ci->tcf_action = parm->action; + ci->net = net; ci->zone = parm->zone; tcf_hash_insert(a); diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 99c9cc1c7af9..d05869646515 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -189,6 +189,7 @@ static int tcf_ipt(struct sk_buff *skb, const struct tc_action *a, * worry later - danger - this API seems to have changed * from earlier kernels */ + par.net = dev_net(skb->dev); par.in = skb->dev; par.out = NULL; par.hooknum = ipt->tcfi_hook; diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index e5168f8b9640..7eeffaf69c75 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -38,6 +38,7 @@ struct cls_bpf_prog { struct bpf_prog *filter; struct list_head link; struct tcf_result res; + bool exts_integrated; struct tcf_exts exts; u32 handle; union { @@ -52,6 +53,7 @@ struct cls_bpf_prog { static const struct nla_policy bpf_policy[TCA_BPF_MAX + 1] = { [TCA_BPF_CLASSID] = { .type = NLA_U32 }, + [TCA_BPF_FLAGS] = { .type = NLA_U32 }, [TCA_BPF_FD] = { .type = NLA_U32 }, [TCA_BPF_NAME] = { .type = NLA_NUL_STRING, .len = CLS_BPF_NAME_LEN }, [TCA_BPF_OPS_LEN] = { .type = NLA_U16 }, @@ -59,6 +61,20 @@ static const struct nla_policy bpf_policy[TCA_BPF_MAX + 1] = { .len = sizeof(struct sock_filter) * BPF_MAXINSNS }, }; +static int cls_bpf_exec_opcode(int code) +{ + switch (code) { + case TC_ACT_OK: + case TC_ACT_SHOT: + case TC_ACT_STOLEN: + case TC_ACT_REDIRECT: + case TC_ACT_UNSPEC: + return code; + default: + return TC_ACT_UNSPEC; + } +} + static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { @@ -79,6 +95,8 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp, list_for_each_entry_rcu(prog, &head->plist, link) { int filter_res; + qdisc_skb_cb(skb)->tc_classid = prog->res.classid; + if (at_ingress) { /* It is safe to push/pull even if skb_shared() */ __skb_push(skb, skb->mac_len); @@ -88,6 +106,16 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp, filter_res = BPF_PROG_RUN(prog->filter, skb); } + if (prog->exts_integrated) { + res->class = prog->res.class; + res->classid = qdisc_skb_cb(skb)->tc_classid; + + ret = cls_bpf_exec_opcode(filter_res); + if (ret == TC_ACT_UNSPEC) + continue; + break; + } + if (filter_res == 0) continue; @@ -195,8 +223,7 @@ static unsigned long cls_bpf_get(struct tcf_proto *tp, u32 handle) return ret; } -static int cls_bpf_prog_from_ops(struct nlattr **tb, - struct cls_bpf_prog *prog, u32 classid) +static int cls_bpf_prog_from_ops(struct nlattr **tb, struct cls_bpf_prog *prog) { struct sock_filter *bpf_ops; struct sock_fprog_kern fprog_tmp; @@ -230,15 +257,12 @@ static int cls_bpf_prog_from_ops(struct nlattr **tb, prog->bpf_ops = bpf_ops; prog->bpf_num_ops = bpf_num_ops; prog->bpf_name = NULL; - prog->filter = fp; - prog->res.classid = classid; return 0; } -static int cls_bpf_prog_from_efd(struct nlattr **tb, - struct cls_bpf_prog *prog, u32 classid) +static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog) { struct bpf_prog *fp; char *name = NULL; @@ -268,9 +292,7 @@ static int cls_bpf_prog_from_efd(struct nlattr **tb, prog->bpf_ops = NULL; prog->bpf_fd = bpf_fd; prog->bpf_name = name; - prog->filter = fp; - prog->res.classid = classid; return 0; } @@ -280,16 +302,13 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp, unsigned long base, struct nlattr **tb, struct nlattr *est, bool ovr) { + bool is_bpf, is_ebpf, have_exts = false; struct tcf_exts exts; - bool is_bpf, is_ebpf; - u32 classid; int ret; is_bpf = tb[TCA_BPF_OPS_LEN] && tb[TCA_BPF_OPS]; is_ebpf = tb[TCA_BPF_FD]; - - if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf) || - !tb[TCA_BPF_CLASSID]) + if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf)) return -EINVAL; tcf_exts_init(&exts, TCA_BPF_ACT, TCA_BPF_POLICE); @@ -297,18 +316,32 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp, if (ret < 0) return ret; - classid = nla_get_u32(tb[TCA_BPF_CLASSID]); + if (tb[TCA_BPF_FLAGS]) { + u32 bpf_flags = nla_get_u32(tb[TCA_BPF_FLAGS]); + + if (bpf_flags & ~TCA_BPF_FLAG_ACT_DIRECT) { + tcf_exts_destroy(&exts); + return -EINVAL; + } + + have_exts = bpf_flags & TCA_BPF_FLAG_ACT_DIRECT; + } + + prog->exts_integrated = have_exts; - ret = is_bpf ? cls_bpf_prog_from_ops(tb, prog, classid) : - cls_bpf_prog_from_efd(tb, prog, classid); + ret = is_bpf ? cls_bpf_prog_from_ops(tb, prog) : + cls_bpf_prog_from_efd(tb, prog); if (ret < 0) { tcf_exts_destroy(&exts); return ret; } - tcf_bind_filter(tp, &prog->res, base); - tcf_exts_change(tp, &prog->exts, &exts); + if (tb[TCA_BPF_CLASSID]) { + prog->res.classid = nla_get_u32(tb[TCA_BPF_CLASSID]); + tcf_bind_filter(tp, &prog->res, base); + } + tcf_exts_change(tp, &prog->exts, &exts); return 0; } @@ -429,6 +462,7 @@ static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, { struct cls_bpf_prog *prog = (struct cls_bpf_prog *) fh; struct nlattr *nest; + u32 bpf_flags = 0; int ret; if (prog == NULL) @@ -440,7 +474,8 @@ static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, if (nest == NULL) goto nla_put_failure; - if (nla_put_u32(skb, TCA_BPF_CLASSID, prog->res.classid)) + if (prog->res.classid && + nla_put_u32(skb, TCA_BPF_CLASSID, prog->res.classid)) goto nla_put_failure; if (cls_bpf_is_ebpf(prog)) @@ -453,6 +488,11 @@ static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, unsigned long fh, if (tcf_exts_dump(skb, &prog->exts) < 0) goto nla_put_failure; + if (prog->exts_integrated) + bpf_flags |= TCA_BPF_FLAG_ACT_DIRECT; + if (bpf_flags && nla_put_u32(skb, TCA_BPF_FLAGS, bpf_flags)) + goto nla_put_failure; + nla_nest_end(skb, nest); if (tcf_exts_dump_stats(skb, &prog->exts) < 0) diff --git a/net/sched/em_ipset.c b/net/sched/em_ipset.c index df0328ba6a48..c66ca9400ab4 100644 --- a/net/sched/em_ipset.c +++ b/net/sched/em_ipset.c @@ -95,6 +95,7 @@ static int em_ipset_match(struct sk_buff *skb, struct tcf_ematch *em, if (skb->skb_iif) indev = dev_get_by_index_rcu(em->net, skb->skb_iif); + acpar.net = em->net; acpar.in = indev ? indev : dev; acpar.out = dev; diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index c4d45fd8c551..f357f34d02d2 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -35,14 +35,20 @@ #define NO_DEFAULT_INDEX (1 << 16) +struct mask_value { + u8 mask; + u8 value; +}; + struct dsmark_qdisc_data { struct Qdisc *q; struct tcf_proto __rcu *filter_list; - u8 *mask; /* "owns" the array */ - u8 *value; + struct mask_value *mv; u16 indices; + u8 set_tc_index; u32 default_index; /* index range is 0...0xffff */ - int set_tc_index; +#define DSMARK_EMBEDDED_SZ 16 + struct mask_value embedded[DSMARK_EMBEDDED_SZ]; }; static inline int dsmark_valid_index(struct dsmark_qdisc_data *p, u16 index) @@ -116,7 +122,6 @@ static int dsmark_change(struct Qdisc *sch, u32 classid, u32 parent, struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_DSMARK_MAX + 1]; int err = -EINVAL; - u8 mask = 0; pr_debug("%s(sch %p,[qdisc %p],classid %x,parent %x), arg 0x%lx\n", __func__, sch, p, classid, parent, *arg); @@ -133,14 +138,11 @@ static int dsmark_change(struct Qdisc *sch, u32 classid, u32 parent, if (err < 0) goto errout; - if (tb[TCA_DSMARK_MASK]) - mask = nla_get_u8(tb[TCA_DSMARK_MASK]); - if (tb[TCA_DSMARK_VALUE]) - p->value[*arg - 1] = nla_get_u8(tb[TCA_DSMARK_VALUE]); + p->mv[*arg - 1].value = nla_get_u8(tb[TCA_DSMARK_VALUE]); if (tb[TCA_DSMARK_MASK]) - p->mask[*arg - 1] = mask; + p->mv[*arg - 1].mask = nla_get_u8(tb[TCA_DSMARK_MASK]); err = 0; @@ -155,8 +157,8 @@ static int dsmark_delete(struct Qdisc *sch, unsigned long arg) if (!dsmark_valid_index(p, arg)) return -EINVAL; - p->mask[arg - 1] = 0xff; - p->value[arg - 1] = 0; + p->mv[arg - 1].mask = 0xff; + p->mv[arg - 1].value = 0; return 0; } @@ -173,7 +175,7 @@ static void dsmark_walk(struct Qdisc *sch, struct qdisc_walker *walker) return; for (i = 0; i < p->indices; i++) { - if (p->mask[i] == 0xff && !p->value[i]) + if (p->mv[i].mask == 0xff && !p->mv[i].value) goto ignore; if (walker->count >= walker->skip) { if (walker->fn(sch, i + 1, walker) < 0) { @@ -291,12 +293,12 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) switch (tc_skb_protocol(skb)) { case htons(ETH_P_IP): - ipv4_change_dsfield(ip_hdr(skb), p->mask[index], - p->value[index]); + ipv4_change_dsfield(ip_hdr(skb), p->mv[index].mask, + p->mv[index].value); break; case htons(ETH_P_IPV6): - ipv6_change_dsfield(ipv6_hdr(skb), p->mask[index], - p->value[index]); + ipv6_change_dsfield(ipv6_hdr(skb), p->mv[index].mask, + p->mv[index].value); break; default: /* @@ -304,7 +306,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) * This way, we can send non-IP traffic through dsmark * and don't need yet another qdisc as a bypass. */ - if (p->mask[index] != 0xff || p->value[index]) + if (p->mv[index].mask != 0xff || p->mv[index].value) pr_warn("%s: unsupported protocol %d\n", __func__, ntohs(tc_skb_protocol(skb))); break; @@ -346,7 +348,7 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt) int err = -EINVAL; u32 default_index = NO_DEFAULT_INDEX; u16 indices; - u8 *mask; + int i; pr_debug("%s(sch %p,[qdisc %p],opt %p)\n", __func__, sch, p, opt); @@ -366,18 +368,18 @@ static int dsmark_init(struct Qdisc *sch, struct nlattr *opt) if (tb[TCA_DSMARK_DEFAULT_INDEX]) default_index = nla_get_u16(tb[TCA_DSMARK_DEFAULT_INDEX]); - mask = kmalloc(indices * 2, GFP_KERNEL); - if (mask == NULL) { + if (indices <= DSMARK_EMBEDDED_SZ) + p->mv = p->embedded; + else + p->mv = kmalloc_array(indices, sizeof(*p->mv), GFP_KERNEL); + if (!p->mv) { err = -ENOMEM; goto errout; } - - p->mask = mask; - memset(p->mask, 0xff, indices); - - p->value = p->mask + indices; - memset(p->value, 0, indices); - + for (i = 0; i < indices; i++) { + p->mv[i].mask = 0xff; + p->mv[i].value = 0; + } p->indices = indices; p->default_index = default_index; p->set_tc_index = nla_get_flag(tb[TCA_DSMARK_SET_TC_INDEX]); @@ -410,7 +412,8 @@ static void dsmark_destroy(struct Qdisc *sch) tcf_destroy_chain(&p->filter_list); qdisc_destroy(p->q); - kfree(p->mask); + if (p->mv != p->embedded) + kfree(p->mv); } static int dsmark_dump_class(struct Qdisc *sch, unsigned long cl, @@ -430,8 +433,8 @@ static int dsmark_dump_class(struct Qdisc *sch, unsigned long cl, opts = nla_nest_start(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; - if (nla_put_u8(skb, TCA_DSMARK_MASK, p->mask[cl - 1]) || - nla_put_u8(skb, TCA_DSMARK_VALUE, p->value[cl - 1])) + if (nla_put_u8(skb, TCA_DSMARK_MASK, p->mv[cl - 1].mask) || + nla_put_u8(skb, TCA_DSMARK_VALUE, p->mv[cl - 1].value)) goto nla_put_failure; return nla_nest_end(skb, opts); diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index fda38f830a10..fe82fab1d55c 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -1,6 +1,6 @@ /* * net/switchdev/switchdev.c - Switch device API - * Copyright (c) 2014 Jiri Pirko <jiri@resnulli.us> + * Copyright (c) 2014-2015 Jiri Pirko <jiri@resnulli.us> * Copyright (c) 2014-2015 Scott Feldman <sfeldma@gmail.com> * * This program is free software; you can redistribute it and/or modify @@ -16,10 +16,83 @@ #include <linux/notifier.h> #include <linux/netdevice.h> #include <linux/if_bridge.h> +#include <linux/list.h> #include <net/ip_fib.h> #include <net/switchdev.h> /** + * switchdev_trans_item_enqueue - Enqueue data item to transaction queue + * + * @trans: transaction + * @data: pointer to data being queued + * @destructor: data destructor + * @tritem: transaction item being queued + * + * Enqeueue data item to transaction queue. tritem is typically placed in + * cointainter pointed at by data pointer. Destructor is called on + * transaction abort and after successful commit phase in case + * the caller did not dequeue the item before. + */ +void switchdev_trans_item_enqueue(struct switchdev_trans *trans, + void *data, void (*destructor)(void const *), + struct switchdev_trans_item *tritem) +{ + tritem->data = data; + tritem->destructor = destructor; + list_add_tail(&tritem->list, &trans->item_list); +} +EXPORT_SYMBOL_GPL(switchdev_trans_item_enqueue); + +static struct switchdev_trans_item * +__switchdev_trans_item_dequeue(struct switchdev_trans *trans) +{ + struct switchdev_trans_item *tritem; + + if (list_empty(&trans->item_list)) + return NULL; + tritem = list_first_entry(&trans->item_list, + struct switchdev_trans_item, list); + list_del(&tritem->list); + return tritem; +} + +/** + * switchdev_trans_item_dequeue - Dequeue data item from transaction queue + * + * @trans: transaction + */ +void *switchdev_trans_item_dequeue(struct switchdev_trans *trans) +{ + struct switchdev_trans_item *tritem; + + tritem = __switchdev_trans_item_dequeue(trans); + BUG_ON(!tritem); + return tritem->data; +} +EXPORT_SYMBOL_GPL(switchdev_trans_item_dequeue); + +static void switchdev_trans_init(struct switchdev_trans *trans) +{ + INIT_LIST_HEAD(&trans->item_list); +} + +static void switchdev_trans_items_destroy(struct switchdev_trans *trans) +{ + struct switchdev_trans_item *tritem; + + while ((tritem = __switchdev_trans_item_dequeue(trans))) + tritem->destructor(tritem->data); +} + +static void switchdev_trans_items_warn_destroy(struct net_device *dev, + struct switchdev_trans *trans) +{ + WARN(!list_empty(&trans->item_list), "%s: transaction item queue is not empty.\n", + dev->name); + switchdev_trans_items_destroy(trans); +} + +/** * switchdev_port_attr_get - Get port attribute * * @dev: port device @@ -62,7 +135,8 @@ int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr) EXPORT_SYMBOL_GPL(switchdev_port_attr_get); static int __switchdev_port_attr_set(struct net_device *dev, - struct switchdev_attr *attr) + struct switchdev_attr *attr, + struct switchdev_trans *trans) { const struct switchdev_ops *ops = dev->switchdev_ops; struct net_device *lower_dev; @@ -70,7 +144,7 @@ static int __switchdev_port_attr_set(struct net_device *dev, int err = -EOPNOTSUPP; if (ops && ops->switchdev_port_attr_set) - return ops->switchdev_port_attr_set(dev, attr); + return ops->switchdev_port_attr_set(dev, attr, trans); if (attr->flags & SWITCHDEV_F_NO_RECURSE) return err; @@ -81,7 +155,7 @@ static int __switchdev_port_attr_set(struct net_device *dev, */ netdev_for_each_lower_dev(dev, lower_dev, iter) { - err = __switchdev_port_attr_set(lower_dev, attr); + err = __switchdev_port_attr_set(lower_dev, attr, trans); if (err) break; } @@ -144,6 +218,7 @@ static int switchdev_port_attr_set_defer(struct net_device *dev, */ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr) { + struct switchdev_trans trans; int err; if (!rtnl_is_locked()) { @@ -156,6 +231,8 @@ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr) return switchdev_port_attr_set_defer(dev, attr); } + switchdev_trans_init(&trans); + /* Phase I: prepare for attr set. Driver/device should fail * here if there are going to be issues in the commit phase, * such as lack of resources or support. The driver/device @@ -163,18 +240,16 @@ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr) * but should not commit the attr. */ - attr->trans = SWITCHDEV_TRANS_PREPARE; - err = __switchdev_port_attr_set(dev, attr); + trans.ph_prepare = true; + err = __switchdev_port_attr_set(dev, attr, &trans); if (err) { /* Prepare phase failed: abort the transaction. Any * resources reserved in the prepare phase are * released. */ - if (err != -EOPNOTSUPP) { - attr->trans = SWITCHDEV_TRANS_ABORT; - __switchdev_port_attr_set(dev, attr); - } + if (err != -EOPNOTSUPP) + switchdev_trans_items_destroy(&trans); return err; } @@ -184,17 +259,19 @@ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr) * because the driver said everythings was OK in phase I. */ - attr->trans = SWITCHDEV_TRANS_COMMIT; - err = __switchdev_port_attr_set(dev, attr); + trans.ph_prepare = false; + err = __switchdev_port_attr_set(dev, attr, &trans); WARN(err, "%s: Commit of attribute (id=%d) failed.\n", dev->name, attr->id); + switchdev_trans_items_warn_destroy(dev, &trans); return err; } EXPORT_SYMBOL_GPL(switchdev_port_attr_set); static int __switchdev_port_obj_add(struct net_device *dev, - struct switchdev_obj *obj) + enum switchdev_obj_id id, const void *obj, + struct switchdev_trans *trans) { const struct switchdev_ops *ops = dev->switchdev_ops; struct net_device *lower_dev; @@ -202,7 +279,7 @@ static int __switchdev_port_obj_add(struct net_device *dev, int err = -EOPNOTSUPP; if (ops && ops->switchdev_port_obj_add) - return ops->switchdev_port_obj_add(dev, obj); + return ops->switchdev_port_obj_add(dev, id, obj, trans); /* Switch device port(s) may be stacked under * bond/team/vlan dev, so recurse down to add object on @@ -210,7 +287,7 @@ static int __switchdev_port_obj_add(struct net_device *dev, */ netdev_for_each_lower_dev(dev, lower_dev, iter) { - err = __switchdev_port_obj_add(lower_dev, obj); + err = __switchdev_port_obj_add(lower_dev, id, obj, trans); if (err) break; } @@ -222,6 +299,7 @@ static int __switchdev_port_obj_add(struct net_device *dev, * switchdev_port_obj_add - Add port object * * @dev: port device + * @id: object ID * @obj: object to add * * Use a 2-phase prepare-commit transaction model to ensure @@ -230,12 +308,16 @@ static int __switchdev_port_obj_add(struct net_device *dev, * * rtnl_lock must be held. */ -int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj) +int switchdev_port_obj_add(struct net_device *dev, enum switchdev_obj_id id, + const void *obj) { + struct switchdev_trans trans; int err; ASSERT_RTNL(); + switchdev_trans_init(&trans); + /* Phase I: prepare for obj add. Driver/device should fail * here if there are going to be issues in the commit phase, * such as lack of resources or support. The driver/device @@ -243,18 +325,16 @@ int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj) * but should not commit the obj. */ - obj->trans = SWITCHDEV_TRANS_PREPARE; - err = __switchdev_port_obj_add(dev, obj); + trans.ph_prepare = true; + err = __switchdev_port_obj_add(dev, id, obj, &trans); if (err) { /* Prepare phase failed: abort the transaction. Any * resources reserved in the prepare phase are * released. */ - if (err != -EOPNOTSUPP) { - obj->trans = SWITCHDEV_TRANS_ABORT; - __switchdev_port_obj_add(dev, obj); - } + if (err != -EOPNOTSUPP) + switchdev_trans_items_destroy(&trans); return err; } @@ -264,9 +344,10 @@ int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj) * because the driver said everythings was OK in phase I. */ - obj->trans = SWITCHDEV_TRANS_COMMIT; - err = __switchdev_port_obj_add(dev, obj); - WARN(err, "%s: Commit of object (id=%d) failed.\n", dev->name, obj->id); + trans.ph_prepare = false; + err = __switchdev_port_obj_add(dev, id, obj, &trans); + WARN(err, "%s: Commit of object (id=%d) failed.\n", dev->name, id); + switchdev_trans_items_warn_destroy(dev, &trans); return err; } @@ -276,9 +357,11 @@ EXPORT_SYMBOL_GPL(switchdev_port_obj_add); * switchdev_port_obj_del - Delete port object * * @dev: port device + * @id: object ID * @obj: object to delete */ -int switchdev_port_obj_del(struct net_device *dev, struct switchdev_obj *obj) +int switchdev_port_obj_del(struct net_device *dev, enum switchdev_obj_id id, + const void *obj) { const struct switchdev_ops *ops = dev->switchdev_ops; struct net_device *lower_dev; @@ -286,7 +369,7 @@ int switchdev_port_obj_del(struct net_device *dev, struct switchdev_obj *obj) int err = -EOPNOTSUPP; if (ops && ops->switchdev_port_obj_del) - return ops->switchdev_port_obj_del(dev, obj); + return ops->switchdev_port_obj_del(dev, id, obj); /* Switch device port(s) may be stacked under * bond/team/vlan dev, so recurse down to delete object on @@ -294,7 +377,7 @@ int switchdev_port_obj_del(struct net_device *dev, struct switchdev_obj *obj) */ netdev_for_each_lower_dev(dev, lower_dev, iter) { - err = switchdev_port_obj_del(lower_dev, obj); + err = switchdev_port_obj_del(lower_dev, id, obj); if (err) break; } @@ -307,9 +390,12 @@ EXPORT_SYMBOL_GPL(switchdev_port_obj_del); * switchdev_port_obj_dump - Dump port objects * * @dev: port device + * @id: object ID * @obj: object to dump + * @cb: function to call with a filled object */ -int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj) +int switchdev_port_obj_dump(struct net_device *dev, enum switchdev_obj_id id, + void *obj, int (*cb)(void *obj)) { const struct switchdev_ops *ops = dev->switchdev_ops; struct net_device *lower_dev; @@ -317,7 +403,7 @@ int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj) int err = -EOPNOTSUPP; if (ops && ops->switchdev_port_obj_dump) - return ops->switchdev_port_obj_dump(dev, obj); + return ops->switchdev_port_obj_dump(dev, id, obj, cb); /* Switch device port(s) may be stacked under * bond/team/vlan dev, so recurse down to dump objects on @@ -325,7 +411,7 @@ int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj) */ netdev_for_each_lower_dev(dev, lower_dev, iter) { - err = switchdev_port_obj_dump(lower_dev, obj); + err = switchdev_port_obj_dump(lower_dev, id, obj, cb); break; } @@ -397,7 +483,7 @@ int call_switchdev_notifiers(unsigned long val, struct net_device *dev, EXPORT_SYMBOL_GPL(call_switchdev_notifiers); struct switchdev_vlan_dump { - struct switchdev_obj obj; + struct switchdev_obj_vlan vlan; struct sk_buff *skb; u32 filter_mask; u16 flags; @@ -405,8 +491,7 @@ struct switchdev_vlan_dump { u16 end; }; -static int switchdev_port_vlan_dump_put(struct net_device *dev, - struct switchdev_vlan_dump *dump) +static int switchdev_port_vlan_dump_put(struct switchdev_vlan_dump *dump) { struct bridge_vlan_info vinfo; @@ -436,12 +521,11 @@ static int switchdev_port_vlan_dump_put(struct net_device *dev, return 0; } -static int switchdev_port_vlan_dump_cb(struct net_device *dev, - struct switchdev_obj *obj) +static int switchdev_port_vlan_dump_cb(void *obj) { + struct switchdev_obj_vlan *vlan = obj; struct switchdev_vlan_dump *dump = - container_of(obj, struct switchdev_vlan_dump, obj); - struct switchdev_obj_vlan *vlan = &dump->obj.u.vlan; + container_of(vlan, struct switchdev_vlan_dump, vlan); int err = 0; if (vlan->vid_begin > vlan->vid_end) @@ -452,7 +536,7 @@ static int switchdev_port_vlan_dump_cb(struct net_device *dev, for (dump->begin = dump->end = vlan->vid_begin; dump->begin <= vlan->vid_end; dump->begin++, dump->end++) { - err = switchdev_port_vlan_dump_put(dev, dump); + err = switchdev_port_vlan_dump_put(dump); if (err) return err; } @@ -464,7 +548,7 @@ static int switchdev_port_vlan_dump_cb(struct net_device *dev, /* prepend */ dump->begin = vlan->vid_begin; } else { - err = switchdev_port_vlan_dump_put(dev, dump); + err = switchdev_port_vlan_dump_put(dump); dump->flags = vlan->flags; dump->begin = vlan->vid_begin; dump->end = vlan->vid_end; @@ -476,7 +560,7 @@ static int switchdev_port_vlan_dump_cb(struct net_device *dev, /* append */ dump->end = vlan->vid_end; } else { - err = switchdev_port_vlan_dump_put(dev, dump); + err = switchdev_port_vlan_dump_put(dump); dump->flags = vlan->flags; dump->begin = vlan->vid_begin; dump->end = vlan->vid_end; @@ -493,10 +577,6 @@ static int switchdev_port_vlan_fill(struct sk_buff *skb, struct net_device *dev, u32 filter_mask) { struct switchdev_vlan_dump dump = { - .obj = { - .id = SWITCHDEV_OBJ_PORT_VLAN, - .cb = switchdev_port_vlan_dump_cb, - }, .skb = skb, .filter_mask = filter_mask, }; @@ -504,12 +584,14 @@ static int switchdev_port_vlan_fill(struct sk_buff *skb, struct net_device *dev, if ((filter_mask & RTEXT_FILTER_BRVLAN) || (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) { - err = switchdev_port_obj_dump(dev, &dump.obj); + err = switchdev_port_obj_dump(dev, SWITCHDEV_OBJ_PORT_VLAN, + &dump.vlan, + switchdev_port_vlan_dump_cb); if (err) goto err_out; if (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED) /* last one */ - err = switchdev_port_vlan_dump_put(dev, &dump); + err = switchdev_port_vlan_dump_put(&dump); } err_out: @@ -617,14 +699,12 @@ static int switchdev_port_br_setlink_protinfo(struct net_device *dev, static int switchdev_port_br_afspec(struct net_device *dev, struct nlattr *afspec, int (*f)(struct net_device *dev, - struct switchdev_obj *obj)) + enum switchdev_obj_id id, + const void *obj)) { struct nlattr *attr; struct bridge_vlan_info *vinfo; - struct switchdev_obj obj = { - .id = SWITCHDEV_OBJ_PORT_VLAN, - }; - struct switchdev_obj_vlan *vlan = &obj.u.vlan; + struct switchdev_obj_vlan vlan = { 0 }; int rem; int err; @@ -634,30 +714,30 @@ static int switchdev_port_br_afspec(struct net_device *dev, if (nla_len(attr) != sizeof(struct bridge_vlan_info)) return -EINVAL; vinfo = nla_data(attr); - vlan->flags = vinfo->flags; + vlan.flags = vinfo->flags; if (vinfo->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) { - if (vlan->vid_begin) + if (vlan.vid_begin) return -EINVAL; - vlan->vid_begin = vinfo->vid; + vlan.vid_begin = vinfo->vid; } else if (vinfo->flags & BRIDGE_VLAN_INFO_RANGE_END) { - if (!vlan->vid_begin) + if (!vlan.vid_begin) return -EINVAL; - vlan->vid_end = vinfo->vid; - if (vlan->vid_end <= vlan->vid_begin) + vlan.vid_end = vinfo->vid; + if (vlan.vid_end <= vlan.vid_begin) return -EINVAL; - err = f(dev, &obj); + err = f(dev, SWITCHDEV_OBJ_PORT_VLAN, &vlan); if (err) return err; - memset(vlan, 0, sizeof(*vlan)); + memset(&vlan, 0, sizeof(vlan)); } else { - if (vlan->vid_begin) + if (vlan.vid_begin) return -EINVAL; - vlan->vid_begin = vinfo->vid; - vlan->vid_end = vinfo->vid; - err = f(dev, &obj); + vlan.vid_begin = vinfo->vid; + vlan.vid_end = vinfo->vid; + err = f(dev, SWITCHDEV_OBJ_PORT_VLAN, &vlan); if (err) return err; - memset(vlan, 0, sizeof(*vlan)); + memset(&vlan, 0, sizeof(vlan)); } } @@ -739,15 +819,12 @@ int switchdev_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, u16 nlm_flags) { - struct switchdev_obj obj = { - .id = SWITCHDEV_OBJ_PORT_FDB, - .u.fdb = { - .addr = addr, - .vid = vid, - }, + struct switchdev_obj_fdb fdb = { + .addr = addr, + .vid = vid, }; - return switchdev_port_obj_add(dev, &obj); + return switchdev_port_obj_add(dev, SWITCHDEV_OBJ_PORT_FDB, &fdb); } EXPORT_SYMBOL_GPL(switchdev_port_fdb_add); @@ -766,30 +843,28 @@ int switchdev_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid) { - struct switchdev_obj obj = { - .id = SWITCHDEV_OBJ_PORT_FDB, - .u.fdb = { - .addr = addr, - .vid = vid, - }, + struct switchdev_obj_fdb fdb = { + .addr = addr, + .vid = vid, }; - return switchdev_port_obj_del(dev, &obj); + return switchdev_port_obj_del(dev, SWITCHDEV_OBJ_PORT_FDB, &fdb); } EXPORT_SYMBOL_GPL(switchdev_port_fdb_del); struct switchdev_fdb_dump { - struct switchdev_obj obj; + struct switchdev_obj_fdb fdb; + struct net_device *dev; struct sk_buff *skb; struct netlink_callback *cb; int idx; }; -static int switchdev_port_fdb_dump_cb(struct net_device *dev, - struct switchdev_obj *obj) +static int switchdev_port_fdb_dump_cb(void *obj) { + struct switchdev_obj_fdb *fdb = obj; struct switchdev_fdb_dump *dump = - container_of(obj, struct switchdev_fdb_dump, obj); + container_of(fdb, struct switchdev_fdb_dump, fdb); u32 portid = NETLINK_CB(dump->cb->skb).portid; u32 seq = dump->cb->nlh->nlmsg_seq; struct nlmsghdr *nlh; @@ -809,13 +884,13 @@ static int switchdev_port_fdb_dump_cb(struct net_device *dev, ndm->ndm_pad2 = 0; ndm->ndm_flags = NTF_SELF; ndm->ndm_type = 0; - ndm->ndm_ifindex = dev->ifindex; - ndm->ndm_state = obj->u.fdb.ndm_state; + ndm->ndm_ifindex = dump->dev->ifindex; + ndm->ndm_state = fdb->ndm_state; - if (nla_put(dump->skb, NDA_LLADDR, ETH_ALEN, obj->u.fdb.addr)) + if (nla_put(dump->skb, NDA_LLADDR, ETH_ALEN, fdb->addr)) goto nla_put_failure; - if (obj->u.fdb.vid && nla_put_u16(dump->skb, NDA_VLAN, obj->u.fdb.vid)) + if (fdb->vid && nla_put_u16(dump->skb, NDA_VLAN, fdb->vid)) goto nla_put_failure; nlmsg_end(dump->skb, nlh); @@ -845,16 +920,14 @@ int switchdev_port_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *filter_dev, int idx) { struct switchdev_fdb_dump dump = { - .obj = { - .id = SWITCHDEV_OBJ_PORT_FDB, - .cb = switchdev_port_fdb_dump_cb, - }, + .dev = dev, .skb = skb, .cb = cb, .idx = idx, }; - switchdev_port_obj_dump(dev, &dump.obj); + switchdev_port_obj_dump(dev, SWITCHDEV_OBJ_PORT_FDB, &dump.fdb, + switchdev_port_fdb_dump_cb); return dump.idx; } EXPORT_SYMBOL_GPL(switchdev_port_fdb_dump); @@ -932,17 +1005,14 @@ static struct net_device *switchdev_get_dev_by_nhs(struct fib_info *fi) int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, u8 tos, u8 type, u32 nlflags, u32 tb_id) { - struct switchdev_obj fib_obj = { - .id = SWITCHDEV_OBJ_IPV4_FIB, - .u.ipv4_fib = { - .dst = dst, - .dst_len = dst_len, - .fi = fi, - .tos = tos, - .type = type, - .nlflags = nlflags, - .tb_id = tb_id, - }, + struct switchdev_obj_ipv4_fib ipv4_fib = { + .dst = dst, + .dst_len = dst_len, + .fi = fi, + .tos = tos, + .type = type, + .nlflags = nlflags, + .tb_id = tb_id, }; struct net_device *dev; int err = 0; @@ -963,7 +1033,7 @@ int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, if (!dev) return 0; - err = switchdev_port_obj_add(dev, &fib_obj); + err = switchdev_port_obj_add(dev, SWITCHDEV_OBJ_IPV4_FIB, &ipv4_fib); if (!err) fi->fib_flags |= RTNH_F_OFFLOAD; @@ -986,17 +1056,14 @@ EXPORT_SYMBOL_GPL(switchdev_fib_ipv4_add); int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, u8 tos, u8 type, u32 tb_id) { - struct switchdev_obj fib_obj = { - .id = SWITCHDEV_OBJ_IPV4_FIB, - .u.ipv4_fib = { - .dst = dst, - .dst_len = dst_len, - .fi = fi, - .tos = tos, - .type = type, - .nlflags = 0, - .tb_id = tb_id, - }, + struct switchdev_obj_ipv4_fib ipv4_fib = { + .dst = dst, + .dst_len = dst_len, + .fi = fi, + .tos = tos, + .type = type, + .nlflags = 0, + .tb_id = tb_id, }; struct net_device *dev; int err = 0; @@ -1008,7 +1075,7 @@ int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, if (!dev) return 0; - err = switchdev_port_obj_del(dev, &fib_obj); + err = switchdev_port_obj_del(dev, SWITCHDEV_OBJ_IPV4_FIB, &ipv4_fib); if (!err) fi->fib_flags &= ~RTNH_F_OFFLOAD; diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 68ada2ca4b60..c48a4b8582bb 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -19,7 +19,7 @@ #include <net/dst.h> #include <net/xfrm.h> -static int xfrm_output2(struct sock *sk, struct sk_buff *skb); +static int xfrm_output2(struct net *net, struct sock *sk, struct sk_buff *skb); static int xfrm_skb_check_space(struct sk_buff *skb) { @@ -131,6 +131,8 @@ out: int xfrm_output_resume(struct sk_buff *skb, int err) { + struct net *net = xs_net(skb_dst(skb)->xfrm); + while (likely((err = xfrm_output_one(skb, err)) == 0)) { nf_reset(skb); @@ -139,10 +141,10 @@ int xfrm_output_resume(struct sk_buff *skb, int err) goto out; if (!skb_dst(skb)->xfrm) - return dst_output(skb); + return dst_output(skb->sk, skb); err = nf_hook(skb_dst(skb)->ops->family, - NF_INET_POST_ROUTING, skb->sk, skb, + NF_INET_POST_ROUTING, net, skb->sk, skb, NULL, skb_dst(skb)->dev, xfrm_output2); if (unlikely(err != 1)) goto out; @@ -156,12 +158,12 @@ out: } EXPORT_SYMBOL_GPL(xfrm_output_resume); -static int xfrm_output2(struct sock *sk, struct sk_buff *skb) +static int xfrm_output2(struct net *net, struct sock *sk, struct sk_buff *skb) { return xfrm_output_resume(skb, 1); } -static int xfrm_output_gso(struct sock *sk, struct sk_buff *skb) +static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb) { struct sk_buff *segs; @@ -177,7 +179,7 @@ static int xfrm_output_gso(struct sock *sk, struct sk_buff *skb) int err; segs->next = NULL; - err = xfrm_output2(sk, segs); + err = xfrm_output2(net, sk, segs); if (unlikely(err)) { kfree_skb_list(nskb); @@ -196,7 +198,7 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb) int err; if (skb_is_gso(skb)) - return xfrm_output_gso(sk, skb); + return xfrm_output_gso(net, sk, skb); if (skb->ip_summed == CHECKSUM_PARTIAL) { err = skb_checksum_help(skb); @@ -207,7 +209,7 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb) } } - return xfrm_output2(sk, skb); + return xfrm_output2(net, sk, skb); } EXPORT_SYMBOL_GPL(xfrm_output); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 94af3d065785..418daa038edf 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1208,7 +1208,7 @@ static inline int policy_to_flow_dir(int dir) } } -static struct xfrm_policy *xfrm_sk_policy_lookup(struct sock *sk, int dir, +static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, const struct flowi *fl) { struct xfrm_policy *pol; @@ -1583,8 +1583,6 @@ static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family) memset(dst + 1, 0, sizeof(*xdst) - sizeof(*dst)); xdst->flo.ops = &xfrm_bundle_fc_ops; - if (afinfo->init_dst) - afinfo->init_dst(net, xdst); } else xdst = ERR_PTR(-ENOBUFS); @@ -1947,7 +1945,7 @@ static void xfrm_policy_queue_process(unsigned long arg) skb_dst_drop(skb); skb_dst_set(skb, dst); - dst_output(skb); + dst_output(skb->sk, skb); } out: @@ -2187,7 +2185,7 @@ static struct dst_entry *make_blackhole(struct net *net, u16 family, */ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, - struct sock *sk, int flags) + const struct sock *sk, int flags) { struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; struct flow_cache_object *flo; @@ -2335,7 +2333,7 @@ EXPORT_SYMBOL(xfrm_lookup); */ struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, - struct sock *sk, int flags) + const struct sock *sk, int flags) { struct dst_entry *dst = xfrm_lookup(net, dst_orig, fl, sk, flags | XFRM_LOOKUP_QUEUE | diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h index 3a44d3a272af..21aa1b44c30c 100644 --- a/samples/bpf/bpf_helpers.h +++ b/samples/bpf/bpf_helpers.h @@ -33,6 +33,10 @@ static int (*bpf_get_current_comm)(void *buf, int buf_size) = (void *) BPF_FUNC_get_current_comm; static int (*bpf_perf_event_read)(void *map, int index) = (void *) BPF_FUNC_perf_event_read; +static int (*bpf_clone_redirect)(void *ctx, int ifindex, int flags) = + (void *) BPF_FUNC_clone_redirect; +static int (*bpf_redirect)(int ifindex, int flags) = + (void *) BPF_FUNC_redirect; /* llvm builtin functions that eBPF C program may use to * emit BPF_LD_ABS and BPF_LD_IND instructions diff --git a/samples/bpf/tcbpf1_kern.c b/samples/bpf/tcbpf1_kern.c index 9bfb2eb34563..fa051b3d53ee 100644 --- a/samples/bpf/tcbpf1_kern.c +++ b/samples/bpf/tcbpf1_kern.c @@ -5,7 +5,7 @@ #include <uapi/linux/in.h> #include <uapi/linux/tcp.h> #include <uapi/linux/filter.h> - +#include <uapi/linux/pkt_cls.h> #include "bpf_helpers.h" /* compiler workaround */ @@ -64,4 +64,26 @@ int bpf_prog1(struct __sk_buff *skb) return 0; } +SEC("redirect_xmit") +int _redirect_xmit(struct __sk_buff *skb) +{ + return bpf_redirect(skb->ifindex + 1, 0); +} +SEC("redirect_recv") +int _redirect_recv(struct __sk_buff *skb) +{ + return bpf_redirect(skb->ifindex + 1, 1); +} +SEC("clone_redirect_xmit") +int _clone_redirect_xmit(struct __sk_buff *skb) +{ + bpf_clone_redirect(skb, skb->ifindex + 1, 0); + return TC_ACT_SHOT; +} +SEC("clone_redirect_recv") +int _clone_redirect_recv(struct __sk_buff *skb) +{ + bpf_clone_redirect(skb, skb->ifindex + 1, 1); + return TC_ACT_SHOT; +} char _license[] SEC("license") = "GPL"; diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index e4369d86e588..64340160f4ac 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -4866,7 +4866,7 @@ static unsigned int selinux_ip_forward(struct sk_buff *skb, return NF_ACCEPT; } -static unsigned int selinux_ipv4_forward(const struct nf_hook_ops *ops, +static unsigned int selinux_ipv4_forward(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -4874,7 +4874,7 @@ static unsigned int selinux_ipv4_forward(const struct nf_hook_ops *ops, } #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) -static unsigned int selinux_ipv6_forward(const struct nf_hook_ops *ops, +static unsigned int selinux_ipv6_forward(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -4924,7 +4924,7 @@ static unsigned int selinux_ip_output(struct sk_buff *skb, return NF_ACCEPT; } -static unsigned int selinux_ipv4_output(const struct nf_hook_ops *ops, +static unsigned int selinux_ipv4_output(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -5099,7 +5099,7 @@ static unsigned int selinux_ip_postroute(struct sk_buff *skb, return NF_ACCEPT; } -static unsigned int selinux_ipv4_postroute(const struct nf_hook_ops *ops, +static unsigned int selinux_ipv4_postroute(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -5107,7 +5107,7 @@ static unsigned int selinux_ipv4_postroute(const struct nf_hook_ops *ops, } #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) -static unsigned int selinux_ipv6_postroute(const struct nf_hook_ops *ops, +static unsigned int selinux_ipv6_postroute(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { diff --git a/security/smack/smack_netfilter.c b/security/smack/smack_netfilter.c index a455cfc9ec1f..a9e41da05d28 100644 --- a/security/smack/smack_netfilter.c +++ b/security/smack/smack_netfilter.c @@ -21,7 +21,7 @@ #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) -static unsigned int smack_ipv6_output(const struct nf_hook_ops *ops, +static unsigned int smack_ipv6_output(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { @@ -38,7 +38,7 @@ static unsigned int smack_ipv6_output(const struct nf_hook_ops *ops, } #endif /* IPV6 */ -static unsigned int smack_ipv4_output(const struct nf_hook_ops *ops, +static unsigned int smack_ipv4_output(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { diff --git a/tools/net/bpf_jit_disasm.c b/tools/net/bpf_jit_disasm.c index 2cd3d4c99738..5b3241340945 100644 --- a/tools/net/bpf_jit_disasm.c +++ b/tools/net/bpf_jit_disasm.c @@ -156,8 +156,8 @@ static void put_log_buff(char *buff) free(buff); } -static int get_last_jit_image(char *haystack, size_t hlen, - uint8_t *image, size_t ilen) +static unsigned int get_last_jit_image(char *haystack, size_t hlen, + uint8_t *image, size_t ilen) { char *ptr, *pptr, *tmp; off_t off = 0; |