diff options
1300 files changed, 33358 insertions, 21321 deletions
diff --git a/Documentation/ABI/stable/sysfs-bus-xen-backend b/Documentation/ABI/stable/sysfs-bus-xen-backend index 3d5951c8bf5f..e8b60bd766f7 100644 --- a/Documentation/ABI/stable/sysfs-bus-xen-backend +++ b/Documentation/ABI/stable/sysfs-bus-xen-backend @@ -73,3 +73,12 @@ KernelVersion: 3.0 Contact: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Description: Number of sectors written by the frontend. + +What: /sys/bus/xen-backend/devices/*/state +Date: August 2018 +KernelVersion: 4.19 +Contact: Joe Jin <joe.jin@oracle.com> +Description: + The state of the device. One of: 'Unknown', + 'Initialising', 'Initialised', 'Connected', 'Closing', + 'Closed', 'Reconfiguring', 'Reconfigured'. diff --git a/Documentation/ABI/stable/sysfs-devices-system-xen_memory b/Documentation/ABI/stable/sysfs-devices-system-xen_memory index caa311d59ac1..6d83f95a8a8e 100644 --- a/Documentation/ABI/stable/sysfs-devices-system-xen_memory +++ b/Documentation/ABI/stable/sysfs-devices-system-xen_memory @@ -75,3 +75,12 @@ Contact: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Description: Amount (in KiB) of low (or normal) memory in the balloon. + +What: /sys/devices/system/xen_memory/xen_memory0/scrub_pages +Date: September 2018 +KernelVersion: 4.20 +Contact: xen-devel@lists.xenproject.org +Description: + Control scrubbing pages before returning them to Xen for others domains + use. Can be set with xen_scrub_pages cmdline + parameter. Default value controlled with CONFIG_XEN_SCRUB_PAGES_DEFAULT. diff --git a/Documentation/ABI/testing/sysfs-class-net b/Documentation/ABI/testing/sysfs-class-net index 2f1788111cd9..e2e0fe553ad8 100644 --- a/Documentation/ABI/testing/sysfs-class-net +++ b/Documentation/ABI/testing/sysfs-class-net @@ -117,7 +117,7 @@ Description: full: full duplex Note: This attribute is only valid for interfaces that implement - the ethtool get_settings method (mostly Ethernet). + the ethtool get_link_ksettings method (mostly Ethernet). What: /sys/class/net/<iface>/flags Date: April 2005 @@ -224,7 +224,7 @@ Description: an integer representing the link speed in Mbits/sec. Note: this attribute is only valid for interfaces that implement - the ethtool get_settings method (mostly Ethernet ). + the ethtool get_link_ksettings method (mostly Ethernet). What: /sys/class/net/<iface>/tx_queue_len Date: April 2005 diff --git a/Documentation/ABI/testing/sysfs-class-net-dsa b/Documentation/ABI/testing/sysfs-class-net-dsa new file mode 100644 index 000000000000..f240221e071e --- /dev/null +++ b/Documentation/ABI/testing/sysfs-class-net-dsa @@ -0,0 +1,7 @@ +What: /sys/class/net/<iface>/tagging +Date: August 2018 +KernelVersion: 4.20 +Contact: netdev@vger.kernel.org +Description: + String indicating the type of tagging protocol used by the + DSA slave network device. diff --git a/Documentation/ABI/testing/sysfs-driver-xen-blkback b/Documentation/ABI/testing/sysfs-driver-xen-blkback index 8bb43b66eb55..4e7babb3ba1f 100644 --- a/Documentation/ABI/testing/sysfs-driver-xen-blkback +++ b/Documentation/ABI/testing/sysfs-driver-xen-blkback @@ -15,3 +15,13 @@ Description: blkback. If the frontend tries to use more than max_persistent_grants, the LRU kicks in and starts removing 5% of max_persistent_grants every 100ms. + +What: /sys/module/xen_blkback/parameters/persistent_grant_unused_seconds +Date: August 2018 +KernelVersion: 4.19 +Contact: Roger Pau Monné <roger.pau@citrix.com> +Description: + How long a persistent grant is allowed to remain + allocated without being in use. The time is in + seconds, 0 means indefinitely long. + The default is 60 seconds. diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 9871e649ffef..92eb1f42240d 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3523,6 +3523,12 @@ ramdisk_size= [RAM] Sizes of RAM disks in kilobytes See Documentation/blockdev/ramdisk.txt. + random.trust_cpu={on,off} + [KNL] Enable or disable trusting the use of the + CPU's random number generator (if available) to + fully seed the kernel's CRNG. Default is controlled + by CONFIG_RANDOM_TRUST_CPU. + ras=option[,option,...] [KNL] RAS-specific options cec_disable [X86] @@ -4994,6 +5000,12 @@ Disables the PV optimizations forcing the HVM guest to run as generic HVM guest with no PV drivers. + xen_scrub_pages= [XEN] + Boolean option to control scrubbing pages before giving them back + to Xen, for use by other domains. Can be also changed at runtime + with /sys/devices/system/xen_memory/xen_memory0/scrub_pages. + Default value controlled with CONFIG_XEN_SCRUB_PAGES_DEFAULT. + xirc2ps_cs= [NET,PCMCIA] Format: <irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]] diff --git a/Documentation/arm64/sve.txt b/Documentation/arm64/sve.txt index f128f736b4a5..7169a0ec41d8 100644 --- a/Documentation/arm64/sve.txt +++ b/Documentation/arm64/sve.txt @@ -200,7 +200,7 @@ prctl(PR_SVE_SET_VL, unsigned long arg) thread. * Changing the vector length causes all of P0..P15, FFR and all bits of - Z0..V31 except for Z0 bits [127:0] .. Z31 bits [127:0] to become + Z0..Z31 except for Z0 bits [127:0] .. Z31 bits [127:0] to become unspecified. Calling PR_SVE_SET_VL with vl equal to the thread's current vector length, or calling PR_SVE_SET_VL with the PR_SVE_SET_VL_ONEXEC flag, does not constitute a change to the vector length for this purpose. @@ -500,7 +500,7 @@ References [2] arch/arm64/include/uapi/asm/ptrace.h AArch64 Linux ptrace ABI definitions -[3] linux/Documentation/arm64/cpu-feature-registers.txt +[3] Documentation/arm64/cpu-feature-registers.txt [4] ARM IHI0055C http://infocenter.arm.com/help/topic/com.arm.doc.ihi0055c/IHI0055C_beta_aapcs64.pdf diff --git a/Documentation/device-mapper/dm-raid.txt b/Documentation/device-mapper/dm-raid.txt index 390c145f01d7..52a719b49afd 100644 --- a/Documentation/device-mapper/dm-raid.txt +++ b/Documentation/device-mapper/dm-raid.txt @@ -348,3 +348,7 @@ Version History 1.13.1 Fix deadlock caused by early md_stop_writes(). Also fix size an state races. 1.13.2 Fix raid redundancy validation and avoid keeping raid set frozen +1.14.0 Fix reshape race on small devices. Fix stripe adding reshape + deadlock/potential data corruption. Update superblock when + specific devices are requested via rebuild. Fix RAID leg + rebuild errors. diff --git a/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.txt b/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.txt index 00e4365d7206..091c8dfd3229 100644 --- a/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.txt +++ b/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.txt @@ -3,7 +3,6 @@ Required properties: - compatible : - "fsl,imx7ulp-lpi2c" for LPI2C compatible with the one integrated on i.MX7ULP soc - - "fsl,imx8dv-lpi2c" for LPI2C compatible with the one integrated on i.MX8DV soc - reg : address and length of the lpi2c master registers - interrupts : lpi2c interrupt - clocks : lpi2c clock specifier @@ -11,7 +10,7 @@ Required properties: Examples: lpi2c7: lpi2c7@40a50000 { - compatible = "fsl,imx8dv-lpi2c"; + compatible = "fsl,imx7ulp-lpi2c"; reg = <0x40A50000 0x10000>; interrupt-parent = <&intc>; interrupts = <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>; diff --git a/Documentation/devicetree/bindings/interrupt-controller/riscv,cpu-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/riscv,cpu-intc.txt index b0a8af51c388..265b223cd978 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/riscv,cpu-intc.txt +++ b/Documentation/devicetree/bindings/interrupt-controller/riscv,cpu-intc.txt @@ -11,7 +11,7 @@ The RISC-V supervisor ISA manual specifies three interrupt sources that are attached to every HLIC: software interrupts, the timer interrupt, and external interrupts. Software interrupts are used to send IPIs between cores. The timer interrupt comes from an architecturally mandated real-time timer that is -controller via Supervisor Binary Interface (SBI) calls and CSR reads. External +controlled via Supervisor Binary Interface (SBI) calls and CSR reads. External interrupts connect all other device interrupts to the HLIC, which are routed via the platform-level interrupt controller (PLIC). @@ -25,7 +25,15 @@ in the system. Required properties: - compatible : "riscv,cpu-intc" -- #interrupt-cells : should be <1> +- #interrupt-cells : should be <1>. The interrupt sources are defined by the + RISC-V supervisor ISA manual, with only the following three interrupts being + defined for supervisor mode: + - Source 1 is the supervisor software interrupt, which can be sent by an SBI + call and is reserved for use by software. + - Source 5 is the supervisor timer interrupt, which can be configured by + SBI calls and implements a one-shot timer. + - Source 9 is the supervisor external interrupt, which chains to all other + device interrupts. - interrupt-controller : Identifies the node as an interrupt controller Furthermore, this interrupt-controller MUST be embedded inside the cpu @@ -38,7 +46,7 @@ An example device tree entry for a HLIC is show below. ... cpu1-intc: interrupt-controller { #interrupt-cells = <1>; - compatible = "riscv,cpu-intc", "sifive,fu540-c000-cpu-intc"; + compatible = "sifive,fu540-c000-cpu-intc", "riscv,cpu-intc"; interrupt-controller; }; }; diff --git a/Documentation/devicetree/bindings/net/cpsw.txt b/Documentation/devicetree/bindings/net/cpsw.txt index 41089369f891..b3acebe08eb0 100644 --- a/Documentation/devicetree/bindings/net/cpsw.txt +++ b/Documentation/devicetree/bindings/net/cpsw.txt @@ -19,6 +19,10 @@ Required properties: - slaves : Specifies number for slaves - active_slave : Specifies the slave to use for time stamping, ethtool and SIOCGMIIPHY +- cpsw-phy-sel : Specifies the phandle to the CPSW phy mode selection + device. See also cpsw-phy-sel.txt for it's binding. + Note that in legacy cases cpsw-phy-sel may be + a child device instead of a phandle. Optional properties: - ti,hwmods : Must be "cpgmac0" @@ -75,6 +79,7 @@ Examples: cpts_clock_mult = <0x80000000>; cpts_clock_shift = <29>; syscon = <&cm>; + cpsw-phy-sel = <&phy_sel>; cpsw_emac0: slave@0 { phy_id = <&davinci_mdio>, <0>; phy-mode = "rgmii-txid"; @@ -103,6 +108,7 @@ Examples: cpts_clock_mult = <0x80000000>; cpts_clock_shift = <29>; syscon = <&cm>; + cpsw-phy-sel = <&phy_sel>; cpsw_emac0: slave@0 { phy_id = <&davinci_mdio>, <0>; phy-mode = "rgmii-txid"; diff --git a/Documentation/devicetree/bindings/net/dsa/lantiq-gswip.txt b/Documentation/devicetree/bindings/net/dsa/lantiq-gswip.txt new file mode 100644 index 000000000000..886cbe8ffb38 --- /dev/null +++ b/Documentation/devicetree/bindings/net/dsa/lantiq-gswip.txt @@ -0,0 +1,143 @@ +Lantiq GSWIP Ethernet switches +================================== + +Required properties for GSWIP core: + +- compatible : "lantiq,xrx200-gswip" for the embedded GSWIP in the + xRX200 SoC +- reg : memory range of the GSWIP core registers + : memory range of the GSWIP MDIO registers + : memory range of the GSWIP MII registers + +See Documentation/devicetree/bindings/net/dsa/dsa.txt for a list of +additional required and optional properties. + + +Required properties for MDIO bus: +- compatible : "lantiq,xrx200-mdio" for the MDIO bus inside the GSWIP + core of the xRX200 SoC and the PHYs connected to it. + +See Documentation/devicetree/bindings/net/mdio.txt for a list of additional +required and optional properties. + + +Required properties for GPHY firmware loading: +- compatible : "lantiq,xrx200-gphy-fw", "lantiq,gphy-fw" + "lantiq,xrx300-gphy-fw", "lantiq,gphy-fw" + "lantiq,xrx330-gphy-fw", "lantiq,gphy-fw" + for the loading of the firmware into the embedded + GPHY core of the SoC. +- lantiq,rcu : reference to the rcu syscon + +The GPHY firmware loader has a list of GPHY entries, one for each +embedded GPHY + +- reg : Offset of the GPHY firmware register in the RCU + register range +- resets : list of resets of the embedded GPHY +- reset-names : list of names of the resets + +Example: + +Ethernet switch on the VRX200 SoC: + +switch@e108000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "lantiq,xrx200-gswip"; + reg = < 0xe108000 0x3100 /* switch */ + 0xe10b100 0xd8 /* mdio */ + 0xe10b1d8 0x130 /* mii */ + >; + dsa,member = <0 0>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + label = "lan3"; + phy-mode = "rgmii"; + phy-handle = <&phy0>; + }; + + port@1 { + reg = <1>; + label = "lan4"; + phy-mode = "rgmii"; + phy-handle = <&phy1>; + }; + + port@2 { + reg = <2>; + label = "lan2"; + phy-mode = "internal"; + phy-handle = <&phy11>; + }; + + port@4 { + reg = <4>; + label = "lan1"; + phy-mode = "internal"; + phy-handle = <&phy13>; + }; + + port@5 { + reg = <5>; + label = "wan"; + phy-mode = "rgmii"; + phy-handle = <&phy5>; + }; + + port@6 { + reg = <0x6>; + label = "cpu"; + ethernet = <ð0>; + }; + }; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + compatible = "lantiq,xrx200-mdio"; + reg = <0>; + + phy0: ethernet-phy@0 { + reg = <0x0>; + }; + phy1: ethernet-phy@1 { + reg = <0x1>; + }; + phy5: ethernet-phy@5 { + reg = <0x5>; + }; + phy11: ethernet-phy@11 { + reg = <0x11>; + }; + phy13: ethernet-phy@13 { + reg = <0x13>; + }; + }; + + gphy-fw { + compatible = "lantiq,xrx200-gphy-fw", "lantiq,gphy-fw"; + lantiq,rcu = <&rcu0>; + #address-cells = <1>; + #size-cells = <0>; + + gphy@20 { + reg = <0x20>; + + resets = <&reset0 31 30>; + reset-names = "gphy"; + }; + + gphy@68 { + reg = <0x68>; + + resets = <&reset0 29 28>; + reset-names = "gphy"; + }; + }; +}; diff --git a/Documentation/devicetree/bindings/net/lantiq,xrx200-net.txt b/Documentation/devicetree/bindings/net/lantiq,xrx200-net.txt new file mode 100644 index 000000000000..5ff5e68bbbb6 --- /dev/null +++ b/Documentation/devicetree/bindings/net/lantiq,xrx200-net.txt @@ -0,0 +1,21 @@ +Lantiq xRX200 GSWIP PMAC Ethernet driver +================================== + +Required properties: + +- compatible : "lantiq,xrx200-net" for the PMAC of the embedded + : GSWIP in the xXR200 +- reg : memory range of the PMAC core inside of the GSWIP core +- interrupts : TX and RX DMA interrupts. Use interrupt-names "tx" for + : the TX interrupt and "rx" for the RX interrupt. + +Example: + +ethernet@e10b308 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "lantiq,xrx200-net"; + reg = <0xe10b308 0xcf8>; + interrupts = <73>, <72>; + interrupt-names = "tx", "rx"; +}; diff --git a/Documentation/devicetree/bindings/net/macb.txt b/Documentation/devicetree/bindings/net/macb.txt index 457d5ae16f23..3e17ac1d5d58 100644 --- a/Documentation/devicetree/bindings/net/macb.txt +++ b/Documentation/devicetree/bindings/net/macb.txt @@ -10,6 +10,7 @@ Required properties: Use "cdns,pc302-gem" for Picochip picoXcell pc302 and later devices based on the Cadence GEM, or the generic form: "cdns,gem". Use "atmel,sama5d2-gem" for the GEM IP (10/100) available on Atmel sama5d2 SoCs. + Use "atmel,sama5d3-macb" for the 10/100Mbit IP available on Atmel sama5d3 SoCs. Use "atmel,sama5d3-gem" for the Gigabit IP available on Atmel sama5d3 SoCs. Use "atmel,sama5d4-gem" for the GEM IP (10/100) available on Atmel sama5d4 SoCs. Use "cdns,zynq-gem" Xilinx Zynq-7xxx SoC. diff --git a/Documentation/devicetree/bindings/net/mscc-phy-vsc8531.txt b/Documentation/devicetree/bindings/net/mscc-phy-vsc8531.txt index 0eedabe22cc3..5ff37c68c941 100644 --- a/Documentation/devicetree/bindings/net/mscc-phy-vsc8531.txt +++ b/Documentation/devicetree/bindings/net/mscc-phy-vsc8531.txt @@ -1,10 +1,5 @@ * Microsemi - vsc8531 Giga bit ethernet phy -Required properties: -- compatible : Should contain phy id as "ethernet-phy-idAAAA.BBBB" - The PHY device uses the binding described in - Documentation/devicetree/bindings/net/phy.txt - Optional properties: - vsc8531,vddmac : The vddmac in mV. Allowed values is listed in the first row of Table 1 (below). @@ -27,14 +22,16 @@ Optional properties: 'vddmac'. Default value is 0%. Ref: Table:1 - Edge rate change (below). -- vsc8531,led-0-mode : LED mode. Specify how the LED[0] should behave. - Allowed values are define in - "include/dt-bindings/net/mscc-phy-vsc8531.h". - Default value is VSC8531_LINK_1000_ACTIVITY (1). -- vsc8531,led-1-mode : LED mode. Specify how the LED[1] should behave. - Allowed values are define in +- vsc8531,led-[N]-mode : LED mode. Specify how the LED[N] should behave. + N depends on the number of LEDs supported by a + PHY. + Allowed values are defined in "include/dt-bindings/net/mscc-phy-vsc8531.h". - Default value is VSC8531_LINK_100_ACTIVITY (2). + Default values are VSC8531_LINK_1000_ACTIVITY (1), + VSC8531_LINK_100_ACTIVITY (2), + VSC8531_LINK_ACTIVITY (0) and + VSC8531_DUPLEX_COLLISION (8). + Table: 1 - Edge rate change ----------------------------------------------------------------| diff --git a/Documentation/devicetree/bindings/net/sh_eth.txt b/Documentation/devicetree/bindings/net/sh_eth.txt index 76db9f13ad96..abc36274227c 100644 --- a/Documentation/devicetree/bindings/net/sh_eth.txt +++ b/Documentation/devicetree/bindings/net/sh_eth.txt @@ -16,6 +16,7 @@ Required properties: "renesas,ether-r8a7794" if the device is a part of R8A7794 SoC. "renesas,gether-r8a77980" if the device is a part of R8A77980 SoC. "renesas,ether-r7s72100" if the device is a part of R7S72100 SoC. + "renesas,ether-r7s9210" if the device is a part of R7S9210 SoC. "renesas,rcar-gen1-ether" for a generic R-Car Gen1 device. "renesas,rcar-gen2-ether" for a generic R-Car Gen2 or RZ/G1 device. diff --git a/Documentation/devicetree/bindings/soc/fsl/cpm_qe/network.txt b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/network.txt index 03c741602c6d..6d2dd8a31482 100644 --- a/Documentation/devicetree/bindings/soc/fsl/cpm_qe/network.txt +++ b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/network.txt @@ -98,6 +98,12 @@ The property below is dependent on fsl,tdm-interface: usage: optional for tdm interface value type: <empty> Definition : Internal loopback connecting on TDM layer. +- fsl,hmask + usage: optional + Value type: <u16> + Definition: HDLC address recognition. Set to zero to disable + address filtering of packets: + fsl,hmask = /bits/ 16 <0x0000>; Example for tdm interface: diff --git a/Documentation/devicetree/bindings/watchdog/renesas-wdt.txt b/Documentation/devicetree/bindings/watchdog/renesas-wdt.txt index 5d47a262474c..9407212a85a8 100644 --- a/Documentation/devicetree/bindings/watchdog/renesas-wdt.txt +++ b/Documentation/devicetree/bindings/watchdog/renesas-wdt.txt @@ -7,6 +7,7 @@ Required properties: Examples with soctypes are: - "renesas,r8a7743-wdt" (RZ/G1M) - "renesas,r8a7745-wdt" (RZ/G1E) + - "renesas,r8a774a1-wdt" (RZ/G2M) - "renesas,r8a7790-wdt" (R-Car H2) - "renesas,r8a7791-wdt" (R-Car M2-W) - "renesas,r8a7792-wdt" (R-Car V2H) @@ -21,8 +22,8 @@ Required properties: - "renesas,r7s72100-wdt" (RZ/A1) The generic compatible string must be: - "renesas,rza-wdt" for RZ/A - - "renesas,rcar-gen2-wdt" for R-Car Gen2 and RZ/G - - "renesas,rcar-gen3-wdt" for R-Car Gen3 + - "renesas,rcar-gen2-wdt" for R-Car Gen2 and RZ/G1 + - "renesas,rcar-gen3-wdt" for R-Car Gen3 and RZ/G2 - reg : Should contain WDT registers location and length - clocks : the clock feeding the watchdog timer. diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index 4b2084d0f1fb..a6c6a8af48a2 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -848,7 +848,7 @@ struct file_operations ---------------------- This describes how the VFS can manipulate an open file. As of kernel -4.1, the following members are defined: +4.18, the following members are defined: struct file_operations { struct module *owner; @@ -858,11 +858,11 @@ struct file_operations { ssize_t (*read_iter) (struct kiocb *, struct iov_iter *); ssize_t (*write_iter) (struct kiocb *, struct iov_iter *); int (*iterate) (struct file *, struct dir_context *); + int (*iterate_shared) (struct file *, struct dir_context *); __poll_t (*poll) (struct file *, struct poll_table_struct *); long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); long (*compat_ioctl) (struct file *, unsigned int, unsigned long); int (*mmap) (struct file *, struct vm_area_struct *); - int (*mremap)(struct file *, struct vm_area_struct *); int (*open) (struct inode *, struct file *); int (*flush) (struct file *, fl_owner_t id); int (*release) (struct inode *, struct file *); @@ -882,6 +882,10 @@ struct file_operations { #ifndef CONFIG_MMU unsigned (*mmap_capabilities)(struct file *); #endif + ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, loff_t, size_t, unsigned int); + int (*clone_file_range)(struct file *, loff_t, struct file *, loff_t, u64); + int (*dedupe_file_range)(struct file *, loff_t, struct file *, loff_t, u64); + int (*fadvise)(struct file *, loff_t, loff_t, int); }; Again, all methods are called without any locks being held, unless @@ -899,6 +903,9 @@ otherwise noted. iterate: called when the VFS needs to read the directory contents + iterate_shared: called when the VFS needs to read the directory contents + when filesystem supports concurrent dir iterators + poll: called by the VFS when a process wants to check if there is activity on this file and (optionally) go to sleep until there is activity. Called by the select(2) and poll(2) system calls @@ -951,6 +958,16 @@ otherwise noted. fallocate: called by the VFS to preallocate blocks or punch a hole. + copy_file_range: called by the copy_file_range(2) system call. + + clone_file_range: called by the ioctl(2) system call for FICLONERANGE and + FICLONE commands. + + dedupe_file_range: called by the ioctl(2) system call for FIDEDUPERANGE + command. + + fadvise: possibly called by the fadvise64() system call. + Note that the file operations are implemented by the specific filesystem in which the inode resides. When opening a device node (character or block special) most filesystems will call special diff --git a/Documentation/hwmon/ina2xx b/Documentation/hwmon/ina2xx index 72d16f08e431..b8df81f6d6bc 100644 --- a/Documentation/hwmon/ina2xx +++ b/Documentation/hwmon/ina2xx @@ -32,7 +32,7 @@ Supported chips: Datasheet: Publicly available at the Texas Instruments website http://www.ti.com/ -Author: Lothar Felten <l-felten@ti.com> +Author: Lothar Felten <lothar.felten@gmail.com> Description ----------- diff --git a/Documentation/i2c/DMA-considerations b/Documentation/i2c/DMA-considerations index 966610aa4620..203002054120 100644 --- a/Documentation/i2c/DMA-considerations +++ b/Documentation/i2c/DMA-considerations @@ -50,10 +50,14 @@ bounce buffer. But you don't need to care about that detail, just use the returned buffer. If NULL is returned, the threshold was not met or a bounce buffer could not be allocated. Fall back to PIO in that case. -In any case, a buffer obtained from above needs to be released. It ensures data -is copied back to the message and a potentially used bounce buffer is freed:: +In any case, a buffer obtained from above needs to be released. Another helper +function ensures a potentially used bounce buffer is freed:: - i2c_release_dma_safe_msg_buf(msg, dma_buf); + i2c_put_dma_safe_msg_buf(dma_buf, msg, xferred); + +The last argument 'xferred' controls if the buffer is synced back to the +message or not. No syncing is needed in cases setting up DMA had an error and +there was no data transferred. The bounce buffer handling from the core is generic and simple. It will always allocate a new bounce buffer. If you want a more sophisticated handling (e.g. diff --git a/Documentation/networking/00-INDEX b/Documentation/networking/00-INDEX index 02a323c43261..f4f2b5d6c8d8 100644 --- a/Documentation/networking/00-INDEX +++ b/Documentation/networking/00-INDEX @@ -94,8 +94,8 @@ gianfar.txt - Gianfar Ethernet Driver. i40e.txt - README for the Intel Ethernet Controller XL710 Driver (i40e). -i40evf.txt - - Short note on the Driver for the Intel(R) XL710 X710 Virtual Function +iavf.txt + - README for the Intel Ethernet Adaptive Virtual Function Driver (iavf). ieee802154.txt - Linux IEEE 802.15.4 implementation, API and drivers igb.txt @@ -198,8 +198,6 @@ tc-actions-env-rules.txt - rules for traffic control (tc) actions. timestamping.txt - overview of network packet timestamping variants. -tcp.txt - - short blurb on how TCP output takes place. tcp-thin.txt - kernel tuning options for low rate 'thin' TCP streams. team.txt diff --git a/drivers/staging/fsl-dpaa2/ethernet/ethernet-driver.rst b/Documentation/networking/dpaa2/ethernet-driver.rst index 90ec940749e8..90ec940749e8 100644 --- a/drivers/staging/fsl-dpaa2/ethernet/ethernet-driver.rst +++ b/Documentation/networking/dpaa2/ethernet-driver.rst diff --git a/Documentation/networking/dpaa2/index.rst b/Documentation/networking/dpaa2/index.rst index 10bea113a7bc..67bd87fe6c53 100644 --- a/Documentation/networking/dpaa2/index.rst +++ b/Documentation/networking/dpaa2/index.rst @@ -7,3 +7,4 @@ DPAA2 Documentation overview dpio-driver + ethernet-driver diff --git a/Documentation/networking/i40evf.txt b/Documentation/networking/iavf.txt index e9b3035b95d0..cc902a2369d6 100644 --- a/Documentation/networking/i40evf.txt +++ b/Documentation/networking/iavf.txt @@ -2,7 +2,7 @@ Linux* Base Driver for Intel(R) Network Connection ================================================== Intel Ethernet Adaptive Virtual Function Linux driver. -Copyright(c) 2013-2017 Intel Corporation. +Copyright(c) 2013-2018 Intel Corporation. Contents ======== @@ -11,20 +11,21 @@ Contents - Known Issues/Troubleshooting - Support -This file describes the i40evf Linux* Base Driver. +This file describes the iavf Linux* Base Driver. This driver +was formerly called i40evf. -The i40evf driver supports the below mentioned virtual function +The iavf driver supports the below mentioned virtual function devices and can only be activated on kernels running the i40e or newer Physical Function (PF) driver compiled with CONFIG_PCI_IOV. -The i40evf driver requires CONFIG_PCI_MSI to be enabled. +The iavf driver requires CONFIG_PCI_MSI to be enabled. -The guest OS loading the i40evf driver must support MSI-X interrupts. +The guest OS loading the iavf driver must support MSI-X interrupts. Supported Hardware ================== Intel XL710 X710 Virtual Function -Intel Ethernet Adaptive Virtual Function Intel X722 Virtual Function +Intel Ethernet Adaptive Virtual Function Identifying Your Adapter ======================== @@ -32,7 +33,8 @@ Identifying Your Adapter For more information on how to identify your adapter, go to the Adapter & Driver ID Guide at: - http://support.intel.com/support/go/network/adapter/idguide.htm + https://www.intel.com/content/www/us/en/support/articles/000005584/network-and-i-o/ethernet-products.html + Known Issues/Troubleshooting ============================ diff --git a/Documentation/networking/tcp.txt b/Documentation/networking/tcp.txt deleted file mode 100644 index 9c7139d57e57..000000000000 --- a/Documentation/networking/tcp.txt +++ /dev/null @@ -1,101 +0,0 @@ -TCP protocol -============ - -Last updated: 3 June 2017 - -Contents -======== - -- Congestion control -- How the new TCP output machine [nyi] works - -Congestion control -================== - -The following variables are used in the tcp_sock for congestion control: -snd_cwnd The size of the congestion window -snd_ssthresh Slow start threshold. We are in slow start if - snd_cwnd is less than this. -snd_cwnd_cnt A counter used to slow down the rate of increase - once we exceed slow start threshold. -snd_cwnd_clamp This is the maximum size that snd_cwnd can grow to. -snd_cwnd_stamp Timestamp for when congestion window last validated. -snd_cwnd_used Used as a highwater mark for how much of the - congestion window is in use. It is used to adjust - snd_cwnd down when the link is limited by the - application rather than the network. - -As of 2.6.13, Linux supports pluggable congestion control algorithms. -A congestion control mechanism can be registered through functions in -tcp_cong.c. The functions used by the congestion control mechanism are -registered via passing a tcp_congestion_ops struct to -tcp_register_congestion_control. As a minimum, the congestion control -mechanism must provide a valid name and must implement either ssthresh, -cong_avoid and undo_cwnd hooks or the "omnipotent" cong_control hook. - -Private data for a congestion control mechanism is stored in tp->ca_priv. -tcp_ca(tp) returns a pointer to this space. This is preallocated space - it -is important to check the size of your private data will fit this space, or -alternatively, space could be allocated elsewhere and a pointer to it could -be stored here. - -There are three kinds of congestion control algorithms currently: The -simplest ones are derived from TCP reno (highspeed, scalable) and just -provide an alternative congestion window calculation. More complex -ones like BIC try to look at other events to provide better -heuristics. There are also round trip time based algorithms like -Vegas and Westwood+. - -Good TCP congestion control is a complex problem because the algorithm -needs to maintain fairness and performance. Please review current -research and RFC's before developing new modules. - -The default congestion control mechanism is chosen based on the -DEFAULT_TCP_CONG Kconfig parameter. If you really want a particular default -value then you can set it using sysctl net.ipv4.tcp_congestion_control. The -module will be autoloaded if needed and you will get the expected protocol. If -you ask for an unknown congestion method, then the sysctl attempt will fail. - -If you remove a TCP congestion control module, then you will get the next -available one. Since reno cannot be built as a module, and cannot be -removed, it will always be available. - -How the new TCP output machine [nyi] works. -=========================================== - -Data is kept on a single queue. The skb->users flag tells us if the frame is -one that has been queued already. To add a frame we throw it on the end. Ack -walks down the list from the start. - -We keep a set of control flags - - - sk->tcp_pend_event - - TCP_PEND_ACK Ack needed - TCP_ACK_NOW Needed now - TCP_WINDOW Window update check - TCP_WINZERO Zero probing - - - sk->transmit_queue The transmission frame begin - sk->transmit_new First new frame pointer - sk->transmit_end Where to add frames - - sk->tcp_last_tx_ack Last ack seen - sk->tcp_dup_ack Dup ack count for fast retransmit - - -Frames are queued for output by tcp_write. We do our best to send the frames -off immediately if possible, but otherwise queue and compute the body -checksum in the copy. - -When a write is done we try to clear any pending events and piggy back them. -If the window is full we queue full sized frames. On the first timeout in -zero window we split this. - -On a timer we walk the retransmit list to send any retransmits, update the -backoff timers etc. A change of route table stamp causes a change of header -and recompute. We add any new tcp level headers and refinish the checksum -before sending. - diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst index 61f918b10a0c..d1bf143b446f 100644 --- a/Documentation/process/changes.rst +++ b/Documentation/process/changes.rst @@ -86,7 +86,7 @@ pkg-config The build system, as of 4.18, requires pkg-config to check for installed kconfig tools and to determine flags settings for use in -'make {menu,n,g,x}config'. Previously pkg-config was being used but not +'make {g,x}config'. Previously pkg-config was being used but not verified or documented. Flex diff --git a/Documentation/process/code-of-conduct.rst b/Documentation/process/code-of-conduct.rst new file mode 100644 index 000000000000..ab7c24b5478c --- /dev/null +++ b/Documentation/process/code-of-conduct.rst @@ -0,0 +1,81 @@ +Contributor Covenant Code of Conduct +++++++++++++++++++++++++++++++++++++ + +Our Pledge +========== + +In the interest of fostering an open and welcoming environment, we as +contributors and maintainers pledge to making participation in our project and +our community a harassment-free experience for everyone, regardless of age, body +size, disability, ethnicity, sex characteristics, gender identity and +expression, level of experience, education, socio-economic status, nationality, +personal appearance, race, religion, or sexual identity and orientation. + +Our Standards +============= + +Examples of behavior that contributes to creating a positive environment +include: + +* Using welcoming and inclusive language +* Being respectful of differing viewpoints and experiences +* Gracefully accepting constructive criticism +* Focusing on what is best for the community +* Showing empathy towards other community members + + +Examples of unacceptable behavior by participants include: + +* The use of sexualized language or imagery and unwelcome sexual attention or + advances +* Trolling, insulting/derogatory comments, and personal or political attacks +* Public or private harassment +* Publishing others’ private information, such as a physical or electronic + address, without explicit permission +* Other conduct which could reasonably be considered inappropriate in a + professional setting + + +Our Responsibilities +==================== + +Maintainers are responsible for clarifying the standards of acceptable behavior +and are expected to take appropriate and fair corrective action in response to +any instances of unacceptable behavior. + +Maintainers have the right and responsibility to remove, edit, or reject +comments, commits, code, wiki edits, issues, and other contributions that are +not aligned to this Code of Conduct, or to ban temporarily or permanently any +contributor for other behaviors that they deem inappropriate, threatening, +offensive, or harmful. + +Scope +===== + +This Code of Conduct applies both within project spaces and in public spaces +when an individual is representing the project or its community. Examples of +representing a project or community include using an official project e-mail +address, posting via an official social media account, or acting as an appointed +representative at an online or offline event. Representation of a project may be +further defined and clarified by project maintainers. + +Enforcement +=========== + +Instances of abusive, harassing, or otherwise unacceptable behavior may be +reported by contacting the Technical Advisory Board (TAB) at +<tab@lists.linux-foundation.org>. All complaints will be reviewed and +investigated and will result in a response that is deemed necessary and +appropriate to the circumstances. The TAB is obligated to maintain +confidentiality with regard to the reporter of an incident. Further details of +specific enforcement policies may be posted separately. + +Maintainers who do not follow or enforce the Code of Conduct in good faith may +face temporary or permanent repercussions as determined by other members of the +project’s leadership. + +Attribution +=========== + +This Code of Conduct is adapted from the Contributor Covenant, version 1.4, +available at https://www.contributor-covenant.org/version/1/4/code-of-conduct.html diff --git a/Documentation/process/code-of-conflict.rst b/Documentation/process/code-of-conflict.rst deleted file mode 100644 index 47b6de763203..000000000000 --- a/Documentation/process/code-of-conflict.rst +++ /dev/null @@ -1,28 +0,0 @@ -Code of Conflict ----------------- - -The Linux kernel development effort is a very personal process compared -to "traditional" ways of developing software. Your code and ideas -behind it will be carefully reviewed, often resulting in critique and -criticism. The review will almost always require improvements to the -code before it can be included in the kernel. Know that this happens -because everyone involved wants to see the best possible solution for -the overall success of Linux. This development process has been proven -to create the most robust operating system kernel ever, and we do not -want to do anything to cause the quality of submission and eventual -result to ever decrease. - -If however, anyone feels personally abused, threatened, or otherwise -uncomfortable due to this process, that is not acceptable. If so, -please contact the Linux Foundation's Technical Advisory Board at -<tab@lists.linux-foundation.org>, or the individual members, and they -will work to resolve the issue to the best of their ability. For more -information on who is on the Technical Advisory Board and what their -role is, please see: - - - http://www.linuxfoundation.org/projects/linux/tab - -As a reviewer of code, please strive to keep things civil and focused on -the technical issues involved. We are all humans, and frustrations can -be high on both sides of the process. Try to keep in mind the immortal -words of Bill and Ted, "Be excellent to each other." diff --git a/Documentation/process/index.rst b/Documentation/process/index.rst index 37bd0628b6ee..9ae3e317bddf 100644 --- a/Documentation/process/index.rst +++ b/Documentation/process/index.rst @@ -20,7 +20,7 @@ Below are the essential guides that every developer should read. :maxdepth: 1 howto - code-of-conflict + code-of-conduct development-process submitting-patches coding-style diff --git a/Documentation/scsi/scsi-parameters.txt b/Documentation/scsi/scsi-parameters.txt index 25a4b4cf04a6..92999d4e0cb8 100644 --- a/Documentation/scsi/scsi-parameters.txt +++ b/Documentation/scsi/scsi-parameters.txt @@ -97,6 +97,11 @@ parameters may be changed at runtime by the command allowing boot to proceed. none ignores them, expecting user space to do the scan. + scsi_mod.use_blk_mq= + [SCSI] use blk-mq I/O path by default + See SCSI_MQ_DEFAULT in drivers/scsi/Kconfig. + Format: <y/n> + sim710= [SCSI,HW] See header of drivers/scsi/sim710.c. diff --git a/Documentation/x86/earlyprintk.txt b/Documentation/x86/earlyprintk.txt index 688e3eeed21d..46933e06c972 100644 --- a/Documentation/x86/earlyprintk.txt +++ b/Documentation/x86/earlyprintk.txt @@ -35,25 +35,25 @@ and two USB cables, connected like this: ( If your system does not list a debug port capability then you probably won't be able to use the USB debug key. ) - b.) You also need a Netchip USB debug cable/key: + b.) You also need a NetChip USB debug cable/key: http://www.plxtech.com/products/NET2000/NET20DC/default.asp - This is a small blue plastic connector with two USB connections, + This is a small blue plastic connector with two USB connections; it draws power from its USB connections. c.) You need a second client/console system with a high speed USB 2.0 port. - d.) The Netchip device must be plugged directly into the physical + d.) The NetChip device must be plugged directly into the physical debug port on the "host/target" system. You cannot use a USB hub in between the physical debug port and the "host/target" system. The EHCI debug controller is bound to a specific physical USB - port and the Netchip device will only work as an early printk + port and the NetChip device will only work as an early printk device in this port. The EHCI host controllers are electrically wired such that the EHCI debug controller is hooked up to the - first physical and there is no way to change this via software. + first physical port and there is no way to change this via software. You can find the physical port through experimentation by trying each physical port on the system and rebooting. Or you can try and use lsusb or look at the kernel info messages emitted by the @@ -65,9 +65,9 @@ and two USB cables, connected like this: to the hardware vendor, because there is no reason not to wire this port into one of the physically accessible ports. - e.) It is also important to note, that many versions of the Netchip + e.) It is also important to note, that many versions of the NetChip device require the "client/console" system to be plugged into the - right and side of the device (with the product logo facing up and + right hand side of the device (with the product logo facing up and readable left to right). The reason being is that the 5 volt power supply is taken from only one side of the device and it must be the side that does not get rebooted. @@ -81,13 +81,18 @@ and two USB cables, connected like this: CONFIG_EARLY_PRINTK_DBGP=y And you need to add the boot command line: "earlyprintk=dbgp". + (If you are using Grub, append it to the 'kernel' line in - /etc/grub.conf) + /etc/grub.conf. If you are using Grub2 on a BIOS firmware system, + append it to the 'linux' line in /boot/grub2/grub.cfg. If you are + using Grub2 on an EFI firmware system, append it to the 'linux' + or 'linuxefi' line in /boot/grub2/grub.cfg or + /boot/efi/EFI/<distro>/grub.cfg.) On systems with more than one EHCI debug controller you must specify the correct EHCI debug controller number. The ordering comes from the PCI bus enumeration of the EHCI controllers. The - default with no number argument is "0" the first EHCI debug + default with no number argument is "0" or the first EHCI debug controller. To use the second EHCI debug controller, you would use the command line: "earlyprintk=dbgp1" @@ -111,7 +116,7 @@ and two USB cables, connected like this: see the raw output. c.) On Nvidia Southbridge based systems: the kernel will try to probe - and find out which port has debug device connected. + and find out which port has a debug device connected. 3. Testing that it works fine: diff --git a/MAINTAINERS b/MAINTAINERS index a5b256b25905..7233a9ed0f5b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2311,6 +2311,7 @@ F: drivers/clocksource/cadence_ttc_timer.c F: drivers/i2c/busses/i2c-cadence.c F: drivers/mmc/host/sdhci-of-arasan.c F: drivers/edac/synopsys_edac.c +F: drivers/i2c/busses/i2c-xiic.c ARM64 PORT (AARCH64 ARCHITECTURE) M: Catalin Marinas <catalin.marinas@arm.com> @@ -4527,9 +4528,9 @@ F: drivers/soc/fsl/dpio DPAA2 ETHERNET DRIVER M: Ioana Radulescu <ruxandra.radulescu@nxp.com> -L: linux-kernel@vger.kernel.org +L: netdev@vger.kernel.org S: Maintained -F: drivers/staging/fsl-dpaa2/ethernet +F: drivers/net/ethernet/freescale/dpaa2 DPAA2 ETHERNET SWITCH DRIVER M: Ioana Radulescu <ruxandra.radulescu@nxp.com> @@ -5624,6 +5625,8 @@ F: lib/fault-inject.c FBTFT Framebuffer drivers M: Thomas Petazzoni <thomas.petazzoni@free-electrons.com> +L: dri-devel@lists.freedesktop.org +L: linux-fbdev@vger.kernel.org S: Maintained F: drivers/staging/fbtft/ @@ -6059,7 +6062,7 @@ F: Documentation/gcc-plugins.txt GASKET DRIVER FRAMEWORK M: Rob Springer <rspringer@google.com> -M: John Joseph <jnjoseph@google.com> +M: Todd Poynor <toddpoynor@google.com> M: Ben Chan <benchan@chromium.org> S: Maintained F: drivers/staging/gasket/ @@ -7015,6 +7018,20 @@ F: drivers/crypto/vmx/aes* F: drivers/crypto/vmx/ghash* F: drivers/crypto/vmx/ppc-xlate.pl +IBM Power PCI Hotplug Driver for RPA-compliant PPC64 platform +M: Tyrel Datwyler <tyreld@linux.vnet.ibm.com> +L: linux-pci@vger.kernel.org +L: linuxppc-dev@lists.ozlabs.org +S: Supported +F: drivers/pci/hotplug/rpaphp* + +IBM Power IO DLPAR Driver for RPA-compliant PPC64 platform +M: Tyrel Datwyler <tyreld@linux.vnet.ibm.com> +L: linux-pci@vger.kernel.org +L: linuxppc-dev@lists.ozlabs.org +S: Supported +F: drivers/pci/hotplug/rpadlpar* + IBM ServeRAID RAID DRIVER S: Orphan F: drivers/scsi/ips.* @@ -7331,7 +7348,7 @@ F: Documentation/networking/ixgb.txt F: Documentation/networking/ixgbe.txt F: Documentation/networking/ixgbevf.txt F: Documentation/networking/i40e.txt -F: Documentation/networking/i40evf.txt +F: Documentation/networking/iavf.txt F: Documentation/networking/ice.txt F: drivers/net/ethernet/intel/ F: drivers/net/ethernet/intel/*/ @@ -8166,6 +8183,15 @@ S: Maintained F: net/l3mdev F: include/net/l3mdev.h +LANTIQ / INTEL Ethernet drivers +M: Hauke Mehrtens <hauke@hauke-m.de> +L: netdev@vger.kernel.org +S: Maintained +F: net/dsa/tag_gswip.c +F: drivers/net/ethernet/lantiq_xrx200.c +F: drivers/net/dsa/lantiq_pce.h +F: drivers/net/dsa/intel_gswip.c + LANTIQ MIPS ARCHITECTURE M: John Crispin <john@phrozen.org> L: linux-mips@linux-mips.org @@ -8255,9 +8281,9 @@ F: drivers/ata/pata_arasan_cf.c LIBATA PATA DRIVERS M: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> -M: Jens Axboe <kernel.dk> +M: Jens Axboe <axboe@kernel.dk> L: linux-ide@vger.kernel.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git S: Maintained F: drivers/ata/pata_*.c F: drivers/ata/ata_generic.c @@ -8275,7 +8301,7 @@ LIBATA SATA AHCI PLATFORM devices support M: Hans de Goede <hdegoede@redhat.com> M: Jens Axboe <axboe@kernel.dk> L: linux-ide@vger.kernel.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git S: Maintained F: drivers/ata/ahci_platform.c F: drivers/ata/libahci_platform.c @@ -8291,7 +8317,7 @@ F: drivers/ata/sata_promise.* LIBATA SUBSYSTEM (Serial and Parallel ATA drivers) M: Jens Axboe <axboe@kernel.dk> L: linux-ide@vger.kernel.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git S: Maintained F: drivers/ata/ F: include/linux/ata.h @@ -8299,7 +8325,7 @@ F: include/linux/libata.h F: Documentation/devicetree/bindings/ata/ LIBLOCKDEP -M: Sasha Levin <alexander.levin@verizon.com> +M: Sasha Levin <alexander.levin@microsoft.com> S: Maintained F: tools/lib/lockdep/ @@ -11153,7 +11179,7 @@ F: drivers/pci/controller/dwc/pci-exynos.c PCI DRIVER FOR SYNOPSYS DESIGNWARE M: Jingoo Han <jingoohan1@gmail.com> -M: Joao Pinto <Joao.Pinto@synopsys.com> +M: Gustavo Pimentel <gustavo.pimentel@synopsys.com> L: linux-pci@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/pci/designware-pcie.txt @@ -11345,10 +11371,10 @@ S: Maintained F: drivers/platform/x86/peaq-wmi.c PER-CPU MEMORY ALLOCATOR +M: Dennis Zhou <dennis@kernel.org> M: Tejun Heo <tj@kernel.org> M: Christoph Lameter <cl@linux.com> -M: Dennis Zhou <dennisszhou@gmail.com> -T: git git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/dennis/percpu.git S: Maintained F: include/linux/percpu*.h F: mm/percpu*.c @@ -2,7 +2,7 @@ VERSION = 4 PATCHLEVEL = 19 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc4 NAME = Merciless Moray # *DOCUMENTATION* @@ -299,19 +299,7 @@ KERNELRELEASE = $(shell cat include/config/kernel.release 2> /dev/null) KERNELVERSION = $(VERSION)$(if $(PATCHLEVEL),.$(PATCHLEVEL)$(if $(SUBLEVEL),.$(SUBLEVEL)))$(EXTRAVERSION) export VERSION PATCHLEVEL SUBLEVEL KERNELRELEASE KERNELVERSION -# SUBARCH tells the usermode build what the underlying arch is. That is set -# first, and if a usermode build is happening, the "ARCH=um" on the command -# line overrides the setting of ARCH below. If a native build is happening, -# then ARCH is assigned, getting whatever value it gets normally, and -# SUBARCH is subsequently ignored. - -SUBARCH := $(shell uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ \ - -e s/sun4u/sparc64/ \ - -e s/arm.*/arm/ -e s/sa110/arm/ \ - -e s/s390x/s390/ -e s/parisc64/parisc/ \ - -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \ - -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ \ - -e s/riscv.*/riscv/) +include scripts/subarch.include # Cross compiling and selecting different set of gcc/bin-utils # --------------------------------------------------------------------------- @@ -616,6 +604,11 @@ CFLAGS_GCOV := -fprofile-arcs -ftest-coverage \ $(call cc-disable-warning,maybe-uninitialized,) export CFLAGS_GCOV +# The arch Makefiles can override CC_FLAGS_FTRACE. We may also append it later. +ifdef CONFIG_FUNCTION_TRACER + CC_FLAGS_FTRACE := -pg +endif + # The arch Makefile can set ARCH_{CPP,A,C}FLAGS to override the default # values of the respective KBUILD_* variables ARCH_CPPFLAGS := @@ -755,9 +748,6 @@ KBUILD_CFLAGS += $(call cc-option, -femit-struct-debug-baseonly) \ endif ifdef CONFIG_FUNCTION_TRACER -ifndef CC_FLAGS_FTRACE -CC_FLAGS_FTRACE := -pg -endif ifdef CONFIG_FTRACE_MCOUNT_RECORD # gcc 5 supports generating the mcount tables directly ifeq ($(call cc-option-yn,-mrecord-mcount),y) @@ -807,6 +797,9 @@ KBUILD_CFLAGS += $(call cc-option,-Wdeclaration-after-statement,) # disable pointer signed / unsigned warnings in gcc 4.0 KBUILD_CFLAGS += $(call cc-disable-warning, pointer-sign) +# disable stringop warnings in gcc 8+ +KBUILD_CFLAGS += $(call cc-disable-warning, stringop-truncation) + # disable invalid "can't wrap" optimizations for signed / pointers KBUILD_CFLAGS += $(call cc-option,-fno-strict-overflow) diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 6d5eb8267e42..b4441b0764d7 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -9,6 +9,7 @@ config ARC def_bool y select ARC_TIMERS + select ARCH_HAS_PTE_SPECIAL select ARCH_HAS_SYNC_DMA_FOR_CPU select ARCH_HAS_SYNC_DMA_FOR_DEVICE select ARCH_HAS_SG_CHAIN @@ -28,8 +29,12 @@ config ARC select GENERIC_SMP_IDLE_THREAD select HAVE_ARCH_KGDB select HAVE_ARCH_TRACEHOOK + select HAVE_DEBUG_STACKOVERFLOW select HAVE_FUTEX_CMPXCHG if FUTEX + select HAVE_GENERIC_DMA_COHERENT select HAVE_IOREMAP_PROT + select HAVE_KERNEL_GZIP + select HAVE_KERNEL_LZMA select HAVE_KPROBES select HAVE_KRETPROBES select HAVE_MEMBLOCK @@ -44,11 +49,6 @@ config ARC select OF_EARLY_FLATTREE select OF_RESERVED_MEM select PERF_USE_VMALLOC if ARC_CACHE_VIPT_ALIASING - select HAVE_DEBUG_STACKOVERFLOW - select HAVE_GENERIC_DMA_COHERENT - select HAVE_KERNEL_GZIP - select HAVE_KERNEL_LZMA - select ARCH_HAS_PTE_SPECIAL config ARCH_HAS_CACHE_LINE_SIZE def_bool y diff --git a/arch/arc/Makefile b/arch/arc/Makefile index fb026196aaab..99cce77ab98f 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -43,10 +43,7 @@ ifdef CONFIG_ARC_CURR_IN_REG LINUXINCLUDE += -include ${src}/arch/arc/include/asm/current.h endif -upto_gcc44 := $(call cc-ifversion, -le, 0404, y) -atleast_gcc44 := $(call cc-ifversion, -ge, 0404, y) - -cflags-$(atleast_gcc44) += -fsection-anchors +cflags-y += -fsection-anchors cflags-$(CONFIG_ARC_HAS_LLSC) += -mlock cflags-$(CONFIG_ARC_HAS_SWAPE) += -mswape @@ -82,11 +79,6 @@ cflags-$(disable_small_data) += -mno-sdata -fcall-used-gp cflags-$(CONFIG_CPU_BIG_ENDIAN) += -mbig-endian ldflags-$(CONFIG_CPU_BIG_ENDIAN) += -EB -# STAR 9000518362: (fixed with binutils shipping with gcc 4.8) -# arc-linux-uclibc-ld (buildroot) or arceb-elf32-ld (EZChip) don't accept -# --build-id w/o "-marclinux". Default arc-elf32-ld is OK -ldflags-$(upto_gcc44) += -marclinux - LIBGCC := $(shell $(CC) $(cflags-y) --print-libgcc-file-name) # Modules with short calls might break for calls into builtin-kernel diff --git a/arch/arc/boot/dts/axc003.dtsi b/arch/arc/boot/dts/axc003.dtsi index dc91c663bcc0..d75d65ddf8e3 100644 --- a/arch/arc/boot/dts/axc003.dtsi +++ b/arch/arc/boot/dts/axc003.dtsi @@ -94,6 +94,32 @@ }; /* + * Mark DMA peripherals connected via IOC port as dma-coherent. We do + * it via overlay because peripherals defined in axs10x_mb.dtsi are + * used for both AXS101 and AXS103 boards and only AXS103 has IOC (so + * only AXS103 board has HW-coherent DMA peripherals) + * We don't need to mark pgu@17000 as dma-coherent because it uses + * external DMA buffer located outside of IOC aperture. + */ + axs10x_mb { + ethernet@0x18000 { + dma-coherent; + }; + + ehci@0x40000 { + dma-coherent; + }; + + ohci@0x60000 { + dma-coherent; + }; + + mmc@0x15000 { + dma-coherent; + }; + }; + + /* * The DW APB ICTL intc on MB is connected to CPU intc via a * DT "invisible" DW APB GPIO block, configured to simply pass thru * interrupts - setup accordinly in platform init (plat-axs10x/ax10x.c) diff --git a/arch/arc/boot/dts/axc003_idu.dtsi b/arch/arc/boot/dts/axc003_idu.dtsi index 69ff4895f2ba..a05bb737ea63 100644 --- a/arch/arc/boot/dts/axc003_idu.dtsi +++ b/arch/arc/boot/dts/axc003_idu.dtsi @@ -101,6 +101,32 @@ }; /* + * Mark DMA peripherals connected via IOC port as dma-coherent. We do + * it via overlay because peripherals defined in axs10x_mb.dtsi are + * used for both AXS101 and AXS103 boards and only AXS103 has IOC (so + * only AXS103 board has HW-coherent DMA peripherals) + * We don't need to mark pgu@17000 as dma-coherent because it uses + * external DMA buffer located outside of IOC aperture. + */ + axs10x_mb { + ethernet@0x18000 { + dma-coherent; + }; + + ehci@0x40000 { + dma-coherent; + }; + + ohci@0x60000 { + dma-coherent; + }; + + mmc@0x15000 { + dma-coherent; + }; + }; + + /* * This INTC is actually connected to DW APB GPIO * which acts as a wire between MB INTC and CPU INTC. * GPIO INTC is configured in platform init code diff --git a/arch/arc/boot/dts/axs10x_mb.dtsi b/arch/arc/boot/dts/axs10x_mb.dtsi index 47b74fbc403c..37bafd44e36d 100644 --- a/arch/arc/boot/dts/axs10x_mb.dtsi +++ b/arch/arc/boot/dts/axs10x_mb.dtsi @@ -9,6 +9,10 @@ */ / { + aliases { + ethernet = &gmac; + }; + axs10x_mb { compatible = "simple-bus"; #address-cells = <1>; @@ -68,7 +72,7 @@ }; }; - ethernet@0x18000 { + gmac: ethernet@0x18000 { #interrupt-cells = <1>; compatible = "snps,dwmac"; reg = < 0x18000 0x2000 >; @@ -81,6 +85,7 @@ max-speed = <100>; resets = <&creg_rst 5>; reset-names = "stmmaceth"; + mac-address = [00 00 00 00 00 00]; /* Filled in by U-Boot */ }; ehci@0x40000 { diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts index 006aa3de5348..ef149f59929a 100644 --- a/arch/arc/boot/dts/hsdk.dts +++ b/arch/arc/boot/dts/hsdk.dts @@ -25,6 +25,10 @@ bootargs = "earlycon=uart8250,mmio32,0xf0005000,115200n8 console=ttyS0,115200n8 debug print-fatal-signals=1"; }; + aliases { + ethernet = &gmac; + }; + cpus { #address-cells = <1>; #size-cells = <0>; @@ -163,7 +167,7 @@ #clock-cells = <0>; }; - ethernet@8000 { + gmac: ethernet@8000 { #interrupt-cells = <1>; compatible = "snps,dwmac"; reg = <0x8000 0x2000>; @@ -176,6 +180,8 @@ phy-handle = <&phy0>; resets = <&cgu_rst HSDK_ETH_RESET>; reset-names = "stmmaceth"; + mac-address = [00 00 00 00 00 00]; /* Filled in by U-Boot */ + dma-coherent; mdio { #address-cells = <1>; @@ -194,12 +200,14 @@ compatible = "snps,hsdk-v1.0-ohci", "generic-ohci"; reg = <0x60000 0x100>; interrupts = <15>; + dma-coherent; }; ehci@40000 { compatible = "snps,hsdk-v1.0-ehci", "generic-ehci"; reg = <0x40000 0x100>; interrupts = <15>; + dma-coherent; }; mmc@a000 { @@ -212,6 +220,7 @@ clock-names = "biu", "ciu"; interrupts = <12>; bus-width = <4>; + dma-coherent; }; }; diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig index a635ea972304..41bc08be6a3b 100644 --- a/arch/arc/configs/axs101_defconfig +++ b/arch/arc/configs/axs101_defconfig @@ -1,5 +1,3 @@ -CONFIG_DEFAULT_HOSTNAME="ARCLinux" -# CONFIG_SWAP is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y # CONFIG_CROSS_MEMORY_ATTACH is not set @@ -63,7 +61,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y CONFIG_MOUSE_SERIAL=y CONFIG_MOUSE_SYNAPTICS_USB=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_DW=y diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig index aa507e423075..1e1c4a8011b5 100644 --- a/arch/arc/configs/axs103_defconfig +++ b/arch/arc/configs/axs103_defconfig @@ -1,5 +1,3 @@ -CONFIG_DEFAULT_HOSTNAME="ARCLinux" -# CONFIG_SWAP is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y # CONFIG_CROSS_MEMORY_ATTACH is not set @@ -64,7 +62,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y CONFIG_MOUSE_SERIAL=y CONFIG_MOUSE_SYNAPTICS_USB=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_DW=y diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig index eba07f468654..6b0c0cfd5c30 100644 --- a/arch/arc/configs/axs103_smp_defconfig +++ b/arch/arc/configs/axs103_smp_defconfig @@ -1,5 +1,3 @@ -CONFIG_DEFAULT_HOSTNAME="ARCLinux" -# CONFIG_SWAP is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y # CONFIG_CROSS_MEMORY_ATTACH is not set @@ -65,7 +63,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y CONFIG_MOUSE_SERIAL=y CONFIG_MOUSE_SYNAPTICS_USB=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_DW=y diff --git a/arch/arc/configs/haps_hs_defconfig b/arch/arc/configs/haps_hs_defconfig index 098b19fbaa51..240dd2cd5148 100644 --- a/arch/arc/configs/haps_hs_defconfig +++ b/arch/arc/configs/haps_hs_defconfig @@ -1,4 +1,3 @@ -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y @@ -57,7 +56,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y # CONFIG_SERIO_SERPORT is not set CONFIG_SERIO_ARC_PS2=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=1 diff --git a/arch/arc/configs/haps_hs_smp_defconfig b/arch/arc/configs/haps_hs_smp_defconfig index 0104c404d897..14ae7e5acc7c 100644 --- a/arch/arc/configs/haps_hs_smp_defconfig +++ b/arch/arc/configs/haps_hs_smp_defconfig @@ -1,4 +1,3 @@ -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y @@ -60,7 +59,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y # CONFIG_SERIO_SERPORT is not set CONFIG_SERIO_ARC_PS2=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=1 diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig index 6491be0ddbc9..1dec2b4bc5e6 100644 --- a/arch/arc/configs/hsdk_defconfig +++ b/arch/arc/configs/hsdk_defconfig @@ -1,4 +1,3 @@ -CONFIG_DEFAULT_HOSTNAME="ARCLinux" CONFIG_SYSVIPC=y # CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_NO_HZ_IDLE=y diff --git a/arch/arc/configs/nps_defconfig b/arch/arc/configs/nps_defconfig index 7c9c706ae7f6..31ba224bbfb4 100644 --- a/arch/arc/configs/nps_defconfig +++ b/arch/arc/configs/nps_defconfig @@ -59,7 +59,6 @@ CONFIG_NETCONSOLE=y # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=1 diff --git a/arch/arc/configs/nsim_700_defconfig b/arch/arc/configs/nsim_700_defconfig index 99e05cf63fca..8e0b8b134cd9 100644 --- a/arch/arc/configs/nsim_700_defconfig +++ b/arch/arc/configs/nsim_700_defconfig @@ -1,5 +1,4 @@ # CONFIG_LOCALVERSION_AUTO is not set -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y @@ -44,7 +43,6 @@ CONFIG_LXT_PHY=y # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_ARC=y CONFIG_SERIAL_ARC_CONSOLE=y # CONFIG_HW_RANDOM is not set diff --git a/arch/arc/configs/nsim_hs_defconfig b/arch/arc/configs/nsim_hs_defconfig index 0dc4f9b737e7..739b90e5e893 100644 --- a/arch/arc/configs/nsim_hs_defconfig +++ b/arch/arc/configs/nsim_hs_defconfig @@ -1,5 +1,4 @@ # CONFIG_LOCALVERSION_AUTO is not set -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y @@ -45,7 +44,6 @@ CONFIG_DEVTMPFS=y # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_ARC=y CONFIG_SERIAL_ARC_CONSOLE=y # CONFIG_HW_RANDOM is not set diff --git a/arch/arc/configs/nsim_hs_smp_defconfig b/arch/arc/configs/nsim_hs_smp_defconfig index be3c30a15e54..b5895bdf3a93 100644 --- a/arch/arc/configs/nsim_hs_smp_defconfig +++ b/arch/arc/configs/nsim_hs_smp_defconfig @@ -1,5 +1,4 @@ # CONFIG_LOCALVERSION_AUTO is not set -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set # CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_HIGH_RES_TIMERS=y @@ -44,7 +43,6 @@ CONFIG_DEVTMPFS=y # CONFIG_INPUT_MOUSE is not set # CONFIG_SERIO is not set # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_ARC=y CONFIG_SERIAL_ARC_CONSOLE=y # CONFIG_HW_RANDOM is not set diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig index 3a74b9b21772..f14eeff7d308 100644 --- a/arch/arc/configs/nsimosci_defconfig +++ b/arch/arc/configs/nsimosci_defconfig @@ -1,5 +1,4 @@ # CONFIG_LOCALVERSION_AUTO is not set -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y # CONFIG_CROSS_MEMORY_ATTACH is not set @@ -48,7 +47,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y # CONFIG_SERIO_SERPORT is not set CONFIG_SERIO_ARC_PS2=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=1 diff --git a/arch/arc/configs/nsimosci_hs_defconfig b/arch/arc/configs/nsimosci_hs_defconfig index ea2834b4dc1d..025298a48305 100644 --- a/arch/arc/configs/nsimosci_hs_defconfig +++ b/arch/arc/configs/nsimosci_hs_defconfig @@ -1,5 +1,4 @@ # CONFIG_LOCALVERSION_AUTO is not set -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y # CONFIG_CROSS_MEMORY_ATTACH is not set @@ -47,7 +46,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y # CONFIG_SERIO_SERPORT is not set CONFIG_SERIO_ARC_PS2=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=1 diff --git a/arch/arc/configs/nsimosci_hs_smp_defconfig b/arch/arc/configs/nsimosci_hs_smp_defconfig index 80a5a1b4924b..df7b77b13b82 100644 --- a/arch/arc/configs/nsimosci_hs_smp_defconfig +++ b/arch/arc/configs/nsimosci_hs_smp_defconfig @@ -1,4 +1,3 @@ -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y # CONFIG_CROSS_MEMORY_ATTACH is not set @@ -58,7 +57,6 @@ CONFIG_MOUSE_PS2_TOUCHKIT=y # CONFIG_SERIO_SERPORT is not set CONFIG_SERIO_ARC_PS2=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=1 diff --git a/arch/arc/configs/tb10x_defconfig b/arch/arc/configs/tb10x_defconfig index 2cc87f909747..a7f65313f84a 100644 --- a/arch/arc/configs/tb10x_defconfig +++ b/arch/arc/configs/tb10x_defconfig @@ -57,7 +57,6 @@ CONFIG_STMMAC_ETH=y # CONFIG_SERIO is not set # CONFIG_VT is not set # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_NR_UARTS=1 diff --git a/arch/arc/configs/vdk_hs38_defconfig b/arch/arc/configs/vdk_hs38_defconfig index f629493929ea..db47c3541f15 100644 --- a/arch/arc/configs/vdk_hs38_defconfig +++ b/arch/arc/configs/vdk_hs38_defconfig @@ -1,5 +1,4 @@ # CONFIG_LOCALVERSION_AUTO is not set -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_HIGH_RES_TIMERS=y CONFIG_IKCONFIG=y @@ -53,7 +52,6 @@ CONFIG_NATIONAL_PHY=y CONFIG_MOUSE_PS2_TOUCHKIT=y CONFIG_SERIO_ARC_PS2=y # CONFIG_LEGACY_PTYS is not set -# CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y CONFIG_SERIAL_8250_CONSOLE=y CONFIG_SERIAL_8250_DW=y diff --git a/arch/arc/configs/vdk_hs38_smp_defconfig b/arch/arc/configs/vdk_hs38_smp_defconfig index 21f0ca26a05d..a8ac5e917d9a 100644 --- a/arch/arc/configs/vdk_hs38_smp_defconfig +++ b/arch/arc/configs/vdk_hs38_smp_defconfig @@ -1,5 +1,4 @@ # CONFIG_LOCALVERSION_AUTO is not set -CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_HIGH_RES_TIMERS=y CONFIG_IKCONFIG=y diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h index 4e0072730241..158af079838d 100644 --- a/arch/arc/include/asm/atomic.h +++ b/arch/arc/include/asm/atomic.h @@ -84,7 +84,7 @@ static inline int atomic_fetch_##op(int i, atomic_t *v) \ "1: llock %[orig], [%[ctr]] \n" \ " " #asm_op " %[val], %[orig], %[i] \n" \ " scond %[val], [%[ctr]] \n" \ - " \n" \ + " bnz 1b \n" \ : [val] "=&r" (val), \ [orig] "=&r" (orig) \ : [ctr] "r" (&v->counter), \ diff --git a/arch/arc/include/asm/dma-mapping.h b/arch/arc/include/asm/dma-mapping.h new file mode 100644 index 000000000000..c946c0a83e76 --- /dev/null +++ b/arch/arc/include/asm/dma-mapping.h @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 +// (C) 2018 Synopsys, Inc. (www.synopsys.com) + +#ifndef ASM_ARC_DMA_MAPPING_H +#define ASM_ARC_DMA_MAPPING_H + +#include <asm-generic/dma-mapping.h> + +void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, + const struct iommu_ops *iommu, bool coherent); +#define arch_setup_dma_ops arch_setup_dma_ops + +#endif diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c index 783b20354f8b..e8d9fb452346 100644 --- a/arch/arc/kernel/troubleshoot.c +++ b/arch/arc/kernel/troubleshoot.c @@ -83,9 +83,6 @@ done: static void show_faulting_vma(unsigned long address, char *buf) { struct vm_area_struct *vma; - struct inode *inode; - unsigned long ino = 0; - dev_t dev = 0; char *nm = buf; struct mm_struct *active_mm = current->active_mm; @@ -99,12 +96,10 @@ static void show_faulting_vma(unsigned long address, char *buf) * if the container VMA is not found */ if (vma && (vma->vm_start <= address)) { - struct file *file = vma->vm_file; - if (file) { - nm = file_path(file, buf, PAGE_SIZE - 1); - inode = file_inode(vma->vm_file); - dev = inode->i_sb->s_dev; - ino = inode->i_ino; + if (vma->vm_file) { + nm = file_path(vma->vm_file, buf, PAGE_SIZE - 1); + if (IS_ERR(nm)) + nm = "?"; } pr_info(" @off 0x%lx in [%s]\n" " VMA: 0x%08lx to 0x%08lx\n", diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index 25c631942500..f2701c13a66b 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -65,7 +65,7 @@ char *arc_cache_mumbojumbo(int c, char *buf, int len) n += scnprintf(buf + n, len - n, "Peripherals\t: %#lx%s%s\n", perip_base, - IS_AVAIL3(ioc_exists, ioc_enable, ", IO-Coherency ")); + IS_AVAIL3(ioc_exists, ioc_enable, ", IO-Coherency (per-device) ")); return buf; } @@ -897,15 +897,6 @@ static void __dma_cache_wback_slc(phys_addr_t start, unsigned long sz) } /* - * DMA ops for systems with IOC - * IOC hardware snoops all DMA traffic keeping the caches consistent with - * memory - eliding need for any explicit cache maintenance of DMA buffers - */ -static void __dma_cache_wback_inv_ioc(phys_addr_t start, unsigned long sz) {} -static void __dma_cache_inv_ioc(phys_addr_t start, unsigned long sz) {} -static void __dma_cache_wback_ioc(phys_addr_t start, unsigned long sz) {} - -/* * Exported DMA API */ void dma_cache_wback_inv(phys_addr_t start, unsigned long sz) @@ -1153,6 +1144,19 @@ noinline void __init arc_ioc_setup(void) { unsigned int ioc_base, mem_sz; + /* + * As for today we don't support both IOC and ZONE_HIGHMEM enabled + * simultaneously. This happens because as of today IOC aperture covers + * only ZONE_NORMAL (low mem) and any dma transactions outside this + * region won't be HW coherent. + * If we want to use both IOC and ZONE_HIGHMEM we can use + * bounce_buffer to handle dma transactions to HIGHMEM. + * Also it is possible to modify dma_direct cache ops or increase IOC + * aperture size if we are planning to use HIGHMEM without PAE. + */ + if (IS_ENABLED(CONFIG_HIGHMEM)) + panic("IOC and HIGHMEM can't be used simultaneously"); + /* Flush + invalidate + disable L1 dcache */ __dc_disable(); @@ -1264,11 +1268,7 @@ void __init arc_cache_init_master(void) if (is_isa_arcv2() && ioc_enable) arc_ioc_setup(); - if (is_isa_arcv2() && ioc_enable) { - __dma_cache_wback_inv = __dma_cache_wback_inv_ioc; - __dma_cache_inv = __dma_cache_inv_ioc; - __dma_cache_wback = __dma_cache_wback_ioc; - } else if (is_isa_arcv2() && l2_line_sz && slc_enable) { + if (is_isa_arcv2() && l2_line_sz && slc_enable) { __dma_cache_wback_inv = __dma_cache_wback_inv_slc; __dma_cache_inv = __dma_cache_inv_slc; __dma_cache_wback = __dma_cache_wback_slc; @@ -1277,6 +1277,12 @@ void __init arc_cache_init_master(void) __dma_cache_inv = __dma_cache_inv_l1; __dma_cache_wback = __dma_cache_wback_l1; } + /* + * In case of IOC (say IOC+SLC case), pointers above could still be set + * but end up not being relevant as the first function in chain is not + * called at all for @dma_direct_ops + * arch_sync_dma_for_cpu() -> dma_cache_*() -> __dma_cache_*() + */ } void __ref arc_cache_init(void) diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c index ec47e6079f5d..c75d5c3470e3 100644 --- a/arch/arc/mm/dma.c +++ b/arch/arc/mm/dma.c @@ -6,20 +6,17 @@ * published by the Free Software Foundation. */ -/* - * DMA Coherent API Notes - * - * I/O is inherently non-coherent on ARC. So a coherent DMA buffer is - * implemented by accessing it using a kernel virtual address, with - * Cache bit off in the TLB entry. - * - * The default DMA address == Phy address which is 0x8000_0000 based. - */ - #include <linux/dma-noncoherent.h> #include <asm/cache.h> #include <asm/cacheflush.h> +/* + * ARCH specific callbacks for generic noncoherent DMA ops (dma/noncoherent.c) + * - hardware IOC not available (or "dma-coherent" not set for device in DT) + * - But still handle both coherent and non-coherent requests from caller + * + * For DMA coherent hardware (IOC) generic code suffices + */ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs) { @@ -27,42 +24,29 @@ void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle, struct page *page; phys_addr_t paddr; void *kvaddr; - int need_coh = 1, need_kvaddr = 0; - - page = alloc_pages(gfp, order); - if (!page) - return NULL; + bool need_coh = !(attrs & DMA_ATTR_NON_CONSISTENT); /* - * IOC relies on all data (even coherent DMA data) being in cache - * Thus allocate normal cached memory - * - * The gains with IOC are two pronged: - * -For streaming data, elides need for cache maintenance, saving - * cycles in flush code, and bus bandwidth as all the lines of a - * buffer need to be flushed out to memory - * -For coherent data, Read/Write to buffers terminate early in cache - * (vs. always going to memory - thus are faster) + * __GFP_HIGHMEM flag is cleared by upper layer functions + * (in include/linux/dma-mapping.h) so we should never get a + * __GFP_HIGHMEM here. */ - if ((is_isa_arcv2() && ioc_enable) || - (attrs & DMA_ATTR_NON_CONSISTENT)) - need_coh = 0; + BUG_ON(gfp & __GFP_HIGHMEM); - /* - * - A coherent buffer needs MMU mapping to enforce non-cachability - * - A highmem page needs a virtual handle (hence MMU mapping) - * independent of cachability - */ - if (PageHighMem(page) || need_coh) - need_kvaddr = 1; + page = alloc_pages(gfp, order); + if (!page) + return NULL; /* This is linear addr (0x8000_0000 based) */ paddr = page_to_phys(page); *dma_handle = paddr; - /* This is kernel Virtual address (0x7000_0000 based) */ - if (need_kvaddr) { + /* + * A coherent buffer needs MMU mapping to enforce non-cachability. + * kvaddr is kernel Virtual address (0x7000_0000 based). + */ + if (need_coh) { kvaddr = ioremap_nocache(paddr, size); if (kvaddr == NULL) { __free_pages(page, order); @@ -93,12 +77,8 @@ void arch_dma_free(struct device *dev, size_t size, void *vaddr, { phys_addr_t paddr = dma_handle; struct page *page = virt_to_page(paddr); - int is_non_coh = 1; - - is_non_coh = (attrs & DMA_ATTR_NON_CONSISTENT) || - (is_isa_arcv2() && ioc_enable); - if (PageHighMem(page) || !is_non_coh) + if (!(attrs & DMA_ATTR_NON_CONSISTENT)) iounmap((void __force __iomem *)vaddr); __free_pages(page, get_order(size)); @@ -185,3 +165,23 @@ void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr, break; } } + +/* + * Plug in coherent or noncoherent dma ops + */ +void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, + const struct iommu_ops *iommu, bool coherent) +{ + /* + * IOC hardware snoops all DMA traffic keeping the caches consistent + * with memory - eliding need for any explicit cache maintenance of + * DMA buffers - so we can use dma_direct cache ops. + */ + if (is_isa_arcv2() && ioc_enable && coherent) { + set_dma_ops(dev, &dma_direct_ops); + dev_info(dev, "use dma_direct_ops cache ops\n"); + } else { + set_dma_ops(dev, &dma_noncoherent_ops); + dev_info(dev, "use dma_noncoherent_ops cache ops\n"); + } +} diff --git a/arch/arm/boot/dts/am335x-osd3358-sm-red.dts b/arch/arm/boot/dts/am335x-osd3358-sm-red.dts index 4d969013f99a..4d969013f99a 100755..100644 --- a/arch/arm/boot/dts/am335x-osd3358-sm-red.dts +++ b/arch/arm/boot/dts/am335x-osd3358-sm-red.dts diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi index f0cbd86312dc..d4b7c59eec68 100644 --- a/arch/arm/boot/dts/am4372.dtsi +++ b/arch/arm/boot/dts/am4372.dtsi @@ -469,6 +469,7 @@ ti,hwmods = "rtc"; clocks = <&clk_32768_ck>; clock-names = "int-clk"; + system-power-controller; status = "disabled"; }; diff --git a/arch/arm/boot/dts/imx23-evk.dts b/arch/arm/boot/dts/imx23-evk.dts index 9fb47724b9c1..ad2ae25b7b4d 100644 --- a/arch/arm/boot/dts/imx23-evk.dts +++ b/arch/arm/boot/dts/imx23-evk.dts @@ -13,6 +13,43 @@ reg = <0x40000000 0x08000000>; }; + reg_vddio_sd0: regulator-vddio-sd0 { + compatible = "regulator-fixed"; + regulator-name = "vddio-sd0"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + gpio = <&gpio1 29 0>; + }; + + reg_lcd_3v3: regulator-lcd-3v3 { + compatible = "regulator-fixed"; + regulator-name = "lcd-3v3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + gpio = <&gpio1 18 0>; + enable-active-high; + }; + + reg_lcd_5v: regulator-lcd-5v { + compatible = "regulator-fixed"; + regulator-name = "lcd-5v"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + }; + + panel { + compatible = "sii,43wvf1g"; + backlight = <&backlight_display>; + dvdd-supply = <®_lcd_3v3>; + avdd-supply = <®_lcd_5v>; + + port { + panel_in: endpoint { + remote-endpoint = <&display_out>; + }; + }; + }; + apb@80000000 { apbh@80000000 { gpmi-nand@8000c000 { @@ -52,31 +89,11 @@ lcdif@80030000 { pinctrl-names = "default"; pinctrl-0 = <&lcdif_24bit_pins_a>; - lcd-supply = <®_lcd_3v3>; - display = <&display0>; status = "okay"; - display0: display0 { - bits-per-pixel = <32>; - bus-width = <24>; - - display-timings { - native-mode = <&timing0>; - timing0: timing0 { - clock-frequency = <9200000>; - hactive = <480>; - vactive = <272>; - hback-porch = <15>; - hfront-porch = <8>; - vback-porch = <12>; - vfront-porch = <4>; - hsync-len = <1>; - vsync-len = <1>; - hsync-active = <0>; - vsync-active = <0>; - de-active = <1>; - pixelclk-active = <0>; - }; + port { + display_out: endpoint { + remote-endpoint = <&panel_in>; }; }; }; @@ -118,32 +135,7 @@ }; }; - regulators { - compatible = "simple-bus"; - #address-cells = <1>; - #size-cells = <0>; - - reg_vddio_sd0: regulator@0 { - compatible = "regulator-fixed"; - reg = <0>; - regulator-name = "vddio-sd0"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - gpio = <&gpio1 29 0>; - }; - - reg_lcd_3v3: regulator@1 { - compatible = "regulator-fixed"; - reg = <1>; - regulator-name = "lcd-3v3"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - gpio = <&gpio1 18 0>; - enable-active-high; - }; - }; - - backlight { + backlight_display: backlight { compatible = "pwm-backlight"; pwms = <&pwm 2 5000000>; brightness-levels = <0 4 8 16 32 64 128 255>; diff --git a/arch/arm/boot/dts/imx28-evk.dts b/arch/arm/boot/dts/imx28-evk.dts index 6b0ae667640f..93ab5bdfe068 100644 --- a/arch/arm/boot/dts/imx28-evk.dts +++ b/arch/arm/boot/dts/imx28-evk.dts @@ -13,6 +13,87 @@ reg = <0x40000000 0x08000000>; }; + + reg_3p3v: regulator-3p3v { + compatible = "regulator-fixed"; + regulator-name = "3P3V"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + + reg_vddio_sd0: regulator-vddio-sd0 { + compatible = "regulator-fixed"; + regulator-name = "vddio-sd0"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + gpio = <&gpio3 28 0>; + }; + + reg_fec_3v3: regulator-fec-3v3 { + compatible = "regulator-fixed"; + regulator-name = "fec-3v3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + gpio = <&gpio2 15 0>; + }; + + reg_usb0_vbus: regulator-usb0-vbus { + compatible = "regulator-fixed"; + regulator-name = "usb0_vbus"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + gpio = <&gpio3 9 0>; + enable-active-high; + }; + + reg_usb1_vbus: regulator-usb1-vbus { + compatible = "regulator-fixed"; + regulator-name = "usb1_vbus"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + gpio = <&gpio3 8 0>; + enable-active-high; + }; + + reg_lcd_3v3: regulator-lcd-3v3 { + compatible = "regulator-fixed"; + regulator-name = "lcd-3v3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + gpio = <&gpio3 30 0>; + enable-active-high; + }; + + reg_can_3v3: regulator-can-3v3 { + compatible = "regulator-fixed"; + regulator-name = "can-3v3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + gpio = <&gpio2 13 0>; + enable-active-high; + }; + + reg_lcd_5v: regulator-lcd-5v { + compatible = "regulator-fixed"; + regulator-name = "lcd-5v"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + }; + + panel { + compatible = "sii,43wvf1g"; + backlight = <&backlight_display>; + dvdd-supply = <®_lcd_3v3>; + avdd-supply = <®_lcd_5v>; + + port { + panel_in: endpoint { + remote-endpoint = <&display_out>; + }; + }; + }; + apb@80000000 { apbh@80000000 { gpmi-nand@8000c000 { @@ -116,31 +197,11 @@ pinctrl-names = "default"; pinctrl-0 = <&lcdif_24bit_pins_a &lcdif_pins_evk>; - lcd-supply = <®_lcd_3v3>; - display = <&display0>; status = "okay"; - display0: display0 { - bits-per-pixel = <32>; - bus-width = <24>; - - display-timings { - native-mode = <&timing0>; - timing0: timing0 { - clock-frequency = <33500000>; - hactive = <800>; - vactive = <480>; - hback-porch = <89>; - hfront-porch = <164>; - vback-porch = <23>; - vfront-porch = <10>; - hsync-len = <10>; - vsync-len = <10>; - hsync-active = <0>; - vsync-active = <0>; - de-active = <1>; - pixelclk-active = <0>; - }; + port { + display_out: endpoint { + remote-endpoint = <&panel_in>; }; }; }; @@ -269,80 +330,6 @@ }; }; - regulators { - compatible = "simple-bus"; - #address-cells = <1>; - #size-cells = <0>; - - reg_3p3v: regulator@0 { - compatible = "regulator-fixed"; - reg = <0>; - regulator-name = "3P3V"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - regulator-always-on; - }; - - reg_vddio_sd0: regulator@1 { - compatible = "regulator-fixed"; - reg = <1>; - regulator-name = "vddio-sd0"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - gpio = <&gpio3 28 0>; - }; - - reg_fec_3v3: regulator@2 { - compatible = "regulator-fixed"; - reg = <2>; - regulator-name = "fec-3v3"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - gpio = <&gpio2 15 0>; - }; - - reg_usb0_vbus: regulator@3 { - compatible = "regulator-fixed"; - reg = <3>; - regulator-name = "usb0_vbus"; - regulator-min-microvolt = <5000000>; - regulator-max-microvolt = <5000000>; - gpio = <&gpio3 9 0>; - enable-active-high; - }; - - reg_usb1_vbus: regulator@4 { - compatible = "regulator-fixed"; - reg = <4>; - regulator-name = "usb1_vbus"; - regulator-min-microvolt = <5000000>; - regulator-max-microvolt = <5000000>; - gpio = <&gpio3 8 0>; - enable-active-high; - }; - - reg_lcd_3v3: regulator@5 { - compatible = "regulator-fixed"; - reg = <5>; - regulator-name = "lcd-3v3"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - gpio = <&gpio3 30 0>; - enable-active-high; - }; - - reg_can_3v3: regulator@6 { - compatible = "regulator-fixed"; - reg = <6>; - regulator-name = "can-3v3"; - regulator-min-microvolt = <3300000>; - regulator-max-microvolt = <3300000>; - gpio = <&gpio2 13 0>; - enable-active-high; - }; - - }; - sound { compatible = "fsl,imx28-evk-sgtl5000", "fsl,mxs-audio-sgtl5000"; @@ -363,7 +350,7 @@ }; }; - backlight { + backlight_display: backlight { compatible = "pwm-backlight"; pwms = <&pwm 2 5000000>; brightness-levels = <0 4 8 16 32 64 128 255>; diff --git a/arch/arm/boot/dts/imx7d.dtsi b/arch/arm/boot/dts/imx7d.dtsi index 7cbc2ffa4b3a..7234e8330a57 100644 --- a/arch/arm/boot/dts/imx7d.dtsi +++ b/arch/arm/boot/dts/imx7d.dtsi @@ -126,10 +126,14 @@ interrupt-names = "msi"; #interrupt-cells = <1>; interrupt-map-mask = <0 0 0 0x7>; - interrupt-map = <0 0 0 1 &intc GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>, - <0 0 0 2 &intc GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>, - <0 0 0 3 &intc GIC_SPI 124 IRQ_TYPE_LEVEL_HIGH>, - <0 0 0 4 &intc GIC_SPI 125 IRQ_TYPE_LEVEL_HIGH>; + /* + * Reference manual lists pci irqs incorrectly + * Real hardware ordering is same as imx6: D+MSI, C, B, A + */ + interrupt-map = <0 0 0 1 &intc GIC_SPI 125 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 2 &intc GIC_SPI 124 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 3 &intc GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>, + <0 0 0 4 &intc GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>; clocks = <&clks IMX7D_PCIE_CTRL_ROOT_CLK>, <&clks IMX7D_PLL_ENET_MAIN_100M_CLK>, <&clks IMX7D_PCIE_PHY_ROOT_CLK>; diff --git a/arch/arm/boot/dts/omap4-droid4-xt894.dts b/arch/arm/boot/dts/omap4-droid4-xt894.dts index 12d6822f0057..04758a2a87f0 100644 --- a/arch/arm/boot/dts/omap4-droid4-xt894.dts +++ b/arch/arm/boot/dts/omap4-droid4-xt894.dts @@ -354,7 +354,7 @@ &mmc2 { vmmc-supply = <&vsdio>; bus-width = <8>; - non-removable; + ti,non-removable; }; &mmc3 { @@ -621,15 +621,6 @@ OMAP4_IOPAD(0x10c, PIN_INPUT | MUX_MODE1) /* abe_mcbsp3_fsx */ >; }; -}; - -&omap4_pmx_wkup { - usb_gpio_mux_sel2: pinmux_usb_gpio_mux_sel2_pins { - /* gpio_wk0 */ - pinctrl-single,pins = < - OMAP4_IOPAD(0x040, PIN_OUTPUT_PULLDOWN | MUX_MODE3) - >; - }; vibrator_direction_pin: pinmux_vibrator_direction_pin { pinctrl-single,pins = < @@ -644,6 +635,15 @@ }; }; +&omap4_pmx_wkup { + usb_gpio_mux_sel2: pinmux_usb_gpio_mux_sel2_pins { + /* gpio_wk0 */ + pinctrl-single,pins = < + OMAP4_IOPAD(0x040, PIN_OUTPUT_PULLDOWN | MUX_MODE3) + >; + }; +}; + /* * As uart1 is wired to mdm6600 with rts and cts, we can use the cts pin for * uart1 wakeirq. diff --git a/arch/arm/boot/dts/sama5d3_emac.dtsi b/arch/arm/boot/dts/sama5d3_emac.dtsi index 7cb235ef0fb6..6e9e1c2f9def 100644 --- a/arch/arm/boot/dts/sama5d3_emac.dtsi +++ b/arch/arm/boot/dts/sama5d3_emac.dtsi @@ -41,7 +41,7 @@ }; macb1: ethernet@f802c000 { - compatible = "cdns,at91sam9260-macb", "cdns,macb"; + compatible = "atmel,sama5d3-macb", "cdns,at91sam9260-macb", "cdns,macb"; reg = <0xf802c000 0x100>; interrupts = <35 IRQ_TYPE_LEVEL_HIGH 3>; pinctrl-names = "default"; diff --git a/arch/arm/configs/imx_v6_v7_defconfig b/arch/arm/configs/imx_v6_v7_defconfig index e2c127608bcc..7eca43ff69bb 100644 --- a/arch/arm/configs/imx_v6_v7_defconfig +++ b/arch/arm/configs/imx_v6_v7_defconfig @@ -257,6 +257,7 @@ CONFIG_IMX_IPUV3_CORE=y CONFIG_DRM=y CONFIG_DRM_PANEL_LVDS=y CONFIG_DRM_PANEL_SIMPLE=y +CONFIG_DRM_PANEL_SEIKO_43WVF1G=y CONFIG_DRM_DW_HDMI_AHB_AUDIO=m CONFIG_DRM_DW_HDMI_CEC=y CONFIG_DRM_IMX=y diff --git a/arch/arm/configs/mxs_defconfig b/arch/arm/configs/mxs_defconfig index 148226e36152..7b8212857535 100644 --- a/arch/arm/configs/mxs_defconfig +++ b/arch/arm/configs/mxs_defconfig @@ -95,6 +95,7 @@ CONFIG_MFD_MXS_LRADC=y CONFIG_REGULATOR=y CONFIG_REGULATOR_FIXED_VOLTAGE=y CONFIG_DRM=y +CONFIG_DRM_PANEL_SEIKO_43WVF1G=y CONFIG_DRM_MXSFB=y CONFIG_FB_MODE_HELPERS=y CONFIG_BACKLIGHT_LCD_SUPPORT=y diff --git a/arch/arm/configs/versatile_defconfig b/arch/arm/configs/versatile_defconfig index df68dc4056e5..5282324c7cef 100644 --- a/arch/arm/configs/versatile_defconfig +++ b/arch/arm/configs/versatile_defconfig @@ -5,19 +5,19 @@ CONFIG_HIGH_RES_TIMERS=y CONFIG_LOG_BUF_SHIFT=14 CONFIG_BLK_DEV_INITRD=y CONFIG_SLAB=y -CONFIG_MODULES=y -CONFIG_MODULE_UNLOAD=y -CONFIG_PARTITION_ADVANCED=y # CONFIG_ARCH_MULTI_V7 is not set CONFIG_ARCH_VERSATILE=y CONFIG_AEABI=y CONFIG_OABI_COMPAT=y -CONFIG_CMA=y CONFIG_ZBOOT_ROM_TEXT=0x0 CONFIG_ZBOOT_ROM_BSS=0x0 CONFIG_CMDLINE="root=1f03 mem=32M" CONFIG_FPE_NWFPE=y CONFIG_VFP=y +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +CONFIG_PARTITION_ADVANCED=y +CONFIG_CMA=y CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -59,6 +59,7 @@ CONFIG_GPIO_PL061=y CONFIG_DRM=y CONFIG_DRM_PANEL_ARM_VERSATILE=y CONFIG_DRM_PANEL_SIMPLE=y +CONFIG_DRM_DUMB_VGA_DAC=y CONFIG_DRM_PL111=y CONFIG_FB_MODE_HELPERS=y CONFIG_BACKLIGHT_LCD_SUPPORT=y @@ -89,9 +90,10 @@ CONFIG_NFSD=y CONFIG_NFSD_V3=y CONFIG_NLS_CODEPAGE_850=m CONFIG_NLS_ISO8859_1=m +CONFIG_FONTS=y +CONFIG_FONT_ACORN_8x8=y +CONFIG_DEBUG_FS=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y CONFIG_DEBUG_USER=y CONFIG_DEBUG_LL=y -CONFIG_FONTS=y -CONFIG_FONT_ACORN_8x8=y diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h index 79906cecb091..3ad482d2f1eb 100644 --- a/arch/arm/include/asm/kvm_host.h +++ b/arch/arm/include/asm/kvm_host.h @@ -223,7 +223,6 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events); #define KVM_ARCH_WANT_MMU_NOTIFIER -int kvm_unmap_hva(struct kvm *kvm, unsigned long hva); int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end); void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index 2ceffd85dd3d..cd65ea4e9c54 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -2161,6 +2161,37 @@ static int of_dev_hwmod_lookup(struct device_node *np, } /** + * omap_hwmod_fix_mpu_rt_idx - fix up mpu_rt_idx register offsets + * + * @oh: struct omap_hwmod * + * @np: struct device_node * + * + * Fix up module register offsets for modules with mpu_rt_idx. + * Only needed for cpsw with interconnect target module defined + * in device tree while still using legacy hwmod platform data + * for rev, sysc and syss registers. + * + * Can be removed when all cpsw hwmod platform data has been + * dropped. + */ +static void omap_hwmod_fix_mpu_rt_idx(struct omap_hwmod *oh, + struct device_node *np, + struct resource *res) +{ + struct device_node *child = NULL; + int error; + + child = of_get_next_child(np, child); + if (!child) + return; + + error = of_address_to_resource(child, oh->mpu_rt_idx, res); + if (error) + pr_err("%s: error mapping mpu_rt_idx: %i\n", + __func__, error); +} + +/** * omap_hwmod_parse_module_range - map module IO range from device tree * @oh: struct omap_hwmod * * @np: struct device_node * @@ -2220,7 +2251,13 @@ int omap_hwmod_parse_module_range(struct omap_hwmod *oh, size = be32_to_cpup(ranges); pr_debug("omap_hwmod: %s %s at 0x%llx size 0x%llx\n", - oh->name, np->name, base, size); + oh ? oh->name : "", np->name, base, size); + + if (oh && oh->mpu_rt_idx) { + omap_hwmod_fix_mpu_rt_idx(oh, np, res); + + return 0; + } res->start = base; res->end = base + size - 1; diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 29e75b47becd..1b1a0e95c751 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -763,7 +763,6 @@ config NEED_PER_CPU_EMBED_FIRST_CHUNK config HOLES_IN_ZONE def_bool y - depends on NUMA source kernel/Kconfig.hz diff --git a/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts b/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts index ceffc40810ee..48daec7f78ba 100644 --- a/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts +++ b/arch/arm64/boot/dts/allwinner/sun50i-h6-pine-h64.dts @@ -46,6 +46,7 @@ pinctrl-0 = <&mmc0_pins>; vmmc-supply = <®_cldo1>; cd-gpios = <&pio 5 6 GPIO_ACTIVE_LOW>; + bus-width = <4>; status = "okay"; }; @@ -56,6 +57,7 @@ vqmmc-supply = <®_bldo2>; non-removable; cap-mmc-hw-reset; + bus-width = <8>; status = "okay"; }; diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index f67e8d5e93ad..db8d364f8476 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -38,6 +38,7 @@ CONFIG_ARCH_BCM_IPROC=y CONFIG_ARCH_BERLIN=y CONFIG_ARCH_BRCMSTB=y CONFIG_ARCH_EXYNOS=y +CONFIG_ARCH_K3=y CONFIG_ARCH_LAYERSCAPE=y CONFIG_ARCH_LG1K=y CONFIG_ARCH_HISI=y @@ -605,6 +606,8 @@ CONFIG_ARCH_TEGRA_132_SOC=y CONFIG_ARCH_TEGRA_210_SOC=y CONFIG_ARCH_TEGRA_186_SOC=y CONFIG_ARCH_TEGRA_194_SOC=y +CONFIG_ARCH_K3_AM6_SOC=y +CONFIG_SOC_TI=y CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND=y CONFIG_EXTCON_USB_GPIO=y CONFIG_EXTCON_USBC_CROS_EC=y diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c index 6e9f33d14930..067d8937d5af 100644 --- a/arch/arm64/crypto/ghash-ce-glue.c +++ b/arch/arm64/crypto/ghash-ce-glue.c @@ -417,7 +417,7 @@ static int gcm_encrypt(struct aead_request *req) __aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv, nrounds); put_unaligned_be32(2, iv + GCM_IV_SIZE); - while (walk.nbytes >= AES_BLOCK_SIZE) { + while (walk.nbytes >= (2 * AES_BLOCK_SIZE)) { int blocks = walk.nbytes / AES_BLOCK_SIZE; u8 *dst = walk.dst.virt.addr; u8 *src = walk.src.virt.addr; @@ -437,11 +437,18 @@ static int gcm_encrypt(struct aead_request *req) NULL); err = skcipher_walk_done(&walk, - walk.nbytes % AES_BLOCK_SIZE); + walk.nbytes % (2 * AES_BLOCK_SIZE)); } - if (walk.nbytes) + if (walk.nbytes) { __aes_arm64_encrypt(ctx->aes_key.key_enc, ks, iv, nrounds); + if (walk.nbytes > AES_BLOCK_SIZE) { + crypto_inc(iv, AES_BLOCK_SIZE); + __aes_arm64_encrypt(ctx->aes_key.key_enc, + ks + AES_BLOCK_SIZE, iv, + nrounds); + } + } } /* handle the tail */ @@ -545,7 +552,7 @@ static int gcm_decrypt(struct aead_request *req) __aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv, nrounds); put_unaligned_be32(2, iv + GCM_IV_SIZE); - while (walk.nbytes >= AES_BLOCK_SIZE) { + while (walk.nbytes >= (2 * AES_BLOCK_SIZE)) { int blocks = walk.nbytes / AES_BLOCK_SIZE; u8 *dst = walk.dst.virt.addr; u8 *src = walk.src.virt.addr; @@ -564,11 +571,21 @@ static int gcm_decrypt(struct aead_request *req) } while (--blocks > 0); err = skcipher_walk_done(&walk, - walk.nbytes % AES_BLOCK_SIZE); + walk.nbytes % (2 * AES_BLOCK_SIZE)); } - if (walk.nbytes) + if (walk.nbytes) { + if (walk.nbytes > AES_BLOCK_SIZE) { + u8 *iv2 = iv + AES_BLOCK_SIZE; + + memcpy(iv2, iv, AES_BLOCK_SIZE); + crypto_inc(iv2, AES_BLOCK_SIZE); + + __aes_arm64_encrypt(ctx->aes_key.key_enc, iv2, + iv2, nrounds); + } __aes_arm64_encrypt(ctx->aes_key.key_enc, iv, iv, nrounds); + } } /* handle the tail */ diff --git a/arch/arm64/crypto/sm4-ce-glue.c b/arch/arm64/crypto/sm4-ce-glue.c index b7fb5274b250..0c4fc223f225 100644 --- a/arch/arm64/crypto/sm4-ce-glue.c +++ b/arch/arm64/crypto/sm4-ce-glue.c @@ -69,5 +69,5 @@ static void __exit sm4_ce_mod_fini(void) crypto_unregister_alg(&sm4_ce_alg); } -module_cpu_feature_match(SM3, sm4_ce_mod_init); +module_cpu_feature_match(SM4, sm4_ce_mod_init); module_exit(sm4_ce_mod_fini); diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h index 1b5e0e843c3a..7e2b3e360086 100644 --- a/arch/arm64/include/asm/jump_label.h +++ b/arch/arm64/include/asm/jump_label.h @@ -28,7 +28,7 @@ static __always_inline bool arch_static_branch(struct static_key *key, bool branch) { - asm goto("1: nop\n\t" + asm_volatile_goto("1: nop\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".align 3\n\t" ".quad 1b, %l[l_yes], %c0\n\t" @@ -42,7 +42,7 @@ l_yes: static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch) { - asm goto("1: b %l[l_yes]\n\t" + asm_volatile_goto("1: b %l[l_yes]\n\t" ".pushsection __jump_table, \"aw\"\n\t" ".align 3\n\t" ".quad 1b, %l[l_yes], %c0\n\t" diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index f26055f2306e..3d6d7336f871 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -61,8 +61,7 @@ struct kvm_arch { u64 vmid_gen; u32 vmid; - /* 1-level 2nd stage table and lock */ - spinlock_t pgd_lock; + /* 1-level 2nd stage table, protected by kvm->mmu_lock */ pgd_t *pgd; /* VTTBR value associated with above pgd and vmid */ @@ -357,7 +356,6 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events); #define KVM_ARCH_WANT_MMU_NOTIFIER -int kvm_unmap_hva(struct kvm *kvm, unsigned long hva); int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end); void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 95ac7374d723..4c8b13bede80 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -54,6 +54,7 @@ arm64-obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o \ arm64-obj-$(CONFIG_ARM64_RELOC_TEST) += arm64-reloc-test.o arm64-reloc-test-y := reloc_test_core.o reloc_test_syms.o arm64-obj-$(CONFIG_CRASH_DUMP) += crash_dump.o +arm64-obj-$(CONFIG_CRASH_CORE) += crash_core.o arm64-obj-$(CONFIG_ARM_SDE_INTERFACE) += sdei.o arm64-obj-$(CONFIG_ARM64_SSBD) += ssbd.o diff --git a/arch/arm64/kernel/crash_core.c b/arch/arm64/kernel/crash_core.c new file mode 100644 index 000000000000..ca4c3e12d8c5 --- /dev/null +++ b/arch/arm64/kernel/crash_core.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) Linaro. + * Copyright (C) Huawei Futurewei Technologies. + */ + +#include <linux/crash_core.h> +#include <asm/memory.h> + +void arch_crash_save_vmcoreinfo(void) +{ + VMCOREINFO_NUMBER(VA_BITS); + /* Please note VMCOREINFO_NUMBER() uses "%d", not "%x" */ + vmcoreinfo_append_str("NUMBER(kimage_voffset)=0x%llx\n", + kimage_voffset); + vmcoreinfo_append_str("NUMBER(PHYS_OFFSET)=0x%llx\n", + PHYS_OFFSET); + vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset()); +} diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c index f6a5c6bc1434..922add8adb74 100644 --- a/arch/arm64/kernel/machine_kexec.c +++ b/arch/arm64/kernel/machine_kexec.c @@ -358,14 +358,3 @@ void crash_free_reserved_phys_range(unsigned long begin, unsigned long end) } } #endif /* CONFIG_HIBERNATION */ - -void arch_crash_save_vmcoreinfo(void) -{ - VMCOREINFO_NUMBER(VA_BITS); - /* Please note VMCOREINFO_NUMBER() uses "%d", not "%x" */ - vmcoreinfo_append_str("NUMBER(kimage_voffset)=0x%llx\n", - kimage_voffset); - vmcoreinfo_append_str("NUMBER(PHYS_OFFSET)=0x%llx\n", - PHYS_OFFSET); - vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset()); -} diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c index d496ef579859..ca46153d7915 100644 --- a/arch/arm64/kvm/hyp/switch.c +++ b/arch/arm64/kvm/hyp/switch.c @@ -98,8 +98,10 @@ static void activate_traps_vhe(struct kvm_vcpu *vcpu) val = read_sysreg(cpacr_el1); val |= CPACR_EL1_TTA; val &= ~CPACR_EL1_ZEN; - if (!update_fp_enabled(vcpu)) + if (!update_fp_enabled(vcpu)) { val &= ~CPACR_EL1_FPEN; + __activate_traps_fpsimd32(vcpu); + } write_sysreg(val, cpacr_el1); @@ -114,8 +116,10 @@ static void __hyp_text __activate_traps_nvhe(struct kvm_vcpu *vcpu) val = CPTR_EL2_DEFAULT; val |= CPTR_EL2_TTA | CPTR_EL2_TZ; - if (!update_fp_enabled(vcpu)) + if (!update_fp_enabled(vcpu)) { val |= CPTR_EL2_TFP; + __activate_traps_fpsimd32(vcpu); + } write_sysreg(val, cptr_el2); } @@ -129,7 +133,6 @@ static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu) if (cpus_have_const_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE)) write_sysreg_s(vcpu->arch.vsesr_el2, SYS_VSESR_EL2); - __activate_traps_fpsimd32(vcpu); if (has_vhe()) activate_traps_vhe(vcpu); else diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 65f86271f02b..8080c9f489c3 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -985,8 +985,9 @@ int pmd_free_pte_page(pmd_t *pmdp, unsigned long addr) pmd = READ_ONCE(*pmdp); - /* No-op for empty entry and WARN_ON for valid entry */ - if (!pmd_present(pmd) || !pmd_table(pmd)) { + if (!pmd_present(pmd)) + return 1; + if (!pmd_table(pmd)) { VM_WARN_ON(!pmd_table(pmd)); return 1; } @@ -1007,8 +1008,9 @@ int pud_free_pmd_page(pud_t *pudp, unsigned long addr) pud = READ_ONCE(*pudp); - /* No-op for empty entry and WARN_ON for valid entry */ - if (!pud_present(pud) || !pud_table(pud)) { + if (!pud_present(pud)) + return 1; + if (!pud_table(pud)) { VM_WARN_ON(!pud_table(pud)); return 1; } diff --git a/arch/hexagon/include/asm/bitops.h b/arch/hexagon/include/asm/bitops.h index 5e4a59b3ec1b..2691a1857d20 100644 --- a/arch/hexagon/include/asm/bitops.h +++ b/arch/hexagon/include/asm/bitops.h @@ -211,7 +211,7 @@ static inline long ffz(int x) * This is defined the same way as ffs. * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32. */ -static inline long fls(int x) +static inline int fls(int x) { int r; @@ -232,7 +232,7 @@ static inline long fls(int x) * the libc and compiler builtin ffs routines, therefore * differs in spirit from the above ffz (man ffs). */ -static inline long ffs(int x) +static inline int ffs(int x) { int r; diff --git a/arch/hexagon/kernel/dma.c b/arch/hexagon/kernel/dma.c index 77459df34e2e..7ebe7ad19d15 100644 --- a/arch/hexagon/kernel/dma.c +++ b/arch/hexagon/kernel/dma.c @@ -60,7 +60,7 @@ static void *hexagon_dma_alloc_coherent(struct device *dev, size_t size, panic("Can't create %s() memory pool!", __func__); else gen_pool_add(coherent_pool, - pfn_to_virt(max_low_pfn), + (unsigned long)pfn_to_virt(max_low_pfn), hexagon_coherent_pool_size, -1); } diff --git a/arch/m68k/mac/misc.c b/arch/m68k/mac/misc.c index 3534aa6a4dc2..1b083c500b9a 100644 --- a/arch/m68k/mac/misc.c +++ b/arch/m68k/mac/misc.c @@ -98,11 +98,10 @@ static time64_t pmu_read_time(void) if (pmu_request(&req, NULL, 1, PMU_READ_RTC) < 0) return 0; - while (!req.complete) - pmu_poll(); + pmu_wait_complete(&req); - time = (u32)((req.reply[1] << 24) | (req.reply[2] << 16) | - (req.reply[3] << 8) | req.reply[4]); + time = (u32)((req.reply[0] << 24) | (req.reply[1] << 16) | + (req.reply[2] << 8) | req.reply[3]); return time - RTC_OFFSET; } @@ -116,8 +115,7 @@ static void pmu_write_time(time64_t time) (data >> 24) & 0xFF, (data >> 16) & 0xFF, (data >> 8) & 0xFF, data & 0xFF) < 0) return; - while (!req.complete) - pmu_poll(); + pmu_wait_complete(&req); } static __u8 pmu_read_pram(int offset) diff --git a/arch/m68k/mm/mcfmmu.c b/arch/m68k/mm/mcfmmu.c index 70dde040779b..f5453d944ff5 100644 --- a/arch/m68k/mm/mcfmmu.c +++ b/arch/m68k/mm/mcfmmu.c @@ -172,7 +172,7 @@ void __init cf_bootmem_alloc(void) high_memory = (void *)_ramend; /* Reserve kernel text/data/bss */ - memblock_reserve(memstart, memstart - _rambase); + memblock_reserve(_rambase, memstart - _rambase); m68k_virt_to_node_shift = fls(_ramend - 1) - 6; module_fixup(NULL, __start_fixup, __stop_fixup); diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h index a9af1d2dcd69..2c1c53d12179 100644 --- a/arch/mips/include/asm/kvm_host.h +++ b/arch/mips/include/asm/kvm_host.h @@ -931,7 +931,6 @@ enum kvm_mips_fault_result kvm_trap_emul_gva_fault(struct kvm_vcpu *vcpu, bool write); #define KVM_ARCH_WANT_MMU_NOTIFIER -int kvm_unmap_hva(struct kvm *kvm, unsigned long hva); int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end); void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte); diff --git a/arch/mips/include/asm/mach-lantiq/xway/xway_dma.h b/arch/mips/include/asm/mach-lantiq/xway/xway_dma.h index 4901833498f7..8441b2698e64 100644 --- a/arch/mips/include/asm/mach-lantiq/xway/xway_dma.h +++ b/arch/mips/include/asm/mach-lantiq/xway/xway_dma.h @@ -40,6 +40,7 @@ struct ltq_dma_channel { int desc; /* the current descriptor */ struct ltq_dma_desc *desc_base; /* the descriptor base */ int phys; /* physical addr */ + struct device *dev; }; enum { diff --git a/arch/mips/kernel/vdso.c b/arch/mips/kernel/vdso.c index 019035d7225c..8f845f6e5f42 100644 --- a/arch/mips/kernel/vdso.c +++ b/arch/mips/kernel/vdso.c @@ -13,6 +13,7 @@ #include <linux/err.h> #include <linux/init.h> #include <linux/ioport.h> +#include <linux/kernel.h> #include <linux/mm.h> #include <linux/sched.h> #include <linux/slab.h> @@ -20,6 +21,7 @@ #include <asm/abi.h> #include <asm/mips-cps.h> +#include <asm/page.h> #include <asm/vdso.h> /* Kernel-provided data used by the VDSO. */ @@ -128,12 +130,30 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) vvar_size = gic_size + PAGE_SIZE; size = vvar_size + image->size; + /* + * Find a region that's large enough for us to perform the + * colour-matching alignment below. + */ + if (cpu_has_dc_aliases) + size += shm_align_mask + 1; + base = get_unmapped_area(NULL, 0, size, 0, 0); if (IS_ERR_VALUE(base)) { ret = base; goto out; } + /* + * If we suffer from dcache aliasing, ensure that the VDSO data page + * mapping is coloured the same as the kernel's mapping of that memory. + * This ensures that when the kernel updates the VDSO data userland + * will observe it without requiring cache invalidations. + */ + if (cpu_has_dc_aliases) { + base = __ALIGN_MASK(base, shm_align_mask); + base += ((unsigned long)&vdso_data - gic_size) & shm_align_mask; + } + data_addr = base + gic_size; vdso_addr = data_addr + PAGE_SIZE; diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c index ee64db032793..d8dcdb350405 100644 --- a/arch/mips/kvm/mmu.c +++ b/arch/mips/kvm/mmu.c @@ -512,16 +512,6 @@ static int kvm_unmap_hva_handler(struct kvm *kvm, gfn_t gfn, gfn_t gfn_end, return 1; } -int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) -{ - unsigned long end = hva + PAGE_SIZE; - - handle_hva_to_gpa(kvm, hva, end, &kvm_unmap_hva_handler, NULL); - - kvm_mips_callbacks->flush_shadow_all(kvm); - return 0; -} - int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) { handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, NULL); diff --git a/arch/mips/lantiq/xway/dma.c b/arch/mips/lantiq/xway/dma.c index 4b9fbb6744ad..982859f2b2a3 100644 --- a/arch/mips/lantiq/xway/dma.c +++ b/arch/mips/lantiq/xway/dma.c @@ -106,7 +106,6 @@ ltq_dma_open(struct ltq_dma_channel *ch) spin_lock_irqsave(<q_dma_lock, flag); ltq_dma_w32(ch->nr, LTQ_DMA_CS); ltq_dma_w32_mask(0, DMA_CHAN_ON, LTQ_DMA_CCTRL); - ltq_dma_w32_mask(0, 1 << ch->nr, LTQ_DMA_IRNEN); spin_unlock_irqrestore(<q_dma_lock, flag); } EXPORT_SYMBOL_GPL(ltq_dma_open); @@ -130,7 +129,7 @@ ltq_dma_alloc(struct ltq_dma_channel *ch) unsigned long flags; ch->desc = 0; - ch->desc_base = dma_zalloc_coherent(NULL, + ch->desc_base = dma_zalloc_coherent(ch->dev, LTQ_DESC_NUM * LTQ_DESC_SIZE, &ch->phys, GFP_ATOMIC); @@ -182,7 +181,7 @@ ltq_dma_free(struct ltq_dma_channel *ch) if (!ch->desc_base) return; ltq_dma_close(ch); - dma_free_coherent(NULL, LTQ_DESC_NUM * LTQ_DESC_SIZE, + dma_free_coherent(ch->dev, LTQ_DESC_NUM * LTQ_DESC_SIZE, ch->desc_base, ch->phys); } EXPORT_SYMBOL_GPL(ltq_dma_free); diff --git a/arch/mips/lantiq/xway/sysctrl.c b/arch/mips/lantiq/xway/sysctrl.c index e0af39b33e28..fe25c99089b7 100644 --- a/arch/mips/lantiq/xway/sysctrl.c +++ b/arch/mips/lantiq/xway/sysctrl.c @@ -505,7 +505,7 @@ void __init ltq_soc_init(void) clkdev_add_pmu("1a800000.pcie", "msi", 1, 1, PMU1_PCIE2_MSI); clkdev_add_pmu("1a800000.pcie", "pdi", 1, 1, PMU1_PCIE2_PDI); clkdev_add_pmu("1a800000.pcie", "ctl", 1, 1, PMU1_PCIE2_CTL); - clkdev_add_pmu("1e108000.eth", NULL, 0, 0, PMU_SWITCH | PMU_PPE_DP); + clkdev_add_pmu("1e10b308.eth", NULL, 0, 0, PMU_SWITCH | PMU_PPE_DP); clkdev_add_pmu("1da00000.usif", "NULL", 1, 0, PMU_USIF); clkdev_add_pmu("1e103100.deu", NULL, 1, 0, PMU_DEU); } else if (of_machine_is_compatible("lantiq,ar10")) { @@ -513,11 +513,11 @@ void __init ltq_soc_init(void) ltq_ar10_fpi_hz(), ltq_ar10_pp32_hz()); clkdev_add_pmu("1e101000.usb", "otg", 1, 0, PMU_USB0); clkdev_add_pmu("1e106000.usb", "otg", 1, 0, PMU_USB1); - clkdev_add_pmu("1e108000.eth", NULL, 0, 0, PMU_SWITCH | + clkdev_add_pmu("1e10b308.eth", NULL, 0, 0, PMU_SWITCH | PMU_PPE_DP | PMU_PPE_TC); clkdev_add_pmu("1da00000.usif", "NULL", 1, 0, PMU_USIF); - clkdev_add_pmu("1f203020.gphy", NULL, 1, 0, PMU_GPHY); - clkdev_add_pmu("1f203068.gphy", NULL, 1, 0, PMU_GPHY); + clkdev_add_pmu("1e108000.gswip", "gphy0", 0, 0, PMU_GPHY); + clkdev_add_pmu("1e108000.gswip", "gphy1", 0, 0, PMU_GPHY); clkdev_add_pmu("1e103100.deu", NULL, 1, 0, PMU_DEU); clkdev_add_pmu("1e116000.mei", "afe", 1, 2, PMU_ANALOG_DSL_AFE); clkdev_add_pmu("1e116000.mei", "dfe", 1, 0, PMU_DFE); @@ -536,12 +536,12 @@ void __init ltq_soc_init(void) clkdev_add_pmu(NULL, "ahb", 1, 0, PMU_AHBM | PMU_AHBS); clkdev_add_pmu("1da00000.usif", "NULL", 1, 0, PMU_USIF); - clkdev_add_pmu("1e108000.eth", NULL, 0, 0, + clkdev_add_pmu("1e10b308.eth", NULL, 0, 0, PMU_SWITCH | PMU_PPE_DPLUS | PMU_PPE_DPLUM | PMU_PPE_EMA | PMU_PPE_TC | PMU_PPE_SLL01 | PMU_PPE_QSB | PMU_PPE_TOP); - clkdev_add_pmu("1f203020.gphy", NULL, 0, 0, PMU_GPHY); - clkdev_add_pmu("1f203068.gphy", NULL, 0, 0, PMU_GPHY); + clkdev_add_pmu("1e108000.gswip", "gphy0", 0, 0, PMU_GPHY); + clkdev_add_pmu("1e108000.gswip", "gphy1", 0, 0, PMU_GPHY); clkdev_add_pmu("1e103000.sdio", NULL, 1, 0, PMU_SDIO); clkdev_add_pmu("1e103100.deu", NULL, 1, 0, PMU_DEU); clkdev_add_pmu("1e116000.mei", "dfe", 1, 0, PMU_DFE); diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig index 1d4248fa55e9..7068f341133d 100644 --- a/arch/nds32/Kconfig +++ b/arch/nds32/Kconfig @@ -40,6 +40,10 @@ config NDS32 select NO_IOPORT_MAP select RTC_LIB select THREAD_INFO_IN_TASK + select HAVE_FUNCTION_TRACER + select HAVE_FUNCTION_GRAPH_TRACER + select HAVE_FTRACE_MCOUNT_RECORD + select HAVE_DYNAMIC_FTRACE help Andes(nds32) Linux support. diff --git a/arch/nds32/Makefile b/arch/nds32/Makefile index 63f4f173e5f4..3509fac10491 100644 --- a/arch/nds32/Makefile +++ b/arch/nds32/Makefile @@ -5,6 +5,10 @@ KBUILD_DEFCONFIG := defconfig comma = , +ifdef CONFIG_FUNCTION_TRACER +arch-y += -malways-save-lp -mno-relax +endif + KBUILD_CFLAGS += $(call cc-option, -mno-sched-prolog-epilog) KBUILD_CFLAGS += -mcmodel=large diff --git a/arch/nds32/include/asm/elf.h b/arch/nds32/include/asm/elf.h index 56c479058802..f5f9cf7e0544 100644 --- a/arch/nds32/include/asm/elf.h +++ b/arch/nds32/include/asm/elf.h @@ -121,9 +121,9 @@ struct elf32_hdr; */ #define ELF_CLASS ELFCLASS32 #ifdef __NDS32_EB__ -#define ELF_DATA ELFDATA2MSB; +#define ELF_DATA ELFDATA2MSB #else -#define ELF_DATA ELFDATA2LSB; +#define ELF_DATA ELFDATA2LSB #endif #define ELF_ARCH EM_NDS32 #define USE_ELF_CORE_DUMP diff --git a/arch/nds32/include/asm/ftrace.h b/arch/nds32/include/asm/ftrace.h new file mode 100644 index 000000000000..2f96cc96aa35 --- /dev/null +++ b/arch/nds32/include/asm/ftrace.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __ASM_NDS32_FTRACE_H +#define __ASM_NDS32_FTRACE_H + +#ifdef CONFIG_FUNCTION_TRACER + +#define HAVE_FUNCTION_GRAPH_FP_TEST + +#define MCOUNT_ADDR ((unsigned long)(_mcount)) +/* mcount call is composed of three instructions: + * sethi + ori + jral + */ +#define MCOUNT_INSN_SIZE 12 + +extern void _mcount(unsigned long parent_ip); + +#ifdef CONFIG_DYNAMIC_FTRACE + +#define FTRACE_ADDR ((unsigned long)_ftrace_caller) + +#ifdef __NDS32_EL__ +#define INSN_NOP 0x09000040 +#define INSN_SIZE(insn) (((insn & 0x00000080) == 0) ? 4 : 2) +#define IS_SETHI(insn) ((insn & 0x000000fe) == 0x00000046) +#define ENDIAN_CONVERT(insn) be32_to_cpu(insn) +#else /* __NDS32_EB__ */ +#define INSN_NOP 0x40000009 +#define INSN_SIZE(insn) (((insn & 0x80000000) == 0) ? 4 : 2) +#define IS_SETHI(insn) ((insn & 0xfe000000) == 0x46000000) +#define ENDIAN_CONVERT(insn) (insn) +#endif + +extern void _ftrace_caller(unsigned long parent_ip); +static inline unsigned long ftrace_call_adjust(unsigned long addr) +{ + return addr; +} +struct dyn_arch_ftrace { +}; + +#endif /* CONFIG_DYNAMIC_FTRACE */ + +#endif /* CONFIG_FUNCTION_TRACER */ + +#endif /* __ASM_NDS32_FTRACE_H */ diff --git a/arch/nds32/include/asm/nds32.h b/arch/nds32/include/asm/nds32.h index 19b19394a936..68c38151c3e4 100644 --- a/arch/nds32/include/asm/nds32.h +++ b/arch/nds32/include/asm/nds32.h @@ -17,6 +17,7 @@ #else #define FP_OFFSET (-2) #endif +#define LP_OFFSET (-1) extern void __init early_trap_init(void); static inline void GIE_ENABLE(void) diff --git a/arch/nds32/include/asm/uaccess.h b/arch/nds32/include/asm/uaccess.h index 18a009f3804d..362a32d9bd16 100644 --- a/arch/nds32/include/asm/uaccess.h +++ b/arch/nds32/include/asm/uaccess.h @@ -38,7 +38,7 @@ struct exception_table_entry { extern int fixup_exception(struct pt_regs *regs); #define KERNEL_DS ((mm_segment_t) { ~0UL }) -#define USER_DS ((mm_segment_t) {TASK_SIZE - 1}) +#define USER_DS ((mm_segment_t) {TASK_SIZE - 1}) #define get_ds() (KERNEL_DS) #define get_fs() (current_thread_info()->addr_limit) @@ -49,11 +49,11 @@ static inline void set_fs(mm_segment_t fs) current_thread_info()->addr_limit = fs; } -#define segment_eq(a, b) ((a) == (b)) +#define segment_eq(a, b) ((a) == (b)) #define __range_ok(addr, size) (size <= get_fs() && addr <= (get_fs() -size)) -#define access_ok(type, addr, size) \ +#define access_ok(type, addr, size) \ __range_ok((unsigned long)addr, (unsigned long)size) /* * Single-value transfer routines. They automatically use the right @@ -75,70 +75,73 @@ static inline void set_fs(mm_segment_t fs) * versions are void (ie, don't return a value as such). */ -#define get_user(x,p) \ -({ \ - long __e = -EFAULT; \ - if(likely(access_ok(VERIFY_READ, p, sizeof(*p)))) { \ - __e = __get_user(x,p); \ - } else \ - x = 0; \ - __e; \ -}) -#define __get_user(x,ptr) \ +#define get_user __get_user \ + +#define __get_user(x, ptr) \ ({ \ long __gu_err = 0; \ - __get_user_err((x),(ptr),__gu_err); \ + __get_user_check((x), (ptr), __gu_err); \ __gu_err; \ }) -#define __get_user_error(x,ptr,err) \ +#define __get_user_error(x, ptr, err) \ ({ \ - __get_user_err((x),(ptr),err); \ - (void) 0; \ + __get_user_check((x), (ptr), (err)); \ + (void)0; \ }) -#define __get_user_err(x,ptr,err) \ +#define __get_user_check(x, ptr, err) \ +({ \ + const __typeof__(*(ptr)) __user *__p = (ptr); \ + might_fault(); \ + if (access_ok(VERIFY_READ, __p, sizeof(*__p))) { \ + __get_user_err((x), __p, (err)); \ + } else { \ + (x) = 0; (err) = -EFAULT; \ + } \ +}) + +#define __get_user_err(x, ptr, err) \ do { \ - unsigned long __gu_addr = (unsigned long)(ptr); \ unsigned long __gu_val; \ __chk_user_ptr(ptr); \ switch (sizeof(*(ptr))) { \ case 1: \ - __get_user_asm("lbi",__gu_val,__gu_addr,err); \ + __get_user_asm("lbi", __gu_val, (ptr), (err)); \ break; \ case 2: \ - __get_user_asm("lhi",__gu_val,__gu_addr,err); \ + __get_user_asm("lhi", __gu_val, (ptr), (err)); \ break; \ case 4: \ - __get_user_asm("lwi",__gu_val,__gu_addr,err); \ + __get_user_asm("lwi", __gu_val, (ptr), (err)); \ break; \ case 8: \ - __get_user_asm_dword(__gu_val,__gu_addr,err); \ + __get_user_asm_dword(__gu_val, (ptr), (err)); \ break; \ default: \ BUILD_BUG(); \ break; \ } \ - (x) = (__typeof__(*(ptr)))__gu_val; \ + (x) = (__force __typeof__(*(ptr)))__gu_val; \ } while (0) -#define __get_user_asm(inst,x,addr,err) \ - asm volatile( \ - "1: "inst" %1,[%2]\n" \ - "2:\n" \ - " .section .fixup,\"ax\"\n" \ - " .align 2\n" \ - "3: move %0, %3\n" \ - " move %1, #0\n" \ - " b 2b\n" \ - " .previous\n" \ - " .section __ex_table,\"a\"\n" \ - " .align 3\n" \ - " .long 1b, 3b\n" \ - " .previous" \ - : "+r" (err), "=&r" (x) \ - : "r" (addr), "i" (-EFAULT) \ - : "cc") +#define __get_user_asm(inst, x, addr, err) \ + __asm__ __volatile__ ( \ + "1: "inst" %1,[%2]\n" \ + "2:\n" \ + " .section .fixup,\"ax\"\n" \ + " .align 2\n" \ + "3: move %0, %3\n" \ + " move %1, #0\n" \ + " b 2b\n" \ + " .previous\n" \ + " .section __ex_table,\"a\"\n" \ + " .align 3\n" \ + " .long 1b, 3b\n" \ + " .previous" \ + : "+r" (err), "=&r" (x) \ + : "r" (addr), "i" (-EFAULT) \ + : "cc") #ifdef __NDS32_EB__ #define __gu_reg_oper0 "%H1" @@ -149,61 +152,66 @@ do { \ #endif #define __get_user_asm_dword(x, addr, err) \ - asm volatile( \ - "\n1:\tlwi " __gu_reg_oper0 ",[%2]\n" \ - "\n2:\tlwi " __gu_reg_oper1 ",[%2+4]\n" \ - "3:\n" \ - " .section .fixup,\"ax\"\n" \ - " .align 2\n" \ - "4: move %0, %3\n" \ - " b 3b\n" \ - " .previous\n" \ - " .section __ex_table,\"a\"\n" \ - " .align 3\n" \ - " .long 1b, 4b\n" \ - " .long 2b, 4b\n" \ - " .previous" \ - : "+r"(err), "=&r"(x) \ - : "r"(addr), "i"(-EFAULT) \ - : "cc") -#define put_user(x,p) \ -({ \ - long __e = -EFAULT; \ - if(likely(access_ok(VERIFY_WRITE, p, sizeof(*p)))) { \ - __e = __put_user(x,p); \ - } \ - __e; \ -}) -#define __put_user(x,ptr) \ + __asm__ __volatile__ ( \ + "\n1:\tlwi " __gu_reg_oper0 ",[%2]\n" \ + "\n2:\tlwi " __gu_reg_oper1 ",[%2+4]\n" \ + "3:\n" \ + " .section .fixup,\"ax\"\n" \ + " .align 2\n" \ + "4: move %0, %3\n" \ + " b 3b\n" \ + " .previous\n" \ + " .section __ex_table,\"a\"\n" \ + " .align 3\n" \ + " .long 1b, 4b\n" \ + " .long 2b, 4b\n" \ + " .previous" \ + : "+r"(err), "=&r"(x) \ + : "r"(addr), "i"(-EFAULT) \ + : "cc") + +#define put_user __put_user \ + +#define __put_user(x, ptr) \ ({ \ long __pu_err = 0; \ - __put_user_err((x),(ptr),__pu_err); \ + __put_user_err((x), (ptr), __pu_err); \ __pu_err; \ }) -#define __put_user_error(x,ptr,err) \ +#define __put_user_error(x, ptr, err) \ +({ \ + __put_user_err((x), (ptr), (err)); \ + (void)0; \ +}) + +#define __put_user_check(x, ptr, err) \ ({ \ - __put_user_err((x),(ptr),err); \ - (void) 0; \ + __typeof__(*(ptr)) __user *__p = (ptr); \ + might_fault(); \ + if (access_ok(VERIFY_WRITE, __p, sizeof(*__p))) { \ + __put_user_err((x), __p, (err)); \ + } else { \ + (err) = -EFAULT; \ + } \ }) -#define __put_user_err(x,ptr,err) \ +#define __put_user_err(x, ptr, err) \ do { \ - unsigned long __pu_addr = (unsigned long)(ptr); \ __typeof__(*(ptr)) __pu_val = (x); \ __chk_user_ptr(ptr); \ switch (sizeof(*(ptr))) { \ case 1: \ - __put_user_asm("sbi",__pu_val,__pu_addr,err); \ + __put_user_asm("sbi", __pu_val, (ptr), (err)); \ break; \ case 2: \ - __put_user_asm("shi",__pu_val,__pu_addr,err); \ + __put_user_asm("shi", __pu_val, (ptr), (err)); \ break; \ case 4: \ - __put_user_asm("swi",__pu_val,__pu_addr,err); \ + __put_user_asm("swi", __pu_val, (ptr), (err)); \ break; \ case 8: \ - __put_user_asm_dword(__pu_val,__pu_addr,err); \ + __put_user_asm_dword(__pu_val, (ptr), (err)); \ break; \ default: \ BUILD_BUG(); \ @@ -211,22 +219,22 @@ do { \ } \ } while (0) -#define __put_user_asm(inst,x,addr,err) \ - asm volatile( \ - "1: "inst" %1,[%2]\n" \ - "2:\n" \ - " .section .fixup,\"ax\"\n" \ - " .align 2\n" \ - "3: move %0, %3\n" \ - " b 2b\n" \ - " .previous\n" \ - " .section __ex_table,\"a\"\n" \ - " .align 3\n" \ - " .long 1b, 3b\n" \ - " .previous" \ - : "+r" (err) \ - : "r" (x), "r" (addr), "i" (-EFAULT) \ - : "cc") +#define __put_user_asm(inst, x, addr, err) \ + __asm__ __volatile__ ( \ + "1: "inst" %1,[%2]\n" \ + "2:\n" \ + " .section .fixup,\"ax\"\n" \ + " .align 2\n" \ + "3: move %0, %3\n" \ + " b 2b\n" \ + " .previous\n" \ + " .section __ex_table,\"a\"\n" \ + " .align 3\n" \ + " .long 1b, 3b\n" \ + " .previous" \ + : "+r" (err) \ + : "r" (x), "r" (addr), "i" (-EFAULT) \ + : "cc") #ifdef __NDS32_EB__ #define __pu_reg_oper0 "%H2" @@ -237,23 +245,24 @@ do { \ #endif #define __put_user_asm_dword(x, addr, err) \ - asm volatile( \ - "\n1:\tswi " __pu_reg_oper0 ",[%1]\n" \ - "\n2:\tswi " __pu_reg_oper1 ",[%1+4]\n" \ - "3:\n" \ - " .section .fixup,\"ax\"\n" \ - " .align 2\n" \ - "4: move %0, %3\n" \ - " b 3b\n" \ - " .previous\n" \ - " .section __ex_table,\"a\"\n" \ - " .align 3\n" \ - " .long 1b, 4b\n" \ - " .long 2b, 4b\n" \ - " .previous" \ - : "+r"(err) \ - : "r"(addr), "r"(x), "i"(-EFAULT) \ - : "cc") + __asm__ __volatile__ ( \ + "\n1:\tswi " __pu_reg_oper0 ",[%1]\n" \ + "\n2:\tswi " __pu_reg_oper1 ",[%1+4]\n" \ + "3:\n" \ + " .section .fixup,\"ax\"\n" \ + " .align 2\n" \ + "4: move %0, %3\n" \ + " b 3b\n" \ + " .previous\n" \ + " .section __ex_table,\"a\"\n" \ + " .align 3\n" \ + " .long 1b, 4b\n" \ + " .long 2b, 4b\n" \ + " .previous" \ + : "+r"(err) \ + : "r"(addr), "r"(x), "i"(-EFAULT) \ + : "cc") + extern unsigned long __arch_clear_user(void __user * addr, unsigned long n); extern long strncpy_from_user(char *dest, const char __user * src, long count); extern __must_check long strlen_user(const char __user * str); diff --git a/arch/nds32/kernel/Makefile b/arch/nds32/kernel/Makefile index 42792743e8b9..27cded39fa66 100644 --- a/arch/nds32/kernel/Makefile +++ b/arch/nds32/kernel/Makefile @@ -21,3 +21,9 @@ extra-y := head.o vmlinux.lds obj-y += vdso/ + +obj-$(CONFIG_FUNCTION_TRACER) += ftrace.o + +ifdef CONFIG_FUNCTION_TRACER +CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE) +endif diff --git a/arch/nds32/kernel/atl2c.c b/arch/nds32/kernel/atl2c.c index 0c6d031a1c4a..0c5386e72098 100644 --- a/arch/nds32/kernel/atl2c.c +++ b/arch/nds32/kernel/atl2c.c @@ -9,7 +9,8 @@ void __iomem *atl2c_base; static const struct of_device_id atl2c_ids[] __initconst = { - {.compatible = "andestech,atl2c",} + {.compatible = "andestech,atl2c",}, + {} }; static int __init atl2c_of_init(void) diff --git a/arch/nds32/kernel/ex-entry.S b/arch/nds32/kernel/ex-entry.S index b8ae4e9a6b93..21a144071566 100644 --- a/arch/nds32/kernel/ex-entry.S +++ b/arch/nds32/kernel/ex-entry.S @@ -118,7 +118,7 @@ common_exception_handler: /* interrupt */ 2: #ifdef CONFIG_TRACE_IRQFLAGS - jal trace_hardirqs_off + jal __trace_hardirqs_off #endif move $r0, $sp sethi $lp, hi20(ret_from_intr) diff --git a/arch/nds32/kernel/ex-exit.S b/arch/nds32/kernel/ex-exit.S index 03e4f7788a18..f00af92f7e22 100644 --- a/arch/nds32/kernel/ex-exit.S +++ b/arch/nds32/kernel/ex-exit.S @@ -138,8 +138,8 @@ no_work_pending: #ifdef CONFIG_TRACE_IRQFLAGS lwi $p0, [$sp+(#IPSW_OFFSET)] andi $p0, $p0, #0x1 - la $r10, trace_hardirqs_off - la $r9, trace_hardirqs_on + la $r10, __trace_hardirqs_off + la $r9, __trace_hardirqs_on cmovz $r9, $p0, $r10 jral $r9 #endif diff --git a/arch/nds32/kernel/ftrace.c b/arch/nds32/kernel/ftrace.c new file mode 100644 index 000000000000..a0a9679ad5de --- /dev/null +++ b/arch/nds32/kernel/ftrace.c @@ -0,0 +1,309 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/ftrace.h> +#include <linux/uaccess.h> +#include <asm/cacheflush.h> + +#ifndef CONFIG_DYNAMIC_FTRACE +extern void (*ftrace_trace_function)(unsigned long, unsigned long, + struct ftrace_ops*, struct pt_regs*); +extern int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace); +extern void ftrace_graph_caller(void); + +noinline void __naked ftrace_stub(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs) +{ + __asm__ (""); /* avoid to optimize as pure function */ +} + +noinline void _mcount(unsigned long parent_ip) +{ + /* save all state by the compiler prologue */ + + unsigned long ip = (unsigned long)__builtin_return_address(0); + + if (ftrace_trace_function != ftrace_stub) + ftrace_trace_function(ip - MCOUNT_INSN_SIZE, parent_ip, + NULL, NULL); + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + if (ftrace_graph_return != (trace_func_graph_ret_t)ftrace_stub + || ftrace_graph_entry != ftrace_graph_entry_stub) + ftrace_graph_caller(); +#endif + + /* restore all state by the compiler epilogue */ +} +EXPORT_SYMBOL(_mcount); + +#else /* CONFIG_DYNAMIC_FTRACE */ + +noinline void __naked ftrace_stub(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs) +{ + __asm__ (""); /* avoid to optimize as pure function */ +} + +noinline void __naked _mcount(unsigned long parent_ip) +{ + __asm__ (""); /* avoid to optimize as pure function */ +} +EXPORT_SYMBOL(_mcount); + +#define XSTR(s) STR(s) +#define STR(s) #s +void _ftrace_caller(unsigned long parent_ip) +{ + /* save all state needed by the compiler prologue */ + + /* + * prepare arguments for real tracing function + * first arg : __builtin_return_address(0) - MCOUNT_INSN_SIZE + * second arg : parent_ip + */ + __asm__ __volatile__ ( + "move $r1, %0 \n\t" + "addi $r0, %1, #-" XSTR(MCOUNT_INSN_SIZE) "\n\t" + : + : "r" (parent_ip), "r" (__builtin_return_address(0))); + + /* a placeholder for the call to a real tracing function */ + __asm__ __volatile__ ( + "ftrace_call: \n\t" + "nop \n\t" + "nop \n\t" + "nop \n\t"); + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + /* a placeholder for the call to ftrace_graph_caller */ + __asm__ __volatile__ ( + "ftrace_graph_call: \n\t" + "nop \n\t" + "nop \n\t" + "nop \n\t"); +#endif + /* restore all state needed by the compiler epilogue */ +} + +int __init ftrace_dyn_arch_init(void) +{ + return 0; +} + +int ftrace_arch_code_modify_prepare(void) +{ + set_all_modules_text_rw(); + return 0; +} + +int ftrace_arch_code_modify_post_process(void) +{ + set_all_modules_text_ro(); + return 0; +} + +static unsigned long gen_sethi_insn(unsigned long addr) +{ + unsigned long opcode = 0x46000000; + unsigned long imm = addr >> 12; + unsigned long rt_num = 0xf << 20; + + return ENDIAN_CONVERT(opcode | rt_num | imm); +} + +static unsigned long gen_ori_insn(unsigned long addr) +{ + unsigned long opcode = 0x58000000; + unsigned long imm = addr & 0x0000fff; + unsigned long rt_num = 0xf << 20; + unsigned long ra_num = 0xf << 15; + + return ENDIAN_CONVERT(opcode | rt_num | ra_num | imm); +} + +static unsigned long gen_jral_insn(unsigned long addr) +{ + unsigned long opcode = 0x4a000001; + unsigned long rt_num = 0x1e << 20; + unsigned long rb_num = 0xf << 10; + + return ENDIAN_CONVERT(opcode | rt_num | rb_num); +} + +static void ftrace_gen_call_insn(unsigned long *call_insns, + unsigned long addr) +{ + call_insns[0] = gen_sethi_insn(addr); /* sethi $r15, imm20u */ + call_insns[1] = gen_ori_insn(addr); /* ori $r15, $r15, imm15u */ + call_insns[2] = gen_jral_insn(addr); /* jral $lp, $r15 */ +} + +static int __ftrace_modify_code(unsigned long pc, unsigned long *old_insn, + unsigned long *new_insn, bool validate) +{ + unsigned long orig_insn[3]; + + if (validate) { + if (probe_kernel_read(orig_insn, (void *)pc, MCOUNT_INSN_SIZE)) + return -EFAULT; + if (memcmp(orig_insn, old_insn, MCOUNT_INSN_SIZE)) + return -EINVAL; + } + + if (probe_kernel_write((void *)pc, new_insn, MCOUNT_INSN_SIZE)) + return -EPERM; + + return 0; +} + +static int ftrace_modify_code(unsigned long pc, unsigned long *old_insn, + unsigned long *new_insn, bool validate) +{ + int ret; + + ret = __ftrace_modify_code(pc, old_insn, new_insn, validate); + if (ret) + return ret; + + flush_icache_range(pc, pc + MCOUNT_INSN_SIZE); + + return ret; +} + +int ftrace_update_ftrace_func(ftrace_func_t func) +{ + unsigned long pc = (unsigned long)&ftrace_call; + unsigned long old_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP}; + unsigned long new_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP}; + + if (func != ftrace_stub) + ftrace_gen_call_insn(new_insn, (unsigned long)func); + + return ftrace_modify_code(pc, old_insn, new_insn, false); +} + +int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned long pc = rec->ip; + unsigned long nop_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP}; + unsigned long call_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP}; + + ftrace_gen_call_insn(call_insn, addr); + + return ftrace_modify_code(pc, nop_insn, call_insn, true); +} + +int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, + unsigned long addr) +{ + unsigned long pc = rec->ip; + unsigned long nop_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP}; + unsigned long call_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP}; + + ftrace_gen_call_insn(call_insn, addr); + + return ftrace_modify_code(pc, call_insn, nop_insn, true); +} +#endif /* CONFIG_DYNAMIC_FTRACE */ + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, + unsigned long frame_pointer) +{ + unsigned long return_hooker = (unsigned long)&return_to_handler; + struct ftrace_graph_ent trace; + unsigned long old; + int err; + + if (unlikely(atomic_read(¤t->tracing_graph_pause))) + return; + + old = *parent; + + trace.func = self_addr; + trace.depth = current->curr_ret_stack + 1; + + /* Only trace if the calling function expects to */ + if (!ftrace_graph_entry(&trace)) + return; + + err = ftrace_push_return_trace(old, self_addr, &trace.depth, + frame_pointer, NULL); + + if (err == -EBUSY) + return; + + *parent = return_hooker; +} + +noinline void ftrace_graph_caller(void) +{ + unsigned long *parent_ip = + (unsigned long *)(__builtin_frame_address(2) - 4); + + unsigned long selfpc = + (unsigned long)(__builtin_return_address(1) - MCOUNT_INSN_SIZE); + + unsigned long frame_pointer = + (unsigned long)__builtin_frame_address(3); + + prepare_ftrace_return(parent_ip, selfpc, frame_pointer); +} + +extern unsigned long ftrace_return_to_handler(unsigned long frame_pointer); +void __naked return_to_handler(void) +{ + __asm__ __volatile__ ( + /* save state needed by the ABI */ + "smw.adm $r0,[$sp],$r1,#0x0 \n\t" + + /* get original return address */ + "move $r0, $fp \n\t" + "bal ftrace_return_to_handler\n\t" + "move $lp, $r0 \n\t" + + /* restore state nedded by the ABI */ + "lmw.bim $r0,[$sp],$r1,#0x0 \n\t"); +} + +#ifdef CONFIG_DYNAMIC_FTRACE +extern unsigned long ftrace_graph_call; + +static int ftrace_modify_graph_caller(bool enable) +{ + unsigned long pc = (unsigned long)&ftrace_graph_call; + unsigned long nop_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP}; + unsigned long call_insn[3] = {INSN_NOP, INSN_NOP, INSN_NOP}; + + ftrace_gen_call_insn(call_insn, (unsigned long)ftrace_graph_caller); + + if (enable) + return ftrace_modify_code(pc, nop_insn, call_insn, true); + else + return ftrace_modify_code(pc, call_insn, nop_insn, true); +} + +int ftrace_enable_ftrace_graph_caller(void) +{ + return ftrace_modify_graph_caller(true); +} + +int ftrace_disable_ftrace_graph_caller(void) +{ + return ftrace_modify_graph_caller(false); +} +#endif /* CONFIG_DYNAMIC_FTRACE */ + +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ + + +#ifdef CONFIG_TRACE_IRQFLAGS +noinline void __trace_hardirqs_off(void) +{ + trace_hardirqs_off(); +} +noinline void __trace_hardirqs_on(void) +{ + trace_hardirqs_on(); +} +#endif /* CONFIG_TRACE_IRQFLAGS */ diff --git a/arch/nds32/kernel/module.c b/arch/nds32/kernel/module.c index 4167283d8293..1e31829cbc2a 100644 --- a/arch/nds32/kernel/module.c +++ b/arch/nds32/kernel/module.c @@ -40,7 +40,7 @@ void do_reloc16(unsigned int val, unsigned int *loc, unsigned int val_mask, tmp2 = tmp & loc_mask; if (partial_in_place) { - tmp &= (!loc_mask); + tmp &= (~loc_mask); tmp = tmp2 | ((tmp + ((val & val_mask) >> val_shift)) & val_mask); } else { @@ -70,7 +70,7 @@ void do_reloc32(unsigned int val, unsigned int *loc, unsigned int val_mask, tmp2 = tmp & loc_mask; if (partial_in_place) { - tmp &= (!loc_mask); + tmp &= (~loc_mask); tmp = tmp2 | ((tmp + ((val & val_mask) >> val_shift)) & val_mask); } else { diff --git a/arch/nds32/kernel/stacktrace.c b/arch/nds32/kernel/stacktrace.c index 8b231e910ea6..d974c0c1c65f 100644 --- a/arch/nds32/kernel/stacktrace.c +++ b/arch/nds32/kernel/stacktrace.c @@ -4,6 +4,7 @@ #include <linux/sched/debug.h> #include <linux/sched/task_stack.h> #include <linux/stacktrace.h> +#include <linux/ftrace.h> void save_stack_trace(struct stack_trace *trace) { @@ -16,6 +17,7 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) unsigned long *fpn; int skip = trace->skip; int savesched; + int graph_idx = 0; if (tsk == current) { __asm__ __volatile__("\tori\t%0, $fp, #0\n":"=r"(fpn)); @@ -29,10 +31,12 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) && (fpn >= (unsigned long *)TASK_SIZE)) { unsigned long lpp, fpp; - lpp = fpn[-1]; + lpp = fpn[LP_OFFSET]; fpp = fpn[FP_OFFSET]; if (!__kernel_text_address(lpp)) break; + else + lpp = ftrace_graph_ret_addr(tsk, &graph_idx, lpp, NULL); if (savesched || !in_sched_functions(lpp)) { if (skip) { diff --git a/arch/nds32/kernel/traps.c b/arch/nds32/kernel/traps.c index a6205fd4db52..1496aab48998 100644 --- a/arch/nds32/kernel/traps.c +++ b/arch/nds32/kernel/traps.c @@ -8,6 +8,7 @@ #include <linux/kdebug.h> #include <linux/sched/task_stack.h> #include <linux/uaccess.h> +#include <linux/ftrace.h> #include <asm/proc-fns.h> #include <asm/unistd.h> @@ -94,28 +95,6 @@ static void dump_instr(struct pt_regs *regs) set_fs(fs); } -#ifdef CONFIG_FUNCTION_GRAPH_TRACER -#include <linux/ftrace.h> -static void -get_real_ret_addr(unsigned long *addr, struct task_struct *tsk, int *graph) -{ - if (*addr == (unsigned long)return_to_handler) { - int index = tsk->curr_ret_stack; - - if (tsk->ret_stack && index >= *graph) { - index -= *graph; - *addr = tsk->ret_stack[index].ret; - (*graph)++; - } - } -} -#else -static inline void -get_real_ret_addr(unsigned long *addr, struct task_struct *tsk, int *graph) -{ -} -#endif - #define LOOP_TIMES (100) static void __dump(struct task_struct *tsk, unsigned long *base_reg) { @@ -126,7 +105,8 @@ static void __dump(struct task_struct *tsk, unsigned long *base_reg) while (!kstack_end(base_reg)) { ret_addr = *base_reg++; if (__kernel_text_address(ret_addr)) { - get_real_ret_addr(&ret_addr, tsk, &graph); + ret_addr = ftrace_graph_ret_addr( + tsk, &graph, ret_addr, NULL); print_ip_sym(ret_addr); } if (--cnt < 0) @@ -137,15 +117,12 @@ static void __dump(struct task_struct *tsk, unsigned long *base_reg) !((unsigned long)base_reg & 0x3) && ((unsigned long)base_reg >= TASK_SIZE)) { unsigned long next_fp; -#if !defined(NDS32_ABI_2) - ret_addr = base_reg[0]; - next_fp = base_reg[1]; -#else - ret_addr = base_reg[-1]; + ret_addr = base_reg[LP_OFFSET]; next_fp = base_reg[FP_OFFSET]; -#endif if (__kernel_text_address(ret_addr)) { - get_real_ret_addr(&ret_addr, tsk, &graph); + + ret_addr = ftrace_graph_ret_addr( + tsk, &graph, ret_addr, NULL); print_ip_sym(ret_addr); } if (--cnt < 0) @@ -196,11 +173,10 @@ void die(const char *str, struct pt_regs *regs, int err) pr_emerg("CPU: %i\n", smp_processor_id()); show_regs(regs); pr_emerg("Process %s (pid: %d, stack limit = 0x%p)\n", - tsk->comm, tsk->pid, task_thread_info(tsk) + 1); + tsk->comm, tsk->pid, end_of_stack(tsk)); if (!user_mode(regs) || in_interrupt()) { - dump_mem("Stack: ", regs->sp, - THREAD_SIZE + (unsigned long)task_thread_info(tsk)); + dump_mem("Stack: ", regs->sp, (regs->sp + PAGE_SIZE) & PAGE_MASK); dump_instr(regs); dump_stack(); } diff --git a/arch/nds32/kernel/vmlinux.lds.S b/arch/nds32/kernel/vmlinux.lds.S index 288313b886ef..9e90f30a181d 100644 --- a/arch/nds32/kernel/vmlinux.lds.S +++ b/arch/nds32/kernel/vmlinux.lds.S @@ -13,14 +13,26 @@ OUTPUT_ARCH(nds32) ENTRY(_stext_lma) jiffies = jiffies_64; +#if defined(CONFIG_GCOV_KERNEL) +#define NDS32_EXIT_KEEP(x) x +#else +#define NDS32_EXIT_KEEP(x) +#endif + SECTIONS { _stext_lma = TEXTADDR - LOAD_OFFSET; . = TEXTADDR; __init_begin = .; HEAD_TEXT_SECTION + .exit.text : { + NDS32_EXIT_KEEP(EXIT_TEXT) + } INIT_TEXT_SECTION(PAGE_SIZE) INIT_DATA_SECTION(16) + .exit.data : { + NDS32_EXIT_KEEP(EXIT_DATA) + } PERCPU_SECTION(L1_CACHE_BYTES) __init_end = .; diff --git a/arch/nios2/Kconfig.debug b/arch/nios2/Kconfig.debug index 7a49f0d28d14..f1da8a7b17ff 100644 --- a/arch/nios2/Kconfig.debug +++ b/arch/nios2/Kconfig.debug @@ -3,15 +3,6 @@ config TRACE_IRQFLAGS_SUPPORT def_bool y -config DEBUG_STACK_USAGE - bool "Enable stack utilization instrumentation" - depends on DEBUG_KERNEL - help - Enables the display of the minimum amount of free stack which each - task has ever had available in the sysrq-T and sysrq-P debug output. - - This option will slow down process creation somewhat. - config EARLY_PRINTK bool "Activate early kernel debugging" default y diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index db0b6eebbfa5..a80669209155 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -177,7 +177,6 @@ config PPC select HAVE_ARCH_KGDB select HAVE_ARCH_MMAP_RND_BITS select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT - select HAVE_ARCH_PREL32_RELOCATIONS select HAVE_ARCH_SECCOMP_FILTER select HAVE_ARCH_TRACEHOOK select HAVE_CBPF_JIT if !PPC64 diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c index 3c0e8fb2b773..68e14afecac8 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_hv.c +++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c @@ -358,7 +358,7 @@ static int kvmppc_mmu_book3s_64_hv_xlate(struct kvm_vcpu *vcpu, gva_t eaddr, unsigned long pp, key; unsigned long v, orig_v, gr; __be64 *hptep; - int index; + long int index; int virtmode = vcpu->arch.shregs.msr & (data ? MSR_DR : MSR_IR); if (kvm_is_radix(vcpu->kvm)) diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c index 0af1c0aea1fe..fd6e8c13685f 100644 --- a/arch/powerpc/kvm/book3s_64_mmu_radix.c +++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c @@ -725,10 +725,10 @@ int kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot, gpa, shift); kvmppc_radix_tlbie_page(kvm, gpa, shift); if ((old & _PAGE_DIRTY) && memslot->dirty_bitmap) { - unsigned long npages = 1; + unsigned long psize = PAGE_SIZE; if (shift) - npages = 1ul << (shift - PAGE_SHIFT); - kvmppc_update_dirty_map(memslot, gfn, npages); + psize = 1ul << shift; + kvmppc_update_dirty_map(memslot, gfn, psize); } } return 0; diff --git a/arch/riscv/include/asm/tlb.h b/arch/riscv/include/asm/tlb.h index c229509288ea..439dc7072e05 100644 --- a/arch/riscv/include/asm/tlb.h +++ b/arch/riscv/include/asm/tlb.h @@ -14,6 +14,10 @@ #ifndef _ASM_RISCV_TLB_H #define _ASM_RISCV_TLB_H +struct mmu_gather; + +static void tlb_flush(struct mmu_gather *tlb); + #include <asm-generic/tlb.h> static inline void tlb_flush(struct mmu_gather *tlb) diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index db20dc630e7e..aee603123030 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -85,15 +85,8 @@ atomic_t hart_lottery; #ifdef CONFIG_BLK_DEV_INITRD static void __init setup_initrd(void) { - extern char __initramfs_start[]; - extern unsigned long __initramfs_size; unsigned long size; - if (__initramfs_size > 0) { - initrd_start = (unsigned long)(&__initramfs_start); - initrd_end = initrd_start + __initramfs_size; - } - if (initrd_start >= initrd_end) { printk(KERN_INFO "initrd not found or empty"); goto disable; diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c index 568026ccf6e8..fb03a4482ad6 100644 --- a/arch/riscv/kernel/sys_riscv.c +++ b/arch/riscv/kernel/sys_riscv.c @@ -65,24 +65,11 @@ SYSCALL_DEFINE6(mmap2, unsigned long, addr, unsigned long, len, SYSCALL_DEFINE3(riscv_flush_icache, uintptr_t, start, uintptr_t, end, uintptr_t, flags) { -#ifdef CONFIG_SMP - struct mm_struct *mm = current->mm; - bool local = (flags & SYS_RISCV_FLUSH_ICACHE_LOCAL) != 0; -#endif - /* Check the reserved flags. */ if (unlikely(flags & ~SYS_RISCV_FLUSH_ICACHE_ALL)) return -EINVAL; - /* - * Without CONFIG_SMP flush_icache_mm is a just a flush_icache_all(), - * which generates unused variable warnings all over this function. - */ -#ifdef CONFIG_SMP - flush_icache_mm(mm, local); -#else - flush_icache_all(); -#endif + flush_icache_mm(current->mm, flags & SYS_RISCV_FLUSH_ICACHE_LOCAL); return 0; } diff --git a/arch/s390/crypto/paes_s390.c b/arch/s390/crypto/paes_s390.c index 80b27294c1de..ab9a0ebecc19 100644 --- a/arch/s390/crypto/paes_s390.c +++ b/arch/s390/crypto/paes_s390.c @@ -208,7 +208,7 @@ static int cbc_paes_crypt(struct blkcipher_desc *desc, unsigned long modifier, walk->dst.virt.addr, walk->src.virt.addr, n); if (k) ret = blkcipher_walk_done(desc, walk, nbytes - k); - if (n < k) { + if (k < n) { if (__cbc_paes_set_key(ctx) != 0) return blkcipher_walk_done(desc, walk, -EIO); memcpy(param.key, ctx->pk.protkey, MAXPROTKEYSIZE); diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h index f31a15044c24..a8418e1379eb 100644 --- a/arch/s390/include/asm/mmu.h +++ b/arch/s390/include/asm/mmu.h @@ -16,7 +16,13 @@ typedef struct { unsigned long asce; unsigned long asce_limit; unsigned long vdso_base; - /* The mmu context allocates 4K page tables. */ + /* + * The following bitfields need a down_write on the mm + * semaphore when they are written to. As they are only + * written once, they can be read without a lock. + * + * The mmu context allocates 4K page tables. + */ unsigned int alloc_pgste:1; /* The mmu context uses extended page tables. */ unsigned int has_pgste:1; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index 91ad4a9425c0..f69333fd2fa3 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -695,7 +695,9 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) r = -EINVAL; else { r = 0; + down_write(&kvm->mm->mmap_sem); kvm->mm->context.allow_gmap_hpage_1m = 1; + up_write(&kvm->mm->mmap_sem); /* * We might have to create fake 4k page * tables. To avoid that the hardware works on diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index d68f10441a16..8679bd74d337 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -280,9 +280,11 @@ retry: goto retry; } } - if (rc) - return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); up_read(¤t->mm->mmap_sem); + if (rc == -EFAULT) + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + if (rc < 0) + return rc; vcpu->run->s.regs.gprs[reg1] &= ~0xff; vcpu->run->s.regs.gprs[reg1] |= key; return 0; @@ -324,9 +326,11 @@ retry: goto retry; } } - if (rc < 0) - return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); up_read(¤t->mm->mmap_sem); + if (rc == -EFAULT) + return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + if (rc < 0) + return rc; kvm_s390_set_psw_cc(vcpu, rc); return 0; } @@ -390,12 +394,12 @@ static int handle_sske(struct kvm_vcpu *vcpu) FAULT_FLAG_WRITE, &unlocked); rc = !rc ? -EAGAIN : rc; } + up_read(¤t->mm->mmap_sem); if (rc == -EFAULT) return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); - - up_read(¤t->mm->mmap_sem); - if (rc >= 0) - start += PAGE_SIZE; + if (rc < 0) + return rc; + start += PAGE_SIZE; } if (m3 & (SSKE_MC | SSKE_MR)) { @@ -1002,13 +1006,15 @@ static int handle_pfmf(struct kvm_vcpu *vcpu) FAULT_FLAG_WRITE, &unlocked); rc = !rc ? -EAGAIN : rc; } + up_read(¤t->mm->mmap_sem); if (rc == -EFAULT) return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); - - up_read(¤t->mm->mmap_sem); - if (rc >= 0) - start += PAGE_SIZE; + if (rc == -EAGAIN) + continue; + if (rc < 0) + return rc; } + start += PAGE_SIZE; } if (vcpu->run->s.regs.gprs[reg1] & PFMF_FSC) { if (psw_bits(vcpu->arch.sie_block->gpsw).eaba == PSW_BITS_AMODE_64BIT) { diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index 63844b95c22c..a2b28cd1e3fe 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -173,7 +173,8 @@ static int shadow_crycb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) return set_validity_icpt(scb_s, 0x0039U); /* copy only the wrapping keys */ - if (read_guest_real(vcpu, crycb_addr + 72, &vsie_page->crycb, 56)) + if (read_guest_real(vcpu, crycb_addr + 72, + vsie_page->crycb.dea_wrapping_key_mask, 56)) return set_validity_icpt(scb_s, 0x0035U); scb_s->ecb3 |= ecb3_flags; diff --git a/arch/sparc/kernel/of_device_32.c b/arch/sparc/kernel/of_device_32.c index 3641a294ed54..e4abe9b8f97a 100644 --- a/arch/sparc/kernel/of_device_32.c +++ b/arch/sparc/kernel/of_device_32.c @@ -9,6 +9,7 @@ #include <linux/irq.h> #include <linux/of_device.h> #include <linux/of_platform.h> +#include <linux/dma-mapping.h> #include <asm/leon.h> #include <asm/leon_amba.h> @@ -381,6 +382,9 @@ static struct platform_device * __init scan_one_device(struct device_node *dp, else dev_set_name(&op->dev, "%08x", dp->phandle); + op->dev.coherent_dma_mask = DMA_BIT_MASK(32); + op->dev.dma_mask = &op->dev.coherent_dma_mask; + if (of_device_register(op)) { printk("%s: Could not register of device.\n", dp->full_name); diff --git a/arch/sparc/kernel/of_device_64.c b/arch/sparc/kernel/of_device_64.c index 44e4d4435bed..6df6086968c6 100644 --- a/arch/sparc/kernel/of_device_64.c +++ b/arch/sparc/kernel/of_device_64.c @@ -2,6 +2,7 @@ #include <linux/string.h> #include <linux/kernel.h> #include <linux/of.h> +#include <linux/dma-mapping.h> #include <linux/init.h> #include <linux/export.h> #include <linux/mod_devicetable.h> @@ -675,6 +676,8 @@ static struct platform_device * __init scan_one_device(struct device_node *dp, dev_set_name(&op->dev, "root"); else dev_set_name(&op->dev, "%08x", dp->phandle); + op->dev.coherent_dma_mask = DMA_BIT_MASK(32); + op->dev.dma_mask = &op->dev.coherent_dma_mask; if (of_device_register(op)) { printk("%s: Could not register of device.\n", diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index c5ff296bc5d1..1a0be022f91d 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2843,7 +2843,7 @@ config X86_SYSFB This option, if enabled, marks VGA/VBE/EFI framebuffers as generic framebuffers so the new generic system-framebuffer drivers can be used on x86. If the framebuffer is not compatible with the generic - modes, it is adverticed as fallback platform framebuffer so legacy + modes, it is advertised as fallback platform framebuffer so legacy drivers like efifb, vesafb and uvesafb can pick it up. If this option is not selected, all system framebuffers are always marked as fallback platform framebuffers as usual. diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 94859241bc3e..8f6e7eb8ae9f 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -175,22 +175,6 @@ ifdef CONFIG_FUNCTION_GRAPH_TRACER endif endif -ifndef CC_HAVE_ASM_GOTO - $(error Compiler lacks asm-goto support.) -endif - -# -# Jump labels need '-maccumulate-outgoing-args' for gcc < 4.5.2 to prevent a -# GCC bug (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=46226). There's no way -# to test for this bug at compile-time because the test case needs to execute, -# which is a no-go for cross compilers. So check the GCC version instead. -# -ifdef CONFIG_JUMP_LABEL - ifneq ($(ACCUMULATE_OUTGOING_ARGS), 1) - ACCUMULATE_OUTGOING_ARGS = $(call cc-if-fullversion, -lt, 040502, 1) - endif -endif - ifeq ($(ACCUMULATE_OUTGOING_ARGS), 1) # This compiler flag is not supported by Clang: KBUILD_CFLAGS += $(call cc-option,-maccumulate-outgoing-args,) @@ -312,6 +296,13 @@ PHONY += vdso_install vdso_install: $(Q)$(MAKE) $(build)=arch/x86/entry/vdso $@ +archprepare: checkbin +checkbin: +ifndef CC_HAVE_ASM_GOTO + @echo Compiler lacks asm-goto support. + @exit 1 +endif + archclean: $(Q)rm -rf $(objtree)/arch/i386 $(Q)rm -rf $(objtree)/arch/x86_64 diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S index 9bd139569b41..cb2deb61c5d9 100644 --- a/arch/x86/crypto/aesni-intel_asm.S +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -223,34 +223,34 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff pcmpeqd TWOONE(%rip), \TMP2 pand POLY(%rip), \TMP2 pxor \TMP2, \TMP3 - movdqa \TMP3, HashKey(%arg2) + movdqu \TMP3, HashKey(%arg2) movdqa \TMP3, \TMP5 pshufd $78, \TMP3, \TMP1 pxor \TMP3, \TMP1 - movdqa \TMP1, HashKey_k(%arg2) + movdqu \TMP1, HashKey_k(%arg2) GHASH_MUL \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7 # TMP5 = HashKey^2<<1 (mod poly) - movdqa \TMP5, HashKey_2(%arg2) + movdqu \TMP5, HashKey_2(%arg2) # HashKey_2 = HashKey^2<<1 (mod poly) pshufd $78, \TMP5, \TMP1 pxor \TMP5, \TMP1 - movdqa \TMP1, HashKey_2_k(%arg2) + movdqu \TMP1, HashKey_2_k(%arg2) GHASH_MUL \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7 # TMP5 = HashKey^3<<1 (mod poly) - movdqa \TMP5, HashKey_3(%arg2) + movdqu \TMP5, HashKey_3(%arg2) pshufd $78, \TMP5, \TMP1 pxor \TMP5, \TMP1 - movdqa \TMP1, HashKey_3_k(%arg2) + movdqu \TMP1, HashKey_3_k(%arg2) GHASH_MUL \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7 # TMP5 = HashKey^3<<1 (mod poly) - movdqa \TMP5, HashKey_4(%arg2) + movdqu \TMP5, HashKey_4(%arg2) pshufd $78, \TMP5, \TMP1 pxor \TMP5, \TMP1 - movdqa \TMP1, HashKey_4_k(%arg2) + movdqu \TMP1, HashKey_4_k(%arg2) .endm # GCM_INIT initializes a gcm_context struct to prepare for encoding/decoding. @@ -271,7 +271,7 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff movdqu %xmm0, CurCount(%arg2) # ctx_data.current_counter = iv PRECOMPUTE \SUBKEY, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, - movdqa HashKey(%arg2), %xmm13 + movdqu HashKey(%arg2), %xmm13 CALC_AAD_HASH %xmm13, \AAD, \AADLEN, %xmm0, %xmm1, %xmm2, %xmm3, \ %xmm4, %xmm5, %xmm6 @@ -997,7 +997,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation pshufd $78, \XMM5, \TMP6 pxor \XMM5, \TMP6 paddd ONE(%rip), \XMM0 # INCR CNT - movdqa HashKey_4(%arg2), \TMP5 + movdqu HashKey_4(%arg2), \TMP5 PCLMULQDQ 0x11, \TMP5, \TMP4 # TMP4 = a1*b1 movdqa \XMM0, \XMM1 paddd ONE(%rip), \XMM0 # INCR CNT @@ -1016,7 +1016,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation pxor (%arg1), \XMM2 pxor (%arg1), \XMM3 pxor (%arg1), \XMM4 - movdqa HashKey_4_k(%arg2), \TMP5 + movdqu HashKey_4_k(%arg2), \TMP5 PCLMULQDQ 0x00, \TMP5, \TMP6 # TMP6 = (a1+a0)*(b1+b0) movaps 0x10(%arg1), \TMP1 AESENC \TMP1, \XMM1 # Round 1 @@ -1031,7 +1031,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation movdqa \XMM6, \TMP1 pshufd $78, \XMM6, \TMP2 pxor \XMM6, \TMP2 - movdqa HashKey_3(%arg2), \TMP5 + movdqu HashKey_3(%arg2), \TMP5 PCLMULQDQ 0x11, \TMP5, \TMP1 # TMP1 = a1 * b1 movaps 0x30(%arg1), \TMP3 AESENC \TMP3, \XMM1 # Round 3 @@ -1044,7 +1044,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation AESENC \TMP3, \XMM2 AESENC \TMP3, \XMM3 AESENC \TMP3, \XMM4 - movdqa HashKey_3_k(%arg2), \TMP5 + movdqu HashKey_3_k(%arg2), \TMP5 PCLMULQDQ 0x00, \TMP5, \TMP2 # TMP2 = (a1+a0)*(b1+b0) movaps 0x50(%arg1), \TMP3 AESENC \TMP3, \XMM1 # Round 5 @@ -1058,7 +1058,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation movdqa \XMM7, \TMP1 pshufd $78, \XMM7, \TMP2 pxor \XMM7, \TMP2 - movdqa HashKey_2(%arg2), \TMP5 + movdqu HashKey_2(%arg2), \TMP5 # Multiply TMP5 * HashKey using karatsuba @@ -1074,7 +1074,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation AESENC \TMP3, \XMM2 AESENC \TMP3, \XMM3 AESENC \TMP3, \XMM4 - movdqa HashKey_2_k(%arg2), \TMP5 + movdqu HashKey_2_k(%arg2), \TMP5 PCLMULQDQ 0x00, \TMP5, \TMP2 # TMP2 = (a1+a0)*(b1+b0) movaps 0x80(%arg1), \TMP3 AESENC \TMP3, \XMM1 # Round 8 @@ -1092,7 +1092,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation movdqa \XMM8, \TMP1 pshufd $78, \XMM8, \TMP2 pxor \XMM8, \TMP2 - movdqa HashKey(%arg2), \TMP5 + movdqu HashKey(%arg2), \TMP5 PCLMULQDQ 0x11, \TMP5, \TMP1 # TMP1 = a1*b1 movaps 0x90(%arg1), \TMP3 AESENC \TMP3, \XMM1 # Round 9 @@ -1121,7 +1121,7 @@ aes_loop_par_enc_done\@: AESENCLAST \TMP3, \XMM2 AESENCLAST \TMP3, \XMM3 AESENCLAST \TMP3, \XMM4 - movdqa HashKey_k(%arg2), \TMP5 + movdqu HashKey_k(%arg2), \TMP5 PCLMULQDQ 0x00, \TMP5, \TMP2 # TMP2 = (a1+a0)*(b1+b0) movdqu (%arg4,%r11,1), \TMP3 pxor \TMP3, \XMM1 # Ciphertext/Plaintext XOR EK @@ -1205,7 +1205,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation pshufd $78, \XMM5, \TMP6 pxor \XMM5, \TMP6 paddd ONE(%rip), \XMM0 # INCR CNT - movdqa HashKey_4(%arg2), \TMP5 + movdqu HashKey_4(%arg2), \TMP5 PCLMULQDQ 0x11, \TMP5, \TMP4 # TMP4 = a1*b1 movdqa \XMM0, \XMM1 paddd ONE(%rip), \XMM0 # INCR CNT @@ -1224,7 +1224,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation pxor (%arg1), \XMM2 pxor (%arg1), \XMM3 pxor (%arg1), \XMM4 - movdqa HashKey_4_k(%arg2), \TMP5 + movdqu HashKey_4_k(%arg2), \TMP5 PCLMULQDQ 0x00, \TMP5, \TMP6 # TMP6 = (a1+a0)*(b1+b0) movaps 0x10(%arg1), \TMP1 AESENC \TMP1, \XMM1 # Round 1 @@ -1239,7 +1239,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation movdqa \XMM6, \TMP1 pshufd $78, \XMM6, \TMP2 pxor \XMM6, \TMP2 - movdqa HashKey_3(%arg2), \TMP5 + movdqu HashKey_3(%arg2), \TMP5 PCLMULQDQ 0x11, \TMP5, \TMP1 # TMP1 = a1 * b1 movaps 0x30(%arg1), \TMP3 AESENC \TMP3, \XMM1 # Round 3 @@ -1252,7 +1252,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation AESENC \TMP3, \XMM2 AESENC \TMP3, \XMM3 AESENC \TMP3, \XMM4 - movdqa HashKey_3_k(%arg2), \TMP5 + movdqu HashKey_3_k(%arg2), \TMP5 PCLMULQDQ 0x00, \TMP5, \TMP2 # TMP2 = (a1+a0)*(b1+b0) movaps 0x50(%arg1), \TMP3 AESENC \TMP3, \XMM1 # Round 5 @@ -1266,7 +1266,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation movdqa \XMM7, \TMP1 pshufd $78, \XMM7, \TMP2 pxor \XMM7, \TMP2 - movdqa HashKey_2(%arg2), \TMP5 + movdqu HashKey_2(%arg2), \TMP5 # Multiply TMP5 * HashKey using karatsuba @@ -1282,7 +1282,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation AESENC \TMP3, \XMM2 AESENC \TMP3, \XMM3 AESENC \TMP3, \XMM4 - movdqa HashKey_2_k(%arg2), \TMP5 + movdqu HashKey_2_k(%arg2), \TMP5 PCLMULQDQ 0x00, \TMP5, \TMP2 # TMP2 = (a1+a0)*(b1+b0) movaps 0x80(%arg1), \TMP3 AESENC \TMP3, \XMM1 # Round 8 @@ -1300,7 +1300,7 @@ TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation movdqa \XMM8, \TMP1 pshufd $78, \XMM8, \TMP2 pxor \XMM8, \TMP2 - movdqa HashKey(%arg2), \TMP5 + movdqu HashKey(%arg2), \TMP5 PCLMULQDQ 0x11, \TMP5, \TMP1 # TMP1 = a1*b1 movaps 0x90(%arg1), \TMP3 AESENC \TMP3, \XMM1 # Round 9 @@ -1329,7 +1329,7 @@ aes_loop_par_dec_done\@: AESENCLAST \TMP3, \XMM2 AESENCLAST \TMP3, \XMM3 AESENCLAST \TMP3, \XMM4 - movdqa HashKey_k(%arg2), \TMP5 + movdqu HashKey_k(%arg2), \TMP5 PCLMULQDQ 0x00, \TMP5, \TMP2 # TMP2 = (a1+a0)*(b1+b0) movdqu (%arg4,%r11,1), \TMP3 pxor \TMP3, \XMM1 # Ciphertext/Plaintext XOR EK @@ -1405,10 +1405,10 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst movdqa \XMM1, \TMP6 pshufd $78, \XMM1, \TMP2 pxor \XMM1, \TMP2 - movdqa HashKey_4(%arg2), \TMP5 + movdqu HashKey_4(%arg2), \TMP5 PCLMULQDQ 0x11, \TMP5, \TMP6 # TMP6 = a1*b1 PCLMULQDQ 0x00, \TMP5, \XMM1 # XMM1 = a0*b0 - movdqa HashKey_4_k(%arg2), \TMP4 + movdqu HashKey_4_k(%arg2), \TMP4 PCLMULQDQ 0x00, \TMP4, \TMP2 # TMP2 = (a1+a0)*(b1+b0) movdqa \XMM1, \XMMDst movdqa \TMP2, \XMM1 # result in TMP6, XMMDst, XMM1 @@ -1418,10 +1418,10 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst movdqa \XMM2, \TMP1 pshufd $78, \XMM2, \TMP2 pxor \XMM2, \TMP2 - movdqa HashKey_3(%arg2), \TMP5 + movdqu HashKey_3(%arg2), \TMP5 PCLMULQDQ 0x11, \TMP5, \TMP1 # TMP1 = a1*b1 PCLMULQDQ 0x00, \TMP5, \XMM2 # XMM2 = a0*b0 - movdqa HashKey_3_k(%arg2), \TMP4 + movdqu HashKey_3_k(%arg2), \TMP4 PCLMULQDQ 0x00, \TMP4, \TMP2 # TMP2 = (a1+a0)*(b1+b0) pxor \TMP1, \TMP6 pxor \XMM2, \XMMDst @@ -1433,10 +1433,10 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst movdqa \XMM3, \TMP1 pshufd $78, \XMM3, \TMP2 pxor \XMM3, \TMP2 - movdqa HashKey_2(%arg2), \TMP5 + movdqu HashKey_2(%arg2), \TMP5 PCLMULQDQ 0x11, \TMP5, \TMP1 # TMP1 = a1*b1 PCLMULQDQ 0x00, \TMP5, \XMM3 # XMM3 = a0*b0 - movdqa HashKey_2_k(%arg2), \TMP4 + movdqu HashKey_2_k(%arg2), \TMP4 PCLMULQDQ 0x00, \TMP4, \TMP2 # TMP2 = (a1+a0)*(b1+b0) pxor \TMP1, \TMP6 pxor \XMM3, \XMMDst @@ -1446,10 +1446,10 @@ TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst movdqa \XMM4, \TMP1 pshufd $78, \XMM4, \TMP2 pxor \XMM4, \TMP2 - movdqa HashKey(%arg2), \TMP5 + movdqu HashKey(%arg2), \TMP5 PCLMULQDQ 0x11, \TMP5, \TMP1 # TMP1 = a1*b1 PCLMULQDQ 0x00, \TMP5, \XMM4 # XMM4 = a0*b0 - movdqa HashKey_k(%arg2), \TMP4 + movdqu HashKey_k(%arg2), \TMP4 PCLMULQDQ 0x00, \TMP4, \TMP2 # TMP2 = (a1+a0)*(b1+b0) pxor \TMP1, \TMP6 pxor \XMM4, \XMMDst diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 5f4829f10129..dfb2f7c0d019 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2465,7 +2465,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs perf_callchain_store(entry, regs->ip); - if (!current->mm) + if (!nmi_uaccess_okay()) return; if (perf_callchain_user32(regs, entry)) diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index f3e006bed9a7..c88ed39582a1 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -1272,4 +1272,8 @@ void intel_pmu_lbr_init_knl(void) x86_pmu.lbr_sel_mask = LBR_SEL_MASK; x86_pmu.lbr_sel_map = snb_lbr_sel_map; + + /* Knights Landing does have MISPREDICT bit */ + if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_LIP) + x86_pmu.intel_cap.lbr_format = LBR_FORMAT_EIP_FLAGS; } diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index b143717b92b3..ce84388e540c 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -80,11 +80,11 @@ static __always_inline void arch_atomic_sub(int i, atomic_t *v) * true if the result is zero, or false for all * other cases. */ -#define arch_atomic_sub_and_test arch_atomic_sub_and_test static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", e); } +#define arch_atomic_sub_and_test arch_atomic_sub_and_test /** * arch_atomic_inc - increment atomic variable @@ -92,12 +92,12 @@ static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v) * * Atomically increments @v by 1. */ -#define arch_atomic_inc arch_atomic_inc static __always_inline void arch_atomic_inc(atomic_t *v) { asm volatile(LOCK_PREFIX "incl %0" : "+m" (v->counter)); } +#define arch_atomic_inc arch_atomic_inc /** * arch_atomic_dec - decrement atomic variable @@ -105,12 +105,12 @@ static __always_inline void arch_atomic_inc(atomic_t *v) * * Atomically decrements @v by 1. */ -#define arch_atomic_dec arch_atomic_dec static __always_inline void arch_atomic_dec(atomic_t *v) { asm volatile(LOCK_PREFIX "decl %0" : "+m" (v->counter)); } +#define arch_atomic_dec arch_atomic_dec /** * arch_atomic_dec_and_test - decrement and test @@ -120,11 +120,11 @@ static __always_inline void arch_atomic_dec(atomic_t *v) * returns true if the result is 0, or false for all other * cases. */ -#define arch_atomic_dec_and_test arch_atomic_dec_and_test static __always_inline bool arch_atomic_dec_and_test(atomic_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", e); } +#define arch_atomic_dec_and_test arch_atomic_dec_and_test /** * arch_atomic_inc_and_test - increment and test @@ -134,11 +134,11 @@ static __always_inline bool arch_atomic_dec_and_test(atomic_t *v) * and returns true if the result is zero, or false for all * other cases. */ -#define arch_atomic_inc_and_test arch_atomic_inc_and_test static __always_inline bool arch_atomic_inc_and_test(atomic_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", e); } +#define arch_atomic_inc_and_test arch_atomic_inc_and_test /** * arch_atomic_add_negative - add and test if negative @@ -149,11 +149,11 @@ static __always_inline bool arch_atomic_inc_and_test(atomic_t *v) * if the result is negative, or false when * result is greater than or equal to zero. */ -#define arch_atomic_add_negative arch_atomic_add_negative static __always_inline bool arch_atomic_add_negative(int i, atomic_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", s); } +#define arch_atomic_add_negative arch_atomic_add_negative /** * arch_atomic_add_return - add integer and return diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h index ef959f02d070..6a5b0ec460da 100644 --- a/arch/x86/include/asm/atomic64_32.h +++ b/arch/x86/include/asm/atomic64_32.h @@ -205,12 +205,12 @@ static inline long long arch_atomic64_sub(long long i, atomic64_t *v) * * Atomically increments @v by 1. */ -#define arch_atomic64_inc arch_atomic64_inc static inline void arch_atomic64_inc(atomic64_t *v) { __alternative_atomic64(inc, inc_return, /* no output */, "S" (v) : "memory", "eax", "ecx", "edx"); } +#define arch_atomic64_inc arch_atomic64_inc /** * arch_atomic64_dec - decrement atomic64 variable @@ -218,12 +218,12 @@ static inline void arch_atomic64_inc(atomic64_t *v) * * Atomically decrements @v by 1. */ -#define arch_atomic64_dec arch_atomic64_dec static inline void arch_atomic64_dec(atomic64_t *v) { __alternative_atomic64(dec, dec_return, /* no output */, "S" (v) : "memory", "eax", "ecx", "edx"); } +#define arch_atomic64_dec arch_atomic64_dec /** * arch_atomic64_add_unless - add unless the number is a given value @@ -245,7 +245,6 @@ static inline int arch_atomic64_add_unless(atomic64_t *v, long long a, return (int)a; } -#define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero static inline int arch_atomic64_inc_not_zero(atomic64_t *v) { int r; @@ -253,8 +252,8 @@ static inline int arch_atomic64_inc_not_zero(atomic64_t *v) "S" (v) : "ecx", "edx", "memory"); return r; } +#define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero -#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive static inline long long arch_atomic64_dec_if_positive(atomic64_t *v) { long long r; @@ -262,6 +261,7 @@ static inline long long arch_atomic64_dec_if_positive(atomic64_t *v) "S" (v) : "ecx", "memory"); return r; } +#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive #undef alternative_atomic64 #undef __alternative_atomic64 diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h index 4343d9b4f30e..5f851d92eecd 100644 --- a/arch/x86/include/asm/atomic64_64.h +++ b/arch/x86/include/asm/atomic64_64.h @@ -71,11 +71,11 @@ static inline void arch_atomic64_sub(long i, atomic64_t *v) * true if the result is zero, or false for all * other cases. */ -#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, "er", i, "%0", e); } +#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test /** * arch_atomic64_inc - increment atomic64 variable @@ -83,13 +83,13 @@ static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v) * * Atomically increments @v by 1. */ -#define arch_atomic64_inc arch_atomic64_inc static __always_inline void arch_atomic64_inc(atomic64_t *v) { asm volatile(LOCK_PREFIX "incq %0" : "=m" (v->counter) : "m" (v->counter)); } +#define arch_atomic64_inc arch_atomic64_inc /** * arch_atomic64_dec - decrement atomic64 variable @@ -97,13 +97,13 @@ static __always_inline void arch_atomic64_inc(atomic64_t *v) * * Atomically decrements @v by 1. */ -#define arch_atomic64_dec arch_atomic64_dec static __always_inline void arch_atomic64_dec(atomic64_t *v) { asm volatile(LOCK_PREFIX "decq %0" : "=m" (v->counter) : "m" (v->counter)); } +#define arch_atomic64_dec arch_atomic64_dec /** * arch_atomic64_dec_and_test - decrement and test @@ -113,11 +113,11 @@ static __always_inline void arch_atomic64_dec(atomic64_t *v) * returns true if the result is 0, or false for all other * cases. */ -#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test static inline bool arch_atomic64_dec_and_test(atomic64_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", e); } +#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test /** * arch_atomic64_inc_and_test - increment and test @@ -127,11 +127,11 @@ static inline bool arch_atomic64_dec_and_test(atomic64_t *v) * and returns true if the result is zero, or false for all * other cases. */ -#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test static inline bool arch_atomic64_inc_and_test(atomic64_t *v) { GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", e); } +#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test /** * arch_atomic64_add_negative - add and test if negative @@ -142,11 +142,11 @@ static inline bool arch_atomic64_inc_and_test(atomic64_t *v) * if the result is negative, or false when * result is greater than or equal to zero. */ -#define arch_atomic64_add_negative arch_atomic64_add_negative static inline bool arch_atomic64_add_negative(long i, atomic64_t *v) { GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", s); } +#define arch_atomic64_add_negative arch_atomic64_add_negative /** * arch_atomic64_add_return - add and return diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h index c14f2a74b2be..15450a675031 100644 --- a/arch/x86/include/asm/irqflags.h +++ b/arch/x86/include/asm/irqflags.h @@ -33,7 +33,8 @@ extern inline unsigned long native_save_fl(void) return flags; } -static inline void native_restore_fl(unsigned long flags) +extern inline void native_restore_fl(unsigned long flags); +extern inline void native_restore_fl(unsigned long flags) { asm volatile("push %0 ; popf" : /* no output */ diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h index 395c9631e000..75f1e35e7c15 100644 --- a/arch/x86/include/asm/kdebug.h +++ b/arch/x86/include/asm/kdebug.h @@ -22,10 +22,20 @@ enum die_val { DIE_NMIUNKNOWN, }; +enum show_regs_mode { + SHOW_REGS_SHORT, + /* + * For when userspace crashed, but we don't think it's our fault, and + * therefore don't print kernel registers. + */ + SHOW_REGS_USER, + SHOW_REGS_ALL +}; + extern void die(const char *, struct pt_regs *,long); extern int __must_check __die(const char *, struct pt_regs *, long); extern void show_stack_regs(struct pt_regs *regs); -extern void __show_regs(struct pt_regs *regs, int all); +extern void __show_regs(struct pt_regs *regs, enum show_regs_mode); extern void show_iret_regs(struct pt_regs *regs); extern unsigned long oops_begin(void); extern void oops_end(unsigned long, struct pt_regs *, int signr); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 00ddb0c9e612..8e90488c3d56 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1237,19 +1237,12 @@ enum emulation_result { #define EMULTYPE_NO_DECODE (1 << 0) #define EMULTYPE_TRAP_UD (1 << 1) #define EMULTYPE_SKIP (1 << 2) -#define EMULTYPE_RETRY (1 << 3) -#define EMULTYPE_NO_REEXECUTE (1 << 4) -#define EMULTYPE_NO_UD_ON_FAIL (1 << 5) -#define EMULTYPE_VMWARE (1 << 6) -int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2, - int emulation_type, void *insn, int insn_len); - -static inline int emulate_instruction(struct kvm_vcpu *vcpu, - int emulation_type) -{ - return x86_emulate_instruction(vcpu, 0, - emulation_type | EMULTYPE_NO_REEXECUTE, NULL, 0); -} +#define EMULTYPE_ALLOW_RETRY (1 << 3) +#define EMULTYPE_NO_UD_ON_FAIL (1 << 4) +#define EMULTYPE_VMWARE (1 << 5) +int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type); +int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu, + void *insn, int insn_len); void kvm_enable_efer_bits(u64); bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer); @@ -1450,7 +1443,6 @@ asmlinkage void kvm_spurious_fault(void); ____kvm_handle_fault_on_reboot(insn, "") #define KVM_ARCH_WANT_MMU_NOTIFIER -int kvm_unmap_hva(struct kvm *kvm, unsigned long hva); int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end); int kvm_test_age_hva(struct kvm *kvm, unsigned long hva); @@ -1463,7 +1455,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event); void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu); int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low, - unsigned long ipi_bitmap_high, int min, + unsigned long ipi_bitmap_high, u32 min, unsigned long icr, int op_64_bit); u64 kvm_get_arch_capabilities(void); diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h index 24c6cf5f16b7..60d0f9015317 100644 --- a/arch/x86/include/asm/pgtable-2level.h +++ b/arch/x86/include/asm/pgtable-2level.h @@ -19,9 +19,6 @@ static inline void native_set_pte(pte_t *ptep , pte_t pte) static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd) { -#ifdef CONFIG_PAGE_TABLE_ISOLATION - pmd.pud.p4d.pgd = pti_set_user_pgtbl(&pmdp->pud.p4d.pgd, pmd.pud.p4d.pgd); -#endif *pmdp = pmd; } @@ -61,9 +58,6 @@ static inline pte_t native_ptep_get_and_clear(pte_t *xp) #ifdef CONFIG_SMP static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp) { -#ifdef CONFIG_PAGE_TABLE_ISOLATION - pti_set_user_pgtbl(&xp->pud.p4d.pgd, __pgd(0)); -#endif return __pmd(xchg((pmdval_t *)xp, 0)); } #else @@ -73,9 +67,6 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp) #ifdef CONFIG_SMP static inline pud_t native_pudp_get_and_clear(pud_t *xp) { -#ifdef CONFIG_PAGE_TABLE_ISOLATION - pti_set_user_pgtbl(&xp->p4d.pgd, __pgd(0)); -#endif return __pud(xchg((pudval_t *)xp, 0)); } #else diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h index a564084c6141..f8b1ad2c3828 100644 --- a/arch/x86/include/asm/pgtable-3level.h +++ b/arch/x86/include/asm/pgtable-3level.h @@ -2,6 +2,8 @@ #ifndef _ASM_X86_PGTABLE_3LEVEL_H #define _ASM_X86_PGTABLE_3LEVEL_H +#include <asm/atomic64_32.h> + /* * Intel Physical Address Extension (PAE) Mode - three-level page * tables on PPro+ CPUs. @@ -150,10 +152,7 @@ static inline pte_t native_ptep_get_and_clear(pte_t *ptep) { pte_t res; - /* xchg acts as a barrier before the setting of the high bits */ - res.pte_low = xchg(&ptep->pte_low, 0); - res.pte_high = ptep->pte_high; - ptep->pte_high = 0; + res.pte = (pteval_t)arch_atomic64_xchg((atomic64_t *)ptep, 0); return res; } diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index e4ffa565a69f..690c0307afed 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -1195,7 +1195,7 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma, return xchg(pmdp, pmd); } else { pmd_t old = *pmdp; - *pmdp = pmd; + WRITE_ONCE(*pmdp, pmd); return old; } } diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index f773d5e6c8cc..ce2b59047cb8 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -55,15 +55,15 @@ struct mm_struct; void set_pte_vaddr_p4d(p4d_t *p4d_page, unsigned long vaddr, pte_t new_pte); void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte); -static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr, - pte_t *ptep) +static inline void native_set_pte(pte_t *ptep, pte_t pte) { - *ptep = native_make_pte(0); + WRITE_ONCE(*ptep, pte); } -static inline void native_set_pte(pte_t *ptep, pte_t pte) +static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) { - *ptep = pte; + native_set_pte(ptep, native_make_pte(0)); } static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte) @@ -73,7 +73,7 @@ static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte) static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd) { - *pmdp = pmd; + WRITE_ONCE(*pmdp, pmd); } static inline void native_pmd_clear(pmd_t *pmd) @@ -109,7 +109,7 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp) static inline void native_set_pud(pud_t *pudp, pud_t pud) { - *pudp = pud; + WRITE_ONCE(*pudp, pud); } static inline void native_pud_clear(pud_t *pud) @@ -137,13 +137,13 @@ static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d) pgd_t pgd; if (pgtable_l5_enabled() || !IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) { - *p4dp = p4d; + WRITE_ONCE(*p4dp, p4d); return; } pgd = native_make_pgd(native_p4d_val(p4d)); pgd = pti_set_user_pgtbl((pgd_t *)p4dp, pgd); - *p4dp = native_make_p4d(native_pgd_val(pgd)); + WRITE_ONCE(*p4dp, native_make_p4d(native_pgd_val(pgd))); } static inline void native_p4d_clear(p4d_t *p4d) @@ -153,7 +153,7 @@ static inline void native_p4d_clear(p4d_t *p4d) static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd) { - *pgdp = pti_set_user_pgtbl(pgdp, pgd); + WRITE_ONCE(*pgdp, pti_set_user_pgtbl(pgdp, pgd)); } static inline void native_pgd_clear(pgd_t *pgd) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index c24297268ebc..d53c54b842da 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -132,6 +132,8 @@ struct cpuinfo_x86 { /* Index into per_cpu list: */ u16 cpu_index; u32 microcode; + /* Address space bits used by the cache internally */ + u8 x86_cache_bits; unsigned initialized : 1; } __randomize_layout; @@ -183,7 +185,7 @@ extern void cpu_detect(struct cpuinfo_x86 *c); static inline unsigned long long l1tf_pfn_limit(void) { - return BIT_ULL(boot_cpu_data.x86_phys_bits - 1 - PAGE_SHIFT); + return BIT_ULL(boot_cpu_data.x86_cache_bits - 1 - PAGE_SHIFT); } extern void early_cpu_init(void); diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h index 5f9012ff52ed..33d3c88a7225 100644 --- a/arch/x86/include/asm/signal.h +++ b/arch/x86/include/asm/signal.h @@ -39,6 +39,7 @@ extern void do_signal(struct pt_regs *regs); #define __ARCH_HAS_SA_RESTORER +#include <asm/asm.h> #include <uapi/asm/sigcontext.h> #ifdef __i386__ @@ -86,9 +87,9 @@ static inline int __const_sigismember(sigset_t *set, int _sig) static inline int __gen_sigismember(sigset_t *set, int _sig) { - unsigned char ret; - asm("btl %2,%1\n\tsetc %0" - : "=qm"(ret) : "m"(*set), "Ir"(_sig-1) : "cc"); + bool ret; + asm("btl %2,%1" CC_SET(c) + : CC_OUT(c) (ret) : "m"(*set), "Ir"(_sig-1)); return ret; } diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index b6dc698f992a..f335aad404a4 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -111,6 +111,6 @@ static inline unsigned long caller_frame_pointer(void) return (unsigned long)frame; } -void show_opcodes(u8 *rip, const char *loglvl); +void show_opcodes(struct pt_regs *regs, const char *loglvl); void show_ip(struct pt_regs *regs, const char *loglvl); #endif /* _ASM_X86_STACKTRACE_H */ diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 29c9da6c62fc..58ce5288878e 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -175,8 +175,16 @@ struct tlb_state { * are on. This means that it may not match current->active_mm, * which will contain the previous user mm when we're in lazy TLB * mode even if we've already switched back to swapper_pg_dir. + * + * During switch_mm_irqs_off(), loaded_mm will be set to + * LOADED_MM_SWITCHING during the brief interrupts-off window + * when CR3 and loaded_mm would otherwise be inconsistent. This + * is for nmi_uaccess_okay()'s benefit. */ struct mm_struct *loaded_mm; + +#define LOADED_MM_SWITCHING ((struct mm_struct *)1) + u16 loaded_mm_asid; u16 next_asid; /* last user mm's ctx id */ @@ -246,6 +254,38 @@ struct tlb_state { }; DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate); +/* + * Blindly accessing user memory from NMI context can be dangerous + * if we're in the middle of switching the current user task or + * switching the loaded mm. It can also be dangerous if we + * interrupted some kernel code that was temporarily using a + * different mm. + */ +static inline bool nmi_uaccess_okay(void) +{ + struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm); + struct mm_struct *current_mm = current->mm; + + VM_WARN_ON_ONCE(!loaded_mm); + + /* + * The condition we want to check is + * current_mm->pgd == __va(read_cr3_pa()). This may be slow, though, + * if we're running in a VM with shadow paging, and nmi_uaccess_okay() + * is supposed to be reasonably fast. + * + * Instead, we check the almost equivalent but somewhat conservative + * condition below, and we rely on the fact that switch_mm_irqs_off() + * sets loaded_mm to LOADED_MM_SWITCHING before writing to CR3. + */ + if (loaded_mm != current_mm) + return false; + + VM_WARN_ON_ONCE(current_mm->pgd != __va(read_cr3_pa())); + + return true; +} + /* Initialize cr4 shadow for this CPU. */ static inline void cr4_init_shadow(void) { diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h index fb856c9f0449..53748541c487 100644 --- a/arch/x86/include/asm/vgtod.h +++ b/arch/x86/include/asm/vgtod.h @@ -93,7 +93,7 @@ static inline unsigned int __getcpu(void) * * If RDPID is available, use it. */ - alternative_io ("lsl %[p],%[seg]", + alternative_io ("lsl %[seg],%[p]", ".byte 0xf3,0x0f,0xc7,0xf8", /* RDPID %eax/rax */ X86_FEATURE_RDPID, [p] "=a" (p), [seg] "r" (__PER_CPU_SEG)); diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 014f214da581..b9d5e7c9ef43 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -684,8 +684,6 @@ void *__init_or_module text_poke_early(void *addr, const void *opcode, * It means the size must be writable atomically and the address must be aligned * in a way that permits an atomic write. It also makes sure we fit on a single * page. - * - * Note: Must be called under text_mutex. */ void *text_poke(void *addr, const void *opcode, size_t len) { @@ -700,6 +698,8 @@ void *text_poke(void *addr, const void *opcode, size_t len) */ BUG_ON(!after_bootmem); + lockdep_assert_held(&text_mutex); + if (!core_kernel_text((unsigned long)addr)) { pages[0] = vmalloc_to_page(addr); pages[1] = vmalloc_to_page(addr + PAGE_SIZE); @@ -782,8 +782,6 @@ int poke_int3_handler(struct pt_regs *regs) * - replace the first byte (int3) by the first byte of * replacing opcode * - sync cores - * - * Note: must be called under text_mutex. */ void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler) { @@ -792,6 +790,9 @@ void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler) bp_int3_handler = handler; bp_int3_addr = (u8 *)addr + sizeof(int3); bp_patching_in_progress = true; + + lockdep_assert_held(&text_mutex); + /* * Corresponding read barrier in int3 notifier for making sure the * in_progress and handler are correctly ordered wrt. patching. diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 9f148e3d45b4..7654febd5102 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -413,7 +413,7 @@ static int activate_managed(struct irq_data *irqd) if (WARN_ON_ONCE(cpumask_empty(vector_searchmask))) { /* Something in the core code broke! Survive gracefully */ pr_err("Managed startup for irq %u, but no CPU\n", irqd->irq); - return EINVAL; + return -EINVAL; } ret = assign_managed_vector(irqd, vector_searchmask); diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index ec00d1ff5098..f7151cd03cb0 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -1640,6 +1640,7 @@ static int do_open(struct inode *inode, struct file *filp) return 0; } +#ifdef CONFIG_PROC_FS static int proc_apm_show(struct seq_file *m, void *v) { unsigned short bx; @@ -1719,6 +1720,7 @@ static int proc_apm_show(struct seq_file *m, void *v) units); return 0; } +#endif static int apm(void *unused) { diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 4c2313d0b9ca..40bdaea97fe7 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -668,6 +668,45 @@ EXPORT_SYMBOL_GPL(l1tf_mitigation); enum vmx_l1d_flush_state l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO; EXPORT_SYMBOL_GPL(l1tf_vmx_mitigation); +/* + * These CPUs all support 44bits physical address space internally in the + * cache but CPUID can report a smaller number of physical address bits. + * + * The L1TF mitigation uses the top most address bit for the inversion of + * non present PTEs. When the installed memory reaches into the top most + * address bit due to memory holes, which has been observed on machines + * which report 36bits physical address bits and have 32G RAM installed, + * then the mitigation range check in l1tf_select_mitigation() triggers. + * This is a false positive because the mitigation is still possible due to + * the fact that the cache uses 44bit internally. Use the cache bits + * instead of the reported physical bits and adjust them on the affected + * machines to 44bit if the reported bits are less than 44. + */ +static void override_cache_bits(struct cpuinfo_x86 *c) +{ + if (c->x86 != 6) + return; + + switch (c->x86_model) { + case INTEL_FAM6_NEHALEM: + case INTEL_FAM6_WESTMERE: + case INTEL_FAM6_SANDYBRIDGE: + case INTEL_FAM6_IVYBRIDGE: + case INTEL_FAM6_HASWELL_CORE: + case INTEL_FAM6_HASWELL_ULT: + case INTEL_FAM6_HASWELL_GT3E: + case INTEL_FAM6_BROADWELL_CORE: + case INTEL_FAM6_BROADWELL_GT3E: + case INTEL_FAM6_SKYLAKE_MOBILE: + case INTEL_FAM6_SKYLAKE_DESKTOP: + case INTEL_FAM6_KABYLAKE_MOBILE: + case INTEL_FAM6_KABYLAKE_DESKTOP: + if (c->x86_cache_bits < 44) + c->x86_cache_bits = 44; + break; + } +} + static void __init l1tf_select_mitigation(void) { u64 half_pa; @@ -675,6 +714,8 @@ static void __init l1tf_select_mitigation(void) if (!boot_cpu_has_bug(X86_BUG_L1TF)) return; + override_cache_bits(&boot_cpu_data); + switch (l1tf_mitigation) { case L1TF_MITIGATION_OFF: case L1TF_MITIGATION_FLUSH_NOWARN: @@ -694,11 +735,6 @@ static void __init l1tf_select_mitigation(void) return; #endif - /* - * This is extremely unlikely to happen because almost all - * systems have far more MAX_PA/2 than RAM can be fit into - * DIMM slots. - */ half_pa = (u64)l1tf_pfn_limit() << PAGE_SHIFT; if (e820__mapped_any(half_pa, ULLONG_MAX - half_pa, E820_TYPE_RAM)) { pr_warn("System has more than MAX_PA/2 memory. L1TF mitigation not effective.\n"); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 84dee5ab745a..44c4ef3d989b 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -919,6 +919,7 @@ void get_cpu_address_sizes(struct cpuinfo_x86 *c) else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36)) c->x86_phys_bits = 36; #endif + c->x86_cache_bits = c->x86_phys_bits; } static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 401e8c133108..fc3c07fe7df5 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -150,6 +150,9 @@ static bool bad_spectre_microcode(struct cpuinfo_x86 *c) if (cpu_has(c, X86_FEATURE_HYPERVISOR)) return false; + if (c->x86 != 6) + return false; + for (i = 0; i < ARRAY_SIZE(spectre_bad_microcodes); i++) { if (c->x86_model == spectre_bad_microcodes[i].model && c->x86_stepping == spectre_bad_microcodes[i].stepping) diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 0624957aa068..07b5fc00b188 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -504,6 +504,7 @@ static enum ucode_state apply_microcode_amd(int cpu) struct microcode_amd *mc_amd; struct ucode_cpu_info *uci; struct ucode_patch *p; + enum ucode_state ret; u32 rev, dummy; BUG_ON(raw_smp_processor_id() != cpu); @@ -521,9 +522,8 @@ static enum ucode_state apply_microcode_amd(int cpu) /* need to apply patch? */ if (rev >= mc_amd->hdr.patch_id) { - c->microcode = rev; - uci->cpu_sig.rev = rev; - return UCODE_OK; + ret = UCODE_OK; + goto out; } if (__apply_microcode_amd(mc_amd)) { @@ -531,13 +531,21 @@ static enum ucode_state apply_microcode_amd(int cpu) cpu, mc_amd->hdr.patch_id); return UCODE_ERROR; } - pr_info("CPU%d: new patch_level=0x%08x\n", cpu, - mc_amd->hdr.patch_id); - uci->cpu_sig.rev = mc_amd->hdr.patch_id; - c->microcode = mc_amd->hdr.patch_id; + rev = mc_amd->hdr.patch_id; + ret = UCODE_UPDATED; + + pr_info("CPU%d: new patch_level=0x%08x\n", cpu, rev); - return UCODE_UPDATED; +out: + uci->cpu_sig.rev = rev; + c->microcode = rev; + + /* Update boot_cpu_data's revision too, if we're on the BSP: */ + if (c->cpu_index == boot_cpu_data.cpu_index) + boot_cpu_data.microcode = rev; + + return ret; } static int install_equiv_cpu_table(const u8 *buf) diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 97ccf4c3b45b..16936a24795c 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -795,6 +795,7 @@ static enum ucode_state apply_microcode_intel(int cpu) struct ucode_cpu_info *uci = ucode_cpu_info + cpu; struct cpuinfo_x86 *c = &cpu_data(cpu); struct microcode_intel *mc; + enum ucode_state ret; static int prev_rev; u32 rev; @@ -817,9 +818,8 @@ static enum ucode_state apply_microcode_intel(int cpu) */ rev = intel_get_microcode_revision(); if (rev >= mc->hdr.rev) { - uci->cpu_sig.rev = rev; - c->microcode = rev; - return UCODE_OK; + ret = UCODE_OK; + goto out; } /* @@ -848,10 +848,17 @@ static enum ucode_state apply_microcode_intel(int cpu) prev_rev = rev; } + ret = UCODE_UPDATED; + +out: uci->cpu_sig.rev = rev; - c->microcode = rev; + c->microcode = rev; + + /* Update boot_cpu_data's revision too, if we're on the BSP: */ + if (c->cpu_index == boot_cpu_data.cpu_index) + boot_cpu_data.microcode = rev; - return UCODE_UPDATED; + return ret; } static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size, diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 9c8652974f8e..2b5886401e5f 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -17,6 +17,7 @@ #include <linux/bug.h> #include <linux/nmi.h> #include <linux/sysfs.h> +#include <linux/kasan.h> #include <asm/cpu_entry_area.h> #include <asm/stacktrace.h> @@ -89,14 +90,24 @@ static void printk_stack_address(unsigned long address, int reliable, * Thus, the 2/3rds prologue and 64 byte OPCODE_BUFSIZE is just a random * guesstimate in attempt to achieve all of the above. */ -void show_opcodes(u8 *rip, const char *loglvl) +void show_opcodes(struct pt_regs *regs, const char *loglvl) { #define PROLOGUE_SIZE 42 #define EPILOGUE_SIZE 21 #define OPCODE_BUFSIZE (PROLOGUE_SIZE + 1 + EPILOGUE_SIZE) u8 opcodes[OPCODE_BUFSIZE]; + unsigned long prologue = regs->ip - PROLOGUE_SIZE; + bool bad_ip; - if (probe_kernel_read(opcodes, rip - PROLOGUE_SIZE, OPCODE_BUFSIZE)) { + /* + * Make sure userspace isn't trying to trick us into dumping kernel + * memory by pointing the userspace instruction pointer at it. + */ + bad_ip = user_mode(regs) && + __chk_range_not_ok(prologue, OPCODE_BUFSIZE, TASK_SIZE_MAX); + + if (bad_ip || probe_kernel_read(opcodes, (u8 *)prologue, + OPCODE_BUFSIZE)) { printk("%sCode: Bad RIP value.\n", loglvl); } else { printk("%sCode: %" __stringify(PROLOGUE_SIZE) "ph <%02x> %" @@ -112,7 +123,7 @@ void show_ip(struct pt_regs *regs, const char *loglvl) #else printk("%sRIP: %04x:%pS\n", loglvl, (int)regs->cs, (void *)regs->ip); #endif - show_opcodes((u8 *)regs->ip, loglvl); + show_opcodes(regs, loglvl); } void show_iret_regs(struct pt_regs *regs) @@ -135,7 +146,7 @@ static void show_regs_if_on_stack(struct stack_info *info, struct pt_regs *regs, * they can be printed in the right context. */ if (!partial && on_stack(info, regs, sizeof(*regs))) { - __show_regs(regs, 0); + __show_regs(regs, SHOW_REGS_SHORT); } else if (partial && on_stack(info, (void *)regs + IRET_FRAME_OFFSET, IRET_FRAME_SIZE)) { @@ -333,7 +344,7 @@ void oops_end(unsigned long flags, struct pt_regs *regs, int signr) oops_exit(); /* Executive summary in case the oops scrolled away */ - __show_regs(&exec_summary_regs, true); + __show_regs(&exec_summary_regs, SHOW_REGS_ALL); if (!signr) return; @@ -346,7 +357,10 @@ void oops_end(unsigned long flags, struct pt_regs *regs, int signr) * We're not going to return, but we might be on an IST stack or * have very little stack space left. Rewind the stack and kill * the task. + * Before we rewind the stack, we have to tell KASAN that we're going to + * reuse the task stack and that existing poisons are invalid. */ + kasan_unpoison_task_stack(current); rewind_stack_do_exit(signr); } NOKPROBE_SYMBOL(oops_end); @@ -393,14 +407,9 @@ void die(const char *str, struct pt_regs *regs, long err) void show_regs(struct pt_regs *regs) { - bool all = true; - show_regs_print_info(KERN_DEFAULT); - if (IS_ENABLED(CONFIG_X86_32)) - all = !user_mode(regs); - - __show_regs(regs, all); + __show_regs(regs, user_mode(regs) ? SHOW_REGS_USER : SHOW_REGS_ALL); /* * When in-kernel, we also print out the stack at the time of the fault.. diff --git a/arch/x86/kernel/eisa.c b/arch/x86/kernel/eisa.c index f260e452e4f8..e8c8c5d78dbd 100644 --- a/arch/x86/kernel/eisa.c +++ b/arch/x86/kernel/eisa.c @@ -7,11 +7,17 @@ #include <linux/eisa.h> #include <linux/io.h> +#include <xen/xen.h> + static __init int eisa_bus_probe(void) { - void __iomem *p = ioremap(0x0FFFD9, 4); + void __iomem *p; + + if (xen_pv_domain() && !xen_initial_domain()) + return 0; - if (readl(p) == 'E' + ('I'<<8) + ('S'<<16) + ('A'<<24)) + p = ioremap(0x0FFFD9, 4); + if (p && readl(p) == 'E' + ('I' << 8) + ('S' << 16) + ('A' << 24)) EISA_bus = 1; iounmap(p); return 0; diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 2924fd447e61..5046a3c9dec2 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -59,7 +59,7 @@ #include <asm/intel_rdt_sched.h> #include <asm/proto.h> -void __show_regs(struct pt_regs *regs, int all) +void __show_regs(struct pt_regs *regs, enum show_regs_mode mode) { unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L; unsigned long d0, d1, d2, d3, d6, d7; @@ -85,7 +85,7 @@ void __show_regs(struct pt_regs *regs, int all) printk(KERN_DEFAULT "DS: %04x ES: %04x FS: %04x GS: %04x SS: %04x EFLAGS: %08lx\n", (u16)regs->ds, (u16)regs->es, (u16)regs->fs, gs, ss, regs->flags); - if (!all) + if (mode != SHOW_REGS_ALL) return; cr0 = read_cr0(); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index a451bc374b9b..ea5ea850348d 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -62,7 +62,7 @@ __visible DEFINE_PER_CPU(unsigned long, rsp_scratch); /* Prints also some state that isn't saved in the pt_regs */ -void __show_regs(struct pt_regs *regs, int all) +void __show_regs(struct pt_regs *regs, enum show_regs_mode mode) { unsigned long cr0 = 0L, cr2 = 0L, cr3 = 0L, cr4 = 0L, fs, gs, shadowgs; unsigned long d0, d1, d2, d3, d6, d7; @@ -87,9 +87,17 @@ void __show_regs(struct pt_regs *regs, int all) printk(KERN_DEFAULT "R13: %016lx R14: %016lx R15: %016lx\n", regs->r13, regs->r14, regs->r15); - if (!all) + if (mode == SHOW_REGS_SHORT) return; + if (mode == SHOW_REGS_USER) { + rdmsrl(MSR_FS_BASE, fs); + rdmsrl(MSR_KERNEL_GS_BASE, shadowgs); + printk(KERN_DEFAULT "FS: %016lx GS: %016lx\n", + fs, shadowgs); + return; + } + asm("movl %%ds,%0" : "=r" (ds)); asm("movl %%cs,%0" : "=r" (cs)); asm("movl %%es,%0" : "=r" (es)); diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c index 12cbe2b88c0f..738bf42b0218 100644 --- a/arch/x86/kernel/topology.c +++ b/arch/x86/kernel/topology.c @@ -111,8 +111,10 @@ int arch_register_cpu(int num) /* * Currently CPU0 is only hotpluggable on Intel platforms. Other * vendors can add hotplug support later. + * Xen PV guests don't support CPU0 hotplug at all. */ - if (c->x86_vendor != X86_VENDOR_INTEL) + if (c->x86_vendor != X86_VENDOR_INTEL || + boot_cpu_has(X86_FEATURE_XENPV)) cpu0_hotpluggable = 0; /* diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 1463468ba9a0..6490f618e096 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -1415,7 +1415,7 @@ static bool __init determine_cpu_tsc_frequencies(bool early) static unsigned long __init get_loops_per_jiffy(void) { - unsigned long lpj = tsc_khz * KHZ; + u64 lpj = (u64)tsc_khz * KHZ; do_div(lpj, HZ); return lpj; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 0cefba28c864..17c0472c5b34 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -548,7 +548,7 @@ int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq, } int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low, - unsigned long ipi_bitmap_high, int min, + unsigned long ipi_bitmap_high, u32 min, unsigned long icr, int op_64_bit) { int i; @@ -571,18 +571,31 @@ int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low, rcu_read_lock(); map = rcu_dereference(kvm->arch.apic_map); + if (min > map->max_apic_id) + goto out; /* Bits above cluster_size are masked in the caller. */ - for_each_set_bit(i, &ipi_bitmap_low, BITS_PER_LONG) { - vcpu = map->phys_map[min + i]->vcpu; - count += kvm_apic_set_irq(vcpu, &irq, NULL); + for_each_set_bit(i, &ipi_bitmap_low, + min((u32)BITS_PER_LONG, (map->max_apic_id - min + 1))) { + if (map->phys_map[min + i]) { + vcpu = map->phys_map[min + i]->vcpu; + count += kvm_apic_set_irq(vcpu, &irq, NULL); + } } min += cluster_size; - for_each_set_bit(i, &ipi_bitmap_high, BITS_PER_LONG) { - vcpu = map->phys_map[min + i]->vcpu; - count += kvm_apic_set_irq(vcpu, &irq, NULL); + + if (min > map->max_apic_id) + goto out; + + for_each_set_bit(i, &ipi_bitmap_high, + min((u32)BITS_PER_LONG, (map->max_apic_id - min + 1))) { + if (map->phys_map[min + i]) { + vcpu = map->phys_map[min + i]->vcpu; + count += kvm_apic_set_irq(vcpu, &irq, NULL); + } } +out: rcu_read_unlock(); return count; } diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index a282321329b5..e24ea7067373 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -1853,11 +1853,6 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, return kvm_handle_hva_range(kvm, hva, hva + 1, data, handler); } -int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) -{ - return kvm_handle_hva(kvm, hva, 0, kvm_unmap_rmapp); -} - int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) { return kvm_handle_hva_range(kvm, start, end, 0, kvm_unmap_rmapp); @@ -5217,7 +5212,7 @@ static int make_mmu_pages_available(struct kvm_vcpu *vcpu) int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, void *insn, int insn_len) { - int r, emulation_type = EMULTYPE_RETRY; + int r, emulation_type = 0; enum emulation_result er; bool direct = vcpu->arch.mmu.direct_map; @@ -5230,10 +5225,8 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, r = RET_PF_INVALID; if (unlikely(error_code & PFERR_RSVD_MASK)) { r = handle_mmio_page_fault(vcpu, cr2, direct); - if (r == RET_PF_EMULATE) { - emulation_type = 0; + if (r == RET_PF_EMULATE) goto emulate; - } } if (r == RET_PF_INVALID) { @@ -5260,8 +5253,19 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code, return 1; } - if (mmio_info_in_cache(vcpu, cr2, direct)) - emulation_type = 0; + /* + * vcpu->arch.mmu.page_fault returned RET_PF_EMULATE, but we can still + * optimistically try to just unprotect the page and let the processor + * re-execute the instruction that caused the page fault. Do not allow + * retrying MMIO emulation, as it's not only pointless but could also + * cause us to enter an infinite loop because the processor will keep + * faulting on the non-existent MMIO address. Retrying an instruction + * from a nested guest is also pointless and dangerous as we are only + * explicitly shadowing L1's page tables, i.e. unprotecting something + * for L1 isn't going to magically fix whatever issue cause L2 to fail. + */ + if (!mmio_info_in_cache(vcpu, cr2, direct) && !is_guest_mode(vcpu)) + emulation_type = EMULTYPE_ALLOW_RETRY; emulate: /* * On AMD platforms, under certain conditions insn_len may be zero on #NPF. diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 6276140044d0..89c4c5aa15f1 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -776,7 +776,7 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) } if (!svm->next_rip) { - if (emulate_instruction(vcpu, EMULTYPE_SKIP) != + if (kvm_emulate_instruction(vcpu, EMULTYPE_SKIP) != EMULATE_DONE) printk(KERN_DEBUG "%s: NOP\n", __func__); return; @@ -2715,7 +2715,7 @@ static int gp_interception(struct vcpu_svm *svm) WARN_ON_ONCE(!enable_vmware_backdoor); - er = emulate_instruction(vcpu, + er = kvm_emulate_instruction(vcpu, EMULTYPE_VMWARE | EMULTYPE_NO_UD_ON_FAIL); if (er == EMULATE_USER_EXIT) return 0; @@ -2819,7 +2819,7 @@ static int io_interception(struct vcpu_svm *svm) string = (io_info & SVM_IOIO_STR_MASK) != 0; in = (io_info & SVM_IOIO_TYPE_MASK) != 0; if (string) - return emulate_instruction(vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE; port = io_info >> 16; size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT; @@ -3861,7 +3861,7 @@ static int iret_interception(struct vcpu_svm *svm) static int invlpg_interception(struct vcpu_svm *svm) { if (!static_cpu_has(X86_FEATURE_DECODEASSISTS)) - return emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE; kvm_mmu_invlpg(&svm->vcpu, svm->vmcb->control.exit_info_1); return kvm_skip_emulated_instruction(&svm->vcpu); @@ -3869,13 +3869,13 @@ static int invlpg_interception(struct vcpu_svm *svm) static int emulate_on_interception(struct vcpu_svm *svm) { - return emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE; } static int rsm_interception(struct vcpu_svm *svm) { - return x86_emulate_instruction(&svm->vcpu, 0, 0, - rsm_ins_bytes, 2) == EMULATE_DONE; + return kvm_emulate_instruction_from_buffer(&svm->vcpu, + rsm_ins_bytes, 2) == EMULATE_DONE; } static int rdpmc_interception(struct vcpu_svm *svm) @@ -4700,7 +4700,7 @@ static int avic_unaccelerated_access_interception(struct vcpu_svm *svm) ret = avic_unaccel_trap_write(svm); } else { /* Handling Fault */ - ret = (emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE); + ret = (kvm_emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE); } return ret; @@ -6747,7 +6747,7 @@ e_free: static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec) { unsigned long vaddr, vaddr_end, next_vaddr; - unsigned long dst_vaddr, dst_vaddr_end; + unsigned long dst_vaddr; struct page **src_p, **dst_p; struct kvm_sev_dbg debug; unsigned long n; @@ -6763,7 +6763,6 @@ static int sev_dbg_crypt(struct kvm *kvm, struct kvm_sev_cmd *argp, bool dec) size = debug.len; vaddr_end = vaddr + size; dst_vaddr = debug.dst_uaddr; - dst_vaddr_end = dst_vaddr + size; for (; vaddr < vaddr_end; vaddr = next_vaddr) { int len, s_off, d_off; diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 1d26f3c4985b..533a327372c8 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -6983,7 +6983,7 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu, * Cause the #SS fault with 0 error code in VM86 mode. */ if (((vec == GP_VECTOR) || (vec == SS_VECTOR)) && err_code == 0) { - if (emulate_instruction(vcpu, 0) == EMULATE_DONE) { + if (kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE) { if (vcpu->arch.halt_request) { vcpu->arch.halt_request = 0; return kvm_vcpu_halt(vcpu); @@ -7054,7 +7054,7 @@ static int handle_exception(struct kvm_vcpu *vcpu) if (!vmx->rmode.vm86_active && is_gp_fault(intr_info)) { WARN_ON_ONCE(!enable_vmware_backdoor); - er = emulate_instruction(vcpu, + er = kvm_emulate_instruction(vcpu, EMULTYPE_VMWARE | EMULTYPE_NO_UD_ON_FAIL); if (er == EMULATE_USER_EXIT) return 0; @@ -7157,7 +7157,7 @@ static int handle_io(struct kvm_vcpu *vcpu) ++vcpu->stat.io_exits; if (string) - return emulate_instruction(vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE; port = exit_qualification >> 16; size = (exit_qualification & 7) + 1; @@ -7231,7 +7231,7 @@ static int handle_set_cr4(struct kvm_vcpu *vcpu, unsigned long val) static int handle_desc(struct kvm_vcpu *vcpu) { WARN_ON(!(vcpu->arch.cr4 & X86_CR4_UMIP)); - return emulate_instruction(vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE; } static int handle_cr(struct kvm_vcpu *vcpu) @@ -7480,7 +7480,7 @@ static int handle_vmcall(struct kvm_vcpu *vcpu) static int handle_invd(struct kvm_vcpu *vcpu) { - return emulate_instruction(vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE; } static int handle_invlpg(struct kvm_vcpu *vcpu) @@ -7547,7 +7547,7 @@ static int handle_apic_access(struct kvm_vcpu *vcpu) return kvm_skip_emulated_instruction(vcpu); } } - return emulate_instruction(vcpu, 0) == EMULATE_DONE; + return kvm_emulate_instruction(vcpu, 0) == EMULATE_DONE; } static int handle_apic_eoi_induced(struct kvm_vcpu *vcpu) @@ -7704,8 +7704,8 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) if (!static_cpu_has(X86_FEATURE_HYPERVISOR)) return kvm_skip_emulated_instruction(vcpu); else - return x86_emulate_instruction(vcpu, gpa, EMULTYPE_SKIP, - NULL, 0) == EMULATE_DONE; + return kvm_emulate_instruction(vcpu, EMULTYPE_SKIP) == + EMULATE_DONE; } return kvm_mmu_page_fault(vcpu, gpa, PFERR_RSVD_MASK, NULL, 0); @@ -7748,7 +7748,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) if (kvm_test_request(KVM_REQ_EVENT, vcpu)) return 1; - err = emulate_instruction(vcpu, 0); + err = kvm_emulate_instruction(vcpu, 0); if (err == EMULATE_USER_EXIT) { ++vcpu->stat.mmio_exits; @@ -12537,8 +12537,11 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, u32 *exit_qual) struct vmcs12 *vmcs12 = get_vmcs12(vcpu); bool from_vmentry = !!exit_qual; u32 dummy_exit_qual; + u32 vmcs01_cpu_exec_ctrl; int r = 0; + vmcs01_cpu_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); + enter_guest_mode(vcpu); if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) @@ -12575,6 +12578,25 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, u32 *exit_qual) } /* + * If L1 had a pending IRQ/NMI until it executed + * VMLAUNCH/VMRESUME which wasn't delivered because it was + * disallowed (e.g. interrupts disabled), L0 needs to + * evaluate if this pending event should cause an exit from L2 + * to L1 or delivered directly to L2 (e.g. In case L1 don't + * intercept EXTERNAL_INTERRUPT). + * + * Usually this would be handled by L0 requesting a + * IRQ/NMI window by setting VMCS accordingly. However, + * this setting was done on VMCS01 and now VMCS02 is active + * instead. Thus, we force L0 to perform pending event + * evaluation by requesting a KVM_REQ_EVENT. + */ + if (vmcs01_cpu_exec_ctrl & + (CPU_BASED_VIRTUAL_INTR_PENDING | CPU_BASED_VIRTUAL_NMI_PENDING)) { + kvm_make_request(KVM_REQ_EVENT, vcpu); + } + + /* * Note no nested_vmx_succeed or nested_vmx_fail here. At this point * we are no longer running L1, and VMLAUNCH/VMRESUME has not yet * returned as far as L1 is concerned. It will only return (and set @@ -13988,9 +14010,6 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, check_vmentry_postreqs(vcpu, vmcs12, &exit_qual)) return -EINVAL; - if (kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING) - vmx->nested.nested_run_pending = 1; - vmx->nested.dirty_vmcs12 = true; ret = enter_vmx_non_root_mode(vcpu, NULL); if (ret) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 506bd2b4b8bb..542f6315444d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4987,7 +4987,7 @@ int handle_ud(struct kvm_vcpu *vcpu) emul_type = 0; } - er = emulate_instruction(vcpu, emul_type); + er = kvm_emulate_instruction(vcpu, emul_type); if (er == EMULATE_USER_EXIT) return 0; if (er != EMULATE_DONE) @@ -5870,7 +5870,10 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2, gpa_t gpa = cr2; kvm_pfn_t pfn; - if (emulation_type & EMULTYPE_NO_REEXECUTE) + if (!(emulation_type & EMULTYPE_ALLOW_RETRY)) + return false; + + if (WARN_ON_ONCE(is_guest_mode(vcpu))) return false; if (!vcpu->arch.mmu.direct_map) { @@ -5958,7 +5961,10 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt, */ vcpu->arch.last_retry_eip = vcpu->arch.last_retry_addr = 0; - if (!(emulation_type & EMULTYPE_RETRY)) + if (!(emulation_type & EMULTYPE_ALLOW_RETRY)) + return false; + + if (WARN_ON_ONCE(is_guest_mode(vcpu))) return false; if (x86_page_table_writing_insn(ctxt)) @@ -6276,7 +6282,19 @@ restart: return r; } -EXPORT_SYMBOL_GPL(x86_emulate_instruction); + +int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type) +{ + return x86_emulate_instruction(vcpu, 0, emulation_type, NULL, 0); +} +EXPORT_SYMBOL_GPL(kvm_emulate_instruction); + +int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu, + void *insn, int insn_len) +{ + return x86_emulate_instruction(vcpu, 0, 0, insn, insn_len); +} +EXPORT_SYMBOL_GPL(kvm_emulate_instruction_from_buffer); static int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port) @@ -7734,7 +7752,7 @@ static inline int complete_emulated_io(struct kvm_vcpu *vcpu) { int r; vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); - r = emulate_instruction(vcpu, EMULTYPE_NO_DECODE); + r = kvm_emulate_instruction(vcpu, EMULTYPE_NO_DECODE); srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); if (r != EMULATE_DONE) return 0; diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 257f27620bc2..67b9568613f3 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -274,6 +274,8 @@ int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata); bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int page_num); bool kvm_vector_hashing_enabled(void); +int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2, + int emulation_type, void *insn, int insn_len); #define KVM_SUPPORTED_XCR0 (XFEATURE_MASK_FP | XFEATURE_MASK_SSE \ | XFEATURE_MASK_YMM | XFEATURE_MASK_BNDREGS \ diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c index c8c6ad0d58b8..3f435d7fca5e 100644 --- a/arch/x86/lib/usercopy.c +++ b/arch/x86/lib/usercopy.c @@ -7,6 +7,8 @@ #include <linux/uaccess.h> #include <linux/export.h> +#include <asm/tlbflush.h> + /* * We rely on the nested NMI work to allow atomic faults from the NMI path; the * nested NMI paths are careful to preserve CR2. @@ -19,6 +21,9 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n) if (__range_not_ok(from, n, TASK_SIZE)) return n; + if (!nmi_uaccess_okay()) + return n; + /* * Even though this function is typically called from NMI/IRQ context * disable pagefaults so that its behaviour is consistent even when diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index b9123c497e0a..47bebfe6efa7 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -837,7 +837,7 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code, printk(KERN_CONT "\n"); - show_opcodes((u8 *)regs->ip, loglvl); + show_opcodes(regs, loglvl); } static void diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 8d6c34fe49be..51a5a69ecac9 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -1420,6 +1420,29 @@ static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias) return 0; } +/* + * Machine check recovery code needs to change cache mode of poisoned + * pages to UC to avoid speculative access logging another error. But + * passing the address of the 1:1 mapping to set_memory_uc() is a fine + * way to encourage a speculative access. So we cheat and flip the top + * bit of the address. This works fine for the code that updates the + * page tables. But at the end of the process we need to flush the cache + * and the non-canonical address causes a #GP fault when used by the + * CLFLUSH instruction. + * + * But in the common case we already have a canonical address. This code + * will fix the top bit if needed and is a no-op otherwise. + */ +static inline unsigned long make_addr_canonical_again(unsigned long addr) +{ +#ifdef CONFIG_X86_64 + return (long)(addr << 1) >> 1; +#else + return addr; +#endif +} + + static int change_page_attr_set_clr(unsigned long *addr, int numpages, pgprot_t mask_set, pgprot_t mask_clr, int force_split, int in_flag, @@ -1465,7 +1488,7 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages, * Save address for cache flush. *addr is modified in the call * to __change_page_attr_set_clr() below. */ - baddr = *addr; + baddr = make_addr_canonical_again(*addr); } /* Must avoid aliasing mappings in the highmem code */ diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index e848a4811785..ae394552fb94 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -269,7 +269,7 @@ static void mop_up_one_pmd(struct mm_struct *mm, pgd_t *pgdp) if (pgd_val(pgd) != 0) { pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd); - *pgdp = native_make_pgd(0); + pgd_clear(pgdp); paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT); pmd_free(mm, pmd); @@ -494,7 +494,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma, int changed = !pte_same(*ptep, entry); if (changed && dirty) - *ptep = entry; + set_pte(ptep, entry); return changed; } @@ -509,7 +509,7 @@ int pmdp_set_access_flags(struct vm_area_struct *vma, VM_BUG_ON(address & ~HPAGE_PMD_MASK); if (changed && dirty) { - *pmdp = entry; + set_pmd(pmdp, entry); /* * We had a write-protection fault here and changed the pmd * to to more permissive. No need to flush the TLB for that, @@ -529,7 +529,7 @@ int pudp_set_access_flags(struct vm_area_struct *vma, unsigned long address, VM_BUG_ON(address & ~HPAGE_PUD_MASK); if (changed && dirty) { - *pudp = entry; + set_pud(pudp, entry); /* * We had a write-protection fault here and changed the pud * to to more permissive. No need to flush the TLB for that, diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index 31341ae7309f..c1fc1ae6b429 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -248,7 +248,7 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address) * * Returns a pointer to a PTE on success, or NULL on failure. */ -static __init pte_t *pti_user_pagetable_walk_pte(unsigned long address) +static pte_t *pti_user_pagetable_walk_pte(unsigned long address) { gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); pmd_t *pmd; diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 9517d1b2a281..e96b99eb800c 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -305,6 +305,10 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, choose_new_asid(next, next_tlb_gen, &new_asid, &need_flush); + /* Let nmi_uaccess_okay() know that we're changing CR3. */ + this_cpu_write(cpu_tlbstate.loaded_mm, LOADED_MM_SWITCHING); + barrier(); + if (need_flush) { this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id); this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen); @@ -335,6 +339,9 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, if (next != &init_mm) this_cpu_write(cpu_tlbstate.last_ctx_id, next->context.ctx_id); + /* Make sure we write CR3 before loaded_mm. */ + barrier(); + this_cpu_write(cpu_tlbstate.loaded_mm, next); this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid); } diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c index 324b93328b37..9959657127f4 100644 --- a/arch/x86/platform/efi/efi_32.c +++ b/arch/x86/platform/efi/efi_32.c @@ -85,12 +85,7 @@ pgd_t * __init efi_call_phys_prolog(void) void __init efi_call_phys_epilog(pgd_t *save_pgd) { - struct desc_ptr gdt_descr; - - gdt_descr.address = (unsigned long)get_cpu_gdt_rw(0); - gdt_descr.size = GDT_SIZE - 1; - load_gdt(&gdt_descr); - + load_fixmap_gdt(0); load_cr3(save_pgd); __flush_tlb_all(); } diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 45b700ac5fe7..2fe5c9b1816b 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -435,14 +435,13 @@ static void xen_set_pud(pud_t *ptr, pud_t val) static void xen_set_pte_atomic(pte_t *ptep, pte_t pte) { trace_xen_mmu_set_pte_atomic(ptep, pte); - set_64bit((u64 *)ptep, native_pte_val(pte)); + __xen_set_pte(ptep, pte); } static void xen_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { trace_xen_mmu_pte_clear(mm, addr, ptep); - if (!xen_batched_set_pte(ptep, native_make_pte(0))) - native_pte_clear(mm, addr, ptep); + __xen_set_pte(ptep, native_make_pte(0)); } static void xen_pmd_clear(pmd_t *pmdp) @@ -1570,7 +1569,7 @@ static void __init xen_set_pte_init(pte_t *ptep, pte_t pte) pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) & pte_val_ma(pte)); #endif - native_set_pte(ptep, pte); + __xen_set_pte(ptep, pte); } /* Early in boot, while setting up the initial pagetable, assume @@ -2061,7 +2060,6 @@ void __init xen_relocate_p2m(void) pud_t *pud; pgd_t *pgd; unsigned long *new_p2m; - int save_pud; size = PAGE_ALIGN(xen_start_info->nr_pages * sizeof(unsigned long)); n_pte = roundup(size, PAGE_SIZE) >> PAGE_SHIFT; @@ -2091,7 +2089,6 @@ void __init xen_relocate_p2m(void) pgd = __va(read_cr3_pa()); new_p2m = (unsigned long *)(2 * PGDIR_SIZE); - save_pud = n_pud; for (idx_pud = 0; idx_pud < n_pud; idx_pud++) { pud = early_memremap(pud_phys, PAGE_SIZE); clear_page(pud); diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index 04d038f3b6fa..b9ad83a0ee5d 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -4,6 +4,7 @@ config ZONE_DMA config XTENSA def_bool y + select ARCH_HAS_SG_CHAIN select ARCH_HAS_SYNC_DMA_FOR_CPU select ARCH_HAS_SYNC_DMA_FOR_DEVICE select ARCH_NO_COHERENT_DMA_MMAP if !MMU diff --git a/arch/xtensa/Makefile b/arch/xtensa/Makefile index 295c120ed099..d67e30faff9c 100644 --- a/arch/xtensa/Makefile +++ b/arch/xtensa/Makefile @@ -64,11 +64,7 @@ endif vardirs := $(patsubst %,arch/xtensa/variants/%/,$(variant-y)) plfdirs := $(patsubst %,arch/xtensa/platforms/%/,$(platform-y)) -ifeq ($(KBUILD_SRC),) -KBUILD_CPPFLAGS += $(patsubst %,-I%include,$(vardirs) $(plfdirs)) -else KBUILD_CPPFLAGS += $(patsubst %,-I$(srctree)/%include,$(vardirs) $(plfdirs)) -endif KBUILD_DEFCONFIG := iss_defconfig diff --git a/arch/xtensa/platforms/iss/setup.c b/arch/xtensa/platforms/iss/setup.c index f4bbb28026f8..58709e89a8ed 100644 --- a/arch/xtensa/platforms/iss/setup.c +++ b/arch/xtensa/platforms/iss/setup.c @@ -78,23 +78,28 @@ static struct notifier_block iss_panic_block = { void __init platform_setup(char **p_cmdline) { + static void *argv[COMMAND_LINE_SIZE / sizeof(void *)] __initdata; + static char cmdline[COMMAND_LINE_SIZE] __initdata; int argc = simc_argc(); int argv_size = simc_argv_size(); if (argc > 1) { - void **argv = alloc_bootmem(argv_size); - char *cmdline = alloc_bootmem(argv_size); - int i; + if (argv_size > sizeof(argv)) { + pr_err("%s: command line too long: argv_size = %d\n", + __func__, argv_size); + } else { + int i; - cmdline[0] = 0; - simc_argv((void *)argv); + cmdline[0] = 0; + simc_argv((void *)argv); - for (i = 1; i < argc; ++i) { - if (i > 1) - strcat(cmdline, " "); - strcat(cmdline, argv[i]); + for (i = 1; i < argc; ++i) { + if (i > 1) + strcat(cmdline, " "); + strcat(cmdline, argv[i]); + } + *p_cmdline = cmdline; } - *p_cmdline = cmdline; } atomic_notifier_chain_register(&panic_notifier_list, &iss_panic_block); diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index 58c6efa9f9a9..9fe5952d117d 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -275,9 +275,9 @@ static void bfqg_and_blkg_get(struct bfq_group *bfqg) void bfqg_and_blkg_put(struct bfq_group *bfqg) { - bfqg_put(bfqg); - blkg_put(bfqg_to_blkg(bfqg)); + + bfqg_put(bfqg); } /* @stats = 0 */ diff --git a/block/bio.c b/block/bio.c index b12966e415d3..8c680a776171 100644 --- a/block/bio.c +++ b/block/bio.c @@ -2015,7 +2015,8 @@ int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg) { if (unlikely(bio->bi_blkg)) return -EBUSY; - blkg_get(blkg); + if (!blkg_try_get(blkg)) + return -ENODEV; bio->bi_blkg = blkg; return 0; } diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 694595b29b8f..c630e02836a8 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -310,28 +310,11 @@ struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, } } -static void blkg_pd_offline(struct blkcg_gq *blkg) -{ - int i; - - lockdep_assert_held(blkg->q->queue_lock); - lockdep_assert_held(&blkg->blkcg->lock); - - for (i = 0; i < BLKCG_MAX_POLS; i++) { - struct blkcg_policy *pol = blkcg_policy[i]; - - if (blkg->pd[i] && !blkg->pd[i]->offline && - pol->pd_offline_fn) { - pol->pd_offline_fn(blkg->pd[i]); - blkg->pd[i]->offline = true; - } - } -} - static void blkg_destroy(struct blkcg_gq *blkg) { struct blkcg *blkcg = blkg->blkcg; struct blkcg_gq *parent = blkg->parent; + int i; lockdep_assert_held(blkg->q->queue_lock); lockdep_assert_held(&blkcg->lock); @@ -340,6 +323,13 @@ static void blkg_destroy(struct blkcg_gq *blkg) WARN_ON_ONCE(list_empty(&blkg->q_node)); WARN_ON_ONCE(hlist_unhashed(&blkg->blkcg_node)); + for (i = 0; i < BLKCG_MAX_POLS; i++) { + struct blkcg_policy *pol = blkcg_policy[i]; + + if (blkg->pd[i] && pol->pd_offline_fn) + pol->pd_offline_fn(blkg->pd[i]); + } + if (parent) { blkg_rwstat_add_aux(&parent->stat_bytes, &blkg->stat_bytes); blkg_rwstat_add_aux(&parent->stat_ios, &blkg->stat_ios); @@ -382,7 +372,6 @@ static void blkg_destroy_all(struct request_queue *q) struct blkcg *blkcg = blkg->blkcg; spin_lock(&blkcg->lock); - blkg_pd_offline(blkg); blkg_destroy(blkg); spin_unlock(&blkcg->lock); } @@ -1053,59 +1042,64 @@ static struct cftype blkcg_legacy_files[] = { { } /* terminate */ }; +/* + * blkcg destruction is a three-stage process. + * + * 1. Destruction starts. The blkcg_css_offline() callback is invoked + * which offlines writeback. Here we tie the next stage of blkg destruction + * to the completion of writeback associated with the blkcg. This lets us + * avoid punting potentially large amounts of outstanding writeback to root + * while maintaining any ongoing policies. The next stage is triggered when + * the nr_cgwbs count goes to zero. + * + * 2. When the nr_cgwbs count goes to zero, blkcg_destroy_blkgs() is called + * and handles the destruction of blkgs. Here the css reference held by + * the blkg is put back eventually allowing blkcg_css_free() to be called. + * This work may occur in cgwb_release_workfn() on the cgwb_release + * workqueue. Any submitted ios that fail to get the blkg ref will be + * punted to the root_blkg. + * + * 3. Once the blkcg ref count goes to zero, blkcg_css_free() is called. + * This finally frees the blkcg. + */ + /** * blkcg_css_offline - cgroup css_offline callback * @css: css of interest * - * This function is called when @css is about to go away and responsible - * for offlining all blkgs pd and killing all wbs associated with @css. - * blkgs pd offline should be done while holding both q and blkcg locks. - * As blkcg lock is nested inside q lock, this function performs reverse - * double lock dancing. - * - * This is the blkcg counterpart of ioc_release_fn(). + * This function is called when @css is about to go away. Here the cgwbs are + * offlined first and only once writeback associated with the blkcg has + * finished do we start step 2 (see above). */ static void blkcg_css_offline(struct cgroup_subsys_state *css) { struct blkcg *blkcg = css_to_blkcg(css); - struct blkcg_gq *blkg; - - spin_lock_irq(&blkcg->lock); - - hlist_for_each_entry(blkg, &blkcg->blkg_list, blkcg_node) { - struct request_queue *q = blkg->q; - - if (spin_trylock(q->queue_lock)) { - blkg_pd_offline(blkg); - spin_unlock(q->queue_lock); - } else { - spin_unlock_irq(&blkcg->lock); - cpu_relax(); - spin_lock_irq(&blkcg->lock); - } - } - - spin_unlock_irq(&blkcg->lock); + /* this prevents anyone from attaching or migrating to this blkcg */ wb_blkcg_offline(blkcg); + + /* put the base cgwb reference allowing step 2 to be triggered */ + blkcg_cgwb_put(blkcg); } /** - * blkcg_destroy_all_blkgs - destroy all blkgs associated with a blkcg + * blkcg_destroy_blkgs - responsible for shooting down blkgs * @blkcg: blkcg of interest * - * This function is called when blkcg css is about to free and responsible for - * destroying all blkgs associated with @blkcg. - * blkgs should be removed while holding both q and blkcg locks. As blkcg lock + * blkgs should be removed while holding both q and blkcg locks. As blkcg lock * is nested inside q lock, this function performs reverse double lock dancing. + * Destroying the blkgs releases the reference held on the blkcg's css allowing + * blkcg_css_free to eventually be called. + * + * This is the blkcg counterpart of ioc_release_fn(). */ -static void blkcg_destroy_all_blkgs(struct blkcg *blkcg) +void blkcg_destroy_blkgs(struct blkcg *blkcg) { spin_lock_irq(&blkcg->lock); + while (!hlist_empty(&blkcg->blkg_list)) { struct blkcg_gq *blkg = hlist_entry(blkcg->blkg_list.first, - struct blkcg_gq, - blkcg_node); + struct blkcg_gq, blkcg_node); struct request_queue *q = blkg->q; if (spin_trylock(q->queue_lock)) { @@ -1117,6 +1111,7 @@ static void blkcg_destroy_all_blkgs(struct blkcg *blkcg) spin_lock_irq(&blkcg->lock); } } + spin_unlock_irq(&blkcg->lock); } @@ -1125,8 +1120,6 @@ static void blkcg_css_free(struct cgroup_subsys_state *css) struct blkcg *blkcg = css_to_blkcg(css); int i; - blkcg_destroy_all_blkgs(blkcg); - mutex_lock(&blkcg_pol_mutex); list_del(&blkcg->all_blkcgs_node); @@ -1189,6 +1182,7 @@ blkcg_css_alloc(struct cgroup_subsys_state *parent_css) INIT_HLIST_HEAD(&blkcg->blkg_list); #ifdef CONFIG_CGROUP_WRITEBACK INIT_LIST_HEAD(&blkcg->cgwb_list); + refcount_set(&blkcg->cgwb_refcnt, 1); #endif list_add_tail(&blkcg->all_blkcgs_node, &all_blkcgs); @@ -1480,11 +1474,8 @@ void blkcg_deactivate_policy(struct request_queue *q, list_for_each_entry(blkg, &q->blkg_list, q_node) { if (blkg->pd[pol->plid]) { - if (!blkg->pd[pol->plid]->offline && - pol->pd_offline_fn) { + if (pol->pd_offline_fn) pol->pd_offline_fn(blkg->pd[pol->plid]); - blkg->pd[pol->plid]->offline = true; - } pol->pd_free_fn(blkg->pd[pol->plid]); blkg->pd[pol->plid] = NULL; } @@ -1519,8 +1510,10 @@ int blkcg_policy_register(struct blkcg_policy *pol) for (i = 0; i < BLKCG_MAX_POLS; i++) if (!blkcg_policy[i]) break; - if (i >= BLKCG_MAX_POLS) + if (i >= BLKCG_MAX_POLS) { + pr_warn("blkcg_policy_register: BLKCG_MAX_POLS too small\n"); goto err_unlock; + } /* Make sure cpd/pd_alloc_fn and cpd/pd_free_fn in pairs */ if ((!pol->cpd_alloc_fn ^ !pol->cpd_free_fn) || diff --git a/block/blk-core.c b/block/blk-core.c index dee56c282efb..4dbc93f43b38 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2163,9 +2163,12 @@ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part) { const int op = bio_op(bio); - if (part->policy && (op_is_write(op) && !op_is_flush(op))) { + if (part->policy && op_is_write(op)) { char b[BDEVNAME_SIZE]; + if (op_is_flush(bio->bi_opf) && !bio_sectors(bio)) + return false; + WARN_ONCE(1, "generic_make_request: Trying to write " "to read-only block-device %s (partno %d)\n", diff --git a/block/blk-throttle.c b/block/blk-throttle.c index a3eede00d302..01d0620a4e4a 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -2129,8 +2129,9 @@ static inline void throtl_update_latency_buckets(struct throtl_data *td) static void blk_throtl_assoc_bio(struct throtl_grp *tg, struct bio *bio) { #ifdef CONFIG_BLK_DEV_THROTTLING_LOW - if (bio->bi_css) - bio_associate_blkg(bio, tg_to_blkg(tg)); + /* fallback to root_blkg if we fail to get a blkg ref */ + if (bio->bi_css && (bio_associate_blkg(bio, tg_to_blkg(tg)) == -ENODEV)) + bio_associate_blkg(bio, bio->bi_disk->queue->root_blkg); bio_issue_init(&bio->bi_issue, bio_sectors(bio)); #endif } diff --git a/block/blk-wbt.c b/block/blk-wbt.c index 84507d3e9a98..8e20a0677dcf 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -123,16 +123,11 @@ static void rwb_wake_all(struct rq_wb *rwb) } } -static void __wbt_done(struct rq_qos *rqos, enum wbt_flags wb_acct) +static void wbt_rqw_done(struct rq_wb *rwb, struct rq_wait *rqw, + enum wbt_flags wb_acct) { - struct rq_wb *rwb = RQWB(rqos); - struct rq_wait *rqw; int inflight, limit; - if (!(wb_acct & WBT_TRACKED)) - return; - - rqw = get_rq_wait(rwb, wb_acct); inflight = atomic_dec_return(&rqw->inflight); /* @@ -166,10 +161,22 @@ static void __wbt_done(struct rq_qos *rqos, enum wbt_flags wb_acct) int diff = limit - inflight; if (!inflight || diff >= rwb->wb_background / 2) - wake_up(&rqw->wait); + wake_up_all(&rqw->wait); } } +static void __wbt_done(struct rq_qos *rqos, enum wbt_flags wb_acct) +{ + struct rq_wb *rwb = RQWB(rqos); + struct rq_wait *rqw; + + if (!(wb_acct & WBT_TRACKED)) + return; + + rqw = get_rq_wait(rwb, wb_acct); + wbt_rqw_done(rwb, rqw, wb_acct); +} + /* * Called on completion of a request. Note that it's also called when * a request is merged, when the request gets freed. @@ -481,6 +488,34 @@ static inline unsigned int get_limit(struct rq_wb *rwb, unsigned long rw) return limit; } +struct wbt_wait_data { + struct wait_queue_entry wq; + struct task_struct *task; + struct rq_wb *rwb; + struct rq_wait *rqw; + unsigned long rw; + bool got_token; +}; + +static int wbt_wake_function(struct wait_queue_entry *curr, unsigned int mode, + int wake_flags, void *key) +{ + struct wbt_wait_data *data = container_of(curr, struct wbt_wait_data, + wq); + + /* + * If we fail to get a budget, return -1 to interrupt the wake up + * loop in __wake_up_common. + */ + if (!rq_wait_inc_below(data->rqw, get_limit(data->rwb, data->rw))) + return -1; + + data->got_token = true; + list_del_init(&curr->entry); + wake_up_process(data->task); + return 1; +} + /* * Block if we will exceed our limit, or if we are currently waiting for * the timer to kick off queuing again. @@ -491,19 +526,40 @@ static void __wbt_wait(struct rq_wb *rwb, enum wbt_flags wb_acct, __acquires(lock) { struct rq_wait *rqw = get_rq_wait(rwb, wb_acct); - DECLARE_WAITQUEUE(wait, current); + struct wbt_wait_data data = { + .wq = { + .func = wbt_wake_function, + .entry = LIST_HEAD_INIT(data.wq.entry), + }, + .task = current, + .rwb = rwb, + .rqw = rqw, + .rw = rw, + }; bool has_sleeper; has_sleeper = wq_has_sleeper(&rqw->wait); if (!has_sleeper && rq_wait_inc_below(rqw, get_limit(rwb, rw))) return; - add_wait_queue_exclusive(&rqw->wait, &wait); + prepare_to_wait_exclusive(&rqw->wait, &data.wq, TASK_UNINTERRUPTIBLE); do { - set_current_state(TASK_UNINTERRUPTIBLE); + if (data.got_token) + break; - if (!has_sleeper && rq_wait_inc_below(rqw, get_limit(rwb, rw))) + if (!has_sleeper && + rq_wait_inc_below(rqw, get_limit(rwb, rw))) { + finish_wait(&rqw->wait, &data.wq); + + /* + * We raced with wbt_wake_function() getting a token, + * which means we now have two. Put our local token + * and wake anyone else potentially waiting for one. + */ + if (data.got_token) + wbt_rqw_done(rwb, rqw, wb_acct); break; + } if (lock) { spin_unlock_irq(lock); @@ -511,11 +567,11 @@ static void __wbt_wait(struct rq_wb *rwb, enum wbt_flags wb_acct, spin_lock_irq(lock); } else io_schedule(); + has_sleeper = false; } while (1); - __set_current_state(TASK_RUNNING); - remove_wait_queue(&rqw->wait, &wait); + finish_wait(&rqw->wait, &data.wq); } static inline bool wbt_should_throttle(struct rq_wb *rwb, struct bio *bio) @@ -580,11 +636,6 @@ static void wbt_wait(struct rq_qos *rqos, struct bio *bio, spinlock_t *lock) return; } - if (current_is_kswapd()) - flags |= WBT_KSWAPD; - if (bio_op(bio) == REQ_OP_DISCARD) - flags |= WBT_DISCARD; - __wbt_wait(rwb, flags, bio->bi_opf, lock); if (!blk_stat_is_active(rwb->cb)) diff --git a/block/bsg.c b/block/bsg.c index db588add6ba6..9a442c23a715 100644 --- a/block/bsg.c +++ b/block/bsg.c @@ -37,7 +37,7 @@ struct bsg_device { struct request_queue *queue; spinlock_t lock; struct hlist_node dev_list; - atomic_t ref_count; + refcount_t ref_count; char name[20]; int max_queue; }; @@ -252,7 +252,7 @@ static int bsg_put_device(struct bsg_device *bd) mutex_lock(&bsg_mutex); - if (!atomic_dec_and_test(&bd->ref_count)) { + if (!refcount_dec_and_test(&bd->ref_count)) { mutex_unlock(&bsg_mutex); return 0; } @@ -290,7 +290,7 @@ static struct bsg_device *bsg_add_device(struct inode *inode, bd->queue = rq; - atomic_set(&bd->ref_count, 1); + refcount_set(&bd->ref_count, 1); hlist_add_head(&bd->dev_list, bsg_dev_idx_hash(iminor(inode))); strncpy(bd->name, dev_name(rq->bsg_dev.class_dev), sizeof(bd->name) - 1); @@ -308,7 +308,7 @@ static struct bsg_device *__bsg_get_device(int minor, struct request_queue *q) hlist_for_each_entry(bd, bsg_dev_idx_hash(minor), dev_list) { if (bd->queue == q) { - atomic_inc(&bd->ref_count); + refcount_inc(&bd->ref_count); goto found; } } diff --git a/block/elevator.c b/block/elevator.c index 5ea6e7d600e4..6a06b5d040e5 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -895,8 +895,7 @@ int elv_register(struct elevator_type *e) spin_lock(&elv_list_lock); if (elevator_find(e->elevator_name, e->uses_mq)) { spin_unlock(&elv_list_lock); - if (e->icq_cache) - kmem_cache_destroy(e->icq_cache); + kmem_cache_destroy(e->icq_cache); return -EBUSY; } list_add_tail(&e->list, &elv_list); diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c index 9706613eecf9..bf64cfa30feb 100644 --- a/drivers/acpi/acpi_lpss.c +++ b/drivers/acpi/acpi_lpss.c @@ -879,7 +879,7 @@ static void acpi_lpss_dismiss(struct device *dev) #define LPSS_GPIODEF0_DMA_LLP BIT(13) static DEFINE_MUTEX(lpss_iosf_mutex); -static bool lpss_iosf_d3_entered; +static bool lpss_iosf_d3_entered = true; static void lpss_iosf_enter_d3_state(void) { diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index 292088fcc624..d2e29a19890d 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -35,11 +35,11 @@ #include <linux/delay.h> #ifdef CONFIG_X86 #include <asm/mpspec.h> +#include <linux/dmi.h> #endif #include <linux/acpi_iort.h> #include <linux/pci.h> #include <acpi/apei.h> -#include <linux/dmi.h> #include <linux/suspend.h> #include "internal.h" @@ -82,10 +82,6 @@ static const struct dmi_system_id dsdt_dmi_table[] __initconst = { }, {} }; -#else -static const struct dmi_system_id dsdt_dmi_table[] __initconst = { - {} -}; #endif /* -------------------------------------------------------------------------- @@ -1033,11 +1029,16 @@ void __init acpi_early_init(void) acpi_permanent_mmap = true; +#ifdef CONFIG_X86 /* * If the machine falls into the DMI check table, - * DSDT will be copied to memory + * DSDT will be copied to memory. + * Note that calling dmi_check_system() here on other architectures + * would not be OK because only x86 initializes dmi early enough. + * Thankfully only x86 systems need such quirks for now. */ dmi_check_system(dsdt_dmi_table); +#endif status = acpi_reallocate_root_table(); if (ACPI_FAILURE(status)) { diff --git a/drivers/android/binder_alloc.c b/drivers/android/binder_alloc.c index 3f3b7b253445..64fd96eada31 100644 --- a/drivers/android/binder_alloc.c +++ b/drivers/android/binder_alloc.c @@ -332,6 +332,35 @@ err_no_vma: return vma ? -ENOMEM : -ESRCH; } + +static inline void binder_alloc_set_vma(struct binder_alloc *alloc, + struct vm_area_struct *vma) +{ + if (vma) + alloc->vma_vm_mm = vma->vm_mm; + /* + * If we see alloc->vma is not NULL, buffer data structures set up + * completely. Look at smp_rmb side binder_alloc_get_vma. + * We also want to guarantee new alloc->vma_vm_mm is always visible + * if alloc->vma is set. + */ + smp_wmb(); + alloc->vma = vma; +} + +static inline struct vm_area_struct *binder_alloc_get_vma( + struct binder_alloc *alloc) +{ + struct vm_area_struct *vma = NULL; + + if (alloc->vma) { + /* Look at description in binder_alloc_set_vma */ + smp_rmb(); + vma = alloc->vma; + } + return vma; +} + static struct binder_buffer *binder_alloc_new_buf_locked( struct binder_alloc *alloc, size_t data_size, @@ -348,7 +377,7 @@ static struct binder_buffer *binder_alloc_new_buf_locked( size_t size, data_offsets_size; int ret; - if (alloc->vma == NULL) { + if (!binder_alloc_get_vma(alloc)) { binder_alloc_debug(BINDER_DEBUG_USER_ERROR, "%d: binder_alloc_buf, no vma\n", alloc->pid); @@ -723,9 +752,7 @@ int binder_alloc_mmap_handler(struct binder_alloc *alloc, buffer->free = 1; binder_insert_free_buffer(alloc, buffer); alloc->free_async_space = alloc->buffer_size / 2; - barrier(); - alloc->vma = vma; - alloc->vma_vm_mm = vma->vm_mm; + binder_alloc_set_vma(alloc, vma); mmgrab(alloc->vma_vm_mm); return 0; @@ -754,10 +781,10 @@ void binder_alloc_deferred_release(struct binder_alloc *alloc) int buffers, page_count; struct binder_buffer *buffer; - BUG_ON(alloc->vma); - buffers = 0; mutex_lock(&alloc->mutex); + BUG_ON(alloc->vma); + while ((n = rb_first(&alloc->allocated_buffers))) { buffer = rb_entry(n, struct binder_buffer, rb_node); @@ -900,7 +927,7 @@ int binder_alloc_get_allocated_count(struct binder_alloc *alloc) */ void binder_alloc_vma_close(struct binder_alloc *alloc) { - WRITE_ONCE(alloc->vma, NULL); + binder_alloc_set_vma(alloc, NULL); } /** @@ -935,7 +962,7 @@ enum lru_status binder_alloc_free_page(struct list_head *item, index = page - alloc->pages; page_addr = (uintptr_t)alloc->buffer + index * PAGE_SIZE; - vma = alloc->vma; + vma = binder_alloc_get_vma(alloc); if (vma) { if (!mmget_not_zero(alloc->vma_vm_mm)) goto err_mmget; diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 172e32840256..599e01bcdef2 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -7394,4 +7394,4 @@ EXPORT_SYMBOL_GPL(ata_cable_unknown); EXPORT_SYMBOL_GPL(ata_cable_ignore); EXPORT_SYMBOL_GPL(ata_cable_sata); EXPORT_SYMBOL_GPL(ata_host_get); -EXPORT_SYMBOL_GPL(ata_host_put);
\ No newline at end of file +EXPORT_SYMBOL_GPL(ata_host_put); diff --git a/drivers/ata/pata_ftide010.c b/drivers/ata/pata_ftide010.c index 5d4b72e21161..569a4a662dcd 100644 --- a/drivers/ata/pata_ftide010.c +++ b/drivers/ata/pata_ftide010.c @@ -256,14 +256,12 @@ static struct ata_port_operations pata_ftide010_port_ops = { .qc_issue = ftide010_qc_issue, }; -static struct ata_port_info ftide010_port_info[] = { - { - .flags = ATA_FLAG_SLAVE_POSS, - .mwdma_mask = ATA_MWDMA2, - .udma_mask = ATA_UDMA6, - .pio_mask = ATA_PIO4, - .port_ops = &pata_ftide010_port_ops, - }, +static struct ata_port_info ftide010_port_info = { + .flags = ATA_FLAG_SLAVE_POSS, + .mwdma_mask = ATA_MWDMA2, + .udma_mask = ATA_UDMA6, + .pio_mask = ATA_PIO4, + .port_ops = &pata_ftide010_port_ops, }; #if IS_ENABLED(CONFIG_SATA_GEMINI) @@ -349,6 +347,7 @@ static int pata_ftide010_gemini_cable_detect(struct ata_port *ap) } static int pata_ftide010_gemini_init(struct ftide010 *ftide, + struct ata_port_info *pi, bool is_ata1) { struct device *dev = ftide->dev; @@ -373,7 +372,13 @@ static int pata_ftide010_gemini_init(struct ftide010 *ftide, /* Flag port as SATA-capable */ if (gemini_sata_bridge_enabled(sg, is_ata1)) - ftide010_port_info[0].flags |= ATA_FLAG_SATA; + pi->flags |= ATA_FLAG_SATA; + + /* This device has broken DMA, only PIO works */ + if (of_machine_is_compatible("itian,sq201")) { + pi->mwdma_mask = 0; + pi->udma_mask = 0; + } /* * We assume that a simple 40-wire cable is used in the PATA mode. @@ -435,6 +440,7 @@ static int pata_ftide010_gemini_init(struct ftide010 *ftide, } #else static int pata_ftide010_gemini_init(struct ftide010 *ftide, + struct ata_port_info *pi, bool is_ata1) { return -ENOTSUPP; @@ -446,7 +452,7 @@ static int pata_ftide010_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct device_node *np = dev->of_node; - const struct ata_port_info pi = ftide010_port_info[0]; + struct ata_port_info pi = ftide010_port_info; const struct ata_port_info *ppi[] = { &pi, NULL }; struct ftide010 *ftide; struct resource *res; @@ -490,6 +496,7 @@ static int pata_ftide010_probe(struct platform_device *pdev) * are ATA0. This will also set up the cable types. */ ret = pata_ftide010_gemini_init(ftide, + &pi, (res->start == 0x63400000)); if (ret) goto err_dis_clk; diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c index 0943e7065e0e..b3c0498ee433 100644 --- a/drivers/base/firmware_loader/main.c +++ b/drivers/base/firmware_loader/main.c @@ -209,21 +209,24 @@ static struct fw_priv *__lookup_fw_priv(const char *fw_name) static int alloc_lookup_fw_priv(const char *fw_name, struct firmware_cache *fwc, struct fw_priv **fw_priv, void *dbuf, - size_t size) + size_t size, enum fw_opt opt_flags) { struct fw_priv *tmp; spin_lock(&fwc->lock); - tmp = __lookup_fw_priv(fw_name); - if (tmp) { - kref_get(&tmp->ref); - spin_unlock(&fwc->lock); - *fw_priv = tmp; - pr_debug("batched request - sharing the same struct fw_priv and lookup for multiple requests\n"); - return 1; + if (!(opt_flags & FW_OPT_NOCACHE)) { + tmp = __lookup_fw_priv(fw_name); + if (tmp) { + kref_get(&tmp->ref); + spin_unlock(&fwc->lock); + *fw_priv = tmp; + pr_debug("batched request - sharing the same struct fw_priv and lookup for multiple requests\n"); + return 1; + } } + tmp = __allocate_fw_priv(fw_name, fwc, dbuf, size); - if (tmp) + if (tmp && !(opt_flags & FW_OPT_NOCACHE)) list_add(&tmp->list, &fwc->head); spin_unlock(&fwc->lock); @@ -493,7 +496,8 @@ int assign_fw(struct firmware *fw, struct device *device, */ static int _request_firmware_prepare(struct firmware **firmware_p, const char *name, - struct device *device, void *dbuf, size_t size) + struct device *device, void *dbuf, size_t size, + enum fw_opt opt_flags) { struct firmware *firmware; struct fw_priv *fw_priv; @@ -511,7 +515,8 @@ _request_firmware_prepare(struct firmware **firmware_p, const char *name, return 0; /* assigned */ } - ret = alloc_lookup_fw_priv(name, &fw_cache, &fw_priv, dbuf, size); + ret = alloc_lookup_fw_priv(name, &fw_cache, &fw_priv, dbuf, size, + opt_flags); /* * bind with 'priv' now to avoid warning in failure path @@ -571,7 +576,8 @@ _request_firmware(const struct firmware **firmware_p, const char *name, goto out; } - ret = _request_firmware_prepare(&fw, name, device, buf, size); + ret = _request_firmware_prepare(&fw, name, device, buf, size, + opt_flags); if (ret <= 0) /* error or already assigned */ goto out; diff --git a/drivers/base/memory.c b/drivers/base/memory.c index c8a1cb0b6136..817320c7c4c1 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -417,25 +417,23 @@ static ssize_t show_valid_zones(struct device *dev, int nid; /* - * The block contains more than one zone can not be offlined. - * This can happen e.g. for ZONE_DMA and ZONE_DMA32 - */ - if (!test_pages_in_a_zone(start_pfn, start_pfn + nr_pages, &valid_start_pfn, &valid_end_pfn)) - return sprintf(buf, "none\n"); - - start_pfn = valid_start_pfn; - nr_pages = valid_end_pfn - start_pfn; - - /* * Check the existing zone. Make sure that we do that only on the * online nodes otherwise the page_zone is not reliable */ if (mem->state == MEM_ONLINE) { + /* + * The block contains more than one zone can not be offlined. + * This can happen e.g. for ZONE_DMA and ZONE_DMA32 + */ + if (!test_pages_in_a_zone(start_pfn, start_pfn + nr_pages, + &valid_start_pfn, &valid_end_pfn)) + return sprintf(buf, "none\n"); + start_pfn = valid_start_pfn; strcat(buf, page_zone(pfn_to_page(start_pfn))->name); goto out; } - nid = pfn_to_nid(start_pfn); + nid = mem->nid; default_zone = zone_for_pfn_range(MMOP_ONLINE_KEEP, nid, start_pfn, nr_pages); strcat(buf, default_zone->name); diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c index 8e2e4757adcb..5a42ae4078c2 100644 --- a/drivers/base/power/clock_ops.c +++ b/drivers/base/power/clock_ops.c @@ -185,7 +185,7 @@ EXPORT_SYMBOL_GPL(of_pm_clk_add_clk); int of_pm_clk_add_clks(struct device *dev) { struct clk **clks; - unsigned int i, count; + int i, count; int ret; if (!dev || !dev->of_node) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 3863c00372bb..14a51254c3db 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1239,6 +1239,9 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd, case NBD_SET_SOCK: return nbd_add_socket(nbd, arg, false); case NBD_SET_BLKSIZE: + if (!arg || !is_power_of_2(arg) || arg < 512 || + arg > PAGE_SIZE) + return -EINVAL; nbd_size_set(nbd, arg, div_s64(config->bytesize, arg)); return 0; diff --git a/drivers/block/null_blk.h b/drivers/block/null_blk.h index d81781f22dba..34e0030f0592 100644 --- a/drivers/block/null_blk.h +++ b/drivers/block/null_blk.h @@ -87,10 +87,10 @@ struct nullb { #ifdef CONFIG_BLK_DEV_ZONED int null_zone_init(struct nullb_device *dev); void null_zone_exit(struct nullb_device *dev); -blk_status_t null_zone_report(struct nullb *nullb, - struct nullb_cmd *cmd); -void null_zone_write(struct nullb_cmd *cmd); -void null_zone_reset(struct nullb_cmd *cmd); +blk_status_t null_zone_report(struct nullb *nullb, struct bio *bio); +void null_zone_write(struct nullb_cmd *cmd, sector_t sector, + unsigned int nr_sectors); +void null_zone_reset(struct nullb_cmd *cmd, sector_t sector); #else static inline int null_zone_init(struct nullb_device *dev) { @@ -98,11 +98,14 @@ static inline int null_zone_init(struct nullb_device *dev) } static inline void null_zone_exit(struct nullb_device *dev) {} static inline blk_status_t null_zone_report(struct nullb *nullb, - struct nullb_cmd *cmd) + struct bio *bio) { return BLK_STS_NOTSUPP; } -static inline void null_zone_write(struct nullb_cmd *cmd) {} -static inline void null_zone_reset(struct nullb_cmd *cmd) {} +static inline void null_zone_write(struct nullb_cmd *cmd, sector_t sector, + unsigned int nr_sectors) +{ +} +static inline void null_zone_reset(struct nullb_cmd *cmd, sector_t sector) {} #endif /* CONFIG_BLK_DEV_ZONED */ #endif /* __NULL_BLK_H */ diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c index 6127e3ff7b4b..093b614d6524 100644 --- a/drivers/block/null_blk_main.c +++ b/drivers/block/null_blk_main.c @@ -1157,16 +1157,33 @@ static void null_restart_queue_async(struct nullb *nullb) } } +static bool cmd_report_zone(struct nullb *nullb, struct nullb_cmd *cmd) +{ + struct nullb_device *dev = cmd->nq->dev; + + if (dev->queue_mode == NULL_Q_BIO) { + if (bio_op(cmd->bio) == REQ_OP_ZONE_REPORT) { + cmd->error = null_zone_report(nullb, cmd->bio); + return true; + } + } else { + if (req_op(cmd->rq) == REQ_OP_ZONE_REPORT) { + cmd->error = null_zone_report(nullb, cmd->rq->bio); + return true; + } + } + + return false; +} + static blk_status_t null_handle_cmd(struct nullb_cmd *cmd) { struct nullb_device *dev = cmd->nq->dev; struct nullb *nullb = dev->nullb; int err = 0; - if (req_op(cmd->rq) == REQ_OP_ZONE_REPORT) { - cmd->error = null_zone_report(nullb, cmd); + if (cmd_report_zone(nullb, cmd)) goto out; - } if (test_bit(NULLB_DEV_FL_THROTTLED, &dev->flags)) { struct request *rq = cmd->rq; @@ -1234,10 +1251,24 @@ static blk_status_t null_handle_cmd(struct nullb_cmd *cmd) cmd->error = errno_to_blk_status(err); if (!cmd->error && dev->zoned) { - if (req_op(cmd->rq) == REQ_OP_WRITE) - null_zone_write(cmd); - else if (req_op(cmd->rq) == REQ_OP_ZONE_RESET) - null_zone_reset(cmd); + sector_t sector; + unsigned int nr_sectors; + int op; + + if (dev->queue_mode == NULL_Q_BIO) { + op = bio_op(cmd->bio); + sector = cmd->bio->bi_iter.bi_sector; + nr_sectors = cmd->bio->bi_iter.bi_size >> 9; + } else { + op = req_op(cmd->rq); + sector = blk_rq_pos(cmd->rq); + nr_sectors = blk_rq_sectors(cmd->rq); + } + + if (op == REQ_OP_WRITE) + null_zone_write(cmd, sector, nr_sectors); + else if (op == REQ_OP_ZONE_RESET) + null_zone_reset(cmd, sector); } out: /* Complete IO by inline, softirq or timer */ diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk_zoned.c index a979ca00d7be..7c6b86d98700 100644 --- a/drivers/block/null_blk_zoned.c +++ b/drivers/block/null_blk_zoned.c @@ -48,8 +48,8 @@ void null_zone_exit(struct nullb_device *dev) kvfree(dev->zones); } -static void null_zone_fill_rq(struct nullb_device *dev, struct request *rq, - unsigned int zno, unsigned int nr_zones) +static void null_zone_fill_bio(struct nullb_device *dev, struct bio *bio, + unsigned int zno, unsigned int nr_zones) { struct blk_zone_report_hdr *hdr = NULL; struct bio_vec bvec; @@ -57,7 +57,7 @@ static void null_zone_fill_rq(struct nullb_device *dev, struct request *rq, void *addr; unsigned int zones_to_cpy; - bio_for_each_segment(bvec, rq->bio, iter) { + bio_for_each_segment(bvec, bio, iter) { addr = kmap_atomic(bvec.bv_page); zones_to_cpy = bvec.bv_len / sizeof(struct blk_zone); @@ -84,29 +84,24 @@ static void null_zone_fill_rq(struct nullb_device *dev, struct request *rq, } } -blk_status_t null_zone_report(struct nullb *nullb, - struct nullb_cmd *cmd) +blk_status_t null_zone_report(struct nullb *nullb, struct bio *bio) { struct nullb_device *dev = nullb->dev; - struct request *rq = cmd->rq; - unsigned int zno = null_zone_no(dev, blk_rq_pos(rq)); + unsigned int zno = null_zone_no(dev, bio->bi_iter.bi_sector); unsigned int nr_zones = dev->nr_zones - zno; - unsigned int max_zones = (blk_rq_bytes(rq) / - sizeof(struct blk_zone)) - 1; + unsigned int max_zones; + max_zones = (bio->bi_iter.bi_size / sizeof(struct blk_zone)) - 1; nr_zones = min_t(unsigned int, nr_zones, max_zones); - - null_zone_fill_rq(nullb->dev, rq, zno, nr_zones); + null_zone_fill_bio(nullb->dev, bio, zno, nr_zones); return BLK_STS_OK; } -void null_zone_write(struct nullb_cmd *cmd) +void null_zone_write(struct nullb_cmd *cmd, sector_t sector, + unsigned int nr_sectors) { struct nullb_device *dev = cmd->nq->dev; - struct request *rq = cmd->rq; - sector_t sector = blk_rq_pos(rq); - unsigned int rq_sectors = blk_rq_sectors(rq); unsigned int zno = null_zone_no(dev, sector); struct blk_zone *zone = &dev->zones[zno]; @@ -118,7 +113,7 @@ void null_zone_write(struct nullb_cmd *cmd) case BLK_ZONE_COND_EMPTY: case BLK_ZONE_COND_IMP_OPEN: /* Writes must be at the write pointer position */ - if (blk_rq_pos(rq) != zone->wp) { + if (sector != zone->wp) { cmd->error = BLK_STS_IOERR; break; } @@ -126,7 +121,7 @@ void null_zone_write(struct nullb_cmd *cmd) if (zone->cond == BLK_ZONE_COND_EMPTY) zone->cond = BLK_ZONE_COND_IMP_OPEN; - zone->wp += rq_sectors; + zone->wp += nr_sectors; if (zone->wp == zone->start + zone->len) zone->cond = BLK_ZONE_COND_FULL; break; @@ -137,11 +132,10 @@ void null_zone_write(struct nullb_cmd *cmd) } } -void null_zone_reset(struct nullb_cmd *cmd) +void null_zone_reset(struct nullb_cmd *cmd, sector_t sector) { struct nullb_device *dev = cmd->nq->dev; - struct request *rq = cmd->rq; - unsigned int zno = null_zone_no(dev, blk_rq_pos(rq)); + unsigned int zno = null_zone_no(dev, sector); struct blk_zone *zone = &dev->zones[zno]; zone->cond = BLK_ZONE_COND_EMPTY; diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 7915f3b03736..73ed5f3a862d 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -4207,11 +4207,13 @@ static ssize_t rbd_parent_show(struct device *dev, count += sprintf(&buf[count], "%s" "pool_id %llu\npool_name %s\n" + "pool_ns %s\n" "image_id %s\nimage_name %s\n" "snap_id %llu\nsnap_name %s\n" "overlap %llu\n", !count ? "" : "\n", /* first? */ spec->pool_id, spec->pool_name, + spec->pool_ns ?: "", spec->image_id, spec->image_name ?: "(unknown)", spec->snap_id, spec->snap_name, rbd_dev->parent_overlap); @@ -4584,47 +4586,177 @@ static int rbd_dev_v2_features(struct rbd_device *rbd_dev) &rbd_dev->header.features); } +struct parent_image_info { + u64 pool_id; + const char *pool_ns; + const char *image_id; + u64 snap_id; + + bool has_overlap; + u64 overlap; +}; + +/* + * The caller is responsible for @pii. + */ +static int decode_parent_image_spec(void **p, void *end, + struct parent_image_info *pii) +{ + u8 struct_v; + u32 struct_len; + int ret; + + ret = ceph_start_decoding(p, end, 1, "ParentImageSpec", + &struct_v, &struct_len); + if (ret) + return ret; + + ceph_decode_64_safe(p, end, pii->pool_id, e_inval); + pii->pool_ns = ceph_extract_encoded_string(p, end, NULL, GFP_KERNEL); + if (IS_ERR(pii->pool_ns)) { + ret = PTR_ERR(pii->pool_ns); + pii->pool_ns = NULL; + return ret; + } + pii->image_id = ceph_extract_encoded_string(p, end, NULL, GFP_KERNEL); + if (IS_ERR(pii->image_id)) { + ret = PTR_ERR(pii->image_id); + pii->image_id = NULL; + return ret; + } + ceph_decode_64_safe(p, end, pii->snap_id, e_inval); + return 0; + +e_inval: + return -EINVAL; +} + +static int __get_parent_info(struct rbd_device *rbd_dev, + struct page *req_page, + struct page *reply_page, + struct parent_image_info *pii) +{ + struct ceph_osd_client *osdc = &rbd_dev->rbd_client->client->osdc; + size_t reply_len = PAGE_SIZE; + void *p, *end; + int ret; + + ret = ceph_osdc_call(osdc, &rbd_dev->header_oid, &rbd_dev->header_oloc, + "rbd", "parent_get", CEPH_OSD_FLAG_READ, + req_page, sizeof(u64), reply_page, &reply_len); + if (ret) + return ret == -EOPNOTSUPP ? 1 : ret; + + p = page_address(reply_page); + end = p + reply_len; + ret = decode_parent_image_spec(&p, end, pii); + if (ret) + return ret; + + ret = ceph_osdc_call(osdc, &rbd_dev->header_oid, &rbd_dev->header_oloc, + "rbd", "parent_overlap_get", CEPH_OSD_FLAG_READ, + req_page, sizeof(u64), reply_page, &reply_len); + if (ret) + return ret; + + p = page_address(reply_page); + end = p + reply_len; + ceph_decode_8_safe(&p, end, pii->has_overlap, e_inval); + if (pii->has_overlap) + ceph_decode_64_safe(&p, end, pii->overlap, e_inval); + + return 0; + +e_inval: + return -EINVAL; +} + +/* + * The caller is responsible for @pii. + */ +static int __get_parent_info_legacy(struct rbd_device *rbd_dev, + struct page *req_page, + struct page *reply_page, + struct parent_image_info *pii) +{ + struct ceph_osd_client *osdc = &rbd_dev->rbd_client->client->osdc; + size_t reply_len = PAGE_SIZE; + void *p, *end; + int ret; + + ret = ceph_osdc_call(osdc, &rbd_dev->header_oid, &rbd_dev->header_oloc, + "rbd", "get_parent", CEPH_OSD_FLAG_READ, + req_page, sizeof(u64), reply_page, &reply_len); + if (ret) + return ret; + + p = page_address(reply_page); + end = p + reply_len; + ceph_decode_64_safe(&p, end, pii->pool_id, e_inval); + pii->image_id = ceph_extract_encoded_string(&p, end, NULL, GFP_KERNEL); + if (IS_ERR(pii->image_id)) { + ret = PTR_ERR(pii->image_id); + pii->image_id = NULL; + return ret; + } + ceph_decode_64_safe(&p, end, pii->snap_id, e_inval); + pii->has_overlap = true; + ceph_decode_64_safe(&p, end, pii->overlap, e_inval); + + return 0; + +e_inval: + return -EINVAL; +} + +static int get_parent_info(struct rbd_device *rbd_dev, + struct parent_image_info *pii) +{ + struct page *req_page, *reply_page; + void *p; + int ret; + + req_page = alloc_page(GFP_KERNEL); + if (!req_page) + return -ENOMEM; + + reply_page = alloc_page(GFP_KERNEL); + if (!reply_page) { + __free_page(req_page); + return -ENOMEM; + } + + p = page_address(req_page); + ceph_encode_64(&p, rbd_dev->spec->snap_id); + ret = __get_parent_info(rbd_dev, req_page, reply_page, pii); + if (ret > 0) + ret = __get_parent_info_legacy(rbd_dev, req_page, reply_page, + pii); + + __free_page(req_page); + __free_page(reply_page); + return ret; +} + static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev) { struct rbd_spec *parent_spec; - size_t size; - void *reply_buf = NULL; - __le64 snapid; - void *p; - void *end; - u64 pool_id; - char *image_id; - u64 snap_id; - u64 overlap; + struct parent_image_info pii = { 0 }; int ret; parent_spec = rbd_spec_alloc(); if (!parent_spec) return -ENOMEM; - size = sizeof (__le64) + /* pool_id */ - sizeof (__le32) + RBD_IMAGE_ID_LEN_MAX + /* image_id */ - sizeof (__le64) + /* snap_id */ - sizeof (__le64); /* overlap */ - reply_buf = kmalloc(size, GFP_KERNEL); - if (!reply_buf) { - ret = -ENOMEM; + ret = get_parent_info(rbd_dev, &pii); + if (ret) goto out_err; - } - snapid = cpu_to_le64(rbd_dev->spec->snap_id); - ret = rbd_obj_method_sync(rbd_dev, &rbd_dev->header_oid, - &rbd_dev->header_oloc, "get_parent", - &snapid, sizeof(snapid), reply_buf, size); - dout("%s: rbd_obj_method_sync returned %d\n", __func__, ret); - if (ret < 0) - goto out_err; + dout("%s pool_id %llu pool_ns %s image_id %s snap_id %llu has_overlap %d overlap %llu\n", + __func__, pii.pool_id, pii.pool_ns, pii.image_id, pii.snap_id, + pii.has_overlap, pii.overlap); - p = reply_buf; - end = reply_buf + ret; - ret = -ERANGE; - ceph_decode_64_safe(&p, end, pool_id, out_err); - if (pool_id == CEPH_NOPOOL) { + if (pii.pool_id == CEPH_NOPOOL || !pii.has_overlap) { /* * Either the parent never existed, or we have * record of it but the image got flattened so it no @@ -4633,6 +4765,10 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev) * overlap to 0. The effect of this is that all new * requests will be treated as if the image had no * parent. + * + * If !pii.has_overlap, the parent image spec is not + * applicable. It's there to avoid duplication in each + * snapshot record. */ if (rbd_dev->parent_overlap) { rbd_dev->parent_overlap = 0; @@ -4647,51 +4783,36 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev) /* The ceph file layout needs to fit pool id in 32 bits */ ret = -EIO; - if (pool_id > (u64)U32_MAX) { + if (pii.pool_id > (u64)U32_MAX) { rbd_warn(NULL, "parent pool id too large (%llu > %u)", - (unsigned long long)pool_id, U32_MAX); + (unsigned long long)pii.pool_id, U32_MAX); goto out_err; } - image_id = ceph_extract_encoded_string(&p, end, NULL, GFP_KERNEL); - if (IS_ERR(image_id)) { - ret = PTR_ERR(image_id); - goto out_err; - } - ceph_decode_64_safe(&p, end, snap_id, out_err); - ceph_decode_64_safe(&p, end, overlap, out_err); - /* * The parent won't change (except when the clone is * flattened, already handled that). So we only need to * record the parent spec we have not already done so. */ if (!rbd_dev->parent_spec) { - parent_spec->pool_id = pool_id; - parent_spec->image_id = image_id; - parent_spec->snap_id = snap_id; - - /* TODO: support cloning across namespaces */ - if (rbd_dev->spec->pool_ns) { - parent_spec->pool_ns = kstrdup(rbd_dev->spec->pool_ns, - GFP_KERNEL); - if (!parent_spec->pool_ns) { - ret = -ENOMEM; - goto out_err; - } + parent_spec->pool_id = pii.pool_id; + if (pii.pool_ns && *pii.pool_ns) { + parent_spec->pool_ns = pii.pool_ns; + pii.pool_ns = NULL; } + parent_spec->image_id = pii.image_id; + pii.image_id = NULL; + parent_spec->snap_id = pii.snap_id; rbd_dev->parent_spec = parent_spec; parent_spec = NULL; /* rbd_dev now owns this */ - } else { - kfree(image_id); } /* * We always update the parent overlap. If it's zero we issue * a warning, as we will proceed as if there was no parent. */ - if (!overlap) { + if (!pii.overlap) { if (parent_spec) { /* refresh, careful to warn just once */ if (rbd_dev->parent_overlap) @@ -4702,14 +4823,14 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev) rbd_warn(rbd_dev, "clone is standalone (overlap 0)"); } } - rbd_dev->parent_overlap = overlap; + rbd_dev->parent_overlap = pii.overlap; out: ret = 0; out_err: - kfree(reply_buf); + kfree(pii.pool_ns); + kfree(pii.image_id); rbd_spec_put(parent_spec); - return ret; } diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index b55b245e8052..fd1e19f1a49f 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -84,6 +84,18 @@ MODULE_PARM_DESC(max_persistent_grants, "Maximum number of grants to map persistently"); /* + * How long a persistent grant is allowed to remain allocated without being in + * use. The time is in seconds, 0 means indefinitely long. + */ + +static unsigned int xen_blkif_pgrant_timeout = 60; +module_param_named(persistent_grant_unused_seconds, xen_blkif_pgrant_timeout, + uint, 0644); +MODULE_PARM_DESC(persistent_grant_unused_seconds, + "Time in seconds an unused persistent grant is allowed to " + "remain allocated. Default is 60, 0 means unlimited."); + +/* * Maximum number of rings/queues blkback supports, allow as many queues as there * are CPUs if user has not specified a value. */ @@ -123,6 +135,13 @@ module_param(log_stats, int, 0644); /* Number of free pages to remove on each call to gnttab_free_pages */ #define NUM_BATCH_FREE_PAGES 10 +static inline bool persistent_gnt_timeout(struct persistent_gnt *persistent_gnt) +{ + return xen_blkif_pgrant_timeout && + (jiffies - persistent_gnt->last_used >= + HZ * xen_blkif_pgrant_timeout); +} + static inline int get_free_page(struct xen_blkif_ring *ring, struct page **page) { unsigned long flags; @@ -236,8 +255,7 @@ static int add_persistent_gnt(struct xen_blkif_ring *ring, } } - bitmap_zero(persistent_gnt->flags, PERSISTENT_GNT_FLAGS_SIZE); - set_bit(PERSISTENT_GNT_ACTIVE, persistent_gnt->flags); + persistent_gnt->active = true; /* Add new node and rebalance tree. */ rb_link_node(&(persistent_gnt->node), parent, new); rb_insert_color(&(persistent_gnt->node), &ring->persistent_gnts); @@ -261,11 +279,11 @@ static struct persistent_gnt *get_persistent_gnt(struct xen_blkif_ring *ring, else if (gref > data->gnt) node = node->rb_right; else { - if(test_bit(PERSISTENT_GNT_ACTIVE, data->flags)) { + if (data->active) { pr_alert_ratelimited("requesting a grant already in use\n"); return NULL; } - set_bit(PERSISTENT_GNT_ACTIVE, data->flags); + data->active = true; atomic_inc(&ring->persistent_gnt_in_use); return data; } @@ -276,10 +294,10 @@ static struct persistent_gnt *get_persistent_gnt(struct xen_blkif_ring *ring, static void put_persistent_gnt(struct xen_blkif_ring *ring, struct persistent_gnt *persistent_gnt) { - if(!test_bit(PERSISTENT_GNT_ACTIVE, persistent_gnt->flags)) + if (!persistent_gnt->active) pr_alert_ratelimited("freeing a grant already unused\n"); - set_bit(PERSISTENT_GNT_WAS_ACTIVE, persistent_gnt->flags); - clear_bit(PERSISTENT_GNT_ACTIVE, persistent_gnt->flags); + persistent_gnt->last_used = jiffies; + persistent_gnt->active = false; atomic_dec(&ring->persistent_gnt_in_use); } @@ -371,26 +389,26 @@ static void purge_persistent_gnt(struct xen_blkif_ring *ring) struct persistent_gnt *persistent_gnt; struct rb_node *n; unsigned int num_clean, total; - bool scan_used = false, clean_used = false; + bool scan_used = false; struct rb_root *root; - if (ring->persistent_gnt_c < xen_blkif_max_pgrants || - (ring->persistent_gnt_c == xen_blkif_max_pgrants && - !ring->blkif->vbd.overflow_max_grants)) { - goto out; - } - if (work_busy(&ring->persistent_purge_work)) { pr_alert_ratelimited("Scheduled work from previous purge is still busy, cannot purge list\n"); goto out; } - num_clean = (xen_blkif_max_pgrants / 100) * LRU_PERCENT_CLEAN; - num_clean = ring->persistent_gnt_c - xen_blkif_max_pgrants + num_clean; - num_clean = min(ring->persistent_gnt_c, num_clean); - if ((num_clean == 0) || - (num_clean > (ring->persistent_gnt_c - atomic_read(&ring->persistent_gnt_in_use)))) - goto out; + if (ring->persistent_gnt_c < xen_blkif_max_pgrants || + (ring->persistent_gnt_c == xen_blkif_max_pgrants && + !ring->blkif->vbd.overflow_max_grants)) { + num_clean = 0; + } else { + num_clean = (xen_blkif_max_pgrants / 100) * LRU_PERCENT_CLEAN; + num_clean = ring->persistent_gnt_c - xen_blkif_max_pgrants + + num_clean; + num_clean = min(ring->persistent_gnt_c, num_clean); + pr_debug("Going to purge at least %u persistent grants\n", + num_clean); + } /* * At this point, we can assure that there will be no calls @@ -401,9 +419,7 @@ static void purge_persistent_gnt(struct xen_blkif_ring *ring) * number of grants. */ - total = num_clean; - - pr_debug("Going to purge %u persistent grants\n", num_clean); + total = 0; BUG_ON(!list_empty(&ring->persistent_purge_list)); root = &ring->persistent_gnts; @@ -412,46 +428,37 @@ purge_list: BUG_ON(persistent_gnt->handle == BLKBACK_INVALID_HANDLE); - if (clean_used) { - clear_bit(PERSISTENT_GNT_WAS_ACTIVE, persistent_gnt->flags); + if (persistent_gnt->active) continue; - } - - if (test_bit(PERSISTENT_GNT_ACTIVE, persistent_gnt->flags)) + if (!scan_used && !persistent_gnt_timeout(persistent_gnt)) continue; - if (!scan_used && - (test_bit(PERSISTENT_GNT_WAS_ACTIVE, persistent_gnt->flags))) + if (scan_used && total >= num_clean) continue; rb_erase(&persistent_gnt->node, root); list_add(&persistent_gnt->remove_node, &ring->persistent_purge_list); - if (--num_clean == 0) - goto finished; + total++; } /* - * If we get here it means we also need to start cleaning + * Check whether we also need to start cleaning * grants that were used since last purge in order to cope * with the requested num */ - if (!scan_used && !clean_used) { - pr_debug("Still missing %u purged frames\n", num_clean); + if (!scan_used && total < num_clean) { + pr_debug("Still missing %u purged frames\n", num_clean - total); scan_used = true; goto purge_list; } -finished: - if (!clean_used) { - pr_debug("Finished scanning for grants to clean, removing used flag\n"); - clean_used = true; - goto purge_list; - } - ring->persistent_gnt_c -= (total - num_clean); - ring->blkif->vbd.overflow_max_grants = 0; + if (total) { + ring->persistent_gnt_c -= total; + ring->blkif->vbd.overflow_max_grants = 0; - /* We can defer this work */ - schedule_work(&ring->persistent_purge_work); - pr_debug("Purged %u/%u\n", (total - num_clean), total); + /* We can defer this work */ + schedule_work(&ring->persistent_purge_work); + pr_debug("Purged %u/%u\n", num_clean, total); + } out: return; diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h index ecb35fe8ca8d..1d3002d773f7 100644 --- a/drivers/block/xen-blkback/common.h +++ b/drivers/block/xen-blkback/common.h @@ -233,16 +233,6 @@ struct xen_vbd { struct backend_info; -/* Number of available flags */ -#define PERSISTENT_GNT_FLAGS_SIZE 2 -/* This persistent grant is currently in use */ -#define PERSISTENT_GNT_ACTIVE 0 -/* - * This persistent grant has been used, this flag is set when we remove the - * PERSISTENT_GNT_ACTIVE, to know that this grant has been used recently. - */ -#define PERSISTENT_GNT_WAS_ACTIVE 1 - /* Number of requests that we can fit in a ring */ #define XEN_BLKIF_REQS_PER_PAGE 32 @@ -250,7 +240,8 @@ struct persistent_gnt { struct page *page; grant_ref_t gnt; grant_handle_t handle; - DECLARE_BITMAP(flags, PERSISTENT_GNT_FLAGS_SIZE); + unsigned long last_used; + bool active; struct rb_node node; struct list_head remove_node; }; @@ -278,7 +269,6 @@ struct xen_blkif_ring { wait_queue_head_t pending_free_wq; /* Tree to store persistent grants. */ - spinlock_t pers_gnts_lock; struct rb_root persistent_gnts; unsigned int persistent_gnt_c; atomic_t persistent_gnt_in_use; diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 8986adab9bf5..a71d817e900d 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -46,6 +46,7 @@ #include <linux/scatterlist.h> #include <linux/bitmap.h> #include <linux/list.h> +#include <linux/workqueue.h> #include <xen/xen.h> #include <xen/xenbus.h> @@ -121,6 +122,8 @@ static inline struct blkif_req *blkif_req(struct request *rq) static DEFINE_MUTEX(blkfront_mutex); static const struct block_device_operations xlvbd_block_fops; +static struct delayed_work blkfront_work; +static LIST_HEAD(info_list); /* * Maximum number of segments in indirect requests, the actual value used by @@ -216,6 +219,7 @@ struct blkfront_info /* Save uncomplete reqs and bios for migration. */ struct list_head requests; struct bio_list bio_list; + struct list_head info_list; }; static unsigned int nr_minors; @@ -1759,6 +1763,12 @@ abort_transaction: return err; } +static void free_info(struct blkfront_info *info) +{ + list_del(&info->info_list); + kfree(info); +} + /* Common code used when first setting up, and when resuming. */ static int talk_to_blkback(struct xenbus_device *dev, struct blkfront_info *info) @@ -1880,7 +1890,10 @@ again: destroy_blkring: blkif_free(info, 0); - kfree(info); + mutex_lock(&blkfront_mutex); + free_info(info); + mutex_unlock(&blkfront_mutex); + dev_set_drvdata(&dev->dev, NULL); return err; @@ -1991,6 +2004,10 @@ static int blkfront_probe(struct xenbus_device *dev, info->handle = simple_strtoul(strrchr(dev->nodename, '/')+1, NULL, 0); dev_set_drvdata(&dev->dev, info); + mutex_lock(&blkfront_mutex); + list_add(&info->info_list, &info_list); + mutex_unlock(&blkfront_mutex); + return 0; } @@ -2301,6 +2318,12 @@ static void blkfront_gather_backend_features(struct blkfront_info *info) if (indirect_segments <= BLKIF_MAX_SEGMENTS_PER_REQUEST) indirect_segments = 0; info->max_indirect_segments = indirect_segments; + + if (info->feature_persistent) { + mutex_lock(&blkfront_mutex); + schedule_delayed_work(&blkfront_work, HZ * 10); + mutex_unlock(&blkfront_mutex); + } } /* @@ -2482,7 +2505,9 @@ static int blkfront_remove(struct xenbus_device *xbdev) mutex_unlock(&info->mutex); if (!bdev) { - kfree(info); + mutex_lock(&blkfront_mutex); + free_info(info); + mutex_unlock(&blkfront_mutex); return 0; } @@ -2502,7 +2527,9 @@ static int blkfront_remove(struct xenbus_device *xbdev) if (info && !bdev->bd_openers) { xlvbd_release_gendisk(info); disk->private_data = NULL; - kfree(info); + mutex_lock(&blkfront_mutex); + free_info(info); + mutex_unlock(&blkfront_mutex); } mutex_unlock(&bdev->bd_mutex); @@ -2585,7 +2612,7 @@ static void blkif_release(struct gendisk *disk, fmode_t mode) dev_info(disk_to_dev(bdev->bd_disk), "releasing disk\n"); xlvbd_release_gendisk(info); disk->private_data = NULL; - kfree(info); + free_info(info); } out: @@ -2618,6 +2645,61 @@ static struct xenbus_driver blkfront_driver = { .is_ready = blkfront_is_ready, }; +static void purge_persistent_grants(struct blkfront_info *info) +{ + unsigned int i; + unsigned long flags; + + for (i = 0; i < info->nr_rings; i++) { + struct blkfront_ring_info *rinfo = &info->rinfo[i]; + struct grant *gnt_list_entry, *tmp; + + spin_lock_irqsave(&rinfo->ring_lock, flags); + + if (rinfo->persistent_gnts_c == 0) { + spin_unlock_irqrestore(&rinfo->ring_lock, flags); + continue; + } + + list_for_each_entry_safe(gnt_list_entry, tmp, &rinfo->grants, + node) { + if (gnt_list_entry->gref == GRANT_INVALID_REF || + gnttab_query_foreign_access(gnt_list_entry->gref)) + continue; + + list_del(&gnt_list_entry->node); + gnttab_end_foreign_access(gnt_list_entry->gref, 0, 0UL); + rinfo->persistent_gnts_c--; + __free_page(gnt_list_entry->page); + kfree(gnt_list_entry); + } + + spin_unlock_irqrestore(&rinfo->ring_lock, flags); + } +} + +static void blkfront_delay_work(struct work_struct *work) +{ + struct blkfront_info *info; + bool need_schedule_work = false; + + mutex_lock(&blkfront_mutex); + + list_for_each_entry(info, &info_list, info_list) { + if (info->feature_persistent) { + need_schedule_work = true; + mutex_lock(&info->mutex); + purge_persistent_grants(info); + mutex_unlock(&info->mutex); + } + } + + if (need_schedule_work) + schedule_delayed_work(&blkfront_work, HZ * 10); + + mutex_unlock(&blkfront_mutex); +} + static int __init xlblk_init(void) { int ret; @@ -2626,6 +2708,15 @@ static int __init xlblk_init(void) if (!xen_domain()) return -ENODEV; + if (!xen_has_pv_disk_devices()) + return -ENODEV; + + if (register_blkdev(XENVBD_MAJOR, DEV_NAME)) { + pr_warn("xen_blk: can't get major %d with name %s\n", + XENVBD_MAJOR, DEV_NAME); + return -ENODEV; + } + if (xen_blkif_max_segments < BLKIF_MAX_SEGMENTS_PER_REQUEST) xen_blkif_max_segments = BLKIF_MAX_SEGMENTS_PER_REQUEST; @@ -2641,14 +2732,7 @@ static int __init xlblk_init(void) xen_blkif_max_queues = nr_cpus; } - if (!xen_has_pv_disk_devices()) - return -ENODEV; - - if (register_blkdev(XENVBD_MAJOR, DEV_NAME)) { - printk(KERN_WARNING "xen_blk: can't get major %d with name %s\n", - XENVBD_MAJOR, DEV_NAME); - return -ENODEV; - } + INIT_DELAYED_WORK(&blkfront_work, blkfront_delay_work); ret = xenbus_register_frontend(&blkfront_driver); if (ret) { @@ -2663,6 +2747,8 @@ module_init(xlblk_init); static void __exit xlblk_exit(void) { + cancel_delayed_work_sync(&blkfront_work); + xenbus_unregister_driver(&blkfront_driver); unregister_blkdev(XENVBD_MAJOR, DEV_NAME); kfree(minors); diff --git a/drivers/bluetooth/Kconfig b/drivers/bluetooth/Kconfig index 2df11cc08a46..845b0314ce3a 100644 --- a/drivers/bluetooth/Kconfig +++ b/drivers/bluetooth/Kconfig @@ -200,6 +200,7 @@ config BT_HCIUART_RTL depends on BT_HCIUART depends on BT_HCIUART_SERDEV depends on GPIOLIB + depends on ACPI select BT_HCIUART_3WIRE select BT_RTL help diff --git a/drivers/bluetooth/btmtkuart.c b/drivers/bluetooth/btmtkuart.c index ed2a5c7cb77f..4593baff2bc9 100644 --- a/drivers/bluetooth/btmtkuart.c +++ b/drivers/bluetooth/btmtkuart.c @@ -144,8 +144,10 @@ static int mtk_setup_fw(struct hci_dev *hdev) fw_size = fw->size; /* The size of patch header is 30 bytes, should be skip */ - if (fw_size < 30) - return -EINVAL; + if (fw_size < 30) { + err = -EINVAL; + goto free_fw; + } fw_size -= 30; fw_ptr += 30; @@ -172,8 +174,8 @@ static int mtk_setup_fw(struct hci_dev *hdev) fw_ptr += dlen; } +free_fw: release_firmware(fw); - return err; } diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c index 963bb0309e25..ea6238ed5c0e 100644 --- a/drivers/bluetooth/hci_ldisc.c +++ b/drivers/bluetooth/hci_ldisc.c @@ -543,6 +543,8 @@ static void hci_uart_tty_close(struct tty_struct *tty) } clear_bit(HCI_UART_PROTO_SET, &hu->flags); + percpu_free_rwsem(&hu->proto_lock); + kfree(hu); } diff --git a/drivers/bus/ti-sysc.c b/drivers/bus/ti-sysc.c index c9bac9dc4637..e4fe954e63a9 100644 --- a/drivers/bus/ti-sysc.c +++ b/drivers/bus/ti-sysc.c @@ -498,32 +498,29 @@ static int sysc_check_registers(struct sysc *ddata) /** * syc_ioremap - ioremap register space for the interconnect target module - * @ddata: deviec driver data + * @ddata: device driver data * * Note that the interconnect target module registers can be anywhere - * within the first child device address space. For example, SGX has - * them at offset 0x1fc00 in the 32MB module address space. We just - * what we need around the interconnect target module registers. + * within the interconnect target module range. For example, SGX has + * them at offset 0x1fc00 in the 32MB module address space. And cpsw + * has them at offset 0x1200 in the CPSW_WR child. Usually the + * the interconnect target module registers are at the beginning of + * the module range though. */ static int sysc_ioremap(struct sysc *ddata) { - u32 size = 0; - - if (ddata->offsets[SYSC_SYSSTATUS] >= 0) - size = ddata->offsets[SYSC_SYSSTATUS]; - else if (ddata->offsets[SYSC_SYSCONFIG] >= 0) - size = ddata->offsets[SYSC_SYSCONFIG]; - else if (ddata->offsets[SYSC_REVISION] >= 0) - size = ddata->offsets[SYSC_REVISION]; - else - return -EINVAL; + int size; - size &= 0xfff00; - size += SZ_256; + size = max3(ddata->offsets[SYSC_REVISION], + ddata->offsets[SYSC_SYSCONFIG], + ddata->offsets[SYSC_SYSSTATUS]); + + if (size < 0 || (size + sizeof(u32)) > ddata->module_size) + return -EINVAL; ddata->module_va = devm_ioremap(ddata->dev, ddata->module_pa, - size); + size + sizeof(u32)); if (!ddata->module_va) return -EIO; @@ -1224,10 +1221,10 @@ static int sysc_child_suspend_noirq(struct device *dev) if (!pm_runtime_status_suspended(dev)) { error = pm_generic_runtime_suspend(dev); if (error) { - dev_err(dev, "%s error at %i: %i\n", - __func__, __LINE__, error); + dev_warn(dev, "%s busy at %i: %i\n", + __func__, __LINE__, error); - return error; + return 0; } error = sysc_runtime_suspend(ddata->dev); diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index 113fc6edb2b0..a5d5a96479bf 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -2546,7 +2546,7 @@ static int cdrom_ioctl_drive_status(struct cdrom_device_info *cdi, if (!CDROM_CAN(CDC_SELECT_DISC) || (arg == CDSL_CURRENT || arg == CDSL_NONE)) return cdi->ops->drive_status(cdi, CDSL_CURRENT); - if (((int)arg >= cdi->capacity)) + if (arg >= cdi->capacity) return -EINVAL; return cdrom_slot_status(cdi, arg); } diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig index ce277ee0a28a..40728491f37b 100644 --- a/drivers/char/Kconfig +++ b/drivers/char/Kconfig @@ -566,5 +566,5 @@ config RANDOM_TRUST_CPU that CPU manufacturer (perhaps with the insistence or mandate of a Nation State's intelligence or law enforcement agencies) has not installed a hidden back door to compromise the CPU's - random number generation facilities. - + random number generation facilities. This can also be configured + at boot with "random.trust_cpu=on/off". diff --git a/drivers/char/ipmi/ipmi_bt_sm.c b/drivers/char/ipmi/ipmi_bt_sm.c index a3397664f800..97d6856c9c0f 100644 --- a/drivers/char/ipmi/ipmi_bt_sm.c +++ b/drivers/char/ipmi/ipmi_bt_sm.c @@ -59,8 +59,6 @@ enum bt_states { BT_STATE_RESET3, BT_STATE_RESTART, BT_STATE_PRINTME, - BT_STATE_CAPABILITIES_BEGIN, - BT_STATE_CAPABILITIES_END, BT_STATE_LONG_BUSY /* BT doesn't get hosed :-) */ }; @@ -86,7 +84,6 @@ struct si_sm_data { int error_retries; /* end of "common" fields */ int nonzero_status; /* hung BMCs stay all 0 */ enum bt_states complete; /* to divert the state machine */ - int BT_CAP_outreqs; long BT_CAP_req2rsp; int BT_CAP_retries; /* Recommended retries */ }; @@ -137,8 +134,6 @@ static char *state2txt(unsigned char state) case BT_STATE_RESET3: return("RESET3"); case BT_STATE_RESTART: return("RESTART"); case BT_STATE_LONG_BUSY: return("LONG_BUSY"); - case BT_STATE_CAPABILITIES_BEGIN: return("CAP_BEGIN"); - case BT_STATE_CAPABILITIES_END: return("CAP_END"); } return("BAD STATE"); } @@ -185,7 +180,6 @@ static unsigned int bt_init_data(struct si_sm_data *bt, struct si_sm_io *io) bt->complete = BT_STATE_IDLE; /* end here */ bt->BT_CAP_req2rsp = BT_NORMAL_TIMEOUT * USEC_PER_SEC; bt->BT_CAP_retries = BT_NORMAL_RETRY_LIMIT; - /* BT_CAP_outreqs == zero is a flag to read BT Capabilities */ return 3; /* We claim 3 bytes of space; ought to check SPMI table */ } @@ -451,7 +445,7 @@ static enum si_sm_result error_recovery(struct si_sm_data *bt, static enum si_sm_result bt_event(struct si_sm_data *bt, long time) { - unsigned char status, BT_CAP[8]; + unsigned char status; static enum bt_states last_printed = BT_STATE_PRINTME; int i; @@ -504,12 +498,6 @@ static enum si_sm_result bt_event(struct si_sm_data *bt, long time) if (status & BT_H_BUSY) /* clear a leftover H_BUSY */ BT_CONTROL(BT_H_BUSY); - bt->timeout = bt->BT_CAP_req2rsp; - - /* Read BT capabilities if it hasn't been done yet */ - if (!bt->BT_CAP_outreqs) - BT_STATE_CHANGE(BT_STATE_CAPABILITIES_BEGIN, - SI_SM_CALL_WITHOUT_DELAY); BT_SI_SM_RETURN(SI_SM_IDLE); case BT_STATE_XACTION_START: @@ -614,37 +602,6 @@ static enum si_sm_result bt_event(struct si_sm_data *bt, long time) BT_STATE_CHANGE(BT_STATE_XACTION_START, SI_SM_CALL_WITH_DELAY); - /* - * Get BT Capabilities, using timing of upper level state machine. - * Set outreqs to prevent infinite loop on timeout. - */ - case BT_STATE_CAPABILITIES_BEGIN: - bt->BT_CAP_outreqs = 1; - { - unsigned char GetBT_CAP[] = { 0x18, 0x36 }; - bt->state = BT_STATE_IDLE; - bt_start_transaction(bt, GetBT_CAP, sizeof(GetBT_CAP)); - } - bt->complete = BT_STATE_CAPABILITIES_END; - BT_STATE_CHANGE(BT_STATE_XACTION_START, - SI_SM_CALL_WITH_DELAY); - - case BT_STATE_CAPABILITIES_END: - i = bt_get_result(bt, BT_CAP, sizeof(BT_CAP)); - bt_init_data(bt, bt->io); - if ((i == 8) && !BT_CAP[2]) { - bt->BT_CAP_outreqs = BT_CAP[3]; - bt->BT_CAP_req2rsp = BT_CAP[6] * USEC_PER_SEC; - bt->BT_CAP_retries = BT_CAP[7]; - } else - printk(KERN_WARNING "IPMI BT: using default values\n"); - if (!bt->BT_CAP_outreqs) - bt->BT_CAP_outreqs = 1; - printk(KERN_WARNING "IPMI BT: req2rsp=%ld secs retries=%d\n", - bt->BT_CAP_req2rsp / USEC_PER_SEC, bt->BT_CAP_retries); - bt->timeout = bt->BT_CAP_req2rsp; - return SI_SM_CALL_WITHOUT_DELAY; - default: /* should never occur */ return error_recovery(bt, status, @@ -655,6 +612,11 @@ static enum si_sm_result bt_event(struct si_sm_data *bt, long time) static int bt_detect(struct si_sm_data *bt) { + unsigned char GetBT_CAP[] = { 0x18, 0x36 }; + unsigned char BT_CAP[8]; + enum si_sm_result smi_result; + int rv; + /* * It's impossible for the BT status and interrupt registers to be * all 1's, (assuming a properly functioning, self-initialized BMC) @@ -665,6 +627,48 @@ static int bt_detect(struct si_sm_data *bt) if ((BT_STATUS == 0xFF) && (BT_INTMASK_R == 0xFF)) return 1; reset_flags(bt); + + /* + * Try getting the BT capabilities here. + */ + rv = bt_start_transaction(bt, GetBT_CAP, sizeof(GetBT_CAP)); + if (rv) { + dev_warn(bt->io->dev, + "Can't start capabilities transaction: %d\n", rv); + goto out_no_bt_cap; + } + + smi_result = SI_SM_CALL_WITHOUT_DELAY; + for (;;) { + if (smi_result == SI_SM_CALL_WITH_DELAY || + smi_result == SI_SM_CALL_WITH_TICK_DELAY) { + schedule_timeout_uninterruptible(1); + smi_result = bt_event(bt, jiffies_to_usecs(1)); + } else if (smi_result == SI_SM_CALL_WITHOUT_DELAY) { + smi_result = bt_event(bt, 0); + } else + break; + } + + rv = bt_get_result(bt, BT_CAP, sizeof(BT_CAP)); + bt_init_data(bt, bt->io); + if (rv < 8) { + dev_warn(bt->io->dev, "bt cap response too short: %d\n", rv); + goto out_no_bt_cap; + } + + if (BT_CAP[2]) { + dev_warn(bt->io->dev, "Error fetching bt cap: %x\n", BT_CAP[2]); +out_no_bt_cap: + dev_warn(bt->io->dev, "using default values\n"); + } else { + bt->BT_CAP_req2rsp = BT_CAP[6] * USEC_PER_SEC; + bt->BT_CAP_retries = BT_CAP[7]; + } + + dev_info(bt->io->dev, "req2rsp=%ld secs retries=%d\n", + bt->BT_CAP_req2rsp / USEC_PER_SEC, bt->BT_CAP_retries); + return 0; } diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index 51832b8a2c62..7fc9612070a1 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -3381,39 +3381,45 @@ int ipmi_register_smi(const struct ipmi_smi_handlers *handlers, rv = handlers->start_processing(send_info, intf); if (rv) - goto out; + goto out_err; rv = __bmc_get_device_id(intf, NULL, &id, NULL, NULL, i); if (rv) { dev_err(si_dev, "Unable to get the device id: %d\n", rv); - goto out; + goto out_err_started; } mutex_lock(&intf->bmc_reg_mutex); rv = __scan_channels(intf, &id); mutex_unlock(&intf->bmc_reg_mutex); + if (rv) + goto out_err_bmc_reg; - out: - if (rv) { - ipmi_bmc_unregister(intf); - list_del_rcu(&intf->link); - mutex_unlock(&ipmi_interfaces_mutex); - synchronize_srcu(&ipmi_interfaces_srcu); - cleanup_srcu_struct(&intf->users_srcu); - kref_put(&intf->refcount, intf_free); - } else { - /* - * Keep memory order straight for RCU readers. Make - * sure everything else is committed to memory before - * setting intf_num to mark the interface valid. - */ - smp_wmb(); - intf->intf_num = i; - mutex_unlock(&ipmi_interfaces_mutex); + /* + * Keep memory order straight for RCU readers. Make + * sure everything else is committed to memory before + * setting intf_num to mark the interface valid. + */ + smp_wmb(); + intf->intf_num = i; + mutex_unlock(&ipmi_interfaces_mutex); - /* After this point the interface is legal to use. */ - call_smi_watchers(i, intf->si_dev); - } + /* After this point the interface is legal to use. */ + call_smi_watchers(i, intf->si_dev); + + return 0; + + out_err_bmc_reg: + ipmi_bmc_unregister(intf); + out_err_started: + if (intf->handlers->shutdown) + intf->handlers->shutdown(intf->send_info); + out_err: + list_del_rcu(&intf->link); + mutex_unlock(&ipmi_interfaces_mutex); + synchronize_srcu(&ipmi_interfaces_srcu); + cleanup_srcu_struct(&intf->users_srcu); + kref_put(&intf->refcount, intf_free); return rv; } @@ -3504,7 +3510,8 @@ void ipmi_unregister_smi(struct ipmi_smi *intf) } srcu_read_unlock(&intf->users_srcu, index); - intf->handlers->shutdown(intf->send_info); + if (intf->handlers->shutdown) + intf->handlers->shutdown(intf->send_info); cleanup_smi_msgs(intf); diff --git a/drivers/char/ipmi/ipmi_si_intf.c b/drivers/char/ipmi/ipmi_si_intf.c index 90ec010bffbd..5faa917df1b6 100644 --- a/drivers/char/ipmi/ipmi_si_intf.c +++ b/drivers/char/ipmi/ipmi_si_intf.c @@ -2083,18 +2083,9 @@ static int try_smi_init(struct smi_info *new_smi) si_to_str[new_smi->io.si_type]); WARN_ON(new_smi->io.dev->init_name != NULL); - kfree(init_name); - - return 0; - -out_err: - if (new_smi->intf) { - ipmi_unregister_smi(new_smi->intf); - new_smi->intf = NULL; - } + out_err: kfree(init_name); - return rv; } @@ -2227,6 +2218,8 @@ static void shutdown_smi(void *send_info) kfree(smi_info->si_sm); smi_info->si_sm = NULL; + + smi_info->intf = NULL; } /* @@ -2240,10 +2233,8 @@ static void cleanup_one_si(struct smi_info *smi_info) list_del(&smi_info->link); - if (smi_info->intf) { + if (smi_info->intf) ipmi_unregister_smi(smi_info->intf); - smi_info->intf = NULL; - } if (smi_info->pdev) { if (smi_info->pdev_registered) diff --git a/drivers/char/ipmi/ipmi_ssif.c b/drivers/char/ipmi/ipmi_ssif.c index 18e4650c233b..29e67a80fb20 100644 --- a/drivers/char/ipmi/ipmi_ssif.c +++ b/drivers/char/ipmi/ipmi_ssif.c @@ -181,6 +181,8 @@ struct ssif_addr_info { struct device *dev; struct i2c_client *client; + struct i2c_client *added_client; + struct mutex clients_mutex; struct list_head clients; @@ -1214,18 +1216,11 @@ static void shutdown_ssif(void *send_info) complete(&ssif_info->wake_thread); kthread_stop(ssif_info->thread); } - - /* - * No message can be outstanding now, we have removed the - * upper layer and it permitted us to do so. - */ - kfree(ssif_info); } static int ssif_remove(struct i2c_client *client) { struct ssif_info *ssif_info = i2c_get_clientdata(client); - struct ipmi_smi *intf; struct ssif_addr_info *addr_info; if (!ssif_info) @@ -1235,9 +1230,7 @@ static int ssif_remove(struct i2c_client *client) * After this point, we won't deliver anything asychronously * to the message handler. We can unregister ourself. */ - intf = ssif_info->intf; - ssif_info->intf = NULL; - ipmi_unregister_smi(intf); + ipmi_unregister_smi(ssif_info->intf); list_for_each_entry(addr_info, &ssif_infos, link) { if (addr_info->client == client) { @@ -1246,6 +1239,8 @@ static int ssif_remove(struct i2c_client *client) } } + kfree(ssif_info); + return 0; } @@ -1648,15 +1643,9 @@ static int ssif_probe(struct i2c_client *client, const struct i2c_device_id *id) out: if (rv) { - /* - * Note that if addr_info->client is assigned, we - * leave it. The i2c client hangs around even if we - * return a failure here, and the failure here is not - * propagated back to the i2c code. This seems to be - * design intent, strange as it may be. But if we - * don't leave it, ssif_platform_remove will not remove - * the client like it should. - */ + if (addr_info) + addr_info->client = NULL; + dev_err(&client->dev, "Unable to start IPMI SSIF: %d\n", rv); kfree(ssif_info); } @@ -1676,7 +1665,8 @@ static int ssif_adapter_handler(struct device *adev, void *opaque) if (adev->type != &i2c_adapter_type) return 0; - i2c_new_device(to_i2c_adapter(adev), &addr_info->binfo); + addr_info->added_client = i2c_new_device(to_i2c_adapter(adev), + &addr_info->binfo); if (!addr_info->adapter_name) return 1; /* Only try the first I2C adapter by default. */ @@ -1849,7 +1839,7 @@ static int ssif_platform_remove(struct platform_device *dev) return 0; mutex_lock(&ssif_infos_mutex); - i2c_unregister_device(addr_info->client); + i2c_unregister_device(addr_info->added_client); list_del(&addr_info->link); kfree(addr_info); diff --git a/drivers/char/ipmi/kcs_bmc.c b/drivers/char/ipmi/kcs_bmc.c index bb882ab161fe..e6124bd548df 100644 --- a/drivers/char/ipmi/kcs_bmc.c +++ b/drivers/char/ipmi/kcs_bmc.c @@ -16,6 +16,8 @@ #include "kcs_bmc.h" +#define DEVICE_NAME "ipmi-kcs" + #define KCS_MSG_BUFSIZ 1000 #define KCS_ZERO_DATA 0 @@ -429,8 +431,6 @@ struct kcs_bmc *kcs_bmc_alloc(struct device *dev, int sizeof_priv, u32 channel) if (!kcs_bmc) return NULL; - dev_set_name(dev, "ipmi-kcs%u", channel); - spin_lock_init(&kcs_bmc->lock); kcs_bmc->channel = channel; @@ -444,7 +444,8 @@ struct kcs_bmc *kcs_bmc_alloc(struct device *dev, int sizeof_priv, u32 channel) return NULL; kcs_bmc->miscdev.minor = MISC_DYNAMIC_MINOR; - kcs_bmc->miscdev.name = dev_name(dev); + kcs_bmc->miscdev.name = devm_kasprintf(dev, GFP_KERNEL, "%s%u", + DEVICE_NAME, channel); kcs_bmc->miscdev.fops = &kcs_bmc_fops; return kcs_bmc; diff --git a/drivers/char/random.c b/drivers/char/random.c index bf5f99fc36f1..c75b6cdf0053 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -779,6 +779,13 @@ static struct crng_state **crng_node_pool __read_mostly; static void invalidate_batched_entropy(void); +static bool trust_cpu __ro_after_init = IS_ENABLED(CONFIG_RANDOM_TRUST_CPU); +static int __init parse_trust_cpu(char *arg) +{ + return kstrtobool(arg, &trust_cpu); +} +early_param("random.trust_cpu", parse_trust_cpu); + static void crng_initialize(struct crng_state *crng) { int i; @@ -799,12 +806,10 @@ static void crng_initialize(struct crng_state *crng) } crng->state[i] ^= rv; } -#ifdef CONFIG_RANDOM_TRUST_CPU - if (arch_init) { + if (trust_cpu && arch_init) { crng_init = 2; pr_notice("random: crng done (trusting CPU's manufacturer)\n"); } -#endif crng->init_time = jiffies - CRNG_RESEED_INTERVAL - 1; } diff --git a/drivers/clk/clk-npcm7xx.c b/drivers/clk/clk-npcm7xx.c index 740af90a9508..c5edf8f2fd19 100644 --- a/drivers/clk/clk-npcm7xx.c +++ b/drivers/clk/clk-npcm7xx.c @@ -558,8 +558,8 @@ static void __init npcm7xx_clk_init(struct device_node *clk_np) if (!clk_base) goto npcm7xx_init_error; - npcm7xx_clk_data = kzalloc(sizeof(*npcm7xx_clk_data->hws) * - NPCM7XX_NUM_CLOCKS + sizeof(npcm7xx_clk_data), GFP_KERNEL); + npcm7xx_clk_data = kzalloc(struct_size(npcm7xx_clk_data, hws, + NPCM7XX_NUM_CLOCKS), GFP_KERNEL); if (!npcm7xx_clk_data) goto npcm7xx_init_np_err; diff --git a/drivers/clk/x86/clk-pmc-atom.c b/drivers/clk/x86/clk-pmc-atom.c index 08ef69945ffb..d977193842df 100644 --- a/drivers/clk/x86/clk-pmc-atom.c +++ b/drivers/clk/x86/clk-pmc-atom.c @@ -55,6 +55,7 @@ struct clk_plt_data { u8 nparents; struct clk_plt *clks[PMC_CLK_NUM]; struct clk_lookup *mclk_lookup; + struct clk_lookup *ether_clk_lookup; }; /* Return an index in parent table */ @@ -186,13 +187,6 @@ static struct clk_plt *plt_clk_register(struct platform_device *pdev, int id, pclk->reg = base + PMC_CLK_CTL_OFFSET + id * PMC_CLK_CTL_SIZE; spin_lock_init(&pclk->lock); - /* - * If the clock was already enabled by the firmware mark it as critical - * to avoid it being gated by the clock framework if no driver owns it. - */ - if (plt_clk_is_enabled(&pclk->hw)) - init.flags |= CLK_IS_CRITICAL; - ret = devm_clk_hw_register(&pdev->dev, &pclk->hw); if (ret) { pclk = ERR_PTR(ret); @@ -351,11 +345,20 @@ static int plt_clk_probe(struct platform_device *pdev) goto err_unreg_clk_plt; } + data->ether_clk_lookup = clkdev_hw_create(&data->clks[4]->hw, + "ether_clk", NULL); + if (!data->ether_clk_lookup) { + err = -ENOMEM; + goto err_drop_mclk; + } + plt_clk_free_parent_names_loop(parent_names, data->nparents); platform_set_drvdata(pdev, data); return 0; +err_drop_mclk: + clkdev_drop(data->mclk_lookup); err_unreg_clk_plt: plt_clk_unregister_loop(data, i); plt_clk_unregister_parents(data); @@ -369,6 +372,7 @@ static int plt_clk_remove(struct platform_device *pdev) data = platform_get_drvdata(pdev); + clkdev_drop(data->ether_clk_lookup); clkdev_drop(data->mclk_lookup); plt_clk_unregister_loop(data, PMC_CLK_NUM); plt_clk_unregister_parents(data); diff --git a/drivers/clk/x86/clk-st.c b/drivers/clk/x86/clk-st.c index fb62f3938008..3a0996f2d556 100644 --- a/drivers/clk/x86/clk-st.c +++ b/drivers/clk/x86/clk-st.c @@ -46,7 +46,7 @@ static int st_clk_probe(struct platform_device *pdev) clk_oscout1_parents, ARRAY_SIZE(clk_oscout1_parents), 0, st_data->base + CLKDRVSTR2, OSCOUT1CLK25MHZ, 3, 0, NULL); - clk_set_parent(hws[ST_CLK_MUX]->clk, hws[ST_CLK_25M]->clk); + clk_set_parent(hws[ST_CLK_MUX]->clk, hws[ST_CLK_48M]->clk); hws[ST_CLK_GATE] = clk_hw_register_gate(NULL, "oscout1", "oscout1_mux", 0, st_data->base + MISCCLKCNTL1, OSCCLKENB, diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c index 110483f0e3fb..e26a40971b26 100644 --- a/drivers/cpuidle/governors/menu.c +++ b/drivers/cpuidle/governors/menu.c @@ -379,9 +379,20 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, if (idx == -1) idx = i; /* first enabled state */ if (s->target_residency > data->predicted_us) { - if (!tick_nohz_tick_stopped()) + if (data->predicted_us < TICK_USEC) break; + if (!tick_nohz_tick_stopped()) { + /* + * If the state selected so far is shallow, + * waking up early won't hurt, so retain the + * tick in that case and let the governor run + * again in the next iteration of the loop. + */ + expected_interval = drv->states[idx].target_residency; + break; + } + /* * If the state selected so far is shallow and this * state's target residency matches the time till the diff --git a/drivers/crypto/caam/caamalg_qi.c b/drivers/crypto/caam/caamalg_qi.c index 6e61cc93c2b0..d7aa7d7ff102 100644 --- a/drivers/crypto/caam/caamalg_qi.c +++ b/drivers/crypto/caam/caamalg_qi.c @@ -679,10 +679,8 @@ static int xts_ablkcipher_setkey(struct crypto_ablkcipher *ablkcipher, int ret = 0; if (keylen != 2 * AES_MIN_KEY_SIZE && keylen != 2 * AES_MAX_KEY_SIZE) { - crypto_ablkcipher_set_flags(ablkcipher, - CRYPTO_TFM_RES_BAD_KEY_LEN); dev_err(jrdev, "key size mismatch\n"); - return -EINVAL; + goto badkey; } ctx->cdata.keylen = keylen; @@ -715,7 +713,7 @@ static int xts_ablkcipher_setkey(struct crypto_ablkcipher *ablkcipher, return ret; badkey: crypto_ablkcipher_set_flags(ablkcipher, CRYPTO_TFM_RES_BAD_KEY_LEN); - return 0; + return -EINVAL; } /* diff --git a/drivers/crypto/caam/caampkc.c b/drivers/crypto/caam/caampkc.c index 578ea63a3109..f26d62e5533a 100644 --- a/drivers/crypto/caam/caampkc.c +++ b/drivers/crypto/caam/caampkc.c @@ -71,8 +71,8 @@ static void rsa_priv_f2_unmap(struct device *dev, struct rsa_edesc *edesc, dma_unmap_single(dev, pdb->d_dma, key->d_sz, DMA_TO_DEVICE); dma_unmap_single(dev, pdb->p_dma, p_sz, DMA_TO_DEVICE); dma_unmap_single(dev, pdb->q_dma, q_sz, DMA_TO_DEVICE); - dma_unmap_single(dev, pdb->tmp1_dma, p_sz, DMA_TO_DEVICE); - dma_unmap_single(dev, pdb->tmp2_dma, q_sz, DMA_TO_DEVICE); + dma_unmap_single(dev, pdb->tmp1_dma, p_sz, DMA_BIDIRECTIONAL); + dma_unmap_single(dev, pdb->tmp2_dma, q_sz, DMA_BIDIRECTIONAL); } static void rsa_priv_f3_unmap(struct device *dev, struct rsa_edesc *edesc, @@ -90,8 +90,8 @@ static void rsa_priv_f3_unmap(struct device *dev, struct rsa_edesc *edesc, dma_unmap_single(dev, pdb->dp_dma, p_sz, DMA_TO_DEVICE); dma_unmap_single(dev, pdb->dq_dma, q_sz, DMA_TO_DEVICE); dma_unmap_single(dev, pdb->c_dma, p_sz, DMA_TO_DEVICE); - dma_unmap_single(dev, pdb->tmp1_dma, p_sz, DMA_TO_DEVICE); - dma_unmap_single(dev, pdb->tmp2_dma, q_sz, DMA_TO_DEVICE); + dma_unmap_single(dev, pdb->tmp1_dma, p_sz, DMA_BIDIRECTIONAL); + dma_unmap_single(dev, pdb->tmp2_dma, q_sz, DMA_BIDIRECTIONAL); } /* RSA Job Completion handler */ @@ -417,13 +417,13 @@ static int set_rsa_priv_f2_pdb(struct akcipher_request *req, goto unmap_p; } - pdb->tmp1_dma = dma_map_single(dev, key->tmp1, p_sz, DMA_TO_DEVICE); + pdb->tmp1_dma = dma_map_single(dev, key->tmp1, p_sz, DMA_BIDIRECTIONAL); if (dma_mapping_error(dev, pdb->tmp1_dma)) { dev_err(dev, "Unable to map RSA tmp1 memory\n"); goto unmap_q; } - pdb->tmp2_dma = dma_map_single(dev, key->tmp2, q_sz, DMA_TO_DEVICE); + pdb->tmp2_dma = dma_map_single(dev, key->tmp2, q_sz, DMA_BIDIRECTIONAL); if (dma_mapping_error(dev, pdb->tmp2_dma)) { dev_err(dev, "Unable to map RSA tmp2 memory\n"); goto unmap_tmp1; @@ -451,7 +451,7 @@ static int set_rsa_priv_f2_pdb(struct akcipher_request *req, return 0; unmap_tmp1: - dma_unmap_single(dev, pdb->tmp1_dma, p_sz, DMA_TO_DEVICE); + dma_unmap_single(dev, pdb->tmp1_dma, p_sz, DMA_BIDIRECTIONAL); unmap_q: dma_unmap_single(dev, pdb->q_dma, q_sz, DMA_TO_DEVICE); unmap_p: @@ -504,13 +504,13 @@ static int set_rsa_priv_f3_pdb(struct akcipher_request *req, goto unmap_dq; } - pdb->tmp1_dma = dma_map_single(dev, key->tmp1, p_sz, DMA_TO_DEVICE); + pdb->tmp1_dma = dma_map_single(dev, key->tmp1, p_sz, DMA_BIDIRECTIONAL); if (dma_mapping_error(dev, pdb->tmp1_dma)) { dev_err(dev, "Unable to map RSA tmp1 memory\n"); goto unmap_qinv; } - pdb->tmp2_dma = dma_map_single(dev, key->tmp2, q_sz, DMA_TO_DEVICE); + pdb->tmp2_dma = dma_map_single(dev, key->tmp2, q_sz, DMA_BIDIRECTIONAL); if (dma_mapping_error(dev, pdb->tmp2_dma)) { dev_err(dev, "Unable to map RSA tmp2 memory\n"); goto unmap_tmp1; @@ -538,7 +538,7 @@ static int set_rsa_priv_f3_pdb(struct akcipher_request *req, return 0; unmap_tmp1: - dma_unmap_single(dev, pdb->tmp1_dma, p_sz, DMA_TO_DEVICE); + dma_unmap_single(dev, pdb->tmp1_dma, p_sz, DMA_BIDIRECTIONAL); unmap_qinv: dma_unmap_single(dev, pdb->c_dma, p_sz, DMA_TO_DEVICE); unmap_dq: diff --git a/drivers/crypto/caam/jr.c b/drivers/crypto/caam/jr.c index f4f258075b89..acdd72016ffe 100644 --- a/drivers/crypto/caam/jr.c +++ b/drivers/crypto/caam/jr.c @@ -190,7 +190,8 @@ static void caam_jr_dequeue(unsigned long devarg) BUG_ON(CIRC_CNT(head, tail + i, JOBR_DEPTH) <= 0); /* Unmap just-run descriptor so we can post-process */ - dma_unmap_single(dev, jrp->outring[hw_idx].desc, + dma_unmap_single(dev, + caam_dma_to_cpu(jrp->outring[hw_idx].desc), jrp->entinfo[sw_idx].desc_size, DMA_TO_DEVICE); diff --git a/drivers/crypto/cavium/nitrox/nitrox_dev.h b/drivers/crypto/cavium/nitrox/nitrox_dev.h index 9a476bb6d4c7..af596455b420 100644 --- a/drivers/crypto/cavium/nitrox/nitrox_dev.h +++ b/drivers/crypto/cavium/nitrox/nitrox_dev.h @@ -35,6 +35,7 @@ struct nitrox_cmdq { /* requests in backlog queues */ atomic_t backlog_count; + int write_idx; /* command size 32B/64B */ u8 instr_size; u8 qno; @@ -87,7 +88,7 @@ struct nitrox_bh { struct bh_data *slc; }; -/* NITROX-5 driver state */ +/* NITROX-V driver state */ #define NITROX_UCODE_LOADED 0 #define NITROX_READY 1 diff --git a/drivers/crypto/cavium/nitrox/nitrox_lib.c b/drivers/crypto/cavium/nitrox/nitrox_lib.c index ebe267379ac9..4d31df07777f 100644 --- a/drivers/crypto/cavium/nitrox/nitrox_lib.c +++ b/drivers/crypto/cavium/nitrox/nitrox_lib.c @@ -36,6 +36,7 @@ static int cmdq_common_init(struct nitrox_cmdq *cmdq) cmdq->head = PTR_ALIGN(cmdq->head_unaligned, PKT_IN_ALIGN); cmdq->dma = PTR_ALIGN(cmdq->dma_unaligned, PKT_IN_ALIGN); cmdq->qsize = (qsize + PKT_IN_ALIGN); + cmdq->write_idx = 0; spin_lock_init(&cmdq->response_lock); spin_lock_init(&cmdq->cmdq_lock); diff --git a/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c b/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c index deaefd532aaa..4a362fc22f62 100644 --- a/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c +++ b/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c @@ -42,6 +42,16 @@ * Invalid flag options in AES-CCM IV. */ +static inline int incr_index(int index, int count, int max) +{ + if ((index + count) >= max) + index = index + count - max; + else + index += count; + + return index; +} + /** * dma_free_sglist - unmap and free the sg lists. * @ndev: N5 device @@ -426,30 +436,29 @@ static void post_se_instr(struct nitrox_softreq *sr, struct nitrox_cmdq *cmdq) { struct nitrox_device *ndev = sr->ndev; - union nps_pkt_in_instr_baoff_dbell pkt_in_baoff_dbell; - u64 offset; + int idx; u8 *ent; spin_lock_bh(&cmdq->cmdq_lock); - /* get the next write offset */ - offset = NPS_PKT_IN_INSTR_BAOFF_DBELLX(cmdq->qno); - pkt_in_baoff_dbell.value = nitrox_read_csr(ndev, offset); + idx = cmdq->write_idx; /* copy the instruction */ - ent = cmdq->head + pkt_in_baoff_dbell.s.aoff; + ent = cmdq->head + (idx * cmdq->instr_size); memcpy(ent, &sr->instr, cmdq->instr_size); - /* flush the command queue updates */ - dma_wmb(); - sr->tstamp = jiffies; atomic_set(&sr->status, REQ_POSTED); response_list_add(sr, cmdq); + sr->tstamp = jiffies; + /* flush the command queue updates */ + dma_wmb(); /* Ring doorbell with count 1 */ writeq(1, cmdq->dbell_csr_addr); /* orders the doorbell rings */ mmiowb(); + cmdq->write_idx = incr_index(idx, 1, ndev->qlen); + spin_unlock_bh(&cmdq->cmdq_lock); } @@ -459,6 +468,9 @@ static int post_backlog_cmds(struct nitrox_cmdq *cmdq) struct nitrox_softreq *sr, *tmp; int ret = 0; + if (!atomic_read(&cmdq->backlog_count)) + return 0; + spin_lock_bh(&cmdq->backlog_lock); list_for_each_entry_safe(sr, tmp, &cmdq->backlog_head, backlog) { @@ -466,7 +478,7 @@ static int post_backlog_cmds(struct nitrox_cmdq *cmdq) /* submit until space available */ if (unlikely(cmdq_full(cmdq, ndev->qlen))) { - ret = -EBUSY; + ret = -ENOSPC; break; } /* delete from backlog list */ @@ -491,23 +503,20 @@ static int nitrox_enqueue_request(struct nitrox_softreq *sr) { struct nitrox_cmdq *cmdq = sr->cmdq; struct nitrox_device *ndev = sr->ndev; - int ret = -EBUSY; + + /* try to post backlog requests */ + post_backlog_cmds(cmdq); if (unlikely(cmdq_full(cmdq, ndev->qlen))) { if (!(sr->flags & CRYPTO_TFM_REQ_MAY_BACKLOG)) - return -EAGAIN; - + return -ENOSPC; + /* add to backlog list */ backlog_list_add(sr, cmdq); - } else { - ret = post_backlog_cmds(cmdq); - if (ret) { - backlog_list_add(sr, cmdq); - return ret; - } - post_se_instr(sr, cmdq); - ret = -EINPROGRESS; + return -EBUSY; } - return ret; + post_se_instr(sr, cmdq); + + return -EINPROGRESS; } /** @@ -624,11 +633,9 @@ int nitrox_process_se_request(struct nitrox_device *ndev, */ sr->instr.fdata[0] = *((u64 *)&req->gph); sr->instr.fdata[1] = 0; - /* flush the soft_req changes before posting the cmd */ - wmb(); ret = nitrox_enqueue_request(sr); - if (ret == -EAGAIN) + if (ret == -ENOSPC) goto send_fail; return ret; diff --git a/drivers/crypto/chelsio/chtls/chtls.h b/drivers/crypto/chelsio/chtls/chtls.h index a53a0e6ba024..7725b6ee14ef 100644 --- a/drivers/crypto/chelsio/chtls/chtls.h +++ b/drivers/crypto/chelsio/chtls/chtls.h @@ -96,6 +96,10 @@ enum csk_flags { CSK_CONN_INLINE, /* Connection on HW */ }; +enum chtls_cdev_state { + CHTLS_CDEV_STATE_UP = 1 +}; + struct listen_ctx { struct sock *lsk; struct chtls_dev *cdev; @@ -146,6 +150,7 @@ struct chtls_dev { unsigned int send_page_order; int max_host_sndbuf; struct key_map kmap; + unsigned int cdev_state; }; struct chtls_hws { diff --git a/drivers/crypto/chelsio/chtls/chtls_main.c b/drivers/crypto/chelsio/chtls/chtls_main.c index 9b07f9165658..f59b044ebd25 100644 --- a/drivers/crypto/chelsio/chtls/chtls_main.c +++ b/drivers/crypto/chelsio/chtls/chtls_main.c @@ -160,6 +160,7 @@ static void chtls_register_dev(struct chtls_dev *cdev) tlsdev->hash = chtls_create_hash; tlsdev->unhash = chtls_destroy_hash; tls_register_device(&cdev->tlsdev); + cdev->cdev_state = CHTLS_CDEV_STATE_UP; } static void chtls_unregister_dev(struct chtls_dev *cdev) @@ -281,8 +282,10 @@ static void chtls_free_all_uld(void) struct chtls_dev *cdev, *tmp; mutex_lock(&cdev_mutex); - list_for_each_entry_safe(cdev, tmp, &cdev_list, list) - chtls_free_uld(cdev); + list_for_each_entry_safe(cdev, tmp, &cdev_list, list) { + if (cdev->cdev_state == CHTLS_CDEV_STATE_UP) + chtls_free_uld(cdev); + } mutex_unlock(&cdev_mutex); } diff --git a/drivers/crypto/vmx/aes_cbc.c b/drivers/crypto/vmx/aes_cbc.c index 5285ece4f33a..b71895871be3 100644 --- a/drivers/crypto/vmx/aes_cbc.c +++ b/drivers/crypto/vmx/aes_cbc.c @@ -107,24 +107,23 @@ static int p8_aes_cbc_encrypt(struct blkcipher_desc *desc, ret = crypto_skcipher_encrypt(req); skcipher_request_zero(req); } else { - preempt_disable(); - pagefault_disable(); - enable_kernel_vsx(); - blkcipher_walk_init(&walk, dst, src, nbytes); ret = blkcipher_walk_virt(desc, &walk); while ((nbytes = walk.nbytes)) { + preempt_disable(); + pagefault_disable(); + enable_kernel_vsx(); aes_p8_cbc_encrypt(walk.src.virt.addr, walk.dst.virt.addr, nbytes & AES_BLOCK_MASK, &ctx->enc_key, walk.iv, 1); + disable_kernel_vsx(); + pagefault_enable(); + preempt_enable(); + nbytes &= AES_BLOCK_SIZE - 1; ret = blkcipher_walk_done(desc, &walk, nbytes); } - - disable_kernel_vsx(); - pagefault_enable(); - preempt_enable(); } return ret; @@ -147,24 +146,23 @@ static int p8_aes_cbc_decrypt(struct blkcipher_desc *desc, ret = crypto_skcipher_decrypt(req); skcipher_request_zero(req); } else { - preempt_disable(); - pagefault_disable(); - enable_kernel_vsx(); - blkcipher_walk_init(&walk, dst, src, nbytes); ret = blkcipher_walk_virt(desc, &walk); while ((nbytes = walk.nbytes)) { + preempt_disable(); + pagefault_disable(); + enable_kernel_vsx(); aes_p8_cbc_encrypt(walk.src.virt.addr, walk.dst.virt.addr, nbytes & AES_BLOCK_MASK, &ctx->dec_key, walk.iv, 0); + disable_kernel_vsx(); + pagefault_enable(); + preempt_enable(); + nbytes &= AES_BLOCK_SIZE - 1; ret = blkcipher_walk_done(desc, &walk, nbytes); } - - disable_kernel_vsx(); - pagefault_enable(); - preempt_enable(); } return ret; diff --git a/drivers/crypto/vmx/aes_xts.c b/drivers/crypto/vmx/aes_xts.c index 8bd9aff0f55f..e9954a7d4694 100644 --- a/drivers/crypto/vmx/aes_xts.c +++ b/drivers/crypto/vmx/aes_xts.c @@ -116,32 +116,39 @@ static int p8_aes_xts_crypt(struct blkcipher_desc *desc, ret = enc? crypto_skcipher_encrypt(req) : crypto_skcipher_decrypt(req); skcipher_request_zero(req); } else { + blkcipher_walk_init(&walk, dst, src, nbytes); + + ret = blkcipher_walk_virt(desc, &walk); + preempt_disable(); pagefault_disable(); enable_kernel_vsx(); - blkcipher_walk_init(&walk, dst, src, nbytes); - - ret = blkcipher_walk_virt(desc, &walk); iv = walk.iv; memset(tweak, 0, AES_BLOCK_SIZE); aes_p8_encrypt(iv, tweak, &ctx->tweak_key); + disable_kernel_vsx(); + pagefault_enable(); + preempt_enable(); + while ((nbytes = walk.nbytes)) { + preempt_disable(); + pagefault_disable(); + enable_kernel_vsx(); if (enc) aes_p8_xts_encrypt(walk.src.virt.addr, walk.dst.virt.addr, nbytes & AES_BLOCK_MASK, &ctx->enc_key, NULL, tweak); else aes_p8_xts_decrypt(walk.src.virt.addr, walk.dst.virt.addr, nbytes & AES_BLOCK_MASK, &ctx->dec_key, NULL, tweak); + disable_kernel_vsx(); + pagefault_enable(); + preempt_enable(); nbytes &= AES_BLOCK_SIZE - 1; ret = blkcipher_walk_done(desc, &walk, nbytes); } - - disable_kernel_vsx(); - pagefault_enable(); - preempt_enable(); } return ret; } diff --git a/drivers/dax/device.c b/drivers/dax/device.c index 6fd46083e629..bbe4d72ca105 100644 --- a/drivers/dax/device.c +++ b/drivers/dax/device.c @@ -392,7 +392,8 @@ static vm_fault_t dev_dax_huge_fault(struct vm_fault *vmf, { struct file *filp = vmf->vma->vm_file; unsigned long fault_size; - int rc, id; + vm_fault_t rc = VM_FAULT_SIGBUS; + int id; pfn_t pfn; struct dev_dax *dev_dax = filp->private_data; diff --git a/drivers/dma/mic_x100_dma.c b/drivers/dma/mic_x100_dma.c index b76cb17d879c..adfd316db1a8 100644 --- a/drivers/dma/mic_x100_dma.c +++ b/drivers/dma/mic_x100_dma.c @@ -639,7 +639,7 @@ static struct mic_dma_device *mic_dma_dev_reg(struct mbus_device *mbdev, int ret; struct device *dev = &mbdev->dev; - mic_dma_dev = kzalloc(sizeof(*mic_dma_dev), GFP_KERNEL); + mic_dma_dev = devm_kzalloc(dev, sizeof(*mic_dma_dev), GFP_KERNEL); if (!mic_dma_dev) { ret = -ENOMEM; goto alloc_error; @@ -664,7 +664,6 @@ static struct mic_dma_device *mic_dma_dev_reg(struct mbus_device *mbdev, reg_error: mic_dma_uninit(mic_dma_dev); init_error: - kfree(mic_dma_dev); mic_dma_dev = NULL; alloc_error: dev_err(dev, "Error at %s %d ret=%d\n", __func__, __LINE__, ret); @@ -674,7 +673,6 @@ alloc_error: static void mic_dma_dev_unreg(struct mic_dma_device *mic_dma_dev) { mic_dma_uninit(mic_dma_dev); - kfree(mic_dma_dev); } /* DEBUGFS CODE */ diff --git a/drivers/firmware/arm_scmi/perf.c b/drivers/firmware/arm_scmi/perf.c index 721e6c57beae..64342944d917 100644 --- a/drivers/firmware/arm_scmi/perf.c +++ b/drivers/firmware/arm_scmi/perf.c @@ -166,7 +166,13 @@ scmi_perf_domain_attributes_get(const struct scmi_handle *handle, u32 domain, le32_to_cpu(attr->sustained_freq_khz); dom_info->sustained_perf_level = le32_to_cpu(attr->sustained_perf_level); - dom_info->mult_factor = (dom_info->sustained_freq_khz * 1000) / + if (!dom_info->sustained_freq_khz || + !dom_info->sustained_perf_level) + /* CPUFreq converts to kHz, hence default 1000 */ + dom_info->mult_factor = 1000; + else + dom_info->mult_factor = + (dom_info->sustained_freq_khz * 1000) / dom_info->sustained_perf_level; memcpy(dom_info->name, attr->name, SCMI_MAX_STR_SIZE); } diff --git a/drivers/fpga/dfl-fme-pr.c b/drivers/fpga/dfl-fme-pr.c index fc9fd2d0482f..0b840531ef33 100644 --- a/drivers/fpga/dfl-fme-pr.c +++ b/drivers/fpga/dfl-fme-pr.c @@ -420,7 +420,7 @@ static int pr_mgmt_init(struct platform_device *pdev, /* Create region for each port */ fme_region = dfl_fme_create_region(pdata, mgr, fme_br->br, i); - if (!fme_region) { + if (IS_ERR(fme_region)) { ret = PTR_ERR(fme_region); goto destroy_region; } diff --git a/drivers/gpio/gpio-adp5588.c b/drivers/gpio/gpio-adp5588.c index 3530ccd17e04..da9781a2ef4a 100644 --- a/drivers/gpio/gpio-adp5588.c +++ b/drivers/gpio/gpio-adp5588.c @@ -41,6 +41,8 @@ struct adp5588_gpio { uint8_t int_en[3]; uint8_t irq_mask[3]; uint8_t irq_stat[3]; + uint8_t int_input_en[3]; + uint8_t int_lvl_cached[3]; }; static int adp5588_gpio_read(struct i2c_client *client, u8 reg) @@ -173,12 +175,28 @@ static void adp5588_irq_bus_sync_unlock(struct irq_data *d) struct adp5588_gpio *dev = irq_data_get_irq_chip_data(d); int i; - for (i = 0; i <= ADP5588_BANK(ADP5588_MAXGPIO); i++) + for (i = 0; i <= ADP5588_BANK(ADP5588_MAXGPIO); i++) { + if (dev->int_input_en[i]) { + mutex_lock(&dev->lock); + dev->dir[i] &= ~dev->int_input_en[i]; + dev->int_input_en[i] = 0; + adp5588_gpio_write(dev->client, GPIO_DIR1 + i, + dev->dir[i]); + mutex_unlock(&dev->lock); + } + + if (dev->int_lvl_cached[i] != dev->int_lvl[i]) { + dev->int_lvl_cached[i] = dev->int_lvl[i]; + adp5588_gpio_write(dev->client, GPIO_INT_LVL1 + i, + dev->int_lvl[i]); + } + if (dev->int_en[i] ^ dev->irq_mask[i]) { dev->int_en[i] = dev->irq_mask[i]; adp5588_gpio_write(dev->client, GPIO_INT_EN1 + i, dev->int_en[i]); } + } mutex_unlock(&dev->irq_lock); } @@ -221,9 +239,7 @@ static int adp5588_irq_set_type(struct irq_data *d, unsigned int type) else return -EINVAL; - adp5588_gpio_direction_input(&dev->gpio_chip, gpio); - adp5588_gpio_write(dev->client, GPIO_INT_LVL1 + bank, - dev->int_lvl[bank]); + dev->int_input_en[bank] |= bit; return 0; } diff --git a/drivers/gpio/gpio-dwapb.c b/drivers/gpio/gpio-dwapb.c index 28da700f5f52..044888fd96a1 100644 --- a/drivers/gpio/gpio-dwapb.c +++ b/drivers/gpio/gpio-dwapb.c @@ -728,6 +728,7 @@ static int dwapb_gpio_probe(struct platform_device *pdev) out_unregister: dwapb_gpio_unregister(gpio); dwapb_irq_teardown(gpio); + clk_disable_unprepare(gpio->clk); return err; } diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index c48ed9d89ff5..8b9d7e42c600 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -25,7 +25,6 @@ struct acpi_gpio_event { struct list_head node; - struct list_head initial_sync_list; acpi_handle handle; unsigned int pin; unsigned int irq; @@ -49,10 +48,19 @@ struct acpi_gpio_chip { struct mutex conn_lock; struct gpio_chip *chip; struct list_head events; + struct list_head deferred_req_irqs_list_entry; }; -static LIST_HEAD(acpi_gpio_initial_sync_list); -static DEFINE_MUTEX(acpi_gpio_initial_sync_list_lock); +/* + * For gpiochips which call acpi_gpiochip_request_interrupts() before late_init + * (so builtin drivers) we register the ACPI GpioInt event handlers from a + * late_initcall_sync handler, so that other builtin drivers can register their + * OpRegions before the event handlers can run. This list contains gpiochips + * for which the acpi_gpiochip_request_interrupts() has been deferred. + */ +static DEFINE_MUTEX(acpi_gpio_deferred_req_irqs_lock); +static LIST_HEAD(acpi_gpio_deferred_req_irqs_list); +static bool acpi_gpio_deferred_req_irqs_done; static int acpi_gpiochip_find(struct gpio_chip *gc, void *data) { @@ -89,21 +97,6 @@ static struct gpio_desc *acpi_get_gpiod(char *path, int pin) return gpiochip_get_desc(chip, pin); } -static void acpi_gpio_add_to_initial_sync_list(struct acpi_gpio_event *event) -{ - mutex_lock(&acpi_gpio_initial_sync_list_lock); - list_add(&event->initial_sync_list, &acpi_gpio_initial_sync_list); - mutex_unlock(&acpi_gpio_initial_sync_list_lock); -} - -static void acpi_gpio_del_from_initial_sync_list(struct acpi_gpio_event *event) -{ - mutex_lock(&acpi_gpio_initial_sync_list_lock); - if (!list_empty(&event->initial_sync_list)) - list_del_init(&event->initial_sync_list); - mutex_unlock(&acpi_gpio_initial_sync_list_lock); -} - static irqreturn_t acpi_gpio_irq_handler(int irq, void *data) { struct acpi_gpio_event *event = data; @@ -186,7 +179,7 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares, gpiod_direction_input(desc); - value = gpiod_get_value(desc); + value = gpiod_get_value_cansleep(desc); ret = gpiochip_lock_as_irq(chip, pin); if (ret) { @@ -229,7 +222,6 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares, event->irq = irq; event->pin = pin; event->desc = desc; - INIT_LIST_HEAD(&event->initial_sync_list); ret = request_threaded_irq(event->irq, NULL, handler, irqflags, "ACPI:Event", event); @@ -251,10 +243,9 @@ static acpi_status acpi_gpiochip_request_interrupt(struct acpi_resource *ares, * may refer to OperationRegions from other (builtin) drivers which * may be probed after us. */ - if (handler == acpi_gpio_irq_handler && - (((irqflags & IRQF_TRIGGER_RISING) && value == 1) || - ((irqflags & IRQF_TRIGGER_FALLING) && value == 0))) - acpi_gpio_add_to_initial_sync_list(event); + if (((irqflags & IRQF_TRIGGER_RISING) && value == 1) || + ((irqflags & IRQF_TRIGGER_FALLING) && value == 0)) + handler(event->irq, event); return AE_OK; @@ -283,6 +274,7 @@ void acpi_gpiochip_request_interrupts(struct gpio_chip *chip) struct acpi_gpio_chip *acpi_gpio; acpi_handle handle; acpi_status status; + bool defer; if (!chip->parent || !chip->to_irq) return; @@ -295,6 +287,16 @@ void acpi_gpiochip_request_interrupts(struct gpio_chip *chip) if (ACPI_FAILURE(status)) return; + mutex_lock(&acpi_gpio_deferred_req_irqs_lock); + defer = !acpi_gpio_deferred_req_irqs_done; + if (defer) + list_add(&acpi_gpio->deferred_req_irqs_list_entry, + &acpi_gpio_deferred_req_irqs_list); + mutex_unlock(&acpi_gpio_deferred_req_irqs_lock); + + if (defer) + return; + acpi_walk_resources(handle, "_AEI", acpi_gpiochip_request_interrupt, acpi_gpio); } @@ -325,11 +327,14 @@ void acpi_gpiochip_free_interrupts(struct gpio_chip *chip) if (ACPI_FAILURE(status)) return; + mutex_lock(&acpi_gpio_deferred_req_irqs_lock); + if (!list_empty(&acpi_gpio->deferred_req_irqs_list_entry)) + list_del_init(&acpi_gpio->deferred_req_irqs_list_entry); + mutex_unlock(&acpi_gpio_deferred_req_irqs_lock); + list_for_each_entry_safe_reverse(event, ep, &acpi_gpio->events, node) { struct gpio_desc *desc; - acpi_gpio_del_from_initial_sync_list(event); - if (irqd_is_wakeup_set(irq_get_irq_data(event->irq))) disable_irq_wake(event->irq); @@ -1052,6 +1057,7 @@ void acpi_gpiochip_add(struct gpio_chip *chip) acpi_gpio->chip = chip; INIT_LIST_HEAD(&acpi_gpio->events); + INIT_LIST_HEAD(&acpi_gpio->deferred_req_irqs_list_entry); status = acpi_attach_data(handle, acpi_gpio_chip_dh, acpi_gpio); if (ACPI_FAILURE(status)) { @@ -1198,20 +1204,28 @@ bool acpi_can_fallback_to_crs(struct acpi_device *adev, const char *con_id) return con_id == NULL; } -/* Sync the initial state of handlers after all builtin drivers have probed */ -static int acpi_gpio_initial_sync(void) +/* Run deferred acpi_gpiochip_request_interrupts() */ +static int acpi_gpio_handle_deferred_request_interrupts(void) { - struct acpi_gpio_event *event, *ep; + struct acpi_gpio_chip *acpi_gpio, *tmp; + + mutex_lock(&acpi_gpio_deferred_req_irqs_lock); + list_for_each_entry_safe(acpi_gpio, tmp, + &acpi_gpio_deferred_req_irqs_list, + deferred_req_irqs_list_entry) { + acpi_handle handle; - mutex_lock(&acpi_gpio_initial_sync_list_lock); - list_for_each_entry_safe(event, ep, &acpi_gpio_initial_sync_list, - initial_sync_list) { - acpi_evaluate_object(event->handle, NULL, NULL, NULL); - list_del_init(&event->initial_sync_list); + handle = ACPI_HANDLE(acpi_gpio->chip->parent); + acpi_walk_resources(handle, "_AEI", + acpi_gpiochip_request_interrupt, acpi_gpio); + + list_del_init(&acpi_gpio->deferred_req_irqs_list_entry); } - mutex_unlock(&acpi_gpio_initial_sync_list_lock); + + acpi_gpio_deferred_req_irqs_done = true; + mutex_unlock(&acpi_gpio_deferred_req_irqs_lock); return 0; } /* We must use _sync so that this runs after the first deferred_probe run */ -late_initcall_sync(acpi_gpio_initial_sync); +late_initcall_sync(acpi_gpio_handle_deferred_request_interrupts); diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c index a4f1157d6aa0..d4e7a09598fa 100644 --- a/drivers/gpio/gpiolib-of.c +++ b/drivers/gpio/gpiolib-of.c @@ -31,6 +31,7 @@ static int of_gpiochip_match_node_and_xlate(struct gpio_chip *chip, void *data) struct of_phandle_args *gpiospec = data; return chip->gpiodev->dev.of_node == gpiospec->np && + chip->of_xlate && chip->of_xlate(chip, gpiospec, NULL) >= 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 502b94fb116a..b31d121a876b 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -39,6 +39,7 @@ static int amdgpu_cs_user_fence_chunk(struct amdgpu_cs_parser *p, { struct drm_gem_object *gobj; unsigned long size; + int r; gobj = drm_gem_object_lookup(p->filp, data->handle); if (gobj == NULL) @@ -50,20 +51,26 @@ static int amdgpu_cs_user_fence_chunk(struct amdgpu_cs_parser *p, p->uf_entry.tv.shared = true; p->uf_entry.user_pages = NULL; - size = amdgpu_bo_size(p->uf_entry.robj); - if (size != PAGE_SIZE || (data->offset + 8) > size) - return -EINVAL; - - *offset = data->offset; - drm_gem_object_put_unlocked(gobj); + size = amdgpu_bo_size(p->uf_entry.robj); + if (size != PAGE_SIZE || (data->offset + 8) > size) { + r = -EINVAL; + goto error_unref; + } + if (amdgpu_ttm_tt_get_usermm(p->uf_entry.robj->tbo.ttm)) { - amdgpu_bo_unref(&p->uf_entry.robj); - return -EINVAL; + r = -EINVAL; + goto error_unref; } + *offset = data->offset; + return 0; + +error_unref: + amdgpu_bo_unref(&p->uf_entry.robj); + return r; } static int amdgpu_cs_bo_handles_chunk(struct amdgpu_cs_parser *p, @@ -1012,13 +1019,9 @@ static int amdgpu_cs_ib_fill(struct amdgpu_device *adev, if (r) return r; - if (chunk_ib->flags & AMDGPU_IB_FLAG_PREAMBLE) { - parser->job->preamble_status |= AMDGPU_PREAMBLE_IB_PRESENT; - if (!parser->ctx->preamble_presented) { - parser->job->preamble_status |= AMDGPU_PREAMBLE_IB_PRESENT_FIRST; - parser->ctx->preamble_presented = true; - } - } + if (chunk_ib->flags & AMDGPU_IB_FLAG_PREAMBLE) + parser->job->preamble_status |= + AMDGPU_PREAMBLE_IB_PRESENT; if (parser->ring && parser->ring != ring) return -EINVAL; @@ -1207,26 +1210,24 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, int r; + job = p->job; + p->job = NULL; + + r = drm_sched_job_init(&job->base, entity, p->filp); + if (r) + goto error_unlock; + + /* No memory allocation is allowed while holding the mn lock */ amdgpu_mn_lock(p->mn); amdgpu_bo_list_for_each_userptr_entry(e, p->bo_list) { struct amdgpu_bo *bo = e->robj; if (amdgpu_ttm_tt_userptr_needs_pages(bo->tbo.ttm)) { - amdgpu_mn_unlock(p->mn); - return -ERESTARTSYS; + r = -ERESTARTSYS; + goto error_abort; } } - job = p->job; - p->job = NULL; - - r = drm_sched_job_init(&job->base, entity, p->filp); - if (r) { - amdgpu_job_free(job); - amdgpu_mn_unlock(p->mn); - return r; - } - job->owner = p->filp; p->fence = dma_fence_get(&job->base.s_fence->finished); @@ -1241,6 +1242,12 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, amdgpu_cs_post_dependencies(p); + if ((job->preamble_status & AMDGPU_PREAMBLE_IB_PRESENT) && + !p->ctx->preamble_presented) { + job->preamble_status |= AMDGPU_PREAMBLE_IB_PRESENT_FIRST; + p->ctx->preamble_presented = true; + } + cs->out.handle = seq; job->uf_sequence = seq; @@ -1258,6 +1265,15 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p, amdgpu_mn_unlock(p->mn); return 0; + +error_abort: + dma_fence_put(&job->base.s_fence->finished); + job->base.s_fence = NULL; + amdgpu_mn_unlock(p->mn); + +error_unlock: + amdgpu_job_free(job); + return r; } int amdgpu_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 8ab5ccbc14ac..39bf2ce548c6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -2063,6 +2063,7 @@ static int amdgpu_device_ip_reinit_early_sriov(struct amdgpu_device *adev) static enum amd_ip_block_type ip_order[] = { AMD_IP_BLOCK_TYPE_GMC, AMD_IP_BLOCK_TYPE_COMMON, + AMD_IP_BLOCK_TYPE_PSP, AMD_IP_BLOCK_TYPE_IH, }; @@ -2093,7 +2094,6 @@ static int amdgpu_device_ip_reinit_late_sriov(struct amdgpu_device *adev) static enum amd_ip_block_type ip_order[] = { AMD_IP_BLOCK_TYPE_SMC, - AMD_IP_BLOCK_TYPE_PSP, AMD_IP_BLOCK_TYPE_DCE, AMD_IP_BLOCK_TYPE_GFX, AMD_IP_BLOCK_TYPE_SDMA, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c index 5518e623fed2..51b5e977ca88 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c @@ -164,8 +164,10 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs, return r; } + need_ctx_switch = ring->current_ctx != fence_ctx; if (ring->funcs->emit_pipeline_sync && job && ((tmp = amdgpu_sync_get_fence(&job->sched_sync, NULL)) || + (amdgpu_sriov_vf(adev) && need_ctx_switch) || amdgpu_vm_need_pipeline_sync(ring, job))) { need_pipe_sync = true; dma_fence_put(tmp); @@ -196,7 +198,6 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs, } skip_preamble = ring->current_ctx == fence_ctx; - need_ctx_switch = ring->current_ctx != fence_ctx; if (job && ring->funcs->emit_cntxcntl) { if (need_ctx_switch) status |= AMDGPU_HAVE_CTX_SWITCH; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c index 8f98629fbe59..7b4e657a95c7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c @@ -1932,14 +1932,6 @@ void amdgpu_pm_compute_clocks(struct amdgpu_device *adev) amdgpu_fence_wait_empty(ring); } - mutex_lock(&adev->pm.mutex); - /* update battery/ac status */ - if (power_supply_is_system_supplied() > 0) - adev->pm.ac_power = true; - else - adev->pm.ac_power = false; - mutex_unlock(&adev->pm.mutex); - if (adev->powerplay.pp_funcs->dispatch_tasks) { if (!amdgpu_device_has_dc_support(adev)) { mutex_lock(&adev->pm.mutex); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index ece0ac703e27..b17771dd5ce7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -172,6 +172,7 @@ static void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base *base, * is validated on next vm use to avoid fault. * */ list_move_tail(&base->vm_status, &vm->evicted); + base->moved = true; } /** @@ -369,7 +370,6 @@ static int amdgpu_vm_clear_bo(struct amdgpu_device *adev, uint64_t addr; int r; - addr = amdgpu_bo_gpu_offset(bo); entries = amdgpu_bo_size(bo) / 8; if (pte_support_ats) { @@ -401,6 +401,7 @@ static int amdgpu_vm_clear_bo(struct amdgpu_device *adev, if (r) goto error; + addr = amdgpu_bo_gpu_offset(bo); if (ats_entries) { uint64_t ats_value; @@ -2483,28 +2484,52 @@ static uint32_t amdgpu_vm_get_block_size(uint64_t vm_size) * amdgpu_vm_adjust_size - adjust vm size, block size and fragment size * * @adev: amdgpu_device pointer - * @vm_size: the default vm size if it's set auto + * @min_vm_size: the minimum vm size in GB if it's set auto * @fragment_size_default: Default PTE fragment size * @max_level: max VMPT level * @max_bits: max address space size in bits * */ -void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint32_t vm_size, +void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint32_t min_vm_size, uint32_t fragment_size_default, unsigned max_level, unsigned max_bits) { + unsigned int max_size = 1 << (max_bits - 30); + unsigned int vm_size; uint64_t tmp; /* adjust vm size first */ if (amdgpu_vm_size != -1) { - unsigned max_size = 1 << (max_bits - 30); - vm_size = amdgpu_vm_size; if (vm_size > max_size) { dev_warn(adev->dev, "VM size (%d) too large, max is %u GB\n", amdgpu_vm_size, max_size); vm_size = max_size; } + } else { + struct sysinfo si; + unsigned int phys_ram_gb; + + /* Optimal VM size depends on the amount of physical + * RAM available. Underlying requirements and + * assumptions: + * + * - Need to map system memory and VRAM from all GPUs + * - VRAM from other GPUs not known here + * - Assume VRAM <= system memory + * - On GFX8 and older, VM space can be segmented for + * different MTYPEs + * - Need to allow room for fragmentation, guard pages etc. + * + * This adds up to a rough guess of system memory x3. + * Round up to power of two to maximize the available + * VM size with the given page table size. + */ + si_meminfo(&si); + phys_ram_gb = ((uint64_t)si.totalram * si.mem_unit + + (1 << 30) - 1) >> 30; + vm_size = roundup_pow_of_two( + min(max(phys_ram_gb * 3, min_vm_size), max_size)); } adev->vm_manager.max_pfn = (uint64_t)vm_size << 18; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h index 67a15d439ac0..9fa9df0c5e7f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h @@ -321,7 +321,7 @@ struct amdgpu_bo_va_mapping *amdgpu_vm_bo_lookup_mapping(struct amdgpu_vm *vm, void amdgpu_vm_bo_trace_cs(struct amdgpu_vm *vm, struct ww_acquire_ctx *ticket); void amdgpu_vm_bo_rmv(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va); -void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint32_t vm_size, +void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint32_t min_vm_size, uint32_t fragment_size_default, unsigned max_level, unsigned max_bits); int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp); diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 5cd45210113f..5a9534a82d40 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -5664,6 +5664,11 @@ static int gfx_v8_0_set_powergating_state(void *handle, if (amdgpu_sriov_vf(adev)) return 0; + if (adev->pg_flags & (AMD_PG_SUPPORT_GFX_SMG | + AMD_PG_SUPPORT_RLC_SMU_HS | + AMD_PG_SUPPORT_CP | + AMD_PG_SUPPORT_GFX_DMG)) + adev->gfx.rlc.funcs->enter_safe_mode(adev); switch (adev->asic_type) { case CHIP_CARRIZO: case CHIP_STONEY: @@ -5713,7 +5718,11 @@ static int gfx_v8_0_set_powergating_state(void *handle, default: break; } - + if (adev->pg_flags & (AMD_PG_SUPPORT_GFX_SMG | + AMD_PG_SUPPORT_RLC_SMU_HS | + AMD_PG_SUPPORT_CP | + AMD_PG_SUPPORT_GFX_DMG)) + adev->gfx.rlc.funcs->exit_safe_mode(adev); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c index 75317f283c69..ad151fefa41f 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c @@ -632,12 +632,6 @@ static void gmc_v6_0_gart_disable(struct amdgpu_device *adev) amdgpu_gart_table_vram_unpin(adev); } -static void gmc_v6_0_gart_fini(struct amdgpu_device *adev) -{ - amdgpu_gart_table_vram_free(adev); - amdgpu_gart_fini(adev); -} - static void gmc_v6_0_vm_decode_fault(struct amdgpu_device *adev, u32 status, u32 addr, u32 mc_client) { @@ -935,8 +929,9 @@ static int gmc_v6_0_sw_fini(void *handle) amdgpu_gem_force_release(adev); amdgpu_vm_manager_fini(adev); - gmc_v6_0_gart_fini(adev); + amdgpu_gart_table_vram_free(adev); amdgpu_bo_fini(adev); + amdgpu_gart_fini(adev); release_firmware(adev->gmc.fw); adev->gmc.fw = NULL; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c index 36dc367c4b45..f8d8a3a73e42 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c @@ -747,19 +747,6 @@ static void gmc_v7_0_gart_disable(struct amdgpu_device *adev) } /** - * gmc_v7_0_gart_fini - vm fini callback - * - * @adev: amdgpu_device pointer - * - * Tears down the driver GART/VM setup (CIK). - */ -static void gmc_v7_0_gart_fini(struct amdgpu_device *adev) -{ - amdgpu_gart_table_vram_free(adev); - amdgpu_gart_fini(adev); -} - -/** * gmc_v7_0_vm_decode_fault - print human readable fault info * * @adev: amdgpu_device pointer @@ -1095,8 +1082,9 @@ static int gmc_v7_0_sw_fini(void *handle) amdgpu_gem_force_release(adev); amdgpu_vm_manager_fini(adev); kfree(adev->gmc.vm_fault_info); - gmc_v7_0_gart_fini(adev); + amdgpu_gart_table_vram_free(adev); amdgpu_bo_fini(adev); + amdgpu_gart_fini(adev); release_firmware(adev->gmc.fw); adev->gmc.fw = NULL; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c index 70fc97b59b4f..9333109b210d 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c @@ -969,19 +969,6 @@ static void gmc_v8_0_gart_disable(struct amdgpu_device *adev) } /** - * gmc_v8_0_gart_fini - vm fini callback - * - * @adev: amdgpu_device pointer - * - * Tears down the driver GART/VM setup (CIK). - */ -static void gmc_v8_0_gart_fini(struct amdgpu_device *adev) -{ - amdgpu_gart_table_vram_free(adev); - amdgpu_gart_fini(adev); -} - -/** * gmc_v8_0_vm_decode_fault - print human readable fault info * * @adev: amdgpu_device pointer @@ -1199,8 +1186,9 @@ static int gmc_v8_0_sw_fini(void *handle) amdgpu_gem_force_release(adev); amdgpu_vm_manager_fini(adev); kfree(adev->gmc.vm_fault_info); - gmc_v8_0_gart_fini(adev); + amdgpu_gart_table_vram_free(adev); amdgpu_bo_fini(adev); + amdgpu_gart_fini(adev); release_firmware(adev->gmc.fw); adev->gmc.fw = NULL; diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index 399a5db27649..72f8018fa2a8 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -942,26 +942,12 @@ static int gmc_v9_0_sw_init(void *handle) return 0; } -/** - * gmc_v9_0_gart_fini - vm fini callback - * - * @adev: amdgpu_device pointer - * - * Tears down the driver GART/VM setup (CIK). - */ -static void gmc_v9_0_gart_fini(struct amdgpu_device *adev) -{ - amdgpu_gart_table_vram_free(adev); - amdgpu_gart_fini(adev); -} - static int gmc_v9_0_sw_fini(void *handle) { struct amdgpu_device *adev = (struct amdgpu_device *)handle; amdgpu_gem_force_release(adev); amdgpu_vm_manager_fini(adev); - gmc_v9_0_gart_fini(adev); /* * TODO: @@ -974,7 +960,9 @@ static int gmc_v9_0_sw_fini(void *handle) */ amdgpu_bo_free_kernel(&adev->stolen_vga_memory, NULL, NULL); + amdgpu_gart_table_vram_free(adev); amdgpu_bo_fini(adev); + amdgpu_gart_fini(adev); return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c index 3f57f6463dc8..cb79a93c2eb7 100644 --- a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c @@ -65,8 +65,6 @@ static int kv_set_thermal_temperature_range(struct amdgpu_device *adev, int min_temp, int max_temp); static int kv_init_fps_limits(struct amdgpu_device *adev); -static void kv_dpm_powergate_uvd(void *handle, bool gate); -static void kv_dpm_powergate_vce(struct amdgpu_device *adev, bool gate); static void kv_dpm_powergate_samu(struct amdgpu_device *adev, bool gate); static void kv_dpm_powergate_acp(struct amdgpu_device *adev, bool gate); @@ -1354,8 +1352,6 @@ static int kv_dpm_enable(struct amdgpu_device *adev) return ret; } - kv_update_current_ps(adev, adev->pm.dpm.boot_ps); - if (adev->irq.installed && amdgpu_is_internal_thermal_sensor(adev->pm.int_thermal_type)) { ret = kv_set_thermal_temperature_range(adev, KV_TEMP_RANGE_MIN, KV_TEMP_RANGE_MAX); @@ -1374,6 +1370,8 @@ static int kv_dpm_enable(struct amdgpu_device *adev) static void kv_dpm_disable(struct amdgpu_device *adev) { + struct kv_power_info *pi = kv_get_pi(adev); + amdgpu_irq_put(adev, &adev->pm.dpm.thermal.irq, AMDGPU_THERMAL_IRQ_LOW_TO_HIGH); amdgpu_irq_put(adev, &adev->pm.dpm.thermal.irq, @@ -1387,8 +1385,10 @@ static void kv_dpm_disable(struct amdgpu_device *adev) /* powerup blocks */ kv_dpm_powergate_acp(adev, false); kv_dpm_powergate_samu(adev, false); - kv_dpm_powergate_vce(adev, false); - kv_dpm_powergate_uvd(adev, false); + if (pi->caps_vce_pg) /* power on the VCE block */ + amdgpu_kv_notify_message_to_smu(adev, PPSMC_MSG_VCEPowerON); + if (pi->caps_uvd_pg) /* power on the UVD block */ + amdgpu_kv_notify_message_to_smu(adev, PPSMC_MSG_UVDPowerON); kv_enable_smc_cac(adev, false); kv_enable_didt(adev, false); @@ -1551,7 +1551,6 @@ static int kv_update_vce_dpm(struct amdgpu_device *adev, int ret; if (amdgpu_new_state->evclk > 0 && amdgpu_current_state->evclk == 0) { - kv_dpm_powergate_vce(adev, false); if (pi->caps_stable_p_state) pi->vce_boot_level = table->count - 1; else @@ -1573,7 +1572,6 @@ static int kv_update_vce_dpm(struct amdgpu_device *adev, kv_enable_vce_dpm(adev, true); } else if (amdgpu_new_state->evclk == 0 && amdgpu_current_state->evclk > 0) { kv_enable_vce_dpm(adev, false); - kv_dpm_powergate_vce(adev, true); } return 0; @@ -1702,24 +1700,32 @@ static void kv_dpm_powergate_uvd(void *handle, bool gate) } } -static void kv_dpm_powergate_vce(struct amdgpu_device *adev, bool gate) +static void kv_dpm_powergate_vce(void *handle, bool gate) { + struct amdgpu_device *adev = (struct amdgpu_device *)handle; struct kv_power_info *pi = kv_get_pi(adev); - - if (pi->vce_power_gated == gate) - return; + int ret; pi->vce_power_gated = gate; - if (!pi->caps_vce_pg) - return; - - if (gate) - amdgpu_kv_notify_message_to_smu(adev, PPSMC_MSG_VCEPowerOFF); - else - amdgpu_kv_notify_message_to_smu(adev, PPSMC_MSG_VCEPowerON); + if (gate) { + /* stop the VCE block */ + ret = amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCE, + AMD_PG_STATE_GATE); + kv_enable_vce_dpm(adev, false); + if (pi->caps_vce_pg) /* power off the VCE block */ + amdgpu_kv_notify_message_to_smu(adev, PPSMC_MSG_VCEPowerOFF); + } else { + if (pi->caps_vce_pg) /* power on the VCE block */ + amdgpu_kv_notify_message_to_smu(adev, PPSMC_MSG_VCEPowerON); + kv_enable_vce_dpm(adev, true); + /* re-init the VCE block */ + ret = amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCE, + AMD_PG_STATE_UNGATE); + } } + static void kv_dpm_powergate_samu(struct amdgpu_device *adev, bool gate) { struct kv_power_info *pi = kv_get_pi(adev); @@ -3061,7 +3067,7 @@ static int kv_dpm_hw_init(void *handle) else adev->pm.dpm_enabled = true; mutex_unlock(&adev->pm.mutex); - + amdgpu_pm_compute_clocks(adev); return ret; } @@ -3313,6 +3319,9 @@ static int kv_set_powergating_by_smu(void *handle, case AMD_IP_BLOCK_TYPE_UVD: kv_dpm_powergate_uvd(handle, gate); break; + case AMD_IP_BLOCK_TYPE_VCE: + kv_dpm_powergate_vce(handle, gate); + break; default: break; } diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index e7ca4623cfb9..7c3b634d8d5f 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -70,6 +70,7 @@ static const struct soc15_reg_golden golden_settings_sdma_4[] = { SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC1_IB_CNTL, 0x800f0100, 0x00000100), SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC1_RB_WPTR_POLL_CNTL, 0x0000fff0, 0x00403000), SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_PAGE, 0x000003ff, 0x000003c0), + SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_WATERMK, 0xfc000000, 0x00000000), SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_CHICKEN_BITS, 0xfe931f07, 0x02831f07), SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_CLK_CTRL, 0xffffffff, 0x3f000100), SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_GFX_IB_CNTL, 0x800f0100, 0x00000100), @@ -81,7 +82,8 @@ static const struct soc15_reg_golden golden_settings_sdma_4[] = { SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_RLC0_RB_WPTR_POLL_CNTL, 0x0000fff0, 0x00403000), SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_RLC1_IB_CNTL, 0x800f0100, 0x00000100), SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_RLC1_RB_WPTR_POLL_CNTL, 0x0000fff0, 0x00403000), - SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_UTCL1_PAGE, 0x000003ff, 0x000003c0) + SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_UTCL1_PAGE, 0x000003ff, 0x000003c0), + SOC15_REG_GOLDEN_VALUE(SDMA1, 0, mmSDMA1_UTCL1_WATERMK, 0xfc000000, 0x00000000) }; static const struct soc15_reg_golden golden_settings_sdma_vg10[] = { @@ -109,7 +111,8 @@ static const struct soc15_reg_golden golden_settings_sdma_4_1[] = SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC0_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000), SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC1_IB_CNTL, 0x800f0111, 0x00000100), SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_RLC1_RB_WPTR_POLL_CNTL, 0xfffffff7, 0x00403000), - SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_PAGE, 0x000003ff, 0x000003c0) + SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_PAGE, 0x000003ff, 0x000003c0), + SOC15_REG_GOLDEN_VALUE(SDMA0, 0, mmSDMA0_UTCL1_WATERMK, 0xfc000000, 0x00000000) }; static const struct soc15_reg_golden golden_settings_sdma_4_2[] = diff --git a/drivers/gpu/drm/amd/amdgpu/si_dpm.c b/drivers/gpu/drm/amd/amdgpu/si_dpm.c index db327b412562..1de96995e690 100644 --- a/drivers/gpu/drm/amd/amdgpu/si_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/si_dpm.c @@ -6887,7 +6887,6 @@ static int si_dpm_enable(struct amdgpu_device *adev) si_enable_auto_throttle_source(adev, AMDGPU_DPM_AUTO_THROTTLE_SRC_THERMAL, true); si_thermal_start_thermal_controller(adev); - ni_update_current_ps(adev, boot_ps); return 0; } @@ -7763,7 +7762,7 @@ static int si_dpm_hw_init(void *handle) else adev->pm.dpm_enabled = true; mutex_unlock(&adev->pm.mutex); - + amdgpu_pm_compute_clocks(adev); return ret; } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c index fbe878ae1e8c..4ba0003a9d32 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c @@ -480,12 +480,20 @@ void pp_rv_set_display_requirement(struct pp_smu *pp, { struct dc_context *ctx = pp->ctx; struct amdgpu_device *adev = ctx->driver_context; + void *pp_handle = adev->powerplay.pp_handle; const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs; + struct pp_display_clock_request clock = {0}; - if (!pp_funcs || !pp_funcs->display_configuration_changed) + if (!pp_funcs || !pp_funcs->display_clock_voltage_request) return; - amdgpu_dpm_display_configuration_changed(adev); + clock.clock_type = amd_pp_dcf_clock; + clock.clock_freq_in_khz = req->hard_min_dcefclk_khz; + pp_funcs->display_clock_voltage_request(pp_handle, &clock); + + clock.clock_type = amd_pp_f_clock; + clock.clock_freq_in_khz = req->hard_min_fclk_khz; + pp_funcs->display_clock_voltage_request(pp_handle, &clock); } void pp_rv_set_wm_ranges(struct pp_smu *pp, diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index 567867915d32..37eaf72ace54 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -754,8 +754,12 @@ bool dc_link_detect(struct dc_link *link, enum dc_detect_reason reason) * fail-safe mode */ if (dc_is_hdmi_signal(link->connector_signal) || - dc_is_dvi_signal(link->connector_signal)) + dc_is_dvi_signal(link->connector_signal)) { + if (prev_sink != NULL) + dc_sink_release(prev_sink); + return false; + } default: break; } diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c index 6e3f56684f4e..51ed99a37803 100644 --- a/drivers/gpu/drm/i915/gvt/dmabuf.c +++ b/drivers/gpu/drm/i915/gvt/dmabuf.c @@ -170,20 +170,22 @@ static struct drm_i915_gem_object *vgpu_create_gem(struct drm_device *dev, unsigned int tiling_mode = 0; unsigned int stride = 0; - switch (info->drm_format_mod << 10) { - case PLANE_CTL_TILED_LINEAR: + switch (info->drm_format_mod) { + case DRM_FORMAT_MOD_LINEAR: tiling_mode = I915_TILING_NONE; break; - case PLANE_CTL_TILED_X: + case I915_FORMAT_MOD_X_TILED: tiling_mode = I915_TILING_X; stride = info->stride; break; - case PLANE_CTL_TILED_Y: + case I915_FORMAT_MOD_Y_TILED: + case I915_FORMAT_MOD_Yf_TILED: tiling_mode = I915_TILING_Y; stride = info->stride; break; default: - gvt_dbg_core("not supported tiling mode\n"); + gvt_dbg_core("invalid drm_format_mod %llx for tiling\n", + info->drm_format_mod); } obj->tiling_and_stride = tiling_mode | stride; } else { @@ -222,9 +224,26 @@ static int vgpu_get_plane_info(struct drm_device *dev, info->height = p.height; info->stride = p.stride; info->drm_format = p.drm_format; - info->drm_format_mod = p.tiled; + + switch (p.tiled) { + case PLANE_CTL_TILED_LINEAR: + info->drm_format_mod = DRM_FORMAT_MOD_LINEAR; + break; + case PLANE_CTL_TILED_X: + info->drm_format_mod = I915_FORMAT_MOD_X_TILED; + break; + case PLANE_CTL_TILED_Y: + info->drm_format_mod = I915_FORMAT_MOD_Y_TILED; + break; + case PLANE_CTL_TILED_YF: + info->drm_format_mod = I915_FORMAT_MOD_Yf_TILED; + break; + default: + gvt_vgpu_err("invalid tiling mode: %x\n", p.tiled); + } + info->size = (((p.stride * p.height * p.bpp) / 8) + - (PAGE_SIZE - 1)) >> PAGE_SHIFT; + (PAGE_SIZE - 1)) >> PAGE_SHIFT; } else if (plane_id == DRM_PLANE_TYPE_CURSOR) { ret = intel_vgpu_decode_cursor_plane(vgpu, &c); if (ret) diff --git a/drivers/gpu/drm/i915/gvt/fb_decoder.c b/drivers/gpu/drm/i915/gvt/fb_decoder.c index face664be3e8..481896fb712a 100644 --- a/drivers/gpu/drm/i915/gvt/fb_decoder.c +++ b/drivers/gpu/drm/i915/gvt/fb_decoder.c @@ -220,8 +220,7 @@ int intel_vgpu_decode_primary_plane(struct intel_vgpu *vgpu, if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv) || IS_BROXTON(dev_priv)) { - plane->tiled = (val & PLANE_CTL_TILED_MASK) >> - _PLANE_CTL_TILED_SHIFT; + plane->tiled = val & PLANE_CTL_TILED_MASK; fmt = skl_format_to_drm( val & PLANE_CTL_FORMAT_MASK, val & PLANE_CTL_ORDER_RGBX, @@ -260,7 +259,7 @@ int intel_vgpu_decode_primary_plane(struct intel_vgpu *vgpu, return -EINVAL; } - plane->stride = intel_vgpu_get_stride(vgpu, pipe, (plane->tiled << 10), + plane->stride = intel_vgpu_get_stride(vgpu, pipe, plane->tiled, (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv) || IS_BROXTON(dev_priv)) ? diff --git a/drivers/gpu/drm/i915/gvt/fb_decoder.h b/drivers/gpu/drm/i915/gvt/fb_decoder.h index cb055f3c81a2..60c155085029 100644 --- a/drivers/gpu/drm/i915/gvt/fb_decoder.h +++ b/drivers/gpu/drm/i915/gvt/fb_decoder.h @@ -101,7 +101,7 @@ struct intel_gvt; /* color space conversion and gamma correction are not included */ struct intel_vgpu_primary_plane_format { u8 enabled; /* plane is enabled */ - u8 tiled; /* X-tiled */ + u32 tiled; /* tiling mode: linear, X-tiled, Y tiled, etc */ u8 bpp; /* bits per pixel */ u32 hw_format; /* format field in the PRI_CTL register */ u32 drm_format; /* format in DRM definition */ diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c index 7a58ca555197..72afa518edd9 100644 --- a/drivers/gpu/drm/i915/gvt/handlers.c +++ b/drivers/gpu/drm/i915/gvt/handlers.c @@ -1296,6 +1296,19 @@ static int power_well_ctl_mmio_write(struct intel_vgpu *vgpu, return 0; } +static int gen9_dbuf_ctl_mmio_write(struct intel_vgpu *vgpu, + unsigned int offset, void *p_data, unsigned int bytes) +{ + write_vreg(vgpu, offset, p_data, bytes); + + if (vgpu_vreg(vgpu, offset) & DBUF_POWER_REQUEST) + vgpu_vreg(vgpu, offset) |= DBUF_POWER_STATE; + else + vgpu_vreg(vgpu, offset) &= ~DBUF_POWER_STATE; + + return 0; +} + static int fpga_dbg_mmio_write(struct intel_vgpu *vgpu, unsigned int offset, void *p_data, unsigned int bytes) { @@ -1525,9 +1538,15 @@ static int bxt_phy_ctl_family_write(struct intel_vgpu *vgpu, u32 v = *(u32 *)p_data; u32 data = v & COMMON_RESET_DIS ? BXT_PHY_LANE_ENABLED : 0; - vgpu_vreg(vgpu, _BXT_PHY_CTL_DDI_A) = data; - vgpu_vreg(vgpu, _BXT_PHY_CTL_DDI_B) = data; - vgpu_vreg(vgpu, _BXT_PHY_CTL_DDI_C) = data; + switch (offset) { + case _PHY_CTL_FAMILY_EDP: + vgpu_vreg(vgpu, _BXT_PHY_CTL_DDI_A) = data; + break; + case _PHY_CTL_FAMILY_DDI: + vgpu_vreg(vgpu, _BXT_PHY_CTL_DDI_B) = data; + vgpu_vreg(vgpu, _BXT_PHY_CTL_DDI_C) = data; + break; + } vgpu_vreg(vgpu, offset) = v; @@ -2812,6 +2831,8 @@ static int init_skl_mmio_info(struct intel_gvt *gvt) MMIO_DH(HSW_PWR_WELL_CTL_DRIVER(SKL_DISP_PW_MISC_IO), D_SKL_PLUS, NULL, skl_power_well_ctl_write); + MMIO_DH(DBUF_CTL, D_SKL_PLUS, NULL, gen9_dbuf_ctl_mmio_write); + MMIO_D(_MMIO(0xa210), D_SKL_PLUS); MMIO_D(GEN9_MEDIA_PG_IDLE_HYSTERESIS, D_SKL_PLUS); MMIO_D(GEN9_RENDER_PG_IDLE_HYSTERESIS, D_SKL_PLUS); @@ -2987,8 +3008,6 @@ static int init_skl_mmio_info(struct intel_gvt *gvt) NULL, gen9_trtte_write); MMIO_DH(_MMIO(0x4dfc), D_SKL_PLUS, NULL, gen9_trtt_chicken_write); - MMIO_D(_MMIO(0x45008), D_SKL_PLUS); - MMIO_D(_MMIO(0x46430), D_SKL_PLUS); MMIO_D(_MMIO(0x46520), D_SKL_PLUS); @@ -3025,7 +3044,9 @@ static int init_skl_mmio_info(struct intel_gvt *gvt) MMIO_D(_MMIO(0x44500), D_SKL_PLUS); MMIO_DFH(GEN9_CSFE_CHICKEN1_RCS, D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL); MMIO_DFH(GEN8_HDC_CHICKEN1, D_SKL_PLUS, F_MODE_MASK | F_CMD_ACCESS, - NULL, NULL); + NULL, NULL); + MMIO_DFH(GEN9_WM_CHICKEN3, D_SKL_PLUS, F_MODE_MASK | F_CMD_ACCESS, + NULL, NULL); MMIO_D(_MMIO(0x4ab8), D_KBL); MMIO_D(_MMIO(0x2248), D_KBL | D_SKL); diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c index a45f46d8537f..c7afee37b2b8 100644 --- a/drivers/gpu/drm/i915/gvt/kvmgt.c +++ b/drivers/gpu/drm/i915/gvt/kvmgt.c @@ -32,6 +32,7 @@ #include <linux/device.h> #include <linux/mm.h> #include <linux/mmu_context.h> +#include <linux/sched/mm.h> #include <linux/types.h> #include <linux/list.h> #include <linux/rbtree.h> @@ -1792,16 +1793,21 @@ static int kvmgt_rw_gpa(unsigned long handle, unsigned long gpa, info = (struct kvmgt_guest_info *)handle; kvm = info->kvm; - if (kthread) + if (kthread) { + if (!mmget_not_zero(kvm->mm)) + return -EFAULT; use_mm(kvm->mm); + } idx = srcu_read_lock(&kvm->srcu); ret = write ? kvm_write_guest(kvm, gpa, buf, len) : kvm_read_guest(kvm, gpa, buf, len); srcu_read_unlock(&kvm->srcu, idx); - if (kthread) + if (kthread) { unuse_mm(kvm->mm); + mmput(kvm->mm); + } return ret; } diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c index 42e1e6bdcc2c..e872f4847fbe 100644 --- a/drivers/gpu/drm/i915/gvt/mmio_context.c +++ b/drivers/gpu/drm/i915/gvt/mmio_context.c @@ -562,11 +562,9 @@ void intel_gvt_switch_mmio(struct intel_vgpu *pre, * performace for batch mmio read/write, so we need * handle forcewake mannually. */ - intel_runtime_pm_get(dev_priv); intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL); switch_mmio(pre, next, ring_id); intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL); - intel_runtime_pm_put(dev_priv); } /** diff --git a/drivers/gpu/drm/i915/gvt/opregion.c b/drivers/gpu/drm/i915/gvt/opregion.c index fa75a2eead90..b0d3a43ccd03 100644 --- a/drivers/gpu/drm/i915/gvt/opregion.c +++ b/drivers/gpu/drm/i915/gvt/opregion.c @@ -42,8 +42,6 @@ #define DEVICE_TYPE_EFP3 0x20 #define DEVICE_TYPE_EFP4 0x10 -#define DEV_SIZE 38 - struct opregion_header { u8 signature[16]; u32 size; @@ -63,6 +61,10 @@ struct bdb_data_header { u16 size; /* data size */ } __packed; +/* For supporting windows guest with opregion, here hardcode the emulated + * bdb header version as '186', and the corresponding child_device_config + * length should be '33' but not '38'. + */ struct efp_child_device_config { u16 handle; u16 device_type; @@ -109,12 +111,6 @@ struct efp_child_device_config { u8 mipi_bridge_type; /* 171 */ u16 device_class_ext; u8 dvo_function; - u8 dp_usb_type_c:1; /* 195 */ - u8 skip6:7; - u8 dp_usb_type_c_2x_gpio_index; /* 195 */ - u16 dp_usb_type_c_2x_gpio_pin; /* 195 */ - u8 iboost_dp:4; /* 196 */ - u8 iboost_hdmi:4; /* 196 */ } __packed; struct vbt { @@ -155,7 +151,7 @@ static void virt_vbt_generation(struct vbt *v) v->header.bdb_offset = offsetof(struct vbt, bdb_header); strcpy(&v->bdb_header.signature[0], "BIOS_DATA_BLOCK"); - v->bdb_header.version = 186; /* child_dev_size = 38 */ + v->bdb_header.version = 186; /* child_dev_size = 33 */ v->bdb_header.header_size = sizeof(v->bdb_header); v->bdb_header.bdb_size = sizeof(struct vbt) - sizeof(struct vbt_header) @@ -169,11 +165,13 @@ static void virt_vbt_generation(struct vbt *v) /* child device */ num_child = 4; /* each port has one child */ + v->general_definitions.child_dev_size = + sizeof(struct efp_child_device_config); v->general_definitions_header.id = BDB_GENERAL_DEFINITIONS; /* size will include child devices */ v->general_definitions_header.size = - sizeof(struct bdb_general_definitions) + num_child * DEV_SIZE; - v->general_definitions.child_dev_size = DEV_SIZE; + sizeof(struct bdb_general_definitions) + + num_child * v->general_definitions.child_dev_size; /* portA */ v->child0.handle = DEVICE_TYPE_EFP1; diff --git a/drivers/gpu/drm/i915/gvt/sched_policy.c b/drivers/gpu/drm/i915/gvt/sched_policy.c index 09d7bb72b4ff..c32e7d5e8629 100644 --- a/drivers/gpu/drm/i915/gvt/sched_policy.c +++ b/drivers/gpu/drm/i915/gvt/sched_policy.c @@ -47,11 +47,15 @@ static bool vgpu_has_pending_workload(struct intel_vgpu *vgpu) return false; } +/* We give 2 seconds higher prio for vGPU during start */ +#define GVT_SCHED_VGPU_PRI_TIME 2 + struct vgpu_sched_data { struct list_head lru_list; struct intel_vgpu *vgpu; bool active; - + bool pri_sched; + ktime_t pri_time; ktime_t sched_in_time; ktime_t sched_time; ktime_t left_ts; @@ -183,6 +187,14 @@ static struct intel_vgpu *find_busy_vgpu(struct gvt_sched_data *sched_data) if (!vgpu_has_pending_workload(vgpu_data->vgpu)) continue; + if (vgpu_data->pri_sched) { + if (ktime_before(ktime_get(), vgpu_data->pri_time)) { + vgpu = vgpu_data->vgpu; + break; + } else + vgpu_data->pri_sched = false; + } + /* Return the vGPU only if it has time slice left */ if (vgpu_data->left_ts > 0) { vgpu = vgpu_data->vgpu; @@ -202,6 +214,7 @@ static void tbs_sched_func(struct gvt_sched_data *sched_data) struct intel_gvt_workload_scheduler *scheduler = &gvt->scheduler; struct vgpu_sched_data *vgpu_data; struct intel_vgpu *vgpu = NULL; + /* no active vgpu or has already had a target */ if (list_empty(&sched_data->lru_runq_head) || scheduler->next_vgpu) goto out; @@ -209,12 +222,13 @@ static void tbs_sched_func(struct gvt_sched_data *sched_data) vgpu = find_busy_vgpu(sched_data); if (vgpu) { scheduler->next_vgpu = vgpu; - - /* Move the last used vGPU to the tail of lru_list */ vgpu_data = vgpu->sched_data; - list_del_init(&vgpu_data->lru_list); - list_add_tail(&vgpu_data->lru_list, - &sched_data->lru_runq_head); + if (!vgpu_data->pri_sched) { + /* Move the last used vGPU to the tail of lru_list */ + list_del_init(&vgpu_data->lru_list); + list_add_tail(&vgpu_data->lru_list, + &sched_data->lru_runq_head); + } } else { scheduler->next_vgpu = gvt->idle_vgpu; } @@ -328,11 +342,17 @@ static void tbs_sched_start_schedule(struct intel_vgpu *vgpu) { struct gvt_sched_data *sched_data = vgpu->gvt->scheduler.sched_data; struct vgpu_sched_data *vgpu_data = vgpu->sched_data; + ktime_t now; if (!list_empty(&vgpu_data->lru_list)) return; - list_add_tail(&vgpu_data->lru_list, &sched_data->lru_runq_head); + now = ktime_get(); + vgpu_data->pri_time = ktime_add(now, + ktime_set(GVT_SCHED_VGPU_PRI_TIME, 0)); + vgpu_data->pri_sched = true; + + list_add(&vgpu_data->lru_list, &sched_data->lru_runq_head); if (!hrtimer_active(&sched_data->timer)) hrtimer_start(&sched_data->timer, ktime_add_ns(ktime_get(), @@ -426,6 +446,7 @@ void intel_vgpu_stop_schedule(struct intel_vgpu *vgpu) &vgpu->gvt->scheduler; int ring_id; struct vgpu_sched_data *vgpu_data = vgpu->sched_data; + struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv; if (!vgpu_data->active) return; @@ -444,6 +465,7 @@ void intel_vgpu_stop_schedule(struct intel_vgpu *vgpu) scheduler->current_vgpu = NULL; } + intel_runtime_pm_get(dev_priv); spin_lock_bh(&scheduler->mmio_context_lock); for (ring_id = 0; ring_id < I915_NUM_ENGINES; ring_id++) { if (scheduler->engine_owner[ring_id] == vgpu) { @@ -452,5 +474,6 @@ void intel_vgpu_stop_schedule(struct intel_vgpu *vgpu) } } spin_unlock_bh(&scheduler->mmio_context_lock); + intel_runtime_pm_put(dev_priv); mutex_unlock(&vgpu->gvt->sched_lock); } diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 08ec7446282e..9e63cd47b60f 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -10422,7 +10422,7 @@ enum skl_power_gate { _ICL_DSC0_PICTURE_PARAMETER_SET_4_PB, \ _ICL_DSC0_PICTURE_PARAMETER_SET_4_PC) #define ICL_DSC1_PICTURE_PARAMETER_SET_4(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ - _ICL_DSC0_PICTURE_PARAMETER_SET_4_PB, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_4_PB, \ _ICL_DSC1_PICTURE_PARAMETER_SET_4_PC) #define DSC_INITIAL_DEC_DELAY(dec_delay) ((dec_delay) << 16) #define DSC_INITIAL_XMIT_DELAY(xmit_delay) ((xmit_delay) << 0) @@ -10437,7 +10437,7 @@ enum skl_power_gate { _ICL_DSC0_PICTURE_PARAMETER_SET_5_PB, \ _ICL_DSC0_PICTURE_PARAMETER_SET_5_PC) #define ICL_DSC1_PICTURE_PARAMETER_SET_5(pipe) _MMIO_PIPE((pipe) - PIPE_B, \ - _ICL_DSC1_PICTURE_PARAMETER_SET_5_PC, \ + _ICL_DSC1_PICTURE_PARAMETER_SET_5_PB, \ _ICL_DSC1_PICTURE_PARAMETER_SET_5_PC) #define DSC_SCALE_DEC_INTINT(scale_dec) ((scale_dec) << 16) #define DSC_SCALE_INC_INT(scale_inc) ((scale_inc) << 0) diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c index 11d834f94220..98358b4b36de 100644 --- a/drivers/gpu/drm/i915/i915_vma.c +++ b/drivers/gpu/drm/i915/i915_vma.c @@ -199,7 +199,6 @@ vma_create(struct drm_i915_gem_object *obj, vma->flags |= I915_VMA_GGTT; list_add(&vma->obj_link, &obj->vma_list); } else { - i915_ppgtt_get(i915_vm_to_ppgtt(vm)); list_add_tail(&vma->obj_link, &obj->vma_list); } @@ -807,9 +806,6 @@ static void __i915_vma_destroy(struct i915_vma *vma) if (vma->obj) rb_erase(&vma->obj_node, &vma->obj->vma_tree); - if (!i915_vma_is_ggtt(vma)) - i915_ppgtt_put(i915_vm_to_ppgtt(vma->vm)); - rbtree_postorder_for_each_entry_safe(iter, n, &vma->active, node) { GEM_BUG_ON(i915_gem_active_isset(&iter->base)); kfree(iter); diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c index b725835b47ef..769f3f586661 100644 --- a/drivers/gpu/drm/i915/intel_audio.c +++ b/drivers/gpu/drm/i915/intel_audio.c @@ -962,9 +962,6 @@ void i915_audio_component_init(struct drm_i915_private *dev_priv) { int ret; - if (INTEL_INFO(dev_priv)->num_pipes == 0) - return; - ret = component_add(dev_priv->drm.dev, &i915_audio_component_bind_ops); if (ret < 0) { DRM_ERROR("failed to add audio component (%d)\n", ret); diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index 8761513f3532..c9af34861d9e 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -2708,7 +2708,8 @@ static void intel_ddi_pre_enable_dp(struct intel_encoder *encoder, if (port != PORT_A || INTEL_GEN(dev_priv) >= 9) intel_dp_stop_link_train(intel_dp); - intel_ddi_enable_pipe_clock(crtc_state); + if (!is_mst) + intel_ddi_enable_pipe_clock(crtc_state); } static void intel_ddi_pre_enable_hdmi(struct intel_encoder *encoder, @@ -2810,14 +2811,14 @@ static void intel_ddi_post_disable_dp(struct intel_encoder *encoder, bool is_mst = intel_crtc_has_type(old_crtc_state, INTEL_OUTPUT_DP_MST); - intel_ddi_disable_pipe_clock(old_crtc_state); - - /* - * Power down sink before disabling the port, otherwise we end - * up getting interrupts from the sink on detecting link loss. - */ - if (!is_mst) + if (!is_mst) { + intel_ddi_disable_pipe_clock(old_crtc_state); + /* + * Power down sink before disabling the port, otherwise we end + * up getting interrupts from the sink on detecting link loss. + */ intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_OFF); + } intel_disable_ddi_buf(encoder); diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index ed3fa1c8a983..d2951096bca0 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -2988,6 +2988,7 @@ static int skl_check_main_surface(const struct intel_crtc_state *crtc_state, int w = drm_rect_width(&plane_state->base.src) >> 16; int h = drm_rect_height(&plane_state->base.src) >> 16; int dst_x = plane_state->base.dst.x1; + int dst_w = drm_rect_width(&plane_state->base.dst); int pipe_src_w = crtc_state->pipe_src_w; int max_width = skl_max_plane_width(fb, 0, rotation); int max_height = 4096; @@ -3009,10 +3010,10 @@ static int skl_check_main_surface(const struct intel_crtc_state *crtc_state, * screen may cause FIFO underflow and display corruption. */ if ((IS_GEMINILAKE(dev_priv) || IS_CANNONLAKE(dev_priv)) && - (dst_x + w < 4 || dst_x > pipe_src_w - 4)) { + (dst_x + dst_w < 4 || dst_x > pipe_src_w - 4)) { DRM_DEBUG_KMS("requested plane X %s position %d invalid (valid range %d-%d)\n", - dst_x + w < 4 ? "end" : "start", - dst_x + w < 4 ? dst_x + w : dst_x, + dst_x + dst_w < 4 ? "end" : "start", + dst_x + dst_w < 4 ? dst_x + dst_w : dst_x, 4, pipe_src_w - 4); return -ERANGE; } @@ -5078,10 +5079,14 @@ void hsw_disable_ips(const struct intel_crtc_state *crtc_state) mutex_lock(&dev_priv->pcu_lock); WARN_ON(sandybridge_pcode_write(dev_priv, DISPLAY_IPS_CONTROL, 0)); mutex_unlock(&dev_priv->pcu_lock); - /* wait for pcode to finish disabling IPS, which may take up to 42ms */ + /* + * Wait for PCODE to finish disabling IPS. The BSpec specified + * 42ms timeout value leads to occasional timeouts so use 100ms + * instead. + */ if (intel_wait_for_register(dev_priv, IPS_CTL, IPS_ENABLE, 0, - 42)) + 100)) DRM_ERROR("Timed out waiting for IPS disable\n"); } else { I915_WRITE(IPS_CTL, 0); diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index cd0f649b57a5..1193202766a2 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -4160,18 +4160,6 @@ intel_dp_needs_link_retrain(struct intel_dp *intel_dp) return !drm_dp_channel_eq_ok(link_status, intel_dp->lane_count); } -/* - * If display is now connected check links status, - * there has been known issues of link loss triggering - * long pulse. - * - * Some sinks (eg. ASUS PB287Q) seem to perform some - * weird HPD ping pong during modesets. So we can apparently - * end up with HPD going low during a modeset, and then - * going back up soon after. And once that happens we must - * retrain the link to get a picture. That's in case no - * userspace component reacted to intermittent HPD dip. - */ int intel_dp_retrain_link(struct intel_encoder *encoder, struct drm_modeset_acquire_ctx *ctx) { @@ -4661,7 +4649,8 @@ intel_dp_unset_edid(struct intel_dp *intel_dp) } static int -intel_dp_long_pulse(struct intel_connector *connector) +intel_dp_long_pulse(struct intel_connector *connector, + struct drm_modeset_acquire_ctx *ctx) { struct drm_i915_private *dev_priv = to_i915(connector->base.dev); struct intel_dp *intel_dp = intel_attached_dp(&connector->base); @@ -4720,6 +4709,22 @@ intel_dp_long_pulse(struct intel_connector *connector) */ status = connector_status_disconnected; goto out; + } else { + /* + * If display is now connected check links status, + * there has been known issues of link loss triggering + * long pulse. + * + * Some sinks (eg. ASUS PB287Q) seem to perform some + * weird HPD ping pong during modesets. So we can apparently + * end up with HPD going low during a modeset, and then + * going back up soon after. And once that happens we must + * retrain the link to get a picture. That's in case no + * userspace component reacted to intermittent HPD dip. + */ + struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; + + intel_dp_retrain_link(encoder, ctx); } /* @@ -4781,7 +4786,7 @@ intel_dp_detect(struct drm_connector *connector, return ret; } - status = intel_dp_long_pulse(intel_dp->attached_connector); + status = intel_dp_long_pulse(intel_dp->attached_connector, ctx); } intel_dp->detect_done = false; diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c index 7e3e01607643..4ecd65375603 100644 --- a/drivers/gpu/drm/i915/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/intel_dp_mst.c @@ -166,6 +166,8 @@ static void intel_mst_post_disable_dp(struct intel_encoder *encoder, struct intel_connector *connector = to_intel_connector(old_conn_state->connector); + intel_ddi_disable_pipe_clock(old_crtc_state); + /* this can fail */ drm_dp_check_act_status(&intel_dp->mst_mgr); /* and this can also fail */ @@ -252,6 +254,8 @@ static void intel_mst_pre_enable_dp(struct intel_encoder *encoder, I915_WRITE(DP_TP_STATUS(port), temp); ret = drm_dp_update_payload_part1(&intel_dp->mst_mgr); + + intel_ddi_enable_pipe_clock(pipe_config); } static void intel_mst_enable_dp(struct intel_encoder *encoder, diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index a9076402dcb0..192972a7d287 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -943,8 +943,12 @@ static int intel_hdmi_hdcp_write(struct intel_digital_port *intel_dig_port, ret = i2c_transfer(adapter, &msg, 1); if (ret == 1) - return 0; - return ret >= 0 ? -EIO : ret; + ret = 0; + else if (ret >= 0) + ret = -EIO; + + kfree(write_buf); + return ret; } static diff --git a/drivers/gpu/drm/i915/intel_lspcon.c b/drivers/gpu/drm/i915/intel_lspcon.c index 5dae16ccd9f1..3e085c5f2b81 100644 --- a/drivers/gpu/drm/i915/intel_lspcon.c +++ b/drivers/gpu/drm/i915/intel_lspcon.c @@ -74,7 +74,7 @@ static enum drm_lspcon_mode lspcon_wait_mode(struct intel_lspcon *lspcon, DRM_DEBUG_KMS("Waiting for LSPCON mode %s to settle\n", lspcon_mode_name(mode)); - wait_for((current_mode = lspcon_get_current_mode(lspcon)) == mode, 100); + wait_for((current_mode = lspcon_get_current_mode(lspcon)) == mode, 400); if (current_mode != mode) DRM_ERROR("LSPCON mode hasn't settled\n"); diff --git a/drivers/gpu/drm/i915/intel_overlay.c b/drivers/gpu/drm/i915/intel_overlay.c index c2f10d899329..443dfaefd7a6 100644 --- a/drivers/gpu/drm/i915/intel_overlay.c +++ b/drivers/gpu/drm/i915/intel_overlay.c @@ -181,8 +181,9 @@ struct intel_overlay { u32 brightness, contrast, saturation; u32 old_xscale, old_yscale; /* register access */ - u32 flip_addr; struct drm_i915_gem_object *reg_bo; + struct overlay_registers __iomem *regs; + u32 flip_addr; /* flip handling */ struct i915_gem_active last_flip; }; @@ -210,29 +211,6 @@ static void i830_overlay_clock_gating(struct drm_i915_private *dev_priv, PCI_DEVFN(0, 0), I830_CLOCK_GATE, val); } -static struct overlay_registers __iomem * -intel_overlay_map_regs(struct intel_overlay *overlay) -{ - struct drm_i915_private *dev_priv = overlay->i915; - struct overlay_registers __iomem *regs; - - if (OVERLAY_NEEDS_PHYSICAL(dev_priv)) - regs = (struct overlay_registers __iomem *)overlay->reg_bo->phys_handle->vaddr; - else - regs = io_mapping_map_wc(&dev_priv->ggtt.iomap, - overlay->flip_addr, - PAGE_SIZE); - - return regs; -} - -static void intel_overlay_unmap_regs(struct intel_overlay *overlay, - struct overlay_registers __iomem *regs) -{ - if (!OVERLAY_NEEDS_PHYSICAL(overlay->i915)) - io_mapping_unmap(regs); -} - static void intel_overlay_submit_request(struct intel_overlay *overlay, struct i915_request *rq, i915_gem_retire_fn retire) @@ -784,13 +762,13 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay, struct drm_i915_gem_object *new_bo, struct put_image_params *params) { - int ret, tmp_width; - struct overlay_registers __iomem *regs; - bool scale_changed = false; + struct overlay_registers __iomem *regs = overlay->regs; struct drm_i915_private *dev_priv = overlay->i915; u32 swidth, swidthsw, sheight, ostride; enum pipe pipe = overlay->crtc->pipe; + bool scale_changed = false; struct i915_vma *vma; + int ret, tmp_width; lockdep_assert_held(&dev_priv->drm.struct_mutex); WARN_ON(!drm_modeset_is_locked(&dev_priv->drm.mode_config.connection_mutex)); @@ -815,30 +793,19 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay, if (!overlay->active) { u32 oconfig; - regs = intel_overlay_map_regs(overlay); - if (!regs) { - ret = -ENOMEM; - goto out_unpin; - } + oconfig = OCONF_CC_OUT_8BIT; if (IS_GEN4(dev_priv)) oconfig |= OCONF_CSC_MODE_BT709; oconfig |= pipe == 0 ? OCONF_PIPE_A : OCONF_PIPE_B; iowrite32(oconfig, ®s->OCONFIG); - intel_overlay_unmap_regs(overlay, regs); ret = intel_overlay_on(overlay); if (ret != 0) goto out_unpin; } - regs = intel_overlay_map_regs(overlay); - if (!regs) { - ret = -ENOMEM; - goto out_unpin; - } - iowrite32((params->dst_y << 16) | params->dst_x, ®s->DWINPOS); iowrite32((params->dst_h << 16) | params->dst_w, ®s->DWINSZ); @@ -882,8 +849,6 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay, iowrite32(overlay_cmd_reg(params), ®s->OCMD); - intel_overlay_unmap_regs(overlay, regs); - ret = intel_overlay_continue(overlay, vma, scale_changed); if (ret) goto out_unpin; @@ -901,7 +866,6 @@ out_pin_section: int intel_overlay_switch_off(struct intel_overlay *overlay) { struct drm_i915_private *dev_priv = overlay->i915; - struct overlay_registers __iomem *regs; int ret; lockdep_assert_held(&dev_priv->drm.struct_mutex); @@ -918,9 +882,7 @@ int intel_overlay_switch_off(struct intel_overlay *overlay) if (ret != 0) return ret; - regs = intel_overlay_map_regs(overlay); - iowrite32(0, ®s->OCMD); - intel_overlay_unmap_regs(overlay, regs); + iowrite32(0, &overlay->regs->OCMD); return intel_overlay_off(overlay); } @@ -1305,7 +1267,6 @@ int intel_overlay_attrs_ioctl(struct drm_device *dev, void *data, struct drm_intel_overlay_attrs *attrs = data; struct drm_i915_private *dev_priv = to_i915(dev); struct intel_overlay *overlay; - struct overlay_registers __iomem *regs; int ret; overlay = dev_priv->overlay; @@ -1345,15 +1306,7 @@ int intel_overlay_attrs_ioctl(struct drm_device *dev, void *data, overlay->contrast = attrs->contrast; overlay->saturation = attrs->saturation; - regs = intel_overlay_map_regs(overlay); - if (!regs) { - ret = -ENOMEM; - goto out_unlock; - } - - update_reg_attrs(overlay, regs); - - intel_overlay_unmap_regs(overlay, regs); + update_reg_attrs(overlay, overlay->regs); if (attrs->flags & I915_OVERLAY_UPDATE_GAMMA) { if (IS_GEN2(dev_priv)) @@ -1386,12 +1339,47 @@ out_unlock: return ret; } +static int get_registers(struct intel_overlay *overlay, bool use_phys) +{ + struct drm_i915_gem_object *obj; + struct i915_vma *vma; + int err; + + obj = i915_gem_object_create_stolen(overlay->i915, PAGE_SIZE); + if (obj == NULL) + obj = i915_gem_object_create_internal(overlay->i915, PAGE_SIZE); + if (IS_ERR(obj)) + return PTR_ERR(obj); + + vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, PIN_MAPPABLE); + if (IS_ERR(vma)) { + err = PTR_ERR(vma); + goto err_put_bo; + } + + if (use_phys) + overlay->flip_addr = sg_dma_address(obj->mm.pages->sgl); + else + overlay->flip_addr = i915_ggtt_offset(vma); + overlay->regs = i915_vma_pin_iomap(vma); + i915_vma_unpin(vma); + + if (IS_ERR(overlay->regs)) { + err = PTR_ERR(overlay->regs); + goto err_put_bo; + } + + overlay->reg_bo = obj; + return 0; + +err_put_bo: + i915_gem_object_put(obj); + return err; +} + void intel_setup_overlay(struct drm_i915_private *dev_priv) { struct intel_overlay *overlay; - struct drm_i915_gem_object *reg_bo; - struct overlay_registers __iomem *regs; - struct i915_vma *vma = NULL; int ret; if (!HAS_OVERLAY(dev_priv)) @@ -1401,46 +1389,8 @@ void intel_setup_overlay(struct drm_i915_private *dev_priv) if (!overlay) return; - mutex_lock(&dev_priv->drm.struct_mutex); - if (WARN_ON(dev_priv->overlay)) - goto out_free; - overlay->i915 = dev_priv; - reg_bo = NULL; - if (!OVERLAY_NEEDS_PHYSICAL(dev_priv)) - reg_bo = i915_gem_object_create_stolen(dev_priv, PAGE_SIZE); - if (reg_bo == NULL) - reg_bo = i915_gem_object_create(dev_priv, PAGE_SIZE); - if (IS_ERR(reg_bo)) - goto out_free; - overlay->reg_bo = reg_bo; - - if (OVERLAY_NEEDS_PHYSICAL(dev_priv)) { - ret = i915_gem_object_attach_phys(reg_bo, PAGE_SIZE); - if (ret) { - DRM_ERROR("failed to attach phys overlay regs\n"); - goto out_free_bo; - } - overlay->flip_addr = reg_bo->phys_handle->busaddr; - } else { - vma = i915_gem_object_ggtt_pin(reg_bo, NULL, - 0, PAGE_SIZE, PIN_MAPPABLE); - if (IS_ERR(vma)) { - DRM_ERROR("failed to pin overlay register bo\n"); - ret = PTR_ERR(vma); - goto out_free_bo; - } - overlay->flip_addr = i915_ggtt_offset(vma); - - ret = i915_gem_object_set_to_gtt_domain(reg_bo, true); - if (ret) { - DRM_ERROR("failed to move overlay register bo into the GTT\n"); - goto out_unpin_bo; - } - } - - /* init all values */ overlay->color_key = 0x0101fe; overlay->color_key_enabled = true; overlay->brightness = -19; @@ -1449,44 +1399,51 @@ void intel_setup_overlay(struct drm_i915_private *dev_priv) init_request_active(&overlay->last_flip, NULL); - regs = intel_overlay_map_regs(overlay); - if (!regs) - goto out_unpin_bo; + mutex_lock(&dev_priv->drm.struct_mutex); + + ret = get_registers(overlay, OVERLAY_NEEDS_PHYSICAL(dev_priv)); + if (ret) + goto out_free; + + ret = i915_gem_object_set_to_gtt_domain(overlay->reg_bo, true); + if (ret) + goto out_reg_bo; - memset_io(regs, 0, sizeof(struct overlay_registers)); - update_polyphase_filter(regs); - update_reg_attrs(overlay, regs); + mutex_unlock(&dev_priv->drm.struct_mutex); - intel_overlay_unmap_regs(overlay, regs); + memset_io(overlay->regs, 0, sizeof(struct overlay_registers)); + update_polyphase_filter(overlay->regs); + update_reg_attrs(overlay, overlay->regs); dev_priv->overlay = overlay; - mutex_unlock(&dev_priv->drm.struct_mutex); - DRM_INFO("initialized overlay support\n"); + DRM_INFO("Initialized overlay support.\n"); return; -out_unpin_bo: - if (vma) - i915_vma_unpin(vma); -out_free_bo: - i915_gem_object_put(reg_bo); +out_reg_bo: + i915_gem_object_put(overlay->reg_bo); out_free: mutex_unlock(&dev_priv->drm.struct_mutex); kfree(overlay); - return; } void intel_cleanup_overlay(struct drm_i915_private *dev_priv) { - if (!dev_priv->overlay) + struct intel_overlay *overlay; + + overlay = fetch_and_zero(&dev_priv->overlay); + if (!overlay) return; - /* The bo's should be free'd by the generic code already. + /* + * The bo's should be free'd by the generic code already. * Furthermore modesetting teardown happens beforehand so the - * hardware should be off already */ - WARN_ON(dev_priv->overlay->active); + * hardware should be off already. + */ + WARN_ON(overlay->active); + + i915_gem_object_put(overlay->reg_bo); - i915_gem_object_put(dev_priv->overlay->reg_bo); - kfree(dev_priv->overlay); + kfree(overlay); } #if IS_ENABLED(CONFIG_DRM_I915_CAPTURE_ERROR) @@ -1498,37 +1455,11 @@ struct intel_overlay_error_state { u32 isr; }; -static struct overlay_registers __iomem * -intel_overlay_map_regs_atomic(struct intel_overlay *overlay) -{ - struct drm_i915_private *dev_priv = overlay->i915; - struct overlay_registers __iomem *regs; - - if (OVERLAY_NEEDS_PHYSICAL(dev_priv)) - /* Cast to make sparse happy, but it's wc memory anyway, so - * equivalent to the wc io mapping on X86. */ - regs = (struct overlay_registers __iomem *) - overlay->reg_bo->phys_handle->vaddr; - else - regs = io_mapping_map_atomic_wc(&dev_priv->ggtt.iomap, - overlay->flip_addr); - - return regs; -} - -static void intel_overlay_unmap_regs_atomic(struct intel_overlay *overlay, - struct overlay_registers __iomem *regs) -{ - if (!OVERLAY_NEEDS_PHYSICAL(overlay->i915)) - io_mapping_unmap_atomic(regs); -} - struct intel_overlay_error_state * intel_overlay_capture_error_state(struct drm_i915_private *dev_priv) { struct intel_overlay *overlay = dev_priv->overlay; struct intel_overlay_error_state *error; - struct overlay_registers __iomem *regs; if (!overlay || !overlay->active) return NULL; @@ -1541,18 +1472,9 @@ intel_overlay_capture_error_state(struct drm_i915_private *dev_priv) error->isr = I915_READ(ISR); error->base = overlay->flip_addr; - regs = intel_overlay_map_regs_atomic(overlay); - if (!regs) - goto err; - - memcpy_fromio(&error->regs, regs, sizeof(struct overlay_registers)); - intel_overlay_unmap_regs_atomic(overlay, regs); + memcpy_fromio(&error->regs, overlay->regs, sizeof(error->regs)); return error; - -err: - kfree(error); - return NULL; } void diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c index 978782a77629..28d191192945 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c @@ -132,6 +132,11 @@ static void mtk_ovl_config(struct mtk_ddp_comp *comp, unsigned int w, writel(0x0, comp->regs + DISP_REG_OVL_RST); } +static unsigned int mtk_ovl_layer_nr(struct mtk_ddp_comp *comp) +{ + return 4; +} + static void mtk_ovl_layer_on(struct mtk_ddp_comp *comp, unsigned int idx) { unsigned int reg; @@ -157,6 +162,11 @@ static void mtk_ovl_layer_off(struct mtk_ddp_comp *comp, unsigned int idx) static unsigned int ovl_fmt_convert(struct mtk_disp_ovl *ovl, unsigned int fmt) { + /* The return value in switch "MEM_MODE_INPUT_FORMAT_XXX" + * is defined in mediatek HW data sheet. + * The alphabet order in XXX is no relation to data + * arrangement in memory. + */ switch (fmt) { default: case DRM_FORMAT_RGB565: @@ -221,6 +231,7 @@ static const struct mtk_ddp_comp_funcs mtk_disp_ovl_funcs = { .stop = mtk_ovl_stop, .enable_vblank = mtk_ovl_enable_vblank, .disable_vblank = mtk_ovl_disable_vblank, + .layer_nr = mtk_ovl_layer_nr, .layer_on = mtk_ovl_layer_on, .layer_off = mtk_ovl_layer_off, .layer_config = mtk_ovl_layer_config, diff --git a/drivers/gpu/drm/mediatek/mtk_disp_rdma.c b/drivers/gpu/drm/mediatek/mtk_disp_rdma.c index 585943c81e1f..b0a5cffe345a 100644 --- a/drivers/gpu/drm/mediatek/mtk_disp_rdma.c +++ b/drivers/gpu/drm/mediatek/mtk_disp_rdma.c @@ -31,14 +31,31 @@ #define RDMA_REG_UPDATE_INT BIT(0) #define DISP_REG_RDMA_GLOBAL_CON 0x0010 #define RDMA_ENGINE_EN BIT(0) +#define RDMA_MODE_MEMORY BIT(1) #define DISP_REG_RDMA_SIZE_CON_0 0x0014 +#define RDMA_MATRIX_ENABLE BIT(17) +#define RDMA_MATRIX_INT_MTX_SEL GENMASK(23, 20) +#define RDMA_MATRIX_INT_MTX_BT601_to_RGB (6 << 20) #define DISP_REG_RDMA_SIZE_CON_1 0x0018 #define DISP_REG_RDMA_TARGET_LINE 0x001c +#define DISP_RDMA_MEM_CON 0x0024 +#define MEM_MODE_INPUT_FORMAT_RGB565 (0x000 << 4) +#define MEM_MODE_INPUT_FORMAT_RGB888 (0x001 << 4) +#define MEM_MODE_INPUT_FORMAT_RGBA8888 (0x002 << 4) +#define MEM_MODE_INPUT_FORMAT_ARGB8888 (0x003 << 4) +#define MEM_MODE_INPUT_FORMAT_UYVY (0x004 << 4) +#define MEM_MODE_INPUT_FORMAT_YUYV (0x005 << 4) +#define MEM_MODE_INPUT_SWAP BIT(8) +#define DISP_RDMA_MEM_SRC_PITCH 0x002c +#define DISP_RDMA_MEM_GMC_SETTING_0 0x0030 #define DISP_REG_RDMA_FIFO_CON 0x0040 #define RDMA_FIFO_UNDERFLOW_EN BIT(31) #define RDMA_FIFO_PSEUDO_SIZE(bytes) (((bytes) / 16) << 16) #define RDMA_OUTPUT_VALID_FIFO_THRESHOLD(bytes) ((bytes) / 16) #define RDMA_FIFO_SIZE(rdma) ((rdma)->data->fifo_size) +#define DISP_RDMA_MEM_START_ADDR 0x0f00 + +#define RDMA_MEM_GMC 0x40402020 struct mtk_disp_rdma_data { unsigned int fifo_size; @@ -138,12 +155,87 @@ static void mtk_rdma_config(struct mtk_ddp_comp *comp, unsigned int width, writel(reg, comp->regs + DISP_REG_RDMA_FIFO_CON); } +static unsigned int rdma_fmt_convert(struct mtk_disp_rdma *rdma, + unsigned int fmt) +{ + /* The return value in switch "MEM_MODE_INPUT_FORMAT_XXX" + * is defined in mediatek HW data sheet. + * The alphabet order in XXX is no relation to data + * arrangement in memory. + */ + switch (fmt) { + default: + case DRM_FORMAT_RGB565: + return MEM_MODE_INPUT_FORMAT_RGB565; + case DRM_FORMAT_BGR565: + return MEM_MODE_INPUT_FORMAT_RGB565 | MEM_MODE_INPUT_SWAP; + case DRM_FORMAT_RGB888: + return MEM_MODE_INPUT_FORMAT_RGB888; + case DRM_FORMAT_BGR888: + return MEM_MODE_INPUT_FORMAT_RGB888 | MEM_MODE_INPUT_SWAP; + case DRM_FORMAT_RGBX8888: + case DRM_FORMAT_RGBA8888: + return MEM_MODE_INPUT_FORMAT_ARGB8888; + case DRM_FORMAT_BGRX8888: + case DRM_FORMAT_BGRA8888: + return MEM_MODE_INPUT_FORMAT_ARGB8888 | MEM_MODE_INPUT_SWAP; + case DRM_FORMAT_XRGB8888: + case DRM_FORMAT_ARGB8888: + return MEM_MODE_INPUT_FORMAT_RGBA8888; + case DRM_FORMAT_XBGR8888: + case DRM_FORMAT_ABGR8888: + return MEM_MODE_INPUT_FORMAT_RGBA8888 | MEM_MODE_INPUT_SWAP; + case DRM_FORMAT_UYVY: + return MEM_MODE_INPUT_FORMAT_UYVY; + case DRM_FORMAT_YUYV: + return MEM_MODE_INPUT_FORMAT_YUYV; + } +} + +static unsigned int mtk_rdma_layer_nr(struct mtk_ddp_comp *comp) +{ + return 1; +} + +static void mtk_rdma_layer_config(struct mtk_ddp_comp *comp, unsigned int idx, + struct mtk_plane_state *state) +{ + struct mtk_disp_rdma *rdma = comp_to_rdma(comp); + struct mtk_plane_pending_state *pending = &state->pending; + unsigned int addr = pending->addr; + unsigned int pitch = pending->pitch & 0xffff; + unsigned int fmt = pending->format; + unsigned int con; + + con = rdma_fmt_convert(rdma, fmt); + writel_relaxed(con, comp->regs + DISP_RDMA_MEM_CON); + + if (fmt == DRM_FORMAT_UYVY || fmt == DRM_FORMAT_YUYV) { + rdma_update_bits(comp, DISP_REG_RDMA_SIZE_CON_0, + RDMA_MATRIX_ENABLE, RDMA_MATRIX_ENABLE); + rdma_update_bits(comp, DISP_REG_RDMA_SIZE_CON_0, + RDMA_MATRIX_INT_MTX_SEL, + RDMA_MATRIX_INT_MTX_BT601_to_RGB); + } else { + rdma_update_bits(comp, DISP_REG_RDMA_SIZE_CON_0, + RDMA_MATRIX_ENABLE, 0); + } + + writel_relaxed(addr, comp->regs + DISP_RDMA_MEM_START_ADDR); + writel_relaxed(pitch, comp->regs + DISP_RDMA_MEM_SRC_PITCH); + writel(RDMA_MEM_GMC, comp->regs + DISP_RDMA_MEM_GMC_SETTING_0); + rdma_update_bits(comp, DISP_REG_RDMA_GLOBAL_CON, + RDMA_MODE_MEMORY, RDMA_MODE_MEMORY); +} + static const struct mtk_ddp_comp_funcs mtk_disp_rdma_funcs = { .config = mtk_rdma_config, .start = mtk_rdma_start, .stop = mtk_rdma_stop, .enable_vblank = mtk_rdma_enable_vblank, .disable_vblank = mtk_rdma_disable_vblank, + .layer_nr = mtk_rdma_layer_nr, + .layer_config = mtk_rdma_layer_config, }; static int mtk_disp_rdma_bind(struct device *dev, struct device *master, diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c index 2d6aa150a9ff..0b976dfd04df 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c @@ -45,7 +45,8 @@ struct mtk_drm_crtc { bool pending_needs_vblank; struct drm_pending_vblank_event *event; - struct drm_plane planes[OVL_LAYER_NR]; + struct drm_plane *planes; + unsigned int layer_nr; bool pending_planes; void __iomem *config_regs; @@ -171,9 +172,9 @@ static void mtk_drm_crtc_mode_set_nofb(struct drm_crtc *crtc) static int mtk_drm_crtc_enable_vblank(struct drm_crtc *crtc) { struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc); - struct mtk_ddp_comp *ovl = mtk_crtc->ddp_comp[0]; + struct mtk_ddp_comp *comp = mtk_crtc->ddp_comp[0]; - mtk_ddp_comp_enable_vblank(ovl, &mtk_crtc->base); + mtk_ddp_comp_enable_vblank(comp, &mtk_crtc->base); return 0; } @@ -181,9 +182,9 @@ static int mtk_drm_crtc_enable_vblank(struct drm_crtc *crtc) static void mtk_drm_crtc_disable_vblank(struct drm_crtc *crtc) { struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc); - struct mtk_ddp_comp *ovl = mtk_crtc->ddp_comp[0]; + struct mtk_ddp_comp *comp = mtk_crtc->ddp_comp[0]; - mtk_ddp_comp_disable_vblank(ovl); + mtk_ddp_comp_disable_vblank(comp); } static int mtk_crtc_ddp_clk_enable(struct mtk_drm_crtc *mtk_crtc) @@ -286,7 +287,7 @@ static int mtk_crtc_ddp_hw_init(struct mtk_drm_crtc *mtk_crtc) } /* Initially configure all planes */ - for (i = 0; i < OVL_LAYER_NR; i++) { + for (i = 0; i < mtk_crtc->layer_nr; i++) { struct drm_plane *plane = &mtk_crtc->planes[i]; struct mtk_plane_state *plane_state; @@ -334,7 +335,7 @@ static void mtk_crtc_ddp_config(struct drm_crtc *crtc) { struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc); struct mtk_crtc_state *state = to_mtk_crtc_state(mtk_crtc->base.state); - struct mtk_ddp_comp *ovl = mtk_crtc->ddp_comp[0]; + struct mtk_ddp_comp *comp = mtk_crtc->ddp_comp[0]; unsigned int i; /* @@ -343,7 +344,7 @@ static void mtk_crtc_ddp_config(struct drm_crtc *crtc) * queue update module registers on vblank. */ if (state->pending_config) { - mtk_ddp_comp_config(ovl, state->pending_width, + mtk_ddp_comp_config(comp, state->pending_width, state->pending_height, state->pending_vrefresh, 0); @@ -351,14 +352,14 @@ static void mtk_crtc_ddp_config(struct drm_crtc *crtc) } if (mtk_crtc->pending_planes) { - for (i = 0; i < OVL_LAYER_NR; i++) { + for (i = 0; i < mtk_crtc->layer_nr; i++) { struct drm_plane *plane = &mtk_crtc->planes[i]; struct mtk_plane_state *plane_state; plane_state = to_mtk_plane_state(plane->state); if (plane_state->pending.config) { - mtk_ddp_comp_layer_config(ovl, i, plane_state); + mtk_ddp_comp_layer_config(comp, i, plane_state); plane_state->pending.config = false; } } @@ -370,12 +371,12 @@ static void mtk_drm_crtc_atomic_enable(struct drm_crtc *crtc, struct drm_crtc_state *old_state) { struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc); - struct mtk_ddp_comp *ovl = mtk_crtc->ddp_comp[0]; + struct mtk_ddp_comp *comp = mtk_crtc->ddp_comp[0]; int ret; DRM_DEBUG_DRIVER("%s %d\n", __func__, crtc->base.id); - ret = mtk_smi_larb_get(ovl->larb_dev); + ret = mtk_smi_larb_get(comp->larb_dev); if (ret) { DRM_ERROR("Failed to get larb: %d\n", ret); return; @@ -383,7 +384,7 @@ static void mtk_drm_crtc_atomic_enable(struct drm_crtc *crtc, ret = mtk_crtc_ddp_hw_init(mtk_crtc); if (ret) { - mtk_smi_larb_put(ovl->larb_dev); + mtk_smi_larb_put(comp->larb_dev); return; } @@ -395,7 +396,7 @@ static void mtk_drm_crtc_atomic_disable(struct drm_crtc *crtc, struct drm_crtc_state *old_state) { struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc); - struct mtk_ddp_comp *ovl = mtk_crtc->ddp_comp[0]; + struct mtk_ddp_comp *comp = mtk_crtc->ddp_comp[0]; int i; DRM_DEBUG_DRIVER("%s %d\n", __func__, crtc->base.id); @@ -403,7 +404,7 @@ static void mtk_drm_crtc_atomic_disable(struct drm_crtc *crtc, return; /* Set all pending plane state to disabled */ - for (i = 0; i < OVL_LAYER_NR; i++) { + for (i = 0; i < mtk_crtc->layer_nr; i++) { struct drm_plane *plane = &mtk_crtc->planes[i]; struct mtk_plane_state *plane_state; @@ -418,7 +419,7 @@ static void mtk_drm_crtc_atomic_disable(struct drm_crtc *crtc, drm_crtc_vblank_off(crtc); mtk_crtc_ddp_hw_fini(mtk_crtc); - mtk_smi_larb_put(ovl->larb_dev); + mtk_smi_larb_put(comp->larb_dev); mtk_crtc->enabled = false; } @@ -450,7 +451,7 @@ static void mtk_drm_crtc_atomic_flush(struct drm_crtc *crtc, if (mtk_crtc->event) mtk_crtc->pending_needs_vblank = true; - for (i = 0; i < OVL_LAYER_NR; i++) { + for (i = 0; i < mtk_crtc->layer_nr; i++) { struct drm_plane *plane = &mtk_crtc->planes[i]; struct mtk_plane_state *plane_state; @@ -516,7 +517,7 @@ err_cleanup_crtc: return ret; } -void mtk_crtc_ddp_irq(struct drm_crtc *crtc, struct mtk_ddp_comp *ovl) +void mtk_crtc_ddp_irq(struct drm_crtc *crtc, struct mtk_ddp_comp *comp) { struct mtk_drm_crtc *mtk_crtc = to_mtk_crtc(crtc); struct mtk_drm_private *priv = crtc->dev->dev_private; @@ -598,7 +599,12 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev, mtk_crtc->ddp_comp[i] = comp; } - for (zpos = 0; zpos < OVL_LAYER_NR; zpos++) { + mtk_crtc->layer_nr = mtk_ddp_comp_layer_nr(mtk_crtc->ddp_comp[0]); + mtk_crtc->planes = devm_kzalloc(dev, mtk_crtc->layer_nr * + sizeof(struct drm_plane), + GFP_KERNEL); + + for (zpos = 0; zpos < mtk_crtc->layer_nr; zpos++) { type = (zpos == 0) ? DRM_PLANE_TYPE_PRIMARY : (zpos == 1) ? DRM_PLANE_TYPE_CURSOR : DRM_PLANE_TYPE_OVERLAY; @@ -609,7 +615,8 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev, } ret = mtk_drm_crtc_init(drm_dev, mtk_crtc, &mtk_crtc->planes[0], - &mtk_crtc->planes[1], pipe); + mtk_crtc->layer_nr > 1 ? &mtk_crtc->planes[1] : + NULL, pipe); if (ret < 0) goto unprepare; drm_mode_crtc_set_gamma_size(&mtk_crtc->base, MTK_LUT_SIZE); diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.h b/drivers/gpu/drm/mediatek/mtk_drm_crtc.h index 9d9410c67ae9..091adb2087eb 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.h +++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.h @@ -18,13 +18,12 @@ #include "mtk_drm_ddp_comp.h" #include "mtk_drm_plane.h" -#define OVL_LAYER_NR 4 #define MTK_LUT_SIZE 512 #define MTK_MAX_BPC 10 #define MTK_MIN_BPC 3 void mtk_drm_crtc_commit(struct drm_crtc *crtc); -void mtk_crtc_ddp_irq(struct drm_crtc *crtc, struct mtk_ddp_comp *ovl); +void mtk_crtc_ddp_irq(struct drm_crtc *crtc, struct mtk_ddp_comp *comp); int mtk_drm_crtc_create(struct drm_device *drm_dev, const enum mtk_ddp_comp_id *path, unsigned int path_len); diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c index 87e4191c250e..546b3e3b300b 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c @@ -106,6 +106,8 @@ #define OVL1_MOUT_EN_COLOR1 0x1 #define GAMMA_MOUT_EN_RDMA1 0x1 #define RDMA0_SOUT_DPI0 0x2 +#define RDMA0_SOUT_DPI1 0x3 +#define RDMA0_SOUT_DSI1 0x1 #define RDMA0_SOUT_DSI2 0x4 #define RDMA0_SOUT_DSI3 0x5 #define RDMA1_SOUT_DPI0 0x2 @@ -122,6 +124,8 @@ #define DPI0_SEL_IN_RDMA2 0x3 #define DPI1_SEL_IN_RDMA1 (0x1 << 8) #define DPI1_SEL_IN_RDMA2 (0x3 << 8) +#define DSI0_SEL_IN_RDMA1 0x1 +#define DSI0_SEL_IN_RDMA2 0x4 #define DSI1_SEL_IN_RDMA1 0x1 #define DSI1_SEL_IN_RDMA2 0x4 #define DSI2_SEL_IN_RDMA1 (0x1 << 16) @@ -224,6 +228,12 @@ static unsigned int mtk_ddp_mout_en(enum mtk_ddp_comp_id cur, } else if (cur == DDP_COMPONENT_RDMA0 && next == DDP_COMPONENT_DPI0) { *addr = DISP_REG_CONFIG_DISP_RDMA0_SOUT_EN; value = RDMA0_SOUT_DPI0; + } else if (cur == DDP_COMPONENT_RDMA0 && next == DDP_COMPONENT_DPI1) { + *addr = DISP_REG_CONFIG_DISP_RDMA0_SOUT_EN; + value = RDMA0_SOUT_DPI1; + } else if (cur == DDP_COMPONENT_RDMA0 && next == DDP_COMPONENT_DSI1) { + *addr = DISP_REG_CONFIG_DISP_RDMA0_SOUT_EN; + value = RDMA0_SOUT_DSI1; } else if (cur == DDP_COMPONENT_RDMA0 && next == DDP_COMPONENT_DSI2) { *addr = DISP_REG_CONFIG_DISP_RDMA0_SOUT_EN; value = RDMA0_SOUT_DSI2; @@ -282,6 +292,9 @@ static unsigned int mtk_ddp_sel_in(enum mtk_ddp_comp_id cur, } else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DPI1) { *addr = DISP_REG_CONFIG_DPI_SEL_IN; value = DPI1_SEL_IN_RDMA1; + } else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DSI0) { + *addr = DISP_REG_CONFIG_DSIE_SEL_IN; + value = DSI0_SEL_IN_RDMA1; } else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DSI1) { *addr = DISP_REG_CONFIG_DSIO_SEL_IN; value = DSI1_SEL_IN_RDMA1; @@ -297,8 +310,11 @@ static unsigned int mtk_ddp_sel_in(enum mtk_ddp_comp_id cur, } else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DPI1) { *addr = DISP_REG_CONFIG_DPI_SEL_IN; value = DPI1_SEL_IN_RDMA2; - } else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DSI1) { + } else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DSI0) { *addr = DISP_REG_CONFIG_DSIE_SEL_IN; + value = DSI0_SEL_IN_RDMA2; + } else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DSI1) { + *addr = DISP_REG_CONFIG_DSIO_SEL_IN; value = DSI1_SEL_IN_RDMA2; } else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DSI2) { *addr = DISP_REG_CONFIG_DSIE_SEL_IN; diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h index 7413ffeb3c9d..8399229e6ad2 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h +++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h @@ -78,6 +78,7 @@ struct mtk_ddp_comp_funcs { void (*stop)(struct mtk_ddp_comp *comp); void (*enable_vblank)(struct mtk_ddp_comp *comp, struct drm_crtc *crtc); void (*disable_vblank)(struct mtk_ddp_comp *comp); + unsigned int (*layer_nr)(struct mtk_ddp_comp *comp); void (*layer_on)(struct mtk_ddp_comp *comp, unsigned int idx); void (*layer_off)(struct mtk_ddp_comp *comp, unsigned int idx); void (*layer_config)(struct mtk_ddp_comp *comp, unsigned int idx, @@ -128,6 +129,14 @@ static inline void mtk_ddp_comp_disable_vblank(struct mtk_ddp_comp *comp) comp->funcs->disable_vblank(comp); } +static inline unsigned int mtk_ddp_comp_layer_nr(struct mtk_ddp_comp *comp) +{ + if (comp->funcs && comp->funcs->layer_nr) + return comp->funcs->layer_nr(comp); + + return 0; +} + static inline void mtk_ddp_comp_layer_on(struct mtk_ddp_comp *comp, unsigned int idx) { diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index 39721119713b..47ec604289b7 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -381,7 +381,7 @@ static int mtk_drm_bind(struct device *dev) err_deinit: mtk_drm_kms_deinit(drm); err_free: - drm_dev_unref(drm); + drm_dev_put(drm); return ret; } @@ -390,7 +390,7 @@ static void mtk_drm_unbind(struct device *dev) struct mtk_drm_private *private = dev_get_drvdata(dev); drm_dev_unregister(private->drm); - drm_dev_unref(private->drm); + drm_dev_put(private->drm); private->drm = NULL; } @@ -564,7 +564,7 @@ static int mtk_drm_remove(struct platform_device *pdev) drm_dev_unregister(drm); mtk_drm_kms_deinit(drm); - drm_dev_unref(drm); + drm_dev_put(drm); component_master_del(&pdev->dev, &mtk_drm_ops); pm_runtime_disable(&pdev->dev); @@ -580,29 +580,24 @@ static int mtk_drm_sys_suspend(struct device *dev) { struct mtk_drm_private *private = dev_get_drvdata(dev); struct drm_device *drm = private->drm; + int ret; - drm_kms_helper_poll_disable(drm); - - private->suspend_state = drm_atomic_helper_suspend(drm); - if (IS_ERR(private->suspend_state)) { - drm_kms_helper_poll_enable(drm); - return PTR_ERR(private->suspend_state); - } - + ret = drm_mode_config_helper_suspend(drm); DRM_DEBUG_DRIVER("mtk_drm_sys_suspend\n"); - return 0; + + return ret; } static int mtk_drm_sys_resume(struct device *dev) { struct mtk_drm_private *private = dev_get_drvdata(dev); struct drm_device *drm = private->drm; + int ret; - drm_atomic_helper_resume(drm, private->suspend_state); - drm_kms_helper_poll_enable(drm); - + ret = drm_mode_config_helper_resume(drm); DRM_DEBUG_DRIVER("mtk_drm_sys_resume\n"); - return 0; + + return ret; } #endif diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index 8412119bd940..5691dfa1db6f 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -1123,17 +1123,21 @@ nv50_mstm_enable(struct nv50_mstm *mstm, u8 dpcd, int state) int ret; if (dpcd >= 0x12) { - ret = drm_dp_dpcd_readb(mstm->mgr.aux, DP_MSTM_CTRL, &dpcd); + /* Even if we're enabling MST, start with disabling the + * branching unit to clear any sink-side MST topology state + * that wasn't set by us + */ + ret = drm_dp_dpcd_writeb(mstm->mgr.aux, DP_MSTM_CTRL, 0); if (ret < 0) return ret; - dpcd &= ~DP_MST_EN; - if (state) - dpcd |= DP_MST_EN; - - ret = drm_dp_dpcd_writeb(mstm->mgr.aux, DP_MSTM_CTRL, dpcd); - if (ret < 0) - return ret; + if (state) { + /* Now, start initializing */ + ret = drm_dp_dpcd_writeb(mstm->mgr.aux, DP_MSTM_CTRL, + DP_MST_EN); + if (ret < 0) + return ret; + } } return nvif_mthd(disp, 0, &args, sizeof(args)); @@ -1142,31 +1146,58 @@ nv50_mstm_enable(struct nv50_mstm *mstm, u8 dpcd, int state) int nv50_mstm_detect(struct nv50_mstm *mstm, u8 dpcd[8], int allow) { - int ret, state = 0; + struct drm_dp_aux *aux; + int ret; + bool old_state, new_state; + u8 mstm_ctrl; if (!mstm) return 0; - if (dpcd[0] >= 0x12) { - ret = drm_dp_dpcd_readb(mstm->mgr.aux, DP_MSTM_CAP, &dpcd[1]); + mutex_lock(&mstm->mgr.lock); + + old_state = mstm->mgr.mst_state; + new_state = old_state; + aux = mstm->mgr.aux; + + if (old_state) { + /* Just check that the MST hub is still as we expect it */ + ret = drm_dp_dpcd_readb(aux, DP_MSTM_CTRL, &mstm_ctrl); + if (ret < 0 || !(mstm_ctrl & DP_MST_EN)) { + DRM_DEBUG_KMS("Hub gone, disabling MST topology\n"); + new_state = false; + } + } else if (dpcd[0] >= 0x12) { + ret = drm_dp_dpcd_readb(aux, DP_MSTM_CAP, &dpcd[1]); if (ret < 0) - return ret; + goto probe_error; if (!(dpcd[1] & DP_MST_CAP)) dpcd[0] = 0x11; else - state = allow; + new_state = allow; + } + + if (new_state == old_state) { + mutex_unlock(&mstm->mgr.lock); + return new_state; } - ret = nv50_mstm_enable(mstm, dpcd[0], state); + ret = nv50_mstm_enable(mstm, dpcd[0], new_state); if (ret) - return ret; + goto probe_error; + + mutex_unlock(&mstm->mgr.lock); - ret = drm_dp_mst_topology_mgr_set_mst(&mstm->mgr, state); + ret = drm_dp_mst_topology_mgr_set_mst(&mstm->mgr, new_state); if (ret) return nv50_mstm_enable(mstm, dpcd[0], 0); - return mstm->mgr.mst_state; + return new_state; + +probe_error: + mutex_unlock(&mstm->mgr.lock); + return ret; } static void @@ -2074,7 +2105,7 @@ nv50_disp_atomic_state_alloc(struct drm_device *dev) static const struct drm_mode_config_funcs nv50_disp_func = { .fb_create = nouveau_user_framebuffer_create, - .output_poll_changed = drm_fb_helper_output_poll_changed, + .output_poll_changed = nouveau_fbcon_output_poll_changed, .atomic_check = nv50_disp_atomic_check, .atomic_commit = nv50_disp_atomic_commit, .atomic_state_alloc = nv50_disp_atomic_state_alloc, diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c index 51932c72334e..247f72cc4d10 100644 --- a/drivers/gpu/drm/nouveau/nouveau_connector.c +++ b/drivers/gpu/drm/nouveau/nouveau_connector.c @@ -409,59 +409,45 @@ static struct nouveau_encoder * nouveau_connector_ddc_detect(struct drm_connector *connector) { struct drm_device *dev = connector->dev; - struct nouveau_connector *nv_connector = nouveau_connector(connector); - struct nouveau_drm *drm = nouveau_drm(dev); - struct nvkm_gpio *gpio = nvxx_gpio(&drm->client.device); - struct nouveau_encoder *nv_encoder = NULL; + struct nouveau_encoder *nv_encoder = NULL, *found = NULL; struct drm_encoder *encoder; - int i, panel = -ENODEV; - - /* eDP panels need powering on by us (if the VBIOS doesn't default it - * to on) before doing any AUX channel transactions. LVDS panel power - * is handled by the SOR itself, and not required for LVDS DDC. - */ - if (nv_connector->type == DCB_CONNECTOR_eDP) { - panel = nvkm_gpio_get(gpio, 0, DCB_GPIO_PANEL_POWER, 0xff); - if (panel == 0) { - nvkm_gpio_set(gpio, 0, DCB_GPIO_PANEL_POWER, 0xff, 1); - msleep(300); - } - } + int i, ret; + bool switcheroo_ddc = false; drm_connector_for_each_possible_encoder(connector, encoder, i) { nv_encoder = nouveau_encoder(encoder); - if (nv_encoder->dcb->type == DCB_OUTPUT_DP) { - int ret = nouveau_dp_detect(nv_encoder); + switch (nv_encoder->dcb->type) { + case DCB_OUTPUT_DP: + ret = nouveau_dp_detect(nv_encoder); if (ret == NOUVEAU_DP_MST) return NULL; - if (ret == NOUVEAU_DP_SST) - break; - } else - if ((vga_switcheroo_handler_flags() & - VGA_SWITCHEROO_CAN_SWITCH_DDC) && - nv_encoder->dcb->type == DCB_OUTPUT_LVDS && - nv_encoder->i2c) { - int ret; - vga_switcheroo_lock_ddc(dev->pdev); - ret = nvkm_probe_i2c(nv_encoder->i2c, 0x50); - vga_switcheroo_unlock_ddc(dev->pdev); - if (ret) + else if (ret == NOUVEAU_DP_SST) + found = nv_encoder; + + break; + case DCB_OUTPUT_LVDS: + switcheroo_ddc = !!(vga_switcheroo_handler_flags() & + VGA_SWITCHEROO_CAN_SWITCH_DDC); + /* fall-through */ + default: + if (!nv_encoder->i2c) break; - } else - if (nv_encoder->i2c) { + + if (switcheroo_ddc) + vga_switcheroo_lock_ddc(dev->pdev); if (nvkm_probe_i2c(nv_encoder->i2c, 0x50)) - break; + found = nv_encoder; + if (switcheroo_ddc) + vga_switcheroo_unlock_ddc(dev->pdev); + + break; } + if (found) + break; } - /* eDP panel not detected, restore panel power GPIO to previous - * state to avoid confusing the SOR for other output types. - */ - if (!nv_encoder && panel == 0) - nvkm_gpio_set(gpio, 0, DCB_GPIO_PANEL_POWER, 0xff, panel); - - return nv_encoder; + return found; } static struct nouveau_encoder * @@ -555,12 +541,16 @@ nouveau_connector_detect(struct drm_connector *connector, bool force) nv_connector->edid = NULL; } - /* Outputs are only polled while runtime active, so acquiring a - * runtime PM ref here is unnecessary (and would deadlock upon - * runtime suspend because it waits for polling to finish). + /* Outputs are only polled while runtime active, so resuming the + * device here is unnecessary (and would deadlock upon runtime suspend + * because it waits for polling to finish). We do however, want to + * prevent the autosuspend timer from elapsing during this operation + * if possible. */ - if (!drm_kms_helper_is_poll_worker()) { - ret = pm_runtime_get_sync(connector->dev->dev); + if (drm_kms_helper_is_poll_worker()) { + pm_runtime_get_noresume(dev->dev); + } else { + ret = pm_runtime_get_sync(dev->dev); if (ret < 0 && ret != -EACCES) return conn_status; } @@ -638,10 +628,8 @@ detect_analog: out: - if (!drm_kms_helper_is_poll_worker()) { - pm_runtime_mark_last_busy(connector->dev->dev); - pm_runtime_put_autosuspend(connector->dev->dev); - } + pm_runtime_mark_last_busy(dev->dev); + pm_runtime_put_autosuspend(dev->dev); return conn_status; } @@ -1105,6 +1093,26 @@ nouveau_connector_hotplug(struct nvif_notify *notify) const struct nvif_notify_conn_rep_v0 *rep = notify->data; const char *name = connector->name; struct nouveau_encoder *nv_encoder; + int ret; + + ret = pm_runtime_get(drm->dev->dev); + if (ret == 0) { + /* We can't block here if there's a pending PM request + * running, as we'll deadlock nouveau_display_fini() when it + * calls nvif_put() on our nvif_notify struct. So, simply + * defer the hotplug event until the device finishes resuming + */ + NV_DEBUG(drm, "Deferring HPD on %s until runtime resume\n", + name); + schedule_work(&drm->hpd_work); + + pm_runtime_put_noidle(drm->dev->dev); + return NVIF_NOTIFY_KEEP; + } else if (ret != 1 && ret != -EACCES) { + NV_WARN(drm, "HPD on %s dropped due to RPM failure: %d\n", + name, ret); + return NVIF_NOTIFY_DROP; + } if (rep->mask & NVIF_NOTIFY_CONN_V0_IRQ) { NV_DEBUG(drm, "service %s\n", name); @@ -1122,6 +1130,8 @@ nouveau_connector_hotplug(struct nvif_notify *notify) drm_helper_hpd_irq_event(connector->dev); } + pm_runtime_mark_last_busy(drm->dev->dev); + pm_runtime_put_autosuspend(drm->dev->dev); return NVIF_NOTIFY_KEEP; } diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c index 139368b31916..540c0cbbfcee 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.c +++ b/drivers/gpu/drm/nouveau/nouveau_display.c @@ -293,7 +293,7 @@ nouveau_user_framebuffer_create(struct drm_device *dev, static const struct drm_mode_config_funcs nouveau_mode_config_funcs = { .fb_create = nouveau_user_framebuffer_create, - .output_poll_changed = drm_fb_helper_output_poll_changed, + .output_poll_changed = nouveau_fbcon_output_poll_changed, }; @@ -355,8 +355,6 @@ nouveau_display_hpd_work(struct work_struct *work) pm_runtime_get_sync(drm->dev->dev); drm_helper_hpd_irq_event(drm->dev); - /* enable polling for external displays */ - drm_kms_helper_poll_enable(drm->dev); pm_runtime_mark_last_busy(drm->dev->dev); pm_runtime_put_sync(drm->dev->dev); @@ -379,15 +377,29 @@ nouveau_display_acpi_ntfy(struct notifier_block *nb, unsigned long val, { struct nouveau_drm *drm = container_of(nb, typeof(*drm), acpi_nb); struct acpi_bus_event *info = data; + int ret; if (!strcmp(info->device_class, ACPI_VIDEO_CLASS)) { if (info->type == ACPI_VIDEO_NOTIFY_PROBE) { - /* - * This may be the only indication we receive of a - * connector hotplug on a runtime suspended GPU, - * schedule hpd_work to check. - */ - schedule_work(&drm->hpd_work); + ret = pm_runtime_get(drm->dev->dev); + if (ret == 1 || ret == -EACCES) { + /* If the GPU is already awake, or in a state + * where we can't wake it up, it can handle + * it's own hotplug events. + */ + pm_runtime_put_autosuspend(drm->dev->dev); + } else if (ret == 0) { + /* This may be the only indication we receive + * of a connector hotplug on a runtime + * suspended GPU, schedule hpd_work to check. + */ + NV_DEBUG(drm, "ACPI requested connector reprobe\n"); + schedule_work(&drm->hpd_work); + pm_runtime_put_noidle(drm->dev->dev); + } else { + NV_WARN(drm, "Dropped ACPI reprobe event due to RPM error: %d\n", + ret); + } /* acpi-video should not generate keypresses for this */ return NOTIFY_BAD; @@ -411,6 +423,11 @@ nouveau_display_init(struct drm_device *dev) if (ret) return ret; + /* enable connector detection and polling for connectors without HPD + * support + */ + drm_kms_helper_poll_enable(dev); + /* enable hotplug interrupts */ drm_connector_list_iter_begin(dev, &conn_iter); nouveau_for_each_non_mst_connector_iter(connector, &conn_iter) { @@ -425,7 +442,7 @@ nouveau_display_init(struct drm_device *dev) } void -nouveau_display_fini(struct drm_device *dev, bool suspend) +nouveau_display_fini(struct drm_device *dev, bool suspend, bool runtime) { struct nouveau_display *disp = nouveau_display(dev); struct nouveau_drm *drm = nouveau_drm(dev); @@ -450,6 +467,9 @@ nouveau_display_fini(struct drm_device *dev, bool suspend) } drm_connector_list_iter_end(&conn_iter); + if (!runtime) + cancel_work_sync(&drm->hpd_work); + drm_kms_helper_poll_disable(dev); disp->fini(dev); } @@ -618,11 +638,11 @@ nouveau_display_suspend(struct drm_device *dev, bool runtime) } } - nouveau_display_fini(dev, true); + nouveau_display_fini(dev, true, runtime); return 0; } - nouveau_display_fini(dev, true); + nouveau_display_fini(dev, true, runtime); list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { struct nouveau_framebuffer *nouveau_fb; diff --git a/drivers/gpu/drm/nouveau/nouveau_display.h b/drivers/gpu/drm/nouveau/nouveau_display.h index 54aa7c3fa42d..ff92b54ce448 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.h +++ b/drivers/gpu/drm/nouveau/nouveau_display.h @@ -62,7 +62,7 @@ nouveau_display(struct drm_device *dev) int nouveau_display_create(struct drm_device *dev); void nouveau_display_destroy(struct drm_device *dev); int nouveau_display_init(struct drm_device *dev); -void nouveau_display_fini(struct drm_device *dev, bool suspend); +void nouveau_display_fini(struct drm_device *dev, bool suspend, bool runtime); int nouveau_display_suspend(struct drm_device *dev, bool runtime); void nouveau_display_resume(struct drm_device *dev, bool runtime); int nouveau_display_vblank_enable(struct drm_device *, unsigned int); diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index c7ec86d6c3c9..74d2283f2c28 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -230,7 +230,7 @@ nouveau_cli_init(struct nouveau_drm *drm, const char *sname, mutex_unlock(&drm->master.lock); } if (ret) { - NV_ERROR(drm, "Client allocation failed: %d\n", ret); + NV_PRINTK(err, cli, "Client allocation failed: %d\n", ret); goto done; } @@ -240,37 +240,37 @@ nouveau_cli_init(struct nouveau_drm *drm, const char *sname, }, sizeof(struct nv_device_v0), &cli->device); if (ret) { - NV_ERROR(drm, "Device allocation failed: %d\n", ret); + NV_PRINTK(err, cli, "Device allocation failed: %d\n", ret); goto done; } ret = nvif_mclass(&cli->device.object, mmus); if (ret < 0) { - NV_ERROR(drm, "No supported MMU class\n"); + NV_PRINTK(err, cli, "No supported MMU class\n"); goto done; } ret = nvif_mmu_init(&cli->device.object, mmus[ret].oclass, &cli->mmu); if (ret) { - NV_ERROR(drm, "MMU allocation failed: %d\n", ret); + NV_PRINTK(err, cli, "MMU allocation failed: %d\n", ret); goto done; } ret = nvif_mclass(&cli->mmu.object, vmms); if (ret < 0) { - NV_ERROR(drm, "No supported VMM class\n"); + NV_PRINTK(err, cli, "No supported VMM class\n"); goto done; } ret = nouveau_vmm_init(cli, vmms[ret].oclass, &cli->vmm); if (ret) { - NV_ERROR(drm, "VMM allocation failed: %d\n", ret); + NV_PRINTK(err, cli, "VMM allocation failed: %d\n", ret); goto done; } ret = nvif_mclass(&cli->mmu.object, mems); if (ret < 0) { - NV_ERROR(drm, "No supported MEM class\n"); + NV_PRINTK(err, cli, "No supported MEM class\n"); goto done; } @@ -592,10 +592,8 @@ nouveau_drm_load(struct drm_device *dev, unsigned long flags) pm_runtime_allow(dev->dev); pm_runtime_mark_last_busy(dev->dev); pm_runtime_put(dev->dev); - } else { - /* enable polling for external displays */ - drm_kms_helper_poll_enable(dev); } + return 0; fail_dispinit: @@ -629,7 +627,7 @@ nouveau_drm_unload(struct drm_device *dev) nouveau_debugfs_fini(drm); if (dev->mode_config.num_crtc) - nouveau_display_fini(dev, false); + nouveau_display_fini(dev, false, false); nouveau_display_destroy(dev); nouveau_bios_takedown(dev); @@ -835,7 +833,6 @@ nouveau_pmops_runtime_suspend(struct device *dev) return -EBUSY; } - drm_kms_helper_poll_disable(drm_dev); nouveau_switcheroo_optimus_dsm(); ret = nouveau_do_suspend(drm_dev, true); pci_save_state(pdev); diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c index 844498c4267c..0f64c0a1d4b3 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c +++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c @@ -466,6 +466,7 @@ nouveau_fbcon_set_suspend_work(struct work_struct *work) console_unlock(); if (state == FBINFO_STATE_RUNNING) { + nouveau_fbcon_hotplug_resume(drm->fbcon); pm_runtime_mark_last_busy(drm->dev->dev); pm_runtime_put_sync(drm->dev->dev); } @@ -487,6 +488,61 @@ nouveau_fbcon_set_suspend(struct drm_device *dev, int state) schedule_work(&drm->fbcon_work); } +void +nouveau_fbcon_output_poll_changed(struct drm_device *dev) +{ + struct nouveau_drm *drm = nouveau_drm(dev); + struct nouveau_fbdev *fbcon = drm->fbcon; + int ret; + + if (!fbcon) + return; + + mutex_lock(&fbcon->hotplug_lock); + + ret = pm_runtime_get(dev->dev); + if (ret == 1 || ret == -EACCES) { + drm_fb_helper_hotplug_event(&fbcon->helper); + + pm_runtime_mark_last_busy(dev->dev); + pm_runtime_put_autosuspend(dev->dev); + } else if (ret == 0) { + /* If the GPU was already in the process of suspending before + * this event happened, then we can't block here as we'll + * deadlock the runtime pmops since they wait for us to + * finish. So, just defer this event for when we runtime + * resume again. It will be handled by fbcon_work. + */ + NV_DEBUG(drm, "fbcon HPD event deferred until runtime resume\n"); + fbcon->hotplug_waiting = true; + pm_runtime_put_noidle(drm->dev->dev); + } else { + DRM_WARN("fbcon HPD event lost due to RPM failure: %d\n", + ret); + } + + mutex_unlock(&fbcon->hotplug_lock); +} + +void +nouveau_fbcon_hotplug_resume(struct nouveau_fbdev *fbcon) +{ + struct nouveau_drm *drm; + + if (!fbcon) + return; + drm = nouveau_drm(fbcon->helper.dev); + + mutex_lock(&fbcon->hotplug_lock); + if (fbcon->hotplug_waiting) { + fbcon->hotplug_waiting = false; + + NV_DEBUG(drm, "Handling deferred fbcon HPD events\n"); + drm_fb_helper_hotplug_event(&fbcon->helper); + } + mutex_unlock(&fbcon->hotplug_lock); +} + int nouveau_fbcon_init(struct drm_device *dev) { @@ -505,6 +561,7 @@ nouveau_fbcon_init(struct drm_device *dev) drm->fbcon = fbcon; INIT_WORK(&drm->fbcon_work, nouveau_fbcon_set_suspend_work); + mutex_init(&fbcon->hotplug_lock); drm_fb_helper_prepare(dev, &fbcon->helper, &nouveau_fbcon_helper_funcs); diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.h b/drivers/gpu/drm/nouveau/nouveau_fbcon.h index a6f192ea3fa6..db9d52047ef8 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fbcon.h +++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.h @@ -41,6 +41,9 @@ struct nouveau_fbdev { struct nvif_object gdi; struct nvif_object blit; struct nvif_object twod; + + struct mutex hotplug_lock; + bool hotplug_waiting; }; void nouveau_fbcon_restore(void); @@ -68,6 +71,8 @@ void nouveau_fbcon_set_suspend(struct drm_device *dev, int state); void nouveau_fbcon_accel_save_disable(struct drm_device *dev); void nouveau_fbcon_accel_restore(struct drm_device *dev); +void nouveau_fbcon_output_poll_changed(struct drm_device *dev); +void nouveau_fbcon_hotplug_resume(struct nouveau_fbdev *fbcon); extern int nouveau_nofbaccel; #endif /* __NV50_FBCON_H__ */ diff --git a/drivers/gpu/drm/nouveau/nouveau_vga.c b/drivers/gpu/drm/nouveau/nouveau_vga.c index 3da5a4305aa4..8f1ce4833230 100644 --- a/drivers/gpu/drm/nouveau/nouveau_vga.c +++ b/drivers/gpu/drm/nouveau/nouveau_vga.c @@ -46,12 +46,10 @@ nouveau_switcheroo_set_state(struct pci_dev *pdev, pr_err("VGA switcheroo: switched nouveau on\n"); dev->switch_power_state = DRM_SWITCH_POWER_CHANGING; nouveau_pmops_resume(&pdev->dev); - drm_kms_helper_poll_enable(dev); dev->switch_power_state = DRM_SWITCH_POWER_ON; } else { pr_err("VGA switcheroo: switched nouveau off\n"); dev->switch_power_state = DRM_SWITCH_POWER_CHANGING; - drm_kms_helper_poll_disable(dev); nouveau_switcheroo_optimus_dsm(); nouveau_pmops_suspend(&pdev->dev); dev->switch_power_state = DRM_SWITCH_POWER_OFF; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c index 32fa94a9773f..cbd33e87b799 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/base.c @@ -275,6 +275,7 @@ nvkm_disp_oneinit(struct nvkm_engine *engine) struct nvkm_outp *outp, *outt, *pair; struct nvkm_conn *conn; struct nvkm_head *head; + struct nvkm_ior *ior; struct nvbios_connE connE; struct dcb_output dcbE; u8 hpd = 0, ver, hdr; @@ -399,6 +400,19 @@ nvkm_disp_oneinit(struct nvkm_engine *engine) return ret; } + /* Enforce identity-mapped SOR assignment for panels, which have + * certain bits (ie. backlight controls) wired to a specific SOR. + */ + list_for_each_entry(outp, &disp->outp, head) { + if (outp->conn->info.type == DCB_CONNECTOR_LVDS || + outp->conn->info.type == DCB_CONNECTOR_eDP) { + ior = nvkm_ior_find(disp, SOR, ffs(outp->info.or) - 1); + if (!WARN_ON(!ior)) + ior->identity = true; + outp->identity = true; + } + } + i = 0; list_for_each_entry(head, &disp->head, head) i = max(i, head->id + 1); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c index 7c5bed29ffef..5f301e632599 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dp.c @@ -28,6 +28,7 @@ #include <subdev/bios.h> #include <subdev/bios/init.h> +#include <subdev/gpio.h> #include <subdev/i2c.h> #include <nvif/event.h> @@ -412,14 +413,10 @@ nvkm_dp_train(struct nvkm_dp *dp, u32 dataKBps) } static void -nvkm_dp_release(struct nvkm_outp *outp, struct nvkm_ior *ior) +nvkm_dp_disable(struct nvkm_outp *outp, struct nvkm_ior *ior) { struct nvkm_dp *dp = nvkm_dp(outp); - /* Prevent link from being retrained if sink sends an IRQ. */ - atomic_set(&dp->lt.done, 0); - ior->dp.nr = 0; - /* Execute DisableLT script from DP Info Table. */ nvbios_init(&ior->disp->engine.subdev, dp->info.script[4], init.outp = &dp->outp.info; @@ -428,6 +425,16 @@ nvkm_dp_release(struct nvkm_outp *outp, struct nvkm_ior *ior) ); } +static void +nvkm_dp_release(struct nvkm_outp *outp) +{ + struct nvkm_dp *dp = nvkm_dp(outp); + + /* Prevent link from being retrained if sink sends an IRQ. */ + atomic_set(&dp->lt.done, 0); + dp->outp.ior->dp.nr = 0; +} + static int nvkm_dp_acquire(struct nvkm_outp *outp) { @@ -491,7 +498,7 @@ done: return ret; } -static void +static bool nvkm_dp_enable(struct nvkm_dp *dp, bool enable) { struct nvkm_i2c_aux *aux = dp->aux; @@ -505,7 +512,7 @@ nvkm_dp_enable(struct nvkm_dp *dp, bool enable) if (!nvkm_rdaux(aux, DPCD_RC00_DPCD_REV, dp->dpcd, sizeof(dp->dpcd))) - return; + return true; } if (dp->present) { @@ -515,6 +522,7 @@ nvkm_dp_enable(struct nvkm_dp *dp, bool enable) } atomic_set(&dp->lt.done, 0); + return false; } static int @@ -555,9 +563,38 @@ nvkm_dp_fini(struct nvkm_outp *outp) static void nvkm_dp_init(struct nvkm_outp *outp) { + struct nvkm_gpio *gpio = outp->disp->engine.subdev.device->gpio; struct nvkm_dp *dp = nvkm_dp(outp); + nvkm_notify_put(&dp->outp.conn->hpd); - nvkm_dp_enable(dp, true); + + /* eDP panels need powering on by us (if the VBIOS doesn't default it + * to on) before doing any AUX channel transactions. LVDS panel power + * is handled by the SOR itself, and not required for LVDS DDC. + */ + if (dp->outp.conn->info.type == DCB_CONNECTOR_eDP) { + int power = nvkm_gpio_get(gpio, 0, DCB_GPIO_PANEL_POWER, 0xff); + if (power == 0) + nvkm_gpio_set(gpio, 0, DCB_GPIO_PANEL_POWER, 0xff, 1); + + /* We delay here unconditionally, even if already powered, + * because some laptop panels having a significant resume + * delay before the panel begins responding. + * + * This is likely a bit of a hack, but no better idea for + * handling this at the moment. + */ + msleep(300); + + /* If the eDP panel can't be detected, we need to restore + * the panel power GPIO to avoid breaking another output. + */ + if (!nvkm_dp_enable(dp, true) && power == 0) + nvkm_gpio_set(gpio, 0, DCB_GPIO_PANEL_POWER, 0xff, 0); + } else { + nvkm_dp_enable(dp, true); + } + nvkm_notify_get(&dp->hpd); } @@ -576,6 +613,7 @@ nvkm_dp_func = { .fini = nvkm_dp_fini, .acquire = nvkm_dp_acquire, .release = nvkm_dp_release, + .disable = nvkm_dp_disable, }; static int diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h index e0b4e0c5704e..19911211a12a 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/ior.h @@ -16,6 +16,7 @@ struct nvkm_ior { char name[8]; struct list_head head; + bool identity; struct nvkm_ior_state { struct nvkm_outp *outp; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c index f89c7b977aa5..def005dd5fda 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/nv50.c @@ -501,11 +501,11 @@ nv50_disp_super_2_0(struct nv50_disp *disp, struct nvkm_head *head) nv50_disp_super_ied_off(head, ior, 2); /* If we're shutting down the OR's only active head, execute - * the output path's release function. + * the output path's disable function. */ if (ior->arm.head == (1 << head->id)) { - if ((outp = ior->arm.outp) && outp->func->release) - outp->func->release(outp, ior); + if ((outp = ior->arm.outp) && outp->func->disable) + outp->func->disable(outp, ior); } } diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c index be9e7f8c3b23..c62030c96fba 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.c @@ -93,6 +93,8 @@ nvkm_outp_release(struct nvkm_outp *outp, u8 user) if (ior) { outp->acquired &= ~user; if (!outp->acquired) { + if (outp->func->release && outp->ior) + outp->func->release(outp); outp->ior->asy.outp = NULL; outp->ior = NULL; } @@ -127,17 +129,26 @@ nvkm_outp_acquire(struct nvkm_outp *outp, u8 user) if (proto == UNKNOWN) return -ENOSYS; + /* Deal with panels requiring identity-mapped SOR assignment. */ + if (outp->identity) { + ior = nvkm_ior_find(outp->disp, SOR, ffs(outp->info.or) - 1); + if (WARN_ON(!ior)) + return -ENOSPC; + return nvkm_outp_acquire_ior(outp, user, ior); + } + /* First preference is to reuse the OR that is currently armed * on HW, if any, in order to prevent unnecessary switching. */ list_for_each_entry(ior, &outp->disp->ior, head) { - if (!ior->asy.outp && ior->arm.outp == outp) + if (!ior->identity && !ior->asy.outp && ior->arm.outp == outp) return nvkm_outp_acquire_ior(outp, user, ior); } /* Failing that, a completely unused OR is the next best thing. */ list_for_each_entry(ior, &outp->disp->ior, head) { - if (!ior->asy.outp && ior->type == type && !ior->arm.outp && + if (!ior->identity && + !ior->asy.outp && ior->type == type && !ior->arm.outp && (ior->func->route.set || ior->id == __ffs(outp->info.or))) return nvkm_outp_acquire_ior(outp, user, ior); } @@ -146,7 +157,7 @@ nvkm_outp_acquire(struct nvkm_outp *outp, u8 user) * but will be released during the next modeset. */ list_for_each_entry(ior, &outp->disp->ior, head) { - if (!ior->asy.outp && ior->type == type && + if (!ior->identity && !ior->asy.outp && ior->type == type && (ior->func->route.set || ior->id == __ffs(outp->info.or))) return nvkm_outp_acquire_ior(outp, user, ior); } @@ -245,7 +256,6 @@ nvkm_outp_ctor(const struct nvkm_outp_func *func, struct nvkm_disp *disp, outp->index = index; outp->info = *dcbE; outp->i2c = nvkm_i2c_bus_find(i2c, dcbE->i2c_index); - outp->or = ffs(outp->info.or) - 1; OUTP_DBG(outp, "type %02x loc %d or %d link %d con %x " "edid %x bus %d head %x", diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.h index ea84d7d5741a..6c8aa5cfed9d 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/outp.h @@ -13,10 +13,10 @@ struct nvkm_outp { struct dcb_output info; struct nvkm_i2c_bus *i2c; - int or; struct list_head head; struct nvkm_conn *conn; + bool identity; /* Assembly state. */ #define NVKM_OUTP_PRIV 1 @@ -41,7 +41,8 @@ struct nvkm_outp_func { void (*init)(struct nvkm_outp *); void (*fini)(struct nvkm_outp *); int (*acquire)(struct nvkm_outp *); - void (*release)(struct nvkm_outp *, struct nvkm_ior *); + void (*release)(struct nvkm_outp *); + void (*disable)(struct nvkm_outp *, struct nvkm_ior *); }; #define OUTP_MSG(o,l,f,a...) do { \ diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm200.c b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm200.c index b80618e35491..17235e940ca9 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm200.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/devinit/gm200.c @@ -86,10 +86,8 @@ pmu_load(struct nv50_devinit *init, u8 type, bool post, struct nvkm_bios *bios = subdev->device->bios; struct nvbios_pmuR pmu; - if (!nvbios_pmuRm(bios, type, &pmu)) { - nvkm_error(subdev, "VBIOS PMU fuc %02x not found\n", type); + if (!nvbios_pmuRm(bios, type, &pmu)) return -EINVAL; - } if (!post) return 0; @@ -124,29 +122,30 @@ gm200_devinit_post(struct nvkm_devinit *base, bool post) return -EINVAL; } + /* Upload DEVINIT application from VBIOS onto PMU. */ ret = pmu_load(init, 0x04, post, &exec, &args); - if (ret) + if (ret) { + nvkm_error(subdev, "VBIOS PMU/DEVINIT not found\n"); return ret; + } - /* upload first chunk of init data */ + /* Upload tables required by opcodes in boot scripts. */ if (post) { - // devinit tables u32 pmu = pmu_args(init, args + 0x08, 0x08); u32 img = nvbios_rd16(bios, bit_I.offset + 0x14); u32 len = nvbios_rd16(bios, bit_I.offset + 0x16); pmu_data(init, pmu, img, len); } - /* upload second chunk of init data */ + /* Upload boot scripts. */ if (post) { - // devinit boot scripts u32 pmu = pmu_args(init, args + 0x08, 0x10); u32 img = nvbios_rd16(bios, bit_I.offset + 0x18); u32 len = nvbios_rd16(bios, bit_I.offset + 0x1a); pmu_data(init, pmu, img, len); } - /* execute init tables */ + /* Execute DEVINIT. */ if (post) { nvkm_wr32(device, 0x10a040, 0x00005000); pmu_exec(init, exec); @@ -157,8 +156,11 @@ gm200_devinit_post(struct nvkm_devinit *base, bool post) return -ETIMEDOUT; } - /* load and execute some other ucode image (bios therm?) */ - return pmu_load(init, 0x01, post, NULL, NULL); + /* Optional: Execute PRE_OS application on PMU, which should at + * least take care of fans until a full PMU has been loaded. + */ + pmu_load(init, 0x01, post, NULL, NULL); + return 0; } static const struct nvkm_devinit_func diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c index de269eb482dd..7459def78d50 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c @@ -1423,7 +1423,7 @@ nvkm_vmm_get(struct nvkm_vmm *vmm, u8 page, u64 size, struct nvkm_vma **pvma) void nvkm_vmm_part(struct nvkm_vmm *vmm, struct nvkm_memory *inst) { - if (vmm->func->part && inst) { + if (inst && vmm->func->part) { mutex_lock(&vmm->mutex); vmm->func->part(vmm, inst); mutex_unlock(&vmm->mutex); diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c index 25b7bd56ae11..1cb41992aaa1 100644 --- a/drivers/hid/hid-apple.c +++ b/drivers/hid/hid-apple.c @@ -335,7 +335,8 @@ static int apple_input_mapping(struct hid_device *hdev, struct hid_input *hi, struct hid_field *field, struct hid_usage *usage, unsigned long **bit, int *max) { - if (usage->hid == (HID_UP_CUSTOM | 0x0003)) { + if (usage->hid == (HID_UP_CUSTOM | 0x0003) || + usage->hid == (HID_UP_MSVENDOR | 0x0003)) { /* The fn key on Apple USB keyboards */ set_bit(EV_REP, hi->input->evbit); hid_map_usage_clear(hi, usage, bit, max, EV_KEY, KEY_FN); @@ -472,6 +473,12 @@ static const struct hid_device_id apple_devices[] = { .driver_data = APPLE_NUMLOCK_EMULATION | APPLE_HAS_FN }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_ANSI), .driver_data = APPLE_HAS_FN }, + { HID_BLUETOOTH_DEVICE(BT_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_ANSI), + .driver_data = APPLE_HAS_FN }, + { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_NUMPAD_ANSI), + .driver_data = APPLE_HAS_FN }, + { HID_BLUETOOTH_DEVICE(BT_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_NUMPAD_ANSI), + .driver_data = APPLE_HAS_FN }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING_ANSI), .driver_data = APPLE_HAS_FN }, { HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING_ISO), diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 3da354af7a0a..44564f61e9cc 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -1000,7 +1000,7 @@ int hid_open_report(struct hid_device *device) parser = vzalloc(sizeof(struct hid_parser)); if (!parser) { ret = -ENOMEM; - goto err; + goto alloc_err; } parser->device = device; @@ -1039,6 +1039,7 @@ int hid_open_report(struct hid_device *device) hid_err(device, "unbalanced delimiter at end of report description\n"); goto err; } + kfree(parser->collection_stack); vfree(parser); device->status |= HID_STAT_PARSED; return 0; @@ -1047,6 +1048,8 @@ int hid_open_report(struct hid_device *device) hid_err(device, "item fetching failed at offset %d\n", (int)(end - start)); err: + kfree(parser->collection_stack); +alloc_err: vfree(parser); hid_close_report(device); return ret; diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 79bdf0c7e351..5146ee029db4 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -88,6 +88,7 @@ #define USB_DEVICE_ID_ANTON_TOUCH_PAD 0x3101 #define USB_VENDOR_ID_APPLE 0x05ac +#define BT_VENDOR_ID_APPLE 0x004c #define USB_DEVICE_ID_APPLE_MIGHTYMOUSE 0x0304 #define USB_DEVICE_ID_APPLE_MAGICMOUSE 0x030d #define USB_DEVICE_ID_APPLE_MAGICTRACKPAD 0x030e @@ -157,6 +158,7 @@ #define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ISO 0x0256 #define USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_JIS 0x0257 #define USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_ANSI 0x0267 +#define USB_DEVICE_ID_APPLE_MAGIC_KEYBOARD_NUMPAD_ANSI 0x026c #define USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI 0x0290 #define USB_DEVICE_ID_APPLE_WELLSPRING8_ISO 0x0291 #define USB_DEVICE_ID_APPLE_WELLSPRING8_JIS 0x0292 @@ -528,9 +530,6 @@ #define I2C_VENDOR_ID_HANTICK 0x0911 #define I2C_PRODUCT_ID_HANTICK_5288 0x5288 -#define I2C_VENDOR_ID_RAYD 0x2386 -#define I2C_PRODUCT_ID_RAYD_3118 0x3118 - #define USB_VENDOR_ID_HANWANG 0x0b57 #define USB_DEVICE_ID_HANWANG_TABLET_FIRST 0x5000 #define USB_DEVICE_ID_HANWANG_TABLET_LAST 0x8fff @@ -950,6 +949,7 @@ #define USB_DEVICE_ID_SAITEK_RUMBLEPAD 0xff17 #define USB_DEVICE_ID_SAITEK_PS1000 0x0621 #define USB_DEVICE_ID_SAITEK_RAT7_OLD 0x0ccb +#define USB_DEVICE_ID_SAITEK_RAT7_CONTAGION 0x0ccd #define USB_DEVICE_ID_SAITEK_RAT7 0x0cd7 #define USB_DEVICE_ID_SAITEK_RAT9 0x0cfa #define USB_DEVICE_ID_SAITEK_MMO7 0x0cd0 diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index 4e94ea3e280a..a481eaf39e88 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -1582,6 +1582,7 @@ static struct hid_input *hidinput_allocate(struct hid_device *hid, input_dev->dev.parent = &hid->dev; hidinput->input = input_dev; + hidinput->application = application; list_add_tail(&hidinput->list, &hid->inputs); INIT_LIST_HEAD(&hidinput->reports); @@ -1677,8 +1678,7 @@ static struct hid_input *hidinput_match_application(struct hid_report *report) struct hid_input *hidinput; list_for_each_entry(hidinput, &hid->inputs, list) { - if (hidinput->report && - hidinput->report->application == report->application) + if (hidinput->application == report->application) return hidinput; } @@ -1815,6 +1815,7 @@ void hidinput_disconnect(struct hid_device *hid) input_unregister_device(hidinput->input); else input_free_device(hidinput->input); + kfree(hidinput->name); kfree(hidinput); } diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c index 40fbb7c52723..da954f3f4da7 100644 --- a/drivers/hid/hid-multitouch.c +++ b/drivers/hid/hid-multitouch.c @@ -1375,7 +1375,8 @@ static bool mt_need_to_apply_feature(struct hid_device *hdev, struct hid_usage *usage, enum latency_mode latency, bool surface_switch, - bool button_switch) + bool button_switch, + bool *inputmode_found) { struct mt_device *td = hid_get_drvdata(hdev); struct mt_class *cls = &td->mtclass; @@ -1387,6 +1388,14 @@ static bool mt_need_to_apply_feature(struct hid_device *hdev, switch (usage->hid) { case HID_DG_INPUTMODE: + /* + * Some elan panels wrongly declare 2 input mode features, + * and silently ignore when we set the value in the second + * field. Skip the second feature and hope for the best. + */ + if (*inputmode_found) + return false; + if (cls->quirks & MT_QUIRK_FORCE_GET_FEATURE) { report_len = hid_report_len(report); buf = hid_alloc_report_buf(report, GFP_KERNEL); @@ -1402,6 +1411,7 @@ static bool mt_need_to_apply_feature(struct hid_device *hdev, } field->value[index] = td->inputmode_value; + *inputmode_found = true; return true; case HID_DG_CONTACTMAX: @@ -1439,6 +1449,7 @@ static void mt_set_modes(struct hid_device *hdev, enum latency_mode latency, struct hid_usage *usage; int i, j; bool update_report; + bool inputmode_found = false; rep_enum = &hdev->report_enum[HID_FEATURE_REPORT]; list_for_each_entry(rep, &rep_enum->report_list, list) { @@ -1457,7 +1468,8 @@ static void mt_set_modes(struct hid_device *hdev, enum latency_mode latency, usage, latency, surface_switch, - button_switch)) + button_switch, + &inputmode_found)) update_report = true; } } @@ -1685,6 +1697,9 @@ static int mt_probe(struct hid_device *hdev, const struct hid_device_id *id) */ hdev->quirks |= HID_QUIRK_INPUT_PER_APP; + if (id->group != HID_GROUP_MULTITOUCH_WIN_8) + hdev->quirks |= HID_QUIRK_MULTI_INPUT; + timer_setup(&td->release_timer, mt_expired_timeout, 0); ret = hid_parse(hdev); diff --git a/drivers/hid/hid-saitek.c b/drivers/hid/hid-saitek.c index 39e642686ff0..683861f324e3 100644 --- a/drivers/hid/hid-saitek.c +++ b/drivers/hid/hid-saitek.c @@ -183,6 +183,8 @@ static const struct hid_device_id saitek_devices[] = { .driver_data = SAITEK_RELEASE_MODE_RAT7 }, { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_RAT7), .driver_data = SAITEK_RELEASE_MODE_RAT7 }, + { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_RAT7_CONTAGION), + .driver_data = SAITEK_RELEASE_MODE_RAT7 }, { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_RAT9), .driver_data = SAITEK_RELEASE_MODE_RAT7 }, { HID_USB_DEVICE(USB_VENDOR_ID_MADCATZ, USB_DEVICE_ID_MADCATZ_RAT9), diff --git a/drivers/hid/hid-sensor-hub.c b/drivers/hid/hid-sensor-hub.c index 50af72baa5ca..2b63487057c2 100644 --- a/drivers/hid/hid-sensor-hub.c +++ b/drivers/hid/hid-sensor-hub.c @@ -579,6 +579,28 @@ void sensor_hub_device_close(struct hid_sensor_hub_device *hsdev) } EXPORT_SYMBOL_GPL(sensor_hub_device_close); +static __u8 *sensor_hub_report_fixup(struct hid_device *hdev, __u8 *rdesc, + unsigned int *rsize) +{ + /* + * Checks if the report descriptor of Thinkpad Helix 2 has a logical + * minimum for magnetic flux axis greater than the maximum. + */ + if (hdev->product == USB_DEVICE_ID_TEXAS_INSTRUMENTS_LENOVO_YOGA && + *rsize == 2558 && rdesc[913] == 0x17 && rdesc[914] == 0x40 && + rdesc[915] == 0x81 && rdesc[916] == 0x08 && + rdesc[917] == 0x00 && rdesc[918] == 0x27 && + rdesc[921] == 0x07 && rdesc[922] == 0x00) { + /* Sets negative logical minimum for mag x, y and z */ + rdesc[914] = rdesc[935] = rdesc[956] = 0xc0; + rdesc[915] = rdesc[936] = rdesc[957] = 0x7e; + rdesc[916] = rdesc[937] = rdesc[958] = 0xf7; + rdesc[917] = rdesc[938] = rdesc[959] = 0xff; + } + + return rdesc; +} + static int sensor_hub_probe(struct hid_device *hdev, const struct hid_device_id *id) { @@ -743,6 +765,7 @@ static struct hid_driver sensor_hub_driver = { .probe = sensor_hub_probe, .remove = sensor_hub_remove, .raw_event = sensor_hub_raw_event, + .report_fixup = sensor_hub_report_fixup, #ifdef CONFIG_PM .suspend = sensor_hub_suspend, .resume = sensor_hub_resume, diff --git a/drivers/hid/i2c-hid/i2c-hid.c b/drivers/hid/i2c-hid/i2c-hid.c index 2ce194a84868..f3076659361a 100644 --- a/drivers/hid/i2c-hid/i2c-hid.c +++ b/drivers/hid/i2c-hid/i2c-hid.c @@ -170,8 +170,6 @@ static const struct i2c_hid_quirks { I2C_HID_QUIRK_SET_PWR_WAKEUP_DEV }, { I2C_VENDOR_ID_HANTICK, I2C_PRODUCT_ID_HANTICK_5288, I2C_HID_QUIRK_NO_IRQ_AFTER_RESET }, - { I2C_VENDOR_ID_RAYD, I2C_PRODUCT_ID_RAYD_3118, - I2C_HID_QUIRK_RESEND_REPORT_DESCR }, { USB_VENDOR_ID_SIS_TOUCH, USB_DEVICE_ID_SIS10FB_TOUCH, I2C_HID_QUIRK_RESEND_REPORT_DESCR }, { 0, 0 } @@ -1235,11 +1233,16 @@ static int i2c_hid_resume(struct device *dev) pm_runtime_enable(dev); enable_irq(client->irq); - ret = i2c_hid_hwreset(client); + + /* Instead of resetting device, simply powers the device on. This + * solves "incomplete reports" on Raydium devices 2386:3118 and + * 2386:4B33 + */ + ret = i2c_hid_set_power(client, I2C_HID_PWR_ON); if (ret) return ret; - /* RAYDIUM device (2386:3118) need to re-send report descr cmd + /* Some devices need to re-send report descr cmd * after resume, after this it will be back normal. * otherwise it issues too many incomplete reports. */ diff --git a/drivers/hid/intel-ish-hid/ipc/hw-ish.h b/drivers/hid/intel-ish-hid/ipc/hw-ish.h index 97869b7410eb..da133716bed0 100644 --- a/drivers/hid/intel-ish-hid/ipc/hw-ish.h +++ b/drivers/hid/intel-ish-hid/ipc/hw-ish.h @@ -29,6 +29,7 @@ #define CNL_Ax_DEVICE_ID 0x9DFC #define GLK_Ax_DEVICE_ID 0x31A2 #define CNL_H_DEVICE_ID 0xA37C +#define SPT_H_DEVICE_ID 0xA135 #define REVISION_ID_CHT_A0 0x6 #define REVISION_ID_CHT_Ax_SI 0x0 diff --git a/drivers/hid/intel-ish-hid/ipc/pci-ish.c b/drivers/hid/intel-ish-hid/ipc/pci-ish.c index 050f9872f5c0..a1125a5c7965 100644 --- a/drivers/hid/intel-ish-hid/ipc/pci-ish.c +++ b/drivers/hid/intel-ish-hid/ipc/pci-ish.c @@ -38,6 +38,7 @@ static const struct pci_device_id ish_pci_tbl[] = { {PCI_DEVICE(PCI_VENDOR_ID_INTEL, CNL_Ax_DEVICE_ID)}, {PCI_DEVICE(PCI_VENDOR_ID_INTEL, GLK_Ax_DEVICE_ID)}, {PCI_DEVICE(PCI_VENDOR_ID_INTEL, CNL_H_DEVICE_ID)}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, SPT_H_DEVICE_ID)}, {0, } }; MODULE_DEVICE_TABLE(pci, ish_pci_tbl); diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index b1b548a21f91..c71cc857b649 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -1291,6 +1291,9 @@ static ssize_t vmbus_chan_attr_show(struct kobject *kobj, if (!attribute->show) return -EIO; + if (chan->state != CHANNEL_OPENED_STATE) + return -EINVAL; + return attribute->show(chan, buf); } diff --git a/drivers/hwmon/adt7475.c b/drivers/hwmon/adt7475.c index 90837f7c7d0f..f4c7516eb989 100644 --- a/drivers/hwmon/adt7475.c +++ b/drivers/hwmon/adt7475.c @@ -302,14 +302,18 @@ static inline u16 volt2reg(int channel, long volt, u8 bypass_attn) return clamp_val(reg, 0, 1023) & (0xff << 2); } -static u16 adt7475_read_word(struct i2c_client *client, int reg) +static int adt7475_read_word(struct i2c_client *client, int reg) { - u16 val; + int val1, val2; - val = i2c_smbus_read_byte_data(client, reg); - val |= (i2c_smbus_read_byte_data(client, reg + 1) << 8); + val1 = i2c_smbus_read_byte_data(client, reg); + if (val1 < 0) + return val1; + val2 = i2c_smbus_read_byte_data(client, reg + 1); + if (val2 < 0) + return val2; - return val; + return val1 | (val2 << 8); } static void adt7475_write_word(struct i2c_client *client, int reg, u16 val) @@ -962,13 +966,14 @@ static ssize_t show_pwmfreq(struct device *dev, struct device_attribute *attr, { struct adt7475_data *data = adt7475_update_device(dev); struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr); - int i = clamp_val(data->range[sattr->index] & 0xf, 0, - ARRAY_SIZE(pwmfreq_table) - 1); + int idx; if (IS_ERR(data)) return PTR_ERR(data); + idx = clamp_val(data->range[sattr->index] & 0xf, 0, + ARRAY_SIZE(pwmfreq_table) - 1); - return sprintf(buf, "%d\n", pwmfreq_table[i]); + return sprintf(buf, "%d\n", pwmfreq_table[idx]); } static ssize_t set_pwmfreq(struct device *dev, struct device_attribute *attr, @@ -1004,6 +1009,10 @@ static ssize_t pwm_use_point2_pwm_at_crit_show(struct device *dev, char *buf) { struct adt7475_data *data = adt7475_update_device(dev); + + if (IS_ERR(data)) + return PTR_ERR(data); + return sprintf(buf, "%d\n", !!(data->config4 & CONFIG4_MAXDUTY)); } diff --git a/drivers/hwmon/ina2xx.c b/drivers/hwmon/ina2xx.c index e9e6aeabbf84..71d3445ba869 100644 --- a/drivers/hwmon/ina2xx.c +++ b/drivers/hwmon/ina2xx.c @@ -17,7 +17,7 @@ * Bi-directional Current/Power Monitor with I2C Interface * Datasheet: http://www.ti.com/product/ina230 * - * Copyright (C) 2012 Lothar Felten <l-felten@ti.com> + * Copyright (C) 2012 Lothar Felten <lothar.felten@gmail.com> * Thanks to Jan Volkering * * This program is free software; you can redistribute it and/or modify @@ -329,6 +329,15 @@ static int ina2xx_set_shunt(struct ina2xx_data *data, long val) return 0; } +static ssize_t ina2xx_show_shunt(struct device *dev, + struct device_attribute *da, + char *buf) +{ + struct ina2xx_data *data = dev_get_drvdata(dev); + + return snprintf(buf, PAGE_SIZE, "%li\n", data->rshunt); +} + static ssize_t ina2xx_store_shunt(struct device *dev, struct device_attribute *da, const char *buf, size_t count) @@ -403,7 +412,7 @@ static SENSOR_DEVICE_ATTR(power1_input, S_IRUGO, ina2xx_show_value, NULL, /* shunt resistance */ static SENSOR_DEVICE_ATTR(shunt_resistor, S_IRUGO | S_IWUSR, - ina2xx_show_value, ina2xx_store_shunt, + ina2xx_show_shunt, ina2xx_store_shunt, INA2XX_CALIBRATION); /* update interval (ina226 only) */ diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c index c6bd61e4695a..944f5b63aecd 100644 --- a/drivers/hwmon/nct6775.c +++ b/drivers/hwmon/nct6775.c @@ -63,6 +63,7 @@ #include <linux/bitops.h> #include <linux/dmi.h> #include <linux/io.h> +#include <linux/nospec.h> #include "lm75.h" #define USE_ALTERNATE @@ -2689,6 +2690,7 @@ store_pwm_weight_temp_sel(struct device *dev, struct device_attribute *attr, return err; if (val > NUM_TEMP) return -EINVAL; + val = array_index_nospec(val, NUM_TEMP + 1); if (val && (!(data->have_temp & BIT(val - 1)) || !data->temp_src[val - 1])) return -EINVAL; diff --git a/drivers/hwmon/raspberrypi-hwmon.c b/drivers/hwmon/raspberrypi-hwmon.c index fb4e4a6bb1f6..be5ba4690895 100644 --- a/drivers/hwmon/raspberrypi-hwmon.c +++ b/drivers/hwmon/raspberrypi-hwmon.c @@ -164,3 +164,4 @@ module_platform_driver(rpi_hwmon_driver); MODULE_AUTHOR("Stefan Wahren <stefan.wahren@i2se.com>"); MODULE_DESCRIPTION("Raspberry Pi voltage sensor driver"); MODULE_LICENSE("GPL v2"); +MODULE_ALIAS("platform:raspberrypi-hwmon"); diff --git a/drivers/i2c/algos/i2c-algo-bit.c b/drivers/i2c/algos/i2c-algo-bit.c index 6ec65adaba49..c33dcfb87993 100644 --- a/drivers/i2c/algos/i2c-algo-bit.c +++ b/drivers/i2c/algos/i2c-algo-bit.c @@ -110,8 +110,8 @@ static int sclhi(struct i2c_algo_bit_data *adap) } #ifdef DEBUG if (jiffies != start && i2c_debug >= 3) - pr_debug("i2c-algo-bit: needed %ld jiffies for SCL to go " - "high\n", jiffies - start); + pr_debug("i2c-algo-bit: needed %ld jiffies for SCL to go high\n", + jiffies - start); #endif done: @@ -171,8 +171,9 @@ static int i2c_outb(struct i2c_adapter *i2c_adap, unsigned char c) setsda(adap, sb); udelay((adap->udelay + 1) / 2); if (sclhi(adap) < 0) { /* timed out */ - bit_dbg(1, &i2c_adap->dev, "i2c_outb: 0x%02x, " - "timeout at bit #%d\n", (int)c, i); + bit_dbg(1, &i2c_adap->dev, + "i2c_outb: 0x%02x, timeout at bit #%d\n", + (int)c, i); return -ETIMEDOUT; } /* FIXME do arbitration here: @@ -185,8 +186,8 @@ static int i2c_outb(struct i2c_adapter *i2c_adap, unsigned char c) } sdahi(adap); if (sclhi(adap) < 0) { /* timeout */ - bit_dbg(1, &i2c_adap->dev, "i2c_outb: 0x%02x, " - "timeout at ack\n", (int)c); + bit_dbg(1, &i2c_adap->dev, + "i2c_outb: 0x%02x, timeout at ack\n", (int)c); return -ETIMEDOUT; } @@ -215,8 +216,9 @@ static int i2c_inb(struct i2c_adapter *i2c_adap) sdahi(adap); for (i = 0; i < 8; i++) { if (sclhi(adap) < 0) { /* timeout */ - bit_dbg(1, &i2c_adap->dev, "i2c_inb: timeout at bit " - "#%d\n", 7 - i); + bit_dbg(1, &i2c_adap->dev, + "i2c_inb: timeout at bit #%d\n", + 7 - i); return -ETIMEDOUT; } indata *= 2; @@ -265,8 +267,9 @@ static int test_bus(struct i2c_adapter *i2c_adap) goto bailout; } if (!scl) { - printk(KERN_WARNING "%s: SCL unexpected low " - "while pulling SDA low!\n", name); + printk(KERN_WARNING + "%s: SCL unexpected low while pulling SDA low!\n", + name); goto bailout; } @@ -278,8 +281,9 @@ static int test_bus(struct i2c_adapter *i2c_adap) goto bailout; } if (!scl) { - printk(KERN_WARNING "%s: SCL unexpected low " - "while pulling SDA high!\n", name); + printk(KERN_WARNING + "%s: SCL unexpected low while pulling SDA high!\n", + name); goto bailout; } @@ -291,8 +295,9 @@ static int test_bus(struct i2c_adapter *i2c_adap) goto bailout; } if (!sda) { - printk(KERN_WARNING "%s: SDA unexpected low " - "while pulling SCL low!\n", name); + printk(KERN_WARNING + "%s: SDA unexpected low while pulling SCL low!\n", + name); goto bailout; } @@ -304,8 +309,9 @@ static int test_bus(struct i2c_adapter *i2c_adap) goto bailout; } if (!sda) { - printk(KERN_WARNING "%s: SDA unexpected low " - "while pulling SCL high!\n", name); + printk(KERN_WARNING + "%s: SDA unexpected low while pulling SCL high!\n", + name); goto bailout; } @@ -352,8 +358,8 @@ static int try_address(struct i2c_adapter *i2c_adap, i2c_start(adap); } if (i && ret) - bit_dbg(1, &i2c_adap->dev, "Used %d tries to %s client at " - "0x%02x: %s\n", i + 1, + bit_dbg(1, &i2c_adap->dev, + "Used %d tries to %s client at 0x%02x: %s\n", i + 1, addr & 1 ? "read from" : "write to", addr >> 1, ret == 1 ? "success" : "failed, timeout?"); return ret; @@ -442,8 +448,9 @@ static int readbytes(struct i2c_adapter *i2c_adap, struct i2c_msg *msg) if (inval <= 0 || inval > I2C_SMBUS_BLOCK_MAX) { if (!(flags & I2C_M_NO_RD_ACK)) acknak(i2c_adap, 0); - dev_err(&i2c_adap->dev, "readbytes: invalid " - "block length (%d)\n", inval); + dev_err(&i2c_adap->dev, + "readbytes: invalid block length (%d)\n", + inval); return -EPROTO; } /* The original count value accounts for the extra @@ -506,8 +513,8 @@ static int bit_doAddress(struct i2c_adapter *i2c_adap, struct i2c_msg *msg) return -ENXIO; } if (flags & I2C_M_RD) { - bit_dbg(3, &i2c_adap->dev, "emitting repeated " - "start condition\n"); + bit_dbg(3, &i2c_adap->dev, + "emitting repeated start condition\n"); i2c_repstart(adap); /* okay, now switch into reading mode */ addr |= 0x01; @@ -564,8 +571,8 @@ static int bit_xfer(struct i2c_adapter *i2c_adap, } ret = bit_doAddress(i2c_adap, pmsg); if ((ret != 0) && !nak_ok) { - bit_dbg(1, &i2c_adap->dev, "NAK from " - "device addr 0x%02x msg #%d\n", + bit_dbg(1, &i2c_adap->dev, + "NAK from device addr 0x%02x msg #%d\n", msgs[i].addr, i); goto bailout; } diff --git a/drivers/i2c/busses/i2c-designware-master.c b/drivers/i2c/busses/i2c-designware-master.c index e18442b9973a..94d94b4a9a0d 100644 --- a/drivers/i2c/busses/i2c-designware-master.c +++ b/drivers/i2c/busses/i2c-designware-master.c @@ -708,7 +708,6 @@ int i2c_dw_probe(struct dw_i2c_dev *dev) i2c_set_adapdata(adap, dev); if (dev->pm_disabled) { - dev_pm_syscore_device(dev->dev, true); irq_flags = IRQF_NO_SUSPEND; } else { irq_flags = IRQF_SHARED | IRQF_COND_SUSPEND; diff --git a/drivers/i2c/busses/i2c-designware-platdrv.c b/drivers/i2c/busses/i2c-designware-platdrv.c index 1a8d2da5b000..b5750fd85125 100644 --- a/drivers/i2c/busses/i2c-designware-platdrv.c +++ b/drivers/i2c/busses/i2c-designware-platdrv.c @@ -434,6 +434,9 @@ static int dw_i2c_plat_suspend(struct device *dev) { struct dw_i2c_dev *i_dev = dev_get_drvdata(dev); + if (i_dev->pm_disabled) + return 0; + i_dev->disable(i_dev); i2c_dw_prepare_clk(i_dev, false); @@ -444,7 +447,9 @@ static int dw_i2c_plat_resume(struct device *dev) { struct dw_i2c_dev *i_dev = dev_get_drvdata(dev); - i2c_dw_prepare_clk(i_dev, true); + if (!i_dev->pm_disabled) + i2c_dw_prepare_clk(i_dev, true); + i_dev->init(i_dev); return 0; diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index 941c223f6491..c91e145ef5a5 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -140,6 +140,7 @@ #define SBREG_BAR 0x10 #define SBREG_SMBCTRL 0xc6000c +#define SBREG_SMBCTRL_DNV 0xcf000c /* Host status bits for SMBPCISTS */ #define SMBPCISTS_INTS BIT(3) @@ -1399,7 +1400,11 @@ static void i801_add_tco(struct i801_priv *priv) spin_unlock(&p2sb_spinlock); res = &tco_res[ICH_RES_MEM_OFF]; - res->start = (resource_size_t)base64_addr + SBREG_SMBCTRL; + if (pci_dev->device == PCI_DEVICE_ID_INTEL_DNV_SMBUS) + res->start = (resource_size_t)base64_addr + SBREG_SMBCTRL_DNV; + else + res->start = (resource_size_t)base64_addr + SBREG_SMBCTRL; + res->end = res->start + 3; res->flags = IORESOURCE_MEM; @@ -1415,6 +1420,13 @@ static void i801_add_tco(struct i801_priv *priv) } #ifdef CONFIG_ACPI +static bool i801_acpi_is_smbus_ioport(const struct i801_priv *priv, + acpi_physical_address address) +{ + return address >= priv->smba && + address <= pci_resource_end(priv->pci_dev, SMBBAR); +} + static acpi_status i801_acpi_io_handler(u32 function, acpi_physical_address address, u32 bits, u64 *value, void *handler_context, void *region_context) @@ -1430,7 +1442,7 @@ i801_acpi_io_handler(u32 function, acpi_physical_address address, u32 bits, */ mutex_lock(&priv->acpi_lock); - if (!priv->acpi_reserved) { + if (!priv->acpi_reserved && i801_acpi_is_smbus_ioport(priv, address)) { priv->acpi_reserved = true; dev_warn(&pdev->dev, "BIOS is accessing SMBus registers\n"); diff --git a/drivers/i2c/busses/i2c-imx-lpi2c.c b/drivers/i2c/busses/i2c-imx-lpi2c.c index 6d975f5221ca..06c4c767af32 100644 --- a/drivers/i2c/busses/i2c-imx-lpi2c.c +++ b/drivers/i2c/busses/i2c-imx-lpi2c.c @@ -538,7 +538,6 @@ static const struct i2c_algorithm lpi2c_imx_algo = { static const struct of_device_id lpi2c_imx_of_match[] = { { .compatible = "fsl,imx7ulp-lpi2c" }, - { .compatible = "fsl,imx8dv-lpi2c" }, { }, }; MODULE_DEVICE_TABLE(of, lpi2c_imx_of_match); diff --git a/drivers/i2c/busses/i2c-sh_mobile.c b/drivers/i2c/busses/i2c-sh_mobile.c index 439e8778f849..818cab14e87c 100644 --- a/drivers/i2c/busses/i2c-sh_mobile.c +++ b/drivers/i2c/busses/i2c-sh_mobile.c @@ -507,8 +507,6 @@ static void sh_mobile_i2c_dma_callback(void *data) pd->pos = pd->msg->len; pd->stop_after_dma = true; - i2c_release_dma_safe_msg_buf(pd->msg, pd->dma_buf); - iic_set_clr(pd, ICIC, 0, ICIC_TDMAE | ICIC_RDMAE); } @@ -602,8 +600,8 @@ static void sh_mobile_i2c_xfer_dma(struct sh_mobile_i2c_data *pd) dma_async_issue_pending(chan); } -static int start_ch(struct sh_mobile_i2c_data *pd, struct i2c_msg *usr_msg, - bool do_init) +static void start_ch(struct sh_mobile_i2c_data *pd, struct i2c_msg *usr_msg, + bool do_init) { if (do_init) { /* Initialize channel registers */ @@ -627,7 +625,6 @@ static int start_ch(struct sh_mobile_i2c_data *pd, struct i2c_msg *usr_msg, /* Enable all interrupts to begin with */ iic_wr(pd, ICIC, ICIC_DTEE | ICIC_WAITE | ICIC_ALE | ICIC_TACKE); - return 0; } static int poll_dte(struct sh_mobile_i2c_data *pd) @@ -698,9 +695,7 @@ static int sh_mobile_i2c_xfer(struct i2c_adapter *adapter, pd->send_stop = i == num - 1 || msg->flags & I2C_M_STOP; pd->stop_after_dma = false; - err = start_ch(pd, msg, do_start); - if (err) - break; + start_ch(pd, msg, do_start); if (do_start) i2c_op(pd, OP_START, 0); @@ -709,6 +704,10 @@ static int sh_mobile_i2c_xfer(struct i2c_adapter *adapter, timeout = wait_event_timeout(pd->wait, pd->sr & (ICSR_TACK | SW_DONE), adapter->timeout); + + /* 'stop_after_dma' tells if DMA transfer was complete */ + i2c_put_dma_safe_msg_buf(pd->dma_buf, pd->msg, pd->stop_after_dma); + if (!timeout) { dev_err(pd->dev, "Transfer request timed out\n"); if (pd->dma_direction != DMA_NONE) diff --git a/drivers/i2c/busses/i2c-uniphier-f.c b/drivers/i2c/busses/i2c-uniphier-f.c index 9918bdd81619..a403e8579b65 100644 --- a/drivers/i2c/busses/i2c-uniphier-f.c +++ b/drivers/i2c/busses/i2c-uniphier-f.c @@ -401,11 +401,8 @@ static int uniphier_fi2c_master_xfer(struct i2c_adapter *adap, return ret; for (msg = msgs; msg < emsg; msg++) { - /* If next message is read, skip the stop condition */ - bool stop = !(msg + 1 < emsg && msg[1].flags & I2C_M_RD); - /* but, force it if I2C_M_STOP is set */ - if (msg->flags & I2C_M_STOP) - stop = true; + /* Emit STOP if it is the last message or I2C_M_STOP is set. */ + bool stop = (msg + 1 == emsg) || (msg->flags & I2C_M_STOP); ret = uniphier_fi2c_master_xfer_one(adap, msg, stop); if (ret) diff --git a/drivers/i2c/busses/i2c-uniphier.c b/drivers/i2c/busses/i2c-uniphier.c index bb181b088291..454f914ae66d 100644 --- a/drivers/i2c/busses/i2c-uniphier.c +++ b/drivers/i2c/busses/i2c-uniphier.c @@ -248,11 +248,8 @@ static int uniphier_i2c_master_xfer(struct i2c_adapter *adap, return ret; for (msg = msgs; msg < emsg; msg++) { - /* If next message is read, skip the stop condition */ - bool stop = !(msg + 1 < emsg && msg[1].flags & I2C_M_RD); - /* but, force it if I2C_M_STOP is set */ - if (msg->flags & I2C_M_STOP) - stop = true; + /* Emit STOP if it is the last message or I2C_M_STOP is set. */ + bool stop = (msg + 1 == emsg) || (msg->flags & I2C_M_STOP); ret = uniphier_i2c_master_xfer_one(adap, msg, stop); if (ret) diff --git a/drivers/i2c/busses/i2c-xiic.c b/drivers/i2c/busses/i2c-xiic.c index 9a71e50d21f1..0c51c0ffdda9 100644 --- a/drivers/i2c/busses/i2c-xiic.c +++ b/drivers/i2c/busses/i2c-xiic.c @@ -532,6 +532,7 @@ static void xiic_start_recv(struct xiic_i2c *i2c) { u8 rx_watermark; struct i2c_msg *msg = i2c->rx_msg = i2c->tx_msg; + unsigned long flags; /* Clear and enable Rx full interrupt. */ xiic_irq_clr_en(i2c, XIIC_INTR_RX_FULL_MASK | XIIC_INTR_TX_ERROR_MASK); @@ -547,6 +548,7 @@ static void xiic_start_recv(struct xiic_i2c *i2c) rx_watermark = IIC_RX_FIFO_DEPTH; xiic_setreg8(i2c, XIIC_RFD_REG_OFFSET, rx_watermark - 1); + local_irq_save(flags); if (!(msg->flags & I2C_M_NOSTART)) /* write the address */ xiic_setreg16(i2c, XIIC_DTR_REG_OFFSET, @@ -556,6 +558,8 @@ static void xiic_start_recv(struct xiic_i2c *i2c) xiic_setreg16(i2c, XIIC_DTR_REG_OFFSET, msg->len | ((i2c->nmsgs == 1) ? XIIC_TX_DYN_STOP_MASK : 0)); + local_irq_restore(flags); + if (i2c->nmsgs == 1) /* very last, enable bus not busy as well */ xiic_irq_clr_en(i2c, XIIC_INTR_BNB_MASK); diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index f15737763608..9ee9a15e7134 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -2293,21 +2293,22 @@ u8 *i2c_get_dma_safe_msg_buf(struct i2c_msg *msg, unsigned int threshold) EXPORT_SYMBOL_GPL(i2c_get_dma_safe_msg_buf); /** - * i2c_release_dma_safe_msg_buf - release DMA safe buffer and sync with i2c_msg - * @msg: the message to be synced with + * i2c_put_dma_safe_msg_buf - release DMA safe buffer and sync with i2c_msg * @buf: the buffer obtained from i2c_get_dma_safe_msg_buf(). May be NULL. + * @msg: the message which the buffer corresponds to + * @xferred: bool saying if the message was transferred */ -void i2c_release_dma_safe_msg_buf(struct i2c_msg *msg, u8 *buf) +void i2c_put_dma_safe_msg_buf(u8 *buf, struct i2c_msg *msg, bool xferred) { if (!buf || buf == msg->buf) return; - if (msg->flags & I2C_M_RD) + if (xferred && msg->flags & I2C_M_RD) memcpy(msg->buf, buf, msg->len); kfree(buf); } -EXPORT_SYMBOL_GPL(i2c_release_dma_safe_msg_buf); +EXPORT_SYMBOL_GPL(i2c_put_dma_safe_msg_buf); MODULE_AUTHOR("Simon G. Vogl <simon@tk.uni-linz.ac.at>"); MODULE_DESCRIPTION("I2C-Bus main module"); diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c index 7589f2ad1dae..631360b14ca7 100644 --- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c +++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c @@ -187,12 +187,15 @@ static int st_lsm6dsx_set_fifo_odr(struct st_lsm6dsx_sensor *sensor, int st_lsm6dsx_update_watermark(struct st_lsm6dsx_sensor *sensor, u16 watermark) { - u16 fifo_watermark = ~0, cur_watermark, sip = 0, fifo_th_mask; + u16 fifo_watermark = ~0, cur_watermark, fifo_th_mask; struct st_lsm6dsx_hw *hw = sensor->hw; struct st_lsm6dsx_sensor *cur_sensor; int i, err, data; __le16 wdata; + if (!hw->sip) + return 0; + for (i = 0; i < ST_LSM6DSX_ID_MAX; i++) { cur_sensor = iio_priv(hw->iio_devs[i]); @@ -203,14 +206,10 @@ int st_lsm6dsx_update_watermark(struct st_lsm6dsx_sensor *sensor, u16 watermark) : cur_sensor->watermark; fifo_watermark = min_t(u16, fifo_watermark, cur_watermark); - sip += cur_sensor->sip; } - if (!sip) - return 0; - - fifo_watermark = max_t(u16, fifo_watermark, sip); - fifo_watermark = (fifo_watermark / sip) * sip; + fifo_watermark = max_t(u16, fifo_watermark, hw->sip); + fifo_watermark = (fifo_watermark / hw->sip) * hw->sip; fifo_watermark = fifo_watermark * hw->settings->fifo_ops.th_wl; err = regmap_read(hw->regmap, hw->settings->fifo_ops.fifo_th.addr + 1, diff --git a/drivers/iio/temperature/maxim_thermocouple.c b/drivers/iio/temperature/maxim_thermocouple.c index 54e383231d1e..c31b9633f32d 100644 --- a/drivers/iio/temperature/maxim_thermocouple.c +++ b/drivers/iio/temperature/maxim_thermocouple.c @@ -258,7 +258,6 @@ static int maxim_thermocouple_remove(struct spi_device *spi) static const struct spi_device_id maxim_thermocouple_id[] = { {"max6675", MAX6675}, {"max31855", MAX31855}, - {"max31856", MAX31855}, {}, }; MODULE_DEVICE_TABLE(spi, maxim_thermocouple_id); diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index f72677291b69..a36c94930c31 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -724,6 +724,7 @@ static int cma_resolve_ib_dev(struct rdma_id_private *id_priv) dgid = (union ib_gid *) &addr->sib_addr; pkey = ntohs(addr->sib_pkey); + mutex_lock(&lock); list_for_each_entry(cur_dev, &dev_list, list) { for (p = 1; p <= cur_dev->device->phys_port_cnt; ++p) { if (!rdma_cap_af_ib(cur_dev->device, p)) @@ -750,18 +751,19 @@ static int cma_resolve_ib_dev(struct rdma_id_private *id_priv) cma_dev = cur_dev; sgid = gid; id_priv->id.port_num = p; + goto found; } } } } - - if (!cma_dev) - return -ENODEV; + mutex_unlock(&lock); + return -ENODEV; found: cma_attach_to_dev(id_priv, cma_dev); - addr = (struct sockaddr_ib *) cma_src_addr(id_priv); - memcpy(&addr->sib_addr, &sgid, sizeof sgid); + mutex_unlock(&lock); + addr = (struct sockaddr_ib *)cma_src_addr(id_priv); + memcpy(&addr->sib_addr, &sgid, sizeof(sgid)); cma_translate_ib(addr, &id_priv->id.route.addr.dev_addr); return 0; } diff --git a/drivers/infiniband/core/rdma_core.c b/drivers/infiniband/core/rdma_core.c index 6eb64c6f0802..c4118bcd5103 100644 --- a/drivers/infiniband/core/rdma_core.c +++ b/drivers/infiniband/core/rdma_core.c @@ -882,6 +882,8 @@ static int __uverbs_cleanup_ufile(struct ib_uverbs_file *ufile, WARN_ON(uverbs_try_lock_object(obj, UVERBS_LOOKUP_WRITE)); if (!uverbs_destroy_uobject(obj, reason)) ret = 0; + else + atomic_set(&obj->usecnt, 0); } return ret; } diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c index ec8fb289621f..5f437d1570fb 100644 --- a/drivers/infiniband/core/ucma.c +++ b/drivers/infiniband/core/ucma.c @@ -124,6 +124,8 @@ static DEFINE_MUTEX(mut); static DEFINE_IDR(ctx_idr); static DEFINE_IDR(multicast_idr); +static const struct file_operations ucma_fops; + static inline struct ucma_context *_ucma_find_context(int id, struct ucma_file *file) { @@ -1581,6 +1583,10 @@ static ssize_t ucma_migrate_id(struct ucma_file *new_file, f = fdget(cmd.fd); if (!f.file) return -ENOENT; + if (f.file->f_op != &ucma_fops) { + ret = -EINVAL; + goto file_put; + } /* Validate current fd and prevent destruction of id. */ ctx = ucma_get_ctx(f.file->private_data, cmd.id); diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 823beca448e1..6d974e2363df 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -1050,7 +1050,7 @@ static void ib_uverbs_add_one(struct ib_device *device) uverbs_dev->num_comp_vectors = device->num_comp_vectors; if (ib_uverbs_create_uapi(device, uverbs_dev)) - goto err; + goto err_uapi; cdev_init(&uverbs_dev->cdev, NULL); uverbs_dev->cdev.owner = THIS_MODULE; @@ -1077,11 +1077,10 @@ static void ib_uverbs_add_one(struct ib_device *device) err_class: device_destroy(uverbs_class, uverbs_dev->cdev.dev); - err_cdev: cdev_del(&uverbs_dev->cdev); +err_uapi: clear_bit(devnum, dev_map); - err: if (atomic_dec_and_test(&uverbs_dev->refcount)) ib_uverbs_comp_dev(uverbs_dev); diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index bbfb86eb2d24..bc2b9e038439 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -833,6 +833,8 @@ int bnxt_re_destroy_qp(struct ib_qp *ib_qp) "Failed to destroy Shadow QP"); return rc; } + bnxt_qplib_free_qp_res(&rdev->qplib_res, + &rdev->qp1_sqp->qplib_qp); mutex_lock(&rdev->qp_lock); list_del(&rdev->qp1_sqp->list); atomic_dec(&rdev->qp_count); diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index e426b990c1dd..6ad0d46ab879 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -196,7 +196,7 @@ static int bnxt_qplib_alloc_qp_hdr_buf(struct bnxt_qplib_res *res, struct bnxt_qplib_qp *qp) { struct bnxt_qplib_q *rq = &qp->rq; - struct bnxt_qplib_q *sq = &qp->rq; + struct bnxt_qplib_q *sq = &qp->sq; int rc = 0; if (qp->sq_hdr_buf_size && sq->hwq.max_elements) { diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c index b3203afa3b1d..347fe18b1a41 100644 --- a/drivers/infiniband/hw/cxgb4/qp.c +++ b/drivers/infiniband/hw/cxgb4/qp.c @@ -1685,6 +1685,12 @@ static void flush_qp(struct c4iw_qp *qhp) schp = to_c4iw_cq(qhp->ibqp.send_cq); if (qhp->ibqp.uobject) { + + /* for user qps, qhp->wq.flushed is protected by qhp->mutex */ + if (qhp->wq.flushed) + return; + + qhp->wq.flushed = 1; t4_set_wq_in_error(&qhp->wq, 0); t4_set_cq_in_error(&rchp->cq); spin_lock_irqsave(&rchp->comp_handler_lock, flag); diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c index eec83757d55f..6c967dde58e7 100644 --- a/drivers/infiniband/hw/hfi1/pcie.c +++ b/drivers/infiniband/hw/hfi1/pcie.c @@ -893,14 +893,11 @@ static int trigger_sbr(struct hfi1_devdata *dd) } /* - * A secondary bus reset (SBR) issues a hot reset to our device. - * The following routine does a 1s wait after the reset is dropped - * per PCI Trhfa (recovery time). PCIe 3.0 section 6.6.1 - - * Conventional Reset, paragraph 3, line 35 also says that a 1s - * delay after a reset is required. Per spec requirements, - * the link is either working or not after that point. + * This is an end around to do an SBR during probe time. A new API needs + * to be implemented to have cleaner interface but this fixes the + * current brokenness */ - return pci_reset_bus(dev); + return pci_bridge_secondary_bus_reset(dev->bus->self); } /* diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index ca0f1ee26091..0bbeaaae47e0 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -517,9 +517,11 @@ static int mlx4_ib_query_device(struct ib_device *ibdev, props->page_size_cap = dev->dev->caps.page_size_cap; props->max_qp = dev->dev->quotas.qp; props->max_qp_wr = dev->dev->caps.max_wqes - MLX4_IB_SQ_MAX_SPARE; - props->max_send_sge = dev->dev->caps.max_sq_sg; - props->max_recv_sge = dev->dev->caps.max_rq_sg; - props->max_sge_rd = MLX4_MAX_SGE_RD; + props->max_send_sge = + min(dev->dev->caps.max_sq_sg, dev->dev->caps.max_rq_sg); + props->max_recv_sge = + min(dev->dev->caps.max_sq_sg, dev->dev->caps.max_rq_sg); + props->max_sge_rd = MLX4_MAX_SGE_RD; props->max_cq = dev->dev->quotas.cq; props->max_cqe = dev->dev->caps.max_cqes; props->max_mr = dev->dev->quotas.mpt; diff --git a/drivers/infiniband/hw/nes/nes_mgt.c b/drivers/infiniband/hw/nes/nes_mgt.c index 9bdb84dc225c..e96ffff61c3a 100644 --- a/drivers/infiniband/hw/nes/nes_mgt.c +++ b/drivers/infiniband/hw/nes/nes_mgt.c @@ -198,9 +198,9 @@ static struct sk_buff *nes_get_next_skb(struct nes_device *nesdev, struct nes_qp if (skb) { /* Continue processing fpdu */ - if (skb->next == (struct sk_buff *)&nesqp->pau_list) + skb = skb_peek_next(skb, &nesqp->pau_list); + if (!skb) goto out; - skb = skb->next; processacks = false; } else { /* Starting a new one */ @@ -553,12 +553,10 @@ static void queue_fpdus(struct sk_buff *skb, struct nes_vnic *nesvnic, struct ne if (skb_queue_len(&nesqp->pau_list) == 0) { skb_queue_head(&nesqp->pau_list, skb); } else { - tmpskb = nesqp->pau_list.next; - while (tmpskb != (struct sk_buff *)&nesqp->pau_list) { + skb_queue_walk(&nesqp->pau_list, tmpskb) { cb = (struct nes_rskb_cb *)&tmpskb->cb[0]; if (before(seqnum, cb->seqnum)) break; - tmpskb = tmpskb->next; } skb_insert(tmpskb, skb, &nesqp->pau_list); } diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c index ea01b8dd2be6..3d5424f335cb 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c @@ -1027,12 +1027,14 @@ static int ipoib_cm_rep_handler(struct ib_cm_id *cm_id, skb_queue_head_init(&skqueue); + netif_tx_lock_bh(p->dev); spin_lock_irq(&priv->lock); set_bit(IPOIB_FLAG_OPER_UP, &p->flags); if (p->neigh) while ((skb = __skb_dequeue(&p->neigh->queue))) __skb_queue_tail(&skqueue, skb); spin_unlock_irq(&priv->lock); + netif_tx_unlock_bh(p->dev); while ((skb = __skb_dequeue(&skqueue))) { skb->dev = p->dev; diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 316a57530f6d..c2df341ff6fa 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -1439,6 +1439,7 @@ static struct irq_chip its_irq_chip = { * The consequence of the above is that allocation is cost is low, but * freeing is expensive. We assumes that freeing rarely occurs. */ +#define ITS_MAX_LPI_NRBITS 16 /* 64K LPIs */ static DEFINE_MUTEX(lpi_range_lock); static LIST_HEAD(lpi_range_list); @@ -1625,7 +1626,8 @@ static int __init its_alloc_lpi_tables(void) { phys_addr_t paddr; - lpi_id_bits = GICD_TYPER_ID_BITS(gic_rdists->gicd_typer); + lpi_id_bits = min_t(u32, GICD_TYPER_ID_BITS(gic_rdists->gicd_typer), + ITS_MAX_LPI_NRBITS); gic_rdists->prop_page = its_allocate_prop_table(GFP_NOWAIT); if (!gic_rdists->prop_page) { pr_err("Failed to allocate PROPBASE\n"); diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index f266c81f396f..0481223b1deb 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -332,7 +332,7 @@ static int crypt_iv_essiv_init(struct crypt_config *cc) int err; desc->tfm = essiv->hash_tfm; - desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; + desc->flags = 0; err = crypto_shash_digest(desc, cc->key, cc->key_size, essiv->salt); shash_desc_zero(desc); @@ -606,7 +606,7 @@ static int crypt_iv_lmk_one(struct crypt_config *cc, u8 *iv, int i, r; desc->tfm = lmk->hash_tfm; - desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; + desc->flags = 0; r = crypto_shash_init(desc); if (r) @@ -768,7 +768,7 @@ static int crypt_iv_tcw_whitening(struct crypt_config *cc, /* calculate crc32 for every 32bit part and xor it */ desc->tfm = tcw->crc32_tfm; - desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; + desc->flags = 0; for (i = 0; i < 4; i++) { r = crypto_shash_init(desc); if (r) @@ -1251,7 +1251,7 @@ static void crypt_alloc_req_skcipher(struct crypt_config *cc, * requests if driver request queue is full. */ skcipher_request_set_callback(ctx->r.req, - CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, + CRYPTO_TFM_REQ_MAY_BACKLOG, kcryptd_async_done, dmreq_of_req(cc, ctx->r.req)); } @@ -1268,7 +1268,7 @@ static void crypt_alloc_req_aead(struct crypt_config *cc, * requests if driver request queue is full. */ aead_request_set_callback(ctx->r.req_aead, - CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, + CRYPTO_TFM_REQ_MAY_BACKLOG, kcryptd_async_done, dmreq_of_req(cc, ctx->r.req_aead)); } diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 378878599466..89ccb64342de 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -532,7 +532,7 @@ static void section_mac(struct dm_integrity_c *ic, unsigned section, __u8 result unsigned j, size; desc->tfm = ic->journal_mac; - desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; + desc->flags = 0; r = crypto_shash_init(desc); if (unlikely(r)) { @@ -676,7 +676,7 @@ static void complete_journal_encrypt(struct crypto_async_request *req, int err) static bool do_crypt(bool encrypt, struct skcipher_request *req, struct journal_completion *comp) { int r; - skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, + skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG, complete_journal_encrypt, comp); if (likely(encrypt)) r = crypto_skcipher_encrypt(req); diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index cae689de75fd..5ba067fa0c72 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -1,6 +1,6 @@ /* * Copyright (C) 2010-2011 Neil Brown - * Copyright (C) 2010-2017 Red Hat, Inc. All rights reserved. + * Copyright (C) 2010-2018 Red Hat, Inc. All rights reserved. * * This file is released under the GPL. */ @@ -29,9 +29,6 @@ */ #define MIN_RAID456_JOURNAL_SPACE (4*2048) -/* Global list of all raid sets */ -static LIST_HEAD(raid_sets); - static bool devices_handle_discard_safely = false; /* @@ -227,7 +224,6 @@ struct rs_layout { struct raid_set { struct dm_target *ti; - struct list_head list; uint32_t stripe_cache_entries; unsigned long ctr_flags; @@ -273,19 +269,6 @@ static void rs_config_restore(struct raid_set *rs, struct rs_layout *l) mddev->new_chunk_sectors = l->new_chunk_sectors; } -/* Find any raid_set in active slot for @rs on global list */ -static struct raid_set *rs_find_active(struct raid_set *rs) -{ - struct raid_set *r; - struct mapped_device *md = dm_table_get_md(rs->ti->table); - - list_for_each_entry(r, &raid_sets, list) - if (r != rs && dm_table_get_md(r->ti->table) == md) - return r; - - return NULL; -} - /* raid10 algorithms (i.e. formats) */ #define ALGORITHM_RAID10_DEFAULT 0 #define ALGORITHM_RAID10_NEAR 1 @@ -764,7 +747,6 @@ static struct raid_set *raid_set_alloc(struct dm_target *ti, struct raid_type *r mddev_init(&rs->md); - INIT_LIST_HEAD(&rs->list); rs->raid_disks = raid_devs; rs->delta_disks = 0; @@ -782,9 +764,6 @@ static struct raid_set *raid_set_alloc(struct dm_target *ti, struct raid_type *r for (i = 0; i < raid_devs; i++) md_rdev_init(&rs->dev[i].rdev); - /* Add @rs to global list. */ - list_add(&rs->list, &raid_sets); - /* * Remaining items to be initialized by further RAID params: * rs->md.persistent @@ -797,7 +776,7 @@ static struct raid_set *raid_set_alloc(struct dm_target *ti, struct raid_type *r return rs; } -/* Free all @rs allocations and remove it from global list. */ +/* Free all @rs allocations */ static void raid_set_free(struct raid_set *rs) { int i; @@ -815,8 +794,6 @@ static void raid_set_free(struct raid_set *rs) dm_put_device(rs->ti, rs->dev[i].data_dev); } - list_del(&rs->list); - kfree(rs); } @@ -2649,7 +2626,7 @@ static int rs_adjust_data_offsets(struct raid_set *rs) return 0; } - /* HM FIXME: get InSync raid_dev? */ + /* HM FIXME: get In_Sync raid_dev? */ rdev = &rs->dev[0].rdev; if (rs->delta_disks < 0) { @@ -3149,6 +3126,11 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv) set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags); rs_set_new(rs); } else if (rs_is_recovering(rs)) { + /* Rebuild particular devices */ + if (test_bit(__CTR_FLAG_REBUILD, &rs->ctr_flags)) { + set_bit(RT_FLAG_UPDATE_SBS, &rs->runtime_flags); + rs_setup_recovery(rs, MaxSector); + } /* A recovering raid set may be resized */ ; /* skip setup rs */ } else if (rs_is_reshaping(rs)) { @@ -3242,6 +3224,8 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv) /* Start raid set read-only and assumed clean to change in raid_resume() */ rs->md.ro = 1; rs->md.in_sync = 1; + + /* Keep array frozen */ set_bit(MD_RECOVERY_FROZEN, &rs->md.recovery); /* Has to be held on running the array */ @@ -3265,7 +3249,7 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv) rs->callbacks.congested_fn = raid_is_congested; dm_table_add_target_callbacks(ti->table, &rs->callbacks); - /* If raid4/5/6 journal mode explictely requested (only possible with journal dev) -> set it */ + /* If raid4/5/6 journal mode explicitly requested (only possible with journal dev) -> set it */ if (test_bit(__CTR_FLAG_JOURNAL_MODE, &rs->ctr_flags)) { r = r5c_journal_mode_set(&rs->md, rs->journal_dev.mode); if (r) { @@ -3350,32 +3334,53 @@ static int raid_map(struct dm_target *ti, struct bio *bio) return DM_MAPIO_SUBMITTED; } -/* Return string describing the current sync action of @mddev */ -static const char *decipher_sync_action(struct mddev *mddev, unsigned long recovery) +/* Return sync state string for @state */ +enum sync_state { st_frozen, st_reshape, st_resync, st_check, st_repair, st_recover, st_idle }; +static const char *sync_str(enum sync_state state) +{ + /* Has to be in above sync_state order! */ + static const char *sync_strs[] = { + "frozen", + "reshape", + "resync", + "check", + "repair", + "recover", + "idle" + }; + + return __within_range(state, 0, ARRAY_SIZE(sync_strs) - 1) ? sync_strs[state] : "undef"; +}; + +/* Return enum sync_state for @mddev derived from @recovery flags */ +static const enum sync_state decipher_sync_action(struct mddev *mddev, unsigned long recovery) { if (test_bit(MD_RECOVERY_FROZEN, &recovery)) - return "frozen"; + return st_frozen; - /* The MD sync thread can be done with io but still be running */ + /* The MD sync thread can be done with io or be interrupted but still be running */ if (!test_bit(MD_RECOVERY_DONE, &recovery) && (test_bit(MD_RECOVERY_RUNNING, &recovery) || (!mddev->ro && test_bit(MD_RECOVERY_NEEDED, &recovery)))) { if (test_bit(MD_RECOVERY_RESHAPE, &recovery)) - return "reshape"; + return st_reshape; if (test_bit(MD_RECOVERY_SYNC, &recovery)) { if (!test_bit(MD_RECOVERY_REQUESTED, &recovery)) - return "resync"; - else if (test_bit(MD_RECOVERY_CHECK, &recovery)) - return "check"; - return "repair"; + return st_resync; + if (test_bit(MD_RECOVERY_CHECK, &recovery)) + return st_check; + return st_repair; } if (test_bit(MD_RECOVERY_RECOVER, &recovery)) - return "recover"; + return st_recover; + + if (mddev->reshape_position != MaxSector) + return st_reshape; } - return "idle"; + return st_idle; } /* @@ -3409,6 +3414,7 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery, sector_t resync_max_sectors) { sector_t r; + enum sync_state state; struct mddev *mddev = &rs->md; clear_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags); @@ -3419,20 +3425,14 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery, set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags); } else { - if (!test_bit(__CTR_FLAG_NOSYNC, &rs->ctr_flags) && - !test_bit(MD_RECOVERY_INTR, &recovery) && - (test_bit(MD_RECOVERY_NEEDED, &recovery) || - test_bit(MD_RECOVERY_RESHAPE, &recovery) || - test_bit(MD_RECOVERY_RUNNING, &recovery))) - r = mddev->curr_resync_completed; - else + state = decipher_sync_action(mddev, recovery); + + if (state == st_idle && !test_bit(MD_RECOVERY_INTR, &recovery)) r = mddev->recovery_cp; + else + r = mddev->curr_resync_completed; - if (r >= resync_max_sectors && - (!test_bit(MD_RECOVERY_REQUESTED, &recovery) || - (!test_bit(MD_RECOVERY_FROZEN, &recovery) && - !test_bit(MD_RECOVERY_NEEDED, &recovery) && - !test_bit(MD_RECOVERY_RUNNING, &recovery)))) { + if (state == st_idle && r >= resync_max_sectors) { /* * Sync complete. */ @@ -3440,24 +3440,20 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery, if (test_bit(MD_RECOVERY_RECOVER, &recovery)) set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags); - } else if (test_bit(MD_RECOVERY_RECOVER, &recovery)) { + } else if (state == st_recover) /* * In case we are recovering, the array is not in sync * and health chars should show the recovering legs. */ ; - - } else if (test_bit(MD_RECOVERY_SYNC, &recovery) && - !test_bit(MD_RECOVERY_REQUESTED, &recovery)) { + else if (state == st_resync) /* * If "resync" is occurring, the raid set * is or may be out of sync hence the health * characters shall be 'a'. */ set_bit(RT_FLAG_RS_RESYNCING, &rs->runtime_flags); - - } else if (test_bit(MD_RECOVERY_RESHAPE, &recovery) && - !test_bit(MD_RECOVERY_REQUESTED, &recovery)) { + else if (state == st_reshape) /* * If "reshape" is occurring, the raid set * is or may be out of sync hence the health @@ -3465,7 +3461,7 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery, */ set_bit(RT_FLAG_RS_RESYNCING, &rs->runtime_flags); - } else if (test_bit(MD_RECOVERY_REQUESTED, &recovery)) { + else if (state == st_check || state == st_repair) /* * If "check" or "repair" is occurring, the raid set has * undergone an initial sync and the health characters @@ -3473,12 +3469,12 @@ static sector_t rs_get_progress(struct raid_set *rs, unsigned long recovery, */ set_bit(RT_FLAG_RS_IN_SYNC, &rs->runtime_flags); - } else { + else { struct md_rdev *rdev; /* * We are idle and recovery is needed, prevent 'A' chars race - * caused by components still set to in-sync by constrcuctor. + * caused by components still set to in-sync by constructor. */ if (test_bit(MD_RECOVERY_NEEDED, &recovery)) set_bit(RT_FLAG_RS_RESYNCING, &rs->runtime_flags); @@ -3542,7 +3538,7 @@ static void raid_status(struct dm_target *ti, status_type_t type, progress = rs_get_progress(rs, recovery, resync_max_sectors); resync_mismatches = (mddev->last_sync_action && !strcasecmp(mddev->last_sync_action, "check")) ? atomic64_read(&mddev->resync_mismatches) : 0; - sync_action = decipher_sync_action(&rs->md, recovery); + sync_action = sync_str(decipher_sync_action(&rs->md, recovery)); /* HM FIXME: do we want another state char for raid0? It shows 'D'/'A'/'-' now */ for (i = 0; i < rs->raid_disks; i++) @@ -3892,14 +3888,13 @@ static int rs_start_reshape(struct raid_set *rs) struct mddev *mddev = &rs->md; struct md_personality *pers = mddev->pers; + /* Don't allow the sync thread to work until the table gets reloaded. */ + set_bit(MD_RECOVERY_WAIT, &mddev->recovery); + r = rs_setup_reshape(rs); if (r) return r; - /* Need to be resumed to be able to start reshape, recovery is frozen until raid_resume() though */ - if (test_and_clear_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags)) - mddev_resume(mddev); - /* * Check any reshape constraints enforced by the personalility * @@ -3923,10 +3918,6 @@ static int rs_start_reshape(struct raid_set *rs) } } - /* Suspend because a resume will happen in raid_resume() */ - set_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags); - mddev_suspend(mddev); - /* * Now reshape got set up, update superblocks to * reflect the fact so that a table reload will @@ -3947,29 +3938,6 @@ static int raid_preresume(struct dm_target *ti) if (test_and_set_bit(RT_FLAG_RS_PRERESUMED, &rs->runtime_flags)) return 0; - if (!test_bit(__CTR_FLAG_REBUILD, &rs->ctr_flags)) { - struct raid_set *rs_active = rs_find_active(rs); - - if (rs_active) { - /* - * In case no rebuilds have been requested - * and an active table slot exists, copy - * current resynchonization completed and - * reshape position pointers across from - * suspended raid set in the active slot. - * - * This resumes the new mapping at current - * offsets to continue recover/reshape without - * necessarily redoing a raid set partially or - * causing data corruption in case of a reshape. - */ - if (rs_active->md.curr_resync_completed != MaxSector) - mddev->curr_resync_completed = rs_active->md.curr_resync_completed; - if (rs_active->md.reshape_position != MaxSector) - mddev->reshape_position = rs_active->md.reshape_position; - } - } - /* * The superblocks need to be updated on disk if the * array is new or new devices got added (thus zeroed @@ -4046,7 +4014,7 @@ static void raid_resume(struct dm_target *ti) static struct target_type raid_target = { .name = "raid", - .version = {1, 13, 2}, + .version = {1, 14, 0}, .module = THIS_MODULE, .ctr = raid_ctr, .dtr = raid_dtr, diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index 72142021b5c9..74f6770c70b1 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -189,6 +189,12 @@ struct dm_pool_metadata { sector_t data_block_size; /* + * We reserve a section of the metadata for commit overhead. + * All reported space does *not* include this. + */ + dm_block_t metadata_reserve; + + /* * Set if a transaction has to be aborted but the attempt to roll back * to the previous (good) transaction failed. The only pool metadata * operation possible in this state is the closing of the device. @@ -816,6 +822,22 @@ static int __commit_transaction(struct dm_pool_metadata *pmd) return dm_tm_commit(pmd->tm, sblock); } +static void __set_metadata_reserve(struct dm_pool_metadata *pmd) +{ + int r; + dm_block_t total; + dm_block_t max_blocks = 4096; /* 16M */ + + r = dm_sm_get_nr_blocks(pmd->metadata_sm, &total); + if (r) { + DMERR("could not get size of metadata device"); + pmd->metadata_reserve = max_blocks; + } else { + sector_div(total, 10); + pmd->metadata_reserve = min(max_blocks, total); + } +} + struct dm_pool_metadata *dm_pool_metadata_open(struct block_device *bdev, sector_t data_block_size, bool format_device) @@ -849,6 +871,8 @@ struct dm_pool_metadata *dm_pool_metadata_open(struct block_device *bdev, return ERR_PTR(r); } + __set_metadata_reserve(pmd); + return pmd; } @@ -1820,6 +1844,13 @@ int dm_pool_get_free_metadata_block_count(struct dm_pool_metadata *pmd, down_read(&pmd->root_lock); if (!pmd->fail_io) r = dm_sm_get_nr_free(pmd->metadata_sm, result); + + if (!r) { + if (*result < pmd->metadata_reserve) + *result = 0; + else + *result -= pmd->metadata_reserve; + } up_read(&pmd->root_lock); return r; @@ -1932,8 +1963,11 @@ int dm_pool_resize_metadata_dev(struct dm_pool_metadata *pmd, dm_block_t new_cou int r = -EINVAL; down_write(&pmd->root_lock); - if (!pmd->fail_io) + if (!pmd->fail_io) { r = __resize_space_map(pmd->metadata_sm, new_count); + if (!r) + __set_metadata_reserve(pmd); + } up_write(&pmd->root_lock); return r; diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 7bd60a150f8f..aaf1ad481ee8 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -200,7 +200,13 @@ struct dm_thin_new_mapping; enum pool_mode { PM_WRITE, /* metadata may be changed */ PM_OUT_OF_DATA_SPACE, /* metadata may be changed, though data may not be allocated */ + + /* + * Like READ_ONLY, except may switch back to WRITE on metadata resize. Reported as READ_ONLY. + */ + PM_OUT_OF_METADATA_SPACE, PM_READ_ONLY, /* metadata may not be changed */ + PM_FAIL, /* all I/O fails */ }; @@ -1371,7 +1377,35 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode); static void requeue_bios(struct pool *pool); -static void check_for_space(struct pool *pool) +static bool is_read_only_pool_mode(enum pool_mode mode) +{ + return (mode == PM_OUT_OF_METADATA_SPACE || mode == PM_READ_ONLY); +} + +static bool is_read_only(struct pool *pool) +{ + return is_read_only_pool_mode(get_pool_mode(pool)); +} + +static void check_for_metadata_space(struct pool *pool) +{ + int r; + const char *ooms_reason = NULL; + dm_block_t nr_free; + + r = dm_pool_get_free_metadata_block_count(pool->pmd, &nr_free); + if (r) + ooms_reason = "Could not get free metadata blocks"; + else if (!nr_free) + ooms_reason = "No free metadata blocks"; + + if (ooms_reason && !is_read_only(pool)) { + DMERR("%s", ooms_reason); + set_pool_mode(pool, PM_OUT_OF_METADATA_SPACE); + } +} + +static void check_for_data_space(struct pool *pool) { int r; dm_block_t nr_free; @@ -1397,14 +1431,16 @@ static int commit(struct pool *pool) { int r; - if (get_pool_mode(pool) >= PM_READ_ONLY) + if (get_pool_mode(pool) >= PM_OUT_OF_METADATA_SPACE) return -EINVAL; r = dm_pool_commit_metadata(pool->pmd); if (r) metadata_operation_failed(pool, "dm_pool_commit_metadata", r); - else - check_for_space(pool); + else { + check_for_metadata_space(pool); + check_for_data_space(pool); + } return r; } @@ -1470,6 +1506,19 @@ static int alloc_data_block(struct thin_c *tc, dm_block_t *result) return r; } + r = dm_pool_get_free_metadata_block_count(pool->pmd, &free_blocks); + if (r) { + metadata_operation_failed(pool, "dm_pool_get_free_metadata_block_count", r); + return r; + } + + if (!free_blocks) { + /* Let's commit before we use up the metadata reserve. */ + r = commit(pool); + if (r) + return r; + } + return 0; } @@ -1501,6 +1550,7 @@ static blk_status_t should_error_unserviceable_bio(struct pool *pool) case PM_OUT_OF_DATA_SPACE: return pool->pf.error_if_no_space ? BLK_STS_NOSPC : 0; + case PM_OUT_OF_METADATA_SPACE: case PM_READ_ONLY: case PM_FAIL: return BLK_STS_IOERR; @@ -2464,8 +2514,9 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode) error_retry_list(pool); break; + case PM_OUT_OF_METADATA_SPACE: case PM_READ_ONLY: - if (old_mode != new_mode) + if (!is_read_only_pool_mode(old_mode)) notify_of_pool_mode_change(pool, "read-only"); dm_pool_metadata_read_only(pool->pmd); pool->process_bio = process_bio_read_only; @@ -3403,6 +3454,10 @@ static int maybe_resize_metadata_dev(struct dm_target *ti, bool *need_commit) DMINFO("%s: growing the metadata device from %llu to %llu blocks", dm_device_name(pool->pool_md), sb_metadata_dev_size, metadata_dev_size); + + if (get_pool_mode(pool) == PM_OUT_OF_METADATA_SPACE) + set_pool_mode(pool, PM_WRITE); + r = dm_pool_resize_metadata_dev(pool->pmd, metadata_dev_size); if (r) { metadata_operation_failed(pool, "dm_pool_resize_metadata_dev", r); @@ -3707,7 +3762,7 @@ static int pool_message(struct dm_target *ti, unsigned argc, char **argv, struct pool_c *pt = ti->private; struct pool *pool = pt->pool; - if (get_pool_mode(pool) >= PM_READ_ONLY) { + if (get_pool_mode(pool) >= PM_OUT_OF_METADATA_SPACE) { DMERR("%s: unable to service pool target messages in READ_ONLY or FAIL mode", dm_device_name(pool->pool_md)); return -EOPNOTSUPP; @@ -3781,6 +3836,7 @@ static void pool_status(struct dm_target *ti, status_type_t type, dm_block_t nr_blocks_data; dm_block_t nr_blocks_metadata; dm_block_t held_root; + enum pool_mode mode; char buf[BDEVNAME_SIZE]; char buf2[BDEVNAME_SIZE]; struct pool_c *pt = ti->private; @@ -3851,9 +3907,10 @@ static void pool_status(struct dm_target *ti, status_type_t type, else DMEMIT("- "); - if (pool->pf.mode == PM_OUT_OF_DATA_SPACE) + mode = get_pool_mode(pool); + if (mode == PM_OUT_OF_DATA_SPACE) DMEMIT("out_of_data_space "); - else if (pool->pf.mode == PM_READ_ONLY) + else if (is_read_only_pool_mode(mode)) DMEMIT("ro "); else DMEMIT("rw "); diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index 12decdbd722d..fc65f0dedf7f 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -99,10 +99,26 @@ static int verity_hash_update(struct dm_verity *v, struct ahash_request *req, { struct scatterlist sg; - sg_init_one(&sg, data, len); - ahash_request_set_crypt(req, &sg, NULL, len); - - return crypto_wait_req(crypto_ahash_update(req), wait); + if (likely(!is_vmalloc_addr(data))) { + sg_init_one(&sg, data, len); + ahash_request_set_crypt(req, &sg, NULL, len); + return crypto_wait_req(crypto_ahash_update(req), wait); + } else { + do { + int r; + size_t this_step = min_t(size_t, len, PAGE_SIZE - offset_in_page(data)); + flush_kernel_vmap_range((void *)data, this_step); + sg_init_table(&sg, 1); + sg_set_page(&sg, vmalloc_to_page(data), this_step, offset_in_page(data)); + ahash_request_set_crypt(req, &sg, NULL, this_step); + r = crypto_wait_req(crypto_ahash_update(req), wait); + if (unlikely(r)) + return r; + data += this_step; + len -= this_step; + } while (len); + return 0; + } } /* diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c index 94329e03001e..0b2af6e74fc3 100644 --- a/drivers/md/md-cluster.c +++ b/drivers/md/md-cluster.c @@ -1276,18 +1276,18 @@ static int resync_info_update(struct mddev *mddev, sector_t lo, sector_t hi) static int resync_finish(struct mddev *mddev) { struct md_cluster_info *cinfo = mddev->cluster_info; + int ret = 0; clear_bit(MD_RESYNCING_REMOTE, &mddev->recovery); - dlm_unlock_sync(cinfo->resync_lockres); /* * If resync thread is interrupted so we can't say resync is finished, * another node will launch resync thread to continue. */ - if (test_bit(MD_CLOSING, &mddev->flags)) - return 0; - else - return resync_info_update(mddev, 0, 0); + if (!test_bit(MD_CLOSING, &mddev->flags)) + ret = resync_info_update(mddev, 0, 0); + dlm_unlock_sync(cinfo->resync_lockres); + return ret; } static int area_resyncing(struct mddev *mddev, int direction, diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 981898049491..d6f7978b4449 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -4529,11 +4529,12 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, allow_barrier(conf); } + raise_barrier(conf, 0); read_more: /* Now schedule reads for blocks from sector_nr to last */ r10_bio = raid10_alloc_init_r10buf(conf); r10_bio->state = 0; - raise_barrier(conf, sectors_done != 0); + raise_barrier(conf, 1); atomic_set(&r10_bio->remaining, 0); r10_bio->mddev = mddev; r10_bio->sector = sector_nr; @@ -4629,6 +4630,8 @@ read_more: if (sector_nr <= last) goto read_more; + lower_barrier(conf); + /* Now that we have done the whole section we can * update reshape_progress */ diff --git a/drivers/md/raid5-log.h b/drivers/md/raid5-log.h index a001808a2b77..bfb811407061 100644 --- a/drivers/md/raid5-log.h +++ b/drivers/md/raid5-log.h @@ -46,6 +46,11 @@ extern int ppl_modify_log(struct r5conf *conf, struct md_rdev *rdev, bool add); extern void ppl_quiesce(struct r5conf *conf, int quiesce); extern int ppl_handle_flush_request(struct r5l_log *log, struct bio *bio); +static inline bool raid5_has_log(struct r5conf *conf) +{ + return test_bit(MD_HAS_JOURNAL, &conf->mddev->flags); +} + static inline bool raid5_has_ppl(struct r5conf *conf) { return test_bit(MD_HAS_PPL, &conf->mddev->flags); diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 4ce0d7502fad..e4e98f47865d 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -733,7 +733,7 @@ static bool stripe_can_batch(struct stripe_head *sh) { struct r5conf *conf = sh->raid_conf; - if (conf->log || raid5_has_ppl(conf)) + if (raid5_has_log(conf) || raid5_has_ppl(conf)) return false; return test_bit(STRIPE_BATCH_READY, &sh->state) && !test_bit(STRIPE_BITMAP_PENDING, &sh->state) && @@ -7737,7 +7737,7 @@ static int raid5_resize(struct mddev *mddev, sector_t sectors) sector_t newsize; struct r5conf *conf = mddev->private; - if (conf->log || raid5_has_ppl(conf)) + if (raid5_has_log(conf) || raid5_has_ppl(conf)) return -EINVAL; sectors &= ~((sector_t)conf->chunk_sectors - 1); newsize = raid5_size(mddev, sectors, mddev->raid_disks); @@ -7788,7 +7788,7 @@ static int check_reshape(struct mddev *mddev) { struct r5conf *conf = mddev->private; - if (conf->log || raid5_has_ppl(conf)) + if (raid5_has_log(conf) || raid5_has_ppl(conf)) return -EINVAL; if (mddev->delta_disks == 0 && mddev->new_layout == mddev->layout && diff --git a/drivers/memory/ti-aemif.c b/drivers/memory/ti-aemif.c index 31112f622b88..475e5b3790ed 100644 --- a/drivers/memory/ti-aemif.c +++ b/drivers/memory/ti-aemif.c @@ -411,7 +411,7 @@ static int aemif_probe(struct platform_device *pdev) if (ret < 0) goto error; } - } else { + } else if (pdata) { for (i = 0; i < pdata->num_sub_devices; i++) { pdata->sub_devices[i].dev.parent = dev; ret = platform_device_register(&pdata->sub_devices[i]); diff --git a/drivers/misc/hmc6352.c b/drivers/misc/hmc6352.c index eeb7eef62174..38f90e179927 100644 --- a/drivers/misc/hmc6352.c +++ b/drivers/misc/hmc6352.c @@ -27,6 +27,7 @@ #include <linux/err.h> #include <linux/delay.h> #include <linux/sysfs.h> +#include <linux/nospec.h> static DEFINE_MUTEX(compass_mutex); @@ -50,6 +51,7 @@ static int compass_store(struct device *dev, const char *buf, size_t count, return ret; if (val >= strlen(map)) return -EINVAL; + val = array_index_nospec(val, strlen(map)); mutex_lock(&compass_mutex); ret = compass_command(c, map[val]); mutex_unlock(&compass_mutex); diff --git a/drivers/misc/ibmvmc.c b/drivers/misc/ibmvmc.c index 8f82bb9d11e2..b8aaa684c397 100644 --- a/drivers/misc/ibmvmc.c +++ b/drivers/misc/ibmvmc.c @@ -2131,7 +2131,7 @@ static int ibmvmc_init_crq_queue(struct crq_server_adapter *adapter) retrc = plpar_hcall_norets(H_REG_CRQ, vdev->unit_address, queue->msg_token, PAGE_SIZE); - retrc = rc; + rc = retrc; if (rc == H_RESOURCE) rc = ibmvmc_reset_crq_queue(adapter); diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c index 7bba62a72921..fc3872fe7b25 100644 --- a/drivers/misc/mei/bus.c +++ b/drivers/misc/mei/bus.c @@ -521,17 +521,15 @@ int mei_cldev_enable(struct mei_cl_device *cldev) cl = cldev->cl; + mutex_lock(&bus->device_lock); if (cl->state == MEI_FILE_UNINITIALIZED) { - mutex_lock(&bus->device_lock); ret = mei_cl_link(cl); - mutex_unlock(&bus->device_lock); if (ret) - return ret; + goto out; /* update pointers */ cl->cldev = cldev; } - mutex_lock(&bus->device_lock); if (mei_cl_is_connected(cl)) { ret = 0; goto out; @@ -616,9 +614,8 @@ int mei_cldev_disable(struct mei_cl_device *cldev) if (err < 0) dev_err(bus->dev, "Could not disconnect from the ME client\n"); -out: mei_cl_bus_module_put(cldev); - +out: /* Flush queues and remove any pending read */ mei_cl_flush_queues(cl, NULL); mei_cl_unlink(cl); @@ -876,12 +873,13 @@ static void mei_cl_bus_dev_release(struct device *dev) mei_me_cl_put(cldev->me_cl); mei_dev_bus_put(cldev->bus); + mei_cl_unlink(cldev->cl); kfree(cldev->cl); kfree(cldev); } static const struct device_type mei_cl_device_type = { - .release = mei_cl_bus_dev_release, + .release = mei_cl_bus_dev_release, }; /** diff --git a/drivers/misc/mei/client.c b/drivers/misc/mei/client.c index 4ab6251d418e..ebdcf0b450e2 100644 --- a/drivers/misc/mei/client.c +++ b/drivers/misc/mei/client.c @@ -1767,7 +1767,7 @@ out: } } - rets = buf->size; + rets = len; err: cl_dbg(dev, cl, "rpm: autosuspend\n"); pm_runtime_mark_last_busy(dev->dev); diff --git a/drivers/misc/mei/hbm.c b/drivers/misc/mei/hbm.c index 09e233d4c0de..e56f3e72d57a 100644 --- a/drivers/misc/mei/hbm.c +++ b/drivers/misc/mei/hbm.c @@ -1161,15 +1161,18 @@ int mei_hbm_dispatch(struct mei_device *dev, struct mei_msg_hdr *hdr) props_res = (struct hbm_props_response *)mei_msg; - if (props_res->status) { + if (props_res->status == MEI_HBMS_CLIENT_NOT_FOUND) { + dev_dbg(dev->dev, "hbm: properties response: %d CLIENT_NOT_FOUND\n", + props_res->me_addr); + } else if (props_res->status) { dev_err(dev->dev, "hbm: properties response: wrong status = %d %s\n", props_res->status, mei_hbm_status_str(props_res->status)); return -EPROTO; + } else { + mei_hbm_me_cl_add(dev, props_res); } - mei_hbm_me_cl_add(dev, props_res); - /* request property for the next client */ if (mei_hbm_prop_req(dev, props_res->me_addr + 1)) return -EIO; diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c index 648eb6743ed5..6edffeed9953 100644 --- a/drivers/mmc/core/queue.c +++ b/drivers/mmc/core/queue.c @@ -238,10 +238,6 @@ static void mmc_mq_exit_request(struct blk_mq_tag_set *set, struct request *req, mmc_exit_request(mq->queue, req); } -/* - * We use BLK_MQ_F_BLOCKING and have only 1 hardware queue, which means requests - * will not be dispatched in parallel. - */ static blk_status_t mmc_mq_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { @@ -264,7 +260,7 @@ static blk_status_t mmc_mq_queue_rq(struct blk_mq_hw_ctx *hctx, spin_lock_irq(q->queue_lock); - if (mq->recovery_needed) { + if (mq->recovery_needed || mq->busy) { spin_unlock_irq(q->queue_lock); return BLK_STS_RESOURCE; } @@ -291,6 +287,9 @@ static blk_status_t mmc_mq_queue_rq(struct blk_mq_hw_ctx *hctx, break; } + /* Parallel dispatch of requests is not supported at the moment */ + mq->busy = true; + mq->in_flight[issue_type] += 1; get_card = (mmc_tot_in_flight(mq) == 1); cqe_retune_ok = (mmc_cqe_qcnt(mq) == 1); @@ -333,9 +332,12 @@ static blk_status_t mmc_mq_queue_rq(struct blk_mq_hw_ctx *hctx, mq->in_flight[issue_type] -= 1; if (mmc_tot_in_flight(mq) == 0) put_card = true; + mq->busy = false; spin_unlock_irq(q->queue_lock); if (put_card) mmc_put_card(card, &mq->ctx); + } else { + WRITE_ONCE(mq->busy, false); } return ret; diff --git a/drivers/mmc/core/queue.h b/drivers/mmc/core/queue.h index 17e59d50b496..9bf3c9245075 100644 --- a/drivers/mmc/core/queue.h +++ b/drivers/mmc/core/queue.h @@ -81,6 +81,7 @@ struct mmc_queue { unsigned int cqe_busy; #define MMC_CQE_DCMD_BUSY BIT(0) #define MMC_CQE_QUEUE_FULL BIT(1) + bool busy; bool use_cqe; bool recovery_needed; bool in_recovery; diff --git a/drivers/mmc/host/android-goldfish.c b/drivers/mmc/host/android-goldfish.c index 294de177632c..61e4e2a213c9 100644 --- a/drivers/mmc/host/android-goldfish.c +++ b/drivers/mmc/host/android-goldfish.c @@ -217,7 +217,7 @@ static void goldfish_mmc_xfer_done(struct goldfish_mmc_host *host, * We don't really have DMA, so we need * to copy from our platform driver buffer */ - sg_copy_to_buffer(data->sg, 1, host->virt_base, + sg_copy_from_buffer(data->sg, 1, host->virt_base, data->sg->length); } host->data->bytes_xfered += data->sg->length; @@ -393,7 +393,7 @@ static void goldfish_mmc_prepare_data(struct goldfish_mmc_host *host, * We don't really have DMA, so we need to copy to our * platform driver buffer */ - sg_copy_from_buffer(data->sg, 1, host->virt_base, + sg_copy_to_buffer(data->sg, 1, host->virt_base, data->sg->length); } } diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c index 5aa2c9404e92..be53044086c7 100644 --- a/drivers/mmc/host/atmel-mci.c +++ b/drivers/mmc/host/atmel-mci.c @@ -1976,7 +1976,7 @@ static void atmci_read_data_pio(struct atmel_mci *host) do { value = atmci_readl(host, ATMCI_RDR); if (likely(offset + 4 <= sg->length)) { - sg_pcopy_to_buffer(sg, 1, &value, sizeof(u32), offset); + sg_pcopy_from_buffer(sg, 1, &value, sizeof(u32), offset); offset += 4; nbytes += 4; @@ -1993,7 +1993,7 @@ static void atmci_read_data_pio(struct atmel_mci *host) } else { unsigned int remaining = sg->length - offset; - sg_pcopy_to_buffer(sg, 1, &value, remaining, offset); + sg_pcopy_from_buffer(sg, 1, &value, remaining, offset); nbytes += remaining; flush_dcache_page(sg_page(sg)); @@ -2003,7 +2003,7 @@ static void atmci_read_data_pio(struct atmel_mci *host) goto done; offset = 4 - remaining; - sg_pcopy_to_buffer(sg, 1, (u8 *)&value + remaining, + sg_pcopy_from_buffer(sg, 1, (u8 *)&value + remaining, offset, 0); nbytes += offset; } @@ -2042,7 +2042,7 @@ static void atmci_write_data_pio(struct atmel_mci *host) do { if (likely(offset + 4 <= sg->length)) { - sg_pcopy_from_buffer(sg, 1, &value, sizeof(u32), offset); + sg_pcopy_to_buffer(sg, 1, &value, sizeof(u32), offset); atmci_writel(host, ATMCI_TDR, value); offset += 4; @@ -2059,7 +2059,7 @@ static void atmci_write_data_pio(struct atmel_mci *host) unsigned int remaining = sg->length - offset; value = 0; - sg_pcopy_from_buffer(sg, 1, &value, remaining, offset); + sg_pcopy_to_buffer(sg, 1, &value, remaining, offset); nbytes += remaining; host->sg = sg = sg_next(sg); @@ -2070,7 +2070,7 @@ static void atmci_write_data_pio(struct atmel_mci *host) } offset = 4 - remaining; - sg_pcopy_from_buffer(sg, 1, (u8 *)&value + remaining, + sg_pcopy_to_buffer(sg, 1, (u8 *)&value + remaining, offset, 0); atmci_writel(host, ATMCI_TDR, value); nbytes += offset; diff --git a/drivers/mmc/host/meson-mx-sdio.c b/drivers/mmc/host/meson-mx-sdio.c index 09cb89645d06..2cfec33178c1 100644 --- a/drivers/mmc/host/meson-mx-sdio.c +++ b/drivers/mmc/host/meson-mx-sdio.c @@ -517,19 +517,23 @@ static struct mmc_host_ops meson_mx_mmc_ops = { static struct platform_device *meson_mx_mmc_slot_pdev(struct device *parent) { struct device_node *slot_node; + struct platform_device *pdev; /* * TODO: the MMC core framework currently does not support * controllers with multiple slots properly. So we only register * the first slot for now */ - slot_node = of_find_compatible_node(parent->of_node, NULL, "mmc-slot"); + slot_node = of_get_compatible_child(parent->of_node, "mmc-slot"); if (!slot_node) { dev_warn(parent, "no 'mmc-slot' sub-node found\n"); return ERR_PTR(-ENOENT); } - return of_platform_device_create(slot_node, NULL, parent); + pdev = of_platform_device_create(slot_node, NULL, parent); + of_node_put(slot_node); + + return pdev; } static int meson_mx_mmc_add_host(struct meson_mx_mmc_host *host) diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c index 071693ebfe18..68760d4a5d3d 100644 --- a/drivers/mmc/host/omap_hsmmc.c +++ b/drivers/mmc/host/omap_hsmmc.c @@ -2177,6 +2177,7 @@ static int omap_hsmmc_remove(struct platform_device *pdev) dma_release_channel(host->tx_chan); dma_release_channel(host->rx_chan); + dev_pm_clear_wake_irq(host->dev); pm_runtime_dont_use_autosuspend(host->dev); pm_runtime_put_sync(host->dev); pm_runtime_disable(host->dev); diff --git a/drivers/mmc/host/renesas_sdhi_internal_dmac.c b/drivers/mmc/host/renesas_sdhi_internal_dmac.c index 35cc0de6be67..ca0b43973769 100644 --- a/drivers/mmc/host/renesas_sdhi_internal_dmac.c +++ b/drivers/mmc/host/renesas_sdhi_internal_dmac.c @@ -45,14 +45,16 @@ /* DM_CM_RST */ #define RST_DTRANRST1 BIT(9) #define RST_DTRANRST0 BIT(8) -#define RST_RESERVED_BITS GENMASK_ULL(32, 0) +#define RST_RESERVED_BITS GENMASK_ULL(31, 0) /* DM_CM_INFO1 and DM_CM_INFO1_MASK */ #define INFO1_CLEAR 0 +#define INFO1_MASK_CLEAR GENMASK_ULL(31, 0) #define INFO1_DTRANEND1 BIT(17) #define INFO1_DTRANEND0 BIT(16) /* DM_CM_INFO2 and DM_CM_INFO2_MASK */ +#define INFO2_MASK_CLEAR GENMASK_ULL(31, 0) #define INFO2_DTRANERR1 BIT(17) #define INFO2_DTRANERR0 BIT(16) @@ -252,6 +254,12 @@ renesas_sdhi_internal_dmac_request_dma(struct tmio_mmc_host *host, { struct renesas_sdhi *priv = host_to_priv(host); + /* Disable DMAC interrupts, we don't use them */ + renesas_sdhi_internal_dmac_dm_write(host, DM_CM_INFO1_MASK, + INFO1_MASK_CLEAR); + renesas_sdhi_internal_dmac_dm_write(host, DM_CM_INFO2_MASK, + INFO2_MASK_CLEAR); + /* Each value is set to non-zero to assume "enabling" each DMA */ host->chan_rx = host->chan_tx = (void *)0xdeadbeaf; diff --git a/drivers/mtd/nand/raw/denali.c b/drivers/mtd/nand/raw/denali.c index ca18612c4201..67b2065e7a19 100644 --- a/drivers/mtd/nand/raw/denali.c +++ b/drivers/mtd/nand/raw/denali.c @@ -1338,6 +1338,11 @@ int denali_init(struct denali_nand_info *denali) denali_enable_irq(denali); denali_reset_banks(denali); + if (!denali->max_banks) { + /* Error out earlier if no chip is found for some reasons. */ + ret = -ENODEV; + goto disable_irq; + } denali->active_bank = DENALI_INVALID_BANK; diff --git a/drivers/mtd/nand/raw/docg4.c b/drivers/mtd/nand/raw/docg4.c index a3f04315c05c..427fcbc1b71c 100644 --- a/drivers/mtd/nand/raw/docg4.c +++ b/drivers/mtd/nand/raw/docg4.c @@ -1218,7 +1218,7 @@ static int docg4_resume(struct platform_device *pdev) return 0; } -static void __init init_mtd_structs(struct mtd_info *mtd) +static void init_mtd_structs(struct mtd_info *mtd) { /* initialize mtd and nand data structures */ @@ -1290,7 +1290,7 @@ static void __init init_mtd_structs(struct mtd_info *mtd) } -static int __init read_id_reg(struct mtd_info *mtd) +static int read_id_reg(struct mtd_info *mtd) { struct nand_chip *nand = mtd_to_nand(mtd); struct docg4_priv *doc = nand_get_controller_data(nand); diff --git a/drivers/net/appletalk/ipddp.c b/drivers/net/appletalk/ipddp.c index 9375cef22420..3d27616d9c85 100644 --- a/drivers/net/appletalk/ipddp.c +++ b/drivers/net/appletalk/ipddp.c @@ -283,8 +283,12 @@ static int ipddp_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCFINDIPDDPRT: spin_lock_bh(&ipddp_route_lock); rp = __ipddp_find_route(&rcp); - if (rp) - memcpy(&rcp2, rp, sizeof(rcp2)); + if (rp) { + memset(&rcp2, 0, sizeof(rcp2)); + rcp2.ip = rp->ip; + rcp2.at = rp->at; + rcp2.flags = rp->flags; + } spin_unlock_bh(&ipddp_route_lock); if (rp) { diff --git a/drivers/net/can/rx-offload.c b/drivers/net/can/rx-offload.c index d94dae216820..c7d05027a7a0 100644 --- a/drivers/net/can/rx-offload.c +++ b/drivers/net/can/rx-offload.c @@ -79,7 +79,7 @@ static int can_rx_offload_napi_poll(struct napi_struct *napi, int quota) static inline void __skb_queue_add_sort(struct sk_buff_head *head, struct sk_buff *new, int (*compare)(struct sk_buff *a, struct sk_buff *b)) { - struct sk_buff *pos, *insert = (struct sk_buff *)head; + struct sk_buff *pos, *insert = NULL; skb_queue_reverse_walk(head, pos) { const struct can_rx_offload_cb *cb_pos, *cb_new; @@ -99,8 +99,10 @@ static inline void __skb_queue_add_sort(struct sk_buff_head *head, struct sk_buf insert = pos; break; } - - __skb_queue_after(head, insert, new); + if (!insert) + __skb_queue_head(head, new); + else + __skb_queue_after(head, insert, new); } static int can_rx_offload_compare(struct sk_buff *a, struct sk_buff *b) diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig index d3ce1e4cb4d3..7c09d8f195ae 100644 --- a/drivers/net/dsa/Kconfig +++ b/drivers/net/dsa/Kconfig @@ -23,6 +23,14 @@ config NET_DSA_LOOP This enables support for a fake mock-up switch chip which exercises the DSA APIs. +config NET_DSA_LANTIQ_GSWIP + tristate "Lantiq / Intel GSWIP" + depends on NET_DSA + select NET_DSA_TAG_GSWIP + ---help--- + This enables support for the Lantiq / Intel GSWIP 2.1 found in + the xrx200 / VR9 SoC. + config NET_DSA_MT7530 tristate "Mediatek MT7530 Ethernet switch support" depends on NET_DSA diff --git a/drivers/net/dsa/Makefile b/drivers/net/dsa/Makefile index 46c1cba91ffe..82e5d794c41f 100644 --- a/drivers/net/dsa/Makefile +++ b/drivers/net/dsa/Makefile @@ -5,6 +5,7 @@ obj-$(CONFIG_NET_DSA_LOOP) += dsa_loop.o ifdef CONFIG_NET_DSA_LOOP obj-$(CONFIG_FIXED_PHY) += dsa_loop_bdinfo.o endif +obj-$(CONFIG_NET_DSA_LANTIQ_GSWIP) += lantiq_gswip.o obj-$(CONFIG_NET_DSA_MT7530) += mt7530.o obj-$(CONFIG_NET_DSA_MV88E6060) += mv88e6060.o obj-$(CONFIG_NET_DSA_QCA8K) += qca8k.o diff --git a/drivers/net/dsa/b53/Kconfig b/drivers/net/dsa/b53/Kconfig index 2f988216dab9..e83ebfafd881 100644 --- a/drivers/net/dsa/b53/Kconfig +++ b/drivers/net/dsa/b53/Kconfig @@ -23,6 +23,7 @@ config B53_MDIO_DRIVER config B53_MMAP_DRIVER tristate "B53 MMAP connected switch driver" depends on B53 && HAS_IOMEM + default BCM63XX || BMIPS_GENERIC help Select to enable support for memory-mapped switches like the BCM63XX integrated switches. @@ -30,6 +31,14 @@ config B53_MMAP_DRIVER config B53_SRAB_DRIVER tristate "B53 SRAB connected switch driver" depends on B53 && HAS_IOMEM + default ARCH_BCM_IPROC help Select to enable support for memory-mapped Switch Register Access Bridge Registers (SRAB) like it is found on the BCM53010 + +config B53_SERDES + tristate "B53 SerDes support" + depends on B53 + default ARCH_BCM_NSP + help + Select to enable support for SerDes on e.g: Northstar Plus SoCs. diff --git a/drivers/net/dsa/b53/Makefile b/drivers/net/dsa/b53/Makefile index 4256fb42a4dd..b1be13023ae4 100644 --- a/drivers/net/dsa/b53/Makefile +++ b/drivers/net/dsa/b53/Makefile @@ -5,3 +5,4 @@ obj-$(CONFIG_B53_SPI_DRIVER) += b53_spi.o obj-$(CONFIG_B53_MDIO_DRIVER) += b53_mdio.o obj-$(CONFIG_B53_MMAP_DRIVER) += b53_mmap.o obj-$(CONFIG_B53_SRAB_DRIVER) += b53_srab.o +obj-$(CONFIG_B53_SERDES) += b53_serdes.o diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index d93c790bfbe8..dbf5b86a07fe 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -26,6 +26,7 @@ #include <linux/module.h> #include <linux/platform_data/b53.h> #include <linux/phy.h> +#include <linux/phylink.h> #include <linux/etherdevice.h> #include <linux/if_bridge.h> #include <net/dsa.h> @@ -502,8 +503,14 @@ int b53_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy) { struct b53_device *dev = ds->priv; unsigned int cpu_port = ds->ports[port].cpu_dp->index; + int ret = 0; u16 pvlan; + if (dev->ops->irq_enable) + ret = dev->ops->irq_enable(dev, port); + if (ret) + return ret; + /* Clear the Rx and Tx disable bits and set to no spanning tree */ b53_write8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(port), 0); @@ -536,6 +543,9 @@ void b53_disable_port(struct dsa_switch *ds, int port, struct phy_device *phy) b53_read8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(port), ®); reg |= PORT_CTRL_RX_DISABLE | PORT_CTRL_TX_DISABLE; b53_write8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(port), reg); + + if (dev->ops->irq_disable) + dev->ops->irq_disable(dev, port); } EXPORT_SYMBOL(b53_disable_port); @@ -755,6 +765,8 @@ static int b53_reset_switch(struct b53_device *priv) memset(priv->vlans, 0, sizeof(*priv->vlans) * priv->num_vlans); memset(priv->ports, 0, sizeof(*priv->ports) * priv->num_ports); + priv->serdes_lane = B53_INVALID_LANE; + return b53_switch_reset(priv); } @@ -938,33 +950,50 @@ static int b53_setup(struct dsa_switch *ds) return ret; } -static void b53_adjust_link(struct dsa_switch *ds, int port, - struct phy_device *phydev) +static void b53_force_link(struct b53_device *dev, int port, int link) { - struct b53_device *dev = ds->priv; - struct ethtool_eee *p = &dev->ports[port].eee; - u8 rgmii_ctrl = 0, reg = 0, off; - - if (!phy_is_pseudo_fixed_link(phydev)) - return; + u8 reg, val, off; /* Override the port settings */ if (port == dev->cpu_port) { off = B53_PORT_OVERRIDE_CTRL; - reg = PORT_OVERRIDE_EN; + val = PORT_OVERRIDE_EN; } else { off = B53_GMII_PORT_OVERRIDE_CTRL(port); - reg = GMII_PO_EN; + val = GMII_PO_EN; } - /* Set the link UP */ - if (phydev->link) + b53_read8(dev, B53_CTRL_PAGE, off, ®); + reg |= val; + if (link) reg |= PORT_OVERRIDE_LINK; + else + reg &= ~PORT_OVERRIDE_LINK; + b53_write8(dev, B53_CTRL_PAGE, off, reg); +} - if (phydev->duplex == DUPLEX_FULL) +static void b53_force_port_config(struct b53_device *dev, int port, + int speed, int duplex, int pause) +{ + u8 reg, val, off; + + /* Override the port settings */ + if (port == dev->cpu_port) { + off = B53_PORT_OVERRIDE_CTRL; + val = PORT_OVERRIDE_EN; + } else { + off = B53_GMII_PORT_OVERRIDE_CTRL(port); + val = GMII_PO_EN; + } + + b53_read8(dev, B53_CTRL_PAGE, off, ®); + reg |= val; + if (duplex == DUPLEX_FULL) reg |= PORT_OVERRIDE_FULL_DUPLEX; + else + reg &= ~PORT_OVERRIDE_FULL_DUPLEX; - switch (phydev->speed) { + switch (speed) { case 2000: reg |= PORT_OVERRIDE_SPEED_2000M; /* fallthrough */ @@ -978,21 +1007,41 @@ static void b53_adjust_link(struct dsa_switch *ds, int port, reg |= PORT_OVERRIDE_SPEED_10M; break; default: - dev_err(ds->dev, "unknown speed: %d\n", phydev->speed); + dev_err(dev->dev, "unknown speed: %d\n", speed); return; } + if (pause & MLO_PAUSE_RX) + reg |= PORT_OVERRIDE_RX_FLOW; + if (pause & MLO_PAUSE_TX) + reg |= PORT_OVERRIDE_TX_FLOW; + + b53_write8(dev, B53_CTRL_PAGE, off, reg); +} + +static void b53_adjust_link(struct dsa_switch *ds, int port, + struct phy_device *phydev) +{ + struct b53_device *dev = ds->priv; + struct ethtool_eee *p = &dev->ports[port].eee; + u8 rgmii_ctrl = 0, reg = 0, off; + int pause = 0; + + if (!phy_is_pseudo_fixed_link(phydev)) + return; + /* Enable flow control on BCM5301x's CPU port */ if (is5301x(dev) && port == dev->cpu_port) - reg |= PORT_OVERRIDE_RX_FLOW | PORT_OVERRIDE_TX_FLOW; + pause = MLO_PAUSE_TXRX_MASK; if (phydev->pause) { if (phydev->asym_pause) - reg |= PORT_OVERRIDE_TX_FLOW; - reg |= PORT_OVERRIDE_RX_FLOW; + pause |= MLO_PAUSE_TX; + pause |= MLO_PAUSE_RX; } - b53_write8(dev, B53_CTRL_PAGE, off, reg); + b53_force_port_config(dev, port, phydev->speed, phydev->duplex, pause); + b53_force_link(dev, port, phydev->link); if (is531x5(dev) && phy_interface_is_rgmii(phydev)) { if (port == 8) @@ -1052,16 +1101,9 @@ static void b53_adjust_link(struct dsa_switch *ds, int port, } } else if (is5301x(dev)) { if (port != dev->cpu_port) { - u8 po_reg = B53_GMII_PORT_OVERRIDE_CTRL(dev->cpu_port); - u8 gmii_po; - - b53_read8(dev, B53_CTRL_PAGE, po_reg, &gmii_po); - gmii_po |= GMII_PO_LINK | - GMII_PO_RX_FLOW | - GMII_PO_TX_FLOW | - GMII_PO_EN | - GMII_PO_SPEED_2000M; - b53_write8(dev, B53_CTRL_PAGE, po_reg, gmii_po); + b53_force_port_config(dev, dev->cpu_port, 2000, + DUPLEX_FULL, MLO_PAUSE_TXRX_MASK); + b53_force_link(dev, dev->cpu_port, 1); } } @@ -1069,6 +1111,146 @@ static void b53_adjust_link(struct dsa_switch *ds, int port, p->eee_enabled = b53_eee_init(ds, port, phydev); } +void b53_port_event(struct dsa_switch *ds, int port) +{ + struct b53_device *dev = ds->priv; + bool link; + u16 sts; + + b53_read16(dev, B53_STAT_PAGE, B53_LINK_STAT, &sts); + link = !!(sts & BIT(port)); + dsa_port_phylink_mac_change(ds, port, link); +} +EXPORT_SYMBOL(b53_port_event); + +void b53_phylink_validate(struct dsa_switch *ds, int port, + unsigned long *supported, + struct phylink_link_state *state) +{ + struct b53_device *dev = ds->priv; + __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; + + if (dev->ops->serdes_phylink_validate) + dev->ops->serdes_phylink_validate(dev, port, mask, state); + + /* Allow all the expected bits */ + phylink_set(mask, Autoneg); + phylink_set_port_modes(mask); + phylink_set(mask, Pause); + phylink_set(mask, Asym_Pause); + + /* With the exclusion of 5325/5365, MII, Reverse MII and 802.3z, we + * support Gigabit, including Half duplex. + */ + if (state->interface != PHY_INTERFACE_MODE_MII && + state->interface != PHY_INTERFACE_MODE_REVMII && + !phy_interface_mode_is_8023z(state->interface) && + !(is5325(dev) || is5365(dev))) { + phylink_set(mask, 1000baseT_Full); + phylink_set(mask, 1000baseT_Half); + } + + if (!phy_interface_mode_is_8023z(state->interface)) { + phylink_set(mask, 10baseT_Half); + phylink_set(mask, 10baseT_Full); + phylink_set(mask, 100baseT_Half); + phylink_set(mask, 100baseT_Full); + } + + bitmap_and(supported, supported, mask, + __ETHTOOL_LINK_MODE_MASK_NBITS); + bitmap_and(state->advertising, state->advertising, mask, + __ETHTOOL_LINK_MODE_MASK_NBITS); + + phylink_helper_basex_speed(state); +} +EXPORT_SYMBOL(b53_phylink_validate); + +int b53_phylink_mac_link_state(struct dsa_switch *ds, int port, + struct phylink_link_state *state) +{ + struct b53_device *dev = ds->priv; + int ret = -EOPNOTSUPP; + + if (phy_interface_mode_is_8023z(state->interface) && + dev->ops->serdes_link_state) + ret = dev->ops->serdes_link_state(dev, port, state); + + return ret; +} +EXPORT_SYMBOL(b53_phylink_mac_link_state); + +void b53_phylink_mac_config(struct dsa_switch *ds, int port, + unsigned int mode, + const struct phylink_link_state *state) +{ + struct b53_device *dev = ds->priv; + + if (mode == MLO_AN_PHY) + return; + + if (mode == MLO_AN_FIXED) { + b53_force_port_config(dev, port, state->speed, + state->duplex, state->pause); + return; + } + + if (phy_interface_mode_is_8023z(state->interface) && + dev->ops->serdes_config) + dev->ops->serdes_config(dev, port, mode, state); +} +EXPORT_SYMBOL(b53_phylink_mac_config); + +void b53_phylink_mac_an_restart(struct dsa_switch *ds, int port) +{ + struct b53_device *dev = ds->priv; + + if (dev->ops->serdes_an_restart) + dev->ops->serdes_an_restart(dev, port); +} +EXPORT_SYMBOL(b53_phylink_mac_an_restart); + +void b53_phylink_mac_link_down(struct dsa_switch *ds, int port, + unsigned int mode, + phy_interface_t interface) +{ + struct b53_device *dev = ds->priv; + + if (mode == MLO_AN_PHY) + return; + + if (mode == MLO_AN_FIXED) { + b53_force_link(dev, port, false); + return; + } + + if (phy_interface_mode_is_8023z(interface) && + dev->ops->serdes_link_set) + dev->ops->serdes_link_set(dev, port, mode, interface, false); +} +EXPORT_SYMBOL(b53_phylink_mac_link_down); + +void b53_phylink_mac_link_up(struct dsa_switch *ds, int port, + unsigned int mode, + phy_interface_t interface, + struct phy_device *phydev) +{ + struct b53_device *dev = ds->priv; + + if (mode == MLO_AN_PHY) + return; + + if (mode == MLO_AN_FIXED) { + b53_force_link(dev, port, true); + return; + } + + if (phy_interface_mode_is_8023z(interface) && + dev->ops->serdes_link_set) + dev->ops->serdes_link_set(dev, port, mode, interface, true); +} +EXPORT_SYMBOL(b53_phylink_mac_link_up); + int b53_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering) { return 0; @@ -1710,6 +1892,12 @@ static const struct dsa_switch_ops b53_switch_ops = { .phy_read = b53_phy_read16, .phy_write = b53_phy_write16, .adjust_link = b53_adjust_link, + .phylink_validate = b53_phylink_validate, + .phylink_mac_link_state = b53_phylink_mac_link_state, + .phylink_mac_config = b53_phylink_mac_config, + .phylink_mac_an_restart = b53_phylink_mac_an_restart, + .phylink_mac_link_down = b53_phylink_mac_link_down, + .phylink_mac_link_up = b53_phylink_mac_link_up, .port_enable = b53_enable_port, .port_disable = b53_disable_port, .get_mac_eee = b53_get_mac_eee, diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h index df149756c282..ec796482792d 100644 --- a/drivers/net/dsa/b53/b53_priv.h +++ b/drivers/net/dsa/b53/b53_priv.h @@ -29,6 +29,7 @@ struct b53_device; struct net_device; +struct phylink_link_state; struct b53_io_ops { int (*read8)(struct b53_device *dev, u8 page, u8 reg, u8 *value); @@ -43,8 +44,25 @@ struct b53_io_ops { int (*write64)(struct b53_device *dev, u8 page, u8 reg, u64 value); int (*phy_read16)(struct b53_device *dev, int addr, int reg, u16 *value); int (*phy_write16)(struct b53_device *dev, int addr, int reg, u16 value); + int (*irq_enable)(struct b53_device *dev, int port); + void (*irq_disable)(struct b53_device *dev, int port); + u8 (*serdes_map_lane)(struct b53_device *dev, int port); + int (*serdes_link_state)(struct b53_device *dev, int port, + struct phylink_link_state *state); + void (*serdes_config)(struct b53_device *dev, int port, + unsigned int mode, + const struct phylink_link_state *state); + void (*serdes_an_restart)(struct b53_device *dev, int port); + void (*serdes_link_set)(struct b53_device *dev, int port, + unsigned int mode, phy_interface_t interface, + bool link_up); + void (*serdes_phylink_validate)(struct b53_device *dev, int port, + unsigned long *supported, + struct phylink_link_state *state); }; +#define B53_INVALID_LANE 0xff + enum { BCM5325_DEVICE_ID = 0x25, BCM5365_DEVICE_ID = 0x65, @@ -107,6 +125,7 @@ struct b53_device { /* connect specific data */ u8 current_page; struct device *dev; + u8 serdes_lane; /* Master MDIO bus we got probed from */ struct mii_bus *bus; @@ -298,6 +317,23 @@ int b53_br_join(struct dsa_switch *ds, int port, struct net_device *bridge); void b53_br_leave(struct dsa_switch *ds, int port, struct net_device *bridge); void b53_br_set_stp_state(struct dsa_switch *ds, int port, u8 state); void b53_br_fast_age(struct dsa_switch *ds, int port); +void b53_port_event(struct dsa_switch *ds, int port); +void b53_phylink_validate(struct dsa_switch *ds, int port, + unsigned long *supported, + struct phylink_link_state *state); +int b53_phylink_mac_link_state(struct dsa_switch *ds, int port, + struct phylink_link_state *state); +void b53_phylink_mac_config(struct dsa_switch *ds, int port, + unsigned int mode, + const struct phylink_link_state *state); +void b53_phylink_mac_an_restart(struct dsa_switch *ds, int port); +void b53_phylink_mac_link_down(struct dsa_switch *ds, int port, + unsigned int mode, + phy_interface_t interface); +void b53_phylink_mac_link_up(struct dsa_switch *ds, int port, + unsigned int mode, + phy_interface_t interface, + struct phy_device *phydev); int b53_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering); int b53_vlan_prepare(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan); diff --git a/drivers/net/dsa/b53/b53_serdes.c b/drivers/net/dsa/b53/b53_serdes.c new file mode 100644 index 000000000000..b45c55e0b8b4 --- /dev/null +++ b/drivers/net/dsa/b53/b53_serdes.c @@ -0,0 +1,217 @@ +// SPDX-License-Identifier: GPL-2.0 or BSD-3-Clause +/* + * Northstar Plus switch SerDes/SGMII PHY main logic + * + * Copyright (C) 2018 Florian Fainelli <f.fainelli@gmail.com> + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/delay.h> +#include <linux/kernel.h> +#include <linux/phy.h> +#include <linux/phylink.h> +#include <net/dsa.h> + +#include "b53_priv.h" +#include "b53_serdes.h" +#include "b53_regs.h" + +static void b53_serdes_write_blk(struct b53_device *dev, u8 offset, u16 block, + u16 value) +{ + b53_write16(dev, B53_SERDES_PAGE, B53_SERDES_BLKADDR, block); + b53_write16(dev, B53_SERDES_PAGE, offset, value); +} + +static u16 b53_serdes_read_blk(struct b53_device *dev, u8 offset, u16 block) +{ + u16 value; + + b53_write16(dev, B53_SERDES_PAGE, B53_SERDES_BLKADDR, block); + b53_read16(dev, B53_SERDES_PAGE, offset, &value); + + return value; +} + +static void b53_serdes_set_lane(struct b53_device *dev, u8 lane) +{ + if (dev->serdes_lane == lane) + return; + + WARN_ON(lane > 1); + + b53_serdes_write_blk(dev, B53_SERDES_LANE, + SERDES_XGXSBLK0_BLOCKADDRESS, lane); + dev->serdes_lane = lane; +} + +static void b53_serdes_write(struct b53_device *dev, u8 lane, + u8 offset, u16 block, u16 value) +{ + b53_serdes_set_lane(dev, lane); + b53_serdes_write_blk(dev, offset, block, value); +} + +static u16 b53_serdes_read(struct b53_device *dev, u8 lane, + u8 offset, u16 block) +{ + b53_serdes_set_lane(dev, lane); + return b53_serdes_read_blk(dev, offset, block); +} + +void b53_serdes_config(struct b53_device *dev, int port, unsigned int mode, + const struct phylink_link_state *state) +{ + u8 lane = b53_serdes_map_lane(dev, port); + u16 reg; + + if (lane == B53_INVALID_LANE) + return; + + reg = b53_serdes_read(dev, lane, B53_SERDES_DIGITAL_CONTROL(1), + SERDES_DIGITAL_BLK); + if (state->interface == PHY_INTERFACE_MODE_1000BASEX) + reg |= FIBER_MODE_1000X; + else + reg &= ~FIBER_MODE_1000X; + b53_serdes_write(dev, lane, B53_SERDES_DIGITAL_CONTROL(1), + SERDES_DIGITAL_BLK, reg); +} +EXPORT_SYMBOL(b53_serdes_config); + +void b53_serdes_an_restart(struct b53_device *dev, int port) +{ + u8 lane = b53_serdes_map_lane(dev, port); + u16 reg; + + if (lane == B53_INVALID_LANE) + return; + + reg = b53_serdes_read(dev, lane, B53_SERDES_MII_REG(MII_BMCR), + SERDES_MII_BLK); + reg |= BMCR_ANRESTART; + b53_serdes_write(dev, lane, B53_SERDES_MII_REG(MII_BMCR), + SERDES_MII_BLK, reg); +} +EXPORT_SYMBOL(b53_serdes_an_restart); + +int b53_serdes_link_state(struct b53_device *dev, int port, + struct phylink_link_state *state) +{ + u8 lane = b53_serdes_map_lane(dev, port); + u16 dig, bmcr, bmsr; + + if (lane == B53_INVALID_LANE) + return 1; + + dig = b53_serdes_read(dev, lane, B53_SERDES_DIGITAL_STATUS, + SERDES_DIGITAL_BLK); + bmcr = b53_serdes_read(dev, lane, B53_SERDES_MII_REG(MII_BMCR), + SERDES_MII_BLK); + bmsr = b53_serdes_read(dev, lane, B53_SERDES_MII_REG(MII_BMSR), + SERDES_MII_BLK); + + switch ((dig >> SPEED_STATUS_SHIFT) & SPEED_STATUS_MASK) { + case SPEED_STATUS_10: + state->speed = SPEED_10; + break; + case SPEED_STATUS_100: + state->speed = SPEED_100; + break; + case SPEED_STATUS_1000: + state->speed = SPEED_1000; + break; + default: + case SPEED_STATUS_2500: + state->speed = SPEED_2500; + break; + } + + state->duplex = dig & DUPLEX_STATUS ? DUPLEX_FULL : DUPLEX_HALF; + state->an_enabled = !!(bmcr & BMCR_ANENABLE); + state->an_complete = !!(bmsr & BMSR_ANEGCOMPLETE); + state->link = !!(dig & LINK_STATUS); + if (dig & PAUSE_RESOLUTION_RX_SIDE) + state->pause |= MLO_PAUSE_RX; + if (dig & PAUSE_RESOLUTION_TX_SIDE) + state->pause |= MLO_PAUSE_TX; + + return 0; +} +EXPORT_SYMBOL(b53_serdes_link_state); + +void b53_serdes_link_set(struct b53_device *dev, int port, unsigned int mode, + phy_interface_t interface, bool link_up) +{ + u8 lane = b53_serdes_map_lane(dev, port); + u16 reg; + + if (lane == B53_INVALID_LANE) + return; + + reg = b53_serdes_read(dev, lane, B53_SERDES_MII_REG(MII_BMCR), + SERDES_MII_BLK); + if (link_up) + reg &= ~BMCR_PDOWN; + else + reg |= BMCR_PDOWN; + b53_serdes_write(dev, lane, B53_SERDES_MII_REG(MII_BMCR), + SERDES_MII_BLK, reg); +} +EXPORT_SYMBOL(b53_serdes_link_set); + +void b53_serdes_phylink_validate(struct b53_device *dev, int port, + unsigned long *supported, + struct phylink_link_state *state) +{ + u8 lane = b53_serdes_map_lane(dev, port); + + if (lane == B53_INVALID_LANE) + return; + + switch (lane) { + case 0: + phylink_set(supported, 2500baseX_Full); + /* fallthrough */ + case 1: + phylink_set(supported, 1000baseX_Full); + break; + default: + break; + } +} +EXPORT_SYMBOL(b53_serdes_phylink_validate); + +int b53_serdes_init(struct b53_device *dev, int port) +{ + u8 lane = b53_serdes_map_lane(dev, port); + u16 id0, msb, lsb; + + if (lane == B53_INVALID_LANE) + return -EINVAL; + + id0 = b53_serdes_read(dev, lane, B53_SERDES_ID0, SERDES_ID0); + msb = b53_serdes_read(dev, lane, B53_SERDES_MII_REG(MII_PHYSID1), + SERDES_MII_BLK); + lsb = b53_serdes_read(dev, lane, B53_SERDES_MII_REG(MII_PHYSID2), + SERDES_MII_BLK); + if (id0 == 0 || id0 == 0xffff) { + dev_err(dev->dev, "SerDes not initialized, check settings\n"); + return -ENODEV; + } + + dev_info(dev->dev, + "SerDes lane %d, model: %d, rev %c%d (OUI: 0x%08x)\n", + lane, id0 & SERDES_ID0_MODEL_MASK, + (id0 >> SERDES_ID0_REV_LETTER_SHIFT) + 0x41, + (id0 >> SERDES_ID0_REV_NUM_SHIFT) & SERDES_ID0_REV_NUM_MASK, + (u32)msb << 16 | lsb); + + return 0; +} +EXPORT_SYMBOL(b53_serdes_init); + +MODULE_AUTHOR("Florian Fainelli <f.fainelli@gmail.com>"); +MODULE_DESCRIPTION("B53 Switch SerDes driver"); +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/net/dsa/b53/b53_serdes.h b/drivers/net/dsa/b53/b53_serdes.h new file mode 100644 index 000000000000..eed7c9357091 --- /dev/null +++ b/drivers/net/dsa/b53/b53_serdes.h @@ -0,0 +1,128 @@ +/* SPDX-License-Identifier: GPL-2.0 or BSD-3-Clause + * + * Northstar Plus switch SerDes/SGMII PHY definitions + * + * Copyright (C) 2018 Florian Fainelli <f.fainelli@gmail.com> + */ + +#include <linux/phy.h> +#include <linux/types.h> + +/* Non-standard page used to access SerDes PHY registers on NorthStar Plus */ +#define B53_SERDES_PAGE 0x16 +#define B53_SERDES_BLKADDR 0x3e +#define B53_SERDES_LANE 0x3c + +#define B53_SERDES_ID0 0x20 +#define SERDES_ID0_MODEL_MASK 0x3f +#define SERDES_ID0_REV_NUM_SHIFT 11 +#define SERDES_ID0_REV_NUM_MASK 0x7 +#define SERDES_ID0_REV_LETTER_SHIFT 14 + +#define B53_SERDES_MII_REG(x) (0x20 + (x) * 2) +#define B53_SERDES_DIGITAL_CONTROL(x) (0x18 + (x) * 2) +#define B53_SERDES_DIGITAL_STATUS 0x28 + +/* SERDES_DIGITAL_CONTROL1 */ +#define FIBER_MODE_1000X BIT(0) +#define TBI_INTERFACE BIT(1) +#define SIGNAL_DETECT_EN BIT(2) +#define INVERT_SIGNAL_DETECT BIT(3) +#define AUTODET_EN BIT(4) +#define SGMII_MASTER_MODE BIT(5) +#define DISABLE_DLL_PWRDOWN BIT(6) +#define CRC_CHECKER_DIS BIT(7) +#define COMMA_DET_EN BIT(8) +#define ZERO_COMMA_DET_EN BIT(9) +#define REMOTE_LOOPBACK BIT(10) +#define SEL_RX_PKTS_FOR_CNTR BIT(11) +#define MASTER_MDIO_PHY_SEL BIT(13) +#define DISABLE_SIGNAL_DETECT_FLT BIT(14) + +/* SERDES_DIGITAL_CONTROL2 */ +#define EN_PARALLEL_DET BIT(0) +#define DIS_FALSE_LINK BIT(1) +#define FLT_FORCE_LINK BIT(2) +#define EN_AUTONEG_ERR_TIMER BIT(3) +#define DIS_REMOTE_FAULT_SENSING BIT(4) +#define FORCE_XMIT_DATA BIT(5) +#define AUTONEG_FAST_TIMERS BIT(6) +#define DIS_CARRIER_EXTEND BIT(7) +#define DIS_TRRR_GENERATION BIT(8) +#define BYPASS_PCS_RX BIT(9) +#define BYPASS_PCS_TX BIT(10) +#define TEST_CNTR_EN BIT(11) +#define TX_PACKET_SEQ_TEST BIT(12) +#define TX_IDLE_JAM_SEQ_TEST BIT(13) +#define CLR_BER_CNTR BIT(14) + +/* SERDES_DIGITAL_CONTROL3 */ +#define TX_FIFO_RST BIT(0) +#define FIFO_ELAST_TX_RX_SHIFT 1 +#define FIFO_ELAST_TX_RX_5K 0 +#define FIFO_ELAST_TX_RX_10K 1 +#define FIFO_ELAST_TX_RX_13_5K 2 +#define FIFO_ELAST_TX_RX_18_5K 3 +#define BLOCK_TXEN_MODE BIT(9) +#define JAM_FALSE_CARRIER_MODE BIT(10) +#define EXT_PHY_CRS_MODE BIT(11) +#define INVERT_EXT_PHY_CRS BIT(12) +#define DISABLE_TX_CRS BIT(13) + +/* SERDES_DIGITAL_STATUS */ +#define SGMII_MODE BIT(0) +#define LINK_STATUS BIT(1) +#define DUPLEX_STATUS BIT(2) +#define SPEED_STATUS_SHIFT 3 +#define SPEED_STATUS_10 0 +#define SPEED_STATUS_100 1 +#define SPEED_STATUS_1000 2 +#define SPEED_STATUS_2500 3 +#define SPEED_STATUS_MASK SPEED_STATUS_2500 +#define PAUSE_RESOLUTION_TX_SIDE BIT(5) +#define PAUSE_RESOLUTION_RX_SIDE BIT(6) +#define LINK_STATUS_CHANGE BIT(7) +#define EARLY_END_EXT_DET BIT(8) +#define CARRIER_EXT_ERR_DET BIT(9) +#define RX_ERR_DET BIT(10) +#define TX_ERR_DET BIT(11) +#define CRC_ERR_DET BIT(12) +#define FALSE_CARRIER_ERR_DET BIT(13) +#define RXFIFO_ERR_DET BIT(14) +#define TXFIFO_ERR_DET BIT(15) + +/* Block offsets */ +#define SERDES_DIGITAL_BLK 0x8300 +#define SERDES_ID0 0x8310 +#define SERDES_MII_BLK 0xffe0 +#define SERDES_XGXSBLK0_BLOCKADDRESS 0xffd0 + +struct phylink_link_state; + +static inline u8 b53_serdes_map_lane(struct b53_device *dev, int port) +{ + if (!dev->ops->serdes_map_lane) + return B53_INVALID_LANE; + + return dev->ops->serdes_map_lane(dev, port); +} + +int b53_serdes_get_link(struct b53_device *dev, int port); +int b53_serdes_link_state(struct b53_device *dev, int port, + struct phylink_link_state *state); +void b53_serdes_config(struct b53_device *dev, int port, unsigned int mode, + const struct phylink_link_state *state); +void b53_serdes_an_restart(struct b53_device *dev, int port); +void b53_serdes_link_set(struct b53_device *dev, int port, unsigned int mode, + phy_interface_t interface, bool link_up); +void b53_serdes_phylink_validate(struct b53_device *dev, int port, + unsigned long *supported, + struct phylink_link_state *state); +#if IS_ENABLED(CONFIG_B53_SERDES) +int b53_serdes_init(struct b53_device *dev, int port); +#else +static inline int b53_serdes_init(struct b53_device *dev, int port) +{ + return -ENODEV; +} +#endif diff --git a/drivers/net/dsa/b53/b53_srab.c b/drivers/net/dsa/b53/b53_srab.c index 91de2ba99ad1..90f514252987 100644 --- a/drivers/net/dsa/b53/b53_srab.c +++ b/drivers/net/dsa/b53/b53_srab.c @@ -19,11 +19,13 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/delay.h> +#include <linux/interrupt.h> #include <linux/platform_device.h> #include <linux/platform_data/b53.h> #include <linux/of.h> #include "b53_priv.h" +#include "b53_serdes.h" /* command and status register of the SRAB */ #define B53_SRAB_CMDSTAT 0x2c @@ -47,6 +49,7 @@ /* command and status register of the SRAB */ #define B53_SRAB_CTRLS 0x40 +#define B53_SRAB_CTRLS_HOST_INTR BIT(1) #define B53_SRAB_CTRLS_RCAREQ BIT(3) #define B53_SRAB_CTRLS_RCAGNT BIT(4) #define B53_SRAB_CTRLS_SW_INIT_DONE BIT(6) @@ -60,8 +63,29 @@ #define B53_SRAB_P7_SLEEP_TIMER BIT(11) #define B53_SRAB_IMP0_SLEEP_TIMER BIT(12) +/* Port mux configuration registers */ +#define B53_MUX_CONFIG_P5 0x00 +#define MUX_CONFIG_SGMII 0 +#define MUX_CONFIG_MII_LITE 1 +#define MUX_CONFIG_RGMII 2 +#define MUX_CONFIG_GMII 3 +#define MUX_CONFIG_GPHY 4 +#define MUX_CONFIG_INTERNAL 5 +#define MUX_CONFIG_MASK 0x7 +#define B53_MUX_CONFIG_P4 0x04 + +struct b53_srab_port_priv { + int irq; + bool irq_enabled; + struct b53_device *dev; + unsigned int num; + phy_interface_t mode; +}; + struct b53_srab_priv { void __iomem *regs; + void __iomem *mux_config; + struct b53_srab_port_priv port_intrs[B53_N_PORTS]; }; static int b53_srab_request_grant(struct b53_device *dev) @@ -344,6 +368,81 @@ err: return ret; } +static irqreturn_t b53_srab_port_thread(int irq, void *dev_id) +{ + struct b53_srab_port_priv *port = dev_id; + struct b53_device *dev = port->dev; + + if (port->mode == PHY_INTERFACE_MODE_SGMII) + b53_port_event(dev->ds, port->num); + + return IRQ_HANDLED; +} + +static irqreturn_t b53_srab_port_isr(int irq, void *dev_id) +{ + struct b53_srab_port_priv *port = dev_id; + struct b53_device *dev = port->dev; + struct b53_srab_priv *priv = dev->priv; + + /* Acknowledge the interrupt */ + writel(BIT(port->num), priv->regs + B53_SRAB_INTR); + + return IRQ_WAKE_THREAD; +} + +#if IS_ENABLED(CONFIG_B53_SERDES) +static u8 b53_srab_serdes_map_lane(struct b53_device *dev, int port) +{ + struct b53_srab_priv *priv = dev->priv; + struct b53_srab_port_priv *p = &priv->port_intrs[port]; + + if (p->mode != PHY_INTERFACE_MODE_SGMII) + return B53_INVALID_LANE; + + switch (port) { + case 5: + return 0; + case 4: + return 1; + default: + return B53_INVALID_LANE; + } +} +#endif + +static int b53_srab_irq_enable(struct b53_device *dev, int port) +{ + struct b53_srab_priv *priv = dev->priv; + struct b53_srab_port_priv *p = &priv->port_intrs[port]; + int ret = 0; + + /* Interrupt is optional and was not specified, do not make + * this fatal + */ + if (p->irq == -ENXIO) + return ret; + + ret = request_threaded_irq(p->irq, b53_srab_port_isr, + b53_srab_port_thread, 0, + dev_name(dev->dev), p); + if (!ret) + p->irq_enabled = true; + + return ret; +} + +static void b53_srab_irq_disable(struct b53_device *dev, int port) +{ + struct b53_srab_priv *priv = dev->priv; + struct b53_srab_port_priv *p = &priv->port_intrs[port]; + + if (p->irq_enabled) { + free_irq(p->irq, p); + p->irq_enabled = false; + } +} + static const struct b53_io_ops b53_srab_ops = { .read8 = b53_srab_read8, .read16 = b53_srab_read16, @@ -355,6 +454,16 @@ static const struct b53_io_ops b53_srab_ops = { .write32 = b53_srab_write32, .write48 = b53_srab_write48, .write64 = b53_srab_write64, + .irq_enable = b53_srab_irq_enable, + .irq_disable = b53_srab_irq_disable, +#if IS_ENABLED(CONFIG_B53_SERDES) + .serdes_map_lane = b53_srab_serdes_map_lane, + .serdes_link_state = b53_serdes_link_state, + .serdes_config = b53_serdes_config, + .serdes_an_restart = b53_serdes_an_restart, + .serdes_link_set = b53_serdes_link_set, + .serdes_phylink_validate = b53_serdes_phylink_validate, +#endif }; static const struct of_device_id b53_srab_of_match[] = { @@ -379,6 +488,107 @@ static const struct of_device_id b53_srab_of_match[] = { }; MODULE_DEVICE_TABLE(of, b53_srab_of_match); +static void b53_srab_intr_set(struct b53_srab_priv *priv, bool set) +{ + u32 reg; + + reg = readl(priv->regs + B53_SRAB_CTRLS); + if (set) + reg |= B53_SRAB_CTRLS_HOST_INTR; + else + reg &= ~B53_SRAB_CTRLS_HOST_INTR; + writel(reg, priv->regs + B53_SRAB_CTRLS); +} + +static void b53_srab_prepare_irq(struct platform_device *pdev) +{ + struct b53_device *dev = platform_get_drvdata(pdev); + struct b53_srab_priv *priv = dev->priv; + struct b53_srab_port_priv *port; + unsigned int i; + char *name; + + /* Clear all pending interrupts */ + writel(0xffffffff, priv->regs + B53_SRAB_INTR); + + if (dev->pdata && dev->pdata->chip_id != BCM58XX_DEVICE_ID) + return; + + for (i = 0; i < B53_N_PORTS; i++) { + port = &priv->port_intrs[i]; + + /* There is no port 6 */ + if (i == 6) + continue; + + name = kasprintf(GFP_KERNEL, "link_state_p%d", i); + if (!name) + return; + + port->num = i; + port->dev = dev; + port->irq = platform_get_irq_byname(pdev, name); + kfree(name); + } + + b53_srab_intr_set(priv, true); +} + +static void b53_srab_mux_init(struct platform_device *pdev) +{ + struct b53_device *dev = platform_get_drvdata(pdev); + struct b53_srab_priv *priv = dev->priv; + struct b53_srab_port_priv *p; + struct resource *r; + unsigned int port; + u32 reg, off = 0; + int ret; + + if (dev->pdata && dev->pdata->chip_id != BCM58XX_DEVICE_ID) + return; + + r = platform_get_resource(pdev, IORESOURCE_MEM, 1); + priv->mux_config = devm_ioremap_resource(&pdev->dev, r); + if (IS_ERR(priv->mux_config)) + return; + + /* Obtain the port mux configuration so we know which lanes + * actually map to SerDes lanes + */ + for (port = 5; port > 3; port--, off += 4) { + p = &priv->port_intrs[port]; + + reg = readl(priv->mux_config + B53_MUX_CONFIG_P5 + off); + switch (reg & MUX_CONFIG_MASK) { + case MUX_CONFIG_SGMII: + p->mode = PHY_INTERFACE_MODE_SGMII; + ret = b53_serdes_init(dev, port); + if (ret) + continue; + break; + case MUX_CONFIG_MII_LITE: + p->mode = PHY_INTERFACE_MODE_MII; + break; + case MUX_CONFIG_GMII: + p->mode = PHY_INTERFACE_MODE_GMII; + break; + case MUX_CONFIG_RGMII: + p->mode = PHY_INTERFACE_MODE_RGMII; + break; + case MUX_CONFIG_INTERNAL: + p->mode = PHY_INTERFACE_MODE_INTERNAL; + break; + default: + p->mode = PHY_INTERFACE_MODE_NA; + break; + } + + if (p->mode != PHY_INTERFACE_MODE_NA) + dev_info(&pdev->dev, "Port %d mode: %s\n", + port, phy_modes(p->mode)); + } +} + static int b53_srab_probe(struct platform_device *pdev) { struct b53_platform_data *pdata = pdev->dev.platform_data; @@ -417,13 +627,18 @@ static int b53_srab_probe(struct platform_device *pdev) platform_set_drvdata(pdev, dev); + b53_srab_prepare_irq(pdev); + b53_srab_mux_init(pdev); + return b53_switch_register(dev); } static int b53_srab_remove(struct platform_device *pdev) { struct b53_device *dev = platform_get_drvdata(pdev); + struct b53_srab_priv *priv = dev->priv; + b53_srab_intr_set(priv, false); if (dev) b53_switch_remove(dev); diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index e0066adcd2f3..1fc27e149e7f 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -465,8 +465,7 @@ static int bcm_sf2_mdio_register(struct dsa_switch *ds) static void bcm_sf2_mdio_unregister(struct bcm_sf2_priv *priv) { mdiobus_unregister(priv->slave_mii_bus); - if (priv->master_mii_dn) - of_node_put(priv->master_mii_dn); + of_node_put(priv->master_mii_dn); } static u32 bcm_sf2_sw_get_phy_flags(struct dsa_switch *ds, int port) diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c new file mode 100644 index 000000000000..693a67f45bef --- /dev/null +++ b/drivers/net/dsa/lantiq_gswip.c @@ -0,0 +1,1167 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Lantiq / Intel GSWIP switch driver for VRX200 SoCs + * + * Copyright (C) 2010 Lantiq Deutschland + * Copyright (C) 2012 John Crispin <john@phrozen.org> + * Copyright (C) 2017 - 2018 Hauke Mehrtens <hauke@hauke-m.de> + */ + +#include <linux/clk.h> +#include <linux/etherdevice.h> +#include <linux/firmware.h> +#include <linux/if_bridge.h> +#include <linux/if_vlan.h> +#include <linux/iopoll.h> +#include <linux/mfd/syscon.h> +#include <linux/module.h> +#include <linux/of_mdio.h> +#include <linux/of_net.h> +#include <linux/of_platform.h> +#include <linux/phy.h> +#include <linux/phylink.h> +#include <linux/platform_device.h> +#include <linux/regmap.h> +#include <linux/reset.h> +#include <net/dsa.h> +#include <dt-bindings/mips/lantiq_rcu_gphy.h> + +#include "lantiq_pce.h" + +/* GSWIP MDIO Registers */ +#define GSWIP_MDIO_GLOB 0x00 +#define GSWIP_MDIO_GLOB_ENABLE BIT(15) +#define GSWIP_MDIO_CTRL 0x08 +#define GSWIP_MDIO_CTRL_BUSY BIT(12) +#define GSWIP_MDIO_CTRL_RD BIT(11) +#define GSWIP_MDIO_CTRL_WR BIT(10) +#define GSWIP_MDIO_CTRL_PHYAD_MASK 0x1f +#define GSWIP_MDIO_CTRL_PHYAD_SHIFT 5 +#define GSWIP_MDIO_CTRL_REGAD_MASK 0x1f +#define GSWIP_MDIO_READ 0x09 +#define GSWIP_MDIO_WRITE 0x0A +#define GSWIP_MDIO_MDC_CFG0 0x0B +#define GSWIP_MDIO_MDC_CFG1 0x0C +#define GSWIP_MDIO_PHYp(p) (0x15 - (p)) +#define GSWIP_MDIO_PHY_LINK_MASK 0x6000 +#define GSWIP_MDIO_PHY_LINK_AUTO 0x0000 +#define GSWIP_MDIO_PHY_LINK_DOWN 0x4000 +#define GSWIP_MDIO_PHY_LINK_UP 0x2000 +#define GSWIP_MDIO_PHY_SPEED_MASK 0x1800 +#define GSWIP_MDIO_PHY_SPEED_AUTO 0x1800 +#define GSWIP_MDIO_PHY_SPEED_M10 0x0000 +#define GSWIP_MDIO_PHY_SPEED_M100 0x0800 +#define GSWIP_MDIO_PHY_SPEED_G1 0x1000 +#define GSWIP_MDIO_PHY_FDUP_MASK 0x0600 +#define GSWIP_MDIO_PHY_FDUP_AUTO 0x0000 +#define GSWIP_MDIO_PHY_FDUP_EN 0x0200 +#define GSWIP_MDIO_PHY_FDUP_DIS 0x0600 +#define GSWIP_MDIO_PHY_FCONTX_MASK 0x0180 +#define GSWIP_MDIO_PHY_FCONTX_AUTO 0x0000 +#define GSWIP_MDIO_PHY_FCONTX_EN 0x0100 +#define GSWIP_MDIO_PHY_FCONTX_DIS 0x0180 +#define GSWIP_MDIO_PHY_FCONRX_MASK 0x0060 +#define GSWIP_MDIO_PHY_FCONRX_AUTO 0x0000 +#define GSWIP_MDIO_PHY_FCONRX_EN 0x0020 +#define GSWIP_MDIO_PHY_FCONRX_DIS 0x0060 +#define GSWIP_MDIO_PHY_ADDR_MASK 0x001f +#define GSWIP_MDIO_PHY_MASK (GSWIP_MDIO_PHY_ADDR_MASK | \ + GSWIP_MDIO_PHY_FCONRX_MASK | \ + GSWIP_MDIO_PHY_FCONTX_MASK | \ + GSWIP_MDIO_PHY_LINK_MASK | \ + GSWIP_MDIO_PHY_SPEED_MASK | \ + GSWIP_MDIO_PHY_FDUP_MASK) + +/* GSWIP MII Registers */ +#define GSWIP_MII_CFG0 0x00 +#define GSWIP_MII_CFG1 0x02 +#define GSWIP_MII_CFG5 0x04 +#define GSWIP_MII_CFG_EN BIT(14) +#define GSWIP_MII_CFG_LDCLKDIS BIT(12) +#define GSWIP_MII_CFG_MODE_MIIP 0x0 +#define GSWIP_MII_CFG_MODE_MIIM 0x1 +#define GSWIP_MII_CFG_MODE_RMIIP 0x2 +#define GSWIP_MII_CFG_MODE_RMIIM 0x3 +#define GSWIP_MII_CFG_MODE_RGMII 0x4 +#define GSWIP_MII_CFG_MODE_MASK 0xf +#define GSWIP_MII_CFG_RATE_M2P5 0x00 +#define GSWIP_MII_CFG_RATE_M25 0x10 +#define GSWIP_MII_CFG_RATE_M125 0x20 +#define GSWIP_MII_CFG_RATE_M50 0x30 +#define GSWIP_MII_CFG_RATE_AUTO 0x40 +#define GSWIP_MII_CFG_RATE_MASK 0x70 +#define GSWIP_MII_PCDU0 0x01 +#define GSWIP_MII_PCDU1 0x03 +#define GSWIP_MII_PCDU5 0x05 +#define GSWIP_MII_PCDU_TXDLY_MASK GENMASK(2, 0) +#define GSWIP_MII_PCDU_RXDLY_MASK GENMASK(9, 7) + +/* GSWIP Core Registers */ +#define GSWIP_SWRES 0x000 +#define GSWIP_SWRES_R1 BIT(1) /* GSWIP Software reset */ +#define GSWIP_SWRES_R0 BIT(0) /* GSWIP Hardware reset */ +#define GSWIP_VERSION 0x013 +#define GSWIP_VERSION_REV_SHIFT 0 +#define GSWIP_VERSION_REV_MASK GENMASK(7, 0) +#define GSWIP_VERSION_MOD_SHIFT 8 +#define GSWIP_VERSION_MOD_MASK GENMASK(15, 8) +#define GSWIP_VERSION_2_0 0x100 +#define GSWIP_VERSION_2_1 0x021 +#define GSWIP_VERSION_2_2 0x122 +#define GSWIP_VERSION_2_2_ETC 0x022 + +#define GSWIP_BM_RAM_VAL(x) (0x043 - (x)) +#define GSWIP_BM_RAM_ADDR 0x044 +#define GSWIP_BM_RAM_CTRL 0x045 +#define GSWIP_BM_RAM_CTRL_BAS BIT(15) +#define GSWIP_BM_RAM_CTRL_OPMOD BIT(5) +#define GSWIP_BM_RAM_CTRL_ADDR_MASK GENMASK(4, 0) +#define GSWIP_BM_QUEUE_GCTRL 0x04A +#define GSWIP_BM_QUEUE_GCTRL_GL_MOD BIT(10) +/* buffer management Port Configuration Register */ +#define GSWIP_BM_PCFGp(p) (0x080 + ((p) * 2)) +#define GSWIP_BM_PCFG_CNTEN BIT(0) /* RMON Counter Enable */ +#define GSWIP_BM_PCFG_IGCNT BIT(1) /* Ingres Special Tag RMON count */ +/* buffer management Port Control Register */ +#define GSWIP_BM_RMON_CTRLp(p) (0x81 + ((p) * 2)) +#define GSWIP_BM_CTRL_RMON_RAM1_RES BIT(0) /* Software Reset for RMON RAM 1 */ +#define GSWIP_BM_CTRL_RMON_RAM2_RES BIT(1) /* Software Reset for RMON RAM 2 */ + +/* PCE */ +#define GSWIP_PCE_TBL_KEY(x) (0x447 - (x)) +#define GSWIP_PCE_TBL_MASK 0x448 +#define GSWIP_PCE_TBL_VAL(x) (0x44D - (x)) +#define GSWIP_PCE_TBL_ADDR 0x44E +#define GSWIP_PCE_TBL_CTRL 0x44F +#define GSWIP_PCE_TBL_CTRL_BAS BIT(15) +#define GSWIP_PCE_TBL_CTRL_TYPE BIT(13) +#define GSWIP_PCE_TBL_CTRL_VLD BIT(12) +#define GSWIP_PCE_TBL_CTRL_KEYFORM BIT(11) +#define GSWIP_PCE_TBL_CTRL_GMAP_MASK GENMASK(10, 7) +#define GSWIP_PCE_TBL_CTRL_OPMOD_MASK GENMASK(6, 5) +#define GSWIP_PCE_TBL_CTRL_OPMOD_ADRD 0x00 +#define GSWIP_PCE_TBL_CTRL_OPMOD_ADWR 0x20 +#define GSWIP_PCE_TBL_CTRL_OPMOD_KSRD 0x40 +#define GSWIP_PCE_TBL_CTRL_OPMOD_KSWR 0x60 +#define GSWIP_PCE_TBL_CTRL_ADDR_MASK GENMASK(4, 0) +#define GSWIP_PCE_PMAP1 0x453 /* Monitoring port map */ +#define GSWIP_PCE_PMAP2 0x454 /* Default Multicast port map */ +#define GSWIP_PCE_PMAP3 0x455 /* Default Unknown Unicast port map */ +#define GSWIP_PCE_GCTRL_0 0x456 +#define GSWIP_PCE_GCTRL_0_MC_VALID BIT(3) +#define GSWIP_PCE_GCTRL_0_VLAN BIT(14) /* VLAN aware Switching */ +#define GSWIP_PCE_GCTRL_1 0x457 +#define GSWIP_PCE_GCTRL_1_MAC_GLOCK BIT(2) /* MAC Address table lock */ +#define GSWIP_PCE_GCTRL_1_MAC_GLOCK_MOD BIT(3) /* Mac address table lock forwarding mode */ +#define GSWIP_PCE_PCTRL_0p(p) (0x480 + ((p) * 0xA)) +#define GSWIP_PCE_PCTRL_0_INGRESS BIT(11) +#define GSWIP_PCE_PCTRL_0_PSTATE_LISTEN 0x0 +#define GSWIP_PCE_PCTRL_0_PSTATE_RX 0x1 +#define GSWIP_PCE_PCTRL_0_PSTATE_TX 0x2 +#define GSWIP_PCE_PCTRL_0_PSTATE_LEARNING 0x3 +#define GSWIP_PCE_PCTRL_0_PSTATE_FORWARDING 0x7 +#define GSWIP_PCE_PCTRL_0_PSTATE_MASK GENMASK(2, 0) + +#define GSWIP_MAC_FLEN 0x8C5 +#define GSWIP_MAC_CTRL_2p(p) (0x905 + ((p) * 0xC)) +#define GSWIP_MAC_CTRL_2_MLEN BIT(3) /* Maximum Untagged Frame Lnegth */ + +/* Ethernet Switch Fetch DMA Port Control Register */ +#define GSWIP_FDMA_PCTRLp(p) (0xA80 + ((p) * 0x6)) +#define GSWIP_FDMA_PCTRL_EN BIT(0) /* FDMA Port Enable */ +#define GSWIP_FDMA_PCTRL_STEN BIT(1) /* Special Tag Insertion Enable */ +#define GSWIP_FDMA_PCTRL_VLANMOD_MASK GENMASK(4, 3) /* VLAN Modification Control */ +#define GSWIP_FDMA_PCTRL_VLANMOD_SHIFT 3 /* VLAN Modification Control */ +#define GSWIP_FDMA_PCTRL_VLANMOD_DIS (0x0 << GSWIP_FDMA_PCTRL_VLANMOD_SHIFT) +#define GSWIP_FDMA_PCTRL_VLANMOD_PRIO (0x1 << GSWIP_FDMA_PCTRL_VLANMOD_SHIFT) +#define GSWIP_FDMA_PCTRL_VLANMOD_ID (0x2 << GSWIP_FDMA_PCTRL_VLANMOD_SHIFT) +#define GSWIP_FDMA_PCTRL_VLANMOD_BOTH (0x3 << GSWIP_FDMA_PCTRL_VLANMOD_SHIFT) + +/* Ethernet Switch Store DMA Port Control Register */ +#define GSWIP_SDMA_PCTRLp(p) (0xBC0 + ((p) * 0x6)) +#define GSWIP_SDMA_PCTRL_EN BIT(0) /* SDMA Port Enable */ +#define GSWIP_SDMA_PCTRL_FCEN BIT(1) /* Flow Control Enable */ +#define GSWIP_SDMA_PCTRL_PAUFWD BIT(1) /* Pause Frame Forwarding */ + +#define XRX200_GPHY_FW_ALIGN (16 * 1024) + +struct gswip_hw_info { + int max_ports; + int cpu_port; +}; + +struct xway_gphy_match_data { + char *fe_firmware_name; + char *ge_firmware_name; +}; + +struct gswip_gphy_fw { + struct clk *clk_gate; + struct reset_control *reset; + u32 fw_addr_offset; + char *fw_name; +}; + +struct gswip_priv { + __iomem void *gswip; + __iomem void *mdio; + __iomem void *mii; + const struct gswip_hw_info *hw_info; + const struct xway_gphy_match_data *gphy_fw_name_cfg; + struct dsa_switch *ds; + struct device *dev; + struct regmap *rcu_regmap; + int num_gphy_fw; + struct gswip_gphy_fw *gphy_fw; +}; + +struct gswip_rmon_cnt_desc { + unsigned int size; + unsigned int offset; + const char *name; +}; + +#define MIB_DESC(_size, _offset, _name) {.size = _size, .offset = _offset, .name = _name} + +static const struct gswip_rmon_cnt_desc gswip_rmon_cnt[] = { + /** Receive Packet Count (only packets that are accepted and not discarded). */ + MIB_DESC(1, 0x1F, "RxGoodPkts"), + MIB_DESC(1, 0x23, "RxUnicastPkts"), + MIB_DESC(1, 0x22, "RxMulticastPkts"), + MIB_DESC(1, 0x21, "RxFCSErrorPkts"), + MIB_DESC(1, 0x1D, "RxUnderSizeGoodPkts"), + MIB_DESC(1, 0x1E, "RxUnderSizeErrorPkts"), + MIB_DESC(1, 0x1B, "RxOversizeGoodPkts"), + MIB_DESC(1, 0x1C, "RxOversizeErrorPkts"), + MIB_DESC(1, 0x20, "RxGoodPausePkts"), + MIB_DESC(1, 0x1A, "RxAlignErrorPkts"), + MIB_DESC(1, 0x12, "Rx64BytePkts"), + MIB_DESC(1, 0x13, "Rx127BytePkts"), + MIB_DESC(1, 0x14, "Rx255BytePkts"), + MIB_DESC(1, 0x15, "Rx511BytePkts"), + MIB_DESC(1, 0x16, "Rx1023BytePkts"), + /** Receive Size 1024-1522 (or more, if configured) Packet Count. */ + MIB_DESC(1, 0x17, "RxMaxBytePkts"), + MIB_DESC(1, 0x18, "RxDroppedPkts"), + MIB_DESC(1, 0x19, "RxFilteredPkts"), + MIB_DESC(2, 0x24, "RxGoodBytes"), + MIB_DESC(2, 0x26, "RxBadBytes"), + MIB_DESC(1, 0x11, "TxAcmDroppedPkts"), + MIB_DESC(1, 0x0C, "TxGoodPkts"), + MIB_DESC(1, 0x06, "TxUnicastPkts"), + MIB_DESC(1, 0x07, "TxMulticastPkts"), + MIB_DESC(1, 0x00, "Tx64BytePkts"), + MIB_DESC(1, 0x01, "Tx127BytePkts"), + MIB_DESC(1, 0x02, "Tx255BytePkts"), + MIB_DESC(1, 0x03, "Tx511BytePkts"), + MIB_DESC(1, 0x04, "Tx1023BytePkts"), + /** Transmit Size 1024-1522 (or more, if configured) Packet Count. */ + MIB_DESC(1, 0x05, "TxMaxBytePkts"), + MIB_DESC(1, 0x08, "TxSingleCollCount"), + MIB_DESC(1, 0x09, "TxMultCollCount"), + MIB_DESC(1, 0x0A, "TxLateCollCount"), + MIB_DESC(1, 0x0B, "TxExcessCollCount"), + MIB_DESC(1, 0x0D, "TxPauseCount"), + MIB_DESC(1, 0x10, "TxDroppedPkts"), + MIB_DESC(2, 0x0E, "TxGoodBytes"), +}; + +static u32 gswip_switch_r(struct gswip_priv *priv, u32 offset) +{ + return __raw_readl(priv->gswip + (offset * 4)); +} + +static void gswip_switch_w(struct gswip_priv *priv, u32 val, u32 offset) +{ + __raw_writel(val, priv->gswip + (offset * 4)); +} + +static void gswip_switch_mask(struct gswip_priv *priv, u32 clear, u32 set, + u32 offset) +{ + u32 val = gswip_switch_r(priv, offset); + + val &= ~(clear); + val |= set; + gswip_switch_w(priv, val, offset); +} + +static u32 gswip_switch_r_timeout(struct gswip_priv *priv, u32 offset, + u32 cleared) +{ + u32 val; + + return readx_poll_timeout(__raw_readl, priv->gswip + (offset * 4), val, + (val & cleared) == 0, 20, 50000); +} + +static u32 gswip_mdio_r(struct gswip_priv *priv, u32 offset) +{ + return __raw_readl(priv->mdio + (offset * 4)); +} + +static void gswip_mdio_w(struct gswip_priv *priv, u32 val, u32 offset) +{ + __raw_writel(val, priv->mdio + (offset * 4)); +} + +static void gswip_mdio_mask(struct gswip_priv *priv, u32 clear, u32 set, + u32 offset) +{ + u32 val = gswip_mdio_r(priv, offset); + + val &= ~(clear); + val |= set; + gswip_mdio_w(priv, val, offset); +} + +static u32 gswip_mii_r(struct gswip_priv *priv, u32 offset) +{ + return __raw_readl(priv->mii + (offset * 4)); +} + +static void gswip_mii_w(struct gswip_priv *priv, u32 val, u32 offset) +{ + __raw_writel(val, priv->mii + (offset * 4)); +} + +static void gswip_mii_mask(struct gswip_priv *priv, u32 clear, u32 set, + u32 offset) +{ + u32 val = gswip_mii_r(priv, offset); + + val &= ~(clear); + val |= set; + gswip_mii_w(priv, val, offset); +} + +static void gswip_mii_mask_cfg(struct gswip_priv *priv, u32 clear, u32 set, + int port) +{ + switch (port) { + case 0: + gswip_mii_mask(priv, clear, set, GSWIP_MII_CFG0); + break; + case 1: + gswip_mii_mask(priv, clear, set, GSWIP_MII_CFG1); + break; + case 5: + gswip_mii_mask(priv, clear, set, GSWIP_MII_CFG5); + break; + } +} + +static void gswip_mii_mask_pcdu(struct gswip_priv *priv, u32 clear, u32 set, + int port) +{ + switch (port) { + case 0: + gswip_mii_mask(priv, clear, set, GSWIP_MII_PCDU0); + break; + case 1: + gswip_mii_mask(priv, clear, set, GSWIP_MII_PCDU1); + break; + case 5: + gswip_mii_mask(priv, clear, set, GSWIP_MII_PCDU5); + break; + } +} + +static int gswip_mdio_poll(struct gswip_priv *priv) +{ + int cnt = 100; + + while (likely(cnt--)) { + u32 ctrl = gswip_mdio_r(priv, GSWIP_MDIO_CTRL); + + if ((ctrl & GSWIP_MDIO_CTRL_BUSY) == 0) + return 0; + usleep_range(20, 40); + } + + return -ETIMEDOUT; +} + +static int gswip_mdio_wr(struct mii_bus *bus, int addr, int reg, u16 val) +{ + struct gswip_priv *priv = bus->priv; + int err; + + err = gswip_mdio_poll(priv); + if (err) { + dev_err(&bus->dev, "waiting for MDIO bus busy timed out\n"); + return err; + } + + gswip_mdio_w(priv, val, GSWIP_MDIO_WRITE); + gswip_mdio_w(priv, GSWIP_MDIO_CTRL_BUSY | GSWIP_MDIO_CTRL_WR | + ((addr & GSWIP_MDIO_CTRL_PHYAD_MASK) << GSWIP_MDIO_CTRL_PHYAD_SHIFT) | + (reg & GSWIP_MDIO_CTRL_REGAD_MASK), + GSWIP_MDIO_CTRL); + + return 0; +} + +static int gswip_mdio_rd(struct mii_bus *bus, int addr, int reg) +{ + struct gswip_priv *priv = bus->priv; + int err; + + err = gswip_mdio_poll(priv); + if (err) { + dev_err(&bus->dev, "waiting for MDIO bus busy timed out\n"); + return err; + } + + gswip_mdio_w(priv, GSWIP_MDIO_CTRL_BUSY | GSWIP_MDIO_CTRL_RD | + ((addr & GSWIP_MDIO_CTRL_PHYAD_MASK) << GSWIP_MDIO_CTRL_PHYAD_SHIFT) | + (reg & GSWIP_MDIO_CTRL_REGAD_MASK), + GSWIP_MDIO_CTRL); + + err = gswip_mdio_poll(priv); + if (err) { + dev_err(&bus->dev, "waiting for MDIO bus busy timed out\n"); + return err; + } + + return gswip_mdio_r(priv, GSWIP_MDIO_READ); +} + +static int gswip_mdio(struct gswip_priv *priv, struct device_node *mdio_np) +{ + struct dsa_switch *ds = priv->ds; + + ds->slave_mii_bus = devm_mdiobus_alloc(priv->dev); + if (!ds->slave_mii_bus) + return -ENOMEM; + + ds->slave_mii_bus->priv = priv; + ds->slave_mii_bus->read = gswip_mdio_rd; + ds->slave_mii_bus->write = gswip_mdio_wr; + ds->slave_mii_bus->name = "lantiq,xrx200-mdio"; + snprintf(ds->slave_mii_bus->id, MII_BUS_ID_SIZE, "%s-mii", + dev_name(priv->dev)); + ds->slave_mii_bus->parent = priv->dev; + ds->slave_mii_bus->phy_mask = ~ds->phys_mii_mask; + + return of_mdiobus_register(ds->slave_mii_bus, mdio_np); +} + +static int gswip_port_enable(struct dsa_switch *ds, int port, + struct phy_device *phydev) +{ + struct gswip_priv *priv = ds->priv; + + /* RMON Counter Enable for port */ + gswip_switch_w(priv, GSWIP_BM_PCFG_CNTEN, GSWIP_BM_PCFGp(port)); + + /* enable port fetch/store dma & VLAN Modification */ + gswip_switch_mask(priv, 0, GSWIP_FDMA_PCTRL_EN | + GSWIP_FDMA_PCTRL_VLANMOD_BOTH, + GSWIP_FDMA_PCTRLp(port)); + gswip_switch_mask(priv, 0, GSWIP_SDMA_PCTRL_EN, + GSWIP_SDMA_PCTRLp(port)); + gswip_switch_mask(priv, 0, GSWIP_PCE_PCTRL_0_INGRESS, + GSWIP_PCE_PCTRL_0p(port)); + + if (!dsa_is_cpu_port(ds, port)) { + u32 macconf = GSWIP_MDIO_PHY_LINK_AUTO | + GSWIP_MDIO_PHY_SPEED_AUTO | + GSWIP_MDIO_PHY_FDUP_AUTO | + GSWIP_MDIO_PHY_FCONTX_AUTO | + GSWIP_MDIO_PHY_FCONRX_AUTO | + (phydev->mdio.addr & GSWIP_MDIO_PHY_ADDR_MASK); + + gswip_mdio_w(priv, macconf, GSWIP_MDIO_PHYp(port)); + /* Activate MDIO auto polling */ + gswip_mdio_mask(priv, 0, BIT(port), GSWIP_MDIO_MDC_CFG0); + } + + return 0; +} + +static void gswip_port_disable(struct dsa_switch *ds, int port, + struct phy_device *phy) +{ + struct gswip_priv *priv = ds->priv; + + if (!dsa_is_cpu_port(ds, port)) { + gswip_mdio_mask(priv, GSWIP_MDIO_PHY_LINK_DOWN, + GSWIP_MDIO_PHY_LINK_MASK, + GSWIP_MDIO_PHYp(port)); + /* Deactivate MDIO auto polling */ + gswip_mdio_mask(priv, BIT(port), 0, GSWIP_MDIO_MDC_CFG0); + } + + gswip_switch_mask(priv, GSWIP_FDMA_PCTRL_EN, 0, + GSWIP_FDMA_PCTRLp(port)); + gswip_switch_mask(priv, GSWIP_SDMA_PCTRL_EN, 0, + GSWIP_SDMA_PCTRLp(port)); +} + +static int gswip_pce_load_microcode(struct gswip_priv *priv) +{ + int i; + int err; + + gswip_switch_mask(priv, GSWIP_PCE_TBL_CTRL_ADDR_MASK | + GSWIP_PCE_TBL_CTRL_OPMOD_MASK, + GSWIP_PCE_TBL_CTRL_OPMOD_ADWR, GSWIP_PCE_TBL_CTRL); + gswip_switch_w(priv, 0, GSWIP_PCE_TBL_MASK); + + for (i = 0; i < ARRAY_SIZE(gswip_pce_microcode); i++) { + gswip_switch_w(priv, i, GSWIP_PCE_TBL_ADDR); + gswip_switch_w(priv, gswip_pce_microcode[i].val_0, + GSWIP_PCE_TBL_VAL(0)); + gswip_switch_w(priv, gswip_pce_microcode[i].val_1, + GSWIP_PCE_TBL_VAL(1)); + gswip_switch_w(priv, gswip_pce_microcode[i].val_2, + GSWIP_PCE_TBL_VAL(2)); + gswip_switch_w(priv, gswip_pce_microcode[i].val_3, + GSWIP_PCE_TBL_VAL(3)); + + /* start the table access: */ + gswip_switch_mask(priv, 0, GSWIP_PCE_TBL_CTRL_BAS, + GSWIP_PCE_TBL_CTRL); + err = gswip_switch_r_timeout(priv, GSWIP_PCE_TBL_CTRL, + GSWIP_PCE_TBL_CTRL_BAS); + if (err) + return err; + } + + /* tell the switch that the microcode is loaded */ + gswip_switch_mask(priv, 0, GSWIP_PCE_GCTRL_0_MC_VALID, + GSWIP_PCE_GCTRL_0); + + return 0; +} + +static int gswip_setup(struct dsa_switch *ds) +{ + struct gswip_priv *priv = ds->priv; + unsigned int cpu_port = priv->hw_info->cpu_port; + int i; + int err; + + gswip_switch_w(priv, GSWIP_SWRES_R0, GSWIP_SWRES); + usleep_range(5000, 10000); + gswip_switch_w(priv, 0, GSWIP_SWRES); + + /* disable port fetch/store dma on all ports */ + for (i = 0; i < priv->hw_info->max_ports; i++) + gswip_port_disable(ds, i, NULL); + + /* enable Switch */ + gswip_mdio_mask(priv, 0, GSWIP_MDIO_GLOB_ENABLE, GSWIP_MDIO_GLOB); + + err = gswip_pce_load_microcode(priv); + if (err) { + dev_err(priv->dev, "writing PCE microcode failed, %i", err); + return err; + } + + /* Default unknown Broadcast/Multicast/Unicast port maps */ + gswip_switch_w(priv, BIT(cpu_port), GSWIP_PCE_PMAP1); + gswip_switch_w(priv, BIT(cpu_port), GSWIP_PCE_PMAP2); + gswip_switch_w(priv, BIT(cpu_port), GSWIP_PCE_PMAP3); + + /* disable PHY auto polling */ + gswip_mdio_w(priv, 0x0, GSWIP_MDIO_MDC_CFG0); + /* Configure the MDIO Clock 2.5 MHz */ + gswip_mdio_mask(priv, 0xff, 0x09, GSWIP_MDIO_MDC_CFG1); + + /* Disable the xMII link */ + gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, 0, 0); + gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, 0, 1); + gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, 0, 5); + + /* enable special tag insertion on cpu port */ + gswip_switch_mask(priv, 0, GSWIP_FDMA_PCTRL_STEN, + GSWIP_FDMA_PCTRLp(cpu_port)); + + gswip_switch_mask(priv, 0, GSWIP_MAC_CTRL_2_MLEN, + GSWIP_MAC_CTRL_2p(cpu_port)); + gswip_switch_w(priv, VLAN_ETH_FRAME_LEN + 8, GSWIP_MAC_FLEN); + gswip_switch_mask(priv, 0, GSWIP_BM_QUEUE_GCTRL_GL_MOD, + GSWIP_BM_QUEUE_GCTRL); + + /* VLAN aware Switching */ + gswip_switch_mask(priv, 0, GSWIP_PCE_GCTRL_0_VLAN, GSWIP_PCE_GCTRL_0); + + /* Mac Address Table Lock */ + gswip_switch_mask(priv, 0, GSWIP_PCE_GCTRL_1_MAC_GLOCK | + GSWIP_PCE_GCTRL_1_MAC_GLOCK_MOD, + GSWIP_PCE_GCTRL_1); + + gswip_port_enable(ds, cpu_port, NULL); + return 0; +} + +static enum dsa_tag_protocol gswip_get_tag_protocol(struct dsa_switch *ds, + int port) +{ + return DSA_TAG_PROTO_GSWIP; +} + +static void gswip_phylink_validate(struct dsa_switch *ds, int port, + unsigned long *supported, + struct phylink_link_state *state) +{ + __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; + + switch (port) { + case 0: + case 1: + if (!phy_interface_mode_is_rgmii(state->interface) && + state->interface != PHY_INTERFACE_MODE_MII && + state->interface != PHY_INTERFACE_MODE_REVMII && + state->interface != PHY_INTERFACE_MODE_RMII) + goto unsupported; + break; + case 2: + case 3: + case 4: + if (state->interface != PHY_INTERFACE_MODE_INTERNAL) + goto unsupported; + break; + case 5: + if (!phy_interface_mode_is_rgmii(state->interface) && + state->interface != PHY_INTERFACE_MODE_INTERNAL) + goto unsupported; + break; + default: + bitmap_zero(supported, __ETHTOOL_LINK_MODE_MASK_NBITS); + dev_err(ds->dev, "Unsupported port: %i\n", port); + return; + } + + /* Allow all the expected bits */ + phylink_set(mask, Autoneg); + phylink_set_port_modes(mask); + phylink_set(mask, Pause); + phylink_set(mask, Asym_Pause); + + /* With the exclusion of MII and Reverse MII, we support Gigabit, + * including Half duplex + */ + if (state->interface != PHY_INTERFACE_MODE_MII && + state->interface != PHY_INTERFACE_MODE_REVMII) { + phylink_set(mask, 1000baseT_Full); + phylink_set(mask, 1000baseT_Half); + } + + phylink_set(mask, 10baseT_Half); + phylink_set(mask, 10baseT_Full); + phylink_set(mask, 100baseT_Half); + phylink_set(mask, 100baseT_Full); + + bitmap_and(supported, supported, mask, + __ETHTOOL_LINK_MODE_MASK_NBITS); + bitmap_and(state->advertising, state->advertising, mask, + __ETHTOOL_LINK_MODE_MASK_NBITS); + return; + +unsupported: + bitmap_zero(supported, __ETHTOOL_LINK_MODE_MASK_NBITS); + dev_err(ds->dev, "Unsupported interface: %d\n", state->interface); + return; +} + +static void gswip_phylink_mac_config(struct dsa_switch *ds, int port, + unsigned int mode, + const struct phylink_link_state *state) +{ + struct gswip_priv *priv = ds->priv; + u32 miicfg = 0; + + miicfg |= GSWIP_MII_CFG_LDCLKDIS; + + switch (state->interface) { + case PHY_INTERFACE_MODE_MII: + case PHY_INTERFACE_MODE_INTERNAL: + miicfg |= GSWIP_MII_CFG_MODE_MIIM; + break; + case PHY_INTERFACE_MODE_REVMII: + miicfg |= GSWIP_MII_CFG_MODE_MIIP; + break; + case PHY_INTERFACE_MODE_RMII: + miicfg |= GSWIP_MII_CFG_MODE_RMIIM; + break; + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_TXID: + miicfg |= GSWIP_MII_CFG_MODE_RGMII; + break; + default: + dev_err(ds->dev, + "Unsupported interface: %d\n", state->interface); + return; + } + gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_MODE_MASK, miicfg, port); + + switch (state->interface) { + case PHY_INTERFACE_MODE_RGMII_ID: + gswip_mii_mask_pcdu(priv, GSWIP_MII_PCDU_TXDLY_MASK | + GSWIP_MII_PCDU_RXDLY_MASK, 0, port); + break; + case PHY_INTERFACE_MODE_RGMII_RXID: + gswip_mii_mask_pcdu(priv, GSWIP_MII_PCDU_RXDLY_MASK, 0, port); + break; + case PHY_INTERFACE_MODE_RGMII_TXID: + gswip_mii_mask_pcdu(priv, GSWIP_MII_PCDU_TXDLY_MASK, 0, port); + break; + default: + break; + } +} + +static void gswip_phylink_mac_link_down(struct dsa_switch *ds, int port, + unsigned int mode, + phy_interface_t interface) +{ + struct gswip_priv *priv = ds->priv; + + gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, 0, port); +} + +static void gswip_phylink_mac_link_up(struct dsa_switch *ds, int port, + unsigned int mode, + phy_interface_t interface, + struct phy_device *phydev) +{ + struct gswip_priv *priv = ds->priv; + + /* Enable the xMII interface only for the external PHY */ + if (interface != PHY_INTERFACE_MODE_INTERNAL) + gswip_mii_mask_cfg(priv, 0, GSWIP_MII_CFG_EN, port); +} + +static void gswip_get_strings(struct dsa_switch *ds, int port, u32 stringset, + uint8_t *data) +{ + int i; + + if (stringset != ETH_SS_STATS) + return; + + for (i = 0; i < ARRAY_SIZE(gswip_rmon_cnt); i++) + strncpy(data + i * ETH_GSTRING_LEN, gswip_rmon_cnt[i].name, + ETH_GSTRING_LEN); +} + +static u32 gswip_bcm_ram_entry_read(struct gswip_priv *priv, u32 table, + u32 index) +{ + u32 result; + int err; + + gswip_switch_w(priv, index, GSWIP_BM_RAM_ADDR); + gswip_switch_mask(priv, GSWIP_BM_RAM_CTRL_ADDR_MASK | + GSWIP_BM_RAM_CTRL_OPMOD, + table | GSWIP_BM_RAM_CTRL_BAS, + GSWIP_BM_RAM_CTRL); + + err = gswip_switch_r_timeout(priv, GSWIP_BM_RAM_CTRL, + GSWIP_BM_RAM_CTRL_BAS); + if (err) { + dev_err(priv->dev, "timeout while reading table: %u, index: %u", + table, index); + return 0; + } + + result = gswip_switch_r(priv, GSWIP_BM_RAM_VAL(0)); + result |= gswip_switch_r(priv, GSWIP_BM_RAM_VAL(1)) << 16; + + return result; +} + +static void gswip_get_ethtool_stats(struct dsa_switch *ds, int port, + uint64_t *data) +{ + struct gswip_priv *priv = ds->priv; + const struct gswip_rmon_cnt_desc *rmon_cnt; + int i; + u64 high; + + for (i = 0; i < ARRAY_SIZE(gswip_rmon_cnt); i++) { + rmon_cnt = &gswip_rmon_cnt[i]; + + data[i] = gswip_bcm_ram_entry_read(priv, port, + rmon_cnt->offset); + if (rmon_cnt->size == 2) { + high = gswip_bcm_ram_entry_read(priv, port, + rmon_cnt->offset + 1); + data[i] |= high << 32; + } + } +} + +static int gswip_get_sset_count(struct dsa_switch *ds, int port, int sset) +{ + if (sset != ETH_SS_STATS) + return 0; + + return ARRAY_SIZE(gswip_rmon_cnt); +} + +static const struct dsa_switch_ops gswip_switch_ops = { + .get_tag_protocol = gswip_get_tag_protocol, + .setup = gswip_setup, + .port_enable = gswip_port_enable, + .port_disable = gswip_port_disable, + .phylink_validate = gswip_phylink_validate, + .phylink_mac_config = gswip_phylink_mac_config, + .phylink_mac_link_down = gswip_phylink_mac_link_down, + .phylink_mac_link_up = gswip_phylink_mac_link_up, + .get_strings = gswip_get_strings, + .get_ethtool_stats = gswip_get_ethtool_stats, + .get_sset_count = gswip_get_sset_count, +}; + +static const struct xway_gphy_match_data xrx200a1x_gphy_data = { + .fe_firmware_name = "lantiq/xrx200_phy22f_a14.bin", + .ge_firmware_name = "lantiq/xrx200_phy11g_a14.bin", +}; + +static const struct xway_gphy_match_data xrx200a2x_gphy_data = { + .fe_firmware_name = "lantiq/xrx200_phy22f_a22.bin", + .ge_firmware_name = "lantiq/xrx200_phy11g_a22.bin", +}; + +static const struct xway_gphy_match_data xrx300_gphy_data = { + .fe_firmware_name = "lantiq/xrx300_phy22f_a21.bin", + .ge_firmware_name = "lantiq/xrx300_phy11g_a21.bin", +}; + +static const struct of_device_id xway_gphy_match[] = { + { .compatible = "lantiq,xrx200-gphy-fw", .data = NULL }, + { .compatible = "lantiq,xrx200a1x-gphy-fw", .data = &xrx200a1x_gphy_data }, + { .compatible = "lantiq,xrx200a2x-gphy-fw", .data = &xrx200a2x_gphy_data }, + { .compatible = "lantiq,xrx300-gphy-fw", .data = &xrx300_gphy_data }, + { .compatible = "lantiq,xrx330-gphy-fw", .data = &xrx300_gphy_data }, + {}, +}; + +static int gswip_gphy_fw_load(struct gswip_priv *priv, struct gswip_gphy_fw *gphy_fw) +{ + struct device *dev = priv->dev; + const struct firmware *fw; + void *fw_addr; + dma_addr_t dma_addr; + dma_addr_t dev_addr; + size_t size; + int ret; + + ret = clk_prepare_enable(gphy_fw->clk_gate); + if (ret) + return ret; + + reset_control_assert(gphy_fw->reset); + + ret = request_firmware(&fw, gphy_fw->fw_name, dev); + if (ret) { + dev_err(dev, "failed to load firmware: %s, error: %i\n", + gphy_fw->fw_name, ret); + return ret; + } + + /* GPHY cores need the firmware code in a persistent and contiguous + * memory area with a 16 kB boundary aligned start address. + */ + size = fw->size + XRX200_GPHY_FW_ALIGN; + + fw_addr = dmam_alloc_coherent(dev, size, &dma_addr, GFP_KERNEL); + if (fw_addr) { + fw_addr = PTR_ALIGN(fw_addr, XRX200_GPHY_FW_ALIGN); + dev_addr = ALIGN(dma_addr, XRX200_GPHY_FW_ALIGN); + memcpy(fw_addr, fw->data, fw->size); + } else { + dev_err(dev, "failed to alloc firmware memory\n"); + release_firmware(fw); + return -ENOMEM; + } + + release_firmware(fw); + + ret = regmap_write(priv->rcu_regmap, gphy_fw->fw_addr_offset, dev_addr); + if (ret) + return ret; + + reset_control_deassert(gphy_fw->reset); + + return ret; +} + +static int gswip_gphy_fw_probe(struct gswip_priv *priv, + struct gswip_gphy_fw *gphy_fw, + struct device_node *gphy_fw_np, int i) +{ + struct device *dev = priv->dev; + u32 gphy_mode; + int ret; + char gphyname[10]; + + snprintf(gphyname, sizeof(gphyname), "gphy%d", i); + + gphy_fw->clk_gate = devm_clk_get(dev, gphyname); + if (IS_ERR(gphy_fw->clk_gate)) { + dev_err(dev, "Failed to lookup gate clock\n"); + return PTR_ERR(gphy_fw->clk_gate); + } + + ret = of_property_read_u32(gphy_fw_np, "reg", &gphy_fw->fw_addr_offset); + if (ret) + return ret; + + ret = of_property_read_u32(gphy_fw_np, "lantiq,gphy-mode", &gphy_mode); + /* Default to GE mode */ + if (ret) + gphy_mode = GPHY_MODE_GE; + + switch (gphy_mode) { + case GPHY_MODE_FE: + gphy_fw->fw_name = priv->gphy_fw_name_cfg->fe_firmware_name; + break; + case GPHY_MODE_GE: + gphy_fw->fw_name = priv->gphy_fw_name_cfg->ge_firmware_name; + break; + default: + dev_err(dev, "Unknown GPHY mode %d\n", gphy_mode); + return -EINVAL; + } + + gphy_fw->reset = of_reset_control_array_get_exclusive(gphy_fw_np); + if (IS_ERR(gphy_fw->reset)) { + if (PTR_ERR(gphy_fw->reset) != -EPROBE_DEFER) + dev_err(dev, "Failed to lookup gphy reset\n"); + return PTR_ERR(gphy_fw->reset); + } + + return gswip_gphy_fw_load(priv, gphy_fw); +} + +static void gswip_gphy_fw_remove(struct gswip_priv *priv, + struct gswip_gphy_fw *gphy_fw) +{ + int ret; + + /* check if the device was fully probed */ + if (!gphy_fw->fw_name) + return; + + ret = regmap_write(priv->rcu_regmap, gphy_fw->fw_addr_offset, 0); + if (ret) + dev_err(priv->dev, "can not reset GPHY FW pointer"); + + clk_disable_unprepare(gphy_fw->clk_gate); + + reset_control_put(gphy_fw->reset); +} + +static int gswip_gphy_fw_list(struct gswip_priv *priv, + struct device_node *gphy_fw_list_np, u32 version) +{ + struct device *dev = priv->dev; + struct device_node *gphy_fw_np; + const struct of_device_id *match; + int err; + int i = 0; + + /* The VRX200 rev 1.1 uses the GSWIP 2.0 and needs the older + * GPHY firmware. The VRX200 rev 1.2 uses the GSWIP 2.1 and also + * needs a different GPHY firmware. + */ + if (of_device_is_compatible(gphy_fw_list_np, "lantiq,xrx200-gphy-fw")) { + switch (version) { + case GSWIP_VERSION_2_0: + priv->gphy_fw_name_cfg = &xrx200a1x_gphy_data; + break; + case GSWIP_VERSION_2_1: + priv->gphy_fw_name_cfg = &xrx200a2x_gphy_data; + break; + default: + dev_err(dev, "unknown GSWIP version: 0x%x", version); + return -ENOENT; + } + } + + match = of_match_node(xway_gphy_match, gphy_fw_list_np); + if (match && match->data) + priv->gphy_fw_name_cfg = match->data; + + if (!priv->gphy_fw_name_cfg) { + dev_err(dev, "GPHY compatible type not supported"); + return -ENOENT; + } + + priv->num_gphy_fw = of_get_available_child_count(gphy_fw_list_np); + if (!priv->num_gphy_fw) + return -ENOENT; + + priv->rcu_regmap = syscon_regmap_lookup_by_phandle(gphy_fw_list_np, + "lantiq,rcu"); + if (IS_ERR(priv->rcu_regmap)) + return PTR_ERR(priv->rcu_regmap); + + priv->gphy_fw = devm_kmalloc_array(dev, priv->num_gphy_fw, + sizeof(*priv->gphy_fw), + GFP_KERNEL | __GFP_ZERO); + if (!priv->gphy_fw) + return -ENOMEM; + + for_each_available_child_of_node(gphy_fw_list_np, gphy_fw_np) { + err = gswip_gphy_fw_probe(priv, &priv->gphy_fw[i], + gphy_fw_np, i); + if (err) + goto remove_gphy; + i++; + } + + return 0; + +remove_gphy: + for (i = 0; i < priv->num_gphy_fw; i++) + gswip_gphy_fw_remove(priv, &priv->gphy_fw[i]); + return err; +} + +static int gswip_probe(struct platform_device *pdev) +{ + struct gswip_priv *priv; + struct resource *gswip_res, *mdio_res, *mii_res; + struct device_node *mdio_np, *gphy_fw_np; + struct device *dev = &pdev->dev; + int err; + int i; + u32 version; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + gswip_res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + priv->gswip = devm_ioremap_resource(dev, gswip_res); + if (IS_ERR(priv->gswip)) + return PTR_ERR(priv->gswip); + + mdio_res = platform_get_resource(pdev, IORESOURCE_MEM, 1); + priv->mdio = devm_ioremap_resource(dev, mdio_res); + if (IS_ERR(priv->mdio)) + return PTR_ERR(priv->mdio); + + mii_res = platform_get_resource(pdev, IORESOURCE_MEM, 2); + priv->mii = devm_ioremap_resource(dev, mii_res); + if (IS_ERR(priv->mii)) + return PTR_ERR(priv->mii); + + priv->hw_info = of_device_get_match_data(dev); + if (!priv->hw_info) + return -EINVAL; + + priv->ds = dsa_switch_alloc(dev, priv->hw_info->max_ports); + if (!priv->ds) + return -ENOMEM; + + priv->ds->priv = priv; + priv->ds->ops = &gswip_switch_ops; + priv->dev = dev; + version = gswip_switch_r(priv, GSWIP_VERSION); + + /* bring up the mdio bus */ + gphy_fw_np = of_find_compatible_node(pdev->dev.of_node, NULL, + "lantiq,gphy-fw"); + if (gphy_fw_np) { + err = gswip_gphy_fw_list(priv, gphy_fw_np, version); + if (err) { + dev_err(dev, "gphy fw probe failed\n"); + return err; + } + } + + /* bring up the mdio bus */ + mdio_np = of_find_compatible_node(pdev->dev.of_node, NULL, + "lantiq,xrx200-mdio"); + if (mdio_np) { + err = gswip_mdio(priv, mdio_np); + if (err) { + dev_err(dev, "mdio probe failed\n"); + goto gphy_fw; + } + } + + err = dsa_register_switch(priv->ds); + if (err) { + dev_err(dev, "dsa switch register failed: %i\n", err); + goto mdio_bus; + } + if (!dsa_is_cpu_port(priv->ds, priv->hw_info->cpu_port)) { + dev_err(dev, "wrong CPU port defined, HW only supports port: %i", + priv->hw_info->cpu_port); + err = -EINVAL; + goto mdio_bus; + } + + platform_set_drvdata(pdev, priv); + + dev_info(dev, "probed GSWIP version %lx mod %lx\n", + (version & GSWIP_VERSION_REV_MASK) >> GSWIP_VERSION_REV_SHIFT, + (version & GSWIP_VERSION_MOD_MASK) >> GSWIP_VERSION_MOD_SHIFT); + return 0; + +mdio_bus: + if (mdio_np) + mdiobus_unregister(priv->ds->slave_mii_bus); +gphy_fw: + for (i = 0; i < priv->num_gphy_fw; i++) + gswip_gphy_fw_remove(priv, &priv->gphy_fw[i]); + return err; +} + +static int gswip_remove(struct platform_device *pdev) +{ + struct gswip_priv *priv = platform_get_drvdata(pdev); + int i; + + if (!priv) + return 0; + + /* disable the switch */ + gswip_mdio_mask(priv, GSWIP_MDIO_GLOB_ENABLE, 0, GSWIP_MDIO_GLOB); + + dsa_unregister_switch(priv->ds); + + if (priv->ds->slave_mii_bus) + mdiobus_unregister(priv->ds->slave_mii_bus); + + for (i = 0; i < priv->num_gphy_fw; i++) + gswip_gphy_fw_remove(priv, &priv->gphy_fw[i]); + + return 0; +} + +static const struct gswip_hw_info gswip_xrx200 = { + .max_ports = 7, + .cpu_port = 6, +}; + +static const struct of_device_id gswip_of_match[] = { + { .compatible = "lantiq,xrx200-gswip", .data = &gswip_xrx200 }, + {}, +}; +MODULE_DEVICE_TABLE(of, gswip_of_match); + +static struct platform_driver gswip_driver = { + .probe = gswip_probe, + .remove = gswip_remove, + .driver = { + .name = "gswip", + .of_match_table = gswip_of_match, + }, +}; + +module_platform_driver(gswip_driver); + +MODULE_AUTHOR("Hauke Mehrtens <hauke@hauke-m.de>"); +MODULE_DESCRIPTION("Lantiq / Intel GSWIP driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/dsa/lantiq_pce.h b/drivers/net/dsa/lantiq_pce.h new file mode 100644 index 000000000000..180663138e75 --- /dev/null +++ b/drivers/net/dsa/lantiq_pce.h @@ -0,0 +1,153 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCE microcode extracted from UGW 7.1.1 switch api + * + * Copyright (c) 2012, 2014, 2015 Lantiq Deutschland GmbH + * Copyright (C) 2012 John Crispin <john@phrozen.org> + * Copyright (C) 2017 - 2018 Hauke Mehrtens <hauke@hauke-m.de> + */ + +enum { + OUT_MAC0 = 0, + OUT_MAC1, + OUT_MAC2, + OUT_MAC3, + OUT_MAC4, + OUT_MAC5, + OUT_ETHTYP, + OUT_VTAG0, + OUT_VTAG1, + OUT_ITAG0, + OUT_ITAG1, /*10 */ + OUT_ITAG2, + OUT_ITAG3, + OUT_IP0, + OUT_IP1, + OUT_IP2, + OUT_IP3, + OUT_SIP0, + OUT_SIP1, + OUT_SIP2, + OUT_SIP3, /*20*/ + OUT_SIP4, + OUT_SIP5, + OUT_SIP6, + OUT_SIP7, + OUT_DIP0, + OUT_DIP1, + OUT_DIP2, + OUT_DIP3, + OUT_DIP4, + OUT_DIP5, /*30*/ + OUT_DIP6, + OUT_DIP7, + OUT_SESID, + OUT_PROT, + OUT_APP0, + OUT_APP1, + OUT_IGMP0, + OUT_IGMP1, + OUT_IPOFF, /*39*/ + OUT_NONE = 63, +}; + +/* parser's microcode length type */ +#define INSTR 0 +#define IPV6 1 +#define LENACCU 2 + +/* parser's microcode flag type */ +enum { + FLAG_ITAG = 0, + FLAG_VLAN, + FLAG_SNAP, + FLAG_PPPOE, + FLAG_IPV6, + FLAG_IPV6FL, + FLAG_IPV4, + FLAG_IGMP, + FLAG_TU, + FLAG_HOP, + FLAG_NN1, /*10 */ + FLAG_NN2, + FLAG_END, + FLAG_NO, /*13*/ +}; + +struct gswip_pce_microcode { + u16 val_3; + u16 val_2; + u16 val_1; + u16 val_0; +}; + +#define MC_ENTRY(val, msk, ns, out, len, type, flags, ipv4_len) \ + { val, msk, ((ns) << 10 | (out) << 4 | (len) >> 1),\ + ((len) & 1) << 15 | (type) << 13 | (flags) << 9 | (ipv4_len) << 8 } +static const struct gswip_pce_microcode gswip_pce_microcode[] = { + /* value mask ns fields L type flags ipv4_len */ + MC_ENTRY(0x88c3, 0xFFFF, 1, OUT_ITAG0, 4, INSTR, FLAG_ITAG, 0), + MC_ENTRY(0x8100, 0xFFFF, 2, OUT_VTAG0, 2, INSTR, FLAG_VLAN, 0), + MC_ENTRY(0x88A8, 0xFFFF, 1, OUT_VTAG0, 2, INSTR, FLAG_VLAN, 0), + MC_ENTRY(0x8100, 0xFFFF, 1, OUT_VTAG0, 2, INSTR, FLAG_VLAN, 0), + MC_ENTRY(0x8864, 0xFFFF, 17, OUT_ETHTYP, 1, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0800, 0xFFFF, 21, OUT_ETHTYP, 1, INSTR, FLAG_NO, 0), + MC_ENTRY(0x86DD, 0xFFFF, 22, OUT_ETHTYP, 1, INSTR, FLAG_NO, 0), + MC_ENTRY(0x8863, 0xFFFF, 16, OUT_ETHTYP, 1, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0000, 0xF800, 10, OUT_NONE, 0, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0000, 0x0000, 40, OUT_ETHTYP, 1, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0600, 0x0600, 40, OUT_ETHTYP, 1, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0000, 0x0000, 12, OUT_NONE, 1, INSTR, FLAG_NO, 0), + MC_ENTRY(0xAAAA, 0xFFFF, 14, OUT_NONE, 1, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0300, 0xFF00, 41, OUT_NONE, 0, INSTR, FLAG_SNAP, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_DIP7, 3, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0000, 0x0000, 18, OUT_DIP7, 3, INSTR, FLAG_PPPOE, 0), + MC_ENTRY(0x0021, 0xFFFF, 21, OUT_NONE, 1, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0057, 0xFFFF, 22, OUT_NONE, 1, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0000, 0x0000, 40, OUT_NONE, 0, INSTR, FLAG_NO, 0), + MC_ENTRY(0x4000, 0xF000, 24, OUT_IP0, 4, INSTR, FLAG_IPV4, 1), + MC_ENTRY(0x6000, 0xF000, 27, OUT_IP0, 3, INSTR, FLAG_IPV6, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0000, 0x0000, 25, OUT_IP3, 2, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0000, 0x0000, 26, OUT_SIP0, 4, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0000, 0x0000, 40, OUT_NONE, 0, LENACCU, FLAG_NO, 0), + MC_ENTRY(0x1100, 0xFF00, 39, OUT_PROT, 1, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0600, 0xFF00, 39, OUT_PROT, 1, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0000, 0xFF00, 33, OUT_IP3, 17, INSTR, FLAG_HOP, 0), + MC_ENTRY(0x2B00, 0xFF00, 33, OUT_IP3, 17, INSTR, FLAG_NN1, 0), + MC_ENTRY(0x3C00, 0xFF00, 33, OUT_IP3, 17, INSTR, FLAG_NN2, 0), + MC_ENTRY(0x0000, 0x0000, 39, OUT_PROT, 1, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0000, 0x00E0, 35, OUT_NONE, 0, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0000, 0x0000, 40, OUT_NONE, 0, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0000, 0xFF00, 33, OUT_NONE, 0, IPV6, FLAG_HOP, 0), + MC_ENTRY(0x2B00, 0xFF00, 33, OUT_NONE, 0, IPV6, FLAG_NN1, 0), + MC_ENTRY(0x3C00, 0xFF00, 33, OUT_NONE, 0, IPV6, FLAG_NN2, 0), + MC_ENTRY(0x0000, 0x0000, 40, OUT_PROT, 1, IPV6, FLAG_NO, 0), + MC_ENTRY(0x0000, 0x0000, 40, OUT_SIP0, 16, INSTR, FLAG_NO, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_APP0, 4, INSTR, FLAG_IGMP, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), + MC_ENTRY(0x0000, 0x0000, 41, OUT_NONE, 0, INSTR, FLAG_END, 0), +}; diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 8da3d39e3218..78ce820b5257 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -434,7 +434,7 @@ static int mv88e6xxx_g1_irq_setup(struct mv88e6xxx_chip *chip) err = request_threaded_irq(chip->irq, NULL, mv88e6xxx_g1_irq_thread_fn, - IRQF_ONESHOT, + IRQF_ONESHOT | IRQF_SHARED, dev_name(chip->dev), chip); if (err) mv88e6xxx_g1_irq_free_common(chip); @@ -575,6 +575,13 @@ restore_link: return err; } +static int mv88e6xxx_phy_is_internal(struct dsa_switch *ds, int port) +{ + struct mv88e6xxx_chip *chip = ds->priv; + + return port < chip->info->num_internal_phys; +} + /* We expect the switch to perform auto negotiation if there is a real * phy. However, in the case of a fixed link phy, we force the port * settings from the fixed link settings. @@ -585,7 +592,8 @@ static void mv88e6xxx_adjust_link(struct dsa_switch *ds, int port, struct mv88e6xxx_chip *chip = ds->priv; int err; - if (!phy_is_pseudo_fixed_link(phydev)) + if (!phy_is_pseudo_fixed_link(phydev) && + mv88e6xxx_phy_is_internal(ds, port)) return; mutex_lock(&chip->reg_lock); @@ -709,13 +717,17 @@ static void mv88e6xxx_mac_config(struct dsa_switch *ds, int port, struct mv88e6xxx_chip *chip = ds->priv; int speed, duplex, link, pause, err; - if (mode == MLO_AN_PHY) + if ((mode == MLO_AN_PHY) && mv88e6xxx_phy_is_internal(ds, port)) return; if (mode == MLO_AN_FIXED) { link = LINK_FORCED_UP; speed = state->speed; duplex = state->duplex; + } else if (!mv88e6xxx_phy_is_internal(ds, port)) { + link = state->link; + speed = state->speed; + duplex = state->duplex; } else { speed = SPEED_UNFORCED; duplex = DUPLEX_UNFORCED; @@ -3160,6 +3172,8 @@ static const struct mv88e6xxx_ops mv88e6176_ops = { .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, .serdes_power = mv88e6352_serdes_power, + .serdes_irq_setup = mv88e6352_serdes_irq_setup, + .serdes_irq_free = mv88e6352_serdes_irq_free, .gpio_ops = &mv88e6352_gpio_ops, .phylink_validate = mv88e6352_phylink_validate, }; @@ -3366,6 +3380,8 @@ static const struct mv88e6xxx_ops mv88e6240_ops = { .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, .serdes_power = mv88e6352_serdes_power, + .serdes_irq_setup = mv88e6352_serdes_irq_setup, + .serdes_irq_free = mv88e6352_serdes_irq_free, .gpio_ops = &mv88e6352_gpio_ops, .avb_ops = &mv88e6352_avb_ops, .ptp_ops = &mv88e6352_ptp_ops, @@ -3664,6 +3680,8 @@ static const struct mv88e6xxx_ops mv88e6352_ops = { .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, .serdes_power = mv88e6352_serdes_power, + .serdes_irq_setup = mv88e6352_serdes_irq_setup, + .serdes_irq_free = mv88e6352_serdes_irq_free, .gpio_ops = &mv88e6352_gpio_ops, .avb_ops = &mv88e6352_avb_ops, .ptp_ops = &mv88e6352_ptp_ops, diff --git a/drivers/net/dsa/mv88e6xxx/global1.h b/drivers/net/dsa/mv88e6xxx/global1.h index 7c791c1da4b9..bef01331266f 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.h +++ b/drivers/net/dsa/mv88e6xxx/global1.h @@ -128,7 +128,7 @@ #define MV88E6XXX_G1_ATU_OP_GET_CLR_VIOLATION 0x7000 #define MV88E6XXX_G1_ATU_OP_AGE_OUT_VIOLATION BIT(7) #define MV88E6XXX_G1_ATU_OP_MEMBER_VIOLATION BIT(6) -#define MV88E6XXX_G1_ATU_OP_MISS_VIOLTATION BIT(5) +#define MV88E6XXX_G1_ATU_OP_MISS_VIOLATION BIT(5) #define MV88E6XXX_G1_ATU_OP_FULL_VIOLATION BIT(4) /* Offset 0x0C: ATU Data Register */ diff --git a/drivers/net/dsa/mv88e6xxx/global1_atu.c b/drivers/net/dsa/mv88e6xxx/global1_atu.c index 307410898fc9..5200e4bdce93 100644 --- a/drivers/net/dsa/mv88e6xxx/global1_atu.c +++ b/drivers/net/dsa/mv88e6xxx/global1_atu.c @@ -349,7 +349,7 @@ static irqreturn_t mv88e6xxx_g1_atu_prob_irq_thread_fn(int irq, void *dev_id) chip->ports[entry.portvec].atu_member_violation++; } - if (val & MV88E6XXX_G1_ATU_OP_MEMBER_VIOLATION) { + if (val & MV88E6XXX_G1_ATU_OP_MISS_VIOLATION) { dev_err_ratelimited(chip->dev, "ATU miss violation for %pM portvec %x\n", entry.mac, entry.portvec); diff --git a/drivers/net/dsa/mv88e6xxx/phy.c b/drivers/net/dsa/mv88e6xxx/phy.c index 46af8052e535..152a65d46e0b 100644 --- a/drivers/net/dsa/mv88e6xxx/phy.c +++ b/drivers/net/dsa/mv88e6xxx/phy.c @@ -110,6 +110,9 @@ int mv88e6xxx_phy_page_write(struct mv88e6xxx_chip *chip, int phy, err = mv88e6xxx_phy_page_get(chip, phy, page); if (!err) { err = mv88e6xxx_phy_write(chip, phy, MV88E6XXX_PHY_PAGE, page); + if (!err) + err = mv88e6xxx_phy_write(chip, phy, reg, val); + mv88e6xxx_phy_page_put(chip, phy); } diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c index e82983975754..bb69650ff772 100644 --- a/drivers/net/dsa/mv88e6xxx/serdes.c +++ b/drivers/net/dsa/mv88e6xxx/serdes.c @@ -185,6 +185,111 @@ int mv88e6352_serdes_get_stats(struct mv88e6xxx_chip *chip, int port, return ARRAY_SIZE(mv88e6352_serdes_hw_stats); } +static void mv88e6352_serdes_irq_link(struct mv88e6xxx_chip *chip, int port) +{ + struct dsa_switch *ds = chip->ds; + u16 status; + bool up; + + mv88e6352_serdes_read(chip, MII_BMSR, &status); + + /* Status must be read twice in order to give the current link + * status. Otherwise the change in link status since the last + * read of the register is returned. + */ + mv88e6352_serdes_read(chip, MII_BMSR, &status); + + up = status & BMSR_LSTATUS; + + dsa_port_phylink_mac_change(ds, port, up); +} + +static irqreturn_t mv88e6352_serdes_thread_fn(int irq, void *dev_id) +{ + struct mv88e6xxx_port *port = dev_id; + struct mv88e6xxx_chip *chip = port->chip; + irqreturn_t ret = IRQ_NONE; + u16 status; + int err; + + mutex_lock(&chip->reg_lock); + + err = mv88e6352_serdes_read(chip, MV88E6352_SERDES_INT_STATUS, &status); + if (err) + goto out; + + if (status & MV88E6352_SERDES_INT_LINK_CHANGE) { + ret = IRQ_HANDLED; + mv88e6352_serdes_irq_link(chip, port->port); + } +out: + mutex_unlock(&chip->reg_lock); + + return ret; +} + +static int mv88e6352_serdes_irq_enable(struct mv88e6xxx_chip *chip) +{ + return mv88e6352_serdes_write(chip, MV88E6352_SERDES_INT_ENABLE, + MV88E6352_SERDES_INT_LINK_CHANGE); +} + +static int mv88e6352_serdes_irq_disable(struct mv88e6xxx_chip *chip) +{ + return mv88e6352_serdes_write(chip, MV88E6352_SERDES_INT_ENABLE, 0); +} + +int mv88e6352_serdes_irq_setup(struct mv88e6xxx_chip *chip, int port) +{ + int err; + + if (!mv88e6352_port_has_serdes(chip, port)) + return 0; + + chip->ports[port].serdes_irq = irq_find_mapping(chip->g2_irq.domain, + MV88E6352_SERDES_IRQ); + if (chip->ports[port].serdes_irq < 0) { + dev_err(chip->dev, "Unable to map SERDES irq: %d\n", + chip->ports[port].serdes_irq); + return chip->ports[port].serdes_irq; + } + + /* Requesting the IRQ will trigger irq callbacks. So we cannot + * hold the reg_lock. + */ + mutex_unlock(&chip->reg_lock); + err = request_threaded_irq(chip->ports[port].serdes_irq, NULL, + mv88e6352_serdes_thread_fn, + IRQF_ONESHOT, "mv88e6xxx-serdes", + &chip->ports[port]); + mutex_lock(&chip->reg_lock); + + if (err) { + dev_err(chip->dev, "Unable to request SERDES interrupt: %d\n", + err); + return err; + } + + return mv88e6352_serdes_irq_enable(chip); +} + +void mv88e6352_serdes_irq_free(struct mv88e6xxx_chip *chip, int port) +{ + if (!mv88e6352_port_has_serdes(chip, port)) + return; + + mv88e6352_serdes_irq_disable(chip); + + /* Freeing the IRQ will trigger irq callbacks. So we cannot + * hold the reg_lock. + */ + mutex_unlock(&chip->reg_lock); + free_irq(chip->ports[port].serdes_irq, &chip->ports[port]); + mutex_lock(&chip->reg_lock); + + chip->ports[port].serdes_irq = 0; +} + /* Return the SERDES lane address a port is using. Only Ports 9 and 10 * have SERDES lanes. Returns -ENODEV if a port does not have a lane. */ diff --git a/drivers/net/dsa/mv88e6xxx/serdes.h b/drivers/net/dsa/mv88e6xxx/serdes.h index b1496de9c6fe..7870c5a9ef12 100644 --- a/drivers/net/dsa/mv88e6xxx/serdes.h +++ b/drivers/net/dsa/mv88e6xxx/serdes.h @@ -18,6 +18,19 @@ #define MV88E6352_ADDR_SERDES 0x0f #define MV88E6352_SERDES_PAGE_FIBER 0x01 +#define MV88E6352_SERDES_IRQ 0x0b +#define MV88E6352_SERDES_INT_ENABLE 0x12 +#define MV88E6352_SERDES_INT_SPEED_CHANGE BIT(14) +#define MV88E6352_SERDES_INT_DUPLEX_CHANGE BIT(13) +#define MV88E6352_SERDES_INT_PAGE_RX BIT(12) +#define MV88E6352_SERDES_INT_AN_COMPLETE BIT(11) +#define MV88E6352_SERDES_INT_LINK_CHANGE BIT(10) +#define MV88E6352_SERDES_INT_SYMBOL_ERROR BIT(9) +#define MV88E6352_SERDES_INT_FALSE_CARRIER BIT(8) +#define MV88E6352_SERDES_INT_FIFO_OVER_UNDER BIT(7) +#define MV88E6352_SERDES_INT_FIBRE_ENERGY BIT(4) +#define MV88E6352_SERDES_INT_STATUS 0x13 + #define MV88E6341_ADDR_SERDES 0x15 @@ -73,5 +86,8 @@ int mv88e6390_serdes_irq_enable(struct mv88e6xxx_chip *chip, int port, int lane); int mv88e6390_serdes_irq_disable(struct mv88e6xxx_chip *chip, int port, int lane); +int mv88e6352_serdes_irq_setup(struct mv88e6xxx_chip *chip, int port); +void mv88e6352_serdes_irq_free(struct mv88e6xxx_chip *chip, int port); + #endif diff --git a/drivers/net/ethernet/8390/ax88796.c b/drivers/net/ethernet/8390/ax88796.c index 2a0ddec1dd56..3dcc61821ed5 100644 --- a/drivers/net/ethernet/8390/ax88796.c +++ b/drivers/net/ethernet/8390/ax88796.c @@ -377,9 +377,7 @@ static int ax_mii_probe(struct net_device *dev) return ret; } - /* mask with MAC supported features */ - phy_dev->supported &= PHY_BASIC_FEATURES; - phy_dev->advertising = phy_dev->supported; + phy_set_max_speed(phy_dev, SPEED_100); netdev_info(dev, "PHY driver [%s] (mii_bus:phy_addr=%s, irq=%d)\n", phy_dev->drv->name, phydev_name(phy_dev), phy_dev->irq); diff --git a/drivers/net/ethernet/8390/etherh.c b/drivers/net/ethernet/8390/etherh.c index 32e9627e3880..77191a281866 100644 --- a/drivers/net/ethernet/8390/etherh.c +++ b/drivers/net/ethernet/8390/etherh.c @@ -564,26 +564,29 @@ static void etherh_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *i sizeof(info->bus_info)); } -static int etherh_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int etherh_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { - cmd->supported = etherh_priv(dev)->supported; - ethtool_cmd_speed_set(cmd, SPEED_10); - cmd->duplex = DUPLEX_HALF; - cmd->port = dev->if_port == IF_PORT_10BASET ? PORT_TP : PORT_BNC; - cmd->autoneg = (dev->flags & IFF_AUTOMEDIA ? - AUTONEG_ENABLE : AUTONEG_DISABLE); + ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported, + etherh_priv(dev)->supported); + cmd->base.speed = SPEED_10; + cmd->base.duplex = DUPLEX_HALF; + cmd->base.port = dev->if_port == IF_PORT_10BASET ? PORT_TP : PORT_BNC; + cmd->base.autoneg = (dev->flags & IFF_AUTOMEDIA ? AUTONEG_ENABLE : + AUTONEG_DISABLE); return 0; } -static int etherh_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) +static int etherh_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { - switch (cmd->autoneg) { + switch (cmd->base.autoneg) { case AUTONEG_ENABLE: dev->flags |= IFF_AUTOMEDIA; break; case AUTONEG_DISABLE: - switch (cmd->port) { + switch (cmd->base.port) { case PORT_TP: dev->if_port = IF_PORT_10BASET; break; @@ -622,12 +625,12 @@ static void etherh_set_msglevel(struct net_device *dev, u32 v) } static const struct ethtool_ops etherh_ethtool_ops = { - .get_settings = etherh_get_settings, - .set_settings = etherh_set_settings, - .get_drvinfo = etherh_get_drvinfo, - .get_ts_info = ethtool_op_get_ts_info, - .get_msglevel = etherh_get_msglevel, - .set_msglevel = etherh_set_msglevel, + .get_drvinfo = etherh_get_drvinfo, + .get_ts_info = ethtool_op_get_ts_info, + .get_msglevel = etherh_get_msglevel, + .set_msglevel = etherh_set_msglevel, + .get_link_ksettings = etherh_get_link_ksettings, + .set_link_ksettings = etherh_set_link_ksettings, }; static const struct net_device_ops etherh_netdev_ops = { diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig index 6fde68aa13a4..885e00d17807 100644 --- a/drivers/net/ethernet/Kconfig +++ b/drivers/net/ethernet/Kconfig @@ -108,6 +108,13 @@ config LANTIQ_ETOP ---help--- Support for the MII0 inside the Lantiq SoC +config LANTIQ_XRX200 + tristate "Lantiq / Intel xRX200 PMAC network driver" + depends on SOC_TYPE_XWAY + ---help--- + Support for the PMAC of the Gigabit switch (GSWIP) inside the + Lantiq / Intel VRX200 VDSL SoC + source "drivers/net/ethernet/marvell/Kconfig" source "drivers/net/ethernet/mediatek/Kconfig" source "drivers/net/ethernet/mellanox/Kconfig" diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile index b45d5f626b59..7b5bf9682066 100644 --- a/drivers/net/ethernet/Makefile +++ b/drivers/net/ethernet/Makefile @@ -49,6 +49,7 @@ obj-$(CONFIG_NET_VENDOR_XSCALE) += xscale/ obj-$(CONFIG_JME) += jme.o obj-$(CONFIG_KORINA) += korina.o obj-$(CONFIG_LANTIQ_ETOP) += lantiq_etop.o +obj-$(CONFIG_LANTIQ_XRX200) += lantiq_xrx200.o obj-$(CONFIG_NET_VENDOR_MARVELL) += marvell/ obj-$(CONFIG_NET_VENDOR_MEDIATEK) += mediatek/ obj-$(CONFIG_NET_VENDOR_MELLANOX) += mellanox/ diff --git a/drivers/net/ethernet/aeroflex/greth.c b/drivers/net/ethernet/aeroflex/greth.c index 4309be3724ad..7c9348a26cbb 100644 --- a/drivers/net/ethernet/aeroflex/greth.c +++ b/drivers/net/ethernet/aeroflex/greth.c @@ -1279,9 +1279,9 @@ static int greth_mdio_probe(struct net_device *dev) } if (greth->gbit_mac) - phy->supported &= PHY_GBIT_FEATURES; + phy_set_max_speed(phy, SPEED_1000); else - phy->supported &= PHY_BASIC_FEATURES; + phy_set_max_speed(phy, SPEED_100); phy->advertising = phy->supported; diff --git a/drivers/net/ethernet/agere/et131x.c b/drivers/net/ethernet/agere/et131x.c index 48220b6c600d..ea34bcb868b5 100644 --- a/drivers/net/ethernet/agere/et131x.c +++ b/drivers/net/ethernet/agere/et131x.c @@ -3258,19 +3258,11 @@ static int et131x_mii_probe(struct net_device *netdev) return PTR_ERR(phydev); } - phydev->supported &= (SUPPORTED_10baseT_Half | - SUPPORTED_10baseT_Full | - SUPPORTED_100baseT_Half | - SUPPORTED_100baseT_Full | - SUPPORTED_Autoneg | - SUPPORTED_MII | - SUPPORTED_TP); + phy_set_max_speed(phydev, SPEED_100); if (adapter->pdev->device != ET131X_PCI_DEVICE_ID_FAST) - phydev->supported |= SUPPORTED_1000baseT_Half | - SUPPORTED_1000baseT_Full; + phy_set_max_speed(phydev, SPEED_1000); - phydev->advertising = phydev->supported; phydev->autoneg = AUTONEG_ENABLE; phy_attached_info(phydev); diff --git a/drivers/net/ethernet/alacritech/slic.h b/drivers/net/ethernet/alacritech/slic.h index d0c388cfd52f..3add305d34b4 100644 --- a/drivers/net/ethernet/alacritech/slic.h +++ b/drivers/net/ethernet/alacritech/slic.h @@ -8,7 +8,6 @@ #include <linux/spinlock_types.h> #include <linux/dma-mapping.h> #include <linux/pci.h> -#include <linux/netdevice.h> #include <linux/list.h> #include <linux/u64_stats_sync.h> diff --git a/drivers/net/ethernet/allwinner/sun4i-emac.c b/drivers/net/ethernet/allwinner/sun4i-emac.c index 3143de45baaa..e1acafa82214 100644 --- a/drivers/net/ethernet/allwinner/sun4i-emac.c +++ b/drivers/net/ethernet/allwinner/sun4i-emac.c @@ -172,8 +172,7 @@ static int emac_mdio_probe(struct net_device *dev) } /* mask with MAC supported features */ - phydev->supported &= PHY_BASIC_FEATURES; - phydev->advertising = phydev->supported; + phy_set_max_speed(phydev, SPEED_100); db->link = 0; db->speed = 0; diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c index baca8f704a45..02921d877c08 100644 --- a/drivers/net/ethernet/altera/altera_tse_main.c +++ b/drivers/net/ethernet/altera/altera_tse_main.c @@ -835,13 +835,10 @@ static int init_phy(struct net_device *dev) } /* Stop Advertising 1000BASE Capability if interface is not GMII - * Note: Checkpatch throws CHECKs for the camel case defines below, - * it's ok to ignore. */ if ((priv->phy_iface == PHY_INTERFACE_MODE_MII) || (priv->phy_iface == PHY_INTERFACE_MODE_RMII)) - phydev->advertising &= ~(SUPPORTED_1000baseT_Half | - SUPPORTED_1000baseT_Full); + phy_set_max_speed(phydev, SPEED_100); /* Broken HW is sometimes missing the pull-up resistor on the * MDIO line, which results in reads to non-existent devices returning diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c index 17f12c18d225..7635c38e77dd 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_com.c @@ -459,12 +459,12 @@ static void ena_com_handle_admin_completion(struct ena_com_admin_queue *admin_qu cqe = &admin_queue->cq.entries[head_masked]; /* Go over all the completions */ - while ((cqe->acq_common_descriptor.flags & + while ((READ_ONCE(cqe->acq_common_descriptor.flags) & ENA_ADMIN_ACQ_COMMON_DESC_PHASE_MASK) == phase) { /* Do not read the rest of the completion entry before the * phase bit was validated */ - rmb(); + dma_rmb(); ena_com_handle_single_admin_completion(admin_queue, cqe); head_masked++; @@ -627,17 +627,10 @@ static u32 ena_com_reg_bar_read32(struct ena_com_dev *ena_dev, u16 offset) mmio_read_reg |= mmio_read->seq_num & ENA_REGS_MMIO_REG_READ_REQ_ID_MASK; - /* make sure read_resp->req_id get updated before the hw can write - * there - */ - wmb(); - - writel_relaxed(mmio_read_reg, - ena_dev->reg_bar + ENA_REGS_MMIO_REG_READ_OFF); + writel(mmio_read_reg, ena_dev->reg_bar + ENA_REGS_MMIO_REG_READ_OFF); - mmiowb(); for (i = 0; i < timeout; i++) { - if (read_resp->req_id == mmio_read->seq_num) + if (READ_ONCE(read_resp->req_id) == mmio_read->seq_num) break; udelay(1); @@ -1796,8 +1789,13 @@ void ena_com_aenq_intr_handler(struct ena_com_dev *dev, void *data) aenq_common = &aenq_e->aenq_common_desc; /* Go over all the events */ - while ((aenq_common->flags & ENA_ADMIN_AENQ_COMMON_DESC_PHASE_MASK) == - phase) { + while ((READ_ONCE(aenq_common->flags) & + ENA_ADMIN_AENQ_COMMON_DESC_PHASE_MASK) == phase) { + /* Make sure the phase bit (ownership) is as expected before + * reading the rest of the descriptor. + */ + dma_rmb(); + pr_debug("AENQ! Group[%x] Syndrom[%x] timestamp: [%llus]\n", aenq_common->group, aenq_common->syndrom, (u64)aenq_common->timestamp_low + diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_com.c b/drivers/net/ethernet/amazon/ena/ena_eth_com.c index ea149c134e15..1c682b76190f 100644 --- a/drivers/net/ethernet/amazon/ena/ena_eth_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_eth_com.c @@ -51,6 +51,11 @@ static inline struct ena_eth_io_rx_cdesc_base *ena_com_get_next_rx_cdesc( if (desc_phase != expected_phase) return NULL; + /* Make sure we read the rest of the descriptor after the phase bit + * has been read + */ + dma_rmb(); + return cdesc; } @@ -493,6 +498,7 @@ int ena_com_tx_comp_req_id_get(struct ena_com_io_cq *io_cq, u16 *req_id) if (cdesc_phase != expected_phase) return -EAGAIN; + dma_rmb(); if (unlikely(cdesc->req_id >= io_cq->q_depth)) { pr_err("Invalid req id %d\n", cdesc->req_id); return -EINVAL; diff --git a/drivers/net/ethernet/amazon/ena/ena_eth_com.h b/drivers/net/ethernet/amazon/ena/ena_eth_com.h index 6fdc753d9483..2f7657227cfe 100644 --- a/drivers/net/ethernet/amazon/ena/ena_eth_com.h +++ b/drivers/net/ethernet/amazon/ena/ena_eth_com.h @@ -107,8 +107,7 @@ static inline int ena_com_sq_empty_space(struct ena_com_io_sq *io_sq) return io_sq->q_depth - 1 - cnt; } -static inline int ena_com_write_sq_doorbell(struct ena_com_io_sq *io_sq, - bool relaxed) +static inline int ena_com_write_sq_doorbell(struct ena_com_io_sq *io_sq) { u16 tail; @@ -117,10 +116,7 @@ static inline int ena_com_write_sq_doorbell(struct ena_com_io_sq *io_sq, pr_debug("write submission queue doorbell for queue: %d tail: %d\n", io_sq->qid, tail); - if (relaxed) - writel_relaxed(tail, io_sq->db_addr); - else - writel(tail, io_sq->db_addr); + writel(tail, io_sq->db_addr); return 0; } diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index c673ac2df65b..b2522e84f482 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -39,7 +39,6 @@ #include <linux/if_vlan.h> #include <linux/kernel.h> #include <linux/module.h> -#include <linux/moduleparam.h> #include <linux/numa.h> #include <linux/pci.h> #include <linux/utsname.h> @@ -76,7 +75,7 @@ MODULE_DEVICE_TABLE(pci, ena_pci_tbl); static int ena_rss_init_default(struct ena_adapter *adapter); static void check_for_admin_com_state(struct ena_adapter *adapter); -static void ena_destroy_device(struct ena_adapter *adapter); +static void ena_destroy_device(struct ena_adapter *adapter, bool graceful); static int ena_restore_device(struct ena_adapter *adapter); static void ena_tx_timeout(struct net_device *dev) @@ -461,7 +460,7 @@ static inline int ena_alloc_rx_page(struct ena_ring *rx_ring, return -ENOMEM; } - dma = dma_map_page(rx_ring->dev, page, 0, PAGE_SIZE, + dma = dma_map_page(rx_ring->dev, page, 0, ENA_PAGE_SIZE, DMA_FROM_DEVICE); if (unlikely(dma_mapping_error(rx_ring->dev, dma))) { u64_stats_update_begin(&rx_ring->syncp); @@ -478,7 +477,7 @@ static inline int ena_alloc_rx_page(struct ena_ring *rx_ring, rx_info->page_offset = 0; ena_buf = &rx_info->ena_buf; ena_buf->paddr = dma; - ena_buf->len = PAGE_SIZE; + ena_buf->len = ENA_PAGE_SIZE; return 0; } @@ -495,7 +494,7 @@ static void ena_free_rx_page(struct ena_ring *rx_ring, return; } - dma_unmap_page(rx_ring->dev, ena_buf->paddr, PAGE_SIZE, + dma_unmap_page(rx_ring->dev, ena_buf->paddr, ENA_PAGE_SIZE, DMA_FROM_DEVICE); __free_page(page); @@ -551,14 +550,9 @@ static int ena_refill_rx_bufs(struct ena_ring *rx_ring, u32 num) rx_ring->qid, i, num); } - if (likely(i)) { - /* Add memory barrier to make sure the desc were written before - * issue a doorbell - */ - wmb(); - ena_com_write_sq_doorbell(rx_ring->ena_com_io_sq, true); - mmiowb(); - } + /* ena_com_write_sq_doorbell issues a wmb() */ + if (likely(i)) + ena_com_write_sq_doorbell(rx_ring->ena_com_io_sq); rx_ring->next_to_use = next_to_use; @@ -916,10 +910,10 @@ static struct sk_buff *ena_rx_skb(struct ena_ring *rx_ring, do { dma_unmap_page(rx_ring->dev, dma_unmap_addr(&rx_info->ena_buf, paddr), - PAGE_SIZE, DMA_FROM_DEVICE); + ENA_PAGE_SIZE, DMA_FROM_DEVICE); skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_info->page, - rx_info->page_offset, len, PAGE_SIZE); + rx_info->page_offset, len, ENA_PAGE_SIZE); netif_dbg(rx_ring->adapter, rx_status, rx_ring->netdev, "rx skb updated. len %d. data_len %d\n", @@ -1900,7 +1894,7 @@ static int ena_close(struct net_device *netdev) "Destroy failure, restarting device\n"); ena_dump_stats_to_dmesg(adapter); /* rtnl lock already obtained in dev_ioctl() layer */ - ena_destroy_device(adapter); + ena_destroy_device(adapter, false); ena_restore_device(adapter); } @@ -2112,12 +2106,6 @@ static netdev_tx_t ena_start_xmit(struct sk_buff *skb, struct net_device *dev) tx_ring->next_to_use = ENA_TX_RING_IDX_NEXT(next_to_use, tx_ring->ring_size); - /* This WMB is aimed to: - * 1 - perform smp barrier before reading next_to_completion - * 2 - make sure the desc were written before trigger DB - */ - wmb(); - /* stop the queue when no more space available, the packet can have up * to sgl_size + 2. one for the meta descriptor and one for header * (if the header is larger than tx_max_header_size). @@ -2136,10 +2124,11 @@ static netdev_tx_t ena_start_xmit(struct sk_buff *skb, struct net_device *dev) * stop the queue but meanwhile clean_tx_irq updates * next_to_completion and terminates. * The queue will remain stopped forever. - * To solve this issue this function perform rmb, check - * the wakeup condition and wake up the queue if needed. + * To solve this issue add a mb() to make sure that + * netif_tx_stop_queue() write is vissible before checking if + * there is additional space in the queue. */ - smp_rmb(); + smp_mb(); if (ena_com_sq_empty_space(tx_ring->ena_com_io_sq) > ENA_TX_WAKEUP_THRESH) { @@ -2151,8 +2140,10 @@ static netdev_tx_t ena_start_xmit(struct sk_buff *skb, struct net_device *dev) } if (netif_xmit_stopped(txq) || !skb->xmit_more) { - /* trigger the dma engine */ - ena_com_write_sq_doorbell(tx_ring->ena_com_io_sq, false); + /* trigger the dma engine. ena_com_write_sq_doorbell() + * has a mb + */ + ena_com_write_sq_doorbell(tx_ring->ena_com_io_sq); u64_stats_update_begin(&tx_ring->syncp); tx_ring->tx_stats.doorbells++; u64_stats_update_end(&tx_ring->syncp); @@ -2550,12 +2541,15 @@ err_disable_msix: return rc; } -static void ena_destroy_device(struct ena_adapter *adapter) +static void ena_destroy_device(struct ena_adapter *adapter, bool graceful) { struct net_device *netdev = adapter->netdev; struct ena_com_dev *ena_dev = adapter->ena_dev; bool dev_up; + if (!test_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags)) + return; + netif_carrier_off(netdev); del_timer_sync(&adapter->timer_service); @@ -2563,7 +2557,8 @@ static void ena_destroy_device(struct ena_adapter *adapter) dev_up = test_bit(ENA_FLAG_DEV_UP, &adapter->flags); adapter->dev_up_before_reset = dev_up; - ena_com_set_admin_running_state(ena_dev, false); + if (!graceful) + ena_com_set_admin_running_state(ena_dev, false); if (test_bit(ENA_FLAG_DEV_UP, &adapter->flags)) ena_down(adapter); @@ -2591,6 +2586,7 @@ static void ena_destroy_device(struct ena_adapter *adapter) adapter->reset_reason = ENA_REGS_RESET_NORMAL; clear_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags); + clear_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags); } static int ena_restore_device(struct ena_adapter *adapter) @@ -2635,6 +2631,7 @@ static int ena_restore_device(struct ena_adapter *adapter) } } + set_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags); mod_timer(&adapter->timer_service, round_jiffies(jiffies + HZ)); dev_err(&pdev->dev, "Device reset completed successfully\n"); @@ -2665,7 +2662,7 @@ static void ena_fw_reset_device(struct work_struct *work) return; } rtnl_lock(); - ena_destroy_device(adapter); + ena_destroy_device(adapter, false); ena_restore_device(adapter); rtnl_unlock(); } @@ -3409,30 +3406,24 @@ static void ena_remove(struct pci_dev *pdev) netdev->rx_cpu_rmap = NULL; } #endif /* CONFIG_RFS_ACCEL */ - - unregister_netdev(netdev); del_timer_sync(&adapter->timer_service); cancel_work_sync(&adapter->reset_task); - /* Reset the device only if the device is running. */ - if (test_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags)) - ena_com_dev_reset(ena_dev, adapter->reset_reason); + unregister_netdev(netdev); - ena_free_mgmnt_irq(adapter); + /* If the device is running then we want to make sure the device will be + * reset to make sure no more events will be issued by the device. + */ + if (test_bit(ENA_FLAG_DEVICE_RUNNING, &adapter->flags)) + set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags); - ena_disable_msix(adapter); + rtnl_lock(); + ena_destroy_device(adapter, true); + rtnl_unlock(); free_netdev(netdev); - ena_com_mmio_reg_read_request_destroy(ena_dev); - - ena_com_abort_admin_commands(ena_dev); - - ena_com_wait_for_abort_completion(ena_dev); - - ena_com_admin_destroy(ena_dev); - ena_com_rss_destroy(ena_dev); ena_com_delete_debug_area(ena_dev); @@ -3467,7 +3458,7 @@ static int ena_suspend(struct pci_dev *pdev, pm_message_t state) "ignoring device reset request as the device is being suspended\n"); clear_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags); } - ena_destroy_device(adapter); + ena_destroy_device(adapter, true); rtnl_unlock(); return 0; } diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h index f1972b5ab650..7c7ae56c52cf 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.h +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h @@ -355,4 +355,15 @@ void ena_dump_stats_to_buf(struct ena_adapter *adapter, u8 *buf); int ena_get_sset_count(struct net_device *netdev, int sset); +/* The ENA buffer length fields is 16 bit long. So when PAGE_SIZE == 64kB the + * driver passas 0. + * Since the max packet size the ENA handles is ~9kB limit the buffer length to + * 16kB. + */ +#if PAGE_SIZE > SZ_16K +#define ENA_PAGE_SIZE SZ_16K +#else +#define ENA_PAGE_SIZE PAGE_SIZE +#endif + #endif /* !(ENA_H) */ diff --git a/drivers/net/ethernet/amd/au1000_eth.c b/drivers/net/ethernet/amd/au1000_eth.c index 73ca8879ada7..7c1eb304c27e 100644 --- a/drivers/net/ethernet/amd/au1000_eth.c +++ b/drivers/net/ethernet/amd/au1000_eth.c @@ -564,17 +564,7 @@ static int au1000_mii_probe(struct net_device *dev) return PTR_ERR(phydev); } - /* mask with MAC supported features */ - phydev->supported &= (SUPPORTED_10baseT_Half - | SUPPORTED_10baseT_Full - | SUPPORTED_100baseT_Half - | SUPPORTED_100baseT_Full - | SUPPORTED_Autoneg - /* | SUPPORTED_Pause | SUPPORTED_Asym_Pause */ - | SUPPORTED_MII - | SUPPORTED_TP); - - phydev->advertising = phydev->supported; + phy_set_max_speed(phydev, SPEED_100); aup->old_link = 0; aup->old_speed = 0; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c index 3ceb4f95ca7c..289129011b9f 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c @@ -879,8 +879,8 @@ static bool xgbe_phy_finisar_phy_quirks(struct xgbe_prv_data *pdata) phy_write(phy_data->phydev, 0x00, 0x9140); phy_data->phydev->supported = PHY_GBIT_FEATURES; - phy_data->phydev->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; phy_data->phydev->advertising = phy_data->phydev->supported; + phy_support_asym_pause(phy_data->phydev); netif_dbg(pdata, drv, pdata->netdev, "Finisar PHY quirk in place\n"); @@ -951,8 +951,8 @@ static bool xgbe_phy_belfuse_phy_quirks(struct xgbe_prv_data *pdata) phy_write(phy_data->phydev, 0x00, reg & ~0x00800); phy_data->phydev->supported = PHY_GBIT_FEATURES; - phy_data->phydev->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; phy_data->phydev->advertising = phy_data->phydev->supported; + phy_support_asym_pause(phy_data->phydev); netif_dbg(pdata, drv, pdata->netdev, "BelFuse PHY quirk in place\n"); diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_ethtool.c b/drivers/net/ethernet/apm/xgene/xgene_enet_ethtool.c index 4f50f11718f4..78dd09b5beeb 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_ethtool.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_ethtool.c @@ -306,45 +306,25 @@ static int xgene_set_pauseparam(struct net_device *ndev, { struct xgene_enet_pdata *pdata = netdev_priv(ndev); struct phy_device *phydev = ndev->phydev; - u32 oldadv, newadv; if (phy_interface_mode_is_rgmii(pdata->phy_mode) || pdata->phy_mode == PHY_INTERFACE_MODE_SGMII) { if (!phydev) return -EINVAL; - if (!(phydev->supported & SUPPORTED_Pause) || - (!(phydev->supported & SUPPORTED_Asym_Pause) && - pp->rx_pause != pp->tx_pause)) + if (!phy_validate_pause(phydev, pp)) return -EINVAL; pdata->pause_autoneg = pp->autoneg; pdata->tx_pause = pp->tx_pause; pdata->rx_pause = pp->rx_pause; - oldadv = phydev->advertising; - newadv = oldadv & ~(ADVERTISED_Pause | ADVERTISED_Asym_Pause); + phy_set_asym_pause(phydev, pp->rx_pause, pp->tx_pause); - if (pp->rx_pause) - newadv |= ADVERTISED_Pause | ADVERTISED_Asym_Pause; - - if (pp->tx_pause) - newadv ^= ADVERTISED_Asym_Pause; - - if (oldadv ^ newadv) { - phydev->advertising = newadv; - - if (phydev->autoneg) - return phy_start_aneg(phydev); - - if (!pp->autoneg) { - pdata->mac_ops->flowctl_tx(pdata, - pdata->tx_pause); - pdata->mac_ops->flowctl_rx(pdata, - pdata->rx_pause); - } + if (!pp->autoneg) { + pdata->mac_ops->flowctl_tx(pdata, pdata->tx_pause); + pdata->mac_ops->flowctl_rx(pdata, pdata->rx_pause); } - } else { if (pp->autoneg) return -EINVAL; diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c index 078a04dc1182..e3560311711a 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c @@ -895,12 +895,10 @@ int xgene_enet_phy_connect(struct net_device *ndev) } pdata->phy_speed = SPEED_UNKNOWN; - phy_dev->supported &= ~SUPPORTED_10baseT_Half & - ~SUPPORTED_100baseT_Half & - ~SUPPORTED_1000baseT_Half; - phy_dev->supported |= SUPPORTED_Pause | - SUPPORTED_Asym_Pause; - phy_dev->advertising = phy_dev->supported; + phy_remove_link_mode(phy_dev, ETHTOOL_LINK_MODE_10baseT_Half_BIT); + phy_remove_link_mode(phy_dev, ETHTOOL_LINK_MODE_100baseT_Half_BIT); + phy_remove_link_mode(phy_dev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT); + phy_support_asym_pause(phy_dev); return 0; } diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_common.h b/drivers/net/ethernet/aquantia/atlantic/aq_common.h index d52b088ff8f0..becb578211ed 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_common.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_common.h @@ -57,4 +57,9 @@ #define AQ_NIC_RATE_1G BIT(4) #define AQ_NIC_RATE_100M BIT(5) +#define AQ_NIC_RATE_EEE_10G BIT(6) +#define AQ_NIC_RATE_EEE_5G BIT(7) +#define AQ_NIC_RATE_EEE_2GS BIT(8) +#define AQ_NIC_RATE_EEE_1G BIT(9) + #endif /* AQ_COMMON_H */ diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c index 08c9fa6ca71f..6a633c70f603 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c @@ -98,8 +98,8 @@ static void aq_ethtool_stats(struct net_device *ndev, struct aq_nic_cfg_s *cfg = aq_nic_get_cfg(aq_nic); memset(data, 0, (ARRAY_SIZE(aq_ethtool_stat_names) + - ARRAY_SIZE(aq_ethtool_queue_stat_names) * - cfg->vecs) * sizeof(u64)); + ARRAY_SIZE(aq_ethtool_queue_stat_names) * + cfg->vecs) * sizeof(u64)); aq_nic_get_stats(aq_nic, data); } @@ -285,6 +285,111 @@ static int aq_ethtool_set_coalesce(struct net_device *ndev, return aq_nic_update_interrupt_moderation_settings(aq_nic); } +static void aq_ethtool_get_wol(struct net_device *ndev, + struct ethtool_wolinfo *wol) +{ + struct aq_nic_s *aq_nic = netdev_priv(ndev); + struct aq_nic_cfg_s *cfg = aq_nic_get_cfg(aq_nic); + + wol->supported = WAKE_MAGIC; + wol->wolopts = 0; + + if (cfg->wol) + wol->wolopts |= WAKE_MAGIC; +} + +static int aq_ethtool_set_wol(struct net_device *ndev, + struct ethtool_wolinfo *wol) +{ + struct pci_dev *pdev = to_pci_dev(ndev->dev.parent); + struct aq_nic_s *aq_nic = netdev_priv(ndev); + struct aq_nic_cfg_s *cfg = aq_nic_get_cfg(aq_nic); + int err = 0; + + if (wol->wolopts & WAKE_MAGIC) + cfg->wol |= AQ_NIC_WOL_ENABLED; + else + cfg->wol &= ~AQ_NIC_WOL_ENABLED; + err = device_set_wakeup_enable(&pdev->dev, wol->wolopts); + + return err; +} + +static enum hw_atl_fw2x_rate eee_mask_to_ethtool_mask(u32 speed) +{ + u32 rate = 0; + + if (speed & AQ_NIC_RATE_EEE_10G) + rate |= SUPPORTED_10000baseT_Full; + + if (speed & AQ_NIC_RATE_EEE_2GS) + rate |= SUPPORTED_2500baseX_Full; + + if (speed & AQ_NIC_RATE_EEE_1G) + rate |= SUPPORTED_1000baseT_Full; + + return rate; +} + +static int aq_ethtool_get_eee(struct net_device *ndev, struct ethtool_eee *eee) +{ + struct aq_nic_s *aq_nic = netdev_priv(ndev); + u32 rate, supported_rates; + int err = 0; + + if (!aq_nic->aq_fw_ops->get_eee_rate) + return -EOPNOTSUPP; + + err = aq_nic->aq_fw_ops->get_eee_rate(aq_nic->aq_hw, &rate, + &supported_rates); + if (err < 0) + return err; + + eee->supported = eee_mask_to_ethtool_mask(supported_rates); + + if (aq_nic->aq_nic_cfg.eee_speeds) + eee->advertised = eee->supported; + + eee->lp_advertised = eee_mask_to_ethtool_mask(rate); + + eee->eee_enabled = !!eee->advertised; + + eee->tx_lpi_enabled = eee->eee_enabled; + if (eee->advertised & eee->lp_advertised) + eee->eee_active = true; + + return 0; +} + +static int aq_ethtool_set_eee(struct net_device *ndev, struct ethtool_eee *eee) +{ + struct aq_nic_s *aq_nic = netdev_priv(ndev); + u32 rate, supported_rates; + struct aq_nic_cfg_s *cfg; + int err = 0; + + cfg = aq_nic_get_cfg(aq_nic); + + if (unlikely(!aq_nic->aq_fw_ops->get_eee_rate || + !aq_nic->aq_fw_ops->set_eee_rate)) + return -EOPNOTSUPP; + + err = aq_nic->aq_fw_ops->get_eee_rate(aq_nic->aq_hw, &rate, + &supported_rates); + if (err < 0) + return err; + + if (eee->eee_enabled) { + rate = supported_rates; + cfg->eee_speeds = rate; + } else { + rate = 0; + cfg->eee_speeds = 0; + } + + return aq_nic->aq_fw_ops->set_eee_rate(aq_nic->aq_hw, rate); +} + static int aq_ethtool_nway_reset(struct net_device *ndev) { struct aq_nic_s *aq_nic = netdev_priv(ndev); @@ -403,9 +508,13 @@ const struct ethtool_ops aq_ethtool_ops = { .get_drvinfo = aq_ethtool_get_drvinfo, .get_strings = aq_ethtool_get_strings, .get_rxfh_indir_size = aq_ethtool_get_rss_indir_size, + .get_wol = aq_ethtool_get_wol, + .set_wol = aq_ethtool_set_wol, .nway_reset = aq_ethtool_nway_reset, .get_ringparam = aq_get_ringparam, .set_ringparam = aq_set_ringparam, + .get_eee = aq_ethtool_get_eee, + .set_eee = aq_ethtool_set_eee, .get_pauseparam = aq_ethtool_get_pauseparam, .set_pauseparam = aq_ethtool_set_pauseparam, .get_rxfh_key_size = aq_ethtool_get_rss_key_size, diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h index 5c00671f248d..e8689241204e 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h @@ -112,7 +112,7 @@ struct aq_hw_s { const struct aq_fw_ops *aq_fw_ops; void __iomem *mmio; struct aq_hw_link_status_s aq_link_status; - struct hw_aq_atl_utils_mbox mbox; + struct hw_atl_utils_mbox mbox; struct hw_atl_stats_s last_stats; struct aq_stats_s curr_stats; u64 speed; @@ -124,7 +124,7 @@ struct aq_hw_s { u32 mbox_addr; u32 rpc_addr; u32 rpc_tid; - struct hw_aq_atl_utils_fw_rpc rpc; + struct hw_atl_utils_fw_rpc rpc; }; struct aq_ring_s; @@ -204,7 +204,6 @@ struct aq_hw_ops { int (*hw_get_fw_version)(struct aq_hw_s *self, u32 *fw_version); - int (*hw_set_power)(struct aq_hw_s *self, unsigned int power_state); }; struct aq_fw_ops { @@ -228,6 +227,14 @@ struct aq_fw_ops { int (*update_stats)(struct aq_hw_s *self); int (*set_flow_control)(struct aq_hw_s *self); + + int (*set_power)(struct aq_hw_s *self, unsigned int power_state, + u8 *mac); + + int (*set_eee_rate)(struct aq_hw_s *self, u32 speed); + + int (*get_eee_rate)(struct aq_hw_s *self, u32 *rate, + u32 *supported_rates); }; #endif /* AQ_HW_H */ diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index 26dc6782b475..5fed24446687 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -189,7 +189,7 @@ static void aq_nic_polling_timer_cb(struct timer_list *t) aq_vec_isr(i, (void *)aq_vec); mod_timer(&self->polling_timer, jiffies + - AQ_CFG_POLLING_TIMER_INTERVAL); + AQ_CFG_POLLING_TIMER_INTERVAL); } int aq_nic_ndev_register(struct aq_nic_s *self) @@ -301,13 +301,13 @@ int aq_nic_start(struct aq_nic_s *self) unsigned int i = 0U; err = self->aq_hw_ops->hw_multicast_list_set(self->aq_hw, - self->mc_list.ar, - self->mc_list.count); + self->mc_list.ar, + self->mc_list.count); if (err < 0) goto err_exit; err = self->aq_hw_ops->hw_packet_filter_set(self->aq_hw, - self->packet_filter); + self->packet_filter); if (err < 0) goto err_exit; @@ -327,7 +327,7 @@ int aq_nic_start(struct aq_nic_s *self) goto err_exit; timer_setup(&self->service_timer, aq_nic_service_timer_cb, 0); mod_timer(&self->service_timer, jiffies + - AQ_CFG_SERVICE_TIMER_INTERVAL); + AQ_CFG_SERVICE_TIMER_INTERVAL); if (self->aq_nic_cfg.is_polling) { timer_setup(&self->polling_timer, aq_nic_polling_timer_cb, 0); @@ -344,7 +344,7 @@ int aq_nic_start(struct aq_nic_s *self) } err = self->aq_hw_ops->hw_irq_enable(self->aq_hw, - AQ_CFG_IRQ_MASK); + AQ_CFG_IRQ_MASK); if (err < 0) goto err_exit; } @@ -889,11 +889,13 @@ void aq_nic_deinit(struct aq_nic_s *self) self->aq_vecs > i; ++i, aq_vec = self->aq_vec[i]) aq_vec_deinit(aq_vec); - if (self->power_state == AQ_HW_POWER_STATE_D0) { - (void)self->aq_fw_ops->deinit(self->aq_hw); - } else { - (void)self->aq_hw_ops->hw_set_power(self->aq_hw, - self->power_state); + self->aq_fw_ops->deinit(self->aq_hw); + + if (self->power_state != AQ_HW_POWER_STATE_D0 || + self->aq_hw->aq_nic_cfg->wol) { + self->aq_fw_ops->set_power(self->aq_hw, + self->power_state, + self->ndev->dev_addr); } err_exit:; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h index fecfc401f95d..c1582f4e8e1b 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.h @@ -36,6 +36,7 @@ struct aq_nic_cfg_s { u32 flow_control; u32 link_speed_msk; u32 vlan_id; + u32 wol; u16 is_mc_list_enabled; u16 mc_list_count; bool is_autoneg; @@ -44,6 +45,7 @@ struct aq_nic_cfg_s { bool is_lro; u8 tcs; struct aq_rss_parameters aq_rss; + u32 eee_speeds; }; #define AQ_NIC_FLAG_STARTED 0x00000004U @@ -54,6 +56,8 @@ struct aq_nic_cfg_s { #define AQ_NIC_FLAG_ERR_UNPLUG 0x40000000U #define AQ_NIC_FLAG_ERR_HW 0x80000000U +#define AQ_NIC_WOL_ENABLED BIT(0) + #define AQ_NIC_TCVEC2RING(_NIC_, _TC_, _VEC_) \ ((_TC_) * AQ_CFG_TCS_MAX + (_VEC_)) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index b5f1f62e8e25..3db91446cc67 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -29,8 +29,8 @@ static struct aq_ring_s *aq_ring_alloc(struct aq_ring_s *self, goto err_exit; } self->dx_ring = dma_alloc_coherent(aq_nic_get_dev(aq_nic), - self->size * self->dx_size, - &self->dx_ring_pa, GFP_KERNEL); + self->size * self->dx_size, + &self->dx_ring_pa, GFP_KERNEL); if (!self->dx_ring) { err = -ENOMEM; goto err_exit; @@ -225,9 +225,10 @@ int aq_ring_rx_clean(struct aq_ring_s *self, } /* for single fragment packets use build_skb() */ - if (buff->is_eop) { + if (buff->is_eop && + buff->len <= AQ_CFG_RX_FRAME_MAX - AQ_SKB_ALIGN) { skb = build_skb(page_address(buff->page), - buff->len + AQ_SKB_ALIGN); + AQ_CFG_RX_FRAME_MAX); if (unlikely(!skb)) { err = -ENOMEM; goto err_exit; @@ -247,18 +248,21 @@ int aq_ring_rx_clean(struct aq_ring_s *self, buff->len - ETH_HLEN, SKB_TRUESIZE(buff->len - ETH_HLEN)); - for (i = 1U, next_ = buff->next, - buff_ = &self->buff_ring[next_]; true; - next_ = buff_->next, - buff_ = &self->buff_ring[next_], ++i) { - skb_add_rx_frag(skb, i, buff_->page, 0, - buff_->len, - SKB_TRUESIZE(buff->len - - ETH_HLEN)); - buff_->is_cleaned = 1; - - if (buff_->is_eop) - break; + if (!buff->is_eop) { + for (i = 1U, next_ = buff->next, + buff_ = &self->buff_ring[next_]; + true; next_ = buff_->next, + buff_ = &self->buff_ring[next_], ++i) { + skb_add_rx_frag(skb, i, + buff_->page, 0, + buff_->len, + SKB_TRUESIZE(buff->len - + ETH_HLEN)); + buff_->is_cleaned = 1; + + if (buff_->is_eop) + break; + } } } diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c index 97addfa6f895..2469ed4d86b9 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c @@ -49,37 +49,37 @@ const struct aq_hw_caps_s hw_atl_a0_caps_aqc100 = { DEFAULT_A0_BOARD_BASIC_CAPABILITIES, .media_type = AQ_HW_MEDIA_TYPE_FIBRE, - .link_speed_msk = HW_ATL_A0_RATE_5G | - HW_ATL_A0_RATE_2G5 | - HW_ATL_A0_RATE_1G | - HW_ATL_A0_RATE_100M, + .link_speed_msk = AQ_NIC_RATE_5G | + AQ_NIC_RATE_2GS | + AQ_NIC_RATE_1G | + AQ_NIC_RATE_100M, }; const struct aq_hw_caps_s hw_atl_a0_caps_aqc107 = { DEFAULT_A0_BOARD_BASIC_CAPABILITIES, .media_type = AQ_HW_MEDIA_TYPE_TP, - .link_speed_msk = HW_ATL_A0_RATE_10G | - HW_ATL_A0_RATE_5G | - HW_ATL_A0_RATE_2G5 | - HW_ATL_A0_RATE_1G | - HW_ATL_A0_RATE_100M, + .link_speed_msk = AQ_NIC_RATE_10G | + AQ_NIC_RATE_5G | + AQ_NIC_RATE_2GS | + AQ_NIC_RATE_1G | + AQ_NIC_RATE_100M, }; const struct aq_hw_caps_s hw_atl_a0_caps_aqc108 = { DEFAULT_A0_BOARD_BASIC_CAPABILITIES, .media_type = AQ_HW_MEDIA_TYPE_TP, - .link_speed_msk = HW_ATL_A0_RATE_5G | - HW_ATL_A0_RATE_2G5 | - HW_ATL_A0_RATE_1G | - HW_ATL_A0_RATE_100M, + .link_speed_msk = AQ_NIC_RATE_5G | + AQ_NIC_RATE_2GS | + AQ_NIC_RATE_1G | + AQ_NIC_RATE_100M, }; const struct aq_hw_caps_s hw_atl_a0_caps_aqc109 = { DEFAULT_A0_BOARD_BASIC_CAPABILITIES, .media_type = AQ_HW_MEDIA_TYPE_TP, - .link_speed_msk = HW_ATL_A0_RATE_2G5 | - HW_ATL_A0_RATE_1G | - HW_ATL_A0_RATE_100M, + .link_speed_msk = AQ_NIC_RATE_2GS | + AQ_NIC_RATE_1G | + AQ_NIC_RATE_100M, }; static int hw_atl_a0_hw_reset(struct aq_hw_s *self) @@ -284,7 +284,7 @@ static int hw_atl_a0_hw_init_rx_path(struct aq_hw_s *self) /* RSS Ring selection */ hw_atl_reg_rx_flr_rss_control1set(self, cfg->is_rss ? - 0xB3333333U : 0x00000000U); + 0xB3333333U : 0x00000000U); /* Multicast filters */ for (i = HW_ATL_A0_MAC_MAX; i--;) { @@ -325,7 +325,7 @@ static int hw_atl_a0_hw_mac_addr_set(struct aq_hw_s *self, u8 *mac_addr) } h = (mac_addr[0] << 8) | (mac_addr[1]); l = (mac_addr[2] << 24) | (mac_addr[3] << 16) | - (mac_addr[4] << 8) | mac_addr[5]; + (mac_addr[4] << 8) | mac_addr[5]; hw_atl_rpfl2_uc_flr_en_set(self, 0U, HW_ATL_A0_MAC); hw_atl_rpfl2unicast_dest_addresslsw_set(self, l, HW_ATL_A0_MAC); @@ -519,7 +519,7 @@ static int hw_atl_a0_hw_ring_rx_init(struct aq_hw_s *self, hw_atl_rdm_rx_desc_data_buff_size_set(self, AQ_CFG_RX_FRAME_MAX / 1024U, - aq_ring->idx); + aq_ring->idx); hw_atl_rdm_rx_desc_head_buff_size_set(self, 0U, aq_ring->idx); hw_atl_rdm_rx_desc_head_splitting_set(self, 0U, aq_ring->idx); @@ -758,7 +758,7 @@ static int hw_atl_a0_hw_packet_filter_set(struct aq_hw_s *self, hw_atl_rpfl2_uc_flr_en_set(self, (self->aq_nic_cfg->is_mc_list_enabled && (i <= self->aq_nic_cfg->mc_list_count)) ? - 1U : 0U, i); + 1U : 0U, i); return aq_hw_err_from_flags(self); } @@ -877,7 +877,6 @@ static int hw_atl_a0_hw_ring_rx_stop(struct aq_hw_s *self, const struct aq_hw_ops hw_atl_ops_a0 = { .hw_set_mac_address = hw_atl_a0_hw_mac_addr_set, .hw_init = hw_atl_a0_hw_init, - .hw_set_power = hw_atl_utils_hw_set_power, .hw_reset = hw_atl_a0_hw_reset, .hw_start = hw_atl_a0_hw_start, .hw_ring_tx_start = hw_atl_a0_hw_ring_tx_start, diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0_internal.h index 3c94cff57876..a021dc431ef7 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0_internal.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0_internal.h @@ -62,12 +62,6 @@ #define HW_ATL_A0_MPI_SPEED_MSK 0xFFFFU #define HW_ATL_A0_MPI_SPEED_SHIFT 16U -#define HW_ATL_A0_RATE_10G BIT(0) -#define HW_ATL_A0_RATE_5G BIT(1) -#define HW_ATL_A0_RATE_2G5 BIT(3) -#define HW_ATL_A0_RATE_1G BIT(4) -#define HW_ATL_A0_RATE_100M BIT(5) - #define HW_ATL_A0_TXBUF_MAX 160U #define HW_ATL_A0_RXBUF_MAX 320U diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c index 1d44a386e7d3..76d25d594a0f 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c @@ -51,38 +51,38 @@ const struct aq_hw_caps_s hw_atl_b0_caps_aqc100 = { DEFAULT_B0_BOARD_BASIC_CAPABILITIES, .media_type = AQ_HW_MEDIA_TYPE_FIBRE, - .link_speed_msk = HW_ATL_B0_RATE_10G | - HW_ATL_B0_RATE_5G | - HW_ATL_B0_RATE_2G5 | - HW_ATL_B0_RATE_1G | - HW_ATL_B0_RATE_100M, + .link_speed_msk = AQ_NIC_RATE_10G | + AQ_NIC_RATE_5G | + AQ_NIC_RATE_2GS | + AQ_NIC_RATE_1G | + AQ_NIC_RATE_100M, }; const struct aq_hw_caps_s hw_atl_b0_caps_aqc107 = { DEFAULT_B0_BOARD_BASIC_CAPABILITIES, .media_type = AQ_HW_MEDIA_TYPE_TP, - .link_speed_msk = HW_ATL_B0_RATE_10G | - HW_ATL_B0_RATE_5G | - HW_ATL_B0_RATE_2G5 | - HW_ATL_B0_RATE_1G | - HW_ATL_B0_RATE_100M, + .link_speed_msk = AQ_NIC_RATE_10G | + AQ_NIC_RATE_5G | + AQ_NIC_RATE_2GS | + AQ_NIC_RATE_1G | + AQ_NIC_RATE_100M, }; const struct aq_hw_caps_s hw_atl_b0_caps_aqc108 = { DEFAULT_B0_BOARD_BASIC_CAPABILITIES, .media_type = AQ_HW_MEDIA_TYPE_TP, - .link_speed_msk = HW_ATL_B0_RATE_5G | - HW_ATL_B0_RATE_2G5 | - HW_ATL_B0_RATE_1G | - HW_ATL_B0_RATE_100M, + .link_speed_msk = AQ_NIC_RATE_5G | + AQ_NIC_RATE_2GS | + AQ_NIC_RATE_1G | + AQ_NIC_RATE_100M, }; const struct aq_hw_caps_s hw_atl_b0_caps_aqc109 = { DEFAULT_B0_BOARD_BASIC_CAPABILITIES, .media_type = AQ_HW_MEDIA_TYPE_TP, - .link_speed_msk = HW_ATL_B0_RATE_2G5 | - HW_ATL_B0_RATE_1G | - HW_ATL_B0_RATE_100M, + .link_speed_msk = AQ_NIC_RATE_2GS | + AQ_NIC_RATE_1G | + AQ_NIC_RATE_100M, }; static int hw_atl_b0_hw_reset(struct aq_hw_s *self) @@ -935,7 +935,6 @@ static int hw_atl_b0_hw_ring_rx_stop(struct aq_hw_s *self, const struct aq_hw_ops hw_atl_ops_b0 = { .hw_set_mac_address = hw_atl_b0_hw_mac_addr_set, .hw_init = hw_atl_b0_hw_init, - .hw_set_power = hw_atl_utils_hw_set_power, .hw_reset = hw_atl_b0_hw_reset, .hw_start = hw_atl_b0_hw_start, .hw_ring_tx_start = hw_atl_b0_hw_ring_tx_start, diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h index 28568f5fa74b..b318eefd36ae 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h @@ -67,12 +67,6 @@ #define HW_ATL_B0_MPI_SPEED_MSK 0xFFFFU #define HW_ATL_B0_MPI_SPEED_SHIFT 16U -#define HW_ATL_B0_RATE_10G BIT(0) -#define HW_ATL_B0_RATE_5G BIT(1) -#define HW_ATL_B0_RATE_2G5 BIT(3) -#define HW_ATL_B0_RATE_1G BIT(4) -#define HW_ATL_B0_RATE_100M BIT(5) - #define HW_ATL_B0_TXBUF_MAX 160U #define HW_ATL_B0_RXBUF_MAX 320U diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c index 10ba035dadb1..be0a3a90dfad 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.c @@ -1460,3 +1460,11 @@ void hw_atl_reg_glb_cpu_scratch_scp_set(struct aq_hw_s *aq_hw, aq_hw_write_reg(aq_hw, HW_ATL_GLB_CPU_SCRATCH_SCP_ADR(scratch_scp), glb_cpu_scratch_scp); } + +void hw_atl_mcp_up_force_intr_set(struct aq_hw_s *aq_hw, u32 up_force_intr) +{ + aq_hw_write_reg_bit(aq_hw, HW_ATL_MCP_UP_FORCE_INTERRUPT_ADR, + HW_ATL_MCP_UP_FORCE_INTERRUPT_MSK, + HW_ATL_MCP_UP_FORCE_INTERRUPT_SHIFT, + up_force_intr); +} diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h index dfb426f2dc2c..7056c7342afc 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh.h @@ -698,4 +698,7 @@ void hw_atl_msm_reg_wr_strobe_set(struct aq_hw_s *aq_hw, u32 reg_wr_strobe); /* set pci register reset disable */ void hw_atl_pci_pci_reg_res_dis_set(struct aq_hw_s *aq_hw, u32 pci_reg_res_dis); +/* set uP Force Interrupt */ +void hw_atl_mcp_up_force_intr_set(struct aq_hw_s *aq_hw, u32 up_force_intr); + #endif /* HW_ATL_LLH_H */ diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h index e0cf70120f1d..716674a9b729 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_llh_internal.h @@ -2387,4 +2387,17 @@ #define HW_ATL_GLB_CPU_SCRATCH_SCP_ADR(scratch_scp) \ (0x00000300u + (scratch_scp) * 0x4) +/* register address for bitfield uP Force Interrupt */ +#define HW_ATL_MCP_UP_FORCE_INTERRUPT_ADR 0x00000404 +/* bitmask for bitfield uP Force Interrupt */ +#define HW_ATL_MCP_UP_FORCE_INTERRUPT_MSK 0x00000002 +/* inverted bitmask for bitfield uP Force Interrupt */ +#define HW_ATL_MCP_UP_FORCE_INTERRUPT_MSKN 0xFFFFFFFD +/* lower bit position of bitfield uP Force Interrupt */ +#define HW_ATL_MCP_UP_FORCE_INTERRUPT_SHIFT 1 +/* width of bitfield uP Force Interrupt */ +#define HW_ATL_MCP_UP_FORCE_INTERRUPT_WIDTH 1 +/* default value of bitfield uP Force Interrupt */ +#define HW_ATL_MCP_UP_FORCE_INTERRUPT_DEFAULT 0x0 + #endif /* HW_ATL_LLH_INTERNAL_H */ diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c index c965e65d07db..0dd59b09060b 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c @@ -49,6 +49,7 @@ #define FORCE_FLASHLESS 0 static int hw_atl_utils_ver_match(u32 ver_expected, u32 ver_actual); + static int hw_atl_utils_mpi_set_state(struct aq_hw_s *self, enum hal_atl_utils_fw_state_e state); @@ -69,10 +70,10 @@ int hw_atl_utils_initfw(struct aq_hw_s *self, const struct aq_fw_ops **fw_ops) self->fw_ver_actual) == 0) { *fw_ops = &aq_fw_1x_ops; } else if (hw_atl_utils_ver_match(HW_ATL_FW_VER_2X, - self->fw_ver_actual) == 0) { + self->fw_ver_actual) == 0) { *fw_ops = &aq_fw_2x_ops; } else if (hw_atl_utils_ver_match(HW_ATL_FW_VER_3X, - self->fw_ver_actual) == 0) { + self->fw_ver_actual) == 0) { *fw_ops = &aq_fw_2x_ops; } else { aq_pr_err("Bad FW version detected: %x\n", @@ -260,7 +261,7 @@ int hw_atl_utils_soft_reset(struct aq_hw_s *self) hw_atl_utils_mpi_set_state(self, MPI_DEINIT); AQ_HW_WAIT_FOR((aq_hw_read_reg(self, HW_ATL_MPI_STATE_ADR) & - HW_ATL_MPI_STATE_MSK) == MPI_DEINIT, + HW_ATL_MPI_STATE_MSK) == MPI_DEINIT, 10, 1000U); } @@ -277,7 +278,7 @@ int hw_atl_utils_fw_downld_dwords(struct aq_hw_s *self, u32 a, AQ_HW_WAIT_FOR(hw_atl_reg_glb_cpu_sem_get(self, HW_ATL_FW_SM_RAM) == 1U, - 1U, 10000U); + 1U, 10000U); if (err < 0) { bool is_locked; @@ -325,17 +326,31 @@ static int hw_atl_utils_fw_upload_dwords(struct aq_hw_s *self, u32 a, u32 *p, err = -ETIME; goto err_exit; } + if (IS_CHIP_FEATURE(REVISION_B1)) { + u32 offset = 0; + + for (; offset < cnt; ++offset) { + aq_hw_write_reg(self, 0x328, p[offset]); + aq_hw_write_reg(self, 0x32C, + (0x80000000 | (0xFFFF & (offset * 4)))); + hw_atl_mcp_up_force_intr_set(self, 1); + /* 1000 times by 10us = 10ms */ + AQ_HW_WAIT_FOR((aq_hw_read_reg(self, + 0x32C) & 0xF0000000) != + 0x80000000, + 10, 1000); + } + } else { + u32 offset = 0; - aq_hw_write_reg(self, 0x00000208U, a); - - for (++cnt; --cnt;) { - u32 i = 0U; + aq_hw_write_reg(self, 0x208, a); - aq_hw_write_reg(self, 0x0000020CU, *(p++)); - aq_hw_write_reg(self, 0x00000200U, 0xC000U); + for (; offset < cnt; ++offset) { + aq_hw_write_reg(self, 0x20C, p[offset]); + aq_hw_write_reg(self, 0x200, 0xC000); - for (i = 1024U; - (0x100U & aq_hw_read_reg(self, 0x00000200U)) && --i;) { + AQ_HW_WAIT_FOR((aq_hw_read_reg(self, 0x200U) & + 0x100) == 0, 10, 1000); } } @@ -379,7 +394,7 @@ static int hw_atl_utils_init_ucp(struct aq_hw_s *self, /* check 10 times by 1ms */ AQ_HW_WAIT_FOR(0U != (self->mbox_addr = - aq_hw_read_reg(self, 0x360U)), 1000U, 10U); + aq_hw_read_reg(self, 0x360U)), 1000U, 10U); return err; } @@ -399,7 +414,7 @@ struct aq_hw_atl_utils_fw_rpc_tid_s { #define hw_atl_utils_fw_rpc_init(_H_) hw_atl_utils_fw_rpc_wait(_H_, NULL) -static int hw_atl_utils_fw_rpc_call(struct aq_hw_s *self, unsigned int rpc_size) +int hw_atl_utils_fw_rpc_call(struct aq_hw_s *self, unsigned int rpc_size) { int err = 0; struct aq_hw_atl_utils_fw_rpc_tid_s sw; @@ -411,7 +426,7 @@ static int hw_atl_utils_fw_rpc_call(struct aq_hw_s *self, unsigned int rpc_size) err = hw_atl_utils_fw_upload_dwords(self, self->rpc_addr, (u32 *)(void *)&self->rpc, (rpc_size + sizeof(u32) - - sizeof(u8)) / sizeof(u32)); + sizeof(u8)) / sizeof(u32)); if (err < 0) goto err_exit; @@ -423,8 +438,8 @@ err_exit: return err; } -static int hw_atl_utils_fw_rpc_wait(struct aq_hw_s *self, - struct hw_aq_atl_utils_fw_rpc **rpc) +int hw_atl_utils_fw_rpc_wait(struct aq_hw_s *self, + struct hw_atl_utils_fw_rpc **rpc) { int err = 0; struct aq_hw_atl_utils_fw_rpc_tid_s sw; @@ -436,7 +451,7 @@ static int hw_atl_utils_fw_rpc_wait(struct aq_hw_s *self, self->rpc_tid = sw.tid; AQ_HW_WAIT_FOR(sw.tid == - (fw.val = + (fw.val = aq_hw_read_reg(self, HW_ATL_RPC_STATE_ADR), fw.tid), 1000U, 100U); if (err < 0) @@ -459,7 +474,7 @@ static int hw_atl_utils_fw_rpc_wait(struct aq_hw_s *self, (u32 *)(void *) &self->rpc, (fw.len + sizeof(u32) - - sizeof(u8)) / + sizeof(u8)) / sizeof(u32)); if (err < 0) goto err_exit; @@ -489,16 +504,16 @@ err_exit: } int hw_atl_utils_mpi_read_mbox(struct aq_hw_s *self, - struct hw_aq_atl_utils_mbox_header *pmbox) + struct hw_atl_utils_mbox_header *pmbox) { return hw_atl_utils_fw_downld_dwords(self, - self->mbox_addr, - (u32 *)(void *)pmbox, - sizeof(*pmbox) / sizeof(u32)); + self->mbox_addr, + (u32 *)(void *)pmbox, + sizeof(*pmbox) / sizeof(u32)); } void hw_atl_utils_mpi_read_stats(struct aq_hw_s *self, - struct hw_aq_atl_utils_mbox *pmbox) + struct hw_atl_utils_mbox *pmbox) { int err = 0; @@ -538,7 +553,7 @@ static int hw_atl_utils_mpi_set_state(struct aq_hw_s *self, { int err = 0; u32 transaction_id = 0; - struct hw_aq_atl_utils_mbox_header mbox; + struct hw_atl_utils_mbox_header mbox; u32 val = aq_hw_read_reg(self, HW_ATL_MPI_CONTROL_ADR); if (state == MPI_RESET) { @@ -547,8 +562,8 @@ static int hw_atl_utils_mpi_set_state(struct aq_hw_s *self, transaction_id = mbox.transaction_id; AQ_HW_WAIT_FOR(transaction_id != - (hw_atl_utils_mpi_read_mbox(self, &mbox), - mbox.transaction_id), + (hw_atl_utils_mpi_read_mbox(self, &mbox), + mbox.transaction_id), 1000U, 100U); if (err < 0) goto err_exit; @@ -645,9 +660,9 @@ int hw_atl_utils_get_mac_permanent(struct aq_hw_s *self, if ((mac[0] & 0x01U) || ((mac[0] | mac[1] | mac[2]) == 0x00U)) { /* chip revision */ - l = 0xE3000000U - | (0xFFFFU & aq_hw_read_reg(self, HW_ATL_UCP_0X370_REG)) - | (0x00 << 16); + l = 0xE3000000U | + (0xFFFFU & aq_hw_read_reg(self, HW_ATL_UCP_0X370_REG)) | + (0x00 << 16); h = 0x8001300EU; mac[5] = (u8)(0xFFU & l); @@ -730,17 +745,9 @@ static int hw_atl_fw1x_deinit(struct aq_hw_s *self) return 0; } -int hw_atl_utils_hw_set_power(struct aq_hw_s *self, - unsigned int power_state) -{ - hw_atl_utils_mpi_set_speed(self, 0); - hw_atl_utils_mpi_set_state(self, MPI_POWER); - return 0; -} - int hw_atl_utils_update_stats(struct aq_hw_s *self) { - struct hw_aq_atl_utils_mbox mbox; + struct hw_atl_utils_mbox mbox; hw_atl_utils_mpi_read_stats(self, &mbox); @@ -825,6 +832,81 @@ int hw_atl_utils_get_fw_version(struct aq_hw_s *self, u32 *fw_version) return 0; } +static int aq_fw1x_set_wol(struct aq_hw_s *self, bool wol_enabled, u8 *mac) +{ + struct hw_atl_utils_fw_rpc *prpc = NULL; + unsigned int rpc_size = 0U; + int err = 0; + + err = hw_atl_utils_fw_rpc_wait(self, &prpc); + if (err < 0) + goto err_exit; + + memset(prpc, 0, sizeof(*prpc)); + + if (wol_enabled) { + rpc_size = sizeof(prpc->msg_id) + sizeof(prpc->msg_wol); + + prpc->msg_id = HAL_ATLANTIC_UTILS_FW_MSG_WOL_ADD; + prpc->msg_wol.priority = + HAL_ATLANTIC_UTILS_FW_MSG_WOL_PRIOR; + prpc->msg_wol.pattern_id = + HAL_ATLANTIC_UTILS_FW_MSG_WOL_PATTERN; + prpc->msg_wol.wol_packet_type = + HAL_ATLANTIC_UTILS_FW_MSG_WOL_MAG_PKT; + + ether_addr_copy((u8 *)&prpc->msg_wol.wol_pattern, mac); + } else { + rpc_size = sizeof(prpc->msg_id) + sizeof(prpc->msg_del_id); + + prpc->msg_id = HAL_ATLANTIC_UTILS_FW_MSG_WOL_DEL; + prpc->msg_wol.pattern_id = + HAL_ATLANTIC_UTILS_FW_MSG_WOL_PATTERN; + } + + err = hw_atl_utils_fw_rpc_call(self, rpc_size); + +err_exit: + return err; +} + +int aq_fw1x_set_power(struct aq_hw_s *self, unsigned int power_state, + u8 *mac) +{ + struct hw_atl_utils_fw_rpc *prpc = NULL; + unsigned int rpc_size = 0U; + int err = 0; + + if (self->aq_nic_cfg->wol & AQ_NIC_WOL_ENABLED) { + err = aq_fw1x_set_wol(self, 1, mac); + + if (err < 0) + goto err_exit; + + rpc_size = sizeof(prpc->msg_id) + + sizeof(prpc->msg_enable_wakeup); + + err = hw_atl_utils_fw_rpc_wait(self, &prpc); + + if (err < 0) + goto err_exit; + + memset(prpc, 0, rpc_size); + + prpc->msg_id = HAL_ATLANTIC_UTILS_FW_MSG_ENABLE_WAKEUP; + prpc->msg_enable_wakeup.pattern_mask = 0x00000002; + + err = hw_atl_utils_fw_rpc_call(self, rpc_size); + if (err < 0) + goto err_exit; + } + hw_atl_utils_mpi_set_speed(self, 0); + hw_atl_utils_mpi_set_state(self, MPI_POWER); + +err_exit: + return err; +} + const struct aq_fw_ops aq_fw_1x_ops = { .init = hw_atl_utils_mpi_create, .deinit = hw_atl_fw1x_deinit, @@ -834,5 +916,8 @@ const struct aq_fw_ops aq_fw_1x_ops = { .set_state = hw_atl_utils_mpi_set_state, .update_link_status = hw_atl_utils_mpi_get_link_status, .update_stats = hw_atl_utils_update_stats, + .set_power = aq_fw1x_set_power, + .set_eee_rate = NULL, + .get_eee_rate = NULL, .set_flow_control = NULL, }; diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h index b875590efcbd..3613fca64b58 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h @@ -75,7 +75,7 @@ union __packed ip_addr { } v4; }; -struct __packed hw_aq_atl_utils_fw_rpc { +struct __packed hw_atl_utils_fw_rpc { u32 msg_id; union { @@ -101,8 +101,6 @@ struct __packed hw_aq_atl_utils_fw_rpc { struct { u32 priority; u32 wol_packet_type; - u16 friendly_name_len; - u16 friendly_name[65]; u32 pattern_id; u32 next_wol_pattern_offset; @@ -134,25 +132,112 @@ struct __packed hw_aq_atl_utils_fw_rpc { u32 pattern_offset; u32 pattern_size; } wol_bit_map_pattern; + + struct { + u8 mac_addr[ETH_ALEN]; + } wol_magic_packet_patter; } wol_pattern; } msg_wol; struct { - u32 is_wake_on_link_down; - u32 is_wake_on_link_up; - } msg_wolink; + union { + u32 pattern_mask; + + struct { + u32 reason_arp_v4_pkt : 1; + u32 reason_ipv4_ping_pkt : 1; + u32 reason_ipv6_ns_pkt : 1; + u32 reason_ipv6_ping_pkt : 1; + u32 reason_link_up : 1; + u32 reason_link_down : 1; + u32 reason_maximum : 1; + }; + }; + + union { + u32 offload_mask; + }; + } msg_enable_wakeup; + + struct { + u32 id; + } msg_del_id; }; }; -struct __packed hw_aq_atl_utils_mbox_header { +struct __packed hw_atl_utils_mbox_header { u32 version; u32 transaction_id; u32 error; }; -struct __packed hw_aq_atl_utils_mbox { - struct hw_aq_atl_utils_mbox_header header; +struct __packed hw_aq_info { + u8 reserved[6]; + u16 phy_fault_code; + u16 phy_temperature; + u8 cable_len; + u8 reserved1; + u32 cable_diag_data[4]; + u8 reserved2[32]; + u32 caps_lo; + u32 caps_hi; +}; + +struct __packed hw_atl_utils_mbox { + struct hw_atl_utils_mbox_header header; struct hw_atl_stats_s stats; + struct hw_aq_info info; +}; + +/* fw2x */ +typedef u32 fw_offset_t; + +struct __packed offload_ip_info { + u8 v4_local_addr_count; + u8 v4_addr_count; + u8 v6_local_addr_count; + u8 v6_addr_count; + fw_offset_t v4_addr; + fw_offset_t v4_prefix; + fw_offset_t v6_addr; + fw_offset_t v6_prefix; +}; + +struct __packed offload_port_info { + u16 udp_port_count; + u16 tcp_port_count; + fw_offset_t udp_port; + fw_offset_t tcp_port; +}; + +struct __packed offload_ka_info { + u16 v4_ka_count; + u16 v6_ka_count; + u32 retry_count; + u32 retry_interval; + fw_offset_t v4_ka; + fw_offset_t v6_ka; +}; + +struct __packed offload_rr_info { + u32 rr_count; + u32 rr_buf_len; + fw_offset_t rr_id_x; + fw_offset_t rr_buf; +}; + +struct __packed offload_info { + u32 version; + u32 len; + u8 mac_addr[ETH_ALEN]; + + u8 reserved[2]; + + struct offload_ip_info ips; + struct offload_port_info ports; + struct offload_ka_info kas; + struct offload_rr_info rrs; + u8 buf[0]; }; #define HAL_ATLANTIC_UTILS_CHIP_MIPS 0x00000001U @@ -181,6 +266,21 @@ enum hal_atl_utils_fw_state_e { #define HAL_ATLANTIC_RATE_100M BIT(5) #define HAL_ATLANTIC_RATE_INVALID BIT(6) +#define HAL_ATLANTIC_UTILS_FW_MSG_PING 0x1U +#define HAL_ATLANTIC_UTILS_FW_MSG_ARP 0x2U +#define HAL_ATLANTIC_UTILS_FW_MSG_INJECT 0x3U +#define HAL_ATLANTIC_UTILS_FW_MSG_WOL_ADD 0x4U +#define HAL_ATLANTIC_UTILS_FW_MSG_WOL_PRIOR 0x10000000U +#define HAL_ATLANTIC_UTILS_FW_MSG_WOL_PATTERN 0x1U +#define HAL_ATLANTIC_UTILS_FW_MSG_WOL_MAG_PKT 0x2U +#define HAL_ATLANTIC_UTILS_FW_MSG_WOL_DEL 0x5U +#define HAL_ATLANTIC_UTILS_FW_MSG_ENABLE_WAKEUP 0x6U +#define HAL_ATLANTIC_UTILS_FW_MSG_MSM_PFC 0x7U +#define HAL_ATLANTIC_UTILS_FW_MSG_PROVISIONING 0x8U +#define HAL_ATLANTIC_UTILS_FW_MSG_OFFLOAD_ADD 0x9U +#define HAL_ATLANTIC_UTILS_FW_MSG_OFFLOAD_DEL 0xAU +#define HAL_ATLANTIC_UTILS_FW_MSG_CABLE_DIAG 0xDU + enum hw_atl_fw2x_rate { FW2X_RATE_100M = 0x20, FW2X_RATE_1G = 0x100, @@ -286,10 +386,10 @@ int hw_atl_utils_soft_reset(struct aq_hw_s *self); void hw_atl_utils_hw_chip_features_init(struct aq_hw_s *self, u32 *p); int hw_atl_utils_mpi_read_mbox(struct aq_hw_s *self, - struct hw_aq_atl_utils_mbox_header *pmbox); + struct hw_atl_utils_mbox_header *pmbox); void hw_atl_utils_mpi_read_stats(struct aq_hw_s *self, - struct hw_aq_atl_utils_mbox *pmbox); + struct hw_atl_utils_mbox *pmbox); void hw_atl_utils_mpi_set(struct aq_hw_s *self, enum hal_atl_utils_fw_state_e state, @@ -316,9 +416,17 @@ int hw_atl_utils_get_fw_version(struct aq_hw_s *self, u32 *fw_version); int hw_atl_utils_update_stats(struct aq_hw_s *self); struct aq_stats_s *hw_atl_utils_get_hw_stats(struct aq_hw_s *self); + int hw_atl_utils_fw_downld_dwords(struct aq_hw_s *self, u32 a, u32 *p, u32 cnt); +int hw_atl_utils_fw_set_wol(struct aq_hw_s *self, bool wol_enabled, u8 *mac); + +int hw_atl_utils_fw_rpc_call(struct aq_hw_s *self, unsigned int rpc_size); + +int hw_atl_utils_fw_rpc_wait(struct aq_hw_s *self, + struct hw_atl_utils_fw_rpc **rpc); + extern const struct aq_fw_ops aq_fw_1x_ops; extern const struct aq_fw_ops aq_fw_2x_ops; diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c index e37943760a58..c0568465e10b 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c @@ -16,11 +16,13 @@ #include "../aq_pci_func.h" #include "../aq_ring.h" #include "../aq_vec.h" +#include "../aq_nic.h" #include "hw_atl_utils.h" #include "hw_atl_llh.h" #define HW_ATL_FW2X_MPI_EFUSE_ADDR 0x364 #define HW_ATL_FW2X_MPI_MBOX_ADDR 0x360 +#define HW_ATL_FW2X_MPI_RPC_ADDR 0x334 #define HW_ATL_FW2X_MPI_CONTROL_ADDR 0x368 #define HW_ATL_FW2X_MPI_CONTROL2_ADDR 0x36C @@ -28,6 +30,42 @@ #define HW_ATL_FW2X_MPI_STATE_ADDR 0x370 #define HW_ATL_FW2X_MPI_STATE2_ADDR 0x374 +#define HW_ATL_FW2X_CAP_SLEEP_PROXY BIT(CAPS_HI_SLEEP_PROXY) +#define HW_ATL_FW2X_CAP_WOL BIT(CAPS_HI_WOL) + +#define HW_ATL_FW2X_CTRL_SLEEP_PROXY BIT(CTRL_SLEEP_PROXY) +#define HW_ATL_FW2X_CTRL_WOL BIT(CTRL_WOL) +#define HW_ATL_FW2X_CTRL_LINK_DROP BIT(CTRL_LINK_DROP) +#define HW_ATL_FW2X_CTRL_PAUSE BIT(CTRL_PAUSE) +#define HW_ATL_FW2X_CTRL_ASYMMETRIC_PAUSE BIT(CTRL_ASYMMETRIC_PAUSE) +#define HW_ATL_FW2X_CTRL_FORCE_RECONNECT BIT(CTRL_FORCE_RECONNECT) + +#define HW_ATL_FW2X_CAP_EEE_1G_MASK BIT(CAPS_HI_1000BASET_FD_EEE) +#define HW_ATL_FW2X_CAP_EEE_2G5_MASK BIT(CAPS_HI_2P5GBASET_FD_EEE) +#define HW_ATL_FW2X_CAP_EEE_5G_MASK BIT(CAPS_HI_5GBASET_FD_EEE) +#define HW_ATL_FW2X_CAP_EEE_10G_MASK BIT(CAPS_HI_10GBASET_FD_EEE) + +#define HAL_ATLANTIC_WOL_FILTERS_COUNT 8 +#define HAL_ATLANTIC_UTILS_FW2X_MSG_WOL 0x0E + +struct __packed fw2x_msg_wol_pattern { + u8 mask[16]; + u32 crc; +}; + +struct __packed fw2x_msg_wol { + u32 msg_id; + u8 hw_addr[ETH_ALEN]; + u8 magic_packet_enabled; + u8 filter_count; + struct fw2x_msg_wol_pattern filter[HAL_ATLANTIC_WOL_FILTERS_COUNT]; + u8 link_up_enabled; + u8 link_down_enabled; + u16 reserved; + u32 link_up_timeout; + u32 link_down_timeout; +}; + static int aq_fw2x_set_link_speed(struct aq_hw_s *self, u32 speed); static int aq_fw2x_set_state(struct aq_hw_s *self, enum hal_atl_utils_fw_state_e state); @@ -38,8 +76,12 @@ static int aq_fw2x_init(struct aq_hw_s *self) /* check 10 times by 1ms */ AQ_HW_WAIT_FOR(0U != (self->mbox_addr = - aq_hw_read_reg(self, HW_ATL_FW2X_MPI_MBOX_ADDR)), + aq_hw_read_reg(self, HW_ATL_FW2X_MPI_MBOX_ADDR)), 1000U, 10U); + AQ_HW_WAIT_FOR(0U != (self->rpc_addr = + aq_hw_read_reg(self, HW_ATL_FW2X_MPI_RPC_ADDR)), + 1000U, 100U); + return err; } @@ -78,6 +120,38 @@ static enum hw_atl_fw2x_rate link_speed_mask_2fw2x_ratemask(u32 speed) return rate; } +static u32 fw2x_to_eee_mask(u32 speed) +{ + u32 rate = 0; + + if (speed & HW_ATL_FW2X_CAP_EEE_10G_MASK) + rate |= AQ_NIC_RATE_EEE_10G; + if (speed & HW_ATL_FW2X_CAP_EEE_5G_MASK) + rate |= AQ_NIC_RATE_EEE_5G; + if (speed & HW_ATL_FW2X_CAP_EEE_2G5_MASK) + rate |= AQ_NIC_RATE_EEE_2GS; + if (speed & HW_ATL_FW2X_CAP_EEE_1G_MASK) + rate |= AQ_NIC_RATE_EEE_1G; + + return rate; +} + +static u32 eee_mask_to_fw2x(u32 speed) +{ + u32 rate = 0; + + if (speed & AQ_NIC_RATE_EEE_10G) + rate |= HW_ATL_FW2X_CAP_EEE_10G_MASK; + if (speed & AQ_NIC_RATE_EEE_5G) + rate |= HW_ATL_FW2X_CAP_EEE_5G_MASK; + if (speed & AQ_NIC_RATE_EEE_2GS) + rate |= HW_ATL_FW2X_CAP_EEE_2G5_MASK; + if (speed & AQ_NIC_RATE_EEE_1G) + rate |= HW_ATL_FW2X_CAP_EEE_1G_MASK; + + return rate; +} + static int aq_fw2x_set_link_speed(struct aq_hw_s *self, u32 speed) { u32 val = link_speed_mask_2fw2x_ratemask(speed); @@ -100,14 +174,27 @@ static void aq_fw2x_set_mpi_flow_control(struct aq_hw_s *self, u32 *mpi_state) *mpi_state &= ~BIT(CAPS_HI_ASYMMETRIC_PAUSE); } +static void aq_fw2x_upd_eee_rate_bits(struct aq_hw_s *self, u32 *mpi_opts, + u32 eee_speeds) +{ + *mpi_opts &= ~(HW_ATL_FW2X_CAP_EEE_1G_MASK | + HW_ATL_FW2X_CAP_EEE_2G5_MASK | + HW_ATL_FW2X_CAP_EEE_5G_MASK | + HW_ATL_FW2X_CAP_EEE_10G_MASK); + + *mpi_opts |= eee_mask_to_fw2x(eee_speeds); +} + static int aq_fw2x_set_state(struct aq_hw_s *self, enum hal_atl_utils_fw_state_e state) { u32 mpi_state = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR); + struct aq_nic_cfg_s *cfg = self->aq_nic_cfg; switch (state) { case MPI_INIT: mpi_state &= ~BIT(CAPS_HI_LINK_DROP); + aq_fw2x_upd_eee_rate_bits(self, &mpi_state, cfg->eee_speeds); aq_fw2x_set_mpi_flow_control(self, &mpi_state); break; case MPI_DEINIT: @@ -126,7 +213,7 @@ static int aq_fw2x_update_link_status(struct aq_hw_s *self) { u32 mpi_state = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_STATE_ADDR); u32 speed = mpi_state & (FW2X_RATE_100M | FW2X_RATE_1G | - FW2X_RATE_2G5 | FW2X_RATE_5G | FW2X_RATE_10G); + FW2X_RATE_2G5 | FW2X_RATE_5G | FW2X_RATE_10G); struct aq_hw_link_status_s *link_status = &self->aq_link_status; if (speed) { @@ -175,9 +262,7 @@ static int aq_fw2x_get_mac_permanent(struct aq_hw_s *self, u8 *mac) get_random_bytes(&rnd, sizeof(unsigned int)); - l = 0xE3000000U - | (0xFFFFU & rnd) - | (0x00 << 16); + l = 0xE3000000U | (0xFFFFU & rnd) | (0x00 << 16); h = 0x8001300EU; mac[5] = (u8)(0xFFU & l); @@ -194,7 +279,7 @@ static int aq_fw2x_get_mac_permanent(struct aq_hw_s *self, u8 *mac) return err; } -static int aq_fw2x_update_stats(struct aq_hw_s *self) +int aq_fw2x_update_stats(struct aq_hw_s *self) { int err = 0; u32 mpi_opts = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR); @@ -207,7 +292,7 @@ static int aq_fw2x_update_stats(struct aq_hw_s *self) /* Wait FW to report back */ AQ_HW_WAIT_FOR(orig_stats_val != (aq_hw_read_reg(self, HW_ATL_FW2X_MPI_STATE2_ADDR) & - BIT(CAPS_HI_STATISTICS)), + BIT(CAPS_HI_STATISTICS)), 1U, 10000U); if (err) return err; @@ -215,6 +300,135 @@ static int aq_fw2x_update_stats(struct aq_hw_s *self) return hw_atl_utils_update_stats(self); } +static int aq_fw2x_set_sleep_proxy(struct aq_hw_s *self, u8 *mac) +{ + struct hw_atl_utils_fw_rpc *rpc = NULL; + struct offload_info *cfg = NULL; + unsigned int rpc_size = 0U; + u32 mpi_opts; + int err = 0; + + rpc_size = sizeof(rpc->msg_id) + sizeof(*cfg); + + err = hw_atl_utils_fw_rpc_wait(self, &rpc); + if (err < 0) + goto err_exit; + + memset(rpc, 0, rpc_size); + cfg = (struct offload_info *)(&rpc->msg_id + 1); + + memcpy(cfg->mac_addr, mac, ETH_ALEN); + cfg->len = sizeof(*cfg); + + /* Clear bit 0x36C.23 and 0x36C.22 */ + mpi_opts = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR); + mpi_opts &= ~HW_ATL_FW2X_CTRL_SLEEP_PROXY; + mpi_opts &= ~HW_ATL_FW2X_CTRL_LINK_DROP; + + aq_hw_write_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR, mpi_opts); + + err = hw_atl_utils_fw_rpc_call(self, rpc_size); + if (err < 0) + goto err_exit; + + /* Set bit 0x36C.23 */ + mpi_opts |= HW_ATL_FW2X_CTRL_SLEEP_PROXY; + aq_hw_write_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR, mpi_opts); + + AQ_HW_WAIT_FOR((aq_hw_read_reg(self, HW_ATL_FW2X_MPI_STATE2_ADDR) & + HW_ATL_FW2X_CTRL_SLEEP_PROXY), 1U, 10000U); + +err_exit: + return err; +} + +static int aq_fw2x_set_wol_params(struct aq_hw_s *self, u8 *mac) +{ + struct hw_atl_utils_fw_rpc *rpc = NULL; + struct fw2x_msg_wol *msg = NULL; + u32 mpi_opts; + int err = 0; + + err = hw_atl_utils_fw_rpc_wait(self, &rpc); + if (err < 0) + goto err_exit; + + msg = (struct fw2x_msg_wol *)rpc; + + msg->msg_id = HAL_ATLANTIC_UTILS_FW2X_MSG_WOL; + msg->magic_packet_enabled = true; + memcpy(msg->hw_addr, mac, ETH_ALEN); + + mpi_opts = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR); + mpi_opts &= ~(HW_ATL_FW2X_CTRL_SLEEP_PROXY | HW_ATL_FW2X_CTRL_WOL); + + aq_hw_write_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR, mpi_opts); + + err = hw_atl_utils_fw_rpc_call(self, sizeof(*msg)); + if (err < 0) + goto err_exit; + + /* Set bit 0x36C.24 */ + mpi_opts |= HW_ATL_FW2X_CTRL_WOL; + aq_hw_write_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR, mpi_opts); + + AQ_HW_WAIT_FOR((aq_hw_read_reg(self, HW_ATL_FW2X_MPI_STATE2_ADDR) & + HW_ATL_FW2X_CTRL_WOL), 1U, 10000U); + +err_exit: + return err; +} + +static int aq_fw2x_set_power(struct aq_hw_s *self, unsigned int power_state, + u8 *mac) +{ + int err = 0; + + if (self->aq_nic_cfg->wol & AQ_NIC_WOL_ENABLED) { + err = aq_fw2x_set_sleep_proxy(self, mac); + if (err < 0) + goto err_exit; + err = aq_fw2x_set_wol_params(self, mac); + } + +err_exit: + return err; +} + +static int aq_fw2x_set_eee_rate(struct aq_hw_s *self, u32 speed) +{ + u32 mpi_opts = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR); + + aq_fw2x_upd_eee_rate_bits(self, &mpi_opts, speed); + + aq_hw_write_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR, mpi_opts); + + return 0; +} + +static int aq_fw2x_get_eee_rate(struct aq_hw_s *self, u32 *rate, + u32 *supported_rates) +{ + u32 mpi_state; + u32 caps_hi; + int err = 0; + u32 addr = self->mbox_addr + offsetof(struct hw_atl_utils_mbox, info) + + offsetof(struct hw_aq_info, caps_hi); + + err = hw_atl_utils_fw_downld_dwords(self, addr, &caps_hi, + sizeof(caps_hi) / sizeof(u32)); + + if (err) + return err; + + *supported_rates = fw2x_to_eee_mask(caps_hi); + + mpi_state = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_STATE2_ADDR); + *rate = fw2x_to_eee_mask(mpi_state); + + return err; +} + static int aq_fw2x_renegotiate(struct aq_hw_s *self) { u32 mpi_opts = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR); @@ -247,5 +461,8 @@ const struct aq_fw_ops aq_fw_2x_ops = { .set_state = aq_fw2x_set_state, .update_link_status = aq_fw2x_update_link_status, .update_stats = aq_fw2x_update_stats, - .set_flow_control = aq_fw2x_set_flow_control, + .set_power = aq_fw2x_set_power, + .set_eee_rate = aq_fw2x_set_eee_rate, + .get_eee_rate = aq_fw2x_get_eee_rate, + .set_flow_control = aq_fw2x_set_flow_control, }; diff --git a/drivers/net/ethernet/aquantia/atlantic/ver.h b/drivers/net/ethernet/aquantia/atlantic/ver.h index 94efc6477bdc..b48260114da3 100644 --- a/drivers/net/ethernet/aquantia/atlantic/ver.h +++ b/drivers/net/ethernet/aquantia/atlantic/ver.h @@ -12,7 +12,7 @@ #define NIC_MAJOR_DRIVER_VERSION 2 #define NIC_MINOR_DRIVER_VERSION 0 -#define NIC_BUILD_DRIVER_VERSION 3 +#define NIC_BUILD_DRIVER_VERSION 4 #define NIC_REVISION_DRIVER_VERSION 0 #define AQ_CFG_DRV_VERSION_SUFFIX "-kern" diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c index b81fbf119bce..72e7fa71e84c 100644 --- a/drivers/net/ethernet/atheros/atlx/atl1.c +++ b/drivers/net/ethernet/atheros/atlx/atl1.c @@ -63,7 +63,6 @@ #include <linux/jiffies.h> #include <linux/mii.h> #include <linux/module.h> -#include <linux/moduleparam.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/pci.h> diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c index c8d1f8fa4713..6f56276015a4 100644 --- a/drivers/net/ethernet/aurora/nb8800.c +++ b/drivers/net/ethernet/aurora/nb8800.c @@ -935,18 +935,11 @@ static void nb8800_pause_adv(struct net_device *dev) { struct nb8800_priv *priv = netdev_priv(dev); struct phy_device *phydev = dev->phydev; - u32 adv = 0; if (!phydev) return; - if (priv->pause_rx) - adv |= ADVERTISED_Pause | ADVERTISED_Asym_Pause; - if (priv->pause_tx) - adv ^= ADVERTISED_Asym_Pause; - - phydev->supported |= adv; - phydev->advertising |= adv; + phy_set_asym_pause(phydev, priv->pause_rx, priv->pause_tx); } static int nb8800_open(struct net_device *dev) diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c index 897302adc38e..02e7dfc1a2ef 100644 --- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c +++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c @@ -890,19 +890,10 @@ static int bcm_enet_open(struct net_device *dev) } /* mask with MAC supported features */ - phydev->supported &= (SUPPORTED_10baseT_Half | - SUPPORTED_10baseT_Full | - SUPPORTED_100baseT_Half | - SUPPORTED_100baseT_Full | - SUPPORTED_Autoneg | - SUPPORTED_Pause | - SUPPORTED_MII); - phydev->advertising = phydev->supported; - - if (priv->pause_auto && priv->pause_rx && priv->pause_tx) - phydev->advertising |= SUPPORTED_Pause; - else - phydev->advertising &= ~SUPPORTED_Pause; + phy_support_sym_pause(phydev); + phy_set_max_speed(phydev, SPEED_100); + phy_set_sym_pause(phydev, priv->pause_rx, priv->pause_rx, + priv->pause_auto); phy_attached_info(phydev); diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index 4c94d9218bba..cabc8e49ad24 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -616,7 +616,6 @@ static int bgmac_dma_alloc(struct bgmac *bgmac) static const u16 ring_base[] = { BGMAC_DMA_BASE0, BGMAC_DMA_BASE1, BGMAC_DMA_BASE2, BGMAC_DMA_BASE3, }; int size; /* ring size: different for Tx and Rx */ - int err; int i; BUILD_BUG_ON(BGMAC_MAX_TX_RINGS > ARRAY_SIZE(ring_base)); @@ -666,7 +665,6 @@ static int bgmac_dma_alloc(struct bgmac *bgmac) if (!ring->cpu_base) { dev_err(bgmac->dev, "Allocation of RX ring 0x%X failed\n", ring->mmio_base); - err = -ENOMEM; goto err_dma_free; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 8bb1e38b1681..177587f9c3f1 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -5913,12 +5913,12 @@ unsigned int bnxt_get_max_func_cp_rings(struct bnxt *bp) return bp->hw_resc.max_cp_rings; } -void bnxt_set_max_func_cp_rings(struct bnxt *bp, unsigned int max) +unsigned int bnxt_get_max_func_cp_rings_for_en(struct bnxt *bp) { - bp->hw_resc.max_cp_rings = max; + return bp->hw_resc.max_cp_rings - bnxt_get_ulp_msix_num(bp); } -unsigned int bnxt_get_max_func_irqs(struct bnxt *bp) +static unsigned int bnxt_get_max_func_irqs(struct bnxt *bp) { struct bnxt_hw_resc *hw_resc = &bp->hw_resc; @@ -6684,6 +6684,8 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up) hw_resc->resv_rx_rings = 0; hw_resc->resv_hw_ring_grps = 0; hw_resc->resv_vnics = 0; + bp->tx_nr_rings = 0; + bp->rx_nr_rings = 0; } return rc; } @@ -8025,7 +8027,7 @@ static int bnxt_change_mac_addr(struct net_device *dev, void *p) if (ether_addr_equal(addr->sa_data, dev->dev_addr)) return 0; - rc = bnxt_approve_mac(bp, addr->sa_data); + rc = bnxt_approve_mac(bp, addr->sa_data, true); if (rc) return rc; @@ -8629,7 +8631,8 @@ static void _bnxt_get_max_rings(struct bnxt *bp, int *max_rx, int *max_tx, *max_tx = hw_resc->max_tx_rings; *max_rx = hw_resc->max_rx_rings; - *max_cp = min_t(int, hw_resc->max_irqs, hw_resc->max_cp_rings); + *max_cp = min_t(int, bnxt_get_max_func_cp_rings_for_en(bp), + hw_resc->max_irqs); *max_cp = min_t(int, *max_cp, hw_resc->max_stat_ctxs); max_ring_grps = hw_resc->max_hw_ring_grps; if (BNXT_CHIP_TYPE_NITRO_A0(bp) && BNXT_PF(bp)) { @@ -8769,20 +8772,25 @@ static int bnxt_init_dflt_ring_mode(struct bnxt *bp) if (bp->tx_nr_rings) return 0; + bnxt_ulp_irq_stop(bp); + bnxt_clear_int_mode(bp); rc = bnxt_set_dflt_rings(bp, true); if (rc) { netdev_err(bp->dev, "Not enough rings available.\n"); - return rc; + goto init_dflt_ring_err; } rc = bnxt_init_int_mode(bp); if (rc) - return rc; + goto init_dflt_ring_err; + bp->tx_nr_rings_per_tc = bp->tx_nr_rings; if (bnxt_rfs_supported(bp) && bnxt_rfs_capable(bp)) { bp->flags |= BNXT_FLAG_RFS; bp->dev->features |= NETIF_F_NTUPLE; } - return 0; +init_dflt_ring_err: + bnxt_ulp_irq_restart(bp, rc); + return rc; } int bnxt_restore_pf_fw_resources(struct bnxt *bp) @@ -8819,14 +8827,19 @@ static int bnxt_init_mac_addr(struct bnxt *bp) } else { #ifdef CONFIG_BNXT_SRIOV struct bnxt_vf_info *vf = &bp->vf; + bool strict_approval = true; if (is_valid_ether_addr(vf->mac_addr)) { /* overwrite netdev dev_addr with admin VF MAC */ memcpy(bp->dev->dev_addr, vf->mac_addr, ETH_ALEN); + /* Older PF driver or firmware may not approve this + * correctly. + */ + strict_approval = false; } else { eth_hw_addr_random(bp->dev); } - rc = bnxt_approve_mac(bp, bp->dev->dev_addr); + rc = bnxt_approve_mac(bp, bp->dev->dev_addr, strict_approval); #endif } return rc; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index fefa011320e0..bde384630a75 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1481,8 +1481,7 @@ int bnxt_hwrm_set_coal(struct bnxt *); unsigned int bnxt_get_max_func_stat_ctxs(struct bnxt *bp); void bnxt_set_max_func_stat_ctxs(struct bnxt *bp, unsigned int max); unsigned int bnxt_get_max_func_cp_rings(struct bnxt *bp); -void bnxt_set_max_func_cp_rings(struct bnxt *bp, unsigned int max); -unsigned int bnxt_get_max_func_irqs(struct bnxt *bp); +unsigned int bnxt_get_max_func_cp_rings_for_en(struct bnxt *bp); int bnxt_get_avail_msix(struct bnxt *bp, int num); int bnxt_reserve_rings(struct bnxt *bp); void bnxt_tx_disable(struct bnxt *bp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c index 6d583bcd2a81..3962f6fd543c 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -451,7 +451,7 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs) bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_VF_RESOURCE_CFG, -1, -1); - vf_cp_rings = hw_resc->max_cp_rings - bp->cp_nr_rings; + vf_cp_rings = bnxt_get_max_func_cp_rings_for_en(bp) - bp->cp_nr_rings; vf_stat_ctx = hw_resc->max_stat_ctxs - bp->num_stat_ctxs; if (bp->flags & BNXT_FLAG_AGG_RINGS) vf_rx_rings = hw_resc->max_rx_rings - bp->rx_nr_rings * 2; @@ -549,7 +549,8 @@ static int bnxt_hwrm_func_cfg(struct bnxt *bp, int num_vfs) max_stat_ctxs = hw_resc->max_stat_ctxs; /* Remaining rings are distributed equally amongs VF's for now */ - vf_cp_rings = (hw_resc->max_cp_rings - bp->cp_nr_rings) / num_vfs; + vf_cp_rings = (bnxt_get_max_func_cp_rings_for_en(bp) - + bp->cp_nr_rings) / num_vfs; vf_stat_ctx = (max_stat_ctxs - bp->num_stat_ctxs) / num_vfs; if (bp->flags & BNXT_FLAG_AGG_RINGS) vf_rx_rings = (hw_resc->max_rx_rings - bp->rx_nr_rings * 2) / @@ -643,7 +644,7 @@ static int bnxt_sriov_enable(struct bnxt *bp, int *num_vfs) */ vfs_supported = *num_vfs; - avail_cp = hw_resc->max_cp_rings - bp->cp_nr_rings; + avail_cp = bnxt_get_max_func_cp_rings_for_en(bp) - bp->cp_nr_rings; avail_stat = hw_resc->max_stat_ctxs - bp->num_stat_ctxs; avail_cp = min_t(int, avail_cp, avail_stat); @@ -1103,7 +1104,7 @@ update_vf_mac_exit: mutex_unlock(&bp->hwrm_cmd_lock); } -int bnxt_approve_mac(struct bnxt *bp, u8 *mac) +int bnxt_approve_mac(struct bnxt *bp, u8 *mac, bool strict) { struct hwrm_func_vf_cfg_input req = {0}; int rc = 0; @@ -1121,12 +1122,13 @@ int bnxt_approve_mac(struct bnxt *bp, u8 *mac) memcpy(req.dflt_mac_addr, mac, ETH_ALEN); rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); mac_done: - if (rc) { + if (rc && strict) { rc = -EADDRNOTAVAIL; netdev_warn(bp->dev, "VF MAC address %pM not approved by the PF\n", mac); + return rc; } - return rc; + return 0; } #else @@ -1143,7 +1145,7 @@ void bnxt_update_vf_mac(struct bnxt *bp) { } -int bnxt_approve_mac(struct bnxt *bp, u8 *mac) +int bnxt_approve_mac(struct bnxt *bp, u8 *mac, bool strict) { return 0; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h index e9b20cd19881..2eed9eda1195 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h @@ -39,5 +39,5 @@ int bnxt_sriov_configure(struct pci_dev *pdev, int num_vfs); void bnxt_sriov_disable(struct bnxt *); void bnxt_hwrm_exec_fwd_req(struct bnxt *); void bnxt_update_vf_mac(struct bnxt *); -int bnxt_approve_mac(struct bnxt *, u8 *); +int bnxt_approve_mac(struct bnxt *, u8 *, bool); #endif diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c index 139d96c5a023..f4ba9b3f8819 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c @@ -110,16 +110,14 @@ static int bnxt_tc_parse_actions(struct bnxt *bp, struct tcf_exts *tc_exts) { const struct tc_action *tc_act; - LIST_HEAD(tc_actions); - int rc; + int i, rc; if (!tcf_exts_has_actions(tc_exts)) { netdev_info(bp->dev, "no actions"); return -EINVAL; } - tcf_exts_to_list(tc_exts, &tc_actions); - list_for_each_entry(tc_act, &tc_actions, list) { + tcf_exts_for_each_action(i, tc_act, tc_exts) { /* Drop action */ if (is_tcf_gact_shot(tc_act)) { actions->flags |= BNXT_TC_ACTION_FLAG_DROP; @@ -183,7 +181,6 @@ static int bnxt_tc_parse_flow(struct bnxt *bp, struct bnxt_tc_flow *flow) { struct flow_dissector *dissector = tc_flow_cmd->dissector; - u16 addr_type = 0; /* KEY_CONTROL and KEY_BASIC are needed for forming a meaningful key */ if ((dissector->used_keys & BIT(FLOW_DISSECTOR_KEY_CONTROL)) == 0 || @@ -193,13 +190,6 @@ static int bnxt_tc_parse_flow(struct bnxt *bp, return -EOPNOTSUPP; } - if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_CONTROL)) { - struct flow_dissector_key_control *key = - GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_CONTROL); - - addr_type = key->addr_type; - } - if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_BASIC)) { struct flow_dissector_key_basic *key = GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_BASIC); @@ -295,13 +285,6 @@ static int bnxt_tc_parse_flow(struct bnxt *bp, flow->l4_mask.icmp.code = mask->code; } - if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL)) { - struct flow_dissector_key_control *key = - GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_CONTROL); - - addr_type = key->addr_type; - } - if (dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) { struct flow_dissector_key_ipv4_addrs *key = GET_KEY(tc_flow_cmd, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c index c37b2842f972..beee61292d5e 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c @@ -169,7 +169,6 @@ static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, int ulp_id, edev->ulp_tbl[ulp_id].msix_requested = avail_msix; } bnxt_fill_msix_vecs(bp, ent); - bnxt_set_max_func_cp_rings(bp, max_cp_rings - avail_msix); edev->flags |= BNXT_EN_FLAG_MSIX_REQUESTED; return avail_msix; } @@ -178,7 +177,6 @@ static int bnxt_free_msix_vecs(struct bnxt_en_dev *edev, int ulp_id) { struct net_device *dev = edev->net; struct bnxt *bp = netdev_priv(dev); - int max_cp_rings, msix_requested; ASSERT_RTNL(); if (ulp_id != BNXT_ROCE_ULP) @@ -187,9 +185,6 @@ static int bnxt_free_msix_vecs(struct bnxt_en_dev *edev, int ulp_id) if (!(edev->flags & BNXT_EN_FLAG_MSIX_REQUESTED)) return 0; - max_cp_rings = bnxt_get_max_func_cp_rings(bp); - msix_requested = edev->ulp_tbl[ulp_id].msix_requested; - bnxt_set_max_func_cp_rings(bp, max_cp_rings + msix_requested); edev->ulp_tbl[ulp_id].msix_requested = 0; edev->flags &= ~BNXT_EN_FLAG_MSIX_REQUESTED; if (netif_running(dev)) { @@ -220,21 +215,6 @@ int bnxt_get_ulp_msix_base(struct bnxt *bp) return 0; } -void bnxt_subtract_ulp_resources(struct bnxt *bp, int ulp_id) -{ - ASSERT_RTNL(); - if (bnxt_ulp_registered(bp->edev, ulp_id)) { - struct bnxt_en_dev *edev = bp->edev; - unsigned int msix_req, max; - - msix_req = edev->ulp_tbl[ulp_id].msix_requested; - max = bnxt_get_max_func_cp_rings(bp); - bnxt_set_max_func_cp_rings(bp, max - msix_req); - max = bnxt_get_max_func_stat_ctxs(bp); - bnxt_set_max_func_stat_ctxs(bp, max - 1); - } -} - static int bnxt_send_msg(struct bnxt_en_dev *edev, int ulp_id, struct bnxt_fw_msg *fw_msg) { diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h index df48ac71729f..d9bea37cd211 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.h @@ -90,7 +90,6 @@ static inline bool bnxt_ulp_registered(struct bnxt_en_dev *edev, int ulp_id) int bnxt_get_ulp_msix_num(struct bnxt *bp); int bnxt_get_ulp_msix_base(struct bnxt *bp); -void bnxt_subtract_ulp_resources(struct bnxt *bp, int ulp_id); void bnxt_ulp_stop(struct bnxt *bp); void bnxt_ulp_start(struct bnxt *bp); void bnxt_ulp_sriov_cfg(struct bnxt *bp, int num_vfs); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c index e31f5d803c13..b574fe8e974e 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c @@ -209,9 +209,7 @@ struct net_device *bnxt_get_vf_rep(struct bnxt *bp, u16 cfa_code) void bnxt_vf_rep_rx(struct bnxt *bp, struct sk_buff *skb) { struct bnxt_vf_rep *vf_rep = netdev_priv(skb->dev); - struct bnxt_vf_rep_stats *rx_stats; - rx_stats = &vf_rep->rx_stats; vf_rep->rx_stats.bytes += skb->len; vf_rep->rx_stats.packets++; diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h index b773bc07edf7..14b49612aa86 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h @@ -186,6 +186,9 @@ struct bcmgenet_mib_counters { #define UMAC_MAC1 0x010 #define UMAC_MAX_FRAME_LEN 0x014 +#define UMAC_MODE 0x44 +#define MODE_LINK_STATUS (1 << 5) + #define UMAC_EEE_CTRL 0x064 #define EN_LPI_RX_PAUSE (1 << 0) #define EN_LPI_TX_PFC (1 << 1) diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 5333274a283c..b756fc79424e 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -115,8 +115,14 @@ void bcmgenet_mii_setup(struct net_device *dev) static int bcmgenet_fixed_phy_link_update(struct net_device *dev, struct fixed_phy_status *status) { - if (dev && dev->phydev && status) - status->link = dev->phydev->link; + struct bcmgenet_priv *priv; + u32 reg; + + if (dev && dev->phydev && status) { + priv = netdev_priv(dev); + reg = bcmgenet_umac_readl(priv, UMAC_MODE); + status->link = !!(reg & MODE_LINK_STATUS); + } return 0; } @@ -208,7 +214,7 @@ int bcmgenet_mii_config(struct net_device *dev, bool init) case PHY_INTERFACE_MODE_MII: phy_name = "external MII"; - phydev->supported &= PHY_BASIC_FEATURES; + phy_set_max_speed(phydev, SPEED_100); bcmgenet_sys_writel(priv, PORT_MODE_EXT_EPHY, SYS_PORT_CTRL); break; @@ -220,11 +226,10 @@ int bcmgenet_mii_config(struct net_device *dev, bool init) * capabilities, use that knowledge to also configure the * Reverse MII interface correctly. */ - if ((dev->phydev->supported & PHY_BASIC_FEATURES) == - PHY_BASIC_FEATURES) - port_ctrl = PORT_MODE_EXT_RVMII_25; - else + if (dev->phydev->supported & PHY_1000BT_FEATURES) port_ctrl = PORT_MODE_EXT_RVMII_50; + else + port_ctrl = PORT_MODE_EXT_RVMII_25; bcmgenet_sys_writel(priv, port_ctrl, SYS_PORT_CTRL); break; diff --git a/drivers/net/ethernet/broadcom/sb1250-mac.c b/drivers/net/ethernet/broadcom/sb1250-mac.c index ef4a0c326736..c44cff54262c 100644 --- a/drivers/net/ethernet/broadcom/sb1250-mac.c +++ b/drivers/net/ethernet/broadcom/sb1250-mac.c @@ -156,7 +156,7 @@ enum sbmac_state { (d)->sbdma_dscrtable : (d)->f+1) -#define NUMCACHEBLKS(x) (((x)+SMP_CACHE_BYTES-1)/SMP_CACHE_BYTES) +#define NUMCACHEBLKS(x) DIV_ROUND_UP(x, SMP_CACHE_BYTES) #define SBMAC_MAX_TXDESCR 256 #define SBMAC_MAX_RXDESCR 256 @@ -2357,21 +2357,11 @@ static int sbmac_mii_probe(struct net_device *dev) } /* Remove any features not supported by the controller */ - phy_dev->supported &= SUPPORTED_10baseT_Half | - SUPPORTED_10baseT_Full | - SUPPORTED_100baseT_Half | - SUPPORTED_100baseT_Full | - SUPPORTED_1000baseT_Half | - SUPPORTED_1000baseT_Full | - SUPPORTED_Autoneg | - SUPPORTED_MII | - SUPPORTED_Pause | - SUPPORTED_Asym_Pause; + phy_set_max_speed(phy_dev, SPEED_1000); + phy_support_asym_pause(phy_dev); phy_attached_info(phy_dev); - phy_dev->advertising = phy_dev->supported; - sc->phy_dev = phy_dev; return 0; diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index e6f28c7942ab..89295306f161 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -1598,7 +1598,7 @@ static int tg3_mdio_init(struct tg3 *tp) phydev->dev_flags |= PHY_BRCM_EXT_IBND_RX_ENABLE; if (tg3_flag(tp, RGMII_EXT_IBND_TX_EN)) phydev->dev_flags |= PHY_BRCM_EXT_IBND_TX_ENABLE; - /* fallthru */ + /* fall through */ case PHY_ID_RTL8211C: phydev->interface = PHY_INTERFACE_MODE_RGMII; break; @@ -2122,16 +2122,14 @@ static int tg3_phy_init(struct tg3 *tp) case PHY_INTERFACE_MODE_GMII: case PHY_INTERFACE_MODE_RGMII: if (!(tp->phy_flags & TG3_PHYFLG_10_100_ONLY)) { - phydev->supported &= (PHY_GBIT_FEATURES | - SUPPORTED_Pause | - SUPPORTED_Asym_Pause); + phy_set_max_speed(phydev, SPEED_1000); + phy_support_asym_pause(phydev); break; } - /* fallthru */ + /* fall through */ case PHY_INTERFACE_MODE_MII: - phydev->supported &= (PHY_BASIC_FEATURES | - SUPPORTED_Pause | - SUPPORTED_Asym_Pause); + phy_set_max_speed(phydev, SPEED_100); + phy_support_asym_pause(phydev); break; default: phy_disconnect(mdiobus_get_phy(tp->mdio_bus, tp->phy_addr)); @@ -2140,8 +2138,6 @@ static int tg3_phy_init(struct tg3 *tp) tp->phy_flags |= TG3_PHYFLG_IS_CONNECTED; - phydev->advertising = phydev->supported; - phy_attached_info(phydev); return 0; @@ -5215,7 +5211,7 @@ static int tg3_fiber_aneg_smachine(struct tg3 *tp, if (ap->flags & (MR_AN_ENABLE | MR_RESTART_AN)) ap->state = ANEG_STATE_AN_ENABLE; - /* fallthru */ + /* fall through */ case ANEG_STATE_AN_ENABLE: ap->flags &= ~(MR_AN_COMPLETE | MR_PAGE_RX); if (ap->flags & MR_AN_ENABLE) { @@ -5245,7 +5241,7 @@ static int tg3_fiber_aneg_smachine(struct tg3 *tp, ret = ANEG_TIMER_ENAB; ap->state = ANEG_STATE_RESTART; - /* fallthru */ + /* fall through */ case ANEG_STATE_RESTART: delta = ap->cur_time - ap->link_time; if (delta > ANEG_STATE_SETTLE_TIME) @@ -5288,7 +5284,7 @@ static int tg3_fiber_aneg_smachine(struct tg3 *tp, ap->state = ANEG_STATE_ACK_DETECT; - /* fallthru */ + /* fall through */ case ANEG_STATE_ACK_DETECT: if (ap->ack_match != 0) { if ((ap->rxconfig & ~ANEG_CFG_ACK) == @@ -12496,31 +12492,24 @@ static int tg3_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam tg3_warn_mgmt_link_flap(tp); if (tg3_flag(tp, USE_PHYLIB)) { - u32 newadv; struct phy_device *phydev; phydev = mdiobus_get_phy(tp->mdio_bus, tp->phy_addr); - if (!(phydev->supported & SUPPORTED_Pause) || - (!(phydev->supported & SUPPORTED_Asym_Pause) && - (epause->rx_pause != epause->tx_pause))) + if (!phy_validate_pause(phydev, epause)) return -EINVAL; tp->link_config.flowctrl = 0; + phy_set_asym_pause(phydev, epause->rx_pause, epause->tx_pause); if (epause->rx_pause) { tp->link_config.flowctrl |= FLOW_CTRL_RX; if (epause->tx_pause) { tp->link_config.flowctrl |= FLOW_CTRL_TX; - newadv = ADVERTISED_Pause; - } else - newadv = ADVERTISED_Pause | - ADVERTISED_Asym_Pause; + } } else if (epause->tx_pause) { tp->link_config.flowctrl |= FLOW_CTRL_TX; - newadv = ADVERTISED_Asym_Pause; - } else - newadv = 0; + } if (epause->autoneg) tg3_flag_set(tp, PAUSE_AUTONEG); @@ -12528,33 +12517,19 @@ static int tg3_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam tg3_flag_clear(tp, PAUSE_AUTONEG); if (tp->phy_flags & TG3_PHYFLG_IS_CONNECTED) { - u32 oldadv = phydev->advertising & - (ADVERTISED_Pause | ADVERTISED_Asym_Pause); - if (oldadv != newadv) { - phydev->advertising &= - ~(ADVERTISED_Pause | - ADVERTISED_Asym_Pause); - phydev->advertising |= newadv; - if (phydev->autoneg) { - /* - * Always renegotiate the link to - * inform our link partner of our - * flow control settings, even if the - * flow control is forced. Let - * tg3_adjust_link() do the final - * flow control setup. - */ - return phy_start_aneg(phydev); - } + if (phydev->autoneg) { + /* phy_set_asym_pause() will + * renegotiate the link to inform our + * link partner of our flow control + * settings, even if the flow control + * is forced. Let tg3_adjust_link() + * do the final flow control setup. + */ + return 0; } if (!epause->autoneg) tg3_setup_flow_control(tp, 0, 0); - } else { - tp->link_config.advertising &= - ~(ADVERTISED_Pause | - ADVERTISED_Asym_Pause); - tp->link_config.advertising |= newadv; } } else { int irq_sync = 0; @@ -14013,7 +13988,7 @@ static int tg3_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCGMIIPHY: data->phy_id = tp->phy_addr; - /* fallthru */ + /* fall through */ case SIOCGMIIREG: { u32 mii_regval; diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index dc09f9a8a49b..7fddf76e6ead 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -482,11 +482,6 @@ static int macb_mii_probe(struct net_device *dev) if (np) { if (of_phy_is_fixed_link(np)) { - if (of_phy_register_fixed_link(np) < 0) { - dev_err(&bp->pdev->dev, - "broken fixed-link specification\n"); - return -ENODEV; - } bp->phy_node = of_node_get(np); } else { bp->phy_node = of_parse_phandle(np, "phy-handle", 0); @@ -549,14 +544,13 @@ static int macb_mii_probe(struct net_device *dev) /* mask with MAC supported features */ if (macb_is_gem(bp) && bp->caps & MACB_CAPS_GIGABIT_MODE_AVAILABLE) - phydev->supported &= PHY_GBIT_FEATURES; + phy_set_max_speed(phydev, SPEED_1000); else - phydev->supported &= PHY_BASIC_FEATURES; + phy_set_max_speed(phydev, SPEED_100); if (bp->caps & MACB_CAPS_NO_GIGABIT_HALF) - phydev->supported &= ~SUPPORTED_1000baseT_Half; - - phydev->advertising = phydev->supported; + phy_remove_link_mode(phydev, + ETHTOOL_LINK_MODE_1000baseT_Half_BIT); bp->link = 0; bp->speed = 0; @@ -569,7 +563,7 @@ static int macb_mii_init(struct macb *bp) { struct macb_platform_data *pdata; struct device_node *np; - int err; + int err = -ENXIO; /* Enable management port */ macb_writel(bp, NCR, MACB_BIT(MPE)); @@ -592,12 +586,23 @@ static int macb_mii_init(struct macb *bp) dev_set_drvdata(&bp->dev->dev, bp->mii_bus); np = bp->pdev->dev.of_node; - if (pdata) - bp->mii_bus->phy_mask = pdata->phy_mask; + if (np && of_phy_is_fixed_link(np)) { + if (of_phy_register_fixed_link(np) < 0) { + dev_err(&bp->pdev->dev, + "broken fixed-link specification %pOF\n", np); + goto err_out_free_mdiobus; + } + + err = mdiobus_register(bp->mii_bus); + } else { + if (pdata) + bp->mii_bus->phy_mask = pdata->phy_mask; + + err = of_mdiobus_register(bp->mii_bus, np); + } - err = of_mdiobus_register(bp->mii_bus, np); if (err) - goto err_out_free_mdiobus; + goto err_out_free_fixed_link; err = macb_mii_probe(bp->dev); if (err) @@ -607,6 +612,7 @@ static int macb_mii_init(struct macb *bp) err_out_unregister_bus: mdiobus_unregister(bp->mii_bus); +err_out_free_fixed_link: if (np && of_phy_is_fixed_link(np)) of_phy_deregister_fixed_link(np); err_out_free_mdiobus: @@ -642,7 +648,7 @@ static int macb_halt_tx(struct macb *bp) if (!(status & MACB_BIT(TGO))) return 0; - usleep_range(10, 250); + udelay(250); } while (time_before(halt_time, timeout)); return -ETIMEDOUT; @@ -2028,14 +2034,17 @@ static void macb_reset_hw(struct macb *bp) { struct macb_queue *queue; unsigned int q; + u32 ctrl = macb_readl(bp, NCR); /* Disable RX and TX (XXX: Should we halt the transmission * more gracefully?) */ - macb_writel(bp, NCR, 0); + ctrl &= ~(MACB_BIT(RE) | MACB_BIT(TE)); /* Clear the stats registers (XXX: Update stats first?) */ - macb_writel(bp, NCR, MACB_BIT(CLRSTAT)); + ctrl |= MACB_BIT(CLRSTAT); + + macb_writel(bp, NCR, ctrl); /* Clear all status flags */ macb_writel(bp, TSR, -1); @@ -2223,7 +2232,7 @@ static void macb_init_hw(struct macb *bp) } /* Enable TX and RX */ - macb_writel(bp, NCR, MACB_BIT(RE) | MACB_BIT(TE) | MACB_BIT(MPE)); + macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(RE) | MACB_BIT(TE)); } /* The hash address register is 64 bits long and takes up two @@ -3827,6 +3836,13 @@ static const struct macb_config at91sam9260_config = { .init = macb_init, }; +static const struct macb_config sama5d3macb_config = { + .caps = MACB_CAPS_SG_DISABLED + | MACB_CAPS_USRIO_HAS_CLKEN | MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII, + .clk_init = macb_clk_init, + .init = macb_init, +}; + static const struct macb_config pc302gem_config = { .caps = MACB_CAPS_SG_DISABLED | MACB_CAPS_GIGABIT_MODE_AVAILABLE, .dma_burst_length = 16, @@ -3894,6 +3910,7 @@ static const struct of_device_id macb_dt_ids[] = { { .compatible = "cdns,gem", .data = &pc302gem_config }, { .compatible = "atmel,sama5d2-gem", .data = &sama5d2_config }, { .compatible = "atmel,sama5d3-gem", .data = &sama5d3_config }, + { .compatible = "atmel,sama5d3-macb", .data = &sama5d3macb_config }, { .compatible = "atmel,sama5d4-gem", .data = &sama5d4_config }, { .compatible = "cdns,at91rm9200-emac", .data = &emac_config }, { .compatible = "cdns,emac", .data = &emac_config }, diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c index 962bb62933db..fda49404968c 100644 --- a/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c +++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c @@ -616,7 +616,7 @@ static void cn23xx_disable_vf_interrupt(struct octeon_device *oct, u8 intr_flag) int cn23xx_setup_octeon_vf_device(struct octeon_device *oct) { struct octeon_cn23xx_vf *cn23xx = (struct octeon_cn23xx_vf *)oct->chip; - u32 rings_per_vf, ring_flag; + u32 rings_per_vf; u64 reg_val; if (octeon_map_pci_barx(oct, 0, 0)) @@ -634,8 +634,6 @@ int cn23xx_setup_octeon_vf_device(struct octeon_device *oct) rings_per_vf = reg_val & CN23XX_PKT_INPUT_CTL_RPVF_MASK; - ring_flag = 0; - cn23xx->conf = oct_get_config_info(oct, LIO_23XX); if (!cn23xx->conf) { dev_err(&oct->pci_dev->dev, "%s No Config found for CN23XX\n", diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c index 8093c5eafea2..eb96b0613cf6 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_core.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c @@ -32,38 +32,6 @@ #define OCTNIC_MAX_SG MAX_SKB_FRAGS /** - * \brief Callback for getting interface configuration - * @param status status of request - * @param buf pointer to resp structure - */ -void lio_if_cfg_callback(struct octeon_device *oct, - u32 status __attribute__((unused)), void *buf) -{ - struct octeon_soft_command *sc = (struct octeon_soft_command *)buf; - struct liquidio_if_cfg_context *ctx; - struct liquidio_if_cfg_resp *resp; - - resp = (struct liquidio_if_cfg_resp *)sc->virtrptr; - ctx = (struct liquidio_if_cfg_context *)sc->ctxptr; - - oct = lio_get_device(ctx->octeon_id); - if (resp->status) - dev_err(&oct->pci_dev->dev, "nic if cfg instruction failed. Status: %llx\n", - CVM_CAST64(resp->status)); - WRITE_ONCE(ctx->cond, 1); - - snprintf(oct->fw_info.liquidio_firmware_version, 32, "%s", - resp->cfg_info.liquidio_firmware_version); - - /* This barrier is required to be sure that the response has been - * written fully before waking up the handler - */ - wmb(); - - wake_up_interruptible(&ctx->wc); -} - -/** * \brief Delete gather lists * @param lio per-network private data */ @@ -198,14 +166,15 @@ int liquidio_set_feature(struct net_device *netdev, int cmd, u16 param1) nctrl.ncmd.s.cmd = cmd; nctrl.ncmd.s.param1 = param1; nctrl.iq_no = lio->linfo.txpciq[0].s.q_no; - nctrl.wait_time = 100; nctrl.netpndev = (u64)netdev; nctrl.cb_fn = liquidio_link_ctrl_cmd_completion; ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl); - if (ret < 0) { + if (ret) { dev_err(&oct->pci_dev->dev, "Feature change failed in core (ret: 0x%x)\n", ret); + if (ret > 0) + ret = -EIO; } return ret; } @@ -285,15 +254,7 @@ void liquidio_link_ctrl_cmd_completion(void *nctrl_ptr) struct octeon_device *oct = lio->oct_dev; u8 *mac; - if (nctrl->completion && nctrl->response_code) { - /* Signal whoever is interested that the response code from the - * firmware has arrived. - */ - WRITE_ONCE(*nctrl->response_code, nctrl->status); - complete(nctrl->completion); - } - - if (nctrl->status) + if (nctrl->sc_status) return; switch (nctrl->ncmd.s.cmd) { @@ -464,56 +425,73 @@ void octeon_pf_changed_vf_macaddr(struct octeon_device *oct, u8 *mac) */ } +void octeon_schedule_rxq_oom_work(struct octeon_device *oct, + struct octeon_droq *droq) +{ + struct net_device *netdev = oct->props[0].netdev; + struct lio *lio = GET_LIO(netdev); + struct cavium_wq *wq = &lio->rxq_status_wq[droq->q_no]; + + queue_delayed_work(wq->wq, &wq->wk.work, + msecs_to_jiffies(LIO_OOM_POLL_INTERVAL_MS)); +} + static void octnet_poll_check_rxq_oom_status(struct work_struct *work) { struct cavium_wk *wk = (struct cavium_wk *)work; struct lio *lio = (struct lio *)wk->ctxptr; struct octeon_device *oct = lio->oct_dev; - struct octeon_droq *droq; - int q, q_no = 0; + int q_no = wk->ctxul; + struct octeon_droq *droq = oct->droq[q_no]; - if (ifstate_check(lio, LIO_IFSTATE_RUNNING)) { - for (q = 0; q < lio->linfo.num_rxpciq; q++) { - q_no = lio->linfo.rxpciq[q].s.q_no; - droq = oct->droq[q_no]; - if (!droq) - continue; - octeon_droq_check_oom(droq); - } - } - queue_delayed_work(lio->rxq_status_wq.wq, - &lio->rxq_status_wq.wk.work, - msecs_to_jiffies(LIO_OOM_POLL_INTERVAL_MS)); + if (!ifstate_check(lio, LIO_IFSTATE_RUNNING) || !droq) + return; + + if (octeon_retry_droq_refill(droq)) + octeon_schedule_rxq_oom_work(oct, droq); } int setup_rx_oom_poll_fn(struct net_device *netdev) { struct lio *lio = GET_LIO(netdev); struct octeon_device *oct = lio->oct_dev; + struct cavium_wq *wq; + int q, q_no; - lio->rxq_status_wq.wq = alloc_workqueue("rxq-oom-status", - WQ_MEM_RECLAIM, 0); - if (!lio->rxq_status_wq.wq) { - dev_err(&oct->pci_dev->dev, "unable to create cavium rxq oom status wq\n"); - return -ENOMEM; + for (q = 0; q < oct->num_oqs; q++) { + q_no = lio->linfo.rxpciq[q].s.q_no; + wq = &lio->rxq_status_wq[q_no]; + wq->wq = alloc_workqueue("rxq-oom-status", + WQ_MEM_RECLAIM, 0); + if (!wq->wq) { + dev_err(&oct->pci_dev->dev, "unable to create cavium rxq oom status wq\n"); + return -ENOMEM; + } + + INIT_DELAYED_WORK(&wq->wk.work, + octnet_poll_check_rxq_oom_status); + wq->wk.ctxptr = lio; + wq->wk.ctxul = q_no; } - INIT_DELAYED_WORK(&lio->rxq_status_wq.wk.work, - octnet_poll_check_rxq_oom_status); - lio->rxq_status_wq.wk.ctxptr = lio; - queue_delayed_work(lio->rxq_status_wq.wq, - &lio->rxq_status_wq.wk.work, - msecs_to_jiffies(LIO_OOM_POLL_INTERVAL_MS)); + return 0; } void cleanup_rx_oom_poll_fn(struct net_device *netdev) { struct lio *lio = GET_LIO(netdev); - - if (lio->rxq_status_wq.wq) { - cancel_delayed_work_sync(&lio->rxq_status_wq.wk.work); - flush_workqueue(lio->rxq_status_wq.wq); - destroy_workqueue(lio->rxq_status_wq.wq); + struct octeon_device *oct = lio->oct_dev; + struct cavium_wq *wq; + int q_no; + + for (q_no = 0; q_no < oct->num_oqs; q_no++) { + wq = &lio->rxq_status_wq[q_no]; + if (wq->wq) { + cancel_delayed_work_sync(&wq->wk.work); + flush_workqueue(wq->wq); + destroy_workqueue(wq->wq); + wq->wq = NULL; + } } } @@ -1218,30 +1196,6 @@ int octeon_setup_interrupt(struct octeon_device *oct, u32 num_ioqs) return 0; } -static void liquidio_change_mtu_completion(struct octeon_device *oct, - u32 status, void *buf) -{ - struct octeon_soft_command *sc = (struct octeon_soft_command *)buf; - struct liquidio_if_cfg_context *ctx; - - ctx = (struct liquidio_if_cfg_context *)sc->ctxptr; - - if (status) { - dev_err(&oct->pci_dev->dev, "MTU change failed. Status: %llx\n", - CVM_CAST64(status)); - WRITE_ONCE(ctx->cond, LIO_CHANGE_MTU_FAIL); - } else { - WRITE_ONCE(ctx->cond, LIO_CHANGE_MTU_SUCCESS); - } - - /* This barrier is required to be sure that the response has been - * written fully before waking up the handler - */ - wmb(); - - wake_up_interruptible(&ctx->wc); -} - /** * \brief Net device change_mtu * @param netdev network device @@ -1250,22 +1204,17 @@ int liquidio_change_mtu(struct net_device *netdev, int new_mtu) { struct lio *lio = GET_LIO(netdev); struct octeon_device *oct = lio->oct_dev; - struct liquidio_if_cfg_context *ctx; struct octeon_soft_command *sc; union octnet_cmd *ncmd; - int ctx_size; int ret = 0; - ctx_size = sizeof(struct liquidio_if_cfg_context); sc = (struct octeon_soft_command *) - octeon_alloc_soft_command(oct, OCTNET_CMD_SIZE, 16, ctx_size); + octeon_alloc_soft_command(oct, OCTNET_CMD_SIZE, 16, 0); ncmd = (union octnet_cmd *)sc->virtdptr; - ctx = (struct liquidio_if_cfg_context *)sc->ctxptr; - WRITE_ONCE(ctx->cond, 0); - ctx->octeon_id = lio_get_device_id(oct); - init_waitqueue_head(&ctx->wc); + init_completion(&sc->complete); + sc->sc_status = OCTEON_REQUEST_PENDING; ncmd->u64 = 0; ncmd->s.cmd = OCTNET_CMD_CHANGE_MTU; @@ -1278,28 +1227,28 @@ int liquidio_change_mtu(struct net_device *netdev, int new_mtu) octeon_prepare_soft_command(oct, sc, OPCODE_NIC, OPCODE_NIC_CMD, 0, 0, 0); - sc->callback = liquidio_change_mtu_completion; - sc->callback_arg = sc; - sc->wait_time = 100; - ret = octeon_send_soft_command(oct, sc); if (ret == IQ_SEND_FAILED) { netif_info(lio, rx_err, lio->netdev, "Failed to change MTU\n"); + octeon_free_soft_command(oct, sc); return -EINVAL; } /* Sleep on a wait queue till the cond flag indicates that the * response arrived or timed-out. */ - if (sleep_cond(&ctx->wc, &ctx->cond) == -EINTR || - ctx->cond == LIO_CHANGE_MTU_FAIL) { - octeon_free_soft_command(oct, sc); + ret = wait_for_sc_completion_timeout(oct, sc, 0); + if (ret) + return ret; + + if (sc->sc_status) { + WRITE_ONCE(sc->caller_is_done, true); return -EINVAL; } netdev->mtu = new_mtu; lio->mtu = new_mtu; - octeon_free_soft_command(oct, sc); + WRITE_ONCE(sc->caller_is_done, true); return 0; } @@ -1333,8 +1282,6 @@ octnet_nic_stats_callback(struct octeon_device *oct_dev, struct octeon_soft_command *sc = (struct octeon_soft_command *)ptr; struct oct_nic_stats_resp *resp = (struct oct_nic_stats_resp *)sc->virtrptr; - struct oct_nic_stats_ctrl *ctrl = - (struct oct_nic_stats_ctrl *)sc->ctxptr; struct nic_rx_stats *rsp_rstats = &resp->stats.fromwire; struct nic_tx_stats *rsp_tstats = &resp->stats.fromhost; struct nic_rx_stats *rstats = &oct_dev->link_stats.fromwire; @@ -1422,93 +1369,148 @@ octnet_nic_stats_callback(struct octeon_device *oct_dev, resp->status = 1; } else { + dev_err(&oct_dev->pci_dev->dev, "sc OPCODE_NIC_PORT_STATS command failed\n"); resp->status = -1; } - complete(&ctrl->complete); } -int octnet_get_link_stats(struct net_device *netdev) +static int lio_fetch_vf_stats(struct lio *lio) { - struct lio *lio = GET_LIO(netdev); struct octeon_device *oct_dev = lio->oct_dev; struct octeon_soft_command *sc; - struct oct_nic_stats_ctrl *ctrl; - struct oct_nic_stats_resp *resp; + struct oct_nic_vf_stats_resp *resp; + int retval; /* Alloc soft command */ sc = (struct octeon_soft_command *) octeon_alloc_soft_command(oct_dev, 0, - sizeof(struct oct_nic_stats_resp), - sizeof(struct octnic_ctrl_pkt)); + sizeof(struct oct_nic_vf_stats_resp), + 0); - if (!sc) - return -ENOMEM; + if (!sc) { + dev_err(&oct_dev->pci_dev->dev, "Soft command allocation failed\n"); + retval = -ENOMEM; + goto lio_fetch_vf_stats_exit; + } - resp = (struct oct_nic_stats_resp *)sc->virtrptr; - memset(resp, 0, sizeof(struct oct_nic_stats_resp)); + resp = (struct oct_nic_vf_stats_resp *)sc->virtrptr; + memset(resp, 0, sizeof(struct oct_nic_vf_stats_resp)); - ctrl = (struct oct_nic_stats_ctrl *)sc->ctxptr; - memset(ctrl, 0, sizeof(struct oct_nic_stats_ctrl)); - ctrl->netdev = netdev; - init_completion(&ctrl->complete); + init_completion(&sc->complete); + sc->sc_status = OCTEON_REQUEST_PENDING; sc->iq_no = lio->linfo.txpciq[0].s.q_no; octeon_prepare_soft_command(oct_dev, sc, OPCODE_NIC, - OPCODE_NIC_PORT_STATS, 0, 0, 0); - - sc->callback = octnet_nic_stats_callback; - sc->callback_arg = sc; - sc->wait_time = 500; /*in milli seconds*/ + OPCODE_NIC_VF_PORT_STATS, 0, 0, 0); retval = octeon_send_soft_command(oct_dev, sc); if (retval == IQ_SEND_FAILED) { octeon_free_soft_command(oct_dev, sc); - return -EINVAL; + goto lio_fetch_vf_stats_exit; } - wait_for_completion_timeout(&ctrl->complete, msecs_to_jiffies(1000)); + retval = + wait_for_sc_completion_timeout(oct_dev, sc, + (2 * LIO_SC_MAX_TMO_MS)); + if (retval) { + dev_err(&oct_dev->pci_dev->dev, + "sc OPCODE_NIC_VF_PORT_STATS command failed\n"); + goto lio_fetch_vf_stats_exit; + } - if (resp->status != 1) { - octeon_free_soft_command(oct_dev, sc); + if (sc->sc_status != OCTEON_REQUEST_TIMEOUT && !resp->status) { + octeon_swap_8B_data((u64 *)&resp->spoofmac_cnt, + (sizeof(u64)) >> 3); - return -EINVAL; + if (resp->spoofmac_cnt != 0) { + dev_warn(&oct_dev->pci_dev->dev, + "%llu Spoofed packets detected\n", + resp->spoofmac_cnt); + } } + WRITE_ONCE(sc->caller_is_done, 1); - octeon_free_soft_command(oct_dev, sc); - - return 0; +lio_fetch_vf_stats_exit: + return retval; } -static void liquidio_nic_seapi_ctl_callback(struct octeon_device *oct, - u32 status, - void *buf) +void lio_fetch_stats(struct work_struct *work) { - struct liquidio_nic_seapi_ctl_context *ctx; - struct octeon_soft_command *sc = buf; + struct cavium_wk *wk = (struct cavium_wk *)work; + struct lio *lio = wk->ctxptr; + struct octeon_device *oct_dev = lio->oct_dev; + struct octeon_soft_command *sc; + struct oct_nic_stats_resp *resp; + unsigned long time_in_jiffies; + int retval; + + if (OCTEON_CN23XX_PF(oct_dev)) { + /* report spoofchk every 2 seconds */ + if (!(oct_dev->vfstats_poll % LIO_VFSTATS_POLL) && + (oct_dev->fw_info.app_cap_flags & LIQUIDIO_SPOOFCHK_CAP) && + oct_dev->sriov_info.num_vfs_alloced) { + lio_fetch_vf_stats(lio); + } - ctx = sc->ctxptr; + oct_dev->vfstats_poll++; + } + + /* Alloc soft command */ + sc = (struct octeon_soft_command *) + octeon_alloc_soft_command(oct_dev, + 0, + sizeof(struct oct_nic_stats_resp), + 0); + + if (!sc) { + dev_err(&oct_dev->pci_dev->dev, "Soft command allocation failed\n"); + goto lio_fetch_stats_exit; + } + + resp = (struct oct_nic_stats_resp *)sc->virtrptr; + memset(resp, 0, sizeof(struct oct_nic_stats_resp)); + + init_completion(&sc->complete); + sc->sc_status = OCTEON_REQUEST_PENDING; - oct = lio_get_device(ctx->octeon_id); - if (status) { - dev_err(&oct->pci_dev->dev, "%s: instruction failed. Status: %llx\n", - __func__, - CVM_CAST64(status)); + sc->iq_no = lio->linfo.txpciq[0].s.q_no; + + octeon_prepare_soft_command(oct_dev, sc, OPCODE_NIC, + OPCODE_NIC_PORT_STATS, 0, 0, 0); + + retval = octeon_send_soft_command(oct_dev, sc); + if (retval == IQ_SEND_FAILED) { + octeon_free_soft_command(oct_dev, sc); + goto lio_fetch_stats_exit; + } + + retval = wait_for_sc_completion_timeout(oct_dev, sc, + (2 * LIO_SC_MAX_TMO_MS)); + if (retval) { + dev_err(&oct_dev->pci_dev->dev, "sc OPCODE_NIC_PORT_STATS command failed\n"); + goto lio_fetch_stats_exit; } - ctx->status = status; - complete(&ctx->complete); + + octnet_nic_stats_callback(oct_dev, sc->sc_status, sc); + WRITE_ONCE(sc->caller_is_done, true); + +lio_fetch_stats_exit: + time_in_jiffies = msecs_to_jiffies(LIQUIDIO_NDEV_STATS_POLL_TIME_MS); + if (ifstate_check(lio, LIO_IFSTATE_RUNNING)) + schedule_delayed_work(&lio->stats_wk.work, time_in_jiffies); + + return; } int liquidio_set_speed(struct lio *lio, int speed) { - struct liquidio_nic_seapi_ctl_context *ctx; struct octeon_device *oct = lio->oct_dev; struct oct_nic_seapi_resp *resp; struct octeon_soft_command *sc; union octnet_cmd *ncmd; - u32 ctx_size; int retval; u32 var; @@ -1521,21 +1523,18 @@ int liquidio_set_speed(struct lio *lio, int speed) return -EOPNOTSUPP; } - ctx_size = sizeof(struct liquidio_nic_seapi_ctl_context); sc = octeon_alloc_soft_command(oct, OCTNET_CMD_SIZE, sizeof(struct oct_nic_seapi_resp), - ctx_size); + 0); if (!sc) return -ENOMEM; ncmd = sc->virtdptr; - ctx = sc->ctxptr; resp = sc->virtrptr; memset(resp, 0, sizeof(struct oct_nic_seapi_resp)); - ctx->octeon_id = lio_get_device_id(oct); - ctx->status = 0; - init_completion(&ctx->complete); + init_completion(&sc->complete); + sc->sc_status = OCTEON_REQUEST_PENDING; ncmd->u64 = 0; ncmd->s.cmd = SEAPI_CMD_SPEED_SET; @@ -1548,30 +1547,24 @@ int liquidio_set_speed(struct lio *lio, int speed) octeon_prepare_soft_command(oct, sc, OPCODE_NIC, OPCODE_NIC_UBOOT_CTL, 0, 0, 0); - sc->callback = liquidio_nic_seapi_ctl_callback; - sc->callback_arg = sc; - sc->wait_time = 5000; - retval = octeon_send_soft_command(oct, sc); if (retval == IQ_SEND_FAILED) { dev_info(&oct->pci_dev->dev, "Failed to send soft command\n"); + octeon_free_soft_command(oct, sc); retval = -EBUSY; } else { /* Wait for response or timeout */ - if (wait_for_completion_timeout(&ctx->complete, - msecs_to_jiffies(10000)) == 0) { - dev_err(&oct->pci_dev->dev, "%s: sc timeout\n", - __func__); - octeon_free_soft_command(oct, sc); - return -EINTR; - } + retval = wait_for_sc_completion_timeout(oct, sc, 0); + if (retval) + return retval; retval = resp->status; if (retval) { dev_err(&oct->pci_dev->dev, "%s failed, retval=%d\n", __func__, retval); - octeon_free_soft_command(oct, sc); + WRITE_ONCE(sc->caller_is_done, true); + return -EIO; } @@ -1583,38 +1576,32 @@ int liquidio_set_speed(struct lio *lio, int speed) } oct->speed_setting = var; + WRITE_ONCE(sc->caller_is_done, true); } - octeon_free_soft_command(oct, sc); - return retval; } int liquidio_get_speed(struct lio *lio) { - struct liquidio_nic_seapi_ctl_context *ctx; struct octeon_device *oct = lio->oct_dev; struct oct_nic_seapi_resp *resp; struct octeon_soft_command *sc; union octnet_cmd *ncmd; - u32 ctx_size; int retval; - ctx_size = sizeof(struct liquidio_nic_seapi_ctl_context); sc = octeon_alloc_soft_command(oct, OCTNET_CMD_SIZE, sizeof(struct oct_nic_seapi_resp), - ctx_size); + 0); if (!sc) return -ENOMEM; ncmd = sc->virtdptr; - ctx = sc->ctxptr; resp = sc->virtrptr; memset(resp, 0, sizeof(struct oct_nic_seapi_resp)); - ctx->octeon_id = lio_get_device_id(oct); - ctx->status = 0; - init_completion(&ctx->complete); + init_completion(&sc->complete); + sc->sc_status = OCTEON_REQUEST_PENDING; ncmd->u64 = 0; ncmd->s.cmd = SEAPI_CMD_SPEED_GET; @@ -1626,37 +1613,20 @@ int liquidio_get_speed(struct lio *lio) octeon_prepare_soft_command(oct, sc, OPCODE_NIC, OPCODE_NIC_UBOOT_CTL, 0, 0, 0); - sc->callback = liquidio_nic_seapi_ctl_callback; - sc->callback_arg = sc; - sc->wait_time = 5000; - retval = octeon_send_soft_command(oct, sc); if (retval == IQ_SEND_FAILED) { dev_info(&oct->pci_dev->dev, "Failed to send soft command\n"); - oct->no_speed_setting = 1; - oct->speed_setting = 25; - - retval = -EBUSY; + octeon_free_soft_command(oct, sc); + retval = -EIO; } else { - if (wait_for_completion_timeout(&ctx->complete, - msecs_to_jiffies(10000)) == 0) { - dev_err(&oct->pci_dev->dev, "%s: sc timeout\n", - __func__); - - oct->speed_setting = 25; - oct->no_speed_setting = 1; - - octeon_free_soft_command(oct, sc); + retval = wait_for_sc_completion_timeout(oct, sc, 0); + if (retval) + return retval; - return -EINTR; - } retval = resp->status; if (retval) { dev_err(&oct->pci_dev->dev, "%s failed retval=%d\n", __func__, retval); - oct->no_speed_setting = 1; - oct->speed_setting = 25; - octeon_free_soft_command(oct, sc); retval = -EIO; } else { u32 var; @@ -1664,16 +1634,171 @@ int liquidio_get_speed(struct lio *lio) var = be32_to_cpu((__force __be32)resp->speed); oct->speed_setting = var; if (var == 0xffff) { - oct->no_speed_setting = 1; /* unable to access boot variables * get the default value based on the NIC type */ - oct->speed_setting = 25; + if (oct->subsystem_id == + OCTEON_CN2350_25GB_SUBSYS_ID || + oct->subsystem_id == + OCTEON_CN2360_25GB_SUBSYS_ID) { + oct->no_speed_setting = 1; + oct->speed_setting = 25; + } else { + oct->speed_setting = 10; + } } + } + WRITE_ONCE(sc->caller_is_done, true); + } + + return retval; +} + +int liquidio_set_fec(struct lio *lio, int on_off) +{ + struct oct_nic_seapi_resp *resp; + struct octeon_soft_command *sc; + struct octeon_device *oct; + union octnet_cmd *ncmd; + int retval; + u32 var; + + oct = lio->oct_dev; + + if (oct->props[lio->ifidx].fec == on_off) + return 0; + + if (!OCTEON_CN23XX_PF(oct)) { + dev_err(&oct->pci_dev->dev, "%s: SET FEC only for PF\n", + __func__); + return -1; + } + + if (oct->speed_boot != 25) { + dev_err(&oct->pci_dev->dev, + "Set FEC only when link speed is 25G during insmod\n"); + return -1; + } + + sc = octeon_alloc_soft_command(oct, OCTNET_CMD_SIZE, + sizeof(struct oct_nic_seapi_resp), 0); + + ncmd = sc->virtdptr; + resp = sc->virtrptr; + memset(resp, 0, sizeof(struct oct_nic_seapi_resp)); + + init_completion(&sc->complete); + sc->sc_status = OCTEON_REQUEST_PENDING; + + ncmd->u64 = 0; + ncmd->s.cmd = SEAPI_CMD_FEC_SET; + ncmd->s.param1 = on_off; + /* SEAPI_CMD_FEC_DISABLE(0) or SEAPI_CMD_FEC_RS(1) */ + + octeon_swap_8B_data((u64 *)ncmd, (OCTNET_CMD_SIZE >> 3)); + + sc->iq_no = lio->linfo.txpciq[0].s.q_no; + + octeon_prepare_soft_command(oct, sc, OPCODE_NIC, + OPCODE_NIC_UBOOT_CTL, 0, 0, 0); + + retval = octeon_send_soft_command(oct, sc); + if (retval == IQ_SEND_FAILED) { + dev_info(&oct->pci_dev->dev, "Failed to send soft command\n"); + octeon_free_soft_command(oct, sc); + return -EIO; + } + + retval = wait_for_sc_completion_timeout(oct, sc, 0); + if (retval) + return (-EIO); + + var = be32_to_cpu(resp->fec_setting); + resp->fec_setting = var; + if (var != on_off) { + dev_err(&oct->pci_dev->dev, + "Setting failed fec= %x, expect %x\n", + var, on_off); + oct->props[lio->ifidx].fec = var; + if (resp->fec_setting == SEAPI_CMD_FEC_SET_RS) + oct->props[lio->ifidx].fec = 1; + else + oct->props[lio->ifidx].fec = 0; + } + + WRITE_ONCE(sc->caller_is_done, true); + + if (oct->props[lio->ifidx].fec != + oct->props[lio->ifidx].fec_boot) { + dev_dbg(&oct->pci_dev->dev, + "Reloade driver to chang fec to %s\n", + oct->props[lio->ifidx].fec ? "on" : "off"); + } + + return retval; +} + +int liquidio_get_fec(struct lio *lio) +{ + struct oct_nic_seapi_resp *resp; + struct octeon_soft_command *sc; + struct octeon_device *oct; + union octnet_cmd *ncmd; + int retval; + u32 var; + + oct = lio->oct_dev; + + sc = octeon_alloc_soft_command(oct, OCTNET_CMD_SIZE, + sizeof(struct oct_nic_seapi_resp), 0); + if (!sc) + return -ENOMEM; + + ncmd = sc->virtdptr; + resp = sc->virtrptr; + memset(resp, 0, sizeof(struct oct_nic_seapi_resp)); + + init_completion(&sc->complete); + sc->sc_status = OCTEON_REQUEST_PENDING; + + ncmd->u64 = 0; + ncmd->s.cmd = SEAPI_CMD_FEC_GET; + + octeon_swap_8B_data((u64 *)ncmd, (OCTNET_CMD_SIZE >> 3)); + + sc->iq_no = lio->linfo.txpciq[0].s.q_no; + + octeon_prepare_soft_command(oct, sc, OPCODE_NIC, + OPCODE_NIC_UBOOT_CTL, 0, 0, 0); + + retval = octeon_send_soft_command(oct, sc); + if (retval == IQ_SEND_FAILED) { + dev_info(&oct->pci_dev->dev, + "%s: Failed to send soft command\n", __func__); + octeon_free_soft_command(oct, sc); + return -EIO; } - octeon_free_soft_command(oct, sc); + retval = wait_for_sc_completion_timeout(oct, sc, 0); + if (retval) + return retval; + + var = be32_to_cpu(resp->fec_setting); + resp->fec_setting = var; + if (resp->fec_setting == SEAPI_CMD_FEC_SET_RS) + oct->props[lio->ifidx].fec = 1; + else + oct->props[lio->ifidx].fec = 0; + + WRITE_ONCE(sc->caller_is_done, true); + + if (oct->props[lio->ifidx].fec != + oct->props[lio->ifidx].fec_boot) { + dev_dbg(&oct->pci_dev->dev, + "Reloade driver to chang fec to %s\n", + oct->props[lio->ifidx].fec ? "on" : "off"); + } return retval; } diff --git a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c index 8e05afd5e39c..4c3925af53bc 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c @@ -33,25 +33,12 @@ static int lio_reset_queues(struct net_device *netdev, uint32_t num_qs); -struct oct_intrmod_context { - int octeon_id; - wait_queue_head_t wc; - int cond; - int status; -}; - struct oct_intrmod_resp { u64 rh; struct oct_intrmod_cfg intrmod; u64 status; }; -struct oct_mdio_cmd_context { - int octeon_id; - wait_queue_head_t wc; - int cond; -}; - struct oct_mdio_cmd_resp { u64 rh; struct oct_mdio_cmd resp; @@ -257,6 +244,7 @@ static int lio_get_link_ksettings(struct net_device *netdev, linfo->link.s.if_mode == INTERFACE_MODE_XLAUI || linfo->link.s.if_mode == INTERFACE_MODE_XFI) { dev_dbg(&oct->pci_dev->dev, "ecmd->base.transceiver is XCVR_EXTERNAL\n"); + ecmd->base.transceiver = XCVR_EXTERNAL; } else { dev_err(&oct->pci_dev->dev, "Unknown link interface mode: %d\n", linfo->link.s.if_mode); @@ -290,10 +278,12 @@ static int lio_get_link_ksettings(struct net_device *netdev, 10000baseCR_Full); } - if (oct->no_speed_setting == 0) + if (oct->no_speed_setting == 0) { liquidio_get_speed(lio); - else + liquidio_get_fec(lio); + } else { oct->speed_setting = 25; + } if (oct->speed_setting == 10) { ethtool_link_ksettings_add_link_mode @@ -317,6 +307,24 @@ static int lio_get_link_ksettings(struct net_device *netdev, (ecmd, advertising, 25000baseCR_Full); } + + if (oct->no_speed_setting) + break; + + ethtool_link_ksettings_add_link_mode + (ecmd, supported, FEC_RS); + ethtool_link_ksettings_add_link_mode + (ecmd, supported, FEC_NONE); + /*FEC_OFF*/ + if (oct->props[lio->ifidx].fec == 1) { + /* ETHTOOL_FEC_RS */ + ethtool_link_ksettings_add_link_mode + (ecmd, advertising, FEC_RS); + } else { + /* ETHTOOL_FEC_OFF */ + ethtool_link_ksettings_add_link_mode + (ecmd, advertising, FEC_NONE); + } } else { /* VF */ if (linfo->link.s.speed == 10000) { ethtool_link_ksettings_add_link_mode @@ -472,12 +480,11 @@ lio_send_queue_count_update(struct net_device *netdev, uint32_t num_queues) nctrl.ncmd.s.param1 = num_queues; nctrl.ncmd.s.param2 = num_queues; nctrl.iq_no = lio->linfo.txpciq[0].s.q_no; - nctrl.wait_time = 100; nctrl.netpndev = (u64)netdev; nctrl.cb_fn = liquidio_link_ctrl_cmd_completion; ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl); - if (ret < 0) { + if (ret) { dev_err(&oct->pci_dev->dev, "Failed to send Queue reset command (ret: 0x%x)\n", ret); return -1; @@ -708,13 +715,13 @@ static int octnet_gpio_access(struct net_device *netdev, int addr, int val) nctrl.ncmd.s.param1 = addr; nctrl.ncmd.s.param2 = val; nctrl.iq_no = lio->linfo.txpciq[0].s.q_no; - nctrl.wait_time = 100; nctrl.netpndev = (u64)netdev; nctrl.cb_fn = liquidio_link_ctrl_cmd_completion; ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl); - if (ret < 0) { - dev_err(&oct->pci_dev->dev, "Failed to configure gpio value\n"); + if (ret) { + dev_err(&oct->pci_dev->dev, + "Failed to configure gpio value, ret=%d\n", ret); return -EINVAL; } @@ -734,41 +741,19 @@ static int octnet_id_active(struct net_device *netdev, int val) nctrl.ncmd.s.cmd = OCTNET_CMD_ID_ACTIVE; nctrl.ncmd.s.param1 = val; nctrl.iq_no = lio->linfo.txpciq[0].s.q_no; - nctrl.wait_time = 100; nctrl.netpndev = (u64)netdev; nctrl.cb_fn = liquidio_link_ctrl_cmd_completion; ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl); - if (ret < 0) { - dev_err(&oct->pci_dev->dev, "Failed to configure gpio value\n"); + if (ret) { + dev_err(&oct->pci_dev->dev, + "Failed to configure gpio value, ret=%d\n", ret); return -EINVAL; } return 0; } -/* Callback for when mdio command response arrives - */ -static void octnet_mdio_resp_callback(struct octeon_device *oct, - u32 status, - void *buf) -{ - struct oct_mdio_cmd_context *mdio_cmd_ctx; - struct octeon_soft_command *sc = (struct octeon_soft_command *)buf; - - mdio_cmd_ctx = (struct oct_mdio_cmd_context *)sc->ctxptr; - - oct = lio_get_device(mdio_cmd_ctx->octeon_id); - if (status) { - dev_err(&oct->pci_dev->dev, "MIDO instruction failed. Status: %llx\n", - CVM_CAST64(status)); - WRITE_ONCE(mdio_cmd_ctx->cond, -1); - } else { - WRITE_ONCE(mdio_cmd_ctx->cond, 1); - } - wake_up_interruptible(&mdio_cmd_ctx->wc); -} - /* This routine provides PHY access routines for * mdio clause45 . */ @@ -778,25 +763,20 @@ octnet_mdio45_access(struct lio *lio, int op, int loc, int *value) struct octeon_device *oct_dev = lio->oct_dev; struct octeon_soft_command *sc; struct oct_mdio_cmd_resp *mdio_cmd_rsp; - struct oct_mdio_cmd_context *mdio_cmd_ctx; struct oct_mdio_cmd *mdio_cmd; int retval = 0; sc = (struct octeon_soft_command *) octeon_alloc_soft_command(oct_dev, sizeof(struct oct_mdio_cmd), - sizeof(struct oct_mdio_cmd_resp), - sizeof(struct oct_mdio_cmd_context)); + sizeof(struct oct_mdio_cmd_resp), 0); if (!sc) return -ENOMEM; - mdio_cmd_ctx = (struct oct_mdio_cmd_context *)sc->ctxptr; mdio_cmd_rsp = (struct oct_mdio_cmd_resp *)sc->virtrptr; mdio_cmd = (struct oct_mdio_cmd *)sc->virtdptr; - WRITE_ONCE(mdio_cmd_ctx->cond, 0); - mdio_cmd_ctx->octeon_id = lio_get_device_id(oct_dev); mdio_cmd->op = op; mdio_cmd->mdio_addr = loc; if (op) @@ -808,42 +788,40 @@ octnet_mdio45_access(struct lio *lio, int op, int loc, int *value) octeon_prepare_soft_command(oct_dev, sc, OPCODE_NIC, OPCODE_NIC_MDIO45, 0, 0, 0); - sc->wait_time = 1000; - sc->callback = octnet_mdio_resp_callback; - sc->callback_arg = sc; - - init_waitqueue_head(&mdio_cmd_ctx->wc); + init_completion(&sc->complete); + sc->sc_status = OCTEON_REQUEST_PENDING; retval = octeon_send_soft_command(oct_dev, sc); - if (retval == IQ_SEND_FAILED) { dev_err(&oct_dev->pci_dev->dev, "octnet_mdio45_access instruction failed status: %x\n", retval); - retval = -EBUSY; + octeon_free_soft_command(oct_dev, sc); + return -EBUSY; } else { /* Sleep on a wait queue till the cond flag indicates that the * response arrived */ - sleep_cond(&mdio_cmd_ctx->wc, &mdio_cmd_ctx->cond); + retval = wait_for_sc_completion_timeout(oct_dev, sc, 0); + if (retval) + return retval; + retval = mdio_cmd_rsp->status; if (retval) { - dev_err(&oct_dev->pci_dev->dev, "octnet mdio45 access failed\n"); - retval = -EBUSY; - } else { - octeon_swap_8B_data((u64 *)(&mdio_cmd_rsp->resp), - sizeof(struct oct_mdio_cmd) / 8); - - if (READ_ONCE(mdio_cmd_ctx->cond) == 1) { - if (!op) - *value = mdio_cmd_rsp->resp.value1; - } else { - retval = -EINVAL; - } + dev_err(&oct_dev->pci_dev->dev, + "octnet mdio45 access failed: %x\n", retval); + WRITE_ONCE(sc->caller_is_done, true); + return -EBUSY; } - } - octeon_free_soft_command(oct_dev, sc); + octeon_swap_8B_data((u64 *)(&mdio_cmd_rsp->resp), + sizeof(struct oct_mdio_cmd) / 8); + + if (!op) + *value = mdio_cmd_rsp->resp.value1; + + WRITE_ONCE(sc->caller_is_done, true); + } return retval; } @@ -1007,8 +985,7 @@ lio_ethtool_get_ringparam(struct net_device *netdev, static int lio_23xx_reconfigure_queue_count(struct lio *lio) { struct octeon_device *oct = lio->oct_dev; - struct liquidio_if_cfg_context *ctx; - u32 resp_size, ctx_size, data_size; + u32 resp_size, data_size; struct liquidio_if_cfg_resp *resp; struct octeon_soft_command *sc; union oct_nic_if_cfg if_cfg; @@ -1018,11 +995,10 @@ static int lio_23xx_reconfigure_queue_count(struct lio *lio) int j; resp_size = sizeof(struct liquidio_if_cfg_resp); - ctx_size = sizeof(struct liquidio_if_cfg_context); data_size = sizeof(struct lio_version); sc = (struct octeon_soft_command *) octeon_alloc_soft_command(oct, data_size, - resp_size, ctx_size); + resp_size, 0); if (!sc) { dev_err(&oct->pci_dev->dev, "%s: Failed to allocate soft command\n", __func__); @@ -1030,7 +1006,6 @@ static int lio_23xx_reconfigure_queue_count(struct lio *lio) } resp = (struct liquidio_if_cfg_resp *)sc->virtrptr; - ctx = (struct liquidio_if_cfg_context *)sc->ctxptr; vdata = (struct lio_version *)sc->virtdptr; vdata->major = (__force u16)cpu_to_be16(LIQUIDIO_BASE_MAJOR_VERSION); @@ -1038,9 +1013,6 @@ static int lio_23xx_reconfigure_queue_count(struct lio *lio) vdata->micro = (__force u16)cpu_to_be16(LIQUIDIO_BASE_MICRO_VERSION); ifidx_or_pfnum = oct->pf_num; - WRITE_ONCE(ctx->cond, 0); - ctx->octeon_id = lio_get_device_id(oct); - init_waitqueue_head(&ctx->wc); if_cfg.u64 = 0; if_cfg.s.num_iqueues = oct->sriov_info.num_pf_rings; @@ -1052,27 +1024,29 @@ static int lio_23xx_reconfigure_queue_count(struct lio *lio) octeon_prepare_soft_command(oct, sc, OPCODE_NIC, OPCODE_NIC_QCOUNT_UPDATE, 0, if_cfg.u64, 0); - sc->callback = lio_if_cfg_callback; - sc->callback_arg = sc; - sc->wait_time = LIO_IFCFG_WAIT_TIME; + + init_completion(&sc->complete); + sc->sc_status = OCTEON_REQUEST_PENDING; retval = octeon_send_soft_command(oct, sc); if (retval == IQ_SEND_FAILED) { dev_err(&oct->pci_dev->dev, - "iq/oq config failed status: %x\n", + "Sending iq/oq config failed status: %x\n", retval); - goto qcount_update_fail; + octeon_free_soft_command(oct, sc); + return -EIO; } - if (sleep_cond(&ctx->wc, &ctx->cond) == -EINTR) { - dev_err(&oct->pci_dev->dev, "Wait interrupted\n"); - return -1; - } + retval = wait_for_sc_completion_timeout(oct, sc, 0); + if (retval) + return retval; retval = resp->status; if (retval) { - dev_err(&oct->pci_dev->dev, "iq/oq config failed\n"); - goto qcount_update_fail; + dev_err(&oct->pci_dev->dev, + "iq/oq config failed: %x\n", retval); + WRITE_ONCE(sc->caller_is_done, true); + return -1; } octeon_swap_8B_data((u64 *)(&resp->cfg_info), @@ -1097,16 +1071,12 @@ static int lio_23xx_reconfigure_queue_count(struct lio *lio) lio->txq = lio->linfo.txpciq[0].s.q_no; lio->rxq = lio->linfo.rxpciq[0].s.q_no; - octeon_free_soft_command(oct, sc); dev_info(&oct->pci_dev->dev, "Queue count updated to %d\n", lio->linfo.num_rxpciq); - return 0; - -qcount_update_fail: - octeon_free_soft_command(oct, sc); + WRITE_ONCE(sc->caller_is_done, true); - return -1; + return 0; } static int lio_reset_queues(struct net_device *netdev, uint32_t num_qs) @@ -1166,6 +1136,8 @@ static int lio_reset_queues(struct net_device *netdev, uint32_t num_qs) * steps like updating sriov_info for the octeon device need to be done. */ if (queue_count_update) { + cleanup_rx_oom_poll_fn(netdev); + lio_delete_glists(lio); /* Delete mbox for PF which is SRIOV disabled because sriov_info @@ -1265,6 +1237,11 @@ static int lio_reset_queues(struct net_device *netdev, uint32_t num_qs) return -1; } + if (setup_rx_oom_poll_fn(netdev)) { + dev_err(&oct->pci_dev->dev, "lio_setup_rx_oom_poll_fn failed\n"); + return 1; + } + /* Send firmware the information about new number of queues * if the interface is a VF or a PF that is SRIOV enabled. */ @@ -1412,7 +1389,6 @@ lio_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause) nctrl.ncmd.u64 = 0; nctrl.ncmd.s.cmd = OCTNET_CMD_SET_FLOW_CTL; nctrl.iq_no = lio->linfo.txpciq[0].s.q_no; - nctrl.wait_time = 100; nctrl.netpndev = (u64)netdev; nctrl.cb_fn = liquidio_link_ctrl_cmd_completion; @@ -1433,8 +1409,9 @@ lio_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause) } ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl); - if (ret < 0) { - dev_err(&oct->pci_dev->dev, "Failed to set pause parameter\n"); + if (ret) { + dev_err(&oct->pci_dev->dev, + "Failed to set pause parameter, ret=%d\n", ret); return -EINVAL; } @@ -1764,7 +1741,8 @@ static void lio_vf_get_ethtool_stats(struct net_device *netdev, */ data[i++] = lstats.rx_dropped; /* sum of oct->instr_queue[iq_no]->stats.tx_dropped */ - data[i++] = lstats.tx_dropped; + data[i++] = lstats.tx_dropped + + oct_dev->link_stats.fromhost.fw_err_drop; data[i++] = oct_dev->link_stats.fromwire.fw_total_mcast; data[i++] = oct_dev->link_stats.fromhost.fw_total_mcast_sent; @@ -2013,34 +1991,11 @@ static int lio_vf_get_sset_count(struct net_device *netdev, int sset) } } -/* Callback function for intrmod */ -static void octnet_intrmod_callback(struct octeon_device *oct_dev, - u32 status, - void *ptr) -{ - struct octeon_soft_command *sc = (struct octeon_soft_command *)ptr; - struct oct_intrmod_context *ctx; - - ctx = (struct oct_intrmod_context *)sc->ctxptr; - - ctx->status = status; - - WRITE_ONCE(ctx->cond, 1); - - /* This barrier is required to be sure that the response has been - * written fully before waking up the handler - */ - wmb(); - - wake_up_interruptible(&ctx->wc); -} - /* get interrupt moderation parameters */ static int octnet_get_intrmod_cfg(struct lio *lio, struct oct_intrmod_cfg *intr_cfg) { struct octeon_soft_command *sc; - struct oct_intrmod_context *ctx; struct oct_intrmod_resp *resp; int retval; struct octeon_device *oct_dev = lio->oct_dev; @@ -2049,8 +2004,7 @@ static int octnet_get_intrmod_cfg(struct lio *lio, sc = (struct octeon_soft_command *) octeon_alloc_soft_command(oct_dev, 0, - sizeof(struct oct_intrmod_resp), - sizeof(struct oct_intrmod_context)); + sizeof(struct oct_intrmod_resp), 0); if (!sc) return -ENOMEM; @@ -2058,20 +2012,13 @@ static int octnet_get_intrmod_cfg(struct lio *lio, resp = (struct oct_intrmod_resp *)sc->virtrptr; memset(resp, 0, sizeof(struct oct_intrmod_resp)); - ctx = (struct oct_intrmod_context *)sc->ctxptr; - memset(ctx, 0, sizeof(struct oct_intrmod_context)); - WRITE_ONCE(ctx->cond, 0); - ctx->octeon_id = lio_get_device_id(oct_dev); - init_waitqueue_head(&ctx->wc); - sc->iq_no = lio->linfo.txpciq[0].s.q_no; octeon_prepare_soft_command(oct_dev, sc, OPCODE_NIC, OPCODE_NIC_INTRMOD_PARAMS, 0, 0, 0); - sc->callback = octnet_intrmod_callback; - sc->callback_arg = sc; - sc->wait_time = 1000; + init_completion(&sc->complete); + sc->sc_status = OCTEON_REQUEST_PENDING; retval = octeon_send_soft_command(oct_dev, sc); if (retval == IQ_SEND_FAILED) { @@ -2082,32 +2029,23 @@ static int octnet_get_intrmod_cfg(struct lio *lio, /* Sleep on a wait queue till the cond flag indicates that the * response arrived or timed-out. */ - if (sleep_cond(&ctx->wc, &ctx->cond) == -EINTR) { - dev_err(&oct_dev->pci_dev->dev, "Wait interrupted\n"); - goto intrmod_info_wait_intr; - } + retval = wait_for_sc_completion_timeout(oct_dev, sc, 0); + if (retval) + return -ENODEV; - retval = ctx->status || resp->status; - if (retval) { + if (resp->status) { dev_err(&oct_dev->pci_dev->dev, "Get interrupt moderation parameters failed\n"); - goto intrmod_info_wait_fail; + WRITE_ONCE(sc->caller_is_done, true); + return -ENODEV; } octeon_swap_8B_data((u64 *)&resp->intrmod, (sizeof(struct oct_intrmod_cfg)) / 8); memcpy(intr_cfg, &resp->intrmod, sizeof(struct oct_intrmod_cfg)); - octeon_free_soft_command(oct_dev, sc); + WRITE_ONCE(sc->caller_is_done, true); return 0; - -intrmod_info_wait_fail: - - octeon_free_soft_command(oct_dev, sc); - -intrmod_info_wait_intr: - - return -ENODEV; } /* Configure interrupt moderation parameters */ @@ -2115,7 +2053,6 @@ static int octnet_set_intrmod_cfg(struct lio *lio, struct oct_intrmod_cfg *intr_cfg) { struct octeon_soft_command *sc; - struct oct_intrmod_context *ctx; struct oct_intrmod_cfg *cfg; int retval; struct octeon_device *oct_dev = lio->oct_dev; @@ -2124,18 +2061,11 @@ static int octnet_set_intrmod_cfg(struct lio *lio, sc = (struct octeon_soft_command *) octeon_alloc_soft_command(oct_dev, sizeof(struct oct_intrmod_cfg), - 0, - sizeof(struct oct_intrmod_context)); + 16, 0); if (!sc) return -ENOMEM; - ctx = (struct oct_intrmod_context *)sc->ctxptr; - - WRITE_ONCE(ctx->cond, 0); - ctx->octeon_id = lio_get_device_id(oct_dev); - init_waitqueue_head(&ctx->wc); - cfg = (struct oct_intrmod_cfg *)sc->virtdptr; memcpy(cfg, intr_cfg, sizeof(struct oct_intrmod_cfg)); @@ -2146,9 +2076,8 @@ static int octnet_set_intrmod_cfg(struct lio *lio, octeon_prepare_soft_command(oct_dev, sc, OPCODE_NIC, OPCODE_NIC_INTRMOD_CFG, 0, 0, 0); - sc->callback = octnet_intrmod_callback; - sc->callback_arg = sc; - sc->wait_time = 1000; + init_completion(&sc->complete); + sc->sc_status = OCTEON_REQUEST_PENDING; retval = octeon_send_soft_command(oct_dev, sc); if (retval == IQ_SEND_FAILED) { @@ -2159,26 +2088,24 @@ static int octnet_set_intrmod_cfg(struct lio *lio, /* Sleep on a wait queue till the cond flag indicates that the * response arrived or timed-out. */ - if (sleep_cond(&ctx->wc, &ctx->cond) != -EINTR) { - retval = ctx->status; - if (retval) - dev_err(&oct_dev->pci_dev->dev, - "intrmod config failed. Status: %llx\n", - CVM_CAST64(retval)); - else - dev_info(&oct_dev->pci_dev->dev, - "Rx-Adaptive Interrupt moderation %s\n", - (intr_cfg->rx_enable) ? - "enabled" : "disabled"); - - octeon_free_soft_command(oct_dev, sc); - - return ((retval) ? -ENODEV : 0); + retval = wait_for_sc_completion_timeout(oct_dev, sc, 0); + if (retval) + return retval; + + retval = sc->sc_status; + if (retval == 0) { + dev_info(&oct_dev->pci_dev->dev, + "Rx-Adaptive Interrupt moderation %s\n", + (intr_cfg->rx_enable) ? + "enabled" : "disabled"); + WRITE_ONCE(sc->caller_is_done, true); + return 0; } - dev_err(&oct_dev->pci_dev->dev, "iq/oq config failed\n"); - - return -EINTR; + dev_err(&oct_dev->pci_dev->dev, + "intrmod config failed. Status: %x\n", retval); + WRITE_ONCE(sc->caller_is_done, true); + return -ENODEV; } static int lio_get_intr_coalesce(struct net_device *netdev, @@ -3123,9 +3050,60 @@ static int lio_set_priv_flags(struct net_device *netdev, u32 flags) return 0; } +static int lio_get_fecparam(struct net_device *netdev, + struct ethtool_fecparam *fec) +{ + struct lio *lio = GET_LIO(netdev); + struct octeon_device *oct = lio->oct_dev; + + fec->active_fec = ETHTOOL_FEC_NONE; + fec->fec = ETHTOOL_FEC_NONE; + + if (oct->subsystem_id == OCTEON_CN2350_25GB_SUBSYS_ID || + oct->subsystem_id == OCTEON_CN2360_25GB_SUBSYS_ID) { + if (oct->no_speed_setting == 1) + return 0; + + liquidio_get_fec(lio); + fec->fec = (ETHTOOL_FEC_RS | ETHTOOL_FEC_OFF); + if (oct->props[lio->ifidx].fec == 1) + fec->active_fec = ETHTOOL_FEC_RS; + else + fec->active_fec = ETHTOOL_FEC_OFF; + } + + return 0; +} + +static int lio_set_fecparam(struct net_device *netdev, + struct ethtool_fecparam *fec) +{ + struct lio *lio = GET_LIO(netdev); + struct octeon_device *oct = lio->oct_dev; + + if (oct->subsystem_id == OCTEON_CN2350_25GB_SUBSYS_ID || + oct->subsystem_id == OCTEON_CN2360_25GB_SUBSYS_ID) { + if (oct->no_speed_setting == 1) + return -EOPNOTSUPP; + + if (fec->fec & ETHTOOL_FEC_OFF) + liquidio_set_fec(lio, 0); + else if (fec->fec & ETHTOOL_FEC_RS) + liquidio_set_fec(lio, 1); + else + return -EOPNOTSUPP; + } else { + return -EOPNOTSUPP; + } + + return 0; +} + static const struct ethtool_ops lio_ethtool_ops = { .get_link_ksettings = lio_get_link_ksettings, .set_link_ksettings = lio_set_link_ksettings, + .get_fecparam = lio_get_fecparam, + .set_fecparam = lio_set_fecparam, .get_link = ethtool_op_get_link, .get_drvinfo = lio_get_drvinfo, .get_ringparam = lio_ethtool_get_ringparam, diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index 6fb13fa73b27..9d70e5c6157f 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -99,14 +99,6 @@ struct lio_trusted_vf_ctx { int status; }; -struct liquidio_rx_ctl_context { - int octeon_id; - - wait_queue_head_t wc; - - int cond; -}; - struct oct_link_status_resp { u64 rh; struct oct_link_info link_info; @@ -642,26 +634,6 @@ static inline void update_link_status(struct net_device *netdev, } /** - * lio_sync_octeon_time_cb - callback that is invoked when soft command - * sent by lio_sync_octeon_time() has completed successfully or failed - * - * @oct - octeon device structure - * @status - indicates success or failure - * @buf - pointer to the command that was sent to firmware - **/ -static void lio_sync_octeon_time_cb(struct octeon_device *oct, - u32 status, void *buf) -{ - struct octeon_soft_command *sc = (struct octeon_soft_command *)buf; - - if (status) - dev_err(&oct->pci_dev->dev, - "Failed to sync time to octeon; error=%d\n", status); - - octeon_free_soft_command(oct, sc); -} - -/** * lio_sync_octeon_time - send latest localtime to octeon firmware so that * firmware will correct it's time, in case there is a time skew * @@ -677,7 +649,7 @@ static void lio_sync_octeon_time(struct work_struct *work) struct lio_time *lt; int ret; - sc = octeon_alloc_soft_command(oct, sizeof(struct lio_time), 0, 0); + sc = octeon_alloc_soft_command(oct, sizeof(struct lio_time), 16, 0); if (!sc) { dev_err(&oct->pci_dev->dev, "Failed to sync time to octeon: soft command allocation failed\n"); @@ -696,15 +668,16 @@ static void lio_sync_octeon_time(struct work_struct *work) octeon_prepare_soft_command(oct, sc, OPCODE_NIC, OPCODE_NIC_SYNC_OCTEON_TIME, 0, 0, 0); - sc->callback = lio_sync_octeon_time_cb; - sc->callback_arg = sc; - sc->wait_time = 1000; + init_completion(&sc->complete); + sc->sc_status = OCTEON_REQUEST_PENDING; ret = octeon_send_soft_command(oct, sc); if (ret == IQ_SEND_FAILED) { dev_err(&oct->pci_dev->dev, "Failed to sync time to octeon: failed to send soft command\n"); octeon_free_soft_command(oct, sc); + } else { + WRITE_ONCE(sc->caller_is_done, true); } queue_delayed_work(lio->sync_octeon_time_wq.wq, @@ -1037,12 +1010,12 @@ static void octeon_destroy_resources(struct octeon_device *oct) /* fallthrough */ case OCT_DEV_IO_QUEUES_DONE: - if (wait_for_pending_requests(oct)) - dev_err(&oct->pci_dev->dev, "There were pending requests\n"); - if (lio_wait_for_instr_fetch(oct)) dev_err(&oct->pci_dev->dev, "IQ had pending instructions\n"); + if (wait_for_pending_requests(oct)) + dev_err(&oct->pci_dev->dev, "There were pending requests\n"); + /* Disable the input and output queues now. No more packets will * arrive from Octeon, but we should wait for all packet * processing to finish. @@ -1052,6 +1025,31 @@ static void octeon_destroy_resources(struct octeon_device *oct) if (lio_wait_for_oq_pkts(oct)) dev_err(&oct->pci_dev->dev, "OQ had pending packets\n"); + /* Force all requests waiting to be fetched by OCTEON to + * complete. + */ + for (i = 0; i < MAX_OCTEON_INSTR_QUEUES(oct); i++) { + struct octeon_instr_queue *iq; + + if (!(oct->io_qmask.iq & BIT_ULL(i))) + continue; + iq = oct->instr_queue[i]; + + if (atomic_read(&iq->instr_pending)) { + spin_lock_bh(&iq->lock); + iq->fill_cnt = 0; + iq->octeon_read_index = iq->host_write_index; + iq->stats.instr_processed += + atomic_read(&iq->instr_pending); + lio_process_iq_request_list(oct, iq, 0); + spin_unlock_bh(&iq->lock); + } + } + + lio_process_ordered_list(oct, 1); + octeon_free_sc_done_list(oct); + octeon_free_sc_zombie_list(oct); + /* fallthrough */ case OCT_DEV_INTR_SET_DONE: /* Disable interrupts */ @@ -1178,34 +1176,6 @@ static void octeon_destroy_resources(struct octeon_device *oct) } /** - * \brief Callback for rx ctrl - * @param status status of request - * @param buf pointer to resp structure - */ -static void rx_ctl_callback(struct octeon_device *oct, - u32 status, - void *buf) -{ - struct octeon_soft_command *sc = (struct octeon_soft_command *)buf; - struct liquidio_rx_ctl_context *ctx; - - ctx = (struct liquidio_rx_ctl_context *)sc->ctxptr; - - oct = lio_get_device(ctx->octeon_id); - if (status) - dev_err(&oct->pci_dev->dev, "rx ctl instruction failed. Status: %llx\n", - CVM_CAST64(status)); - WRITE_ONCE(ctx->cond, 1); - - /* This barrier is required to be sure that the response has been - * written fully before waking up the handler - */ - wmb(); - - wake_up_interruptible(&ctx->wc); -} - -/** * \brief Send Rx control command * @param lio per-network private data * @param start_stop whether to start or stop @@ -1213,9 +1183,7 @@ static void rx_ctl_callback(struct octeon_device *oct, static void send_rx_ctrl_cmd(struct lio *lio, int start_stop) { struct octeon_soft_command *sc; - struct liquidio_rx_ctl_context *ctx; union octnet_cmd *ncmd; - int ctx_size = sizeof(struct liquidio_rx_ctl_context); struct octeon_device *oct = (struct octeon_device *)lio->oct_dev; int retval; @@ -1224,14 +1192,9 @@ static void send_rx_ctrl_cmd(struct lio *lio, int start_stop) sc = (struct octeon_soft_command *) octeon_alloc_soft_command(oct, OCTNET_CMD_SIZE, - 16, ctx_size); + 16, 0); ncmd = (union octnet_cmd *)sc->virtdptr; - ctx = (struct liquidio_rx_ctl_context *)sc->ctxptr; - - WRITE_ONCE(ctx->cond, 0); - ctx->octeon_id = lio_get_device_id(oct); - init_waitqueue_head(&ctx->wc); ncmd->u64 = 0; ncmd->s.cmd = OCTNET_CMD_RX_CTL; @@ -1244,23 +1207,25 @@ static void send_rx_ctrl_cmd(struct lio *lio, int start_stop) octeon_prepare_soft_command(oct, sc, OPCODE_NIC, OPCODE_NIC_CMD, 0, 0, 0); - sc->callback = rx_ctl_callback; - sc->callback_arg = sc; - sc->wait_time = 5000; + init_completion(&sc->complete); + sc->sc_status = OCTEON_REQUEST_PENDING; retval = octeon_send_soft_command(oct, sc); if (retval == IQ_SEND_FAILED) { netif_info(lio, rx_err, lio->netdev, "Failed to send RX Control message\n"); + octeon_free_soft_command(oct, sc); + return; } else { /* Sleep on a wait queue till the cond flag indicates that the * response arrived or timed-out. */ - if (sleep_cond(&ctx->wc, &ctx->cond) == -EINTR) + retval = wait_for_sc_completion_timeout(oct, sc, 0); + if (retval) return; + oct->props[lio->ifidx].rx_on = start_stop; + WRITE_ONCE(sc->caller_is_done, true); } - - octeon_free_soft_command(oct, sc); } /** @@ -1274,8 +1239,10 @@ static void send_rx_ctrl_cmd(struct lio *lio, int start_stop) static void liquidio_destroy_nic_device(struct octeon_device *oct, int ifidx) { struct net_device *netdev = oct->props[ifidx].netdev; - struct lio *lio; + struct octeon_device_priv *oct_priv = + (struct octeon_device_priv *)oct->priv; struct napi_struct *napi, *n; + struct lio *lio; if (!netdev) { dev_err(&oct->pci_dev->dev, "%s No netdevice ptr for index %d\n", @@ -1304,6 +1271,8 @@ static void liquidio_destroy_nic_device(struct octeon_device *oct, int ifidx) list_for_each_entry_safe(napi, n, &netdev->napi_list, dev_list) netif_napi_del(napi); + tasklet_enable(&oct_priv->droq_tasklet); + if (atomic_read(&lio->ifstate) & LIO_IFSTATE_REGISTERED) unregister_netdev(netdev); @@ -1840,9 +1809,13 @@ static int liquidio_open(struct net_device *netdev) { struct lio *lio = GET_LIO(netdev); struct octeon_device *oct = lio->oct_dev; + struct octeon_device_priv *oct_priv = + (struct octeon_device_priv *)oct->priv; struct napi_struct *napi, *n; if (oct->props[lio->ifidx].napi_enabled == 0) { + tasklet_disable(&oct_priv->droq_tasklet); + list_for_each_entry_safe(napi, n, &netdev->napi_list, dev_list) napi_enable(napi); @@ -1876,6 +1849,12 @@ static int liquidio_open(struct net_device *netdev) /* tell Octeon to start forwarding packets to host */ send_rx_ctrl_cmd(lio, 1); + /* start periodical statistics fetch */ + INIT_DELAYED_WORK(&lio->stats_wk.work, lio_fetch_stats); + lio->stats_wk.ctxptr = lio; + schedule_delayed_work(&lio->stats_wk.work, msecs_to_jiffies + (LIQUIDIO_NDEV_STATS_POLL_TIME_MS)); + dev_info(&oct->pci_dev->dev, "%s interface is opened\n", netdev->name); @@ -1890,6 +1869,8 @@ static int liquidio_stop(struct net_device *netdev) { struct lio *lio = GET_LIO(netdev); struct octeon_device *oct = lio->oct_dev; + struct octeon_device_priv *oct_priv = + (struct octeon_device_priv *)oct->priv; struct napi_struct *napi, *n; ifstate_reset(lio, LIO_IFSTATE_RUNNING); @@ -1916,6 +1897,8 @@ static int liquidio_stop(struct net_device *netdev) cleanup_tx_poll_fn(netdev); } + cancel_delayed_work_sync(&lio->stats_wk.work); + if (lio->ptp_clock) { ptp_clock_unregister(lio->ptp_clock); lio->ptp_clock = NULL; @@ -1934,6 +1917,8 @@ static int liquidio_stop(struct net_device *netdev) if (OCTEON_CN23XX_PF(oct)) oct->droq[0]->ops.poll_mode = 0; + + tasklet_enable(&oct_priv->droq_tasklet); } dev_info(&oct->pci_dev->dev, "%s interface is stopped\n", netdev->name); @@ -2014,10 +1999,9 @@ static void liquidio_set_mcast_list(struct net_device *netdev) /* Apparently, any activity in this call from the kernel has to * be atomic. So we won't wait for response. */ - nctrl.wait_time = 0; ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl); - if (ret < 0) { + if (ret) { dev_err(&oct->pci_dev->dev, "DEVFLAGS change failed in core (ret: 0x%x)\n", ret); } @@ -2046,8 +2030,6 @@ static int liquidio_set_mac(struct net_device *netdev, void *p) nctrl.ncmd.s.more = 1; nctrl.iq_no = lio->linfo.txpciq[0].s.q_no; nctrl.netpndev = (u64)netdev; - nctrl.cb_fn = liquidio_link_ctrl_cmd_completion; - nctrl.wait_time = 100; nctrl.udd[0] = 0; /* The MAC Address is presented in network byte order. */ @@ -2058,6 +2040,14 @@ static int liquidio_set_mac(struct net_device *netdev, void *p) dev_err(&oct->pci_dev->dev, "MAC Address change failed\n"); return -ENOMEM; } + + if (nctrl.sc_status) { + dev_err(&oct->pci_dev->dev, + "%s: MAC Address change failed. sc return=%x\n", + __func__, nctrl.sc_status); + return -EIO; + } + memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len); memcpy(((u8 *)&lio->linfo.hw_addr) + 2, addr->sa_data, ETH_ALEN); @@ -2111,7 +2101,6 @@ liquidio_get_stats64(struct net_device *netdev, lstats->rx_packets = pkts; lstats->rx_dropped = drop; - octnet_get_link_stats(netdev); lstats->multicast = oct->link_stats.fromwire.fw_total_mcast; lstats->collisions = oct->link_stats.fromhost.total_collisions; @@ -2324,7 +2313,7 @@ static inline int send_nic_timestamp_pkt(struct octeon_device *oct, * @returns whether the packet was transmitted to the device okay or not * (NETDEV_TX_OK or NETDEV_TX_BUSY) */ -static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) +static netdev_tx_t liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) { struct lio *lio; struct octnet_buf_free_info *finfo; @@ -2598,14 +2587,15 @@ static int liquidio_vlan_rx_add_vid(struct net_device *netdev, nctrl.ncmd.s.cmd = OCTNET_CMD_ADD_VLAN_FILTER; nctrl.ncmd.s.param1 = vid; nctrl.iq_no = lio->linfo.txpciq[0].s.q_no; - nctrl.wait_time = 100; nctrl.netpndev = (u64)netdev; nctrl.cb_fn = liquidio_link_ctrl_cmd_completion; ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl); - if (ret < 0) { + if (ret) { dev_err(&oct->pci_dev->dev, "Add VLAN filter failed in core (ret: 0x%x)\n", ret); + if (ret > 0) + ret = -EIO; } return ret; @@ -2626,14 +2616,15 @@ static int liquidio_vlan_rx_kill_vid(struct net_device *netdev, nctrl.ncmd.s.cmd = OCTNET_CMD_DEL_VLAN_FILTER; nctrl.ncmd.s.param1 = vid; nctrl.iq_no = lio->linfo.txpciq[0].s.q_no; - nctrl.wait_time = 100; nctrl.netpndev = (u64)netdev; nctrl.cb_fn = liquidio_link_ctrl_cmd_completion; ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl); - if (ret < 0) { + if (ret) { dev_err(&oct->pci_dev->dev, "Del VLAN filter failed in core (ret: 0x%x)\n", ret); + if (ret > 0) + ret = -EIO; } return ret; } @@ -2659,15 +2650,16 @@ static int liquidio_set_rxcsum_command(struct net_device *netdev, int command, nctrl.ncmd.s.cmd = command; nctrl.ncmd.s.param1 = rx_cmd; nctrl.iq_no = lio->linfo.txpciq[0].s.q_no; - nctrl.wait_time = 100; nctrl.netpndev = (u64)netdev; nctrl.cb_fn = liquidio_link_ctrl_cmd_completion; ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl); - if (ret < 0) { + if (ret) { dev_err(&oct->pci_dev->dev, "DEVFLAGS RXCSUM change failed in core(ret:0x%x)\n", ret); + if (ret > 0) + ret = -EIO; } return ret; } @@ -2695,15 +2687,16 @@ static int liquidio_vxlan_port_command(struct net_device *netdev, int command, nctrl.ncmd.s.more = vxlan_cmd_bit; nctrl.ncmd.s.param1 = vxlan_port; nctrl.iq_no = lio->linfo.txpciq[0].s.q_no; - nctrl.wait_time = 100; nctrl.netpndev = (u64)netdev; nctrl.cb_fn = liquidio_link_ctrl_cmd_completion; ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl); - if (ret < 0) { + if (ret) { dev_err(&oct->pci_dev->dev, "VxLAN port add/delete failed in core (ret:0x%x)\n", ret); + if (ret > 0) + ret = -EIO; } return ret; } @@ -2826,6 +2819,7 @@ static int __liquidio_set_vf_mac(struct net_device *netdev, int vfidx, struct lio *lio = GET_LIO(netdev); struct octeon_device *oct = lio->oct_dev; struct octnic_ctrl_pkt nctrl; + int ret = 0; if (!is_valid_ether_addr(mac)) return -EINVAL; @@ -2839,12 +2833,13 @@ static int __liquidio_set_vf_mac(struct net_device *netdev, int vfidx, nctrl.ncmd.s.cmd = OCTNET_CMD_CHANGE_MACADDR; /* vfidx is 0 based, but vf_num (param1) is 1 based */ nctrl.ncmd.s.param1 = vfidx + 1; - nctrl.ncmd.s.param2 = (is_admin_assigned ? 1 : 0); nctrl.ncmd.s.more = 1; nctrl.iq_no = lio->linfo.txpciq[0].s.q_no; nctrl.netpndev = (u64)netdev; - nctrl.cb_fn = liquidio_link_ctrl_cmd_completion; - nctrl.wait_time = LIO_CMD_WAIT_TM; + if (is_admin_assigned) { + nctrl.ncmd.s.param2 = true; + nctrl.cb_fn = liquidio_link_ctrl_cmd_completion; + } nctrl.udd[0] = 0; /* The MAC Address is presented in network byte order. */ @@ -2852,9 +2847,11 @@ static int __liquidio_set_vf_mac(struct net_device *netdev, int vfidx, oct->sriov_info.vf_macaddr[vfidx] = nctrl.udd[0]; - octnet_send_nic_ctrl_pkt(oct, &nctrl); + ret = octnet_send_nic_ctrl_pkt(oct, &nctrl); + if (ret > 0) + ret = -EIO; - return 0; + return ret; } static int liquidio_set_vf_mac(struct net_device *netdev, int vfidx, u8 *mac) @@ -2873,6 +2870,62 @@ static int liquidio_set_vf_mac(struct net_device *netdev, int vfidx, u8 *mac) return retval; } +static int liquidio_set_vf_spoofchk(struct net_device *netdev, int vfidx, + bool enable) +{ + struct lio *lio = GET_LIO(netdev); + struct octeon_device *oct = lio->oct_dev; + struct octnic_ctrl_pkt nctrl; + int retval; + + if (!(oct->fw_info.app_cap_flags & LIQUIDIO_SPOOFCHK_CAP)) { + netif_info(lio, drv, lio->netdev, + "firmware does not support spoofchk\n"); + return -EOPNOTSUPP; + } + + if (vfidx < 0 || vfidx >= oct->sriov_info.num_vfs_alloced) { + netif_info(lio, drv, lio->netdev, "Invalid vfidx %d\n", vfidx); + return -EINVAL; + } + + if (enable) { + if (oct->sriov_info.vf_spoofchk[vfidx]) + return 0; + } else { + /* Clear */ + if (!oct->sriov_info.vf_spoofchk[vfidx]) + return 0; + } + + memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt)); + nctrl.ncmd.s.cmdgroup = OCTNET_CMD_GROUP1; + nctrl.ncmd.s.cmd = OCTNET_CMD_SET_VF_SPOOFCHK; + nctrl.ncmd.s.param1 = + vfidx + 1; /* vfidx is 0 based, + * but vf_num (param1) is 1 based + */ + nctrl.ncmd.s.param2 = enable; + nctrl.ncmd.s.more = 0; + nctrl.iq_no = lio->linfo.txpciq[0].s.q_no; + nctrl.cb_fn = 0; + + retval = octnet_send_nic_ctrl_pkt(oct, &nctrl); + + if (retval) { + netif_info(lio, drv, lio->netdev, + "Failed to set VF %d spoofchk %s\n", vfidx, + enable ? "on" : "off"); + return -1; + } + + oct->sriov_info.vf_spoofchk[vfidx] = enable; + netif_info(lio, drv, lio->netdev, "VF %u spoofchk is %s\n", vfidx, + enable ? "on" : "off"); + + return 0; +} + static int liquidio_set_vf_vlan(struct net_device *netdev, int vfidx, u16 vlan, u8 qos, __be16 vlan_proto) { @@ -2880,6 +2933,7 @@ static int liquidio_set_vf_vlan(struct net_device *netdev, int vfidx, struct octeon_device *oct = lio->oct_dev; struct octnic_ctrl_pkt nctrl; u16 vlantci; + int ret = 0; if (vfidx < 0 || vfidx >= oct->sriov_info.num_vfs_alloced) return -EINVAL; @@ -2911,13 +2965,17 @@ static int liquidio_set_vf_vlan(struct net_device *netdev, int vfidx, nctrl.ncmd.s.more = 0; nctrl.iq_no = lio->linfo.txpciq[0].s.q_no; nctrl.cb_fn = NULL; - nctrl.wait_time = LIO_CMD_WAIT_TM; - octnet_send_nic_ctrl_pkt(oct, &nctrl); + ret = octnet_send_nic_ctrl_pkt(oct, &nctrl); + if (ret) { + if (ret > 0) + ret = -EIO; + return ret; + } oct->sriov_info.vf_vlantci[vfidx] = vlantci; - return 0; + return ret; } static int liquidio_get_vf_config(struct net_device *netdev, int vfidx, @@ -2930,6 +2988,8 @@ static int liquidio_get_vf_config(struct net_device *netdev, int vfidx, if (vfidx < 0 || vfidx >= oct->sriov_info.num_vfs_alloced) return -EINVAL; + memset(ivi, 0, sizeof(struct ifla_vf_info)); + ivi->vf = vfidx; macaddr = 2 + (u8 *)&oct->sriov_info.vf_macaddr[vfidx]; ether_addr_copy(&ivi->mac[0], macaddr); @@ -2941,33 +3001,22 @@ static int liquidio_get_vf_config(struct net_device *netdev, int vfidx, else ivi->trusted = false; ivi->linkstate = oct->sriov_info.vf_linkstate[vfidx]; - return 0; -} - -static void trusted_vf_callback(struct octeon_device *oct_dev, - u32 status, void *ptr) -{ - struct octeon_soft_command *sc = (struct octeon_soft_command *)ptr; - struct lio_trusted_vf_ctx *ctx; + ivi->spoofchk = oct->sriov_info.vf_spoofchk[vfidx]; + ivi->max_tx_rate = lio->linfo.link.s.speed; + ivi->min_tx_rate = 0; - ctx = (struct lio_trusted_vf_ctx *)sc->ctxptr; - ctx->status = status; - - complete(&ctx->complete); + return 0; } static int liquidio_send_vf_trust_cmd(struct lio *lio, int vfidx, bool trusted) { struct octeon_device *oct = lio->oct_dev; - struct lio_trusted_vf_ctx *ctx; struct octeon_soft_command *sc; - int ctx_size, retval; - - ctx_size = sizeof(struct lio_trusted_vf_ctx); - sc = octeon_alloc_soft_command(oct, 0, 0, ctx_size); + int retval; - ctx = (struct lio_trusted_vf_ctx *)sc->ctxptr; - init_completion(&ctx->complete); + sc = octeon_alloc_soft_command(oct, 0, 16, 0); + if (!sc) + return -ENOMEM; sc->iq_no = lio->linfo.txpciq[0].s.q_no; @@ -2976,23 +3025,21 @@ static int liquidio_send_vf_trust_cmd(struct lio *lio, int vfidx, bool trusted) OPCODE_NIC_SET_TRUSTED_VF, 0, vfidx + 1, trusted); - sc->callback = trusted_vf_callback; - sc->callback_arg = sc; - sc->wait_time = 1000; + init_completion(&sc->complete); + sc->sc_status = OCTEON_REQUEST_PENDING; retval = octeon_send_soft_command(oct, sc); if (retval == IQ_SEND_FAILED) { + octeon_free_soft_command(oct, sc); retval = -1; } else { /* Wait for response or timeout */ - if (wait_for_completion_timeout(&ctx->complete, - msecs_to_jiffies(2000))) - retval = ctx->status; - else - retval = -1; - } + retval = wait_for_sc_completion_timeout(oct, sc, 0); + if (retval) + return (retval); - octeon_free_soft_command(oct, sc); + WRITE_ONCE(sc->caller_is_done, true); + } return retval; } @@ -3055,6 +3102,7 @@ static int liquidio_set_vf_link_state(struct net_device *netdev, int vfidx, struct lio *lio = GET_LIO(netdev); struct octeon_device *oct = lio->oct_dev; struct octnic_ctrl_pkt nctrl; + int ret = 0; if (vfidx < 0 || vfidx >= oct->sriov_info.num_vfs_alloced) return -EINVAL; @@ -3070,13 +3118,15 @@ static int liquidio_set_vf_link_state(struct net_device *netdev, int vfidx, nctrl.ncmd.s.more = 0; nctrl.iq_no = lio->linfo.txpciq[0].s.q_no; nctrl.cb_fn = NULL; - nctrl.wait_time = LIO_CMD_WAIT_TM; - octnet_send_nic_ctrl_pkt(oct, &nctrl); + ret = octnet_send_nic_ctrl_pkt(oct, &nctrl); - oct->sriov_info.vf_linkstate[vfidx] = linkstate; + if (!ret) + oct->sriov_info.vf_linkstate[vfidx] = linkstate; + else if (ret > 0) + ret = -EIO; - return 0; + return ret; } static int @@ -3204,6 +3254,7 @@ static const struct net_device_ops lionetdevops = { .ndo_set_vf_mac = liquidio_set_vf_mac, .ndo_set_vf_vlan = liquidio_set_vf_vlan, .ndo_get_vf_config = liquidio_get_vf_config, + .ndo_set_vf_spoofchk = liquidio_set_vf_spoofchk, .ndo_set_vf_trust = liquidio_set_vf_trust, .ndo_set_vf_link_state = liquidio_set_vf_link_state, .ndo_get_vf_stats = liquidio_get_vf_stats, @@ -3307,7 +3358,6 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) unsigned long micro; u32 cur_ver; struct octeon_soft_command *sc; - struct liquidio_if_cfg_context *ctx; struct liquidio_if_cfg_resp *resp; struct octdev_props *props; int retval, num_iqueues, num_oqueues; @@ -3315,7 +3365,7 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) union oct_nic_if_cfg if_cfg; unsigned int base_queue; unsigned int gmx_port_id; - u32 resp_size, ctx_size, data_size; + u32 resp_size, data_size; u32 ifidx_or_pfnum; struct lio_version *vdata; struct devlink *devlink; @@ -3340,13 +3390,11 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) for (i = 0; i < octeon_dev->ifcount; i++) { resp_size = sizeof(struct liquidio_if_cfg_resp); - ctx_size = sizeof(struct liquidio_if_cfg_context); data_size = sizeof(struct lio_version); sc = (struct octeon_soft_command *) octeon_alloc_soft_command(octeon_dev, data_size, - resp_size, ctx_size); + resp_size, 0); resp = (struct liquidio_if_cfg_resp *)sc->virtrptr; - ctx = (struct liquidio_if_cfg_context *)sc->ctxptr; vdata = (struct lio_version *)sc->virtdptr; *((u64 *)vdata) = 0; @@ -3376,9 +3424,6 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) dev_dbg(&octeon_dev->pci_dev->dev, "requesting config for interface %d, iqs %d, oqs %d\n", ifidx_or_pfnum, num_iqueues, num_oqueues); - WRITE_ONCE(ctx->cond, 0); - ctx->octeon_id = lio_get_device_id(octeon_dev); - init_waitqueue_head(&ctx->wc); if_cfg.u64 = 0; if_cfg.s.num_iqueues = num_iqueues; @@ -3392,9 +3437,8 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) OPCODE_NIC_IF_CFG, 0, if_cfg.u64, 0); - sc->callback = lio_if_cfg_callback; - sc->callback_arg = sc; - sc->wait_time = LIO_IFCFG_WAIT_TIME; + init_completion(&sc->complete); + sc->sc_status = OCTEON_REQUEST_PENDING; retval = octeon_send_soft_command(octeon_dev, sc); if (retval == IQ_SEND_FAILED) { @@ -3402,22 +3446,26 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) "iq/oq config failed status: %x\n", retval); /* Soft instr is freed by driver in case of failure. */ - goto setup_nic_dev_fail; + octeon_free_soft_command(octeon_dev, sc); + return(-EIO); } /* Sleep on a wait queue till the cond flag indicates that the * response arrived or timed-out. */ - if (sleep_cond(&ctx->wc, &ctx->cond) == -EINTR) { - dev_err(&octeon_dev->pci_dev->dev, "Wait interrupted\n"); - goto setup_nic_wait_intr; - } + retval = wait_for_sc_completion_timeout(octeon_dev, sc, 0); + if (retval) + return retval; retval = resp->status; if (retval) { dev_err(&octeon_dev->pci_dev->dev, "iq/oq config failed\n"); - goto setup_nic_dev_fail; + WRITE_ONCE(sc->caller_is_done, true); + goto setup_nic_dev_done; } + snprintf(octeon_dev->fw_info.liquidio_firmware_version, + 32, "%s", + resp->cfg_info.liquidio_firmware_version); /* Verify f/w version (in case of 'auto' loading from flash) */ fw_ver = octeon_dev->fw_info.liquidio_firmware_version; @@ -3427,7 +3475,8 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) dev_err(&octeon_dev->pci_dev->dev, "Unmatched firmware version. Expected %s.x, got %s.\n", LIQUIDIO_BASE_VERSION, fw_ver); - goto setup_nic_dev_fail; + WRITE_ONCE(sc->caller_is_done, true); + goto setup_nic_dev_done; } else if (atomic_read(octeon_dev->adapter_fw_state) == FW_IS_PRELOADED) { dev_info(&octeon_dev->pci_dev->dev, @@ -3454,7 +3503,8 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) "Got bad iqueues (%016llx) or oqueues (%016llx) from firmware.\n", resp->cfg_info.iqmask, resp->cfg_info.oqmask); - goto setup_nic_dev_fail; + WRITE_ONCE(sc->caller_is_done, true); + goto setup_nic_dev_done; } if (OCTEON_CN6XXX(octeon_dev)) { @@ -3473,7 +3523,8 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) if (!netdev) { dev_err(&octeon_dev->pci_dev->dev, "Device allocation failed\n"); - goto setup_nic_dev_fail; + WRITE_ONCE(sc->caller_is_done, true); + goto setup_nic_dev_done; } SET_NETDEV_DEV(netdev, &octeon_dev->pci_dev->dev); @@ -3488,14 +3539,16 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) if (retval) { dev_err(&octeon_dev->pci_dev->dev, "setting real number rx failed\n"); - goto setup_nic_dev_fail; + WRITE_ONCE(sc->caller_is_done, true); + goto setup_nic_dev_free; } retval = netif_set_real_num_tx_queues(netdev, num_iqueues); if (retval) { dev_err(&octeon_dev->pci_dev->dev, "setting real number tx failed\n"); - goto setup_nic_dev_fail; + WRITE_ONCE(sc->caller_is_done, true); + goto setup_nic_dev_free; } lio = GET_LIO(netdev); @@ -3522,6 +3575,8 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) lio->linfo.gmxport = resp->cfg_info.linfo.gmxport; lio->linfo.link.u64 = resp->cfg_info.linfo.link.u64; + WRITE_ONCE(sc->caller_is_done, true); + lio->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE); if (OCTEON_CN23XX_PF(octeon_dev) || @@ -3588,7 +3643,7 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) dev_err(&octeon_dev->pci_dev->dev, "Error setting VF%d MAC address\n", j); - goto setup_nic_dev_fail; + goto setup_nic_dev_free; } } @@ -3610,7 +3665,7 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) lio->linfo.num_txpciq, lio->linfo.num_rxpciq)) { dev_err(&octeon_dev->pci_dev->dev, "I/O queues creation failed\n"); - goto setup_nic_dev_fail; + goto setup_nic_dev_free; } ifstate_set(lio, LIO_IFSTATE_DROQ_OPS); @@ -3621,7 +3676,7 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) if (lio_setup_glists(octeon_dev, lio, num_iqueues)) { dev_err(&octeon_dev->pci_dev->dev, "Gather list allocation failed\n"); - goto setup_nic_dev_fail; + goto setup_nic_dev_free; } /* Register ethtool support */ @@ -3643,20 +3698,20 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) OCTNET_CMD_VERBOSE_ENABLE, 0); if (setup_link_status_change_wq(netdev)) - goto setup_nic_dev_fail; + goto setup_nic_dev_free; if ((octeon_dev->fw_info.app_cap_flags & LIQUIDIO_TIME_SYNC_CAP) && setup_sync_octeon_time_wq(netdev)) - goto setup_nic_dev_fail; + goto setup_nic_dev_free; if (setup_rx_oom_poll_fn(netdev)) - goto setup_nic_dev_fail; + goto setup_nic_dev_free; /* Register the network device with the OS */ if (register_netdev(netdev)) { dev_err(&octeon_dev->pci_dev->dev, "Device registration failed\n"); - goto setup_nic_dev_fail; + goto setup_nic_dev_free; } dev_dbg(&octeon_dev->pci_dev->dev, @@ -3679,8 +3734,6 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) dev_dbg(&octeon_dev->pci_dev->dev, "NIC ifidx:%d Setup successful\n", i); - octeon_free_soft_command(octeon_dev, sc); - if (octeon_dev->subsystem_id == OCTEON_CN2350_25GB_SUBSYS_ID || octeon_dev->subsystem_id == @@ -3709,13 +3762,20 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) } octeon_dev->speed_boot = octeon_dev->speed_setting; + /* don't read FEC setting if unsupported by f/w (see above) */ + if (octeon_dev->speed_boot == 25 && + !octeon_dev->no_speed_setting) { + liquidio_get_fec(lio); + octeon_dev->props[lio->ifidx].fec_boot = + octeon_dev->props[lio->ifidx].fec; + } } devlink = devlink_alloc(&liquidio_devlink_ops, sizeof(struct lio_devlink_priv)); if (!devlink) { dev_err(&octeon_dev->pci_dev->dev, "devlink alloc failed\n"); - goto setup_nic_wait_intr; + goto setup_nic_dev_free; } lio_devlink = devlink_priv(devlink); @@ -3725,7 +3785,7 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) devlink_free(devlink); dev_err(&octeon_dev->pci_dev->dev, "devlink registration failed\n"); - goto setup_nic_wait_intr; + goto setup_nic_dev_free; } octeon_dev->devlink = devlink; @@ -3733,17 +3793,16 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) return 0; -setup_nic_dev_fail: - - octeon_free_soft_command(octeon_dev, sc); - -setup_nic_wait_intr: +setup_nic_dev_free: while (i--) { dev_err(&octeon_dev->pci_dev->dev, "NIC ifidx:%d Setup failed\n", i); liquidio_destroy_nic_device(octeon_dev, i); } + +setup_nic_dev_done: + return -ENODEV; } diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c index b77835724dc8..54b245797d2e 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c @@ -40,14 +40,6 @@ MODULE_PARM_DESC(debug, "NETIF_MSG debug bits"); #define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK) -struct liquidio_rx_ctl_context { - int octeon_id; - - wait_queue_head_t wc; - - int cond; -}; - struct oct_timestamp_resp { u64 rh; u64 timestamp; @@ -452,6 +444,8 @@ static void octeon_pci_flr(struct octeon_device *oct) */ static void octeon_destroy_resources(struct octeon_device *oct) { + struct octeon_device_priv *oct_priv = + (struct octeon_device_priv *)oct->priv; struct msix_entry *msix_entries; int i; @@ -471,12 +465,12 @@ static void octeon_destroy_resources(struct octeon_device *oct) case OCT_DEV_HOST_OK: /* fallthrough */ case OCT_DEV_IO_QUEUES_DONE: - if (wait_for_pending_requests(oct)) - dev_err(&oct->pci_dev->dev, "There were pending requests\n"); - if (lio_wait_for_instr_fetch(oct)) dev_err(&oct->pci_dev->dev, "IQ had pending instructions\n"); + if (wait_for_pending_requests(oct)) + dev_err(&oct->pci_dev->dev, "There were pending requests\n"); + /* Disable the input and output queues now. No more packets will * arrive from Octeon, but we should wait for all packet * processing to finish. @@ -485,7 +479,33 @@ static void octeon_destroy_resources(struct octeon_device *oct) if (lio_wait_for_oq_pkts(oct)) dev_err(&oct->pci_dev->dev, "OQ had pending packets\n"); - /* fall through */ + + /* Force all requests waiting to be fetched by OCTEON to + * complete. + */ + for (i = 0; i < MAX_OCTEON_INSTR_QUEUES(oct); i++) { + struct octeon_instr_queue *iq; + + if (!(oct->io_qmask.iq & BIT_ULL(i))) + continue; + iq = oct->instr_queue[i]; + + if (atomic_read(&iq->instr_pending)) { + spin_lock_bh(&iq->lock); + iq->fill_cnt = 0; + iq->octeon_read_index = iq->host_write_index; + iq->stats.instr_processed += + atomic_read(&iq->instr_pending); + lio_process_iq_request_list(oct, iq, 0); + spin_unlock_bh(&iq->lock); + } + } + + lio_process_ordered_list(oct, 1); + octeon_free_sc_done_list(oct); + octeon_free_sc_zombie_list(oct); + + /* fall through */ case OCT_DEV_INTR_SET_DONE: /* Disable interrupts */ oct->fn_list.disable_interrupt(oct, OCTEON_ALL_INTR); @@ -569,33 +589,8 @@ static void octeon_destroy_resources(struct octeon_device *oct) /* Nothing to be done here either */ break; } -} - -/** - * \brief Callback for rx ctrl - * @param status status of request - * @param buf pointer to resp structure - */ -static void rx_ctl_callback(struct octeon_device *oct, - u32 status, void *buf) -{ - struct octeon_soft_command *sc = (struct octeon_soft_command *)buf; - struct liquidio_rx_ctl_context *ctx; - - ctx = (struct liquidio_rx_ctl_context *)sc->ctxptr; - oct = lio_get_device(ctx->octeon_id); - if (status) - dev_err(&oct->pci_dev->dev, "rx ctl instruction failed. Status: %llx\n", - CVM_CAST64(status)); - WRITE_ONCE(ctx->cond, 1); - - /* This barrier is required to be sure that the response has been - * written fully before waking up the handler - */ - wmb(); - - wake_up_interruptible(&ctx->wc); + tasklet_kill(&oct_priv->droq_tasklet); } /** @@ -606,8 +601,6 @@ static void rx_ctl_callback(struct octeon_device *oct, static void send_rx_ctrl_cmd(struct lio *lio, int start_stop) { struct octeon_device *oct = (struct octeon_device *)lio->oct_dev; - int ctx_size = sizeof(struct liquidio_rx_ctl_context); - struct liquidio_rx_ctl_context *ctx; struct octeon_soft_command *sc; union octnet_cmd *ncmd; int retval; @@ -617,14 +610,9 @@ static void send_rx_ctrl_cmd(struct lio *lio, int start_stop) sc = (struct octeon_soft_command *) octeon_alloc_soft_command(oct, OCTNET_CMD_SIZE, - 16, ctx_size); + 16, 0); ncmd = (union octnet_cmd *)sc->virtdptr; - ctx = (struct liquidio_rx_ctl_context *)sc->ctxptr; - - WRITE_ONCE(ctx->cond, 0); - ctx->octeon_id = lio_get_device_id(oct); - init_waitqueue_head(&ctx->wc); ncmd->u64 = 0; ncmd->s.cmd = OCTNET_CMD_RX_CTL; @@ -637,23 +625,24 @@ static void send_rx_ctrl_cmd(struct lio *lio, int start_stop) octeon_prepare_soft_command(oct, sc, OPCODE_NIC, OPCODE_NIC_CMD, 0, 0, 0); - sc->callback = rx_ctl_callback; - sc->callback_arg = sc; - sc->wait_time = 5000; + init_completion(&sc->complete); + sc->sc_status = OCTEON_REQUEST_PENDING; retval = octeon_send_soft_command(oct, sc); if (retval == IQ_SEND_FAILED) { netif_info(lio, rx_err, lio->netdev, "Failed to send RX Control message\n"); + octeon_free_soft_command(oct, sc); } else { /* Sleep on a wait queue till the cond flag indicates that the * response arrived or timed-out. */ - if (sleep_cond(&ctx->wc, &ctx->cond) == -EINTR) + retval = wait_for_sc_completion_timeout(oct, sc, 0); + if (retval) return; + oct->props[lio->ifidx].rx_on = start_stop; + WRITE_ONCE(sc->caller_is_done, true); } - - octeon_free_soft_command(oct, sc); } /** @@ -667,6 +656,8 @@ static void send_rx_ctrl_cmd(struct lio *lio, int start_stop) static void liquidio_destroy_nic_device(struct octeon_device *oct, int ifidx) { struct net_device *netdev = oct->props[ifidx].netdev; + struct octeon_device_priv *oct_priv = + (struct octeon_device_priv *)oct->priv; struct napi_struct *napi, *n; struct lio *lio; @@ -696,6 +687,8 @@ static void liquidio_destroy_nic_device(struct octeon_device *oct, int ifidx) list_for_each_entry_safe(napi, n, &netdev->napi_list, dev_list) netif_napi_del(napi); + tasklet_enable(&oct_priv->droq_tasklet); + if (atomic_read(&lio->ifstate) & LIO_IFSTATE_REGISTERED) unregister_netdev(netdev); @@ -913,9 +906,13 @@ static int liquidio_open(struct net_device *netdev) { struct lio *lio = GET_LIO(netdev); struct octeon_device *oct = lio->oct_dev; + struct octeon_device_priv *oct_priv = + (struct octeon_device_priv *)oct->priv; struct napi_struct *napi, *n; if (!oct->props[lio->ifidx].napi_enabled) { + tasklet_disable(&oct_priv->droq_tasklet); + list_for_each_entry_safe(napi, n, &netdev->napi_list, dev_list) napi_enable(napi); @@ -932,6 +929,11 @@ static int liquidio_open(struct net_device *netdev) netif_info(lio, ifup, lio->netdev, "Interface Open, ready for traffic\n"); start_txqs(netdev); + INIT_DELAYED_WORK(&lio->stats_wk.work, lio_fetch_stats); + lio->stats_wk.ctxptr = lio; + schedule_delayed_work(&lio->stats_wk.work, msecs_to_jiffies + (LIQUIDIO_NDEV_STATS_POLL_TIME_MS)); + /* tell Octeon to start forwarding packets to host */ send_rx_ctrl_cmd(lio, 1); @@ -948,6 +950,8 @@ static int liquidio_stop(struct net_device *netdev) { struct lio *lio = GET_LIO(netdev); struct octeon_device *oct = lio->oct_dev; + struct octeon_device_priv *oct_priv = + (struct octeon_device_priv *)oct->priv; struct napi_struct *napi, *n; /* tell Octeon to stop forwarding packets to host */ @@ -977,8 +981,12 @@ static int liquidio_stop(struct net_device *netdev) oct->props[lio->ifidx].napi_enabled = 0; oct->droq[0]->ops.poll_mode = 0; + + tasklet_enable(&oct_priv->droq_tasklet); } + cancel_delayed_work_sync(&lio->stats_wk.work); + dev_info(&oct->pci_dev->dev, "%s interface is stopped\n", netdev->name); return 0; @@ -1093,10 +1101,9 @@ static void liquidio_set_mcast_list(struct net_device *netdev) /* Apparently, any activity in this call from the kernel has to * be atomic. So we won't wait for response. */ - nctrl.wait_time = 0; ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl); - if (ret < 0) { + if (ret) { dev_err(&oct->pci_dev->dev, "DEVFLAGS change failed in core (ret: 0x%x)\n", ret); } @@ -1133,8 +1140,6 @@ static int liquidio_set_mac(struct net_device *netdev, void *p) nctrl.ncmd.s.more = 1; nctrl.iq_no = lio->linfo.txpciq[0].s.q_no; nctrl.netpndev = (u64)netdev; - nctrl.cb_fn = liquidio_link_ctrl_cmd_completion; - nctrl.wait_time = 100; nctrl.udd[0] = 0; /* The MAC Address is presented in network byte order. */ @@ -1145,6 +1150,13 @@ static int liquidio_set_mac(struct net_device *netdev, void *p) dev_err(&oct->pci_dev->dev, "MAC Address change failed\n"); return -ENOMEM; } + + if (nctrl.sc_status == + FIRMWARE_STATUS_CODE(OCTEON_REQUEST_NO_PERMISSION)) { + dev_err(&oct->pci_dev->dev, "MAC Address change failed: no permission\n"); + return -EPERM; + } + memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len); ether_addr_copy(((u8 *)&lio->linfo.hw_addr) + 2, addr->sa_data); @@ -1198,7 +1210,6 @@ liquidio_get_stats64(struct net_device *netdev, lstats->rx_packets = pkts; lstats->rx_dropped = drop; - octnet_get_link_stats(netdev); lstats->multicast = oct->link_stats.fromwire.fw_total_mcast; /* detailed rx_errors: */ @@ -1390,7 +1401,7 @@ static int send_nic_timestamp_pkt(struct octeon_device *oct, * @returns whether the packet was transmitted to the device okay or not * (NETDEV_TX_OK or NETDEV_TX_BUSY) */ -static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) +static netdev_tx_t liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) { struct octnet_buf_free_info *finfo; union octnic_cmd_setup cmdsetup; @@ -1638,8 +1649,6 @@ liquidio_vlan_rx_add_vid(struct net_device *netdev, struct lio *lio = GET_LIO(netdev); struct octeon_device *oct = lio->oct_dev; struct octnic_ctrl_pkt nctrl; - struct completion compl; - u16 response_code; int ret = 0; memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt)); @@ -1648,26 +1657,15 @@ liquidio_vlan_rx_add_vid(struct net_device *netdev, nctrl.ncmd.s.cmd = OCTNET_CMD_ADD_VLAN_FILTER; nctrl.ncmd.s.param1 = vid; nctrl.iq_no = lio->linfo.txpciq[0].s.q_no; - nctrl.wait_time = 100; nctrl.netpndev = (u64)netdev; nctrl.cb_fn = liquidio_link_ctrl_cmd_completion; - init_completion(&compl); - nctrl.completion = &compl; - nctrl.response_code = &response_code; ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl); - if (ret < 0) { + if (ret) { dev_err(&oct->pci_dev->dev, "Add VLAN filter failed in core (ret: 0x%x)\n", ret); - return -EIO; - } - - if (!wait_for_completion_timeout(&compl, - msecs_to_jiffies(nctrl.wait_time))) - return -EPERM; - - if (READ_ONCE(response_code)) return -EPERM; + } return 0; } @@ -1687,14 +1685,15 @@ liquidio_vlan_rx_kill_vid(struct net_device *netdev, nctrl.ncmd.s.cmd = OCTNET_CMD_DEL_VLAN_FILTER; nctrl.ncmd.s.param1 = vid; nctrl.iq_no = lio->linfo.txpciq[0].s.q_no; - nctrl.wait_time = 100; nctrl.netpndev = (u64)netdev; nctrl.cb_fn = liquidio_link_ctrl_cmd_completion; ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl); - if (ret < 0) { + if (ret) { dev_err(&oct->pci_dev->dev, "Del VLAN filter failed in core (ret: 0x%x)\n", ret); + if (ret > 0) + ret = -EIO; } return ret; } @@ -1720,14 +1719,15 @@ static int liquidio_set_rxcsum_command(struct net_device *netdev, int command, nctrl.ncmd.s.cmd = command; nctrl.ncmd.s.param1 = rx_cmd; nctrl.iq_no = lio->linfo.txpciq[0].s.q_no; - nctrl.wait_time = 100; nctrl.netpndev = (u64)netdev; nctrl.cb_fn = liquidio_link_ctrl_cmd_completion; ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl); - if (ret < 0) { + if (ret) { dev_err(&oct->pci_dev->dev, "DEVFLAGS RXCSUM change failed in core (ret:0x%x)\n", ret); + if (ret > 0) + ret = -EIO; } return ret; } @@ -1755,15 +1755,16 @@ static int liquidio_vxlan_port_command(struct net_device *netdev, int command, nctrl.ncmd.s.more = vxlan_cmd_bit; nctrl.ncmd.s.param1 = vxlan_port; nctrl.iq_no = lio->linfo.txpciq[0].s.q_no; - nctrl.wait_time = 100; nctrl.netpndev = (u64)netdev; nctrl.cb_fn = liquidio_link_ctrl_cmd_completion; ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl); - if (ret < 0) { + if (ret) { dev_err(&oct->pci_dev->dev, "DEVFLAGS VxLAN port add/delete failed in core (ret : 0x%x)\n", ret); + if (ret > 0) + ret = -EIO; } return ret; } @@ -1924,8 +1925,7 @@ nic_info_err: static int setup_nic_devices(struct octeon_device *octeon_dev) { int retval, num_iqueues, num_oqueues; - struct liquidio_if_cfg_context *ctx; - u32 resp_size, ctx_size, data_size; + u32 resp_size, data_size; struct liquidio_if_cfg_resp *resp; struct octeon_soft_command *sc; union oct_nic_if_cfg if_cfg; @@ -1956,13 +1956,11 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) for (i = 0; i < octeon_dev->ifcount; i++) { resp_size = sizeof(struct liquidio_if_cfg_resp); - ctx_size = sizeof(struct liquidio_if_cfg_context); data_size = sizeof(struct lio_version); sc = (struct octeon_soft_command *) octeon_alloc_soft_command(octeon_dev, data_size, - resp_size, ctx_size); + resp_size, 0); resp = (struct liquidio_if_cfg_resp *)sc->virtrptr; - ctx = (struct liquidio_if_cfg_context *)sc->ctxptr; vdata = (struct lio_version *)sc->virtdptr; *((u64 *)vdata) = 0; @@ -1970,10 +1968,6 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) vdata->minor = cpu_to_be16(LIQUIDIO_BASE_MINOR_VERSION); vdata->micro = cpu_to_be16(LIQUIDIO_BASE_MICRO_VERSION); - WRITE_ONCE(ctx->cond, 0); - ctx->octeon_id = lio_get_device_id(octeon_dev); - init_waitqueue_head(&ctx->wc); - if_cfg.u64 = 0; if_cfg.s.num_iqueues = octeon_dev->sriov_info.rings_per_vf; @@ -1986,32 +1980,37 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) OPCODE_NIC_IF_CFG, 0, if_cfg.u64, 0); - sc->callback = lio_if_cfg_callback; - sc->callback_arg = sc; - sc->wait_time = 5000; + init_completion(&sc->complete); + sc->sc_status = OCTEON_REQUEST_PENDING; retval = octeon_send_soft_command(octeon_dev, sc); if (retval == IQ_SEND_FAILED) { dev_err(&octeon_dev->pci_dev->dev, "iq/oq config failed status: %x\n", retval); /* Soft instr is freed by driver in case of failure. */ - goto setup_nic_dev_fail; + octeon_free_soft_command(octeon_dev, sc); + return(-EIO); } /* Sleep on a wait queue till the cond flag indicates that the * response arrived or timed-out. */ - if (sleep_cond(&ctx->wc, &ctx->cond) == -EINTR) { - dev_err(&octeon_dev->pci_dev->dev, "Wait interrupted\n"); - goto setup_nic_wait_intr; - } + retval = wait_for_sc_completion_timeout(octeon_dev, sc, 0); + if (retval) + return retval; retval = resp->status; if (retval) { - dev_err(&octeon_dev->pci_dev->dev, "iq/oq config failed\n"); - goto setup_nic_dev_fail; + dev_err(&octeon_dev->pci_dev->dev, + "iq/oq config failed, retval = %d\n", retval); + WRITE_ONCE(sc->caller_is_done, true); + return -EIO; } + snprintf(octeon_dev->fw_info.liquidio_firmware_version, + 32, "%s", + resp->cfg_info.liquidio_firmware_version); + octeon_swap_8B_data((u64 *)(&resp->cfg_info), (sizeof(struct liquidio_if_cfg_info)) >> 3); @@ -2022,7 +2021,8 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) dev_err(&octeon_dev->pci_dev->dev, "Got bad iqueues (%016llx) or oqueues (%016llx) from firmware.\n", resp->cfg_info.iqmask, resp->cfg_info.oqmask); - goto setup_nic_dev_fail; + WRITE_ONCE(sc->caller_is_done, true); + goto setup_nic_dev_done; } dev_dbg(&octeon_dev->pci_dev->dev, "interface %d, iqmask %016llx, oqmask %016llx, numiqueues %d, numoqueues %d\n", @@ -2033,7 +2033,8 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) if (!netdev) { dev_err(&octeon_dev->pci_dev->dev, "Device allocation failed\n"); - goto setup_nic_dev_fail; + WRITE_ONCE(sc->caller_is_done, true); + goto setup_nic_dev_done; } SET_NETDEV_DEV(netdev, &octeon_dev->pci_dev->dev); @@ -2070,6 +2071,8 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) lio->linfo.link.u64 = resp->cfg_info.linfo.link.u64; lio->linfo.macaddr_is_admin_asgnd = resp->cfg_info.linfo.macaddr_is_admin_asgnd; + lio->linfo.macaddr_spoofchk = + resp->cfg_info.linfo.macaddr_spoofchk; lio->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE); @@ -2109,6 +2112,8 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) netdev->min_mtu = LIO_MIN_MTU_SIZE; netdev->max_mtu = LIO_MAX_MTU_SIZE; + WRITE_ONCE(sc->caller_is_done, true); + /* Point to the properties for octeon device to which this * interface belongs. */ @@ -2132,7 +2137,7 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) lio->linfo.num_txpciq, lio->linfo.num_rxpciq)) { dev_err(&octeon_dev->pci_dev->dev, "I/O queues creation failed\n"); - goto setup_nic_dev_fail; + goto setup_nic_dev_free; } ifstate_set(lio, LIO_IFSTATE_DROQ_OPS); @@ -2155,7 +2160,7 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) if (lio_setup_glists(octeon_dev, lio, num_iqueues)) { dev_err(&octeon_dev->pci_dev->dev, "Gather list allocation failed\n"); - goto setup_nic_dev_fail; + goto setup_nic_dev_free; } /* Register ethtool support */ @@ -2170,15 +2175,15 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) OCTNIC_LROIPV4 | OCTNIC_LROIPV6); if (setup_link_status_change_wq(netdev)) - goto setup_nic_dev_fail; + goto setup_nic_dev_free; if (setup_rx_oom_poll_fn(netdev)) - goto setup_nic_dev_fail; + goto setup_nic_dev_free; /* Register the network device with the OS */ if (register_netdev(netdev)) { dev_err(&octeon_dev->pci_dev->dev, "Device registration failed\n"); - goto setup_nic_dev_fail; + goto setup_nic_dev_free; } dev_dbg(&octeon_dev->pci_dev->dev, @@ -2201,24 +2206,21 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) dev_dbg(&octeon_dev->pci_dev->dev, "NIC ifidx:%d Setup successful\n", i); - octeon_free_soft_command(octeon_dev, sc); - octeon_dev->no_speed_setting = 1; } return 0; -setup_nic_dev_fail: - - octeon_free_soft_command(octeon_dev, sc); - -setup_nic_wait_intr: +setup_nic_dev_free: while (i--) { dev_err(&octeon_dev->pci_dev->dev, "NIC ifidx:%d Setup failed\n", i); liquidio_destroy_nic_device(octeon_dev, i); } + +setup_nic_dev_done: + return -ENODEV; } diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c index ddd7431579f4..ea9859e028d4 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c @@ -27,11 +27,11 @@ #include "octeon_network.h" #include <net/switchdev.h> #include "lio_vf_rep.h" -#include "octeon_network.h" static int lio_vf_rep_open(struct net_device *ndev); static int lio_vf_rep_stop(struct net_device *ndev); -static int lio_vf_rep_pkt_xmit(struct sk_buff *skb, struct net_device *ndev); +static netdev_tx_t lio_vf_rep_pkt_xmit(struct sk_buff *skb, + struct net_device *ndev); static void lio_vf_rep_tx_timeout(struct net_device *netdev); static int lio_vf_rep_phys_port_name(struct net_device *dev, char *buf, size_t len); @@ -49,44 +49,25 @@ static const struct net_device_ops lio_vf_rep_ndev_ops = { .ndo_change_mtu = lio_vf_rep_change_mtu, }; -static void -lio_vf_rep_send_sc_complete(struct octeon_device *oct, - u32 status, void *ptr) -{ - struct octeon_soft_command *sc = (struct octeon_soft_command *)ptr; - struct lio_vf_rep_sc_ctx *ctx = - (struct lio_vf_rep_sc_ctx *)sc->ctxptr; - struct lio_vf_rep_resp *resp = - (struct lio_vf_rep_resp *)sc->virtrptr; - - if (status != OCTEON_REQUEST_TIMEOUT && READ_ONCE(resp->status)) - WRITE_ONCE(resp->status, 0); - - complete(&ctx->complete); -} - static int lio_vf_rep_send_soft_command(struct octeon_device *oct, void *req, int req_size, void *resp, int resp_size) { int tot_resp_size = sizeof(struct lio_vf_rep_resp) + resp_size; - int ctx_size = sizeof(struct lio_vf_rep_sc_ctx); struct octeon_soft_command *sc = NULL; struct lio_vf_rep_resp *rep_resp; - struct lio_vf_rep_sc_ctx *ctx; void *sc_req; int err; sc = (struct octeon_soft_command *) octeon_alloc_soft_command(oct, req_size, - tot_resp_size, ctx_size); + tot_resp_size, 0); if (!sc) return -ENOMEM; - ctx = (struct lio_vf_rep_sc_ctx *)sc->ctxptr; - memset(ctx, 0, ctx_size); - init_completion(&ctx->complete); + init_completion(&sc->complete); + sc->sc_status = OCTEON_REQUEST_PENDING; sc_req = (struct lio_vf_rep_req *)sc->virtdptr; memcpy(sc_req, req, req_size); @@ -98,23 +79,24 @@ lio_vf_rep_send_soft_command(struct octeon_device *oct, sc->iq_no = 0; octeon_prepare_soft_command(oct, sc, OPCODE_NIC, OPCODE_NIC_VF_REP_CMD, 0, 0, 0); - sc->callback = lio_vf_rep_send_sc_complete; - sc->callback_arg = sc; - sc->wait_time = LIO_VF_REP_REQ_TMO_MS; err = octeon_send_soft_command(oct, sc); if (err == IQ_SEND_FAILED) goto free_buff; - wait_for_completion_timeout(&ctx->complete, - msecs_to_jiffies - (2 * LIO_VF_REP_REQ_TMO_MS)); + err = wait_for_sc_completion_timeout(oct, sc, 0); + if (err) + return err; + err = READ_ONCE(rep_resp->status) ? -EBUSY : 0; if (err) dev_err(&oct->pci_dev->dev, "VF rep send config failed\n"); - - if (resp) + else if (resp) memcpy(resp, (rep_resp + 1), resp_size); + + WRITE_ONCE(sc->caller_is_done, true); + return err; + free_buff: octeon_free_soft_command(oct, sc); @@ -380,7 +362,7 @@ lio_vf_rep_packet_sent_callback(struct octeon_device *oct, netif_wake_queue(ndev); } -static int +static netdev_tx_t lio_vf_rep_pkt_xmit(struct sk_buff *skb, struct net_device *ndev) { struct lio_vf_rep_desc *vf_rep = netdev_priv(ndev); @@ -404,7 +386,7 @@ lio_vf_rep_pkt_xmit(struct sk_buff *skb, struct net_device *ndev) } sc = (struct octeon_soft_command *) - octeon_alloc_soft_command(oct, 0, 0, 0); + octeon_alloc_soft_command(oct, 0, 16, 0); if (!sc) { dev_err(&oct->pci_dev->dev, "VF rep: Soft command alloc failed\n"); goto xmit_failed; @@ -413,6 +395,7 @@ lio_vf_rep_pkt_xmit(struct sk_buff *skb, struct net_device *ndev) /* Multiple buffers are not used for vf_rep packets. */ if (skb_shinfo(skb)->nr_frags != 0) { dev_err(&oct->pci_dev->dev, "VF rep: nr_frags != 0. Dropping packet\n"); + octeon_free_soft_command(oct, sc); goto xmit_failed; } @@ -420,6 +403,7 @@ lio_vf_rep_pkt_xmit(struct sk_buff *skb, struct net_device *ndev) skb->data, skb->len, DMA_TO_DEVICE); if (dma_mapping_error(&oct->pci_dev->dev, sc->dmadptr)) { dev_err(&oct->pci_dev->dev, "VF rep: DMA mapping failed\n"); + octeon_free_soft_command(oct, sc); goto xmit_failed; } @@ -440,6 +424,7 @@ lio_vf_rep_pkt_xmit(struct sk_buff *skb, struct net_device *ndev) if (status == IQ_SEND_FAILED) { dma_unmap_single(&oct->pci_dev->dev, sc->dmadptr, sc->datasize, DMA_TO_DEVICE); + octeon_free_soft_command(oct, sc); goto xmit_failed; } diff --git a/drivers/net/ethernet/cavium/liquidio/liquidio_common.h b/drivers/net/ethernet/cavium/liquidio/liquidio_common.h index 7407fcd338e9..a5e0e9f17959 100644 --- a/drivers/net/ethernet/cavium/liquidio/liquidio_common.h +++ b/drivers/net/ethernet/cavium/liquidio/liquidio_common.h @@ -118,6 +118,10 @@ enum octeon_tag_type { /* App specific capabilities from firmware to pf driver */ #define LIQUIDIO_TIME_SYNC_CAP 0x1 #define LIQUIDIO_SWITCHDEV_CAP 0x2 +#define LIQUIDIO_SPOOFCHK_CAP 0x4 + +/* error status return from firmware */ +#define OCTEON_REQUEST_NO_PERMISSION 0xc static inline u32 incr_index(u32 index, u32 count, u32 max) { @@ -241,6 +245,10 @@ static inline void add_sg_size(struct octeon_sg_entry *sg_entry, #define OCTNET_CMD_QUEUE_COUNT_CTL 0x1f +#define OCTNET_CMD_GROUP1 1 +#define OCTNET_CMD_SET_VF_SPOOFCHK 0x1 +#define OCTNET_GROUP1_LAST_CMD OCTNET_CMD_SET_VF_SPOOFCHK + #define OCTNET_CMD_VXLAN_PORT_ADD 0x0 #define OCTNET_CMD_VXLAN_PORT_DEL 0x1 #define OCTNET_CMD_RXCSUM_ENABLE 0x0 @@ -250,9 +258,18 @@ static inline void add_sg_size(struct octeon_sg_entry *sg_entry, #define OCTNET_CMD_VLAN_FILTER_ENABLE 0x1 #define OCTNET_CMD_VLAN_FILTER_DISABLE 0x0 +#define OCTNET_CMD_FAIL 0x1 + +#define SEAPI_CMD_FEC_SET 0x0 +#define SEAPI_CMD_FEC_SET_DISABLE 0x0 +#define SEAPI_CMD_FEC_SET_RS 0x1 +#define SEAPI_CMD_FEC_GET 0x1 + #define SEAPI_CMD_SPEED_SET 0x2 #define SEAPI_CMD_SPEED_GET 0x3 +#define OPCODE_NIC_VF_PORT_STATS 0x22 + #define LIO_CMD_WAIT_TM 100 /* RX(packets coming from wire) Checksum verification flags */ @@ -301,7 +318,8 @@ union octnet_cmd { u64 more:6; /* How many udd words follow the command */ - u64 reserved:29; + u64 cmdgroup:8; + u64 reserved:21; u64 param1:16; @@ -313,7 +331,8 @@ union octnet_cmd { u64 param1:16; - u64 reserved:29; + u64 reserved:21; + u64 cmdgroup:8; u64 more:6; @@ -757,13 +776,17 @@ struct oct_link_info { #ifdef __BIG_ENDIAN_BITFIELD u64 gmxport:16; u64 macaddr_is_admin_asgnd:1; - u64 rsvd:31; + u64 rsvd:13; + u64 macaddr_spoofchk:1; + u64 rsvd1:17; u64 num_txpciq:8; u64 num_rxpciq:8; #else u64 num_rxpciq:8; u64 num_txpciq:8; - u64 rsvd:31; + u64 rsvd1:17; + u64 macaddr_spoofchk:1; + u64 rsvd:13; u64 macaddr_is_admin_asgnd:1; u64 gmxport:16; #endif diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_config.h b/drivers/net/ethernet/cavium/liquidio/octeon_config.h index ceac74388e09..24c212001212 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_config.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_config.h @@ -438,9 +438,10 @@ struct octeon_config { #define MAX_BAR1_IOREMAP_SIZE (16 * OCTEON_BAR1_ENTRY_SIZE) /* Response lists - 1 ordered, 1 unordered-blocking, 1 unordered-nonblocking + * 1 process done list, 1 zombie lists(timeouted sc list) * NoResponse Lists are now maintained with each IQ. (Dec' 2007). */ -#define MAX_RESPONSE_LISTS 4 +#define MAX_RESPONSE_LISTS 6 /* Opcode hash bits. The opcode is hashed on the lower 6-bits to lookup the * dispatch table. diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.c b/drivers/net/ethernet/cavium/liquidio/octeon_device.c index f878a552fef3..0f0275cd153e 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_device.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.c @@ -1440,18 +1440,15 @@ void lio_enable_irq(struct octeon_droq *droq, struct octeon_instr_queue *iq) /* the whole thing needs to be atomic, ideally */ if (droq) { pkts_pend = (u32)atomic_read(&droq->pkts_pending); - spin_lock_bh(&droq->lock); writel(droq->pkt_count - pkts_pend, droq->pkts_sent_reg); droq->pkt_count = pkts_pend; - /* this write needs to be flushed before we release the lock */ - mmiowb(); - spin_unlock_bh(&droq->lock); oct = droq->oct_dev; } if (iq) { spin_lock_bh(&iq->lock); - writel(iq->pkt_in_done, iq->inst_cnt_reg); - iq->pkt_in_done = 0; + writel(iq->pkts_processed, iq->inst_cnt_reg); + iq->pkt_in_done -= iq->pkts_processed; + iq->pkts_processed = 0; /* this write needs to be flushed before we release the lock */ mmiowb(); spin_unlock_bh(&iq->lock); diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.h b/drivers/net/ethernet/cavium/liquidio/octeon_device.h index d99ca6ba23a4..3d01d3602d8f 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_device.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.h @@ -316,6 +316,8 @@ struct octdev_props { * device pointer (used for OS specific calls). */ int rx_on; + int fec; + int fec_boot; int napi_enabled; int gmxport; struct net_device *netdev; @@ -397,6 +399,8 @@ struct octeon_sriov_info { int vf_linkstate[MAX_POSSIBLE_VFS]; + bool vf_spoofchk[MAX_POSSIBLE_VFS]; + u64 vf_drv_loaded_mask; }; @@ -607,6 +611,9 @@ struct octeon_device { u8 speed_boot; u8 speed_setting; u8 no_speed_setting; + + u32 vfstats_poll; +#define LIO_VFSTATS_POLL 10 }; #define OCT_DRV_ONLINE 1 diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c index a71dbb7ab6af..a0c099f71524 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c @@ -301,8 +301,6 @@ int octeon_init_droq(struct octeon_device *oct, dev_dbg(&oct->pci_dev->dev, "DROQ INIT: max_empty_descs: %d\n", droq->max_empty_descs); - spin_lock_init(&droq->lock); - INIT_LIST_HEAD(&droq->dispatch_list); /* For 56xx Pass1, this function won't be called, so no checks. */ @@ -333,8 +331,6 @@ init_droq_fail: * Returns: * Success: Pointer to recv_info_t * Failure: NULL. - * Locks: - * The droq->lock is held when this routine is called. */ static inline struct octeon_recv_info *octeon_create_recv_info( struct octeon_device *octeon_dev, @@ -433,8 +429,6 @@ octeon_droq_refill_pullup_descs(struct octeon_droq *droq, * up buffers (that were not dispatched) to form a contiguous ring. * Returns: * No of descriptors refilled. - * Locks: - * This routine is called with droq->lock held. */ static u32 octeon_droq_refill(struct octeon_device *octeon_dev, struct octeon_droq *droq) @@ -449,8 +443,7 @@ octeon_droq_refill(struct octeon_device *octeon_dev, struct octeon_droq *droq) while (droq->refill_count && (desc_refilled < droq->max_count)) { /* If a valid buffer exists (happens if there is no dispatch), - * reuse - * the buffer, else allocate. + * reuse the buffer, else allocate. */ if (!droq->recv_buf_list[droq->refill_idx].buffer) { pg_info = @@ -503,34 +496,37 @@ octeon_droq_refill(struct octeon_device *octeon_dev, struct octeon_droq *droq) /** check if we can allocate packets to get out of oom. * @param droq - Droq being checked. - * @return does not return anything + * @return 1 if fails to refill minimum */ -void octeon_droq_check_oom(struct octeon_droq *droq) +int octeon_retry_droq_refill(struct octeon_droq *droq) { - int desc_refilled; struct octeon_device *oct = droq->oct_dev; + int desc_refilled, reschedule = 1; + u32 pkts_credit; + + pkts_credit = readl(droq->pkts_credit_reg); + desc_refilled = octeon_droq_refill(oct, droq); + if (desc_refilled) { + /* Flush the droq descriptor data to memory to be sure + * that when we update the credits the data in memory + * is accurate. + */ + wmb(); + writel(desc_refilled, droq->pkts_credit_reg); + /* make sure mmio write completes */ + mmiowb(); - if (readl(droq->pkts_credit_reg) <= CN23XX_SLI_DEF_BP) { - spin_lock_bh(&droq->lock); - desc_refilled = octeon_droq_refill(oct, droq); - if (desc_refilled) { - /* Flush the droq descriptor data to memory to be sure - * that when we update the credits the data in memory - * is accurate. - */ - wmb(); - writel(desc_refilled, droq->pkts_credit_reg); - /* make sure mmio write completes */ - mmiowb(); - } - spin_unlock_bh(&droq->lock); + if (pkts_credit + desc_refilled >= CN23XX_SLI_DEF_BP) + reschedule = 0; } + + return reschedule; } static inline u32 octeon_droq_get_bufcount(u32 buf_size, u32 total_len) { - return ((total_len + buf_size - 1) / buf_size); + return DIV_ROUND_UP(total_len, buf_size); } static int @@ -603,9 +599,9 @@ octeon_droq_fast_process_packets(struct octeon_device *oct, struct octeon_droq *droq, u32 pkts_to_process) { + u32 pkt, total_len = 0, pkt_count, retval; struct octeon_droq_info *info; union octeon_rh *rh; - u32 pkt, total_len = 0, pkt_count; pkt_count = pkts_to_process; @@ -709,30 +705,43 @@ octeon_droq_fast_process_packets(struct octeon_device *oct, if (droq->refill_count >= droq->refill_threshold) { int desc_refilled = octeon_droq_refill(oct, droq); - /* Flush the droq descriptor data to memory to be sure - * that when we update the credits the data in memory - * is accurate. - */ - wmb(); - writel((desc_refilled), droq->pkts_credit_reg); - /* make sure mmio write completes */ - mmiowb(); + if (desc_refilled) { + /* Flush the droq descriptor data to memory to + * be sure that when we update the credits the + * data in memory is accurate. + */ + wmb(); + writel(desc_refilled, droq->pkts_credit_reg); + /* make sure mmio write completes */ + mmiowb(); + } } - } /* for (each packet)... */ /* Increment refill_count by the number of buffers processed. */ droq->stats.pkts_received += pkt; droq->stats.bytes_received += total_len; + retval = pkt; if ((droq->ops.drop_on_max) && (pkts_to_process - pkt)) { octeon_droq_drop_packets(oct, droq, (pkts_to_process - pkt)); droq->stats.dropped_toomany += (pkts_to_process - pkt); - return pkts_to_process; + retval = pkts_to_process; + } + + atomic_sub(retval, &droq->pkts_pending); + + if (droq->refill_count >= droq->refill_threshold && + readl(droq->pkts_credit_reg) < CN23XX_SLI_DEF_BP) { + octeon_droq_check_hw_for_pkts(droq); + + /* Make sure there are no pkts_pending */ + if (!atomic_read(&droq->pkts_pending)) + octeon_schedule_rxq_oom_work(oct, droq); } - return pkt; + return retval; } int @@ -740,29 +749,19 @@ octeon_droq_process_packets(struct octeon_device *oct, struct octeon_droq *droq, u32 budget) { - u32 pkt_count = 0, pkts_processed = 0; + u32 pkt_count = 0; struct list_head *tmp, *tmp2; - /* Grab the droq lock */ - spin_lock(&droq->lock); - octeon_droq_check_hw_for_pkts(droq); pkt_count = atomic_read(&droq->pkts_pending); - if (!pkt_count) { - spin_unlock(&droq->lock); + if (!pkt_count) return 0; - } if (pkt_count > budget) pkt_count = budget; - pkts_processed = octeon_droq_fast_process_packets(oct, droq, pkt_count); - - atomic_sub(pkts_processed, &droq->pkts_pending); - - /* Release the spin lock */ - spin_unlock(&droq->lock); + octeon_droq_fast_process_packets(oct, droq, pkt_count); list_for_each_safe(tmp, tmp2, &droq->dispatch_list) { struct __dispatch *rdisp = (struct __dispatch *)tmp; @@ -798,8 +797,6 @@ octeon_droq_process_poll_pkts(struct octeon_device *oct, if (budget > droq->max_count) budget = droq->max_count; - spin_lock(&droq->lock); - while (total_pkts_processed < budget) { octeon_droq_check_hw_for_pkts(droq); @@ -813,13 +810,9 @@ octeon_droq_process_poll_pkts(struct octeon_device *oct, octeon_droq_fast_process_packets(oct, droq, pkts_available); - atomic_sub(pkts_processed, &droq->pkts_pending); - total_pkts_processed += pkts_processed; } - spin_unlock(&droq->lock); - list_for_each_safe(tmp, tmp2, &droq->dispatch_list) { struct __dispatch *rdisp = (struct __dispatch *)tmp; @@ -879,9 +872,8 @@ octeon_enable_irq(struct octeon_device *oct, u32 q_no) int octeon_register_droq_ops(struct octeon_device *oct, u32 q_no, struct octeon_droq_ops *ops) { - struct octeon_droq *droq; - unsigned long flags; struct octeon_config *oct_cfg = NULL; + struct octeon_droq *droq; oct_cfg = octeon_get_conf(oct); @@ -901,21 +893,15 @@ int octeon_register_droq_ops(struct octeon_device *oct, u32 q_no, } droq = oct->droq[q_no]; - - spin_lock_irqsave(&droq->lock, flags); - memcpy(&droq->ops, ops, sizeof(struct octeon_droq_ops)); - spin_unlock_irqrestore(&droq->lock, flags); - return 0; } int octeon_unregister_droq_ops(struct octeon_device *oct, u32 q_no) { - unsigned long flags; - struct octeon_droq *droq; struct octeon_config *oct_cfg = NULL; + struct octeon_droq *droq; oct_cfg = octeon_get_conf(oct); @@ -936,14 +922,10 @@ int octeon_unregister_droq_ops(struct octeon_device *oct, u32 q_no) return 0; } - spin_lock_irqsave(&droq->lock, flags); - droq->ops.fptr = NULL; droq->ops.farg = NULL; droq->ops.drop_on_max = 0; - spin_unlock_irqrestore(&droq->lock, flags); - return 0; } diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.h b/drivers/net/ethernet/cavium/liquidio/octeon_droq.h index f28f262d4ab6..c9b19e624dce 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.h @@ -245,9 +245,6 @@ struct octeon_droq_ops { * Octeon DROQ. */ struct octeon_droq { - /** A spinlock to protect access to this ring. */ - spinlock_t lock; - u32 q_no; u32 pkt_count; @@ -414,6 +411,6 @@ int octeon_droq_process_poll_pkts(struct octeon_device *oct, int octeon_enable_irq(struct octeon_device *oct, u32 q_no); -void octeon_droq_check_oom(struct octeon_droq *droq); +int octeon_retry_droq_refill(struct octeon_droq *droq); #endif /*__OCTEON_DROQ_H__ */ diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_iq.h b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h index 2327062e8af6..bebf3bd349c6 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_iq.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h @@ -94,6 +94,8 @@ struct octeon_instr_queue { u32 pkt_in_done; + u32 pkts_processed; + /** A spinlock to protect access to the input ring.*/ spinlock_t iq_flush_running_lock; @@ -290,13 +292,19 @@ struct octeon_soft_command { u32 ctxsize; /** Time out and callback */ - size_t wait_time; - size_t timeout; + size_t expiry_time; u32 iq_no; void (*callback)(struct octeon_device *, u32, void *); void *callback_arg; + + int caller_is_done; + u32 sc_status; + struct completion complete; }; +/* max timeout (in milli sec) for soft request */ +#define LIO_SC_MAX_TMO_MS 60000 + /** Maximum number of buffers to allocate into soft command buffer pool */ #define MAX_SOFT_COMMAND_BUFFERS 256 @@ -317,6 +325,8 @@ struct octeon_sc_buffer_pool { (((octeon_dev_ptr)->instr_queue[iq_no]->stats.field) += count) int octeon_setup_sc_buffer_pool(struct octeon_device *oct); +int octeon_free_sc_done_list(struct octeon_device *oct); +int octeon_free_sc_zombie_list(struct octeon_device *oct); int octeon_free_sc_buffer_pool(struct octeon_device *oct); struct octeon_soft_command * octeon_alloc_soft_command(struct octeon_device *oct, @@ -368,6 +378,9 @@ int octeon_send_command(struct octeon_device *oct, u32 iq_no, u32 force_db, void *cmd, void *buf, u32 datasize, u32 reqtype); +void octeon_dump_soft_command(struct octeon_device *oct, + struct octeon_soft_command *sc); + void octeon_prepare_soft_command(struct octeon_device *oct, struct octeon_soft_command *sc, u8 opcode, u8 subcode, diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_main.h b/drivers/net/ethernet/cavium/liquidio/octeon_main.h index c846eec11a45..073d0647b439 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_main.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_main.h @@ -70,6 +70,10 @@ void octeon_update_tx_completion_counters(void *buf, int reqtype, void octeon_report_tx_completion_to_bql(void *txq, unsigned int pkts_compl, unsigned int bytes_compl); void octeon_pf_changed_vf_macaddr(struct octeon_device *oct, u8 *mac); + +void octeon_schedule_rxq_oom_work(struct octeon_device *oct, + struct octeon_droq *droq); + /** Swap 8B blocks */ static inline void octeon_swap_8B_data(u64 *data, u32 blocks) { @@ -146,46 +150,70 @@ err_release_region: return 1; } +/* input parameter: + * sc: pointer to a soft request + * timeout: milli sec which an application wants to wait for the + response of the request. + * 0: the request will wait until its response gets back + * from the firmware within LIO_SC_MAX_TMO_MS milli sec. + * It the response does not return within + * LIO_SC_MAX_TMO_MS milli sec, lio_process_ordered_list() + * will move the request to zombie response list. + * + * return value: + * 0: got the response from firmware for the sc request. + * errno -EINTR: user abort the command. + * errno -ETIME: user spefified timeout value has been expired. + * errno -EBUSY: the response of the request does not return in + * resonable time (LIO_SC_MAX_TMO_MS). + * the sc wll be move to zombie response list by + * lio_process_ordered_list() + * + * A request with non-zero return value, the sc->caller_is_done + * will be marked 1. + * When getting a request with zero return value, the requestor + * should mark sc->caller_is_done with 1 after examing the + * response of sc. + * lio_process_ordered_list() will free the soft command on behalf + * of the soft command requestor. + * This is to fix the possible race condition of both timeout process + * and lio_process_ordered_list()/callback function to free a + * sc strucutre. + */ static inline int -sleep_cond(wait_queue_head_t *wait_queue, int *condition) +wait_for_sc_completion_timeout(struct octeon_device *oct_dev, + struct octeon_soft_command *sc, + unsigned long timeout) { int errno = 0; - wait_queue_entry_t we; - - init_waitqueue_entry(&we, current); - add_wait_queue(wait_queue, &we); - while (!(READ_ONCE(*condition))) { - set_current_state(TASK_INTERRUPTIBLE); - if (signal_pending(current)) { - errno = -EINTR; - goto out; - } - schedule(); + long timeout_jiff; + + if (timeout) + timeout_jiff = msecs_to_jiffies(timeout); + else + timeout_jiff = MAX_SCHEDULE_TIMEOUT; + + timeout_jiff = + wait_for_completion_interruptible_timeout(&sc->complete, + timeout_jiff); + if (timeout_jiff == 0) { + dev_err(&oct_dev->pci_dev->dev, "%s: sc is timeout\n", + __func__); + WRITE_ONCE(sc->caller_is_done, true); + errno = -ETIME; + } else if (timeout_jiff == -ERESTARTSYS) { + dev_err(&oct_dev->pci_dev->dev, "%s: sc is interrupted\n", + __func__); + WRITE_ONCE(sc->caller_is_done, true); + errno = -EINTR; + } else if (sc->sc_status == OCTEON_REQUEST_TIMEOUT) { + dev_err(&oct_dev->pci_dev->dev, "%s: sc has fatal timeout\n", + __func__); + WRITE_ONCE(sc->caller_is_done, true); + errno = -EBUSY; } -out: - set_current_state(TASK_RUNNING); - remove_wait_queue(wait_queue, &we); - return errno; -} -/* Gives up the CPU for a timeout period. - * Check that the condition is not true before we go to sleep for a - * timeout period. - */ -static inline void -sleep_timeout_cond(wait_queue_head_t *wait_queue, - int *condition, - int timeout) -{ - wait_queue_entry_t we; - - init_waitqueue_entry(&we, current); - add_wait_queue(wait_queue, &we); - set_current_state(TASK_INTERRUPTIBLE); - if (!(*condition)) - schedule_timeout(timeout); - set_current_state(TASK_RUNNING); - remove_wait_queue(wait_queue, &we); + return errno; } #ifndef ROUNDUP4 diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_network.h b/drivers/net/ethernet/cavium/liquidio/octeon_network.h index d7a3916fe877..50201fc86dcf 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_network.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_network.h @@ -35,12 +35,6 @@ #define LIO_IFSTATE_RX_TIMESTAMP_ENABLED 0x08 #define LIO_IFSTATE_RESETTING 0x10 -struct liquidio_if_cfg_context { - u32 octeon_id; - wait_queue_head_t wc; - int cond; -}; - struct liquidio_if_cfg_resp { u64 rh; struct liquidio_if_cfg_info cfg_info; @@ -48,6 +42,7 @@ struct liquidio_if_cfg_resp { }; #define LIO_IFCFG_WAIT_TIME 3000 /* In milli seconds */ +#define LIQUIDIO_NDEV_STATS_POLL_TIME_MS 200 /* Structure of a node in list of gather components maintained by * NIC driver for each network device. @@ -76,6 +71,12 @@ struct oct_nic_stats_resp { u64 status; }; +struct oct_nic_vf_stats_resp { + u64 rh; + u64 spoofmac_cnt; + u64 status; +}; + struct oct_nic_stats_ctrl { struct completion complete; struct net_device *netdev; @@ -83,16 +84,13 @@ struct oct_nic_stats_ctrl { struct oct_nic_seapi_resp { u64 rh; - u32 speed; + union { + u32 fec_setting; + u32 speed; + }; u64 status; }; -struct liquidio_nic_seapi_ctl_context { - int octeon_id; - u32 status; - struct completion complete; -}; - /** LiquidIO per-interface network private data */ struct lio { /** State of the interface. Rx/Tx happens only in the RUNNING state. */ @@ -178,7 +176,7 @@ struct lio { struct cavium_wq txq_status_wq; /* work queue for rxq oom status */ - struct cavium_wq rxq_status_wq; + struct cavium_wq rxq_status_wq[MAX_POSSIBLE_OCTEON_OUTPUT_QUEUES]; /* work queue for link status */ struct cavium_wq link_status_wq; @@ -187,6 +185,7 @@ struct lio { struct cavium_wq sync_octeon_time_wq; int netdev_uc_count; + struct cavium_wk stats_wk; }; #define LIO_SIZE (sizeof(struct lio)) @@ -225,7 +224,7 @@ irqreturn_t liquidio_msix_intr_handler(int irq __attribute__((unused)), int octeon_setup_interrupt(struct octeon_device *oct, u32 num_ioqs); -int octnet_get_link_stats(struct net_device *netdev); +void lio_fetch_stats(struct work_struct *work); int lio_wait_for_clean_oq(struct octeon_device *oct); /** @@ -234,16 +233,14 @@ int lio_wait_for_clean_oq(struct octeon_device *oct); */ void liquidio_set_ethtool_ops(struct net_device *netdev); -void lio_if_cfg_callback(struct octeon_device *oct, - u32 status __attribute__((unused)), - void *buf); - void lio_delete_glists(struct lio *lio); int lio_setup_glists(struct octeon_device *oct, struct lio *lio, int num_qs); int liquidio_get_speed(struct lio *lio); int liquidio_set_speed(struct lio *lio, int speed); +int liquidio_get_fec(struct lio *lio); +int liquidio_set_fec(struct lio *lio, int on_off); /** * \brief Net device change_mtu diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_nic.c b/drivers/net/ethernet/cavium/liquidio/octeon_nic.c index 150609bd8849..1a706f81bbb0 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_nic.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_nic.c @@ -75,8 +75,7 @@ octeon_alloc_soft_command_resp(struct octeon_device *oct, else sc->cmd.cmd2.rptr = sc->dmarptr; - sc->wait_time = 1000; - sc->timeout = jiffies + sc->wait_time; + sc->expiry_time = jiffies + msecs_to_jiffies(LIO_SC_MAX_TMO_MS); return sc; } @@ -92,29 +91,6 @@ int octnet_send_nic_data_pkt(struct octeon_device *oct, ndata->reqtype); } -static void octnet_link_ctrl_callback(struct octeon_device *oct, - u32 status, - void *sc_ptr) -{ - struct octeon_soft_command *sc = (struct octeon_soft_command *)sc_ptr; - struct octnic_ctrl_pkt *nctrl; - - nctrl = (struct octnic_ctrl_pkt *)sc->ctxptr; - - /* Call the callback function if status is zero (meaning OK) or status - * contains a firmware status code bigger than zero (meaning the - * firmware is reporting an error). - * If no response was expected, status is OK if the command was posted - * successfully. - */ - if ((!status || status > FIRMWARE_STATUS_CODE(0)) && nctrl->cb_fn) { - nctrl->status = status; - nctrl->cb_fn(nctrl); - } - - octeon_free_soft_command(oct, sc); -} - static inline struct octeon_soft_command *octnic_alloc_ctrl_pkt_sc(struct octeon_device *oct, struct octnic_ctrl_pkt *nctrl) @@ -127,17 +103,14 @@ static inline struct octeon_soft_command uddsize = (u32)(nctrl->ncmd.s.more * 8); datasize = OCTNET_CMD_SIZE + uddsize; - rdatasize = (nctrl->wait_time) ? 16 : 0; + rdatasize = 16; sc = (struct octeon_soft_command *) - octeon_alloc_soft_command(oct, datasize, rdatasize, - sizeof(struct octnic_ctrl_pkt)); + octeon_alloc_soft_command(oct, datasize, rdatasize, 0); if (!sc) return NULL; - memcpy(sc->ctxptr, nctrl, sizeof(struct octnic_ctrl_pkt)); - data = (u8 *)sc->virtdptr; memcpy(data, &nctrl->ncmd, OCTNET_CMD_SIZE); @@ -154,9 +127,8 @@ static inline struct octeon_soft_command octeon_prepare_soft_command(oct, sc, OPCODE_NIC, OPCODE_NIC_CMD, 0, 0, 0); - sc->callback = octnet_link_ctrl_callback; - sc->callback_arg = sc; - sc->wait_time = nctrl->wait_time; + init_completion(&sc->complete); + sc->sc_status = OCTEON_REQUEST_PENDING; return sc; } @@ -199,5 +171,28 @@ octnet_send_nic_ctrl_pkt(struct octeon_device *oct, } spin_unlock_bh(&oct->cmd_resp_wqlock); + + if (nctrl->ncmd.s.cmdgroup == 0) { + switch (nctrl->ncmd.s.cmd) { + /* caller holds lock, can not sleep */ + case OCTNET_CMD_CHANGE_DEVFLAGS: + case OCTNET_CMD_SET_MULTI_LIST: + case OCTNET_CMD_SET_UC_LIST: + WRITE_ONCE(sc->caller_is_done, true); + return retval; + } + } + + retval = wait_for_sc_completion_timeout(oct, sc, 0); + if (retval) + return (retval); + + nctrl->sc_status = sc->sc_status; + retval = nctrl->sc_status; + if (nctrl->cb_fn) + nctrl->cb_fn(nctrl); + + WRITE_ONCE(sc->caller_is_done, true); + return retval; } diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_nic.h b/drivers/net/ethernet/cavium/liquidio/octeon_nic.h index de4130d26a98..87dd6f89ce51 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_nic.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_nic.h @@ -52,20 +52,13 @@ struct octnic_ctrl_pkt { /** Input queue to use to send this command. */ u64 iq_no; - /** Time to wait for Octeon software to respond to this control command. - * If wait_time is 0, OSI assumes no response is expected. - */ - size_t wait_time; - /** The network device that issued the control command. */ u64 netpndev; /** Callback function called when the command has been fetched */ octnic_ctrl_pkt_cb_fn_t cb_fn; - u32 status; - u16 *response_code; - struct completion *completion; + u32 sc_status; }; #define MAX_UDD_SIZE(nctrl) (sizeof((nctrl)->udd)) diff --git a/drivers/net/ethernet/cavium/liquidio/request_manager.c b/drivers/net/ethernet/cavium/liquidio/request_manager.c index 8f746e1348d4..c6f4cbda040f 100644 --- a/drivers/net/ethernet/cavium/liquidio/request_manager.c +++ b/drivers/net/ethernet/cavium/liquidio/request_manager.c @@ -123,6 +123,7 @@ int octeon_init_instr_queue(struct octeon_device *oct, iq->do_auto_flush = 1; iq->db_timeout = (u32)conf->db_timeout; atomic_set(&iq->instr_pending, 0); + iq->pkts_processed = 0; /* Initialize the spinlock for this instruction queue */ spin_lock_init(&iq->lock); @@ -379,7 +380,6 @@ lio_process_iq_request_list(struct octeon_device *oct, u32 inst_count = 0; unsigned int pkts_compl = 0, bytes_compl = 0; struct octeon_soft_command *sc; - struct octeon_instr_irh *irh; unsigned long flags; while (old != iq->octeon_read_index) { @@ -401,40 +401,21 @@ lio_process_iq_request_list(struct octeon_device *oct, case REQTYPE_RESP_NET: case REQTYPE_SOFT_COMMAND: sc = buf; - - if (OCTEON_CN23XX_PF(oct) || OCTEON_CN23XX_VF(oct)) - irh = (struct octeon_instr_irh *) - &sc->cmd.cmd3.irh; - else - irh = (struct octeon_instr_irh *) - &sc->cmd.cmd2.irh; - if (irh->rflag) { - /* We're expecting a response from Octeon. - * It's up to lio_process_ordered_list() to - * process sc. Add sc to the ordered soft - * command response list because we expect - * a response from Octeon. - */ - spin_lock_irqsave - (&oct->response_list - [OCTEON_ORDERED_SC_LIST].lock, - flags); - atomic_inc(&oct->response_list - [OCTEON_ORDERED_SC_LIST]. - pending_req_count); - list_add_tail(&sc->node, &oct->response_list - [OCTEON_ORDERED_SC_LIST].head); - spin_unlock_irqrestore - (&oct->response_list - [OCTEON_ORDERED_SC_LIST].lock, - flags); - } else { - if (sc->callback) { - /* This callback must not sleep */ - sc->callback(oct, OCTEON_REQUEST_DONE, - sc->callback_arg); - } - } + /* We're expecting a response from Octeon. + * It's up to lio_process_ordered_list() to + * process sc. Add sc to the ordered soft + * command response list because we expect + * a response from Octeon. + */ + spin_lock_irqsave(&oct->response_list + [OCTEON_ORDERED_SC_LIST].lock, flags); + atomic_inc(&oct->response_list + [OCTEON_ORDERED_SC_LIST].pending_req_count); + list_add_tail(&sc->node, &oct->response_list + [OCTEON_ORDERED_SC_LIST].head); + spin_unlock_irqrestore(&oct->response_list + [OCTEON_ORDERED_SC_LIST].lock, + flags); break; default: dev_err(&oct->pci_dev->dev, @@ -459,7 +440,7 @@ lio_process_iq_request_list(struct octeon_device *oct, if (atomic_read(&oct->response_list [OCTEON_ORDERED_SC_LIST].pending_req_count)) - queue_delayed_work(cwq->wq, &cwq->wk.work, msecs_to_jiffies(1)); + queue_work(cwq->wq, &cwq->wk.work.work); return inst_count; } @@ -495,6 +476,7 @@ octeon_flush_iq(struct octeon_device *oct, struct octeon_instr_queue *iq, lio_process_iq_request_list(oct, iq, 0); if (inst_processed) { + iq->pkts_processed += inst_processed; atomic_sub(inst_processed, &iq->instr_pending); iq->stats.instr_processed += inst_processed; } @@ -753,8 +735,7 @@ int octeon_send_soft_command(struct octeon_device *oct, len = (u32)ih2->dlengsz; } - if (sc->wait_time) - sc->timeout = jiffies + sc->wait_time; + sc->expiry_time = jiffies + msecs_to_jiffies(LIO_SC_MAX_TMO_MS); return (octeon_send_command(oct, sc->iq_no, 1, &sc->cmd, sc, len, REQTYPE_SOFT_COMMAND)); @@ -789,11 +770,76 @@ int octeon_setup_sc_buffer_pool(struct octeon_device *oct) return 0; } +int octeon_free_sc_done_list(struct octeon_device *oct) +{ + struct octeon_response_list *done_sc_list, *zombie_sc_list; + struct octeon_soft_command *sc; + struct list_head *tmp, *tmp2; + spinlock_t *sc_lists_lock; /* lock for response_list */ + + done_sc_list = &oct->response_list[OCTEON_DONE_SC_LIST]; + zombie_sc_list = &oct->response_list[OCTEON_ZOMBIE_SC_LIST]; + + if (!atomic_read(&done_sc_list->pending_req_count)) + return 0; + + sc_lists_lock = &oct->response_list[OCTEON_ORDERED_SC_LIST].lock; + + spin_lock_bh(sc_lists_lock); + + list_for_each_safe(tmp, tmp2, &done_sc_list->head) { + sc = list_entry(tmp, struct octeon_soft_command, node); + + if (READ_ONCE(sc->caller_is_done)) { + list_del(&sc->node); + atomic_dec(&done_sc_list->pending_req_count); + + if (*sc->status_word == COMPLETION_WORD_INIT) { + /* timeout; move sc to zombie list */ + list_add_tail(&sc->node, &zombie_sc_list->head); + atomic_inc(&zombie_sc_list->pending_req_count); + } else { + octeon_free_soft_command(oct, sc); + } + } + } + + spin_unlock_bh(sc_lists_lock); + + return 0; +} + +int octeon_free_sc_zombie_list(struct octeon_device *oct) +{ + struct octeon_response_list *zombie_sc_list; + struct octeon_soft_command *sc; + struct list_head *tmp, *tmp2; + spinlock_t *sc_lists_lock; /* lock for response_list */ + + zombie_sc_list = &oct->response_list[OCTEON_ZOMBIE_SC_LIST]; + sc_lists_lock = &oct->response_list[OCTEON_ORDERED_SC_LIST].lock; + + spin_lock_bh(sc_lists_lock); + + list_for_each_safe(tmp, tmp2, &zombie_sc_list->head) { + list_del(tmp); + atomic_dec(&zombie_sc_list->pending_req_count); + sc = list_entry(tmp, struct octeon_soft_command, node); + octeon_free_soft_command(oct, sc); + } + + spin_unlock_bh(sc_lists_lock); + + return 0; +} + int octeon_free_sc_buffer_pool(struct octeon_device *oct) { struct list_head *tmp, *tmp2; struct octeon_soft_command *sc; + octeon_free_sc_zombie_list(oct); + spin_lock_bh(&oct->sc_buf_pool.lock); list_for_each_safe(tmp, tmp2, &oct->sc_buf_pool.head) { @@ -822,6 +868,9 @@ struct octeon_soft_command *octeon_alloc_soft_command(struct octeon_device *oct, struct octeon_soft_command *sc = NULL; struct list_head *tmp; + if (!rdatasize) + rdatasize = 16; + WARN_ON((offset + datasize + rdatasize + ctxsize) > SOFT_COMMAND_BUFFER_SIZE); diff --git a/drivers/net/ethernet/cavium/liquidio/response_manager.c b/drivers/net/ethernet/cavium/liquidio/response_manager.c index fe5b53700576..ac7747ccf56a 100644 --- a/drivers/net/ethernet/cavium/liquidio/response_manager.c +++ b/drivers/net/ethernet/cavium/liquidio/response_manager.c @@ -69,6 +69,8 @@ int lio_process_ordered_list(struct octeon_device *octeon_dev, u32 status; u64 status64; + octeon_free_sc_done_list(octeon_dev); + ordered_sc_list = &octeon_dev->response_list[OCTEON_ORDERED_SC_LIST]; do { @@ -111,26 +113,88 @@ int lio_process_ordered_list(struct octeon_device *octeon_dev, } } } - } else if (force_quit || (sc->timeout && - time_after(jiffies, (unsigned long)sc->timeout))) { - dev_err(&octeon_dev->pci_dev->dev, "%s: cmd failed, timeout (%ld, %ld)\n", - __func__, (long)jiffies, (long)sc->timeout); + } else if (unlikely(force_quit) || (sc->expiry_time && + time_after(jiffies, (unsigned long)sc->expiry_time))) { + struct octeon_instr_irh *irh = + (struct octeon_instr_irh *)&sc->cmd.cmd3.irh; + + dev_err(&octeon_dev->pci_dev->dev, "%s: ", __func__); + dev_err(&octeon_dev->pci_dev->dev, + "cmd %x/%x/%llx/%llx failed, ", + irh->opcode, irh->subcode, + sc->cmd.cmd3.ossp[0], sc->cmd.cmd3.ossp[1]); + dev_err(&octeon_dev->pci_dev->dev, + "timeout (%ld, %ld)\n", + (long)jiffies, (long)sc->expiry_time); status = OCTEON_REQUEST_TIMEOUT; } if (status != OCTEON_REQUEST_PENDING) { + sc->sc_status = status; + /* we have received a response or we have timed out */ /* remove node from linked list */ list_del(&sc->node); atomic_dec(&octeon_dev->response_list - [OCTEON_ORDERED_SC_LIST]. - pending_req_count); - spin_unlock_bh - (&ordered_sc_list->lock); + [OCTEON_ORDERED_SC_LIST]. + pending_req_count); + + if (!sc->callback) { + atomic_inc(&octeon_dev->response_list + [OCTEON_DONE_SC_LIST]. + pending_req_count); + list_add_tail(&sc->node, + &octeon_dev->response_list + [OCTEON_DONE_SC_LIST].head); + + if (unlikely(READ_ONCE(sc->caller_is_done))) { + /* caller does not wait for response + * from firmware + */ + if (status != OCTEON_REQUEST_DONE) { + struct octeon_instr_irh *irh; + + irh = + (struct octeon_instr_irh *) + &sc->cmd.cmd3.irh; + dev_dbg + (&octeon_dev->pci_dev->dev, + "%s: sc failed: opcode=%x, ", + __func__, irh->opcode); + dev_dbg + (&octeon_dev->pci_dev->dev, + "subcode=%x, ossp[0]=%llx, ", + irh->subcode, + sc->cmd.cmd3.ossp[0]); + dev_dbg + (&octeon_dev->pci_dev->dev, + "ossp[1]=%llx, status=%d\n", + sc->cmd.cmd3.ossp[1], + status); + } + } else { + complete(&sc->complete); + } + + spin_unlock_bh(&ordered_sc_list->lock); + } else { + /* sc with callback function */ + if (status == OCTEON_REQUEST_TIMEOUT) { + atomic_inc(&octeon_dev->response_list + [OCTEON_ZOMBIE_SC_LIST]. + pending_req_count); + list_add_tail(&sc->node, + &octeon_dev->response_list + [OCTEON_ZOMBIE_SC_LIST]. + head); + } + + spin_unlock_bh(&ordered_sc_list->lock); - if (sc->callback) sc->callback(octeon_dev, status, sc->callback_arg); + /* sc is freed by caller */ + } request_complete++; diff --git a/drivers/net/ethernet/cavium/liquidio/response_manager.h b/drivers/net/ethernet/cavium/liquidio/response_manager.h index 9169c2815dba..ed4020d26fae 100644 --- a/drivers/net/ethernet/cavium/liquidio/response_manager.h +++ b/drivers/net/ethernet/cavium/liquidio/response_manager.h @@ -53,7 +53,9 @@ enum { OCTEON_ORDERED_LIST = 0, OCTEON_UNORDERED_NONBLOCKING_LIST = 1, OCTEON_UNORDERED_BLOCKING_LIST = 2, - OCTEON_ORDERED_SC_LIST = 3 + OCTEON_ORDERED_SC_LIST = 3, + OCTEON_DONE_SC_LIST = 4, + OCTEON_ZOMBIE_SC_LIST = 5 }; /** Response Order values for a Octeon Request. */ diff --git a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c index bb43ddb7539e..4b3aecf98f2a 100644 --- a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c +++ b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c @@ -1268,12 +1268,13 @@ static int octeon_mgmt_stop(struct net_device *netdev) return 0; } -static int octeon_mgmt_xmit(struct sk_buff *skb, struct net_device *netdev) +static netdev_tx_t +octeon_mgmt_xmit(struct sk_buff *skb, struct net_device *netdev) { struct octeon_mgmt *p = netdev_priv(netdev); union mgmt_port_ring_entry re; unsigned long flags; - int rv = NETDEV_TX_BUSY; + netdev_tx_t rv = NETDEV_TX_BUSY; re.d64 = 0; re.s.tstamp = ((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) != 0); diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c index a19172dbe6be..921dd71f9cda 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c +++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c @@ -33,7 +33,6 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> -#include <linux/moduleparam.h> #include <linux/init.h> #include <linux/pci.h> #include <linux/dma-mapping.h> diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h index 36d25883d123..b2d617abcf49 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h @@ -315,6 +315,48 @@ struct cudbg_pbt_tables { u32 pbt_data[CUDBG_PBT_DATA_ENTRIES]; }; +enum cudbg_qdesc_qtype { + CUDBG_QTYPE_UNKNOWN = 0, + CUDBG_QTYPE_NIC_TXQ, + CUDBG_QTYPE_NIC_RXQ, + CUDBG_QTYPE_NIC_FLQ, + CUDBG_QTYPE_CTRLQ, + CUDBG_QTYPE_FWEVTQ, + CUDBG_QTYPE_INTRQ, + CUDBG_QTYPE_PTP_TXQ, + CUDBG_QTYPE_OFLD_TXQ, + CUDBG_QTYPE_RDMA_RXQ, + CUDBG_QTYPE_RDMA_FLQ, + CUDBG_QTYPE_RDMA_CIQ, + CUDBG_QTYPE_ISCSI_RXQ, + CUDBG_QTYPE_ISCSI_FLQ, + CUDBG_QTYPE_ISCSIT_RXQ, + CUDBG_QTYPE_ISCSIT_FLQ, + CUDBG_QTYPE_CRYPTO_TXQ, + CUDBG_QTYPE_CRYPTO_RXQ, + CUDBG_QTYPE_CRYPTO_FLQ, + CUDBG_QTYPE_TLS_RXQ, + CUDBG_QTYPE_TLS_FLQ, + CUDBG_QTYPE_MAX, +}; + +#define CUDBG_QDESC_REV 1 + +struct cudbg_qdesc_entry { + u32 data_size; + u32 qtype; + u32 qid; + u32 desc_size; + u32 num_desc; + u8 data[0]; /* Must be last */ +}; + +struct cudbg_qdesc_info { + u32 qdesc_entry_size; + u32 num_queues; + u8 data[0]; /* Must be last */ +}; + #define IREG_NUM_ELEM 4 static const u32 t6_tp_pio_array[][IREG_NUM_ELEM] = { diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h index 215fe6260fd7..dec63c15c0ba 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_if.h @@ -81,7 +81,8 @@ enum cudbg_dbg_entity_type { CUDBG_MBOX_LOG = 66, CUDBG_HMA_INDIRECT = 67, CUDBG_HMA = 68, - CUDBG_MAX_ENTITY = 70, + CUDBG_QDESC = 70, + CUDBG_MAX_ENTITY = 71, }; struct cudbg_init { diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c index d97e0d7e541a..7c49681407ad 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c @@ -19,6 +19,7 @@ #include "t4_regs.h" #include "cxgb4.h" +#include "cxgb4_cudbg.h" #include "cudbg_if.h" #include "cudbg_lib_common.h" #include "cudbg_entity.h" @@ -2890,3 +2891,240 @@ int cudbg_collect_hma_indirect(struct cudbg_init *pdbg_init, } return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff); } + +void cudbg_fill_qdesc_num_and_size(const struct adapter *padap, + u32 *num, u32 *size) +{ + u32 tot_entries = 0, tot_size = 0; + + /* NIC TXQ, RXQ, FLQ, and CTRLQ */ + tot_entries += MAX_ETH_QSETS * 3; + tot_entries += MAX_CTRL_QUEUES; + + tot_size += MAX_ETH_QSETS * MAX_TXQ_ENTRIES * MAX_TXQ_DESC_SIZE; + tot_size += MAX_ETH_QSETS * MAX_RSPQ_ENTRIES * MAX_RXQ_DESC_SIZE; + tot_size += MAX_ETH_QSETS * MAX_RX_BUFFERS * MAX_FL_DESC_SIZE; + tot_size += MAX_CTRL_QUEUES * MAX_CTRL_TXQ_ENTRIES * + MAX_CTRL_TXQ_DESC_SIZE; + + /* FW_EVTQ and INTRQ */ + tot_entries += INGQ_EXTRAS; + tot_size += INGQ_EXTRAS * MAX_RSPQ_ENTRIES * MAX_RXQ_DESC_SIZE; + + /* PTP_TXQ */ + tot_entries += 1; + tot_size += MAX_TXQ_ENTRIES * MAX_TXQ_DESC_SIZE; + + /* ULD TXQ, RXQ, and FLQ */ + tot_entries += CXGB4_TX_MAX * MAX_OFLD_QSETS; + tot_entries += CXGB4_ULD_MAX * MAX_ULD_QSETS * 2; + + tot_size += CXGB4_TX_MAX * MAX_OFLD_QSETS * MAX_TXQ_ENTRIES * + MAX_TXQ_DESC_SIZE; + tot_size += CXGB4_ULD_MAX * MAX_ULD_QSETS * MAX_RSPQ_ENTRIES * + MAX_RXQ_DESC_SIZE; + tot_size += CXGB4_ULD_MAX * MAX_ULD_QSETS * MAX_RX_BUFFERS * + MAX_FL_DESC_SIZE; + + /* ULD CIQ */ + tot_entries += CXGB4_ULD_MAX * MAX_ULD_QSETS; + tot_size += CXGB4_ULD_MAX * MAX_ULD_QSETS * SGE_MAX_IQ_SIZE * + MAX_RXQ_DESC_SIZE; + + tot_size += sizeof(struct cudbg_ver_hdr) + + sizeof(struct cudbg_qdesc_info) + + sizeof(struct cudbg_qdesc_entry) * tot_entries; + + if (num) + *num = tot_entries; + + if (size) + *size = tot_size; +} + +int cudbg_collect_qdesc(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err) +{ + u32 num_queues = 0, tot_entries = 0, size = 0; + struct adapter *padap = pdbg_init->adap; + struct cudbg_buffer temp_buff = { 0 }; + struct cudbg_qdesc_entry *qdesc_entry; + struct cudbg_qdesc_info *qdesc_info; + struct cudbg_ver_hdr *ver_hdr; + struct sge *s = &padap->sge; + u32 i, j, cur_off, tot_len; + u8 *data; + int rc; + + cudbg_fill_qdesc_num_and_size(padap, &tot_entries, &size); + size = min_t(u32, size, CUDBG_DUMP_BUFF_SIZE); + tot_len = size; + data = kvzalloc(size, GFP_KERNEL); + if (!data) + return -ENOMEM; + + ver_hdr = (struct cudbg_ver_hdr *)data; + ver_hdr->signature = CUDBG_ENTITY_SIGNATURE; + ver_hdr->revision = CUDBG_QDESC_REV; + ver_hdr->size = sizeof(struct cudbg_qdesc_info); + size -= sizeof(*ver_hdr); + + qdesc_info = (struct cudbg_qdesc_info *)(data + + sizeof(*ver_hdr)); + size -= sizeof(*qdesc_info); + qdesc_entry = (struct cudbg_qdesc_entry *)qdesc_info->data; + +#define QDESC_GET(q, desc, type, label) do { \ + if (size <= 0) { \ + goto label; \ + } \ + if (desc) { \ + cudbg_fill_qdesc_##q(q, type, qdesc_entry); \ + size -= sizeof(*qdesc_entry) + qdesc_entry->data_size; \ + num_queues++; \ + qdesc_entry = cudbg_next_qdesc(qdesc_entry); \ + } \ +} while (0) + +#define QDESC_GET_TXQ(q, type, label) do { \ + struct sge_txq *txq = (struct sge_txq *)q; \ + QDESC_GET(txq, txq->desc, type, label); \ +} while (0) + +#define QDESC_GET_RXQ(q, type, label) do { \ + struct sge_rspq *rxq = (struct sge_rspq *)q; \ + QDESC_GET(rxq, rxq->desc, type, label); \ +} while (0) + +#define QDESC_GET_FLQ(q, type, label) do { \ + struct sge_fl *flq = (struct sge_fl *)q; \ + QDESC_GET(flq, flq->desc, type, label); \ +} while (0) + + /* NIC TXQ */ + for (i = 0; i < s->ethqsets; i++) + QDESC_GET_TXQ(&s->ethtxq[i].q, CUDBG_QTYPE_NIC_TXQ, out); + + /* NIC RXQ */ + for (i = 0; i < s->ethqsets; i++) + QDESC_GET_RXQ(&s->ethrxq[i].rspq, CUDBG_QTYPE_NIC_RXQ, out); + + /* NIC FLQ */ + for (i = 0; i < s->ethqsets; i++) + QDESC_GET_FLQ(&s->ethrxq[i].fl, CUDBG_QTYPE_NIC_FLQ, out); + + /* NIC CTRLQ */ + for (i = 0; i < padap->params.nports; i++) + QDESC_GET_TXQ(&s->ctrlq[i].q, CUDBG_QTYPE_CTRLQ, out); + + /* FW_EVTQ */ + QDESC_GET_RXQ(&s->fw_evtq, CUDBG_QTYPE_FWEVTQ, out); + + /* INTRQ */ + QDESC_GET_RXQ(&s->intrq, CUDBG_QTYPE_INTRQ, out); + + /* PTP_TXQ */ + QDESC_GET_TXQ(&s->ptptxq.q, CUDBG_QTYPE_PTP_TXQ, out); + + /* ULD Queues */ + mutex_lock(&uld_mutex); + + if (s->uld_txq_info) { + struct sge_uld_txq_info *utxq; + + /* ULD TXQ */ + for (j = 0; j < CXGB4_TX_MAX; j++) { + if (!s->uld_txq_info[j]) + continue; + + utxq = s->uld_txq_info[j]; + for (i = 0; i < utxq->ntxq; i++) + QDESC_GET_TXQ(&utxq->uldtxq[i].q, + cudbg_uld_txq_to_qtype(j), + out_unlock); + } + } + + if (s->uld_rxq_info) { + struct sge_uld_rxq_info *urxq; + u32 base; + + /* ULD RXQ */ + for (j = 0; j < CXGB4_ULD_MAX; j++) { + if (!s->uld_rxq_info[j]) + continue; + + urxq = s->uld_rxq_info[j]; + for (i = 0; i < urxq->nrxq; i++) + QDESC_GET_RXQ(&urxq->uldrxq[i].rspq, + cudbg_uld_rxq_to_qtype(j), + out_unlock); + } + + /* ULD FLQ */ + for (j = 0; j < CXGB4_ULD_MAX; j++) { + if (!s->uld_rxq_info[j]) + continue; + + urxq = s->uld_rxq_info[j]; + for (i = 0; i < urxq->nrxq; i++) + QDESC_GET_FLQ(&urxq->uldrxq[i].fl, + cudbg_uld_flq_to_qtype(j), + out_unlock); + } + + /* ULD CIQ */ + for (j = 0; j < CXGB4_ULD_MAX; j++) { + if (!s->uld_rxq_info[j]) + continue; + + urxq = s->uld_rxq_info[j]; + base = urxq->nrxq; + for (i = 0; i < urxq->nciq; i++) + QDESC_GET_RXQ(&urxq->uldrxq[base + i].rspq, + cudbg_uld_ciq_to_qtype(j), + out_unlock); + } + } + +out_unlock: + mutex_unlock(&uld_mutex); + +out: + qdesc_info->qdesc_entry_size = sizeof(*qdesc_entry); + qdesc_info->num_queues = num_queues; + cur_off = 0; + while (tot_len) { + u32 chunk_size = min_t(u32, tot_len, CUDBG_CHUNK_SIZE); + + rc = cudbg_get_buff(pdbg_init, dbg_buff, chunk_size, + &temp_buff); + if (rc) { + cudbg_err->sys_warn = CUDBG_STATUS_PARTIAL_DATA; + goto out_free; + } + + memcpy(temp_buff.data, data + cur_off, chunk_size); + tot_len -= chunk_size; + cur_off += chunk_size; + rc = cudbg_write_and_release_buff(pdbg_init, &temp_buff, + dbg_buff); + if (rc) { + cudbg_put_buff(pdbg_init, &temp_buff); + cudbg_err->sys_warn = CUDBG_STATUS_PARTIAL_DATA; + goto out_free; + } + } + +out_free: + if (data) + kvfree(data); + +#undef QDESC_GET_FLQ +#undef QDESC_GET_RXQ +#undef QDESC_GET_TXQ +#undef QDESC_GET + + return rc; +} diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h index eebefe7cd18e..f047a01a3e5b 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.h @@ -171,6 +171,9 @@ int cudbg_collect_hma_indirect(struct cudbg_init *pdbg_init, int cudbg_collect_hma_meminfo(struct cudbg_init *pdbg_init, struct cudbg_buffer *dbg_buff, struct cudbg_error *cudbg_err); +int cudbg_collect_qdesc(struct cudbg_init *pdbg_init, + struct cudbg_buffer *dbg_buff, + struct cudbg_error *cudbg_err); struct cudbg_entity_hdr *cudbg_get_entity_hdr(void *outbuf, int i); void cudbg_align_debug_buffer(struct cudbg_buffer *dbg_buff, @@ -182,4 +185,107 @@ int cudbg_fill_meminfo(struct adapter *padap, struct cudbg_meminfo *meminfo_buff); void cudbg_fill_le_tcam_info(struct adapter *padap, struct cudbg_tcam *tcam_region); +void cudbg_fill_qdesc_num_and_size(const struct adapter *padap, + u32 *num, u32 *size); + +static inline u32 cudbg_uld_txq_to_qtype(u32 uld) +{ + switch (uld) { + case CXGB4_TX_OFLD: + return CUDBG_QTYPE_OFLD_TXQ; + case CXGB4_TX_CRYPTO: + return CUDBG_QTYPE_CRYPTO_TXQ; + } + + return CUDBG_QTYPE_UNKNOWN; +} + +static inline u32 cudbg_uld_rxq_to_qtype(u32 uld) +{ + switch (uld) { + case CXGB4_ULD_RDMA: + return CUDBG_QTYPE_RDMA_RXQ; + case CXGB4_ULD_ISCSI: + return CUDBG_QTYPE_ISCSI_RXQ; + case CXGB4_ULD_ISCSIT: + return CUDBG_QTYPE_ISCSIT_RXQ; + case CXGB4_ULD_CRYPTO: + return CUDBG_QTYPE_CRYPTO_RXQ; + case CXGB4_ULD_TLS: + return CUDBG_QTYPE_TLS_RXQ; + } + + return CUDBG_QTYPE_UNKNOWN; +} + +static inline u32 cudbg_uld_flq_to_qtype(u32 uld) +{ + switch (uld) { + case CXGB4_ULD_RDMA: + return CUDBG_QTYPE_RDMA_FLQ; + case CXGB4_ULD_ISCSI: + return CUDBG_QTYPE_ISCSI_FLQ; + case CXGB4_ULD_ISCSIT: + return CUDBG_QTYPE_ISCSIT_FLQ; + case CXGB4_ULD_CRYPTO: + return CUDBG_QTYPE_CRYPTO_FLQ; + case CXGB4_ULD_TLS: + return CUDBG_QTYPE_TLS_FLQ; + } + + return CUDBG_QTYPE_UNKNOWN; +} + +static inline u32 cudbg_uld_ciq_to_qtype(u32 uld) +{ + switch (uld) { + case CXGB4_ULD_RDMA: + return CUDBG_QTYPE_RDMA_CIQ; + } + + return CUDBG_QTYPE_UNKNOWN; +} + +static inline void cudbg_fill_qdesc_txq(const struct sge_txq *txq, + enum cudbg_qdesc_qtype type, + struct cudbg_qdesc_entry *entry) +{ + entry->qtype = type; + entry->qid = txq->cntxt_id; + entry->desc_size = sizeof(struct tx_desc); + entry->num_desc = txq->size; + entry->data_size = txq->size * sizeof(struct tx_desc); + memcpy(entry->data, txq->desc, entry->data_size); +} + +static inline void cudbg_fill_qdesc_rxq(const struct sge_rspq *rxq, + enum cudbg_qdesc_qtype type, + struct cudbg_qdesc_entry *entry) +{ + entry->qtype = type; + entry->qid = rxq->cntxt_id; + entry->desc_size = rxq->iqe_len; + entry->num_desc = rxq->size; + entry->data_size = rxq->size * rxq->iqe_len; + memcpy(entry->data, rxq->desc, entry->data_size); +} + +static inline void cudbg_fill_qdesc_flq(const struct sge_fl *flq, + enum cudbg_qdesc_qtype type, + struct cudbg_qdesc_entry *entry) +{ + entry->qtype = type; + entry->qid = flq->cntxt_id; + entry->desc_size = sizeof(__be64); + entry->num_desc = flq->size; + entry->data_size = flq->size * sizeof(__be64); + memcpy(entry->data, flq->desc, entry->data_size); +} + +static inline +struct cudbg_qdesc_entry *cudbg_next_qdesc(struct cudbg_qdesc_entry *e) +{ + return (struct cudbg_qdesc_entry *) + ((u8 *)e + sizeof(*e) + e->data_size); +} #endif /* __CUDBG_LIB_H__ */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index 76d16747f513..b5010bd32ea3 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -533,6 +533,13 @@ enum { }; enum { + MAX_TXQ_DESC_SIZE = 64, + MAX_RXQ_DESC_SIZE = 128, + MAX_FL_DESC_SIZE = 8, + MAX_CTRL_TXQ_DESC_SIZE = 64, +}; + +enum { INGQ_EXTRAS = 2, /* firmware event queue and */ /* forwarded interrupts */ MAX_INGQ = MAX_ETH_QSETS + INGQ_EXTRAS, @@ -685,6 +692,7 @@ struct sge_eth_stats { /* Ethernet queue statistics */ unsigned long rx_cso; /* # of Rx checksum offloads */ unsigned long vlan_ex; /* # of Rx VLAN extractions */ unsigned long rx_drops; /* # of packets dropped due to no mem */ + unsigned long bad_rx_pkts; /* # of packets with err_vec!=0 */ }; struct sge_eth_rxq { /* SW Ethernet Rx queue */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c index 5f01c0a7fd98..972f0a124714 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c @@ -30,6 +30,7 @@ static const struct cxgb4_collect_entity cxgb4_collect_mem_dump[] = { static const struct cxgb4_collect_entity cxgb4_collect_hw_dump[] = { { CUDBG_MBOX_LOG, cudbg_collect_mbox_log }, + { CUDBG_QDESC, cudbg_collect_qdesc }, { CUDBG_DEV_LOG, cudbg_collect_fw_devlog }, { CUDBG_REG_DUMP, cudbg_collect_reg_dump }, { CUDBG_CIM_LA, cudbg_collect_cim_la }, @@ -311,6 +312,9 @@ static u32 cxgb4_get_entity_length(struct adapter *adap, u32 entity) } len = cudbg_mbytes_to_bytes(len); break; + case CUDBG_QDESC: + cudbg_fill_qdesc_num_and_size(adap, NULL, &len); + break; default: break; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c index b34f0f077a31..6ba3104ff7eb 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c @@ -114,6 +114,24 @@ void cxgb4_dcb_reset(struct net_device *dev) cxgb4_dcb_state_init(dev); } +/* update the dcb port support, if version is IEEE then set it to + * FW_PORT_DCB_VER_IEEE and if DCB_CAP_DCBX_VER_CEE is already set then + * clear that. and if it is set to CEE then set dcb supported to + * DCB_CAP_DCBX_VER_CEE & if DCB_CAP_DCBX_VER_IEEE is set, clear it + */ +static inline void cxgb4_dcb_update_support(struct port_dcb_info *dcb) +{ + if (dcb->dcb_version == FW_PORT_DCB_VER_IEEE) { + if (dcb->supported & DCB_CAP_DCBX_VER_CEE) + dcb->supported &= ~DCB_CAP_DCBX_VER_CEE; + dcb->supported |= DCB_CAP_DCBX_VER_IEEE; + } else if (dcb->dcb_version == FW_PORT_DCB_VER_CEE1D01) { + if (dcb->supported & DCB_CAP_DCBX_VER_IEEE) + dcb->supported &= ~DCB_CAP_DCBX_VER_IEEE; + dcb->supported |= DCB_CAP_DCBX_VER_CEE; + } +} + /* Finite State machine for Data Center Bridging. */ void cxgb4_dcb_state_fsm(struct net_device *dev, @@ -165,6 +183,15 @@ void cxgb4_dcb_state_fsm(struct net_device *dev, } case CXGB4_DCB_STATE_FW_INCOMPLETE: { + if (transition_to != CXGB4_DCB_INPUT_FW_DISABLED) { + /* during this CXGB4_DCB_STATE_FW_INCOMPLETE state, + * check if the dcb version is changed (there can be + * mismatch in default config & the negotiated switch + * configuration at FW, so update the dcb support + * accordingly. + */ + cxgb4_dcb_update_support(dcb); + } switch (transition_to) { case CXGB4_DCB_INPUT_FW_ENABLED: { /* we're alreaady in firmware DCB mode */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c index 0f72f9c4ec74..cab492ec8f59 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c @@ -2784,6 +2784,7 @@ do { \ RL("LROmerged:", stats.lro_merged); RL("LROpackets:", stats.lro_pkts); RL("RxDrops:", stats.rx_drops); + RL("RxBadPkts:", stats.bad_rx_pkts); TL("TSO:", tso); TL("TxCSO:", tx_cso); TL("VLANins:", vlan_ins); diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 961e3087d1d3..1a93efa60e71 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -62,7 +62,6 @@ #include <net/netevent.h> #include <net/addrconf.h> #include <net/bonding.h> -#include <net/addrconf.h> #include <linux/uaccess.h> #include <linux/crash_dump.h> #include <net/udp_tunnel.h> @@ -2749,6 +2748,27 @@ static int cxgb4_mgmt_set_vf_rate(struct net_device *dev, int vf, return -EINVAL; } + if (max_tx_rate == 0) { + /* unbind VF to to any Traffic Class */ + fw_pfvf = + (FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_PFVF) | + FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_PFVF_SCHEDCLASS_ETH)); + fw_class = 0xffffffff; + ret = t4_set_params(adap, adap->mbox, adap->pf, vf + 1, 1, + &fw_pfvf, &fw_class); + if (ret) { + dev_err(adap->pdev_dev, + "Err %d in unbinding PF %d VF %d from TX Rate Limiting\n", + ret, adap->pf, vf); + return -EINVAL; + } + dev_info(adap->pdev_dev, + "PF %d VF %d is unbound from TX Rate Limiting\n", + adap->pf, vf); + adap->vfinfo[vf].tx_rate = 0; + return 0; + } + ret = t4_get_link_params(pi, &link_ok, &speed, &mtu); if (ret != FW_SUCCESS) { dev_err(adap->pdev_dev, @@ -2798,8 +2818,8 @@ static int cxgb4_mgmt_set_vf_rate(struct net_device *dev, int vf, &fw_class); if (ret) { dev_err(adap->pdev_dev, - "Err %d in binding VF %d to Traffic Class %d\n", - ret, vf, class_id); + "Err %d in binding PF %d VF %d to Traffic Class %d\n", + ret, adap->pf, vf, class_id); return -EINVAL; } dev_info(adap->pdev_dev, "PF %d VF %d is bound to Class %d\n", diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c index 623f73dd7738..c116f96956fe 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c @@ -417,10 +417,9 @@ static void cxgb4_process_flow_actions(struct net_device *in, struct ch_filter_specification *fs) { const struct tc_action *a; - LIST_HEAD(actions); + int i; - tcf_exts_to_list(cls->exts, &actions); - list_for_each_entry(a, &actions, list) { + tcf_exts_for_each_action(i, a, cls->exts) { if (is_tcf_gact_ok(a)) { fs->action = FILTER_PASS; } else if (is_tcf_gact_shot(a)) { @@ -591,10 +590,9 @@ static int cxgb4_validate_flow_actions(struct net_device *dev, bool act_redir = false; bool act_pedit = false; bool act_vlan = false; - LIST_HEAD(actions); + int i; - tcf_exts_to_list(cls->exts, &actions); - list_for_each_entry(a, &actions, list) { + tcf_exts_for_each_action(i, a, cls->exts) { if (is_tcf_gact_ok(a)) { /* Do nothing */ } else if (is_tcf_gact_shot(a)) { diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c index 18eb2aedd4cb..c7d2b4dc7568 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_u32.c @@ -93,14 +93,13 @@ static int fill_action_fields(struct adapter *adap, unsigned int num_actions = 0; const struct tc_action *a; struct tcf_exts *exts; - LIST_HEAD(actions); + int i; exts = cls->knode.exts; if (!tcf_exts_has_actions(exts)) return -EINVAL; - tcf_exts_to_list(exts, &actions); - list_for_each_entry(a, &actions, list) { + tcf_exts_for_each_action(i, a, exts) { /* Don't allow more than one action per rule. */ if (num_actions) return -EINVAL; diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.c b/drivers/net/ethernet/chelsio/cxgb4/l2t.c index 301c4df8a566..99022c0898b5 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/l2t.c +++ b/drivers/net/ethernet/chelsio/cxgb4/l2t.c @@ -433,10 +433,12 @@ struct l2t_entry *cxgb4_l2t_get(struct l2t_data *d, struct neighbour *neigh, else lport = netdev2pinfo(physdev)->lport; - if (is_vlan_dev(neigh->dev)) + if (is_vlan_dev(neigh->dev)) { vlan = vlan_dev_vlan_id(neigh->dev); - else + vlan |= vlan_dev_get_egress_qos_mask(neigh->dev, priority); + } else { vlan = VLAN_NONE; + } write_lock_bh(&d->lock); for (e = d->l2tab[hash].first; e; e = e->next) diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index 6807bc3a44fb..b90188401d4a 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -2830,6 +2830,10 @@ int t4_ethrx_handler(struct sge_rspq *q, const __be64 *rsp, csum_ok = pkt->csum_calc && !err_vec && (q->netdev->features & NETIF_F_RXCSUM); + + if (err_vec) + rxq->stats.bad_rx_pkts++; + if (((pkt->l2info & htonl(RXF_TCP_F)) || tnl_hdr_len) && (q->netdev->features & NETIF_F_GRO) && csum_ok && !pkt->ip_frag) { diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 5fe5d16dee72..f85eab57e9e1 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -3889,7 +3889,7 @@ int t4_fwcache(struct adapter *adap, enum fw_params_param_dev_fwcache op) c.param[0].mnem = cpu_to_be32(FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) | FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_FWCACHE)); - c.param[0].val = (__force __be32)op; + c.param[0].val = cpu_to_be32(op); return t4_wr_mbox(adap, adap->mbox, &c, sizeof(c), NULL); } @@ -10209,7 +10209,9 @@ int t4_set_vlan_acl(struct adapter *adap, unsigned int mbox, unsigned int vf, FW_ACL_VLAN_CMD_VFN_V(vf)); vlan_cmd.en_to_len16 = cpu_to_be32(enable | FW_LEN16(vlan_cmd)); /* Drop all packets that donot match vlan id */ - vlan_cmd.dropnovlan_fm = FW_ACL_VLAN_CMD_FM_F; + vlan_cmd.dropnovlan_fm = (enable + ? (FW_ACL_VLAN_CMD_DROPNOVLAN_F | + FW_ACL_VLAN_CMD_FM_F) : 0); if (enable != 0) { vlan_cmd.nvlan = 1; vlan_cmd.vlanid[0] = cpu_to_be16(vlan); diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h index 5dc6c4154af8..6d2bc8789223 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h @@ -2464,6 +2464,7 @@ struct fw_acl_vlan_cmd { #define FW_ACL_VLAN_CMD_DROPNOVLAN_S 7 #define FW_ACL_VLAN_CMD_DROPNOVLAN_V(x) ((x) << FW_ACL_VLAN_CMD_DROPNOVLAN_S) +#define FW_ACL_VLAN_CMD_DROPNOVLAN_F FW_ACL_VLAN_CMD_DROPNOVLAN_V(1U) #define FW_ACL_VLAN_CMD_FM_S 6 #define FW_ACL_VLAN_CMD_FM_M 0x1 diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 1c9ad3630c77..ceec467f590d 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -372,9 +372,8 @@ static int gmac_setup_phy(struct net_device *netdev) return -ENODEV; netdev->phydev = phy; - phy->supported &= PHY_GBIT_FEATURES; - phy->supported |= SUPPORTED_Asym_Pause | SUPPORTED_Pause; - phy->advertising = phy->supported; + phy_set_max_speed(phy, SPEED_1000); + phy_support_asym_pause(phy); /* set PHY interface type */ switch (phy->interface) { diff --git a/drivers/net/ethernet/dnet.c b/drivers/net/ethernet/dnet.c index 5a847941c46b..79521e27f0d1 100644 --- a/drivers/net/ethernet/dnet.c +++ b/drivers/net/ethernet/dnet.c @@ -284,13 +284,11 @@ static int dnet_mii_probe(struct net_device *dev) /* mask with MAC supported features */ if (bp->capabilities & DNET_HAS_GIGABIT) - phydev->supported &= PHY_GBIT_FEATURES; + phy_set_max_speed(phydev, SPEED_1000); else - phydev->supported &= PHY_BASIC_FEATURES; + phy_set_max_speed(phydev, SPEED_100); - phydev->supported |= SUPPORTED_Asym_Pause | SUPPORTED_Pause; - - phydev->advertising = phydev->supported; + phy_support_asym_pause(phydev); bp->link = 0; bp->speed = 0; diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index ff92ab1daeb8..1e9d882c04ef 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -4500,7 +4500,7 @@ int be_cmd_get_profile_config(struct be_adapter *adapter, port_res->max_vfs += le16_to_cpu(pcie->num_vfs); } } - return status; + goto err; } pcie = be_get_pcie_desc(resp->func_param, desc_count, diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c index 60da0499ad66..0f3e7f21c6fa 100644 --- a/drivers/net/ethernet/ethoc.c +++ b/drivers/net/ethernet/ethoc.c @@ -721,10 +721,7 @@ static int ethoc_mdio_probe(struct net_device *dev) return err; } - phy->advertising &= ~(ADVERTISED_1000baseT_Full | - ADVERTISED_1000baseT_Half); - phy->supported &= ~(SUPPORTED_1000baseT_Full | - SUPPORTED_1000baseT_Half); + phy_set_max_speed(phy, SPEED_100); return 0; } diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index ed6c76d20b45..d8ead7e4177e 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -1079,8 +1079,7 @@ static int ftgmac100_mii_probe(struct ftgmac100 *priv, phy_interface_t intf) /* Indicate that we support PAUSE frames (see comment in * Documentation/networking/phy.txt) */ - phydev->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; - phydev->advertising = phydev->supported; + phy_support_asym_pause(phydev); /* Display what we found */ phy_attached_info(phydev); @@ -1220,22 +1219,11 @@ static int ftgmac100_set_pauseparam(struct net_device *netdev, priv->tx_pause = pause->tx_pause; priv->rx_pause = pause->rx_pause; - if (phydev) { - phydev->advertising &= ~ADVERTISED_Pause; - phydev->advertising &= ~ADVERTISED_Asym_Pause; + if (phydev) + phy_set_asym_pause(phydev, pause->rx_pause, pause->tx_pause); - if (pause->rx_pause) { - phydev->advertising |= ADVERTISED_Pause; - phydev->advertising |= ADVERTISED_Asym_Pause; - } - - if (pause->tx_pause) - phydev->advertising ^= ADVERTISED_Asym_Pause; - } if (netif_running(netdev)) { - if (phydev && priv->aneg_pause) - phy_start_aneg(phydev); - else + if (!(phydev && priv->aneg_pause)) ftgmac100_config_pause(priv); } diff --git a/drivers/net/ethernet/freescale/Kconfig b/drivers/net/ethernet/freescale/Kconfig index a580a3dcbe59..7a30276e1ba6 100644 --- a/drivers/net/ethernet/freescale/Kconfig +++ b/drivers/net/ethernet/freescale/Kconfig @@ -97,4 +97,12 @@ config GIANFAR source "drivers/net/ethernet/freescale/dpaa/Kconfig" +config FSL_DPAA2_ETH + tristate "Freescale DPAA2 Ethernet" + depends on FSL_MC_BUS && FSL_MC_DPIO + depends on NETDEVICES && ETHERNET + ---help--- + Ethernet driver for Freescale DPAA2 SoCs, using the + Freescale MC bus driver + endif # NET_VENDOR_FREESCALE diff --git a/drivers/net/ethernet/freescale/Makefile b/drivers/net/ethernet/freescale/Makefile index 0914a3ea4405..3b4ff08e3841 100644 --- a/drivers/net/ethernet/freescale/Makefile +++ b/drivers/net/ethernet/freescale/Makefile @@ -21,3 +21,5 @@ ucc_geth_driver-objs := ucc_geth.o ucc_geth_ethtool.o obj-$(CONFIG_FSL_FMAN) += fman/ obj-$(CONFIG_FSL_DPAA_ETH) += dpaa/ + +obj-$(CONFIG_FSL_DPAA2_ETH) += dpaa2/ diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index 65a22cd9aef2..a5131a510e8b 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -1280,7 +1280,7 @@ static int dpaa_bman_release(const struct dpaa_bp *dpaa_bp, err = bman_release(dpaa_bp->pool, bmb, cnt); /* Should never occur, address anyway to avoid leaking the buffers */ - if (unlikely(WARN_ON(err)) && dpaa_bp->free_buf_cb) + if (WARN_ON(err) && dpaa_bp->free_buf_cb) while (cnt-- > 0) dpaa_bp->free_buf_cb(dpaa_bp, &bmb[cnt]); @@ -1704,10 +1704,8 @@ static struct sk_buff *contig_fd_to_skb(const struct dpaa_priv *priv, skb = build_skb(vaddr, dpaa_bp->size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info))); - if (unlikely(!skb)) { - WARN_ONCE(1, "Build skb failure on Rx\n"); + if (WARN_ONCE(!skb, "Build skb failure on Rx\n")) goto free_buffer; - } WARN_ON(fd_off != priv->rx_headroom); skb_reserve(skb, fd_off); skb_put(skb, qm_fd_get_length(fd)); @@ -1770,7 +1768,7 @@ static struct sk_buff *sg_fd_to_skb(const struct dpaa_priv *priv, sz = dpaa_bp->size + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); skb = build_skb(sg_vaddr, sz); - if (WARN_ON(unlikely(!skb))) + if (WARN_ON(!skb)) goto free_buffers; skb->ip_summed = rx_csum_offload(priv, fd); @@ -2493,8 +2491,7 @@ static int dpaa_phy_init(struct net_device *net_dev) /* Remove any features not supported by the controller */ phy_dev->supported &= mac_dev->if_support; - phy_dev->supported |= (SUPPORTED_Pause | SUPPORTED_Asym_Pause); - phy_dev->advertising = phy_dev->supported; + phy_support_asym_pause(phy_dev); mac_dev->phy_dev = phy_dev; net_dev->phydev = phy_dev; diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c index 3184c8f7cdd0..5d0fdf667b82 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c @@ -194,9 +194,7 @@ static int dpaa_set_pauseparam(struct net_device *net_dev, return -ENODEV; } - if (!(phydev->supported & SUPPORTED_Pause) || - (!(phydev->supported & SUPPORTED_Asym_Pause) && - (epause->rx_pause != epause->tx_pause))) + if (!phy_validate_pause(phydev, epause)) return -EINVAL; /* The MAC should know how to handle PAUSE frame autonegotiation before @@ -210,29 +208,8 @@ static int dpaa_set_pauseparam(struct net_device *net_dev, /* Determine the sym/asym advertised PAUSE capabilities from the desired * rx/tx pause settings. */ - newadv = 0; - if (epause->rx_pause) - newadv = ADVERTISED_Pause | ADVERTISED_Asym_Pause; - if (epause->tx_pause) - newadv ^= ADVERTISED_Asym_Pause; - oldadv = phydev->advertising & - (ADVERTISED_Pause | ADVERTISED_Asym_Pause); - - /* If there are differences between the old and the new advertised - * values, restart PHY autonegotiation and advertise the new values. - */ - if (oldadv != newadv) { - phydev->advertising &= ~(ADVERTISED_Pause - | ADVERTISED_Asym_Pause); - phydev->advertising |= newadv; - if (phydev->autoneg) { - err = phy_start_aneg(phydev); - if (err < 0) - netdev_err(net_dev, "phy_start_aneg() = %d\n", - err); - } - } + phy_set_asym_pause(phydev, epause->rx_pause, epause->tx_pause); fman_get_pause_cfg(mac_dev, &rx_pause, &tx_pause); err = fman_set_mac_active_pause(mac_dev, rx_pause, tx_pause); diff --git a/drivers/staging/fsl-dpaa2/ethernet/Makefile b/drivers/net/ethernet/freescale/dpaa2/Makefile index 9315ecdba612..9315ecdba612 100644 --- a/drivers/staging/fsl-dpaa2/ethernet/Makefile +++ b/drivers/net/ethernet/freescale/dpaa2/Makefile diff --git a/drivers/staging/fsl-dpaa2/ethernet/dpaa2-eth-trace.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-trace.h index 9801528db2a5..9801528db2a5 100644 --- a/drivers/staging/fsl-dpaa2/ethernet/dpaa2-eth-trace.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-trace.h diff --git a/drivers/staging/fsl-dpaa2/ethernet/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 9329fcad95ac..559154a5d9e9 100644 --- a/drivers/staging/fsl-dpaa2/ethernet/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -1143,34 +1143,6 @@ static int dpaa2_eth_stop(struct net_device *net_dev) return 0; } -static int dpaa2_eth_init(struct net_device *net_dev) -{ - u64 supported = 0; - u64 not_supported = 0; - struct dpaa2_eth_priv *priv = netdev_priv(net_dev); - u32 options = priv->dpni_attrs.options; - - /* Capabilities listing */ - supported |= IFF_LIVE_ADDR_CHANGE; - - if (options & DPNI_OPT_NO_MAC_FILTER) - not_supported |= IFF_UNICAST_FLT; - else - supported |= IFF_UNICAST_FLT; - - net_dev->priv_flags |= supported; - net_dev->priv_flags &= ~not_supported; - - /* Features */ - net_dev->features = NETIF_F_RXCSUM | - NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | - NETIF_F_SG | NETIF_F_HIGHDMA | - NETIF_F_LLTX; - net_dev->hw_features = net_dev->features; - - return 0; -} - static int dpaa2_eth_set_addr(struct net_device *net_dev, void *addr) { struct dpaa2_eth_priv *priv = netdev_priv(net_dev); @@ -1418,7 +1390,6 @@ static const struct net_device_ops dpaa2_eth_ops = { .ndo_open = dpaa2_eth_open, .ndo_start_xmit = dpaa2_eth_tx, .ndo_stop = dpaa2_eth_stop, - .ndo_init = dpaa2_eth_init, .ndo_set_mac_address = dpaa2_eth_set_addr, .ndo_get_stats64 = dpaa2_eth_get_stats, .ndo_set_rx_mode = dpaa2_eth_set_rx_mode, @@ -2316,11 +2287,14 @@ static int netdev_init(struct net_device *net_dev) { struct device *dev = net_dev->dev.parent; struct dpaa2_eth_priv *priv = netdev_priv(net_dev); + u32 options = priv->dpni_attrs.options; + u64 supported = 0, not_supported = 0; u8 bcast_addr[ETH_ALEN]; u8 num_queues; int err; net_dev->netdev_ops = &dpaa2_eth_ops; + net_dev->ethtool_ops = &dpaa2_ethtool_ops; err = set_mac_addr(priv); if (err) @@ -2356,12 +2330,23 @@ static int netdev_init(struct net_device *net_dev) return err; } - /* Our .ndo_init will be called herein */ - err = register_netdev(net_dev); - if (err < 0) { - dev_err(dev, "register_netdev() failed\n"); - return err; - } + /* Capabilities listing */ + supported |= IFF_LIVE_ADDR_CHANGE; + + if (options & DPNI_OPT_NO_MAC_FILTER) + not_supported |= IFF_UNICAST_FLT; + else + supported |= IFF_UNICAST_FLT; + + net_dev->priv_flags |= supported; + net_dev->priv_flags &= ~not_supported; + + /* Features */ + net_dev->features = NETIF_F_RXCSUM | + NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | + NETIF_F_SG | NETIF_F_HIGHDMA | + NETIF_F_LLTX; + net_dev->hw_features = net_dev->features; return 0; } @@ -2561,28 +2546,36 @@ static int dpaa2_eth_probe(struct fsl_mc_device *dpni_dev) if (err) goto err_alloc_rings; - net_dev->ethtool_ops = &dpaa2_ethtool_ops; - err = setup_irqs(dpni_dev); if (err) { netdev_warn(net_dev, "Failed to set link interrupt, fall back to polling\n"); priv->poll_thread = kthread_run(poll_link_state, priv, "%s_poll_link", net_dev->name); if (IS_ERR(priv->poll_thread)) { - netdev_err(net_dev, "Error starting polling thread\n"); + dev_err(dev, "Error starting polling thread\n"); goto err_poll_thread; } priv->do_link_poll = true; } + err = register_netdev(net_dev); + if (err < 0) { + dev_err(dev, "register_netdev() failed\n"); + goto err_netdev_reg; + } + dev_info(dev, "Probed interface %s\n", net_dev->name); return 0; +err_netdev_reg: + if (priv->do_link_poll) + kthread_stop(priv->poll_thread); + else + fsl_mc_free_irqs(dpni_dev); err_poll_thread: free_rings(priv); err_alloc_rings: err_csum: - unregister_netdev(net_dev); err_netdev_init: free_percpu(priv->percpu_extras); err_alloc_percpu_extras: diff --git a/drivers/staging/fsl-dpaa2/ethernet/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h index d54cb0b99d08..d54cb0b99d08 100644 --- a/drivers/staging/fsl-dpaa2/ethernet/dpaa2-eth.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h diff --git a/drivers/staging/fsl-dpaa2/ethernet/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c index 8056a95e1265..8056a95e1265 100644 --- a/drivers/staging/fsl-dpaa2/ethernet/dpaa2-ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c diff --git a/drivers/staging/fsl-dpaa2/ethernet/dpkg.h b/drivers/net/ethernet/freescale/dpaa2/dpkg.h index 6de613b13e4d..6de613b13e4d 100644 --- a/drivers/staging/fsl-dpaa2/ethernet/dpkg.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpkg.h diff --git a/drivers/staging/fsl-dpaa2/ethernet/dpni-cmd.h b/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h index 83698abce8b4..83698abce8b4 100644 --- a/drivers/staging/fsl-dpaa2/ethernet/dpni-cmd.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h diff --git a/drivers/staging/fsl-dpaa2/ethernet/dpni.c b/drivers/net/ethernet/freescale/dpaa2/dpni.c index d6ac26797cec..d6ac26797cec 100644 --- a/drivers/staging/fsl-dpaa2/ethernet/dpni.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpni.c diff --git a/drivers/staging/fsl-dpaa2/ethernet/dpni.h b/drivers/net/ethernet/freescale/dpaa2/dpni.h index b378a00c7c53..b378a00c7c53 100644 --- a/drivers/staging/fsl-dpaa2/ethernet/dpni.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpni.h diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 2708297e7795..ce74b7a46d07 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1946,16 +1946,15 @@ static int fec_enet_mii_probe(struct net_device *ndev) /* mask with MAC supported features */ if (fep->quirks & FEC_QUIRK_HAS_GBIT) { - phy_dev->supported &= PHY_GBIT_FEATURES; - phy_dev->supported &= ~SUPPORTED_1000baseT_Half; + phy_set_max_speed(phy_dev, 1000); + phy_remove_link_mode(phy_dev, + ETHTOOL_LINK_MODE_1000baseT_Half_BIT); #if !defined(CONFIG_M5272) - phy_dev->supported |= SUPPORTED_Pause; + phy_support_sym_pause(phy_dev); #endif } else - phy_dev->supported &= PHY_BASIC_FEATURES; - - phy_dev->advertising = phy_dev->supported; + phy_set_max_speed(phy_dev, 100); fep->link = 0; fep->full_duplex = 0; @@ -2055,8 +2054,7 @@ static int fec_enet_mii_init(struct platform_device *pdev) node = of_get_child_by_name(pdev->dev.of_node, "mdio"); err = of_mdiobus_register(fep->mii_bus, node); - if (node) - of_node_put(node); + of_node_put(node); if (err) goto err_out_free_mdiobus; @@ -2230,13 +2228,8 @@ static int fec_enet_set_pauseparam(struct net_device *ndev, fep->pause_flag |= pause->rx_pause ? FEC_PAUSE_FLAG_ENABLE : 0; fep->pause_flag |= pause->autoneg ? FEC_PAUSE_FLAG_AUTONEG : 0; - if (pause->rx_pause || pause->autoneg) { - ndev->phydev->supported |= ADVERTISED_Pause; - ndev->phydev->advertising |= ADVERTISED_Pause; - } else { - ndev->phydev->supported &= ~ADVERTISED_Pause; - ndev->phydev->advertising &= ~ADVERTISED_Pause; - } + phy_set_sym_pause(ndev->phydev, pause->rx_pause, pause->tx_pause, + pause->autoneg); if (pause->autoneg) { if (netif_running(ndev)) diff --git a/drivers/net/ethernet/freescale/fsl_pq_mdio.c b/drivers/net/ethernet/freescale/fsl_pq_mdio.c index ac2c3f6a12bc..82722d05fedb 100644 --- a/drivers/net/ethernet/freescale/fsl_pq_mdio.c +++ b/drivers/net/ethernet/freescale/fsl_pq_mdio.c @@ -446,8 +446,8 @@ static int fsl_pq_mdio_probe(struct platform_device *pdev) goto error; } - snprintf(new_bus->id, MII_BUS_ID_SIZE, "%s@%llx", np->name, - (unsigned long long)res.start); + snprintf(new_bus->id, MII_BUS_ID_SIZE, "%pOFn@%llx", np, + (unsigned long long)res.start); priv->map = of_iomap(np, 0); if (!priv->map) { diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index f27f9bae1a4a..c488d31e2af6 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -102,8 +102,6 @@ #include <linux/phy_fixed.h> #include <linux/of.h> #include <linux/of_net.h> -#include <linux/of_address.h> -#include <linux/of_irq.h> #include "gianfar.h" @@ -1814,8 +1812,8 @@ static int init_phy(struct net_device *dev) phydev->supported &= (GFAR_SUPPORTED | gigabit_support); phydev->advertising = phydev->supported; - /* Add support for flow control, but don't advertise it by default */ - phydev->supported |= (SUPPORTED_Pause | SUPPORTED_Asym_Pause); + /* Add support for flow control */ + phy_support_asym_pause(phydev); /* disable EEE autoneg, EEE not supported by eTSEC */ memset(&edata, 0, sizeof(struct ethtool_eee)); diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c index 395a5266ea30..0d76e15cd6dd 100644 --- a/drivers/net/ethernet/freescale/gianfar_ethtool.c +++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c @@ -230,7 +230,7 @@ static unsigned int gfar_usecs2ticks(struct gfar_private *priv, /* Make sure we return a number greater than 0 * if usecs > 0 */ - return (usecs * 1000 + count - 1) / count; + return DIV_ROUND_UP(usecs * 1000, count); } /* Convert ethernet clock ticks to microseconds */ @@ -503,65 +503,44 @@ static int gfar_spauseparam(struct net_device *dev, struct gfar_private *priv = netdev_priv(dev); struct phy_device *phydev = dev->phydev; struct gfar __iomem *regs = priv->gfargrp[0].regs; - u32 oldadv, newadv; if (!phydev) return -ENODEV; - if (!(phydev->supported & SUPPORTED_Pause) || - (!(phydev->supported & SUPPORTED_Asym_Pause) && - (epause->rx_pause != epause->tx_pause))) + if (!phy_validate_pause(phydev, epause)) return -EINVAL; priv->rx_pause_en = priv->tx_pause_en = 0; + phy_set_asym_pause(phydev, epause->rx_pause, epause->tx_pause); if (epause->rx_pause) { priv->rx_pause_en = 1; if (epause->tx_pause) { priv->tx_pause_en = 1; - /* FLOW_CTRL_RX & TX */ - newadv = ADVERTISED_Pause; - } else /* FLOW_CTLR_RX */ - newadv = ADVERTISED_Pause | ADVERTISED_Asym_Pause; + } } else if (epause->tx_pause) { priv->tx_pause_en = 1; - /* FLOW_CTLR_TX */ - newadv = ADVERTISED_Asym_Pause; - } else - newadv = 0; + } if (epause->autoneg) priv->pause_aneg_en = 1; else priv->pause_aneg_en = 0; - oldadv = phydev->advertising & - (ADVERTISED_Pause | ADVERTISED_Asym_Pause); - if (oldadv != newadv) { - phydev->advertising &= - ~(ADVERTISED_Pause | ADVERTISED_Asym_Pause); - phydev->advertising |= newadv; - if (phydev->autoneg) - /* inform link partner of our - * new flow ctrl settings - */ - return phy_start_aneg(phydev); - - if (!epause->autoneg) { - u32 tempval; - tempval = gfar_read(®s->maccfg1); - tempval &= ~(MACCFG1_TX_FLOW | MACCFG1_RX_FLOW); - - priv->tx_actual_en = 0; - if (priv->tx_pause_en) { - priv->tx_actual_en = 1; - tempval |= MACCFG1_TX_FLOW; - } + if (!epause->autoneg) { + u32 tempval = gfar_read(®s->maccfg1); - if (priv->rx_pause_en) - tempval |= MACCFG1_RX_FLOW; - gfar_write(®s->maccfg1, tempval); + tempval &= ~(MACCFG1_TX_FLOW | MACCFG1_RX_FLOW); + + priv->tx_actual_en = 0; + if (priv->tx_pause_en) { + priv->tx_actual_en = 1; + tempval |= MACCFG1_TX_FLOW; } + + if (priv->rx_pause_en) + tempval |= MACCFG1_RX_FLOW; + gfar_write(®s->maccfg1, tempval); } return 0; diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c index 22a817da861e..9600837f21b8 100644 --- a/drivers/net/ethernet/freescale/ucc_geth.c +++ b/drivers/net/ethernet/freescale/ucc_geth.c @@ -1742,12 +1742,7 @@ static int init_phy(struct net_device *dev) if (priv->phy_interface == PHY_INTERFACE_MODE_SGMII) uec_configure_serdes(dev); - phydev->supported &= (SUPPORTED_MII | - SUPPORTED_Autoneg | - ADVERTISED_10baseT_Half | - ADVERTISED_10baseT_Full | - ADVERTISED_100baseT_Half | - ADVERTISED_100baseT_Full); + phy_set_max_speed(phydev, SPEED_100); if (priv->max_speed == SPEED_1000) phydev->supported |= ADVERTISED_1000baseT_Full; diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c index 14374a856d30..be268dcde8fa 100644 --- a/drivers/net/ethernet/hisilicon/hip04_eth.c +++ b/drivers/net/ethernet/hisilicon/hip04_eth.c @@ -422,7 +422,8 @@ static void hip04_start_tx_timer(struct hip04_priv *priv) ns, HRTIMER_MODE_REL); } -static int hip04_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev) +static netdev_tx_t +hip04_mac_start_xmit(struct sk_buff *skb, struct net_device *ndev) { struct hip04_priv *priv = netdev_priv(ndev); struct net_device_stats *stats = &ndev->stats; diff --git a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c index c5727003af8c..471805ea363b 100644 --- a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c +++ b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c @@ -736,7 +736,7 @@ static int hix5hd2_fill_sg_desc(struct hix5hd2_priv *priv, return 0; } -static int hix5hd2_net_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t hix5hd2_net_xmit(struct sk_buff *skb, struct net_device *dev) { struct hix5hd2_priv *priv = netdev_priv(dev); struct hix5hd2_desc *desc; diff --git a/drivers/net/ethernet/hisilicon/hns/hnae.h b/drivers/net/ethernet/hisilicon/hns/hnae.h index fa5b30f547f6..08a750fb60c4 100644 --- a/drivers/net/ethernet/hisilicon/hns/hnae.h +++ b/drivers/net/ethernet/hisilicon/hns/hnae.h @@ -220,10 +220,10 @@ struct hnae_desc_cb { /* priv data for the desc, e.g. skb when use with ip stack*/ void *priv; - u16 page_offset; - u16 reuse_flag; + u32 page_offset; + u32 length; /* length of the buffer */ - u16 length; /* length of the buffer */ + u16 reuse_flag; /* desc type, used by the ring user to mark the type of the priv data */ u16 type; @@ -486,6 +486,8 @@ struct hnae_ae_ops { u8 *auto_neg, u16 *speed, u8 *duplex); void (*toggle_ring_irq)(struct hnae_ring *ring, u32 val); void (*adjust_link)(struct hnae_handle *handle, int speed, int duplex); + bool (*need_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, diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c index e6aad30e7e69..b52029e26d15 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c @@ -155,6 +155,41 @@ static void hns_ae_put_handle(struct hnae_handle *handle) hns_ae_get_ring_pair(handle->qs[i])->used_by_vf = 0; } +static int hns_ae_wait_flow_down(struct hnae_handle *handle) +{ + struct dsaf_device *dsaf_dev; + struct hns_ppe_cb *ppe_cb; + struct hnae_vf_cb *vf_cb; + int ret; + int i; + + for (i = 0; i < handle->q_num; i++) { + ret = hns_rcb_wait_tx_ring_clean(handle->qs[i]); + if (ret) + return ret; + } + + ppe_cb = hns_get_ppe_cb(handle); + ret = hns_ppe_wait_tx_fifo_clean(ppe_cb); + if (ret) + return ret; + + dsaf_dev = hns_ae_get_dsaf_dev(handle->dev); + if (!dsaf_dev) + return -EINVAL; + ret = hns_dsaf_wait_pkt_clean(dsaf_dev, handle->dport_id); + if (ret) + return ret; + + vf_cb = hns_ae_get_vf_cb(handle); + ret = hns_mac_wait_fifo_clean(vf_cb->mac_cb); + if (ret) + return ret; + + mdelay(10); + return 0; +} + static void hns_ae_ring_enable_all(struct hnae_handle *handle, int val) { int q_num = handle->q_num; @@ -399,12 +434,41 @@ static int hns_ae_get_mac_info(struct hnae_handle *handle, return hns_mac_get_port_info(mac_cb, auto_neg, speed, duplex); } +static bool hns_ae_need_adjust_link(struct hnae_handle *handle, int speed, + int duplex) +{ + struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle); + + return hns_mac_need_adjust_link(mac_cb, 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); + switch (mac_cb->dsaf_dev->dsaf_ver) { + case AE_VERSION_1: + hns_mac_adjust_link(mac_cb, speed, duplex); + break; + + case AE_VERSION_2: + /* chip need to clear all pkt inside */ + hns_mac_disable(mac_cb, MAC_COMM_MODE_RX); + if (hns_ae_wait_flow_down(handle)) { + hns_mac_enable(mac_cb, MAC_COMM_MODE_RX); + break; + } + + hns_mac_adjust_link(mac_cb, speed, duplex); + hns_mac_enable(mac_cb, MAC_COMM_MODE_RX); + break; + + default: + break; + } + + return; } static void hns_ae_get_ring_bdnum_limit(struct hnae_queue *queue, @@ -902,6 +966,7 @@ static struct hnae_ae_ops hns_dsaf_ops = { .get_status = hns_ae_get_link_status, .get_info = hns_ae_get_mac_info, .adjust_link = hns_ae_adjust_link, + .need_adjust_link = hns_ae_need_adjust_link, .set_loopback = hns_ae_config_loopback, .get_ring_bdnum_limit = hns_ae_get_ring_bdnum_limit, .get_pauseparam = hns_ae_get_pauseparam, diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c index 5488c6e89f21..aaf72c055711 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c @@ -257,6 +257,16 @@ static void hns_gmac_get_pausefrm_cfg(void *mac_drv, u32 *rx_pause_en, *tx_pause_en = dsaf_get_bit(pause_en, GMAC_PAUSE_EN_TX_FDFC_B); } +static bool hns_gmac_need_adjust_link(void *mac_drv, enum mac_speed speed, + int duplex) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + struct hns_mac_cb *mac_cb = drv->mac_cb; + + return (mac_cb->speed != speed) || + (mac_cb->half_duplex == duplex); +} + static int hns_gmac_adjust_link(void *mac_drv, enum mac_speed speed, u32 full_duplex) { @@ -309,6 +319,30 @@ static void hns_gmac_set_promisc(void *mac_drv, u8 en) hns_gmac_set_uc_match(mac_drv, en); } +static int hns_gmac_wait_fifo_clean(void *mac_drv) +{ + struct mac_driver *drv = (struct mac_driver *)mac_drv; + int wait_cnt; + u32 val; + + wait_cnt = 0; + while (wait_cnt++ < HNS_MAX_WAIT_CNT) { + val = dsaf_read_dev(drv, GMAC_FIFO_STATE_REG); + /* bit5~bit0 is not send complete pkts */ + if ((val & 0x3f) == 0) + break; + usleep_range(100, 200); + } + + if (wait_cnt >= HNS_MAX_WAIT_CNT) { + dev_err(drv->dev, + "hns ge %d fifo was not idle.\n", drv->mac_id); + return -EBUSY; + } + + return 0; +} + static void hns_gmac_init(void *mac_drv) { u32 port; @@ -690,6 +724,7 @@ void *hns_gmac_config(struct hns_mac_cb *mac_cb, struct mac_params *mac_param) mac_drv->mac_disable = hns_gmac_disable; mac_drv->mac_free = hns_gmac_free; mac_drv->adjust_link = hns_gmac_adjust_link; + mac_drv->need_adjust_link = hns_gmac_need_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; @@ -717,6 +752,7 @@ void *hns_gmac_config(struct hns_mac_cb *mac_cb, struct mac_params *mac_param) mac_drv->get_strings = hns_gmac_get_strings; mac_drv->update_stats = hns_gmac_update_stats; mac_drv->set_promiscuous = hns_gmac_set_promisc; + mac_drv->wait_fifo_clean = hns_gmac_wait_fifo_clean; return (void *)mac_drv; } diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c index 1c2326bd76e2..3613e400e816 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c @@ -114,6 +114,26 @@ int hns_mac_get_port_info(struct hns_mac_cb *mac_cb, return 0; } +/** + *hns_mac_is_adjust_link - check is need change mac speed and duplex register + *@mac_cb: mac device + *@speed: phy device speed + *@duplex:phy device duplex + * + */ +bool hns_mac_need_adjust_link(struct hns_mac_cb *mac_cb, int speed, int duplex) +{ + struct mac_driver *mac_ctrl_drv; + + mac_ctrl_drv = (struct mac_driver *)(mac_cb->priv.mac); + + if (mac_ctrl_drv->need_adjust_link) + return mac_ctrl_drv->need_adjust_link(mac_ctrl_drv, + (enum mac_speed)speed, duplex); + else + return true; +} + void hns_mac_adjust_link(struct hns_mac_cb *mac_cb, int speed, int duplex) { int ret; @@ -430,6 +450,16 @@ int hns_mac_vm_config_bc_en(struct hns_mac_cb *mac_cb, u32 vmid, bool enable) return 0; } +int hns_mac_wait_fifo_clean(struct hns_mac_cb *mac_cb) +{ + struct mac_driver *drv = hns_mac_get_drv(mac_cb); + + if (drv->wait_fifo_clean) + return drv->wait_fifo_clean(drv); + + return 0; +} + void hns_mac_reset(struct hns_mac_cb *mac_cb) { struct mac_driver *drv = hns_mac_get_drv(mac_cb); @@ -807,8 +837,8 @@ static int hns_mac_get_info(struct hns_mac_cb *mac_cb) */ put_device(&mac_cb->phy_dev->mdio.dev); - dev_dbg(mac_cb->dev, "mac%d phy_node: %s\n", - mac_cb->mac_id, np->name); + dev_dbg(mac_cb->dev, "mac%d phy_node: %pOFn\n", + mac_cb->mac_id, np); } of_node_put(np); @@ -825,8 +855,8 @@ static int hns_mac_get_info(struct hns_mac_cb *mac_cb) * if the phy_dev is found */ put_device(&mac_cb->phy_dev->mdio.dev); - dev_dbg(mac_cb->dev, "mac%d phy_node: %s\n", - mac_cb->mac_id, np->name); + dev_dbg(mac_cb->dev, "mac%d phy_node: %pOFn\n", + mac_cb->mac_id, np); } of_node_put(np); @@ -998,6 +1028,20 @@ static int hns_mac_get_max_port_num(struct dsaf_device *dsaf_dev) return DSAF_MAX_PORT_NUM; } +void hns_mac_enable(struct hns_mac_cb *mac_cb, enum mac_commom_mode mode) +{ + struct mac_driver *mac_ctrl_drv = hns_mac_get_drv(mac_cb); + + mac_ctrl_drv->mac_enable(mac_cb->priv.mac, mode); +} + +void hns_mac_disable(struct hns_mac_cb *mac_cb, enum mac_commom_mode mode) +{ + struct mac_driver *mac_ctrl_drv = hns_mac_get_drv(mac_cb); + + mac_ctrl_drv->mac_disable(mac_cb->priv.mac, mode); +} + /** * hns_mac_init - init mac * @dsaf_dev: dsa fabric device struct pointer diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h index bbc0a98e7ca3..fbc75341bef7 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.h @@ -356,6 +356,9 @@ struct mac_driver { /*adjust mac mode of port,include speed and duplex*/ int (*adjust_link)(void *mac_drv, enum mac_speed speed, u32 full_duplex); + /* need adjust link */ + bool (*need_adjust_link)(void *mac_drv, enum mac_speed speed, + int duplex); /* config autoegotaite mode of port*/ void (*set_an_mode)(void *mac_drv, u8 enable); /* config loopbank mode */ @@ -394,6 +397,7 @@ struct mac_driver { void (*get_info)(void *mac_drv, struct mac_info *mac_info); void (*update_stats)(void *mac_drv); + int (*wait_fifo_clean)(void *mac_drv); enum mac_mode mac_mode; u8 mac_id; @@ -427,6 +431,7 @@ void *hns_xgmac_config(struct hns_mac_cb *mac_cb, int hns_mac_init(struct dsaf_device *dsaf_dev); void mac_adjust_link(struct net_device *net_dev); +bool hns_mac_need_adjust_link(struct hns_mac_cb *mac_cb, int speed, int duplex); 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, @@ -463,5 +468,8 @@ int hns_mac_add_uc_addr(struct hns_mac_cb *mac_cb, u8 vf_id, int hns_mac_rm_uc_addr(struct hns_mac_cb *mac_cb, u8 vf_id, const unsigned char *addr); int hns_mac_clr_multicast(struct hns_mac_cb *mac_cb, int vfn); +void hns_mac_enable(struct hns_mac_cb *mac_cb, enum mac_commom_mode mode); +void hns_mac_disable(struct hns_mac_cb *mac_cb, enum mac_commom_mode mode); +int hns_mac_wait_fifo_clean(struct hns_mac_cb *mac_cb); #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 index ca50c2553a9c..e557a4ef5996 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c @@ -2727,6 +2727,35 @@ void hns_dsaf_set_promisc_tcam(struct dsaf_device *dsaf_dev, soft_mac_entry->index = enable ? entry_index : DSAF_INVALID_ENTRY_IDX; } +int hns_dsaf_wait_pkt_clean(struct dsaf_device *dsaf_dev, int port) +{ + u32 val, val_tmp; + int wait_cnt; + + if (port >= DSAF_SERVICE_NW_NUM) + return 0; + + wait_cnt = 0; + while (wait_cnt++ < HNS_MAX_WAIT_CNT) { + val = dsaf_read_dev(dsaf_dev, DSAF_VOQ_IN_PKT_NUM_0_REG + + (port + DSAF_XGE_NUM) * 0x40); + val_tmp = dsaf_read_dev(dsaf_dev, DSAF_VOQ_OUT_PKT_NUM_0_REG + + (port + DSAF_XGE_NUM) * 0x40); + if (val == val_tmp) + break; + + usleep_range(100, 200); + } + + if (wait_cnt >= HNS_MAX_WAIT_CNT) { + dev_err(dsaf_dev->dev, "hns dsaf clean wait timeout(%u - %u).\n", + val, val_tmp); + return -EBUSY; + } + + return 0; +} + /** * dsaf_probe - probo dsaf dev * @pdev: dasf platform device diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h index 4507e8222683..0e1cd99831a6 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.h @@ -44,6 +44,8 @@ struct hns_mac_cb; #define DSAF_ROCE_CREDIT_CHN 8 #define DSAF_ROCE_CHAN_MODE 3 +#define HNS_MAX_WAIT_CNT 10000 + enum dsaf_roce_port_mode { DSAF_ROCE_6PORT_MODE, DSAF_ROCE_4PORT_MODE, @@ -463,5 +465,6 @@ int hns_dsaf_rm_mac_addr( int hns_dsaf_clr_mac_mc_port(struct dsaf_device *dsaf_dev, u8 mac_id, u8 port_num); +int hns_dsaf_wait_pkt_clean(struct dsaf_device *dsaf_dev, int port); #endif /* __HNS_DSAF_MAIN_H__ */ diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c index d160d8c9e45b..0942e4916d9d 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c @@ -275,6 +275,29 @@ static void hns_ppe_exc_irq_en(struct hns_ppe_cb *ppe_cb, int en) dsaf_write_dev(ppe_cb, PPE_INTEN_REG, msk_vlue & vld_msk); } +int hns_ppe_wait_tx_fifo_clean(struct hns_ppe_cb *ppe_cb) +{ + int wait_cnt; + u32 val; + + wait_cnt = 0; + while (wait_cnt++ < HNS_MAX_WAIT_CNT) { + val = dsaf_read_dev(ppe_cb, PPE_CURR_TX_FIFO0_REG) & 0x3ffU; + if (!val) + break; + + usleep_range(100, 200); + } + + if (wait_cnt >= HNS_MAX_WAIT_CNT) { + dev_err(ppe_cb->dev, "hns ppe tx fifo clean wait timeout, still has %u pkt.\n", + val); + return -EBUSY; + } + + return 0; +} + /** * ppe_init_hw - init ppe * @ppe_cb: ppe device diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h index 9d8e643e8aa6..f670e63a5a01 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.h @@ -100,6 +100,7 @@ struct ppe_common_cb { }; +int hns_ppe_wait_tx_fifo_clean(struct hns_ppe_cb *ppe_cb); int hns_ppe_init(struct dsaf_device *dsaf_dev); void hns_ppe_uninit(struct dsaf_device *dsaf_dev); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c index 9d76e2e54f9d..5d64519b9b1d 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c @@ -66,6 +66,29 @@ void hns_rcb_wait_fbd_clean(struct hnae_queue **qs, int q_num, u32 flag) "queue(%d) wait fbd(%d) clean fail!!\n", i, fbd_num); } +int hns_rcb_wait_tx_ring_clean(struct hnae_queue *qs) +{ + u32 head, tail; + int wait_cnt; + + tail = dsaf_read_dev(&qs->tx_ring, RCB_REG_TAIL); + wait_cnt = 0; + while (wait_cnt++ < HNS_MAX_WAIT_CNT) { + head = dsaf_read_dev(&qs->tx_ring, RCB_REG_HEAD); + if (tail == head) + break; + + usleep_range(100, 200); + } + + if (wait_cnt >= HNS_MAX_WAIT_CNT) { + dev_err(qs->dev->dev, "rcb wait timeout, head not equal to tail.\n"); + return -EBUSY; + } + + return 0; +} + /** *hns_rcb_reset_ring_hw - ring reset *@q: ring struct pointer diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h index 602816498c8d..2319b772a271 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.h @@ -136,6 +136,7 @@ void hns_rcbv2_int_clr_hw(struct hnae_queue *q, u32 flag); 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); +int hns_rcb_wait_tx_ring_clean(struct hnae_queue *qs); u32 hns_rcb_get_rx_coalesced_frames( struct rcb_common_cb *rcb_common, u32 port_idx); u32 hns_rcb_get_tx_coalesced_frames( diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h index 886cbbf25761..74d935d82cbc 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_reg.h @@ -464,6 +464,7 @@ #define RCB_RING_INTMSK_TX_OVERTIME_REG 0x000C4 #define RCB_RING_INTSTS_TX_OVERTIME_REG 0x000C8 +#define GMAC_FIFO_STATE_REG 0x0000UL #define GMAC_DUPLEX_TYPE_REG 0x0008UL #define GMAC_FD_FC_TYPE_REG 0x000CUL #define GMAC_TX_WATER_LINE_REG 0x0010UL diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 9f2b552aee33..f56855e63c96 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -406,113 +406,13 @@ out_net_tx_busy: 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 sk_buff *skb, int i, struct hnae_ring *ring, int pull_len, struct hnae_desc_cb *desc_cb) { struct hnae_desc *desc; - int truesize, size; + u32 truesize; + int size; int last_offset; bool twobufs; @@ -530,7 +430,7 @@ static void hns_nic_reuse_page(struct sk_buff *skb, int i, } skb_add_rx_frag(skb, i, desc_cb->priv, desc_cb->page_offset + pull_len, - size - pull_len, truesize - pull_len); + size - pull_len, truesize); /* avoid re-using remote pages,flag default unreuse */ if (unlikely(page_to_nid(desc_cb->priv) != numa_node_id())) @@ -695,7 +595,7 @@ static int hns_nic_poll_rx_skb(struct hns_nic_ring_data *ring_data, } else { ring->stats.seg_pkt_cnt++; - pull_len = hns_nic_get_headlen(va, bnum_flag, HNS_RX_HEAD_SIZE); + pull_len = eth_get_headlen(va, HNS_RX_HEAD_SIZE); memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long))); @@ -1212,11 +1112,26 @@ static void hns_nic_adjust_link(struct net_device *ndev) struct hnae_handle *h = priv->ae_handle; int state = 1; + /* If there is no phy, do not need adjust link */ if (ndev->phydev) { - h->dev->ops->adjust_link(h, ndev->phydev->speed, - ndev->phydev->duplex); - state = ndev->phydev->link; + /* When phy link down, do nothing */ + if (ndev->phydev->link == 0) + return; + + if (h->dev->ops->need_adjust_link(h, ndev->phydev->speed, + ndev->phydev->duplex)) { + /* because Hi161X chip don't support to change gmac + * speed and duplex with traffic. Delay 200ms to + * make sure there is no more data in chip FIFO. + */ + netif_carrier_off(ndev); + msleep(200); + h->dev->ops->adjust_link(h, ndev->phydev->speed, + ndev->phydev->duplex); + netif_carrier_on(ndev); + } } + state = state && h->dev->ops->get_status(h); if (state != priv->link) { diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c index 08f3c4743f74..774beda040a1 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c @@ -243,7 +243,9 @@ static int hns_nic_set_link_ksettings(struct net_device *net_dev, } if (h->dev->ops->adjust_link) { + netif_carrier_off(net_dev); h->dev->ops->adjust_link(h, (int)speed, cmd->base.duplex); + netif_carrier_on(net_dev); return 0; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 3554dca7a680..75e8ee9d4e2e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -1662,11 +1662,24 @@ static int hns3_pci_sriov_configure(struct pci_dev *pdev, int num_vfs) return 0; } +static void hns3_shutdown(struct pci_dev *pdev) +{ + struct hnae3_ae_dev *ae_dev = pci_get_drvdata(pdev); + + hnae3_unregister_ae_dev(ae_dev); + devm_kfree(&pdev->dev, ae_dev); + pci_set_drvdata(pdev, NULL); + + if (system_state == SYSTEM_POWER_OFF) + pci_set_power_state(pdev, PCI_D3hot); +} + static struct pci_driver hns3_driver = { .name = hns3_driver_name, .id_table = hns3_pci_tbl, .probe = hns3_probe, .remove = hns3_remove, + .shutdown = hns3_shutdown, .sriov_configure = hns3_pci_sriov_configure, }; @@ -2019,7 +2032,8 @@ static void hns3_nic_reuse_page(struct sk_buff *skb, int i, struct hns3_desc_cb *desc_cb) { struct hns3_desc *desc; - int truesize, size; + u32 truesize; + int size; int last_offset; bool twobufs; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h index a02a96aee2a2..cb450d7ec8c1 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h @@ -284,11 +284,11 @@ struct hns3_desc_cb { /* priv data for the desc, e.g. skb when use with ip stack*/ void *priv; - u16 page_offset; - u16 reuse_flag; - + u32 page_offset; u32 length; /* length of the buffer */ + u16 reuse_flag; + /* desc type, used by the ring user to mark the type of the priv data */ u16 type; }; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index f70ee6910ee2..3019007d7ceb 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -100,41 +100,26 @@ static int hns3_lp_up(struct net_device *ndev, enum hnae3_loop loop_mode) struct hnae3_handle *h = hns3_get_handle(ndev); int ret; - if (!h->ae_algo->ops->start) - return -EOPNOTSUPP; - ret = hns3_nic_reset_all_ring(h); if (ret) return ret; - ret = h->ae_algo->ops->start(h); - if (ret) { - netdev_err(ndev, - "hns3_lb_up ae start return error: %d\n", ret); - return ret; - } - ret = hns3_lp_setup(ndev, loop_mode, true); usleep_range(10000, 20000); - return ret; + return 0; } static int hns3_lp_down(struct net_device *ndev, enum hnae3_loop loop_mode) { - struct hnae3_handle *h = hns3_get_handle(ndev); int ret; - if (!h->ae_algo->ops->stop) - return -EOPNOTSUPP; - ret = hns3_lp_setup(ndev, loop_mode, false); if (ret) { netdev_err(ndev, "lb_setup return error: %d\n", ret); return ret; } - h->ae_algo->ops->stop(h); usleep_range(10000, 20000); return 0; @@ -152,6 +137,7 @@ static void hns3_lp_setup_skb(struct sk_buff *skb) packet = skb_put(skb, HNS3_NIC_LB_TEST_PACKET_SIZE); memcpy(ethh->h_dest, ndev->dev_addr, ETH_ALEN); + ethh->h_dest[5] += 0x1f; eth_zero_addr(ethh->h_source); ethh->h_proto = htons(ETH_P_ARP); skb_reset_mac_header(skb); @@ -309,7 +295,7 @@ static void hns3_self_test(struct net_device *ndev, h->flags & HNAE3_SUPPORT_SERDES_LOOPBACK; if (if_running) - dev_close(ndev); + ndev->netdev_ops->ndo_stop(ndev); #if IS_ENABLED(CONFIG_VLAN_8021Q) /* Disable the vlan filter for selftest does not support it */ @@ -347,7 +333,7 @@ static void hns3_self_test(struct net_device *ndev, #endif if (if_running) - dev_open(ndev); + ndev->netdev_ops->ndo_open(ndev); } static int hns3_get_sset_count(struct net_device *netdev, int stringset) @@ -560,26 +546,56 @@ static int hns3_get_link_ksettings(struct net_device *netdev, struct ethtool_link_ksettings *cmd) { struct hnae3_handle *h = hns3_get_handle(netdev); - u32 flowctrl_adv = 0; + const struct hnae3_ae_ops *ops; u8 link_stat; if (!h->ae_algo || !h->ae_algo->ops) return -EOPNOTSUPP; - /* 1.auto_neg & speed & duplex from cmd */ - if (netdev->phydev) { + ops = h->ae_algo->ops; + if (ops->get_port_type) + ops->get_port_type(h, &cmd->base.port); + else + return -EOPNOTSUPP; + + switch (cmd->base.port) { + case PORT_FIBRE: + /* 1.auto_neg & speed & duplex from cmd */ + if (ops->get_ksettings_an_result) + ops->get_ksettings_an_result(h, + &cmd->base.autoneg, + &cmd->base.speed, + &cmd->base.duplex); + else + return -EOPNOTSUPP; + + /* 2.get link mode*/ + if (ops->get_link_mode) + ops->get_link_mode(h, + cmd->link_modes.supported, + cmd->link_modes.advertising); + + /* 3.mdix_ctrl&mdix get from phy reg */ + if (ops->get_mdix_mode) + ops->get_mdix_mode(h, &cmd->base.eth_tp_mdix_ctrl, + &cmd->base.eth_tp_mdix); + + break; + case PORT_TP: + if (!netdev->phydev) + return -EOPNOTSUPP; + phy_ethtool_ksettings_get(netdev->phydev, cmd); + break; + default: + netdev_warn(netdev, + "Unknown port type, neither Fibre/Copper detected"); return 0; } - if (h->ae_algo->ops->get_ksettings_an_result) - h->ae_algo->ops->get_ksettings_an_result(h, - &cmd->base.autoneg, - &cmd->base.speed, - &cmd->base.duplex); - else - return -EOPNOTSUPP; + /* mdio_support */ + cmd->base.mdio_support = ETH_MDIO_SUPPORTS_C22; link_stat = hns3_get_link(netdev); if (!link_stat) { @@ -587,36 +603,6 @@ static int hns3_get_link_ksettings(struct net_device *netdev, cmd->base.duplex = DUPLEX_UNKNOWN; } - /* 2.get link mode and port type*/ - if (h->ae_algo->ops->get_link_mode) - h->ae_algo->ops->get_link_mode(h, - cmd->link_modes.supported, - cmd->link_modes.advertising); - - cmd->base.port = PORT_NONE; - if (h->ae_algo->ops->get_port_type) - h->ae_algo->ops->get_port_type(h, - &cmd->base.port); - - /* 3.mdix_ctrl&mdix get from phy reg */ - if (h->ae_algo->ops->get_mdix_mode) - h->ae_algo->ops->get_mdix_mode(h, &cmd->base.eth_tp_mdix_ctrl, - &cmd->base.eth_tp_mdix); - /* 4.mdio_support */ - cmd->base.mdio_support = ETH_MDIO_SUPPORTS_C22; - - /* 5.get flow control setttings */ - if (h->ae_algo->ops->get_flowctrl_adv) - h->ae_algo->ops->get_flowctrl_adv(h, &flowctrl_adv); - - if (flowctrl_adv & ADVERTISED_Pause) - ethtool_link_ksettings_add_link_mode(cmd, advertising, - Pause); - - if (flowctrl_adv & ADVERTISED_Asym_Pause) - ethtool_link_ksettings_add_link_mode(cmd, advertising, - Asym_Pause); - return 0; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 8577dfc799ad..cf18608669f5 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -2066,19 +2066,17 @@ static int hclge_init_msi(struct hclge_dev *hdev) return 0; } -static void hclge_check_speed_dup(struct hclge_dev *hdev, int duplex, int speed) +static u8 hclge_check_speed_dup(u8 duplex, int speed) { - struct hclge_mac *mac = &hdev->hw.mac; - if ((speed == HCLGE_MAC_SPEED_10M) || (speed == HCLGE_MAC_SPEED_100M)) - mac->duplex = (u8)duplex; - else - mac->duplex = HCLGE_MAC_FULL; + if (!(speed == HCLGE_MAC_SPEED_10M || speed == HCLGE_MAC_SPEED_100M)) + duplex = HCLGE_MAC_FULL; - mac->speed = speed; + return duplex; } -int hclge_cfg_mac_speed_dup(struct hclge_dev *hdev, int speed, u8 duplex) +static int hclge_cfg_mac_speed_dup_hw(struct hclge_dev *hdev, int speed, + u8 duplex) { struct hclge_config_mac_speed_dup_cmd *req; struct hclge_desc desc; @@ -2138,7 +2136,23 @@ int hclge_cfg_mac_speed_dup(struct hclge_dev *hdev, int speed, u8 duplex) return ret; } - hclge_check_speed_dup(hdev, duplex, speed); + return 0; +} + +int hclge_cfg_mac_speed_dup(struct hclge_dev *hdev, int speed, u8 duplex) +{ + int ret; + + duplex = hclge_check_speed_dup(duplex, speed); + if (hdev->hw.mac.speed == speed && hdev->hw.mac.duplex == duplex) + return 0; + + ret = hclge_cfg_mac_speed_dup_hw(hdev, speed, duplex); + if (ret) + return ret; + + hdev->hw.mac.speed = speed; + hdev->hw.mac.duplex = duplex; return 0; } @@ -2259,7 +2273,9 @@ static int hclge_mac_init(struct hclge_dev *hdev) int ret; int i; - ret = hclge_cfg_mac_speed_dup(hdev, hdev->hw.mac.speed, HCLGE_MAC_FULL); + hdev->hw.mac.duplex = HCLGE_MAC_FULL; + ret = hclge_cfg_mac_speed_dup_hw(hdev, hdev->hw.mac.speed, + hdev->hw.mac.duplex); if (ret) { dev_err(&hdev->pdev->dev, "Config mac speed dup fail ret=%d\n", ret); @@ -2415,13 +2431,11 @@ static int hclge_update_speed_duplex(struct hclge_dev *hdev) return ret; } - if ((mac.speed != speed) || (mac.duplex != duplex)) { - ret = hclge_cfg_mac_speed_dup(hdev, speed, duplex); - if (ret) { - dev_err(&hdev->pdev->dev, - "mac speed/duplex config failed %d\n", ret); - return ret; - } + ret = hclge_cfg_mac_speed_dup(hdev, speed, duplex); + if (ret) { + dev_err(&hdev->pdev->dev, + "mac speed/duplex config failed %d\n", ret); + return ret; } return 0; @@ -3659,6 +3673,8 @@ static int hclge_set_mac_loopback(struct hclge_dev *hdev, bool en) /* 2 Then setup the loopback flag */ loop_en = le32_to_cpu(req->txrx_pad_fcs_loop_en); hnae3_set_bit(loop_en, HCLGE_MAC_APP_LP_B, en ? 1 : 0); + hnae3_set_bit(loop_en, HCLGE_MAC_TX_EN_B, en ? 1 : 0); + hnae3_set_bit(loop_en, HCLGE_MAC_RX_EN_B, en ? 1 : 0); req->txrx_pad_fcs_loop_en = cpu_to_le32(loop_en); @@ -3719,15 +3735,36 @@ static int hclge_set_serdes_loopback(struct hclge_dev *hdev, bool en) return -EIO; } + hclge_cfg_mac_mode(hdev, en); return 0; } +static int hclge_tqp_enable(struct hclge_dev *hdev, int tqp_id, + int stream_id, bool enable) +{ + struct hclge_desc desc; + struct hclge_cfg_com_tqp_queue_cmd *req = + (struct hclge_cfg_com_tqp_queue_cmd *)desc.data; + int ret; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_COM_TQP_QUEUE, false); + req->tqp_id = cpu_to_le16(tqp_id & HCLGE_RING_ID_MASK); + req->stream_id = cpu_to_le16(stream_id); + req->enable |= enable << HCLGE_TQP_ENABLE_B; + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) + dev_err(&hdev->pdev->dev, + "Tqp enable fail, status =%d.\n", ret); + return ret; +} + static int hclge_set_loopback(struct hnae3_handle *handle, enum hnae3_loop loop_mode, bool en) { struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_dev *hdev = vport->back; - int ret; + int i, ret; switch (loop_mode) { case HNAE3_MAC_INTER_LOOP_MAC: @@ -3743,27 +3780,13 @@ static int hclge_set_loopback(struct hnae3_handle *handle, break; } - return ret; -} - -static int hclge_tqp_enable(struct hclge_dev *hdev, int tqp_id, - int stream_id, bool enable) -{ - struct hclge_desc desc; - struct hclge_cfg_com_tqp_queue_cmd *req = - (struct hclge_cfg_com_tqp_queue_cmd *)desc.data; - int ret; - - hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_COM_TQP_QUEUE, false); - req->tqp_id = cpu_to_le16(tqp_id & HCLGE_RING_ID_MASK); - req->stream_id = cpu_to_le16(stream_id); - req->enable |= enable << HCLGE_TQP_ENABLE_B; + for (i = 0; i < vport->alloc_tqps; i++) { + ret = hclge_tqp_enable(hdev, i, 0, en); + if (ret) + return ret; + } - ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) - dev_err(&hdev->pdev->dev, - "Tqp enable fail, status =%d.\n", ret); - return ret; + return 0; } static void hclge_reset_tqp_stats(struct hnae3_handle *handle) @@ -4362,7 +4385,7 @@ int hclge_add_mc_addr_common(struct hclge_vport *vport, hnae3_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1); hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0); hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 1); - hnae3_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 0); + hnae3_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 1); hclge_prepare_mac_addr(&req, addr); status = hclge_lookup_mac_vlan_tbl(vport, &req, desc, true); if (!status) { @@ -4429,7 +4452,7 @@ int hclge_rm_mc_addr_common(struct hclge_vport *vport, hnae3_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1); hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0); hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 1); - hnae3_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 0); + hnae3_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 1); hclge_prepare_mac_addr(&req, addr); status = hclge_lookup_mac_vlan_tbl(vport, &req, desc, true); if (!status) { @@ -4686,9 +4709,17 @@ static int hclge_set_vf_vlan_common(struct hclge_dev *hdev, int vfid, "Add vf vlan filter fail, ret =%d.\n", req0->resp_code); } else { +#define HCLGE_VF_VLAN_DEL_NO_FOUND 1 if (!req0->resp_code) return 0; + if (req0->resp_code == HCLGE_VF_VLAN_DEL_NO_FOUND) { + dev_warn(&hdev->pdev->dev, + "vlan %d filter is not in vf vlan table\n", + vlan); + return 0; + } + dev_err(&hdev->pdev->dev, "Kill vf vlan filter fail, ret =%d.\n", req0->resp_code); @@ -4732,6 +4763,9 @@ static int hclge_set_vlan_filter_hw(struct hclge_dev *hdev, __be16 proto, u16 vport_idx, vport_num = 0; int ret; + if (is_kill && !vlan_id) + return 0; + ret = hclge_set_vf_vlan_common(hdev, vport_id, is_kill, vlan_id, 0, proto); if (ret) { @@ -4761,7 +4795,7 @@ static int hclge_set_vlan_filter_hw(struct hclge_dev *hdev, __be16 proto, return -EINVAL; } - for_each_set_bit(vport_idx, hdev->vlan_table[vlan_id], VLAN_N_VID) + for_each_set_bit(vport_idx, hdev->vlan_table[vlan_id], HCLGE_VPORT_NUM) vport_num++; if ((is_kill && vport_num == 0) || (!is_kill && vport_num == 1)) @@ -5187,20 +5221,6 @@ static u32 hclge_get_fw_version(struct hnae3_handle *handle) return hdev->fw_version; } -static void hclge_get_flowctrl_adv(struct hnae3_handle *handle, - u32 *flowctrl_adv) -{ - struct hclge_vport *vport = hclge_get_vport(handle); - struct hclge_dev *hdev = vport->back; - struct phy_device *phydev = hdev->hw.mac.phydev; - - if (!phydev) - return; - - *flowctrl_adv |= (phydev->advertising & ADVERTISED_Pause) | - (phydev->advertising & ADVERTISED_Asym_Pause); -} - static void hclge_set_flowctrl_adv(struct hclge_dev *hdev, u32 rx_en, u32 tx_en) { struct phy_device *phydev = hdev->hw.mac.phydev; @@ -5208,13 +5228,7 @@ static void hclge_set_flowctrl_adv(struct hclge_dev *hdev, u32 rx_en, u32 tx_en) if (!phydev) return; - phydev->advertising &= ~(ADVERTISED_Pause | ADVERTISED_Asym_Pause); - - if (rx_en) - phydev->advertising |= ADVERTISED_Pause | ADVERTISED_Asym_Pause; - - if (tx_en) - phydev->advertising ^= ADVERTISED_Asym_Pause; + phy_set_asym_pause(phydev, rx_en, tx_en); } static int hclge_cfg_pauseparam(struct hclge_dev *hdev, u32 rx_en, u32 tx_en) @@ -6301,7 +6315,6 @@ static const struct hnae3_ae_ops hclge_ops = { .get_tqps_and_rss_info = hclge_get_tqps_and_rss_info, .set_channels = hclge_set_channels, .get_channels = hclge_get_channels, - .get_flowctrl_adv = hclge_get_flowctrl_adv, .get_regs_len = hclge_get_regs_len, .get_regs = hclge_get_regs, .set_led_id = hclge_set_led_id, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c index 398971a062f4..24b1f2a0c32a 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c @@ -10,8 +10,6 @@ #define HCLGE_PHY_SUPPORTED_FEATURES (SUPPORTED_Autoneg | \ SUPPORTED_TP | \ - SUPPORTED_Pause | \ - SUPPORTED_Asym_Pause | \ PHY_10BT_FEATURES | \ PHY_100BT_FEATURES | \ PHY_1000BT_FEATURES) @@ -213,7 +211,7 @@ int hclge_mac_connect_phy(struct hclge_dev *hdev) } phydev->supported &= HCLGE_PHY_SUPPORTED_FEATURES; - phydev->advertising = phydev->supported; + phy_support_asym_pause(phydev); return 0; } diff --git a/drivers/net/ethernet/hp/hp100.c b/drivers/net/ethernet/hp/hp100.c index c8c7ad2eff77..9b5a68b65432 100644 --- a/drivers/net/ethernet/hp/hp100.c +++ b/drivers/net/ethernet/hp/hp100.c @@ -2634,7 +2634,7 @@ static int hp100_login_to_vg_hub(struct net_device *dev, u_short force_relogin) /* Wait for link to drop */ time = jiffies + (HZ / 10); do { - if (~(hp100_inb(VG_LAN_CFG_1) & HP100_LINK_UP_ST)) + if (!(hp100_inb(VG_LAN_CFG_1) & HP100_LINK_UP_ST)) break; if (!in_interrupt()) schedule_timeout_interruptible(1); diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c index ba580bfae512..88128d3b6429 100644 --- a/drivers/net/ethernet/ibm/ehea/ehea_main.c +++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c @@ -2038,7 +2038,7 @@ static void ehea_xmit3(struct sk_buff *skb, struct net_device *dev, dev_consume_skb_any(skb); } -static int ehea_start_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t ehea_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct ehea_port *port = netdev_priv(dev); struct ehea_swqe *swqe; diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c index 354c0982847b..5107c9450a19 100644 --- a/drivers/net/ethernet/ibm/emac/core.c +++ b/drivers/net/ethernet/ibm/emac/core.c @@ -423,7 +423,7 @@ static void emac_hash_mc(struct emac_instance *dev) { const int regs = EMAC_XAHT_REGS(dev); u32 *gaht_base = emac_gaht_base(dev); - u32 gaht_temp[regs]; + u32 gaht_temp[EMAC_XAHT_MAX_REGS]; struct netdev_hw_addr *ha; int i; @@ -494,9 +494,6 @@ static u32 __emac_calc_base_mr1(struct emac_instance *dev, int tx_size, int rx_s case 16384: ret |= EMAC_MR1_RFS_16K; break; - case 8192: - ret |= EMAC4_MR1_RFS_8K; - break; case 4096: ret |= EMAC_MR1_RFS_4K; break; @@ -537,6 +534,9 @@ static u32 __emac4_calc_base_mr1(struct emac_instance *dev, int tx_size, int rx_ case 16384: ret |= EMAC4_MR1_RFS_16K; break; + case 8192: + ret |= EMAC4_MR1_RFS_8K; + break; case 4096: ret |= EMAC4_MR1_RFS_4K; break; @@ -1409,7 +1409,7 @@ static inline u16 emac_tx_csum(struct emac_instance *dev, return 0; } -static inline int emac_xmit_finish(struct emac_instance *dev, int len) +static inline netdev_tx_t emac_xmit_finish(struct emac_instance *dev, int len) { struct emac_regs __iomem *p = dev->emacp; struct net_device *ndev = dev->ndev; @@ -1436,7 +1436,7 @@ static inline int emac_xmit_finish(struct emac_instance *dev, int len) } /* Tx lock BH */ -static int emac_start_xmit(struct sk_buff *skb, struct net_device *ndev) +static netdev_tx_t emac_start_xmit(struct sk_buff *skb, struct net_device *ndev) { struct emac_instance *dev = netdev_priv(ndev); unsigned int len = skb->len; @@ -1494,7 +1494,8 @@ static inline int emac_xmit_split(struct emac_instance *dev, int slot, } /* Tx lock BH disabled (SG version for TAH equipped EMACs) */ -static int emac_start_xmit_sg(struct sk_buff *skb, struct net_device *ndev) +static netdev_tx_t +emac_start_xmit_sg(struct sk_buff *skb, struct net_device *ndev) { struct emac_instance *dev = netdev_priv(ndev); int nr_frags = skb_shinfo(skb)->nr_frags; @@ -2964,6 +2965,10 @@ static int emac_init_config(struct emac_instance *dev) dev->xaht_width_shift = EMAC4_XAHT_WIDTH_SHIFT; } + /* This should never happen */ + if (WARN_ON(EMAC_XAHT_REGS(dev) > EMAC_XAHT_MAX_REGS)) + return -ENXIO; + DBG(dev, "features : 0x%08x / 0x%08x\n", dev->features, EMAC_FTRS_POSSIBLE); DBG(dev, "tx_fifo_size : %d (%d gige)\n", dev->tx_fifo_size, dev->tx_fifo_size_gige); DBG(dev, "rx_fifo_size : %d (%d gige)\n", dev->rx_fifo_size, dev->rx_fifo_size_gige); diff --git a/drivers/net/ethernet/ibm/emac/core.h b/drivers/net/ethernet/ibm/emac/core.h index 369de2cfb15b..84caa4a3fc52 100644 --- a/drivers/net/ethernet/ibm/emac/core.h +++ b/drivers/net/ethernet/ibm/emac/core.h @@ -390,6 +390,9 @@ static inline int emac_has_feature(struct emac_instance *dev, #define EMAC4SYNC_XAHT_SLOTS_SHIFT 8 #define EMAC4SYNC_XAHT_WIDTH_SHIFT 5 +/* The largest span between slots and widths above is 3 */ +#define EMAC_XAHT_MAX_REGS (1 << 3) + #define EMAC_XAHT_SLOTS(dev) (1 << (dev)->xaht_slots_shift) #define EMAC_XAHT_WIDTH(dev) (1 << (dev)->xaht_width_shift) #define EMAC_XAHT_REGS(dev) (1 << ((dev)->xaht_slots_shift - \ diff --git a/drivers/net/ethernet/ibm/emac/mal.h b/drivers/net/ethernet/ibm/emac/mal.h index eeade2ea8334..e4c20f0024f6 100644 --- a/drivers/net/ethernet/ibm/emac/mal.h +++ b/drivers/net/ethernet/ibm/emac/mal.h @@ -136,7 +136,7 @@ static inline int mal_rx_size(int len) static inline int mal_tx_chunks(int len) { - return (len + MAL_MAX_TX_SIZE - 1) / MAL_MAX_TX_SIZE; + return DIV_ROUND_UP(len, MAL_MAX_TX_SIZE); } #define MAL_CHAN_MASK(n) (0x80000000 >> (n)) diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c index 525d8b89187b..a4681780a55d 100644 --- a/drivers/net/ethernet/ibm/ibmveth.c +++ b/drivers/net/ethernet/ibm/ibmveth.c @@ -24,7 +24,6 @@ */ #include <linux/module.h> -#include <linux/moduleparam.h> #include <linux/types.h> #include <linux/errno.h> #include <linux/dma-mapping.h> diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index dafdd4ade705..a8369addfe68 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -1428,7 +1428,7 @@ static int ibmvnic_xmit_workarounds(struct sk_buff *skb, return 0; } -static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) +static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) { struct ibmvnic_adapter *adapter = netdev_priv(netdev); int queue_num = skb_get_queue_mapping(skb); @@ -1452,7 +1452,7 @@ static int ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) u64 *handle_array; int index = 0; u8 proto = 0; - int ret = 0; + netdev_tx_t ret = NETDEV_TX_OK; if (adapter->resetting) { if (!netif_subqueue_stopped(netdev, skb)) @@ -1823,11 +1823,17 @@ static int do_reset(struct ibmvnic_adapter *adapter, adapter->map_id = 1; release_rx_pools(adapter); release_tx_pools(adapter); - init_rx_pools(netdev); - init_tx_pools(netdev); + rc = init_rx_pools(netdev); + if (rc) + return rc; + rc = init_tx_pools(netdev); + if (rc) + return rc; release_napi(adapter); - init_napi(adapter); + rc = init_napi(adapter); + if (rc) + return rc; } else { rc = reset_tx_pools(adapter); if (rc) diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig index 1ab613eb5796..b542aba6f0e8 100644 --- a/drivers/net/ethernet/intel/Kconfig +++ b/drivers/net/ethernet/intel/Kconfig @@ -235,20 +235,27 @@ config I40E_DCB If unsure, say N. +# this is here to allow seamless migration from I40EVF --> IAVF name +# so that CONFIG_IAVF symbol will always mirror the state of CONFIG_I40EVF +config IAVF + tristate config I40EVF tristate "Intel(R) Ethernet Adaptive Virtual Function support" + select IAVF depends on PCI_MSI ---help--- This driver supports virtual functions for Intel XL710, - X710, X722, and all devices advertising support for Intel - Ethernet Adaptive Virtual Function devices. For more + X710, X722, XXV710, and all devices advertising support for + Intel Ethernet Adaptive Virtual Function devices. For more information on how to identify your adapter, go to the Adapter & Driver ID Guide that can be located at: - <http://support.intel.com> + <https://support.intel.com> + + This driver was formerly named i40evf. To compile this driver as a module, choose M here. The module - will be called i40evf. MSI-X interrupt support is required + will be called iavf. MSI-X interrupt support is required for this driver to work correctly. config ICE diff --git a/drivers/net/ethernet/intel/Makefile b/drivers/net/ethernet/intel/Makefile index 807a4f8c7e4e..b91153df6ee8 100644 --- a/drivers/net/ethernet/intel/Makefile +++ b/drivers/net/ethernet/intel/Makefile @@ -12,6 +12,6 @@ obj-$(CONFIG_IXGBE) += ixgbe/ obj-$(CONFIG_IXGBEVF) += ixgbevf/ obj-$(CONFIG_I40E) += i40e/ obj-$(CONFIG_IXGB) += ixgb/ -obj-$(CONFIG_I40EVF) += i40evf/ +obj-$(CONFIG_IAVF) += iavf/ obj-$(CONFIG_FM10K) += fm10k/ obj-$(CONFIG_ICE) += ice/ diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c index 27d5f27163d2..7c4b55482f72 100644 --- a/drivers/net/ethernet/intel/e100.c +++ b/drivers/net/ethernet/intel/e100.c @@ -164,7 +164,7 @@ MODULE_DESCRIPTION(DRV_DESCRIPTION); MODULE_AUTHOR(DRV_COPYRIGHT); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); MODULE_VERSION(DRV_VERSION); MODULE_FIRMWARE(FIRMWARE_D101M); MODULE_FIRMWARE(FIRMWARE_D101S); diff --git a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c index bdb3f8e65ed4..2569a168334c 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c +++ b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c @@ -624,14 +624,14 @@ static int e1000_set_ringparam(struct net_device *netdev, adapter->tx_ring = tx_old; e1000_free_all_rx_resources(adapter); e1000_free_all_tx_resources(adapter); - kfree(tx_old); - kfree(rx_old); adapter->rx_ring = rxdr; adapter->tx_ring = txdr; err = e1000_up(adapter); if (err) goto err_setup; } + kfree(tx_old); + kfree(rx_old); clear_bit(__E1000_RESETTING, &adapter->flags); return 0; @@ -644,7 +644,8 @@ err_setup_rx: err_alloc_rx: kfree(txdr); err_alloc_tx: - e1000_up(adapter); + if (netif_running(adapter->netdev)) + e1000_up(adapter); err_setup: clear_bit(__E1000_RESETTING, &adapter->flags); return err; diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index 2110d5f2da19..7e0f1f96a8a1 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -195,7 +195,7 @@ static struct pci_driver e1000_driver = { MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION("Intel(R) PRO/1000 Network Driver"); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); MODULE_VERSION(DRV_VERSION); #define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV|NETIF_MSG_PROBE|NETIF_MSG_LINK) diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 3ba0c90e7055..c0f9faca70c4 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -7592,7 +7592,7 @@ module_exit(e1000_exit_module); MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION("Intel(R) PRO/1000 Network Driver"); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); MODULE_VERSION(DRV_VERSION); /* netdev.c */ diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index 3f536541f45f..503bbc017792 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -21,7 +21,7 @@ static const char fm10k_copyright[] = MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION(DRV_SUMMARY); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); MODULE_VERSION(DRV_VERSION); /* single workqueue for entire fm10k driver */ diff --git a/drivers/net/ethernet/intel/i40e/Makefile b/drivers/net/ethernet/intel/i40e/Makefile index 14397e7e9925..50590e8d1fd1 100644 --- a/drivers/net/ethernet/intel/i40e/Makefile +++ b/drivers/net/ethernet/intel/i40e/Makefile @@ -22,6 +22,7 @@ i40e-objs := i40e_main.o \ i40e_txrx.o \ i40e_ptp.o \ i40e_client.o \ - i40e_virtchnl_pf.o + i40e_virtchnl_pf.o \ + i40e_xsk.o i40e-$(CONFIG_I40E_DCB) += i40e_dcb.o i40e_dcb_nl.o diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 7a80652e2500..876cac317e79 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -786,6 +786,11 @@ struct i40e_vsi { /* VSI specific handlers */ irqreturn_t (*irq_handler)(int irq, void *data); + + /* AF_XDP zero-copy */ + struct xdp_umem **xsk_umems; + u16 num_xsk_umems_used; + u16 num_xsk_umems; } ____cacheline_internodealigned_in_smp; struct i40e_netdev_priv { @@ -1090,6 +1095,20 @@ static inline bool i40e_enabled_xdp_vsi(struct i40e_vsi *vsi) return !!vsi->xdp_prog; } +static inline struct xdp_umem *i40e_xsk_umem(struct i40e_ring *ring) +{ + bool xdp_on = i40e_enabled_xdp_vsi(ring->vsi); + int qid = ring->queue_index; + + if (ring_is_xdp(ring)) + qid -= ring->vsi->alloc_queue_pairs; + + if (!ring->vsi->xsk_umems || !ring->vsi->xsk_umems[qid] || !xdp_on) + return NULL; + + return ring->vsi->xsk_umems[qid]; +} + int i40e_create_queue_channel(struct i40e_vsi *vsi, struct i40e_channel *ch); int i40e_set_bw_limit(struct i40e_vsi *vsi, u16 seid, u64 max_tx_rate); int i40e_add_del_cloud_filter(struct i40e_vsi *vsi, diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index abcd096ede14..87fe2e60602f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -6,25 +6,225 @@ #include "i40e.h" #include "i40e_diag.h" +/* ethtool statistics helpers */ + +/** + * struct i40e_stats - definition for an ethtool statistic + * @stat_string: statistic name to display in ethtool -S output + * @sizeof_stat: the sizeof() the stat, must be no greater than sizeof(u64) + * @stat_offset: offsetof() the stat from a base pointer + * + * This structure defines a statistic to be added to the ethtool stats buffer. + * It defines a statistic as offset from a common base pointer. Stats should + * be defined in constant arrays using the I40E_STAT macro, with every element + * of the array using the same _type for calculating the sizeof_stat and + * stat_offset. + * + * The @sizeof_stat is expected to be sizeof(u8), sizeof(u16), sizeof(u32) or + * sizeof(u64). Other sizes are not expected and will produce a WARN_ONCE from + * the i40e_add_ethtool_stat() helper function. + * + * The @stat_string is interpreted as a format string, allowing formatted + * values to be inserted while looping over multiple structures for a given + * statistics array. Thus, every statistic string in an array should have the + * same type and number of format specifiers, to be formatted by variadic + * arguments to the i40e_add_stat_string() helper function. + **/ struct i40e_stats { - /* The stat_string is expected to be a format string formatted using - * vsnprintf by i40e_add_stat_strings. Every member of a stats array - * should use the same format specifiers as they will be formatted - * using the same variadic arguments. - */ char stat_string[ETH_GSTRING_LEN]; int sizeof_stat; int stat_offset; }; +/* Helper macro to define an i40e_stat structure with proper size and type. + * Use this when defining constant statistics arrays. Note that @_type expects + * only a type name and is used multiple times. + */ #define I40E_STAT(_type, _name, _stat) { \ .stat_string = _name, \ .sizeof_stat = FIELD_SIZEOF(_type, _stat), \ .stat_offset = offsetof(_type, _stat) \ } +/* Helper macro for defining some statistics directly copied from the netdev + * stats structure. + */ #define I40E_NETDEV_STAT(_net_stat) \ I40E_STAT(struct rtnl_link_stats64, #_net_stat, _net_stat) + +/* Helper macro for defining some statistics related to queues */ +#define I40E_QUEUE_STAT(_name, _stat) \ + I40E_STAT(struct i40e_ring, _name, _stat) + +/* Stats associated with a Tx or Rx ring */ +static const struct i40e_stats i40e_gstrings_queue_stats[] = { + I40E_QUEUE_STAT("%s-%u.packets", stats.packets), + I40E_QUEUE_STAT("%s-%u.bytes", stats.bytes), +}; + +/** + * i40e_add_one_ethtool_stat - copy the stat into the supplied buffer + * @data: location to store the stat value + * @pointer: basis for where to copy from + * @stat: the stat definition + * + * Copies the stat data defined by the pointer and stat structure pair into + * the memory supplied as data. Used to implement i40e_add_ethtool_stats and + * i40e_add_queue_stats. If the pointer is null, data will be zero'd. + */ +static void +i40e_add_one_ethtool_stat(u64 *data, void *pointer, + const struct i40e_stats *stat) +{ + char *p; + + if (!pointer) { + /* ensure that the ethtool data buffer is zero'd for any stats + * which don't have a valid pointer. + */ + *data = 0; + return; + } + + p = (char *)pointer + stat->stat_offset; + switch (stat->sizeof_stat) { + case sizeof(u64): + *data = *((u64 *)p); + break; + case sizeof(u32): + *data = *((u32 *)p); + break; + case sizeof(u16): + *data = *((u16 *)p); + break; + case sizeof(u8): + *data = *((u8 *)p); + break; + default: + WARN_ONCE(1, "unexpected stat size for %s", + stat->stat_string); + *data = 0; + } +} + +/** + * __i40e_add_ethtool_stats - copy stats into the ethtool supplied buffer + * @data: ethtool stats buffer + * @pointer: location to copy stats from + * @stats: array of stats to copy + * @size: the size of the stats definition + * + * Copy the stats defined by the stats array using the pointer as a base into + * the data buffer supplied by ethtool. Updates the data pointer to point to + * the next empty location for successive calls to __i40e_add_ethtool_stats. + * If pointer is null, set the data values to zero and update the pointer to + * skip these stats. + **/ +static void +__i40e_add_ethtool_stats(u64 **data, void *pointer, + const struct i40e_stats stats[], + const unsigned int size) +{ + unsigned int i; + + for (i = 0; i < size; i++) + i40e_add_one_ethtool_stat((*data)++, pointer, &stats[i]); +} + +/** + * i40e_add_ethtool_stats - copy stats into ethtool supplied buffer + * @data: ethtool stats buffer + * @pointer: location where stats are stored + * @stats: static const array of stat definitions + * + * Macro to ease the use of __i40e_add_ethtool_stats by taking a static + * constant stats array and passing the ARRAY_SIZE(). This avoids typos by + * ensuring that we pass the size associated with the given stats array. + * + * The parameter @stats is evaluated twice, so parameters with side effects + * should be avoided. + **/ +#define i40e_add_ethtool_stats(data, pointer, stats) \ + __i40e_add_ethtool_stats(data, pointer, stats, ARRAY_SIZE(stats)) + +/** + * i40e_add_queue_stats - copy queue statistics into supplied buffer + * @data: ethtool stats buffer + * @ring: the ring to copy + * + * Queue statistics must be copied while protected by + * u64_stats_fetch_begin_irq, so we can't directly use i40e_add_ethtool_stats. + * Assumes that queue stats are defined in i40e_gstrings_queue_stats. If the + * ring pointer is null, zero out the queue stat values and update the data + * pointer. Otherwise safely copy the stats from the ring into the supplied + * buffer and update the data pointer when finished. + * + * This function expects to be called while under rcu_read_lock(). + **/ +static void +i40e_add_queue_stats(u64 **data, struct i40e_ring *ring) +{ + const unsigned int size = ARRAY_SIZE(i40e_gstrings_queue_stats); + const struct i40e_stats *stats = i40e_gstrings_queue_stats; + unsigned int start; + unsigned int i; + + /* To avoid invalid statistics values, ensure that we keep retrying + * the copy until we get a consistent value according to + * u64_stats_fetch_retry_irq. But first, make sure our ring is + * non-null before attempting to access its syncp. + */ + do { + start = !ring ? 0 : u64_stats_fetch_begin_irq(&ring->syncp); + for (i = 0; i < size; i++) { + i40e_add_one_ethtool_stat(&(*data)[i], ring, + &stats[i]); + } + } while (ring && u64_stats_fetch_retry_irq(&ring->syncp, start)); + + /* Once we successfully copy the stats in, update the data pointer */ + *data += size; +} + +/** + * __i40e_add_stat_strings - copy stat strings into ethtool buffer + * @p: ethtool supplied buffer + * @stats: stat definitions array + * @size: size of the stats array + * + * Format and copy the strings described by stats into the buffer pointed at + * by p. + **/ +static void __i40e_add_stat_strings(u8 **p, const struct i40e_stats stats[], + const unsigned int size, ...) +{ + unsigned int i; + + for (i = 0; i < size; i++) { + va_list args; + + va_start(args, size); + vsnprintf(*p, ETH_GSTRING_LEN, stats[i].stat_string, args); + *p += ETH_GSTRING_LEN; + va_end(args); + } +} + +/** + * 40e_add_stat_strings - copy stat strings into ethtool buffer + * @p: ethtool supplied buffer + * @stats: stat definitions array + * + * Format and copy the strings described by the const static stats value into + * the buffer pointed at by p. + * + * The parameter @stats is evaluated twice, so parameters with side effects + * should be avoided. Additionally, stats must be an array such that + * ARRAY_SIZE can be called on it. + **/ +#define i40e_add_stat_strings(p, stats, ...) \ + __i40e_add_stat_strings(p, stats, ARRAY_SIZE(stats), ## __VA_ARGS__) + #define I40E_PF_STAT(_name, _stat) \ I40E_STAT(struct i40e_pf, _name, _stat) #define I40E_VSI_STAT(_name, _stat) \ @@ -33,6 +233,8 @@ struct i40e_stats { I40E_STAT(struct i40e_veb, _name, _stat) #define I40E_PFC_STAT(_name, _stat) \ I40E_STAT(struct i40e_pfc_stats, _name, _stat) +#define I40E_QUEUE_STAT(_name, _stat) \ + I40E_STAT(struct i40e_ring, _name, _stat) static const struct i40e_stats i40e_gstrings_net_stats[] = { I40E_NETDEV_STAT(rx_packets), @@ -171,20 +373,11 @@ static const struct i40e_stats i40e_gstrings_pfc_stats[] = { I40E_PFC_STAT("port.rx_priority_%u_xon_2_xoff", priority_xon_2_xoff), }; -/* We use num_tx_queues here as a proxy for the maximum number of queues - * available because we always allocate queues symmetrically. - */ -#define I40E_MAX_NUM_QUEUES(n) ((n)->num_tx_queues) -#define I40E_QUEUE_STATS_LEN(n) \ - (I40E_MAX_NUM_QUEUES(n) \ - * 2 /* Tx and Rx together */ \ - * (sizeof(struct i40e_queue_stats) / sizeof(u64))) -#define I40E_GLOBAL_STATS_LEN ARRAY_SIZE(i40e_gstrings_stats) #define I40E_NETDEV_STATS_LEN ARRAY_SIZE(i40e_gstrings_net_stats) + #define I40E_MISC_STATS_LEN ARRAY_SIZE(i40e_gstrings_misc_stats) -#define I40E_VSI_STATS_LEN(n) (I40E_NETDEV_STATS_LEN + \ - I40E_MISC_STATS_LEN + \ - I40E_QUEUE_STATS_LEN((n))) + +#define I40E_VSI_STATS_LEN (I40E_NETDEV_STATS_LEN + I40E_MISC_STATS_LEN) #define I40E_PFC_STATS_LEN (ARRAY_SIZE(i40e_gstrings_pfc_stats) * \ I40E_MAX_USER_PRIORITY) @@ -193,10 +386,15 @@ static const struct i40e_stats i40e_gstrings_pfc_stats[] = { (ARRAY_SIZE(i40e_gstrings_veb_tc_stats) * \ I40E_MAX_TRAFFIC_CLASS)) -#define I40E_PF_STATS_LEN(n) (I40E_GLOBAL_STATS_LEN + \ +#define I40E_GLOBAL_STATS_LEN ARRAY_SIZE(i40e_gstrings_stats) + +#define I40E_PF_STATS_LEN (I40E_GLOBAL_STATS_LEN + \ I40E_PFC_STATS_LEN + \ I40E_VEB_STATS_LEN + \ - I40E_VSI_STATS_LEN((n))) + I40E_VSI_STATS_LEN) + +/* Length of stats for a single queue */ +#define I40E_QUEUE_STATS_LEN ARRAY_SIZE(i40e_gstrings_queue_stats) enum i40e_ethtool_test_id { I40E_ETH_TEST_REG = 0, @@ -1701,11 +1899,30 @@ static int i40e_get_stats_count(struct net_device *netdev) struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; + int stats_len; if (vsi == pf->vsi[pf->lan_vsi] && pf->hw.partition_id == 1) - return I40E_PF_STATS_LEN(netdev); + stats_len = I40E_PF_STATS_LEN; else - return I40E_VSI_STATS_LEN(netdev); + stats_len = I40E_VSI_STATS_LEN; + + /* The number of stats reported for a given net_device must remain + * constant throughout the life of that device. + * + * This is because the API for obtaining the size, strings, and stats + * is spread out over three separate ethtool ioctls. There is no safe + * way to lock the number of stats across these calls, so we must + * assume that they will never change. + * + * Due to this, we report the maximum number of queues, even if not + * every queue is currently configured. Since we always allocate + * queues in pairs, we'll just use netdev->num_tx_queues * 2. This + * works because the num_tx_queues is set at device creation and never + * changes. + */ + stats_len += I40E_QUEUE_STATS_LEN * 2 * netdev->num_tx_queues; + + return stats_len; } static int i40e_get_sset_count(struct net_device *netdev, int sset) @@ -1728,89 +1945,6 @@ static int i40e_get_sset_count(struct net_device *netdev, int sset) } /** - * i40e_add_one_ethtool_stat - copy the stat into the supplied buffer - * @data: location to store the stat value - * @pointer: basis for where to copy from - * @stat: the stat definition - * - * Copies the stat data defined by the pointer and stat structure pair into - * the memory supplied as data. Used to implement i40e_add_ethtool_stats. - * If the pointer is null, data will be zero'd. - */ -static inline void -i40e_add_one_ethtool_stat(u64 *data, void *pointer, - const struct i40e_stats *stat) -{ - char *p; - - if (!pointer) { - /* ensure that the ethtool data buffer is zero'd for any stats - * which don't have a valid pointer. - */ - *data = 0; - return; - } - - p = (char *)pointer + stat->stat_offset; - switch (stat->sizeof_stat) { - case sizeof(u64): - *data = *((u64 *)p); - break; - case sizeof(u32): - *data = *((u32 *)p); - break; - case sizeof(u16): - *data = *((u16 *)p); - break; - case sizeof(u8): - *data = *((u8 *)p); - break; - default: - WARN_ONCE(1, "unexpected stat size for %s", - stat->stat_string); - *data = 0; - } -} - -/** - * __i40e_add_ethtool_stats - copy stats into the ethtool supplied buffer - * @data: ethtool stats buffer - * @pointer: location to copy stats from - * @stats: array of stats to copy - * @size: the size of the stats definition - * - * Copy the stats defined by the stats array using the pointer as a base into - * the data buffer supplied by ethtool. Updates the data pointer to point to - * the next empty location for successive calls to __i40e_add_ethtool_stats. - * If pointer is null, set the data values to zero and update the pointer to - * skip these stats. - **/ -static inline void -__i40e_add_ethtool_stats(u64 **data, void *pointer, - const struct i40e_stats stats[], - const unsigned int size) -{ - unsigned int i; - - for (i = 0; i < size; i++) - i40e_add_one_ethtool_stat((*data)++, pointer, &stats[i]); -} - -/** - * i40e_add_ethtool_stats - copy stats into ethtool supplied buffer - * @data: ethtool stats buffer - * @pointer: location where stats are stored - * @stats: static const array of stat definitions - * - * Macro to ease the use of __i40e_add_ethtool_stats by taking a static - * constant stats array and passing the ARRAY_SIZE(). This avoids typos by - * ensuring that we pass the size associated with the given stats array. - * Assumes that stats is an array. - **/ -#define i40e_add_ethtool_stats(data, pointer, stats) \ - __i40e_add_ethtool_stats(data, pointer, stats, ARRAY_SIZE(stats)) - -/** * i40e_get_pfc_stats - copy HW PFC statistics to formatted structure * @pf: the PF device structure * @i: the priority value to copy @@ -1853,12 +1987,10 @@ static void i40e_get_ethtool_stats(struct net_device *netdev, struct ethtool_stats *stats, u64 *data) { struct i40e_netdev_priv *np = netdev_priv(netdev); - struct i40e_ring *tx_ring, *rx_ring; struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; struct i40e_veb *veb = pf->veb[pf->lan_veb]; unsigned int i; - unsigned int start; bool veb_stats; u64 *p = data; @@ -1870,38 +2002,12 @@ static void i40e_get_ethtool_stats(struct net_device *netdev, i40e_add_ethtool_stats(&data, vsi, i40e_gstrings_misc_stats); rcu_read_lock(); - for (i = 0; i < I40E_MAX_NUM_QUEUES(netdev) ; i++) { - tx_ring = READ_ONCE(vsi->tx_rings[i]); - - if (!tx_ring) { - /* Bump the stat counter to skip these stats, and make - * sure the memory is zero'd - */ - *(data++) = 0; - *(data++) = 0; - *(data++) = 0; - *(data++) = 0; - continue; - } - - /* process Tx ring statistics */ - do { - start = u64_stats_fetch_begin_irq(&tx_ring->syncp); - data[0] = tx_ring->stats.packets; - data[1] = tx_ring->stats.bytes; - } while (u64_stats_fetch_retry_irq(&tx_ring->syncp, start)); - data += 2; - - /* Rx ring is the 2nd half of the queue pair */ - rx_ring = &tx_ring[1]; - do { - start = u64_stats_fetch_begin_irq(&rx_ring->syncp); - data[0] = rx_ring->stats.packets; - data[1] = rx_ring->stats.bytes; - } while (u64_stats_fetch_retry_irq(&rx_ring->syncp, start)); - data += 2; + for (i = 0; i < netdev->num_tx_queues; i++) { + i40e_add_queue_stats(&data, READ_ONCE(vsi->tx_rings[i])); + i40e_add_queue_stats(&data, READ_ONCE(vsi->rx_rings[i])); } rcu_read_unlock(); + if (vsi != pf->vsi[pf->lan_vsi] || pf->hw.partition_id != 1) goto check_data_pointer; @@ -1933,42 +2039,6 @@ check_data_pointer: } /** - * __i40e_add_stat_strings - copy stat strings into ethtool buffer - * @p: ethtool supplied buffer - * @stats: stat definitions array - * @size: size of the stats array - * - * Format and copy the strings described by stats into the buffer pointed at - * by p. - **/ -static void __i40e_add_stat_strings(u8 **p, const struct i40e_stats stats[], - const unsigned int size, ...) -{ - unsigned int i; - - for (i = 0; i < size; i++) { - va_list args; - - va_start(args, size); - vsnprintf(*p, ETH_GSTRING_LEN, stats[i].stat_string, args); - *p += ETH_GSTRING_LEN; - va_end(args); - } -} - -/** - * 40e_add_stat_strings - copy stat strings into ethtool buffer - * @p: ethtool supplied buffer - * @stats: stat definitions array - * - * Format and copy the strings described by the const static stats value into - * the buffer pointed at by p. Assumes that stats can have ARRAY_SIZE called - * for it. - **/ -#define i40e_add_stat_strings(p, stats, ...) \ - __i40e_add_stat_strings(p, stats, ARRAY_SIZE(stats), ## __VA_ARGS__) - -/** * i40e_get_stat_strings - copy stat strings into supplied buffer * @netdev: the netdev to collect strings for * @data: supplied buffer to copy strings into @@ -1990,16 +2060,13 @@ static void i40e_get_stat_strings(struct net_device *netdev, u8 *data) i40e_add_stat_strings(&data, i40e_gstrings_misc_stats); - for (i = 0; i < I40E_MAX_NUM_QUEUES(netdev); i++) { - snprintf(data, ETH_GSTRING_LEN, "tx-%u.tx_packets", i); - data += ETH_GSTRING_LEN; - snprintf(data, ETH_GSTRING_LEN, "tx-%u.tx_bytes", i); - data += ETH_GSTRING_LEN; - snprintf(data, ETH_GSTRING_LEN, "rx-%u.rx_packets", i); - data += ETH_GSTRING_LEN; - snprintf(data, ETH_GSTRING_LEN, "rx-%u.rx_bytes", i); - data += ETH_GSTRING_LEN; + for (i = 0; i < netdev->num_tx_queues; i++) { + i40e_add_stat_strings(&data, i40e_gstrings_queue_stats, + "tx", i); + i40e_add_stat_strings(&data, i40e_gstrings_queue_stats, + "rx", i); } + if (vsi != pf->vsi[pf->lan_vsi] || pf->hw.partition_id != 1) return; @@ -2013,7 +2080,7 @@ static void i40e_get_stat_strings(struct net_device *netdev, u8 *data) for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) i40e_add_stat_strings(&data, i40e_gstrings_pfc_stats, i); - WARN_ONCE(p - data != i40e_get_stats_count(netdev) * ETH_GSTRING_LEN, + WARN_ONCE(data - p != i40e_get_stats_count(netdev) * ETH_GSTRING_LEN, "stat strings count mismatch!"); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index f2c622e78802..c7d2c9010fdf 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -9,7 +9,9 @@ /* Local includes */ #include "i40e.h" #include "i40e_diag.h" +#include "i40e_xsk.h" #include <net/udp_tunnel.h> +#include <net/xdp_sock.h> /* All i40e tracepoints are defined by the include below, which * must be included exactly once across the whole kernel with * CREATE_TRACE_POINTS defined @@ -89,7 +91,7 @@ MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all), Debug mask (0x8XXXXXXX MODULE_AUTHOR("Intel Corporation, <e1000-devel@lists.sourceforge.net>"); MODULE_DESCRIPTION("Intel(R) Ethernet Connection XL710 Network Driver"); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); MODULE_VERSION(DRV_VERSION); static struct workqueue_struct *i40e_wq; @@ -420,9 +422,9 @@ static void i40e_get_netdev_stats_struct(struct net_device *netdev, struct rtnl_link_stats64 *stats) { struct i40e_netdev_priv *np = netdev_priv(netdev); - struct i40e_ring *tx_ring, *rx_ring; struct i40e_vsi *vsi = np->vsi; struct rtnl_link_stats64 *vsi_stats = i40e_get_vsi_stats_struct(vsi); + struct i40e_ring *ring; int i; if (test_bit(__I40E_VSI_DOWN, vsi->state)) @@ -436,24 +438,26 @@ static void i40e_get_netdev_stats_struct(struct net_device *netdev, u64 bytes, packets; unsigned int start; - tx_ring = READ_ONCE(vsi->tx_rings[i]); - if (!tx_ring) + ring = READ_ONCE(vsi->tx_rings[i]); + if (!ring) continue; - i40e_get_netdev_stats_struct_tx(tx_ring, stats); + i40e_get_netdev_stats_struct_tx(ring, stats); - rx_ring = &tx_ring[1]; + if (i40e_enabled_xdp_vsi(vsi)) { + ring++; + i40e_get_netdev_stats_struct_tx(ring, stats); + } + ring++; do { - start = u64_stats_fetch_begin_irq(&rx_ring->syncp); - packets = rx_ring->stats.packets; - bytes = rx_ring->stats.bytes; - } while (u64_stats_fetch_retry_irq(&rx_ring->syncp, start)); + start = u64_stats_fetch_begin_irq(&ring->syncp); + packets = ring->stats.packets; + bytes = ring->stats.bytes; + } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); stats->rx_packets += packets; stats->rx_bytes += bytes; - if (i40e_enabled_xdp_vsi(vsi)) - i40e_get_netdev_stats_struct_tx(&rx_ring[1], stats); } rcu_read_unlock(); @@ -3072,6 +3076,9 @@ static int i40e_configure_tx_ring(struct i40e_ring *ring) i40e_status err = 0; u32 qtx_ctl = 0; + if (ring_is_xdp(ring)) + ring->xsk_umem = i40e_xsk_umem(ring); + /* some ATR related tx ring init */ if (vsi->back->flags & I40E_FLAG_FD_ATR_ENABLED) { ring->atr_sample_rate = vsi->back->atr_sample_rate; @@ -3181,13 +3188,46 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) struct i40e_hw *hw = &vsi->back->hw; struct i40e_hmc_obj_rxq rx_ctx; i40e_status err = 0; + bool ok; + int ret; bitmap_zero(ring->state, __I40E_RING_STATE_NBITS); /* clear the context structure first */ memset(&rx_ctx, 0, sizeof(rx_ctx)); - ring->rx_buf_len = vsi->rx_buf_len; + if (ring->vsi->type == I40E_VSI_MAIN) + xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); + + ring->xsk_umem = i40e_xsk_umem(ring); + if (ring->xsk_umem) { + ring->rx_buf_len = ring->xsk_umem->chunk_size_nohr - + XDP_PACKET_HEADROOM; + /* For AF_XDP ZC, we disallow packets to span on + * multiple buffers, thus letting us skip that + * handling in the fast-path. + */ + chain_len = 1; + ring->zca.free = i40e_zca_free; + ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, + MEM_TYPE_ZERO_COPY, + &ring->zca); + if (ret) + return ret; + dev_info(&vsi->back->pdev->dev, + "Registered XDP mem model MEM_TYPE_ZERO_COPY on Rx ring %d\n", + ring->queue_index); + + } else { + ring->rx_buf_len = vsi->rx_buf_len; + if (ring->vsi->type == I40E_VSI_MAIN) { + ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, + MEM_TYPE_PAGE_SHARED, + NULL); + if (ret) + return ret; + } + } rx_ctx.dbuff = DIV_ROUND_UP(ring->rx_buf_len, BIT_ULL(I40E_RXQ_CTX_DBUFF_SHIFT)); @@ -3243,7 +3283,15 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) ring->tail = hw->hw_addr + I40E_QRX_TAIL(pf_q); writel(0, ring->tail); - i40e_alloc_rx_buffers(ring, I40E_DESC_UNUSED(ring)); + ok = ring->xsk_umem ? + i40e_alloc_rx_buffers_zc(ring, I40E_DESC_UNUSED(ring)) : + !i40e_alloc_rx_buffers(ring, I40E_DESC_UNUSED(ring)); + if (!ok) { + dev_info(&vsi->back->pdev->dev, + "Failed allocate some buffers on %sRx ring %d (pf_q %d)\n", + ring->xsk_umem ? "UMEM enabled " : "", + ring->queue_index, pf_q); + } return 0; } @@ -5122,15 +5170,17 @@ static int i40e_vsi_configure_bw_alloc(struct i40e_vsi *vsi, u8 enabled_tc, u8 *bw_share) { struct i40e_aqc_configure_vsi_tc_bw_data bw_data; + struct i40e_pf *pf = vsi->back; i40e_status ret; int i; - if (vsi->back->flags & I40E_FLAG_TC_MQPRIO) + /* There is no need to reset BW when mqprio mode is on. */ + if (pf->flags & I40E_FLAG_TC_MQPRIO) return 0; - if (!vsi->mqprio_qopt.qopt.hw) { + if (!vsi->mqprio_qopt.qopt.hw && !(pf->flags & I40E_FLAG_DCB_ENABLED)) { ret = i40e_set_bw_limit(vsi, vsi->seid, 0); if (ret) - dev_info(&vsi->back->pdev->dev, + dev_info(&pf->pdev->dev, "Failed to reset tx rate for vsi->seid %u\n", vsi->seid); return ret; @@ -5139,12 +5189,11 @@ static int i40e_vsi_configure_bw_alloc(struct i40e_vsi *vsi, u8 enabled_tc, for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) bw_data.tc_bw_credits[i] = bw_share[i]; - ret = i40e_aq_config_vsi_tc_bw(&vsi->back->hw, vsi->seid, &bw_data, - NULL); + ret = i40e_aq_config_vsi_tc_bw(&pf->hw, vsi->seid, &bw_data, NULL); if (ret) { - dev_info(&vsi->back->pdev->dev, + dev_info(&pf->pdev->dev, "AQ command Config VSI BW allocation per TC failed = %d\n", - vsi->back->hw.aq.asq_last_status); + pf->hw.aq.asq_last_status); return -EINVAL; } @@ -6567,6 +6616,24 @@ static i40e_status i40e_force_link_state(struct i40e_pf *pf, bool is_up) struct i40e_hw *hw = &pf->hw; i40e_status err; u64 mask; + u8 speed; + + /* Card might've been put in an unstable state by other drivers + * and applications, which causes incorrect speed values being + * set on startup. In order to clear speed registers, we call + * get_phy_capabilities twice, once to get initial state of + * available speeds, and once to get current PHY config. + */ + err = i40e_aq_get_phy_capabilities(hw, false, true, &abilities, + NULL); + if (err) { + dev_err(&pf->pdev->dev, + "failed to get phy cap., ret = %s last_status = %s\n", + i40e_stat_str(hw, err), + i40e_aq_str(hw, hw->aq.asq_last_status)); + return err; + } + speed = abilities.link_speed; /* Get the current phy config */ err = i40e_aq_get_phy_capabilities(hw, false, false, &abilities, @@ -6580,9 +6647,9 @@ static i40e_status i40e_force_link_state(struct i40e_pf *pf, bool is_up) } /* If link needs to go up, but was not forced to go down, - * no need for a flap + * and its speed values are OK, no need for a flap */ - if (is_up && abilities.phy_type != 0) + if (is_up && abilities.phy_type != 0 && abilities.link_speed != 0) return I40E_SUCCESS; /* To force link we need to set bits for all supported PHY types, @@ -6594,7 +6661,10 @@ static i40e_status i40e_force_link_state(struct i40e_pf *pf, bool is_up) config.phy_type_ext = is_up ? (u8)((mask >> 32) & 0xff) : 0; /* Copy the old settings, except of phy_type */ config.abilities = abilities.abilities; - config.link_speed = abilities.link_speed; + if (abilities.link_speed != 0) + config.link_speed = abilities.link_speed; + else + config.link_speed = speed; config.eee_capability = abilities.eee_capability; config.eeer = abilities.eeer_val; config.low_power_ctrl = abilities.d3_lpan; @@ -11827,6 +11897,256 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, } /** + * i40e_enter_busy_conf - Enters busy config state + * @vsi: vsi + * + * Returns 0 on success, <0 for failure. + **/ +static int i40e_enter_busy_conf(struct i40e_vsi *vsi) +{ + struct i40e_pf *pf = vsi->back; + int timeout = 50; + + while (test_and_set_bit(__I40E_CONFIG_BUSY, pf->state)) { + timeout--; + if (!timeout) + return -EBUSY; + usleep_range(1000, 2000); + } + + return 0; +} + +/** + * i40e_exit_busy_conf - Exits busy config state + * @vsi: vsi + **/ +static void i40e_exit_busy_conf(struct i40e_vsi *vsi) +{ + struct i40e_pf *pf = vsi->back; + + clear_bit(__I40E_CONFIG_BUSY, pf->state); +} + +/** + * i40e_queue_pair_reset_stats - Resets all statistics for a queue pair + * @vsi: vsi + * @queue_pair: queue pair + **/ +static void i40e_queue_pair_reset_stats(struct i40e_vsi *vsi, int queue_pair) +{ + memset(&vsi->rx_rings[queue_pair]->rx_stats, 0, + sizeof(vsi->rx_rings[queue_pair]->rx_stats)); + memset(&vsi->tx_rings[queue_pair]->stats, 0, + sizeof(vsi->tx_rings[queue_pair]->stats)); + if (i40e_enabled_xdp_vsi(vsi)) { + memset(&vsi->xdp_rings[queue_pair]->stats, 0, + sizeof(vsi->xdp_rings[queue_pair]->stats)); + } +} + +/** + * i40e_queue_pair_clean_rings - Cleans all the rings of a queue pair + * @vsi: vsi + * @queue_pair: queue pair + **/ +static void i40e_queue_pair_clean_rings(struct i40e_vsi *vsi, int queue_pair) +{ + i40e_clean_tx_ring(vsi->tx_rings[queue_pair]); + if (i40e_enabled_xdp_vsi(vsi)) + i40e_clean_tx_ring(vsi->xdp_rings[queue_pair]); + i40e_clean_rx_ring(vsi->rx_rings[queue_pair]); +} + +/** + * i40e_queue_pair_toggle_napi - Enables/disables NAPI for a queue pair + * @vsi: vsi + * @queue_pair: queue pair + * @enable: true for enable, false for disable + **/ +static void i40e_queue_pair_toggle_napi(struct i40e_vsi *vsi, int queue_pair, + bool enable) +{ + struct i40e_ring *rxr = vsi->rx_rings[queue_pair]; + struct i40e_q_vector *q_vector = rxr->q_vector; + + if (!vsi->netdev) + return; + + /* All rings in a qp belong to the same qvector. */ + if (q_vector->rx.ring || q_vector->tx.ring) { + if (enable) + napi_enable(&q_vector->napi); + else + napi_disable(&q_vector->napi); + } +} + +/** + * i40e_queue_pair_toggle_rings - Enables/disables all rings for a queue pair + * @vsi: vsi + * @queue_pair: queue pair + * @enable: true for enable, false for disable + * + * Returns 0 on success, <0 on failure. + **/ +static int i40e_queue_pair_toggle_rings(struct i40e_vsi *vsi, int queue_pair, + bool enable) +{ + struct i40e_pf *pf = vsi->back; + int pf_q, ret = 0; + + pf_q = vsi->base_queue + queue_pair; + ret = i40e_control_wait_tx_q(vsi->seid, pf, pf_q, + false /*is xdp*/, enable); + if (ret) { + dev_info(&pf->pdev->dev, + "VSI seid %d Tx ring %d %sable timeout\n", + vsi->seid, pf_q, (enable ? "en" : "dis")); + return ret; + } + + i40e_control_rx_q(pf, pf_q, enable); + ret = i40e_pf_rxq_wait(pf, pf_q, enable); + if (ret) { + dev_info(&pf->pdev->dev, + "VSI seid %d Rx ring %d %sable timeout\n", + vsi->seid, pf_q, (enable ? "en" : "dis")); + return ret; + } + + /* Due to HW errata, on Rx disable only, the register can + * indicate done before it really is. Needs 50ms to be sure + */ + if (!enable) + mdelay(50); + + if (!i40e_enabled_xdp_vsi(vsi)) + return ret; + + ret = i40e_control_wait_tx_q(vsi->seid, pf, + pf_q + vsi->alloc_queue_pairs, + true /*is xdp*/, enable); + if (ret) { + dev_info(&pf->pdev->dev, + "VSI seid %d XDP Tx ring %d %sable timeout\n", + vsi->seid, pf_q, (enable ? "en" : "dis")); + } + + return ret; +} + +/** + * i40e_queue_pair_enable_irq - Enables interrupts for a queue pair + * @vsi: vsi + * @queue_pair: queue_pair + **/ +static void i40e_queue_pair_enable_irq(struct i40e_vsi *vsi, int queue_pair) +{ + struct i40e_ring *rxr = vsi->rx_rings[queue_pair]; + struct i40e_pf *pf = vsi->back; + struct i40e_hw *hw = &pf->hw; + + /* All rings in a qp belong to the same qvector. */ + if (pf->flags & I40E_FLAG_MSIX_ENABLED) + i40e_irq_dynamic_enable(vsi, rxr->q_vector->v_idx); + else + i40e_irq_dynamic_enable_icr0(pf); + + i40e_flush(hw); +} + +/** + * i40e_queue_pair_disable_irq - Disables interrupts for a queue pair + * @vsi: vsi + * @queue_pair: queue_pair + **/ +static void i40e_queue_pair_disable_irq(struct i40e_vsi *vsi, int queue_pair) +{ + struct i40e_ring *rxr = vsi->rx_rings[queue_pair]; + struct i40e_pf *pf = vsi->back; + struct i40e_hw *hw = &pf->hw; + + /* For simplicity, instead of removing the qp interrupt causes + * from the interrupt linked list, we simply disable the interrupt, and + * leave the list intact. + * + * All rings in a qp belong to the same qvector. + */ + if (pf->flags & I40E_FLAG_MSIX_ENABLED) { + u32 intpf = vsi->base_vector + rxr->q_vector->v_idx; + + wr32(hw, I40E_PFINT_DYN_CTLN(intpf - 1), 0); + i40e_flush(hw); + synchronize_irq(pf->msix_entries[intpf].vector); + } else { + /* Legacy and MSI mode - this stops all interrupt handling */ + wr32(hw, I40E_PFINT_ICR0_ENA, 0); + wr32(hw, I40E_PFINT_DYN_CTL0, 0); + i40e_flush(hw); + synchronize_irq(pf->pdev->irq); + } +} + +/** + * i40e_queue_pair_disable - Disables a queue pair + * @vsi: vsi + * @queue_pair: queue pair + * + * Returns 0 on success, <0 on failure. + **/ +int i40e_queue_pair_disable(struct i40e_vsi *vsi, int queue_pair) +{ + int err; + + err = i40e_enter_busy_conf(vsi); + if (err) + return err; + + i40e_queue_pair_disable_irq(vsi, queue_pair); + err = i40e_queue_pair_toggle_rings(vsi, queue_pair, false /* off */); + i40e_queue_pair_toggle_napi(vsi, queue_pair, false /* off */); + i40e_queue_pair_clean_rings(vsi, queue_pair); + i40e_queue_pair_reset_stats(vsi, queue_pair); + + return err; +} + +/** + * i40e_queue_pair_enable - Enables a queue pair + * @vsi: vsi + * @queue_pair: queue pair + * + * Returns 0 on success, <0 on failure. + **/ +int i40e_queue_pair_enable(struct i40e_vsi *vsi, int queue_pair) +{ + int err; + + err = i40e_configure_tx_ring(vsi->tx_rings[queue_pair]); + if (err) + return err; + + if (i40e_enabled_xdp_vsi(vsi)) { + err = i40e_configure_tx_ring(vsi->xdp_rings[queue_pair]); + if (err) + return err; + } + + err = i40e_configure_rx_ring(vsi->rx_rings[queue_pair]); + if (err) + return err; + + err = i40e_queue_pair_toggle_rings(vsi, queue_pair, true /* on */); + i40e_queue_pair_toggle_napi(vsi, queue_pair, true /* on */); + i40e_queue_pair_enable_irq(vsi, queue_pair); + + i40e_exit_busy_conf(vsi); + + return err; +} + +/** * i40e_xdp - implements ndo_bpf for i40e * @dev: netdevice * @xdp: XDP command @@ -11846,6 +12166,12 @@ static int i40e_xdp(struct net_device *dev, case XDP_QUERY_PROG: xdp->prog_id = vsi->xdp_prog ? vsi->xdp_prog->aux->id : 0; return 0; + case XDP_QUERY_XSK_UMEM: + return i40e_xsk_umem_query(vsi, &xdp->xsk.umem, + xdp->xsk.queue_id); + case XDP_SETUP_XSK_UMEM: + return i40e_xsk_umem_setup(vsi, xdp->xsk.umem, + xdp->xsk.queue_id); default: return -EINVAL; } @@ -11885,6 +12211,7 @@ static const struct net_device_ops i40e_netdev_ops = { .ndo_bridge_setlink = i40e_ndo_bridge_setlink, .ndo_bpf = i40e_xdp, .ndo_xdp_xmit = i40e_xdp_xmit, + .ndo_xsk_async_xmit = i40e_xsk_async_xmit, }; /** @@ -13032,7 +13359,7 @@ struct i40e_veb *i40e_veb_setup(struct i40e_pf *pf, u16 flags, for (vsi_idx = 0; vsi_idx < pf->num_alloc_vsi; vsi_idx++) if (pf->vsi[vsi_idx] && pf->vsi[vsi_idx]->seid == vsi_seid) break; - if (vsi_idx >= pf->num_alloc_vsi && vsi_seid != 0) { + if (vsi_idx == pf->num_alloc_vsi && vsi_seid != 0) { dev_info(&pf->pdev->dev, "vsi seid %d not found\n", vsi_seid); return NULL; @@ -14158,6 +14485,7 @@ static void i40e_remove(struct pci_dev *pdev) mutex_destroy(&hw->aq.asq_mutex); /* Clear all dynamic memory lists of rings, q_vectors, and VSIs */ + rtnl_lock(); i40e_clear_interrupt_scheme(pf); for (i = 0; i < pf->num_alloc_vsi; i++) { if (pf->vsi[i]) { @@ -14166,6 +14494,7 @@ static void i40e_remove(struct pci_dev *pdev) pf->vsi[i] = NULL; } } + rtnl_unlock(); for (i = 0; i < I40E_MAX_VEB; i++) { kfree(pf->veb[i]); @@ -14377,7 +14706,13 @@ static void i40e_shutdown(struct pci_dev *pdev) wr32(hw, I40E_PFPM_WUFC, (pf->wol_en ? I40E_PFPM_WUFC_MAG_MASK : 0)); + /* Since we're going to destroy queues during the + * i40e_clear_interrupt_scheme() we should hold the RTNL lock for this + * whole section + */ + rtnl_lock(); i40e_clear_interrupt_scheme(pf); + rtnl_unlock(); if (system_state == SYSTEM_POWER_OFF) { pci_wake_from_d3(pdev, pf->wol_en); diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c index 35f2866b38c6..1199f0502d6d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c @@ -694,7 +694,8 @@ static long i40e_ptp_create_clock(struct i40e_pf *pf) if (!IS_ERR_OR_NULL(pf->ptp_clock)) return 0; - strncpy(pf->ptp_caps.name, i40e_driver_name, sizeof(pf->ptp_caps.name)); + strncpy(pf->ptp_caps.name, i40e_driver_name, + sizeof(pf->ptp_caps.name) - 1); pf->ptp_caps.owner = THIS_MODULE; pf->ptp_caps.max_adj = 999999999; pf->ptp_caps.n_ext_ts = 0; diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index b5042d1a63c0..37bd4e50ccde 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -8,16 +8,8 @@ #include "i40e.h" #include "i40e_trace.h" #include "i40e_prototype.h" - -static inline __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size, - u32 td_tag) -{ - return cpu_to_le64(I40E_TX_DESC_DTYPE_DATA | - ((u64)td_cmd << I40E_TXD_QW1_CMD_SHIFT) | - ((u64)td_offset << I40E_TXD_QW1_OFFSET_SHIFT) | - ((u64)size << I40E_TXD_QW1_TX_BUF_SZ_SHIFT) | - ((u64)td_tag << I40E_TXD_QW1_L2TAG1_SHIFT)); -} +#include "i40e_txrx_common.h" +#include "i40e_xsk.h" #define I40E_TXD_CMD (I40E_TX_DESC_CMD_EOP | I40E_TX_DESC_CMD_RS) /** @@ -536,8 +528,8 @@ int i40e_add_del_fdir(struct i40e_vsi *vsi, * This is used to verify if the FD programming or invalidation * requested by SW to the HW is successful or not and take actions accordingly. **/ -static void i40e_fd_handle_status(struct i40e_ring *rx_ring, - union i40e_rx_desc *rx_desc, u8 prog_id) +void i40e_fd_handle_status(struct i40e_ring *rx_ring, + union i40e_rx_desc *rx_desc, u8 prog_id) { struct i40e_pf *pf = rx_ring->vsi->back; struct pci_dev *pdev = pf->pdev; @@ -767,8 +759,6 @@ void i40e_detect_recover_hung(struct i40e_vsi *vsi) } } -#define WB_STRIDE 4 - /** * i40e_clean_tx_irq - Reclaim resources after transmit completes * @vsi: the VSI we care about @@ -873,27 +863,8 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, i += tx_ring->count; tx_ring->next_to_clean = i; - u64_stats_update_begin(&tx_ring->syncp); - tx_ring->stats.bytes += total_bytes; - tx_ring->stats.packets += total_packets; - u64_stats_update_end(&tx_ring->syncp); - tx_ring->q_vector->tx.total_bytes += total_bytes; - tx_ring->q_vector->tx.total_packets += total_packets; - - if (tx_ring->flags & I40E_TXR_FLAGS_WB_ON_ITR) { - /* 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. - */ - unsigned int j = i40e_get_tx_pending(tx_ring, false); - - if (budget && - ((j / WB_STRIDE) == 0) && (j > 0) && - !test_bit(__I40E_VSI_DOWN, vsi->state) && - (I40E_DESC_UNUSED(tx_ring) != tx_ring->count)) - tx_ring->arm_wb = true; - } + i40e_update_tx_stats(tx_ring, total_packets, total_bytes); + i40e_arm_wb(tx_ring, vsi, budget); if (ring_is_xdp(tx_ring)) return !!budget; @@ -1244,6 +1215,11 @@ static void i40e_reuse_rx_page(struct i40e_ring *rx_ring, new_buff->page = old_buff->page; new_buff->page_offset = old_buff->page_offset; new_buff->pagecnt_bias = old_buff->pagecnt_bias; + + rx_ring->rx_stats.page_reuse_count++; + + /* clear contents of buffer_info */ + old_buff->page = NULL; } /** @@ -1266,7 +1242,7 @@ static inline bool i40e_rx_is_programming_status(u64 qw) } /** - * i40e_clean_programming_status - clean the programming status descriptor + * i40e_clean_programming_status - try clean the programming status descriptor * @rx_ring: the rx ring that has this descriptor * @rx_desc: the rx descriptor written back by HW * @qw: qword representing status_error_len in CPU ordering @@ -1275,15 +1251,22 @@ static inline bool i40e_rx_is_programming_status(u64 qw) * status being successful or not and take actions accordingly. FCoE should * handle its context/filter programming/invalidation status and take actions. * + * Returns an i40e_rx_buffer to reuse if the cleanup occurred, otherwise NULL. **/ -static void i40e_clean_programming_status(struct i40e_ring *rx_ring, - union i40e_rx_desc *rx_desc, - u64 qw) +struct i40e_rx_buffer *i40e_clean_programming_status( + struct i40e_ring *rx_ring, + union i40e_rx_desc *rx_desc, + u64 qw) { struct i40e_rx_buffer *rx_buffer; - u32 ntc = rx_ring->next_to_clean; + u32 ntc; u8 id; + if (!i40e_rx_is_programming_status(qw)) + return NULL; + + ntc = rx_ring->next_to_clean; + /* fetch, update, and store next to clean */ rx_buffer = &rx_ring->rx_bi[ntc++]; ntc = (ntc < rx_ring->count) ? ntc : 0; @@ -1291,18 +1274,13 @@ static void i40e_clean_programming_status(struct i40e_ring *rx_ring, prefetch(I40E_RX_DESC(rx_ring, ntc)); - /* place unused page back on the ring */ - i40e_reuse_rx_page(rx_ring, rx_buffer); - rx_ring->rx_stats.page_reuse_count++; - - /* clear contents of buffer_info */ - rx_buffer->page = NULL; - id = (qw & I40E_RX_PROG_STATUS_DESC_QW1_PROGID_MASK) >> I40E_RX_PROG_STATUS_DESC_QW1_PROGID_SHIFT; if (id == I40E_RX_PROG_STATUS_DESC_FD_FILTER_STATUS) i40e_fd_handle_status(rx_ring, rx_desc, id); + + return rx_buffer; } /** @@ -1372,6 +1350,9 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring) rx_ring->skb = NULL; } + if (rx_ring->xsk_umem) + goto skip_free; + /* Free all the Rx ring sk_buffs */ for (i = 0; i < rx_ring->count; i++) { struct i40e_rx_buffer *rx_bi = &rx_ring->rx_bi[i]; @@ -1400,6 +1381,7 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring) rx_bi->page_offset = 0; } +skip_free: bi_size = sizeof(struct i40e_rx_buffer) * rx_ring->count; memset(rx_ring->rx_bi, 0, bi_size); @@ -1492,7 +1474,7 @@ err: * @rx_ring: ring to bump * @val: new head index **/ -static inline void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val) +void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val) { rx_ring->next_to_use = val; @@ -1576,8 +1558,8 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring, * @skb: packet to send up * @vlan_tag: vlan tag for packet **/ -static void i40e_receive_skb(struct i40e_ring *rx_ring, - struct sk_buff *skb, u16 vlan_tag) +void i40e_receive_skb(struct i40e_ring *rx_ring, + struct sk_buff *skb, u16 vlan_tag) { struct i40e_q_vector *q_vector = rx_ring->q_vector; @@ -1804,7 +1786,6 @@ static inline void i40e_rx_hash(struct i40e_ring *ring, * order to populate the hash, checksum, VLAN, protocol, and * other fields within the skb. **/ -static inline void i40e_process_skb_fields(struct i40e_ring *rx_ring, union i40e_rx_desc *rx_desc, struct sk_buff *skb, u8 rx_ptype) @@ -2152,7 +2133,6 @@ static void i40e_put_rx_buffer(struct i40e_ring *rx_ring, if (i40e_can_reuse_rx_page(rx_buffer)) { /* hand second half of page back to the ring */ i40e_reuse_rx_page(rx_ring, rx_buffer); - rx_ring->rx_stats.page_reuse_count++; } else { /* we are not reusing the buffer so unmap it */ dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, @@ -2160,10 +2140,9 @@ static void i40e_put_rx_buffer(struct i40e_ring *rx_ring, DMA_FROM_DEVICE, I40E_RX_DMA_ATTR); __page_frag_cache_drain(rx_buffer->page, rx_buffer->pagecnt_bias); + /* clear contents of buffer_info */ + rx_buffer->page = NULL; } - - /* clear contents of buffer_info */ - rx_buffer->page = NULL; } /** @@ -2199,16 +2178,10 @@ static bool i40e_is_non_eop(struct i40e_ring *rx_ring, return true; } -#define I40E_XDP_PASS 0 -#define I40E_XDP_CONSUMED BIT(0) -#define I40E_XDP_TX BIT(1) -#define I40E_XDP_REDIR BIT(2) - static int i40e_xmit_xdp_ring(struct xdp_frame *xdpf, struct i40e_ring *xdp_ring); -static int i40e_xmit_xdp_tx_ring(struct xdp_buff *xdp, - struct i40e_ring *xdp_ring) +int i40e_xmit_xdp_tx_ring(struct xdp_buff *xdp, struct i40e_ring *xdp_ring) { struct xdp_frame *xdpf = convert_to_xdp_frame(xdp); @@ -2287,7 +2260,13 @@ static void i40e_rx_buffer_flip(struct i40e_ring *rx_ring, #endif } -static inline void i40e_xdp_ring_update_tail(struct i40e_ring *xdp_ring) +/** + * i40e_xdp_ring_update_tail - Updates the XDP Tx ring tail register + * @xdp_ring: XDP Tx ring + * + * This function updates the XDP Tx ring tail register. + **/ +void i40e_xdp_ring_update_tail(struct i40e_ring *xdp_ring) { /* Force memory writes to complete before letting h/w * know there are new descriptors to fetch. @@ -2297,6 +2276,48 @@ static inline void i40e_xdp_ring_update_tail(struct i40e_ring *xdp_ring) } /** + * i40e_update_rx_stats - Update Rx ring statistics + * @rx_ring: rx descriptor ring + * @total_rx_bytes: number of bytes received + * @total_rx_packets: number of packets received + * + * This function updates the Rx ring statistics. + **/ +void i40e_update_rx_stats(struct i40e_ring *rx_ring, + unsigned int total_rx_bytes, + unsigned int total_rx_packets) +{ + u64_stats_update_begin(&rx_ring->syncp); + rx_ring->stats.packets += total_rx_packets; + rx_ring->stats.bytes += total_rx_bytes; + u64_stats_update_end(&rx_ring->syncp); + rx_ring->q_vector->rx.total_packets += total_rx_packets; + rx_ring->q_vector->rx.total_bytes += total_rx_bytes; +} + +/** + * i40e_finalize_xdp_rx - Bump XDP Tx tail and/or flush redirect map + * @rx_ring: Rx ring + * @xdp_res: Result of the receive batch + * + * This function bumps XDP Tx tail and/or flush redirect map, and + * should be called when a batch of packets has been processed in the + * napi loop. + **/ +void i40e_finalize_xdp_rx(struct i40e_ring *rx_ring, unsigned int xdp_res) +{ + if (xdp_res & I40E_XDP_REDIR) + xdp_do_flush_map(); + + if (xdp_res & I40E_XDP_TX) { + struct i40e_ring *xdp_ring = + rx_ring->vsi->xdp_rings[rx_ring->queue_index]; + + i40e_xdp_ring_update_tail(xdp_ring); + } +} + +/** * i40e_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf * @rx_ring: rx descriptor ring to transact packets on * @budget: Total limit on number of packets to process @@ -2349,11 +2370,14 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) */ dma_rmb(); - if (unlikely(i40e_rx_is_programming_status(qword))) { - i40e_clean_programming_status(rx_ring, rx_desc, qword); + rx_buffer = i40e_clean_programming_status(rx_ring, rx_desc, + qword); + if (unlikely(rx_buffer)) { + i40e_reuse_rx_page(rx_ring, rx_buffer); cleaned_count++; continue; } + size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >> I40E_RXD_QW1_LENGTH_PBUF_SHIFT; if (!size) @@ -2432,24 +2456,10 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) total_rx_packets++; } - if (xdp_xmit & I40E_XDP_REDIR) - xdp_do_flush_map(); - - if (xdp_xmit & I40E_XDP_TX) { - struct i40e_ring *xdp_ring = - rx_ring->vsi->xdp_rings[rx_ring->queue_index]; - - i40e_xdp_ring_update_tail(xdp_ring); - } - + i40e_finalize_xdp_rx(rx_ring, xdp_xmit); rx_ring->skb = skb; - u64_stats_update_begin(&rx_ring->syncp); - rx_ring->stats.packets += total_rx_packets; - rx_ring->stats.bytes += total_rx_bytes; - u64_stats_update_end(&rx_ring->syncp); - rx_ring->q_vector->rx.total_packets += total_rx_packets; - rx_ring->q_vector->rx.total_bytes += total_rx_bytes; + i40e_update_rx_stats(rx_ring, total_rx_bytes, total_rx_packets); /* guarantee a trip back through this routine if there was a failure */ return failure ? budget : (int)total_rx_packets; @@ -2587,7 +2597,11 @@ int i40e_napi_poll(struct napi_struct *napi, int budget) * budget and be more aggressive about cleaning up the Tx descriptors. */ i40e_for_each_ring(ring, q_vector->tx) { - if (!i40e_clean_tx_irq(vsi, ring, budget)) { + bool wd = ring->xsk_umem ? + i40e_clean_xdp_tx_irq(vsi, ring, budget) : + i40e_clean_tx_irq(vsi, ring, budget); + + if (!wd) { clean_complete = false; continue; } @@ -2605,7 +2619,9 @@ int i40e_napi_poll(struct napi_struct *napi, int budget) budget_per_ring = max(budget/q_vector->num_ringpairs, 1); i40e_for_each_ring(ring, q_vector->rx) { - int cleaned = i40e_clean_rx_irq(ring, budget_per_ring); + int cleaned = ring->xsk_umem ? + i40e_clean_rx_irq_zc(ring, budget_per_ring) : + i40e_clean_rx_irq(ring, budget_per_ring); work_done += cleaned; /* if we clean as many as budgeted, we must not be done */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index bb04f6a731fe..100e92d2982f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -296,13 +296,17 @@ struct i40e_tx_buffer { struct i40e_rx_buffer { dma_addr_t dma; - struct page *page; -#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536) - __u32 page_offset; -#else - __u16 page_offset; -#endif - __u16 pagecnt_bias; + union { + struct { + struct page *page; + __u32 page_offset; + __u16 pagecnt_bias; + }; + struct { + void *addr; + u64 handle; + }; + }; }; struct i40e_queue_stats { @@ -414,6 +418,8 @@ struct i40e_ring { struct i40e_channel *ch; struct xdp_rxq_info xdp_rxq; + struct xdp_umem *xsk_umem; + struct zero_copy_allocator zca; /* ZC allocator anchor */ } ____cacheline_internodealigned_in_smp; static inline bool ring_uses_build_skb(struct i40e_ring *ring) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h b/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h new file mode 100644 index 000000000000..b5afd479a9c5 --- /dev/null +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h @@ -0,0 +1,90 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2018 Intel Corporation. */ + +#ifndef I40E_TXRX_COMMON_ +#define I40E_TXRX_COMMON_ + +void i40e_fd_handle_status(struct i40e_ring *rx_ring, + union i40e_rx_desc *rx_desc, u8 prog_id); +int i40e_xmit_xdp_tx_ring(struct xdp_buff *xdp, struct i40e_ring *xdp_ring); +struct i40e_rx_buffer *i40e_clean_programming_status( + struct i40e_ring *rx_ring, + union i40e_rx_desc *rx_desc, + u64 qw); +void i40e_process_skb_fields(struct i40e_ring *rx_ring, + union i40e_rx_desc *rx_desc, struct sk_buff *skb, + u8 rx_ptype); +void i40e_receive_skb(struct i40e_ring *rx_ring, + struct sk_buff *skb, u16 vlan_tag); +void i40e_xdp_ring_update_tail(struct i40e_ring *xdp_ring); +void i40e_update_rx_stats(struct i40e_ring *rx_ring, + unsigned int total_rx_bytes, + unsigned int total_rx_packets); +void i40e_finalize_xdp_rx(struct i40e_ring *rx_ring, unsigned int xdp_res); +void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val); + +#define I40E_XDP_PASS 0 +#define I40E_XDP_CONSUMED BIT(0) +#define I40E_XDP_TX BIT(1) +#define I40E_XDP_REDIR BIT(2) + +/** + * build_ctob - Builds the Tx descriptor (cmd, offset and type) qword + **/ +static inline __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size, + u32 td_tag) +{ + return cpu_to_le64(I40E_TX_DESC_DTYPE_DATA | + ((u64)td_cmd << I40E_TXD_QW1_CMD_SHIFT) | + ((u64)td_offset << I40E_TXD_QW1_OFFSET_SHIFT) | + ((u64)size << I40E_TXD_QW1_TX_BUF_SZ_SHIFT) | + ((u64)td_tag << I40E_TXD_QW1_L2TAG1_SHIFT)); +} + +/** + * i40e_update_tx_stats - Update the egress statistics for the Tx ring + * @tx_ring: Tx ring to update + * @total_packet: total packets sent + * @total_bytes: total bytes sent + **/ +static inline void i40e_update_tx_stats(struct i40e_ring *tx_ring, + unsigned int total_packets, + unsigned int total_bytes) +{ + u64_stats_update_begin(&tx_ring->syncp); + tx_ring->stats.bytes += total_bytes; + tx_ring->stats.packets += total_packets; + u64_stats_update_end(&tx_ring->syncp); + tx_ring->q_vector->tx.total_bytes += total_bytes; + tx_ring->q_vector->tx.total_packets += total_packets; +} + +#define WB_STRIDE 4 + +/** + * i40e_arm_wb - (Possibly) arms Tx write-back + * @tx_ring: Tx ring to update + * @vsi: the VSI + * @budget: the NAPI budget left + **/ +static inline void i40e_arm_wb(struct i40e_ring *tx_ring, + struct i40e_vsi *vsi, + int budget) +{ + if (tx_ring->flags & I40E_TXR_FLAGS_WB_ON_ITR) { + /* 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. + */ + unsigned int j = i40e_get_tx_pending(tx_ring, false); + + if (budget && + ((j / WB_STRIDE) == 0) && j > 0 && + !test_bit(__I40E_VSI_DOWN, vsi->state) && + (I40E_DESC_UNUSED(tx_ring) != tx_ring->count)) + tx_ring->arm_wb = true; + } +} + +#endif /* I40E_TXRX_COMMON_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index c6d24eaede18..3e707c7e6782 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -2458,7 +2458,7 @@ static inline int i40e_check_vf_permission(struct i40e_vf *vf, !is_multicast_ether_addr(addr) && vf->pf_set_mac && !ether_addr_equal(addr, vf->default_lan_addr.addr)) { dev_err(&pf->pdev->dev, - "VF attempting to override administratively set MAC address, reload the VF driver to resume normal operation\n"); + "VF attempting to override administratively set MAC address, bring down and up the VF interface to resume normal operation\n"); return -EPERM; } } @@ -2569,6 +2569,16 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) ret = I40E_ERR_INVALID_MAC_ADDR; goto error_param; } + + if (vf->pf_set_mac && + ether_addr_equal(al->list[i].addr, + vf->default_lan_addr.addr)) { + dev_err(&pf->pdev->dev, + "MAC addr %pM has been set by PF, cannot delete it for VF %d, reset VF to change MAC addr\n", + vf->default_lan_addr.addr, vf->vf_id); + ret = I40E_ERR_PARAM; + goto error_param; + } } vsi = pf->vsi[vf->lan_vsi_idx]; @@ -3873,9 +3883,11 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) mac, vf_id); } - /* Force the VF driver stop so it has to reload with new MAC address */ + /* Force the VF interface down so it has to bring up with new MAC + * address + */ i40e_vc_disable_vf(vf); - dev_info(&pf->pdev->dev, "Reload the VF driver to make this change effective.\n"); + dev_info(&pf->pdev->dev, "Bring down and up the VF interface to make this change effective.\n"); error_param: return ret; diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c new file mode 100644 index 000000000000..2ebfc78bbd09 --- /dev/null +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -0,0 +1,832 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2018 Intel Corporation. */ + +#include <linux/bpf_trace.h> +#include <net/xdp_sock.h> +#include <net/xdp.h> + +#include "i40e.h" +#include "i40e_txrx_common.h" +#include "i40e_xsk.h" + +/** + * i40e_alloc_xsk_umems - Allocate an array to store per ring UMEMs + * @vsi: Current VSI + * + * Returns 0 on success, <0 on failure + **/ +static int i40e_alloc_xsk_umems(struct i40e_vsi *vsi) +{ + if (vsi->xsk_umems) + return 0; + + vsi->num_xsk_umems_used = 0; + vsi->num_xsk_umems = vsi->alloc_queue_pairs; + vsi->xsk_umems = kcalloc(vsi->num_xsk_umems, sizeof(*vsi->xsk_umems), + GFP_KERNEL); + if (!vsi->xsk_umems) { + vsi->num_xsk_umems = 0; + return -ENOMEM; + } + + return 0; +} + +/** + * i40e_add_xsk_umem - Store an UMEM for a certain ring/qid + * @vsi: Current VSI + * @umem: UMEM to store + * @qid: Ring/qid to associate with the UMEM + * + * Returns 0 on success, <0 on failure + **/ +static int i40e_add_xsk_umem(struct i40e_vsi *vsi, struct xdp_umem *umem, + u16 qid) +{ + int err; + + err = i40e_alloc_xsk_umems(vsi); + if (err) + return err; + + vsi->xsk_umems[qid] = umem; + vsi->num_xsk_umems_used++; + + return 0; +} + +/** + * i40e_remove_xsk_umem - Remove an UMEM for a certain ring/qid + * @vsi: Current VSI + * @qid: Ring/qid associated with the UMEM + **/ +static void i40e_remove_xsk_umem(struct i40e_vsi *vsi, u16 qid) +{ + vsi->xsk_umems[qid] = NULL; + vsi->num_xsk_umems_used--; + + if (vsi->num_xsk_umems == 0) { + kfree(vsi->xsk_umems); + vsi->xsk_umems = NULL; + vsi->num_xsk_umems = 0; + } +} + +/** + * i40e_xsk_umem_dma_map - DMA maps all UMEM memory for the netdev + * @vsi: Current VSI + * @umem: UMEM to DMA map + * + * Returns 0 on success, <0 on failure + **/ +static int i40e_xsk_umem_dma_map(struct i40e_vsi *vsi, struct xdp_umem *umem) +{ + struct i40e_pf *pf = vsi->back; + struct device *dev; + unsigned int i, j; + dma_addr_t dma; + + dev = &pf->pdev->dev; + for (i = 0; i < umem->npgs; i++) { + dma = dma_map_page_attrs(dev, umem->pgs[i], 0, PAGE_SIZE, + DMA_BIDIRECTIONAL, I40E_RX_DMA_ATTR); + if (dma_mapping_error(dev, dma)) + goto out_unmap; + + umem->pages[i].dma = dma; + } + + return 0; + +out_unmap: + for (j = 0; j < i; j++) { + dma_unmap_page_attrs(dev, umem->pages[i].dma, PAGE_SIZE, + DMA_BIDIRECTIONAL, I40E_RX_DMA_ATTR); + umem->pages[i].dma = 0; + } + + return -1; +} + +/** + * i40e_xsk_umem_dma_unmap - DMA unmaps all UMEM memory for the netdev + * @vsi: Current VSI + * @umem: UMEM to DMA map + **/ +static void i40e_xsk_umem_dma_unmap(struct i40e_vsi *vsi, struct xdp_umem *umem) +{ + struct i40e_pf *pf = vsi->back; + struct device *dev; + unsigned int i; + + dev = &pf->pdev->dev; + + for (i = 0; i < umem->npgs; i++) { + dma_unmap_page_attrs(dev, umem->pages[i].dma, PAGE_SIZE, + DMA_BIDIRECTIONAL, I40E_RX_DMA_ATTR); + + umem->pages[i].dma = 0; + } +} + +/** + * i40e_xsk_umem_enable - Enable/associate an UMEM to a certain ring/qid + * @vsi: Current VSI + * @umem: UMEM + * @qid: Rx ring to associate UMEM to + * + * Returns 0 on success, <0 on failure + **/ +static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem, + u16 qid) +{ + bool if_running; + int err; + + if (vsi->type != I40E_VSI_MAIN) + return -EINVAL; + + if (qid >= vsi->num_queue_pairs) + return -EINVAL; + + if (vsi->xsk_umems) { + if (qid >= vsi->num_xsk_umems) + return -EINVAL; + if (vsi->xsk_umems[qid]) + return -EBUSY; + } + + err = i40e_xsk_umem_dma_map(vsi, umem); + if (err) + return err; + + if_running = netif_running(vsi->netdev) && i40e_enabled_xdp_vsi(vsi); + + if (if_running) { + err = i40e_queue_pair_disable(vsi, qid); + if (err) + return err; + } + + err = i40e_add_xsk_umem(vsi, umem, qid); + if (err) + return err; + + if (if_running) { + err = i40e_queue_pair_enable(vsi, qid); + if (err) + return err; + } + + return 0; +} + +/** + * i40e_xsk_umem_disable - Diassociate an UMEM from a certain ring/qid + * @vsi: Current VSI + * @qid: Rx ring to associate UMEM to + * + * Returns 0 on success, <0 on failure + **/ +static int i40e_xsk_umem_disable(struct i40e_vsi *vsi, u16 qid) +{ + bool if_running; + int err; + + if (!vsi->xsk_umems || qid >= vsi->num_xsk_umems || + !vsi->xsk_umems[qid]) + return -EINVAL; + + if_running = netif_running(vsi->netdev) && i40e_enabled_xdp_vsi(vsi); + + if (if_running) { + err = i40e_queue_pair_disable(vsi, qid); + if (err) + return err; + } + + i40e_xsk_umem_dma_unmap(vsi, vsi->xsk_umems[qid]); + i40e_remove_xsk_umem(vsi, qid); + + if (if_running) { + err = i40e_queue_pair_enable(vsi, qid); + if (err) + return err; + } + + return 0; +} + +/** + * i40e_xsk_umem_query - Queries a certain ring/qid for its UMEM + * @vsi: Current VSI + * @umem: UMEM associated to the ring, if any + * @qid: Rx ring to associate UMEM to + * + * This function will store, if any, the UMEM associated to certain ring. + * + * Returns 0 on success, <0 on failure + **/ +int i40e_xsk_umem_query(struct i40e_vsi *vsi, struct xdp_umem **umem, + u16 qid) +{ + if (vsi->type != I40E_VSI_MAIN) + return -EINVAL; + + if (qid >= vsi->num_queue_pairs) + return -EINVAL; + + if (vsi->xsk_umems) { + if (qid >= vsi->num_xsk_umems) + return -EINVAL; + *umem = vsi->xsk_umems[qid]; + return 0; + } + + *umem = NULL; + return 0; +} + +/** + * i40e_xsk_umem_query - Queries a certain ring/qid for its UMEM + * @vsi: Current VSI + * @umem: UMEM to enable/associate to a ring, or NULL to disable + * @qid: Rx ring to (dis)associate UMEM (from)to + * + * This function enables or disables an UMEM to a certain ring. + * + * Returns 0 on success, <0 on failure + **/ +int i40e_xsk_umem_setup(struct i40e_vsi *vsi, struct xdp_umem *umem, + u16 qid) +{ + return umem ? i40e_xsk_umem_enable(vsi, umem, qid) : + i40e_xsk_umem_disable(vsi, qid); +} + +/** + * i40e_run_xdp_zc - Executes an XDP program on an xdp_buff + * @rx_ring: Rx ring + * @xdp: xdp_buff used as input to the XDP program + * + * This function enables or disables an UMEM to a certain ring. + * + * Returns any of I40E_XDP_{PASS, CONSUMED, TX, REDIR} + **/ +static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp) +{ + int err, result = I40E_XDP_PASS; + struct i40e_ring *xdp_ring; + struct bpf_prog *xdp_prog; + u32 act; + + rcu_read_lock(); + /* NB! xdp_prog will always be !NULL, due to the fact that + * this path is enabled by setting an XDP program. + */ + xdp_prog = READ_ONCE(rx_ring->xdp_prog); + act = bpf_prog_run_xdp(xdp_prog, xdp); + xdp->handle += xdp->data - xdp->data_hard_start; + switch (act) { + case XDP_PASS: + break; + case XDP_TX: + xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->queue_index]; + result = i40e_xmit_xdp_tx_ring(xdp, xdp_ring); + break; + case XDP_REDIRECT: + err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); + result = !err ? I40E_XDP_REDIR : I40E_XDP_CONSUMED; + break; + default: + bpf_warn_invalid_xdp_action(act); + case XDP_ABORTED: + trace_xdp_exception(rx_ring->netdev, xdp_prog, act); + /* fallthrough -- handle aborts by dropping packet */ + case XDP_DROP: + result = I40E_XDP_CONSUMED; + break; + } + rcu_read_unlock(); + return result; +} + +/** + * i40e_alloc_buffer_zc - Allocates an i40e_rx_buffer + * @rx_ring: Rx ring + * @bi: Rx buffer to populate + * + * This function allocates an Rx buffer. The buffer can come from fill + * queue, or via the recycle queue (next_to_alloc). + * + * Returns true for a successful allocation, false otherwise + **/ +static bool i40e_alloc_buffer_zc(struct i40e_ring *rx_ring, + struct i40e_rx_buffer *bi) +{ + struct xdp_umem *umem = rx_ring->xsk_umem; + void *addr = bi->addr; + u64 handle, hr; + + if (addr) { + rx_ring->rx_stats.page_reuse_count++; + return true; + } + + if (!xsk_umem_peek_addr(umem, &handle)) { + rx_ring->rx_stats.alloc_page_failed++; + return false; + } + + hr = umem->headroom + XDP_PACKET_HEADROOM; + + bi->dma = xdp_umem_get_dma(umem, handle); + bi->dma += hr; + + bi->addr = xdp_umem_get_data(umem, handle); + bi->addr += hr; + + bi->handle = handle + umem->headroom; + + xsk_umem_discard_addr(umem); + return true; +} + +/** + * i40e_alloc_rx_buffers_zc - Allocates a number of Rx buffers + * @rx_ring: Rx ring + * @count: The number of buffers to allocate + * + * This function allocates a number of Rx buffers and places them on + * the Rx ring. + * + * Returns true for a successful allocation, false otherwise + **/ +bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count) +{ + u16 ntu = rx_ring->next_to_use; + union i40e_rx_desc *rx_desc; + struct i40e_rx_buffer *bi; + bool ok = true; + + rx_desc = I40E_RX_DESC(rx_ring, ntu); + bi = &rx_ring->rx_bi[ntu]; + do { + if (!i40e_alloc_buffer_zc(rx_ring, bi)) { + ok = false; + goto no_buffers; + } + + dma_sync_single_range_for_device(rx_ring->dev, bi->dma, 0, + rx_ring->rx_buf_len, + DMA_BIDIRECTIONAL); + + rx_desc->read.pkt_addr = cpu_to_le64(bi->dma); + + rx_desc++; + bi++; + ntu++; + + if (unlikely(ntu == rx_ring->count)) { + rx_desc = I40E_RX_DESC(rx_ring, 0); + bi = rx_ring->rx_bi; + ntu = 0; + } + + rx_desc->wb.qword1.status_error_len = 0; + count--; + } while (count); + +no_buffers: + if (rx_ring->next_to_use != ntu) + i40e_release_rx_desc(rx_ring, ntu); + + return ok; +} + +/** + * i40e_get_rx_buffer_zc - Return the current Rx buffer + * @rx_ring: Rx ring + * @size: The size of the rx buffer (read from descriptor) + * + * This function returns the current, received Rx buffer, and also + * does DMA synchronization. the Rx ring. + * + * Returns the received Rx buffer + **/ +static struct i40e_rx_buffer *i40e_get_rx_buffer_zc(struct i40e_ring *rx_ring, + const unsigned int size) +{ + struct i40e_rx_buffer *bi; + + bi = &rx_ring->rx_bi[rx_ring->next_to_clean]; + + /* we are reusing so sync this buffer for CPU use */ + dma_sync_single_range_for_cpu(rx_ring->dev, + bi->dma, 0, + size, + DMA_BIDIRECTIONAL); + + return bi; +} + +/** + * i40e_reuse_rx_buffer_zc - Recycle an Rx buffer + * @rx_ring: Rx ring + * @old_bi: The Rx buffer to recycle + * + * This function recycles a finished Rx buffer, and places it on the + * recycle queue (next_to_alloc). + **/ +static void i40e_reuse_rx_buffer_zc(struct i40e_ring *rx_ring, + struct i40e_rx_buffer *old_bi) +{ + struct i40e_rx_buffer *new_bi = &rx_ring->rx_bi[rx_ring->next_to_alloc]; + unsigned long mask = (unsigned long)rx_ring->xsk_umem->chunk_mask; + u64 hr = rx_ring->xsk_umem->headroom + XDP_PACKET_HEADROOM; + u16 nta = rx_ring->next_to_alloc; + + /* update, and store next to alloc */ + nta++; + rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; + + /* transfer page from old buffer to new buffer */ + new_bi->dma = old_bi->dma & mask; + new_bi->dma += hr; + + new_bi->addr = (void *)((unsigned long)old_bi->addr & mask); + new_bi->addr += hr; + + new_bi->handle = old_bi->handle & mask; + new_bi->handle += rx_ring->xsk_umem->headroom; + + old_bi->addr = NULL; +} + +/** + * i40e_zca_free - Free callback for MEM_TYPE_ZERO_COPY allocations + * @alloc: Zero-copy allocator + * @handle: Buffer handle + **/ +void i40e_zca_free(struct zero_copy_allocator *alloc, unsigned long handle) +{ + struct i40e_rx_buffer *bi; + struct i40e_ring *rx_ring; + u64 hr, mask; + u16 nta; + + rx_ring = container_of(alloc, struct i40e_ring, zca); + hr = rx_ring->xsk_umem->headroom + XDP_PACKET_HEADROOM; + mask = rx_ring->xsk_umem->chunk_mask; + + nta = rx_ring->next_to_alloc; + bi = &rx_ring->rx_bi[nta]; + + nta++; + rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; + + handle &= mask; + + bi->dma = xdp_umem_get_dma(rx_ring->xsk_umem, handle); + bi->dma += hr; + + bi->addr = xdp_umem_get_data(rx_ring->xsk_umem, handle); + bi->addr += hr; + + bi->handle = (u64)handle + rx_ring->xsk_umem->headroom; +} + +/** + * i40e_construct_skb_zc - Create skbufff from zero-copy Rx buffer + * @rx_ring: Rx ring + * @bi: Rx buffer + * @xdp: xdp_buff + * + * This functions allocates a new skb from a zero-copy Rx buffer. + * + * Returns the skb, or NULL on failure. + **/ +static struct sk_buff *i40e_construct_skb_zc(struct i40e_ring *rx_ring, + struct i40e_rx_buffer *bi, + struct xdp_buff *xdp) +{ + unsigned int metasize = xdp->data - xdp->data_meta; + unsigned int datasize = xdp->data_end - xdp->data; + struct sk_buff *skb; + + /* allocate a skb to store the frags */ + skb = __napi_alloc_skb(&rx_ring->q_vector->napi, + xdp->data_end - xdp->data_hard_start, + GFP_ATOMIC | __GFP_NOWARN); + if (unlikely(!skb)) + return NULL; + + skb_reserve(skb, xdp->data - xdp->data_hard_start); + memcpy(__skb_put(skb, datasize), xdp->data, datasize); + if (metasize) + skb_metadata_set(skb, metasize); + + i40e_reuse_rx_buffer_zc(rx_ring, bi); + return skb; +} + +/** + * i40e_inc_ntc: Advance the next_to_clean index + * @rx_ring: Rx ring + **/ +static void i40e_inc_ntc(struct i40e_ring *rx_ring) +{ + u32 ntc = rx_ring->next_to_clean + 1; + + ntc = (ntc < rx_ring->count) ? ntc : 0; + rx_ring->next_to_clean = ntc; + prefetch(I40E_RX_DESC(rx_ring, ntc)); +} + +/** + * i40e_clean_rx_irq_zc - Consumes Rx packets from the hardware ring + * @rx_ring: Rx ring + * @budget: NAPI budget + * + * Returns amount of work completed + **/ +int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) +{ + unsigned int total_rx_bytes = 0, total_rx_packets = 0; + u16 cleaned_count = I40E_DESC_UNUSED(rx_ring); + unsigned int xdp_res, xdp_xmit = 0; + bool failure = false; + struct sk_buff *skb; + struct xdp_buff xdp; + + xdp.rxq = &rx_ring->xdp_rxq; + + while (likely(total_rx_packets < (unsigned int)budget)) { + struct i40e_rx_buffer *bi; + union i40e_rx_desc *rx_desc; + unsigned int size; + u16 vlan_tag; + u8 rx_ptype; + u64 qword; + + if (cleaned_count >= I40E_RX_BUFFER_WRITE) { + failure = failure || + !i40e_alloc_rx_buffers_zc(rx_ring, + cleaned_count); + cleaned_count = 0; + } + + rx_desc = I40E_RX_DESC(rx_ring, rx_ring->next_to_clean); + qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); + + /* This memory barrier is needed to keep us from reading + * any other fields out of the rx_desc until we have + * verified the descriptor has been written back. + */ + dma_rmb(); + + bi = i40e_clean_programming_status(rx_ring, rx_desc, + qword); + if (unlikely(bi)) { + i40e_reuse_rx_buffer_zc(rx_ring, bi); + cleaned_count++; + continue; + } + + size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >> + I40E_RXD_QW1_LENGTH_PBUF_SHIFT; + if (!size) + break; + + bi = i40e_get_rx_buffer_zc(rx_ring, size); + xdp.data = bi->addr; + xdp.data_meta = xdp.data; + xdp.data_hard_start = xdp.data - XDP_PACKET_HEADROOM; + xdp.data_end = xdp.data + size; + xdp.handle = bi->handle; + + xdp_res = i40e_run_xdp_zc(rx_ring, &xdp); + if (xdp_res) { + if (xdp_res & (I40E_XDP_TX | I40E_XDP_REDIR)) { + xdp_xmit |= xdp_res; + bi->addr = NULL; + } else { + i40e_reuse_rx_buffer_zc(rx_ring, bi); + } + + total_rx_bytes += size; + total_rx_packets++; + + cleaned_count++; + i40e_inc_ntc(rx_ring); + continue; + } + + /* XDP_PASS path */ + + /* NB! We are not checking for errors using + * i40e_test_staterr with + * BIT(I40E_RXD_QW1_ERROR_SHIFT). This is due to that + * SBP is *not* set in PRT_SBPVSI (default not set). + */ + skb = i40e_construct_skb_zc(rx_ring, bi, &xdp); + if (!skb) { + rx_ring->rx_stats.alloc_buff_failed++; + break; + } + + cleaned_count++; + i40e_inc_ntc(rx_ring); + + if (eth_skb_pad(skb)) + continue; + + total_rx_bytes += skb->len; + total_rx_packets++; + + qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); + rx_ptype = (qword & I40E_RXD_QW1_PTYPE_MASK) >> + I40E_RXD_QW1_PTYPE_SHIFT; + i40e_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype); + + vlan_tag = (qword & BIT(I40E_RX_DESC_STATUS_L2TAG1P_SHIFT)) ? + le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1) : 0; + i40e_receive_skb(rx_ring, skb, vlan_tag); + } + + i40e_finalize_xdp_rx(rx_ring, xdp_xmit); + i40e_update_rx_stats(rx_ring, total_rx_bytes, total_rx_packets); + return failure ? budget : (int)total_rx_packets; +} + +/** + * i40e_xmit_zc - Performs zero-copy Tx AF_XDP + * @xdp_ring: XDP Tx ring + * @budget: NAPI budget + * + * Returns true if the work is finished. + **/ +static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget) +{ + struct i40e_tx_desc *tx_desc = NULL; + struct i40e_tx_buffer *tx_bi; + bool work_done = true; + dma_addr_t dma; + u32 len; + + while (budget-- > 0) { + if (!unlikely(I40E_DESC_UNUSED(xdp_ring))) { + xdp_ring->tx_stats.tx_busy++; + work_done = false; + break; + } + + if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &dma, &len)) + break; + + dma_sync_single_for_device(xdp_ring->dev, dma, len, + DMA_BIDIRECTIONAL); + + tx_bi = &xdp_ring->tx_bi[xdp_ring->next_to_use]; + tx_bi->bytecount = len; + + tx_desc = I40E_TX_DESC(xdp_ring, xdp_ring->next_to_use); + tx_desc->buffer_addr = cpu_to_le64(dma); + tx_desc->cmd_type_offset_bsz = + build_ctob(I40E_TX_DESC_CMD_ICRC + | I40E_TX_DESC_CMD_EOP, + 0, len, 0); + + xdp_ring->next_to_use++; + if (xdp_ring->next_to_use == xdp_ring->count) + xdp_ring->next_to_use = 0; + } + + if (tx_desc) { + /* Request an interrupt for the last frame and bump tail ptr. */ + tx_desc->cmd_type_offset_bsz |= (I40E_TX_DESC_CMD_RS << + I40E_TXD_QW1_CMD_SHIFT); + i40e_xdp_ring_update_tail(xdp_ring); + + xsk_umem_consume_tx_done(xdp_ring->xsk_umem); + } + + return !!budget && work_done; +} + +/** + * i40e_clean_xdp_tx_buffer - Frees and unmaps an XDP Tx entry + * @tx_ring: XDP Tx ring + * @tx_bi: Tx buffer info to clean + **/ +static void i40e_clean_xdp_tx_buffer(struct i40e_ring *tx_ring, + struct i40e_tx_buffer *tx_bi) +{ + xdp_return_frame(tx_bi->xdpf); + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_bi, dma), + dma_unmap_len(tx_bi, len), DMA_TO_DEVICE); + dma_unmap_len_set(tx_bi, len, 0); +} + +/** + * i40e_clean_xdp_tx_irq - Completes AF_XDP entries, and cleans XDP entries + * @tx_ring: XDP Tx ring + * @tx_bi: Tx buffer info to clean + * + * Returns true if cleanup/tranmission is done. + **/ +bool i40e_clean_xdp_tx_irq(struct i40e_vsi *vsi, + struct i40e_ring *tx_ring, int napi_budget) +{ + unsigned int ntc, total_bytes = 0, budget = vsi->work_limit; + u32 i, completed_frames, frames_ready, xsk_frames = 0; + struct xdp_umem *umem = tx_ring->xsk_umem; + u32 head_idx = i40e_get_head(tx_ring); + bool work_done = true, xmit_done; + struct i40e_tx_buffer *tx_bi; + + if (head_idx < tx_ring->next_to_clean) + head_idx += tx_ring->count; + frames_ready = head_idx - tx_ring->next_to_clean; + + if (frames_ready == 0) { + goto out_xmit; + } else if (frames_ready > budget) { + completed_frames = budget; + work_done = false; + } else { + completed_frames = frames_ready; + } + + ntc = tx_ring->next_to_clean; + + for (i = 0; i < completed_frames; i++) { + tx_bi = &tx_ring->tx_bi[ntc]; + + if (tx_bi->xdpf) + i40e_clean_xdp_tx_buffer(tx_ring, tx_bi); + else + xsk_frames++; + + tx_bi->xdpf = NULL; + total_bytes += tx_bi->bytecount; + + if (++ntc >= tx_ring->count) + ntc = 0; + } + + tx_ring->next_to_clean += completed_frames; + if (unlikely(tx_ring->next_to_clean >= tx_ring->count)) + tx_ring->next_to_clean -= tx_ring->count; + + if (xsk_frames) + xsk_umem_complete_tx(umem, xsk_frames); + + i40e_arm_wb(tx_ring, vsi, budget); + i40e_update_tx_stats(tx_ring, completed_frames, total_bytes); + +out_xmit: + xmit_done = i40e_xmit_zc(tx_ring, budget); + + return work_done && xmit_done; +} + +/** + * i40e_xsk_async_xmit - Implements the ndo_xsk_async_xmit + * @dev: the netdevice + * @queue_id: queue id to wake up + * + * Returns <0 for errors, 0 otherwise. + **/ +int i40e_xsk_async_xmit(struct net_device *dev, u32 queue_id) +{ + struct i40e_netdev_priv *np = netdev_priv(dev); + struct i40e_vsi *vsi = np->vsi; + struct i40e_ring *ring; + + if (test_bit(__I40E_VSI_DOWN, vsi->state)) + return -ENETDOWN; + + if (!i40e_enabled_xdp_vsi(vsi)) + return -ENXIO; + + if (queue_id >= vsi->num_queue_pairs) + return -ENXIO; + + if (!vsi->xdp_rings[queue_id]->xsk_umem) + return -ENXIO; + + ring = vsi->xdp_rings[queue_id]; + + /* The idea here is that if NAPI is running, mark a miss, so + * it will run again. If not, trigger an interrupt and + * schedule the NAPI from interrupt context. If NAPI would be + * scheduled here, the interrupt affinity would not be + * honored. + */ + if (!napi_if_scheduled_mark_missed(&ring->q_vector->napi)) + i40e_force_wb(vsi, ring->q_vector); + + return 0; +} diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.h b/drivers/net/ethernet/intel/i40e/i40e_xsk.h new file mode 100644 index 000000000000..9038c5d5cf08 --- /dev/null +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2018 Intel Corporation. */ + +#ifndef _I40E_XSK_H_ +#define _I40E_XSK_H_ + +struct i40e_vsi; +struct xdp_umem; +struct zero_copy_allocator; + +int i40e_queue_pair_disable(struct i40e_vsi *vsi, int queue_pair); +int i40e_queue_pair_enable(struct i40e_vsi *vsi, int queue_pair); +int i40e_xsk_umem_query(struct i40e_vsi *vsi, struct xdp_umem **umem, + u16 qid); +int i40e_xsk_umem_setup(struct i40e_vsi *vsi, struct xdp_umem *umem, + u16 qid); +void i40e_zca_free(struct zero_copy_allocator *alloc, unsigned long handle); +bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 cleaned_count); +int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget); + +bool i40e_clean_xdp_tx_irq(struct i40e_vsi *vsi, + struct i40e_ring *tx_ring, int napi_budget); +int i40e_xsk_async_xmit(struct net_device *dev, u32 queue_id); + +#endif /* _I40E_XSK_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/Makefile b/drivers/net/ethernet/intel/i40evf/Makefile deleted file mode 100644 index 3c5c6e962280..000000000000 --- a/drivers/net/ethernet/intel/i40evf/Makefile +++ /dev/null @@ -1,16 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -# Copyright(c) 2013 - 2018 Intel Corporation. - -# -## Makefile for the Intel(R) 40GbE VF driver -# -# - -ccflags-y += -I$(src) -subdir-ccflags-y += -I$(src) - -obj-$(CONFIG_I40EVF) += i40evf.o - -i40evf-objs := i40evf_main.o i40evf_ethtool.o i40evf_virtchnl.o \ - i40e_txrx.o i40e_common.o i40e_adminq.o i40evf_client.o - diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h deleted file mode 100644 index 5fd8529465d4..000000000000 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h +++ /dev/null @@ -1,2717 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 2013 - 2018 Intel Corporation. */ - -#ifndef _I40E_ADMINQ_CMD_H_ -#define _I40E_ADMINQ_CMD_H_ - -/* This header file defines the i40e Admin Queue commands and is shared between - * i40e Firmware and Software. - * - * This file needs to comply with the Linux Kernel coding style. - */ - -#define I40E_FW_API_VERSION_MAJOR 0x0001 -#define I40E_FW_API_VERSION_MINOR_X722 0x0005 -#define I40E_FW_API_VERSION_MINOR_X710 0x0007 - -#define I40E_FW_MINOR_VERSION(_h) ((_h)->mac.type == I40E_MAC_XL710 ? \ - I40E_FW_API_VERSION_MINOR_X710 : \ - I40E_FW_API_VERSION_MINOR_X722) - -/* API version 1.7 implements additional link and PHY-specific APIs */ -#define I40E_MINOR_VER_GET_LINK_INFO_XL710 0x0007 - -struct i40e_aq_desc { - __le16 flags; - __le16 opcode; - __le16 datalen; - __le16 retval; - __le32 cookie_high; - __le32 cookie_low; - union { - struct { - __le32 param0; - __le32 param1; - __le32 param2; - __le32 param3; - } internal; - struct { - __le32 param0; - __le32 param1; - __le32 addr_high; - __le32 addr_low; - } external; - u8 raw[16]; - } params; -}; - -/* Flags sub-structure - * |0 |1 |2 |3 |4 |5 |6 |7 |8 |9 |10 |11 |12 |13 |14 |15 | - * |DD |CMP|ERR|VFE| * * RESERVED * * |LB |RD |VFC|BUF|SI |EI |FE | - */ - -/* command flags and offsets*/ -#define I40E_AQ_FLAG_DD_SHIFT 0 -#define I40E_AQ_FLAG_CMP_SHIFT 1 -#define I40E_AQ_FLAG_ERR_SHIFT 2 -#define I40E_AQ_FLAG_VFE_SHIFT 3 -#define I40E_AQ_FLAG_LB_SHIFT 9 -#define I40E_AQ_FLAG_RD_SHIFT 10 -#define I40E_AQ_FLAG_VFC_SHIFT 11 -#define I40E_AQ_FLAG_BUF_SHIFT 12 -#define I40E_AQ_FLAG_SI_SHIFT 13 -#define I40E_AQ_FLAG_EI_SHIFT 14 -#define I40E_AQ_FLAG_FE_SHIFT 15 - -#define I40E_AQ_FLAG_DD BIT(I40E_AQ_FLAG_DD_SHIFT) /* 0x1 */ -#define I40E_AQ_FLAG_CMP BIT(I40E_AQ_FLAG_CMP_SHIFT) /* 0x2 */ -#define I40E_AQ_FLAG_ERR BIT(I40E_AQ_FLAG_ERR_SHIFT) /* 0x4 */ -#define I40E_AQ_FLAG_VFE BIT(I40E_AQ_FLAG_VFE_SHIFT) /* 0x8 */ -#define I40E_AQ_FLAG_LB BIT(I40E_AQ_FLAG_LB_SHIFT) /* 0x200 */ -#define I40E_AQ_FLAG_RD BIT(I40E_AQ_FLAG_RD_SHIFT) /* 0x400 */ -#define I40E_AQ_FLAG_VFC BIT(I40E_AQ_FLAG_VFC_SHIFT) /* 0x800 */ -#define I40E_AQ_FLAG_BUF BIT(I40E_AQ_FLAG_BUF_SHIFT) /* 0x1000 */ -#define I40E_AQ_FLAG_SI BIT(I40E_AQ_FLAG_SI_SHIFT) /* 0x2000 */ -#define I40E_AQ_FLAG_EI BIT(I40E_AQ_FLAG_EI_SHIFT) /* 0x4000 */ -#define I40E_AQ_FLAG_FE BIT(I40E_AQ_FLAG_FE_SHIFT) /* 0x8000 */ - -/* error codes */ -enum i40e_admin_queue_err { - I40E_AQ_RC_OK = 0, /* success */ - I40E_AQ_RC_EPERM = 1, /* Operation not permitted */ - I40E_AQ_RC_ENOENT = 2, /* No such element */ - I40E_AQ_RC_ESRCH = 3, /* Bad opcode */ - I40E_AQ_RC_EINTR = 4, /* operation interrupted */ - I40E_AQ_RC_EIO = 5, /* I/O error */ - I40E_AQ_RC_ENXIO = 6, /* No such resource */ - I40E_AQ_RC_E2BIG = 7, /* Arg too long */ - I40E_AQ_RC_EAGAIN = 8, /* Try again */ - I40E_AQ_RC_ENOMEM = 9, /* Out of memory */ - I40E_AQ_RC_EACCES = 10, /* Permission denied */ - I40E_AQ_RC_EFAULT = 11, /* Bad address */ - I40E_AQ_RC_EBUSY = 12, /* Device or resource busy */ - I40E_AQ_RC_EEXIST = 13, /* object already exists */ - I40E_AQ_RC_EINVAL = 14, /* Invalid argument */ - I40E_AQ_RC_ENOTTY = 15, /* Not a typewriter */ - I40E_AQ_RC_ENOSPC = 16, /* No space left or alloc failure */ - I40E_AQ_RC_ENOSYS = 17, /* Function not implemented */ - I40E_AQ_RC_ERANGE = 18, /* Parameter out of range */ - I40E_AQ_RC_EFLUSHED = 19, /* Cmd flushed due to prev cmd error */ - I40E_AQ_RC_BAD_ADDR = 20, /* Descriptor contains a bad pointer */ - I40E_AQ_RC_EMODE = 21, /* Op not allowed in current dev mode */ - I40E_AQ_RC_EFBIG = 22, /* File too large */ -}; - -/* Admin Queue command opcodes */ -enum i40e_admin_queue_opc { - /* aq commands */ - i40e_aqc_opc_get_version = 0x0001, - i40e_aqc_opc_driver_version = 0x0002, - i40e_aqc_opc_queue_shutdown = 0x0003, - i40e_aqc_opc_set_pf_context = 0x0004, - - /* resource ownership */ - i40e_aqc_opc_request_resource = 0x0008, - i40e_aqc_opc_release_resource = 0x0009, - - i40e_aqc_opc_list_func_capabilities = 0x000A, - i40e_aqc_opc_list_dev_capabilities = 0x000B, - - /* Proxy commands */ - i40e_aqc_opc_set_proxy_config = 0x0104, - i40e_aqc_opc_set_ns_proxy_table_entry = 0x0105, - - /* LAA */ - i40e_aqc_opc_mac_address_read = 0x0107, - i40e_aqc_opc_mac_address_write = 0x0108, - - /* PXE */ - i40e_aqc_opc_clear_pxe_mode = 0x0110, - - /* WoL commands */ - i40e_aqc_opc_set_wol_filter = 0x0120, - i40e_aqc_opc_get_wake_reason = 0x0121, - - /* internal switch commands */ - i40e_aqc_opc_get_switch_config = 0x0200, - i40e_aqc_opc_add_statistics = 0x0201, - i40e_aqc_opc_remove_statistics = 0x0202, - i40e_aqc_opc_set_port_parameters = 0x0203, - i40e_aqc_opc_get_switch_resource_alloc = 0x0204, - i40e_aqc_opc_set_switch_config = 0x0205, - i40e_aqc_opc_rx_ctl_reg_read = 0x0206, - i40e_aqc_opc_rx_ctl_reg_write = 0x0207, - - i40e_aqc_opc_add_vsi = 0x0210, - i40e_aqc_opc_update_vsi_parameters = 0x0211, - i40e_aqc_opc_get_vsi_parameters = 0x0212, - - i40e_aqc_opc_add_pv = 0x0220, - i40e_aqc_opc_update_pv_parameters = 0x0221, - i40e_aqc_opc_get_pv_parameters = 0x0222, - - i40e_aqc_opc_add_veb = 0x0230, - i40e_aqc_opc_update_veb_parameters = 0x0231, - i40e_aqc_opc_get_veb_parameters = 0x0232, - - i40e_aqc_opc_delete_element = 0x0243, - - i40e_aqc_opc_add_macvlan = 0x0250, - i40e_aqc_opc_remove_macvlan = 0x0251, - i40e_aqc_opc_add_vlan = 0x0252, - i40e_aqc_opc_remove_vlan = 0x0253, - i40e_aqc_opc_set_vsi_promiscuous_modes = 0x0254, - i40e_aqc_opc_add_tag = 0x0255, - i40e_aqc_opc_remove_tag = 0x0256, - i40e_aqc_opc_add_multicast_etag = 0x0257, - i40e_aqc_opc_remove_multicast_etag = 0x0258, - i40e_aqc_opc_update_tag = 0x0259, - i40e_aqc_opc_add_control_packet_filter = 0x025A, - i40e_aqc_opc_remove_control_packet_filter = 0x025B, - i40e_aqc_opc_add_cloud_filters = 0x025C, - i40e_aqc_opc_remove_cloud_filters = 0x025D, - i40e_aqc_opc_clear_wol_switch_filters = 0x025E, - - i40e_aqc_opc_add_mirror_rule = 0x0260, - i40e_aqc_opc_delete_mirror_rule = 0x0261, - - /* Dynamic Device Personalization */ - i40e_aqc_opc_write_personalization_profile = 0x0270, - i40e_aqc_opc_get_personalization_profile_list = 0x0271, - - /* DCB commands */ - i40e_aqc_opc_dcb_ignore_pfc = 0x0301, - i40e_aqc_opc_dcb_updated = 0x0302, - i40e_aqc_opc_set_dcb_parameters = 0x0303, - - /* TX scheduler */ - i40e_aqc_opc_configure_vsi_bw_limit = 0x0400, - i40e_aqc_opc_configure_vsi_ets_sla_bw_limit = 0x0406, - i40e_aqc_opc_configure_vsi_tc_bw = 0x0407, - i40e_aqc_opc_query_vsi_bw_config = 0x0408, - i40e_aqc_opc_query_vsi_ets_sla_config = 0x040A, - i40e_aqc_opc_configure_switching_comp_bw_limit = 0x0410, - - i40e_aqc_opc_enable_switching_comp_ets = 0x0413, - i40e_aqc_opc_modify_switching_comp_ets = 0x0414, - i40e_aqc_opc_disable_switching_comp_ets = 0x0415, - i40e_aqc_opc_configure_switching_comp_ets_bw_limit = 0x0416, - i40e_aqc_opc_configure_switching_comp_bw_config = 0x0417, - i40e_aqc_opc_query_switching_comp_ets_config = 0x0418, - i40e_aqc_opc_query_port_ets_config = 0x0419, - i40e_aqc_opc_query_switching_comp_bw_config = 0x041A, - i40e_aqc_opc_suspend_port_tx = 0x041B, - i40e_aqc_opc_resume_port_tx = 0x041C, - i40e_aqc_opc_configure_partition_bw = 0x041D, - /* hmc */ - i40e_aqc_opc_query_hmc_resource_profile = 0x0500, - i40e_aqc_opc_set_hmc_resource_profile = 0x0501, - - /* phy commands*/ - i40e_aqc_opc_get_phy_abilities = 0x0600, - i40e_aqc_opc_set_phy_config = 0x0601, - i40e_aqc_opc_set_mac_config = 0x0603, - i40e_aqc_opc_set_link_restart_an = 0x0605, - i40e_aqc_opc_get_link_status = 0x0607, - i40e_aqc_opc_set_phy_int_mask = 0x0613, - i40e_aqc_opc_get_local_advt_reg = 0x0614, - i40e_aqc_opc_set_local_advt_reg = 0x0615, - i40e_aqc_opc_get_partner_advt = 0x0616, - i40e_aqc_opc_set_lb_modes = 0x0618, - i40e_aqc_opc_get_phy_wol_caps = 0x0621, - i40e_aqc_opc_set_phy_debug = 0x0622, - i40e_aqc_opc_upload_ext_phy_fm = 0x0625, - i40e_aqc_opc_run_phy_activity = 0x0626, - i40e_aqc_opc_set_phy_register = 0x0628, - i40e_aqc_opc_get_phy_register = 0x0629, - - /* NVM commands */ - i40e_aqc_opc_nvm_read = 0x0701, - i40e_aqc_opc_nvm_erase = 0x0702, - i40e_aqc_opc_nvm_update = 0x0703, - i40e_aqc_opc_nvm_config_read = 0x0704, - i40e_aqc_opc_nvm_config_write = 0x0705, - i40e_aqc_opc_oem_post_update = 0x0720, - i40e_aqc_opc_thermal_sensor = 0x0721, - - /* virtualization commands */ - i40e_aqc_opc_send_msg_to_pf = 0x0801, - i40e_aqc_opc_send_msg_to_vf = 0x0802, - i40e_aqc_opc_send_msg_to_peer = 0x0803, - - /* alternate structure */ - i40e_aqc_opc_alternate_write = 0x0900, - i40e_aqc_opc_alternate_write_indirect = 0x0901, - i40e_aqc_opc_alternate_read = 0x0902, - i40e_aqc_opc_alternate_read_indirect = 0x0903, - i40e_aqc_opc_alternate_write_done = 0x0904, - i40e_aqc_opc_alternate_set_mode = 0x0905, - i40e_aqc_opc_alternate_clear_port = 0x0906, - - /* LLDP commands */ - i40e_aqc_opc_lldp_get_mib = 0x0A00, - i40e_aqc_opc_lldp_update_mib = 0x0A01, - i40e_aqc_opc_lldp_add_tlv = 0x0A02, - i40e_aqc_opc_lldp_update_tlv = 0x0A03, - i40e_aqc_opc_lldp_delete_tlv = 0x0A04, - i40e_aqc_opc_lldp_stop = 0x0A05, - i40e_aqc_opc_lldp_start = 0x0A06, - - /* Tunnel commands */ - i40e_aqc_opc_add_udp_tunnel = 0x0B00, - i40e_aqc_opc_del_udp_tunnel = 0x0B01, - i40e_aqc_opc_set_rss_key = 0x0B02, - i40e_aqc_opc_set_rss_lut = 0x0B03, - i40e_aqc_opc_get_rss_key = 0x0B04, - i40e_aqc_opc_get_rss_lut = 0x0B05, - - /* Async Events */ - i40e_aqc_opc_event_lan_overflow = 0x1001, - - /* OEM commands */ - i40e_aqc_opc_oem_parameter_change = 0xFE00, - i40e_aqc_opc_oem_device_status_change = 0xFE01, - i40e_aqc_opc_oem_ocsd_initialize = 0xFE02, - i40e_aqc_opc_oem_ocbb_initialize = 0xFE03, - - /* debug commands */ - i40e_aqc_opc_debug_read_reg = 0xFF03, - i40e_aqc_opc_debug_write_reg = 0xFF04, - i40e_aqc_opc_debug_modify_reg = 0xFF07, - i40e_aqc_opc_debug_dump_internals = 0xFF08, -}; - -/* command structures and indirect data structures */ - -/* Structure naming conventions: - * - no suffix for direct command descriptor structures - * - _data for indirect sent data - * - _resp for indirect return data (data which is both will use _data) - * - _completion for direct return data - * - _element_ for repeated elements (may also be _data or _resp) - * - * Command structures are expected to overlay the params.raw member of the basic - * descriptor, and as such cannot exceed 16 bytes in length. - */ - -/* This macro is used to generate a compilation error if a structure - * is not exactly the correct length. It gives a divide by zero error if the - * structure is not of the correct size, otherwise it creates an enum that is - * never used. - */ -#define I40E_CHECK_STRUCT_LEN(n, X) enum i40e_static_assert_enum_##X \ - { i40e_static_assert_##X = (n)/((sizeof(struct X) == (n)) ? 1 : 0) } - -/* This macro is used extensively to ensure that command structures are 16 - * bytes in length as they have to map to the raw array of that size. - */ -#define I40E_CHECK_CMD_LENGTH(X) I40E_CHECK_STRUCT_LEN(16, X) - -/* internal (0x00XX) commands */ - -/* Get version (direct 0x0001) */ -struct i40e_aqc_get_version { - __le32 rom_ver; - __le32 fw_build; - __le16 fw_major; - __le16 fw_minor; - __le16 api_major; - __le16 api_minor; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_get_version); - -/* Send driver version (indirect 0x0002) */ -struct i40e_aqc_driver_version { - u8 driver_major_ver; - u8 driver_minor_ver; - u8 driver_build_ver; - u8 driver_subbuild_ver; - u8 reserved[4]; - __le32 address_high; - __le32 address_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_driver_version); - -/* Queue Shutdown (direct 0x0003) */ -struct i40e_aqc_queue_shutdown { - __le32 driver_unloading; -#define I40E_AQ_DRIVER_UNLOADING 0x1 - u8 reserved[12]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_queue_shutdown); - -/* Set PF context (0x0004, direct) */ -struct i40e_aqc_set_pf_context { - u8 pf_id; - u8 reserved[15]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_set_pf_context); - -/* Request resource ownership (direct 0x0008) - * Release resource ownership (direct 0x0009) - */ -#define I40E_AQ_RESOURCE_NVM 1 -#define I40E_AQ_RESOURCE_SDP 2 -#define I40E_AQ_RESOURCE_ACCESS_READ 1 -#define I40E_AQ_RESOURCE_ACCESS_WRITE 2 -#define I40E_AQ_RESOURCE_NVM_READ_TIMEOUT 3000 -#define I40E_AQ_RESOURCE_NVM_WRITE_TIMEOUT 180000 - -struct i40e_aqc_request_resource { - __le16 resource_id; - __le16 access_type; - __le32 timeout; - __le32 resource_number; - u8 reserved[4]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_request_resource); - -/* Get function capabilities (indirect 0x000A) - * Get device capabilities (indirect 0x000B) - */ -struct i40e_aqc_list_capabilites { - u8 command_flags; -#define I40E_AQ_LIST_CAP_PF_INDEX_EN 1 - u8 pf_index; - u8 reserved[2]; - __le32 count; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_list_capabilites); - -struct i40e_aqc_list_capabilities_element_resp { - __le16 id; - u8 major_rev; - u8 minor_rev; - __le32 number; - __le32 logical_id; - __le32 phys_id; - u8 reserved[16]; -}; - -/* list of caps */ - -#define I40E_AQ_CAP_ID_SWITCH_MODE 0x0001 -#define I40E_AQ_CAP_ID_MNG_MODE 0x0002 -#define I40E_AQ_CAP_ID_NPAR_ACTIVE 0x0003 -#define I40E_AQ_CAP_ID_OS2BMC_CAP 0x0004 -#define I40E_AQ_CAP_ID_FUNCTIONS_VALID 0x0005 -#define I40E_AQ_CAP_ID_ALTERNATE_RAM 0x0006 -#define I40E_AQ_CAP_ID_WOL_AND_PROXY 0x0008 -#define I40E_AQ_CAP_ID_SRIOV 0x0012 -#define I40E_AQ_CAP_ID_VF 0x0013 -#define I40E_AQ_CAP_ID_VMDQ 0x0014 -#define I40E_AQ_CAP_ID_8021QBG 0x0015 -#define I40E_AQ_CAP_ID_8021QBR 0x0016 -#define I40E_AQ_CAP_ID_VSI 0x0017 -#define I40E_AQ_CAP_ID_DCB 0x0018 -#define I40E_AQ_CAP_ID_FCOE 0x0021 -#define I40E_AQ_CAP_ID_ISCSI 0x0022 -#define I40E_AQ_CAP_ID_RSS 0x0040 -#define I40E_AQ_CAP_ID_RXQ 0x0041 -#define I40E_AQ_CAP_ID_TXQ 0x0042 -#define I40E_AQ_CAP_ID_MSIX 0x0043 -#define I40E_AQ_CAP_ID_VF_MSIX 0x0044 -#define I40E_AQ_CAP_ID_FLOW_DIRECTOR 0x0045 -#define I40E_AQ_CAP_ID_1588 0x0046 -#define I40E_AQ_CAP_ID_IWARP 0x0051 -#define I40E_AQ_CAP_ID_LED 0x0061 -#define I40E_AQ_CAP_ID_SDP 0x0062 -#define I40E_AQ_CAP_ID_MDIO 0x0063 -#define I40E_AQ_CAP_ID_WSR_PROT 0x0064 -#define I40E_AQ_CAP_ID_NVM_MGMT 0x0080 -#define I40E_AQ_CAP_ID_FLEX10 0x00F1 -#define I40E_AQ_CAP_ID_CEM 0x00F2 - -/* Set CPPM Configuration (direct 0x0103) */ -struct i40e_aqc_cppm_configuration { - __le16 command_flags; -#define I40E_AQ_CPPM_EN_LTRC 0x0800 -#define I40E_AQ_CPPM_EN_DMCTH 0x1000 -#define I40E_AQ_CPPM_EN_DMCTLX 0x2000 -#define I40E_AQ_CPPM_EN_HPTC 0x4000 -#define I40E_AQ_CPPM_EN_DMARC 0x8000 - __le16 ttlx; - __le32 dmacr; - __le16 dmcth; - u8 hptc; - u8 reserved; - __le32 pfltrc; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_cppm_configuration); - -/* Set ARP Proxy command / response (indirect 0x0104) */ -struct i40e_aqc_arp_proxy_data { - __le16 command_flags; -#define I40E_AQ_ARP_INIT_IPV4 0x0800 -#define I40E_AQ_ARP_UNSUP_CTL 0x1000 -#define I40E_AQ_ARP_ENA 0x2000 -#define I40E_AQ_ARP_ADD_IPV4 0x4000 -#define I40E_AQ_ARP_DEL_IPV4 0x8000 - __le16 table_id; - __le32 enabled_offloads; -#define I40E_AQ_ARP_DIRECTED_OFFLOAD_ENABLE 0x00000020 -#define I40E_AQ_ARP_OFFLOAD_ENABLE 0x00000800 - __le32 ip_addr; - u8 mac_addr[6]; - u8 reserved[2]; -}; - -I40E_CHECK_STRUCT_LEN(0x14, i40e_aqc_arp_proxy_data); - -/* Set NS Proxy Table Entry Command (indirect 0x0105) */ -struct i40e_aqc_ns_proxy_data { - __le16 table_idx_mac_addr_0; - __le16 table_idx_mac_addr_1; - __le16 table_idx_ipv6_0; - __le16 table_idx_ipv6_1; - __le16 control; -#define I40E_AQ_NS_PROXY_ADD_0 0x0001 -#define I40E_AQ_NS_PROXY_DEL_0 0x0002 -#define I40E_AQ_NS_PROXY_ADD_1 0x0004 -#define I40E_AQ_NS_PROXY_DEL_1 0x0008 -#define I40E_AQ_NS_PROXY_ADD_IPV6_0 0x0010 -#define I40E_AQ_NS_PROXY_DEL_IPV6_0 0x0020 -#define I40E_AQ_NS_PROXY_ADD_IPV6_1 0x0040 -#define I40E_AQ_NS_PROXY_DEL_IPV6_1 0x0080 -#define I40E_AQ_NS_PROXY_COMMAND_SEQ 0x0100 -#define I40E_AQ_NS_PROXY_INIT_IPV6_TBL 0x0200 -#define I40E_AQ_NS_PROXY_INIT_MAC_TBL 0x0400 -#define I40E_AQ_NS_PROXY_OFFLOAD_ENABLE 0x0800 -#define I40E_AQ_NS_PROXY_DIRECTED_OFFLOAD_ENABLE 0x1000 - u8 mac_addr_0[6]; - u8 mac_addr_1[6]; - u8 local_mac_addr[6]; - u8 ipv6_addr_0[16]; /* Warning! spec specifies BE byte order */ - u8 ipv6_addr_1[16]; -}; - -I40E_CHECK_STRUCT_LEN(0x3c, i40e_aqc_ns_proxy_data); - -/* Manage LAA Command (0x0106) - obsolete */ -struct i40e_aqc_mng_laa { - __le16 command_flags; -#define I40E_AQ_LAA_FLAG_WR 0x8000 - u8 reserved[2]; - __le32 sal; - __le16 sah; - u8 reserved2[6]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_mng_laa); - -/* Manage MAC Address Read Command (indirect 0x0107) */ -struct i40e_aqc_mac_address_read { - __le16 command_flags; -#define I40E_AQC_LAN_ADDR_VALID 0x10 -#define I40E_AQC_SAN_ADDR_VALID 0x20 -#define I40E_AQC_PORT_ADDR_VALID 0x40 -#define I40E_AQC_WOL_ADDR_VALID 0x80 -#define I40E_AQC_MC_MAG_EN_VALID 0x100 -#define I40E_AQC_ADDR_VALID_MASK 0x3F0 - u8 reserved[6]; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_mac_address_read); - -struct i40e_aqc_mac_address_read_data { - u8 pf_lan_mac[6]; - u8 pf_san_mac[6]; - u8 port_mac[6]; - u8 pf_wol_mac[6]; -}; - -I40E_CHECK_STRUCT_LEN(24, i40e_aqc_mac_address_read_data); - -/* Manage MAC Address Write Command (0x0108) */ -struct i40e_aqc_mac_address_write { - __le16 command_flags; -#define I40E_AQC_WRITE_TYPE_LAA_ONLY 0x0000 -#define I40E_AQC_WRITE_TYPE_LAA_WOL 0x4000 -#define I40E_AQC_WRITE_TYPE_PORT 0x8000 -#define I40E_AQC_WRITE_TYPE_UPDATE_MC_MAG 0xC000 -#define I40E_AQC_WRITE_TYPE_MASK 0xC000 - - __le16 mac_sah; - __le32 mac_sal; - u8 reserved[8]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_mac_address_write); - -/* PXE commands (0x011x) */ - -/* Clear PXE Command and response (direct 0x0110) */ -struct i40e_aqc_clear_pxe { - u8 rx_cnt; - u8 reserved[15]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_clear_pxe); - -/* Set WoL Filter (0x0120) */ - -struct i40e_aqc_set_wol_filter { - __le16 filter_index; -#define I40E_AQC_MAX_NUM_WOL_FILTERS 8 -#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT 15 -#define I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_MASK (0x1 << \ - I40E_AQC_SET_WOL_FILTER_TYPE_MAGIC_SHIFT) - -#define I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT 0 -#define I40E_AQC_SET_WOL_FILTER_INDEX_MASK (0x7 << \ - I40E_AQC_SET_WOL_FILTER_INDEX_SHIFT) - __le16 cmd_flags; -#define I40E_AQC_SET_WOL_FILTER 0x8000 -#define I40E_AQC_SET_WOL_FILTER_NO_TCO_WOL 0x4000 -#define I40E_AQC_SET_WOL_FILTER_WOL_PRESERVE_ON_PFR 0x2000 -#define I40E_AQC_SET_WOL_FILTER_ACTION_CLEAR 0 -#define I40E_AQC_SET_WOL_FILTER_ACTION_SET 1 - __le16 valid_flags; -#define I40E_AQC_SET_WOL_FILTER_ACTION_VALID 0x8000 -#define I40E_AQC_SET_WOL_FILTER_NO_TCO_ACTION_VALID 0x4000 - u8 reserved[2]; - __le32 address_high; - __le32 address_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_set_wol_filter); - -struct i40e_aqc_set_wol_filter_data { - u8 filter[128]; - u8 mask[16]; -}; - -I40E_CHECK_STRUCT_LEN(0x90, i40e_aqc_set_wol_filter_data); - -/* Get Wake Reason (0x0121) */ - -struct i40e_aqc_get_wake_reason_completion { - u8 reserved_1[2]; - __le16 wake_reason; -#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT 0 -#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_MASK (0xFF << \ - I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_MATCHED_INDEX_SHIFT) -#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT 8 -#define I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_MASK (0xFF << \ - I40E_AQC_GET_WAKE_UP_REASON_WOL_REASON_RESERVED_SHIFT) - u8 reserved_2[12]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_get_wake_reason_completion); - -/* Switch configuration commands (0x02xx) */ - -/* Used by many indirect commands that only pass an seid and a buffer in the - * command - */ -struct i40e_aqc_switch_seid { - __le16 seid; - u8 reserved[6]; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_switch_seid); - -/* Get Switch Configuration command (indirect 0x0200) - * uses i40e_aqc_switch_seid for the descriptor - */ -struct i40e_aqc_get_switch_config_header_resp { - __le16 num_reported; - __le16 num_total; - u8 reserved[12]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_get_switch_config_header_resp); - -struct i40e_aqc_switch_config_element_resp { - u8 element_type; -#define I40E_AQ_SW_ELEM_TYPE_MAC 1 -#define I40E_AQ_SW_ELEM_TYPE_PF 2 -#define I40E_AQ_SW_ELEM_TYPE_VF 3 -#define I40E_AQ_SW_ELEM_TYPE_EMP 4 -#define I40E_AQ_SW_ELEM_TYPE_BMC 5 -#define I40E_AQ_SW_ELEM_TYPE_PV 16 -#define I40E_AQ_SW_ELEM_TYPE_VEB 17 -#define I40E_AQ_SW_ELEM_TYPE_PA 18 -#define I40E_AQ_SW_ELEM_TYPE_VSI 19 - u8 revision; -#define I40E_AQ_SW_ELEM_REV_1 1 - __le16 seid; - __le16 uplink_seid; - __le16 downlink_seid; - u8 reserved[3]; - u8 connection_type; -#define I40E_AQ_CONN_TYPE_REGULAR 0x1 -#define I40E_AQ_CONN_TYPE_DEFAULT 0x2 -#define I40E_AQ_CONN_TYPE_CASCADED 0x3 - __le16 scheduler_id; - __le16 element_info; -}; - -I40E_CHECK_STRUCT_LEN(0x10, i40e_aqc_switch_config_element_resp); - -/* Get Switch Configuration (indirect 0x0200) - * an array of elements are returned in the response buffer - * the first in the array is the header, remainder are elements - */ -struct i40e_aqc_get_switch_config_resp { - struct i40e_aqc_get_switch_config_header_resp header; - struct i40e_aqc_switch_config_element_resp element[1]; -}; - -I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_get_switch_config_resp); - -/* Add Statistics (direct 0x0201) - * Remove Statistics (direct 0x0202) - */ -struct i40e_aqc_add_remove_statistics { - __le16 seid; - __le16 vlan; - __le16 stat_index; - u8 reserved[10]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_statistics); - -/* Set Port Parameters command (direct 0x0203) */ -struct i40e_aqc_set_port_parameters { - __le16 command_flags; -#define I40E_AQ_SET_P_PARAMS_SAVE_BAD_PACKETS 1 -#define I40E_AQ_SET_P_PARAMS_PAD_SHORT_PACKETS 2 /* must set! */ -#define I40E_AQ_SET_P_PARAMS_DOUBLE_VLAN_ENA 4 - __le16 bad_frame_vsi; -#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_SHIFT 0x0 -#define I40E_AQ_SET_P_PARAMS_BFRAME_SEID_MASK 0x3FF - __le16 default_seid; /* reserved for command */ - u8 reserved[10]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_set_port_parameters); - -/* Get Switch Resource Allocation (indirect 0x0204) */ -struct i40e_aqc_get_switch_resource_alloc { - u8 num_entries; /* reserved for command */ - u8 reserved[7]; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_get_switch_resource_alloc); - -/* expect an array of these structs in the response buffer */ -struct i40e_aqc_switch_resource_alloc_element_resp { - u8 resource_type; -#define I40E_AQ_RESOURCE_TYPE_VEB 0x0 -#define I40E_AQ_RESOURCE_TYPE_VSI 0x1 -#define I40E_AQ_RESOURCE_TYPE_MACADDR 0x2 -#define I40E_AQ_RESOURCE_TYPE_STAG 0x3 -#define I40E_AQ_RESOURCE_TYPE_ETAG 0x4 -#define I40E_AQ_RESOURCE_TYPE_MULTICAST_HASH 0x5 -#define I40E_AQ_RESOURCE_TYPE_UNICAST_HASH 0x6 -#define I40E_AQ_RESOURCE_TYPE_VLAN 0x7 -#define I40E_AQ_RESOURCE_TYPE_VSI_LIST_ENTRY 0x8 -#define I40E_AQ_RESOURCE_TYPE_ETAG_LIST_ENTRY 0x9 -#define I40E_AQ_RESOURCE_TYPE_VLAN_STAT_POOL 0xA -#define I40E_AQ_RESOURCE_TYPE_MIRROR_RULE 0xB -#define I40E_AQ_RESOURCE_TYPE_QUEUE_SETS 0xC -#define I40E_AQ_RESOURCE_TYPE_VLAN_FILTERS 0xD -#define I40E_AQ_RESOURCE_TYPE_INNER_MAC_FILTERS 0xF -#define I40E_AQ_RESOURCE_TYPE_IP_FILTERS 0x10 -#define I40E_AQ_RESOURCE_TYPE_GRE_VN_KEYS 0x11 -#define I40E_AQ_RESOURCE_TYPE_VN2_KEYS 0x12 -#define I40E_AQ_RESOURCE_TYPE_TUNNEL_PORTS 0x13 - u8 reserved1; - __le16 guaranteed; - __le16 total; - __le16 used; - __le16 total_unalloced; - u8 reserved2[6]; -}; - -I40E_CHECK_STRUCT_LEN(0x10, i40e_aqc_switch_resource_alloc_element_resp); - -/* Set Switch Configuration (direct 0x0205) */ -struct i40e_aqc_set_switch_config { - __le16 flags; -/* flags used for both fields below */ -#define I40E_AQ_SET_SWITCH_CFG_PROMISC 0x0001 -#define I40E_AQ_SET_SWITCH_CFG_L2_FILTER 0x0002 - __le16 valid_flags; - /* The ethertype in switch_tag is dropped on ingress and used - * internally by the switch. Set this to zero for the default - * of 0x88a8 (802.1ad). Should be zero for firmware API - * versions lower than 1.7. - */ - __le16 switch_tag; - /* The ethertypes in first_tag and second_tag are used to - * match the outer and inner VLAN tags (respectively) when HW - * double VLAN tagging is enabled via the set port parameters - * AQ command. Otherwise these are both ignored. Set them to - * zero for their defaults of 0x8100 (802.1Q). Should be zero - * for firmware API versions lower than 1.7. - */ - __le16 first_tag; - __le16 second_tag; - u8 reserved[6]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_set_switch_config); - -/* Read Receive control registers (direct 0x0206) - * Write Receive control registers (direct 0x0207) - * used for accessing Rx control registers that can be - * slow and need special handling when under high Rx load - */ -struct i40e_aqc_rx_ctl_reg_read_write { - __le32 reserved1; - __le32 address; - __le32 reserved2; - __le32 value; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_rx_ctl_reg_read_write); - -/* Add VSI (indirect 0x0210) - * this indirect command uses struct i40e_aqc_vsi_properties_data - * as the indirect buffer (128 bytes) - * - * Update VSI (indirect 0x211) - * uses the same data structure as Add VSI - * - * Get VSI (indirect 0x0212) - * uses the same completion and data structure as Add VSI - */ -struct i40e_aqc_add_get_update_vsi { - __le16 uplink_seid; - u8 connection_type; -#define I40E_AQ_VSI_CONN_TYPE_NORMAL 0x1 -#define I40E_AQ_VSI_CONN_TYPE_DEFAULT 0x2 -#define I40E_AQ_VSI_CONN_TYPE_CASCADED 0x3 - u8 reserved1; - u8 vf_id; - u8 reserved2; - __le16 vsi_flags; -#define I40E_AQ_VSI_TYPE_SHIFT 0x0 -#define I40E_AQ_VSI_TYPE_MASK (0x3 << I40E_AQ_VSI_TYPE_SHIFT) -#define I40E_AQ_VSI_TYPE_VF 0x0 -#define I40E_AQ_VSI_TYPE_VMDQ2 0x1 -#define I40E_AQ_VSI_TYPE_PF 0x2 -#define I40E_AQ_VSI_TYPE_EMP_MNG 0x3 -#define I40E_AQ_VSI_FLAG_CASCADED_PV 0x4 - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_get_update_vsi); - -struct i40e_aqc_add_get_update_vsi_completion { - __le16 seid; - __le16 vsi_number; - __le16 vsi_used; - __le16 vsi_free; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_get_update_vsi_completion); - -struct i40e_aqc_vsi_properties_data { - /* first 96 byte are written by SW */ - __le16 valid_sections; -#define I40E_AQ_VSI_PROP_SWITCH_VALID 0x0001 -#define I40E_AQ_VSI_PROP_SECURITY_VALID 0x0002 -#define I40E_AQ_VSI_PROP_VLAN_VALID 0x0004 -#define I40E_AQ_VSI_PROP_CAS_PV_VALID 0x0008 -#define I40E_AQ_VSI_PROP_INGRESS_UP_VALID 0x0010 -#define I40E_AQ_VSI_PROP_EGRESS_UP_VALID 0x0020 -#define I40E_AQ_VSI_PROP_QUEUE_MAP_VALID 0x0040 -#define I40E_AQ_VSI_PROP_QUEUE_OPT_VALID 0x0080 -#define I40E_AQ_VSI_PROP_OUTER_UP_VALID 0x0100 -#define I40E_AQ_VSI_PROP_SCHED_VALID 0x0200 - /* switch section */ - __le16 switch_id; /* 12bit id combined with flags below */ -#define I40E_AQ_VSI_SW_ID_SHIFT 0x0000 -#define I40E_AQ_VSI_SW_ID_MASK (0xFFF << I40E_AQ_VSI_SW_ID_SHIFT) -#define I40E_AQ_VSI_SW_ID_FLAG_NOT_STAG 0x1000 -#define I40E_AQ_VSI_SW_ID_FLAG_ALLOW_LB 0x2000 -#define I40E_AQ_VSI_SW_ID_FLAG_LOCAL_LB 0x4000 - u8 sw_reserved[2]; - /* security section */ - u8 sec_flags; -#define I40E_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD 0x01 -#define I40E_AQ_VSI_SEC_FLAG_ENABLE_VLAN_CHK 0x02 -#define I40E_AQ_VSI_SEC_FLAG_ENABLE_MAC_CHK 0x04 - u8 sec_reserved; - /* VLAN section */ - __le16 pvid; /* VLANS include priority bits */ - __le16 fcoe_pvid; - u8 port_vlan_flags; -#define I40E_AQ_VSI_PVLAN_MODE_SHIFT 0x00 -#define I40E_AQ_VSI_PVLAN_MODE_MASK (0x03 << \ - I40E_AQ_VSI_PVLAN_MODE_SHIFT) -#define I40E_AQ_VSI_PVLAN_MODE_TAGGED 0x01 -#define I40E_AQ_VSI_PVLAN_MODE_UNTAGGED 0x02 -#define I40E_AQ_VSI_PVLAN_MODE_ALL 0x03 -#define I40E_AQ_VSI_PVLAN_INSERT_PVID 0x04 -#define I40E_AQ_VSI_PVLAN_EMOD_SHIFT 0x03 -#define I40E_AQ_VSI_PVLAN_EMOD_MASK (0x3 << \ - I40E_AQ_VSI_PVLAN_EMOD_SHIFT) -#define I40E_AQ_VSI_PVLAN_EMOD_STR_BOTH 0x0 -#define I40E_AQ_VSI_PVLAN_EMOD_STR_UP 0x08 -#define I40E_AQ_VSI_PVLAN_EMOD_STR 0x10 -#define I40E_AQ_VSI_PVLAN_EMOD_NOTHING 0x18 - u8 pvlan_reserved[3]; - /* ingress egress up sections */ - __le32 ingress_table; /* bitmap, 3 bits per up */ -#define I40E_AQ_VSI_UP_TABLE_UP0_SHIFT 0 -#define I40E_AQ_VSI_UP_TABLE_UP0_MASK (0x7 << \ - I40E_AQ_VSI_UP_TABLE_UP0_SHIFT) -#define I40E_AQ_VSI_UP_TABLE_UP1_SHIFT 3 -#define I40E_AQ_VSI_UP_TABLE_UP1_MASK (0x7 << \ - I40E_AQ_VSI_UP_TABLE_UP1_SHIFT) -#define I40E_AQ_VSI_UP_TABLE_UP2_SHIFT 6 -#define I40E_AQ_VSI_UP_TABLE_UP2_MASK (0x7 << \ - I40E_AQ_VSI_UP_TABLE_UP2_SHIFT) -#define I40E_AQ_VSI_UP_TABLE_UP3_SHIFT 9 -#define I40E_AQ_VSI_UP_TABLE_UP3_MASK (0x7 << \ - I40E_AQ_VSI_UP_TABLE_UP3_SHIFT) -#define I40E_AQ_VSI_UP_TABLE_UP4_SHIFT 12 -#define I40E_AQ_VSI_UP_TABLE_UP4_MASK (0x7 << \ - I40E_AQ_VSI_UP_TABLE_UP4_SHIFT) -#define I40E_AQ_VSI_UP_TABLE_UP5_SHIFT 15 -#define I40E_AQ_VSI_UP_TABLE_UP5_MASK (0x7 << \ - I40E_AQ_VSI_UP_TABLE_UP5_SHIFT) -#define I40E_AQ_VSI_UP_TABLE_UP6_SHIFT 18 -#define I40E_AQ_VSI_UP_TABLE_UP6_MASK (0x7 << \ - I40E_AQ_VSI_UP_TABLE_UP6_SHIFT) -#define I40E_AQ_VSI_UP_TABLE_UP7_SHIFT 21 -#define I40E_AQ_VSI_UP_TABLE_UP7_MASK (0x7 << \ - I40E_AQ_VSI_UP_TABLE_UP7_SHIFT) - __le32 egress_table; /* same defines as for ingress table */ - /* cascaded PV section */ - __le16 cas_pv_tag; - u8 cas_pv_flags; -#define I40E_AQ_VSI_CAS_PV_TAGX_SHIFT 0x00 -#define I40E_AQ_VSI_CAS_PV_TAGX_MASK (0x03 << \ - I40E_AQ_VSI_CAS_PV_TAGX_SHIFT) -#define I40E_AQ_VSI_CAS_PV_TAGX_LEAVE 0x00 -#define I40E_AQ_VSI_CAS_PV_TAGX_REMOVE 0x01 -#define I40E_AQ_VSI_CAS_PV_TAGX_COPY 0x02 -#define I40E_AQ_VSI_CAS_PV_INSERT_TAG 0x10 -#define I40E_AQ_VSI_CAS_PV_ETAG_PRUNE 0x20 -#define I40E_AQ_VSI_CAS_PV_ACCEPT_HOST_TAG 0x40 - u8 cas_pv_reserved; - /* queue mapping section */ - __le16 mapping_flags; -#define I40E_AQ_VSI_QUE_MAP_CONTIG 0x0 -#define I40E_AQ_VSI_QUE_MAP_NONCONTIG 0x1 - __le16 queue_mapping[16]; -#define I40E_AQ_VSI_QUEUE_SHIFT 0x0 -#define I40E_AQ_VSI_QUEUE_MASK (0x7FF << I40E_AQ_VSI_QUEUE_SHIFT) - __le16 tc_mapping[8]; -#define I40E_AQ_VSI_TC_QUE_OFFSET_SHIFT 0 -#define I40E_AQ_VSI_TC_QUE_OFFSET_MASK (0x1FF << \ - I40E_AQ_VSI_TC_QUE_OFFSET_SHIFT) -#define I40E_AQ_VSI_TC_QUE_NUMBER_SHIFT 9 -#define I40E_AQ_VSI_TC_QUE_NUMBER_MASK (0x7 << \ - I40E_AQ_VSI_TC_QUE_NUMBER_SHIFT) - /* queueing option section */ - u8 queueing_opt_flags; -#define I40E_AQ_VSI_QUE_OPT_MULTICAST_UDP_ENA 0x04 -#define I40E_AQ_VSI_QUE_OPT_UNICAST_UDP_ENA 0x08 -#define I40E_AQ_VSI_QUE_OPT_TCP_ENA 0x10 -#define I40E_AQ_VSI_QUE_OPT_FCOE_ENA 0x20 -#define I40E_AQ_VSI_QUE_OPT_RSS_LUT_PF 0x00 -#define I40E_AQ_VSI_QUE_OPT_RSS_LUT_VSI 0x40 - u8 queueing_opt_reserved[3]; - /* scheduler section */ - u8 up_enable_bits; - u8 sched_reserved; - /* outer up section */ - __le32 outer_up_table; /* same structure and defines as ingress tbl */ - u8 cmd_reserved[8]; - /* last 32 bytes are written by FW */ - __le16 qs_handle[8]; -#define I40E_AQ_VSI_QS_HANDLE_INVALID 0xFFFF - __le16 stat_counter_idx; - __le16 sched_id; - u8 resp_reserved[12]; -}; - -I40E_CHECK_STRUCT_LEN(128, i40e_aqc_vsi_properties_data); - -/* Add Port Virtualizer (direct 0x0220) - * also used for update PV (direct 0x0221) but only flags are used - * (IS_CTRL_PORT only works on add PV) - */ -struct i40e_aqc_add_update_pv { - __le16 command_flags; -#define I40E_AQC_PV_FLAG_PV_TYPE 0x1 -#define I40E_AQC_PV_FLAG_FWD_UNKNOWN_STAG_EN 0x2 -#define I40E_AQC_PV_FLAG_FWD_UNKNOWN_ETAG_EN 0x4 -#define I40E_AQC_PV_FLAG_IS_CTRL_PORT 0x8 - __le16 uplink_seid; - __le16 connected_seid; - u8 reserved[10]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_update_pv); - -struct i40e_aqc_add_update_pv_completion { - /* reserved for update; for add also encodes error if rc == ENOSPC */ - __le16 pv_seid; -#define I40E_AQC_PV_ERR_FLAG_NO_PV 0x1 -#define I40E_AQC_PV_ERR_FLAG_NO_SCHED 0x2 -#define I40E_AQC_PV_ERR_FLAG_NO_COUNTER 0x4 -#define I40E_AQC_PV_ERR_FLAG_NO_ENTRY 0x8 - u8 reserved[14]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_update_pv_completion); - -/* Get PV Params (direct 0x0222) - * uses i40e_aqc_switch_seid for the descriptor - */ - -struct i40e_aqc_get_pv_params_completion { - __le16 seid; - __le16 default_stag; - __le16 pv_flags; /* same flags as add_pv */ -#define I40E_AQC_GET_PV_PV_TYPE 0x1 -#define I40E_AQC_GET_PV_FRWD_UNKNOWN_STAG 0x2 -#define I40E_AQC_GET_PV_FRWD_UNKNOWN_ETAG 0x4 - u8 reserved[8]; - __le16 default_port_seid; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_get_pv_params_completion); - -/* Add VEB (direct 0x0230) */ -struct i40e_aqc_add_veb { - __le16 uplink_seid; - __le16 downlink_seid; - __le16 veb_flags; -#define I40E_AQC_ADD_VEB_FLOATING 0x1 -#define I40E_AQC_ADD_VEB_PORT_TYPE_SHIFT 1 -#define I40E_AQC_ADD_VEB_PORT_TYPE_MASK (0x3 << \ - I40E_AQC_ADD_VEB_PORT_TYPE_SHIFT) -#define I40E_AQC_ADD_VEB_PORT_TYPE_DEFAULT 0x2 -#define I40E_AQC_ADD_VEB_PORT_TYPE_DATA 0x4 -#define I40E_AQC_ADD_VEB_ENABLE_L2_FILTER 0x8 /* deprecated */ -#define I40E_AQC_ADD_VEB_ENABLE_DISABLE_STATS 0x10 - u8 enable_tcs; - u8 reserved[9]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_veb); - -struct i40e_aqc_add_veb_completion { - u8 reserved[6]; - __le16 switch_seid; - /* also encodes error if rc == ENOSPC; codes are the same as add_pv */ - __le16 veb_seid; -#define I40E_AQC_VEB_ERR_FLAG_NO_VEB 0x1 -#define I40E_AQC_VEB_ERR_FLAG_NO_SCHED 0x2 -#define I40E_AQC_VEB_ERR_FLAG_NO_COUNTER 0x4 -#define I40E_AQC_VEB_ERR_FLAG_NO_ENTRY 0x8 - __le16 statistic_index; - __le16 vebs_used; - __le16 vebs_free; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_veb_completion); - -/* Get VEB Parameters (direct 0x0232) - * uses i40e_aqc_switch_seid for the descriptor - */ -struct i40e_aqc_get_veb_parameters_completion { - __le16 seid; - __le16 switch_id; - __le16 veb_flags; /* only the first/last flags from 0x0230 is valid */ - __le16 statistic_index; - __le16 vebs_used; - __le16 vebs_free; - u8 reserved[4]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_get_veb_parameters_completion); - -/* Delete Element (direct 0x0243) - * uses the generic i40e_aqc_switch_seid - */ - -/* Add MAC-VLAN (indirect 0x0250) */ - -/* used for the command for most vlan commands */ -struct i40e_aqc_macvlan { - __le16 num_addresses; - __le16 seid[3]; -#define I40E_AQC_MACVLAN_CMD_SEID_NUM_SHIFT 0 -#define I40E_AQC_MACVLAN_CMD_SEID_NUM_MASK (0x3FF << \ - I40E_AQC_MACVLAN_CMD_SEID_NUM_SHIFT) -#define I40E_AQC_MACVLAN_CMD_SEID_VALID 0x8000 - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_macvlan); - -/* indirect data for command and response */ -struct i40e_aqc_add_macvlan_element_data { - u8 mac_addr[6]; - __le16 vlan_tag; - __le16 flags; -#define I40E_AQC_MACVLAN_ADD_PERFECT_MATCH 0x0001 -#define I40E_AQC_MACVLAN_ADD_HASH_MATCH 0x0002 -#define I40E_AQC_MACVLAN_ADD_IGNORE_VLAN 0x0004 -#define I40E_AQC_MACVLAN_ADD_TO_QUEUE 0x0008 -#define I40E_AQC_MACVLAN_ADD_USE_SHARED_MAC 0x0010 - __le16 queue_number; -#define I40E_AQC_MACVLAN_CMD_QUEUE_SHIFT 0 -#define I40E_AQC_MACVLAN_CMD_QUEUE_MASK (0x7FF << \ - I40E_AQC_MACVLAN_CMD_SEID_NUM_SHIFT) - /* response section */ - u8 match_method; -#define I40E_AQC_MM_PERFECT_MATCH 0x01 -#define I40E_AQC_MM_HASH_MATCH 0x02 -#define I40E_AQC_MM_ERR_NO_RES 0xFF - u8 reserved1[3]; -}; - -struct i40e_aqc_add_remove_macvlan_completion { - __le16 perfect_mac_used; - __le16 perfect_mac_free; - __le16 unicast_hash_free; - __le16 multicast_hash_free; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_macvlan_completion); - -/* Remove MAC-VLAN (indirect 0x0251) - * uses i40e_aqc_macvlan for the descriptor - * data points to an array of num_addresses of elements - */ - -struct i40e_aqc_remove_macvlan_element_data { - u8 mac_addr[6]; - __le16 vlan_tag; - u8 flags; -#define I40E_AQC_MACVLAN_DEL_PERFECT_MATCH 0x01 -#define I40E_AQC_MACVLAN_DEL_HASH_MATCH 0x02 -#define I40E_AQC_MACVLAN_DEL_IGNORE_VLAN 0x08 -#define I40E_AQC_MACVLAN_DEL_ALL_VSIS 0x10 - u8 reserved[3]; - /* reply section */ - u8 error_code; -#define I40E_AQC_REMOVE_MACVLAN_SUCCESS 0x0 -#define I40E_AQC_REMOVE_MACVLAN_FAIL 0xFF - u8 reply_reserved[3]; -}; - -/* Add VLAN (indirect 0x0252) - * Remove VLAN (indirect 0x0253) - * use the generic i40e_aqc_macvlan for the command - */ -struct i40e_aqc_add_remove_vlan_element_data { - __le16 vlan_tag; - u8 vlan_flags; -/* flags for add VLAN */ -#define I40E_AQC_ADD_VLAN_LOCAL 0x1 -#define I40E_AQC_ADD_PVLAN_TYPE_SHIFT 1 -#define I40E_AQC_ADD_PVLAN_TYPE_MASK (0x3 << I40E_AQC_ADD_PVLAN_TYPE_SHIFT) -#define I40E_AQC_ADD_PVLAN_TYPE_REGULAR 0x0 -#define I40E_AQC_ADD_PVLAN_TYPE_PRIMARY 0x2 -#define I40E_AQC_ADD_PVLAN_TYPE_SECONDARY 0x4 -#define I40E_AQC_VLAN_PTYPE_SHIFT 3 -#define I40E_AQC_VLAN_PTYPE_MASK (0x3 << I40E_AQC_VLAN_PTYPE_SHIFT) -#define I40E_AQC_VLAN_PTYPE_REGULAR_VSI 0x0 -#define I40E_AQC_VLAN_PTYPE_PROMISC_VSI 0x8 -#define I40E_AQC_VLAN_PTYPE_COMMUNITY_VSI 0x10 -#define I40E_AQC_VLAN_PTYPE_ISOLATED_VSI 0x18 -/* flags for remove VLAN */ -#define I40E_AQC_REMOVE_VLAN_ALL 0x1 - u8 reserved; - u8 result; -/* flags for add VLAN */ -#define I40E_AQC_ADD_VLAN_SUCCESS 0x0 -#define I40E_AQC_ADD_VLAN_FAIL_REQUEST 0xFE -#define I40E_AQC_ADD_VLAN_FAIL_RESOURCE 0xFF -/* flags for remove VLAN */ -#define I40E_AQC_REMOVE_VLAN_SUCCESS 0x0 -#define I40E_AQC_REMOVE_VLAN_FAIL 0xFF - u8 reserved1[3]; -}; - -struct i40e_aqc_add_remove_vlan_completion { - u8 reserved[4]; - __le16 vlans_used; - __le16 vlans_free; - __le32 addr_high; - __le32 addr_low; -}; - -/* Set VSI Promiscuous Modes (direct 0x0254) */ -struct i40e_aqc_set_vsi_promiscuous_modes { - __le16 promiscuous_flags; - __le16 valid_flags; -/* flags used for both fields above */ -#define I40E_AQC_SET_VSI_PROMISC_UNICAST 0x01 -#define I40E_AQC_SET_VSI_PROMISC_MULTICAST 0x02 -#define I40E_AQC_SET_VSI_PROMISC_BROADCAST 0x04 -#define I40E_AQC_SET_VSI_DEFAULT 0x08 -#define I40E_AQC_SET_VSI_PROMISC_VLAN 0x10 -#define I40E_AQC_SET_VSI_PROMISC_TX 0x8000 - __le16 seid; -#define I40E_AQC_VSI_PROM_CMD_SEID_MASK 0x3FF - __le16 vlan_tag; -#define I40E_AQC_SET_VSI_VLAN_MASK 0x0FFF -#define I40E_AQC_SET_VSI_VLAN_VALID 0x8000 - u8 reserved[8]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_set_vsi_promiscuous_modes); - -/* Add S/E-tag command (direct 0x0255) - * Uses generic i40e_aqc_add_remove_tag_completion for completion - */ -struct i40e_aqc_add_tag { - __le16 flags; -#define I40E_AQC_ADD_TAG_FLAG_TO_QUEUE 0x0001 - __le16 seid; -#define I40E_AQC_ADD_TAG_CMD_SEID_NUM_SHIFT 0 -#define I40E_AQC_ADD_TAG_CMD_SEID_NUM_MASK (0x3FF << \ - I40E_AQC_ADD_TAG_CMD_SEID_NUM_SHIFT) - __le16 tag; - __le16 queue_number; - u8 reserved[8]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_tag); - -struct i40e_aqc_add_remove_tag_completion { - u8 reserved[12]; - __le16 tags_used; - __le16 tags_free; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_tag_completion); - -/* Remove S/E-tag command (direct 0x0256) - * Uses generic i40e_aqc_add_remove_tag_completion for completion - */ -struct i40e_aqc_remove_tag { - __le16 seid; -#define I40E_AQC_REMOVE_TAG_CMD_SEID_NUM_SHIFT 0 -#define I40E_AQC_REMOVE_TAG_CMD_SEID_NUM_MASK (0x3FF << \ - I40E_AQC_REMOVE_TAG_CMD_SEID_NUM_SHIFT) - __le16 tag; - u8 reserved[12]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_remove_tag); - -/* Add multicast E-Tag (direct 0x0257) - * del multicast E-Tag (direct 0x0258) only uses pv_seid and etag fields - * and no external data - */ -struct i40e_aqc_add_remove_mcast_etag { - __le16 pv_seid; - __le16 etag; - u8 num_unicast_etags; - u8 reserved[3]; - __le32 addr_high; /* address of array of 2-byte s-tags */ - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_mcast_etag); - -struct i40e_aqc_add_remove_mcast_etag_completion { - u8 reserved[4]; - __le16 mcast_etags_used; - __le16 mcast_etags_free; - __le32 addr_high; - __le32 addr_low; - -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_mcast_etag_completion); - -/* Update S/E-Tag (direct 0x0259) */ -struct i40e_aqc_update_tag { - __le16 seid; -#define I40E_AQC_UPDATE_TAG_CMD_SEID_NUM_SHIFT 0 -#define I40E_AQC_UPDATE_TAG_CMD_SEID_NUM_MASK (0x3FF << \ - I40E_AQC_UPDATE_TAG_CMD_SEID_NUM_SHIFT) - __le16 old_tag; - __le16 new_tag; - u8 reserved[10]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_update_tag); - -struct i40e_aqc_update_tag_completion { - u8 reserved[12]; - __le16 tags_used; - __le16 tags_free; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_update_tag_completion); - -/* Add Control Packet filter (direct 0x025A) - * Remove Control Packet filter (direct 0x025B) - * uses the i40e_aqc_add_oveb_cloud, - * and the generic direct completion structure - */ -struct i40e_aqc_add_remove_control_packet_filter { - u8 mac[6]; - __le16 etype; - __le16 flags; -#define I40E_AQC_ADD_CONTROL_PACKET_FLAGS_IGNORE_MAC 0x0001 -#define I40E_AQC_ADD_CONTROL_PACKET_FLAGS_DROP 0x0002 -#define I40E_AQC_ADD_CONTROL_PACKET_FLAGS_TO_QUEUE 0x0004 -#define I40E_AQC_ADD_CONTROL_PACKET_FLAGS_TX 0x0008 -#define I40E_AQC_ADD_CONTROL_PACKET_FLAGS_RX 0x0000 - __le16 seid; -#define I40E_AQC_ADD_CONTROL_PACKET_CMD_SEID_NUM_SHIFT 0 -#define I40E_AQC_ADD_CONTROL_PACKET_CMD_SEID_NUM_MASK (0x3FF << \ - I40E_AQC_ADD_CONTROL_PACKET_CMD_SEID_NUM_SHIFT) - __le16 queue; - u8 reserved[2]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_control_packet_filter); - -struct i40e_aqc_add_remove_control_packet_filter_completion { - __le16 mac_etype_used; - __le16 etype_used; - __le16 mac_etype_free; - __le16 etype_free; - u8 reserved[8]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_control_packet_filter_completion); - -/* Add Cloud filters (indirect 0x025C) - * Remove Cloud filters (indirect 0x025D) - * uses the i40e_aqc_add_remove_cloud_filters, - * and the generic indirect completion structure - */ -struct i40e_aqc_add_remove_cloud_filters { - u8 num_filters; - u8 reserved; - __le16 seid; -#define I40E_AQC_ADD_CLOUD_CMD_SEID_NUM_SHIFT 0 -#define I40E_AQC_ADD_CLOUD_CMD_SEID_NUM_MASK (0x3FF << \ - I40E_AQC_ADD_CLOUD_CMD_SEID_NUM_SHIFT) - u8 big_buffer_flag; -#define I40E_AQC_ADD_CLOUD_CMD_BB 1 - u8 reserved2[3]; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_remove_cloud_filters); - -struct i40e_aqc_cloud_filters_element_data { - u8 outer_mac[6]; - u8 inner_mac[6]; - __le16 inner_vlan; - union { - struct { - u8 reserved[12]; - u8 data[4]; - } v4; - struct { - u8 data[16]; - } v6; - struct { - __le16 data[8]; - } raw_v6; - } ipaddr; - __le16 flags; -#define I40E_AQC_ADD_CLOUD_FILTER_SHIFT 0 -#define I40E_AQC_ADD_CLOUD_FILTER_MASK (0x3F << \ - I40E_AQC_ADD_CLOUD_FILTER_SHIFT) -/* 0x0000 reserved */ -#define I40E_AQC_ADD_CLOUD_FILTER_OIP 0x0001 -/* 0x0002 reserved */ -#define I40E_AQC_ADD_CLOUD_FILTER_IMAC_IVLAN 0x0003 -#define I40E_AQC_ADD_CLOUD_FILTER_IMAC_IVLAN_TEN_ID 0x0004 -/* 0x0005 reserved */ -#define I40E_AQC_ADD_CLOUD_FILTER_IMAC_TEN_ID 0x0006 -/* 0x0007 reserved */ -/* 0x0008 reserved */ -#define I40E_AQC_ADD_CLOUD_FILTER_OMAC 0x0009 -#define I40E_AQC_ADD_CLOUD_FILTER_IMAC 0x000A -#define I40E_AQC_ADD_CLOUD_FILTER_OMAC_TEN_ID_IMAC 0x000B -#define I40E_AQC_ADD_CLOUD_FILTER_IIP 0x000C -/* 0x0010 to 0x0017 is for custom filters */ -#define I40E_AQC_ADD_CLOUD_FILTER_IP_PORT 0x0010 /* Dest IP + L4 Port */ -#define I40E_AQC_ADD_CLOUD_FILTER_MAC_PORT 0x0011 /* Dest MAC + L4 Port */ -#define I40E_AQC_ADD_CLOUD_FILTER_MAC_VLAN_PORT 0x0012 /* Dest MAC + VLAN + L4 Port */ - -#define I40E_AQC_ADD_CLOUD_FLAGS_TO_QUEUE 0x0080 -#define I40E_AQC_ADD_CLOUD_VNK_SHIFT 6 -#define I40E_AQC_ADD_CLOUD_VNK_MASK 0x00C0 -#define I40E_AQC_ADD_CLOUD_FLAGS_IPV4 0 -#define I40E_AQC_ADD_CLOUD_FLAGS_IPV6 0x0100 - -#define I40E_AQC_ADD_CLOUD_TNL_TYPE_SHIFT 9 -#define I40E_AQC_ADD_CLOUD_TNL_TYPE_MASK 0x1E00 -#define I40E_AQC_ADD_CLOUD_TNL_TYPE_VXLAN 0 -#define I40E_AQC_ADD_CLOUD_TNL_TYPE_NVGRE_OMAC 1 -#define I40E_AQC_ADD_CLOUD_TNL_TYPE_GENEVE 2 -#define I40E_AQC_ADD_CLOUD_TNL_TYPE_IP 3 -#define I40E_AQC_ADD_CLOUD_TNL_TYPE_RESERVED 4 -#define I40E_AQC_ADD_CLOUD_TNL_TYPE_VXLAN_GPE 5 - -#define I40E_AQC_ADD_CLOUD_FLAGS_SHARED_OUTER_MAC 0x2000 -#define I40E_AQC_ADD_CLOUD_FLAGS_SHARED_INNER_MAC 0x4000 -#define I40E_AQC_ADD_CLOUD_FLAGS_SHARED_OUTER_IP 0x8000 - - __le32 tenant_id; - u8 reserved[4]; - __le16 queue_number; -#define I40E_AQC_ADD_CLOUD_QUEUE_SHIFT 0 -#define I40E_AQC_ADD_CLOUD_QUEUE_MASK (0x7FF << \ - I40E_AQC_ADD_CLOUD_QUEUE_SHIFT) - u8 reserved2[14]; - /* response section */ - u8 allocation_result; -#define I40E_AQC_ADD_CLOUD_FILTER_SUCCESS 0x0 -#define I40E_AQC_ADD_CLOUD_FILTER_FAIL 0xFF - u8 response_reserved[7]; -}; - -I40E_CHECK_STRUCT_LEN(0x40, i40e_aqc_cloud_filters_element_data); - -/* i40e_aqc_cloud_filters_element_bb is used when - * I40E_AQC_ADD_CLOUD_CMD_BB flag is set. - */ -struct i40e_aqc_cloud_filters_element_bb { - struct i40e_aqc_cloud_filters_element_data element; - u16 general_fields[32]; -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X10_WORD0 0 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X10_WORD1 1 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X10_WORD2 2 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X11_WORD0 3 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X11_WORD1 4 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X11_WORD2 5 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X12_WORD0 6 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X12_WORD1 7 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X12_WORD2 8 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X13_WORD0 9 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X13_WORD1 10 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X13_WORD2 11 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X14_WORD0 12 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X14_WORD1 13 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X14_WORD2 14 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD0 15 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD1 16 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD2 17 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD3 18 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD4 19 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD5 20 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD6 21 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X16_WORD7 22 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD0 23 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD1 24 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD2 25 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD3 26 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD4 27 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD5 28 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD6 29 -#define I40E_AQC_ADD_CLOUD_FV_FLU_0X17_WORD7 30 -}; - -I40E_CHECK_STRUCT_LEN(0x80, i40e_aqc_cloud_filters_element_bb); - -struct i40e_aqc_remove_cloud_filters_completion { - __le16 perfect_ovlan_used; - __le16 perfect_ovlan_free; - __le16 vlan_used; - __le16 vlan_free; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_remove_cloud_filters_completion); - -/* Replace filter Command 0x025F - * uses the i40e_aqc_replace_cloud_filters, - * and the generic indirect completion structure - */ -struct i40e_filter_data { - u8 filter_type; - u8 input[3]; -}; - -I40E_CHECK_STRUCT_LEN(4, i40e_filter_data); - -struct i40e_aqc_replace_cloud_filters_cmd { - u8 valid_flags; -#define I40E_AQC_REPLACE_L1_FILTER 0x0 -#define I40E_AQC_REPLACE_CLOUD_FILTER 0x1 -#define I40E_AQC_GET_CLOUD_FILTERS 0x2 -#define I40E_AQC_MIRROR_CLOUD_FILTER 0x4 -#define I40E_AQC_HIGH_PRIORITY_CLOUD_FILTER 0x8 - u8 old_filter_type; - u8 new_filter_type; - u8 tr_bit; - u8 reserved[4]; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_replace_cloud_filters_cmd); - -struct i40e_aqc_replace_cloud_filters_cmd_buf { - u8 data[32]; -/* Filter type INPUT codes*/ -#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_ENTRIES_MAX 3 -#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_VALIDATED BIT(7) - -/* Field Vector offsets */ -#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_MAC_DA 0 -#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_STAG_ETH 6 -#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_STAG 7 -#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_VLAN 8 -#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_STAG_OVLAN 9 -#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_STAG_IVLAN 10 -#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_TUNNLE_KEY 11 -#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_IMAC 12 -/* big FLU */ -#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_IP_DA 14 -/* big FLU */ -#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_OIP_DA 15 - -#define I40E_AQC_REPLACE_CLOUD_CMD_INPUT_FV_INNER_VLAN 37 - struct i40e_filter_data filters[8]; -}; - -I40E_CHECK_STRUCT_LEN(0x40, i40e_aqc_replace_cloud_filters_cmd_buf); - -/* Add Mirror Rule (indirect or direct 0x0260) - * Delete Mirror Rule (indirect or direct 0x0261) - * note: some rule types (4,5) do not use an external buffer. - * take care to set the flags correctly. - */ -struct i40e_aqc_add_delete_mirror_rule { - __le16 seid; - __le16 rule_type; -#define I40E_AQC_MIRROR_RULE_TYPE_SHIFT 0 -#define I40E_AQC_MIRROR_RULE_TYPE_MASK (0x7 << \ - I40E_AQC_MIRROR_RULE_TYPE_SHIFT) -#define I40E_AQC_MIRROR_RULE_TYPE_VPORT_INGRESS 1 -#define I40E_AQC_MIRROR_RULE_TYPE_VPORT_EGRESS 2 -#define I40E_AQC_MIRROR_RULE_TYPE_VLAN 3 -#define I40E_AQC_MIRROR_RULE_TYPE_ALL_INGRESS 4 -#define I40E_AQC_MIRROR_RULE_TYPE_ALL_EGRESS 5 - __le16 num_entries; - __le16 destination; /* VSI for add, rule id for delete */ - __le32 addr_high; /* address of array of 2-byte VSI or VLAN ids */ - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_delete_mirror_rule); - -struct i40e_aqc_add_delete_mirror_rule_completion { - u8 reserved[2]; - __le16 rule_id; /* only used on add */ - __le16 mirror_rules_used; - __le16 mirror_rules_free; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_delete_mirror_rule_completion); - -/* Dynamic Device Personalization */ -struct i40e_aqc_write_personalization_profile { - u8 flags; - u8 reserved[3]; - __le32 profile_track_id; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_write_personalization_profile); - -struct i40e_aqc_write_ddp_resp { - __le32 error_offset; - __le32 error_info; - __le32 addr_high; - __le32 addr_low; -}; - -struct i40e_aqc_get_applied_profiles { - u8 flags; -#define I40E_AQC_GET_DDP_GET_CONF 0x1 -#define I40E_AQC_GET_DDP_GET_RDPU_CONF 0x2 - u8 rsv[3]; - __le32 reserved; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_get_applied_profiles); - -/* DCB 0x03xx*/ - -/* PFC Ignore (direct 0x0301) - * the command and response use the same descriptor structure - */ -struct i40e_aqc_pfc_ignore { - u8 tc_bitmap; - u8 command_flags; /* unused on response */ -#define I40E_AQC_PFC_IGNORE_SET 0x80 -#define I40E_AQC_PFC_IGNORE_CLEAR 0x0 - u8 reserved[14]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_pfc_ignore); - -/* DCB Update (direct 0x0302) uses the i40e_aq_desc structure - * with no parameters - */ - -/* TX scheduler 0x04xx */ - -/* Almost all the indirect commands use - * this generic struct to pass the SEID in param0 - */ -struct i40e_aqc_tx_sched_ind { - __le16 vsi_seid; - u8 reserved[6]; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_tx_sched_ind); - -/* Several commands respond with a set of queue set handles */ -struct i40e_aqc_qs_handles_resp { - __le16 qs_handles[8]; -}; - -/* Configure VSI BW limits (direct 0x0400) */ -struct i40e_aqc_configure_vsi_bw_limit { - __le16 vsi_seid; - u8 reserved[2]; - __le16 credit; - u8 reserved1[2]; - u8 max_credit; /* 0-3, limit = 2^max */ - u8 reserved2[7]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_configure_vsi_bw_limit); - -/* Configure VSI Bandwidth Limit per Traffic Type (indirect 0x0406) - * responds with i40e_aqc_qs_handles_resp - */ -struct i40e_aqc_configure_vsi_ets_sla_bw_data { - u8 tc_valid_bits; - u8 reserved[15]; - __le16 tc_bw_credits[8]; /* FW writesback QS handles here */ - - /* 4 bits per tc 0-7, 4th bit is reserved, limit = 2^max */ - __le16 tc_bw_max[2]; - u8 reserved1[28]; -}; - -I40E_CHECK_STRUCT_LEN(0x40, i40e_aqc_configure_vsi_ets_sla_bw_data); - -/* Configure VSI Bandwidth Allocation per Traffic Type (indirect 0x0407) - * responds with i40e_aqc_qs_handles_resp - */ -struct i40e_aqc_configure_vsi_tc_bw_data { - u8 tc_valid_bits; - u8 reserved[3]; - u8 tc_bw_credits[8]; - u8 reserved1[4]; - __le16 qs_handles[8]; -}; - -I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_configure_vsi_tc_bw_data); - -/* Query vsi bw configuration (indirect 0x0408) */ -struct i40e_aqc_query_vsi_bw_config_resp { - u8 tc_valid_bits; - u8 tc_suspended_bits; - u8 reserved[14]; - __le16 qs_handles[8]; - u8 reserved1[4]; - __le16 port_bw_limit; - u8 reserved2[2]; - u8 max_bw; /* 0-3, limit = 2^max */ - u8 reserved3[23]; -}; - -I40E_CHECK_STRUCT_LEN(0x40, i40e_aqc_query_vsi_bw_config_resp); - -/* Query VSI Bandwidth Allocation per Traffic Type (indirect 0x040A) */ -struct i40e_aqc_query_vsi_ets_sla_config_resp { - u8 tc_valid_bits; - u8 reserved[3]; - u8 share_credits[8]; - __le16 credits[8]; - - /* 4 bits per tc 0-7, 4th bit is reserved, limit = 2^max */ - __le16 tc_bw_max[2]; -}; - -I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_query_vsi_ets_sla_config_resp); - -/* Configure Switching Component Bandwidth Limit (direct 0x0410) */ -struct i40e_aqc_configure_switching_comp_bw_limit { - __le16 seid; - u8 reserved[2]; - __le16 credit; - u8 reserved1[2]; - u8 max_bw; /* 0-3, limit = 2^max */ - u8 reserved2[7]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_configure_switching_comp_bw_limit); - -/* Enable Physical Port ETS (indirect 0x0413) - * Modify Physical Port ETS (indirect 0x0414) - * Disable Physical Port ETS (indirect 0x0415) - */ -struct i40e_aqc_configure_switching_comp_ets_data { - u8 reserved[4]; - u8 tc_valid_bits; - u8 seepage; -#define I40E_AQ_ETS_SEEPAGE_EN_MASK 0x1 - u8 tc_strict_priority_flags; - u8 reserved1[17]; - u8 tc_bw_share_credits[8]; - u8 reserved2[96]; -}; - -I40E_CHECK_STRUCT_LEN(0x80, i40e_aqc_configure_switching_comp_ets_data); - -/* Configure Switching Component Bandwidth Limits per Tc (indirect 0x0416) */ -struct i40e_aqc_configure_switching_comp_ets_bw_limit_data { - u8 tc_valid_bits; - u8 reserved[15]; - __le16 tc_bw_credit[8]; - - /* 4 bits per tc 0-7, 4th bit is reserved, limit = 2^max */ - __le16 tc_bw_max[2]; - u8 reserved1[28]; -}; - -I40E_CHECK_STRUCT_LEN(0x40, - i40e_aqc_configure_switching_comp_ets_bw_limit_data); - -/* Configure Switching Component Bandwidth Allocation per Tc - * (indirect 0x0417) - */ -struct i40e_aqc_configure_switching_comp_bw_config_data { - u8 tc_valid_bits; - u8 reserved[2]; - u8 absolute_credits; /* bool */ - u8 tc_bw_share_credits[8]; - u8 reserved1[20]; -}; - -I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_configure_switching_comp_bw_config_data); - -/* Query Switching Component Configuration (indirect 0x0418) */ -struct i40e_aqc_query_switching_comp_ets_config_resp { - u8 tc_valid_bits; - u8 reserved[35]; - __le16 port_bw_limit; - u8 reserved1[2]; - u8 tc_bw_max; /* 0-3, limit = 2^max */ - u8 reserved2[23]; -}; - -I40E_CHECK_STRUCT_LEN(0x40, i40e_aqc_query_switching_comp_ets_config_resp); - -/* Query PhysicalPort ETS Configuration (indirect 0x0419) */ -struct i40e_aqc_query_port_ets_config_resp { - u8 reserved[4]; - u8 tc_valid_bits; - u8 reserved1; - u8 tc_strict_priority_bits; - u8 reserved2; - u8 tc_bw_share_credits[8]; - __le16 tc_bw_limits[8]; - - /* 4 bits per tc 0-7, 4th bit reserved, limit = 2^max */ - __le16 tc_bw_max[2]; - u8 reserved3[32]; -}; - -I40E_CHECK_STRUCT_LEN(0x44, i40e_aqc_query_port_ets_config_resp); - -/* Query Switching Component Bandwidth Allocation per Traffic Type - * (indirect 0x041A) - */ -struct i40e_aqc_query_switching_comp_bw_config_resp { - u8 tc_valid_bits; - u8 reserved[2]; - u8 absolute_credits_enable; /* bool */ - u8 tc_bw_share_credits[8]; - __le16 tc_bw_limits[8]; - - /* 4 bits per tc 0-7, 4th bit is reserved, limit = 2^max */ - __le16 tc_bw_max[2]; -}; - -I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_query_switching_comp_bw_config_resp); - -/* Suspend/resume port TX traffic - * (direct 0x041B and 0x041C) uses the generic SEID struct - */ - -/* Configure partition BW - * (indirect 0x041D) - */ -struct i40e_aqc_configure_partition_bw_data { - __le16 pf_valid_bits; - u8 min_bw[16]; /* guaranteed bandwidth */ - u8 max_bw[16]; /* bandwidth limit */ -}; - -I40E_CHECK_STRUCT_LEN(0x22, i40e_aqc_configure_partition_bw_data); - -/* Get and set the active HMC resource profile and status. - * (direct 0x0500) and (direct 0x0501) - */ -struct i40e_aq_get_set_hmc_resource_profile { - u8 pm_profile; - u8 pe_vf_enabled; - u8 reserved[14]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aq_get_set_hmc_resource_profile); - -enum i40e_aq_hmc_profile { - /* I40E_HMC_PROFILE_NO_CHANGE = 0, reserved */ - I40E_HMC_PROFILE_DEFAULT = 1, - I40E_HMC_PROFILE_FAVOR_VF = 2, - I40E_HMC_PROFILE_EQUAL = 3, -}; - -/* Get PHY Abilities (indirect 0x0600) uses the generic indirect struct */ - -/* set in param0 for get phy abilities to report qualified modules */ -#define I40E_AQ_PHY_REPORT_QUALIFIED_MODULES 0x0001 -#define I40E_AQ_PHY_REPORT_INITIAL_VALUES 0x0002 - -enum i40e_aq_phy_type { - I40E_PHY_TYPE_SGMII = 0x0, - I40E_PHY_TYPE_1000BASE_KX = 0x1, - I40E_PHY_TYPE_10GBASE_KX4 = 0x2, - I40E_PHY_TYPE_10GBASE_KR = 0x3, - I40E_PHY_TYPE_40GBASE_KR4 = 0x4, - I40E_PHY_TYPE_XAUI = 0x5, - I40E_PHY_TYPE_XFI = 0x6, - I40E_PHY_TYPE_SFI = 0x7, - I40E_PHY_TYPE_XLAUI = 0x8, - I40E_PHY_TYPE_XLPPI = 0x9, - I40E_PHY_TYPE_40GBASE_CR4_CU = 0xA, - I40E_PHY_TYPE_10GBASE_CR1_CU = 0xB, - I40E_PHY_TYPE_10GBASE_AOC = 0xC, - I40E_PHY_TYPE_40GBASE_AOC = 0xD, - I40E_PHY_TYPE_UNRECOGNIZED = 0xE, - I40E_PHY_TYPE_UNSUPPORTED = 0xF, - I40E_PHY_TYPE_100BASE_TX = 0x11, - I40E_PHY_TYPE_1000BASE_T = 0x12, - I40E_PHY_TYPE_10GBASE_T = 0x13, - I40E_PHY_TYPE_10GBASE_SR = 0x14, - I40E_PHY_TYPE_10GBASE_LR = 0x15, - I40E_PHY_TYPE_10GBASE_SFPP_CU = 0x16, - I40E_PHY_TYPE_10GBASE_CR1 = 0x17, - I40E_PHY_TYPE_40GBASE_CR4 = 0x18, - I40E_PHY_TYPE_40GBASE_SR4 = 0x19, - I40E_PHY_TYPE_40GBASE_LR4 = 0x1A, - I40E_PHY_TYPE_1000BASE_SX = 0x1B, - I40E_PHY_TYPE_1000BASE_LX = 0x1C, - I40E_PHY_TYPE_1000BASE_T_OPTICAL = 0x1D, - I40E_PHY_TYPE_20GBASE_KR2 = 0x1E, - I40E_PHY_TYPE_25GBASE_KR = 0x1F, - I40E_PHY_TYPE_25GBASE_CR = 0x20, - I40E_PHY_TYPE_25GBASE_SR = 0x21, - I40E_PHY_TYPE_25GBASE_LR = 0x22, - I40E_PHY_TYPE_25GBASE_AOC = 0x23, - I40E_PHY_TYPE_25GBASE_ACC = 0x24, - I40E_PHY_TYPE_MAX, - I40E_PHY_TYPE_NOT_SUPPORTED_HIGH_TEMP = 0xFD, - I40E_PHY_TYPE_EMPTY = 0xFE, - I40E_PHY_TYPE_DEFAULT = 0xFF, -}; - -#define I40E_LINK_SPEED_100MB_SHIFT 0x1 -#define I40E_LINK_SPEED_1000MB_SHIFT 0x2 -#define I40E_LINK_SPEED_10GB_SHIFT 0x3 -#define I40E_LINK_SPEED_40GB_SHIFT 0x4 -#define I40E_LINK_SPEED_20GB_SHIFT 0x5 -#define I40E_LINK_SPEED_25GB_SHIFT 0x6 - -enum i40e_aq_link_speed { - I40E_LINK_SPEED_UNKNOWN = 0, - I40E_LINK_SPEED_100MB = BIT(I40E_LINK_SPEED_100MB_SHIFT), - I40E_LINK_SPEED_1GB = BIT(I40E_LINK_SPEED_1000MB_SHIFT), - I40E_LINK_SPEED_10GB = BIT(I40E_LINK_SPEED_10GB_SHIFT), - I40E_LINK_SPEED_40GB = BIT(I40E_LINK_SPEED_40GB_SHIFT), - I40E_LINK_SPEED_20GB = BIT(I40E_LINK_SPEED_20GB_SHIFT), - I40E_LINK_SPEED_25GB = BIT(I40E_LINK_SPEED_25GB_SHIFT), -}; - -struct i40e_aqc_module_desc { - u8 oui[3]; - u8 reserved1; - u8 part_number[16]; - u8 revision[4]; - u8 reserved2[8]; -}; - -I40E_CHECK_STRUCT_LEN(0x20, i40e_aqc_module_desc); - -struct i40e_aq_get_phy_abilities_resp { - __le32 phy_type; /* bitmap using the above enum for offsets */ - u8 link_speed; /* bitmap using the above enum bit patterns */ - u8 abilities; -#define I40E_AQ_PHY_FLAG_PAUSE_TX 0x01 -#define I40E_AQ_PHY_FLAG_PAUSE_RX 0x02 -#define I40E_AQ_PHY_FLAG_LOW_POWER 0x04 -#define I40E_AQ_PHY_LINK_ENABLED 0x08 -#define I40E_AQ_PHY_AN_ENABLED 0x10 -#define I40E_AQ_PHY_FLAG_MODULE_QUAL 0x20 -#define I40E_AQ_PHY_FEC_ABILITY_KR 0x40 -#define I40E_AQ_PHY_FEC_ABILITY_RS 0x80 - __le16 eee_capability; -#define I40E_AQ_EEE_100BASE_TX 0x0002 -#define I40E_AQ_EEE_1000BASE_T 0x0004 -#define I40E_AQ_EEE_10GBASE_T 0x0008 -#define I40E_AQ_EEE_1000BASE_KX 0x0010 -#define I40E_AQ_EEE_10GBASE_KX4 0x0020 -#define I40E_AQ_EEE_10GBASE_KR 0x0040 - __le32 eeer_val; - u8 d3_lpan; -#define I40E_AQ_SET_PHY_D3_LPAN_ENA 0x01 - u8 phy_type_ext; -#define I40E_AQ_PHY_TYPE_EXT_25G_KR 0X01 -#define I40E_AQ_PHY_TYPE_EXT_25G_CR 0X02 -#define I40E_AQ_PHY_TYPE_EXT_25G_SR 0x04 -#define I40E_AQ_PHY_TYPE_EXT_25G_LR 0x08 -#define I40E_AQ_PHY_TYPE_EXT_25G_AOC 0x10 -#define I40E_AQ_PHY_TYPE_EXT_25G_ACC 0x20 - u8 fec_cfg_curr_mod_ext_info; -#define I40E_AQ_ENABLE_FEC_KR 0x01 -#define I40E_AQ_ENABLE_FEC_RS 0x02 -#define I40E_AQ_REQUEST_FEC_KR 0x04 -#define I40E_AQ_REQUEST_FEC_RS 0x08 -#define I40E_AQ_ENABLE_FEC_AUTO 0x10 -#define I40E_AQ_FEC -#define I40E_AQ_MODULE_TYPE_EXT_MASK 0xE0 -#define I40E_AQ_MODULE_TYPE_EXT_SHIFT 5 - - u8 ext_comp_code; - u8 phy_id[4]; - u8 module_type[3]; - u8 qualified_module_count; -#define I40E_AQ_PHY_MAX_QMS 16 - struct i40e_aqc_module_desc qualified_module[I40E_AQ_PHY_MAX_QMS]; -}; - -I40E_CHECK_STRUCT_LEN(0x218, i40e_aq_get_phy_abilities_resp); - -/* Set PHY Config (direct 0x0601) */ -struct i40e_aq_set_phy_config { /* same bits as above in all */ - __le32 phy_type; - u8 link_speed; - u8 abilities; -/* bits 0-2 use the values from get_phy_abilities_resp */ -#define I40E_AQ_PHY_ENABLE_LINK 0x08 -#define I40E_AQ_PHY_ENABLE_AN 0x10 -#define I40E_AQ_PHY_ENABLE_ATOMIC_LINK 0x20 - __le16 eee_capability; - __le32 eeer; - u8 low_power_ctrl; - u8 phy_type_ext; -#define I40E_AQ_PHY_TYPE_EXT_25G_KR 0X01 -#define I40E_AQ_PHY_TYPE_EXT_25G_CR 0X02 -#define I40E_AQ_PHY_TYPE_EXT_25G_SR 0x04 -#define I40E_AQ_PHY_TYPE_EXT_25G_LR 0x08 - u8 fec_config; -#define I40E_AQ_SET_FEC_ABILITY_KR BIT(0) -#define I40E_AQ_SET_FEC_ABILITY_RS BIT(1) -#define I40E_AQ_SET_FEC_REQUEST_KR BIT(2) -#define I40E_AQ_SET_FEC_REQUEST_RS BIT(3) -#define I40E_AQ_SET_FEC_AUTO BIT(4) -#define I40E_AQ_PHY_FEC_CONFIG_SHIFT 0x0 -#define I40E_AQ_PHY_FEC_CONFIG_MASK (0x1F << I40E_AQ_PHY_FEC_CONFIG_SHIFT) - u8 reserved; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aq_set_phy_config); - -/* Set MAC Config command data structure (direct 0x0603) */ -struct i40e_aq_set_mac_config { - __le16 max_frame_size; - u8 params; -#define I40E_AQ_SET_MAC_CONFIG_CRC_EN 0x04 -#define I40E_AQ_SET_MAC_CONFIG_PACING_MASK 0x78 -#define I40E_AQ_SET_MAC_CONFIG_PACING_SHIFT 3 -#define I40E_AQ_SET_MAC_CONFIG_PACING_NONE 0x0 -#define I40E_AQ_SET_MAC_CONFIG_PACING_1B_13TX 0xF -#define I40E_AQ_SET_MAC_CONFIG_PACING_1DW_9TX 0x9 -#define I40E_AQ_SET_MAC_CONFIG_PACING_1DW_4TX 0x8 -#define I40E_AQ_SET_MAC_CONFIG_PACING_3DW_7TX 0x7 -#define I40E_AQ_SET_MAC_CONFIG_PACING_2DW_3TX 0x6 -#define I40E_AQ_SET_MAC_CONFIG_PACING_1DW_1TX 0x5 -#define I40E_AQ_SET_MAC_CONFIG_PACING_3DW_2TX 0x4 -#define I40E_AQ_SET_MAC_CONFIG_PACING_7DW_3TX 0x3 -#define I40E_AQ_SET_MAC_CONFIG_PACING_4DW_1TX 0x2 -#define I40E_AQ_SET_MAC_CONFIG_PACING_9DW_1TX 0x1 - u8 tx_timer_priority; /* bitmap */ - __le16 tx_timer_value; - __le16 fc_refresh_threshold; - u8 reserved[8]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aq_set_mac_config); - -/* Restart Auto-Negotiation (direct 0x605) */ -struct i40e_aqc_set_link_restart_an { - u8 command; -#define I40E_AQ_PHY_RESTART_AN 0x02 -#define I40E_AQ_PHY_LINK_ENABLE 0x04 - u8 reserved[15]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_set_link_restart_an); - -/* Get Link Status cmd & response data structure (direct 0x0607) */ -struct i40e_aqc_get_link_status { - __le16 command_flags; /* only field set on command */ -#define I40E_AQ_LSE_MASK 0x3 -#define I40E_AQ_LSE_NOP 0x0 -#define I40E_AQ_LSE_DISABLE 0x2 -#define I40E_AQ_LSE_ENABLE 0x3 -/* only response uses this flag */ -#define I40E_AQ_LSE_IS_ENABLED 0x1 - u8 phy_type; /* i40e_aq_phy_type */ - u8 link_speed; /* i40e_aq_link_speed */ - u8 link_info; -#define I40E_AQ_LINK_UP 0x01 /* obsolete */ -#define I40E_AQ_LINK_UP_FUNCTION 0x01 -#define I40E_AQ_LINK_FAULT 0x02 -#define I40E_AQ_LINK_FAULT_TX 0x04 -#define I40E_AQ_LINK_FAULT_RX 0x08 -#define I40E_AQ_LINK_FAULT_REMOTE 0x10 -#define I40E_AQ_LINK_UP_PORT 0x20 -#define I40E_AQ_MEDIA_AVAILABLE 0x40 -#define I40E_AQ_SIGNAL_DETECT 0x80 - u8 an_info; -#define I40E_AQ_AN_COMPLETED 0x01 -#define I40E_AQ_LP_AN_ABILITY 0x02 -#define I40E_AQ_PD_FAULT 0x04 -#define I40E_AQ_FEC_EN 0x08 -#define I40E_AQ_PHY_LOW_POWER 0x10 -#define I40E_AQ_LINK_PAUSE_TX 0x20 -#define I40E_AQ_LINK_PAUSE_RX 0x40 -#define I40E_AQ_QUALIFIED_MODULE 0x80 - u8 ext_info; -#define I40E_AQ_LINK_PHY_TEMP_ALARM 0x01 -#define I40E_AQ_LINK_XCESSIVE_ERRORS 0x02 -#define I40E_AQ_LINK_TX_SHIFT 0x02 -#define I40E_AQ_LINK_TX_MASK (0x03 << I40E_AQ_LINK_TX_SHIFT) -#define I40E_AQ_LINK_TX_ACTIVE 0x00 -#define I40E_AQ_LINK_TX_DRAINED 0x01 -#define I40E_AQ_LINK_TX_FLUSHED 0x03 -#define I40E_AQ_LINK_FORCED_40G 0x10 -/* 25G Error Codes */ -#define I40E_AQ_25G_NO_ERR 0X00 -#define I40E_AQ_25G_NOT_PRESENT 0X01 -#define I40E_AQ_25G_NVM_CRC_ERR 0X02 -#define I40E_AQ_25G_SBUS_UCODE_ERR 0X03 -#define I40E_AQ_25G_SERDES_UCODE_ERR 0X04 -#define I40E_AQ_25G_NIMB_UCODE_ERR 0X05 - u8 loopback; /* use defines from i40e_aqc_set_lb_mode */ -/* Since firmware API 1.7 loopback field keeps power class info as well */ -#define I40E_AQ_LOOPBACK_MASK 0x07 -#define I40E_AQ_PWR_CLASS_SHIFT_LB 6 -#define I40E_AQ_PWR_CLASS_MASK_LB (0x03 << I40E_AQ_PWR_CLASS_SHIFT_LB) - __le16 max_frame_size; - u8 config; -#define I40E_AQ_CONFIG_FEC_KR_ENA 0x01 -#define I40E_AQ_CONFIG_FEC_RS_ENA 0x02 -#define I40E_AQ_CONFIG_CRC_ENA 0x04 -#define I40E_AQ_CONFIG_PACING_MASK 0x78 - union { - struct { - u8 power_desc; -#define I40E_AQ_LINK_POWER_CLASS_1 0x00 -#define I40E_AQ_LINK_POWER_CLASS_2 0x01 -#define I40E_AQ_LINK_POWER_CLASS_3 0x02 -#define I40E_AQ_LINK_POWER_CLASS_4 0x03 -#define I40E_AQ_PWR_CLASS_MASK 0x03 - u8 reserved[4]; - }; - struct { - u8 link_type[4]; - u8 link_type_ext; - }; - }; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_get_link_status); - -/* Set event mask command (direct 0x613) */ -struct i40e_aqc_set_phy_int_mask { - u8 reserved[8]; - __le16 event_mask; -#define I40E_AQ_EVENT_LINK_UPDOWN 0x0002 -#define I40E_AQ_EVENT_MEDIA_NA 0x0004 -#define I40E_AQ_EVENT_LINK_FAULT 0x0008 -#define I40E_AQ_EVENT_PHY_TEMP_ALARM 0x0010 -#define I40E_AQ_EVENT_EXCESSIVE_ERRORS 0x0020 -#define I40E_AQ_EVENT_SIGNAL_DETECT 0x0040 -#define I40E_AQ_EVENT_AN_COMPLETED 0x0080 -#define I40E_AQ_EVENT_MODULE_QUAL_FAIL 0x0100 -#define I40E_AQ_EVENT_PORT_TX_SUSPENDED 0x0200 - u8 reserved1[6]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_set_phy_int_mask); - -/* Get Local AN advt register (direct 0x0614) - * Set Local AN advt register (direct 0x0615) - * Get Link Partner AN advt register (direct 0x0616) - */ -struct i40e_aqc_an_advt_reg { - __le32 local_an_reg0; - __le16 local_an_reg1; - u8 reserved[10]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_an_advt_reg); - -/* Set Loopback mode (0x0618) */ -struct i40e_aqc_set_lb_mode { - __le16 lb_mode; -#define I40E_AQ_LB_PHY_LOCAL 0x01 -#define I40E_AQ_LB_PHY_REMOTE 0x02 -#define I40E_AQ_LB_MAC_LOCAL 0x04 - u8 reserved[14]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_set_lb_mode); - -/* Set PHY Debug command (0x0622) */ -struct i40e_aqc_set_phy_debug { - u8 command_flags; -#define I40E_AQ_PHY_DEBUG_RESET_INTERNAL 0x02 -#define I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_SHIFT 2 -#define I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_MASK (0x03 << \ - I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_SHIFT) -#define I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_NONE 0x00 -#define I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_HARD 0x01 -#define I40E_AQ_PHY_DEBUG_RESET_EXTERNAL_SOFT 0x02 -#define I40E_AQ_PHY_DEBUG_DISABLE_LINK_FW 0x10 - u8 reserved[15]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_set_phy_debug); - -enum i40e_aq_phy_reg_type { - I40E_AQC_PHY_REG_INTERNAL = 0x1, - I40E_AQC_PHY_REG_EXERNAL_BASET = 0x2, - I40E_AQC_PHY_REG_EXERNAL_MODULE = 0x3 -}; - -/* Run PHY Activity (0x0626) */ -struct i40e_aqc_run_phy_activity { - __le16 activity_id; - u8 flags; - u8 reserved1; - __le32 control; - __le32 data; - u8 reserved2[4]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_run_phy_activity); - -/* Set PHY Register command (0x0628) */ -/* Get PHY Register command (0x0629) */ -struct i40e_aqc_phy_register_access { - u8 phy_interface; -#define I40E_AQ_PHY_REG_ACCESS_INTERNAL 0 -#define I40E_AQ_PHY_REG_ACCESS_EXTERNAL 1 -#define I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE 2 - u8 dev_address; - u8 reserved1[2]; - __le32 reg_address; - __le32 reg_value; - u8 reserved2[4]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_phy_register_access); - -/* NVM Read command (indirect 0x0701) - * NVM Erase commands (direct 0x0702) - * NVM Update commands (indirect 0x0703) - */ -struct i40e_aqc_nvm_update { - u8 command_flags; -#define I40E_AQ_NVM_LAST_CMD 0x01 -#define I40E_AQ_NVM_REARRANGE_TO_FLAT 0x20 -#define I40E_AQ_NVM_REARRANGE_TO_STRUCT 0x40 -#define I40E_AQ_NVM_FLASH_ONLY 0x80 -#define I40E_AQ_NVM_PRESERVATION_FLAGS_SHIFT 1 -#define I40E_AQ_NVM_PRESERVATION_FLAGS_MASK 0x03 -#define I40E_AQ_NVM_PRESERVATION_FLAGS_SELECTED 0x03 -#define I40E_AQ_NVM_PRESERVATION_FLAGS_ALL 0x01 - u8 module_pointer; - __le16 length; - __le32 offset; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_nvm_update); - -/* NVM Config Read (indirect 0x0704) */ -struct i40e_aqc_nvm_config_read { - __le16 cmd_flags; -#define I40E_AQ_ANVM_SINGLE_OR_MULTIPLE_FEATURES_MASK 1 -#define I40E_AQ_ANVM_READ_SINGLE_FEATURE 0 -#define I40E_AQ_ANVM_READ_MULTIPLE_FEATURES 1 - __le16 element_count; - __le16 element_id; /* Feature/field ID */ - __le16 element_id_msw; /* MSWord of field ID */ - __le32 address_high; - __le32 address_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_nvm_config_read); - -/* NVM Config Write (indirect 0x0705) */ -struct i40e_aqc_nvm_config_write { - __le16 cmd_flags; - __le16 element_count; - u8 reserved[4]; - __le32 address_high; - __le32 address_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_nvm_config_write); - -/* Used for 0x0704 as well as for 0x0705 commands */ -#define I40E_AQ_ANVM_FEATURE_OR_IMMEDIATE_SHIFT 1 -#define I40E_AQ_ANVM_FEATURE_OR_IMMEDIATE_MASK \ - BIT(I40E_AQ_ANVM_FEATURE_OR_IMMEDIATE_SHIFT) -#define I40E_AQ_ANVM_FEATURE 0 -#define I40E_AQ_ANVM_IMMEDIATE_FIELD BIT(FEATURE_OR_IMMEDIATE_SHIFT) -struct i40e_aqc_nvm_config_data_feature { - __le16 feature_id; -#define I40E_AQ_ANVM_FEATURE_OPTION_OEM_ONLY 0x01 -#define I40E_AQ_ANVM_FEATURE_OPTION_DWORD_MAP 0x08 -#define I40E_AQ_ANVM_FEATURE_OPTION_POR_CSR 0x10 - __le16 feature_options; - __le16 feature_selection; -}; - -I40E_CHECK_STRUCT_LEN(0x6, i40e_aqc_nvm_config_data_feature); - -struct i40e_aqc_nvm_config_data_immediate_field { - __le32 field_id; - __le32 field_value; - __le16 field_options; - __le16 reserved; -}; - -I40E_CHECK_STRUCT_LEN(0xc, i40e_aqc_nvm_config_data_immediate_field); - -/* OEM Post Update (indirect 0x0720) - * no command data struct used - */ - struct i40e_aqc_nvm_oem_post_update { -#define I40E_AQ_NVM_OEM_POST_UPDATE_EXTERNAL_DATA 0x01 - u8 sel_data; - u8 reserved[7]; -}; - -I40E_CHECK_STRUCT_LEN(0x8, i40e_aqc_nvm_oem_post_update); - -struct i40e_aqc_nvm_oem_post_update_buffer { - u8 str_len; - u8 dev_addr; - __le16 eeprom_addr; - u8 data[36]; -}; - -I40E_CHECK_STRUCT_LEN(0x28, i40e_aqc_nvm_oem_post_update_buffer); - -/* Thermal Sensor (indirect 0x0721) - * read or set thermal sensor configs and values - * takes a sensor and command specific data buffer, not detailed here - */ -struct i40e_aqc_thermal_sensor { - u8 sensor_action; -#define I40E_AQ_THERMAL_SENSOR_READ_CONFIG 0 -#define I40E_AQ_THERMAL_SENSOR_SET_CONFIG 1 -#define I40E_AQ_THERMAL_SENSOR_READ_TEMP 2 - u8 reserved[7]; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_thermal_sensor); - -/* Send to PF command (indirect 0x0801) id is only used by PF - * Send to VF command (indirect 0x0802) id is only used by PF - * Send to Peer PF command (indirect 0x0803) - */ -struct i40e_aqc_pf_vf_message { - __le32 id; - u8 reserved[4]; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_pf_vf_message); - -/* Alternate structure */ - -/* Direct write (direct 0x0900) - * Direct read (direct 0x0902) - */ -struct i40e_aqc_alternate_write { - __le32 address0; - __le32 data0; - __le32 address1; - __le32 data1; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_alternate_write); - -/* Indirect write (indirect 0x0901) - * Indirect read (indirect 0x0903) - */ - -struct i40e_aqc_alternate_ind_write { - __le32 address; - __le32 length; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_alternate_ind_write); - -/* Done alternate write (direct 0x0904) - * uses i40e_aq_desc - */ -struct i40e_aqc_alternate_write_done { - __le16 cmd_flags; -#define I40E_AQ_ALTERNATE_MODE_BIOS_MASK 1 -#define I40E_AQ_ALTERNATE_MODE_BIOS_LEGACY 0 -#define I40E_AQ_ALTERNATE_MODE_BIOS_UEFI 1 -#define I40E_AQ_ALTERNATE_RESET_NEEDED 2 - u8 reserved[14]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_alternate_write_done); - -/* Set OEM mode (direct 0x0905) */ -struct i40e_aqc_alternate_set_mode { - __le32 mode; -#define I40E_AQ_ALTERNATE_MODE_NONE 0 -#define I40E_AQ_ALTERNATE_MODE_OEM 1 - u8 reserved[12]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_alternate_set_mode); - -/* Clear port Alternate RAM (direct 0x0906) uses i40e_aq_desc */ - -/* async events 0x10xx */ - -/* Lan Queue Overflow Event (direct, 0x1001) */ -struct i40e_aqc_lan_overflow { - __le32 prtdcb_rupto; - __le32 otx_ctl; - u8 reserved[8]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_lan_overflow); - -/* Get LLDP MIB (indirect 0x0A00) */ -struct i40e_aqc_lldp_get_mib { - u8 type; - u8 reserved1; -#define I40E_AQ_LLDP_MIB_TYPE_MASK 0x3 -#define I40E_AQ_LLDP_MIB_LOCAL 0x0 -#define I40E_AQ_LLDP_MIB_REMOTE 0x1 -#define I40E_AQ_LLDP_MIB_LOCAL_AND_REMOTE 0x2 -#define I40E_AQ_LLDP_BRIDGE_TYPE_MASK 0xC -#define I40E_AQ_LLDP_BRIDGE_TYPE_SHIFT 0x2 -#define I40E_AQ_LLDP_BRIDGE_TYPE_NEAREST_BRIDGE 0x0 -#define I40E_AQ_LLDP_BRIDGE_TYPE_NON_TPMR 0x1 -#define I40E_AQ_LLDP_TX_SHIFT 0x4 -#define I40E_AQ_LLDP_TX_MASK (0x03 << I40E_AQ_LLDP_TX_SHIFT) -/* TX pause flags use I40E_AQ_LINK_TX_* above */ - __le16 local_len; - __le16 remote_len; - u8 reserved2[2]; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_get_mib); - -/* Configure LLDP MIB Change Event (direct 0x0A01) - * also used for the event (with type in the command field) - */ -struct i40e_aqc_lldp_update_mib { - u8 command; -#define I40E_AQ_LLDP_MIB_UPDATE_ENABLE 0x0 -#define I40E_AQ_LLDP_MIB_UPDATE_DISABLE 0x1 - u8 reserved[7]; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_update_mib); - -/* Add LLDP TLV (indirect 0x0A02) - * Delete LLDP TLV (indirect 0x0A04) - */ -struct i40e_aqc_lldp_add_tlv { - u8 type; /* only nearest bridge and non-TPMR from 0x0A00 */ - u8 reserved1[1]; - __le16 len; - u8 reserved2[4]; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_add_tlv); - -/* Update LLDP TLV (indirect 0x0A03) */ -struct i40e_aqc_lldp_update_tlv { - u8 type; /* only nearest bridge and non-TPMR from 0x0A00 */ - u8 reserved; - __le16 old_len; - __le16 new_offset; - __le16 new_len; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_update_tlv); - -/* Stop LLDP (direct 0x0A05) */ -struct i40e_aqc_lldp_stop { - u8 command; -#define I40E_AQ_LLDP_AGENT_STOP 0x0 -#define I40E_AQ_LLDP_AGENT_SHUTDOWN 0x1 - u8 reserved[15]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_stop); - -/* Start LLDP (direct 0x0A06) */ - -struct i40e_aqc_lldp_start { - u8 command; -#define I40E_AQ_LLDP_AGENT_START 0x1 - u8 reserved[15]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_lldp_start); - -/* Set DCB (direct 0x0303) */ -struct i40e_aqc_set_dcb_parameters { - u8 command; -#define I40E_AQ_DCB_SET_AGENT 0x1 -#define I40E_DCB_VALID 0x1 - u8 valid_flags; - u8 reserved[14]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_set_dcb_parameters); - -/* Apply MIB changes (0x0A07) - * uses the generic struc as it contains no data - */ - -/* Add Udp Tunnel command and completion (direct 0x0B00) */ -struct i40e_aqc_add_udp_tunnel { - __le16 udp_port; - u8 reserved0[3]; - u8 protocol_type; -#define I40E_AQC_TUNNEL_TYPE_VXLAN 0x00 -#define I40E_AQC_TUNNEL_TYPE_NGE 0x01 -#define I40E_AQC_TUNNEL_TYPE_TEREDO 0x10 -#define I40E_AQC_TUNNEL_TYPE_VXLAN_GPE 0x11 - u8 reserved1[10]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_udp_tunnel); - -struct i40e_aqc_add_udp_tunnel_completion { - __le16 udp_port; - u8 filter_entry_index; - u8 multiple_pfs; -#define I40E_AQC_SINGLE_PF 0x0 -#define I40E_AQC_MULTIPLE_PFS 0x1 - u8 total_filters; - u8 reserved[11]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_add_udp_tunnel_completion); - -/* remove UDP Tunnel command (0x0B01) */ -struct i40e_aqc_remove_udp_tunnel { - u8 reserved[2]; - u8 index; /* 0 to 15 */ - u8 reserved2[13]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_remove_udp_tunnel); - -struct i40e_aqc_del_udp_tunnel_completion { - __le16 udp_port; - u8 index; /* 0 to 15 */ - u8 multiple_pfs; - u8 total_filters_used; - u8 reserved1[11]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_del_udp_tunnel_completion); - -struct i40e_aqc_get_set_rss_key { -#define I40E_AQC_SET_RSS_KEY_VSI_VALID BIT(15) -#define I40E_AQC_SET_RSS_KEY_VSI_ID_SHIFT 0 -#define I40E_AQC_SET_RSS_KEY_VSI_ID_MASK (0x3FF << \ - I40E_AQC_SET_RSS_KEY_VSI_ID_SHIFT) - __le16 vsi_id; - u8 reserved[6]; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_get_set_rss_key); - -struct i40e_aqc_get_set_rss_key_data { - u8 standard_rss_key[0x28]; - u8 extended_hash_key[0xc]; -}; - -I40E_CHECK_STRUCT_LEN(0x34, i40e_aqc_get_set_rss_key_data); - -struct i40e_aqc_get_set_rss_lut { -#define I40E_AQC_SET_RSS_LUT_VSI_VALID BIT(15) -#define I40E_AQC_SET_RSS_LUT_VSI_ID_SHIFT 0 -#define I40E_AQC_SET_RSS_LUT_VSI_ID_MASK (0x3FF << \ - I40E_AQC_SET_RSS_LUT_VSI_ID_SHIFT) - __le16 vsi_id; -#define I40E_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT 0 -#define I40E_AQC_SET_RSS_LUT_TABLE_TYPE_MASK \ - BIT(I40E_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT) - -#define I40E_AQC_SET_RSS_LUT_TABLE_TYPE_VSI 0 -#define I40E_AQC_SET_RSS_LUT_TABLE_TYPE_PF 1 - __le16 flags; - u8 reserved[4]; - __le32 addr_high; - __le32 addr_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_get_set_rss_lut); - -/* tunnel key structure 0x0B10 */ - -struct i40e_aqc_tunnel_key_structure_A0 { - __le16 key1_off; - __le16 key1_len; - __le16 key2_off; - __le16 key2_len; - __le16 flags; -#define I40E_AQC_TUNNEL_KEY_STRUCT_OVERRIDE 0x01 -/* response flags */ -#define I40E_AQC_TUNNEL_KEY_STRUCT_SUCCESS 0x01 -#define I40E_AQC_TUNNEL_KEY_STRUCT_MODIFIED 0x02 -#define I40E_AQC_TUNNEL_KEY_STRUCT_OVERRIDDEN 0x03 - u8 resreved[6]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_tunnel_key_structure_A0); - -struct i40e_aqc_tunnel_key_structure { - u8 key1_off; - u8 key2_off; - u8 key1_len; /* 0 to 15 */ - u8 key2_len; /* 0 to 15 */ - u8 flags; -#define I40E_AQC_TUNNEL_KEY_STRUCT_OVERRIDE 0x01 -/* response flags */ -#define I40E_AQC_TUNNEL_KEY_STRUCT_SUCCESS 0x01 -#define I40E_AQC_TUNNEL_KEY_STRUCT_MODIFIED 0x02 -#define I40E_AQC_TUNNEL_KEY_STRUCT_OVERRIDDEN 0x03 - u8 network_key_index; -#define I40E_AQC_NETWORK_KEY_INDEX_VXLAN 0x0 -#define I40E_AQC_NETWORK_KEY_INDEX_NGE 0x1 -#define I40E_AQC_NETWORK_KEY_INDEX_FLEX_MAC_IN_UDP 0x2 -#define I40E_AQC_NETWORK_KEY_INDEX_GRE 0x3 - u8 reserved[10]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_tunnel_key_structure); - -/* OEM mode commands (direct 0xFE0x) */ -struct i40e_aqc_oem_param_change { - __le32 param_type; -#define I40E_AQ_OEM_PARAM_TYPE_PF_CTL 0 -#define I40E_AQ_OEM_PARAM_TYPE_BW_CTL 1 -#define I40E_AQ_OEM_PARAM_MAC 2 - __le32 param_value1; - __le16 param_value2; - u8 reserved[6]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_oem_param_change); - -struct i40e_aqc_oem_state_change { - __le32 state; -#define I40E_AQ_OEM_STATE_LINK_DOWN 0x0 -#define I40E_AQ_OEM_STATE_LINK_UP 0x1 - u8 reserved[12]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_oem_state_change); - -/* Initialize OCSD (0xFE02, direct) */ -struct i40e_aqc_opc_oem_ocsd_initialize { - u8 type_status; - u8 reserved1[3]; - __le32 ocsd_memory_block_addr_high; - __le32 ocsd_memory_block_addr_low; - __le32 requested_update_interval; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_opc_oem_ocsd_initialize); - -/* Initialize OCBB (0xFE03, direct) */ -struct i40e_aqc_opc_oem_ocbb_initialize { - u8 type_status; - u8 reserved1[3]; - __le32 ocbb_memory_block_addr_high; - __le32 ocbb_memory_block_addr_low; - u8 reserved2[4]; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_opc_oem_ocbb_initialize); - -/* debug commands */ - -/* get device id (0xFF00) uses the generic structure */ - -/* set test more (0xFF01, internal) */ - -struct i40e_acq_set_test_mode { - u8 mode; -#define I40E_AQ_TEST_PARTIAL 0 -#define I40E_AQ_TEST_FULL 1 -#define I40E_AQ_TEST_NVM 2 - u8 reserved[3]; - u8 command; -#define I40E_AQ_TEST_OPEN 0 -#define I40E_AQ_TEST_CLOSE 1 -#define I40E_AQ_TEST_INC 2 - u8 reserved2[3]; - __le32 address_high; - __le32 address_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_acq_set_test_mode); - -/* Debug Read Register command (0xFF03) - * Debug Write Register command (0xFF04) - */ -struct i40e_aqc_debug_reg_read_write { - __le32 reserved; - __le32 address; - __le32 value_high; - __le32 value_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_debug_reg_read_write); - -/* Scatter/gather Reg Read (indirect 0xFF05) - * Scatter/gather Reg Write (indirect 0xFF06) - */ - -/* i40e_aq_desc is used for the command */ -struct i40e_aqc_debug_reg_sg_element_data { - __le32 address; - __le32 value; -}; - -/* Debug Modify register (direct 0xFF07) */ -struct i40e_aqc_debug_modify_reg { - __le32 address; - __le32 value; - __le32 clear_mask; - __le32 set_mask; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_debug_modify_reg); - -/* dump internal data (0xFF08, indirect) */ - -#define I40E_AQ_CLUSTER_ID_AUX 0 -#define I40E_AQ_CLUSTER_ID_SWITCH_FLU 1 -#define I40E_AQ_CLUSTER_ID_TXSCHED 2 -#define I40E_AQ_CLUSTER_ID_HMC 3 -#define I40E_AQ_CLUSTER_ID_MAC0 4 -#define I40E_AQ_CLUSTER_ID_MAC1 5 -#define I40E_AQ_CLUSTER_ID_MAC2 6 -#define I40E_AQ_CLUSTER_ID_MAC3 7 -#define I40E_AQ_CLUSTER_ID_DCB 8 -#define I40E_AQ_CLUSTER_ID_EMP_MEM 9 -#define I40E_AQ_CLUSTER_ID_PKT_BUF 10 -#define I40E_AQ_CLUSTER_ID_ALTRAM 11 - -struct i40e_aqc_debug_dump_internals { - u8 cluster_id; - u8 table_id; - __le16 data_size; - __le32 idx; - __le32 address_high; - __le32 address_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_debug_dump_internals); - -struct i40e_aqc_debug_modify_internals { - u8 cluster_id; - u8 cluster_specific_params[7]; - __le32 address_high; - __le32 address_low; -}; - -I40E_CHECK_CMD_LENGTH(i40e_aqc_debug_modify_internals); - -#endif /* _I40E_ADMINQ_CMD_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_alloc.h b/drivers/net/ethernet/intel/i40evf/i40e_alloc.h deleted file mode 100644 index cb8689222c8b..000000000000 --- a/drivers/net/ethernet/intel/i40evf/i40e_alloc.h +++ /dev/null @@ -1,35 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 2013 - 2018 Intel Corporation. */ - -#ifndef _I40E_ALLOC_H_ -#define _I40E_ALLOC_H_ - -struct i40e_hw; - -/* Memory allocation types */ -enum i40e_memory_type { - i40e_mem_arq_buf = 0, /* ARQ indirect command buffer */ - i40e_mem_asq_buf = 1, - i40e_mem_atq_buf = 2, /* ATQ indirect command buffer */ - i40e_mem_arq_ring = 3, /* ARQ descriptor ring */ - i40e_mem_atq_ring = 4, /* ATQ descriptor ring */ - i40e_mem_pd = 5, /* Page Descriptor */ - i40e_mem_bp = 6, /* Backing Page - 4KB */ - i40e_mem_bp_jumbo = 7, /* Backing Page - > 4KB */ - i40e_mem_reserved -}; - -/* prototype for functions used for dynamic memory allocation */ -i40e_status i40e_allocate_dma_mem(struct i40e_hw *hw, - struct i40e_dma_mem *mem, - enum i40e_memory_type type, - u64 size, u32 alignment); -i40e_status i40e_free_dma_mem(struct i40e_hw *hw, - struct i40e_dma_mem *mem); -i40e_status i40e_allocate_virt_mem(struct i40e_hw *hw, - struct i40e_virt_mem *mem, - u32 size); -i40e_status i40e_free_virt_mem(struct i40e_hw *hw, - struct i40e_virt_mem *mem); - -#endif /* _I40E_ALLOC_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_common.c b/drivers/net/ethernet/intel/i40evf/i40e_common.c deleted file mode 100644 index eea280ba411e..000000000000 --- a/drivers/net/ethernet/intel/i40evf/i40e_common.c +++ /dev/null @@ -1,1320 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ - -#include "i40e_type.h" -#include "i40e_adminq.h" -#include "i40e_prototype.h" -#include <linux/avf/virtchnl.h> - -/** - * i40e_set_mac_type - Sets MAC type - * @hw: pointer to the HW structure - * - * This function sets the mac type of the adapter based on the - * vendor ID and device ID stored in the hw structure. - **/ -i40e_status i40e_set_mac_type(struct i40e_hw *hw) -{ - i40e_status status = 0; - - if (hw->vendor_id == PCI_VENDOR_ID_INTEL) { - switch (hw->device_id) { - case I40E_DEV_ID_SFP_XL710: - case I40E_DEV_ID_QEMU: - case I40E_DEV_ID_KX_B: - case I40E_DEV_ID_KX_C: - case I40E_DEV_ID_QSFP_A: - case I40E_DEV_ID_QSFP_B: - case I40E_DEV_ID_QSFP_C: - case I40E_DEV_ID_10G_BASE_T: - case I40E_DEV_ID_10G_BASE_T4: - case I40E_DEV_ID_20G_KR2: - case I40E_DEV_ID_20G_KR2_A: - case I40E_DEV_ID_25G_B: - case I40E_DEV_ID_25G_SFP28: - hw->mac.type = I40E_MAC_XL710; - break; - case I40E_DEV_ID_SFP_X722: - case I40E_DEV_ID_1G_BASE_T_X722: - case I40E_DEV_ID_10G_BASE_T_X722: - case I40E_DEV_ID_SFP_I_X722: - hw->mac.type = I40E_MAC_X722; - break; - case I40E_DEV_ID_X722_VF: - hw->mac.type = I40E_MAC_X722_VF; - break; - case I40E_DEV_ID_VF: - case I40E_DEV_ID_VF_HV: - case I40E_DEV_ID_ADAPTIVE_VF: - hw->mac.type = I40E_MAC_VF; - break; - default: - hw->mac.type = I40E_MAC_GENERIC; - break; - } - } else { - status = I40E_ERR_DEVICE_NOT_SUPPORTED; - } - - hw_dbg(hw, "i40e_set_mac_type found mac: %d, returns: %d\n", - hw->mac.type, status); - return status; -} - -/** - * i40evf_aq_str - convert AQ err code to a string - * @hw: pointer to the HW structure - * @aq_err: the AQ error code to convert - **/ -const char *i40evf_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err) -{ - switch (aq_err) { - case I40E_AQ_RC_OK: - return "OK"; - case I40E_AQ_RC_EPERM: - return "I40E_AQ_RC_EPERM"; - case I40E_AQ_RC_ENOENT: - return "I40E_AQ_RC_ENOENT"; - case I40E_AQ_RC_ESRCH: - return "I40E_AQ_RC_ESRCH"; - case I40E_AQ_RC_EINTR: - return "I40E_AQ_RC_EINTR"; - case I40E_AQ_RC_EIO: - return "I40E_AQ_RC_EIO"; - case I40E_AQ_RC_ENXIO: - return "I40E_AQ_RC_ENXIO"; - case I40E_AQ_RC_E2BIG: - return "I40E_AQ_RC_E2BIG"; - case I40E_AQ_RC_EAGAIN: - return "I40E_AQ_RC_EAGAIN"; - case I40E_AQ_RC_ENOMEM: - return "I40E_AQ_RC_ENOMEM"; - case I40E_AQ_RC_EACCES: - return "I40E_AQ_RC_EACCES"; - case I40E_AQ_RC_EFAULT: - return "I40E_AQ_RC_EFAULT"; - case I40E_AQ_RC_EBUSY: - return "I40E_AQ_RC_EBUSY"; - case I40E_AQ_RC_EEXIST: - return "I40E_AQ_RC_EEXIST"; - case I40E_AQ_RC_EINVAL: - return "I40E_AQ_RC_EINVAL"; - case I40E_AQ_RC_ENOTTY: - return "I40E_AQ_RC_ENOTTY"; - case I40E_AQ_RC_ENOSPC: - return "I40E_AQ_RC_ENOSPC"; - case I40E_AQ_RC_ENOSYS: - return "I40E_AQ_RC_ENOSYS"; - case I40E_AQ_RC_ERANGE: - return "I40E_AQ_RC_ERANGE"; - case I40E_AQ_RC_EFLUSHED: - return "I40E_AQ_RC_EFLUSHED"; - case I40E_AQ_RC_BAD_ADDR: - return "I40E_AQ_RC_BAD_ADDR"; - case I40E_AQ_RC_EMODE: - return "I40E_AQ_RC_EMODE"; - case I40E_AQ_RC_EFBIG: - return "I40E_AQ_RC_EFBIG"; - } - - snprintf(hw->err_str, sizeof(hw->err_str), "%d", aq_err); - return hw->err_str; -} - -/** - * i40evf_stat_str - convert status err code to a string - * @hw: pointer to the HW structure - * @stat_err: the status error code to convert - **/ -const char *i40evf_stat_str(struct i40e_hw *hw, i40e_status stat_err) -{ - switch (stat_err) { - case 0: - return "OK"; - case I40E_ERR_NVM: - return "I40E_ERR_NVM"; - case I40E_ERR_NVM_CHECKSUM: - return "I40E_ERR_NVM_CHECKSUM"; - case I40E_ERR_PHY: - return "I40E_ERR_PHY"; - case I40E_ERR_CONFIG: - return "I40E_ERR_CONFIG"; - case I40E_ERR_PARAM: - return "I40E_ERR_PARAM"; - case I40E_ERR_MAC_TYPE: - return "I40E_ERR_MAC_TYPE"; - case I40E_ERR_UNKNOWN_PHY: - return "I40E_ERR_UNKNOWN_PHY"; - case I40E_ERR_LINK_SETUP: - return "I40E_ERR_LINK_SETUP"; - case I40E_ERR_ADAPTER_STOPPED: - return "I40E_ERR_ADAPTER_STOPPED"; - case I40E_ERR_INVALID_MAC_ADDR: - return "I40E_ERR_INVALID_MAC_ADDR"; - case I40E_ERR_DEVICE_NOT_SUPPORTED: - return "I40E_ERR_DEVICE_NOT_SUPPORTED"; - case I40E_ERR_MASTER_REQUESTS_PENDING: - return "I40E_ERR_MASTER_REQUESTS_PENDING"; - case I40E_ERR_INVALID_LINK_SETTINGS: - return "I40E_ERR_INVALID_LINK_SETTINGS"; - case I40E_ERR_AUTONEG_NOT_COMPLETE: - return "I40E_ERR_AUTONEG_NOT_COMPLETE"; - case I40E_ERR_RESET_FAILED: - return "I40E_ERR_RESET_FAILED"; - case I40E_ERR_SWFW_SYNC: - return "I40E_ERR_SWFW_SYNC"; - case I40E_ERR_NO_AVAILABLE_VSI: - return "I40E_ERR_NO_AVAILABLE_VSI"; - case I40E_ERR_NO_MEMORY: - return "I40E_ERR_NO_MEMORY"; - case I40E_ERR_BAD_PTR: - return "I40E_ERR_BAD_PTR"; - case I40E_ERR_RING_FULL: - return "I40E_ERR_RING_FULL"; - case I40E_ERR_INVALID_PD_ID: - return "I40E_ERR_INVALID_PD_ID"; - case I40E_ERR_INVALID_QP_ID: - return "I40E_ERR_INVALID_QP_ID"; - case I40E_ERR_INVALID_CQ_ID: - return "I40E_ERR_INVALID_CQ_ID"; - case I40E_ERR_INVALID_CEQ_ID: - return "I40E_ERR_INVALID_CEQ_ID"; - case I40E_ERR_INVALID_AEQ_ID: - return "I40E_ERR_INVALID_AEQ_ID"; - case I40E_ERR_INVALID_SIZE: - return "I40E_ERR_INVALID_SIZE"; - case I40E_ERR_INVALID_ARP_INDEX: - return "I40E_ERR_INVALID_ARP_INDEX"; - case I40E_ERR_INVALID_FPM_FUNC_ID: - return "I40E_ERR_INVALID_FPM_FUNC_ID"; - case I40E_ERR_QP_INVALID_MSG_SIZE: - return "I40E_ERR_QP_INVALID_MSG_SIZE"; - case I40E_ERR_QP_TOOMANY_WRS_POSTED: - return "I40E_ERR_QP_TOOMANY_WRS_POSTED"; - case I40E_ERR_INVALID_FRAG_COUNT: - return "I40E_ERR_INVALID_FRAG_COUNT"; - case I40E_ERR_QUEUE_EMPTY: - return "I40E_ERR_QUEUE_EMPTY"; - case I40E_ERR_INVALID_ALIGNMENT: - return "I40E_ERR_INVALID_ALIGNMENT"; - case I40E_ERR_FLUSHED_QUEUE: - return "I40E_ERR_FLUSHED_QUEUE"; - case I40E_ERR_INVALID_PUSH_PAGE_INDEX: - return "I40E_ERR_INVALID_PUSH_PAGE_INDEX"; - case I40E_ERR_INVALID_IMM_DATA_SIZE: - return "I40E_ERR_INVALID_IMM_DATA_SIZE"; - case I40E_ERR_TIMEOUT: - return "I40E_ERR_TIMEOUT"; - case I40E_ERR_OPCODE_MISMATCH: - return "I40E_ERR_OPCODE_MISMATCH"; - case I40E_ERR_CQP_COMPL_ERROR: - return "I40E_ERR_CQP_COMPL_ERROR"; - case I40E_ERR_INVALID_VF_ID: - return "I40E_ERR_INVALID_VF_ID"; - case I40E_ERR_INVALID_HMCFN_ID: - return "I40E_ERR_INVALID_HMCFN_ID"; - case I40E_ERR_BACKING_PAGE_ERROR: - return "I40E_ERR_BACKING_PAGE_ERROR"; - case I40E_ERR_NO_PBLCHUNKS_AVAILABLE: - return "I40E_ERR_NO_PBLCHUNKS_AVAILABLE"; - case I40E_ERR_INVALID_PBLE_INDEX: - return "I40E_ERR_INVALID_PBLE_INDEX"; - case I40E_ERR_INVALID_SD_INDEX: - return "I40E_ERR_INVALID_SD_INDEX"; - case I40E_ERR_INVALID_PAGE_DESC_INDEX: - return "I40E_ERR_INVALID_PAGE_DESC_INDEX"; - case I40E_ERR_INVALID_SD_TYPE: - return "I40E_ERR_INVALID_SD_TYPE"; - case I40E_ERR_MEMCPY_FAILED: - return "I40E_ERR_MEMCPY_FAILED"; - case I40E_ERR_INVALID_HMC_OBJ_INDEX: - return "I40E_ERR_INVALID_HMC_OBJ_INDEX"; - case I40E_ERR_INVALID_HMC_OBJ_COUNT: - return "I40E_ERR_INVALID_HMC_OBJ_COUNT"; - case I40E_ERR_INVALID_SRQ_ARM_LIMIT: - return "I40E_ERR_INVALID_SRQ_ARM_LIMIT"; - case I40E_ERR_SRQ_ENABLED: - return "I40E_ERR_SRQ_ENABLED"; - case I40E_ERR_ADMIN_QUEUE_ERROR: - return "I40E_ERR_ADMIN_QUEUE_ERROR"; - case I40E_ERR_ADMIN_QUEUE_TIMEOUT: - return "I40E_ERR_ADMIN_QUEUE_TIMEOUT"; - case I40E_ERR_BUF_TOO_SHORT: - return "I40E_ERR_BUF_TOO_SHORT"; - case I40E_ERR_ADMIN_QUEUE_FULL: - return "I40E_ERR_ADMIN_QUEUE_FULL"; - case I40E_ERR_ADMIN_QUEUE_NO_WORK: - return "I40E_ERR_ADMIN_QUEUE_NO_WORK"; - case I40E_ERR_BAD_IWARP_CQE: - return "I40E_ERR_BAD_IWARP_CQE"; - case I40E_ERR_NVM_BLANK_MODE: - return "I40E_ERR_NVM_BLANK_MODE"; - case I40E_ERR_NOT_IMPLEMENTED: - return "I40E_ERR_NOT_IMPLEMENTED"; - case I40E_ERR_PE_DOORBELL_NOT_ENABLED: - return "I40E_ERR_PE_DOORBELL_NOT_ENABLED"; - case I40E_ERR_DIAG_TEST_FAILED: - return "I40E_ERR_DIAG_TEST_FAILED"; - case I40E_ERR_NOT_READY: - return "I40E_ERR_NOT_READY"; - case I40E_NOT_SUPPORTED: - return "I40E_NOT_SUPPORTED"; - case I40E_ERR_FIRMWARE_API_VERSION: - return "I40E_ERR_FIRMWARE_API_VERSION"; - case I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR: - return "I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR"; - } - - snprintf(hw->err_str, sizeof(hw->err_str), "%d", stat_err); - return hw->err_str; -} - -/** - * i40evf_debug_aq - * @hw: debug mask related to admin queue - * @mask: debug mask - * @desc: pointer to admin queue descriptor - * @buffer: pointer to command buffer - * @buf_len: max length of buffer - * - * Dumps debug log about adminq command with descriptor contents. - **/ -void i40evf_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask, void *desc, - void *buffer, u16 buf_len) -{ - struct i40e_aq_desc *aq_desc = (struct i40e_aq_desc *)desc; - u8 *buf = (u8 *)buffer; - - if ((!(mask & hw->debug_mask)) || (desc == NULL)) - return; - - i40e_debug(hw, mask, - "AQ CMD: opcode 0x%04X, flags 0x%04X, datalen 0x%04X, retval 0x%04X\n", - le16_to_cpu(aq_desc->opcode), - le16_to_cpu(aq_desc->flags), - le16_to_cpu(aq_desc->datalen), - le16_to_cpu(aq_desc->retval)); - i40e_debug(hw, mask, "\tcookie (h,l) 0x%08X 0x%08X\n", - le32_to_cpu(aq_desc->cookie_high), - le32_to_cpu(aq_desc->cookie_low)); - i40e_debug(hw, mask, "\tparam (0,1) 0x%08X 0x%08X\n", - le32_to_cpu(aq_desc->params.internal.param0), - le32_to_cpu(aq_desc->params.internal.param1)); - i40e_debug(hw, mask, "\taddr (h,l) 0x%08X 0x%08X\n", - le32_to_cpu(aq_desc->params.external.addr_high), - le32_to_cpu(aq_desc->params.external.addr_low)); - - if ((buffer != NULL) && (aq_desc->datalen != 0)) { - u16 len = le16_to_cpu(aq_desc->datalen); - - i40e_debug(hw, mask, "AQ CMD Buffer:\n"); - if (buf_len < len) - len = buf_len; - /* write the full 16-byte chunks */ - if (hw->debug_mask & mask) { - char prefix[27]; - - snprintf(prefix, sizeof(prefix), - "i40evf %02x:%02x.%x: \t0x", - hw->bus.bus_id, - hw->bus.device, - hw->bus.func); - - print_hex_dump(KERN_INFO, prefix, DUMP_PREFIX_OFFSET, - 16, 1, buf, len, false); - } - } -} - -/** - * i40evf_check_asq_alive - * @hw: pointer to the hw struct - * - * Returns true if Queue is enabled else false. - **/ -bool i40evf_check_asq_alive(struct i40e_hw *hw) -{ - if (hw->aq.asq.len) - return !!(rd32(hw, hw->aq.asq.len) & - I40E_VF_ATQLEN1_ATQENABLE_MASK); - else - return false; -} - -/** - * i40evf_aq_queue_shutdown - * @hw: pointer to the hw struct - * @unloading: is the driver unloading itself - * - * Tell the Firmware that we're shutting down the AdminQ and whether - * or not the driver is unloading as well. - **/ -i40e_status i40evf_aq_queue_shutdown(struct i40e_hw *hw, - bool unloading) -{ - struct i40e_aq_desc desc; - struct i40e_aqc_queue_shutdown *cmd = - (struct i40e_aqc_queue_shutdown *)&desc.params.raw; - i40e_status status; - - i40evf_fill_default_direct_cmd_desc(&desc, - i40e_aqc_opc_queue_shutdown); - - if (unloading) - cmd->driver_unloading = cpu_to_le32(I40E_AQ_DRIVER_UNLOADING); - status = i40evf_asq_send_command(hw, &desc, NULL, 0, NULL); - - return status; -} - -/** - * i40e_aq_get_set_rss_lut - * @hw: pointer to the hardware structure - * @vsi_id: vsi fw index - * @pf_lut: for PF table set true, for VSI table set false - * @lut: pointer to the lut buffer provided by the caller - * @lut_size: size of the lut buffer - * @set: set true to set the table, false to get the table - * - * Internal function to get or set RSS look up table - **/ -static i40e_status i40e_aq_get_set_rss_lut(struct i40e_hw *hw, - u16 vsi_id, bool pf_lut, - u8 *lut, u16 lut_size, - bool set) -{ - i40e_status status; - struct i40e_aq_desc desc; - struct i40e_aqc_get_set_rss_lut *cmd_resp = - (struct i40e_aqc_get_set_rss_lut *)&desc.params.raw; - - if (set) - i40evf_fill_default_direct_cmd_desc(&desc, - i40e_aqc_opc_set_rss_lut); - else - i40evf_fill_default_direct_cmd_desc(&desc, - i40e_aqc_opc_get_rss_lut); - - /* Indirect command */ - desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF); - desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_RD); - - cmd_resp->vsi_id = - cpu_to_le16((u16)((vsi_id << - I40E_AQC_SET_RSS_LUT_VSI_ID_SHIFT) & - I40E_AQC_SET_RSS_LUT_VSI_ID_MASK)); - cmd_resp->vsi_id |= cpu_to_le16((u16)I40E_AQC_SET_RSS_LUT_VSI_VALID); - - if (pf_lut) - cmd_resp->flags |= cpu_to_le16((u16) - ((I40E_AQC_SET_RSS_LUT_TABLE_TYPE_PF << - I40E_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT) & - I40E_AQC_SET_RSS_LUT_TABLE_TYPE_MASK)); - else - cmd_resp->flags |= cpu_to_le16((u16) - ((I40E_AQC_SET_RSS_LUT_TABLE_TYPE_VSI << - I40E_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT) & - I40E_AQC_SET_RSS_LUT_TABLE_TYPE_MASK)); - - status = i40evf_asq_send_command(hw, &desc, lut, lut_size, NULL); - - return status; -} - -/** - * i40evf_aq_get_rss_lut - * @hw: pointer to the hardware structure - * @vsi_id: vsi fw index - * @pf_lut: for PF table set true, for VSI table set false - * @lut: pointer to the lut buffer provided by the caller - * @lut_size: size of the lut buffer - * - * get the RSS lookup table, PF or VSI type - **/ -i40e_status i40evf_aq_get_rss_lut(struct i40e_hw *hw, u16 vsi_id, - bool pf_lut, u8 *lut, u16 lut_size) -{ - return i40e_aq_get_set_rss_lut(hw, vsi_id, pf_lut, lut, lut_size, - false); -} - -/** - * i40evf_aq_set_rss_lut - * @hw: pointer to the hardware structure - * @vsi_id: vsi fw index - * @pf_lut: for PF table set true, for VSI table set false - * @lut: pointer to the lut buffer provided by the caller - * @lut_size: size of the lut buffer - * - * set the RSS lookup table, PF or VSI type - **/ -i40e_status i40evf_aq_set_rss_lut(struct i40e_hw *hw, u16 vsi_id, - bool pf_lut, u8 *lut, u16 lut_size) -{ - return i40e_aq_get_set_rss_lut(hw, vsi_id, pf_lut, lut, lut_size, true); -} - -/** - * i40e_aq_get_set_rss_key - * @hw: pointer to the hw struct - * @vsi_id: vsi fw index - * @key: pointer to key info struct - * @set: set true to set the key, false to get the key - * - * get the RSS key per VSI - **/ -static i40e_status i40e_aq_get_set_rss_key(struct i40e_hw *hw, - u16 vsi_id, - struct i40e_aqc_get_set_rss_key_data *key, - bool set) -{ - i40e_status status; - struct i40e_aq_desc desc; - struct i40e_aqc_get_set_rss_key *cmd_resp = - (struct i40e_aqc_get_set_rss_key *)&desc.params.raw; - u16 key_size = sizeof(struct i40e_aqc_get_set_rss_key_data); - - if (set) - i40evf_fill_default_direct_cmd_desc(&desc, - i40e_aqc_opc_set_rss_key); - else - i40evf_fill_default_direct_cmd_desc(&desc, - i40e_aqc_opc_get_rss_key); - - /* Indirect command */ - desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF); - desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_RD); - - cmd_resp->vsi_id = - cpu_to_le16((u16)((vsi_id << - I40E_AQC_SET_RSS_KEY_VSI_ID_SHIFT) & - I40E_AQC_SET_RSS_KEY_VSI_ID_MASK)); - cmd_resp->vsi_id |= cpu_to_le16((u16)I40E_AQC_SET_RSS_KEY_VSI_VALID); - - status = i40evf_asq_send_command(hw, &desc, key, key_size, NULL); - - return status; -} - -/** - * i40evf_aq_get_rss_key - * @hw: pointer to the hw struct - * @vsi_id: vsi fw index - * @key: pointer to key info struct - * - **/ -i40e_status i40evf_aq_get_rss_key(struct i40e_hw *hw, - u16 vsi_id, - struct i40e_aqc_get_set_rss_key_data *key) -{ - return i40e_aq_get_set_rss_key(hw, vsi_id, key, false); -} - -/** - * i40evf_aq_set_rss_key - * @hw: pointer to the hw struct - * @vsi_id: vsi fw index - * @key: pointer to key info struct - * - * set the RSS key per VSI - **/ -i40e_status i40evf_aq_set_rss_key(struct i40e_hw *hw, - u16 vsi_id, - struct i40e_aqc_get_set_rss_key_data *key) -{ - return i40e_aq_get_set_rss_key(hw, vsi_id, key, true); -} - - -/* The i40evf_ptype_lookup table is used to convert from the 8-bit ptype in the - * hardware to a bit-field that can be used by SW to more easily determine the - * packet type. - * - * Macros are used to shorten the table lines and make this table human - * readable. - * - * We store the PTYPE in the top byte of the bit field - this is just so that - * we can check that the table doesn't have a row missing, as the index into - * the table should be the PTYPE. - * - * Typical work flow: - * - * IF NOT i40evf_ptype_lookup[ptype].known - * THEN - * Packet is unknown - * ELSE IF i40evf_ptype_lookup[ptype].outer_ip == I40E_RX_PTYPE_OUTER_IP - * Use the rest of the fields to look at the tunnels, inner protocols, etc - * ELSE - * Use the enum i40e_rx_l2_ptype to decode the packet type - * ENDIF - */ - -/* macro to make the table lines short */ -#define I40E_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\ - { PTYPE, \ - 1, \ - I40E_RX_PTYPE_OUTER_##OUTER_IP, \ - I40E_RX_PTYPE_OUTER_##OUTER_IP_VER, \ - I40E_RX_PTYPE_##OUTER_FRAG, \ - I40E_RX_PTYPE_TUNNEL_##T, \ - I40E_RX_PTYPE_TUNNEL_END_##TE, \ - I40E_RX_PTYPE_##TEF, \ - I40E_RX_PTYPE_INNER_PROT_##I, \ - I40E_RX_PTYPE_PAYLOAD_LAYER_##PL } - -#define I40E_PTT_UNUSED_ENTRY(PTYPE) \ - { PTYPE, 0, 0, 0, 0, 0, 0, 0, 0, 0 } - -/* shorter macros makes the table fit but are terse */ -#define I40E_RX_PTYPE_NOF I40E_RX_PTYPE_NOT_FRAG -#define I40E_RX_PTYPE_FRG I40E_RX_PTYPE_FRAG -#define I40E_RX_PTYPE_INNER_PROT_TS I40E_RX_PTYPE_INNER_PROT_TIMESYNC - -/* Lookup table mapping the HW PTYPE to the bit field for decoding */ -struct i40e_rx_ptype_decoded i40evf_ptype_lookup[] = { - /* L2 Packet types */ - I40E_PTT_UNUSED_ENTRY(0), - I40E_PTT(1, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), - I40E_PTT(2, L2, NONE, NOF, NONE, NONE, NOF, TS, PAY2), - I40E_PTT(3, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), - I40E_PTT_UNUSED_ENTRY(4), - I40E_PTT_UNUSED_ENTRY(5), - I40E_PTT(6, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), - I40E_PTT(7, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), - I40E_PTT_UNUSED_ENTRY(8), - I40E_PTT_UNUSED_ENTRY(9), - I40E_PTT(10, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), - I40E_PTT(11, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE), - I40E_PTT(12, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(13, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(14, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(15, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(16, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(17, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(18, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(19, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(20, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(21, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - - /* Non Tunneled IPv4 */ - I40E_PTT(22, IP, IPV4, FRG, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(23, IP, IPV4, NOF, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(24, IP, IPV4, NOF, NONE, NONE, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(25), - I40E_PTT(26, IP, IPV4, NOF, NONE, NONE, NOF, TCP, PAY4), - I40E_PTT(27, IP, IPV4, NOF, NONE, NONE, NOF, SCTP, PAY4), - I40E_PTT(28, IP, IPV4, NOF, NONE, NONE, NOF, ICMP, PAY4), - - /* IPv4 --> IPv4 */ - I40E_PTT(29, IP, IPV4, NOF, IP_IP, IPV4, FRG, NONE, PAY3), - I40E_PTT(30, IP, IPV4, NOF, IP_IP, IPV4, NOF, NONE, PAY3), - I40E_PTT(31, IP, IPV4, NOF, IP_IP, IPV4, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(32), - I40E_PTT(33, IP, IPV4, NOF, IP_IP, IPV4, NOF, TCP, PAY4), - I40E_PTT(34, IP, IPV4, NOF, IP_IP, IPV4, NOF, SCTP, PAY4), - I40E_PTT(35, IP, IPV4, NOF, IP_IP, IPV4, NOF, ICMP, PAY4), - - /* IPv4 --> IPv6 */ - I40E_PTT(36, IP, IPV4, NOF, IP_IP, IPV6, FRG, NONE, PAY3), - I40E_PTT(37, IP, IPV4, NOF, IP_IP, IPV6, NOF, NONE, PAY3), - I40E_PTT(38, IP, IPV4, NOF, IP_IP, IPV6, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(39), - I40E_PTT(40, IP, IPV4, NOF, IP_IP, IPV6, NOF, TCP, PAY4), - I40E_PTT(41, IP, IPV4, NOF, IP_IP, IPV6, NOF, SCTP, PAY4), - I40E_PTT(42, IP, IPV4, NOF, IP_IP, IPV6, NOF, ICMP, PAY4), - - /* IPv4 --> GRE/NAT */ - I40E_PTT(43, IP, IPV4, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3), - - /* IPv4 --> GRE/NAT --> IPv4 */ - I40E_PTT(44, IP, IPV4, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3), - I40E_PTT(45, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3), - I40E_PTT(46, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(47), - I40E_PTT(48, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4), - I40E_PTT(49, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4), - I40E_PTT(50, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4), - - /* IPv4 --> GRE/NAT --> IPv6 */ - I40E_PTT(51, IP, IPV4, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3), - I40E_PTT(52, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3), - I40E_PTT(53, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(54), - I40E_PTT(55, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4), - I40E_PTT(56, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4), - I40E_PTT(57, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4), - - /* IPv4 --> GRE/NAT --> MAC */ - I40E_PTT(58, IP, IPV4, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3), - - /* IPv4 --> GRE/NAT --> MAC --> IPv4 */ - I40E_PTT(59, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3), - I40E_PTT(60, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3), - I40E_PTT(61, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(62), - I40E_PTT(63, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4), - I40E_PTT(64, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4), - I40E_PTT(65, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4), - - /* IPv4 --> GRE/NAT -> MAC --> IPv6 */ - I40E_PTT(66, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3), - I40E_PTT(67, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3), - I40E_PTT(68, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(69), - I40E_PTT(70, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4), - I40E_PTT(71, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4), - I40E_PTT(72, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4), - - /* IPv4 --> GRE/NAT --> MAC/VLAN */ - I40E_PTT(73, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3), - - /* IPv4 ---> GRE/NAT -> MAC/VLAN --> IPv4 */ - I40E_PTT(74, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3), - I40E_PTT(75, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3), - I40E_PTT(76, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(77), - I40E_PTT(78, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4), - I40E_PTT(79, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4), - I40E_PTT(80, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4), - - /* IPv4 -> GRE/NAT -> MAC/VLAN --> IPv6 */ - I40E_PTT(81, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3), - I40E_PTT(82, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3), - I40E_PTT(83, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(84), - I40E_PTT(85, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4), - I40E_PTT(86, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4), - I40E_PTT(87, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4), - - /* Non Tunneled IPv6 */ - I40E_PTT(88, IP, IPV6, FRG, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(89, IP, IPV6, NOF, NONE, NONE, NOF, NONE, PAY3), - I40E_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP, PAY3), - I40E_PTT_UNUSED_ENTRY(91), - I40E_PTT(92, IP, IPV6, NOF, NONE, NONE, NOF, TCP, PAY4), - I40E_PTT(93, IP, IPV6, NOF, NONE, NONE, NOF, SCTP, PAY4), - I40E_PTT(94, IP, IPV6, NOF, NONE, NONE, NOF, ICMP, PAY4), - - /* IPv6 --> IPv4 */ - I40E_PTT(95, IP, IPV6, NOF, IP_IP, IPV4, FRG, NONE, PAY3), - I40E_PTT(96, IP, IPV6, NOF, IP_IP, IPV4, NOF, NONE, PAY3), - I40E_PTT(97, IP, IPV6, NOF, IP_IP, IPV4, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(98), - I40E_PTT(99, IP, IPV6, NOF, IP_IP, IPV4, NOF, TCP, PAY4), - I40E_PTT(100, IP, IPV6, NOF, IP_IP, IPV4, NOF, SCTP, PAY4), - I40E_PTT(101, IP, IPV6, NOF, IP_IP, IPV4, NOF, ICMP, PAY4), - - /* IPv6 --> IPv6 */ - I40E_PTT(102, IP, IPV6, NOF, IP_IP, IPV6, FRG, NONE, PAY3), - I40E_PTT(103, IP, IPV6, NOF, IP_IP, IPV6, NOF, NONE, PAY3), - I40E_PTT(104, IP, IPV6, NOF, IP_IP, IPV6, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(105), - I40E_PTT(106, IP, IPV6, NOF, IP_IP, IPV6, NOF, TCP, PAY4), - I40E_PTT(107, IP, IPV6, NOF, IP_IP, IPV6, NOF, SCTP, PAY4), - I40E_PTT(108, IP, IPV6, NOF, IP_IP, IPV6, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT */ - I40E_PTT(109, IP, IPV6, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3), - - /* IPv6 --> GRE/NAT -> IPv4 */ - I40E_PTT(110, IP, IPV6, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3), - I40E_PTT(111, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3), - I40E_PTT(112, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(113), - I40E_PTT(114, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4), - I40E_PTT(115, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4), - I40E_PTT(116, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT -> IPv6 */ - I40E_PTT(117, IP, IPV6, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3), - I40E_PTT(118, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3), - I40E_PTT(119, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(120), - I40E_PTT(121, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4), - I40E_PTT(122, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4), - I40E_PTT(123, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT -> MAC */ - I40E_PTT(124, IP, IPV6, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3), - - /* IPv6 --> GRE/NAT -> MAC -> IPv4 */ - I40E_PTT(125, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3), - I40E_PTT(126, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3), - I40E_PTT(127, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(128), - I40E_PTT(129, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4), - I40E_PTT(130, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4), - I40E_PTT(131, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT -> MAC -> IPv6 */ - I40E_PTT(132, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3), - I40E_PTT(133, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3), - I40E_PTT(134, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(135), - I40E_PTT(136, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4), - I40E_PTT(137, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4), - I40E_PTT(138, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT -> MAC/VLAN */ - I40E_PTT(139, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3), - - /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv4 */ - I40E_PTT(140, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3), - I40E_PTT(141, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3), - I40E_PTT(142, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(143), - I40E_PTT(144, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4), - I40E_PTT(145, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4), - I40E_PTT(146, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv6 */ - I40E_PTT(147, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3), - I40E_PTT(148, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3), - I40E_PTT(149, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4), - I40E_PTT_UNUSED_ENTRY(150), - I40E_PTT(151, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4), - I40E_PTT(152, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4), - I40E_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4), - - /* unused entries */ - I40E_PTT_UNUSED_ENTRY(154), - I40E_PTT_UNUSED_ENTRY(155), - I40E_PTT_UNUSED_ENTRY(156), - I40E_PTT_UNUSED_ENTRY(157), - I40E_PTT_UNUSED_ENTRY(158), - I40E_PTT_UNUSED_ENTRY(159), - - I40E_PTT_UNUSED_ENTRY(160), - I40E_PTT_UNUSED_ENTRY(161), - I40E_PTT_UNUSED_ENTRY(162), - I40E_PTT_UNUSED_ENTRY(163), - I40E_PTT_UNUSED_ENTRY(164), - I40E_PTT_UNUSED_ENTRY(165), - I40E_PTT_UNUSED_ENTRY(166), - I40E_PTT_UNUSED_ENTRY(167), - I40E_PTT_UNUSED_ENTRY(168), - I40E_PTT_UNUSED_ENTRY(169), - - I40E_PTT_UNUSED_ENTRY(170), - I40E_PTT_UNUSED_ENTRY(171), - I40E_PTT_UNUSED_ENTRY(172), - I40E_PTT_UNUSED_ENTRY(173), - I40E_PTT_UNUSED_ENTRY(174), - I40E_PTT_UNUSED_ENTRY(175), - I40E_PTT_UNUSED_ENTRY(176), - I40E_PTT_UNUSED_ENTRY(177), - I40E_PTT_UNUSED_ENTRY(178), - I40E_PTT_UNUSED_ENTRY(179), - - I40E_PTT_UNUSED_ENTRY(180), - I40E_PTT_UNUSED_ENTRY(181), - I40E_PTT_UNUSED_ENTRY(182), - I40E_PTT_UNUSED_ENTRY(183), - I40E_PTT_UNUSED_ENTRY(184), - I40E_PTT_UNUSED_ENTRY(185), - I40E_PTT_UNUSED_ENTRY(186), - I40E_PTT_UNUSED_ENTRY(187), - I40E_PTT_UNUSED_ENTRY(188), - I40E_PTT_UNUSED_ENTRY(189), - - I40E_PTT_UNUSED_ENTRY(190), - I40E_PTT_UNUSED_ENTRY(191), - I40E_PTT_UNUSED_ENTRY(192), - I40E_PTT_UNUSED_ENTRY(193), - I40E_PTT_UNUSED_ENTRY(194), - I40E_PTT_UNUSED_ENTRY(195), - I40E_PTT_UNUSED_ENTRY(196), - I40E_PTT_UNUSED_ENTRY(197), - I40E_PTT_UNUSED_ENTRY(198), - I40E_PTT_UNUSED_ENTRY(199), - - I40E_PTT_UNUSED_ENTRY(200), - I40E_PTT_UNUSED_ENTRY(201), - I40E_PTT_UNUSED_ENTRY(202), - I40E_PTT_UNUSED_ENTRY(203), - I40E_PTT_UNUSED_ENTRY(204), - I40E_PTT_UNUSED_ENTRY(205), - I40E_PTT_UNUSED_ENTRY(206), - I40E_PTT_UNUSED_ENTRY(207), - I40E_PTT_UNUSED_ENTRY(208), - I40E_PTT_UNUSED_ENTRY(209), - - I40E_PTT_UNUSED_ENTRY(210), - I40E_PTT_UNUSED_ENTRY(211), - I40E_PTT_UNUSED_ENTRY(212), - I40E_PTT_UNUSED_ENTRY(213), - I40E_PTT_UNUSED_ENTRY(214), - I40E_PTT_UNUSED_ENTRY(215), - I40E_PTT_UNUSED_ENTRY(216), - I40E_PTT_UNUSED_ENTRY(217), - I40E_PTT_UNUSED_ENTRY(218), - I40E_PTT_UNUSED_ENTRY(219), - - I40E_PTT_UNUSED_ENTRY(220), - I40E_PTT_UNUSED_ENTRY(221), - I40E_PTT_UNUSED_ENTRY(222), - I40E_PTT_UNUSED_ENTRY(223), - I40E_PTT_UNUSED_ENTRY(224), - I40E_PTT_UNUSED_ENTRY(225), - I40E_PTT_UNUSED_ENTRY(226), - I40E_PTT_UNUSED_ENTRY(227), - I40E_PTT_UNUSED_ENTRY(228), - I40E_PTT_UNUSED_ENTRY(229), - - I40E_PTT_UNUSED_ENTRY(230), - I40E_PTT_UNUSED_ENTRY(231), - I40E_PTT_UNUSED_ENTRY(232), - I40E_PTT_UNUSED_ENTRY(233), - I40E_PTT_UNUSED_ENTRY(234), - I40E_PTT_UNUSED_ENTRY(235), - I40E_PTT_UNUSED_ENTRY(236), - I40E_PTT_UNUSED_ENTRY(237), - I40E_PTT_UNUSED_ENTRY(238), - I40E_PTT_UNUSED_ENTRY(239), - - I40E_PTT_UNUSED_ENTRY(240), - I40E_PTT_UNUSED_ENTRY(241), - I40E_PTT_UNUSED_ENTRY(242), - I40E_PTT_UNUSED_ENTRY(243), - I40E_PTT_UNUSED_ENTRY(244), - I40E_PTT_UNUSED_ENTRY(245), - I40E_PTT_UNUSED_ENTRY(246), - I40E_PTT_UNUSED_ENTRY(247), - I40E_PTT_UNUSED_ENTRY(248), - I40E_PTT_UNUSED_ENTRY(249), - - I40E_PTT_UNUSED_ENTRY(250), - I40E_PTT_UNUSED_ENTRY(251), - I40E_PTT_UNUSED_ENTRY(252), - I40E_PTT_UNUSED_ENTRY(253), - I40E_PTT_UNUSED_ENTRY(254), - I40E_PTT_UNUSED_ENTRY(255) -}; - -/** - * i40evf_aq_rx_ctl_read_register - use FW to read from an Rx control register - * @hw: pointer to the hw struct - * @reg_addr: register address - * @reg_val: ptr to register value - * @cmd_details: pointer to command details structure or NULL - * - * Use the firmware to read the Rx control register, - * especially useful if the Rx unit is under heavy pressure - **/ -i40e_status i40evf_aq_rx_ctl_read_register(struct i40e_hw *hw, - u32 reg_addr, u32 *reg_val, - struct i40e_asq_cmd_details *cmd_details) -{ - struct i40e_aq_desc desc; - struct i40e_aqc_rx_ctl_reg_read_write *cmd_resp = - (struct i40e_aqc_rx_ctl_reg_read_write *)&desc.params.raw; - i40e_status status; - - if (!reg_val) - return I40E_ERR_PARAM; - - i40evf_fill_default_direct_cmd_desc(&desc, - i40e_aqc_opc_rx_ctl_reg_read); - - cmd_resp->address = cpu_to_le32(reg_addr); - - status = i40evf_asq_send_command(hw, &desc, NULL, 0, cmd_details); - - if (status == 0) - *reg_val = le32_to_cpu(cmd_resp->value); - - return status; -} - -/** - * i40evf_read_rx_ctl - read from an Rx control register - * @hw: pointer to the hw struct - * @reg_addr: register address - **/ -u32 i40evf_read_rx_ctl(struct i40e_hw *hw, u32 reg_addr) -{ - i40e_status status = 0; - bool use_register; - int retry = 5; - u32 val = 0; - - use_register = (((hw->aq.api_maj_ver == 1) && - (hw->aq.api_min_ver < 5)) || - (hw->mac.type == I40E_MAC_X722)); - if (!use_register) { -do_retry: - status = i40evf_aq_rx_ctl_read_register(hw, reg_addr, - &val, NULL); - if (hw->aq.asq_last_status == I40E_AQ_RC_EAGAIN && retry) { - usleep_range(1000, 2000); - retry--; - goto do_retry; - } - } - - /* if the AQ access failed, try the old-fashioned way */ - if (status || use_register) - val = rd32(hw, reg_addr); - - return val; -} - -/** - * i40evf_aq_rx_ctl_write_register - * @hw: pointer to the hw struct - * @reg_addr: register address - * @reg_val: register value - * @cmd_details: pointer to command details structure or NULL - * - * Use the firmware to write to an Rx control register, - * especially useful if the Rx unit is under heavy pressure - **/ -i40e_status i40evf_aq_rx_ctl_write_register(struct i40e_hw *hw, - u32 reg_addr, u32 reg_val, - struct i40e_asq_cmd_details *cmd_details) -{ - struct i40e_aq_desc desc; - struct i40e_aqc_rx_ctl_reg_read_write *cmd = - (struct i40e_aqc_rx_ctl_reg_read_write *)&desc.params.raw; - i40e_status status; - - i40evf_fill_default_direct_cmd_desc(&desc, - i40e_aqc_opc_rx_ctl_reg_write); - - cmd->address = cpu_to_le32(reg_addr); - cmd->value = cpu_to_le32(reg_val); - - status = i40evf_asq_send_command(hw, &desc, NULL, 0, cmd_details); - - return status; -} - -/** - * i40evf_write_rx_ctl - write to an Rx control register - * @hw: pointer to the hw struct - * @reg_addr: register address - * @reg_val: register value - **/ -void i40evf_write_rx_ctl(struct i40e_hw *hw, u32 reg_addr, u32 reg_val) -{ - i40e_status status = 0; - bool use_register; - int retry = 5; - - use_register = (((hw->aq.api_maj_ver == 1) && - (hw->aq.api_min_ver < 5)) || - (hw->mac.type == I40E_MAC_X722)); - if (!use_register) { -do_retry: - status = i40evf_aq_rx_ctl_write_register(hw, reg_addr, - reg_val, NULL); - if (hw->aq.asq_last_status == I40E_AQ_RC_EAGAIN && retry) { - usleep_range(1000, 2000); - retry--; - goto do_retry; - } - } - - /* if the AQ access failed, try the old-fashioned way */ - if (status || use_register) - wr32(hw, reg_addr, reg_val); -} - -/** - * i40e_aq_send_msg_to_pf - * @hw: pointer to the hardware structure - * @v_opcode: opcodes for VF-PF communication - * @v_retval: return error code - * @msg: pointer to the msg buffer - * @msglen: msg length - * @cmd_details: pointer to command details - * - * Send message to PF driver using admin queue. By default, this message - * is sent asynchronously, i.e. i40evf_asq_send_command() does not wait for - * completion before returning. - **/ -i40e_status i40e_aq_send_msg_to_pf(struct i40e_hw *hw, - enum virtchnl_ops v_opcode, - i40e_status v_retval, - u8 *msg, u16 msglen, - struct i40e_asq_cmd_details *cmd_details) -{ - struct i40e_aq_desc desc; - struct i40e_asq_cmd_details details; - i40e_status status; - - i40evf_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_send_msg_to_pf); - desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_SI); - desc.cookie_high = cpu_to_le32(v_opcode); - desc.cookie_low = cpu_to_le32(v_retval); - if (msglen) { - desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF - | I40E_AQ_FLAG_RD)); - if (msglen > I40E_AQ_LARGE_BUF) - desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB); - desc.datalen = cpu_to_le16(msglen); - } - if (!cmd_details) { - memset(&details, 0, sizeof(details)); - details.async = true; - cmd_details = &details; - } - status = i40evf_asq_send_command(hw, &desc, msg, msglen, cmd_details); - return status; -} - -/** - * i40e_vf_parse_hw_config - * @hw: pointer to the hardware structure - * @msg: pointer to the virtual channel VF resource structure - * - * Given a VF resource message from the PF, populate the hw struct - * with appropriate information. - **/ -void i40e_vf_parse_hw_config(struct i40e_hw *hw, - struct virtchnl_vf_resource *msg) -{ - struct virtchnl_vsi_resource *vsi_res; - int i; - - vsi_res = &msg->vsi_res[0]; - - hw->dev_caps.num_vsis = msg->num_vsis; - hw->dev_caps.num_rx_qp = msg->num_queue_pairs; - hw->dev_caps.num_tx_qp = msg->num_queue_pairs; - hw->dev_caps.num_msix_vectors_vf = msg->max_vectors; - hw->dev_caps.dcb = msg->vf_cap_flags & - VIRTCHNL_VF_OFFLOAD_L2; - hw->dev_caps.fcoe = 0; - for (i = 0; i < msg->num_vsis; i++) { - if (vsi_res->vsi_type == VIRTCHNL_VSI_SRIOV) { - ether_addr_copy(hw->mac.perm_addr, - vsi_res->default_mac_addr); - ether_addr_copy(hw->mac.addr, - vsi_res->default_mac_addr); - } - vsi_res++; - } -} - -/** - * i40e_vf_reset - * @hw: pointer to the hardware structure - * - * Send a VF_RESET message to the PF. Does not wait for response from PF - * as none will be forthcoming. Immediately after calling this function, - * the admin queue should be shut down and (optionally) reinitialized. - **/ -i40e_status i40e_vf_reset(struct i40e_hw *hw) -{ - return i40e_aq_send_msg_to_pf(hw, VIRTCHNL_OP_RESET_VF, - 0, NULL, 0, NULL); -} - -/** - * i40evf_aq_write_ddp - Write dynamic device personalization (ddp) - * @hw: pointer to the hw struct - * @buff: command buffer (size in bytes = buff_size) - * @buff_size: buffer size in bytes - * @track_id: package tracking id - * @error_offset: returns error offset - * @error_info: returns error information - * @cmd_details: pointer to command details structure or NULL - **/ -enum -i40e_status_code i40evf_aq_write_ddp(struct i40e_hw *hw, void *buff, - u16 buff_size, u32 track_id, - u32 *error_offset, u32 *error_info, - struct i40e_asq_cmd_details *cmd_details) -{ - struct i40e_aq_desc desc; - struct i40e_aqc_write_personalization_profile *cmd = - (struct i40e_aqc_write_personalization_profile *) - &desc.params.raw; - struct i40e_aqc_write_ddp_resp *resp; - i40e_status status; - - i40evf_fill_default_direct_cmd_desc(&desc, - i40e_aqc_opc_write_personalization_profile); - - desc.flags |= cpu_to_le16(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD); - if (buff_size > I40E_AQ_LARGE_BUF) - desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB); - - desc.datalen = cpu_to_le16(buff_size); - - cmd->profile_track_id = cpu_to_le32(track_id); - - status = i40evf_asq_send_command(hw, &desc, buff, buff_size, cmd_details); - if (!status) { - resp = (struct i40e_aqc_write_ddp_resp *)&desc.params.raw; - if (error_offset) - *error_offset = le32_to_cpu(resp->error_offset); - if (error_info) - *error_info = le32_to_cpu(resp->error_info); - } - - return status; -} - -/** - * i40evf_aq_get_ddp_list - Read dynamic device personalization (ddp) - * @hw: pointer to the hw struct - * @buff: command buffer (size in bytes = buff_size) - * @buff_size: buffer size in bytes - * @flags: AdminQ command flags - * @cmd_details: pointer to command details structure or NULL - **/ -enum -i40e_status_code i40evf_aq_get_ddp_list(struct i40e_hw *hw, void *buff, - u16 buff_size, u8 flags, - struct i40e_asq_cmd_details *cmd_details) -{ - struct i40e_aq_desc desc; - struct i40e_aqc_get_applied_profiles *cmd = - (struct i40e_aqc_get_applied_profiles *)&desc.params.raw; - i40e_status status; - - i40evf_fill_default_direct_cmd_desc(&desc, - i40e_aqc_opc_get_personalization_profile_list); - - desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF); - if (buff_size > I40E_AQ_LARGE_BUF) - desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB); - desc.datalen = cpu_to_le16(buff_size); - - cmd->flags = flags; - - status = i40evf_asq_send_command(hw, &desc, buff, buff_size, cmd_details); - - return status; -} - -/** - * i40evf_find_segment_in_package - * @segment_type: the segment type to search for (i.e., SEGMENT_TYPE_I40E) - * @pkg_hdr: pointer to the package header to be searched - * - * This function searches a package file for a particular segment type. On - * success it returns a pointer to the segment header, otherwise it will - * return NULL. - **/ -struct i40e_generic_seg_header * -i40evf_find_segment_in_package(u32 segment_type, - struct i40e_package_header *pkg_hdr) -{ - struct i40e_generic_seg_header *segment; - u32 i; - - /* Search all package segments for the requested segment type */ - for (i = 0; i < pkg_hdr->segment_count; i++) { - segment = - (struct i40e_generic_seg_header *)((u8 *)pkg_hdr + - pkg_hdr->segment_offset[i]); - - if (segment->type == segment_type) - return segment; - } - - return NULL; -} - -/** - * i40evf_write_profile - * @hw: pointer to the hardware structure - * @profile: pointer to the profile segment of the package to be downloaded - * @track_id: package tracking id - * - * Handles the download of a complete package. - */ -enum i40e_status_code -i40evf_write_profile(struct i40e_hw *hw, struct i40e_profile_segment *profile, - u32 track_id) -{ - i40e_status status = 0; - struct i40e_section_table *sec_tbl; - struct i40e_profile_section_header *sec = NULL; - u32 dev_cnt; - u32 vendor_dev_id; - u32 *nvm; - u32 section_size = 0; - u32 offset = 0, info = 0; - u32 i; - - dev_cnt = profile->device_table_count; - - for (i = 0; i < dev_cnt; i++) { - vendor_dev_id = profile->device_table[i].vendor_dev_id; - if ((vendor_dev_id >> 16) == PCI_VENDOR_ID_INTEL) - if (hw->device_id == (vendor_dev_id & 0xFFFF)) - break; - } - if (i == dev_cnt) { - i40e_debug(hw, I40E_DEBUG_PACKAGE, "Device doesn't support DDP"); - return I40E_ERR_DEVICE_NOT_SUPPORTED; - } - - nvm = (u32 *)&profile->device_table[dev_cnt]; - sec_tbl = (struct i40e_section_table *)&nvm[nvm[0] + 1]; - - for (i = 0; i < sec_tbl->section_count; i++) { - sec = (struct i40e_profile_section_header *)((u8 *)profile + - sec_tbl->section_offset[i]); - - /* Skip 'AQ', 'note' and 'name' sections */ - if (sec->section.type != SECTION_TYPE_MMIO) - continue; - - section_size = sec->section.size + - sizeof(struct i40e_profile_section_header); - - /* Write profile */ - status = i40evf_aq_write_ddp(hw, (void *)sec, (u16)section_size, - track_id, &offset, &info, NULL); - if (status) { - i40e_debug(hw, I40E_DEBUG_PACKAGE, - "Failed to write profile: offset %d, info %d", - offset, info); - break; - } - } - return status; -} - -/** - * i40evf_add_pinfo_to_list - * @hw: pointer to the hardware structure - * @profile: pointer to the profile segment of the package - * @profile_info_sec: buffer for information section - * @track_id: package tracking id - * - * Register a profile to the list of loaded profiles. - */ -enum i40e_status_code -i40evf_add_pinfo_to_list(struct i40e_hw *hw, - struct i40e_profile_segment *profile, - u8 *profile_info_sec, u32 track_id) -{ - i40e_status status = 0; - struct i40e_profile_section_header *sec = NULL; - struct i40e_profile_info *pinfo; - u32 offset = 0, info = 0; - - sec = (struct i40e_profile_section_header *)profile_info_sec; - sec->tbl_size = 1; - sec->data_end = sizeof(struct i40e_profile_section_header) + - sizeof(struct i40e_profile_info); - sec->section.type = SECTION_TYPE_INFO; - sec->section.offset = sizeof(struct i40e_profile_section_header); - sec->section.size = sizeof(struct i40e_profile_info); - pinfo = (struct i40e_profile_info *)(profile_info_sec + - sec->section.offset); - pinfo->track_id = track_id; - pinfo->version = profile->version; - pinfo->op = I40E_DDP_ADD_TRACKID; - memcpy(pinfo->name, profile->name, I40E_DDP_NAME_SIZE); - - status = i40evf_aq_write_ddp(hw, (void *)sec, sec->data_end, - track_id, &offset, &info, NULL); - return status; -} diff --git a/drivers/net/ethernet/intel/i40evf/i40e_devids.h b/drivers/net/ethernet/intel/i40evf/i40e_devids.h deleted file mode 100644 index f300bf271824..000000000000 --- a/drivers/net/ethernet/intel/i40evf/i40e_devids.h +++ /dev/null @@ -1,34 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 2013 - 2018 Intel Corporation. */ - -#ifndef _I40E_DEVIDS_H_ -#define _I40E_DEVIDS_H_ - -/* Device IDs */ -#define I40E_DEV_ID_SFP_XL710 0x1572 -#define I40E_DEV_ID_QEMU 0x1574 -#define I40E_DEV_ID_KX_B 0x1580 -#define I40E_DEV_ID_KX_C 0x1581 -#define I40E_DEV_ID_QSFP_A 0x1583 -#define I40E_DEV_ID_QSFP_B 0x1584 -#define I40E_DEV_ID_QSFP_C 0x1585 -#define I40E_DEV_ID_10G_BASE_T 0x1586 -#define I40E_DEV_ID_20G_KR2 0x1587 -#define I40E_DEV_ID_20G_KR2_A 0x1588 -#define I40E_DEV_ID_10G_BASE_T4 0x1589 -#define I40E_DEV_ID_25G_B 0x158A -#define I40E_DEV_ID_25G_SFP28 0x158B -#define I40E_DEV_ID_VF 0x154C -#define I40E_DEV_ID_VF_HV 0x1571 -#define I40E_DEV_ID_ADAPTIVE_VF 0x1889 -#define I40E_DEV_ID_SFP_X722 0x37D0 -#define I40E_DEV_ID_1G_BASE_T_X722 0x37D1 -#define I40E_DEV_ID_10G_BASE_T_X722 0x37D2 -#define I40E_DEV_ID_SFP_I_X722 0x37D3 -#define I40E_DEV_ID_X722_VF 0x37CD - -#define i40e_is_40G_device(d) ((d) == I40E_DEV_ID_QSFP_A || \ - (d) == I40E_DEV_ID_QSFP_B || \ - (d) == I40E_DEV_ID_QSFP_C) - -#endif /* _I40E_DEVIDS_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_hmc.h b/drivers/net/ethernet/intel/i40evf/i40e_hmc.h deleted file mode 100644 index 1c78de838857..000000000000 --- a/drivers/net/ethernet/intel/i40evf/i40e_hmc.h +++ /dev/null @@ -1,215 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 2013 - 2018 Intel Corporation. */ - -#ifndef _I40E_HMC_H_ -#define _I40E_HMC_H_ - -#define I40E_HMC_MAX_BP_COUNT 512 - -/* forward-declare the HW struct for the compiler */ -struct i40e_hw; - -#define I40E_HMC_INFO_SIGNATURE 0x484D5347 /* HMSG */ -#define I40E_HMC_PD_CNT_IN_SD 512 -#define I40E_HMC_DIRECT_BP_SIZE 0x200000 /* 2M */ -#define I40E_HMC_PAGED_BP_SIZE 4096 -#define I40E_HMC_PD_BP_BUF_ALIGNMENT 4096 -#define I40E_FIRST_VF_FPM_ID 16 - -struct i40e_hmc_obj_info { - u64 base; /* base addr in FPM */ - u32 max_cnt; /* max count available for this hmc func */ - u32 cnt; /* count of objects driver actually wants to create */ - u64 size; /* size in bytes of one object */ -}; - -enum i40e_sd_entry_type { - I40E_SD_TYPE_INVALID = 0, - I40E_SD_TYPE_PAGED = 1, - I40E_SD_TYPE_DIRECT = 2 -}; - -struct i40e_hmc_bp { - enum i40e_sd_entry_type entry_type; - struct i40e_dma_mem addr; /* populate to be used by hw */ - u32 sd_pd_index; - u32 ref_cnt; -}; - -struct i40e_hmc_pd_entry { - struct i40e_hmc_bp bp; - u32 sd_index; - bool rsrc_pg; - bool valid; -}; - -struct i40e_hmc_pd_table { - struct i40e_dma_mem pd_page_addr; /* populate to be used by hw */ - struct i40e_hmc_pd_entry *pd_entry; /* [512] for sw book keeping */ - struct i40e_virt_mem pd_entry_virt_mem; /* virt mem for pd_entry */ - - u32 ref_cnt; - u32 sd_index; -}; - -struct i40e_hmc_sd_entry { - enum i40e_sd_entry_type entry_type; - bool valid; - - union { - struct i40e_hmc_pd_table pd_table; - struct i40e_hmc_bp bp; - } u; -}; - -struct i40e_hmc_sd_table { - struct i40e_virt_mem addr; /* used to track sd_entry allocations */ - u32 sd_cnt; - u32 ref_cnt; - struct i40e_hmc_sd_entry *sd_entry; /* (sd_cnt*512) entries max */ -}; - -struct i40e_hmc_info { - u32 signature; - /* equals to pci func num for PF and dynamically allocated for VFs */ - u8 hmc_fn_id; - u16 first_sd_index; /* index of the first available SD */ - - /* hmc objects */ - struct i40e_hmc_obj_info *hmc_obj; - struct i40e_virt_mem hmc_obj_virt_mem; - struct i40e_hmc_sd_table sd_table; -}; - -#define I40E_INC_SD_REFCNT(sd_table) ((sd_table)->ref_cnt++) -#define I40E_INC_PD_REFCNT(pd_table) ((pd_table)->ref_cnt++) -#define I40E_INC_BP_REFCNT(bp) ((bp)->ref_cnt++) - -#define I40E_DEC_SD_REFCNT(sd_table) ((sd_table)->ref_cnt--) -#define I40E_DEC_PD_REFCNT(pd_table) ((pd_table)->ref_cnt--) -#define I40E_DEC_BP_REFCNT(bp) ((bp)->ref_cnt--) - -/** - * I40E_SET_PF_SD_ENTRY - marks the sd entry as valid in the hardware - * @hw: pointer to our hw struct - * @pa: pointer to physical address - * @sd_index: segment descriptor index - * @type: if sd entry is direct or paged - **/ -#define I40E_SET_PF_SD_ENTRY(hw, pa, sd_index, type) \ -{ \ - u32 val1, val2, val3; \ - val1 = (u32)(upper_32_bits(pa)); \ - val2 = (u32)(pa) | (I40E_HMC_MAX_BP_COUNT << \ - I40E_PFHMC_SDDATALOW_PMSDBPCOUNT_SHIFT) | \ - ((((type) == I40E_SD_TYPE_PAGED) ? 0 : 1) << \ - I40E_PFHMC_SDDATALOW_PMSDTYPE_SHIFT) | \ - BIT(I40E_PFHMC_SDDATALOW_PMSDVALID_SHIFT); \ - val3 = (sd_index) | BIT_ULL(I40E_PFHMC_SDCMD_PMSDWR_SHIFT); \ - wr32((hw), I40E_PFHMC_SDDATAHIGH, val1); \ - wr32((hw), I40E_PFHMC_SDDATALOW, val2); \ - wr32((hw), I40E_PFHMC_SDCMD, val3); \ -} - -/** - * I40E_CLEAR_PF_SD_ENTRY - marks the sd entry as invalid in the hardware - * @hw: pointer to our hw struct - * @sd_index: segment descriptor index - * @type: if sd entry is direct or paged - **/ -#define I40E_CLEAR_PF_SD_ENTRY(hw, sd_index, type) \ -{ \ - u32 val2, val3; \ - val2 = (I40E_HMC_MAX_BP_COUNT << \ - I40E_PFHMC_SDDATALOW_PMSDBPCOUNT_SHIFT) | \ - ((((type) == I40E_SD_TYPE_PAGED) ? 0 : 1) << \ - I40E_PFHMC_SDDATALOW_PMSDTYPE_SHIFT); \ - val3 = (sd_index) | BIT_ULL(I40E_PFHMC_SDCMD_PMSDWR_SHIFT); \ - wr32((hw), I40E_PFHMC_SDDATAHIGH, 0); \ - wr32((hw), I40E_PFHMC_SDDATALOW, val2); \ - wr32((hw), I40E_PFHMC_SDCMD, val3); \ -} - -/** - * I40E_INVALIDATE_PF_HMC_PD - Invalidates the pd cache in the hardware - * @hw: pointer to our hw struct - * @sd_idx: segment descriptor index - * @pd_idx: page descriptor index - **/ -#define I40E_INVALIDATE_PF_HMC_PD(hw, sd_idx, pd_idx) \ - wr32((hw), I40E_PFHMC_PDINV, \ - (((sd_idx) << I40E_PFHMC_PDINV_PMSDIDX_SHIFT) | \ - ((pd_idx) << I40E_PFHMC_PDINV_PMPDIDX_SHIFT))) - -/** - * I40E_FIND_SD_INDEX_LIMIT - finds segment descriptor index limit - * @hmc_info: pointer to the HMC configuration information structure - * @type: type of HMC resources we're searching - * @index: starting index for the object - * @cnt: number of objects we're trying to create - * @sd_idx: pointer to return index of the segment descriptor in question - * @sd_limit: pointer to return the maximum number of segment descriptors - * - * This function calculates the segment descriptor index and index limit - * for the resource defined by i40e_hmc_rsrc_type. - **/ -#define I40E_FIND_SD_INDEX_LIMIT(hmc_info, type, index, cnt, sd_idx, sd_limit)\ -{ \ - u64 fpm_addr, fpm_limit; \ - fpm_addr = (hmc_info)->hmc_obj[(type)].base + \ - (hmc_info)->hmc_obj[(type)].size * (index); \ - fpm_limit = fpm_addr + (hmc_info)->hmc_obj[(type)].size * (cnt);\ - *(sd_idx) = (u32)(fpm_addr / I40E_HMC_DIRECT_BP_SIZE); \ - *(sd_limit) = (u32)((fpm_limit - 1) / I40E_HMC_DIRECT_BP_SIZE); \ - /* add one more to the limit to correct our range */ \ - *(sd_limit) += 1; \ -} - -/** - * I40E_FIND_PD_INDEX_LIMIT - finds page descriptor index limit - * @hmc_info: pointer to the HMC configuration information struct - * @type: HMC resource type we're examining - * @idx: starting index for the object - * @cnt: number of objects we're trying to create - * @pd_index: pointer to return page descriptor index - * @pd_limit: pointer to return page descriptor index limit - * - * Calculates the page descriptor index and index limit for the resource - * defined by i40e_hmc_rsrc_type. - **/ -#define I40E_FIND_PD_INDEX_LIMIT(hmc_info, type, idx, cnt, pd_index, pd_limit)\ -{ \ - u64 fpm_adr, fpm_limit; \ - fpm_adr = (hmc_info)->hmc_obj[(type)].base + \ - (hmc_info)->hmc_obj[(type)].size * (idx); \ - fpm_limit = fpm_adr + (hmc_info)->hmc_obj[(type)].size * (cnt); \ - *(pd_index) = (u32)(fpm_adr / I40E_HMC_PAGED_BP_SIZE); \ - *(pd_limit) = (u32)((fpm_limit - 1) / I40E_HMC_PAGED_BP_SIZE); \ - /* add one more to the limit to correct our range */ \ - *(pd_limit) += 1; \ -} -i40e_status i40e_add_sd_table_entry(struct i40e_hw *hw, - struct i40e_hmc_info *hmc_info, - u32 sd_index, - enum i40e_sd_entry_type type, - u64 direct_mode_sz); - -i40e_status i40e_add_pd_table_entry(struct i40e_hw *hw, - struct i40e_hmc_info *hmc_info, - u32 pd_index, - struct i40e_dma_mem *rsrc_pg); -i40e_status i40e_remove_pd_bp(struct i40e_hw *hw, - struct i40e_hmc_info *hmc_info, - u32 idx); -i40e_status i40e_prep_remove_sd_bp(struct i40e_hmc_info *hmc_info, - u32 idx); -i40e_status i40e_remove_sd_bp_new(struct i40e_hw *hw, - struct i40e_hmc_info *hmc_info, - u32 idx, bool is_pf); -i40e_status i40e_prep_remove_pd_page(struct i40e_hmc_info *hmc_info, - u32 idx); -i40e_status i40e_remove_pd_page_new(struct i40e_hw *hw, - struct i40e_hmc_info *hmc_info, - u32 idx, bool is_pf); - -#endif /* _I40E_HMC_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_lan_hmc.h b/drivers/net/ethernet/intel/i40evf/i40e_lan_hmc.h deleted file mode 100644 index 82b00f70a632..000000000000 --- a/drivers/net/ethernet/intel/i40evf/i40e_lan_hmc.h +++ /dev/null @@ -1,158 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 2013 - 2018 Intel Corporation. */ - -#ifndef _I40E_LAN_HMC_H_ -#define _I40E_LAN_HMC_H_ - -/* forward-declare the HW struct for the compiler */ -struct i40e_hw; - -/* HMC element context information */ - -/* Rx queue context data - * - * The sizes of the variables may be larger than needed due to crossing byte - * boundaries. If we do not have the width of the variable set to the correct - * size then we could end up shifting bits off the top of the variable when the - * variable is at the top of a byte and crosses over into the next byte. - */ -struct i40e_hmc_obj_rxq { - u16 head; - u16 cpuid; /* bigger than needed, see above for reason */ - u64 base; - u16 qlen; -#define I40E_RXQ_CTX_DBUFF_SHIFT 7 - u16 dbuff; /* bigger than needed, see above for reason */ -#define I40E_RXQ_CTX_HBUFF_SHIFT 6 - u16 hbuff; /* bigger than needed, see above for reason */ - u8 dtype; - u8 dsize; - u8 crcstrip; - u8 fc_ena; - u8 l2tsel; - u8 hsplit_0; - u8 hsplit_1; - u8 showiv; - u32 rxmax; /* bigger than needed, see above for reason */ - u8 tphrdesc_ena; - u8 tphwdesc_ena; - u8 tphdata_ena; - u8 tphhead_ena; - u16 lrxqthresh; /* bigger than needed, see above for reason */ - u8 prefena; /* NOTE: normally must be set to 1 at init */ -}; - -/* Tx queue context data -* -* The sizes of the variables may be larger than needed due to crossing byte -* boundaries. If we do not have the width of the variable set to the correct -* size then we could end up shifting bits off the top of the variable when the -* variable is at the top of a byte and crosses over into the next byte. -*/ -struct i40e_hmc_obj_txq { - u16 head; - u8 new_context; - u64 base; - u8 fc_ena; - u8 timesync_ena; - u8 fd_ena; - u8 alt_vlan_ena; - u16 thead_wb; - u8 cpuid; - u8 head_wb_ena; - u16 qlen; - u8 tphrdesc_ena; - u8 tphrpacket_ena; - u8 tphwdesc_ena; - u64 head_wb_addr; - u32 crc; - u16 rdylist; - u8 rdylist_act; -}; - -/* for hsplit_0 field of Rx HMC context */ -enum i40e_hmc_obj_rx_hsplit_0 { - I40E_HMC_OBJ_RX_HSPLIT_0_NO_SPLIT = 0, - I40E_HMC_OBJ_RX_HSPLIT_0_SPLIT_L2 = 1, - I40E_HMC_OBJ_RX_HSPLIT_0_SPLIT_IP = 2, - I40E_HMC_OBJ_RX_HSPLIT_0_SPLIT_TCP_UDP = 4, - I40E_HMC_OBJ_RX_HSPLIT_0_SPLIT_SCTP = 8, -}; - -/* fcoe_cntx and fcoe_filt are for debugging purpose only */ -struct i40e_hmc_obj_fcoe_cntx { - u32 rsv[32]; -}; - -struct i40e_hmc_obj_fcoe_filt { - u32 rsv[8]; -}; - -/* Context sizes for LAN objects */ -enum i40e_hmc_lan_object_size { - I40E_HMC_LAN_OBJ_SZ_8 = 0x3, - I40E_HMC_LAN_OBJ_SZ_16 = 0x4, - I40E_HMC_LAN_OBJ_SZ_32 = 0x5, - I40E_HMC_LAN_OBJ_SZ_64 = 0x6, - I40E_HMC_LAN_OBJ_SZ_128 = 0x7, - I40E_HMC_LAN_OBJ_SZ_256 = 0x8, - I40E_HMC_LAN_OBJ_SZ_512 = 0x9, -}; - -#define I40E_HMC_L2OBJ_BASE_ALIGNMENT 512 -#define I40E_HMC_OBJ_SIZE_TXQ 128 -#define I40E_HMC_OBJ_SIZE_RXQ 32 -#define I40E_HMC_OBJ_SIZE_FCOE_CNTX 128 -#define I40E_HMC_OBJ_SIZE_FCOE_FILT 64 - -enum i40e_hmc_lan_rsrc_type { - I40E_HMC_LAN_FULL = 0, - I40E_HMC_LAN_TX = 1, - I40E_HMC_LAN_RX = 2, - I40E_HMC_FCOE_CTX = 3, - I40E_HMC_FCOE_FILT = 4, - I40E_HMC_LAN_MAX = 5 -}; - -enum i40e_hmc_model { - I40E_HMC_MODEL_DIRECT_PREFERRED = 0, - I40E_HMC_MODEL_DIRECT_ONLY = 1, - I40E_HMC_MODEL_PAGED_ONLY = 2, - I40E_HMC_MODEL_UNKNOWN, -}; - -struct i40e_hmc_lan_create_obj_info { - struct i40e_hmc_info *hmc_info; - u32 rsrc_type; - u32 start_idx; - u32 count; - enum i40e_sd_entry_type entry_type; - u64 direct_mode_sz; -}; - -struct i40e_hmc_lan_delete_obj_info { - struct i40e_hmc_info *hmc_info; - u32 rsrc_type; - u32 start_idx; - u32 count; -}; - -i40e_status i40e_init_lan_hmc(struct i40e_hw *hw, u32 txq_num, - u32 rxq_num, u32 fcoe_cntx_num, - u32 fcoe_filt_num); -i40e_status i40e_configure_lan_hmc(struct i40e_hw *hw, - enum i40e_hmc_model model); -i40e_status i40e_shutdown_lan_hmc(struct i40e_hw *hw); - -i40e_status i40e_clear_lan_tx_queue_context(struct i40e_hw *hw, - u16 queue); -i40e_status i40e_set_lan_tx_queue_context(struct i40e_hw *hw, - u16 queue, - struct i40e_hmc_obj_txq *s); -i40e_status i40e_clear_lan_rx_queue_context(struct i40e_hw *hw, - u16 queue); -i40e_status i40e_set_lan_rx_queue_context(struct i40e_hw *hw, - u16 queue, - struct i40e_hmc_obj_rxq *s); - -#endif /* _I40E_LAN_HMC_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h deleted file mode 100644 index a358f4b9d5aa..000000000000 --- a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h +++ /dev/null @@ -1,130 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 2013 - 2018 Intel Corporation. */ - -#ifndef _I40E_PROTOTYPE_H_ -#define _I40E_PROTOTYPE_H_ - -#include "i40e_type.h" -#include "i40e_alloc.h" -#include <linux/avf/virtchnl.h> - -/* Prototypes for shared code functions that are not in - * the standard function pointer structures. These are - * mostly because they are needed even before the init - * has happened and will assist in the early SW and FW - * setup. - */ - -/* adminq functions */ -i40e_status i40evf_init_adminq(struct i40e_hw *hw); -i40e_status i40evf_shutdown_adminq(struct i40e_hw *hw); -void i40e_adminq_init_ring_data(struct i40e_hw *hw); -i40e_status i40evf_clean_arq_element(struct i40e_hw *hw, - struct i40e_arq_event_info *e, - u16 *events_pending); -i40e_status i40evf_asq_send_command(struct i40e_hw *hw, - struct i40e_aq_desc *desc, - void *buff, /* can be NULL */ - u16 buff_size, - struct i40e_asq_cmd_details *cmd_details); -bool i40evf_asq_done(struct i40e_hw *hw); - -/* debug function for adminq */ -void i40evf_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask, - void *desc, void *buffer, u16 buf_len); - -void i40e_idle_aq(struct i40e_hw *hw); -void i40evf_resume_aq(struct i40e_hw *hw); -bool i40evf_check_asq_alive(struct i40e_hw *hw); -i40e_status i40evf_aq_queue_shutdown(struct i40e_hw *hw, bool unloading); -const char *i40evf_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err); -const char *i40evf_stat_str(struct i40e_hw *hw, i40e_status stat_err); - -i40e_status i40evf_aq_get_rss_lut(struct i40e_hw *hw, u16 seid, - bool pf_lut, u8 *lut, u16 lut_size); -i40e_status i40evf_aq_set_rss_lut(struct i40e_hw *hw, u16 seid, - bool pf_lut, u8 *lut, u16 lut_size); -i40e_status i40evf_aq_get_rss_key(struct i40e_hw *hw, - u16 seid, - struct i40e_aqc_get_set_rss_key_data *key); -i40e_status i40evf_aq_set_rss_key(struct i40e_hw *hw, - u16 seid, - struct i40e_aqc_get_set_rss_key_data *key); - -i40e_status i40e_set_mac_type(struct i40e_hw *hw); - -extern struct i40e_rx_ptype_decoded i40evf_ptype_lookup[]; - -static inline struct i40e_rx_ptype_decoded decode_rx_desc_ptype(u8 ptype) -{ - return i40evf_ptype_lookup[ptype]; -} - -/* prototype for functions used for SW locks */ - -/* i40e_common for VF drivers*/ -void i40e_vf_parse_hw_config(struct i40e_hw *hw, - struct virtchnl_vf_resource *msg); -i40e_status i40e_vf_reset(struct i40e_hw *hw); -i40e_status i40e_aq_send_msg_to_pf(struct i40e_hw *hw, - enum virtchnl_ops v_opcode, - i40e_status v_retval, - u8 *msg, u16 msglen, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_set_filter_control(struct i40e_hw *hw, - struct i40e_filter_control_settings *settings); -i40e_status i40e_aq_add_rem_control_packet_filter(struct i40e_hw *hw, - u8 *mac_addr, u16 ethtype, u16 flags, - u16 vsi_seid, u16 queue, bool is_add, - struct i40e_control_filter_stats *stats, - struct i40e_asq_cmd_details *cmd_details); -void i40e_add_filter_to_drop_tx_flow_control_frames(struct i40e_hw *hw, - u16 vsi_seid); -i40e_status i40evf_aq_rx_ctl_read_register(struct i40e_hw *hw, - u32 reg_addr, u32 *reg_val, - struct i40e_asq_cmd_details *cmd_details); -u32 i40evf_read_rx_ctl(struct i40e_hw *hw, u32 reg_addr); -i40e_status i40evf_aq_rx_ctl_write_register(struct i40e_hw *hw, - u32 reg_addr, u32 reg_val, - struct i40e_asq_cmd_details *cmd_details); -void i40evf_write_rx_ctl(struct i40e_hw *hw, u32 reg_addr, u32 reg_val); -i40e_status i40e_aq_set_phy_register(struct i40e_hw *hw, - u8 phy_select, u8 dev_addr, - u32 reg_addr, u32 reg_val, - struct i40e_asq_cmd_details *cmd_details); -i40e_status i40e_aq_get_phy_register(struct i40e_hw *hw, - u8 phy_select, u8 dev_addr, - u32 reg_addr, u32 *reg_val, - struct i40e_asq_cmd_details *cmd_details); - -i40e_status i40e_read_phy_register(struct i40e_hw *hw, u8 page, - u16 reg, u8 phy_addr, u16 *value); -i40e_status i40e_write_phy_register(struct i40e_hw *hw, u8 page, - u16 reg, u8 phy_addr, u16 value); -i40e_status i40e_read_phy_register(struct i40e_hw *hw, u8 page, u16 reg, - u8 phy_addr, u16 *value); -i40e_status i40e_write_phy_register(struct i40e_hw *hw, u8 page, u16 reg, - u8 phy_addr, u16 value); -u8 i40e_get_phy_address(struct i40e_hw *hw, u8 dev_num); -i40e_status i40e_blink_phy_link_led(struct i40e_hw *hw, - u32 time, u32 interval); -i40e_status i40evf_aq_write_ddp(struct i40e_hw *hw, void *buff, - u16 buff_size, u32 track_id, - u32 *error_offset, u32 *error_info, - struct i40e_asq_cmd_details * - cmd_details); -i40e_status i40evf_aq_get_ddp_list(struct i40e_hw *hw, void *buff, - u16 buff_size, u8 flags, - struct i40e_asq_cmd_details * - cmd_details); -struct i40e_generic_seg_header * -i40evf_find_segment_in_package(u32 segment_type, - struct i40e_package_header *pkg_header); -enum i40e_status_code -i40evf_write_profile(struct i40e_hw *hw, struct i40e_profile_segment *i40e_seg, - u32 track_id); -enum i40e_status_code -i40evf_add_pinfo_to_list(struct i40e_hw *hw, - struct i40e_profile_segment *profile, - u8 *profile_info_sec, u32 track_id); -#endif /* _I40E_PROTOTYPE_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_register.h b/drivers/net/ethernet/intel/i40evf/i40e_register.h deleted file mode 100644 index 49e1f57d99cc..000000000000 --- a/drivers/net/ethernet/intel/i40evf/i40e_register.h +++ /dev/null @@ -1,313 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 2013 - 2018 Intel Corporation. */ - -#ifndef _I40E_REGISTER_H_ -#define _I40E_REGISTER_H_ - -#define I40E_VFMSIX_PBA1(_i) (0x00002000 + ((_i) * 4)) /* _i=0...19 */ /* Reset: VFLR */ -#define I40E_VFMSIX_PBA1_MAX_INDEX 19 -#define I40E_VFMSIX_PBA1_PENBIT_SHIFT 0 -#define I40E_VFMSIX_PBA1_PENBIT_MASK I40E_MASK(0xFFFFFFFF, I40E_VFMSIX_PBA1_PENBIT_SHIFT) -#define I40E_VFMSIX_TADD1(_i) (0x00002100 + ((_i) * 16)) /* _i=0...639 */ /* Reset: VFLR */ -#define I40E_VFMSIX_TADD1_MAX_INDEX 639 -#define I40E_VFMSIX_TADD1_MSIXTADD10_SHIFT 0 -#define I40E_VFMSIX_TADD1_MSIXTADD10_MASK I40E_MASK(0x3, I40E_VFMSIX_TADD1_MSIXTADD10_SHIFT) -#define I40E_VFMSIX_TADD1_MSIXTADD_SHIFT 2 -#define I40E_VFMSIX_TADD1_MSIXTADD_MASK I40E_MASK(0x3FFFFFFF, I40E_VFMSIX_TADD1_MSIXTADD_SHIFT) -#define I40E_VFMSIX_TMSG1(_i) (0x00002108 + ((_i) * 16)) /* _i=0...639 */ /* Reset: VFLR */ -#define I40E_VFMSIX_TMSG1_MAX_INDEX 639 -#define I40E_VFMSIX_TMSG1_MSIXTMSG_SHIFT 0 -#define I40E_VFMSIX_TMSG1_MSIXTMSG_MASK I40E_MASK(0xFFFFFFFF, I40E_VFMSIX_TMSG1_MSIXTMSG_SHIFT) -#define I40E_VFMSIX_TUADD1(_i) (0x00002104 + ((_i) * 16)) /* _i=0...639 */ /* Reset: VFLR */ -#define I40E_VFMSIX_TUADD1_MAX_INDEX 639 -#define I40E_VFMSIX_TUADD1_MSIXTUADD_SHIFT 0 -#define I40E_VFMSIX_TUADD1_MSIXTUADD_MASK I40E_MASK(0xFFFFFFFF, I40E_VFMSIX_TUADD1_MSIXTUADD_SHIFT) -#define I40E_VFMSIX_TVCTRL1(_i) (0x0000210C + ((_i) * 16)) /* _i=0...639 */ /* Reset: VFLR */ -#define I40E_VFMSIX_TVCTRL1_MAX_INDEX 639 -#define I40E_VFMSIX_TVCTRL1_MASK_SHIFT 0 -#define I40E_VFMSIX_TVCTRL1_MASK_MASK I40E_MASK(0x1, I40E_VFMSIX_TVCTRL1_MASK_SHIFT) -#define I40E_VF_ARQBAH1 0x00006000 /* Reset: EMPR */ -#define I40E_VF_ARQBAH1_ARQBAH_SHIFT 0 -#define I40E_VF_ARQBAH1_ARQBAH_MASK I40E_MASK(0xFFFFFFFF, I40E_VF_ARQBAH1_ARQBAH_SHIFT) -#define I40E_VF_ARQBAL1 0x00006C00 /* Reset: EMPR */ -#define I40E_VF_ARQBAL1_ARQBAL_SHIFT 0 -#define I40E_VF_ARQBAL1_ARQBAL_MASK I40E_MASK(0xFFFFFFFF, I40E_VF_ARQBAL1_ARQBAL_SHIFT) -#define I40E_VF_ARQH1 0x00007400 /* Reset: EMPR */ -#define I40E_VF_ARQH1_ARQH_SHIFT 0 -#define I40E_VF_ARQH1_ARQH_MASK I40E_MASK(0x3FF, I40E_VF_ARQH1_ARQH_SHIFT) -#define I40E_VF_ARQLEN1 0x00008000 /* Reset: EMPR */ -#define I40E_VF_ARQLEN1_ARQLEN_SHIFT 0 -#define I40E_VF_ARQLEN1_ARQLEN_MASK I40E_MASK(0x3FF, I40E_VF_ARQLEN1_ARQLEN_SHIFT) -#define I40E_VF_ARQLEN1_ARQVFE_SHIFT 28 -#define I40E_VF_ARQLEN1_ARQVFE_MASK I40E_MASK(0x1, I40E_VF_ARQLEN1_ARQVFE_SHIFT) -#define I40E_VF_ARQLEN1_ARQOVFL_SHIFT 29 -#define I40E_VF_ARQLEN1_ARQOVFL_MASK I40E_MASK(0x1, I40E_VF_ARQLEN1_ARQOVFL_SHIFT) -#define I40E_VF_ARQLEN1_ARQCRIT_SHIFT 30 -#define I40E_VF_ARQLEN1_ARQCRIT_MASK I40E_MASK(0x1, I40E_VF_ARQLEN1_ARQCRIT_SHIFT) -#define I40E_VF_ARQLEN1_ARQENABLE_SHIFT 31 -#define I40E_VF_ARQLEN1_ARQENABLE_MASK I40E_MASK(0x1, I40E_VF_ARQLEN1_ARQENABLE_SHIFT) -#define I40E_VF_ARQT1 0x00007000 /* Reset: EMPR */ -#define I40E_VF_ARQT1_ARQT_SHIFT 0 -#define I40E_VF_ARQT1_ARQT_MASK I40E_MASK(0x3FF, I40E_VF_ARQT1_ARQT_SHIFT) -#define I40E_VF_ATQBAH1 0x00007800 /* Reset: EMPR */ -#define I40E_VF_ATQBAH1_ATQBAH_SHIFT 0 -#define I40E_VF_ATQBAH1_ATQBAH_MASK I40E_MASK(0xFFFFFFFF, I40E_VF_ATQBAH1_ATQBAH_SHIFT) -#define I40E_VF_ATQBAL1 0x00007C00 /* Reset: EMPR */ -#define I40E_VF_ATQBAL1_ATQBAL_SHIFT 0 -#define I40E_VF_ATQBAL1_ATQBAL_MASK I40E_MASK(0xFFFFFFFF, I40E_VF_ATQBAL1_ATQBAL_SHIFT) -#define I40E_VF_ATQH1 0x00006400 /* Reset: EMPR */ -#define I40E_VF_ATQH1_ATQH_SHIFT 0 -#define I40E_VF_ATQH1_ATQH_MASK I40E_MASK(0x3FF, I40E_VF_ATQH1_ATQH_SHIFT) -#define I40E_VF_ATQLEN1 0x00006800 /* Reset: EMPR */ -#define I40E_VF_ATQLEN1_ATQLEN_SHIFT 0 -#define I40E_VF_ATQLEN1_ATQLEN_MASK I40E_MASK(0x3FF, I40E_VF_ATQLEN1_ATQLEN_SHIFT) -#define I40E_VF_ATQLEN1_ATQVFE_SHIFT 28 -#define I40E_VF_ATQLEN1_ATQVFE_MASK I40E_MASK(0x1, I40E_VF_ATQLEN1_ATQVFE_SHIFT) -#define I40E_VF_ATQLEN1_ATQOVFL_SHIFT 29 -#define I40E_VF_ATQLEN1_ATQOVFL_MASK I40E_MASK(0x1, I40E_VF_ATQLEN1_ATQOVFL_SHIFT) -#define I40E_VF_ATQLEN1_ATQCRIT_SHIFT 30 -#define I40E_VF_ATQLEN1_ATQCRIT_MASK I40E_MASK(0x1, I40E_VF_ATQLEN1_ATQCRIT_SHIFT) -#define I40E_VF_ATQLEN1_ATQENABLE_SHIFT 31 -#define I40E_VF_ATQLEN1_ATQENABLE_MASK I40E_MASK(0x1, I40E_VF_ATQLEN1_ATQENABLE_SHIFT) -#define I40E_VF_ATQT1 0x00008400 /* Reset: EMPR */ -#define I40E_VF_ATQT1_ATQT_SHIFT 0 -#define I40E_VF_ATQT1_ATQT_MASK I40E_MASK(0x3FF, I40E_VF_ATQT1_ATQT_SHIFT) -#define I40E_VFGEN_RSTAT 0x00008800 /* Reset: VFR */ -#define I40E_VFGEN_RSTAT_VFR_STATE_SHIFT 0 -#define I40E_VFGEN_RSTAT_VFR_STATE_MASK I40E_MASK(0x3, I40E_VFGEN_RSTAT_VFR_STATE_SHIFT) -#define I40E_VFINT_DYN_CTL01 0x00005C00 /* Reset: VFR */ -#define I40E_VFINT_DYN_CTL01_INTENA_SHIFT 0 -#define I40E_VFINT_DYN_CTL01_INTENA_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTL01_INTENA_SHIFT) -#define I40E_VFINT_DYN_CTL01_CLEARPBA_SHIFT 1 -#define I40E_VFINT_DYN_CTL01_CLEARPBA_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTL01_CLEARPBA_SHIFT) -#define I40E_VFINT_DYN_CTL01_SWINT_TRIG_SHIFT 2 -#define I40E_VFINT_DYN_CTL01_SWINT_TRIG_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTL01_SWINT_TRIG_SHIFT) -#define I40E_VFINT_DYN_CTL01_ITR_INDX_SHIFT 3 -#define I40E_VFINT_DYN_CTL01_ITR_INDX_MASK I40E_MASK(0x3, I40E_VFINT_DYN_CTL01_ITR_INDX_SHIFT) -#define I40E_VFINT_DYN_CTL01_INTERVAL_SHIFT 5 -#define I40E_VFINT_DYN_CTL01_INTERVAL_MASK I40E_MASK(0xFFF, I40E_VFINT_DYN_CTL01_INTERVAL_SHIFT) -#define I40E_VFINT_DYN_CTL01_SW_ITR_INDX_ENA_SHIFT 24 -#define I40E_VFINT_DYN_CTL01_SW_ITR_INDX_ENA_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTL01_SW_ITR_INDX_ENA_SHIFT) -#define I40E_VFINT_DYN_CTL01_SW_ITR_INDX_SHIFT 25 -#define I40E_VFINT_DYN_CTL01_SW_ITR_INDX_MASK I40E_MASK(0x3, I40E_VFINT_DYN_CTL01_SW_ITR_INDX_SHIFT) -#define I40E_VFINT_DYN_CTL01_INTENA_MSK_SHIFT 31 -#define I40E_VFINT_DYN_CTL01_INTENA_MSK_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTL01_INTENA_MSK_SHIFT) -#define I40E_VFINT_DYN_CTLN1(_INTVF) (0x00003800 + ((_INTVF) * 4)) /* _i=0...15 */ /* Reset: VFR */ -#define I40E_VFINT_DYN_CTLN1_MAX_INDEX 15 -#define I40E_VFINT_DYN_CTLN1_INTENA_SHIFT 0 -#define I40E_VFINT_DYN_CTLN1_INTENA_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTLN1_INTENA_SHIFT) -#define I40E_VFINT_DYN_CTLN1_CLEARPBA_SHIFT 1 -#define I40E_VFINT_DYN_CTLN1_CLEARPBA_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTLN1_CLEARPBA_SHIFT) -#define I40E_VFINT_DYN_CTLN1_SWINT_TRIG_SHIFT 2 -#define I40E_VFINT_DYN_CTLN1_SWINT_TRIG_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTLN1_SWINT_TRIG_SHIFT) -#define I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT 3 -#define I40E_VFINT_DYN_CTLN1_ITR_INDX_MASK I40E_MASK(0x3, I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT) -#define I40E_VFINT_DYN_CTLN1_INTERVAL_SHIFT 5 -#define I40E_VFINT_DYN_CTLN1_INTERVAL_MASK I40E_MASK(0xFFF, I40E_VFINT_DYN_CTLN1_INTERVAL_SHIFT) -#define I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_SHIFT 24 -#define I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_SHIFT) -#define I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_SHIFT 25 -#define I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_MASK I40E_MASK(0x3, I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_SHIFT) -#define I40E_VFINT_DYN_CTLN1_INTENA_MSK_SHIFT 31 -#define I40E_VFINT_DYN_CTLN1_INTENA_MSK_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTLN1_INTENA_MSK_SHIFT) -#define I40E_VFINT_ICR0_ENA1 0x00005000 /* Reset: CORER */ -#define I40E_VFINT_ICR0_ENA1_LINK_STAT_CHANGE_SHIFT 25 -#define I40E_VFINT_ICR0_ENA1_LINK_STAT_CHANGE_MASK I40E_MASK(0x1, I40E_VFINT_ICR0_ENA1_LINK_STAT_CHANGE_SHIFT) -#define I40E_VFINT_ICR0_ENA1_ADMINQ_SHIFT 30 -#define I40E_VFINT_ICR0_ENA1_ADMINQ_MASK I40E_MASK(0x1, I40E_VFINT_ICR0_ENA1_ADMINQ_SHIFT) -#define I40E_VFINT_ICR0_ENA1_RSVD_SHIFT 31 -#define I40E_VFINT_ICR0_ENA1_RSVD_MASK I40E_MASK(0x1, I40E_VFINT_ICR0_ENA1_RSVD_SHIFT) -#define I40E_VFINT_ICR01 0x00004800 /* Reset: CORER */ -#define I40E_VFINT_ICR01_INTEVENT_SHIFT 0 -#define I40E_VFINT_ICR01_INTEVENT_MASK I40E_MASK(0x1, I40E_VFINT_ICR01_INTEVENT_SHIFT) -#define I40E_VFINT_ICR01_QUEUE_0_SHIFT 1 -#define I40E_VFINT_ICR01_QUEUE_0_MASK I40E_MASK(0x1, I40E_VFINT_ICR01_QUEUE_0_SHIFT) -#define I40E_VFINT_ICR01_QUEUE_1_SHIFT 2 -#define I40E_VFINT_ICR01_QUEUE_1_MASK I40E_MASK(0x1, I40E_VFINT_ICR01_QUEUE_1_SHIFT) -#define I40E_VFINT_ICR01_QUEUE_2_SHIFT 3 -#define I40E_VFINT_ICR01_QUEUE_2_MASK I40E_MASK(0x1, I40E_VFINT_ICR01_QUEUE_2_SHIFT) -#define I40E_VFINT_ICR01_QUEUE_3_SHIFT 4 -#define I40E_VFINT_ICR01_QUEUE_3_MASK I40E_MASK(0x1, I40E_VFINT_ICR01_QUEUE_3_SHIFT) -#define I40E_VFINT_ICR01_LINK_STAT_CHANGE_SHIFT 25 -#define I40E_VFINT_ICR01_LINK_STAT_CHANGE_MASK I40E_MASK(0x1, I40E_VFINT_ICR01_LINK_STAT_CHANGE_SHIFT) -#define I40E_VFINT_ICR01_ADMINQ_SHIFT 30 -#define I40E_VFINT_ICR01_ADMINQ_MASK I40E_MASK(0x1, I40E_VFINT_ICR01_ADMINQ_SHIFT) -#define I40E_VFINT_ICR01_SWINT_SHIFT 31 -#define I40E_VFINT_ICR01_SWINT_MASK I40E_MASK(0x1, I40E_VFINT_ICR01_SWINT_SHIFT) -#define I40E_VFINT_ITR01(_i) (0x00004C00 + ((_i) * 4)) /* _i=0...2 */ /* Reset: VFR */ -#define I40E_VFINT_ITR01_MAX_INDEX 2 -#define I40E_VFINT_ITR01_INTERVAL_SHIFT 0 -#define I40E_VFINT_ITR01_INTERVAL_MASK I40E_MASK(0xFFF, I40E_VFINT_ITR01_INTERVAL_SHIFT) -#define I40E_VFINT_ITRN1(_i, _INTVF) (0x00002800 + ((_i) * 64 + (_INTVF) * 4)) /* _i=0...2, _INTVF=0...15 */ /* Reset: VFR */ -#define I40E_VFINT_ITRN1_MAX_INDEX 2 -#define I40E_VFINT_ITRN1_INTERVAL_SHIFT 0 -#define I40E_VFINT_ITRN1_INTERVAL_MASK I40E_MASK(0xFFF, I40E_VFINT_ITRN1_INTERVAL_SHIFT) -#define I40E_VFINT_STAT_CTL01 0x00005400 /* Reset: CORER */ -#define I40E_VFINT_STAT_CTL01_OTHER_ITR_INDX_SHIFT 2 -#define I40E_VFINT_STAT_CTL01_OTHER_ITR_INDX_MASK I40E_MASK(0x3, I40E_VFINT_STAT_CTL01_OTHER_ITR_INDX_SHIFT) -#define I40E_QRX_TAIL1(_Q) (0x00002000 + ((_Q) * 4)) /* _i=0...15 */ /* Reset: CORER */ -#define I40E_QRX_TAIL1_MAX_INDEX 15 -#define I40E_QRX_TAIL1_TAIL_SHIFT 0 -#define I40E_QRX_TAIL1_TAIL_MASK I40E_MASK(0x1FFF, I40E_QRX_TAIL1_TAIL_SHIFT) -#define I40E_QTX_TAIL1(_Q) (0x00000000 + ((_Q) * 4)) /* _i=0...15 */ /* Reset: PFR */ -#define I40E_QTX_TAIL1_MAX_INDEX 15 -#define I40E_QTX_TAIL1_TAIL_SHIFT 0 -#define I40E_QTX_TAIL1_TAIL_MASK I40E_MASK(0x1FFF, I40E_QTX_TAIL1_TAIL_SHIFT) -#define I40E_VFMSIX_PBA 0x00002000 /* Reset: VFLR */ -#define I40E_VFMSIX_PBA_PENBIT_SHIFT 0 -#define I40E_VFMSIX_PBA_PENBIT_MASK I40E_MASK(0xFFFFFFFF, I40E_VFMSIX_PBA_PENBIT_SHIFT) -#define I40E_VFMSIX_TADD(_i) (0x00000000 + ((_i) * 16)) /* _i=0...16 */ /* Reset: VFLR */ -#define I40E_VFMSIX_TADD_MAX_INDEX 16 -#define I40E_VFMSIX_TADD_MSIXTADD10_SHIFT 0 -#define I40E_VFMSIX_TADD_MSIXTADD10_MASK I40E_MASK(0x3, I40E_VFMSIX_TADD_MSIXTADD10_SHIFT) -#define I40E_VFMSIX_TADD_MSIXTADD_SHIFT 2 -#define I40E_VFMSIX_TADD_MSIXTADD_MASK I40E_MASK(0x3FFFFFFF, I40E_VFMSIX_TADD_MSIXTADD_SHIFT) -#define I40E_VFMSIX_TMSG(_i) (0x00000008 + ((_i) * 16)) /* _i=0...16 */ /* Reset: VFLR */ -#define I40E_VFMSIX_TMSG_MAX_INDEX 16 -#define I40E_VFMSIX_TMSG_MSIXTMSG_SHIFT 0 -#define I40E_VFMSIX_TMSG_MSIXTMSG_MASK I40E_MASK(0xFFFFFFFF, I40E_VFMSIX_TMSG_MSIXTMSG_SHIFT) -#define I40E_VFMSIX_TUADD(_i) (0x00000004 + ((_i) * 16)) /* _i=0...16 */ /* Reset: VFLR */ -#define I40E_VFMSIX_TUADD_MAX_INDEX 16 -#define I40E_VFMSIX_TUADD_MSIXTUADD_SHIFT 0 -#define I40E_VFMSIX_TUADD_MSIXTUADD_MASK I40E_MASK(0xFFFFFFFF, I40E_VFMSIX_TUADD_MSIXTUADD_SHIFT) -#define I40E_VFMSIX_TVCTRL(_i) (0x0000000C + ((_i) * 16)) /* _i=0...16 */ /* Reset: VFLR */ -#define I40E_VFMSIX_TVCTRL_MAX_INDEX 16 -#define I40E_VFMSIX_TVCTRL_MASK_SHIFT 0 -#define I40E_VFMSIX_TVCTRL_MASK_MASK I40E_MASK(0x1, I40E_VFMSIX_TVCTRL_MASK_SHIFT) -#define I40E_VFCM_PE_ERRDATA 0x0000DC00 /* Reset: VFR */ -#define I40E_VFCM_PE_ERRDATA_ERROR_CODE_SHIFT 0 -#define I40E_VFCM_PE_ERRDATA_ERROR_CODE_MASK I40E_MASK(0xF, I40E_VFCM_PE_ERRDATA_ERROR_CODE_SHIFT) -#define I40E_VFCM_PE_ERRDATA_Q_TYPE_SHIFT 4 -#define I40E_VFCM_PE_ERRDATA_Q_TYPE_MASK I40E_MASK(0x7, I40E_VFCM_PE_ERRDATA_Q_TYPE_SHIFT) -#define I40E_VFCM_PE_ERRDATA_Q_NUM_SHIFT 8 -#define I40E_VFCM_PE_ERRDATA_Q_NUM_MASK I40E_MASK(0x3FFFF, I40E_VFCM_PE_ERRDATA_Q_NUM_SHIFT) -#define I40E_VFCM_PE_ERRINFO 0x0000D800 /* Reset: VFR */ -#define I40E_VFCM_PE_ERRINFO_ERROR_VALID_SHIFT 0 -#define I40E_VFCM_PE_ERRINFO_ERROR_VALID_MASK I40E_MASK(0x1, I40E_VFCM_PE_ERRINFO_ERROR_VALID_SHIFT) -#define I40E_VFCM_PE_ERRINFO_ERROR_INST_SHIFT 4 -#define I40E_VFCM_PE_ERRINFO_ERROR_INST_MASK I40E_MASK(0x7, I40E_VFCM_PE_ERRINFO_ERROR_INST_SHIFT) -#define I40E_VFCM_PE_ERRINFO_DBL_ERROR_CNT_SHIFT 8 -#define I40E_VFCM_PE_ERRINFO_DBL_ERROR_CNT_MASK I40E_MASK(0xFF, I40E_VFCM_PE_ERRINFO_DBL_ERROR_CNT_SHIFT) -#define I40E_VFCM_PE_ERRINFO_RLU_ERROR_CNT_SHIFT 16 -#define I40E_VFCM_PE_ERRINFO_RLU_ERROR_CNT_MASK I40E_MASK(0xFF, I40E_VFCM_PE_ERRINFO_RLU_ERROR_CNT_SHIFT) -#define I40E_VFCM_PE_ERRINFO_RLS_ERROR_CNT_SHIFT 24 -#define I40E_VFCM_PE_ERRINFO_RLS_ERROR_CNT_MASK I40E_MASK(0xFF, I40E_VFCM_PE_ERRINFO_RLS_ERROR_CNT_SHIFT) -#define I40E_VFQF_HENA(_i) (0x0000C400 + ((_i) * 4)) /* _i=0...1 */ /* Reset: CORER */ -#define I40E_VFQF_HENA_MAX_INDEX 1 -#define I40E_VFQF_HENA_PTYPE_ENA_SHIFT 0 -#define I40E_VFQF_HENA_PTYPE_ENA_MASK I40E_MASK(0xFFFFFFFF, I40E_VFQF_HENA_PTYPE_ENA_SHIFT) -#define I40E_VFQF_HKEY(_i) (0x0000CC00 + ((_i) * 4)) /* _i=0...12 */ /* Reset: CORER */ -#define I40E_VFQF_HKEY_MAX_INDEX 12 -#define I40E_VFQF_HKEY_KEY_0_SHIFT 0 -#define I40E_VFQF_HKEY_KEY_0_MASK I40E_MASK(0xFF, I40E_VFQF_HKEY_KEY_0_SHIFT) -#define I40E_VFQF_HKEY_KEY_1_SHIFT 8 -#define I40E_VFQF_HKEY_KEY_1_MASK I40E_MASK(0xFF, I40E_VFQF_HKEY_KEY_1_SHIFT) -#define I40E_VFQF_HKEY_KEY_2_SHIFT 16 -#define I40E_VFQF_HKEY_KEY_2_MASK I40E_MASK(0xFF, I40E_VFQF_HKEY_KEY_2_SHIFT) -#define I40E_VFQF_HKEY_KEY_3_SHIFT 24 -#define I40E_VFQF_HKEY_KEY_3_MASK I40E_MASK(0xFF, I40E_VFQF_HKEY_KEY_3_SHIFT) -#define I40E_VFQF_HLUT(_i) (0x0000D000 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */ -#define I40E_VFQF_HLUT_MAX_INDEX 15 -#define I40E_VFQF_HLUT_LUT0_SHIFT 0 -#define I40E_VFQF_HLUT_LUT0_MASK I40E_MASK(0xF, I40E_VFQF_HLUT_LUT0_SHIFT) -#define I40E_VFQF_HLUT_LUT1_SHIFT 8 -#define I40E_VFQF_HLUT_LUT1_MASK I40E_MASK(0xF, I40E_VFQF_HLUT_LUT1_SHIFT) -#define I40E_VFQF_HLUT_LUT2_SHIFT 16 -#define I40E_VFQF_HLUT_LUT2_MASK I40E_MASK(0xF, I40E_VFQF_HLUT_LUT2_SHIFT) -#define I40E_VFQF_HLUT_LUT3_SHIFT 24 -#define I40E_VFQF_HLUT_LUT3_MASK I40E_MASK(0xF, I40E_VFQF_HLUT_LUT3_SHIFT) -#define I40E_VFQF_HREGION(_i) (0x0000D400 + ((_i) * 4)) /* _i=0...7 */ /* Reset: CORER */ -#define I40E_VFQF_HREGION_MAX_INDEX 7 -#define I40E_VFQF_HREGION_OVERRIDE_ENA_0_SHIFT 0 -#define I40E_VFQF_HREGION_OVERRIDE_ENA_0_MASK I40E_MASK(0x1, I40E_VFQF_HREGION_OVERRIDE_ENA_0_SHIFT) -#define I40E_VFQF_HREGION_REGION_0_SHIFT 1 -#define I40E_VFQF_HREGION_REGION_0_MASK I40E_MASK(0x7, I40E_VFQF_HREGION_REGION_0_SHIFT) -#define I40E_VFQF_HREGION_OVERRIDE_ENA_1_SHIFT 4 -#define I40E_VFQF_HREGION_OVERRIDE_ENA_1_MASK I40E_MASK(0x1, I40E_VFQF_HREGION_OVERRIDE_ENA_1_SHIFT) -#define I40E_VFQF_HREGION_REGION_1_SHIFT 5 -#define I40E_VFQF_HREGION_REGION_1_MASK I40E_MASK(0x7, I40E_VFQF_HREGION_REGION_1_SHIFT) -#define I40E_VFQF_HREGION_OVERRIDE_ENA_2_SHIFT 8 -#define I40E_VFQF_HREGION_OVERRIDE_ENA_2_MASK I40E_MASK(0x1, I40E_VFQF_HREGION_OVERRIDE_ENA_2_SHIFT) -#define I40E_VFQF_HREGION_REGION_2_SHIFT 9 -#define I40E_VFQF_HREGION_REGION_2_MASK I40E_MASK(0x7, I40E_VFQF_HREGION_REGION_2_SHIFT) -#define I40E_VFQF_HREGION_OVERRIDE_ENA_3_SHIFT 12 -#define I40E_VFQF_HREGION_OVERRIDE_ENA_3_MASK I40E_MASK(0x1, I40E_VFQF_HREGION_OVERRIDE_ENA_3_SHIFT) -#define I40E_VFQF_HREGION_REGION_3_SHIFT 13 -#define I40E_VFQF_HREGION_REGION_3_MASK I40E_MASK(0x7, I40E_VFQF_HREGION_REGION_3_SHIFT) -#define I40E_VFQF_HREGION_OVERRIDE_ENA_4_SHIFT 16 -#define I40E_VFQF_HREGION_OVERRIDE_ENA_4_MASK I40E_MASK(0x1, I40E_VFQF_HREGION_OVERRIDE_ENA_4_SHIFT) -#define I40E_VFQF_HREGION_REGION_4_SHIFT 17 -#define I40E_VFQF_HREGION_REGION_4_MASK I40E_MASK(0x7, I40E_VFQF_HREGION_REGION_4_SHIFT) -#define I40E_VFQF_HREGION_OVERRIDE_ENA_5_SHIFT 20 -#define I40E_VFQF_HREGION_OVERRIDE_ENA_5_MASK I40E_MASK(0x1, I40E_VFQF_HREGION_OVERRIDE_ENA_5_SHIFT) -#define I40E_VFQF_HREGION_REGION_5_SHIFT 21 -#define I40E_VFQF_HREGION_REGION_5_MASK I40E_MASK(0x7, I40E_VFQF_HREGION_REGION_5_SHIFT) -#define I40E_VFQF_HREGION_OVERRIDE_ENA_6_SHIFT 24 -#define I40E_VFQF_HREGION_OVERRIDE_ENA_6_MASK I40E_MASK(0x1, I40E_VFQF_HREGION_OVERRIDE_ENA_6_SHIFT) -#define I40E_VFQF_HREGION_REGION_6_SHIFT 25 -#define I40E_VFQF_HREGION_REGION_6_MASK I40E_MASK(0x7, I40E_VFQF_HREGION_REGION_6_SHIFT) -#define I40E_VFQF_HREGION_OVERRIDE_ENA_7_SHIFT 28 -#define I40E_VFQF_HREGION_OVERRIDE_ENA_7_MASK I40E_MASK(0x1, I40E_VFQF_HREGION_OVERRIDE_ENA_7_SHIFT) -#define I40E_VFQF_HREGION_REGION_7_SHIFT 29 -#define I40E_VFQF_HREGION_REGION_7_MASK I40E_MASK(0x7, I40E_VFQF_HREGION_REGION_7_SHIFT) -#define I40E_VFINT_DYN_CTL01_WB_ON_ITR_SHIFT 30 -#define I40E_VFINT_DYN_CTL01_WB_ON_ITR_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTL01_WB_ON_ITR_SHIFT) -#define I40E_VFINT_DYN_CTLN1_WB_ON_ITR_SHIFT 30 -#define I40E_VFINT_DYN_CTLN1_WB_ON_ITR_MASK I40E_MASK(0x1, I40E_VFINT_DYN_CTLN1_WB_ON_ITR_SHIFT) -#define I40E_VFPE_AEQALLOC1 0x0000A400 /* Reset: VFR */ -#define I40E_VFPE_AEQALLOC1_AECOUNT_SHIFT 0 -#define I40E_VFPE_AEQALLOC1_AECOUNT_MASK I40E_MASK(0xFFFFFFFF, I40E_VFPE_AEQALLOC1_AECOUNT_SHIFT) -#define I40E_VFPE_CCQPHIGH1 0x00009800 /* Reset: VFR */ -#define I40E_VFPE_CCQPHIGH1_PECCQPHIGH_SHIFT 0 -#define I40E_VFPE_CCQPHIGH1_PECCQPHIGH_MASK I40E_MASK(0xFFFFFFFF, I40E_VFPE_CCQPHIGH1_PECCQPHIGH_SHIFT) -#define I40E_VFPE_CCQPLOW1 0x0000AC00 /* Reset: VFR */ -#define I40E_VFPE_CCQPLOW1_PECCQPLOW_SHIFT 0 -#define I40E_VFPE_CCQPLOW1_PECCQPLOW_MASK I40E_MASK(0xFFFFFFFF, I40E_VFPE_CCQPLOW1_PECCQPLOW_SHIFT) -#define I40E_VFPE_CCQPSTATUS1 0x0000B800 /* Reset: VFR */ -#define I40E_VFPE_CCQPSTATUS1_CCQP_DONE_SHIFT 0 -#define I40E_VFPE_CCQPSTATUS1_CCQP_DONE_MASK I40E_MASK(0x1, I40E_VFPE_CCQPSTATUS1_CCQP_DONE_SHIFT) -#define I40E_VFPE_CCQPSTATUS1_HMC_PROFILE_SHIFT 4 -#define I40E_VFPE_CCQPSTATUS1_HMC_PROFILE_MASK I40E_MASK(0x7, I40E_VFPE_CCQPSTATUS1_HMC_PROFILE_SHIFT) -#define I40E_VFPE_CCQPSTATUS1_RDMA_EN_VFS_SHIFT 16 -#define I40E_VFPE_CCQPSTATUS1_RDMA_EN_VFS_MASK I40E_MASK(0x3F, I40E_VFPE_CCQPSTATUS1_RDMA_EN_VFS_SHIFT) -#define I40E_VFPE_CCQPSTATUS1_CCQP_ERR_SHIFT 31 -#define I40E_VFPE_CCQPSTATUS1_CCQP_ERR_MASK I40E_MASK(0x1, I40E_VFPE_CCQPSTATUS1_CCQP_ERR_SHIFT) -#define I40E_VFPE_CQACK1 0x0000B000 /* Reset: VFR */ -#define I40E_VFPE_CQACK1_PECQID_SHIFT 0 -#define I40E_VFPE_CQACK1_PECQID_MASK I40E_MASK(0x1FFFF, I40E_VFPE_CQACK1_PECQID_SHIFT) -#define I40E_VFPE_CQARM1 0x0000B400 /* Reset: VFR */ -#define I40E_VFPE_CQARM1_PECQID_SHIFT 0 -#define I40E_VFPE_CQARM1_PECQID_MASK I40E_MASK(0x1FFFF, I40E_VFPE_CQARM1_PECQID_SHIFT) -#define I40E_VFPE_CQPDB1 0x0000BC00 /* Reset: VFR */ -#define I40E_VFPE_CQPDB1_WQHEAD_SHIFT 0 -#define I40E_VFPE_CQPDB1_WQHEAD_MASK I40E_MASK(0x7FF, I40E_VFPE_CQPDB1_WQHEAD_SHIFT) -#define I40E_VFPE_CQPERRCODES1 0x00009C00 /* Reset: VFR */ -#define I40E_VFPE_CQPERRCODES1_CQP_MINOR_CODE_SHIFT 0 -#define I40E_VFPE_CQPERRCODES1_CQP_MINOR_CODE_MASK I40E_MASK(0xFFFF, I40E_VFPE_CQPERRCODES1_CQP_MINOR_CODE_SHIFT) -#define I40E_VFPE_CQPERRCODES1_CQP_MAJOR_CODE_SHIFT 16 -#define I40E_VFPE_CQPERRCODES1_CQP_MAJOR_CODE_MASK I40E_MASK(0xFFFF, I40E_VFPE_CQPERRCODES1_CQP_MAJOR_CODE_SHIFT) -#define I40E_VFPE_CQPTAIL1 0x0000A000 /* Reset: VFR */ -#define I40E_VFPE_CQPTAIL1_WQTAIL_SHIFT 0 -#define I40E_VFPE_CQPTAIL1_WQTAIL_MASK I40E_MASK(0x7FF, I40E_VFPE_CQPTAIL1_WQTAIL_SHIFT) -#define I40E_VFPE_CQPTAIL1_CQP_OP_ERR_SHIFT 31 -#define I40E_VFPE_CQPTAIL1_CQP_OP_ERR_MASK I40E_MASK(0x1, I40E_VFPE_CQPTAIL1_CQP_OP_ERR_SHIFT) -#define I40E_VFPE_IPCONFIG01 0x00008C00 /* Reset: VFR */ -#define I40E_VFPE_IPCONFIG01_PEIPID_SHIFT 0 -#define I40E_VFPE_IPCONFIG01_PEIPID_MASK I40E_MASK(0xFFFF, I40E_VFPE_IPCONFIG01_PEIPID_SHIFT) -#define I40E_VFPE_IPCONFIG01_USEENTIREIDRANGE_SHIFT 16 -#define I40E_VFPE_IPCONFIG01_USEENTIREIDRANGE_MASK I40E_MASK(0x1, I40E_VFPE_IPCONFIG01_USEENTIREIDRANGE_SHIFT) -#define I40E_VFPE_MRTEIDXMASK1 0x00009000 /* Reset: VFR */ -#define I40E_VFPE_MRTEIDXMASK1_MRTEIDXMASKBITS_SHIFT 0 -#define I40E_VFPE_MRTEIDXMASK1_MRTEIDXMASKBITS_MASK I40E_MASK(0x1F, I40E_VFPE_MRTEIDXMASK1_MRTEIDXMASKBITS_SHIFT) -#define I40E_VFPE_RCVUNEXPECTEDERROR1 0x00009400 /* Reset: VFR */ -#define I40E_VFPE_RCVUNEXPECTEDERROR1_TCP_RX_UNEXP_ERR_SHIFT 0 -#define I40E_VFPE_RCVUNEXPECTEDERROR1_TCP_RX_UNEXP_ERR_MASK I40E_MASK(0xFFFFFF, I40E_VFPE_RCVUNEXPECTEDERROR1_TCP_RX_UNEXP_ERR_SHIFT) -#define I40E_VFPE_TCPNOWTIMER1 0x0000A800 /* Reset: VFR */ -#define I40E_VFPE_TCPNOWTIMER1_TCP_NOW_SHIFT 0 -#define I40E_VFPE_TCPNOWTIMER1_TCP_NOW_MASK I40E_MASK(0xFFFFFFFF, I40E_VFPE_TCPNOWTIMER1_TCP_NOW_SHIFT) -#define I40E_VFPE_WQEALLOC1 0x0000C000 /* Reset: VFR */ -#define I40E_VFPE_WQEALLOC1_PEQPID_SHIFT 0 -#define I40E_VFPE_WQEALLOC1_PEQPID_MASK I40E_MASK(0x3FFFF, I40E_VFPE_WQEALLOC1_PEQPID_SHIFT) -#define I40E_VFPE_WQEALLOC1_WQE_DESC_INDEX_SHIFT 20 -#define I40E_VFPE_WQEALLOC1_WQE_DESC_INDEX_MASK I40E_MASK(0xFFF, I40E_VFPE_WQEALLOC1_WQE_DESC_INDEX_SHIFT) -#endif /* _I40E_REGISTER_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h deleted file mode 100644 index 094387db3c11..000000000000 --- a/drivers/net/ethernet/intel/i40evf/i40e_type.h +++ /dev/null @@ -1,1496 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 2013 - 2018 Intel Corporation. */ - -#ifndef _I40E_TYPE_H_ -#define _I40E_TYPE_H_ - -#include "i40e_status.h" -#include "i40e_osdep.h" -#include "i40e_register.h" -#include "i40e_adminq.h" -#include "i40e_hmc.h" -#include "i40e_lan_hmc.h" -#include "i40e_devids.h" - -/* I40E_MASK is a macro used on 32 bit registers */ -#define I40E_MASK(mask, shift) ((u32)(mask) << (shift)) - -#define I40E_MAX_VSI_QP 16 -#define I40E_MAX_VF_VSI 3 -#define I40E_MAX_CHAINED_RX_BUFFERS 5 -#define I40E_MAX_PF_UDP_OFFLOAD_PORTS 16 - -/* Max default timeout in ms, */ -#define I40E_MAX_NVM_TIMEOUT 18000 - -/* Max timeout in ms for the phy to respond */ -#define I40E_MAX_PHY_TIMEOUT 500 - -/* Switch from ms to the 1usec global time (this is the GTIME resolution) */ -#define I40E_MS_TO_GTIME(time) ((time) * 1000) - -/* forward declaration */ -struct i40e_hw; -typedef void (*I40E_ADMINQ_CALLBACK)(struct i40e_hw *, struct i40e_aq_desc *); - -/* Data type manipulation macros. */ - -#define I40E_DESC_UNUSED(R) \ - ((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \ - (R)->next_to_clean - (R)->next_to_use - 1) - -/* bitfields for Tx queue mapping in QTX_CTL */ -#define I40E_QTX_CTL_VF_QUEUE 0x0 -#define I40E_QTX_CTL_VM_QUEUE 0x1 -#define I40E_QTX_CTL_PF_QUEUE 0x2 - -/* debug masks - set these bits in hw->debug_mask to control output */ -enum i40e_debug_mask { - I40E_DEBUG_INIT = 0x00000001, - I40E_DEBUG_RELEASE = 0x00000002, - - I40E_DEBUG_LINK = 0x00000010, - I40E_DEBUG_PHY = 0x00000020, - I40E_DEBUG_HMC = 0x00000040, - I40E_DEBUG_NVM = 0x00000080, - I40E_DEBUG_LAN = 0x00000100, - I40E_DEBUG_FLOW = 0x00000200, - I40E_DEBUG_DCB = 0x00000400, - I40E_DEBUG_DIAG = 0x00000800, - I40E_DEBUG_FD = 0x00001000, - I40E_DEBUG_PACKAGE = 0x00002000, - - I40E_DEBUG_AQ_MESSAGE = 0x01000000, - I40E_DEBUG_AQ_DESCRIPTOR = 0x02000000, - I40E_DEBUG_AQ_DESC_BUFFER = 0x04000000, - I40E_DEBUG_AQ_COMMAND = 0x06000000, - I40E_DEBUG_AQ = 0x0F000000, - - I40E_DEBUG_USER = 0xF0000000, - - I40E_DEBUG_ALL = 0xFFFFFFFF -}; - -/* These are structs for managing the hardware information and the operations. - * The structures of function pointers are filled out at init time when we - * know for sure exactly which hardware we're working with. This gives us the - * flexibility of using the same main driver code but adapting to slightly - * different hardware needs as new parts are developed. For this architecture, - * the Firmware and AdminQ are intended to insulate the driver from most of the - * future changes, but these structures will also do part of the job. - */ -enum i40e_mac_type { - I40E_MAC_UNKNOWN = 0, - I40E_MAC_XL710, - I40E_MAC_VF, - I40E_MAC_X722, - I40E_MAC_X722_VF, - I40E_MAC_GENERIC, -}; - -enum i40e_media_type { - I40E_MEDIA_TYPE_UNKNOWN = 0, - I40E_MEDIA_TYPE_FIBER, - I40E_MEDIA_TYPE_BASET, - I40E_MEDIA_TYPE_BACKPLANE, - I40E_MEDIA_TYPE_CX4, - I40E_MEDIA_TYPE_DA, - I40E_MEDIA_TYPE_VIRTUAL -}; - -enum i40e_fc_mode { - I40E_FC_NONE = 0, - I40E_FC_RX_PAUSE, - I40E_FC_TX_PAUSE, - I40E_FC_FULL, - I40E_FC_PFC, - I40E_FC_DEFAULT -}; - -enum i40e_set_fc_aq_failures { - I40E_SET_FC_AQ_FAIL_NONE = 0, - I40E_SET_FC_AQ_FAIL_GET = 1, - I40E_SET_FC_AQ_FAIL_SET = 2, - I40E_SET_FC_AQ_FAIL_UPDATE = 4, - I40E_SET_FC_AQ_FAIL_SET_UPDATE = 6 -}; - -enum i40e_vsi_type { - I40E_VSI_MAIN = 0, - I40E_VSI_VMDQ1 = 1, - I40E_VSI_VMDQ2 = 2, - I40E_VSI_CTRL = 3, - I40E_VSI_FCOE = 4, - I40E_VSI_MIRROR = 5, - I40E_VSI_SRIOV = 6, - I40E_VSI_FDIR = 7, - I40E_VSI_TYPE_UNKNOWN -}; - -enum i40e_queue_type { - I40E_QUEUE_TYPE_RX = 0, - I40E_QUEUE_TYPE_TX, - I40E_QUEUE_TYPE_PE_CEQ, - I40E_QUEUE_TYPE_UNKNOWN -}; - -struct i40e_link_status { - enum i40e_aq_phy_type phy_type; - enum i40e_aq_link_speed link_speed; - u8 link_info; - u8 an_info; - u8 req_fec_info; - u8 fec_info; - u8 ext_info; - u8 loopback; - /* is Link Status Event notification to SW enabled */ - bool lse_enable; - u16 max_frame_size; - bool crc_enable; - u8 pacing; - u8 requested_speeds; - u8 module_type[3]; - /* 1st byte: module identifier */ -#define I40E_MODULE_TYPE_SFP 0x03 -#define I40E_MODULE_TYPE_QSFP 0x0D - /* 2nd byte: ethernet compliance codes for 10/40G */ -#define I40E_MODULE_TYPE_40G_ACTIVE 0x01 -#define I40E_MODULE_TYPE_40G_LR4 0x02 -#define I40E_MODULE_TYPE_40G_SR4 0x04 -#define I40E_MODULE_TYPE_40G_CR4 0x08 -#define I40E_MODULE_TYPE_10G_BASE_SR 0x10 -#define I40E_MODULE_TYPE_10G_BASE_LR 0x20 -#define I40E_MODULE_TYPE_10G_BASE_LRM 0x40 -#define I40E_MODULE_TYPE_10G_BASE_ER 0x80 - /* 3rd byte: ethernet compliance codes for 1G */ -#define I40E_MODULE_TYPE_1000BASE_SX 0x01 -#define I40E_MODULE_TYPE_1000BASE_LX 0x02 -#define I40E_MODULE_TYPE_1000BASE_CX 0x04 -#define I40E_MODULE_TYPE_1000BASE_T 0x08 -}; - -struct i40e_phy_info { - struct i40e_link_status link_info; - struct i40e_link_status link_info_old; - bool get_link_info; - enum i40e_media_type media_type; - /* all the phy types the NVM is capable of */ - u64 phy_types; -}; - -#define I40E_CAP_PHY_TYPE_SGMII BIT_ULL(I40E_PHY_TYPE_SGMII) -#define I40E_CAP_PHY_TYPE_1000BASE_KX BIT_ULL(I40E_PHY_TYPE_1000BASE_KX) -#define I40E_CAP_PHY_TYPE_10GBASE_KX4 BIT_ULL(I40E_PHY_TYPE_10GBASE_KX4) -#define I40E_CAP_PHY_TYPE_10GBASE_KR BIT_ULL(I40E_PHY_TYPE_10GBASE_KR) -#define I40E_CAP_PHY_TYPE_40GBASE_KR4 BIT_ULL(I40E_PHY_TYPE_40GBASE_KR4) -#define I40E_CAP_PHY_TYPE_XAUI BIT_ULL(I40E_PHY_TYPE_XAUI) -#define I40E_CAP_PHY_TYPE_XFI BIT_ULL(I40E_PHY_TYPE_XFI) -#define I40E_CAP_PHY_TYPE_SFI BIT_ULL(I40E_PHY_TYPE_SFI) -#define I40E_CAP_PHY_TYPE_XLAUI BIT_ULL(I40E_PHY_TYPE_XLAUI) -#define I40E_CAP_PHY_TYPE_XLPPI BIT_ULL(I40E_PHY_TYPE_XLPPI) -#define I40E_CAP_PHY_TYPE_40GBASE_CR4_CU BIT_ULL(I40E_PHY_TYPE_40GBASE_CR4_CU) -#define I40E_CAP_PHY_TYPE_10GBASE_CR1_CU BIT_ULL(I40E_PHY_TYPE_10GBASE_CR1_CU) -#define I40E_CAP_PHY_TYPE_10GBASE_AOC BIT_ULL(I40E_PHY_TYPE_10GBASE_AOC) -#define I40E_CAP_PHY_TYPE_40GBASE_AOC BIT_ULL(I40E_PHY_TYPE_40GBASE_AOC) -#define I40E_CAP_PHY_TYPE_100BASE_TX BIT_ULL(I40E_PHY_TYPE_100BASE_TX) -#define I40E_CAP_PHY_TYPE_1000BASE_T BIT_ULL(I40E_PHY_TYPE_1000BASE_T) -#define I40E_CAP_PHY_TYPE_10GBASE_T BIT_ULL(I40E_PHY_TYPE_10GBASE_T) -#define I40E_CAP_PHY_TYPE_10GBASE_SR BIT_ULL(I40E_PHY_TYPE_10GBASE_SR) -#define I40E_CAP_PHY_TYPE_10GBASE_LR BIT_ULL(I40E_PHY_TYPE_10GBASE_LR) -#define I40E_CAP_PHY_TYPE_10GBASE_SFPP_CU BIT_ULL(I40E_PHY_TYPE_10GBASE_SFPP_CU) -#define I40E_CAP_PHY_TYPE_10GBASE_CR1 BIT_ULL(I40E_PHY_TYPE_10GBASE_CR1) -#define I40E_CAP_PHY_TYPE_40GBASE_CR4 BIT_ULL(I40E_PHY_TYPE_40GBASE_CR4) -#define I40E_CAP_PHY_TYPE_40GBASE_SR4 BIT_ULL(I40E_PHY_TYPE_40GBASE_SR4) -#define I40E_CAP_PHY_TYPE_40GBASE_LR4 BIT_ULL(I40E_PHY_TYPE_40GBASE_LR4) -#define I40E_CAP_PHY_TYPE_1000BASE_SX BIT_ULL(I40E_PHY_TYPE_1000BASE_SX) -#define I40E_CAP_PHY_TYPE_1000BASE_LX BIT_ULL(I40E_PHY_TYPE_1000BASE_LX) -#define I40E_CAP_PHY_TYPE_1000BASE_T_OPTICAL \ - BIT_ULL(I40E_PHY_TYPE_1000BASE_T_OPTICAL) -#define I40E_CAP_PHY_TYPE_20GBASE_KR2 BIT_ULL(I40E_PHY_TYPE_20GBASE_KR2) -/* Defining the macro I40E_TYPE_OFFSET to implement a bit shift for some - * PHY types. There is an unused bit (31) in the I40E_CAP_PHY_TYPE_* bit - * fields but no corresponding gap in the i40e_aq_phy_type enumeration. So, - * a shift is needed to adjust for this with values larger than 31. The - * only affected values are I40E_PHY_TYPE_25GBASE_*. - */ -#define I40E_PHY_TYPE_OFFSET 1 -#define I40E_CAP_PHY_TYPE_25GBASE_KR BIT_ULL(I40E_PHY_TYPE_25GBASE_KR + \ - I40E_PHY_TYPE_OFFSET) -#define I40E_CAP_PHY_TYPE_25GBASE_CR BIT_ULL(I40E_PHY_TYPE_25GBASE_CR + \ - I40E_PHY_TYPE_OFFSET) -#define I40E_CAP_PHY_TYPE_25GBASE_SR BIT_ULL(I40E_PHY_TYPE_25GBASE_SR + \ - I40E_PHY_TYPE_OFFSET) -#define I40E_CAP_PHY_TYPE_25GBASE_LR BIT_ULL(I40E_PHY_TYPE_25GBASE_LR + \ - I40E_PHY_TYPE_OFFSET) -#define I40E_HW_CAP_MAX_GPIO 30 -/* Capabilities of a PF or a VF or the whole device */ -struct i40e_hw_capabilities { - u32 switch_mode; -#define I40E_NVM_IMAGE_TYPE_EVB 0x0 -#define I40E_NVM_IMAGE_TYPE_CLOUD 0x2 -#define I40E_NVM_IMAGE_TYPE_UDP_CLOUD 0x3 - - u32 management_mode; - u32 mng_protocols_over_mctp; -#define I40E_MNG_PROTOCOL_PLDM 0x2 -#define I40E_MNG_PROTOCOL_OEM_COMMANDS 0x4 -#define I40E_MNG_PROTOCOL_NCSI 0x8 - u32 npar_enable; - u32 os2bmc; - u32 valid_functions; - bool sr_iov_1_1; - bool vmdq; - bool evb_802_1_qbg; /* Edge Virtual Bridging */ - bool evb_802_1_qbh; /* Bridge Port Extension */ - bool dcb; - bool fcoe; - bool iscsi; /* Indicates iSCSI enabled */ - bool flex10_enable; - bool flex10_capable; - u32 flex10_mode; -#define I40E_FLEX10_MODE_UNKNOWN 0x0 -#define I40E_FLEX10_MODE_DCC 0x1 -#define I40E_FLEX10_MODE_DCI 0x2 - - u32 flex10_status; -#define I40E_FLEX10_STATUS_DCC_ERROR 0x1 -#define I40E_FLEX10_STATUS_VC_MODE 0x2 - - bool sec_rev_disabled; - bool update_disabled; -#define I40E_NVM_MGMT_SEC_REV_DISABLED 0x1 -#define I40E_NVM_MGMT_UPDATE_DISABLED 0x2 - - bool mgmt_cem; - bool ieee_1588; - bool iwarp; - bool fd; - u32 fd_filters_guaranteed; - u32 fd_filters_best_effort; - bool rss; - u32 rss_table_size; - u32 rss_table_entry_width; - bool led[I40E_HW_CAP_MAX_GPIO]; - bool sdp[I40E_HW_CAP_MAX_GPIO]; - u32 nvm_image_type; - u32 num_flow_director_filters; - u32 num_vfs; - u32 vf_base_id; - u32 num_vsis; - u32 num_rx_qp; - u32 num_tx_qp; - u32 base_queue; - u32 num_msix_vectors; - u32 num_msix_vectors_vf; - u32 led_pin_num; - u32 sdp_pin_num; - u32 mdio_port_num; - u32 mdio_port_mode; - u8 rx_buf_chain_len; - u32 enabled_tcmap; - u32 maxtc; - u64 wr_csr_prot; -}; - -struct i40e_mac_info { - enum i40e_mac_type type; - u8 addr[ETH_ALEN]; - u8 perm_addr[ETH_ALEN]; - u8 san_addr[ETH_ALEN]; - u16 max_fcoeq; -}; - -enum i40e_aq_resources_ids { - I40E_NVM_RESOURCE_ID = 1 -}; - -enum i40e_aq_resource_access_type { - I40E_RESOURCE_READ = 1, - I40E_RESOURCE_WRITE -}; - -struct i40e_nvm_info { - u64 hw_semaphore_timeout; /* usec global time (GTIME resolution) */ - u32 timeout; /* [ms] */ - u16 sr_size; /* Shadow RAM size in words */ - bool blank_nvm_mode; /* is NVM empty (no FW present)*/ - u16 version; /* NVM package version */ - u32 eetrack; /* NVM data version */ - u32 oem_ver; /* OEM version info */ -}; - -/* definitions used in NVM update support */ - -enum i40e_nvmupd_cmd { - I40E_NVMUPD_INVALID, - I40E_NVMUPD_READ_CON, - I40E_NVMUPD_READ_SNT, - I40E_NVMUPD_READ_LCB, - I40E_NVMUPD_READ_SA, - I40E_NVMUPD_WRITE_ERA, - I40E_NVMUPD_WRITE_CON, - I40E_NVMUPD_WRITE_SNT, - I40E_NVMUPD_WRITE_LCB, - I40E_NVMUPD_WRITE_SA, - I40E_NVMUPD_CSUM_CON, - I40E_NVMUPD_CSUM_SA, - I40E_NVMUPD_CSUM_LCB, - I40E_NVMUPD_STATUS, - I40E_NVMUPD_EXEC_AQ, - I40E_NVMUPD_GET_AQ_RESULT, - I40E_NVMUPD_GET_AQ_EVENT, -}; - -enum i40e_nvmupd_state { - I40E_NVMUPD_STATE_INIT, - I40E_NVMUPD_STATE_READING, - I40E_NVMUPD_STATE_WRITING, - I40E_NVMUPD_STATE_INIT_WAIT, - I40E_NVMUPD_STATE_WRITE_WAIT, - I40E_NVMUPD_STATE_ERROR -}; - -/* nvm_access definition and its masks/shifts need to be accessible to - * application, core driver, and shared code. Where is the right file? - */ -#define I40E_NVM_READ 0xB -#define I40E_NVM_WRITE 0xC - -#define I40E_NVM_MOD_PNT_MASK 0xFF - -#define I40E_NVM_TRANS_SHIFT 8 -#define I40E_NVM_TRANS_MASK (0xf << I40E_NVM_TRANS_SHIFT) -#define I40E_NVM_PRESERVATION_FLAGS_SHIFT 12 -#define I40E_NVM_PRESERVATION_FLAGS_MASK \ - (0x3 << I40E_NVM_PRESERVATION_FLAGS_SHIFT) -#define I40E_NVM_PRESERVATION_FLAGS_SELECTED 0x01 -#define I40E_NVM_PRESERVATION_FLAGS_ALL 0x02 -#define I40E_NVM_CON 0x0 -#define I40E_NVM_SNT 0x1 -#define I40E_NVM_LCB 0x2 -#define I40E_NVM_SA (I40E_NVM_SNT | I40E_NVM_LCB) -#define I40E_NVM_ERA 0x4 -#define I40E_NVM_CSUM 0x8 -#define I40E_NVM_AQE 0xe -#define I40E_NVM_EXEC 0xf - -#define I40E_NVM_ADAPT_SHIFT 16 -#define I40E_NVM_ADAPT_MASK (0xffff << I40E_NVM_ADAPT_SHIFT) - -#define I40E_NVMUPD_MAX_DATA 4096 -#define I40E_NVMUPD_IFACE_TIMEOUT 2 /* seconds */ - -struct i40e_nvm_access { - u32 command; - u32 config; - u32 offset; /* in bytes */ - u32 data_size; /* in bytes */ - u8 data[1]; -}; - -/* (Q)SFP module access definitions */ -#define I40E_I2C_EEPROM_DEV_ADDR 0xA0 -#define I40E_I2C_EEPROM_DEV_ADDR2 0xA2 -#define I40E_MODULE_TYPE_ADDR 0x00 -#define I40E_MODULE_REVISION_ADDR 0x01 -#define I40E_MODULE_SFF_8472_COMP 0x5E -#define I40E_MODULE_SFF_8472_SWAP 0x5C -#define I40E_MODULE_SFF_ADDR_MODE 0x04 -#define I40E_MODULE_TYPE_QSFP_PLUS 0x0D -#define I40E_MODULE_TYPE_QSFP28 0x11 -#define I40E_MODULE_QSFP_MAX_LEN 640 - -/* PCI bus types */ -enum i40e_bus_type { - i40e_bus_type_unknown = 0, - i40e_bus_type_pci, - i40e_bus_type_pcix, - i40e_bus_type_pci_express, - i40e_bus_type_reserved -}; - -/* PCI bus speeds */ -enum i40e_bus_speed { - i40e_bus_speed_unknown = 0, - i40e_bus_speed_33 = 33, - i40e_bus_speed_66 = 66, - i40e_bus_speed_100 = 100, - i40e_bus_speed_120 = 120, - i40e_bus_speed_133 = 133, - i40e_bus_speed_2500 = 2500, - i40e_bus_speed_5000 = 5000, - i40e_bus_speed_8000 = 8000, - i40e_bus_speed_reserved -}; - -/* PCI bus widths */ -enum i40e_bus_width { - i40e_bus_width_unknown = 0, - i40e_bus_width_pcie_x1 = 1, - i40e_bus_width_pcie_x2 = 2, - i40e_bus_width_pcie_x4 = 4, - i40e_bus_width_pcie_x8 = 8, - i40e_bus_width_32 = 32, - i40e_bus_width_64 = 64, - i40e_bus_width_reserved -}; - -/* Bus parameters */ -struct i40e_bus_info { - enum i40e_bus_speed speed; - enum i40e_bus_width width; - enum i40e_bus_type type; - - u16 func; - u16 device; - u16 lan_id; - u16 bus_id; -}; - -/* Flow control (FC) parameters */ -struct i40e_fc_info { - enum i40e_fc_mode current_mode; /* FC mode in effect */ - enum i40e_fc_mode requested_mode; /* FC mode requested by caller */ -}; - -#define I40E_MAX_TRAFFIC_CLASS 8 -#define I40E_MAX_USER_PRIORITY 8 -#define I40E_DCBX_MAX_APPS 32 -#define I40E_LLDPDU_SIZE 1500 - -/* IEEE 802.1Qaz ETS Configuration data */ -struct i40e_ieee_ets_config { - u8 willing; - u8 cbs; - u8 maxtcs; - u8 prioritytable[I40E_MAX_TRAFFIC_CLASS]; - u8 tcbwtable[I40E_MAX_TRAFFIC_CLASS]; - u8 tsatable[I40E_MAX_TRAFFIC_CLASS]; -}; - -/* IEEE 802.1Qaz ETS Recommendation data */ -struct i40e_ieee_ets_recommend { - u8 prioritytable[I40E_MAX_TRAFFIC_CLASS]; - u8 tcbwtable[I40E_MAX_TRAFFIC_CLASS]; - u8 tsatable[I40E_MAX_TRAFFIC_CLASS]; -}; - -/* IEEE 802.1Qaz PFC Configuration data */ -struct i40e_ieee_pfc_config { - u8 willing; - u8 mbc; - u8 pfccap; - u8 pfcenable; -}; - -/* IEEE 802.1Qaz Application Priority data */ -struct i40e_ieee_app_priority_table { - u8 priority; - u8 selector; - u16 protocolid; -}; - -struct i40e_dcbx_config { - u32 numapps; - u32 tlv_status; /* CEE mode TLV status */ - struct i40e_ieee_ets_config etscfg; - struct i40e_ieee_ets_recommend etsrec; - struct i40e_ieee_pfc_config pfc; - struct i40e_ieee_app_priority_table app[I40E_DCBX_MAX_APPS]; -}; - -/* Port hardware description */ -struct i40e_hw { - u8 __iomem *hw_addr; - void *back; - - /* subsystem structs */ - struct i40e_phy_info phy; - struct i40e_mac_info mac; - struct i40e_bus_info bus; - struct i40e_nvm_info nvm; - struct i40e_fc_info fc; - - /* pci info */ - u16 device_id; - u16 vendor_id; - u16 subsystem_device_id; - u16 subsystem_vendor_id; - u8 revision_id; - u8 port; - bool adapter_stopped; - - /* capabilities for entire device and PCI func */ - struct i40e_hw_capabilities dev_caps; - struct i40e_hw_capabilities func_caps; - - /* Flow Director shared filter space */ - u16 fdir_shared_filter_count; - - /* device profile info */ - u8 pf_id; - u16 main_vsi_seid; - - /* for multi-function MACs */ - u16 partition_id; - u16 num_partitions; - u16 num_ports; - - /* Closest numa node to the device */ - u16 numa_node; - - /* Admin Queue info */ - struct i40e_adminq_info aq; - - /* state of nvm update process */ - enum i40e_nvmupd_state nvmupd_state; - struct i40e_aq_desc nvm_wb_desc; - struct i40e_aq_desc nvm_aq_event_desc; - struct i40e_virt_mem nvm_buff; - bool nvm_release_on_done; - u16 nvm_wait_opcode; - - /* HMC info */ - struct i40e_hmc_info hmc; /* HMC info struct */ - - /* LLDP/DCBX Status */ - u16 dcbx_status; - -#define I40E_HW_FLAG_802_1AD_CAPABLE BIT_ULL(1) -#define I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE BIT_ULL(2) - - /* DCBX info */ - struct i40e_dcbx_config local_dcbx_config; /* Oper/Local Cfg */ - struct i40e_dcbx_config remote_dcbx_config; /* Peer Cfg */ - struct i40e_dcbx_config desired_dcbx_config; /* CEE Desired Cfg */ - - /* Used in set switch config AQ command */ - u16 switch_tag; - u16 first_tag; - u16 second_tag; - - /* debug mask */ - u32 debug_mask; - char err_str[16]; -}; - -static inline bool i40e_is_vf(struct i40e_hw *hw) -{ - return (hw->mac.type == I40E_MAC_VF || - hw->mac.type == I40E_MAC_X722_VF); -} - -struct i40e_driver_version { - u8 major_version; - u8 minor_version; - u8 build_version; - u8 subbuild_version; - u8 driver_string[32]; -}; - -/* RX Descriptors */ -union i40e_16byte_rx_desc { - struct { - __le64 pkt_addr; /* Packet buffer address */ - __le64 hdr_addr; /* Header buffer address */ - } read; - struct { - struct { - struct { - union { - __le16 mirroring_status; - __le16 fcoe_ctx_id; - } mirr_fcoe; - __le16 l2tag1; - } lo_dword; - union { - __le32 rss; /* RSS Hash */ - __le32 fd_id; /* Flow director filter id */ - __le32 fcoe_param; /* FCoE DDP Context id */ - } hi_dword; - } qword0; - struct { - /* ext status/error/pktype/length */ - __le64 status_error_len; - } qword1; - } wb; /* writeback */ -}; - -union i40e_32byte_rx_desc { - struct { - __le64 pkt_addr; /* Packet buffer address */ - __le64 hdr_addr; /* Header buffer address */ - /* bit 0 of hdr_buffer_addr is DD bit */ - __le64 rsvd1; - __le64 rsvd2; - } read; - struct { - struct { - struct { - union { - __le16 mirroring_status; - __le16 fcoe_ctx_id; - } mirr_fcoe; - __le16 l2tag1; - } lo_dword; - union { - __le32 rss; /* RSS Hash */ - __le32 fcoe_param; /* FCoE DDP Context id */ - /* Flow director filter id in case of - * Programming status desc WB - */ - __le32 fd_id; - } hi_dword; - } qword0; - struct { - /* status/error/pktype/length */ - __le64 status_error_len; - } qword1; - struct { - __le16 ext_status; /* extended status */ - __le16 rsvd; - __le16 l2tag2_1; - __le16 l2tag2_2; - } qword2; - struct { - union { - __le32 flex_bytes_lo; - __le32 pe_status; - } lo_dword; - union { - __le32 flex_bytes_hi; - __le32 fd_id; - } hi_dword; - } qword3; - } wb; /* writeback */ -}; - -enum i40e_rx_desc_status_bits { - /* Note: These are predefined bit offsets */ - I40E_RX_DESC_STATUS_DD_SHIFT = 0, - I40E_RX_DESC_STATUS_EOF_SHIFT = 1, - I40E_RX_DESC_STATUS_L2TAG1P_SHIFT = 2, - I40E_RX_DESC_STATUS_L3L4P_SHIFT = 3, - I40E_RX_DESC_STATUS_CRCP_SHIFT = 4, - I40E_RX_DESC_STATUS_TSYNINDX_SHIFT = 5, /* 2 BITS */ - I40E_RX_DESC_STATUS_TSYNVALID_SHIFT = 7, - /* Note: Bit 8 is reserved in X710 and XL710 */ - I40E_RX_DESC_STATUS_EXT_UDP_0_SHIFT = 8, - I40E_RX_DESC_STATUS_UMBCAST_SHIFT = 9, /* 2 BITS */ - I40E_RX_DESC_STATUS_FLM_SHIFT = 11, - I40E_RX_DESC_STATUS_FLTSTAT_SHIFT = 12, /* 2 BITS */ - I40E_RX_DESC_STATUS_LPBK_SHIFT = 14, - I40E_RX_DESC_STATUS_IPV6EXADD_SHIFT = 15, - I40E_RX_DESC_STATUS_RESERVED_SHIFT = 16, /* 2 BITS */ - /* Note: For non-tunnel packets INT_UDP_0 is the right status for - * UDP header - */ - I40E_RX_DESC_STATUS_INT_UDP_0_SHIFT = 18, - I40E_RX_DESC_STATUS_LAST /* this entry must be last!!! */ -}; - -#define I40E_RXD_QW1_STATUS_SHIFT 0 -#define I40E_RXD_QW1_STATUS_MASK ((BIT(I40E_RX_DESC_STATUS_LAST) - 1) \ - << I40E_RXD_QW1_STATUS_SHIFT) - -#define I40E_RXD_QW1_STATUS_TSYNINDX_SHIFT I40E_RX_DESC_STATUS_TSYNINDX_SHIFT -#define I40E_RXD_QW1_STATUS_TSYNINDX_MASK (0x3UL << \ - I40E_RXD_QW1_STATUS_TSYNINDX_SHIFT) - -#define I40E_RXD_QW1_STATUS_TSYNVALID_SHIFT I40E_RX_DESC_STATUS_TSYNVALID_SHIFT -#define I40E_RXD_QW1_STATUS_TSYNVALID_MASK \ - BIT_ULL(I40E_RXD_QW1_STATUS_TSYNVALID_SHIFT) - -enum i40e_rx_desc_fltstat_values { - I40E_RX_DESC_FLTSTAT_NO_DATA = 0, - I40E_RX_DESC_FLTSTAT_RSV_FD_ID = 1, /* 16byte desc? FD_ID : RSV */ - I40E_RX_DESC_FLTSTAT_RSV = 2, - I40E_RX_DESC_FLTSTAT_RSS_HASH = 3, -}; - -#define I40E_RXD_QW1_ERROR_SHIFT 19 -#define I40E_RXD_QW1_ERROR_MASK (0xFFUL << I40E_RXD_QW1_ERROR_SHIFT) - -enum i40e_rx_desc_error_bits { - /* Note: These are predefined bit offsets */ - I40E_RX_DESC_ERROR_RXE_SHIFT = 0, - I40E_RX_DESC_ERROR_RECIPE_SHIFT = 1, - I40E_RX_DESC_ERROR_HBO_SHIFT = 2, - I40E_RX_DESC_ERROR_L3L4E_SHIFT = 3, /* 3 BITS */ - I40E_RX_DESC_ERROR_IPE_SHIFT = 3, - I40E_RX_DESC_ERROR_L4E_SHIFT = 4, - I40E_RX_DESC_ERROR_EIPE_SHIFT = 5, - I40E_RX_DESC_ERROR_OVERSIZE_SHIFT = 6, - I40E_RX_DESC_ERROR_PPRS_SHIFT = 7 -}; - -enum i40e_rx_desc_error_l3l4e_fcoe_masks { - I40E_RX_DESC_ERROR_L3L4E_NONE = 0, - I40E_RX_DESC_ERROR_L3L4E_PROT = 1, - I40E_RX_DESC_ERROR_L3L4E_FC = 2, - I40E_RX_DESC_ERROR_L3L4E_DMAC_ERR = 3, - I40E_RX_DESC_ERROR_L3L4E_DMAC_WARN = 4 -}; - -#define I40E_RXD_QW1_PTYPE_SHIFT 30 -#define I40E_RXD_QW1_PTYPE_MASK (0xFFULL << I40E_RXD_QW1_PTYPE_SHIFT) - -/* Packet type non-ip values */ -enum i40e_rx_l2_ptype { - I40E_RX_PTYPE_L2_RESERVED = 0, - I40E_RX_PTYPE_L2_MAC_PAY2 = 1, - I40E_RX_PTYPE_L2_TIMESYNC_PAY2 = 2, - I40E_RX_PTYPE_L2_FIP_PAY2 = 3, - I40E_RX_PTYPE_L2_OUI_PAY2 = 4, - I40E_RX_PTYPE_L2_MACCNTRL_PAY2 = 5, - I40E_RX_PTYPE_L2_LLDP_PAY2 = 6, - I40E_RX_PTYPE_L2_ECP_PAY2 = 7, - I40E_RX_PTYPE_L2_EVB_PAY2 = 8, - I40E_RX_PTYPE_L2_QCN_PAY2 = 9, - I40E_RX_PTYPE_L2_EAPOL_PAY2 = 10, - I40E_RX_PTYPE_L2_ARP = 11, - I40E_RX_PTYPE_L2_FCOE_PAY3 = 12, - I40E_RX_PTYPE_L2_FCOE_FCDATA_PAY3 = 13, - I40E_RX_PTYPE_L2_FCOE_FCRDY_PAY3 = 14, - I40E_RX_PTYPE_L2_FCOE_FCRSP_PAY3 = 15, - I40E_RX_PTYPE_L2_FCOE_FCOTHER_PA = 16, - I40E_RX_PTYPE_L2_FCOE_VFT_PAY3 = 17, - I40E_RX_PTYPE_L2_FCOE_VFT_FCDATA = 18, - I40E_RX_PTYPE_L2_FCOE_VFT_FCRDY = 19, - I40E_RX_PTYPE_L2_FCOE_VFT_FCRSP = 20, - I40E_RX_PTYPE_L2_FCOE_VFT_FCOTHER = 21, - I40E_RX_PTYPE_GRENAT4_MAC_PAY3 = 58, - I40E_RX_PTYPE_GRENAT4_MACVLAN_IPV6_ICMP_PAY4 = 87, - I40E_RX_PTYPE_GRENAT6_MAC_PAY3 = 124, - I40E_RX_PTYPE_GRENAT6_MACVLAN_IPV6_ICMP_PAY4 = 153 -}; - -struct i40e_rx_ptype_decoded { - u32 ptype:8; - u32 known:1; - u32 outer_ip:1; - u32 outer_ip_ver:1; - u32 outer_frag:1; - u32 tunnel_type:3; - u32 tunnel_end_prot:2; - u32 tunnel_end_frag:1; - u32 inner_prot:4; - u32 payload_layer:3; -}; - -enum i40e_rx_ptype_outer_ip { - I40E_RX_PTYPE_OUTER_L2 = 0, - I40E_RX_PTYPE_OUTER_IP = 1 -}; - -enum i40e_rx_ptype_outer_ip_ver { - I40E_RX_PTYPE_OUTER_NONE = 0, - I40E_RX_PTYPE_OUTER_IPV4 = 0, - I40E_RX_PTYPE_OUTER_IPV6 = 1 -}; - -enum i40e_rx_ptype_outer_fragmented { - I40E_RX_PTYPE_NOT_FRAG = 0, - I40E_RX_PTYPE_FRAG = 1 -}; - -enum i40e_rx_ptype_tunnel_type { - I40E_RX_PTYPE_TUNNEL_NONE = 0, - I40E_RX_PTYPE_TUNNEL_IP_IP = 1, - I40E_RX_PTYPE_TUNNEL_IP_GRENAT = 2, - I40E_RX_PTYPE_TUNNEL_IP_GRENAT_MAC = 3, - I40E_RX_PTYPE_TUNNEL_IP_GRENAT_MAC_VLAN = 4, -}; - -enum i40e_rx_ptype_tunnel_end_prot { - I40E_RX_PTYPE_TUNNEL_END_NONE = 0, - I40E_RX_PTYPE_TUNNEL_END_IPV4 = 1, - I40E_RX_PTYPE_TUNNEL_END_IPV6 = 2, -}; - -enum i40e_rx_ptype_inner_prot { - I40E_RX_PTYPE_INNER_PROT_NONE = 0, - I40E_RX_PTYPE_INNER_PROT_UDP = 1, - I40E_RX_PTYPE_INNER_PROT_TCP = 2, - I40E_RX_PTYPE_INNER_PROT_SCTP = 3, - I40E_RX_PTYPE_INNER_PROT_ICMP = 4, - I40E_RX_PTYPE_INNER_PROT_TIMESYNC = 5 -}; - -enum i40e_rx_ptype_payload_layer { - I40E_RX_PTYPE_PAYLOAD_LAYER_NONE = 0, - I40E_RX_PTYPE_PAYLOAD_LAYER_PAY2 = 1, - I40E_RX_PTYPE_PAYLOAD_LAYER_PAY3 = 2, - I40E_RX_PTYPE_PAYLOAD_LAYER_PAY4 = 3, -}; - -#define I40E_RXD_QW1_LENGTH_PBUF_SHIFT 38 -#define I40E_RXD_QW1_LENGTH_PBUF_MASK (0x3FFFULL << \ - I40E_RXD_QW1_LENGTH_PBUF_SHIFT) - -#define I40E_RXD_QW1_LENGTH_HBUF_SHIFT 52 -#define I40E_RXD_QW1_LENGTH_HBUF_MASK (0x7FFULL << \ - I40E_RXD_QW1_LENGTH_HBUF_SHIFT) - -#define I40E_RXD_QW1_LENGTH_SPH_SHIFT 63 -#define I40E_RXD_QW1_LENGTH_SPH_MASK BIT_ULL(I40E_RXD_QW1_LENGTH_SPH_SHIFT) - -enum i40e_rx_desc_ext_status_bits { - /* Note: These are predefined bit offsets */ - I40E_RX_DESC_EXT_STATUS_L2TAG2P_SHIFT = 0, - I40E_RX_DESC_EXT_STATUS_L2TAG3P_SHIFT = 1, - I40E_RX_DESC_EXT_STATUS_FLEXBL_SHIFT = 2, /* 2 BITS */ - I40E_RX_DESC_EXT_STATUS_FLEXBH_SHIFT = 4, /* 2 BITS */ - I40E_RX_DESC_EXT_STATUS_FDLONGB_SHIFT = 9, - I40E_RX_DESC_EXT_STATUS_FCOELONGB_SHIFT = 10, - I40E_RX_DESC_EXT_STATUS_PELONGB_SHIFT = 11, -}; - -enum i40e_rx_desc_pe_status_bits { - /* Note: These are predefined bit offsets */ - I40E_RX_DESC_PE_STATUS_QPID_SHIFT = 0, /* 18 BITS */ - I40E_RX_DESC_PE_STATUS_L4PORT_SHIFT = 0, /* 16 BITS */ - I40E_RX_DESC_PE_STATUS_IPINDEX_SHIFT = 16, /* 8 BITS */ - I40E_RX_DESC_PE_STATUS_QPIDHIT_SHIFT = 24, - I40E_RX_DESC_PE_STATUS_APBVTHIT_SHIFT = 25, - I40E_RX_DESC_PE_STATUS_PORTV_SHIFT = 26, - I40E_RX_DESC_PE_STATUS_URG_SHIFT = 27, - I40E_RX_DESC_PE_STATUS_IPFRAG_SHIFT = 28, - I40E_RX_DESC_PE_STATUS_IPOPT_SHIFT = 29 -}; - -#define I40E_RX_PROG_STATUS_DESC_LENGTH_SHIFT 38 -#define I40E_RX_PROG_STATUS_DESC_LENGTH 0x2000000 - -#define I40E_RX_PROG_STATUS_DESC_QW1_PROGID_SHIFT 2 -#define I40E_RX_PROG_STATUS_DESC_QW1_PROGID_MASK (0x7UL << \ - I40E_RX_PROG_STATUS_DESC_QW1_PROGID_SHIFT) - -#define I40E_RX_PROG_STATUS_DESC_QW1_ERROR_SHIFT 19 -#define I40E_RX_PROG_STATUS_DESC_QW1_ERROR_MASK (0x3FUL << \ - I40E_RX_PROG_STATUS_DESC_QW1_ERROR_SHIFT) - -enum i40e_rx_prog_status_desc_status_bits { - /* Note: These are predefined bit offsets */ - I40E_RX_PROG_STATUS_DESC_DD_SHIFT = 0, - I40E_RX_PROG_STATUS_DESC_PROG_ID_SHIFT = 2 /* 3 BITS */ -}; - -enum i40e_rx_prog_status_desc_prog_id_masks { - I40E_RX_PROG_STATUS_DESC_FD_FILTER_STATUS = 1, - I40E_RX_PROG_STATUS_DESC_FCOE_CTXT_PROG_STATUS = 2, - I40E_RX_PROG_STATUS_DESC_FCOE_CTXT_INVL_STATUS = 4, -}; - -enum i40e_rx_prog_status_desc_error_bits { - /* Note: These are predefined bit offsets */ - I40E_RX_PROG_STATUS_DESC_FD_TBL_FULL_SHIFT = 0, - I40E_RX_PROG_STATUS_DESC_NO_FD_ENTRY_SHIFT = 1, - I40E_RX_PROG_STATUS_DESC_FCOE_TBL_FULL_SHIFT = 2, - I40E_RX_PROG_STATUS_DESC_FCOE_CONFLICT_SHIFT = 3 -}; - -/* TX Descriptor */ -struct i40e_tx_desc { - __le64 buffer_addr; /* Address of descriptor's data buf */ - __le64 cmd_type_offset_bsz; -}; - -#define I40E_TXD_QW1_DTYPE_SHIFT 0 -#define I40E_TXD_QW1_DTYPE_MASK (0xFUL << I40E_TXD_QW1_DTYPE_SHIFT) - -enum i40e_tx_desc_dtype_value { - I40E_TX_DESC_DTYPE_DATA = 0x0, - I40E_TX_DESC_DTYPE_NOP = 0x1, /* same as Context desc */ - I40E_TX_DESC_DTYPE_CONTEXT = 0x1, - I40E_TX_DESC_DTYPE_FCOE_CTX = 0x2, - I40E_TX_DESC_DTYPE_FILTER_PROG = 0x8, - I40E_TX_DESC_DTYPE_DDP_CTX = 0x9, - I40E_TX_DESC_DTYPE_FLEX_DATA = 0xB, - I40E_TX_DESC_DTYPE_FLEX_CTX_1 = 0xC, - I40E_TX_DESC_DTYPE_FLEX_CTX_2 = 0xD, - I40E_TX_DESC_DTYPE_DESC_DONE = 0xF -}; - -#define I40E_TXD_QW1_CMD_SHIFT 4 -#define I40E_TXD_QW1_CMD_MASK (0x3FFUL << I40E_TXD_QW1_CMD_SHIFT) - -enum i40e_tx_desc_cmd_bits { - I40E_TX_DESC_CMD_EOP = 0x0001, - I40E_TX_DESC_CMD_RS = 0x0002, - I40E_TX_DESC_CMD_ICRC = 0x0004, - I40E_TX_DESC_CMD_IL2TAG1 = 0x0008, - I40E_TX_DESC_CMD_DUMMY = 0x0010, - I40E_TX_DESC_CMD_IIPT_NONIP = 0x0000, /* 2 BITS */ - I40E_TX_DESC_CMD_IIPT_IPV6 = 0x0020, /* 2 BITS */ - I40E_TX_DESC_CMD_IIPT_IPV4 = 0x0040, /* 2 BITS */ - I40E_TX_DESC_CMD_IIPT_IPV4_CSUM = 0x0060, /* 2 BITS */ - I40E_TX_DESC_CMD_FCOET = 0x0080, - I40E_TX_DESC_CMD_L4T_EOFT_UNK = 0x0000, /* 2 BITS */ - I40E_TX_DESC_CMD_L4T_EOFT_TCP = 0x0100, /* 2 BITS */ - I40E_TX_DESC_CMD_L4T_EOFT_SCTP = 0x0200, /* 2 BITS */ - I40E_TX_DESC_CMD_L4T_EOFT_UDP = 0x0300, /* 2 BITS */ - I40E_TX_DESC_CMD_L4T_EOFT_EOF_N = 0x0000, /* 2 BITS */ - I40E_TX_DESC_CMD_L4T_EOFT_EOF_T = 0x0100, /* 2 BITS */ - I40E_TX_DESC_CMD_L4T_EOFT_EOF_NI = 0x0200, /* 2 BITS */ - I40E_TX_DESC_CMD_L4T_EOFT_EOF_A = 0x0300, /* 2 BITS */ -}; - -#define I40E_TXD_QW1_OFFSET_SHIFT 16 -#define I40E_TXD_QW1_OFFSET_MASK (0x3FFFFULL << \ - I40E_TXD_QW1_OFFSET_SHIFT) - -enum i40e_tx_desc_length_fields { - /* Note: These are predefined bit offsets */ - I40E_TX_DESC_LENGTH_MACLEN_SHIFT = 0, /* 7 BITS */ - I40E_TX_DESC_LENGTH_IPLEN_SHIFT = 7, /* 7 BITS */ - I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT = 14 /* 4 BITS */ -}; - -#define I40E_TXD_QW1_TX_BUF_SZ_SHIFT 34 -#define I40E_TXD_QW1_TX_BUF_SZ_MASK (0x3FFFULL << \ - I40E_TXD_QW1_TX_BUF_SZ_SHIFT) - -#define I40E_TXD_QW1_L2TAG1_SHIFT 48 -#define I40E_TXD_QW1_L2TAG1_MASK (0xFFFFULL << I40E_TXD_QW1_L2TAG1_SHIFT) - -/* Context descriptors */ -struct i40e_tx_context_desc { - __le32 tunneling_params; - __le16 l2tag2; - __le16 rsvd; - __le64 type_cmd_tso_mss; -}; - -#define I40E_TXD_CTX_QW1_DTYPE_SHIFT 0 -#define I40E_TXD_CTX_QW1_DTYPE_MASK (0xFUL << I40E_TXD_CTX_QW1_DTYPE_SHIFT) - -#define I40E_TXD_CTX_QW1_CMD_SHIFT 4 -#define I40E_TXD_CTX_QW1_CMD_MASK (0xFFFFUL << I40E_TXD_CTX_QW1_CMD_SHIFT) - -enum i40e_tx_ctx_desc_cmd_bits { - I40E_TX_CTX_DESC_TSO = 0x01, - I40E_TX_CTX_DESC_TSYN = 0x02, - I40E_TX_CTX_DESC_IL2TAG2 = 0x04, - I40E_TX_CTX_DESC_IL2TAG2_IL2H = 0x08, - I40E_TX_CTX_DESC_SWTCH_NOTAG = 0x00, - I40E_TX_CTX_DESC_SWTCH_UPLINK = 0x10, - I40E_TX_CTX_DESC_SWTCH_LOCAL = 0x20, - I40E_TX_CTX_DESC_SWTCH_VSI = 0x30, - I40E_TX_CTX_DESC_SWPE = 0x40 -}; - -#define I40E_TXD_CTX_QW1_TSO_LEN_SHIFT 30 -#define I40E_TXD_CTX_QW1_TSO_LEN_MASK (0x3FFFFULL << \ - I40E_TXD_CTX_QW1_TSO_LEN_SHIFT) - -#define I40E_TXD_CTX_QW1_MSS_SHIFT 50 -#define I40E_TXD_CTX_QW1_MSS_MASK (0x3FFFULL << \ - I40E_TXD_CTX_QW1_MSS_SHIFT) - -#define I40E_TXD_CTX_QW1_VSI_SHIFT 50 -#define I40E_TXD_CTX_QW1_VSI_MASK (0x1FFULL << I40E_TXD_CTX_QW1_VSI_SHIFT) - -#define I40E_TXD_CTX_QW0_EXT_IP_SHIFT 0 -#define I40E_TXD_CTX_QW0_EXT_IP_MASK (0x3ULL << \ - I40E_TXD_CTX_QW0_EXT_IP_SHIFT) - -enum i40e_tx_ctx_desc_eipt_offload { - I40E_TX_CTX_EXT_IP_NONE = 0x0, - I40E_TX_CTX_EXT_IP_IPV6 = 0x1, - I40E_TX_CTX_EXT_IP_IPV4_NO_CSUM = 0x2, - I40E_TX_CTX_EXT_IP_IPV4 = 0x3 -}; - -#define I40E_TXD_CTX_QW0_EXT_IPLEN_SHIFT 2 -#define I40E_TXD_CTX_QW0_EXT_IPLEN_MASK (0x3FULL << \ - I40E_TXD_CTX_QW0_EXT_IPLEN_SHIFT) - -#define I40E_TXD_CTX_QW0_NATT_SHIFT 9 -#define I40E_TXD_CTX_QW0_NATT_MASK (0x3ULL << I40E_TXD_CTX_QW0_NATT_SHIFT) - -#define I40E_TXD_CTX_UDP_TUNNELING BIT_ULL(I40E_TXD_CTX_QW0_NATT_SHIFT) -#define I40E_TXD_CTX_GRE_TUNNELING (0x2ULL << I40E_TXD_CTX_QW0_NATT_SHIFT) - -#define I40E_TXD_CTX_QW0_EIP_NOINC_SHIFT 11 -#define I40E_TXD_CTX_QW0_EIP_NOINC_MASK \ - BIT_ULL(I40E_TXD_CTX_QW0_EIP_NOINC_SHIFT) - -#define I40E_TXD_CTX_EIP_NOINC_IPID_CONST I40E_TXD_CTX_QW0_EIP_NOINC_MASK - -#define I40E_TXD_CTX_QW0_NATLEN_SHIFT 12 -#define I40E_TXD_CTX_QW0_NATLEN_MASK (0X7FULL << \ - I40E_TXD_CTX_QW0_NATLEN_SHIFT) - -#define I40E_TXD_CTX_QW0_DECTTL_SHIFT 19 -#define I40E_TXD_CTX_QW0_DECTTL_MASK (0xFULL << \ - I40E_TXD_CTX_QW0_DECTTL_SHIFT) - -#define I40E_TXD_CTX_QW0_L4T_CS_SHIFT 23 -#define I40E_TXD_CTX_QW0_L4T_CS_MASK BIT_ULL(I40E_TXD_CTX_QW0_L4T_CS_SHIFT) -struct i40e_filter_program_desc { - __le32 qindex_flex_ptype_vsi; - __le32 rsvd; - __le32 dtype_cmd_cntindex; - __le32 fd_id; -}; -#define I40E_TXD_FLTR_QW0_QINDEX_SHIFT 0 -#define I40E_TXD_FLTR_QW0_QINDEX_MASK (0x7FFUL << \ - I40E_TXD_FLTR_QW0_QINDEX_SHIFT) -#define I40E_TXD_FLTR_QW0_FLEXOFF_SHIFT 11 -#define I40E_TXD_FLTR_QW0_FLEXOFF_MASK (0x7UL << \ - I40E_TXD_FLTR_QW0_FLEXOFF_SHIFT) -#define I40E_TXD_FLTR_QW0_PCTYPE_SHIFT 17 -#define I40E_TXD_FLTR_QW0_PCTYPE_MASK (0x3FUL << \ - I40E_TXD_FLTR_QW0_PCTYPE_SHIFT) - -/* Packet Classifier Types for filters */ -enum i40e_filter_pctype { - /* Note: Values 0-28 are reserved for future use. - * Value 29, 30, 32 are not supported on XL710 and X710. - */ - I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP = 29, - I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP = 30, - I40E_FILTER_PCTYPE_NONF_IPV4_UDP = 31, - I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK = 32, - I40E_FILTER_PCTYPE_NONF_IPV4_TCP = 33, - I40E_FILTER_PCTYPE_NONF_IPV4_SCTP = 34, - I40E_FILTER_PCTYPE_NONF_IPV4_OTHER = 35, - I40E_FILTER_PCTYPE_FRAG_IPV4 = 36, - /* Note: Values 37-38 are reserved for future use. - * Value 39, 40, 42 are not supported on XL710 and X710. - */ - I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP = 39, - I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP = 40, - I40E_FILTER_PCTYPE_NONF_IPV6_UDP = 41, - I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK = 42, - I40E_FILTER_PCTYPE_NONF_IPV6_TCP = 43, - I40E_FILTER_PCTYPE_NONF_IPV6_SCTP = 44, - I40E_FILTER_PCTYPE_NONF_IPV6_OTHER = 45, - I40E_FILTER_PCTYPE_FRAG_IPV6 = 46, - /* Note: Value 47 is reserved for future use */ - I40E_FILTER_PCTYPE_FCOE_OX = 48, - I40E_FILTER_PCTYPE_FCOE_RX = 49, - I40E_FILTER_PCTYPE_FCOE_OTHER = 50, - /* Note: Values 51-62 are reserved for future use */ - I40E_FILTER_PCTYPE_L2_PAYLOAD = 63, -}; - -enum i40e_filter_program_desc_dest { - I40E_FILTER_PROGRAM_DESC_DEST_DROP_PACKET = 0x0, - I40E_FILTER_PROGRAM_DESC_DEST_DIRECT_PACKET_QINDEX = 0x1, - I40E_FILTER_PROGRAM_DESC_DEST_DIRECT_PACKET_OTHER = 0x2, -}; - -enum i40e_filter_program_desc_fd_status { - I40E_FILTER_PROGRAM_DESC_FD_STATUS_NONE = 0x0, - I40E_FILTER_PROGRAM_DESC_FD_STATUS_FD_ID = 0x1, - I40E_FILTER_PROGRAM_DESC_FD_STATUS_FD_ID_4FLEX_BYTES = 0x2, - I40E_FILTER_PROGRAM_DESC_FD_STATUS_8FLEX_BYTES = 0x3, -}; - -#define I40E_TXD_FLTR_QW0_DEST_VSI_SHIFT 23 -#define I40E_TXD_FLTR_QW0_DEST_VSI_MASK (0x1FFUL << \ - I40E_TXD_FLTR_QW0_DEST_VSI_SHIFT) - -#define I40E_TXD_FLTR_QW1_CMD_SHIFT 4 -#define I40E_TXD_FLTR_QW1_CMD_MASK (0xFFFFULL << \ - I40E_TXD_FLTR_QW1_CMD_SHIFT) - -#define I40E_TXD_FLTR_QW1_PCMD_SHIFT (0x0ULL + I40E_TXD_FLTR_QW1_CMD_SHIFT) -#define I40E_TXD_FLTR_QW1_PCMD_MASK (0x7ULL << I40E_TXD_FLTR_QW1_PCMD_SHIFT) - -enum i40e_filter_program_desc_pcmd { - I40E_FILTER_PROGRAM_DESC_PCMD_ADD_UPDATE = 0x1, - I40E_FILTER_PROGRAM_DESC_PCMD_REMOVE = 0x2, -}; - -#define I40E_TXD_FLTR_QW1_DEST_SHIFT (0x3ULL + I40E_TXD_FLTR_QW1_CMD_SHIFT) -#define I40E_TXD_FLTR_QW1_DEST_MASK (0x3ULL << I40E_TXD_FLTR_QW1_DEST_SHIFT) - -#define I40E_TXD_FLTR_QW1_CNT_ENA_SHIFT (0x7ULL + I40E_TXD_FLTR_QW1_CMD_SHIFT) -#define I40E_TXD_FLTR_QW1_CNT_ENA_MASK BIT_ULL(I40E_TXD_FLTR_QW1_CNT_ENA_SHIFT) - -#define I40E_TXD_FLTR_QW1_FD_STATUS_SHIFT (0x9ULL + \ - I40E_TXD_FLTR_QW1_CMD_SHIFT) -#define I40E_TXD_FLTR_QW1_FD_STATUS_MASK (0x3ULL << \ - I40E_TXD_FLTR_QW1_FD_STATUS_SHIFT) - -#define I40E_TXD_FLTR_QW1_CNTINDEX_SHIFT 20 -#define I40E_TXD_FLTR_QW1_CNTINDEX_MASK (0x1FFUL << \ - I40E_TXD_FLTR_QW1_CNTINDEX_SHIFT) - -enum i40e_filter_type { - I40E_FLOW_DIRECTOR_FLTR = 0, - I40E_PE_QUAD_HASH_FLTR = 1, - I40E_ETHERTYPE_FLTR, - I40E_FCOE_CTX_FLTR, - I40E_MAC_VLAN_FLTR, - I40E_HASH_FLTR -}; - -struct i40e_vsi_context { - u16 seid; - u16 uplink_seid; - u16 vsi_number; - u16 vsis_allocated; - u16 vsis_unallocated; - u16 flags; - u8 pf_num; - u8 vf_num; - u8 connection_type; - struct i40e_aqc_vsi_properties_data info; -}; - -struct i40e_veb_context { - u16 seid; - u16 uplink_seid; - u16 veb_number; - u16 vebs_allocated; - u16 vebs_unallocated; - u16 flags; - struct i40e_aqc_get_veb_parameters_completion info; -}; - -/* Statistics collected by each port, VSI, VEB, and S-channel */ -struct i40e_eth_stats { - u64 rx_bytes; /* gorc */ - u64 rx_unicast; /* uprc */ - u64 rx_multicast; /* mprc */ - u64 rx_broadcast; /* bprc */ - u64 rx_discards; /* rdpc */ - u64 rx_unknown_protocol; /* rupp */ - u64 tx_bytes; /* gotc */ - u64 tx_unicast; /* uptc */ - u64 tx_multicast; /* mptc */ - u64 tx_broadcast; /* bptc */ - u64 tx_discards; /* tdpc */ - u64 tx_errors; /* tepc */ -}; - -/* Statistics collected per VEB per TC */ -struct i40e_veb_tc_stats { - u64 tc_rx_packets[I40E_MAX_TRAFFIC_CLASS]; - u64 tc_rx_bytes[I40E_MAX_TRAFFIC_CLASS]; - u64 tc_tx_packets[I40E_MAX_TRAFFIC_CLASS]; - u64 tc_tx_bytes[I40E_MAX_TRAFFIC_CLASS]; -}; - -/* Statistics collected by the MAC */ -struct i40e_hw_port_stats { - /* eth stats collected by the port */ - struct i40e_eth_stats eth; - - /* additional port specific stats */ - u64 tx_dropped_link_down; /* tdold */ - u64 crc_errors; /* crcerrs */ - u64 illegal_bytes; /* illerrc */ - u64 error_bytes; /* errbc */ - u64 mac_local_faults; /* mlfc */ - u64 mac_remote_faults; /* mrfc */ - u64 rx_length_errors; /* rlec */ - u64 link_xon_rx; /* lxonrxc */ - u64 link_xoff_rx; /* lxoffrxc */ - u64 priority_xon_rx[8]; /* pxonrxc[8] */ - u64 priority_xoff_rx[8]; /* pxoffrxc[8] */ - u64 link_xon_tx; /* lxontxc */ - u64 link_xoff_tx; /* lxofftxc */ - u64 priority_xon_tx[8]; /* pxontxc[8] */ - u64 priority_xoff_tx[8]; /* pxofftxc[8] */ - u64 priority_xon_2_xoff[8]; /* pxon2offc[8] */ - u64 rx_size_64; /* prc64 */ - u64 rx_size_127; /* prc127 */ - u64 rx_size_255; /* prc255 */ - u64 rx_size_511; /* prc511 */ - u64 rx_size_1023; /* prc1023 */ - u64 rx_size_1522; /* prc1522 */ - u64 rx_size_big; /* prc9522 */ - u64 rx_undersize; /* ruc */ - u64 rx_fragments; /* rfc */ - u64 rx_oversize; /* roc */ - u64 rx_jabber; /* rjc */ - u64 tx_size_64; /* ptc64 */ - u64 tx_size_127; /* ptc127 */ - u64 tx_size_255; /* ptc255 */ - u64 tx_size_511; /* ptc511 */ - u64 tx_size_1023; /* ptc1023 */ - u64 tx_size_1522; /* ptc1522 */ - u64 tx_size_big; /* ptc9522 */ - u64 mac_short_packet_dropped; /* mspdc */ - u64 checksum_error; /* xec */ - /* flow director stats */ - u64 fd_atr_match; - u64 fd_sb_match; - u64 fd_atr_tunnel_match; - u32 fd_atr_status; - u32 fd_sb_status; - /* EEE LPI */ - u32 tx_lpi_status; - u32 rx_lpi_status; - u64 tx_lpi_count; /* etlpic */ - u64 rx_lpi_count; /* erlpic */ -}; - -/* Checksum and Shadow RAM pointers */ -#define I40E_SR_NVM_CONTROL_WORD 0x00 -#define I40E_EMP_MODULE_PTR 0x0F -#define I40E_SR_EMP_MODULE_PTR 0x48 -#define I40E_NVM_OEM_VER_OFF 0x83 -#define I40E_SR_NVM_DEV_STARTER_VERSION 0x18 -#define I40E_SR_NVM_WAKE_ON_LAN 0x19 -#define I40E_SR_ALTERNATE_SAN_MAC_ADDRESS_PTR 0x27 -#define I40E_SR_NVM_EETRACK_LO 0x2D -#define I40E_SR_NVM_EETRACK_HI 0x2E -#define I40E_SR_VPD_PTR 0x2F -#define I40E_SR_PCIE_ALT_AUTO_LOAD_PTR 0x3E -#define I40E_SR_SW_CHECKSUM_WORD 0x3F - -/* Auxiliary field, mask and shift definition for Shadow RAM and NVM Flash */ -#define I40E_SR_VPD_MODULE_MAX_SIZE 1024 -#define I40E_SR_PCIE_ALT_MODULE_MAX_SIZE 1024 -#define I40E_SR_CONTROL_WORD_1_SHIFT 0x06 -#define I40E_SR_CONTROL_WORD_1_MASK (0x03 << I40E_SR_CONTROL_WORD_1_SHIFT) -#define I40E_SR_CONTROL_WORD_1_NVM_BANK_VALID BIT(5) -#define I40E_SR_NVM_MAP_STRUCTURE_TYPE BIT(12) -#define I40E_PTR_TYPE BIT(15) - -/* Shadow RAM related */ -#define I40E_SR_SECTOR_SIZE_IN_WORDS 0x800 -#define I40E_SR_WORDS_IN_1KB 512 -/* Checksum should be calculated such that after adding all the words, - * including the checksum word itself, the sum should be 0xBABA. - */ -#define I40E_SR_SW_CHECKSUM_BASE 0xBABA - -#define I40E_SRRD_SRCTL_ATTEMPTS 100000 - -enum i40e_switch_element_types { - I40E_SWITCH_ELEMENT_TYPE_MAC = 1, - I40E_SWITCH_ELEMENT_TYPE_PF = 2, - I40E_SWITCH_ELEMENT_TYPE_VF = 3, - I40E_SWITCH_ELEMENT_TYPE_EMP = 4, - I40E_SWITCH_ELEMENT_TYPE_BMC = 6, - I40E_SWITCH_ELEMENT_TYPE_PE = 16, - I40E_SWITCH_ELEMENT_TYPE_VEB = 17, - I40E_SWITCH_ELEMENT_TYPE_PA = 18, - I40E_SWITCH_ELEMENT_TYPE_VSI = 19, -}; - -/* Supported EtherType filters */ -enum i40e_ether_type_index { - I40E_ETHER_TYPE_1588 = 0, - I40E_ETHER_TYPE_FIP = 1, - I40E_ETHER_TYPE_OUI_EXTENDED = 2, - I40E_ETHER_TYPE_MAC_CONTROL = 3, - I40E_ETHER_TYPE_LLDP = 4, - I40E_ETHER_TYPE_EVB_PROTOCOL1 = 5, - I40E_ETHER_TYPE_EVB_PROTOCOL2 = 6, - I40E_ETHER_TYPE_QCN_CNM = 7, - I40E_ETHER_TYPE_8021X = 8, - I40E_ETHER_TYPE_ARP = 9, - I40E_ETHER_TYPE_RSV1 = 10, - I40E_ETHER_TYPE_RSV2 = 11, -}; - -/* Filter context base size is 1K */ -#define I40E_HASH_FILTER_BASE_SIZE 1024 -/* Supported Hash filter values */ -enum i40e_hash_filter_size { - I40E_HASH_FILTER_SIZE_1K = 0, - I40E_HASH_FILTER_SIZE_2K = 1, - I40E_HASH_FILTER_SIZE_4K = 2, - I40E_HASH_FILTER_SIZE_8K = 3, - I40E_HASH_FILTER_SIZE_16K = 4, - I40E_HASH_FILTER_SIZE_32K = 5, - I40E_HASH_FILTER_SIZE_64K = 6, - I40E_HASH_FILTER_SIZE_128K = 7, - I40E_HASH_FILTER_SIZE_256K = 8, - I40E_HASH_FILTER_SIZE_512K = 9, - I40E_HASH_FILTER_SIZE_1M = 10, -}; - -/* DMA context base size is 0.5K */ -#define I40E_DMA_CNTX_BASE_SIZE 512 -/* Supported DMA context values */ -enum i40e_dma_cntx_size { - I40E_DMA_CNTX_SIZE_512 = 0, - I40E_DMA_CNTX_SIZE_1K = 1, - I40E_DMA_CNTX_SIZE_2K = 2, - I40E_DMA_CNTX_SIZE_4K = 3, - I40E_DMA_CNTX_SIZE_8K = 4, - I40E_DMA_CNTX_SIZE_16K = 5, - I40E_DMA_CNTX_SIZE_32K = 6, - I40E_DMA_CNTX_SIZE_64K = 7, - I40E_DMA_CNTX_SIZE_128K = 8, - I40E_DMA_CNTX_SIZE_256K = 9, -}; - -/* Supported Hash look up table (LUT) sizes */ -enum i40e_hash_lut_size { - I40E_HASH_LUT_SIZE_128 = 0, - I40E_HASH_LUT_SIZE_512 = 1, -}; - -/* Structure to hold a per PF filter control settings */ -struct i40e_filter_control_settings { - /* number of PE Quad Hash filter buckets */ - enum i40e_hash_filter_size pe_filt_num; - /* number of PE Quad Hash contexts */ - enum i40e_dma_cntx_size pe_cntx_num; - /* number of FCoE filter buckets */ - enum i40e_hash_filter_size fcoe_filt_num; - /* number of FCoE DDP contexts */ - enum i40e_dma_cntx_size fcoe_cntx_num; - /* size of the Hash LUT */ - enum i40e_hash_lut_size hash_lut_size; - /* enable FDIR filters for PF and its VFs */ - bool enable_fdir; - /* enable Ethertype filters for PF and its VFs */ - bool enable_ethtype; - /* enable MAC/VLAN filters for PF and its VFs */ - bool enable_macvlan; -}; - -/* Structure to hold device level control filter counts */ -struct i40e_control_filter_stats { - u16 mac_etype_used; /* Used perfect match MAC/EtherType filters */ - u16 etype_used; /* Used perfect EtherType filters */ - u16 mac_etype_free; /* Un-used perfect match MAC/EtherType filters */ - u16 etype_free; /* Un-used perfect EtherType filters */ -}; - -enum i40e_reset_type { - I40E_RESET_POR = 0, - I40E_RESET_CORER = 1, - I40E_RESET_GLOBR = 2, - I40E_RESET_EMPR = 3, -}; - -/* IEEE 802.1AB LLDP Agent Variables from NVM */ -#define I40E_NVM_LLDP_CFG_PTR 0x06 -#define I40E_SR_LLDP_CFG_PTR 0x31 - -/* RSS Hash Table Size */ -#define I40E_PFQF_CTL_0_HASHLUTSIZE_512 0x00010000 - -/* INPUT SET MASK for RSS, flow director and flexible payload */ -#define I40E_FD_INSET_L3_SRC_SHIFT 47 -#define I40E_FD_INSET_L3_SRC_WORD_MASK (0x3ULL << \ - I40E_FD_INSET_L3_SRC_SHIFT) -#define I40E_FD_INSET_L3_DST_SHIFT 35 -#define I40E_FD_INSET_L3_DST_WORD_MASK (0x3ULL << \ - I40E_FD_INSET_L3_DST_SHIFT) -#define I40E_FD_INSET_L4_SRC_SHIFT 34 -#define I40E_FD_INSET_L4_SRC_WORD_MASK (0x1ULL << \ - I40E_FD_INSET_L4_SRC_SHIFT) -#define I40E_FD_INSET_L4_DST_SHIFT 33 -#define I40E_FD_INSET_L4_DST_WORD_MASK (0x1ULL << \ - I40E_FD_INSET_L4_DST_SHIFT) -#define I40E_FD_INSET_VERIFY_TAG_SHIFT 31 -#define I40E_FD_INSET_VERIFY_TAG_WORD_MASK (0x3ULL << \ - I40E_FD_INSET_VERIFY_TAG_SHIFT) - -#define I40E_FD_INSET_FLEX_WORD50_SHIFT 17 -#define I40E_FD_INSET_FLEX_WORD50_MASK (0x1ULL << \ - I40E_FD_INSET_FLEX_WORD50_SHIFT) -#define I40E_FD_INSET_FLEX_WORD51_SHIFT 16 -#define I40E_FD_INSET_FLEX_WORD51_MASK (0x1ULL << \ - I40E_FD_INSET_FLEX_WORD51_SHIFT) -#define I40E_FD_INSET_FLEX_WORD52_SHIFT 15 -#define I40E_FD_INSET_FLEX_WORD52_MASK (0x1ULL << \ - I40E_FD_INSET_FLEX_WORD52_SHIFT) -#define I40E_FD_INSET_FLEX_WORD53_SHIFT 14 -#define I40E_FD_INSET_FLEX_WORD53_MASK (0x1ULL << \ - I40E_FD_INSET_FLEX_WORD53_SHIFT) -#define I40E_FD_INSET_FLEX_WORD54_SHIFT 13 -#define I40E_FD_INSET_FLEX_WORD54_MASK (0x1ULL << \ - I40E_FD_INSET_FLEX_WORD54_SHIFT) -#define I40E_FD_INSET_FLEX_WORD55_SHIFT 12 -#define I40E_FD_INSET_FLEX_WORD55_MASK (0x1ULL << \ - I40E_FD_INSET_FLEX_WORD55_SHIFT) -#define I40E_FD_INSET_FLEX_WORD56_SHIFT 11 -#define I40E_FD_INSET_FLEX_WORD56_MASK (0x1ULL << \ - I40E_FD_INSET_FLEX_WORD56_SHIFT) -#define I40E_FD_INSET_FLEX_WORD57_SHIFT 10 -#define I40E_FD_INSET_FLEX_WORD57_MASK (0x1ULL << \ - I40E_FD_INSET_FLEX_WORD57_SHIFT) - -/* Version format for Dynamic Device Personalization(DDP) */ -struct i40e_ddp_version { - u8 major; - u8 minor; - u8 update; - u8 draft; -}; - -#define I40E_DDP_NAME_SIZE 32 - -/* Package header */ -struct i40e_package_header { - struct i40e_ddp_version version; - u32 segment_count; - u32 segment_offset[1]; -}; - -/* Generic segment header */ -struct i40e_generic_seg_header { -#define SEGMENT_TYPE_METADATA 0x00000001 -#define SEGMENT_TYPE_NOTES 0x00000002 -#define SEGMENT_TYPE_I40E 0x00000011 -#define SEGMENT_TYPE_X722 0x00000012 - u32 type; - struct i40e_ddp_version version; - u32 size; - char name[I40E_DDP_NAME_SIZE]; -}; - -struct i40e_metadata_segment { - struct i40e_generic_seg_header header; - struct i40e_ddp_version version; - u32 track_id; - char name[I40E_DDP_NAME_SIZE]; -}; - -struct i40e_device_id_entry { - u32 vendor_dev_id; - u32 sub_vendor_dev_id; -}; - -struct i40e_profile_segment { - struct i40e_generic_seg_header header; - struct i40e_ddp_version version; - char name[I40E_DDP_NAME_SIZE]; - u32 device_table_count; - struct i40e_device_id_entry device_table[1]; -}; - -struct i40e_section_table { - u32 section_count; - u32 section_offset[1]; -}; - -struct i40e_profile_section_header { - u16 tbl_size; - u16 data_end; - struct { -#define SECTION_TYPE_INFO 0x00000010 -#define SECTION_TYPE_MMIO 0x00000800 -#define SECTION_TYPE_AQ 0x00000801 -#define SECTION_TYPE_NOTE 0x80000000 -#define SECTION_TYPE_NAME 0x80000001 - u32 type; - u32 offset; - u32 size; - } section; -}; - -struct i40e_profile_info { - u32 track_id; - struct i40e_ddp_version version; - u8 op; -#define I40E_DDP_ADD_TRACKID 0x01 -#define I40E_DDP_REMOVE_TRACKID 0x02 - u8 reserved[7]; - u8 name[I40E_DDP_NAME_SIZE]; -}; -#endif /* _I40E_TYPE_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h deleted file mode 100644 index 96e537a35000..000000000000 --- a/drivers/net/ethernet/intel/i40evf/i40evf.h +++ /dev/null @@ -1,427 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 2013 - 2018 Intel Corporation. */ - -#ifndef _I40EVF_H_ -#define _I40EVF_H_ - -#include <linux/module.h> -#include <linux/pci.h> -#include <linux/aer.h> -#include <linux/netdevice.h> -#include <linux/vmalloc.h> -#include <linux/interrupt.h> -#include <linux/ethtool.h> -#include <linux/if_vlan.h> -#include <linux/ip.h> -#include <linux/tcp.h> -#include <linux/sctp.h> -#include <linux/ipv6.h> -#include <linux/kernel.h> -#include <linux/bitops.h> -#include <linux/timer.h> -#include <linux/workqueue.h> -#include <linux/wait.h> -#include <linux/delay.h> -#include <linux/gfp.h> -#include <linux/skbuff.h> -#include <linux/dma-mapping.h> -#include <linux/etherdevice.h> -#include <linux/socket.h> -#include <linux/jiffies.h> -#include <net/ip6_checksum.h> -#include <net/pkt_cls.h> -#include <net/udp.h> -#include <net/tc_act/tc_gact.h> -#include <net/tc_act/tc_mirred.h> - -#include "i40e_type.h" -#include <linux/avf/virtchnl.h> -#include "i40e_txrx.h" - -#define DEFAULT_DEBUG_LEVEL_SHIFT 3 -#define PFX "i40evf: " - -/* VSI state flags shared with common code */ -enum i40evf_vsi_state_t { - __I40E_VSI_DOWN, - /* This must be last as it determines the size of the BITMAP */ - __I40E_VSI_STATE_SIZE__, -}; - -/* dummy struct to make common code less painful */ -struct i40e_vsi { - struct i40evf_adapter *back; - struct net_device *netdev; - unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; - u16 seid; - u16 id; - DECLARE_BITMAP(state, __I40E_VSI_STATE_SIZE__); - int base_vector; - u16 work_limit; - u16 qs_handle; - void *priv; /* client driver data reference. */ -}; - -/* How many Rx Buffers do we bundle into one write to the hardware ? */ -#define I40EVF_RX_BUFFER_WRITE 16 /* Must be power of 2 */ -#define I40EVF_DEFAULT_TXD 512 -#define I40EVF_DEFAULT_RXD 512 -#define I40EVF_MAX_TXD 4096 -#define I40EVF_MIN_TXD 64 -#define I40EVF_MAX_RXD 4096 -#define I40EVF_MIN_RXD 64 -#define I40EVF_REQ_DESCRIPTOR_MULTIPLE 32 -#define I40EVF_MAX_AQ_BUF_SIZE 4096 -#define I40EVF_AQ_LEN 32 -#define I40EVF_AQ_MAX_ERR 20 /* times to try before resetting AQ */ - -#define MAXIMUM_ETHERNET_VLAN_SIZE (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN) - -#define I40E_RX_DESC(R, i) (&(((union i40e_32byte_rx_desc *)((R)->desc))[i])) -#define I40E_TX_DESC(R, i) (&(((struct i40e_tx_desc *)((R)->desc))[i])) -#define I40E_TX_CTXTDESC(R, i) \ - (&(((struct i40e_tx_context_desc *)((R)->desc))[i])) -#define I40EVF_MAX_REQ_QUEUES 4 - -#define I40EVF_HKEY_ARRAY_SIZE ((I40E_VFQF_HKEY_MAX_INDEX + 1) * 4) -#define I40EVF_HLUT_ARRAY_SIZE ((I40E_VFQF_HLUT_MAX_INDEX + 1) * 4) -#define I40EVF_MBPS_DIVISOR 125000 /* divisor to convert to Mbps */ - -/* MAX_MSIX_Q_VECTORS of these are allocated, - * but we only use one per queue-specific vector. - */ -struct i40e_q_vector { - struct i40evf_adapter *adapter; - struct i40e_vsi *vsi; - struct napi_struct napi; - struct i40e_ring_container rx; - struct i40e_ring_container tx; - u32 ring_mask; - u8 itr_countdown; /* when 0 should adjust adaptive ITR */ - u8 num_ringpairs; /* total number of ring pairs in vector */ - u16 v_idx; /* index in the vsi->q_vector array. */ - u16 reg_idx; /* register index of the interrupt */ - char name[IFNAMSIZ + 15]; - bool arm_wb_state; - cpumask_t affinity_mask; - struct irq_affinity_notify affinity_notify; -}; - -/* Helper macros to switch between ints/sec and what the register uses. - * And yes, it's the same math going both ways. The lowest value - * supported by all of the i40e hardware is 8. - */ -#define EITR_INTS_PER_SEC_TO_REG(_eitr) \ - ((_eitr) ? (1000000000 / ((_eitr) * 256)) : 8) -#define EITR_REG_TO_INTS_PER_SEC EITR_INTS_PER_SEC_TO_REG - -#define I40EVF_DESC_UNUSED(R) \ - ((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \ - (R)->next_to_clean - (R)->next_to_use - 1) - -#define I40EVF_RX_DESC_ADV(R, i) \ - (&(((union i40e_adv_rx_desc *)((R).desc))[i])) -#define I40EVF_TX_DESC_ADV(R, i) \ - (&(((union i40e_adv_tx_desc *)((R).desc))[i])) -#define I40EVF_TX_CTXTDESC_ADV(R, i) \ - (&(((struct i40e_adv_tx_context_desc *)((R).desc))[i])) - -#define OTHER_VECTOR 1 -#define NONQ_VECS (OTHER_VECTOR) - -#define MIN_MSIX_Q_VECTORS 1 -#define MIN_MSIX_COUNT (MIN_MSIX_Q_VECTORS + NONQ_VECS) - -#define I40EVF_QUEUE_END_OF_LIST 0x7FF -#define I40EVF_FREE_VECTOR 0x7FFF -struct i40evf_mac_filter { - struct list_head list; - u8 macaddr[ETH_ALEN]; - bool remove; /* filter needs to be removed */ - bool add; /* filter needs to be added */ -}; - -struct i40evf_vlan_filter { - struct list_head list; - u16 vlan; - bool remove; /* filter needs to be removed */ - bool add; /* filter needs to be added */ -}; - -#define I40EVF_MAX_TRAFFIC_CLASS 4 -/* State of traffic class creation */ -enum i40evf_tc_state_t { - __I40EVF_TC_INVALID, /* no traffic class, default state */ - __I40EVF_TC_RUNNING, /* traffic classes have been created */ -}; - -/* channel info */ -struct i40evf_channel_config { - struct virtchnl_channel_info ch_info[I40EVF_MAX_TRAFFIC_CLASS]; - enum i40evf_tc_state_t state; - u8 total_qps; -}; - -/* State of cloud filter */ -enum i40evf_cloud_filter_state_t { - __I40EVF_CF_INVALID, /* cloud filter not added */ - __I40EVF_CF_ADD_PENDING, /* cloud filter pending add by the PF */ - __I40EVF_CF_DEL_PENDING, /* cloud filter pending del by the PF */ - __I40EVF_CF_ACTIVE, /* cloud filter is active */ -}; - -/* Driver state. The order of these is important! */ -enum i40evf_state_t { - __I40EVF_STARTUP, /* driver loaded, probe complete */ - __I40EVF_REMOVE, /* driver is being unloaded */ - __I40EVF_INIT_VERSION_CHECK, /* aq msg sent, awaiting reply */ - __I40EVF_INIT_GET_RESOURCES, /* aq msg sent, awaiting reply */ - __I40EVF_INIT_SW, /* got resources, setting up structs */ - __I40EVF_RESETTING, /* in reset */ - /* Below here, watchdog is running */ - __I40EVF_DOWN, /* ready, can be opened */ - __I40EVF_DOWN_PENDING, /* descending, waiting for watchdog */ - __I40EVF_TESTING, /* in ethtool self-test */ - __I40EVF_RUNNING, /* opened, working */ -}; - -enum i40evf_critical_section_t { - __I40EVF_IN_CRITICAL_TASK, /* cannot be interrupted */ - __I40EVF_IN_CLIENT_TASK, - __I40EVF_IN_REMOVE_TASK, /* device being removed */ -}; - -#define I40EVF_CLOUD_FIELD_OMAC 0x01 -#define I40EVF_CLOUD_FIELD_IMAC 0x02 -#define I40EVF_CLOUD_FIELD_IVLAN 0x04 -#define I40EVF_CLOUD_FIELD_TEN_ID 0x08 -#define I40EVF_CLOUD_FIELD_IIP 0x10 - -#define I40EVF_CF_FLAGS_OMAC I40EVF_CLOUD_FIELD_OMAC -#define I40EVF_CF_FLAGS_IMAC I40EVF_CLOUD_FIELD_IMAC -#define I40EVF_CF_FLAGS_IMAC_IVLAN (I40EVF_CLOUD_FIELD_IMAC |\ - I40EVF_CLOUD_FIELD_IVLAN) -#define I40EVF_CF_FLAGS_IMAC_TEN_ID (I40EVF_CLOUD_FIELD_IMAC |\ - I40EVF_CLOUD_FIELD_TEN_ID) -#define I40EVF_CF_FLAGS_OMAC_TEN_ID_IMAC (I40EVF_CLOUD_FIELD_OMAC |\ - I40EVF_CLOUD_FIELD_IMAC |\ - I40EVF_CLOUD_FIELD_TEN_ID) -#define I40EVF_CF_FLAGS_IMAC_IVLAN_TEN_ID (I40EVF_CLOUD_FIELD_IMAC |\ - I40EVF_CLOUD_FIELD_IVLAN |\ - I40EVF_CLOUD_FIELD_TEN_ID) -#define I40EVF_CF_FLAGS_IIP I40E_CLOUD_FIELD_IIP - -/* bookkeeping of cloud filters */ -struct i40evf_cloud_filter { - enum i40evf_cloud_filter_state_t state; - struct list_head list; - struct virtchnl_filter f; - unsigned long cookie; - bool del; /* filter needs to be deleted */ - bool add; /* filter needs to be added */ -}; - -/* board specific private data structure */ -struct i40evf_adapter { - struct timer_list watchdog_timer; - struct work_struct reset_task; - struct work_struct adminq_task; - struct delayed_work client_task; - struct delayed_work init_task; - wait_queue_head_t down_waitqueue; - struct i40e_q_vector *q_vectors; - struct list_head vlan_filter_list; - struct list_head mac_filter_list; - /* Lock to protect accesses to MAC and VLAN lists */ - spinlock_t mac_vlan_list_lock; - char misc_vector_name[IFNAMSIZ + 9]; - int num_active_queues; - int num_req_queues; - - /* TX */ - struct i40e_ring *tx_rings; - u32 tx_timeout_count; - u32 tx_desc_count; - - /* RX */ - struct i40e_ring *rx_rings; - u64 hw_csum_rx_error; - u32 rx_desc_count; - int num_msix_vectors; - int num_iwarp_msix; - int iwarp_base_vector; - u32 client_pending; - struct i40e_client_instance *cinst; - struct msix_entry *msix_entries; - - u32 flags; -#define I40EVF_FLAG_RX_CSUM_ENABLED BIT(0) -#define I40EVF_FLAG_PF_COMMS_FAILED BIT(3) -#define I40EVF_FLAG_RESET_PENDING BIT(4) -#define I40EVF_FLAG_RESET_NEEDED BIT(5) -#define I40EVF_FLAG_WB_ON_ITR_CAPABLE BIT(6) -#define I40EVF_FLAG_ADDR_SET_BY_PF BIT(8) -#define I40EVF_FLAG_SERVICE_CLIENT_REQUESTED BIT(9) -#define I40EVF_FLAG_CLIENT_NEEDS_OPEN BIT(10) -#define I40EVF_FLAG_CLIENT_NEEDS_CLOSE BIT(11) -#define I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS BIT(12) -#define I40EVF_FLAG_PROMISC_ON BIT(13) -#define I40EVF_FLAG_ALLMULTI_ON BIT(14) -#define I40EVF_FLAG_LEGACY_RX BIT(15) -#define I40EVF_FLAG_REINIT_ITR_NEEDED BIT(16) -#define I40EVF_FLAG_QUEUES_DISABLED BIT(17) -/* duplicates for common code */ -#define I40E_FLAG_DCB_ENABLED 0 -#define I40E_FLAG_RX_CSUM_ENABLED I40EVF_FLAG_RX_CSUM_ENABLED -#define I40E_FLAG_LEGACY_RX I40EVF_FLAG_LEGACY_RX - /* flags for admin queue service task */ - u32 aq_required; -#define I40EVF_FLAG_AQ_ENABLE_QUEUES BIT(0) -#define I40EVF_FLAG_AQ_DISABLE_QUEUES BIT(1) -#define I40EVF_FLAG_AQ_ADD_MAC_FILTER BIT(2) -#define I40EVF_FLAG_AQ_ADD_VLAN_FILTER BIT(3) -#define I40EVF_FLAG_AQ_DEL_MAC_FILTER BIT(4) -#define I40EVF_FLAG_AQ_DEL_VLAN_FILTER BIT(5) -#define I40EVF_FLAG_AQ_CONFIGURE_QUEUES BIT(6) -#define I40EVF_FLAG_AQ_MAP_VECTORS BIT(7) -#define I40EVF_FLAG_AQ_HANDLE_RESET BIT(8) -#define I40EVF_FLAG_AQ_CONFIGURE_RSS BIT(9) /* direct AQ config */ -#define I40EVF_FLAG_AQ_GET_CONFIG BIT(10) -/* Newer style, RSS done by the PF so we can ignore hardware vagaries. */ -#define I40EVF_FLAG_AQ_GET_HENA BIT(11) -#define I40EVF_FLAG_AQ_SET_HENA BIT(12) -#define I40EVF_FLAG_AQ_SET_RSS_KEY BIT(13) -#define I40EVF_FLAG_AQ_SET_RSS_LUT BIT(14) -#define I40EVF_FLAG_AQ_REQUEST_PROMISC BIT(15) -#define I40EVF_FLAG_AQ_RELEASE_PROMISC BIT(16) -#define I40EVF_FLAG_AQ_REQUEST_ALLMULTI BIT(17) -#define I40EVF_FLAG_AQ_RELEASE_ALLMULTI BIT(18) -#define I40EVF_FLAG_AQ_ENABLE_VLAN_STRIPPING BIT(19) -#define I40EVF_FLAG_AQ_DISABLE_VLAN_STRIPPING BIT(20) -#define I40EVF_FLAG_AQ_ENABLE_CHANNELS BIT(21) -#define I40EVF_FLAG_AQ_DISABLE_CHANNELS BIT(22) -#define I40EVF_FLAG_AQ_ADD_CLOUD_FILTER BIT(23) -#define I40EVF_FLAG_AQ_DEL_CLOUD_FILTER BIT(24) - - /* OS defined structs */ - struct net_device *netdev; - struct pci_dev *pdev; - - struct i40e_hw hw; /* defined in i40e_type.h */ - - enum i40evf_state_t state; - unsigned long crit_section; - - struct work_struct watchdog_task; - bool netdev_registered; - bool link_up; - enum virtchnl_link_speed link_speed; - enum virtchnl_ops current_op; -#define CLIENT_ALLOWED(_a) ((_a)->vf_res ? \ - (_a)->vf_res->vf_cap_flags & \ - VIRTCHNL_VF_OFFLOAD_IWARP : \ - 0) -#define CLIENT_ENABLED(_a) ((_a)->cinst) -/* RSS by the PF should be preferred over RSS via other methods. */ -#define RSS_PF(_a) ((_a)->vf_res->vf_cap_flags & \ - VIRTCHNL_VF_OFFLOAD_RSS_PF) -#define RSS_AQ(_a) ((_a)->vf_res->vf_cap_flags & \ - VIRTCHNL_VF_OFFLOAD_RSS_AQ) -#define RSS_REG(_a) (!((_a)->vf_res->vf_cap_flags & \ - (VIRTCHNL_VF_OFFLOAD_RSS_AQ | \ - VIRTCHNL_VF_OFFLOAD_RSS_PF))) -#define VLAN_ALLOWED(_a) ((_a)->vf_res->vf_cap_flags & \ - VIRTCHNL_VF_OFFLOAD_VLAN) - struct virtchnl_vf_resource *vf_res; /* incl. all VSIs */ - struct virtchnl_vsi_resource *vsi_res; /* our LAN VSI */ - struct virtchnl_version_info pf_version; -#define PF_IS_V11(_a) (((_a)->pf_version.major == 1) && \ - ((_a)->pf_version.minor == 1)) - u16 msg_enable; - struct i40e_eth_stats current_stats; - struct i40e_vsi vsi; - u32 aq_wait_count; - /* RSS stuff */ - u64 hena; - u16 rss_key_size; - u16 rss_lut_size; - u8 *rss_key; - u8 *rss_lut; - /* ADQ related members */ - struct i40evf_channel_config ch_config; - u8 num_tc; - struct list_head cloud_filter_list; - /* lock to protest access to the cloud filter list */ - spinlock_t cloud_filter_list_lock; - u16 num_cloud_filters; -}; - - -/* Ethtool Private Flags */ - -/* lan device */ -struct i40e_device { - struct list_head list; - struct i40evf_adapter *vf; -}; - -/* needed by i40evf_ethtool.c */ -extern char i40evf_driver_name[]; -extern const char i40evf_driver_version[]; - -int i40evf_up(struct i40evf_adapter *adapter); -void i40evf_down(struct i40evf_adapter *adapter); -int i40evf_process_config(struct i40evf_adapter *adapter); -void i40evf_schedule_reset(struct i40evf_adapter *adapter); -void i40evf_reset(struct i40evf_adapter *adapter); -void i40evf_set_ethtool_ops(struct net_device *netdev); -void i40evf_update_stats(struct i40evf_adapter *adapter); -void i40evf_reset_interrupt_capability(struct i40evf_adapter *adapter); -int i40evf_init_interrupt_scheme(struct i40evf_adapter *adapter); -void i40evf_irq_enable_queues(struct i40evf_adapter *adapter, u32 mask); -void i40evf_free_all_tx_resources(struct i40evf_adapter *adapter); -void i40evf_free_all_rx_resources(struct i40evf_adapter *adapter); - -void i40e_napi_add_all(struct i40evf_adapter *adapter); -void i40e_napi_del_all(struct i40evf_adapter *adapter); - -int i40evf_send_api_ver(struct i40evf_adapter *adapter); -int i40evf_verify_api_ver(struct i40evf_adapter *adapter); -int i40evf_send_vf_config_msg(struct i40evf_adapter *adapter); -int i40evf_get_vf_config(struct i40evf_adapter *adapter); -void i40evf_irq_enable(struct i40evf_adapter *adapter, bool flush); -void i40evf_configure_queues(struct i40evf_adapter *adapter); -void i40evf_deconfigure_queues(struct i40evf_adapter *adapter); -void i40evf_enable_queues(struct i40evf_adapter *adapter); -void i40evf_disable_queues(struct i40evf_adapter *adapter); -void i40evf_map_queues(struct i40evf_adapter *adapter); -int i40evf_request_queues(struct i40evf_adapter *adapter, int num); -void i40evf_add_ether_addrs(struct i40evf_adapter *adapter); -void i40evf_del_ether_addrs(struct i40evf_adapter *adapter); -void i40evf_add_vlans(struct i40evf_adapter *adapter); -void i40evf_del_vlans(struct i40evf_adapter *adapter); -void i40evf_set_promiscuous(struct i40evf_adapter *adapter, int flags); -void i40evf_request_stats(struct i40evf_adapter *adapter); -void i40evf_request_reset(struct i40evf_adapter *adapter); -void i40evf_get_hena(struct i40evf_adapter *adapter); -void i40evf_set_hena(struct i40evf_adapter *adapter); -void i40evf_set_rss_key(struct i40evf_adapter *adapter); -void i40evf_set_rss_lut(struct i40evf_adapter *adapter); -void i40evf_enable_vlan_stripping(struct i40evf_adapter *adapter); -void i40evf_disable_vlan_stripping(struct i40evf_adapter *adapter); -void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, - enum virtchnl_ops v_opcode, - i40e_status v_retval, u8 *msg, u16 msglen); -int i40evf_config_rss(struct i40evf_adapter *adapter); -int i40evf_lan_add_device(struct i40evf_adapter *adapter); -int i40evf_lan_del_device(struct i40evf_adapter *adapter); -void i40evf_client_subtask(struct i40evf_adapter *adapter); -void i40evf_notify_client_message(struct i40e_vsi *vsi, u8 *msg, u16 len); -void i40evf_notify_client_l2_params(struct i40e_vsi *vsi); -void i40evf_notify_client_open(struct i40e_vsi *vsi); -void i40evf_notify_client_close(struct i40e_vsi *vsi, bool reset); -void i40evf_enable_channels(struct i40evf_adapter *adapter); -void i40evf_disable_channels(struct i40evf_adapter *adapter); -void i40evf_add_cloud_filter(struct i40evf_adapter *adapter); -void i40evf_del_cloud_filter(struct i40evf_adapter *adapter); -#endif /* _I40EVF_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c deleted file mode 100644 index 69efe0aec76a..000000000000 --- a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c +++ /dev/null @@ -1,820 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ - -/* ethtool support for i40evf */ -#include "i40evf.h" - -#include <linux/uaccess.h> - -struct i40evf_stats { - char stat_string[ETH_GSTRING_LEN]; - int stat_offset; -}; - -#define I40EVF_STAT(_name, _stat) { \ - .stat_string = _name, \ - .stat_offset = offsetof(struct i40evf_adapter, _stat) \ -} - -/* All stats are u64, so we don't need to track the size of the field. */ -static const struct i40evf_stats i40evf_gstrings_stats[] = { - I40EVF_STAT("rx_bytes", current_stats.rx_bytes), - I40EVF_STAT("rx_unicast", current_stats.rx_unicast), - I40EVF_STAT("rx_multicast", current_stats.rx_multicast), - I40EVF_STAT("rx_broadcast", current_stats.rx_broadcast), - I40EVF_STAT("rx_discards", current_stats.rx_discards), - I40EVF_STAT("rx_unknown_protocol", current_stats.rx_unknown_protocol), - I40EVF_STAT("tx_bytes", current_stats.tx_bytes), - I40EVF_STAT("tx_unicast", current_stats.tx_unicast), - I40EVF_STAT("tx_multicast", current_stats.tx_multicast), - I40EVF_STAT("tx_broadcast", current_stats.tx_broadcast), - I40EVF_STAT("tx_discards", current_stats.tx_discards), - I40EVF_STAT("tx_errors", current_stats.tx_errors), -}; - -#define I40EVF_GLOBAL_STATS_LEN ARRAY_SIZE(i40evf_gstrings_stats) -#define I40EVF_QUEUE_STATS_LEN(_dev) \ - (((struct i40evf_adapter *)\ - netdev_priv(_dev))->num_active_queues \ - * 2 * (sizeof(struct i40e_queue_stats) / sizeof(u64))) -#define I40EVF_STATS_LEN(_dev) \ - (I40EVF_GLOBAL_STATS_LEN + I40EVF_QUEUE_STATS_LEN(_dev)) - -/* For now we have one and only one private flag and it is only defined - * when we have support for the SKIP_CPU_SYNC DMA attribute. Instead - * of leaving all this code sitting around empty we will strip it unless - * our one private flag is actually available. - */ -struct i40evf_priv_flags { - char flag_string[ETH_GSTRING_LEN]; - u32 flag; - bool read_only; -}; - -#define I40EVF_PRIV_FLAG(_name, _flag, _read_only) { \ - .flag_string = _name, \ - .flag = _flag, \ - .read_only = _read_only, \ -} - -static const struct i40evf_priv_flags i40evf_gstrings_priv_flags[] = { - I40EVF_PRIV_FLAG("legacy-rx", I40EVF_FLAG_LEGACY_RX, 0), -}; - -#define I40EVF_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40evf_gstrings_priv_flags) - -/** - * i40evf_get_link_ksettings - Get Link Speed and Duplex settings - * @netdev: network interface device structure - * @cmd: ethtool command - * - * Reports speed/duplex settings. Because this is a VF, we don't know what - * kind of link we really have, so we fake it. - **/ -static int i40evf_get_link_ksettings(struct net_device *netdev, - struct ethtool_link_ksettings *cmd) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - - ethtool_link_ksettings_zero_link_mode(cmd, supported); - cmd->base.autoneg = AUTONEG_DISABLE; - cmd->base.port = PORT_NONE; - /* Set speed and duplex */ - switch (adapter->link_speed) { - case I40E_LINK_SPEED_40GB: - cmd->base.speed = SPEED_40000; - break; - case I40E_LINK_SPEED_25GB: -#ifdef SPEED_25000 - cmd->base.speed = SPEED_25000; -#else - netdev_info(netdev, - "Speed is 25G, display not supported by this version of ethtool.\n"); -#endif - break; - case I40E_LINK_SPEED_20GB: - cmd->base.speed = SPEED_20000; - break; - case I40E_LINK_SPEED_10GB: - cmd->base.speed = SPEED_10000; - break; - case I40E_LINK_SPEED_1GB: - cmd->base.speed = SPEED_1000; - break; - case I40E_LINK_SPEED_100MB: - cmd->base.speed = SPEED_100; - break; - default: - break; - } - cmd->base.duplex = DUPLEX_FULL; - - return 0; -} - -/** - * i40evf_get_sset_count - Get length of string set - * @netdev: network interface device structure - * @sset: id of string set - * - * Reports size of string table. This driver only supports - * strings for statistics. - **/ -static int i40evf_get_sset_count(struct net_device *netdev, int sset) -{ - if (sset == ETH_SS_STATS) - return I40EVF_STATS_LEN(netdev); - else if (sset == ETH_SS_PRIV_FLAGS) - return I40EVF_PRIV_FLAGS_STR_LEN; - else - return -EINVAL; -} - -/** - * i40evf_get_ethtool_stats - report device statistics - * @netdev: network interface device structure - * @stats: ethtool statistics structure - * @data: pointer to data buffer - * - * All statistics are added to the data buffer as an array of u64. - **/ -static void i40evf_get_ethtool_stats(struct net_device *netdev, - struct ethtool_stats *stats, u64 *data) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - unsigned int i, j; - char *p; - - for (i = 0; i < I40EVF_GLOBAL_STATS_LEN; i++) { - p = (char *)adapter + i40evf_gstrings_stats[i].stat_offset; - data[i] = *(u64 *)p; - } - for (j = 0; j < adapter->num_active_queues; j++) { - data[i++] = adapter->tx_rings[j].stats.packets; - data[i++] = adapter->tx_rings[j].stats.bytes; - } - for (j = 0; j < adapter->num_active_queues; j++) { - data[i++] = adapter->rx_rings[j].stats.packets; - data[i++] = adapter->rx_rings[j].stats.bytes; - } -} - -/** - * i40evf_get_strings - Get string set - * @netdev: network interface device structure - * @sset: id of string set - * @data: buffer for string data - * - * Builds stats string table. - **/ -static void i40evf_get_strings(struct net_device *netdev, u32 sset, u8 *data) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - u8 *p = data; - int i; - - if (sset == ETH_SS_STATS) { - for (i = 0; i < (int)I40EVF_GLOBAL_STATS_LEN; i++) { - memcpy(p, i40evf_gstrings_stats[i].stat_string, - ETH_GSTRING_LEN); - p += ETH_GSTRING_LEN; - } - for (i = 0; i < adapter->num_active_queues; i++) { - snprintf(p, ETH_GSTRING_LEN, "tx-%u.packets", i); - p += ETH_GSTRING_LEN; - snprintf(p, ETH_GSTRING_LEN, "tx-%u.bytes", i); - p += ETH_GSTRING_LEN; - } - for (i = 0; i < adapter->num_active_queues; i++) { - snprintf(p, ETH_GSTRING_LEN, "rx-%u.packets", i); - p += ETH_GSTRING_LEN; - snprintf(p, ETH_GSTRING_LEN, "rx-%u.bytes", i); - p += ETH_GSTRING_LEN; - } - } else if (sset == ETH_SS_PRIV_FLAGS) { - for (i = 0; i < I40EVF_PRIV_FLAGS_STR_LEN; i++) { - snprintf(p, ETH_GSTRING_LEN, "%s", - i40evf_gstrings_priv_flags[i].flag_string); - p += ETH_GSTRING_LEN; - } - } -} - -/** - * i40evf_get_priv_flags - report device private flags - * @netdev: network interface device structure - * - * The get string set count and the string set should be matched for each - * flag returned. Add new strings for each flag to the i40e_gstrings_priv_flags - * array. - * - * Returns a u32 bitmap of flags. - **/ -static u32 i40evf_get_priv_flags(struct net_device *netdev) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - u32 i, ret_flags = 0; - - for (i = 0; i < I40EVF_PRIV_FLAGS_STR_LEN; i++) { - const struct i40evf_priv_flags *priv_flags; - - priv_flags = &i40evf_gstrings_priv_flags[i]; - - if (priv_flags->flag & adapter->flags) - ret_flags |= BIT(i); - } - - return ret_flags; -} - -/** - * i40evf_set_priv_flags - set private flags - * @netdev: network interface device structure - * @flags: bit flags to be set - **/ -static int i40evf_set_priv_flags(struct net_device *netdev, u32 flags) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - u32 orig_flags, new_flags, changed_flags; - u32 i; - - orig_flags = READ_ONCE(adapter->flags); - new_flags = orig_flags; - - for (i = 0; i < I40EVF_PRIV_FLAGS_STR_LEN; i++) { - const struct i40evf_priv_flags *priv_flags; - - priv_flags = &i40evf_gstrings_priv_flags[i]; - - if (flags & BIT(i)) - new_flags |= priv_flags->flag; - else - new_flags &= ~(priv_flags->flag); - - if (priv_flags->read_only && - ((orig_flags ^ new_flags) & ~BIT(i))) - return -EOPNOTSUPP; - } - - /* Before we finalize any flag changes, any checks which we need to - * perform to determine if the new flags will be supported should go - * here... - */ - - /* Compare and exchange the new flags into place. If we failed, that - * is if cmpxchg returns anything but the old value, this means - * something else must have modified the flags variable since we - * copied it. We'll just punt with an error and log something in the - * message buffer. - */ - if (cmpxchg(&adapter->flags, orig_flags, new_flags) != orig_flags) { - dev_warn(&adapter->pdev->dev, - "Unable to update adapter->flags as it was modified by another thread...\n"); - return -EAGAIN; - } - - changed_flags = orig_flags ^ new_flags; - - /* Process any additional changes needed as a result of flag changes. - * The changed_flags value reflects the list of bits that were changed - * in the code above. - */ - - /* issue a reset to force legacy-rx change to take effect */ - if (changed_flags & I40EVF_FLAG_LEGACY_RX) { - if (netif_running(netdev)) { - adapter->flags |= I40EVF_FLAG_RESET_NEEDED; - schedule_work(&adapter->reset_task); - } - } - - return 0; -} - -/** - * i40evf_get_msglevel - Get debug message level - * @netdev: network interface device structure - * - * Returns current debug message level. - **/ -static u32 i40evf_get_msglevel(struct net_device *netdev) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - - return adapter->msg_enable; -} - -/** - * i40evf_set_msglevel - Set debug message level - * @netdev: network interface device structure - * @data: message level - * - * Set current debug message level. Higher values cause the driver to - * be noisier. - **/ -static void i40evf_set_msglevel(struct net_device *netdev, u32 data) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - - if (I40E_DEBUG_USER & data) - adapter->hw.debug_mask = data; - adapter->msg_enable = data; -} - -/** - * i40evf_get_drvinfo - Get driver info - * @netdev: network interface device structure - * @drvinfo: ethool driver info structure - * - * Returns information about the driver and device for display to the user. - **/ -static void i40evf_get_drvinfo(struct net_device *netdev, - struct ethtool_drvinfo *drvinfo) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - - strlcpy(drvinfo->driver, i40evf_driver_name, 32); - strlcpy(drvinfo->version, i40evf_driver_version, 32); - strlcpy(drvinfo->fw_version, "N/A", 4); - strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), 32); - drvinfo->n_priv_flags = I40EVF_PRIV_FLAGS_STR_LEN; -} - -/** - * i40evf_get_ringparam - Get ring parameters - * @netdev: network interface device structure - * @ring: ethtool ringparam structure - * - * Returns current ring parameters. TX and RX rings are reported separately, - * but the number of rings is not reported. - **/ -static void i40evf_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - - ring->rx_max_pending = I40EVF_MAX_RXD; - ring->tx_max_pending = I40EVF_MAX_TXD; - ring->rx_pending = adapter->rx_desc_count; - ring->tx_pending = adapter->tx_desc_count; -} - -/** - * i40evf_set_ringparam - Set ring parameters - * @netdev: network interface device structure - * @ring: ethtool ringparam structure - * - * Sets ring parameters. TX and RX rings are controlled separately, but the - * number of rings is not specified, so all rings get the same settings. - **/ -static int i40evf_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - u32 new_rx_count, new_tx_count; - - if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending)) - return -EINVAL; - - new_tx_count = clamp_t(u32, ring->tx_pending, - I40EVF_MIN_TXD, - I40EVF_MAX_TXD); - new_tx_count = ALIGN(new_tx_count, I40EVF_REQ_DESCRIPTOR_MULTIPLE); - - new_rx_count = clamp_t(u32, ring->rx_pending, - I40EVF_MIN_RXD, - I40EVF_MAX_RXD); - new_rx_count = ALIGN(new_rx_count, I40EVF_REQ_DESCRIPTOR_MULTIPLE); - - /* if nothing to do return success */ - if ((new_tx_count == adapter->tx_desc_count) && - (new_rx_count == adapter->rx_desc_count)) - return 0; - - adapter->tx_desc_count = new_tx_count; - adapter->rx_desc_count = new_rx_count; - - if (netif_running(netdev)) { - adapter->flags |= I40EVF_FLAG_RESET_NEEDED; - schedule_work(&adapter->reset_task); - } - - return 0; -} - -/** - * __i40evf_get_coalesce - get per-queue coalesce settings - * @netdev: the netdev to check - * @ec: ethtool coalesce data structure - * @queue: which queue to pick - * - * Gets the per-queue settings for coalescence. Specifically Rx and Tx usecs - * are per queue. If queue is <0 then we default to queue 0 as the - * representative value. - **/ -static int __i40evf_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec, - int queue) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - struct i40e_vsi *vsi = &adapter->vsi; - struct i40e_ring *rx_ring, *tx_ring; - - ec->tx_max_coalesced_frames = vsi->work_limit; - ec->rx_max_coalesced_frames = vsi->work_limit; - - /* Rx and Tx usecs per queue value. If user doesn't specify the - * queue, return queue 0's value to represent. - */ - if (queue < 0) - queue = 0; - else if (queue >= adapter->num_active_queues) - return -EINVAL; - - rx_ring = &adapter->rx_rings[queue]; - tx_ring = &adapter->tx_rings[queue]; - - if (ITR_IS_DYNAMIC(rx_ring->itr_setting)) - ec->use_adaptive_rx_coalesce = 1; - - if (ITR_IS_DYNAMIC(tx_ring->itr_setting)) - ec->use_adaptive_tx_coalesce = 1; - - ec->rx_coalesce_usecs = rx_ring->itr_setting & ~I40E_ITR_DYNAMIC; - ec->tx_coalesce_usecs = tx_ring->itr_setting & ~I40E_ITR_DYNAMIC; - - return 0; -} - -/** - * i40evf_get_coalesce - Get interrupt coalescing settings - * @netdev: network interface device structure - * @ec: ethtool coalesce structure - * - * Returns current coalescing settings. This is referred to elsewhere in the - * driver as Interrupt Throttle Rate, as this is how the hardware describes - * this functionality. Note that if per-queue settings have been modified this - * only represents the settings of queue 0. - **/ -static int i40evf_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec) -{ - return __i40evf_get_coalesce(netdev, ec, -1); -} - -/** - * i40evf_get_per_queue_coalesce - get coalesce values for specific queue - * @netdev: netdev to read - * @ec: coalesce settings from ethtool - * @queue: the queue to read - * - * Read specific queue's coalesce settings. - **/ -static int i40evf_get_per_queue_coalesce(struct net_device *netdev, - u32 queue, - struct ethtool_coalesce *ec) -{ - return __i40evf_get_coalesce(netdev, ec, queue); -} - -/** - * i40evf_set_itr_per_queue - set ITR values for specific queue - * @adapter: the VF adapter struct to set values for - * @ec: coalesce settings from ethtool - * @queue: the queue to modify - * - * Change the ITR settings for a specific queue. - **/ -static void i40evf_set_itr_per_queue(struct i40evf_adapter *adapter, - struct ethtool_coalesce *ec, - int queue) -{ - struct i40e_ring *rx_ring = &adapter->rx_rings[queue]; - struct i40e_ring *tx_ring = &adapter->tx_rings[queue]; - struct i40e_q_vector *q_vector; - - rx_ring->itr_setting = ITR_REG_ALIGN(ec->rx_coalesce_usecs); - tx_ring->itr_setting = ITR_REG_ALIGN(ec->tx_coalesce_usecs); - - rx_ring->itr_setting |= I40E_ITR_DYNAMIC; - if (!ec->use_adaptive_rx_coalesce) - rx_ring->itr_setting ^= I40E_ITR_DYNAMIC; - - tx_ring->itr_setting |= I40E_ITR_DYNAMIC; - if (!ec->use_adaptive_tx_coalesce) - tx_ring->itr_setting ^= I40E_ITR_DYNAMIC; - - q_vector = rx_ring->q_vector; - q_vector->rx.target_itr = ITR_TO_REG(rx_ring->itr_setting); - - q_vector = tx_ring->q_vector; - q_vector->tx.target_itr = ITR_TO_REG(tx_ring->itr_setting); - - /* The interrupt handler itself will take care of programming - * the Tx and Rx ITR values based on the values we have entered - * into the q_vector, no need to write the values now. - */ -} - -/** - * __i40evf_set_coalesce - set coalesce settings for particular queue - * @netdev: the netdev to change - * @ec: ethtool coalesce settings - * @queue: the queue to change - * - * Sets the coalesce settings for a particular queue. - **/ -static int __i40evf_set_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec, - int queue) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - struct i40e_vsi *vsi = &adapter->vsi; - int i; - - if (ec->tx_max_coalesced_frames_irq || ec->rx_max_coalesced_frames_irq) - vsi->work_limit = ec->tx_max_coalesced_frames_irq; - - if (ec->rx_coalesce_usecs == 0) { - if (ec->use_adaptive_rx_coalesce) - netif_info(adapter, drv, netdev, "rx-usecs=0, need to disable adaptive-rx for a complete disable\n"); - } else if ((ec->rx_coalesce_usecs < I40E_MIN_ITR) || - (ec->rx_coalesce_usecs > I40E_MAX_ITR)) { - netif_info(adapter, drv, netdev, "Invalid value, rx-usecs range is 0-8160\n"); - return -EINVAL; - } - - else - if (ec->tx_coalesce_usecs == 0) { - if (ec->use_adaptive_tx_coalesce) - netif_info(adapter, drv, netdev, "tx-usecs=0, need to disable adaptive-tx for a complete disable\n"); - } else if ((ec->tx_coalesce_usecs < I40E_MIN_ITR) || - (ec->tx_coalesce_usecs > I40E_MAX_ITR)) { - netif_info(adapter, drv, netdev, "Invalid value, tx-usecs range is 0-8160\n"); - return -EINVAL; - } - - /* Rx and Tx usecs has per queue value. If user doesn't specify the - * queue, apply to all queues. - */ - if (queue < 0) { - for (i = 0; i < adapter->num_active_queues; i++) - i40evf_set_itr_per_queue(adapter, ec, i); - } else if (queue < adapter->num_active_queues) { - i40evf_set_itr_per_queue(adapter, ec, queue); - } else { - netif_info(adapter, drv, netdev, "Invalid queue value, queue range is 0 - %d\n", - adapter->num_active_queues - 1); - return -EINVAL; - } - - return 0; -} - -/** - * i40evf_set_coalesce - Set interrupt coalescing settings - * @netdev: network interface device structure - * @ec: ethtool coalesce structure - * - * Change current coalescing settings for every queue. - **/ -static int i40evf_set_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec) -{ - return __i40evf_set_coalesce(netdev, ec, -1); -} - -/** - * i40evf_set_per_queue_coalesce - set specific queue's coalesce settings - * @netdev: the netdev to change - * @ec: ethtool's coalesce settings - * @queue: the queue to modify - * - * Modifies a specific queue's coalesce settings. - */ -static int i40evf_set_per_queue_coalesce(struct net_device *netdev, - u32 queue, - struct ethtool_coalesce *ec) -{ - return __i40evf_set_coalesce(netdev, ec, queue); -} - -/** - * i40evf_get_rxnfc - command to get RX flow classification rules - * @netdev: network interface device structure - * @cmd: ethtool rxnfc command - * @rule_locs: pointer to store rule locations - * - * Returns Success if the command is supported. - **/ -static int i40evf_get_rxnfc(struct net_device *netdev, - struct ethtool_rxnfc *cmd, - u32 *rule_locs) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - int ret = -EOPNOTSUPP; - - switch (cmd->cmd) { - case ETHTOOL_GRXRINGS: - cmd->data = adapter->num_active_queues; - ret = 0; - break; - case ETHTOOL_GRXFH: - netdev_info(netdev, - "RSS hash info is not available to vf, use pf.\n"); - break; - default: - break; - } - - return ret; -} -/** - * i40evf_get_channels: get the number of channels supported by the device - * @netdev: network interface device structure - * @ch: channel information structure - * - * For the purposes of our device, we only use combined channels, i.e. a tx/rx - * queue pair. Report one extra channel to match our "other" MSI-X vector. - **/ -static void i40evf_get_channels(struct net_device *netdev, - struct ethtool_channels *ch) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - - /* Report maximum channels */ - ch->max_combined = I40EVF_MAX_REQ_QUEUES; - - ch->max_other = NONQ_VECS; - ch->other_count = NONQ_VECS; - - ch->combined_count = adapter->num_active_queues; -} - -/** - * i40evf_set_channels: set the new channel count - * @netdev: network interface device structure - * @ch: channel information structure - * - * Negotiate a new number of channels with the PF then do a reset. During - * reset we'll realloc queues and fix the RSS table. Returns 0 on success, - * negative on failure. - **/ -static int i40evf_set_channels(struct net_device *netdev, - struct ethtool_channels *ch) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - int num_req = ch->combined_count; - - if (num_req != adapter->num_active_queues && - !(adapter->vf_res->vf_cap_flags & - VIRTCHNL_VF_OFFLOAD_REQ_QUEUES)) { - dev_info(&adapter->pdev->dev, "PF is not capable of queue negotiation.\n"); - return -EINVAL; - } - - if ((adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) && - adapter->num_tc) { - dev_info(&adapter->pdev->dev, "Cannot set channels since ADq is enabled.\n"); - return -EINVAL; - } - - /* All of these should have already been checked by ethtool before this - * even gets to us, but just to be sure. - */ - if (num_req <= 0 || num_req > I40EVF_MAX_REQ_QUEUES) - return -EINVAL; - - if (ch->rx_count || ch->tx_count || ch->other_count != NONQ_VECS) - return -EINVAL; - - adapter->num_req_queues = num_req; - return i40evf_request_queues(adapter, num_req); -} - -/** - * i40evf_get_rxfh_key_size - get the RSS hash key size - * @netdev: network interface device structure - * - * Returns the table size. - **/ -static u32 i40evf_get_rxfh_key_size(struct net_device *netdev) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - - return adapter->rss_key_size; -} - -/** - * i40evf_get_rxfh_indir_size - get the rx flow hash indirection table size - * @netdev: network interface device structure - * - * Returns the table size. - **/ -static u32 i40evf_get_rxfh_indir_size(struct net_device *netdev) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - - return adapter->rss_lut_size; -} - -/** - * i40evf_get_rxfh - get the rx flow hash indirection table - * @netdev: network interface device structure - * @indir: indirection table - * @key: hash key - * @hfunc: hash function in use - * - * Reads the indirection table directly from the hardware. Always returns 0. - **/ -static int i40evf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, - u8 *hfunc) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - u16 i; - - if (hfunc) - *hfunc = ETH_RSS_HASH_TOP; - if (!indir) - return 0; - - memcpy(key, adapter->rss_key, adapter->rss_key_size); - - /* Each 32 bits pointed by 'indir' is stored with a lut entry */ - for (i = 0; i < adapter->rss_lut_size; i++) - indir[i] = (u32)adapter->rss_lut[i]; - - return 0; -} - -/** - * i40evf_set_rxfh - set the rx flow hash indirection table - * @netdev: network interface device structure - * @indir: indirection table - * @key: hash key - * @hfunc: hash function to use - * - * Returns -EINVAL if the table specifies an inavlid queue id, otherwise - * returns 0 after programming the table. - **/ -static int i40evf_set_rxfh(struct net_device *netdev, const u32 *indir, - const u8 *key, const u8 hfunc) -{ - struct i40evf_adapter *adapter = netdev_priv(netdev); - u16 i; - - /* We do not allow change in unsupported parameters */ - if (key || - (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)) - return -EOPNOTSUPP; - if (!indir) - return 0; - - if (key) { - memcpy(adapter->rss_key, key, adapter->rss_key_size); - } - - /* Each 32 bits pointed by 'indir' is stored with a lut entry */ - for (i = 0; i < adapter->rss_lut_size; i++) - adapter->rss_lut[i] = (u8)(indir[i]); - - return i40evf_config_rss(adapter); -} - -static const struct ethtool_ops i40evf_ethtool_ops = { - .get_drvinfo = i40evf_get_drvinfo, - .get_link = ethtool_op_get_link, - .get_ringparam = i40evf_get_ringparam, - .set_ringparam = i40evf_set_ringparam, - .get_strings = i40evf_get_strings, - .get_ethtool_stats = i40evf_get_ethtool_stats, - .get_sset_count = i40evf_get_sset_count, - .get_priv_flags = i40evf_get_priv_flags, - .set_priv_flags = i40evf_set_priv_flags, - .get_msglevel = i40evf_get_msglevel, - .set_msglevel = i40evf_set_msglevel, - .get_coalesce = i40evf_get_coalesce, - .set_coalesce = i40evf_set_coalesce, - .get_per_queue_coalesce = i40evf_get_per_queue_coalesce, - .set_per_queue_coalesce = i40evf_set_per_queue_coalesce, - .get_rxnfc = i40evf_get_rxnfc, - .get_rxfh_indir_size = i40evf_get_rxfh_indir_size, - .get_rxfh = i40evf_get_rxfh, - .set_rxfh = i40evf_set_rxfh, - .get_channels = i40evf_get_channels, - .set_channels = i40evf_set_channels, - .get_rxfh_key_size = i40evf_get_rxfh_key_size, - .get_link_ksettings = i40evf_get_link_ksettings, -}; - -/** - * i40evf_set_ethtool_ops - Initialize ethtool ops struct - * @netdev: network interface device structure - * - * Sets ethtool ops struct in our netdev so that ethtool can call - * our functions. - **/ -void i40evf_set_ethtool_ops(struct net_device *netdev) -{ - netdev->ethtool_ops = &i40evf_ethtool_ops; -} diff --git a/drivers/net/ethernet/intel/iavf/Makefile b/drivers/net/ethernet/intel/iavf/Makefile new file mode 100644 index 000000000000..9cbb5743ed12 --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/Makefile @@ -0,0 +1,15 @@ +# SPDX-License-Identifier: GPL-2.0 +# Copyright(c) 2013 - 2018 Intel Corporation. +# +# Makefile for the Intel(R) Ethernet Adaptive Virtual Function (iavf) +# driver +# +# + +ccflags-y += -I$(src) +subdir-ccflags-y += -I$(src) + +obj-$(CONFIG_IAVF) += iavf.o + +iavf-objs := iavf_main.o iavf_ethtool.o iavf_virtchnl.o \ + iavf_txrx.o iavf_common.o i40e_adminq.o iavf_client.o diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c b/drivers/net/ethernet/intel/iavf/i40e_adminq.c index 21a0dbf6ccf6..fca1ecfd9f71 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c +++ b/drivers/net/ethernet/intel/iavf/i40e_adminq.c @@ -1,21 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2013 - 2018 Intel Corporation. */ -#include "i40e_status.h" -#include "i40e_type.h" -#include "i40e_register.h" +#include "iavf_status.h" +#include "iavf_type.h" +#include "iavf_register.h" #include "i40e_adminq.h" -#include "i40e_prototype.h" - -/** - * i40e_is_nvm_update_op - return true if this is an NVM update operation - * @desc: API request descriptor - **/ -static inline bool i40e_is_nvm_update_op(struct i40e_aq_desc *desc) -{ - return (desc->opcode == i40e_aqc_opc_nvm_erase) || - (desc->opcode == i40e_aqc_opc_nvm_update); -} +#include "iavf_prototype.h" /** * i40e_adminq_init_regs - Initialize AdminQ registers @@ -23,44 +13,42 @@ static inline bool i40e_is_nvm_update_op(struct i40e_aq_desc *desc) * * This assumes the alloc_asq and alloc_arq functions have already been called **/ -static void i40e_adminq_init_regs(struct i40e_hw *hw) +static void i40e_adminq_init_regs(struct iavf_hw *hw) { /* set head and tail registers in our local struct */ - if (i40e_is_vf(hw)) { - hw->aq.asq.tail = I40E_VF_ATQT1; - hw->aq.asq.head = I40E_VF_ATQH1; - hw->aq.asq.len = I40E_VF_ATQLEN1; - hw->aq.asq.bal = I40E_VF_ATQBAL1; - hw->aq.asq.bah = I40E_VF_ATQBAH1; - hw->aq.arq.tail = I40E_VF_ARQT1; - hw->aq.arq.head = I40E_VF_ARQH1; - hw->aq.arq.len = I40E_VF_ARQLEN1; - hw->aq.arq.bal = I40E_VF_ARQBAL1; - hw->aq.arq.bah = I40E_VF_ARQBAH1; - } + hw->aq.asq.tail = IAVF_VF_ATQT1; + hw->aq.asq.head = IAVF_VF_ATQH1; + hw->aq.asq.len = IAVF_VF_ATQLEN1; + hw->aq.asq.bal = IAVF_VF_ATQBAL1; + hw->aq.asq.bah = IAVF_VF_ATQBAH1; + hw->aq.arq.tail = IAVF_VF_ARQT1; + hw->aq.arq.head = IAVF_VF_ARQH1; + hw->aq.arq.len = IAVF_VF_ARQLEN1; + hw->aq.arq.bal = IAVF_VF_ARQBAL1; + hw->aq.arq.bah = IAVF_VF_ARQBAH1; } /** * i40e_alloc_adminq_asq_ring - Allocate Admin Queue send rings * @hw: pointer to the hardware structure **/ -static i40e_status i40e_alloc_adminq_asq_ring(struct i40e_hw *hw) +static iavf_status i40e_alloc_adminq_asq_ring(struct iavf_hw *hw) { - i40e_status ret_code; + iavf_status ret_code; - ret_code = i40e_allocate_dma_mem(hw, &hw->aq.asq.desc_buf, + ret_code = iavf_allocate_dma_mem(hw, &hw->aq.asq.desc_buf, i40e_mem_atq_ring, (hw->aq.num_asq_entries * sizeof(struct i40e_aq_desc)), - I40E_ADMINQ_DESC_ALIGNMENT); + IAVF_ADMINQ_DESC_ALIGNMENT); if (ret_code) return ret_code; - ret_code = i40e_allocate_virt_mem(hw, &hw->aq.asq.cmd_buf, + ret_code = iavf_allocate_virt_mem(hw, &hw->aq.asq.cmd_buf, (hw->aq.num_asq_entries * sizeof(struct i40e_asq_cmd_details))); if (ret_code) { - i40e_free_dma_mem(hw, &hw->aq.asq.desc_buf); + iavf_free_dma_mem(hw, &hw->aq.asq.desc_buf); return ret_code; } @@ -71,15 +59,15 @@ static i40e_status i40e_alloc_adminq_asq_ring(struct i40e_hw *hw) * i40e_alloc_adminq_arq_ring - Allocate Admin Queue receive rings * @hw: pointer to the hardware structure **/ -static i40e_status i40e_alloc_adminq_arq_ring(struct i40e_hw *hw) +static iavf_status i40e_alloc_adminq_arq_ring(struct iavf_hw *hw) { - i40e_status ret_code; + iavf_status ret_code; - ret_code = i40e_allocate_dma_mem(hw, &hw->aq.arq.desc_buf, + ret_code = iavf_allocate_dma_mem(hw, &hw->aq.arq.desc_buf, i40e_mem_arq_ring, (hw->aq.num_arq_entries * sizeof(struct i40e_aq_desc)), - I40E_ADMINQ_DESC_ALIGNMENT); + IAVF_ADMINQ_DESC_ALIGNMENT); return ret_code; } @@ -91,9 +79,9 @@ static i40e_status i40e_alloc_adminq_arq_ring(struct i40e_hw *hw) * This assumes the posted send buffers have already been cleaned * and de-allocated **/ -static void i40e_free_adminq_asq(struct i40e_hw *hw) +static void i40e_free_adminq_asq(struct iavf_hw *hw) { - i40e_free_dma_mem(hw, &hw->aq.asq.desc_buf); + iavf_free_dma_mem(hw, &hw->aq.asq.desc_buf); } /** @@ -103,20 +91,20 @@ static void i40e_free_adminq_asq(struct i40e_hw *hw) * This assumes the posted receive buffers have already been cleaned * and de-allocated **/ -static void i40e_free_adminq_arq(struct i40e_hw *hw) +static void i40e_free_adminq_arq(struct iavf_hw *hw) { - i40e_free_dma_mem(hw, &hw->aq.arq.desc_buf); + iavf_free_dma_mem(hw, &hw->aq.arq.desc_buf); } /** * i40e_alloc_arq_bufs - Allocate pre-posted buffers for the receive queue * @hw: pointer to the hardware structure **/ -static i40e_status i40e_alloc_arq_bufs(struct i40e_hw *hw) +static iavf_status i40e_alloc_arq_bufs(struct iavf_hw *hw) { - i40e_status ret_code; struct i40e_aq_desc *desc; - struct i40e_dma_mem *bi; + struct iavf_dma_mem *bi; + iavf_status ret_code; int i; /* We'll be allocating the buffer info memory first, then we can @@ -124,24 +112,25 @@ static i40e_status i40e_alloc_arq_bufs(struct i40e_hw *hw) */ /* buffer_info structures do not need alignment */ - ret_code = i40e_allocate_virt_mem(hw, &hw->aq.arq.dma_head, - (hw->aq.num_arq_entries * sizeof(struct i40e_dma_mem))); + ret_code = iavf_allocate_virt_mem(hw, &hw->aq.arq.dma_head, + (hw->aq.num_arq_entries * + sizeof(struct iavf_dma_mem))); if (ret_code) goto alloc_arq_bufs; - hw->aq.arq.r.arq_bi = (struct i40e_dma_mem *)hw->aq.arq.dma_head.va; + hw->aq.arq.r.arq_bi = (struct iavf_dma_mem *)hw->aq.arq.dma_head.va; /* allocate the mapped buffers */ for (i = 0; i < hw->aq.num_arq_entries; i++) { bi = &hw->aq.arq.r.arq_bi[i]; - ret_code = i40e_allocate_dma_mem(hw, bi, + ret_code = iavf_allocate_dma_mem(hw, bi, i40e_mem_arq_buf, hw->aq.arq_buf_size, - I40E_ADMINQ_DESC_ALIGNMENT); + IAVF_ADMINQ_DESC_ALIGNMENT); if (ret_code) goto unwind_alloc_arq_bufs; /* now configure the descriptors for use */ - desc = I40E_ADMINQ_DESC(hw->aq.arq, i); + desc = IAVF_ADMINQ_DESC(hw->aq.arq, i); desc->flags = cpu_to_le16(I40E_AQ_FLAG_BUF); if (hw->aq.arq_buf_size > I40E_AQ_LARGE_BUF) @@ -169,8 +158,8 @@ unwind_alloc_arq_bufs: /* don't try to free the one that failed... */ i--; for (; i >= 0; i--) - i40e_free_dma_mem(hw, &hw->aq.arq.r.arq_bi[i]); - i40e_free_virt_mem(hw, &hw->aq.arq.dma_head); + iavf_free_dma_mem(hw, &hw->aq.arq.r.arq_bi[i]); + iavf_free_virt_mem(hw, &hw->aq.arq.dma_head); return ret_code; } @@ -179,26 +168,27 @@ unwind_alloc_arq_bufs: * i40e_alloc_asq_bufs - Allocate empty buffer structs for the send queue * @hw: pointer to the hardware structure **/ -static i40e_status i40e_alloc_asq_bufs(struct i40e_hw *hw) +static iavf_status i40e_alloc_asq_bufs(struct iavf_hw *hw) { - i40e_status ret_code; - struct i40e_dma_mem *bi; + struct iavf_dma_mem *bi; + iavf_status ret_code; int i; /* No mapped memory needed yet, just the buffer info structures */ - ret_code = i40e_allocate_virt_mem(hw, &hw->aq.asq.dma_head, - (hw->aq.num_asq_entries * sizeof(struct i40e_dma_mem))); + ret_code = iavf_allocate_virt_mem(hw, &hw->aq.asq.dma_head, + (hw->aq.num_asq_entries * + sizeof(struct iavf_dma_mem))); if (ret_code) goto alloc_asq_bufs; - hw->aq.asq.r.asq_bi = (struct i40e_dma_mem *)hw->aq.asq.dma_head.va; + hw->aq.asq.r.asq_bi = (struct iavf_dma_mem *)hw->aq.asq.dma_head.va; /* allocate the mapped buffers */ for (i = 0; i < hw->aq.num_asq_entries; i++) { bi = &hw->aq.asq.r.asq_bi[i]; - ret_code = i40e_allocate_dma_mem(hw, bi, + ret_code = iavf_allocate_dma_mem(hw, bi, i40e_mem_asq_buf, hw->aq.asq_buf_size, - I40E_ADMINQ_DESC_ALIGNMENT); + IAVF_ADMINQ_DESC_ALIGNMENT); if (ret_code) goto unwind_alloc_asq_bufs; } @@ -209,8 +199,8 @@ unwind_alloc_asq_bufs: /* don't try to free the one that failed... */ i--; for (; i >= 0; i--) - i40e_free_dma_mem(hw, &hw->aq.asq.r.asq_bi[i]); - i40e_free_virt_mem(hw, &hw->aq.asq.dma_head); + iavf_free_dma_mem(hw, &hw->aq.asq.r.asq_bi[i]); + iavf_free_virt_mem(hw, &hw->aq.asq.dma_head); return ret_code; } @@ -219,42 +209,42 @@ unwind_alloc_asq_bufs: * i40e_free_arq_bufs - Free receive queue buffer info elements * @hw: pointer to the hardware structure **/ -static void i40e_free_arq_bufs(struct i40e_hw *hw) +static void i40e_free_arq_bufs(struct iavf_hw *hw) { int i; /* free descriptors */ for (i = 0; i < hw->aq.num_arq_entries; i++) - i40e_free_dma_mem(hw, &hw->aq.arq.r.arq_bi[i]); + iavf_free_dma_mem(hw, &hw->aq.arq.r.arq_bi[i]); /* free the descriptor memory */ - i40e_free_dma_mem(hw, &hw->aq.arq.desc_buf); + iavf_free_dma_mem(hw, &hw->aq.arq.desc_buf); /* free the dma header */ - i40e_free_virt_mem(hw, &hw->aq.arq.dma_head); + iavf_free_virt_mem(hw, &hw->aq.arq.dma_head); } /** * i40e_free_asq_bufs - Free send queue buffer info elements * @hw: pointer to the hardware structure **/ -static void i40e_free_asq_bufs(struct i40e_hw *hw) +static void i40e_free_asq_bufs(struct iavf_hw *hw) { int i; /* only unmap if the address is non-NULL */ for (i = 0; i < hw->aq.num_asq_entries; i++) if (hw->aq.asq.r.asq_bi[i].pa) - i40e_free_dma_mem(hw, &hw->aq.asq.r.asq_bi[i]); + iavf_free_dma_mem(hw, &hw->aq.asq.r.asq_bi[i]); /* free the buffer info list */ - i40e_free_virt_mem(hw, &hw->aq.asq.cmd_buf); + iavf_free_virt_mem(hw, &hw->aq.asq.cmd_buf); /* free the descriptor memory */ - i40e_free_dma_mem(hw, &hw->aq.asq.desc_buf); + iavf_free_dma_mem(hw, &hw->aq.asq.desc_buf); /* free the dma header */ - i40e_free_virt_mem(hw, &hw->aq.asq.dma_head); + iavf_free_virt_mem(hw, &hw->aq.asq.dma_head); } /** @@ -263,9 +253,9 @@ static void i40e_free_asq_bufs(struct i40e_hw *hw) * * Configure base address and length registers for the transmit queue **/ -static i40e_status i40e_config_asq_regs(struct i40e_hw *hw) +static iavf_status i40e_config_asq_regs(struct iavf_hw *hw) { - i40e_status ret_code = 0; + iavf_status ret_code = 0; u32 reg = 0; /* Clear Head and Tail */ @@ -274,7 +264,7 @@ static i40e_status i40e_config_asq_regs(struct i40e_hw *hw) /* set starting point */ wr32(hw, hw->aq.asq.len, (hw->aq.num_asq_entries | - I40E_VF_ATQLEN1_ATQENABLE_MASK)); + IAVF_VF_ATQLEN1_ATQENABLE_MASK)); wr32(hw, hw->aq.asq.bal, lower_32_bits(hw->aq.asq.desc_buf.pa)); wr32(hw, hw->aq.asq.bah, upper_32_bits(hw->aq.asq.desc_buf.pa)); @@ -292,9 +282,9 @@ static i40e_status i40e_config_asq_regs(struct i40e_hw *hw) * * Configure base address and length registers for the receive (event queue) **/ -static i40e_status i40e_config_arq_regs(struct i40e_hw *hw) +static iavf_status i40e_config_arq_regs(struct iavf_hw *hw) { - i40e_status ret_code = 0; + iavf_status ret_code = 0; u32 reg = 0; /* Clear Head and Tail */ @@ -303,7 +293,7 @@ static i40e_status i40e_config_arq_regs(struct i40e_hw *hw) /* set starting point */ wr32(hw, hw->aq.arq.len, (hw->aq.num_arq_entries | - I40E_VF_ARQLEN1_ARQENABLE_MASK)); + IAVF_VF_ARQLEN1_ARQENABLE_MASK)); wr32(hw, hw->aq.arq.bal, lower_32_bits(hw->aq.arq.desc_buf.pa)); wr32(hw, hw->aq.arq.bah, upper_32_bits(hw->aq.arq.desc_buf.pa)); @@ -331,9 +321,9 @@ static i40e_status i40e_config_arq_regs(struct i40e_hw *hw) * Do *NOT* hold the lock when calling this as the memory allocation routines * called are not going to be atomic context safe **/ -static i40e_status i40e_init_asq(struct i40e_hw *hw) +static iavf_status i40e_init_asq(struct iavf_hw *hw) { - i40e_status ret_code = 0; + iavf_status ret_code = 0; if (hw->aq.asq.count > 0) { /* queue already initialized */ @@ -390,9 +380,9 @@ init_adminq_exit: * Do *NOT* hold the lock when calling this as the memory allocation routines * called are not going to be atomic context safe **/ -static i40e_status i40e_init_arq(struct i40e_hw *hw) +static iavf_status i40e_init_arq(struct iavf_hw *hw) { - i40e_status ret_code = 0; + iavf_status ret_code = 0; if (hw->aq.arq.count > 0) { /* queue already initialized */ @@ -442,9 +432,9 @@ init_adminq_exit: * * The main shutdown routine for the Admin Send Queue **/ -static i40e_status i40e_shutdown_asq(struct i40e_hw *hw) +static iavf_status i40e_shutdown_asq(struct iavf_hw *hw) { - i40e_status ret_code = 0; + iavf_status ret_code = 0; mutex_lock(&hw->aq.asq_mutex); @@ -476,9 +466,9 @@ shutdown_asq_out: * * The main shutdown routine for the Admin Receive Queue **/ -static i40e_status i40e_shutdown_arq(struct i40e_hw *hw) +static iavf_status i40e_shutdown_arq(struct iavf_hw *hw) { - i40e_status ret_code = 0; + iavf_status ret_code = 0; mutex_lock(&hw->aq.arq_mutex); @@ -505,7 +495,7 @@ shutdown_arq_out: } /** - * i40evf_init_adminq - main initialization routine for Admin Queue + * iavf_init_adminq - main initialization routine for Admin Queue * @hw: pointer to the hardware structure * * Prior to calling this function, drivers *MUST* set the following fields @@ -515,9 +505,9 @@ shutdown_arq_out: * - hw->aq.arq_buf_size * - hw->aq.asq_buf_size **/ -i40e_status i40evf_init_adminq(struct i40e_hw *hw) +iavf_status iavf_init_adminq(struct iavf_hw *hw) { - i40e_status ret_code; + iavf_status ret_code; /* verify input for valid configuration */ if ((hw->aq.num_arq_entries == 0) || @@ -556,22 +546,19 @@ init_adminq_exit: } /** - * i40evf_shutdown_adminq - shutdown routine for the Admin Queue + * iavf_shutdown_adminq - shutdown routine for the Admin Queue * @hw: pointer to the hardware structure **/ -i40e_status i40evf_shutdown_adminq(struct i40e_hw *hw) +iavf_status iavf_shutdown_adminq(struct iavf_hw *hw) { - i40e_status ret_code = 0; + iavf_status ret_code = 0; - if (i40evf_check_asq_alive(hw)) - i40evf_aq_queue_shutdown(hw, true); + if (iavf_check_asq_alive(hw)) + iavf_aq_queue_shutdown(hw, true); i40e_shutdown_asq(hw); i40e_shutdown_arq(hw); - if (hw->nvm_buff.va) - i40e_free_virt_mem(hw, &hw->nvm_buff); - return ret_code; } @@ -581,18 +568,18 @@ i40e_status i40evf_shutdown_adminq(struct i40e_hw *hw) * * returns the number of free desc **/ -static u16 i40e_clean_asq(struct i40e_hw *hw) +static u16 i40e_clean_asq(struct iavf_hw *hw) { - struct i40e_adminq_ring *asq = &(hw->aq.asq); + struct iavf_adminq_ring *asq = &hw->aq.asq; struct i40e_asq_cmd_details *details; u16 ntc = asq->next_to_clean; struct i40e_aq_desc desc_cb; struct i40e_aq_desc *desc; - desc = I40E_ADMINQ_DESC(*asq, ntc); + desc = IAVF_ADMINQ_DESC(*asq, ntc); details = I40E_ADMINQ_DETAILS(*asq, ntc); while (rd32(hw, hw->aq.asq.head) != ntc) { - i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, + iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE, "ntc %d head %d.\n", ntc, rd32(hw, hw->aq.asq.head)); if (details->callback) { @@ -607,33 +594,32 @@ static u16 i40e_clean_asq(struct i40e_hw *hw) ntc++; if (ntc == asq->count) ntc = 0; - desc = I40E_ADMINQ_DESC(*asq, ntc); + desc = IAVF_ADMINQ_DESC(*asq, ntc); details = I40E_ADMINQ_DETAILS(*asq, ntc); } asq->next_to_clean = ntc; - return I40E_DESC_UNUSED(asq); + return IAVF_DESC_UNUSED(asq); } /** - * i40evf_asq_done - check if FW has processed the Admin Send Queue + * iavf_asq_done - check if FW has processed the Admin Send Queue * @hw: pointer to the hw struct * * Returns true if the firmware has processed all descriptors on the * admin send queue. Returns false if there are still requests pending. **/ -bool i40evf_asq_done(struct i40e_hw *hw) +bool iavf_asq_done(struct iavf_hw *hw) { /* AQ designers suggest use of head for better * timing reliability than DD bit */ return rd32(hw, hw->aq.asq.head) == hw->aq.asq.next_to_use; - } /** - * i40evf_asq_send_command - send command to Admin Queue + * iavf_asq_send_command - send command to Admin Queue * @hw: pointer to the hw struct * @desc: prefilled descriptor describing the command (non DMA mem) * @buff: buffer to use for indirect commands @@ -643,24 +629,23 @@ bool i40evf_asq_done(struct i40e_hw *hw) * This is the main send command driver routine for the Admin Queue send * queue. It runs the queue, cleans the queue, etc **/ -i40e_status i40evf_asq_send_command(struct i40e_hw *hw, - struct i40e_aq_desc *desc, - void *buff, /* can be NULL */ - u16 buff_size, - struct i40e_asq_cmd_details *cmd_details) +iavf_status iavf_asq_send_command(struct iavf_hw *hw, struct i40e_aq_desc *desc, + void *buff, /* can be NULL */ + u16 buff_size, + struct i40e_asq_cmd_details *cmd_details) { - i40e_status status = 0; - struct i40e_dma_mem *dma_buff = NULL; + struct iavf_dma_mem *dma_buff = NULL; struct i40e_asq_cmd_details *details; struct i40e_aq_desc *desc_on_ring; bool cmd_completed = false; + iavf_status status = 0; u16 retval = 0; u32 val = 0; mutex_lock(&hw->aq.asq_mutex); if (hw->aq.asq.count == 0) { - i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, + iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE, "AQTX: Admin queue not initialized.\n"); status = I40E_ERR_QUEUE_EMPTY; goto asq_send_command_error; @@ -670,7 +655,7 @@ i40e_status i40evf_asq_send_command(struct i40e_hw *hw, val = rd32(hw, hw->aq.asq.head); if (val >= hw->aq.num_asq_entries) { - i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, + iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE, "AQTX: head overrun at %d\n", val); status = I40E_ERR_QUEUE_EMPTY; goto asq_send_command_error; @@ -699,8 +684,8 @@ i40e_status i40evf_asq_send_command(struct i40e_hw *hw, desc->flags |= cpu_to_le16(details->flags_ena); if (buff_size > hw->aq.asq_buf_size) { - i40e_debug(hw, - I40E_DEBUG_AQ_MESSAGE, + iavf_debug(hw, + IAVF_DEBUG_AQ_MESSAGE, "AQTX: Invalid buffer size: %d.\n", buff_size); status = I40E_ERR_INVALID_SIZE; @@ -708,8 +693,8 @@ i40e_status i40evf_asq_send_command(struct i40e_hw *hw, } if (details->postpone && !details->async) { - i40e_debug(hw, - I40E_DEBUG_AQ_MESSAGE, + iavf_debug(hw, + IAVF_DEBUG_AQ_MESSAGE, "AQTX: Async flag not set along with postpone flag"); status = I40E_ERR_PARAM; goto asq_send_command_error; @@ -723,22 +708,22 @@ i40e_status i40evf_asq_send_command(struct i40e_hw *hw, * in case of asynchronous completions */ if (i40e_clean_asq(hw) == 0) { - i40e_debug(hw, - I40E_DEBUG_AQ_MESSAGE, + iavf_debug(hw, + IAVF_DEBUG_AQ_MESSAGE, "AQTX: Error queue is full.\n"); status = I40E_ERR_ADMIN_QUEUE_FULL; goto asq_send_command_error; } /* initialize the temp desc pointer with the right desc */ - desc_on_ring = I40E_ADMINQ_DESC(hw->aq.asq, hw->aq.asq.next_to_use); + desc_on_ring = IAVF_ADMINQ_DESC(hw->aq.asq, hw->aq.asq.next_to_use); /* if the desc is available copy the temp desc to the right place */ *desc_on_ring = *desc; /* if buff is not NULL assume indirect command */ - if (buff != NULL) { - dma_buff = &(hw->aq.asq.r.asq_bi[hw->aq.asq.next_to_use]); + if (buff) { + dma_buff = &hw->aq.asq.r.asq_bi[hw->aq.asq.next_to_use]; /* copy the user buff into the respective DMA buff */ memcpy(dma_buff->va, buff, buff_size); desc_on_ring->datalen = cpu_to_le16(buff_size); @@ -753,9 +738,9 @@ i40e_status i40evf_asq_send_command(struct i40e_hw *hw, } /* bump the tail */ - i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, "AQTX: desc and buffer:\n"); - i40evf_debug_aq(hw, I40E_DEBUG_AQ_COMMAND, (void *)desc_on_ring, - buff, buff_size); + iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE, "AQTX: desc and buffer:\n"); + iavf_debug_aq(hw, IAVF_DEBUG_AQ_COMMAND, (void *)desc_on_ring, + buff, buff_size); (hw->aq.asq.next_to_use)++; if (hw->aq.asq.next_to_use == hw->aq.asq.count) hw->aq.asq.next_to_use = 0; @@ -772,7 +757,7 @@ i40e_status i40evf_asq_send_command(struct i40e_hw *hw, /* AQ designers suggest use of head for better * timing reliability than DD bit */ - if (i40evf_asq_done(hw)) + if (iavf_asq_done(hw)) break; udelay(50); total_delay += 50; @@ -780,14 +765,14 @@ i40e_status i40evf_asq_send_command(struct i40e_hw *hw, } /* if ready, copy the desc back to temp */ - if (i40evf_asq_done(hw)) { + if (iavf_asq_done(hw)) { *desc = *desc_on_ring; - if (buff != NULL) + if (buff) memcpy(buff, dma_buff->va, buff_size); retval = le16_to_cpu(desc->retval); if (retval != 0) { - i40e_debug(hw, - I40E_DEBUG_AQ_MESSAGE, + iavf_debug(hw, + IAVF_DEBUG_AQ_MESSAGE, "AQTX: Command completed with error 0x%X.\n", retval); @@ -804,10 +789,9 @@ i40e_status i40evf_asq_send_command(struct i40e_hw *hw, hw->aq.asq_last_status = (enum i40e_admin_queue_err)retval; } - i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, + iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE, "AQTX: desc and buffer writeback:\n"); - i40evf_debug_aq(hw, I40E_DEBUG_AQ_COMMAND, (void *)desc, buff, - buff_size); + iavf_debug_aq(hw, IAVF_DEBUG_AQ_COMMAND, (void *)desc, buff, buff_size); /* save writeback aq if requested */ if (details->wb_desc) @@ -816,12 +800,12 @@ i40e_status i40evf_asq_send_command(struct i40e_hw *hw, /* update the error if time out occurred */ if ((!cmd_completed) && (!details->async && !details->postpone)) { - if (rd32(hw, hw->aq.asq.len) & I40E_VF_ATQLEN1_ATQCRIT_MASK) { - i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, + if (rd32(hw, hw->aq.asq.len) & IAVF_VF_ATQLEN1_ATQCRIT_MASK) { + iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE, "AQTX: AQ Critical error.\n"); status = I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR; } else { - i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, + iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE, "AQTX: Writeback timeout.\n"); status = I40E_ERR_ADMIN_QUEUE_TIMEOUT; } @@ -833,14 +817,13 @@ asq_send_command_error: } /** - * i40evf_fill_default_direct_cmd_desc - AQ descriptor helper function + * iavf_fill_default_direct_cmd_desc - AQ descriptor helper function * @desc: pointer to the temp descriptor (non DMA mem) * @opcode: the opcode can be used to decide which flags to turn off or on * * Fill the desc with default values **/ -void i40evf_fill_default_direct_cmd_desc(struct i40e_aq_desc *desc, - u16 opcode) +void iavf_fill_default_direct_cmd_desc(struct i40e_aq_desc *desc, u16 opcode) { /* zero out the desc */ memset((void *)desc, 0, sizeof(struct i40e_aq_desc)); @@ -849,7 +832,7 @@ void i40evf_fill_default_direct_cmd_desc(struct i40e_aq_desc *desc, } /** - * i40evf_clean_arq_element + * iavf_clean_arq_element * @hw: pointer to the hw struct * @e: event info from the receive descriptor, includes any buffers * @pending: number of events that could be left to process @@ -858,14 +841,14 @@ void i40evf_fill_default_direct_cmd_desc(struct i40e_aq_desc *desc, * the contents through e. It can also return how many events are * left to process through 'pending' **/ -i40e_status i40evf_clean_arq_element(struct i40e_hw *hw, - struct i40e_arq_event_info *e, - u16 *pending) +iavf_status iavf_clean_arq_element(struct iavf_hw *hw, + struct i40e_arq_event_info *e, + u16 *pending) { - i40e_status ret_code = 0; u16 ntc = hw->aq.arq.next_to_clean; struct i40e_aq_desc *desc; - struct i40e_dma_mem *bi; + iavf_status ret_code = 0; + struct iavf_dma_mem *bi; u16 desc_idx; u16 datalen; u16 flags; @@ -878,14 +861,14 @@ i40e_status i40evf_clean_arq_element(struct i40e_hw *hw, mutex_lock(&hw->aq.arq_mutex); if (hw->aq.arq.count == 0) { - i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, + iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE, "AQRX: Admin queue not initialized.\n"); ret_code = I40E_ERR_QUEUE_EMPTY; goto clean_arq_element_err; } /* set next_to_use to head */ - ntu = rd32(hw, hw->aq.arq.head) & I40E_VF_ARQH1_ARQH_MASK; + ntu = rd32(hw, hw->aq.arq.head) & IAVF_VF_ARQH1_ARQH_MASK; if (ntu == ntc) { /* nothing to do - shouldn't need to update ring's values */ ret_code = I40E_ERR_ADMIN_QUEUE_NO_WORK; @@ -893,7 +876,7 @@ i40e_status i40evf_clean_arq_element(struct i40e_hw *hw, } /* now clean the next descriptor */ - desc = I40E_ADMINQ_DESC(hw->aq.arq, ntc); + desc = IAVF_ADMINQ_DESC(hw->aq.arq, ntc); desc_idx = ntc; hw->aq.arq_last_status = @@ -901,8 +884,8 @@ i40e_status i40evf_clean_arq_element(struct i40e_hw *hw, flags = le16_to_cpu(desc->flags); if (flags & I40E_AQ_FLAG_ERR) { ret_code = I40E_ERR_ADMIN_QUEUE_ERROR; - i40e_debug(hw, - I40E_DEBUG_AQ_MESSAGE, + iavf_debug(hw, + IAVF_DEBUG_AQ_MESSAGE, "AQRX: Event received with error 0x%X.\n", hw->aq.arq_last_status); } @@ -910,13 +893,13 @@ i40e_status i40evf_clean_arq_element(struct i40e_hw *hw, e->desc = *desc; datalen = le16_to_cpu(desc->datalen); e->msg_len = min(datalen, e->buf_len); - if (e->msg_buf != NULL && (e->msg_len != 0)) + if (e->msg_buf && (e->msg_len != 0)) memcpy(e->msg_buf, hw->aq.arq.r.arq_bi[desc_idx].va, e->msg_len); - i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, "AQRX: desc and buffer:\n"); - i40evf_debug_aq(hw, I40E_DEBUG_AQ_COMMAND, (void *)desc, e->msg_buf, - hw->aq.arq_buf_size); + iavf_debug(hw, IAVF_DEBUG_AQ_MESSAGE, "AQRX: desc and buffer:\n"); + iavf_debug_aq(hw, IAVF_DEBUG_AQ_COMMAND, (void *)desc, e->msg_buf, + hw->aq.arq_buf_size); /* Restore the original datalen and buffer address in the desc, * FW updates datalen to indicate the event message @@ -943,7 +926,7 @@ i40e_status i40evf_clean_arq_element(struct i40e_hw *hw, clean_arq_element_out: /* Set pending if needed, unlock and return */ - if (pending != NULL) + if (pending) *pending = (ntc > ntu ? hw->aq.arq.count : 0) + (ntu - ntc); clean_arq_element_err: @@ -951,17 +934,3 @@ clean_arq_element_err: return ret_code; } - -void i40evf_resume_aq(struct i40e_hw *hw) -{ - /* Registers are reset after PF reset */ - hw->aq.asq.next_to_use = 0; - hw->aq.asq.next_to_clean = 0; - - i40e_config_asq_regs(hw); - - hw->aq.arq.next_to_use = 0; - hw->aq.arq.next_to_clean = 0; - - i40e_config_arq_regs(hw); -} diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.h b/drivers/net/ethernet/intel/iavf/i40e_adminq.h index 1f264b9b6805..ee983889eab0 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.h +++ b/drivers/net/ethernet/intel/iavf/i40e_adminq.h @@ -1,26 +1,26 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright(c) 2013 - 2018 Intel Corporation. */ -#ifndef _I40E_ADMINQ_H_ -#define _I40E_ADMINQ_H_ +#ifndef _IAVF_ADMINQ_H_ +#define _IAVF_ADMINQ_H_ -#include "i40e_osdep.h" -#include "i40e_status.h" +#include "iavf_osdep.h" +#include "iavf_status.h" #include "i40e_adminq_cmd.h" -#define I40E_ADMINQ_DESC(R, i) \ +#define IAVF_ADMINQ_DESC(R, i) \ (&(((struct i40e_aq_desc *)((R).desc_buf.va))[i])) -#define I40E_ADMINQ_DESC_ALIGNMENT 4096 +#define IAVF_ADMINQ_DESC_ALIGNMENT 4096 -struct i40e_adminq_ring { - struct i40e_virt_mem dma_head; /* space for dma structures */ - struct i40e_dma_mem desc_buf; /* descriptor ring memory */ - struct i40e_virt_mem cmd_buf; /* command buffer memory */ +struct iavf_adminq_ring { + struct iavf_virt_mem dma_head; /* space for dma structures */ + struct iavf_dma_mem desc_buf; /* descriptor ring memory */ + struct iavf_virt_mem cmd_buf; /* command buffer memory */ union { - struct i40e_dma_mem *asq_bi; - struct i40e_dma_mem *arq_bi; + struct iavf_dma_mem *asq_bi; + struct iavf_dma_mem *arq_bi; } r; u16 count; /* Number of descriptors */ @@ -61,9 +61,9 @@ struct i40e_arq_event_info { }; /* Admin Queue information */ -struct i40e_adminq_info { - struct i40e_adminq_ring arq; /* receive queue */ - struct i40e_adminq_ring asq; /* send queue */ +struct iavf_adminq_info { + struct iavf_adminq_ring arq; /* receive queue */ + struct iavf_adminq_ring asq; /* send queue */ u32 asq_cmd_timeout; /* send queue cmd write back timeout*/ u16 num_arq_entries; /* receive queue depth */ u16 num_asq_entries; /* send queue depth */ @@ -130,7 +130,6 @@ static inline int i40e_aq_rc_to_posix(int aq_ret, int aq_rc) #define I40E_AQ_LARGE_BUF 512 #define I40E_ASQ_CMD_TIMEOUT 250000 /* usecs */ -void i40evf_fill_default_direct_cmd_desc(struct i40e_aq_desc *desc, - u16 opcode); +void iavf_fill_default_direct_cmd_desc(struct i40e_aq_desc *desc, u16 opcode); -#endif /* _I40E_ADMINQ_H_ */ +#endif /* _IAVF_ADMINQ_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/iavf/i40e_adminq_cmd.h new file mode 100644 index 000000000000..af4f94a6541e --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/i40e_adminq_cmd.h @@ -0,0 +1,530 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#ifndef _I40E_ADMINQ_CMD_H_ +#define _I40E_ADMINQ_CMD_H_ + +/* This header file defines the i40e Admin Queue commands and is shared between + * i40e Firmware and Software. Do not change the names in this file to IAVF + * because this file should be diff-able against the i40e version, even + * though many parts have been removed in this VF version. + * + * This file needs to comply with the Linux Kernel coding style. + */ + +#define I40E_FW_API_VERSION_MAJOR 0x0001 +#define I40E_FW_API_VERSION_MINOR_X722 0x0005 +#define I40E_FW_API_VERSION_MINOR_X710 0x0007 + +#define I40E_FW_MINOR_VERSION(_h) ((_h)->mac.type == I40E_MAC_XL710 ? \ + I40E_FW_API_VERSION_MINOR_X710 : \ + I40E_FW_API_VERSION_MINOR_X722) + +/* API version 1.7 implements additional link and PHY-specific APIs */ +#define I40E_MINOR_VER_GET_LINK_INFO_XL710 0x0007 + +struct i40e_aq_desc { + __le16 flags; + __le16 opcode; + __le16 datalen; + __le16 retval; + __le32 cookie_high; + __le32 cookie_low; + union { + struct { + __le32 param0; + __le32 param1; + __le32 param2; + __le32 param3; + } internal; + struct { + __le32 param0; + __le32 param1; + __le32 addr_high; + __le32 addr_low; + } external; + u8 raw[16]; + } params; +}; + +/* Flags sub-structure + * |0 |1 |2 |3 |4 |5 |6 |7 |8 |9 |10 |11 |12 |13 |14 |15 | + * |DD |CMP|ERR|VFE| * * RESERVED * * |LB |RD |VFC|BUF|SI |EI |FE | + */ + +/* command flags and offsets*/ +#define I40E_AQ_FLAG_DD_SHIFT 0 +#define I40E_AQ_FLAG_CMP_SHIFT 1 +#define I40E_AQ_FLAG_ERR_SHIFT 2 +#define I40E_AQ_FLAG_VFE_SHIFT 3 +#define I40E_AQ_FLAG_LB_SHIFT 9 +#define I40E_AQ_FLAG_RD_SHIFT 10 +#define I40E_AQ_FLAG_VFC_SHIFT 11 +#define I40E_AQ_FLAG_BUF_SHIFT 12 +#define I40E_AQ_FLAG_SI_SHIFT 13 +#define I40E_AQ_FLAG_EI_SHIFT 14 +#define I40E_AQ_FLAG_FE_SHIFT 15 + +#define I40E_AQ_FLAG_DD BIT(I40E_AQ_FLAG_DD_SHIFT) /* 0x1 */ +#define I40E_AQ_FLAG_CMP BIT(I40E_AQ_FLAG_CMP_SHIFT) /* 0x2 */ +#define I40E_AQ_FLAG_ERR BIT(I40E_AQ_FLAG_ERR_SHIFT) /* 0x4 */ +#define I40E_AQ_FLAG_VFE BIT(I40E_AQ_FLAG_VFE_SHIFT) /* 0x8 */ +#define I40E_AQ_FLAG_LB BIT(I40E_AQ_FLAG_LB_SHIFT) /* 0x200 */ +#define I40E_AQ_FLAG_RD BIT(I40E_AQ_FLAG_RD_SHIFT) /* 0x400 */ +#define I40E_AQ_FLAG_VFC BIT(I40E_AQ_FLAG_VFC_SHIFT) /* 0x800 */ +#define I40E_AQ_FLAG_BUF BIT(I40E_AQ_FLAG_BUF_SHIFT) /* 0x1000 */ +#define I40E_AQ_FLAG_SI BIT(I40E_AQ_FLAG_SI_SHIFT) /* 0x2000 */ +#define I40E_AQ_FLAG_EI BIT(I40E_AQ_FLAG_EI_SHIFT) /* 0x4000 */ +#define I40E_AQ_FLAG_FE BIT(I40E_AQ_FLAG_FE_SHIFT) /* 0x8000 */ + +/* error codes */ +enum i40e_admin_queue_err { + I40E_AQ_RC_OK = 0, /* success */ + I40E_AQ_RC_EPERM = 1, /* Operation not permitted */ + I40E_AQ_RC_ENOENT = 2, /* No such element */ + I40E_AQ_RC_ESRCH = 3, /* Bad opcode */ + I40E_AQ_RC_EINTR = 4, /* operation interrupted */ + I40E_AQ_RC_EIO = 5, /* I/O error */ + I40E_AQ_RC_ENXIO = 6, /* No such resource */ + I40E_AQ_RC_E2BIG = 7, /* Arg too long */ + I40E_AQ_RC_EAGAIN = 8, /* Try again */ + I40E_AQ_RC_ENOMEM = 9, /* Out of memory */ + I40E_AQ_RC_EACCES = 10, /* Permission denied */ + I40E_AQ_RC_EFAULT = 11, /* Bad address */ + I40E_AQ_RC_EBUSY = 12, /* Device or resource busy */ + I40E_AQ_RC_EEXIST = 13, /* object already exists */ + I40E_AQ_RC_EINVAL = 14, /* Invalid argument */ + I40E_AQ_RC_ENOTTY = 15, /* Not a typewriter */ + I40E_AQ_RC_ENOSPC = 16, /* No space left or alloc failure */ + I40E_AQ_RC_ENOSYS = 17, /* Function not implemented */ + I40E_AQ_RC_ERANGE = 18, /* Parameter out of range */ + I40E_AQ_RC_EFLUSHED = 19, /* Cmd flushed due to prev cmd error */ + I40E_AQ_RC_BAD_ADDR = 20, /* Descriptor contains a bad pointer */ + I40E_AQ_RC_EMODE = 21, /* Op not allowed in current dev mode */ + I40E_AQ_RC_EFBIG = 22, /* File too large */ +}; + +/* Admin Queue command opcodes */ +enum i40e_admin_queue_opc { + /* aq commands */ + i40e_aqc_opc_get_version = 0x0001, + i40e_aqc_opc_driver_version = 0x0002, + i40e_aqc_opc_queue_shutdown = 0x0003, + i40e_aqc_opc_set_pf_context = 0x0004, + + /* resource ownership */ + i40e_aqc_opc_request_resource = 0x0008, + i40e_aqc_opc_release_resource = 0x0009, + + i40e_aqc_opc_list_func_capabilities = 0x000A, + i40e_aqc_opc_list_dev_capabilities = 0x000B, + + /* Proxy commands */ + i40e_aqc_opc_set_proxy_config = 0x0104, + i40e_aqc_opc_set_ns_proxy_table_entry = 0x0105, + + /* LAA */ + i40e_aqc_opc_mac_address_read = 0x0107, + i40e_aqc_opc_mac_address_write = 0x0108, + + /* PXE */ + i40e_aqc_opc_clear_pxe_mode = 0x0110, + + /* WoL commands */ + i40e_aqc_opc_set_wol_filter = 0x0120, + i40e_aqc_opc_get_wake_reason = 0x0121, + + /* internal switch commands */ + i40e_aqc_opc_get_switch_config = 0x0200, + i40e_aqc_opc_add_statistics = 0x0201, + i40e_aqc_opc_remove_statistics = 0x0202, + i40e_aqc_opc_set_port_parameters = 0x0203, + i40e_aqc_opc_get_switch_resource_alloc = 0x0204, + i40e_aqc_opc_set_switch_config = 0x0205, + i40e_aqc_opc_rx_ctl_reg_read = 0x0206, + i40e_aqc_opc_rx_ctl_reg_write = 0x0207, + + i40e_aqc_opc_add_vsi = 0x0210, + i40e_aqc_opc_update_vsi_parameters = 0x0211, + i40e_aqc_opc_get_vsi_parameters = 0x0212, + + i40e_aqc_opc_add_pv = 0x0220, + i40e_aqc_opc_update_pv_parameters = 0x0221, + i40e_aqc_opc_get_pv_parameters = 0x0222, + + i40e_aqc_opc_add_veb = 0x0230, + i40e_aqc_opc_update_veb_parameters = 0x0231, + i40e_aqc_opc_get_veb_parameters = 0x0232, + + i40e_aqc_opc_delete_element = 0x0243, + + i40e_aqc_opc_add_macvlan = 0x0250, + i40e_aqc_opc_remove_macvlan = 0x0251, + i40e_aqc_opc_add_vlan = 0x0252, + i40e_aqc_opc_remove_vlan = 0x0253, + i40e_aqc_opc_set_vsi_promiscuous_modes = 0x0254, + i40e_aqc_opc_add_tag = 0x0255, + i40e_aqc_opc_remove_tag = 0x0256, + i40e_aqc_opc_add_multicast_etag = 0x0257, + i40e_aqc_opc_remove_multicast_etag = 0x0258, + i40e_aqc_opc_update_tag = 0x0259, + i40e_aqc_opc_add_control_packet_filter = 0x025A, + i40e_aqc_opc_remove_control_packet_filter = 0x025B, + i40e_aqc_opc_add_cloud_filters = 0x025C, + i40e_aqc_opc_remove_cloud_filters = 0x025D, + i40e_aqc_opc_clear_wol_switch_filters = 0x025E, + + i40e_aqc_opc_add_mirror_rule = 0x0260, + i40e_aqc_opc_delete_mirror_rule = 0x0261, + + /* Dynamic Device Personalization */ + i40e_aqc_opc_write_personalization_profile = 0x0270, + i40e_aqc_opc_get_personalization_profile_list = 0x0271, + + /* DCB commands */ + i40e_aqc_opc_dcb_ignore_pfc = 0x0301, + i40e_aqc_opc_dcb_updated = 0x0302, + i40e_aqc_opc_set_dcb_parameters = 0x0303, + + /* TX scheduler */ + i40e_aqc_opc_configure_vsi_bw_limit = 0x0400, + i40e_aqc_opc_configure_vsi_ets_sla_bw_limit = 0x0406, + i40e_aqc_opc_configure_vsi_tc_bw = 0x0407, + i40e_aqc_opc_query_vsi_bw_config = 0x0408, + i40e_aqc_opc_query_vsi_ets_sla_config = 0x040A, + i40e_aqc_opc_configure_switching_comp_bw_limit = 0x0410, + + i40e_aqc_opc_enable_switching_comp_ets = 0x0413, + i40e_aqc_opc_modify_switching_comp_ets = 0x0414, + i40e_aqc_opc_disable_switching_comp_ets = 0x0415, + i40e_aqc_opc_configure_switching_comp_ets_bw_limit = 0x0416, + i40e_aqc_opc_configure_switching_comp_bw_config = 0x0417, + i40e_aqc_opc_query_switching_comp_ets_config = 0x0418, + i40e_aqc_opc_query_port_ets_config = 0x0419, + i40e_aqc_opc_query_switching_comp_bw_config = 0x041A, + i40e_aqc_opc_suspend_port_tx = 0x041B, + i40e_aqc_opc_resume_port_tx = 0x041C, + i40e_aqc_opc_configure_partition_bw = 0x041D, + /* hmc */ + i40e_aqc_opc_query_hmc_resource_profile = 0x0500, + i40e_aqc_opc_set_hmc_resource_profile = 0x0501, + + /* phy commands*/ + i40e_aqc_opc_get_phy_abilities = 0x0600, + i40e_aqc_opc_set_phy_config = 0x0601, + i40e_aqc_opc_set_mac_config = 0x0603, + i40e_aqc_opc_set_link_restart_an = 0x0605, + i40e_aqc_opc_get_link_status = 0x0607, + i40e_aqc_opc_set_phy_int_mask = 0x0613, + i40e_aqc_opc_get_local_advt_reg = 0x0614, + i40e_aqc_opc_set_local_advt_reg = 0x0615, + i40e_aqc_opc_get_partner_advt = 0x0616, + i40e_aqc_opc_set_lb_modes = 0x0618, + i40e_aqc_opc_get_phy_wol_caps = 0x0621, + i40e_aqc_opc_set_phy_debug = 0x0622, + i40e_aqc_opc_upload_ext_phy_fm = 0x0625, + i40e_aqc_opc_run_phy_activity = 0x0626, + i40e_aqc_opc_set_phy_register = 0x0628, + i40e_aqc_opc_get_phy_register = 0x0629, + + /* NVM commands */ + i40e_aqc_opc_nvm_read = 0x0701, + i40e_aqc_opc_nvm_erase = 0x0702, + i40e_aqc_opc_nvm_update = 0x0703, + i40e_aqc_opc_nvm_config_read = 0x0704, + i40e_aqc_opc_nvm_config_write = 0x0705, + i40e_aqc_opc_oem_post_update = 0x0720, + i40e_aqc_opc_thermal_sensor = 0x0721, + + /* virtualization commands */ + i40e_aqc_opc_send_msg_to_pf = 0x0801, + i40e_aqc_opc_send_msg_to_vf = 0x0802, + i40e_aqc_opc_send_msg_to_peer = 0x0803, + + /* alternate structure */ + i40e_aqc_opc_alternate_write = 0x0900, + i40e_aqc_opc_alternate_write_indirect = 0x0901, + i40e_aqc_opc_alternate_read = 0x0902, + i40e_aqc_opc_alternate_read_indirect = 0x0903, + i40e_aqc_opc_alternate_write_done = 0x0904, + i40e_aqc_opc_alternate_set_mode = 0x0905, + i40e_aqc_opc_alternate_clear_port = 0x0906, + + /* LLDP commands */ + i40e_aqc_opc_lldp_get_mib = 0x0A00, + i40e_aqc_opc_lldp_update_mib = 0x0A01, + i40e_aqc_opc_lldp_add_tlv = 0x0A02, + i40e_aqc_opc_lldp_update_tlv = 0x0A03, + i40e_aqc_opc_lldp_delete_tlv = 0x0A04, + i40e_aqc_opc_lldp_stop = 0x0A05, + i40e_aqc_opc_lldp_start = 0x0A06, + + /* Tunnel commands */ + i40e_aqc_opc_add_udp_tunnel = 0x0B00, + i40e_aqc_opc_del_udp_tunnel = 0x0B01, + i40e_aqc_opc_set_rss_key = 0x0B02, + i40e_aqc_opc_set_rss_lut = 0x0B03, + i40e_aqc_opc_get_rss_key = 0x0B04, + i40e_aqc_opc_get_rss_lut = 0x0B05, + + /* Async Events */ + i40e_aqc_opc_event_lan_overflow = 0x1001, + + /* OEM commands */ + i40e_aqc_opc_oem_parameter_change = 0xFE00, + i40e_aqc_opc_oem_device_status_change = 0xFE01, + i40e_aqc_opc_oem_ocsd_initialize = 0xFE02, + i40e_aqc_opc_oem_ocbb_initialize = 0xFE03, + + /* debug commands */ + i40e_aqc_opc_debug_read_reg = 0xFF03, + i40e_aqc_opc_debug_write_reg = 0xFF04, + i40e_aqc_opc_debug_modify_reg = 0xFF07, + i40e_aqc_opc_debug_dump_internals = 0xFF08, +}; + +/* command structures and indirect data structures */ + +/* Structure naming conventions: + * - no suffix for direct command descriptor structures + * - _data for indirect sent data + * - _resp for indirect return data (data which is both will use _data) + * - _completion for direct return data + * - _element_ for repeated elements (may also be _data or _resp) + * + * Command structures are expected to overlay the params.raw member of the basic + * descriptor, and as such cannot exceed 16 bytes in length. + */ + +/* This macro is used to generate a compilation error if a structure + * is not exactly the correct length. It gives a divide by zero error if the + * structure is not of the correct size, otherwise it creates an enum that is + * never used. + */ +#define I40E_CHECK_STRUCT_LEN(n, X) enum i40e_static_assert_enum_##X \ + { i40e_static_assert_##X = (n)/((sizeof(struct X) == (n)) ? 1 : 0) } + +/* This macro is used extensively to ensure that command structures are 16 + * bytes in length as they have to map to the raw array of that size. + */ +#define I40E_CHECK_CMD_LENGTH(X) I40E_CHECK_STRUCT_LEN(16, X) + +/* Queue Shutdown (direct 0x0003) */ +struct i40e_aqc_queue_shutdown { + __le32 driver_unloading; +#define I40E_AQ_DRIVER_UNLOADING 0x1 + u8 reserved[12]; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_queue_shutdown); + +struct i40e_aqc_vsi_properties_data { + /* first 96 byte are written by SW */ + __le16 valid_sections; +#define I40E_AQ_VSI_PROP_SWITCH_VALID 0x0001 +#define I40E_AQ_VSI_PROP_SECURITY_VALID 0x0002 +#define I40E_AQ_VSI_PROP_VLAN_VALID 0x0004 +#define I40E_AQ_VSI_PROP_CAS_PV_VALID 0x0008 +#define I40E_AQ_VSI_PROP_INGRESS_UP_VALID 0x0010 +#define I40E_AQ_VSI_PROP_EGRESS_UP_VALID 0x0020 +#define I40E_AQ_VSI_PROP_QUEUE_MAP_VALID 0x0040 +#define I40E_AQ_VSI_PROP_QUEUE_OPT_VALID 0x0080 +#define I40E_AQ_VSI_PROP_OUTER_UP_VALID 0x0100 +#define I40E_AQ_VSI_PROP_SCHED_VALID 0x0200 + /* switch section */ + __le16 switch_id; /* 12bit id combined with flags below */ +#define I40E_AQ_VSI_SW_ID_SHIFT 0x0000 +#define I40E_AQ_VSI_SW_ID_MASK (0xFFF << I40E_AQ_VSI_SW_ID_SHIFT) +#define I40E_AQ_VSI_SW_ID_FLAG_NOT_STAG 0x1000 +#define I40E_AQ_VSI_SW_ID_FLAG_ALLOW_LB 0x2000 +#define I40E_AQ_VSI_SW_ID_FLAG_LOCAL_LB 0x4000 + u8 sw_reserved[2]; + /* security section */ + u8 sec_flags; +#define I40E_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD 0x01 +#define I40E_AQ_VSI_SEC_FLAG_ENABLE_VLAN_CHK 0x02 +#define I40E_AQ_VSI_SEC_FLAG_ENABLE_MAC_CHK 0x04 + u8 sec_reserved; + /* VLAN section */ + __le16 pvid; /* VLANS include priority bits */ + __le16 fcoe_pvid; + u8 port_vlan_flags; +#define I40E_AQ_VSI_PVLAN_MODE_SHIFT 0x00 +#define I40E_AQ_VSI_PVLAN_MODE_MASK (0x03 << \ + I40E_AQ_VSI_PVLAN_MODE_SHIFT) +#define I40E_AQ_VSI_PVLAN_MODE_TAGGED 0x01 +#define I40E_AQ_VSI_PVLAN_MODE_UNTAGGED 0x02 +#define I40E_AQ_VSI_PVLAN_MODE_ALL 0x03 +#define I40E_AQ_VSI_PVLAN_INSERT_PVID 0x04 +#define I40E_AQ_VSI_PVLAN_EMOD_SHIFT 0x03 +#define I40E_AQ_VSI_PVLAN_EMOD_MASK (0x3 << \ + I40E_AQ_VSI_PVLAN_EMOD_SHIFT) +#define I40E_AQ_VSI_PVLAN_EMOD_STR_BOTH 0x0 +#define I40E_AQ_VSI_PVLAN_EMOD_STR_UP 0x08 +#define I40E_AQ_VSI_PVLAN_EMOD_STR 0x10 +#define I40E_AQ_VSI_PVLAN_EMOD_NOTHING 0x18 + u8 pvlan_reserved[3]; + /* ingress egress up sections */ + __le32 ingress_table; /* bitmap, 3 bits per up */ +#define I40E_AQ_VSI_UP_TABLE_UP0_SHIFT 0 +#define I40E_AQ_VSI_UP_TABLE_UP0_MASK (0x7 << \ + I40E_AQ_VSI_UP_TABLE_UP0_SHIFT) +#define I40E_AQ_VSI_UP_TABLE_UP1_SHIFT 3 +#define I40E_AQ_VSI_UP_TABLE_UP1_MASK (0x7 << \ + I40E_AQ_VSI_UP_TABLE_UP1_SHIFT) +#define I40E_AQ_VSI_UP_TABLE_UP2_SHIFT 6 +#define I40E_AQ_VSI_UP_TABLE_UP2_MASK (0x7 << \ + I40E_AQ_VSI_UP_TABLE_UP2_SHIFT) +#define I40E_AQ_VSI_UP_TABLE_UP3_SHIFT 9 +#define I40E_AQ_VSI_UP_TABLE_UP3_MASK (0x7 << \ + I40E_AQ_VSI_UP_TABLE_UP3_SHIFT) +#define I40E_AQ_VSI_UP_TABLE_UP4_SHIFT 12 +#define I40E_AQ_VSI_UP_TABLE_UP4_MASK (0x7 << \ + I40E_AQ_VSI_UP_TABLE_UP4_SHIFT) +#define I40E_AQ_VSI_UP_TABLE_UP5_SHIFT 15 +#define I40E_AQ_VSI_UP_TABLE_UP5_MASK (0x7 << \ + I40E_AQ_VSI_UP_TABLE_UP5_SHIFT) +#define I40E_AQ_VSI_UP_TABLE_UP6_SHIFT 18 +#define I40E_AQ_VSI_UP_TABLE_UP6_MASK (0x7 << \ + I40E_AQ_VSI_UP_TABLE_UP6_SHIFT) +#define I40E_AQ_VSI_UP_TABLE_UP7_SHIFT 21 +#define I40E_AQ_VSI_UP_TABLE_UP7_MASK (0x7 << \ + I40E_AQ_VSI_UP_TABLE_UP7_SHIFT) + __le32 egress_table; /* same defines as for ingress table */ + /* cascaded PV section */ + __le16 cas_pv_tag; + u8 cas_pv_flags; +#define I40E_AQ_VSI_CAS_PV_TAGX_SHIFT 0x00 +#define I40E_AQ_VSI_CAS_PV_TAGX_MASK (0x03 << \ + I40E_AQ_VSI_CAS_PV_TAGX_SHIFT) +#define I40E_AQ_VSI_CAS_PV_TAGX_LEAVE 0x00 +#define I40E_AQ_VSI_CAS_PV_TAGX_REMOVE 0x01 +#define I40E_AQ_VSI_CAS_PV_TAGX_COPY 0x02 +#define I40E_AQ_VSI_CAS_PV_INSERT_TAG 0x10 +#define I40E_AQ_VSI_CAS_PV_ETAG_PRUNE 0x20 +#define I40E_AQ_VSI_CAS_PV_ACCEPT_HOST_TAG 0x40 + u8 cas_pv_reserved; + /* queue mapping section */ + __le16 mapping_flags; +#define I40E_AQ_VSI_QUE_MAP_CONTIG 0x0 +#define I40E_AQ_VSI_QUE_MAP_NONCONTIG 0x1 + __le16 queue_mapping[16]; +#define I40E_AQ_VSI_QUEUE_SHIFT 0x0 +#define I40E_AQ_VSI_QUEUE_MASK (0x7FF << I40E_AQ_VSI_QUEUE_SHIFT) + __le16 tc_mapping[8]; +#define I40E_AQ_VSI_TC_QUE_OFFSET_SHIFT 0 +#define I40E_AQ_VSI_TC_QUE_OFFSET_MASK (0x1FF << \ + I40E_AQ_VSI_TC_QUE_OFFSET_SHIFT) +#define I40E_AQ_VSI_TC_QUE_NUMBER_SHIFT 9 +#define I40E_AQ_VSI_TC_QUE_NUMBER_MASK (0x7 << \ + I40E_AQ_VSI_TC_QUE_NUMBER_SHIFT) + /* queueing option section */ + u8 queueing_opt_flags; +#define I40E_AQ_VSI_QUE_OPT_MULTICAST_UDP_ENA 0x04 +#define I40E_AQ_VSI_QUE_OPT_UNICAST_UDP_ENA 0x08 +#define I40E_AQ_VSI_QUE_OPT_TCP_ENA 0x10 +#define I40E_AQ_VSI_QUE_OPT_FCOE_ENA 0x20 +#define I40E_AQ_VSI_QUE_OPT_RSS_LUT_PF 0x00 +#define I40E_AQ_VSI_QUE_OPT_RSS_LUT_VSI 0x40 + u8 queueing_opt_reserved[3]; + /* scheduler section */ + u8 up_enable_bits; + u8 sched_reserved; + /* outer up section */ + __le32 outer_up_table; /* same structure and defines as ingress tbl */ + u8 cmd_reserved[8]; + /* last 32 bytes are written by FW */ + __le16 qs_handle[8]; +#define I40E_AQ_VSI_QS_HANDLE_INVALID 0xFFFF + __le16 stat_counter_idx; + __le16 sched_id; + u8 resp_reserved[12]; +}; + +I40E_CHECK_STRUCT_LEN(128, i40e_aqc_vsi_properties_data); + +/* Get VEB Parameters (direct 0x0232) + * uses i40e_aqc_switch_seid for the descriptor + */ +struct i40e_aqc_get_veb_parameters_completion { + __le16 seid; + __le16 switch_id; + __le16 veb_flags; /* only the first/last flags from 0x0230 is valid */ + __le16 statistic_index; + __le16 vebs_used; + __le16 vebs_free; + u8 reserved[4]; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_get_veb_parameters_completion); + +#define I40E_LINK_SPEED_100MB_SHIFT 0x1 +#define I40E_LINK_SPEED_1000MB_SHIFT 0x2 +#define I40E_LINK_SPEED_10GB_SHIFT 0x3 +#define I40E_LINK_SPEED_40GB_SHIFT 0x4 +#define I40E_LINK_SPEED_20GB_SHIFT 0x5 +#define I40E_LINK_SPEED_25GB_SHIFT 0x6 + +enum i40e_aq_link_speed { + I40E_LINK_SPEED_UNKNOWN = 0, + I40E_LINK_SPEED_100MB = BIT(I40E_LINK_SPEED_100MB_SHIFT), + I40E_LINK_SPEED_1GB = BIT(I40E_LINK_SPEED_1000MB_SHIFT), + I40E_LINK_SPEED_10GB = BIT(I40E_LINK_SPEED_10GB_SHIFT), + I40E_LINK_SPEED_40GB = BIT(I40E_LINK_SPEED_40GB_SHIFT), + I40E_LINK_SPEED_20GB = BIT(I40E_LINK_SPEED_20GB_SHIFT), + I40E_LINK_SPEED_25GB = BIT(I40E_LINK_SPEED_25GB_SHIFT), +}; + +/* Send to PF command (indirect 0x0801) id is only used by PF + * Send to VF command (indirect 0x0802) id is only used by PF + * Send to Peer PF command (indirect 0x0803) + */ +struct i40e_aqc_pf_vf_message { + __le32 id; + u8 reserved[4]; + __le32 addr_high; + __le32 addr_low; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_pf_vf_message); + +struct i40e_aqc_get_set_rss_key { +#define I40E_AQC_SET_RSS_KEY_VSI_VALID BIT(15) +#define I40E_AQC_SET_RSS_KEY_VSI_ID_SHIFT 0 +#define I40E_AQC_SET_RSS_KEY_VSI_ID_MASK (0x3FF << \ + I40E_AQC_SET_RSS_KEY_VSI_ID_SHIFT) + __le16 vsi_id; + u8 reserved[6]; + __le32 addr_high; + __le32 addr_low; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_get_set_rss_key); + +struct i40e_aqc_get_set_rss_key_data { + u8 standard_rss_key[0x28]; + u8 extended_hash_key[0xc]; +}; + +I40E_CHECK_STRUCT_LEN(0x34, i40e_aqc_get_set_rss_key_data); + +struct i40e_aqc_get_set_rss_lut { +#define I40E_AQC_SET_RSS_LUT_VSI_VALID BIT(15) +#define I40E_AQC_SET_RSS_LUT_VSI_ID_SHIFT 0 +#define I40E_AQC_SET_RSS_LUT_VSI_ID_MASK (0x3FF << \ + I40E_AQC_SET_RSS_LUT_VSI_ID_SHIFT) + __le16 vsi_id; +#define I40E_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT 0 +#define I40E_AQC_SET_RSS_LUT_TABLE_TYPE_MASK \ + BIT(I40E_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT) + +#define I40E_AQC_SET_RSS_LUT_TABLE_TYPE_VSI 0 +#define I40E_AQC_SET_RSS_LUT_TABLE_TYPE_PF 1 + __le16 flags; + u8 reserved[4]; + __le32 addr_high; + __le32 addr_low; +}; + +I40E_CHECK_CMD_LENGTH(i40e_aqc_get_set_rss_lut); +#endif /* _I40E_ADMINQ_CMD_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h new file mode 100644 index 000000000000..a512f7521841 --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -0,0 +1,418 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#ifndef _IAVF_H_ +#define _IAVF_H_ + +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/aer.h> +#include <linux/netdevice.h> +#include <linux/vmalloc.h> +#include <linux/interrupt.h> +#include <linux/ethtool.h> +#include <linux/if_vlan.h> +#include <linux/ip.h> +#include <linux/tcp.h> +#include <linux/sctp.h> +#include <linux/ipv6.h> +#include <linux/kernel.h> +#include <linux/bitops.h> +#include <linux/timer.h> +#include <linux/workqueue.h> +#include <linux/wait.h> +#include <linux/delay.h> +#include <linux/gfp.h> +#include <linux/skbuff.h> +#include <linux/dma-mapping.h> +#include <linux/etherdevice.h> +#include <linux/socket.h> +#include <linux/jiffies.h> +#include <net/ip6_checksum.h> +#include <net/pkt_cls.h> +#include <net/udp.h> +#include <net/tc_act/tc_gact.h> +#include <net/tc_act/tc_mirred.h> + +#include "iavf_type.h" +#include <linux/avf/virtchnl.h> +#include "iavf_txrx.h" + +#define DEFAULT_DEBUG_LEVEL_SHIFT 3 +#define PFX "iavf: " + +/* VSI state flags shared with common code */ +enum iavf_vsi_state_t { + __IAVF_VSI_DOWN, + /* This must be last as it determines the size of the BITMAP */ + __IAVF_VSI_STATE_SIZE__, +}; + +/* dummy struct to make common code less painful */ +struct iavf_vsi { + struct iavf_adapter *back; + struct net_device *netdev; + unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; + u16 seid; + u16 id; + DECLARE_BITMAP(state, __IAVF_VSI_STATE_SIZE__); + int base_vector; + u16 work_limit; + u16 qs_handle; + void *priv; /* client driver data reference. */ +}; + +/* How many Rx Buffers do we bundle into one write to the hardware ? */ +#define IAVF_RX_BUFFER_WRITE 16 /* Must be power of 2 */ +#define IAVF_DEFAULT_TXD 512 +#define IAVF_DEFAULT_RXD 512 +#define IAVF_MAX_TXD 4096 +#define IAVF_MIN_TXD 64 +#define IAVF_MAX_RXD 4096 +#define IAVF_MIN_RXD 64 +#define IAVF_REQ_DESCRIPTOR_MULTIPLE 32 +#define IAVF_MAX_AQ_BUF_SIZE 4096 +#define IAVF_AQ_LEN 32 +#define IAVF_AQ_MAX_ERR 20 /* times to try before resetting AQ */ + +#define MAXIMUM_ETHERNET_VLAN_SIZE (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN) + +#define IAVF_RX_DESC(R, i) (&(((union iavf_32byte_rx_desc *)((R)->desc))[i])) +#define IAVF_TX_DESC(R, i) (&(((struct iavf_tx_desc *)((R)->desc))[i])) +#define IAVF_TX_CTXTDESC(R, i) \ + (&(((struct iavf_tx_context_desc *)((R)->desc))[i])) +#define IAVF_MAX_REQ_QUEUES 4 + +#define IAVF_HKEY_ARRAY_SIZE ((IAVF_VFQF_HKEY_MAX_INDEX + 1) * 4) +#define IAVF_HLUT_ARRAY_SIZE ((IAVF_VFQF_HLUT_MAX_INDEX + 1) * 4) +#define IAVF_MBPS_DIVISOR 125000 /* divisor to convert to Mbps */ + +/* MAX_MSIX_Q_VECTORS of these are allocated, + * but we only use one per queue-specific vector. + */ +struct iavf_q_vector { + struct iavf_adapter *adapter; + struct iavf_vsi *vsi; + struct napi_struct napi; + struct iavf_ring_container rx; + struct iavf_ring_container tx; + u32 ring_mask; + u8 itr_countdown; /* when 0 should adjust adaptive ITR */ + u8 num_ringpairs; /* total number of ring pairs in vector */ + u16 v_idx; /* index in the vsi->q_vector array. */ + u16 reg_idx; /* register index of the interrupt */ + char name[IFNAMSIZ + 15]; + bool arm_wb_state; + cpumask_t affinity_mask; + struct irq_affinity_notify affinity_notify; +}; + +/* Helper macros to switch between ints/sec and what the register uses. + * And yes, it's the same math going both ways. The lowest value + * supported by all of the i40e hardware is 8. + */ +#define EITR_INTS_PER_SEC_TO_REG(_eitr) \ + ((_eitr) ? (1000000000 / ((_eitr) * 256)) : 8) +#define EITR_REG_TO_INTS_PER_SEC EITR_INTS_PER_SEC_TO_REG + +#define IAVF_DESC_UNUSED(R) \ + ((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \ + (R)->next_to_clean - (R)->next_to_use - 1) + +#define OTHER_VECTOR 1 +#define NONQ_VECS (OTHER_VECTOR) + +#define MIN_MSIX_Q_VECTORS 1 +#define MIN_MSIX_COUNT (MIN_MSIX_Q_VECTORS + NONQ_VECS) + +#define IAVF_QUEUE_END_OF_LIST 0x7FF +#define IAVF_FREE_VECTOR 0x7FFF +struct iavf_mac_filter { + struct list_head list; + u8 macaddr[ETH_ALEN]; + bool remove; /* filter needs to be removed */ + bool add; /* filter needs to be added */ +}; + +struct iavf_vlan_filter { + struct list_head list; + u16 vlan; + bool remove; /* filter needs to be removed */ + bool add; /* filter needs to be added */ +}; + +#define IAVF_MAX_TRAFFIC_CLASS 4 +/* State of traffic class creation */ +enum iavf_tc_state_t { + __IAVF_TC_INVALID, /* no traffic class, default state */ + __IAVF_TC_RUNNING, /* traffic classes have been created */ +}; + +/* channel info */ +struct iavf_channel_config { + struct virtchnl_channel_info ch_info[IAVF_MAX_TRAFFIC_CLASS]; + enum iavf_tc_state_t state; + u8 total_qps; +}; + +/* State of cloud filter */ +enum iavf_cloud_filter_state_t { + __IAVF_CF_INVALID, /* cloud filter not added */ + __IAVF_CF_ADD_PENDING, /* cloud filter pending add by the PF */ + __IAVF_CF_DEL_PENDING, /* cloud filter pending del by the PF */ + __IAVF_CF_ACTIVE, /* cloud filter is active */ +}; + +/* Driver state. The order of these is important! */ +enum iavf_state_t { + __IAVF_STARTUP, /* driver loaded, probe complete */ + __IAVF_REMOVE, /* driver is being unloaded */ + __IAVF_INIT_VERSION_CHECK, /* aq msg sent, awaiting reply */ + __IAVF_INIT_GET_RESOURCES, /* aq msg sent, awaiting reply */ + __IAVF_INIT_SW, /* got resources, setting up structs */ + __IAVF_RESETTING, /* in reset */ + /* Below here, watchdog is running */ + __IAVF_DOWN, /* ready, can be opened */ + __IAVF_DOWN_PENDING, /* descending, waiting for watchdog */ + __IAVF_TESTING, /* in ethtool self-test */ + __IAVF_RUNNING, /* opened, working */ +}; + +enum iavf_critical_section_t { + __IAVF_IN_CRITICAL_TASK, /* cannot be interrupted */ + __IAVF_IN_CLIENT_TASK, + __IAVF_IN_REMOVE_TASK, /* device being removed */ +}; + +#define IAVF_CLOUD_FIELD_OMAC 0x01 +#define IAVF_CLOUD_FIELD_IMAC 0x02 +#define IAVF_CLOUD_FIELD_IVLAN 0x04 +#define IAVF_CLOUD_FIELD_TEN_ID 0x08 +#define IAVF_CLOUD_FIELD_IIP 0x10 + +#define IAVF_CF_FLAGS_OMAC IAVF_CLOUD_FIELD_OMAC +#define IAVF_CF_FLAGS_IMAC IAVF_CLOUD_FIELD_IMAC +#define IAVF_CF_FLAGS_IMAC_IVLAN (IAVF_CLOUD_FIELD_IMAC |\ + IAVF_CLOUD_FIELD_IVLAN) +#define IAVF_CF_FLAGS_IMAC_TEN_ID (IAVF_CLOUD_FIELD_IMAC |\ + IAVF_CLOUD_FIELD_TEN_ID) +#define IAVF_CF_FLAGS_OMAC_TEN_ID_IMAC (IAVF_CLOUD_FIELD_OMAC |\ + IAVF_CLOUD_FIELD_IMAC |\ + IAVF_CLOUD_FIELD_TEN_ID) +#define IAVF_CF_FLAGS_IMAC_IVLAN_TEN_ID (IAVF_CLOUD_FIELD_IMAC |\ + IAVF_CLOUD_FIELD_IVLAN |\ + IAVF_CLOUD_FIELD_TEN_ID) +#define IAVF_CF_FLAGS_IIP IAVF_CLOUD_FIELD_IIP + +/* bookkeeping of cloud filters */ +struct iavf_cloud_filter { + enum iavf_cloud_filter_state_t state; + struct list_head list; + struct virtchnl_filter f; + unsigned long cookie; + bool del; /* filter needs to be deleted */ + bool add; /* filter needs to be added */ +}; + +/* board specific private data structure */ +struct iavf_adapter { + struct timer_list watchdog_timer; + struct work_struct reset_task; + struct work_struct adminq_task; + struct delayed_work client_task; + struct delayed_work init_task; + wait_queue_head_t down_waitqueue; + struct iavf_q_vector *q_vectors; + struct list_head vlan_filter_list; + struct list_head mac_filter_list; + /* Lock to protect accesses to MAC and VLAN lists */ + spinlock_t mac_vlan_list_lock; + char misc_vector_name[IFNAMSIZ + 9]; + int num_active_queues; + int num_req_queues; + + /* TX */ + struct iavf_ring *tx_rings; + u32 tx_timeout_count; + u32 tx_desc_count; + + /* RX */ + struct iavf_ring *rx_rings; + u64 hw_csum_rx_error; + u32 rx_desc_count; + int num_msix_vectors; + int num_iwarp_msix; + int iwarp_base_vector; + u32 client_pending; + struct i40e_client_instance *cinst; + struct msix_entry *msix_entries; + + u32 flags; +#define IAVF_FLAG_RX_CSUM_ENABLED BIT(0) +#define IAVF_FLAG_PF_COMMS_FAILED BIT(3) +#define IAVF_FLAG_RESET_PENDING BIT(4) +#define IAVF_FLAG_RESET_NEEDED BIT(5) +#define IAVF_FLAG_WB_ON_ITR_CAPABLE BIT(6) +#define IAVF_FLAG_ADDR_SET_BY_PF BIT(8) +#define IAVF_FLAG_SERVICE_CLIENT_REQUESTED BIT(9) +#define IAVF_FLAG_CLIENT_NEEDS_OPEN BIT(10) +#define IAVF_FLAG_CLIENT_NEEDS_CLOSE BIT(11) +#define IAVF_FLAG_CLIENT_NEEDS_L2_PARAMS BIT(12) +#define IAVF_FLAG_PROMISC_ON BIT(13) +#define IAVF_FLAG_ALLMULTI_ON BIT(14) +#define IAVF_FLAG_LEGACY_RX BIT(15) +#define IAVF_FLAG_REINIT_ITR_NEEDED BIT(16) +#define IAVF_FLAG_QUEUES_DISABLED BIT(17) +/* duplicates for common code */ +#define IAVF_FLAG_DCB_ENABLED 0 + /* flags for admin queue service task */ + u32 aq_required; +#define IAVF_FLAG_AQ_ENABLE_QUEUES BIT(0) +#define IAVF_FLAG_AQ_DISABLE_QUEUES BIT(1) +#define IAVF_FLAG_AQ_ADD_MAC_FILTER BIT(2) +#define IAVF_FLAG_AQ_ADD_VLAN_FILTER BIT(3) +#define IAVF_FLAG_AQ_DEL_MAC_FILTER BIT(4) +#define IAVF_FLAG_AQ_DEL_VLAN_FILTER BIT(5) +#define IAVF_FLAG_AQ_CONFIGURE_QUEUES BIT(6) +#define IAVF_FLAG_AQ_MAP_VECTORS BIT(7) +#define IAVF_FLAG_AQ_HANDLE_RESET BIT(8) +#define IAVF_FLAG_AQ_CONFIGURE_RSS BIT(9) /* direct AQ config */ +#define IAVF_FLAG_AQ_GET_CONFIG BIT(10) +/* Newer style, RSS done by the PF so we can ignore hardware vagaries. */ +#define IAVF_FLAG_AQ_GET_HENA BIT(11) +#define IAVF_FLAG_AQ_SET_HENA BIT(12) +#define IAVF_FLAG_AQ_SET_RSS_KEY BIT(13) +#define IAVF_FLAG_AQ_SET_RSS_LUT BIT(14) +#define IAVF_FLAG_AQ_REQUEST_PROMISC BIT(15) +#define IAVF_FLAG_AQ_RELEASE_PROMISC BIT(16) +#define IAVF_FLAG_AQ_REQUEST_ALLMULTI BIT(17) +#define IAVF_FLAG_AQ_RELEASE_ALLMULTI BIT(18) +#define IAVF_FLAG_AQ_ENABLE_VLAN_STRIPPING BIT(19) +#define IAVF_FLAG_AQ_DISABLE_VLAN_STRIPPING BIT(20) +#define IAVF_FLAG_AQ_ENABLE_CHANNELS BIT(21) +#define IAVF_FLAG_AQ_DISABLE_CHANNELS BIT(22) +#define IAVF_FLAG_AQ_ADD_CLOUD_FILTER BIT(23) +#define IAVF_FLAG_AQ_DEL_CLOUD_FILTER BIT(24) + + /* OS defined structs */ + struct net_device *netdev; + struct pci_dev *pdev; + + struct iavf_hw hw; /* defined in iavf_type.h */ + + enum iavf_state_t state; + unsigned long crit_section; + + struct work_struct watchdog_task; + bool netdev_registered; + bool link_up; + enum virtchnl_link_speed link_speed; + enum virtchnl_ops current_op; +#define CLIENT_ALLOWED(_a) ((_a)->vf_res ? \ + (_a)->vf_res->vf_cap_flags & \ + VIRTCHNL_VF_OFFLOAD_IWARP : \ + 0) +#define CLIENT_ENABLED(_a) ((_a)->cinst) +/* RSS by the PF should be preferred over RSS via other methods. */ +#define RSS_PF(_a) ((_a)->vf_res->vf_cap_flags & \ + VIRTCHNL_VF_OFFLOAD_RSS_PF) +#define RSS_AQ(_a) ((_a)->vf_res->vf_cap_flags & \ + VIRTCHNL_VF_OFFLOAD_RSS_AQ) +#define RSS_REG(_a) (!((_a)->vf_res->vf_cap_flags & \ + (VIRTCHNL_VF_OFFLOAD_RSS_AQ | \ + VIRTCHNL_VF_OFFLOAD_RSS_PF))) +#define VLAN_ALLOWED(_a) ((_a)->vf_res->vf_cap_flags & \ + VIRTCHNL_VF_OFFLOAD_VLAN) + struct virtchnl_vf_resource *vf_res; /* incl. all VSIs */ + struct virtchnl_vsi_resource *vsi_res; /* our LAN VSI */ + struct virtchnl_version_info pf_version; +#define PF_IS_V11(_a) (((_a)->pf_version.major == 1) && \ + ((_a)->pf_version.minor == 1)) + u16 msg_enable; + struct iavf_eth_stats current_stats; + struct iavf_vsi vsi; + u32 aq_wait_count; + /* RSS stuff */ + u64 hena; + u16 rss_key_size; + u16 rss_lut_size; + u8 *rss_key; + u8 *rss_lut; + /* ADQ related members */ + struct iavf_channel_config ch_config; + u8 num_tc; + struct list_head cloud_filter_list; + /* lock to protest access to the cloud filter list */ + spinlock_t cloud_filter_list_lock; + u16 num_cloud_filters; +}; + + +/* Ethtool Private Flags */ + +/* lan device, used by client interface */ +struct i40e_device { + struct list_head list; + struct iavf_adapter *vf; +}; + +/* needed by iavf_ethtool.c */ +extern char iavf_driver_name[]; +extern const char iavf_driver_version[]; + +int iavf_up(struct iavf_adapter *adapter); +void iavf_down(struct iavf_adapter *adapter); +int iavf_process_config(struct iavf_adapter *adapter); +void iavf_schedule_reset(struct iavf_adapter *adapter); +void iavf_reset(struct iavf_adapter *adapter); +void iavf_set_ethtool_ops(struct net_device *netdev); +void iavf_update_stats(struct iavf_adapter *adapter); +void iavf_reset_interrupt_capability(struct iavf_adapter *adapter); +int iavf_init_interrupt_scheme(struct iavf_adapter *adapter); +void iavf_irq_enable_queues(struct iavf_adapter *adapter, u32 mask); +void iavf_free_all_tx_resources(struct iavf_adapter *adapter); +void iavf_free_all_rx_resources(struct iavf_adapter *adapter); + +void iavf_napi_add_all(struct iavf_adapter *adapter); +void iavf_napi_del_all(struct iavf_adapter *adapter); + +int iavf_send_api_ver(struct iavf_adapter *adapter); +int iavf_verify_api_ver(struct iavf_adapter *adapter); +int iavf_send_vf_config_msg(struct iavf_adapter *adapter); +int iavf_get_vf_config(struct iavf_adapter *adapter); +void iavf_irq_enable(struct iavf_adapter *adapter, bool flush); +void iavf_configure_queues(struct iavf_adapter *adapter); +void iavf_deconfigure_queues(struct iavf_adapter *adapter); +void iavf_enable_queues(struct iavf_adapter *adapter); +void iavf_disable_queues(struct iavf_adapter *adapter); +void iavf_map_queues(struct iavf_adapter *adapter); +int iavf_request_queues(struct iavf_adapter *adapter, int num); +void iavf_add_ether_addrs(struct iavf_adapter *adapter); +void iavf_del_ether_addrs(struct iavf_adapter *adapter); +void iavf_add_vlans(struct iavf_adapter *adapter); +void iavf_del_vlans(struct iavf_adapter *adapter); +void iavf_set_promiscuous(struct iavf_adapter *adapter, int flags); +void iavf_request_stats(struct iavf_adapter *adapter); +void iavf_request_reset(struct iavf_adapter *adapter); +void iavf_get_hena(struct iavf_adapter *adapter); +void iavf_set_hena(struct iavf_adapter *adapter); +void iavf_set_rss_key(struct iavf_adapter *adapter); +void iavf_set_rss_lut(struct iavf_adapter *adapter); +void iavf_enable_vlan_stripping(struct iavf_adapter *adapter); +void iavf_disable_vlan_stripping(struct iavf_adapter *adapter); +void iavf_virtchnl_completion(struct iavf_adapter *adapter, + enum virtchnl_ops v_opcode, + iavf_status v_retval, u8 *msg, u16 msglen); +int iavf_config_rss(struct iavf_adapter *adapter); +int iavf_lan_add_device(struct iavf_adapter *adapter); +int iavf_lan_del_device(struct iavf_adapter *adapter); +void iavf_client_subtask(struct iavf_adapter *adapter); +void iavf_notify_client_message(struct iavf_vsi *vsi, u8 *msg, u16 len); +void iavf_notify_client_l2_params(struct iavf_vsi *vsi); +void iavf_notify_client_open(struct iavf_vsi *vsi); +void iavf_notify_client_close(struct iavf_vsi *vsi, bool reset); +void iavf_enable_channels(struct iavf_adapter *adapter); +void iavf_disable_channels(struct iavf_adapter *adapter); +void iavf_add_cloud_filter(struct iavf_adapter *adapter); +void iavf_del_cloud_filter(struct iavf_adapter *adapter); +#endif /* _IAVF_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_alloc.h b/drivers/net/ethernet/intel/iavf/iavf_alloc.h new file mode 100644 index 000000000000..bf2753146f30 --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_alloc.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#ifndef _IAVF_ALLOC_H_ +#define _IAVF_ALLOC_H_ + +struct iavf_hw; + +/* Memory allocation types */ +enum iavf_memory_type { + iavf_mem_arq_buf = 0, /* ARQ indirect command buffer */ + iavf_mem_asq_buf = 1, + iavf_mem_atq_buf = 2, /* ATQ indirect command buffer */ + iavf_mem_arq_ring = 3, /* ARQ descriptor ring */ + iavf_mem_atq_ring = 4, /* ATQ descriptor ring */ + iavf_mem_pd = 5, /* Page Descriptor */ + iavf_mem_bp = 6, /* Backing Page - 4KB */ + iavf_mem_bp_jumbo = 7, /* Backing Page - > 4KB */ + iavf_mem_reserved +}; + +/* prototype for functions used for dynamic memory allocation */ +iavf_status iavf_allocate_dma_mem(struct iavf_hw *hw, struct iavf_dma_mem *mem, + enum iavf_memory_type type, + u64 size, u32 alignment); +iavf_status iavf_free_dma_mem(struct iavf_hw *hw, struct iavf_dma_mem *mem); +iavf_status iavf_allocate_virt_mem(struct iavf_hw *hw, + struct iavf_virt_mem *mem, u32 size); +iavf_status iavf_free_virt_mem(struct iavf_hw *hw, struct iavf_virt_mem *mem); + +#endif /* _IAVF_ALLOC_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_client.c b/drivers/net/ethernet/intel/iavf/iavf_client.c index 3cc9d60d0d72..aea45364fd1c 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_client.c +++ b/drivers/net/ethernet/intel/iavf/iavf_client.c @@ -4,36 +4,36 @@ #include <linux/list.h> #include <linux/errno.h> -#include "i40evf.h" -#include "i40e_prototype.h" -#include "i40evf_client.h" +#include "iavf.h" +#include "iavf_prototype.h" +#include "iavf_client.h" static -const char i40evf_client_interface_version_str[] = I40EVF_CLIENT_VERSION_STR; +const char iavf_client_interface_version_str[] = IAVF_CLIENT_VERSION_STR; static struct i40e_client *vf_registered_client; -static LIST_HEAD(i40evf_devices); -static DEFINE_MUTEX(i40evf_device_mutex); +static LIST_HEAD(i40e_devices); +static DEFINE_MUTEX(iavf_device_mutex); -static u32 i40evf_client_virtchnl_send(struct i40e_info *ldev, - struct i40e_client *client, - u8 *msg, u16 len); +static u32 iavf_client_virtchnl_send(struct i40e_info *ldev, + struct i40e_client *client, + u8 *msg, u16 len); -static int i40evf_client_setup_qvlist(struct i40e_info *ldev, - struct i40e_client *client, - struct i40e_qvlist_info *qvlist_info); +static int iavf_client_setup_qvlist(struct i40e_info *ldev, + struct i40e_client *client, + struct i40e_qvlist_info *qvlist_info); -static struct i40e_ops i40evf_lan_ops = { - .virtchnl_send = i40evf_client_virtchnl_send, - .setup_qvlist = i40evf_client_setup_qvlist, +static struct i40e_ops iavf_lan_ops = { + .virtchnl_send = iavf_client_virtchnl_send, + .setup_qvlist = iavf_client_setup_qvlist, }; /** - * i40evf_client_get_params - retrieve relevant client parameters + * iavf_client_get_params - retrieve relevant client parameters * @vsi: VSI with parameters * @params: client param struct **/ static -void i40evf_client_get_params(struct i40e_vsi *vsi, struct i40e_params *params) +void iavf_client_get_params(struct iavf_vsi *vsi, struct i40e_params *params) { int i; @@ -41,21 +41,21 @@ void i40evf_client_get_params(struct i40e_vsi *vsi, struct i40e_params *params) params->mtu = vsi->netdev->mtu; params->link_up = vsi->back->link_up; - for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) { + for (i = 0; i < IAVF_MAX_USER_PRIORITY; i++) { params->qos.prio_qos[i].tc = 0; params->qos.prio_qos[i].qs_handle = vsi->qs_handle; } } /** - * i40evf_notify_client_message - call the client message receive callback + * iavf_notify_client_message - call the client message receive callback * @vsi: the VSI associated with this client * @msg: message buffer * @len: length of message * * If there is a client to this VSI, call the client **/ -void i40evf_notify_client_message(struct i40e_vsi *vsi, u8 *msg, u16 len) +void iavf_notify_client_message(struct iavf_vsi *vsi, u8 *msg, u16 len) { struct i40e_client_instance *cinst; @@ -74,12 +74,12 @@ void i40evf_notify_client_message(struct i40e_vsi *vsi, u8 *msg, u16 len) } /** - * i40evf_notify_client_l2_params - call the client notify callback + * iavf_notify_client_l2_params - call the client notify callback * @vsi: the VSI with l2 param changes * * If there is a client to this VSI, call the client **/ -void i40evf_notify_client_l2_params(struct i40e_vsi *vsi) +void iavf_notify_client_l2_params(struct iavf_vsi *vsi) { struct i40e_client_instance *cinst; struct i40e_params params; @@ -95,21 +95,21 @@ void i40evf_notify_client_l2_params(struct i40e_vsi *vsi) "Cannot locate client instance l2_param_change function\n"); return; } - i40evf_client_get_params(vsi, ¶ms); + iavf_client_get_params(vsi, ¶ms); cinst->lan_info.params = params; cinst->client->ops->l2_param_change(&cinst->lan_info, cinst->client, ¶ms); } /** - * i40evf_notify_client_open - call the client open callback + * iavf_notify_client_open - call the client open callback * @vsi: the VSI with netdev opened * * If there is a client to this netdev, call the client with open **/ -void i40evf_notify_client_open(struct i40e_vsi *vsi) +void iavf_notify_client_open(struct iavf_vsi *vsi) { - struct i40evf_adapter *adapter = vsi->back; + struct iavf_adapter *adapter = vsi->back; struct i40e_client_instance *cinst = adapter->cinst; int ret; @@ -127,22 +127,22 @@ void i40evf_notify_client_open(struct i40e_vsi *vsi) } /** - * i40evf_client_release_qvlist - send a message to the PF to release iwarp qv map + * iavf_client_release_qvlist - send a message to the PF to release iwarp qv map * @ldev: pointer to L2 context. * * Return 0 on success or < 0 on error **/ -static int i40evf_client_release_qvlist(struct i40e_info *ldev) +static int iavf_client_release_qvlist(struct i40e_info *ldev) { - struct i40evf_adapter *adapter = ldev->vf; - i40e_status err; + struct iavf_adapter *adapter = ldev->vf; + iavf_status err; if (adapter->aq_required) return -EAGAIN; - err = i40e_aq_send_msg_to_pf(&adapter->hw, - VIRTCHNL_OP_RELEASE_IWARP_IRQ_MAP, - I40E_SUCCESS, NULL, 0, NULL); + err = iavf_aq_send_msg_to_pf(&adapter->hw, + VIRTCHNL_OP_RELEASE_IWARP_IRQ_MAP, + I40E_SUCCESS, NULL, 0, NULL); if (err) dev_err(&adapter->pdev->dev, @@ -153,15 +153,15 @@ static int i40evf_client_release_qvlist(struct i40e_info *ldev) } /** - * i40evf_notify_client_close - call the client close callback + * iavf_notify_client_close - call the client close callback * @vsi: the VSI with netdev closed * @reset: true when close called due to reset pending * * If there is a client to this netdev, call the client with close **/ -void i40evf_notify_client_close(struct i40e_vsi *vsi, bool reset) +void iavf_notify_client_close(struct iavf_vsi *vsi, bool reset) { - struct i40evf_adapter *adapter = vsi->back; + struct iavf_adapter *adapter = vsi->back; struct i40e_client_instance *cinst = adapter->cinst; if (!cinst || !cinst->client || !cinst->client->ops || @@ -171,21 +171,21 @@ void i40evf_notify_client_close(struct i40e_vsi *vsi, bool reset) return; } cinst->client->ops->close(&cinst->lan_info, cinst->client, reset); - i40evf_client_release_qvlist(&cinst->lan_info); + iavf_client_release_qvlist(&cinst->lan_info); clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state); } /** - * i40evf_client_add_instance - add a client instance to the instance list + * iavf_client_add_instance - add a client instance to the instance list * @adapter: pointer to the board struct * * Returns cinst ptr on success, NULL on failure **/ static struct i40e_client_instance * -i40evf_client_add_instance(struct i40evf_adapter *adapter) +iavf_client_add_instance(struct iavf_adapter *adapter) { struct i40e_client_instance *cinst = NULL; - struct i40e_vsi *vsi = &adapter->vsi; + struct iavf_vsi *vsi = &adapter->vsi; struct netdev_hw_addr *mac = NULL; struct i40e_params params; @@ -207,11 +207,11 @@ i40evf_client_add_instance(struct i40evf_adapter *adapter) cinst->lan_info.fid = 0; cinst->lan_info.ftype = I40E_CLIENT_FTYPE_VF; cinst->lan_info.hw_addr = adapter->hw.hw_addr; - cinst->lan_info.ops = &i40evf_lan_ops; - cinst->lan_info.version.major = I40EVF_CLIENT_VERSION_MAJOR; - cinst->lan_info.version.minor = I40EVF_CLIENT_VERSION_MINOR; - cinst->lan_info.version.build = I40EVF_CLIENT_VERSION_BUILD; - i40evf_client_get_params(vsi, ¶ms); + cinst->lan_info.ops = &iavf_lan_ops; + cinst->lan_info.version.major = IAVF_CLIENT_VERSION_MAJOR; + cinst->lan_info.version.minor = IAVF_CLIENT_VERSION_MINOR; + cinst->lan_info.version.build = IAVF_CLIENT_VERSION_BUILD; + iavf_client_get_params(vsi, ¶ms); cinst->lan_info.params = params; set_bit(__I40E_CLIENT_INSTANCE_NONE, &cinst->state); @@ -233,28 +233,28 @@ out: } /** - * i40evf_client_del_instance - removes a client instance from the list + * iavf_client_del_instance - removes a client instance from the list * @adapter: pointer to the board struct * **/ static -void i40evf_client_del_instance(struct i40evf_adapter *adapter) +void iavf_client_del_instance(struct iavf_adapter *adapter) { kfree(adapter->cinst); adapter->cinst = NULL; } /** - * i40evf_client_subtask - client maintenance work + * iavf_client_subtask - client maintenance work * @adapter: board private structure **/ -void i40evf_client_subtask(struct i40evf_adapter *adapter) +void iavf_client_subtask(struct iavf_adapter *adapter) { struct i40e_client *client = vf_registered_client; struct i40e_client_instance *cinst; int ret = 0; - if (adapter->state < __I40EVF_DOWN) + if (adapter->state < __IAVF_DOWN) return; /* first check client is registered */ @@ -262,7 +262,7 @@ void i40evf_client_subtask(struct i40evf_adapter *adapter) return; /* Add the client instance to the instance list */ - cinst = i40evf_client_add_instance(adapter); + cinst = iavf_client_add_instance(adapter); if (!cinst) return; @@ -279,23 +279,23 @@ void i40evf_client_subtask(struct i40evf_adapter *adapter) &cinst->state); else /* remove client instance */ - i40evf_client_del_instance(adapter); + iavf_client_del_instance(adapter); } } /** - * i40evf_lan_add_device - add a lan device struct to the list of lan devices + * iavf_lan_add_device - add a lan device struct to the list of lan devices * @adapter: pointer to the board struct * * Returns 0 on success or none 0 on error **/ -int i40evf_lan_add_device(struct i40evf_adapter *adapter) +int iavf_lan_add_device(struct iavf_adapter *adapter) { struct i40e_device *ldev; int ret = 0; - mutex_lock(&i40evf_device_mutex); - list_for_each_entry(ldev, &i40evf_devices, list) { + mutex_lock(&iavf_device_mutex); + list_for_each_entry(ldev, &i40e_devices, list) { if (ldev->vf == adapter) { ret = -EEXIST; goto out; @@ -308,7 +308,7 @@ int i40evf_lan_add_device(struct i40evf_adapter *adapter) } ldev->vf = adapter; INIT_LIST_HEAD(&ldev->list); - list_add(&ldev->list, &i40evf_devices); + list_add(&ldev->list, &i40e_devices); dev_info(&adapter->pdev->dev, "Added LAN device bus=0x%02x dev=0x%02x func=0x%02x\n", adapter->hw.bus.bus_id, adapter->hw.bus.device, adapter->hw.bus.func); @@ -316,26 +316,26 @@ int i40evf_lan_add_device(struct i40evf_adapter *adapter) /* Since in some cases register may have happened before a device gets * added, we can schedule a subtask to go initiate the clients. */ - adapter->flags |= I40EVF_FLAG_SERVICE_CLIENT_REQUESTED; + adapter->flags |= IAVF_FLAG_SERVICE_CLIENT_REQUESTED; out: - mutex_unlock(&i40evf_device_mutex); + mutex_unlock(&iavf_device_mutex); return ret; } /** - * i40evf_lan_del_device - removes a lan device from the device list + * iavf_lan_del_device - removes a lan device from the device list * @adapter: pointer to the board struct * * Returns 0 on success or non-0 on error **/ -int i40evf_lan_del_device(struct i40evf_adapter *adapter) +int iavf_lan_del_device(struct iavf_adapter *adapter) { struct i40e_device *ldev, *tmp; int ret = -ENODEV; - mutex_lock(&i40evf_device_mutex); - list_for_each_entry_safe(ldev, tmp, &i40evf_devices, list) { + mutex_lock(&iavf_device_mutex); + list_for_each_entry_safe(ldev, tmp, &i40e_devices, list) { if (ldev->vf == adapter) { dev_info(&adapter->pdev->dev, "Deleted LAN device bus=0x%02x dev=0x%02x func=0x%02x\n", @@ -348,23 +348,23 @@ int i40evf_lan_del_device(struct i40evf_adapter *adapter) } } - mutex_unlock(&i40evf_device_mutex); + mutex_unlock(&iavf_device_mutex); return ret; } /** - * i40evf_client_release - release client specific resources + * iavf_client_release - release client specific resources * @client: pointer to the registered client * **/ -static void i40evf_client_release(struct i40e_client *client) +static void iavf_client_release(struct i40e_client *client) { struct i40e_client_instance *cinst; struct i40e_device *ldev; - struct i40evf_adapter *adapter; + struct iavf_adapter *adapter; - mutex_lock(&i40evf_device_mutex); - list_for_each_entry(ldev, &i40evf_devices, list) { + mutex_lock(&iavf_device_mutex); + list_for_each_entry(ldev, &i40e_devices, list) { adapter = ldev->vf; cinst = adapter->cinst; if (!cinst) @@ -373,41 +373,41 @@ static void i40evf_client_release(struct i40e_client *client) if (client->ops && client->ops->close) client->ops->close(&cinst->lan_info, client, false); - i40evf_client_release_qvlist(&cinst->lan_info); + iavf_client_release_qvlist(&cinst->lan_info); clear_bit(__I40E_CLIENT_INSTANCE_OPENED, &cinst->state); dev_warn(&adapter->pdev->dev, "Client %s instance closed\n", client->name); } /* delete the client instance */ - i40evf_client_del_instance(adapter); + iavf_client_del_instance(adapter); dev_info(&adapter->pdev->dev, "Deleted client instance of Client %s\n", client->name); } - mutex_unlock(&i40evf_device_mutex); + mutex_unlock(&iavf_device_mutex); } /** - * i40evf_client_prepare - prepare client specific resources + * iavf_client_prepare - prepare client specific resources * @client: pointer to the registered client * **/ -static void i40evf_client_prepare(struct i40e_client *client) +static void iavf_client_prepare(struct i40e_client *client) { struct i40e_device *ldev; - struct i40evf_adapter *adapter; + struct iavf_adapter *adapter; - mutex_lock(&i40evf_device_mutex); - list_for_each_entry(ldev, &i40evf_devices, list) { + mutex_lock(&iavf_device_mutex); + list_for_each_entry(ldev, &i40e_devices, list) { adapter = ldev->vf; /* Signal the watchdog to service the client */ - adapter->flags |= I40EVF_FLAG_SERVICE_CLIENT_REQUESTED; + adapter->flags |= IAVF_FLAG_SERVICE_CLIENT_REQUESTED; } - mutex_unlock(&i40evf_device_mutex); + mutex_unlock(&iavf_device_mutex); } /** - * i40evf_client_virtchnl_send - send a message to the PF instance + * iavf_client_virtchnl_send - send a message to the PF instance * @ldev: pointer to L2 context. * @client: Client pointer. * @msg: pointer to message buffer @@ -415,17 +415,17 @@ static void i40evf_client_prepare(struct i40e_client *client) * * Return 0 on success or < 0 on error **/ -static u32 i40evf_client_virtchnl_send(struct i40e_info *ldev, - struct i40e_client *client, - u8 *msg, u16 len) +static u32 iavf_client_virtchnl_send(struct i40e_info *ldev, + struct i40e_client *client, + u8 *msg, u16 len) { - struct i40evf_adapter *adapter = ldev->vf; - i40e_status err; + struct iavf_adapter *adapter = ldev->vf; + iavf_status err; if (adapter->aq_required) return -EAGAIN; - err = i40e_aq_send_msg_to_pf(&adapter->hw, VIRTCHNL_OP_IWARP, + err = iavf_aq_send_msg_to_pf(&adapter->hw, VIRTCHNL_OP_IWARP, I40E_SUCCESS, msg, len, NULL); if (err) dev_err(&adapter->pdev->dev, "Unable to send iWarp message to PF, error %d, aq status %d\n", @@ -435,21 +435,21 @@ static u32 i40evf_client_virtchnl_send(struct i40e_info *ldev, } /** - * i40evf_client_setup_qvlist - send a message to the PF to setup iwarp qv map + * iavf_client_setup_qvlist - send a message to the PF to setup iwarp qv map * @ldev: pointer to L2 context. * @client: Client pointer. * @qvlist_info: queue and vector list * * Return 0 on success or < 0 on error **/ -static int i40evf_client_setup_qvlist(struct i40e_info *ldev, - struct i40e_client *client, - struct i40e_qvlist_info *qvlist_info) +static int iavf_client_setup_qvlist(struct i40e_info *ldev, + struct i40e_client *client, + struct i40e_qvlist_info *qvlist_info) { struct virtchnl_iwarp_qvlist_info *v_qvlist_info; - struct i40evf_adapter *adapter = ldev->vf; + struct iavf_adapter *adapter = ldev->vf; struct i40e_qv_info *qv_info; - i40e_status err; + iavf_status err; u32 v_idx, i; u32 msg_size; @@ -474,9 +474,9 @@ static int i40evf_client_setup_qvlist(struct i40e_info *ldev, (v_qvlist_info->num_vectors - 1)); adapter->client_pending |= BIT(VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP); - err = i40e_aq_send_msg_to_pf(&adapter->hw, - VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP, - I40E_SUCCESS, (u8 *)v_qvlist_info, msg_size, NULL); + err = iavf_aq_send_msg_to_pf(&adapter->hw, + VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP, I40E_SUCCESS, + (u8 *)v_qvlist_info, msg_size, NULL); if (err) { dev_err(&adapter->pdev->dev, @@ -499,12 +499,12 @@ out: } /** - * i40evf_register_client - Register a i40e client driver with the L2 driver + * iavf_register_client - Register a i40e client driver with the L2 driver * @client: pointer to the i40e_client struct * * Returns 0 on success or non-0 on error **/ -int i40evf_register_client(struct i40e_client *client) +int iavf_register_client(struct i40e_client *client) { int ret = 0; @@ -514,48 +514,48 @@ int i40evf_register_client(struct i40e_client *client) } if (strlen(client->name) == 0) { - pr_info("i40evf: Failed to register client with no name\n"); + pr_info("iavf: Failed to register client with no name\n"); ret = -EIO; goto out; } if (vf_registered_client) { - pr_info("i40evf: Client %s has already been registered!\n", + pr_info("iavf: Client %s has already been registered!\n", client->name); ret = -EEXIST; goto out; } - if ((client->version.major != I40EVF_CLIENT_VERSION_MAJOR) || - (client->version.minor != I40EVF_CLIENT_VERSION_MINOR)) { - pr_info("i40evf: Failed to register client %s due to mismatched client interface version\n", + if ((client->version.major != IAVF_CLIENT_VERSION_MAJOR) || + (client->version.minor != IAVF_CLIENT_VERSION_MINOR)) { + pr_info("iavf: Failed to register client %s due to mismatched client interface version\n", client->name); pr_info("Client is using version: %02d.%02d.%02d while LAN driver supports %s\n", client->version.major, client->version.minor, client->version.build, - i40evf_client_interface_version_str); + iavf_client_interface_version_str); ret = -EIO; goto out; } vf_registered_client = client; - i40evf_client_prepare(client); + iavf_client_prepare(client); - pr_info("i40evf: Registered client %s with return code %d\n", + pr_info("iavf: Registered client %s with return code %d\n", client->name, ret); out: return ret; } -EXPORT_SYMBOL(i40evf_register_client); +EXPORT_SYMBOL(iavf_register_client); /** - * i40evf_unregister_client - Unregister a i40e client driver with the L2 driver + * iavf_unregister_client - Unregister a i40e client driver with the L2 driver * @client: pointer to the i40e_client struct * * Returns 0 on success or non-0 on error **/ -int i40evf_unregister_client(struct i40e_client *client) +int iavf_unregister_client(struct i40e_client *client) { int ret = 0; @@ -563,17 +563,17 @@ int i40evf_unregister_client(struct i40e_client *client) * a close for each of the client instances that were opened. * client_release function is called to handle this. */ - i40evf_client_release(client); + iavf_client_release(client); if (vf_registered_client != client) { - pr_info("i40evf: Client %s has not been registered\n", + pr_info("iavf: Client %s has not been registered\n", client->name); ret = -ENODEV; goto out; } vf_registered_client = NULL; - pr_info("i40evf: Unregistered client %s\n", client->name); + pr_info("iavf: Unregistered client %s\n", client->name); out: return ret; } -EXPORT_SYMBOL(i40evf_unregister_client); +EXPORT_SYMBOL(iavf_unregister_client); diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_client.h b/drivers/net/ethernet/intel/iavf/iavf_client.h index 5585f362048a..e216fc9dfd81 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_client.h +++ b/drivers/net/ethernet/intel/iavf/iavf_client.h @@ -1,21 +1,21 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright(c) 2013 - 2018 Intel Corporation. */ -#ifndef _I40EVF_CLIENT_H_ -#define _I40EVF_CLIENT_H_ +#ifndef _IAVF_CLIENT_H_ +#define _IAVF_CLIENT_H_ -#define I40EVF_CLIENT_STR_LENGTH 10 +#define IAVF_CLIENT_STR_LENGTH 10 /* Client interface version should be updated anytime there is a change in the * existing APIs or data structures. */ -#define I40EVF_CLIENT_VERSION_MAJOR 0 -#define I40EVF_CLIENT_VERSION_MINOR 01 -#define I40EVF_CLIENT_VERSION_BUILD 00 -#define I40EVF_CLIENT_VERSION_STR \ - __stringify(I40EVF_CLIENT_VERSION_MAJOR) "." \ - __stringify(I40EVF_CLIENT_VERSION_MINOR) "." \ - __stringify(I40EVF_CLIENT_VERSION_BUILD) +#define IAVF_CLIENT_VERSION_MAJOR 0 +#define IAVF_CLIENT_VERSION_MINOR 01 +#define IAVF_CLIENT_VERSION_BUILD 00 +#define IAVF_CLIENT_VERSION_STR \ + __stringify(IAVF_CLIENT_VERSION_MAJOR) "." \ + __stringify(IAVF_CLIENT_VERSION_MINOR) "." \ + __stringify(IAVF_CLIENT_VERSION_BUILD) struct i40e_client_version { u8 major; @@ -90,7 +90,7 @@ struct i40e_info { #define I40E_CLIENT_FTYPE_PF 0 #define I40E_CLIENT_FTYPE_VF 1 u8 ftype; /* function type, PF or VF */ - void *vf; /* cast to i40evf_adapter */ + void *vf; /* cast to iavf_adapter */ /* All L2 params that could change during the life span of the device * and needs to be communicated to the client when they change @@ -151,7 +151,7 @@ struct i40e_client_instance { struct i40e_client { struct list_head list; /* list of registered clients */ - char name[I40EVF_CLIENT_STR_LENGTH]; + char name[IAVF_CLIENT_STR_LENGTH]; struct i40e_client_version version; unsigned long state; /* client state */ atomic_t ref_cnt; /* Count of all the client devices of this kind */ @@ -164,6 +164,6 @@ struct i40e_client { }; /* used by clients */ -int i40evf_register_client(struct i40e_client *client); -int i40evf_unregister_client(struct i40e_client *client); -#endif /* _I40EVF_CLIENT_H_ */ +int iavf_register_client(struct i40e_client *client); +int iavf_unregister_client(struct i40e_client *client); +#endif /* _IAVF_CLIENT_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_common.c b/drivers/net/ethernet/intel/iavf/iavf_common.c new file mode 100644 index 000000000000..768369c89e77 --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_common.c @@ -0,0 +1,955 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#include "iavf_type.h" +#include "i40e_adminq.h" +#include "iavf_prototype.h" +#include <linux/avf/virtchnl.h> + +/** + * iavf_set_mac_type - Sets MAC type + * @hw: pointer to the HW structure + * + * This function sets the mac type of the adapter based on the + * vendor ID and device ID stored in the hw structure. + **/ +iavf_status iavf_set_mac_type(struct iavf_hw *hw) +{ + iavf_status status = 0; + + if (hw->vendor_id == PCI_VENDOR_ID_INTEL) { + switch (hw->device_id) { + case IAVF_DEV_ID_X722_VF: + hw->mac.type = IAVF_MAC_X722_VF; + break; + case IAVF_DEV_ID_VF: + case IAVF_DEV_ID_VF_HV: + case IAVF_DEV_ID_ADAPTIVE_VF: + hw->mac.type = IAVF_MAC_VF; + break; + default: + hw->mac.type = IAVF_MAC_GENERIC; + break; + } + } else { + status = I40E_ERR_DEVICE_NOT_SUPPORTED; + } + + hw_dbg(hw, "found mac: %d, returns: %d\n", hw->mac.type, status); + return status; +} + +/** + * iavf_aq_str - convert AQ err code to a string + * @hw: pointer to the HW structure + * @aq_err: the AQ error code to convert + **/ +const char *iavf_aq_str(struct iavf_hw *hw, enum i40e_admin_queue_err aq_err) +{ + switch (aq_err) { + case I40E_AQ_RC_OK: + return "OK"; + case I40E_AQ_RC_EPERM: + return "I40E_AQ_RC_EPERM"; + case I40E_AQ_RC_ENOENT: + return "I40E_AQ_RC_ENOENT"; + case I40E_AQ_RC_ESRCH: + return "I40E_AQ_RC_ESRCH"; + case I40E_AQ_RC_EINTR: + return "I40E_AQ_RC_EINTR"; + case I40E_AQ_RC_EIO: + return "I40E_AQ_RC_EIO"; + case I40E_AQ_RC_ENXIO: + return "I40E_AQ_RC_ENXIO"; + case I40E_AQ_RC_E2BIG: + return "I40E_AQ_RC_E2BIG"; + case I40E_AQ_RC_EAGAIN: + return "I40E_AQ_RC_EAGAIN"; + case I40E_AQ_RC_ENOMEM: + return "I40E_AQ_RC_ENOMEM"; + case I40E_AQ_RC_EACCES: + return "I40E_AQ_RC_EACCES"; + case I40E_AQ_RC_EFAULT: + return "I40E_AQ_RC_EFAULT"; + case I40E_AQ_RC_EBUSY: + return "I40E_AQ_RC_EBUSY"; + case I40E_AQ_RC_EEXIST: + return "I40E_AQ_RC_EEXIST"; + case I40E_AQ_RC_EINVAL: + return "I40E_AQ_RC_EINVAL"; + case I40E_AQ_RC_ENOTTY: + return "I40E_AQ_RC_ENOTTY"; + case I40E_AQ_RC_ENOSPC: + return "I40E_AQ_RC_ENOSPC"; + case I40E_AQ_RC_ENOSYS: + return "I40E_AQ_RC_ENOSYS"; + case I40E_AQ_RC_ERANGE: + return "I40E_AQ_RC_ERANGE"; + case I40E_AQ_RC_EFLUSHED: + return "I40E_AQ_RC_EFLUSHED"; + case I40E_AQ_RC_BAD_ADDR: + return "I40E_AQ_RC_BAD_ADDR"; + case I40E_AQ_RC_EMODE: + return "I40E_AQ_RC_EMODE"; + case I40E_AQ_RC_EFBIG: + return "I40E_AQ_RC_EFBIG"; + } + + snprintf(hw->err_str, sizeof(hw->err_str), "%d", aq_err); + return hw->err_str; +} + +/** + * iavf_stat_str - convert status err code to a string + * @hw: pointer to the HW structure + * @stat_err: the status error code to convert + **/ +const char *iavf_stat_str(struct iavf_hw *hw, iavf_status stat_err) +{ + switch (stat_err) { + case 0: + return "OK"; + case I40E_ERR_NVM: + return "I40E_ERR_NVM"; + case I40E_ERR_NVM_CHECKSUM: + return "I40E_ERR_NVM_CHECKSUM"; + case I40E_ERR_PHY: + return "I40E_ERR_PHY"; + case I40E_ERR_CONFIG: + return "I40E_ERR_CONFIG"; + case I40E_ERR_PARAM: + return "I40E_ERR_PARAM"; + case I40E_ERR_MAC_TYPE: + return "I40E_ERR_MAC_TYPE"; + case I40E_ERR_UNKNOWN_PHY: + return "I40E_ERR_UNKNOWN_PHY"; + case I40E_ERR_LINK_SETUP: + return "I40E_ERR_LINK_SETUP"; + case I40E_ERR_ADAPTER_STOPPED: + return "I40E_ERR_ADAPTER_STOPPED"; + case I40E_ERR_INVALID_MAC_ADDR: + return "I40E_ERR_INVALID_MAC_ADDR"; + case I40E_ERR_DEVICE_NOT_SUPPORTED: + return "I40E_ERR_DEVICE_NOT_SUPPORTED"; + case I40E_ERR_MASTER_REQUESTS_PENDING: + return "I40E_ERR_MASTER_REQUESTS_PENDING"; + case I40E_ERR_INVALID_LINK_SETTINGS: + return "I40E_ERR_INVALID_LINK_SETTINGS"; + case I40E_ERR_AUTONEG_NOT_COMPLETE: + return "I40E_ERR_AUTONEG_NOT_COMPLETE"; + case I40E_ERR_RESET_FAILED: + return "I40E_ERR_RESET_FAILED"; + case I40E_ERR_SWFW_SYNC: + return "I40E_ERR_SWFW_SYNC"; + case I40E_ERR_NO_AVAILABLE_VSI: + return "I40E_ERR_NO_AVAILABLE_VSI"; + case I40E_ERR_NO_MEMORY: + return "I40E_ERR_NO_MEMORY"; + case I40E_ERR_BAD_PTR: + return "I40E_ERR_BAD_PTR"; + case I40E_ERR_RING_FULL: + return "I40E_ERR_RING_FULL"; + case I40E_ERR_INVALID_PD_ID: + return "I40E_ERR_INVALID_PD_ID"; + case I40E_ERR_INVALID_QP_ID: + return "I40E_ERR_INVALID_QP_ID"; + case I40E_ERR_INVALID_CQ_ID: + return "I40E_ERR_INVALID_CQ_ID"; + case I40E_ERR_INVALID_CEQ_ID: + return "I40E_ERR_INVALID_CEQ_ID"; + case I40E_ERR_INVALID_AEQ_ID: + return "I40E_ERR_INVALID_AEQ_ID"; + case I40E_ERR_INVALID_SIZE: + return "I40E_ERR_INVALID_SIZE"; + case I40E_ERR_INVALID_ARP_INDEX: + return "I40E_ERR_INVALID_ARP_INDEX"; + case I40E_ERR_INVALID_FPM_FUNC_ID: + return "I40E_ERR_INVALID_FPM_FUNC_ID"; + case I40E_ERR_QP_INVALID_MSG_SIZE: + return "I40E_ERR_QP_INVALID_MSG_SIZE"; + case I40E_ERR_QP_TOOMANY_WRS_POSTED: + return "I40E_ERR_QP_TOOMANY_WRS_POSTED"; + case I40E_ERR_INVALID_FRAG_COUNT: + return "I40E_ERR_INVALID_FRAG_COUNT"; + case I40E_ERR_QUEUE_EMPTY: + return "I40E_ERR_QUEUE_EMPTY"; + case I40E_ERR_INVALID_ALIGNMENT: + return "I40E_ERR_INVALID_ALIGNMENT"; + case I40E_ERR_FLUSHED_QUEUE: + return "I40E_ERR_FLUSHED_QUEUE"; + case I40E_ERR_INVALID_PUSH_PAGE_INDEX: + return "I40E_ERR_INVALID_PUSH_PAGE_INDEX"; + case I40E_ERR_INVALID_IMM_DATA_SIZE: + return "I40E_ERR_INVALID_IMM_DATA_SIZE"; + case I40E_ERR_TIMEOUT: + return "I40E_ERR_TIMEOUT"; + case I40E_ERR_OPCODE_MISMATCH: + return "I40E_ERR_OPCODE_MISMATCH"; + case I40E_ERR_CQP_COMPL_ERROR: + return "I40E_ERR_CQP_COMPL_ERROR"; + case I40E_ERR_INVALID_VF_ID: + return "I40E_ERR_INVALID_VF_ID"; + case I40E_ERR_INVALID_HMCFN_ID: + return "I40E_ERR_INVALID_HMCFN_ID"; + case I40E_ERR_BACKING_PAGE_ERROR: + return "I40E_ERR_BACKING_PAGE_ERROR"; + case I40E_ERR_NO_PBLCHUNKS_AVAILABLE: + return "I40E_ERR_NO_PBLCHUNKS_AVAILABLE"; + case I40E_ERR_INVALID_PBLE_INDEX: + return "I40E_ERR_INVALID_PBLE_INDEX"; + case I40E_ERR_INVALID_SD_INDEX: + return "I40E_ERR_INVALID_SD_INDEX"; + case I40E_ERR_INVALID_PAGE_DESC_INDEX: + return "I40E_ERR_INVALID_PAGE_DESC_INDEX"; + case I40E_ERR_INVALID_SD_TYPE: + return "I40E_ERR_INVALID_SD_TYPE"; + case I40E_ERR_MEMCPY_FAILED: + return "I40E_ERR_MEMCPY_FAILED"; + case I40E_ERR_INVALID_HMC_OBJ_INDEX: + return "I40E_ERR_INVALID_HMC_OBJ_INDEX"; + case I40E_ERR_INVALID_HMC_OBJ_COUNT: + return "I40E_ERR_INVALID_HMC_OBJ_COUNT"; + case I40E_ERR_INVALID_SRQ_ARM_LIMIT: + return "I40E_ERR_INVALID_SRQ_ARM_LIMIT"; + case I40E_ERR_SRQ_ENABLED: + return "I40E_ERR_SRQ_ENABLED"; + case I40E_ERR_ADMIN_QUEUE_ERROR: + return "I40E_ERR_ADMIN_QUEUE_ERROR"; + case I40E_ERR_ADMIN_QUEUE_TIMEOUT: + return "I40E_ERR_ADMIN_QUEUE_TIMEOUT"; + case I40E_ERR_BUF_TOO_SHORT: + return "I40E_ERR_BUF_TOO_SHORT"; + case I40E_ERR_ADMIN_QUEUE_FULL: + return "I40E_ERR_ADMIN_QUEUE_FULL"; + case I40E_ERR_ADMIN_QUEUE_NO_WORK: + return "I40E_ERR_ADMIN_QUEUE_NO_WORK"; + case I40E_ERR_BAD_IWARP_CQE: + return "I40E_ERR_BAD_IWARP_CQE"; + case I40E_ERR_NVM_BLANK_MODE: + return "I40E_ERR_NVM_BLANK_MODE"; + case I40E_ERR_NOT_IMPLEMENTED: + return "I40E_ERR_NOT_IMPLEMENTED"; + case I40E_ERR_PE_DOORBELL_NOT_ENABLED: + return "I40E_ERR_PE_DOORBELL_NOT_ENABLED"; + case I40E_ERR_DIAG_TEST_FAILED: + return "I40E_ERR_DIAG_TEST_FAILED"; + case I40E_ERR_NOT_READY: + return "I40E_ERR_NOT_READY"; + case I40E_NOT_SUPPORTED: + return "I40E_NOT_SUPPORTED"; + case I40E_ERR_FIRMWARE_API_VERSION: + return "I40E_ERR_FIRMWARE_API_VERSION"; + case I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR: + return "I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR"; + } + + snprintf(hw->err_str, sizeof(hw->err_str), "%d", stat_err); + return hw->err_str; +} + +/** + * iavf_debug_aq + * @hw: debug mask related to admin queue + * @mask: debug mask + * @desc: pointer to admin queue descriptor + * @buffer: pointer to command buffer + * @buf_len: max length of buffer + * + * Dumps debug log about adminq command with descriptor contents. + **/ +void iavf_debug_aq(struct iavf_hw *hw, enum iavf_debug_mask mask, void *desc, + void *buffer, u16 buf_len) +{ + struct i40e_aq_desc *aq_desc = (struct i40e_aq_desc *)desc; + u8 *buf = (u8 *)buffer; + + if ((!(mask & hw->debug_mask)) || !desc) + return; + + iavf_debug(hw, mask, + "AQ CMD: opcode 0x%04X, flags 0x%04X, datalen 0x%04X, retval 0x%04X\n", + le16_to_cpu(aq_desc->opcode), + le16_to_cpu(aq_desc->flags), + le16_to_cpu(aq_desc->datalen), + le16_to_cpu(aq_desc->retval)); + iavf_debug(hw, mask, "\tcookie (h,l) 0x%08X 0x%08X\n", + le32_to_cpu(aq_desc->cookie_high), + le32_to_cpu(aq_desc->cookie_low)); + iavf_debug(hw, mask, "\tparam (0,1) 0x%08X 0x%08X\n", + le32_to_cpu(aq_desc->params.internal.param0), + le32_to_cpu(aq_desc->params.internal.param1)); + iavf_debug(hw, mask, "\taddr (h,l) 0x%08X 0x%08X\n", + le32_to_cpu(aq_desc->params.external.addr_high), + le32_to_cpu(aq_desc->params.external.addr_low)); + + if (buffer && aq_desc->datalen) { + u16 len = le16_to_cpu(aq_desc->datalen); + + iavf_debug(hw, mask, "AQ CMD Buffer:\n"); + if (buf_len < len) + len = buf_len; + /* write the full 16-byte chunks */ + if (hw->debug_mask & mask) { + char prefix[27]; + + snprintf(prefix, sizeof(prefix), + "iavf %02x:%02x.%x: \t0x", + hw->bus.bus_id, + hw->bus.device, + hw->bus.func); + + print_hex_dump(KERN_INFO, prefix, DUMP_PREFIX_OFFSET, + 16, 1, buf, len, false); + } + } +} + +/** + * iavf_check_asq_alive + * @hw: pointer to the hw struct + * + * Returns true if Queue is enabled else false. + **/ +bool iavf_check_asq_alive(struct iavf_hw *hw) +{ + if (hw->aq.asq.len) + return !!(rd32(hw, hw->aq.asq.len) & + IAVF_VF_ATQLEN1_ATQENABLE_MASK); + else + return false; +} + +/** + * iavf_aq_queue_shutdown + * @hw: pointer to the hw struct + * @unloading: is the driver unloading itself + * + * Tell the Firmware that we're shutting down the AdminQ and whether + * or not the driver is unloading as well. + **/ +iavf_status iavf_aq_queue_shutdown(struct iavf_hw *hw, bool unloading) +{ + struct i40e_aq_desc desc; + struct i40e_aqc_queue_shutdown *cmd = + (struct i40e_aqc_queue_shutdown *)&desc.params.raw; + iavf_status status; + + iavf_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_queue_shutdown); + + if (unloading) + cmd->driver_unloading = cpu_to_le32(I40E_AQ_DRIVER_UNLOADING); + status = iavf_asq_send_command(hw, &desc, NULL, 0, NULL); + + return status; +} + +/** + * iavf_aq_get_set_rss_lut + * @hw: pointer to the hardware structure + * @vsi_id: vsi fw index + * @pf_lut: for PF table set true, for VSI table set false + * @lut: pointer to the lut buffer provided by the caller + * @lut_size: size of the lut buffer + * @set: set true to set the table, false to get the table + * + * Internal function to get or set RSS look up table + **/ +static iavf_status iavf_aq_get_set_rss_lut(struct iavf_hw *hw, + u16 vsi_id, bool pf_lut, + u8 *lut, u16 lut_size, + bool set) +{ + iavf_status status; + struct i40e_aq_desc desc; + struct i40e_aqc_get_set_rss_lut *cmd_resp = + (struct i40e_aqc_get_set_rss_lut *)&desc.params.raw; + + if (set) + iavf_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_set_rss_lut); + else + iavf_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_get_rss_lut); + + /* Indirect command */ + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF); + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_RD); + + cmd_resp->vsi_id = + cpu_to_le16((u16)((vsi_id << + I40E_AQC_SET_RSS_LUT_VSI_ID_SHIFT) & + I40E_AQC_SET_RSS_LUT_VSI_ID_MASK)); + cmd_resp->vsi_id |= cpu_to_le16((u16)I40E_AQC_SET_RSS_LUT_VSI_VALID); + + if (pf_lut) + cmd_resp->flags |= cpu_to_le16((u16) + ((I40E_AQC_SET_RSS_LUT_TABLE_TYPE_PF << + I40E_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT) & + I40E_AQC_SET_RSS_LUT_TABLE_TYPE_MASK)); + else + cmd_resp->flags |= cpu_to_le16((u16) + ((I40E_AQC_SET_RSS_LUT_TABLE_TYPE_VSI << + I40E_AQC_SET_RSS_LUT_TABLE_TYPE_SHIFT) & + I40E_AQC_SET_RSS_LUT_TABLE_TYPE_MASK)); + + status = iavf_asq_send_command(hw, &desc, lut, lut_size, NULL); + + return status; +} + +/** + * iavf_aq_get_rss_lut + * @hw: pointer to the hardware structure + * @vsi_id: vsi fw index + * @pf_lut: for PF table set true, for VSI table set false + * @lut: pointer to the lut buffer provided by the caller + * @lut_size: size of the lut buffer + * + * get the RSS lookup table, PF or VSI type + **/ +iavf_status iavf_aq_get_rss_lut(struct iavf_hw *hw, u16 vsi_id, + bool pf_lut, u8 *lut, u16 lut_size) +{ + return iavf_aq_get_set_rss_lut(hw, vsi_id, pf_lut, lut, lut_size, + false); +} + +/** + * iavf_aq_set_rss_lut + * @hw: pointer to the hardware structure + * @vsi_id: vsi fw index + * @pf_lut: for PF table set true, for VSI table set false + * @lut: pointer to the lut buffer provided by the caller + * @lut_size: size of the lut buffer + * + * set the RSS lookup table, PF or VSI type + **/ +iavf_status iavf_aq_set_rss_lut(struct iavf_hw *hw, u16 vsi_id, + bool pf_lut, u8 *lut, u16 lut_size) +{ + return iavf_aq_get_set_rss_lut(hw, vsi_id, pf_lut, lut, lut_size, true); +} + +/** + * iavf_aq_get_set_rss_key + * @hw: pointer to the hw struct + * @vsi_id: vsi fw index + * @key: pointer to key info struct + * @set: set true to set the key, false to get the key + * + * get the RSS key per VSI + **/ +static +iavf_status iavf_aq_get_set_rss_key(struct iavf_hw *hw, u16 vsi_id, + struct i40e_aqc_get_set_rss_key_data *key, + bool set) +{ + iavf_status status; + struct i40e_aq_desc desc; + struct i40e_aqc_get_set_rss_key *cmd_resp = + (struct i40e_aqc_get_set_rss_key *)&desc.params.raw; + u16 key_size = sizeof(struct i40e_aqc_get_set_rss_key_data); + + if (set) + iavf_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_set_rss_key); + else + iavf_fill_default_direct_cmd_desc(&desc, + i40e_aqc_opc_get_rss_key); + + /* Indirect command */ + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF); + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_RD); + + cmd_resp->vsi_id = + cpu_to_le16((u16)((vsi_id << + I40E_AQC_SET_RSS_KEY_VSI_ID_SHIFT) & + I40E_AQC_SET_RSS_KEY_VSI_ID_MASK)); + cmd_resp->vsi_id |= cpu_to_le16((u16)I40E_AQC_SET_RSS_KEY_VSI_VALID); + + status = iavf_asq_send_command(hw, &desc, key, key_size, NULL); + + return status; +} + +/** + * iavf_aq_get_rss_key + * @hw: pointer to the hw struct + * @vsi_id: vsi fw index + * @key: pointer to key info struct + * + **/ +iavf_status iavf_aq_get_rss_key(struct iavf_hw *hw, u16 vsi_id, + struct i40e_aqc_get_set_rss_key_data *key) +{ + return iavf_aq_get_set_rss_key(hw, vsi_id, key, false); +} + +/** + * iavf_aq_set_rss_key + * @hw: pointer to the hw struct + * @vsi_id: vsi fw index + * @key: pointer to key info struct + * + * set the RSS key per VSI + **/ +iavf_status iavf_aq_set_rss_key(struct iavf_hw *hw, u16 vsi_id, + struct i40e_aqc_get_set_rss_key_data *key) +{ + return iavf_aq_get_set_rss_key(hw, vsi_id, key, true); +} + +/* The iavf_ptype_lookup table is used to convert from the 8-bit ptype in the + * hardware to a bit-field that can be used by SW to more easily determine the + * packet type. + * + * Macros are used to shorten the table lines and make this table human + * readable. + * + * We store the PTYPE in the top byte of the bit field - this is just so that + * we can check that the table doesn't have a row missing, as the index into + * the table should be the PTYPE. + * + * Typical work flow: + * + * IF NOT iavf_ptype_lookup[ptype].known + * THEN + * Packet is unknown + * ELSE IF iavf_ptype_lookup[ptype].outer_ip == I40E_RX_PTYPE_OUTER_IP + * Use the rest of the fields to look at the tunnels, inner protocols, etc + * ELSE + * Use the enum iavf_rx_l2_ptype to decode the packet type + * ENDIF + */ + +/* macro to make the table lines short */ +#define IAVF_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\ + { PTYPE, \ + 1, \ + IAVF_RX_PTYPE_OUTER_##OUTER_IP, \ + IAVF_RX_PTYPE_OUTER_##OUTER_IP_VER, \ + IAVF_RX_PTYPE_##OUTER_FRAG, \ + IAVF_RX_PTYPE_TUNNEL_##T, \ + IAVF_RX_PTYPE_TUNNEL_END_##TE, \ + IAVF_RX_PTYPE_##TEF, \ + IAVF_RX_PTYPE_INNER_PROT_##I, \ + IAVF_RX_PTYPE_PAYLOAD_LAYER_##PL } + +#define IAVF_PTT_UNUSED_ENTRY(PTYPE) \ + { PTYPE, 0, 0, 0, 0, 0, 0, 0, 0, 0 } + +/* shorter macros makes the table fit but are terse */ +#define IAVF_RX_PTYPE_NOF IAVF_RX_PTYPE_NOT_FRAG +#define IAVF_RX_PTYPE_FRG IAVF_RX_PTYPE_FRAG +#define IAVF_RX_PTYPE_INNER_PROT_TS IAVF_RX_PTYPE_INNER_PROT_TIMESYNC + +/* Lookup table mapping the HW PTYPE to the bit field for decoding */ +struct iavf_rx_ptype_decoded iavf_ptype_lookup[] = { + /* L2 Packet types */ + IAVF_PTT_UNUSED_ENTRY(0), + IAVF_PTT(1, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), + IAVF_PTT(2, L2, NONE, NOF, NONE, NONE, NOF, TS, PAY2), + IAVF_PTT(3, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), + IAVF_PTT_UNUSED_ENTRY(4), + IAVF_PTT_UNUSED_ENTRY(5), + IAVF_PTT(6, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), + IAVF_PTT(7, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), + IAVF_PTT_UNUSED_ENTRY(8), + IAVF_PTT_UNUSED_ENTRY(9), + IAVF_PTT(10, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), + IAVF_PTT(11, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE), + IAVF_PTT(12, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(13, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(14, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(15, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(16, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(17, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(18, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(19, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(20, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(21, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), + + /* Non Tunneled IPv4 */ + IAVF_PTT(22, IP, IPV4, FRG, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(23, IP, IPV4, NOF, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(24, IP, IPV4, NOF, NONE, NONE, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(25), + IAVF_PTT(26, IP, IPV4, NOF, NONE, NONE, NOF, TCP, PAY4), + IAVF_PTT(27, IP, IPV4, NOF, NONE, NONE, NOF, SCTP, PAY4), + IAVF_PTT(28, IP, IPV4, NOF, NONE, NONE, NOF, ICMP, PAY4), + + /* IPv4 --> IPv4 */ + IAVF_PTT(29, IP, IPV4, NOF, IP_IP, IPV4, FRG, NONE, PAY3), + IAVF_PTT(30, IP, IPV4, NOF, IP_IP, IPV4, NOF, NONE, PAY3), + IAVF_PTT(31, IP, IPV4, NOF, IP_IP, IPV4, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(32), + IAVF_PTT(33, IP, IPV4, NOF, IP_IP, IPV4, NOF, TCP, PAY4), + IAVF_PTT(34, IP, IPV4, NOF, IP_IP, IPV4, NOF, SCTP, PAY4), + IAVF_PTT(35, IP, IPV4, NOF, IP_IP, IPV4, NOF, ICMP, PAY4), + + /* IPv4 --> IPv6 */ + IAVF_PTT(36, IP, IPV4, NOF, IP_IP, IPV6, FRG, NONE, PAY3), + IAVF_PTT(37, IP, IPV4, NOF, IP_IP, IPV6, NOF, NONE, PAY3), + IAVF_PTT(38, IP, IPV4, NOF, IP_IP, IPV6, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(39), + IAVF_PTT(40, IP, IPV4, NOF, IP_IP, IPV6, NOF, TCP, PAY4), + IAVF_PTT(41, IP, IPV4, NOF, IP_IP, IPV6, NOF, SCTP, PAY4), + IAVF_PTT(42, IP, IPV4, NOF, IP_IP, IPV6, NOF, ICMP, PAY4), + + /* IPv4 --> GRE/NAT */ + IAVF_PTT(43, IP, IPV4, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3), + + /* IPv4 --> GRE/NAT --> IPv4 */ + IAVF_PTT(44, IP, IPV4, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3), + IAVF_PTT(45, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3), + IAVF_PTT(46, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(47), + IAVF_PTT(48, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4), + IAVF_PTT(49, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4), + IAVF_PTT(50, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4), + + /* IPv4 --> GRE/NAT --> IPv6 */ + IAVF_PTT(51, IP, IPV4, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3), + IAVF_PTT(52, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3), + IAVF_PTT(53, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(54), + IAVF_PTT(55, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4), + IAVF_PTT(56, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4), + IAVF_PTT(57, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4), + + /* IPv4 --> GRE/NAT --> MAC */ + IAVF_PTT(58, IP, IPV4, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3), + + /* IPv4 --> GRE/NAT --> MAC --> IPv4 */ + IAVF_PTT(59, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3), + IAVF_PTT(60, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3), + IAVF_PTT(61, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(62), + IAVF_PTT(63, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4), + IAVF_PTT(64, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4), + IAVF_PTT(65, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4), + + /* IPv4 --> GRE/NAT -> MAC --> IPv6 */ + IAVF_PTT(66, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3), + IAVF_PTT(67, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3), + IAVF_PTT(68, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(69), + IAVF_PTT(70, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4), + IAVF_PTT(71, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4), + IAVF_PTT(72, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4), + + /* IPv4 --> GRE/NAT --> MAC/VLAN */ + IAVF_PTT(73, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3), + + /* IPv4 ---> GRE/NAT -> MAC/VLAN --> IPv4 */ + IAVF_PTT(74, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3), + IAVF_PTT(75, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3), + IAVF_PTT(76, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(77), + IAVF_PTT(78, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4), + IAVF_PTT(79, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4), + IAVF_PTT(80, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4), + + /* IPv4 -> GRE/NAT -> MAC/VLAN --> IPv6 */ + IAVF_PTT(81, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3), + IAVF_PTT(82, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3), + IAVF_PTT(83, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(84), + IAVF_PTT(85, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4), + IAVF_PTT(86, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4), + IAVF_PTT(87, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4), + + /* Non Tunneled IPv6 */ + IAVF_PTT(88, IP, IPV6, FRG, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(89, IP, IPV6, NOF, NONE, NONE, NOF, NONE, PAY3), + IAVF_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP, PAY3), + IAVF_PTT_UNUSED_ENTRY(91), + IAVF_PTT(92, IP, IPV6, NOF, NONE, NONE, NOF, TCP, PAY4), + IAVF_PTT(93, IP, IPV6, NOF, NONE, NONE, NOF, SCTP, PAY4), + IAVF_PTT(94, IP, IPV6, NOF, NONE, NONE, NOF, ICMP, PAY4), + + /* IPv6 --> IPv4 */ + IAVF_PTT(95, IP, IPV6, NOF, IP_IP, IPV4, FRG, NONE, PAY3), + IAVF_PTT(96, IP, IPV6, NOF, IP_IP, IPV4, NOF, NONE, PAY3), + IAVF_PTT(97, IP, IPV6, NOF, IP_IP, IPV4, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(98), + IAVF_PTT(99, IP, IPV6, NOF, IP_IP, IPV4, NOF, TCP, PAY4), + IAVF_PTT(100, IP, IPV6, NOF, IP_IP, IPV4, NOF, SCTP, PAY4), + IAVF_PTT(101, IP, IPV6, NOF, IP_IP, IPV4, NOF, ICMP, PAY4), + + /* IPv6 --> IPv6 */ + IAVF_PTT(102, IP, IPV6, NOF, IP_IP, IPV6, FRG, NONE, PAY3), + IAVF_PTT(103, IP, IPV6, NOF, IP_IP, IPV6, NOF, NONE, PAY3), + IAVF_PTT(104, IP, IPV6, NOF, IP_IP, IPV6, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(105), + IAVF_PTT(106, IP, IPV6, NOF, IP_IP, IPV6, NOF, TCP, PAY4), + IAVF_PTT(107, IP, IPV6, NOF, IP_IP, IPV6, NOF, SCTP, PAY4), + IAVF_PTT(108, IP, IPV6, NOF, IP_IP, IPV6, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT */ + IAVF_PTT(109, IP, IPV6, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3), + + /* IPv6 --> GRE/NAT -> IPv4 */ + IAVF_PTT(110, IP, IPV6, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3), + IAVF_PTT(111, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3), + IAVF_PTT(112, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(113), + IAVF_PTT(114, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4), + IAVF_PTT(115, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4), + IAVF_PTT(116, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT -> IPv6 */ + IAVF_PTT(117, IP, IPV6, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3), + IAVF_PTT(118, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3), + IAVF_PTT(119, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(120), + IAVF_PTT(121, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4), + IAVF_PTT(122, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4), + IAVF_PTT(123, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT -> MAC */ + IAVF_PTT(124, IP, IPV6, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3), + + /* IPv6 --> GRE/NAT -> MAC -> IPv4 */ + IAVF_PTT(125, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3), + IAVF_PTT(126, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3), + IAVF_PTT(127, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(128), + IAVF_PTT(129, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4), + IAVF_PTT(130, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4), + IAVF_PTT(131, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT -> MAC -> IPv6 */ + IAVF_PTT(132, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3), + IAVF_PTT(133, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3), + IAVF_PTT(134, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(135), + IAVF_PTT(136, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4), + IAVF_PTT(137, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4), + IAVF_PTT(138, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT -> MAC/VLAN */ + IAVF_PTT(139, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3), + + /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv4 */ + IAVF_PTT(140, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3), + IAVF_PTT(141, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3), + IAVF_PTT(142, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(143), + IAVF_PTT(144, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4), + IAVF_PTT(145, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4), + IAVF_PTT(146, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4), + + /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv6 */ + IAVF_PTT(147, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3), + IAVF_PTT(148, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3), + IAVF_PTT(149, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4), + IAVF_PTT_UNUSED_ENTRY(150), + IAVF_PTT(151, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4), + IAVF_PTT(152, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4), + IAVF_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4), + + /* unused entries */ + IAVF_PTT_UNUSED_ENTRY(154), + IAVF_PTT_UNUSED_ENTRY(155), + IAVF_PTT_UNUSED_ENTRY(156), + IAVF_PTT_UNUSED_ENTRY(157), + IAVF_PTT_UNUSED_ENTRY(158), + IAVF_PTT_UNUSED_ENTRY(159), + + IAVF_PTT_UNUSED_ENTRY(160), + IAVF_PTT_UNUSED_ENTRY(161), + IAVF_PTT_UNUSED_ENTRY(162), + IAVF_PTT_UNUSED_ENTRY(163), + IAVF_PTT_UNUSED_ENTRY(164), + IAVF_PTT_UNUSED_ENTRY(165), + IAVF_PTT_UNUSED_ENTRY(166), + IAVF_PTT_UNUSED_ENTRY(167), + IAVF_PTT_UNUSED_ENTRY(168), + IAVF_PTT_UNUSED_ENTRY(169), + + IAVF_PTT_UNUSED_ENTRY(170), + IAVF_PTT_UNUSED_ENTRY(171), + IAVF_PTT_UNUSED_ENTRY(172), + IAVF_PTT_UNUSED_ENTRY(173), + IAVF_PTT_UNUSED_ENTRY(174), + IAVF_PTT_UNUSED_ENTRY(175), + IAVF_PTT_UNUSED_ENTRY(176), + IAVF_PTT_UNUSED_ENTRY(177), + IAVF_PTT_UNUSED_ENTRY(178), + IAVF_PTT_UNUSED_ENTRY(179), + + IAVF_PTT_UNUSED_ENTRY(180), + IAVF_PTT_UNUSED_ENTRY(181), + IAVF_PTT_UNUSED_ENTRY(182), + IAVF_PTT_UNUSED_ENTRY(183), + IAVF_PTT_UNUSED_ENTRY(184), + IAVF_PTT_UNUSED_ENTRY(185), + IAVF_PTT_UNUSED_ENTRY(186), + IAVF_PTT_UNUSED_ENTRY(187), + IAVF_PTT_UNUSED_ENTRY(188), + IAVF_PTT_UNUSED_ENTRY(189), + + IAVF_PTT_UNUSED_ENTRY(190), + IAVF_PTT_UNUSED_ENTRY(191), + IAVF_PTT_UNUSED_ENTRY(192), + IAVF_PTT_UNUSED_ENTRY(193), + IAVF_PTT_UNUSED_ENTRY(194), + IAVF_PTT_UNUSED_ENTRY(195), + IAVF_PTT_UNUSED_ENTRY(196), + IAVF_PTT_UNUSED_ENTRY(197), + IAVF_PTT_UNUSED_ENTRY(198), + IAVF_PTT_UNUSED_ENTRY(199), + + IAVF_PTT_UNUSED_ENTRY(200), + IAVF_PTT_UNUSED_ENTRY(201), + IAVF_PTT_UNUSED_ENTRY(202), + IAVF_PTT_UNUSED_ENTRY(203), + IAVF_PTT_UNUSED_ENTRY(204), + IAVF_PTT_UNUSED_ENTRY(205), + IAVF_PTT_UNUSED_ENTRY(206), + IAVF_PTT_UNUSED_ENTRY(207), + IAVF_PTT_UNUSED_ENTRY(208), + IAVF_PTT_UNUSED_ENTRY(209), + + IAVF_PTT_UNUSED_ENTRY(210), + IAVF_PTT_UNUSED_ENTRY(211), + IAVF_PTT_UNUSED_ENTRY(212), + IAVF_PTT_UNUSED_ENTRY(213), + IAVF_PTT_UNUSED_ENTRY(214), + IAVF_PTT_UNUSED_ENTRY(215), + IAVF_PTT_UNUSED_ENTRY(216), + IAVF_PTT_UNUSED_ENTRY(217), + IAVF_PTT_UNUSED_ENTRY(218), + IAVF_PTT_UNUSED_ENTRY(219), + + IAVF_PTT_UNUSED_ENTRY(220), + IAVF_PTT_UNUSED_ENTRY(221), + IAVF_PTT_UNUSED_ENTRY(222), + IAVF_PTT_UNUSED_ENTRY(223), + IAVF_PTT_UNUSED_ENTRY(224), + IAVF_PTT_UNUSED_ENTRY(225), + IAVF_PTT_UNUSED_ENTRY(226), + IAVF_PTT_UNUSED_ENTRY(227), + IAVF_PTT_UNUSED_ENTRY(228), + IAVF_PTT_UNUSED_ENTRY(229), + + IAVF_PTT_UNUSED_ENTRY(230), + IAVF_PTT_UNUSED_ENTRY(231), + IAVF_PTT_UNUSED_ENTRY(232), + IAVF_PTT_UNUSED_ENTRY(233), + IAVF_PTT_UNUSED_ENTRY(234), + IAVF_PTT_UNUSED_ENTRY(235), + IAVF_PTT_UNUSED_ENTRY(236), + IAVF_PTT_UNUSED_ENTRY(237), + IAVF_PTT_UNUSED_ENTRY(238), + IAVF_PTT_UNUSED_ENTRY(239), + + IAVF_PTT_UNUSED_ENTRY(240), + IAVF_PTT_UNUSED_ENTRY(241), + IAVF_PTT_UNUSED_ENTRY(242), + IAVF_PTT_UNUSED_ENTRY(243), + IAVF_PTT_UNUSED_ENTRY(244), + IAVF_PTT_UNUSED_ENTRY(245), + IAVF_PTT_UNUSED_ENTRY(246), + IAVF_PTT_UNUSED_ENTRY(247), + IAVF_PTT_UNUSED_ENTRY(248), + IAVF_PTT_UNUSED_ENTRY(249), + + IAVF_PTT_UNUSED_ENTRY(250), + IAVF_PTT_UNUSED_ENTRY(251), + IAVF_PTT_UNUSED_ENTRY(252), + IAVF_PTT_UNUSED_ENTRY(253), + IAVF_PTT_UNUSED_ENTRY(254), + IAVF_PTT_UNUSED_ENTRY(255) +}; + +/** + * iavf_aq_send_msg_to_pf + * @hw: pointer to the hardware structure + * @v_opcode: opcodes for VF-PF communication + * @v_retval: return error code + * @msg: pointer to the msg buffer + * @msglen: msg length + * @cmd_details: pointer to command details + * + * Send message to PF driver using admin queue. By default, this message + * is sent asynchronously, i.e. iavf_asq_send_command() does not wait for + * completion before returning. + **/ +iavf_status iavf_aq_send_msg_to_pf(struct iavf_hw *hw, + enum virtchnl_ops v_opcode, + iavf_status v_retval, u8 *msg, u16 msglen, + struct i40e_asq_cmd_details *cmd_details) +{ + struct i40e_asq_cmd_details details; + struct i40e_aq_desc desc; + iavf_status status; + + iavf_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_send_msg_to_pf); + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_SI); + desc.cookie_high = cpu_to_le32(v_opcode); + desc.cookie_low = cpu_to_le32(v_retval); + if (msglen) { + desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF + | I40E_AQ_FLAG_RD)); + if (msglen > I40E_AQ_LARGE_BUF) + desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB); + desc.datalen = cpu_to_le16(msglen); + } + if (!cmd_details) { + memset(&details, 0, sizeof(details)); + details.async = true; + cmd_details = &details; + } + status = iavf_asq_send_command(hw, &desc, msg, msglen, cmd_details); + return status; +} + +/** + * iavf_vf_parse_hw_config + * @hw: pointer to the hardware structure + * @msg: pointer to the virtual channel VF resource structure + * + * Given a VF resource message from the PF, populate the hw struct + * with appropriate information. + **/ +void iavf_vf_parse_hw_config(struct iavf_hw *hw, + struct virtchnl_vf_resource *msg) +{ + struct virtchnl_vsi_resource *vsi_res; + int i; + + vsi_res = &msg->vsi_res[0]; + + hw->dev_caps.num_vsis = msg->num_vsis; + hw->dev_caps.num_rx_qp = msg->num_queue_pairs; + hw->dev_caps.num_tx_qp = msg->num_queue_pairs; + hw->dev_caps.num_msix_vectors_vf = msg->max_vectors; + hw->dev_caps.dcb = msg->vf_cap_flags & + VIRTCHNL_VF_OFFLOAD_L2; + hw->dev_caps.fcoe = 0; + for (i = 0; i < msg->num_vsis; i++) { + if (vsi_res->vsi_type == VIRTCHNL_VSI_SRIOV) { + ether_addr_copy(hw->mac.perm_addr, + vsi_res->default_mac_addr); + ether_addr_copy(hw->mac.addr, + vsi_res->default_mac_addr); + } + vsi_res++; + } +} + +/** + * iavf_vf_reset + * @hw: pointer to the hardware structure + * + * Send a VF_RESET message to the PF. Does not wait for response from PF + * as none will be forthcoming. Immediately after calling this function, + * the admin queue should be shut down and (optionally) reinitialized. + **/ +iavf_status iavf_vf_reset(struct iavf_hw *hw) +{ + return iavf_aq_send_msg_to_pf(hw, VIRTCHNL_OP_RESET_VF, + 0, NULL, 0, NULL); +} diff --git a/drivers/net/ethernet/intel/iavf/iavf_devids.h b/drivers/net/ethernet/intel/iavf/iavf_devids.h new file mode 100644 index 000000000000..8eb7b697e96c --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_devids.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#ifndef _IAVF_DEVIDS_H_ +#define _IAVF_DEVIDS_H_ + +/* Device IDs for the VF driver */ +#define IAVF_DEV_ID_VF 0x154C +#define IAVF_DEV_ID_VF_HV 0x1571 +#define IAVF_DEV_ID_ADAPTIVE_VF 0x1889 +#define IAVF_DEV_ID_X722_VF 0x37CD +#endif /* _IAVF_DEVIDS_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c new file mode 100644 index 000000000000..9f87304109fe --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -0,0 +1,1036 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +/* ethtool support for iavf */ +#include "iavf.h" + +#include <linux/uaccess.h> + +/* ethtool statistics helpers */ + +/** + * struct iavf_stats - definition for an ethtool statistic + * @stat_string: statistic name to display in ethtool -S output + * @sizeof_stat: the sizeof() the stat, must be no greater than sizeof(u64) + * @stat_offset: offsetof() the stat from a base pointer + * + * This structure defines a statistic to be added to the ethtool stats buffer. + * It defines a statistic as offset from a common base pointer. Stats should + * be defined in constant arrays using the IAVF_STAT macro, with every element + * of the array using the same _type for calculating the sizeof_stat and + * stat_offset. + * + * The @sizeof_stat is expected to be sizeof(u8), sizeof(u16), sizeof(u32) or + * sizeof(u64). Other sizes are not expected and will produce a WARN_ONCE from + * the iavf_add_ethtool_stat() helper function. + * + * The @stat_string is interpreted as a format string, allowing formatted + * values to be inserted while looping over multiple structures for a given + * statistics array. Thus, every statistic string in an array should have the + * same type and number of format specifiers, to be formatted by variadic + * arguments to the iavf_add_stat_string() helper function. + **/ +struct iavf_stats { + char stat_string[ETH_GSTRING_LEN]; + int sizeof_stat; + int stat_offset; +}; + +/* Helper macro to define an iavf_stat structure with proper size and type. + * Use this when defining constant statistics arrays. Note that @_type expects + * only a type name and is used multiple times. + */ +#define IAVF_STAT(_type, _name, _stat) { \ + .stat_string = _name, \ + .sizeof_stat = FIELD_SIZEOF(_type, _stat), \ + .stat_offset = offsetof(_type, _stat) \ +} + +/* Helper macro for defining some statistics related to queues */ +#define IAVF_QUEUE_STAT(_name, _stat) \ + IAVF_STAT(struct iavf_ring, _name, _stat) + +/* Stats associated with a Tx or Rx ring */ +static const struct iavf_stats iavf_gstrings_queue_stats[] = { + IAVF_QUEUE_STAT("%s-%u.packets", stats.packets), + IAVF_QUEUE_STAT("%s-%u.bytes", stats.bytes), +}; + +/** + * iavf_add_one_ethtool_stat - copy the stat into the supplied buffer + * @data: location to store the stat value + * @pointer: basis for where to copy from + * @stat: the stat definition + * + * Copies the stat data defined by the pointer and stat structure pair into + * the memory supplied as data. Used to implement iavf_add_ethtool_stats and + * iavf_add_queue_stats. If the pointer is null, data will be zero'd. + */ +static void +iavf_add_one_ethtool_stat(u64 *data, void *pointer, + const struct iavf_stats *stat) +{ + char *p; + + if (!pointer) { + /* ensure that the ethtool data buffer is zero'd for any stats + * which don't have a valid pointer. + */ + *data = 0; + return; + } + + p = (char *)pointer + stat->stat_offset; + switch (stat->sizeof_stat) { + case sizeof(u64): + *data = *((u64 *)p); + break; + case sizeof(u32): + *data = *((u32 *)p); + break; + case sizeof(u16): + *data = *((u16 *)p); + break; + case sizeof(u8): + *data = *((u8 *)p); + break; + default: + WARN_ONCE(1, "unexpected stat size for %s", + stat->stat_string); + *data = 0; + } +} + +/** + * __iavf_add_ethtool_stats - copy stats into the ethtool supplied buffer + * @data: ethtool stats buffer + * @pointer: location to copy stats from + * @stats: array of stats to copy + * @size: the size of the stats definition + * + * Copy the stats defined by the stats array using the pointer as a base into + * the data buffer supplied by ethtool. Updates the data pointer to point to + * the next empty location for successive calls to __iavf_add_ethtool_stats. + * If pointer is null, set the data values to zero and update the pointer to + * skip these stats. + **/ +static void +__iavf_add_ethtool_stats(u64 **data, void *pointer, + const struct iavf_stats stats[], + const unsigned int size) +{ + unsigned int i; + + for (i = 0; i < size; i++) + iavf_add_one_ethtool_stat((*data)++, pointer, &stats[i]); +} + +/** + * iavf_add_ethtool_stats - copy stats into ethtool supplied buffer + * @data: ethtool stats buffer + * @pointer: location where stats are stored + * @stats: static const array of stat definitions + * + * Macro to ease the use of __iavf_add_ethtool_stats by taking a static + * constant stats array and passing the ARRAY_SIZE(). This avoids typos by + * ensuring that we pass the size associated with the given stats array. + * + * The parameter @stats is evaluated twice, so parameters with side effects + * should be avoided. + **/ +#define iavf_add_ethtool_stats(data, pointer, stats) \ + __iavf_add_ethtool_stats(data, pointer, stats, ARRAY_SIZE(stats)) + +/** + * iavf_add_queue_stats - copy queue statistics into supplied buffer + * @data: ethtool stats buffer + * @ring: the ring to copy + * + * Queue statistics must be copied while protected by + * u64_stats_fetch_begin_irq, so we can't directly use iavf_add_ethtool_stats. + * Assumes that queue stats are defined in iavf_gstrings_queue_stats. If the + * ring pointer is null, zero out the queue stat values and update the data + * pointer. Otherwise safely copy the stats from the ring into the supplied + * buffer and update the data pointer when finished. + * + * This function expects to be called while under rcu_read_lock(). + **/ +static void +iavf_add_queue_stats(u64 **data, struct iavf_ring *ring) +{ + const unsigned int size = ARRAY_SIZE(iavf_gstrings_queue_stats); + const struct iavf_stats *stats = iavf_gstrings_queue_stats; + unsigned int start; + unsigned int i; + + /* To avoid invalid statistics values, ensure that we keep retrying + * the copy until we get a consistent value according to + * u64_stats_fetch_retry_irq. But first, make sure our ring is + * non-null before attempting to access its syncp. + */ + do { + start = !ring ? 0 : u64_stats_fetch_begin_irq(&ring->syncp); + for (i = 0; i < size; i++) + iavf_add_one_ethtool_stat(&(*data)[i], ring, &stats[i]); + } while (ring && u64_stats_fetch_retry_irq(&ring->syncp, start)); + + /* Once we successfully copy the stats in, update the data pointer */ + *data += size; +} + +/** + * __iavf_add_stat_strings - copy stat strings into ethtool buffer + * @p: ethtool supplied buffer + * @stats: stat definitions array + * @size: size of the stats array + * + * Format and copy the strings described by stats into the buffer pointed at + * by p. + **/ +static void __iavf_add_stat_strings(u8 **p, const struct iavf_stats stats[], + const unsigned int size, ...) +{ + unsigned int i; + + for (i = 0; i < size; i++) { + va_list args; + + va_start(args, size); + vsnprintf(*p, ETH_GSTRING_LEN, stats[i].stat_string, args); + *p += ETH_GSTRING_LEN; + va_end(args); + } +} + +/** + * iavf_add_stat_strings - copy stat strings into ethtool buffer + * @p: ethtool supplied buffer + * @stats: stat definitions array + * + * Format and copy the strings described by the const static stats value into + * the buffer pointed at by p. + * + * The parameter @stats is evaluated twice, so parameters with side effects + * should be avoided. Additionally, stats must be an array such that + * ARRAY_SIZE can be called on it. + **/ +#define iavf_add_stat_strings(p, stats, ...) \ + __iavf_add_stat_strings(p, stats, ARRAY_SIZE(stats), ## __VA_ARGS__) + +#define VF_STAT(_name, _stat) \ + IAVF_STAT(struct iavf_adapter, _name, _stat) + +static const struct iavf_stats iavf_gstrings_stats[] = { + VF_STAT("rx_bytes", current_stats.rx_bytes), + VF_STAT("rx_unicast", current_stats.rx_unicast), + VF_STAT("rx_multicast", current_stats.rx_multicast), + VF_STAT("rx_broadcast", current_stats.rx_broadcast), + VF_STAT("rx_discards", current_stats.rx_discards), + VF_STAT("rx_unknown_protocol", current_stats.rx_unknown_protocol), + VF_STAT("tx_bytes", current_stats.tx_bytes), + VF_STAT("tx_unicast", current_stats.tx_unicast), + VF_STAT("tx_multicast", current_stats.tx_multicast), + VF_STAT("tx_broadcast", current_stats.tx_broadcast), + VF_STAT("tx_discards", current_stats.tx_discards), + VF_STAT("tx_errors", current_stats.tx_errors), +}; + +#define IAVF_STATS_LEN ARRAY_SIZE(iavf_gstrings_stats) + +#define IAVF_QUEUE_STATS_LEN ARRAY_SIZE(iavf_gstrings_queue_stats) + +/* For now we have one and only one private flag and it is only defined + * when we have support for the SKIP_CPU_SYNC DMA attribute. Instead + * of leaving all this code sitting around empty we will strip it unless + * our one private flag is actually available. + */ +struct iavf_priv_flags { + char flag_string[ETH_GSTRING_LEN]; + u32 flag; + bool read_only; +}; + +#define IAVF_PRIV_FLAG(_name, _flag, _read_only) { \ + .flag_string = _name, \ + .flag = _flag, \ + .read_only = _read_only, \ +} + +static const struct iavf_priv_flags iavf_gstrings_priv_flags[] = { + IAVF_PRIV_FLAG("legacy-rx", IAVF_FLAG_LEGACY_RX, 0), +}; + +#define IAVF_PRIV_FLAGS_STR_LEN ARRAY_SIZE(iavf_gstrings_priv_flags) + +/** + * iavf_get_link_ksettings - Get Link Speed and Duplex settings + * @netdev: network interface device structure + * @cmd: ethtool command + * + * Reports speed/duplex settings. Because this is a VF, we don't know what + * kind of link we really have, so we fake it. + **/ +static int iavf_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + ethtool_link_ksettings_zero_link_mode(cmd, supported); + cmd->base.autoneg = AUTONEG_DISABLE; + cmd->base.port = PORT_NONE; + /* Set speed and duplex */ + switch (adapter->link_speed) { + case I40E_LINK_SPEED_40GB: + cmd->base.speed = SPEED_40000; + break; + case I40E_LINK_SPEED_25GB: +#ifdef SPEED_25000 + cmd->base.speed = SPEED_25000; +#else + netdev_info(netdev, + "Speed is 25G, display not supported by this version of ethtool.\n"); +#endif + break; + case I40E_LINK_SPEED_20GB: + cmd->base.speed = SPEED_20000; + break; + case I40E_LINK_SPEED_10GB: + cmd->base.speed = SPEED_10000; + break; + case I40E_LINK_SPEED_1GB: + cmd->base.speed = SPEED_1000; + break; + case I40E_LINK_SPEED_100MB: + cmd->base.speed = SPEED_100; + break; + default: + break; + } + cmd->base.duplex = DUPLEX_FULL; + + return 0; +} + +/** + * iavf_get_sset_count - Get length of string set + * @netdev: network interface device structure + * @sset: id of string set + * + * Reports size of various string tables. + **/ +static int iavf_get_sset_count(struct net_device *netdev, int sset) +{ + if (sset == ETH_SS_STATS) + return IAVF_STATS_LEN + + (IAVF_QUEUE_STATS_LEN * 2 * IAVF_MAX_REQ_QUEUES); + else if (sset == ETH_SS_PRIV_FLAGS) + return IAVF_PRIV_FLAGS_STR_LEN; + else + return -EINVAL; +} + +/** + * iavf_get_ethtool_stats - report device statistics + * @netdev: network interface device structure + * @stats: ethtool statistics structure + * @data: pointer to data buffer + * + * All statistics are added to the data buffer as an array of u64. + **/ +static void iavf_get_ethtool_stats(struct net_device *netdev, + struct ethtool_stats *stats, u64 *data) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + unsigned int i; + + iavf_add_ethtool_stats(&data, adapter, iavf_gstrings_stats); + + rcu_read_lock(); + for (i = 0; i < IAVF_MAX_REQ_QUEUES; i++) { + struct iavf_ring *ring; + + /* Avoid accessing un-allocated queues */ + ring = (i < adapter->num_active_queues ? + &adapter->tx_rings[i] : NULL); + iavf_add_queue_stats(&data, ring); + + /* Avoid accessing un-allocated queues */ + ring = (i < adapter->num_active_queues ? + &adapter->rx_rings[i] : NULL); + iavf_add_queue_stats(&data, ring); + } + rcu_read_unlock(); +} + +/** + * iavf_get_priv_flag_strings - Get private flag strings + * @netdev: network interface device structure + * @data: buffer for string data + * + * Builds the private flags string table + **/ +static void iavf_get_priv_flag_strings(struct net_device *netdev, u8 *data) +{ + unsigned int i; + + for (i = 0; i < IAVF_PRIV_FLAGS_STR_LEN; i++) { + snprintf(data, ETH_GSTRING_LEN, "%s", + iavf_gstrings_priv_flags[i].flag_string); + data += ETH_GSTRING_LEN; + } +} + +/** + * iavf_get_stat_strings - Get stat strings + * @netdev: network interface device structure + * @data: buffer for string data + * + * Builds the statistics string table + **/ +static void iavf_get_stat_strings(struct net_device *netdev, u8 *data) +{ + unsigned int i; + + iavf_add_stat_strings(&data, iavf_gstrings_stats); + + /* Queues are always allocated in pairs, so we just use num_tx_queues + * for both Tx and Rx queues. + */ + for (i = 0; i < netdev->num_tx_queues; i++) { + iavf_add_stat_strings(&data, iavf_gstrings_queue_stats, + "tx", i); + iavf_add_stat_strings(&data, iavf_gstrings_queue_stats, + "rx", i); + } +} + +/** + * iavf_get_strings - Get string set + * @netdev: network interface device structure + * @sset: id of string set + * @data: buffer for string data + * + * Builds string tables for various string sets + **/ +static void iavf_get_strings(struct net_device *netdev, u32 sset, u8 *data) +{ + switch (sset) { + case ETH_SS_STATS: + iavf_get_stat_strings(netdev, data); + break; + case ETH_SS_PRIV_FLAGS: + iavf_get_priv_flag_strings(netdev, data); + break; + default: + break; + } +} + +/** + * iavf_get_priv_flags - report device private flags + * @netdev: network interface device structure + * + * The get string set count and the string set should be matched for each + * flag returned. Add new strings for each flag to the iavf_gstrings_priv_flags + * array. + * + * Returns a u32 bitmap of flags. + **/ +static u32 iavf_get_priv_flags(struct net_device *netdev) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + u32 i, ret_flags = 0; + + for (i = 0; i < IAVF_PRIV_FLAGS_STR_LEN; i++) { + const struct iavf_priv_flags *priv_flags; + + priv_flags = &iavf_gstrings_priv_flags[i]; + + if (priv_flags->flag & adapter->flags) + ret_flags |= BIT(i); + } + + return ret_flags; +} + +/** + * iavf_set_priv_flags - set private flags + * @netdev: network interface device structure + * @flags: bit flags to be set + **/ +static int iavf_set_priv_flags(struct net_device *netdev, u32 flags) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + u32 orig_flags, new_flags, changed_flags; + u32 i; + + orig_flags = READ_ONCE(adapter->flags); + new_flags = orig_flags; + + for (i = 0; i < IAVF_PRIV_FLAGS_STR_LEN; i++) { + const struct iavf_priv_flags *priv_flags; + + priv_flags = &iavf_gstrings_priv_flags[i]; + + if (flags & BIT(i)) + new_flags |= priv_flags->flag; + else + new_flags &= ~(priv_flags->flag); + + if (priv_flags->read_only && + ((orig_flags ^ new_flags) & ~BIT(i))) + return -EOPNOTSUPP; + } + + /* Before we finalize any flag changes, any checks which we need to + * perform to determine if the new flags will be supported should go + * here... + */ + + /* Compare and exchange the new flags into place. If we failed, that + * is if cmpxchg returns anything but the old value, this means + * something else must have modified the flags variable since we + * copied it. We'll just punt with an error and log something in the + * message buffer. + */ + if (cmpxchg(&adapter->flags, orig_flags, new_flags) != orig_flags) { + dev_warn(&adapter->pdev->dev, + "Unable to update adapter->flags as it was modified by another thread...\n"); + return -EAGAIN; + } + + changed_flags = orig_flags ^ new_flags; + + /* Process any additional changes needed as a result of flag changes. + * The changed_flags value reflects the list of bits that were changed + * in the code above. + */ + + /* issue a reset to force legacy-rx change to take effect */ + if (changed_flags & IAVF_FLAG_LEGACY_RX) { + if (netif_running(netdev)) { + adapter->flags |= IAVF_FLAG_RESET_NEEDED; + schedule_work(&adapter->reset_task); + } + } + + return 0; +} + +/** + * iavf_get_msglevel - Get debug message level + * @netdev: network interface device structure + * + * Returns current debug message level. + **/ +static u32 iavf_get_msglevel(struct net_device *netdev) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + return adapter->msg_enable; +} + +/** + * iavf_set_msglevel - Set debug message level + * @netdev: network interface device structure + * @data: message level + * + * Set current debug message level. Higher values cause the driver to + * be noisier. + **/ +static void iavf_set_msglevel(struct net_device *netdev, u32 data) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + if (IAVF_DEBUG_USER & data) + adapter->hw.debug_mask = data; + adapter->msg_enable = data; +} + +/** + * iavf_get_drvinfo - Get driver info + * @netdev: network interface device structure + * @drvinfo: ethool driver info structure + * + * Returns information about the driver and device for display to the user. + **/ +static void iavf_get_drvinfo(struct net_device *netdev, + struct ethtool_drvinfo *drvinfo) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + strlcpy(drvinfo->driver, iavf_driver_name, 32); + strlcpy(drvinfo->version, iavf_driver_version, 32); + strlcpy(drvinfo->fw_version, "N/A", 4); + strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), 32); + drvinfo->n_priv_flags = IAVF_PRIV_FLAGS_STR_LEN; +} + +/** + * iavf_get_ringparam - Get ring parameters + * @netdev: network interface device structure + * @ring: ethtool ringparam structure + * + * Returns current ring parameters. TX and RX rings are reported separately, + * but the number of rings is not reported. + **/ +static void iavf_get_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + ring->rx_max_pending = IAVF_MAX_RXD; + ring->tx_max_pending = IAVF_MAX_TXD; + ring->rx_pending = adapter->rx_desc_count; + ring->tx_pending = adapter->tx_desc_count; +} + +/** + * iavf_set_ringparam - Set ring parameters + * @netdev: network interface device structure + * @ring: ethtool ringparam structure + * + * Sets ring parameters. TX and RX rings are controlled separately, but the + * number of rings is not specified, so all rings get the same settings. + **/ +static int iavf_set_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + u32 new_rx_count, new_tx_count; + + if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending)) + return -EINVAL; + + new_tx_count = clamp_t(u32, ring->tx_pending, + IAVF_MIN_TXD, + IAVF_MAX_TXD); + new_tx_count = ALIGN(new_tx_count, IAVF_REQ_DESCRIPTOR_MULTIPLE); + + new_rx_count = clamp_t(u32, ring->rx_pending, + IAVF_MIN_RXD, + IAVF_MAX_RXD); + new_rx_count = ALIGN(new_rx_count, IAVF_REQ_DESCRIPTOR_MULTIPLE); + + /* if nothing to do return success */ + if ((new_tx_count == adapter->tx_desc_count) && + (new_rx_count == adapter->rx_desc_count)) + return 0; + + adapter->tx_desc_count = new_tx_count; + adapter->rx_desc_count = new_rx_count; + + if (netif_running(netdev)) { + adapter->flags |= IAVF_FLAG_RESET_NEEDED; + schedule_work(&adapter->reset_task); + } + + return 0; +} + +/** + * __iavf_get_coalesce - get per-queue coalesce settings + * @netdev: the netdev to check + * @ec: ethtool coalesce data structure + * @queue: which queue to pick + * + * Gets the per-queue settings for coalescence. Specifically Rx and Tx usecs + * are per queue. If queue is <0 then we default to queue 0 as the + * representative value. + **/ +static int __iavf_get_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec, int queue) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + struct iavf_vsi *vsi = &adapter->vsi; + struct iavf_ring *rx_ring, *tx_ring; + + ec->tx_max_coalesced_frames = vsi->work_limit; + ec->rx_max_coalesced_frames = vsi->work_limit; + + /* Rx and Tx usecs per queue value. If user doesn't specify the + * queue, return queue 0's value to represent. + */ + if (queue < 0) + queue = 0; + else if (queue >= adapter->num_active_queues) + return -EINVAL; + + rx_ring = &adapter->rx_rings[queue]; + tx_ring = &adapter->tx_rings[queue]; + + if (ITR_IS_DYNAMIC(rx_ring->itr_setting)) + ec->use_adaptive_rx_coalesce = 1; + + if (ITR_IS_DYNAMIC(tx_ring->itr_setting)) + ec->use_adaptive_tx_coalesce = 1; + + ec->rx_coalesce_usecs = rx_ring->itr_setting & ~IAVF_ITR_DYNAMIC; + ec->tx_coalesce_usecs = tx_ring->itr_setting & ~IAVF_ITR_DYNAMIC; + + return 0; +} + +/** + * iavf_get_coalesce - Get interrupt coalescing settings + * @netdev: network interface device structure + * @ec: ethtool coalesce structure + * + * Returns current coalescing settings. This is referred to elsewhere in the + * driver as Interrupt Throttle Rate, as this is how the hardware describes + * this functionality. Note that if per-queue settings have been modified this + * only represents the settings of queue 0. + **/ +static int iavf_get_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec) +{ + return __iavf_get_coalesce(netdev, ec, -1); +} + +/** + * iavf_get_per_queue_coalesce - get coalesce values for specific queue + * @netdev: netdev to read + * @ec: coalesce settings from ethtool + * @queue: the queue to read + * + * Read specific queue's coalesce settings. + **/ +static int iavf_get_per_queue_coalesce(struct net_device *netdev, u32 queue, + struct ethtool_coalesce *ec) +{ + return __iavf_get_coalesce(netdev, ec, queue); +} + +/** + * iavf_set_itr_per_queue - set ITR values for specific queue + * @adapter: the VF adapter struct to set values for + * @ec: coalesce settings from ethtool + * @queue: the queue to modify + * + * Change the ITR settings for a specific queue. + **/ +static void iavf_set_itr_per_queue(struct iavf_adapter *adapter, + struct ethtool_coalesce *ec, int queue) +{ + struct iavf_ring *rx_ring = &adapter->rx_rings[queue]; + struct iavf_ring *tx_ring = &adapter->tx_rings[queue]; + struct iavf_q_vector *q_vector; + + rx_ring->itr_setting = ITR_REG_ALIGN(ec->rx_coalesce_usecs); + tx_ring->itr_setting = ITR_REG_ALIGN(ec->tx_coalesce_usecs); + + rx_ring->itr_setting |= IAVF_ITR_DYNAMIC; + if (!ec->use_adaptive_rx_coalesce) + rx_ring->itr_setting ^= IAVF_ITR_DYNAMIC; + + tx_ring->itr_setting |= IAVF_ITR_DYNAMIC; + if (!ec->use_adaptive_tx_coalesce) + tx_ring->itr_setting ^= IAVF_ITR_DYNAMIC; + + q_vector = rx_ring->q_vector; + q_vector->rx.target_itr = ITR_TO_REG(rx_ring->itr_setting); + + q_vector = tx_ring->q_vector; + q_vector->tx.target_itr = ITR_TO_REG(tx_ring->itr_setting); + + /* The interrupt handler itself will take care of programming + * the Tx and Rx ITR values based on the values we have entered + * into the q_vector, no need to write the values now. + */ +} + +/** + * __iavf_set_coalesce - set coalesce settings for particular queue + * @netdev: the netdev to change + * @ec: ethtool coalesce settings + * @queue: the queue to change + * + * Sets the coalesce settings for a particular queue. + **/ +static int __iavf_set_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec, int queue) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + struct iavf_vsi *vsi = &adapter->vsi; + int i; + + if (ec->tx_max_coalesced_frames_irq || ec->rx_max_coalesced_frames_irq) + vsi->work_limit = ec->tx_max_coalesced_frames_irq; + + if (ec->rx_coalesce_usecs == 0) { + if (ec->use_adaptive_rx_coalesce) + netif_info(adapter, drv, netdev, "rx-usecs=0, need to disable adaptive-rx for a complete disable\n"); + } else if ((ec->rx_coalesce_usecs < IAVF_MIN_ITR) || + (ec->rx_coalesce_usecs > IAVF_MAX_ITR)) { + netif_info(adapter, drv, netdev, "Invalid value, rx-usecs range is 0-8160\n"); + return -EINVAL; + } else if (ec->tx_coalesce_usecs == 0) { + if (ec->use_adaptive_tx_coalesce) + netif_info(adapter, drv, netdev, "tx-usecs=0, need to disable adaptive-tx for a complete disable\n"); + } else if ((ec->tx_coalesce_usecs < IAVF_MIN_ITR) || + (ec->tx_coalesce_usecs > IAVF_MAX_ITR)) { + netif_info(adapter, drv, netdev, "Invalid value, tx-usecs range is 0-8160\n"); + return -EINVAL; + } + + /* Rx and Tx usecs has per queue value. If user doesn't specify the + * queue, apply to all queues. + */ + if (queue < 0) { + for (i = 0; i < adapter->num_active_queues; i++) + iavf_set_itr_per_queue(adapter, ec, i); + } else if (queue < adapter->num_active_queues) { + iavf_set_itr_per_queue(adapter, ec, queue); + } else { + netif_info(adapter, drv, netdev, "Invalid queue value, queue range is 0 - %d\n", + adapter->num_active_queues - 1); + return -EINVAL; + } + + return 0; +} + +/** + * iavf_set_coalesce - Set interrupt coalescing settings + * @netdev: network interface device structure + * @ec: ethtool coalesce structure + * + * Change current coalescing settings for every queue. + **/ +static int iavf_set_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec) +{ + return __iavf_set_coalesce(netdev, ec, -1); +} + +/** + * iavf_set_per_queue_coalesce - set specific queue's coalesce settings + * @netdev: the netdev to change + * @ec: ethtool's coalesce settings + * @queue: the queue to modify + * + * Modifies a specific queue's coalesce settings. + */ +static int iavf_set_per_queue_coalesce(struct net_device *netdev, u32 queue, + struct ethtool_coalesce *ec) +{ + return __iavf_set_coalesce(netdev, ec, queue); +} + +/** + * iavf_get_rxnfc - command to get RX flow classification rules + * @netdev: network interface device structure + * @cmd: ethtool rxnfc command + * @rule_locs: pointer to store rule locations + * + * Returns Success if the command is supported. + **/ +static int iavf_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, + u32 *rule_locs) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + int ret = -EOPNOTSUPP; + + switch (cmd->cmd) { + case ETHTOOL_GRXRINGS: + cmd->data = adapter->num_active_queues; + ret = 0; + break; + case ETHTOOL_GRXFH: + netdev_info(netdev, + "RSS hash info is not available to vf, use pf.\n"); + break; + default: + break; + } + + return ret; +} +/** + * iavf_get_channels: get the number of channels supported by the device + * @netdev: network interface device structure + * @ch: channel information structure + * + * For the purposes of our device, we only use combined channels, i.e. a tx/rx + * queue pair. Report one extra channel to match our "other" MSI-X vector. + **/ +static void iavf_get_channels(struct net_device *netdev, + struct ethtool_channels *ch) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + /* Report maximum channels */ + ch->max_combined = IAVF_MAX_REQ_QUEUES; + + ch->max_other = NONQ_VECS; + ch->other_count = NONQ_VECS; + + ch->combined_count = adapter->num_active_queues; +} + +/** + * iavf_set_channels: set the new channel count + * @netdev: network interface device structure + * @ch: channel information structure + * + * Negotiate a new number of channels with the PF then do a reset. During + * reset we'll realloc queues and fix the RSS table. Returns 0 on success, + * negative on failure. + **/ +static int iavf_set_channels(struct net_device *netdev, + struct ethtool_channels *ch) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + int num_req = ch->combined_count; + + if (num_req != adapter->num_active_queues && + !(adapter->vf_res->vf_cap_flags & + VIRTCHNL_VF_OFFLOAD_REQ_QUEUES)) { + dev_info(&adapter->pdev->dev, "PF is not capable of queue negotiation.\n"); + return -EINVAL; + } + + if ((adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) && + adapter->num_tc) { + dev_info(&adapter->pdev->dev, "Cannot set channels since ADq is enabled.\n"); + return -EINVAL; + } + + /* All of these should have already been checked by ethtool before this + * even gets to us, but just to be sure. + */ + if (num_req <= 0 || num_req > IAVF_MAX_REQ_QUEUES) + return -EINVAL; + + if (ch->rx_count || ch->tx_count || ch->other_count != NONQ_VECS) + return -EINVAL; + + adapter->num_req_queues = num_req; + return iavf_request_queues(adapter, num_req); +} + +/** + * iavf_get_rxfh_key_size - get the RSS hash key size + * @netdev: network interface device structure + * + * Returns the table size. + **/ +static u32 iavf_get_rxfh_key_size(struct net_device *netdev) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + return adapter->rss_key_size; +} + +/** + * iavf_get_rxfh_indir_size - get the rx flow hash indirection table size + * @netdev: network interface device structure + * + * Returns the table size. + **/ +static u32 iavf_get_rxfh_indir_size(struct net_device *netdev) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + return adapter->rss_lut_size; +} + +/** + * iavf_get_rxfh - get the rx flow hash indirection table + * @netdev: network interface device structure + * @indir: indirection table + * @key: hash key + * @hfunc: hash function in use + * + * Reads the indirection table directly from the hardware. Always returns 0. + **/ +static int iavf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, + u8 *hfunc) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + u16 i; + + if (hfunc) + *hfunc = ETH_RSS_HASH_TOP; + if (!indir) + return 0; + + memcpy(key, adapter->rss_key, adapter->rss_key_size); + + /* Each 32 bits pointed by 'indir' is stored with a lut entry */ + for (i = 0; i < adapter->rss_lut_size; i++) + indir[i] = (u32)adapter->rss_lut[i]; + + return 0; +} + +/** + * iavf_set_rxfh - set the rx flow hash indirection table + * @netdev: network interface device structure + * @indir: indirection table + * @key: hash key + * @hfunc: hash function to use + * + * Returns -EINVAL if the table specifies an inavlid queue id, otherwise + * returns 0 after programming the table. + **/ +static int iavf_set_rxfh(struct net_device *netdev, const u32 *indir, + const u8 *key, const u8 hfunc) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + u16 i; + + /* We do not allow change in unsupported parameters */ + if (key || + (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)) + return -EOPNOTSUPP; + if (!indir) + return 0; + + if (key) + memcpy(adapter->rss_key, key, adapter->rss_key_size); + + /* Each 32 bits pointed by 'indir' is stored with a lut entry */ + for (i = 0; i < adapter->rss_lut_size; i++) + adapter->rss_lut[i] = (u8)(indir[i]); + + return iavf_config_rss(adapter); +} + +static const struct ethtool_ops iavf_ethtool_ops = { + .get_drvinfo = iavf_get_drvinfo, + .get_link = ethtool_op_get_link, + .get_ringparam = iavf_get_ringparam, + .set_ringparam = iavf_set_ringparam, + .get_strings = iavf_get_strings, + .get_ethtool_stats = iavf_get_ethtool_stats, + .get_sset_count = iavf_get_sset_count, + .get_priv_flags = iavf_get_priv_flags, + .set_priv_flags = iavf_set_priv_flags, + .get_msglevel = iavf_get_msglevel, + .set_msglevel = iavf_set_msglevel, + .get_coalesce = iavf_get_coalesce, + .set_coalesce = iavf_set_coalesce, + .get_per_queue_coalesce = iavf_get_per_queue_coalesce, + .set_per_queue_coalesce = iavf_set_per_queue_coalesce, + .get_rxnfc = iavf_get_rxnfc, + .get_rxfh_indir_size = iavf_get_rxfh_indir_size, + .get_rxfh = iavf_get_rxfh, + .set_rxfh = iavf_set_rxfh, + .get_channels = iavf_get_channels, + .set_channels = iavf_set_channels, + .get_rxfh_key_size = iavf_get_rxfh_key_size, + .get_link_ksettings = iavf_get_link_ksettings, +}; + +/** + * iavf_set_ethtool_ops - Initialize ethtool ops struct + * @netdev: network interface device structure + * + * Sets ethtool ops struct in our netdev so that ethtool can call + * our functions. + **/ +void iavf_set_ethtool_ops(struct net_device *netdev) +{ + netdev->ethtool_ops = &iavf_ethtool_ops; +} diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 5906c1c1d19d..8c71c698a2ef 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -1,38 +1,38 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2013 - 2018 Intel Corporation. */ -#include "i40evf.h" -#include "i40e_prototype.h" -#include "i40evf_client.h" -/* All i40evf tracepoints are defined by the include below, which must +#include "iavf.h" +#include "iavf_prototype.h" +#include "iavf_client.h" +/* All iavf tracepoints are defined by the include below, which must * be included exactly once across the whole kernel with * CREATE_TRACE_POINTS defined */ #define CREATE_TRACE_POINTS -#include "i40e_trace.h" +#include "iavf_trace.h" -static int i40evf_setup_all_tx_resources(struct i40evf_adapter *adapter); -static int i40evf_setup_all_rx_resources(struct i40evf_adapter *adapter); -static int i40evf_close(struct net_device *netdev); +static int iavf_setup_all_tx_resources(struct iavf_adapter *adapter); +static int iavf_setup_all_rx_resources(struct iavf_adapter *adapter); +static int iavf_close(struct net_device *netdev); -char i40evf_driver_name[] = "i40evf"; -static const char i40evf_driver_string[] = - "Intel(R) 40-10 Gigabit Virtual Function Network Driver"; +char iavf_driver_name[] = "iavf"; +static const char iavf_driver_string[] = + "Intel(R) Ethernet Adaptive Virtual Function Network Driver"; #define DRV_KERN "-k" #define DRV_VERSION_MAJOR 3 #define DRV_VERSION_MINOR 2 -#define DRV_VERSION_BUILD 2 +#define DRV_VERSION_BUILD 3 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \ __stringify(DRV_VERSION_MINOR) "." \ __stringify(DRV_VERSION_BUILD) \ DRV_KERN -const char i40evf_driver_version[] = DRV_VERSION; -static const char i40evf_copyright[] = - "Copyright (c) 2013 - 2015 Intel Corporation."; +const char iavf_driver_version[] = DRV_VERSION; +static const char iavf_copyright[] = + "Copyright (c) 2013 - 2018 Intel Corporation."; -/* i40evf_pci_tbl - PCI Device ID Table +/* iavf_pci_tbl - PCI Device ID Table * * Wildcard entries (PCI_ANY_ID) should come last * Last entry must be all 0s @@ -40,36 +40,37 @@ static const char i40evf_copyright[] = * { Vendor ID, Device ID, SubVendor ID, SubDevice ID, * Class, Class Mask, private data (not used) } */ -static const struct pci_device_id i40evf_pci_tbl[] = { - {PCI_VDEVICE(INTEL, I40E_DEV_ID_VF), 0}, - {PCI_VDEVICE(INTEL, I40E_DEV_ID_VF_HV), 0}, - {PCI_VDEVICE(INTEL, I40E_DEV_ID_X722_VF), 0}, - {PCI_VDEVICE(INTEL, I40E_DEV_ID_ADAPTIVE_VF), 0}, +static const struct pci_device_id iavf_pci_tbl[] = { + {PCI_VDEVICE(INTEL, IAVF_DEV_ID_VF), 0}, + {PCI_VDEVICE(INTEL, IAVF_DEV_ID_VF_HV), 0}, + {PCI_VDEVICE(INTEL, IAVF_DEV_ID_X722_VF), 0}, + {PCI_VDEVICE(INTEL, IAVF_DEV_ID_ADAPTIVE_VF), 0}, /* required last entry */ {0, } }; -MODULE_DEVICE_TABLE(pci, i40evf_pci_tbl); +MODULE_DEVICE_TABLE(pci, iavf_pci_tbl); +MODULE_ALIAS("i40evf"); MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); -MODULE_DESCRIPTION("Intel(R) XL710 X710 Virtual Function Network Driver"); -MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Intel(R) Ethernet Adaptive Virtual Function Network Driver"); +MODULE_LICENSE("GPL v2"); MODULE_VERSION(DRV_VERSION); -static struct workqueue_struct *i40evf_wq; +static struct workqueue_struct *iavf_wq; /** - * i40evf_allocate_dma_mem_d - OS specific memory alloc for shared code + * iavf_allocate_dma_mem_d - OS specific memory alloc for shared code * @hw: pointer to the HW structure * @mem: ptr to mem struct to fill out * @size: size of memory requested * @alignment: what to align the allocation to **/ -i40e_status i40evf_allocate_dma_mem_d(struct i40e_hw *hw, - struct i40e_dma_mem *mem, - u64 size, u32 alignment) +iavf_status iavf_allocate_dma_mem_d(struct iavf_hw *hw, + struct iavf_dma_mem *mem, + u64 size, u32 alignment) { - struct i40evf_adapter *adapter = (struct i40evf_adapter *)hw->back; + struct iavf_adapter *adapter = (struct iavf_adapter *)hw->back; if (!mem) return I40E_ERR_PARAM; @@ -84,13 +85,13 @@ i40e_status i40evf_allocate_dma_mem_d(struct i40e_hw *hw, } /** - * i40evf_free_dma_mem_d - OS specific memory free for shared code + * iavf_free_dma_mem_d - OS specific memory free for shared code * @hw: pointer to the HW structure * @mem: ptr to mem struct to free **/ -i40e_status i40evf_free_dma_mem_d(struct i40e_hw *hw, struct i40e_dma_mem *mem) +iavf_status iavf_free_dma_mem_d(struct iavf_hw *hw, struct iavf_dma_mem *mem) { - struct i40evf_adapter *adapter = (struct i40evf_adapter *)hw->back; + struct iavf_adapter *adapter = (struct iavf_adapter *)hw->back; if (!mem || !mem->va) return I40E_ERR_PARAM; @@ -100,13 +101,13 @@ i40e_status i40evf_free_dma_mem_d(struct i40e_hw *hw, struct i40e_dma_mem *mem) } /** - * i40evf_allocate_virt_mem_d - OS specific memory alloc for shared code + * iavf_allocate_virt_mem_d - OS specific memory alloc for shared code * @hw: pointer to the HW structure * @mem: ptr to mem struct to fill out * @size: size of memory requested **/ -i40e_status i40evf_allocate_virt_mem_d(struct i40e_hw *hw, - struct i40e_virt_mem *mem, u32 size) +iavf_status iavf_allocate_virt_mem_d(struct iavf_hw *hw, + struct iavf_virt_mem *mem, u32 size) { if (!mem) return I40E_ERR_PARAM; @@ -121,12 +122,11 @@ i40e_status i40evf_allocate_virt_mem_d(struct i40e_hw *hw, } /** - * i40evf_free_virt_mem_d - OS specific memory free for shared code + * iavf_free_virt_mem_d - OS specific memory free for shared code * @hw: pointer to the HW structure * @mem: ptr to mem struct to free **/ -i40e_status i40evf_free_virt_mem_d(struct i40e_hw *hw, - struct i40e_virt_mem *mem) +iavf_status iavf_free_virt_mem_d(struct iavf_hw *hw, struct iavf_virt_mem *mem) { if (!mem) return I40E_ERR_PARAM; @@ -138,17 +138,17 @@ i40e_status i40evf_free_virt_mem_d(struct i40e_hw *hw, } /** - * i40evf_debug_d - OS dependent version of debug printing + * iavf_debug_d - OS dependent version of debug printing * @hw: pointer to the HW structure * @mask: debug level mask * @fmt_str: printf-type format description **/ -void i40evf_debug_d(void *hw, u32 mask, char *fmt_str, ...) +void iavf_debug_d(void *hw, u32 mask, char *fmt_str, ...) { char buf[512]; va_list argptr; - if (!(mask & ((struct i40e_hw *)hw)->debug_mask)) + if (!(mask & ((struct iavf_hw *)hw)->debug_mask)) return; va_start(argptr, fmt_str); @@ -160,134 +160,131 @@ void i40evf_debug_d(void *hw, u32 mask, char *fmt_str, ...) } /** - * i40evf_schedule_reset - Set the flags and schedule a reset event + * iavf_schedule_reset - Set the flags and schedule a reset event * @adapter: board private structure **/ -void i40evf_schedule_reset(struct i40evf_adapter *adapter) +void iavf_schedule_reset(struct iavf_adapter *adapter) { if (!(adapter->flags & - (I40EVF_FLAG_RESET_PENDING | I40EVF_FLAG_RESET_NEEDED))) { - adapter->flags |= I40EVF_FLAG_RESET_NEEDED; + (IAVF_FLAG_RESET_PENDING | IAVF_FLAG_RESET_NEEDED))) { + adapter->flags |= IAVF_FLAG_RESET_NEEDED; schedule_work(&adapter->reset_task); } } /** - * i40evf_tx_timeout - Respond to a Tx Hang + * iavf_tx_timeout - Respond to a Tx Hang * @netdev: network interface device structure **/ -static void i40evf_tx_timeout(struct net_device *netdev) +static void iavf_tx_timeout(struct net_device *netdev) { - struct i40evf_adapter *adapter = netdev_priv(netdev); + struct iavf_adapter *adapter = netdev_priv(netdev); adapter->tx_timeout_count++; - i40evf_schedule_reset(adapter); + iavf_schedule_reset(adapter); } /** - * i40evf_misc_irq_disable - Mask off interrupt generation on the NIC + * iavf_misc_irq_disable - Mask off interrupt generation on the NIC * @adapter: board private structure **/ -static void i40evf_misc_irq_disable(struct i40evf_adapter *adapter) +static void iavf_misc_irq_disable(struct iavf_adapter *adapter) { - struct i40e_hw *hw = &adapter->hw; + struct iavf_hw *hw = &adapter->hw; if (!adapter->msix_entries) return; - wr32(hw, I40E_VFINT_DYN_CTL01, 0); + wr32(hw, IAVF_VFINT_DYN_CTL01, 0); - /* read flush */ - rd32(hw, I40E_VFGEN_RSTAT); + iavf_flush(hw); synchronize_irq(adapter->msix_entries[0].vector); } /** - * i40evf_misc_irq_enable - Enable default interrupt generation settings + * iavf_misc_irq_enable - Enable default interrupt generation settings * @adapter: board private structure **/ -static void i40evf_misc_irq_enable(struct i40evf_adapter *adapter) +static void iavf_misc_irq_enable(struct iavf_adapter *adapter) { - struct i40e_hw *hw = &adapter->hw; + struct iavf_hw *hw = &adapter->hw; - wr32(hw, I40E_VFINT_DYN_CTL01, I40E_VFINT_DYN_CTL01_INTENA_MASK | - I40E_VFINT_DYN_CTL01_ITR_INDX_MASK); - wr32(hw, I40E_VFINT_ICR0_ENA1, I40E_VFINT_ICR0_ENA1_ADMINQ_MASK); + wr32(hw, IAVF_VFINT_DYN_CTL01, IAVF_VFINT_DYN_CTL01_INTENA_MASK | + IAVF_VFINT_DYN_CTL01_ITR_INDX_MASK); + wr32(hw, IAVF_VFINT_ICR0_ENA1, IAVF_VFINT_ICR0_ENA1_ADMINQ_MASK); - /* read flush */ - rd32(hw, I40E_VFGEN_RSTAT); + iavf_flush(hw); } /** - * i40evf_irq_disable - Mask off interrupt generation on the NIC + * iavf_irq_disable - Mask off interrupt generation on the NIC * @adapter: board private structure **/ -static void i40evf_irq_disable(struct i40evf_adapter *adapter) +static void iavf_irq_disable(struct iavf_adapter *adapter) { int i; - struct i40e_hw *hw = &adapter->hw; + struct iavf_hw *hw = &adapter->hw; if (!adapter->msix_entries) return; for (i = 1; i < adapter->num_msix_vectors; i++) { - wr32(hw, I40E_VFINT_DYN_CTLN1(i - 1), 0); + wr32(hw, IAVF_VFINT_DYN_CTLN1(i - 1), 0); synchronize_irq(adapter->msix_entries[i].vector); } - /* read flush */ - rd32(hw, I40E_VFGEN_RSTAT); + iavf_flush(hw); } /** - * i40evf_irq_enable_queues - Enable interrupt for specified queues + * iavf_irq_enable_queues - Enable interrupt for specified queues * @adapter: board private structure * @mask: bitmap of queues to enable **/ -void i40evf_irq_enable_queues(struct i40evf_adapter *adapter, u32 mask) +void iavf_irq_enable_queues(struct iavf_adapter *adapter, u32 mask) { - struct i40e_hw *hw = &adapter->hw; + struct iavf_hw *hw = &adapter->hw; int i; for (i = 1; i < adapter->num_msix_vectors; i++) { if (mask & BIT(i - 1)) { - wr32(hw, I40E_VFINT_DYN_CTLN1(i - 1), - I40E_VFINT_DYN_CTLN1_INTENA_MASK | - I40E_VFINT_DYN_CTLN1_ITR_INDX_MASK); + wr32(hw, IAVF_VFINT_DYN_CTLN1(i - 1), + IAVF_VFINT_DYN_CTLN1_INTENA_MASK | + IAVF_VFINT_DYN_CTLN1_ITR_INDX_MASK); } } } /** - * i40evf_irq_enable - Enable default interrupt generation settings + * iavf_irq_enable - Enable default interrupt generation settings * @adapter: board private structure * @flush: boolean value whether to run rd32() **/ -void i40evf_irq_enable(struct i40evf_adapter *adapter, bool flush) +void iavf_irq_enable(struct iavf_adapter *adapter, bool flush) { - struct i40e_hw *hw = &adapter->hw; + struct iavf_hw *hw = &adapter->hw; - i40evf_misc_irq_enable(adapter); - i40evf_irq_enable_queues(adapter, ~0); + iavf_misc_irq_enable(adapter); + iavf_irq_enable_queues(adapter, ~0); if (flush) - rd32(hw, I40E_VFGEN_RSTAT); + iavf_flush(hw); } /** - * i40evf_msix_aq - Interrupt handler for vector 0 + * iavf_msix_aq - Interrupt handler for vector 0 * @irq: interrupt number * @data: pointer to netdev **/ -static irqreturn_t i40evf_msix_aq(int irq, void *data) +static irqreturn_t iavf_msix_aq(int irq, void *data) { struct net_device *netdev = data; - struct i40evf_adapter *adapter = netdev_priv(netdev); - struct i40e_hw *hw = &adapter->hw; + struct iavf_adapter *adapter = netdev_priv(netdev); + struct iavf_hw *hw = &adapter->hw; /* handle non-queue interrupts, these reads clear the registers */ - rd32(hw, I40E_VFINT_ICR01); - rd32(hw, I40E_VFINT_ICR0_ENA1); + rd32(hw, IAVF_VFINT_ICR01); + rd32(hw, IAVF_VFINT_ICR0_ENA1); /* schedule work on the private workqueue */ schedule_work(&adapter->adminq_task); @@ -296,13 +293,13 @@ static irqreturn_t i40evf_msix_aq(int irq, void *data) } /** - * i40evf_msix_clean_rings - MSIX mode Interrupt Handler + * iavf_msix_clean_rings - MSIX mode Interrupt Handler * @irq: interrupt number * @data: pointer to a q_vector **/ -static irqreturn_t i40evf_msix_clean_rings(int irq, void *data) +static irqreturn_t iavf_msix_clean_rings(int irq, void *data) { - struct i40e_q_vector *q_vector = data; + struct iavf_q_vector *q_vector = data; if (!q_vector->tx.ring && !q_vector->rx.ring) return IRQ_HANDLED; @@ -313,17 +310,17 @@ static irqreturn_t i40evf_msix_clean_rings(int irq, void *data) } /** - * i40evf_map_vector_to_rxq - associate irqs with rx queues + * iavf_map_vector_to_rxq - associate irqs with rx queues * @adapter: board private structure * @v_idx: interrupt number * @r_idx: queue number **/ static void -i40evf_map_vector_to_rxq(struct i40evf_adapter *adapter, int v_idx, int r_idx) +iavf_map_vector_to_rxq(struct iavf_adapter *adapter, int v_idx, int r_idx) { - struct i40e_q_vector *q_vector = &adapter->q_vectors[v_idx]; - struct i40e_ring *rx_ring = &adapter->rx_rings[r_idx]; - struct i40e_hw *hw = &adapter->hw; + struct iavf_q_vector *q_vector = &adapter->q_vectors[v_idx]; + struct iavf_ring *rx_ring = &adapter->rx_rings[r_idx]; + struct iavf_hw *hw = &adapter->hw; rx_ring->q_vector = q_vector; rx_ring->next = q_vector->rx.ring; @@ -333,23 +330,23 @@ i40evf_map_vector_to_rxq(struct i40evf_adapter *adapter, int v_idx, int r_idx) q_vector->rx.next_update = jiffies + 1; q_vector->rx.target_itr = ITR_TO_REG(rx_ring->itr_setting); q_vector->ring_mask |= BIT(r_idx); - wr32(hw, I40E_VFINT_ITRN1(I40E_RX_ITR, q_vector->reg_idx), + wr32(hw, IAVF_VFINT_ITRN1(IAVF_RX_ITR, q_vector->reg_idx), q_vector->rx.current_itr); q_vector->rx.current_itr = q_vector->rx.target_itr; } /** - * i40evf_map_vector_to_txq - associate irqs with tx queues + * iavf_map_vector_to_txq - associate irqs with tx queues * @adapter: board private structure * @v_idx: interrupt number * @t_idx: queue number **/ static void -i40evf_map_vector_to_txq(struct i40evf_adapter *adapter, int v_idx, int t_idx) +iavf_map_vector_to_txq(struct iavf_adapter *adapter, int v_idx, int t_idx) { - struct i40e_q_vector *q_vector = &adapter->q_vectors[v_idx]; - struct i40e_ring *tx_ring = &adapter->tx_rings[t_idx]; - struct i40e_hw *hw = &adapter->hw; + struct iavf_q_vector *q_vector = &adapter->q_vectors[v_idx]; + struct iavf_ring *tx_ring = &adapter->tx_rings[t_idx]; + struct iavf_hw *hw = &adapter->hw; tx_ring->q_vector = q_vector; tx_ring->next = q_vector->tx.ring; @@ -359,13 +356,13 @@ i40evf_map_vector_to_txq(struct i40evf_adapter *adapter, int v_idx, int t_idx) q_vector->tx.next_update = jiffies + 1; q_vector->tx.target_itr = ITR_TO_REG(tx_ring->itr_setting); q_vector->num_ringpairs++; - wr32(hw, I40E_VFINT_ITRN1(I40E_TX_ITR, q_vector->reg_idx), + wr32(hw, IAVF_VFINT_ITRN1(IAVF_TX_ITR, q_vector->reg_idx), q_vector->tx.target_itr); q_vector->tx.current_itr = q_vector->tx.target_itr; } /** - * i40evf_map_rings_to_vectors - Maps descriptor rings to vectors + * iavf_map_rings_to_vectors - Maps descriptor rings to vectors * @adapter: board private structure to initialize * * This function maps descriptor rings to the queue-specific vectors @@ -374,7 +371,7 @@ i40evf_map_vector_to_txq(struct i40evf_adapter *adapter, int v_idx, int t_idx) * group the rings as "efficiently" as possible. You would add new * mapping configurations in here. **/ -static void i40evf_map_rings_to_vectors(struct i40evf_adapter *adapter) +static void iavf_map_rings_to_vectors(struct iavf_adapter *adapter) { int rings_remaining = adapter->num_active_queues; int ridx = 0, vidx = 0; @@ -383,8 +380,8 @@ static void i40evf_map_rings_to_vectors(struct i40evf_adapter *adapter) q_vectors = adapter->num_msix_vectors - NONQ_VECS; for (; ridx < rings_remaining; ridx++) { - i40evf_map_vector_to_rxq(adapter, vidx, ridx); - i40evf_map_vector_to_txq(adapter, vidx, ridx); + iavf_map_vector_to_rxq(adapter, vidx, ridx); + iavf_map_vector_to_txq(adapter, vidx, ridx); /* In the case where we have more queues than vectors, continue * round-robin on vectors until all queues are mapped. @@ -393,61 +390,61 @@ static void i40evf_map_rings_to_vectors(struct i40evf_adapter *adapter) vidx = 0; } - adapter->aq_required |= I40EVF_FLAG_AQ_MAP_VECTORS; + adapter->aq_required |= IAVF_FLAG_AQ_MAP_VECTORS; } #ifdef CONFIG_NET_POLL_CONTROLLER /** - * i40evf_netpoll - A Polling 'interrupt' handler + * iavf_netpoll - A Polling 'interrupt' handler * @netdev: network interface device structure * * This is used by netconsole to send skbs without having to re-enable * interrupts. It's not called while the normal interrupt routine is executing. **/ -static void i40evf_netpoll(struct net_device *netdev) +static void iavf_netpoll(struct net_device *netdev) { - struct i40evf_adapter *adapter = netdev_priv(netdev); + struct iavf_adapter *adapter = netdev_priv(netdev); int q_vectors = adapter->num_msix_vectors - NONQ_VECS; int i; /* if interface is down do nothing */ - if (test_bit(__I40E_VSI_DOWN, adapter->vsi.state)) + if (test_bit(__IAVF_VSI_DOWN, adapter->vsi.state)) return; for (i = 0; i < q_vectors; i++) - i40evf_msix_clean_rings(0, &adapter->q_vectors[i]); + iavf_msix_clean_rings(0, &adapter->q_vectors[i]); } #endif /** - * i40evf_irq_affinity_notify - Callback for affinity changes + * iavf_irq_affinity_notify - Callback for affinity changes * @notify: context as to what irq was changed * @mask: the new affinity mask * * This is a callback function used by the irq_set_affinity_notifier function * so that we may register to receive changes to the irq affinity masks. **/ -static void i40evf_irq_affinity_notify(struct irq_affinity_notify *notify, - const cpumask_t *mask) +static void iavf_irq_affinity_notify(struct irq_affinity_notify *notify, + const cpumask_t *mask) { - struct i40e_q_vector *q_vector = - container_of(notify, struct i40e_q_vector, affinity_notify); + struct iavf_q_vector *q_vector = + container_of(notify, struct iavf_q_vector, affinity_notify); cpumask_copy(&q_vector->affinity_mask, mask); } /** - * i40evf_irq_affinity_release - Callback for affinity notifier release + * iavf_irq_affinity_release - Callback for affinity notifier release * @ref: internal core kernel usage * * This is a callback function used by the irq_set_affinity_notifier function * to inform the current notification subscriber that they will no longer * receive notifications. **/ -static void i40evf_irq_affinity_release(struct kref *ref) {} +static void iavf_irq_affinity_release(struct kref *ref) {} /** - * i40evf_request_traffic_irqs - Initialize MSI-X interrupts + * iavf_request_traffic_irqs - Initialize MSI-X interrupts * @adapter: board private structure * @basename: device basename * @@ -455,37 +452,38 @@ static void i40evf_irq_affinity_release(struct kref *ref) {} * interrupts from the kernel. **/ static int -i40evf_request_traffic_irqs(struct i40evf_adapter *adapter, char *basename) +iavf_request_traffic_irqs(struct iavf_adapter *adapter, char *basename) { unsigned int vector, q_vectors; unsigned int rx_int_idx = 0, tx_int_idx = 0; int irq_num, err; int cpu; - i40evf_irq_disable(adapter); + iavf_irq_disable(adapter); /* Decrement for Other and TCP Timer vectors */ q_vectors = adapter->num_msix_vectors - NONQ_VECS; for (vector = 0; vector < q_vectors; vector++) { - struct i40e_q_vector *q_vector = &adapter->q_vectors[vector]; + struct iavf_q_vector *q_vector = &adapter->q_vectors[vector]; + irq_num = adapter->msix_entries[vector + NONQ_VECS].vector; if (q_vector->tx.ring && q_vector->rx.ring) { snprintf(q_vector->name, sizeof(q_vector->name), - "i40evf-%s-TxRx-%d", basename, rx_int_idx++); + "iavf-%s-TxRx-%d", basename, rx_int_idx++); tx_int_idx++; } else if (q_vector->rx.ring) { snprintf(q_vector->name, sizeof(q_vector->name), - "i40evf-%s-rx-%d", basename, rx_int_idx++); + "iavf-%s-rx-%d", basename, rx_int_idx++); } else if (q_vector->tx.ring) { snprintf(q_vector->name, sizeof(q_vector->name), - "i40evf-%s-tx-%d", basename, tx_int_idx++); + "iavf-%s-tx-%d", basename, tx_int_idx++); } else { /* skip this unused q_vector */ continue; } err = request_irq(irq_num, - i40evf_msix_clean_rings, + iavf_msix_clean_rings, 0, q_vector->name, q_vector); @@ -495,9 +493,9 @@ i40evf_request_traffic_irqs(struct i40evf_adapter *adapter, char *basename) goto free_queue_irqs; } /* register for affinity change notifications */ - q_vector->affinity_notify.notify = i40evf_irq_affinity_notify; + q_vector->affinity_notify.notify = iavf_irq_affinity_notify; q_vector->affinity_notify.release = - i40evf_irq_affinity_release; + iavf_irq_affinity_release; irq_set_affinity_notifier(irq_num, &q_vector->affinity_notify); /* Spread the IRQ affinity hints across online CPUs. Note that * get_cpu_mask returns a mask with a permanent lifetime so @@ -521,23 +519,23 @@ free_queue_irqs: } /** - * i40evf_request_misc_irq - Initialize MSI-X interrupts + * iavf_request_misc_irq - Initialize MSI-X interrupts * @adapter: board private structure * * Allocates MSI-X vector 0 and requests interrupts from the kernel. This * vector is only for the admin queue, and stays active even when the netdev * is closed. **/ -static int i40evf_request_misc_irq(struct i40evf_adapter *adapter) +static int iavf_request_misc_irq(struct iavf_adapter *adapter) { struct net_device *netdev = adapter->netdev; int err; snprintf(adapter->misc_vector_name, - sizeof(adapter->misc_vector_name) - 1, "i40evf-%s:mbx", + sizeof(adapter->misc_vector_name) - 1, "iavf-%s:mbx", dev_name(&adapter->pdev->dev)); err = request_irq(adapter->msix_entries[0].vector, - &i40evf_msix_aq, 0, + &iavf_msix_aq, 0, adapter->misc_vector_name, netdev); if (err) { dev_err(&adapter->pdev->dev, @@ -549,12 +547,12 @@ static int i40evf_request_misc_irq(struct i40evf_adapter *adapter) } /** - * i40evf_free_traffic_irqs - Free MSI-X interrupts + * iavf_free_traffic_irqs - Free MSI-X interrupts * @adapter: board private structure * * Frees all MSI-X vectors other than 0. **/ -static void i40evf_free_traffic_irqs(struct i40evf_adapter *adapter) +static void iavf_free_traffic_irqs(struct iavf_adapter *adapter) { int vector, irq_num, q_vectors; @@ -572,12 +570,12 @@ static void i40evf_free_traffic_irqs(struct i40evf_adapter *adapter) } /** - * i40evf_free_misc_irq - Free MSI-X miscellaneous vector + * iavf_free_misc_irq - Free MSI-X miscellaneous vector * @adapter: board private structure * * Frees MSI-X vector 0. **/ -static void i40evf_free_misc_irq(struct i40evf_adapter *adapter) +static void iavf_free_misc_irq(struct iavf_adapter *adapter) { struct net_device *netdev = adapter->netdev; @@ -588,58 +586,58 @@ static void i40evf_free_misc_irq(struct i40evf_adapter *adapter) } /** - * i40evf_configure_tx - Configure Transmit Unit after Reset + * iavf_configure_tx - Configure Transmit Unit after Reset * @adapter: board private structure * * Configure the Tx unit of the MAC after a reset. **/ -static void i40evf_configure_tx(struct i40evf_adapter *adapter) +static void iavf_configure_tx(struct iavf_adapter *adapter) { - struct i40e_hw *hw = &adapter->hw; + struct iavf_hw *hw = &adapter->hw; int i; for (i = 0; i < adapter->num_active_queues; i++) - adapter->tx_rings[i].tail = hw->hw_addr + I40E_QTX_TAIL1(i); + adapter->tx_rings[i].tail = hw->hw_addr + IAVF_QTX_TAIL1(i); } /** - * i40evf_configure_rx - Configure Receive Unit after Reset + * iavf_configure_rx - Configure Receive Unit after Reset * @adapter: board private structure * * Configure the Rx unit of the MAC after a reset. **/ -static void i40evf_configure_rx(struct i40evf_adapter *adapter) +static void iavf_configure_rx(struct iavf_adapter *adapter) { - unsigned int rx_buf_len = I40E_RXBUFFER_2048; - struct i40e_hw *hw = &adapter->hw; + unsigned int rx_buf_len = IAVF_RXBUFFER_2048; + struct iavf_hw *hw = &adapter->hw; int i; /* Legacy Rx will always default to a 2048 buffer size. */ #if (PAGE_SIZE < 8192) - if (!(adapter->flags & I40EVF_FLAG_LEGACY_RX)) { + if (!(adapter->flags & IAVF_FLAG_LEGACY_RX)) { struct net_device *netdev = adapter->netdev; /* For jumbo frames on systems with 4K pages we have to use * an order 1 page, so we might as well increase the size * of our Rx buffer to make better use of the available space */ - rx_buf_len = I40E_RXBUFFER_3072; + rx_buf_len = IAVF_RXBUFFER_3072; /* We use a 1536 buffer size for configurations with * standard Ethernet mtu. On x86 this gives us enough room * for shared info and 192 bytes of padding. */ - if (!I40E_2K_TOO_SMALL_WITH_PADDING && + if (!IAVF_2K_TOO_SMALL_WITH_PADDING && (netdev->mtu <= ETH_DATA_LEN)) - rx_buf_len = I40E_RXBUFFER_1536 - NET_IP_ALIGN; + rx_buf_len = IAVF_RXBUFFER_1536 - NET_IP_ALIGN; } #endif for (i = 0; i < adapter->num_active_queues; i++) { - adapter->rx_rings[i].tail = hw->hw_addr + I40E_QRX_TAIL1(i); + adapter->rx_rings[i].tail = hw->hw_addr + IAVF_QRX_TAIL1(i); adapter->rx_rings[i].rx_buf_len = rx_buf_len; - if (adapter->flags & I40EVF_FLAG_LEGACY_RX) + if (adapter->flags & IAVF_FLAG_LEGACY_RX) clear_ring_build_skb_enabled(&adapter->rx_rings[i]); else set_ring_build_skb_enabled(&adapter->rx_rings[i]); @@ -647,7 +645,7 @@ static void i40evf_configure_rx(struct i40evf_adapter *adapter) } /** - * i40evf_find_vlan - Search filter list for specific vlan filter + * iavf_find_vlan - Search filter list for specific vlan filter * @adapter: board private structure * @vlan: vlan tag * @@ -655,9 +653,9 @@ static void i40evf_configure_rx(struct i40evf_adapter *adapter) * mac_vlan_list_lock. **/ static struct -i40evf_vlan_filter *i40evf_find_vlan(struct i40evf_adapter *adapter, u16 vlan) +iavf_vlan_filter *iavf_find_vlan(struct iavf_adapter *adapter, u16 vlan) { - struct i40evf_vlan_filter *f; + struct iavf_vlan_filter *f; list_for_each_entry(f, &adapter->vlan_filter_list, list) { if (vlan == f->vlan) @@ -667,20 +665,20 @@ i40evf_vlan_filter *i40evf_find_vlan(struct i40evf_adapter *adapter, u16 vlan) } /** - * i40evf_add_vlan - Add a vlan filter to the list + * iavf_add_vlan - Add a vlan filter to the list * @adapter: board private structure * @vlan: VLAN tag * * Returns ptr to the filter object or NULL when no memory available. **/ static struct -i40evf_vlan_filter *i40evf_add_vlan(struct i40evf_adapter *adapter, u16 vlan) +iavf_vlan_filter *iavf_add_vlan(struct iavf_adapter *adapter, u16 vlan) { - struct i40evf_vlan_filter *f = NULL; + struct iavf_vlan_filter *f = NULL; spin_lock_bh(&adapter->mac_vlan_list_lock); - f = i40evf_find_vlan(adapter, vlan); + f = iavf_find_vlan(adapter, vlan); if (!f) { f = kzalloc(sizeof(*f), GFP_KERNEL); if (!f) @@ -691,7 +689,7 @@ i40evf_vlan_filter *i40evf_add_vlan(struct i40evf_adapter *adapter, u16 vlan) INIT_LIST_HEAD(&f->list); list_add(&f->list, &adapter->vlan_filter_list); f->add = true; - adapter->aq_required |= I40EVF_FLAG_AQ_ADD_VLAN_FILTER; + adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; } clearout: @@ -700,63 +698,63 @@ clearout: } /** - * i40evf_del_vlan - Remove a vlan filter from the list + * iavf_del_vlan - Remove a vlan filter from the list * @adapter: board private structure * @vlan: VLAN tag **/ -static void i40evf_del_vlan(struct i40evf_adapter *adapter, u16 vlan) +static void iavf_del_vlan(struct iavf_adapter *adapter, u16 vlan) { - struct i40evf_vlan_filter *f; + struct iavf_vlan_filter *f; spin_lock_bh(&adapter->mac_vlan_list_lock); - f = i40evf_find_vlan(adapter, vlan); + f = iavf_find_vlan(adapter, vlan); if (f) { f->remove = true; - adapter->aq_required |= I40EVF_FLAG_AQ_DEL_VLAN_FILTER; + adapter->aq_required |= IAVF_FLAG_AQ_DEL_VLAN_FILTER; } spin_unlock_bh(&adapter->mac_vlan_list_lock); } /** - * i40evf_vlan_rx_add_vid - Add a VLAN filter to a device + * iavf_vlan_rx_add_vid - Add a VLAN filter to a device * @netdev: network device struct * @proto: unused protocol data * @vid: VLAN tag **/ -static int i40evf_vlan_rx_add_vid(struct net_device *netdev, - __always_unused __be16 proto, u16 vid) +static int iavf_vlan_rx_add_vid(struct net_device *netdev, + __always_unused __be16 proto, u16 vid) { - struct i40evf_adapter *adapter = netdev_priv(netdev); + struct iavf_adapter *adapter = netdev_priv(netdev); if (!VLAN_ALLOWED(adapter)) return -EIO; - if (i40evf_add_vlan(adapter, vid) == NULL) + if (iavf_add_vlan(adapter, vid) == NULL) return -ENOMEM; return 0; } /** - * i40evf_vlan_rx_kill_vid - Remove a VLAN filter from a device + * iavf_vlan_rx_kill_vid - Remove a VLAN filter from a device * @netdev: network device struct * @proto: unused protocol data * @vid: VLAN tag **/ -static int i40evf_vlan_rx_kill_vid(struct net_device *netdev, - __always_unused __be16 proto, u16 vid) +static int iavf_vlan_rx_kill_vid(struct net_device *netdev, + __always_unused __be16 proto, u16 vid) { - struct i40evf_adapter *adapter = netdev_priv(netdev); + struct iavf_adapter *adapter = netdev_priv(netdev); if (VLAN_ALLOWED(adapter)) { - i40evf_del_vlan(adapter, vid); + iavf_del_vlan(adapter, vid); return 0; } return -EIO; } /** - * i40evf_find_filter - Search filter list for specific mac filter + * iavf_find_filter - Search filter list for specific mac filter * @adapter: board private structure * @macaddr: the MAC address * @@ -764,10 +762,10 @@ static int i40evf_vlan_rx_kill_vid(struct net_device *netdev, * mac_vlan_list_lock. **/ static struct -i40evf_mac_filter *i40evf_find_filter(struct i40evf_adapter *adapter, - const u8 *macaddr) +iavf_mac_filter *iavf_find_filter(struct iavf_adapter *adapter, + const u8 *macaddr) { - struct i40evf_mac_filter *f; + struct iavf_mac_filter *f; if (!macaddr) return NULL; @@ -780,22 +778,22 @@ i40evf_mac_filter *i40evf_find_filter(struct i40evf_adapter *adapter, } /** - * i40e_add_filter - Add a mac filter to the filter list + * iavf_add_filter - Add a mac filter to the filter list * @adapter: board private structure * @macaddr: the MAC address * * Returns ptr to the filter object or NULL when no memory available. **/ static struct -i40evf_mac_filter *i40evf_add_filter(struct i40evf_adapter *adapter, - const u8 *macaddr) +iavf_mac_filter *iavf_add_filter(struct iavf_adapter *adapter, + const u8 *macaddr) { - struct i40evf_mac_filter *f; + struct iavf_mac_filter *f; if (!macaddr) return NULL; - f = i40evf_find_filter(adapter, macaddr); + f = iavf_find_filter(adapter, macaddr); if (!f) { f = kzalloc(sizeof(*f), GFP_ATOMIC); if (!f) @@ -805,7 +803,7 @@ i40evf_mac_filter *i40evf_add_filter(struct i40evf_adapter *adapter, list_add_tail(&f->list, &adapter->mac_filter_list); f->add = true; - adapter->aq_required |= I40EVF_FLAG_AQ_ADD_MAC_FILTER; + adapter->aq_required |= IAVF_FLAG_AQ_ADD_MAC_FILTER; } else { f->remove = false; } @@ -814,17 +812,17 @@ i40evf_mac_filter *i40evf_add_filter(struct i40evf_adapter *adapter, } /** - * i40evf_set_mac - NDO callback to set port mac address + * iavf_set_mac - NDO callback to set port mac address * @netdev: network interface device structure * @p: pointer to an address structure * * Returns 0 on success, negative on failure **/ -static int i40evf_set_mac(struct net_device *netdev, void *p) +static int iavf_set_mac(struct net_device *netdev, void *p) { - struct i40evf_adapter *adapter = netdev_priv(netdev); - struct i40e_hw *hw = &adapter->hw; - struct i40evf_mac_filter *f; + struct iavf_adapter *adapter = netdev_priv(netdev); + struct iavf_hw *hw = &adapter->hw; + struct iavf_mac_filter *f; struct sockaddr *addr = p; if (!is_valid_ether_addr(addr->sa_data)) @@ -833,18 +831,18 @@ static int i40evf_set_mac(struct net_device *netdev, void *p) if (ether_addr_equal(netdev->dev_addr, addr->sa_data)) return 0; - if (adapter->flags & I40EVF_FLAG_ADDR_SET_BY_PF) + if (adapter->flags & IAVF_FLAG_ADDR_SET_BY_PF) return -EPERM; spin_lock_bh(&adapter->mac_vlan_list_lock); - f = i40evf_find_filter(adapter, hw->mac.addr); + f = iavf_find_filter(adapter, hw->mac.addr); if (f) { f->remove = true; - adapter->aq_required |= I40EVF_FLAG_AQ_DEL_MAC_FILTER; + adapter->aq_required |= IAVF_FLAG_AQ_DEL_MAC_FILTER; } - f = i40evf_add_filter(adapter, addr->sa_data); + f = iavf_add_filter(adapter, addr->sa_data); spin_unlock_bh(&adapter->mac_vlan_list_lock); @@ -857,35 +855,35 @@ static int i40evf_set_mac(struct net_device *netdev, void *p) } /** - * i40evf_addr_sync - Callback for dev_(mc|uc)_sync to add address + * iavf_addr_sync - Callback for dev_(mc|uc)_sync to add address * @netdev: the netdevice * @addr: address to add * * Called by __dev_(mc|uc)_sync when an address needs to be added. We call * __dev_(uc|mc)_sync from .set_rx_mode and guarantee to hold the hash lock. */ -static int i40evf_addr_sync(struct net_device *netdev, const u8 *addr) +static int iavf_addr_sync(struct net_device *netdev, const u8 *addr) { - struct i40evf_adapter *adapter = netdev_priv(netdev); + struct iavf_adapter *adapter = netdev_priv(netdev); - if (i40evf_add_filter(adapter, addr)) + if (iavf_add_filter(adapter, addr)) return 0; else return -ENOMEM; } /** - * i40evf_addr_unsync - Callback for dev_(mc|uc)_sync to remove address + * iavf_addr_unsync - Callback for dev_(mc|uc)_sync to remove address * @netdev: the netdevice * @addr: address to add * * Called by __dev_(mc|uc)_sync when an address needs to be removed. We call * __dev_(uc|mc)_sync from .set_rx_mode and guarantee to hold the hash lock. */ -static int i40evf_addr_unsync(struct net_device *netdev, const u8 *addr) +static int iavf_addr_unsync(struct net_device *netdev, const u8 *addr) { - struct i40evf_adapter *adapter = netdev_priv(netdev); - struct i40evf_mac_filter *f; + struct iavf_adapter *adapter = netdev_priv(netdev); + struct iavf_mac_filter *f; /* Under some circumstances, we might receive a request to delete * our own device address from our uc list. Because we store the @@ -895,50 +893,50 @@ static int i40evf_addr_unsync(struct net_device *netdev, const u8 *addr) if (ether_addr_equal(addr, netdev->dev_addr)) return 0; - f = i40evf_find_filter(adapter, addr); + f = iavf_find_filter(adapter, addr); if (f) { f->remove = true; - adapter->aq_required |= I40EVF_FLAG_AQ_DEL_MAC_FILTER; + adapter->aq_required |= IAVF_FLAG_AQ_DEL_MAC_FILTER; } return 0; } /** - * i40evf_set_rx_mode - NDO callback to set the netdev filters + * iavf_set_rx_mode - NDO callback to set the netdev filters * @netdev: network interface device structure **/ -static void i40evf_set_rx_mode(struct net_device *netdev) +static void iavf_set_rx_mode(struct net_device *netdev) { - struct i40evf_adapter *adapter = netdev_priv(netdev); + struct iavf_adapter *adapter = netdev_priv(netdev); spin_lock_bh(&adapter->mac_vlan_list_lock); - __dev_uc_sync(netdev, i40evf_addr_sync, i40evf_addr_unsync); - __dev_mc_sync(netdev, i40evf_addr_sync, i40evf_addr_unsync); + __dev_uc_sync(netdev, iavf_addr_sync, iavf_addr_unsync); + __dev_mc_sync(netdev, iavf_addr_sync, iavf_addr_unsync); spin_unlock_bh(&adapter->mac_vlan_list_lock); if (netdev->flags & IFF_PROMISC && - !(adapter->flags & I40EVF_FLAG_PROMISC_ON)) - adapter->aq_required |= I40EVF_FLAG_AQ_REQUEST_PROMISC; + !(adapter->flags & IAVF_FLAG_PROMISC_ON)) + adapter->aq_required |= IAVF_FLAG_AQ_REQUEST_PROMISC; else if (!(netdev->flags & IFF_PROMISC) && - adapter->flags & I40EVF_FLAG_PROMISC_ON) - adapter->aq_required |= I40EVF_FLAG_AQ_RELEASE_PROMISC; + adapter->flags & IAVF_FLAG_PROMISC_ON) + adapter->aq_required |= IAVF_FLAG_AQ_RELEASE_PROMISC; if (netdev->flags & IFF_ALLMULTI && - !(adapter->flags & I40EVF_FLAG_ALLMULTI_ON)) - adapter->aq_required |= I40EVF_FLAG_AQ_REQUEST_ALLMULTI; + !(adapter->flags & IAVF_FLAG_ALLMULTI_ON)) + adapter->aq_required |= IAVF_FLAG_AQ_REQUEST_ALLMULTI; else if (!(netdev->flags & IFF_ALLMULTI) && - adapter->flags & I40EVF_FLAG_ALLMULTI_ON) - adapter->aq_required |= I40EVF_FLAG_AQ_RELEASE_ALLMULTI; + adapter->flags & IAVF_FLAG_ALLMULTI_ON) + adapter->aq_required |= IAVF_FLAG_AQ_RELEASE_ALLMULTI; } /** - * i40evf_napi_enable_all - enable NAPI on all queue vectors + * iavf_napi_enable_all - enable NAPI on all queue vectors * @adapter: board private structure **/ -static void i40evf_napi_enable_all(struct i40evf_adapter *adapter) +static void iavf_napi_enable_all(struct iavf_adapter *adapter) { int q_idx; - struct i40e_q_vector *q_vector; + struct iavf_q_vector *q_vector; int q_vectors = adapter->num_msix_vectors - NONQ_VECS; for (q_idx = 0; q_idx < q_vectors; q_idx++) { @@ -951,13 +949,13 @@ static void i40evf_napi_enable_all(struct i40evf_adapter *adapter) } /** - * i40evf_napi_disable_all - disable NAPI on all queue vectors + * iavf_napi_disable_all - disable NAPI on all queue vectors * @adapter: board private structure **/ -static void i40evf_napi_disable_all(struct i40evf_adapter *adapter) +static void iavf_napi_disable_all(struct iavf_adapter *adapter) { int q_idx; - struct i40e_q_vector *q_vector; + struct iavf_q_vector *q_vector; int q_vectors = adapter->num_msix_vectors - NONQ_VECS; for (q_idx = 0; q_idx < q_vectors; q_idx++) { @@ -967,67 +965,67 @@ static void i40evf_napi_disable_all(struct i40evf_adapter *adapter) } /** - * i40evf_configure - set up transmit and receive data structures + * iavf_configure - set up transmit and receive data structures * @adapter: board private structure **/ -static void i40evf_configure(struct i40evf_adapter *adapter) +static void iavf_configure(struct iavf_adapter *adapter) { struct net_device *netdev = adapter->netdev; int i; - i40evf_set_rx_mode(netdev); + iavf_set_rx_mode(netdev); - i40evf_configure_tx(adapter); - i40evf_configure_rx(adapter); - adapter->aq_required |= I40EVF_FLAG_AQ_CONFIGURE_QUEUES; + iavf_configure_tx(adapter); + iavf_configure_rx(adapter); + adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_QUEUES; for (i = 0; i < adapter->num_active_queues; i++) { - struct i40e_ring *ring = &adapter->rx_rings[i]; + struct iavf_ring *ring = &adapter->rx_rings[i]; - i40evf_alloc_rx_buffers(ring, I40E_DESC_UNUSED(ring)); + iavf_alloc_rx_buffers(ring, IAVF_DESC_UNUSED(ring)); } } /** - * i40evf_up_complete - Finish the last steps of bringing up a connection + * iavf_up_complete - Finish the last steps of bringing up a connection * @adapter: board private structure * - * Expects to be called while holding the __I40EVF_IN_CRITICAL_TASK bit lock. + * Expects to be called while holding the __IAVF_IN_CRITICAL_TASK bit lock. **/ -static void i40evf_up_complete(struct i40evf_adapter *adapter) +static void iavf_up_complete(struct iavf_adapter *adapter) { - adapter->state = __I40EVF_RUNNING; - clear_bit(__I40E_VSI_DOWN, adapter->vsi.state); + adapter->state = __IAVF_RUNNING; + clear_bit(__IAVF_VSI_DOWN, adapter->vsi.state); - i40evf_napi_enable_all(adapter); + iavf_napi_enable_all(adapter); - adapter->aq_required |= I40EVF_FLAG_AQ_ENABLE_QUEUES; + adapter->aq_required |= IAVF_FLAG_AQ_ENABLE_QUEUES; if (CLIENT_ENABLED(adapter)) - adapter->flags |= I40EVF_FLAG_CLIENT_NEEDS_OPEN; + adapter->flags |= IAVF_FLAG_CLIENT_NEEDS_OPEN; mod_timer_pending(&adapter->watchdog_timer, jiffies + 1); } /** - * i40e_down - Shutdown the connection processing + * iavf_down - Shutdown the connection processing * @adapter: board private structure * - * Expects to be called while holding the __I40EVF_IN_CRITICAL_TASK bit lock. + * Expects to be called while holding the __IAVF_IN_CRITICAL_TASK bit lock. **/ -void i40evf_down(struct i40evf_adapter *adapter) +void iavf_down(struct iavf_adapter *adapter) { struct net_device *netdev = adapter->netdev; - struct i40evf_vlan_filter *vlf; - struct i40evf_mac_filter *f; - struct i40evf_cloud_filter *cf; + struct iavf_vlan_filter *vlf; + struct iavf_mac_filter *f; + struct iavf_cloud_filter *cf; - if (adapter->state <= __I40EVF_DOWN_PENDING) + if (adapter->state <= __IAVF_DOWN_PENDING) return; netif_carrier_off(netdev); netif_tx_disable(netdev); adapter->link_up = false; - i40evf_napi_disable_all(adapter); - i40evf_irq_disable(adapter); + iavf_napi_disable_all(adapter); + iavf_irq_disable(adapter); spin_lock_bh(&adapter->mac_vlan_list_lock); @@ -1054,25 +1052,25 @@ void i40evf_down(struct i40evf_adapter *adapter) } spin_unlock_bh(&adapter->cloud_filter_list_lock); - if (!(adapter->flags & I40EVF_FLAG_PF_COMMS_FAILED) && - adapter->state != __I40EVF_RESETTING) { + if (!(adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) && + adapter->state != __IAVF_RESETTING) { /* cancel any current operation */ adapter->current_op = VIRTCHNL_OP_UNKNOWN; /* Schedule operations to close down the HW. Don't wait * here for this to complete. The watchdog is still running * and it will take care of this. */ - adapter->aq_required = I40EVF_FLAG_AQ_DEL_MAC_FILTER; - adapter->aq_required |= I40EVF_FLAG_AQ_DEL_VLAN_FILTER; - adapter->aq_required |= I40EVF_FLAG_AQ_DEL_CLOUD_FILTER; - adapter->aq_required |= I40EVF_FLAG_AQ_DISABLE_QUEUES; + adapter->aq_required = IAVF_FLAG_AQ_DEL_MAC_FILTER; + adapter->aq_required |= IAVF_FLAG_AQ_DEL_VLAN_FILTER; + adapter->aq_required |= IAVF_FLAG_AQ_DEL_CLOUD_FILTER; + adapter->aq_required |= IAVF_FLAG_AQ_DISABLE_QUEUES; } mod_timer_pending(&adapter->watchdog_timer, jiffies + 1); } /** - * i40evf_acquire_msix_vectors - Setup the MSIX capability + * iavf_acquire_msix_vectors - Setup the MSIX capability * @adapter: board private structure * @vectors: number of vectors to request * @@ -1081,7 +1079,7 @@ void i40evf_down(struct i40evf_adapter *adapter) * Returns 0 on success, negative on failure **/ static int -i40evf_acquire_msix_vectors(struct i40evf_adapter *adapter, int vectors) +iavf_acquire_msix_vectors(struct iavf_adapter *adapter, int vectors) { int err, vector_threshold; @@ -1115,12 +1113,12 @@ i40evf_acquire_msix_vectors(struct i40evf_adapter *adapter, int vectors) } /** - * i40evf_free_queues - Free memory for all rings + * iavf_free_queues - Free memory for all rings * @adapter: board private structure to initialize * * Free all of the memory associated with queue pairs. **/ -static void i40evf_free_queues(struct i40evf_adapter *adapter) +static void iavf_free_queues(struct iavf_adapter *adapter) { if (!adapter->vsi_res) return; @@ -1132,14 +1130,14 @@ static void i40evf_free_queues(struct i40evf_adapter *adapter) } /** - * i40evf_alloc_queues - Allocate memory for all rings + * iavf_alloc_queues - Allocate memory for all rings * @adapter: board private structure to initialize * * We allocate one ring per queue at run-time since we don't know the * number of queues at compile-time. The polling_netdev array is * intended for Multiqueue, but should work fine with a single queue. **/ -static int i40evf_alloc_queues(struct i40evf_adapter *adapter) +static int iavf_alloc_queues(struct iavf_adapter *adapter) { int i, num_active_queues; @@ -1160,17 +1158,17 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter) adapter->tx_rings = kcalloc(num_active_queues, - sizeof(struct i40e_ring), GFP_KERNEL); + sizeof(struct iavf_ring), GFP_KERNEL); if (!adapter->tx_rings) goto err_out; adapter->rx_rings = kcalloc(num_active_queues, - sizeof(struct i40e_ring), GFP_KERNEL); + sizeof(struct iavf_ring), GFP_KERNEL); if (!adapter->rx_rings) goto err_out; for (i = 0; i < num_active_queues; i++) { - struct i40e_ring *tx_ring; - struct i40e_ring *rx_ring; + struct iavf_ring *tx_ring; + struct iavf_ring *rx_ring; tx_ring = &adapter->tx_rings[i]; @@ -1178,16 +1176,16 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter) tx_ring->netdev = adapter->netdev; tx_ring->dev = &adapter->pdev->dev; tx_ring->count = adapter->tx_desc_count; - tx_ring->itr_setting = I40E_ITR_TX_DEF; - if (adapter->flags & I40EVF_FLAG_WB_ON_ITR_CAPABLE) - tx_ring->flags |= I40E_TXR_FLAGS_WB_ON_ITR; + tx_ring->itr_setting = IAVF_ITR_TX_DEF; + if (adapter->flags & IAVF_FLAG_WB_ON_ITR_CAPABLE) + tx_ring->flags |= IAVF_TXR_FLAGS_WB_ON_ITR; rx_ring = &adapter->rx_rings[i]; rx_ring->queue_index = i; rx_ring->netdev = adapter->netdev; rx_ring->dev = &adapter->pdev->dev; rx_ring->count = adapter->rx_desc_count; - rx_ring->itr_setting = I40E_ITR_RX_DEF; + rx_ring->itr_setting = IAVF_ITR_RX_DEF; } adapter->num_active_queues = num_active_queues; @@ -1195,18 +1193,18 @@ static int i40evf_alloc_queues(struct i40evf_adapter *adapter) return 0; err_out: - i40evf_free_queues(adapter); + iavf_free_queues(adapter); return -ENOMEM; } /** - * i40evf_set_interrupt_capability - set MSI-X or FAIL if not supported + * iavf_set_interrupt_capability - set MSI-X or FAIL if not supported * @adapter: board private structure to initialize * * Attempt to configure the interrupts using the best available * capabilities of the hardware and the kernel. **/ -static int i40evf_set_interrupt_capability(struct i40evf_adapter *adapter) +static int iavf_set_interrupt_capability(struct iavf_adapter *adapter) { int vector, v_budget; int pairs = 0; @@ -1236,7 +1234,7 @@ static int i40evf_set_interrupt_capability(struct i40evf_adapter *adapter) for (vector = 0; vector < v_budget; vector++) adapter->msix_entries[vector].entry = vector; - err = i40evf_acquire_msix_vectors(adapter, v_budget); + err = iavf_acquire_msix_vectors(adapter, v_budget); out: netif_set_real_num_rx_queues(adapter->netdev, pairs); @@ -1245,16 +1243,16 @@ out: } /** - * i40e_config_rss_aq - Configure RSS keys and lut by using AQ commands + * iavf_config_rss_aq - Configure RSS keys and lut by using AQ commands * @adapter: board private structure * * Return 0 on success, negative on failure **/ -static int i40evf_config_rss_aq(struct i40evf_adapter *adapter) +static int iavf_config_rss_aq(struct iavf_adapter *adapter) { struct i40e_aqc_get_set_rss_key_data *rss_key = (struct i40e_aqc_get_set_rss_key_data *)adapter->rss_key; - struct i40e_hw *hw = &adapter->hw; + struct iavf_hw *hw = &adapter->hw; int ret = 0; if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { @@ -1264,21 +1262,21 @@ static int i40evf_config_rss_aq(struct i40evf_adapter *adapter) return -EBUSY; } - ret = i40evf_aq_set_rss_key(hw, adapter->vsi.id, rss_key); + ret = iavf_aq_set_rss_key(hw, adapter->vsi.id, rss_key); if (ret) { dev_err(&adapter->pdev->dev, "Cannot set RSS key, err %s aq_err %s\n", - i40evf_stat_str(hw, ret), - i40evf_aq_str(hw, hw->aq.asq_last_status)); + iavf_stat_str(hw, ret), + iavf_aq_str(hw, hw->aq.asq_last_status)); return ret; } - ret = i40evf_aq_set_rss_lut(hw, adapter->vsi.id, false, - adapter->rss_lut, adapter->rss_lut_size); + ret = iavf_aq_set_rss_lut(hw, adapter->vsi.id, false, + adapter->rss_lut, adapter->rss_lut_size); if (ret) { dev_err(&adapter->pdev->dev, "Cannot set RSS lut, err %s aq_err %s\n", - i40evf_stat_str(hw, ret), - i40evf_aq_str(hw, hw->aq.asq_last_status)); + iavf_stat_str(hw, ret), + iavf_aq_str(hw, hw->aq.asq_last_status)); } return ret; @@ -1286,55 +1284,55 @@ static int i40evf_config_rss_aq(struct i40evf_adapter *adapter) } /** - * i40evf_config_rss_reg - Configure RSS keys and lut by writing registers + * iavf_config_rss_reg - Configure RSS keys and lut by writing registers * @adapter: board private structure * * Returns 0 on success, negative on failure **/ -static int i40evf_config_rss_reg(struct i40evf_adapter *adapter) +static int iavf_config_rss_reg(struct iavf_adapter *adapter) { - struct i40e_hw *hw = &adapter->hw; + struct iavf_hw *hw = &adapter->hw; u32 *dw; u16 i; dw = (u32 *)adapter->rss_key; for (i = 0; i <= adapter->rss_key_size / 4; i++) - wr32(hw, I40E_VFQF_HKEY(i), dw[i]); + wr32(hw, IAVF_VFQF_HKEY(i), dw[i]); dw = (u32 *)adapter->rss_lut; for (i = 0; i <= adapter->rss_lut_size / 4; i++) - wr32(hw, I40E_VFQF_HLUT(i), dw[i]); + wr32(hw, IAVF_VFQF_HLUT(i), dw[i]); - i40e_flush(hw); + iavf_flush(hw); return 0; } /** - * i40evf_config_rss - Configure RSS keys and lut + * iavf_config_rss - Configure RSS keys and lut * @adapter: board private structure * * Returns 0 on success, negative on failure **/ -int i40evf_config_rss(struct i40evf_adapter *adapter) +int iavf_config_rss(struct iavf_adapter *adapter) { if (RSS_PF(adapter)) { - adapter->aq_required |= I40EVF_FLAG_AQ_SET_RSS_LUT | - I40EVF_FLAG_AQ_SET_RSS_KEY; + adapter->aq_required |= IAVF_FLAG_AQ_SET_RSS_LUT | + IAVF_FLAG_AQ_SET_RSS_KEY; return 0; } else if (RSS_AQ(adapter)) { - return i40evf_config_rss_aq(adapter); + return iavf_config_rss_aq(adapter); } else { - return i40evf_config_rss_reg(adapter); + return iavf_config_rss_reg(adapter); } } /** - * i40evf_fill_rss_lut - Fill the lut with default values + * iavf_fill_rss_lut - Fill the lut with default values * @adapter: board private structure **/ -static void i40evf_fill_rss_lut(struct i40evf_adapter *adapter) +static void iavf_fill_rss_lut(struct iavf_adapter *adapter) { u16 i; @@ -1343,47 +1341,46 @@ static void i40evf_fill_rss_lut(struct i40evf_adapter *adapter) } /** - * i40evf_init_rss - Prepare for RSS + * iavf_init_rss - Prepare for RSS * @adapter: board private structure * * Return 0 on success, negative on failure **/ -static int i40evf_init_rss(struct i40evf_adapter *adapter) +static int iavf_init_rss(struct iavf_adapter *adapter) { - struct i40e_hw *hw = &adapter->hw; + struct iavf_hw *hw = &adapter->hw; int ret; if (!RSS_PF(adapter)) { /* Enable PCTYPES for RSS, TCP/UDP with IPv4/IPv6 */ if (adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2) - adapter->hena = I40E_DEFAULT_RSS_HENA_EXPANDED; + adapter->hena = IAVF_DEFAULT_RSS_HENA_EXPANDED; else - adapter->hena = I40E_DEFAULT_RSS_HENA; + adapter->hena = IAVF_DEFAULT_RSS_HENA; - wr32(hw, I40E_VFQF_HENA(0), (u32)adapter->hena); - wr32(hw, I40E_VFQF_HENA(1), (u32)(adapter->hena >> 32)); + wr32(hw, IAVF_VFQF_HENA(0), (u32)adapter->hena); + wr32(hw, IAVF_VFQF_HENA(1), (u32)(adapter->hena >> 32)); } - i40evf_fill_rss_lut(adapter); - + iavf_fill_rss_lut(adapter); netdev_rss_key_fill((void *)adapter->rss_key, adapter->rss_key_size); - ret = i40evf_config_rss(adapter); + ret = iavf_config_rss(adapter); return ret; } /** - * i40evf_alloc_q_vectors - Allocate memory for interrupt vectors + * iavf_alloc_q_vectors - Allocate memory for interrupt vectors * @adapter: board private structure to initialize * * We allocate one q_vector per queue interrupt. If allocation fails we * return -ENOMEM. **/ -static int i40evf_alloc_q_vectors(struct i40evf_adapter *adapter) +static int iavf_alloc_q_vectors(struct iavf_adapter *adapter) { int q_idx = 0, num_q_vectors; - struct i40e_q_vector *q_vector; + struct iavf_q_vector *q_vector; num_q_vectors = adapter->num_msix_vectors - NONQ_VECS; adapter->q_vectors = kcalloc(num_q_vectors, sizeof(*q_vector), @@ -1399,21 +1396,21 @@ static int i40evf_alloc_q_vectors(struct i40evf_adapter *adapter) q_vector->reg_idx = q_idx; cpumask_copy(&q_vector->affinity_mask, cpu_possible_mask); netif_napi_add(adapter->netdev, &q_vector->napi, - i40evf_napi_poll, NAPI_POLL_WEIGHT); + iavf_napi_poll, NAPI_POLL_WEIGHT); } return 0; } /** - * i40evf_free_q_vectors - Free memory allocated for interrupt vectors + * iavf_free_q_vectors - Free memory allocated for interrupt vectors * @adapter: board private structure to initialize * * This function frees the memory allocated to the q_vectors. In addition if * NAPI is enabled it will delete any references to the NAPI struct prior * to freeing the q_vector. **/ -static void i40evf_free_q_vectors(struct i40evf_adapter *adapter) +static void iavf_free_q_vectors(struct iavf_adapter *adapter) { int q_idx, num_q_vectors; int napi_vectors; @@ -1425,7 +1422,8 @@ static void i40evf_free_q_vectors(struct i40evf_adapter *adapter) napi_vectors = adapter->num_active_queues; for (q_idx = 0; q_idx < num_q_vectors; q_idx++) { - struct i40e_q_vector *q_vector = &adapter->q_vectors[q_idx]; + struct iavf_q_vector *q_vector = &adapter->q_vectors[q_idx]; + if (q_idx < napi_vectors) netif_napi_del(&q_vector->napi); } @@ -1434,11 +1432,11 @@ static void i40evf_free_q_vectors(struct i40evf_adapter *adapter) } /** - * i40evf_reset_interrupt_capability - Reset MSIX setup + * iavf_reset_interrupt_capability - Reset MSIX setup * @adapter: board private structure * **/ -void i40evf_reset_interrupt_capability(struct i40evf_adapter *adapter) +void iavf_reset_interrupt_capability(struct iavf_adapter *adapter) { if (!adapter->msix_entries) return; @@ -1449,15 +1447,15 @@ void i40evf_reset_interrupt_capability(struct i40evf_adapter *adapter) } /** - * i40evf_init_interrupt_scheme - Determine if MSIX is supported and init + * iavf_init_interrupt_scheme - Determine if MSIX is supported and init * @adapter: board private structure to initialize * **/ -int i40evf_init_interrupt_scheme(struct i40evf_adapter *adapter) +int iavf_init_interrupt_scheme(struct iavf_adapter *adapter) { int err; - err = i40evf_alloc_queues(adapter); + err = iavf_alloc_queues(adapter); if (err) { dev_err(&adapter->pdev->dev, "Unable to allocate memory for queues\n"); @@ -1465,7 +1463,7 @@ int i40evf_init_interrupt_scheme(struct i40evf_adapter *adapter) } rtnl_lock(); - err = i40evf_set_interrupt_capability(adapter); + err = iavf_set_interrupt_capability(adapter); rtnl_unlock(); if (err) { dev_err(&adapter->pdev->dev, @@ -1473,7 +1471,7 @@ int i40evf_init_interrupt_scheme(struct i40evf_adapter *adapter) goto err_set_interrupt; } - err = i40evf_alloc_q_vectors(adapter); + err = iavf_alloc_q_vectors(adapter); if (err) { dev_err(&adapter->pdev->dev, "Unable to allocate memory for queue vectors\n"); @@ -1496,18 +1494,18 @@ int i40evf_init_interrupt_scheme(struct i40evf_adapter *adapter) return 0; err_alloc_q_vectors: - i40evf_reset_interrupt_capability(adapter); + iavf_reset_interrupt_capability(adapter); err_set_interrupt: - i40evf_free_queues(adapter); + iavf_free_queues(adapter); err_alloc_queues: return err; } /** - * i40evf_free_rss - Free memory used by RSS structs + * iavf_free_rss - Free memory used by RSS structs * @adapter: board private structure **/ -static void i40evf_free_rss(struct i40evf_adapter *adapter) +static void iavf_free_rss(struct iavf_adapter *adapter) { kfree(adapter->rss_key); adapter->rss_key = NULL; @@ -1517,52 +1515,52 @@ static void i40evf_free_rss(struct i40evf_adapter *adapter) } /** - * i40evf_reinit_interrupt_scheme - Reallocate queues and vectors + * iavf_reinit_interrupt_scheme - Reallocate queues and vectors * @adapter: board private structure * * Returns 0 on success, negative on failure **/ -static int i40evf_reinit_interrupt_scheme(struct i40evf_adapter *adapter) +static int iavf_reinit_interrupt_scheme(struct iavf_adapter *adapter) { struct net_device *netdev = adapter->netdev; int err; if (netif_running(netdev)) - i40evf_free_traffic_irqs(adapter); - i40evf_free_misc_irq(adapter); - i40evf_reset_interrupt_capability(adapter); - i40evf_free_q_vectors(adapter); - i40evf_free_queues(adapter); + iavf_free_traffic_irqs(adapter); + iavf_free_misc_irq(adapter); + iavf_reset_interrupt_capability(adapter); + iavf_free_q_vectors(adapter); + iavf_free_queues(adapter); - err = i40evf_init_interrupt_scheme(adapter); + err = iavf_init_interrupt_scheme(adapter); if (err) goto err; netif_tx_stop_all_queues(netdev); - err = i40evf_request_misc_irq(adapter); + err = iavf_request_misc_irq(adapter); if (err) goto err; - set_bit(__I40E_VSI_DOWN, adapter->vsi.state); + set_bit(__IAVF_VSI_DOWN, adapter->vsi.state); - i40evf_map_rings_to_vectors(adapter); + iavf_map_rings_to_vectors(adapter); if (RSS_AQ(adapter)) - adapter->aq_required |= I40EVF_FLAG_AQ_CONFIGURE_RSS; + adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_RSS; else - err = i40evf_init_rss(adapter); + err = iavf_init_rss(adapter); err: return err; } /** - * i40evf_watchdog_timer - Periodic call-back timer + * iavf_watchdog_timer - Periodic call-back timer * @data: pointer to adapter disguised as unsigned long **/ -static void i40evf_watchdog_timer(struct timer_list *t) +static void iavf_watchdog_timer(struct timer_list *t) { - struct i40evf_adapter *adapter = from_timer(adapter, t, + struct iavf_adapter *adapter = from_timer(adapter, t, watchdog_timer); schedule_work(&adapter->watchdog_task); @@ -1570,31 +1568,31 @@ static void i40evf_watchdog_timer(struct timer_list *t) } /** - * i40evf_watchdog_task - Periodic call-back task + * iavf_watchdog_task - Periodic call-back task * @work: pointer to work_struct **/ -static void i40evf_watchdog_task(struct work_struct *work) +static void iavf_watchdog_task(struct work_struct *work) { - struct i40evf_adapter *adapter = container_of(work, - struct i40evf_adapter, + struct iavf_adapter *adapter = container_of(work, + struct iavf_adapter, watchdog_task); - struct i40e_hw *hw = &adapter->hw; + struct iavf_hw *hw = &adapter->hw; u32 reg_val; - if (test_and_set_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section)) + if (test_and_set_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section)) goto restart_watchdog; - if (adapter->flags & I40EVF_FLAG_PF_COMMS_FAILED) { - reg_val = rd32(hw, I40E_VFGEN_RSTAT) & - I40E_VFGEN_RSTAT_VFR_STATE_MASK; + if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) { + reg_val = rd32(hw, IAVF_VFGEN_RSTAT) & + IAVF_VFGEN_RSTAT_VFR_STATE_MASK; if ((reg_val == VIRTCHNL_VFR_VFACTIVE) || (reg_val == VIRTCHNL_VFR_COMPLETED)) { /* A chance for redemption! */ dev_err(&adapter->pdev->dev, "Hardware came out of reset. Attempting reinit.\n"); - adapter->state = __I40EVF_STARTUP; - adapter->flags &= ~I40EVF_FLAG_PF_COMMS_FAILED; + adapter->state = __IAVF_STARTUP; + adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED; schedule_delayed_work(&adapter->init_task, 10); - clear_bit(__I40EVF_IN_CRITICAL_TASK, + clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); /* Don't reschedule the watchdog, since we've restarted * the init task. When init_task contacts the PF and @@ -1608,15 +1606,15 @@ static void i40evf_watchdog_task(struct work_struct *work) goto watchdog_done; } - if ((adapter->state < __I40EVF_DOWN) || - (adapter->flags & I40EVF_FLAG_RESET_PENDING)) + if ((adapter->state < __IAVF_DOWN) || + (adapter->flags & IAVF_FLAG_RESET_PENDING)) goto watchdog_done; /* check for reset */ - reg_val = rd32(hw, I40E_VF_ARQLEN1) & I40E_VF_ARQLEN1_ARQENABLE_MASK; - if (!(adapter->flags & I40EVF_FLAG_RESET_PENDING) && !reg_val) { - adapter->state = __I40EVF_RESETTING; - adapter->flags |= I40EVF_FLAG_RESET_PENDING; + reg_val = rd32(hw, IAVF_VF_ARQLEN1) & IAVF_VF_ARQLEN1_ARQENABLE_MASK; + if (!(adapter->flags & IAVF_FLAG_RESET_PENDING) && !reg_val) { + adapter->state = __IAVF_RESETTING; + adapter->flags |= IAVF_FLAG_RESET_PENDING; dev_err(&adapter->pdev->dev, "Hardware reset detected\n"); schedule_work(&adapter->reset_task); adapter->aq_required = 0; @@ -1628,140 +1626,140 @@ static void i40evf_watchdog_task(struct work_struct *work) * here so we don't race on the admin queue. */ if (adapter->current_op) { - if (!i40evf_asq_done(hw)) { + if (!iavf_asq_done(hw)) { dev_dbg(&adapter->pdev->dev, "Admin queue timeout\n"); - i40evf_send_api_ver(adapter); + iavf_send_api_ver(adapter); } goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_GET_CONFIG) { - i40evf_send_vf_config_msg(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_GET_CONFIG) { + iavf_send_vf_config_msg(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_DISABLE_QUEUES) { - i40evf_disable_queues(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_DISABLE_QUEUES) { + iavf_disable_queues(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_MAP_VECTORS) { - i40evf_map_queues(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_MAP_VECTORS) { + iavf_map_queues(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_ADD_MAC_FILTER) { - i40evf_add_ether_addrs(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_ADD_MAC_FILTER) { + iavf_add_ether_addrs(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_ADD_VLAN_FILTER) { - i40evf_add_vlans(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_ADD_VLAN_FILTER) { + iavf_add_vlans(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_DEL_MAC_FILTER) { - i40evf_del_ether_addrs(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_DEL_MAC_FILTER) { + iavf_del_ether_addrs(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_DEL_VLAN_FILTER) { - i40evf_del_vlans(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_DEL_VLAN_FILTER) { + iavf_del_vlans(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_ENABLE_VLAN_STRIPPING) { - i40evf_enable_vlan_stripping(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_ENABLE_VLAN_STRIPPING) { + iavf_enable_vlan_stripping(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_DISABLE_VLAN_STRIPPING) { - i40evf_disable_vlan_stripping(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_DISABLE_VLAN_STRIPPING) { + iavf_disable_vlan_stripping(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_CONFIGURE_QUEUES) { - i40evf_configure_queues(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_CONFIGURE_QUEUES) { + iavf_configure_queues(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_ENABLE_QUEUES) { - i40evf_enable_queues(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_ENABLE_QUEUES) { + iavf_enable_queues(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_CONFIGURE_RSS) { + if (adapter->aq_required & IAVF_FLAG_AQ_CONFIGURE_RSS) { /* This message goes straight to the firmware, not the * PF, so we don't have to set current_op as we will * not get a response through the ARQ. */ - i40evf_init_rss(adapter); - adapter->aq_required &= ~I40EVF_FLAG_AQ_CONFIGURE_RSS; + iavf_init_rss(adapter); + adapter->aq_required &= ~IAVF_FLAG_AQ_CONFIGURE_RSS; goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_GET_HENA) { - i40evf_get_hena(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_GET_HENA) { + iavf_get_hena(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_SET_HENA) { - i40evf_set_hena(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_SET_HENA) { + iavf_set_hena(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_SET_RSS_KEY) { - i40evf_set_rss_key(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_SET_RSS_KEY) { + iavf_set_rss_key(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_SET_RSS_LUT) { - i40evf_set_rss_lut(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_SET_RSS_LUT) { + iavf_set_rss_lut(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_REQUEST_PROMISC) { - i40evf_set_promiscuous(adapter, FLAG_VF_UNICAST_PROMISC | + if (adapter->aq_required & IAVF_FLAG_AQ_REQUEST_PROMISC) { + iavf_set_promiscuous(adapter, FLAG_VF_UNICAST_PROMISC | FLAG_VF_MULTICAST_PROMISC); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_REQUEST_ALLMULTI) { - i40evf_set_promiscuous(adapter, FLAG_VF_MULTICAST_PROMISC); + if (adapter->aq_required & IAVF_FLAG_AQ_REQUEST_ALLMULTI) { + iavf_set_promiscuous(adapter, FLAG_VF_MULTICAST_PROMISC); goto watchdog_done; } - if ((adapter->aq_required & I40EVF_FLAG_AQ_RELEASE_PROMISC) && - (adapter->aq_required & I40EVF_FLAG_AQ_RELEASE_ALLMULTI)) { - i40evf_set_promiscuous(adapter, 0); + if ((adapter->aq_required & IAVF_FLAG_AQ_RELEASE_PROMISC) && + (adapter->aq_required & IAVF_FLAG_AQ_RELEASE_ALLMULTI)) { + iavf_set_promiscuous(adapter, 0); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_ENABLE_CHANNELS) { - i40evf_enable_channels(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_ENABLE_CHANNELS) { + iavf_enable_channels(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_DISABLE_CHANNELS) { - i40evf_disable_channels(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_DISABLE_CHANNELS) { + iavf_disable_channels(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_ADD_CLOUD_FILTER) { - i40evf_add_cloud_filter(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_ADD_CLOUD_FILTER) { + iavf_add_cloud_filter(adapter); goto watchdog_done; } - if (adapter->aq_required & I40EVF_FLAG_AQ_DEL_CLOUD_FILTER) { - i40evf_del_cloud_filter(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_DEL_CLOUD_FILTER) { + iavf_del_cloud_filter(adapter); goto watchdog_done; } schedule_delayed_work(&adapter->client_task, msecs_to_jiffies(5)); - if (adapter->state == __I40EVF_RUNNING) - i40evf_request_stats(adapter); + if (adapter->state == __IAVF_RUNNING) + iavf_request_stats(adapter); watchdog_done: - if (adapter->state == __I40EVF_RUNNING) - i40evf_detect_recover_hung(&adapter->vsi); - clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); + if (adapter->state == __IAVF_RUNNING) + iavf_detect_recover_hung(&adapter->vsi); + clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); restart_watchdog: - if (adapter->state == __I40EVF_REMOVE) + if (adapter->state == __IAVF_REMOVE) return; if (adapter->aq_required) mod_timer(&adapter->watchdog_timer, @@ -1771,28 +1769,28 @@ restart_watchdog: schedule_work(&adapter->adminq_task); } -static void i40evf_disable_vf(struct i40evf_adapter *adapter) +static void iavf_disable_vf(struct iavf_adapter *adapter) { - struct i40evf_mac_filter *f, *ftmp; - struct i40evf_vlan_filter *fv, *fvtmp; - struct i40evf_cloud_filter *cf, *cftmp; + struct iavf_mac_filter *f, *ftmp; + struct iavf_vlan_filter *fv, *fvtmp; + struct iavf_cloud_filter *cf, *cftmp; - adapter->flags |= I40EVF_FLAG_PF_COMMS_FAILED; + adapter->flags |= IAVF_FLAG_PF_COMMS_FAILED; /* We don't use netif_running() because it may be true prior to * ndo_open() returning, so we can't assume it means all our open * tasks have finished, since we're not holding the rtnl_lock here. */ - if (adapter->state == __I40EVF_RUNNING) { - set_bit(__I40E_VSI_DOWN, adapter->vsi.state); + if (adapter->state == __IAVF_RUNNING) { + set_bit(__IAVF_VSI_DOWN, adapter->vsi.state); netif_carrier_off(adapter->netdev); netif_tx_disable(adapter->netdev); adapter->link_up = false; - i40evf_napi_disable_all(adapter); - i40evf_irq_disable(adapter); - i40evf_free_traffic_irqs(adapter); - i40evf_free_all_tx_resources(adapter); - i40evf_free_all_rx_resources(adapter); + iavf_napi_disable_all(adapter); + iavf_irq_disable(adapter); + iavf_free_traffic_irqs(adapter); + iavf_free_all_tx_resources(adapter); + iavf_free_all_rx_resources(adapter); } spin_lock_bh(&adapter->mac_vlan_list_lock); @@ -1818,41 +1816,41 @@ static void i40evf_disable_vf(struct i40evf_adapter *adapter) } spin_unlock_bh(&adapter->cloud_filter_list_lock); - i40evf_free_misc_irq(adapter); - i40evf_reset_interrupt_capability(adapter); - i40evf_free_queues(adapter); - i40evf_free_q_vectors(adapter); + iavf_free_misc_irq(adapter); + iavf_reset_interrupt_capability(adapter); + iavf_free_queues(adapter); + iavf_free_q_vectors(adapter); kfree(adapter->vf_res); - i40evf_shutdown_adminq(&adapter->hw); + iavf_shutdown_adminq(&adapter->hw); adapter->netdev->flags &= ~IFF_UP; - clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); - adapter->flags &= ~I40EVF_FLAG_RESET_PENDING; - adapter->state = __I40EVF_DOWN; + clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); + adapter->flags &= ~IAVF_FLAG_RESET_PENDING; + adapter->state = __IAVF_DOWN; wake_up(&adapter->down_waitqueue); dev_info(&adapter->pdev->dev, "Reset task did not complete, VF disabled\n"); } -#define I40EVF_RESET_WAIT_MS 10 -#define I40EVF_RESET_WAIT_COUNT 500 +#define IAVF_RESET_WAIT_MS 10 +#define IAVF_RESET_WAIT_COUNT 500 /** - * i40evf_reset_task - Call-back task to handle hardware reset + * iavf_reset_task - Call-back task to handle hardware reset * @work: pointer to work_struct * * During reset we need to shut down and reinitialize the admin queue * before we can use it to communicate with the PF again. We also clear * and reinit the rings because that context is lost as well. **/ -static void i40evf_reset_task(struct work_struct *work) +static void iavf_reset_task(struct work_struct *work) { - struct i40evf_adapter *adapter = container_of(work, - struct i40evf_adapter, + struct iavf_adapter *adapter = container_of(work, + struct iavf_adapter, reset_task); struct virtchnl_vf_resource *vfres = adapter->vf_res; struct net_device *netdev = adapter->netdev; - struct i40e_hw *hw = &adapter->hw; - struct i40evf_vlan_filter *vlf; - struct i40evf_cloud_filter *cf; - struct i40evf_mac_filter *f; + struct iavf_hw *hw = &adapter->hw; + struct iavf_vlan_filter *vlf; + struct iavf_cloud_filter *cf; + struct iavf_mac_filter *f; u32 reg_val; int i = 0, err; bool running; @@ -1860,63 +1858,63 @@ static void i40evf_reset_task(struct work_struct *work) /* When device is being removed it doesn't make sense to run the reset * task, just return in such a case. */ - if (test_bit(__I40EVF_IN_REMOVE_TASK, &adapter->crit_section)) + if (test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section)) return; - while (test_and_set_bit(__I40EVF_IN_CLIENT_TASK, + while (test_and_set_bit(__IAVF_IN_CLIENT_TASK, &adapter->crit_section)) usleep_range(500, 1000); if (CLIENT_ENABLED(adapter)) { - adapter->flags &= ~(I40EVF_FLAG_CLIENT_NEEDS_OPEN | - I40EVF_FLAG_CLIENT_NEEDS_CLOSE | - I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS | - I40EVF_FLAG_SERVICE_CLIENT_REQUESTED); + adapter->flags &= ~(IAVF_FLAG_CLIENT_NEEDS_OPEN | + IAVF_FLAG_CLIENT_NEEDS_CLOSE | + IAVF_FLAG_CLIENT_NEEDS_L2_PARAMS | + IAVF_FLAG_SERVICE_CLIENT_REQUESTED); cancel_delayed_work_sync(&adapter->client_task); - i40evf_notify_client_close(&adapter->vsi, true); + iavf_notify_client_close(&adapter->vsi, true); } - i40evf_misc_irq_disable(adapter); - if (adapter->flags & I40EVF_FLAG_RESET_NEEDED) { - adapter->flags &= ~I40EVF_FLAG_RESET_NEEDED; + iavf_misc_irq_disable(adapter); + if (adapter->flags & IAVF_FLAG_RESET_NEEDED) { + adapter->flags &= ~IAVF_FLAG_RESET_NEEDED; /* Restart the AQ here. If we have been reset but didn't * detect it, or if the PF had to reinit, our AQ will be hosed. */ - i40evf_shutdown_adminq(hw); - i40evf_init_adminq(hw); - i40evf_request_reset(adapter); + iavf_shutdown_adminq(hw); + iavf_init_adminq(hw); + iavf_request_reset(adapter); } - adapter->flags |= I40EVF_FLAG_RESET_PENDING; + adapter->flags |= IAVF_FLAG_RESET_PENDING; /* poll until we see the reset actually happen */ - for (i = 0; i < I40EVF_RESET_WAIT_COUNT; i++) { - reg_val = rd32(hw, I40E_VF_ARQLEN1) & - I40E_VF_ARQLEN1_ARQENABLE_MASK; + for (i = 0; i < IAVF_RESET_WAIT_COUNT; i++) { + reg_val = rd32(hw, IAVF_VF_ARQLEN1) & + IAVF_VF_ARQLEN1_ARQENABLE_MASK; if (!reg_val) break; usleep_range(5000, 10000); } - if (i == I40EVF_RESET_WAIT_COUNT) { + if (i == IAVF_RESET_WAIT_COUNT) { dev_info(&adapter->pdev->dev, "Never saw reset\n"); goto continue_reset; /* act like the reset happened */ } /* wait until the reset is complete and the PF is responding to us */ - for (i = 0; i < I40EVF_RESET_WAIT_COUNT; i++) { + for (i = 0; i < IAVF_RESET_WAIT_COUNT; i++) { /* sleep first to make sure a minimum wait time is met */ - msleep(I40EVF_RESET_WAIT_MS); + msleep(IAVF_RESET_WAIT_MS); - reg_val = rd32(hw, I40E_VFGEN_RSTAT) & - I40E_VFGEN_RSTAT_VFR_STATE_MASK; + reg_val = rd32(hw, IAVF_VFGEN_RSTAT) & + IAVF_VFGEN_RSTAT_VFR_STATE_MASK; if (reg_val == VIRTCHNL_VFR_VFACTIVE) break; } pci_set_master(adapter->pdev); - if (i == I40EVF_RESET_WAIT_COUNT) { + if (i == IAVF_RESET_WAIT_COUNT) { dev_err(&adapter->pdev->dev, "Reset never finished (%x)\n", reg_val); - i40evf_disable_vf(adapter); - clear_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section); + iavf_disable_vf(adapter); + clear_bit(__IAVF_IN_CLIENT_TASK, &adapter->crit_section); return; /* Do not attempt to reinit. It's dead, Jim. */ } @@ -1925,44 +1923,44 @@ continue_reset: * ndo_open() returning, so we can't assume it means all our open * tasks have finished, since we're not holding the rtnl_lock here. */ - running = ((adapter->state == __I40EVF_RUNNING) || - (adapter->state == __I40EVF_RESETTING)); + running = ((adapter->state == __IAVF_RUNNING) || + (adapter->state == __IAVF_RESETTING)); if (running) { netif_carrier_off(netdev); netif_tx_stop_all_queues(netdev); adapter->link_up = false; - i40evf_napi_disable_all(adapter); + iavf_napi_disable_all(adapter); } - i40evf_irq_disable(adapter); + iavf_irq_disable(adapter); - adapter->state = __I40EVF_RESETTING; - adapter->flags &= ~I40EVF_FLAG_RESET_PENDING; + adapter->state = __IAVF_RESETTING; + adapter->flags &= ~IAVF_FLAG_RESET_PENDING; /* free the Tx/Rx rings and descriptors, might be better to just * re-use them sometime in the future */ - i40evf_free_all_rx_resources(adapter); - i40evf_free_all_tx_resources(adapter); + iavf_free_all_rx_resources(adapter); + iavf_free_all_tx_resources(adapter); - adapter->flags |= I40EVF_FLAG_QUEUES_DISABLED; + adapter->flags |= IAVF_FLAG_QUEUES_DISABLED; /* kill and reinit the admin queue */ - i40evf_shutdown_adminq(hw); + iavf_shutdown_adminq(hw); adapter->current_op = VIRTCHNL_OP_UNKNOWN; - err = i40evf_init_adminq(hw); + err = iavf_init_adminq(hw); if (err) dev_info(&adapter->pdev->dev, "Failed to init adminq: %d\n", err); adapter->aq_required = 0; - if (adapter->flags & I40EVF_FLAG_REINIT_ITR_NEEDED) { - err = i40evf_reinit_interrupt_scheme(adapter); + if (adapter->flags & IAVF_FLAG_REINIT_ITR_NEEDED) { + err = iavf_reinit_interrupt_scheme(adapter); if (err) goto reset_err; } - adapter->aq_required |= I40EVF_FLAG_AQ_GET_CONFIG; - adapter->aq_required |= I40EVF_FLAG_AQ_MAP_VECTORS; + adapter->aq_required |= IAVF_FLAG_AQ_GET_CONFIG; + adapter->aq_required |= IAVF_FLAG_AQ_MAP_VECTORS; spin_lock_bh(&adapter->mac_vlan_list_lock); @@ -1987,10 +1985,10 @@ continue_reset: } spin_unlock_bh(&adapter->cloud_filter_list_lock); - adapter->aq_required |= I40EVF_FLAG_AQ_ADD_MAC_FILTER; - adapter->aq_required |= I40EVF_FLAG_AQ_ADD_VLAN_FILTER; - adapter->aq_required |= I40EVF_FLAG_AQ_ADD_CLOUD_FILTER; - i40evf_misc_irq_enable(adapter); + adapter->aq_required |= IAVF_FLAG_AQ_ADD_MAC_FILTER; + adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; + adapter->aq_required |= IAVF_FLAG_AQ_ADD_CLOUD_FILTER; + iavf_misc_irq_enable(adapter); mod_timer(&adapter->watchdog_timer, jiffies + 2); @@ -1999,84 +1997,83 @@ continue_reset: */ if (running) { /* allocate transmit descriptors */ - err = i40evf_setup_all_tx_resources(adapter); + err = iavf_setup_all_tx_resources(adapter); if (err) goto reset_err; /* allocate receive descriptors */ - err = i40evf_setup_all_rx_resources(adapter); + err = iavf_setup_all_rx_resources(adapter); if (err) goto reset_err; - if (adapter->flags & I40EVF_FLAG_REINIT_ITR_NEEDED) { - err = i40evf_request_traffic_irqs(adapter, - netdev->name); + if (adapter->flags & IAVF_FLAG_REINIT_ITR_NEEDED) { + err = iavf_request_traffic_irqs(adapter, netdev->name); if (err) goto reset_err; - adapter->flags &= ~I40EVF_FLAG_REINIT_ITR_NEEDED; + adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; } - i40evf_configure(adapter); + iavf_configure(adapter); - i40evf_up_complete(adapter); + iavf_up_complete(adapter); - i40evf_irq_enable(adapter, true); + iavf_irq_enable(adapter, true); } else { - adapter->state = __I40EVF_DOWN; + adapter->state = __IAVF_DOWN; wake_up(&adapter->down_waitqueue); } - clear_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section); - clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); + clear_bit(__IAVF_IN_CLIENT_TASK, &adapter->crit_section); + clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); return; reset_err: - clear_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section); - clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); + clear_bit(__IAVF_IN_CLIENT_TASK, &adapter->crit_section); + clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n"); - i40evf_close(netdev); + iavf_close(netdev); } /** - * i40evf_adminq_task - worker thread to clean the admin queue + * iavf_adminq_task - worker thread to clean the admin queue * @work: pointer to work_struct containing our data **/ -static void i40evf_adminq_task(struct work_struct *work) +static void iavf_adminq_task(struct work_struct *work) { - struct i40evf_adapter *adapter = - container_of(work, struct i40evf_adapter, adminq_task); - struct i40e_hw *hw = &adapter->hw; + struct iavf_adapter *adapter = + container_of(work, struct iavf_adapter, adminq_task); + struct iavf_hw *hw = &adapter->hw; struct i40e_arq_event_info event; enum virtchnl_ops v_op; - i40e_status ret, v_ret; + iavf_status ret, v_ret; u32 val, oldval; u16 pending; - if (adapter->flags & I40EVF_FLAG_PF_COMMS_FAILED) + if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) goto out; - event.buf_len = I40EVF_MAX_AQ_BUF_SIZE; + event.buf_len = IAVF_MAX_AQ_BUF_SIZE; event.msg_buf = kzalloc(event.buf_len, GFP_KERNEL); if (!event.msg_buf) goto out; do { - ret = i40evf_clean_arq_element(hw, &event, &pending); + ret = iavf_clean_arq_element(hw, &event, &pending); v_op = (enum virtchnl_ops)le32_to_cpu(event.desc.cookie_high); - v_ret = (i40e_status)le32_to_cpu(event.desc.cookie_low); + v_ret = (iavf_status)le32_to_cpu(event.desc.cookie_low); if (ret || !v_op) break; /* No event to process or error cleaning ARQ */ - i40evf_virtchnl_completion(adapter, v_op, v_ret, event.msg_buf, - event.msg_len); + iavf_virtchnl_completion(adapter, v_op, v_ret, event.msg_buf, + event.msg_len); if (pending != 0) - memset(event.msg_buf, 0, I40EVF_MAX_AQ_BUF_SIZE); + memset(event.msg_buf, 0, IAVF_MAX_AQ_BUF_SIZE); } while (pending); if ((adapter->flags & - (I40EVF_FLAG_RESET_PENDING | I40EVF_FLAG_RESET_NEEDED)) || - adapter->state == __I40EVF_RESETTING) + (IAVF_FLAG_RESET_PENDING | IAVF_FLAG_RESET_NEEDED)) || + adapter->state == __IAVF_RESETTING) goto freedom; /* check for error indications */ @@ -2084,34 +2081,34 @@ static void i40evf_adminq_task(struct work_struct *work) if (val == 0xdeadbeef) /* indicates device in reset */ goto freedom; oldval = val; - if (val & I40E_VF_ARQLEN1_ARQVFE_MASK) { + if (val & IAVF_VF_ARQLEN1_ARQVFE_MASK) { dev_info(&adapter->pdev->dev, "ARQ VF Error detected\n"); - val &= ~I40E_VF_ARQLEN1_ARQVFE_MASK; + val &= ~IAVF_VF_ARQLEN1_ARQVFE_MASK; } - if (val & I40E_VF_ARQLEN1_ARQOVFL_MASK) { + if (val & IAVF_VF_ARQLEN1_ARQOVFL_MASK) { dev_info(&adapter->pdev->dev, "ARQ Overflow Error detected\n"); - val &= ~I40E_VF_ARQLEN1_ARQOVFL_MASK; + val &= ~IAVF_VF_ARQLEN1_ARQOVFL_MASK; } - if (val & I40E_VF_ARQLEN1_ARQCRIT_MASK) { + if (val & IAVF_VF_ARQLEN1_ARQCRIT_MASK) { dev_info(&adapter->pdev->dev, "ARQ Critical Error detected\n"); - val &= ~I40E_VF_ARQLEN1_ARQCRIT_MASK; + val &= ~IAVF_VF_ARQLEN1_ARQCRIT_MASK; } if (oldval != val) wr32(hw, hw->aq.arq.len, val); val = rd32(hw, hw->aq.asq.len); oldval = val; - if (val & I40E_VF_ATQLEN1_ATQVFE_MASK) { + if (val & IAVF_VF_ATQLEN1_ATQVFE_MASK) { dev_info(&adapter->pdev->dev, "ASQ VF Error detected\n"); - val &= ~I40E_VF_ATQLEN1_ATQVFE_MASK; + val &= ~IAVF_VF_ATQLEN1_ATQVFE_MASK; } - if (val & I40E_VF_ATQLEN1_ATQOVFL_MASK) { + if (val & IAVF_VF_ATQLEN1_ATQOVFL_MASK) { dev_info(&adapter->pdev->dev, "ASQ Overflow Error detected\n"); - val &= ~I40E_VF_ATQLEN1_ATQOVFL_MASK; + val &= ~IAVF_VF_ATQLEN1_ATQOVFL_MASK; } - if (val & I40E_VF_ATQLEN1_ATQCRIT_MASK) { + if (val & IAVF_VF_ATQLEN1_ATQCRIT_MASK) { dev_info(&adapter->pdev->dev, "ASQ Critical Error detected\n"); - val &= ~I40E_VF_ATQLEN1_ATQCRIT_MASK; + val &= ~IAVF_VF_ATQLEN1_ATQCRIT_MASK; } if (oldval != val) wr32(hw, hw->aq.asq.len, val); @@ -2120,58 +2117,58 @@ freedom: kfree(event.msg_buf); out: /* re-enable Admin queue interrupt cause */ - i40evf_misc_irq_enable(adapter); + iavf_misc_irq_enable(adapter); } /** - * i40evf_client_task - worker thread to perform client work + * iavf_client_task - worker thread to perform client work * @work: pointer to work_struct containing our data * * This task handles client interactions. Because client calls can be * reentrant, we can't handle them in the watchdog. **/ -static void i40evf_client_task(struct work_struct *work) +static void iavf_client_task(struct work_struct *work) { - struct i40evf_adapter *adapter = - container_of(work, struct i40evf_adapter, client_task.work); + struct iavf_adapter *adapter = + container_of(work, struct iavf_adapter, client_task.work); /* If we can't get the client bit, just give up. We'll be rescheduled * later. */ - if (test_and_set_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section)) + if (test_and_set_bit(__IAVF_IN_CLIENT_TASK, &adapter->crit_section)) return; - if (adapter->flags & I40EVF_FLAG_SERVICE_CLIENT_REQUESTED) { - i40evf_client_subtask(adapter); - adapter->flags &= ~I40EVF_FLAG_SERVICE_CLIENT_REQUESTED; + if (adapter->flags & IAVF_FLAG_SERVICE_CLIENT_REQUESTED) { + iavf_client_subtask(adapter); + adapter->flags &= ~IAVF_FLAG_SERVICE_CLIENT_REQUESTED; goto out; } - if (adapter->flags & I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS) { - i40evf_notify_client_l2_params(&adapter->vsi); - adapter->flags &= ~I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS; + if (adapter->flags & IAVF_FLAG_CLIENT_NEEDS_L2_PARAMS) { + iavf_notify_client_l2_params(&adapter->vsi); + adapter->flags &= ~IAVF_FLAG_CLIENT_NEEDS_L2_PARAMS; goto out; } - if (adapter->flags & I40EVF_FLAG_CLIENT_NEEDS_CLOSE) { - i40evf_notify_client_close(&adapter->vsi, false); - adapter->flags &= ~I40EVF_FLAG_CLIENT_NEEDS_CLOSE; + if (adapter->flags & IAVF_FLAG_CLIENT_NEEDS_CLOSE) { + iavf_notify_client_close(&adapter->vsi, false); + adapter->flags &= ~IAVF_FLAG_CLIENT_NEEDS_CLOSE; goto out; } - if (adapter->flags & I40EVF_FLAG_CLIENT_NEEDS_OPEN) { - i40evf_notify_client_open(&adapter->vsi); - adapter->flags &= ~I40EVF_FLAG_CLIENT_NEEDS_OPEN; + if (adapter->flags & IAVF_FLAG_CLIENT_NEEDS_OPEN) { + iavf_notify_client_open(&adapter->vsi); + adapter->flags &= ~IAVF_FLAG_CLIENT_NEEDS_OPEN; } out: - clear_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section); + clear_bit(__IAVF_IN_CLIENT_TASK, &adapter->crit_section); } /** - * i40evf_free_all_tx_resources - Free Tx Resources for All Queues + * iavf_free_all_tx_resources - Free Tx Resources for All Queues * @adapter: board private structure * * Free all transmit software resources **/ -void i40evf_free_all_tx_resources(struct i40evf_adapter *adapter) +void iavf_free_all_tx_resources(struct iavf_adapter *adapter) { int i; @@ -2180,11 +2177,11 @@ void i40evf_free_all_tx_resources(struct i40evf_adapter *adapter) for (i = 0; i < adapter->num_active_queues; i++) if (adapter->tx_rings[i].desc) - i40evf_free_tx_resources(&adapter->tx_rings[i]); + iavf_free_tx_resources(&adapter->tx_rings[i]); } /** - * i40evf_setup_all_tx_resources - allocate all queues Tx resources + * iavf_setup_all_tx_resources - allocate all queues Tx resources * @adapter: board private structure * * If this function returns with an error, then it's possible one or @@ -2193,13 +2190,13 @@ void i40evf_free_all_tx_resources(struct i40evf_adapter *adapter) * * Return 0 on success, negative on failure **/ -static int i40evf_setup_all_tx_resources(struct i40evf_adapter *adapter) +static int iavf_setup_all_tx_resources(struct iavf_adapter *adapter) { int i, err = 0; for (i = 0; i < adapter->num_active_queues; i++) { adapter->tx_rings[i].count = adapter->tx_desc_count; - err = i40evf_setup_tx_descriptors(&adapter->tx_rings[i]); + err = iavf_setup_tx_descriptors(&adapter->tx_rings[i]); if (!err) continue; dev_err(&adapter->pdev->dev, @@ -2211,7 +2208,7 @@ static int i40evf_setup_all_tx_resources(struct i40evf_adapter *adapter) } /** - * i40evf_setup_all_rx_resources - allocate all queues Rx resources + * iavf_setup_all_rx_resources - allocate all queues Rx resources * @adapter: board private structure * * If this function returns with an error, then it's possible one or @@ -2220,13 +2217,13 @@ static int i40evf_setup_all_tx_resources(struct i40evf_adapter *adapter) * * Return 0 on success, negative on failure **/ -static int i40evf_setup_all_rx_resources(struct i40evf_adapter *adapter) +static int iavf_setup_all_rx_resources(struct iavf_adapter *adapter) { int i, err = 0; for (i = 0; i < adapter->num_active_queues; i++) { adapter->rx_rings[i].count = adapter->rx_desc_count; - err = i40evf_setup_rx_descriptors(&adapter->rx_rings[i]); + err = iavf_setup_rx_descriptors(&adapter->rx_rings[i]); if (!err) continue; dev_err(&adapter->pdev->dev, @@ -2237,12 +2234,12 @@ static int i40evf_setup_all_rx_resources(struct i40evf_adapter *adapter) } /** - * i40evf_free_all_rx_resources - Free Rx Resources for All Queues + * iavf_free_all_rx_resources - Free Rx Resources for All Queues * @adapter: board private structure * * Free all receive software resources **/ -void i40evf_free_all_rx_resources(struct i40evf_adapter *adapter) +void iavf_free_all_rx_resources(struct iavf_adapter *adapter) { int i; @@ -2251,16 +2248,16 @@ void i40evf_free_all_rx_resources(struct i40evf_adapter *adapter) for (i = 0; i < adapter->num_active_queues; i++) if (adapter->rx_rings[i].desc) - i40evf_free_rx_resources(&adapter->rx_rings[i]); + iavf_free_rx_resources(&adapter->rx_rings[i]); } /** - * i40evf_validate_tx_bandwidth - validate the max Tx bandwidth + * iavf_validate_tx_bandwidth - validate the max Tx bandwidth * @adapter: board private structure * @max_tx_rate: max Tx bw for a tc **/ -static int i40evf_validate_tx_bandwidth(struct i40evf_adapter *adapter, - u64 max_tx_rate) +static int iavf_validate_tx_bandwidth(struct iavf_adapter *adapter, + u64 max_tx_rate) { int speed = 0, ret = 0; @@ -2297,7 +2294,7 @@ static int i40evf_validate_tx_bandwidth(struct i40evf_adapter *adapter, } /** - * i40evf_validate_channel_config - validate queue mapping info + * iavf_validate_channel_config - validate queue mapping info * @adapter: board private structure * @mqprio_qopt: queue parameters * @@ -2305,15 +2302,15 @@ static int i40evf_validate_tx_bandwidth(struct i40evf_adapter *adapter, * configure queue channels is valid or not. Returns 0 on a valid * config. **/ -static int i40evf_validate_ch_config(struct i40evf_adapter *adapter, - struct tc_mqprio_qopt_offload *mqprio_qopt) +static int iavf_validate_ch_config(struct iavf_adapter *adapter, + struct tc_mqprio_qopt_offload *mqprio_qopt) { u64 total_max_rate = 0; int i, num_qps = 0; u64 tx_rate = 0; int ret = 0; - if (mqprio_qopt->qopt.num_tc > I40EVF_MAX_TRAFFIC_CLASS || + if (mqprio_qopt->qopt.num_tc > IAVF_MAX_TRAFFIC_CLASS || mqprio_qopt->qopt.num_tc < 1) return -EINVAL; @@ -2328,24 +2325,24 @@ static int i40evf_validate_ch_config(struct i40evf_adapter *adapter, } /*convert to Mbps */ tx_rate = div_u64(mqprio_qopt->max_rate[i], - I40EVF_MBPS_DIVISOR); + IAVF_MBPS_DIVISOR); total_max_rate += tx_rate; num_qps += mqprio_qopt->qopt.count[i]; } - if (num_qps > I40EVF_MAX_REQ_QUEUES) + if (num_qps > IAVF_MAX_REQ_QUEUES) return -EINVAL; - ret = i40evf_validate_tx_bandwidth(adapter, total_max_rate); + ret = iavf_validate_tx_bandwidth(adapter, total_max_rate); return ret; } /** - * i40evf_del_all_cloud_filters - delete all cloud filters + * iavf_del_all_cloud_filters - delete all cloud filters * on the traffic classes **/ -static void i40evf_del_all_cloud_filters(struct i40evf_adapter *adapter) +static void iavf_del_all_cloud_filters(struct iavf_adapter *adapter) { - struct i40evf_cloud_filter *cf, *cftmp; + struct iavf_cloud_filter *cf, *cftmp; spin_lock_bh(&adapter->cloud_filter_list_lock); list_for_each_entry_safe(cf, cftmp, &adapter->cloud_filter_list, @@ -2358,7 +2355,7 @@ static void i40evf_del_all_cloud_filters(struct i40evf_adapter *adapter) } /** - * __i40evf_setup_tc - configure multiple traffic classes + * __iavf_setup_tc - configure multiple traffic classes * @netdev: network interface device structure * @type_date: tc offload data * @@ -2368,10 +2365,10 @@ static void i40evf_del_all_cloud_filters(struct i40evf_adapter *adapter) * * Returns 0 on success. **/ -static int __i40evf_setup_tc(struct net_device *netdev, void *type_data) +static int __iavf_setup_tc(struct net_device *netdev, void *type_data) { struct tc_mqprio_qopt_offload *mqprio_qopt = type_data; - struct i40evf_adapter *adapter = netdev_priv(netdev); + struct iavf_adapter *adapter = netdev_priv(netdev); struct virtchnl_vf_resource *vfres = adapter->vf_res; u8 num_tc = 0, total_qps = 0; int ret = 0, netdev_tc = 0; @@ -2384,14 +2381,14 @@ static int __i40evf_setup_tc(struct net_device *netdev, void *type_data) /* delete queue_channel */ if (!mqprio_qopt->qopt.hw) { - if (adapter->ch_config.state == __I40EVF_TC_RUNNING) { + if (adapter->ch_config.state == __IAVF_TC_RUNNING) { /* reset the tc configuration */ netdev_reset_tc(netdev); adapter->num_tc = 0; netif_tx_stop_all_queues(netdev); netif_tx_disable(netdev); - i40evf_del_all_cloud_filters(adapter); - adapter->aq_required = I40EVF_FLAG_AQ_DISABLE_CHANNELS; + iavf_del_all_cloud_filters(adapter); + adapter->aq_required = IAVF_FLAG_AQ_DISABLE_CHANNELS; goto exit; } else { return -EINVAL; @@ -2404,12 +2401,12 @@ static int __i40evf_setup_tc(struct net_device *netdev, void *type_data) dev_err(&adapter->pdev->dev, "ADq not supported\n"); return -EOPNOTSUPP; } - if (adapter->ch_config.state != __I40EVF_TC_INVALID) { + if (adapter->ch_config.state != __IAVF_TC_INVALID) { dev_err(&adapter->pdev->dev, "TC configuration already exists\n"); return -EINVAL; } - ret = i40evf_validate_ch_config(adapter, mqprio_qopt); + ret = iavf_validate_ch_config(adapter, mqprio_qopt); if (ret) return ret; /* Return if same TC config is requested */ @@ -2417,7 +2414,7 @@ static int __i40evf_setup_tc(struct net_device *netdev, void *type_data) return 0; adapter->num_tc = num_tc; - for (i = 0; i < I40EVF_MAX_TRAFFIC_CLASS; i++) { + for (i = 0; i < IAVF_MAX_TRAFFIC_CLASS; i++) { if (i < num_tc) { adapter->ch_config.ch_info[i].count = mqprio_qopt->qopt.count[i]; @@ -2427,7 +2424,7 @@ static int __i40evf_setup_tc(struct net_device *netdev, void *type_data) max_tx_rate = mqprio_qopt->max_rate[i]; /* convert to Mbps */ max_tx_rate = div_u64(max_tx_rate, - I40EVF_MBPS_DIVISOR); + IAVF_MBPS_DIVISOR); adapter->ch_config.ch_info[i].max_tx_rate = max_tx_rate; } else { @@ -2438,11 +2435,11 @@ static int __i40evf_setup_tc(struct net_device *netdev, void *type_data) adapter->ch_config.total_qps = total_qps; netif_tx_stop_all_queues(netdev); netif_tx_disable(netdev); - adapter->aq_required |= I40EVF_FLAG_AQ_ENABLE_CHANNELS; + adapter->aq_required |= IAVF_FLAG_AQ_ENABLE_CHANNELS; netdev_reset_tc(netdev); /* Report the tc mapping up the stack */ netdev_set_num_tc(adapter->netdev, num_tc); - for (i = 0; i < I40EVF_MAX_TRAFFIC_CLASS; i++) { + for (i = 0; i < IAVF_MAX_TRAFFIC_CLASS; i++) { u16 qcount = mqprio_qopt->qopt.count[i]; u16 qoffset = mqprio_qopt->qopt.offset[i]; @@ -2456,14 +2453,14 @@ exit: } /** - * i40evf_parse_cls_flower - Parse tc flower filters provided by kernel + * iavf_parse_cls_flower - Parse tc flower filters provided by kernel * @adapter: board private structure * @cls_flower: pointer to struct tc_cls_flower_offload * @filter: pointer to cloud filter structure */ -static int i40evf_parse_cls_flower(struct i40evf_adapter *adapter, - struct tc_cls_flower_offload *f, - struct i40evf_cloud_filter *filter) +static int iavf_parse_cls_flower(struct iavf_adapter *adapter, + struct tc_cls_flower_offload *f, + struct iavf_cloud_filter *filter) { u16 n_proto_mask = 0; u16 n_proto_key = 0; @@ -2494,7 +2491,7 @@ static int i40evf_parse_cls_flower(struct i40evf_adapter *adapter, f->mask); if (mask->keyid != 0) - field_flags |= I40EVF_CLOUD_FIELD_TEN_ID; + field_flags |= IAVF_CLOUD_FIELD_TEN_ID; } if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) { @@ -2541,7 +2538,7 @@ static int i40evf_parse_cls_flower(struct i40evf_adapter *adapter, /* use is_broadcast and is_zero to check for all 0xf or 0 */ if (!is_zero_ether_addr(mask->dst)) { if (is_broadcast_ether_addr(mask->dst)) { - field_flags |= I40EVF_CLOUD_FIELD_OMAC; + field_flags |= IAVF_CLOUD_FIELD_OMAC; } else { dev_err(&adapter->pdev->dev, "Bad ether dest mask %pM\n", mask->dst); @@ -2551,7 +2548,7 @@ static int i40evf_parse_cls_flower(struct i40evf_adapter *adapter, if (!is_zero_ether_addr(mask->src)) { if (is_broadcast_ether_addr(mask->src)) { - field_flags |= I40EVF_CLOUD_FIELD_IMAC; + field_flags |= IAVF_CLOUD_FIELD_IMAC; } else { dev_err(&adapter->pdev->dev, "Bad ether src mask %pM\n", mask->src); @@ -2592,7 +2589,7 @@ static int i40evf_parse_cls_flower(struct i40evf_adapter *adapter, if (mask->vlan_id) { if (mask->vlan_id == VLAN_VID_MASK) { - field_flags |= I40EVF_CLOUD_FIELD_IVLAN; + field_flags |= IAVF_CLOUD_FIELD_IVLAN; } else { dev_err(&adapter->pdev->dev, "Bad vlan mask %u\n", mask->vlan_id); @@ -2624,7 +2621,7 @@ static int i40evf_parse_cls_flower(struct i40evf_adapter *adapter, if (mask->dst) { if (mask->dst == cpu_to_be32(0xffffffff)) { - field_flags |= I40EVF_CLOUD_FIELD_IIP; + field_flags |= IAVF_CLOUD_FIELD_IIP; } else { dev_err(&adapter->pdev->dev, "Bad ip dst mask 0x%08x\n", be32_to_cpu(mask->dst)); @@ -2634,7 +2631,7 @@ static int i40evf_parse_cls_flower(struct i40evf_adapter *adapter, if (mask->src) { if (mask->src == cpu_to_be32(0xffffffff)) { - field_flags |= I40EVF_CLOUD_FIELD_IIP; + field_flags |= IAVF_CLOUD_FIELD_IIP; } else { dev_err(&adapter->pdev->dev, "Bad ip src mask 0x%08x\n", be32_to_cpu(mask->dst)); @@ -2642,7 +2639,7 @@ static int i40evf_parse_cls_flower(struct i40evf_adapter *adapter, } } - if (field_flags & I40EVF_CLOUD_FIELD_TEN_ID) { + if (field_flags & IAVF_CLOUD_FIELD_TEN_ID) { dev_info(&adapter->pdev->dev, "Tenant id not allowed for ip filter\n"); return I40E_ERR_CONFIG; } @@ -2683,7 +2680,7 @@ static int i40evf_parse_cls_flower(struct i40evf_adapter *adapter, return I40E_ERR_CONFIG; } if (!ipv6_addr_any(&mask->dst) || !ipv6_addr_any(&mask->src)) - field_flags |= I40EVF_CLOUD_FIELD_IIP; + field_flags |= IAVF_CLOUD_FIELD_IIP; for (i = 0; i < 4; i++) vf->mask.tcp_spec.dst_ip[i] |= cpu_to_be32(0xffffffff); @@ -2706,7 +2703,7 @@ static int i40evf_parse_cls_flower(struct i40evf_adapter *adapter, if (mask->src) { if (mask->src == cpu_to_be16(0xffff)) { - field_flags |= I40EVF_CLOUD_FIELD_IIP; + field_flags |= IAVF_CLOUD_FIELD_IIP; } else { dev_err(&adapter->pdev->dev, "Bad src port mask %u\n", be16_to_cpu(mask->src)); @@ -2716,7 +2713,7 @@ static int i40evf_parse_cls_flower(struct i40evf_adapter *adapter, if (mask->dst) { if (mask->dst == cpu_to_be16(0xffff)) { - field_flags |= I40EVF_CLOUD_FIELD_IIP; + field_flags |= IAVF_CLOUD_FIELD_IIP; } else { dev_err(&adapter->pdev->dev, "Bad dst port mask %u\n", be16_to_cpu(mask->dst)); @@ -2739,13 +2736,13 @@ static int i40evf_parse_cls_flower(struct i40evf_adapter *adapter, } /** - * i40evf_handle_tclass - Forward to a traffic class on the device + * iavf_handle_tclass - Forward to a traffic class on the device * @adapter: board private structure * @tc: traffic class index on the device * @filter: pointer to cloud filter structure */ -static int i40evf_handle_tclass(struct i40evf_adapter *adapter, u32 tc, - struct i40evf_cloud_filter *filter) +static int iavf_handle_tclass(struct iavf_adapter *adapter, u32 tc, + struct iavf_cloud_filter *filter) { if (tc == 0) return 0; @@ -2763,15 +2760,15 @@ static int i40evf_handle_tclass(struct i40evf_adapter *adapter, u32 tc, } /** - * i40evf_configure_clsflower - Add tc flower filters + * iavf_configure_clsflower - Add tc flower filters * @adapter: board private structure * @cls_flower: Pointer to struct tc_cls_flower_offload */ -static int i40evf_configure_clsflower(struct i40evf_adapter *adapter, - struct tc_cls_flower_offload *cls_flower) +static int iavf_configure_clsflower(struct iavf_adapter *adapter, + struct tc_cls_flower_offload *cls_flower) { int tc = tc_classid_to_hwtc(adapter->netdev, cls_flower->classid); - struct i40evf_cloud_filter *filter = NULL; + struct iavf_cloud_filter *filter = NULL; int err = -EINVAL, count = 50; if (tc < 0) { @@ -2783,7 +2780,7 @@ static int i40evf_configure_clsflower(struct i40evf_adapter *adapter, if (!filter) return -ENOMEM; - while (test_and_set_bit(__I40EVF_IN_CRITICAL_TASK, + while (test_and_set_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section)) { if (--count == 0) goto err; @@ -2796,11 +2793,11 @@ static int i40evf_configure_clsflower(struct i40evf_adapter *adapter, memset(&filter->f.mask.tcp_spec, 0, sizeof(struct virtchnl_l4_spec)); /* start out with flow type and eth type IPv4 to begin with */ filter->f.flow_type = VIRTCHNL_TCP_V4_FLOW; - err = i40evf_parse_cls_flower(adapter, cls_flower, filter); + err = iavf_parse_cls_flower(adapter, cls_flower, filter); if (err < 0) goto err; - err = i40evf_handle_tclass(adapter, tc, filter); + err = iavf_handle_tclass(adapter, tc, filter); if (err < 0) goto err; @@ -2809,27 +2806,27 @@ static int i40evf_configure_clsflower(struct i40evf_adapter *adapter, list_add_tail(&filter->list, &adapter->cloud_filter_list); adapter->num_cloud_filters++; filter->add = true; - adapter->aq_required |= I40EVF_FLAG_AQ_ADD_CLOUD_FILTER; + adapter->aq_required |= IAVF_FLAG_AQ_ADD_CLOUD_FILTER; spin_unlock_bh(&adapter->cloud_filter_list_lock); err: if (err) kfree(filter); - clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); + clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); return err; } -/* i40evf_find_cf - Find the cloud filter in the list +/* iavf_find_cf - Find the cloud filter in the list * @adapter: Board private structure * @cookie: filter specific cookie * * Returns ptr to the filter object or NULL. Must be called while holding the * cloud_filter_list_lock. */ -static struct i40evf_cloud_filter *i40evf_find_cf(struct i40evf_adapter *adapter, - unsigned long *cookie) +static struct iavf_cloud_filter *iavf_find_cf(struct iavf_adapter *adapter, + unsigned long *cookie) { - struct i40evf_cloud_filter *filter = NULL; + struct iavf_cloud_filter *filter = NULL; if (!cookie) return NULL; @@ -2842,21 +2839,21 @@ static struct i40evf_cloud_filter *i40evf_find_cf(struct i40evf_adapter *adapter } /** - * i40evf_delete_clsflower - Remove tc flower filters + * iavf_delete_clsflower - Remove tc flower filters * @adapter: board private structure * @cls_flower: Pointer to struct tc_cls_flower_offload */ -static int i40evf_delete_clsflower(struct i40evf_adapter *adapter, - struct tc_cls_flower_offload *cls_flower) +static int iavf_delete_clsflower(struct iavf_adapter *adapter, + struct tc_cls_flower_offload *cls_flower) { - struct i40evf_cloud_filter *filter = NULL; + struct iavf_cloud_filter *filter = NULL; int err = 0; spin_lock_bh(&adapter->cloud_filter_list_lock); - filter = i40evf_find_cf(adapter, &cls_flower->cookie); + filter = iavf_find_cf(adapter, &cls_flower->cookie); if (filter) { filter->del = true; - adapter->aq_required |= I40EVF_FLAG_AQ_DEL_CLOUD_FILTER; + adapter->aq_required |= IAVF_FLAG_AQ_DEL_CLOUD_FILTER; } else { err = -EINVAL; } @@ -2866,21 +2863,21 @@ static int i40evf_delete_clsflower(struct i40evf_adapter *adapter, } /** - * i40evf_setup_tc_cls_flower - flower classifier offloads + * iavf_setup_tc_cls_flower - flower classifier offloads * @netdev: net device to configure * @type_data: offload data */ -static int i40evf_setup_tc_cls_flower(struct i40evf_adapter *adapter, - struct tc_cls_flower_offload *cls_flower) +static int iavf_setup_tc_cls_flower(struct iavf_adapter *adapter, + struct tc_cls_flower_offload *cls_flower) { if (cls_flower->common.chain_index) return -EOPNOTSUPP; switch (cls_flower->command) { case TC_CLSFLOWER_REPLACE: - return i40evf_configure_clsflower(adapter, cls_flower); + return iavf_configure_clsflower(adapter, cls_flower); case TC_CLSFLOWER_DESTROY: - return i40evf_delete_clsflower(adapter, cls_flower); + return iavf_delete_clsflower(adapter, cls_flower); case TC_CLSFLOWER_STATS: return -EOPNOTSUPP; default: @@ -2889,46 +2886,46 @@ static int i40evf_setup_tc_cls_flower(struct i40evf_adapter *adapter, } /** - * i40evf_setup_tc_block_cb - block callback for tc + * iavf_setup_tc_block_cb - block callback for tc * @type: type of offload * @type_data: offload data * @cb_priv: * * This function is the block callback for traffic classes **/ -static int i40evf_setup_tc_block_cb(enum tc_setup_type type, void *type_data, - void *cb_priv) +static int iavf_setup_tc_block_cb(enum tc_setup_type type, void *type_data, + void *cb_priv) { switch (type) { case TC_SETUP_CLSFLOWER: - return i40evf_setup_tc_cls_flower(cb_priv, type_data); + return iavf_setup_tc_cls_flower(cb_priv, type_data); default: return -EOPNOTSUPP; } } /** - * i40evf_setup_tc_block - register callbacks for tc + * iavf_setup_tc_block - register callbacks for tc * @netdev: network interface device structure * @f: tc offload data * * This function registers block callbacks for tc * offloads **/ -static int i40evf_setup_tc_block(struct net_device *dev, - struct tc_block_offload *f) +static int iavf_setup_tc_block(struct net_device *dev, + struct tc_block_offload *f) { - struct i40evf_adapter *adapter = netdev_priv(dev); + struct iavf_adapter *adapter = netdev_priv(dev); if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS) return -EOPNOTSUPP; switch (f->command) { case TC_BLOCK_BIND: - return tcf_block_cb_register(f->block, i40evf_setup_tc_block_cb, + return tcf_block_cb_register(f->block, iavf_setup_tc_block_cb, adapter, adapter, f->extack); case TC_BLOCK_UNBIND: - tcf_block_cb_unregister(f->block, i40evf_setup_tc_block_cb, + tcf_block_cb_unregister(f->block, iavf_setup_tc_block_cb, adapter); return 0; default: @@ -2937,7 +2934,7 @@ static int i40evf_setup_tc_block(struct net_device *dev, } /** - * i40evf_setup_tc - configure multiple traffic classes + * iavf_setup_tc - configure multiple traffic classes * @netdev: network interface device structure * @type: type of offload * @type_date: tc offload data @@ -2947,21 +2944,21 @@ static int i40evf_setup_tc_block(struct net_device *dev, * * Returns 0 on success **/ -static int i40evf_setup_tc(struct net_device *netdev, enum tc_setup_type type, - void *type_data) +static int iavf_setup_tc(struct net_device *netdev, enum tc_setup_type type, + void *type_data) { switch (type) { case TC_SETUP_QDISC_MQPRIO: - return __i40evf_setup_tc(netdev, type_data); + return __iavf_setup_tc(netdev, type_data); case TC_SETUP_BLOCK: - return i40evf_setup_tc_block(netdev, type_data); + return iavf_setup_tc_block(netdev, type_data); default: return -EOPNOTSUPP; } } /** - * i40evf_open - Called when a network interface is made active + * iavf_open - Called when a network interface is made active * @netdev: network interface device structure * * Returns 0 on success, negative value on failure @@ -2972,71 +2969,71 @@ static int i40evf_setup_tc(struct net_device *netdev, enum tc_setup_type type, * handler is registered with the OS, the watchdog timer is started, * and the stack is notified that the interface is ready. **/ -static int i40evf_open(struct net_device *netdev) +static int iavf_open(struct net_device *netdev) { - struct i40evf_adapter *adapter = netdev_priv(netdev); + struct iavf_adapter *adapter = netdev_priv(netdev); int err; - if (adapter->flags & I40EVF_FLAG_PF_COMMS_FAILED) { + if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) { dev_err(&adapter->pdev->dev, "Unable to open device due to PF driver failure.\n"); return -EIO; } - while (test_and_set_bit(__I40EVF_IN_CRITICAL_TASK, + while (test_and_set_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section)) usleep_range(500, 1000); - if (adapter->state != __I40EVF_DOWN) { + if (adapter->state != __IAVF_DOWN) { err = -EBUSY; goto err_unlock; } /* allocate transmit descriptors */ - err = i40evf_setup_all_tx_resources(adapter); + err = iavf_setup_all_tx_resources(adapter); if (err) goto err_setup_tx; /* allocate receive descriptors */ - err = i40evf_setup_all_rx_resources(adapter); + err = iavf_setup_all_rx_resources(adapter); if (err) goto err_setup_rx; /* clear any pending interrupts, may auto mask */ - err = i40evf_request_traffic_irqs(adapter, netdev->name); + err = iavf_request_traffic_irqs(adapter, netdev->name); if (err) goto err_req_irq; spin_lock_bh(&adapter->mac_vlan_list_lock); - i40evf_add_filter(adapter, adapter->hw.mac.addr); + iavf_add_filter(adapter, adapter->hw.mac.addr); spin_unlock_bh(&adapter->mac_vlan_list_lock); - i40evf_configure(adapter); + iavf_configure(adapter); - i40evf_up_complete(adapter); + iavf_up_complete(adapter); - i40evf_irq_enable(adapter, true); + iavf_irq_enable(adapter, true); - clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); + clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); return 0; err_req_irq: - i40evf_down(adapter); - i40evf_free_traffic_irqs(adapter); + iavf_down(adapter); + iavf_free_traffic_irqs(adapter); err_setup_rx: - i40evf_free_all_rx_resources(adapter); + iavf_free_all_rx_resources(adapter); err_setup_tx: - i40evf_free_all_tx_resources(adapter); + iavf_free_all_tx_resources(adapter); err_unlock: - clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); + clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); return err; } /** - * i40evf_close - Disables a network interface + * iavf_close - Disables a network interface * @netdev: network interface device structure * * Returns 0, this is not allowed to fail @@ -3046,41 +3043,41 @@ err_unlock: * needs to be disabled. All IRQs except vector 0 (reserved for admin queue) * are freed, along with all transmit and receive resources. **/ -static int i40evf_close(struct net_device *netdev) +static int iavf_close(struct net_device *netdev) { - struct i40evf_adapter *adapter = netdev_priv(netdev); + struct iavf_adapter *adapter = netdev_priv(netdev); int status; - if (adapter->state <= __I40EVF_DOWN_PENDING) + if (adapter->state <= __IAVF_DOWN_PENDING) return 0; - while (test_and_set_bit(__I40EVF_IN_CRITICAL_TASK, + while (test_and_set_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section)) usleep_range(500, 1000); - set_bit(__I40E_VSI_DOWN, adapter->vsi.state); + set_bit(__IAVF_VSI_DOWN, adapter->vsi.state); if (CLIENT_ENABLED(adapter)) - adapter->flags |= I40EVF_FLAG_CLIENT_NEEDS_CLOSE; + adapter->flags |= IAVF_FLAG_CLIENT_NEEDS_CLOSE; - i40evf_down(adapter); - adapter->state = __I40EVF_DOWN_PENDING; - i40evf_free_traffic_irqs(adapter); + iavf_down(adapter); + adapter->state = __IAVF_DOWN_PENDING; + iavf_free_traffic_irqs(adapter); - clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); + clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); /* We explicitly don't free resources here because the hardware is * still active and can DMA into memory. Resources are cleared in - * i40evf_virtchnl_completion() after we get confirmation from the PF + * iavf_virtchnl_completion() after we get confirmation from the PF * driver that the rings have been stopped. * - * Also, we wait for state to transition to __I40EVF_DOWN before - * returning. State change occurs in i40evf_virtchnl_completion() after + * Also, we wait for state to transition to __IAVF_DOWN before + * returning. State change occurs in iavf_virtchnl_completion() after * VF resources are released (which occurs after PF driver processes and * responds to admin queue commands). */ status = wait_event_timeout(adapter->down_waitqueue, - adapter->state == __I40EVF_DOWN, + adapter->state == __IAVF_DOWN, msecs_to_jiffies(200)); if (!status) netdev_warn(netdev, "Device resources not yet released\n"); @@ -3088,64 +3085,65 @@ static int i40evf_close(struct net_device *netdev) } /** - * i40evf_change_mtu - Change the Maximum Transfer Unit + * iavf_change_mtu - Change the Maximum Transfer Unit * @netdev: network interface device structure * @new_mtu: new value for maximum frame size * * Returns 0 on success, negative on failure **/ -static int i40evf_change_mtu(struct net_device *netdev, int new_mtu) +static int iavf_change_mtu(struct net_device *netdev, int new_mtu) { - struct i40evf_adapter *adapter = netdev_priv(netdev); + struct iavf_adapter *adapter = netdev_priv(netdev); netdev->mtu = new_mtu; if (CLIENT_ENABLED(adapter)) { - i40evf_notify_client_l2_params(&adapter->vsi); - adapter->flags |= I40EVF_FLAG_SERVICE_CLIENT_REQUESTED; + iavf_notify_client_l2_params(&adapter->vsi); + adapter->flags |= IAVF_FLAG_SERVICE_CLIENT_REQUESTED; } - adapter->flags |= I40EVF_FLAG_RESET_NEEDED; + adapter->flags |= IAVF_FLAG_RESET_NEEDED; schedule_work(&adapter->reset_task); return 0; } /** - * i40e_set_features - set the netdev feature flags + * iavf_set_features - set the netdev feature flags * @netdev: ptr to the netdev being adjusted * @features: the feature set that the stack is suggesting * Note: expects to be called while under rtnl_lock() **/ -static int i40evf_set_features(struct net_device *netdev, - netdev_features_t features) +static int iavf_set_features(struct net_device *netdev, + netdev_features_t features) { - struct i40evf_adapter *adapter = netdev_priv(netdev); + struct iavf_adapter *adapter = netdev_priv(netdev); - /* Don't allow changing VLAN_RX flag when VLAN is set for VF - * and return an error in this case + /* Don't allow changing VLAN_RX flag when adapter is not capable + * of VLAN offload */ - if (VLAN_ALLOWED(adapter)) { + if (!VLAN_ALLOWED(adapter)) { + if ((netdev->features ^ features) & NETIF_F_HW_VLAN_CTAG_RX) + return -EINVAL; + } else if ((netdev->features ^ features) & NETIF_F_HW_VLAN_CTAG_RX) { if (features & NETIF_F_HW_VLAN_CTAG_RX) adapter->aq_required |= - I40EVF_FLAG_AQ_ENABLE_VLAN_STRIPPING; + IAVF_FLAG_AQ_ENABLE_VLAN_STRIPPING; else adapter->aq_required |= - I40EVF_FLAG_AQ_DISABLE_VLAN_STRIPPING; - } else if ((netdev->features ^ features) & NETIF_F_HW_VLAN_CTAG_RX) { - return -EINVAL; + IAVF_FLAG_AQ_DISABLE_VLAN_STRIPPING; } return 0; } /** - * i40evf_features_check - Validate encapsulated packet conforms to limits + * iavf_features_check - Validate encapsulated packet conforms to limits * @skb: skb buff * @dev: This physical port's netdev * @features: Offload features that the stack believes apply **/ -static netdev_features_t i40evf_features_check(struct sk_buff *skb, - struct net_device *dev, - netdev_features_t features) +static netdev_features_t iavf_features_check(struct sk_buff *skb, + struct net_device *dev, + netdev_features_t features) { size_t len; @@ -3196,16 +3194,16 @@ out_err: } /** - * i40evf_fix_features - fix up the netdev feature bits + * iavf_fix_features - fix up the netdev feature bits * @netdev: our net device * @features: desired feature bits * * Returns fixed-up features bits **/ -static netdev_features_t i40evf_fix_features(struct net_device *netdev, - netdev_features_t features) +static netdev_features_t iavf_fix_features(struct net_device *netdev, + netdev_features_t features) { - struct i40evf_adapter *adapter = netdev_priv(netdev); + struct iavf_adapter *adapter = netdev_priv(netdev); if (!(adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN)) features &= ~(NETIF_F_HW_VLAN_CTAG_TX | @@ -3215,40 +3213,40 @@ static netdev_features_t i40evf_fix_features(struct net_device *netdev, return features; } -static const struct net_device_ops i40evf_netdev_ops = { - .ndo_open = i40evf_open, - .ndo_stop = i40evf_close, - .ndo_start_xmit = i40evf_xmit_frame, - .ndo_set_rx_mode = i40evf_set_rx_mode, +static const struct net_device_ops iavf_netdev_ops = { + .ndo_open = iavf_open, + .ndo_stop = iavf_close, + .ndo_start_xmit = iavf_xmit_frame, + .ndo_set_rx_mode = iavf_set_rx_mode, .ndo_validate_addr = eth_validate_addr, - .ndo_set_mac_address = i40evf_set_mac, - .ndo_change_mtu = i40evf_change_mtu, - .ndo_tx_timeout = i40evf_tx_timeout, - .ndo_vlan_rx_add_vid = i40evf_vlan_rx_add_vid, - .ndo_vlan_rx_kill_vid = i40evf_vlan_rx_kill_vid, - .ndo_features_check = i40evf_features_check, - .ndo_fix_features = i40evf_fix_features, - .ndo_set_features = i40evf_set_features, + .ndo_set_mac_address = iavf_set_mac, + .ndo_change_mtu = iavf_change_mtu, + .ndo_tx_timeout = iavf_tx_timeout, + .ndo_vlan_rx_add_vid = iavf_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = iavf_vlan_rx_kill_vid, + .ndo_features_check = iavf_features_check, + .ndo_fix_features = iavf_fix_features, + .ndo_set_features = iavf_set_features, #ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = i40evf_netpoll, + .ndo_poll_controller = iavf_netpoll, #endif - .ndo_setup_tc = i40evf_setup_tc, + .ndo_setup_tc = iavf_setup_tc, }; /** - * i40evf_check_reset_complete - check that VF reset is complete + * iavf_check_reset_complete - check that VF reset is complete * @hw: pointer to hw struct * * Returns 0 if device is ready to use, or -EBUSY if it's in reset. **/ -static int i40evf_check_reset_complete(struct i40e_hw *hw) +static int iavf_check_reset_complete(struct iavf_hw *hw) { u32 rstat; int i; for (i = 0; i < 100; i++) { - rstat = rd32(hw, I40E_VFGEN_RSTAT) & - I40E_VFGEN_RSTAT_VFR_STATE_MASK; + rstat = rd32(hw, IAVF_VFGEN_RSTAT) & + IAVF_VFGEN_RSTAT_VFR_STATE_MASK; if ((rstat == VIRTCHNL_VFR_VFACTIVE) || (rstat == VIRTCHNL_VFR_COMPLETED)) return 0; @@ -3258,18 +3256,18 @@ static int i40evf_check_reset_complete(struct i40e_hw *hw) } /** - * i40evf_process_config - Process the config information we got from the PF + * iavf_process_config - Process the config information we got from the PF * @adapter: board private structure * * Verify that we have a valid config struct, and set up our netdev features * and our VSI struct. **/ -int i40evf_process_config(struct i40evf_adapter *adapter) +int iavf_process_config(struct iavf_adapter *adapter) { struct virtchnl_vf_resource *vfres = adapter->vf_res; int i, num_req_queues = adapter->num_req_queues; struct net_device *netdev = adapter->netdev; - struct i40e_vsi *vsi = &adapter->vsi; + struct iavf_vsi *vsi = &adapter->vsi; netdev_features_t hw_enc_features; netdev_features_t hw_features; @@ -3293,9 +3291,9 @@ int i40evf_process_config(struct i40evf_adapter *adapter) "Requested %d queues, but PF only gave us %d.\n", num_req_queues, adapter->vsi_res->num_queue_pairs); - adapter->flags |= I40EVF_FLAG_REINIT_ITR_NEEDED; + adapter->flags |= IAVF_FLAG_REINIT_ITR_NEEDED; adapter->num_req_queues = adapter->vsi_res->num_queue_pairs; - i40evf_schedule_reset(adapter); + iavf_schedule_reset(adapter); return -ENODEV; } adapter->num_req_queues = 0; @@ -3358,6 +3356,8 @@ int i40evf_process_config(struct i40evf_adapter *adapter) if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN) netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + netdev->priv_flags |= IFF_UNICAST_FLT; + /* Do not turn on offloads when they are requested to be turned off. * TSO needs minimum 576 bytes to work correctly. */ @@ -3380,22 +3380,22 @@ int i40evf_process_config(struct i40evf_adapter *adapter) adapter->vsi.back = adapter; adapter->vsi.base_vector = 1; - adapter->vsi.work_limit = I40E_DEFAULT_IRQ_WORK; + adapter->vsi.work_limit = IAVF_DEFAULT_IRQ_WORK; vsi->netdev = adapter->netdev; vsi->qs_handle = adapter->vsi_res->qset_handle; if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_RSS_PF) { adapter->rss_key_size = vfres->rss_key_size; adapter->rss_lut_size = vfres->rss_lut_size; } else { - adapter->rss_key_size = I40EVF_HKEY_ARRAY_SIZE; - adapter->rss_lut_size = I40EVF_HLUT_ARRAY_SIZE; + adapter->rss_key_size = IAVF_HKEY_ARRAY_SIZE; + adapter->rss_lut_size = IAVF_HLUT_ARRAY_SIZE; } return 0; } /** - * i40evf_init_task - worker thread to perform delayed initialization + * iavf_init_task - worker thread to perform delayed initialization * @work: pointer to work_struct containing our data * * This task completes the work that was begun in probe. Due to the nature @@ -3406,65 +3406,65 @@ int i40evf_process_config(struct i40evf_adapter *adapter) * communications with the PF driver and set up our netdev, the watchdog * takes over. **/ -static void i40evf_init_task(struct work_struct *work) +static void iavf_init_task(struct work_struct *work) { - struct i40evf_adapter *adapter = container_of(work, - struct i40evf_adapter, + struct iavf_adapter *adapter = container_of(work, + struct iavf_adapter, init_task.work); struct net_device *netdev = adapter->netdev; - struct i40e_hw *hw = &adapter->hw; + struct iavf_hw *hw = &adapter->hw; struct pci_dev *pdev = adapter->pdev; int err, bufsz; switch (adapter->state) { - case __I40EVF_STARTUP: + case __IAVF_STARTUP: /* driver loaded, probe complete */ - adapter->flags &= ~I40EVF_FLAG_PF_COMMS_FAILED; - adapter->flags &= ~I40EVF_FLAG_RESET_PENDING; - err = i40e_set_mac_type(hw); + adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED; + adapter->flags &= ~IAVF_FLAG_RESET_PENDING; + err = iavf_set_mac_type(hw); if (err) { dev_err(&pdev->dev, "Failed to set MAC type (%d)\n", err); goto err; } - err = i40evf_check_reset_complete(hw); + err = iavf_check_reset_complete(hw); if (err) { dev_info(&pdev->dev, "Device is still in reset (%d), retrying\n", err); goto err; } - hw->aq.num_arq_entries = I40EVF_AQ_LEN; - hw->aq.num_asq_entries = I40EVF_AQ_LEN; - hw->aq.arq_buf_size = I40EVF_MAX_AQ_BUF_SIZE; - hw->aq.asq_buf_size = I40EVF_MAX_AQ_BUF_SIZE; + hw->aq.num_arq_entries = IAVF_AQ_LEN; + hw->aq.num_asq_entries = IAVF_AQ_LEN; + hw->aq.arq_buf_size = IAVF_MAX_AQ_BUF_SIZE; + hw->aq.asq_buf_size = IAVF_MAX_AQ_BUF_SIZE; - err = i40evf_init_adminq(hw); + err = iavf_init_adminq(hw); if (err) { dev_err(&pdev->dev, "Failed to init Admin Queue (%d)\n", err); goto err; } - err = i40evf_send_api_ver(adapter); + err = iavf_send_api_ver(adapter); if (err) { dev_err(&pdev->dev, "Unable to send to PF (%d)\n", err); - i40evf_shutdown_adminq(hw); + iavf_shutdown_adminq(hw); goto err; } - adapter->state = __I40EVF_INIT_VERSION_CHECK; + adapter->state = __IAVF_INIT_VERSION_CHECK; goto restart; - case __I40EVF_INIT_VERSION_CHECK: - if (!i40evf_asq_done(hw)) { + case __IAVF_INIT_VERSION_CHECK: + if (!iavf_asq_done(hw)) { dev_err(&pdev->dev, "Admin queue command never completed\n"); - i40evf_shutdown_adminq(hw); - adapter->state = __I40EVF_STARTUP; + iavf_shutdown_adminq(hw); + adapter->state = __IAVF_STARTUP; goto err; } /* aq msg sent, awaiting reply */ - err = i40evf_verify_api_ver(adapter); + err = iavf_verify_api_ver(adapter); if (err) { if (err == I40E_ERR_ADMIN_QUEUE_NO_WORK) - err = i40evf_send_api_ver(adapter); + err = iavf_send_api_ver(adapter); else dev_err(&pdev->dev, "Unsupported PF API version %d.%d, expected %d.%d\n", adapter->pf_version.major, @@ -3473,34 +3473,34 @@ static void i40evf_init_task(struct work_struct *work) VIRTCHNL_VERSION_MINOR); goto err; } - err = i40evf_send_vf_config_msg(adapter); + err = iavf_send_vf_config_msg(adapter); if (err) { dev_err(&pdev->dev, "Unable to send config request (%d)\n", err); goto err; } - adapter->state = __I40EVF_INIT_GET_RESOURCES; + adapter->state = __IAVF_INIT_GET_RESOURCES; goto restart; - case __I40EVF_INIT_GET_RESOURCES: + case __IAVF_INIT_GET_RESOURCES: /* aq msg sent, awaiting reply */ if (!adapter->vf_res) { bufsz = sizeof(struct virtchnl_vf_resource) + - (I40E_MAX_VF_VSI * + (IAVF_MAX_VF_VSI * sizeof(struct virtchnl_vsi_resource)); adapter->vf_res = kzalloc(bufsz, GFP_KERNEL); if (!adapter->vf_res) goto err; } - err = i40evf_get_vf_config(adapter); + err = iavf_get_vf_config(adapter); if (err == I40E_ERR_ADMIN_QUEUE_NO_WORK) { - err = i40evf_send_vf_config_msg(adapter); + err = iavf_send_vf_config_msg(adapter); goto err; } else if (err == I40E_ERR_PARAM) { /* We only get ERR_PARAM if the device is in a very bad * state or if we've been disabled for previous bad * behavior. Either way, we're done now. */ - i40evf_shutdown_adminq(hw); + iavf_shutdown_adminq(hw); dev_err(&pdev->dev, "Unable to get VF config due to PF error condition, not retrying\n"); return; } @@ -3509,25 +3509,25 @@ static void i40evf_init_task(struct work_struct *work) err); goto err_alloc; } - adapter->state = __I40EVF_INIT_SW; + adapter->state = __IAVF_INIT_SW; break; default: goto err_alloc; } - if (i40evf_process_config(adapter)) + if (iavf_process_config(adapter)) goto err_alloc; adapter->current_op = VIRTCHNL_OP_UNKNOWN; - adapter->flags |= I40EVF_FLAG_RX_CSUM_ENABLED; + adapter->flags |= IAVF_FLAG_RX_CSUM_ENABLED; - netdev->netdev_ops = &i40evf_netdev_ops; - i40evf_set_ethtool_ops(netdev); + netdev->netdev_ops = &iavf_netdev_ops; + iavf_set_ethtool_ops(netdev); netdev->watchdog_timeo = 5 * HZ; /* MTU range: 68 - 9710 */ netdev->min_mtu = ETH_MIN_MTU; - netdev->max_mtu = I40E_MAX_RXBUFFER - I40E_PACKET_HDR_PAD; + netdev->max_mtu = IAVF_MAX_RXBUFFER - IAVF_PACKET_HDR_PAD; if (!is_valid_ether_addr(adapter->hw.mac.addr)) { dev_info(&pdev->dev, "Invalid MAC address %pM, using random\n", @@ -3535,25 +3535,25 @@ static void i40evf_init_task(struct work_struct *work) eth_hw_addr_random(netdev); ether_addr_copy(adapter->hw.mac.addr, netdev->dev_addr); } else { - adapter->flags |= I40EVF_FLAG_ADDR_SET_BY_PF; + adapter->flags |= IAVF_FLAG_ADDR_SET_BY_PF; ether_addr_copy(netdev->dev_addr, adapter->hw.mac.addr); ether_addr_copy(netdev->perm_addr, adapter->hw.mac.addr); } - timer_setup(&adapter->watchdog_timer, i40evf_watchdog_timer, 0); + timer_setup(&adapter->watchdog_timer, iavf_watchdog_timer, 0); mod_timer(&adapter->watchdog_timer, jiffies + 1); - adapter->tx_desc_count = I40EVF_DEFAULT_TXD; - adapter->rx_desc_count = I40EVF_DEFAULT_RXD; - err = i40evf_init_interrupt_scheme(adapter); + adapter->tx_desc_count = IAVF_DEFAULT_TXD; + adapter->rx_desc_count = IAVF_DEFAULT_RXD; + err = iavf_init_interrupt_scheme(adapter); if (err) goto err_sw_init; - i40evf_map_rings_to_vectors(adapter); + iavf_map_rings_to_vectors(adapter); if (adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_WB_ON_ITR) - adapter->flags |= I40EVF_FLAG_WB_ON_ITR_CAPABLE; + adapter->flags |= IAVF_FLAG_WB_ON_ITR_CAPABLE; - err = i40evf_request_misc_irq(adapter); + err = iavf_request_misc_irq(adapter); if (err) goto err_sw_init; @@ -3570,7 +3570,7 @@ static void i40evf_init_task(struct work_struct *work) netif_tx_stop_all_queues(netdev); if (CLIENT_ALLOWED(adapter)) { - err = i40evf_lan_add_device(adapter); + err = iavf_lan_add_device(adapter); if (err) dev_info(&pdev->dev, "Failed to add VF to client API service list: %d\n", err); @@ -3580,9 +3580,9 @@ static void i40evf_init_task(struct work_struct *work) if (netdev->features & NETIF_F_GRO) dev_info(&pdev->dev, "GRO is enabled\n"); - adapter->state = __I40EVF_DOWN; - set_bit(__I40E_VSI_DOWN, adapter->vsi.state); - i40evf_misc_irq_enable(adapter); + adapter->state = __IAVF_DOWN; + set_bit(__IAVF_VSI_DOWN, adapter->vsi.state); + iavf_misc_irq_enable(adapter); wake_up(&adapter->down_waitqueue); adapter->rss_key = kzalloc(adapter->rss_key_size, GFP_KERNEL); @@ -3591,31 +3591,31 @@ static void i40evf_init_task(struct work_struct *work) goto err_mem; if (RSS_AQ(adapter)) { - adapter->aq_required |= I40EVF_FLAG_AQ_CONFIGURE_RSS; + adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_RSS; mod_timer_pending(&adapter->watchdog_timer, jiffies + 1); } else { - i40evf_init_rss(adapter); + iavf_init_rss(adapter); } return; restart: schedule_delayed_work(&adapter->init_task, msecs_to_jiffies(30)); return; err_mem: - i40evf_free_rss(adapter); + iavf_free_rss(adapter); err_register: - i40evf_free_misc_irq(adapter); + iavf_free_misc_irq(adapter); err_sw_init: - i40evf_reset_interrupt_capability(adapter); + iavf_reset_interrupt_capability(adapter); err_alloc: kfree(adapter->vf_res); adapter->vf_res = NULL; err: /* Things went into the weeds, so try again later */ - if (++adapter->aq_wait_count > I40EVF_AQ_MAX_ERR) { + if (++adapter->aq_wait_count > IAVF_AQ_MAX_ERR) { dev_err(&pdev->dev, "Failed to communicate with PF; waiting before retry\n"); - adapter->flags |= I40EVF_FLAG_PF_COMMS_FAILED; - i40evf_shutdown_adminq(hw); - adapter->state = __I40EVF_STARTUP; + adapter->flags |= IAVF_FLAG_PF_COMMS_FAILED; + iavf_shutdown_adminq(hw); + adapter->state = __IAVF_STARTUP; schedule_delayed_work(&adapter->init_task, HZ * 5); return; } @@ -3623,21 +3623,21 @@ err: } /** - * i40evf_shutdown - Shutdown the device in preparation for a reboot + * iavf_shutdown - Shutdown the device in preparation for a reboot * @pdev: pci device structure **/ -static void i40evf_shutdown(struct pci_dev *pdev) +static void iavf_shutdown(struct pci_dev *pdev) { struct net_device *netdev = pci_get_drvdata(pdev); - struct i40evf_adapter *adapter = netdev_priv(netdev); + struct iavf_adapter *adapter = netdev_priv(netdev); netif_device_detach(netdev); if (netif_running(netdev)) - i40evf_close(netdev); + iavf_close(netdev); /* Prevent the watchdog from running. */ - adapter->state = __I40EVF_REMOVE; + adapter->state = __IAVF_REMOVE; adapter->aq_required = 0; #ifdef CONFIG_PM @@ -3648,21 +3648,21 @@ static void i40evf_shutdown(struct pci_dev *pdev) } /** - * i40evf_probe - Device Initialization Routine + * iavf_probe - Device Initialization Routine * @pdev: PCI device information struct - * @ent: entry in i40evf_pci_tbl + * @ent: entry in iavf_pci_tbl * * Returns 0 on success, negative on failure * - * i40evf_probe initializes an adapter identified by a pci_dev structure. + * iavf_probe initializes an adapter identified by a pci_dev structure. * The OS initialization, configuring of the adapter private structure, * and a hardware reset occur. **/ -static int i40evf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) +static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { struct net_device *netdev; - struct i40evf_adapter *adapter = NULL; - struct i40e_hw *hw = NULL; + struct iavf_adapter *adapter = NULL; + struct iavf_hw *hw = NULL; int err; err = pci_enable_device(pdev); @@ -3679,7 +3679,7 @@ static int i40evf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) } } - err = pci_request_regions(pdev, i40evf_driver_name); + err = pci_request_regions(pdev, iavf_driver_name); if (err) { dev_err(&pdev->dev, "pci_request_regions failed 0x%x\n", err); @@ -3690,8 +3690,8 @@ static int i40evf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pci_set_master(pdev); - netdev = alloc_etherdev_mq(sizeof(struct i40evf_adapter), - I40EVF_MAX_REQ_QUEUES); + netdev = alloc_etherdev_mq(sizeof(struct iavf_adapter), + IAVF_MAX_REQ_QUEUES); if (!netdev) { err = -ENOMEM; goto err_alloc_etherdev; @@ -3709,7 +3709,7 @@ static int i40evf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) hw->back = adapter; adapter->msg_enable = BIT(DEFAULT_DEBUG_LEVEL_SHIFT) - 1; - adapter->state = __I40EVF_STARTUP; + adapter->state = __IAVF_STARTUP; /* Call save state here because it relies on the adapter struct. */ pci_save_state(pdev); @@ -3742,11 +3742,11 @@ static int i40evf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) INIT_LIST_HEAD(&adapter->vlan_filter_list); INIT_LIST_HEAD(&adapter->cloud_filter_list); - INIT_WORK(&adapter->reset_task, i40evf_reset_task); - INIT_WORK(&adapter->adminq_task, i40evf_adminq_task); - INIT_WORK(&adapter->watchdog_task, i40evf_watchdog_task); - INIT_DELAYED_WORK(&adapter->client_task, i40evf_client_task); - INIT_DELAYED_WORK(&adapter->init_task, i40evf_init_task); + INIT_WORK(&adapter->reset_task, iavf_reset_task); + INIT_WORK(&adapter->adminq_task, iavf_adminq_task); + INIT_WORK(&adapter->watchdog_task, iavf_watchdog_task); + INIT_DELAYED_WORK(&adapter->client_task, iavf_client_task); + INIT_DELAYED_WORK(&adapter->init_task, iavf_init_task); schedule_delayed_work(&adapter->init_task, msecs_to_jiffies(5 * (pdev->devfn & 0x07))); @@ -3767,33 +3767,33 @@ err_dma: #ifdef CONFIG_PM /** - * i40evf_suspend - Power management suspend routine + * iavf_suspend - Power management suspend routine * @pdev: PCI device information struct * @state: unused * * Called when the system (VM) is entering sleep/suspend. **/ -static int i40evf_suspend(struct pci_dev *pdev, pm_message_t state) +static int iavf_suspend(struct pci_dev *pdev, pm_message_t state) { struct net_device *netdev = pci_get_drvdata(pdev); - struct i40evf_adapter *adapter = netdev_priv(netdev); + struct iavf_adapter *adapter = netdev_priv(netdev); int retval = 0; netif_device_detach(netdev); - while (test_and_set_bit(__I40EVF_IN_CRITICAL_TASK, + while (test_and_set_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section)) usleep_range(500, 1000); if (netif_running(netdev)) { rtnl_lock(); - i40evf_down(adapter); + iavf_down(adapter); rtnl_unlock(); } - i40evf_free_misc_irq(adapter); - i40evf_reset_interrupt_capability(adapter); + iavf_free_misc_irq(adapter); + iavf_reset_interrupt_capability(adapter); - clear_bit(__I40EVF_IN_CRITICAL_TASK, &adapter->crit_section); + clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); retval = pci_save_state(pdev); if (retval) @@ -3805,14 +3805,14 @@ static int i40evf_suspend(struct pci_dev *pdev, pm_message_t state) } /** - * i40evf_resume - Power management resume routine + * iavf_resume - Power management resume routine * @pdev: PCI device information struct * * Called when the system (VM) is resumed from sleep/suspend. **/ -static int i40evf_resume(struct pci_dev *pdev) +static int iavf_resume(struct pci_dev *pdev) { - struct i40evf_adapter *adapter = pci_get_drvdata(pdev); + struct iavf_adapter *adapter = pci_get_drvdata(pdev); struct net_device *netdev = adapter->netdev; u32 err; @@ -3831,13 +3831,13 @@ static int i40evf_resume(struct pci_dev *pdev) pci_set_master(pdev); rtnl_lock(); - err = i40evf_set_interrupt_capability(adapter); + err = iavf_set_interrupt_capability(adapter); if (err) { rtnl_unlock(); dev_err(&pdev->dev, "Cannot enable MSI-X interrupts.\n"); return err; } - err = i40evf_request_misc_irq(adapter); + err = iavf_request_misc_irq(adapter); rtnl_unlock(); if (err) { dev_err(&pdev->dev, "Cannot get interrupt vector.\n"); @@ -3853,25 +3853,25 @@ static int i40evf_resume(struct pci_dev *pdev) #endif /* CONFIG_PM */ /** - * i40evf_remove - Device Removal Routine + * iavf_remove - Device Removal Routine * @pdev: PCI device information struct * - * i40evf_remove is called by the PCI subsystem to alert the driver + * iavf_remove is called by the PCI subsystem to alert the driver * that it should release a PCI device. The could be caused by a * Hot-Plug event, or because the driver is going to be removed from * memory. **/ -static void i40evf_remove(struct pci_dev *pdev) +static void iavf_remove(struct pci_dev *pdev) { struct net_device *netdev = pci_get_drvdata(pdev); - struct i40evf_adapter *adapter = netdev_priv(netdev); - struct i40evf_vlan_filter *vlf, *vlftmp; - struct i40evf_mac_filter *f, *ftmp; - struct i40evf_cloud_filter *cf, *cftmp; - struct i40e_hw *hw = &adapter->hw; + struct iavf_adapter *adapter = netdev_priv(netdev); + struct iavf_vlan_filter *vlf, *vlftmp; + struct iavf_mac_filter *f, *ftmp; + struct iavf_cloud_filter *cf, *cftmp; + struct iavf_hw *hw = &adapter->hw; int err; /* Indicate we are in remove and not to run reset_task */ - set_bit(__I40EVF_IN_REMOVE_TASK, &adapter->crit_section); + set_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section); cancel_delayed_work_sync(&adapter->init_task); cancel_work_sync(&adapter->reset_task); cancel_delayed_work_sync(&adapter->client_task); @@ -3880,37 +3880,39 @@ static void i40evf_remove(struct pci_dev *pdev) adapter->netdev_registered = false; } if (CLIENT_ALLOWED(adapter)) { - err = i40evf_lan_del_device(adapter); + err = iavf_lan_del_device(adapter); if (err) dev_warn(&pdev->dev, "Failed to delete client device: %d\n", err); } /* Shut down all the garbage mashers on the detention level */ - adapter->state = __I40EVF_REMOVE; + adapter->state = __IAVF_REMOVE; adapter->aq_required = 0; - adapter->flags &= ~I40EVF_FLAG_REINIT_ITR_NEEDED; - i40evf_request_reset(adapter); + adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; + iavf_request_reset(adapter); msleep(50); /* If the FW isn't responding, kick it once, but only once. */ - if (!i40evf_asq_done(hw)) { - i40evf_request_reset(adapter); + if (!iavf_asq_done(hw)) { + iavf_request_reset(adapter); msleep(50); } - i40evf_free_all_tx_resources(adapter); - i40evf_free_all_rx_resources(adapter); - i40evf_misc_irq_disable(adapter); - i40evf_free_misc_irq(adapter); - i40evf_reset_interrupt_capability(adapter); - i40evf_free_q_vectors(adapter); + iavf_free_all_tx_resources(adapter); + iavf_free_all_rx_resources(adapter); + iavf_misc_irq_disable(adapter); + iavf_free_misc_irq(adapter); + iavf_reset_interrupt_capability(adapter); + iavf_free_q_vectors(adapter); if (adapter->watchdog_timer.function) del_timer_sync(&adapter->watchdog_timer); - i40evf_free_rss(adapter); + cancel_work_sync(&adapter->adminq_task); + + iavf_free_rss(adapter); if (hw->aq.asq.count) - i40evf_shutdown_adminq(hw); + iavf_shutdown_adminq(hw); /* destroy the locks only once, here */ mutex_destroy(&hw->aq.arq_mutex); @@ -3918,9 +3920,9 @@ static void i40evf_remove(struct pci_dev *pdev) iounmap(hw->hw_addr); pci_release_regions(pdev); - i40evf_free_all_tx_resources(adapter); - i40evf_free_all_rx_resources(adapter); - i40evf_free_queues(adapter); + iavf_free_all_tx_resources(adapter); + iavf_free_all_rx_resources(adapter); + iavf_free_queues(adapter); kfree(adapter->vf_res); spin_lock_bh(&adapter->mac_vlan_list_lock); /* If we got removed before an up/down sequence, we've got a filter @@ -3952,57 +3954,57 @@ static void i40evf_remove(struct pci_dev *pdev) pci_disable_device(pdev); } -static struct pci_driver i40evf_driver = { - .name = i40evf_driver_name, - .id_table = i40evf_pci_tbl, - .probe = i40evf_probe, - .remove = i40evf_remove, +static struct pci_driver iavf_driver = { + .name = iavf_driver_name, + .id_table = iavf_pci_tbl, + .probe = iavf_probe, + .remove = iavf_remove, #ifdef CONFIG_PM - .suspend = i40evf_suspend, - .resume = i40evf_resume, + .suspend = iavf_suspend, + .resume = iavf_resume, #endif - .shutdown = i40evf_shutdown, + .shutdown = iavf_shutdown, }; /** - * i40e_init_module - Driver Registration Routine + * iavf_init_module - Driver Registration Routine * - * i40e_init_module is the first routine called when the driver is + * iavf_init_module is the first routine called when the driver is * loaded. All it does is register with the PCI subsystem. **/ -static int __init i40evf_init_module(void) +static int __init iavf_init_module(void) { int ret; - pr_info("i40evf: %s - version %s\n", i40evf_driver_string, - i40evf_driver_version); + pr_info("iavf: %s - version %s\n", iavf_driver_string, + iavf_driver_version); - pr_info("%s\n", i40evf_copyright); + pr_info("%s\n", iavf_copyright); - i40evf_wq = alloc_workqueue("%s", WQ_UNBOUND | WQ_MEM_RECLAIM, 1, - i40evf_driver_name); - if (!i40evf_wq) { - pr_err("%s: Failed to create workqueue\n", i40evf_driver_name); + iavf_wq = alloc_workqueue("%s", WQ_UNBOUND | WQ_MEM_RECLAIM, 1, + iavf_driver_name); + if (!iavf_wq) { + pr_err("%s: Failed to create workqueue\n", iavf_driver_name); return -ENOMEM; } - ret = pci_register_driver(&i40evf_driver); + ret = pci_register_driver(&iavf_driver); return ret; } -module_init(i40evf_init_module); +module_init(iavf_init_module); /** - * i40e_exit_module - Driver Exit Cleanup Routine + * iavf_exit_module - Driver Exit Cleanup Routine * - * i40e_exit_module is called just before the driver is removed + * iavf_exit_module is called just before the driver is removed * from memory. **/ -static void __exit i40evf_exit_module(void) +static void __exit iavf_exit_module(void) { - pci_unregister_driver(&i40evf_driver); - destroy_workqueue(i40evf_wq); + pci_unregister_driver(&iavf_driver); + destroy_workqueue(iavf_wq); } -module_exit(i40evf_exit_module); +module_exit(iavf_exit_module); -/* i40evf_main.c */ +/* iavf_main.c */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_osdep.h b/drivers/net/ethernet/intel/iavf/iavf_osdep.h index 3ddddb46455b..e6e0b0328706 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_osdep.h +++ b/drivers/net/ethernet/intel/iavf/iavf_osdep.h @@ -1,8 +1,8 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright(c) 2013 - 2018 Intel Corporation. */ -#ifndef _I40E_OSDEP_H_ -#define _I40E_OSDEP_H_ +#ifndef _IAVF_OSDEP_H_ +#define _IAVF_OSDEP_H_ #include <linux/types.h> #include <linux/if_ether.h> @@ -24,29 +24,29 @@ #define wr64(a, reg, value) writeq((value), ((a)->hw_addr + (reg))) #define rd64(a, reg) readq((a)->hw_addr + (reg)) -#define i40e_flush(a) readl((a)->hw_addr + I40E_VFGEN_RSTAT) +#define iavf_flush(a) readl((a)->hw_addr + IAVF_VFGEN_RSTAT) /* memory allocation tracking */ -struct i40e_dma_mem { +struct iavf_dma_mem { void *va; dma_addr_t pa; u32 size; }; -#define i40e_allocate_dma_mem(h, m, unused, s, a) \ - i40evf_allocate_dma_mem_d(h, m, s, a) -#define i40e_free_dma_mem(h, m) i40evf_free_dma_mem_d(h, m) +#define iavf_allocate_dma_mem(h, m, unused, s, a) \ + iavf_allocate_dma_mem_d(h, m, s, a) +#define iavf_free_dma_mem(h, m) iavf_free_dma_mem_d(h, m) -struct i40e_virt_mem { +struct iavf_virt_mem { void *va; u32 size; }; -#define i40e_allocate_virt_mem(h, m, s) i40evf_allocate_virt_mem_d(h, m, s) -#define i40e_free_virt_mem(h, m) i40evf_free_virt_mem_d(h, m) +#define iavf_allocate_virt_mem(h, m, s) iavf_allocate_virt_mem_d(h, m, s) +#define iavf_free_virt_mem(h, m) iavf_free_virt_mem_d(h, m) -#define i40e_debug(h, m, s, ...) i40evf_debug_d(h, m, s, ##__VA_ARGS__) -extern void i40evf_debug_d(void *hw, u32 mask, char *fmt_str, ...) +#define iavf_debug(h, m, s, ...) iavf_debug_d(h, m, s, ##__VA_ARGS__) +extern void iavf_debug_d(void *hw, u32 mask, char *fmt_str, ...) __attribute__ ((format(gnu_printf, 3, 4))); -typedef enum i40e_status_code i40e_status; -#endif /* _I40E_OSDEP_H_ */ +typedef enum iavf_status_code iavf_status; +#endif /* _IAVF_OSDEP_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_prototype.h b/drivers/net/ethernet/intel/iavf/iavf_prototype.h new file mode 100644 index 000000000000..d6685103af39 --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_prototype.h @@ -0,0 +1,67 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#ifndef _IAVF_PROTOTYPE_H_ +#define _IAVF_PROTOTYPE_H_ + +#include "iavf_type.h" +#include "iavf_alloc.h" +#include <linux/avf/virtchnl.h> + +/* Prototypes for shared code functions that are not in + * the standard function pointer structures. These are + * mostly because they are needed even before the init + * has happened and will assist in the early SW and FW + * setup. + */ + +/* adminq functions */ +iavf_status iavf_init_adminq(struct iavf_hw *hw); +iavf_status iavf_shutdown_adminq(struct iavf_hw *hw); +void i40e_adminq_init_ring_data(struct iavf_hw *hw); +iavf_status iavf_clean_arq_element(struct iavf_hw *hw, + struct i40e_arq_event_info *e, + u16 *events_pending); +iavf_status iavf_asq_send_command(struct iavf_hw *hw, struct i40e_aq_desc *desc, + void *buff, /* can be NULL */ + u16 buff_size, + struct i40e_asq_cmd_details *cmd_details); +bool iavf_asq_done(struct iavf_hw *hw); + +/* debug function for adminq */ +void iavf_debug_aq(struct iavf_hw *hw, enum iavf_debug_mask mask, + void *desc, void *buffer, u16 buf_len); + +void i40e_idle_aq(struct iavf_hw *hw); +void iavf_resume_aq(struct iavf_hw *hw); +bool iavf_check_asq_alive(struct iavf_hw *hw); +iavf_status iavf_aq_queue_shutdown(struct iavf_hw *hw, bool unloading); +const char *iavf_aq_str(struct iavf_hw *hw, enum i40e_admin_queue_err aq_err); +const char *iavf_stat_str(struct iavf_hw *hw, iavf_status stat_err); + +iavf_status iavf_aq_get_rss_lut(struct iavf_hw *hw, u16 seid, + bool pf_lut, u8 *lut, u16 lut_size); +iavf_status iavf_aq_set_rss_lut(struct iavf_hw *hw, u16 seid, + bool pf_lut, u8 *lut, u16 lut_size); +iavf_status iavf_aq_get_rss_key(struct iavf_hw *hw, u16 seid, + struct i40e_aqc_get_set_rss_key_data *key); +iavf_status iavf_aq_set_rss_key(struct iavf_hw *hw, u16 seid, + struct i40e_aqc_get_set_rss_key_data *key); + +iavf_status iavf_set_mac_type(struct iavf_hw *hw); + +extern struct iavf_rx_ptype_decoded iavf_ptype_lookup[]; + +static inline struct iavf_rx_ptype_decoded decode_rx_desc_ptype(u8 ptype) +{ + return iavf_ptype_lookup[ptype]; +} + +void iavf_vf_parse_hw_config(struct iavf_hw *hw, + struct virtchnl_vf_resource *msg); +iavf_status iavf_vf_reset(struct iavf_hw *hw); +iavf_status iavf_aq_send_msg_to_pf(struct iavf_hw *hw, + enum virtchnl_ops v_opcode, + iavf_status v_retval, u8 *msg, u16 msglen, + struct i40e_asq_cmd_details *cmd_details); +#endif /* _IAVF_PROTOTYPE_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_register.h b/drivers/net/ethernet/intel/iavf/iavf_register.h new file mode 100644 index 000000000000..bf793332fc9d --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_register.h @@ -0,0 +1,68 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#ifndef _IAVF_REGISTER_H_ +#define _IAVF_REGISTER_H_ + +#define IAVF_VF_ARQBAH1 0x00006000 /* Reset: EMPR */ +#define IAVF_VF_ARQBAL1 0x00006C00 /* Reset: EMPR */ +#define IAVF_VF_ARQH1 0x00007400 /* Reset: EMPR */ +#define IAVF_VF_ARQH1_ARQH_SHIFT 0 +#define IAVF_VF_ARQH1_ARQH_MASK IAVF_MASK(0x3FF, IAVF_VF_ARQH1_ARQH_SHIFT) +#define IAVF_VF_ARQLEN1 0x00008000 /* Reset: EMPR */ +#define IAVF_VF_ARQLEN1_ARQVFE_SHIFT 28 +#define IAVF_VF_ARQLEN1_ARQVFE_MASK IAVF_MASK(0x1, IAVF_VF_ARQLEN1_ARQVFE_SHIFT) +#define IAVF_VF_ARQLEN1_ARQOVFL_SHIFT 29 +#define IAVF_VF_ARQLEN1_ARQOVFL_MASK IAVF_MASK(0x1, IAVF_VF_ARQLEN1_ARQOVFL_SHIFT) +#define IAVF_VF_ARQLEN1_ARQCRIT_SHIFT 30 +#define IAVF_VF_ARQLEN1_ARQCRIT_MASK IAVF_MASK(0x1, IAVF_VF_ARQLEN1_ARQCRIT_SHIFT) +#define IAVF_VF_ARQLEN1_ARQENABLE_SHIFT 31 +#define IAVF_VF_ARQLEN1_ARQENABLE_MASK IAVF_MASK(0x1, IAVF_VF_ARQLEN1_ARQENABLE_SHIFT) +#define IAVF_VF_ARQT1 0x00007000 /* Reset: EMPR */ +#define IAVF_VF_ATQBAH1 0x00007800 /* Reset: EMPR */ +#define IAVF_VF_ATQBAL1 0x00007C00 /* Reset: EMPR */ +#define IAVF_VF_ATQH1 0x00006400 /* Reset: EMPR */ +#define IAVF_VF_ATQLEN1 0x00006800 /* Reset: EMPR */ +#define IAVF_VF_ATQLEN1_ATQVFE_SHIFT 28 +#define IAVF_VF_ATQLEN1_ATQVFE_MASK IAVF_MASK(0x1, IAVF_VF_ATQLEN1_ATQVFE_SHIFT) +#define IAVF_VF_ATQLEN1_ATQOVFL_SHIFT 29 +#define IAVF_VF_ATQLEN1_ATQOVFL_MASK IAVF_MASK(0x1, IAVF_VF_ATQLEN1_ATQOVFL_SHIFT) +#define IAVF_VF_ATQLEN1_ATQCRIT_SHIFT 30 +#define IAVF_VF_ATQLEN1_ATQCRIT_MASK IAVF_MASK(0x1, IAVF_VF_ATQLEN1_ATQCRIT_SHIFT) +#define IAVF_VF_ATQLEN1_ATQENABLE_SHIFT 31 +#define IAVF_VF_ATQLEN1_ATQENABLE_MASK IAVF_MASK(0x1, IAVF_VF_ATQLEN1_ATQENABLE_SHIFT) +#define IAVF_VF_ATQT1 0x00008400 /* Reset: EMPR */ +#define IAVF_VFGEN_RSTAT 0x00008800 /* Reset: VFR */ +#define IAVF_VFGEN_RSTAT_VFR_STATE_SHIFT 0 +#define IAVF_VFGEN_RSTAT_VFR_STATE_MASK IAVF_MASK(0x3, IAVF_VFGEN_RSTAT_VFR_STATE_SHIFT) +#define IAVF_VFINT_DYN_CTL01 0x00005C00 /* Reset: VFR */ +#define IAVF_VFINT_DYN_CTL01_INTENA_SHIFT 0 +#define IAVF_VFINT_DYN_CTL01_INTENA_MASK IAVF_MASK(0x1, IAVF_VFINT_DYN_CTL01_INTENA_SHIFT) +#define IAVF_VFINT_DYN_CTL01_ITR_INDX_SHIFT 3 +#define IAVF_VFINT_DYN_CTL01_ITR_INDX_MASK IAVF_MASK(0x3, IAVF_VFINT_DYN_CTL01_ITR_INDX_SHIFT) +#define IAVF_VFINT_DYN_CTLN1(_INTVF) (0x00003800 + ((_INTVF) * 4)) /* _i=0...15 */ /* Reset: VFR */ +#define IAVF_VFINT_DYN_CTLN1_INTENA_SHIFT 0 +#define IAVF_VFINT_DYN_CTLN1_INTENA_MASK IAVF_MASK(0x1, IAVF_VFINT_DYN_CTLN1_INTENA_SHIFT) +#define IAVF_VFINT_DYN_CTLN1_SWINT_TRIG_SHIFT 2 +#define IAVF_VFINT_DYN_CTLN1_SWINT_TRIG_MASK IAVF_MASK(0x1, IAVF_VFINT_DYN_CTLN1_SWINT_TRIG_SHIFT) +#define IAVF_VFINT_DYN_CTLN1_ITR_INDX_SHIFT 3 +#define IAVF_VFINT_DYN_CTLN1_ITR_INDX_MASK IAVF_MASK(0x3, IAVF_VFINT_DYN_CTLN1_ITR_INDX_SHIFT) +#define IAVF_VFINT_DYN_CTLN1_INTERVAL_SHIFT 5 +#define IAVF_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_SHIFT 24 +#define IAVF_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_MASK IAVF_MASK(0x1, IAVF_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_SHIFT) +#define IAVF_VFINT_ICR0_ENA1 0x00005000 /* Reset: CORER */ +#define IAVF_VFINT_ICR0_ENA1_ADMINQ_SHIFT 30 +#define IAVF_VFINT_ICR0_ENA1_ADMINQ_MASK IAVF_MASK(0x1, IAVF_VFINT_ICR0_ENA1_ADMINQ_SHIFT) +#define IAVF_VFINT_ICR0_ENA1_RSVD_SHIFT 31 +#define IAVF_VFINT_ICR01 0x00004800 /* Reset: CORER */ +#define IAVF_VFINT_ITRN1(_i, _INTVF) (0x00002800 + ((_i) * 64 + (_INTVF) * 4)) /* _i=0...2, _INTVF=0...15 */ /* Reset: VFR */ +#define IAVF_QRX_TAIL1(_Q) (0x00002000 + ((_Q) * 4)) /* _i=0...15 */ /* Reset: CORER */ +#define IAVF_QTX_TAIL1(_Q) (0x00000000 + ((_Q) * 4)) /* _i=0...15 */ /* Reset: PFR */ +#define IAVF_VFQF_HENA(_i) (0x0000C400 + ((_i) * 4)) /* _i=0...1 */ /* Reset: CORER */ +#define IAVF_VFQF_HKEY(_i) (0x0000CC00 + ((_i) * 4)) /* _i=0...12 */ /* Reset: CORER */ +#define IAVF_VFQF_HKEY_MAX_INDEX 12 +#define IAVF_VFQF_HLUT(_i) (0x0000D000 + ((_i) * 4)) /* _i=0...15 */ /* Reset: CORER */ +#define IAVF_VFQF_HLUT_MAX_INDEX 15 +#define IAVF_VFINT_DYN_CTLN1_WB_ON_ITR_SHIFT 30 +#define IAVF_VFINT_DYN_CTLN1_WB_ON_ITR_MASK IAVF_MASK(0x1, IAVF_VFINT_DYN_CTLN1_WB_ON_ITR_SHIFT) +#endif /* _IAVF_REGISTER_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_status.h b/drivers/net/ethernet/intel/iavf/iavf_status.h index 77be0702d07c..46742fab7b8c 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_status.h +++ b/drivers/net/ethernet/intel/iavf/iavf_status.h @@ -1,11 +1,11 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright(c) 2013 - 2018 Intel Corporation. */ -#ifndef _I40E_STATUS_H_ -#define _I40E_STATUS_H_ +#ifndef _IAVF_STATUS_H_ +#define _IAVF_STATUS_H_ /* Error Codes */ -enum i40e_status_code { +enum iavf_status_code { I40E_SUCCESS = 0, I40E_ERR_NVM = -1, I40E_ERR_NVM_CHECKSUM = -2, @@ -75,4 +75,4 @@ enum i40e_status_code { I40E_ERR_ADMIN_QUEUE_CRITICAL_ERROR = -66, }; -#endif /* _I40E_STATUS_H_ */ +#endif /* _IAVF_STATUS_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_trace.h b/drivers/net/ethernet/intel/iavf/iavf_trace.h index d7a4e68820a8..1474f5539751 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_trace.h +++ b/drivers/net/ethernet/intel/iavf/iavf_trace.h @@ -3,16 +3,16 @@ /* Modeled on trace-events-sample.h */ -/* The trace subsystem name for i40evf will be "i40evf". +/* The trace subsystem name for iavf will be "iavf". * - * This file is named i40e_trace.h. + * This file is named iavf_trace.h. * * Since this include file's name is different from the trace * subsystem name, we'll have to define TRACE_INCLUDE_FILE at the end * of this file. */ #undef TRACE_SYSTEM -#define TRACE_SYSTEM i40evf +#define TRACE_SYSTEM iavf /* See trace-events-sample.h for a detailed description of why this * guard clause is different from most normal include files. @@ -23,14 +23,14 @@ #include <linux/tracepoint.h> /** - * i40e_trace() macro enables shared code to refer to trace points + * iavf_trace() macro enables shared code to refer to trace points * like: * - * trace_i40e{,vf}_example(args...) + * trace_iavf{,vf}_example(args...) * * ... as: * - * i40e_trace(example, args...) + * iavf_trace(example, args...) * * ... to resolve to the PF or VF version of the tracepoint without * ifdefs, and to allow tracepoints to be disabled entirely at build @@ -39,29 +39,29 @@ * Trace point should always be referred to in the driver via this * macro. * - * Similarly, i40e_trace_enabled(trace_name) wraps references to - * trace_i40e{,vf}_<trace_name>_enabled() functions. + * Similarly, iavf_trace_enabled(trace_name) wraps references to + * trace_iavf{,vf}_<trace_name>_enabled() functions. */ -#define _I40E_TRACE_NAME(trace_name) (trace_ ## i40evf ## _ ## trace_name) -#define I40E_TRACE_NAME(trace_name) _I40E_TRACE_NAME(trace_name) +#define _IAVF_TRACE_NAME(trace_name) (trace_ ## iavf ## _ ## trace_name) +#define IAVF_TRACE_NAME(trace_name) _IAVF_TRACE_NAME(trace_name) -#define i40e_trace(trace_name, args...) I40E_TRACE_NAME(trace_name)(args) +#define iavf_trace(trace_name, args...) IAVF_TRACE_NAME(trace_name)(args) -#define i40e_trace_enabled(trace_name) I40E_TRACE_NAME(trace_name##_enabled)() +#define iavf_trace_enabled(trace_name) IAVF_TRACE_NAME(trace_name##_enabled)() /* Events common to PF and VF. Corresponding versions will be defined - * for both, named trace_i40e_* and trace_i40evf_*. The i40e_trace() + * for both, named trace_iavf_* and trace_iavf_*. The iavf_trace() * macro above will select the right trace point name for the driver * being built from shared code. */ /* Events related to a vsi & ring */ DECLARE_EVENT_CLASS( - i40evf_tx_template, + iavf_tx_template, - TP_PROTO(struct i40e_ring *ring, - struct i40e_tx_desc *desc, - struct i40e_tx_buffer *buf), + TP_PROTO(struct iavf_ring *ring, + struct iavf_tx_desc *desc, + struct iavf_tx_buffer *buf), TP_ARGS(ring, desc, buf), @@ -93,26 +93,26 @@ DECLARE_EVENT_CLASS( ); DEFINE_EVENT( - i40evf_tx_template, i40evf_clean_tx_irq, - TP_PROTO(struct i40e_ring *ring, - struct i40e_tx_desc *desc, - struct i40e_tx_buffer *buf), + iavf_tx_template, iavf_clean_tx_irq, + TP_PROTO(struct iavf_ring *ring, + struct iavf_tx_desc *desc, + struct iavf_tx_buffer *buf), TP_ARGS(ring, desc, buf)); DEFINE_EVENT( - i40evf_tx_template, i40evf_clean_tx_irq_unmap, - TP_PROTO(struct i40e_ring *ring, - struct i40e_tx_desc *desc, - struct i40e_tx_buffer *buf), + iavf_tx_template, iavf_clean_tx_irq_unmap, + TP_PROTO(struct iavf_ring *ring, + struct iavf_tx_desc *desc, + struct iavf_tx_buffer *buf), TP_ARGS(ring, desc, buf)); DECLARE_EVENT_CLASS( - i40evf_rx_template, + iavf_rx_template, - TP_PROTO(struct i40e_ring *ring, - union i40e_32byte_rx_desc *desc, + TP_PROTO(struct iavf_ring *ring, + union iavf_32byte_rx_desc *desc, struct sk_buff *skb), TP_ARGS(ring, desc, skb), @@ -138,26 +138,26 @@ DECLARE_EVENT_CLASS( ); DEFINE_EVENT( - i40evf_rx_template, i40evf_clean_rx_irq, - TP_PROTO(struct i40e_ring *ring, - union i40e_32byte_rx_desc *desc, + iavf_rx_template, iavf_clean_rx_irq, + TP_PROTO(struct iavf_ring *ring, + union iavf_32byte_rx_desc *desc, struct sk_buff *skb), TP_ARGS(ring, desc, skb)); DEFINE_EVENT( - i40evf_rx_template, i40evf_clean_rx_irq_rx, - TP_PROTO(struct i40e_ring *ring, - union i40e_32byte_rx_desc *desc, + iavf_rx_template, iavf_clean_rx_irq_rx, + TP_PROTO(struct iavf_ring *ring, + union iavf_32byte_rx_desc *desc, struct sk_buff *skb), TP_ARGS(ring, desc, skb)); DECLARE_EVENT_CLASS( - i40evf_xmit_template, + iavf_xmit_template, TP_PROTO(struct sk_buff *skb, - struct i40e_ring *ring), + struct iavf_ring *ring), TP_ARGS(skb, ring), @@ -180,23 +180,23 @@ DECLARE_EVENT_CLASS( ); DEFINE_EVENT( - i40evf_xmit_template, i40evf_xmit_frame_ring, + iavf_xmit_template, iavf_xmit_frame_ring, TP_PROTO(struct sk_buff *skb, - struct i40e_ring *ring), + struct iavf_ring *ring), TP_ARGS(skb, ring)); DEFINE_EVENT( - i40evf_xmit_template, i40evf_xmit_frame_ring_drop, + iavf_xmit_template, iavf_xmit_frame_ring_drop, TP_PROTO(struct sk_buff *skb, - struct i40e_ring *ring), + struct iavf_ring *ring), TP_ARGS(skb, ring)); /* Events unique to the VF. */ -#endif /* _I40E_TRACE_H_ */ -/* This must be outside ifdef _I40E_TRACE_H */ +#endif /* _IAVF_TRACE_H_ */ +/* This must be outside ifdef _IAVF_TRACE_H */ /* This trace include file is not located in the .../include/trace * with the kernel tracepoint definitions, because we're a loadable @@ -205,5 +205,5 @@ DEFINE_EVENT( #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . #undef TRACE_INCLUDE_FILE -#define TRACE_INCLUDE_FILE i40e_trace +#define TRACE_INCLUDE_FILE iavf_trace #include <trace/define_trace.h> diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c index a9730711e257..edc349f49748 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c @@ -4,32 +4,32 @@ #include <linux/prefetch.h> #include <net/busy_poll.h> -#include "i40evf.h" -#include "i40e_trace.h" -#include "i40e_prototype.h" +#include "iavf.h" +#include "iavf_trace.h" +#include "iavf_prototype.h" static inline __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size, u32 td_tag) { - return cpu_to_le64(I40E_TX_DESC_DTYPE_DATA | - ((u64)td_cmd << I40E_TXD_QW1_CMD_SHIFT) | - ((u64)td_offset << I40E_TXD_QW1_OFFSET_SHIFT) | - ((u64)size << I40E_TXD_QW1_TX_BUF_SZ_SHIFT) | - ((u64)td_tag << I40E_TXD_QW1_L2TAG1_SHIFT)); + return cpu_to_le64(IAVF_TX_DESC_DTYPE_DATA | + ((u64)td_cmd << IAVF_TXD_QW1_CMD_SHIFT) | + ((u64)td_offset << IAVF_TXD_QW1_OFFSET_SHIFT) | + ((u64)size << IAVF_TXD_QW1_TX_BUF_SZ_SHIFT) | + ((u64)td_tag << IAVF_TXD_QW1_L2TAG1_SHIFT)); } -#define I40E_TXD_CMD (I40E_TX_DESC_CMD_EOP | I40E_TX_DESC_CMD_RS) +#define IAVF_TXD_CMD (IAVF_TX_DESC_CMD_EOP | IAVF_TX_DESC_CMD_RS) /** - * i40e_unmap_and_free_tx_resource - Release a Tx buffer + * iavf_unmap_and_free_tx_resource - Release a Tx buffer * @ring: the ring that owns the buffer * @tx_buffer: the buffer to free **/ -static void i40e_unmap_and_free_tx_resource(struct i40e_ring *ring, - struct i40e_tx_buffer *tx_buffer) +static void iavf_unmap_and_free_tx_resource(struct iavf_ring *ring, + struct iavf_tx_buffer *tx_buffer) { if (tx_buffer->skb) { - if (tx_buffer->tx_flags & I40E_TX_FLAGS_FD_SB) + if (tx_buffer->tx_flags & IAVF_TX_FLAGS_FD_SB) kfree(tx_buffer->raw_buf); else dev_kfree_skb_any(tx_buffer->skb); @@ -52,10 +52,10 @@ static void i40e_unmap_and_free_tx_resource(struct i40e_ring *ring, } /** - * i40evf_clean_tx_ring - Free any empty Tx buffers + * iavf_clean_tx_ring - Free any empty Tx buffers * @tx_ring: ring to be cleaned **/ -void i40evf_clean_tx_ring(struct i40e_ring *tx_ring) +void iavf_clean_tx_ring(struct iavf_ring *tx_ring) { unsigned long bi_size; u16 i; @@ -66,9 +66,9 @@ void i40evf_clean_tx_ring(struct i40e_ring *tx_ring) /* Free all the Tx ring sk_buffs */ for (i = 0; i < tx_ring->count; i++) - i40e_unmap_and_free_tx_resource(tx_ring, &tx_ring->tx_bi[i]); + iavf_unmap_and_free_tx_resource(tx_ring, &tx_ring->tx_bi[i]); - bi_size = sizeof(struct i40e_tx_buffer) * tx_ring->count; + bi_size = sizeof(struct iavf_tx_buffer) * tx_ring->count; memset(tx_ring->tx_bi, 0, bi_size); /* Zero out the descriptor ring */ @@ -85,14 +85,14 @@ void i40evf_clean_tx_ring(struct i40e_ring *tx_ring) } /** - * i40evf_free_tx_resources - Free Tx resources per queue + * iavf_free_tx_resources - Free Tx resources per queue * @tx_ring: Tx descriptor ring for a specific queue * * Free all transmit software resources **/ -void i40evf_free_tx_resources(struct i40e_ring *tx_ring) +void iavf_free_tx_resources(struct iavf_ring *tx_ring) { - i40evf_clean_tx_ring(tx_ring); + iavf_clean_tx_ring(tx_ring); kfree(tx_ring->tx_bi); tx_ring->tx_bi = NULL; @@ -104,14 +104,14 @@ void i40evf_free_tx_resources(struct i40e_ring *tx_ring) } /** - * i40evf_get_tx_pending - how many Tx descriptors not processed + * iavf_get_tx_pending - how many Tx descriptors not processed * @ring: the ring of descriptors * @in_sw: is tx_pending being checked in SW or HW * * Since there is no access to the ring head register * in XL710, we need to use our local copies **/ -u32 i40evf_get_tx_pending(struct i40e_ring *ring, bool in_sw) +u32 iavf_get_tx_pending(struct iavf_ring *ring, bool in_sw) { u32 head, tail; @@ -126,15 +126,15 @@ u32 i40evf_get_tx_pending(struct i40e_ring *ring, bool in_sw) } /** - * i40evf_detect_recover_hung - Function to detect and recover hung_queues + * iavf_detect_recover_hung - Function to detect and recover hung_queues * @vsi: pointer to vsi struct with tx queues * * 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. **/ -void i40evf_detect_recover_hung(struct i40e_vsi *vsi) +void iavf_detect_recover_hung(struct iavf_vsi *vsi) { - struct i40e_ring *tx_ring = NULL; + struct iavf_ring *tx_ring = NULL; struct net_device *netdev; unsigned int i; int packets; @@ -142,7 +142,7 @@ void i40evf_detect_recover_hung(struct i40e_vsi *vsi) if (!vsi) return; - if (test_bit(__I40E_VSI_DOWN, vsi->state)) + if (test_bit(__IAVF_VSI_DOWN, vsi->state)) return; netdev = vsi->netdev; @@ -164,16 +164,16 @@ void i40evf_detect_recover_hung(struct i40e_vsi *vsi) */ packets = tx_ring->stats.packets & INT_MAX; if (tx_ring->tx_stats.prev_pkt_ctr == packets) { - i40evf_force_wb(vsi, tx_ring->q_vector); + iavf_force_wb(vsi, tx_ring->q_vector); continue; } /* Memory barrier between read of packet count and call - * to i40evf_get_tx_pending() + * to iavf_get_tx_pending() */ smp_rmb(); tx_ring->tx_stats.prev_pkt_ctr = - i40evf_get_tx_pending(tx_ring, true) ? packets : -1; + iavf_get_tx_pending(tx_ring, true) ? packets : -1; } } } @@ -181,28 +181,28 @@ void i40evf_detect_recover_hung(struct i40e_vsi *vsi) #define WB_STRIDE 4 /** - * i40e_clean_tx_irq - Reclaim resources after transmit completes + * iavf_clean_tx_irq - Reclaim resources after transmit completes * @vsi: the VSI we care about * @tx_ring: Tx ring to clean * @napi_budget: Used to determine if we are in netpoll * * Returns true if there's any budget left (e.g. the clean is finished) **/ -static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, - struct i40e_ring *tx_ring, int napi_budget) +static bool iavf_clean_tx_irq(struct iavf_vsi *vsi, + struct iavf_ring *tx_ring, int napi_budget) { u16 i = tx_ring->next_to_clean; - struct i40e_tx_buffer *tx_buf; - struct i40e_tx_desc *tx_desc; + struct iavf_tx_buffer *tx_buf; + struct iavf_tx_desc *tx_desc; unsigned int total_bytes = 0, total_packets = 0; unsigned int budget = vsi->work_limit; tx_buf = &tx_ring->tx_bi[i]; - tx_desc = I40E_TX_DESC(tx_ring, i); + tx_desc = IAVF_TX_DESC(tx_ring, i); i -= tx_ring->count; do { - struct i40e_tx_desc *eop_desc = tx_buf->next_to_watch; + struct iavf_tx_desc *eop_desc = tx_buf->next_to_watch; /* if next_to_watch is not set then there is no work pending */ if (!eop_desc) @@ -211,10 +211,10 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, /* prevent any other reads prior to eop_desc */ smp_rmb(); - i40e_trace(clean_tx_irq, tx_ring, tx_desc, tx_buf); + iavf_trace(clean_tx_irq, tx_ring, tx_desc, tx_buf); /* if the descriptor isn't done, no work yet to do */ if (!(eop_desc->cmd_type_offset_bsz & - cpu_to_le64(I40E_TX_DESC_DTYPE_DESC_DONE))) + cpu_to_le64(IAVF_TX_DESC_DTYPE_DESC_DONE))) break; /* clear next_to_watch to prevent false hangs */ @@ -239,7 +239,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, /* unmap remaining buffers */ while (tx_desc != eop_desc) { - i40e_trace(clean_tx_irq_unmap, + iavf_trace(clean_tx_irq_unmap, tx_ring, tx_desc, tx_buf); tx_buf++; @@ -248,7 +248,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, if (unlikely(!i)) { i -= tx_ring->count; tx_buf = tx_ring->tx_bi; - tx_desc = I40E_TX_DESC(tx_ring, 0); + tx_desc = IAVF_TX_DESC(tx_ring, 0); } /* unmap any remaining paged data */ @@ -268,7 +268,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, if (unlikely(!i)) { i -= tx_ring->count; tx_buf = tx_ring->tx_bi; - tx_desc = I40E_TX_DESC(tx_ring, 0); + tx_desc = IAVF_TX_DESC(tx_ring, 0); } prefetch(tx_desc); @@ -286,18 +286,18 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, tx_ring->q_vector->tx.total_bytes += total_bytes; tx_ring->q_vector->tx.total_packets += total_packets; - if (tx_ring->flags & I40E_TXR_FLAGS_WB_ON_ITR) { + if (tx_ring->flags & IAVF_TXR_FLAGS_WB_ON_ITR) { /* 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. */ - unsigned int j = i40evf_get_tx_pending(tx_ring, false); + unsigned int j = iavf_get_tx_pending(tx_ring, false); if (budget && ((j / WB_STRIDE) == 0) && (j > 0) && - !test_bit(__I40E_VSI_DOWN, vsi->state) && - (I40E_DESC_UNUSED(tx_ring) != tx_ring->count)) + !test_bit(__IAVF_VSI_DOWN, vsi->state) && + (IAVF_DESC_UNUSED(tx_ring) != tx_ring->count)) tx_ring->arm_wb = true; } @@ -307,14 +307,14 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, #define TX_WAKE_THRESHOLD ((s16)(DESC_NEEDED * 2)) if (unlikely(total_packets && netif_carrier_ok(tx_ring->netdev) && - (I40E_DESC_UNUSED(tx_ring) >= TX_WAKE_THRESHOLD))) { + (IAVF_DESC_UNUSED(tx_ring) >= TX_WAKE_THRESHOLD))) { /* Make sure that anybody stopping the queue after this * sees the new next_to_clean. */ smp_mb(); if (__netif_subqueue_stopped(tx_ring->netdev, tx_ring->queue_index) && - !test_bit(__I40E_VSI_DOWN, vsi->state)) { + !test_bit(__IAVF_VSI_DOWN, vsi->state)) { netif_wake_subqueue(tx_ring->netdev, tx_ring->queue_index); ++tx_ring->tx_stats.restart_queue; @@ -325,75 +325,75 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, } /** - * i40evf_enable_wb_on_itr - Arm hardware to do a wb, interrupts are not enabled + * iavf_enable_wb_on_itr - Arm hardware to do a wb, interrupts are not enabled * @vsi: the VSI we care about * @q_vector: the vector on which to enable writeback * **/ -static void i40e_enable_wb_on_itr(struct i40e_vsi *vsi, - struct i40e_q_vector *q_vector) +static void iavf_enable_wb_on_itr(struct iavf_vsi *vsi, + struct iavf_q_vector *q_vector) { u16 flags = q_vector->tx.ring[0].flags; u32 val; - if (!(flags & I40E_TXR_FLAGS_WB_ON_ITR)) + if (!(flags & IAVF_TXR_FLAGS_WB_ON_ITR)) return; if (q_vector->arm_wb_state) return; - val = I40E_VFINT_DYN_CTLN1_WB_ON_ITR_MASK | - I40E_VFINT_DYN_CTLN1_ITR_INDX_MASK; /* set noitr */ + val = IAVF_VFINT_DYN_CTLN1_WB_ON_ITR_MASK | + IAVF_VFINT_DYN_CTLN1_ITR_INDX_MASK; /* set noitr */ wr32(&vsi->back->hw, - I40E_VFINT_DYN_CTLN1(q_vector->reg_idx), val); + IAVF_VFINT_DYN_CTLN1(q_vector->reg_idx), val); q_vector->arm_wb_state = true; } /** - * i40evf_force_wb - Issue SW Interrupt so HW does a wb + * iavf_force_wb - Issue SW Interrupt so HW does a wb * @vsi: the VSI we care about * @q_vector: the vector on which to force writeback * **/ -void i40evf_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector) +void iavf_force_wb(struct iavf_vsi *vsi, struct iavf_q_vector *q_vector) { - u32 val = I40E_VFINT_DYN_CTLN1_INTENA_MASK | - I40E_VFINT_DYN_CTLN1_ITR_INDX_MASK | /* set noitr */ - I40E_VFINT_DYN_CTLN1_SWINT_TRIG_MASK | - I40E_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_MASK + u32 val = IAVF_VFINT_DYN_CTLN1_INTENA_MASK | + IAVF_VFINT_DYN_CTLN1_ITR_INDX_MASK | /* set noitr */ + IAVF_VFINT_DYN_CTLN1_SWINT_TRIG_MASK | + IAVF_VFINT_DYN_CTLN1_SW_ITR_INDX_ENA_MASK /* allow 00 to be written to the index */; wr32(&vsi->back->hw, - I40E_VFINT_DYN_CTLN1(q_vector->reg_idx), + IAVF_VFINT_DYN_CTLN1(q_vector->reg_idx), val); } -static inline bool i40e_container_is_rx(struct i40e_q_vector *q_vector, - struct i40e_ring_container *rc) +static inline bool iavf_container_is_rx(struct iavf_q_vector *q_vector, + struct iavf_ring_container *rc) { return &q_vector->rx == rc; } -static inline unsigned int i40e_itr_divisor(struct i40e_q_vector *q_vector) +static inline unsigned int iavf_itr_divisor(struct iavf_q_vector *q_vector) { unsigned int divisor; switch (q_vector->adapter->link_speed) { case I40E_LINK_SPEED_40GB: - divisor = I40E_ITR_ADAPTIVE_MIN_INC * 1024; + divisor = IAVF_ITR_ADAPTIVE_MIN_INC * 1024; break; case I40E_LINK_SPEED_25GB: case I40E_LINK_SPEED_20GB: - divisor = I40E_ITR_ADAPTIVE_MIN_INC * 512; + divisor = IAVF_ITR_ADAPTIVE_MIN_INC * 512; break; default: case I40E_LINK_SPEED_10GB: - divisor = I40E_ITR_ADAPTIVE_MIN_INC * 256; + divisor = IAVF_ITR_ADAPTIVE_MIN_INC * 256; break; case I40E_LINK_SPEED_1GB: case I40E_LINK_SPEED_100MB: - divisor = I40E_ITR_ADAPTIVE_MIN_INC * 32; + divisor = IAVF_ITR_ADAPTIVE_MIN_INC * 32; break; } @@ -401,7 +401,7 @@ static inline unsigned int i40e_itr_divisor(struct i40e_q_vector *q_vector) } /** - * i40e_update_itr - update the dynamic ITR value based on statistics + * iavf_update_itr - update the dynamic ITR value based on statistics * @q_vector: structure containing interrupt and ring information * @rc: structure containing ring performance data * @@ -413,8 +413,8 @@ static inline unsigned int i40e_itr_divisor(struct i40e_q_vector *q_vector) * on testing data as well as attempting to minimize response time * while increasing bulk throughput. **/ -static void i40e_update_itr(struct i40e_q_vector *q_vector, - struct i40e_ring_container *rc) +static void iavf_update_itr(struct iavf_q_vector *q_vector, + struct iavf_ring_container *rc) { unsigned int avg_wire_size, packets, bytes, itr; unsigned long next_update = jiffies; @@ -428,9 +428,9 @@ static void i40e_update_itr(struct i40e_q_vector *q_vector, /* For Rx we want to push the delay up and default to low latency. * for Tx we want to pull the delay down and default to high latency. */ - itr = i40e_container_is_rx(q_vector, rc) ? - I40E_ITR_ADAPTIVE_MIN_USECS | I40E_ITR_ADAPTIVE_LATENCY : - I40E_ITR_ADAPTIVE_MAX_USECS | I40E_ITR_ADAPTIVE_LATENCY; + itr = iavf_container_is_rx(q_vector, rc) ? + IAVF_ITR_ADAPTIVE_MIN_USECS | IAVF_ITR_ADAPTIVE_LATENCY : + IAVF_ITR_ADAPTIVE_MAX_USECS | IAVF_ITR_ADAPTIVE_LATENCY; /* If we didn't update within up to 1 - 2 jiffies we can assume * that either packets are coming in so slow there hasn't been @@ -454,15 +454,15 @@ static void i40e_update_itr(struct i40e_q_vector *q_vector, packets = rc->total_packets; bytes = rc->total_bytes; - if (i40e_container_is_rx(q_vector, rc)) { + if (iavf_container_is_rx(q_vector, rc)) { /* If Rx there are 1 to 4 packets and bytes are less than * 9000 assume insufficient data to use bulk rate limiting * approach unless Tx is already in bulk rate limiting. We * are likely latency driven. */ if (packets && packets < 4 && bytes < 9000 && - (q_vector->tx.target_itr & I40E_ITR_ADAPTIVE_LATENCY)) { - itr = I40E_ITR_ADAPTIVE_LATENCY; + (q_vector->tx.target_itr & IAVF_ITR_ADAPTIVE_LATENCY)) { + itr = IAVF_ITR_ADAPTIVE_LATENCY; goto adjust_by_size; } } else if (packets < 4) { @@ -471,15 +471,15 @@ static void i40e_update_itr(struct i40e_q_vector *q_vector, * reset the ITR_ADAPTIVE_LATENCY bit for latency mode so * that the Rx can relax. */ - if (rc->target_itr == I40E_ITR_ADAPTIVE_MAX_USECS && - (q_vector->rx.target_itr & I40E_ITR_MASK) == - I40E_ITR_ADAPTIVE_MAX_USECS) + if (rc->target_itr == IAVF_ITR_ADAPTIVE_MAX_USECS && + (q_vector->rx.target_itr & IAVF_ITR_MASK) == + IAVF_ITR_ADAPTIVE_MAX_USECS) goto clear_counts; } else if (packets > 32) { /* If we have processed over 32 packets in a single interrupt * for Tx assume we need to switch over to "bulk" mode. */ - rc->target_itr &= ~I40E_ITR_ADAPTIVE_LATENCY; + rc->target_itr &= ~IAVF_ITR_ADAPTIVE_LATENCY; } /* We have no packets to actually measure against. This means @@ -491,17 +491,17 @@ static void i40e_update_itr(struct i40e_q_vector *q_vector, * fixed amount. */ if (packets < 56) { - itr = rc->target_itr + I40E_ITR_ADAPTIVE_MIN_INC; - if ((itr & I40E_ITR_MASK) > I40E_ITR_ADAPTIVE_MAX_USECS) { - itr &= I40E_ITR_ADAPTIVE_LATENCY; - itr += I40E_ITR_ADAPTIVE_MAX_USECS; + itr = rc->target_itr + IAVF_ITR_ADAPTIVE_MIN_INC; + if ((itr & IAVF_ITR_MASK) > IAVF_ITR_ADAPTIVE_MAX_USECS) { + itr &= IAVF_ITR_ADAPTIVE_LATENCY; + itr += IAVF_ITR_ADAPTIVE_MAX_USECS; } goto clear_counts; } if (packets <= 256) { itr = min(q_vector->tx.current_itr, q_vector->rx.current_itr); - itr &= I40E_ITR_MASK; + itr &= IAVF_ITR_MASK; /* Between 56 and 112 is our "goldilocks" zone where we are * working out "just right". Just report that our current @@ -516,9 +516,9 @@ static void i40e_update_itr(struct i40e_q_vector *q_vector, * in half per interrupt. */ itr /= 2; - itr &= I40E_ITR_MASK; - if (itr < I40E_ITR_ADAPTIVE_MIN_USECS) - itr = I40E_ITR_ADAPTIVE_MIN_USECS; + itr &= IAVF_ITR_MASK; + if (itr < IAVF_ITR_ADAPTIVE_MIN_USECS) + itr = IAVF_ITR_ADAPTIVE_MIN_USECS; goto clear_counts; } @@ -529,7 +529,7 @@ static void i40e_update_itr(struct i40e_q_vector *q_vector, * though for smaller packet sizes there isn't much we can do as * NAPI polling will likely be kicking in sooner rather than later. */ - itr = I40E_ITR_ADAPTIVE_BULK; + itr = IAVF_ITR_ADAPTIVE_BULK; adjust_by_size: /* If packet counts are 256 or greater we can assume we have a gross @@ -577,7 +577,7 @@ adjust_by_size: /* If we are in low latency mode halve our delay which doubles the * rate to somewhere between 100K to 16K ints/sec */ - if (itr & I40E_ITR_ADAPTIVE_LATENCY) + if (itr & IAVF_ITR_ADAPTIVE_LATENCY) avg_wire_size /= 2; /* Resultant value is 256 times larger than it needs to be. This @@ -587,12 +587,12 @@ adjust_by_size: * Use addition as we have already recorded the new latency flag * for the ITR value. */ - itr += DIV_ROUND_UP(avg_wire_size, i40e_itr_divisor(q_vector)) * - I40E_ITR_ADAPTIVE_MIN_INC; + itr += DIV_ROUND_UP(avg_wire_size, iavf_itr_divisor(q_vector)) * + IAVF_ITR_ADAPTIVE_MIN_INC; - if ((itr & I40E_ITR_MASK) > I40E_ITR_ADAPTIVE_MAX_USECS) { - itr &= I40E_ITR_ADAPTIVE_LATENCY; - itr += I40E_ITR_ADAPTIVE_MAX_USECS; + if ((itr & IAVF_ITR_MASK) > IAVF_ITR_ADAPTIVE_MAX_USECS) { + itr &= IAVF_ITR_ADAPTIVE_LATENCY; + itr += IAVF_ITR_ADAPTIVE_MAX_USECS; } clear_counts: @@ -607,12 +607,12 @@ clear_counts: } /** - * i40evf_setup_tx_descriptors - Allocate the Tx descriptors + * iavf_setup_tx_descriptors - Allocate the Tx descriptors * @tx_ring: the tx ring to set up * * Return 0 on success, negative on error **/ -int i40evf_setup_tx_descriptors(struct i40e_ring *tx_ring) +int iavf_setup_tx_descriptors(struct iavf_ring *tx_ring) { struct device *dev = tx_ring->dev; int bi_size; @@ -622,13 +622,13 @@ int i40evf_setup_tx_descriptors(struct i40e_ring *tx_ring) /* warn if we are about to overwrite the pointer */ WARN_ON(tx_ring->tx_bi); - bi_size = sizeof(struct i40e_tx_buffer) * tx_ring->count; + bi_size = sizeof(struct iavf_tx_buffer) * tx_ring->count; tx_ring->tx_bi = kzalloc(bi_size, GFP_KERNEL); if (!tx_ring->tx_bi) goto err; /* round up to nearest 4K */ - tx_ring->size = tx_ring->count * sizeof(struct i40e_tx_desc); + tx_ring->size = tx_ring->count * sizeof(struct iavf_tx_desc); tx_ring->size = ALIGN(tx_ring->size, 4096); tx_ring->desc = dma_alloc_coherent(dev, tx_ring->size, &tx_ring->dma, GFP_KERNEL); @@ -650,10 +650,10 @@ err: } /** - * i40evf_clean_rx_ring - Free Rx buffers + * iavf_clean_rx_ring - Free Rx buffers * @rx_ring: ring to be cleaned **/ -void i40evf_clean_rx_ring(struct i40e_ring *rx_ring) +void iavf_clean_rx_ring(struct iavf_ring *rx_ring) { unsigned long bi_size; u16 i; @@ -669,7 +669,7 @@ void i40evf_clean_rx_ring(struct i40e_ring *rx_ring) /* Free all the Rx ring sk_buffs */ for (i = 0; i < rx_ring->count; i++) { - struct i40e_rx_buffer *rx_bi = &rx_ring->rx_bi[i]; + struct iavf_rx_buffer *rx_bi = &rx_ring->rx_bi[i]; if (!rx_bi->page) continue; @@ -685,9 +685,9 @@ void i40evf_clean_rx_ring(struct i40e_ring *rx_ring) /* free resources associated with mapping */ dma_unmap_page_attrs(rx_ring->dev, rx_bi->dma, - i40e_rx_pg_size(rx_ring), + iavf_rx_pg_size(rx_ring), DMA_FROM_DEVICE, - I40E_RX_DMA_ATTR); + IAVF_RX_DMA_ATTR); __page_frag_cache_drain(rx_bi->page, rx_bi->pagecnt_bias); @@ -695,7 +695,7 @@ void i40evf_clean_rx_ring(struct i40e_ring *rx_ring) rx_bi->page_offset = 0; } - bi_size = sizeof(struct i40e_rx_buffer) * rx_ring->count; + bi_size = sizeof(struct iavf_rx_buffer) * rx_ring->count; memset(rx_ring->rx_bi, 0, bi_size); /* Zero out the descriptor ring */ @@ -707,14 +707,14 @@ void i40evf_clean_rx_ring(struct i40e_ring *rx_ring) } /** - * i40evf_free_rx_resources - Free Rx resources + * iavf_free_rx_resources - Free Rx resources * @rx_ring: ring to clean the resources from * * Free all receive software resources **/ -void i40evf_free_rx_resources(struct i40e_ring *rx_ring) +void iavf_free_rx_resources(struct iavf_ring *rx_ring) { - i40evf_clean_rx_ring(rx_ring); + iavf_clean_rx_ring(rx_ring); kfree(rx_ring->rx_bi); rx_ring->rx_bi = NULL; @@ -726,19 +726,19 @@ void i40evf_free_rx_resources(struct i40e_ring *rx_ring) } /** - * i40evf_setup_rx_descriptors - Allocate Rx descriptors + * iavf_setup_rx_descriptors - Allocate Rx descriptors * @rx_ring: Rx descriptor ring (for a specific queue) to setup * * Returns 0 on success, negative on failure **/ -int i40evf_setup_rx_descriptors(struct i40e_ring *rx_ring) +int iavf_setup_rx_descriptors(struct iavf_ring *rx_ring) { struct device *dev = rx_ring->dev; int bi_size; /* warn if we are about to overwrite the pointer */ WARN_ON(rx_ring->rx_bi); - bi_size = sizeof(struct i40e_rx_buffer) * rx_ring->count; + bi_size = sizeof(struct iavf_rx_buffer) * rx_ring->count; rx_ring->rx_bi = kzalloc(bi_size, GFP_KERNEL); if (!rx_ring->rx_bi) goto err; @@ -746,7 +746,7 @@ int i40evf_setup_rx_descriptors(struct i40e_ring *rx_ring) u64_stats_init(&rx_ring->syncp); /* Round up to nearest 4K */ - rx_ring->size = rx_ring->count * sizeof(union i40e_32byte_rx_desc); + rx_ring->size = rx_ring->count * sizeof(union iavf_32byte_rx_desc); rx_ring->size = ALIGN(rx_ring->size, 4096); rx_ring->desc = dma_alloc_coherent(dev, rx_ring->size, &rx_ring->dma, GFP_KERNEL); @@ -769,11 +769,11 @@ err: } /** - * i40e_release_rx_desc - Store the new tail and head values + * iavf_release_rx_desc - Store the new tail and head values * @rx_ring: ring to bump * @val: new head index **/ -static inline void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val) +static inline void iavf_release_rx_desc(struct iavf_ring *rx_ring, u32 val) { rx_ring->next_to_use = val; @@ -790,26 +790,26 @@ static inline void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val) } /** - * i40e_rx_offset - Return expected offset into page to access data + * iavf_rx_offset - Return expected offset into page to access data * @rx_ring: Ring we are requesting offset of * * Returns the offset value for ring into the data buffer. */ -static inline unsigned int i40e_rx_offset(struct i40e_ring *rx_ring) +static inline unsigned int iavf_rx_offset(struct iavf_ring *rx_ring) { - return ring_uses_build_skb(rx_ring) ? I40E_SKB_PAD : 0; + return ring_uses_build_skb(rx_ring) ? IAVF_SKB_PAD : 0; } /** - * i40e_alloc_mapped_page - recycle or make a new page + * iavf_alloc_mapped_page - recycle or make a new page * @rx_ring: ring to use * @bi: rx_buffer struct to modify * * Returns true if the page was successfully allocated or * reused. **/ -static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring, - struct i40e_rx_buffer *bi) +static bool iavf_alloc_mapped_page(struct iavf_ring *rx_ring, + struct iavf_rx_buffer *bi) { struct page *page = bi->page; dma_addr_t dma; @@ -821,7 +821,7 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring, } /* alloc new page for storage */ - page = dev_alloc_pages(i40e_rx_pg_order(rx_ring)); + page = dev_alloc_pages(iavf_rx_pg_order(rx_ring)); if (unlikely(!page)) { rx_ring->rx_stats.alloc_page_failed++; return false; @@ -829,22 +829,22 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring, /* map page for use */ dma = dma_map_page_attrs(rx_ring->dev, page, 0, - i40e_rx_pg_size(rx_ring), + iavf_rx_pg_size(rx_ring), DMA_FROM_DEVICE, - I40E_RX_DMA_ATTR); + IAVF_RX_DMA_ATTR); /* if mapping failed free memory back to system since * there isn't much point in holding memory we can't use */ if (dma_mapping_error(rx_ring->dev, dma)) { - __free_pages(page, i40e_rx_pg_order(rx_ring)); + __free_pages(page, iavf_rx_pg_order(rx_ring)); rx_ring->rx_stats.alloc_page_failed++; return false; } bi->dma = dma; bi->page = page; - bi->page_offset = i40e_rx_offset(rx_ring); + bi->page_offset = iavf_rx_offset(rx_ring); /* initialize pagecnt_bias to 1 representing we fully own page */ bi->pagecnt_bias = 1; @@ -853,15 +853,15 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring, } /** - * i40e_receive_skb - Send a completed packet up the stack + * iavf_receive_skb - Send a completed packet up the stack * @rx_ring: rx ring in play * @skb: packet to send up * @vlan_tag: vlan tag for packet **/ -static void i40e_receive_skb(struct i40e_ring *rx_ring, +static void iavf_receive_skb(struct iavf_ring *rx_ring, struct sk_buff *skb, u16 vlan_tag) { - struct i40e_q_vector *q_vector = rx_ring->q_vector; + struct iavf_q_vector *q_vector = rx_ring->q_vector; if ((rx_ring->netdev->features & NETIF_F_HW_VLAN_CTAG_RX) && (vlan_tag & VLAN_VID_MASK)) @@ -871,27 +871,27 @@ static void i40e_receive_skb(struct i40e_ring *rx_ring, } /** - * i40evf_alloc_rx_buffers - Replace used receive buffers + * iavf_alloc_rx_buffers - Replace used receive buffers * @rx_ring: ring to place buffers on * @cleaned_count: number of buffers to replace * * Returns false if all allocations were successful, true if any fail **/ -bool i40evf_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count) +bool iavf_alloc_rx_buffers(struct iavf_ring *rx_ring, u16 cleaned_count) { u16 ntu = rx_ring->next_to_use; - union i40e_rx_desc *rx_desc; - struct i40e_rx_buffer *bi; + union iavf_rx_desc *rx_desc; + struct iavf_rx_buffer *bi; /* do nothing if no valid netdev defined */ if (!rx_ring->netdev || !cleaned_count) return false; - rx_desc = I40E_RX_DESC(rx_ring, ntu); + rx_desc = IAVF_RX_DESC(rx_ring, ntu); bi = &rx_ring->rx_bi[ntu]; do { - if (!i40e_alloc_mapped_page(rx_ring, bi)) + if (!iavf_alloc_mapped_page(rx_ring, bi)) goto no_buffers; /* sync the buffer for use by the device */ @@ -909,7 +909,7 @@ bool i40evf_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count) bi++; ntu++; if (unlikely(ntu == rx_ring->count)) { - rx_desc = I40E_RX_DESC(rx_ring, 0); + rx_desc = IAVF_RX_DESC(rx_ring, 0); bi = rx_ring->rx_bi; ntu = 0; } @@ -921,13 +921,13 @@ bool i40evf_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count) } while (cleaned_count); if (rx_ring->next_to_use != ntu) - i40e_release_rx_desc(rx_ring, ntu); + iavf_release_rx_desc(rx_ring, ntu); return false; no_buffers: if (rx_ring->next_to_use != ntu) - i40e_release_rx_desc(rx_ring, ntu); + iavf_release_rx_desc(rx_ring, ntu); /* make sure to come back via polling to try again after * allocation failure @@ -936,27 +936,27 @@ no_buffers: } /** - * i40e_rx_checksum - Indicate in skb if hw indicated a good cksum + * iavf_rx_checksum - Indicate in skb if hw indicated a good cksum * @vsi: the VSI we care about * @skb: skb currently being received and modified * @rx_desc: the receive descriptor **/ -static inline void i40e_rx_checksum(struct i40e_vsi *vsi, +static inline void iavf_rx_checksum(struct iavf_vsi *vsi, struct sk_buff *skb, - union i40e_rx_desc *rx_desc) + union iavf_rx_desc *rx_desc) { - struct i40e_rx_ptype_decoded decoded; + struct iavf_rx_ptype_decoded decoded; u32 rx_error, rx_status; bool ipv4, ipv6; u8 ptype; u64 qword; qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); - ptype = (qword & I40E_RXD_QW1_PTYPE_MASK) >> I40E_RXD_QW1_PTYPE_SHIFT; - rx_error = (qword & I40E_RXD_QW1_ERROR_MASK) >> - I40E_RXD_QW1_ERROR_SHIFT; - rx_status = (qword & I40E_RXD_QW1_STATUS_MASK) >> - I40E_RXD_QW1_STATUS_SHIFT; + ptype = (qword & IAVF_RXD_QW1_PTYPE_MASK) >> IAVF_RXD_QW1_PTYPE_SHIFT; + rx_error = (qword & IAVF_RXD_QW1_ERROR_MASK) >> + IAVF_RXD_QW1_ERROR_SHIFT; + rx_status = (qword & IAVF_RXD_QW1_STATUS_MASK) >> + IAVF_RXD_QW1_STATUS_SHIFT; decoded = decode_rx_desc_ptype(ptype); skb->ip_summed = CHECKSUM_NONE; @@ -968,45 +968,45 @@ static inline void i40e_rx_checksum(struct i40e_vsi *vsi, return; /* did the hardware decode the packet and checksum? */ - if (!(rx_status & BIT(I40E_RX_DESC_STATUS_L3L4P_SHIFT))) + if (!(rx_status & BIT(IAVF_RX_DESC_STATUS_L3L4P_SHIFT))) return; /* both known and outer_ip must be set for the below code to work */ if (!(decoded.known && decoded.outer_ip)) return; - ipv4 = (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP) && - (decoded.outer_ip_ver == I40E_RX_PTYPE_OUTER_IPV4); - ipv6 = (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP) && - (decoded.outer_ip_ver == I40E_RX_PTYPE_OUTER_IPV6); + ipv4 = (decoded.outer_ip == IAVF_RX_PTYPE_OUTER_IP) && + (decoded.outer_ip_ver == IAVF_RX_PTYPE_OUTER_IPV4); + ipv6 = (decoded.outer_ip == IAVF_RX_PTYPE_OUTER_IP) && + (decoded.outer_ip_ver == IAVF_RX_PTYPE_OUTER_IPV6); if (ipv4 && - (rx_error & (BIT(I40E_RX_DESC_ERROR_IPE_SHIFT) | - BIT(I40E_RX_DESC_ERROR_EIPE_SHIFT)))) + (rx_error & (BIT(IAVF_RX_DESC_ERROR_IPE_SHIFT) | + BIT(IAVF_RX_DESC_ERROR_EIPE_SHIFT)))) goto checksum_fail; /* likely incorrect csum if alternate IP extension headers found */ if (ipv6 && - rx_status & BIT(I40E_RX_DESC_STATUS_IPV6EXADD_SHIFT)) + rx_status & BIT(IAVF_RX_DESC_STATUS_IPV6EXADD_SHIFT)) /* don't increment checksum err here, non-fatal err */ return; /* there was some L4 error, count error and punt packet to the stack */ - if (rx_error & BIT(I40E_RX_DESC_ERROR_L4E_SHIFT)) + if (rx_error & BIT(IAVF_RX_DESC_ERROR_L4E_SHIFT)) goto checksum_fail; /* handle packets that were not able to be checksummed due * to arrival speed, in this case the stack can compute * the csum. */ - if (rx_error & BIT(I40E_RX_DESC_ERROR_PPRS_SHIFT)) + if (rx_error & BIT(IAVF_RX_DESC_ERROR_PPRS_SHIFT)) return; /* Only report checksum unnecessary for TCP, UDP, or SCTP */ switch (decoded.inner_prot) { - case I40E_RX_PTYPE_INNER_PROT_TCP: - case I40E_RX_PTYPE_INNER_PROT_UDP: - case I40E_RX_PTYPE_INNER_PROT_SCTP: + case IAVF_RX_PTYPE_INNER_PROT_TCP: + case IAVF_RX_PTYPE_INNER_PROT_UDP: + case IAVF_RX_PTYPE_INNER_PROT_SCTP: skb->ip_summed = CHECKSUM_UNNECESSARY; /* fall though */ default: @@ -1020,56 +1020,56 @@ checksum_fail: } /** - * i40e_ptype_to_htype - get a hash type + * iavf_ptype_to_htype - get a hash type * @ptype: the ptype value from the descriptor * * Returns a hash type to be used by skb_set_hash **/ -static inline int i40e_ptype_to_htype(u8 ptype) +static inline int iavf_ptype_to_htype(u8 ptype) { - struct i40e_rx_ptype_decoded decoded = decode_rx_desc_ptype(ptype); + struct iavf_rx_ptype_decoded decoded = decode_rx_desc_ptype(ptype); if (!decoded.known) return PKT_HASH_TYPE_NONE; - if (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP && - decoded.payload_layer == I40E_RX_PTYPE_PAYLOAD_LAYER_PAY4) + if (decoded.outer_ip == IAVF_RX_PTYPE_OUTER_IP && + decoded.payload_layer == IAVF_RX_PTYPE_PAYLOAD_LAYER_PAY4) return PKT_HASH_TYPE_L4; - else if (decoded.outer_ip == I40E_RX_PTYPE_OUTER_IP && - decoded.payload_layer == I40E_RX_PTYPE_PAYLOAD_LAYER_PAY3) + else if (decoded.outer_ip == IAVF_RX_PTYPE_OUTER_IP && + decoded.payload_layer == IAVF_RX_PTYPE_PAYLOAD_LAYER_PAY3) return PKT_HASH_TYPE_L3; else return PKT_HASH_TYPE_L2; } /** - * i40e_rx_hash - set the hash value in the skb + * iavf_rx_hash - set the hash value in the skb * @ring: descriptor ring * @rx_desc: specific descriptor * @skb: skb currently being received and modified * @rx_ptype: Rx packet type **/ -static inline void i40e_rx_hash(struct i40e_ring *ring, - union i40e_rx_desc *rx_desc, +static inline void iavf_rx_hash(struct iavf_ring *ring, + union iavf_rx_desc *rx_desc, struct sk_buff *skb, u8 rx_ptype) { u32 hash; const __le64 rss_mask = - cpu_to_le64((u64)I40E_RX_DESC_FLTSTAT_RSS_HASH << - I40E_RX_DESC_STATUS_FLTSTAT_SHIFT); + cpu_to_le64((u64)IAVF_RX_DESC_FLTSTAT_RSS_HASH << + IAVF_RX_DESC_STATUS_FLTSTAT_SHIFT); if (ring->netdev->features & NETIF_F_RXHASH) return; if ((rx_desc->wb.qword1.status_error_len & rss_mask) == rss_mask) { hash = le32_to_cpu(rx_desc->wb.qword0.hi_dword.rss); - skb_set_hash(skb, hash, i40e_ptype_to_htype(rx_ptype)); + skb_set_hash(skb, hash, iavf_ptype_to_htype(rx_ptype)); } } /** - * i40evf_process_skb_fields - Populate skb header fields from Rx descriptor + * iavf_process_skb_fields - Populate skb header fields from Rx descriptor * @rx_ring: rx descriptor ring packet is being transacted on * @rx_desc: pointer to the EOP Rx descriptor * @skb: pointer to current skb being populated @@ -1080,13 +1080,13 @@ static inline void i40e_rx_hash(struct i40e_ring *ring, * other fields within the skb. **/ static inline -void i40evf_process_skb_fields(struct i40e_ring *rx_ring, - union i40e_rx_desc *rx_desc, struct sk_buff *skb, - u8 rx_ptype) +void iavf_process_skb_fields(struct iavf_ring *rx_ring, + union iavf_rx_desc *rx_desc, struct sk_buff *skb, + u8 rx_ptype) { - i40e_rx_hash(rx_ring, rx_desc, skb, rx_ptype); + iavf_rx_hash(rx_ring, rx_desc, skb, rx_ptype); - i40e_rx_checksum(rx_ring->vsi, skb, rx_desc); + iavf_rx_checksum(rx_ring->vsi, skb, rx_desc); skb_record_rx_queue(skb, rx_ring->queue_index); @@ -1095,7 +1095,7 @@ void i40evf_process_skb_fields(struct i40e_ring *rx_ring, } /** - * i40e_cleanup_headers - Correct empty headers + * iavf_cleanup_headers - Correct empty headers * @rx_ring: rx descriptor ring packet is being transacted on * @skb: pointer to current skb being fixed * @@ -1107,7 +1107,7 @@ void i40evf_process_skb_fields(struct i40e_ring *rx_ring, * * Returns true if an error was encountered and skb was freed. **/ -static bool i40e_cleanup_headers(struct i40e_ring *rx_ring, struct sk_buff *skb) +static bool iavf_cleanup_headers(struct iavf_ring *rx_ring, struct sk_buff *skb) { /* if eth_skb_pad returns an error the skb was freed */ if (eth_skb_pad(skb)) @@ -1117,16 +1117,16 @@ static bool i40e_cleanup_headers(struct i40e_ring *rx_ring, struct sk_buff *skb) } /** - * i40e_reuse_rx_page - page flip buffer and store it back on the ring + * iavf_reuse_rx_page - page flip buffer and store it back on the ring * @rx_ring: rx descriptor ring to store buffers on * @old_buff: donor buffer to have page reused * * Synchronizes page for reuse by the adapter **/ -static void i40e_reuse_rx_page(struct i40e_ring *rx_ring, - struct i40e_rx_buffer *old_buff) +static void iavf_reuse_rx_page(struct iavf_ring *rx_ring, + struct iavf_rx_buffer *old_buff) { - struct i40e_rx_buffer *new_buff; + struct iavf_rx_buffer *new_buff; u16 nta = rx_ring->next_to_alloc; new_buff = &rx_ring->rx_bi[nta]; @@ -1143,20 +1143,20 @@ static void i40e_reuse_rx_page(struct i40e_ring *rx_ring, } /** - * i40e_page_is_reusable - check if any reuse is possible + * iavf_page_is_reusable - check if any reuse is possible * @page: page struct to check * * A page is not reusable if it was allocated under low memory * conditions, or it's not in the same NUMA node as this CPU. */ -static inline bool i40e_page_is_reusable(struct page *page) +static inline bool iavf_page_is_reusable(struct page *page) { return (page_to_nid(page) == numa_mem_id()) && !page_is_pfmemalloc(page); } /** - * i40e_can_reuse_rx_page - Determine if this page can be reused by + * iavf_can_reuse_rx_page - Determine if this page can be reused by * the adapter for another receive * * @rx_buffer: buffer containing the page @@ -1182,13 +1182,13 @@ static inline bool i40e_page_is_reusable(struct page *page) * * In either case, if the page is reusable its refcount is increased. **/ -static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer) +static bool iavf_can_reuse_rx_page(struct iavf_rx_buffer *rx_buffer) { unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; struct page *page = rx_buffer->page; /* Is any reuse possible? */ - if (unlikely(!i40e_page_is_reusable(page))) + if (unlikely(!iavf_page_is_reusable(page))) return false; #if (PAGE_SIZE < 8192) @@ -1196,9 +1196,9 @@ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer) if (unlikely((page_count(page) - pagecnt_bias) > 1)) return false; #else -#define I40E_LAST_OFFSET \ - (SKB_WITH_OVERHEAD(PAGE_SIZE) - I40E_RXBUFFER_2048) - if (rx_buffer->page_offset > I40E_LAST_OFFSET) +#define IAVF_LAST_OFFSET \ + (SKB_WITH_OVERHEAD(PAGE_SIZE) - IAVF_RXBUFFER_2048) + if (rx_buffer->page_offset > IAVF_LAST_OFFSET) return false; #endif @@ -1215,7 +1215,7 @@ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer) } /** - * i40e_add_rx_frag - Add contents of Rx buffer to sk_buff + * iavf_add_rx_frag - Add contents of Rx buffer to sk_buff * @rx_ring: rx descriptor ring to transact packets on * @rx_buffer: buffer containing page to add * @skb: sk_buff to place the data into @@ -1226,15 +1226,15 @@ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer) * * The function will then update the page offset. **/ -static void i40e_add_rx_frag(struct i40e_ring *rx_ring, - struct i40e_rx_buffer *rx_buffer, +static void iavf_add_rx_frag(struct iavf_ring *rx_ring, + struct iavf_rx_buffer *rx_buffer, struct sk_buff *skb, unsigned int size) { #if (PAGE_SIZE < 8192) - unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2; + unsigned int truesize = iavf_rx_pg_size(rx_ring) / 2; #else - unsigned int truesize = SKB_DATA_ALIGN(size + i40e_rx_offset(rx_ring)); + unsigned int truesize = SKB_DATA_ALIGN(size + iavf_rx_offset(rx_ring)); #endif skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page, @@ -1249,17 +1249,17 @@ static void i40e_add_rx_frag(struct i40e_ring *rx_ring, } /** - * i40e_get_rx_buffer - Fetch Rx buffer and synchronize data for use + * iavf_get_rx_buffer - Fetch Rx buffer and synchronize data for use * @rx_ring: rx descriptor ring to transact packets on * @size: size of buffer to add to skb * * This function will pull an Rx buffer from the ring and synchronize it * for use by the CPU. */ -static struct i40e_rx_buffer *i40e_get_rx_buffer(struct i40e_ring *rx_ring, +static struct iavf_rx_buffer *iavf_get_rx_buffer(struct iavf_ring *rx_ring, const unsigned int size) { - struct i40e_rx_buffer *rx_buffer; + struct iavf_rx_buffer *rx_buffer; rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean]; prefetchw(rx_buffer->page); @@ -1278,7 +1278,7 @@ static struct i40e_rx_buffer *i40e_get_rx_buffer(struct i40e_ring *rx_ring, } /** - * i40e_construct_skb - Allocate skb and populate it + * iavf_construct_skb - Allocate skb and populate it * @rx_ring: rx descriptor ring to transact packets on * @rx_buffer: rx buffer to pull data from * @size: size of buffer to add to skb @@ -1287,13 +1287,13 @@ static struct i40e_rx_buffer *i40e_get_rx_buffer(struct i40e_ring *rx_ring, * data from the current receive descriptor, taking care to set up the * skb correctly. */ -static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring, - struct i40e_rx_buffer *rx_buffer, +static struct sk_buff *iavf_construct_skb(struct iavf_ring *rx_ring, + struct iavf_rx_buffer *rx_buffer, unsigned int size) { void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; #if (PAGE_SIZE < 8192) - unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2; + unsigned int truesize = iavf_rx_pg_size(rx_ring) / 2; #else unsigned int truesize = SKB_DATA_ALIGN(size); #endif @@ -1308,15 +1308,15 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring, /* allocate a skb to store the frags */ skb = __napi_alloc_skb(&rx_ring->q_vector->napi, - I40E_RX_HDR_SIZE, + IAVF_RX_HDR_SIZE, GFP_ATOMIC | __GFP_NOWARN); if (unlikely(!skb)) return NULL; /* Determine available headroom for copy */ headlen = size; - if (headlen > I40E_RX_HDR_SIZE) - headlen = eth_get_headlen(va, I40E_RX_HDR_SIZE); + if (headlen > IAVF_RX_HDR_SIZE) + headlen = eth_get_headlen(va, IAVF_RX_HDR_SIZE); /* align pull length to size of long to optimize memcpy performance */ memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long))); @@ -1343,7 +1343,7 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring, } /** - * i40e_build_skb - Build skb around an existing buffer + * iavf_build_skb - Build skb around an existing buffer * @rx_ring: Rx descriptor ring to transact packets on * @rx_buffer: Rx buffer to pull data from * @size: size of buffer to add to skb @@ -1351,16 +1351,16 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring, * This function builds an skb around an existing Rx buffer, taking care * to set up the skb correctly and avoid any memcpy overhead. */ -static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring, - struct i40e_rx_buffer *rx_buffer, +static struct sk_buff *iavf_build_skb(struct iavf_ring *rx_ring, + struct iavf_rx_buffer *rx_buffer, unsigned int size) { void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; #if (PAGE_SIZE < 8192) - unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2; + unsigned int truesize = iavf_rx_pg_size(rx_ring) / 2; #else unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) + - SKB_DATA_ALIGN(I40E_SKB_PAD + size); + SKB_DATA_ALIGN(IAVF_SKB_PAD + size); #endif struct sk_buff *skb; @@ -1370,12 +1370,12 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring, prefetch(va + L1_CACHE_BYTES); #endif /* build an skb around the page buffer */ - skb = build_skb(va - I40E_SKB_PAD, truesize); + skb = build_skb(va - IAVF_SKB_PAD, truesize); if (unlikely(!skb)) return NULL; /* update pointers within the skb to store the data */ - skb_reserve(skb, I40E_SKB_PAD); + skb_reserve(skb, IAVF_SKB_PAD); __skb_put(skb, size); /* buffer is used by skb, update page_offset */ @@ -1389,25 +1389,25 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring, } /** - * i40e_put_rx_buffer - Clean up used buffer and either recycle or free + * iavf_put_rx_buffer - Clean up used buffer and either recycle or free * @rx_ring: rx descriptor ring to transact packets on * @rx_buffer: rx buffer to pull data from * * This function will clean up the contents of the rx_buffer. It will * either recycle the buffer or unmap it and free the associated resources. */ -static void i40e_put_rx_buffer(struct i40e_ring *rx_ring, - struct i40e_rx_buffer *rx_buffer) +static void iavf_put_rx_buffer(struct iavf_ring *rx_ring, + struct iavf_rx_buffer *rx_buffer) { - if (i40e_can_reuse_rx_page(rx_buffer)) { + if (iavf_can_reuse_rx_page(rx_buffer)) { /* hand second half of page back to the ring */ - i40e_reuse_rx_page(rx_ring, rx_buffer); + iavf_reuse_rx_page(rx_ring, rx_buffer); rx_ring->rx_stats.page_reuse_count++; } else { /* we are not reusing the buffer so unmap it */ dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, - i40e_rx_pg_size(rx_ring), - DMA_FROM_DEVICE, I40E_RX_DMA_ATTR); + iavf_rx_pg_size(rx_ring), + DMA_FROM_DEVICE, IAVF_RX_DMA_ATTR); __page_frag_cache_drain(rx_buffer->page, rx_buffer->pagecnt_bias); } @@ -1417,7 +1417,7 @@ static void i40e_put_rx_buffer(struct i40e_ring *rx_ring, } /** - * i40e_is_non_eop - process handling of non-EOP buffers + * iavf_is_non_eop - process handling of non-EOP buffers * @rx_ring: Rx ring being processed * @rx_desc: Rx descriptor for current buffer * @skb: Current socket buffer containing buffer in progress @@ -1427,8 +1427,8 @@ static void i40e_put_rx_buffer(struct i40e_ring *rx_ring, * sk_buff in the next buffer to be chained and return true indicating * that this is in fact a non-EOP buffer. **/ -static bool i40e_is_non_eop(struct i40e_ring *rx_ring, - union i40e_rx_desc *rx_desc, +static bool iavf_is_non_eop(struct iavf_ring *rx_ring, + union iavf_rx_desc *rx_desc, struct sk_buff *skb) { u32 ntc = rx_ring->next_to_clean + 1; @@ -1437,11 +1437,11 @@ static bool i40e_is_non_eop(struct i40e_ring *rx_ring, ntc = (ntc < rx_ring->count) ? ntc : 0; rx_ring->next_to_clean = ntc; - prefetch(I40E_RX_DESC(rx_ring, ntc)); + prefetch(IAVF_RX_DESC(rx_ring, ntc)); /* if we are the last buffer then there is nothing else to do */ -#define I40E_RXD_EOF BIT(I40E_RX_DESC_STATUS_EOF_SHIFT) - if (likely(i40e_test_staterr(rx_desc, I40E_RXD_EOF))) +#define IAVF_RXD_EOF BIT(IAVF_RX_DESC_STATUS_EOF_SHIFT) + if (likely(iavf_test_staterr(rx_desc, IAVF_RXD_EOF))) return false; rx_ring->rx_stats.non_eop_descs++; @@ -1450,7 +1450,7 @@ static bool i40e_is_non_eop(struct i40e_ring *rx_ring, } /** - * i40e_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf + * iavf_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf * @rx_ring: rx descriptor ring to transact packets on * @budget: Total limit on number of packets to process * @@ -1461,29 +1461,29 @@ static bool i40e_is_non_eop(struct i40e_ring *rx_ring, * * Returns amount of work completed **/ -static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) +static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget) { unsigned int total_rx_bytes = 0, total_rx_packets = 0; struct sk_buff *skb = rx_ring->skb; - u16 cleaned_count = I40E_DESC_UNUSED(rx_ring); + u16 cleaned_count = IAVF_DESC_UNUSED(rx_ring); bool failure = false; while (likely(total_rx_packets < (unsigned int)budget)) { - struct i40e_rx_buffer *rx_buffer; - union i40e_rx_desc *rx_desc; + struct iavf_rx_buffer *rx_buffer; + union iavf_rx_desc *rx_desc; unsigned int size; u16 vlan_tag; u8 rx_ptype; u64 qword; /* return some buffers to hardware, one at a time is too slow */ - if (cleaned_count >= I40E_RX_BUFFER_WRITE) { + if (cleaned_count >= IAVF_RX_BUFFER_WRITE) { failure = failure || - i40evf_alloc_rx_buffers(rx_ring, cleaned_count); + iavf_alloc_rx_buffers(rx_ring, cleaned_count); cleaned_count = 0; } - rx_desc = I40E_RX_DESC(rx_ring, rx_ring->next_to_clean); + rx_desc = IAVF_RX_DESC(rx_ring, rx_ring->next_to_clean); /* status_error_len will always be zero for unused descriptors * because it's cleared in cleanup, and overlaps with hdr_addr @@ -1498,21 +1498,21 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) */ dma_rmb(); - size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >> - I40E_RXD_QW1_LENGTH_PBUF_SHIFT; + size = (qword & IAVF_RXD_QW1_LENGTH_PBUF_MASK) >> + IAVF_RXD_QW1_LENGTH_PBUF_SHIFT; if (!size) break; - i40e_trace(clean_rx_irq, rx_ring, rx_desc, skb); - rx_buffer = i40e_get_rx_buffer(rx_ring, size); + iavf_trace(clean_rx_irq, rx_ring, rx_desc, skb); + rx_buffer = iavf_get_rx_buffer(rx_ring, size); /* retrieve a buffer from the ring */ if (skb) - i40e_add_rx_frag(rx_ring, rx_buffer, skb, size); + iavf_add_rx_frag(rx_ring, rx_buffer, skb, size); else if (ring_uses_build_skb(rx_ring)) - skb = i40e_build_skb(rx_ring, rx_buffer, size); + skb = iavf_build_skb(rx_ring, rx_buffer, size); else - skb = i40e_construct_skb(rx_ring, rx_buffer, size); + skb = iavf_construct_skb(rx_ring, rx_buffer, size); /* exit if we failed to retrieve a buffer */ if (!skb) { @@ -1521,24 +1521,24 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) break; } - i40e_put_rx_buffer(rx_ring, rx_buffer); + iavf_put_rx_buffer(rx_ring, rx_buffer); cleaned_count++; - if (i40e_is_non_eop(rx_ring, rx_desc, skb)) + if (iavf_is_non_eop(rx_ring, rx_desc, skb)) continue; /* ERR_MASK will only have valid bits if EOP set, and * what we are doing here is actually checking - * I40E_RX_DESC_ERROR_RXE_SHIFT, since it is the zeroth bit in + * IAVF_RX_DESC_ERROR_RXE_SHIFT, since it is the zeroth bit in * the error field */ - if (unlikely(i40e_test_staterr(rx_desc, BIT(I40E_RXD_QW1_ERROR_SHIFT)))) { + if (unlikely(iavf_test_staterr(rx_desc, BIT(IAVF_RXD_QW1_ERROR_SHIFT)))) { dev_kfree_skb_any(skb); skb = NULL; continue; } - if (i40e_cleanup_headers(rx_ring, skb)) { + if (iavf_cleanup_headers(rx_ring, skb)) { skb = NULL; continue; } @@ -1547,18 +1547,18 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) total_rx_bytes += skb->len; qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); - rx_ptype = (qword & I40E_RXD_QW1_PTYPE_MASK) >> - I40E_RXD_QW1_PTYPE_SHIFT; + rx_ptype = (qword & IAVF_RXD_QW1_PTYPE_MASK) >> + IAVF_RXD_QW1_PTYPE_SHIFT; /* populate checksum, VLAN, and protocol */ - i40evf_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype); + iavf_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype); - vlan_tag = (qword & BIT(I40E_RX_DESC_STATUS_L2TAG1P_SHIFT)) ? + vlan_tag = (qword & BIT(IAVF_RX_DESC_STATUS_L2TAG1P_SHIFT)) ? le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1) : 0; - i40e_trace(clean_rx_irq_rx, rx_ring, rx_desc, skb); - i40e_receive_skb(rx_ring, skb, vlan_tag); + iavf_trace(clean_rx_irq_rx, rx_ring, rx_desc, skb); + iavf_receive_skb(rx_ring, skb, vlan_tag); skb = NULL; /* update budget accounting */ @@ -1578,7 +1578,7 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) return failure ? budget : (int)total_rx_packets; } -static inline u32 i40e_buildreg_itr(const int type, u16 itr) +static inline u32 iavf_buildreg_itr(const int type, u16 itr) { u32 val; @@ -1597,17 +1597,17 @@ static inline u32 i40e_buildreg_itr(const int type, u16 itr) * only need to shift by the interval shift - 1 instead of the * full value. */ - itr &= I40E_ITR_MASK; + itr &= IAVF_ITR_MASK; - val = I40E_VFINT_DYN_CTLN1_INTENA_MASK | - (type << I40E_VFINT_DYN_CTLN1_ITR_INDX_SHIFT) | - (itr << (I40E_VFINT_DYN_CTLN1_INTERVAL_SHIFT - 1)); + val = IAVF_VFINT_DYN_CTLN1_INTENA_MASK | + (type << IAVF_VFINT_DYN_CTLN1_ITR_INDX_SHIFT) | + (itr << (IAVF_VFINT_DYN_CTLN1_INTERVAL_SHIFT - 1)); return val; } /* a small macro to shorten up some long lines */ -#define INTREG I40E_VFINT_DYN_CTLN1 +#define INTREG IAVF_VFINT_DYN_CTLN1 /* The act of updating the ITR will cause it to immediately trigger. In order * to prevent this from throwing off adaptive update statistics we defer the @@ -1619,20 +1619,20 @@ static inline u32 i40e_buildreg_itr(const int type, u16 itr) #define ITR_COUNTDOWN_START 3 /** - * i40e_update_enable_itr - Update itr and re-enable MSIX interrupt + * iavf_update_enable_itr - Update itr and re-enable MSIX interrupt * @vsi: the VSI we care about * @q_vector: q_vector for which itr is being updated and interrupt enabled * **/ -static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, - struct i40e_q_vector *q_vector) +static inline void iavf_update_enable_itr(struct iavf_vsi *vsi, + struct iavf_q_vector *q_vector) { - struct i40e_hw *hw = &vsi->back->hw; + struct iavf_hw *hw = &vsi->back->hw; u32 intval; /* These will do nothing if dynamic updates are not enabled */ - i40e_update_itr(q_vector, &q_vector->tx); - i40e_update_itr(q_vector, &q_vector->rx); + iavf_update_itr(q_vector, &q_vector->tx); + iavf_update_itr(q_vector, &q_vector->rx); /* This block of logic allows us to get away with only updating * one ITR value with each interrupt. The idea is to perform a @@ -1644,7 +1644,7 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, */ if (q_vector->rx.target_itr < q_vector->rx.current_itr) { /* Rx ITR needs to be reduced, this is highest priority */ - intval = i40e_buildreg_itr(I40E_RX_ITR, + intval = iavf_buildreg_itr(IAVF_RX_ITR, q_vector->rx.target_itr); q_vector->rx.current_itr = q_vector->rx.target_itr; q_vector->itr_countdown = ITR_COUNTDOWN_START; @@ -1654,29 +1654,29 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, /* Tx ITR needs to be reduced, this is second priority * Tx ITR needs to be increased more than Rx, fourth priority */ - intval = i40e_buildreg_itr(I40E_TX_ITR, + intval = iavf_buildreg_itr(IAVF_TX_ITR, q_vector->tx.target_itr); q_vector->tx.current_itr = q_vector->tx.target_itr; q_vector->itr_countdown = ITR_COUNTDOWN_START; } else if (q_vector->rx.current_itr != q_vector->rx.target_itr) { /* Rx ITR needs to be increased, third priority */ - intval = i40e_buildreg_itr(I40E_RX_ITR, + intval = iavf_buildreg_itr(IAVF_RX_ITR, q_vector->rx.target_itr); q_vector->rx.current_itr = q_vector->rx.target_itr; q_vector->itr_countdown = ITR_COUNTDOWN_START; } else { /* No ITR update, lowest priority */ - intval = i40e_buildreg_itr(I40E_ITR_NONE, 0); + intval = iavf_buildreg_itr(IAVF_ITR_NONE, 0); if (q_vector->itr_countdown) q_vector->itr_countdown--; } - if (!test_bit(__I40E_VSI_DOWN, vsi->state)) + if (!test_bit(__IAVF_VSI_DOWN, vsi->state)) wr32(hw, INTREG(q_vector->reg_idx), intval); } /** - * i40evf_napi_poll - NAPI polling Rx/Tx cleanup routine + * iavf_napi_poll - NAPI polling Rx/Tx cleanup routine * @napi: napi struct with our devices info in it * @budget: amount of work driver is allowed to do this pass, in packets * @@ -1684,18 +1684,18 @@ static inline void i40e_update_enable_itr(struct i40e_vsi *vsi, * * Returns the amount of work done **/ -int i40evf_napi_poll(struct napi_struct *napi, int budget) +int iavf_napi_poll(struct napi_struct *napi, int budget) { - struct i40e_q_vector *q_vector = - container_of(napi, struct i40e_q_vector, napi); - struct i40e_vsi *vsi = q_vector->vsi; - struct i40e_ring *ring; + struct iavf_q_vector *q_vector = + container_of(napi, struct iavf_q_vector, napi); + struct iavf_vsi *vsi = q_vector->vsi; + struct iavf_ring *ring; bool clean_complete = true; bool arm_wb = false; int budget_per_ring; int work_done = 0; - if (test_bit(__I40E_VSI_DOWN, vsi->state)) { + if (test_bit(__IAVF_VSI_DOWN, vsi->state)) { napi_complete(napi); return 0; } @@ -1703,8 +1703,8 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget) /* Since the actual Tx work is minimal, we can give the Tx a larger * budget and be more aggressive about cleaning up the Tx descriptors. */ - i40e_for_each_ring(ring, q_vector->tx) { - if (!i40e_clean_tx_irq(vsi, ring, budget)) { + iavf_for_each_ring(ring, q_vector->tx) { + if (!iavf_clean_tx_irq(vsi, ring, budget)) { clean_complete = false; continue; } @@ -1721,8 +1721,8 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget) */ budget_per_ring = max(budget/q_vector->num_ringpairs, 1); - i40e_for_each_ring(ring, q_vector->rx) { - int cleaned = i40e_clean_rx_irq(ring, budget_per_ring); + iavf_for_each_ring(ring, q_vector->rx) { + int cleaned = iavf_clean_rx_irq(ring, budget_per_ring); work_done += cleaned; /* if we clean as many as budgeted, we must not be done */ @@ -1746,7 +1746,7 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget) napi_complete_done(napi, work_done); /* Force an interrupt */ - i40evf_force_wb(vsi, q_vector); + iavf_force_wb(vsi, q_vector); /* Return budget-1 so that polling stops */ return budget - 1; @@ -1754,24 +1754,24 @@ int i40evf_napi_poll(struct napi_struct *napi, int budget) tx_only: if (arm_wb) { q_vector->tx.ring[0].tx_stats.tx_force_wb++; - i40e_enable_wb_on_itr(vsi, q_vector); + iavf_enable_wb_on_itr(vsi, q_vector); } return budget; } - if (vsi->back->flags & I40E_TXR_FLAGS_WB_ON_ITR) + if (vsi->back->flags & IAVF_TXR_FLAGS_WB_ON_ITR) q_vector->arm_wb_state = false; /* Work is done so exit the polling mode and re-enable the interrupt */ napi_complete_done(napi, work_done); - i40e_update_enable_itr(vsi, q_vector); + iavf_update_enable_itr(vsi, q_vector); return min(work_done, budget - 1); } /** - * i40evf_tx_prepare_vlan_flags - prepare generic TX VLAN tagging flags for HW + * iavf_tx_prepare_vlan_flags - prepare generic TX VLAN tagging flags for HW * @skb: send buffer * @tx_ring: ring to send buffer on * @flags: the tx flags to be set @@ -1782,9 +1782,9 @@ tx_only: * Returns error code indicate the frame should be dropped upon error and the * otherwise returns 0 to indicate the flags has been set properly. **/ -static inline int i40evf_tx_prepare_vlan_flags(struct sk_buff *skb, - struct i40e_ring *tx_ring, - u32 *flags) +static inline int iavf_tx_prepare_vlan_flags(struct sk_buff *skb, + struct iavf_ring *tx_ring, + u32 *flags) { __be16 protocol = skb->protocol; u32 tx_flags = 0; @@ -1804,8 +1804,8 @@ static inline int i40evf_tx_prepare_vlan_flags(struct sk_buff *skb, /* if we have a HW VLAN tag being added, default to the HW one */ if (skb_vlan_tag_present(skb)) { - tx_flags |= skb_vlan_tag_get(skb) << I40E_TX_FLAGS_VLAN_SHIFT; - tx_flags |= I40E_TX_FLAGS_HW_VLAN; + tx_flags |= skb_vlan_tag_get(skb) << IAVF_TX_FLAGS_VLAN_SHIFT; + tx_flags |= IAVF_TX_FLAGS_HW_VLAN; /* else if it is a SW VLAN, check the next protocol and store the tag */ } else if (protocol == htons(ETH_P_8021Q)) { struct vlan_hdr *vhdr, _vhdr; @@ -1815,8 +1815,8 @@ static inline int i40evf_tx_prepare_vlan_flags(struct sk_buff *skb, return -EINVAL; protocol = vhdr->h_vlan_encapsulated_proto; - tx_flags |= ntohs(vhdr->h_vlan_TCI) << I40E_TX_FLAGS_VLAN_SHIFT; - tx_flags |= I40E_TX_FLAGS_SW_VLAN; + tx_flags |= ntohs(vhdr->h_vlan_TCI) << IAVF_TX_FLAGS_VLAN_SHIFT; + tx_flags |= IAVF_TX_FLAGS_SW_VLAN; } out: @@ -1825,14 +1825,14 @@ out: } /** - * i40e_tso - set up the tso context descriptor + * iavf_tso - set up the tso context descriptor * @first: pointer to first Tx buffer for xmit * @hdr_len: ptr to the size of the packet header * @cd_type_cmd_tso_mss: Quad Word 1 * * Returns 0 if no TSO can happen, 1 if tso is going, or error **/ -static int i40e_tso(struct i40e_tx_buffer *first, u8 *hdr_len, +static int iavf_tso(struct iavf_tx_buffer *first, u8 *hdr_len, u64 *cd_type_cmd_tso_mss) { struct sk_buff *skb = first->skb; @@ -1923,17 +1923,17 @@ static int i40e_tso(struct i40e_tx_buffer *first, u8 *hdr_len, first->bytecount += (first->gso_segs - 1) * *hdr_len; /* find the field values */ - cd_cmd = I40E_TX_CTX_DESC_TSO; + cd_cmd = IAVF_TX_CTX_DESC_TSO; cd_tso_len = skb->len - *hdr_len; cd_mss = gso_size; - *cd_type_cmd_tso_mss |= (cd_cmd << I40E_TXD_CTX_QW1_CMD_SHIFT) | - (cd_tso_len << I40E_TXD_CTX_QW1_TSO_LEN_SHIFT) | - (cd_mss << I40E_TXD_CTX_QW1_MSS_SHIFT); + *cd_type_cmd_tso_mss |= (cd_cmd << IAVF_TXD_CTX_QW1_CMD_SHIFT) | + (cd_tso_len << IAVF_TXD_CTX_QW1_TSO_LEN_SHIFT) | + (cd_mss << IAVF_TXD_CTX_QW1_MSS_SHIFT); return 1; } /** - * i40e_tx_enable_csum - Enable Tx checksum offloads + * iavf_tx_enable_csum - Enable Tx checksum offloads * @skb: send buffer * @tx_flags: pointer to Tx flags currently set * @td_cmd: Tx descriptor command bits to set @@ -1941,9 +1941,9 @@ static int i40e_tso(struct i40e_tx_buffer *first, u8 *hdr_len, * @tx_ring: Tx descriptor ring * @cd_tunneling: ptr to context desc bits **/ -static int i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags, +static int iavf_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags, u32 *td_cmd, u32 *td_offset, - struct i40e_ring *tx_ring, + struct iavf_ring *tx_ring, u32 *cd_tunneling) { union { @@ -1968,19 +1968,19 @@ static int i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags, l4.hdr = skb_transport_header(skb); /* compute outer L2 header size */ - offset = ((ip.hdr - skb->data) / 2) << I40E_TX_DESC_LENGTH_MACLEN_SHIFT; + offset = ((ip.hdr - skb->data) / 2) << IAVF_TX_DESC_LENGTH_MACLEN_SHIFT; if (skb->encapsulation) { u32 tunnel = 0; /* define outer network header type */ - if (*tx_flags & I40E_TX_FLAGS_IPV4) { - tunnel |= (*tx_flags & I40E_TX_FLAGS_TSO) ? - I40E_TX_CTX_EXT_IP_IPV4 : - I40E_TX_CTX_EXT_IP_IPV4_NO_CSUM; + if (*tx_flags & IAVF_TX_FLAGS_IPV4) { + tunnel |= (*tx_flags & IAVF_TX_FLAGS_TSO) ? + IAVF_TX_CTX_EXT_IP_IPV4 : + IAVF_TX_CTX_EXT_IP_IPV4_NO_CSUM; l4_proto = ip.v4->protocol; - } else if (*tx_flags & I40E_TX_FLAGS_IPV6) { - tunnel |= I40E_TX_CTX_EXT_IP_IPV6; + } else if (*tx_flags & IAVF_TX_FLAGS_IPV6) { + tunnel |= IAVF_TX_CTX_EXT_IP_IPV6; exthdr = ip.hdr + sizeof(*ip.v6); l4_proto = ip.v6->nexthdr; @@ -1992,20 +1992,20 @@ static int i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags, /* define outer transport */ switch (l4_proto) { case IPPROTO_UDP: - tunnel |= I40E_TXD_CTX_UDP_TUNNELING; - *tx_flags |= I40E_TX_FLAGS_VXLAN_TUNNEL; + tunnel |= IAVF_TXD_CTX_UDP_TUNNELING; + *tx_flags |= IAVF_TX_FLAGS_VXLAN_TUNNEL; break; case IPPROTO_GRE: - tunnel |= I40E_TXD_CTX_GRE_TUNNELING; - *tx_flags |= I40E_TX_FLAGS_VXLAN_TUNNEL; + tunnel |= IAVF_TXD_CTX_GRE_TUNNELING; + *tx_flags |= IAVF_TX_FLAGS_VXLAN_TUNNEL; break; case IPPROTO_IPIP: case IPPROTO_IPV6: - *tx_flags |= I40E_TX_FLAGS_VXLAN_TUNNEL; + *tx_flags |= IAVF_TX_FLAGS_VXLAN_TUNNEL; l4.hdr = skb_inner_network_header(skb); break; default: - if (*tx_flags & I40E_TX_FLAGS_TSO) + if (*tx_flags & IAVF_TX_FLAGS_TSO) return -1; skb_checksum_help(skb); @@ -2014,20 +2014,20 @@ static int i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags, /* compute outer L3 header size */ tunnel |= ((l4.hdr - ip.hdr) / 4) << - I40E_TXD_CTX_QW0_EXT_IPLEN_SHIFT; + IAVF_TXD_CTX_QW0_EXT_IPLEN_SHIFT; /* switch IP header pointer from outer to inner header */ ip.hdr = skb_inner_network_header(skb); /* compute tunnel header size */ tunnel |= ((ip.hdr - l4.hdr) / 2) << - I40E_TXD_CTX_QW0_NATLEN_SHIFT; + IAVF_TXD_CTX_QW0_NATLEN_SHIFT; /* indicate if we need to offload outer UDP header */ - if ((*tx_flags & I40E_TX_FLAGS_TSO) && + if ((*tx_flags & IAVF_TX_FLAGS_TSO) && !(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) && (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM)) - tunnel |= I40E_TXD_CTX_QW0_L4T_CS_MASK; + tunnel |= IAVF_TXD_CTX_QW0_L4T_CS_MASK; /* record tunnel offload values */ *cd_tunneling |= tunnel; @@ -2037,24 +2037,24 @@ static int i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags, l4_proto = 0; /* reset type as we transition from outer to inner headers */ - *tx_flags &= ~(I40E_TX_FLAGS_IPV4 | I40E_TX_FLAGS_IPV6); + *tx_flags &= ~(IAVF_TX_FLAGS_IPV4 | IAVF_TX_FLAGS_IPV6); if (ip.v4->version == 4) - *tx_flags |= I40E_TX_FLAGS_IPV4; + *tx_flags |= IAVF_TX_FLAGS_IPV4; if (ip.v6->version == 6) - *tx_flags |= I40E_TX_FLAGS_IPV6; + *tx_flags |= IAVF_TX_FLAGS_IPV6; } /* Enable IP checksum offloads */ - if (*tx_flags & I40E_TX_FLAGS_IPV4) { + if (*tx_flags & IAVF_TX_FLAGS_IPV4) { l4_proto = ip.v4->protocol; /* the stack computes the IP header already, the only time we * need the hardware to recompute it is in the case of TSO. */ - cmd |= (*tx_flags & I40E_TX_FLAGS_TSO) ? - I40E_TX_DESC_CMD_IIPT_IPV4_CSUM : - I40E_TX_DESC_CMD_IIPT_IPV4; - } else if (*tx_flags & I40E_TX_FLAGS_IPV6) { - cmd |= I40E_TX_DESC_CMD_IIPT_IPV6; + cmd |= (*tx_flags & IAVF_TX_FLAGS_TSO) ? + IAVF_TX_DESC_CMD_IIPT_IPV4_CSUM : + IAVF_TX_DESC_CMD_IIPT_IPV4; + } else if (*tx_flags & IAVF_TX_FLAGS_IPV6) { + cmd |= IAVF_TX_DESC_CMD_IIPT_IPV6; exthdr = ip.hdr + sizeof(*ip.v6); l4_proto = ip.v6->nexthdr; @@ -2064,29 +2064,29 @@ static int i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags, } /* compute inner L3 header size */ - offset |= ((l4.hdr - ip.hdr) / 4) << I40E_TX_DESC_LENGTH_IPLEN_SHIFT; + offset |= ((l4.hdr - ip.hdr) / 4) << IAVF_TX_DESC_LENGTH_IPLEN_SHIFT; /* Enable L4 checksum offloads */ switch (l4_proto) { case IPPROTO_TCP: /* enable checksum offloads */ - cmd |= I40E_TX_DESC_CMD_L4T_EOFT_TCP; - offset |= l4.tcp->doff << I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT; + cmd |= IAVF_TX_DESC_CMD_L4T_EOFT_TCP; + offset |= l4.tcp->doff << IAVF_TX_DESC_LENGTH_L4_FC_LEN_SHIFT; break; case IPPROTO_SCTP: /* enable SCTP checksum offload */ - cmd |= I40E_TX_DESC_CMD_L4T_EOFT_SCTP; + cmd |= IAVF_TX_DESC_CMD_L4T_EOFT_SCTP; offset |= (sizeof(struct sctphdr) >> 2) << - I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT; + IAVF_TX_DESC_LENGTH_L4_FC_LEN_SHIFT; break; case IPPROTO_UDP: /* enable UDP checksum offload */ - cmd |= I40E_TX_DESC_CMD_L4T_EOFT_UDP; + cmd |= IAVF_TX_DESC_CMD_L4T_EOFT_UDP; offset |= (sizeof(struct udphdr) >> 2) << - I40E_TX_DESC_LENGTH_L4_FC_LEN_SHIFT; + IAVF_TX_DESC_LENGTH_L4_FC_LEN_SHIFT; break; default: - if (*tx_flags & I40E_TX_FLAGS_TSO) + if (*tx_flags & IAVF_TX_FLAGS_TSO) return -1; skb_checksum_help(skb); return 0; @@ -2099,25 +2099,25 @@ static int i40e_tx_enable_csum(struct sk_buff *skb, u32 *tx_flags, } /** - * i40e_create_tx_ctx Build the Tx context descriptor + * iavf_create_tx_ctx Build the Tx context descriptor * @tx_ring: ring to create the descriptor on * @cd_type_cmd_tso_mss: Quad Word 1 * @cd_tunneling: Quad Word 0 - bits 0-31 * @cd_l2tag2: Quad Word 0 - bits 32-63 **/ -static void i40e_create_tx_ctx(struct i40e_ring *tx_ring, +static void iavf_create_tx_ctx(struct iavf_ring *tx_ring, const u64 cd_type_cmd_tso_mss, const u32 cd_tunneling, const u32 cd_l2tag2) { - struct i40e_tx_context_desc *context_desc; + struct iavf_tx_context_desc *context_desc; int i = tx_ring->next_to_use; - if ((cd_type_cmd_tso_mss == I40E_TX_DESC_DTYPE_CONTEXT) && + if ((cd_type_cmd_tso_mss == IAVF_TX_DESC_DTYPE_CONTEXT) && !cd_tunneling && !cd_l2tag2) return; /* grab the next descriptor */ - context_desc = I40E_TX_CTXTDESC(tx_ring, i); + context_desc = IAVF_TX_CTXTDESC(tx_ring, i); i++; tx_ring->next_to_use = (i < tx_ring->count) ? i : 0; @@ -2130,7 +2130,7 @@ static void i40e_create_tx_ctx(struct i40e_ring *tx_ring, } /** - * __i40evf_chk_linearize - Check if there are more than 8 buffers per packet + * __iavf_chk_linearize - Check if there are more than 8 buffers per packet * @skb: send buffer * * Note: Our HW can't DMA more than 8 buffers to build a packet on the wire @@ -2142,20 +2142,20 @@ static void i40e_create_tx_ctx(struct i40e_ring *tx_ring, * the segment payload in the first descriptor, and another 7 for the * fragments. **/ -bool __i40evf_chk_linearize(struct sk_buff *skb) +bool __iavf_chk_linearize(struct sk_buff *skb) { const struct skb_frag_struct *frag, *stale; int nr_frags, sum; /* no need to check if number of frags is less than 7 */ nr_frags = skb_shinfo(skb)->nr_frags; - if (nr_frags < (I40E_MAX_BUFFER_TXD - 1)) + if (nr_frags < (IAVF_MAX_BUFFER_TXD - 1)) return false; /* We need to walk through the list and validate that each group * of 6 fragments totals at least gso_size. */ - nr_frags -= I40E_MAX_BUFFER_TXD - 2; + nr_frags -= IAVF_MAX_BUFFER_TXD - 2; frag = &skb_shinfo(skb)->frags[0]; /* Initialize size to the negative value of gso_size minus 1. We @@ -2187,17 +2187,17 @@ bool __i40evf_chk_linearize(struct sk_buff *skb) * figure out what the remainder would be in the last * descriptor associated with the fragment. */ - if (stale_size > I40E_MAX_DATA_PER_TXD) { + if (stale_size > IAVF_MAX_DATA_PER_TXD) { int align_pad = -(stale->page_offset) & - (I40E_MAX_READ_REQ_SIZE - 1); + (IAVF_MAX_READ_REQ_SIZE - 1); sum -= align_pad; stale_size -= align_pad; do { - sum -= I40E_MAX_DATA_PER_TXD_ALIGNED; - stale_size -= I40E_MAX_DATA_PER_TXD_ALIGNED; - } while (stale_size > I40E_MAX_DATA_PER_TXD); + sum -= IAVF_MAX_DATA_PER_TXD_ALIGNED; + stale_size -= IAVF_MAX_DATA_PER_TXD_ALIGNED; + } while (stale_size > IAVF_MAX_DATA_PER_TXD); } /* if sum is negative we failed to make sufficient progress */ @@ -2214,20 +2214,20 @@ bool __i40evf_chk_linearize(struct sk_buff *skb) } /** - * __i40evf_maybe_stop_tx - 2nd level check for tx stop conditions + * __iavf_maybe_stop_tx - 2nd level check for tx stop conditions * @tx_ring: the ring to be checked * @size: the size buffer we want to assure is available * * Returns -EBUSY if a stop is needed, else 0 **/ -int __i40evf_maybe_stop_tx(struct i40e_ring *tx_ring, int size) +int __iavf_maybe_stop_tx(struct iavf_ring *tx_ring, int size) { netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index); /* Memory barrier before checking head and tail */ smp_mb(); /* Check again in a case another CPU has just made room available. */ - if (likely(I40E_DESC_UNUSED(tx_ring) < size)) + if (likely(IAVF_DESC_UNUSED(tx_ring) < size)) return -EBUSY; /* A reprieve! - use start_queue because it doesn't call schedule */ @@ -2237,7 +2237,7 @@ int __i40evf_maybe_stop_tx(struct i40e_ring *tx_ring, int size) } /** - * i40evf_tx_map - Build the Tx descriptor + * iavf_tx_map - Build the Tx descriptor * @tx_ring: ring to send buffer on * @skb: send buffer * @first: first buffer info buffer to use @@ -2246,34 +2246,34 @@ int __i40evf_maybe_stop_tx(struct i40e_ring *tx_ring, int size) * @td_cmd: the command field in the descriptor * @td_offset: offset for checksum or crc **/ -static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, - struct i40e_tx_buffer *first, u32 tx_flags, - const u8 hdr_len, u32 td_cmd, u32 td_offset) +static inline void iavf_tx_map(struct iavf_ring *tx_ring, struct sk_buff *skb, + struct iavf_tx_buffer *first, u32 tx_flags, + const u8 hdr_len, u32 td_cmd, u32 td_offset) { unsigned int data_len = skb->data_len; unsigned int size = skb_headlen(skb); struct skb_frag_struct *frag; - struct i40e_tx_buffer *tx_bi; - struct i40e_tx_desc *tx_desc; + struct iavf_tx_buffer *tx_bi; + struct iavf_tx_desc *tx_desc; u16 i = tx_ring->next_to_use; u32 td_tag = 0; dma_addr_t dma; - if (tx_flags & I40E_TX_FLAGS_HW_VLAN) { - td_cmd |= I40E_TX_DESC_CMD_IL2TAG1; - td_tag = (tx_flags & I40E_TX_FLAGS_VLAN_MASK) >> - I40E_TX_FLAGS_VLAN_SHIFT; + if (tx_flags & IAVF_TX_FLAGS_HW_VLAN) { + td_cmd |= IAVF_TX_DESC_CMD_IL2TAG1; + td_tag = (tx_flags & IAVF_TX_FLAGS_VLAN_MASK) >> + IAVF_TX_FLAGS_VLAN_SHIFT; } first->tx_flags = tx_flags; dma = dma_map_single(tx_ring->dev, skb->data, size, DMA_TO_DEVICE); - tx_desc = I40E_TX_DESC(tx_ring, i); + tx_desc = IAVF_TX_DESC(tx_ring, i); tx_bi = first; for (frag = &skb_shinfo(skb)->frags[0];; frag++) { - unsigned int max_data = I40E_MAX_DATA_PER_TXD_ALIGNED; + unsigned int max_data = IAVF_MAX_DATA_PER_TXD_ALIGNED; if (dma_mapping_error(tx_ring->dev, dma)) goto dma_error; @@ -2283,10 +2283,10 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, dma_unmap_addr_set(tx_bi, dma, dma); /* align size to end of page */ - max_data += -dma & (I40E_MAX_READ_REQ_SIZE - 1); + max_data += -dma & (IAVF_MAX_READ_REQ_SIZE - 1); tx_desc->buffer_addr = cpu_to_le64(dma); - while (unlikely(size > I40E_MAX_DATA_PER_TXD)) { + while (unlikely(size > IAVF_MAX_DATA_PER_TXD)) { tx_desc->cmd_type_offset_bsz = build_ctob(td_cmd, td_offset, max_data, td_tag); @@ -2295,14 +2295,14 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, i++; if (i == tx_ring->count) { - tx_desc = I40E_TX_DESC(tx_ring, 0); + tx_desc = IAVF_TX_DESC(tx_ring, 0); i = 0; } dma += max_data; size -= max_data; - max_data = I40E_MAX_DATA_PER_TXD_ALIGNED; + max_data = IAVF_MAX_DATA_PER_TXD_ALIGNED; tx_desc->buffer_addr = cpu_to_le64(dma); } @@ -2316,7 +2316,7 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, i++; if (i == tx_ring->count) { - tx_desc = I40E_TX_DESC(tx_ring, 0); + tx_desc = IAVF_TX_DESC(tx_ring, 0); i = 0; } @@ -2337,10 +2337,10 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, tx_ring->next_to_use = i; - i40e_maybe_stop_tx(tx_ring, DESC_NEEDED); + iavf_maybe_stop_tx(tx_ring, DESC_NEEDED); /* write last descriptor with RS and EOP bits */ - td_cmd |= I40E_TXD_CMD; + td_cmd |= IAVF_TXD_CMD; tx_desc->cmd_type_offset_bsz = build_ctob(td_cmd, td_offset, size, td_tag); @@ -2373,7 +2373,7 @@ dma_error: /* clear dma mappings for failed tx_bi map */ for (;;) { tx_bi = &tx_ring->tx_bi[i]; - i40e_unmap_and_free_tx_resource(tx_ring, tx_bi); + iavf_unmap_and_free_tx_resource(tx_ring, tx_bi); if (tx_bi == first) break; if (i == 0) @@ -2385,18 +2385,18 @@ dma_error: } /** - * i40e_xmit_frame_ring - Sends buffer on Tx ring + * iavf_xmit_frame_ring - Sends buffer on Tx ring * @skb: send buffer * @tx_ring: ring to send buffer on * * Returns NETDEV_TX_OK if sent, else an error code **/ -static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, - struct i40e_ring *tx_ring) +static netdev_tx_t iavf_xmit_frame_ring(struct sk_buff *skb, + struct iavf_ring *tx_ring) { - u64 cd_type_cmd_tso_mss = I40E_TX_DESC_DTYPE_CONTEXT; + u64 cd_type_cmd_tso_mss = IAVF_TX_DESC_DTYPE_CONTEXT; u32 cd_tunneling = 0, cd_l2tag2 = 0; - struct i40e_tx_buffer *first; + struct iavf_tx_buffer *first; u32 td_offset = 0; u32 tx_flags = 0; __be16 protocol; @@ -2407,25 +2407,25 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, /* prefetch the data, we'll need it later */ prefetch(skb->data); - i40e_trace(xmit_frame_ring, skb, tx_ring); + iavf_trace(xmit_frame_ring, skb, tx_ring); - count = i40e_xmit_descriptor_count(skb); - if (i40e_chk_linearize(skb, count)) { + count = iavf_xmit_descriptor_count(skb); + if (iavf_chk_linearize(skb, count)) { if (__skb_linearize(skb)) { dev_kfree_skb_any(skb); return NETDEV_TX_OK; } - count = i40e_txd_use_count(skb->len); + count = iavf_txd_use_count(skb->len); tx_ring->tx_stats.tx_linearize++; } - /* need: 1 descriptor per page * PAGE_SIZE/I40E_MAX_DATA_PER_TXD, - * + 1 desc for skb_head_len/I40E_MAX_DATA_PER_TXD, + /* need: 1 descriptor per page * PAGE_SIZE/IAVF_MAX_DATA_PER_TXD, + * + 1 desc for skb_head_len/IAVF_MAX_DATA_PER_TXD, * + 4 desc gap to avoid the cache line where head is, * + 1 desc for context descriptor, * otherwise try next time */ - if (i40e_maybe_stop_tx(tx_ring, count + 4 + 1)) { + if (iavf_maybe_stop_tx(tx_ring, count + 4 + 1)) { tx_ring->tx_stats.tx_busy++; return NETDEV_TX_BUSY; } @@ -2437,7 +2437,7 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, first->gso_segs = 1; /* prepare the xmit flags */ - if (i40evf_tx_prepare_vlan_flags(skb, tx_ring, &tx_flags)) + if (iavf_tx_prepare_vlan_flags(skb, tx_ring, &tx_flags)) goto out_drop; /* obtain protocol of skb */ @@ -2445,19 +2445,19 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, /* setup IPv4/IPv6 offloads */ if (protocol == htons(ETH_P_IP)) - tx_flags |= I40E_TX_FLAGS_IPV4; + tx_flags |= IAVF_TX_FLAGS_IPV4; else if (protocol == htons(ETH_P_IPV6)) - tx_flags |= I40E_TX_FLAGS_IPV6; + tx_flags |= IAVF_TX_FLAGS_IPV6; - tso = i40e_tso(first, &hdr_len, &cd_type_cmd_tso_mss); + tso = iavf_tso(first, &hdr_len, &cd_type_cmd_tso_mss); if (tso < 0) goto out_drop; else if (tso) - tx_flags |= I40E_TX_FLAGS_TSO; + tx_flags |= IAVF_TX_FLAGS_TSO; /* Always offload the checksum, since it's in the data descriptor */ - tso = i40e_tx_enable_csum(skb, &tx_flags, &td_cmd, &td_offset, + tso = iavf_tx_enable_csum(skb, &tx_flags, &td_cmd, &td_offset, tx_ring, &cd_tunneling); if (tso < 0) goto out_drop; @@ -2465,44 +2465,44 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, skb_tx_timestamp(skb); /* always enable CRC insertion offload */ - td_cmd |= I40E_TX_DESC_CMD_ICRC; + td_cmd |= IAVF_TX_DESC_CMD_ICRC; - i40e_create_tx_ctx(tx_ring, cd_type_cmd_tso_mss, + iavf_create_tx_ctx(tx_ring, cd_type_cmd_tso_mss, cd_tunneling, cd_l2tag2); - i40evf_tx_map(tx_ring, skb, first, tx_flags, hdr_len, - td_cmd, td_offset); + iavf_tx_map(tx_ring, skb, first, tx_flags, hdr_len, + td_cmd, td_offset); return NETDEV_TX_OK; out_drop: - i40e_trace(xmit_frame_ring_drop, first->skb, tx_ring); + iavf_trace(xmit_frame_ring_drop, first->skb, tx_ring); dev_kfree_skb_any(first->skb); first->skb = NULL; return NETDEV_TX_OK; } /** - * i40evf_xmit_frame - Selects the correct VSI and Tx queue to send buffer + * iavf_xmit_frame - Selects the correct VSI and Tx queue to send buffer * @skb: send buffer * @netdev: network interface device structure * * Returns NETDEV_TX_OK if sent, else an error code **/ -netdev_tx_t i40evf_xmit_frame(struct sk_buff *skb, struct net_device *netdev) +netdev_tx_t iavf_xmit_frame(struct sk_buff *skb, struct net_device *netdev) { - struct i40evf_adapter *adapter = netdev_priv(netdev); - struct i40e_ring *tx_ring = &adapter->tx_rings[skb->queue_mapping]; + struct iavf_adapter *adapter = netdev_priv(netdev); + struct iavf_ring *tx_ring = &adapter->tx_rings[skb->queue_mapping]; /* hardware can't handle really short frames, hardware padding works * beyond this point */ - if (unlikely(skb->len < I40E_MIN_TX_LEN)) { - if (skb_pad(skb, I40E_MIN_TX_LEN - skb->len)) + if (unlikely(skb->len < IAVF_MIN_TX_LEN)) { + if (skb_pad(skb, IAVF_MIN_TX_LEN - skb->len)) return NETDEV_TX_OK; - skb->len = I40E_MIN_TX_LEN; - skb_set_tail_pointer(skb, I40E_MIN_TX_LEN); + skb->len = IAVF_MIN_TX_LEN; + skb_set_tail_pointer(skb, IAVF_MIN_TX_LEN); } - return i40e_xmit_frame_ring(skb, tx_ring); + return iavf_xmit_frame_ring(skb, tx_ring); } diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/iavf/iavf_txrx.h index 3b5a63b3236e..71e7d090f8db 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.h @@ -1,11 +1,11 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright(c) 2013 - 2018 Intel Corporation. */ -#ifndef _I40E_TXRX_H_ -#define _I40E_TXRX_H_ +#ifndef _IAVF_TXRX_H_ +#define _IAVF_TXRX_H_ /* Interrupt Throttling and Rate Limiting Goodies */ -#define I40E_DEFAULT_IRQ_WORK 256 +#define IAVF_DEFAULT_IRQ_WORK 256 /* The datasheet for the X710 and XL710 indicate that the maximum value for * the ITR is 8160usec which is then called out as 0xFF0 with a 2usec @@ -13,80 +13,80 @@ * the register value which is divided by 2 lets use the actual values and * avoid an excessive amount of translation. */ -#define I40E_ITR_DYNAMIC 0x8000 /* use top bit as a flag */ -#define I40E_ITR_MASK 0x1FFE /* mask for ITR register value */ -#define I40E_MIN_ITR 2 /* reg uses 2 usec resolution */ -#define I40E_ITR_100K 10 /* all values below must be even */ -#define I40E_ITR_50K 20 -#define I40E_ITR_20K 50 -#define I40E_ITR_18K 60 -#define I40E_ITR_8K 122 -#define I40E_MAX_ITR 8160 /* maximum value as per datasheet */ -#define ITR_TO_REG(setting) ((setting) & ~I40E_ITR_DYNAMIC) -#define ITR_REG_ALIGN(setting) __ALIGN_MASK(setting, ~I40E_ITR_MASK) -#define ITR_IS_DYNAMIC(setting) (!!((setting) & I40E_ITR_DYNAMIC)) - -#define I40E_ITR_RX_DEF (I40E_ITR_20K | I40E_ITR_DYNAMIC) -#define I40E_ITR_TX_DEF (I40E_ITR_20K | I40E_ITR_DYNAMIC) +#define IAVF_ITR_DYNAMIC 0x8000 /* use top bit as a flag */ +#define IAVF_ITR_MASK 0x1FFE /* mask for ITR register value */ +#define IAVF_MIN_ITR 2 /* reg uses 2 usec resolution */ +#define IAVF_ITR_100K 10 /* all values below must be even */ +#define IAVF_ITR_50K 20 +#define IAVF_ITR_20K 50 +#define IAVF_ITR_18K 60 +#define IAVF_ITR_8K 122 +#define IAVF_MAX_ITR 8160 /* maximum value as per datasheet */ +#define ITR_TO_REG(setting) ((setting) & ~IAVF_ITR_DYNAMIC) +#define ITR_REG_ALIGN(setting) __ALIGN_MASK(setting, ~IAVF_ITR_MASK) +#define ITR_IS_DYNAMIC(setting) (!!((setting) & IAVF_ITR_DYNAMIC)) + +#define IAVF_ITR_RX_DEF (IAVF_ITR_20K | IAVF_ITR_DYNAMIC) +#define IAVF_ITR_TX_DEF (IAVF_ITR_20K | IAVF_ITR_DYNAMIC) /* 0x40 is the enable bit for interrupt rate limiting, and must be set if * the value of the rate limit is non-zero */ #define INTRL_ENA BIT(6) -#define I40E_MAX_INTRL 0x3B /* reg uses 4 usec resolution */ +#define IAVF_MAX_INTRL 0x3B /* reg uses 4 usec resolution */ #define INTRL_REG_TO_USEC(intrl) ((intrl & ~INTRL_ENA) << 2) #define INTRL_USEC_TO_REG(set) ((set) ? ((set) >> 2) | INTRL_ENA : 0) -#define I40E_INTRL_8K 125 /* 8000 ints/sec */ -#define I40E_INTRL_62K 16 /* 62500 ints/sec */ -#define I40E_INTRL_83K 12 /* 83333 ints/sec */ +#define IAVF_INTRL_8K 125 /* 8000 ints/sec */ +#define IAVF_INTRL_62K 16 /* 62500 ints/sec */ +#define IAVF_INTRL_83K 12 /* 83333 ints/sec */ -#define I40E_QUEUE_END_OF_LIST 0x7FF +#define IAVF_QUEUE_END_OF_LIST 0x7FF /* this enum matches hardware bits and is meant to be used by DYN_CTLN * registers and QINT registers or more generally anywhere in the manual * mentioning ITR_INDX, ITR_NONE cannot be used as an index 'n' into any * register but instead is a special value meaning "don't update" ITR0/1/2. */ -enum i40e_dyn_idx_t { - I40E_IDX_ITR0 = 0, - I40E_IDX_ITR1 = 1, - I40E_IDX_ITR2 = 2, - I40E_ITR_NONE = 3 /* ITR_NONE must not be used as an index */ +enum iavf_dyn_idx_t { + IAVF_IDX_ITR0 = 0, + IAVF_IDX_ITR1 = 1, + IAVF_IDX_ITR2 = 2, + IAVF_ITR_NONE = 3 /* ITR_NONE must not be used as an index */ }; /* these are indexes into ITRN registers */ -#define I40E_RX_ITR I40E_IDX_ITR0 -#define I40E_TX_ITR I40E_IDX_ITR1 -#define I40E_PE_ITR I40E_IDX_ITR2 +#define IAVF_RX_ITR IAVF_IDX_ITR0 +#define IAVF_TX_ITR IAVF_IDX_ITR1 +#define IAVF_PE_ITR IAVF_IDX_ITR2 /* Supported RSS offloads */ -#define I40E_DEFAULT_RSS_HENA ( \ - BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_UDP) | \ - BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_SCTP) | \ - BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP) | \ - BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_OTHER) | \ - BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV4) | \ - BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_UDP) | \ - BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP) | \ - BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_SCTP) | \ - BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_OTHER) | \ - BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV6) | \ - BIT_ULL(I40E_FILTER_PCTYPE_L2_PAYLOAD)) - -#define I40E_DEFAULT_RSS_HENA_EXPANDED (I40E_DEFAULT_RSS_HENA | \ - BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK) | \ - BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) | \ - BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP) | \ - BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK) | \ - BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \ - BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP)) +#define IAVF_DEFAULT_RSS_HENA ( \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV4_UDP) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV4_SCTP) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV4_TCP) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV4_OTHER) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_FRAG_IPV4) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV6_UDP) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV6_TCP) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV6_SCTP) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV6_OTHER) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_FRAG_IPV6) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_L2_PAYLOAD)) + +#define IAVF_DEFAULT_RSS_HENA_EXPANDED (IAVF_DEFAULT_RSS_HENA | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \ + BIT_ULL(IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP)) /* Supported Rx Buffer Sizes (a multiple of 128) */ -#define I40E_RXBUFFER_256 256 -#define I40E_RXBUFFER_1536 1536 /* 128B aligned standard Ethernet frame */ -#define I40E_RXBUFFER_2048 2048 -#define I40E_RXBUFFER_3072 3072 /* Used for large frames w/ padding */ -#define I40E_MAX_RXBUFFER 9728 /* largest size for single descriptor */ +#define IAVF_RXBUFFER_256 256 +#define IAVF_RXBUFFER_1536 1536 /* 128B aligned standard Ethernet frame */ +#define IAVF_RXBUFFER_2048 2048 +#define IAVF_RXBUFFER_3072 3072 /* Used for large frames w/ padding */ +#define IAVF_MAX_RXBUFFER 9728 /* largest size for single descriptor */ /* NOTE: netdev_alloc_skb reserves up to 64 bytes, NET_IP_ALIGN means we * reserve 2 more, and skb_shared_info adds an additional 384 bytes more, @@ -95,11 +95,11 @@ enum i40e_dyn_idx_t { * i.e. RXBUFFER_256 --> 960 byte skb (size-1024 slab) * i.e. RXBUFFER_512 --> 1216 byte skb (size-2048 slab) */ -#define I40E_RX_HDR_SIZE I40E_RXBUFFER_256 -#define I40E_PACKET_HDR_PAD (ETH_HLEN + ETH_FCS_LEN + (VLAN_HLEN * 2)) -#define i40e_rx_desc i40e_32byte_rx_desc +#define IAVF_RX_HDR_SIZE IAVF_RXBUFFER_256 +#define IAVF_PACKET_HDR_PAD (ETH_HLEN + ETH_FCS_LEN + (VLAN_HLEN * 2)) +#define iavf_rx_desc iavf_32byte_rx_desc -#define I40E_RX_DMA_ATTR \ +#define IAVF_RX_DMA_ATTR \ (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING) /* Attempt to maximize the headroom available for incoming frames. We @@ -113,10 +113,10 @@ enum i40e_dyn_idx_t { * receive path. */ #if (PAGE_SIZE < 8192) -#define I40E_2K_TOO_SMALL_WITH_PADDING \ -((NET_SKB_PAD + I40E_RXBUFFER_1536) > SKB_WITH_OVERHEAD(I40E_RXBUFFER_2048)) +#define IAVF_2K_TOO_SMALL_WITH_PADDING \ +((NET_SKB_PAD + IAVF_RXBUFFER_1536) > SKB_WITH_OVERHEAD(IAVF_RXBUFFER_2048)) -static inline int i40e_compute_pad(int rx_buf_len) +static inline int iavf_compute_pad(int rx_buf_len) { int page_size, pad_size; @@ -126,7 +126,7 @@ static inline int i40e_compute_pad(int rx_buf_len) return pad_size; } -static inline int i40e_skb_pad(void) +static inline int iavf_skb_pad(void) { int rx_buf_len; @@ -137,25 +137,25 @@ static inline int i40e_skb_pad(void) * tailroom due to NET_IP_ALIGN possibly shifting us out of * cache-line alignment. */ - if (I40E_2K_TOO_SMALL_WITH_PADDING) - rx_buf_len = I40E_RXBUFFER_3072 + SKB_DATA_ALIGN(NET_IP_ALIGN); + if (IAVF_2K_TOO_SMALL_WITH_PADDING) + rx_buf_len = IAVF_RXBUFFER_3072 + SKB_DATA_ALIGN(NET_IP_ALIGN); else - rx_buf_len = I40E_RXBUFFER_1536; + rx_buf_len = IAVF_RXBUFFER_1536; /* if needed make room for NET_IP_ALIGN */ rx_buf_len -= NET_IP_ALIGN; - return i40e_compute_pad(rx_buf_len); + return iavf_compute_pad(rx_buf_len); } -#define I40E_SKB_PAD i40e_skb_pad() +#define IAVF_SKB_PAD iavf_skb_pad() #else -#define I40E_2K_TOO_SMALL_WITH_PADDING false -#define I40E_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN) +#define IAVF_2K_TOO_SMALL_WITH_PADDING false +#define IAVF_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN) #endif /** - * i40e_test_staterr - tests bits in Rx descriptor status and error fields + * iavf_test_staterr - tests bits in Rx descriptor status and error fields * @rx_desc: pointer to receive descriptor (in le64 format) * @stat_err_bits: value to mask * @@ -164,7 +164,7 @@ static inline int i40e_skb_pad(void) * The status_error_len doesn't need to be shifted because it begins * at offset zero. */ -static inline bool i40e_test_staterr(union i40e_rx_desc *rx_desc, +static inline bool iavf_test_staterr(union iavf_rx_desc *rx_desc, const u64 stat_err_bits) { return !!(rx_desc->wb.qword1.status_error_len & @@ -172,8 +172,7 @@ static inline bool i40e_test_staterr(union i40e_rx_desc *rx_desc, } /* How many Rx Buffers do we bundle into one write to the hardware ? */ -#define I40E_RX_BUFFER_WRITE 32 /* Must be power of 2 */ -#define I40E_RX_INCREMENT(r, i) \ +#define IAVF_RX_INCREMENT(r, i) \ do { \ (i)++; \ if ((i) == (r)->count) \ @@ -181,34 +180,34 @@ static inline bool i40e_test_staterr(union i40e_rx_desc *rx_desc, r->next_to_clean = i; \ } while (0) -#define I40E_RX_NEXT_DESC(r, i, n) \ +#define IAVF_RX_NEXT_DESC(r, i, n) \ do { \ (i)++; \ if ((i) == (r)->count) \ i = 0; \ - (n) = I40E_RX_DESC((r), (i)); \ + (n) = IAVF_RX_DESC((r), (i)); \ } while (0) -#define I40E_RX_NEXT_DESC_PREFETCH(r, i, n) \ +#define IAVF_RX_NEXT_DESC_PREFETCH(r, i, n) \ do { \ - I40E_RX_NEXT_DESC((r), (i), (n)); \ + IAVF_RX_NEXT_DESC((r), (i), (n)); \ prefetch((n)); \ } while (0) -#define I40E_MAX_BUFFER_TXD 8 -#define I40E_MIN_TX_LEN 17 +#define IAVF_MAX_BUFFER_TXD 8 +#define IAVF_MIN_TX_LEN 17 /* The size limit for a transmit buffer in a descriptor is (16K - 1). * In order to align with the read requests we will align the value to * the nearest 4K which represents our maximum read request size. */ -#define I40E_MAX_READ_REQ_SIZE 4096 -#define I40E_MAX_DATA_PER_TXD (16 * 1024 - 1) -#define I40E_MAX_DATA_PER_TXD_ALIGNED \ - (I40E_MAX_DATA_PER_TXD & ~(I40E_MAX_READ_REQ_SIZE - 1)) +#define IAVF_MAX_READ_REQ_SIZE 4096 +#define IAVF_MAX_DATA_PER_TXD (16 * 1024 - 1) +#define IAVF_MAX_DATA_PER_TXD_ALIGNED \ + (IAVF_MAX_DATA_PER_TXD & ~(IAVF_MAX_READ_REQ_SIZE - 1)) /** - * i40e_txd_use_count - estimate the number of descriptors needed for Tx + * iavf_txd_use_count - estimate the number of descriptors needed for Tx * @size: transmit request size in bytes * * Due to hardware alignment restrictions (4K alignment), we need to @@ -235,31 +234,31 @@ static inline bool i40e_test_staterr(union i40e_rx_desc *rx_desc, * operations into: * return ((size * 85) >> 20) + 1; */ -static inline unsigned int i40e_txd_use_count(unsigned int size) +static inline unsigned int iavf_txd_use_count(unsigned int size) { return ((size * 85) >> 20) + 1; } /* Tx Descriptors needed, worst case */ #define DESC_NEEDED (MAX_SKB_FRAGS + 6) -#define I40E_MIN_DESC_PENDING 4 - -#define I40E_TX_FLAGS_HW_VLAN BIT(1) -#define I40E_TX_FLAGS_SW_VLAN BIT(2) -#define I40E_TX_FLAGS_TSO BIT(3) -#define I40E_TX_FLAGS_IPV4 BIT(4) -#define I40E_TX_FLAGS_IPV6 BIT(5) -#define I40E_TX_FLAGS_FCCRC BIT(6) -#define I40E_TX_FLAGS_FSO BIT(7) -#define I40E_TX_FLAGS_FD_SB BIT(9) -#define I40E_TX_FLAGS_VXLAN_TUNNEL BIT(10) -#define I40E_TX_FLAGS_VLAN_MASK 0xffff0000 -#define I40E_TX_FLAGS_VLAN_PRIO_MASK 0xe0000000 -#define I40E_TX_FLAGS_VLAN_PRIO_SHIFT 29 -#define I40E_TX_FLAGS_VLAN_SHIFT 16 - -struct i40e_tx_buffer { - struct i40e_tx_desc *next_to_watch; +#define IAVF_MIN_DESC_PENDING 4 + +#define IAVF_TX_FLAGS_HW_VLAN BIT(1) +#define IAVF_TX_FLAGS_SW_VLAN BIT(2) +#define IAVF_TX_FLAGS_TSO BIT(3) +#define IAVF_TX_FLAGS_IPV4 BIT(4) +#define IAVF_TX_FLAGS_IPV6 BIT(5) +#define IAVF_TX_FLAGS_FCCRC BIT(6) +#define IAVF_TX_FLAGS_FSO BIT(7) +#define IAVF_TX_FLAGS_FD_SB BIT(9) +#define IAVF_TX_FLAGS_VXLAN_TUNNEL BIT(10) +#define IAVF_TX_FLAGS_VLAN_MASK 0xffff0000 +#define IAVF_TX_FLAGS_VLAN_PRIO_MASK 0xe0000000 +#define IAVF_TX_FLAGS_VLAN_PRIO_SHIFT 29 +#define IAVF_TX_FLAGS_VLAN_SHIFT 16 + +struct iavf_tx_buffer { + struct iavf_tx_desc *next_to_watch; union { struct sk_buff *skb; void *raw_buf; @@ -272,7 +271,7 @@ struct i40e_tx_buffer { u32 tx_flags; }; -struct i40e_rx_buffer { +struct iavf_rx_buffer { dma_addr_t dma; struct page *page; #if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536) @@ -283,12 +282,12 @@ struct i40e_rx_buffer { __u16 pagecnt_bias; }; -struct i40e_queue_stats { +struct iavf_queue_stats { u64 packets; u64 bytes; }; -struct i40e_tx_queue_stats { +struct iavf_tx_queue_stats { u64 restart_queue; u64 tx_busy; u64 tx_done_old; @@ -298,7 +297,7 @@ struct i40e_tx_queue_stats { u64 tx_lost_interrupt; }; -struct i40e_rx_queue_stats { +struct iavf_rx_queue_stats { u64 non_eop_descs; u64 alloc_page_failed; u64 alloc_buff_failed; @@ -306,34 +305,34 @@ struct i40e_rx_queue_stats { u64 realloc_count; }; -enum i40e_ring_state_t { - __I40E_TX_FDIR_INIT_DONE, - __I40E_TX_XPS_INIT_DONE, - __I40E_RING_STATE_NBITS /* must be last */ +enum iavf_ring_state_t { + __IAVF_TX_FDIR_INIT_DONE, + __IAVF_TX_XPS_INIT_DONE, + __IAVF_RING_STATE_NBITS /* must be last */ }; /* some useful defines for virtchannel interface, which * is the only remaining user of header split */ -#define I40E_RX_DTYPE_NO_SPLIT 0 -#define I40E_RX_DTYPE_HEADER_SPLIT 1 -#define I40E_RX_DTYPE_SPLIT_ALWAYS 2 -#define I40E_RX_SPLIT_L2 0x1 -#define I40E_RX_SPLIT_IP 0x2 -#define I40E_RX_SPLIT_TCP_UDP 0x4 -#define I40E_RX_SPLIT_SCTP 0x8 +#define IAVF_RX_DTYPE_NO_SPLIT 0 +#define IAVF_RX_DTYPE_HEADER_SPLIT 1 +#define IAVF_RX_DTYPE_SPLIT_ALWAYS 2 +#define IAVF_RX_SPLIT_L2 0x1 +#define IAVF_RX_SPLIT_IP 0x2 +#define IAVF_RX_SPLIT_TCP_UDP 0x4 +#define IAVF_RX_SPLIT_SCTP 0x8 /* struct that defines a descriptor ring, associated with a VSI */ -struct i40e_ring { - struct i40e_ring *next; /* pointer to next ring in q_vector */ +struct iavf_ring { + struct iavf_ring *next; /* pointer to next ring in q_vector */ void *desc; /* Descriptor ring memory */ struct device *dev; /* Used for DMA mapping */ struct net_device *netdev; /* netdev ring maps to */ union { - struct i40e_tx_buffer *tx_bi; - struct i40e_rx_buffer *rx_bi; + struct iavf_tx_buffer *tx_bi; + struct iavf_rx_buffer *rx_bi; }; - DECLARE_BITMAP(state, __I40E_RING_STATE_NBITS); + DECLARE_BITMAP(state, __IAVF_RING_STATE_NBITS); u16 queue_index; /* Queue number of ring */ u8 dcb_tc; /* Traffic class of ring */ u8 __iomem *tail; @@ -361,59 +360,59 @@ struct i40e_ring { u8 packet_stride; u16 flags; -#define I40E_TXR_FLAGS_WB_ON_ITR BIT(0) -#define I40E_RXR_FLAGS_BUILD_SKB_ENABLED BIT(1) +#define IAVF_TXR_FLAGS_WB_ON_ITR BIT(0) +#define IAVF_RXR_FLAGS_BUILD_SKB_ENABLED BIT(1) /* stats structs */ - struct i40e_queue_stats stats; + struct iavf_queue_stats stats; struct u64_stats_sync syncp; union { - struct i40e_tx_queue_stats tx_stats; - struct i40e_rx_queue_stats rx_stats; + struct iavf_tx_queue_stats tx_stats; + struct iavf_rx_queue_stats rx_stats; }; unsigned int size; /* length of descriptor ring in bytes */ dma_addr_t dma; /* physical address of ring */ - struct i40e_vsi *vsi; /* Backreference to associated VSI */ - struct i40e_q_vector *q_vector; /* Backreference to associated vector */ + struct iavf_vsi *vsi; /* Backreference to associated VSI */ + struct iavf_q_vector *q_vector; /* Backreference to associated vector */ struct rcu_head rcu; /* to avoid race on free */ u16 next_to_alloc; - struct sk_buff *skb; /* When i40evf_clean_rx_ring_irq() must + struct sk_buff *skb; /* When iavf_clean_rx_ring_irq() must * return before it sees the EOP for * the current packet, we save that skb * here and resume receiving this * packet the next time - * i40evf_clean_rx_ring_irq() is called + * iavf_clean_rx_ring_irq() is called * for this ring. */ } ____cacheline_internodealigned_in_smp; -static inline bool ring_uses_build_skb(struct i40e_ring *ring) +static inline bool ring_uses_build_skb(struct iavf_ring *ring) { - return !!(ring->flags & I40E_RXR_FLAGS_BUILD_SKB_ENABLED); + return !!(ring->flags & IAVF_RXR_FLAGS_BUILD_SKB_ENABLED); } -static inline void set_ring_build_skb_enabled(struct i40e_ring *ring) +static inline void set_ring_build_skb_enabled(struct iavf_ring *ring) { - ring->flags |= I40E_RXR_FLAGS_BUILD_SKB_ENABLED; + ring->flags |= IAVF_RXR_FLAGS_BUILD_SKB_ENABLED; } -static inline void clear_ring_build_skb_enabled(struct i40e_ring *ring) +static inline void clear_ring_build_skb_enabled(struct iavf_ring *ring) { - ring->flags &= ~I40E_RXR_FLAGS_BUILD_SKB_ENABLED; + ring->flags &= ~IAVF_RXR_FLAGS_BUILD_SKB_ENABLED; } -#define I40E_ITR_ADAPTIVE_MIN_INC 0x0002 -#define I40E_ITR_ADAPTIVE_MIN_USECS 0x0002 -#define I40E_ITR_ADAPTIVE_MAX_USECS 0x007e -#define I40E_ITR_ADAPTIVE_LATENCY 0x8000 -#define I40E_ITR_ADAPTIVE_BULK 0x0000 -#define ITR_IS_BULK(x) (!((x) & I40E_ITR_ADAPTIVE_LATENCY)) +#define IAVF_ITR_ADAPTIVE_MIN_INC 0x0002 +#define IAVF_ITR_ADAPTIVE_MIN_USECS 0x0002 +#define IAVF_ITR_ADAPTIVE_MAX_USECS 0x007e +#define IAVF_ITR_ADAPTIVE_LATENCY 0x8000 +#define IAVF_ITR_ADAPTIVE_BULK 0x0000 +#define ITR_IS_BULK(x) (!((x) & IAVF_ITR_ADAPTIVE_LATENCY)) -struct i40e_ring_container { - struct i40e_ring *ring; /* pointer to linked list of ring(s) */ +struct iavf_ring_container { + struct iavf_ring *ring; /* pointer to linked list of ring(s) */ unsigned long next_update; /* jiffies value of next update */ unsigned int total_bytes; /* total bytes processed this int */ unsigned int total_packets; /* total packets processed this int */ @@ -423,10 +422,10 @@ struct i40e_ring_container { }; /* iterator for handling rings in ring container */ -#define i40e_for_each_ring(pos, head) \ +#define iavf_for_each_ring(pos, head) \ for (pos = (head).ring; pos != NULL; pos = pos->next) -static inline unsigned int i40e_rx_pg_order(struct i40e_ring *ring) +static inline unsigned int iavf_rx_pg_order(struct iavf_ring *ring) { #if (PAGE_SIZE < 8192) if (ring->rx_buf_len > (PAGE_SIZE / 2)) @@ -435,25 +434,25 @@ static inline unsigned int i40e_rx_pg_order(struct i40e_ring *ring) return 0; } -#define i40e_rx_pg_size(_ring) (PAGE_SIZE << i40e_rx_pg_order(_ring)) - -bool i40evf_alloc_rx_buffers(struct i40e_ring *rxr, u16 cleaned_count); -netdev_tx_t i40evf_xmit_frame(struct sk_buff *skb, struct net_device *netdev); -void i40evf_clean_tx_ring(struct i40e_ring *tx_ring); -void i40evf_clean_rx_ring(struct i40e_ring *rx_ring); -int i40evf_setup_tx_descriptors(struct i40e_ring *tx_ring); -int i40evf_setup_rx_descriptors(struct i40e_ring *rx_ring); -void i40evf_free_tx_resources(struct i40e_ring *tx_ring); -void i40evf_free_rx_resources(struct i40e_ring *rx_ring); -int i40evf_napi_poll(struct napi_struct *napi, int budget); -void i40evf_force_wb(struct i40e_vsi *vsi, struct i40e_q_vector *q_vector); -u32 i40evf_get_tx_pending(struct i40e_ring *ring, bool in_sw); -void i40evf_detect_recover_hung(struct i40e_vsi *vsi); -int __i40evf_maybe_stop_tx(struct i40e_ring *tx_ring, int size); -bool __i40evf_chk_linearize(struct sk_buff *skb); +#define iavf_rx_pg_size(_ring) (PAGE_SIZE << iavf_rx_pg_order(_ring)) + +bool iavf_alloc_rx_buffers(struct iavf_ring *rxr, u16 cleaned_count); +netdev_tx_t iavf_xmit_frame(struct sk_buff *skb, struct net_device *netdev); +void iavf_clean_tx_ring(struct iavf_ring *tx_ring); +void iavf_clean_rx_ring(struct iavf_ring *rx_ring); +int iavf_setup_tx_descriptors(struct iavf_ring *tx_ring); +int iavf_setup_rx_descriptors(struct iavf_ring *rx_ring); +void iavf_free_tx_resources(struct iavf_ring *tx_ring); +void iavf_free_rx_resources(struct iavf_ring *rx_ring); +int iavf_napi_poll(struct napi_struct *napi, int budget); +void iavf_force_wb(struct iavf_vsi *vsi, struct iavf_q_vector *q_vector); +u32 iavf_get_tx_pending(struct iavf_ring *ring, bool in_sw); +void iavf_detect_recover_hung(struct iavf_vsi *vsi); +int __iavf_maybe_stop_tx(struct iavf_ring *tx_ring, int size); +bool __iavf_chk_linearize(struct sk_buff *skb); /** - * i40e_xmit_descriptor_count - calculate number of Tx descriptors needed + * iavf_xmit_descriptor_count - calculate number of Tx descriptors needed * @skb: send buffer * @tx_ring: ring to send buffer on * @@ -461,14 +460,14 @@ bool __i40evf_chk_linearize(struct sk_buff *skb); * there is not enough descriptors available in this ring since we need at least * one descriptor. **/ -static inline int i40e_xmit_descriptor_count(struct sk_buff *skb) +static inline int iavf_xmit_descriptor_count(struct sk_buff *skb) { const struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0]; unsigned int nr_frags = skb_shinfo(skb)->nr_frags; int count = 0, size = skb_headlen(skb); for (;;) { - count += i40e_txd_use_count(size); + count += iavf_txd_use_count(size); if (!nr_frags--) break; @@ -480,21 +479,21 @@ static inline int i40e_xmit_descriptor_count(struct sk_buff *skb) } /** - * i40e_maybe_stop_tx - 1st level check for Tx stop conditions + * iavf_maybe_stop_tx - 1st level check for Tx stop conditions * @tx_ring: the ring to be checked * @size: the size buffer we want to assure is available * * Returns 0 if stop is not needed **/ -static inline int i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size) +static inline int iavf_maybe_stop_tx(struct iavf_ring *tx_ring, int size) { - if (likely(I40E_DESC_UNUSED(tx_ring) >= size)) + if (likely(IAVF_DESC_UNUSED(tx_ring) >= size)) return 0; - return __i40evf_maybe_stop_tx(tx_ring, size); + return __iavf_maybe_stop_tx(tx_ring, size); } /** - * i40e_chk_linearize - Check if there are more than 8 fragments per packet + * iavf_chk_linearize - Check if there are more than 8 fragments per packet * @skb: send buffer * @count: number of buffers used * @@ -502,23 +501,23 @@ static inline int i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size) * a packet on the wire and so we need to figure out the cases where we * need to linearize the skb. **/ -static inline bool i40e_chk_linearize(struct sk_buff *skb, int count) +static inline bool iavf_chk_linearize(struct sk_buff *skb, int count) { /* Both TSO and single send will work if count is less than 8 */ - if (likely(count < I40E_MAX_BUFFER_TXD)) + if (likely(count < IAVF_MAX_BUFFER_TXD)) return false; if (skb_is_gso(skb)) - return __i40evf_chk_linearize(skb); + return __iavf_chk_linearize(skb); /* we can support up to 8 data buffers for a single send */ - return count != I40E_MAX_BUFFER_TXD; + return count != IAVF_MAX_BUFFER_TXD; } /** * @ring: Tx ring to find the netdev equivalent of **/ -static inline struct netdev_queue *txring_txq(const struct i40e_ring *ring) +static inline struct netdev_queue *txring_txq(const struct iavf_ring *ring) { return netdev_get_tx_queue(ring->netdev, ring->queue_index); } -#endif /* _I40E_TXRX_H_ */ +#endif /* _IAVF_TXRX_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_type.h b/drivers/net/ethernet/intel/iavf/iavf_type.h new file mode 100644 index 000000000000..ca89583613fb --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_type.h @@ -0,0 +1,688 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + +#ifndef _IAVF_TYPE_H_ +#define _IAVF_TYPE_H_ + +#include "iavf_status.h" +#include "iavf_osdep.h" +#include "iavf_register.h" +#include "i40e_adminq.h" +#include "iavf_devids.h" + +#define IAVF_RXQ_CTX_DBUFF_SHIFT 7 + +/* IAVF_MASK is a macro used on 32 bit registers */ +#define IAVF_MASK(mask, shift) ((u32)(mask) << (shift)) + +#define IAVF_MAX_VSI_QP 16 +#define IAVF_MAX_VF_VSI 3 +#define IAVF_MAX_CHAINED_RX_BUFFERS 5 + +/* forward declaration */ +struct iavf_hw; +typedef void (*I40E_ADMINQ_CALLBACK)(struct iavf_hw *, struct i40e_aq_desc *); + +/* Data type manipulation macros. */ + +#define IAVF_DESC_UNUSED(R) \ + ((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \ + (R)->next_to_clean - (R)->next_to_use - 1) + +/* bitfields for Tx queue mapping in QTX_CTL */ +#define IAVF_QTX_CTL_VF_QUEUE 0x0 +#define IAVF_QTX_CTL_VM_QUEUE 0x1 +#define IAVF_QTX_CTL_PF_QUEUE 0x2 + +/* debug masks - set these bits in hw->debug_mask to control output */ +enum iavf_debug_mask { + IAVF_DEBUG_INIT = 0x00000001, + IAVF_DEBUG_RELEASE = 0x00000002, + + IAVF_DEBUG_LINK = 0x00000010, + IAVF_DEBUG_PHY = 0x00000020, + IAVF_DEBUG_HMC = 0x00000040, + IAVF_DEBUG_NVM = 0x00000080, + IAVF_DEBUG_LAN = 0x00000100, + IAVF_DEBUG_FLOW = 0x00000200, + IAVF_DEBUG_DCB = 0x00000400, + IAVF_DEBUG_DIAG = 0x00000800, + IAVF_DEBUG_FD = 0x00001000, + IAVF_DEBUG_PACKAGE = 0x00002000, + + IAVF_DEBUG_AQ_MESSAGE = 0x01000000, + IAVF_DEBUG_AQ_DESCRIPTOR = 0x02000000, + IAVF_DEBUG_AQ_DESC_BUFFER = 0x04000000, + IAVF_DEBUG_AQ_COMMAND = 0x06000000, + IAVF_DEBUG_AQ = 0x0F000000, + + IAVF_DEBUG_USER = 0xF0000000, + + IAVF_DEBUG_ALL = 0xFFFFFFFF +}; + +/* These are structs for managing the hardware information and the operations. + * The structures of function pointers are filled out at init time when we + * know for sure exactly which hardware we're working with. This gives us the + * flexibility of using the same main driver code but adapting to slightly + * different hardware needs as new parts are developed. For this architecture, + * the Firmware and AdminQ are intended to insulate the driver from most of the + * future changes, but these structures will also do part of the job. + */ +enum iavf_mac_type { + IAVF_MAC_UNKNOWN = 0, + IAVF_MAC_XL710, + IAVF_MAC_VF, + IAVF_MAC_X722, + IAVF_MAC_X722_VF, + IAVF_MAC_GENERIC, +}; + +enum iavf_vsi_type { + IAVF_VSI_MAIN = 0, + IAVF_VSI_VMDQ1 = 1, + IAVF_VSI_VMDQ2 = 2, + IAVF_VSI_CTRL = 3, + IAVF_VSI_FCOE = 4, + IAVF_VSI_MIRROR = 5, + IAVF_VSI_SRIOV = 6, + IAVF_VSI_FDIR = 7, + IAVF_VSI_TYPE_UNKNOWN +}; + +enum iavf_queue_type { + IAVF_QUEUE_TYPE_RX = 0, + IAVF_QUEUE_TYPE_TX, + IAVF_QUEUE_TYPE_PE_CEQ, + IAVF_QUEUE_TYPE_UNKNOWN +}; + +#define IAVF_HW_CAP_MAX_GPIO 30 +/* Capabilities of a PF or a VF or the whole device */ +struct iavf_hw_capabilities { + bool dcb; + bool fcoe; + u32 num_vsis; + u32 num_rx_qp; + u32 num_tx_qp; + u32 base_queue; + u32 num_msix_vectors_vf; +}; + +struct iavf_mac_info { + enum iavf_mac_type type; + u8 addr[ETH_ALEN]; + u8 perm_addr[ETH_ALEN]; + u8 san_addr[ETH_ALEN]; + u16 max_fcoeq; +}; + +/* PCI bus types */ +enum iavf_bus_type { + iavf_bus_type_unknown = 0, + iavf_bus_type_pci, + iavf_bus_type_pcix, + iavf_bus_type_pci_express, + iavf_bus_type_reserved +}; + +/* PCI bus speeds */ +enum iavf_bus_speed { + iavf_bus_speed_unknown = 0, + iavf_bus_speed_33 = 33, + iavf_bus_speed_66 = 66, + iavf_bus_speed_100 = 100, + iavf_bus_speed_120 = 120, + iavf_bus_speed_133 = 133, + iavf_bus_speed_2500 = 2500, + iavf_bus_speed_5000 = 5000, + iavf_bus_speed_8000 = 8000, + iavf_bus_speed_reserved +}; + +/* PCI bus widths */ +enum iavf_bus_width { + iavf_bus_width_unknown = 0, + iavf_bus_width_pcie_x1 = 1, + iavf_bus_width_pcie_x2 = 2, + iavf_bus_width_pcie_x4 = 4, + iavf_bus_width_pcie_x8 = 8, + iavf_bus_width_32 = 32, + iavf_bus_width_64 = 64, + iavf_bus_width_reserved +}; + +/* Bus parameters */ +struct iavf_bus_info { + enum iavf_bus_speed speed; + enum iavf_bus_width width; + enum iavf_bus_type type; + + u16 func; + u16 device; + u16 lan_id; + u16 bus_id; +}; + +#define IAVF_MAX_USER_PRIORITY 8 +/* Port hardware description */ +struct iavf_hw { + u8 __iomem *hw_addr; + void *back; + + /* subsystem structs */ + struct iavf_mac_info mac; + struct iavf_bus_info bus; + + /* pci info */ + u16 device_id; + u16 vendor_id; + u16 subsystem_device_id; + u16 subsystem_vendor_id; + u8 revision_id; + + /* capabilities for entire device and PCI func */ + struct iavf_hw_capabilities dev_caps; + + /* Admin Queue info */ + struct iavf_adminq_info aq; + + /* debug mask */ + u32 debug_mask; + char err_str[16]; +}; + +struct iavf_driver_version { + u8 major_version; + u8 minor_version; + u8 build_version; + u8 subbuild_version; + u8 driver_string[32]; +}; + +/* RX Descriptors */ +union iavf_16byte_rx_desc { + struct { + __le64 pkt_addr; /* Packet buffer address */ + __le64 hdr_addr; /* Header buffer address */ + } read; + struct { + struct { + struct { + union { + __le16 mirroring_status; + __le16 fcoe_ctx_id; + } mirr_fcoe; + __le16 l2tag1; + } lo_dword; + union { + __le32 rss; /* RSS Hash */ + __le32 fd_id; /* Flow director filter id */ + __le32 fcoe_param; /* FCoE DDP Context id */ + } hi_dword; + } qword0; + struct { + /* ext status/error/pktype/length */ + __le64 status_error_len; + } qword1; + } wb; /* writeback */ +}; + +union iavf_32byte_rx_desc { + struct { + __le64 pkt_addr; /* Packet buffer address */ + __le64 hdr_addr; /* Header buffer address */ + /* bit 0 of hdr_buffer_addr is DD bit */ + __le64 rsvd1; + __le64 rsvd2; + } read; + struct { + struct { + struct { + union { + __le16 mirroring_status; + __le16 fcoe_ctx_id; + } mirr_fcoe; + __le16 l2tag1; + } lo_dword; + union { + __le32 rss; /* RSS Hash */ + __le32 fcoe_param; /* FCoE DDP Context id */ + /* Flow director filter id in case of + * Programming status desc WB + */ + __le32 fd_id; + } hi_dword; + } qword0; + struct { + /* status/error/pktype/length */ + __le64 status_error_len; + } qword1; + struct { + __le16 ext_status; /* extended status */ + __le16 rsvd; + __le16 l2tag2_1; + __le16 l2tag2_2; + } qword2; + struct { + union { + __le32 flex_bytes_lo; + __le32 pe_status; + } lo_dword; + union { + __le32 flex_bytes_hi; + __le32 fd_id; + } hi_dword; + } qword3; + } wb; /* writeback */ +}; + +enum iavf_rx_desc_status_bits { + /* Note: These are predefined bit offsets */ + IAVF_RX_DESC_STATUS_DD_SHIFT = 0, + IAVF_RX_DESC_STATUS_EOF_SHIFT = 1, + IAVF_RX_DESC_STATUS_L2TAG1P_SHIFT = 2, + IAVF_RX_DESC_STATUS_L3L4P_SHIFT = 3, + IAVF_RX_DESC_STATUS_CRCP_SHIFT = 4, + IAVF_RX_DESC_STATUS_TSYNINDX_SHIFT = 5, /* 2 BITS */ + IAVF_RX_DESC_STATUS_TSYNVALID_SHIFT = 7, + /* Note: Bit 8 is reserved in X710 and XL710 */ + IAVF_RX_DESC_STATUS_EXT_UDP_0_SHIFT = 8, + IAVF_RX_DESC_STATUS_UMBCAST_SHIFT = 9, /* 2 BITS */ + IAVF_RX_DESC_STATUS_FLM_SHIFT = 11, + IAVF_RX_DESC_STATUS_FLTSTAT_SHIFT = 12, /* 2 BITS */ + IAVF_RX_DESC_STATUS_LPBK_SHIFT = 14, + IAVF_RX_DESC_STATUS_IPV6EXADD_SHIFT = 15, + IAVF_RX_DESC_STATUS_RESERVED_SHIFT = 16, /* 2 BITS */ + /* Note: For non-tunnel packets INT_UDP_0 is the right status for + * UDP header + */ + IAVF_RX_DESC_STATUS_INT_UDP_0_SHIFT = 18, + IAVF_RX_DESC_STATUS_LAST /* this entry must be last!!! */ +}; + +#define IAVF_RXD_QW1_STATUS_SHIFT 0 +#define IAVF_RXD_QW1_STATUS_MASK ((BIT(IAVF_RX_DESC_STATUS_LAST) - 1) \ + << IAVF_RXD_QW1_STATUS_SHIFT) + +#define IAVF_RXD_QW1_STATUS_TSYNINDX_SHIFT IAVF_RX_DESC_STATUS_TSYNINDX_SHIFT +#define IAVF_RXD_QW1_STATUS_TSYNINDX_MASK (0x3UL << \ + IAVF_RXD_QW1_STATUS_TSYNINDX_SHIFT) + +#define IAVF_RXD_QW1_STATUS_TSYNVALID_SHIFT IAVF_RX_DESC_STATUS_TSYNVALID_SHIFT +#define IAVF_RXD_QW1_STATUS_TSYNVALID_MASK \ + BIT_ULL(IAVF_RXD_QW1_STATUS_TSYNVALID_SHIFT) + +enum iavf_rx_desc_fltstat_values { + IAVF_RX_DESC_FLTSTAT_NO_DATA = 0, + IAVF_RX_DESC_FLTSTAT_RSV_FD_ID = 1, /* 16byte desc? FD_ID : RSV */ + IAVF_RX_DESC_FLTSTAT_RSV = 2, + IAVF_RX_DESC_FLTSTAT_RSS_HASH = 3, +}; + +#define IAVF_RXD_QW1_ERROR_SHIFT 19 +#define IAVF_RXD_QW1_ERROR_MASK (0xFFUL << IAVF_RXD_QW1_ERROR_SHIFT) + +enum iavf_rx_desc_error_bits { + /* Note: These are predefined bit offsets */ + IAVF_RX_DESC_ERROR_RXE_SHIFT = 0, + IAVF_RX_DESC_ERROR_RECIPE_SHIFT = 1, + IAVF_RX_DESC_ERROR_HBO_SHIFT = 2, + IAVF_RX_DESC_ERROR_L3L4E_SHIFT = 3, /* 3 BITS */ + IAVF_RX_DESC_ERROR_IPE_SHIFT = 3, + IAVF_RX_DESC_ERROR_L4E_SHIFT = 4, + IAVF_RX_DESC_ERROR_EIPE_SHIFT = 5, + IAVF_RX_DESC_ERROR_OVERSIZE_SHIFT = 6, + IAVF_RX_DESC_ERROR_PPRS_SHIFT = 7 +}; + +enum iavf_rx_desc_error_l3l4e_fcoe_masks { + IAVF_RX_DESC_ERROR_L3L4E_NONE = 0, + IAVF_RX_DESC_ERROR_L3L4E_PROT = 1, + IAVF_RX_DESC_ERROR_L3L4E_FC = 2, + IAVF_RX_DESC_ERROR_L3L4E_DMAC_ERR = 3, + IAVF_RX_DESC_ERROR_L3L4E_DMAC_WARN = 4 +}; + +#define IAVF_RXD_QW1_PTYPE_SHIFT 30 +#define IAVF_RXD_QW1_PTYPE_MASK (0xFFULL << IAVF_RXD_QW1_PTYPE_SHIFT) + +/* Packet type non-ip values */ +enum iavf_rx_l2_ptype { + IAVF_RX_PTYPE_L2_RESERVED = 0, + IAVF_RX_PTYPE_L2_MAC_PAY2 = 1, + IAVF_RX_PTYPE_L2_TIMESYNC_PAY2 = 2, + IAVF_RX_PTYPE_L2_FIP_PAY2 = 3, + IAVF_RX_PTYPE_L2_OUI_PAY2 = 4, + IAVF_RX_PTYPE_L2_MACCNTRL_PAY2 = 5, + IAVF_RX_PTYPE_L2_LLDP_PAY2 = 6, + IAVF_RX_PTYPE_L2_ECP_PAY2 = 7, + IAVF_RX_PTYPE_L2_EVB_PAY2 = 8, + IAVF_RX_PTYPE_L2_QCN_PAY2 = 9, + IAVF_RX_PTYPE_L2_EAPOL_PAY2 = 10, + IAVF_RX_PTYPE_L2_ARP = 11, + IAVF_RX_PTYPE_L2_FCOE_PAY3 = 12, + IAVF_RX_PTYPE_L2_FCOE_FCDATA_PAY3 = 13, + IAVF_RX_PTYPE_L2_FCOE_FCRDY_PAY3 = 14, + IAVF_RX_PTYPE_L2_FCOE_FCRSP_PAY3 = 15, + IAVF_RX_PTYPE_L2_FCOE_FCOTHER_PA = 16, + IAVF_RX_PTYPE_L2_FCOE_VFT_PAY3 = 17, + IAVF_RX_PTYPE_L2_FCOE_VFT_FCDATA = 18, + IAVF_RX_PTYPE_L2_FCOE_VFT_FCRDY = 19, + IAVF_RX_PTYPE_L2_FCOE_VFT_FCRSP = 20, + IAVF_RX_PTYPE_L2_FCOE_VFT_FCOTHER = 21, + IAVF_RX_PTYPE_GRENAT4_MAC_PAY3 = 58, + IAVF_RX_PTYPE_GRENAT4_MACVLAN_IPV6_ICMP_PAY4 = 87, + IAVF_RX_PTYPE_GRENAT6_MAC_PAY3 = 124, + IAVF_RX_PTYPE_GRENAT6_MACVLAN_IPV6_ICMP_PAY4 = 153 +}; + +struct iavf_rx_ptype_decoded { + u32 ptype:8; + u32 known:1; + u32 outer_ip:1; + u32 outer_ip_ver:1; + u32 outer_frag:1; + u32 tunnel_type:3; + u32 tunnel_end_prot:2; + u32 tunnel_end_frag:1; + u32 inner_prot:4; + u32 payload_layer:3; +}; + +enum iavf_rx_ptype_outer_ip { + IAVF_RX_PTYPE_OUTER_L2 = 0, + IAVF_RX_PTYPE_OUTER_IP = 1 +}; + +enum iavf_rx_ptype_outer_ip_ver { + IAVF_RX_PTYPE_OUTER_NONE = 0, + IAVF_RX_PTYPE_OUTER_IPV4 = 0, + IAVF_RX_PTYPE_OUTER_IPV6 = 1 +}; + +enum iavf_rx_ptype_outer_fragmented { + IAVF_RX_PTYPE_NOT_FRAG = 0, + IAVF_RX_PTYPE_FRAG = 1 +}; + +enum iavf_rx_ptype_tunnel_type { + IAVF_RX_PTYPE_TUNNEL_NONE = 0, + IAVF_RX_PTYPE_TUNNEL_IP_IP = 1, + IAVF_RX_PTYPE_TUNNEL_IP_GRENAT = 2, + IAVF_RX_PTYPE_TUNNEL_IP_GRENAT_MAC = 3, + IAVF_RX_PTYPE_TUNNEL_IP_GRENAT_MAC_VLAN = 4, +}; + +enum iavf_rx_ptype_tunnel_end_prot { + IAVF_RX_PTYPE_TUNNEL_END_NONE = 0, + IAVF_RX_PTYPE_TUNNEL_END_IPV4 = 1, + IAVF_RX_PTYPE_TUNNEL_END_IPV6 = 2, +}; + +enum iavf_rx_ptype_inner_prot { + IAVF_RX_PTYPE_INNER_PROT_NONE = 0, + IAVF_RX_PTYPE_INNER_PROT_UDP = 1, + IAVF_RX_PTYPE_INNER_PROT_TCP = 2, + IAVF_RX_PTYPE_INNER_PROT_SCTP = 3, + IAVF_RX_PTYPE_INNER_PROT_ICMP = 4, + IAVF_RX_PTYPE_INNER_PROT_TIMESYNC = 5 +}; + +enum iavf_rx_ptype_payload_layer { + IAVF_RX_PTYPE_PAYLOAD_LAYER_NONE = 0, + IAVF_RX_PTYPE_PAYLOAD_LAYER_PAY2 = 1, + IAVF_RX_PTYPE_PAYLOAD_LAYER_PAY3 = 2, + IAVF_RX_PTYPE_PAYLOAD_LAYER_PAY4 = 3, +}; + +#define IAVF_RXD_QW1_LENGTH_PBUF_SHIFT 38 +#define IAVF_RXD_QW1_LENGTH_PBUF_MASK (0x3FFFULL << \ + IAVF_RXD_QW1_LENGTH_PBUF_SHIFT) + +#define IAVF_RXD_QW1_LENGTH_HBUF_SHIFT 52 +#define IAVF_RXD_QW1_LENGTH_HBUF_MASK (0x7FFULL << \ + IAVF_RXD_QW1_LENGTH_HBUF_SHIFT) + +#define IAVF_RXD_QW1_LENGTH_SPH_SHIFT 63 +#define IAVF_RXD_QW1_LENGTH_SPH_MASK BIT_ULL(IAVF_RXD_QW1_LENGTH_SPH_SHIFT) + +enum iavf_rx_desc_ext_status_bits { + /* Note: These are predefined bit offsets */ + IAVF_RX_DESC_EXT_STATUS_L2TAG2P_SHIFT = 0, + IAVF_RX_DESC_EXT_STATUS_L2TAG3P_SHIFT = 1, + IAVF_RX_DESC_EXT_STATUS_FLEXBL_SHIFT = 2, /* 2 BITS */ + IAVF_RX_DESC_EXT_STATUS_FLEXBH_SHIFT = 4, /* 2 BITS */ + IAVF_RX_DESC_EXT_STATUS_FDLONGB_SHIFT = 9, + IAVF_RX_DESC_EXT_STATUS_FCOELONGB_SHIFT = 10, + IAVF_RX_DESC_EXT_STATUS_PELONGB_SHIFT = 11, +}; + +enum iavf_rx_desc_pe_status_bits { + /* Note: These are predefined bit offsets */ + IAVF_RX_DESC_PE_STATUS_QPID_SHIFT = 0, /* 18 BITS */ + IAVF_RX_DESC_PE_STATUS_L4PORT_SHIFT = 0, /* 16 BITS */ + IAVF_RX_DESC_PE_STATUS_IPINDEX_SHIFT = 16, /* 8 BITS */ + IAVF_RX_DESC_PE_STATUS_QPIDHIT_SHIFT = 24, + IAVF_RX_DESC_PE_STATUS_APBVTHIT_SHIFT = 25, + IAVF_RX_DESC_PE_STATUS_PORTV_SHIFT = 26, + IAVF_RX_DESC_PE_STATUS_URG_SHIFT = 27, + IAVF_RX_DESC_PE_STATUS_IPFRAG_SHIFT = 28, + IAVF_RX_DESC_PE_STATUS_IPOPT_SHIFT = 29 +}; + +#define IAVF_RX_PROG_STATUS_DESC_LENGTH_SHIFT 38 +#define IAVF_RX_PROG_STATUS_DESC_LENGTH 0x2000000 + +#define IAVF_RX_PROG_STATUS_DESC_QW1_PROGID_SHIFT 2 +#define IAVF_RX_PROG_STATUS_DESC_QW1_PROGID_MASK (0x7UL << \ + IAVF_RX_PROG_STATUS_DESC_QW1_PROGID_SHIFT) + +#define IAVF_RX_PROG_STATUS_DESC_QW1_ERROR_SHIFT 19 +#define IAVF_RX_PROG_STATUS_DESC_QW1_ERROR_MASK (0x3FUL << \ + IAVF_RX_PROG_STATUS_DESC_QW1_ERROR_SHIFT) + +enum iavf_rx_prog_status_desc_status_bits { + /* Note: These are predefined bit offsets */ + IAVF_RX_PROG_STATUS_DESC_DD_SHIFT = 0, + IAVF_RX_PROG_STATUS_DESC_PROG_ID_SHIFT = 2 /* 3 BITS */ +}; + +enum iavf_rx_prog_status_desc_prog_id_masks { + IAVF_RX_PROG_STATUS_DESC_FD_FILTER_STATUS = 1, + IAVF_RX_PROG_STATUS_DESC_FCOE_CTXT_PROG_STATUS = 2, + IAVF_RX_PROG_STATUS_DESC_FCOE_CTXT_INVL_STATUS = 4, +}; + +enum iavf_rx_prog_status_desc_error_bits { + /* Note: These are predefined bit offsets */ + IAVF_RX_PROG_STATUS_DESC_FD_TBL_FULL_SHIFT = 0, + IAVF_RX_PROG_STATUS_DESC_NO_FD_ENTRY_SHIFT = 1, + IAVF_RX_PROG_STATUS_DESC_FCOE_TBL_FULL_SHIFT = 2, + IAVF_RX_PROG_STATUS_DESC_FCOE_CONFLICT_SHIFT = 3 +}; + +/* TX Descriptor */ +struct iavf_tx_desc { + __le64 buffer_addr; /* Address of descriptor's data buf */ + __le64 cmd_type_offset_bsz; +}; + +#define IAVF_TXD_QW1_DTYPE_SHIFT 0 +#define IAVF_TXD_QW1_DTYPE_MASK (0xFUL << IAVF_TXD_QW1_DTYPE_SHIFT) + +enum iavf_tx_desc_dtype_value { + IAVF_TX_DESC_DTYPE_DATA = 0x0, + IAVF_TX_DESC_DTYPE_NOP = 0x1, /* same as Context desc */ + IAVF_TX_DESC_DTYPE_CONTEXT = 0x1, + IAVF_TX_DESC_DTYPE_FCOE_CTX = 0x2, + IAVF_TX_DESC_DTYPE_FILTER_PROG = 0x8, + IAVF_TX_DESC_DTYPE_DDP_CTX = 0x9, + IAVF_TX_DESC_DTYPE_FLEX_DATA = 0xB, + IAVF_TX_DESC_DTYPE_FLEX_CTX_1 = 0xC, + IAVF_TX_DESC_DTYPE_FLEX_CTX_2 = 0xD, + IAVF_TX_DESC_DTYPE_DESC_DONE = 0xF +}; + +#define IAVF_TXD_QW1_CMD_SHIFT 4 +#define IAVF_TXD_QW1_CMD_MASK (0x3FFUL << IAVF_TXD_QW1_CMD_SHIFT) + +enum iavf_tx_desc_cmd_bits { + IAVF_TX_DESC_CMD_EOP = 0x0001, + IAVF_TX_DESC_CMD_RS = 0x0002, + IAVF_TX_DESC_CMD_ICRC = 0x0004, + IAVF_TX_DESC_CMD_IL2TAG1 = 0x0008, + IAVF_TX_DESC_CMD_DUMMY = 0x0010, + IAVF_TX_DESC_CMD_IIPT_NONIP = 0x0000, /* 2 BITS */ + IAVF_TX_DESC_CMD_IIPT_IPV6 = 0x0020, /* 2 BITS */ + IAVF_TX_DESC_CMD_IIPT_IPV4 = 0x0040, /* 2 BITS */ + IAVF_TX_DESC_CMD_IIPT_IPV4_CSUM = 0x0060, /* 2 BITS */ + IAVF_TX_DESC_CMD_FCOET = 0x0080, + IAVF_TX_DESC_CMD_L4T_EOFT_UNK = 0x0000, /* 2 BITS */ + IAVF_TX_DESC_CMD_L4T_EOFT_TCP = 0x0100, /* 2 BITS */ + IAVF_TX_DESC_CMD_L4T_EOFT_SCTP = 0x0200, /* 2 BITS */ + IAVF_TX_DESC_CMD_L4T_EOFT_UDP = 0x0300, /* 2 BITS */ + IAVF_TX_DESC_CMD_L4T_EOFT_EOF_N = 0x0000, /* 2 BITS */ + IAVF_TX_DESC_CMD_L4T_EOFT_EOF_T = 0x0100, /* 2 BITS */ + IAVF_TX_DESC_CMD_L4T_EOFT_EOF_NI = 0x0200, /* 2 BITS */ + IAVF_TX_DESC_CMD_L4T_EOFT_EOF_A = 0x0300, /* 2 BITS */ +}; + +#define IAVF_TXD_QW1_OFFSET_SHIFT 16 +#define IAVF_TXD_QW1_OFFSET_MASK (0x3FFFFULL << \ + IAVF_TXD_QW1_OFFSET_SHIFT) + +enum iavf_tx_desc_length_fields { + /* Note: These are predefined bit offsets */ + IAVF_TX_DESC_LENGTH_MACLEN_SHIFT = 0, /* 7 BITS */ + IAVF_TX_DESC_LENGTH_IPLEN_SHIFT = 7, /* 7 BITS */ + IAVF_TX_DESC_LENGTH_L4_FC_LEN_SHIFT = 14 /* 4 BITS */ +}; + +#define IAVF_TXD_QW1_TX_BUF_SZ_SHIFT 34 +#define IAVF_TXD_QW1_TX_BUF_SZ_MASK (0x3FFFULL << \ + IAVF_TXD_QW1_TX_BUF_SZ_SHIFT) + +#define IAVF_TXD_QW1_L2TAG1_SHIFT 48 +#define IAVF_TXD_QW1_L2TAG1_MASK (0xFFFFULL << IAVF_TXD_QW1_L2TAG1_SHIFT) + +/* Context descriptors */ +struct iavf_tx_context_desc { + __le32 tunneling_params; + __le16 l2tag2; + __le16 rsvd; + __le64 type_cmd_tso_mss; +}; + +#define IAVF_TXD_CTX_QW1_CMD_SHIFT 4 +#define IAVF_TXD_CTX_QW1_CMD_MASK (0xFFFFUL << IAVF_TXD_CTX_QW1_CMD_SHIFT) + +enum iavf_tx_ctx_desc_cmd_bits { + IAVF_TX_CTX_DESC_TSO = 0x01, + IAVF_TX_CTX_DESC_TSYN = 0x02, + IAVF_TX_CTX_DESC_IL2TAG2 = 0x04, + IAVF_TX_CTX_DESC_IL2TAG2_IL2H = 0x08, + IAVF_TX_CTX_DESC_SWTCH_NOTAG = 0x00, + IAVF_TX_CTX_DESC_SWTCH_UPLINK = 0x10, + IAVF_TX_CTX_DESC_SWTCH_LOCAL = 0x20, + IAVF_TX_CTX_DESC_SWTCH_VSI = 0x30, + IAVF_TX_CTX_DESC_SWPE = 0x40 +}; + +/* Packet Classifier Types for filters */ +enum iavf_filter_pctype { + /* Note: Values 0-28 are reserved for future use. + * Value 29, 30, 32 are not supported on XL710 and X710. + */ + IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP = 29, + IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP = 30, + IAVF_FILTER_PCTYPE_NONF_IPV4_UDP = 31, + IAVF_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK = 32, + IAVF_FILTER_PCTYPE_NONF_IPV4_TCP = 33, + IAVF_FILTER_PCTYPE_NONF_IPV4_SCTP = 34, + IAVF_FILTER_PCTYPE_NONF_IPV4_OTHER = 35, + IAVF_FILTER_PCTYPE_FRAG_IPV4 = 36, + /* Note: Values 37-38 are reserved for future use. + * Value 39, 40, 42 are not supported on XL710 and X710. + */ + IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP = 39, + IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP = 40, + IAVF_FILTER_PCTYPE_NONF_IPV6_UDP = 41, + IAVF_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK = 42, + IAVF_FILTER_PCTYPE_NONF_IPV6_TCP = 43, + IAVF_FILTER_PCTYPE_NONF_IPV6_SCTP = 44, + IAVF_FILTER_PCTYPE_NONF_IPV6_OTHER = 45, + IAVF_FILTER_PCTYPE_FRAG_IPV6 = 46, + /* Note: Value 47 is reserved for future use */ + IAVF_FILTER_PCTYPE_FCOE_OX = 48, + IAVF_FILTER_PCTYPE_FCOE_RX = 49, + IAVF_FILTER_PCTYPE_FCOE_OTHER = 50, + /* Note: Values 51-62 are reserved for future use */ + IAVF_FILTER_PCTYPE_L2_PAYLOAD = 63, +}; + +#define IAVF_TXD_CTX_QW1_TSO_LEN_SHIFT 30 +#define IAVF_TXD_CTX_QW1_TSO_LEN_MASK (0x3FFFFULL << \ + IAVF_TXD_CTX_QW1_TSO_LEN_SHIFT) + +#define IAVF_TXD_CTX_QW1_MSS_SHIFT 50 +#define IAVF_TXD_CTX_QW1_MSS_MASK (0x3FFFULL << \ + IAVF_TXD_CTX_QW1_MSS_SHIFT) + +#define IAVF_TXD_CTX_QW1_VSI_SHIFT 50 +#define IAVF_TXD_CTX_QW1_VSI_MASK (0x1FFULL << IAVF_TXD_CTX_QW1_VSI_SHIFT) + +#define IAVF_TXD_CTX_QW0_EXT_IP_SHIFT 0 +#define IAVF_TXD_CTX_QW0_EXT_IP_MASK (0x3ULL << \ + IAVF_TXD_CTX_QW0_EXT_IP_SHIFT) + +enum iavf_tx_ctx_desc_eipt_offload { + IAVF_TX_CTX_EXT_IP_NONE = 0x0, + IAVF_TX_CTX_EXT_IP_IPV6 = 0x1, + IAVF_TX_CTX_EXT_IP_IPV4_NO_CSUM = 0x2, + IAVF_TX_CTX_EXT_IP_IPV4 = 0x3 +}; + +#define IAVF_TXD_CTX_QW0_EXT_IPLEN_SHIFT 2 +#define IAVF_TXD_CTX_QW0_EXT_IPLEN_MASK (0x3FULL << \ + IAVF_TXD_CTX_QW0_EXT_IPLEN_SHIFT) + +#define IAVF_TXD_CTX_QW0_NATT_SHIFT 9 +#define IAVF_TXD_CTX_QW0_NATT_MASK (0x3ULL << IAVF_TXD_CTX_QW0_NATT_SHIFT) + +#define IAVF_TXD_CTX_UDP_TUNNELING BIT_ULL(IAVF_TXD_CTX_QW0_NATT_SHIFT) +#define IAVF_TXD_CTX_GRE_TUNNELING (0x2ULL << IAVF_TXD_CTX_QW0_NATT_SHIFT) + +#define IAVF_TXD_CTX_QW0_EIP_NOINC_SHIFT 11 +#define IAVF_TXD_CTX_QW0_EIP_NOINC_MASK \ + BIT_ULL(IAVF_TXD_CTX_QW0_EIP_NOINC_SHIFT) + +#define IAVF_TXD_CTX_EIP_NOINC_IPID_CONST IAVF_TXD_CTX_QW0_EIP_NOINC_MASK + +#define IAVF_TXD_CTX_QW0_NATLEN_SHIFT 12 +#define IAVF_TXD_CTX_QW0_NATLEN_MASK (0X7FULL << \ + IAVF_TXD_CTX_QW0_NATLEN_SHIFT) + +#define IAVF_TXD_CTX_QW0_DECTTL_SHIFT 19 +#define IAVF_TXD_CTX_QW0_DECTTL_MASK (0xFULL << \ + IAVF_TXD_CTX_QW0_DECTTL_SHIFT) + +#define IAVF_TXD_CTX_QW0_L4T_CS_SHIFT 23 +#define IAVF_TXD_CTX_QW0_L4T_CS_MASK BIT_ULL(IAVF_TXD_CTX_QW0_L4T_CS_SHIFT) + +/* Statistics collected by each port, VSI, VEB, and S-channel */ +struct iavf_eth_stats { + u64 rx_bytes; /* gorc */ + u64 rx_unicast; /* uprc */ + u64 rx_multicast; /* mprc */ + u64 rx_broadcast; /* bprc */ + u64 rx_discards; /* rdpc */ + u64 rx_unknown_protocol; /* rupp */ + u64 tx_bytes; /* gotc */ + u64 tx_unicast; /* uptc */ + u64 tx_multicast; /* mptc */ + u64 tx_broadcast; /* bptc */ + u64 tx_discards; /* tdpc */ + u64 tx_errors; /* tepc */ +}; +#endif /* _IAVF_TYPE_H_ */ diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 565677de5ba3..e64751da0921 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -1,16 +1,16 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2013 - 2018 Intel Corporation. */ -#include "i40evf.h" -#include "i40e_prototype.h" -#include "i40evf_client.h" +#include "iavf.h" +#include "iavf_prototype.h" +#include "iavf_client.h" /* busy wait delay in msec */ -#define I40EVF_BUSY_WAIT_DELAY 10 -#define I40EVF_BUSY_WAIT_COUNT 50 +#define IAVF_BUSY_WAIT_DELAY 10 +#define IAVF_BUSY_WAIT_COUNT 50 /** - * i40evf_send_pf_msg + * iavf_send_pf_msg * @adapter: adapter structure * @op: virtual channel opcode * @msg: pointer to message buffer @@ -18,44 +18,44 @@ * * Send message to PF and print status if failure. **/ -static int i40evf_send_pf_msg(struct i40evf_adapter *adapter, - enum virtchnl_ops op, u8 *msg, u16 len) +static int iavf_send_pf_msg(struct iavf_adapter *adapter, + enum virtchnl_ops op, u8 *msg, u16 len) { - struct i40e_hw *hw = &adapter->hw; - i40e_status err; + struct iavf_hw *hw = &adapter->hw; + iavf_status err; - if (adapter->flags & I40EVF_FLAG_PF_COMMS_FAILED) + if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) return 0; /* nothing to see here, move along */ - err = i40e_aq_send_msg_to_pf(hw, op, 0, msg, len, NULL); + err = iavf_aq_send_msg_to_pf(hw, op, 0, msg, len, NULL); if (err) dev_dbg(&adapter->pdev->dev, "Unable to send opcode %d to PF, err %s, aq_err %s\n", - op, i40evf_stat_str(hw, err), - i40evf_aq_str(hw, hw->aq.asq_last_status)); + op, iavf_stat_str(hw, err), + iavf_aq_str(hw, hw->aq.asq_last_status)); return err; } /** - * i40evf_send_api_ver + * iavf_send_api_ver * @adapter: adapter structure * * Send API version admin queue message to the PF. The reply is not checked * in this function. Returns 0 if the message was successfully * sent, or one of the I40E_ADMIN_QUEUE_ERROR_ statuses if not. **/ -int i40evf_send_api_ver(struct i40evf_adapter *adapter) +int iavf_send_api_ver(struct iavf_adapter *adapter) { struct virtchnl_version_info vvi; vvi.major = VIRTCHNL_VERSION_MAJOR; vvi.minor = VIRTCHNL_VERSION_MINOR; - return i40evf_send_pf_msg(adapter, VIRTCHNL_OP_VERSION, (u8 *)&vvi, - sizeof(vvi)); + return iavf_send_pf_msg(adapter, VIRTCHNL_OP_VERSION, (u8 *)&vvi, + sizeof(vvi)); } /** - * i40evf_verify_api_ver + * iavf_verify_api_ver * @adapter: adapter structure * * Compare API versions with the PF. Must be called after admin queue is @@ -63,15 +63,15 @@ int i40evf_send_api_ver(struct i40evf_adapter *adapter) * I40E_ERR_ADMIN_QUEUE_NO_WORK if the admin queue is empty, and any errors * from the firmware are propagated. **/ -int i40evf_verify_api_ver(struct i40evf_adapter *adapter) +int iavf_verify_api_ver(struct iavf_adapter *adapter) { struct virtchnl_version_info *pf_vvi; - struct i40e_hw *hw = &adapter->hw; + struct iavf_hw *hw = &adapter->hw; struct i40e_arq_event_info event; enum virtchnl_ops op; - i40e_status err; + iavf_status err; - event.buf_len = I40EVF_MAX_AQ_BUF_SIZE; + event.buf_len = IAVF_MAX_AQ_BUF_SIZE; event.msg_buf = kzalloc(event.buf_len, GFP_KERNEL); if (!event.msg_buf) { err = -ENOMEM; @@ -79,8 +79,8 @@ int i40evf_verify_api_ver(struct i40evf_adapter *adapter) } while (1) { - err = i40evf_clean_arq_element(hw, &event, NULL); - /* When the AQ is empty, i40evf_clean_arq_element will return + err = iavf_clean_arq_element(hw, &event, NULL); + /* When the AQ is empty, iavf_clean_arq_element will return * nonzero and this loop will terminate. */ if (err) @@ -92,7 +92,7 @@ int i40evf_verify_api_ver(struct i40evf_adapter *adapter) } - err = (i40e_status)le32_to_cpu(event.desc.cookie_low); + err = (iavf_status)le32_to_cpu(event.desc.cookie_low); if (err) goto out_alloc; @@ -118,14 +118,14 @@ out: } /** - * i40evf_send_vf_config_msg + * iavf_send_vf_config_msg * @adapter: adapter structure * * Send VF configuration request admin queue message to the PF. The reply * is not checked in this function. Returns 0 if the message was * successfully sent, or one of the I40E_ADMIN_QUEUE_ERROR_ statuses if not. **/ -int i40evf_send_vf_config_msg(struct i40evf_adapter *adapter) +int iavf_send_vf_config_msg(struct iavf_adapter *adapter) { u32 caps; @@ -142,19 +142,43 @@ int i40evf_send_vf_config_msg(struct i40evf_adapter *adapter) VIRTCHNL_VF_OFFLOAD_ADQ; adapter->current_op = VIRTCHNL_OP_GET_VF_RESOURCES; - adapter->aq_required &= ~I40EVF_FLAG_AQ_GET_CONFIG; + adapter->aq_required &= ~IAVF_FLAG_AQ_GET_CONFIG; if (PF_IS_V11(adapter)) - return i40evf_send_pf_msg(adapter, - VIRTCHNL_OP_GET_VF_RESOURCES, - (u8 *)&caps, sizeof(caps)); + return iavf_send_pf_msg(adapter, VIRTCHNL_OP_GET_VF_RESOURCES, + (u8 *)&caps, sizeof(caps)); else - return i40evf_send_pf_msg(adapter, - VIRTCHNL_OP_GET_VF_RESOURCES, - NULL, 0); + return iavf_send_pf_msg(adapter, VIRTCHNL_OP_GET_VF_RESOURCES, + NULL, 0); } /** - * i40evf_get_vf_config + * iavf_validate_num_queues + * @adapter: adapter structure + * + * Validate that the number of queues the PF has sent in + * VIRTCHNL_OP_GET_VF_RESOURCES is not larger than the VF can handle. + **/ +static void iavf_validate_num_queues(struct iavf_adapter *adapter) +{ + if (adapter->vf_res->num_queue_pairs > IAVF_MAX_REQ_QUEUES) { + struct virtchnl_vsi_resource *vsi_res; + int i; + + dev_info(&adapter->pdev->dev, "Received %d queues, but can only have a max of %d\n", + adapter->vf_res->num_queue_pairs, + IAVF_MAX_REQ_QUEUES); + dev_info(&adapter->pdev->dev, "Fixing by reducing queues to %d\n", + IAVF_MAX_REQ_QUEUES); + adapter->vf_res->num_queue_pairs = IAVF_MAX_REQ_QUEUES; + for (i = 0; i < adapter->vf_res->num_vsis; i++) { + vsi_res = &adapter->vf_res->vsi_res[i]; + vsi_res->num_queue_pairs = IAVF_MAX_REQ_QUEUES; + } + } +} + +/** + * iavf_get_vf_config * @adapter: private adapter structure * * Get VF configuration from PF and populate hw structure. Must be called after @@ -162,16 +186,16 @@ int i40evf_send_vf_config_msg(struct i40evf_adapter *adapter) * with maximum timeout. Response from PF is returned in the buffer for further * processing by the caller. **/ -int i40evf_get_vf_config(struct i40evf_adapter *adapter) +int iavf_get_vf_config(struct iavf_adapter *adapter) { - struct i40e_hw *hw = &adapter->hw; + struct iavf_hw *hw = &adapter->hw; struct i40e_arq_event_info event; enum virtchnl_ops op; - i40e_status err; + iavf_status err; u16 len; len = sizeof(struct virtchnl_vf_resource) + - I40E_MAX_VF_VSI * sizeof(struct virtchnl_vsi_resource); + IAVF_MAX_VF_VSI * sizeof(struct virtchnl_vsi_resource); event.buf_len = len; event.msg_buf = kzalloc(event.buf_len, GFP_KERNEL); if (!event.msg_buf) { @@ -180,10 +204,10 @@ int i40evf_get_vf_config(struct i40evf_adapter *adapter) } while (1) { - /* When the AQ is empty, i40evf_clean_arq_element will return + /* When the AQ is empty, iavf_clean_arq_element will return * nonzero and this loop will terminate. */ - err = i40evf_clean_arq_element(hw, &event, NULL); + err = iavf_clean_arq_element(hw, &event, NULL); if (err) goto out_alloc; op = @@ -192,10 +216,15 @@ int i40evf_get_vf_config(struct i40evf_adapter *adapter) break; } - err = (i40e_status)le32_to_cpu(event.desc.cookie_low); + err = (iavf_status)le32_to_cpu(event.desc.cookie_low); memcpy(adapter->vf_res, event.msg_buf, min(event.msg_len, len)); - i40e_vf_parse_hw_config(hw, adapter->vf_res); + /* some PFs send more queues than we should have so validate that + * we aren't getting too many queues + */ + if (!err) + iavf_validate_num_queues(adapter); + iavf_vf_parse_hw_config(hw, adapter->vf_res); out_alloc: kfree(event.msg_buf); out: @@ -203,17 +232,17 @@ out: } /** - * i40evf_configure_queues + * iavf_configure_queues * @adapter: adapter structure * * Request that the PF set up our (previously allocated) queues. **/ -void i40evf_configure_queues(struct i40evf_adapter *adapter) +void iavf_configure_queues(struct iavf_adapter *adapter) { struct virtchnl_vsi_queue_config_info *vqci; struct virtchnl_queue_pair_info *vqpi; int pairs = adapter->num_active_queues; - int i, len, max_frame = I40E_MAX_RXBUFFER; + int i, len, max_frame = IAVF_MAX_RXBUFFER; if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { /* bail because we already have a command pending */ @@ -229,9 +258,9 @@ void i40evf_configure_queues(struct i40evf_adapter *adapter) return; /* Limit maximum frame size when jumbo frames is not enabled */ - if (!(adapter->flags & I40EVF_FLAG_LEGACY_RX) && + if (!(adapter->flags & IAVF_FLAG_LEGACY_RX) && (adapter->netdev->mtu <= ETH_DATA_LEN)) - max_frame = I40E_RXBUFFER_1536 - NET_IP_ALIGN; + max_frame = IAVF_RXBUFFER_1536 - NET_IP_ALIGN; vqci->vsi_id = adapter->vsi_res->vsi_id; vqci->num_queue_pairs = pairs; @@ -251,23 +280,23 @@ void i40evf_configure_queues(struct i40evf_adapter *adapter) vqpi->rxq.max_pkt_size = max_frame; vqpi->rxq.databuffer_size = ALIGN(adapter->rx_rings[i].rx_buf_len, - BIT_ULL(I40E_RXQ_CTX_DBUFF_SHIFT)); + BIT_ULL(IAVF_RXQ_CTX_DBUFF_SHIFT)); vqpi++; } - adapter->aq_required &= ~I40EVF_FLAG_AQ_CONFIGURE_QUEUES; - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_VSI_QUEUES, - (u8 *)vqci, len); + adapter->aq_required &= ~IAVF_FLAG_AQ_CONFIGURE_QUEUES; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_VSI_QUEUES, + (u8 *)vqci, len); kfree(vqci); } /** - * i40evf_enable_queues + * iavf_enable_queues * @adapter: adapter structure * * Request that the PF enable all of our queues. **/ -void i40evf_enable_queues(struct i40evf_adapter *adapter) +void iavf_enable_queues(struct iavf_adapter *adapter) { struct virtchnl_queue_select vqs; @@ -281,18 +310,18 @@ void i40evf_enable_queues(struct i40evf_adapter *adapter) vqs.vsi_id = adapter->vsi_res->vsi_id; vqs.tx_queues = BIT(adapter->num_active_queues) - 1; vqs.rx_queues = vqs.tx_queues; - adapter->aq_required &= ~I40EVF_FLAG_AQ_ENABLE_QUEUES; - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_ENABLE_QUEUES, - (u8 *)&vqs, sizeof(vqs)); + adapter->aq_required &= ~IAVF_FLAG_AQ_ENABLE_QUEUES; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_ENABLE_QUEUES, + (u8 *)&vqs, sizeof(vqs)); } /** - * i40evf_disable_queues + * iavf_disable_queues * @adapter: adapter structure * * Request that the PF disable all of our queues. **/ -void i40evf_disable_queues(struct i40evf_adapter *adapter) +void iavf_disable_queues(struct iavf_adapter *adapter) { struct virtchnl_queue_select vqs; @@ -306,24 +335,24 @@ void i40evf_disable_queues(struct i40evf_adapter *adapter) vqs.vsi_id = adapter->vsi_res->vsi_id; vqs.tx_queues = BIT(adapter->num_active_queues) - 1; vqs.rx_queues = vqs.tx_queues; - adapter->aq_required &= ~I40EVF_FLAG_AQ_DISABLE_QUEUES; - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_DISABLE_QUEUES, - (u8 *)&vqs, sizeof(vqs)); + adapter->aq_required &= ~IAVF_FLAG_AQ_DISABLE_QUEUES; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_DISABLE_QUEUES, + (u8 *)&vqs, sizeof(vqs)); } /** - * i40evf_map_queues + * iavf_map_queues * @adapter: adapter structure * * Request that the PF map queues to interrupt vectors. Misc causes, including * admin queue, are always mapped to vector 0. **/ -void i40evf_map_queues(struct i40evf_adapter *adapter) +void iavf_map_queues(struct iavf_adapter *adapter) { struct virtchnl_irq_map_info *vimi; struct virtchnl_vector_map *vecmap; int v_idx, q_vectors, len; - struct i40e_q_vector *q_vector; + struct iavf_q_vector *q_vector; if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { /* bail because we already have a command pending */ @@ -352,8 +381,8 @@ void i40evf_map_queues(struct i40evf_adapter *adapter) vecmap->vector_id = v_idx + NONQ_VECS; vecmap->txq_map = q_vector->ring_mask; vecmap->rxq_map = q_vector->ring_mask; - vecmap->rxitr_idx = I40E_RX_ITR; - vecmap->txitr_idx = I40E_TX_ITR; + vecmap->rxitr_idx = IAVF_RX_ITR; + vecmap->txitr_idx = IAVF_TX_ITR; } /* Misc vector last - this is only for AdminQ messages */ vecmap = &vimi->vecmap[v_idx]; @@ -362,21 +391,21 @@ void i40evf_map_queues(struct i40evf_adapter *adapter) vecmap->txq_map = 0; vecmap->rxq_map = 0; - adapter->aq_required &= ~I40EVF_FLAG_AQ_MAP_VECTORS; - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_IRQ_MAP, - (u8 *)vimi, len); + adapter->aq_required &= ~IAVF_FLAG_AQ_MAP_VECTORS; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_IRQ_MAP, + (u8 *)vimi, len); kfree(vimi); } /** - * i40evf_request_queues + * iavf_request_queues * @adapter: adapter structure * @num: number of requested queues * * We get a default number of queues from the PF. This enables us to request a * different number. Returns 0 on success, negative on failure **/ -int i40evf_request_queues(struct i40evf_adapter *adapter, int num) +int iavf_request_queues(struct iavf_adapter *adapter, int num) { struct virtchnl_vf_res_request vfres; @@ -390,22 +419,22 @@ int i40evf_request_queues(struct i40evf_adapter *adapter, int num) vfres.num_queue_pairs = num; adapter->current_op = VIRTCHNL_OP_REQUEST_QUEUES; - adapter->flags |= I40EVF_FLAG_REINIT_ITR_NEEDED; - return i40evf_send_pf_msg(adapter, VIRTCHNL_OP_REQUEST_QUEUES, - (u8 *)&vfres, sizeof(vfres)); + adapter->flags |= IAVF_FLAG_REINIT_ITR_NEEDED; + return iavf_send_pf_msg(adapter, VIRTCHNL_OP_REQUEST_QUEUES, + (u8 *)&vfres, sizeof(vfres)); } /** - * i40evf_add_ether_addrs + * iavf_add_ether_addrs * @adapter: adapter structure * * Request that the PF add one or more addresses to our filters. **/ -void i40evf_add_ether_addrs(struct i40evf_adapter *adapter) +void iavf_add_ether_addrs(struct iavf_adapter *adapter) { struct virtchnl_ether_addr_list *veal; int len, i = 0, count = 0; - struct i40evf_mac_filter *f; + struct iavf_mac_filter *f; bool more = false; if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { @@ -422,7 +451,7 @@ void i40evf_add_ether_addrs(struct i40evf_adapter *adapter) count++; } if (!count) { - adapter->aq_required &= ~I40EVF_FLAG_AQ_ADD_MAC_FILTER; + adapter->aq_required &= ~IAVF_FLAG_AQ_ADD_MAC_FILTER; spin_unlock_bh(&adapter->mac_vlan_list_lock); return; } @@ -430,9 +459,9 @@ void i40evf_add_ether_addrs(struct i40evf_adapter *adapter) len = sizeof(struct virtchnl_ether_addr_list) + (count * sizeof(struct virtchnl_ether_addr)); - if (len > I40EVF_MAX_AQ_BUF_SIZE) { + if (len > IAVF_MAX_AQ_BUF_SIZE) { dev_warn(&adapter->pdev->dev, "Too many add MAC changes in one request\n"); - count = (I40EVF_MAX_AQ_BUF_SIZE - + count = (IAVF_MAX_AQ_BUF_SIZE - sizeof(struct virtchnl_ether_addr_list)) / sizeof(struct virtchnl_ether_addr); len = sizeof(struct virtchnl_ether_addr_list) + @@ -458,25 +487,24 @@ void i40evf_add_ether_addrs(struct i40evf_adapter *adapter) } } if (!more) - adapter->aq_required &= ~I40EVF_FLAG_AQ_ADD_MAC_FILTER; + adapter->aq_required &= ~IAVF_FLAG_AQ_ADD_MAC_FILTER; spin_unlock_bh(&adapter->mac_vlan_list_lock); - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_ADD_ETH_ADDR, - (u8 *)veal, len); + iavf_send_pf_msg(adapter, VIRTCHNL_OP_ADD_ETH_ADDR, (u8 *)veal, len); kfree(veal); } /** - * i40evf_del_ether_addrs + * iavf_del_ether_addrs * @adapter: adapter structure * * Request that the PF remove one or more addresses from our filters. **/ -void i40evf_del_ether_addrs(struct i40evf_adapter *adapter) +void iavf_del_ether_addrs(struct iavf_adapter *adapter) { struct virtchnl_ether_addr_list *veal; - struct i40evf_mac_filter *f, *ftmp; + struct iavf_mac_filter *f, *ftmp; int len, i = 0, count = 0; bool more = false; @@ -494,7 +522,7 @@ void i40evf_del_ether_addrs(struct i40evf_adapter *adapter) count++; } if (!count) { - adapter->aq_required &= ~I40EVF_FLAG_AQ_DEL_MAC_FILTER; + adapter->aq_required &= ~IAVF_FLAG_AQ_DEL_MAC_FILTER; spin_unlock_bh(&adapter->mac_vlan_list_lock); return; } @@ -502,9 +530,9 @@ void i40evf_del_ether_addrs(struct i40evf_adapter *adapter) len = sizeof(struct virtchnl_ether_addr_list) + (count * sizeof(struct virtchnl_ether_addr)); - if (len > I40EVF_MAX_AQ_BUF_SIZE) { + if (len > IAVF_MAX_AQ_BUF_SIZE) { dev_warn(&adapter->pdev->dev, "Too many delete MAC changes in one request\n"); - count = (I40EVF_MAX_AQ_BUF_SIZE - + count = (IAVF_MAX_AQ_BUF_SIZE - sizeof(struct virtchnl_ether_addr_list)) / sizeof(struct virtchnl_ether_addr); len = sizeof(struct virtchnl_ether_addr_list) + @@ -530,26 +558,25 @@ void i40evf_del_ether_addrs(struct i40evf_adapter *adapter) } } if (!more) - adapter->aq_required &= ~I40EVF_FLAG_AQ_DEL_MAC_FILTER; + adapter->aq_required &= ~IAVF_FLAG_AQ_DEL_MAC_FILTER; spin_unlock_bh(&adapter->mac_vlan_list_lock); - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_DEL_ETH_ADDR, - (u8 *)veal, len); + iavf_send_pf_msg(adapter, VIRTCHNL_OP_DEL_ETH_ADDR, (u8 *)veal, len); kfree(veal); } /** - * i40evf_add_vlans + * iavf_add_vlans * @adapter: adapter structure * * Request that the PF add one or more VLAN filters to our VSI. **/ -void i40evf_add_vlans(struct i40evf_adapter *adapter) +void iavf_add_vlans(struct iavf_adapter *adapter) { struct virtchnl_vlan_filter_list *vvfl; int len, i = 0, count = 0; - struct i40evf_vlan_filter *f; + struct iavf_vlan_filter *f; bool more = false; if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { @@ -566,7 +593,7 @@ void i40evf_add_vlans(struct i40evf_adapter *adapter) count++; } if (!count) { - adapter->aq_required &= ~I40EVF_FLAG_AQ_ADD_VLAN_FILTER; + adapter->aq_required &= ~IAVF_FLAG_AQ_ADD_VLAN_FILTER; spin_unlock_bh(&adapter->mac_vlan_list_lock); return; } @@ -574,9 +601,9 @@ void i40evf_add_vlans(struct i40evf_adapter *adapter) len = sizeof(struct virtchnl_vlan_filter_list) + (count * sizeof(u16)); - if (len > I40EVF_MAX_AQ_BUF_SIZE) { + if (len > IAVF_MAX_AQ_BUF_SIZE) { dev_warn(&adapter->pdev->dev, "Too many add VLAN changes in one request\n"); - count = (I40EVF_MAX_AQ_BUF_SIZE - + count = (IAVF_MAX_AQ_BUF_SIZE - sizeof(struct virtchnl_vlan_filter_list)) / sizeof(u16); len = sizeof(struct virtchnl_vlan_filter_list) + @@ -601,24 +628,24 @@ void i40evf_add_vlans(struct i40evf_adapter *adapter) } } if (!more) - adapter->aq_required &= ~I40EVF_FLAG_AQ_ADD_VLAN_FILTER; + adapter->aq_required &= ~IAVF_FLAG_AQ_ADD_VLAN_FILTER; spin_unlock_bh(&adapter->mac_vlan_list_lock); - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_ADD_VLAN, (u8 *)vvfl, len); + iavf_send_pf_msg(adapter, VIRTCHNL_OP_ADD_VLAN, (u8 *)vvfl, len); kfree(vvfl); } /** - * i40evf_del_vlans + * iavf_del_vlans * @adapter: adapter structure * * Request that the PF remove one or more VLAN filters from our VSI. **/ -void i40evf_del_vlans(struct i40evf_adapter *adapter) +void iavf_del_vlans(struct iavf_adapter *adapter) { struct virtchnl_vlan_filter_list *vvfl; - struct i40evf_vlan_filter *f, *ftmp; + struct iavf_vlan_filter *f, *ftmp; int len, i = 0, count = 0; bool more = false; @@ -636,7 +663,7 @@ void i40evf_del_vlans(struct i40evf_adapter *adapter) count++; } if (!count) { - adapter->aq_required &= ~I40EVF_FLAG_AQ_DEL_VLAN_FILTER; + adapter->aq_required &= ~IAVF_FLAG_AQ_DEL_VLAN_FILTER; spin_unlock_bh(&adapter->mac_vlan_list_lock); return; } @@ -644,9 +671,9 @@ void i40evf_del_vlans(struct i40evf_adapter *adapter) len = sizeof(struct virtchnl_vlan_filter_list) + (count * sizeof(u16)); - if (len > I40EVF_MAX_AQ_BUF_SIZE) { + if (len > IAVF_MAX_AQ_BUF_SIZE) { dev_warn(&adapter->pdev->dev, "Too many delete VLAN changes in one request\n"); - count = (I40EVF_MAX_AQ_BUF_SIZE - + count = (IAVF_MAX_AQ_BUF_SIZE - sizeof(struct virtchnl_vlan_filter_list)) / sizeof(u16); len = sizeof(struct virtchnl_vlan_filter_list) + @@ -672,22 +699,22 @@ void i40evf_del_vlans(struct i40evf_adapter *adapter) } } if (!more) - adapter->aq_required &= ~I40EVF_FLAG_AQ_DEL_VLAN_FILTER; + adapter->aq_required &= ~IAVF_FLAG_AQ_DEL_VLAN_FILTER; spin_unlock_bh(&adapter->mac_vlan_list_lock); - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_DEL_VLAN, (u8 *)vvfl, len); + iavf_send_pf_msg(adapter, VIRTCHNL_OP_DEL_VLAN, (u8 *)vvfl, len); kfree(vvfl); } /** - * i40evf_set_promiscuous + * iavf_set_promiscuous * @adapter: adapter structure * @flags: bitmask to control unicast/multicast promiscuous. * * Request that the PF enable promiscuous mode for our VSI. **/ -void i40evf_set_promiscuous(struct i40evf_adapter *adapter, int flags) +void iavf_set_promiscuous(struct iavf_adapter *adapter, int flags) { struct virtchnl_promisc_info vpi; int promisc_all; @@ -702,39 +729,39 @@ void i40evf_set_promiscuous(struct i40evf_adapter *adapter, int flags) promisc_all = FLAG_VF_UNICAST_PROMISC | FLAG_VF_MULTICAST_PROMISC; if ((flags & promisc_all) == promisc_all) { - adapter->flags |= I40EVF_FLAG_PROMISC_ON; - adapter->aq_required &= ~I40EVF_FLAG_AQ_REQUEST_PROMISC; + adapter->flags |= IAVF_FLAG_PROMISC_ON; + adapter->aq_required &= ~IAVF_FLAG_AQ_REQUEST_PROMISC; dev_info(&adapter->pdev->dev, "Entering promiscuous mode\n"); } if (flags & FLAG_VF_MULTICAST_PROMISC) { - adapter->flags |= I40EVF_FLAG_ALLMULTI_ON; - adapter->aq_required &= ~I40EVF_FLAG_AQ_REQUEST_ALLMULTI; + adapter->flags |= IAVF_FLAG_ALLMULTI_ON; + adapter->aq_required &= ~IAVF_FLAG_AQ_REQUEST_ALLMULTI; dev_info(&adapter->pdev->dev, "Entering multicast promiscuous mode\n"); } if (!flags) { - adapter->flags &= ~(I40EVF_FLAG_PROMISC_ON | - I40EVF_FLAG_ALLMULTI_ON); - adapter->aq_required &= ~(I40EVF_FLAG_AQ_RELEASE_PROMISC | - I40EVF_FLAG_AQ_RELEASE_ALLMULTI); + adapter->flags &= ~(IAVF_FLAG_PROMISC_ON | + IAVF_FLAG_ALLMULTI_ON); + adapter->aq_required &= ~(IAVF_FLAG_AQ_RELEASE_PROMISC | + IAVF_FLAG_AQ_RELEASE_ALLMULTI); dev_info(&adapter->pdev->dev, "Leaving promiscuous mode\n"); } adapter->current_op = VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE; vpi.vsi_id = adapter->vsi_res->vsi_id; vpi.flags = flags; - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE, - (u8 *)&vpi, sizeof(vpi)); + iavf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE, + (u8 *)&vpi, sizeof(vpi)); } /** - * i40evf_request_stats + * iavf_request_stats * @adapter: adapter structure * * Request VSI statistics from PF. **/ -void i40evf_request_stats(struct i40evf_adapter *adapter) +void iavf_request_stats(struct iavf_adapter *adapter) { struct virtchnl_queue_select vqs; @@ -745,19 +772,19 @@ void i40evf_request_stats(struct i40evf_adapter *adapter) adapter->current_op = VIRTCHNL_OP_GET_STATS; vqs.vsi_id = adapter->vsi_res->vsi_id; /* queue maps are ignored for this message - only the vsi is used */ - if (i40evf_send_pf_msg(adapter, VIRTCHNL_OP_GET_STATS, - (u8 *)&vqs, sizeof(vqs))) + if (iavf_send_pf_msg(adapter, VIRTCHNL_OP_GET_STATS, (u8 *)&vqs, + sizeof(vqs))) /* if the request failed, don't lock out others */ adapter->current_op = VIRTCHNL_OP_UNKNOWN; } /** - * i40evf_get_hena + * iavf_get_hena * @adapter: adapter structure * * Request hash enable capabilities from PF **/ -void i40evf_get_hena(struct i40evf_adapter *adapter) +void iavf_get_hena(struct iavf_adapter *adapter) { if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { /* bail because we already have a command pending */ @@ -766,18 +793,17 @@ void i40evf_get_hena(struct i40evf_adapter *adapter) return; } adapter->current_op = VIRTCHNL_OP_GET_RSS_HENA_CAPS; - adapter->aq_required &= ~I40EVF_FLAG_AQ_GET_HENA; - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_GET_RSS_HENA_CAPS, - NULL, 0); + adapter->aq_required &= ~IAVF_FLAG_AQ_GET_HENA; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_GET_RSS_HENA_CAPS, NULL, 0); } /** - * i40evf_set_hena + * iavf_set_hena * @adapter: adapter structure * * Request the PF to set our RSS hash capabilities **/ -void i40evf_set_hena(struct i40evf_adapter *adapter) +void iavf_set_hena(struct iavf_adapter *adapter) { struct virtchnl_rss_hena vrh; @@ -789,18 +815,18 @@ void i40evf_set_hena(struct i40evf_adapter *adapter) } vrh.hena = adapter->hena; adapter->current_op = VIRTCHNL_OP_SET_RSS_HENA; - adapter->aq_required &= ~I40EVF_FLAG_AQ_SET_HENA; - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_SET_RSS_HENA, - (u8 *)&vrh, sizeof(vrh)); + adapter->aq_required &= ~IAVF_FLAG_AQ_SET_HENA; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_SET_RSS_HENA, (u8 *)&vrh, + sizeof(vrh)); } /** - * i40evf_set_rss_key + * iavf_set_rss_key * @adapter: adapter structure * * Request the PF to set our RSS hash key **/ -void i40evf_set_rss_key(struct i40evf_adapter *adapter) +void iavf_set_rss_key(struct iavf_adapter *adapter) { struct virtchnl_rss_key *vrk; int len; @@ -821,19 +847,18 @@ void i40evf_set_rss_key(struct i40evf_adapter *adapter) memcpy(vrk->key, adapter->rss_key, adapter->rss_key_size); adapter->current_op = VIRTCHNL_OP_CONFIG_RSS_KEY; - adapter->aq_required &= ~I40EVF_FLAG_AQ_SET_RSS_KEY; - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_RSS_KEY, - (u8 *)vrk, len); + adapter->aq_required &= ~IAVF_FLAG_AQ_SET_RSS_KEY; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_RSS_KEY, (u8 *)vrk, len); kfree(vrk); } /** - * i40evf_set_rss_lut + * iavf_set_rss_lut * @adapter: adapter structure * * Request the PF to set our RSS lookup table **/ -void i40evf_set_rss_lut(struct i40evf_adapter *adapter) +void iavf_set_rss_lut(struct iavf_adapter *adapter) { struct virtchnl_rss_lut *vrl; int len; @@ -853,19 +878,18 @@ void i40evf_set_rss_lut(struct i40evf_adapter *adapter) vrl->lut_entries = adapter->rss_lut_size; memcpy(vrl->lut, adapter->rss_lut, adapter->rss_lut_size); adapter->current_op = VIRTCHNL_OP_CONFIG_RSS_LUT; - adapter->aq_required &= ~I40EVF_FLAG_AQ_SET_RSS_LUT; - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_RSS_LUT, - (u8 *)vrl, len); + adapter->aq_required &= ~IAVF_FLAG_AQ_SET_RSS_LUT; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_RSS_LUT, (u8 *)vrl, len); kfree(vrl); } /** - * i40evf_enable_vlan_stripping + * iavf_enable_vlan_stripping * @adapter: adapter structure * * Request VLAN header stripping to be enabled **/ -void i40evf_enable_vlan_stripping(struct i40evf_adapter *adapter) +void iavf_enable_vlan_stripping(struct iavf_adapter *adapter) { if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { /* bail because we already have a command pending */ @@ -874,18 +898,17 @@ void i40evf_enable_vlan_stripping(struct i40evf_adapter *adapter) return; } adapter->current_op = VIRTCHNL_OP_ENABLE_VLAN_STRIPPING; - adapter->aq_required &= ~I40EVF_FLAG_AQ_ENABLE_VLAN_STRIPPING; - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_ENABLE_VLAN_STRIPPING, - NULL, 0); + adapter->aq_required &= ~IAVF_FLAG_AQ_ENABLE_VLAN_STRIPPING; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_ENABLE_VLAN_STRIPPING, NULL, 0); } /** - * i40evf_disable_vlan_stripping + * iavf_disable_vlan_stripping * @adapter: adapter structure * * Request VLAN header stripping to be disabled **/ -void i40evf_disable_vlan_stripping(struct i40evf_adapter *adapter) +void iavf_disable_vlan_stripping(struct iavf_adapter *adapter) { if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { /* bail because we already have a command pending */ @@ -894,18 +917,17 @@ void i40evf_disable_vlan_stripping(struct i40evf_adapter *adapter) return; } adapter->current_op = VIRTCHNL_OP_DISABLE_VLAN_STRIPPING; - adapter->aq_required &= ~I40EVF_FLAG_AQ_DISABLE_VLAN_STRIPPING; - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_DISABLE_VLAN_STRIPPING, - NULL, 0); + adapter->aq_required &= ~IAVF_FLAG_AQ_DISABLE_VLAN_STRIPPING; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_DISABLE_VLAN_STRIPPING, NULL, 0); } /** - * i40evf_print_link_message - print link up or down + * iavf_print_link_message - print link up or down * @adapter: adapter structure * * Log a message telling the world of our wonderous link status */ -static void i40evf_print_link_message(struct i40evf_adapter *adapter) +static void iavf_print_link_message(struct iavf_adapter *adapter) { struct net_device *netdev = adapter->netdev; char *speed = "Unknown "; @@ -942,13 +964,13 @@ static void i40evf_print_link_message(struct i40evf_adapter *adapter) } /** - * i40evf_enable_channel + * iavf_enable_channel * @adapter: adapter structure * * Request that the PF enable channels as specified by * the user via tc tool. **/ -void i40evf_enable_channels(struct i40evf_adapter *adapter) +void iavf_enable_channels(struct iavf_adapter *adapter) { struct virtchnl_tc_info *vti = NULL; u16 len; @@ -976,22 +998,21 @@ void i40evf_enable_channels(struct i40evf_adapter *adapter) adapter->ch_config.ch_info[i].max_tx_rate; } - adapter->ch_config.state = __I40EVF_TC_RUNNING; - adapter->flags |= I40EVF_FLAG_REINIT_ITR_NEEDED; + adapter->ch_config.state = __IAVF_TC_RUNNING; + adapter->flags |= IAVF_FLAG_REINIT_ITR_NEEDED; adapter->current_op = VIRTCHNL_OP_ENABLE_CHANNELS; - adapter->aq_required &= ~I40EVF_FLAG_AQ_ENABLE_CHANNELS; - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_ENABLE_CHANNELS, - (u8 *)vti, len); + adapter->aq_required &= ~IAVF_FLAG_AQ_ENABLE_CHANNELS; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_ENABLE_CHANNELS, (u8 *)vti, len); kfree(vti); } /** - * i40evf_disable_channel + * iavf_disable_channel * @adapter: adapter structure * * Request that the PF disable channels that are configured **/ -void i40evf_disable_channels(struct i40evf_adapter *adapter) +void iavf_disable_channels(struct iavf_adapter *adapter) { if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { /* bail because we already have a command pending */ @@ -1000,23 +1021,22 @@ void i40evf_disable_channels(struct i40evf_adapter *adapter) return; } - adapter->ch_config.state = __I40EVF_TC_INVALID; - adapter->flags |= I40EVF_FLAG_REINIT_ITR_NEEDED; + adapter->ch_config.state = __IAVF_TC_INVALID; + adapter->flags |= IAVF_FLAG_REINIT_ITR_NEEDED; adapter->current_op = VIRTCHNL_OP_DISABLE_CHANNELS; - adapter->aq_required &= ~I40EVF_FLAG_AQ_DISABLE_CHANNELS; - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_DISABLE_CHANNELS, - NULL, 0); + adapter->aq_required &= ~IAVF_FLAG_AQ_DISABLE_CHANNELS; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_DISABLE_CHANNELS, NULL, 0); } /** - * i40evf_print_cloud_filter + * iavf_print_cloud_filter * @adapter: adapter structure * @f: cloud filter to print * * Print the cloud filter **/ -static void i40evf_print_cloud_filter(struct i40evf_adapter *adapter, - struct virtchnl_filter *f) +static void iavf_print_cloud_filter(struct iavf_adapter *adapter, + struct virtchnl_filter *f) { switch (f->flow_type) { case VIRTCHNL_TCP_V4_FLOW: @@ -1043,15 +1063,15 @@ static void i40evf_print_cloud_filter(struct i40evf_adapter *adapter, } /** - * i40evf_add_cloud_filter + * iavf_add_cloud_filter * @adapter: adapter structure * * Request that the PF add cloud filters as specified * by the user via tc tool. **/ -void i40evf_add_cloud_filter(struct i40evf_adapter *adapter) +void iavf_add_cloud_filter(struct iavf_adapter *adapter) { - struct i40evf_cloud_filter *cf; + struct iavf_cloud_filter *cf; struct virtchnl_filter *f; int len = 0, count = 0; @@ -1068,7 +1088,7 @@ void i40evf_add_cloud_filter(struct i40evf_adapter *adapter) } } if (!count) { - adapter->aq_required &= ~I40EVF_FLAG_AQ_ADD_CLOUD_FILTER; + adapter->aq_required &= ~IAVF_FLAG_AQ_ADD_CLOUD_FILTER; return; } adapter->current_op = VIRTCHNL_OP_ADD_CLOUD_FILTER; @@ -1082,25 +1102,24 @@ void i40evf_add_cloud_filter(struct i40evf_adapter *adapter) if (cf->add) { memcpy(f, &cf->f, sizeof(struct virtchnl_filter)); cf->add = false; - cf->state = __I40EVF_CF_ADD_PENDING; - i40evf_send_pf_msg(adapter, - VIRTCHNL_OP_ADD_CLOUD_FILTER, - (u8 *)f, len); + cf->state = __IAVF_CF_ADD_PENDING; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_ADD_CLOUD_FILTER, + (u8 *)f, len); } } kfree(f); } /** - * i40evf_del_cloud_filter + * iavf_del_cloud_filter * @adapter: adapter structure * * Request that the PF delete cloud filters as specified * by the user via tc tool. **/ -void i40evf_del_cloud_filter(struct i40evf_adapter *adapter) +void iavf_del_cloud_filter(struct iavf_adapter *adapter) { - struct i40evf_cloud_filter *cf, *cftmp; + struct iavf_cloud_filter *cf, *cftmp; struct virtchnl_filter *f; int len = 0, count = 0; @@ -1117,7 +1136,7 @@ void i40evf_del_cloud_filter(struct i40evf_adapter *adapter) } } if (!count) { - adapter->aq_required &= ~I40EVF_FLAG_AQ_DEL_CLOUD_FILTER; + adapter->aq_required &= ~IAVF_FLAG_AQ_DEL_CLOUD_FILTER; return; } adapter->current_op = VIRTCHNL_OP_DEL_CLOUD_FILTER; @@ -1131,30 +1150,29 @@ void i40evf_del_cloud_filter(struct i40evf_adapter *adapter) if (cf->del) { memcpy(f, &cf->f, sizeof(struct virtchnl_filter)); cf->del = false; - cf->state = __I40EVF_CF_DEL_PENDING; - i40evf_send_pf_msg(adapter, - VIRTCHNL_OP_DEL_CLOUD_FILTER, - (u8 *)f, len); + cf->state = __IAVF_CF_DEL_PENDING; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_DEL_CLOUD_FILTER, + (u8 *)f, len); } } kfree(f); } /** - * i40evf_request_reset + * iavf_request_reset * @adapter: adapter structure * * Request that the PF reset this VF. No response is expected. **/ -void i40evf_request_reset(struct i40evf_adapter *adapter) +void iavf_request_reset(struct iavf_adapter *adapter) { /* Don't check CURRENT_OP - this is always higher priority */ - i40evf_send_pf_msg(adapter, VIRTCHNL_OP_RESET_VF, NULL, 0); + iavf_send_pf_msg(adapter, VIRTCHNL_OP_RESET_VF, NULL, 0); adapter->current_op = VIRTCHNL_OP_UNKNOWN; } /** - * i40evf_virtchnl_completion + * iavf_virtchnl_completion * @adapter: adapter structure * @v_opcode: opcode sent by PF * @v_retval: retval sent by PF @@ -1165,10 +1183,9 @@ void i40evf_request_reset(struct i40evf_adapter *adapter) * wait, we fire off our requests and assume that no errors will be returned. * This function handles the reply messages. **/ -void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, - enum virtchnl_ops v_opcode, - i40e_status v_retval, - u8 *msg, u16 msglen) +void iavf_virtchnl_completion(struct iavf_adapter *adapter, + enum virtchnl_ops v_opcode, iavf_status v_retval, + u8 *msg, u16 msglen) { struct net_device *netdev = adapter->netdev; @@ -1176,6 +1193,7 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, struct virtchnl_pf_event *vpe = (struct virtchnl_pf_event *)msg; bool link_up = vpe->event_data.link_event.link_status; + switch (vpe->event) { case VIRTCHNL_EVENT_LINK_CHANGE: adapter->link_speed = @@ -1193,7 +1211,7 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, * after we enable queues and actually prepared * to send traffic. */ - if (adapter->state != __I40EVF_RUNNING) + if (adapter->state != __IAVF_RUNNING) break; /* For ADq enabled VF, we reconfigure VSIs and @@ -1201,7 +1219,7 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, * queues are enabled. */ if (adapter->flags & - I40EVF_FLAG_QUEUES_DISABLED) + IAVF_FLAG_QUEUES_DISABLED) break; } @@ -1213,12 +1231,12 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, netif_tx_stop_all_queues(netdev); netif_carrier_off(netdev); } - i40evf_print_link_message(adapter); + iavf_print_link_message(adapter); break; case VIRTCHNL_EVENT_RESET_IMPENDING: dev_info(&adapter->pdev->dev, "Reset warning received from the PF\n"); - if (!(adapter->flags & I40EVF_FLAG_RESET_PENDING)) { - adapter->flags |= I40EVF_FLAG_RESET_PENDING; + if (!(adapter->flags & IAVF_FLAG_RESET_PENDING)) { + adapter->flags |= IAVF_FLAG_RESET_PENDING; dev_info(&adapter->pdev->dev, "Scheduling reset task\n"); schedule_work(&adapter->reset_task); } @@ -1234,48 +1252,48 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, switch (v_opcode) { case VIRTCHNL_OP_ADD_VLAN: dev_err(&adapter->pdev->dev, "Failed to add VLAN filter, error %s\n", - i40evf_stat_str(&adapter->hw, v_retval)); + iavf_stat_str(&adapter->hw, v_retval)); break; case VIRTCHNL_OP_ADD_ETH_ADDR: dev_err(&adapter->pdev->dev, "Failed to add MAC filter, error %s\n", - i40evf_stat_str(&adapter->hw, v_retval)); + iavf_stat_str(&adapter->hw, v_retval)); break; case VIRTCHNL_OP_DEL_VLAN: dev_err(&adapter->pdev->dev, "Failed to delete VLAN filter, error %s\n", - i40evf_stat_str(&adapter->hw, v_retval)); + iavf_stat_str(&adapter->hw, v_retval)); break; case VIRTCHNL_OP_DEL_ETH_ADDR: dev_err(&adapter->pdev->dev, "Failed to delete MAC filter, error %s\n", - i40evf_stat_str(&adapter->hw, v_retval)); + iavf_stat_str(&adapter->hw, v_retval)); break; case VIRTCHNL_OP_ENABLE_CHANNELS: dev_err(&adapter->pdev->dev, "Failed to configure queue channels, error %s\n", - i40evf_stat_str(&adapter->hw, v_retval)); - adapter->flags &= ~I40EVF_FLAG_REINIT_ITR_NEEDED; - adapter->ch_config.state = __I40EVF_TC_INVALID; + iavf_stat_str(&adapter->hw, v_retval)); + adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; + adapter->ch_config.state = __IAVF_TC_INVALID; netdev_reset_tc(netdev); netif_tx_start_all_queues(netdev); break; case VIRTCHNL_OP_DISABLE_CHANNELS: dev_err(&adapter->pdev->dev, "Failed to disable queue channels, error %s\n", - i40evf_stat_str(&adapter->hw, v_retval)); - adapter->flags &= ~I40EVF_FLAG_REINIT_ITR_NEEDED; - adapter->ch_config.state = __I40EVF_TC_RUNNING; + iavf_stat_str(&adapter->hw, v_retval)); + adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; + adapter->ch_config.state = __IAVF_TC_RUNNING; netif_tx_start_all_queues(netdev); break; case VIRTCHNL_OP_ADD_CLOUD_FILTER: { - struct i40evf_cloud_filter *cf, *cftmp; + struct iavf_cloud_filter *cf, *cftmp; list_for_each_entry_safe(cf, cftmp, &adapter->cloud_filter_list, list) { - if (cf->state == __I40EVF_CF_ADD_PENDING) { - cf->state = __I40EVF_CF_INVALID; + if (cf->state == __IAVF_CF_ADD_PENDING) { + cf->state = __IAVF_CF_INVALID; dev_info(&adapter->pdev->dev, "Failed to add cloud filter, error %s\n", - i40evf_stat_str(&adapter->hw, - v_retval)); - i40evf_print_cloud_filter(adapter, - &cf->f); + iavf_stat_str(&adapter->hw, + v_retval)); + iavf_print_cloud_filter(adapter, + &cf->f); list_del(&cf->list); kfree(cf); adapter->num_cloud_filters--; @@ -1284,32 +1302,31 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, } break; case VIRTCHNL_OP_DEL_CLOUD_FILTER: { - struct i40evf_cloud_filter *cf; + struct iavf_cloud_filter *cf; list_for_each_entry(cf, &adapter->cloud_filter_list, list) { - if (cf->state == __I40EVF_CF_DEL_PENDING) { - cf->state = __I40EVF_CF_ACTIVE; + if (cf->state == __IAVF_CF_DEL_PENDING) { + cf->state = __IAVF_CF_ACTIVE; dev_info(&adapter->pdev->dev, "Failed to del cloud filter, error %s\n", - i40evf_stat_str(&adapter->hw, - v_retval)); - i40evf_print_cloud_filter(adapter, - &cf->f); + iavf_stat_str(&adapter->hw, + v_retval)); + iavf_print_cloud_filter(adapter, + &cf->f); } } } break; default: dev_err(&adapter->pdev->dev, "PF returned error %d (%s) to our request %d\n", - v_retval, - i40evf_stat_str(&adapter->hw, v_retval), + v_retval, iavf_stat_str(&adapter->hw, v_retval), v_opcode); } } switch (v_opcode) { case VIRTCHNL_OP_GET_STATS: { - struct i40e_eth_stats *stats = - (struct i40e_eth_stats *)msg; + struct iavf_eth_stats *stats = + (struct iavf_eth_stats *)msg; netdev->stats.rx_packets = stats->rx_unicast + stats->rx_multicast + stats->rx_broadcast; @@ -1326,25 +1343,33 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, break; case VIRTCHNL_OP_GET_VF_RESOURCES: { u16 len = sizeof(struct virtchnl_vf_resource) + - I40E_MAX_VF_VSI * + IAVF_MAX_VF_VSI * sizeof(struct virtchnl_vsi_resource); memcpy(adapter->vf_res, msg, min(msglen, len)); - i40e_vf_parse_hw_config(&adapter->hw, adapter->vf_res); - /* restore current mac address */ - ether_addr_copy(adapter->hw.mac.addr, netdev->dev_addr); - i40evf_process_config(adapter); + iavf_validate_num_queues(adapter); + iavf_vf_parse_hw_config(&adapter->hw, adapter->vf_res); + if (is_zero_ether_addr(adapter->hw.mac.addr)) { + /* restore current mac address */ + ether_addr_copy(adapter->hw.mac.addr, netdev->dev_addr); + } else { + /* refresh current mac address if changed */ + ether_addr_copy(netdev->dev_addr, adapter->hw.mac.addr); + ether_addr_copy(netdev->perm_addr, + adapter->hw.mac.addr); + } + iavf_process_config(adapter); } break; case VIRTCHNL_OP_ENABLE_QUEUES: /* enable transmits */ - i40evf_irq_enable(adapter, true); - adapter->flags &= ~I40EVF_FLAG_QUEUES_DISABLED; + iavf_irq_enable(adapter, true); + adapter->flags &= ~IAVF_FLAG_QUEUES_DISABLED; break; case VIRTCHNL_OP_DISABLE_QUEUES: - i40evf_free_all_tx_resources(adapter); - i40evf_free_all_rx_resources(adapter); - if (adapter->state == __I40EVF_DOWN_PENDING) { - adapter->state = __I40EVF_DOWN; + iavf_free_all_tx_resources(adapter); + iavf_free_all_rx_resources(adapter); + if (adapter->state == __IAVF_DOWN_PENDING) { + adapter->state = __IAVF_DOWN; wake_up(&adapter->down_waitqueue); } break; @@ -1363,8 +1388,7 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, * care about that. */ if (msglen && CLIENT_ENABLED(adapter)) - i40evf_notify_client_message(&adapter->vsi, - msg, msglen); + iavf_notify_client_message(&adapter->vsi, msg, msglen); break; case VIRTCHNL_OP_CONFIG_IWARP_IRQ_MAP: @@ -1373,6 +1397,7 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, break; case VIRTCHNL_OP_GET_RSS_HENA_CAPS: { struct virtchnl_rss_hena *vrh = (struct virtchnl_rss_hena *)msg; + if (msglen == sizeof(*vrh)) adapter->hena = vrh->hena; else @@ -1383,32 +1408,33 @@ void i40evf_virtchnl_completion(struct i40evf_adapter *adapter, case VIRTCHNL_OP_REQUEST_QUEUES: { struct virtchnl_vf_res_request *vfres = (struct virtchnl_vf_res_request *)msg; + if (vfres->num_queue_pairs != adapter->num_req_queues) { dev_info(&adapter->pdev->dev, "Requested %d queues, PF can support %d\n", adapter->num_req_queues, vfres->num_queue_pairs); adapter->num_req_queues = 0; - adapter->flags &= ~I40EVF_FLAG_REINIT_ITR_NEEDED; + adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; } } break; case VIRTCHNL_OP_ADD_CLOUD_FILTER: { - struct i40evf_cloud_filter *cf; + struct iavf_cloud_filter *cf; list_for_each_entry(cf, &adapter->cloud_filter_list, list) { - if (cf->state == __I40EVF_CF_ADD_PENDING) - cf->state = __I40EVF_CF_ACTIVE; + if (cf->state == __IAVF_CF_ADD_PENDING) + cf->state = __IAVF_CF_ACTIVE; } } break; case VIRTCHNL_OP_DEL_CLOUD_FILTER: { - struct i40evf_cloud_filter *cf, *cftmp; + struct iavf_cloud_filter *cf, *cftmp; list_for_each_entry_safe(cf, cftmp, &adapter->cloud_filter_list, list) { - if (cf->state == __I40EVF_CF_DEL_PENDING) { - cf->state = __I40EVF_CF_INVALID; + if (cf->state == __IAVF_CF_DEL_PENDING) { + cf->state = __IAVF_CF_INVALID; list_del(&cf->list); kfree(cf); adapter->num_cloud_filters--; diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index d8b5fff581e7..9cf233d085d8 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -62,6 +62,7 @@ extern const char ice_drv_ver[]; #define ICE_RES_VALID_BIT 0x8000 #define ICE_RES_MISC_VEC_ID (ICE_RES_VALID_BIT - 1) #define ICE_INVAL_Q_INDEX 0xffff +#define ICE_INVAL_VFID 256 #define ICE_VSIQF_HKEY_ARRAY_SIZE ((VSIQF_HKEY_MAX_INDEX + 1) * 4) @@ -89,6 +90,13 @@ extern const char ice_drv_ver[]; #define ice_for_each_rxq(vsi, i) \ for ((i) = 0; (i) < (vsi)->num_rxq; (i)++) +/* Macros for each allocated tx/rx ring whether used or not in a VSI */ +#define ice_for_each_alloc_txq(vsi, i) \ + for ((i) = 0; (i) < (vsi)->alloc_txq; (i)++) + +#define ice_for_each_alloc_rxq(vsi, i) \ + for ((i) = 0; (i) < (vsi)->alloc_rxq; (i)++) + struct ice_tc_info { u16 qoffset; u16 qcount; @@ -115,6 +123,7 @@ struct ice_sw { enum ice_state { __ICE_DOWN, __ICE_NEEDS_RESTART, + __ICE_PREPARED_FOR_RESET, /* set by driver when prepared */ __ICE_RESET_RECOVERY_PENDING, /* set by driver when reset starts */ __ICE_PFR_REQ, /* set by driver and peers */ __ICE_CORER_REQ, /* set by driver and peers */ @@ -125,9 +134,11 @@ enum ice_state { __ICE_SUSPENDED, /* set on module remove path */ __ICE_RESET_FAILED, /* set by reset/rebuild */ __ICE_ADMINQ_EVENT_PENDING, + __ICE_MDD_EVENT_PENDING, __ICE_FLTR_OVERFLOW_PROMISC, __ICE_CFG_BUSY, __ICE_SERVICE_SCHED, + __ICE_SERVICE_DIS, __ICE_STATE_NBITS /* must be last */ }; @@ -189,9 +200,9 @@ struct ice_vsi { struct list_head tmp_sync_list; /* MAC filters to be synced */ struct list_head tmp_unsync_list; /* MAC filters to be unsynced */ - bool irqs_ready; - bool current_isup; /* Sync 'link up' logging */ - bool stat_offsets_loaded; + u8 irqs_ready; + u8 current_isup; /* Sync 'link up' logging */ + u8 stat_offsets_loaded; /* queue information */ u8 tx_mapping_mode; /* ICE_MAP_MODE_[CONTIG|SCATTER] */ @@ -262,7 +273,10 @@ struct ice_pf { struct ice_hw_port_stats stats; struct ice_hw_port_stats stats_prev; struct ice_hw hw; - bool stat_prev_loaded; /* has previous stats been loaded */ + u8 stat_prev_loaded; /* has previous stats been loaded */ + u32 tx_timeout_count; + unsigned long tx_timeout_last_recovery; + u32 tx_timeout_recovery_level; char int_name[ICE_INT_NAME_STR_LEN]; }; diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index 7541ec2270b3..f8dfd675486c 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -329,19 +329,19 @@ struct ice_aqc_vsi_props { /* VLAN section */ __le16 pvid; /* VLANS include priority bits */ u8 pvlan_reserved[2]; - u8 port_vlan_flags; -#define ICE_AQ_VSI_PVLAN_MODE_S 0 -#define ICE_AQ_VSI_PVLAN_MODE_M (0x3 << ICE_AQ_VSI_PVLAN_MODE_S) -#define ICE_AQ_VSI_PVLAN_MODE_UNTAGGED 0x1 -#define ICE_AQ_VSI_PVLAN_MODE_TAGGED 0x2 -#define ICE_AQ_VSI_PVLAN_MODE_ALL 0x3 + u8 vlan_flags; +#define ICE_AQ_VSI_VLAN_MODE_S 0 +#define ICE_AQ_VSI_VLAN_MODE_M (0x3 << ICE_AQ_VSI_VLAN_MODE_S) +#define ICE_AQ_VSI_VLAN_MODE_UNTAGGED 0x1 +#define ICE_AQ_VSI_VLAN_MODE_TAGGED 0x2 +#define ICE_AQ_VSI_VLAN_MODE_ALL 0x3 #define ICE_AQ_VSI_PVLAN_INSERT_PVID BIT(2) -#define ICE_AQ_VSI_PVLAN_EMOD_S 3 -#define ICE_AQ_VSI_PVLAN_EMOD_M (0x3 << ICE_AQ_VSI_PVLAN_EMOD_S) -#define ICE_AQ_VSI_PVLAN_EMOD_STR_BOTH (0x0 << ICE_AQ_VSI_PVLAN_EMOD_S) -#define ICE_AQ_VSI_PVLAN_EMOD_STR_UP (0x1 << ICE_AQ_VSI_PVLAN_EMOD_S) -#define ICE_AQ_VSI_PVLAN_EMOD_STR (0x2 << ICE_AQ_VSI_PVLAN_EMOD_S) -#define ICE_AQ_VSI_PVLAN_EMOD_NOTHING (0x3 << ICE_AQ_VSI_PVLAN_EMOD_S) +#define ICE_AQ_VSI_VLAN_EMOD_S 3 +#define ICE_AQ_VSI_VLAN_EMOD_M (0x3 << ICE_AQ_VSI_VLAN_EMOD_S) +#define ICE_AQ_VSI_VLAN_EMOD_STR_BOTH (0x0 << ICE_AQ_VSI_VLAN_EMOD_S) +#define ICE_AQ_VSI_VLAN_EMOD_STR_UP (0x1 << ICE_AQ_VSI_VLAN_EMOD_S) +#define ICE_AQ_VSI_VLAN_EMOD_STR (0x2 << ICE_AQ_VSI_VLAN_EMOD_S) +#define ICE_AQ_VSI_VLAN_EMOD_NOTHING (0x3 << ICE_AQ_VSI_VLAN_EMOD_S) u8 pvlan_reserved2[3]; /* ingress egress up sections */ __le32 ingress_table; /* bitmap, 3 bits per up */ @@ -443,6 +443,8 @@ struct ice_aqc_vsi_props { u8 reserved[24]; }; +#define ICE_MAX_NUM_RECIPES 64 + /* Add/Update/Remove/Get switch rules (indirect 0x02A0, 0x02A1, 0x02A2, 0x02A3) */ struct ice_aqc_sw_rules { @@ -594,6 +596,7 @@ struct ice_sw_rule_lg_act { #define ICE_LG_ACT_GENERIC_OFFSET_M (0x7 << ICE_LG_ACT_GENERIC_OFFSET_S) #define ICE_LG_ACT_GENERIC_PRIORITY_S 22 #define ICE_LG_ACT_GENERIC_PRIORITY_M (0x7 << ICE_LG_ACT_GENERIC_PRIORITY_S) +#define ICE_LG_ACT_GENERIC_OFF_RX_DESC_PROF_IDX 7 /* Action = 7 - Set Stat count */ #define ICE_LG_ACT_STAT_COUNT 0x7 @@ -770,9 +773,8 @@ struct ice_aqc_layer_props { u8 chunk_size; __le16 max_device_nodes; __le16 max_pf_nodes; - u8 rsvd0[2]; - __le16 max_shared_rate_lmtr; - __le16 max_children; + u8 rsvd0[4]; + __le16 max_sibl_grp_sz; __le16 max_cir_rl_profiles; __le16 max_eir_rl_profiles; __le16 max_srl_profiles; @@ -918,9 +920,11 @@ struct ice_aqc_set_phy_cfg_data { u8 caps; #define ICE_AQ_PHY_ENA_TX_PAUSE_ABILITY BIT(0) #define ICE_AQ_PHY_ENA_RX_PAUSE_ABILITY BIT(1) -#define ICE_AQ_PHY_ENA_LOW_POWER BIT(2) -#define ICE_AQ_PHY_ENA_LINK BIT(3) -#define ICE_AQ_PHY_ENA_ATOMIC_LINK BIT(5) +#define ICE_AQ_PHY_ENA_LOW_POWER BIT(2) +#define ICE_AQ_PHY_ENA_LINK BIT(3) +#define ICE_AQ_PHY_ENA_AUTO_LINK_UPDT BIT(5) +#define ICE_AQ_PHY_ENA_LESM BIT(6) +#define ICE_AQ_PHY_ENA_AUTO_FEC BIT(7) u8 low_power_ctrl; __le16 eee_cap; /* Value from ice_aqc_get_phy_caps */ __le16 eeer_value; @@ -1202,6 +1206,84 @@ struct ice_aqc_dis_txq { struct ice_aqc_dis_txq_item qgrps[1]; }; +/* Configure Firmware Logging Command (indirect 0xFF09) + * Logging Information Read Response (indirect 0xFF10) + * Note: The 0xFF10 command has no input parameters. + */ +struct ice_aqc_fw_logging { + u8 log_ctrl; +#define ICE_AQC_FW_LOG_AQ_EN BIT(0) +#define ICE_AQC_FW_LOG_UART_EN BIT(1) + u8 rsvd0; + u8 log_ctrl_valid; /* Not used by 0xFF10 Response */ +#define ICE_AQC_FW_LOG_AQ_VALID BIT(0) +#define ICE_AQC_FW_LOG_UART_VALID BIT(1) + u8 rsvd1[5]; + __le32 addr_high; + __le32 addr_low; +}; + +enum ice_aqc_fw_logging_mod { + ICE_AQC_FW_LOG_ID_GENERAL = 0, + ICE_AQC_FW_LOG_ID_CTRL, + ICE_AQC_FW_LOG_ID_LINK, + ICE_AQC_FW_LOG_ID_LINK_TOPO, + ICE_AQC_FW_LOG_ID_DNL, + ICE_AQC_FW_LOG_ID_I2C, + ICE_AQC_FW_LOG_ID_SDP, + ICE_AQC_FW_LOG_ID_MDIO, + ICE_AQC_FW_LOG_ID_ADMINQ, + ICE_AQC_FW_LOG_ID_HDMA, + ICE_AQC_FW_LOG_ID_LLDP, + ICE_AQC_FW_LOG_ID_DCBX, + ICE_AQC_FW_LOG_ID_DCB, + ICE_AQC_FW_LOG_ID_NETPROXY, + ICE_AQC_FW_LOG_ID_NVM, + ICE_AQC_FW_LOG_ID_AUTH, + ICE_AQC_FW_LOG_ID_VPD, + ICE_AQC_FW_LOG_ID_IOSF, + ICE_AQC_FW_LOG_ID_PARSER, + ICE_AQC_FW_LOG_ID_SW, + ICE_AQC_FW_LOG_ID_SCHEDULER, + ICE_AQC_FW_LOG_ID_TXQ, + ICE_AQC_FW_LOG_ID_RSVD, + ICE_AQC_FW_LOG_ID_POST, + ICE_AQC_FW_LOG_ID_WATCHDOG, + ICE_AQC_FW_LOG_ID_TASK_DISPATCH, + ICE_AQC_FW_LOG_ID_MNG, + ICE_AQC_FW_LOG_ID_MAX, +}; + +/* This is the buffer for both of the logging commands. + * The entry array size depends on the datalen parameter in the descriptor. + * There will be a total of datalen / 2 entries. + */ +struct ice_aqc_fw_logging_data { + __le16 entry[1]; +#define ICE_AQC_FW_LOG_ID_S 0 +#define ICE_AQC_FW_LOG_ID_M (0xFFF << ICE_AQC_FW_LOG_ID_S) + +#define ICE_AQC_FW_LOG_CONF_SUCCESS 0 /* Used by response */ +#define ICE_AQC_FW_LOG_CONF_BAD_INDX BIT(12) /* Used by response */ + +#define ICE_AQC_FW_LOG_EN_S 12 +#define ICE_AQC_FW_LOG_EN_M (0xF << ICE_AQC_FW_LOG_EN_S) +#define ICE_AQC_FW_LOG_INFO_EN BIT(12) /* Used by command */ +#define ICE_AQC_FW_LOG_INIT_EN BIT(13) /* Used by command */ +#define ICE_AQC_FW_LOG_FLOW_EN BIT(14) /* Used by command */ +#define ICE_AQC_FW_LOG_ERR_EN BIT(15) /* Used by command */ +}; + +/* Get/Clear FW Log (indirect 0xFF11) */ +struct ice_aqc_get_clear_fw_log { + u8 flags; +#define ICE_AQC_FW_LOG_CLEAR BIT(0) +#define ICE_AQC_FW_LOG_MORE_DATA_AVAIL BIT(1) + u8 rsvd1[7]; + __le32 addr_high; + __le32 addr_low; +}; + /** * struct ice_aq_desc - Admin Queue (AQ) descriptor * @flags: ICE_AQ_FLAG_* flags @@ -1251,6 +1333,9 @@ struct ice_aq_desc { struct ice_aqc_add_txqs add_txqs; struct ice_aqc_dis_txqs dis_txqs; struct ice_aqc_add_get_update_free_vsi vsi_cmd; + struct ice_aqc_add_update_free_vsi_resp add_update_free_vsi_res; + struct ice_aqc_fw_logging fw_logging; + struct ice_aqc_get_clear_fw_log get_clear_fw_log; struct ice_aqc_alloc_free_res_cmd sw_res_ctrl; struct ice_aqc_set_event_mask set_event_mask; struct ice_aqc_get_link_status get_link_status; @@ -1348,6 +1433,9 @@ enum ice_adminq_opc { /* TX queue handling commands/events */ ice_aqc_opc_add_txqs = 0x0C30, ice_aqc_opc_dis_txqs = 0x0C31, + + /* debug commands */ + ice_aqc_opc_fw_logging = 0xFF09, }; #endif /* _ICE_ADMINQ_CMD_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 71d032cc5fa7..0847dbf9d42f 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -7,16 +7,16 @@ #define ICE_PF_RESET_WAIT_COUNT 200 -#define ICE_NIC_FLX_ENTRY(hw, mdid, idx) \ - wr32((hw), GLFLXP_RXDID_FLX_WRD_##idx(ICE_RXDID_FLEX_NIC), \ +#define ICE_PROG_FLEX_ENTRY(hw, rxdid, mdid, idx) \ + wr32((hw), GLFLXP_RXDID_FLX_WRD_##idx(rxdid), \ ((ICE_RX_OPC_MDID << \ GLFLXP_RXDID_FLX_WRD_##idx##_RXDID_OPCODE_S) & \ GLFLXP_RXDID_FLX_WRD_##idx##_RXDID_OPCODE_M) | \ (((mdid) << GLFLXP_RXDID_FLX_WRD_##idx##_PROT_MDID_S) & \ GLFLXP_RXDID_FLX_WRD_##idx##_PROT_MDID_M)) -#define ICE_NIC_FLX_FLG_ENTRY(hw, flg_0, flg_1, flg_2, flg_3, idx) \ - wr32((hw), GLFLXP_RXDID_FLAGS(ICE_RXDID_FLEX_NIC, idx), \ +#define ICE_PROG_FLG_ENTRY(hw, rxdid, flg_0, flg_1, flg_2, flg_3, idx) \ + wr32((hw), GLFLXP_RXDID_FLAGS(rxdid, idx), \ (((flg_0) << GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_S) & \ GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_M) | \ (((flg_1) << GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_1_S) & \ @@ -45,6 +45,9 @@ static enum ice_status ice_set_mac_type(struct ice_hw *hw) /** * ice_clear_pf_cfg - Clear PF configuration * @hw: pointer to the hardware structure + * + * Clears any existing PF configuration (VSIs, VSI lists, switch rules, port + * configuration, flow director filters, etc.). */ enum ice_status ice_clear_pf_cfg(struct ice_hw *hw) { @@ -122,7 +125,7 @@ ice_aq_manage_mac_read(struct ice_hw *hw, void *buf, u16 buf_size, * * Returns the various PHY capabilities supported on the Port (0x0600) */ -static enum ice_status +enum ice_status ice_aq_get_phy_caps(struct ice_port_info *pi, bool qual_mods, u8 report_mode, struct ice_aqc_get_phy_caps_data *pcaps, struct ice_sq_cd *cd) @@ -287,30 +290,85 @@ ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse, } /** - * ice_init_flex_parser - initialize rx flex parser + * ice_init_flex_flags * @hw: pointer to the hardware structure + * @prof_id: Rx Descriptor Builder profile ID * - * Function to initialize flex descriptors + * Function to initialize Rx flex flags */ -static void ice_init_flex_parser(struct ice_hw *hw) +static void ice_init_flex_flags(struct ice_hw *hw, enum ice_rxdid prof_id) { u8 idx = 0; - ICE_NIC_FLX_ENTRY(hw, ICE_RX_MDID_HASH_LOW, 0); - ICE_NIC_FLX_ENTRY(hw, ICE_RX_MDID_HASH_HIGH, 1); - ICE_NIC_FLX_ENTRY(hw, ICE_RX_MDID_FLOW_ID_LOWER, 2); - ICE_NIC_FLX_ENTRY(hw, ICE_RX_MDID_FLOW_ID_HIGH, 3); - ICE_NIC_FLX_FLG_ENTRY(hw, ICE_RXFLG_PKT_FRG, ICE_RXFLG_UDP_GRE, - ICE_RXFLG_PKT_DSI, ICE_RXFLG_FIN, idx++); - ICE_NIC_FLX_FLG_ENTRY(hw, ICE_RXFLG_SYN, ICE_RXFLG_RST, - ICE_RXFLG_PKT_DSI, ICE_RXFLG_PKT_DSI, idx++); - ICE_NIC_FLX_FLG_ENTRY(hw, ICE_RXFLG_PKT_DSI, ICE_RXFLG_PKT_DSI, - ICE_RXFLG_EVLAN_x8100, ICE_RXFLG_EVLAN_x9100, - idx++); - ICE_NIC_FLX_FLG_ENTRY(hw, ICE_RXFLG_VLAN_x8100, ICE_RXFLG_TNL_VLAN, - ICE_RXFLG_TNL_MAC, ICE_RXFLG_TNL0, idx++); - ICE_NIC_FLX_FLG_ENTRY(hw, ICE_RXFLG_TNL1, ICE_RXFLG_TNL2, - ICE_RXFLG_PKT_DSI, ICE_RXFLG_PKT_DSI, idx); + /* Flex-flag fields (0-2) are programmed with FLG64 bits with layout: + * flexiflags0[5:0] - TCP flags, is_packet_fragmented, is_packet_UDP_GRE + * flexiflags1[3:0] - Not used for flag programming + * flexiflags2[7:0] - Tunnel and VLAN types + * 2 invalid fields in last index + */ + switch (prof_id) { + /* Rx flex flags are currently programmed for the NIC profiles only. + * Different flag bit programming configurations can be added per + * profile as needed. + */ + case ICE_RXDID_FLEX_NIC: + case ICE_RXDID_FLEX_NIC_2: + ICE_PROG_FLG_ENTRY(hw, prof_id, ICE_RXFLG_PKT_FRG, + ICE_RXFLG_UDP_GRE, ICE_RXFLG_PKT_DSI, + ICE_RXFLG_FIN, idx++); + /* flex flag 1 is not used for flexi-flag programming, skipping + * these four FLG64 bits. + */ + ICE_PROG_FLG_ENTRY(hw, prof_id, ICE_RXFLG_SYN, ICE_RXFLG_RST, + ICE_RXFLG_PKT_DSI, ICE_RXFLG_PKT_DSI, idx++); + ICE_PROG_FLG_ENTRY(hw, prof_id, ICE_RXFLG_PKT_DSI, + ICE_RXFLG_PKT_DSI, ICE_RXFLG_EVLAN_x8100, + ICE_RXFLG_EVLAN_x9100, idx++); + ICE_PROG_FLG_ENTRY(hw, prof_id, ICE_RXFLG_VLAN_x8100, + ICE_RXFLG_TNL_VLAN, ICE_RXFLG_TNL_MAC, + ICE_RXFLG_TNL0, idx++); + ICE_PROG_FLG_ENTRY(hw, prof_id, ICE_RXFLG_TNL1, ICE_RXFLG_TNL2, + ICE_RXFLG_PKT_DSI, ICE_RXFLG_PKT_DSI, idx); + break; + + default: + ice_debug(hw, ICE_DBG_INIT, + "Flag programming for profile ID %d not supported\n", + prof_id); + } +} + +/** + * ice_init_flex_flds + * @hw: pointer to the hardware structure + * @prof_id: Rx Descriptor Builder profile ID + * + * Function to initialize flex descriptors + */ +static void ice_init_flex_flds(struct ice_hw *hw, enum ice_rxdid prof_id) +{ + enum ice_flex_rx_mdid mdid; + + switch (prof_id) { + case ICE_RXDID_FLEX_NIC: + case ICE_RXDID_FLEX_NIC_2: + ICE_PROG_FLEX_ENTRY(hw, prof_id, ICE_RX_MDID_HASH_LOW, 0); + ICE_PROG_FLEX_ENTRY(hw, prof_id, ICE_RX_MDID_HASH_HIGH, 1); + ICE_PROG_FLEX_ENTRY(hw, prof_id, ICE_RX_MDID_FLOW_ID_LOWER, 2); + + mdid = (prof_id == ICE_RXDID_FLEX_NIC_2) ? + ICE_RX_MDID_SRC_VSI : ICE_RX_MDID_FLOW_ID_HIGH; + + ICE_PROG_FLEX_ENTRY(hw, prof_id, mdid, 3); + + ice_init_flex_flags(hw, prof_id); + break; + + default: + ice_debug(hw, ICE_DBG_INIT, + "Field init for profile ID %d not supported\n", + prof_id); + } } /** @@ -330,20 +388,7 @@ static enum ice_status ice_init_fltr_mgmt_struct(struct ice_hw *hw) INIT_LIST_HEAD(&sw->vsi_list_map_head); - mutex_init(&sw->mac_list_lock); - INIT_LIST_HEAD(&sw->mac_list_head); - - mutex_init(&sw->vlan_list_lock); - INIT_LIST_HEAD(&sw->vlan_list_head); - - mutex_init(&sw->eth_m_list_lock); - INIT_LIST_HEAD(&sw->eth_m_list_head); - - mutex_init(&sw->promisc_list_lock); - INIT_LIST_HEAD(&sw->promisc_list_head); - - mutex_init(&sw->mac_vlan_list_lock); - INIT_LIST_HEAD(&sw->mac_vlan_list_head); + ice_init_def_sw_recp(hw); return 0; } @@ -357,22 +402,201 @@ static void ice_cleanup_fltr_mgmt_struct(struct ice_hw *hw) struct ice_switch_info *sw = hw->switch_info; struct ice_vsi_list_map_info *v_pos_map; struct ice_vsi_list_map_info *v_tmp_map; + struct ice_sw_recipe *recps; + u8 i; list_for_each_entry_safe(v_pos_map, v_tmp_map, &sw->vsi_list_map_head, list_entry) { list_del(&v_pos_map->list_entry); devm_kfree(ice_hw_to_dev(hw), v_pos_map); } + recps = hw->switch_info->recp_list; + for (i = 0; i < ICE_SW_LKUP_LAST; i++) { + struct ice_fltr_mgmt_list_entry *lst_itr, *tmp_entry; + + recps[i].root_rid = i; + mutex_destroy(&recps[i].filt_rule_lock); + list_for_each_entry_safe(lst_itr, tmp_entry, + &recps[i].filt_rules, list_entry) { + list_del(&lst_itr->list_entry); + devm_kfree(ice_hw_to_dev(hw), lst_itr); + } + } - mutex_destroy(&sw->mac_list_lock); - mutex_destroy(&sw->vlan_list_lock); - mutex_destroy(&sw->eth_m_list_lock); - mutex_destroy(&sw->promisc_list_lock); - mutex_destroy(&sw->mac_vlan_list_lock); - + devm_kfree(ice_hw_to_dev(hw), sw->recp_list); devm_kfree(ice_hw_to_dev(hw), sw); } +#define ICE_FW_LOG_DESC_SIZE(n) (sizeof(struct ice_aqc_fw_logging_data) + \ + (((n) - 1) * sizeof(((struct ice_aqc_fw_logging_data *)0)->entry))) +#define ICE_FW_LOG_DESC_SIZE_MAX \ + ICE_FW_LOG_DESC_SIZE(ICE_AQC_FW_LOG_ID_MAX) + +/** + * ice_cfg_fw_log - configure FW logging + * @hw: pointer to the hw struct + * @enable: enable certain FW logging events if true, disable all if false + * + * This function enables/disables the FW logging via Rx CQ events and a UART + * port based on predetermined configurations. FW logging via the Rx CQ can be + * enabled/disabled for individual PF's. However, FW logging via the UART can + * only be enabled/disabled for all PFs on the same device. + * + * To enable overall FW logging, the "cq_en" and "uart_en" enable bits in + * hw->fw_log need to be set accordingly, e.g. based on user-provided input, + * before initializing the device. + * + * When re/configuring FW logging, callers need to update the "cfg" elements of + * the hw->fw_log.evnts array with the desired logging event configurations for + * modules of interest. When disabling FW logging completely, the callers can + * just pass false in the "enable" parameter. On completion, the function will + * update the "cur" element of the hw->fw_log.evnts array with the resulting + * logging event configurations of the modules that are being re/configured. FW + * logging modules that are not part of a reconfiguration operation retain their + * previous states. + * + * Before resetting the device, it is recommended that the driver disables FW + * logging before shutting down the control queue. When disabling FW logging + * ("enable" = false), the latest configurations of FW logging events stored in + * hw->fw_log.evnts[] are not overridden to allow them to be reconfigured after + * a device reset. + * + * When enabling FW logging to emit log messages via the Rx CQ during the + * device's initialization phase, a mechanism alternative to interrupt handlers + * needs to be used to extract FW log messages from the Rx CQ periodically and + * to prevent the Rx CQ from being full and stalling other types of control + * messages from FW to SW. Interrupts are typically disabled during the device's + * initialization phase. + */ +static enum ice_status ice_cfg_fw_log(struct ice_hw *hw, bool enable) +{ + struct ice_aqc_fw_logging_data *data = NULL; + struct ice_aqc_fw_logging *cmd; + enum ice_status status = 0; + u16 i, chgs = 0, len = 0; + struct ice_aq_desc desc; + u8 actv_evnts = 0; + void *buf = NULL; + + if (!hw->fw_log.cq_en && !hw->fw_log.uart_en) + return 0; + + /* Disable FW logging only when the control queue is still responsive */ + if (!enable && + (!hw->fw_log.actv_evnts || !ice_check_sq_alive(hw, &hw->adminq))) + return 0; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_fw_logging); + cmd = &desc.params.fw_logging; + + /* Indicate which controls are valid */ + if (hw->fw_log.cq_en) + cmd->log_ctrl_valid |= ICE_AQC_FW_LOG_AQ_VALID; + + if (hw->fw_log.uart_en) + cmd->log_ctrl_valid |= ICE_AQC_FW_LOG_UART_VALID; + + if (enable) { + /* Fill in an array of entries with FW logging modules and + * logging events being reconfigured. + */ + for (i = 0; i < ICE_AQC_FW_LOG_ID_MAX; i++) { + u16 val; + + /* Keep track of enabled event types */ + actv_evnts |= hw->fw_log.evnts[i].cfg; + + if (hw->fw_log.evnts[i].cfg == hw->fw_log.evnts[i].cur) + continue; + + if (!data) { + data = devm_kzalloc(ice_hw_to_dev(hw), + ICE_FW_LOG_DESC_SIZE_MAX, + GFP_KERNEL); + if (!data) + return ICE_ERR_NO_MEMORY; + } + + val = i << ICE_AQC_FW_LOG_ID_S; + val |= hw->fw_log.evnts[i].cfg << ICE_AQC_FW_LOG_EN_S; + data->entry[chgs++] = cpu_to_le16(val); + } + + /* Only enable FW logging if at least one module is specified. + * If FW logging is currently enabled but all modules are not + * enabled to emit log messages, disable FW logging altogether. + */ + if (actv_evnts) { + /* Leave if there is effectively no change */ + if (!chgs) + goto out; + + if (hw->fw_log.cq_en) + cmd->log_ctrl |= ICE_AQC_FW_LOG_AQ_EN; + + if (hw->fw_log.uart_en) + cmd->log_ctrl |= ICE_AQC_FW_LOG_UART_EN; + + buf = data; + len = ICE_FW_LOG_DESC_SIZE(chgs); + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + } + } + + status = ice_aq_send_cmd(hw, &desc, buf, len, NULL); + if (!status) { + /* Update the current configuration to reflect events enabled. + * hw->fw_log.cq_en and hw->fw_log.uart_en indicate if the FW + * logging mode is enabled for the device. They do not reflect + * actual modules being enabled to emit log messages. So, their + * values remain unchanged even when all modules are disabled. + */ + u16 cnt = enable ? chgs : (u16)ICE_AQC_FW_LOG_ID_MAX; + + hw->fw_log.actv_evnts = actv_evnts; + for (i = 0; i < cnt; i++) { + u16 v, m; + + if (!enable) { + /* When disabling all FW logging events as part + * of device's de-initialization, the original + * configurations are retained, and can be used + * to reconfigure FW logging later if the device + * is re-initialized. + */ + hw->fw_log.evnts[i].cur = 0; + continue; + } + + v = le16_to_cpu(data->entry[i]); + m = (v & ICE_AQC_FW_LOG_ID_M) >> ICE_AQC_FW_LOG_ID_S; + hw->fw_log.evnts[m].cur = hw->fw_log.evnts[m].cfg; + } + } + +out: + if (data) + devm_kfree(ice_hw_to_dev(hw), data); + + return status; +} + +/** + * ice_output_fw_log + * @hw: pointer to the hw struct + * @desc: pointer to the AQ message descriptor + * @buf: pointer to the buffer accompanying the AQ message + * + * Formats a FW Log message and outputs it via the standard driver logs. + */ +void ice_output_fw_log(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf) +{ + ice_debug(hw, ICE_DBG_AQ_MSG, "[ FW Log Msg Start ]\n"); + ice_debug_array(hw, ICE_DBG_AQ_MSG, 16, 1, (u8 *)buf, + le16_to_cpu(desc->datalen)); + ice_debug(hw, ICE_DBG_AQ_MSG, "[ FW Log Msg End ]\n"); +} + /** * ice_init_hw - main hardware initialization routine * @hw: pointer to the hardware structure @@ -407,6 +631,11 @@ enum ice_status ice_init_hw(struct ice_hw *hw) if (status) goto err_unroll_cqinit; + /* Enable FW logging. Not fatal if this fails. */ + status = ice_cfg_fw_log(hw, true); + if (status) + ice_debug(hw, ICE_DBG_INIT, "Failed to enable FW logging.\n"); + status = ice_clear_pf_cfg(hw); if (status) goto err_unroll_cqinit; @@ -469,6 +698,13 @@ enum ice_status ice_init_hw(struct ice_hw *hw) if (status) goto err_unroll_sched; + /* need a valid SW entry point to build a Tx tree */ + if (!hw->sw_entry_point_layer) { + ice_debug(hw, ICE_DBG_SCHED, "invalid sw entry point\n"); + status = ICE_ERR_CFG; + goto err_unroll_sched; + } + status = ice_init_fltr_mgmt_struct(hw); if (status) goto err_unroll_sched; @@ -491,7 +727,8 @@ enum ice_status ice_init_hw(struct ice_hw *hw) if (status) goto err_unroll_fltr_mgmt_struct; - ice_init_flex_parser(hw); + ice_init_flex_flds(hw, ICE_RXDID_FLEX_NIC); + ice_init_flex_flds(hw, ICE_RXDID_FLEX_NIC_2); return 0; @@ -512,15 +749,18 @@ err_unroll_cqinit: */ void ice_deinit_hw(struct ice_hw *hw) { + ice_cleanup_fltr_mgmt_struct(hw); + ice_sched_cleanup_all(hw); - ice_shutdown_all_ctrlq(hw); if (hw->port_info) { devm_kfree(ice_hw_to_dev(hw), hw->port_info); hw->port_info = NULL; } - ice_cleanup_fltr_mgmt_struct(hw); + /* Attempt to disable FW logging before shutting down control queues */ + ice_cfg_fw_log(hw, false); + ice_shutdown_all_ctrlq(hw); } /** @@ -649,6 +889,8 @@ enum ice_status ice_reset(struct ice_hw *hw, enum ice_reset_req req) ice_debug(hw, ICE_DBG_INIT, "GlobalR requested\n"); val = GLGEN_RTRIG_GLOBR_M; break; + default: + return ICE_ERR_PARAM; } val |= rd32(hw, GLGEN_RTRIG); @@ -901,7 +1143,22 @@ enum ice_status ice_aq_q_shutdown(struct ice_hw *hw, bool unloading) * @timeout: the maximum time in ms that the driver may hold the resource * @cd: pointer to command details structure or NULL * - * requests common resource using the admin queue commands (0x0008) + * Requests common resource using the admin queue commands (0x0008). + * When attempting to acquire the Global Config Lock, the driver can + * learn of three states: + * 1) ICE_SUCCESS - acquired lock, and can perform download package + * 2) ICE_ERR_AQ_ERROR - did not get lock, driver should fail to load + * 3) ICE_ERR_AQ_NO_WORK - did not get lock, but another driver has + * successfully downloaded the package; the driver does + * not have to download the package and can continue + * loading + * + * Note that if the caller is in an acquire lock, perform action, release lock + * phase of operation, it is possible that the FW may detect a timeout and issue + * a CORER. In this case, the driver will receive a CORER interrupt and will + * have to determine its cause. The calling thread that is handling this flow + * will likely get an error propagated back to it indicating the Download + * Package, Update Package or the Release Resource AQ commands timed out. */ static enum ice_status ice_aq_req_res(struct ice_hw *hw, enum ice_aq_res_ids res, @@ -919,13 +1176,43 @@ ice_aq_req_res(struct ice_hw *hw, enum ice_aq_res_ids res, cmd_resp->res_id = cpu_to_le16(res); cmd_resp->access_type = cpu_to_le16(access); cmd_resp->res_number = cpu_to_le32(sdp_number); + cmd_resp->timeout = cpu_to_le32(*timeout); + *timeout = 0; status = ice_aq_send_cmd(hw, &desc, NULL, 0, cd); + /* The completion specifies the maximum time in ms that the driver * may hold the resource in the Timeout field. - * If the resource is held by someone else, the command completes with - * busy return value and the timeout field indicates the maximum time - * the current owner of the resource has to free it. + */ + + /* Global config lock response utilizes an additional status field. + * + * If the Global config lock resource is held by some other driver, the + * command completes with ICE_AQ_RES_GLBL_IN_PROG in the status field + * and the timeout field indicates the maximum time the current owner + * of the resource has to free it. + */ + if (res == ICE_GLOBAL_CFG_LOCK_RES_ID) { + if (le16_to_cpu(cmd_resp->status) == ICE_AQ_RES_GLBL_SUCCESS) { + *timeout = le32_to_cpu(cmd_resp->timeout); + return 0; + } else if (le16_to_cpu(cmd_resp->status) == + ICE_AQ_RES_GLBL_IN_PROG) { + *timeout = le32_to_cpu(cmd_resp->timeout); + return ICE_ERR_AQ_ERROR; + } else if (le16_to_cpu(cmd_resp->status) == + ICE_AQ_RES_GLBL_DONE) { + return ICE_ERR_AQ_NO_WORK; + } + + /* invalid FW response, force a timeout immediately */ + *timeout = 0; + return ICE_ERR_AQ_ERROR; + } + + /* If the resource is held by some other driver, the command completes + * with a busy return value and the timeout field indicates the maximum + * time the current owner of the resource has to free it. */ if (!status || hw->adminq.sq_last_status == ICE_AQ_RC_EBUSY) *timeout = le32_to_cpu(cmd_resp->timeout); @@ -964,30 +1251,28 @@ ice_aq_release_res(struct ice_hw *hw, enum ice_aq_res_ids res, u8 sdp_number, * @hw: pointer to the HW structure * @res: resource id * @access: access type (read or write) + * @timeout: timeout in milliseconds * * This function will attempt to acquire the ownership of a resource. */ enum ice_status ice_acquire_res(struct ice_hw *hw, enum ice_aq_res_ids res, - enum ice_aq_res_access_type access) + enum ice_aq_res_access_type access, u32 timeout) { #define ICE_RES_POLLING_DELAY_MS 10 u32 delay = ICE_RES_POLLING_DELAY_MS; + u32 time_left = timeout; enum ice_status status; - u32 time_left = 0; - u32 timeout; status = ice_aq_req_res(hw, res, access, 0, &time_left, NULL); - /* An admin queue return code of ICE_AQ_RC_EEXIST means that another - * driver has previously acquired the resource and performed any - * necessary updates; in this case the caller does not obtain the - * resource and has no further work to do. + /* A return code of ICE_ERR_AQ_NO_WORK means that another driver has + * previously acquired the resource and performed any necessary updates; + * in this case the caller does not obtain the resource and has no + * further work to do. */ - if (hw->adminq.sq_last_status == ICE_AQ_RC_EEXIST) { - status = ICE_ERR_AQ_NO_WORK; + if (status == ICE_ERR_AQ_NO_WORK) goto ice_acquire_res_exit; - } if (status) ice_debug(hw, ICE_DBG_RES, @@ -1000,11 +1285,9 @@ ice_acquire_res(struct ice_hw *hw, enum ice_aq_res_ids res, timeout = (timeout > delay) ? timeout - delay : 0; status = ice_aq_req_res(hw, res, access, 0, &time_left, NULL); - if (hw->adminq.sq_last_status == ICE_AQ_RC_EEXIST) { + if (status == ICE_ERR_AQ_NO_WORK) /* lock free, but no work to do */ - status = ICE_ERR_AQ_NO_WORK; break; - } if (!status) /* lock acquired */ @@ -1304,6 +1587,110 @@ void ice_clear_pxe_mode(struct ice_hw *hw) } /** + * ice_get_link_speed_based_on_phy_type - returns link speed + * @phy_type_low: lower part of phy_type + * + * This helper function will convert a phy_type_low to its corresponding link + * speed. + * Note: In the structure of phy_type_low, there should be one bit set, as + * this function will convert one phy type to its speed. + * If no bit gets set, ICE_LINK_SPEED_UNKNOWN will be returned + * If more than one bit gets set, ICE_LINK_SPEED_UNKNOWN will be returned + */ +static u16 +ice_get_link_speed_based_on_phy_type(u64 phy_type_low) +{ + u16 speed_phy_type_low = ICE_AQ_LINK_SPEED_UNKNOWN; + + switch (phy_type_low) { + case ICE_PHY_TYPE_LOW_100BASE_TX: + case ICE_PHY_TYPE_LOW_100M_SGMII: + speed_phy_type_low = ICE_AQ_LINK_SPEED_100MB; + break; + case ICE_PHY_TYPE_LOW_1000BASE_T: + case ICE_PHY_TYPE_LOW_1000BASE_SX: + case ICE_PHY_TYPE_LOW_1000BASE_LX: + case ICE_PHY_TYPE_LOW_1000BASE_KX: + case ICE_PHY_TYPE_LOW_1G_SGMII: + speed_phy_type_low = ICE_AQ_LINK_SPEED_1000MB; + break; + case ICE_PHY_TYPE_LOW_2500BASE_T: + case ICE_PHY_TYPE_LOW_2500BASE_X: + case ICE_PHY_TYPE_LOW_2500BASE_KX: + speed_phy_type_low = ICE_AQ_LINK_SPEED_2500MB; + break; + case ICE_PHY_TYPE_LOW_5GBASE_T: + case ICE_PHY_TYPE_LOW_5GBASE_KR: + speed_phy_type_low = ICE_AQ_LINK_SPEED_5GB; + break; + case ICE_PHY_TYPE_LOW_10GBASE_T: + case ICE_PHY_TYPE_LOW_10G_SFI_DA: + case ICE_PHY_TYPE_LOW_10GBASE_SR: + case ICE_PHY_TYPE_LOW_10GBASE_LR: + case ICE_PHY_TYPE_LOW_10GBASE_KR_CR1: + case ICE_PHY_TYPE_LOW_10G_SFI_AOC_ACC: + case ICE_PHY_TYPE_LOW_10G_SFI_C2C: + speed_phy_type_low = ICE_AQ_LINK_SPEED_10GB; + break; + case ICE_PHY_TYPE_LOW_25GBASE_T: + case ICE_PHY_TYPE_LOW_25GBASE_CR: + case ICE_PHY_TYPE_LOW_25GBASE_CR_S: + case ICE_PHY_TYPE_LOW_25GBASE_CR1: + case ICE_PHY_TYPE_LOW_25GBASE_SR: + case ICE_PHY_TYPE_LOW_25GBASE_LR: + case ICE_PHY_TYPE_LOW_25GBASE_KR: + case ICE_PHY_TYPE_LOW_25GBASE_KR_S: + case ICE_PHY_TYPE_LOW_25GBASE_KR1: + case ICE_PHY_TYPE_LOW_25G_AUI_AOC_ACC: + case ICE_PHY_TYPE_LOW_25G_AUI_C2C: + speed_phy_type_low = ICE_AQ_LINK_SPEED_25GB; + break; + case ICE_PHY_TYPE_LOW_40GBASE_CR4: + case ICE_PHY_TYPE_LOW_40GBASE_SR4: + case ICE_PHY_TYPE_LOW_40GBASE_LR4: + case ICE_PHY_TYPE_LOW_40GBASE_KR4: + case ICE_PHY_TYPE_LOW_40G_XLAUI_AOC_ACC: + case ICE_PHY_TYPE_LOW_40G_XLAUI: + speed_phy_type_low = ICE_AQ_LINK_SPEED_40GB; + break; + default: + speed_phy_type_low = ICE_AQ_LINK_SPEED_UNKNOWN; + break; + } + + return speed_phy_type_low; +} + +/** + * ice_update_phy_type + * @phy_type_low: pointer to the lower part of phy_type + * @link_speeds_bitmap: targeted link speeds bitmap + * + * Note: For the link_speeds_bitmap structure, you can check it at + * [ice_aqc_get_link_status->link_speed]. Caller can pass in + * link_speeds_bitmap include multiple speeds. + * + * The value of phy_type_low will present a certain link speed. This helper + * function will turn on bits in the phy_type_low based on the value of + * link_speeds_bitmap input parameter. + */ +void ice_update_phy_type(u64 *phy_type_low, u16 link_speeds_bitmap) +{ + u16 speed = ICE_AQ_LINK_SPEED_UNKNOWN; + u64 pt_low; + int index; + + /* We first check with low part of phy_type */ + for (index = 0; index <= ICE_PHY_TYPE_LOW_MAX_INDEX; index++) { + pt_low = BIT_ULL(index); + speed = ice_get_link_speed_based_on_phy_type(pt_low); + + if (link_speeds_bitmap & speed) + *phy_type_low |= BIT_ULL(index); + } +} + +/** * ice_aq_set_phy_cfg * @hw: pointer to the hw struct * @lport: logical port number @@ -1315,19 +1702,18 @@ void ice_clear_pxe_mode(struct ice_hw *hw) * mode as the PF may not have the privilege to set some of the PHY Config * parameters. This status will be indicated by the command response (0x0601). */ -static enum ice_status +enum ice_status ice_aq_set_phy_cfg(struct ice_hw *hw, u8 lport, struct ice_aqc_set_phy_cfg_data *cfg, struct ice_sq_cd *cd) { - struct ice_aqc_set_phy_cfg *cmd; struct ice_aq_desc desc; if (!cfg) return ICE_ERR_PARAM; - cmd = &desc.params.set_phy; ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_phy_cfg); - cmd->lport_num = lport; + desc.params.set_phy.lport_num = lport; + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); return ice_aq_send_cmd(hw, &desc, cfg, sizeof(*cfg), cd); } @@ -1376,12 +1762,12 @@ out: * ice_set_fc * @pi: port information structure * @aq_failures: pointer to status code, specific to ice_set_fc routine - * @atomic_restart: enable automatic link update + * @ena_auto_link_update: enable automatic link update * * Set the requested flow control mode. */ enum ice_status -ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, bool atomic_restart) +ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, bool ena_auto_link_update) { struct ice_aqc_set_phy_cfg_data cfg = { 0 }; struct ice_aqc_get_phy_caps_data *pcaps; @@ -1431,8 +1817,8 @@ ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, bool atomic_restart) int retry_count, retry_max = 10; /* Auto restart link so settings take effect */ - if (atomic_restart) - cfg.caps |= ICE_AQ_PHY_ENA_ATOMIC_LINK; + if (ena_auto_link_update) + cfg.caps |= ICE_AQ_PHY_ENA_AUTO_LINK_UPDT; /* Copy over all the old settings */ cfg.phy_type_low = pcaps->phy_type_low; cfg.low_power_ctrl = pcaps->low_power_ctrl; @@ -1483,7 +1869,7 @@ enum ice_status ice_get_link_status(struct ice_port_info *pi, bool *link_up) struct ice_phy_info *phy_info; enum ice_status status = 0; - if (!pi) + if (!pi || !link_up) return ICE_ERR_PARAM; phy_info = &pi->phy; @@ -1619,20 +2005,23 @@ __ice_aq_get_set_rss_lut(struct ice_hw *hw, u16 vsi_id, u8 lut_type, u8 *lut, } /* LUT size is only valid for Global and PF table types */ - if (lut_size == ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_128) { - flags |= (ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_128_FLAG << - ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_S) & - ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_M; - } else if (lut_size == ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_512) { + switch (lut_size) { + case ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_128: + break; + case ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_512: flags |= (ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_512_FLAG << ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_S) & ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_M; - } else if ((lut_size == ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_2K) && - (lut_type == ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF)) { - flags |= (ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_2K_FLAG << - ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_S) & - ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_M; - } else { + break; + case ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_2K: + if (lut_type == ICE_AQC_GSET_RSS_LUT_TABLE_TYPE_PF) { + flags |= (ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_2K_FLAG << + ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_S) & + ICE_AQC_GSET_RSS_LUT_TABLE_SIZE_M; + break; + } + /* fall-through */ + default: status = ICE_ERR_PARAM; goto ice_aq_get_set_rss_lut_exit; } diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index 9a5519130af1..aac2d6cadaaf 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -23,7 +23,7 @@ enum ice_status ice_get_link_status(struct ice_port_info *pi, bool *link_up); enum ice_status ice_acquire_res(struct ice_hw *hw, enum ice_aq_res_ids res, - enum ice_aq_res_access_type access); + enum ice_aq_res_access_type access, u32 timeout); void ice_release_res(struct ice_hw *hw, enum ice_aq_res_ids res); enum ice_status ice_init_nvm(struct ice_hw *hw); enum ice_status @@ -58,12 +58,24 @@ enum ice_status ice_aq_send_cmd(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf, u16 buf_size, struct ice_sq_cd *cd); enum ice_status ice_aq_get_fw_ver(struct ice_hw *hw, struct ice_sq_cd *cd); + +enum ice_status +ice_aq_get_phy_caps(struct ice_port_info *pi, bool qual_mods, u8 report_mode, + struct ice_aqc_get_phy_caps_data *caps, + struct ice_sq_cd *cd); +void +ice_update_phy_type(u64 *phy_type_low, u16 link_speeds_bitmap); enum ice_status ice_aq_manage_mac_write(struct ice_hw *hw, u8 *mac_addr, u8 flags, struct ice_sq_cd *cd); enum ice_status ice_clear_pf_cfg(struct ice_hw *hw); enum ice_status -ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, bool atomic_restart); +ice_aq_set_phy_cfg(struct ice_hw *hw, u8 lport, + struct ice_aqc_set_phy_cfg_data *cfg, struct ice_sq_cd *cd); +enum ice_status +ice_set_fc(struct ice_port_info *pi, u8 *aq_failures, + bool ena_auto_link_update); + enum ice_status ice_aq_set_link_restart_an(struct ice_port_info *pi, bool ena_link, struct ice_sq_cd *cd); @@ -83,4 +95,5 @@ enum ice_status ice_ena_vsi_txq(struct ice_port_info *pi, u16 vsi_id, u8 tc, u8 num_qgrps, struct ice_aqc_add_tx_qgrp *buf, u16 buf_size, struct ice_sq_cd *cd); +void ice_output_fw_log(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf); #endif /* _ICE_COMMON_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c index 7c511f144ed6..1fe026a65d75 100644 --- a/drivers/net/ethernet/intel/ice/ice_controlq.c +++ b/drivers/net/ethernet/intel/ice/ice_controlq.c @@ -597,10 +597,14 @@ static enum ice_status ice_init_check_adminq(struct ice_hw *hw) return 0; init_ctrlq_free_rq: - ice_shutdown_rq(hw, cq); - ice_shutdown_sq(hw, cq); - mutex_destroy(&cq->sq_lock); - mutex_destroy(&cq->rq_lock); + if (cq->rq.head) { + ice_shutdown_rq(hw, cq); + mutex_destroy(&cq->rq_lock); + } + if (cq->sq.head) { + ice_shutdown_sq(hw, cq); + mutex_destroy(&cq->sq_lock); + } return status; } @@ -706,10 +710,14 @@ static void ice_shutdown_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type) return; } - ice_shutdown_sq(hw, cq); - ice_shutdown_rq(hw, cq); - mutex_destroy(&cq->sq_lock); - mutex_destroy(&cq->rq_lock); + if (cq->sq.head) { + ice_shutdown_sq(hw, cq); + mutex_destroy(&cq->sq_lock); + } + if (cq->rq.head) { + ice_shutdown_rq(hw, cq); + mutex_destroy(&cq->rq_lock); + } } /** @@ -798,6 +806,9 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq, u16 retval = 0; u32 val = 0; + /* if reset is in progress return a soft error */ + if (hw->reset_ongoing) + return ICE_ERR_RESET_ONGOING; mutex_lock(&cq->sq_lock); cq->sq_last_status = ICE_AQ_RC_OK; @@ -1057,8 +1068,11 @@ ice_clean_rq_elem(struct ice_hw *hw, struct ice_ctl_q_info *cq, clean_rq_elem_out: /* Set pending if needed, unlock and return */ - if (pending) + if (pending) { + /* re-read HW head to calculate actual pending messages */ + ntu = (u16)(rd32(hw, cq->rq.head) & cq->rq.head_mask); *pending = (u16)((ntc > ntu ? cq->rq.count : 0) + (ntu - ntc)); + } clean_rq_elem_err: mutex_unlock(&cq->rq_lock); diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 1db304c01d10..db2c502ae932 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -26,7 +26,7 @@ static int ice_q_stats_len(struct net_device *netdev) { struct ice_netdev_priv *np = netdev_priv(netdev); - return ((np->vsi->num_txq + np->vsi->num_rxq) * + return ((np->vsi->alloc_txq + np->vsi->alloc_rxq) * (sizeof(struct ice_q_stats) / sizeof(u64))); } @@ -218,7 +218,7 @@ static void ice_get_strings(struct net_device *netdev, u32 stringset, u8 *data) p += ETH_GSTRING_LEN; } - ice_for_each_txq(vsi, i) { + ice_for_each_alloc_txq(vsi, i) { snprintf(p, ETH_GSTRING_LEN, "tx-queue-%u.tx_packets", i); p += ETH_GSTRING_LEN; @@ -226,7 +226,7 @@ static void ice_get_strings(struct net_device *netdev, u32 stringset, u8 *data) p += ETH_GSTRING_LEN; } - ice_for_each_rxq(vsi, i) { + ice_for_each_alloc_rxq(vsi, i) { snprintf(p, ETH_GSTRING_LEN, "rx-queue-%u.rx_packets", i); p += ETH_GSTRING_LEN; @@ -253,6 +253,24 @@ static int ice_get_sset_count(struct net_device *netdev, int sset) { switch (sset) { case ETH_SS_STATS: + /* The number (and order) of strings reported *must* remain + * constant for a given netdevice. This function must not + * report a different number based on run time parameters + * (such as the number of queues in use, or the setting of + * a private ethtool flag). This is due to the nature of the + * ethtool stats API. + * + * User space programs such as ethtool must make 3 separate + * ioctl requests, one for size, one for the strings, and + * finally one for the stats. Since these cross into + * user space, changes to the number or size could result in + * undefined memory access or incorrect string<->value + * correlations for statistics. + * + * Even if it appears to be safe, changes to the size or + * order of strings will suffer from race conditions and are + * not safe. + */ return ICE_ALL_STATS_LEN(netdev); default: return -EOPNOTSUPP; @@ -280,18 +298,26 @@ ice_get_ethtool_stats(struct net_device *netdev, /* populate per queue stats */ rcu_read_lock(); - ice_for_each_txq(vsi, j) { + ice_for_each_alloc_txq(vsi, j) { ring = READ_ONCE(vsi->tx_rings[j]); - if (!ring) - continue; - data[i++] = ring->stats.pkts; - data[i++] = ring->stats.bytes; + if (ring) { + data[i++] = ring->stats.pkts; + data[i++] = ring->stats.bytes; + } else { + data[i++] = 0; + data[i++] = 0; + } } - ice_for_each_rxq(vsi, j) { + ice_for_each_alloc_rxq(vsi, j) { ring = READ_ONCE(vsi->rx_rings[j]); - data[i++] = ring->stats.pkts; - data[i++] = ring->stats.bytes; + if (ring) { + data[i++] = ring->stats.pkts; + data[i++] = ring->stats.bytes; + } else { + data[i++] = 0; + data[i++] = 0; + } } rcu_read_unlock(); @@ -306,58 +332,473 @@ ice_get_ethtool_stats(struct net_device *netdev, } } -static int -ice_get_link_ksettings(struct net_device *netdev, - struct ethtool_link_ksettings *ks) +/** + * ice_phy_type_to_ethtool - convert the phy_types to ethtool link modes + * @netdev: network interface device structure + * @ks: ethtool link ksettings struct to fill out + */ +static void ice_phy_type_to_ethtool(struct net_device *netdev, + struct ethtool_link_ksettings *ks) { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_link_status *hw_link_info; struct ice_vsi *vsi = np->vsi; - bool link_up; + u64 phy_types_low; hw_link_info = &vsi->port_info->phy.link_info; - link_up = hw_link_info->link_info & ICE_AQ_LINK_UP; + phy_types_low = vsi->port_info->phy.phy_type_low; + + ethtool_link_ksettings_zero_link_mode(ks, supported); + ethtool_link_ksettings_zero_link_mode(ks, advertising); + + if (phy_types_low & ICE_PHY_TYPE_LOW_100BASE_TX || + phy_types_low & ICE_PHY_TYPE_LOW_100M_SGMII) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 100baseT_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_100MB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 100baseT_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_T || + phy_types_low & ICE_PHY_TYPE_LOW_1G_SGMII) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseT_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_1000MB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 1000baseT_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_KX) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseKX_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_1000MB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 1000baseKX_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_SX || + phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_LX) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseX_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_1000MB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 1000baseX_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_2500BASE_T) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 2500baseT_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_2500MB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 2500baseT_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_2500BASE_X || + phy_types_low & ICE_PHY_TYPE_LOW_2500BASE_KX) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 2500baseX_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_2500MB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 2500baseX_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_5GBASE_T || + phy_types_low & ICE_PHY_TYPE_LOW_5GBASE_KR) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 5000baseT_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_5GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 5000baseT_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_T || + phy_types_low & ICE_PHY_TYPE_LOW_10G_SFI_DA || + phy_types_low & ICE_PHY_TYPE_LOW_10G_SFI_AOC_ACC || + phy_types_low & ICE_PHY_TYPE_LOW_10G_SFI_C2C) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseT_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_10GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseT_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_KR_CR1) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseKR_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_10GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseKR_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_SR) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseSR_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_10GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseSR_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_LR) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseLR_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_10GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseLR_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_T || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR_S || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR1 || + phy_types_low & ICE_PHY_TYPE_LOW_25G_AUI_AOC_ACC || + phy_types_low & ICE_PHY_TYPE_LOW_25G_AUI_C2C) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseCR_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_25GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 25000baseCR_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_SR || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_LR) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseSR_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_25GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 25000baseSR_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR_S || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR1) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseKR_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_25GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 25000baseKR_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_KR4) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseKR4_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_40GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 40000baseKR4_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_CR4 || + phy_types_low & ICE_PHY_TYPE_LOW_40G_XLAUI_AOC_ACC || + phy_types_low & ICE_PHY_TYPE_LOW_40G_XLAUI) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseCR4_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_40GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 40000baseCR4_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_SR4) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseSR4_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_40GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 40000baseSR4_Full); + } + if (phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_LR4) { + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseLR4_Full); + if (hw_link_info->req_speeds & ICE_AQ_LINK_SPEED_40GB) + ethtool_link_ksettings_add_link_mode(ks, advertising, + 40000baseLR4_Full); + } - ethtool_link_ksettings_add_link_mode(ks, supported, - 10000baseT_Full); - ethtool_link_ksettings_add_link_mode(ks, advertising, - 10000baseT_Full); + /* Autoneg PHY types */ + if (phy_types_low & ICE_PHY_TYPE_LOW_100BASE_TX || + phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_T || + phy_types_low & ICE_PHY_TYPE_LOW_1000BASE_KX || + phy_types_low & ICE_PHY_TYPE_LOW_2500BASE_T || + phy_types_low & ICE_PHY_TYPE_LOW_2500BASE_KX || + phy_types_low & ICE_PHY_TYPE_LOW_5GBASE_T || + phy_types_low & ICE_PHY_TYPE_LOW_5GBASE_KR || + phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_T || + phy_types_low & ICE_PHY_TYPE_LOW_10GBASE_KR_CR1 || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_T || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR_S || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_CR1 || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR_S || + phy_types_low & ICE_PHY_TYPE_LOW_25GBASE_KR1 || + phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_CR4 || + phy_types_low & ICE_PHY_TYPE_LOW_40GBASE_KR4) { + ethtool_link_ksettings_add_link_mode(ks, supported, + Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + Autoneg); + } +} - /* set speed and duplex */ - if (link_up) { - switch (hw_link_info->link_speed) { - case ICE_AQ_LINK_SPEED_100MB: - ks->base.speed = SPEED_100; - break; - case ICE_AQ_LINK_SPEED_2500MB: - ks->base.speed = SPEED_2500; - break; - case ICE_AQ_LINK_SPEED_5GB: - ks->base.speed = SPEED_5000; - break; - case ICE_AQ_LINK_SPEED_10GB: - ks->base.speed = SPEED_10000; - break; - case ICE_AQ_LINK_SPEED_25GB: - ks->base.speed = SPEED_25000; - break; - case ICE_AQ_LINK_SPEED_40GB: - ks->base.speed = SPEED_40000; - break; - default: - ks->base.speed = SPEED_UNKNOWN; - break; - } +#define TEST_SET_BITS_TIMEOUT 50 +#define TEST_SET_BITS_SLEEP_MAX 2000 +#define TEST_SET_BITS_SLEEP_MIN 1000 - ks->base.duplex = DUPLEX_FULL; - } else { - ks->base.speed = SPEED_UNKNOWN; - ks->base.duplex = DUPLEX_UNKNOWN; +/** + * ice_get_settings_link_up - Get Link settings for when link is up + * @ks: ethtool ksettings to fill in + * @netdev: network interface device structure + */ +static void ice_get_settings_link_up(struct ethtool_link_ksettings *ks, + struct net_device *netdev) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ethtool_link_ksettings cap_ksettings; + struct ice_link_status *link_info; + struct ice_vsi *vsi = np->vsi; + bool unrecog_phy_low = false; + + link_info = &vsi->port_info->phy.link_info; + + /* Initialize supported and advertised settings based on phy settings */ + switch (link_info->phy_type_low) { + case ICE_PHY_TYPE_LOW_100BASE_TX: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 100baseT_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 100baseT_Full); + break; + case ICE_PHY_TYPE_LOW_100M_SGMII: + ethtool_link_ksettings_add_link_mode(ks, supported, + 100baseT_Full); + break; + case ICE_PHY_TYPE_LOW_1000BASE_T: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseT_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 1000baseT_Full); + break; + case ICE_PHY_TYPE_LOW_1G_SGMII: + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseT_Full); + break; + case ICE_PHY_TYPE_LOW_1000BASE_SX: + case ICE_PHY_TYPE_LOW_1000BASE_LX: + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseX_Full); + break; + case ICE_PHY_TYPE_LOW_1000BASE_KX: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 1000baseKX_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 1000baseKX_Full); + break; + case ICE_PHY_TYPE_LOW_2500BASE_T: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 2500baseT_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 2500baseT_Full); + break; + case ICE_PHY_TYPE_LOW_2500BASE_X: + ethtool_link_ksettings_add_link_mode(ks, supported, + 2500baseX_Full); + break; + case ICE_PHY_TYPE_LOW_2500BASE_KX: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 2500baseX_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 2500baseX_Full); + break; + case ICE_PHY_TYPE_LOW_5GBASE_T: + case ICE_PHY_TYPE_LOW_5GBASE_KR: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 5000baseT_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 5000baseT_Full); + break; + case ICE_PHY_TYPE_LOW_10GBASE_T: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseT_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseT_Full); + break; + case ICE_PHY_TYPE_LOW_10G_SFI_DA: + case ICE_PHY_TYPE_LOW_10G_SFI_AOC_ACC: + case ICE_PHY_TYPE_LOW_10G_SFI_C2C: + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseT_Full); + break; + case ICE_PHY_TYPE_LOW_10GBASE_SR: + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseSR_Full); + break; + case ICE_PHY_TYPE_LOW_10GBASE_LR: + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseLR_Full); + break; + case ICE_PHY_TYPE_LOW_10GBASE_KR_CR1: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseKR_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 10000baseKR_Full); + break; + case ICE_PHY_TYPE_LOW_25GBASE_T: + case ICE_PHY_TYPE_LOW_25GBASE_CR: + case ICE_PHY_TYPE_LOW_25GBASE_CR_S: + case ICE_PHY_TYPE_LOW_25GBASE_CR1: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseCR_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 25000baseCR_Full); + break; + case ICE_PHY_TYPE_LOW_25G_AUI_AOC_ACC: + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseCR_Full); + break; + case ICE_PHY_TYPE_LOW_25GBASE_SR: + case ICE_PHY_TYPE_LOW_25GBASE_LR: + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseSR_Full); + break; + case ICE_PHY_TYPE_LOW_25GBASE_KR: + case ICE_PHY_TYPE_LOW_25GBASE_KR1: + case ICE_PHY_TYPE_LOW_25GBASE_KR_S: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseKR_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 25000baseKR_Full); + break; + case ICE_PHY_TYPE_LOW_40GBASE_CR4: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseCR4_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 40000baseCR4_Full); + break; + case ICE_PHY_TYPE_LOW_40G_XLAUI_AOC_ACC: + case ICE_PHY_TYPE_LOW_40G_XLAUI: + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseCR4_Full); + break; + case ICE_PHY_TYPE_LOW_40GBASE_SR4: + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseSR4_Full); + break; + case ICE_PHY_TYPE_LOW_40GBASE_LR4: + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseLR4_Full); + break; + case ICE_PHY_TYPE_LOW_40GBASE_KR4: + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseKR4_Full); + ethtool_link_ksettings_add_link_mode(ks, advertising, Autoneg); + ethtool_link_ksettings_add_link_mode(ks, advertising, + 40000baseKR4_Full); + break; + default: + unrecog_phy_low = true; + } + + if (unrecog_phy_low) { + /* if we got here and link is up something bad is afoot */ + netdev_info(netdev, "WARNING: Unrecognized PHY_Low (0x%llx).\n", + (u64)link_info->phy_type_low); } + /* Now that we've worked out everything that could be supported by the + * current PHY type, get what is supported by the NVM and intersect + * them to get what is truly supported + */ + memset(&cap_ksettings, 0, sizeof(struct ethtool_link_ksettings)); + ice_phy_type_to_ethtool(netdev, &cap_ksettings); + ethtool_intersect_link_masks(ks, &cap_ksettings); + + switch (link_info->link_speed) { + case ICE_AQ_LINK_SPEED_40GB: + ks->base.speed = SPEED_40000; + break; + case ICE_AQ_LINK_SPEED_25GB: + ks->base.speed = SPEED_25000; + break; + case ICE_AQ_LINK_SPEED_20GB: + ks->base.speed = SPEED_20000; + break; + case ICE_AQ_LINK_SPEED_10GB: + ks->base.speed = SPEED_10000; + break; + case ICE_AQ_LINK_SPEED_5GB: + ks->base.speed = SPEED_5000; + break; + case ICE_AQ_LINK_SPEED_2500MB: + ks->base.speed = SPEED_2500; + break; + case ICE_AQ_LINK_SPEED_1000MB: + ks->base.speed = SPEED_1000; + break; + case ICE_AQ_LINK_SPEED_100MB: + ks->base.speed = SPEED_100; + break; + default: + netdev_info(netdev, + "WARNING: Unrecognized link_speed (0x%x).\n", + link_info->link_speed); + break; + } + ks->base.duplex = DUPLEX_FULL; +} + +/** + * ice_get_settings_link_down - Get the Link settings when link is down + * @ks: ethtool ksettings to fill in + * @netdev: network interface device structure + * + * Reports link settings that can be determined when link is down + */ +static void +ice_get_settings_link_down(struct ethtool_link_ksettings *ks, + struct net_device __always_unused *netdev) +{ + /* link is down and the driver needs to fall back on + * supported phy types to figure out what info to display + */ + ice_phy_type_to_ethtool(netdev, ks); + + /* With no link, speed and duplex are unknown */ + ks->base.speed = SPEED_UNKNOWN; + ks->base.duplex = DUPLEX_UNKNOWN; +} + +/** + * ice_get_link_ksettings - Get Link Speed and Duplex settings + * @netdev: network interface device structure + * @ks: ethtool ksettings + * + * Reports speed/duplex settings based on media_type + */ +static int ice_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *ks) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_link_status *hw_link_info; + struct ice_vsi *vsi = np->vsi; + + ethtool_link_ksettings_zero_link_mode(ks, supported); + ethtool_link_ksettings_zero_link_mode(ks, advertising); + hw_link_info = &vsi->port_info->phy.link_info; + + /* set speed and duplex */ + if (hw_link_info->link_info & ICE_AQ_LINK_UP) + ice_get_settings_link_up(ks, netdev); + else + ice_get_settings_link_down(ks, netdev); + /* set autoneg settings */ - ks->base.autoneg = ((hw_link_info->an_info & ICE_AQ_AN_COMPLETED) ? - AUTONEG_ENABLE : AUTONEG_DISABLE); + ks->base.autoneg = (hw_link_info->an_info & ICE_AQ_AN_COMPLETED) ? + AUTONEG_ENABLE : AUTONEG_DISABLE; /* set media type settings */ switch (vsi->port_info->phy.media_type) { @@ -416,6 +857,311 @@ ice_get_link_ksettings(struct net_device *netdev, } /** + * ice_ksettings_find_adv_link_speed - Find advertising link speed + * @ks: ethtool ksettings + */ +static u16 +ice_ksettings_find_adv_link_speed(const struct ethtool_link_ksettings *ks) +{ + u16 adv_link_speed = 0; + + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 100baseT_Full)) + adv_link_speed |= ICE_AQ_LINK_SPEED_100MB; + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 1000baseX_Full)) + adv_link_speed |= ICE_AQ_LINK_SPEED_1000MB; + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 1000baseT_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 1000baseKX_Full)) + adv_link_speed |= ICE_AQ_LINK_SPEED_1000MB; + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 2500baseT_Full)) + adv_link_speed |= ICE_AQ_LINK_SPEED_2500MB; + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 2500baseX_Full)) + adv_link_speed |= ICE_AQ_LINK_SPEED_2500MB; + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 5000baseT_Full)) + adv_link_speed |= ICE_AQ_LINK_SPEED_5GB; + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 10000baseT_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 10000baseKR_Full)) + adv_link_speed |= ICE_AQ_LINK_SPEED_10GB; + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 10000baseSR_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 10000baseLR_Full)) + adv_link_speed |= ICE_AQ_LINK_SPEED_10GB; + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 25000baseCR_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 25000baseSR_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 25000baseKR_Full)) + adv_link_speed |= ICE_AQ_LINK_SPEED_25GB; + if (ethtool_link_ksettings_test_link_mode(ks, advertising, + 40000baseCR4_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 40000baseSR4_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 40000baseLR4_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 40000baseKR4_Full)) + adv_link_speed |= ICE_AQ_LINK_SPEED_40GB; + + return adv_link_speed; +} + +/** + * ice_setup_autoneg + * @p: port info + * @ks: ethtool_link_ksettings + * @config: configuration that will be sent down to FW + * @autoneg_enabled: autonegotiation is enabled or not + * @autoneg_changed: will there a change in autonegotiation + * @netdev: network interface device structure + * + * Setup PHY autonegotiation feature + */ +static int +ice_setup_autoneg(struct ice_port_info *p, struct ethtool_link_ksettings *ks, + struct ice_aqc_set_phy_cfg_data *config, + u8 autoneg_enabled, u8 *autoneg_changed, + struct net_device *netdev) +{ + int err = 0; + + *autoneg_changed = 0; + + /* Check autoneg */ + if (autoneg_enabled == AUTONEG_ENABLE) { + /* If autoneg was not already enabled */ + if (!(p->phy.link_info.an_info & ICE_AQ_AN_COMPLETED)) { + /* If autoneg is not supported, return error */ + if (!ethtool_link_ksettings_test_link_mode(ks, + supported, + Autoneg)) { + netdev_info(netdev, "Autoneg not supported on this phy.\n"); + err = -EINVAL; + } else { + /* Autoneg is allowed to change */ + config->caps |= ICE_AQ_PHY_ENA_AUTO_LINK_UPDT; + *autoneg_changed = 1; + } + } + } else { + /* If autoneg is currently enabled */ + if (p->phy.link_info.an_info & ICE_AQ_AN_COMPLETED) { + /* If autoneg is supported 10GBASE_T is the only phy + * that can disable it, so otherwise return error + */ + if (ethtool_link_ksettings_test_link_mode(ks, + supported, + Autoneg)) { + netdev_info(netdev, "Autoneg cannot be disabled on this phy\n"); + err = -EINVAL; + } else { + /* Autoneg is allowed to change */ + config->caps &= ~ICE_AQ_PHY_ENA_AUTO_LINK_UPDT; + *autoneg_changed = 1; + } + } + } + + return err; +} + +/** + * ice_set_link_ksettings - Set Speed and Duplex + * @netdev: network interface device structure + * @ks: ethtool ksettings + * + * Set speed/duplex per media_types advertised/forced + */ +static int ice_set_link_ksettings(struct net_device *netdev, + const struct ethtool_link_ksettings *ks) +{ + u8 autoneg, timeout = TEST_SET_BITS_TIMEOUT, lport = 0; + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ethtool_link_ksettings safe_ks, copy_ks; + struct ice_aqc_get_phy_caps_data *abilities; + u16 adv_link_speed, curr_link_speed, idx; + struct ice_aqc_set_phy_cfg_data config; + struct ice_pf *pf = np->vsi->back; + struct ice_port_info *p; + u8 autoneg_changed = 0; + enum ice_status status; + u64 phy_type_low; + int err = 0; + bool linkup; + + p = np->vsi->port_info; + + if (!p) + return -EOPNOTSUPP; + + /* Check if this is lan vsi */ + for (idx = 0 ; idx < pf->num_alloc_vsi ; idx++) { + if (pf->vsi[idx]->type == ICE_VSI_PF) { + if (np->vsi != pf->vsi[idx]) + return -EOPNOTSUPP; + break; + } + } + + if (p->phy.media_type != ICE_MEDIA_BASET && + p->phy.media_type != ICE_MEDIA_FIBER && + p->phy.media_type != ICE_MEDIA_BACKPLANE && + p->phy.media_type != ICE_MEDIA_DA && + p->phy.link_info.link_info & ICE_AQ_LINK_UP) + return -EOPNOTSUPP; + + /* copy the ksettings to copy_ks to avoid modifying the original */ + memcpy(©_ks, ks, sizeof(struct ethtool_link_ksettings)); + + /* save autoneg out of ksettings */ + autoneg = copy_ks.base.autoneg; + + memset(&safe_ks, 0, sizeof(safe_ks)); + + /* Get link modes supported by hardware.*/ + ice_phy_type_to_ethtool(netdev, &safe_ks); + + /* and check against modes requested by user. + * Return an error if unsupported mode was set. + */ + if (!bitmap_subset(copy_ks.link_modes.advertising, + safe_ks.link_modes.supported, + __ETHTOOL_LINK_MODE_MASK_NBITS)) + return -EINVAL; + + /* get our own copy of the bits to check against */ + memset(&safe_ks, 0, sizeof(struct ethtool_link_ksettings)); + safe_ks.base.cmd = copy_ks.base.cmd; + safe_ks.base.link_mode_masks_nwords = + copy_ks.base.link_mode_masks_nwords; + ice_get_link_ksettings(netdev, &safe_ks); + + /* set autoneg back to what it currently is */ + copy_ks.base.autoneg = safe_ks.base.autoneg; + /* we don't compare the speed */ + copy_ks.base.speed = safe_ks.base.speed; + + /* If copy_ks.base and safe_ks.base are not the same now, then they are + * trying to set something that we do not support. + */ + if (memcmp(©_ks.base, &safe_ks.base, + sizeof(struct ethtool_link_settings))) + return -EOPNOTSUPP; + + while (test_and_set_bit(__ICE_CFG_BUSY, pf->state)) { + timeout--; + if (!timeout) + return -EBUSY; + usleep_range(TEST_SET_BITS_SLEEP_MIN, TEST_SET_BITS_SLEEP_MAX); + } + + abilities = devm_kzalloc(&pf->pdev->dev, sizeof(*abilities), + GFP_KERNEL); + if (!abilities) + return -ENOMEM; + + /* Get the current phy config */ + status = ice_aq_get_phy_caps(p, false, ICE_AQC_REPORT_SW_CFG, abilities, + NULL); + if (status) { + err = -EAGAIN; + goto done; + } + + /* Copy abilities to config in case autoneg is not set below */ + memset(&config, 0, sizeof(struct ice_aqc_set_phy_cfg_data)); + config.caps = abilities->caps & ~ICE_AQC_PHY_AN_MODE; + if (abilities->caps & ICE_AQC_PHY_AN_MODE) + config.caps |= ICE_AQ_PHY_ENA_AUTO_LINK_UPDT; + + /* Check autoneg */ + err = ice_setup_autoneg(p, &safe_ks, &config, autoneg, &autoneg_changed, + netdev); + + if (err) + goto done; + + /* Call to get the current link speed */ + p->phy.get_link_info = true; + status = ice_get_link_status(p, &linkup); + if (status) { + err = -EAGAIN; + goto done; + } + + curr_link_speed = p->phy.link_info.link_speed; + adv_link_speed = ice_ksettings_find_adv_link_speed(ks); + + /* If speed didn't get set, set it to what it currently is. + * This is needed because if advertise is 0 (as it is when autoneg + * is disabled) then speed won't get set. + */ + if (!adv_link_speed) + adv_link_speed = curr_link_speed; + + /* Convert the advertise link speeds to their corresponded PHY_TYPE */ + ice_update_phy_type(&phy_type_low, adv_link_speed); + + if (!autoneg_changed && adv_link_speed == curr_link_speed) { + netdev_info(netdev, "Nothing changed, exiting without setting anything.\n"); + goto done; + } + + /* copy over the rest of the abilities */ + config.low_power_ctrl = abilities->low_power_ctrl; + config.eee_cap = abilities->eee_cap; + config.eeer_value = abilities->eeer_value; + config.link_fec_opt = abilities->link_fec_options; + + /* save the requested speeds */ + p->phy.link_info.req_speeds = adv_link_speed; + + /* set link and auto negotiation so changes take effect */ + config.caps |= ICE_AQ_PHY_ENA_LINK; + + if (phy_type_low) { + config.phy_type_low = cpu_to_le64(phy_type_low) & + abilities->phy_type_low; + } else { + err = -EAGAIN; + netdev_info(netdev, "Nothing changed. No PHY_TYPE is corresponded to advertised link speed.\n"); + goto done; + } + + /* If link is up put link down */ + if (p->phy.link_info.link_info & ICE_AQ_LINK_UP) { + /* Tell the OS link is going down, the link will go + * back up when fw says it is ready asynchronously + */ + ice_print_link_msg(np->vsi, false); + netif_carrier_off(netdev); + netif_tx_stop_all_queues(netdev); + } + + /* make the aq call */ + status = ice_aq_set_phy_cfg(&pf->hw, lport, &config, NULL); + if (status) { + netdev_info(netdev, "Set phy config failed,\n"); + err = -EAGAIN; + } + +done: + devm_kfree(&pf->pdev->dev, abilities); + clear_bit(__ICE_CFG_BUSY, pf->state); + + return err; +} + +/** * ice_get_rxnfc - command to get RX flow classification rules * @netdev: network interface device structure * @cmd: ethtool rxnfc command @@ -519,7 +1265,7 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring) goto done; } - for (i = 0; i < vsi->num_txq; i++) { + for (i = 0; i < vsi->alloc_txq; i++) { /* clone ring and setup updated count */ tx_rings[i] = *vsi->tx_rings[i]; tx_rings[i].count = new_tx_cnt; @@ -551,7 +1297,7 @@ process_rx: goto done; } - for (i = 0; i < vsi->num_rxq; i++) { + for (i = 0; i < vsi->alloc_rxq; i++) { /* clone ring and setup updated count */ rx_rings[i] = *vsi->rx_rings[i]; rx_rings[i].count = new_rx_cnt; @@ -907,6 +1653,7 @@ static int ice_set_rxfh(struct net_device *netdev, const u32 *indir, static const struct ethtool_ops ice_ethtool_ops = { .get_link_ksettings = ice_get_link_ksettings, + .set_link_ksettings = ice_set_link_ksettings, .get_drvinfo = ice_get_drvinfo, .get_regs_len = ice_get_regs_len, .get_regs = ice_get_regs, diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h index 499904874b3f..88f11498804b 100644 --- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h +++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h @@ -6,259 +6,249 @@ #ifndef _ICE_HW_AUTOGEN_H_ #define _ICE_HW_AUTOGEN_H_ -#define QTX_COMM_DBELL(_DBQM) (0x002C0000 + ((_DBQM) * 4)) -#define PF_FW_ARQBAH 0x00080180 -#define PF_FW_ARQBAL 0x00080080 -#define PF_FW_ARQH 0x00080380 -#define PF_FW_ARQH_ARQH_S 0 -#define PF_FW_ARQH_ARQH_M ICE_M(0x3FF, PF_FW_ARQH_ARQH_S) -#define PF_FW_ARQLEN 0x00080280 -#define PF_FW_ARQLEN_ARQLEN_S 0 -#define PF_FW_ARQLEN_ARQLEN_M ICE_M(0x3FF, PF_FW_ARQLEN_ARQLEN_S) -#define PF_FW_ARQLEN_ARQVFE_S 28 -#define PF_FW_ARQLEN_ARQVFE_M BIT(PF_FW_ARQLEN_ARQVFE_S) -#define PF_FW_ARQLEN_ARQOVFL_S 29 -#define PF_FW_ARQLEN_ARQOVFL_M BIT(PF_FW_ARQLEN_ARQOVFL_S) -#define PF_FW_ARQLEN_ARQCRIT_S 30 -#define PF_FW_ARQLEN_ARQCRIT_M BIT(PF_FW_ARQLEN_ARQCRIT_S) -#define PF_FW_ARQLEN_ARQENABLE_S 31 -#define PF_FW_ARQLEN_ARQENABLE_M BIT(PF_FW_ARQLEN_ARQENABLE_S) -#define PF_FW_ARQT 0x00080480 -#define PF_FW_ATQBAH 0x00080100 -#define PF_FW_ATQBAL 0x00080000 -#define PF_FW_ATQH 0x00080300 -#define PF_FW_ATQH_ATQH_S 0 -#define PF_FW_ATQH_ATQH_M ICE_M(0x3FF, PF_FW_ATQH_ATQH_S) -#define PF_FW_ATQLEN 0x00080200 -#define PF_FW_ATQLEN_ATQLEN_S 0 -#define PF_FW_ATQLEN_ATQLEN_M ICE_M(0x3FF, PF_FW_ATQLEN_ATQLEN_S) -#define PF_FW_ATQLEN_ATQVFE_S 28 -#define PF_FW_ATQLEN_ATQVFE_M BIT(PF_FW_ATQLEN_ATQVFE_S) -#define PF_FW_ATQLEN_ATQOVFL_S 29 -#define PF_FW_ATQLEN_ATQOVFL_M BIT(PF_FW_ATQLEN_ATQOVFL_S) -#define PF_FW_ATQLEN_ATQCRIT_S 30 -#define PF_FW_ATQLEN_ATQCRIT_M BIT(PF_FW_ATQLEN_ATQCRIT_S) -#define PF_FW_ATQLEN_ATQENABLE_S 31 -#define PF_FW_ATQLEN_ATQENABLE_M BIT(PF_FW_ATQLEN_ATQENABLE_S) -#define PF_FW_ATQT 0x00080400 - +#define QTX_COMM_DBELL(_DBQM) (0x002C0000 + ((_DBQM) * 4)) +#define PF_FW_ARQBAH 0x00080180 +#define PF_FW_ARQBAL 0x00080080 +#define PF_FW_ARQH 0x00080380 +#define PF_FW_ARQH_ARQH_M ICE_M(0x3FF, 0) +#define PF_FW_ARQLEN 0x00080280 +#define PF_FW_ARQLEN_ARQLEN_M ICE_M(0x3FF, 0) +#define PF_FW_ARQLEN_ARQVFE_M BIT(28) +#define PF_FW_ARQLEN_ARQOVFL_M BIT(29) +#define PF_FW_ARQLEN_ARQCRIT_M BIT(30) +#define PF_FW_ARQLEN_ARQENABLE_M BIT(31) +#define PF_FW_ARQT 0x00080480 +#define PF_FW_ATQBAH 0x00080100 +#define PF_FW_ATQBAL 0x00080000 +#define PF_FW_ATQH 0x00080300 +#define PF_FW_ATQH_ATQH_M ICE_M(0x3FF, 0) +#define PF_FW_ATQLEN 0x00080200 +#define PF_FW_ATQLEN_ATQLEN_M ICE_M(0x3FF, 0) +#define PF_FW_ATQLEN_ATQVFE_M BIT(28) +#define PF_FW_ATQLEN_ATQOVFL_M BIT(29) +#define PF_FW_ATQLEN_ATQCRIT_M BIT(30) +#define PF_FW_ATQLEN_ATQENABLE_M BIT(31) +#define PF_FW_ATQT 0x00080400 #define GLFLXP_RXDID_FLAGS(_i, _j) (0x0045D000 + ((_i) * 4 + (_j) * 256)) #define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_S 0 -#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_M ICE_M(0x3F, GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_S) +#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_M ICE_M(0x3F, 0) #define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_1_S 8 -#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_1_M ICE_M(0x3F, GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_1_S) +#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_1_M ICE_M(0x3F, 8) #define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_2_S 16 -#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_2_M ICE_M(0x3F, GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_2_S) +#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_2_M ICE_M(0x3F, 16) #define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_3_S 24 -#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_3_M ICE_M(0x3F, GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_3_S) +#define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_3_M ICE_M(0x3F, 24) #define GLFLXP_RXDID_FLX_WRD_0(_i) (0x0045c800 + ((_i) * 4)) #define GLFLXP_RXDID_FLX_WRD_0_PROT_MDID_S 0 -#define GLFLXP_RXDID_FLX_WRD_0_PROT_MDID_M ICE_M(0xFF, GLFLXP_RXDID_FLX_WRD_0_PROT_MDID_S) +#define GLFLXP_RXDID_FLX_WRD_0_PROT_MDID_M ICE_M(0xFF, 0) #define GLFLXP_RXDID_FLX_WRD_0_RXDID_OPCODE_S 30 -#define GLFLXP_RXDID_FLX_WRD_0_RXDID_OPCODE_M ICE_M(0x3, GLFLXP_RXDID_FLX_WRD_0_RXDID_OPCODE_S) +#define GLFLXP_RXDID_FLX_WRD_0_RXDID_OPCODE_M ICE_M(0x3, 30) #define GLFLXP_RXDID_FLX_WRD_1(_i) (0x0045c900 + ((_i) * 4)) #define GLFLXP_RXDID_FLX_WRD_1_PROT_MDID_S 0 -#define GLFLXP_RXDID_FLX_WRD_1_PROT_MDID_M ICE_M(0xFF, GLFLXP_RXDID_FLX_WRD_1_PROT_MDID_S) +#define GLFLXP_RXDID_FLX_WRD_1_PROT_MDID_M ICE_M(0xFF, 0) #define GLFLXP_RXDID_FLX_WRD_1_RXDID_OPCODE_S 30 -#define GLFLXP_RXDID_FLX_WRD_1_RXDID_OPCODE_M ICE_M(0x3, GLFLXP_RXDID_FLX_WRD_1_RXDID_OPCODE_S) +#define GLFLXP_RXDID_FLX_WRD_1_RXDID_OPCODE_M ICE_M(0x3, 30) #define GLFLXP_RXDID_FLX_WRD_2(_i) (0x0045ca00 + ((_i) * 4)) #define GLFLXP_RXDID_FLX_WRD_2_PROT_MDID_S 0 -#define GLFLXP_RXDID_FLX_WRD_2_PROT_MDID_M ICE_M(0xFF, GLFLXP_RXDID_FLX_WRD_2_PROT_MDID_S) +#define GLFLXP_RXDID_FLX_WRD_2_PROT_MDID_M ICE_M(0xFF, 0) #define GLFLXP_RXDID_FLX_WRD_2_RXDID_OPCODE_S 30 -#define GLFLXP_RXDID_FLX_WRD_2_RXDID_OPCODE_M ICE_M(0x3, GLFLXP_RXDID_FLX_WRD_2_RXDID_OPCODE_S) +#define GLFLXP_RXDID_FLX_WRD_2_RXDID_OPCODE_M ICE_M(0x3, 30) #define GLFLXP_RXDID_FLX_WRD_3(_i) (0x0045cb00 + ((_i) * 4)) #define GLFLXP_RXDID_FLX_WRD_3_PROT_MDID_S 0 -#define GLFLXP_RXDID_FLX_WRD_3_PROT_MDID_M ICE_M(0xFF, GLFLXP_RXDID_FLX_WRD_3_PROT_MDID_S) +#define GLFLXP_RXDID_FLX_WRD_3_PROT_MDID_M ICE_M(0xFF, 0) #define GLFLXP_RXDID_FLX_WRD_3_RXDID_OPCODE_S 30 -#define GLFLXP_RXDID_FLX_WRD_3_RXDID_OPCODE_M ICE_M(0x3, GLFLXP_RXDID_FLX_WRD_3_RXDID_OPCODE_S) - -#define QRXFLXP_CNTXT(_QRX) (0x00480000 + ((_QRX) * 4)) -#define QRXFLXP_CNTXT_RXDID_IDX_S 0 -#define QRXFLXP_CNTXT_RXDID_IDX_M ICE_M(0x3F, QRXFLXP_CNTXT_RXDID_IDX_S) -#define QRXFLXP_CNTXT_RXDID_PRIO_S 8 -#define QRXFLXP_CNTXT_RXDID_PRIO_M ICE_M(0x7, QRXFLXP_CNTXT_RXDID_PRIO_S) -#define QRXFLXP_CNTXT_TS_S 11 -#define QRXFLXP_CNTXT_TS_M BIT(QRXFLXP_CNTXT_TS_S) -#define GLGEN_RSTAT 0x000B8188 -#define GLGEN_RSTAT_DEVSTATE_S 0 -#define GLGEN_RSTAT_DEVSTATE_M ICE_M(0x3, GLGEN_RSTAT_DEVSTATE_S) -#define GLGEN_RSTCTL 0x000B8180 -#define GLGEN_RSTCTL_GRSTDEL_S 0 -#define GLGEN_RSTCTL_GRSTDEL_M ICE_M(0x3F, GLGEN_RSTCTL_GRSTDEL_S) -#define GLGEN_RSTAT_RESET_TYPE_S 2 -#define GLGEN_RSTAT_RESET_TYPE_M ICE_M(0x3, GLGEN_RSTAT_RESET_TYPE_S) -#define GLGEN_RTRIG 0x000B8190 -#define GLGEN_RTRIG_CORER_S 0 -#define GLGEN_RTRIG_CORER_M BIT(GLGEN_RTRIG_CORER_S) -#define GLGEN_RTRIG_GLOBR_S 1 -#define GLGEN_RTRIG_GLOBR_M BIT(GLGEN_RTRIG_GLOBR_S) -#define GLGEN_STAT 0x000B612C -#define PFGEN_CTRL 0x00091000 -#define PFGEN_CTRL_PFSWR_S 0 -#define PFGEN_CTRL_PFSWR_M BIT(PFGEN_CTRL_PFSWR_S) -#define PFGEN_STATE 0x00088000 -#define PRTGEN_STATUS 0x000B8100 -#define PFHMC_ERRORDATA 0x00520500 -#define PFHMC_ERRORINFO 0x00520400 -#define GLINT_DYN_CTL(_INT) (0x00160000 + ((_INT) * 4)) -#define GLINT_DYN_CTL_INTENA_S 0 -#define GLINT_DYN_CTL_INTENA_M BIT(GLINT_DYN_CTL_INTENA_S) -#define GLINT_DYN_CTL_CLEARPBA_S 1 -#define GLINT_DYN_CTL_CLEARPBA_M BIT(GLINT_DYN_CTL_CLEARPBA_S) -#define GLINT_DYN_CTL_SWINT_TRIG_S 2 -#define GLINT_DYN_CTL_SWINT_TRIG_M BIT(GLINT_DYN_CTL_SWINT_TRIG_S) -#define GLINT_DYN_CTL_ITR_INDX_S 3 -#define GLINT_DYN_CTL_SW_ITR_INDX_S 25 -#define GLINT_DYN_CTL_SW_ITR_INDX_M ICE_M(0x3, GLINT_DYN_CTL_SW_ITR_INDX_S) -#define GLINT_DYN_CTL_INTENA_MSK_S 31 -#define GLINT_DYN_CTL_INTENA_MSK_M BIT(GLINT_DYN_CTL_INTENA_MSK_S) -#define GLINT_ITR(_i, _INT) (0x00154000 + ((_i) * 8192 + (_INT) * 4)) -#define PFINT_FW_CTL 0x0016C800 -#define PFINT_FW_CTL_MSIX_INDX_S 0 -#define PFINT_FW_CTL_MSIX_INDX_M ICE_M(0x7FF, PFINT_FW_CTL_MSIX_INDX_S) -#define PFINT_FW_CTL_ITR_INDX_S 11 -#define PFINT_FW_CTL_ITR_INDX_M ICE_M(0x3, PFINT_FW_CTL_ITR_INDX_S) -#define PFINT_FW_CTL_CAUSE_ENA_S 30 -#define PFINT_FW_CTL_CAUSE_ENA_M BIT(PFINT_FW_CTL_CAUSE_ENA_S) -#define PFINT_OICR 0x0016CA00 -#define PFINT_OICR_HLP_RDY_S 14 -#define PFINT_OICR_HLP_RDY_M BIT(PFINT_OICR_HLP_RDY_S) -#define PFINT_OICR_CPM_RDY_S 15 -#define PFINT_OICR_CPM_RDY_M BIT(PFINT_OICR_CPM_RDY_S) -#define PFINT_OICR_ECC_ERR_S 16 -#define PFINT_OICR_ECC_ERR_M BIT(PFINT_OICR_ECC_ERR_S) -#define PFINT_OICR_MAL_DETECT_S 19 -#define PFINT_OICR_MAL_DETECT_M BIT(PFINT_OICR_MAL_DETECT_S) -#define PFINT_OICR_GRST_S 20 -#define PFINT_OICR_GRST_M BIT(PFINT_OICR_GRST_S) -#define PFINT_OICR_PCI_EXCEPTION_S 21 -#define PFINT_OICR_PCI_EXCEPTION_M BIT(PFINT_OICR_PCI_EXCEPTION_S) -#define PFINT_OICR_GPIO_S 22 -#define PFINT_OICR_GPIO_M BIT(PFINT_OICR_GPIO_S) -#define PFINT_OICR_STORM_DETECT_S 24 -#define PFINT_OICR_STORM_DETECT_M BIT(PFINT_OICR_STORM_DETECT_S) -#define PFINT_OICR_HMC_ERR_S 26 -#define PFINT_OICR_HMC_ERR_M BIT(PFINT_OICR_HMC_ERR_S) -#define PFINT_OICR_PE_CRITERR_S 28 -#define PFINT_OICR_PE_CRITERR_M BIT(PFINT_OICR_PE_CRITERR_S) -#define PFINT_OICR_CTL 0x0016CA80 -#define PFINT_OICR_CTL_MSIX_INDX_S 0 -#define PFINT_OICR_CTL_MSIX_INDX_M ICE_M(0x7FF, PFINT_OICR_CTL_MSIX_INDX_S) -#define PFINT_OICR_CTL_ITR_INDX_S 11 -#define PFINT_OICR_CTL_ITR_INDX_M ICE_M(0x3, PFINT_OICR_CTL_ITR_INDX_S) -#define PFINT_OICR_CTL_CAUSE_ENA_S 30 -#define PFINT_OICR_CTL_CAUSE_ENA_M BIT(PFINT_OICR_CTL_CAUSE_ENA_S) -#define PFINT_OICR_ENA 0x0016C900 -#define QINT_RQCTL(_QRX) (0x00150000 + ((_QRX) * 4)) -#define QINT_RQCTL_MSIX_INDX_S 0 -#define QINT_RQCTL_ITR_INDX_S 11 -#define QINT_RQCTL_CAUSE_ENA_S 30 -#define QINT_RQCTL_CAUSE_ENA_M BIT(QINT_RQCTL_CAUSE_ENA_S) -#define QINT_TQCTL(_DBQM) (0x00140000 + ((_DBQM) * 4)) -#define QINT_TQCTL_MSIX_INDX_S 0 -#define QINT_TQCTL_ITR_INDX_S 11 -#define QINT_TQCTL_CAUSE_ENA_S 30 -#define QINT_TQCTL_CAUSE_ENA_M BIT(QINT_TQCTL_CAUSE_ENA_S) -#define GLLAN_RCTL_0 0x002941F8 -#define QRX_CONTEXT(_i, _QRX) (0x00280000 + ((_i) * 8192 + (_QRX) * 4)) -#define QRX_CTRL(_QRX) (0x00120000 + ((_QRX) * 4)) -#define QRX_CTRL_MAX_INDEX 2047 -#define QRX_CTRL_QENA_REQ_S 0 -#define QRX_CTRL_QENA_REQ_M BIT(QRX_CTRL_QENA_REQ_S) -#define QRX_CTRL_QENA_STAT_S 2 -#define QRX_CTRL_QENA_STAT_M BIT(QRX_CTRL_QENA_STAT_S) -#define QRX_ITR(_QRX) (0x00292000 + ((_QRX) * 4)) -#define QRX_TAIL(_QRX) (0x00290000 + ((_QRX) * 4)) -#define GLNVM_FLA 0x000B6108 -#define GLNVM_FLA_LOCKED_S 6 -#define GLNVM_FLA_LOCKED_M BIT(GLNVM_FLA_LOCKED_S) -#define GLNVM_GENS 0x000B6100 -#define GLNVM_GENS_SR_SIZE_S 5 -#define GLNVM_GENS_SR_SIZE_M ICE_M(0x7, GLNVM_GENS_SR_SIZE_S) -#define GLNVM_ULD 0x000B6008 -#define GLNVM_ULD_CORER_DONE_S 3 -#define GLNVM_ULD_CORER_DONE_M BIT(GLNVM_ULD_CORER_DONE_S) -#define GLNVM_ULD_GLOBR_DONE_S 4 -#define GLNVM_ULD_GLOBR_DONE_M BIT(GLNVM_ULD_GLOBR_DONE_S) -#define PF_FUNC_RID 0x0009E880 -#define PF_FUNC_RID_FUNC_NUM_S 0 -#define PF_FUNC_RID_FUNC_NUM_M ICE_M(0x7, PF_FUNC_RID_FUNC_NUM_S) -#define GLPRT_BPRCH(_i) (0x00381384 + ((_i) * 8)) -#define GLPRT_BPRCL(_i) (0x00381380 + ((_i) * 8)) -#define GLPRT_BPTCH(_i) (0x00381244 + ((_i) * 8)) -#define GLPRT_BPTCL(_i) (0x00381240 + ((_i) * 8)) -#define GLPRT_CRCERRS(_i) (0x00380100 + ((_i) * 8)) -#define GLPRT_GORCH(_i) (0x00380004 + ((_i) * 8)) -#define GLPRT_GORCL(_i) (0x00380000 + ((_i) * 8)) -#define GLPRT_GOTCH(_i) (0x00380B44 + ((_i) * 8)) -#define GLPRT_GOTCL(_i) (0x00380B40 + ((_i) * 8)) -#define GLPRT_ILLERRC(_i) (0x003801C0 + ((_i) * 8)) -#define GLPRT_LXOFFRXC(_i) (0x003802C0 + ((_i) * 8)) -#define GLPRT_LXOFFTXC(_i) (0x00381180 + ((_i) * 8)) -#define GLPRT_LXONRXC(_i) (0x00380280 + ((_i) * 8)) -#define GLPRT_LXONTXC(_i) (0x00381140 + ((_i) * 8)) -#define GLPRT_MLFC(_i) (0x00380040 + ((_i) * 8)) -#define GLPRT_MPRCH(_i) (0x00381344 + ((_i) * 8)) -#define GLPRT_MPRCL(_i) (0x00381340 + ((_i) * 8)) -#define GLPRT_MPTCH(_i) (0x00381204 + ((_i) * 8)) -#define GLPRT_MPTCL(_i) (0x00381200 + ((_i) * 8)) -#define GLPRT_MRFC(_i) (0x00380080 + ((_i) * 8)) -#define GLPRT_PRC1023H(_i) (0x00380A04 + ((_i) * 8)) -#define GLPRT_PRC1023L(_i) (0x00380A00 + ((_i) * 8)) -#define GLPRT_PRC127H(_i) (0x00380944 + ((_i) * 8)) -#define GLPRT_PRC127L(_i) (0x00380940 + ((_i) * 8)) -#define GLPRT_PRC1522H(_i) (0x00380A44 + ((_i) * 8)) -#define GLPRT_PRC1522L(_i) (0x00380A40 + ((_i) * 8)) -#define GLPRT_PRC255H(_i) (0x00380984 + ((_i) * 8)) -#define GLPRT_PRC255L(_i) (0x00380980 + ((_i) * 8)) -#define GLPRT_PRC511H(_i) (0x003809C4 + ((_i) * 8)) -#define GLPRT_PRC511L(_i) (0x003809C0 + ((_i) * 8)) -#define GLPRT_PRC64H(_i) (0x00380904 + ((_i) * 8)) -#define GLPRT_PRC64L(_i) (0x00380900 + ((_i) * 8)) -#define GLPRT_PRC9522H(_i) (0x00380A84 + ((_i) * 8)) -#define GLPRT_PRC9522L(_i) (0x00380A80 + ((_i) * 8)) -#define GLPRT_PTC1023H(_i) (0x00380C84 + ((_i) * 8)) -#define GLPRT_PTC1023L(_i) (0x00380C80 + ((_i) * 8)) -#define GLPRT_PTC127H(_i) (0x00380BC4 + ((_i) * 8)) -#define GLPRT_PTC127L(_i) (0x00380BC0 + ((_i) * 8)) -#define GLPRT_PTC1522H(_i) (0x00380CC4 + ((_i) * 8)) -#define GLPRT_PTC1522L(_i) (0x00380CC0 + ((_i) * 8)) -#define GLPRT_PTC255H(_i) (0x00380C04 + ((_i) * 8)) -#define GLPRT_PTC255L(_i) (0x00380C00 + ((_i) * 8)) -#define GLPRT_PTC511H(_i) (0x00380C44 + ((_i) * 8)) -#define GLPRT_PTC511L(_i) (0x00380C40 + ((_i) * 8)) -#define GLPRT_PTC64H(_i) (0x00380B84 + ((_i) * 8)) -#define GLPRT_PTC64L(_i) (0x00380B80 + ((_i) * 8)) -#define GLPRT_PTC9522H(_i) (0x00380D04 + ((_i) * 8)) -#define GLPRT_PTC9522L(_i) (0x00380D00 + ((_i) * 8)) -#define GLPRT_RFC(_i) (0x00380AC0 + ((_i) * 8)) -#define GLPRT_RJC(_i) (0x00380B00 + ((_i) * 8)) -#define GLPRT_RLEC(_i) (0x00380140 + ((_i) * 8)) -#define GLPRT_ROC(_i) (0x00380240 + ((_i) * 8)) -#define GLPRT_RUC(_i) (0x00380200 + ((_i) * 8)) -#define GLPRT_TDOLD(_i) (0x00381280 + ((_i) * 8)) -#define GLPRT_UPRCH(_i) (0x00381304 + ((_i) * 8)) -#define GLPRT_UPRCL(_i) (0x00381300 + ((_i) * 8)) -#define GLPRT_UPTCH(_i) (0x003811C4 + ((_i) * 8)) -#define GLPRT_UPTCL(_i) (0x003811C0 + ((_i) * 8)) -#define GLV_BPRCH(_i) (0x003B6004 + ((_i) * 8)) -#define GLV_BPRCL(_i) (0x003B6000 + ((_i) * 8)) -#define GLV_BPTCH(_i) (0x0030E004 + ((_i) * 8)) -#define GLV_BPTCL(_i) (0x0030E000 + ((_i) * 8)) -#define GLV_GORCH(_i) (0x003B0004 + ((_i) * 8)) -#define GLV_GORCL(_i) (0x003B0000 + ((_i) * 8)) -#define GLV_GOTCH(_i) (0x00300004 + ((_i) * 8)) -#define GLV_GOTCL(_i) (0x00300000 + ((_i) * 8)) -#define GLV_MPRCH(_i) (0x003B4004 + ((_i) * 8)) -#define GLV_MPRCL(_i) (0x003B4000 + ((_i) * 8)) -#define GLV_MPTCH(_i) (0x0030C004 + ((_i) * 8)) -#define GLV_MPTCL(_i) (0x0030C000 + ((_i) * 8)) -#define GLV_RDPC(_i) (0x00294C04 + ((_i) * 4)) -#define GLV_TEPC(_VSI) (0x00312000 + ((_VSI) * 4)) -#define GLV_UPRCH(_i) (0x003B2004 + ((_i) * 8)) -#define GLV_UPRCL(_i) (0x003B2000 + ((_i) * 8)) -#define GLV_UPTCH(_i) (0x0030A004 + ((_i) * 8)) -#define GLV_UPTCL(_i) (0x0030A000 + ((_i) * 8)) -#define VSIQF_HKEY_MAX_INDEX 12 +#define GLFLXP_RXDID_FLX_WRD_3_RXDID_OPCODE_M ICE_M(0x3, 30) +#define QRXFLXP_CNTXT(_QRX) (0x00480000 + ((_QRX) * 4)) +#define QRXFLXP_CNTXT_RXDID_IDX_S 0 +#define QRXFLXP_CNTXT_RXDID_IDX_M ICE_M(0x3F, 0) +#define QRXFLXP_CNTXT_RXDID_PRIO_S 8 +#define QRXFLXP_CNTXT_RXDID_PRIO_M ICE_M(0x7, 8) +#define GLGEN_RSTAT 0x000B8188 +#define GLGEN_RSTAT_DEVSTATE_M ICE_M(0x3, 0) +#define GLGEN_RSTCTL 0x000B8180 +#define GLGEN_RSTCTL_GRSTDEL_S 0 +#define GLGEN_RSTCTL_GRSTDEL_M ICE_M(0x3F, GLGEN_RSTCTL_GRSTDEL_S) +#define GLGEN_RSTAT_RESET_TYPE_S 2 +#define GLGEN_RSTAT_RESET_TYPE_M ICE_M(0x3, 2) +#define GLGEN_RTRIG 0x000B8190 +#define GLGEN_RTRIG_CORER_M BIT(0) +#define GLGEN_RTRIG_GLOBR_M BIT(1) +#define GLGEN_STAT 0x000B612C +#define PFGEN_CTRL 0x00091000 +#define PFGEN_CTRL_PFSWR_M BIT(0) +#define PFGEN_STATE 0x00088000 +#define PRTGEN_STATUS 0x000B8100 +#define PFHMC_ERRORDATA 0x00520500 +#define PFHMC_ERRORINFO 0x00520400 +#define GLINT_DYN_CTL(_INT) (0x00160000 + ((_INT) * 4)) +#define GLINT_DYN_CTL_INTENA_M BIT(0) +#define GLINT_DYN_CTL_CLEARPBA_M BIT(1) +#define GLINT_DYN_CTL_SWINT_TRIG_M BIT(2) +#define GLINT_DYN_CTL_ITR_INDX_S 3 +#define GLINT_DYN_CTL_SW_ITR_INDX_M ICE_M(0x3, 25) +#define GLINT_DYN_CTL_INTENA_MSK_M BIT(31) +#define GLINT_ITR(_i, _INT) (0x00154000 + ((_i) * 8192 + (_INT) * 4)) +#define PFINT_FW_CTL 0x0016C800 +#define PFINT_FW_CTL_MSIX_INDX_M ICE_M(0x7FF, 0) +#define PFINT_FW_CTL_ITR_INDX_S 11 +#define PFINT_FW_CTL_ITR_INDX_M ICE_M(0x3, 11) +#define PFINT_FW_CTL_CAUSE_ENA_M BIT(30) +#define PFINT_OICR 0x0016CA00 +#define PFINT_OICR_ECC_ERR_M BIT(16) +#define PFINT_OICR_MAL_DETECT_M BIT(19) +#define PFINT_OICR_GRST_M BIT(20) +#define PFINT_OICR_PCI_EXCEPTION_M BIT(21) +#define PFINT_OICR_HMC_ERR_M BIT(26) +#define PFINT_OICR_PE_CRITERR_M BIT(28) +#define PFINT_OICR_CTL 0x0016CA80 +#define PFINT_OICR_CTL_MSIX_INDX_M ICE_M(0x7FF, 0) +#define PFINT_OICR_CTL_ITR_INDX_S 11 +#define PFINT_OICR_CTL_ITR_INDX_M ICE_M(0x3, 11) +#define PFINT_OICR_CTL_CAUSE_ENA_M BIT(30) +#define PFINT_OICR_ENA 0x0016C900 +#define QINT_RQCTL(_QRX) (0x00150000 + ((_QRX) * 4)) +#define QINT_RQCTL_MSIX_INDX_S 0 +#define QINT_RQCTL_ITR_INDX_S 11 +#define QINT_RQCTL_CAUSE_ENA_M BIT(30) +#define QINT_TQCTL(_DBQM) (0x00140000 + ((_DBQM) * 4)) +#define QINT_TQCTL_MSIX_INDX_S 0 +#define QINT_TQCTL_ITR_INDX_S 11 +#define QINT_TQCTL_CAUSE_ENA_M BIT(30) +#define QRX_CONTEXT(_i, _QRX) (0x00280000 + ((_i) * 8192 + (_QRX) * 4)) +#define QRX_CTRL(_QRX) (0x00120000 + ((_QRX) * 4)) +#define QRX_CTRL_MAX_INDEX 2047 +#define QRX_CTRL_QENA_REQ_S 0 +#define QRX_CTRL_QENA_REQ_M BIT(0) +#define QRX_CTRL_QENA_STAT_S 2 +#define QRX_CTRL_QENA_STAT_M BIT(2) +#define QRX_ITR(_QRX) (0x00292000 + ((_QRX) * 4)) +#define QRX_TAIL(_QRX) (0x00290000 + ((_QRX) * 4)) +#define QRX_TAIL_MAX_INDEX 2047 +#define QRX_TAIL_TAIL_S 0 +#define QRX_TAIL_TAIL_M ICE_M(0x1FFF, 0) +#define GL_MDET_RX 0x00294C00 +#define GL_MDET_RX_QNUM_S 0 +#define GL_MDET_RX_QNUM_M ICE_M(0x7FFF, 0) +#define GL_MDET_RX_VF_NUM_S 15 +#define GL_MDET_RX_VF_NUM_M ICE_M(0xFF, 15) +#define GL_MDET_RX_PF_NUM_S 23 +#define GL_MDET_RX_PF_NUM_M ICE_M(0x7, 23) +#define GL_MDET_RX_MAL_TYPE_S 26 +#define GL_MDET_RX_MAL_TYPE_M ICE_M(0x1F, 26) +#define GL_MDET_RX_VALID_M BIT(31) +#define GL_MDET_TX_PQM 0x002D2E00 +#define GL_MDET_TX_PQM_PF_NUM_S 0 +#define GL_MDET_TX_PQM_PF_NUM_M ICE_M(0x7, 0) +#define GL_MDET_TX_PQM_VF_NUM_S 4 +#define GL_MDET_TX_PQM_VF_NUM_M ICE_M(0xFF, 4) +#define GL_MDET_TX_PQM_QNUM_S 12 +#define GL_MDET_TX_PQM_QNUM_M ICE_M(0x3FFF, 12) +#define GL_MDET_TX_PQM_MAL_TYPE_S 26 +#define GL_MDET_TX_PQM_MAL_TYPE_M ICE_M(0x1F, 26) +#define GL_MDET_TX_PQM_VALID_M BIT(31) +#define GL_MDET_TX_TCLAN 0x000FC068 +#define GL_MDET_TX_TCLAN_QNUM_S 0 +#define GL_MDET_TX_TCLAN_QNUM_M ICE_M(0x7FFF, 0) +#define GL_MDET_TX_TCLAN_VF_NUM_S 15 +#define GL_MDET_TX_TCLAN_VF_NUM_M ICE_M(0xFF, 15) +#define GL_MDET_TX_TCLAN_PF_NUM_S 23 +#define GL_MDET_TX_TCLAN_PF_NUM_M ICE_M(0x7, 23) +#define GL_MDET_TX_TCLAN_MAL_TYPE_S 26 +#define GL_MDET_TX_TCLAN_MAL_TYPE_M ICE_M(0x1F, 26) +#define GL_MDET_TX_TCLAN_VALID_M BIT(31) +#define PF_MDET_RX 0x00294280 +#define PF_MDET_RX_VALID_M BIT(0) +#define PF_MDET_TX_PQM 0x002D2C80 +#define PF_MDET_TX_PQM_VALID_M BIT(0) +#define PF_MDET_TX_TCLAN 0x000FC000 +#define PF_MDET_TX_TCLAN_VALID_M BIT(0) +#define GLNVM_FLA 0x000B6108 +#define GLNVM_FLA_LOCKED_M BIT(6) +#define GLNVM_GENS 0x000B6100 +#define GLNVM_GENS_SR_SIZE_S 5 +#define GLNVM_GENS_SR_SIZE_M ICE_M(0x7, 5) +#define GLNVM_ULD 0x000B6008 +#define GLNVM_ULD_CORER_DONE_M BIT(3) +#define GLNVM_ULD_GLOBR_DONE_M BIT(4) +#define PF_FUNC_RID 0x0009E880 +#define PF_FUNC_RID_FUNC_NUM_S 0 +#define PF_FUNC_RID_FUNC_NUM_M ICE_M(0x7, 0) +#define GLPRT_BPRCH(_i) (0x00381384 + ((_i) * 8)) +#define GLPRT_BPRCL(_i) (0x00381380 + ((_i) * 8)) +#define GLPRT_BPTCH(_i) (0x00381244 + ((_i) * 8)) +#define GLPRT_BPTCL(_i) (0x00381240 + ((_i) * 8)) +#define GLPRT_CRCERRS(_i) (0x00380100 + ((_i) * 8)) +#define GLPRT_GORCH(_i) (0x00380004 + ((_i) * 8)) +#define GLPRT_GORCL(_i) (0x00380000 + ((_i) * 8)) +#define GLPRT_GOTCH(_i) (0x00380B44 + ((_i) * 8)) +#define GLPRT_GOTCL(_i) (0x00380B40 + ((_i) * 8)) +#define GLPRT_ILLERRC(_i) (0x003801C0 + ((_i) * 8)) +#define GLPRT_LXOFFRXC(_i) (0x003802C0 + ((_i) * 8)) +#define GLPRT_LXOFFTXC(_i) (0x00381180 + ((_i) * 8)) +#define GLPRT_LXONRXC(_i) (0x00380280 + ((_i) * 8)) +#define GLPRT_LXONTXC(_i) (0x00381140 + ((_i) * 8)) +#define GLPRT_MLFC(_i) (0x00380040 + ((_i) * 8)) +#define GLPRT_MPRCH(_i) (0x00381344 + ((_i) * 8)) +#define GLPRT_MPRCL(_i) (0x00381340 + ((_i) * 8)) +#define GLPRT_MPTCH(_i) (0x00381204 + ((_i) * 8)) +#define GLPRT_MPTCL(_i) (0x00381200 + ((_i) * 8)) +#define GLPRT_MRFC(_i) (0x00380080 + ((_i) * 8)) +#define GLPRT_PRC1023H(_i) (0x00380A04 + ((_i) * 8)) +#define GLPRT_PRC1023L(_i) (0x00380A00 + ((_i) * 8)) +#define GLPRT_PRC127H(_i) (0x00380944 + ((_i) * 8)) +#define GLPRT_PRC127L(_i) (0x00380940 + ((_i) * 8)) +#define GLPRT_PRC1522H(_i) (0x00380A44 + ((_i) * 8)) +#define GLPRT_PRC1522L(_i) (0x00380A40 + ((_i) * 8)) +#define GLPRT_PRC255H(_i) (0x00380984 + ((_i) * 8)) +#define GLPRT_PRC255L(_i) (0x00380980 + ((_i) * 8)) +#define GLPRT_PRC511H(_i) (0x003809C4 + ((_i) * 8)) +#define GLPRT_PRC511L(_i) (0x003809C0 + ((_i) * 8)) +#define GLPRT_PRC64H(_i) (0x00380904 + ((_i) * 8)) +#define GLPRT_PRC64L(_i) (0x00380900 + ((_i) * 8)) +#define GLPRT_PRC9522H(_i) (0x00380A84 + ((_i) * 8)) +#define GLPRT_PRC9522L(_i) (0x00380A80 + ((_i) * 8)) +#define GLPRT_PTC1023H(_i) (0x00380C84 + ((_i) * 8)) +#define GLPRT_PTC1023L(_i) (0x00380C80 + ((_i) * 8)) +#define GLPRT_PTC127H(_i) (0x00380BC4 + ((_i) * 8)) +#define GLPRT_PTC127L(_i) (0x00380BC0 + ((_i) * 8)) +#define GLPRT_PTC1522H(_i) (0x00380CC4 + ((_i) * 8)) +#define GLPRT_PTC1522L(_i) (0x00380CC0 + ((_i) * 8)) +#define GLPRT_PTC255H(_i) (0x00380C04 + ((_i) * 8)) +#define GLPRT_PTC255L(_i) (0x00380C00 + ((_i) * 8)) +#define GLPRT_PTC511H(_i) (0x00380C44 + ((_i) * 8)) +#define GLPRT_PTC511L(_i) (0x00380C40 + ((_i) * 8)) +#define GLPRT_PTC64H(_i) (0x00380B84 + ((_i) * 8)) +#define GLPRT_PTC64L(_i) (0x00380B80 + ((_i) * 8)) +#define GLPRT_PTC9522H(_i) (0x00380D04 + ((_i) * 8)) +#define GLPRT_PTC9522L(_i) (0x00380D00 + ((_i) * 8)) +#define GLPRT_RFC(_i) (0x00380AC0 + ((_i) * 8)) +#define GLPRT_RJC(_i) (0x00380B00 + ((_i) * 8)) +#define GLPRT_RLEC(_i) (0x00380140 + ((_i) * 8)) +#define GLPRT_ROC(_i) (0x00380240 + ((_i) * 8)) +#define GLPRT_RUC(_i) (0x00380200 + ((_i) * 8)) +#define GLPRT_TDOLD(_i) (0x00381280 + ((_i) * 8)) +#define GLPRT_UPRCH(_i) (0x00381304 + ((_i) * 8)) +#define GLPRT_UPRCL(_i) (0x00381300 + ((_i) * 8)) +#define GLPRT_UPTCH(_i) (0x003811C4 + ((_i) * 8)) +#define GLPRT_UPTCL(_i) (0x003811C0 + ((_i) * 8)) +#define GLV_BPRCH(_i) (0x003B6004 + ((_i) * 8)) +#define GLV_BPRCL(_i) (0x003B6000 + ((_i) * 8)) +#define GLV_BPTCH(_i) (0x0030E004 + ((_i) * 8)) +#define GLV_BPTCL(_i) (0x0030E000 + ((_i) * 8)) +#define GLV_GORCH(_i) (0x003B0004 + ((_i) * 8)) +#define GLV_GORCL(_i) (0x003B0000 + ((_i) * 8)) +#define GLV_GOTCH(_i) (0x00300004 + ((_i) * 8)) +#define GLV_GOTCL(_i) (0x00300000 + ((_i) * 8)) +#define GLV_MPRCH(_i) (0x003B4004 + ((_i) * 8)) +#define GLV_MPRCL(_i) (0x003B4000 + ((_i) * 8)) +#define GLV_MPTCH(_i) (0x0030C004 + ((_i) * 8)) +#define GLV_MPTCL(_i) (0x0030C000 + ((_i) * 8)) +#define GLV_RDPC(_i) (0x00294C04 + ((_i) * 4)) +#define GLV_TEPC(_VSI) (0x00312000 + ((_VSI) * 4)) +#define GLV_UPRCH(_i) (0x003B2004 + ((_i) * 8)) +#define GLV_UPRCL(_i) (0x003B2000 + ((_i) * 8)) +#define GLV_UPTCH(_i) (0x0030A004 + ((_i) * 8)) +#define GLV_UPTCL(_i) (0x0030A000 + ((_i) * 8)) +#define VSIQF_HKEY_MAX_INDEX 12 #endif /* _ICE_HW_AUTOGEN_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h index d23a91665b46..94504023d86e 100644 --- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h +++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h @@ -188,23 +188,25 @@ struct ice_32b_rx_flex_desc_nic { * with a specific metadata (profile 7 reserved for HW) */ enum ice_rxdid { - ICE_RXDID_START = 0, - ICE_RXDID_LEGACY_0 = ICE_RXDID_START, - ICE_RXDID_LEGACY_1, - ICE_RXDID_FLX_START, - ICE_RXDID_FLEX_NIC = ICE_RXDID_FLX_START, - ICE_RXDID_FLX_LAST = 63, - ICE_RXDID_LAST = ICE_RXDID_FLX_LAST + ICE_RXDID_LEGACY_0 = 0, + ICE_RXDID_LEGACY_1 = 1, + ICE_RXDID_FLEX_NIC = 2, + ICE_RXDID_FLEX_NIC_2 = 6, + ICE_RXDID_HW = 7, + ICE_RXDID_LAST = 63, }; /* Receive Flex Descriptor Rx opcode values */ #define ICE_RX_OPC_MDID 0x01 /* Receive Descriptor MDID values */ -#define ICE_RX_MDID_FLOW_ID_LOWER 5 -#define ICE_RX_MDID_FLOW_ID_HIGH 6 -#define ICE_RX_MDID_HASH_LOW 56 -#define ICE_RX_MDID_HASH_HIGH 57 +enum ice_flex_rx_mdid { + ICE_RX_MDID_FLOW_ID_LOWER = 5, + ICE_RX_MDID_FLOW_ID_HIGH, + ICE_RX_MDID_SRC_VSI = 19, + ICE_RX_MDID_HASH_LOW = 56, + ICE_RX_MDID_HASH_HIGH, +}; /* Rx Flag64 packet flag bits */ enum ice_rx_flg64_bits { @@ -265,6 +267,7 @@ enum ice_rx_flex_desc_status_error_0_bits { struct ice_rlan_ctx { u16 head; u16 cpuid; /* bigger than needed, see above for reason */ +#define ICE_RLAN_BASE_S 7 u64 base; u16 qlen; #define ICE_RLAN_CTX_DBUF_S 7 diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 5299caf55a7f..d54e63785ff0 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -7,7 +7,7 @@ #include "ice.h" -#define DRV_VERSION "ice-0.7.0-k" +#define DRV_VERSION "0.7.1-k" #define DRV_SUMMARY "Intel(R) Ethernet Connection E800 Series Linux Driver" const char ice_drv_ver[] = DRV_VERSION; static const char ice_driver_string[] = DRV_SUMMARY; @@ -15,7 +15,7 @@ static const char ice_copyright[] = "Copyright (c) 2018, Intel Corporation."; MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION(DRV_SUMMARY); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); MODULE_VERSION(DRV_VERSION); static int debug = -1; @@ -32,10 +32,86 @@ static const struct net_device_ops ice_netdev_ops; static void ice_pf_dis_all_vsi(struct ice_pf *pf); static void ice_rebuild(struct ice_pf *pf); static int ice_vsi_release(struct ice_vsi *vsi); +static void ice_vsi_release_all(struct ice_pf *pf); static void ice_update_vsi_stats(struct ice_vsi *vsi); static void ice_update_pf_stats(struct ice_pf *pf); /** + * ice_get_tx_pending - returns number of Tx descriptors not processed + * @ring: the ring of descriptors + */ +static u32 ice_get_tx_pending(struct ice_ring *ring) +{ + u32 head, tail; + + head = ring->next_to_clean; + tail = readl(ring->tail); + + if (head != tail) + return (head < tail) ? + tail - head : (tail + ring->count - head); + return 0; +} + +/** + * ice_check_for_hang_subtask - check for and recover hung queues + * @pf: pointer to PF struct + */ +static void ice_check_for_hang_subtask(struct ice_pf *pf) +{ + struct ice_vsi *vsi = NULL; + unsigned int i; + u32 v, v_idx; + int packets; + + ice_for_each_vsi(pf, v) + if (pf->vsi[v] && pf->vsi[v]->type == ICE_VSI_PF) { + vsi = pf->vsi[v]; + break; + } + + if (!vsi || test_bit(__ICE_DOWN, vsi->state)) + return; + + if (!(vsi->netdev && netif_carrier_ok(vsi->netdev))) + return; + + for (i = 0; i < vsi->num_txq; i++) { + struct ice_ring *tx_ring = vsi->tx_rings[i]; + + if (tx_ring && tx_ring->desc) { + int itr = ICE_ITR_NONE; + + /* If packet counter has not changed the queue is + * likely stalled, so force an interrupt for this + * queue. + * + * prev_pkt would be negative if there was no + * pending work. + */ + packets = tx_ring->stats.pkts & INT_MAX; + if (tx_ring->tx_stats.prev_pkt == packets) { + /* Trigger sw interrupt to revive the queue */ + v_idx = tx_ring->q_vector->v_idx; + wr32(&vsi->back->hw, + GLINT_DYN_CTL(vsi->base_vector + v_idx), + (itr << GLINT_DYN_CTL_ITR_INDX_S) | + GLINT_DYN_CTL_SWINT_TRIG_M | + GLINT_DYN_CTL_INTENA_MSK_M); + continue; + } + + /* Memory barrier between read of packet count and call + * to ice_get_tx_pending() + */ + smp_rmb(); + tx_ring->tx_stats.prev_pkt = + ice_get_tx_pending(tx_ring) ? packets : -1; + } + } +} + +/** * ice_get_free_slot - get the next non-NULL location index in array * @array: array to search * @size: size of the array @@ -274,6 +350,63 @@ static bool ice_vsi_fltr_changed(struct ice_vsi *vsi) } /** + * ice_cfg_vlan_pruning - enable or disable VLAN pruning on the VSI + * @vsi: VSI to enable or disable VLAN pruning on + * @ena: set to true to enable VLAN pruning and false to disable it + * + * returns 0 if VSI is updated, negative otherwise + */ +static int ice_cfg_vlan_pruning(struct ice_vsi *vsi, bool ena) +{ + struct ice_vsi_ctx *ctxt; + struct device *dev; + int status; + + if (!vsi) + return -EINVAL; + + dev = &vsi->back->pdev->dev; + ctxt = devm_kzalloc(dev, sizeof(*ctxt), GFP_KERNEL); + if (!ctxt) + return -ENOMEM; + + ctxt->info = vsi->info; + + if (ena) { + ctxt->info.sec_flags |= + ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA << + ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S; + ctxt->info.sw_flags2 |= ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; + } else { + ctxt->info.sec_flags &= + ~(ICE_AQ_VSI_SEC_TX_VLAN_PRUNE_ENA << + ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S); + ctxt->info.sw_flags2 &= ~ICE_AQ_VSI_SW_FLAG_RX_VLAN_PRUNE_ENA; + } + + ctxt->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID | + ICE_AQ_VSI_PROP_SW_VALID); + ctxt->vsi_num = vsi->vsi_num; + status = ice_aq_update_vsi(&vsi->back->hw, ctxt, NULL); + if (status) { + netdev_err(vsi->netdev, "%sabling VLAN pruning on VSI %d failed, err = %d, aq_err = %d\n", + ena ? "Ena" : "Dis", vsi->vsi_num, status, + vsi->back->hw.adminq.sq_last_status); + goto err_out; + } + + vsi->info.sec_flags = ctxt->info.sec_flags; + vsi->info.sw_flags2 = ctxt->info.sw_flags2; + + devm_kfree(dev, ctxt); + return 0; + +err_out: + devm_kfree(dev, ctxt); + return -EIO; +} + +/** * ice_vsi_sync_fltr - Update the VSI filter list to the HW * @vsi: ptr to the VSI * @@ -456,23 +589,13 @@ static void ice_prepare_for_reset(struct ice_pf *pf) { struct ice_hw *hw = &pf->hw; - u32 v; - - ice_for_each_vsi(pf, v) - if (pf->vsi[v]) - ice_remove_vsi_fltr(hw, pf->vsi[v]->vsi_num); - - dev_dbg(&pf->pdev->dev, "Tearing down internal switch for reset\n"); /* disable the VSIs and their queues that are not already DOWN */ - /* pf_dis_all_vsi modifies netdev structures -rtnl_lock needed */ ice_pf_dis_all_vsi(pf); - ice_for_each_vsi(pf, v) - if (pf->vsi[v]) - pf->vsi[v]->vsi_num = 0; - ice_shutdown_all_ctrlq(hw); + + set_bit(__ICE_PREPARED_FOR_RESET, pf->state); } /** @@ -490,26 +613,32 @@ static void ice_do_reset(struct ice_pf *pf, enum ice_reset_req reset_type) WARN_ON(in_interrupt()); /* PFR is a bit of a special case because it doesn't result in an OICR - * interrupt. So for PFR, we prepare for reset, issue the reset and - * rebuild sequentially. + * interrupt. Set pending bit here which otherwise gets set in the + * OICR handler. */ - if (reset_type == ICE_RESET_PFR) { + if (reset_type == ICE_RESET_PFR) set_bit(__ICE_RESET_RECOVERY_PENDING, pf->state); - ice_prepare_for_reset(pf); - } + + ice_prepare_for_reset(pf); /* trigger the reset */ if (ice_reset(hw, reset_type)) { dev_err(dev, "reset %d failed\n", reset_type); set_bit(__ICE_RESET_FAILED, pf->state); clear_bit(__ICE_RESET_RECOVERY_PENDING, pf->state); + clear_bit(__ICE_PREPARED_FOR_RESET, pf->state); return; } + /* PFR is a bit of a special case because it doesn't result in an OICR + * interrupt. So for PFR, rebuild after the reset and clear the reset- + * associated state bits. + */ if (reset_type == ICE_RESET_PFR) { pf->pfr_count++; ice_rebuild(pf); clear_bit(__ICE_RESET_RECOVERY_PENDING, pf->state); + clear_bit(__ICE_PREPARED_FOR_RESET, pf->state); } } @@ -519,48 +648,57 @@ static void ice_do_reset(struct ice_pf *pf, enum ice_reset_req reset_type) */ static void ice_reset_subtask(struct ice_pf *pf) { - enum ice_reset_req reset_type; - - rtnl_lock(); + enum ice_reset_req reset_type = ICE_RESET_INVAL; /* When a CORER/GLOBR/EMPR is about to happen, the hardware triggers an - * OICR interrupt. The OICR handler (ice_misc_intr) determines what - * type of reset happened and sets __ICE_RESET_RECOVERY_PENDING bit in - * pf->state. So if reset/recovery is pending (as indicated by this bit) - * we do a rebuild and return. + * OICR interrupt. The OICR handler (ice_misc_intr) determines what type + * of reset is pending and sets bits in pf->state indicating the reset + * type and __ICE_RESET_RECOVERY_PENDING. So, if the latter bit is set + * prepare for pending reset if not already (for PF software-initiated + * global resets the software should already be prepared for it as + * indicated by __ICE_PREPARED_FOR_RESET; for global resets initiated + * by firmware or software on other PFs, that bit is not set so prepare + * for the reset now), poll for reset done, rebuild and return. */ if (ice_is_reset_recovery_pending(pf->state)) { clear_bit(__ICE_GLOBR_RECV, pf->state); clear_bit(__ICE_CORER_RECV, pf->state); - ice_prepare_for_reset(pf); + if (!test_bit(__ICE_PREPARED_FOR_RESET, pf->state)) + ice_prepare_for_reset(pf); /* make sure we are ready to rebuild */ - if (ice_check_reset(&pf->hw)) + if (ice_check_reset(&pf->hw)) { set_bit(__ICE_RESET_FAILED, pf->state); - else + } else { + /* done with reset. start rebuild */ + pf->hw.reset_ongoing = false; ice_rebuild(pf); - clear_bit(__ICE_RESET_RECOVERY_PENDING, pf->state); - goto unlock; + /* clear bit to resume normal operations, but + * ICE_NEEDS_RESTART bit is set incase rebuild failed + */ + clear_bit(__ICE_RESET_RECOVERY_PENDING, pf->state); + clear_bit(__ICE_PREPARED_FOR_RESET, pf->state); + } + + return; } /* No pending resets to finish processing. Check for new resets */ + if (test_and_clear_bit(__ICE_PFR_REQ, pf->state)) + reset_type = ICE_RESET_PFR; + if (test_and_clear_bit(__ICE_CORER_REQ, pf->state)) + reset_type = ICE_RESET_CORER; if (test_and_clear_bit(__ICE_GLOBR_REQ, pf->state)) reset_type = ICE_RESET_GLOBR; - else if (test_and_clear_bit(__ICE_CORER_REQ, pf->state)) - reset_type = ICE_RESET_CORER; - else if (test_and_clear_bit(__ICE_PFR_REQ, pf->state)) - reset_type = ICE_RESET_PFR; - else - goto unlock; + /* If no valid reset type requested just return */ + if (reset_type == ICE_RESET_INVAL) + return; - /* reset if not already down or resetting */ + /* reset if not already down or busy */ if (!test_bit(__ICE_DOWN, pf->state) && !test_bit(__ICE_CFG_BUSY, pf->state)) { ice_do_reset(pf, reset_type); } - -unlock: - rtnl_unlock(); } /** @@ -901,7 +1039,10 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type) case ice_aqc_opc_get_link_status: if (ice_handle_link_event(pf)) dev_err(&pf->pdev->dev, - "Could not handle link event"); + "Could not handle link event\n"); + break; + case ice_aqc_opc_fw_logging: + ice_output_fw_log(hw, &event.desc, event.msg_buf); break; default: dev_dbg(&pf->pdev->dev, @@ -917,13 +1058,27 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type) } /** + * ice_ctrlq_pending - check if there is a difference between ntc and ntu + * @hw: pointer to hardware info + * @cq: control queue information + * + * returns true if there are pending messages in a queue, false if there aren't + */ +static bool ice_ctrlq_pending(struct ice_hw *hw, struct ice_ctl_q_info *cq) +{ + u16 ntu; + + ntu = (u16)(rd32(hw, cq->rq.head) & cq->rq.head_mask); + return cq->rq.next_to_clean != ntu; +} + +/** * ice_clean_adminq_subtask - clean the AdminQ rings * @pf: board private structure */ static void ice_clean_adminq_subtask(struct ice_pf *pf) { struct ice_hw *hw = &pf->hw; - u32 val; if (!test_bit(__ICE_ADMINQ_EVENT_PENDING, pf->state)) return; @@ -933,9 +1088,13 @@ static void ice_clean_adminq_subtask(struct ice_pf *pf) clear_bit(__ICE_ADMINQ_EVENT_PENDING, pf->state); - /* re-enable Admin queue interrupt causes */ - val = rd32(hw, PFINT_FW_CTL); - wr32(hw, PFINT_FW_CTL, (val | PFINT_FW_CTL_CAUSE_ENA_M)); + /* There might be a situation where new messages arrive to a control + * queue between processing the last message and clearing the + * EVENT_PENDING bit. So before exiting, check queue head again (using + * ice_ctrlq_pending) and process new messages if any. + */ + if (ice_ctrlq_pending(hw, &hw->adminq)) + __ice_clean_ctrlq(pf, ICE_CTL_Q_ADMIN); ice_flush(hw); } @@ -948,8 +1107,9 @@ static void ice_clean_adminq_subtask(struct ice_pf *pf) */ static void ice_service_task_schedule(struct ice_pf *pf) { - if (!test_bit(__ICE_DOWN, pf->state) && - !test_and_set_bit(__ICE_SERVICE_SCHED, pf->state)) + if (!test_bit(__ICE_SERVICE_DIS, pf->state) && + !test_and_set_bit(__ICE_SERVICE_SCHED, pf->state) && + !test_bit(__ICE_NEEDS_RESTART, pf->state)) queue_work(ice_wq, &pf->serv_task); } @@ -967,6 +1127,22 @@ static void ice_service_task_complete(struct ice_pf *pf) } /** + * ice_service_task_stop - stop service task and cancel works + * @pf: board private structure + */ +static void ice_service_task_stop(struct ice_pf *pf) +{ + set_bit(__ICE_SERVICE_DIS, pf->state); + + if (pf->serv_tmr.function) + del_timer_sync(&pf->serv_tmr); + if (pf->serv_task.func) + cancel_work_sync(&pf->serv_task); + + clear_bit(__ICE_SERVICE_SCHED, pf->state); +} + +/** * ice_service_timer - timer callback to schedule service task * @t: pointer to timer_list */ @@ -979,6 +1155,114 @@ static void ice_service_timer(struct timer_list *t) } /** + * ice_handle_mdd_event - handle malicious driver detect event + * @pf: pointer to the PF structure + * + * Called from service task. OICR interrupt handler indicates MDD event + */ +static void ice_handle_mdd_event(struct ice_pf *pf) +{ + struct ice_hw *hw = &pf->hw; + bool mdd_detected = false; + u32 reg; + + if (!test_bit(__ICE_MDD_EVENT_PENDING, pf->state)) + return; + + /* find what triggered the MDD event */ + reg = rd32(hw, GL_MDET_TX_PQM); + if (reg & GL_MDET_TX_PQM_VALID_M) { + u8 pf_num = (reg & GL_MDET_TX_PQM_PF_NUM_M) >> + GL_MDET_TX_PQM_PF_NUM_S; + u16 vf_num = (reg & GL_MDET_TX_PQM_VF_NUM_M) >> + GL_MDET_TX_PQM_VF_NUM_S; + u8 event = (reg & GL_MDET_TX_PQM_MAL_TYPE_M) >> + GL_MDET_TX_PQM_MAL_TYPE_S; + u16 queue = ((reg & GL_MDET_TX_PQM_QNUM_M) >> + GL_MDET_TX_PQM_QNUM_S); + + if (netif_msg_tx_err(pf)) + dev_info(&pf->pdev->dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n", + event, queue, pf_num, vf_num); + wr32(hw, GL_MDET_TX_PQM, 0xffffffff); + mdd_detected = true; + } + + reg = rd32(hw, GL_MDET_TX_TCLAN); + if (reg & GL_MDET_TX_TCLAN_VALID_M) { + u8 pf_num = (reg & GL_MDET_TX_TCLAN_PF_NUM_M) >> + GL_MDET_TX_TCLAN_PF_NUM_S; + u16 vf_num = (reg & GL_MDET_TX_TCLAN_VF_NUM_M) >> + GL_MDET_TX_TCLAN_VF_NUM_S; + u8 event = (reg & GL_MDET_TX_TCLAN_MAL_TYPE_M) >> + GL_MDET_TX_TCLAN_MAL_TYPE_S; + u16 queue = ((reg & GL_MDET_TX_TCLAN_QNUM_M) >> + GL_MDET_TX_TCLAN_QNUM_S); + + if (netif_msg_rx_err(pf)) + dev_info(&pf->pdev->dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n", + event, queue, pf_num, vf_num); + wr32(hw, GL_MDET_TX_TCLAN, 0xffffffff); + mdd_detected = true; + } + + reg = rd32(hw, GL_MDET_RX); + if (reg & GL_MDET_RX_VALID_M) { + u8 pf_num = (reg & GL_MDET_RX_PF_NUM_M) >> + GL_MDET_RX_PF_NUM_S; + u16 vf_num = (reg & GL_MDET_RX_VF_NUM_M) >> + GL_MDET_RX_VF_NUM_S; + u8 event = (reg & GL_MDET_RX_MAL_TYPE_M) >> + GL_MDET_RX_MAL_TYPE_S; + u16 queue = ((reg & GL_MDET_RX_QNUM_M) >> + GL_MDET_RX_QNUM_S); + + if (netif_msg_rx_err(pf)) + dev_info(&pf->pdev->dev, "Malicious Driver Detection event %d on RX queue %d PF# %d VF# %d\n", + event, queue, pf_num, vf_num); + wr32(hw, GL_MDET_RX, 0xffffffff); + mdd_detected = true; + } + + if (mdd_detected) { + bool pf_mdd_detected = false; + + reg = rd32(hw, PF_MDET_TX_PQM); + if (reg & PF_MDET_TX_PQM_VALID_M) { + wr32(hw, PF_MDET_TX_PQM, 0xFFFF); + dev_info(&pf->pdev->dev, "TX driver issue detected, PF reset issued\n"); + pf_mdd_detected = true; + } + + reg = rd32(hw, PF_MDET_TX_TCLAN); + if (reg & PF_MDET_TX_TCLAN_VALID_M) { + wr32(hw, PF_MDET_TX_TCLAN, 0xFFFF); + dev_info(&pf->pdev->dev, "TX driver issue detected, PF reset issued\n"); + pf_mdd_detected = true; + } + + reg = rd32(hw, PF_MDET_RX); + if (reg & PF_MDET_RX_VALID_M) { + wr32(hw, PF_MDET_RX, 0xFFFF); + dev_info(&pf->pdev->dev, "RX driver issue detected, PF reset issued\n"); + pf_mdd_detected = true; + } + /* Queue belongs to the PF initiate a reset */ + if (pf_mdd_detected) { + set_bit(__ICE_NEEDS_RESTART, pf->state); + ice_service_task_schedule(pf); + } + } + + /* re-enable MDD interrupt cause */ + clear_bit(__ICE_MDD_EVENT_PENDING, pf->state); + reg = rd32(hw, PFINT_OICR_ENA); + reg |= PFINT_OICR_MAL_DETECT_M; + wr32(hw, PFINT_OICR_ENA, reg); + ice_flush(hw); +} + +/** * ice_service_task - manage and run subtasks * @work: pointer to work_struct contained by the PF struct */ @@ -992,14 +1276,17 @@ static void ice_service_task(struct work_struct *work) /* process reset requests first */ ice_reset_subtask(pf); - /* bail if a reset/recovery cycle is pending */ + /* bail if a reset/recovery cycle is pending or rebuild failed */ if (ice_is_reset_recovery_pending(pf->state) || - test_bit(__ICE_SUSPENDED, pf->state)) { + test_bit(__ICE_SUSPENDED, pf->state) || + test_bit(__ICE_NEEDS_RESTART, pf->state)) { ice_service_task_complete(pf); return; } + ice_check_for_hang_subtask(pf); ice_sync_fltr_subtask(pf); + ice_handle_mdd_event(pf); ice_watchdog_subtask(pf); ice_clean_adminq_subtask(pf); @@ -1011,6 +1298,7 @@ static void ice_service_task(struct work_struct *work) * schedule the service task now. */ if (time_after(jiffies, (start_time + pf->serv_tmr_period)) || + test_bit(__ICE_MDD_EVENT_PENDING, pf->state) || test_bit(__ICE_ADMINQ_EVENT_PENDING, pf->state)) mod_timer(&pf->serv_tmr, jiffies); } @@ -1139,7 +1427,7 @@ static void ice_vsi_delete(struct ice_vsi *vsi) memcpy(&ctxt.info, &vsi->info, sizeof(struct ice_aqc_vsi_props)); - status = ice_aq_free_vsi(&pf->hw, &ctxt, false, NULL); + status = ice_free_vsi(&pf->hw, vsi->idx, &ctxt, false, NULL); if (status) dev_err(&pf->pdev->dev, "Failed to delete VSI %i in FW\n", vsi->vsi_num); @@ -1295,11 +1583,8 @@ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) qcount = numq_tc; } - /* find higher power-of-2 of qcount */ - pow = ilog2(qcount); - - if (!is_power_of_2(qcount)) - pow++; + /* find the (rounded up) power-of-2 of qcount */ + pow = order_base_2(qcount); for (i = 0; i < ICE_MAX_TRAFFIC_CLASS; i++) { if (!(vsi->tc_cfg.ena_tc & BIT(i))) { @@ -1352,14 +1637,15 @@ static void ice_set_dflt_vsi_ctx(struct ice_vsi_ctx *ctxt) ctxt->info.sw_flags = ICE_AQ_VSI_SW_FLAG_SRC_PRUNE; /* Traffic from VSI can be sent to LAN */ ctxt->info.sw_flags2 = ICE_AQ_VSI_SW_FLAG_LAN_ENA; - /* Allow all packets untagged/tagged */ - ctxt->info.port_vlan_flags = ((ICE_AQ_VSI_PVLAN_MODE_ALL & - ICE_AQ_VSI_PVLAN_MODE_M) >> - ICE_AQ_VSI_PVLAN_MODE_S); - /* Show VLAN/UP from packets in Rx descriptors */ - ctxt->info.port_vlan_flags |= ((ICE_AQ_VSI_PVLAN_EMOD_STR_BOTH & - ICE_AQ_VSI_PVLAN_EMOD_M) >> - ICE_AQ_VSI_PVLAN_EMOD_S); + + /* By default bits 3 and 4 in vlan_flags are 0's which results in legacy + * behavior (show VLAN, DEI, and UP) in descriptor. Also, allow all + * packets untagged/tagged. + */ + ctxt->info.vlan_flags = ((ICE_AQ_VSI_VLAN_MODE_ALL & + ICE_AQ_VSI_VLAN_MODE_M) >> + ICE_AQ_VSI_VLAN_MODE_S); + /* Have 1:1 UP mapping for both ingress/egress tables */ table |= ICE_UP_TABLE_TRANSLATE(0, 0); table |= ICE_UP_TABLE_TRANSLATE(1, 1); @@ -1404,13 +1690,13 @@ static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi) } /** - * ice_vsi_add - Create a new VSI or fetch preallocated VSI + * ice_vsi_init - Create and initialize a VSI * @vsi: the VSI being configured * * This initializes a VSI context depending on the VSI type to be added and * passes it down to the add_vsi aq command to create a new VSI. */ -static int ice_vsi_add(struct ice_vsi *vsi) +static int ice_vsi_init(struct ice_vsi *vsi) { struct ice_vsi_ctx ctxt = { 0 }; struct ice_pf *pf = vsi->back; @@ -1437,13 +1723,17 @@ static int ice_vsi_add(struct ice_vsi *vsi) ctxt.info.sw_id = vsi->port_info->sw_id; ice_vsi_setup_q_map(vsi, &ctxt); - ret = ice_aq_add_vsi(hw, &ctxt, NULL); + ret = ice_add_vsi(hw, vsi->idx, &ctxt, NULL); if (ret) { - dev_err(&vsi->back->pdev->dev, - "Add VSI AQ call failed, err %d\n", ret); + dev_err(&pf->pdev->dev, + "Add VSI failed, err %d\n", ret); return -EIO; } + + /* keep context for update VSI operations */ vsi->info = ctxt.info; + + /* record VSI number returned */ vsi->vsi_num = ctxt.vsi_num; return ret; @@ -1688,15 +1978,12 @@ static void ice_ena_misc_vector(struct ice_pf *pf) wr32(hw, PFINT_OICR_ENA, 0); /* disable all */ rd32(hw, PFINT_OICR); /* read to clear */ - val = (PFINT_OICR_HLP_RDY_M | - PFINT_OICR_CPM_RDY_M | - PFINT_OICR_ECC_ERR_M | + val = (PFINT_OICR_ECC_ERR_M | PFINT_OICR_MAL_DETECT_M | PFINT_OICR_GRST_M | PFINT_OICR_PCI_EXCEPTION_M | - PFINT_OICR_GPIO_M | - PFINT_OICR_STORM_DETECT_M | - PFINT_OICR_HMC_ERR_M); + PFINT_OICR_HMC_ERR_M | + PFINT_OICR_PE_CRITERR_M); wr32(hw, PFINT_OICR_ENA, val); @@ -1722,8 +2009,14 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) oicr = rd32(hw, PFINT_OICR); ena_mask = rd32(hw, PFINT_OICR_ENA); + if (oicr & PFINT_OICR_MAL_DETECT_M) { + ena_mask &= ~PFINT_OICR_MAL_DETECT_M; + set_bit(__ICE_MDD_EVENT_PENDING, pf->state); + } + if (oicr & PFINT_OICR_GRST_M) { u32 reset; + /* we have a reset warning */ ena_mask &= ~PFINT_OICR_GRST_M; reset = (rd32(hw, GLGEN_RSTAT) & GLGEN_RSTAT_RESET_TYPE_M) >> @@ -1741,7 +2034,8 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) * We also make note of which reset happened so that peer * devices/drivers can be informed. */ - if (!test_bit(__ICE_RESET_RECOVERY_PENDING, pf->state)) { + if (!test_and_set_bit(__ICE_RESET_RECOVERY_PENDING, + pf->state)) { if (reset == ICE_RESET_CORER) set_bit(__ICE_CORER_RECV, pf->state); else if (reset == ICE_RESET_GLOBR) @@ -1749,7 +2043,20 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) else set_bit(__ICE_EMPR_RECV, pf->state); - set_bit(__ICE_RESET_RECOVERY_PENDING, pf->state); + /* There are couple of different bits at play here. + * hw->reset_ongoing indicates whether the hardware is + * in reset. This is set to true when a reset interrupt + * is received and set back to false after the driver + * has determined that the hardware is out of reset. + * + * __ICE_RESET_RECOVERY_PENDING in pf->state indicates + * that a post reset rebuild is required before the + * driver is operational again. This is set above. + * + * As this is the start of the reset/rebuild cycle, set + * both to indicate that. + */ + hw->reset_ongoing = true; } } @@ -2058,15 +2365,13 @@ static int ice_req_irq_msix_misc(struct ice_pf *pf) skip_req_irq: ice_ena_misc_vector(pf); - val = (pf->oicr_idx & PFINT_OICR_CTL_MSIX_INDX_M) | - (ICE_RX_ITR & PFINT_OICR_CTL_ITR_INDX_M) | - PFINT_OICR_CTL_CAUSE_ENA_M; + val = ((pf->oicr_idx & PFINT_OICR_CTL_MSIX_INDX_M) | + PFINT_OICR_CTL_CAUSE_ENA_M); wr32(hw, PFINT_OICR_CTL, val); /* This enables Admin queue Interrupt causes */ - val = (pf->oicr_idx & PFINT_FW_CTL_MSIX_INDX_M) | - (ICE_RX_ITR & PFINT_FW_CTL_ITR_INDX_M) | - PFINT_FW_CTL_CAUSE_ENA_M; + val = ((pf->oicr_idx & PFINT_FW_CTL_MSIX_INDX_M) | + PFINT_FW_CTL_CAUSE_ENA_M); wr32(hw, PFINT_FW_CTL, val); itr_gran = hw->itr_gran_200; @@ -2624,14 +2929,12 @@ ice_vsi_cfg_rss_exit: } /** - * ice_vsi_reinit_setup - return resource and reallocate resource for a VSI - * @vsi: pointer to the ice_vsi - * - * This reallocates the VSIs queue resources + * ice_vsi_rebuild - Rebuild VSI after reset + * @vsi: vsi to be rebuild * * Returns 0 on success and negative value on failure */ -static int ice_vsi_reinit_setup(struct ice_vsi *vsi) +static int ice_vsi_rebuild(struct ice_vsi *vsi) { u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; int ret, i; @@ -2647,7 +2950,7 @@ static int ice_vsi_reinit_setup(struct ice_vsi *vsi) ice_vsi_set_num_qs(vsi); /* Initialize VSI struct elements and create VSI in FW */ - ret = ice_vsi_add(vsi); + ret = ice_vsi_init(vsi); if (ret < 0) goto err_vsi; @@ -2657,19 +2960,7 @@ static int ice_vsi_reinit_setup(struct ice_vsi *vsi) switch (vsi->type) { case ICE_VSI_PF: - if (!vsi->netdev) { - ret = ice_cfg_netdev(vsi); - if (ret) - goto err_rings; - - ret = register_netdev(vsi->netdev); - if (ret) - goto err_rings; - - netif_carrier_off(vsi->netdev); - netif_tx_stop_all_queues(vsi->netdev); - } - + /* fall through */ ret = ice_vsi_alloc_q_vectors(vsi); if (ret) goto err_rings; @@ -2721,21 +3012,23 @@ err_vsi: /** * ice_vsi_setup - Set up a VSI by a given type * @pf: board private structure - * @type: VSI type * @pi: pointer to the port_info instance + * @type: VSI type + * @vf_id: defines VF id to which this VSI connects. This field is meant to be + * used only for ICE_VSI_VF VSI type. For other VSI types, should + * fill-in ICE_INVAL_VFID as input. * * This allocates the sw VSI structure and its queue resources. * - * Returns pointer to the successfully allocated and configure VSI sw struct on - * success, otherwise returns NULL on failure. + * Returns pointer to the successfully allocated and configured VSI sw struct on + * success, NULL on failure. */ static struct ice_vsi * -ice_vsi_setup(struct ice_pf *pf, enum ice_vsi_type type, - struct ice_port_info *pi) +ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, + enum ice_vsi_type type, u16 __always_unused vf_id) { u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; struct device *dev = &pf->pdev->dev; - struct ice_vsi_ctx ctxt = { 0 }; struct ice_vsi *vsi; int ret, i; @@ -2758,12 +3051,10 @@ ice_vsi_setup(struct ice_pf *pf, enum ice_vsi_type type, ice_vsi_set_rss_params(vsi); /* create the VSI */ - ret = ice_vsi_add(vsi); + ret = ice_vsi_init(vsi); if (ret) goto err_vsi; - ctxt.vsi_num = vsi->vsi_num; - switch (vsi->type) { case ICE_VSI_PF: ret = ice_cfg_netdev(vsi); @@ -2832,10 +3123,7 @@ err_register_netdev: vsi->netdev = NULL; } err_cfg_netdev: - ret = ice_aq_free_vsi(&pf->hw, &ctxt, false, NULL); - if (ret) - dev_err(&vsi->back->pdev->dev, - "Free VSI AQ call failed, err %d\n", ret); + ice_vsi_delete(vsi); err_vsi: ice_vsi_put_qs(vsi); err_get_qs: @@ -2847,6 +3135,20 @@ err_get_qs: } /** + * ice_pf_vsi_setup - Set up a PF VSI + * @pf: board private structure + * @pi: pointer to the port_info instance + * + * Returns pointer to the successfully allocated VSI sw struct on success, + * otherwise returns NULL on failure. + */ +static struct ice_vsi * +ice_pf_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi) +{ + return ice_vsi_setup(pf, pi, ICE_VSI_PF, ICE_INVAL_VFID); +} + +/** * ice_vsi_add_vlan - Add vsi membership for given vlan * @vsi: the vsi being configured * @vid: vlan id to be added @@ -2897,7 +3199,7 @@ static int ice_vlan_rx_add_vid(struct net_device *netdev, { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; - int ret = 0; + int ret; if (vid >= VLAN_N_VID) { netdev_err(netdev, "VLAN id requested %d is out of range %d\n", @@ -2908,6 +3210,13 @@ static int ice_vlan_rx_add_vid(struct net_device *netdev, if (vsi->info.pvid) return -EINVAL; + /* Enable VLAN pruning when VLAN 0 is added */ + if (unlikely(!vid)) { + ret = ice_cfg_vlan_pruning(vsi, true); + if (ret) + return ret; + } + /* Add all VLAN ids including 0 to the switch filter. VLAN id 0 is * needed to continue allowing all untagged packets since VLAN prune * list is applied to all packets by the switch @@ -2924,16 +3233,19 @@ static int ice_vlan_rx_add_vid(struct net_device *netdev, * ice_vsi_kill_vlan - Remove VSI membership for a given VLAN * @vsi: the VSI being configured * @vid: VLAN id to be removed + * + * Returns 0 on success and negative on failure */ -static void ice_vsi_kill_vlan(struct ice_vsi *vsi, u16 vid) +static int ice_vsi_kill_vlan(struct ice_vsi *vsi, u16 vid) { struct ice_fltr_list_entry *list; struct ice_pf *pf = vsi->back; LIST_HEAD(tmp_add_list); + int status = 0; list = devm_kzalloc(&pf->pdev->dev, sizeof(*list), GFP_KERNEL); if (!list) - return; + return -ENOMEM; list->fltr_info.lkup_type = ICE_SW_LKUP_VLAN; list->fltr_info.fwd_id.vsi_id = vsi->vsi_num; @@ -2945,11 +3257,14 @@ static void ice_vsi_kill_vlan(struct ice_vsi *vsi, u16 vid) INIT_LIST_HEAD(&list->list_entry); list_add(&list->list_entry, &tmp_add_list); - if (ice_remove_vlan(&pf->hw, &tmp_add_list)) + if (ice_remove_vlan(&pf->hw, &tmp_add_list)) { dev_err(&pf->pdev->dev, "Error removing VLAN %d on vsi %i\n", vid, vsi->vsi_num); + status = -EIO; + } ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list); + return status; } /** @@ -2965,19 +3280,25 @@ static int ice_vlan_rx_kill_vid(struct net_device *netdev, { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; + int status; if (vsi->info.pvid) return -EINVAL; - /* return code is ignored as there is nothing a user - * can do about failure to remove and a log message was - * already printed from the other function + /* Make sure ice_vsi_kill_vlan is successful before updating VLAN + * information */ - ice_vsi_kill_vlan(vsi, vid); + status = ice_vsi_kill_vlan(vsi, vid); + if (status) + return status; clear_bit(vid, vsi->active_vlans); - return 0; + /* Disable VLAN pruning when VLAN 0 is removed */ + if (unlikely(!vid)) + status = ice_cfg_vlan_pruning(vsi, false); + + return status; } /** @@ -2993,50 +3314,48 @@ static int ice_setup_pf_sw(struct ice_pf *pf) struct ice_vsi *vsi; int status = 0; - if (!ice_is_reset_recovery_pending(pf->state)) { - vsi = ice_vsi_setup(pf, ICE_VSI_PF, pf->hw.port_info); - if (!vsi) { - status = -ENOMEM; - goto error_exit; - } - } else { - vsi = pf->vsi[0]; - status = ice_vsi_reinit_setup(vsi); - if (status < 0) - return -EIO; + if (ice_is_reset_recovery_pending(pf->state)) + return -EBUSY; + + vsi = ice_pf_vsi_setup(pf, pf->hw.port_info); + if (!vsi) { + status = -ENOMEM; + goto unroll_vsi_setup; } - /* tmp_add_list contains a list of MAC addresses for which MAC - * filters need to be programmed. Add the VSI's unicast MAC to - * this list + /* To add a MAC filter, first add the MAC to a list and then + * pass the list to ice_add_mac. */ + + /* Add a unicast MAC filter so the VSI can get its packets */ status = ice_add_mac_to_list(vsi, &tmp_add_list, vsi->port_info->mac.perm_addr); if (status) - goto error_exit; + goto unroll_vsi_setup; /* VSI needs to receive broadcast traffic, so add the broadcast - * MAC address to the list. + * MAC address to the list as well. */ eth_broadcast_addr(broadcast); status = ice_add_mac_to_list(vsi, &tmp_add_list, broadcast); if (status) - goto error_exit; + goto free_mac_list; /* program MAC filters for entries in tmp_add_list */ status = ice_add_mac(&pf->hw, &tmp_add_list); if (status) { dev_err(&pf->pdev->dev, "Could not add MAC filters\n"); status = -ENOMEM; - goto error_exit; + goto free_mac_list; } ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list); return status; -error_exit: +free_mac_list: ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list); +unroll_vsi_setup: if (vsi) { ice_vsi_free_q_vectors(vsi); if (vsi->netdev && vsi->netdev->reg_state == NETREG_REGISTERED) @@ -3086,10 +3405,7 @@ static void ice_determine_q_usage(struct ice_pf *pf) */ static void ice_deinit_pf(struct ice_pf *pf) { - if (pf->serv_tmr.function) - del_timer_sync(&pf->serv_tmr); - if (pf->serv_task.func) - cancel_work_sync(&pf->serv_task); + ice_service_task_stop(pf); mutex_destroy(&pf->sw_mutex); mutex_destroy(&pf->avail_q_mutex); } @@ -3246,8 +3562,10 @@ static void ice_clear_interrupt_scheme(struct ice_pf *pf) if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) ice_dis_msix(pf); - devm_kfree(&pf->pdev->dev, pf->irq_tracker); - pf->irq_tracker = NULL; + if (pf->irq_tracker) { + devm_kfree(&pf->pdev->dev, pf->irq_tracker); + pf->irq_tracker = NULL; + } } /** @@ -3271,7 +3589,7 @@ static int ice_probe(struct pci_dev *pdev, err = pcim_iomap_regions(pdev, BIT(ICE_BAR0), pci_name(pdev)); if (err) { - dev_err(&pdev->dev, "I/O map error %d\n", err); + dev_err(&pdev->dev, "BAR0 I/O map error %d\n", err); return err; } @@ -3294,6 +3612,8 @@ static int ice_probe(struct pci_dev *pdev, pf->pdev = pdev; pci_set_drvdata(pdev, pf); set_bit(__ICE_DOWN, pf->state); + /* Disable service task until DOWN bit is cleared */ + set_bit(__ICE_SERVICE_DIS, pf->state); hw = &pf->hw; hw->hw_addr = pcim_iomap_table(pdev)[ICE_BAR0]; @@ -3351,6 +3671,9 @@ static int ice_probe(struct pci_dev *pdev, goto err_init_interrupt_unroll; } + /* Driver is mostly up */ + clear_bit(__ICE_DOWN, pf->state); + /* In case of MSIX we are going to setup the misc vector right here * to handle admin queue events etc. In case of legacy and MSI * the misc functionality and queue processing is combined in @@ -3373,7 +3696,11 @@ static int ice_probe(struct pci_dev *pdev, goto err_msix_misc_unroll; } - pf->first_sw->bridge_mode = BRIDGE_MODE_VEB; + if (hw->evb_veb) + pf->first_sw->bridge_mode = BRIDGE_MODE_VEB; + else + pf->first_sw->bridge_mode = BRIDGE_MODE_VEPA; + pf->first_sw->pf = pf; /* record the sw_id available for later use */ @@ -3386,8 +3713,7 @@ static int ice_probe(struct pci_dev *pdev, goto err_alloc_sw_unroll; } - /* Driver is mostly up */ - clear_bit(__ICE_DOWN, pf->state); + clear_bit(__ICE_SERVICE_DIS, pf->state); /* since everything is good, start the service timer */ mod_timer(&pf->serv_tmr, round_jiffies(jiffies + pf->serv_tmr_period)); @@ -3401,6 +3727,7 @@ static int ice_probe(struct pci_dev *pdev, return 0; err_alloc_sw_unroll: + set_bit(__ICE_SERVICE_DIS, pf->state); set_bit(__ICE_DOWN, pf->state); devm_kfree(&pf->pdev->dev, pf->first_sw); err_msix_misc_unroll: @@ -3423,24 +3750,14 @@ err_exit_unroll: static void ice_remove(struct pci_dev *pdev) { struct ice_pf *pf = pci_get_drvdata(pdev); - int i = 0; - int err; if (!pf) return; set_bit(__ICE_DOWN, pf->state); + ice_service_task_stop(pf); - for (i = 0; i < pf->num_alloc_vsi; i++) { - if (!pf->vsi[i]) - continue; - - err = ice_vsi_release(pf->vsi[i]); - if (err) - dev_dbg(&pf->pdev->dev, "Failed to release VSI index %d (err %d)\n", - i, err); - } - + ice_vsi_release_all(pf); ice_free_irq_msix_misc(pf); ice_clear_interrupt_scheme(pf); ice_deinit_pf(pf); @@ -3487,7 +3804,7 @@ static int __init ice_module_init(void) pr_info("%s - version %s\n", ice_driver_string, ice_drv_ver); pr_info("%s\n", ice_copyright); - ice_wq = alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM, KBUILD_MODNAME); + ice_wq = alloc_workqueue("%s", WQ_MEM_RECLAIM, 0, KBUILD_MODNAME); if (!ice_wq) { pr_err("Failed to create workqueue\n"); return -ENOMEM; @@ -3720,10 +4037,10 @@ static int ice_vsi_manage_vlan_insertion(struct ice_vsi *vsi) enum ice_status status; /* Here we are configuring the VSI to let the driver add VLAN tags by - * setting port_vlan_flags to ICE_AQ_VSI_PVLAN_MODE_ALL. The actual VLAN - * tag insertion happens in the Tx hot path, in ice_tx_map. + * setting vlan_flags to ICE_AQ_VSI_VLAN_MODE_ALL. The actual VLAN tag + * insertion happens in the Tx hot path, in ice_tx_map. */ - ctxt.info.port_vlan_flags = ICE_AQ_VSI_PVLAN_MODE_ALL; + ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_MODE_ALL; ctxt.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID); ctxt.vsi_num = vsi->vsi_num; @@ -3735,7 +4052,7 @@ static int ice_vsi_manage_vlan_insertion(struct ice_vsi *vsi) return -EIO; } - vsi->info.port_vlan_flags = ctxt.info.port_vlan_flags; + vsi->info.vlan_flags = ctxt.info.vlan_flags; return 0; } @@ -3757,12 +4074,15 @@ static int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena) */ if (ena) { /* Strip VLAN tag from Rx packet and put it in the desc */ - ctxt.info.port_vlan_flags = ICE_AQ_VSI_PVLAN_EMOD_STR_BOTH; + ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_EMOD_STR_BOTH; } else { /* Disable stripping. Leave tag in packet */ - ctxt.info.port_vlan_flags = ICE_AQ_VSI_PVLAN_EMOD_NOTHING; + ctxt.info.vlan_flags = ICE_AQ_VSI_VLAN_EMOD_NOTHING; } + /* Allow all packets untagged/tagged */ + ctxt.info.vlan_flags |= ICE_AQ_VSI_VLAN_MODE_ALL; + ctxt.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_VLAN_VALID); ctxt.vsi_num = vsi->vsi_num; @@ -3773,7 +4093,7 @@ static int ice_vsi_manage_vlan_stripping(struct ice_vsi *vsi, bool ena) return -EIO; } - vsi->info.port_vlan_flags = ctxt.info.port_vlan_flags; + vsi->info.vlan_flags = ctxt.info.vlan_flags; return 0; } @@ -3986,7 +4306,7 @@ static int ice_setup_rx_ctx(struct ice_ring *ring) /* clear the context structure first */ memset(&rlan_ctx, 0, sizeof(rlan_ctx)); - rlan_ctx.base = ring->dma >> 7; + rlan_ctx.base = ring->dma >> ICE_RLAN_BASE_S; rlan_ctx.qlen = ring->count; @@ -4098,11 +4418,12 @@ static int ice_vsi_cfg(struct ice_vsi *vsi) { int err; - ice_set_rx_mode(vsi->netdev); - - err = ice_restore_vlan(vsi); - if (err) - return err; + if (vsi->netdev) { + ice_set_rx_mode(vsi->netdev); + err = ice_restore_vlan(vsi); + if (err) + return err; + } err = ice_vsi_cfg_txqs(vsi); if (!err) @@ -4168,7 +4489,14 @@ static int ice_vsi_stop_tx_rings(struct ice_vsi *vsi) } status = ice_dis_vsi_txq(vsi->port_info, vsi->num_txq, q_ids, q_teids, NULL); - if (status) { + /* if the disable queue command was exercised during an active reset + * flow, ICE_ERR_RESET_ONGOING is returned. This is not an error as + * the reset operation disables queues at the hardware level anyway. + */ + if (status == ICE_ERR_RESET_ONGOING) { + dev_dbg(&pf->pdev->dev, + "Reset in progress. LAN Tx queues already disabled\n"); + } else if (status) { dev_err(&pf->pdev->dev, "Failed to disable LAN Tx queues, error: %d\n", status); @@ -4868,7 +5196,7 @@ int ice_down(struct ice_vsi *vsi) */ static int ice_vsi_setup_tx_rings(struct ice_vsi *vsi) { - int i, err; + int i, err = 0; if (!vsi->num_txq) { dev_err(&vsi->back->pdev->dev, "VSI %d has 0 Tx queues\n", @@ -4893,7 +5221,7 @@ static int ice_vsi_setup_tx_rings(struct ice_vsi *vsi) */ static int ice_vsi_setup_rx_rings(struct ice_vsi *vsi) { - int i, err; + int i, err = 0; if (!vsi->num_rxq) { dev_err(&vsi->back->pdev->dev, "VSI %d has 0 Rx queues\n", @@ -5063,8 +5391,14 @@ static int ice_vsi_release(struct ice_vsi *vsi) if (!vsi->back) return -ENODEV; pf = vsi->back; - - if (vsi->netdev) { + /* do not unregister and free netdevs while driver is in the reset + * recovery pending state. Since reset/rebuild happens through PF + * service task workqueue, its not a good idea to unregister netdev + * that is associated to the PF that is running the work queue items + * currently. This is done to avoid check_flush_dependency() warning + * on this wq + */ + if (vsi->netdev && !ice_is_reset_recovery_pending(pf->state)) { unregister_netdev(vsi->netdev); free_netdev(vsi->netdev); vsi->netdev = NULL; @@ -5090,12 +5424,40 @@ static int ice_vsi_release(struct ice_vsi *vsi) pf->q_left_tx += vsi->alloc_txq; pf->q_left_rx += vsi->alloc_rxq; - ice_vsi_clear(vsi); + /* retain SW VSI data structure since it is needed to unregister and + * free VSI netdev when PF is not in reset recovery pending state,\ + * for ex: during rmmod. + */ + if (!ice_is_reset_recovery_pending(pf->state)) + ice_vsi_clear(vsi); return 0; } /** + * ice_vsi_release_all - Delete all VSIs + * @pf: PF from which all VSIs are being removed + */ +static void ice_vsi_release_all(struct ice_pf *pf) +{ + int err, i; + + if (!pf->vsi) + return; + + for (i = 0; i < pf->num_alloc_vsi; i++) { + if (!pf->vsi[i]) + continue; + + err = ice_vsi_release(pf->vsi[i]); + if (err) + dev_dbg(&pf->pdev->dev, + "Failed to release pf->vsi[%d], err %d, vsi_num = %d\n", + i, err, pf->vsi[i]->vsi_num); + } +} + +/** * ice_dis_vsi - pause a VSI * @vsi: the VSI being paused */ @@ -5107,27 +5469,31 @@ static void ice_dis_vsi(struct ice_vsi *vsi) set_bit(__ICE_NEEDS_RESTART, vsi->state); if (vsi->netdev && netif_running(vsi->netdev) && - vsi->type == ICE_VSI_PF) + vsi->type == ICE_VSI_PF) { + rtnl_lock(); vsi->netdev->netdev_ops->ndo_stop(vsi->netdev); - - ice_vsi_close(vsi); + rtnl_unlock(); + } else { + ice_vsi_close(vsi); + } } /** * ice_ena_vsi - resume a VSI * @vsi: the VSI being resume */ -static void ice_ena_vsi(struct ice_vsi *vsi) +static int ice_ena_vsi(struct ice_vsi *vsi) { - if (!test_and_clear_bit(__ICE_NEEDS_RESTART, vsi->state)) - return; + int err = 0; + + if (test_and_clear_bit(__ICE_NEEDS_RESTART, vsi->state)) + if (vsi->netdev && netif_running(vsi->netdev)) { + rtnl_lock(); + err = vsi->netdev->netdev_ops->ndo_open(vsi->netdev); + rtnl_unlock(); + } - if (vsi->netdev && netif_running(vsi->netdev)) - vsi->netdev->netdev_ops->ndo_open(vsi->netdev); - else if (ice_vsi_open(vsi)) - /* this clears the DOWN bit */ - dev_dbg(&vsi->back->pdev->dev, "Failed open VSI 0x%04X on switch 0x%04X\n", - vsi->vsi_num, vsi->vsw->sw_id); + return err; } /** @@ -5147,13 +5513,47 @@ static void ice_pf_dis_all_vsi(struct ice_pf *pf) * ice_pf_ena_all_vsi - Resume all VSIs on a PF * @pf: the PF */ -static void ice_pf_ena_all_vsi(struct ice_pf *pf) +static int ice_pf_ena_all_vsi(struct ice_pf *pf) { int v; ice_for_each_vsi(pf, v) if (pf->vsi[v]) - ice_ena_vsi(pf->vsi[v]); + if (ice_ena_vsi(pf->vsi[v])) + return -EIO; + + return 0; +} + +/** + * ice_vsi_rebuild_all - rebuild all VSIs in pf + * @pf: the PF + */ +static int ice_vsi_rebuild_all(struct ice_pf *pf) +{ + int i; + + /* loop through pf->vsi array and reinit the VSI if found */ + for (i = 0; i < pf->num_alloc_vsi; i++) { + int err; + + if (!pf->vsi[i]) + continue; + + err = ice_vsi_rebuild(pf->vsi[i]); + if (err) { + dev_err(&pf->pdev->dev, + "VSI at index %d rebuild failed\n", + pf->vsi[i]->idx); + return err; + } + + dev_info(&pf->pdev->dev, + "VSI at index %d rebuilt. vsi_num = 0x%x\n", + pf->vsi[i]->idx, pf->vsi[i]->vsi_num); + } + + return 0; } /** @@ -5175,13 +5575,13 @@ static void ice_rebuild(struct ice_pf *pf) ret = ice_init_all_ctrlq(hw); if (ret) { dev_err(dev, "control queues init failed %d\n", ret); - goto fail_reset; + goto err_init_ctrlq; } ret = ice_clear_pf_cfg(hw); if (ret) { dev_err(dev, "clear PF configuration failed %d\n", ret); - goto fail_reset; + goto err_init_ctrlq; } ice_clear_pxe_mode(hw); @@ -5189,14 +5589,24 @@ static void ice_rebuild(struct ice_pf *pf) ret = ice_get_caps(hw); if (ret) { dev_err(dev, "ice_get_caps failed %d\n", ret); - goto fail_reset; + goto err_init_ctrlq; } - /* basic nic switch setup */ - err = ice_setup_pf_sw(pf); + err = ice_sched_init_port(hw->port_info); + if (err) + goto err_sched_init_port; + + err = ice_vsi_rebuild_all(pf); if (err) { - dev_err(dev, "ice_setup_pf_sw failed\n"); - goto fail_reset; + dev_err(dev, "ice_vsi_rebuild_all failed\n"); + goto err_vsi_rebuild; + } + + ret = ice_replay_all_fltr(&pf->hw); + if (ret) { + dev_err(&pf->pdev->dev, + "error replaying switch filter rules\n"); + goto err_vsi_rebuild; } /* start misc vector */ @@ -5204,20 +5614,35 @@ static void ice_rebuild(struct ice_pf *pf) err = ice_req_irq_msix_misc(pf); if (err) { dev_err(dev, "misc vector setup failed: %d\n", err); - goto fail_reset; + goto err_vsi_rebuild; } } /* restart the VSIs that were rebuilt and running before the reset */ - ice_pf_ena_all_vsi(pf); + err = ice_pf_ena_all_vsi(pf); + if (err) { + dev_err(&pf->pdev->dev, "error enabling VSIs\n"); + /* no need to disable VSIs in tear down path in ice_rebuild() + * since its already taken care in ice_vsi_open() + */ + goto err_vsi_rebuild; + } + /* if we get here, reset flow is successful */ + clear_bit(__ICE_RESET_FAILED, pf->state); return; -fail_reset: +err_vsi_rebuild: + ice_vsi_release_all(pf); +err_sched_init_port: + ice_sched_cleanup_all(hw); +err_init_ctrlq: ice_shutdown_all_ctrlq(hw); set_bit(__ICE_RESET_FAILED, pf->state); clear_recovery: - set_bit(__ICE_RESET_RECOVERY_PENDING, pf->state); + /* set this bit in PF state to control service task scheduling */ + set_bit(__ICE_NEEDS_RESTART, pf->state); + dev_err(dev, "Rebuild failed, unload and reload driver\n"); } /** @@ -5235,7 +5660,7 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu) u8 count = 0; if (new_mtu == netdev->mtu) { - netdev_warn(netdev, "mtu is already %d\n", netdev->mtu); + netdev_warn(netdev, "mtu is already %u\n", netdev->mtu); return 0; } @@ -5373,6 +5798,232 @@ int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size) } /** + * ice_bridge_getlink - Get the hardware bridge mode + * @skb: skb buff + * @pid: process id + * @seq: RTNL message seq + * @dev: the netdev being configured + * @filter_mask: filter mask passed in + * @nlflags: netlink flags passed in + * + * Return the bridge mode (VEB/VEPA) + */ +static int +ice_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, + struct net_device *dev, u32 filter_mask, int nlflags) +{ + struct ice_netdev_priv *np = netdev_priv(dev); + struct ice_vsi *vsi = np->vsi; + struct ice_pf *pf = vsi->back; + u16 bmode; + + bmode = pf->first_sw->bridge_mode; + + return ndo_dflt_bridge_getlink(skb, pid, seq, dev, bmode, 0, 0, nlflags, + filter_mask, NULL); +} + +/** + * ice_vsi_update_bridge_mode - Update VSI for switching bridge mode (VEB/VEPA) + * @vsi: Pointer to VSI structure + * @bmode: Hardware bridge mode (VEB/VEPA) + * + * Returns 0 on success, negative on failure + */ +static int ice_vsi_update_bridge_mode(struct ice_vsi *vsi, u16 bmode) +{ + struct device *dev = &vsi->back->pdev->dev; + struct ice_aqc_vsi_props *vsi_props; + struct ice_hw *hw = &vsi->back->hw; + struct ice_vsi_ctx ctxt = { 0 }; + enum ice_status status; + + vsi_props = &vsi->info; + ctxt.info = vsi->info; + + if (bmode == BRIDGE_MODE_VEB) + /* change from VEPA to VEB mode */ + ctxt.info.sw_flags |= ICE_AQ_VSI_SW_FLAG_ALLOW_LB; + else + /* change from VEB to VEPA mode */ + ctxt.info.sw_flags &= ~ICE_AQ_VSI_SW_FLAG_ALLOW_LB; + ctxt.vsi_num = vsi->vsi_num; + ctxt.info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_SW_VALID); + status = ice_aq_update_vsi(hw, &ctxt, NULL); + if (status) { + dev_err(dev, "update VSI for bridge mode failed, bmode = %d err %d aq_err %d\n", + bmode, status, hw->adminq.sq_last_status); + return -EIO; + } + /* Update sw flags for book keeping */ + vsi_props->sw_flags = ctxt.info.sw_flags; + + return 0; +} + +/** + * ice_bridge_setlink - Set the hardware bridge mode + * @dev: the netdev being configured + * @nlh: RTNL message + * @flags: bridge setlink flags + * + * Sets the bridge mode (VEB/VEPA) of the switch to which the netdev (VSI) is + * hooked up to. Iterates through the PF VSI list and sets the loopback mode (if + * not already set for all VSIs connected to this switch. And also update the + * unicast switch filter rules for the corresponding switch of the netdev. + */ +static int +ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, + u16 __always_unused flags) +{ + struct ice_netdev_priv *np = netdev_priv(dev); + struct ice_pf *pf = np->vsi->back; + struct nlattr *attr, *br_spec; + struct ice_hw *hw = &pf->hw; + enum ice_status status; + struct ice_sw *pf_sw; + int rem, v, err = 0; + + pf_sw = pf->first_sw; + /* find the attribute in the netlink message */ + br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); + + nla_for_each_nested(attr, br_spec, rem) { + __u16 mode; + + if (nla_type(attr) != IFLA_BRIDGE_MODE) + continue; + mode = nla_get_u16(attr); + if (mode != BRIDGE_MODE_VEPA && mode != BRIDGE_MODE_VEB) + return -EINVAL; + /* Continue if bridge mode is not being flipped */ + if (mode == pf_sw->bridge_mode) + continue; + /* Iterates through the PF VSI list and update the loopback + * mode of the VSI + */ + ice_for_each_vsi(pf, v) { + if (!pf->vsi[v]) + continue; + err = ice_vsi_update_bridge_mode(pf->vsi[v], mode); + if (err) + return err; + } + + hw->evb_veb = (mode == BRIDGE_MODE_VEB); + /* Update the unicast switch filter rules for the corresponding + * switch of the netdev + */ + status = ice_update_sw_rule_bridge_mode(hw); + if (status) { + netdev_err(dev, "update SW_RULE for bridge mode failed, = %d err %d aq_err %d\n", + mode, status, hw->adminq.sq_last_status); + /* revert hw->evb_veb */ + hw->evb_veb = (pf_sw->bridge_mode == BRIDGE_MODE_VEB); + return -EIO; + } + + pf_sw->bridge_mode = mode; + } + + return 0; +} + +/** + * ice_tx_timeout - Respond to a Tx Hang + * @netdev: network interface device structure + */ +static void ice_tx_timeout(struct net_device *netdev) +{ + struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_ring *tx_ring = NULL; + struct ice_vsi *vsi = np->vsi; + struct ice_pf *pf = vsi->back; + u32 head, val = 0, i; + int hung_queue = -1; + + 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; + 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_txq; i++) { + if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc) { + if (hung_queue == + vsi->tx_rings[i]->q_index) { + tx_ring = vsi->tx_rings[i]; + break; + } + } + } + } + + /* Reset recovery level if enough time has elapsed after last timeout. + * Also ensure no new reset action happens before next timeout period. + */ + if (time_after(jiffies, (pf->tx_timeout_last_recovery + HZ * 20))) + pf->tx_timeout_recovery_level = 1; + else if (time_before(jiffies, (pf->tx_timeout_last_recovery + + netdev->watchdog_timeo))) + return; + + if (tx_ring) { + head = tx_ring->next_to_clean; + /* Read interrupt register */ + if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) + val = rd32(&pf->hw, + GLINT_DYN_CTL(tx_ring->q_vector->v_idx + + tx_ring->vsi->base_vector - 1)); + + netdev_info(netdev, "tx_timeout: VSI_num: %d, Q %d, NTC: 0x%x, HWB: 0x%x, NTU: 0x%x, TAIL: 0x%x, INT: 0x%x\n", + vsi->vsi_num, 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, hung_queue %d\n", + pf->tx_timeout_recovery_level, hung_queue); + + switch (pf->tx_timeout_recovery_level) { + case 1: + set_bit(__ICE_PFR_REQ, pf->state); + break; + case 2: + set_bit(__ICE_CORER_REQ, pf->state); + break; + case 3: + set_bit(__ICE_GLOBR_REQ, pf->state); + break; + default: + netdev_err(netdev, "tx_timeout recovery unsuccessful, device is in unrecoverable state.\n"); + set_bit(__ICE_DOWN, pf->state); + set_bit(__ICE_NEEDS_RESTART, vsi->state); + set_bit(__ICE_SERVICE_DIS, pf->state); + break; + } + + ice_service_task_schedule(pf); + pf->tx_timeout_recovery_level++; +} + +/** * ice_open - Called when a network interface becomes active * @netdev: network interface device structure * @@ -5390,6 +6041,11 @@ static int ice_open(struct net_device *netdev) struct ice_vsi *vsi = np->vsi; int err; + if (test_bit(__ICE_NEEDS_RESTART, vsi->back->state)) { + netdev_err(netdev, "driver needs to be unloaded and reloaded\n"); + return -EIO; + } + netif_carrier_off(netdev); err = ice_vsi_open(vsi); @@ -5486,6 +6142,9 @@ static const struct net_device_ops ice_netdev_ops = { .ndo_vlan_rx_add_vid = ice_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = ice_vlan_rx_kill_vid, .ndo_set_features = ice_set_features, + .ndo_bridge_getlink = ice_bridge_getlink, + .ndo_bridge_setlink = ice_bridge_setlink, .ndo_fdb_add = ice_fdb_add, .ndo_fdb_del = ice_fdb_del, + .ndo_tx_timeout = ice_tx_timeout, }; diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c index 92da0a626ce0..3274c543283c 100644 --- a/drivers/net/ethernet/intel/ice/ice_nvm.c +++ b/drivers/net/ethernet/intel/ice/ice_nvm.c @@ -131,14 +131,13 @@ ice_read_sr_word_aq(struct ice_hw *hw, u16 offset, u16 *data) * * This function will request NVM ownership. */ -static enum -ice_status ice_acquire_nvm(struct ice_hw *hw, - enum ice_aq_res_access_type access) +static enum ice_status +ice_acquire_nvm(struct ice_hw *hw, enum ice_aq_res_access_type access) { if (hw->nvm.blank_nvm_mode) return 0; - return ice_acquire_res(hw, ICE_NVM_RES_ID, access); + return ice_acquire_res(hw, ICE_NVM_RES_ID, access, ICE_NVM_TIMEOUT); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c index 2e6c1d92cc88..9b7b50554952 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.c +++ b/drivers/net/ethernet/intel/ice/ice_sched.c @@ -17,7 +17,6 @@ ice_sched_add_root_node(struct ice_port_info *pi, { struct ice_sched_node *root; struct ice_hw *hw; - u16 max_children; if (!pi) return ICE_ERR_PARAM; @@ -28,8 +27,8 @@ ice_sched_add_root_node(struct ice_port_info *pi, if (!root) return ICE_ERR_NO_MEMORY; - max_children = le16_to_cpu(hw->layer_info[0].max_children); - root->children = devm_kcalloc(ice_hw_to_dev(hw), max_children, + /* coverity[suspicious_sizeof] */ + root->children = devm_kcalloc(ice_hw_to_dev(hw), hw->max_children[0], sizeof(*root), GFP_KERNEL); if (!root->children) { devm_kfree(ice_hw_to_dev(hw), root); @@ -100,7 +99,6 @@ ice_sched_add_node(struct ice_port_info *pi, u8 layer, struct ice_sched_node *parent; struct ice_sched_node *node; struct ice_hw *hw; - u16 max_children; if (!pi) return ICE_ERR_PARAM; @@ -120,9 +118,10 @@ ice_sched_add_node(struct ice_port_info *pi, u8 layer, node = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*node), GFP_KERNEL); if (!node) return ICE_ERR_NO_MEMORY; - max_children = le16_to_cpu(hw->layer_info[layer].max_children); - if (max_children) { - node->children = devm_kcalloc(ice_hw_to_dev(hw), max_children, + if (hw->max_children[layer]) { + /* coverity[suspicious_sizeof] */ + node->children = devm_kcalloc(ice_hw_to_dev(hw), + hw->max_children[layer], sizeof(*node), GFP_KERNEL); if (!node->children) { devm_kfree(ice_hw_to_dev(hw), node); @@ -192,14 +191,17 @@ ice_sched_remove_elems(struct ice_hw *hw, struct ice_sched_node *parent, buf = devm_kzalloc(ice_hw_to_dev(hw), buf_size, GFP_KERNEL); if (!buf) return ICE_ERR_NO_MEMORY; + buf->hdr.parent_teid = parent->info.node_teid; buf->hdr.num_elems = cpu_to_le16(num_nodes); for (i = 0; i < num_nodes; i++) buf->teid[i] = cpu_to_le32(node_teids[i]); + status = ice_aq_delete_sched_elems(hw, 1, buf, buf_size, &num_groups_removed, NULL); if (status || num_groups_removed != 1) ice_debug(hw, ICE_DBG_SCHED, "remove elements failed\n"); + devm_kfree(ice_hw_to_dev(hw), buf); return status; } @@ -592,13 +594,16 @@ static void ice_sched_clear_port(struct ice_port_info *pi) */ void ice_sched_cleanup_all(struct ice_hw *hw) { - if (!hw || !hw->port_info) + if (!hw) return; - if (hw->layer_info) + if (hw->layer_info) { devm_kfree(ice_hw_to_dev(hw), hw->layer_info); + hw->layer_info = NULL; + } - ice_sched_clear_port(hw->port_info); + if (hw->port_info) + ice_sched_clear_port(hw->port_info); hw->num_tx_sched_layers = 0; hw->num_tx_sched_phys_layers = 0; @@ -671,9 +676,13 @@ ice_sched_add_elems(struct ice_port_info *pi, struct ice_sched_node *tc_node, ICE_AQC_ELEM_VALID_EIR; buf->generic[i].data.generic = 0; buf->generic[i].data.cir_bw.bw_profile_idx = - ICE_SCHED_DFLT_RL_PROF_ID; + cpu_to_le16(ICE_SCHED_DFLT_RL_PROF_ID); + buf->generic[i].data.cir_bw.bw_alloc = + cpu_to_le16(ICE_SCHED_DFLT_BW_WT); buf->generic[i].data.eir_bw.bw_profile_idx = - ICE_SCHED_DFLT_RL_PROF_ID; + cpu_to_le16(ICE_SCHED_DFLT_RL_PROF_ID); + buf->generic[i].data.eir_bw.bw_alloc = + cpu_to_le16(ICE_SCHED_DFLT_BW_WT); } status = ice_aq_add_sched_elems(hw, 1, buf, buf_size, @@ -697,7 +706,6 @@ ice_sched_add_elems(struct ice_port_info *pi, struct ice_sched_node *tc_node, teid = le32_to_cpu(buf->generic[i].node_teid); new_node = ice_sched_find_node_by_teid(parent, teid); - if (!new_node) { ice_debug(hw, ICE_DBG_SCHED, "Node is missing for teid =%d\n", teid); @@ -710,7 +718,6 @@ ice_sched_add_elems(struct ice_port_info *pi, struct ice_sched_node *tc_node, /* add it to previous node sibling pointer */ /* Note: siblings are not linked across branches */ prev = ice_sched_get_first_node(hw, tc_node, layer); - if (prev && prev != new_node) { while (prev->sibling) prev = prev->sibling; @@ -760,8 +767,7 @@ ice_sched_add_nodes_to_layer(struct ice_port_info *pi, return ICE_ERR_PARAM; /* max children per node per layer */ - max_child_nodes = - le16_to_cpu(hw->layer_info[parent->tx_sched_layer].max_children); + max_child_nodes = hw->max_children[parent->tx_sched_layer]; /* current number of children + required nodes exceed max children ? */ if ((parent->num_children + num_nodes) > max_child_nodes) { @@ -851,78 +857,6 @@ static u8 ice_sched_get_vsi_layer(struct ice_hw *hw) } /** - * ice_sched_get_num_nodes_per_layer - Get the total number of nodes per layer - * @pi: pointer to the port info struct - * @layer: layer number - * - * This function calculates the number of nodes present in the scheduler tree - * including all the branches for a given layer - */ -static u16 -ice_sched_get_num_nodes_per_layer(struct ice_port_info *pi, u8 layer) -{ - struct ice_hw *hw; - u16 num_nodes = 0; - u8 i; - - if (!pi) - return num_nodes; - - hw = pi->hw; - - /* Calculate the number of nodes for all TCs */ - for (i = 0; i < pi->root->num_children; i++) { - struct ice_sched_node *tc_node, *node; - - tc_node = pi->root->children[i]; - - /* Get the first node */ - node = ice_sched_get_first_node(hw, tc_node, layer); - if (!node) - continue; - - /* count the siblings */ - while (node) { - num_nodes++; - node = node->sibling; - } - } - - return num_nodes; -} - -/** - * ice_sched_val_max_nodes - check max number of nodes reached or not - * @pi: port information structure - * @new_num_nodes_per_layer: pointer to the new number of nodes array - * - * This function checks whether the scheduler tree layers have enough space to - * add new nodes - */ -static enum ice_status -ice_sched_validate_for_max_nodes(struct ice_port_info *pi, - u16 *new_num_nodes_per_layer) -{ - struct ice_hw *hw = pi->hw; - u8 i, qg_layer; - u16 num_nodes; - - qg_layer = ice_sched_get_qgrp_layer(hw); - - /* walk through all the layers from SW entry point to qgroup layer */ - for (i = hw->sw_entry_point_layer; i <= qg_layer; i++) { - num_nodes = ice_sched_get_num_nodes_per_layer(pi, i); - if (num_nodes + new_num_nodes_per_layer[i] > - le16_to_cpu(hw->layer_info[i].max_pf_nodes)) { - ice_debug(hw, ICE_DBG_SCHED, - "max nodes reached for layer = %d\n", i); - return ICE_ERR_CFG; - } - } - return 0; -} - -/** * ice_rm_dflt_leaf_node - remove the default leaf node in the tree * @pi: port information structure * @@ -1003,14 +937,12 @@ enum ice_status ice_sched_init_port(struct ice_port_info *pi) hw = pi->hw; /* Query the Default Topology from FW */ - buf = devm_kcalloc(ice_hw_to_dev(hw), ICE_TXSCHED_MAX_BRANCHES, - sizeof(*buf), GFP_KERNEL); + buf = devm_kzalloc(ice_hw_to_dev(hw), ICE_AQ_MAX_BUF_LEN, GFP_KERNEL); if (!buf) return ICE_ERR_NO_MEMORY; /* Query default scheduling tree topology */ - status = ice_aq_get_dflt_topo(hw, pi->lport, buf, - sizeof(*buf) * ICE_TXSCHED_MAX_BRANCHES, + status = ice_aq_get_dflt_topo(hw, pi->lport, buf, ICE_AQ_MAX_BUF_LEN, &num_branches, NULL); if (status) goto err_init_port; @@ -1097,6 +1029,8 @@ enum ice_status ice_sched_query_res_alloc(struct ice_hw *hw) { struct ice_aqc_query_txsched_res_resp *buf; enum ice_status status = 0; + __le16 max_sibl; + u8 i; if (hw->layer_info) return status; @@ -1115,7 +1049,20 @@ enum ice_status ice_sched_query_res_alloc(struct ice_hw *hw) hw->flattened_layers = buf->sched_props.flattening_bitmap; hw->max_cgds = buf->sched_props.max_pf_cgds; - hw->layer_info = devm_kmemdup(ice_hw_to_dev(hw), buf->layer_props, + /* max sibling group size of current layer refers to the max children + * of the below layer node. + * layer 1 node max children will be layer 2 max sibling group size + * layer 2 node max children will be layer 3 max sibling group size + * and so on. This array will be populated from root (index 0) to + * qgroup layer 7. Leaf node has no children. + */ + for (i = 0; i < hw->num_tx_sched_layers; i++) { + max_sibl = buf->layer_props[i].max_sibl_grp_sz; + hw->max_children[i] = le16_to_cpu(max_sibl); + } + + hw->layer_info = (struct ice_aqc_layer_props *) + devm_kmemdup(ice_hw_to_dev(hw), buf->layer_props, (hw->num_tx_sched_layers * sizeof(*hw->layer_info)), GFP_KERNEL); @@ -1202,7 +1149,7 @@ ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_id, u8 tc, u8 qgrp_layer; qgrp_layer = ice_sched_get_qgrp_layer(pi->hw); - max_children = le16_to_cpu(pi->hw->layer_info[qgrp_layer].max_children); + max_children = pi->hw->max_children[qgrp_layer]; list_elem = ice_sched_get_vsi_info_entry(pi, vsi_id); if (!list_elem) @@ -1278,10 +1225,8 @@ ice_sched_calc_vsi_child_nodes(struct ice_hw *hw, u16 num_qs, u16 *num_nodes) /* calculate num nodes from q group to VSI layer */ for (i = qgl; i > vsil; i--) { - u16 max_children = le16_to_cpu(hw->layer_info[i].max_children); - /* round to the next integer if there is a remainder */ - num = DIV_ROUND_UP(num, max_children); + num = DIV_ROUND_UP(num, hw->max_children[i]); /* need at least one node */ num_nodes[i] = num ? num : 1; @@ -1311,16 +1256,13 @@ ice_sched_add_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_id, u16 num_added = 0; u8 i, qgl, vsil; - status = ice_sched_validate_for_max_nodes(pi, num_nodes); - if (status) - return status; - qgl = ice_sched_get_qgrp_layer(hw); vsil = ice_sched_get_vsi_layer(hw); parent = ice_sched_get_vsi_node(hw, tc_node, vsi_id); for (i = vsil + 1; i <= qgl; i++) { if (!parent) return ICE_ERR_CFG; + status = ice_sched_add_nodes_to_layer(pi, tc_node, parent, i, num_nodes[i], &first_node_teid, @@ -1398,8 +1340,8 @@ ice_sched_calc_vsi_support_nodes(struct ice_hw *hw, struct ice_sched_node *tc_node, u16 *num_nodes) { struct ice_sched_node *node; - u16 max_child; - u8 i, vsil; + u8 vsil; + int i; vsil = ice_sched_get_vsi_layer(hw); for (i = vsil; i >= hw->sw_entry_point_layer; i--) @@ -1412,12 +1354,10 @@ ice_sched_calc_vsi_support_nodes(struct ice_hw *hw, /* If intermediate nodes are reached max children * then add a new one. */ - node = ice_sched_get_first_node(hw, tc_node, i); - max_child = le16_to_cpu(hw->layer_info[i].max_children); - + node = ice_sched_get_first_node(hw, tc_node, (u8)i); /* scan all the siblings */ while (node) { - if (node->num_children < max_child) + if (node->num_children < hw->max_children[i]) break; node = node->sibling; } @@ -1451,10 +1391,6 @@ ice_sched_add_vsi_support_nodes(struct ice_port_info *pi, u16 vsi_id, if (!pi) return ICE_ERR_PARAM; - status = ice_sched_validate_for_max_nodes(pi, num_nodes); - if (status) - return status; - vsil = ice_sched_get_vsi_layer(pi->hw); for (i = pi->hw->sw_entry_point_layer; i <= vsil; i++) { status = ice_sched_add_nodes_to_layer(pi, tc_node, parent, @@ -1479,6 +1415,7 @@ ice_sched_add_vsi_support_nodes(struct ice_port_info *pi, u16 vsi_id, if (i == vsil) parent->vsi_id = vsi_id; } + return 0; } @@ -1576,8 +1513,7 @@ ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_id, u8 tc, return status; } - if (owner == ICE_SCHED_NODE_OWNER_LAN) - vsi->max_lanq[tc] = new_numqs; + vsi->max_lanq[tc] = new_numqs; return status; } @@ -1634,9 +1570,11 @@ ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_id, u8 tc, u16 maxqs, status = ice_sched_add_vsi_to_topo(pi, vsi_id, tc); if (status) return status; + vsi_node = ice_sched_get_vsi_node(hw, tc_node, vsi_id); if (!vsi_node) return ICE_ERR_CFG; + vsi->vsi_node[tc] = vsi_node; vsi_node->in_use = true; } diff --git a/drivers/net/ethernet/intel/ice/ice_status.h b/drivers/net/ethernet/intel/ice/ice_status.h index 9a95c4ffd7d7..d2dae913d81e 100644 --- a/drivers/net/ethernet/intel/ice/ice_status.h +++ b/drivers/net/ethernet/intel/ice/ice_status.h @@ -20,6 +20,7 @@ enum ice_status { ICE_ERR_ALREADY_EXISTS = -14, ICE_ERR_DOES_NOT_EXIST = -15, ICE_ERR_MAX_LIMIT = -17, + ICE_ERR_RESET_ONGOING = -18, ICE_ERR_BUF_TOO_SHORT = -52, ICE_ERR_NVM_BLANK_MODE = -53, ICE_ERR_AQ_ERROR = -100, diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 723d15f1e90b..65b4e1cca6be 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -86,6 +86,35 @@ ice_aq_alloc_free_res(struct ice_hw *hw, u16 num_entries, } /** + * ice_init_def_sw_recp - initialize the recipe book keeping tables + * @hw: pointer to the hw struct + * + * Allocate memory for the entire recipe table and initialize the structures/ + * entries corresponding to basic recipes. + */ +enum ice_status +ice_init_def_sw_recp(struct ice_hw *hw) +{ + struct ice_sw_recipe *recps; + u8 i; + + recps = devm_kcalloc(ice_hw_to_dev(hw), ICE_MAX_NUM_RECIPES, + sizeof(struct ice_sw_recipe), GFP_KERNEL); + if (!recps) + return ICE_ERR_NO_MEMORY; + + for (i = 0; i < ICE_SW_LKUP_LAST; i++) { + recps[i].root_rid = i; + INIT_LIST_HEAD(&recps[i].filt_rules); + mutex_init(&recps[i].filt_rule_lock); + } + + hw->switch_info->recp_list = recps; + + return 0; +} + +/** * ice_aq_get_sw_cfg - get switch configuration * @hw: pointer to the hardware structure * @buf: pointer to the result buffer @@ -140,17 +169,17 @@ ice_aq_get_sw_cfg(struct ice_hw *hw, struct ice_aqc_get_sw_cfg_resp *buf, * * Add a VSI context to the hardware (0x0210) */ -enum ice_status +static enum ice_status ice_aq_add_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, struct ice_sq_cd *cd) { struct ice_aqc_add_update_free_vsi_resp *res; struct ice_aqc_add_get_update_free_vsi *cmd; - enum ice_status status; struct ice_aq_desc desc; + enum ice_status status; cmd = &desc.params.vsi_cmd; - res = (struct ice_aqc_add_update_free_vsi_resp *)&desc.params.raw; + res = &desc.params.add_update_free_vsi_res; ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_add_vsi); @@ -175,6 +204,42 @@ ice_aq_add_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, } /** + * ice_aq_free_vsi + * @hw: pointer to the hw struct + * @vsi_ctx: pointer to a VSI context struct + * @keep_vsi_alloc: keep VSI allocation as part of this PF's resources + * @cd: pointer to command details structure or NULL + * + * Free VSI context info from hardware (0x0213) + */ +static enum ice_status +ice_aq_free_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, + bool keep_vsi_alloc, struct ice_sq_cd *cd) +{ + struct ice_aqc_add_update_free_vsi_resp *resp; + struct ice_aqc_add_get_update_free_vsi *cmd; + struct ice_aq_desc desc; + enum ice_status status; + + cmd = &desc.params.vsi_cmd; + resp = &desc.params.add_update_free_vsi_res; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_free_vsi); + + cmd->vsi_num = cpu_to_le16(vsi_ctx->vsi_num | ICE_AQ_VSI_IS_VALID); + if (keep_vsi_alloc) + cmd->cmd_flags = cpu_to_le16(ICE_AQ_VSI_KEEP_ALLOC); + + status = ice_aq_send_cmd(hw, &desc, NULL, 0, cd); + if (!status) { + vsi_ctx->vsis_allocd = le16_to_cpu(resp->vsi_used); + vsi_ctx->vsis_unallocated = le16_to_cpu(resp->vsi_free); + } + + return status; +} + +/** * ice_aq_update_vsi * @hw: pointer to the hw struct * @vsi_ctx: pointer to a VSI context struct @@ -192,7 +257,7 @@ ice_aq_update_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, enum ice_status status; cmd = &desc.params.vsi_cmd; - resp = (struct ice_aqc_add_update_free_vsi_resp *)&desc.params.raw; + resp = &desc.params.add_update_free_vsi_res; ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_update_vsi); @@ -212,38 +277,202 @@ ice_aq_update_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, } /** - * ice_aq_free_vsi + * ice_update_fltr_vsi_map - update given filter VSI map + * @list_head: list for which filters needs to be updated + * @list_lock: filter lock which needs to be updated + * @old_vsi_num: old VSI HW id + * @new_vsi_num: new VSI HW id + * + * update the VSI map for a given filter list + */ +static void +ice_update_fltr_vsi_map(struct list_head *list_head, + struct mutex *list_lock, u16 old_vsi_num, + u16 new_vsi_num) +{ + struct ice_fltr_mgmt_list_entry *itr; + + mutex_lock(list_lock); + if (list_empty(list_head)) + goto exit_update_map; + + list_for_each_entry(itr, list_head, list_entry) { + if (itr->vsi_list_info && + test_bit(old_vsi_num, itr->vsi_list_info->vsi_map)) { + clear_bit(old_vsi_num, itr->vsi_list_info->vsi_map); + set_bit(new_vsi_num, itr->vsi_list_info->vsi_map); + } else if (itr->fltr_info.fltr_act == ICE_FWD_TO_VSI && + itr->fltr_info.fwd_id.vsi_id == old_vsi_num) { + itr->fltr_info.fwd_id.vsi_id = new_vsi_num; + itr->fltr_info.src = new_vsi_num; + } + } +exit_update_map: + mutex_unlock(list_lock); +} + +/** + * ice_update_all_fltr_vsi_map - update all filters VSI map + * @hw: pointer to the hardware structure + * @old_vsi_num: old VSI HW id + * @new_vsi_num: new VSI HW id + * + * update all filters VSI map + */ +static void +ice_update_all_fltr_vsi_map(struct ice_hw *hw, u16 old_vsi_num, u16 new_vsi_num) +{ + struct ice_switch_info *sw = hw->switch_info; + u8 i; + + for (i = 0; i < ICE_SW_LKUP_LAST; i++) { + struct list_head *head = &sw->recp_list[i].filt_rules; + struct mutex *lock; /* Lock to protect filter rule list */ + + lock = &sw->recp_list[i].filt_rule_lock; + ice_update_fltr_vsi_map(head, lock, old_vsi_num, + new_vsi_num); + } +} + +/** + * ice_is_vsi_valid - check whether the VSI is valid or not * @hw: pointer to the hw struct + * @vsi_handle: VSI handle + * + * check whether the VSI is valid or not + */ +static bool ice_is_vsi_valid(struct ice_hw *hw, u16 vsi_handle) +{ + return vsi_handle < ICE_MAX_VSI && hw->vsi_ctx[vsi_handle]; +} + +/** + * ice_get_hw_vsi_num - return the hw VSI number + * @hw: pointer to the hw struct + * @vsi_handle: VSI handle + * + * return the hw VSI number + * Caution: call this function only if VSI is valid (ice_is_vsi_valid) + */ +static u16 ice_get_hw_vsi_num(struct ice_hw *hw, u16 vsi_handle) +{ + return hw->vsi_ctx[vsi_handle]->vsi_num; +} + +/** + * ice_get_vsi_ctx - return the VSI context entry for a given VSI handle + * @hw: pointer to the hw struct + * @vsi_handle: VSI handle + * + * return the VSI context entry for a given VSI handle + */ +static struct ice_vsi_ctx *ice_get_vsi_ctx(struct ice_hw *hw, u16 vsi_handle) +{ + return (vsi_handle >= ICE_MAX_VSI) ? NULL : hw->vsi_ctx[vsi_handle]; +} + +/** + * ice_save_vsi_ctx - save the VSI context for a given VSI handle + * @hw: pointer to the hw struct + * @vsi_handle: VSI handle + * @vsi: VSI context pointer + * + * save the VSI context entry for a given VSI handle + */ +static void ice_save_vsi_ctx(struct ice_hw *hw, u16 vsi_handle, + struct ice_vsi_ctx *vsi) +{ + hw->vsi_ctx[vsi_handle] = vsi; +} + +/** + * ice_clear_vsi_ctx - clear the VSI context entry + * @hw: pointer to the hw struct + * @vsi_handle: VSI handle + * + * clear the VSI context entry + */ +static void ice_clear_vsi_ctx(struct ice_hw *hw, u16 vsi_handle) +{ + struct ice_vsi_ctx *vsi; + + vsi = ice_get_vsi_ctx(hw, vsi_handle); + if (vsi) { + devm_kfree(ice_hw_to_dev(hw), vsi); + hw->vsi_ctx[vsi_handle] = NULL; + } +} + +/** + * ice_add_vsi - add VSI context to the hardware and VSI handle list + * @hw: pointer to the hw struct + * @vsi_handle: unique VSI handle provided by drivers * @vsi_ctx: pointer to a VSI context struct - * @keep_vsi_alloc: keep VSI allocation as part of this PF's resources * @cd: pointer to command details structure or NULL * - * Get VSI context info from hardware (0x0213) + * Add a VSI context to the hardware also add it into the VSI handle list. + * If this function gets called after reset for existing VSIs then update + * with the new HW VSI number in the corresponding VSI handle list entry. */ enum ice_status -ice_aq_free_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, - bool keep_vsi_alloc, struct ice_sq_cd *cd) +ice_add_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, + struct ice_sq_cd *cd) { - struct ice_aqc_add_update_free_vsi_resp *resp; - struct ice_aqc_add_get_update_free_vsi *cmd; - struct ice_aq_desc desc; + struct ice_vsi_ctx *tmp_vsi_ctx; enum ice_status status; - cmd = &desc.params.vsi_cmd; - resp = (struct ice_aqc_add_update_free_vsi_resp *)&desc.params.raw; - - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_free_vsi); + if (vsi_handle >= ICE_MAX_VSI) + return ICE_ERR_PARAM; + status = ice_aq_add_vsi(hw, vsi_ctx, cd); + if (status) + return status; + tmp_vsi_ctx = ice_get_vsi_ctx(hw, vsi_handle); + if (!tmp_vsi_ctx) { + /* Create a new vsi context */ + tmp_vsi_ctx = devm_kzalloc(ice_hw_to_dev(hw), + sizeof(*tmp_vsi_ctx), GFP_KERNEL); + if (!tmp_vsi_ctx) { + ice_aq_free_vsi(hw, vsi_ctx, false, cd); + return ICE_ERR_NO_MEMORY; + } + *tmp_vsi_ctx = *vsi_ctx; + ice_save_vsi_ctx(hw, vsi_handle, tmp_vsi_ctx); + } else { + /* update with new HW VSI num */ + if (tmp_vsi_ctx->vsi_num != vsi_ctx->vsi_num) { + /* update all filter lists with new HW VSI num */ + ice_update_all_fltr_vsi_map(hw, tmp_vsi_ctx->vsi_num, + vsi_ctx->vsi_num); + tmp_vsi_ctx->vsi_num = vsi_ctx->vsi_num; + } + } - cmd->vsi_num = cpu_to_le16(vsi_ctx->vsi_num | ICE_AQ_VSI_IS_VALID); - if (keep_vsi_alloc) - cmd->cmd_flags = cpu_to_le16(ICE_AQ_VSI_KEEP_ALLOC); + return status; +} - status = ice_aq_send_cmd(hw, &desc, NULL, 0, cd); - if (!status) { - vsi_ctx->vsis_allocd = le16_to_cpu(resp->vsi_used); - vsi_ctx->vsis_unallocated = le16_to_cpu(resp->vsi_free); - } +/** + * ice_free_vsi- free VSI context from hardware and VSI handle list + * @hw: pointer to the hw struct + * @vsi_handle: unique VSI handle + * @vsi_ctx: pointer to a VSI context struct + * @keep_vsi_alloc: keep VSI allocation as part of this PF's resources + * @cd: pointer to command details structure or NULL + * + * Free VSI context info from hardware as well as from VSI handle list + */ +enum ice_status +ice_free_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, + bool keep_vsi_alloc, struct ice_sq_cd *cd) +{ + enum ice_status status; + if (!ice_is_vsi_valid(hw, vsi_handle)) + return ICE_ERR_PARAM; + vsi_ctx->vsi_num = ice_get_hw_vsi_num(hw, vsi_handle); + status = ice_aq_free_vsi(hw, vsi_ctx, keep_vsi_alloc, cd); + if (!status) + ice_clear_vsi_ctx(hw, vsi_handle); return status; } @@ -464,8 +693,9 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info, struct ice_aqc_sw_rules_elem *s_rule, enum ice_adminq_opc opc) { u16 vlan_id = ICE_MAX_VLAN_ID + 1; - u8 eth_hdr[DUMMY_ETH_HDR_LEN]; void *daddr = NULL; + u16 eth_hdr_sz; + u8 *eth_hdr; u32 act = 0; __be16 *off; @@ -477,8 +707,11 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info, return; } + eth_hdr_sz = sizeof(dummy_eth_header); + eth_hdr = s_rule->pdata.lkup_tx_rx.hdr; + /* initialize the ether header with a dummy header */ - memcpy(eth_hdr, dummy_eth_header, sizeof(dummy_eth_header)); + memcpy(eth_hdr, dummy_eth_header, eth_hdr_sz); ice_fill_sw_info(hw, f_info); switch (f_info->fltr_act) { @@ -536,7 +769,7 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info, daddr = f_info->l_data.ethertype_mac.mac_addr; /* fall-through */ case ICE_SW_LKUP_ETHERTYPE: - off = (__be16 *)ð_hdr[ICE_ETH_ETHTYPE_OFFSET]; + off = (__be16 *)(eth_hdr + ICE_ETH_ETHTYPE_OFFSET); *off = cpu_to_be16(f_info->l_data.ethertype_mac.ethertype); break; case ICE_SW_LKUP_MAC_VLAN: @@ -563,18 +796,16 @@ ice_fill_sw_rule(struct ice_hw *hw, struct ice_fltr_info *f_info, s_rule->pdata.lkup_tx_rx.act = cpu_to_le32(act); if (daddr) - ether_addr_copy(ð_hdr[ICE_ETH_DA_OFFSET], daddr); + ether_addr_copy(eth_hdr + ICE_ETH_DA_OFFSET, daddr); if (!(vlan_id > ICE_MAX_VLAN_ID)) { - off = (__be16 *)ð_hdr[ICE_ETH_VLAN_TCI_OFFSET]; + off = (__be16 *)(eth_hdr + ICE_ETH_VLAN_TCI_OFFSET); *off = cpu_to_be16(vlan_id); } /* Create the switch rule with the final dummy Ethernet header */ if (opc != ice_aqc_opc_update_sw_rules) - s_rule->pdata.lkup_tx_rx.hdr_len = cpu_to_le16(sizeof(eth_hdr)); - - memcpy(s_rule->pdata.lkup_tx_rx.hdr, eth_hdr, sizeof(eth_hdr)); + s_rule->pdata.lkup_tx_rx.hdr_len = cpu_to_le16(eth_hdr_sz); } /** @@ -645,14 +876,14 @@ ice_add_marker_act(struct ice_hw *hw, struct ice_fltr_mgmt_list_entry *m_ent, act |= (1 << ICE_LG_ACT_GENERIC_VALUE_S) & ICE_LG_ACT_GENERIC_VALUE_M; lg_act->pdata.lg_act.act[1] = cpu_to_le32(act); - act = (7 << ICE_LG_ACT_GENERIC_OFFSET_S) & ICE_LG_ACT_GENERIC_VALUE_M; + act = (ICE_LG_ACT_GENERIC_OFF_RX_DESC_PROF_IDX << + ICE_LG_ACT_GENERIC_OFFSET_S) & ICE_LG_ACT_GENERIC_OFFSET_M; /* Third action Marker value */ act |= ICE_LG_ACT_GENERIC; act |= (sw_marker << ICE_LG_ACT_GENERIC_VALUE_S) & ICE_LG_ACT_GENERIC_VALUE_M; - act |= (0 << ICE_LG_ACT_GENERIC_OFFSET_S) & ICE_LG_ACT_GENERIC_VALUE_M; lg_act->pdata.lg_act.act[2] = cpu_to_le32(act); /* call the fill switch rule to fill the lookup tx rx structure */ @@ -816,10 +1047,10 @@ static enum ice_status ice_create_pkt_fwd_rule(struct ice_hw *hw, struct ice_fltr_list_entry *f_entry) { - struct ice_switch_info *sw = hw->switch_info; struct ice_fltr_mgmt_list_entry *fm_entry; struct ice_aqc_sw_rules_elem *s_rule; enum ice_sw_lkup_type l_type; + struct ice_sw_recipe *recp; enum ice_status status; s_rule = devm_kzalloc(ice_hw_to_dev(hw), @@ -860,31 +1091,9 @@ ice_create_pkt_fwd_rule(struct ice_hw *hw, * calls remove filter AQ command */ l_type = fm_entry->fltr_info.lkup_type; - if (l_type == ICE_SW_LKUP_MAC) { - mutex_lock(&sw->mac_list_lock); - list_add(&fm_entry->list_entry, &sw->mac_list_head); - mutex_unlock(&sw->mac_list_lock); - } else if (l_type == ICE_SW_LKUP_VLAN) { - mutex_lock(&sw->vlan_list_lock); - list_add(&fm_entry->list_entry, &sw->vlan_list_head); - mutex_unlock(&sw->vlan_list_lock); - } else if (l_type == ICE_SW_LKUP_ETHERTYPE || - l_type == ICE_SW_LKUP_ETHERTYPE_MAC) { - mutex_lock(&sw->eth_m_list_lock); - list_add(&fm_entry->list_entry, &sw->eth_m_list_head); - mutex_unlock(&sw->eth_m_list_lock); - } else if (l_type == ICE_SW_LKUP_PROMISC || - l_type == ICE_SW_LKUP_PROMISC_VLAN) { - mutex_lock(&sw->promisc_list_lock); - list_add(&fm_entry->list_entry, &sw->promisc_list_head); - mutex_unlock(&sw->promisc_list_lock); - } else if (fm_entry->fltr_info.lkup_type == ICE_SW_LKUP_MAC_VLAN) { - mutex_lock(&sw->mac_vlan_list_lock); - list_add(&fm_entry->list_entry, &sw->mac_vlan_list_head); - mutex_unlock(&sw->mac_vlan_list_lock); - } else { - status = ICE_ERR_NOT_IMPL; - } + recp = &hw->switch_info->recp_list[l_type]; + list_add(&fm_entry->list_entry, &recp->filt_rules); + ice_create_pkt_fwd_rule_exit: devm_kfree(ice_hw_to_dev(hw), s_rule); return status; @@ -893,19 +1102,15 @@ ice_create_pkt_fwd_rule_exit: /** * ice_update_pkt_fwd_rule * @hw: pointer to the hardware structure - * @rule_id: rule of previously created switch rule to update - * @vsi_list_id: VSI list id to be updated with - * @f_info: ice_fltr_info to pull other information for switch rule + * @f_info: filter information for switch rule * * Call AQ command to update a previously created switch rule with a * VSI list id */ static enum ice_status -ice_update_pkt_fwd_rule(struct ice_hw *hw, u16 rule_id, u16 vsi_list_id, - struct ice_fltr_info f_info) +ice_update_pkt_fwd_rule(struct ice_hw *hw, struct ice_fltr_info *f_info) { struct ice_aqc_sw_rules_elem *s_rule; - struct ice_fltr_info tmp_fltr; enum ice_status status; s_rule = devm_kzalloc(ice_hw_to_dev(hw), @@ -913,14 +1118,9 @@ ice_update_pkt_fwd_rule(struct ice_hw *hw, u16 rule_id, u16 vsi_list_id, if (!s_rule) return ICE_ERR_NO_MEMORY; - tmp_fltr = f_info; - tmp_fltr.fltr_act = ICE_FWD_TO_VSI_LIST; - tmp_fltr.fwd_id.vsi_list_id = vsi_list_id; + ice_fill_sw_rule(hw, f_info, s_rule, ice_aqc_opc_update_sw_rules); - ice_fill_sw_rule(hw, &tmp_fltr, s_rule, - ice_aqc_opc_update_sw_rules); - - s_rule->pdata.lkup_tx_rx.index = cpu_to_le16(rule_id); + s_rule->pdata.lkup_tx_rx.index = cpu_to_le16(f_info->fltr_rule_id); /* Update switch rule with new rule set to forward VSI list */ status = ice_aq_sw_rules(hw, s_rule, ICE_SW_RULE_RX_TX_ETH_HDR_SIZE, 1, @@ -931,7 +1131,48 @@ ice_update_pkt_fwd_rule(struct ice_hw *hw, u16 rule_id, u16 vsi_list_id, } /** - * ice_handle_vsi_list_mgmt + * ice_update_sw_rule_bridge_mode + * @hw: pointer to the hw struct + * + * Updates unicast switch filter rules based on VEB/VEPA mode + */ +enum ice_status ice_update_sw_rule_bridge_mode(struct ice_hw *hw) +{ + struct ice_switch_info *sw = hw->switch_info; + struct ice_fltr_mgmt_list_entry *fm_entry; + enum ice_status status = 0; + struct list_head *rule_head; + struct mutex *rule_lock; /* Lock to protect filter rule list */ + + rule_lock = &sw->recp_list[ICE_SW_LKUP_MAC].filt_rule_lock; + rule_head = &sw->recp_list[ICE_SW_LKUP_MAC].filt_rules; + + mutex_lock(rule_lock); + list_for_each_entry(fm_entry, rule_head, list_entry) { + struct ice_fltr_info *fi = &fm_entry->fltr_info; + u8 *addr = fi->l_data.mac.mac_addr; + + /* Update unicast Tx rules to reflect the selected + * VEB/VEPA mode + */ + if ((fi->flag & ICE_FLTR_TX) && is_unicast_ether_addr(addr) && + (fi->fltr_act == ICE_FWD_TO_VSI || + fi->fltr_act == ICE_FWD_TO_VSI_LIST || + fi->fltr_act == ICE_FWD_TO_Q || + fi->fltr_act == ICE_FWD_TO_QGRP)) { + status = ice_update_pkt_fwd_rule(hw, fi); + if (status) + break; + } + } + + mutex_unlock(rule_lock); + + return status; +} + +/** + * ice_add_update_vsi_list * @hw: pointer to the hardware structure * @m_entry: pointer to current filter management list entry * @cur_fltr: filter information from the book keeping entry @@ -952,10 +1193,10 @@ ice_update_pkt_fwd_rule(struct ice_hw *hw, u16 rule_id, u16 vsi_list_id, * using the update switch rule command */ static enum ice_status -ice_handle_vsi_list_mgmt(struct ice_hw *hw, - struct ice_fltr_mgmt_list_entry *m_entry, - struct ice_fltr_info *cur_fltr, - struct ice_fltr_info *new_fltr) +ice_add_update_vsi_list(struct ice_hw *hw, + struct ice_fltr_mgmt_list_entry *m_entry, + struct ice_fltr_info *cur_fltr, + struct ice_fltr_info *new_fltr) { enum ice_status status = 0; u16 vsi_list_id = 0; @@ -975,8 +1216,8 @@ ice_handle_vsi_list_mgmt(struct ice_hw *hw, * a part of a VSI list. So, create a VSI list with the old and * new VSIs. */ + struct ice_fltr_info tmp_fltr; u16 vsi_id_arr[2]; - u16 fltr_rule; /* A rule already exists with the new VSI being added */ if (cur_fltr->fwd_id.vsi_id == new_fltr->fwd_id.vsi_id) @@ -990,12 +1231,14 @@ ice_handle_vsi_list_mgmt(struct ice_hw *hw, if (status) return status; - fltr_rule = cur_fltr->fltr_rule_id; + tmp_fltr = *new_fltr; + tmp_fltr.fltr_rule_id = cur_fltr->fltr_rule_id; + tmp_fltr.fltr_act = ICE_FWD_TO_VSI_LIST; + tmp_fltr.fwd_id.vsi_list_id = vsi_list_id; /* Update the previous switch rule of "MAC forward to VSI" to * "MAC fwd to VSI list" */ - status = ice_update_pkt_fwd_rule(hw, fltr_rule, vsi_list_id, - *new_fltr); + status = ice_update_pkt_fwd_rule(hw, &tmp_fltr); if (status) return status; @@ -1040,54 +1283,245 @@ ice_handle_vsi_list_mgmt(struct ice_hw *hw, } /** - * ice_find_mac_entry + * ice_find_rule_entry - Search a rule entry * @hw: pointer to the hardware structure - * @mac_addr: MAC address to search for + * @recp_id: lookup type for which the specified rule needs to be searched + * @f_info: rule information * - * Helper function to search for a MAC entry using a given MAC address - * Returns pointer to the entry if found. + * Helper function to search for a given rule entry + * Returns pointer to entry storing the rule if found */ static struct ice_fltr_mgmt_list_entry * -ice_find_mac_entry(struct ice_hw *hw, u8 *mac_addr) +ice_find_rule_entry(struct ice_hw *hw, u8 recp_id, struct ice_fltr_info *f_info) { - struct ice_fltr_mgmt_list_entry *m_list_itr, *mac_ret = NULL; + struct ice_fltr_mgmt_list_entry *list_itr, *ret = NULL; struct ice_switch_info *sw = hw->switch_info; - - mutex_lock(&sw->mac_list_lock); - list_for_each_entry(m_list_itr, &sw->mac_list_head, list_entry) { - u8 *buf = &m_list_itr->fltr_info.l_data.mac.mac_addr[0]; - - if (ether_addr_equal(buf, mac_addr)) { - mac_ret = m_list_itr; + struct list_head *list_head; + + list_head = &sw->recp_list[recp_id].filt_rules; + list_for_each_entry(list_itr, list_head, list_entry) { + if (!memcmp(&f_info->l_data, &list_itr->fltr_info.l_data, + sizeof(f_info->l_data)) && + f_info->flag == list_itr->fltr_info.flag) { + ret = list_itr; break; } } - mutex_unlock(&sw->mac_list_lock); - return mac_ret; + return ret; } /** - * ice_add_shared_mac - Add one MAC shared filter rule + * ice_add_rule_internal - add rule for a given lookup type * @hw: pointer to the hardware structure + * @recp_id: lookup type (recipe id) for which rule has to be added * @f_entry: structure containing MAC forwarding information * - * Adds or updates the book keeping list for the MAC addresses + * Adds or updates the rule lists for a given recipe */ static enum ice_status -ice_add_shared_mac(struct ice_hw *hw, struct ice_fltr_list_entry *f_entry) +ice_add_rule_internal(struct ice_hw *hw, u8 recp_id, + struct ice_fltr_list_entry *f_entry) { + struct ice_switch_info *sw = hw->switch_info; struct ice_fltr_info *new_fltr, *cur_fltr; struct ice_fltr_mgmt_list_entry *m_entry; + struct mutex *rule_lock; /* Lock to protect filter rule list */ + enum ice_status status = 0; - new_fltr = &f_entry->fltr_info; + rule_lock = &sw->recp_list[recp_id].filt_rule_lock; - m_entry = ice_find_mac_entry(hw, &new_fltr->l_data.mac.mac_addr[0]); - if (!m_entry) + mutex_lock(rule_lock); + new_fltr = &f_entry->fltr_info; + if (new_fltr->flag & ICE_FLTR_RX) + new_fltr->src = hw->port_info->lport; + else if (new_fltr->flag & ICE_FLTR_TX) + new_fltr->src = f_entry->fltr_info.fwd_id.vsi_id; + + m_entry = ice_find_rule_entry(hw, recp_id, new_fltr); + if (!m_entry) { + mutex_unlock(rule_lock); return ice_create_pkt_fwd_rule(hw, f_entry); + } cur_fltr = &m_entry->fltr_info; + status = ice_add_update_vsi_list(hw, m_entry, cur_fltr, new_fltr); + mutex_unlock(rule_lock); - return ice_handle_vsi_list_mgmt(hw, m_entry, cur_fltr, new_fltr); + return status; +} + +/** + * ice_remove_vsi_list_rule + * @hw: pointer to the hardware structure + * @vsi_list_id: VSI list id generated as part of allocate resource + * @lkup_type: switch rule filter lookup type + * + * The VSI list should be emptied before this function is called to remove the + * VSI list. + */ +static enum ice_status +ice_remove_vsi_list_rule(struct ice_hw *hw, u16 vsi_list_id, + enum ice_sw_lkup_type lkup_type) +{ + struct ice_aqc_sw_rules_elem *s_rule; + enum ice_status status; + u16 s_rule_size; + + s_rule_size = (u16)ICE_SW_RULE_VSI_LIST_SIZE(0); + s_rule = devm_kzalloc(ice_hw_to_dev(hw), s_rule_size, GFP_KERNEL); + if (!s_rule) + return ICE_ERR_NO_MEMORY; + + s_rule->type = cpu_to_le16(ICE_AQC_SW_RULES_T_VSI_LIST_CLEAR); + s_rule->pdata.vsi_list.index = cpu_to_le16(vsi_list_id); + + /* Free the vsi_list resource that we allocated. It is assumed that the + * list is empty at this point. + */ + status = ice_aq_alloc_free_vsi_list(hw, &vsi_list_id, lkup_type, + ice_aqc_opc_free_res); + + devm_kfree(ice_hw_to_dev(hw), s_rule); + return status; +} + +/** + * ice_rem_update_vsi_list + * @hw: pointer to the hardware structure + * @vsi_id: ID of the VSI to remove + * @fm_list: filter management entry for which the VSI list management needs to + * be done + */ +static enum ice_status +ice_rem_update_vsi_list(struct ice_hw *hw, u16 vsi_id, + struct ice_fltr_mgmt_list_entry *fm_list) +{ + enum ice_sw_lkup_type lkup_type; + enum ice_status status = 0; + u16 vsi_list_id; + + if (fm_list->fltr_info.fltr_act != ICE_FWD_TO_VSI_LIST || + fm_list->vsi_count == 0) + return ICE_ERR_PARAM; + + /* A rule with the VSI being removed does not exist */ + if (!test_bit(vsi_id, fm_list->vsi_list_info->vsi_map)) + return ICE_ERR_DOES_NOT_EXIST; + + lkup_type = fm_list->fltr_info.lkup_type; + vsi_list_id = fm_list->fltr_info.fwd_id.vsi_list_id; + + status = ice_update_vsi_list_rule(hw, &vsi_id, 1, vsi_list_id, true, + ice_aqc_opc_update_sw_rules, + lkup_type); + if (status) + return status; + + fm_list->vsi_count--; + clear_bit(vsi_id, fm_list->vsi_list_info->vsi_map); + + if ((fm_list->vsi_count == 1 && lkup_type != ICE_SW_LKUP_VLAN) || + (fm_list->vsi_count == 0 && lkup_type == ICE_SW_LKUP_VLAN)) { + struct ice_vsi_list_map_info *vsi_list_info = + fm_list->vsi_list_info; + u16 rem_vsi_id; + + rem_vsi_id = find_first_bit(vsi_list_info->vsi_map, + ICE_MAX_VSI); + if (rem_vsi_id == ICE_MAX_VSI) + return ICE_ERR_OUT_OF_RANGE; + + status = ice_update_vsi_list_rule(hw, &rem_vsi_id, 1, + vsi_list_id, true, + ice_aqc_opc_update_sw_rules, + lkup_type); + if (status) + return status; + + /* Remove the VSI list since it is no longer used */ + status = ice_remove_vsi_list_rule(hw, vsi_list_id, lkup_type); + if (status) + return status; + + /* Change the list entry action from VSI_LIST to VSI */ + fm_list->fltr_info.fltr_act = ICE_FWD_TO_VSI; + fm_list->fltr_info.fwd_id.vsi_id = rem_vsi_id; + + list_del(&vsi_list_info->list_entry); + devm_kfree(ice_hw_to_dev(hw), vsi_list_info); + fm_list->vsi_list_info = NULL; + } + + return status; +} + +/** + * ice_remove_rule_internal - Remove a filter rule of a given type + * @hw: pointer to the hardware structure + * @recp_id: recipe id for which the rule needs to removed + * @f_entry: rule entry containing filter information + */ +static enum ice_status +ice_remove_rule_internal(struct ice_hw *hw, u8 recp_id, + struct ice_fltr_list_entry *f_entry) +{ + struct ice_switch_info *sw = hw->switch_info; + struct ice_fltr_mgmt_list_entry *list_elem; + struct mutex *rule_lock; /* Lock to protect filter rule list */ + enum ice_status status = 0; + bool remove_rule = false; + u16 vsi_id; + + rule_lock = &sw->recp_list[recp_id].filt_rule_lock; + mutex_lock(rule_lock); + list_elem = ice_find_rule_entry(hw, recp_id, &f_entry->fltr_info); + if (!list_elem) { + status = ICE_ERR_DOES_NOT_EXIST; + goto exit; + } + + if (list_elem->fltr_info.fltr_act != ICE_FWD_TO_VSI_LIST) { + remove_rule = true; + } else { + vsi_id = f_entry->fltr_info.fwd_id.vsi_id; + status = ice_rem_update_vsi_list(hw, vsi_id, list_elem); + if (status) + goto exit; + /* if vsi count goes to zero after updating the vsi list */ + if (list_elem->vsi_count == 0) + remove_rule = true; + } + + if (remove_rule) { + /* Remove the lookup rule */ + struct ice_aqc_sw_rules_elem *s_rule; + + s_rule = devm_kzalloc(ice_hw_to_dev(hw), + ICE_SW_RULE_RX_TX_NO_HDR_SIZE, + GFP_KERNEL); + if (!s_rule) { + status = ICE_ERR_NO_MEMORY; + goto exit; + } + + ice_fill_sw_rule(hw, &list_elem->fltr_info, s_rule, + ice_aqc_opc_remove_sw_rules); + + status = ice_aq_sw_rules(hw, s_rule, + ICE_SW_RULE_RX_TX_NO_HDR_SIZE, 1, + ice_aqc_opc_remove_sw_rules, NULL); + if (status) + goto exit; + + /* Remove a book keeping from the list */ + devm_kfree(ice_hw_to_dev(hw), s_rule); + + list_del(&list_elem->list_entry); + devm_kfree(ice_hw_to_dev(hw), list_elem); + } +exit: + mutex_unlock(rule_lock); + return status; } /** @@ -1106,7 +1540,10 @@ ice_add_mac(struct ice_hw *hw, struct list_head *m_list) { struct ice_aqc_sw_rules_elem *s_rule, *r_iter; struct ice_fltr_list_entry *m_list_itr; + struct list_head *rule_head; u16 elem_sent, total_elem_left; + struct ice_switch_info *sw; + struct mutex *rule_lock; /* Lock to protect filter rule list */ enum ice_status status = 0; u16 num_unicast = 0; u16 s_rule_size; @@ -1114,48 +1551,62 @@ ice_add_mac(struct ice_hw *hw, struct list_head *m_list) if (!m_list || !hw) return ICE_ERR_PARAM; + s_rule = NULL; + sw = hw->switch_info; + rule_lock = &sw->recp_list[ICE_SW_LKUP_MAC].filt_rule_lock; list_for_each_entry(m_list_itr, m_list, list_entry) { u8 *add = &m_list_itr->fltr_info.l_data.mac.mac_addr[0]; - if (m_list_itr->fltr_info.lkup_type != ICE_SW_LKUP_MAC) - return ICE_ERR_PARAM; - if (is_zero_ether_addr(add)) + m_list_itr->fltr_info.flag = ICE_FLTR_TX; + if (m_list_itr->fltr_info.lkup_type != ICE_SW_LKUP_MAC || + is_zero_ether_addr(add)) return ICE_ERR_PARAM; if (is_unicast_ether_addr(add) && !hw->ucast_shared) { /* Don't overwrite the unicast address */ - if (ice_find_mac_entry(hw, add)) + mutex_lock(rule_lock); + if (ice_find_rule_entry(hw, ICE_SW_LKUP_MAC, + &m_list_itr->fltr_info)) { + mutex_unlock(rule_lock); return ICE_ERR_ALREADY_EXISTS; + } + mutex_unlock(rule_lock); num_unicast++; } else if (is_multicast_ether_addr(add) || (is_unicast_ether_addr(add) && hw->ucast_shared)) { - status = ice_add_shared_mac(hw, m_list_itr); - if (status) { - m_list_itr->status = ICE_FLTR_STATUS_FW_FAIL; - return status; - } - m_list_itr->status = ICE_FLTR_STATUS_FW_SUCCESS; + m_list_itr->status = + ice_add_rule_internal(hw, ICE_SW_LKUP_MAC, + m_list_itr); + if (m_list_itr->status) + return m_list_itr->status; } } + mutex_lock(rule_lock); /* Exit if no suitable entries were found for adding bulk switch rule */ - if (!num_unicast) - return 0; + if (!num_unicast) { + status = 0; + goto ice_add_mac_exit; + } + + rule_head = &sw->recp_list[ICE_SW_LKUP_MAC].filt_rules; /* Allocate switch rule buffer for the bulk update for unicast */ s_rule_size = ICE_SW_RULE_RX_TX_ETH_HDR_SIZE; s_rule = devm_kcalloc(ice_hw_to_dev(hw), num_unicast, s_rule_size, GFP_KERNEL); - if (!s_rule) - return ICE_ERR_NO_MEMORY; + if (!s_rule) { + status = ICE_ERR_NO_MEMORY; + goto ice_add_mac_exit; + } r_iter = s_rule; list_for_each_entry(m_list_itr, m_list, list_entry) { struct ice_fltr_info *f_info = &m_list_itr->fltr_info; - u8 *addr = &f_info->l_data.mac.mac_addr[0]; + u8 *mac_addr = &f_info->l_data.mac.mac_addr[0]; - if (is_unicast_ether_addr(addr)) { - ice_fill_sw_rule(hw, &m_list_itr->fltr_info, - r_iter, ice_aqc_opc_add_sw_rules); + if (is_unicast_ether_addr(mac_addr)) { + ice_fill_sw_rule(hw, &m_list_itr->fltr_info, r_iter, + ice_aqc_opc_add_sw_rules); r_iter = (struct ice_aqc_sw_rules_elem *) ((u8 *)r_iter + s_rule_size); } @@ -1183,11 +1634,10 @@ ice_add_mac(struct ice_hw *hw, struct list_head *m_list) r_iter = s_rule; list_for_each_entry(m_list_itr, m_list, list_entry) { struct ice_fltr_info *f_info = &m_list_itr->fltr_info; - u8 *addr = &f_info->l_data.mac.mac_addr[0]; - struct ice_switch_info *sw = hw->switch_info; + u8 *mac_addr = &f_info->l_data.mac.mac_addr[0]; struct ice_fltr_mgmt_list_entry *fm_entry; - if (is_unicast_ether_addr(addr)) { + if (is_unicast_ether_addr(mac_addr)) { f_info->fltr_rule_id = le16_to_cpu(r_iter->pdata.lkup_tx_rx.index); f_info->fltr_act = ICE_FWD_TO_VSI; @@ -1203,46 +1653,21 @@ ice_add_mac(struct ice_hw *hw, struct list_head *m_list) /* The book keeping entries will get removed when * base driver calls remove filter AQ command */ - mutex_lock(&sw->mac_list_lock); - list_add(&fm_entry->list_entry, &sw->mac_list_head); - mutex_unlock(&sw->mac_list_lock); + list_add(&fm_entry->list_entry, rule_head); r_iter = (struct ice_aqc_sw_rules_elem *) ((u8 *)r_iter + s_rule_size); } } ice_add_mac_exit: - devm_kfree(ice_hw_to_dev(hw), s_rule); + mutex_unlock(rule_lock); + if (s_rule) + devm_kfree(ice_hw_to_dev(hw), s_rule); return status; } /** - * ice_find_vlan_entry - * @hw: pointer to the hardware structure - * @vlan_id: VLAN id to search for - * - * Helper function to search for a VLAN entry using a given VLAN id - * Returns pointer to the entry if found. - */ -static struct ice_fltr_mgmt_list_entry * -ice_find_vlan_entry(struct ice_hw *hw, u16 vlan_id) -{ - struct ice_fltr_mgmt_list_entry *vlan_list_itr, *vlan_ret = NULL; - struct ice_switch_info *sw = hw->switch_info; - - mutex_lock(&sw->vlan_list_lock); - list_for_each_entry(vlan_list_itr, &sw->vlan_list_head, list_entry) - if (vlan_list_itr->fltr_info.l_data.vlan.vlan_id == vlan_id) { - vlan_ret = vlan_list_itr; - break; - } - - mutex_unlock(&sw->vlan_list_lock); - return vlan_ret; -} - -/** * ice_add_vlan_internal - Add one VLAN based filter rule * @hw: pointer to the hardware structure * @f_entry: filter entry containing one VLAN information @@ -1250,20 +1675,22 @@ ice_find_vlan_entry(struct ice_hw *hw, u16 vlan_id) static enum ice_status ice_add_vlan_internal(struct ice_hw *hw, struct ice_fltr_list_entry *f_entry) { + struct ice_switch_info *sw = hw->switch_info; struct ice_fltr_info *new_fltr, *cur_fltr; struct ice_fltr_mgmt_list_entry *v_list_itr; - u16 vlan_id; + struct mutex *rule_lock; /* Lock to protect filter rule list */ + enum ice_status status = 0; new_fltr = &f_entry->fltr_info; /* VLAN id should only be 12 bits */ if (new_fltr->l_data.vlan.vlan_id > ICE_MAX_VLAN_ID) return ICE_ERR_PARAM; - vlan_id = new_fltr->l_data.vlan.vlan_id; - v_list_itr = ice_find_vlan_entry(hw, vlan_id); + rule_lock = &sw->recp_list[ICE_SW_LKUP_VLAN].filt_rule_lock; + mutex_lock(rule_lock); + v_list_itr = ice_find_rule_entry(hw, ICE_SW_LKUP_VLAN, new_fltr); if (!v_list_itr) { u16 vsi_id = ICE_VSI_INVAL_ID; - enum ice_status status; u16 vsi_list_id = 0; if (new_fltr->fltr_act == ICE_FWD_TO_VSI) { @@ -1277,26 +1704,33 @@ ice_add_vlan_internal(struct ice_hw *hw, struct ice_fltr_list_entry *f_entry) &vsi_list_id, lkup_type); if (status) - return status; + goto exit; new_fltr->fltr_act = ICE_FWD_TO_VSI_LIST; new_fltr->fwd_id.vsi_list_id = vsi_list_id; } status = ice_create_pkt_fwd_rule(hw, f_entry); if (!status && vsi_id != ICE_VSI_INVAL_ID) { - v_list_itr = ice_find_vlan_entry(hw, vlan_id); - if (!v_list_itr) - return ICE_ERR_DOES_NOT_EXIST; + v_list_itr = ice_find_rule_entry(hw, ICE_SW_LKUP_VLAN, + new_fltr); + if (!v_list_itr) { + status = ICE_ERR_DOES_NOT_EXIST; + goto exit; + } v_list_itr->vsi_list_info = ice_create_vsi_list_map(hw, &vsi_id, 1, vsi_list_id); } - return status; + goto exit; } cur_fltr = &v_list_itr->fltr_info; - return ice_handle_vsi_list_mgmt(hw, v_list_itr, cur_fltr, new_fltr); + status = ice_add_update_vsi_list(hw, v_list_itr, cur_fltr, new_fltr); + +exit: + mutex_unlock(rule_lock); + return status; } /** @@ -1313,326 +1747,44 @@ ice_add_vlan(struct ice_hw *hw, struct list_head *v_list) return ICE_ERR_PARAM; list_for_each_entry(v_list_itr, v_list, list_entry) { - enum ice_status status; - if (v_list_itr->fltr_info.lkup_type != ICE_SW_LKUP_VLAN) return ICE_ERR_PARAM; - - status = ice_add_vlan_internal(hw, v_list_itr); - if (status) { - v_list_itr->status = ICE_FLTR_STATUS_FW_FAIL; - return status; - } - v_list_itr->status = ICE_FLTR_STATUS_FW_SUCCESS; + v_list_itr->fltr_info.flag = ICE_FLTR_TX; + v_list_itr->status = ice_add_vlan_internal(hw, v_list_itr); + if (v_list_itr->status) + return v_list_itr->status; } return 0; } /** - * ice_remove_vsi_list_rule + * ice_rem_sw_rule_info * @hw: pointer to the hardware structure - * @vsi_list_id: VSI list id generated as part of allocate resource - * @lkup_type: switch rule filter lookup type + * @rule_head: pointer to the switch list structure that we want to delete */ -static enum ice_status -ice_remove_vsi_list_rule(struct ice_hw *hw, u16 vsi_list_id, - enum ice_sw_lkup_type lkup_type) -{ - struct ice_aqc_sw_rules_elem *s_rule; - enum ice_status status; - u16 s_rule_size; - - s_rule_size = (u16)ICE_SW_RULE_VSI_LIST_SIZE(0); - s_rule = devm_kzalloc(ice_hw_to_dev(hw), s_rule_size, GFP_KERNEL); - if (!s_rule) - return ICE_ERR_NO_MEMORY; - - s_rule->type = cpu_to_le16(ICE_AQC_SW_RULES_T_VSI_LIST_CLEAR); - s_rule->pdata.vsi_list.index = cpu_to_le16(vsi_list_id); - /* FW expects number of VSIs in vsi_list resource to be 0 for clear - * command. Since memory is zero'ed out during initialization, it's not - * necessary to explicitly initialize the variable to 0. - */ - - status = ice_aq_sw_rules(hw, s_rule, s_rule_size, 1, - ice_aqc_opc_remove_sw_rules, NULL); - if (!status) - /* Free the vsi_list resource that we allocated */ - status = ice_aq_alloc_free_vsi_list(hw, &vsi_list_id, lkup_type, - ice_aqc_opc_free_res); - - devm_kfree(ice_hw_to_dev(hw), s_rule); - return status; -} - -/** - * ice_handle_rem_vsi_list_mgmt - * @hw: pointer to the hardware structure - * @vsi_id: ID of the VSI to remove - * @fm_list_itr: filter management entry for which the VSI list management - * needs to be done - */ -static enum ice_status -ice_handle_rem_vsi_list_mgmt(struct ice_hw *hw, u16 vsi_id, - struct ice_fltr_mgmt_list_entry *fm_list_itr) +static void +ice_rem_sw_rule_info(struct ice_hw *hw, struct list_head *rule_head) { - struct ice_switch_info *sw = hw->switch_info; - enum ice_status status = 0; - enum ice_sw_lkup_type lkup_type; - bool is_last_elem = true; - bool conv_list = false; - bool del_list = false; - u16 vsi_list_id; + if (!list_empty(rule_head)) { + struct ice_fltr_mgmt_list_entry *entry; + struct ice_fltr_mgmt_list_entry *tmp; - lkup_type = fm_list_itr->fltr_info.lkup_type; - vsi_list_id = fm_list_itr->fltr_info.fwd_id.vsi_list_id; - - if (fm_list_itr->vsi_count > 1) { - status = ice_update_vsi_list_rule(hw, &vsi_id, 1, vsi_list_id, - true, - ice_aqc_opc_update_sw_rules, - lkup_type); - if (status) - return status; - fm_list_itr->vsi_count--; - is_last_elem = false; - clear_bit(vsi_id, fm_list_itr->vsi_list_info->vsi_map); - } - - /* For non-VLAN rules that forward packets to a VSI list, convert them - * to forwarding packets to a VSI if there is only one VSI left in the - * list. Unused lists are then removed. - * VLAN rules need to use VSI lists even with only one VSI. - */ - if (fm_list_itr->fltr_info.fltr_act == ICE_FWD_TO_VSI_LIST) { - if (lkup_type == ICE_SW_LKUP_VLAN) { - del_list = is_last_elem; - } else if (fm_list_itr->vsi_count == 1) { - conv_list = true; - del_list = true; + list_for_each_entry_safe(entry, tmp, rule_head, list_entry) { + list_del(&entry->list_entry); + devm_kfree(ice_hw_to_dev(hw), entry); } } - - if (del_list) { - /* Remove the VSI list since it is no longer used */ - struct ice_vsi_list_map_info *vsi_list_info = - fm_list_itr->vsi_list_info; - - status = ice_remove_vsi_list_rule(hw, vsi_list_id, lkup_type); - if (status) - return status; - - if (conv_list) { - u16 rem_vsi_id; - - rem_vsi_id = find_first_bit(vsi_list_info->vsi_map, - ICE_MAX_VSI); - - /* Error out when the expected last element is not in - * the VSI list map - */ - if (rem_vsi_id == ICE_MAX_VSI) - return ICE_ERR_OUT_OF_RANGE; - - /* Change the list entry action from VSI_LIST to VSI */ - fm_list_itr->fltr_info.fltr_act = ICE_FWD_TO_VSI; - fm_list_itr->fltr_info.fwd_id.vsi_id = rem_vsi_id; - } - - list_del(&vsi_list_info->list_entry); - devm_kfree(ice_hw_to_dev(hw), vsi_list_info); - fm_list_itr->vsi_list_info = NULL; - } - - if (conv_list) { - /* Convert the rule's forward action to forwarding packets to - * a VSI - */ - struct ice_aqc_sw_rules_elem *s_rule; - - s_rule = devm_kzalloc(ice_hw_to_dev(hw), - ICE_SW_RULE_RX_TX_ETH_HDR_SIZE, - GFP_KERNEL); - if (!s_rule) - return ICE_ERR_NO_MEMORY; - - ice_fill_sw_rule(hw, &fm_list_itr->fltr_info, s_rule, - ice_aqc_opc_update_sw_rules); - - s_rule->pdata.lkup_tx_rx.index = - cpu_to_le16(fm_list_itr->fltr_info.fltr_rule_id); - - status = ice_aq_sw_rules(hw, s_rule, - ICE_SW_RULE_RX_TX_ETH_HDR_SIZE, 1, - ice_aqc_opc_update_sw_rules, NULL); - devm_kfree(ice_hw_to_dev(hw), s_rule); - if (status) - return status; - } - - if (is_last_elem) { - /* Remove the lookup rule */ - struct ice_aqc_sw_rules_elem *s_rule; - - s_rule = devm_kzalloc(ice_hw_to_dev(hw), - ICE_SW_RULE_RX_TX_NO_HDR_SIZE, - GFP_KERNEL); - if (!s_rule) - return ICE_ERR_NO_MEMORY; - - ice_fill_sw_rule(hw, &fm_list_itr->fltr_info, s_rule, - ice_aqc_opc_remove_sw_rules); - - status = ice_aq_sw_rules(hw, s_rule, - ICE_SW_RULE_RX_TX_NO_HDR_SIZE, 1, - ice_aqc_opc_remove_sw_rules, NULL); - if (status) - return status; - - /* Remove a book keeping entry from the MAC address list */ - mutex_lock(&sw->mac_list_lock); - list_del(&fm_list_itr->list_entry); - mutex_unlock(&sw->mac_list_lock); - devm_kfree(ice_hw_to_dev(hw), fm_list_itr); - devm_kfree(ice_hw_to_dev(hw), s_rule); - } - return status; -} - -/** - * ice_remove_mac_entry - * @hw: pointer to the hardware structure - * @f_entry: structure containing MAC forwarding information - */ -static enum ice_status -ice_remove_mac_entry(struct ice_hw *hw, struct ice_fltr_list_entry *f_entry) -{ - struct ice_fltr_mgmt_list_entry *m_entry; - u16 vsi_id; - u8 *add; - - add = &f_entry->fltr_info.l_data.mac.mac_addr[0]; - - m_entry = ice_find_mac_entry(hw, add); - if (!m_entry) - return ICE_ERR_PARAM; - - vsi_id = f_entry->fltr_info.fwd_id.vsi_id; - return ice_handle_rem_vsi_list_mgmt(hw, vsi_id, m_entry); } /** - * ice_remove_mac - remove a MAC address based filter rule - * @hw: pointer to the hardware structure - * @m_list: list of MAC addresses and forwarding information - * - * This function removes either a MAC filter rule or a specific VSI from a - * VSI list for a multicast MAC address. - * - * Returns ICE_ERR_DOES_NOT_EXIST if a given entry was not added by - * ice_add_mac. Caller should be aware that this call will only work if all - * the entries passed into m_list were added previously. It will not attempt to - * do a partial remove of entries that were found. - */ -enum ice_status -ice_remove_mac(struct ice_hw *hw, struct list_head *m_list) -{ - struct ice_aqc_sw_rules_elem *s_rule, *r_iter; - u8 s_rule_size = ICE_SW_RULE_RX_TX_NO_HDR_SIZE; - struct ice_switch_info *sw = hw->switch_info; - struct ice_fltr_mgmt_list_entry *m_entry; - struct ice_fltr_list_entry *m_list_itr; - u16 elem_sent, total_elem_left; - enum ice_status status = 0; - u16 num_unicast = 0; - - if (!m_list) - return ICE_ERR_PARAM; - - list_for_each_entry(m_list_itr, m_list, list_entry) { - u8 *addr = m_list_itr->fltr_info.l_data.mac.mac_addr; - - if (is_unicast_ether_addr(addr) && !hw->ucast_shared) - num_unicast++; - else if (is_multicast_ether_addr(addr) || - (is_unicast_ether_addr(addr) && hw->ucast_shared)) - ice_remove_mac_entry(hw, m_list_itr); - } - - /* Exit if no unicast addresses found. Multicast switch rules - * were added individually - */ - if (!num_unicast) - return 0; - - /* Allocate switch rule buffer for the bulk update for unicast */ - s_rule = devm_kcalloc(ice_hw_to_dev(hw), num_unicast, s_rule_size, - GFP_KERNEL); - if (!s_rule) - return ICE_ERR_NO_MEMORY; - - r_iter = s_rule; - list_for_each_entry(m_list_itr, m_list, list_entry) { - u8 *addr = m_list_itr->fltr_info.l_data.mac.mac_addr; - - if (is_unicast_ether_addr(addr)) { - m_entry = ice_find_mac_entry(hw, addr); - if (!m_entry) { - status = ICE_ERR_DOES_NOT_EXIST; - goto ice_remove_mac_exit; - } - - ice_fill_sw_rule(hw, &m_entry->fltr_info, - r_iter, ice_aqc_opc_remove_sw_rules); - r_iter = (struct ice_aqc_sw_rules_elem *) - ((u8 *)r_iter + s_rule_size); - } - } - - /* Call AQ bulk switch rule update for all unicast addresses */ - r_iter = s_rule; - /* Call AQ switch rule in AQ_MAX chunk */ - for (total_elem_left = num_unicast; total_elem_left > 0; - total_elem_left -= elem_sent) { - struct ice_aqc_sw_rules_elem *entry = r_iter; - - elem_sent = min(total_elem_left, - (u16)(ICE_AQ_MAX_BUF_LEN / s_rule_size)); - status = ice_aq_sw_rules(hw, entry, elem_sent * s_rule_size, - elem_sent, ice_aqc_opc_remove_sw_rules, - NULL); - if (status) - break; - r_iter = (struct ice_aqc_sw_rules_elem *) - ((u8 *)r_iter + s_rule_size); - } - - list_for_each_entry(m_list_itr, m_list, list_entry) { - u8 *addr = m_list_itr->fltr_info.l_data.mac.mac_addr; - - if (is_unicast_ether_addr(addr)) { - m_entry = ice_find_mac_entry(hw, addr); - if (!m_entry) - return ICE_ERR_OUT_OF_RANGE; - mutex_lock(&sw->mac_list_lock); - list_del(&m_entry->list_entry); - mutex_unlock(&sw->mac_list_lock); - devm_kfree(ice_hw_to_dev(hw), m_entry); - } - } - -ice_remove_mac_exit: - devm_kfree(ice_hw_to_dev(hw), s_rule); - return status; -} - -/** - * ice_cfg_dflt_vsi - add filter rule to set/unset given VSI as default - * VSI for the switch (represented by swid) + * ice_cfg_dflt_vsi - change state of VSI to set/clear default * @hw: pointer to the hardware structure * @vsi_id: number of VSI to set as default * @set: true to add the above mentioned switch rule, false to remove it * @direction: ICE_FLTR_RX or ICE_FLTR_TX + * + * add filter rule to set/unset given VSI as default VSI for the switch + * (represented by swid) */ enum ice_status ice_cfg_dflt_vsi(struct ice_hw *hw, u16 vsi_id, bool set, u8 direction) @@ -1704,26 +1856,38 @@ out: } /** - * ice_remove_vlan_internal - Remove one VLAN based filter rule + * ice_remove_mac - remove a MAC address based filter rule * @hw: pointer to the hardware structure - * @f_entry: filter entry containing one VLAN information + * @m_list: list of MAC addresses and forwarding information + * + * This function removes either a MAC filter rule or a specific VSI from a + * VSI list for a multicast MAC address. + * + * Returns ICE_ERR_DOES_NOT_EXIST if a given entry was not added by + * ice_add_mac. Caller should be aware that this call will only work if all + * the entries passed into m_list were added previously. It will not attempt to + * do a partial remove of entries that were found. */ -static enum ice_status -ice_remove_vlan_internal(struct ice_hw *hw, - struct ice_fltr_list_entry *f_entry) +enum ice_status +ice_remove_mac(struct ice_hw *hw, struct list_head *m_list) { - struct ice_fltr_info *new_fltr; - struct ice_fltr_mgmt_list_entry *v_list_elem; - u16 vsi_id; + struct ice_fltr_list_entry *list_itr; - new_fltr = &f_entry->fltr_info; - - v_list_elem = ice_find_vlan_entry(hw, new_fltr->l_data.vlan.vlan_id); - if (!v_list_elem) + if (!m_list) return ICE_ERR_PARAM; - vsi_id = f_entry->fltr_info.fwd_id.vsi_id; - return ice_handle_rem_vsi_list_mgmt(hw, vsi_id, v_list_elem); + list_for_each_entry(list_itr, m_list, list_entry) { + enum ice_sw_lkup_type l_type = list_itr->fltr_info.lkup_type; + + if (l_type != ICE_SW_LKUP_MAC) + return ICE_ERR_PARAM; + list_itr->status = ice_remove_rule_internal(hw, + ICE_SW_LKUP_MAC, + list_itr); + if (list_itr->status) + return list_itr->status; + } + return 0; } /** @@ -1735,20 +1899,78 @@ enum ice_status ice_remove_vlan(struct ice_hw *hw, struct list_head *v_list) { struct ice_fltr_list_entry *v_list_itr; - enum ice_status status = 0; if (!v_list || !hw) return ICE_ERR_PARAM; list_for_each_entry(v_list_itr, v_list, list_entry) { - status = ice_remove_vlan_internal(hw, v_list_itr); - if (status) { - v_list_itr->status = ICE_FLTR_STATUS_FW_FAIL; - return status; - } - v_list_itr->status = ICE_FLTR_STATUS_FW_SUCCESS; + enum ice_sw_lkup_type l_type = v_list_itr->fltr_info.lkup_type; + + if (l_type != ICE_SW_LKUP_VLAN) + return ICE_ERR_PARAM; + v_list_itr->status = ice_remove_rule_internal(hw, + ICE_SW_LKUP_VLAN, + v_list_itr); + if (v_list_itr->status) + return v_list_itr->status; } - return status; + return 0; +} + +/** + * ice_vsi_uses_fltr - Determine if given VSI uses specified filter + * @fm_entry: filter entry to inspect + * @vsi_id: ID of VSI to compare with filter info + */ +static bool +ice_vsi_uses_fltr(struct ice_fltr_mgmt_list_entry *fm_entry, u16 vsi_id) +{ + return ((fm_entry->fltr_info.fltr_act == ICE_FWD_TO_VSI && + fm_entry->fltr_info.fwd_id.vsi_id == vsi_id) || + (fm_entry->fltr_info.fltr_act == ICE_FWD_TO_VSI_LIST && + (test_bit(vsi_id, fm_entry->vsi_list_info->vsi_map)))); +} + +/** + * ice_add_entry_to_vsi_fltr_list - Add copy of fltr_list_entry to remove list + * @hw: pointer to the hardware structure + * @vsi_id: ID of VSI to remove filters from + * @vsi_list_head: pointer to the list to add entry to + * @fi: pointer to fltr_info of filter entry to copy & add + * + * Helper function, used when creating a list of filters to remove from + * a specific VSI. The entry added to vsi_list_head is a COPY of the + * original filter entry, with the exception of fltr_info.fltr_act and + * fltr_info.fwd_id fields. These are set such that later logic can + * extract which VSI to remove the fltr from, and pass on that information. + */ +static enum ice_status +ice_add_entry_to_vsi_fltr_list(struct ice_hw *hw, u16 vsi_id, + struct list_head *vsi_list_head, + struct ice_fltr_info *fi) +{ + struct ice_fltr_list_entry *tmp; + + /* this memory is freed up in the caller function + * once filters for this VSI are removed + */ + tmp = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*tmp), GFP_KERNEL); + if (!tmp) + return ICE_ERR_NO_MEMORY; + + tmp->fltr_info = *fi; + + /* Overwrite these fields to indicate which VSI to remove filter from, + * so find and remove logic can extract the information from the + * list entries. Note that original entries will still have proper + * values. + */ + tmp->fltr_info.fltr_act = ICE_FWD_TO_VSI; + tmp->fltr_info.fwd_id.vsi_id = vsi_id; + + list_add(&tmp->list_entry, vsi_list_head); + + return 0; } /** @@ -1757,6 +1979,12 @@ ice_remove_vlan(struct ice_hw *hw, struct list_head *v_list) * @vsi_id: ID of VSI to remove filters from * @lkup_list_head: pointer to the list that has certain lookup type filters * @vsi_list_head: pointer to the list pertaining to VSI with vsi_id + * + * Locates all filters in lkup_list_head that are used by the given VSI, + * and adds COPIES of those entries to vsi_list_head (intended to be used + * to remove the listed filters). + * Note that this means all entries in vsi_list_head must be explicitly + * deallocated by the caller when done with list. */ static enum ice_status ice_add_to_vsi_fltr_list(struct ice_hw *hw, u16 vsi_id, @@ -1764,46 +1992,25 @@ ice_add_to_vsi_fltr_list(struct ice_hw *hw, u16 vsi_id, struct list_head *vsi_list_head) { struct ice_fltr_mgmt_list_entry *fm_entry; + enum ice_status status = 0; /* check to make sure VSI id is valid and within boundary */ - if (vsi_id >= - (sizeof(fm_entry->vsi_list_info->vsi_map) * BITS_PER_BYTE - 1)) + if (vsi_id >= ICE_MAX_VSI) return ICE_ERR_PARAM; list_for_each_entry(fm_entry, lkup_list_head, list_entry) { struct ice_fltr_info *fi; fi = &fm_entry->fltr_info; - if ((fi->fltr_act == ICE_FWD_TO_VSI && - fi->fwd_id.vsi_id == vsi_id) || - (fi->fltr_act == ICE_FWD_TO_VSI_LIST && - (test_bit(vsi_id, fm_entry->vsi_list_info->vsi_map)))) { - struct ice_fltr_list_entry *tmp; - - /* this memory is freed up in the caller function - * ice_remove_vsi_lkup_fltr() once filters for - * this VSI are removed - */ - tmp = devm_kzalloc(ice_hw_to_dev(hw), sizeof(*tmp), - GFP_KERNEL); - if (!tmp) - return ICE_ERR_NO_MEMORY; - - memcpy(&tmp->fltr_info, fi, sizeof(*fi)); + if (!ice_vsi_uses_fltr(fm_entry, vsi_id)) + continue; - /* Expected below fields to be set to ICE_FWD_TO_VSI and - * the particular VSI id since we are only removing this - * one VSI - */ - if (fi->fltr_act == ICE_FWD_TO_VSI_LIST) { - tmp->fltr_info.fltr_act = ICE_FWD_TO_VSI; - tmp->fltr_info.fwd_id.vsi_id = vsi_id; - } - - list_add(&tmp->list_entry, vsi_list_head); - } + status = ice_add_entry_to_vsi_fltr_list(hw, vsi_id, + vsi_list_head, fi); + if (status) + return status; } - return 0; + return status; } /** @@ -1819,46 +2026,40 @@ ice_remove_vsi_lkup_fltr(struct ice_hw *hw, u16 vsi_id, struct ice_switch_info *sw = hw->switch_info; struct ice_fltr_list_entry *fm_entry; struct list_head remove_list_head; + struct list_head *rule_head; struct ice_fltr_list_entry *tmp; + struct mutex *rule_lock; /* Lock to protect filter rule list */ enum ice_status status; INIT_LIST_HEAD(&remove_list_head); + rule_lock = &sw->recp_list[lkup].filt_rule_lock; + rule_head = &sw->recp_list[lkup].filt_rules; + mutex_lock(rule_lock); + status = ice_add_to_vsi_fltr_list(hw, vsi_id, rule_head, + &remove_list_head); + mutex_unlock(rule_lock); + if (status) + return; + switch (lkup) { case ICE_SW_LKUP_MAC: - mutex_lock(&sw->mac_list_lock); - status = ice_add_to_vsi_fltr_list(hw, vsi_id, - &sw->mac_list_head, - &remove_list_head); - mutex_unlock(&sw->mac_list_lock); - if (!status) { - ice_remove_mac(hw, &remove_list_head); - goto free_fltr_list; - } + ice_remove_mac(hw, &remove_list_head); break; case ICE_SW_LKUP_VLAN: - mutex_lock(&sw->vlan_list_lock); - status = ice_add_to_vsi_fltr_list(hw, vsi_id, - &sw->vlan_list_head, - &remove_list_head); - mutex_unlock(&sw->vlan_list_lock); - if (!status) { - ice_remove_vlan(hw, &remove_list_head); - goto free_fltr_list; - } + ice_remove_vlan(hw, &remove_list_head); break; case ICE_SW_LKUP_MAC_VLAN: case ICE_SW_LKUP_ETHERTYPE: case ICE_SW_LKUP_ETHERTYPE_MAC: case ICE_SW_LKUP_PROMISC: - case ICE_SW_LKUP_PROMISC_VLAN: case ICE_SW_LKUP_DFLT: - ice_debug(hw, ICE_DBG_SW, - "Remove filters for this lookup type hasn't been implemented yet\n"); + case ICE_SW_LKUP_PROMISC_VLAN: + case ICE_SW_LKUP_LAST: + default: + ice_debug(hw, ICE_DBG_SW, "Unsupported lookup type %d\n", lkup); break; } - return; -free_fltr_list: list_for_each_entry_safe(fm_entry, tmp, &remove_list_head, list_entry) { list_del(&fm_entry->list_entry); devm_kfree(ice_hw_to_dev(hw), fm_entry); @@ -1881,3 +2082,89 @@ void ice_remove_vsi_fltr(struct ice_hw *hw, u16 vsi_id) ice_remove_vsi_lkup_fltr(hw, vsi_id, ICE_SW_LKUP_ETHERTYPE_MAC); ice_remove_vsi_lkup_fltr(hw, vsi_id, ICE_SW_LKUP_PROMISC_VLAN); } + +/** + * ice_replay_fltr - Replay all the filters stored by a specific list head + * @hw: pointer to the hardware structure + * @list_head: list for which filters needs to be replayed + * @recp_id: Recipe id for which rules need to be replayed + */ +static enum ice_status +ice_replay_fltr(struct ice_hw *hw, u8 recp_id, struct list_head *list_head) +{ + struct ice_fltr_mgmt_list_entry *itr; + struct list_head l_head; + enum ice_status status = 0; + + if (list_empty(list_head)) + return status; + + /* Move entries from the given list_head to a temporary l_head so that + * they can be replayed. Otherwise when trying to re-add the same + * filter, the function will return already exists + */ + list_replace_init(list_head, &l_head); + + /* Mark the given list_head empty by reinitializing it so filters + * could be added again by *handler + */ + list_for_each_entry(itr, &l_head, list_entry) { + struct ice_fltr_list_entry f_entry; + + f_entry.fltr_info = itr->fltr_info; + if (itr->vsi_count < 2 && recp_id != ICE_SW_LKUP_VLAN) { + status = ice_add_rule_internal(hw, recp_id, &f_entry); + if (status) + goto end; + continue; + } + + /* Add a filter per vsi separately */ + while (1) { + u16 vsi; + + vsi = find_first_bit(itr->vsi_list_info->vsi_map, + ICE_MAX_VSI); + if (vsi == ICE_MAX_VSI) + break; + + clear_bit(vsi, itr->vsi_list_info->vsi_map); + f_entry.fltr_info.fwd_id.vsi_id = vsi; + f_entry.fltr_info.fltr_act = ICE_FWD_TO_VSI; + if (recp_id == ICE_SW_LKUP_VLAN) + status = ice_add_vlan_internal(hw, &f_entry); + else + status = ice_add_rule_internal(hw, recp_id, + &f_entry); + if (status) + goto end; + } + } +end: + /* Clear the filter management list */ + ice_rem_sw_rule_info(hw, &l_head); + return status; +} + +/** + * ice_replay_all_fltr - replay all filters stored in bookkeeping lists + * @hw: pointer to the hardware structure + * + * NOTE: This function does not clean up partially added filters on error. + * It is up to caller of the function to issue a reset or fail early. + */ +enum ice_status ice_replay_all_fltr(struct ice_hw *hw) +{ + struct ice_switch_info *sw = hw->switch_info; + enum ice_status status = 0; + u8 i; + + for (i = 0; i < ICE_SW_LKUP_LAST; i++) { + struct list_head *head = &sw->recp_list[i].filt_rules; + + status = ice_replay_fltr(hw, i, head); + if (status) + return status; + } + return status; +} diff --git a/drivers/net/ethernet/intel/ice/ice_switch.h b/drivers/net/ethernet/intel/ice/ice_switch.h index 6f4a0d159dbf..646389ca1238 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.h +++ b/drivers/net/ethernet/intel/ice/ice_switch.h @@ -17,7 +17,7 @@ struct ice_vsi_ctx { u16 vsis_unallocated; u16 flags; struct ice_aqc_vsi_props info; - bool alloc_from_pool; + u8 alloc_from_pool; }; enum ice_sw_fwd_act_type { @@ -39,6 +39,7 @@ enum ice_sw_lkup_type { ICE_SW_LKUP_DFLT = 5, ICE_SW_LKUP_ETHERTYPE_MAC = 8, ICE_SW_LKUP_PROMISC_VLAN = 9, + ICE_SW_LKUP_LAST }; struct ice_fltr_info { @@ -94,8 +95,33 @@ struct ice_fltr_info { u8 qgrp_size; /* Rule creations populate these indicators basing on the switch type */ - bool lb_en; /* Indicate if packet can be looped back */ - bool lan_en; /* Indicate if packet can be forwarded to the uplink */ + u8 lb_en; /* Indicate if packet can be looped back */ + u8 lan_en; /* Indicate if packet can be forwarded to the uplink */ +}; + +struct ice_sw_recipe { + struct list_head l_entry; + + /* To protect modification of filt_rule list + * defined below + */ + struct mutex filt_rule_lock; + + /* List of type ice_fltr_mgmt_list_entry */ + struct list_head filt_rules; + + /* linked list of type recipe_list_entry */ + struct list_head rg_list; + /* linked list of type ice_sw_fv_list_entry*/ + struct list_head fv_list; + struct ice_aqc_recipe_data_elem *r_buf; + u8 recp_count; + u8 root_rid; + u8 num_profs; + u8 *prof_ids; + + /* recipe bitmap: what all recipes makes this recipe */ + DECLARE_BITMAP(r_bitmap, ICE_MAX_NUM_RECIPES); }; /* Bookkeeping structure to hold bitmap of VSIs corresponding to VSI list id */ @@ -105,15 +131,9 @@ struct ice_vsi_list_map_info { u16 vsi_list_id; }; -enum ice_sw_fltr_status { - ICE_FLTR_STATUS_NEW = 0, - ICE_FLTR_STATUS_FW_SUCCESS, - ICE_FLTR_STATUS_FW_FAIL, -}; - struct ice_fltr_list_entry { struct list_head list_entry; - enum ice_sw_fltr_status status; + enum ice_status status; struct ice_fltr_info fltr_info; }; @@ -138,18 +158,18 @@ struct ice_fltr_mgmt_list_entry { /* VSI related commands */ enum ice_status -ice_aq_add_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, - struct ice_sq_cd *cd); -enum ice_status ice_aq_update_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, struct ice_sq_cd *cd); enum ice_status -ice_aq_free_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx, - bool keep_vsi_alloc, struct ice_sq_cd *cd); - +ice_add_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, + struct ice_sq_cd *cd); +enum ice_status +ice_free_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, + bool keep_vsi_alloc, struct ice_sq_cd *cd); enum ice_status ice_get_initial_sw_cfg(struct ice_hw *hw); /* Switch/bridge related commands */ +enum ice_status ice_update_sw_rule_bridge_mode(struct ice_hw *hw); enum ice_status ice_add_mac(struct ice_hw *hw, struct list_head *m_lst); enum ice_status ice_remove_mac(struct ice_hw *hw, struct list_head *m_lst); void ice_remove_vsi_fltr(struct ice_hw *hw, u16 vsi_id); @@ -158,4 +178,8 @@ enum ice_status ice_remove_vlan(struct ice_hw *hw, struct list_head *v_list); enum ice_status ice_cfg_dflt_vsi(struct ice_hw *hw, u16 vsi_id, bool set, u8 direction); +enum ice_status ice_replay_all_fltr(struct ice_hw *hw); + +enum ice_status ice_init_def_sw_recp(struct ice_hw *hw); + #endif /* _ICE_SWITCH_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 6481e3d86374..5dae968d853e 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -251,6 +251,7 @@ int ice_setup_tx_ring(struct ice_ring *tx_ring) tx_ring->next_to_use = 0; tx_ring->next_to_clean = 0; + tx_ring->tx_stats.prev_pkt = -1; return 0; err: diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index 567067b650c4..839fd9ff6043 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -71,6 +71,7 @@ struct ice_txq_stats { u64 restart_q; u64 tx_busy; u64 tx_linearize; + int prev_pkt; /* negative if no pending Tx descriptors */ }; struct ice_rxq_stats { @@ -143,7 +144,7 @@ struct ice_ring { u16 next_to_use; u16 next_to_clean; - bool ring_active; /* is ring online or not */ + u8 ring_active; /* is ring online or not */ /* stats structs */ struct ice_q_stats stats; diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index 99c8a9a71b5e..e681804be4d4 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -34,10 +34,15 @@ static inline bool ice_is_tc_ena(u8 bitmap, u8 tc) enum ice_aq_res_ids { ICE_NVM_RES_ID = 1, ICE_SPD_RES_ID, - ICE_GLOBAL_CFG_LOCK_RES_ID, - ICE_CHANGE_LOCK_RES_ID + ICE_CHANGE_LOCK_RES_ID, + ICE_GLOBAL_CFG_LOCK_RES_ID }; +/* FW update timeout definitions are in milliseconds */ +#define ICE_NVM_TIMEOUT 180000 +#define ICE_CHANGE_LOCK_TIMEOUT 1000 +#define ICE_GLOBAL_CFG_LOCK_TIMEOUT 3000 + enum ice_aq_res_access_type { ICE_RES_READ = 1, ICE_RES_WRITE @@ -83,7 +88,7 @@ struct ice_link_status { u64 phy_type_low; u16 max_frame_size; u16 link_speed; - bool lse_ena; /* Link Status Event notification */ + u8 lse_ena; /* Link Status Event notification */ u8 link_info; u8 an_info; u8 ext_info; @@ -101,7 +106,7 @@ struct ice_phy_info { struct ice_link_status link_info_old; u64 phy_type_low; enum ice_media_type media_type; - bool get_link_info; + u8 get_link_info; }; /* Common HW capabilities for SW use */ @@ -144,9 +149,10 @@ struct ice_mac_info { /* Various RESET request, These are not tied with HW reset types */ enum ice_reset_req { - ICE_RESET_PFR = 0, - ICE_RESET_CORER = 1, - ICE_RESET_GLOBR = 2, + ICE_RESET_INVAL = 0, + ICE_RESET_PFR = 1, + ICE_RESET_CORER = 2, + ICE_RESET_GLOBR = 3, }; /* Bus parameters */ @@ -167,7 +173,7 @@ struct ice_nvm_info { u32 oem_ver; /* OEM version info */ u16 sr_words; /* Shadow RAM size in words */ u16 ver; /* NVM package version */ - bool blank_nvm_mode; /* is NVM empty (no FW present) */ + u8 blank_nvm_mode; /* is NVM empty (no FW present) */ }; /* Max number of port to queue branches w.r.t topology */ @@ -181,7 +187,7 @@ struct ice_sched_node { struct ice_aqc_txsched_elem_data info; u32 agg_id; /* aggregator group id */ u16 vsi_id; - bool in_use; /* suspended or in use */ + u8 in_use; /* suspended or in use */ u8 tx_sched_layer; /* Logical Layer (1-9) */ u8 num_children; u8 tc_num; @@ -204,6 +210,7 @@ enum ice_agg_type { }; #define ICE_SCHED_DFLT_RL_PROF_ID 0 +#define ICE_SCHED_DFLT_BW_WT 1 /* vsi type list entry to locate corresponding vsi/ag nodes */ struct ice_sched_vsi_info { @@ -218,7 +225,7 @@ struct ice_sched_vsi_info { struct ice_sched_tx_policy { u16 max_num_vsis; u8 max_num_lan_qs_per_tc[ICE_MAX_TRAFFIC_CLASS]; - bool rdma_ena; + u8 rdma_ena; }; struct ice_port_info { @@ -243,23 +250,30 @@ struct ice_port_info { struct list_head agg_list; /* lists all aggregator */ u8 lport; #define ICE_LPORT_MASK 0xff - bool is_vf; + u8 is_vf; }; struct ice_switch_info { - /* Switch VSI lists to MAC/VLAN translation */ - struct mutex mac_list_lock; /* protect MAC list */ - struct list_head mac_list_head; - struct mutex vlan_list_lock; /* protect VLAN list */ - struct list_head vlan_list_head; - struct mutex eth_m_list_lock; /* protect ethtype list */ - struct list_head eth_m_list_head; - struct mutex promisc_list_lock; /* protect promisc mode list */ - struct list_head promisc_list_head; - struct mutex mac_vlan_list_lock; /* protect MAC-VLAN list */ - struct list_head mac_vlan_list_head; - struct list_head vsi_list_map_head; + struct ice_sw_recipe *recp_list; +}; + +/* FW logging configuration */ +struct ice_fw_log_evnt { + u8 cfg : 4; /* New event enables to configure */ + u8 cur : 4; /* Current/active event enables */ +}; + +struct ice_fw_log_cfg { + u8 cq_en : 1; /* FW logging is enabled via the control queue */ + u8 uart_en : 1; /* FW logging is enabled via UART for all PFs */ + u8 actv_evnts; /* Cumulation of currently enabled log events */ + +#define ICE_FW_LOG_EVNT_INFO (ICE_AQC_FW_LOG_INFO_EN >> ICE_AQC_FW_LOG_EN_S) +#define ICE_FW_LOG_EVNT_INIT (ICE_AQC_FW_LOG_INIT_EN >> ICE_AQC_FW_LOG_EN_S) +#define ICE_FW_LOG_EVNT_FLOW (ICE_AQC_FW_LOG_FLOW_EN >> ICE_AQC_FW_LOG_EN_S) +#define ICE_FW_LOG_EVNT_ERR (ICE_AQC_FW_LOG_ERR_EN >> ICE_AQC_FW_LOG_EN_S) + struct ice_fw_log_evnt evnts[ICE_AQC_FW_LOG_ID_MAX]; }; /* Port hardware description */ @@ -286,8 +300,11 @@ struct ice_hw { u8 flattened_layers; u8 max_cgds; u8 sw_entry_point_layer; + u16 max_children[ICE_AQC_TOPO_MAX_LEVEL_NUM]; - bool evb_veb; /* true for VEB, false for VEPA */ + struct ice_vsi_ctx *vsi_ctx[ICE_MAX_VSI]; + u8 evb_veb; /* true for VEB, false for VEPA */ + u8 reset_ongoing; /* true if hw is in reset, false otherwise */ struct ice_bus_info bus; struct ice_nvm_info nvm; struct ice_hw_dev_caps dev_caps; /* device capabilities */ @@ -308,6 +325,7 @@ struct ice_hw { u8 fw_patch; /* firmware patch version */ u32 fw_build; /* firmware build number */ + struct ice_fw_log_cfg fw_log; /* minimum allowed value for different speeds */ #define ICE_ITR_GRAN_MIN_200 1 #define ICE_ITR_GRAN_MIN_100 1 @@ -318,7 +336,7 @@ struct ice_hw { u8 itr_gran_100; u8 itr_gran_50; u8 itr_gran_25; - bool ucast_shared; /* true if VSIs can share unicast addr */ + u8 ucast_shared; /* true if VSIs can share unicast addr */ }; diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index f92f7918112d..5acf3b743876 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -1649,7 +1649,7 @@ static int igb_integrated_phy_loopback(struct igb_adapter *adapter) if (hw->phy.type == e1000_phy_m88) igb_phy_disable_receiver(adapter); - mdelay(500); + msleep(500); return 0; } diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index d03c2f0d7592..c18e79112cad 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -243,7 +243,7 @@ static struct pci_driver igb_driver = { MODULE_AUTHOR("Intel Corporation, <e1000-devel@lists.sourceforge.net>"); MODULE_DESCRIPTION("Intel(R) Gigabit Ethernet Network Driver"); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); MODULE_VERSION(DRV_VERSION); #define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV|NETIF_MSG_PROBE|NETIF_MSG_LINK) @@ -3873,7 +3873,7 @@ static int igb_sw_init(struct igb_adapter *adapter) adapter->mac_table = kcalloc(hw->mac.rar_entry_count, sizeof(struct igb_mac_addr), - GFP_ATOMIC); + GFP_KERNEL); if (!adapter->mac_table) return -ENOMEM; @@ -3883,7 +3883,7 @@ static int igb_sw_init(struct igb_adapter *adapter) /* Setup and initialize a copy of the hw vlan table array */ adapter->shadow_vfta = kcalloc(E1000_VLAN_FILTER_TBL_SIZE, sizeof(u32), - GFP_ATOMIC); + GFP_KERNEL); if (!adapter->shadow_vfta) return -ENOMEM; @@ -5816,7 +5816,8 @@ static void igb_tx_csum(struct igb_ring *tx_ring, struct igb_tx_buffer *first) if (skb->ip_summed != CHECKSUM_PARTIAL) { csum_failed: - if (!(first->tx_flags & IGB_TX_FLAGS_VLAN)) + if (!(first->tx_flags & IGB_TX_FLAGS_VLAN) && + !tx_ring->launchtime_enable) return; goto no_csum; } diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index e0c989ffb2b3..820d49eb41ab 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -3011,7 +3011,7 @@ module_exit(igbvf_exit_module); MODULE_AUTHOR("Intel Corporation, <e1000-devel@lists.sourceforge.net>"); MODULE_DESCRIPTION("Intel(R) Gigabit Virtual Function Network Driver"); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); MODULE_VERSION(DRV_VERSION); /* netdev.c */ diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c index 43664adf7a3c..4bb89587cd6a 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c @@ -107,7 +107,7 @@ static struct pci_driver ixgb_driver = { MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION("Intel(R) PRO/10GbE Network Driver"); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); MODULE_VERSION(DRV_VERSION); #define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV|NETIF_MSG_PROBE|NETIF_MSG_LINK) @@ -771,14 +771,13 @@ ixgb_setup_rx_resources(struct ixgb_adapter *adapter) rxdr->size = rxdr->count * sizeof(struct ixgb_rx_desc); rxdr->size = ALIGN(rxdr->size, 4096); - rxdr->desc = dma_alloc_coherent(&pdev->dev, rxdr->size, &rxdr->dma, - GFP_KERNEL); + rxdr->desc = dma_zalloc_coherent(&pdev->dev, rxdr->size, &rxdr->dma, + GFP_KERNEL); if (!rxdr->desc) { vfree(rxdr->buffer_info); return -ENOMEM; } - memset(rxdr->desc, 0, rxdr->size); rxdr->next_to_clean = 0; rxdr->next_to_use = 0; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index 4fc906c6166b..5c6fd42e90ed 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -605,6 +605,7 @@ struct ixgbe_adapter { #define IXGBE_FLAG2_EEE_ENABLED BIT(15) #define IXGBE_FLAG2_RX_LEGACY BIT(16) #define IXGBE_FLAG2_IPSEC_ENABLED BIT(17) +#define IXGBE_FLAG2_VF_IPSEC_ENABLED BIT(18) /* Tx fast path data */ int num_tx_queues; @@ -1003,15 +1004,24 @@ void ixgbe_ipsec_rx(struct ixgbe_ring *rx_ring, struct sk_buff *skb); int ixgbe_ipsec_tx(struct ixgbe_ring *tx_ring, struct ixgbe_tx_buffer *first, struct ixgbe_ipsec_tx_data *itd); +void ixgbe_ipsec_vf_clear(struct ixgbe_adapter *adapter, u32 vf); +int ixgbe_ipsec_vf_add_sa(struct ixgbe_adapter *adapter, u32 *mbuf, u32 vf); +int ixgbe_ipsec_vf_del_sa(struct ixgbe_adapter *adapter, u32 *mbuf, u32 vf); #else -static inline void ixgbe_init_ipsec_offload(struct ixgbe_adapter *adapter) { }; -static inline void ixgbe_stop_ipsec_offload(struct ixgbe_adapter *adapter) { }; -static inline void ixgbe_ipsec_restore(struct ixgbe_adapter *adapter) { }; +static inline void ixgbe_init_ipsec_offload(struct ixgbe_adapter *adapter) { } +static inline void ixgbe_stop_ipsec_offload(struct ixgbe_adapter *adapter) { } +static inline void ixgbe_ipsec_restore(struct ixgbe_adapter *adapter) { } static inline void ixgbe_ipsec_rx(struct ixgbe_ring *rx_ring, union ixgbe_adv_rx_desc *rx_desc, - struct sk_buff *skb) { }; + struct sk_buff *skb) { } static inline int ixgbe_ipsec_tx(struct ixgbe_ring *tx_ring, struct ixgbe_tx_buffer *first, - struct ixgbe_ipsec_tx_data *itd) { return 0; }; + struct ixgbe_ipsec_tx_data *itd) { return 0; } +static inline void ixgbe_ipsec_vf_clear(struct ixgbe_adapter *adapter, + u32 vf) { } +static inline int ixgbe_ipsec_vf_add_sa(struct ixgbe_adapter *adapter, + u32 *mbuf, u32 vf) { return -EACCES; } +static inline int ixgbe_ipsec_vf_del_sa(struct ixgbe_adapter *adapter, + u32 *mbuf, u32 vf) { return -EACCES; } #endif /* CONFIG_XFRM_OFFLOAD */ #endif /* _IXGBE_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index 0bd1294ba517..970f71d5da04 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -3485,6 +3485,17 @@ void ixgbe_set_vlan_anti_spoofing(struct ixgbe_hw *hw, bool enable, int vf) } /** + * ixgbe_fw_recovery_mode - Check if in FW NVM recovery mode + * @hw: pointer to hardware structure + */ +bool ixgbe_fw_recovery_mode(struct ixgbe_hw *hw) +{ + if (hw->mac.ops.fw_recovery_mode) + return hw->mac.ops.fw_recovery_mode(hw); + return false; +} + +/** * ixgbe_get_device_caps_generic - Get additional device capabilities * @hw: pointer to hardware structure * @device_caps: the EEPROM word with the extra device capabilities diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index e5a8461fe6a9..732b1e6ecc43 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -136,6 +136,8 @@ static const char ixgbe_gstrings_test[][ETH_GSTRING_LEN] = { static const char ixgbe_priv_flags_strings[][ETH_GSTRING_LEN] = { #define IXGBE_PRIV_FLAGS_LEGACY_RX BIT(0) "legacy-rx", +#define IXGBE_PRIV_FLAGS_VF_IPSEC_EN BIT(1) + "vf-ipsec", }; #define IXGBE_PRIV_FLAGS_STR_LEN ARRAY_SIZE(ixgbe_priv_flags_strings) @@ -3409,6 +3411,9 @@ static u32 ixgbe_get_priv_flags(struct net_device *netdev) if (adapter->flags2 & IXGBE_FLAG2_RX_LEGACY) priv_flags |= IXGBE_PRIV_FLAGS_LEGACY_RX; + if (adapter->flags2 & IXGBE_FLAG2_VF_IPSEC_ENABLED) + priv_flags |= IXGBE_PRIV_FLAGS_VF_IPSEC_EN; + return priv_flags; } @@ -3421,6 +3426,10 @@ static int ixgbe_set_priv_flags(struct net_device *netdev, u32 priv_flags) if (priv_flags & IXGBE_PRIV_FLAGS_LEGACY_RX) flags2 |= IXGBE_FLAG2_RX_LEGACY; + flags2 &= ~IXGBE_FLAG2_VF_IPSEC_ENABLED; + if (priv_flags & IXGBE_PRIV_FLAGS_VF_IPSEC_EN) + flags2 |= IXGBE_FLAG2_VF_IPSEC_ENABLED; + if (flags2 != adapter->flags2) { adapter->flags2 = flags2; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c index 94b3165ff543..ccd852ad62a4 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c @@ -192,7 +192,7 @@ static int ixgbe_fcoe_ddp_setup(struct net_device *netdev, u16 xid, } /* alloc the udl from per cpu ddp pool */ - ddp->udl = dma_pool_alloc(ddp_pool->pool, GFP_ATOMIC, &ddp->udp); + ddp->udl = dma_pool_alloc(ddp_pool->pool, GFP_KERNEL, &ddp->udp); if (!ddp->udl) { e_err(drv, "failed allocated ddp context\n"); goto out_noddp_unmap; @@ -760,7 +760,7 @@ int ixgbe_setup_fcoe_ddp_resources(struct ixgbe_adapter *adapter) return 0; /* Extra buffer to be shared by all DDPs for HW work around */ - buffer = kmalloc(IXGBE_FCBUFF_MIN, GFP_ATOMIC); + buffer = kmalloc(IXGBE_FCBUFF_MIN, GFP_KERNEL); if (!buffer) return -ENOMEM; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c index da4322e4daed..fd1b0546fd67 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c @@ -5,6 +5,11 @@ #include <net/xfrm.h> #include <crypto/aead.h> +#define IXGBE_IPSEC_KEY_BITS 160 +static const char aes_gcm_name[] = "rfc4106(gcm(aes))"; + +static void ixgbe_ipsec_del_sa(struct xfrm_state *xs); + /** * ixgbe_ipsec_set_tx_sa - set the Tx SA registers * @hw: hw specific details @@ -113,7 +118,6 @@ static void ixgbe_ipsec_set_rx_ip(struct ixgbe_hw *hw, u16 idx, __be32 addr[]) **/ static void ixgbe_ipsec_clear_hw_tables(struct ixgbe_adapter *adapter) { - struct ixgbe_ipsec *ipsec = adapter->ipsec; struct ixgbe_hw *hw = &adapter->hw; u32 buf[4] = {0, 0, 0, 0}; u16 idx; @@ -132,9 +136,6 @@ static void ixgbe_ipsec_clear_hw_tables(struct ixgbe_adapter *adapter) ixgbe_ipsec_set_tx_sa(hw, idx, buf, 0); ixgbe_ipsec_set_rx_sa(hw, idx, 0, buf, 0, 0, 0); } - - ipsec->num_rx_sa = 0; - ipsec->num_tx_sa = 0; } /** @@ -290,6 +291,13 @@ static void ixgbe_ipsec_start_engine(struct ixgbe_adapter *adapter) /** * ixgbe_ipsec_restore - restore the ipsec HW settings after a reset * @adapter: board private structure + * + * Reload the HW tables from the SW tables after they've been bashed + * by a chip reset. + * + * Any VF entries are removed from the SW and HW tables since either + * (a) the VF also gets reset on PF reset and will ask again for the + * offloads, or (b) the VF has been removed by a change in the num_vfs. **/ void ixgbe_ipsec_restore(struct ixgbe_adapter *adapter) { @@ -305,6 +313,28 @@ void ixgbe_ipsec_restore(struct ixgbe_adapter *adapter) ixgbe_ipsec_clear_hw_tables(adapter); ixgbe_ipsec_start_engine(adapter); + /* reload the Rx and Tx keys */ + for (i = 0; i < IXGBE_IPSEC_MAX_SA_COUNT; i++) { + struct rx_sa *r = &ipsec->rx_tbl[i]; + struct tx_sa *t = &ipsec->tx_tbl[i]; + + if (r->used) { + if (r->mode & IXGBE_RXTXMOD_VF) + ixgbe_ipsec_del_sa(r->xs); + else + ixgbe_ipsec_set_rx_sa(hw, i, r->xs->id.spi, + r->key, r->salt, + r->mode, r->iptbl_ind); + } + + if (t->used) { + if (t->mode & IXGBE_RXTXMOD_VF) + ixgbe_ipsec_del_sa(t->xs); + else + ixgbe_ipsec_set_tx_sa(hw, i, t->key, t->salt); + } + } + /* reload the IP addrs */ for (i = 0; i < IXGBE_IPSEC_MAX_RX_IP_COUNT; i++) { struct rx_ip_sa *ipsa = &ipsec->ip_tbl[i]; @@ -312,20 +342,6 @@ void ixgbe_ipsec_restore(struct ixgbe_adapter *adapter) if (ipsa->used) ixgbe_ipsec_set_rx_ip(hw, i, ipsa->ipaddr); } - - /* reload the Rx and Tx keys */ - for (i = 0; i < IXGBE_IPSEC_MAX_SA_COUNT; i++) { - struct rx_sa *rsa = &ipsec->rx_tbl[i]; - struct tx_sa *tsa = &ipsec->tx_tbl[i]; - - if (rsa->used) - ixgbe_ipsec_set_rx_sa(hw, i, rsa->xs->id.spi, - rsa->key, rsa->salt, - rsa->mode, rsa->iptbl_ind); - - if (tsa->used) - ixgbe_ipsec_set_tx_sa(hw, i, tsa->key, tsa->salt); - } } /** @@ -382,6 +398,8 @@ static struct xfrm_state *ixgbe_ipsec_find_rx_state(struct ixgbe_ipsec *ipsec, rcu_read_lock(); hash_for_each_possible_rcu(ipsec->rx_sa_list, rsa, hlist, (__force u32)spi) { + if (rsa->mode & IXGBE_RXTXMOD_VF) + continue; if (spi == rsa->xs->id.spi && ((ip4 && *daddr == rsa->xs->id.daddr.a4) || (!ip4 && !memcmp(daddr, &rsa->xs->id.daddr.a6, @@ -411,7 +429,6 @@ static int ixgbe_ipsec_parse_proto_keys(struct xfrm_state *xs, struct net_device *dev = xs->xso.dev; unsigned char *key_data; char *alg_name = NULL; - const char aes_gcm_name[] = "rfc4106(gcm(aes))"; int key_len; if (!xs->aead) { @@ -439,9 +456,9 @@ static int ixgbe_ipsec_parse_proto_keys(struct xfrm_state *xs, * we don't need to do any byteswapping. * 160 accounts for 16 byte key and 4 byte salt */ - if (key_len == 160) { + if (key_len == IXGBE_IPSEC_KEY_BITS) { *mysalt = ((u32 *)key_data)[4]; - } else if (key_len != 128) { + } else if (key_len != (IXGBE_IPSEC_KEY_BITS - (sizeof(*mysalt) * 8))) { netdev_err(dev, "IPsec hw offload only supports keys up to 128 bits with a 32 bit salt\n"); return -EINVAL; } else { @@ -676,6 +693,9 @@ static int ixgbe_ipsec_add_sa(struct xfrm_state *xs) } else { struct tx_sa tsa; + if (adapter->num_vfs) + return -EOPNOTSUPP; + /* find the first unused index */ ret = ixgbe_ipsec_find_empty_idx(ipsec, false); if (ret < 0) { @@ -811,6 +831,226 @@ static const struct xfrmdev_ops ixgbe_xfrmdev_ops = { }; /** + * ixgbe_ipsec_vf_clear - clear the tables of data for a VF + * @adapter: board private structure + * @vf: VF id to be removed + **/ +void ixgbe_ipsec_vf_clear(struct ixgbe_adapter *adapter, u32 vf) +{ + struct ixgbe_ipsec *ipsec = adapter->ipsec; + int i; + + /* search rx sa table */ + for (i = 0; i < IXGBE_IPSEC_MAX_SA_COUNT && ipsec->num_rx_sa; i++) { + if (!ipsec->rx_tbl[i].used) + continue; + if (ipsec->rx_tbl[i].mode & IXGBE_RXTXMOD_VF && + ipsec->rx_tbl[i].vf == vf) + ixgbe_ipsec_del_sa(ipsec->rx_tbl[i].xs); + } + + /* search tx sa table */ + for (i = 0; i < IXGBE_IPSEC_MAX_SA_COUNT && ipsec->num_tx_sa; i++) { + if (!ipsec->tx_tbl[i].used) + continue; + if (ipsec->tx_tbl[i].mode & IXGBE_RXTXMOD_VF && + ipsec->tx_tbl[i].vf == vf) + ixgbe_ipsec_del_sa(ipsec->tx_tbl[i].xs); + } +} + +/** + * ixgbe_ipsec_vf_add_sa - translate VF request to SA add + * @adapter: board private structure + * @msgbuf: The message buffer + * @vf: the VF index + * + * Make up a new xs and algorithm info from the data sent by the VF. + * We only need to sketch in just enough to set up the HW offload. + * Put the resulting offload_handle into the return message to the VF. + * + * Returns 0 or error value + **/ +int ixgbe_ipsec_vf_add_sa(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) +{ + struct ixgbe_ipsec *ipsec = adapter->ipsec; + struct xfrm_algo_desc *algo; + struct sa_mbx_msg *sam; + struct xfrm_state *xs; + size_t aead_len; + u16 sa_idx; + u32 pfsa; + int err; + + sam = (struct sa_mbx_msg *)(&msgbuf[1]); + if (!adapter->vfinfo[vf].trusted || + !(adapter->flags2 & IXGBE_FLAG2_VF_IPSEC_ENABLED)) { + e_warn(drv, "VF %d attempted to add an IPsec SA\n", vf); + err = -EACCES; + goto err_out; + } + + /* Tx IPsec offload doesn't seem to work on this + * device, so block these requests for now. + */ + if (!(sam->flags & XFRM_OFFLOAD_INBOUND)) { + err = -EOPNOTSUPP; + goto err_out; + } + + xs = kzalloc(sizeof(*xs), GFP_KERNEL); + if (unlikely(!xs)) { + err = -ENOMEM; + goto err_out; + } + + xs->xso.flags = sam->flags; + xs->id.spi = sam->spi; + xs->id.proto = sam->proto; + xs->props.family = sam->family; + if (xs->props.family == AF_INET6) + memcpy(&xs->id.daddr.a6, sam->addr, sizeof(xs->id.daddr.a6)); + else + memcpy(&xs->id.daddr.a4, sam->addr, sizeof(xs->id.daddr.a4)); + xs->xso.dev = adapter->netdev; + + algo = xfrm_aead_get_byname(aes_gcm_name, IXGBE_IPSEC_AUTH_BITS, 1); + if (unlikely(!algo)) { + err = -ENOENT; + goto err_xs; + } + + aead_len = sizeof(*xs->aead) + IXGBE_IPSEC_KEY_BITS / 8; + xs->aead = kzalloc(aead_len, GFP_KERNEL); + if (unlikely(!xs->aead)) { + err = -ENOMEM; + goto err_xs; + } + + xs->props.ealgo = algo->desc.sadb_alg_id; + xs->geniv = algo->uinfo.aead.geniv; + xs->aead->alg_icv_len = IXGBE_IPSEC_AUTH_BITS; + xs->aead->alg_key_len = IXGBE_IPSEC_KEY_BITS; + memcpy(xs->aead->alg_key, sam->key, sizeof(sam->key)); + memcpy(xs->aead->alg_name, aes_gcm_name, sizeof(aes_gcm_name)); + + /* set up the HW offload */ + err = ixgbe_ipsec_add_sa(xs); + if (err) + goto err_aead; + + pfsa = xs->xso.offload_handle; + if (pfsa < IXGBE_IPSEC_BASE_TX_INDEX) { + sa_idx = pfsa - IXGBE_IPSEC_BASE_RX_INDEX; + ipsec->rx_tbl[sa_idx].vf = vf; + ipsec->rx_tbl[sa_idx].mode |= IXGBE_RXTXMOD_VF; + } else { + sa_idx = pfsa - IXGBE_IPSEC_BASE_TX_INDEX; + ipsec->tx_tbl[sa_idx].vf = vf; + ipsec->tx_tbl[sa_idx].mode |= IXGBE_RXTXMOD_VF; + } + + msgbuf[1] = xs->xso.offload_handle; + + return 0; + +err_aead: + memset(xs->aead, 0, sizeof(*xs->aead)); + kfree(xs->aead); +err_xs: + memset(xs, 0, sizeof(*xs)); + kfree(xs); +err_out: + msgbuf[1] = err; + return err; +} + +/** + * ixgbe_ipsec_vf_del_sa - translate VF request to SA delete + * @adapter: board private structure + * @msgbuf: The message buffer + * @vf: the VF index + * + * Given the offload_handle sent by the VF, look for the related SA table + * entry and use its xs field to call for a delete of the SA. + * + * Note: We silently ignore requests to delete entries that are already + * set to unused because when a VF is set to "DOWN", the PF first + * gets a reset and clears all the VF's entries; then the VF's + * XFRM stack sends individual deletes for each entry, which the + * reset already removed. In the future it might be good to try to + * optimize this so not so many unnecessary delete messages are sent. + * + * Returns 0 or error value + **/ +int ixgbe_ipsec_vf_del_sa(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) +{ + struct ixgbe_ipsec *ipsec = adapter->ipsec; + struct xfrm_state *xs; + u32 pfsa = msgbuf[1]; + u16 sa_idx; + + if (!adapter->vfinfo[vf].trusted) { + e_err(drv, "vf %d attempted to delete an SA\n", vf); + return -EPERM; + } + + if (pfsa < IXGBE_IPSEC_BASE_TX_INDEX) { + struct rx_sa *rsa; + + sa_idx = pfsa - IXGBE_IPSEC_BASE_RX_INDEX; + if (sa_idx >= IXGBE_IPSEC_MAX_SA_COUNT) { + e_err(drv, "vf %d SA index %d out of range\n", + vf, sa_idx); + return -EINVAL; + } + + rsa = &ipsec->rx_tbl[sa_idx]; + + if (!rsa->used) + return 0; + + if (!(rsa->mode & IXGBE_RXTXMOD_VF) || + rsa->vf != vf) { + e_err(drv, "vf %d bad Rx SA index %d\n", vf, sa_idx); + return -ENOENT; + } + + xs = ipsec->rx_tbl[sa_idx].xs; + } else { + struct tx_sa *tsa; + + sa_idx = pfsa - IXGBE_IPSEC_BASE_TX_INDEX; + if (sa_idx >= IXGBE_IPSEC_MAX_SA_COUNT) { + e_err(drv, "vf %d SA index %d out of range\n", + vf, sa_idx); + return -EINVAL; + } + + tsa = &ipsec->tx_tbl[sa_idx]; + + if (!tsa->used) + return 0; + + if (!(tsa->mode & IXGBE_RXTXMOD_VF) || + tsa->vf != vf) { + e_err(drv, "vf %d bad Tx SA index %d\n", vf, sa_idx); + return -ENOENT; + } + + xs = ipsec->tx_tbl[sa_idx].xs; + } + + ixgbe_ipsec_del_sa(xs); + + /* remove the xs that was made-up in the add request */ + memset(xs, 0, sizeof(*xs)); + kfree(xs); + + return 0; +} + +/** * ixgbe_ipsec_tx - setup Tx flags for ipsec offload * @tx_ring: outgoing context * @first: current data packet diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.h index 9ef7faadda69..d2b64ff8eb4e 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.h @@ -26,6 +26,7 @@ enum ixgbe_ipsec_tbl_sel { #define IXGBE_RXMOD_PROTO_ESP 0x00000004 #define IXGBE_RXMOD_DECRYPT 0x00000008 #define IXGBE_RXMOD_IPV6 0x00000010 +#define IXGBE_RXTXMOD_VF 0x00000020 struct rx_sa { struct hlist_node hlist; @@ -37,6 +38,7 @@ struct rx_sa { u8 iptbl_ind; bool used; bool decrypt; + u32 vf; }; struct rx_ip_sa { @@ -49,8 +51,10 @@ struct tx_sa { struct xfrm_state *xs; u32 key[4]; u32 salt; + u32 mode; bool encrypt; bool used; + u32 vf; }; struct ixgbe_ipsec_tx_data { @@ -67,4 +71,13 @@ struct ixgbe_ipsec { struct tx_sa *tx_tbl; DECLARE_HASHTABLE(rx_sa_list, 10); }; + +struct sa_mbx_msg { + __be32 spi; + u8 flags; + u8 proto; + u16 family; + __be32 addr[4]; + u32 key[5]; +}; #endif /* _IXGBE_IPSEC_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 447098005490..27a8546c88b2 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -159,7 +159,7 @@ MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)"); MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION("Intel(R) 10 Gigabit PCI Express Network Driver"); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); MODULE_VERSION(DRV_VERSION); static struct workqueue_struct *ixgbe_wq; @@ -6201,7 +6201,7 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter, adapter->mac_table = kcalloc(hw->mac.num_rar_entries, sizeof(struct ixgbe_mac_addr), - GFP_ATOMIC); + GFP_KERNEL); if (!adapter->mac_table) return -ENOMEM; @@ -6620,8 +6620,18 @@ static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu) struct ixgbe_adapter *adapter = netdev_priv(netdev); if (adapter->xdp_prog) { - e_warn(probe, "MTU cannot be changed while XDP program is loaded\n"); - return -EPERM; + int new_frame_size = new_mtu + ETH_HLEN + ETH_FCS_LEN + + VLAN_HLEN; + int i; + + for (i = 0; i < adapter->num_rx_queues; i++) { + struct ixgbe_ring *ring = adapter->rx_ring[i]; + + if (new_frame_size > ixgbe_rx_bufsz(ring)) { + e_warn(probe, "Requested MTU size is not supported with XDP\n"); + return -EINVAL; + } + } } /* @@ -7765,6 +7775,33 @@ static void ixgbe_reset_subtask(struct ixgbe_adapter *adapter) } /** + * ixgbe_check_fw_error - Check firmware for errors + * @adapter: the adapter private structure + * + * Check firmware errors in register FWSM + */ +static bool ixgbe_check_fw_error(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 fwsm; + + /* read fwsm.ext_err_ind register and log errors */ + fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM(hw)); + + if (fwsm & IXGBE_FWSM_EXT_ERR_IND_MASK || + !(fwsm & IXGBE_FWSM_FW_VAL_BIT)) + e_dev_warn("Warning firmware error detected FWSM: 0x%08X\n", + fwsm); + + if (hw->mac.ops.fw_recovery_mode && hw->mac.ops.fw_recovery_mode(hw)) { + e_dev_err("Firmware recovery mode detected. Limiting functionality. Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware recovery mode.\n"); + return true; + } + + return false; +} + +/** * ixgbe_service_task - manages and runs subtasks * @work: pointer to work_struct containing our data **/ @@ -7782,6 +7819,15 @@ static void ixgbe_service_task(struct work_struct *work) ixgbe_service_event_complete(adapter); return; } + if (ixgbe_check_fw_error(adapter)) { + if (!test_bit(__IXGBE_DOWN, &adapter->state)) { + rtnl_lock(); + unregister_netdev(adapter->netdev); + rtnl_unlock(); + } + ixgbe_service_event_complete(adapter); + return; + } if (adapter->flags2 & IXGBE_FLAG2_UDP_TUN_REREG_NEEDED) { rtnl_lock(); adapter->flags2 &= ~IXGBE_FLAG2_UDP_TUN_REREG_NEEDED; @@ -8983,6 +9029,15 @@ int ixgbe_setup_tc(struct net_device *dev, u8 tc) #ifdef CONFIG_IXGBE_DCB if (tc) { + if (adapter->xdp_prog) { + e_warn(probe, "DCB is not supported with XDP\n"); + + ixgbe_init_interrupt_scheme(adapter); + if (netif_running(dev)) + ixgbe_open(dev); + return -EINVAL; + } + netdev_set_num_tc(dev, tc); ixgbe_set_prio_tc_map(adapter); @@ -9171,14 +9226,12 @@ static int parse_tc_actions(struct ixgbe_adapter *adapter, struct tcf_exts *exts, u64 *action, u8 *queue) { const struct tc_action *a; - LIST_HEAD(actions); + int i; if (!tcf_exts_has_actions(exts)) return -EINVAL; - tcf_exts_to_list(exts, &actions); - list_for_each_entry(a, &actions, list) { - + tcf_exts_for_each_action(i, a, exts) { /* Drop action */ if (is_tcf_gact_shot(a)) { *action = IXGBE_FDIR_DROP_QUEUE; @@ -9936,6 +9989,11 @@ static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev) int tcs = adapter->hw_tcs ? : 1; int pool, err; + if (adapter->xdp_prog) { + e_warn(probe, "L2FW offload is not supported with XDP\n"); + return ERR_PTR(-EINVAL); + } + /* The hardware supported by ixgbe only filters on the destination MAC * address. In order to avoid issues we only support offloading modes * where the hardware can actually provide the functionality. @@ -10694,6 +10752,11 @@ skip_sriov: if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) netdev->features |= NETIF_F_LRO; + if (ixgbe_check_fw_error(adapter)) { + err = -EIO; + goto err_sw_init; + } + /* make sure the EEPROM is good */ if (hw->eeprom.ops.validate_checksum(hw, NULL) < 0) { e_dev_err("The EEPROM Checksum Is Not Valid\n"); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h index e085b6520dac..a148534d7256 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h @@ -50,6 +50,7 @@ enum ixgbe_pfvf_api_rev { ixgbe_mbox_api_11, /* API version 1.1, linux/freebsd VF driver */ ixgbe_mbox_api_12, /* API version 1.2, linux/freebsd VF driver */ ixgbe_mbox_api_13, /* API version 1.3, linux/freebsd VF driver */ + ixgbe_mbox_api_14, /* API version 1.4, linux/freebsd VF driver */ /* This value should always be last */ ixgbe_mbox_api_unknown, /* indicates that API version is not known */ }; @@ -80,6 +81,10 @@ enum ixgbe_pfvf_api_rev { #define IXGBE_VF_UPDATE_XCAST_MODE 0x0c +/* mailbox API, version 1.4 VF requests */ +#define IXGBE_VF_IPSEC_ADD 0x0d +#define IXGBE_VF_IPSEC_DEL 0x0e + /* length of permanent address message returned from PF */ #define IXGBE_VF_PERMADDR_MSG_LEN 4 /* word in permanent address message with the current multicast type */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index 6f59933cdff7..af25a8fffeb8 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -53,6 +53,11 @@ static int __ixgbe_enable_sriov(struct ixgbe_adapter *adapter, struct ixgbe_hw *hw = &adapter->hw; int i; + if (adapter->xdp_prog) { + e_warn(probe, "SRIOV is not supported with XDP\n"); + return -EINVAL; + } + /* Enable VMDq flag so device will be set in VM mode */ adapter->flags |= IXGBE_FLAG_SRIOV_ENABLED | IXGBE_FLAG_VMDQ_ENABLED; @@ -491,6 +496,7 @@ static s32 ixgbe_set_vf_lpe(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) case ixgbe_mbox_api_11: case ixgbe_mbox_api_12: case ixgbe_mbox_api_13: + case ixgbe_mbox_api_14: /* Version 1.1 supports jumbo frames on VFs if PF has * jumbo frames enabled which means legacy VFs are * disabled @@ -688,8 +694,13 @@ static int ixgbe_set_vf_macvlan(struct ixgbe_adapter *adapter, static inline void ixgbe_vf_reset_event(struct ixgbe_adapter *adapter, u32 vf) { struct ixgbe_hw *hw = &adapter->hw; + struct ixgbe_ring_feature *vmdq = &adapter->ring_feature[RING_F_VMDQ]; struct vf_data_storage *vfinfo = &adapter->vfinfo[vf]; + u32 q_per_pool = __ALIGN_MASK(1, ~vmdq->mask); u8 num_tcs = adapter->hw_tcs; + u32 reg_val; + u32 queue; + u32 word; /* remove VLAN filters beloning to this VF */ ixgbe_clear_vf_vlans(adapter, vf); @@ -718,6 +729,9 @@ static inline void ixgbe_vf_reset_event(struct ixgbe_adapter *adapter, u32 vf) /* reset multicast table array for vf */ adapter->vfinfo[vf].num_vf_mc_hashes = 0; + /* clear any ipsec table info */ + ixgbe_ipsec_vf_clear(adapter, vf); + /* Flush and reset the mta with the new values */ ixgbe_set_rx_mode(adapter->netdev); @@ -726,6 +740,27 @@ static inline void ixgbe_vf_reset_event(struct ixgbe_adapter *adapter, u32 vf) /* reset VF api back to unknown */ adapter->vfinfo[vf].vf_api = ixgbe_mbox_api_10; + + /* Restart each queue for given VF */ + for (queue = 0; queue < q_per_pool; queue++) { + unsigned int reg_idx = (vf * q_per_pool) + queue; + + reg_val = IXGBE_READ_REG(hw, IXGBE_PVFTXDCTL(reg_idx)); + + /* Re-enabling only configured queues */ + if (reg_val) { + reg_val |= IXGBE_TXDCTL_ENABLE; + IXGBE_WRITE_REG(hw, IXGBE_PVFTXDCTL(reg_idx), reg_val); + reg_val &= ~IXGBE_TXDCTL_ENABLE; + IXGBE_WRITE_REG(hw, IXGBE_PVFTXDCTL(reg_idx), reg_val); + } + } + + /* Clear VF's mailbox memory */ + for (word = 0; word < IXGBE_VFMAILBOX_SIZE; word++) + IXGBE_WRITE_REG_ARRAY(hw, IXGBE_PFMBMEM(vf), word, 0); + + IXGBE_WRITE_FLUSH(hw); } static int ixgbe_set_vf_mac(struct ixgbe_adapter *adapter, @@ -969,6 +1004,7 @@ static int ixgbe_negotiate_vf_api(struct ixgbe_adapter *adapter, case ixgbe_mbox_api_11: case ixgbe_mbox_api_12: case ixgbe_mbox_api_13: + case ixgbe_mbox_api_14: adapter->vfinfo[vf].vf_api = api; return 0; default: @@ -994,6 +1030,7 @@ static int ixgbe_get_vf_queues(struct ixgbe_adapter *adapter, case ixgbe_mbox_api_11: case ixgbe_mbox_api_12: case ixgbe_mbox_api_13: + case ixgbe_mbox_api_14: break; default: return -1; @@ -1034,6 +1071,7 @@ static int ixgbe_get_vf_reta(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) /* verify the PF is supporting the correct API */ switch (adapter->vfinfo[vf].vf_api) { + case ixgbe_mbox_api_14: case ixgbe_mbox_api_13: case ixgbe_mbox_api_12: break; @@ -1066,6 +1104,7 @@ static int ixgbe_get_vf_rss_key(struct ixgbe_adapter *adapter, /* verify the PF is supporting the correct API */ switch (adapter->vfinfo[vf].vf_api) { + case ixgbe_mbox_api_14: case ixgbe_mbox_api_13: case ixgbe_mbox_api_12: break; @@ -1091,8 +1130,9 @@ static int ixgbe_update_vf_xcast_mode(struct ixgbe_adapter *adapter, /* promisc introduced in 1.3 version */ if (xcast_mode == IXGBEVF_XCAST_MODE_PROMISC) return -EOPNOTSUPP; - /* Fall threw */ + /* Fall through */ case ixgbe_mbox_api_13: + case ixgbe_mbox_api_14: break; default: return -EOPNOTSUPP; @@ -1218,6 +1258,12 @@ static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf) case IXGBE_VF_UPDATE_XCAST_MODE: retval = ixgbe_update_vf_xcast_mode(adapter, msgbuf, vf); break; + case IXGBE_VF_IPSEC_ADD: + retval = ixgbe_ipsec_vf_add_sa(adapter, msgbuf, vf); + break; + case IXGBE_VF_IPSEC_DEL: + retval = ixgbe_ipsec_vf_del_sa(adapter, msgbuf, vf); + break; default: e_err(drv, "Unhandled Msg %8.8x\n", msgbuf[0]); retval = IXGBE_ERR_MBX; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h index 44cfb2021145..84f2dba39e36 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h @@ -924,6 +924,9 @@ struct ixgbe_nvm_version { /* Firmware Semaphore Register */ #define IXGBE_FWSM_MODE_MASK 0xE #define IXGBE_FWSM_FW_MODE_PT 0x4 +#define IXGBE_FWSM_FW_NVM_RECOVERY_MODE BIT(5) +#define IXGBE_FWSM_EXT_ERR_IND_MASK 0x01F80000 +#define IXGBE_FWSM_FW_VAL_BIT BIT(15) /* ARC Subsystem registers */ #define IXGBE_HICR 0x15F00 @@ -2518,6 +2521,7 @@ enum { /* Translated register #defines */ #define IXGBE_PVFTDH(P) (0x06010 + (0x40 * (P))) #define IXGBE_PVFTDT(P) (0x06018 + (0x40 * (P))) +#define IXGBE_PVFTXDCTL(P) (0x06028 + (0x40 * (P))) #define IXGBE_PVFTDWBAL(P) (0x06038 + (0x40 * (P))) #define IXGBE_PVFTDWBAH(P) (0x0603C + (0x40 * (P))) @@ -3460,6 +3464,7 @@ struct ixgbe_mac_operations { const char *); s32 (*get_thermal_sensor_data)(struct ixgbe_hw *); s32 (*init_thermal_sensor_thresh)(struct ixgbe_hw *hw); + bool (*fw_recovery_mode)(struct ixgbe_hw *hw); void (*disable_rx)(struct ixgbe_hw *hw); void (*enable_rx)(struct ixgbe_hw *hw); void (*set_source_address_pruning)(struct ixgbe_hw *, bool, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c index a8148c7126e5..10dbaf4f6e80 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c @@ -1247,6 +1247,20 @@ static s32 ixgbe_get_bus_info_X550em(struct ixgbe_hw *hw) return 0; } +/** + * ixgbe_fw_recovery_mode - Check FW NVM recovery mode + * @hw: pointer t hardware structure + * + * Returns true if in FW NVM recovery mode. + */ +static bool ixgbe_fw_recovery_mode_X550(struct ixgbe_hw *hw) +{ + u32 fwsm; + + fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM(hw)); + return !!(fwsm & IXGBE_FWSM_FW_NVM_RECOVERY_MODE); +} + /** ixgbe_disable_rx_x550 - Disable RX unit * * Enables the Rx DMA unit for x550 @@ -3816,6 +3830,7 @@ static s32 ixgbe_write_phy_reg_x550a(struct ixgbe_hw *hw, u32 reg_addr, .enable_rx_buff = &ixgbe_enable_rx_buff_generic, \ .get_thermal_sensor_data = NULL, \ .init_thermal_sensor_thresh = NULL, \ + .fw_recovery_mode = &ixgbe_fw_recovery_mode_X550, \ .enable_rx = &ixgbe_enable_rx_generic, \ .disable_rx = &ixgbe_disable_rx_x550, \ diff --git a/drivers/net/ethernet/intel/ixgbevf/Makefile b/drivers/net/ethernet/intel/ixgbevf/Makefile index aba1e6a37a6a..297d0f0858b5 100644 --- a/drivers/net/ethernet/intel/ixgbevf/Makefile +++ b/drivers/net/ethernet/intel/ixgbevf/Makefile @@ -10,4 +10,5 @@ ixgbevf-objs := vf.o \ mbx.o \ ethtool.o \ ixgbevf_main.o +ixgbevf-$(CONFIG_XFRM_OFFLOAD) += ipsec.o diff --git a/drivers/net/ethernet/intel/ixgbevf/defines.h b/drivers/net/ethernet/intel/ixgbevf/defines.h index 700d8eb2f6f8..6bace746eaac 100644 --- a/drivers/net/ethernet/intel/ixgbevf/defines.h +++ b/drivers/net/ethernet/intel/ixgbevf/defines.h @@ -133,9 +133,14 @@ typedef u32 ixgbe_link_speed; #define IXGBE_RXDADV_STAT_FCSTAT_NODDP 0x00000010 /* 01: Ctxt w/o DDP */ #define IXGBE_RXDADV_STAT_FCSTAT_FCPRSP 0x00000020 /* 10: Recv. FCP_RSP */ #define IXGBE_RXDADV_STAT_FCSTAT_DDP 0x00000030 /* 11: Ctxt w/ DDP */ +#define IXGBE_RXDADV_STAT_SECP 0x00020000 /* IPsec/MACsec pkt found */ #define IXGBE_RXDADV_RSSTYPE_MASK 0x0000000F #define IXGBE_RXDADV_PKTTYPE_MASK 0x0000FFF0 +#define IXGBE_RXDADV_PKTTYPE_IPV4 0x00000010 /* IPv4 hdr present */ +#define IXGBE_RXDADV_PKTTYPE_IPV6 0x00000040 /* IPv6 hdr present */ +#define IXGBE_RXDADV_PKTTYPE_IPSEC_ESP 0x00001000 /* IPSec ESP */ +#define IXGBE_RXDADV_PKTTYPE_IPSEC_AH 0x00002000 /* IPSec AH */ #define IXGBE_RXDADV_PKTTYPE_MASK_EX 0x0001FFF0 #define IXGBE_RXDADV_HDRBUFLEN_MASK 0x00007FE0 #define IXGBE_RXDADV_RSCCNT_MASK 0x001E0000 @@ -229,7 +234,7 @@ union ixgbe_adv_rx_desc { /* Context descriptors */ struct ixgbe_adv_tx_context_desc { __le32 vlan_macip_lens; - __le32 seqnum_seed; + __le32 fceof_saidx; __le32 type_tucmd_mlhl; __le32 mss_l4len_idx; }; @@ -250,9 +255,12 @@ struct ixgbe_adv_tx_context_desc { #define IXGBE_ADVTXD_TUCMD_L4T_UDP 0x00000000 /* L4 Packet TYPE of UDP */ #define IXGBE_ADVTXD_TUCMD_L4T_TCP 0x00000800 /* L4 Packet TYPE of TCP */ #define IXGBE_ADVTXD_TUCMD_L4T_SCTP 0x00001000 /* L4 Packet TYPE of SCTP */ +#define IXGBE_ADVTXD_TUCMD_IPSEC_TYPE_ESP 0x00002000 /* IPSec Type ESP */ +#define IXGBE_ADVTXD_TUCMD_IPSEC_ENCRYPT_EN 0x00004000 /* ESP Encrypt Enable */ #define IXGBE_ADVTXD_IDX_SHIFT 4 /* Adv desc Index shift */ #define IXGBE_ADVTXD_CC 0x00000080 /* Check Context */ #define IXGBE_ADVTXD_POPTS_SHIFT 8 /* Adv desc POPTS shift */ +#define IXGBE_ADVTXD_POPTS_IPSEC 0x00000400 /* IPSec offload request */ #define IXGBE_ADVTXD_POPTS_IXSM (IXGBE_TXD_POPTS_IXSM << \ IXGBE_ADVTXD_POPTS_SHIFT) #define IXGBE_ADVTXD_POPTS_TXSM (IXGBE_TXD_POPTS_TXSM << \ diff --git a/drivers/net/ethernet/intel/ixgbevf/ethtool.c b/drivers/net/ethernet/intel/ixgbevf/ethtool.c index 631c91046f39..5399787e07af 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ethtool.c +++ b/drivers/net/ethernet/intel/ixgbevf/ethtool.c @@ -55,6 +55,8 @@ static struct ixgbe_stats ixgbevf_gstrings_stats[] = { IXGBEVF_STAT("alloc_rx_page", alloc_rx_page), IXGBEVF_STAT("alloc_rx_page_failed", alloc_rx_page_failed), IXGBEVF_STAT("alloc_rx_buff_failed", alloc_rx_buff_failed), + IXGBEVF_STAT("tx_ipsec", tx_ipsec), + IXGBEVF_STAT("rx_ipsec", rx_ipsec), }; #define IXGBEVF_QUEUE_STATS_LEN ( \ diff --git a/drivers/net/ethernet/intel/ixgbevf/ipsec.c b/drivers/net/ethernet/intel/ixgbevf/ipsec.c new file mode 100644 index 000000000000..997cea675a37 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbevf/ipsec.c @@ -0,0 +1,673 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2018 Oracle and/or its affiliates. All rights reserved. */ + +#include "ixgbevf.h" +#include <net/xfrm.h> +#include <crypto/aead.h> + +#define IXGBE_IPSEC_KEY_BITS 160 +static const char aes_gcm_name[] = "rfc4106(gcm(aes))"; + +/** + * ixgbevf_ipsec_set_pf_sa - ask the PF to set up an SA + * @adapter: board private structure + * @xs: xfrm info to be sent to the PF + * + * Returns: positive offload handle from the PF, or negative error code + **/ +static int ixgbevf_ipsec_set_pf_sa(struct ixgbevf_adapter *adapter, + struct xfrm_state *xs) +{ + u32 msgbuf[IXGBE_VFMAILBOX_SIZE] = { 0 }; + struct ixgbe_hw *hw = &adapter->hw; + struct sa_mbx_msg *sam; + u16 msglen; + int ret; + + /* send the important bits to the PF */ + sam = (struct sa_mbx_msg *)(&msgbuf[1]); + sam->flags = xs->xso.flags; + sam->spi = xs->id.spi; + sam->proto = xs->id.proto; + sam->family = xs->props.family; + + if (xs->props.family == AF_INET6) + memcpy(sam->addr, &xs->id.daddr.a6, sizeof(xs->id.daddr.a6)); + else + memcpy(sam->addr, &xs->id.daddr.a4, sizeof(xs->id.daddr.a4)); + memcpy(sam->key, xs->aead->alg_key, sizeof(sam->key)); + + msgbuf[0] = IXGBE_VF_IPSEC_ADD; + msglen = sizeof(*sam) + sizeof(msgbuf[0]); + + spin_lock_bh(&adapter->mbx_lock); + + ret = hw->mbx.ops.write_posted(hw, msgbuf, msglen); + if (ret) + goto out; + + msglen = sizeof(msgbuf[0]) * 2; + ret = hw->mbx.ops.read_posted(hw, msgbuf, msglen); + if (ret) + goto out; + + ret = (int)msgbuf[1]; + if (msgbuf[0] & IXGBE_VT_MSGTYPE_NACK && ret >= 0) + ret = -1; + +out: + spin_unlock_bh(&adapter->mbx_lock); + + return ret; +} + +/** + * ixgbevf_ipsec_del_pf_sa - ask the PF to delete an SA + * @adapter: board private structure + * @pfsa: sa index returned from PF when created, -1 for all + * + * Returns: 0 on success, or negative error code + **/ +static int ixgbevf_ipsec_del_pf_sa(struct ixgbevf_adapter *adapter, int pfsa) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 msgbuf[2]; + int err; + + memset(msgbuf, 0, sizeof(msgbuf)); + msgbuf[0] = IXGBE_VF_IPSEC_DEL; + msgbuf[1] = (u32)pfsa; + + spin_lock_bh(&adapter->mbx_lock); + + err = hw->mbx.ops.write_posted(hw, msgbuf, sizeof(msgbuf)); + if (err) + goto out; + + err = hw->mbx.ops.read_posted(hw, msgbuf, sizeof(msgbuf)); + if (err) + goto out; + +out: + spin_unlock_bh(&adapter->mbx_lock); + return err; +} + +/** + * ixgbevf_ipsec_restore - restore the IPsec HW settings after a reset + * @adapter: board private structure + * + * Reload the HW tables from the SW tables after they've been bashed + * by a chip reset. While we're here, make sure any stale VF data is + * removed, since we go through reset when num_vfs changes. + **/ +void ixgbevf_ipsec_restore(struct ixgbevf_adapter *adapter) +{ + struct ixgbevf_ipsec *ipsec = adapter->ipsec; + struct net_device *netdev = adapter->netdev; + int i; + + if (!(adapter->netdev->features & NETIF_F_HW_ESP)) + return; + + /* reload the Rx and Tx keys */ + for (i = 0; i < IXGBE_IPSEC_MAX_SA_COUNT; i++) { + struct rx_sa *r = &ipsec->rx_tbl[i]; + struct tx_sa *t = &ipsec->tx_tbl[i]; + int ret; + + if (r->used) { + ret = ixgbevf_ipsec_set_pf_sa(adapter, r->xs); + if (ret < 0) + netdev_err(netdev, "reload rx_tbl[%d] failed = %d\n", + i, ret); + } + + if (t->used) { + ret = ixgbevf_ipsec_set_pf_sa(adapter, t->xs); + if (ret < 0) + netdev_err(netdev, "reload tx_tbl[%d] failed = %d\n", + i, ret); + } + } +} + +/** + * ixgbevf_ipsec_find_empty_idx - find the first unused security parameter index + * @ipsec: pointer to IPsec struct + * @rxtable: true if we need to look in the Rx table + * + * Returns the first unused index in either the Rx or Tx SA table + **/ +static +int ixgbevf_ipsec_find_empty_idx(struct ixgbevf_ipsec *ipsec, bool rxtable) +{ + u32 i; + + if (rxtable) { + if (ipsec->num_rx_sa == IXGBE_IPSEC_MAX_SA_COUNT) + return -ENOSPC; + + /* search rx sa table */ + for (i = 0; i < IXGBE_IPSEC_MAX_SA_COUNT; i++) { + if (!ipsec->rx_tbl[i].used) + return i; + } + } else { + if (ipsec->num_tx_sa == IXGBE_IPSEC_MAX_SA_COUNT) + return -ENOSPC; + + /* search tx sa table */ + for (i = 0; i < IXGBE_IPSEC_MAX_SA_COUNT; i++) { + if (!ipsec->tx_tbl[i].used) + return i; + } + } + + return -ENOSPC; +} + +/** + * ixgbevf_ipsec_find_rx_state - find the state that matches + * @ipsec: pointer to IPsec struct + * @daddr: inbound address to match + * @proto: protocol to match + * @spi: SPI to match + * @ip4: true if using an IPv4 address + * + * Returns a pointer to the matching SA state information + **/ +static +struct xfrm_state *ixgbevf_ipsec_find_rx_state(struct ixgbevf_ipsec *ipsec, + __be32 *daddr, u8 proto, + __be32 spi, bool ip4) +{ + struct xfrm_state *ret = NULL; + struct rx_sa *rsa; + + rcu_read_lock(); + hash_for_each_possible_rcu(ipsec->rx_sa_list, rsa, hlist, + (__force u32)spi) { + if (spi == rsa->xs->id.spi && + ((ip4 && *daddr == rsa->xs->id.daddr.a4) || + (!ip4 && !memcmp(daddr, &rsa->xs->id.daddr.a6, + sizeof(rsa->xs->id.daddr.a6)))) && + proto == rsa->xs->id.proto) { + ret = rsa->xs; + xfrm_state_hold(ret); + break; + } + } + rcu_read_unlock(); + return ret; +} + +/** + * ixgbevf_ipsec_parse_proto_keys - find the key and salt based on the protocol + * @xs: pointer to xfrm_state struct + * @mykey: pointer to key array to populate + * @mysalt: pointer to salt value to populate + * + * This copies the protocol keys and salt to our own data tables. The + * 82599 family only supports the one algorithm. + **/ +static int ixgbevf_ipsec_parse_proto_keys(struct xfrm_state *xs, + u32 *mykey, u32 *mysalt) +{ + struct net_device *dev = xs->xso.dev; + unsigned char *key_data; + char *alg_name = NULL; + int key_len; + + if (!xs->aead) { + netdev_err(dev, "Unsupported IPsec algorithm\n"); + return -EINVAL; + } + + if (xs->aead->alg_icv_len != IXGBE_IPSEC_AUTH_BITS) { + netdev_err(dev, "IPsec offload requires %d bit authentication\n", + IXGBE_IPSEC_AUTH_BITS); + return -EINVAL; + } + + key_data = &xs->aead->alg_key[0]; + key_len = xs->aead->alg_key_len; + alg_name = xs->aead->alg_name; + + if (strcmp(alg_name, aes_gcm_name)) { + netdev_err(dev, "Unsupported IPsec algorithm - please use %s\n", + aes_gcm_name); + return -EINVAL; + } + + /* The key bytes come down in a big endian array of bytes, so + * we don't need to do any byte swapping. + * 160 accounts for 16 byte key and 4 byte salt + */ + if (key_len > IXGBE_IPSEC_KEY_BITS) { + *mysalt = ((u32 *)key_data)[4]; + } else if (key_len == IXGBE_IPSEC_KEY_BITS) { + *mysalt = 0; + } else { + netdev_err(dev, "IPsec hw offload only supports keys up to 128 bits with a 32 bit salt\n"); + return -EINVAL; + } + memcpy(mykey, key_data, 16); + + return 0; +} + +/** + * ixgbevf_ipsec_add_sa - program device with a security association + * @xs: pointer to transformer state struct + **/ +static int ixgbevf_ipsec_add_sa(struct xfrm_state *xs) +{ + struct net_device *dev = xs->xso.dev; + struct ixgbevf_adapter *adapter = netdev_priv(dev); + struct ixgbevf_ipsec *ipsec = adapter->ipsec; + u16 sa_idx; + int ret; + + if (xs->id.proto != IPPROTO_ESP && xs->id.proto != IPPROTO_AH) { + netdev_err(dev, "Unsupported protocol 0x%04x for IPsec offload\n", + xs->id.proto); + return -EINVAL; + } + + if (xs->xso.flags & XFRM_OFFLOAD_INBOUND) { + struct rx_sa rsa; + + if (xs->calg) { + netdev_err(dev, "Compression offload not supported\n"); + return -EINVAL; + } + + /* find the first unused index */ + ret = ixgbevf_ipsec_find_empty_idx(ipsec, true); + if (ret < 0) { + netdev_err(dev, "No space for SA in Rx table!\n"); + return ret; + } + sa_idx = (u16)ret; + + memset(&rsa, 0, sizeof(rsa)); + rsa.used = true; + rsa.xs = xs; + + if (rsa.xs->id.proto & IPPROTO_ESP) + rsa.decrypt = xs->ealg || xs->aead; + + /* get the key and salt */ + ret = ixgbevf_ipsec_parse_proto_keys(xs, rsa.key, &rsa.salt); + if (ret) { + netdev_err(dev, "Failed to get key data for Rx SA table\n"); + return ret; + } + + /* get ip for rx sa table */ + if (xs->props.family == AF_INET6) + memcpy(rsa.ipaddr, &xs->id.daddr.a6, 16); + else + memcpy(&rsa.ipaddr[3], &xs->id.daddr.a4, 4); + + rsa.mode = IXGBE_RXMOD_VALID; + if (rsa.xs->id.proto & IPPROTO_ESP) + rsa.mode |= IXGBE_RXMOD_PROTO_ESP; + if (rsa.decrypt) + rsa.mode |= IXGBE_RXMOD_DECRYPT; + if (rsa.xs->props.family == AF_INET6) + rsa.mode |= IXGBE_RXMOD_IPV6; + + ret = ixgbevf_ipsec_set_pf_sa(adapter, xs); + if (ret < 0) + return ret; + rsa.pfsa = ret; + + /* the preparations worked, so save the info */ + memcpy(&ipsec->rx_tbl[sa_idx], &rsa, sizeof(rsa)); + + xs->xso.offload_handle = sa_idx + IXGBE_IPSEC_BASE_RX_INDEX; + + ipsec->num_rx_sa++; + + /* hash the new entry for faster search in Rx path */ + hash_add_rcu(ipsec->rx_sa_list, &ipsec->rx_tbl[sa_idx].hlist, + (__force u32)rsa.xs->id.spi); + } else { + struct tx_sa tsa; + + /* find the first unused index */ + ret = ixgbevf_ipsec_find_empty_idx(ipsec, false); + if (ret < 0) { + netdev_err(dev, "No space for SA in Tx table\n"); + return ret; + } + sa_idx = (u16)ret; + + memset(&tsa, 0, sizeof(tsa)); + tsa.used = true; + tsa.xs = xs; + + if (xs->id.proto & IPPROTO_ESP) + tsa.encrypt = xs->ealg || xs->aead; + + ret = ixgbevf_ipsec_parse_proto_keys(xs, tsa.key, &tsa.salt); + if (ret) { + netdev_err(dev, "Failed to get key data for Tx SA table\n"); + memset(&tsa, 0, sizeof(tsa)); + return ret; + } + + ret = ixgbevf_ipsec_set_pf_sa(adapter, xs); + if (ret < 0) + return ret; + tsa.pfsa = ret; + + /* the preparations worked, so save the info */ + memcpy(&ipsec->tx_tbl[sa_idx], &tsa, sizeof(tsa)); + + xs->xso.offload_handle = sa_idx + IXGBE_IPSEC_BASE_TX_INDEX; + + ipsec->num_tx_sa++; + } + + return 0; +} + +/** + * ixgbevf_ipsec_del_sa - clear out this specific SA + * @xs: pointer to transformer state struct + **/ +static void ixgbevf_ipsec_del_sa(struct xfrm_state *xs) +{ + struct net_device *dev = xs->xso.dev; + struct ixgbevf_adapter *adapter = netdev_priv(dev); + struct ixgbevf_ipsec *ipsec = adapter->ipsec; + u16 sa_idx; + + if (xs->xso.flags & XFRM_OFFLOAD_INBOUND) { + sa_idx = xs->xso.offload_handle - IXGBE_IPSEC_BASE_RX_INDEX; + + if (!ipsec->rx_tbl[sa_idx].used) { + netdev_err(dev, "Invalid Rx SA selected sa_idx=%d offload_handle=%lu\n", + sa_idx, xs->xso.offload_handle); + return; + } + + ixgbevf_ipsec_del_pf_sa(adapter, ipsec->rx_tbl[sa_idx].pfsa); + hash_del_rcu(&ipsec->rx_tbl[sa_idx].hlist); + memset(&ipsec->rx_tbl[sa_idx], 0, sizeof(struct rx_sa)); + ipsec->num_rx_sa--; + } else { + sa_idx = xs->xso.offload_handle - IXGBE_IPSEC_BASE_TX_INDEX; + + if (!ipsec->tx_tbl[sa_idx].used) { + netdev_err(dev, "Invalid Tx SA selected sa_idx=%d offload_handle=%lu\n", + sa_idx, xs->xso.offload_handle); + return; + } + + ixgbevf_ipsec_del_pf_sa(adapter, ipsec->tx_tbl[sa_idx].pfsa); + memset(&ipsec->tx_tbl[sa_idx], 0, sizeof(struct tx_sa)); + ipsec->num_tx_sa--; + } +} + +/** + * ixgbevf_ipsec_offload_ok - can this packet use the xfrm hw offload + * @skb: current data packet + * @xs: pointer to transformer state struct + **/ +static bool ixgbevf_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs) +{ + if (xs->props.family == AF_INET) { + /* Offload with IPv4 options is not supported yet */ + if (ip_hdr(skb)->ihl != 5) + return false; + } else { + /* Offload with IPv6 extension headers is not support yet */ + if (ipv6_ext_hdr(ipv6_hdr(skb)->nexthdr)) + return false; + } + + return true; +} + +static const struct xfrmdev_ops ixgbevf_xfrmdev_ops = { + .xdo_dev_state_add = ixgbevf_ipsec_add_sa, + .xdo_dev_state_delete = ixgbevf_ipsec_del_sa, + .xdo_dev_offload_ok = ixgbevf_ipsec_offload_ok, +}; + +/** + * ixgbevf_ipsec_tx - setup Tx flags for IPsec offload + * @tx_ring: outgoing context + * @first: current data packet + * @itd: ipsec Tx data for later use in building context descriptor + **/ +int ixgbevf_ipsec_tx(struct ixgbevf_ring *tx_ring, + struct ixgbevf_tx_buffer *first, + struct ixgbevf_ipsec_tx_data *itd) +{ + struct ixgbevf_adapter *adapter = netdev_priv(tx_ring->netdev); + struct ixgbevf_ipsec *ipsec = adapter->ipsec; + struct xfrm_state *xs; + struct tx_sa *tsa; + u16 sa_idx; + + if (unlikely(!first->skb->sp->len)) { + netdev_err(tx_ring->netdev, "%s: no xfrm state len = %d\n", + __func__, first->skb->sp->len); + return 0; + } + + xs = xfrm_input_state(first->skb); + if (unlikely(!xs)) { + netdev_err(tx_ring->netdev, "%s: no xfrm_input_state() xs = %p\n", + __func__, xs); + return 0; + } + + sa_idx = xs->xso.offload_handle - IXGBE_IPSEC_BASE_TX_INDEX; + if (unlikely(sa_idx > IXGBE_IPSEC_MAX_SA_COUNT)) { + netdev_err(tx_ring->netdev, "%s: bad sa_idx=%d handle=%lu\n", + __func__, sa_idx, xs->xso.offload_handle); + return 0; + } + + tsa = &ipsec->tx_tbl[sa_idx]; + if (unlikely(!tsa->used)) { + netdev_err(tx_ring->netdev, "%s: unused sa_idx=%d\n", + __func__, sa_idx); + return 0; + } + + itd->pfsa = tsa->pfsa - IXGBE_IPSEC_BASE_TX_INDEX; + + first->tx_flags |= IXGBE_TX_FLAGS_IPSEC | IXGBE_TX_FLAGS_CSUM; + + if (xs->id.proto == IPPROTO_ESP) { + itd->flags |= IXGBE_ADVTXD_TUCMD_IPSEC_TYPE_ESP | + IXGBE_ADVTXD_TUCMD_L4T_TCP; + if (first->protocol == htons(ETH_P_IP)) + itd->flags |= IXGBE_ADVTXD_TUCMD_IPV4; + + /* The actual trailer length is authlen (16 bytes) plus + * 2 bytes for the proto and the padlen values, plus + * padlen bytes of padding. This ends up not the same + * as the static value found in xs->props.trailer_len (21). + * + * ... but if we're doing GSO, don't bother as the stack + * doesn't add a trailer for those. + */ + if (!skb_is_gso(first->skb)) { + /* The "correct" way to get the auth length would be + * to use + * authlen = crypto_aead_authsize(xs->data); + * but since we know we only have one size to worry + * about * we can let the compiler use the constant + * and save us a few CPU cycles. + */ + const int authlen = IXGBE_IPSEC_AUTH_BITS / 8; + struct sk_buff *skb = first->skb; + u8 padlen; + int ret; + + ret = skb_copy_bits(skb, skb->len - (authlen + 2), + &padlen, 1); + if (unlikely(ret)) + return 0; + itd->trailer_len = authlen + 2 + padlen; + } + } + if (tsa->encrypt) + itd->flags |= IXGBE_ADVTXD_TUCMD_IPSEC_ENCRYPT_EN; + + return 1; +} + +/** + * ixgbevf_ipsec_rx - decode IPsec bits from Rx descriptor + * @rx_ring: receiving ring + * @rx_desc: receive data descriptor + * @skb: current data packet + * + * Determine if there was an IPsec encapsulation noticed, and if so set up + * the resulting status for later in the receive stack. + **/ +void ixgbevf_ipsec_rx(struct ixgbevf_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + struct ixgbevf_adapter *adapter = netdev_priv(rx_ring->netdev); + __le16 pkt_info = rx_desc->wb.lower.lo_dword.hs_rss.pkt_info; + __le16 ipsec_pkt_types = cpu_to_le16(IXGBE_RXDADV_PKTTYPE_IPSEC_AH | + IXGBE_RXDADV_PKTTYPE_IPSEC_ESP); + struct ixgbevf_ipsec *ipsec = adapter->ipsec; + struct xfrm_offload *xo = NULL; + struct xfrm_state *xs = NULL; + struct ipv6hdr *ip6 = NULL; + struct iphdr *ip4 = NULL; + void *daddr; + __be32 spi; + u8 *c_hdr; + u8 proto; + + /* Find the IP and crypto headers in the data. + * We can assume no VLAN header in the way, b/c the + * hw won't recognize the IPsec packet and anyway the + * currently VLAN device doesn't support xfrm offload. + */ + if (pkt_info & cpu_to_le16(IXGBE_RXDADV_PKTTYPE_IPV4)) { + ip4 = (struct iphdr *)(skb->data + ETH_HLEN); + daddr = &ip4->daddr; + c_hdr = (u8 *)ip4 + ip4->ihl * 4; + } else if (pkt_info & cpu_to_le16(IXGBE_RXDADV_PKTTYPE_IPV6)) { + ip6 = (struct ipv6hdr *)(skb->data + ETH_HLEN); + daddr = &ip6->daddr; + c_hdr = (u8 *)ip6 + sizeof(struct ipv6hdr); + } else { + return; + } + + switch (pkt_info & ipsec_pkt_types) { + case cpu_to_le16(IXGBE_RXDADV_PKTTYPE_IPSEC_AH): + spi = ((struct ip_auth_hdr *)c_hdr)->spi; + proto = IPPROTO_AH; + break; + case cpu_to_le16(IXGBE_RXDADV_PKTTYPE_IPSEC_ESP): + spi = ((struct ip_esp_hdr *)c_hdr)->spi; + proto = IPPROTO_ESP; + break; + default: + return; + } + + xs = ixgbevf_ipsec_find_rx_state(ipsec, daddr, proto, spi, !!ip4); + if (unlikely(!xs)) + return; + + skb->sp = secpath_dup(skb->sp); + if (unlikely(!skb->sp)) + return; + + skb->sp->xvec[skb->sp->len++] = xs; + skb->sp->olen++; + xo = xfrm_offload(skb); + xo->flags = CRYPTO_DONE; + xo->status = CRYPTO_SUCCESS; + + adapter->rx_ipsec++; +} + +/** + * ixgbevf_init_ipsec_offload - initialize registers for IPsec operation + * @adapter: board private structure + **/ +void ixgbevf_init_ipsec_offload(struct ixgbevf_adapter *adapter) +{ + struct ixgbevf_ipsec *ipsec; + size_t size; + + switch (adapter->hw.api_version) { + case ixgbe_mbox_api_14: + break; + default: + return; + } + + ipsec = kzalloc(sizeof(*ipsec), GFP_KERNEL); + if (!ipsec) + goto err1; + hash_init(ipsec->rx_sa_list); + + size = sizeof(struct rx_sa) * IXGBE_IPSEC_MAX_SA_COUNT; + ipsec->rx_tbl = kzalloc(size, GFP_KERNEL); + if (!ipsec->rx_tbl) + goto err2; + + size = sizeof(struct tx_sa) * IXGBE_IPSEC_MAX_SA_COUNT; + ipsec->tx_tbl = kzalloc(size, GFP_KERNEL); + if (!ipsec->tx_tbl) + goto err2; + + ipsec->num_rx_sa = 0; + ipsec->num_tx_sa = 0; + + adapter->ipsec = ipsec; + + adapter->netdev->xfrmdev_ops = &ixgbevf_xfrmdev_ops; + +#define IXGBEVF_ESP_FEATURES (NETIF_F_HW_ESP | \ + NETIF_F_HW_ESP_TX_CSUM | \ + NETIF_F_GSO_ESP) + + adapter->netdev->features |= IXGBEVF_ESP_FEATURES; + adapter->netdev->hw_enc_features |= IXGBEVF_ESP_FEATURES; + + return; + +err2: + kfree(ipsec->rx_tbl); + kfree(ipsec->tx_tbl); + kfree(ipsec); +err1: + netdev_err(adapter->netdev, "Unable to allocate memory for SA tables"); +} + +/** + * ixgbevf_stop_ipsec_offload - tear down the IPsec offload + * @adapter: board private structure + **/ +void ixgbevf_stop_ipsec_offload(struct ixgbevf_adapter *adapter) +{ + struct ixgbevf_ipsec *ipsec = adapter->ipsec; + + adapter->ipsec = NULL; + if (ipsec) { + kfree(ipsec->rx_tbl); + kfree(ipsec->tx_tbl); + kfree(ipsec); + } +} diff --git a/drivers/net/ethernet/intel/ixgbevf/ipsec.h b/drivers/net/ethernet/intel/ixgbevf/ipsec.h new file mode 100644 index 000000000000..3740725041c3 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbevf/ipsec.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2018 Oracle and/or its affiliates. All rights reserved. */ + +#ifndef _IXGBEVF_IPSEC_H_ +#define _IXGBEVF_IPSEC_H_ + +#define IXGBE_IPSEC_MAX_SA_COUNT 1024 +#define IXGBE_IPSEC_BASE_RX_INDEX 0 +#define IXGBE_IPSEC_BASE_TX_INDEX IXGBE_IPSEC_MAX_SA_COUNT +#define IXGBE_IPSEC_AUTH_BITS 128 + +#define IXGBE_RXMOD_VALID 0x00000001 +#define IXGBE_RXMOD_PROTO_ESP 0x00000004 +#define IXGBE_RXMOD_DECRYPT 0x00000008 +#define IXGBE_RXMOD_IPV6 0x00000010 + +struct rx_sa { + struct hlist_node hlist; + struct xfrm_state *xs; + __be32 ipaddr[4]; + u32 key[4]; + u32 salt; + u32 mode; + u32 pfsa; + bool used; + bool decrypt; +}; + +struct rx_ip_sa { + __be32 ipaddr[4]; + u32 ref_cnt; + bool used; +}; + +struct tx_sa { + struct xfrm_state *xs; + u32 key[4]; + u32 salt; + u32 pfsa; + bool encrypt; + bool used; +}; + +struct ixgbevf_ipsec_tx_data { + u32 flags; + u16 trailer_len; + u16 pfsa; +}; + +struct ixgbevf_ipsec { + u16 num_rx_sa; + u16 num_tx_sa; + struct rx_sa *rx_tbl; + struct tx_sa *tx_tbl; + DECLARE_HASHTABLE(rx_sa_list, 10); +}; + +struct sa_mbx_msg { + __be32 spi; + u8 flags; + u8 proto; + u16 family; + __be32 addr[4]; + u32 key[5]; +}; +#endif /* _IXGBEVF_IPSEC_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h index 56a1031dcc07..e399e1c0c54a 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h @@ -14,6 +14,7 @@ #include <net/xdp.h> #include "vf.h" +#include "ipsec.h" #define IXGBE_MAX_TXD_PWR 14 #define IXGBE_MAX_DATA_PER_TXD BIT(IXGBE_MAX_TXD_PWR) @@ -163,6 +164,7 @@ struct ixgbevf_ring { #define IXGBE_TX_FLAGS_VLAN BIT(1) #define IXGBE_TX_FLAGS_TSO BIT(2) #define IXGBE_TX_FLAGS_IPV4 BIT(3) +#define IXGBE_TX_FLAGS_IPSEC BIT(4) #define IXGBE_TX_FLAGS_VLAN_MASK 0xffff0000 #define IXGBE_TX_FLAGS_VLAN_PRIO_MASK 0x0000e000 #define IXGBE_TX_FLAGS_VLAN_SHIFT 16 @@ -338,6 +340,7 @@ struct ixgbevf_adapter { struct ixgbevf_ring *tx_ring[MAX_TX_QUEUES]; /* One per active queue */ u64 restart_queue; u32 tx_timeout_count; + u64 tx_ipsec; /* RX */ int num_rx_queues; @@ -348,6 +351,7 @@ struct ixgbevf_adapter { u64 alloc_rx_page_failed; u64 alloc_rx_buff_failed; u64 alloc_rx_page; + u64 rx_ipsec; struct msix_entry *msix_entries; @@ -384,6 +388,10 @@ struct ixgbevf_adapter { u8 rss_indir_tbl[IXGBEVF_X550_VFRETA_SIZE]; u32 flags; #define IXGBEVF_FLAGS_LEGACY_RX BIT(1) + +#ifdef CONFIG_XFRM + struct ixgbevf_ipsec *ipsec; +#endif /* CONFIG_XFRM */ }; enum ixbgevf_state_t { @@ -451,6 +459,31 @@ int ethtool_ioctl(struct ifreq *ifr); extern void ixgbevf_write_eitr(struct ixgbevf_q_vector *q_vector); +#ifdef CONFIG_XFRM_OFFLOAD +void ixgbevf_init_ipsec_offload(struct ixgbevf_adapter *adapter); +void ixgbevf_stop_ipsec_offload(struct ixgbevf_adapter *adapter); +void ixgbevf_ipsec_restore(struct ixgbevf_adapter *adapter); +void ixgbevf_ipsec_rx(struct ixgbevf_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb); +int ixgbevf_ipsec_tx(struct ixgbevf_ring *tx_ring, + struct ixgbevf_tx_buffer *first, + struct ixgbevf_ipsec_tx_data *itd); +#else +static inline void ixgbevf_init_ipsec_offload(struct ixgbevf_adapter *adapter) +{ } +static inline void ixgbevf_stop_ipsec_offload(struct ixgbevf_adapter *adapter) +{ } +static inline void ixgbevf_ipsec_restore(struct ixgbevf_adapter *adapter) { } +static inline void ixgbevf_ipsec_rx(struct ixgbevf_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) { } +static inline int ixgbevf_ipsec_tx(struct ixgbevf_ring *tx_ring, + struct ixgbevf_tx_buffer *first, + struct ixgbevf_ipsec_tx_data *itd) +{ return 0; } +#endif /* CONFIG_XFRM_OFFLOAD */ + void ixgbe_napi_add_all(struct ixgbevf_adapter *adapter); void ixgbe_napi_del_all(struct ixgbevf_adapter *adapter); diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index d86446d202d5..ba6562e8cd73 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -40,7 +40,7 @@ static const char ixgbevf_driver_string[] = #define DRV_VERSION "4.1.0-k" const char ixgbevf_driver_version[] = DRV_VERSION; static char ixgbevf_copyright[] = - "Copyright (c) 2009 - 2015 Intel Corporation."; + "Copyright (c) 2009 - 2018 Intel Corporation."; static const struct ixgbevf_info *ixgbevf_info_tbl[] = { [board_82599_vf] = &ixgbevf_82599_vf_info, @@ -79,7 +79,7 @@ MODULE_DEVICE_TABLE(pci, ixgbevf_pci_tbl); MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION("Intel(R) 10 Gigabit Virtual Function Network Driver"); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); MODULE_VERSION(DRV_VERSION); #define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV|NETIF_MSG_PROBE|NETIF_MSG_LINK) @@ -268,7 +268,7 @@ static bool ixgbevf_clean_tx_irq(struct ixgbevf_q_vector *q_vector, struct ixgbevf_adapter *adapter = q_vector->adapter; struct ixgbevf_tx_buffer *tx_buffer; union ixgbe_adv_tx_desc *tx_desc; - unsigned int total_bytes = 0, total_packets = 0; + unsigned int total_bytes = 0, total_packets = 0, total_ipsec = 0; unsigned int budget = tx_ring->count / 2; unsigned int i = tx_ring->next_to_clean; @@ -299,6 +299,8 @@ static bool ixgbevf_clean_tx_irq(struct ixgbevf_q_vector *q_vector, /* update the statistics for this packet */ total_bytes += tx_buffer->bytecount; total_packets += tx_buffer->gso_segs; + if (tx_buffer->tx_flags & IXGBE_TX_FLAGS_IPSEC) + total_ipsec++; /* free the skb */ if (ring_is_xdp(tx_ring)) @@ -361,6 +363,7 @@ static bool ixgbevf_clean_tx_irq(struct ixgbevf_q_vector *q_vector, u64_stats_update_end(&tx_ring->syncp); q_vector->tx.total_bytes += total_bytes; q_vector->tx.total_packets += total_packets; + adapter->tx_ipsec += total_ipsec; if (check_for_tx_hang(tx_ring) && ixgbevf_check_tx_hang(tx_ring)) { struct ixgbe_hw *hw = &adapter->hw; @@ -516,6 +519,9 @@ static void ixgbevf_process_skb_fields(struct ixgbevf_ring *rx_ring, __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vid); } + if (ixgbevf_test_staterr(rx_desc, IXGBE_RXDADV_STAT_SECP)) + ixgbevf_ipsec_rx(rx_ring, rx_desc, skb); + skb->protocol = eth_type_trans(skb, rx_ring->netdev); } @@ -1012,7 +1018,7 @@ static int ixgbevf_xmit_xdp_ring(struct ixgbevf_ring *ring, context_desc = IXGBEVF_TX_CTXTDESC(ring, 0); context_desc->vlan_macip_lens = cpu_to_le32(ETH_HLEN << IXGBE_ADVTXD_MACLEN_SHIFT); - context_desc->seqnum_seed = 0; + context_desc->fceof_saidx = 0; context_desc->type_tucmd_mlhl = cpu_to_le32(IXGBE_TXD_CMD_DEXT | IXGBE_ADVTXD_DTYP_CTXT); @@ -2200,6 +2206,7 @@ static void ixgbevf_configure(struct ixgbevf_adapter *adapter) ixgbevf_set_rx_mode(adapter->netdev); ixgbevf_restore_vlan(adapter); + ixgbevf_ipsec_restore(adapter); ixgbevf_configure_tx(adapter); ixgbevf_configure_rx(adapter); @@ -2246,7 +2253,8 @@ static void ixgbevf_init_last_counter_stats(struct ixgbevf_adapter *adapter) static void ixgbevf_negotiate_api(struct ixgbevf_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; - int api[] = { ixgbe_mbox_api_13, + int api[] = { ixgbe_mbox_api_14, + ixgbe_mbox_api_13, ixgbe_mbox_api_12, ixgbe_mbox_api_11, ixgbe_mbox_api_10, @@ -2605,6 +2613,7 @@ static void ixgbevf_set_num_queues(struct ixgbevf_adapter *adapter) case ixgbe_mbox_api_11: case ixgbe_mbox_api_12: case ixgbe_mbox_api_13: + case ixgbe_mbox_api_14: if (adapter->xdp_prog && hw->mac.max_tx_queues == rss) rss = rss > 3 ? 2 : 1; @@ -3700,8 +3709,8 @@ static void ixgbevf_queue_reset_subtask(struct ixgbevf_adapter *adapter) } static void ixgbevf_tx_ctxtdesc(struct ixgbevf_ring *tx_ring, - u32 vlan_macip_lens, u32 type_tucmd, - u32 mss_l4len_idx) + u32 vlan_macip_lens, u32 fceof_saidx, + u32 type_tucmd, u32 mss_l4len_idx) { struct ixgbe_adv_tx_context_desc *context_desc; u16 i = tx_ring->next_to_use; @@ -3715,14 +3724,15 @@ static void ixgbevf_tx_ctxtdesc(struct ixgbevf_ring *tx_ring, type_tucmd |= IXGBE_TXD_CMD_DEXT | IXGBE_ADVTXD_DTYP_CTXT; context_desc->vlan_macip_lens = cpu_to_le32(vlan_macip_lens); - context_desc->seqnum_seed = 0; + context_desc->fceof_saidx = cpu_to_le32(fceof_saidx); context_desc->type_tucmd_mlhl = cpu_to_le32(type_tucmd); context_desc->mss_l4len_idx = cpu_to_le32(mss_l4len_idx); } static int ixgbevf_tso(struct ixgbevf_ring *tx_ring, struct ixgbevf_tx_buffer *first, - u8 *hdr_len) + u8 *hdr_len, + struct ixgbevf_ipsec_tx_data *itd) { u32 vlan_macip_lens, type_tucmd, mss_l4len_idx; struct sk_buff *skb = first->skb; @@ -3736,6 +3746,7 @@ static int ixgbevf_tso(struct ixgbevf_ring *tx_ring, unsigned char *hdr; } l4; u32 paylen, l4_offset; + u32 fceof_saidx = 0; int err; if (skb->ip_summed != CHECKSUM_PARTIAL) @@ -3761,13 +3772,15 @@ static int ixgbevf_tso(struct ixgbevf_ring *tx_ring, if (ip.v4->version == 4) { unsigned char *csum_start = skb_checksum_start(skb); unsigned char *trans_start = ip.hdr + (ip.v4->ihl * 4); + int len = csum_start - trans_start; /* IP header will have to cancel out any data that - * is not a part of the outer IP header + * is not a part of the outer IP header, so set to + * a reverse csum if needed, else init check to 0. */ - ip.v4->check = csum_fold(csum_partial(trans_start, - csum_start - trans_start, - 0)); + ip.v4->check = (skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) ? + csum_fold(csum_partial(trans_start, + len, 0)) : 0; type_tucmd |= IXGBE_ADVTXD_TUCMD_IPV4; ip.v4->tot_len = 0; @@ -3799,13 +3812,16 @@ static int ixgbevf_tso(struct ixgbevf_ring *tx_ring, mss_l4len_idx |= skb_shinfo(skb)->gso_size << IXGBE_ADVTXD_MSS_SHIFT; mss_l4len_idx |= (1u << IXGBE_ADVTXD_IDX_SHIFT); + fceof_saidx |= itd->pfsa; + type_tucmd |= itd->flags | itd->trailer_len; + /* vlan_macip_lens: HEADLEN, MACLEN, VLAN tag */ vlan_macip_lens = l4.hdr - ip.hdr; vlan_macip_lens |= (ip.hdr - skb->data) << IXGBE_ADVTXD_MACLEN_SHIFT; vlan_macip_lens |= first->tx_flags & IXGBE_TX_FLAGS_VLAN_MASK; - ixgbevf_tx_ctxtdesc(tx_ring, vlan_macip_lens, - type_tucmd, mss_l4len_idx); + ixgbevf_tx_ctxtdesc(tx_ring, vlan_macip_lens, fceof_saidx, type_tucmd, + mss_l4len_idx); return 1; } @@ -3820,10 +3836,12 @@ static inline bool ixgbevf_ipv6_csum_is_sctp(struct sk_buff *skb) } static void ixgbevf_tx_csum(struct ixgbevf_ring *tx_ring, - struct ixgbevf_tx_buffer *first) + struct ixgbevf_tx_buffer *first, + struct ixgbevf_ipsec_tx_data *itd) { struct sk_buff *skb = first->skb; u32 vlan_macip_lens = 0; + u32 fceof_saidx = 0; u32 type_tucmd = 0; if (skb->ip_summed != CHECKSUM_PARTIAL) @@ -3849,6 +3867,10 @@ static void ixgbevf_tx_csum(struct ixgbevf_ring *tx_ring, skb_checksum_help(skb); goto no_csum; } + + if (first->protocol == htons(ETH_P_IP)) + type_tucmd |= IXGBE_ADVTXD_TUCMD_IPV4; + /* update TX checksum flag */ first->tx_flags |= IXGBE_TX_FLAGS_CSUM; vlan_macip_lens = skb_checksum_start_offset(skb) - @@ -3858,7 +3880,11 @@ no_csum: vlan_macip_lens |= skb_network_offset(skb) << IXGBE_ADVTXD_MACLEN_SHIFT; vlan_macip_lens |= first->tx_flags & IXGBE_TX_FLAGS_VLAN_MASK; - ixgbevf_tx_ctxtdesc(tx_ring, vlan_macip_lens, type_tucmd, 0); + fceof_saidx |= itd->pfsa; + type_tucmd |= itd->flags | itd->trailer_len; + + ixgbevf_tx_ctxtdesc(tx_ring, vlan_macip_lens, + fceof_saidx, type_tucmd, 0); } static __le32 ixgbevf_tx_cmd_type(u32 tx_flags) @@ -3892,8 +3918,12 @@ static void ixgbevf_tx_olinfo_status(union ixgbe_adv_tx_desc *tx_desc, if (tx_flags & IXGBE_TX_FLAGS_IPV4) olinfo_status |= cpu_to_le32(IXGBE_ADVTXD_POPTS_IXSM); - /* use index 1 context for TSO/FSO/FCOE */ - if (tx_flags & IXGBE_TX_FLAGS_TSO) + /* enable IPsec */ + if (tx_flags & IXGBE_TX_FLAGS_IPSEC) + olinfo_status |= cpu_to_le32(IXGBE_ADVTXD_POPTS_IPSEC); + + /* use index 1 context for TSO/FSO/FCOE/IPSEC */ + if (tx_flags & (IXGBE_TX_FLAGS_TSO | IXGBE_TX_FLAGS_IPSEC)) olinfo_status |= cpu_to_le32(1u << IXGBE_ADVTXD_IDX_SHIFT); /* Check Context must be set if Tx switch is enabled, which it @@ -4075,6 +4105,7 @@ static int ixgbevf_xmit_frame_ring(struct sk_buff *skb, int tso; u32 tx_flags = 0; u16 count = TXD_USE_COUNT(skb_headlen(skb)); + struct ixgbevf_ipsec_tx_data ipsec_tx = { 0 }; #if PAGE_SIZE > IXGBE_MAX_DATA_PER_TXD unsigned short f; #endif @@ -4119,11 +4150,15 @@ static int ixgbevf_xmit_frame_ring(struct sk_buff *skb, first->tx_flags = tx_flags; first->protocol = vlan_get_protocol(skb); - tso = ixgbevf_tso(tx_ring, first, &hdr_len); +#ifdef CONFIG_XFRM_OFFLOAD + if (skb->sp && !ixgbevf_ipsec_tx(tx_ring, first, &ipsec_tx)) + goto out_drop; +#endif + tso = ixgbevf_tso(tx_ring, first, &hdr_len, &ipsec_tx); if (tso < 0) goto out_drop; else if (!tso) - ixgbevf_tx_csum(tx_ring, first); + ixgbevf_tx_csum(tx_ring, first, &ipsec_tx); ixgbevf_tx_map(tx_ring, first, hdr_len); @@ -4634,6 +4669,7 @@ static int ixgbevf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) case ixgbe_mbox_api_11: case ixgbe_mbox_api_12: case ixgbe_mbox_api_13: + case ixgbe_mbox_api_14: netdev->max_mtu = IXGBE_MAX_JUMBO_FRAME_SIZE - (ETH_HLEN + ETH_FCS_LEN); break; @@ -4669,6 +4705,7 @@ static int ixgbevf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pci_set_drvdata(pdev, netdev); netif_carrier_off(netdev); + ixgbevf_init_ipsec_offload(adapter); ixgbevf_init_last_counter_stats(adapter); @@ -4735,6 +4772,7 @@ static void ixgbevf_remove(struct pci_dev *pdev) if (netdev->reg_state == NETREG_REGISTERED) unregister_netdev(netdev); + ixgbevf_stop_ipsec_offload(adapter); ixgbevf_clear_interrupt_scheme(adapter); ixgbevf_reset_interrupt_capability(adapter); diff --git a/drivers/net/ethernet/intel/ixgbevf/mbx.h b/drivers/net/ethernet/intel/ixgbevf/mbx.h index bfd9ae150808..853796c8ef0e 100644 --- a/drivers/net/ethernet/intel/ixgbevf/mbx.h +++ b/drivers/net/ethernet/intel/ixgbevf/mbx.h @@ -62,6 +62,7 @@ enum ixgbe_pfvf_api_rev { ixgbe_mbox_api_11, /* API version 1.1, linux/freebsd VF driver */ ixgbe_mbox_api_12, /* API version 1.2, linux/freebsd VF driver */ ixgbe_mbox_api_13, /* API version 1.3, linux/freebsd VF driver */ + ixgbe_mbox_api_14, /* API version 1.4, linux/freebsd VF driver */ /* This value should always be last */ ixgbe_mbox_api_unknown, /* indicates that API version is not known */ }; @@ -92,6 +93,10 @@ enum ixgbe_pfvf_api_rev { #define IXGBE_VF_UPDATE_XCAST_MODE 0x0c +/* mailbox API, version 1.4 VF requests */ +#define IXGBE_VF_IPSEC_ADD 0x0d +#define IXGBE_VF_IPSEC_DEL 0x0e + /* length of permanent address message returned from PF */ #define IXGBE_VF_PERMADDR_MSG_LEN 4 /* word in permanent address message with the current multicast type */ diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.c b/drivers/net/ethernet/intel/ixgbevf/vf.c index bf0577e819e1..cd3b81300cc7 100644 --- a/drivers/net/ethernet/intel/ixgbevf/vf.c +++ b/drivers/net/ethernet/intel/ixgbevf/vf.c @@ -309,6 +309,7 @@ int ixgbevf_get_reta_locked(struct ixgbe_hw *hw, u32 *reta, int num_rx_queues) * is not supported for this device type. */ switch (hw->api_version) { + case ixgbe_mbox_api_14: case ixgbe_mbox_api_13: case ixgbe_mbox_api_12: if (hw->mac.type < ixgbe_mac_X550_vf) @@ -376,6 +377,7 @@ int ixgbevf_get_rss_key_locked(struct ixgbe_hw *hw, u8 *rss_key) * or if the operation is not supported for this device type. */ switch (hw->api_version) { + case ixgbe_mbox_api_14: case ixgbe_mbox_api_13: case ixgbe_mbox_api_12: if (hw->mac.type < ixgbe_mac_X550_vf) @@ -540,6 +542,7 @@ static s32 ixgbevf_update_xcast_mode(struct ixgbe_hw *hw, int xcast_mode) if (xcast_mode == IXGBEVF_XCAST_MODE_PROMISC) return -EOPNOTSUPP; /* Fall threw */ + case ixgbe_mbox_api_14: case ixgbe_mbox_api_13: break; default: @@ -890,6 +893,7 @@ int ixgbevf_get_queues(struct ixgbe_hw *hw, unsigned int *num_tcs, case ixgbe_mbox_api_11: case ixgbe_mbox_api_12: case ixgbe_mbox_api_13: + case ixgbe_mbox_api_14: break; default: return 0; diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c index 7a637b51c7d2..32ac9045cdae 100644 --- a/drivers/net/ethernet/lantiq_etop.c +++ b/drivers/net/ethernet/lantiq_etop.c @@ -274,6 +274,7 @@ ltq_etop_hw_init(struct net_device *dev) struct ltq_etop_chan *ch = &priv->ch[i]; ch->idx = ch->dma.nr = i; + ch->dma.dev = &priv->pdev->dev; if (IS_TX(i)) { ltq_dma_alloc_tx(&ch->dma); @@ -364,15 +365,8 @@ ltq_etop_mdio_probe(struct net_device *dev) return PTR_ERR(phydev); } - phydev->supported &= (SUPPORTED_10baseT_Half - | SUPPORTED_10baseT_Full - | SUPPORTED_100baseT_Half - | SUPPORTED_100baseT_Full - | SUPPORTED_Autoneg - | SUPPORTED_MII - | SUPPORTED_TP); + phy_set_max_speed(phydev, SPEED_100); - phydev->advertising = phydev->supported; phy_attached_info(phydev); return 0; @@ -438,6 +432,7 @@ ltq_etop_open(struct net_device *dev) if (!IS_TX(i) && (!IS_RX(i))) continue; ltq_dma_open(&ch->dma); + ltq_dma_enable_irq(&ch->dma); napi_enable(&ch->napi); } phy_start(dev->phydev); diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c new file mode 100644 index 000000000000..8c5ba4b81fb7 --- /dev/null +++ b/drivers/net/ethernet/lantiq_xrx200.c @@ -0,0 +1,567 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Lantiq / Intel PMAC driver for XRX200 SoCs + * + * Copyright (C) 2010 Lantiq Deutschland + * Copyright (C) 2012 John Crispin <john@phrozen.org> + * Copyright (C) 2017 - 2018 Hauke Mehrtens <hauke@hauke-m.de> + */ + +#include <linux/etherdevice.h> +#include <linux/module.h> +#include <linux/platform_device.h> +#include <linux/interrupt.h> +#include <linux/clk.h> +#include <linux/delay.h> + +#include <linux/of_net.h> +#include <linux/of_platform.h> + +#include <xway_dma.h> + +/* DMA */ +#define XRX200_DMA_DATA_LEN 0x600 +#define XRX200_DMA_RX 0 +#define XRX200_DMA_TX 1 + +/* cpu port mac */ +#define PMAC_RX_IPG 0x0024 +#define PMAC_RX_IPG_MASK 0xf + +#define PMAC_HD_CTL 0x0000 +/* Add Ethernet header to packets from DMA to PMAC */ +#define PMAC_HD_CTL_ADD BIT(0) +/* Add VLAN tag to Packets from DMA to PMAC */ +#define PMAC_HD_CTL_TAG BIT(1) +/* Add CRC to packets from DMA to PMAC */ +#define PMAC_HD_CTL_AC BIT(2) +/* Add status header to packets from PMAC to DMA */ +#define PMAC_HD_CTL_AS BIT(3) +/* Remove CRC from packets from PMAC to DMA */ +#define PMAC_HD_CTL_RC BIT(4) +/* Remove Layer-2 header from packets from PMAC to DMA */ +#define PMAC_HD_CTL_RL2 BIT(5) +/* Status header is present from DMA to PMAC */ +#define PMAC_HD_CTL_RXSH BIT(6) +/* Add special tag from PMAC to switch */ +#define PMAC_HD_CTL_AST BIT(7) +/* Remove specail Tag from PMAC to DMA */ +#define PMAC_HD_CTL_RST BIT(8) +/* Check CRC from DMA to PMAC */ +#define PMAC_HD_CTL_CCRC BIT(9) +/* Enable reaction to Pause frames in the PMAC */ +#define PMAC_HD_CTL_FC BIT(10) + +struct xrx200_chan { + int tx_free; + + struct napi_struct napi; + struct ltq_dma_channel dma; + struct sk_buff *skb[LTQ_DESC_NUM]; + + struct xrx200_priv *priv; +}; + +struct xrx200_priv { + struct clk *clk; + + struct xrx200_chan chan_tx; + struct xrx200_chan chan_rx; + + struct net_device *net_dev; + struct device *dev; + + __iomem void *pmac_reg; +}; + +static u32 xrx200_pmac_r32(struct xrx200_priv *priv, u32 offset) +{ + return __raw_readl(priv->pmac_reg + offset); +} + +static void xrx200_pmac_w32(struct xrx200_priv *priv, u32 val, u32 offset) +{ + __raw_writel(val, priv->pmac_reg + offset); +} + +static void xrx200_pmac_mask(struct xrx200_priv *priv, u32 clear, u32 set, + u32 offset) +{ + u32 val = xrx200_pmac_r32(priv, offset); + + val &= ~(clear); + val |= set; + xrx200_pmac_w32(priv, val, offset); +} + +/* drop all the packets from the DMA ring */ +static void xrx200_flush_dma(struct xrx200_chan *ch) +{ + int i; + + for (i = 0; i < LTQ_DESC_NUM; i++) { + struct ltq_dma_desc *desc = &ch->dma.desc_base[ch->dma.desc]; + + if ((desc->ctl & (LTQ_DMA_OWN | LTQ_DMA_C)) != LTQ_DMA_C) + break; + + desc->ctl = LTQ_DMA_OWN | LTQ_DMA_RX_OFFSET(NET_IP_ALIGN) | + XRX200_DMA_DATA_LEN; + ch->dma.desc++; + ch->dma.desc %= LTQ_DESC_NUM; + } +} + +static int xrx200_open(struct net_device *net_dev) +{ + struct xrx200_priv *priv = netdev_priv(net_dev); + + napi_enable(&priv->chan_tx.napi); + ltq_dma_open(&priv->chan_tx.dma); + ltq_dma_enable_irq(&priv->chan_tx.dma); + + napi_enable(&priv->chan_rx.napi); + ltq_dma_open(&priv->chan_rx.dma); + /* The boot loader does not always deactivate the receiving of frames + * on the ports and then some packets queue up in the PPE buffers. + * They already passed the PMAC so they do not have the tags + * configured here. Read the these packets here and drop them. + * The HW should have written them into memory after 10us + */ + usleep_range(20, 40); + xrx200_flush_dma(&priv->chan_rx); + ltq_dma_enable_irq(&priv->chan_rx.dma); + + netif_wake_queue(net_dev); + + return 0; +} + +static int xrx200_close(struct net_device *net_dev) +{ + struct xrx200_priv *priv = netdev_priv(net_dev); + + netif_stop_queue(net_dev); + + napi_disable(&priv->chan_rx.napi); + ltq_dma_close(&priv->chan_rx.dma); + + napi_disable(&priv->chan_tx.napi); + ltq_dma_close(&priv->chan_tx.dma); + + return 0; +} + +static int xrx200_alloc_skb(struct xrx200_chan *ch) +{ + int ret = 0; + + ch->skb[ch->dma.desc] = netdev_alloc_skb_ip_align(ch->priv->net_dev, + XRX200_DMA_DATA_LEN); + if (!ch->skb[ch->dma.desc]) { + ret = -ENOMEM; + goto skip; + } + + ch->dma.desc_base[ch->dma.desc].addr = dma_map_single(ch->priv->dev, + ch->skb[ch->dma.desc]->data, XRX200_DMA_DATA_LEN, + DMA_FROM_DEVICE); + if (unlikely(dma_mapping_error(ch->priv->dev, + ch->dma.desc_base[ch->dma.desc].addr))) { + dev_kfree_skb_any(ch->skb[ch->dma.desc]); + ret = -ENOMEM; + goto skip; + } + +skip: + ch->dma.desc_base[ch->dma.desc].ctl = + LTQ_DMA_OWN | LTQ_DMA_RX_OFFSET(NET_IP_ALIGN) | + XRX200_DMA_DATA_LEN; + + return ret; +} + +static int xrx200_hw_receive(struct xrx200_chan *ch) +{ + struct xrx200_priv *priv = ch->priv; + struct ltq_dma_desc *desc = &ch->dma.desc_base[ch->dma.desc]; + struct sk_buff *skb = ch->skb[ch->dma.desc]; + int len = (desc->ctl & LTQ_DMA_SIZE_MASK); + struct net_device *net_dev = priv->net_dev; + int ret; + + ret = xrx200_alloc_skb(ch); + + ch->dma.desc++; + ch->dma.desc %= LTQ_DESC_NUM; + + if (ret) { + netdev_err(net_dev, "failed to allocate new rx buffer\n"); + return ret; + } + + skb_put(skb, len); + skb->protocol = eth_type_trans(skb, net_dev); + netif_receive_skb(skb); + net_dev->stats.rx_packets++; + net_dev->stats.rx_bytes += len - ETH_FCS_LEN; + + return 0; +} + +static int xrx200_poll_rx(struct napi_struct *napi, int budget) +{ + struct xrx200_chan *ch = container_of(napi, + struct xrx200_chan, napi); + int rx = 0; + int ret; + + while (rx < budget) { + struct ltq_dma_desc *desc = &ch->dma.desc_base[ch->dma.desc]; + + if ((desc->ctl & (LTQ_DMA_OWN | LTQ_DMA_C)) == LTQ_DMA_C) { + ret = xrx200_hw_receive(ch); + if (ret) + return ret; + rx++; + } else { + break; + } + } + + if (rx < budget) { + napi_complete(&ch->napi); + ltq_dma_enable_irq(&ch->dma); + } + + return rx; +} + +static int xrx200_tx_housekeeping(struct napi_struct *napi, int budget) +{ + struct xrx200_chan *ch = container_of(napi, + struct xrx200_chan, napi); + struct net_device *net_dev = ch->priv->net_dev; + int pkts = 0; + int bytes = 0; + + while (pkts < budget) { + struct ltq_dma_desc *desc = &ch->dma.desc_base[ch->tx_free]; + + if ((desc->ctl & (LTQ_DMA_OWN | LTQ_DMA_C)) == LTQ_DMA_C) { + struct sk_buff *skb = ch->skb[ch->tx_free]; + + pkts++; + bytes += skb->len; + ch->skb[ch->tx_free] = NULL; + consume_skb(skb); + memset(&ch->dma.desc_base[ch->tx_free], 0, + sizeof(struct ltq_dma_desc)); + ch->tx_free++; + ch->tx_free %= LTQ_DESC_NUM; + } else { + break; + } + } + + net_dev->stats.tx_packets += pkts; + net_dev->stats.tx_bytes += bytes; + netdev_completed_queue(ch->priv->net_dev, pkts, bytes); + + if (pkts < budget) { + napi_complete(&ch->napi); + ltq_dma_enable_irq(&ch->dma); + } + + return pkts; +} + +static int xrx200_start_xmit(struct sk_buff *skb, struct net_device *net_dev) +{ + struct xrx200_priv *priv = netdev_priv(net_dev); + struct xrx200_chan *ch = &priv->chan_tx; + struct ltq_dma_desc *desc = &ch->dma.desc_base[ch->dma.desc]; + u32 byte_offset; + dma_addr_t mapping; + int len; + + skb->dev = net_dev; + if (skb_put_padto(skb, ETH_ZLEN)) { + net_dev->stats.tx_dropped++; + return NETDEV_TX_OK; + } + + len = skb->len; + + if ((desc->ctl & (LTQ_DMA_OWN | LTQ_DMA_C)) || ch->skb[ch->dma.desc]) { + netdev_err(net_dev, "tx ring full\n"); + netif_stop_queue(net_dev); + return NETDEV_TX_BUSY; + } + + ch->skb[ch->dma.desc] = skb; + + mapping = dma_map_single(priv->dev, skb->data, len, DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(priv->dev, mapping))) + goto err_drop; + + /* dma needs to start on a 16 byte aligned address */ + byte_offset = mapping % 16; + + desc->addr = mapping - byte_offset; + /* Make sure the address is written before we give it to HW */ + wmb(); + desc->ctl = LTQ_DMA_OWN | LTQ_DMA_SOP | LTQ_DMA_EOP | + LTQ_DMA_TX_OFFSET(byte_offset) | (len & LTQ_DMA_SIZE_MASK); + ch->dma.desc++; + ch->dma.desc %= LTQ_DESC_NUM; + if (ch->dma.desc == ch->tx_free) + netif_stop_queue(net_dev); + + netdev_sent_queue(net_dev, len); + + return NETDEV_TX_OK; + +err_drop: + dev_kfree_skb(skb); + net_dev->stats.tx_dropped++; + net_dev->stats.tx_errors++; + return NETDEV_TX_OK; +} + +static const struct net_device_ops xrx200_netdev_ops = { + .ndo_open = xrx200_open, + .ndo_stop = xrx200_close, + .ndo_start_xmit = xrx200_start_xmit, + .ndo_set_mac_address = eth_mac_addr, + .ndo_validate_addr = eth_validate_addr, + .ndo_change_mtu = eth_change_mtu, +}; + +static irqreturn_t xrx200_dma_irq(int irq, void *ptr) +{ + struct xrx200_chan *ch = ptr; + + ltq_dma_disable_irq(&ch->dma); + ltq_dma_ack_irq(&ch->dma); + + napi_schedule(&ch->napi); + + return IRQ_HANDLED; +} + +static int xrx200_dma_init(struct xrx200_priv *priv) +{ + struct xrx200_chan *ch_rx = &priv->chan_rx; + struct xrx200_chan *ch_tx = &priv->chan_tx; + int ret = 0; + int i; + + ltq_dma_init_port(DMA_PORT_ETOP); + + ch_rx->dma.nr = XRX200_DMA_RX; + ch_rx->dma.dev = priv->dev; + ch_rx->priv = priv; + + ltq_dma_alloc_rx(&ch_rx->dma); + for (ch_rx->dma.desc = 0; ch_rx->dma.desc < LTQ_DESC_NUM; + ch_rx->dma.desc++) { + ret = xrx200_alloc_skb(ch_rx); + if (ret) + goto rx_free; + } + ch_rx->dma.desc = 0; + ret = devm_request_irq(priv->dev, ch_rx->dma.irq, xrx200_dma_irq, 0, + "xrx200_net_rx", &priv->chan_rx); + if (ret) { + dev_err(priv->dev, "failed to request RX irq %d\n", + ch_rx->dma.irq); + goto rx_ring_free; + } + + ch_tx->dma.nr = XRX200_DMA_TX; + ch_tx->dma.dev = priv->dev; + ch_tx->priv = priv; + + ltq_dma_alloc_tx(&ch_tx->dma); + ret = devm_request_irq(priv->dev, ch_tx->dma.irq, xrx200_dma_irq, 0, + "xrx200_net_tx", &priv->chan_tx); + if (ret) { + dev_err(priv->dev, "failed to request TX irq %d\n", + ch_tx->dma.irq); + goto tx_free; + } + + return ret; + +tx_free: + ltq_dma_free(&ch_tx->dma); + +rx_ring_free: + /* free the allocated RX ring */ + for (i = 0; i < LTQ_DESC_NUM; i++) { + if (priv->chan_rx.skb[i]) + dev_kfree_skb_any(priv->chan_rx.skb[i]); + } + +rx_free: + ltq_dma_free(&ch_rx->dma); + return ret; +} + +static void xrx200_hw_cleanup(struct xrx200_priv *priv) +{ + int i; + + ltq_dma_free(&priv->chan_tx.dma); + ltq_dma_free(&priv->chan_rx.dma); + + /* free the allocated RX ring */ + for (i = 0; i < LTQ_DESC_NUM; i++) + dev_kfree_skb_any(priv->chan_rx.skb[i]); +} + +static int xrx200_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct device_node *np = dev->of_node; + struct resource *res; + struct xrx200_priv *priv; + struct net_device *net_dev; + const u8 *mac; + int err; + + /* alloc the network device */ + net_dev = devm_alloc_etherdev(dev, sizeof(struct xrx200_priv)); + if (!net_dev) + return -ENOMEM; + + priv = netdev_priv(net_dev); + priv->net_dev = net_dev; + priv->dev = dev; + + net_dev->netdev_ops = &xrx200_netdev_ops; + SET_NETDEV_DEV(net_dev, dev); + net_dev->min_mtu = ETH_ZLEN; + net_dev->max_mtu = XRX200_DMA_DATA_LEN; + + /* load the memory ranges */ + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) { + dev_err(dev, "failed to get resources\n"); + return -ENOENT; + } + + priv->pmac_reg = devm_ioremap_resource(dev, res); + if (IS_ERR(priv->pmac_reg)) { + dev_err(dev, "failed to request and remap io ranges\n"); + return PTR_ERR(priv->pmac_reg); + } + + priv->chan_rx.dma.irq = platform_get_irq_byname(pdev, "rx"); + if (priv->chan_rx.dma.irq < 0) { + dev_err(dev, "failed to get RX IRQ, %i\n", + priv->chan_rx.dma.irq); + return -ENOENT; + } + priv->chan_tx.dma.irq = platform_get_irq_byname(pdev, "tx"); + if (priv->chan_tx.dma.irq < 0) { + dev_err(dev, "failed to get TX IRQ, %i\n", + priv->chan_tx.dma.irq); + return -ENOENT; + } + + /* get the clock */ + priv->clk = devm_clk_get(dev, NULL); + if (IS_ERR(priv->clk)) { + dev_err(dev, "failed to get clock\n"); + return PTR_ERR(priv->clk); + } + + mac = of_get_mac_address(np); + if (mac && is_valid_ether_addr(mac)) + ether_addr_copy(net_dev->dev_addr, mac); + else + eth_hw_addr_random(net_dev); + + /* bring up the dma engine and IP core */ + err = xrx200_dma_init(priv); + if (err) + return err; + + /* enable clock gate */ + err = clk_prepare_enable(priv->clk); + if (err) + goto err_uninit_dma; + + /* set IPG to 12 */ + xrx200_pmac_mask(priv, PMAC_RX_IPG_MASK, 0xb, PMAC_RX_IPG); + + /* enable status header, enable CRC */ + xrx200_pmac_mask(priv, 0, + PMAC_HD_CTL_RST | PMAC_HD_CTL_AST | PMAC_HD_CTL_RXSH | + PMAC_HD_CTL_AS | PMAC_HD_CTL_AC | PMAC_HD_CTL_RC, + PMAC_HD_CTL); + + /* setup NAPI */ + netif_napi_add(net_dev, &priv->chan_rx.napi, xrx200_poll_rx, 32); + netif_napi_add(net_dev, &priv->chan_tx.napi, xrx200_tx_housekeeping, 32); + + platform_set_drvdata(pdev, priv); + + err = register_netdev(net_dev); + if (err) + goto err_unprepare_clk; + return err; + +err_unprepare_clk: + clk_disable_unprepare(priv->clk); + +err_uninit_dma: + xrx200_hw_cleanup(priv); + + return 0; +} + +static int xrx200_remove(struct platform_device *pdev) +{ + struct xrx200_priv *priv = platform_get_drvdata(pdev); + struct net_device *net_dev = priv->net_dev; + + /* free stack related instances */ + netif_stop_queue(net_dev); + netif_napi_del(&priv->chan_tx.napi); + netif_napi_del(&priv->chan_rx.napi); + + /* remove the actual device */ + unregister_netdev(net_dev); + + /* release the clock */ + clk_disable_unprepare(priv->clk); + + /* shut down hardware */ + xrx200_hw_cleanup(priv); + + return 0; +} + +static const struct of_device_id xrx200_match[] = { + { .compatible = "lantiq,xrx200-net" }, + {}, +}; +MODULE_DEVICE_TABLE(of, xrx200_match); + +static struct platform_driver xrx200_driver = { + .probe = xrx200_probe, + .remove = xrx200_remove, + .driver = { + .name = "lantiq,xrx200-net", + .of_match_table = xrx200_match, + }, +}; + +module_platform_driver(xrx200_driver); + +MODULE_AUTHOR("John Crispin <john@phrozen.org>"); +MODULE_DESCRIPTION("Lantiq SoC XRX200 ethernet"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 62f204f32316..1e9bcbdc6a90 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -2733,17 +2733,17 @@ static int mv643xx_eth_shared_of_add_port(struct platform_device *pdev, memset(&res, 0, sizeof(res)); if (of_irq_to_resource(pnp, 0, &res) <= 0) { - dev_err(&pdev->dev, "missing interrupt on %s\n", pnp->name); + dev_err(&pdev->dev, "missing interrupt on %pOFn\n", pnp); return -EINVAL; } if (of_property_read_u32(pnp, "reg", &ppd.port_number)) { - dev_err(&pdev->dev, "missing reg property on %s\n", pnp->name); + dev_err(&pdev->dev, "missing reg property on %pOFn\n", pnp); return -EINVAL; } if (ppd.port_number >= 3) { - dev_err(&pdev->dev, "invalid reg property on %s\n", pnp->name); + dev_err(&pdev->dev, "invalid reg property on %pOFn\n", pnp); return -EINVAL; } diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index bc80a678abc3..fe3edb3c2bf4 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -2065,10 +2065,7 @@ static int mvneta_rx_swbm(struct napi_struct *napi, /* Linux processing */ rxq->skb->protocol = eth_type_trans(rxq->skb, dev); - if (dev->features & NETIF_F_GRO) - napi_gro_receive(napi, rxq->skb); - else - netif_receive_skb(rxq->skb); + napi_gro_receive(napi, rxq->skb); /* clean uncomplete skb pointer in queue */ rxq->skb = NULL; @@ -2510,12 +2507,13 @@ static void mvneta_tx_done_gbe(struct mvneta_port *pp, u32 cause_tx_done) { struct mvneta_tx_queue *txq; struct netdev_queue *nq; + int cpu = smp_processor_id(); while (cause_tx_done) { txq = mvneta_tx_done_policy(pp, cause_tx_done); nq = netdev_get_tx_queue(pp->dev, txq->id); - __netif_tx_lock(nq, smp_processor_id()); + __netif_tx_lock(nq, cpu); if (txq->count) mvneta_txq_done(pp, txq); @@ -4598,7 +4596,8 @@ static int mvneta_probe(struct platform_device *pdev) } } - dev->features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_TSO; + dev->features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | + NETIF_F_TSO | NETIF_F_RXCSUM; dev->hw_features |= dev->features; dev->vlan_features |= dev->features; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 32d785b616e1..702fec82d806 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -58,6 +58,8 @@ static struct { */ static void mvpp2_mac_config(struct net_device *dev, unsigned int mode, const struct phylink_link_state *state); +static void mvpp2_mac_link_up(struct net_device *dev, unsigned int mode, + phy_interface_t interface, struct phy_device *phy); /* Queue modes */ #define MVPP2_QDIST_SINGLE_MODE 0 @@ -3142,6 +3144,7 @@ static void mvpp2_start_dev(struct mvpp2_port *port) mvpp22_mode_reconfigure(port); if (port->phylink) { + netif_carrier_off(port->dev); phylink_start(port->phylink); } else { /* Phylink isn't used as of now for ACPI, so the MAC has to be @@ -3150,9 +3153,10 @@ static void mvpp2_start_dev(struct mvpp2_port *port) */ struct phylink_link_state state = { .interface = port->phy_interface, - .link = 1, }; mvpp2_mac_config(port->dev, MLO_AN_INBAND, &state); + mvpp2_mac_link_up(port->dev, MLO_AN_INBAND, port->phy_interface, + NULL); } netif_tx_start_all_queues(port->dev); @@ -4495,10 +4499,6 @@ static void mvpp2_mac_config(struct net_device *dev, unsigned int mode, return; } - netif_tx_stop_all_queues(port->dev); - if (!port->has_phy) - netif_carrier_off(port->dev); - /* Make sure the port is disabled when reconfiguring the mode */ mvpp2_port_disable(port); @@ -4523,16 +4523,7 @@ static void mvpp2_mac_config(struct net_device *dev, unsigned int mode, if (port->priv->hw_version == MVPP21 && port->flags & MVPP2_F_LOOPBACK) mvpp2_port_loopback_set(port, state); - /* If the port already was up, make sure it's still in the same state */ - if (state->link || !port->has_phy) { - mvpp2_port_enable(port); - - mvpp2_egress_enable(port); - mvpp2_ingress_enable(port); - if (!port->has_phy) - netif_carrier_on(dev); - netif_tx_wake_all_queues(dev); - } + mvpp2_port_enable(port); } static void mvpp2_mac_link_up(struct net_device *dev, unsigned int mode, @@ -4803,6 +4794,7 @@ static int mvpp2_port_probe(struct platform_device *pdev, dev->min_mtu = ETH_MIN_MTU; /* 9704 == 9728 - 20 and rounding to 8 */ dev->max_mtu = MVPP2_BM_JUMBO_PKT_SIZE; + dev->dev.of_node = port_node; /* Phylink isn't used w/ ACPI as of now */ if (port_node) { diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 6e6abdc399de..cc1e9a96a43b 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -355,12 +355,8 @@ static int mtk_phy_connect(struct net_device *dev) dev->phydev->speed = 0; dev->phydev->duplex = 0; - if (of_phy_is_fixed_link(mac->of_node)) - dev->phydev->supported |= - SUPPORTED_Pause | SUPPORTED_Asym_Pause; - - dev->phydev->supported &= PHY_GBIT_FEATURES | SUPPORTED_Pause | - SUPPORTED_Asym_Pause; + phy_set_max_speed(dev->phydev, SPEED_1000); + phy_support_asym_pause(dev->phydev); dev->phydev->advertising = dev->phydev->supported | ADVERTISED_Autoneg; phy_start_aneg(dev->phydev); @@ -405,7 +401,7 @@ static int mtk_mdio_init(struct mtk_eth *eth) eth->mii_bus->priv = eth; eth->mii_bus->parent = eth->dev; - snprintf(eth->mii_bus->id, MII_BUS_ID_SIZE, "%s", mii_np->name); + snprintf(eth->mii_bus->id, MII_BUS_ID_SIZE, "%pOFn", mii_np); ret = of_mdiobus_register(eth->mii_bus, mii_np); err_put_node: diff --git a/drivers/net/ethernet/mellanox/mlx4/alloc.c b/drivers/net/ethernet/mellanox/mlx4/alloc.c index 4bdf25059542..deef5a998985 100644 --- a/drivers/net/ethernet/mellanox/mlx4/alloc.c +++ b/drivers/net/ethernet/mellanox/mlx4/alloc.c @@ -614,7 +614,7 @@ int mlx4_buf_alloc(struct mlx4_dev *dev, int size, int max_direct, int i; buf->direct.buf = NULL; - buf->nbufs = (size + PAGE_SIZE - 1) / PAGE_SIZE; + buf->nbufs = DIV_ROUND_UP(size, PAGE_SIZE); buf->npages = buf->nbufs; buf->page_shift = PAGE_SHIFT; buf->page_list = kcalloc(buf->nbufs, sizeof(*buf->page_list), diff --git a/drivers/net/ethernet/mellanox/mlx4/icm.c b/drivers/net/ethernet/mellanox/mlx4/icm.c index 7262c6310650..4b4351141b94 100644 --- a/drivers/net/ethernet/mellanox/mlx4/icm.c +++ b/drivers/net/ethernet/mellanox/mlx4/icm.c @@ -406,7 +406,7 @@ int mlx4_init_icm_table(struct mlx4_dev *dev, struct mlx4_icm_table *table, obj_per_chunk = MLX4_TABLE_CHUNK_SIZE / obj_size; if (WARN_ON(!obj_per_chunk)) return -EINVAL; - num_icm = (nobj + obj_per_chunk - 1) / obj_per_chunk; + num_icm = DIV_ROUND_UP(nobj, obj_per_chunk); table->icm = kvcalloc(num_icm, sizeof(*table->icm), GFP_KERNEL); if (!table->icm) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c index b994b80d5714..37ba7c78859d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c @@ -132,11 +132,11 @@ void mlx5_add_device(struct mlx5_interface *intf, struct mlx5_priv *priv) delayed_event_start(priv); dev_ctx->context = intf->add(dev); - set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state); - if (intf->attach) - set_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state); - if (dev_ctx->context) { + set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state); + if (intf->attach) + set_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state); + spin_lock_irq(&priv->ctx_lock); list_add_tail(&dev_ctx->list, &priv->ctx_list); @@ -211,12 +211,17 @@ static void mlx5_attach_interface(struct mlx5_interface *intf, struct mlx5_priv if (intf->attach) { if (test_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state)) goto out; - intf->attach(dev, dev_ctx->context); + if (intf->attach(dev, dev_ctx->context)) + goto out; + set_bit(MLX5_INTERFACE_ATTACHED, &dev_ctx->state); } else { if (test_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state)) goto out; dev_ctx->context = intf->add(dev); + if (!dev_ctx->context) + goto out; + set_bit(MLX5_INTERFACE_ADDED, &dev_ctx->state); } @@ -391,16 +396,17 @@ void mlx5_remove_dev_by_protocol(struct mlx5_core_dev *dev, int protocol) } } -static u16 mlx5_gen_pci_id(struct mlx5_core_dev *dev) +static u32 mlx5_gen_pci_id(struct mlx5_core_dev *dev) { - return (u16)((dev->pdev->bus->number << 8) | + return (u32)((pci_domain_nr(dev->pdev->bus) << 16) | + (dev->pdev->bus->number << 8) | PCI_SLOT(dev->pdev->devfn)); } /* Must be called with intf_mutex held */ struct mlx5_core_dev *mlx5_get_next_phys_dev(struct mlx5_core_dev *dev) { - u16 pci_id = mlx5_gen_pci_id(dev); + u32 pci_id = mlx5_gen_pci_id(dev); struct mlx5_core_dev *res = NULL; struct mlx5_core_dev *tmp_dev; struct mlx5_priv *priv; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index db2cfcd21d43..01a967e717e7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -204,13 +204,6 @@ struct mlx5e_umr_wqe { extern const char mlx5e_self_tests[][ETH_GSTRING_LEN]; -static const char mlx5e_priv_flags[][ETH_GSTRING_LEN] = { - "rx_cqe_moder", - "tx_cqe_moder", - "rx_cqe_compress", - "rx_striding_rq", -}; - enum mlx5e_priv_flag { MLX5E_PFLAG_RX_CQE_BASED_MODER = (1 << 0), MLX5E_PFLAG_TX_CQE_BASED_MODER = (1 << 1), @@ -905,6 +898,12 @@ void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev); int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb); /* common netdev helpers */ +void mlx5e_create_q_counters(struct mlx5e_priv *priv); +void mlx5e_destroy_q_counters(struct mlx5e_priv *priv); +int mlx5e_open_drop_rq(struct mlx5e_priv *priv, + struct mlx5e_rq *drop_rq); +void mlx5e_close_drop_rq(struct mlx5e_rq *drop_rq); + int mlx5e_create_indirect_rqt(struct mlx5e_priv *priv); int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 98dd3e0ada72..8cd338ceb237 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -135,6 +135,13 @@ void mlx5e_build_ptys2ethtool_map(void) ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT); } +static const char mlx5e_priv_flags[][ETH_GSTRING_LEN] = { + "rx_cqe_moder", + "tx_cqe_moder", + "rx_cqe_compress", + "rx_striding_rq", +}; + int mlx5e_ethtool_get_sset_count(struct mlx5e_priv *priv, int sset) { int i, num_stats = 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c index 75bb981e00b7..41cde926cdab 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c @@ -191,7 +191,7 @@ set_udp(void *headers_c, void *headers_v, __be16 psrc_m, __be16 psrc_v, { if (psrc_m) { MLX5E_FTE_SET(headers_c, udp_sport, 0xffff); - MLX5E_FTE_SET(headers_c, udp_sport, ntohs(psrc_v)); + MLX5E_FTE_SET(headers_v, udp_sport, ntohs(psrc_v)); } if (pdst_m) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 5a7939e70190..d14c4051edd8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3049,8 +3049,8 @@ static int mlx5e_alloc_drop_cq(struct mlx5_core_dev *mdev, return mlx5e_alloc_cq_common(mdev, param, cq); } -static int mlx5e_open_drop_rq(struct mlx5e_priv *priv, - struct mlx5e_rq *drop_rq) +int mlx5e_open_drop_rq(struct mlx5e_priv *priv, + struct mlx5e_rq *drop_rq) { struct mlx5_core_dev *mdev = priv->mdev; struct mlx5e_cq_param cq_param = {}; @@ -3094,7 +3094,7 @@ err_free_cq: return err; } -static void mlx5e_close_drop_rq(struct mlx5e_rq *drop_rq) +void mlx5e_close_drop_rq(struct mlx5e_rq *drop_rq) { mlx5e_destroy_rq(drop_rq); mlx5e_free_rq(drop_rq); @@ -4726,7 +4726,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) mlx5e_tls_build_netdev(priv); } -static void mlx5e_create_q_counters(struct mlx5e_priv *priv) +void mlx5e_create_q_counters(struct mlx5e_priv *priv) { struct mlx5_core_dev *mdev = priv->mdev; int err; @@ -4744,7 +4744,7 @@ static void mlx5e_create_q_counters(struct mlx5e_priv *priv) } } -static void mlx5e_destroy_q_counters(struct mlx5e_priv *priv) +void mlx5e_destroy_q_counters(struct mlx5e_priv *priv) { if (priv->q_counter) mlx5_core_dealloc_q_counter(priv->mdev, priv->q_counter); @@ -4783,9 +4783,17 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv) struct mlx5_core_dev *mdev = priv->mdev; int err; + mlx5e_create_q_counters(priv); + + err = mlx5e_open_drop_rq(priv, &priv->drop_rq); + if (err) { + mlx5_core_err(mdev, "open drop rq failed, %d\n", err); + goto err_destroy_q_counters; + } + err = mlx5e_create_indirect_rqt(priv); if (err) - return err; + goto err_close_drop_rq; err = mlx5e_create_direct_rqts(priv); if (err) @@ -4821,6 +4829,10 @@ err_destroy_direct_rqts: mlx5e_destroy_direct_rqts(priv); err_destroy_indirect_rqts: mlx5e_destroy_rqt(priv, &priv->indir_rqt); +err_close_drop_rq: + mlx5e_close_drop_rq(&priv->drop_rq); +err_destroy_q_counters: + mlx5e_destroy_q_counters(priv); return err; } @@ -4832,6 +4844,8 @@ static void mlx5e_cleanup_nic_rx(struct mlx5e_priv *priv) mlx5e_destroy_indirect_tirs(priv); mlx5e_destroy_direct_rqts(priv); mlx5e_destroy_rqt(priv, &priv->indir_rqt); + mlx5e_close_drop_rq(&priv->drop_rq); + mlx5e_destroy_q_counters(priv); } static int mlx5e_init_nic_tx(struct mlx5e_priv *priv) @@ -4975,7 +4989,6 @@ err_cleanup_nic: int mlx5e_attach_netdev(struct mlx5e_priv *priv) { - struct mlx5_core_dev *mdev = priv->mdev; const struct mlx5e_profile *profile; int err; @@ -4986,28 +4999,16 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv) if (err) goto out; - mlx5e_create_q_counters(priv); - - err = mlx5e_open_drop_rq(priv, &priv->drop_rq); - if (err) { - mlx5_core_err(mdev, "open drop rq failed, %d\n", err); - goto err_destroy_q_counters; - } - err = profile->init_rx(priv); if (err) - goto err_close_drop_rq; + goto err_cleanup_tx; if (profile->enable) profile->enable(priv); return 0; -err_close_drop_rq: - mlx5e_close_drop_rq(&priv->drop_rq); - -err_destroy_q_counters: - mlx5e_destroy_q_counters(priv); +err_cleanup_tx: profile->cleanup_tx(priv); out: @@ -5025,8 +5026,6 @@ void mlx5e_detach_netdev(struct mlx5e_priv *priv) flush_workqueue(priv->wq); profile->cleanup_rx(priv); - mlx5e_close_drop_rq(&priv->drop_rq); - mlx5e_destroy_q_counters(priv); profile->cleanup_tx(priv); cancel_delayed_work_sync(&priv->update_stats_work); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index c9cc9747d21d..f6eead24931f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -999,14 +999,21 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv) struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_eswitch_rep *rep = rpriv->rep; + struct mlx5_core_dev *mdev = priv->mdev; struct mlx5_flow_handle *flow_rule; int err; mlx5e_init_l2_addr(priv); + err = mlx5e_open_drop_rq(priv, &priv->drop_rq); + if (err) { + mlx5_core_err(mdev, "open drop rq failed, %d\n", err); + return err; + } + err = mlx5e_create_direct_rqts(priv); if (err) - return err; + goto err_close_drop_rq; err = mlx5e_create_direct_tirs(priv); if (err) @@ -1027,6 +1034,8 @@ err_destroy_direct_tirs: mlx5e_destroy_direct_tirs(priv); err_destroy_direct_rqts: mlx5e_destroy_direct_rqts(priv); +err_close_drop_rq: + mlx5e_close_drop_rq(&priv->drop_rq); return err; } @@ -1037,6 +1046,7 @@ static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv) mlx5_del_flow_rules(rpriv->vport_rx_rule); mlx5e_destroy_direct_tirs(priv); mlx5e_destroy_direct_rqts(priv); + mlx5e_close_drop_rq(&priv->drop_rq); } static int mlx5e_init_rep_tx(struct mlx5e_priv *priv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 15d8ae28c040..424bc89184c6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -37,6 +37,7 @@ #include <net/busy_poll.h> #include <net/ip6_checksum.h> #include <net/page_pool.h> +#include <net/inet_ecn.h> #include "en.h" #include "en_tc.h" #include "eswitch.h" @@ -690,12 +691,29 @@ static inline void mlx5e_skb_set_hash(struct mlx5_cqe64 *cqe, skb_set_hash(skb, be32_to_cpu(cqe->rss_hash_result), ht); } -static inline bool is_last_ethertype_ip(struct sk_buff *skb, int *network_depth) +static inline bool is_last_ethertype_ip(struct sk_buff *skb, int *network_depth, + __be16 *proto) { - __be16 ethertype = ((struct ethhdr *)skb->data)->h_proto; + *proto = ((struct ethhdr *)skb->data)->h_proto; + *proto = __vlan_get_protocol(skb, *proto, network_depth); + return (*proto == htons(ETH_P_IP) || *proto == htons(ETH_P_IPV6)); +} + +static inline void mlx5e_enable_ecn(struct mlx5e_rq *rq, struct sk_buff *skb) +{ + int network_depth = 0; + __be16 proto; + void *ip; + int rc; - ethertype = __vlan_get_protocol(skb, ethertype, network_depth); - return (ethertype == htons(ETH_P_IP) || ethertype == htons(ETH_P_IPV6)); + if (unlikely(!is_last_ethertype_ip(skb, &network_depth, &proto))) + return; + + ip = skb->data + network_depth; + rc = ((proto == htons(ETH_P_IP)) ? IP_ECN_set_ce((struct iphdr *)ip) : + IP6_ECN_set_ce(skb, (struct ipv6hdr *)ip)); + + rq->stats->ecn_mark += !!rc; } static __be32 mlx5e_get_fcs(struct sk_buff *skb) @@ -737,6 +755,14 @@ static __be32 mlx5e_get_fcs(struct sk_buff *skb) return fcs_bytes; } +static u8 get_ip_proto(struct sk_buff *skb, __be16 proto) +{ + void *ip_p = skb->data + sizeof(struct ethhdr); + + return (proto == htons(ETH_P_IP)) ? ((struct iphdr *)ip_p)->protocol : + ((struct ipv6hdr *)ip_p)->nexthdr; +} + static inline void mlx5e_handle_csum(struct net_device *netdev, struct mlx5_cqe64 *cqe, struct mlx5e_rq *rq, @@ -745,6 +771,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev, { struct mlx5e_rq_stats *stats = rq->stats; int network_depth = 0; + __be16 proto; if (unlikely(!(netdev->features & NETIF_F_RXCSUM))) goto csum_none; @@ -755,7 +782,10 @@ static inline void mlx5e_handle_csum(struct net_device *netdev, return; } - if (likely(is_last_ethertype_ip(skb, &network_depth))) { + if (likely(is_last_ethertype_ip(skb, &network_depth, &proto))) { + if (unlikely(get_ip_proto(skb, proto) == IPPROTO_SCTP)) + goto csum_unnecessary; + skb->ip_summed = CHECKSUM_COMPLETE; skb->csum = csum_unfold((__force __sum16)cqe->check_sum); if (network_depth > ETH_HLEN) @@ -773,6 +803,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev, return; } +csum_unnecessary: if (likely((cqe->hds_ip_ext & CQE_L3_OK) && (cqe->hds_ip_ext & CQE_L4_OK))) { skb->ip_summed = CHECKSUM_UNNECESSARY; @@ -790,6 +821,8 @@ csum_none: stats->csum_none++; } +#define MLX5E_CE_BIT_MASK 0x80 + static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe, u32 cqe_bcnt, struct mlx5e_rq *rq, @@ -834,6 +867,10 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe, skb->mark = be32_to_cpu(cqe->sop_drop_qpn) & MLX5E_TC_FLOW_ID_MASK; mlx5e_handle_csum(netdev, cqe, rq, skb, !!lro_num_seg); + /* checking CE bit in cqe - MSB in ml_path field */ + if (unlikely(cqe->ml_path & MLX5E_CE_BIT_MASK)) + mlx5e_enable_ecn(rq, skb); + skb->protocol = eth_type_trans(skb, netdev); } @@ -1230,8 +1267,8 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq, u32 cqe_bcnt, struct sk_buff *skb) { - struct mlx5e_rq_stats *stats = rq->stats; struct hwtstamp_config *tstamp; + struct mlx5e_rq_stats *stats; struct net_device *netdev; struct mlx5e_priv *priv; char *pseudo_header; @@ -1254,6 +1291,7 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq, priv = mlx5i_epriv(netdev); tstamp = &priv->tstamp; + stats = &priv->channel_stats[rq->ix].rq; g = (be32_to_cpu(cqe->flags_rqpn) >> 28) & 3; dgid = skb->data + MLX5_IB_GRH_DGID_OFFSET; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index 6839481f7697..90c7607b1f44 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -53,6 +53,7 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_lro_packets) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_lro_bytes) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_ecn_mark) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_removed_vlan_packets) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_none) }, @@ -144,6 +145,7 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv) s->rx_bytes += rq_stats->bytes; s->rx_lro_packets += rq_stats->lro_packets; s->rx_lro_bytes += rq_stats->lro_bytes; + s->rx_ecn_mark += rq_stats->ecn_mark; s->rx_removed_vlan_packets += rq_stats->removed_vlan_packets; s->rx_csum_none += rq_stats->csum_none; s->rx_csum_complete += rq_stats->csum_complete; @@ -1144,6 +1146,7 @@ static const struct counter_desc rq_stats_desc[] = { { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_redirect) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_packets) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_bytes) }, + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, ecn_mark) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, removed_vlan_packets) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, wqe_err) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_filler_cqes) }, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index a4c035aedd46..a5fb3dc27f50 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -66,6 +66,7 @@ struct mlx5e_sw_stats { u64 tx_nop; u64 rx_lro_packets; u64 rx_lro_bytes; + u64 rx_ecn_mark; u64 rx_removed_vlan_packets; u64 rx_csum_unnecessary; u64 rx_csum_none; @@ -184,6 +185,7 @@ struct mlx5e_rq_stats { u64 csum_none; u64 lro_packets; u64 lro_bytes; + u64 ecn_mark; u64 removed_vlan_packets; u64 xdp_drop; u64 xdp_redirect; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 9131a1376e7d..9fed54017659 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1982,14 +1982,15 @@ static bool modify_header_match_supported(struct mlx5_flow_spec *spec, goto out_ok; modify_ip_header = false; - tcf_exts_to_list(exts, &actions); - list_for_each_entry(a, &actions, list) { + tcf_exts_for_each_action(i, a, exts) { + int k; + if (!is_tcf_pedit(a)) continue; nkeys = tcf_pedit_nkeys(a); - for (i = 0; i < nkeys; i++) { - htype = tcf_pedit_htype(a, i); + for (k = 0; k < nkeys; k++) { + htype = tcf_pedit_htype(a, k); if (htype == TCA_PEDIT_KEY_EX_HDR_TYPE_IP4 || htype == TCA_PEDIT_KEY_EX_HDR_TYPE_IP6) { modify_ip_header = true; @@ -2053,15 +2054,14 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, const struct tc_action *a; LIST_HEAD(actions); u32 action = 0; - int err; + int err, i; if (!tcf_exts_has_actions(exts)) return -EINVAL; attr->flow_tag = MLX5_FS_DEFAULT_FLOW_TAG; - tcf_exts_to_list(exts, &actions); - list_for_each_entry(a, &actions, list) { + tcf_exts_for_each_action(i, a, exts) { if (is_tcf_gact_shot(a)) { action |= MLX5_FLOW_CONTEXT_ACTION_DROP; if (MLX5_CAP_FLOWTABLE(priv->mdev, @@ -2666,7 +2666,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, LIST_HEAD(actions); bool encap = false; u32 action = 0; - int err; + int err, i; if (!tcf_exts_has_actions(exts)) return -EINVAL; @@ -2674,8 +2674,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts, attr->in_rep = rpriv->rep; attr->in_mdev = priv->mdev; - tcf_exts_to_list(exts, &actions); - list_for_each_entry(a, &actions, list) { + tcf_exts_for_each_action(i, a, exts) { if (is_tcf_gact_shot(a)) { action |= MLX5_FLOW_CONTEXT_ACTION_DROP | MLX5_FLOW_CONTEXT_ACTION_COUNT; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index f72b5c9dcfe9..3028e8d90920 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -663,6 +663,7 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports) if (err) goto miss_rule_err; + kvfree(flow_group_in); return 0; miss_rule_err: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index f418541af7cf..37d114c668b7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -1578,6 +1578,33 @@ static u64 matched_fgs_get_version(struct list_head *match_head) return version; } +static struct fs_fte * +lookup_fte_locked(struct mlx5_flow_group *g, + u32 *match_value, + bool take_write) +{ + struct fs_fte *fte_tmp; + + if (take_write) + nested_down_write_ref_node(&g->node, FS_LOCK_PARENT); + else + nested_down_read_ref_node(&g->node, FS_LOCK_PARENT); + fte_tmp = rhashtable_lookup_fast(&g->ftes_hash, match_value, + rhash_fte); + if (!fte_tmp || !tree_get_node(&fte_tmp->node)) { + fte_tmp = NULL; + goto out; + } + + nested_down_write_ref_node(&fte_tmp->node, FS_LOCK_CHILD); +out: + if (take_write) + up_write_ref_node(&g->node); + else + up_read_ref_node(&g->node); + return fte_tmp; +} + static struct mlx5_flow_handle * try_add_to_existing_fg(struct mlx5_flow_table *ft, struct list_head *match_head, @@ -1600,10 +1627,6 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft, if (IS_ERR(fte)) return ERR_PTR(-ENOMEM); - list_for_each_entry(iter, match_head, list) { - nested_down_read_ref_node(&iter->g->node, FS_LOCK_PARENT); - } - search_again_locked: version = matched_fgs_get_version(match_head); /* Try to find a fg that already contains a matching fte */ @@ -1611,20 +1634,9 @@ search_again_locked: struct fs_fte *fte_tmp; g = iter->g; - fte_tmp = rhashtable_lookup_fast(&g->ftes_hash, spec->match_value, - rhash_fte); - if (!fte_tmp || !tree_get_node(&fte_tmp->node)) + fte_tmp = lookup_fte_locked(g, spec->match_value, take_write); + if (!fte_tmp) continue; - - nested_down_write_ref_node(&fte_tmp->node, FS_LOCK_CHILD); - if (!take_write) { - list_for_each_entry(iter, match_head, list) - up_read_ref_node(&iter->g->node); - } else { - list_for_each_entry(iter, match_head, list) - up_write_ref_node(&iter->g->node); - } - rule = add_rule_fg(g, spec->match_value, flow_act, dest, dest_num, fte_tmp); up_write_ref_node(&fte_tmp->node); @@ -1633,19 +1645,6 @@ search_again_locked: return rule; } - /* No group with matching fte found. Try to add a new fte to any - * matching fg. - */ - - if (!take_write) { - list_for_each_entry(iter, match_head, list) - up_read_ref_node(&iter->g->node); - list_for_each_entry(iter, match_head, list) - nested_down_write_ref_node(&iter->g->node, - FS_LOCK_PARENT); - take_write = true; - } - /* Check the ft version, for case that new flow group * was added while the fgs weren't locked */ @@ -1657,27 +1656,30 @@ search_again_locked: /* Check the fgs version, for case the new FTE with the * same values was added while the fgs weren't locked */ - if (version != matched_fgs_get_version(match_head)) + if (version != matched_fgs_get_version(match_head)) { + take_write = true; goto search_again_locked; + } list_for_each_entry(iter, match_head, list) { g = iter->g; if (!g->node.active) continue; + + nested_down_write_ref_node(&g->node, FS_LOCK_PARENT); + err = insert_fte(g, fte); if (err) { + up_write_ref_node(&g->node); if (err == -ENOSPC) continue; - list_for_each_entry(iter, match_head, list) - up_write_ref_node(&iter->g->node); kmem_cache_free(steering->ftes_cache, fte); return ERR_PTR(err); } nested_down_write_ref_node(&fte->node, FS_LOCK_CHILD); - list_for_each_entry(iter, match_head, list) - up_write_ref_node(&iter->g->node); + up_write_ref_node(&g->node); rule = add_rule_fg(g, spec->match_value, flow_act, dest, dest_num, fte); up_write_ref_node(&fte->node); @@ -1686,8 +1688,6 @@ search_again_locked: } rule = ERR_PTR(-ENOENT); out: - list_for_each_entry(iter, match_head, list) - up_write_ref_node(&iter->g->node); kmem_cache_free(steering->ftes_cache, fte); return rule; } @@ -1726,6 +1726,8 @@ search_again_locked: if (err) { if (take_write) up_write_ref_node(&ft->node); + else + up_read_ref_node(&ft->node); return ERR_PTR(err); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 32070e5d993d..a06f83c0c2b6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -36,6 +36,7 @@ #include <linux/refcount.h> #include <linux/mlx5/fs.h> #include <linux/rhashtable.h> +#include <linux/llist.h> enum fs_node_type { FS_TYPE_NAMESPACE, @@ -138,8 +139,9 @@ struct mlx5_fc_cache { }; struct mlx5_fc { - struct rb_node node; struct list_head list; + struct llist_node addlist; + struct llist_node dellist; /* last{packets,bytes} members are used when calculating the delta since * last reading @@ -148,7 +150,6 @@ struct mlx5_fc { u64 lastbytes; u32 id; - bool deleted; bool aging; struct mlx5_fc_cache cache ____cacheline_aligned_in_smp; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c index 58af6be13dfa..09206c4acd9a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c @@ -52,11 +52,13 @@ * access to counter list: * - create (user context) * - mlx5_fc_create() only adds to an addlist to be used by - * mlx5_fc_stats_query_work(). addlist is protected by a spinlock. + * mlx5_fc_stats_query_work(). addlist is a lockless single linked list + * that doesn't require any additional synchronization when adding single + * node. * - spawn thread to do the actual destroy * * - destroy (user context) - * - mark a counter as deleted + * - add a counter to lockless dellist * - spawn thread to do the actual del * * - dump (user context) @@ -71,36 +73,43 @@ * elapsed, the thread will actually query the hardware. */ -static void mlx5_fc_stats_insert(struct rb_root *root, struct mlx5_fc *counter) +static struct list_head *mlx5_fc_counters_lookup_next(struct mlx5_core_dev *dev, + u32 id) { - struct rb_node **new = &root->rb_node; - struct rb_node *parent = NULL; - - while (*new) { - struct mlx5_fc *this = rb_entry(*new, struct mlx5_fc, node); - int result = counter->id - this->id; - - parent = *new; - if (result < 0) - new = &((*new)->rb_left); - else - new = &((*new)->rb_right); - } + struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + unsigned long next_id = (unsigned long)id + 1; + struct mlx5_fc *counter; + + rcu_read_lock(); + /* skip counters that are in idr, but not yet in counters list */ + while ((counter = idr_get_next_ul(&fc_stats->counters_idr, + &next_id)) != NULL && + list_empty(&counter->list)) + next_id++; + rcu_read_unlock(); + + return counter ? &counter->list : &fc_stats->counters; +} - /* Add new node and rebalance tree. */ - rb_link_node(&counter->node, parent, new); - rb_insert_color(&counter->node, root); +static void mlx5_fc_stats_insert(struct mlx5_core_dev *dev, + struct mlx5_fc *counter) +{ + struct list_head *next = mlx5_fc_counters_lookup_next(dev, counter->id); + + list_add_tail(&counter->list, next); } -/* The function returns the last node that was queried so the caller +/* The function returns the last counter that was queried so the caller * function can continue calling it till all counters are queried. */ -static struct rb_node *mlx5_fc_stats_query(struct mlx5_core_dev *dev, +static struct mlx5_fc *mlx5_fc_stats_query(struct mlx5_core_dev *dev, struct mlx5_fc *first, u32 last_id) { + struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + struct mlx5_fc *counter = NULL; struct mlx5_cmd_fc_bulk *b; - struct rb_node *node = NULL; + bool more = false; u32 afirst_id; int num; int err; @@ -130,14 +139,16 @@ static struct rb_node *mlx5_fc_stats_query(struct mlx5_core_dev *dev, goto out; } - for (node = &first->node; node; node = rb_next(node)) { - struct mlx5_fc *counter = rb_entry(node, struct mlx5_fc, node); + counter = first; + list_for_each_entry_from(counter, &fc_stats->counters, list) { struct mlx5_fc_cache *c = &counter->cache; u64 packets; u64 bytes; - if (counter->id > last_id) + if (counter->id > last_id) { + more = true; break; + } mlx5_cmd_fc_bulk_get(dev, b, counter->id, &packets, &bytes); @@ -153,7 +164,14 @@ static struct rb_node *mlx5_fc_stats_query(struct mlx5_core_dev *dev, out: mlx5_cmd_fc_bulk_free(b); - return node; + return more ? counter : NULL; +} + +static void mlx5_free_fc(struct mlx5_core_dev *dev, + struct mlx5_fc *counter) +{ + mlx5_cmd_fc_free(dev, counter->id); + kfree(counter); } static void mlx5_fc_stats_work(struct work_struct *work) @@ -161,52 +179,33 @@ static void mlx5_fc_stats_work(struct work_struct *work) struct mlx5_core_dev *dev = container_of(work, struct mlx5_core_dev, priv.fc_stats.work.work); struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + struct llist_node *tmplist = llist_del_all(&fc_stats->addlist); + struct mlx5_fc *counter = NULL, *last = NULL, *tmp; unsigned long now = jiffies; - struct mlx5_fc *counter = NULL; - struct mlx5_fc *last = NULL; - struct rb_node *node; - LIST_HEAD(tmplist); - - spin_lock(&fc_stats->addlist_lock); - list_splice_tail_init(&fc_stats->addlist, &tmplist); - - if (!list_empty(&tmplist) || !RB_EMPTY_ROOT(&fc_stats->counters)) + if (tmplist || !list_empty(&fc_stats->counters)) queue_delayed_work(fc_stats->wq, &fc_stats->work, fc_stats->sampling_interval); - spin_unlock(&fc_stats->addlist_lock); - - list_for_each_entry(counter, &tmplist, list) - mlx5_fc_stats_insert(&fc_stats->counters, counter); - - node = rb_first(&fc_stats->counters); - while (node) { - counter = rb_entry(node, struct mlx5_fc, node); - - node = rb_next(node); - - if (counter->deleted) { - rb_erase(&counter->node, &fc_stats->counters); + llist_for_each_entry(counter, tmplist, addlist) + mlx5_fc_stats_insert(dev, counter); - mlx5_cmd_fc_free(dev, counter->id); - - kfree(counter); - continue; - } + tmplist = llist_del_all(&fc_stats->dellist); + llist_for_each_entry_safe(counter, tmp, tmplist, dellist) { + list_del(&counter->list); - last = counter; + mlx5_free_fc(dev, counter); } - if (time_before(now, fc_stats->next_query) || !last) + if (time_before(now, fc_stats->next_query) || + list_empty(&fc_stats->counters)) return; + last = list_last_entry(&fc_stats->counters, struct mlx5_fc, list); - node = rb_first(&fc_stats->counters); - while (node) { - counter = rb_entry(node, struct mlx5_fc, node); - - node = mlx5_fc_stats_query(dev, counter, last->id); - } + counter = list_first_entry(&fc_stats->counters, struct mlx5_fc, + list); + while (counter) + counter = mlx5_fc_stats_query(dev, counter, last->id); fc_stats->next_query = now + fc_stats->sampling_interval; } @@ -220,24 +219,38 @@ struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging) counter = kzalloc(sizeof(*counter), GFP_KERNEL); if (!counter) return ERR_PTR(-ENOMEM); + INIT_LIST_HEAD(&counter->list); err = mlx5_cmd_fc_alloc(dev, &counter->id); if (err) goto err_out; if (aging) { + u32 id = counter->id; + counter->cache.lastuse = jiffies; counter->aging = true; - spin_lock(&fc_stats->addlist_lock); - list_add(&counter->list, &fc_stats->addlist); - spin_unlock(&fc_stats->addlist_lock); + idr_preload(GFP_KERNEL); + spin_lock(&fc_stats->counters_idr_lock); + + err = idr_alloc_u32(&fc_stats->counters_idr, counter, &id, id, + GFP_NOWAIT); + + spin_unlock(&fc_stats->counters_idr_lock); + idr_preload_end(); + if (err) + goto err_out_alloc; + + llist_add(&counter->addlist, &fc_stats->addlist); mod_delayed_work(fc_stats->wq, &fc_stats->work, 0); } return counter; +err_out_alloc: + mlx5_cmd_fc_free(dev, counter->id); err_out: kfree(counter); @@ -253,13 +266,16 @@ void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter) return; if (counter->aging) { - counter->deleted = true; + spin_lock(&fc_stats->counters_idr_lock); + WARN_ON(!idr_remove(&fc_stats->counters_idr, counter->id)); + spin_unlock(&fc_stats->counters_idr_lock); + + llist_add(&counter->dellist, &fc_stats->dellist); mod_delayed_work(fc_stats->wq, &fc_stats->work, 0); return; } - mlx5_cmd_fc_free(dev, counter->id); - kfree(counter); + mlx5_free_fc(dev, counter); } EXPORT_SYMBOL(mlx5_fc_destroy); @@ -267,9 +283,11 @@ int mlx5_init_fc_stats(struct mlx5_core_dev *dev) { struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; - fc_stats->counters = RB_ROOT; - INIT_LIST_HEAD(&fc_stats->addlist); - spin_lock_init(&fc_stats->addlist_lock); + spin_lock_init(&fc_stats->counters_idr_lock); + idr_init(&fc_stats->counters_idr); + INIT_LIST_HEAD(&fc_stats->counters); + init_llist_head(&fc_stats->addlist); + init_llist_head(&fc_stats->dellist); fc_stats->wq = create_singlethread_workqueue("mlx5_fc"); if (!fc_stats->wq) @@ -284,34 +302,22 @@ int mlx5_init_fc_stats(struct mlx5_core_dev *dev) void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev) { struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + struct llist_node *tmplist; struct mlx5_fc *counter; struct mlx5_fc *tmp; - struct rb_node *node; cancel_delayed_work_sync(&dev->priv.fc_stats.work); destroy_workqueue(dev->priv.fc_stats.wq); dev->priv.fc_stats.wq = NULL; - list_for_each_entry_safe(counter, tmp, &fc_stats->addlist, list) { - list_del(&counter->list); - - mlx5_cmd_fc_free(dev, counter->id); + idr_destroy(&fc_stats->counters_idr); - kfree(counter); - } + tmplist = llist_del_all(&fc_stats->addlist); + llist_for_each_entry_safe(counter, tmp, tmplist, addlist) + mlx5_free_fc(dev, counter); - node = rb_first(&fc_stats->counters); - while (node) { - counter = rb_entry(node, struct mlx5_fc, node); - - node = rb_next(node); - - rb_erase(&counter->node, &fc_stats->counters); - - mlx5_cmd_fc_free(dev, counter->id); - - kfree(counter); - } + list_for_each_entry_safe(counter, tmp, &fc_stats->counters, list) + mlx5_free_fc(dev, counter); } int mlx5_fc_query(struct mlx5_core_dev *dev, struct mlx5_fc *counter, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index d39b0b7011b2..9f39aeca863f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -331,9 +331,17 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev) add_timer(&health->timer); } -void mlx5_stop_health_poll(struct mlx5_core_dev *dev) +void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health) { struct mlx5_core_health *health = &dev->priv.health; + unsigned long flags; + + if (disable_health) { + spin_lock_irqsave(&health->wq_lock, flags); + set_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags); + set_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags); + spin_unlock_irqrestore(&health->wq_lock, flags); + } del_timer_sync(&health->timer); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index e3797a44e074..a825ed093efd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -45,6 +45,7 @@ static int mlx5i_change_mtu(struct net_device *netdev, int new_mtu); static const struct net_device_ops mlx5i_netdev_ops = { .ndo_open = mlx5i_open, .ndo_stop = mlx5i_close, + .ndo_get_stats64 = mlx5i_get_stats, .ndo_init = mlx5i_dev_init, .ndo_uninit = mlx5i_dev_cleanup, .ndo_change_mtu = mlx5i_change_mtu, @@ -83,6 +84,7 @@ void mlx5i_init(struct mlx5_core_dev *mdev, priv->netdev = netdev; priv->profile = profile; priv->ppriv = ppriv; + priv->max_opened_tc = 1; mutex_init(&priv->state_lock); mlx5_query_port_max_mtu(mdev, &max_mtu, 1); @@ -114,6 +116,47 @@ static void mlx5i_cleanup(struct mlx5e_priv *priv) /* Do nothing .. */ } +static void mlx5i_grp_sw_update_stats(struct mlx5e_priv *priv) +{ + struct mlx5e_sw_stats s = { 0 }; + int i, j; + + for (i = 0; i < priv->profile->max_nch(priv->mdev); i++) { + struct mlx5e_channel_stats *channel_stats; + struct mlx5e_rq_stats *rq_stats; + + channel_stats = &priv->channel_stats[i]; + rq_stats = &channel_stats->rq; + + s.rx_packets += rq_stats->packets; + s.rx_bytes += rq_stats->bytes; + + for (j = 0; j < priv->max_opened_tc; j++) { + struct mlx5e_sq_stats *sq_stats = &channel_stats->sq[j]; + + s.tx_packets += sq_stats->packets; + s.tx_bytes += sq_stats->bytes; + s.tx_queue_dropped += sq_stats->dropped; + } + } + + memcpy(&priv->stats.sw, &s, sizeof(s)); +} + +void mlx5i_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) +{ + struct mlx5e_priv *priv = mlx5i_epriv(dev); + struct mlx5e_sw_stats *sstats = &priv->stats.sw; + + mlx5i_grp_sw_update_stats(priv); + + stats->rx_packets = sstats->rx_packets; + stats->rx_bytes = sstats->rx_bytes; + stats->tx_packets = sstats->tx_packets; + stats->tx_bytes = sstats->tx_bytes; + stats->tx_dropped = sstats->tx_queue_dropped; +} + int mlx5i_init_underlay_qp(struct mlx5e_priv *priv) { struct mlx5_core_dev *mdev = priv->mdev; @@ -306,11 +349,20 @@ static void mlx5i_destroy_flow_steering(struct mlx5e_priv *priv) static int mlx5i_init_rx(struct mlx5e_priv *priv) { + struct mlx5_core_dev *mdev = priv->mdev; int err; + mlx5e_create_q_counters(priv); + + err = mlx5e_open_drop_rq(priv, &priv->drop_rq); + if (err) { + mlx5_core_err(mdev, "open drop rq failed, %d\n", err); + goto err_destroy_q_counters; + } + err = mlx5e_create_indirect_rqt(priv); if (err) - return err; + goto err_close_drop_rq; err = mlx5e_create_direct_rqts(priv); if (err) @@ -338,6 +390,10 @@ err_destroy_direct_rqts: mlx5e_destroy_direct_rqts(priv); err_destroy_indirect_rqts: mlx5e_destroy_rqt(priv, &priv->indir_rqt); +err_close_drop_rq: + mlx5e_close_drop_rq(&priv->drop_rq); +err_destroy_q_counters: + mlx5e_destroy_q_counters(priv); return err; } @@ -348,6 +404,8 @@ static void mlx5i_cleanup_rx(struct mlx5e_priv *priv) mlx5e_destroy_indirect_tirs(priv); mlx5e_destroy_direct_rqts(priv); mlx5e_destroy_rqt(priv, &priv->indir_rqt); + mlx5e_close_drop_rq(&priv->drop_rq); + mlx5e_destroy_q_counters(priv); } static const struct mlx5e_profile mlx5i_nic_profile = { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h index 08eac92fc26c..2e7fb829e1b0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h @@ -121,6 +121,7 @@ static inline void mlx5i_sq_fetch_wqe(struct mlx5e_txqsq *sq, netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, struct mlx5_av *av, u32 dqpn, u32 dqkey); void mlx5i_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); +void mlx5i_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats); #endif /* CONFIG_MLX5_CORE_IPOIB */ #endif /* __MLX5E_IPOB_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c index 54a188f41f90..e3e8a5f1ac9b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c @@ -146,6 +146,7 @@ static const struct net_device_ops mlx5i_pkey_netdev_ops = { .ndo_open = mlx5i_pkey_open, .ndo_stop = mlx5i_pkey_close, .ndo_init = mlx5i_pkey_dev_init, + .ndo_get_stats64 = mlx5i_get_stats, .ndo_uninit = mlx5i_pkey_dev_cleanup, .ndo_change_mtu = mlx5i_pkey_change_mtu, .ndo_do_ioctl = mlx5i_pkey_ioctl, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index 3f767cde4c1d..0d90b1b4a3d3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -111,10 +111,10 @@ static void mlx5_pps_out(struct work_struct *work) for (i = 0; i < clock->ptp_info.n_pins; i++) { u64 tstart; - write_lock_irqsave(&clock->lock, flags); + write_seqlock_irqsave(&clock->lock, flags); tstart = clock->pps_info.start[i]; clock->pps_info.start[i] = 0; - write_unlock_irqrestore(&clock->lock, flags); + write_sequnlock_irqrestore(&clock->lock, flags); if (!tstart) continue; @@ -132,10 +132,10 @@ static void mlx5_timestamp_overflow(struct work_struct *work) overflow_work); unsigned long flags; - write_lock_irqsave(&clock->lock, flags); + write_seqlock_irqsave(&clock->lock, flags); timecounter_read(&clock->tc); mlx5_update_clock_info_page(clock->mdev); - write_unlock_irqrestore(&clock->lock, flags); + write_sequnlock_irqrestore(&clock->lock, flags); schedule_delayed_work(&clock->overflow_work, clock->overflow_period); } @@ -147,10 +147,10 @@ static int mlx5_ptp_settime(struct ptp_clock_info *ptp, u64 ns = timespec64_to_ns(ts); unsigned long flags; - write_lock_irqsave(&clock->lock, flags); + write_seqlock_irqsave(&clock->lock, flags); timecounter_init(&clock->tc, &clock->cycles, ns); mlx5_update_clock_info_page(clock->mdev); - write_unlock_irqrestore(&clock->lock, flags); + write_sequnlock_irqrestore(&clock->lock, flags); return 0; } @@ -162,9 +162,9 @@ static int mlx5_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) u64 ns; unsigned long flags; - write_lock_irqsave(&clock->lock, flags); + write_seqlock_irqsave(&clock->lock, flags); ns = timecounter_read(&clock->tc); - write_unlock_irqrestore(&clock->lock, flags); + write_sequnlock_irqrestore(&clock->lock, flags); *ts = ns_to_timespec64(ns); @@ -177,10 +177,10 @@ static int mlx5_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) ptp_info); unsigned long flags; - write_lock_irqsave(&clock->lock, flags); + write_seqlock_irqsave(&clock->lock, flags); timecounter_adjtime(&clock->tc, delta); mlx5_update_clock_info_page(clock->mdev); - write_unlock_irqrestore(&clock->lock, flags); + write_sequnlock_irqrestore(&clock->lock, flags); return 0; } @@ -203,12 +203,12 @@ static int mlx5_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta) adj *= delta; diff = div_u64(adj, 1000000000ULL); - write_lock_irqsave(&clock->lock, flags); + write_seqlock_irqsave(&clock->lock, flags); timecounter_read(&clock->tc); clock->cycles.mult = neg_adj ? clock->nominal_c_mult - diff : clock->nominal_c_mult + diff; mlx5_update_clock_info_page(clock->mdev); - write_unlock_irqrestore(&clock->lock, flags); + write_sequnlock_irqrestore(&clock->lock, flags); return 0; } @@ -307,12 +307,12 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp, ts.tv_nsec = rq->perout.start.nsec; ns = timespec64_to_ns(&ts); cycles_now = mlx5_read_internal_timer(mdev); - write_lock_irqsave(&clock->lock, flags); + write_seqlock_irqsave(&clock->lock, flags); nsec_now = timecounter_cyc2time(&clock->tc, cycles_now); nsec_delta = ns - nsec_now; cycles_delta = div64_u64(nsec_delta << clock->cycles.shift, clock->cycles.mult); - write_unlock_irqrestore(&clock->lock, flags); + write_sequnlock_irqrestore(&clock->lock, flags); time_stamp = cycles_now + cycles_delta; field_select = MLX5_MTPPS_FS_PIN_MODE | MLX5_MTPPS_FS_PATTERN | @@ -471,14 +471,14 @@ void mlx5_pps_event(struct mlx5_core_dev *mdev, ts.tv_sec += 1; ts.tv_nsec = 0; ns = timespec64_to_ns(&ts); - write_lock_irqsave(&clock->lock, flags); + write_seqlock_irqsave(&clock->lock, flags); nsec_now = timecounter_cyc2time(&clock->tc, cycles_now); nsec_delta = ns - nsec_now; cycles_delta = div64_u64(nsec_delta << clock->cycles.shift, clock->cycles.mult); clock->pps_info.start[pin] = cycles_now + cycles_delta; schedule_work(&clock->pps_info.out_work); - write_unlock_irqrestore(&clock->lock, flags); + write_sequnlock_irqrestore(&clock->lock, flags); break; default: mlx5_core_err(mdev, " Unhandled event\n"); @@ -498,7 +498,7 @@ void mlx5_init_clock(struct mlx5_core_dev *mdev) mlx5_core_warn(mdev, "invalid device_frequency_khz, aborting HW clock init\n"); return; } - rwlock_init(&clock->lock); + seqlock_init(&clock->lock); clock->cycles.read = read_internal_timer; clock->cycles.shift = MLX5_CYCLES_SHIFT; clock->cycles.mult = clocksource_khz2mult(dev_freq, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h index 02e2e4575e4f..263cb6e2aeee 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h @@ -46,11 +46,13 @@ static inline int mlx5_clock_get_ptp_index(struct mlx5_core_dev *mdev) static inline ktime_t mlx5_timecounter_cyc2time(struct mlx5_clock *clock, u64 timestamp) { + unsigned int seq; u64 nsec; - read_lock(&clock->lock); - nsec = timecounter_cyc2time(&clock->tc, timestamp); - read_unlock(&clock->lock); + do { + seq = read_seqbegin(&clock->lock); + nsec = timecounter_cyc2time(&clock->tc, timestamp); + } while (read_seqretry(&clock->lock, seq)); return ns_to_ktime(nsec); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index cf3e4a659052..b5e9f664fc66 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -878,8 +878,10 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct mlx5_priv *priv) priv->numa_node = dev_to_node(&dev->pdev->dev); priv->dbg_root = debugfs_create_dir(dev_name(&pdev->dev), mlx5_debugfs_root); - if (!priv->dbg_root) + if (!priv->dbg_root) { + dev_err(&pdev->dev, "Cannot create debugfs dir, aborting\n"); return -ENOMEM; + } err = mlx5_pci_enable_device(dev); if (err) { @@ -928,7 +930,7 @@ static void mlx5_pci_close(struct mlx5_core_dev *dev, struct mlx5_priv *priv) pci_clear_master(dev->pdev); release_bar(dev->pdev); mlx5_pci_disable_device(dev); - debugfs_remove(priv->dbg_root); + debugfs_remove_recursive(priv->dbg_root); } static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv) @@ -1286,7 +1288,7 @@ err_cleanup_once: mlx5_cleanup_once(dev); err_stop_poll: - mlx5_stop_health_poll(dev); + mlx5_stop_health_poll(dev, boot); if (mlx5_cmd_teardown_hca(dev)) { dev_err(&dev->pdev->dev, "tear_down_hca failed, skip cleanup\n"); goto out_err; @@ -1346,7 +1348,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, mlx5_free_irq_vectors(dev); if (cleanup) mlx5_cleanup_once(dev); - mlx5_stop_health_poll(dev); + mlx5_stop_health_poll(dev, cleanup); err = mlx5_cmd_teardown_hca(dev); if (err) { dev_err(&dev->pdev->dev, "tear_down_hca failed, skip cleanup\n"); @@ -1608,7 +1610,7 @@ static int mlx5_try_fast_unload(struct mlx5_core_dev *dev) * with the HCA, so the health polll is no longer needed. */ mlx5_drain_health_wq(dev); - mlx5_stop_health_poll(dev); + mlx5_stop_health_poll(dev, false); ret = mlx5_cmd_force_teardown_hca(dev); if (ret) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/srq.c b/drivers/net/ethernet/mellanox/mlx5/core/srq.c index 23cc337a96c9..7e20666ce5ae 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/srq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/srq.c @@ -73,7 +73,7 @@ static int get_pas_size(struct mlx5_srq_attr *in) u32 rq_sz = 1 << (log_srq_size + 4 + log_rq_stride); u32 page_size = 1 << log_page_size; u32 rq_sz_po = rq_sz + (page_offset * po_quanta); - u32 rq_num_pas = (rq_sz_po + page_size - 1) / page_size; + u32 rq_num_pas = DIV_ROUND_UP(rq_sz_po, page_size); return rq_num_pas * sizeof(u64); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c index 86478a6b99c5..68e7f8df2a6d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c @@ -39,9 +39,9 @@ u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq) return (u32)wq->fbc.sz_m1 + 1; } -u32 mlx5_wq_cyc_get_frag_size(struct mlx5_wq_cyc *wq) +u16 mlx5_wq_cyc_get_frag_size(struct mlx5_wq_cyc *wq) { - return (u32)wq->fbc.frag_sz_m1 + 1; + return wq->fbc.frag_sz_m1 + 1; } u32 mlx5_cqwq_get_size(struct mlx5_cqwq *wq) @@ -138,15 +138,16 @@ int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *qpc, struct mlx5_wq_qp *wq, struct mlx5_wq_ctrl *wq_ctrl) { - u32 sq_strides_offset; + u16 sq_strides_offset; + u32 rq_pg_remainder; int err; mlx5_fill_fbc(MLX5_GET(qpc, qpc, log_rq_stride) + 4, MLX5_GET(qpc, qpc, log_rq_size), &wq->rq.fbc); - sq_strides_offset = - ((wq->rq.fbc.frag_sz_m1 + 1) % PAGE_SIZE) / MLX5_SEND_WQE_BB; + rq_pg_remainder = mlx5_wq_cyc_get_byte_size(&wq->rq) % PAGE_SIZE; + sq_strides_offset = rq_pg_remainder / MLX5_SEND_WQE_BB; mlx5_fill_fbc_offset(ilog2(MLX5_SEND_WQE_BB), MLX5_GET(qpc, qpc, log_sq_size), diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.h b/drivers/net/ethernet/mellanox/mlx5/core/wq.h index 2bd4c3184eba..3a1a170bb2d7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h @@ -80,7 +80,7 @@ int mlx5_wq_cyc_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *wqc, struct mlx5_wq_cyc *wq, struct mlx5_wq_ctrl *wq_ctrl); u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq); -u32 mlx5_wq_cyc_get_frag_size(struct mlx5_wq_cyc *wq); +u16 mlx5_wq_cyc_get_frag_size(struct mlx5_wq_cyc *wq); int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *qpc, struct mlx5_wq_qp *wq, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 6070d1591d1e..930700413b1d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -1346,8 +1346,7 @@ static int mlxsw_sp_port_add_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port, return -ENOMEM; mall_tc_entry->cookie = f->cookie; - tcf_exts_to_list(f->exts, &actions); - a = list_first_entry(&actions, struct tc_action, list); + a = tcf_exts_first_action(f->exts); if (is_tcf_mirred_egress_mirror(a) && protocol == htons(ETH_P_ALL)) { struct mlxsw_sp_port_mall_mirror_tc_entry *mirror; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 3ae930196741..3cdb7aca90b7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -414,6 +414,8 @@ mlxsw_sp_netdevice_ipip_ul_event(struct mlxsw_sp *mlxsw_sp, void mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan); void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif); +void mlxsw_sp_rif_destroy_by_dev(struct mlxsw_sp *mlxsw_sp, + struct net_device *dev); /* spectrum_kvdl.c */ enum mlxsw_sp_kvdl_entry_type { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c index 4327487553c5..3589432d1643 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c @@ -337,14 +337,14 @@ static const struct mlxsw_sp_sb_cm mlxsw_sp_sb_cms_egress[] = { MLXSW_SP_SB_CM(1500, 9, 0), MLXSW_SP_SB_CM(1500, 9, 0), MLXSW_SP_SB_CM(1500, 9, 0), - MLXSW_SP_SB_CM(0, 0, 0), - MLXSW_SP_SB_CM(0, 0, 0), - MLXSW_SP_SB_CM(0, 0, 0), - MLXSW_SP_SB_CM(0, 0, 0), - MLXSW_SP_SB_CM(0, 0, 0), - MLXSW_SP_SB_CM(0, 0, 0), - MLXSW_SP_SB_CM(0, 0, 0), - MLXSW_SP_SB_CM(0, 0, 0), + MLXSW_SP_SB_CM(0, 140000, 15), + MLXSW_SP_SB_CM(0, 140000, 15), + MLXSW_SP_SB_CM(0, 140000, 15), + MLXSW_SP_SB_CM(0, 140000, 15), + MLXSW_SP_SB_CM(0, 140000, 15), + MLXSW_SP_SB_CM(0, 140000, 15), + MLXSW_SP_SB_CM(0, 140000, 15), + MLXSW_SP_SB_CM(0, 140000, 15), MLXSW_SP_SB_CM(1, 0xff, 0), }; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c index ebd1b24ebaa5..8d211972c5e9 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c @@ -21,8 +21,7 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, struct netlink_ext_ack *extack) { const struct tc_action *a; - LIST_HEAD(actions); - int err; + int err, i; if (!tcf_exts_has_actions(exts)) return 0; @@ -32,8 +31,7 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, if (err) return err; - tcf_exts_to_list(exts, &actions); - list_for_each_entry(a, &actions, list) { + tcf_exts_for_each_action(i, a, exts) { if (is_tcf_gact_ok(a)) { err = mlxsw_sp_acl_rulei_act_terminate(rulei); if (err) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 3a96307f51b0..2ab9cf25a08a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -6234,6 +6234,17 @@ void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif) mlxsw_sp_vr_put(mlxsw_sp, vr); } +void mlxsw_sp_rif_destroy_by_dev(struct mlxsw_sp *mlxsw_sp, + struct net_device *dev) +{ + struct mlxsw_sp_rif *rif; + + rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev); + if (!rif) + return; + mlxsw_sp_rif_destroy(rif); +} + static void mlxsw_sp_rif_subport_params_init(struct mlxsw_sp_rif_params *params, struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 0d8444aaba01..db715da7bab7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -127,6 +127,24 @@ bool mlxsw_sp_bridge_device_is_offloaded(const struct mlxsw_sp *mlxsw_sp, return !!mlxsw_sp_bridge_device_find(mlxsw_sp->bridge, br_dev); } +static int mlxsw_sp_bridge_device_upper_rif_destroy(struct net_device *dev, + void *data) +{ + struct mlxsw_sp *mlxsw_sp = data; + + mlxsw_sp_rif_destroy_by_dev(mlxsw_sp, dev); + return 0; +} + +static void mlxsw_sp_bridge_device_rifs_destroy(struct mlxsw_sp *mlxsw_sp, + struct net_device *dev) +{ + mlxsw_sp_rif_destroy_by_dev(mlxsw_sp, dev); + netdev_walk_all_upper_dev_rcu(dev, + mlxsw_sp_bridge_device_upper_rif_destroy, + mlxsw_sp); +} + static struct mlxsw_sp_bridge_device * mlxsw_sp_bridge_device_create(struct mlxsw_sp_bridge *bridge, struct net_device *br_dev) @@ -165,6 +183,8 @@ static void mlxsw_sp_bridge_device_destroy(struct mlxsw_sp_bridge *bridge, struct mlxsw_sp_bridge_device *bridge_device) { + mlxsw_sp_bridge_device_rifs_destroy(bridge->mlxsw_sp, + bridge_device->dev); list_del(&bridge_device->list); if (bridge_device->vlan_enabled) bridge->vlan_enabled_exists = false; diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index e7dce79ff2c9..867cddba840f 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -999,7 +999,6 @@ static int lan743x_phy_open(struct lan743x_adapter *adapter) struct phy_device *phydev; struct net_device *netdev; int ret = -EIO; - u32 mii_adv; netdev = adapter->netdev; phydev = phy_find_first(adapter->mdiobus); @@ -1013,13 +1012,11 @@ static int lan743x_phy_open(struct lan743x_adapter *adapter) goto return_error; /* MAC doesn't support 1000T Half */ - phydev->supported &= ~SUPPORTED_1000baseT_Half; + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT); /* support both flow controls */ + phy_support_asym_pause(phydev); phy->fc_request_control = (FLOW_CTRL_RX | FLOW_CTRL_TX); - phydev->advertising &= ~(ADVERTISED_Pause | ADVERTISED_Asym_Pause); - mii_adv = (u32)mii_advertise_flowctrl(phy->fc_request_control); - phydev->advertising |= mii_adv_to_ethtool_adv_t(mii_adv); phy->fc_autoneg = phydev->autoneg; phy_start(phydev); @@ -2850,7 +2847,7 @@ static void lan743x_pcidev_shutdown(struct pci_dev *pdev) lan743x_hardware_cleanup(adapter); } -#ifdef CONFIG_PM +#ifdef CONFIG_PM_SLEEP static u16 lan743x_pm_wakeframe_crc16(const u8 *buf, int len) { return bitrev16(crc16(0xFFFF, buf, len)); @@ -3016,7 +3013,7 @@ static int lan743x_pm_resume(struct device *dev) static const struct dev_pm_ops lan743x_pm_ops = { SET_SYSTEM_SLEEP_PM_OPS(lan743x_pm_suspend, lan743x_pm_resume) }; -#endif /*CONFIG_PM */ +#endif /* CONFIG_PM_SLEEP */ static const struct pci_device_id lan743x_pcidev_tbl[] = { { PCI_DEVICE(PCI_VENDOR_ID_SMSC, PCI_DEVICE_ID_SMSC_LAN7430) }, @@ -3028,7 +3025,7 @@ static struct pci_driver lan743x_pcidev_driver = { .id_table = lan743x_pcidev_tbl, .probe = lan743x_pcidev_probe, .remove = lan743x_pcidev_remove, -#ifdef CONFIG_PM +#ifdef CONFIG_PM_SLEEP .driver.pm = &lan743x_pm_ops, #endif .shutdown = lan743x_pcidev_shutdown, diff --git a/drivers/net/ethernet/microchip/lan743x_ptp.c b/drivers/net/ethernet/microchip/lan743x_ptp.c index ccdf9123f26f..b2109eca81fd 100644 --- a/drivers/net/ethernet/microchip/lan743x_ptp.c +++ b/drivers/net/ethernet/microchip/lan743x_ptp.c @@ -977,8 +977,8 @@ void lan743x_ptp_close(struct lan743x_adapter *adapter) lan743x_ptp_disable(adapter); } -void lan743x_ptp_set_sync_ts_insert(struct lan743x_adapter *adapter, - bool ts_insert_enable) +static void lan743x_ptp_set_sync_ts_insert(struct lan743x_adapter *adapter, + bool ts_insert_enable) { u32 ptp_tx_mod = lan743x_csr_read(adapter, PTP_TX_MOD); diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c index b8983e73265a..626603266ca7 100644 --- a/drivers/net/ethernet/neterion/s2io.c +++ b/drivers/net/ethernet/neterion/s2io.c @@ -75,6 +75,7 @@ #include <linux/tcp.h> #include <linux/uaccess.h> #include <linux/io.h> +#include <linux/io-64-nonatomic-lo-hi.h> #include <linux/slab.h> #include <linux/prefetch.h> #include <net/tcp.h> @@ -491,7 +492,7 @@ static struct pci_driver s2io_driver = { }; /* A simplifier macro used both by init and free shared_mem Fns(). */ -#define TXD_MEM_PAGE_CNT(len, per_each) ((len+per_each - 1) / per_each) +#define TXD_MEM_PAGE_CNT(len, per_each) DIV_ROUND_UP(len, per_each) /* netqueue manipulation helper functions */ static inline void s2io_stop_all_tx_queue(struct s2io_nic *sp) diff --git a/drivers/net/ethernet/neterion/s2io.h b/drivers/net/ethernet/neterion/s2io.h index 1a24a7218794..0a921f30f98f 100644 --- a/drivers/net/ethernet/neterion/s2io.h +++ b/drivers/net/ethernet/neterion/s2io.h @@ -10,6 +10,7 @@ * system is licensed under the GPL. * See the file COPYING in this distribution for more information. ************************************************************************/ +#include <linux/io-64-nonatomic-lo-hi.h> #ifndef _S2IO_H #define _S2IO_H @@ -970,27 +971,6 @@ struct s2io_nic { #define RESET_ERROR 1 #define CMD_ERROR 2 -/* OS related system calls */ -#ifndef readq -static inline u64 readq(void __iomem *addr) -{ - u64 ret = 0; - ret = readl(addr + 4); - ret <<= 32; - ret |= readl(addr); - - return ret; -} -#endif - -#ifndef writeq -static inline void writeq(u64 val, void __iomem *addr) -{ - writel((u32) (val), addr); - writel((u32) (val >> 32), (addr + 4)); -} -#endif - /* * Some registers have to be written in a particular order to * expect correct hardware operation. The macro SPECIAL_REG_WRITE diff --git a/drivers/net/ethernet/neterion/vxge/vxge-config.c b/drivers/net/ethernet/neterion/vxge/vxge-config.c index 398011c87643..4c1fb7e57888 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-config.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-config.c @@ -13,6 +13,7 @@ ******************************************************************************/ #include <linux/vmalloc.h> #include <linux/etherdevice.h> +#include <linux/io-64-nonatomic-lo-hi.h> #include <linux/pci.h> #include <linux/slab.h> diff --git a/drivers/net/ethernet/neterion/vxge/vxge-config.h b/drivers/net/ethernet/neterion/vxge/vxge-config.h index d743a37a3cee..e678ba379598 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-config.h +++ b/drivers/net/ethernet/neterion/vxge/vxge-config.h @@ -2011,26 +2011,6 @@ enum vxge_hw_status vxge_hw_vpath_mtu_set( void vxge_hw_vpath_rx_doorbell_init(struct __vxge_hw_vpath_handle *vp); -#ifndef readq -static inline u64 readq(void __iomem *addr) -{ - u64 ret = 0; - ret = readl(addr + 4); - ret <<= 32; - ret |= readl(addr); - - return ret; -} -#endif - -#ifndef writeq -static inline void writeq(u64 val, void __iomem *addr) -{ - writel((u32) (val), addr); - writel((u32) (val >> 32), (addr + 4)); -} -#endif - static inline void __vxge_hw_pio_mem_write32_upper(u32 val, void __iomem *addr) { writel(val, addr + 4); diff --git a/drivers/net/ethernet/neterion/vxge/vxge-traffic.c b/drivers/net/ethernet/neterion/vxge/vxge-traffic.c index 0c3b5dea2858..30e5cdc52eb6 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-traffic.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-traffic.c @@ -12,6 +12,7 @@ * Copyright(c) 2002-2010 Exar Corp. ******************************************************************************/ #include <linux/etherdevice.h> +#include <linux/io-64-nonatomic-lo-hi.h> #include <linux/prefetch.h> #include "vxge-traffic.h" diff --git a/drivers/net/ethernet/netronome/nfp/abm/ctrl.c b/drivers/net/ethernet/netronome/nfp/abm/ctrl.c index b157ccd8c80f..5b06f07c78cd 100644 --- a/drivers/net/ethernet/netronome/nfp/abm/ctrl.c +++ b/drivers/net/ethernet/netronome/nfp/abm/ctrl.c @@ -55,30 +55,21 @@ #define NFP_QMSTAT_DROP 16 #define NFP_QMSTAT_ECN 24 -static unsigned long long -nfp_abm_q_lvl_thrs(struct nfp_abm_link *alink, unsigned int queue) -{ - return alink->abm->q_lvls->addr + - (alink->queue_base + queue) * NFP_QLVL_STRIDE + NFP_QLVL_THRS; -} - static int nfp_abm_ctrl_stat(struct nfp_abm_link *alink, const struct nfp_rtsym *sym, unsigned int stride, unsigned int offset, unsigned int i, bool is_u64, u64 *res) { struct nfp_cpp *cpp = alink->abm->app->cpp; - u32 val32, mur; - u64 val, addr; + u64 val, sym_offset; + u32 val32; int err; - mur = NFP_CPP_ATOMIC_RD(sym->target, sym->domain); - - addr = sym->addr + (alink->queue_base + i) * stride + offset; + sym_offset = (alink->queue_base + i) * stride + offset; if (is_u64) - err = nfp_cpp_readq(cpp, mur, addr, &val); + err = __nfp_rtsym_readq(cpp, sym, 3, 0, sym_offset, &val); else - err = nfp_cpp_readl(cpp, mur, addr, &val32); + err = __nfp_rtsym_readl(cpp, sym, 3, 0, sym_offset, &val32); if (err) { nfp_err(cpp, "RED offload reading stat failed on vNIC %d queue %d\n", @@ -114,13 +105,12 @@ nfp_abm_ctrl_stat_all(struct nfp_abm_link *alink, const struct nfp_rtsym *sym, int nfp_abm_ctrl_set_q_lvl(struct nfp_abm_link *alink, unsigned int i, u32 val) { struct nfp_cpp *cpp = alink->abm->app->cpp; - u32 muw; + u64 sym_offset; int err; - muw = NFP_CPP_ATOMIC_WR(alink->abm->q_lvls->target, - alink->abm->q_lvls->domain); - - err = nfp_cpp_writel(cpp, muw, nfp_abm_q_lvl_thrs(alink, i), val); + sym_offset = (alink->queue_base + i) * NFP_QLVL_STRIDE + NFP_QLVL_THRS; + err = __nfp_rtsym_writel(cpp, alink->abm->q_lvls, 4, 0, + sym_offset, val); if (err) { nfp_err(cpp, "RED offload setting level failed on vNIC %d queue %d\n", alink->id, i); @@ -290,10 +280,10 @@ nfp_abm_ctrl_find_rtsym(struct nfp_pf *pf, const char *name, unsigned int size) nfp_err(pf->cpp, "Symbol '%s' not found\n", name); return ERR_PTR(-ENOENT); } - if (sym->size != size) { + if (nfp_rtsym_size(sym) != size) { nfp_err(pf->cpp, "Symbol '%s' wrong size: expected %u got %llu\n", - name, size, sym->size); + name, size, nfp_rtsym_size(sym)); return ERR_PTR(-EINVAL); } diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.c b/drivers/net/ethernet/netronome/nfp/abm/main.c index b84a6c2d387b..305ac07dc1e7 100644 --- a/drivers/net/ethernet/netronome/nfp/abm/main.c +++ b/drivers/net/ethernet/netronome/nfp/abm/main.c @@ -540,8 +540,9 @@ nfp_abm_vnic_set_mac(struct nfp_pf *pf, struct nfp_abm *abm, struct nfp_net *nn, { struct nfp_eth_table_port *eth_port = &pf->eth_tbl->ports[id]; u8 mac_addr[ETH_ALEN]; - const char *mac_str; - char name[32]; + struct nfp_nsp *nsp; + char hwinfo[32]; + int err; if (id > pf->eth_tbl->count) { nfp_warn(pf->cpp, "No entry for persistent MAC address\n"); @@ -549,22 +550,37 @@ nfp_abm_vnic_set_mac(struct nfp_pf *pf, struct nfp_abm *abm, struct nfp_net *nn, return; } - snprintf(name, sizeof(name), "eth%u.mac.pf%u", + snprintf(hwinfo, sizeof(hwinfo), "eth%u.mac.pf%u", eth_port->eth_index, abm->pf_id); - mac_str = nfp_hwinfo_lookup(pf->hwinfo, name); - if (!mac_str) { - nfp_warn(pf->cpp, "Can't lookup persistent MAC address (%s)\n", - name); + nsp = nfp_nsp_open(pf->cpp); + if (IS_ERR(nsp)) { + nfp_warn(pf->cpp, "Failed to access the NSP for persistent MAC address: %ld\n", + PTR_ERR(nsp)); + eth_hw_addr_random(nn->dp.netdev); + return; + } + + if (!nfp_nsp_has_hwinfo_lookup(nsp)) { + nfp_warn(pf->cpp, "NSP doesn't support PF MAC generation\n"); + eth_hw_addr_random(nn->dp.netdev); + return; + } + + err = nfp_nsp_hwinfo_lookup(nsp, hwinfo, sizeof(hwinfo)); + nfp_nsp_close(nsp); + if (err) { + nfp_warn(pf->cpp, "Reading persistent MAC address failed: %d\n", + err); eth_hw_addr_random(nn->dp.netdev); return; } - if (sscanf(mac_str, "%02hhx:%02hhx:%02hhx:%02hhx:%02hhx:%02hhx", + if (sscanf(hwinfo, "%02hhx:%02hhx:%02hhx:%02hhx:%02hhx:%02hhx", &mac_addr[0], &mac_addr[1], &mac_addr[2], &mac_addr[3], &mac_addr[4], &mac_addr[5]) != 6) { nfp_warn(pf->cpp, "Can't parse persistent MAC address (%s)\n", - mac_str); + hwinfo); eth_hw_addr_random(nn->dp.netdev); return; } diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c index 0ba0356ec4e6..46ba0cf257c6 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/action.c +++ b/drivers/net/ethernet/netronome/nfp/flower/action.c @@ -52,6 +52,7 @@ #define NFP_FL_TUNNEL_CSUM cpu_to_be16(0x01) #define NFP_FL_TUNNEL_KEY cpu_to_be16(0x04) #define NFP_FL_TUNNEL_GENEVE_OPT cpu_to_be16(0x0800) +#define NFP_FL_SUPPORTED_TUNNEL_INFO_FLAGS IP_TUNNEL_INFO_TX #define NFP_FL_SUPPORTED_IPV4_UDP_TUN_FLAGS (NFP_FL_TUNNEL_CSUM | \ NFP_FL_TUNNEL_KEY | \ NFP_FL_TUNNEL_GENEVE_OPT) @@ -741,11 +742,16 @@ nfp_flower_loop_action(struct nfp_app *app, const struct tc_action *a, nfp_fl_push_vlan(psh_v, a); *a_len += sizeof(struct nfp_fl_push_vlan); } else if (is_tcf_tunnel_set(a)) { + struct ip_tunnel_info *ip_tun = tcf_tunnel_info(a); struct nfp_repr *repr = netdev_priv(netdev); + *tun_type = nfp_fl_get_tun_from_act_l4_port(repr->app, a); if (*tun_type == NFP_FL_TUNNEL_NONE) return -EOPNOTSUPP; + if (ip_tun->mode & ~NFP_FL_SUPPORTED_TUNNEL_INFO_FLAGS) + return -EOPNOTSUPP; + /* Pre-tunnel action is required for tunnel encap. * This checks for next hop entries on NFP. * If none, the packet falls back before applying other actions. @@ -796,11 +802,10 @@ int nfp_flower_compile_action(struct nfp_app *app, struct net_device *netdev, struct nfp_fl_payload *nfp_flow) { - int act_len, act_cnt, err, tun_out_cnt, out_cnt; + int act_len, act_cnt, err, tun_out_cnt, out_cnt, i; enum nfp_flower_tun_type tun_type; const struct tc_action *a; u32 csum_updated = 0; - LIST_HEAD(actions); memset(nfp_flow->action_data, 0, NFP_FL_MAX_A_SIZ); nfp_flow->meta.act_len = 0; @@ -810,8 +815,7 @@ int nfp_flower_compile_action(struct nfp_app *app, tun_out_cnt = 0; out_cnt = 0; - tcf_exts_to_list(flow->exts, &actions); - list_for_each_entry(a, &actions, list) { + tcf_exts_for_each_action(i, a, flow->exts) { err = nfp_flower_loop_action(app, a, flow, nfp_flow, &act_len, netdev, &tun_type, &tun_out_cnt, &out_cnt, &csum_updated); diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h index 85f8209bf007..81d941ab895c 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.h +++ b/drivers/net/ethernet/netronome/nfp/flower/main.h @@ -70,6 +70,7 @@ struct nfp_app; #define NFP_FL_FEATS_GENEVE BIT(0) #define NFP_FL_NBI_MTU_SETTING BIT(1) #define NFP_FL_FEATS_GENEVE_OPT BIT(2) +#define NFP_FL_FEATS_VLAN_PCP BIT(3) #define NFP_FL_FEATS_LAG BIT(31) struct nfp_fl_mask_id { diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c index a0c72f277faa..17acb8cc6044 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/match.c +++ b/drivers/net/ethernet/netronome/nfp/flower/match.c @@ -56,7 +56,7 @@ nfp_flower_compile_meta_tci(struct nfp_flower_meta_tci *frame, FLOW_DISSECTOR_KEY_VLAN, target); /* Populate the tci field. */ - if (flow_vlan->vlan_id) { + if (flow_vlan->vlan_id || flow_vlan->vlan_priority) { tmp_tci = FIELD_PREP(NFP_FLOWER_MASK_VLAN_PRIO, flow_vlan->vlan_priority) | FIELD_PREP(NFP_FLOWER_MASK_VLAN_VID, diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index 2edab01c3beb..bd19624f10cf 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -192,6 +192,17 @@ nfp_flower_calculate_key_layers(struct nfp_app *app, key_size += sizeof(struct nfp_flower_mac_mpls); } + if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_dissector_key_vlan *flow_vlan; + + flow_vlan = skb_flow_dissector_target(flow->dissector, + FLOW_DISSECTOR_KEY_VLAN, + flow->mask); + if (!(priv->flower_ext_feats & NFP_FL_FEATS_VLAN_PCP) && + flow_vlan->vlan_priority) + return -EOPNOTSUPP; + } + if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_ENC_CONTROL)) { struct flow_dissector_key_ipv4_addrs *mask_ipv4 = NULL; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.c b/drivers/net/ethernet/netronome/nfp/nfp_main.c index 4a540c5e27fe..9474a4eed8ce 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_main.c @@ -68,6 +68,10 @@ static const struct pci_device_id nfp_pci_device_ids[] = { PCI_VENDOR_ID_NETRONOME, PCI_ANY_ID, PCI_ANY_ID, 0, }, + { PCI_VENDOR_ID_NETRONOME, PCI_DEVICE_ID_NETRONOME_NFP5000, + PCI_VENDOR_ID_NETRONOME, PCI_ANY_ID, + PCI_ANY_ID, 0, + }, { PCI_VENDOR_ID_NETRONOME, PCI_DEVICE_ID_NETRONOME_NFP4000, PCI_VENDOR_ID_NETRONOME, PCI_ANY_ID, PCI_ANY_ID, 0, @@ -112,23 +116,18 @@ nfp_pf_map_rtsym(struct nfp_pf *pf, const char *name, const char *sym_fmt, int nfp_mbox_cmd(struct nfp_pf *pf, u32 cmd, void *in_data, u64 in_length, void *out_data, u64 out_length) { - unsigned long long addr; unsigned long err_at; u64 max_data_sz; u32 val = 0; - u32 cpp_id; int n, err; if (!pf->mbox) return -EOPNOTSUPP; - cpp_id = NFP_CPP_ISLAND_ID(pf->mbox->target, NFP_CPP_ACTION_RW, 0, - pf->mbox->domain); - addr = pf->mbox->addr; - max_data_sz = pf->mbox->size - NFP_MBOX_SYM_MIN_SIZE; + max_data_sz = nfp_rtsym_size(pf->mbox) - NFP_MBOX_SYM_MIN_SIZE; /* Check if cmd field is clear */ - err = nfp_cpp_readl(pf->cpp, cpp_id, addr + NFP_MBOX_CMD, &val); + err = nfp_rtsym_readl(pf->cpp, pf->mbox, NFP_MBOX_CMD, &val); if (err || val) { nfp_warn(pf->cpp, "failed to issue command (%u): %u, err: %d\n", cmd, val, err); @@ -136,30 +135,29 @@ int nfp_mbox_cmd(struct nfp_pf *pf, u32 cmd, void *in_data, u64 in_length, } in_length = min(in_length, max_data_sz); - n = nfp_cpp_write(pf->cpp, cpp_id, addr + NFP_MBOX_DATA, - in_data, in_length); + n = nfp_rtsym_write(pf->cpp, pf->mbox, NFP_MBOX_DATA, in_data, + in_length); if (n != in_length) return -EIO; /* Write data_len and wipe reserved */ - err = nfp_cpp_writeq(pf->cpp, cpp_id, addr + NFP_MBOX_DATA_LEN, - in_length); + err = nfp_rtsym_writeq(pf->cpp, pf->mbox, NFP_MBOX_DATA_LEN, in_length); if (err) return err; /* Read back for ordering */ - err = nfp_cpp_readl(pf->cpp, cpp_id, addr + NFP_MBOX_DATA_LEN, &val); + err = nfp_rtsym_readl(pf->cpp, pf->mbox, NFP_MBOX_DATA_LEN, &val); if (err) return err; /* Write cmd and wipe return value */ - err = nfp_cpp_writeq(pf->cpp, cpp_id, addr + NFP_MBOX_CMD, cmd); + err = nfp_rtsym_writeq(pf->cpp, pf->mbox, NFP_MBOX_CMD, cmd); if (err) return err; err_at = jiffies + 5 * HZ; while (true) { /* Wait for command to go to 0 (NFP_MBOX_NO_CMD) */ - err = nfp_cpp_readl(pf->cpp, cpp_id, addr + NFP_MBOX_CMD, &val); + err = nfp_rtsym_readl(pf->cpp, pf->mbox, NFP_MBOX_CMD, &val); if (err) return err; if (!val) @@ -172,18 +170,18 @@ int nfp_mbox_cmd(struct nfp_pf *pf, u32 cmd, void *in_data, u64 in_length, } /* Copy output if any (could be error info, do it before reading ret) */ - err = nfp_cpp_readl(pf->cpp, cpp_id, addr + NFP_MBOX_DATA_LEN, &val); + err = nfp_rtsym_readl(pf->cpp, pf->mbox, NFP_MBOX_DATA_LEN, &val); if (err) return err; out_length = min_t(u32, val, min(out_length, max_data_sz)); - n = nfp_cpp_read(pf->cpp, cpp_id, addr + NFP_MBOX_DATA, - out_data, out_length); + n = nfp_rtsym_read(pf->cpp, pf->mbox, NFP_MBOX_DATA, + out_data, out_length); if (n != out_length) return -EIO; /* Check if there is an error */ - err = nfp_cpp_readl(pf->cpp, cpp_id, addr + NFP_MBOX_RET, &val); + err = nfp_rtsym_readl(pf->cpp, pf->mbox, NFP_MBOX_RET, &val); if (err) return err; if (val) @@ -441,8 +439,11 @@ nfp_fw_load(struct pci_dev *pdev, struct nfp_pf *pf, struct nfp_nsp *nsp) } fw = nfp_net_fw_find(pdev, pf); - if (!fw) + if (!fw) { + if (nfp_nsp_has_stored_fw_load(nsp)) + nfp_nsp_load_stored_fw(nsp); return 0; + } dev_info(&pdev->dev, "Soft-reset, loading FW image\n"); err = nfp_nsp_device_soft_reset(nsp); @@ -453,7 +454,6 @@ nfp_fw_load(struct pci_dev *pdev, struct nfp_pf *pf, struct nfp_nsp *nsp) } err = nfp_nsp_load_fw(nsp, fw); - if (err < 0) { dev_err(&pdev->dev, "FW loading failed: %d\n", err); goto exit_release_fw; @@ -566,9 +566,9 @@ static int nfp_pf_find_rtsyms(struct nfp_pf *pf) /* Optional per-PCI PF mailbox */ snprintf(pf_symbol, sizeof(pf_symbol), NFP_MBOX_SYM_NAME, pf_id); pf->mbox = nfp_rtsym_lookup(pf->rtbl, pf_symbol); - if (pf->mbox && pf->mbox->size < NFP_MBOX_SYM_MIN_SIZE) { + if (pf->mbox && nfp_rtsym_size(pf->mbox) < NFP_MBOX_SYM_MIN_SIZE) { nfp_err(pf->cpp, "PF mailbox symbol too small: %llu < %d\n", - pf->mbox->size, NFP_MBOX_SYM_MIN_SIZE); + nfp_rtsym_size(pf->mbox), NFP_MBOX_SYM_MIN_SIZE); return -EINVAL; } diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index a8b9fbab5f73..1aac55d66404 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -229,29 +229,16 @@ done: spin_unlock_bh(&nn->reconfig_lock); } -/** - * nfp_net_reconfig() - Reconfigure the firmware - * @nn: NFP Net device to reconfigure - * @update: The value for the update field in the BAR config - * - * Write the update word to the BAR and ping the reconfig queue. The - * poll until the firmware has acknowledged the update by zeroing the - * update word. - * - * Return: Negative errno on error, 0 on success - */ -int nfp_net_reconfig(struct nfp_net *nn, u32 update) +static void nfp_net_reconfig_sync_enter(struct nfp_net *nn) { bool cancelled_timer = false; u32 pre_posted_requests; - int ret; spin_lock_bh(&nn->reconfig_lock); nn->reconfig_sync_present = true; if (nn->reconfig_timer_active) { - del_timer(&nn->reconfig_timer); nn->reconfig_timer_active = false; cancelled_timer = true; } @@ -260,14 +247,43 @@ int nfp_net_reconfig(struct nfp_net *nn, u32 update) spin_unlock_bh(&nn->reconfig_lock); - if (cancelled_timer) + if (cancelled_timer) { + del_timer_sync(&nn->reconfig_timer); nfp_net_reconfig_wait(nn, nn->reconfig_timer.expires); + } /* Run the posted reconfigs which were issued before we started */ if (pre_posted_requests) { nfp_net_reconfig_start(nn, pre_posted_requests); nfp_net_reconfig_wait(nn, jiffies + HZ * NFP_NET_POLL_TIMEOUT); } +} + +static void nfp_net_reconfig_wait_posted(struct nfp_net *nn) +{ + nfp_net_reconfig_sync_enter(nn); + + spin_lock_bh(&nn->reconfig_lock); + nn->reconfig_sync_present = false; + spin_unlock_bh(&nn->reconfig_lock); +} + +/** + * nfp_net_reconfig() - Reconfigure the firmware + * @nn: NFP Net device to reconfigure + * @update: The value for the update field in the BAR config + * + * Write the update word to the BAR and ping the reconfig queue. The + * poll until the firmware has acknowledged the update by zeroing the + * update word. + * + * Return: Negative errno on error, 0 on success + */ +int nfp_net_reconfig(struct nfp_net *nn, u32 update) +{ + int ret; + + nfp_net_reconfig_sync_enter(nn); nfp_net_reconfig_start(nn, update); ret = nfp_net_reconfig_wait(nn, jiffies + HZ * NFP_NET_POLL_TIMEOUT); @@ -2075,10 +2091,10 @@ static void nfp_ctrl_poll(unsigned long arg) { struct nfp_net_r_vector *r_vec = (void *)arg; - spin_lock_bh(&r_vec->lock); + spin_lock(&r_vec->lock); nfp_net_tx_complete(r_vec->tx_ring, 0); __nfp_ctrl_tx_queued(r_vec); - spin_unlock_bh(&r_vec->lock); + spin_unlock(&r_vec->lock); nfp_ctrl_rx(r_vec); @@ -3151,6 +3167,7 @@ static void nfp_net_stat64(struct net_device *netdev, struct nfp_net *nn = netdev_priv(netdev); int r; + /* Collect software stats */ for (r = 0; r < nn->max_r_vecs; r++) { struct nfp_net_r_vector *r_vec = &nn->r_vecs[r]; u64 data[3]; @@ -3176,6 +3193,14 @@ static void nfp_net_stat64(struct net_device *netdev, stats->tx_bytes += data[1]; stats->tx_errors += data[2]; } + + /* Add in device stats */ + stats->multicast += nn_readq(nn, NFP_NET_CFG_STATS_RX_MC_FRAMES); + stats->rx_dropped += nn_readq(nn, NFP_NET_CFG_STATS_RX_DISCARDS); + stats->rx_errors += nn_readq(nn, NFP_NET_CFG_STATS_RX_ERRORS); + + stats->tx_dropped += nn_readq(nn, NFP_NET_CFG_STATS_TX_DISCARDS); + stats->tx_errors += nn_readq(nn, NFP_NET_CFG_STATS_TX_ERRORS); } static int nfp_net_set_features(struct net_device *netdev, @@ -3633,6 +3658,7 @@ struct nfp_net *nfp_net_alloc(struct pci_dev *pdev, bool needs_netdev, */ void nfp_net_free(struct nfp_net *nn) { + WARN_ON(timer_pending(&nn->reconfig_timer) || nn->reconfig_posted); if (nn->dp.netdev) free_netdev(nn->dp.netdev); else @@ -3745,15 +3771,18 @@ static void nfp_net_netdev_init(struct nfp_net *nn) } if (nn->cap & NFP_NET_CFG_CTRL_RSS_ANY) netdev->hw_features |= NETIF_F_RXHASH; - if (nn->cap & NFP_NET_CFG_CTRL_VXLAN && - nn->cap & NFP_NET_CFG_CTRL_NVGRE) { + if (nn->cap & NFP_NET_CFG_CTRL_VXLAN) { if (nn->cap & NFP_NET_CFG_CTRL_LSO) - netdev->hw_features |= NETIF_F_GSO_GRE | - NETIF_F_GSO_UDP_TUNNEL; - nn->dp.ctrl |= NFP_NET_CFG_CTRL_VXLAN | NFP_NET_CFG_CTRL_NVGRE; - - netdev->hw_enc_features = netdev->hw_features; + netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL; + nn->dp.ctrl |= NFP_NET_CFG_CTRL_VXLAN; } + if (nn->cap & NFP_NET_CFG_CTRL_NVGRE) { + if (nn->cap & NFP_NET_CFG_CTRL_LSO) + netdev->hw_features |= NETIF_F_GSO_GRE; + nn->dp.ctrl |= NFP_NET_CFG_CTRL_NVGRE; + } + if (nn->cap & (NFP_NET_CFG_CTRL_VXLAN | NFP_NET_CFG_CTRL_NVGRE)) + netdev->hw_enc_features = netdev->hw_features; netdev->vlan_features = netdev->hw_features; @@ -3920,4 +3949,5 @@ void nfp_net_clean(struct nfp_net *nn) return; unregister_netdev(nn->dp.netdev); + nfp_net_reconfig_wait_posted(nn); } diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_debugdump.c b/drivers/net/ethernet/netronome/nfp/nfp_net_debugdump.c index bb8ed460086e..b6b897840ac5 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_debugdump.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_debugdump.c @@ -188,25 +188,21 @@ nfp_net_dump_load_dumpspec(struct nfp_cpp *cpp, struct nfp_rtsym_table *rtbl) const struct nfp_rtsym *specsym; struct nfp_dumpspec *dumpspec; int bytes_read; - u32 cpp_id; + u64 sym_size; specsym = nfp_rtsym_lookup(rtbl, NFP_DUMP_SPEC_RTSYM); if (!specsym) return NULL; + sym_size = nfp_rtsym_size(specsym); /* expected size of this buffer is in the order of tens of kilobytes */ - dumpspec = vmalloc(sizeof(*dumpspec) + specsym->size); + dumpspec = vmalloc(sizeof(*dumpspec) + sym_size); if (!dumpspec) return NULL; + dumpspec->size = sym_size; - dumpspec->size = specsym->size; - - cpp_id = NFP_CPP_ISLAND_ID(specsym->target, NFP_CPP_ACTION_RW, 0, - specsym->domain); - - bytes_read = nfp_cpp_read(cpp, cpp_id, specsym->addr, dumpspec->data, - specsym->size); - if (bytes_read != specsym->size) { + bytes_read = nfp_rtsym_read(cpp, specsym, 0, dumpspec->data, sym_size); + if (bytes_read != sym_size) { vfree(dumpspec); nfp_warn(cpp, "Debug dump specification read failed.\n"); return NULL; @@ -266,7 +262,6 @@ nfp_calc_rtsym_dump_sz(struct nfp_pf *pf, struct nfp_dump_tl *spec) struct nfp_dumpspec_rtsym *spec_rtsym; const struct nfp_rtsym *sym; u32 tl_len, key_len; - u32 size; spec_rtsym = (struct nfp_dumpspec_rtsym *)spec; tl_len = be32_to_cpu(spec->length); @@ -278,13 +273,8 @@ nfp_calc_rtsym_dump_sz(struct nfp_pf *pf, struct nfp_dump_tl *spec) if (!sym) return nfp_dump_error_tlv_size(spec); - if (sym->type == NFP_RTSYM_TYPE_ABS) - size = sizeof(sym->addr); - else - size = sym->size; - return ALIGN8(offsetof(struct nfp_dump_rtsym, rtsym) + key_len + 1) + - ALIGN8(size); + ALIGN8(nfp_rtsym_size(sym)); } static int @@ -644,7 +634,6 @@ nfp_dump_single_rtsym(struct nfp_pf *pf, struct nfp_dumpspec_rtsym *spec, const struct nfp_rtsym *sym; u32 tl_len, key_len; int bytes_read; - u32 cpp_id; void *dest; int err; @@ -657,11 +646,7 @@ nfp_dump_single_rtsym(struct nfp_pf *pf, struct nfp_dumpspec_rtsym *spec, if (!sym) return nfp_dump_error_tlv(&spec->tl, -ENOENT, dump); - if (sym->type == NFP_RTSYM_TYPE_ABS) - sym_size = sizeof(sym->addr); - else - sym_size = sym->size; - + sym_size = nfp_rtsym_size(sym); header_size = ALIGN8(offsetof(struct nfp_dump_rtsym, rtsym) + key_len + 1); total_size = header_size + ALIGN8(sym_size); @@ -676,23 +661,20 @@ nfp_dump_single_rtsym(struct nfp_pf *pf, struct nfp_dumpspec_rtsym *spec, memcpy(dump_header->rtsym, spec->rtsym, key_len + 1); dump_header->cpp.dump_length = cpu_to_be32(sym_size); - if (sym->type == NFP_RTSYM_TYPE_ABS) { - *(u64 *)dest = sym->addr; - } else { + if (sym->type != NFP_RTSYM_TYPE_ABS) { cpp_params.target = sym->target; cpp_params.action = NFP_CPP_ACTION_RW; cpp_params.token = 0; cpp_params.island = sym->domain; - cpp_id = nfp_get_numeric_cpp_id(&cpp_params); dump_header->cpp.cpp_id = cpp_params; dump_header->cpp.offset = cpu_to_be32(sym->addr); - bytes_read = nfp_cpp_read(pf->cpp, cpp_id, sym->addr, dest, - sym_size); - if (bytes_read != sym_size) { - if (bytes_read >= 0) - bytes_read = -EIO; - dump_header->error = cpu_to_be32(bytes_read); - } + } + + bytes_read = nfp_rtsym_read(pf->cpp, sym, 0, dest, sym_size); + if (bytes_read != sym_size) { + if (bytes_read >= 0) + bytes_read = -EIO; + dump_header->error = cpu_to_be32(bytes_read); } return 0; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c index 28516eecccc8..0b1ac9c234d1 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c @@ -470,8 +470,8 @@ static void nfp_net_pci_unmap_mem(struct nfp_pf *pf) static int nfp_net_pci_map_mem(struct nfp_pf *pf) { + u32 min_size, cpp_id; u8 __iomem *mem; - u32 min_size; int err; min_size = pf->max_data_vnics * NFP_PF_CSR_SLICE_SIZE; @@ -519,9 +519,9 @@ static int nfp_net_pci_map_mem(struct nfp_pf *pf) pf->vfcfg_tbl2 = NULL; } - mem = nfp_cpp_map_area(pf->cpp, "net.qc", 0, 0, - NFP_PCIE_QUEUE(0), NFP_QCP_QUEUE_AREA_SZ, - &pf->qc_area); + cpp_id = NFP_CPP_ISLAND_ID(0, NFP_CPP_ACTION_RW, 0, 0); + mem = nfp_cpp_map_area(pf->cpp, "net.qc", cpp_id, NFP_PCIE_QUEUE(0), + NFP_QCP_QUEUE_AREA_SZ, &pf->qc_area); if (IS_ERR(mem)) { nfp_err(pf->cpp, "Failed to map Queue Controller area.\n"); err = PTR_ERR(mem); diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c index c8d0b1016a64..fd63d83bdea5 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c @@ -138,6 +138,7 @@ /* The number of explicit BARs to reserve. * Minimum is 0, maximum is 4 on the NFP6000. + * The NFP3800 can have only one per PF. */ #define NFP_PCIE_EXPLICIT_BARS 2 @@ -589,8 +590,8 @@ static int enable_bars(struct nfp6000_pcie *nfp, u16 interface) NFP_PCIE_BAR_PCIE2CPP_MapType_EXPLICIT3), }; char status_msg[196] = {}; + int i, err, bars_free; struct nfp_bar *bar; - int i, bars_free; int expl_groups; char *msg, *end; @@ -643,6 +644,8 @@ static int enable_bars(struct nfp6000_pcie *nfp, u16 interface) bar->iomem = ioremap_nocache(nfp_bar_resource_start(bar), nfp_bar_resource_len(bar)); if (bar->iomem) { + int pf; + msg += snprintf(msg, end - msg, "0.0: General/MSI-X SRAM, "); atomic_inc(&bar->refcnt); bars_free--; @@ -651,22 +654,40 @@ static int enable_bars(struct nfp6000_pcie *nfp, u16 interface) nfp->expl.data = bar->iomem + NFP_PCIE_SRAM + 0x1000; - if (nfp->pdev->device == PCI_DEVICE_ID_NETRONOME_NFP4000 || - nfp->pdev->device == PCI_DEVICE_ID_NETRONOME_NFP6000) { - nfp->iomem.csr = bar->iomem + NFP_PCIE_BAR(0); - } else { - int pf = nfp->pdev->devfn & 7; - + switch (nfp->pdev->device) { + case PCI_DEVICE_ID_NETRONOME_NFP3800: + pf = nfp->pdev->devfn & 7; nfp->iomem.csr = bar->iomem + NFP_PCIE_BAR(pf); + break; + case PCI_DEVICE_ID_NETRONOME_NFP4000: + case PCI_DEVICE_ID_NETRONOME_NFP5000: + case PCI_DEVICE_ID_NETRONOME_NFP6000: + nfp->iomem.csr = bar->iomem + NFP_PCIE_BAR(0); + break; + default: + dev_err(nfp->dev, "Unsupported device ID: %04hx!\n", + nfp->pdev->device); + err = -EINVAL; + goto err_unmap_bar0; } nfp->iomem.em = bar->iomem + NFP_PCIE_EM; } - if (nfp->pdev->device == PCI_DEVICE_ID_NETRONOME_NFP4000 || - nfp->pdev->device == PCI_DEVICE_ID_NETRONOME_NFP6000) - expl_groups = 4; - else + switch (nfp->pdev->device) { + case PCI_DEVICE_ID_NETRONOME_NFP3800: expl_groups = 1; + break; + case PCI_DEVICE_ID_NETRONOME_NFP4000: + case PCI_DEVICE_ID_NETRONOME_NFP5000: + case PCI_DEVICE_ID_NETRONOME_NFP6000: + expl_groups = 4; + break; + default: + dev_err(nfp->dev, "Unsupported device ID: %04hx!\n", + nfp->pdev->device); + err = -EINVAL; + goto err_unmap_bar0; + } /* Configure, and lock, BAR0.1 for PCIe XPB (MSI-X PBA) */ bar = &nfp->bar[1]; @@ -711,6 +732,11 @@ static int enable_bars(struct nfp6000_pcie *nfp, u16 interface) dev_info(nfp->dev, "%sfree: %d/%d\n", status_msg, bars_free, nfp->bars); return 0; + +err_unmap_bar0: + if (nfp->bar[0].iomem) + iounmap(nfp->bar[0].iomem); + return err; } static void disable_bars(struct nfp6000_pcie *nfp) @@ -1327,7 +1353,7 @@ struct nfp_cpp *nfp_cpp_from_nfp6000_pcie(struct pci_dev *pdev) /* Finished with card initialization. */ dev_info(&pdev->dev, - "Netronome Flow Processor NFP4000/NFP6000 PCIe Card Probe\n"); + "Netronome Flow Processor NFP4000/NFP5000/NFP6000 PCIe Card Probe\n"); pcie_print_link_status(pdev); nfp = kzalloc(sizeof(*nfp), GFP_KERNEL); diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpp.h b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpp.h index c338d539fa96..123e29cba6d1 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpp.h +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpp.h @@ -56,9 +56,16 @@ dev_info(nfp_cpp_device(cpp)->parent, NFP_SUBSYS ": " fmt, ## args) #define nfp_dbg(cpp, fmt, args...) \ dev_dbg(nfp_cpp_device(cpp)->parent, NFP_SUBSYS ": " fmt, ## args) +#define nfp_printk(level, cpp, fmt, args...) \ + dev_printk(level, nfp_cpp_device(cpp)->parent, \ + NFP_SUBSYS ": " fmt, ## args) #define PCI_64BIT_BAR_COUNT 3 +/* NFP hardware vendor/device ids. + */ +#define PCI_DEVICE_ID_NETRONOME_NFP3800 0x3800 + #define NFP_CPP_NUM_TARGETS 16 /* Max size of area it should be safe to request */ #define NFP_CPP_SAFE_AREA_SIZE SZ_2M @@ -226,6 +233,7 @@ void nfp_cpp_free(struct nfp_cpp *cpp); u32 nfp_cpp_model(struct nfp_cpp *cpp); u16 nfp_cpp_interface(struct nfp_cpp *cpp); int nfp_cpp_serial(struct nfp_cpp *cpp, const u8 **serial); +unsigned int nfp_cpp_mu_locality_lsb(struct nfp_cpp *cpp); struct nfp_cpp_area *nfp_cpp_area_alloc_with_name(struct nfp_cpp *cpp, u32 cpp_id, @@ -286,8 +294,8 @@ int nfp_cpp_writeq(struct nfp_cpp *cpp, u32 cpp_id, unsigned long long address, u64 value); u8 __iomem * -nfp_cpp_map_area(struct nfp_cpp *cpp, const char *name, int domain, int target, - u64 addr, unsigned long size, struct nfp_cpp_area **area); +nfp_cpp_map_area(struct nfp_cpp *cpp, const char *name, u32 cpp_id, u64 addr, + unsigned long size, struct nfp_cpp_area **area); struct nfp_cpp_mutex; diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c index 73de57a09800..f7e1d79e735f 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c @@ -75,6 +75,7 @@ struct nfp_cpp_resource { * @interface: chip interface id we are using to reach it * @serial: chip serial number * @imb_cat_table: CPP Mapping Table + * @mu_locality_lsb: MU access type bit offset * * Following fields use explicit locking: * @resource_list: NFP CPP resource list @@ -100,6 +101,7 @@ struct nfp_cpp { wait_queue_head_t waitq; u32 imb_cat_table[16]; + unsigned int mu_locality_lsb; struct mutex area_cache_mutex; struct list_head area_cache_list; @@ -266,6 +268,34 @@ int nfp_cpp_serial(struct nfp_cpp *cpp, const u8 **serial) return sizeof(cpp->serial); } +#define NFP_IMB_TGTADDRESSMODECFG_MODE_of(_x) (((_x) >> 13) & 0x7) +#define NFP_IMB_TGTADDRESSMODECFG_ADDRMODE BIT(12) +#define NFP_IMB_TGTADDRESSMODECFG_ADDRMODE_32_BIT 0 +#define NFP_IMB_TGTADDRESSMODECFG_ADDRMODE_40_BIT BIT(12) + +static int nfp_cpp_set_mu_locality_lsb(struct nfp_cpp *cpp) +{ + unsigned int mode, addr40; + u32 imbcppat; + int res; + + imbcppat = cpp->imb_cat_table[NFP_CPP_TARGET_MU]; + mode = NFP_IMB_TGTADDRESSMODECFG_MODE_of(imbcppat); + addr40 = !!(imbcppat & NFP_IMB_TGTADDRESSMODECFG_ADDRMODE); + + res = nfp_cppat_mu_locality_lsb(mode, addr40); + if (res < 0) + return res; + cpp->mu_locality_lsb = res; + + return 0; +} + +unsigned int nfp_cpp_mu_locality_lsb(struct nfp_cpp *cpp) +{ + return cpp->mu_locality_lsb; +} + /** * nfp_cpp_area_alloc_with_name() - allocate a new CPP area * @cpp: CPP device handle @@ -1241,6 +1271,12 @@ nfp_cpp_from_operations(const struct nfp_cpp_operations *ops, nfp_cpp_readl(cpp, arm, NFP_ARM_GCSR + NFP_ARM_GCSR_SOFTMODEL3, &mask[1]); + err = nfp_cpp_set_mu_locality_lsb(cpp); + if (err < 0) { + dev_err(parent, "Can't calculate MU locality bit offset\n"); + goto err_out; + } + dev_info(cpp->dev.parent, "Model: 0x%08x, SN: %pM, Ifc: 0x%04x\n", nfp_cpp_model(cpp), cpp->serial, nfp_cpp_interface(cpp)); diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpplib.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpplib.c index 20bad05e2e92..03fcde5fa137 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpplib.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpplib.c @@ -294,8 +294,7 @@ exit_release: * nfp_cpp_map_area() - Helper function to map an area * @cpp: NFP CPP handler * @name: Name for the area - * @domain: CPP domain - * @target: CPP target + * @cpp_id: CPP ID for operation * @addr: CPP address * @size: Size of the area * @area: Area handle (output) @@ -306,15 +305,12 @@ exit_release: * Return: Pointer to memory mapped area or ERR_PTR */ u8 __iomem * -nfp_cpp_map_area(struct nfp_cpp *cpp, const char *name, int domain, int target, - u64 addr, unsigned long size, struct nfp_cpp_area **area) +nfp_cpp_map_area(struct nfp_cpp *cpp, const char *name, u32 cpp_id, u64 addr, + unsigned long size, struct nfp_cpp_area **area) { u8 __iomem *res; - u32 dest; - dest = NFP_CPP_ISLAND_ID(target, NFP_CPP_ACTION_RW, 0, domain); - - *area = nfp_cpp_area_alloc_acquire(cpp, name, dest, addr, size); + *area = nfp_cpp_area_alloc_acquire(cpp, name, cpp_id, addr, size); if (!*area) goto err_eio; diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c index 40510860341b..a164fbc85cd3 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c @@ -156,29 +156,6 @@ static u64 nffw_fwinfo_mip_offset_get(const struct nffw_fwinfo *fi) return (mip_off_hi & 0xFF) << 32 | le32_to_cpu(fi->mip_offset_lo); } -#define NFP_IMB_TGTADDRESSMODECFG_MODE_of(_x) (((_x) >> 13) & 0x7) -#define NFP_IMB_TGTADDRESSMODECFG_ADDRMODE BIT(12) -#define NFP_IMB_TGTADDRESSMODECFG_ADDRMODE_32_BIT 0 -#define NFP_IMB_TGTADDRESSMODECFG_ADDRMODE_40_BIT BIT(12) - -static int nfp_mip_mu_locality_lsb(struct nfp_cpp *cpp) -{ - unsigned int mode, addr40; - u32 xpbaddr, imbcppat; - int err; - - /* Hardcoded XPB IMB Base, island 0 */ - xpbaddr = 0x000a0000 + NFP_CPP_TARGET_MU * 4; - err = nfp_xpb_readl(cpp, xpbaddr, &imbcppat); - if (err < 0) - return err; - - mode = NFP_IMB_TGTADDRESSMODECFG_MODE_of(imbcppat); - addr40 = !!(imbcppat & NFP_IMB_TGTADDRESSMODECFG_ADDRMODE); - - return nfp_cppat_mu_locality_lsb(mode, addr40); -} - static unsigned int nffw_res_fwinfos(struct nfp_nffw_info_data *fwinf, struct nffw_fwinfo **arr) { @@ -304,14 +281,7 @@ int nfp_nffw_info_mip_first(struct nfp_nffw_info *state, u32 *cpp_id, u64 *off) *off = nffw_fwinfo_mip_offset_get(fwinfo); if (nffw_fwinfo_mip_mu_da_get(fwinfo)) { - int locality_off; - - if (NFP_CPP_ID_TARGET_of(*cpp_id) != NFP_CPP_TARGET_MU) - return 0; - - locality_off = nfp_mip_mu_locality_lsb(state->cpp); - if (locality_off < 0) - return locality_off; + int locality_off = nfp_cpp_mu_locality_lsb(state->cpp); *off &= ~(NFP_MU_ADDR_ACCESS_TYPE_MASK << locality_off); *off |= NFP_MU_ADDR_ACCESS_TYPE_DIRECT << locality_off; diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.h b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.h index df599d5b6bb3..8d2cbdf4d517 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.h +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.h @@ -61,10 +61,12 @@ void nfp_mip_strtab(const struct nfp_mip *mip, u32 *addr, u32 *size); /* Implemented in nfp_rtsym.c */ -#define NFP_RTSYM_TYPE_NONE 0 -#define NFP_RTSYM_TYPE_OBJECT 1 -#define NFP_RTSYM_TYPE_FUNCTION 2 -#define NFP_RTSYM_TYPE_ABS 3 +enum nfp_rtsym_type { + NFP_RTSYM_TYPE_NONE = 0, + NFP_RTSYM_TYPE_OBJECT = 1, + NFP_RTSYM_TYPE_FUNCTION = 2, + NFP_RTSYM_TYPE_ABS = 3, +}; #define NFP_RTSYM_TARGET_NONE 0 #define NFP_RTSYM_TARGET_LMEM -1 @@ -83,7 +85,7 @@ struct nfp_rtsym { const char *name; u64 addr; u64 size; - int type; + enum nfp_rtsym_type type; int target; int domain; }; @@ -98,6 +100,32 @@ const struct nfp_rtsym *nfp_rtsym_get(struct nfp_rtsym_table *rtbl, int idx); const struct nfp_rtsym * nfp_rtsym_lookup(struct nfp_rtsym_table *rtbl, const char *name); +u64 nfp_rtsym_size(const struct nfp_rtsym *rtsym); +int __nfp_rtsym_read(struct nfp_cpp *cpp, const struct nfp_rtsym *sym, + u8 action, u8 token, u64 off, void *buf, size_t len); +int nfp_rtsym_read(struct nfp_cpp *cpp, const struct nfp_rtsym *sym, u64 off, + void *buf, size_t len); +int __nfp_rtsym_readl(struct nfp_cpp *cpp, const struct nfp_rtsym *sym, + u8 action, u8 token, u64 off, u32 *value); +int nfp_rtsym_readl(struct nfp_cpp *cpp, const struct nfp_rtsym *sym, u64 off, + u32 *value); +int __nfp_rtsym_readq(struct nfp_cpp *cpp, const struct nfp_rtsym *sym, + u8 action, u8 token, u64 off, u64 *value); +int nfp_rtsym_readq(struct nfp_cpp *cpp, const struct nfp_rtsym *sym, u64 off, + u64 *value); +int __nfp_rtsym_write(struct nfp_cpp *cpp, const struct nfp_rtsym *sym, + u8 action, u8 token, u64 off, void *buf, size_t len); +int nfp_rtsym_write(struct nfp_cpp *cpp, const struct nfp_rtsym *sym, u64 off, + void *buf, size_t len); +int __nfp_rtsym_writel(struct nfp_cpp *cpp, const struct nfp_rtsym *sym, + u8 action, u8 token, u64 off, u32 value); +int nfp_rtsym_writel(struct nfp_cpp *cpp, const struct nfp_rtsym *sym, u64 off, + u32 value); +int __nfp_rtsym_writeq(struct nfp_cpp *cpp, const struct nfp_rtsym *sym, + u8 action, u8 token, u64 off, u64 value); +int nfp_rtsym_writeq(struct nfp_cpp *cpp, const struct nfp_rtsym *sym, u64 off, + u64 value); + u64 nfp_rtsym_read_le(struct nfp_rtsym_table *rtbl, const char *name, int *error); int nfp_rtsym_write_le(struct nfp_rtsym_table *rtbl, const char *name, diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c index 2abee0fe3a7c..bf593a6b26a1 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c @@ -87,6 +87,11 @@ #define NSP_CODE_MAJOR GENMASK(15, 12) #define NSP_CODE_MINOR GENMASK(11, 0) +#define NFP_FW_LOAD_RET_MAJOR GENMASK(15, 8) +#define NFP_FW_LOAD_RET_MINOR GENMASK(23, 16) + +#define NFP_HWINFO_LOOKUP_SIZE GENMASK(11, 0) + enum nfp_nsp_cmd { SPCODE_NOOP = 0, /* No operation */ SPCODE_SOFT_RESET = 1, /* Soft reset the NFP */ @@ -100,6 +105,8 @@ enum nfp_nsp_cmd { SPCODE_NSP_WRITE_FLASH = 11, /* Load and flash image from buffer */ SPCODE_NSP_SENSORS = 12, /* Read NSP sensor(s) */ SPCODE_NSP_IDENTIFY = 13, /* Read NSP version */ + SPCODE_FW_STORED = 16, /* If no FW loaded, load flash app FW */ + SPCODE_HWINFO_LOOKUP = 17, /* Lookup HWinfo with overwrites etc. */ }; static const struct { @@ -127,6 +134,40 @@ struct nfp_nsp { void *entries; }; +/** + * struct nfp_nsp_command_arg - NFP command argument structure + * @code: NFP SP Command Code + * @timeout_sec:Timeout value to wait for completion in seconds + * @option: NFP SP Command Argument + * @buff_cpp: NFP SP Buffer CPP Address info + * @buff_addr: NFP SP Buffer Host address + * @error_cb: Callback for interpreting option if error occurred + */ +struct nfp_nsp_command_arg { + u16 code; + unsigned int timeout_sec; + u32 option; + u32 buff_cpp; + u64 buff_addr; + void (*error_cb)(struct nfp_nsp *state, u32 ret_val); +}; + +/** + * struct nfp_nsp_command_buf_arg - NFP command with buffer argument structure + * @arg: NFP command argument structure + * @in_buf: Buffer with data for input + * @in_size: Size of @in_buf + * @out_buf: Buffer for output data + * @out_size: Size of @out_buf + */ +struct nfp_nsp_command_buf_arg { + struct nfp_nsp_command_arg arg; + const void *in_buf; + unsigned int in_size; + void *out_buf; + unsigned int out_size; +}; + struct nfp_cpp *nfp_nsp_cpp(struct nfp_nsp *state) { return state->cpp; @@ -291,11 +332,7 @@ nfp_nsp_wait_reg(struct nfp_cpp *cpp, u64 *reg, u32 nsp_cpp, u64 addr, /** * __nfp_nsp_command() - Execute a command on the NFP Service Processor * @state: NFP SP state - * @code: NFP SP Command Code - * @option: NFP SP Command Argument - * @buff_cpp: NFP SP Buffer CPP Address info - * @buff_addr: NFP SP Buffer Host address - * @timeout_sec:Timeout value to wait for completion in seconds + * @arg: NFP command argument structure * * Return: 0 for success with no result * @@ -308,8 +345,7 @@ nfp_nsp_wait_reg(struct nfp_cpp *cpp, u64 *reg, u32 nsp_cpp, u64 addr, * -ETIMEDOUT if the NSP took longer than @timeout_sec seconds to complete */ static int -__nfp_nsp_command(struct nfp_nsp *state, u16 code, u32 option, u32 buff_cpp, - u64 buff_addr, u32 timeout_sec) +__nfp_nsp_command(struct nfp_nsp *state, const struct nfp_nsp_command_arg *arg) { u64 reg, ret_val, nsp_base, nsp_buffer, nsp_status, nsp_command; struct nfp_cpp *cpp = state->cpp; @@ -326,22 +362,22 @@ __nfp_nsp_command(struct nfp_nsp *state, u16 code, u32 option, u32 buff_cpp, if (err) return err; - if (!FIELD_FIT(NSP_BUFFER_CPP, buff_cpp >> 8) || - !FIELD_FIT(NSP_BUFFER_ADDRESS, buff_addr)) { + if (!FIELD_FIT(NSP_BUFFER_CPP, arg->buff_cpp >> 8) || + !FIELD_FIT(NSP_BUFFER_ADDRESS, arg->buff_addr)) { nfp_err(cpp, "Host buffer out of reach %08x %016llx\n", - buff_cpp, buff_addr); + arg->buff_cpp, arg->buff_addr); return -EINVAL; } err = nfp_cpp_writeq(cpp, nsp_cpp, nsp_buffer, - FIELD_PREP(NSP_BUFFER_CPP, buff_cpp >> 8) | - FIELD_PREP(NSP_BUFFER_ADDRESS, buff_addr)); + FIELD_PREP(NSP_BUFFER_CPP, arg->buff_cpp >> 8) | + FIELD_PREP(NSP_BUFFER_ADDRESS, arg->buff_addr)); if (err < 0) return err; err = nfp_cpp_writeq(cpp, nsp_cpp, nsp_command, - FIELD_PREP(NSP_COMMAND_OPTION, option) | - FIELD_PREP(NSP_COMMAND_CODE, code) | + FIELD_PREP(NSP_COMMAND_OPTION, arg->option) | + FIELD_PREP(NSP_COMMAND_CODE, arg->code) | FIELD_PREP(NSP_COMMAND_START, 1)); if (err < 0) return err; @@ -351,16 +387,16 @@ __nfp_nsp_command(struct nfp_nsp *state, u16 code, u32 option, u32 buff_cpp, NSP_COMMAND_START, 0, NFP_NSP_TIMEOUT_DEFAULT); if (err) { nfp_err(cpp, "Error %d waiting for code 0x%04x to start\n", - err, code); + err, arg->code); return err; } /* Wait for NSP_STATUS_BUSY to go to 0 */ err = nfp_nsp_wait_reg(cpp, ®, nsp_cpp, nsp_status, NSP_STATUS_BUSY, - 0, timeout_sec); + 0, arg->timeout_sec ?: NFP_NSP_TIMEOUT_DEFAULT); if (err) { nfp_err(cpp, "Error %d waiting for code 0x%04x to complete\n", - err, code); + err, arg->code); return err; } @@ -372,26 +408,28 @@ __nfp_nsp_command(struct nfp_nsp *state, u16 code, u32 option, u32 buff_cpp, err = FIELD_GET(NSP_STATUS_RESULT, reg); if (err) { nfp_warn(cpp, "Result (error) code set: %d (%d) command: %d\n", - -err, (int)ret_val, code); - nfp_nsp_print_extended_error(state, ret_val); + -err, (int)ret_val, arg->code); + if (arg->error_cb) + arg->error_cb(state, ret_val); + else + nfp_nsp_print_extended_error(state, ret_val); return -err; } return ret_val; } -static int -nfp_nsp_command(struct nfp_nsp *state, u16 code, u32 option, u32 buff_cpp, - u64 buff_addr) +static int nfp_nsp_command(struct nfp_nsp *state, u16 code) { - return __nfp_nsp_command(state, code, option, buff_cpp, buff_addr, - NFP_NSP_TIMEOUT_DEFAULT); + const struct nfp_nsp_command_arg arg = { + .code = code, + }; + + return __nfp_nsp_command(state, &arg); } static int -__nfp_nsp_command_buf(struct nfp_nsp *nsp, u16 code, u32 option, - const void *in_buf, unsigned int in_size, void *out_buf, - unsigned int out_size, u32 timeout_sec) +nfp_nsp_command_buf(struct nfp_nsp *nsp, struct nfp_nsp_command_buf_arg *arg) { struct nfp_cpp *cpp = nsp->cpp; unsigned int max_size; @@ -401,7 +439,7 @@ __nfp_nsp_command_buf(struct nfp_nsp *nsp, u16 code, u32 option, if (nsp->ver.minor < 13) { nfp_err(cpp, "NSP: Code 0x%04x with buffer not supported (ABI %hu.%hu)\n", - code, nsp->ver.major, nsp->ver.minor); + arg->arg.code, nsp->ver.major, nsp->ver.minor); return -EOPNOTSUPP; } @@ -412,10 +450,11 @@ __nfp_nsp_command_buf(struct nfp_nsp *nsp, u16 code, u32 option, if (err < 0) return err; - max_size = max(in_size, out_size); + max_size = max(arg->in_size, arg->out_size); if (FIELD_GET(NSP_DFLT_BUFFER_SIZE_MB, reg) * SZ_1M < max_size) { nfp_err(cpp, "NSP: default buffer too small for command 0x%04x (%llu < %u)\n", - code, FIELD_GET(NSP_DFLT_BUFFER_SIZE_MB, reg) * SZ_1M, + arg->arg.code, + FIELD_GET(NSP_DFLT_BUFFER_SIZE_MB, reg) * SZ_1M, max_size); return -EINVAL; } @@ -430,27 +469,30 @@ __nfp_nsp_command_buf(struct nfp_nsp *nsp, u16 code, u32 option, cpp_id = FIELD_GET(NSP_DFLT_BUFFER_CPP, reg) << 8; cpp_buf = FIELD_GET(NSP_DFLT_BUFFER_ADDRESS, reg); - if (in_buf && in_size) { - err = nfp_cpp_write(cpp, cpp_id, cpp_buf, in_buf, in_size); + if (arg->in_buf && arg->in_size) { + err = nfp_cpp_write(cpp, cpp_id, cpp_buf, + arg->in_buf, arg->in_size); if (err < 0) return err; } /* Zero out remaining part of the buffer */ - if (out_buf && out_size && out_size > in_size) { - memset(out_buf, 0, out_size - in_size); - err = nfp_cpp_write(cpp, cpp_id, cpp_buf + in_size, - out_buf, out_size - in_size); + if (arg->out_buf && arg->out_size && arg->out_size > arg->in_size) { + memset(arg->out_buf, 0, arg->out_size - arg->in_size); + err = nfp_cpp_write(cpp, cpp_id, cpp_buf + arg->in_size, + arg->out_buf, arg->out_size - arg->in_size); if (err < 0) return err; } - ret = __nfp_nsp_command(nsp, code, option, cpp_id, cpp_buf, - timeout_sec); + arg->arg.buff_cpp = cpp_id; + arg->arg.buff_addr = cpp_buf; + ret = __nfp_nsp_command(nsp, &arg->arg); if (ret < 0) return ret; - if (out_buf && out_size) { - err = nfp_cpp_read(cpp, cpp_id, cpp_buf, out_buf, out_size); + if (arg->out_buf && arg->out_size) { + err = nfp_cpp_read(cpp, cpp_id, cpp_buf, + arg->out_buf, arg->out_size); if (err < 0) return err; } @@ -458,16 +500,6 @@ __nfp_nsp_command_buf(struct nfp_nsp *nsp, u16 code, u32 option, return ret; } -static int -nfp_nsp_command_buf(struct nfp_nsp *nsp, u16 code, u32 option, - const void *in_buf, unsigned int in_size, void *out_buf, - unsigned int out_size) -{ - return __nfp_nsp_command_buf(nsp, code, option, in_buf, in_size, - out_buf, out_size, - NFP_NSP_TIMEOUT_DEFAULT); -} - int nfp_nsp_wait(struct nfp_nsp *state) { const unsigned long wait_until = jiffies + NFP_NSP_TIMEOUT_BOOT * HZ; @@ -479,7 +511,7 @@ int nfp_nsp_wait(struct nfp_nsp *state) for (;;) { const unsigned long start_time = jiffies; - err = nfp_nsp_command(state, SPCODE_NOOP, 0, 0, 0); + err = nfp_nsp_command(state, SPCODE_NOOP); if (err != -EAGAIN) break; @@ -501,53 +533,211 @@ int nfp_nsp_wait(struct nfp_nsp *state) int nfp_nsp_device_soft_reset(struct nfp_nsp *state) { - return nfp_nsp_command(state, SPCODE_SOFT_RESET, 0, 0, 0); + return nfp_nsp_command(state, SPCODE_SOFT_RESET); } int nfp_nsp_mac_reinit(struct nfp_nsp *state) { - return nfp_nsp_command(state, SPCODE_MAC_INIT, 0, 0, 0); + return nfp_nsp_command(state, SPCODE_MAC_INIT); +} + +static void nfp_nsp_load_fw_extended_msg(struct nfp_nsp *state, u32 ret_val) +{ + static const char * const major_msg[] = { + /* 0 */ "Firmware from driver loaded", + /* 1 */ "Firmware from flash loaded", + /* 2 */ "Firmware loading failure", + }; + static const char * const minor_msg[] = { + /* 0 */ "", + /* 1 */ "no named partition on flash", + /* 2 */ "error reading from flash", + /* 3 */ "can not deflate", + /* 4 */ "not a trusted file", + /* 5 */ "can not parse FW file", + /* 6 */ "MIP not found in FW file", + /* 7 */ "null firmware name in MIP", + /* 8 */ "FW version none", + /* 9 */ "FW build number none", + /* 10 */ "no FW selection policy HWInfo key found", + /* 11 */ "static FW selection policy", + /* 12 */ "FW version has precedence", + /* 13 */ "different FW application load requested", + /* 14 */ "development build", + }; + unsigned int major, minor; + const char *level; + + major = FIELD_GET(NFP_FW_LOAD_RET_MAJOR, ret_val); + minor = FIELD_GET(NFP_FW_LOAD_RET_MINOR, ret_val); + + if (!nfp_nsp_has_stored_fw_load(state)) + return; + + /* Lower the message level in legacy case */ + if (major == 0 && (minor == 0 || minor == 10)) + level = KERN_DEBUG; + else if (major == 2) + level = KERN_ERR; + else + level = KERN_INFO; + + if (major >= ARRAY_SIZE(major_msg)) + nfp_printk(level, state->cpp, "FW loading status: %x\n", + ret_val); + else if (minor >= ARRAY_SIZE(minor_msg)) + nfp_printk(level, state->cpp, "%s, reason code: %d\n", + major_msg[major], minor); + else + nfp_printk(level, state->cpp, "%s%c %s\n", + major_msg[major], minor ? ',' : '.', + minor_msg[minor]); } int nfp_nsp_load_fw(struct nfp_nsp *state, const struct firmware *fw) { - return nfp_nsp_command_buf(state, SPCODE_FW_LOAD, fw->size, fw->data, - fw->size, NULL, 0); + struct nfp_nsp_command_buf_arg load_fw = { + { + .code = SPCODE_FW_LOAD, + .option = fw->size, + .error_cb = nfp_nsp_load_fw_extended_msg, + }, + .in_buf = fw->data, + .in_size = fw->size, + }; + int ret; + + ret = nfp_nsp_command_buf(state, &load_fw); + if (ret < 0) + return ret; + + nfp_nsp_load_fw_extended_msg(state, ret); + return 0; } int nfp_nsp_write_flash(struct nfp_nsp *state, const struct firmware *fw) { - /* The flash time is specified to take a maximum of 70s so we add an - * additional factor to this spec time. - */ - u32 timeout_sec = 2.5 * 70; - - return __nfp_nsp_command_buf(state, SPCODE_NSP_WRITE_FLASH, fw->size, - fw->data, fw->size, NULL, 0, timeout_sec); + struct nfp_nsp_command_buf_arg write_flash = { + { + .code = SPCODE_NSP_WRITE_FLASH, + .option = fw->size, + /* The flash time is specified to take a maximum of 70s + * so we add an additional factor to this spec time. + */ + .timeout_sec = 2.5 * 70, + }, + .in_buf = fw->data, + .in_size = fw->size, + }; + + return nfp_nsp_command_buf(state, &write_flash); } int nfp_nsp_read_eth_table(struct nfp_nsp *state, void *buf, unsigned int size) { - return nfp_nsp_command_buf(state, SPCODE_ETH_RESCAN, size, NULL, 0, - buf, size); + struct nfp_nsp_command_buf_arg eth_rescan = { + { + .code = SPCODE_ETH_RESCAN, + .option = size, + }, + .out_buf = buf, + .out_size = size, + }; + + return nfp_nsp_command_buf(state, ð_rescan); } int nfp_nsp_write_eth_table(struct nfp_nsp *state, const void *buf, unsigned int size) { - return nfp_nsp_command_buf(state, SPCODE_ETH_CONTROL, size, buf, size, - NULL, 0); + struct nfp_nsp_command_buf_arg eth_ctrl = { + { + .code = SPCODE_ETH_CONTROL, + .option = size, + }, + .in_buf = buf, + .in_size = size, + }; + + return nfp_nsp_command_buf(state, ð_ctrl); } int nfp_nsp_read_identify(struct nfp_nsp *state, void *buf, unsigned int size) { - return nfp_nsp_command_buf(state, SPCODE_NSP_IDENTIFY, size, NULL, 0, - buf, size); + struct nfp_nsp_command_buf_arg identify = { + { + .code = SPCODE_NSP_IDENTIFY, + .option = size, + }, + .out_buf = buf, + .out_size = size, + }; + + return nfp_nsp_command_buf(state, &identify); } int nfp_nsp_read_sensors(struct nfp_nsp *state, unsigned int sensor_mask, void *buf, unsigned int size) { - return nfp_nsp_command_buf(state, SPCODE_NSP_SENSORS, sensor_mask, - NULL, 0, buf, size); + struct nfp_nsp_command_buf_arg sensors = { + { + .code = SPCODE_NSP_SENSORS, + .option = sensor_mask, + }, + .out_buf = buf, + .out_size = size, + }; + + return nfp_nsp_command_buf(state, &sensors); +} + +int nfp_nsp_load_stored_fw(struct nfp_nsp *state) +{ + const struct nfp_nsp_command_arg arg = { + .code = SPCODE_FW_STORED, + .error_cb = nfp_nsp_load_fw_extended_msg, + }; + int ret; + + ret = __nfp_nsp_command(state, &arg); + if (ret < 0) + return ret; + + nfp_nsp_load_fw_extended_msg(state, ret); + return 0; +} + +static int +__nfp_nsp_hwinfo_lookup(struct nfp_nsp *state, void *buf, unsigned int size) +{ + struct nfp_nsp_command_buf_arg hwinfo_lookup = { + { + .code = SPCODE_HWINFO_LOOKUP, + .option = size, + }, + .in_buf = buf, + .in_size = size, + .out_buf = buf, + .out_size = size, + }; + + return nfp_nsp_command_buf(state, &hwinfo_lookup); +} + +int nfp_nsp_hwinfo_lookup(struct nfp_nsp *state, void *buf, unsigned int size) +{ + int err; + + size = min_t(u32, size, NFP_HWINFO_LOOKUP_SIZE); + + err = __nfp_nsp_hwinfo_lookup(state, buf, size); + if (err) + return err; + + if (strnlen(buf, size) == size) { + nfp_err(state->cpp, "NSP HWinfo value not NULL-terminated\n"); + return -EINVAL; + } + + return 0; } diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h index f23d9e06f097..bd6c9071c8e9 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h @@ -50,12 +50,24 @@ int nfp_nsp_device_soft_reset(struct nfp_nsp *state); int nfp_nsp_load_fw(struct nfp_nsp *state, const struct firmware *fw); int nfp_nsp_write_flash(struct nfp_nsp *state, const struct firmware *fw); int nfp_nsp_mac_reinit(struct nfp_nsp *state); +int nfp_nsp_load_stored_fw(struct nfp_nsp *state); +int nfp_nsp_hwinfo_lookup(struct nfp_nsp *state, void *buf, unsigned int size); static inline bool nfp_nsp_has_mac_reinit(struct nfp_nsp *state) { return nfp_nsp_get_abi_ver_minor(state) > 20; } +static inline bool nfp_nsp_has_stored_fw_load(struct nfp_nsp *state) +{ + return nfp_nsp_get_abi_ver_minor(state) > 23; +} + +static inline bool nfp_nsp_has_hwinfo_lookup(struct nfp_nsp *state) +{ + return nfp_nsp_get_abi_ver_minor(state) > 24; +} + enum nfp_eth_interface { NFP_INTERFACE_NONE = 0, NFP_INTERFACE_SFP = 1, diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_rtsym.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_rtsym.c index 9e34216578da..1ad0a015572e 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_rtsym.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_rtsym.c @@ -39,6 +39,8 @@ * Espen Skoglund <espen.skoglund@netronome.com> * Francois H. Theron <francois.theron@netronome.com> */ + +#include <asm/unaligned.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/slab.h> @@ -233,6 +235,229 @@ nfp_rtsym_lookup(struct nfp_rtsym_table *rtbl, const char *name) return NULL; } +u64 nfp_rtsym_size(const struct nfp_rtsym *sym) +{ + switch (sym->type) { + case NFP_RTSYM_TYPE_NONE: + pr_err("rtsym '%s': type NONE\n", sym->name); + return 0; + default: + pr_warn("rtsym '%s': unknown type: %d\n", sym->name, sym->type); + /* fall through */ + case NFP_RTSYM_TYPE_OBJECT: + case NFP_RTSYM_TYPE_FUNCTION: + return sym->size; + case NFP_RTSYM_TYPE_ABS: + return sizeof(u64); + } +} + +static int +nfp_rtsym_to_dest(struct nfp_cpp *cpp, const struct nfp_rtsym *sym, + u8 action, u8 token, u64 off, u32 *cpp_id, u64 *addr) +{ + if (sym->type != NFP_RTSYM_TYPE_OBJECT) { + nfp_err(cpp, "rtsym '%s': direct access to non-object rtsym\n", + sym->name); + return -EINVAL; + } + + *addr = sym->addr + off; + + if (sym->target == NFP_RTSYM_TARGET_EMU_CACHE) { + int locality_off = nfp_cpp_mu_locality_lsb(cpp); + + *addr &= ~(NFP_MU_ADDR_ACCESS_TYPE_MASK << locality_off); + *addr |= NFP_MU_ADDR_ACCESS_TYPE_DIRECT << locality_off; + + *cpp_id = NFP_CPP_ISLAND_ID(NFP_CPP_TARGET_MU, action, token, + sym->domain); + } else if (sym->target < 0) { + nfp_err(cpp, "rtsym '%s': unhandled target encoding: %d\n", + sym->name, sym->target); + return -EINVAL; + } else { + *cpp_id = NFP_CPP_ISLAND_ID(sym->target, action, token, + sym->domain); + } + + return 0; +} + +int __nfp_rtsym_read(struct nfp_cpp *cpp, const struct nfp_rtsym *sym, + u8 action, u8 token, u64 off, void *buf, size_t len) +{ + u64 sym_size = nfp_rtsym_size(sym); + u32 cpp_id; + u64 addr; + int err; + + if (off > sym_size) { + nfp_err(cpp, "rtsym '%s': read out of bounds: off: %lld + len: %zd > size: %lld\n", + sym->name, off, len, sym_size); + return -ENXIO; + } + len = min_t(size_t, len, sym_size - off); + + if (sym->type == NFP_RTSYM_TYPE_ABS) { + u8 tmp[8]; + + put_unaligned_le64(sym->addr, tmp); + memcpy(buf, &tmp[off], len); + + return len; + } + + err = nfp_rtsym_to_dest(cpp, sym, action, token, off, &cpp_id, &addr); + if (err) + return err; + + return nfp_cpp_read(cpp, cpp_id, addr, buf, len); +} + +int nfp_rtsym_read(struct nfp_cpp *cpp, const struct nfp_rtsym *sym, u64 off, + void *buf, size_t len) +{ + return __nfp_rtsym_read(cpp, sym, NFP_CPP_ACTION_RW, 0, off, buf, len); +} + +int __nfp_rtsym_readl(struct nfp_cpp *cpp, const struct nfp_rtsym *sym, + u8 action, u8 token, u64 off, u32 *value) +{ + u32 cpp_id; + u64 addr; + int err; + + if (off + 4 > nfp_rtsym_size(sym)) { + nfp_err(cpp, "rtsym '%s': readl out of bounds: off: %lld + 4 > size: %lld\n", + sym->name, off, nfp_rtsym_size(sym)); + return -ENXIO; + } + + err = nfp_rtsym_to_dest(cpp, sym, action, token, off, &cpp_id, &addr); + if (err) + return err; + + return nfp_cpp_readl(cpp, cpp_id, addr, value); +} + +int nfp_rtsym_readl(struct nfp_cpp *cpp, const struct nfp_rtsym *sym, u64 off, + u32 *value) +{ + return __nfp_rtsym_readl(cpp, sym, NFP_CPP_ACTION_RW, 0, off, value); +} + +int __nfp_rtsym_readq(struct nfp_cpp *cpp, const struct nfp_rtsym *sym, + u8 action, u8 token, u64 off, u64 *value) +{ + u32 cpp_id; + u64 addr; + int err; + + if (off + 8 > nfp_rtsym_size(sym)) { + nfp_err(cpp, "rtsym '%s': readq out of bounds: off: %lld + 8 > size: %lld\n", + sym->name, off, nfp_rtsym_size(sym)); + return -ENXIO; + } + + if (sym->type == NFP_RTSYM_TYPE_ABS) { + *value = sym->addr; + return 0; + } + + err = nfp_rtsym_to_dest(cpp, sym, action, token, off, &cpp_id, &addr); + if (err) + return err; + + return nfp_cpp_readq(cpp, cpp_id, addr, value); +} + +int nfp_rtsym_readq(struct nfp_cpp *cpp, const struct nfp_rtsym *sym, u64 off, + u64 *value) +{ + return __nfp_rtsym_readq(cpp, sym, NFP_CPP_ACTION_RW, 0, off, value); +} + +int __nfp_rtsym_write(struct nfp_cpp *cpp, const struct nfp_rtsym *sym, + u8 action, u8 token, u64 off, void *buf, size_t len) +{ + u64 sym_size = nfp_rtsym_size(sym); + u32 cpp_id; + u64 addr; + int err; + + if (off > sym_size) { + nfp_err(cpp, "rtsym '%s': write out of bounds: off: %lld + len: %zd > size: %lld\n", + sym->name, off, len, sym_size); + return -ENXIO; + } + len = min_t(size_t, len, sym_size - off); + + err = nfp_rtsym_to_dest(cpp, sym, action, token, off, &cpp_id, &addr); + if (err) + return err; + + return nfp_cpp_write(cpp, cpp_id, addr, buf, len); +} + +int nfp_rtsym_write(struct nfp_cpp *cpp, const struct nfp_rtsym *sym, u64 off, + void *buf, size_t len) +{ + return __nfp_rtsym_write(cpp, sym, NFP_CPP_ACTION_RW, 0, off, buf, len); +} + +int __nfp_rtsym_writel(struct nfp_cpp *cpp, const struct nfp_rtsym *sym, + u8 action, u8 token, u64 off, u32 value) +{ + u32 cpp_id; + u64 addr; + int err; + + if (off + 4 > nfp_rtsym_size(sym)) { + nfp_err(cpp, "rtsym '%s': writel out of bounds: off: %lld + 4 > size: %lld\n", + sym->name, off, nfp_rtsym_size(sym)); + return -ENXIO; + } + + err = nfp_rtsym_to_dest(cpp, sym, action, token, off, &cpp_id, &addr); + if (err) + return err; + + return nfp_cpp_writel(cpp, cpp_id, addr, value); +} + +int nfp_rtsym_writel(struct nfp_cpp *cpp, const struct nfp_rtsym *sym, u64 off, + u32 value) +{ + return __nfp_rtsym_writel(cpp, sym, NFP_CPP_ACTION_RW, 0, off, value); +} + +int __nfp_rtsym_writeq(struct nfp_cpp *cpp, const struct nfp_rtsym *sym, + u8 action, u8 token, u64 off, u64 value) +{ + u32 cpp_id; + u64 addr; + int err; + + if (off + 8 > nfp_rtsym_size(sym)) { + nfp_err(cpp, "rtsym '%s': writeq out of bounds: off: %lld + 8 > size: %lld\n", + sym->name, off, nfp_rtsym_size(sym)); + return -ENXIO; + } + + err = nfp_rtsym_to_dest(cpp, sym, action, token, off, &cpp_id, &addr); + if (err) + return err; + + return nfp_cpp_writeq(cpp, cpp_id, addr, value); +} + +int nfp_rtsym_writeq(struct nfp_cpp *cpp, const struct nfp_rtsym *sym, u64 off, + u64 value) +{ + return __nfp_rtsym_writeq(cpp, sym, NFP_CPP_ACTION_RW, 0, off, value); +} + /** * nfp_rtsym_read_le() - Read a simple unsigned scalar value from symbol * @rtbl: NFP RTsym table @@ -249,7 +474,7 @@ u64 nfp_rtsym_read_le(struct nfp_rtsym_table *rtbl, const char *name, int *error) { const struct nfp_rtsym *sym; - u32 val32, id; + u32 val32; u64 val; int err; @@ -259,20 +484,18 @@ u64 nfp_rtsym_read_le(struct nfp_rtsym_table *rtbl, const char *name, goto exit; } - id = NFP_CPP_ISLAND_ID(sym->target, NFP_CPP_ACTION_RW, 0, sym->domain); - - switch (sym->size) { + switch (nfp_rtsym_size(sym)) { case 4: - err = nfp_cpp_readl(rtbl->cpp, id, sym->addr, &val32); + err = nfp_rtsym_readl(rtbl->cpp, sym, 0, &val32); val = val32; break; case 8: - err = nfp_cpp_readq(rtbl->cpp, id, sym->addr, &val); + err = nfp_rtsym_readq(rtbl->cpp, sym, 0, &val); break; default: nfp_err(rtbl->cpp, - "rtsym '%s' unsupported or non-scalar size: %lld\n", - name, sym->size); + "rtsym '%s': unsupported or non-scalar size: %lld\n", + name, nfp_rtsym_size(sym)); err = -EINVAL; break; } @@ -303,25 +526,22 @@ int nfp_rtsym_write_le(struct nfp_rtsym_table *rtbl, const char *name, { const struct nfp_rtsym *sym; int err; - u32 id; sym = nfp_rtsym_lookup(rtbl, name); if (!sym) return -ENOENT; - id = NFP_CPP_ISLAND_ID(sym->target, NFP_CPP_ACTION_RW, 0, sym->domain); - - switch (sym->size) { + switch (nfp_rtsym_size(sym)) { case 4: - err = nfp_cpp_writel(rtbl->cpp, id, sym->addr, value); + err = nfp_rtsym_writel(rtbl->cpp, sym, 0, value); break; case 8: - err = nfp_cpp_writeq(rtbl->cpp, id, sym->addr, value); + err = nfp_rtsym_writeq(rtbl->cpp, sym, 0, value); break; default: nfp_err(rtbl->cpp, - "rtsym '%s' unsupported or non-scalar size: %lld\n", - name, sym->size); + "rtsym '%s': unsupported or non-scalar size: %lld\n", + name, nfp_rtsym_size(sym)); err = -EINVAL; break; } @@ -335,20 +555,29 @@ nfp_rtsym_map(struct nfp_rtsym_table *rtbl, const char *name, const char *id, { const struct nfp_rtsym *sym; u8 __iomem *mem; + u32 cpp_id; + u64 addr; + int err; sym = nfp_rtsym_lookup(rtbl, name); if (!sym) return (u8 __iomem *)ERR_PTR(-ENOENT); + err = nfp_rtsym_to_dest(rtbl->cpp, sym, NFP_CPP_ACTION_RW, 0, 0, + &cpp_id, &addr); + if (err) { + nfp_err(rtbl->cpp, "rtsym '%s': mapping failed\n", name); + return (u8 __iomem *)ERR_PTR(err); + } + if (sym->size < min_size) { - nfp_err(rtbl->cpp, "Symbol %s too small\n", name); + nfp_err(rtbl->cpp, "rtsym '%s': too small\n", name); return (u8 __iomem *)ERR_PTR(-EINVAL); } - mem = nfp_cpp_map_area(rtbl->cpp, id, sym->domain, sym->target, - sym->addr, sym->size, area); + mem = nfp_cpp_map_area(rtbl->cpp, id, cpp_id, addr, sym->size, area); if (IS_ERR(mem)) { - nfp_err(rtbl->cpp, "Failed to map symbol %s: %ld\n", + nfp_err(rtbl->cpp, "rtysm '%s': failed to map: %ld\n", name, PTR_ERR(mem)); return mem; } diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_target.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_target.c index 4ea1e585d945..f691c6587c76 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_target.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_target.c @@ -39,7 +39,11 @@ * Francois H. Theron <francois.theron@netronome.com> */ +#define pr_fmt(fmt) "NFP target: " fmt + #include <linux/bitops.h> +#include <linux/kernel.h> +#include <linux/printk.h> #include "nfp_cpp.h" @@ -733,8 +737,10 @@ int nfp_target_cpp(u32 cpp_island_id, u64 cpp_island_address, u32 imb; int err; - if (target < 0 || target >= 16) + if (target < 0 || target >= 16) { + pr_err("Invalid CPP target: %d\n", target); return -EINVAL; + } if (island == 0) { /* Already translated */ @@ -753,8 +759,10 @@ int nfp_target_cpp(u32 cpp_island_id, u64 cpp_island_address, err = nfp_cppat_addr_encode(cpp_target_address, island, target, ((imb >> 13) & 7), ((imb >> 12) & 1), ((imb >> 6) & 0x3f), ((imb >> 0) & 0x3f)); - if (err) + if (err) { + pr_err("Can't encode CPP address: %d\n", err); return err; + } *cpp_target_id = NFP_CPP_ID(target, NFP_CPP_ID_ACTION_of(cpp_island_id), diff --git a/drivers/net/ethernet/ni/Kconfig b/drivers/net/ethernet/ni/Kconfig index aa41e5f6e437..c73978474c4b 100644 --- a/drivers/net/ethernet/ni/Kconfig +++ b/drivers/net/ethernet/ni/Kconfig @@ -18,8 +18,9 @@ if NET_VENDOR_NI config NI_XGE_MANAGEMENT_ENET tristate "National Instruments XGE management enet support" - depends on ARCH_ZYNQ + depends on HAS_IOMEM && HAS_DMA select PHYLIB + select OF_MDIO if OF help Simple LAN device for debug or management purposes. Can support either 10G or 1G PHYs via SFP+ ports. diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c index 76efed058f33..74cf52e3fb09 100644 --- a/drivers/net/ethernet/ni/nixge.c +++ b/drivers/net/ethernet/ni/nixge.c @@ -106,10 +106,10 @@ (NIXGE_JUMBO_MTU + NIXGE_HDR_SIZE + NIXGE_TRL_SIZE) struct nixge_hw_dma_bd { - u32 next; - u32 reserved1; - u32 phys; - u32 reserved2; + u32 next_lo; + u32 next_hi; + u32 phys_lo; + u32 phys_hi; u32 reserved3; u32 reserved4; u32 cntrl; @@ -119,11 +119,39 @@ struct nixge_hw_dma_bd { u32 app2; u32 app3; u32 app4; - u32 sw_id_offset; - u32 reserved5; + u32 sw_id_offset_lo; + u32 sw_id_offset_hi; u32 reserved6; }; +#ifdef CONFIG_PHYS_ADDR_T_64BIT +#define nixge_hw_dma_bd_set_addr(bd, field, addr) \ + do { \ + (bd)->field##_lo = lower_32_bits(((u64)addr)); \ + (bd)->field##_hi = upper_32_bits(((u64)addr)); \ + } while (0) +#else +#define nixge_hw_dma_bd_set_addr(bd, field, addr) \ + ((bd)->field##_lo = lower_32_bits((addr))) +#endif + +#define nixge_hw_dma_bd_set_phys(bd, addr) \ + nixge_hw_dma_bd_set_addr((bd), phys, (addr)) + +#define nixge_hw_dma_bd_set_next(bd, addr) \ + nixge_hw_dma_bd_set_addr((bd), next, (addr)) + +#define nixge_hw_dma_bd_set_offset(bd, addr) \ + nixge_hw_dma_bd_set_addr((bd), sw_id_offset, (addr)) + +#ifdef CONFIG_PHYS_ADDR_T_64BIT +#define nixge_hw_dma_bd_get_addr(bd, field) \ + (dma_addr_t)((((u64)(bd)->field##_hi) << 32) | ((bd)->field##_lo)) +#else +#define nixge_hw_dma_bd_get_addr(bd, field) \ + (dma_addr_t)((bd)->field##_lo) +#endif + struct nixge_tx_skb { struct sk_buff *skb; dma_addr_t mapping; @@ -176,6 +204,15 @@ static void nixge_dma_write_reg(struct nixge_priv *priv, off_t offset, u32 val) writel(val, priv->dma_regs + offset); } +static void nixge_dma_write_desc_reg(struct nixge_priv *priv, off_t offset, + dma_addr_t addr) +{ + writel(lower_32_bits(addr), priv->dma_regs + offset); +#ifdef CONFIG_PHYS_ADDR_T_64BIT + writel(upper_32_bits(addr), priv->dma_regs + offset + 4); +#endif +} + static u32 nixge_dma_read_reg(const struct nixge_priv *priv, off_t offset) { return readl(priv->dma_regs + offset); @@ -202,13 +239,22 @@ static u32 nixge_ctrl_read_reg(struct nixge_priv *priv, off_t offset) static void nixge_hw_dma_bd_release(struct net_device *ndev) { struct nixge_priv *priv = netdev_priv(ndev); + dma_addr_t phys_addr; + struct sk_buff *skb; int i; for (i = 0; i < RX_BD_NUM; i++) { - dma_unmap_single(ndev->dev.parent, priv->rx_bd_v[i].phys, - NIXGE_MAX_JUMBO_FRAME_SIZE, DMA_FROM_DEVICE); - dev_kfree_skb((struct sk_buff *) - (priv->rx_bd_v[i].sw_id_offset)); + phys_addr = nixge_hw_dma_bd_get_addr(&priv->rx_bd_v[i], + phys); + + dma_unmap_single(ndev->dev.parent, phys_addr, + NIXGE_MAX_JUMBO_FRAME_SIZE, + DMA_FROM_DEVICE); + + skb = (struct sk_buff *) + nixge_hw_dma_bd_get_addr(&priv->rx_bd_v[i], + sw_id_offset); + dev_kfree_skb(skb); } if (priv->rx_bd_v) @@ -231,6 +277,7 @@ static int nixge_hw_dma_bd_init(struct net_device *ndev) { struct nixge_priv *priv = netdev_priv(ndev); struct sk_buff *skb; + dma_addr_t phys; u32 cr; int i; @@ -259,27 +306,30 @@ static int nixge_hw_dma_bd_init(struct net_device *ndev) goto out; for (i = 0; i < TX_BD_NUM; i++) { - priv->tx_bd_v[i].next = priv->tx_bd_p + - sizeof(*priv->tx_bd_v) * - ((i + 1) % TX_BD_NUM); + nixge_hw_dma_bd_set_next(&priv->tx_bd_v[i], + priv->tx_bd_p + + sizeof(*priv->tx_bd_v) * + ((i + 1) % TX_BD_NUM)); } for (i = 0; i < RX_BD_NUM; i++) { - priv->rx_bd_v[i].next = priv->rx_bd_p + - sizeof(*priv->rx_bd_v) * - ((i + 1) % RX_BD_NUM); + nixge_hw_dma_bd_set_next(&priv->rx_bd_v[i], + priv->rx_bd_p + + sizeof(*priv->rx_bd_v) * + ((i + 1) % RX_BD_NUM)); skb = netdev_alloc_skb_ip_align(ndev, NIXGE_MAX_JUMBO_FRAME_SIZE); if (!skb) goto out; - priv->rx_bd_v[i].sw_id_offset = (u32)skb; - priv->rx_bd_v[i].phys = - dma_map_single(ndev->dev.parent, - skb->data, - NIXGE_MAX_JUMBO_FRAME_SIZE, - DMA_FROM_DEVICE); + nixge_hw_dma_bd_set_offset(&priv->rx_bd_v[i], skb); + phys = dma_map_single(ndev->dev.parent, skb->data, + NIXGE_MAX_JUMBO_FRAME_SIZE, + DMA_FROM_DEVICE); + + nixge_hw_dma_bd_set_phys(&priv->rx_bd_v[i], phys); + priv->rx_bd_v[i].cntrl = NIXGE_MAX_JUMBO_FRAME_SIZE; } @@ -312,18 +362,18 @@ static int nixge_hw_dma_bd_init(struct net_device *ndev) /* Populate the tail pointer and bring the Rx Axi DMA engine out of * halted state. This will make the Rx side ready for reception. */ - nixge_dma_write_reg(priv, XAXIDMA_RX_CDESC_OFFSET, priv->rx_bd_p); + nixge_dma_write_desc_reg(priv, XAXIDMA_RX_CDESC_OFFSET, priv->rx_bd_p); cr = nixge_dma_read_reg(priv, XAXIDMA_RX_CR_OFFSET); nixge_dma_write_reg(priv, XAXIDMA_RX_CR_OFFSET, cr | XAXIDMA_CR_RUNSTOP_MASK); - nixge_dma_write_reg(priv, XAXIDMA_RX_TDESC_OFFSET, priv->rx_bd_p + + nixge_dma_write_desc_reg(priv, XAXIDMA_RX_TDESC_OFFSET, priv->rx_bd_p + (sizeof(*priv->rx_bd_v) * (RX_BD_NUM - 1))); /* Write to the RS (Run-stop) bit in the Tx channel control register. * Tx channel is now ready to run. But only after we write to the * tail pointer register that the Tx channel will start transmitting. */ - nixge_dma_write_reg(priv, XAXIDMA_TX_CDESC_OFFSET, priv->tx_bd_p); + nixge_dma_write_desc_reg(priv, XAXIDMA_TX_CDESC_OFFSET, priv->tx_bd_p); cr = nixge_dma_read_reg(priv, XAXIDMA_TX_CR_OFFSET); nixge_dma_write_reg(priv, XAXIDMA_TX_CR_OFFSET, cr | XAXIDMA_CR_RUNSTOP_MASK); @@ -451,7 +501,7 @@ static int nixge_start_xmit(struct sk_buff *skb, struct net_device *ndev) struct nixge_priv *priv = netdev_priv(ndev); struct nixge_hw_dma_bd *cur_p; struct nixge_tx_skb *tx_skb; - dma_addr_t tail_p; + dma_addr_t tail_p, cur_phys; skb_frag_t *frag; u32 num_frag; u32 ii; @@ -466,15 +516,16 @@ static int nixge_start_xmit(struct sk_buff *skb, struct net_device *ndev) return NETDEV_TX_OK; } - cur_p->phys = dma_map_single(ndev->dev.parent, skb->data, - skb_headlen(skb), DMA_TO_DEVICE); - if (dma_mapping_error(ndev->dev.parent, cur_p->phys)) + cur_phys = dma_map_single(ndev->dev.parent, skb->data, + skb_headlen(skb), DMA_TO_DEVICE); + if (dma_mapping_error(ndev->dev.parent, cur_phys)) goto drop; + nixge_hw_dma_bd_set_phys(cur_p, cur_phys); cur_p->cntrl = skb_headlen(skb) | XAXIDMA_BD_CTRL_TXSOF_MASK; tx_skb->skb = NULL; - tx_skb->mapping = cur_p->phys; + tx_skb->mapping = cur_phys; tx_skb->size = skb_headlen(skb); tx_skb->mapped_as_page = false; @@ -485,16 +536,17 @@ static int nixge_start_xmit(struct sk_buff *skb, struct net_device *ndev) tx_skb = &priv->tx_skb[priv->tx_bd_tail]; frag = &skb_shinfo(skb)->frags[ii]; - cur_p->phys = skb_frag_dma_map(ndev->dev.parent, frag, 0, - skb_frag_size(frag), - DMA_TO_DEVICE); - if (dma_mapping_error(ndev->dev.parent, cur_p->phys)) + cur_phys = skb_frag_dma_map(ndev->dev.parent, frag, 0, + skb_frag_size(frag), + DMA_TO_DEVICE); + if (dma_mapping_error(ndev->dev.parent, cur_phys)) goto frag_err; + nixge_hw_dma_bd_set_phys(cur_p, cur_phys); cur_p->cntrl = skb_frag_size(frag); tx_skb->skb = NULL; - tx_skb->mapping = cur_p->phys; + tx_skb->mapping = cur_phys; tx_skb->size = skb_frag_size(frag); tx_skb->mapped_as_page = true; } @@ -506,7 +558,7 @@ static int nixge_start_xmit(struct sk_buff *skb, struct net_device *ndev) tail_p = priv->tx_bd_p + sizeof(*priv->tx_bd_v) * priv->tx_bd_tail; /* Start the transfer */ - nixge_dma_write_reg(priv, XAXIDMA_TX_TDESC_OFFSET, tail_p); + nixge_dma_write_desc_reg(priv, XAXIDMA_TX_TDESC_OFFSET, tail_p); ++priv->tx_bd_tail; priv->tx_bd_tail %= TX_BD_NUM; @@ -537,7 +589,7 @@ static int nixge_recv(struct net_device *ndev, int budget) struct nixge_priv *priv = netdev_priv(ndev); struct sk_buff *skb, *new_skb; struct nixge_hw_dma_bd *cur_p; - dma_addr_t tail_p = 0; + dma_addr_t tail_p = 0, cur_phys = 0; u32 packets = 0; u32 length = 0; u32 size = 0; @@ -549,13 +601,15 @@ static int nixge_recv(struct net_device *ndev, int budget) tail_p = priv->rx_bd_p + sizeof(*priv->rx_bd_v) * priv->rx_bd_ci; - skb = (struct sk_buff *)(cur_p->sw_id_offset); + skb = (struct sk_buff *)nixge_hw_dma_bd_get_addr(cur_p, + sw_id_offset); length = cur_p->status & XAXIDMA_BD_STS_ACTUAL_LEN_MASK; if (length > NIXGE_MAX_JUMBO_FRAME_SIZE) length = NIXGE_MAX_JUMBO_FRAME_SIZE; - dma_unmap_single(ndev->dev.parent, cur_p->phys, + dma_unmap_single(ndev->dev.parent, + nixge_hw_dma_bd_get_addr(cur_p, phys), NIXGE_MAX_JUMBO_FRAME_SIZE, DMA_FROM_DEVICE); @@ -579,16 +633,17 @@ static int nixge_recv(struct net_device *ndev, int budget) if (!new_skb) return packets; - cur_p->phys = dma_map_single(ndev->dev.parent, new_skb->data, - NIXGE_MAX_JUMBO_FRAME_SIZE, - DMA_FROM_DEVICE); - if (dma_mapping_error(ndev->dev.parent, cur_p->phys)) { + cur_phys = dma_map_single(ndev->dev.parent, new_skb->data, + NIXGE_MAX_JUMBO_FRAME_SIZE, + DMA_FROM_DEVICE); + if (dma_mapping_error(ndev->dev.parent, cur_phys)) { /* FIXME: bail out and clean up */ netdev_err(ndev, "Failed to map ...\n"); } + nixge_hw_dma_bd_set_phys(cur_p, cur_phys); cur_p->cntrl = NIXGE_MAX_JUMBO_FRAME_SIZE; cur_p->status = 0; - cur_p->sw_id_offset = (u32)new_skb; + nixge_hw_dma_bd_set_offset(cur_p, new_skb); ++priv->rx_bd_ci; priv->rx_bd_ci %= RX_BD_NUM; @@ -599,7 +654,7 @@ static int nixge_recv(struct net_device *ndev, int budget) ndev->stats.rx_bytes += size; if (tail_p) - nixge_dma_write_reg(priv, XAXIDMA_RX_TDESC_OFFSET, tail_p); + nixge_dma_write_desc_reg(priv, XAXIDMA_RX_TDESC_OFFSET, tail_p); return packets; } @@ -637,6 +692,7 @@ static irqreturn_t nixge_tx_irq(int irq, void *_ndev) struct nixge_priv *priv = netdev_priv(_ndev); struct net_device *ndev = _ndev; unsigned int status; + dma_addr_t phys; u32 cr; status = nixge_dma_read_reg(priv, XAXIDMA_TX_SR_OFFSET); @@ -650,9 +706,11 @@ static irqreturn_t nixge_tx_irq(int irq, void *_ndev) return IRQ_NONE; } if (status & XAXIDMA_IRQ_ERROR_MASK) { + phys = nixge_hw_dma_bd_get_addr(&priv->tx_bd_v[priv->tx_bd_ci], + phys); + netdev_err(ndev, "DMA Tx error 0x%x\n", status); - netdev_err(ndev, "Current BD is at: 0x%x\n", - (priv->tx_bd_v[priv->tx_bd_ci]).phys); + netdev_err(ndev, "Current BD is at: 0x%llx\n", (u64)phys); cr = nixge_dma_read_reg(priv, XAXIDMA_TX_CR_OFFSET); /* Disable coalesce, delay timer and error interrupts */ @@ -678,6 +736,7 @@ static irqreturn_t nixge_rx_irq(int irq, void *_ndev) struct nixge_priv *priv = netdev_priv(_ndev); struct net_device *ndev = _ndev; unsigned int status; + dma_addr_t phys; u32 cr; status = nixge_dma_read_reg(priv, XAXIDMA_RX_SR_OFFSET); @@ -697,9 +756,10 @@ static irqreturn_t nixge_rx_irq(int irq, void *_ndev) return IRQ_NONE; } if (status & XAXIDMA_IRQ_ERROR_MASK) { + phys = nixge_hw_dma_bd_get_addr(&priv->rx_bd_v[priv->rx_bd_ci], + phys); netdev_err(ndev, "DMA Rx error 0x%x\n", status); - netdev_err(ndev, "Current BD is at: 0x%x\n", - (priv->rx_bd_v[priv->rx_bd_ci]).phys); + netdev_err(ndev, "Current BD is at: 0x%llx\n", (u64)phys); cr = nixge_dma_read_reg(priv, XAXIDMA_TX_CR_OFFSET); /* Disable coalesce, delay timer and error interrupts */ @@ -735,10 +795,10 @@ static void nixge_dma_err_handler(unsigned long data) tx_skb = &lp->tx_skb[i]; nixge_tx_skb_unmap(lp, tx_skb); - cur_p->phys = 0; + nixge_hw_dma_bd_set_phys(cur_p, 0); cur_p->cntrl = 0; cur_p->status = 0; - cur_p->sw_id_offset = 0; + nixge_hw_dma_bd_set_offset(cur_p, 0); } for (i = 0; i < RX_BD_NUM; i++) { @@ -779,18 +839,18 @@ static void nixge_dma_err_handler(unsigned long data) /* Populate the tail pointer and bring the Rx Axi DMA engine out of * halted state. This will make the Rx side ready for reception. */ - nixge_dma_write_reg(lp, XAXIDMA_RX_CDESC_OFFSET, lp->rx_bd_p); + nixge_dma_write_desc_reg(lp, XAXIDMA_RX_CDESC_OFFSET, lp->rx_bd_p); cr = nixge_dma_read_reg(lp, XAXIDMA_RX_CR_OFFSET); nixge_dma_write_reg(lp, XAXIDMA_RX_CR_OFFSET, cr | XAXIDMA_CR_RUNSTOP_MASK); - nixge_dma_write_reg(lp, XAXIDMA_RX_TDESC_OFFSET, lp->rx_bd_p + + nixge_dma_write_desc_reg(lp, XAXIDMA_RX_TDESC_OFFSET, lp->rx_bd_p + (sizeof(*lp->rx_bd_v) * (RX_BD_NUM - 1))); /* Write to the RS (Run-stop) bit in the Tx channel control register. * Tx channel is now ready to run. But only after we write to the * tail pointer register that the Tx channel will start transmitting */ - nixge_dma_write_reg(lp, XAXIDMA_TX_CDESC_OFFSET, lp->tx_bd_p); + nixge_dma_write_desc_reg(lp, XAXIDMA_TX_CDESC_OFFSET, lp->tx_bd_p); cr = nixge_dma_read_reg(lp, XAXIDMA_TX_CR_OFFSET); nixge_dma_write_reg(lp, XAXIDMA_TX_CR_OFFSET, cr | XAXIDMA_CR_RUNSTOP_MASK); diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c index 08381ef8bdb4..8b23d2848457 100644 --- a/drivers/net/ethernet/nxp/lpc_eth.c +++ b/drivers/net/ethernet/nxp/lpc_eth.c @@ -797,8 +797,7 @@ static int lpc_mii_probe(struct net_device *ndev) return PTR_ERR(phydev); } - /* mask with MAC supported features */ - phydev->supported &= PHY_BASIC_FEATURES; + phy_set_max_speed(phydev, SPEED_100); phydev->advertising = phydev->supported; diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h index a60e1c8d470a..5f0962d353ce 100644 --- a/drivers/net/ethernet/qlogic/qed/qed.h +++ b/drivers/net/ethernet/qlogic/qed/qed.h @@ -623,6 +623,7 @@ struct qed_hwfn { void *unzip_buf; struct dbg_tools_data dbg_info; + void *dbg_user_info; /* PWM region specific data */ u16 wid_count; diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c index f1977aa440e5..dc1c1b616084 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c +++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c @@ -40,7 +40,6 @@ #include <linux/pci.h> #include <linux/slab.h> #include <linux/string.h> -#include <linux/bitops.h> #include "qed.h" #include "qed_cxt.h" #include "qed_dev_api.h" diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c index 6bb76e6d3c14..6ce9a762cfc0 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c @@ -253,8 +253,9 @@ qed_dcbx_get_app_protocol_type(struct qed_hwfn *p_hwfn, *type = DCBX_PROTOCOL_ROCE_V2; } else { *type = DCBX_MAX_PROTOCOL_TYPE; - DP_ERR(p_hwfn, "No action required, App TLV entry = 0x%x\n", - app_prio_bitmap); + DP_VERBOSE(p_hwfn, QED_MSG_DCB, + "No action required, App TLV entry = 0x%x\n", + app_prio_bitmap); return false; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c index 1aa9fc1c5890..78a638ec7c0a 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_debug.c +++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c @@ -3454,7 +3454,8 @@ static u32 qed_grc_dump_iors(struct qed_hwfn *p_hwfn, addr = BYTES_TO_DWORDS(storm->sem_fast_mem_addr + SEM_FAST_REG_STORM_REG_FILE) + IOR_SET_OFFSET(set_id); - buf[strlen(buf) - 1] = '0' + set_id; + if (strlen(buf) > 0) + buf[strlen(buf) - 1] = '0' + set_id; offset += qed_grc_dump_mem(p_hwfn, p_ptt, dump_buf + offset, @@ -5563,35 +5564,6 @@ struct block_info { enum block_id id; }; -struct mcp_trace_format { - u32 data; -#define MCP_TRACE_FORMAT_MODULE_MASK 0x0000ffff -#define MCP_TRACE_FORMAT_MODULE_SHIFT 0 -#define MCP_TRACE_FORMAT_LEVEL_MASK 0x00030000 -#define MCP_TRACE_FORMAT_LEVEL_SHIFT 16 -#define MCP_TRACE_FORMAT_P1_SIZE_MASK 0x000c0000 -#define MCP_TRACE_FORMAT_P1_SIZE_SHIFT 18 -#define MCP_TRACE_FORMAT_P2_SIZE_MASK 0x00300000 -#define MCP_TRACE_FORMAT_P2_SIZE_SHIFT 20 -#define MCP_TRACE_FORMAT_P3_SIZE_MASK 0x00c00000 -#define MCP_TRACE_FORMAT_P3_SIZE_SHIFT 22 -#define MCP_TRACE_FORMAT_LEN_MASK 0xff000000 -#define MCP_TRACE_FORMAT_LEN_SHIFT 24 - - char *format_str; -}; - -/* Meta data structure, generated by a perl script during MFW build. therefore, - * the structs mcp_trace_meta and mcp_trace_format are duplicated in the perl - * script. - */ -struct mcp_trace_meta { - u32 modules_num; - char **modules; - u32 formats_num; - struct mcp_trace_format *formats; -}; - /* REG fifo element */ struct reg_fifo_element { u64 data; @@ -5714,6 +5686,20 @@ struct igu_fifo_addr_data { enum igu_fifo_addr_types type; }; +struct mcp_trace_meta { + u32 modules_num; + char **modules; + u32 formats_num; + struct mcp_trace_format *formats; + bool is_allocated; +}; + +/* Debug Tools user data */ +struct dbg_tools_user_data { + struct mcp_trace_meta mcp_trace_meta; + const u32 *mcp_trace_user_meta_buf; +}; + /******************************** Constants **********************************/ #define MAX_MSG_LEN 1024 @@ -6137,15 +6123,6 @@ static const struct igu_fifo_addr_data s_igu_fifo_addr_data[] = { /******************************** Variables **********************************/ -/* MCP Trace meta data array - used in case the dump doesn't contain the - * meta data (e.g. due to no NVRAM access). - */ -static struct user_dbg_array s_mcp_trace_meta_arr = { NULL, 0 }; - -/* Parsed MCP Trace meta data info, based on MCP trace meta array */ -static struct mcp_trace_meta s_mcp_trace_meta; -static bool s_mcp_trace_meta_valid; - /* Temporary buffer, used for print size calculations */ static char s_temp_buf[MAX_MSG_LEN]; @@ -6311,6 +6288,12 @@ static u32 qed_print_section_params(u32 *dump_buf, return dump_offset; } +static struct dbg_tools_user_data * +qed_dbg_get_user_data(struct qed_hwfn *p_hwfn) +{ + return (struct dbg_tools_user_data *)p_hwfn->dbg_user_info; +} + /* Parses the idle check rules and returns the number of characters printed. * In case of parsing error, returns 0. */ @@ -6570,43 +6553,26 @@ static enum dbg_status qed_parse_idle_chk_dump(u32 *dump_buf, return DBG_STATUS_OK; } -/* Frees the specified MCP Trace meta data */ -static void qed_mcp_trace_free_meta(struct qed_hwfn *p_hwfn, - struct mcp_trace_meta *meta) -{ - u32 i; - - s_mcp_trace_meta_valid = false; - - /* Release modules */ - if (meta->modules) { - for (i = 0; i < meta->modules_num; i++) - kfree(meta->modules[i]); - kfree(meta->modules); - } - - /* Release formats */ - if (meta->formats) { - for (i = 0; i < meta->formats_num; i++) - kfree(meta->formats[i].format_str); - kfree(meta->formats); - } -} - /* Allocates and fills MCP Trace meta data based on the specified meta data * dump buffer. * Returns debug status code. */ -static enum dbg_status qed_mcp_trace_alloc_meta(struct qed_hwfn *p_hwfn, - const u32 *meta_buf, - struct mcp_trace_meta *meta) +static enum dbg_status +qed_mcp_trace_alloc_meta_data(struct qed_hwfn *p_hwfn, + const u32 *meta_buf) { - u8 *meta_buf_bytes = (u8 *)meta_buf; + struct dbg_tools_user_data *dev_user_data; u32 offset = 0, signature, i; + struct mcp_trace_meta *meta; + u8 *meta_buf_bytes; + + dev_user_data = qed_dbg_get_user_data(p_hwfn); + meta = &dev_user_data->mcp_trace_meta; + meta_buf_bytes = (u8 *)meta_buf; /* Free the previous meta before loading a new one. */ - if (s_mcp_trace_meta_valid) - qed_mcp_trace_free_meta(p_hwfn, meta); + if (meta->is_allocated) + qed_mcp_trace_free_meta_data(p_hwfn); memset(meta, 0, sizeof(*meta)); @@ -6674,7 +6640,7 @@ static enum dbg_status qed_mcp_trace_alloc_meta(struct qed_hwfn *p_hwfn, format_len, format_ptr->format_str); } - s_mcp_trace_meta_valid = true; + meta->is_allocated = true; return DBG_STATUS_OK; } @@ -6687,21 +6653,26 @@ static enum dbg_status qed_mcp_trace_alloc_meta(struct qed_hwfn *p_hwfn, * buffer. * data_size - size in bytes of data to parse. * parsed_buf - destination buffer for parsed data. - * parsed_bytes - size of parsed data in bytes. + * parsed_results_bytes - size of parsed data in bytes. */ -static enum dbg_status qed_parse_mcp_trace_buf(u8 *trace_buf, +static enum dbg_status qed_parse_mcp_trace_buf(struct qed_hwfn *p_hwfn, + u8 *trace_buf, u32 trace_buf_size, u32 data_offset, u32 data_size, char *parsed_buf, - u32 *parsed_bytes) + u32 *parsed_results_bytes) { + struct dbg_tools_user_data *dev_user_data; + struct mcp_trace_meta *meta; u32 param_mask, param_shift; enum dbg_status status; - *parsed_bytes = 0; + dev_user_data = qed_dbg_get_user_data(p_hwfn); + meta = &dev_user_data->mcp_trace_meta; + *parsed_results_bytes = 0; - if (!s_mcp_trace_meta_valid) + if (!meta->is_allocated) return DBG_STATUS_MCP_TRACE_BAD_DATA; status = DBG_STATUS_OK; @@ -6723,7 +6694,7 @@ static enum dbg_status qed_parse_mcp_trace_buf(u8 *trace_buf, format_idx = header & MFW_TRACE_EVENTID_MASK; /* Skip message if its index doesn't exist in the meta data */ - if (format_idx >= s_mcp_trace_meta.formats_num) { + if (format_idx >= meta->formats_num) { u8 format_size = (u8)((header & MFW_TRACE_PRM_SIZE_MASK) >> MFW_TRACE_PRM_SIZE_SHIFT); @@ -6738,7 +6709,7 @@ static enum dbg_status qed_parse_mcp_trace_buf(u8 *trace_buf, continue; } - format_ptr = &s_mcp_trace_meta.formats[format_idx]; + format_ptr = &meta->formats[format_idx]; for (i = 0, param_mask = MCP_TRACE_FORMAT_P1_SIZE_MASK, @@ -6783,19 +6754,20 @@ static enum dbg_status qed_parse_mcp_trace_buf(u8 *trace_buf, return DBG_STATUS_MCP_TRACE_BAD_DATA; /* Print current message to results buffer */ - *parsed_bytes += - sprintf(qed_get_buf_ptr(parsed_buf, *parsed_bytes), + *parsed_results_bytes += + sprintf(qed_get_buf_ptr(parsed_buf, + *parsed_results_bytes), "%s %-8s: ", s_mcp_trace_level_str[format_level], - s_mcp_trace_meta.modules[format_module]); - *parsed_bytes += - sprintf(qed_get_buf_ptr(parsed_buf, *parsed_bytes), + meta->modules[format_module]); + *parsed_results_bytes += + sprintf(qed_get_buf_ptr(parsed_buf, *parsed_results_bytes), format_ptr->format_str, params[0], params[1], params[2]); } /* Add string NULL terminator */ - (*parsed_bytes)++; + (*parsed_results_bytes)++; return status; } @@ -6803,24 +6775,25 @@ static enum dbg_status qed_parse_mcp_trace_buf(u8 *trace_buf, /* Parses an MCP Trace dump buffer. * If result_buf is not NULL, the MCP Trace results are printed to it. * In any case, the required results buffer size is assigned to - * parsed_bytes. + * parsed_results_bytes. * The parsing status is returned. */ static enum dbg_status qed_parse_mcp_trace_dump(struct qed_hwfn *p_hwfn, u32 *dump_buf, - char *parsed_buf, - u32 *parsed_bytes) + char *results_buf, + u32 *parsed_results_bytes, + bool free_meta_data) { const char *section_name, *param_name, *param_str_val; u32 data_size, trace_data_dwords, trace_meta_dwords; - u32 offset, results_offset, parsed_buf_bytes; + u32 offset, results_offset, results_buf_bytes; u32 param_num_val, num_section_params; struct mcp_trace *trace; enum dbg_status status; const u32 *meta_buf; u8 *trace_buf; - *parsed_bytes = 0; + *parsed_results_bytes = 0; /* Read global_params section */ dump_buf += qed_read_section_hdr(dump_buf, @@ -6831,7 +6804,7 @@ static enum dbg_status qed_parse_mcp_trace_dump(struct qed_hwfn *p_hwfn, /* Print global params */ dump_buf += qed_print_section_params(dump_buf, num_section_params, - parsed_buf, &results_offset); + results_buf, &results_offset); /* Read trace_data section */ dump_buf += qed_read_section_hdr(dump_buf, @@ -6846,6 +6819,9 @@ static enum dbg_status qed_parse_mcp_trace_dump(struct qed_hwfn *p_hwfn, /* Prepare trace info */ trace = (struct mcp_trace *)dump_buf; + if (trace->signature != MFW_TRACE_SIGNATURE || !trace->size) + return DBG_STATUS_MCP_TRACE_BAD_DATA; + trace_buf = (u8 *)dump_buf + sizeof(*trace); offset = trace->trace_oldest; data_size = qed_cyclic_sub(trace->trace_prod, offset, trace->size); @@ -6865,31 +6841,39 @@ static enum dbg_status qed_parse_mcp_trace_dump(struct qed_hwfn *p_hwfn, /* Choose meta data buffer */ if (!trace_meta_dwords) { /* Dump doesn't include meta data */ - if (!s_mcp_trace_meta_arr.ptr) + struct dbg_tools_user_data *dev_user_data = + qed_dbg_get_user_data(p_hwfn); + + if (!dev_user_data->mcp_trace_user_meta_buf) return DBG_STATUS_MCP_TRACE_NO_META; - meta_buf = s_mcp_trace_meta_arr.ptr; + + meta_buf = dev_user_data->mcp_trace_user_meta_buf; } else { /* Dump includes meta data */ meta_buf = dump_buf; } /* Allocate meta data memory */ - status = qed_mcp_trace_alloc_meta(p_hwfn, meta_buf, &s_mcp_trace_meta); + status = qed_mcp_trace_alloc_meta_data(p_hwfn, meta_buf); if (status != DBG_STATUS_OK) return status; - status = qed_parse_mcp_trace_buf(trace_buf, + status = qed_parse_mcp_trace_buf(p_hwfn, + trace_buf, trace->size, offset, data_size, - parsed_buf ? - parsed_buf + results_offset : + results_buf ? + results_buf + results_offset : NULL, - &parsed_buf_bytes); + &results_buf_bytes); if (status != DBG_STATUS_OK) return status; - *parsed_bytes = results_offset + parsed_buf_bytes; + if (free_meta_data) + qed_mcp_trace_free_meta_data(p_hwfn); + + *parsed_results_bytes = results_offset + results_buf_bytes; return DBG_STATUS_OK; } @@ -7361,6 +7345,16 @@ enum dbg_status qed_dbg_user_set_bin_ptr(const u8 * const bin_ptr) return DBG_STATUS_OK; } +enum dbg_status qed_dbg_alloc_user_data(struct qed_hwfn *p_hwfn) +{ + p_hwfn->dbg_user_info = kzalloc(sizeof(struct dbg_tools_user_data), + GFP_KERNEL); + if (!p_hwfn->dbg_user_info) + return DBG_STATUS_VIRT_MEM_ALLOC_FAILED; + + return DBG_STATUS_OK; +} + const char *qed_dbg_get_status_str(enum dbg_status status) { return (status < @@ -7397,10 +7391,13 @@ enum dbg_status qed_print_idle_chk_results(struct qed_hwfn *p_hwfn, num_errors, num_warnings); } -void qed_dbg_mcp_trace_set_meta_data(u32 *data, u32 size) +void qed_dbg_mcp_trace_set_meta_data(struct qed_hwfn *p_hwfn, + const u32 *meta_buf) { - s_mcp_trace_meta_arr.ptr = data; - s_mcp_trace_meta_arr.size_in_dwords = size; + struct dbg_tools_user_data *dev_user_data = + qed_dbg_get_user_data(p_hwfn); + + dev_user_data->mcp_trace_user_meta_buf = meta_buf; } enum dbg_status qed_get_mcp_trace_results_buf_size(struct qed_hwfn *p_hwfn, @@ -7409,7 +7406,7 @@ enum dbg_status qed_get_mcp_trace_results_buf_size(struct qed_hwfn *p_hwfn, u32 *results_buf_size) { return qed_parse_mcp_trace_dump(p_hwfn, - dump_buf, NULL, results_buf_size); + dump_buf, NULL, results_buf_size, true); } enum dbg_status qed_print_mcp_trace_results(struct qed_hwfn *p_hwfn, @@ -7421,20 +7418,61 @@ enum dbg_status qed_print_mcp_trace_results(struct qed_hwfn *p_hwfn, return qed_parse_mcp_trace_dump(p_hwfn, dump_buf, - results_buf, &parsed_buf_size); + results_buf, &parsed_buf_size, true); +} + +enum dbg_status qed_print_mcp_trace_results_cont(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + char *results_buf) +{ + u32 parsed_buf_size; + + return qed_parse_mcp_trace_dump(p_hwfn, dump_buf, results_buf, + &parsed_buf_size, false); } -enum dbg_status qed_print_mcp_trace_line(u8 *dump_buf, +enum dbg_status qed_print_mcp_trace_line(struct qed_hwfn *p_hwfn, + u8 *dump_buf, u32 num_dumped_bytes, char *results_buf) { - u32 parsed_bytes; + u32 parsed_results_bytes; - return qed_parse_mcp_trace_buf(dump_buf, + return qed_parse_mcp_trace_buf(p_hwfn, + dump_buf, num_dumped_bytes, 0, num_dumped_bytes, - results_buf, &parsed_bytes); + results_buf, &parsed_results_bytes); +} + +/* Frees the specified MCP Trace meta data */ +void qed_mcp_trace_free_meta_data(struct qed_hwfn *p_hwfn) +{ + struct dbg_tools_user_data *dev_user_data; + struct mcp_trace_meta *meta; + u32 i; + + dev_user_data = qed_dbg_get_user_data(p_hwfn); + meta = &dev_user_data->mcp_trace_meta; + if (!meta->is_allocated) + return; + + /* Release modules */ + if (meta->modules) { + for (i = 0; i < meta->modules_num; i++) + kfree(meta->modules[i]); + kfree(meta->modules); + } + + /* Release formats */ + if (meta->formats) { + for (i = 0; i < meta->formats_num; i++) + kfree(meta->formats[i].format_str); + kfree(meta->formats); + } + + meta->is_allocated = false; } enum dbg_status qed_get_reg_fifo_results_buf_size(struct qed_hwfn *p_hwfn, diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index 016ca8a7ec8a..128eb63ca54a 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -144,6 +144,12 @@ static void qed_qm_info_free(struct qed_hwfn *p_hwfn) qm_info->wfq_data = NULL; } +static void qed_dbg_user_data_free(struct qed_hwfn *p_hwfn) +{ + kfree(p_hwfn->dbg_user_info); + p_hwfn->dbg_user_info = NULL; +} + void qed_resc_free(struct qed_dev *cdev) { int i; @@ -183,6 +189,7 @@ void qed_resc_free(struct qed_dev *cdev) qed_l2_free(p_hwfn); qed_dmae_info_free(p_hwfn); qed_dcbx_info_free(p_hwfn); + qed_dbg_user_data_free(p_hwfn); } } @@ -1083,6 +1090,10 @@ int qed_resc_alloc(struct qed_dev *cdev) rc = qed_dcbx_info_alloc(p_hwfn); if (rc) goto alloc_err; + + rc = qed_dbg_alloc_user_data(p_hwfn); + if (rc) + goto alloc_err; } cdev->reset_stats = kzalloc(sizeof(*cdev->reset_stats), GFP_KERNEL); diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h index 8faceb691657..21ec8091a24a 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h @@ -274,7 +274,8 @@ struct core_rx_start_ramrod_data { u8 mf_si_mcast_accept_all; struct core_rx_action_on_error action_on_error; u8 gsi_offload_flag; - u8 reserved[6]; + u8 wipe_inner_vlan_pri_en; + u8 reserved[5]; }; /* Ramrod data for rx queue stop ramrod */ @@ -351,7 +352,8 @@ struct core_tx_start_ramrod_data { __le16 pbl_size; __le16 qm_pq_id; u8 gsi_offload_flag; - u8 resrved[3]; + u8 vport_id; + u8 resrved[2]; }; /* Ramrod data for tx queue stop ramrod */ @@ -914,6 +916,16 @@ struct eth_rx_rate_limit { __le16 reserved1; }; +/* Update RSS indirection table entry command */ +struct eth_tstorm_rss_update_data { + u8 valid; + u8 vport_id; + u8 ind_table_index; + u8 reserved; + __le16 ind_table_value; + __le16 reserved1; +}; + struct eth_ustorm_per_pf_stat { struct regpair rcv_lb_ucast_bytes; struct regpair rcv_lb_mcast_bytes; @@ -1241,6 +1253,10 @@ struct rl_update_ramrod_data { u8 rl_id_first; u8 rl_id_last; u8 rl_dc_qcn_flg; + u8 dcqcn_reset_alpha_on_idle; + u8 rl_bc_stage_th; + u8 rl_timer_stage_th; + u8 reserved1; __le32 rl_bc_rate; __le16 rl_max_rate; __le16 rl_r_ai; @@ -1249,7 +1265,7 @@ struct rl_update_ramrod_data { __le32 dcqcn_k_us; __le32 dcqcn_timeuot_us; __le32 qcn_timeuot_us; - __le32 reserved[2]; + __le32 reserved2; }; /* Slowpath Element (SPQE) */ @@ -3322,6 +3338,25 @@ enum dbg_status qed_dbg_read_attn(struct qed_hwfn *p_hwfn, enum dbg_status qed_dbg_print_attn(struct qed_hwfn *p_hwfn, struct dbg_attn_block_result *results); +/******************************* Data Types **********************************/ + +struct mcp_trace_format { + u32 data; +#define MCP_TRACE_FORMAT_MODULE_MASK 0x0000ffff +#define MCP_TRACE_FORMAT_MODULE_SHIFT 0 +#define MCP_TRACE_FORMAT_LEVEL_MASK 0x00030000 +#define MCP_TRACE_FORMAT_LEVEL_SHIFT 16 +#define MCP_TRACE_FORMAT_P1_SIZE_MASK 0x000c0000 +#define MCP_TRACE_FORMAT_P1_SIZE_SHIFT 18 +#define MCP_TRACE_FORMAT_P2_SIZE_MASK 0x00300000 +#define MCP_TRACE_FORMAT_P2_SIZE_SHIFT 20 +#define MCP_TRACE_FORMAT_P3_SIZE_MASK 0x00c00000 +#define MCP_TRACE_FORMAT_P3_SIZE_SHIFT 22 +#define MCP_TRACE_FORMAT_LEN_MASK 0xff000000 +#define MCP_TRACE_FORMAT_LEN_SHIFT 24 + char *format_str; +}; + /******************************** Constants **********************************/ #define MAX_NAME_LEN 16 @@ -3337,6 +3372,13 @@ enum dbg_status qed_dbg_print_attn(struct qed_hwfn *p_hwfn, enum dbg_status qed_dbg_user_set_bin_ptr(const u8 * const bin_ptr); /** + * @brief qed_dbg_alloc_user_data - Allocates user debug data. + * + * @param p_hwfn - HW device data + */ +enum dbg_status qed_dbg_alloc_user_data(struct qed_hwfn *p_hwfn); + +/** * @brief qed_dbg_get_status_str - Returns a string for the specified status. * * @param status - a debug status code. @@ -3381,8 +3423,7 @@ enum dbg_status qed_print_idle_chk_results(struct qed_hwfn *p_hwfn, u32 *num_warnings); /** - * @brief qed_dbg_mcp_trace_set_meta_data - Sets a pointer to the MCP Trace - * meta data. + * @brief qed_dbg_mcp_trace_set_meta_data - Sets the MCP Trace meta data. * * Needed in case the MCP Trace dump doesn't contain the meta data (e.g. due to * no NVRAM access). @@ -3390,7 +3431,8 @@ enum dbg_status qed_print_idle_chk_results(struct qed_hwfn *p_hwfn, * @param data - pointer to MCP Trace meta data * @param size - size of MCP Trace meta data in dwords */ -void qed_dbg_mcp_trace_set_meta_data(u32 *data, u32 size); +void qed_dbg_mcp_trace_set_meta_data(struct qed_hwfn *p_hwfn, + const u32 *meta_buf); /** * @brief qed_get_mcp_trace_results_buf_size - Returns the required buffer size @@ -3425,19 +3467,45 @@ enum dbg_status qed_print_mcp_trace_results(struct qed_hwfn *p_hwfn, char *results_buf); /** + * @brief qed_print_mcp_trace_results_cont - Prints MCP Trace results, and + * keeps the MCP trace meta data allocated, to support continuous MCP Trace + * parsing. After the continuous parsing ends, mcp_trace_free_meta_data should + * be called to free the meta data. + * + * @param p_hwfn - HW device data + * @param dump_buf - mcp trace dump buffer, starting from the header. + * @param results_buf - buffer for printing the mcp trace results. + * + * @return error if the parsing fails, ok otherwise. + */ +enum dbg_status qed_print_mcp_trace_results_cont(struct qed_hwfn *p_hwfn, + u32 *dump_buf, + char *results_buf); + +/** * @brief print_mcp_trace_line - Prints MCP Trace results for a single line * + * @param p_hwfn - HW device data * @param dump_buf - mcp trace dump buffer, starting from the header. * @param num_dumped_bytes - number of bytes that were dumped. * @param results_buf - buffer for printing the mcp trace results. * * @return error if the parsing fails, ok otherwise. */ -enum dbg_status qed_print_mcp_trace_line(u8 *dump_buf, +enum dbg_status qed_print_mcp_trace_line(struct qed_hwfn *p_hwfn, + u8 *dump_buf, u32 num_dumped_bytes, char *results_buf); /** + * @brief mcp_trace_free_meta_data - Frees the MCP Trace meta data. + * Should be called after continuous MCP Trace parsing. + * + * @param p_hwfn - HW device data + */ +void qed_mcp_trace_free_meta_data(struct qed_hwfn *p_hwfn); + +/** * @brief qed_get_reg_fifo_results_buf_size - Returns the required buffer size * for reg_fifo results (in bytes). * @@ -4303,154 +4371,161 @@ void qed_set_rdma_error_level(struct qed_hwfn *p_hwfn, (IRO[29].base + ((pf_id) * IRO[29].m1)) #define ETH_RX_RATE_LIMIT_SIZE (IRO[29].size) +/* RSS indirection table entry update command per PF offset in TSTORM PF BAR0. + * Use eth_tstorm_rss_update_data for update. + */ +#define TSTORM_ETH_RSS_UPDATE_OFFSET(pf_id) \ + (IRO[30].base + ((pf_id) * IRO[30].m1)) +#define TSTORM_ETH_RSS_UPDATE_SIZE (IRO[30].size) + /* Xstorm queue zone */ #define XSTORM_ETH_QUEUE_ZONE_OFFSET(queue_id) \ - (IRO[30].base + ((queue_id) * IRO[30].m1)) -#define XSTORM_ETH_QUEUE_ZONE_SIZE (IRO[30].size) + (IRO[31].base + ((queue_id) * IRO[31].m1)) +#define XSTORM_ETH_QUEUE_ZONE_SIZE (IRO[31].size) /* Ystorm cqe producer */ #define YSTORM_TOE_CQ_PROD_OFFSET(rss_id) \ - (IRO[31].base + ((rss_id) * IRO[31].m1)) -#define YSTORM_TOE_CQ_PROD_SIZE (IRO[31].size) + (IRO[32].base + ((rss_id) * IRO[32].m1)) +#define YSTORM_TOE_CQ_PROD_SIZE (IRO[32].size) /* Ustorm cqe producer */ #define USTORM_TOE_CQ_PROD_OFFSET(rss_id) \ - (IRO[32].base + ((rss_id) * IRO[32].m1)) -#define USTORM_TOE_CQ_PROD_SIZE (IRO[32].size) + (IRO[33].base + ((rss_id) * IRO[33].m1)) +#define USTORM_TOE_CQ_PROD_SIZE (IRO[33].size) /* Ustorm grq producer */ #define USTORM_TOE_GRQ_PROD_OFFSET(pf_id) \ - (IRO[33].base + ((pf_id) * IRO[33].m1)) -#define USTORM_TOE_GRQ_PROD_SIZE (IRO[33].size) + (IRO[34].base + ((pf_id) * IRO[34].m1)) +#define USTORM_TOE_GRQ_PROD_SIZE (IRO[34].size) /* Tstorm cmdq-cons of given command queue-id */ #define TSTORM_SCSI_CMDQ_CONS_OFFSET(cmdq_queue_id) \ - (IRO[34].base + ((cmdq_queue_id) * IRO[34].m1)) -#define TSTORM_SCSI_CMDQ_CONS_SIZE (IRO[34].size) + (IRO[35].base + ((cmdq_queue_id) * IRO[35].m1)) +#define TSTORM_SCSI_CMDQ_CONS_SIZE (IRO[35].size) /* Tstorm (reflects M-Storm) bdq-external-producer of given function ID, * BDqueue-id. */ #define TSTORM_SCSI_BDQ_EXT_PROD_OFFSET(func_id, bdq_id) \ - (IRO[35].base + ((func_id) * IRO[35].m1) + ((bdq_id) * IRO[35].m2)) -#define TSTORM_SCSI_BDQ_EXT_PROD_SIZE (IRO[35].size) + (IRO[36].base + ((func_id) * IRO[36].m1) + ((bdq_id) * IRO[36].m2)) +#define TSTORM_SCSI_BDQ_EXT_PROD_SIZE (IRO[36].size) /* Mstorm bdq-external-producer of given BDQ resource ID, BDqueue-id */ #define MSTORM_SCSI_BDQ_EXT_PROD_OFFSET(func_id, bdq_id) \ - (IRO[36].base + ((func_id) * IRO[36].m1) + ((bdq_id) * IRO[36].m2)) -#define MSTORM_SCSI_BDQ_EXT_PROD_SIZE (IRO[36].size) + (IRO[37].base + ((func_id) * IRO[37].m1) + ((bdq_id) * IRO[37].m2)) +#define MSTORM_SCSI_BDQ_EXT_PROD_SIZE (IRO[37].size) /* Tstorm iSCSI RX stats */ #define TSTORM_ISCSI_RX_STATS_OFFSET(pf_id) \ - (IRO[37].base + ((pf_id) * IRO[37].m1)) -#define TSTORM_ISCSI_RX_STATS_SIZE (IRO[37].size) + (IRO[38].base + ((pf_id) * IRO[38].m1)) +#define TSTORM_ISCSI_RX_STATS_SIZE (IRO[38].size) /* Mstorm iSCSI RX stats */ #define MSTORM_ISCSI_RX_STATS_OFFSET(pf_id) \ - (IRO[38].base + ((pf_id) * IRO[38].m1)) -#define MSTORM_ISCSI_RX_STATS_SIZE (IRO[38].size) + (IRO[39].base + ((pf_id) * IRO[39].m1)) +#define MSTORM_ISCSI_RX_STATS_SIZE (IRO[39].size) /* Ustorm iSCSI RX stats */ #define USTORM_ISCSI_RX_STATS_OFFSET(pf_id) \ - (IRO[39].base + ((pf_id) * IRO[39].m1)) -#define USTORM_ISCSI_RX_STATS_SIZE (IRO[39].size) + (IRO[40].base + ((pf_id) * IRO[40].m1)) +#define USTORM_ISCSI_RX_STATS_SIZE (IRO[40].size) /* Xstorm iSCSI TX stats */ #define XSTORM_ISCSI_TX_STATS_OFFSET(pf_id) \ - (IRO[40].base + ((pf_id) * IRO[40].m1)) -#define XSTORM_ISCSI_TX_STATS_SIZE (IRO[40].size) + (IRO[41].base + ((pf_id) * IRO[41].m1)) +#define XSTORM_ISCSI_TX_STATS_SIZE (IRO[41].size) /* Ystorm iSCSI TX stats */ #define YSTORM_ISCSI_TX_STATS_OFFSET(pf_id) \ - (IRO[41].base + ((pf_id) * IRO[41].m1)) -#define YSTORM_ISCSI_TX_STATS_SIZE (IRO[41].size) + (IRO[42].base + ((pf_id) * IRO[42].m1)) +#define YSTORM_ISCSI_TX_STATS_SIZE (IRO[42].size) /* Pstorm iSCSI TX stats */ #define PSTORM_ISCSI_TX_STATS_OFFSET(pf_id) \ - (IRO[42].base + ((pf_id) * IRO[42].m1)) -#define PSTORM_ISCSI_TX_STATS_SIZE (IRO[42].size) + (IRO[43].base + ((pf_id) * IRO[43].m1)) +#define PSTORM_ISCSI_TX_STATS_SIZE (IRO[43].size) /* Tstorm FCoE RX stats */ #define TSTORM_FCOE_RX_STATS_OFFSET(pf_id) \ - (IRO[43].base + ((pf_id) * IRO[43].m1)) -#define TSTORM_FCOE_RX_STATS_SIZE (IRO[43].size) + (IRO[44].base + ((pf_id) * IRO[44].m1)) +#define TSTORM_FCOE_RX_STATS_SIZE (IRO[44].size) /* Pstorm FCoE TX stats */ #define PSTORM_FCOE_TX_STATS_OFFSET(pf_id) \ - (IRO[44].base + ((pf_id) * IRO[44].m1)) -#define PSTORM_FCOE_TX_STATS_SIZE (IRO[44].size) + (IRO[45].base + ((pf_id) * IRO[45].m1)) +#define PSTORM_FCOE_TX_STATS_SIZE (IRO[45].size) /* Pstorm RDMA queue statistics */ #define PSTORM_RDMA_QUEUE_STAT_OFFSET(rdma_stat_counter_id) \ - (IRO[45].base + ((rdma_stat_counter_id) * IRO[45].m1)) -#define PSTORM_RDMA_QUEUE_STAT_SIZE (IRO[45].size) + (IRO[46].base + ((rdma_stat_counter_id) * IRO[46].m1)) +#define PSTORM_RDMA_QUEUE_STAT_SIZE (IRO[46].size) /* Tstorm RDMA queue statistics */ #define TSTORM_RDMA_QUEUE_STAT_OFFSET(rdma_stat_counter_id) \ - (IRO[46].base + ((rdma_stat_counter_id) * IRO[46].m1)) -#define TSTORM_RDMA_QUEUE_STAT_SIZE (IRO[46].size) + (IRO[47].base + ((rdma_stat_counter_id) * IRO[47].m1)) +#define TSTORM_RDMA_QUEUE_STAT_SIZE (IRO[47].size) /* Xstorm error level for assert */ #define XSTORM_RDMA_ASSERT_LEVEL_OFFSET(pf_id) \ - (IRO[47].base + ((pf_id) * IRO[47].m1)) -#define XSTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[47].size) + (IRO[48].base + ((pf_id) * IRO[48].m1)) +#define XSTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[48].size) /* Ystorm error level for assert */ #define YSTORM_RDMA_ASSERT_LEVEL_OFFSET(pf_id) \ - (IRO[48].base + ((pf_id) * IRO[48].m1)) -#define YSTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[48].size) + (IRO[49].base + ((pf_id) * IRO[49].m1)) +#define YSTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[49].size) /* Pstorm error level for assert */ #define PSTORM_RDMA_ASSERT_LEVEL_OFFSET(pf_id) \ - (IRO[49].base + ((pf_id) * IRO[49].m1)) -#define PSTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[49].size) + (IRO[50].base + ((pf_id) * IRO[50].m1)) +#define PSTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[50].size) /* Tstorm error level for assert */ #define TSTORM_RDMA_ASSERT_LEVEL_OFFSET(pf_id) \ - (IRO[50].base + ((pf_id) * IRO[50].m1)) -#define TSTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[50].size) + (IRO[51].base + ((pf_id) * IRO[51].m1)) +#define TSTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[51].size) /* Mstorm error level for assert */ #define MSTORM_RDMA_ASSERT_LEVEL_OFFSET(pf_id) \ - (IRO[51].base + ((pf_id) * IRO[51].m1)) -#define MSTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[51].size) + (IRO[52].base + ((pf_id) * IRO[52].m1)) +#define MSTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[52].size) /* Ustorm error level for assert */ #define USTORM_RDMA_ASSERT_LEVEL_OFFSET(pf_id) \ - (IRO[52].base + ((pf_id) * IRO[52].m1)) -#define USTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[52].size) + (IRO[53].base + ((pf_id) * IRO[53].m1)) +#define USTORM_RDMA_ASSERT_LEVEL_SIZE (IRO[53].size) /* Xstorm iWARP rxmit stats */ #define XSTORM_IWARP_RXMIT_STATS_OFFSET(pf_id) \ - (IRO[53].base + ((pf_id) * IRO[53].m1)) -#define XSTORM_IWARP_RXMIT_STATS_SIZE (IRO[53].size) + (IRO[54].base + ((pf_id) * IRO[54].m1)) +#define XSTORM_IWARP_RXMIT_STATS_SIZE (IRO[54].size) /* Tstorm RoCE Event Statistics */ #define TSTORM_ROCE_EVENTS_STAT_OFFSET(roce_pf_id) \ - (IRO[54].base + ((roce_pf_id) * IRO[54].m1)) -#define TSTORM_ROCE_EVENTS_STAT_SIZE (IRO[54].size) + (IRO[55].base + ((roce_pf_id) * IRO[55].m1)) +#define TSTORM_ROCE_EVENTS_STAT_SIZE (IRO[55].size) /* DCQCN Received Statistics */ #define YSTORM_ROCE_DCQCN_RECEIVED_STATS_OFFSET(roce_pf_id) \ - (IRO[55].base + ((roce_pf_id) * IRO[55].m1)) -#define YSTORM_ROCE_DCQCN_RECEIVED_STATS_SIZE (IRO[55].size) + (IRO[56].base + ((roce_pf_id) * IRO[56].m1)) +#define YSTORM_ROCE_DCQCN_RECEIVED_STATS_SIZE (IRO[56].size) /* RoCE Error Statistics */ #define YSTORM_ROCE_ERROR_STATS_OFFSET(roce_pf_id) \ - (IRO[56].base + ((roce_pf_id) * IRO[56].m1)) -#define YSTORM_ROCE_ERROR_STATS_SIZE (IRO[56].size) + (IRO[57].base + ((roce_pf_id) * IRO[57].m1)) +#define YSTORM_ROCE_ERROR_STATS_SIZE (IRO[57].size) /* DCQCN Sent Statistics */ #define PSTORM_ROCE_DCQCN_SENT_STATS_OFFSET(roce_pf_id) \ - (IRO[57].base + ((roce_pf_id) * IRO[57].m1)) -#define PSTORM_ROCE_DCQCN_SENT_STATS_SIZE (IRO[57].size) + (IRO[58].base + ((roce_pf_id) * IRO[58].m1)) +#define PSTORM_ROCE_DCQCN_SENT_STATS_SIZE (IRO[58].size) /* RoCE CQEs Statistics */ #define USTORM_ROCE_CQE_STATS_OFFSET(roce_pf_id) \ - (IRO[58].base + ((roce_pf_id) * IRO[58].m1)) -#define USTORM_ROCE_CQE_STATS_SIZE (IRO[58].size) + (IRO[59].base + ((roce_pf_id) * IRO[59].m1)) +#define USTORM_ROCE_CQE_STATS_SIZE (IRO[59].size) -static const struct iro iro_arr[59] = { +static const struct iro iro_arr[60] = { {0x0, 0x0, 0x0, 0x0, 0x8}, {0x4cb8, 0x88, 0x0, 0x0, 0x88}, {0x6530, 0x20, 0x0, 0x0, 0x20}, @@ -4461,14 +4536,14 @@ static const struct iro iro_arr[59] = { {0x84, 0x8, 0x0, 0x0, 0x2}, {0x4c48, 0x0, 0x0, 0x0, 0x78}, {0x3e38, 0x0, 0x0, 0x0, 0x78}, - {0x2b78, 0x0, 0x0, 0x0, 0x78}, + {0x3ef8, 0x0, 0x0, 0x0, 0x78}, {0x4c40, 0x0, 0x0, 0x0, 0x78}, {0x4998, 0x0, 0x0, 0x0, 0x78}, {0x7f50, 0x0, 0x0, 0x0, 0x78}, {0xa28, 0x8, 0x0, 0x0, 0x8}, {0x6210, 0x10, 0x0, 0x0, 0x10}, {0xb820, 0x30, 0x0, 0x0, 0x30}, - {0x96c0, 0x30, 0x0, 0x0, 0x30}, + {0xa990, 0x30, 0x0, 0x0, 0x30}, {0x4b68, 0x80, 0x0, 0x0, 0x40}, {0x1f8, 0x4, 0x0, 0x0, 0x4}, {0x53a8, 0x80, 0x4, 0x0, 0x4}, @@ -4476,11 +4551,12 @@ static const struct iro iro_arr[59] = { {0x4ba8, 0x80, 0x0, 0x0, 0x20}, {0x8158, 0x40, 0x0, 0x0, 0x30}, {0xe770, 0x60, 0x0, 0x0, 0x60}, - {0x2d10, 0x80, 0x0, 0x0, 0x38}, - {0xf2b8, 0x78, 0x0, 0x0, 0x78}, + {0x4090, 0x80, 0x0, 0x0, 0x38}, + {0xfea8, 0x78, 0x0, 0x0, 0x78}, {0x1f8, 0x4, 0x0, 0x0, 0x4}, {0xaf20, 0x0, 0x0, 0x0, 0xf0}, {0xb010, 0x8, 0x0, 0x0, 0x8}, + {0xc00, 0x8, 0x0, 0x0, 0x8}, {0x1f8, 0x8, 0x0, 0x0, 0x8}, {0xac0, 0x8, 0x0, 0x0, 0x8}, {0x2578, 0x8, 0x0, 0x0, 0x8}, @@ -4492,23 +4568,23 @@ static const struct iro iro_arr[59] = { {0x12908, 0x18, 0x0, 0x0, 0x10}, {0x11aa8, 0x40, 0x0, 0x0, 0x18}, {0xa588, 0x50, 0x0, 0x0, 0x20}, - {0x8700, 0x40, 0x0, 0x0, 0x28}, - {0x10300, 0x18, 0x0, 0x0, 0x10}, + {0x8f00, 0x40, 0x0, 0x0, 0x28}, + {0x10e30, 0x18, 0x0, 0x0, 0x10}, {0xde48, 0x48, 0x0, 0x0, 0x38}, - {0x10768, 0x20, 0x0, 0x0, 0x20}, - {0x2d48, 0x80, 0x0, 0x0, 0x10}, + {0x11298, 0x20, 0x0, 0x0, 0x20}, + {0x40c8, 0x80, 0x0, 0x0, 0x10}, {0x5048, 0x10, 0x0, 0x0, 0x10}, {0xc748, 0x8, 0x0, 0x0, 0x1}, - {0xa128, 0x8, 0x0, 0x0, 0x1}, - {0x10f00, 0x8, 0x0, 0x0, 0x1}, + {0xa928, 0x8, 0x0, 0x0, 0x1}, + {0x11a30, 0x8, 0x0, 0x0, 0x1}, {0xf030, 0x8, 0x0, 0x0, 0x1}, {0x13028, 0x8, 0x0, 0x0, 0x1}, {0x12c58, 0x8, 0x0, 0x0, 0x1}, {0xc9b8, 0x30, 0x0, 0x0, 0x10}, {0xed90, 0x28, 0x0, 0x0, 0x28}, - {0xa520, 0x18, 0x0, 0x0, 0x18}, - {0xa6a0, 0x8, 0x0, 0x0, 0x8}, - {0x13108, 0x8, 0x0, 0x0, 0x8}, + {0xad20, 0x18, 0x0, 0x0, 0x18}, + {0xaea0, 0x8, 0x0, 0x0, 0x8}, + {0x13c38, 0x8, 0x0, 0x0, 0x8}, {0x13c50, 0x18, 0x0, 0x0, 0x18}, }; @@ -5661,6 +5737,14 @@ enum eth_filter_type { MAX_ETH_FILTER_TYPE }; +/* inner to inner vlan priority translation configurations */ +struct eth_in_to_in_pri_map_cfg { + u8 inner_vlan_pri_remap_en; + u8 reserved[7]; + u8 non_rdma_in_to_in_pri_map[8]; + u8 rdma_in_to_in_pri_map[8]; +}; + /* Eth IPv4 Fragment Type */ enum eth_ipv4_frag_type { ETH_IPV4_NOT_FRAG, @@ -6018,6 +6102,14 @@ struct tx_queue_update_ramrod_data { struct regpair reserved1[5]; }; +/* Inner to Inner VLAN priority map update mode */ +enum update_in_to_in_pri_map_mode_enum { + ETH_IN_TO_IN_PRI_MAP_UPDATE_DISABLED, + ETH_IN_TO_IN_PRI_MAP_UPDATE_NON_RDMA_TBL, + ETH_IN_TO_IN_PRI_MAP_UPDATE_RDMA_TBL, + MAX_UPDATE_IN_TO_IN_PRI_MAP_MODE_ENUM +}; + /* Ramrod data for vport update ramrod */ struct vport_filter_update_ramrod_data { struct eth_filter_cmd_header filter_cmd_hdr; @@ -6048,7 +6140,8 @@ struct vport_start_ramrod_data { u8 zero_placement_offset; u8 ctl_frame_mac_check_en; u8 ctl_frame_ethtype_check_en; - u8 reserved[1]; + u8 wipe_inner_vlan_pri_en; + struct eth_in_to_in_pri_map_cfg in_to_in_vlan_pri_map_cfg; }; /* Ramrod data for vport stop ramrod */ @@ -6100,7 +6193,9 @@ struct vport_update_ramrod_data_cmn { u8 update_ctl_frame_checks_en_flg; u8 ctl_frame_mac_check_en; u8 ctl_frame_ethtype_check_en; - u8 reserved[15]; + u8 update_in_to_in_pri_map_mode; + u8 in_to_in_pri_map[8]; + u8 reserved[6]; }; struct vport_update_ramrod_mcast { @@ -6929,11 +7024,6 @@ struct mstorm_rdma_task_st_ctx { struct regpair temp[4]; }; -/* The roce task context of Ustorm */ -struct ustorm_rdma_task_st_ctx { - struct regpair temp[2]; -}; - struct e4_ustorm_rdma_task_ag_ctx { u8 reserved; u8 state; @@ -7007,8 +7097,6 @@ struct e4_rdma_task_context { struct e4_mstorm_rdma_task_ag_ctx mstorm_ag_context; struct mstorm_rdma_task_st_ctx mstorm_st_context; struct rdif_task_context rdif_context; - struct ustorm_rdma_task_st_ctx ustorm_st_context; - struct regpair ustorm_st_padding[2]; struct e4_ustorm_rdma_task_ag_ctx ustorm_ag_context; }; @@ -7388,7 +7476,7 @@ struct e4_ustorm_rdma_conn_ag_ctx { #define E4_USTORM_RDMA_CONN_AG_CTX_RULE8EN_MASK 0x1 #define E4_USTORM_RDMA_CONN_AG_CTX_RULE8EN_SHIFT 7 u8 byte2; - u8 byte3; + u8 nvmf_only; __le16 conn_dpi; __le16 word1; __le32 cq_cons; @@ -7831,7 +7919,12 @@ struct roce_create_qp_req_ramrod_data { struct regpair qp_handle_for_cqe; struct regpair qp_handle_for_async; u8 stats_counter_id; - u8 reserved3[7]; + u8 reserved3[6]; + u8 flags2; +#define ROCE_CREATE_QP_REQ_RAMROD_DATA_EDPM_MODE_MASK 0x1 +#define ROCE_CREATE_QP_REQ_RAMROD_DATA_EDPM_MODE_SHIFT 0 +#define ROCE_CREATE_QP_REQ_RAMROD_DATA_RESERVED_MASK 0x7F +#define ROCE_CREATE_QP_REQ_RAMROD_DATA_RESERVED_SHIFT 1 __le16 regular_latency_phy_queue; __le16 dpi; }; @@ -7954,6 +8047,7 @@ enum roce_event_opcode { ROCE_EVENT_DESTROY_QP, ROCE_EVENT_CREATE_UD_QP, ROCE_EVENT_DESTROY_UD_QP, + ROCE_EVENT_FUNC_UPDATE, MAX_ROCE_EVENT_OPCODE }; @@ -7962,7 +8056,13 @@ struct roce_init_func_params { u8 ll2_queue_id; u8 cnp_vlan_priority; u8 cnp_dscp; - u8 reserved; + u8 flags; +#define ROCE_INIT_FUNC_PARAMS_DCQCN_NP_EN_MASK 0x1 +#define ROCE_INIT_FUNC_PARAMS_DCQCN_NP_EN_SHIFT 0 +#define ROCE_INIT_FUNC_PARAMS_DCQCN_RP_EN_MASK 0x1 +#define ROCE_INIT_FUNC_PARAMS_DCQCN_RP_EN_SHIFT 1 +#define ROCE_INIT_FUNC_PARAMS_RESERVED0_MASK 0x3F +#define ROCE_INIT_FUNC_PARAMS_RESERVED0_SHIFT 2 __le32 cnp_send_timeout; __le16 rl_offset; u8 rl_count_log; @@ -8109,9 +8209,24 @@ enum roce_ramrod_cmd_id { ROCE_RAMROD_DESTROY_QP, ROCE_RAMROD_CREATE_UD_QP, ROCE_RAMROD_DESTROY_UD_QP, + ROCE_RAMROD_FUNC_UPDATE, MAX_ROCE_RAMROD_CMD_ID }; +/* RoCE func init ramrod data */ +struct roce_update_func_params { + u8 cnp_vlan_priority; + u8 cnp_dscp; + __le16 flags; +#define ROCE_UPDATE_FUNC_PARAMS_DCQCN_NP_EN_MASK 0x1 +#define ROCE_UPDATE_FUNC_PARAMS_DCQCN_NP_EN_SHIFT 0 +#define ROCE_UPDATE_FUNC_PARAMS_DCQCN_RP_EN_MASK 0x1 +#define ROCE_UPDATE_FUNC_PARAMS_DCQCN_RP_EN_SHIFT 1 +#define ROCE_UPDATE_FUNC_PARAMS_RESERVED0_MASK 0x3FFF +#define ROCE_UPDATE_FUNC_PARAMS_RESERVED0_SHIFT 2 + __le32 cnp_send_timeout; +}; + struct e4_xstorm_roce_conn_ag_ctx_dq_ext_ld_part { u8 reserved0; u8 state; diff --git a/drivers/net/ethernet/qlogic/qed/qed_init_ops.c b/drivers/net/ethernet/qlogic/qed/qed_init_ops.c index d9ab5add27a8..34193c2f1699 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_init_ops.c +++ b/drivers/net/ethernet/qlogic/qed/qed_init_ops.c @@ -407,7 +407,7 @@ static void qed_init_cmd_rd(struct qed_hwfn *p_hwfn, if (i == QED_INIT_MAX_POLL_COUNT) { DP_ERR(p_hwfn, - "Timeout when polling reg: 0x%08x [ Waiting-for: %08x Got: %08x (comparsion %08x)]\n", + "Timeout when polling reg: 0x%08x [ Waiting-for: %08x Got: %08x (comparison %08x)]\n", addr, le32_to_cpu(cmd->expected_val), val, le32_to_cpu(cmd->op_data)); } diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index d89a0e22f6e4..5d37ec7e9b0b 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -48,7 +48,7 @@ #include "qed_reg_addr.h" #include "qed_sriov.h" -#define CHIP_MCP_RESP_ITER_US 10 +#define QED_MCP_RESP_ITER_US 10 #define QED_DRV_MB_MAX_RETRIES (500 * 1000) /* Account for 5 sec */ #define QED_MCP_RESET_RETRIES (50 * 1000) /* Account for 500 msec */ @@ -183,18 +183,57 @@ int qed_mcp_free(struct qed_hwfn *p_hwfn) return 0; } +/* Maximum of 1 sec to wait for the SHMEM ready indication */ +#define QED_MCP_SHMEM_RDY_MAX_RETRIES 20 +#define QED_MCP_SHMEM_RDY_ITER_MS 50 + static int qed_load_mcp_offsets(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) { struct qed_mcp_info *p_info = p_hwfn->mcp_info; + u8 cnt = QED_MCP_SHMEM_RDY_MAX_RETRIES; + u8 msec = QED_MCP_SHMEM_RDY_ITER_MS; u32 drv_mb_offsize, mfw_mb_offsize; u32 mcp_pf_id = MCP_PF_ID(p_hwfn); p_info->public_base = qed_rd(p_hwfn, p_ptt, MISC_REG_SHARED_MEM_ADDR); - if (!p_info->public_base) - return 0; + if (!p_info->public_base) { + DP_NOTICE(p_hwfn, + "The address of the MCP scratch-pad is not configured\n"); + return -EINVAL; + } p_info->public_base |= GRCBASE_MCP; + /* Get the MFW MB address and number of supported messages */ + mfw_mb_offsize = qed_rd(p_hwfn, p_ptt, + SECTION_OFFSIZE_ADDR(p_info->public_base, + PUBLIC_MFW_MB)); + p_info->mfw_mb_addr = SECTION_ADDR(mfw_mb_offsize, mcp_pf_id); + p_info->mfw_mb_length = (u16)qed_rd(p_hwfn, p_ptt, + p_info->mfw_mb_addr + + offsetof(struct public_mfw_mb, + sup_msgs)); + + /* The driver can notify that there was an MCP reset, and might read the + * SHMEM values before the MFW has completed initializing them. + * To avoid this, the "sup_msgs" field in the MFW mailbox is used as a + * data ready indication. + */ + while (!p_info->mfw_mb_length && --cnt) { + msleep(msec); + p_info->mfw_mb_length = + (u16)qed_rd(p_hwfn, p_ptt, + p_info->mfw_mb_addr + + offsetof(struct public_mfw_mb, sup_msgs)); + } + + if (!cnt) { + DP_NOTICE(p_hwfn, + "Failed to get the SHMEM ready notification after %d msec\n", + QED_MCP_SHMEM_RDY_MAX_RETRIES * msec); + return -EBUSY; + } + /* Calculate the driver and MFW mailbox address */ drv_mb_offsize = qed_rd(p_hwfn, p_ptt, SECTION_OFFSIZE_ADDR(p_info->public_base, @@ -204,13 +243,6 @@ static int qed_load_mcp_offsets(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) "drv_mb_offsiz = 0x%x, drv_mb_addr = 0x%x mcp_pf_id = 0x%x\n", drv_mb_offsize, p_info->drv_mb_addr, mcp_pf_id); - /* Set the MFW MB address */ - mfw_mb_offsize = qed_rd(p_hwfn, p_ptt, - SECTION_OFFSIZE_ADDR(p_info->public_base, - PUBLIC_MFW_MB)); - p_info->mfw_mb_addr = SECTION_ADDR(mfw_mb_offsize, mcp_pf_id); - p_info->mfw_mb_length = (u16)qed_rd(p_hwfn, p_ptt, p_info->mfw_mb_addr); - /* Get the current driver mailbox sequence before sending * the first command */ @@ -285,9 +317,15 @@ static void qed_mcp_reread_offsets(struct qed_hwfn *p_hwfn, int qed_mcp_reset(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) { - u32 org_mcp_reset_seq, seq, delay = CHIP_MCP_RESP_ITER_US, cnt = 0; + u32 org_mcp_reset_seq, seq, delay = QED_MCP_RESP_ITER_US, cnt = 0; int rc = 0; + if (p_hwfn->mcp_info->b_block_cmd) { + DP_NOTICE(p_hwfn, + "The MFW is not responsive. Avoid sending MCP_RESET mailbox command.\n"); + return -EBUSY; + } + /* Ensure that only a single thread is accessing the mailbox */ spin_lock_bh(&p_hwfn->mcp_info->cmd_lock); @@ -413,14 +451,41 @@ static void __qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn, (p_mb_params->cmd | seq_num), p_mb_params->param); } +static void qed_mcp_cmd_set_blocking(struct qed_hwfn *p_hwfn, bool block_cmd) +{ + p_hwfn->mcp_info->b_block_cmd = block_cmd; + + DP_INFO(p_hwfn, "%s sending of mailbox commands to the MFW\n", + block_cmd ? "Block" : "Unblock"); +} + +static void qed_mcp_print_cpu_info(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt) +{ + u32 cpu_mode, cpu_state, cpu_pc_0, cpu_pc_1, cpu_pc_2; + u32 delay = QED_MCP_RESP_ITER_US; + + cpu_mode = qed_rd(p_hwfn, p_ptt, MCP_REG_CPU_MODE); + cpu_state = qed_rd(p_hwfn, p_ptt, MCP_REG_CPU_STATE); + cpu_pc_0 = qed_rd(p_hwfn, p_ptt, MCP_REG_CPU_PROGRAM_COUNTER); + udelay(delay); + cpu_pc_1 = qed_rd(p_hwfn, p_ptt, MCP_REG_CPU_PROGRAM_COUNTER); + udelay(delay); + cpu_pc_2 = qed_rd(p_hwfn, p_ptt, MCP_REG_CPU_PROGRAM_COUNTER); + + DP_NOTICE(p_hwfn, + "MCP CPU info: mode 0x%08x, state 0x%08x, pc {0x%08x, 0x%08x, 0x%08x}\n", + cpu_mode, cpu_state, cpu_pc_0, cpu_pc_1, cpu_pc_2); +} + static int _qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, struct qed_mcp_mb_params *p_mb_params, - u32 max_retries, u32 delay) + u32 max_retries, u32 usecs) { + u32 cnt = 0, msecs = DIV_ROUND_UP(usecs, 1000); struct qed_mcp_cmd_elem *p_cmd_elem; - u32 cnt = 0; u16 seq_num; int rc = 0; @@ -443,7 +508,11 @@ _qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn, goto err; spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock); - udelay(delay); + + if (QED_MB_FLAGS_IS_SET(p_mb_params, CAN_SLEEP)) + msleep(msecs); + else + udelay(usecs); } while (++cnt < max_retries); if (cnt >= max_retries) { @@ -472,7 +541,11 @@ _qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn, * The spinlock stays locked until the list element is removed. */ - udelay(delay); + if (QED_MB_FLAGS_IS_SET(p_mb_params, CAN_SLEEP)) + msleep(msecs); + else + udelay(usecs); + spin_lock_bh(&p_hwfn->mcp_info->cmd_lock); if (p_cmd_elem->b_is_completed) @@ -491,11 +564,15 @@ _qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn, DP_NOTICE(p_hwfn, "The MFW failed to respond to command 0x%08x [param 0x%08x].\n", p_mb_params->cmd, p_mb_params->param); + qed_mcp_print_cpu_info(p_hwfn, p_ptt); spin_lock_bh(&p_hwfn->mcp_info->cmd_lock); qed_mcp_cmd_del_elem(p_hwfn, p_cmd_elem); spin_unlock_bh(&p_hwfn->mcp_info->cmd_lock); + if (!QED_MB_FLAGS_IS_SET(p_mb_params, AVOID_BLOCK)) + qed_mcp_cmd_set_blocking(p_hwfn, true); + return -EAGAIN; } @@ -507,7 +584,7 @@ _qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn, "MFW mailbox: response 0x%08x param 0x%08x [after %d.%03d ms]\n", p_mb_params->mcp_resp, p_mb_params->mcp_param, - (cnt * delay) / 1000, (cnt * delay) % 1000); + (cnt * usecs) / 1000, (cnt * usecs) % 1000); /* Clear the sequence number from the MFW response */ p_mb_params->mcp_resp &= FW_MSG_CODE_MASK; @@ -525,7 +602,7 @@ static int qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn, { size_t union_data_size = sizeof(union drv_union_data); u32 max_retries = QED_DRV_MB_MAX_RETRIES; - u32 delay = CHIP_MCP_RESP_ITER_US; + u32 usecs = QED_MCP_RESP_ITER_US; /* MCP not initialized */ if (!qed_mcp_is_init(p_hwfn)) { @@ -533,6 +610,13 @@ static int qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn, return -EBUSY; } + if (p_hwfn->mcp_info->b_block_cmd) { + DP_NOTICE(p_hwfn, + "The MFW is not responsive. Avoid sending mailbox command 0x%08x [param 0x%08x].\n", + p_mb_params->cmd, p_mb_params->param); + return -EBUSY; + } + if (p_mb_params->data_src_size > union_data_size || p_mb_params->data_dst_size > union_data_size) { DP_ERR(p_hwfn, @@ -542,8 +626,13 @@ static int qed_mcp_cmd_and_union(struct qed_hwfn *p_hwfn, return -EINVAL; } + if (QED_MB_FLAGS_IS_SET(p_mb_params, CAN_SLEEP)) { + max_retries = DIV_ROUND_UP(max_retries, 1000); + usecs *= 1000; + } + return _qed_mcp_cmd_and_union(p_hwfn, p_ptt, p_mb_params, max_retries, - delay); + usecs); } int qed_mcp_cmd(struct qed_hwfn *p_hwfn, @@ -761,6 +850,7 @@ __qed_mcp_load_req(struct qed_hwfn *p_hwfn, mb_params.data_src_size = sizeof(load_req); mb_params.p_data_dst = &load_rsp; mb_params.data_dst_size = sizeof(load_rsp); + mb_params.flags = QED_MB_FLAG_CAN_SLEEP | QED_MB_FLAG_AVOID_BLOCK; DP_VERBOSE(p_hwfn, QED_MSG_SP, "Load Request: param 0x%08x [init_hw %d, drv_type %d, hsi_ver %d, pda 0x%04x]\n", @@ -982,7 +1072,8 @@ int qed_mcp_load_req(struct qed_hwfn *p_hwfn, int qed_mcp_unload_req(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) { - u32 wol_param, mcp_resp, mcp_param; + struct qed_mcp_mb_params mb_params; + u32 wol_param; switch (p_hwfn->cdev->wol_config) { case QED_OV_WOL_DISABLED: @@ -1000,8 +1091,12 @@ int qed_mcp_unload_req(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) wol_param = DRV_MB_PARAM_UNLOAD_WOL_MCP; } - return qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_UNLOAD_REQ, wol_param, - &mcp_resp, &mcp_param); + memset(&mb_params, 0, sizeof(mb_params)); + mb_params.cmd = DRV_MSG_CODE_UNLOAD_REQ; + mb_params.param = wol_param; + mb_params.flags = QED_MB_FLAG_CAN_SLEEP | QED_MB_FLAG_AVOID_BLOCK; + + return qed_mcp_cmd_and_union(p_hwfn, p_ptt, &mb_params); } int qed_mcp_unload_done(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) @@ -2077,31 +2172,65 @@ qed_mcp_send_drv_version(struct qed_hwfn *p_hwfn, return rc; } +/* A maximal 100 msec waiting time for the MCP to halt */ +#define QED_MCP_HALT_SLEEP_MS 10 +#define QED_MCP_HALT_MAX_RETRIES 10 + int qed_mcp_halt(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) { - u32 resp = 0, param = 0; + u32 resp = 0, param = 0, cpu_state, cnt = 0; int rc; rc = qed_mcp_cmd(p_hwfn, p_ptt, DRV_MSG_CODE_MCP_HALT, 0, &resp, ¶m); - if (rc) + if (rc) { DP_ERR(p_hwfn, "MCP response failure, aborting\n"); + return rc; + } - return rc; + do { + msleep(QED_MCP_HALT_SLEEP_MS); + cpu_state = qed_rd(p_hwfn, p_ptt, MCP_REG_CPU_STATE); + if (cpu_state & MCP_REG_CPU_STATE_SOFT_HALTED) + break; + } while (++cnt < QED_MCP_HALT_MAX_RETRIES); + + if (cnt == QED_MCP_HALT_MAX_RETRIES) { + DP_NOTICE(p_hwfn, + "Failed to halt the MCP [CPU_MODE = 0x%08x, CPU_STATE = 0x%08x]\n", + qed_rd(p_hwfn, p_ptt, MCP_REG_CPU_MODE), cpu_state); + return -EBUSY; + } + + qed_mcp_cmd_set_blocking(p_hwfn, true); + + return 0; } +#define QED_MCP_RESUME_SLEEP_MS 10 + int qed_mcp_resume(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) { - u32 value, cpu_mode; + u32 cpu_mode, cpu_state; qed_wr(p_hwfn, p_ptt, MCP_REG_CPU_STATE, 0xffffffff); - value = qed_rd(p_hwfn, p_ptt, MCP_REG_CPU_MODE); - value &= ~MCP_REG_CPU_MODE_SOFT_HALT; - qed_wr(p_hwfn, p_ptt, MCP_REG_CPU_MODE, value); cpu_mode = qed_rd(p_hwfn, p_ptt, MCP_REG_CPU_MODE); + cpu_mode &= ~MCP_REG_CPU_MODE_SOFT_HALT; + qed_wr(p_hwfn, p_ptt, MCP_REG_CPU_MODE, cpu_mode); + msleep(QED_MCP_RESUME_SLEEP_MS); + cpu_state = qed_rd(p_hwfn, p_ptt, MCP_REG_CPU_STATE); - return (cpu_mode & MCP_REG_CPU_MODE_SOFT_HALT) ? -EAGAIN : 0; + if (cpu_state & MCP_REG_CPU_STATE_SOFT_HALTED) { + DP_NOTICE(p_hwfn, + "Failed to resume the MCP [CPU_MODE = 0x%08x, CPU_STATE = 0x%08x]\n", + cpu_mode, cpu_state); + return -EBUSY; + } + + qed_mcp_cmd_set_blocking(p_hwfn, false); + + return 0; } int qed_mcp_ov_update_current_config(struct qed_hwfn *p_hwfn, diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h index 047976d5c6e9..85e6b3989e7a 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h @@ -635,11 +635,14 @@ struct qed_mcp_info { */ spinlock_t cmd_lock; + /* Flag to indicate whether sending a MFW mailbox command is blocked */ + bool b_block_cmd; + /* Spinlock used for syncing SW link-changes and link-changes * originating from attention context. */ spinlock_t link_lock; - bool block_mb_sending; + u32 public_base; u32 drv_mb_addr; u32 mfw_mb_addr; @@ -660,14 +663,20 @@ struct qed_mcp_info { }; struct qed_mcp_mb_params { - u32 cmd; - u32 param; - void *p_data_src; - u8 data_src_size; - void *p_data_dst; - u8 data_dst_size; - u32 mcp_resp; - u32 mcp_param; + u32 cmd; + u32 param; + void *p_data_src; + void *p_data_dst; + u8 data_src_size; + u8 data_dst_size; + u32 mcp_resp; + u32 mcp_param; + u32 flags; +#define QED_MB_FLAG_CAN_SLEEP (0x1 << 0) +#define QED_MB_FLAG_AVOID_BLOCK (0x1 << 1) +#define QED_MB_FLAGS_IS_SET(params, flag) \ + ({ typeof(params) __params = (params); \ + (__params && (__params->flags & QED_MB_FLAG_ ## flag)); }) }; struct qed_drv_tlv_hdr { diff --git a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h index d8ad2dcad8d5..f736f70956fd 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h +++ b/drivers/net/ethernet/qlogic/qed/qed_reg_addr.h @@ -562,8 +562,10 @@ 0 #define MCP_REG_CPU_STATE \ 0xe05004UL +#define MCP_REG_CPU_STATE_SOFT_HALTED (0x1UL << 10) #define MCP_REG_CPU_EVENT_MASK \ 0xe05008UL +#define MCP_REG_CPU_PROGRAM_COUNTER 0xe0501cUL #define PGLUE_B_REG_PF_BAR0_SIZE \ 0x2aae60UL #define PGLUE_B_REG_PF_BAR1_SIZE \ diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c index 9673d19308e6..b16ce7d93caf 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_filter.c +++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c @@ -2006,18 +2006,16 @@ unlock: static int qede_parse_actions(struct qede_dev *edev, struct tcf_exts *exts) { - int rc = -EINVAL, num_act = 0; + int rc = -EINVAL, num_act = 0, i; const struct tc_action *a; bool is_drop = false; - LIST_HEAD(actions); if (!tcf_exts_has_actions(exts)) { DP_NOTICE(edev, "No tc actions received\n"); return rc; } - tcf_exts_to_list(exts, &actions); - list_for_each_entry(a, &actions, list) { + tcf_exts_for_each_action(i, a, exts) { num_act++; if (is_tcf_gact_shot(a)) diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c index 77e386ebff09..f7c2f32237cb 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c @@ -904,13 +904,11 @@ static void qlcnic_sriov_pull_bc_msg(struct qlcnic_adapter *adapter, u32 *hdr, u32 *pay, u32 size) { struct qlcnic_hardware_context *ahw = adapter->ahw; - u32 fw_mbx; u8 i, max = 2, hdr_size, j; hdr_size = (sizeof(struct qlcnic_bc_hdr) / sizeof(u32)); max = (size / sizeof(u32)) + hdr_size; - fw_mbx = readl(QLCNIC_MBX_FW(ahw, 0)); for (i = 2, j = 0; j < hdr_size; i++, j++) *(hdr++) = readl(QLCNIC_MBX_FW(ahw, i)); for (; j < max; i++, j++) @@ -936,7 +934,7 @@ static int __qlcnic_sriov_issue_bc_post(struct qlcnic_vf_info *vf) static int qlcnic_sriov_issue_bc_post(struct qlcnic_bc_trans *trans, u8 type) { struct qlcnic_vf_info *vf = trans->vf; - u32 pay_size, hdr_size; + u32 pay_size; u32 *hdr, *pay; int ret; u8 pci_func = trans->func_id; @@ -947,14 +945,12 @@ static int qlcnic_sriov_issue_bc_post(struct qlcnic_bc_trans *trans, u8 type) if (type == QLC_BC_COMMAND) { hdr = (u32 *)(trans->req_hdr + trans->curr_req_frag); pay = (u32 *)(trans->req_pay + trans->curr_req_frag); - hdr_size = (sizeof(struct qlcnic_bc_hdr) / sizeof(u32)); pay_size = qlcnic_sriov_get_bc_paysize(trans->req_pay_size, trans->curr_req_frag); pay_size = (pay_size / sizeof(u32)); } else { hdr = (u32 *)(trans->rsp_hdr + trans->curr_rsp_frag); pay = (u32 *)(trans->rsp_pay + trans->curr_rsp_frag); - hdr_size = (sizeof(struct qlcnic_bc_hdr) / sizeof(u32)); pay_size = qlcnic_sriov_get_bc_paysize(trans->rsp_pay_size, trans->curr_rsp_frag); pay_size = (pay_size / sizeof(u32)); diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c index 353f1c129af1..059ba9429e51 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c +++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c @@ -2384,26 +2384,20 @@ static int qlge_update_hw_vlan_features(struct net_device *ndev, return status; } -static netdev_features_t qlge_fix_features(struct net_device *ndev, - netdev_features_t features) -{ - int err; - - /* Update the behavior of vlan accel in the adapter */ - err = qlge_update_hw_vlan_features(ndev, features); - if (err) - return err; - - return features; -} - static int qlge_set_features(struct net_device *ndev, netdev_features_t features) { netdev_features_t changed = ndev->features ^ features; + int err; + + if (changed & NETIF_F_HW_VLAN_CTAG_RX) { + /* Update the behavior of vlan accel in the adapter */ + err = qlge_update_hw_vlan_features(ndev, features); + if (err) + return err; - if (changed & NETIF_F_HW_VLAN_CTAG_RX) qlge_vlan_mode(ndev, features); + } return 0; } @@ -4719,7 +4713,6 @@ static const struct net_device_ops qlge_netdev_ops = { .ndo_set_mac_address = qlge_set_mac_address, .ndo_validate_addr = eth_validate_addr, .ndo_tx_timeout = qlge_tx_timeout, - .ndo_fix_features = qlge_fix_features, .ndo_set_features = qlge_set_features, .ndo_vlan_rx_add_vid = qlge_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = qlge_vlan_rx_kill_vid, diff --git a/drivers/net/ethernet/qualcomm/qca_7k.c b/drivers/net/ethernet/qualcomm/qca_7k.c index ffe7a16bdfc8..6c8543fb90c0 100644 --- a/drivers/net/ethernet/qualcomm/qca_7k.c +++ b/drivers/net/ethernet/qualcomm/qca_7k.c @@ -45,34 +45,33 @@ qcaspi_read_register(struct qcaspi *qca, u16 reg, u16 *result) { __be16 rx_data; __be16 tx_data; - struct spi_transfer *transfer; - struct spi_message *msg; + struct spi_transfer transfer[2]; + struct spi_message msg; int ret; + memset(transfer, 0, sizeof(transfer)); + + spi_message_init(&msg); + tx_data = cpu_to_be16(QCA7K_SPI_READ | QCA7K_SPI_INTERNAL | reg); + *result = 0; + + transfer[0].tx_buf = &tx_data; + transfer[0].len = QCASPI_CMD_LEN; + transfer[1].rx_buf = &rx_data; + transfer[1].len = QCASPI_CMD_LEN; + + spi_message_add_tail(&transfer[0], &msg); if (qca->legacy_mode) { - msg = &qca->spi_msg1; - transfer = &qca->spi_xfer1; - transfer->tx_buf = &tx_data; - transfer->rx_buf = NULL; - transfer->len = QCASPI_CMD_LEN; - spi_sync(qca->spi_dev, msg); - } else { - msg = &qca->spi_msg2; - transfer = &qca->spi_xfer2[0]; - transfer->tx_buf = &tx_data; - transfer->rx_buf = NULL; - transfer->len = QCASPI_CMD_LEN; - transfer = &qca->spi_xfer2[1]; + spi_sync(qca->spi_dev, &msg); + spi_message_init(&msg); } - transfer->tx_buf = NULL; - transfer->rx_buf = &rx_data; - transfer->len = QCASPI_CMD_LEN; - ret = spi_sync(qca->spi_dev, msg); + spi_message_add_tail(&transfer[1], &msg); + ret = spi_sync(qca->spi_dev, &msg); if (!ret) - ret = msg->status; + ret = msg.status; if (ret) qcaspi_spi_error(qca); @@ -86,35 +85,32 @@ int qcaspi_write_register(struct qcaspi *qca, u16 reg, u16 value) { __be16 tx_data[2]; - struct spi_transfer *transfer; - struct spi_message *msg; + struct spi_transfer transfer[2]; + struct spi_message msg; int ret; + memset(&transfer, 0, sizeof(transfer)); + + spi_message_init(&msg); + tx_data[0] = cpu_to_be16(QCA7K_SPI_WRITE | QCA7K_SPI_INTERNAL | reg); tx_data[1] = cpu_to_be16(value); + transfer[0].tx_buf = &tx_data[0]; + transfer[0].len = QCASPI_CMD_LEN; + transfer[1].tx_buf = &tx_data[1]; + transfer[1].len = QCASPI_CMD_LEN; + + spi_message_add_tail(&transfer[0], &msg); if (qca->legacy_mode) { - msg = &qca->spi_msg1; - transfer = &qca->spi_xfer1; - transfer->tx_buf = &tx_data[0]; - transfer->rx_buf = NULL; - transfer->len = QCASPI_CMD_LEN; - spi_sync(qca->spi_dev, msg); - } else { - msg = &qca->spi_msg2; - transfer = &qca->spi_xfer2[0]; - transfer->tx_buf = &tx_data[0]; - transfer->rx_buf = NULL; - transfer->len = QCASPI_CMD_LEN; - transfer = &qca->spi_xfer2[1]; + spi_sync(qca->spi_dev, &msg); + spi_message_init(&msg); } - transfer->tx_buf = &tx_data[1]; - transfer->rx_buf = NULL; - transfer->len = QCASPI_CMD_LEN; - ret = spi_sync(qca->spi_dev, msg); + spi_message_add_tail(&transfer[1], &msg); + ret = spi_sync(qca->spi_dev, &msg); if (!ret) - ret = msg->status; + ret = msg.status; if (ret) qcaspi_spi_error(qca); diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c index 206f0266463e..66b775d462fd 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.c +++ b/drivers/net/ethernet/qualcomm/qca_spi.c @@ -99,22 +99,24 @@ static u32 qcaspi_write_burst(struct qcaspi *qca, u8 *src, u32 len) { __be16 cmd; - struct spi_message *msg = &qca->spi_msg2; - struct spi_transfer *transfer = &qca->spi_xfer2[0]; + struct spi_message msg; + struct spi_transfer transfer[2]; int ret; + memset(&transfer, 0, sizeof(transfer)); + spi_message_init(&msg); + cmd = cpu_to_be16(QCA7K_SPI_WRITE | QCA7K_SPI_EXTERNAL); - transfer->tx_buf = &cmd; - transfer->rx_buf = NULL; - transfer->len = QCASPI_CMD_LEN; - transfer = &qca->spi_xfer2[1]; - transfer->tx_buf = src; - transfer->rx_buf = NULL; - transfer->len = len; + transfer[0].tx_buf = &cmd; + transfer[0].len = QCASPI_CMD_LEN; + transfer[1].tx_buf = src; + transfer[1].len = len; - ret = spi_sync(qca->spi_dev, msg); + spi_message_add_tail(&transfer[0], &msg); + spi_message_add_tail(&transfer[1], &msg); + ret = spi_sync(qca->spi_dev, &msg); - if (ret || (msg->actual_length != QCASPI_CMD_LEN + len)) { + if (ret || (msg.actual_length != QCASPI_CMD_LEN + len)) { qcaspi_spi_error(qca); return 0; } @@ -125,17 +127,20 @@ qcaspi_write_burst(struct qcaspi *qca, u8 *src, u32 len) static u32 qcaspi_write_legacy(struct qcaspi *qca, u8 *src, u32 len) { - struct spi_message *msg = &qca->spi_msg1; - struct spi_transfer *transfer = &qca->spi_xfer1; + struct spi_message msg; + struct spi_transfer transfer; int ret; - transfer->tx_buf = src; - transfer->rx_buf = NULL; - transfer->len = len; + memset(&transfer, 0, sizeof(transfer)); + spi_message_init(&msg); + + transfer.tx_buf = src; + transfer.len = len; - ret = spi_sync(qca->spi_dev, msg); + spi_message_add_tail(&transfer, &msg); + ret = spi_sync(qca->spi_dev, &msg); - if (ret || (msg->actual_length != len)) { + if (ret || (msg.actual_length != len)) { qcaspi_spi_error(qca); return 0; } @@ -146,23 +151,25 @@ qcaspi_write_legacy(struct qcaspi *qca, u8 *src, u32 len) static u32 qcaspi_read_burst(struct qcaspi *qca, u8 *dst, u32 len) { - struct spi_message *msg = &qca->spi_msg2; + struct spi_message msg; __be16 cmd; - struct spi_transfer *transfer = &qca->spi_xfer2[0]; + struct spi_transfer transfer[2]; int ret; + memset(&transfer, 0, sizeof(transfer)); + spi_message_init(&msg); + cmd = cpu_to_be16(QCA7K_SPI_READ | QCA7K_SPI_EXTERNAL); - transfer->tx_buf = &cmd; - transfer->rx_buf = NULL; - transfer->len = QCASPI_CMD_LEN; - transfer = &qca->spi_xfer2[1]; - transfer->tx_buf = NULL; - transfer->rx_buf = dst; - transfer->len = len; + transfer[0].tx_buf = &cmd; + transfer[0].len = QCASPI_CMD_LEN; + transfer[1].rx_buf = dst; + transfer[1].len = len; - ret = spi_sync(qca->spi_dev, msg); + spi_message_add_tail(&transfer[0], &msg); + spi_message_add_tail(&transfer[1], &msg); + ret = spi_sync(qca->spi_dev, &msg); - if (ret || (msg->actual_length != QCASPI_CMD_LEN + len)) { + if (ret || (msg.actual_length != QCASPI_CMD_LEN + len)) { qcaspi_spi_error(qca); return 0; } @@ -173,17 +180,20 @@ qcaspi_read_burst(struct qcaspi *qca, u8 *dst, u32 len) static u32 qcaspi_read_legacy(struct qcaspi *qca, u8 *dst, u32 len) { - struct spi_message *msg = &qca->spi_msg1; - struct spi_transfer *transfer = &qca->spi_xfer1; + struct spi_message msg; + struct spi_transfer transfer; int ret; - transfer->tx_buf = NULL; - transfer->rx_buf = dst; - transfer->len = len; + memset(&transfer, 0, sizeof(transfer)); + spi_message_init(&msg); - ret = spi_sync(qca->spi_dev, msg); + transfer.rx_buf = dst; + transfer.len = len; - if (ret || (msg->actual_length != len)) { + spi_message_add_tail(&transfer, &msg); + ret = spi_sync(qca->spi_dev, &msg); + + if (ret || (msg.actual_length != len)) { qcaspi_spi_error(qca); return 0; } @@ -195,19 +205,23 @@ static int qcaspi_tx_cmd(struct qcaspi *qca, u16 cmd) { __be16 tx_data; - struct spi_message *msg = &qca->spi_msg1; - struct spi_transfer *transfer = &qca->spi_xfer1; + struct spi_message msg; + struct spi_transfer transfer; int ret; + memset(&transfer, 0, sizeof(transfer)); + + spi_message_init(&msg); + tx_data = cpu_to_be16(cmd); - transfer->len = sizeof(tx_data); - transfer->tx_buf = &tx_data; - transfer->rx_buf = NULL; + transfer.len = sizeof(cmd); + transfer.tx_buf = &tx_data; + spi_message_add_tail(&transfer, &msg); - ret = spi_sync(qca->spi_dev, msg); + ret = spi_sync(qca->spi_dev, &msg); if (!ret) - ret = msg->status; + ret = msg.status; if (ret) qcaspi_spi_error(qca); @@ -835,16 +849,6 @@ qcaspi_netdev_setup(struct net_device *dev) qca = netdev_priv(dev); memset(qca, 0, sizeof(struct qcaspi)); - memset(&qca->spi_xfer1, 0, sizeof(struct spi_transfer)); - memset(&qca->spi_xfer2, 0, sizeof(struct spi_transfer) * 2); - - spi_message_init(&qca->spi_msg1); - spi_message_add_tail(&qca->spi_xfer1, &qca->spi_msg1); - - spi_message_init(&qca->spi_msg2); - spi_message_add_tail(&qca->spi_xfer2[0], &qca->spi_msg2); - spi_message_add_tail(&qca->spi_xfer2[1], &qca->spi_msg2); - memset(&qca->txr, 0, sizeof(qca->txr)); qca->txr.count = TX_RING_MAX_LEN; } diff --git a/drivers/net/ethernet/qualcomm/qca_spi.h b/drivers/net/ethernet/qualcomm/qca_spi.h index fc4beb1b32d1..fc0e98726b36 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.h +++ b/drivers/net/ethernet/qualcomm/qca_spi.h @@ -83,11 +83,6 @@ struct qcaspi { struct tx_ring txr; struct qcaspi_stats stats; - struct spi_message spi_msg1; - struct spi_message spi_msg2; - struct spi_transfer spi_xfer1; - struct spi_transfer spi_xfer2[2]; - u8 *rx_buffer; u32 buffer_size; u8 sync; diff --git a/drivers/net/ethernet/rdc/r6040.c b/drivers/net/ethernet/rdc/r6040.c index aa11b70b9ca4..04aa592f35c3 100644 --- a/drivers/net/ethernet/rdc/r6040.c +++ b/drivers/net/ethernet/rdc/r6040.c @@ -1024,16 +1024,8 @@ static int r6040_mii_probe(struct net_device *dev) return PTR_ERR(phydev); } - /* mask with MAC supported features */ - phydev->supported &= (SUPPORTED_10baseT_Half - | SUPPORTED_10baseT_Full - | SUPPORTED_100baseT_Half - | SUPPORTED_100baseT_Full - | SUPPORTED_Autoneg - | SUPPORTED_MII - | SUPPORTED_TP); - - phydev->advertising = phydev->supported; + phy_set_max_speed(phydev, SPEED_100); + lp->old_link = 0; lp->old_duplex = -1; diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 0efa977c422d..bb529ff2ca81 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -13,6 +13,7 @@ #include <linux/pci.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> +#include <linux/clk.h> #include <linux/delay.h> #include <linux/ethtool.h> #include <linux/phy.h> @@ -218,6 +219,7 @@ static const struct pci_device_id rtl8169_pci_tbl[] = { { PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x8161), 0, 0, RTL_CFG_1 }, { PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x8167), 0, 0, RTL_CFG_0 }, { PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x8168), 0, 0, RTL_CFG_1 }, + { PCI_DEVICE(PCI_VENDOR_ID_NCUBE, 0x8168), 0, 0, RTL_CFG_1 }, { PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x8169), 0, 0, RTL_CFG_0 }, { PCI_VENDOR_ID_DLINK, 0x4300, PCI_VENDOR_ID_DLINK, 0x4b10, 0, 0, RTL_CFG_1 }, @@ -630,7 +632,7 @@ struct rtl8169_tc_offsets { }; enum rtl_flag { - RTL_FLAG_TASK_ENABLED, + RTL_FLAG_TASK_ENABLED = 0, RTL_FLAG_TASK_SLOW_PENDING, RTL_FLAG_TASK_RESET_PENDING, RTL_FLAG_MAX @@ -664,6 +666,7 @@ struct rtl8169_private { u16 event_slow; const struct rtl_coalesce_info *coalesce_info; + struct clk *clk; struct mdio_ops { void (*write)(struct rtl8169_private *, int, int); @@ -4522,7 +4525,7 @@ static void rtl8169_hw_reset(struct rtl8169_private *tp) rtl_hw_reset(tp); } -static void rtl_set_rx_tx_config_registers(struct rtl8169_private *tp) +static void rtl_set_tx_config_registers(struct rtl8169_private *tp) { /* Set DMA burst size and Interframe Gap Time */ RTL_W32(tp, TxConfig, (TX_DMA_BURST << TxDMAShift) | @@ -4633,12 +4636,14 @@ static void rtl_hw_start(struct rtl8169_private *tp) rtl_set_rx_max_size(tp); rtl_set_rx_tx_desc_registers(tp); - rtl_set_rx_tx_config_registers(tp); RTL_W8(tp, Cfg9346, Cfg9346_Lock); /* Initially a 10 us delay. Turned it into a PCI commit. - FR */ RTL_R8(tp, IntrMask); RTL_W8(tp, ChipCmd, CmdTxEnb | CmdRxEnb); + rtl_init_rxcfg(tp); + rtl_set_tx_config_registers(tp); + rtl_set_rx_mode(tp->dev); /* no early-rx interrupts */ RTL_W16(tp, MultiIntr, RTL_R16(tp, MultiIntr) & 0xf000); @@ -4772,12 +4777,14 @@ static void rtl_pcie_state_l2l3_enable(struct rtl8169_private *tp, bool enable) static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable) { if (enable) { - RTL_W8(tp, Config2, RTL_R8(tp, Config2) | ClkReqEn); RTL_W8(tp, Config5, RTL_R8(tp, Config5) | ASPM_en); + RTL_W8(tp, Config2, RTL_R8(tp, Config2) | ClkReqEn); } else { RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn); RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en); } + + udelay(10); } static void rtl_hw_start_8168bb(struct rtl8169_private *tp) @@ -5622,6 +5629,8 @@ static void rtl_hw_start_8402(struct rtl8169_private *tp) static void rtl_hw_start_8106(struct rtl8169_private *tp) { + rtl_hw_aspm_clkreq_enable(tp, false); + /* Force LAN exit from ASPM if Rx/Tx are not idle */ RTL_W32(tp, FuncEvent, RTL_R32(tp, FuncEvent) | 0x002800); @@ -5630,6 +5639,7 @@ static void rtl_hw_start_8106(struct rtl8169_private *tp) RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~PFM_EN); rtl_pcie_state_l2l3_enable(tp, false); + rtl_hw_aspm_clkreq_enable(tp, true); } static void rtl_hw_start_8101(struct rtl8169_private *tp) @@ -6652,7 +6662,8 @@ static int rtl8169_close(struct net_device *dev) rtl8169_update_counters(tp); rtl_lock_work(tp); - clear_bit(RTL_FLAG_TASK_ENABLED, tp->wk.flags); + /* Clear all task flags */ + bitmap_zero(tp->wk.flags, RTL_FLAG_MAX); rtl8169_down(dev); rtl_unlock_work(tp); @@ -6835,7 +6846,9 @@ static void rtl8169_net_suspend(struct net_device *dev) rtl_lock_work(tp); napi_disable(&tp->napi); - clear_bit(RTL_FLAG_TASK_ENABLED, tp->wk.flags); + /* Clear all task flags */ + bitmap_zero(tp->wk.flags, RTL_FLAG_MAX); + rtl_unlock_work(tp); rtl_pll_power_down(tp); @@ -7251,6 +7264,11 @@ static int rtl_jumbo_max(struct rtl8169_private *tp) } } +static void rtl_disable_clk(void *data) +{ + clk_disable_unprepare(data); +} + static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) { const struct rtl_cfg_info *cfg = rtl_cfg_infos + ent->driver_data; @@ -7271,6 +7289,32 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) tp->msg_enable = netif_msg_init(debug.msg_enable, R8169_MSG_DEFAULT); tp->supports_gmii = cfg->has_gmii; + /* Get the *optional* external "ether_clk" used on some boards */ + tp->clk = devm_clk_get(&pdev->dev, "ether_clk"); + if (IS_ERR(tp->clk)) { + rc = PTR_ERR(tp->clk); + if (rc == -ENOENT) { + /* clk-core allows NULL (for suspend / resume) */ + tp->clk = NULL; + } else if (rc == -EPROBE_DEFER) { + return rc; + } else { + dev_err(&pdev->dev, "failed to get clk: %d\n", rc); + return rc; + } + } else { + rc = clk_prepare_enable(tp->clk); + if (rc) { + dev_err(&pdev->dev, "failed to enable clk: %d\n", rc); + return rc; + } + + rc = devm_add_action_or_reset(&pdev->dev, rtl_disable_clk, + tp->clk); + if (rc) + return rc; + } + /* enable device (incl. PCI PM wakeup and hotplug setup) */ rc = pcim_enable_device(pdev); if (rc < 0) { diff --git a/drivers/net/ethernet/renesas/Kconfig b/drivers/net/ethernet/renesas/Kconfig index f3f7477043ce..bb0ebdfd4459 100644 --- a/drivers/net/ethernet/renesas/Kconfig +++ b/drivers/net/ethernet/renesas/Kconfig @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # Renesas device configuration # diff --git a/drivers/net/ethernet/renesas/Makefile b/drivers/net/ethernet/renesas/Makefile index a05102a7df02..f21ab8c02af0 100644 --- a/drivers/net/ethernet/renesas/Makefile +++ b/drivers/net/ethernet/renesas/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # Makefile for the Renesas device drivers. # diff --git a/drivers/net/ethernet/renesas/ravb.h b/drivers/net/ethernet/renesas/ravb.h index b81f4faf7b10..1470fc12282b 100644 --- a/drivers/net/ethernet/renesas/ravb.h +++ b/drivers/net/ethernet/renesas/ravb.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* Renesas Ethernet AVB device driver * * Copyright (C) 2014-2015 Renesas Electronics Corporation @@ -5,10 +6,6 @@ * Copyright (C) 2015-2016 Cogent Embedded, Inc. <source@cogentembedded.com> * * Based on the SuperH Ethernet driver - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License version 2, - * as published by the Free Software Foundation. */ #ifndef __RAVB_H__ diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index c06f2df895c2..fb2a1125780d 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* Renesas Ethernet AVB device driver * * Copyright (C) 2014-2015 Renesas Electronics Corporation @@ -5,10 +6,6 @@ * Copyright (C) 2015-2016 Cogent Embedded, Inc. <source@cogentembedded.com> * * Based on the SuperH Ethernet driver - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License version 2, - * as published by the Free Software Foundation. */ #include <linux/cache.h> @@ -1077,7 +1074,8 @@ static int ravb_phy_init(struct net_device *ndev) } /* 10BASE is not supported */ - phydev->supported &= ~PHY_10BT_FEATURES; + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_10baseT_Half_BIT); + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_10baseT_Full_BIT); phy_attached_info(phydev); diff --git a/drivers/net/ethernet/renesas/ravb_ptp.c b/drivers/net/ethernet/renesas/ravb_ptp.c index eede70ec37f8..0721b5c35d91 100644 --- a/drivers/net/ethernet/renesas/ravb_ptp.c +++ b/drivers/net/ethernet/renesas/ravb_ptp.c @@ -1,13 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* PTP 1588 clock using the Renesas Ethernet AVB * * Copyright (C) 2013-2015 Renesas Electronics Corporation * Copyright (C) 2015 Renesas Solutions Corp. * Copyright (C) 2015-2016 Cogent Embedded, Inc. <source@cogentembedded.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 "ravb.h" diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index 5573199c4536..f27a0dc8c563 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* SuperH Ethernet device driver * * Copyright (C) 2014 Renesas Electronics Corporation @@ -5,18 +6,6 @@ * Copyright (C) 2008-2014 Renesas Solutions Corp. * Copyright (C) 2013-2017 Cogent Embedded, Inc. * Copyright (C) 2014 Codethink Limited - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". */ #include <linux/module.h> @@ -809,6 +798,41 @@ static struct sh_eth_cpu_data r8a77980_data = { .magic = 1, .cexcr = 1, }; + +/* R7S9210 */ +static struct sh_eth_cpu_data r7s9210_data = { + .soft_reset = sh_eth_soft_reset, + + .set_duplex = sh_eth_set_duplex, + .set_rate = sh_eth_set_rate_rcar, + + .register_type = SH_ETH_REG_FAST_SH4, + + .edtrr_trns = EDTRR_TRNS_ETHER, + .ecsr_value = ECSR_ICD, + .ecsipr_value = ECSIPR_ICDIP, + .eesipr_value = EESIPR_TWBIP | EESIPR_TABTIP | EESIPR_RABTIP | + EESIPR_RFCOFIP | EESIPR_ECIIP | EESIPR_FTCIP | + EESIPR_TDEIP | EESIPR_TFUFIP | EESIPR_FRIP | + EESIPR_RDEIP | EESIPR_RFOFIP | EESIPR_CNDIP | + EESIPR_DLCIP | EESIPR_CDIP | EESIPR_TROIP | + EESIPR_RMAFIP | EESIPR_RRFIP | EESIPR_RTLFIP | + EESIPR_RTSFIP | EESIPR_PREIP | EESIPR_CERFIP, + + .tx_check = EESR_FTC | EESR_CND | EESR_DLC | EESR_CD | EESR_TRO, + .eesr_err_check = EESR_TWB | EESR_TABT | EESR_RABT | EESR_RFE | + EESR_RDE | EESR_RFRMER | EESR_TFE | EESR_TDE, + + .fdr_value = 0x0000070f, + + .apr = 1, + .mpr = 1, + .tpauser = 1, + .hw_swap = 1, + .rpadir = 1, + .no_ade = 1, + .xdfar_rw = 1, +}; #endif /* CONFIG_OF */ static void sh_eth_set_rate_sh7724(struct net_device *ndev) @@ -3132,6 +3156,7 @@ static const struct of_device_id sh_eth_match_table[] = { { .compatible = "renesas,ether-r8a7794", .data = &rcar_gen2_data }, { .compatible = "renesas,gether-r8a77980", .data = &r8a77980_data }, { .compatible = "renesas,ether-r7s72100", .data = &r7s72100_data }, + { .compatible = "renesas,ether-r7s9210", .data = &r7s9210_data }, { .compatible = "renesas,rcar-gen1-ether", .data = &rcar_gen1_data }, { .compatible = "renesas,rcar-gen2-ether", .data = &rcar_gen2_data }, { } diff --git a/drivers/net/ethernet/renesas/sh_eth.h b/drivers/net/ethernet/renesas/sh_eth.h index f94be99cf400..0c18650bbfe6 100644 --- a/drivers/net/ethernet/renesas/sh_eth.h +++ b/drivers/net/ethernet/renesas/sh_eth.h @@ -1,19 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* SuperH Ethernet device driver * * Copyright (C) 2006-2012 Nobuhiro Iwamatsu * Copyright (C) 2008-2012 Renesas Solutions Corp. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". */ #ifndef __SH_ETH_H__ diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c index a9da1ad4b4f2..690aee88f0eb 100644 --- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c +++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c @@ -298,8 +298,8 @@ static int sxgbe_init_phy(struct net_device *ndev) /* Stop Advertising 1000BASE Capability if interface is not GMII */ if ((phy_iface == PHY_INTERFACE_MODE_MII) || (phy_iface == PHY_INTERFACE_MODE_RMII)) - phydev->advertising &= ~(SUPPORTED_1000baseT_Half | - SUPPORTED_1000baseT_Full); + phy_set_max_speed(phydev, SPEED_1000); + if (phydev->phy_id == 0) { phy_disconnect(phydev); return -ENODEV; diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c index f0afb88d7bc2..c009407618d9 100644 --- a/drivers/net/ethernet/smsc/smsc911x.c +++ b/drivers/net/ethernet/smsc/smsc911x.c @@ -1048,10 +1048,10 @@ static int smsc911x_mii_probe(struct net_device *dev) phy_attached_info(phydev); + phy_set_max_speed(phydev, SPEED_100); + /* mask with MAC supported features */ - phydev->supported &= (PHY_BASIC_FEATURES | SUPPORTED_Pause | - SUPPORTED_Asym_Pause); - phydev->advertising = phydev->supported; + phy_support_asym_pause(phydev); pdata->last_duplex = -1; pdata->last_carrier = -1; diff --git a/drivers/net/ethernet/smsc/smsc9420.c b/drivers/net/ethernet/smsc/smsc9420.c index 2fa3c1d03abc..9b6366b20110 100644 --- a/drivers/net/ethernet/smsc/smsc9420.c +++ b/drivers/net/ethernet/smsc/smsc9420.c @@ -1135,10 +1135,10 @@ static int smsc9420_mii_probe(struct net_device *dev) return PTR_ERR(phydev); } + phy_set_max_speed(phydev, SPEED_100); + /* mask with MAC supported features */ - phydev->supported &= (PHY_BASIC_FEATURES | SUPPORTED_Pause | - SUPPORTED_Asym_Pause); - phydev->advertising = phydev->supported; + phy_support_asym_pause(phydev); phy_attached_info(phydev); diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c index f7ecceeb1e28..2a156dcd4534 100644 --- a/drivers/net/ethernet/socionext/sni_ave.c +++ b/drivers/net/ethernet/socionext/sni_ave.c @@ -461,16 +461,7 @@ static int ave_ethtool_set_pauseparam(struct net_device *ndev, priv->pause_rx = pause->rx_pause; priv->pause_tx = pause->tx_pause; - phydev->advertising &= ~(ADVERTISED_Pause | ADVERTISED_Asym_Pause); - if (pause->rx_pause) - phydev->advertising |= ADVERTISED_Pause | ADVERTISED_Asym_Pause; - if (pause->tx_pause) - phydev->advertising ^= ADVERTISED_Asym_Pause; - - if (pause->autoneg) { - if (netif_running(ndev)) - phy_start_aneg(phydev); - } + phy_set_asym_pause(phydev, pause->rx_pause, pause->tx_pause); return 0; } @@ -904,11 +895,11 @@ static void ave_rxfifo_reset(struct net_device *ndev) /* assert reset */ writel(AVE_GRR_RXFFR, priv->base + AVE_GRR); - usleep_range(40, 50); + udelay(50); /* negate reset */ writel(0, priv->base + AVE_GRR); - usleep_range(10, 20); + udelay(20); /* negate interrupt status */ writel(AVE_GI_RXOVF, priv->base + AVE_GISR); @@ -1223,11 +1214,10 @@ static int ave_init(struct net_device *ndev) phy_ethtool_get_wol(phydev, &wol); device_set_wakeup_capable(&ndev->dev, !!wol.supported); - if (!phy_interface_is_rgmii(phydev)) { - phydev->supported &= ~PHY_GBIT_FEATURES; - phydev->supported |= PHY_BASIC_FEATURES; - } - phydev->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; + if (!phy_interface_is_rgmii(phydev)) + phy_set_max_speed(phydev, SPEED_100); + + phy_support_asym_pause(phydev); phy_attached_info(phydev); diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig index edf20361ea5f..324049eebb9b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Kconfig +++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig @@ -33,7 +33,7 @@ config DWMAC_DWC_QOS_ETH select PHYLIB select CRC32 select MII - depends on OF && COMMON_CLK && HAS_DMA + depends on OF && HAS_DMA help Support for chips using the snps,dwc-qos-ethernet.txt DT binding. @@ -57,7 +57,7 @@ config DWMAC_ANARION config DWMAC_IPQ806X tristate "QCA IPQ806x DWMAC support" default ARCH_QCOM - depends on OF && COMMON_CLK && (ARCH_QCOM || COMPILE_TEST) + depends on OF && (ARCH_QCOM || COMPILE_TEST) select MFD_SYSCON help Support for QCA IPQ806X DWMAC Ethernet. @@ -100,7 +100,7 @@ config DWMAC_OXNAS config DWMAC_ROCKCHIP tristate "Rockchip dwmac support" default ARCH_ROCKCHIP - depends on OF && COMMON_CLK && (ARCH_ROCKCHIP || COMPILE_TEST) + depends on OF && (ARCH_ROCKCHIP || COMPILE_TEST) select MFD_SYSCON help Support for Ethernet controller on Rockchip RK3288 SoC. @@ -110,7 +110,7 @@ config DWMAC_ROCKCHIP config DWMAC_SOCFPGA tristate "SOCFPGA dwmac support" - default ARCH_SOCFPGA + default (ARCH_SOCFPGA || ARCH_STRATIX10) depends on OF && (ARCH_SOCFPGA || ARCH_STRATIX10 || COMPILE_TEST) select MFD_SYSCON help @@ -123,7 +123,7 @@ config DWMAC_SOCFPGA config DWMAC_STI tristate "STi GMAC support" default ARCH_STI - depends on OF && COMMON_CLK && (ARCH_STI || COMPILE_TEST) + depends on OF && (ARCH_STI || COMPILE_TEST) select MFD_SYSCON ---help--- Support for ethernet controller on STi SOCs. @@ -147,7 +147,7 @@ config DWMAC_STM32 config DWMAC_SUNXI tristate "Allwinner GMAC support" default ARCH_SUNXI - depends on OF && COMMON_CLK && (ARCH_SUNXI || COMPILE_TEST) + depends on OF && (ARCH_SUNXI || COMPILE_TEST) ---help--- Support for Allwinner A20/A31 GMAC ethernet controllers. diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h index 0a80fa25afe3..d6bb953685fa 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h @@ -119,11 +119,23 @@ #define XGMAC_MTL_TXQ_OPMODE(x) (0x00001100 + (0x80 * (x))) #define XGMAC_TQS GENMASK(25, 16) #define XGMAC_TQS_SHIFT 16 +#define XGMAC_Q2TCMAP GENMASK(10, 8) +#define XGMAC_Q2TCMAP_SHIFT 8 #define XGMAC_TTC GENMASK(6, 4) #define XGMAC_TTC_SHIFT 4 #define XGMAC_TXQEN GENMASK(3, 2) #define XGMAC_TXQEN_SHIFT 2 #define XGMAC_TSF BIT(1) +#define XGMAC_MTL_TCx_ETS_CONTROL(x) (0x00001110 + (0x80 * (x))) +#define XGMAC_MTL_TCx_QUANTUM_WEIGHT(x) (0x00001118 + (0x80 * (x))) +#define XGMAC_MTL_TCx_SENDSLOPE(x) (0x0000111c + (0x80 * (x))) +#define XGMAC_MTL_TCx_HICREDIT(x) (0x00001120 + (0x80 * (x))) +#define XGMAC_MTL_TCx_LOCREDIT(x) (0x00001124 + (0x80 * (x))) +#define XGMAC_CC BIT(3) +#define XGMAC_TSA GENMASK(1, 0) +#define XGMAC_SP (0x0 << 0) +#define XGMAC_CBS (0x1 << 0) +#define XGMAC_ETS (0x2 << 0) #define XGMAC_MTL_RXQ_OPMODE(x) (0x00001140 + (0x80 * (x))) #define XGMAC_RQS GENMASK(25, 16) #define XGMAC_RQS_SHIFT 16 diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index d182f82f7b58..64b8cb88ea45 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -177,6 +177,23 @@ static void dwxgmac2_map_mtl_to_dma(struct mac_device_info *hw, u32 queue, writel(value, ioaddr + reg); } +static void dwxgmac2_config_cbs(struct mac_device_info *hw, + u32 send_slope, u32 idle_slope, + u32 high_credit, u32 low_credit, u32 queue) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value; + + writel(send_slope, ioaddr + XGMAC_MTL_TCx_SENDSLOPE(queue)); + writel(idle_slope, ioaddr + XGMAC_MTL_TCx_QUANTUM_WEIGHT(queue)); + writel(high_credit, ioaddr + XGMAC_MTL_TCx_HICREDIT(queue)); + writel(low_credit, ioaddr + XGMAC_MTL_TCx_LOCREDIT(queue)); + + value = readl(ioaddr + XGMAC_MTL_TCx_ETS_CONTROL(queue)); + value |= XGMAC_CC | XGMAC_CBS; + writel(value, ioaddr + XGMAC_MTL_TCx_ETS_CONTROL(queue)); +} + static int dwxgmac2_host_irq_status(struct mac_device_info *hw, struct stmmac_extra_stats *x) { @@ -316,7 +333,7 @@ const struct stmmac_ops dwxgmac210_ops = { .prog_mtl_tx_algorithms = dwxgmac2_prog_mtl_tx_algorithms, .set_mtl_tx_queue_weight = NULL, .map_mtl_to_dma = dwxgmac2_map_mtl_to_dma, - .config_cbs = NULL, + .config_cbs = dwxgmac2_config_cbs, .dump_regs = NULL, .host_irq_status = dwxgmac2_host_irq_status, .host_mtl_irq_status = dwxgmac2_host_mtl_irq_status, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c index 20909036e002..6c5092e7771c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c @@ -182,6 +182,9 @@ static void dwxgmac2_dma_tx_mode(void __iomem *ioaddr, int mode, value |= 0x7 << XGMAC_TTC_SHIFT; } + /* Use static TC to Queue mapping */ + value |= (channel << XGMAC_Q2TCMAP_SHIFT) & XGMAC_Q2TCMAP; + value &= ~XGMAC_TXQEN; if (qmode != MTL_QUEUE_AVB) value |= 0x2 << XGMAC_TXQEN_SHIFT; @@ -374,6 +377,21 @@ static void dwxgmac2_enable_tso(void __iomem *ioaddr, bool en, u32 chan) writel(value, ioaddr + XGMAC_DMA_CH_TX_CONTROL(chan)); } +static void dwxgmac2_qmode(void __iomem *ioaddr, u32 channel, u8 qmode) +{ + u32 value = readl(ioaddr + XGMAC_MTL_TXQ_OPMODE(channel)); + + value &= ~XGMAC_TXQEN; + if (qmode != MTL_QUEUE_AVB) { + value |= 0x2 << XGMAC_TXQEN_SHIFT; + writel(0, ioaddr + XGMAC_MTL_TCx_ETS_CONTROL(channel)); + } else { + value |= 0x1 << XGMAC_TXQEN_SHIFT; + } + + writel(value, ioaddr + XGMAC_MTL_TXQ_OPMODE(channel)); +} + static void dwxgmac2_set_bfsize(void __iomem *ioaddr, int bfsize, u32 chan) { u32 value; @@ -407,5 +425,6 @@ const struct stmmac_dma_ops dwxgmac210_dma_ops = { .set_rx_tail_ptr = dwxgmac2_set_rx_tail_ptr, .set_tx_tail_ptr = dwxgmac2_set_tx_tail_ptr, .enable_tso = dwxgmac2_enable_tso, + .qmode = dwxgmac2_qmode, .set_bfsize = dwxgmac2_set_bfsize, }; diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.c b/drivers/net/ethernet/stmicro/stmmac/hwif.c index 357309a6d6a5..81b966a8261b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.c +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.c @@ -133,7 +133,7 @@ static const struct stmmac_hwif_entry { .mac = &dwmac4_ops, .hwtimestamp = &stmmac_ptp, .mode = NULL, - .tc = NULL, + .tc = &dwmac510_tc_ops, .setup = dwmac4_setup, .quirks = stmmac_dwmac4_quirks, }, { @@ -150,7 +150,7 @@ static const struct stmmac_hwif_entry { .mac = &dwmac410_ops, .hwtimestamp = &stmmac_ptp, .mode = &dwmac4_ring_mode_ops, - .tc = NULL, + .tc = &dwmac510_tc_ops, .setup = dwmac4_setup, .quirks = NULL, }, { @@ -167,7 +167,7 @@ static const struct stmmac_hwif_entry { .mac = &dwmac410_ops, .hwtimestamp = &stmmac_ptp, .mode = &dwmac4_ring_mode_ops, - .tc = NULL, + .tc = &dwmac510_tc_ops, .setup = dwmac4_setup, .quirks = NULL, }, { @@ -201,7 +201,7 @@ static const struct stmmac_hwif_entry { .mac = &dwxgmac210_ops, .hwtimestamp = &stmmac_ptp, .mode = NULL, - .tc = NULL, + .tc = &dwmac510_tc_ops, .setup = dwxgmac2_setup, .quirks = NULL, }, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 76649adf8fb0..c0a855b7ab3b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -112,7 +112,6 @@ struct stmmac_priv { u32 tx_count_frames; u32 tx_coal_frames; u32 tx_coal_timer; - bool tx_timer_armed; int tx_coalesce; int hwts_tx_en; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index ff1ffb46198a..3715a0a4af3c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -987,17 +987,20 @@ static int stmmac_init_phy(struct net_device *dev) if ((interface == PHY_INTERFACE_MODE_MII) || (interface == PHY_INTERFACE_MODE_RMII) || (max_speed < 1000 && max_speed > 0)) - phydev->advertising &= ~(SUPPORTED_1000baseT_Half | - SUPPORTED_1000baseT_Full); + phy_set_max_speed(phydev, SPEED_100); /* * Half-duplex mode not supported with multiqueue * half-duplex can only works with single queue */ - if (tx_cnt > 1) - phydev->supported &= ~(SUPPORTED_1000baseT_Half | - SUPPORTED_100baseT_Half | - SUPPORTED_10baseT_Half); + if (tx_cnt > 1) { + phy_remove_link_mode(phydev, + ETHTOOL_LINK_MODE_10baseT_Half_BIT); + phy_remove_link_mode(phydev, + ETHTOOL_LINK_MODE_100baseT_Half_BIT); + phy_remove_link_mode(phydev, + ETHTOOL_LINK_MODE_1000baseT_Half_BIT); + } /* * Broken HW is sometimes missing the pull-up resistor on the @@ -3147,16 +3150,13 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) * element in case of no SG. */ priv->tx_count_frames += nfrags + 1; - if (likely(priv->tx_coal_frames > priv->tx_count_frames) && - !priv->tx_timer_armed) { + if (likely(priv->tx_coal_frames > priv->tx_count_frames)) { mod_timer(&priv->txtimer, STMMAC_COAL_TIMER(priv->tx_coal_timer)); - priv->tx_timer_armed = true; } else { priv->tx_count_frames = 0; stmmac_set_tx_ic(priv, desc); priv->xstats.tx_set_ic_bit++; - priv->tx_timer_armed = false; } skb_tx_timestamp(skb); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 3609c7b696c7..2b800ce1d5bf 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -67,7 +67,7 @@ static int dwmac1000_validate_mcast_bins(int mcast_bins) * Description: * This function validates the number of Unicast address entries supported * by a particular Synopsys 10/100/1000 controller. The Synopsys controller - * supports 1, 32, 64, or 128 Unicast filter entries for it's Unicast filter + * supports 1..32, 64, or 128 Unicast filter entries for it's Unicast filter * logic. This function validates a valid, supported configuration is * selected, and defaults to 1 Unicast address if an unsupported * configuration is selected. @@ -77,8 +77,7 @@ static int dwmac1000_validate_ucast_entries(int ucast_entries) int x = ucast_entries; switch (x) { - case 1: - case 32: + case 1 ... 32: case 64: case 128: break; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index 1a96dd9c1091..531294f4978b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -61,7 +61,7 @@ static int tc_fill_actions(struct stmmac_tc_entry *entry, struct stmmac_tc_entry *action_entry = entry; const struct tc_action *act; struct tcf_exts *exts; - LIST_HEAD(actions); + int i; exts = cls->knode.exts; if (!tcf_exts_has_actions(exts)) @@ -69,8 +69,7 @@ static int tc_fill_actions(struct stmmac_tc_entry *entry, if (frag) action_entry = frag; - tcf_exts_to_list(exts, &actions); - list_for_each_entry(act, &actions, list) { + tcf_exts_for_each_action(i, act, exts) { /* Accept */ if (is_tcf_gact_ok(act)) { action_entry->val.af = 1; diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c index 06da2f59fcbf..863fd602fd33 100644 --- a/drivers/net/ethernet/sun/sunhme.c +++ b/drivers/net/ethernet/sun/sunhme.c @@ -2999,7 +2999,7 @@ static int happy_meal_pci_probe(struct pci_dev *pdev, /* Now make sure pci_dev cookie is there. */ #ifdef CONFIG_SPARC dp = pci_device_to_OF_node(pdev); - strcpy(prom_name, dp->name); + snprintf(prom_name, sizeof(prom_name), "%pOFn", dp); #else if (is_quattro_p(pdev)) strcpy(prom_name, "SUNW,qfe"); diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig index 9263d638bd6d..f932923f7d56 100644 --- a/drivers/net/ethernet/ti/Kconfig +++ b/drivers/net/ethernet/ti/Kconfig @@ -41,6 +41,7 @@ config TI_DAVINCI_MDIO config TI_DAVINCI_CPDMA tristate "TI DaVinci CPDMA Support" depends on ARCH_DAVINCI || ARCH_OMAP2PLUS || COMPILE_TEST + select GENERIC_ALLOCATOR ---help--- This driver supports TI's DaVinci CPDMA dma engine. diff --git a/drivers/net/ethernet/ti/cpsw-phy-sel.c b/drivers/net/ethernet/ti/cpsw-phy-sel.c index 0c1adad7415d..396e1cd10667 100644 --- a/drivers/net/ethernet/ti/cpsw-phy-sel.c +++ b/drivers/net/ethernet/ti/cpsw-phy-sel.c @@ -170,10 +170,13 @@ void cpsw_phy_sel(struct device *dev, phy_interface_t phy_mode, int slave) struct device_node *node; struct cpsw_phy_sel_priv *priv; - node = of_get_child_by_name(dev->of_node, "cpsw-phy-sel"); + node = of_parse_phandle(dev->of_node, "cpsw-phy-sel", 0); if (!node) { - dev_err(dev, "Phy mode driver DT not found\n"); - return; + node = of_get_child_by_name(dev->of_node, "cpsw-phy-sel"); + if (!node) { + dev_err(dev, "Phy mode driver DT not found\n"); + return; + } } dev = bus_find_device(&platform_bus_type, NULL, node, match); diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index a1d335a3c5e4..1f612268c998 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -225,17 +225,6 @@ static int emac_arch_get_mac_addr(char *x, void __iomem *efuse_mac, u32 swap) return 0; } -static const char *netcp_node_name(struct device_node *node) -{ - const char *name; - - if (of_property_read_string(node, "label", &name) < 0) - name = node->name; - if (!name) - name = "unknown"; - return name; -} - /* Module management routines */ static int netcp_register_interface(struct netcp_intf *netcp) { @@ -267,8 +256,13 @@ static int netcp_module_probe(struct netcp_device *netcp_device, } for_each_available_child_of_node(devices, child) { - const char *name = netcp_node_name(child); + const char *name; + char node_name[32]; + if (of_property_read_string(node, "label", &name) < 0) { + snprintf(node_name, sizeof(node_name), "%pOFn", child); + name = node_name; + } if (!strcasecmp(module->name, name)) break; } @@ -2209,8 +2203,8 @@ static int netcp_probe(struct platform_device *pdev) for_each_available_child_of_node(interfaces, child) { ret = netcp_create_interface(netcp_device, child); if (ret) { - dev_err(dev, "could not create interface(%s)\n", - child->name); + dev_err(dev, "could not create interface(%pOFn)\n", + child); goto probe_quit_interface; } } diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c index 72b98e27c992..0397ccb6597e 100644 --- a/drivers/net/ethernet/ti/netcp_ethss.c +++ b/drivers/net/ethernet/ti/netcp_ethss.c @@ -3137,15 +3137,15 @@ static void init_secondary_ports(struct gbe_priv *gbe_dev, for_each_child_of_node(node, port) { slave = devm_kzalloc(dev, sizeof(*slave), GFP_KERNEL); if (!slave) { - dev_err(dev, "memory alloc failed for secondary port(%s), skipping...\n", - port->name); + dev_err(dev, "memory alloc failed for secondary port(%pOFn), skipping...\n", + port); continue; } if (init_slave(gbe_dev, slave, port)) { dev_err(dev, - "Failed to initialize secondary port(%s), skipping...\n", - port->name); + "Failed to initialize secondary port(%pOFn), skipping...\n", + port); devm_kfree(dev, slave); continue; } @@ -3239,8 +3239,8 @@ static int set_xgbe_ethss10_priv(struct gbe_priv *gbe_dev, ret = of_address_to_resource(node, XGBE_SS_REG_INDEX, &res); if (ret) { dev_err(gbe_dev->dev, - "Can't xlate xgbe of node(%s) ss address at %d\n", - node->name, XGBE_SS_REG_INDEX); + "Can't xlate xgbe of node(%pOFn) ss address at %d\n", + node, XGBE_SS_REG_INDEX); return ret; } @@ -3254,8 +3254,8 @@ static int set_xgbe_ethss10_priv(struct gbe_priv *gbe_dev, ret = of_address_to_resource(node, XGBE_SM_REG_INDEX, &res); if (ret) { dev_err(gbe_dev->dev, - "Can't xlate xgbe of node(%s) sm address at %d\n", - node->name, XGBE_SM_REG_INDEX); + "Can't xlate xgbe of node(%pOFn) sm address at %d\n", + node, XGBE_SM_REG_INDEX); return ret; } @@ -3269,8 +3269,8 @@ static int set_xgbe_ethss10_priv(struct gbe_priv *gbe_dev, ret = of_address_to_resource(node, XGBE_SERDES_REG_INDEX, &res); if (ret) { dev_err(gbe_dev->dev, - "Can't xlate xgbe serdes of node(%s) address at %d\n", - node->name, XGBE_SERDES_REG_INDEX); + "Can't xlate xgbe serdes of node(%pOFn) address at %d\n", + node, XGBE_SERDES_REG_INDEX); return ret; } @@ -3347,8 +3347,8 @@ static int get_gbe_resource_version(struct gbe_priv *gbe_dev, ret = of_address_to_resource(node, GBE_SS_REG_INDEX, &res); if (ret) { dev_err(gbe_dev->dev, - "Can't translate of node(%s) of gbe ss address at %d\n", - node->name, GBE_SS_REG_INDEX); + "Can't translate of node(%pOFn) of gbe ss address at %d\n", + node, GBE_SS_REG_INDEX); return ret; } @@ -3372,8 +3372,8 @@ static int set_gbe_ethss14_priv(struct gbe_priv *gbe_dev, ret = of_address_to_resource(node, GBE_SGMII34_REG_INDEX, &res); if (ret) { dev_err(gbe_dev->dev, - "Can't translate of gbe node(%s) address at index %d\n", - node->name, GBE_SGMII34_REG_INDEX); + "Can't translate of gbe node(%pOFn) address at index %d\n", + node, GBE_SGMII34_REG_INDEX); return ret; } @@ -3388,8 +3388,8 @@ static int set_gbe_ethss14_priv(struct gbe_priv *gbe_dev, ret = of_address_to_resource(node, GBE_SM_REG_INDEX, &res); if (ret) { dev_err(gbe_dev->dev, - "Can't translate of gbe node(%s) address at index %d\n", - node->name, GBE_SM_REG_INDEX); + "Can't translate of gbe node(%pOFn) address at index %d\n", + node, GBE_SM_REG_INDEX); return ret; } @@ -3498,8 +3498,8 @@ static int set_gbenu_ethss_priv(struct gbe_priv *gbe_dev, ret = of_address_to_resource(node, GBENU_SM_REG_INDEX, &res); if (ret) { dev_err(gbe_dev->dev, - "Can't translate of gbenu node(%s) addr at index %d\n", - node->name, GBENU_SM_REG_INDEX); + "Can't translate of gbenu node(%pOFn) addr at index %d\n", + node, GBENU_SM_REG_INDEX); return ret; } @@ -3642,7 +3642,7 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev, ret = netcp_xgbe_serdes_init(gbe_dev->xgbe_serdes_regs, gbe_dev->ss_regs); } else { - dev_err(dev, "unknown GBE node(%s)\n", node->name); + dev_err(dev, "unknown GBE node(%pOFn)\n", node); ret = -ENODEV; } @@ -3667,8 +3667,8 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev, for_each_child_of_node(interfaces, interface) { ret = of_property_read_u32(interface, "slave-port", &slave_num); if (ret) { - dev_err(dev, "missing slave-port parameter, skipping interface configuration for %s\n", - interface->name); + dev_err(dev, "missing slave-port parameter, skipping interface configuration for %pOFn\n", + interface); continue; } gbe_dev->num_slaves++; diff --git a/drivers/net/ethernet/toshiba/tc35815.c b/drivers/net/ethernet/toshiba/tc35815.c index cce9c9ed46aa..7163a8d10dba 100644 --- a/drivers/net/ethernet/toshiba/tc35815.c +++ b/drivers/net/ethernet/toshiba/tc35815.c @@ -628,7 +628,7 @@ static int tc_mii_probe(struct net_device *dev) phy_attached_info(phydev); /* mask with MAC supported features */ - phydev->supported &= PHY_BASIC_FEATURES; + phy_set_max_speed(phydev, SPEED_100); dropmask = 0; if (options.speed == 10) dropmask |= SUPPORTED_100baseT_Half | SUPPORTED_100baseT_Full; diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c index 42f1f518dad6..46d3092b8aad 100644 --- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c +++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c @@ -941,8 +941,7 @@ static int xemaclite_open(struct net_device *dev) } /* EmacLite doesn't support giga-bit speeds */ - lp->phy_dev->supported &= (PHY_BASIC_FEATURES); - lp->phy_dev->advertising = lp->phy_dev->supported; + phy_set_max_speed(lp->phy_dev, SPEED_100); /* Don't advertise 1000BASE-T Full/Half duplex speeds */ phy_write(lp->phy_dev, MII_CTRL1000, 0); diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 6acb6b5718b9..6625fabe2c88 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -69,6 +69,7 @@ struct geneve_dev { struct gro_cells gro_cells; bool collect_md; bool use_udp6_rx_checksums; + bool ttl_inherit; }; struct geneve_sock { @@ -843,7 +844,11 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, ttl = key->ttl; } else { tos = ip_tunnel_ecn_encap(fl4.flowi4_tos, ip_hdr(skb), skb); - ttl = key->ttl ? : ip4_dst_hoplimit(&rt->dst); + if (geneve->ttl_inherit) + ttl = ip_tunnel_get_ttl(ip_hdr(skb), skb); + else + ttl = key->ttl; + ttl = ttl ? : ip4_dst_hoplimit(&rt->dst); } df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0; @@ -889,7 +894,11 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, } else { prio = ip_tunnel_ecn_encap(ip6_tclass(fl6.flowlabel), ip_hdr(skb), skb); - ttl = key->ttl ? : ip6_dst_hoplimit(dst); + if (geneve->ttl_inherit) + ttl = ip_tunnel_get_ttl(ip_hdr(skb), skb); + else + ttl = key->ttl; + ttl = ttl ? : ip6_dst_hoplimit(dst); } err = geneve_build_skb(dst, skb, info, xnet, sizeof(struct ipv6hdr)); if (unlikely(err)) @@ -1091,6 +1100,7 @@ static const struct nla_policy geneve_policy[IFLA_GENEVE_MAX + 1] = { [IFLA_GENEVE_UDP_CSUM] = { .type = NLA_U8 }, [IFLA_GENEVE_UDP_ZERO_CSUM6_TX] = { .type = NLA_U8 }, [IFLA_GENEVE_UDP_ZERO_CSUM6_RX] = { .type = NLA_U8 }, + [IFLA_GENEVE_TTL_INHERIT] = { .type = NLA_U8 }, }; static int geneve_validate(struct nlattr *tb[], struct nlattr *data[], @@ -1170,7 +1180,8 @@ static bool geneve_dst_addr_equal(struct ip_tunnel_info *a, static int geneve_configure(struct net *net, struct net_device *dev, struct netlink_ext_ack *extack, const struct ip_tunnel_info *info, - bool metadata, bool ipv6_rx_csum) + bool metadata, bool ipv6_rx_csum, + bool ttl_inherit) { struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_dev *t, *geneve = netdev_priv(dev); @@ -1219,6 +1230,7 @@ static int geneve_configure(struct net *net, struct net_device *dev, geneve->info = *info; geneve->collect_md = metadata; geneve->use_udp6_rx_checksums = ipv6_rx_csum; + geneve->ttl_inherit = ttl_inherit; err = register_netdevice(dev); if (err) @@ -1237,7 +1249,8 @@ static void init_tnl_info(struct ip_tunnel_info *info, __u16 dst_port) static int geneve_nl2info(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack, struct ip_tunnel_info *info, bool *metadata, - bool *use_udp6_rx_checksums, bool changelink) + bool *use_udp6_rx_checksums, bool *ttl_inherit, + bool changelink) { int attrtype; @@ -1315,6 +1328,9 @@ static int geneve_nl2info(struct nlattr *tb[], struct nlattr *data[], if (data[IFLA_GENEVE_TTL]) info->key.ttl = nla_get_u8(data[IFLA_GENEVE_TTL]); + if (data[IFLA_GENEVE_TTL_INHERIT]) + *ttl_inherit = true; + if (data[IFLA_GENEVE_TOS]) info->key.tos = nla_get_u8(data[IFLA_GENEVE_TOS]); @@ -1438,17 +1454,18 @@ static int geneve_newlink(struct net *net, struct net_device *dev, { bool use_udp6_rx_checksums = false; struct ip_tunnel_info info; + bool ttl_inherit = false; bool metadata = false; int err; init_tnl_info(&info, GENEVE_UDP_PORT); err = geneve_nl2info(tb, data, extack, &info, &metadata, - &use_udp6_rx_checksums, false); + &use_udp6_rx_checksums, &ttl_inherit, false); if (err) return err; err = geneve_configure(net, dev, extack, &info, metadata, - use_udp6_rx_checksums); + use_udp6_rx_checksums, ttl_inherit); if (err) return err; @@ -1511,6 +1528,7 @@ static int geneve_changelink(struct net_device *dev, struct nlattr *tb[], struct ip_tunnel_info info; bool metadata; bool use_udp6_rx_checksums; + bool ttl_inherit; int err; /* If the geneve device is configured for metadata (or externally @@ -1523,8 +1541,9 @@ static int geneve_changelink(struct net_device *dev, struct nlattr *tb[], memcpy(&info, &geneve->info, sizeof(info)); metadata = geneve->collect_md; use_udp6_rx_checksums = geneve->use_udp6_rx_checksums; + ttl_inherit = geneve->ttl_inherit; err = geneve_nl2info(tb, data, extack, &info, &metadata, - &use_udp6_rx_checksums, true); + &use_udp6_rx_checksums, &ttl_inherit, true); if (err) return err; @@ -1537,6 +1556,7 @@ static int geneve_changelink(struct net_device *dev, struct nlattr *tb[], geneve->info = info; geneve->collect_md = metadata; geneve->use_udp6_rx_checksums = use_udp6_rx_checksums; + geneve->ttl_inherit = ttl_inherit; geneve_unquiesce(geneve, gs4, gs6); return 0; @@ -1562,6 +1582,7 @@ static size_t geneve_get_size(const struct net_device *dev) nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_CSUM */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_ZERO_CSUM6_TX */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_ZERO_CSUM6_RX */ + nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TTL_INHERIT */ 0; } @@ -1569,6 +1590,7 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); struct ip_tunnel_info *info = &geneve->info; + bool ttl_inherit = geneve->ttl_inherit; bool metadata = geneve->collect_md; __u8 tmp_vni[3]; __u32 vni; @@ -1614,6 +1636,9 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev) goto nla_put_failure; #endif + if (nla_put_u8(skb, IFLA_GENEVE_TTL_INHERIT, ttl_inherit)) + goto nla_put_failure; + return 0; nla_put_failure: @@ -1650,7 +1675,7 @@ struct net_device *geneve_dev_create_fb(struct net *net, const char *name, return dev; init_tnl_info(&info, dst_port); - err = geneve_configure(net, dev, NULL, &info, true, true); + err = geneve_configure(net, dev, NULL, &info, true, true, false); if (err) { free_netdev(dev); return ERR_PTR(err); diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 31c3d77b4733..fe01e141c8f8 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -1203,6 +1203,9 @@ static void netvsc_send_vf(struct net_device *ndev, net_device_ctx->vf_alloc = nvmsg->msg.v4_msg.vf_assoc.allocated; net_device_ctx->vf_serial = nvmsg->msg.v4_msg.vf_assoc.serial; + netdev_info(ndev, "VF slot %u %s\n", + net_device_ctx->vf_serial, + net_device_ctx->vf_alloc ? "added" : "removed"); } static void netvsc_receive_inband(struct net_device *ndev, diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 507f68190cb1..3af6d8d15233 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -29,6 +29,7 @@ #include <linux/netdevice.h> #include <linux/inetdevice.h> #include <linux/etherdevice.h> +#include <linux/pci.h> #include <linux/skbuff.h> #include <linux/if_vlan.h> #include <linux/in.h> @@ -1893,20 +1894,6 @@ out_unlock: rtnl_unlock(); } -static struct net_device *get_netvsc_bymac(const u8 *mac) -{ - struct net_device_context *ndev_ctx; - - list_for_each_entry(ndev_ctx, &netvsc_dev_list, list) { - struct net_device *dev = hv_get_drvdata(ndev_ctx->device_ctx); - - if (ether_addr_equal(mac, dev->perm_addr)) - return dev; - } - - return NULL; -} - static struct net_device *get_netvsc_byref(struct net_device *vf_netdev) { struct net_device_context *net_device_ctx; @@ -2035,22 +2022,48 @@ static void netvsc_vf_setup(struct work_struct *w) rtnl_unlock(); } +/* Find netvsc by VMBus serial number. + * The PCI hyperv controller records the serial number as the slot. + */ +static struct net_device *get_netvsc_byslot(const struct net_device *vf_netdev) +{ + struct device *parent = vf_netdev->dev.parent; + struct net_device_context *ndev_ctx; + struct pci_dev *pdev; + + if (!parent || !dev_is_pci(parent)) + return NULL; /* not a PCI device */ + + pdev = to_pci_dev(parent); + if (!pdev->slot) { + netdev_notice(vf_netdev, "no PCI slot information\n"); + return NULL; + } + + list_for_each_entry(ndev_ctx, &netvsc_dev_list, list) { + if (!ndev_ctx->vf_alloc) + continue; + + if (ndev_ctx->vf_serial == pdev->slot->number) + return hv_get_drvdata(ndev_ctx->device_ctx); + } + + netdev_notice(vf_netdev, + "no netdev found for slot %u\n", pdev->slot->number); + return NULL; +} + static int netvsc_register_vf(struct net_device *vf_netdev) { - struct net_device *ndev; struct net_device_context *net_device_ctx; struct netvsc_device *netvsc_dev; + struct net_device *ndev; int ret; if (vf_netdev->addr_len != ETH_ALEN) return NOTIFY_DONE; - /* - * We will use the MAC address to locate the synthetic interface to - * associate with the VF interface. If we don't find a matching - * synthetic interface, move on. - */ - ndev = get_netvsc_bymac(vf_netdev->perm_addr); + ndev = get_netvsc_byslot(vf_netdev); if (!ndev) return NOTIFY_DONE; @@ -2201,6 +2214,16 @@ static int netvsc_probe(struct hv_device *dev, memcpy(net->dev_addr, device_info.mac_adr, ETH_ALEN); + /* We must get rtnl lock before scheduling nvdev->subchan_work, + * otherwise netvsc_subchan_work() can get rtnl lock first and wait + * all subchannels to show up, but that may not happen because + * netvsc_probe() can't get rtnl lock and as a result vmbus_onoffer() + * -> ... -> device_add() -> ... -> __device_attach() can't get + * the device lock, so all the subchannels can't be processed -- + * finally netvsc_subchan_work() hangs for ever. + */ + rtnl_lock(); + if (nvdev->num_chn > 1) schedule_work(&nvdev->subchan_work); @@ -2219,7 +2242,6 @@ static int netvsc_probe(struct hv_device *dev, else net->max_mtu = ETH_DATA_LEN; - rtnl_lock(); ret = register_netdevice(net); if (ret != 0) { pr_err("Unable to register netdev.\n"); @@ -2258,17 +2280,15 @@ static int netvsc_remove(struct hv_device *dev) cancel_delayed_work_sync(&ndev_ctx->dwork); - rcu_read_lock(); - nvdev = rcu_dereference(ndev_ctx->nvdev); - - if (nvdev) + rtnl_lock(); + nvdev = rtnl_dereference(ndev_ctx->nvdev); + if (nvdev) cancel_work_sync(&nvdev->subchan_work); /* * Call to the vsc driver to let it know that the device is being * removed. Also blocks mtu and channel changes. */ - rtnl_lock(); vf_netdev = rtnl_dereference(ndev_ctx->vf_netdev); if (vf_netdev) netvsc_unregister_vf(vf_netdev); @@ -2280,7 +2300,6 @@ static int netvsc_remove(struct hv_device *dev) list_del(&ndev_ctx->list); rtnl_unlock(); - rcu_read_unlock(); hv_set_drvdata(dev, NULL); diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index 30612497643c..a7207fa7e451 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -59,12 +59,6 @@ #include <net/net_namespace.h> #include <linux/u64_stats_sync.h> -struct pcpu_lstats { - u64 packets; - u64 bytes; - struct u64_stats_sync syncp; -}; - /* The higher levels take care of making this non-reentrant (it's * called with bh's disabled). */ diff --git a/drivers/net/net_failover.c b/drivers/net/net_failover.c index 7ae1856d1f18..e964d312f4ca 100644 --- a/drivers/net/net_failover.c +++ b/drivers/net/net_failover.c @@ -19,7 +19,6 @@ #include <linux/ethtool.h> #include <linux/module.h> #include <linux/slab.h> -#include <linux/netdevice.h> #include <linux/netpoll.h> #include <linux/rtnetlink.h> #include <linux/if_vlan.h> @@ -603,6 +602,9 @@ static int net_failover_slave_unregister(struct net_device *slave_dev, primary_dev = rtnl_dereference(nfo_info->primary_dev); standby_dev = rtnl_dereference(nfo_info->standby_dev); + if (WARN_ON_ONCE(slave_dev != primary_dev && slave_dev != standby_dev)) + return -ENODEV; + vlan_vids_del_by_dev(slave_dev, failover_dev); dev_uc_unsync(slave_dev, failover_dev); dev_mc_unsync(slave_dev, failover_dev); @@ -762,8 +764,10 @@ struct failover *net_failover_create(struct net_device *standby_dev) netif_carrier_off(failover_dev); failover = failover_register(failover_dev, &net_failover_ops); - if (IS_ERR(failover)) + if (IS_ERR(failover)) { + err = PTR_ERR(failover); goto err_failover_register; + } return failover; diff --git a/drivers/net/nlmon.c b/drivers/net/nlmon.c index 4b22955de191..dd0db7534cb3 100644 --- a/drivers/net/nlmon.c +++ b/drivers/net/nlmon.c @@ -6,12 +6,6 @@ #include <linux/if_arp.h> #include <net/rtnetlink.h> -struct pcpu_lstats { - u64 packets; - u64 bytes; - struct u64_stats_sync syncp; -}; - static netdev_tx_t nlmon_xmit(struct sk_buff *skb, struct net_device *dev) { int len = skb->len; diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 82070792edbb..3d187cd50eb0 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -240,7 +240,7 @@ config AT803X_PHY config BCM63XX_PHY tristate "Broadcom 63xx SOCs internal PHY" - depends on BCM63XX + depends on BCM63XX || COMPILE_TEST select BCM_NET_PHYLIB ---help--- Currently supports the 6348 and 6358 PHYs. diff --git a/drivers/net/phy/et1011c.c b/drivers/net/phy/et1011c.c index a9a4edfa23c8..565e49e7f76f 100644 --- a/drivers/net/phy/et1011c.c +++ b/drivers/net/phy/et1011c.c @@ -91,8 +91,7 @@ static struct phy_driver et1011c_driver[] = { { .phy_id = 0x0282f014, .name = "ET1011C", .phy_id_mask = 0xfffffff0, - .features = (PHY_BASIC_FEATURES | SUPPORTED_1000baseT_Full), - .flags = PHY_POLL, + .features = PHY_GBIT_FEATURES, .config_aneg = et1011c_config_aneg, .read_status = et1011c_read_status, } }; diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 98f4b1f706df..2e59a8419b17 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -38,7 +38,6 @@ #include <linux/phy.h> #include <linux/io.h> #include <linux/uaccess.h> -#include <linux/gpio/consumer.h> #include <asm/irq.h> diff --git a/drivers/net/phy/mscc.c b/drivers/net/phy/mscc.c index 84ca9ff40ae0..2d9676d78d3f 100644 --- a/drivers/net/phy/mscc.c +++ b/drivers/net/phy/mscc.c @@ -54,9 +54,9 @@ enum rgmii_rx_clock_delay { #define HP_AUTO_MDIX_X_OVER_IND_MASK 0x2000 #define MSCC_PHY_LED_MODE_SEL 29 -#define LED_1_MODE_SEL_MASK 0x00F0 -#define LED_0_MODE_SEL_MASK 0x000F -#define LED_1_MODE_SEL_POS 4 +#define LED_MODE_SEL_POS(x) ((x) * 4) +#define LED_MODE_SEL_MASK(x) (GENMASK(3, 0) << LED_MODE_SEL_POS(x)) +#define LED_MODE_SEL(x, mode) (((mode) << LED_MODE_SEL_POS(x)) & LED_MODE_SEL_MASK(x)) #define MSCC_EXT_PAGE_ACCESS 31 #define MSCC_PHY_PAGE_STANDARD 0x0000 /* Standard registers */ @@ -103,16 +103,33 @@ enum rgmii_rx_clock_delay { #define DOWNSHIFT_COUNT_MAX 5 +#define MAX_LEDS 4 +#define VSC85XX_SUPP_LED_MODES (BIT(VSC8531_LINK_ACTIVITY) | \ + BIT(VSC8531_LINK_1000_ACTIVITY) | \ + BIT(VSC8531_LINK_100_ACTIVITY) | \ + BIT(VSC8531_LINK_10_ACTIVITY) | \ + BIT(VSC8531_LINK_100_1000_ACTIVITY) | \ + BIT(VSC8531_LINK_10_1000_ACTIVITY) | \ + BIT(VSC8531_LINK_10_100_ACTIVITY) | \ + BIT(VSC8531_DUPLEX_COLLISION) | \ + BIT(VSC8531_COLLISION) | \ + BIT(VSC8531_ACTIVITY) | \ + BIT(VSC8531_AUTONEG_FAULT) | \ + BIT(VSC8531_SERIAL_MODE) | \ + BIT(VSC8531_FORCE_LED_OFF) | \ + BIT(VSC8531_FORCE_LED_ON)) + struct vsc8531_private { int rate_magic; - u8 led_0_mode; - u8 led_1_mode; + u16 supp_led_modes; + u32 leds_mode[MAX_LEDS]; + u8 nleds; }; #ifdef CONFIG_OF_MDIO struct vsc8531_edge_rate_table { - u16 vddmac; - u8 slowdown[8]; + u32 vddmac; + u32 slowdown[8]; }; static const struct vsc8531_edge_rate_table edge_table[] = { @@ -140,14 +157,8 @@ static int vsc85xx_led_cntl_set(struct phy_device *phydev, mutex_lock(&phydev->lock); reg_val = phy_read(phydev, MSCC_PHY_LED_MODE_SEL); - if (led_num) { - reg_val &= ~LED_1_MODE_SEL_MASK; - reg_val |= (((u16)mode << LED_1_MODE_SEL_POS) & - LED_1_MODE_SEL_MASK); - } else { - reg_val &= ~LED_0_MODE_SEL_MASK; - reg_val |= ((u16)mode & LED_0_MODE_SEL_MASK); - } + reg_val &= ~LED_MODE_SEL_MASK(led_num); + reg_val |= LED_MODE_SEL(led_num, (u16)mode); rc = phy_write(phydev, MSCC_PHY_LED_MODE_SEL, reg_val); mutex_unlock(&phydev->lock); @@ -375,8 +386,7 @@ out_unlock: #ifdef CONFIG_OF_MDIO static int vsc85xx_edge_rate_magic_get(struct phy_device *phydev) { - u8 sd; - u16 vdd; + u32 vdd, sd; int rc, i, j; struct device *dev = &phydev->mdio.dev; struct device_node *of_node = dev->of_node; @@ -385,11 +395,11 @@ static int vsc85xx_edge_rate_magic_get(struct phy_device *phydev) if (!of_node) return -ENODEV; - rc = of_property_read_u16(of_node, "vsc8531,vddmac", &vdd); + rc = of_property_read_u32(of_node, "vsc8531,vddmac", &vdd); if (rc != 0) vdd = MSCC_VDDMAC_3300; - rc = of_property_read_u8(of_node, "vsc8531,edge-slowdown", &sd); + rc = of_property_read_u32(of_node, "vsc8531,edge-slowdown", &sd); if (rc != 0) sd = 0; @@ -404,19 +414,20 @@ static int vsc85xx_edge_rate_magic_get(struct phy_device *phydev) static int vsc85xx_dt_led_mode_get(struct phy_device *phydev, char *led, - u8 default_mode) + u32 default_mode) { + struct vsc8531_private *priv = phydev->priv; struct device *dev = &phydev->mdio.dev; struct device_node *of_node = dev->of_node; - u8 led_mode; + u32 led_mode; int err; if (!of_node) return -ENODEV; led_mode = default_mode; - err = of_property_read_u8(of_node, led, &led_mode); - if (!err && (led_mode > 15 || led_mode == 7 || led_mode == 11)) { + err = of_property_read_u32(of_node, led, &led_mode); + if (!err && !(BIT(led_mode) & priv->supp_led_modes)) { phydev_err(phydev, "DT %s invalid\n", led); return -EINVAL; } @@ -438,6 +449,28 @@ static int vsc85xx_dt_led_mode_get(struct phy_device *phydev, } #endif /* CONFIG_OF_MDIO */ +static int vsc85xx_dt_led_modes_get(struct phy_device *phydev, + u32 *default_mode) +{ + struct vsc8531_private *priv = phydev->priv; + char led_dt_prop[19]; + int i, ret; + + for (i = 0; i < priv->nleds; i++) { + ret = sprintf(led_dt_prop, "vsc8531,led-%d-mode", i); + if (ret < 0) + return ret; + + ret = vsc85xx_dt_led_mode_get(phydev, led_dt_prop, + default_mode[i]); + if (ret < 0) + return ret; + priv->leds_mode[i] = ret; + } + + return 0; +} + static int vsc85xx_edge_rate_cntl_set(struct phy_device *phydev, u8 edge_rate) { int rc; @@ -545,7 +578,7 @@ static int vsc85xx_set_tunable(struct phy_device *phydev, static int vsc85xx_config_init(struct phy_device *phydev) { - int rc; + int rc, i; struct vsc8531_private *vsc8531 = phydev->priv; rc = vsc85xx_default_config(phydev); @@ -560,13 +593,11 @@ static int vsc85xx_config_init(struct phy_device *phydev) if (rc) return rc; - rc = vsc85xx_led_cntl_set(phydev, 1, vsc8531->led_1_mode); - if (rc) - return rc; - - rc = vsc85xx_led_cntl_set(phydev, 0, vsc8531->led_0_mode); - if (rc) - return rc; + for (i = 0; i < vsc8531->nleds; i++) { + rc = vsc85xx_led_cntl_set(phydev, i, vsc8531->leds_mode[i]); + if (rc) + return rc; + } rc = genphy_config_init(phydev); @@ -626,7 +657,8 @@ static int vsc85xx_probe(struct phy_device *phydev) { struct vsc8531_private *vsc8531; int rate_magic; - int led_mode; + u32 default_mode[2] = {VSC8531_LINK_1000_ACTIVITY, + VSC8531_LINK_100_ACTIVITY}; rate_magic = vsc85xx_edge_rate_magic_get(phydev); if (rate_magic < 0) @@ -639,21 +671,10 @@ static int vsc85xx_probe(struct phy_device *phydev) phydev->priv = vsc8531; vsc8531->rate_magic = rate_magic; + vsc8531->nleds = 2; + vsc8531->supp_led_modes = VSC85XX_SUPP_LED_MODES; - /* LED[0] and LED[1] mode */ - led_mode = vsc85xx_dt_led_mode_get(phydev, "vsc8531,led-0-mode", - VSC8531_LINK_1000_ACTIVITY); - if (led_mode < 0) - return led_mode; - vsc8531->led_0_mode = led_mode; - - led_mode = vsc85xx_dt_led_mode_get(phydev, "vsc8531,led-1-mode", - VSC8531_LINK_100_ACTIVITY); - if (led_mode < 0) - return led_mode; - vsc8531->led_1_mode = led_mode; - - return 0; + return vsc85xx_dt_led_modes_get(phydev, default_mode); } /* Microsemi VSC85xx PHYs */ diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index db1172db1e7c..af64a9320fb0 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1765,6 +1765,124 @@ int phy_set_max_speed(struct phy_device *phydev, u32 max_speed) } EXPORT_SYMBOL(phy_set_max_speed); +/** + * phy_remove_link_mode - Remove a supported link mode + * @phydev: phy_device structure to remove link mode from + * @link_mode: Link mode to be removed + * + * Description: Some MACs don't support all link modes which the PHY + * does. e.g. a 1G MAC often does not support 1000Half. Add a helper + * to remove a link mode. + */ +void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode) +{ + WARN_ON(link_mode > 31); + + phydev->supported &= ~BIT(link_mode); + phydev->advertising = phydev->supported; +} +EXPORT_SYMBOL(phy_remove_link_mode); + +/** + * phy_support_sym_pause - Enable support of symmetrical pause + * @phydev: target phy_device struct + * + * Description: Called by the MAC to indicate is supports symmetrical + * Pause, but not asym pause. + */ +void phy_support_sym_pause(struct phy_device *phydev) +{ + phydev->supported |= SUPPORTED_Pause; + phydev->advertising = phydev->supported; +} +EXPORT_SYMBOL(phy_support_sym_pause); + +/** + * phy_support_asym_pause - Enable support of asym pause + * @phydev: target phy_device struct + * + * Description: Called by the MAC to indicate is supports Asym Pause. + */ +void phy_support_asym_pause(struct phy_device *phydev) +{ + phydev->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; + phydev->advertising = phydev->supported; +} +EXPORT_SYMBOL(phy_support_asym_pause); + +/** + * phy_set_sym_pause - Configure symmetric Pause + * @phydev: target phy_device struct + * @rx: Receiver Pause is supported + * @tx: Transmit Pause is supported + * @autoneg: Auto neg should be used + * + * Description: Configure advertised Pause support depending on if + * receiver pause and pause auto neg is supported. Generally called + * from the set_pauseparam .ndo. + */ +void phy_set_sym_pause(struct phy_device *phydev, bool rx, bool tx, + bool autoneg) +{ + phydev->supported &= ~SUPPORTED_Pause; + + if (rx && tx && autoneg) + phydev->supported |= SUPPORTED_Pause; + + phydev->advertising = phydev->supported; +} +EXPORT_SYMBOL(phy_set_sym_pause); + +/** + * phy_set_asym_pause - Configure Pause and Asym Pause + * @phydev: target phy_device struct + * @rx: Receiver Pause is supported + * @tx: Transmit Pause is supported + * + * Description: Configure advertised Pause support depending on if + * transmit and receiver pause is supported. If there has been a + * change in adverting, trigger a new autoneg. Generally called from + * the set_pauseparam .ndo. + */ +void phy_set_asym_pause(struct phy_device *phydev, bool rx, bool tx) +{ + u16 oldadv = phydev->advertising; + u16 newadv = oldadv &= ~(SUPPORTED_Pause | SUPPORTED_Asym_Pause); + + if (rx) + newadv |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; + if (tx) + newadv ^= SUPPORTED_Asym_Pause; + + if (oldadv != newadv) { + phydev->advertising = newadv; + + if (phydev->autoneg) + phy_start_aneg(phydev); + } +} +EXPORT_SYMBOL(phy_set_asym_pause); + +/** + * phy_validate_pause - Test if the PHY/MAC support the pause configuration + * @phydev: phy_device struct + * @pp: requested pause configuration + * + * Description: Test if the PHY/MAC combination supports the Pause + * configuration the user is requesting. Returns True if it is + * supported, false otherwise. + */ +bool phy_validate_pause(struct phy_device *phydev, + struct ethtool_pauseparam *pp) +{ + if (!(phydev->supported & SUPPORTED_Pause) || + (!(phydev->supported & SUPPORTED_Asym_Pause) && + pp->rx_pause != pp->tx_pause)) + return false; + return true; +} +EXPORT_SYMBOL(phy_validate_pause); + static void of_set_phy_supported(struct phy_device *phydev) { struct device_node *node = phydev->mdio.dev.of_node; diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index 4637d980310e..52fffb98fde9 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -398,7 +398,6 @@ static umode_t sfp_hwmon_is_visible(const void *data, switch (type) { case hwmon_temp: switch (attr) { - case hwmon_temp_input: case hwmon_temp_min_alarm: case hwmon_temp_max_alarm: case hwmon_temp_lcrit_alarm: @@ -407,13 +406,16 @@ static umode_t sfp_hwmon_is_visible(const void *data, case hwmon_temp_max: case hwmon_temp_lcrit: case hwmon_temp_crit: + if (!(sfp->id.ext.enhopts & SFP_ENHOPTS_ALARMWARN)) + return 0; + /* fall through */ + case hwmon_temp_input: return 0444; default: return 0; } case hwmon_in: switch (attr) { - case hwmon_in_input: case hwmon_in_min_alarm: case hwmon_in_max_alarm: case hwmon_in_lcrit_alarm: @@ -422,13 +424,16 @@ static umode_t sfp_hwmon_is_visible(const void *data, case hwmon_in_max: case hwmon_in_lcrit: case hwmon_in_crit: + if (!(sfp->id.ext.enhopts & SFP_ENHOPTS_ALARMWARN)) + return 0; + /* fall through */ + case hwmon_in_input: return 0444; default: return 0; } case hwmon_curr: switch (attr) { - case hwmon_curr_input: case hwmon_curr_min_alarm: case hwmon_curr_max_alarm: case hwmon_curr_lcrit_alarm: @@ -437,6 +442,10 @@ static umode_t sfp_hwmon_is_visible(const void *data, case hwmon_curr_max: case hwmon_curr_lcrit: case hwmon_curr_crit: + if (!(sfp->id.ext.enhopts & SFP_ENHOPTS_ALARMWARN)) + return 0; + /* fall through */ + case hwmon_curr_input: return 0444; default: return 0; @@ -452,7 +461,6 @@ static umode_t sfp_hwmon_is_visible(const void *data, channel == 1) return 0; switch (attr) { - case hwmon_power_input: case hwmon_power_min_alarm: case hwmon_power_max_alarm: case hwmon_power_lcrit_alarm: @@ -461,6 +469,10 @@ static umode_t sfp_hwmon_is_visible(const void *data, case hwmon_power_max: case hwmon_power_lcrit: case hwmon_power_crit: + if (!(sfp->id.ext.enhopts & SFP_ENHOPTS_ALARMWARN)) + return 0; + /* fall through */ + case hwmon_power_input: return 0444; default: return 0; diff --git a/drivers/net/phy/ste10Xp.c b/drivers/net/phy/ste10Xp.c index fbd548a1ad84..2fe9a87b55b5 100644 --- a/drivers/net/phy/ste10Xp.c +++ b/drivers/net/phy/ste10Xp.c @@ -86,7 +86,7 @@ static struct phy_driver ste10xp_pdriver[] = { .phy_id = STE101P_PHY_ID, .phy_id_mask = 0xfffffff0, .name = "STe101p", - .features = PHY_BASIC_FEATURES | SUPPORTED_Pause, + .features = PHY_BASIC_FEATURES, .flags = PHY_HAS_INTERRUPT, .config_init = ste10Xp_config_init, .ack_interrupt = ste10Xp_ack_interrupt, @@ -97,7 +97,7 @@ static struct phy_driver ste10xp_pdriver[] = { .phy_id = STE100P_PHY_ID, .phy_id_mask = 0xffffffff, .name = "STe100p", - .features = PHY_BASIC_FEATURES | SUPPORTED_Pause, + .features = PHY_BASIC_FEATURES, .flags = PHY_HAS_INTERRUPT, .config_init = ste10Xp_config_init, .ack_interrupt = ste10Xp_ack_interrupt, diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 02ad03a2fab7..500bc0027c1b 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -2400,7 +2400,7 @@ ppp_mp_reconstruct(struct ppp *ppp) if (ppp->mrru == 0) /* do nothing until mrru is set */ return NULL; - head = list->next; + head = __skb_peek(list); tail = NULL; skb_queue_walk_safe(list, p, tmp) { again: diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index ce61231e96ea..62dc564b251d 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -429,6 +429,9 @@ static int pppoe_rcv(struct sk_buff *skb, struct net_device *dev, if (!skb) goto out; + if (skb_mac_header_len(skb) < ETH_HLEN) + goto drop; + if (!pskb_may_pull(skb, sizeof(struct pppoe_hdr))) goto drop; diff --git a/drivers/net/tap.c b/drivers/net/tap.c index f0f7cd977667..a4ab4a791fe7 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -619,7 +619,7 @@ static inline struct sk_buff *tap_alloc_skb(struct sock *sk, size_t prepad, #define TAP_RESERVE HH_DATA_OFF(ETH_HLEN) /* Get packet from user space buffer */ -static ssize_t tap_get_user(struct tap_queue *q, struct msghdr *m, +static ssize_t tap_get_user(struct tap_queue *q, void *msg_control, struct iov_iter *from, int noblock) { int good_linear = SKB_MAX_HEAD(TAP_RESERVE); @@ -663,7 +663,7 @@ static ssize_t tap_get_user(struct tap_queue *q, struct msghdr *m, if (unlikely(len < ETH_HLEN)) goto err; - if (m && m->msg_control && sock_flag(&q->sk, SOCK_ZEROCOPY)) { + if (msg_control && sock_flag(&q->sk, SOCK_ZEROCOPY)) { struct iov_iter i; copylen = vnet_hdr.hdr_len ? @@ -724,11 +724,11 @@ static ssize_t tap_get_user(struct tap_queue *q, struct msghdr *m, tap = rcu_dereference(q->tap); /* copy skb_ubuf_info for callback when skb has no error */ if (zerocopy) { - skb_shinfo(skb)->destructor_arg = m->msg_control; + skb_shinfo(skb)->destructor_arg = msg_control; skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY; skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; - } else if (m && m->msg_control) { - struct ubuf_info *uarg = m->msg_control; + } else if (msg_control) { + struct ubuf_info *uarg = msg_control; uarg->callback(uarg, false); } @@ -1146,11 +1146,87 @@ static const struct file_operations tap_fops = { #endif }; +static int tap_get_user_xdp(struct tap_queue *q, struct xdp_buff *xdp) +{ + struct tun_xdp_hdr *hdr = xdp->data_hard_start; + struct virtio_net_hdr *gso = &hdr->gso; + int buflen = hdr->buflen; + int vnet_hdr_len = 0; + struct tap_dev *tap; + struct sk_buff *skb; + int err, depth; + + if (q->flags & IFF_VNET_HDR) + vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz); + + skb = build_skb(xdp->data_hard_start, buflen); + if (!skb) { + err = -ENOMEM; + goto err; + } + + skb_reserve(skb, xdp->data - xdp->data_hard_start); + skb_put(skb, xdp->data_end - xdp->data); + + skb_set_network_header(skb, ETH_HLEN); + skb_reset_mac_header(skb); + skb->protocol = eth_hdr(skb)->h_proto; + + if (vnet_hdr_len) { + err = virtio_net_hdr_to_skb(skb, gso, tap_is_little_endian(q)); + if (err) + goto err_kfree; + } + + skb_probe_transport_header(skb, ETH_HLEN); + + /* Move network header to the right position for VLAN tagged packets */ + if ((skb->protocol == htons(ETH_P_8021Q) || + skb->protocol == htons(ETH_P_8021AD)) && + __vlan_get_protocol(skb, skb->protocol, &depth) != 0) + skb_set_network_header(skb, depth); + + rcu_read_lock(); + tap = rcu_dereference(q->tap); + if (tap) { + skb->dev = tap->dev; + dev_queue_xmit(skb); + } else { + kfree_skb(skb); + } + rcu_read_unlock(); + + return 0; + +err_kfree: + kfree_skb(skb); +err: + rcu_read_lock(); + tap = rcu_dereference(q->tap); + if (tap && tap->count_tx_dropped) + tap->count_tx_dropped(tap); + rcu_read_unlock(); + return err; +} + static int tap_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) { struct tap_queue *q = container_of(sock, struct tap_queue, sock); - return tap_get_user(q, m, &m->msg_iter, m->msg_flags & MSG_DONTWAIT); + struct tun_msg_ctl *ctl = m->msg_control; + struct xdp_buff *xdp; + int i; + + if (ctl && (ctl->type == TUN_MSG_PTR)) { + for (i = 0; i < ctl->num; i++) { + xdp = &((struct xdp_buff *)ctl->ptr)[i]; + tap_get_user_xdp(q, xdp); + } + return 0; + } + + return tap_get_user(q, ctl ? ctl->ptr : NULL, &m->msg_iter, + m->msg_flags & MSG_DONTWAIT); } static int tap_recvmsg(struct socket *sock, struct msghdr *m, diff --git a/drivers/net/thunderbolt.c b/drivers/net/thunderbolt.c index e0d6760f3219..c48c3a1eb1f8 100644 --- a/drivers/net/thunderbolt.c +++ b/drivers/net/thunderbolt.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Networking over Thunderbolt cable using Apple ThunderboltIP protocol * @@ -5,10 +6,6 @@ * Authors: Amir Levy <amir.jer.levy@intel.com> * Michael Jamet <michael.jamet@intel.com> * Mika Westerberg <mika.westerberg@linux.intel.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. */ #include <linux/atomic.h> diff --git a/drivers/net/tun.c b/drivers/net/tun.c index ebd07ad82431..2a2cd35853b7 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -113,7 +113,6 @@ do { \ } while (0) #endif -#define TUN_HEADROOM 256 #define TUN_RX_PAD (NET_IP_ALIGN + NET_SKB_PAD) /* TUN device flags */ @@ -869,6 +868,9 @@ static int tun_attach(struct tun_struct *tun, struct file *file, tun_napi_init(tun, tfile, napi); } + if (rtnl_dereference(tun->xdp_prog)) + sock_set_flag(&tfile->sk, SOCK_XDP); + tun_set_real_num_queues(tun); /* device is allowed to go away first, so no need to hold extra @@ -1241,13 +1243,29 @@ static int tun_xdp_set(struct net_device *dev, struct bpf_prog *prog, struct netlink_ext_ack *extack) { struct tun_struct *tun = netdev_priv(dev); + struct tun_file *tfile; struct bpf_prog *old_prog; + int i; old_prog = rtnl_dereference(tun->xdp_prog); rcu_assign_pointer(tun->xdp_prog, prog); if (old_prog) bpf_prog_put(old_prog); + for (i = 0; i < tun->numqueues; i++) { + tfile = rtnl_dereference(tun->tfiles[i]); + if (prog) + sock_set_flag(&tfile->sk, SOCK_XDP); + else + sock_reset_flag(&tfile->sk, SOCK_XDP); + } + list_for_each_entry(tfile, &tun->disabled, next) { + if (prog) + sock_set_flag(&tfile->sk, SOCK_XDP); + else + sock_reset_flag(&tfile->sk, SOCK_XDP); + } + return 0; } @@ -1617,6 +1635,55 @@ static bool tun_can_build_skb(struct tun_struct *tun, struct tun_file *tfile, return true; } +static struct sk_buff *__tun_build_skb(struct page_frag *alloc_frag, char *buf, + int buflen, int len, int pad) +{ + struct sk_buff *skb = build_skb(buf, buflen); + + if (!skb) + return ERR_PTR(-ENOMEM); + + skb_reserve(skb, pad); + skb_put(skb, len); + + get_page(alloc_frag->page); + alloc_frag->offset += buflen; + + return skb; +} + +static int tun_xdp_act(struct tun_struct *tun, struct bpf_prog *xdp_prog, + struct xdp_buff *xdp, u32 act) +{ + int err; + + switch (act) { + case XDP_REDIRECT: + err = xdp_do_redirect(tun->dev, xdp, xdp_prog); + if (err) + return err; + break; + case XDP_TX: + err = tun_xdp_tx(tun->dev, xdp); + if (err < 0) + return err; + break; + case XDP_PASS: + break; + default: + bpf_warn_invalid_xdp_action(act); + /* fall through */ + case XDP_ABORTED: + trace_xdp_exception(tun->dev, xdp_prog, act); + /* fall through */ + case XDP_DROP: + this_cpu_inc(tun->pcpu_stats->rx_dropped); + break; + } + + return act; +} + static struct sk_buff *tun_build_skb(struct tun_struct *tun, struct tun_file *tfile, struct iov_iter *from, @@ -1624,18 +1691,17 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun, int len, int *skb_xdp) { struct page_frag *alloc_frag = ¤t->task_frag; - struct sk_buff *skb; struct bpf_prog *xdp_prog; int buflen = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - unsigned int delta = 0; char *buf; size_t copied; - int err, pad = TUN_RX_PAD; + int pad = TUN_RX_PAD; + int err = 0; rcu_read_lock(); xdp_prog = rcu_dereference(tun->xdp_prog); if (xdp_prog) - pad += TUN_HEADROOM; + pad += XDP_PACKET_HEADROOM; buflen += SKB_DATA_ALIGN(len + pad); rcu_read_unlock(); @@ -1654,17 +1720,18 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun, * of xdp_prog above, this should be rare and for simplicity * we do XDP on skb in case the headroom is not enough. */ - if (hdr->gso_type || !xdp_prog) + if (hdr->gso_type || !xdp_prog) { *skb_xdp = 1; - else - *skb_xdp = 0; + return __tun_build_skb(alloc_frag, buf, buflen, len, pad); + } + + *skb_xdp = 0; local_bh_disable(); rcu_read_lock(); xdp_prog = rcu_dereference(tun->xdp_prog); - if (xdp_prog && !*skb_xdp) { + if (xdp_prog) { struct xdp_buff xdp; - void *orig_data; u32 act; xdp.data_hard_start = buf; @@ -1672,66 +1739,33 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun, xdp_set_data_meta_invalid(&xdp); xdp.data_end = xdp.data + len; xdp.rxq = &tfile->xdp_rxq; - orig_data = xdp.data; - act = bpf_prog_run_xdp(xdp_prog, &xdp); - switch (act) { - case XDP_REDIRECT: - get_page(alloc_frag->page); - alloc_frag->offset += buflen; - err = xdp_do_redirect(tun->dev, &xdp, xdp_prog); - xdp_do_flush_map(); - if (err) - goto err_redirect; - rcu_read_unlock(); - local_bh_enable(); - return NULL; - case XDP_TX: + act = bpf_prog_run_xdp(xdp_prog, &xdp); + if (act == XDP_REDIRECT || act == XDP_TX) { get_page(alloc_frag->page); alloc_frag->offset += buflen; - if (tun_xdp_tx(tun->dev, &xdp) < 0) - goto err_redirect; - rcu_read_unlock(); - local_bh_enable(); - return NULL; - case XDP_PASS: - delta = orig_data - xdp.data; - len = xdp.data_end - xdp.data; - break; - default: - bpf_warn_invalid_xdp_action(act); - /* fall through */ - case XDP_ABORTED: - trace_xdp_exception(tun->dev, xdp_prog, act); - /* fall through */ - case XDP_DROP: - goto err_xdp; } - } + err = tun_xdp_act(tun, xdp_prog, &xdp, act); + if (err < 0) + goto err_xdp; + if (err == XDP_REDIRECT) + xdp_do_flush_map(); + if (err != XDP_PASS) + goto out; - skb = build_skb(buf, buflen); - if (!skb) { - rcu_read_unlock(); - local_bh_enable(); - return ERR_PTR(-ENOMEM); + pad = xdp.data - xdp.data_hard_start; + len = xdp.data_end - xdp.data; } - - skb_reserve(skb, pad - delta); - skb_put(skb, len); - get_page(alloc_frag->page); - alloc_frag->offset += buflen; - rcu_read_unlock(); local_bh_enable(); - return skb; + return __tun_build_skb(alloc_frag, buf, buflen, len, pad); -err_redirect: - put_page(alloc_frag->page); err_xdp: + put_page(alloc_frag->page); +out: rcu_read_unlock(); local_bh_enable(); - this_cpu_inc(tun->pcpu_stats->rx_dropped); return NULL; } @@ -2392,18 +2426,133 @@ static void tun_sock_write_space(struct sock *sk) kill_fasync(&tfile->fasync, SIGIO, POLL_OUT); } +static int tun_xdp_one(struct tun_struct *tun, + struct tun_file *tfile, + struct xdp_buff *xdp, int *flush) +{ + struct tun_xdp_hdr *hdr = xdp->data_hard_start; + struct virtio_net_hdr *gso = &hdr->gso; + struct tun_pcpu_stats *stats; + struct bpf_prog *xdp_prog; + struct sk_buff *skb = NULL; + u32 rxhash = 0, act; + int buflen = hdr->buflen; + int err = 0; + bool skb_xdp = false; + + xdp_prog = rcu_dereference(tun->xdp_prog); + if (xdp_prog) { + if (gso->gso_type) { + skb_xdp = true; + goto build; + } + xdp_set_data_meta_invalid(xdp); + xdp->rxq = &tfile->xdp_rxq; + + act = bpf_prog_run_xdp(xdp_prog, xdp); + err = tun_xdp_act(tun, xdp_prog, xdp, act); + if (err < 0) { + put_page(virt_to_head_page(xdp->data)); + return err; + } + + switch (err) { + case XDP_REDIRECT: + *flush = true; + /* fall through */ + case XDP_TX: + return 0; + case XDP_PASS: + break; + default: + put_page(virt_to_head_page(xdp->data)); + return 0; + } + } + +build: + skb = build_skb(xdp->data_hard_start, buflen); + if (!skb) { + err = -ENOMEM; + goto out; + } + + skb_reserve(skb, xdp->data - xdp->data_hard_start); + skb_put(skb, xdp->data_end - xdp->data); + + if (virtio_net_hdr_to_skb(skb, gso, tun_is_little_endian(tun))) { + this_cpu_inc(tun->pcpu_stats->rx_frame_errors); + kfree_skb(skb); + err = -EINVAL; + goto out; + } + + skb->protocol = eth_type_trans(skb, tun->dev); + skb_reset_network_header(skb); + skb_probe_transport_header(skb, 0); + + if (skb_xdp) { + err = do_xdp_generic(xdp_prog, skb); + if (err != XDP_PASS) + goto out; + } + + if (!rcu_dereference(tun->steering_prog)) + rxhash = __skb_get_hash_symmetric(skb); + + netif_receive_skb(skb); + + stats = get_cpu_ptr(tun->pcpu_stats); + u64_stats_update_begin(&stats->syncp); + stats->rx_packets++; + stats->rx_bytes += skb->len; + u64_stats_update_end(&stats->syncp); + put_cpu_ptr(stats); + + if (rxhash) + tun_flow_update(tun, rxhash, tfile); + +out: + return err; +} + static int tun_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) { - int ret; + int ret, i; struct tun_file *tfile = container_of(sock, struct tun_file, socket); struct tun_struct *tun = tun_get(tfile); + struct tun_msg_ctl *ctl = m->msg_control; + struct xdp_buff *xdp; if (!tun) return -EBADFD; - ret = tun_get_user(tun, tfile, m->msg_control, &m->msg_iter, + if (ctl && (ctl->type == TUN_MSG_PTR)) { + int n = ctl->num; + int flush = 0; + + local_bh_disable(); + rcu_read_lock(); + + for (i = 0; i < n; i++) { + xdp = &((struct xdp_buff *)ctl->ptr)[i]; + tun_xdp_one(tun, tfile, xdp, &flush); + } + + if (flush) + xdp_do_flush_map(); + + rcu_read_unlock(); + local_bh_enable(); + + ret = total_len; + goto out; + } + + ret = tun_get_user(tun, tfile, ctl ? ctl->ptr : NULL, &m->msg_iter, m->msg_flags & MSG_DONTWAIT, m->msg_flags & MSG_MORE); +out: tun_put(tun); return ret; } diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index a9991c5f4736..04f0a094d864 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -1,18 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * Copyright (C) 2015 Microchip Technology - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #include <linux/version.h> #include <linux/module.h> @@ -1027,7 +1015,7 @@ done: static void lan78xx_set_addr_filter(struct lan78xx_priv *pdata, int index, u8 addr[ETH_ALEN]) { - u32 temp; + u32 temp; if ((pdata) && (index > 0) && (index < NUM_OF_MAF)) { temp = addr[3]; @@ -1847,8 +1835,7 @@ static int lan78xx_mdio_init(struct lan78xx_net *dev) node = of_get_child_by_name(dev->udev->dev.of_node, "mdio"); ret = of_mdiobus_register(dev->mdiobus, node); - if (node) - of_node_put(node); + of_node_put(node); if (ret) { netdev_err(dev->net, "can't register MDIO bus\n"); goto exit1; @@ -2178,7 +2165,7 @@ static int lan78xx_phy_init(struct lan78xx_net *dev) } /* MAC doesn't support 1000T Half */ - phydev->supported &= ~SUPPORTED_1000baseT_Half; + phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT); /* support both flow controls */ dev->fc_request_control = (FLOW_CTRL_RX | FLOW_CTRL_TX); @@ -2702,7 +2689,7 @@ static void lan78xx_terminate_urbs(struct lan78xx_net *dev) static int lan78xx_stop(struct net_device *net) { - struct lan78xx_net *dev = netdev_priv(net); + struct lan78xx_net *dev = netdev_priv(net); if (timer_pending(&dev->stat_monitor)) del_timer_sync(&dev->stat_monitor); @@ -2952,6 +2939,11 @@ static int lan78xx_bind(struct lan78xx_net *dev, struct usb_interface *intf) int i; ret = lan78xx_get_endpoints(dev, intf); + if (ret) { + netdev_warn(dev->net, "lan78xx_get_endpoints failed: %d\n", + ret); + return ret; + } dev->data[0] = (unsigned long)kzalloc(sizeof(*pdata), GFP_KERNEL); @@ -3080,7 +3072,7 @@ static void lan78xx_rx_vlan_offload(struct lan78xx_net *dev, static void lan78xx_skb_return(struct lan78xx_net *dev, struct sk_buff *skb) { - int status; + int status; if (test_bit(EVENT_RX_PAUSED, &dev->flags)) { skb_queue_tail(&dev->rxq_pause, skb); @@ -3347,9 +3339,9 @@ static void lan78xx_tx_bh(struct lan78xx_net *dev) count = 0; length = 0; spin_lock_irqsave(&tqp->lock, flags); - for (skb = tqp->next; pkt_cnt < tqp->qlen; skb = skb->next) { + skb_queue_walk(tqp, skb) { if (skb_is_gso(skb)) { - if (pkt_cnt) { + if (!skb_queue_is_first(tqp, skb)) { /* handle previous packets first */ break; } @@ -3640,10 +3632,10 @@ static void intr_complete(struct urb *urb) static void lan78xx_disconnect(struct usb_interface *intf) { - struct lan78xx_net *dev; - struct usb_device *udev; - struct net_device *net; - struct phy_device *phydev; + struct lan78xx_net *dev; + struct usb_device *udev; + struct net_device *net; + struct phy_device *phydev; dev = usb_get_intfdata(intf); usb_set_intfdata(intf, NULL); @@ -3761,7 +3753,6 @@ static int lan78xx_probe(struct usb_interface *intf, ret = lan78xx_bind(dev, intf); if (ret < 0) goto out2; - strcpy(netdev->name, "eth%d"); if (netdev->mtu > (dev->hard_mtu - netdev->hard_header_len)) netdev->mtu = dev->hard_mtu - netdev->hard_header_len; diff --git a/drivers/net/usb/lan78xx.h b/drivers/net/usb/lan78xx.h index 25aa54611774..968e5e5faee0 100644 --- a/drivers/net/usb/lan78xx.h +++ b/drivers/net/usb/lan78xx.h @@ -1,18 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * Copyright (C) 2015 Microchip Technology - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version 2 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, see <http://www.gnu.org/licenses/>. */ #ifndef _LAN78XX_H #define _LAN78XX_H diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index cb0cc30c3d6a..533b6fb8d923 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -967,6 +967,13 @@ static const struct usb_device_id products[] = { USB_DEVICE_AND_INTERFACE_INFO(0x03f0, 0x581d, USB_CLASS_VENDOR_SPEC, 1, 7), .driver_info = (unsigned long)&qmi_wwan_info, }, + { /* Quectel EP06/EG06/EM06 */ + USB_DEVICE_AND_INTERFACE_INFO(0x2c7c, 0x0306, + USB_CLASS_VENDOR_SPEC, + USB_SUBCLASS_VENDOR_SPEC, + 0xff), + .driver_info = (unsigned long)&qmi_wwan_info_quirk_dtr, + }, /* 3. Combined interface devices matching on interface number */ {QMI_FIXED_INTF(0x0408, 0xea42, 4)}, /* Yota / Megafon M100-1 */ @@ -1206,13 +1213,13 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x1199, 0x9061, 8)}, /* Sierra Wireless Modem */ {QMI_FIXED_INTF(0x1199, 0x9063, 8)}, /* Sierra Wireless EM7305 */ {QMI_FIXED_INTF(0x1199, 0x9063, 10)}, /* Sierra Wireless EM7305 */ - {QMI_FIXED_INTF(0x1199, 0x9071, 8)}, /* Sierra Wireless MC74xx */ - {QMI_FIXED_INTF(0x1199, 0x9071, 10)}, /* Sierra Wireless MC74xx */ - {QMI_FIXED_INTF(0x1199, 0x9079, 8)}, /* Sierra Wireless EM74xx */ - {QMI_FIXED_INTF(0x1199, 0x9079, 10)}, /* Sierra Wireless EM74xx */ - {QMI_FIXED_INTF(0x1199, 0x907b, 8)}, /* Sierra Wireless EM74xx */ - {QMI_FIXED_INTF(0x1199, 0x907b, 10)}, /* Sierra Wireless EM74xx */ - {QMI_FIXED_INTF(0x1199, 0x9091, 8)}, /* Sierra Wireless EM7565 */ + {QMI_QUIRK_SET_DTR(0x1199, 0x9071, 8)}, /* Sierra Wireless MC74xx */ + {QMI_QUIRK_SET_DTR(0x1199, 0x9071, 10)},/* Sierra Wireless MC74xx */ + {QMI_QUIRK_SET_DTR(0x1199, 0x9079, 8)}, /* Sierra Wireless EM74xx */ + {QMI_QUIRK_SET_DTR(0x1199, 0x9079, 10)},/* Sierra Wireless EM74xx */ + {QMI_QUIRK_SET_DTR(0x1199, 0x907b, 8)}, /* Sierra Wireless EM74xx */ + {QMI_QUIRK_SET_DTR(0x1199, 0x907b, 10)},/* Sierra Wireless EM74xx */ + {QMI_QUIRK_SET_DTR(0x1199, 0x9091, 8)}, /* Sierra Wireless EM7565 */ {QMI_FIXED_INTF(0x1bbb, 0x011e, 4)}, /* Telekom Speedstick LTE II (Alcatel One Touch L100V LTE) */ {QMI_FIXED_INTF(0x1bbb, 0x0203, 2)}, /* Alcatel L800MA */ {QMI_FIXED_INTF(0x2357, 0x0201, 4)}, /* TP-LINK HSUPA Modem MA180 */ @@ -1255,7 +1262,6 @@ static const struct usb_device_id products[] = { {QMI_QUIRK_SET_DTR(0x2c7c, 0x0121, 4)}, /* Quectel EC21 Mini PCIe */ {QMI_QUIRK_SET_DTR(0x2c7c, 0x0191, 4)}, /* Quectel EG91 */ {QMI_FIXED_INTF(0x2c7c, 0x0296, 4)}, /* Quectel BG96 */ - {QMI_QUIRK_SET_DTR(0x2c7c, 0x0306, 4)}, /* Quectel EP06 Mini PCIe */ /* 4. Gobi 1000 devices */ {QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */ @@ -1331,6 +1337,19 @@ static bool quectel_ec20_detected(struct usb_interface *intf) return false; } +static bool quectel_ep06_diag_detected(struct usb_interface *intf) +{ + struct usb_device *dev = interface_to_usbdev(intf); + struct usb_interface_descriptor intf_desc = intf->cur_altsetting->desc; + + if (le16_to_cpu(dev->descriptor.idVendor) == 0x2c7c && + le16_to_cpu(dev->descriptor.idProduct) == 0x0306 && + intf_desc.bNumEndpoints == 2) + return true; + + return false; +} + static int qmi_wwan_probe(struct usb_interface *intf, const struct usb_device_id *prod) { @@ -1365,6 +1384,15 @@ static int qmi_wwan_probe(struct usb_interface *intf, return -ENODEV; } + /* Quectel EP06/EM06/EG06 supports dynamic interface configuration, so + * we need to match on class/subclass/protocol. These values are + * identical for the diagnostic- and QMI-interface, but bNumEndpoints is + * different. Ignore the current interface if the number of endpoints + * the number for the diag interface (two). + */ + if (quectel_ep06_diag_detected(intf)) + return -ENODEV; + return usbnet_probe(intf, id); } diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 97742708460b..2cd71bdb6484 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -5217,8 +5217,8 @@ static int rtl8152_probe(struct usb_interface *intf, netdev->hw_features &= ~NETIF_F_RXCSUM; } - if (le16_to_cpu(udev->descriptor.bcdDevice) == 0x3011 && - udev->serial && !strcmp(udev->serial, "000001000000")) { + if (le16_to_cpu(udev->descriptor.bcdDevice) == 0x3011 && udev->serial && + (!strcmp(udev->serial, "000001000000") || !strcmp(udev->serial, "000002000000"))) { dev_info(&udev->dev, "Dell TB16 Dock, disable RX aggregation"); set_bit(DELL_TB_RX_AGG_BUG, &tp->flags); } diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 770aa624147f..73aa33364d80 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1527,6 +1527,7 @@ static void usbnet_bh (struct timer_list *t) continue; case tx_done: kfree(entry->urb->sg); + /* fall through */ case rx_cleanup: usb_free_urb (entry->urb); dev_kfree_skb (skb); diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 8d679c8b7f25..224c56a4e2b1 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -24,6 +24,7 @@ #include <linux/filter.h> #include <linux/ptr_ring.h> #include <linux/bpf_trace.h> +#include <linux/net_tstamp.h> #define DRV_NAME "veth" #define DRV_VERSION "1.0" @@ -36,12 +37,6 @@ #define VETH_XDP_TX BIT(0) #define VETH_XDP_REDIR BIT(1) -struct pcpu_vstats { - u64 packets; - u64 bytes; - struct u64_stats_sync syncp; -}; - struct veth_rq { struct napi_struct xdp_napi; struct net_device *dev; @@ -114,6 +109,18 @@ static void veth_get_ethtool_stats(struct net_device *dev, data[0] = peer ? peer->ifindex : 0; } +static int veth_get_ts_info(struct net_device *dev, + struct ethtool_ts_info *info) +{ + info->so_timestamping = + SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE; + info->phc_index = -1; + + return 0; +} + static const struct ethtool_ops veth_ethtool_ops = { .get_drvinfo = veth_get_drvinfo, .get_link = ethtool_op_get_link, @@ -121,6 +128,7 @@ static const struct ethtool_ops veth_ethtool_ops = { .get_sset_count = veth_get_sset_count, .get_ethtool_stats = veth_get_ethtool_stats, .get_link_ksettings = veth_get_link_ksettings, + .get_ts_info = veth_get_ts_info, }; /* general routines */ @@ -201,8 +209,9 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev) skb_record_rx_queue(skb, rxq); } + skb_tx_timestamp(skb); if (likely(veth_forward_skb(rcv, skb, rq, rcv_xdp) == NET_RX_SUCCESS)) { - struct pcpu_vstats *stats = this_cpu_ptr(dev->vstats); + struct pcpu_lstats *stats = this_cpu_ptr(dev->lstats); u64_stats_update_begin(&stats->syncp); stats->bytes += length; @@ -221,7 +230,7 @@ drop: return NETDEV_TX_OK; } -static u64 veth_stats_one(struct pcpu_vstats *result, struct net_device *dev) +static u64 veth_stats_one(struct pcpu_lstats *result, struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); int cpu; @@ -229,7 +238,7 @@ static u64 veth_stats_one(struct pcpu_vstats *result, struct net_device *dev) result->packets = 0; result->bytes = 0; for_each_possible_cpu(cpu) { - struct pcpu_vstats *stats = per_cpu_ptr(dev->vstats, cpu); + struct pcpu_lstats *stats = per_cpu_ptr(dev->lstats, cpu); u64 packets, bytes; unsigned int start; @@ -249,7 +258,7 @@ static void veth_get_stats64(struct net_device *dev, { struct veth_priv *priv = netdev_priv(dev); struct net_device *peer; - struct pcpu_vstats one; + struct pcpu_lstats one; tot->tx_dropped = veth_stats_one(&one, dev); tot->tx_bytes = one.bytes; @@ -463,6 +472,8 @@ static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq, struct sk_buff *skb, int mac_len, delta, off; struct xdp_buff xdp; + skb_orphan(skb); + rcu_read_lock(); xdp_prog = rcu_dereference(rq->xdp_prog); if (unlikely(!xdp_prog)) { @@ -508,8 +519,6 @@ static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq, struct sk_buff *skb, skb_copy_header(nskb, skb); head_off = skb_headroom(nskb) - skb_headroom(skb); skb_headers_offset_update(nskb, head_off); - if (skb->sk) - skb_set_owner_w(nskb, skb->sk); consume_skb(skb); skb = nskb; } @@ -815,13 +824,13 @@ static int veth_dev_init(struct net_device *dev) { int err; - dev->vstats = netdev_alloc_pcpu_stats(struct pcpu_vstats); - if (!dev->vstats) + dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats); + if (!dev->lstats) return -ENOMEM; err = veth_alloc_queues(dev); if (err) { - free_percpu(dev->vstats); + free_percpu(dev->lstats); return err; } @@ -831,7 +840,7 @@ static int veth_dev_init(struct net_device *dev) static void veth_dev_free(struct net_device *dev) { veth_free_queues(dev); - free_percpu(dev->vstats); + free_percpu(dev->lstats); } #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/vsockmon.c b/drivers/net/vsockmon.c index c28bdce14fd5..7bad5c95551f 100644 --- a/drivers/net/vsockmon.c +++ b/drivers/net/vsockmon.c @@ -11,12 +11,6 @@ #define DEFAULT_MTU (VIRTIO_VSOCK_MAX_PKT_BUF_SIZE + \ sizeof(struct af_vsockmon_hdr)) -struct pcpu_lstats { - u64 rx_packets; - u64 rx_bytes; - struct u64_stats_sync syncp; -}; - static int vsockmon_dev_init(struct net_device *dev) { dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats); @@ -56,8 +50,8 @@ static netdev_tx_t vsockmon_xmit(struct sk_buff *skb, struct net_device *dev) struct pcpu_lstats *stats = this_cpu_ptr(dev->lstats); u64_stats_update_begin(&stats->syncp); - stats->rx_bytes += len; - stats->rx_packets++; + stats->bytes += len; + stats->packets++; u64_stats_update_end(&stats->syncp); dev_kfree_skb(skb); @@ -80,8 +74,8 @@ vsockmon_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) do { start = u64_stats_fetch_begin_irq(&vstats->syncp); - tbytes = vstats->rx_bytes; - tpackets = vstats->rx_packets; + tbytes = vstats->bytes; + tpackets = vstats->packets; } while (u64_stats_fetch_retry_irq(&vstats->syncp, start)); packets += tpackets; diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index ababba37d735..e5d236595206 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -464,7 +464,7 @@ static struct vxlan_fdb *vxlan_find_mac(struct vxlan_dev *vxlan, struct vxlan_fdb *f; f = __vxlan_find_mac(vxlan, mac, vni); - if (f) + if (f && f->used != jiffies) f->used = jiffies; return f; diff --git a/drivers/net/wan/c101.c b/drivers/net/wan/c101.c index 2371e078afbb..91dbbde3c35b 100644 --- a/drivers/net/wan/c101.c +++ b/drivers/net/wan/c101.c @@ -24,7 +24,6 @@ #include <linux/string.h> #include <linux/errno.h> #include <linux/init.h> -#include <linux/moduleparam.h> #include <linux/netdevice.h> #include <linux/hdlc.h> #include <linux/delay.h> diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c index 5f0366a125e2..8523ade16030 100644 --- a/drivers/net/wan/fsl_ucc_hdlc.c +++ b/drivers/net/wan/fsl_ucc_hdlc.c @@ -97,6 +97,12 @@ static int uhdlc_init(struct ucc_hdlc_private *priv) if (priv->tsa) { uf_info->tsa = 1; uf_info->ctsp = 1; + uf_info->cds = 1; + uf_info->ctss = 1; + } else { + uf_info->cds = 0; + uf_info->ctsp = 0; + uf_info->ctss = 0; } /* This sets HPM register in CMXUCR register which configures a @@ -265,7 +271,7 @@ static int uhdlc_init(struct ucc_hdlc_private *priv) iowrite16be(MAX_FRAME_LENGTH, &priv->ucc_pram->mflr); iowrite16be(DEFAULT_RFTHR, &priv->ucc_pram->rfthr); iowrite16be(DEFAULT_RFTHR, &priv->ucc_pram->rfcnt); - iowrite16be(DEFAULT_ADDR_MASK, &priv->ucc_pram->hmask); + iowrite16be(priv->hmask, &priv->ucc_pram->hmask); iowrite16be(DEFAULT_HDLC_ADDR, &priv->ucc_pram->haddr1); iowrite16be(DEFAULT_HDLC_ADDR, &priv->ucc_pram->haddr2); iowrite16be(DEFAULT_HDLC_ADDR, &priv->ucc_pram->haddr3); @@ -375,6 +381,10 @@ static netdev_tx_t ucc_hdlc_tx(struct sk_buff *skb, struct net_device *dev) dev->stats.tx_bytes += skb->len; break; + case ARPHRD_ETHER: + dev->stats.tx_bytes += skb->len; + break; + default: dev->stats.tx_dropped++; dev_kfree_skb(skb); @@ -512,6 +522,7 @@ static int hdlc_rx_done(struct ucc_hdlc_private *priv, int rx_work_limit) break; case ARPHRD_PPP: + case ARPHRD_ETHER: length -= HDLC_CRC_SIZE; skb = dev_alloc_skb(length); @@ -780,6 +791,7 @@ static int ucc_hdlc_attach(struct net_device *dev, unsigned short encoding, if (parity != PARITY_NONE && parity != PARITY_CRC32_PR1_CCITT && + parity != PARITY_CRC16_PR0_CCITT && parity != PARITY_CRC16_PR1_CCITT) return -EINVAL; @@ -987,11 +999,17 @@ static const struct dev_pm_ops uhdlc_pm_ops = { #define HDLC_PM_OPS NULL #endif +static void uhdlc_tx_timeout(struct net_device *ndev) +{ + netdev_err(ndev, "%s\n", __func__); +} + static const struct net_device_ops uhdlc_ops = { .ndo_open = uhdlc_open, .ndo_stop = uhdlc_close, .ndo_start_xmit = hdlc_start_xmit, .ndo_do_ioctl = uhdlc_ioctl, + .ndo_tx_timeout = uhdlc_tx_timeout, }; static int ucc_hdlc_probe(struct platform_device *pdev) @@ -1015,7 +1033,7 @@ static int ucc_hdlc_probe(struct platform_device *pdev) } ucc_num = val - 1; - if ((ucc_num > 3) || (ucc_num < 0)) { + if (ucc_num > (UCC_MAX_NUM - 1) || ucc_num < 0) { dev_err(&pdev->dev, ": Invalid UCC num\n"); return -EINVAL; } @@ -1090,6 +1108,9 @@ static int ucc_hdlc_probe(struct platform_device *pdev) goto free_utdm; } + if (of_property_read_u16(np, "fsl,hmask", &uhdlc_priv->hmask)) + uhdlc_priv->hmask = DEFAULT_ADDR_MASK; + ret = uhdlc_init(uhdlc_priv); if (ret) { dev_err(&pdev->dev, "Failed to init uhdlc\n"); @@ -1107,6 +1128,7 @@ static int ucc_hdlc_probe(struct platform_device *pdev) hdlc = dev_to_hdlc(dev); dev->tx_queue_len = 16; dev->netdev_ops = &uhdlc_ops; + dev->watchdog_timeo = 2 * HZ; hdlc->attach = ucc_hdlc_attach; hdlc->xmit = ucc_hdlc_tx; netif_napi_add(dev, &uhdlc_priv->napi, ucc_hdlc_poll, 32); diff --git a/drivers/net/wan/fsl_ucc_hdlc.h b/drivers/net/wan/fsl_ucc_hdlc.h index c21134c1f180..b99fa2f1cd99 100644 --- a/drivers/net/wan/fsl_ucc_hdlc.h +++ b/drivers/net/wan/fsl_ucc_hdlc.h @@ -106,6 +106,7 @@ struct ucc_hdlc_private { unsigned short encoding; unsigned short parity; + unsigned short hmask; u32 clocking; spinlock_t lock; /* lock for Tx BD and Tx buffer */ #ifdef CONFIG_PM diff --git a/drivers/net/wan/pci200syn.c b/drivers/net/wan/pci200syn.c index 4e437c599e9a..1f8a3f77a7b9 100644 --- a/drivers/net/wan/pci200syn.c +++ b/drivers/net/wan/pci200syn.c @@ -27,7 +27,6 @@ #include <linux/errno.h> #include <linux/init.h> #include <linux/ioport.h> -#include <linux/moduleparam.h> #include <linux/netdevice.h> #include <linux/hdlc.h> #include <linux/pci.h> diff --git a/drivers/net/wireless/ath/wil6210/debugfs.c b/drivers/net/wireless/ath/wil6210/debugfs.c index 51c3330bc316..49533f884993 100644 --- a/drivers/net/wireless/ath/wil6210/debugfs.c +++ b/drivers/net/wireless/ath/wil6210/debugfs.c @@ -1436,7 +1436,7 @@ static int wil_freq_debugfs_show(struct seq_file *s, void *data) { struct wil6210_priv *wil = s->private; struct wireless_dev *wdev = wil->main_ndev->ieee80211_ptr; - u16 freq = wdev->chandef.chan ? wdev->chandef.chan->center_freq : 0; + u32 freq = wdev->chandef.chan ? wdev->chandef.chan->center_freq : 0; seq_printf(s, "Freq = %d\n", freq); diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c index d2f788d88668..3e37c8cf82c6 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c @@ -576,7 +576,7 @@ int brcmf_sdiod_recv_chain(struct brcmf_sdio_dev *sdiodev, if (pktq->qlen == 1) err = brcmf_sdiod_skbuff_read(sdiodev, sdiodev->func2, addr, - pktq->next); + __skb_peek(pktq)); else if (!sdiodev->sg_support) { glom_skb = brcmu_pkt_buf_get_skb(totlen); if (!glom_skb) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c index a907d7b065fa..1e2fd289323a 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c @@ -2189,7 +2189,7 @@ brcmf_sdio_txpkt_prep(struct brcmf_sdio *bus, struct sk_buff_head *pktq, * length of the chain (including padding) */ if (bus->txglom) - brcmf_sdio_update_hwhdr(pktq->next->data, total_len); + brcmf_sdio_update_hwhdr(__skb_peek(pktq)->data, total_len); return 0; } diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c index b4c3a957c102..27db4a3ba1f8 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c @@ -476,30 +476,40 @@ static struct ieee80211_sband_iftype_data iwl_he_capa = { .has_he = true, .he_cap_elem = { .mac_cap_info[0] = - IEEE80211_HE_MAC_CAP0_HTC_HE, + IEEE80211_HE_MAC_CAP0_HTC_HE | + IEEE80211_HE_MAC_CAP0_TWT_REQ, .mac_cap_info[1] = IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US | - IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_8, + IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8, .mac_cap_info[2] = IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP | + IEEE80211_HE_MAC_CAP2_MU_CASCADING | IEEE80211_HE_MAC_CAP2_ACK_EN, .mac_cap_info[3] = - IEEE80211_HE_MAC_CAP3_GRP_ADDR_MULTI_STA_BA_DL_MU | - IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_VHT_2, - .mac_cap_info[4] = IEEE80211_HE_MAC_CAP4_AMDSU_IN_AMPDU, + IEEE80211_HE_MAC_CAP3_OMI_CONTROL | + IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_VHT_2, + .mac_cap_info[4] = + IEEE80211_HE_MAC_CAP4_AMDSU_IN_AMPDU | + IEEE80211_HE_MAC_CAP4_MULTI_TID_AGG_TX_QOS_B39, + .mac_cap_info[5] = + IEEE80211_HE_MAC_CAP5_MULTI_TID_AGG_TX_QOS_B40 | + IEEE80211_HE_MAC_CAP5_MULTI_TID_AGG_TX_QOS_B41 | + IEEE80211_HE_MAC_CAP5_UL_2x996_TONE_RU, .phy_cap_info[0] = - IEEE80211_HE_PHY_CAP0_DUAL_BAND | IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G | IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G | IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G, .phy_cap_info[1] = + IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK | IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A | IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD | - IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_MAX_NSTS, + IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS, .phy_cap_info[2] = IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US | IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ | - IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ, + IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ | + IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO | + IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO, .phy_cap_info[3] = IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_BPSK | IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_1 | @@ -511,18 +521,31 @@ static struct ieee80211_sband_iftype_data iwl_he_capa = { IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_8, .phy_cap_info[5] = IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_2 | - IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_2, + IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_2 | + IEEE80211_HE_PHY_CAP5_NG16_SU_FEEDBACK | + IEEE80211_HE_PHY_CAP5_NG16_MU_FEEDBACK, .phy_cap_info[6] = + IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_42_SU | + IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_75_MU | + IEEE80211_HE_PHY_CAP6_TRIG_SU_BEAMFORMER_FB | + IEEE80211_HE_PHY_CAP6_TRIG_MU_BEAMFORMER_FB | + IEEE80211_HE_PHY_CAP6_TRIG_CQI_FB | + IEEE80211_HE_PHY_CAP6_PARTIAL_BANDWIDTH_DL_MUMIMO | IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT, .phy_cap_info[7] = IEEE80211_HE_PHY_CAP7_POWER_BOOST_FACTOR_AR | IEEE80211_HE_PHY_CAP7_HE_SU_MU_PPDU_4XLTF_AND_08_US_GI | - IEEE80211_HE_PHY_CAP7_MAX_NC_7, + IEEE80211_HE_PHY_CAP7_MAX_NC_1, .phy_cap_info[8] = IEEE80211_HE_PHY_CAP8_HE_ER_SU_PPDU_4XLTF_AND_08_US_GI | IEEE80211_HE_PHY_CAP8_20MHZ_IN_40MHZ_HE_PPDU_IN_2G | IEEE80211_HE_PHY_CAP8_20MHZ_IN_160MHZ_HE_PPDU | - IEEE80211_HE_PHY_CAP8_80MHZ_IN_160MHZ_HE_PPDU, + IEEE80211_HE_PHY_CAP8_80MHZ_IN_160MHZ_HE_PPDU | + IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_160_OR_80P80_MHZ, + .phy_cap_info[9] = + IEEE80211_HE_PHY_CAP9_NON_TRIGGERED_CQI_FEEDBACK | + IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_COMP_SIGB | + IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_NON_COMP_SIGB, }, /* * Set default Tx/Rx HE MCS NSS Support field. Indicate support @@ -559,9 +582,11 @@ static void iwl_init_he_hw_capab(struct ieee80211_supported_band *sband, /* If not 2x2, we need to indicate 1x1 in the Midamble RX Max NSTS */ if ((tx_chains & rx_chains) != ANT_AB) { iwl_he_capa.he_cap.he_cap_elem.phy_cap_info[1] &= - ~IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_MAX_NSTS; + ~IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS; iwl_he_capa.he_cap.he_cap_elem.phy_cap_info[2] &= - ~IEEE80211_HE_PHY_CAP2_MIDAMBLE_RX_MAX_NSTS; + ~IEEE80211_HE_PHY_CAP2_MIDAMBLE_RX_TX_MAX_NSTS; + iwl_he_capa.he_cap.he_cap_elem.phy_cap_info[7] &= + ~IEEE80211_HE_PHY_CAP7_MAX_NC_MASK; } } @@ -985,15 +1010,12 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg, const u8 *nvm_chan = cfg->nvm_type == IWL_NVM_EXT ? iwl_ext_nvm_channels : iwl_nvm_channels; struct ieee80211_regdomain *regd, *copy_rd; - int size_of_regd, regd_to_copy, wmms_to_copy; - int size_of_wmms = 0; + int size_of_regd, regd_to_copy; struct ieee80211_reg_rule *rule; - struct ieee80211_wmm_rule *wmm_rule, *d_wmm, *s_wmm; struct regdb_ptrs *regdb_ptrs; enum nl80211_band band; int center_freq, prev_center_freq = 0; - int valid_rules = 0, n_wmms = 0; - int i; + int valid_rules = 0; bool new_rule; int max_num_ch = cfg->nvm_type == IWL_NVM_EXT ? IWL_NVM_NUM_CHANNELS_EXT : IWL_NVM_NUM_CHANNELS; @@ -1012,11 +1034,7 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg, sizeof(struct ieee80211_regdomain) + num_of_ch * sizeof(struct ieee80211_reg_rule); - if (geo_info & GEO_WMM_ETSI_5GHZ_INFO) - size_of_wmms = - num_of_ch * sizeof(struct ieee80211_wmm_rule); - - regd = kzalloc(size_of_regd + size_of_wmms, GFP_KERNEL); + regd = kzalloc(size_of_regd, GFP_KERNEL); if (!regd) return ERR_PTR(-ENOMEM); @@ -1030,8 +1048,6 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg, regd->alpha2[0] = fw_mcc >> 8; regd->alpha2[1] = fw_mcc & 0xff; - wmm_rule = (struct ieee80211_wmm_rule *)((u8 *)regd + size_of_regd); - for (ch_idx = 0; ch_idx < num_of_ch; ch_idx++) { ch_flags = (u16)__le32_to_cpup(channels + ch_idx); band = (ch_idx < NUM_2GHZ_CHANNELS) ? @@ -1085,26 +1101,10 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg, band == NL80211_BAND_2GHZ) continue; - if (!reg_query_regdb_wmm(regd->alpha2, center_freq, - ®db_ptrs[n_wmms].token, wmm_rule)) { - /* Add only new rules */ - for (i = 0; i < n_wmms; i++) { - if (regdb_ptrs[i].token == - regdb_ptrs[n_wmms].token) { - rule->wmm_rule = regdb_ptrs[i].rule; - break; - } - } - if (i == n_wmms) { - rule->wmm_rule = wmm_rule; - regdb_ptrs[n_wmms++].rule = wmm_rule; - wmm_rule++; - } - } + reg_query_regdb_wmm(regd->alpha2, center_freq, rule); } regd->n_reg_rules = valid_rules; - regd->n_wmm_rules = n_wmms; /* * Narrow down regdom for unused regulatory rules to prevent hole @@ -1113,28 +1113,13 @@ iwl_parse_nvm_mcc_info(struct device *dev, const struct iwl_cfg *cfg, regd_to_copy = sizeof(struct ieee80211_regdomain) + valid_rules * sizeof(struct ieee80211_reg_rule); - wmms_to_copy = sizeof(struct ieee80211_wmm_rule) * n_wmms; - - copy_rd = kzalloc(regd_to_copy + wmms_to_copy, GFP_KERNEL); + copy_rd = kzalloc(regd_to_copy, GFP_KERNEL); if (!copy_rd) { copy_rd = ERR_PTR(-ENOMEM); goto out; } memcpy(copy_rd, regd, regd_to_copy); - memcpy((u8 *)copy_rd + regd_to_copy, (u8 *)regd + size_of_regd, - wmms_to_copy); - - d_wmm = (struct ieee80211_wmm_rule *)((u8 *)copy_rd + regd_to_copy); - s_wmm = (struct ieee80211_wmm_rule *)((u8 *)regd + size_of_regd); - - for (i = 0; i < regd->n_reg_rules; i++) { - if (!regd->reg_rules[i].wmm_rule) - continue; - - copy_rd->reg_rules[i].wmm_rule = d_wmm + - (regd->reg_rules[i].wmm_rule - s_wmm); - } out: kfree(regdb_ptrs); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index b15b0d84bb7e..d46f3fbea46e 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -1978,10 +1978,6 @@ static void iwl_mvm_cfg_he_sta(struct iwl_mvm *mvm, sta_ctxt_cmd.htc_flags |= cpu_to_le32(IWL_HE_HTC_LINK_ADAP_BOTH); } - if (sta->he_cap.he_cap_elem.mac_cap_info[2] & - IEEE80211_HE_MAC_CAP2_UL_MU_RESP_SCHED) - sta_ctxt_cmd.htc_flags |= - cpu_to_le32(IWL_HE_HTC_UL_MU_RESP_SCHED); if (sta->he_cap.he_cap_elem.mac_cap_info[2] & IEEE80211_HE_MAC_CAP2_BSR) sta_ctxt_cmd.htc_flags |= cpu_to_le32(IWL_HE_HTC_BSR_SUPP); if (sta->he_cap.he_cap_elem.mac_cap_info[3] & diff --git a/drivers/net/wireless/intersil/p54/txrx.c b/drivers/net/wireless/intersil/p54/txrx.c index 3a4214d362ff..790784568ad2 100644 --- a/drivers/net/wireless/intersil/p54/txrx.c +++ b/drivers/net/wireless/intersil/p54/txrx.c @@ -121,8 +121,8 @@ static int p54_assign_address(struct p54_common *priv, struct sk_buff *skb) } if (unlikely(!target_skb)) { if (priv->rx_end - last_addr >= len) { - target_skb = priv->tx_queue.prev; - if (!skb_queue_empty(&priv->tx_queue)) { + target_skb = skb_peek_tail(&priv->tx_queue); + if (target_skb) { info = IEEE80211_SKB_CB(target_skb); range = (void *)info->rate_driver_data; target_addr = range->end_addr; diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 998dfac0fcff..f3863101af78 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -3,6 +3,7 @@ * Copyright (c) 2008, Jouni Malinen <j@w1.fi> * Copyright (c) 2011, Javier Lopez <jlopex@gmail.com> * Copyright (c) 2016 - 2017 Intel Deutschland GmbH + * Copyright (C) 2018 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -34,6 +35,7 @@ #include <net/net_namespace.h> #include <net/netns/generic.h> #include <linux/rhashtable.h> +#include <linux/nospec.h> #include "mac80211_hwsim.h" #define WARN_QUEUE 100 @@ -2528,23 +2530,20 @@ static const struct ieee80211_sband_iftype_data he_capa_2ghz = { IEEE80211_HE_MAC_CAP0_HTC_HE, .mac_cap_info[1] = IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US | - IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_8, + IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8, .mac_cap_info[2] = IEEE80211_HE_MAC_CAP2_BSR | IEEE80211_HE_MAC_CAP2_MU_CASCADING | IEEE80211_HE_MAC_CAP2_ACK_EN, .mac_cap_info[3] = - IEEE80211_HE_MAC_CAP3_GRP_ADDR_MULTI_STA_BA_DL_MU | IEEE80211_HE_MAC_CAP3_OMI_CONTROL | - IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_VHT_2, + IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_VHT_2, .mac_cap_info[4] = IEEE80211_HE_MAC_CAP4_AMDSU_IN_AMPDU, - .phy_cap_info[0] = - IEEE80211_HE_PHY_CAP0_DUAL_BAND, .phy_cap_info[1] = IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK | IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A | IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD | - IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_MAX_NSTS, + IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS, .phy_cap_info[2] = IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US | IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ | @@ -2578,18 +2577,16 @@ static const struct ieee80211_sband_iftype_data he_capa_5ghz = { IEEE80211_HE_MAC_CAP0_HTC_HE, .mac_cap_info[1] = IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US | - IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_8, + IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8, .mac_cap_info[2] = IEEE80211_HE_MAC_CAP2_BSR | IEEE80211_HE_MAC_CAP2_MU_CASCADING | IEEE80211_HE_MAC_CAP2_ACK_EN, .mac_cap_info[3] = - IEEE80211_HE_MAC_CAP3_GRP_ADDR_MULTI_STA_BA_DL_MU | IEEE80211_HE_MAC_CAP3_OMI_CONTROL | - IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_VHT_2, + IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_VHT_2, .mac_cap_info[4] = IEEE80211_HE_MAC_CAP4_AMDSU_IN_AMPDU, .phy_cap_info[0] = - IEEE80211_HE_PHY_CAP0_DUAL_BAND | IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G | IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G | IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G, @@ -2597,7 +2594,7 @@ static const struct ieee80211_sband_iftype_data he_capa_5ghz = { IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK | IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A | IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD | - IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_MAX_NSTS, + IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS, .phy_cap_info[2] = IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US | IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ | @@ -2820,9 +2817,6 @@ static int mac80211_hwsim_new_radio(struct genl_info *info, IEEE80211_VHT_CAP_SHORT_GI_80 | IEEE80211_VHT_CAP_SHORT_GI_160 | IEEE80211_VHT_CAP_TXSTBC | - IEEE80211_VHT_CAP_RXSTBC_1 | - IEEE80211_VHT_CAP_RXSTBC_2 | - IEEE80211_VHT_CAP_RXSTBC_3 | IEEE80211_VHT_CAP_RXSTBC_4 | IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK; sband->vht_cap.vht_mcs.rx_mcs_map = @@ -3317,6 +3311,11 @@ static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info) if (info->attrs[HWSIM_ATTR_CHANNELS]) param.channels = nla_get_u32(info->attrs[HWSIM_ATTR_CHANNELS]); + if (param.channels < 1) { + GENL_SET_ERR_MSG(info, "must have at least one channel"); + return -EINVAL; + } + if (param.channels > CFG80211_MAX_NUM_DIFFERENT_CHANNELS) { GENL_SET_ERR_MSG(info, "too many channels specified"); return -EINVAL; @@ -3350,6 +3349,9 @@ static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info) kfree(hwname); return -EINVAL; } + + idx = array_index_nospec(idx, + ARRAY_SIZE(hwsim_world_regdom_custom)); param.regd = hwsim_world_regdom_custom[idx]; } diff --git a/drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c b/drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c index 9a1d15b3ce45..cec37787ecf8 100644 --- a/drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c +++ b/drivers/net/wireless/realtek/rtl818x/rtl8187/dev.c @@ -499,7 +499,7 @@ static void rtl8187b_status_cb(struct urb *urb) if (cmd_type == 1) { unsigned int pkt_rc, seq_no; bool tok; - struct sk_buff *skb; + struct sk_buff *skb, *iter; struct ieee80211_hdr *ieee80211hdr; unsigned long flags; @@ -508,8 +508,9 @@ static void rtl8187b_status_cb(struct urb *urb) seq_no = (val >> 16) & 0xFFF; spin_lock_irqsave(&priv->b_tx_status.queue.lock, flags); - skb_queue_reverse_walk(&priv->b_tx_status.queue, skb) { - ieee80211hdr = (struct ieee80211_hdr *)skb->data; + skb = NULL; + skb_queue_reverse_walk(&priv->b_tx_status.queue, iter) { + ieee80211hdr = (struct ieee80211_hdr *)iter->data; /* * While testing, it was discovered that the seq_no @@ -522,10 +523,12 @@ static void rtl8187b_status_cb(struct urb *urb) * it's unlikely we wrongly ack some sent data */ if ((le16_to_cpu(ieee80211hdr->seq_ctrl) - & 0xFFF) == seq_no) + & 0xFFF) == seq_no) { + skb = iter; break; + } } - if (skb != (struct sk_buff *) &priv->b_tx_status.queue) { + if (skb) { struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); __skb_unlink(skb, &priv->b_tx_status.queue); diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 3621e05a7494..80aae3a32c2a 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -1660,8 +1660,7 @@ module_init(netback_init); static void __exit netback_fini(void) { #ifdef CONFIG_DEBUG_FS - if (!IS_ERR_OR_NULL(xen_netback_dbg_root)) - debugfs_remove_recursive(xen_netback_dbg_root); + debugfs_remove_recursive(xen_netback_dbg_root); #endif /* CONFIG_DEBUG_FS */ xenvif_xenbus_fini(); } diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c index cd51492ae6c2..fe1d52247bbe 100644 --- a/drivers/net/xen-netback/xenbus.c +++ b/drivers/net/xen-netback/xenbus.c @@ -254,8 +254,7 @@ static void xenvif_debugfs_delif(struct xenvif *vif) if (IS_ERR_OR_NULL(xen_netback_dbg_root)) return; - if (!IS_ERR_OR_NULL(vif->xenvif_dbg_root)) - debugfs_remove_recursive(vif->xenvif_dbg_root); + debugfs_remove_recursive(vif->xenvif_dbg_root); vif->xenvif_dbg_root = NULL; } #endif /* CONFIG_DEBUG_FS */ diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 73f596a90c69..f17f602e6171 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -87,8 +87,7 @@ struct netfront_cb { /* IRQ name is queue name with "-tx" or "-rx" appended */ #define IRQ_NAME_SIZE (QUEUE_NAME_SIZE + 3) -static DECLARE_WAIT_QUEUE_HEAD(module_load_q); -static DECLARE_WAIT_QUEUE_HEAD(module_unload_q); +static DECLARE_WAIT_QUEUE_HEAD(module_wq); struct netfront_stats { u64 packets; @@ -909,7 +908,11 @@ static RING_IDX xennet_fill_frags(struct netfront_queue *queue, BUG_ON(pull_to <= skb_headlen(skb)); __pskb_pull_tail(skb, pull_to - skb_headlen(skb)); } - BUG_ON(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS); + if (unlikely(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS)) { + queue->rx.rsp_cons = ++cons; + kfree_skb(nskb); + return ~0U; + } skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, skb_frag_page(nfrag), @@ -1046,6 +1049,8 @@ err: skb->len += rx->status; i = xennet_fill_frags(queue, skb, &tmpq); + if (unlikely(i == ~0U)) + goto err; if (rx->flags & XEN_NETRXF_csum_blank) skb->ip_summed = CHECKSUM_PARTIAL; @@ -1332,11 +1337,11 @@ static struct net_device *xennet_create_dev(struct xenbus_device *dev) netif_carrier_off(netdev); xenbus_switch_state(dev, XenbusStateInitialising); - wait_event(module_load_q, - xenbus_read_driver_state(dev->otherend) != - XenbusStateClosed && - xenbus_read_driver_state(dev->otherend) != - XenbusStateUnknown); + wait_event(module_wq, + xenbus_read_driver_state(dev->otherend) != + XenbusStateClosed && + xenbus_read_driver_state(dev->otherend) != + XenbusStateUnknown); return netdev; exit: @@ -2010,15 +2015,14 @@ static void netback_changed(struct xenbus_device *dev, dev_dbg(&dev->dev, "%s\n", xenbus_strstate(backend_state)); + wake_up_all(&module_wq); + switch (backend_state) { case XenbusStateInitialising: case XenbusStateInitialised: case XenbusStateReconfiguring: case XenbusStateReconfigured: - break; - case XenbusStateUnknown: - wake_up_all(&module_unload_q); break; case XenbusStateInitWait: @@ -2034,12 +2038,10 @@ static void netback_changed(struct xenbus_device *dev, break; case XenbusStateClosed: - wake_up_all(&module_unload_q); if (dev->state == XenbusStateClosed) break; /* Missed the backend's CLOSING state -- fallthrough */ case XenbusStateClosing: - wake_up_all(&module_unload_q); xenbus_frontend_closed(dev); break; } @@ -2147,14 +2149,14 @@ static int xennet_remove(struct xenbus_device *dev) if (xenbus_read_driver_state(dev->otherend) != XenbusStateClosed) { xenbus_switch_state(dev, XenbusStateClosing); - wait_event(module_unload_q, + wait_event(module_wq, xenbus_read_driver_state(dev->otherend) == XenbusStateClosing || xenbus_read_driver_state(dev->otherend) == XenbusStateUnknown); xenbus_switch_state(dev, XenbusStateClosed); - wait_event(module_unload_q, + wait_event(module_wq, xenbus_read_driver_state(dev->otherend) == XenbusStateClosed || xenbus_read_driver_state(dev->otherend) == diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 1b9951d2067e..d668682f91df 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -316,6 +316,14 @@ static bool nvme_dbbuf_update_and_check_event(u16 value, u32 *dbbuf_db, old_value = *dbbuf_db; *dbbuf_db = value; + /* + * Ensure that the doorbell is updated before reading the event + * index from memory. The controller needs to provide similar + * ordering to ensure the envent index is updated before reading + * the doorbell. + */ + mb(); + if (!nvme_dbbuf_need_event(*dbbuf_ei, value, old_value)) return false; } diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index ebf3e7a6c49e..b5ec96abd048 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -1210,7 +1210,7 @@ static int __init nvmet_init(void) error = nvmet_init_discovery(); if (error) - goto out; + goto out_free_work_queue; error = nvmet_init_configfs(); if (error) @@ -1219,6 +1219,8 @@ static int __init nvmet_init(void) out_exit_discovery: nvmet_exit_discovery(); +out_free_work_queue: + destroy_workqueue(buffered_io_wq); out: return error; } diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c index 34712def81b1..5251689a1d9a 100644 --- a/drivers/nvme/target/fcloop.c +++ b/drivers/nvme/target/fcloop.c @@ -311,7 +311,7 @@ fcloop_tgt_lsrqst_done_work(struct work_struct *work) struct fcloop_tport *tport = tls_req->tport; struct nvmefc_ls_req *lsreq = tls_req->lsreq; - if (tport->remoteport) + if (!tport || tport->remoteport) lsreq->done(lsreq, tls_req->status); } @@ -329,6 +329,7 @@ fcloop_ls_req(struct nvme_fc_local_port *localport, if (!rport->targetport) { tls_req->status = -ECONNREFUSED; + tls_req->tport = NULL; schedule_work(&tls_req->work); return ret; } diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 3533e918ea37..bfc4da660bb4 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -66,6 +66,7 @@ struct nvmet_rdma_rsp { struct nvmet_req req; + bool allocated; u8 n_rdma; u32 flags; u32 invalidate_rkey; @@ -174,11 +175,19 @@ nvmet_rdma_get_rsp(struct nvmet_rdma_queue *queue) unsigned long flags; spin_lock_irqsave(&queue->rsps_lock, flags); - rsp = list_first_entry(&queue->free_rsps, + rsp = list_first_entry_or_null(&queue->free_rsps, struct nvmet_rdma_rsp, free_list); - list_del(&rsp->free_list); + if (likely(rsp)) + list_del(&rsp->free_list); spin_unlock_irqrestore(&queue->rsps_lock, flags); + if (unlikely(!rsp)) { + rsp = kmalloc(sizeof(*rsp), GFP_KERNEL); + if (unlikely(!rsp)) + return NULL; + rsp->allocated = true; + } + return rsp; } @@ -187,6 +196,11 @@ nvmet_rdma_put_rsp(struct nvmet_rdma_rsp *rsp) { unsigned long flags; + if (rsp->allocated) { + kfree(rsp); + return; + } + spin_lock_irqsave(&rsp->queue->rsps_lock, flags); list_add_tail(&rsp->free_list, &rsp->queue->free_rsps); spin_unlock_irqrestore(&rsp->queue->rsps_lock, flags); @@ -776,6 +790,15 @@ static void nvmet_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc) cmd->queue = queue; rsp = nvmet_rdma_get_rsp(queue); + if (unlikely(!rsp)) { + /* + * we get here only under memory pressure, + * silently drop and have the host retry + * as we can't even fail it. + */ + nvmet_rdma_post_recv(queue->dev, cmd); + return; + } rsp->queue = queue; rsp->cmd = cmd; rsp->flags = 0; diff --git a/drivers/of/base.c b/drivers/of/base.c index 466e3c8582f0..74eaedd5b860 100644 --- a/drivers/of/base.c +++ b/drivers/of/base.c @@ -54,6 +54,28 @@ DEFINE_MUTEX(of_mutex); */ DEFINE_RAW_SPINLOCK(devtree_lock); +bool of_node_name_eq(const struct device_node *np, const char *name) +{ + const char *node_name; + size_t len; + + if (!np) + return false; + + node_name = kbasename(np->full_name); + len = strchrnul(node_name, '@') - node_name; + + return (strlen(name) == len) && (strncmp(node_name, name, len) == 0); +} + +bool of_node_name_prefix(const struct device_node *np, const char *prefix) +{ + if (!np) + return false; + + return strncmp(kbasename(np->full_name), prefix, strlen(prefix)) == 0; +} + int of_n_addr_cells(struct device_node *np) { u32 cells; @@ -118,6 +140,9 @@ void of_populate_phandle_cache(void) if (np->phandle && np->phandle != OF_PHANDLE_ILLEGAL) phandles++; + if (!phandles) + goto out; + cache_entries = roundup_pow_of_two(phandles); phandle_cache_mask = cache_entries - 1; @@ -720,6 +745,31 @@ struct device_node *of_get_next_available_child(const struct device_node *node, EXPORT_SYMBOL(of_get_next_available_child); /** + * of_get_compatible_child - Find compatible child node + * @parent: parent node + * @compatible: compatible string + * + * Lookup child node whose compatible property contains the given compatible + * string. + * + * Returns a node pointer with refcount incremented, use of_node_put() on it + * when done; or NULL if not found. + */ +struct device_node *of_get_compatible_child(const struct device_node *parent, + const char *compatible) +{ + struct device_node *child; + + for_each_child_of_node(parent, child) { + if (of_device_is_compatible(child, compatible)) + break; + } + + return child; +} +EXPORT_SYMBOL(of_get_compatible_child); + +/** * of_get_child_by_name - Find the child node by name for a given parent * @node: parent node * @name: child name to look for. diff --git a/drivers/of/platform.c b/drivers/of/platform.c index 7ba90c290a42..6c59673933e9 100644 --- a/drivers/of/platform.c +++ b/drivers/of/platform.c @@ -241,6 +241,10 @@ static struct amba_device *of_amba_device_create(struct device_node *node, if (!dev) goto err_clear_flag; + /* AMBA devices only support a single DMA mask */ + dev->dev.coherent_dma_mask = DMA_BIT_MASK(32); + dev->dev.dma_mask = &dev->dev.coherent_dma_mask; + /* setup generic device info */ dev->dev.of_node = of_node_get(node); dev->dev.fwnode = &node->fwnode; diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index c00f82cc54aa..ee80e79db21a 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -89,6 +89,9 @@ static enum pci_protocol_version_t pci_protocol_version; #define STATUS_REVISION_MISMATCH 0xC0000059 +/* space for 32bit serial number as string */ +#define SLOT_NAME_SIZE 11 + /* * Message Types */ @@ -494,6 +497,7 @@ struct hv_pci_dev { struct list_head list_entry; refcount_t refs; enum hv_pcichild_state state; + struct pci_slot *pci_slot; struct pci_function_description desc; bool reported_missing; struct hv_pcibus_device *hbus; @@ -1457,6 +1461,34 @@ static void prepopulate_bars(struct hv_pcibus_device *hbus) spin_unlock_irqrestore(&hbus->device_list_lock, flags); } +/* + * Assign entries in sysfs pci slot directory. + * + * Note that this function does not need to lock the children list + * because it is called from pci_devices_present_work which + * is serialized with hv_eject_device_work because they are on the + * same ordered workqueue. Therefore hbus->children list will not change + * even when pci_create_slot sleeps. + */ +static void hv_pci_assign_slots(struct hv_pcibus_device *hbus) +{ + struct hv_pci_dev *hpdev; + char name[SLOT_NAME_SIZE]; + int slot_nr; + + list_for_each_entry(hpdev, &hbus->children, list_entry) { + if (hpdev->pci_slot) + continue; + + slot_nr = PCI_SLOT(wslot_to_devfn(hpdev->desc.win_slot.slot)); + snprintf(name, SLOT_NAME_SIZE, "%u", hpdev->desc.ser); + hpdev->pci_slot = pci_create_slot(hbus->pci_bus, slot_nr, + name, NULL); + if (!hpdev->pci_slot) + pr_warn("pci_create slot %s failed\n", name); + } +} + /** * create_root_hv_pci_bus() - Expose a new root PCI bus * @hbus: Root PCI bus, as understood by this driver @@ -1480,6 +1512,7 @@ static int create_root_hv_pci_bus(struct hv_pcibus_device *hbus) pci_lock_rescan_remove(); pci_scan_child_bus(hbus->pci_bus); pci_bus_assign_resources(hbus->pci_bus); + hv_pci_assign_slots(hbus); pci_bus_add_devices(hbus->pci_bus); pci_unlock_rescan_remove(); hbus->state = hv_pcibus_installed; @@ -1742,6 +1775,7 @@ static void pci_devices_present_work(struct work_struct *work) */ pci_lock_rescan_remove(); pci_scan_child_bus(hbus->pci_bus); + hv_pci_assign_slots(hbus); pci_unlock_rescan_remove(); break; @@ -1858,6 +1892,9 @@ static void hv_eject_device_work(struct work_struct *work) list_del(&hpdev->list_entry); spin_unlock_irqrestore(&hpdev->hbus->device_list_lock, flags); + if (hpdev->pci_slot) + pci_destroy_slot(hpdev->pci_slot); + memset(&ctxt, 0, sizeof(ctxt)); ejct_pkt = (struct pci_eject_response *)&ctxt.pkt.message; ejct_pkt->message_type.type = PCI_EJECTION_COMPLETE; diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c index 7136e3430925..a938abdb41ce 100644 --- a/drivers/pci/hotplug/pciehp_hpc.c +++ b/drivers/pci/hotplug/pciehp_hpc.c @@ -496,7 +496,7 @@ int pciehp_power_on_slot(struct slot *slot) u16 slot_status; int retval; - /* Clear sticky power-fault bit from previous power failures */ + /* Clear power-fault bit from previous power failures */ pcie_capability_read_word(pdev, PCI_EXP_SLTSTA, &slot_status); if (slot_status & PCI_EXP_SLTSTA_PFD) pcie_capability_write_word(pdev, PCI_EXP_SLTSTA, @@ -646,6 +646,14 @@ static irqreturn_t pciehp_ist(int irq, void *dev_id) pciehp_handle_button_press(slot); } + /* Check Power Fault Detected */ + if ((events & PCI_EXP_SLTSTA_PFD) && !ctrl->power_fault_detected) { + ctrl->power_fault_detected = 1; + ctrl_err(ctrl, "Slot(%s): Power fault\n", slot_name(slot)); + pciehp_set_attention_status(slot, 1); + pciehp_green_led_off(slot); + } + /* * Disable requests have higher priority than Presence Detect Changed * or Data Link Layer State Changed events. @@ -657,14 +665,6 @@ static irqreturn_t pciehp_ist(int irq, void *dev_id) pciehp_handle_presence_or_link_change(slot, events); up_read(&ctrl->reset_lock); - /* Check Power Fault Detected */ - if ((events & PCI_EXP_SLTSTA_PFD) && !ctrl->power_fault_detected) { - ctrl->power_fault_detected = 1; - ctrl_err(ctrl, "Slot(%s): Power fault\n", slot_name(slot)); - pciehp_set_attention_status(slot, 1); - pciehp_green_led_off(slot); - } - pci_config_pm_runtime_put(pdev); wake_up(&ctrl->requester); return IRQ_HANDLED; diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 29ff9619b5fa..1835f3a7aa8d 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -4547,6 +4547,7 @@ int pci_bridge_secondary_bus_reset(struct pci_dev *dev) return pci_dev_wait(dev, "bus reset", PCIE_RESET_READY_POLL_MS); } +EXPORT_SYMBOL_GPL(pci_bridge_secondary_bus_reset); static int pci_parent_bus_reset(struct pci_dev *dev, int probe) { @@ -5200,7 +5201,7 @@ static int __pci_reset_bus(struct pci_bus *bus) */ int pci_reset_bus(struct pci_dev *pdev) { - return pci_probe_reset_slot(pdev->slot) ? + return (!pci_probe_reset_slot(pdev->slot)) ? __pci_reset_slot(pdev->slot) : __pci_reset_bus(pdev->bus); } EXPORT_SYMBOL_GPL(pci_reset_bus); diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index ec784009a36b..201f9e5ff55c 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -2074,6 +2074,7 @@ static void pci_configure_eetlp_prefix(struct pci_dev *dev) { #ifdef CONFIG_PCI_PASID struct pci_dev *bridge; + int pcie_type; u32 cap; if (!pci_is_pcie(dev)) @@ -2083,7 +2084,9 @@ static void pci_configure_eetlp_prefix(struct pci_dev *dev) if (!(cap & PCI_EXP_DEVCAP2_EE_PREFIX)) return; - if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT) + pcie_type = pci_pcie_type(dev); + if (pcie_type == PCI_EXP_TYPE_ROOT_PORT || + pcie_type == PCI_EXP_TYPE_RC_END) dev->eetlp_prefix_path = 1; else { bridge = pci_upstream_bridge(dev); diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index ef7143a274e0..6bc27b7fd452 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -4355,11 +4355,6 @@ static int pci_quirk_qcom_rp_acs(struct pci_dev *dev, u16 acs_flags) * * 0x9d10-0x9d1b PCI Express Root port #{1-12} * - * The 300 series chipset suffers from the same bug so include those root - * ports here as well. - * - * 0xa32c-0xa343 PCI Express Root port #{0-24} - * * [1] http://www.intel.com/content/www/us/en/chipsets/100-series-chipset-datasheet-vol-2.html * [2] http://www.intel.com/content/www/us/en/chipsets/100-series-chipset-datasheet-vol-1.html * [3] http://www.intel.com/content/www/us/en/chipsets/100-series-chipset-spec-update.html @@ -4377,7 +4372,6 @@ static bool pci_quirk_intel_spt_pch_acs_match(struct pci_dev *dev) case 0xa110 ... 0xa11f: case 0xa167 ... 0xa16a: /* Sunrise Point */ case 0xa290 ... 0xa29f: case 0xa2e7 ... 0xa2ee: /* Union Point */ case 0x9d10 ... 0x9d1b: /* 7th & 8th Gen Mobile */ - case 0xa32c ... 0xa343: /* 300 series */ return true; } diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c index 9940cc70f38b..54a8b30dda38 100644 --- a/drivers/pci/switch/switchtec.c +++ b/drivers/pci/switch/switchtec.c @@ -14,6 +14,8 @@ #include <linux/poll.h> #include <linux/wait.h> +#include <linux/nospec.h> + MODULE_DESCRIPTION("Microsemi Switchtec(tm) PCIe Management Driver"); MODULE_VERSION("0.1"); MODULE_LICENSE("GPL"); @@ -909,6 +911,8 @@ static int ioctl_port_to_pff(struct switchtec_dev *stdev, default: if (p.port > ARRAY_SIZE(pcfg->dsp_pff_inst_id)) return -EINVAL; + p.port = array_index_nospec(p.port, + ARRAY_SIZE(pcfg->dsp_pff_inst_id) + 1); p.pff = ioread32(&pcfg->dsp_pff_inst_id[p.port - 1]); break; } diff --git a/drivers/pinctrl/cirrus/pinctrl-madera-core.c b/drivers/pinctrl/cirrus/pinctrl-madera-core.c index ece41fb2848f..c4f4d904e4a6 100644 --- a/drivers/pinctrl/cirrus/pinctrl-madera-core.c +++ b/drivers/pinctrl/cirrus/pinctrl-madera-core.c @@ -1040,7 +1040,7 @@ static int madera_pin_probe(struct platform_device *pdev) } /* if the configuration is provided through pdata, apply it */ - if (pdata) { + if (pdata && pdata->gpio_configs) { ret = pinctrl_register_mappings(pdata->gpio_configs, pdata->n_gpio_configs); if (ret) { diff --git a/drivers/pinctrl/pinctrl-ingenic.c b/drivers/pinctrl/pinctrl-ingenic.c index 6a1b6058b991..628817c40e3b 100644 --- a/drivers/pinctrl/pinctrl-ingenic.c +++ b/drivers/pinctrl/pinctrl-ingenic.c @@ -793,7 +793,7 @@ static int ingenic_pinctrl_probe(struct platform_device *pdev) err = pinctrl_generic_add_group(jzpc->pctl, group->name, group->pins, group->num_pins, group->data); - if (err) { + if (err < 0) { dev_err(dev, "Failed to register group %s\n", group->name); return err; @@ -806,7 +806,7 @@ static int ingenic_pinctrl_probe(struct platform_device *pdev) err = pinmux_generic_add_function(jzpc->pctl, func->name, func->group_names, func->num_group_names, func->data); - if (err) { + if (err < 0) { dev_err(dev, "Failed to register function %s\n", func->name); return err; diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c index 2155a30c282b..5d72ffad32c2 100644 --- a/drivers/pinctrl/qcom/pinctrl-msm.c +++ b/drivers/pinctrl/qcom/pinctrl-msm.c @@ -634,6 +634,29 @@ static void msm_gpio_irq_mask(struct irq_data *d) raw_spin_lock_irqsave(&pctrl->lock, flags); val = readl(pctrl->regs + g->intr_cfg_reg); + /* + * There are two bits that control interrupt forwarding to the CPU. The + * RAW_STATUS_EN bit causes the level or edge sensed on the line to be + * latched into the interrupt status register when the hardware detects + * an irq that it's configured for (either edge for edge type or level + * for level type irq). The 'non-raw' status enable bit causes the + * hardware to assert the summary interrupt to the CPU if the latched + * status bit is set. There's a bug though, the edge detection logic + * seems to have a problem where toggling the RAW_STATUS_EN bit may + * cause the status bit to latch spuriously when there isn't any edge + * so we can't touch that bit for edge type irqs and we have to keep + * the bit set anyway so that edges are latched while the line is masked. + * + * To make matters more complicated, leaving the RAW_STATUS_EN bit + * enabled all the time causes level interrupts to re-latch into the + * status register because the level is still present on the line after + * we ack it. We clear the raw status enable bit during mask here and + * set the bit on unmask so the interrupt can't latch into the hardware + * while it's masked. + */ + if (irqd_get_trigger_type(d) & IRQ_TYPE_LEVEL_MASK) + val &= ~BIT(g->intr_raw_status_bit); + val &= ~BIT(g->intr_enable_bit); writel(val, pctrl->regs + g->intr_cfg_reg); @@ -655,6 +678,7 @@ static void msm_gpio_irq_unmask(struct irq_data *d) raw_spin_lock_irqsave(&pctrl->lock, flags); val = readl(pctrl->regs + g->intr_cfg_reg); + val |= BIT(g->intr_raw_status_bit); val |= BIT(g->intr_enable_bit); writel(val, pctrl->regs + g->intr_cfg_reg); diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index ec891bc7d10a..f039266b275d 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -872,8 +872,6 @@ static int hex2bitmap(const char *str, unsigned long *bitmap, int bits) if (bits & 0x07) return -EINVAL; - memset(bitmap, 0, bits / 8); - if (str[0] == '0' && str[1] == 'x') str++; if (*str == 'x') @@ -895,25 +893,23 @@ static int hex2bitmap(const char *str, unsigned long *bitmap, int bits) } /* - * str2clrsetmasks() - parse bitmask argument and set the clear and - * the set bitmap mask. A concatenation (done with ',') of these terms - * is recognized: + * modify_bitmap() - parse bitmask argument and modify an existing + * bit mask accordingly. A concatenation (done with ',') of these + * terms is recognized: * +<bitnr>[-<bitnr>] or -<bitnr>[-<bitnr>] * <bitnr> may be any valid number (hex, decimal or octal) in the range * 0...bits-1; the leading + or - is required. Here are some examples: * +0-15,+32,-128,-0xFF * -0-255,+1-16,+0x128 * +1,+2,+3,+4,-5,-7-10 - * Returns a clear and a set bitmask. Every positive value in the string - * results in a bit set in the set mask and every negative value in the - * string results in a bit SET in the clear mask. As a bit may be touched - * more than once, the last 'operation' wins: +0-255,-128 = all but bit - * 128 set in the set mask, only bit 128 set in the clear mask. + * Returns the new bitmap after all changes have been applied. Every + * positive value in the string will set a bit and every negative value + * in the string will clear a bit. As a bit may be touched more than once, + * the last 'operation' wins: + * +0-255,-128 = first bits 0-255 will be set, then bit 128 will be + * cleared again. All other bits are unmodified. */ -static int str2clrsetmasks(const char *str, - unsigned long *clrmap, - unsigned long *setmap, - int bits) +static int modify_bitmap(const char *str, unsigned long *bitmap, int bits) { int a, i, z; char *np, sign; @@ -922,9 +918,6 @@ static int str2clrsetmasks(const char *str, if (bits & 0x07) return -EINVAL; - memset(clrmap, 0, bits / 8); - memset(setmap, 0, bits / 8); - while (*str) { sign = *str++; if (sign != '+' && sign != '-') @@ -940,13 +933,10 @@ static int str2clrsetmasks(const char *str, str = np; } for (i = a; i <= z; i++) - if (sign == '+') { - set_bit_inv(i, setmap); - clear_bit_inv(i, clrmap); - } else { - clear_bit_inv(i, setmap); - set_bit_inv(i, clrmap); - } + if (sign == '+') + set_bit_inv(i, bitmap); + else + clear_bit_inv(i, bitmap); while (*str == ',' || *str == '\n') str++; } @@ -970,44 +960,34 @@ static int process_mask_arg(const char *str, unsigned long *bitmap, int bits, struct mutex *lock) { - int i; + unsigned long *newmap, size; + int rc; /* bits needs to be a multiple of 8 */ if (bits & 0x07) return -EINVAL; + size = BITS_TO_LONGS(bits)*sizeof(unsigned long); + newmap = kmalloc(size, GFP_KERNEL); + if (!newmap) + return -ENOMEM; + if (mutex_lock_interruptible(lock)) { + kfree(newmap); + return -ERESTARTSYS; + } + if (*str == '+' || *str == '-') { - DECLARE_BITMAP(clrm, bits); - DECLARE_BITMAP(setm, bits); - - i = str2clrsetmasks(str, clrm, setm, bits); - if (i) - return i; - if (mutex_lock_interruptible(lock)) - return -ERESTARTSYS; - for (i = 0; i < bits; i++) { - if (test_bit_inv(i, clrm)) - clear_bit_inv(i, bitmap); - if (test_bit_inv(i, setm)) - set_bit_inv(i, bitmap); - } + memcpy(newmap, bitmap, size); + rc = modify_bitmap(str, newmap, bits); } else { - DECLARE_BITMAP(setm, bits); - - i = hex2bitmap(str, setm, bits); - if (i) - return i; - if (mutex_lock_interruptible(lock)) - return -ERESTARTSYS; - for (i = 0; i < bits; i++) - if (test_bit_inv(i, setm)) - set_bit_inv(i, bitmap); - else - clear_bit_inv(i, bitmap); + memset(newmap, 0, size); + rc = hex2bitmap(str, newmap, bits); } + if (rc == 0) + memcpy(bitmap, newmap, size); mutex_unlock(lock); - - return 0; + kfree(newmap); + return rc; } /* diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index 34e0d476c5c6..0dbe81f958f0 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -26,6 +26,7 @@ #include <net/ipv6.h> #include <net/if_inet6.h> #include <net/addrconf.h> +#include <net/tcp.h> #include <asm/debug.h> #include <asm/qdio.h> @@ -638,7 +639,6 @@ struct qeth_reply { atomic_t received; int rc; void *param; - struct qeth_card *card; refcount_t refcnt; }; @@ -892,11 +892,6 @@ static inline void qeth_tx_csum(struct sk_buff *skb, u8 *flags, int ipv) if ((ipv == 4 && ip_hdr(skb)->protocol == IPPROTO_UDP) || (ipv == 6 && ipv6_hdr(skb)->nexthdr == IPPROTO_UDP)) *flags |= QETH_HDR_EXT_UDP; - if (ipv == 4) { - /* some HW requires combined L3+L4 csum offload: */ - *flags |= QETH_HDR_EXT_CSUM_HDR_REQ; - ip_hdr(skb)->check = 0; - } } static inline void qeth_put_buffer_pool_entry(struct qeth_card *card, @@ -1007,9 +1002,7 @@ int qeth_query_switch_attributes(struct qeth_card *card, int qeth_send_control_data(struct qeth_card *, int, struct qeth_cmd_buffer *, int (*reply_cb)(struct qeth_card *, struct qeth_reply*, unsigned long), void *reply_param); -int qeth_get_elements_no(struct qeth_card *card, struct sk_buff *skb, - int extra_elems, int data_offset); -int qeth_get_elements_for_frags(struct sk_buff *); +unsigned int qeth_count_elements(struct sk_buff *skb, unsigned int data_offset); int qeth_do_send_packet_fast(struct qeth_qdio_out_q *queue, struct sk_buff *skb, struct qeth_hdr *hdr, unsigned int offset, unsigned int hd_len); @@ -1027,7 +1020,6 @@ void qeth_dbf_longtext(debug_info_t *id, int level, char *text, ...); int qeth_core_ethtool_get_link_ksettings(struct net_device *netdev, struct ethtool_link_ksettings *cmd); int qeth_set_access_ctrl_online(struct qeth_card *card, int fallback); -int qeth_hdr_chk_and_bounce(struct sk_buff *, struct qeth_hdr **, int); int qeth_configure_cq(struct qeth_card *, enum qeth_cq); int qeth_hw_trap(struct qeth_card *, enum qeth_diags_trap_action); void qeth_trace_features(struct qeth_card *); @@ -1052,6 +1044,11 @@ int qeth_vm_request_mac(struct qeth_card *card); int qeth_add_hw_header(struct qeth_card *card, struct sk_buff *skb, struct qeth_hdr **hdr, unsigned int hdr_len, unsigned int proto_len, unsigned int *elements); +int qeth_xmit(struct qeth_card *card, struct sk_buff *skb, + struct qeth_qdio_out_q *queue, int ipv, int cast_type, + void (*fill_header)(struct qeth_card *card, struct qeth_hdr *hdr, + struct sk_buff *skb, int ipv, int cast_type, + unsigned int data_len)); /* 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 49f64eb3eab0..89e09e7b8fff 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -16,6 +16,7 @@ #include <linux/string.h> #include <linux/errno.h> #include <linux/kernel.h> +#include <linux/log2.h> #include <linux/ip.h> #include <linux/tcp.h> #include <linux/mii.h> @@ -25,6 +26,7 @@ #include <linux/netdevice.h> #include <linux/netdev_features.h> #include <linux/skbuff.h> +#include <linux/vmalloc.h> #include <net/iucv/af_iucv.h> #include <net/dsfield.h> @@ -590,7 +592,6 @@ static struct qeth_reply *qeth_alloc_reply(struct qeth_card *card) if (reply) { refcount_set(&reply->refcnt, 1); atomic_set(&reply->received, 0); - reply->card = card; } return reply; } @@ -779,7 +780,6 @@ void qeth_release_buffer(struct qeth_channel *channel, QETH_CARD_TEXT(CARD_FROM_CDEV(channel->ccwdev), 6, "relbuff"); spin_lock_irqsave(&channel->iob_lock, flags); - memset(iob->data, 0, QETH_BUFSIZE); iob->state = BUF_STATE_FREE; iob->callback = qeth_send_control_data_cb; iob->rc = 0; @@ -899,44 +899,6 @@ out: qeth_release_buffer(channel, iob); } -static int qeth_setup_channel(struct qeth_channel *channel, bool alloc_buffers) -{ - int cnt; - - QETH_DBF_TEXT(SETUP, 2, "setupch"); - - channel->ccw = kmalloc(sizeof(struct ccw1), GFP_KERNEL | GFP_DMA); - if (!channel->ccw) - return -ENOMEM; - channel->state = CH_STATE_DOWN; - atomic_set(&channel->irq_pending, 0); - init_waitqueue_head(&channel->wait_q); - - if (!alloc_buffers) - return 0; - - for (cnt = 0; cnt < QETH_CMD_BUFFER_NO; cnt++) { - channel->iob[cnt].data = - kzalloc(QETH_BUFSIZE, GFP_DMA|GFP_KERNEL); - if (channel->iob[cnt].data == NULL) - break; - channel->iob[cnt].state = BUF_STATE_FREE; - channel->iob[cnt].channel = channel; - channel->iob[cnt].callback = qeth_send_control_data_cb; - channel->iob[cnt].rc = 0; - } - if (cnt < QETH_CMD_BUFFER_NO) { - kfree(channel->ccw); - while (cnt-- > 0) - kfree(channel->iob[cnt].data); - return -ENOMEM; - } - channel->io_buf_no = 0; - spin_lock_init(&channel->iob_lock); - - return 0; -} - static int qeth_set_thread_start_bit(struct qeth_card *card, unsigned long thread) { @@ -1335,14 +1297,61 @@ static void qeth_free_buffer_pool(struct qeth_card *card) static void qeth_clean_channel(struct qeth_channel *channel) { + struct ccw_device *cdev = channel->ccwdev; int cnt; QETH_DBF_TEXT(SETUP, 2, "freech"); + + spin_lock_irq(get_ccwdev_lock(cdev)); + cdev->handler = NULL; + spin_unlock_irq(get_ccwdev_lock(cdev)); + for (cnt = 0; cnt < QETH_CMD_BUFFER_NO; cnt++) kfree(channel->iob[cnt].data); kfree(channel->ccw); } +static int qeth_setup_channel(struct qeth_channel *channel, bool alloc_buffers) +{ + struct ccw_device *cdev = channel->ccwdev; + int cnt; + + QETH_DBF_TEXT(SETUP, 2, "setupch"); + + channel->ccw = kmalloc(sizeof(struct ccw1), GFP_KERNEL | GFP_DMA); + if (!channel->ccw) + return -ENOMEM; + channel->state = CH_STATE_DOWN; + atomic_set(&channel->irq_pending, 0); + init_waitqueue_head(&channel->wait_q); + + spin_lock_irq(get_ccwdev_lock(cdev)); + cdev->handler = qeth_irq; + spin_unlock_irq(get_ccwdev_lock(cdev)); + + if (!alloc_buffers) + return 0; + + for (cnt = 0; cnt < QETH_CMD_BUFFER_NO; cnt++) { + channel->iob[cnt].data = kmalloc(QETH_BUFSIZE, + GFP_KERNEL | GFP_DMA); + if (channel->iob[cnt].data == NULL) + break; + channel->iob[cnt].state = BUF_STATE_FREE; + channel->iob[cnt].channel = channel; + channel->iob[cnt].callback = qeth_send_control_data_cb; + channel->iob[cnt].rc = 0; + } + if (cnt < QETH_CMD_BUFFER_NO) { + qeth_clean_channel(channel); + return -ENOMEM; + } + channel->io_buf_no = 0; + spin_lock_init(&channel->iob_lock); + + return 0; +} + static void qeth_set_single_write_queues(struct qeth_card *card) { if ((atomic_read(&card->qdio.state) != QETH_QDIO_UNINITIALIZED) && @@ -1493,7 +1502,7 @@ static void qeth_core_sl_print(struct seq_file *m, struct service_level *slr) CARD_BUS_ID(card), card->info.mcl_level); } -static struct qeth_card *qeth_alloc_card(void) +static struct qeth_card *qeth_alloc_card(struct ccwgroup_device *gdev) { struct qeth_card *card; @@ -1502,6 +1511,11 @@ static struct qeth_card *qeth_alloc_card(void) if (!card) goto out; QETH_DBF_HEX(SETUP, 2, &card, sizeof(void *)); + + card->gdev = gdev; + CARD_RDEV(card) = gdev->cdev[0]; + CARD_WDEV(card) = gdev->cdev[1]; + CARD_DDEV(card) = gdev->cdev[2]; if (qeth_setup_channel(&card->read, true)) goto out_ip; if (qeth_setup_channel(&card->write, true)) @@ -1525,15 +1539,14 @@ out: static int qeth_clear_channel(struct qeth_channel *channel) { - unsigned long flags; struct qeth_card *card; int rc; card = CARD_FROM_CDEV(channel->ccwdev); QETH_CARD_TEXT(card, 3, "clearch"); - spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags); + spin_lock_irq(get_ccwdev_lock(channel->ccwdev)); rc = ccw_device_clear(channel->ccwdev, QETH_CLEAR_CHANNEL_PARM); - spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags); + spin_unlock_irq(get_ccwdev_lock(channel->ccwdev)); if (rc) return rc; @@ -1549,15 +1562,14 @@ static int qeth_clear_channel(struct qeth_channel *channel) static int qeth_halt_channel(struct qeth_channel *channel) { - unsigned long flags; struct qeth_card *card; int rc; card = CARD_FROM_CDEV(channel->ccwdev); QETH_CARD_TEXT(card, 3, "haltch"); - spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags); + spin_lock_irq(get_ccwdev_lock(channel->ccwdev)); rc = ccw_device_halt(channel->ccwdev, QETH_HALT_CHANNEL_PARM); - spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags); + spin_unlock_irq(get_ccwdev_lock(channel->ccwdev)); if (rc) return rc; @@ -1651,7 +1663,6 @@ static int qeth_read_conf_data(struct qeth_card *card, void **buffer, char *rcd_buf; int ret; struct qeth_channel *channel = &card->data; - unsigned long flags; /* * scan for RCD command in extended SenseID data @@ -1665,11 +1676,11 @@ static int qeth_read_conf_data(struct qeth_card *card, void **buffer, qeth_setup_ccw(channel->ccw, ciw->cmd, ciw->count, rcd_buf); channel->state = CH_STATE_RCD; - spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags); + spin_lock_irq(get_ccwdev_lock(channel->ccwdev)); ret = ccw_device_start_timeout(channel->ccwdev, channel->ccw, QETH_RCD_PARM, LPM_ANYPATH, 0, QETH_RCD_TIMEOUT); - spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags); + spin_unlock_irq(get_ccwdev_lock(channel->ccwdev)); if (!ret) wait_event(card->wait_q, (channel->state == CH_STATE_RCD_DONE || @@ -1827,7 +1838,6 @@ static int qeth_idx_activate_get_answer(struct qeth_channel *channel, struct qeth_cmd_buffer *)) { struct qeth_cmd_buffer *iob; - unsigned long flags; int rc; struct qeth_card *card; @@ -1842,10 +1852,10 @@ static int qeth_idx_activate_get_answer(struct qeth_channel *channel, wait_event(card->wait_q, atomic_cmpxchg(&channel->irq_pending, 0, 1) == 0); QETH_DBF_TEXT(SETUP, 6, "noirqpnd"); - spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags); + spin_lock_irq(get_ccwdev_lock(channel->ccwdev)); rc = ccw_device_start_timeout(channel->ccwdev, channel->ccw, (addr_t) iob, 0, 0, QETH_TIMEOUT); - spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags); + spin_unlock_irq(get_ccwdev_lock(channel->ccwdev)); if (rc) { QETH_DBF_MESSAGE(2, "Error2 in activating channel rc=%d\n", rc); @@ -1872,7 +1882,6 @@ static int qeth_idx_activate_channel(struct qeth_channel *channel, { struct qeth_card *card; struct qeth_cmd_buffer *iob; - unsigned long flags; __u16 temp; __u8 tmp; int rc; @@ -1912,10 +1921,10 @@ static int qeth_idx_activate_channel(struct qeth_channel *channel, wait_event(card->wait_q, atomic_cmpxchg(&channel->irq_pending, 0, 1) == 0); QETH_DBF_TEXT(SETUP, 6, "noirqpnd"); - spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags); + spin_lock_irq(get_ccwdev_lock(channel->ccwdev)); rc = ccw_device_start_timeout(channel->ccwdev, channel->ccw, (addr_t) iob, 0, 0, QETH_TIMEOUT); - spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags); + spin_unlock_irq(get_ccwdev_lock(channel->ccwdev)); if (rc) { QETH_DBF_MESSAGE(2, "Error1 in activating channel. rc=%d\n", @@ -2096,7 +2105,6 @@ int qeth_send_control_data(struct qeth_card *card, int len, { struct qeth_channel *channel = iob->channel; int rc; - unsigned long flags; struct qeth_reply *reply = NULL; unsigned long timeout, event_timeout; struct qeth_ipa_cmd *cmd = NULL; @@ -2129,26 +2137,26 @@ int qeth_send_control_data(struct qeth_card *card, int len, } qeth_prepare_control_data(card, len, iob); - spin_lock_irqsave(&card->lock, flags); + spin_lock_irq(&card->lock); list_add_tail(&reply->list, &card->cmd_waiter_list); - spin_unlock_irqrestore(&card->lock, flags); + spin_unlock_irq(&card->lock); timeout = jiffies + event_timeout; QETH_CARD_TEXT(card, 6, "noirqpnd"); - spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags); + spin_lock_irq(get_ccwdev_lock(channel->ccwdev)); rc = ccw_device_start_timeout(channel->ccwdev, channel->ccw, (addr_t) iob, 0, 0, event_timeout); - spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags); + spin_unlock_irq(get_ccwdev_lock(channel->ccwdev)); if (rc) { QETH_DBF_MESSAGE(2, "%s qeth_send_control_data: " "ccw_device_start rc = %i\n", dev_name(&channel->ccwdev->dev), rc); QETH_CARD_TEXT_(card, 2, " err%d", rc); - spin_lock_irqsave(&card->lock, flags); + spin_lock_irq(&card->lock); list_del_init(&reply->list); qeth_put_reply(reply); - spin_unlock_irqrestore(&card->lock, flags); + spin_unlock_irq(&card->lock); qeth_release_buffer(channel, iob); atomic_set(&channel->irq_pending, 0); wake_up(&card->wait_q); @@ -2176,9 +2184,9 @@ int qeth_send_control_data(struct qeth_card *card, int len, time_err: reply->rc = -ETIME; - spin_lock_irqsave(&reply->card->lock, flags); + spin_lock_irq(&card->lock); list_del_init(&reply->list); - spin_unlock_irqrestore(&reply->card->lock, flags); + spin_unlock_irq(&card->lock); atomic_inc(&reply->received); rc = reply->rc; qeth_put_reply(reply); @@ -2879,10 +2887,10 @@ static __u8 qeth_get_ipa_adp_type(enum qeth_link_types link_type) } static void qeth_fill_ipacmd_header(struct qeth_card *card, - struct qeth_ipa_cmd *cmd, __u8 command, - enum qeth_prot_versions prot) + struct qeth_ipa_cmd *cmd, + enum qeth_ipa_cmds command, + enum qeth_prot_versions prot) { - memset(cmd, 0, sizeof(struct qeth_ipa_cmd)); cmd->hdr.command = command; cmd->hdr.initiator = IPA_CMD_INITIATOR_HOST; /* cmd->hdr.seqno is set by qeth_send_control_data() */ @@ -2894,8 +2902,6 @@ static void qeth_fill_ipacmd_header(struct qeth_card *card, cmd->hdr.prim_version_no = 1; cmd->hdr.param_count = 1; cmd->hdr.prot_version = prot; - cmd->hdr.ipa_supported = 0; - cmd->hdr.ipa_enabled = 0; } struct qeth_cmd_buffer *qeth_get_ipacmd_buffer(struct qeth_card *card, @@ -3042,7 +3048,7 @@ static int qeth_query_ipassists_cb(struct qeth_card *card, QETH_DBF_TEXT(SETUP, 2, "ipaunsup"); card->options.ipa4.supported_funcs |= IPA_SETADAPTERPARMS; card->options.ipa6.supported_funcs |= IPA_SETADAPTERPARMS; - return -0; + return 0; default: if (cmd->hdr.return_code) { QETH_DBF_MESSAGE(1, "%s IPA_CMD_QIPASSIST: Unhandled " @@ -3786,7 +3792,7 @@ EXPORT_SYMBOL_GPL(qeth_get_priority_queue); * Returns the number of pages, and thus QDIO buffer elements, needed to cover * fragmented part of the SKB. Returns zero for linear SKB. */ -int qeth_get_elements_for_frags(struct sk_buff *skb) +static int qeth_get_elements_for_frags(struct sk_buff *skb) { int cnt, elements = 0; @@ -3799,9 +3805,17 @@ int qeth_get_elements_for_frags(struct sk_buff *skb) } return elements; } -EXPORT_SYMBOL_GPL(qeth_get_elements_for_frags); -static unsigned int qeth_count_elements(struct sk_buff *skb, int data_offset) +/** + * qeth_count_elements() - Counts the number of QDIO buffer elements needed + * to transmit an skb. + * @skb: the skb to operate on. + * @data_offset: skip this part of the skb's linear data + * + * Returns the number of pages, and thus QDIO buffer elements, needed to map the + * skb's data (both its linear part and paged fragments). + */ +unsigned int qeth_count_elements(struct sk_buff *skb, unsigned int data_offset) { unsigned int elements = qeth_get_elements_for_frags(skb); addr_t end = (addr_t)skb->data + skb_headlen(skb); @@ -3811,54 +3825,10 @@ static unsigned int qeth_count_elements(struct sk_buff *skb, int data_offset) elements += qeth_get_elements_for_range(start, end); return elements; } +EXPORT_SYMBOL_GPL(qeth_count_elements); -/** - * qeth_get_elements_no() - find number of SBALEs for skb data, inc. frags. - * @card: qeth card structure, to check max. elems. - * @skb: SKB address - * @extra_elems: extra elems needed, to check against max. - * @data_offset: range starts at skb->data + data_offset - * - * Returns the number of pages, and thus QDIO buffer elements, needed to cover - * skb data, including linear part and fragments. Checks if the result plus - * extra_elems fits under the limit for the card. Returns 0 if it does not. - * Note: extra_elems is not included in the returned result. - */ -int qeth_get_elements_no(struct qeth_card *card, - struct sk_buff *skb, int extra_elems, int data_offset) -{ - int elements = qeth_count_elements(skb, data_offset); - - if ((elements + extra_elems) > QETH_MAX_BUFFER_ELEMENTS(card)) { - QETH_DBF_MESSAGE(2, "Invalid size of IP packet " - "(Number=%d / Length=%d). Discarded.\n", - elements + extra_elems, skb->len); - return 0; - } - return elements; -} -EXPORT_SYMBOL_GPL(qeth_get_elements_no); - -int qeth_hdr_chk_and_bounce(struct sk_buff *skb, struct qeth_hdr **hdr, int len) -{ - int hroom, inpage, rest; - - if (((unsigned long)skb->data & PAGE_MASK) != - (((unsigned long)skb->data + len - 1) & PAGE_MASK)) { - hroom = skb_headroom(skb); - inpage = PAGE_SIZE - ((unsigned long) skb->data % PAGE_SIZE); - rest = len - inpage; - if (rest > hroom) - return 1; - memmove(skb->data - rest, skb->data, skb_headlen(skb)); - skb->data -= rest; - skb->tail -= rest; - *hdr = (struct qeth_hdr *)skb->data; - QETH_DBF_MESSAGE(2, "skb bounce len: %d rest: %d\n", len, rest); - } - return 0; -} -EXPORT_SYMBOL_GPL(qeth_hdr_chk_and_bounce); +#define QETH_HDR_CACHE_OBJ_SIZE (sizeof(struct qeth_hdr_tso) + \ + MAX_TCP_HEADER) /** * qeth_add_hw_header() - add a HW header to an skb. @@ -3893,7 +3863,11 @@ check_layout: if (qeth_get_elements_for_range(start, end + contiguous) == 1) { /* Push HW header into same page as first protocol header. */ push_ok = true; - __elements = qeth_count_elements(skb, 0); + /* ... but TSO always needs a separate element for headers: */ + if (skb_is_gso(skb)) + __elements = 1 + qeth_count_elements(skb, proto_len); + else + __elements = qeth_count_elements(skb, 0); } else if (!proto_len && qeth_get_elements_for_range(start, end) == 1) { /* Push HW header into a new page. */ push_ok = true; @@ -3934,6 +3908,8 @@ check_layout: return hdr_len; } /* fall back */ + if (hdr_len + proto_len > QETH_HDR_CACHE_OBJ_SIZE) + return -E2BIG; *hdr = kmem_cache_alloc(qeth_core_header_cache, GFP_ATOMIC); if (!*hdr) return -ENOMEM; @@ -4175,6 +4151,66 @@ out: } EXPORT_SYMBOL_GPL(qeth_do_send_packet); +int qeth_xmit(struct qeth_card *card, struct sk_buff *skb, + struct qeth_qdio_out_q *queue, int ipv, int cast_type, + void (*fill_header)(struct qeth_card *card, struct qeth_hdr *hdr, + struct sk_buff *skb, int ipv, int cast_type, + unsigned int data_len)) +{ + const unsigned int proto_len = IS_IQD(card) ? ETH_HLEN : 0; + const unsigned int hw_hdr_len = sizeof(struct qeth_hdr); + unsigned int frame_len = skb->len; + unsigned int data_offset = 0; + struct qeth_hdr *hdr = NULL; + unsigned int hd_len = 0; + unsigned int elements; + int push_len, rc; + bool is_sg; + + rc = skb_cow_head(skb, hw_hdr_len); + if (rc) + return rc; + + push_len = qeth_add_hw_header(card, skb, &hdr, hw_hdr_len, proto_len, + &elements); + if (push_len < 0) + return push_len; + if (!push_len) { + /* HW header needs its own buffer element. */ + hd_len = hw_hdr_len + proto_len; + data_offset = proto_len; + } + memset(hdr, 0, hw_hdr_len); + fill_header(card, hdr, skb, ipv, cast_type, frame_len); + + is_sg = skb_is_nonlinear(skb); + if (IS_IQD(card)) { + rc = qeth_do_send_packet_fast(queue, skb, hdr, data_offset, + hd_len); + } else { + /* TODO: drop skb_orphan() once TX completion is fast enough */ + skb_orphan(skb); + rc = qeth_do_send_packet(card, queue, skb, hdr, data_offset, + hd_len, elements); + } + + if (!rc) { + if (card->options.performance_stats) { + card->perf_stats.buf_elements_sent += elements; + if (is_sg) + card->perf_stats.sg_skbs_sent++; + } + } else { + if (!push_len) + kmem_cache_free(qeth_core_header_cache, hdr); + if (rc == -EBUSY) + /* roll back to ETH header */ + skb_pull(skb, push_len); + } + return rc; +} +EXPORT_SYMBOL_GPL(qeth_xmit); + static int qeth_setadp_promisc_mode_cb(struct qeth_card *card, struct qeth_reply *reply, unsigned long data) { @@ -4699,7 +4735,7 @@ static int qeth_query_oat_command(struct qeth_card *card, char __user *udata) priv.buffer_len = oat_data.buffer_len; priv.response_len = 0; - priv.buffer = kzalloc(oat_data.buffer_len, GFP_KERNEL); + priv.buffer = vzalloc(oat_data.buffer_len); if (!priv.buffer) { rc = -ENOMEM; goto out; @@ -4740,7 +4776,7 @@ static int qeth_query_oat_command(struct qeth_card *card, char __user *udata) rc = -EFAULT; out_free: - kfree(priv.buffer); + vfree(priv.buffer); out: return rc; } @@ -5455,8 +5491,6 @@ struct qeth_cmd_buffer *qeth_get_setassparms_cmd(struct qeth_card *card, 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; @@ -5706,6 +5740,8 @@ static struct net_device *qeth_alloc_netdev(struct qeth_card *card) dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->hw_features |= NETIF_F_SG; dev->vlan_features |= NETIF_F_SG; + if (IS_IQD(card)) + dev->features |= NETIF_F_SG; } return dev; @@ -5728,7 +5764,6 @@ static int qeth_core_probe_device(struct ccwgroup_device *gdev) struct device *dev; int rc; enum qeth_discipline_id enforced_disc; - unsigned long flags; char dbf_name[DBF_NAME_LEN]; QETH_DBF_TEXT(SETUP, 2, "probedev"); @@ -5739,7 +5774,7 @@ static int qeth_core_probe_device(struct ccwgroup_device *gdev) QETH_DBF_TEXT_(SETUP, 2, "%s", dev_name(&gdev->dev)); - card = qeth_alloc_card(); + card = qeth_alloc_card(gdev); if (!card) { QETH_DBF_TEXT_(SETUP, 2, "1err%d", -ENOMEM); rc = -ENOMEM; @@ -5755,21 +5790,15 @@ static int qeth_core_probe_device(struct ccwgroup_device *gdev) goto err_card; } - card->read.ccwdev = gdev->cdev[0]; - card->write.ccwdev = gdev->cdev[1]; - card->data.ccwdev = gdev->cdev[2]; dev_set_drvdata(&gdev->dev, card); - card->gdev = gdev; - gdev->cdev[0]->handler = qeth_irq; - gdev->cdev[1]->handler = qeth_irq; - gdev->cdev[2]->handler = qeth_irq; - qeth_setup_card(card); qeth_update_from_chp_desc(card); card->dev = qeth_alloc_netdev(card); - if (!card->dev) + if (!card->dev) { + rc = -ENOMEM; goto err_card; + } qeth_determine_capabilities(card); enforced_disc = qeth_enforce_discipline(card); @@ -5792,9 +5821,9 @@ static int qeth_core_probe_device(struct ccwgroup_device *gdev) break; } - write_lock_irqsave(&qeth_core_card_list.rwlock, flags); + write_lock_irq(&qeth_core_card_list.rwlock); list_add_tail(&card->list, &qeth_core_card_list.list); - write_unlock_irqrestore(&qeth_core_card_list.rwlock, flags); + write_unlock_irq(&qeth_core_card_list.rwlock); return 0; err_disc: @@ -5810,7 +5839,6 @@ err_dev: static void qeth_core_remove_device(struct ccwgroup_device *gdev) { - unsigned long flags; struct qeth_card *card = dev_get_drvdata(&gdev->dev); QETH_DBF_TEXT(SETUP, 2, "removedv"); @@ -5820,9 +5848,9 @@ static void qeth_core_remove_device(struct ccwgroup_device *gdev) qeth_core_free_discipline(card); } - write_lock_irqsave(&qeth_core_card_list.rwlock, flags); + write_lock_irq(&qeth_core_card_list.rwlock); list_del(&card->list); - write_unlock_irqrestore(&qeth_core_card_list.rwlock, flags); + write_unlock_irq(&qeth_core_card_list.rwlock); free_netdev(card->dev); qeth_core_free_card(card); dev_set_drvdata(&gdev->dev, NULL); @@ -6614,8 +6642,10 @@ static int __init qeth_core_init(void) rc = PTR_ERR_OR_ZERO(qeth_core_root_dev); if (rc) goto register_err; - qeth_core_header_cache = kmem_cache_create("qeth_hdr", - sizeof(struct qeth_hdr) + ETH_HLEN, 64, 0, NULL); + qeth_core_header_cache = + kmem_cache_create("qeth_hdr", QETH_HDR_CACHE_OBJ_SIZE, + roundup_pow_of_two(QETH_HDR_CACHE_OBJ_SIZE), + 0, NULL); if (!qeth_core_header_cache) { rc = -ENOMEM; goto slab_err; diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 710fa74892ae..12858ffa28cf 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -193,15 +193,21 @@ static int qeth_l2_get_cast_type(struct qeth_card *card, struct sk_buff *skb) return RTN_UNICAST; } -static void qeth_l2_fill_header(struct qeth_hdr *hdr, struct sk_buff *skb, - int cast_type, unsigned int data_len) +static void qeth_l2_fill_header(struct qeth_card *card, struct qeth_hdr *hdr, + struct sk_buff *skb, int ipv, int cast_type, + unsigned int data_len) { struct vlan_ethhdr *veth = (struct vlan_ethhdr *)skb_mac_header(skb); - memset(hdr, 0, sizeof(struct qeth_hdr)); hdr->hdr.l2.id = QETH_HEADER_TYPE_LAYER2; hdr->hdr.l2.pkt_length = data_len; + if (skb->ip_summed == CHECKSUM_PARTIAL) { + qeth_tx_csum(skb, &hdr->hdr.l2.flags[1], ipv); + if (card->options.performance_stats) + card->perf_stats.tx_csum++; + } + /* set byte byte 3 to casting flags */ if (cast_type == RTN_MULTICAST) hdr->hdr.l2.flags[2] |= QETH_LAYER2_FLAG_MULTICAST; @@ -423,7 +429,7 @@ static int qeth_l2_process_inbound_buffer(struct qeth_card *card, default: dev_kfree_skb_any(skb); QETH_CARD_TEXT(card, 3, "inbunkno"); - QETH_DBF_HEX(CTRL, 3, hdr, QETH_DBF_CTRL_LEN); + QETH_DBF_HEX(CTRL, 3, hdr, sizeof(*hdr)); continue; } work_done++; @@ -641,84 +647,43 @@ static void qeth_l2_set_rx_mode(struct net_device *dev) qeth_promisc_to_bridge(card); } -static int qeth_l2_xmit(struct qeth_card *card, struct sk_buff *skb, - struct qeth_qdio_out_q *queue, int cast_type, int ipv) +static int qeth_l2_xmit_osn(struct qeth_card *card, struct sk_buff *skb, + struct qeth_qdio_out_q *queue) { - const unsigned int proto_len = IS_IQD(card) ? ETH_HLEN : 0; - const unsigned int hw_hdr_len = sizeof(struct qeth_hdr); - unsigned int frame_len = skb->len; - unsigned int data_offset = 0; - struct qeth_hdr *hdr = NULL; + struct qeth_hdr *hdr = (struct qeth_hdr *)skb->data; + addr_t end = (addr_t)(skb->data + sizeof(*hdr)); + addr_t start = (addr_t)skb->data; + unsigned int elements = 0; unsigned int hd_len = 0; - unsigned int elements; - int push_len, rc; - bool is_sg; + int rc; - rc = skb_cow_head(skb, hw_hdr_len); - if (rc) - return rc; + if (skb->protocol == htons(ETH_P_IPV6)) + return -EPROTONOSUPPORT; - push_len = qeth_add_hw_header(card, skb, &hdr, hw_hdr_len, proto_len, - &elements); - if (push_len < 0) - return push_len; - if (!push_len) { - /* HW header needs its own buffer element. */ - hd_len = hw_hdr_len + proto_len; - data_offset = proto_len; - } - qeth_l2_fill_header(hdr, skb, cast_type, frame_len); - if (skb->ip_summed == CHECKSUM_PARTIAL) { - qeth_tx_csum(skb, &hdr->hdr.l2.flags[1], ipv); - if (card->options.performance_stats) - card->perf_stats.tx_csum++; + if (qeth_get_elements_for_range(start, end) > 1) { + /* Misaligned HW header, move it to its own buffer element. */ + hdr = kmem_cache_alloc(qeth_core_header_cache, GFP_ATOMIC); + if (!hdr) + return -ENOMEM; + hd_len = sizeof(*hdr); + skb_copy_from_linear_data(skb, (char *)hdr, hd_len); + elements++; } - is_sg = skb_is_nonlinear(skb); - if (IS_IQD(card)) { - rc = qeth_do_send_packet_fast(queue, skb, hdr, data_offset, - hd_len); - } else { - /* TODO: drop skb_orphan() once TX completion is fast enough */ - skb_orphan(skb); - rc = qeth_do_send_packet(card, queue, skb, hdr, data_offset, - hd_len, elements); + elements += qeth_count_elements(skb, hd_len); + if (elements > QETH_MAX_BUFFER_ELEMENTS(card)) { + rc = -E2BIG; + goto out; } - if (!rc) { - if (card->options.performance_stats) { - card->perf_stats.buf_elements_sent += elements; - if (is_sg) - card->perf_stats.sg_skbs_sent++; - } - } else { - if (!push_len) - kmem_cache_free(qeth_core_header_cache, hdr); - if (rc == -EBUSY) - /* roll back to ETH header */ - skb_pull(skb, push_len); - } + rc = qeth_do_send_packet(card, queue, skb, hdr, hd_len, hd_len, + elements); +out: + if (rc && hd_len) + kmem_cache_free(qeth_core_header_cache, hdr); return rc; } -static int qeth_l2_xmit_osn(struct qeth_card *card, struct sk_buff *skb, - struct qeth_qdio_out_q *queue) -{ - unsigned int elements; - struct qeth_hdr *hdr; - - if (skb->protocol == htons(ETH_P_IPV6)) - return -EPROTONOSUPPORT; - - hdr = (struct qeth_hdr *)skb->data; - elements = qeth_get_elements_no(card, skb, 0, 0); - if (!elements) - return -E2BIG; - if (qeth_hdr_chk_and_bounce(skb, &hdr, sizeof(*hdr))) - return -EINVAL; - return qeth_do_send_packet(card, queue, skb, hdr, 0, 0, elements); -} - static netdev_tx_t qeth_l2_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) { @@ -745,7 +710,8 @@ static netdev_tx_t qeth_l2_hard_start_xmit(struct sk_buff *skb, if (IS_OSN(card)) rc = qeth_l2_xmit_osn(card, skb, queue); else - rc = qeth_l2_xmit(card, skb, queue, cast_type, ipv); + rc = qeth_xmit(card, skb, queue, ipv, cast_type, + qeth_l2_fill_header); if (!rc) { card->stats.tx_packets++; @@ -789,7 +755,10 @@ static int __qeth_l2_open(struct net_device *dev) if (qdio_stop_irq(card->data.ccwdev, 0) >= 0) { napi_enable(&card->napi); + local_bh_disable(); napi_schedule(&card->napi); + /* kick-start the NAPI softirq: */ + local_bh_enable(); } else rc = -EIO; return rc; @@ -1240,7 +1209,6 @@ static int qeth_osn_send_control_data(struct qeth_card *card, int len, struct qeth_cmd_buffer *iob) { struct qeth_channel *channel = iob->channel; - unsigned long flags; int rc = 0; QETH_CARD_TEXT(card, 5, "osndctrd"); @@ -1249,10 +1217,10 @@ static int qeth_osn_send_control_data(struct qeth_card *card, int len, atomic_cmpxchg(&channel->irq_pending, 0, 1) == 0); qeth_prepare_control_data(card, len, iob); QETH_CARD_TEXT(card, 6, "osnoirqp"); - spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags); + spin_lock_irq(get_ccwdev_lock(channel->ccwdev)); rc = ccw_device_start_timeout(channel->ccwdev, channel->ccw, (addr_t) iob, 0, 0, QETH_IPA_TIMEOUT); - spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags); + spin_unlock_irq(get_ccwdev_lock(channel->ccwdev)); if (rc) { QETH_DBF_MESSAGE(2, "qeth_osn_send_control_data: " "ccw_device_start rc = %i\n", rc); diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index 7175086677fb..8930d2a9fcad 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -33,7 +33,6 @@ #include <net/ipv6.h> #include <net/ip6_route.h> #include <net/ip6_fib.h> -#include <net/ip6_checksum.h> #include <net/iucv/af_iucv.h> #include <linux/hashtable.h> @@ -1390,7 +1389,7 @@ static int qeth_l3_process_inbound_buffer(struct qeth_card *card, default: dev_kfree_skb_any(skb); QETH_CARD_TEXT(card, 3, "inbunkno"); - QETH_DBF_HEX(CTRL, 3, hdr, QETH_DBF_CTRL_LEN); + QETH_DBF_HEX(CTRL, 3, hdr, sizeof(*hdr)); continue; } work_done++; @@ -1983,21 +1982,23 @@ static int qeth_l3_get_cast_type(struct sk_buff *skb) rcu_read_unlock(); /* no neighbour (eg AF_PACKET), fall back to target's IP address ... */ - if (be16_to_cpu(skb->protocol) == ETH_P_IPV6) - return ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr) ? - RTN_MULTICAST : RTN_UNICAST; - else if (be16_to_cpu(skb->protocol) == ETH_P_IP) + switch (qeth_get_ip_version(skb)) { + case 4: return ipv4_is_multicast(ip_hdr(skb)->daddr) ? RTN_MULTICAST : RTN_UNICAST; - - /* ... and MAC address */ - if (ether_addr_equal_64bits(eth_hdr(skb)->h_dest, skb->dev->broadcast)) - return RTN_BROADCAST; - if (is_multicast_ether_addr(eth_hdr(skb)->h_dest)) - return RTN_MULTICAST; - - /* default to unicast */ - return RTN_UNICAST; + case 6: + return ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr) ? + RTN_MULTICAST : RTN_UNICAST; + default: + /* ... and MAC address */ + if (ether_addr_equal_64bits(eth_hdr(skb)->h_dest, + skb->dev->broadcast)) + return RTN_BROADCAST; + if (is_multicast_ether_addr(eth_hdr(skb)->h_dest)) + return RTN_MULTICAST; + /* default to unicast */ + return RTN_UNICAST; + } } static void qeth_l3_fill_af_iucv_hdr(struct qeth_hdr *hdr, struct sk_buff *skb, @@ -2006,7 +2007,6 @@ static void qeth_l3_fill_af_iucv_hdr(struct qeth_hdr *hdr, struct sk_buff *skb, char daddr[16]; struct af_iucv_trans_hdr *iucv_hdr; - memset(hdr, 0, sizeof(struct qeth_hdr)); hdr->hdr.l3.id = QETH_HEADER_TYPE_LAYER3; hdr->hdr.l3.length = data_len; hdr->hdr.l3.flags = QETH_HDR_IPV6 | QETH_CAST_UNICAST; @@ -2034,26 +2034,33 @@ static void qeth_l3_fill_header(struct qeth_card *card, struct qeth_hdr *hdr, struct sk_buff *skb, int ipv, int cast_type, unsigned int data_len) { - memset(hdr, 0, sizeof(struct qeth_hdr)); - hdr->hdr.l3.id = QETH_HEADER_TYPE_LAYER3; + struct vlan_ethhdr *veth = vlan_eth_hdr(skb); + hdr->hdr.l3.length = data_len; - /* - * before we're going to overwrite this location with next hop ip. - * v6 uses passthrough, v4 sets the tag in the QDIO header. - */ - if (skb_vlan_tag_present(skb)) { - if ((ipv == 4) || (card->info.type == QETH_CARD_TYPE_IQD)) - hdr->hdr.l3.ext_flags = QETH_HDR_EXT_VLAN_FRAME; - else - hdr->hdr.l3.ext_flags = QETH_HDR_EXT_INCLUDE_VLAN_TAG; - hdr->hdr.l3.vlan_id = skb_vlan_tag_get(skb); + if (skb_is_gso(skb)) { + hdr->hdr.l3.id = QETH_HEADER_TYPE_TSO; + } else { + hdr->hdr.l3.id = QETH_HEADER_TYPE_LAYER3; + if (skb->ip_summed == CHECKSUM_PARTIAL) { + qeth_tx_csum(skb, &hdr->hdr.l3.ext_flags, ipv); + /* some HW requires combined L3+L4 csum offload: */ + if (ipv == 4) + hdr->hdr.l3.ext_flags |= QETH_HDR_EXT_CSUM_HDR_REQ; + if (card->options.performance_stats) + card->perf_stats.tx_csum++; + } } - if (!skb_is_gso(skb) && skb->ip_summed == CHECKSUM_PARTIAL) { - qeth_tx_csum(skb, &hdr->hdr.l3.ext_flags, ipv); - if (card->options.performance_stats) - card->perf_stats.tx_csum++; + if (ipv == 4 || IS_IQD(card)) { + /* NETIF_F_HW_VLAN_CTAG_TX */ + if (skb_vlan_tag_present(skb)) { + hdr->hdr.l3.ext_flags |= QETH_HDR_EXT_VLAN_FRAME; + hdr->hdr.l3.vlan_id = skb_vlan_tag_get(skb); + } + } else if (veth->h_vlan_proto == htons(ETH_P_8021Q)) { + hdr->hdr.l3.ext_flags |= QETH_HDR_EXT_INCLUDE_VLAN_TAG; + hdr->hdr.l3.vlan_id = ntohs(veth->h_vlan_TCI); } /* OSA only: */ @@ -2094,85 +2101,57 @@ static void qeth_l3_fill_header(struct qeth_card *card, struct qeth_hdr *hdr, rcu_read_unlock(); } -static void qeth_tso_fill_header(struct qeth_card *card, - struct qeth_hdr *qhdr, struct sk_buff *skb) +static void qeth_l3_fill_tso_ext(struct qeth_hdr_tso *hdr, + unsigned int payload_len, struct sk_buff *skb, + unsigned int proto_len) { - struct qeth_hdr_tso *hdr = (struct qeth_hdr_tso *)qhdr; - struct tcphdr *tcph = tcp_hdr(skb); - struct iphdr *iph = ip_hdr(skb); - struct ipv6hdr *ip6h = ipv6_hdr(skb); - - /*fix header to TSO values ...*/ - hdr->hdr.hdr.l3.id = QETH_HEADER_TYPE_TSO; - /*set values which are fix for the first approach ...*/ - hdr->ext.hdr_tot_len = (__u16) sizeof(struct qeth_hdr_ext_tso); - hdr->ext.imb_hdr_no = 1; - hdr->ext.hdr_type = 1; - hdr->ext.hdr_version = 1; - hdr->ext.hdr_len = 28; - /*insert non-fix values */ - hdr->ext.mss = skb_shinfo(skb)->gso_size; - hdr->ext.dg_hdr_len = (__u16)(ip_hdrlen(skb) + tcp_hdrlen(skb)); - hdr->ext.payload_len = (__u16)(skb->len - hdr->ext.dg_hdr_len - - sizeof(struct qeth_hdr_tso)); - tcph->check = 0; - if (be16_to_cpu(skb->protocol) == ETH_P_IPV6) { - ip6h->payload_len = 0; - tcph->check = ~csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, - 0, IPPROTO_TCP, 0); - } else { - /*OSA want us to set these values ...*/ - tcph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, - 0, IPPROTO_TCP, 0); - iph->tot_len = 0; - iph->check = 0; - } + struct qeth_hdr_ext_tso *ext = &hdr->ext; + + ext->hdr_tot_len = sizeof(*ext); + ext->imb_hdr_no = 1; + ext->hdr_type = 1; + ext->hdr_version = 1; + ext->hdr_len = 28; + ext->payload_len = payload_len; + ext->mss = skb_shinfo(skb)->gso_size; + ext->dg_hdr_len = proto_len; } -/** - * qeth_l3_get_elements_no_tso() - find number of SBALEs for skb data for tso - * @card: qeth card structure, to check max. elems. - * @skb: SKB address - * @extra_elems: extra elems needed, to check against max. - * - * Returns the number of pages, and thus QDIO buffer elements, needed to cover - * skb data, including linear part and fragments, but excluding TCP header. - * (Exclusion of TCP header distinguishes it from qeth_get_elements_no().) - * Checks if the result plus extra_elems fits under the limit for the card. - * Returns 0 if it does not. - * Note: extra_elems is not included in the returned result. - */ -static int qeth_l3_get_elements_no_tso(struct qeth_card *card, - struct sk_buff *skb, int extra_elems) +static void qeth_l3_fixup_headers(struct sk_buff *skb) { - addr_t start = (addr_t)tcp_hdr(skb) + tcp_hdrlen(skb); - addr_t end = (addr_t)skb->data + skb_headlen(skb); - int elements = qeth_get_elements_for_frags(skb); - - if (start != end) - elements += qeth_get_elements_for_range(start, end); + struct iphdr *iph = ip_hdr(skb); - if ((elements + extra_elems) > QETH_MAX_BUFFER_ELEMENTS(card)) { - QETH_DBF_MESSAGE(2, - "Invalid size of TSO IP packet (Number=%d / Length=%d). Discarded.\n", - elements + extra_elems, skb->len); - return 0; + /* this is safe, IPv6 traffic takes a different path */ + if (skb->ip_summed == CHECKSUM_PARTIAL) + iph->check = 0; + if (skb_is_gso(skb)) { + iph->tot_len = 0; + tcp_hdr(skb)->check = ~tcp_v4_check(0, iph->saddr, + iph->daddr, 0); } - return elements; } -static int qeth_l3_xmit_offload(struct qeth_card *card, struct sk_buff *skb, - struct qeth_qdio_out_q *queue, int ipv, - int cast_type) +static int qeth_l3_xmit(struct qeth_card *card, struct sk_buff *skb, + struct qeth_qdio_out_q *queue, int ipv, int cast_type) { - const unsigned int hw_hdr_len = sizeof(struct qeth_hdr); - unsigned int frame_len, elements; + unsigned int hw_hdr_len, proto_len, frame_len, elements; unsigned char eth_hdr[ETH_HLEN]; + bool is_tso = skb_is_gso(skb); + unsigned int data_offset = 0; struct qeth_hdr *hdr = NULL; unsigned int hd_len = 0; int push_len, rc; bool is_sg; + if (is_tso) { + hw_hdr_len = sizeof(struct qeth_hdr_tso); + proto_len = skb_transport_offset(skb) + tcp_hdrlen(skb) - + ETH_HLEN; + } else { + hw_hdr_len = sizeof(struct qeth_hdr); + proto_len = 0; + } + /* re-use the L2 header area for the HW header: */ rc = skb_cow_head(skb, hw_hdr_len - ETH_HLEN); if (rc) @@ -2181,28 +2160,37 @@ static int qeth_l3_xmit_offload(struct qeth_card *card, struct sk_buff *skb, skb_pull(skb, ETH_HLEN); frame_len = skb->len; - push_len = qeth_add_hw_header(card, skb, &hdr, hw_hdr_len, 0, + qeth_l3_fixup_headers(skb); + push_len = qeth_add_hw_header(card, skb, &hdr, hw_hdr_len, proto_len, &elements); if (push_len < 0) return push_len; - if (!push_len) { - /* hdr was added discontiguous from skb->data */ - hd_len = hw_hdr_len; + if (is_tso || !push_len) { + /* HW header needs its own buffer element. */ + hd_len = hw_hdr_len + proto_len; + data_offset = push_len + proto_len; } + memset(hdr, 0, hw_hdr_len); - if (skb->protocol == htons(ETH_P_AF_IUCV)) + if (skb->protocol == htons(ETH_P_AF_IUCV)) { qeth_l3_fill_af_iucv_hdr(hdr, skb, frame_len); - else + } else { qeth_l3_fill_header(card, hdr, skb, ipv, cast_type, frame_len); + if (is_tso) + qeth_l3_fill_tso_ext((struct qeth_hdr_tso *) hdr, + frame_len - proto_len, skb, + proto_len); + } is_sg = skb_is_nonlinear(skb); if (IS_IQD(card)) { - rc = qeth_do_send_packet_fast(queue, skb, hdr, 0, hd_len); + rc = qeth_do_send_packet_fast(queue, skb, hdr, data_offset, + hd_len); } else { /* TODO: drop skb_orphan() once TX completion is fast enough */ skb_orphan(skb); - rc = qeth_do_send_packet(card, queue, skb, hdr, 0, hd_len, - elements); + rc = qeth_do_send_packet(card, queue, skb, hdr, data_offset, + hd_len, elements); } if (!rc) { @@ -2210,6 +2198,10 @@ static int qeth_l3_xmit_offload(struct qeth_card *card, struct sk_buff *skb, card->perf_stats.buf_elements_sent += elements; if (is_sg) card->perf_stats.sg_skbs_sent++; + if (is_tso) { + card->perf_stats.large_send_bytes += frame_len; + card->perf_stats.large_send_cnt++; + } } } else { if (!push_len) @@ -2224,118 +2216,6 @@ static int qeth_l3_xmit_offload(struct qeth_card *card, struct sk_buff *skb, return rc; } -static int qeth_l3_xmit(struct qeth_card *card, struct sk_buff *skb, - struct qeth_qdio_out_q *queue, int ipv, int cast_type) -{ - int elements, len, rc; - __be16 *tag; - struct qeth_hdr *hdr = NULL; - int hdr_elements = 0; - struct sk_buff *new_skb = NULL; - int tx_bytes = skb->len; - unsigned int hd_len; - bool use_tso, is_sg; - - /* Ignore segment size from skb_is_gso(), 1 page is always used. */ - use_tso = skb_is_gso(skb) && - (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4); - - /* create a clone with writeable headroom */ - new_skb = skb_realloc_headroom(skb, sizeof(struct qeth_hdr_tso) + - VLAN_HLEN); - if (!new_skb) - return -ENOMEM; - - if (ipv == 4) { - skb_pull(new_skb, ETH_HLEN); - } else if (skb_vlan_tag_present(new_skb)) { - skb_push(new_skb, VLAN_HLEN); - skb_copy_to_linear_data(new_skb, new_skb->data + 4, 4); - skb_copy_to_linear_data_offset(new_skb, 4, - new_skb->data + 8, 4); - skb_copy_to_linear_data_offset(new_skb, 8, - new_skb->data + 12, 4); - tag = (__be16 *)(new_skb->data + 12); - *tag = cpu_to_be16(ETH_P_8021Q); - *(tag + 1) = cpu_to_be16(skb_vlan_tag_get(new_skb)); - } - - /* fix hardware limitation: as long as we do not have sbal - * chaining we can not send long frag lists - */ - if ((use_tso && !qeth_l3_get_elements_no_tso(card, new_skb, 1)) || - (!use_tso && !qeth_get_elements_no(card, new_skb, 0, 0))) { - rc = skb_linearize(new_skb); - - if (card->options.performance_stats) { - if (rc) - card->perf_stats.tx_linfail++; - else - card->perf_stats.tx_lin++; - } - if (rc) - goto out; - } - - if (use_tso) { - hdr = skb_push(new_skb, sizeof(struct qeth_hdr_tso)); - memset(hdr, 0, sizeof(struct qeth_hdr_tso)); - qeth_l3_fill_header(card, hdr, new_skb, ipv, cast_type, - new_skb->len - sizeof(struct qeth_hdr_tso)); - qeth_tso_fill_header(card, hdr, new_skb); - hdr_elements++; - } else { - hdr = skb_push(new_skb, sizeof(struct qeth_hdr)); - qeth_l3_fill_header(card, hdr, new_skb, ipv, cast_type, - new_skb->len - sizeof(struct qeth_hdr)); - } - - elements = use_tso ? - qeth_l3_get_elements_no_tso(card, new_skb, hdr_elements) : - qeth_get_elements_no(card, new_skb, hdr_elements, 0); - if (!elements) { - rc = -E2BIG; - goto out; - } - elements += hdr_elements; - - if (use_tso) { - hd_len = sizeof(struct qeth_hdr_tso) + - ip_hdrlen(new_skb) + tcp_hdrlen(new_skb); - len = hd_len; - } else { - hd_len = 0; - len = sizeof(struct qeth_hdr_layer3); - } - - if (qeth_hdr_chk_and_bounce(new_skb, &hdr, len)) { - rc = -EINVAL; - goto out; - } - - is_sg = skb_is_nonlinear(new_skb); - rc = qeth_do_send_packet(card, queue, new_skb, hdr, hd_len, hd_len, - elements); -out: - if (!rc) { - if (new_skb != skb) - dev_kfree_skb_any(skb); - if (card->options.performance_stats) { - card->perf_stats.buf_elements_sent += elements; - if (is_sg) - card->perf_stats.sg_skbs_sent++; - if (use_tso) { - card->perf_stats.large_send_bytes += tx_bytes; - card->perf_stats.large_send_cnt++; - } - } - } else { - if (new_skb != skb) - dev_kfree_skb_any(new_skb); - } - return rc; -} - static netdev_tx_t qeth_l3_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) { @@ -2371,10 +2251,11 @@ static netdev_tx_t qeth_l3_hard_start_xmit(struct sk_buff *skb, } netif_stop_queue(dev); - if (IS_IQD(card) || (!skb_is_gso(skb) && ipv == 4)) - rc = qeth_l3_xmit_offload(card, skb, queue, ipv, cast_type); - else + if (ipv == 4 || IS_IQD(card)) rc = qeth_l3_xmit(card, skb, queue, ipv, cast_type); + else + rc = qeth_xmit(card, skb, queue, ipv, cast_type, + qeth_l3_fill_header); if (!rc) { card->stats.tx_packets++; @@ -2412,7 +2293,10 @@ static int __qeth_l3_open(struct net_device *dev) if (qdio_stop_irq(card->data.ccwdev, 0) >= 0) { napi_enable(&card->napi); + local_bh_disable(); napi_schedule(&card->napi); + /* kick-start the NAPI softirq: */ + local_bh_enable(); } else rc = -EIO; return rc; @@ -2476,6 +2360,15 @@ qeth_l3_neigh_setup(struct net_device *dev, struct neigh_parms *np) return 0; } +static netdev_features_t qeth_l3_osa_features_check(struct sk_buff *skb, + struct net_device *dev, + netdev_features_t features) +{ + if (qeth_get_ip_version(skb) != 4) + features &= ~NETIF_F_HW_VLAN_CTAG_TX; + return qeth_features_check(skb, dev, features); +} + static const struct net_device_ops qeth_l3_netdev_ops = { .ndo_open = qeth_l3_open, .ndo_stop = qeth_l3_stop, @@ -2496,7 +2389,7 @@ static const struct net_device_ops qeth_l3_osa_netdev_ops = { .ndo_stop = qeth_l3_stop, .ndo_get_stats = qeth_get_stats, .ndo_start_xmit = qeth_l3_hard_start_xmit, - .ndo_features_check = qeth_features_check, + .ndo_features_check = qeth_l3_osa_features_check, .ndo_validate_addr = eth_validate_addr, .ndo_set_rx_mode = qeth_l3_set_rx_mode, .ndo_do_ioctl = qeth_do_ioctl, @@ -2524,6 +2417,11 @@ static int qeth_l3_setup_netdev(struct qeth_card *card) } card->dev->netdev_ops = &qeth_l3_osa_netdev_ops; + card->dev->needed_headroom = sizeof(struct qeth_hdr); + /* allow for de-acceleration of NETIF_F_HW_VLAN_CTAG_TX: */ + card->dev->needed_headroom += VLAN_HLEN; + if (qeth_is_supported(card, IPA_OUTBOUND_TSO)) + card->dev->needed_headroom = sizeof(struct qeth_hdr_tso); /*IPv6 address autoconfiguration stuff*/ qeth_l3_get_unique_id(card); @@ -2545,6 +2443,7 @@ static int qeth_l3_setup_netdev(struct qeth_card *card) } else if (card->info.type == QETH_CARD_TYPE_IQD) { card->dev->flags |= IFF_NOARP; card->dev->netdev_ops = &qeth_l3_netdev_ops; + card->dev->needed_headroom = sizeof(struct qeth_hdr) - ETH_HLEN; rc = qeth_l3_iqd_read_initial_mac(card); if (rc) @@ -2556,7 +2455,6 @@ static int qeth_l3_setup_netdev(struct qeth_card *card) return -ENODEV; card->dev->ethtool_ops = &qeth_l3_ethtool_ops; - card->dev->needed_headroom = sizeof(struct qeth_hdr) - ETH_HLEN; card->dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER; diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index 8fc851a9e116..7c097006c54d 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -52,12 +52,12 @@ config SCSI_MQ_DEFAULT default y depends on SCSI ---help--- - This option enables the new blk-mq based I/O path for SCSI - devices by default. With the option the scsi_mod.use_blk_mq - module/boot option defaults to Y, without it to N, but it can - still be overridden either way. + This option enables the blk-mq based I/O path for SCSI devices by + default. With this option the scsi_mod.use_blk_mq module/boot + option defaults to Y, without it to N, but it can still be + overridden either way. - If unsure say N. + If unsure say Y. config SCSI_PROC_FS bool "legacy /proc/scsi/ support" diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h index 29bf1e60f542..39eb415987fc 100644 --- a/drivers/scsi/aacraid/aacraid.h +++ b/drivers/scsi/aacraid/aacraid.h @@ -1346,7 +1346,7 @@ struct fib { struct aac_hba_map_info { __le32 rmw_nexus; /* nexus for native HBA devices */ u8 devtype; /* device type */ - u8 reset_state; /* 0 - no reset, 1..x - */ + s8 reset_state; /* 0 - no reset, 1..x - */ /* after xth TM LUN reset */ u16 qd_limit; u32 scan_counter; diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c index f00045813378..27c8d6ba05bb 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c +++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c @@ -150,15 +150,11 @@ static void bnx2fc_clean_rx_queue(struct fc_lport *lp) struct fcoe_rcv_info *fr; struct sk_buff_head *list; struct sk_buff *skb, *next; - struct sk_buff *head; bg = &bnx2fc_global; spin_lock_bh(&bg->fcoe_rx_list.lock); list = &bg->fcoe_rx_list; - head = list->next; - for (skb = head; skb != (struct sk_buff *)list; - skb = next) { - next = skb->next; + skb_queue_walk_safe(list, skb, next) { fr = fcoe_dev_from_skb(skb); if (fr->fr_dev == lp) { __skb_unlink(skb, list); diff --git a/drivers/scsi/csiostor/csio_hw.c b/drivers/scsi/csiostor/csio_hw.c index 23d07e9f87d0..e51923886475 100644 --- a/drivers/scsi/csiostor/csio_hw.c +++ b/drivers/scsi/csiostor/csio_hw.c @@ -1602,6 +1602,46 @@ fw_port_cap32_t fwcaps16_to_caps32(fw_port_cap16_t caps16) } /** + * fwcaps32_to_caps16 - convert 32-bit Port Capabilities to 16-bits + * @caps32: a 32-bit Port Capabilities value + * + * Returns the equivalent 16-bit Port Capabilities value. Note that + * not all 32-bit Port Capabilities can be represented in the 16-bit + * Port Capabilities and some fields/values may not make it. + */ +fw_port_cap16_t fwcaps32_to_caps16(fw_port_cap32_t caps32) +{ + fw_port_cap16_t caps16 = 0; + + #define CAP32_TO_CAP16(__cap) \ + do { \ + if (caps32 & FW_PORT_CAP32_##__cap) \ + caps16 |= FW_PORT_CAP_##__cap; \ + } while (0) + + CAP32_TO_CAP16(SPEED_100M); + CAP32_TO_CAP16(SPEED_1G); + CAP32_TO_CAP16(SPEED_10G); + CAP32_TO_CAP16(SPEED_25G); + CAP32_TO_CAP16(SPEED_40G); + CAP32_TO_CAP16(SPEED_100G); + CAP32_TO_CAP16(FC_RX); + CAP32_TO_CAP16(FC_TX); + CAP32_TO_CAP16(802_3_PAUSE); + CAP32_TO_CAP16(802_3_ASM_DIR); + CAP32_TO_CAP16(ANEG); + CAP32_TO_CAP16(FORCE_PAUSE); + CAP32_TO_CAP16(MDIAUTO); + CAP32_TO_CAP16(MDISTRAIGHT); + CAP32_TO_CAP16(FEC_RS); + CAP32_TO_CAP16(FEC_BASER_RS); + + #undef CAP32_TO_CAP16 + + return caps16; +} + +/** * lstatus_to_fwcap - translate old lstatus to 32-bit Port Capabilities * @lstatus: old FW_PORT_ACTION_GET_PORT_INFO lstatus value * @@ -1759,7 +1799,7 @@ csio_enable_ports(struct csio_hw *hw) val = 1; csio_mb_params(hw, mbp, CSIO_MB_DEFAULT_TMO, - hw->pfn, 0, 1, ¶m, &val, false, + hw->pfn, 0, 1, ¶m, &val, true, NULL); if (csio_mb_issue(hw, mbp)) { @@ -1769,16 +1809,9 @@ csio_enable_ports(struct csio_hw *hw) return -EINVAL; } - csio_mb_process_read_params_rsp(hw, mbp, &retval, 1, - &val); - if (retval != FW_SUCCESS) { - csio_err(hw, "FW_PARAMS_CMD(r) port:%d failed: 0x%x\n", - portid, retval); - mempool_free(mbp, hw->mb_mempool); - return -EINVAL; - } - - fw_caps = val; + csio_mb_process_read_params_rsp(hw, mbp, &retval, + 0, NULL); + fw_caps = retval ? FW_CAPS16 : FW_CAPS32; } /* Read PORT information */ @@ -2364,8 +2397,8 @@ bye: } /* - * Returns -EINVAL if attempts to flash the firmware failed - * else returns 0, + * Returns -EINVAL if attempts to flash the firmware failed, + * -ENOMEM if memory allocation failed else returns 0, * if flashing was not attempted because the card had the * latest firmware ECANCELED is returned */ @@ -2393,6 +2426,13 @@ csio_hw_flash_fw(struct csio_hw *hw, int *reset) return -EINVAL; } + /* allocate memory to read the header of the firmware on the + * card + */ + card_fw = kmalloc(sizeof(*card_fw), GFP_KERNEL); + if (!card_fw) + return -ENOMEM; + if (csio_is_t5(pci_dev->device & CSIO_HW_CHIP_MASK)) fw_bin_file = FW_FNAME_T5; else @@ -2406,11 +2446,6 @@ csio_hw_flash_fw(struct csio_hw *hw, int *reset) fw_size = fw->size; } - /* allocate memory to read the header of the firmware on the - * card - */ - card_fw = kmalloc(sizeof(*card_fw), GFP_KERNEL); - /* upgrade FW logic */ ret = csio_hw_prep_fw(hw, fw_info, fw_data, fw_size, card_fw, hw->fw_state, reset); diff --git a/drivers/scsi/csiostor/csio_hw.h b/drivers/scsi/csiostor/csio_hw.h index 9e73ef771eb7..e351af6e7c81 100644 --- a/drivers/scsi/csiostor/csio_hw.h +++ b/drivers/scsi/csiostor/csio_hw.h @@ -639,6 +639,7 @@ int csio_handle_intr_status(struct csio_hw *, unsigned int, fw_port_cap32_t fwcap_to_fwspeed(fw_port_cap32_t acaps); fw_port_cap32_t fwcaps16_to_caps32(fw_port_cap16_t caps16); +fw_port_cap16_t fwcaps32_to_caps16(fw_port_cap32_t caps32); fw_port_cap32_t lstatus_to_fwcap(u32 lstatus); int csio_hw_start(struct csio_hw *); diff --git a/drivers/scsi/csiostor/csio_mb.c b/drivers/scsi/csiostor/csio_mb.c index c026417269c3..6f13673d6aa0 100644 --- a/drivers/scsi/csiostor/csio_mb.c +++ b/drivers/scsi/csiostor/csio_mb.c @@ -368,7 +368,7 @@ csio_mb_port(struct csio_hw *hw, struct csio_mb *mbp, uint32_t tmo, FW_CMD_LEN16_V(sizeof(*cmdp) / 16)); if (fw_caps == FW_CAPS16) - cmdp->u.l1cfg.rcap = cpu_to_be32(fc); + cmdp->u.l1cfg.rcap = cpu_to_be32(fwcaps32_to_caps16(fc)); else cmdp->u.l1cfg32.rcap32 = cpu_to_be32(fc); } @@ -395,8 +395,8 @@ csio_mb_process_read_port_rsp(struct csio_hw *hw, struct csio_mb *mbp, *pcaps = fwcaps16_to_caps32(ntohs(rsp->u.info.pcap)); *acaps = fwcaps16_to_caps32(ntohs(rsp->u.info.acap)); } else { - *pcaps = ntohs(rsp->u.info32.pcaps32); - *acaps = ntohs(rsp->u.info32.acaps32); + *pcaps = be32_to_cpu(rsp->u.info32.pcaps32); + *acaps = be32_to_cpu(rsp->u.info32.acaps32); } } } diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c index 3f3af5e74a07..75f876409fb9 100644 --- a/drivers/scsi/cxgbi/libcxgbi.c +++ b/drivers/scsi/cxgbi/libcxgbi.c @@ -784,7 +784,8 @@ cxgbi_check_route6(struct sockaddr *dst_addr, int ifindex) csk->mtu = mtu; csk->dst = dst; - if (ipv6_addr_any(&rt->rt6i_prefsrc.addr)) { + rt6_get_prefsrc(rt, &pref_saddr); + if (ipv6_addr_any(&pref_saddr)) { struct inet6_dev *idev = ip6_dst_idev((struct dst_entry *)rt); err = ipv6_dev_get_saddr(&init_net, idev ? idev->dev : NULL, @@ -794,8 +795,6 @@ cxgbi_check_route6(struct sockaddr *dst_addr, int ifindex) &daddr6->sin6_addr); goto rel_rt; } - } else { - pref_saddr = rt->rt6i_prefsrc.addr; } csk->csk_family = AF_INET6; diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c index f02dcc875a09..ea4b0bb0c1cd 100644 --- a/drivers/scsi/hosts.c +++ b/drivers/scsi/hosts.c @@ -563,35 +563,13 @@ struct Scsi_Host *scsi_host_get(struct Scsi_Host *shost) } EXPORT_SYMBOL(scsi_host_get); -struct scsi_host_mq_in_flight { - int cnt; -}; - -static void scsi_host_check_in_flight(struct request *rq, void *data, - bool reserved) -{ - struct scsi_host_mq_in_flight *in_flight = data; - - if (blk_mq_request_started(rq)) - in_flight->cnt++; -} - /** * scsi_host_busy - Return the host busy counter * @shost: Pointer to Scsi_Host to inc. **/ int scsi_host_busy(struct Scsi_Host *shost) { - struct scsi_host_mq_in_flight in_flight = { - .cnt = 0, - }; - - if (!shost->use_blk_mq) - return atomic_read(&shost->host_busy); - - blk_mq_tagset_busy_iter(&shost->tag_set, scsi_host_check_in_flight, - &in_flight); - return in_flight.cnt; + return atomic_read(&shost->host_busy); } EXPORT_SYMBOL(scsi_host_busy); diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c index 58bb70b886d7..c120929d4ffe 100644 --- a/drivers/scsi/hpsa.c +++ b/drivers/scsi/hpsa.c @@ -976,7 +976,7 @@ static struct scsi_host_template hpsa_driver_template = { #endif .sdev_attrs = hpsa_sdev_attrs, .shost_attrs = hpsa_shost_attrs, - .max_sectors = 1024, + .max_sectors = 2048, .no_write_same = 1, }; diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h index e0d0da5f43d6..43732e8d1347 100644 --- a/drivers/scsi/lpfc/lpfc.h +++ b/drivers/scsi/lpfc/lpfc.h @@ -672,7 +672,7 @@ struct lpfc_hba { #define LS_NPIV_FAB_SUPPORTED 0x2 /* Fabric supports NPIV */ #define LS_IGNORE_ERATT 0x4 /* intr handler should ignore ERATT */ #define LS_MDS_LINK_DOWN 0x8 /* MDS Diagnostics Link Down */ -#define LS_MDS_LOOPBACK 0x16 /* MDS Diagnostics Link Up (Loopback) */ +#define LS_MDS_LOOPBACK 0x10 /* MDS Diagnostics Link Up (Loopback) */ uint32_t hba_flag; /* hba generic flags */ #define HBA_ERATT_HANDLED 0x1 /* This flag is set when eratt handled */ diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c index 5a25553415f8..057a60abe664 100644 --- a/drivers/scsi/lpfc/lpfc_attr.c +++ b/drivers/scsi/lpfc/lpfc_attr.c @@ -5122,16 +5122,16 @@ LPFC_ATTR_R(enable_SmartSAN, 0, 0, 1, "Enable SmartSAN functionality"); /* # lpfc_fdmi_on: Controls FDMI support. -# 0 No FDMI support (default) -# 1 Traditional FDMI support +# 0 No FDMI support +# 1 Traditional FDMI support (default) # Traditional FDMI support means the driver will assume FDMI-2 support; # however, if that fails, it will fallback to FDMI-1. # If lpfc_enable_SmartSAN is set to 1, the driver ignores lpfc_fdmi_on. # If lpfc_enable_SmartSAN is set 0, the driver uses the current value of # lpfc_fdmi_on. -# Value range [0,1]. Default value is 0. +# Value range [0,1]. Default value is 1. */ -LPFC_ATTR_R(fdmi_on, 0, 0, 1, "Enable FDMI support"); +LPFC_ATTR_R(fdmi_on, 1, 0, 1, "Enable FDMI support"); /* # Specifies the maximum number of ELS cmds we can have outstanding (for diff --git a/drivers/scsi/qedi/qedi.h b/drivers/scsi/qedi/qedi.h index fc3babc15fa3..a6f96b35e971 100644 --- a/drivers/scsi/qedi/qedi.h +++ b/drivers/scsi/qedi/qedi.h @@ -77,6 +77,11 @@ enum qedi_nvm_tgts { QEDI_NVM_TGT_SEC, }; +struct qedi_nvm_iscsi_image { + struct nvm_iscsi_cfg iscsi_cfg; + u32 crc; +}; + struct qedi_uio_ctrl { /* meta data */ u32 uio_hsi_version; @@ -294,7 +299,7 @@ struct qedi_ctx { void *bdq_pbl_list; dma_addr_t bdq_pbl_list_dma; u8 bdq_pbl_list_num_entries; - struct nvm_iscsi_cfg *iscsi_cfg; + struct qedi_nvm_iscsi_image *iscsi_image; dma_addr_t nvm_buf_dma; void __iomem *bdq_primary_prod; void __iomem *bdq_secondary_prod; diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c index aa96bccb5a96..cc8e64dc65ad 100644 --- a/drivers/scsi/qedi/qedi_main.c +++ b/drivers/scsi/qedi/qedi_main.c @@ -1346,23 +1346,26 @@ exit_setup_int: static void qedi_free_nvm_iscsi_cfg(struct qedi_ctx *qedi) { - if (qedi->iscsi_cfg) + if (qedi->iscsi_image) dma_free_coherent(&qedi->pdev->dev, - sizeof(struct nvm_iscsi_cfg), - qedi->iscsi_cfg, qedi->nvm_buf_dma); + sizeof(struct qedi_nvm_iscsi_image), + qedi->iscsi_image, qedi->nvm_buf_dma); } static int qedi_alloc_nvm_iscsi_cfg(struct qedi_ctx *qedi) { - qedi->iscsi_cfg = dma_zalloc_coherent(&qedi->pdev->dev, - sizeof(struct nvm_iscsi_cfg), - &qedi->nvm_buf_dma, GFP_KERNEL); - if (!qedi->iscsi_cfg) { + struct qedi_nvm_iscsi_image nvm_image; + + qedi->iscsi_image = dma_zalloc_coherent(&qedi->pdev->dev, + sizeof(nvm_image), + &qedi->nvm_buf_dma, + GFP_KERNEL); + if (!qedi->iscsi_image) { QEDI_ERR(&qedi->dbg_ctx, "Could not allocate NVM BUF.\n"); return -ENOMEM; } QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO, - "NVM BUF addr=0x%p dma=0x%llx.\n", qedi->iscsi_cfg, + "NVM BUF addr=0x%p dma=0x%llx.\n", qedi->iscsi_image, qedi->nvm_buf_dma); return 0; @@ -1905,7 +1908,7 @@ qedi_get_nvram_block(struct qedi_ctx *qedi) struct nvm_iscsi_block *block; pf = qedi->dev_info.common.abs_pf_id; - block = &qedi->iscsi_cfg->block[0]; + block = &qedi->iscsi_image->iscsi_cfg.block[0]; for (i = 0; i < NUM_OF_ISCSI_PF_SUPPORTED; i++, block++) { flags = ((block->id) & NVM_ISCSI_CFG_BLK_CTRL_FLAG_MASK) >> NVM_ISCSI_CFG_BLK_CTRL_FLAG_OFFSET; @@ -2194,15 +2197,14 @@ static void qedi_boot_release(void *data) static int qedi_get_boot_info(struct qedi_ctx *qedi) { int ret = 1; - u16 len; - - len = sizeof(struct nvm_iscsi_cfg); + struct qedi_nvm_iscsi_image nvm_image; QEDI_INFO(&qedi->dbg_ctx, QEDI_LOG_INFO, "Get NVM iSCSI CFG image\n"); ret = qedi_ops->common->nvm_get_image(qedi->cdev, QED_NVM_IMAGE_ISCSI_CFG, - (char *)qedi->iscsi_cfg, len); + (char *)qedi->iscsi_image, + sizeof(nvm_image)); if (ret) QEDI_ERR(&qedi->dbg_ctx, "Could not get NVM image. ret = %d\n", ret); diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 0adfb3bce0fd..eb97d2dd3651 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -345,8 +345,7 @@ static void scsi_dec_host_busy(struct Scsi_Host *shost) unsigned long flags; rcu_read_lock(); - if (!shost->use_blk_mq) - atomic_dec(&shost->host_busy); + atomic_dec(&shost->host_busy); if (unlikely(scsi_host_in_recovery(shost))) { spin_lock_irqsave(shost->host_lock, flags); if (shost->host_failed || shost->host_eh_scheduled) @@ -445,12 +444,7 @@ static inline bool scsi_target_is_busy(struct scsi_target *starget) static inline bool scsi_host_is_busy(struct Scsi_Host *shost) { - /* - * blk-mq can handle host queue busy efficiently via host-wide driver - * tag allocation - */ - - if (!shost->use_blk_mq && shost->can_queue > 0 && + if (shost->can_queue > 0 && atomic_read(&shost->host_busy) >= shost->can_queue) return true; if (atomic_read(&shost->host_blocked) > 0) @@ -1606,10 +1600,7 @@ static inline int scsi_host_queue_ready(struct request_queue *q, if (scsi_host_in_recovery(shost)) return 0; - if (!shost->use_blk_mq) - busy = atomic_inc_return(&shost->host_busy) - 1; - else - busy = 0; + busy = atomic_inc_return(&shost->host_busy) - 1; if (atomic_read(&shost->host_blocked) > 0) { if (busy) goto starved; @@ -1625,7 +1616,7 @@ static inline int scsi_host_queue_ready(struct request_queue *q, "unblocking host at zero depth\n")); } - if (!shost->use_blk_mq && shost->can_queue > 0 && busy >= shost->can_queue) + if (shost->can_queue > 0 && busy >= shost->can_queue) goto starved; if (shost->host_self_blocked) goto starved; @@ -1711,9 +1702,7 @@ static void scsi_kill_request(struct request *req, struct request_queue *q) * with the locks as normal issue path does. */ atomic_inc(&sdev->device_busy); - - if (!shost->use_blk_mq) - atomic_inc(&shost->host_busy); + atomic_inc(&shost->host_busy); if (starget->can_queue > 0) atomic_inc(&starget->target_busy); diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c index 7cb3ab0a35a0..3082e72e4f6c 100644 --- a/drivers/spi/spi-fsl-dspi.c +++ b/drivers/spi/spi-fsl-dspi.c @@ -30,7 +30,11 @@ #define DRIVER_NAME "fsl-dspi" +#ifdef CONFIG_M5441x +#define DSPI_FIFO_SIZE 16 +#else #define DSPI_FIFO_SIZE 4 +#endif #define DSPI_DMA_BUFSIZE (DSPI_FIFO_SIZE * 1024) #define SPI_MCR 0x00 @@ -623,9 +627,11 @@ static void dspi_tcfq_read(struct fsl_dspi *dspi) static void dspi_eoq_write(struct fsl_dspi *dspi) { int fifo_size = DSPI_FIFO_SIZE; + u16 xfer_cmd = dspi->tx_cmd; /* Fill TX FIFO with as many transfers as possible */ while (dspi->len && fifo_size--) { + dspi->tx_cmd = xfer_cmd; /* Request EOQF for last transfer in FIFO */ if (dspi->len == dspi->bytes_per_word || fifo_size == 0) dspi->tx_cmd |= SPI_PUSHR_CMD_EOQ; diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index ec395a6baf9c..9da0bc5a036c 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -2143,8 +2143,17 @@ int spi_register_controller(struct spi_controller *ctlr) */ if (ctlr->num_chipselect == 0) return -EINVAL; - /* allocate dynamic bus number using Linux idr */ - if ((ctlr->bus_num < 0) && ctlr->dev.of_node) { + if (ctlr->bus_num >= 0) { + /* devices with a fixed bus num must check-in with the num */ + mutex_lock(&board_lock); + id = idr_alloc(&spi_master_idr, ctlr, ctlr->bus_num, + ctlr->bus_num + 1, GFP_KERNEL); + mutex_unlock(&board_lock); + if (WARN(id < 0, "couldn't get idr")) + return id == -ENOSPC ? -EBUSY : id; + ctlr->bus_num = id; + } else if (ctlr->dev.of_node) { + /* allocate dynamic bus number using Linux idr */ id = of_alias_get_id(ctlr->dev.of_node, "spi"); if (id >= 0) { ctlr->bus_num = id; diff --git a/drivers/staging/erofs/Kconfig b/drivers/staging/erofs/Kconfig index 96f614934df1..663b755bf2fb 100644 --- a/drivers/staging/erofs/Kconfig +++ b/drivers/staging/erofs/Kconfig @@ -2,7 +2,7 @@ config EROFS_FS tristate "EROFS filesystem support" - depends on BROKEN + depends on BLOCK help EROFS(Enhanced Read-Only File System) is a lightweight read-only file system with modern designs (eg. page-sized diff --git a/drivers/staging/erofs/super.c b/drivers/staging/erofs/super.c index 1aec509c805f..2df9768edac9 100644 --- a/drivers/staging/erofs/super.c +++ b/drivers/staging/erofs/super.c @@ -340,7 +340,7 @@ static int erofs_read_super(struct super_block *sb, goto err_sbread; sb->s_magic = EROFS_SUPER_MAGIC; - sb->s_flags |= MS_RDONLY | MS_NOATIME; + sb->s_flags |= SB_RDONLY | SB_NOATIME; sb->s_maxbytes = MAX_LFS_FILESIZE; sb->s_time_gran = 1; @@ -627,7 +627,7 @@ static int erofs_remount(struct super_block *sb, int *flags, char *data) { BUG_ON(!sb_rdonly(sb)); - *flags |= MS_RDONLY; + *flags |= SB_RDONLY; return 0; } diff --git a/drivers/staging/fbtft/TODO b/drivers/staging/fbtft/TODO index 7e64c7e438f0..a9f4802bb6be 100644 --- a/drivers/staging/fbtft/TODO +++ b/drivers/staging/fbtft/TODO @@ -2,3 +2,7 @@ GPIO descriptor API in <linux/gpio/consumer.h> and look up GPIO lines from device tree, ACPI or board files, board files should use <linux/gpio/machine.h> + +* convert all these over to drm_simple_display_pipe and submit for inclusion + into the DRM subsystem under drivers/gpu/drm - fbdev doesn't take any new + drivers anymore. diff --git a/drivers/staging/fsl-dpaa2/Kconfig b/drivers/staging/fsl-dpaa2/Kconfig index a4c4b83ddc9c..59aaae7268cd 100644 --- a/drivers/staging/fsl-dpaa2/Kconfig +++ b/drivers/staging/fsl-dpaa2/Kconfig @@ -9,14 +9,6 @@ config FSL_DPAA2 Build drivers for Freescale DataPath Acceleration Architecture (DPAA2) family of SoCs. -config FSL_DPAA2_ETH - tristate "Freescale DPAA2 Ethernet" - depends on FSL_DPAA2 && FSL_MC_DPIO - depends on NETDEVICES && ETHERNET - ---help--- - Ethernet driver for Freescale DPAA2 SoCs, using the - Freescale MC bus driver - config FSL_DPAA2_ETHSW tristate "Freescale DPAA2 Ethernet Switch" depends on FSL_DPAA2 diff --git a/drivers/staging/fsl-dpaa2/Makefile b/drivers/staging/fsl-dpaa2/Makefile index 9c7062945758..464f242a8a4e 100644 --- a/drivers/staging/fsl-dpaa2/Makefile +++ b/drivers/staging/fsl-dpaa2/Makefile @@ -2,6 +2,5 @@ # Freescale DataPath Acceleration Architecture Gen2 (DPAA2) drivers # -obj-$(CONFIG_FSL_DPAA2_ETH) += ethernet/ obj-$(CONFIG_FSL_DPAA2_ETHSW) += ethsw/ obj-$(CONFIG_FSL_DPAA2_PTP_CLOCK) += rtc/ diff --git a/drivers/staging/fsl-dpaa2/ethernet/TODO b/drivers/staging/fsl-dpaa2/ethernet/TODO deleted file mode 100644 index e400a5e427a5..000000000000 --- a/drivers/staging/fsl-dpaa2/ethernet/TODO +++ /dev/null @@ -1,18 +0,0 @@ -* Add a DPAA2 MAC kernel driver in order to allow PHY management; currently - the DPMAC objects and their link to DPNIs are handled by MC internally - and all PHYs are seen as fixed-link -* add more debug support: decide how to expose detailed debug statistics, - add ingress error queue support -* MC firmware uprev; the DPAA2 objects used by the Ethernet driver need to - be kept in sync with binary interface changes in MC -* refine README file -* cleanup - -NOTE: None of the above is must-have before getting the DPAA2 Ethernet driver -out of staging. The main requirement for that is to have the drivers it -depends on, fsl-mc bus and DPIO driver, moved to drivers/bus and drivers/soc -respectively. - - Please send any patches to Greg Kroah-Hartman <gregkh@linuxfoundation.org>, - ruxandra.radulescu@nxp.com, devel@driverdev.osuosl.org, - linux-kernel@vger.kernel.org diff --git a/drivers/staging/gasket/TODO b/drivers/staging/gasket/TODO index 6ff8e01b04cc..5b1865f8af2d 100644 --- a/drivers/staging/gasket/TODO +++ b/drivers/staging/gasket/TODO @@ -1,9 +1,22 @@ This is a list of things that need to be done to get this driver out of the staging directory. + +- Implement the gasket framework's functionality through UIO instead of + introducing a new user-space drivers framework that is quite similar. + + UIO provides the necessary bits to implement user-space drivers. Meanwhile + the gasket APIs adds some extra conveniences like PCI BAR mapping, and + MSI interrupts. Add these features to the UIO subsystem, then re-implement + the Apex driver as a basic UIO driver instead (include/linux/uio_driver.h) + - Document sysfs files with Documentation/ABI/ entries. + - Use misc interface instead of major number for driver version description. + - Add descriptions of module_param's + - apex_get_status() should actually check status. + - "drivers" should never be dealing with "raw" sysfs calls or mess around with kobjects at all. The driver core should handle all of this for you automaically. There should not be a need for raw attribute macros. diff --git a/drivers/staging/mt7621-eth/mdio.c b/drivers/staging/mt7621-eth/mdio.c index 7ad0c4141205..2c6e1800a3fd 100644 --- a/drivers/staging/mt7621-eth/mdio.c +++ b/drivers/staging/mt7621-eth/mdio.c @@ -112,7 +112,7 @@ static void phy_init(struct mtk_eth *eth, struct mtk_mac *mac, phy->autoneg = AUTONEG_ENABLE; phy->speed = 0; phy->duplex = 0; - phy->supported &= PHY_BASIC_FEATURES; + phy_set_max_speed(phy, SPEED_100); phy->advertising = phy->supported | ADVERTISED_Autoneg; phy_start_aneg(phy); diff --git a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c index d2605158546b..96f265eee007 100644 --- a/drivers/staging/rtl8192e/rtl8192e/rtl_core.c +++ b/drivers/staging/rtl8192e/rtl8192e/rtl_core.c @@ -1149,7 +1149,7 @@ static enum reset_type _rtl92e_tx_check_stuck(struct net_device *dev) if (skb_queue_len(&ring->queue) == 0) { continue; } else { - skb = (&ring->queue)->next; + skb = __skb_peek(&ring->queue); tcb_desc = (struct cb_desc *)(skb->cb + MAX_DEV_ADDR_SIZE); tcb_desc->nStuckCount++; diff --git a/drivers/staging/vboxvideo/vbox_drv.c b/drivers/staging/vboxvideo/vbox_drv.c index da92c493f157..69cc508af1bc 100644 --- a/drivers/staging/vboxvideo/vbox_drv.c +++ b/drivers/staging/vboxvideo/vbox_drv.c @@ -59,6 +59,11 @@ static int vbox_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) ret = PTR_ERR(dev); goto err_drv_alloc; } + + ret = pci_enable_device(pdev); + if (ret) + goto err_pci_enable; + dev->pdev = pdev; pci_set_drvdata(pdev, dev); @@ -75,6 +80,8 @@ static int vbox_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err_drv_dev_register: vbox_driver_unload(dev); err_vbox_driver_load: + pci_disable_device(pdev); + err_pci_enable: drm_dev_put(dev); err_drv_alloc: return ret; diff --git a/drivers/staging/vboxvideo/vbox_mode.c b/drivers/staging/vboxvideo/vbox_mode.c index a83eac8668d0..79836c8fb909 100644 --- a/drivers/staging/vboxvideo/vbox_mode.c +++ b/drivers/staging/vboxvideo/vbox_mode.c @@ -323,6 +323,11 @@ static int vbox_crtc_page_flip(struct drm_crtc *crtc, if (rc) return rc; + mutex_lock(&vbox->hw_mutex); + vbox_set_view(crtc); + vbox_do_modeset(crtc, &crtc->mode); + mutex_unlock(&vbox->hw_mutex); + spin_lock_irqsave(&drm->event_lock, flags); if (event) diff --git a/drivers/staging/wilc1000/Makefile b/drivers/staging/wilc1000/Makefile index f7b07c0b5ce2..ee7e26b886a5 100644 --- a/drivers/staging/wilc1000/Makefile +++ b/drivers/staging/wilc1000/Makefile @@ -1,4 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_WILC1000) += wilc1000.o ccflags-y += -DFIRMWARE_1002=\"atmel/wilc1002_firmware.bin\" \ -DFIRMWARE_1003=\"atmel/wilc1003_firmware.bin\" @@ -11,9 +12,7 @@ wilc1000-objs := wilc_wfi_cfgoperations.o linux_wlan.o linux_mon.o \ wilc_wlan.o obj-$(CONFIG_WILC1000_SDIO) += wilc1000-sdio.o -wilc1000-sdio-objs += $(wilc1000-objs) wilc1000-sdio-objs += wilc_sdio.o obj-$(CONFIG_WILC1000_SPI) += wilc1000-spi.o -wilc1000-spi-objs += $(wilc1000-objs) wilc1000-spi-objs += wilc_spi.o diff --git a/drivers/staging/wilc1000/linux_wlan.c b/drivers/staging/wilc1000/linux_wlan.c index 01cf4bd2e192..3b8d237decbf 100644 --- a/drivers/staging/wilc1000/linux_wlan.c +++ b/drivers/staging/wilc1000/linux_wlan.c @@ -1038,8 +1038,8 @@ void wilc_netdev_cleanup(struct wilc *wilc) } kfree(wilc); - wilc_debugfs_remove(); } +EXPORT_SYMBOL_GPL(wilc_netdev_cleanup); static const struct net_device_ops wilc_netdev_ops = { .ndo_init = mac_init_fn, @@ -1062,7 +1062,6 @@ int wilc_netdev_init(struct wilc **wilc, struct device *dev, int io_type, if (!wl) return -ENOMEM; - wilc_debugfs_init(); *wilc = wl; wl->io_type = io_type; wl->hif_func = ops; @@ -1124,3 +1123,6 @@ int wilc_netdev_init(struct wilc **wilc, struct device *dev, int io_type, return 0; } +EXPORT_SYMBOL_GPL(wilc_netdev_init); + +MODULE_LICENSE("GPL"); diff --git a/drivers/staging/wilc1000/wilc_debugfs.c b/drivers/staging/wilc1000/wilc_debugfs.c index edc72876458d..8001df66b8c2 100644 --- a/drivers/staging/wilc1000/wilc_debugfs.c +++ b/drivers/staging/wilc1000/wilc_debugfs.c @@ -19,6 +19,7 @@ static struct dentry *wilc_dir; #define DBG_LEVEL_ALL (DEBUG | INFO | WRN | ERR) static atomic_t WILC_DEBUG_LEVEL = ATOMIC_INIT(ERR); +EXPORT_SYMBOL_GPL(WILC_DEBUG_LEVEL); static ssize_t wilc_debug_level_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) @@ -87,7 +88,7 @@ static struct wilc_debugfs_info_t debugfs_info[] = { }, }; -int wilc_debugfs_init(void) +static int __init wilc_debugfs_init(void) { int i; struct wilc_debugfs_info_t *info; @@ -103,10 +104,12 @@ int wilc_debugfs_init(void) } return 0; } +module_init(wilc_debugfs_init); -void wilc_debugfs_remove(void) +static void __exit wilc_debugfs_remove(void) { debugfs_remove_recursive(wilc_dir); } +module_exit(wilc_debugfs_remove); #endif diff --git a/drivers/staging/wilc1000/wilc_wlan.c b/drivers/staging/wilc1000/wilc_wlan.c index 6787b6e9f124..8b184aa30d25 100644 --- a/drivers/staging/wilc1000/wilc_wlan.c +++ b/drivers/staging/wilc1000/wilc_wlan.c @@ -417,6 +417,7 @@ void chip_allow_sleep(struct wilc *wilc) wilc->hif_func->hif_write_reg(wilc, 0xf0, reg & ~BIT(0)); wilc->hif_func->hif_write_reg(wilc, 0xfa, 0); } +EXPORT_SYMBOL_GPL(chip_allow_sleep); void chip_wakeup(struct wilc *wilc) { @@ -471,6 +472,7 @@ void chip_wakeup(struct wilc *wilc) } chip_ps_state = CHIP_WAKEDUP; } +EXPORT_SYMBOL_GPL(chip_wakeup); void wilc_chip_sleep_manually(struct wilc *wilc) { @@ -484,6 +486,7 @@ void wilc_chip_sleep_manually(struct wilc *wilc) chip_ps_state = CHIP_SLEEPING_MANUAL; release_bus(wilc, RELEASE_ONLY); } +EXPORT_SYMBOL_GPL(wilc_chip_sleep_manually); void host_wakeup_notify(struct wilc *wilc) { @@ -491,6 +494,7 @@ void host_wakeup_notify(struct wilc *wilc) wilc->hif_func->hif_write_reg(wilc, 0x10b0, 1); release_bus(wilc, RELEASE_ONLY); } +EXPORT_SYMBOL_GPL(host_wakeup_notify); void host_sleep_notify(struct wilc *wilc) { @@ -498,6 +502,7 @@ void host_sleep_notify(struct wilc *wilc) wilc->hif_func->hif_write_reg(wilc, 0x10ac, 1); release_bus(wilc, RELEASE_ONLY); } +EXPORT_SYMBOL_GPL(host_sleep_notify); int wilc_wlan_handle_txq(struct net_device *dev, u32 *txq_count) { @@ -871,6 +876,7 @@ void wilc_handle_isr(struct wilc *wilc) release_bus(wilc, RELEASE_ALLOW_SLEEP); } +EXPORT_SYMBOL_GPL(wilc_handle_isr); int wilc_wlan_firmware_download(struct wilc *wilc, const u8 *buffer, u32 buffer_size) diff --git a/drivers/staging/wilc1000/wilc_wlan_if.h b/drivers/staging/wilc1000/wilc_wlan_if.h index 00d13b153f80..b81a73b9bd67 100644 --- a/drivers/staging/wilc1000/wilc_wlan_if.h +++ b/drivers/staging/wilc1000/wilc_wlan_if.h @@ -831,6 +831,4 @@ struct wilc; int wilc_wlan_init(struct net_device *dev); u32 wilc_get_chipid(struct wilc *wilc, bool update); -int wilc_debugfs_init(void); -void wilc_debugfs_remove(void); #endif diff --git a/drivers/target/iscsi/cxgbit/cxgbit_ddp.c b/drivers/target/iscsi/cxgbit/cxgbit_ddp.c index 768cce0ccb80..76a262674c8d 100644 --- a/drivers/target/iscsi/cxgbit/cxgbit_ddp.c +++ b/drivers/target/iscsi/cxgbit/cxgbit_ddp.c @@ -207,8 +207,8 @@ cxgbit_ddp_reserve(struct cxgbit_sock *csk, struct cxgbi_task_tag_info *ttinfo, ret = dma_map_sg(&ppm->pdev->dev, sgl, sgcnt, DMA_FROM_DEVICE); sgl->offset = sg_offset; if (!ret) { - pr_info("%s: 0x%x, xfer %u, sgl %u dma mapping err.\n", - __func__, 0, xferlen, sgcnt); + pr_debug("%s: 0x%x, xfer %u, sgl %u dma mapping err.\n", + __func__, 0, xferlen, sgcnt); goto rel_ppods; } @@ -250,8 +250,8 @@ cxgbit_get_r2t_ttt(struct iscsi_conn *conn, struct iscsi_cmd *cmd, ret = cxgbit_ddp_reserve(csk, ttinfo, cmd->se_cmd.data_length); if (ret < 0) { - pr_info("csk 0x%p, cmd 0x%p, xfer len %u, sgcnt %u no ddp.\n", - csk, cmd, cmd->se_cmd.data_length, ttinfo->nents); + pr_debug("csk 0x%p, cmd 0x%p, xfer len %u, sgcnt %u no ddp.\n", + csk, cmd, cmd->se_cmd.data_length, ttinfo->nents); ttinfo->sgl = NULL; ttinfo->nents = 0; diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c index 94bad43c41ff..9cdfccbdd06f 100644 --- a/drivers/target/iscsi/iscsi_target.c +++ b/drivers/target/iscsi/iscsi_target.c @@ -4208,22 +4208,15 @@ int iscsit_close_connection( crypto_free_ahash(tfm); } - free_cpumask_var(conn->conn_cpumask); - - kfree(conn->conn_ops); - conn->conn_ops = NULL; - if (conn->sock) sock_release(conn->sock); if (conn->conn_transport->iscsit_free_conn) conn->conn_transport->iscsit_free_conn(conn); - iscsit_put_transport(conn->conn_transport); - pr_debug("Moving to TARG_CONN_STATE_FREE.\n"); conn->conn_state = TARG_CONN_STATE_FREE; - kfree(conn); + iscsit_free_conn(conn); spin_lock_bh(&sess->conn_lock); atomic_dec(&sess->nconn); diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index 9e74f8bc2963..bb90c80ff388 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -67,45 +67,10 @@ static struct iscsi_login *iscsi_login_init_conn(struct iscsi_conn *conn) goto out_req_buf; } - conn->conn_ops = kzalloc(sizeof(struct iscsi_conn_ops), GFP_KERNEL); - if (!conn->conn_ops) { - pr_err("Unable to allocate memory for" - " struct iscsi_conn_ops.\n"); - goto out_rsp_buf; - } - - init_waitqueue_head(&conn->queues_wq); - INIT_LIST_HEAD(&conn->conn_list); - INIT_LIST_HEAD(&conn->conn_cmd_list); - INIT_LIST_HEAD(&conn->immed_queue_list); - INIT_LIST_HEAD(&conn->response_queue_list); - init_completion(&conn->conn_post_wait_comp); - init_completion(&conn->conn_wait_comp); - init_completion(&conn->conn_wait_rcfr_comp); - init_completion(&conn->conn_waiting_on_uc_comp); - init_completion(&conn->conn_logout_comp); - init_completion(&conn->rx_half_close_comp); - init_completion(&conn->tx_half_close_comp); - init_completion(&conn->rx_login_comp); - spin_lock_init(&conn->cmd_lock); - spin_lock_init(&conn->conn_usage_lock); - spin_lock_init(&conn->immed_queue_lock); - spin_lock_init(&conn->nopin_timer_lock); - spin_lock_init(&conn->response_queue_lock); - spin_lock_init(&conn->state_lock); - - if (!zalloc_cpumask_var(&conn->conn_cpumask, GFP_KERNEL)) { - pr_err("Unable to allocate conn->conn_cpumask\n"); - goto out_conn_ops; - } conn->conn_login = login; return login; -out_conn_ops: - kfree(conn->conn_ops); -out_rsp_buf: - kfree(login->rsp_buf); out_req_buf: kfree(login->req_buf); out_login: @@ -310,11 +275,9 @@ static int iscsi_login_zero_tsih_s1( return -ENOMEM; } - ret = iscsi_login_set_conn_values(sess, conn, pdu->cid); - if (unlikely(ret)) { - kfree(sess); - return ret; - } + if (iscsi_login_set_conn_values(sess, conn, pdu->cid)) + goto free_sess; + sess->init_task_tag = pdu->itt; memcpy(&sess->isid, pdu->isid, 6); sess->exp_cmd_sn = be32_to_cpu(pdu->cmdsn); @@ -1149,6 +1112,75 @@ iscsit_conn_set_transport(struct iscsi_conn *conn, struct iscsit_transport *t) return 0; } +static struct iscsi_conn *iscsit_alloc_conn(struct iscsi_np *np) +{ + struct iscsi_conn *conn; + + conn = kzalloc(sizeof(struct iscsi_conn), GFP_KERNEL); + if (!conn) { + pr_err("Could not allocate memory for new connection\n"); + return NULL; + } + pr_debug("Moving to TARG_CONN_STATE_FREE.\n"); + conn->conn_state = TARG_CONN_STATE_FREE; + + init_waitqueue_head(&conn->queues_wq); + INIT_LIST_HEAD(&conn->conn_list); + INIT_LIST_HEAD(&conn->conn_cmd_list); + INIT_LIST_HEAD(&conn->immed_queue_list); + INIT_LIST_HEAD(&conn->response_queue_list); + init_completion(&conn->conn_post_wait_comp); + init_completion(&conn->conn_wait_comp); + init_completion(&conn->conn_wait_rcfr_comp); + init_completion(&conn->conn_waiting_on_uc_comp); + init_completion(&conn->conn_logout_comp); + init_completion(&conn->rx_half_close_comp); + init_completion(&conn->tx_half_close_comp); + init_completion(&conn->rx_login_comp); + spin_lock_init(&conn->cmd_lock); + spin_lock_init(&conn->conn_usage_lock); + spin_lock_init(&conn->immed_queue_lock); + spin_lock_init(&conn->nopin_timer_lock); + spin_lock_init(&conn->response_queue_lock); + spin_lock_init(&conn->state_lock); + + timer_setup(&conn->nopin_response_timer, + iscsit_handle_nopin_response_timeout, 0); + timer_setup(&conn->nopin_timer, iscsit_handle_nopin_timeout, 0); + + if (iscsit_conn_set_transport(conn, np->np_transport) < 0) + goto free_conn; + + conn->conn_ops = kzalloc(sizeof(struct iscsi_conn_ops), GFP_KERNEL); + if (!conn->conn_ops) { + pr_err("Unable to allocate memory for struct iscsi_conn_ops.\n"); + goto put_transport; + } + + if (!zalloc_cpumask_var(&conn->conn_cpumask, GFP_KERNEL)) { + pr_err("Unable to allocate conn->conn_cpumask\n"); + goto free_mask; + } + + return conn; + +free_mask: + free_cpumask_var(conn->conn_cpumask); +put_transport: + iscsit_put_transport(conn->conn_transport); +free_conn: + kfree(conn); + return NULL; +} + +void iscsit_free_conn(struct iscsi_conn *conn) +{ + free_cpumask_var(conn->conn_cpumask); + kfree(conn->conn_ops); + iscsit_put_transport(conn->conn_transport); + kfree(conn); +} + void iscsi_target_login_sess_out(struct iscsi_conn *conn, struct iscsi_np *np, bool zero_tsih, bool new_sess) { @@ -1198,10 +1230,6 @@ old_sess_out: crypto_free_ahash(tfm); } - free_cpumask_var(conn->conn_cpumask); - - kfree(conn->conn_ops); - if (conn->param_list) { iscsi_release_param_list(conn->param_list); conn->param_list = NULL; @@ -1219,8 +1247,7 @@ old_sess_out: if (conn->conn_transport->iscsit_free_conn) conn->conn_transport->iscsit_free_conn(conn); - iscsit_put_transport(conn->conn_transport); - kfree(conn); + iscsit_free_conn(conn); } static int __iscsi_target_login_thread(struct iscsi_np *np) @@ -1250,31 +1277,16 @@ static int __iscsi_target_login_thread(struct iscsi_np *np) } spin_unlock_bh(&np->np_thread_lock); - conn = kzalloc(sizeof(struct iscsi_conn), GFP_KERNEL); + conn = iscsit_alloc_conn(np); if (!conn) { - pr_err("Could not allocate memory for" - " new connection\n"); /* Get another socket */ return 1; } - pr_debug("Moving to TARG_CONN_STATE_FREE.\n"); - conn->conn_state = TARG_CONN_STATE_FREE; - - timer_setup(&conn->nopin_response_timer, - iscsit_handle_nopin_response_timeout, 0); - timer_setup(&conn->nopin_timer, iscsit_handle_nopin_timeout, 0); - - if (iscsit_conn_set_transport(conn, np->np_transport) < 0) { - kfree(conn); - return 1; - } rc = np->np_transport->iscsit_accept_np(np, conn); if (rc == -ENOSYS) { complete(&np->np_restart_comp); - iscsit_put_transport(conn->conn_transport); - kfree(conn); - conn = NULL; + iscsit_free_conn(conn); goto exit; } else if (rc < 0) { spin_lock_bh(&np->np_thread_lock); @@ -1282,17 +1294,13 @@ static int __iscsi_target_login_thread(struct iscsi_np *np) np->np_thread_state = ISCSI_NP_THREAD_ACTIVE; spin_unlock_bh(&np->np_thread_lock); complete(&np->np_restart_comp); - iscsit_put_transport(conn->conn_transport); - kfree(conn); - conn = NULL; + iscsit_free_conn(conn); /* Get another socket */ return 1; } spin_unlock_bh(&np->np_thread_lock); - iscsit_put_transport(conn->conn_transport); - kfree(conn); - conn = NULL; - goto out; + iscsit_free_conn(conn); + return 1; } /* * Perform the remaining iSCSI connection initialization items.. @@ -1442,7 +1450,6 @@ old_sess_out: tpg_np = NULL; } -out: return 1; exit: diff --git a/drivers/target/iscsi/iscsi_target_login.h b/drivers/target/iscsi/iscsi_target_login.h index 74ac3abc44a0..3b8e3639ff5d 100644 --- a/drivers/target/iscsi/iscsi_target_login.h +++ b/drivers/target/iscsi/iscsi_target_login.h @@ -19,7 +19,7 @@ extern int iscsi_target_setup_login_socket(struct iscsi_np *, extern int iscsit_accept_np(struct iscsi_np *, struct iscsi_conn *); extern int iscsit_get_login_rx(struct iscsi_conn *, struct iscsi_login *); extern int iscsit_put_login_tx(struct iscsi_conn *, struct iscsi_login *, u32); -extern void iscsit_free_conn(struct iscsi_np *, struct iscsi_conn *); +extern void iscsit_free_conn(struct iscsi_conn *); extern int iscsit_start_kthreads(struct iscsi_conn *); extern void iscsi_post_login_handler(struct iscsi_np *, struct iscsi_conn *, u8); extern void iscsi_target_login_sess_out(struct iscsi_conn *, struct iscsi_np *, diff --git a/drivers/thermal/of-thermal.c b/drivers/thermal/of-thermal.c index 977a8307fbb1..4f2816559205 100644 --- a/drivers/thermal/of-thermal.c +++ b/drivers/thermal/of-thermal.c @@ -260,10 +260,13 @@ static int of_thermal_set_mode(struct thermal_zone_device *tz, mutex_lock(&tz->lock); - if (mode == THERMAL_DEVICE_ENABLED) + if (mode == THERMAL_DEVICE_ENABLED) { tz->polling_delay = data->polling_delay; - else + tz->passive_delay = data->passive_delay; + } else { tz->polling_delay = 0; + tz->passive_delay = 0; + } mutex_unlock(&tz->lock); diff --git a/drivers/thermal/qoriq_thermal.c b/drivers/thermal/qoriq_thermal.c index c866cc165960..450ed66edf58 100644 --- a/drivers/thermal/qoriq_thermal.c +++ b/drivers/thermal/qoriq_thermal.c @@ -1,16 +1,6 @@ -/* - * Copyright 2016 Freescale Semiconductor, Inc. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - */ +// SPDX-License-Identifier: GPL-2.0 +// +// Copyright 2016 Freescale Semiconductor, Inc. #include <linux/module.h> #include <linux/platform_device.h> @@ -197,7 +187,7 @@ static int qoriq_tmu_probe(struct platform_device *pdev) int ret; struct qoriq_tmu_data *data; struct device_node *np = pdev->dev.of_node; - u32 site = 0; + u32 site; if (!np) { dev_err(&pdev->dev, "Device OF-Node is NULL"); @@ -233,8 +223,9 @@ static int qoriq_tmu_probe(struct platform_device *pdev) if (ret < 0) goto err_tmu; - data->tz = thermal_zone_of_sensor_register(&pdev->dev, data->sensor_id, - data, &tmu_tz_ops); + data->tz = devm_thermal_zone_of_sensor_register(&pdev->dev, + data->sensor_id, + data, &tmu_tz_ops); if (IS_ERR(data->tz)) { ret = PTR_ERR(data->tz); dev_err(&pdev->dev, @@ -243,7 +234,7 @@ static int qoriq_tmu_probe(struct platform_device *pdev) } /* Enable monitoring */ - site |= 0x1 << (15 - data->sensor_id); + site = 0x1 << (15 - data->sensor_id); tmu_write(data, site | TMR_ME | TMR_ALPF, &data->regs->tmr); return 0; @@ -261,8 +252,6 @@ static int qoriq_tmu_remove(struct platform_device *pdev) { struct qoriq_tmu_data *data = platform_get_drvdata(pdev); - thermal_zone_of_sensor_unregister(&pdev->dev, data->tz); - /* Disable monitoring */ tmu_write(data, TMR_DISABLE, &data->regs->tmr); diff --git a/drivers/thermal/rcar_gen3_thermal.c b/drivers/thermal/rcar_gen3_thermal.c index 766521eb7071..7aed5337bdd3 100644 --- a/drivers/thermal/rcar_gen3_thermal.c +++ b/drivers/thermal/rcar_gen3_thermal.c @@ -1,19 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 /* * R-Car Gen3 THS thermal sensor driver * Based on rcar_thermal.c and work from Hien Dang and Khiem Nguyen. * * Copyright (C) 2016 Renesas Electronics Corporation. * Copyright (C) 2016 Sang Engineering - * - * 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; version 2 of the License. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * */ #include <linux/delay.h> #include <linux/err.h> diff --git a/drivers/thermal/rcar_thermal.c b/drivers/thermal/rcar_thermal.c index e77e63070e99..78f932822d38 100644 --- a/drivers/thermal/rcar_thermal.c +++ b/drivers/thermal/rcar_thermal.c @@ -1,21 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * R-Car THS/TSC thermal sensor driver * * Copyright (C) 2012 Renesas Solutions Corp. * Kuninori Morimoto <kuninori.morimoto.gx@renesas.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; version 2 of the License. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, write to the Free Software Foundation, Inc., - * 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA. */ #include <linux/delay.h> #include <linux/err.h> @@ -660,6 +648,6 @@ static struct platform_driver rcar_thermal_driver = { }; module_platform_driver(rcar_thermal_driver); -MODULE_LICENSE("GPL"); +MODULE_LICENSE("GPL v2"); MODULE_DESCRIPTION("R-Car THS/TSC thermal sensor driver"); MODULE_AUTHOR("Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>"); diff --git a/drivers/tty/hvc/hvc_console.c b/drivers/tty/hvc/hvc_console.c index 5414c4a87bea..27284a2dcd2b 100644 --- a/drivers/tty/hvc/hvc_console.c +++ b/drivers/tty/hvc/hvc_console.c @@ -522,6 +522,8 @@ static int hvc_write(struct tty_struct *tty, const unsigned char *buf, int count return -EIO; while (count > 0) { + int ret = 0; + spin_lock_irqsave(&hp->lock, flags); rsize = hp->outbuf_size - hp->n_outbuf; @@ -537,10 +539,13 @@ static int hvc_write(struct tty_struct *tty, const unsigned char *buf, int count } if (hp->n_outbuf > 0) - hvc_push(hp); + ret = hvc_push(hp); spin_unlock_irqrestore(&hp->lock, flags); + if (!ret) + break; + if (count) { if (hp->n_outbuf > 0) hvc_flush(hp); @@ -623,6 +628,15 @@ static int hvc_chars_in_buffer(struct tty_struct *tty) #define MAX_TIMEOUT (2000) static u32 timeout = MIN_TIMEOUT; +/* + * Maximum number of bytes to get from the console driver if hvc_poll is + * called from driver (and can't sleep). Any more than this and we break + * and start polling with khvcd. This value was derived from from an OpenBMC + * console with the OPAL driver that results in about 0.25ms interrupts off + * latency. + */ +#define HVC_ATOMIC_READ_MAX 128 + #define HVC_POLL_READ 0x00000001 #define HVC_POLL_WRITE 0x00000002 @@ -669,8 +683,8 @@ static int __hvc_poll(struct hvc_struct *hp, bool may_sleep) if (!hp->irq_requested) poll_mask |= HVC_POLL_READ; + read_again: /* Read data if any */ - count = tty_buffer_request_room(&hp->port, N_INBUF); /* If flip is full, just reschedule a later read */ @@ -717,9 +731,23 @@ static int __hvc_poll(struct hvc_struct *hp, bool may_sleep) #endif /* CONFIG_MAGIC_SYSRQ */ tty_insert_flip_char(&hp->port, buf[i], 0); } - if (n == count) - poll_mask |= HVC_POLL_READ; - read_total = n; + read_total += n; + + if (may_sleep) { + /* Keep going until the flip is full */ + spin_unlock_irqrestore(&hp->lock, flags); + cond_resched(); + spin_lock_irqsave(&hp->lock, flags); + goto read_again; + } else if (read_total < HVC_ATOMIC_READ_MAX) { + /* Break and defer if it's a large read in atomic */ + goto read_again; + } + + /* + * Latency break, schedule another poll immediately. + */ + poll_mask |= HVC_POLL_READ; out: /* Wakeup write queue if necessary */ diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c index 27346d69f393..f9b40a9dc4d3 100644 --- a/drivers/usb/class/cdc-acm.c +++ b/drivers/usb/class/cdc-acm.c @@ -780,20 +780,9 @@ static int acm_tty_write(struct tty_struct *tty, } if (acm->susp_count) { - if (acm->putbuffer) { - /* now to preserve order */ - usb_anchor_urb(acm->putbuffer->urb, &acm->delayed); - acm->putbuffer = NULL; - } usb_anchor_urb(wb->urb, &acm->delayed); spin_unlock_irqrestore(&acm->write_lock, flags); return count; - } else { - if (acm->putbuffer) { - /* at this point there is no good way to handle errors */ - acm_start_wb(acm, acm->putbuffer); - acm->putbuffer = NULL; - } } stat = acm_start_wb(acm, wb); @@ -804,66 +793,6 @@ static int acm_tty_write(struct tty_struct *tty, return count; } -static void acm_tty_flush_chars(struct tty_struct *tty) -{ - struct acm *acm = tty->driver_data; - struct acm_wb *cur; - int err; - unsigned long flags; - - spin_lock_irqsave(&acm->write_lock, flags); - - cur = acm->putbuffer; - if (!cur) /* nothing to do */ - goto out; - - acm->putbuffer = NULL; - err = usb_autopm_get_interface_async(acm->control); - if (err < 0) { - cur->use = 0; - acm->putbuffer = cur; - goto out; - } - - if (acm->susp_count) - usb_anchor_urb(cur->urb, &acm->delayed); - else - acm_start_wb(acm, cur); -out: - spin_unlock_irqrestore(&acm->write_lock, flags); - return; -} - -static int acm_tty_put_char(struct tty_struct *tty, unsigned char ch) -{ - struct acm *acm = tty->driver_data; - struct acm_wb *cur; - int wbn; - unsigned long flags; - -overflow: - cur = acm->putbuffer; - if (!cur) { - spin_lock_irqsave(&acm->write_lock, flags); - wbn = acm_wb_alloc(acm); - if (wbn >= 0) { - cur = &acm->wb[wbn]; - acm->putbuffer = cur; - } - spin_unlock_irqrestore(&acm->write_lock, flags); - if (!cur) - return 0; - } - - if (cur->len == acm->writesize) { - acm_tty_flush_chars(tty); - goto overflow; - } - - cur->buf[cur->len++] = ch; - return 1; -} - static int acm_tty_write_room(struct tty_struct *tty) { struct acm *acm = tty->driver_data; @@ -1987,8 +1916,6 @@ static const struct tty_operations acm_ops = { .cleanup = acm_tty_cleanup, .hangup = acm_tty_hangup, .write = acm_tty_write, - .put_char = acm_tty_put_char, - .flush_chars = acm_tty_flush_chars, .write_room = acm_tty_write_room, .ioctl = acm_tty_ioctl, .throttle = acm_tty_throttle, diff --git a/drivers/usb/class/cdc-acm.h b/drivers/usb/class/cdc-acm.h index eacc116e83da..ca06b20d7af9 100644 --- a/drivers/usb/class/cdc-acm.h +++ b/drivers/usb/class/cdc-acm.h @@ -96,7 +96,6 @@ struct acm { unsigned long read_urbs_free; struct urb *read_urbs[ACM_NR]; struct acm_rb read_buffers[ACM_NR]; - struct acm_wb *putbuffer; /* for acm_tty_put_char() */ int rx_buflimit; spinlock_t read_lock; u8 *notification_buffer; /* to reassemble fragmented notifications */ diff --git a/drivers/usb/class/cdc-wdm.c b/drivers/usb/class/cdc-wdm.c index bec581fb7c63..656d247819c9 100644 --- a/drivers/usb/class/cdc-wdm.c +++ b/drivers/usb/class/cdc-wdm.c @@ -460,7 +460,7 @@ static int service_outstanding_interrupt(struct wdm_device *desc) set_bit(WDM_RESPONDING, &desc->flags); spin_unlock_irq(&desc->iuspin); - rv = usb_submit_urb(desc->response, GFP_KERNEL); + rv = usb_submit_urb(desc->response, GFP_ATOMIC); spin_lock_irq(&desc->iuspin); if (rv) { dev_err(&desc->intf->dev, diff --git a/drivers/usb/common/common.c b/drivers/usb/common/common.c index 50a2362ed3ea..48277bbc15e4 100644 --- a/drivers/usb/common/common.c +++ b/drivers/usb/common/common.c @@ -246,6 +246,31 @@ int of_usb_update_otg_caps(struct device_node *np, } EXPORT_SYMBOL_GPL(of_usb_update_otg_caps); +/** + * usb_of_get_companion_dev - Find the companion device + * @dev: the device pointer to find a companion + * + * Find the companion device from platform bus. + * + * Takes a reference to the returned struct device which needs to be dropped + * after use. + * + * Return: On success, a pointer to the companion device, %NULL on failure. + */ +struct device *usb_of_get_companion_dev(struct device *dev) +{ + struct device_node *node; + struct platform_device *pdev = NULL; + + node = of_parse_phandle(dev->of_node, "companion", 0); + if (node) + pdev = of_find_device_by_node(node); + + of_node_put(node); + + return pdev ? &pdev->dev : NULL; +} +EXPORT_SYMBOL_GPL(usb_of_get_companion_dev); #endif MODULE_LICENSE("GPL"); diff --git a/drivers/usb/core/hcd-pci.c b/drivers/usb/core/hcd-pci.c index 66fe1b78d952..03432467b05f 100644 --- a/drivers/usb/core/hcd-pci.c +++ b/drivers/usb/core/hcd-pci.c @@ -515,8 +515,6 @@ static int resume_common(struct device *dev, int event) event == PM_EVENT_RESTORE); if (retval) { dev_err(dev, "PCI post-resume error %d!\n", retval); - if (hcd->shared_hcd) - usb_hc_died(hcd->shared_hcd); usb_hc_died(hcd); } } diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c index 228672f2c4a1..bfa5eda0cc26 100644 --- a/drivers/usb/core/message.c +++ b/drivers/usb/core/message.c @@ -1341,6 +1341,11 @@ void usb_enable_interface(struct usb_device *dev, * is submitted that needs that bandwidth. Some other operating systems * allocate bandwidth early, when a configuration is chosen. * + * xHCI reserves bandwidth and configures the alternate setting in + * usb_hcd_alloc_bandwidth(). If it fails the original interface altsetting + * may be disabled. Drivers cannot rely on any particular alternate + * setting being in effect after a failure. + * * This call is synchronous, and may not be used in an interrupt context. * Also, drivers must not change altsettings while urbs are scheduled for * endpoints in that interface; all such urbs must first be completed @@ -1376,6 +1381,12 @@ int usb_set_interface(struct usb_device *dev, int interface, int alternate) alternate); return -EINVAL; } + /* + * usb3 hosts configure the interface in usb_hcd_alloc_bandwidth, + * including freeing dropped endpoint ring buffers. + * Make sure the interface endpoints are flushed before that + */ + usb_disable_interface(dev, iface, false); /* Make sure we have enough bandwidth for this alternate interface. * Remove the current alt setting and add the new alt setting. diff --git a/drivers/usb/core/of.c b/drivers/usb/core/of.c index fd77442c2d12..651708d8c908 100644 --- a/drivers/usb/core/of.c +++ b/drivers/usb/core/of.c @@ -105,29 +105,3 @@ usb_of_get_interface_node(struct usb_device *udev, u8 config, u8 ifnum) return NULL; } EXPORT_SYMBOL_GPL(usb_of_get_interface_node); - -/** - * usb_of_get_companion_dev - Find the companion device - * @dev: the device pointer to find a companion - * - * Find the companion device from platform bus. - * - * Takes a reference to the returned struct device which needs to be dropped - * after use. - * - * Return: On success, a pointer to the companion device, %NULL on failure. - */ -struct device *usb_of_get_companion_dev(struct device *dev) -{ - struct device_node *node; - struct platform_device *pdev = NULL; - - node = of_parse_phandle(dev->of_node, "companion", 0); - if (node) - pdev = of_find_device_by_node(node); - - of_node_put(node); - - return pdev ? &pdev->dev : NULL; -} -EXPORT_SYMBOL_GPL(usb_of_get_companion_dev); diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index 097057d2eacf..e77dfe5ed5ec 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -178,6 +178,10 @@ static const struct usb_device_id usb_quirk_list[] = { /* CBM - Flash disk */ { USB_DEVICE(0x0204, 0x6025), .driver_info = USB_QUIRK_RESET_RESUME }, + /* WORLDE Controller KS49 or Prodipe MIDI 49C USB controller */ + { USB_DEVICE(0x0218, 0x0201), .driver_info = + USB_QUIRK_CONFIG_INTF_STRINGS }, + /* WORLDE easy key (easykey.25) MIDI controller */ { USB_DEVICE(0x0218, 0x0401), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS }, @@ -406,6 +410,9 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x2040, 0x7200), .driver_info = USB_QUIRK_CONFIG_INTF_STRINGS }, + /* DJI CineSSD */ + { USB_DEVICE(0x2ca3, 0x0031), .driver_info = USB_QUIRK_NO_LPM }, + /* INTEL VALUE SSD */ { USB_DEVICE(0x8086, 0xf1a5), .driver_info = USB_QUIRK_RESET_RESUME }, diff --git a/drivers/usb/dwc2/platform.c b/drivers/usb/dwc2/platform.c index 9a53a58e676e..577642895b57 100644 --- a/drivers/usb/dwc2/platform.c +++ b/drivers/usb/dwc2/platform.c @@ -412,8 +412,6 @@ static int dwc2_driver_probe(struct platform_device *dev) dev_dbg(&dev->dev, "mapped PA %08lx to VA %p\n", (unsigned long)res->start, hsotg->regs); - hsotg->needs_byte_swap = dwc2_check_core_endianness(hsotg); - retval = dwc2_lowlevel_hw_init(hsotg); if (retval) return retval; @@ -438,6 +436,8 @@ static int dwc2_driver_probe(struct platform_device *dev) if (retval) return retval; + hsotg->needs_byte_swap = dwc2_check_core_endianness(hsotg); + retval = dwc2_get_dr_mode(hsotg); if (retval) goto error; diff --git a/drivers/usb/dwc3/dwc3-of-simple.c b/drivers/usb/dwc3/dwc3-of-simple.c index 40bf9e0bbc59..4c2771c5e727 100644 --- a/drivers/usb/dwc3/dwc3-of-simple.c +++ b/drivers/usb/dwc3/dwc3-of-simple.c @@ -180,8 +180,7 @@ static int dwc3_of_simple_remove(struct platform_device *pdev) return 0; } -#ifdef CONFIG_PM -static int dwc3_of_simple_runtime_suspend(struct device *dev) +static int __maybe_unused dwc3_of_simple_runtime_suspend(struct device *dev) { struct dwc3_of_simple *simple = dev_get_drvdata(dev); int i; @@ -192,7 +191,7 @@ static int dwc3_of_simple_runtime_suspend(struct device *dev) return 0; } -static int dwc3_of_simple_runtime_resume(struct device *dev) +static int __maybe_unused dwc3_of_simple_runtime_resume(struct device *dev) { struct dwc3_of_simple *simple = dev_get_drvdata(dev); int ret; @@ -210,7 +209,7 @@ static int dwc3_of_simple_runtime_resume(struct device *dev) return 0; } -static int dwc3_of_simple_suspend(struct device *dev) +static int __maybe_unused dwc3_of_simple_suspend(struct device *dev) { struct dwc3_of_simple *simple = dev_get_drvdata(dev); @@ -220,7 +219,7 @@ static int dwc3_of_simple_suspend(struct device *dev) return 0; } -static int dwc3_of_simple_resume(struct device *dev) +static int __maybe_unused dwc3_of_simple_resume(struct device *dev) { struct dwc3_of_simple *simple = dev_get_drvdata(dev); @@ -229,7 +228,6 @@ static int dwc3_of_simple_resume(struct device *dev) return 0; } -#endif static const struct dev_pm_ops dwc3_of_simple_dev_pm_ops = { SET_SYSTEM_SLEEP_PM_OPS(dwc3_of_simple_suspend, dwc3_of_simple_resume) diff --git a/drivers/usb/dwc3/dwc3-pci.c b/drivers/usb/dwc3/dwc3-pci.c index 5edd79470368..1286076a8890 100644 --- a/drivers/usb/dwc3/dwc3-pci.c +++ b/drivers/usb/dwc3/dwc3-pci.c @@ -85,8 +85,8 @@ static int dwc3_byt_enable_ulpi_refclock(struct pci_dev *pci) u32 value; reg = pcim_iomap(pci, GP_RWBAR, 0); - if (IS_ERR(reg)) - return PTR_ERR(reg); + if (!reg) + return -ENOMEM; value = readl(reg + GP_RWREG1); if (!(value & GP_RWREG1_ULPI_REFCLK_DISABLE)) diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 032ea7d709ba..2b53194081ba 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -473,7 +473,6 @@ static int dwc3_gadget_set_xfer_resource(struct dwc3_ep *dep) /** * dwc3_gadget_start_config - configure ep resources - * @dwc: pointer to our controller context structure * @dep: endpoint that is being enabled * * Issue a %DWC3_DEPCMD_DEPSTARTCFG command to @dep. After the command's diff --git a/drivers/usb/gadget/udc/fotg210-udc.c b/drivers/usb/gadget/udc/fotg210-udc.c index 53a48f561458..587c5037ff07 100644 --- a/drivers/usb/gadget/udc/fotg210-udc.c +++ b/drivers/usb/gadget/udc/fotg210-udc.c @@ -1063,12 +1063,15 @@ static const struct usb_gadget_ops fotg210_gadget_ops = { static int fotg210_udc_remove(struct platform_device *pdev) { struct fotg210_udc *fotg210 = platform_get_drvdata(pdev); + int i; usb_del_gadget_udc(&fotg210->gadget); iounmap(fotg210->reg); free_irq(platform_get_irq(pdev, 0), fotg210); fotg210_ep_free_request(&fotg210->ep[0]->ep, fotg210->ep0_req); + for (i = 0; i < FOTG210_MAX_NUM_EP; i++) + kfree(fotg210->ep[i]); kfree(fotg210); return 0; @@ -1099,7 +1102,7 @@ static int fotg210_udc_probe(struct platform_device *pdev) /* initialize udc */ fotg210 = kzalloc(sizeof(struct fotg210_udc), GFP_KERNEL); if (fotg210 == NULL) - goto err_alloc; + goto err; for (i = 0; i < FOTG210_MAX_NUM_EP; i++) { _ep[i] = kzalloc(sizeof(struct fotg210_ep), GFP_KERNEL); @@ -1111,7 +1114,7 @@ static int fotg210_udc_probe(struct platform_device *pdev) fotg210->reg = ioremap(res->start, resource_size(res)); if (fotg210->reg == NULL) { pr_err("ioremap error.\n"); - goto err_map; + goto err_alloc; } spin_lock_init(&fotg210->lock); @@ -1159,7 +1162,7 @@ static int fotg210_udc_probe(struct platform_device *pdev) fotg210->ep0_req = fotg210_ep_alloc_request(&fotg210->ep[0]->ep, GFP_KERNEL); if (fotg210->ep0_req == NULL) - goto err_req; + goto err_map; fotg210_init(fotg210); @@ -1187,12 +1190,14 @@ err_req: fotg210_ep_free_request(&fotg210->ep[0]->ep, fotg210->ep0_req); err_map: - if (fotg210->reg) - iounmap(fotg210->reg); + iounmap(fotg210->reg); err_alloc: + for (i = 0; i < FOTG210_MAX_NUM_EP; i++) + kfree(fotg210->ep[i]); kfree(fotg210); +err: return ret; } diff --git a/drivers/usb/gadget/udc/net2280.c b/drivers/usb/gadget/udc/net2280.c index 318246d8b2e2..b02ab2a8d927 100644 --- a/drivers/usb/gadget/udc/net2280.c +++ b/drivers/usb/gadget/udc/net2280.c @@ -1545,11 +1545,14 @@ static int net2280_pullup(struct usb_gadget *_gadget, int is_on) writel(tmp | BIT(USB_DETECT_ENABLE), &dev->usb->usbctl); } else { writel(tmp & ~BIT(USB_DETECT_ENABLE), &dev->usb->usbctl); - stop_activity(dev, dev->driver); + stop_activity(dev, NULL); } spin_unlock_irqrestore(&dev->lock, flags); + if (!is_on && dev->driver) + dev->driver->disconnect(&dev->gadget); + return 0; } @@ -2466,8 +2469,11 @@ static void stop_activity(struct net2280 *dev, struct usb_gadget_driver *driver) nuke(&dev->ep[i]); /* report disconnect; the driver is already quiesced */ - if (driver) + if (driver) { + spin_unlock(&dev->lock); driver->disconnect(&dev->gadget); + spin_lock(&dev->lock); + } usb_reinit(dev); } @@ -3341,6 +3347,8 @@ next_endpoints: BIT(PCI_RETRY_ABORT_INTERRUPT)) static void handle_stat1_irqs(struct net2280 *dev, u32 stat) +__releases(dev->lock) +__acquires(dev->lock) { struct net2280_ep *ep; u32 tmp, num, mask, scratch; @@ -3381,12 +3389,14 @@ static void handle_stat1_irqs(struct net2280 *dev, u32 stat) if (disconnect || reset) { stop_activity(dev, dev->driver); ep0_start(dev); + spin_unlock(&dev->lock); if (reset) usb_gadget_udc_reset (&dev->gadget, dev->driver); else (dev->driver->disconnect) (&dev->gadget); + spin_lock(&dev->lock); return; } } @@ -3405,6 +3415,7 @@ static void handle_stat1_irqs(struct net2280 *dev, u32 stat) tmp = BIT(SUSPEND_REQUEST_CHANGE_INTERRUPT); if (stat & tmp) { writel(tmp, &dev->regs->irqstat1); + spin_unlock(&dev->lock); if (stat & BIT(SUSPEND_REQUEST_INTERRUPT)) { if (dev->driver->suspend) dev->driver->suspend(&dev->gadget); @@ -3415,6 +3426,7 @@ static void handle_stat1_irqs(struct net2280 *dev, u32 stat) dev->driver->resume(&dev->gadget); /* at high speed, note erratum 0133 */ } + spin_lock(&dev->lock); stat &= ~tmp; } diff --git a/drivers/usb/gadget/udc/renesas_usb3.c b/drivers/usb/gadget/udc/renesas_usb3.c index 1f879b3f2c96..e1656f361e08 100644 --- a/drivers/usb/gadget/udc/renesas_usb3.c +++ b/drivers/usb/gadget/udc/renesas_usb3.c @@ -812,12 +812,15 @@ static void usb3_irq_epc_int_1_speed(struct renesas_usb3 *usb3) switch (speed) { case USB_STA_SPEED_SS: usb3->gadget.speed = USB_SPEED_SUPER; + usb3->gadget.ep0->maxpacket = USB3_EP0_SS_MAX_PACKET_SIZE; break; case USB_STA_SPEED_HS: usb3->gadget.speed = USB_SPEED_HIGH; + usb3->gadget.ep0->maxpacket = USB3_EP0_HSFS_MAX_PACKET_SIZE; break; case USB_STA_SPEED_FS: usb3->gadget.speed = USB_SPEED_FULL; + usb3->gadget.ep0->maxpacket = USB3_EP0_HSFS_MAX_PACKET_SIZE; break; default: usb3->gadget.speed = USB_SPEED_UNKNOWN; @@ -2513,7 +2516,7 @@ static int renesas_usb3_init_ep(struct renesas_usb3 *usb3, struct device *dev, /* for control pipe */ usb3->gadget.ep0 = &usb3_ep->ep; usb_ep_set_maxpacket_limit(&usb3_ep->ep, - USB3_EP0_HSFS_MAX_PACKET_SIZE); + USB3_EP0_SS_MAX_PACKET_SIZE); usb3_ep->ep.caps.type_control = true; usb3_ep->ep.caps.dir_in = true; usb3_ep->ep.caps.dir_out = true; diff --git a/drivers/usb/host/u132-hcd.c b/drivers/usb/host/u132-hcd.c index 072bd5d5738e..5b8a3d9530c4 100644 --- a/drivers/usb/host/u132-hcd.c +++ b/drivers/usb/host/u132-hcd.c @@ -2555,7 +2555,7 @@ static int u132_get_frame(struct usb_hcd *hcd) } else { int frame = 0; dev_err(&u132->platform_dev->dev, "TODO: u132_get_frame\n"); - msleep(100); + mdelay(100); return frame; } } diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index ef350c33dc4a..b1f27aa38b10 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -1613,6 +1613,10 @@ void xhci_endpoint_copy(struct xhci_hcd *xhci, in_ep_ctx->ep_info2 = out_ep_ctx->ep_info2; in_ep_ctx->deq = out_ep_ctx->deq; in_ep_ctx->tx_info = out_ep_ctx->tx_info; + if (xhci->quirks & XHCI_MTK_HOST) { + in_ep_ctx->reserved[0] = out_ep_ctx->reserved[0]; + in_ep_ctx->reserved[1] = out_ep_ctx->reserved[1]; + } } /* Copy output xhci_slot_ctx to the input xhci_slot_ctx. diff --git a/drivers/usb/host/xhci-plat.c b/drivers/usb/host/xhci-plat.c index 8dc77e34a859..94e939249b2b 100644 --- a/drivers/usb/host/xhci-plat.c +++ b/drivers/usb/host/xhci-plat.c @@ -153,7 +153,7 @@ static int xhci_plat_probe(struct platform_device *pdev) { const struct xhci_plat_priv *priv_match; const struct hc_driver *driver; - struct device *sysdev; + struct device *sysdev, *tmpdev; struct xhci_hcd *xhci; struct resource *res; struct usb_hcd *hcd; @@ -273,19 +273,24 @@ static int xhci_plat_probe(struct platform_device *pdev) goto disable_clk; } - if (device_property_read_bool(sysdev, "usb2-lpm-disable")) - xhci->quirks |= XHCI_HW_LPM_DISABLE; + /* imod_interval is the interrupt moderation value in nanoseconds. */ + xhci->imod_interval = 40000; - if (device_property_read_bool(sysdev, "usb3-lpm-capable")) - xhci->quirks |= XHCI_LPM_SUPPORT; + /* Iterate over all parent nodes for finding quirks */ + for (tmpdev = &pdev->dev; tmpdev; tmpdev = tmpdev->parent) { - if (device_property_read_bool(&pdev->dev, "quirk-broken-port-ped")) - xhci->quirks |= XHCI_BROKEN_PORT_PED; + if (device_property_read_bool(tmpdev, "usb2-lpm-disable")) + xhci->quirks |= XHCI_HW_LPM_DISABLE; - /* imod_interval is the interrupt moderation value in nanoseconds. */ - xhci->imod_interval = 40000; - device_property_read_u32(sysdev, "imod-interval-ns", - &xhci->imod_interval); + if (device_property_read_bool(tmpdev, "usb3-lpm-capable")) + xhci->quirks |= XHCI_LPM_SUPPORT; + + if (device_property_read_bool(tmpdev, "quirk-broken-port-ped")) + xhci->quirks |= XHCI_BROKEN_PORT_PED; + + device_property_read_u32(tmpdev, "imod-interval-ns", + &xhci->imod_interval); + } hcd->usb_phy = devm_usb_get_phy_by_phandle(sysdev, "usb-phy", 0); if (IS_ERR(hcd->usb_phy)) { diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c index 61f48b17e57b..0420eefa647a 100644 --- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -37,6 +37,21 @@ static unsigned long long quirks; module_param(quirks, ullong, S_IRUGO); MODULE_PARM_DESC(quirks, "Bit flags for quirks to be enabled as default"); +static bool td_on_ring(struct xhci_td *td, struct xhci_ring *ring) +{ + struct xhci_segment *seg = ring->first_seg; + + if (!td || !td->start_seg) + return false; + do { + if (seg == td->start_seg) + return true; + seg = seg->next; + } while (seg && seg != ring->first_seg); + + return false; +} + /* TODO: copied from ehci-hcd.c - can this be refactored? */ /* * xhci_handshake - spin reading hc until handshake completes or fails @@ -1571,6 +1586,21 @@ static int xhci_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status) goto done; } + /* + * check ring is not re-allocated since URB was enqueued. If it is, then + * make sure none of the ring related pointers in this URB private data + * are touched, such as td_list, otherwise we overwrite freed data + */ + if (!td_on_ring(&urb_priv->td[0], ep_ring)) { + xhci_err(xhci, "Canceled URB td not found on endpoint ring"); + for (i = urb_priv->num_tds_done; i < urb_priv->num_tds; i++) { + td = &urb_priv->td[i]; + if (!list_empty(&td->cancelled_td_list)) + list_del_init(&td->cancelled_td_list); + } + goto err_giveback; + } + if (xhci->xhc_state & XHCI_STATE_HALTED) { xhci_dbg_trace(xhci, trace_xhci_dbg_cancel_urb, "HC halted, freeing TD manually."); diff --git a/drivers/usb/misc/uss720.c b/drivers/usb/misc/uss720.c index 82f220631bd7..b5d661644263 100644 --- a/drivers/usb/misc/uss720.c +++ b/drivers/usb/misc/uss720.c @@ -369,7 +369,7 @@ static unsigned char parport_uss720_frob_control(struct parport *pp, unsigned ch mask &= 0x0f; val &= 0x0f; d = (priv->reg[1] & (~mask)) ^ val; - if (set_1284_register(pp, 2, d, GFP_KERNEL)) + if (set_1284_register(pp, 2, d, GFP_ATOMIC)) return 0; priv->reg[1] = d; return d & 0xf; @@ -379,7 +379,7 @@ static unsigned char parport_uss720_read_status(struct parport *pp) { unsigned char ret; - if (get_1284_register(pp, 1, &ret, GFP_KERNEL)) + if (get_1284_register(pp, 1, &ret, GFP_ATOMIC)) return 0; return ret & 0xf8; } diff --git a/drivers/usb/misc/yurex.c b/drivers/usb/misc/yurex.c index 3be40eaa1ac9..6d9fd5f64903 100644 --- a/drivers/usb/misc/yurex.c +++ b/drivers/usb/misc/yurex.c @@ -413,6 +413,9 @@ static ssize_t yurex_read(struct file *file, char __user *buffer, size_t count, spin_unlock_irqrestore(&dev->lock, flags); mutex_unlock(&dev->io_mutex); + if (WARN_ON_ONCE(len >= sizeof(in_buffer))) + return -EIO; + return simple_read_from_buffer(buffer, count, ppos, in_buffer, len); } @@ -421,13 +424,13 @@ static ssize_t yurex_write(struct file *file, const char __user *user_buffer, { struct usb_yurex *dev; int i, set = 0, retval = 0; - char buffer[16]; + char buffer[16 + 1]; char *data = buffer; unsigned long long c, c2 = 0; signed long timeout = 0; DEFINE_WAIT(wait); - count = min(sizeof(buffer), count); + count = min(sizeof(buffer) - 1, count); dev = file->private_data; /* verify that we actually have some data to write */ @@ -446,6 +449,7 @@ static ssize_t yurex_write(struct file *file, const char __user *user_buffer, retval = -EFAULT; goto error; } + buffer[count] = 0; memset(dev->cntl_buffer, CMD_PADDING, YUREX_BUF_SIZE); switch (buffer[0]) { diff --git a/drivers/usb/mtu3/mtu3_core.c b/drivers/usb/mtu3/mtu3_core.c index eecfd0671362..d045d8458f81 100644 --- a/drivers/usb/mtu3/mtu3_core.c +++ b/drivers/usb/mtu3/mtu3_core.c @@ -107,8 +107,12 @@ static int mtu3_device_enable(struct mtu3 *mtu) (SSUSB_U2_PORT_DIS | SSUSB_U2_PORT_PDN | SSUSB_U2_PORT_HOST_SEL)); - if (mtu->ssusb->dr_mode == USB_DR_MODE_OTG) + if (mtu->ssusb->dr_mode == USB_DR_MODE_OTG) { mtu3_setbits(ibase, SSUSB_U2_CTRL(0), SSUSB_U2_PORT_OTG_SEL); + if (mtu->is_u3_ip) + mtu3_setbits(ibase, SSUSB_U3_CTRL(0), + SSUSB_U3_PORT_DUAL_MODE); + } return ssusb_check_clocks(mtu->ssusb, check_clk); } diff --git a/drivers/usb/mtu3/mtu3_hw_regs.h b/drivers/usb/mtu3/mtu3_hw_regs.h index 6ee371478d89..a45bb253939f 100644 --- a/drivers/usb/mtu3/mtu3_hw_regs.h +++ b/drivers/usb/mtu3/mtu3_hw_regs.h @@ -459,6 +459,7 @@ /* U3D_SSUSB_U3_CTRL_0P */ #define SSUSB_U3_PORT_SSP_SPEED BIT(9) +#define SSUSB_U3_PORT_DUAL_MODE BIT(7) #define SSUSB_U3_PORT_HOST_SEL BIT(2) #define SSUSB_U3_PORT_PDN BIT(1) #define SSUSB_U3_PORT_DIS BIT(0) diff --git a/drivers/usb/serial/io_ti.h b/drivers/usb/serial/io_ti.h index e53c68261017..9bbcee37524e 100644 --- a/drivers/usb/serial/io_ti.h +++ b/drivers/usb/serial/io_ti.h @@ -173,7 +173,7 @@ struct ump_interrupt { } __attribute__((packed)); -#define TIUMP_GET_PORT_FROM_CODE(c) (((c) >> 4) - 3) +#define TIUMP_GET_PORT_FROM_CODE(c) (((c) >> 6) & 0x01) #define TIUMP_GET_FUNC_FROM_CODE(c) ((c) & 0x0f) #define TIUMP_INTERRUPT_CODE_LSR 0x03 #define TIUMP_INTERRUPT_CODE_MSR 0x04 diff --git a/drivers/usb/serial/ti_usb_3410_5052.c b/drivers/usb/serial/ti_usb_3410_5052.c index 3010878f7f8e..e3c5832337e0 100644 --- a/drivers/usb/serial/ti_usb_3410_5052.c +++ b/drivers/usb/serial/ti_usb_3410_5052.c @@ -1119,7 +1119,7 @@ static void ti_break(struct tty_struct *tty, int break_state) static int ti_get_port_from_code(unsigned char code) { - return (code >> 4) - 3; + return (code >> 6) & 0x01; } static int ti_get_func_from_code(unsigned char code) diff --git a/drivers/usb/storage/scsiglue.c b/drivers/usb/storage/scsiglue.c index c267f2812a04..e227bb5b794f 100644 --- a/drivers/usb/storage/scsiglue.c +++ b/drivers/usb/storage/scsiglue.c @@ -376,6 +376,15 @@ static int queuecommand_lck(struct scsi_cmnd *srb, return 0; } + if ((us->fflags & US_FL_NO_ATA_1X) && + (srb->cmnd[0] == ATA_12 || srb->cmnd[0] == ATA_16)) { + memcpy(srb->sense_buffer, usb_stor_sense_invalidCDB, + sizeof(usb_stor_sense_invalidCDB)); + srb->result = SAM_STAT_CHECK_CONDITION; + done(srb); + return 0; + } + /* enqueue the command and wake up the control thread */ srb->scsi_done = done; us->srb = srb; diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c index 9e9de5452860..1f7b401c4d04 100644 --- a/drivers/usb/storage/uas.c +++ b/drivers/usb/storage/uas.c @@ -842,6 +842,27 @@ static int uas_slave_configure(struct scsi_device *sdev) sdev->skip_ms_page_8 = 1; sdev->wce_default_on = 1; } + + /* + * Some disks return the total number of blocks in response + * to READ CAPACITY rather than the highest block number. + * If this device makes that mistake, tell the sd driver. + */ + if (devinfo->flags & US_FL_FIX_CAPACITY) + sdev->fix_capacity = 1; + + /* + * Some devices don't like MODE SENSE with page=0x3f, + * which is the command used for checking if a device + * is write-protected. Now that we tell the sd driver + * to do a 192-byte transfer with this command the + * majority of devices work fine, but a few still can't + * handle it. The sd driver will simply assume those + * devices are write-enabled. + */ + if (devinfo->flags & US_FL_NO_WP_DETECT) + sdev->skip_ms_page_3f = 1; + scsi_change_queue_depth(sdev, devinfo->qdepth - 2); return 0; } diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h index 22fcfccf453a..f7f83b21dc74 100644 --- a/drivers/usb/storage/unusual_devs.h +++ b/drivers/usb/storage/unusual_devs.h @@ -2288,6 +2288,13 @@ UNUSUAL_DEV( 0x2735, 0x100b, 0x0000, 0x9999, USB_SC_DEVICE, USB_PR_DEVICE, NULL, US_FL_GO_SLOW ), +/* Reported-by: Tim Anderson <tsa@biglakesoftware.com> */ +UNUSUAL_DEV( 0x2ca3, 0x0031, 0x0000, 0x9999, + "DJI", + "CineSSD", + USB_SC_DEVICE, USB_PR_DEVICE, NULL, + US_FL_NO_ATA_1X), + /* * Reported by Frederic Marchal <frederic.marchal@wowcompany.com> * Mio Moov 330 diff --git a/drivers/usb/typec/bus.c b/drivers/usb/typec/bus.c index 95a2b10127db..76299b6ff06d 100644 --- a/drivers/usb/typec/bus.c +++ b/drivers/usb/typec/bus.c @@ -255,12 +255,13 @@ EXPORT_SYMBOL_GPL(typec_altmode_unregister_driver); /* API for the port drivers */ /** - * typec_match_altmode - Match SVID to an array of alternate modes + * typec_match_altmode - Match SVID and mode to an array of alternate modes * @altmodes: Array of alternate modes - * @n: Number of elements in the array, or -1 for NULL termiated arrays + * @n: Number of elements in the array, or -1 for NULL terminated arrays * @svid: Standard or Vendor ID to match with + * @mode: Mode to match with * - * Return pointer to an alternate mode with SVID mathing @svid, or NULL when no + * Return pointer to an alternate mode with SVID matching @svid, or NULL when no * match is found. */ struct typec_altmode *typec_match_altmode(struct typec_altmode **altmodes, diff --git a/drivers/usb/typec/class.c b/drivers/usb/typec/class.c index c202975f8097..e61dffb27a0c 100644 --- a/drivers/usb/typec/class.c +++ b/drivers/usb/typec/class.c @@ -1484,7 +1484,6 @@ EXPORT_SYMBOL_GPL(typec_set_mode); * typec_port_register_altmode - Register USB Type-C Port Alternate Mode * @port: USB Type-C Port that supports the alternate mode * @desc: Description of the alternate mode - * @drvdata: Private pointer to driver specific info * * This routine is used to register an alternate mode that @port is capable of * supporting. diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 4e656f89cb22..dd4e0a301635 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -116,6 +116,8 @@ struct vhost_net_virtqueue { * For RX, number of batched heads */ int done_idx; + /* Number of XDP frames batched */ + int batched_xdp; /* an array of userspace buffers info */ struct ubuf_info *ubuf_info; /* Reference counting for outstanding ubufs. @@ -123,6 +125,8 @@ struct vhost_net_virtqueue { struct vhost_net_ubuf_ref *ubufs; struct ptr_ring *rx_ring; struct vhost_net_buf rxq; + /* Batched XDP buffs */ + struct xdp_buff *xdp; }; struct vhost_net { @@ -338,6 +342,11 @@ static bool vhost_sock_zcopy(struct socket *sock) sock_flag(sock->sk, SOCK_ZEROCOPY); } +static bool vhost_sock_xdp(struct socket *sock) +{ + return sock_flag(sock->sk, SOCK_XDP); +} + /* In case of DMA done not in order in lower device driver for some reason. * upend_idx is used to track end of used idx, done_idx is used to track head * of used idx. Once lower device DMA done contiguously, we will signal KVM @@ -444,10 +453,37 @@ static void vhost_net_signal_used(struct vhost_net_virtqueue *nvq) nvq->done_idx = 0; } +static void vhost_tx_batch(struct vhost_net *net, + struct vhost_net_virtqueue *nvq, + struct socket *sock, + struct msghdr *msghdr) +{ + struct tun_msg_ctl ctl = { + .type = TUN_MSG_PTR, + .num = nvq->batched_xdp, + .ptr = nvq->xdp, + }; + int err; + + if (nvq->batched_xdp == 0) + goto signal_used; + + msghdr->msg_control = &ctl; + err = sock->ops->sendmsg(sock, msghdr, 0); + if (unlikely(err < 0)) { + vq_err(&nvq->vq, "Fail to batch sending packets\n"); + return; + } + +signal_used: + vhost_net_signal_used(nvq); + nvq->batched_xdp = 0; +} + static int vhost_net_tx_get_vq_desc(struct vhost_net *net, struct vhost_net_virtqueue *nvq, unsigned int *out_num, unsigned int *in_num, - bool *busyloop_intr) + struct msghdr *msghdr, bool *busyloop_intr) { struct vhost_virtqueue *vq = &nvq->vq; unsigned long uninitialized_var(endtime); @@ -455,8 +491,9 @@ static int vhost_net_tx_get_vq_desc(struct vhost_net *net, out_num, in_num, NULL, NULL); if (r == vq->num && vq->busyloop_timeout) { + /* Flush batched packets first */ if (!vhost_sock_zcopy(vq->private_data)) - vhost_net_signal_used(nvq); + vhost_tx_batch(net, nvq, vq->private_data, msghdr); preempt_disable(); endtime = busy_clock() + vq->busyloop_timeout; while (vhost_can_busy_poll(endtime)) { @@ -512,7 +549,7 @@ static int get_tx_bufs(struct vhost_net *net, struct vhost_virtqueue *vq = &nvq->vq; int ret; - ret = vhost_net_tx_get_vq_desc(net, nvq, out, in, busyloop_intr); + ret = vhost_net_tx_get_vq_desc(net, nvq, out, in, msg, busyloop_intr); if (ret < 0 || ret == vq->num) return ret; @@ -540,6 +577,80 @@ static bool tx_can_batch(struct vhost_virtqueue *vq, size_t total_len) !vhost_vq_avail_empty(vq->dev, vq); } +#define VHOST_NET_RX_PAD (NET_IP_ALIGN + NET_SKB_PAD) + +static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq, + struct iov_iter *from) +{ + struct vhost_virtqueue *vq = &nvq->vq; + struct socket *sock = vq->private_data; + struct page_frag *alloc_frag = ¤t->task_frag; + struct virtio_net_hdr *gso; + struct xdp_buff *xdp = &nvq->xdp[nvq->batched_xdp]; + struct tun_xdp_hdr *hdr; + size_t len = iov_iter_count(from); + int headroom = vhost_sock_xdp(sock) ? XDP_PACKET_HEADROOM : 0; + int buflen = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + int pad = SKB_DATA_ALIGN(VHOST_NET_RX_PAD + headroom + nvq->sock_hlen); + int sock_hlen = nvq->sock_hlen; + void *buf; + int copied; + + if (unlikely(len < nvq->sock_hlen)) + return -EFAULT; + + if (SKB_DATA_ALIGN(len + pad) + + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) > PAGE_SIZE) + return -ENOSPC; + + buflen += SKB_DATA_ALIGN(len + pad); + alloc_frag->offset = ALIGN((u64)alloc_frag->offset, SMP_CACHE_BYTES); + if (unlikely(!skb_page_frag_refill(buflen, alloc_frag, GFP_KERNEL))) + return -ENOMEM; + + buf = (char *)page_address(alloc_frag->page) + alloc_frag->offset; + copied = copy_page_from_iter(alloc_frag->page, + alloc_frag->offset + + offsetof(struct tun_xdp_hdr, gso), + sock_hlen, from); + if (copied != sock_hlen) + return -EFAULT; + + hdr = buf; + gso = &hdr->gso; + + if ((gso->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) && + vhost16_to_cpu(vq, gso->csum_start) + + vhost16_to_cpu(vq, gso->csum_offset) + 2 > + vhost16_to_cpu(vq, gso->hdr_len)) { + gso->hdr_len = cpu_to_vhost16(vq, + vhost16_to_cpu(vq, gso->csum_start) + + vhost16_to_cpu(vq, gso->csum_offset) + 2); + + if (vhost16_to_cpu(vq, gso->hdr_len) > len) + return -EINVAL; + } + + len -= sock_hlen; + copied = copy_page_from_iter(alloc_frag->page, + alloc_frag->offset + pad, + len, from); + if (copied != len) + return -EFAULT; + + xdp->data_hard_start = buf; + xdp->data = buf + pad; + xdp->data_end = xdp->data + len; + hdr->buflen = buflen; + + get_page(alloc_frag->page); + alloc_frag->offset += buflen; + + ++nvq->batched_xdp; + + return 0; +} + static void handle_tx_copy(struct vhost_net *net, struct socket *sock) { struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX]; @@ -556,10 +667,14 @@ static void handle_tx_copy(struct vhost_net *net, struct socket *sock) size_t len, total_len = 0; int err; int sent_pkts = 0; + bool sock_can_batch = (sock->sk->sk_sndbuf == INT_MAX); for (;;) { bool busyloop_intr = false; + if (nvq->done_idx == VHOST_NET_BATCH) + vhost_tx_batch(net, nvq, sock, &msg); + head = get_tx_bufs(net, nvq, &msg, &out, &in, &len, &busyloop_intr); /* On error, stop handling until the next kick. */ @@ -577,14 +692,34 @@ static void handle_tx_copy(struct vhost_net *net, struct socket *sock) break; } - vq->heads[nvq->done_idx].id = cpu_to_vhost32(vq, head); - vq->heads[nvq->done_idx].len = 0; - total_len += len; - if (tx_can_batch(vq, total_len)) - msg.msg_flags |= MSG_MORE; - else - msg.msg_flags &= ~MSG_MORE; + + /* For simplicity, TX batching is only enabled if + * sndbuf is unlimited. + */ + if (sock_can_batch) { + err = vhost_net_build_xdp(nvq, &msg.msg_iter); + if (!err) { + goto done; + } else if (unlikely(err != -ENOSPC)) { + vhost_tx_batch(net, nvq, sock, &msg); + vhost_discard_vq_desc(vq, 1); + vhost_net_enable_vq(net, vq); + break; + } + + /* We can't build XDP buff, go for single + * packet path but let's flush batched + * packets. + */ + vhost_tx_batch(net, nvq, sock, &msg); + msg.msg_control = NULL; + } else { + if (tx_can_batch(vq, total_len)) + msg.msg_flags |= MSG_MORE; + else + msg.msg_flags &= ~MSG_MORE; + } /* TODO: Check specific error and bomb out unless ENOBUFS? */ err = sock->ops->sendmsg(sock, &msg, len); @@ -596,15 +731,17 @@ static void handle_tx_copy(struct vhost_net *net, struct socket *sock) if (err != len) pr_debug("Truncated TX packet: len %d != %zd\n", err, len); - if (++nvq->done_idx >= VHOST_NET_BATCH) - vhost_net_signal_used(nvq); +done: + vq->heads[nvq->done_idx].id = cpu_to_vhost32(vq, head); + vq->heads[nvq->done_idx].len = 0; + ++nvq->done_idx; if (vhost_exceeds_weight(++sent_pkts, total_len)) { vhost_poll_queue(&vq->poll); break; } } - vhost_net_signal_used(nvq); + vhost_tx_batch(net, nvq, sock, &msg); } static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock) @@ -620,6 +757,7 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock) .msg_controllen = 0, .msg_flags = MSG_DONTWAIT, }; + struct tun_msg_ctl ctl; size_t len, total_len = 0; int err; struct vhost_net_ubuf_ref *uninitialized_var(ubufs); @@ -664,8 +802,10 @@ static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock) ubuf->ctx = nvq->ubufs; ubuf->desc = nvq->upend_idx; refcount_set(&ubuf->refcnt, 1); - msg.msg_control = ubuf; - msg.msg_controllen = sizeof(ubuf); + msg.msg_control = &ctl; + ctl.type = TUN_MSG_UBUF; + ctl.ptr = ubuf; + msg.msg_controllen = sizeof(ctl); ubufs = nvq->ubufs; atomic_inc(&ubufs->refcount); nvq->upend_idx = (nvq->upend_idx + 1) % UIO_MAXIOV; @@ -1078,6 +1218,7 @@ static int vhost_net_open(struct inode *inode, struct file *f) struct vhost_dev *dev; struct vhost_virtqueue **vqs; void **queue; + struct xdp_buff *xdp; int i; n = kvmalloc(sizeof *n, GFP_KERNEL | __GFP_RETRY_MAYFAIL); @@ -1098,6 +1239,14 @@ static int vhost_net_open(struct inode *inode, struct file *f) } n->vqs[VHOST_NET_VQ_RX].rxq.queue = queue; + xdp = kmalloc_array(VHOST_NET_BATCH, sizeof(*xdp), GFP_KERNEL); + if (!xdp) { + kfree(vqs); + kvfree(n); + kfree(queue); + } + n->vqs[VHOST_NET_VQ_TX].xdp = xdp; + dev = &n->dev; vqs[VHOST_NET_VQ_TX] = &n->vqs[VHOST_NET_VQ_TX].vq; vqs[VHOST_NET_VQ_RX] = &n->vqs[VHOST_NET_VQ_RX].vq; @@ -1108,6 +1257,7 @@ static int vhost_net_open(struct inode *inode, struct file *f) n->vqs[i].ubuf_info = NULL; n->vqs[i].upend_idx = 0; n->vqs[i].done_idx = 0; + n->vqs[i].batched_xdp = 0; n->vqs[i].vhost_hlen = 0; n->vqs[i].sock_hlen = 0; n->vqs[i].rx_ring = NULL; @@ -1191,6 +1341,7 @@ static int vhost_net_release(struct inode *inode, struct file *f) * since jobs can re-queue themselves. */ vhost_net_flush(n); kfree(n->vqs[VHOST_NET_VQ_RX].rxq.queue); + kfree(n->vqs[VHOST_NET_VQ_TX].xdp); kfree(n->dev.vqs); kvfree(n); return 0; diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 96c1d8400822..b13c6b4b2c66 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -952,7 +952,7 @@ static void vhost_iotlb_notify_vq(struct vhost_dev *d, list_for_each_entry_safe(node, n, &d->pending_list, node) { struct vhost_iotlb_msg *vq_msg = &node->msg.iotlb; if (msg->iova <= vq_msg->iova && - msg->iova + msg->size - 1 > vq_msg->iova && + msg->iova + msg->size - 1 >= vq_msg->iova && vq_msg->type == VHOST_IOTLB_MISS) { vhost_poll_queue(&node->vq->poll); list_del(&node->node); diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig index b459edfacff3..90d387b50ab7 100644 --- a/drivers/xen/Kconfig +++ b/drivers/xen/Kconfig @@ -79,15 +79,19 @@ config XEN_BALLOON_MEMORY_HOTPLUG_LIMIT This value is used to allocate enough space in internal tables needed for physical memory administration. -config XEN_SCRUB_PAGES - bool "Scrub pages before returning them to system" +config XEN_SCRUB_PAGES_DEFAULT + bool "Scrub pages before returning them to system by default" depends on XEN_BALLOON default y help Scrub pages before returning them to the system for reuse by other domains. This makes sure that any confidential data is not accidentally visible to other domains. Is it more - secure, but slightly less efficient. + secure, but slightly less efficient. This can be controlled with + xen_scrub_pages=0 parameter and + /sys/devices/system/xen_memory/xen_memory0/scrub_pages. + This option only sets the default value. + If in doubt, say yes. config XEN_DEV_EVTCHN diff --git a/drivers/xen/cpu_hotplug.c b/drivers/xen/cpu_hotplug.c index d4265c8ebb22..b1357aa4bc55 100644 --- a/drivers/xen/cpu_hotplug.c +++ b/drivers/xen/cpu_hotplug.c @@ -19,15 +19,16 @@ static void enable_hotplug_cpu(int cpu) static void disable_hotplug_cpu(int cpu) { - if (cpu_online(cpu)) { - lock_device_hotplug(); + if (!cpu_is_hotpluggable(cpu)) + return; + lock_device_hotplug(); + if (cpu_online(cpu)) device_offline(get_cpu_device(cpu)); - unlock_device_hotplug(); - } - if (cpu_present(cpu)) + if (!cpu_online(cpu) && cpu_present(cpu)) { xen_arch_unregister_cpu(cpu); - - set_cpu_present(cpu, false); + set_cpu_present(cpu, false); + } + unlock_device_hotplug(); } static int vcpu_online(unsigned int cpu) diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index 08e4af04d6f2..e6c1934734b7 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -138,7 +138,7 @@ static int set_evtchn_to_irq(unsigned evtchn, unsigned irq) clear_evtchn_to_irq_row(row); } - evtchn_to_irq[EVTCHN_ROW(evtchn)][EVTCHN_COL(evtchn)] = irq; + evtchn_to_irq[row][col] = irq; return 0; } diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c index 57390c7666e5..b0b02a501167 100644 --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -492,12 +492,19 @@ static bool in_range(struct gntdev_grant_map *map, return true; } -static void unmap_if_in_range(struct gntdev_grant_map *map, - unsigned long start, unsigned long end) +static int unmap_if_in_range(struct gntdev_grant_map *map, + unsigned long start, unsigned long end, + bool blockable) { unsigned long mstart, mend; int err; + if (!in_range(map, start, end)) + return 0; + + if (!blockable) + return -EAGAIN; + mstart = max(start, map->vma->vm_start); mend = min(end, map->vma->vm_end); pr_debug("map %d+%d (%lx %lx), range %lx %lx, mrange %lx %lx\n", @@ -508,6 +515,8 @@ static void unmap_if_in_range(struct gntdev_grant_map *map, (mstart - map->vma->vm_start) >> PAGE_SHIFT, (mend - mstart) >> PAGE_SHIFT); WARN_ON(err); + + return 0; } static int mn_invl_range_start(struct mmu_notifier *mn, @@ -519,25 +528,20 @@ static int mn_invl_range_start(struct mmu_notifier *mn, struct gntdev_grant_map *map; int ret = 0; - /* TODO do we really need a mutex here? */ if (blockable) mutex_lock(&priv->lock); else if (!mutex_trylock(&priv->lock)) return -EAGAIN; list_for_each_entry(map, &priv->maps, next) { - if (in_range(map, start, end)) { - ret = -EAGAIN; + ret = unmap_if_in_range(map, start, end, blockable); + if (ret) goto out_unlock; - } - unmap_if_in_range(map, start, end); } list_for_each_entry(map, &priv->freeable_maps, next) { - if (in_range(map, start, end)) { - ret = -EAGAIN; + ret = unmap_if_in_range(map, start, end, blockable); + if (ret) goto out_unlock; - } - unmap_if_in_range(map, start, end); } out_unlock: diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c index c93d8ef8df34..5bb01a62f214 100644 --- a/drivers/xen/manage.c +++ b/drivers/xen/manage.c @@ -280,9 +280,11 @@ static void sysrq_handler(struct xenbus_watch *watch, const char *path, /* * The Xenstore watch fires directly after registering it and * after a suspend/resume cycle. So ENOENT is no error but - * might happen in those cases. + * might happen in those cases. ERANGE is observed when we get + * an empty value (''), this happens when we acknowledge the + * request by writing '\0' below. */ - if (err != -ENOENT) + if (err != -ENOENT && err != -ERANGE) pr_err("Error %d reading sysrq code in control/sysrq\n", err); xenbus_transaction_end(xbt, 1); diff --git a/drivers/xen/mem-reservation.c b/drivers/xen/mem-reservation.c index 084799c6180e..3782cf070338 100644 --- a/drivers/xen/mem-reservation.c +++ b/drivers/xen/mem-reservation.c @@ -14,6 +14,10 @@ #include <xen/interface/memory.h> #include <xen/mem-reservation.h> +#include <linux/moduleparam.h> + +bool __read_mostly xen_scrub_pages = IS_ENABLED(CONFIG_XEN_SCRUB_PAGES_DEFAULT); +core_param(xen_scrub_pages, xen_scrub_pages, bool, 0); /* * Use one extent per PAGE_SIZE to avoid to break down the page into diff --git a/drivers/xen/xen-balloon.c b/drivers/xen/xen-balloon.c index 294f35ce9e46..63c1494a8d73 100644 --- a/drivers/xen/xen-balloon.c +++ b/drivers/xen/xen-balloon.c @@ -44,6 +44,7 @@ #include <xen/xenbus.h> #include <xen/features.h> #include <xen/page.h> +#include <xen/mem-reservation.h> #define PAGES2KB(_p) ((_p)<<(PAGE_SHIFT-10)) @@ -137,6 +138,7 @@ static DEVICE_ULONG_ATTR(schedule_delay, 0444, balloon_stats.schedule_delay); static DEVICE_ULONG_ATTR(max_schedule_delay, 0644, balloon_stats.max_schedule_delay); static DEVICE_ULONG_ATTR(retry_count, 0444, balloon_stats.retry_count); static DEVICE_ULONG_ATTR(max_retry_count, 0644, balloon_stats.max_retry_count); +static DEVICE_BOOL_ATTR(scrub_pages, 0644, xen_scrub_pages); static ssize_t show_target_kb(struct device *dev, struct device_attribute *attr, char *buf) @@ -203,6 +205,7 @@ static struct attribute *balloon_attrs[] = { &dev_attr_max_schedule_delay.attr.attr, &dev_attr_retry_count.attr.attr, &dev_attr_max_retry_count.attr.attr, + &dev_attr_scrub_pages.attr.attr, NULL }; diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c index f2088838f690..5b471889d723 100644 --- a/drivers/xen/xenbus/xenbus_probe.c +++ b/drivers/xen/xenbus/xenbus_probe.c @@ -402,10 +402,19 @@ static ssize_t modalias_show(struct device *dev, } static DEVICE_ATTR_RO(modalias); +static ssize_t state_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return sprintf(buf, "%s\n", + xenbus_strstate(to_xenbus_device(dev)->state)); +} +static DEVICE_ATTR_RO(state); + static struct attribute *xenbus_dev_attrs[] = { &dev_attr_nodename.attr, &dev_attr_devtype.attr, &dev_attr_modalias.attr, + &dev_attr_state.attr, NULL, }; diff --git a/fs/afs/proc.c b/fs/afs/proc.c index 0c3285c8db95..476dcbb79713 100644 --- a/fs/afs/proc.c +++ b/fs/afs/proc.c @@ -98,13 +98,13 @@ static int afs_proc_cells_write(struct file *file, char *buf, size_t size) goto inval; args = strchr(name, ' '); - if (!args) - goto inval; - do { - *args++ = 0; - } while(*args == ' '); - if (!*args) - goto inval; + if (args) { + do { + *args++ = 0; + } while(*args == ' '); + if (!*args) + goto inval; + } /* determine command to perform */ _debug("cmd=%s name=%s args=%s", buf, name, args); @@ -120,7 +120,6 @@ static int afs_proc_cells_write(struct file *file, char *buf, size_t size) if (test_and_set_bit(AFS_CELL_FL_NO_GC, &cell->flags)) afs_put_cell(net, cell); - printk("kAFS: Added new cell '%s'\n", name); } else { goto inval; } diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 53af9f5253f4..2cddfe7806a4 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1280,6 +1280,7 @@ struct btrfs_root { int send_in_progress; struct btrfs_subvolume_writers *subv_writers; atomic_t will_be_snapshotted; + atomic_t snapshot_force_cow; /* For qgroup metadata reserved space */ spinlock_t qgroup_meta_rsv_lock; @@ -3390,9 +3391,9 @@ do { \ #define btrfs_debug(fs_info, fmt, args...) \ btrfs_no_printk(fs_info, KERN_DEBUG fmt, ##args) #define btrfs_debug_in_rcu(fs_info, fmt, args...) \ - btrfs_no_printk(fs_info, KERN_DEBUG fmt, ##args) + btrfs_no_printk_in_rcu(fs_info, KERN_DEBUG fmt, ##args) #define btrfs_debug_rl_in_rcu(fs_info, fmt, args...) \ - btrfs_no_printk(fs_info, KERN_DEBUG fmt, ##args) + btrfs_no_printk_in_rcu(fs_info, KERN_DEBUG fmt, ##args) #define btrfs_debug_rl(fs_info, fmt, args...) \ btrfs_no_printk(fs_info, KERN_DEBUG fmt, ##args) #endif @@ -3404,6 +3405,13 @@ do { \ rcu_read_unlock(); \ } while (0) +#define btrfs_no_printk_in_rcu(fs_info, fmt, args...) \ +do { \ + rcu_read_lock(); \ + btrfs_no_printk(fs_info, fmt, ##args); \ + rcu_read_unlock(); \ +} while (0) + #define btrfs_printk_ratelimited(fs_info, fmt, args...) \ do { \ static DEFINE_RATELIMIT_STATE(_rs, \ diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 5124c15705ce..05dc3c17cb62 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1187,6 +1187,7 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, atomic_set(&root->log_batch, 0); refcount_set(&root->refs, 1); atomic_set(&root->will_be_snapshotted, 0); + atomic_set(&root->snapshot_force_cow, 0); root->log_transid = 0; root->log_transid_committed = -1; root->last_log_commit = 0; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index de6f75f5547b..2d9074295d7f 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -5800,7 +5800,7 @@ void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans) * root: the root of the parent directory * rsv: block reservation * items: the number of items that we need do reservation - * qgroup_reserved: used to return the reserved size in qgroup + * use_global_rsv: allow fallback to the global block reservation * * This function is used to reserve the space for snapshot/subvolume * creation and deletion. Those operations are different with the @@ -5810,10 +5810,10 @@ void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans) * the space reservation mechanism in start_transaction(). */ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, - struct btrfs_block_rsv *rsv, - int items, + struct btrfs_block_rsv *rsv, int items, bool use_global_rsv) { + u64 qgroup_num_bytes = 0; u64 num_bytes; int ret; struct btrfs_fs_info *fs_info = root->fs_info; @@ -5821,12 +5821,11 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, if (test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) { /* One for parent inode, two for dir entries */ - num_bytes = 3 * fs_info->nodesize; - ret = btrfs_qgroup_reserve_meta_prealloc(root, num_bytes, true); + qgroup_num_bytes = 3 * fs_info->nodesize; + ret = btrfs_qgroup_reserve_meta_prealloc(root, + qgroup_num_bytes, true); if (ret) return ret; - } else { - num_bytes = 0; } num_bytes = btrfs_calc_trans_metadata_size(fs_info, items); @@ -5838,8 +5837,8 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, if (ret == -ENOSPC && use_global_rsv) ret = btrfs_block_rsv_migrate(global_rsv, rsv, num_bytes, 1); - if (ret && num_bytes) - btrfs_qgroup_free_meta_prealloc(root, num_bytes); + if (ret && qgroup_num_bytes) + btrfs_qgroup_free_meta_prealloc(root, qgroup_num_bytes); return ret; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 9357a19d2bff..3ea5339603cf 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1271,7 +1271,7 @@ static noinline int run_delalloc_nocow(struct inode *inode, u64 disk_num_bytes; u64 ram_bytes; int extent_type; - int ret, err; + int ret; int type; int nocow; int check_prev = 1; @@ -1403,11 +1403,8 @@ next_slot: * if there are pending snapshots for this root, * we fall into common COW way. */ - if (!nolock) { - err = btrfs_start_write_no_snapshotting(root); - if (!err) - goto out_check; - } + if (!nolock && atomic_read(&root->snapshot_force_cow)) + goto out_check; /* * force cow if csum exists in the range. * this ensure that csum for a given extent are @@ -1416,9 +1413,6 @@ next_slot: ret = csum_exist_in_range(fs_info, disk_bytenr, num_bytes); if (ret) { - if (!nolock) - btrfs_end_write_no_snapshotting(root); - /* * ret could be -EIO if the above fails to read * metadata. @@ -1431,11 +1425,8 @@ next_slot: WARN_ON_ONCE(nolock); goto out_check; } - if (!btrfs_inc_nocow_writers(fs_info, disk_bytenr)) { - if (!nolock) - btrfs_end_write_no_snapshotting(root); + if (!btrfs_inc_nocow_writers(fs_info, disk_bytenr)) goto out_check; - } nocow = 1; } else if (extent_type == BTRFS_FILE_EXTENT_INLINE) { extent_end = found_key.offset + @@ -1448,8 +1439,6 @@ next_slot: out_check: if (extent_end <= start) { path->slots[0]++; - if (!nolock && nocow) - btrfs_end_write_no_snapshotting(root); if (nocow) btrfs_dec_nocow_writers(fs_info, disk_bytenr); goto next_slot; @@ -1471,8 +1460,6 @@ out_check: end, page_started, nr_written, 1, NULL); if (ret) { - if (!nolock && nocow) - btrfs_end_write_no_snapshotting(root); if (nocow) btrfs_dec_nocow_writers(fs_info, disk_bytenr); @@ -1492,8 +1479,6 @@ out_check: ram_bytes, BTRFS_COMPRESS_NONE, BTRFS_ORDERED_PREALLOC); if (IS_ERR(em)) { - if (!nolock && nocow) - btrfs_end_write_no_snapshotting(root); if (nocow) btrfs_dec_nocow_writers(fs_info, disk_bytenr); @@ -1532,8 +1517,6 @@ out_check: EXTENT_CLEAR_DATA_RESV, PAGE_UNLOCK | PAGE_SET_PRIVATE2); - if (!nolock && nocow) - btrfs_end_write_no_snapshotting(root); cur_offset = extent_end; /* @@ -6639,6 +6622,8 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, drop_inode = 1; } else { struct dentry *parent = dentry->d_parent; + int ret; + err = btrfs_update_inode(trans, root, inode); if (err) goto fail; @@ -6652,7 +6637,12 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, goto fail; } d_instantiate(dentry, inode); - btrfs_log_new_name(trans, BTRFS_I(inode), NULL, parent); + ret = btrfs_log_new_name(trans, BTRFS_I(inode), NULL, parent, + true, NULL); + if (ret == BTRFS_NEED_TRANS_COMMIT) { + err = btrfs_commit_transaction(trans); + trans = NULL; + } } fail: @@ -9388,14 +9378,21 @@ static int btrfs_rename_exchange(struct inode *old_dir, u64 new_idx = 0; u64 root_objectid; int ret; - int ret2; bool root_log_pinned = false; bool dest_log_pinned = false; + struct btrfs_log_ctx ctx_root; + struct btrfs_log_ctx ctx_dest; + bool sync_log_root = false; + bool sync_log_dest = false; + bool commit_transaction = false; /* we only allow rename subvolume link between subvolumes */ if (old_ino != BTRFS_FIRST_FREE_OBJECTID && root != dest) return -EXDEV; + btrfs_init_log_ctx(&ctx_root, old_inode); + btrfs_init_log_ctx(&ctx_dest, new_inode); + /* close the race window with snapshot create/destroy ioctl */ if (old_ino == BTRFS_FIRST_FREE_OBJECTID) down_read(&fs_info->subvol_sem); @@ -9542,15 +9539,29 @@ static int btrfs_rename_exchange(struct inode *old_dir, if (root_log_pinned) { parent = new_dentry->d_parent; - btrfs_log_new_name(trans, BTRFS_I(old_inode), BTRFS_I(old_dir), - parent); + ret = btrfs_log_new_name(trans, BTRFS_I(old_inode), + BTRFS_I(old_dir), parent, + false, &ctx_root); + if (ret == BTRFS_NEED_LOG_SYNC) + sync_log_root = true; + else if (ret == BTRFS_NEED_TRANS_COMMIT) + commit_transaction = true; + ret = 0; btrfs_end_log_trans(root); root_log_pinned = false; } if (dest_log_pinned) { - parent = old_dentry->d_parent; - btrfs_log_new_name(trans, BTRFS_I(new_inode), BTRFS_I(new_dir), - parent); + if (!commit_transaction) { + parent = old_dentry->d_parent; + ret = btrfs_log_new_name(trans, BTRFS_I(new_inode), + BTRFS_I(new_dir), parent, + false, &ctx_dest); + if (ret == BTRFS_NEED_LOG_SYNC) + sync_log_dest = true; + else if (ret == BTRFS_NEED_TRANS_COMMIT) + commit_transaction = true; + ret = 0; + } btrfs_end_log_trans(dest); dest_log_pinned = false; } @@ -9583,8 +9594,26 @@ out_fail: dest_log_pinned = false; } } - ret2 = btrfs_end_transaction(trans); - ret = ret ? ret : ret2; + if (!ret && sync_log_root && !commit_transaction) { + ret = btrfs_sync_log(trans, BTRFS_I(old_inode)->root, + &ctx_root); + if (ret) + commit_transaction = true; + } + if (!ret && sync_log_dest && !commit_transaction) { + ret = btrfs_sync_log(trans, BTRFS_I(new_inode)->root, + &ctx_dest); + if (ret) + commit_transaction = true; + } + if (commit_transaction) { + ret = btrfs_commit_transaction(trans); + } else { + int ret2; + + ret2 = btrfs_end_transaction(trans); + ret = ret ? ret : ret2; + } out_notrans: if (new_ino == BTRFS_FIRST_FREE_OBJECTID) up_read(&fs_info->subvol_sem); @@ -9661,6 +9690,9 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, int ret; u64 old_ino = btrfs_ino(BTRFS_I(old_inode)); bool log_pinned = false; + struct btrfs_log_ctx ctx; + bool sync_log = false; + bool commit_transaction = false; if (btrfs_ino(BTRFS_I(new_dir)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID) return -EPERM; @@ -9818,8 +9850,15 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry, if (log_pinned) { struct dentry *parent = new_dentry->d_parent; - btrfs_log_new_name(trans, BTRFS_I(old_inode), BTRFS_I(old_dir), - parent); + btrfs_init_log_ctx(&ctx, old_inode); + ret = btrfs_log_new_name(trans, BTRFS_I(old_inode), + BTRFS_I(old_dir), parent, + false, &ctx); + if (ret == BTRFS_NEED_LOG_SYNC) + sync_log = true; + else if (ret == BTRFS_NEED_TRANS_COMMIT) + commit_transaction = true; + ret = 0; btrfs_end_log_trans(root); log_pinned = false; } @@ -9856,7 +9895,19 @@ out_fail: btrfs_end_log_trans(root); log_pinned = false; } - btrfs_end_transaction(trans); + if (!ret && sync_log) { + ret = btrfs_sync_log(trans, BTRFS_I(old_inode)->root, &ctx); + if (ret) + commit_transaction = true; + } + if (commit_transaction) { + ret = btrfs_commit_transaction(trans); + } else { + int ret2; + + ret2 = btrfs_end_transaction(trans); + ret = ret ? ret : ret2; + } out_notrans: if (old_ino == BTRFS_FIRST_FREE_OBJECTID) up_read(&fs_info->subvol_sem); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 63600dc2ac4c..d60b6caf09e8 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -747,6 +747,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, struct btrfs_pending_snapshot *pending_snapshot; struct btrfs_trans_handle *trans; int ret; + bool snapshot_force_cow = false; if (!test_bit(BTRFS_ROOT_REF_COWS, &root->state)) return -EINVAL; @@ -763,6 +764,11 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, goto free_pending; } + /* + * Force new buffered writes to reserve space even when NOCOW is + * possible. This is to avoid later writeback (running dealloc) to + * fallback to COW mode and unexpectedly fail with ENOSPC. + */ atomic_inc(&root->will_be_snapshotted); smp_mb__after_atomic(); /* wait for no snapshot writes */ @@ -773,6 +779,14 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, if (ret) goto dec_and_free; + /* + * All previous writes have started writeback in NOCOW mode, so now + * we force future writes to fallback to COW mode during snapshot + * creation. + */ + atomic_inc(&root->snapshot_force_cow); + snapshot_force_cow = true; + btrfs_wait_ordered_extents(root, U64_MAX, 0, (u64)-1); btrfs_init_block_rsv(&pending_snapshot->block_rsv, @@ -837,6 +851,8 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, fail: btrfs_subvolume_release_metadata(fs_info, &pending_snapshot->block_rsv); dec_and_free: + if (snapshot_force_cow) + atomic_dec(&root->snapshot_force_cow); if (atomic_dec_and_test(&root->will_be_snapshotted)) wake_up_var(&root->will_be_snapshotted); free_pending: @@ -3453,6 +3469,25 @@ static int btrfs_extent_same_range(struct inode *src, u64 loff, u64 olen, same_lock_start = min_t(u64, loff, dst_loff); same_lock_len = max_t(u64, loff, dst_loff) + len - same_lock_start; + } else { + /* + * If the source and destination inodes are different, the + * source's range end offset matches the source's i_size, that + * i_size is not a multiple of the sector size, and the + * destination range does not go past the destination's i_size, + * we must round down the length to the nearest sector size + * multiple. If we don't do this adjustment we end replacing + * with zeroes the bytes in the range that starts at the + * deduplication range's end offset and ends at the next sector + * size multiple. + */ + if (loff + olen == i_size_read(src) && + dst_loff + len < i_size_read(dst)) { + const u64 sz = BTRFS_I(src)->root->fs_info->sectorsize; + + len = round_down(i_size_read(src), sz) - loff; + olen = len; + } } again: diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 4353bb69bb86..d4917c0cddf5 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1019,10 +1019,9 @@ out_add_root: spin_unlock(&fs_info->qgroup_lock); ret = btrfs_commit_transaction(trans); - if (ret) { - trans = NULL; + trans = NULL; + if (ret) goto out_free_path; - } ret = qgroup_rescan_init(fs_info, 0, 1); if (!ret) { diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 1650dc44a5e3..3c2ae0e4f25a 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -6025,14 +6025,25 @@ void btrfs_record_snapshot_destroy(struct btrfs_trans_handle *trans, * Call this after adding a new name for a file and it will properly * update the log to reflect the new name. * - * It will return zero if all goes well, and it will return 1 if a - * full transaction commit is required. + * @ctx can not be NULL when @sync_log is false, and should be NULL when it's + * true (because it's not used). + * + * Return value depends on whether @sync_log is true or false. + * When true: returns BTRFS_NEED_TRANS_COMMIT if the transaction needs to be + * committed by the caller, and BTRFS_DONT_NEED_TRANS_COMMIT + * otherwise. + * When false: returns BTRFS_DONT_NEED_LOG_SYNC if the caller does not need to + * to sync the log, BTRFS_NEED_LOG_SYNC if it needs to sync the log, + * or BTRFS_NEED_TRANS_COMMIT if the transaction needs to be + * committed (without attempting to sync the log). */ int btrfs_log_new_name(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_inode *old_dir, - struct dentry *parent) + struct dentry *parent, + bool sync_log, struct btrfs_log_ctx *ctx) { struct btrfs_fs_info *fs_info = trans->fs_info; + int ret; /* * this will force the logging code to walk the dentry chain @@ -6047,9 +6058,34 @@ int btrfs_log_new_name(struct btrfs_trans_handle *trans, */ if (inode->logged_trans <= fs_info->last_trans_committed && (!old_dir || old_dir->logged_trans <= fs_info->last_trans_committed)) - return 0; + return sync_log ? BTRFS_DONT_NEED_TRANS_COMMIT : + BTRFS_DONT_NEED_LOG_SYNC; + + if (sync_log) { + struct btrfs_log_ctx ctx2; + + btrfs_init_log_ctx(&ctx2, &inode->vfs_inode); + ret = btrfs_log_inode_parent(trans, inode, parent, 0, LLONG_MAX, + LOG_INODE_EXISTS, &ctx2); + if (ret == BTRFS_NO_LOG_SYNC) + return BTRFS_DONT_NEED_TRANS_COMMIT; + else if (ret) + return BTRFS_NEED_TRANS_COMMIT; + + ret = btrfs_sync_log(trans, inode->root, &ctx2); + if (ret) + return BTRFS_NEED_TRANS_COMMIT; + return BTRFS_DONT_NEED_TRANS_COMMIT; + } + + ASSERT(ctx); + ret = btrfs_log_inode_parent(trans, inode, parent, 0, LLONG_MAX, + LOG_INODE_EXISTS, ctx); + if (ret == BTRFS_NO_LOG_SYNC) + return BTRFS_DONT_NEED_LOG_SYNC; + else if (ret) + return BTRFS_NEED_TRANS_COMMIT; - return btrfs_log_inode_parent(trans, inode, parent, 0, LLONG_MAX, - LOG_INODE_EXISTS, NULL); + return BTRFS_NEED_LOG_SYNC; } diff --git a/fs/btrfs/tree-log.h b/fs/btrfs/tree-log.h index 122e68b89a5a..7ab9bb88a639 100644 --- a/fs/btrfs/tree-log.h +++ b/fs/btrfs/tree-log.h @@ -71,8 +71,16 @@ void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans, int for_rename); void btrfs_record_snapshot_destroy(struct btrfs_trans_handle *trans, struct btrfs_inode *dir); +/* Return values for btrfs_log_new_name() */ +enum { + BTRFS_DONT_NEED_TRANS_COMMIT, + BTRFS_NEED_TRANS_COMMIT, + BTRFS_DONT_NEED_LOG_SYNC, + BTRFS_NEED_LOG_SYNC, +}; int btrfs_log_new_name(struct btrfs_trans_handle *trans, struct btrfs_inode *inode, struct btrfs_inode *old_dir, - struct dentry *parent); + struct dentry *parent, + bool sync_log, struct btrfs_log_ctx *ctx); #endif diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index da86706123ff..f4405e430da6 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -4491,7 +4491,12 @@ again: /* Now btrfs_update_device() will change the on-disk size. */ ret = btrfs_update_device(trans, device); - btrfs_end_transaction(trans); + if (ret < 0) { + btrfs_abort_transaction(trans, ret); + btrfs_end_transaction(trans); + } else { + ret = btrfs_commit_transaction(trans); + } done: btrfs_free_path(path); if (ret) { diff --git a/fs/buffer.c b/fs/buffer.c index 4cc679d5bf58..6f1ae3ac9789 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -39,7 +39,6 @@ #include <linux/buffer_head.h> #include <linux/task_io_accounting_ops.h> #include <linux/bio.h> -#include <linux/notifier.h> #include <linux/cpu.h> #include <linux/bitops.h> #include <linux/mpage.h> diff --git a/fs/ceph/super.c b/fs/ceph/super.c index 43ca3b763875..eab1359d0553 100644 --- a/fs/ceph/super.c +++ b/fs/ceph/super.c @@ -602,6 +602,8 @@ static int extra_mon_dispatch(struct ceph_client *client, struct ceph_msg *msg) /* * create a new fs client + * + * Success or not, this function consumes @fsopt and @opt. */ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt, struct ceph_options *opt) @@ -609,17 +611,20 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt, struct ceph_fs_client *fsc; int page_count; size_t size; - int err = -ENOMEM; + int err; fsc = kzalloc(sizeof(*fsc), GFP_KERNEL); - if (!fsc) - return ERR_PTR(-ENOMEM); + if (!fsc) { + err = -ENOMEM; + goto fail; + } fsc->client = ceph_create_client(opt, fsc); if (IS_ERR(fsc->client)) { err = PTR_ERR(fsc->client); goto fail; } + opt = NULL; /* fsc->client now owns this */ fsc->client->extra_mon_dispatch = extra_mon_dispatch; fsc->client->osdc.abort_on_full = true; @@ -677,6 +682,9 @@ fail_client: ceph_destroy_client(fsc->client); fail: kfree(fsc); + if (opt) + ceph_destroy_options(opt); + destroy_mount_options(fsopt); return ERR_PTR(err); } @@ -1042,8 +1050,6 @@ static struct dentry *ceph_mount(struct file_system_type *fs_type, fsc = create_fs_client(fsopt, opt); if (IS_ERR(fsc)) { res = ERR_CAST(fsc); - destroy_mount_options(fsopt); - ceph_destroy_options(opt); goto out_final; } diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig index 35c83fe7dba0..abcd78e332fe 100644 --- a/fs/cifs/Kconfig +++ b/fs/cifs/Kconfig @@ -6,6 +6,7 @@ config CIFS select CRYPTO_MD4 select CRYPTO_MD5 select CRYPTO_SHA256 + select CRYPTO_SHA512 select CRYPTO_CMAC select CRYPTO_HMAC select CRYPTO_ARC4 diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c index b380e0871372..a2b2355e7f01 100644 --- a/fs/cifs/cifs_unicode.c +++ b/fs/cifs/cifs_unicode.c @@ -105,9 +105,6 @@ convert_sfm_char(const __u16 src_char, char *target) case SFM_LESSTHAN: *target = '<'; break; - case SFM_SLASH: - *target = '\\'; - break; case SFM_SPACE: *target = ' '; break; diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index dc2f4cf08fe9..5657b79dbc99 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -601,10 +601,15 @@ CIFSSMBNegotiate(const unsigned int xid, struct cifs_ses *ses) } count = 0; + /* + * We know that all the name entries in the protocols array + * are short (< 16 bytes anyway) and are NUL terminated. + */ for (i = 0; i < CIFS_NUM_PROT; i++) { - strncpy(pSMB->DialectsArray+count, protocols[i].name, 16); - count += strlen(protocols[i].name) + 1; - /* null at end of source and target buffers anyway */ + size_t len = strlen(protocols[i].name) + 1; + + memcpy(pSMB->DialectsArray+count, protocols[i].name, len); + count += len; } inc_rfc1001_len(pSMB, count); pSMB->ByteCount = cpu_to_le16(count); diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index c832a8a1970a..7aa08dba4719 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -2547,7 +2547,7 @@ cifs_setup_ipc(struct cifs_ses *ses, struct smb_vol *volume_info) if (tcon == NULL) return -ENOMEM; - snprintf(unc, sizeof(unc), "\\\\%s\\IPC$", ses->serverName); + snprintf(unc, sizeof(unc), "\\\\%s\\IPC$", ses->server->hostname); /* cannot fail */ nls_codepage = load_nls_default(); diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index d32eaa4b2437..6e8765f44508 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -467,6 +467,8 @@ cifs_sfu_type(struct cifs_fattr *fattr, const char *path, oparms.cifs_sb = cifs_sb; oparms.desired_access = GENERIC_READ; oparms.create_options = CREATE_NOT_DIR; + if (backup_cred(cifs_sb)) + oparms.create_options |= CREATE_OPEN_BACKUP_INTENT; oparms.disposition = FILE_OPEN; oparms.path = path; oparms.fid = &fid; diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index dacb2c05674c..6926685e513c 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -402,9 +402,17 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) (struct smb_com_transaction_change_notify_rsp *)buf; struct file_notify_information *pnotify; __u32 data_offset = 0; + size_t len = srv->total_read - sizeof(pSMBr->hdr.smb_buf_length); + if (get_bcc(buf) > sizeof(struct file_notify_information)) { data_offset = le32_to_cpu(pSMBr->DataOffset); + if (data_offset > + len - sizeof(struct file_notify_information)) { + cifs_dbg(FYI, "invalid data_offset %u\n", + data_offset); + return true; + } pnotify = (struct file_notify_information *) ((char *)&pSMBr->hdr.Protocol + data_offset); cifs_dbg(FYI, "dnotify on %s Action: 0x%x\n", diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index eeab81c9452f..e169e1a5fd35 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -376,8 +376,15 @@ static char *nxt_dir_entry(char *old_entry, char *end_of_smb, int level) new_entry = old_entry + sizeof(FIND_FILE_STANDARD_INFO) + pfData->FileNameLength; - } else - new_entry = old_entry + le32_to_cpu(pDirInfo->NextEntryOffset); + } else { + u32 next_offset = le32_to_cpu(pDirInfo->NextEntryOffset); + + if (old_entry + next_offset < old_entry) { + cifs_dbg(VFS, "invalid offset %u\n", next_offset); + return NULL; + } + new_entry = old_entry + next_offset; + } cifs_dbg(FYI, "new entry %p old entry %p\n", new_entry, old_entry); /* validate that new_entry is not past end of SMB */ if (new_entry >= end_of_smb) { diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index db0453660ff6..6a9c47541c53 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -248,16 +248,20 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *srvr) * MacOS server pads after SMB2.1 write response with 3 bytes * of junk. Other servers match RFC1001 len to actual * SMB2/SMB3 frame length (header + smb2 response specific data) - * Some windows servers do too when compounding is used. - * Log the server error (once), but allow it and continue + * Some windows servers also pad up to 8 bytes when compounding. + * If pad is longer than eight bytes, log the server behavior + * (once), since may indicate a problem but allow it and continue * since the frame is parseable. */ if (clc_len < len) { - printk_once(KERN_WARNING - "SMB2 server sent bad RFC1001 len %d not %d\n", - len, clc_len); + pr_warn_once( + "srv rsp padded more than expected. Length %d not %d for cmd:%d mid:%llu\n", + len, clc_len, command, mid); return 0; } + pr_warn_once( + "srv rsp too short, len %d not %d. cmd:%d mid:%llu\n", + len, clc_len, command, mid); return 1; } diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 247a98e6c856..d954ce36b473 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -630,7 +630,10 @@ smb2_is_path_accessible(const unsigned int xid, struct cifs_tcon *tcon, oparms.tcon = tcon; oparms.desired_access = FILE_READ_ATTRIBUTES; oparms.disposition = FILE_OPEN; - oparms.create_options = 0; + if (backup_cred(cifs_sb)) + oparms.create_options = CREATE_OPEN_BACKUP_INTENT; + else + oparms.create_options = 0; oparms.fid = &fid; oparms.reconnect = false; @@ -779,7 +782,10 @@ smb2_query_eas(const unsigned int xid, struct cifs_tcon *tcon, oparms.tcon = tcon; oparms.desired_access = FILE_READ_EA; oparms.disposition = FILE_OPEN; - oparms.create_options = 0; + if (backup_cred(cifs_sb)) + oparms.create_options = CREATE_OPEN_BACKUP_INTENT; + else + oparms.create_options = 0; oparms.fid = &fid; oparms.reconnect = false; @@ -858,7 +864,10 @@ smb2_set_ea(const unsigned int xid, struct cifs_tcon *tcon, oparms.tcon = tcon; oparms.desired_access = FILE_WRITE_EA; oparms.disposition = FILE_OPEN; - oparms.create_options = 0; + if (backup_cred(cifs_sb)) + oparms.create_options = CREATE_OPEN_BACKUP_INTENT; + else + oparms.create_options = 0; oparms.fid = &fid; oparms.reconnect = false; @@ -1453,7 +1462,10 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon, oparms.tcon = tcon; oparms.desired_access = FILE_READ_ATTRIBUTES | FILE_READ_DATA; oparms.disposition = FILE_OPEN; - oparms.create_options = 0; + if (backup_cred(cifs_sb)) + oparms.create_options = CREATE_OPEN_BACKUP_INTENT; + else + oparms.create_options = 0; oparms.fid = fid; oparms.reconnect = false; @@ -1857,7 +1869,10 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon, oparms.tcon = tcon; oparms.desired_access = FILE_READ_ATTRIBUTES; oparms.disposition = FILE_OPEN; - oparms.create_options = 0; + if (backup_cred(cifs_sb)) + oparms.create_options = CREATE_OPEN_BACKUP_INTENT; + else + oparms.create_options = 0; oparms.fid = &fid; oparms.reconnect = false; @@ -3639,7 +3654,7 @@ struct smb_version_values smb21_values = { struct smb_version_values smb3any_values = { .version_string = SMB3ANY_VERSION_STRING, .protocol_id = SMB302_PROT_ID, /* doesn't matter, send protocol array */ - .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION, + .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION | SMB2_GLOBAL_CAP_DIRECTORY_LEASING, .large_lock_type = 0, .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK, .shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK, @@ -3660,7 +3675,7 @@ struct smb_version_values smb3any_values = { struct smb_version_values smbdefault_values = { .version_string = SMBDEFAULT_VERSION_STRING, .protocol_id = SMB302_PROT_ID, /* doesn't matter, send protocol array */ - .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION, + .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION | SMB2_GLOBAL_CAP_DIRECTORY_LEASING, .large_lock_type = 0, .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK, .shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK, @@ -3681,7 +3696,7 @@ struct smb_version_values smbdefault_values = { struct smb_version_values smb30_values = { .version_string = SMB30_VERSION_STRING, .protocol_id = SMB30_PROT_ID, - .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION, + .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION | SMB2_GLOBAL_CAP_DIRECTORY_LEASING, .large_lock_type = 0, .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK, .shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK, @@ -3702,7 +3717,7 @@ struct smb_version_values smb30_values = { struct smb_version_values smb302_values = { .version_string = SMB302_VERSION_STRING, .protocol_id = SMB302_PROT_ID, - .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION, + .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION | SMB2_GLOBAL_CAP_DIRECTORY_LEASING, .large_lock_type = 0, .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK, .shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK, @@ -3723,7 +3738,7 @@ struct smb_version_values smb302_values = { struct smb_version_values smb311_values = { .version_string = SMB311_VERSION_STRING, .protocol_id = SMB311_PROT_ID, - .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION, + .req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION | SMB2_GLOBAL_CAP_DIRECTORY_LEASING, .large_lock_type = 0, .exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK, .shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK, diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 5740aa809be6..f54d07bda067 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -2178,6 +2178,9 @@ SMB2_open_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, __u8 *oplock, if (!(server->capabilities & SMB2_GLOBAL_CAP_LEASING) || *oplock == SMB2_OPLOCK_LEVEL_NONE) req->RequestedOplockLevel = *oplock; + else if (!(server->capabilities & SMB2_GLOBAL_CAP_DIRECTORY_LEASING) && + (oparms->create_options & CREATE_NOT_FILE)) + req->RequestedOplockLevel = *oplock; /* no srv lease support */ else { rc = add_lease_context(server, iov, &n_iov, oparms->fid->lease_key, oplock); @@ -2456,14 +2459,14 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid, /* We check for obvious errors in the output buffer length and offset */ if (*plen == 0) goto ioctl_exit; /* server returned no data */ - else if (*plen > 0xFF00) { + else if (*plen > rsp_iov.iov_len || *plen > 0xFF00) { cifs_dbg(VFS, "srv returned invalid ioctl length: %d\n", *plen); *plen = 0; rc = -EIO; goto ioctl_exit; } - if (rsp_iov.iov_len < le32_to_cpu(rsp->OutputOffset) + *plen) { + if (rsp_iov.iov_len - *plen < le32_to_cpu(rsp->OutputOffset)) { cifs_dbg(VFS, "Malformed ioctl resp: len %d offset %d\n", *plen, le32_to_cpu(rsp->OutputOffset)); *plen = 0; @@ -3574,33 +3577,38 @@ num_entries(char *bufstart, char *end_of_buf, char **lastentry, size_t size) int len; unsigned int entrycount = 0; unsigned int next_offset = 0; - FILE_DIRECTORY_INFO *entryptr; + char *entryptr; + FILE_DIRECTORY_INFO *dir_info; if (bufstart == NULL) return 0; - entryptr = (FILE_DIRECTORY_INFO *)bufstart; + entryptr = bufstart; while (1) { - entryptr = (FILE_DIRECTORY_INFO *) - ((char *)entryptr + next_offset); - - if ((char *)entryptr + size > end_of_buf) { + if (entryptr + next_offset < entryptr || + entryptr + next_offset > end_of_buf || + entryptr + next_offset + size > end_of_buf) { cifs_dbg(VFS, "malformed search entry would overflow\n"); break; } - len = le32_to_cpu(entryptr->FileNameLength); - if ((char *)entryptr + len + size > end_of_buf) { + entryptr = entryptr + next_offset; + dir_info = (FILE_DIRECTORY_INFO *)entryptr; + + len = le32_to_cpu(dir_info->FileNameLength); + if (entryptr + len < entryptr || + entryptr + len > end_of_buf || + entryptr + len + size > end_of_buf) { cifs_dbg(VFS, "directory entry name would overflow frame end of buf %p\n", end_of_buf); break; } - *lastentry = (char *)entryptr; + *lastentry = entryptr; entrycount++; - next_offset = le32_to_cpu(entryptr->NextEntryOffset); + next_offset = le32_to_cpu(dir_info->NextEntryOffset); if (!next_offset) break; } diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index e2902d394f1b..f93f9881ec18 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -76,7 +76,7 @@ int __ext4_check_dir_entry(const char *function, unsigned int line, else if (unlikely(rlen < EXT4_DIR_REC_LEN(de->name_len))) error_msg = "rec_len is too small for name_len"; else if (unlikely(((char *) de - buf) + rlen > size)) - error_msg = "directory entry across range"; + error_msg = "directory entry overrun"; else if (unlikely(le32_to_cpu(de->inode) > le32_to_cpu(EXT4_SB(dir->i_sb)->s_es->s_inodes_count))) error_msg = "inode out of bounds"; @@ -85,18 +85,16 @@ int __ext4_check_dir_entry(const char *function, unsigned int line, if (filp) ext4_error_file(filp, function, line, bh->b_blocknr, - "bad entry in directory: %s - offset=%u(%u), " - "inode=%u, rec_len=%d, name_len=%d", - error_msg, (unsigned) (offset % size), - offset, le32_to_cpu(de->inode), - rlen, de->name_len); + "bad entry in directory: %s - offset=%u, " + "inode=%u, rec_len=%d, name_len=%d, size=%d", + error_msg, offset, le32_to_cpu(de->inode), + rlen, de->name_len, size); else ext4_error_inode(dir, function, line, bh->b_blocknr, - "bad entry in directory: %s - offset=%u(%u), " - "inode=%u, rec_len=%d, name_len=%d", - error_msg, (unsigned) (offset % size), - offset, le32_to_cpu(de->inode), - rlen, de->name_len); + "bad entry in directory: %s - offset=%u, " + "inode=%u, rec_len=%d, name_len=%d, size=%d", + error_msg, offset, le32_to_cpu(de->inode), + rlen, de->name_len, size); return 1; } diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 0f0edd1cd0cd..caff935fbeb8 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -43,6 +43,17 @@ #define __FS_HAS_ENCRYPTION IS_ENABLED(CONFIG_EXT4_FS_ENCRYPTION) #include <linux/fscrypt.h> +#include <linux/compiler.h> + +/* Until this gets included into linux/compiler-gcc.h */ +#ifndef __nonstring +#if defined(GCC_VERSION) && (GCC_VERSION >= 80000) +#define __nonstring __attribute__((nonstring)) +#else +#define __nonstring +#endif +#endif + /* * The fourth extended filesystem constants/structures */ @@ -675,6 +686,9 @@ enum { /* Max physical block we can address w/o extents */ #define EXT4_MAX_BLOCK_FILE_PHYS 0xFFFFFFFF +/* Max logical block we can support */ +#define EXT4_MAX_LOGICAL_BLOCK 0xFFFFFFFF + /* * Structure of an inode on the disk */ @@ -1226,7 +1240,7 @@ struct ext4_super_block { __le32 s_feature_ro_compat; /* readonly-compatible feature set */ /*68*/ __u8 s_uuid[16]; /* 128-bit uuid for volume */ /*78*/ char s_volume_name[16]; /* volume name */ -/*88*/ char s_last_mounted[64]; /* directory where last mounted */ +/*88*/ char s_last_mounted[64] __nonstring; /* directory where last mounted */ /*C8*/ __le32 s_algorithm_usage_bitmap; /* For compression */ /* * Performance hints. Directory preallocation should only @@ -1277,13 +1291,13 @@ struct ext4_super_block { __le32 s_first_error_time; /* first time an error happened */ __le32 s_first_error_ino; /* inode involved in first error */ __le64 s_first_error_block; /* block involved of first error */ - __u8 s_first_error_func[32]; /* function where the error happened */ + __u8 s_first_error_func[32] __nonstring; /* function where the error happened */ __le32 s_first_error_line; /* line number where error happened */ __le32 s_last_error_time; /* most recent time of an error */ __le32 s_last_error_ino; /* inode involved in last error */ __le32 s_last_error_line; /* line number where error happened */ __le64 s_last_error_block; /* block involved of last error */ - __u8 s_last_error_func[32]; /* function where the error happened */ + __u8 s_last_error_func[32] __nonstring; /* function where the error happened */ #define EXT4_S_ERR_END offsetof(struct ext4_super_block, s_mount_opts) __u8 s_mount_opts[64]; __le32 s_usr_quota_inum; /* inode for tracking user quota */ diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 3543fe80a3c4..7b4736022761 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -1753,6 +1753,7 @@ bool empty_inline_dir(struct inode *dir, int *has_inline_data) { int err, inline_size; struct ext4_iloc iloc; + size_t inline_len; void *inline_pos; unsigned int offset; struct ext4_dir_entry_2 *de; @@ -1780,8 +1781,9 @@ bool empty_inline_dir(struct inode *dir, int *has_inline_data) goto out; } + inline_len = ext4_get_inline_size(dir); offset = EXT4_INLINE_DOTDOT_SIZE; - while (offset < dir->i_size) { + while (offset < inline_len) { de = ext4_get_inline_entry(dir, &iloc, offset, &inline_pos, &inline_size); if (ext4_check_dir_entry(dir, NULL, de, diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index d0dd585add6a..d767e993591d 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3413,12 +3413,16 @@ static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length, { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); unsigned int blkbits = inode->i_blkbits; - unsigned long first_block = offset >> blkbits; - unsigned long last_block = (offset + length - 1) >> blkbits; + unsigned long first_block, last_block; struct ext4_map_blocks map; bool delalloc = false; int ret; + if ((offset >> blkbits) > EXT4_MAX_LOGICAL_BLOCK) + return -EINVAL; + first_block = offset >> blkbits; + last_block = min_t(loff_t, (offset + length - 1) >> blkbits, + EXT4_MAX_LOGICAL_BLOCK); if (flags & IOMAP_REPORT) { if (ext4_has_inline_data(inode)) { @@ -3948,6 +3952,7 @@ static const struct address_space_operations ext4_dax_aops = { .writepages = ext4_dax_writepages, .direct_IO = noop_direct_IO, .set_page_dirty = noop_set_page_dirty, + .bmap = ext4_bmap, .invalidatepage = noop_invalidatepage, }; @@ -4192,9 +4197,8 @@ int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset, return 0; } -static void ext4_wait_dax_page(struct ext4_inode_info *ei, bool *did_unlock) +static void ext4_wait_dax_page(struct ext4_inode_info *ei) { - *did_unlock = true; up_write(&ei->i_mmap_sem); schedule(); down_write(&ei->i_mmap_sem); @@ -4204,14 +4208,12 @@ int ext4_break_layouts(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct page *page; - bool retry; int error; if (WARN_ON_ONCE(!rwsem_is_locked(&ei->i_mmap_sem))) return -EINVAL; do { - retry = false; page = dax_layout_busy_page(inode->i_mapping); if (!page) return 0; @@ -4219,8 +4221,8 @@ int ext4_break_layouts(struct inode *inode) error = ___wait_var_event(&page->_refcount, atomic_read(&page->_refcount) == 1, TASK_INTERRUPTIBLE, 0, 0, - ext4_wait_dax_page(ei, &retry)); - } while (error == 0 && retry); + ext4_wait_dax_page(ei)); + } while (error == 0); return error; } @@ -4895,6 +4897,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) * not initialized on a new filesystem. */ } ei->i_flags = le32_to_cpu(raw_inode->i_flags); + ext4_set_inode_flags(inode); inode->i_blocks = ext4_inode_blocks(raw_inode, ei); ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl_lo); if (ext4_has_feature_64bit(sb)) @@ -5041,7 +5044,6 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino) goto bad_inode; } brelse(iloc.bh); - ext4_set_inode_flags(inode); unlock_new_inode(inode); return inode; diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c index 39b07c2d3384..2305b4374fd3 100644 --- a/fs/ext4/mmp.c +++ b/fs/ext4/mmp.c @@ -49,7 +49,6 @@ static int write_mmp_block(struct super_block *sb, struct buffer_head *bh) */ sb_start_write(sb); ext4_mmp_csum_set(sb, mmp); - mark_buffer_dirty(bh); lock_buffer(bh); bh->b_end_io = end_buffer_write_sync; get_bh(bh); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 116ff68c5bd4..377d516c475f 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -3478,6 +3478,12 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry, int credits; u8 old_file_type; + if (new.inode && new.inode->i_nlink == 0) { + EXT4_ERROR_INODE(new.inode, + "target of rename is already freed"); + return -EFSCORRUPTED; + } + if ((ext4_test_inode_flag(new_dir, EXT4_INODE_PROJINHERIT)) && (!projid_eq(EXT4_I(new_dir)->i_projid, EXT4_I(old_dentry->d_inode)->i_projid))) diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index e5fb38451a73..ebbc663d0798 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -19,6 +19,7 @@ int ext4_resize_begin(struct super_block *sb) { + struct ext4_sb_info *sbi = EXT4_SB(sb); int ret = 0; if (!capable(CAP_SYS_RESOURCE)) @@ -29,7 +30,7 @@ int ext4_resize_begin(struct super_block *sb) * because the user tools have no way of handling this. Probably a * bad time to do it anyways. */ - if (EXT4_SB(sb)->s_sbh->b_blocknr != + if (EXT4_B2C(sbi, sbi->s_sbh->b_blocknr) != le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) { ext4_warning(sb, "won't resize using backup superblock at %llu", (unsigned long long)EXT4_SB(sb)->s_sbh->b_blocknr); @@ -1986,6 +1987,26 @@ retry: } } + /* + * Make sure the last group has enough space so that it's + * guaranteed to have enough space for all metadata blocks + * that it might need to hold. (We might not need to store + * the inode table blocks in the last block group, but there + * will be cases where this might be needed.) + */ + if ((ext4_group_first_block_no(sb, n_group) + + ext4_group_overhead_blocks(sb, n_group) + 2 + + sbi->s_itb_per_group + sbi->s_cluster_ratio) >= n_blocks_count) { + n_blocks_count = ext4_group_first_block_no(sb, n_group); + n_group--; + n_blocks_count_retry = 0; + if (resize_inode) { + iput(resize_inode); + resize_inode = NULL; + } + goto retry; + } + /* extend the last group */ if (n_group == o_group) add = n_blocks_count - o_blocks_count; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 5863fd22e90b..1145109968ef 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2145,6 +2145,8 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, SEQ_OPTS_PRINT("max_dir_size_kb=%u", sbi->s_max_dir_size_kb); if (test_opt(sb, DATA_ERR_ABORT)) SEQ_OPTS_PUTS("data_err=abort"); + if (DUMMY_ENCRYPTION_ENABLED(sbi)) + SEQ_OPTS_PUTS("test_dummy_encryption"); ext4_show_quota_options(seq, sb); return 0; @@ -4378,11 +4380,13 @@ no_journal: block = ext4_count_free_clusters(sb); ext4_free_blocks_count_set(sbi->s_es, EXT4_C2B(sbi, block)); + ext4_superblock_csum_set(sb); err = percpu_counter_init(&sbi->s_freeclusters_counter, block, GFP_KERNEL); if (!err) { unsigned long freei = ext4_count_free_inodes(sb); sbi->s_es->s_free_inodes_count = cpu_to_le32(freei); + ext4_superblock_csum_set(sb); err = percpu_counter_init(&sbi->s_freeinodes_counter, freei, GFP_KERNEL); } diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index ec3fba7d492f..488a9e7f8f66 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -24,6 +24,7 @@ #include <linux/mpage.h> #include <linux/user_namespace.h> #include <linux/seq_file.h> +#include <linux/blkdev.h> #include "isofs.h" #include "zisofs.h" @@ -653,6 +654,12 @@ static int isofs_fill_super(struct super_block *s, void *data, int silent) /* * What if bugger tells us to go beyond page size? */ + if (bdev_logical_block_size(s->s_bdev) > 2048) { + printk(KERN_WARNING + "ISOFS: unsupported/invalid hardware sector size %d\n", + bdev_logical_block_size(s->s_bdev)); + goto out_freesbi; + } opt.blocksize = sb_min_blocksize(s, opt.blocksize); sbi->s_high_sierra = 0; /* default is iso9660 */ diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 34830f6457ea..8220a168282e 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1637,6 +1637,14 @@ static void nfs_state_set_delegation(struct nfs4_state *state, write_sequnlock(&state->seqlock); } +static void nfs_state_clear_delegation(struct nfs4_state *state) +{ + write_seqlock(&state->seqlock); + nfs4_stateid_copy(&state->stateid, &state->open_stateid); + clear_bit(NFS_DELEGATED_STATE, &state->flags); + write_sequnlock(&state->seqlock); +} + static int update_open_stateid(struct nfs4_state *state, const nfs4_stateid *open_stateid, const nfs4_stateid *delegation, @@ -2145,10 +2153,7 @@ int nfs4_open_delegation_recall(struct nfs_open_context *ctx, if (IS_ERR(opendata)) return PTR_ERR(opendata); nfs4_stateid_copy(&opendata->o_arg.u.delegation, stateid); - write_seqlock(&state->seqlock); - nfs4_stateid_copy(&state->stateid, &state->open_stateid); - write_sequnlock(&state->seqlock); - clear_bit(NFS_DELEGATED_STATE, &state->flags); + nfs_state_clear_delegation(state); switch (type & (FMODE_READ|FMODE_WRITE)) { case FMODE_READ|FMODE_WRITE: case FMODE_WRITE: @@ -2601,10 +2606,7 @@ static void nfs_finish_clear_delegation_stateid(struct nfs4_state *state, const nfs4_stateid *stateid) { nfs_remove_bad_delegation(state->inode, stateid); - write_seqlock(&state->seqlock); - nfs4_stateid_copy(&state->stateid, &state->open_stateid); - write_sequnlock(&state->seqlock); - clear_bit(NFS_DELEGATED_STATE, &state->flags); + nfs_state_clear_delegation(state); } static void nfs40_clear_delegation_stateid(struct nfs4_state *state) @@ -2672,15 +2674,20 @@ static void nfs41_check_delegation_stateid(struct nfs4_state *state) delegation = rcu_dereference(NFS_I(state->inode)->delegation); if (delegation == NULL) { rcu_read_unlock(); + nfs_state_clear_delegation(state); return; } nfs4_stateid_copy(&stateid, &delegation->stateid); - if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags) || - !test_and_clear_bit(NFS_DELEGATION_TEST_EXPIRED, - &delegation->flags)) { + if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) { + rcu_read_unlock(); + nfs_state_clear_delegation(state); + return; + } + + if (!test_and_clear_bit(NFS_DELEGATION_TEST_EXPIRED, + &delegation->flags)) { rcu_read_unlock(); - nfs_finish_clear_delegation_stateid(state, &stateid); return; } diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 3df0eb52da1c..40a08cd483f0 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1390,6 +1390,8 @@ int nfs4_schedule_stateid_recovery(const struct nfs_server *server, struct nfs4_ if (!nfs4_state_mark_reclaim_nograce(clp, state)) return -EBADF; + nfs_inode_find_delegation_state_and_recover(state->inode, + &state->stateid); dprintk("%s: scheduling stateid recovery for server %s\n", __func__, clp->cl_hostname); nfs4_schedule_state_manager(clp); diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h index a275fba93170..b1483b303e0b 100644 --- a/fs/nfs/nfs4trace.h +++ b/fs/nfs/nfs4trace.h @@ -1137,7 +1137,7 @@ DECLARE_EVENT_CLASS(nfs4_inode_callback_event, TP_fast_assign( __entry->error = error; __entry->fhandle = nfs_fhandle_hash(fhandle); - if (inode != NULL) { + if (!IS_ERR_OR_NULL(inode)) { __entry->fileid = NFS_FILEID(inode); __entry->dev = inode->i_sb->s_dev; } else { @@ -1194,7 +1194,7 @@ DECLARE_EVENT_CLASS(nfs4_inode_stateid_callback_event, TP_fast_assign( __entry->error = error; __entry->fhandle = nfs_fhandle_hash(fhandle); - if (inode != NULL) { + if (!IS_ERR_OR_NULL(inode)) { __entry->fileid = NFS_FILEID(inode); __entry->dev = inode->i_sb->s_dev; } else { diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index e8f232de484f..7d9a51e6b847 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1740,16 +1740,16 @@ static bool pnfs_within_mdsthreshold(struct nfs_open_context *ctx, return ret; } -static bool pnfs_prepare_to_retry_layoutget(struct pnfs_layout_hdr *lo) +static int pnfs_prepare_to_retry_layoutget(struct pnfs_layout_hdr *lo) { /* * send layoutcommit as it can hold up layoutreturn due to lseg * reference */ pnfs_layoutcommit_inode(lo->plh_inode, false); - return !wait_on_bit_action(&lo->plh_flags, NFS_LAYOUT_RETURN, + return wait_on_bit_action(&lo->plh_flags, NFS_LAYOUT_RETURN, nfs_wait_bit_killable, - TASK_UNINTERRUPTIBLE); + TASK_KILLABLE); } static void nfs_layoutget_begin(struct pnfs_layout_hdr *lo) @@ -1830,7 +1830,9 @@ pnfs_update_layout(struct inode *ino, } lookup_again: - nfs4_client_recover_expired_lease(clp); + lseg = ERR_PTR(nfs4_client_recover_expired_lease(clp)); + if (IS_ERR(lseg)) + goto out; first = false; spin_lock(&ino->i_lock); lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags); @@ -1863,9 +1865,9 @@ lookup_again: if (list_empty(&lo->plh_segs) && atomic_read(&lo->plh_outstanding) != 0) { spin_unlock(&ino->i_lock); - if (wait_var_event_killable(&lo->plh_outstanding, - atomic_read(&lo->plh_outstanding) == 0 - || !list_empty(&lo->plh_segs))) + lseg = ERR_PTR(wait_var_event_killable(&lo->plh_outstanding, + atomic_read(&lo->plh_outstanding))); + if (IS_ERR(lseg) || !list_empty(&lo->plh_segs)) goto out_put_layout_hdr; pnfs_put_layout_hdr(lo); goto lookup_again; @@ -1898,8 +1900,11 @@ lookup_again: if (test_and_set_bit(NFS_LAYOUT_FIRST_LAYOUTGET, &lo->plh_flags)) { spin_unlock(&ino->i_lock); - wait_on_bit(&lo->plh_flags, NFS_LAYOUT_FIRST_LAYOUTGET, - TASK_UNINTERRUPTIBLE); + lseg = ERR_PTR(wait_on_bit(&lo->plh_flags, + NFS_LAYOUT_FIRST_LAYOUTGET, + TASK_KILLABLE)); + if (IS_ERR(lseg)) + goto out_put_layout_hdr; pnfs_put_layout_hdr(lo); dprintk("%s retrying\n", __func__); goto lookup_again; @@ -1925,7 +1930,8 @@ lookup_again: if (test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) { spin_unlock(&ino->i_lock); dprintk("%s wait for layoutreturn\n", __func__); - if (pnfs_prepare_to_retry_layoutget(lo)) { + lseg = ERR_PTR(pnfs_prepare_to_retry_layoutget(lo)); + if (!IS_ERR(lseg)) { if (first) pnfs_clear_first_layoutget(lo); pnfs_put_layout_hdr(lo); diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c index 03b8ba933eb2..235b959fc2b3 100644 --- a/fs/nilfs2/alloc.c +++ b/fs/nilfs2/alloc.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * alloc.c - NILFS dat/inode allocator * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Originally written by Koji Sato. * Two allocators were unified by Ryusuke Konishi and Amagai Yoshiji. */ diff --git a/fs/nilfs2/alloc.h b/fs/nilfs2/alloc.h index 05149e606a78..0303c3968cee 100644 --- a/fs/nilfs2/alloc.h +++ b/fs/nilfs2/alloc.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * alloc.h - persistent object (dat entry/disk inode) allocator/deallocator * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Originally written by Koji Sato. * Two allocators were unified by Ryusuke Konishi and Amagai Yoshiji. */ diff --git a/fs/nilfs2/bmap.c b/fs/nilfs2/bmap.c index 01fb1831ca25..fb5a9a8a13cf 100644 --- a/fs/nilfs2/bmap.c +++ b/fs/nilfs2/bmap.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * bmap.c - NILFS block mapping. * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/bmap.h b/fs/nilfs2/bmap.h index 2b6ffbe5997a..2c63858e81c9 100644 --- a/fs/nilfs2/bmap.h +++ b/fs/nilfs2/bmap.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * bmap.h - NILFS block mapping. * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c index dec98cab729d..ebb24a314f43 100644 --- a/fs/nilfs2/btnode.c +++ b/fs/nilfs2/btnode.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * btnode.c - NILFS B-tree node cache * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Originally written by Seiji Kihara. * Fully revised by Ryusuke Konishi for stabilization and simplification. * diff --git a/fs/nilfs2/btnode.h b/fs/nilfs2/btnode.h index 4e8aaa1aeb65..0f88dbc9bcb3 100644 --- a/fs/nilfs2/btnode.h +++ b/fs/nilfs2/btnode.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * btnode.h - NILFS B-tree node cache * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Seiji Kihara. * Revised by Ryusuke Konishi. */ diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index 16a7a67a11c9..23e043eca237 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * btree.c - NILFS B-tree. * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/btree.h b/fs/nilfs2/btree.h index 2184e47fa4bf..d1421b646ce4 100644 --- a/fs/nilfs2/btree.h +++ b/fs/nilfs2/btree.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * btree.h - NILFS B-tree. * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/cpfile.c b/fs/nilfs2/cpfile.c index a15a1601e931..8d41311b5db4 100644 --- a/fs/nilfs2/cpfile.c +++ b/fs/nilfs2/cpfile.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * cpfile.c - NILFS checkpoint file. * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/cpfile.h b/fs/nilfs2/cpfile.h index 6eca972f9673..6336222df24a 100644 --- a/fs/nilfs2/cpfile.h +++ b/fs/nilfs2/cpfile.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * cpfile.h - NILFS checkpoint file. * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c index dffedb2f8817..6f4066636be9 100644 --- a/fs/nilfs2/dat.c +++ b/fs/nilfs2/dat.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * dat.c - NILFS disk address translation. * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/dat.h b/fs/nilfs2/dat.h index 57dc6cf466d0..b17ee34580ae 100644 --- a/fs/nilfs2/dat.h +++ b/fs/nilfs2/dat.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * dat.h - NILFS disk address translation. * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c index 582831ab3eb9..81394e22d0a0 100644 --- a/fs/nilfs2/dir.c +++ b/fs/nilfs2/dir.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * dir.c - NILFS directory entry operations * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Modified for NILFS by Amagai Yoshiji. */ /* diff --git a/fs/nilfs2/direct.c b/fs/nilfs2/direct.c index 96e3ed0d9652..533e24ea3a88 100644 --- a/fs/nilfs2/direct.c +++ b/fs/nilfs2/direct.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * direct.c - NILFS direct block pointer. * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/direct.h b/fs/nilfs2/direct.h index cfe85e848bba..ec9a23c77994 100644 --- a/fs/nilfs2/direct.h +++ b/fs/nilfs2/direct.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * direct.h - NILFS direct block pointer. * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index 7da0fac71dc2..64bc81363c6c 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * file.c - NILFS regular file handling primitives including fsync(). * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Amagai Yoshiji and Ryusuke Konishi. */ diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c index 853a831dcde0..aa3c328ee189 100644 --- a/fs/nilfs2/gcinode.c +++ b/fs/nilfs2/gcinode.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * gcinode.c - dummy inodes to buffer blocks for garbage collection * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Seiji Kihara, Amagai Yoshiji, and Ryusuke Konishi. * Revised by Ryusuke Konishi. * diff --git a/fs/nilfs2/ifile.c b/fs/nilfs2/ifile.c index b8fa45c20c63..4140d232cadc 100644 --- a/fs/nilfs2/ifile.c +++ b/fs/nilfs2/ifile.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * ifile.c - NILFS inode file * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Amagai Yoshiji. * Revised by Ryusuke Konishi. * diff --git a/fs/nilfs2/ifile.h b/fs/nilfs2/ifile.h index 188b94fe0ec5..a1e1e5711a05 100644 --- a/fs/nilfs2/ifile.h +++ b/fs/nilfs2/ifile.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * ifile.h - NILFS inode file * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Amagai Yoshiji. * Revised by Ryusuke Konishi. * diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c index 6a612d832e7d..671085512e0f 100644 --- a/fs/nilfs2/inode.c +++ b/fs/nilfs2/inode.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * inode.c - NILFS inode operations. * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi. * */ diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c index 1d2c3d7711fe..9b96d79eea6c 100644 --- a/fs/nilfs2/ioctl.c +++ b/fs/nilfs2/ioctl.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * ioctl.c - NILFS ioctl operations. * * Copyright (C) 2007, 2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c index c6bc1033e7d2..700870a92bc4 100644 --- a/fs/nilfs2/mdt.c +++ b/fs/nilfs2/mdt.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * mdt.c - meta data file for NILFS * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi. */ diff --git a/fs/nilfs2/mdt.h b/fs/nilfs2/mdt.h index 3f67f3932097..e77aea4bb921 100644 --- a/fs/nilfs2/mdt.h +++ b/fs/nilfs2/mdt.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * mdt.h - NILFS meta data file prototype and definitions * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi. */ diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c index dd52d3f82e8d..9fe6d4ab74f0 100644 --- a/fs/nilfs2/namei.c +++ b/fs/nilfs2/namei.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * namei.c - NILFS pathname lookup operations. * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Modified for NILFS by Amagai Yoshiji and Ryusuke Konishi. */ /* diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index 33f8c8fc96e8..a2f247b6a209 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * nilfs.h - NILFS local header file. * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato and Ryusuke Konishi. */ diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c index 4cb850a6f1c2..329a056b73b1 100644 --- a/fs/nilfs2/page.c +++ b/fs/nilfs2/page.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * page.c - buffer/page management specific to NILFS * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi and Seiji Kihara. */ diff --git a/fs/nilfs2/page.h b/fs/nilfs2/page.h index f3687c958fa8..62b9bb469e92 100644 --- a/fs/nilfs2/page.h +++ b/fs/nilfs2/page.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * page.h - buffer/page management specific to NILFS * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi and Seiji Kihara. */ diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c index 5139efed1888..140b663e91c7 100644 --- a/fs/nilfs2/recovery.c +++ b/fs/nilfs2/recovery.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * recovery.c - NILFS recovery logic * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi. */ diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c index 68cb9e4740b4..20c479b5e41b 100644 --- a/fs/nilfs2/segbuf.c +++ b/fs/nilfs2/segbuf.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * segbuf.c - NILFS segment buffer * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi. * */ diff --git a/fs/nilfs2/segbuf.h b/fs/nilfs2/segbuf.h index 10e16935fff6..9bea1bd59041 100644 --- a/fs/nilfs2/segbuf.h +++ b/fs/nilfs2/segbuf.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * segbuf.h - NILFS Segment buffer prototypes and definitions * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi. * */ diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 0953635e7d48..445eef41bfaf 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * segment.c - NILFS segment constructor. * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi. * */ diff --git a/fs/nilfs2/segment.h b/fs/nilfs2/segment.h index 04634e3e3d58..f5cf5308f3fc 100644 --- a/fs/nilfs2/segment.h +++ b/fs/nilfs2/segment.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * segment.h - NILFS Segment constructor prototypes and definitions * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi. * */ diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c index c7fa139d50e8..bf3f8f05c89b 100644 --- a/fs/nilfs2/sufile.c +++ b/fs/nilfs2/sufile.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * sufile.c - NILFS segment usage file. * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. * Revised by Ryusuke Konishi. */ diff --git a/fs/nilfs2/sufile.h b/fs/nilfs2/sufile.h index 673a891350f4..c4e2c7a7add1 100644 --- a/fs/nilfs2/sufile.h +++ b/fs/nilfs2/sufile.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * sufile.h - NILFS segment usage file. * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Koji Sato. */ diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 1b9067cf4511..26290aa1023f 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * super.c - NILFS module and super block management. * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi. */ /* diff --git a/fs/nilfs2/sysfs.c b/fs/nilfs2/sysfs.c index 4b25837e7724..e60be7bb55b0 100644 --- a/fs/nilfs2/sysfs.c +++ b/fs/nilfs2/sysfs.c @@ -1,19 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * sysfs.c - sysfs support implementation. * * Copyright (C) 2005-2014 Nippon Telegraph and Telephone Corporation. * Copyright (C) 2014 HGST, Inc., a Western Digital Company. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Vyacheslav Dubeyko <Vyacheslav.Dubeyko@hgst.com> */ diff --git a/fs/nilfs2/sysfs.h b/fs/nilfs2/sysfs.h index 648cedf9c06e..d001eb862dae 100644 --- a/fs/nilfs2/sysfs.h +++ b/fs/nilfs2/sysfs.h @@ -1,19 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * sysfs.h - sysfs support declarations. * * Copyright (C) 2005-2014 Nippon Telegraph and Telephone Corporation. * Copyright (C) 2014 HGST, Inc., a Western Digital Company. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Vyacheslav Dubeyko <Vyacheslav.Dubeyko@hgst.com> */ diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index 1a85317e83f0..484785cdf96e 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -1,18 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0+ /* * the_nilfs.c - the_nilfs shared structure. * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi. * */ diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h index 36da1779f976..380a543c5b19 100644 --- a/fs/nilfs2/the_nilfs.h +++ b/fs/nilfs2/the_nilfs.h @@ -1,18 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * the_nilfs.h - the_nilfs shared structure. * * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation. * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * * Written by Ryusuke Konishi. * */ diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index f174397b63a0..ababdbfab537 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -351,16 +351,9 @@ int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is, iter_info.srcu_idx = srcu_read_lock(&fsnotify_mark_srcu); - if ((mask & FS_MODIFY) || - (test_mask & to_tell->i_fsnotify_mask)) { - iter_info.marks[FSNOTIFY_OBJ_TYPE_INODE] = - fsnotify_first_mark(&to_tell->i_fsnotify_marks); - } - - if (mnt && ((mask & FS_MODIFY) || - (test_mask & mnt->mnt_fsnotify_mask))) { - iter_info.marks[FSNOTIFY_OBJ_TYPE_INODE] = - fsnotify_first_mark(&to_tell->i_fsnotify_marks); + iter_info.marks[FSNOTIFY_OBJ_TYPE_INODE] = + fsnotify_first_mark(&to_tell->i_fsnotify_marks); + if (mnt) { iter_info.marks[FSNOTIFY_OBJ_TYPE_VFSMOUNT] = fsnotify_first_mark(&mnt->mnt_fsnotify_marks); } diff --git a/fs/notify/mark.c b/fs/notify/mark.c index 05506d60131c..59cdb27826de 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -132,13 +132,13 @@ static void __fsnotify_recalc_mask(struct fsnotify_mark_connector *conn) struct fsnotify_mark *mark; assert_spin_locked(&conn->lock); + /* We can get detached connector here when inode is getting unlinked. */ + if (!fsnotify_valid_obj_type(conn->type)) + return; hlist_for_each_entry(mark, &conn->list, obj_list) { if (mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED) new_mask |= mark->mask; } - if (WARN_ON(!fsnotify_valid_obj_type(conn->type))) - return; - *fsnotify_conn_mask_p(conn) = new_mask; } diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index 32e9282893c9..aeaefd2a551b 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -131,9 +131,6 @@ static int ovl_open(struct inode *inode, struct file *file) if (IS_ERR(realfile)) return PTR_ERR(realfile); - /* For O_DIRECT dentry_open() checks f_mapping->a_ops->direct_IO */ - file->f_mapping = realfile->f_mapping; - file->private_data = realfile; return 0; @@ -334,6 +331,25 @@ static long ovl_fallocate(struct file *file, int mode, loff_t offset, loff_t len return ret; } +static int ovl_fadvise(struct file *file, loff_t offset, loff_t len, int advice) +{ + struct fd real; + const struct cred *old_cred; + int ret; + + ret = ovl_real_fdget(file, &real); + if (ret) + return ret; + + old_cred = ovl_override_creds(file_inode(file)->i_sb); + ret = vfs_fadvise(real.file, offset, len, advice); + revert_creds(old_cred); + + fdput(real); + + return ret; +} + static long ovl_real_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -502,6 +518,7 @@ const struct file_operations ovl_file_operations = { .fsync = ovl_fsync, .mmap = ovl_mmap, .fallocate = ovl_fallocate, + .fadvise = ovl_fadvise, .unlocked_ioctl = ovl_ioctl, .compat_ioctl = ovl_compat_ioctl, diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index e0bb217c01e2..b6ac545b5a32 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -467,6 +467,10 @@ static int ovl_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, return -EOPNOTSUPP; old_cred = ovl_override_creds(inode->i_sb); + + if (fieinfo->fi_flags & FIEMAP_FLAG_SYNC) + filemap_write_and_wait(realinode->i_mapping); + err = realinode->i_op->fiemap(realinode, fieinfo, start, len); revert_creds(old_cred); @@ -500,6 +504,11 @@ static const struct inode_operations ovl_special_inode_operations = { .update_time = ovl_update_time, }; +const struct address_space_operations ovl_aops = { + /* For O_DIRECT dentry_open() checks f_mapping->a_ops->direct_IO */ + .direct_IO = noop_direct_IO, +}; + /* * It is possible to stack overlayfs instance on top of another * overlayfs instance as lower layer. We need to annonate the @@ -571,6 +580,7 @@ static void ovl_fill_inode(struct inode *inode, umode_t mode, dev_t rdev, case S_IFREG: inode->i_op = &ovl_file_inode_operations; inode->i_fop = &ovl_file_operations; + inode->i_mapping->a_ops = &ovl_aops; break; case S_IFDIR: diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 2e0fc93c2c06..30adc9d408a0 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -982,16 +982,6 @@ static int ovl_get_upper(struct ovl_fs *ofs, struct path *upperpath) if (err) goto out; - err = -EBUSY; - if (ovl_inuse_trylock(upperpath->dentry)) { - ofs->upperdir_locked = true; - } else if (ofs->config.index) { - pr_err("overlayfs: upperdir is in-use by another mount, mount with '-o index=off' to override exclusive upperdir protection.\n"); - goto out; - } else { - pr_warn("overlayfs: upperdir is in-use by another mount, accessing files from both mounts will result in undefined behavior.\n"); - } - upper_mnt = clone_private_mount(upperpath); err = PTR_ERR(upper_mnt); if (IS_ERR(upper_mnt)) { @@ -1002,6 +992,17 @@ static int ovl_get_upper(struct ovl_fs *ofs, struct path *upperpath) /* Don't inherit atime flags */ upper_mnt->mnt_flags &= ~(MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME); ofs->upper_mnt = upper_mnt; + + err = -EBUSY; + if (ovl_inuse_trylock(ofs->upper_mnt->mnt_root)) { + ofs->upperdir_locked = true; + } else if (ofs->config.index) { + pr_err("overlayfs: upperdir is in-use by another mount, mount with '-o index=off' to override exclusive upperdir protection.\n"); + goto out; + } else { + pr_warn("overlayfs: upperdir is in-use by another mount, accessing files from both mounts will result in undefined behavior.\n"); + } + err = 0; out: return err; @@ -1101,8 +1102,10 @@ static int ovl_get_workdir(struct ovl_fs *ofs, struct path *upperpath) goto out; } + ofs->workbasedir = dget(workpath.dentry); + err = -EBUSY; - if (ovl_inuse_trylock(workpath.dentry)) { + if (ovl_inuse_trylock(ofs->workbasedir)) { ofs->workdir_locked = true; } else if (ofs->config.index) { pr_err("overlayfs: workdir is in-use by another mount, mount with '-o index=off' to override exclusive workdir protection.\n"); @@ -1111,7 +1114,6 @@ static int ovl_get_workdir(struct ovl_fs *ofs, struct path *upperpath) pr_warn("overlayfs: workdir is in-use by another mount, accessing files from both mounts will result in undefined behavior.\n"); } - ofs->workbasedir = dget(workpath.dentry); err = ovl_make_workdir(ofs, &workpath); if (err) goto out; diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c index 951a14edcf51..0792595ebcfb 100644 --- a/fs/pstore/ram_core.c +++ b/fs/pstore/ram_core.c @@ -429,7 +429,12 @@ static void *persistent_ram_vmap(phys_addr_t start, size_t size, vaddr = vmap(pages, page_count, VM_MAP, prot); kfree(pages); - return vaddr; + /* + * Since vmap() uses page granularity, we must add the offset + * into the page here, to get the byte granularity address + * into the mapping to represent the actual "start" location. + */ + return vaddr + offset_in_page(start); } static void *persistent_ram_iomap(phys_addr_t start, size_t size, @@ -448,6 +453,11 @@ static void *persistent_ram_iomap(phys_addr_t start, size_t size, else va = ioremap_wc(start, size); + /* + * Since request_mem_region() and ioremap() are byte-granularity + * there is no need handle anything special like we do when the + * vmap() case in persistent_ram_vmap() above. + */ return va; } @@ -468,7 +478,7 @@ static int persistent_ram_buffer_map(phys_addr_t start, phys_addr_t size, return -ENOMEM; } - prz->buffer = prz->vaddr + offset_in_page(start); + prz->buffer = prz->vaddr; prz->buffer_size = size - sizeof(struct persistent_ram_buffer); return 0; @@ -515,7 +525,8 @@ void persistent_ram_free(struct persistent_ram_zone *prz) if (prz->vaddr) { if (pfn_valid(prz->paddr >> PAGE_SHIFT)) { - vunmap(prz->vaddr); + /* We must vunmap() at page-granularity. */ + vunmap(prz->vaddr - offset_in_page(prz->paddr)); } else { iounmap(prz->vaddr); release_mem_region(prz->paddr, prz->size); diff --git a/fs/quota/quota.c b/fs/quota/quota.c index 860bfbe7a07a..f0cbf58ad4da 100644 --- a/fs/quota/quota.c +++ b/fs/quota/quota.c @@ -18,6 +18,7 @@ #include <linux/quotaops.h> #include <linux/types.h> #include <linux/writeback.h> +#include <linux/nospec.h> static int check_quotactl_permission(struct super_block *sb, int type, int cmd, qid_t id) @@ -120,8 +121,6 @@ static int quota_getinfo(struct super_block *sb, int type, void __user *addr) struct if_dqinfo uinfo; int ret; - /* This checks whether qc_state has enough entries... */ - BUILD_BUG_ON(MAXQUOTAS > XQM_MAXQUOTAS); if (!sb->s_qcop->get_state) return -ENOSYS; ret = sb->s_qcop->get_state(sb, &state); @@ -354,10 +353,10 @@ static int quota_getstate(struct super_block *sb, struct fs_quota_stat *fqs) * GETXSTATE quotactl has space for just one set of time limits so * report them for the first enabled quota type */ - for (type = 0; type < XQM_MAXQUOTAS; type++) + for (type = 0; type < MAXQUOTAS; type++) if (state.s_state[type].flags & QCI_ACCT_ENABLED) break; - BUG_ON(type == XQM_MAXQUOTAS); + BUG_ON(type == MAXQUOTAS); fqs->qs_btimelimit = state.s_state[type].spc_timelimit; fqs->qs_itimelimit = state.s_state[type].ino_timelimit; fqs->qs_rtbtimelimit = state.s_state[type].rt_spc_timelimit; @@ -427,10 +426,10 @@ static int quota_getstatev(struct super_block *sb, struct fs_quota_statv *fqs) * GETXSTATV quotactl has space for just one set of time limits so * report them for the first enabled quota type */ - for (type = 0; type < XQM_MAXQUOTAS; type++) + for (type = 0; type < MAXQUOTAS; type++) if (state.s_state[type].flags & QCI_ACCT_ENABLED) break; - BUG_ON(type == XQM_MAXQUOTAS); + BUG_ON(type == MAXQUOTAS); fqs->qs_btimelimit = state.s_state[type].spc_timelimit; fqs->qs_itimelimit = state.s_state[type].ino_timelimit; fqs->qs_rtbtimelimit = state.s_state[type].rt_spc_timelimit; @@ -701,8 +700,9 @@ static int do_quotactl(struct super_block *sb, int type, int cmd, qid_t id, { int ret; - if (type >= (XQM_COMMAND(cmd) ? XQM_MAXQUOTAS : MAXQUOTAS)) + if (type >= MAXQUOTAS) return -EINVAL; + type = array_index_nospec(type, MAXQUOTAS); /* * Quota not supported on this fs? Check this before s_quota_types * since they needn't be set if quota is not supported at all. diff --git a/fs/udf/super.c b/fs/udf/super.c index 3040dc2a32f6..6f515651a2c2 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -764,9 +764,7 @@ static int udf_find_fileset(struct super_block *sb, struct kernel_lb_addr *root) { struct buffer_head *bh = NULL; - long lastblock; uint16_t ident; - struct udf_sb_info *sbi; if (fileset->logicalBlockNum != 0xFFFFFFFF || fileset->partitionReferenceNum != 0xFFFF) { @@ -779,69 +777,11 @@ static int udf_find_fileset(struct super_block *sb, return 1; } - } - - sbi = UDF_SB(sb); - if (!bh) { - /* Search backwards through the partitions */ - struct kernel_lb_addr newfileset; - -/* --> cvg: FIXME - is it reasonable? */ - return 1; - - for (newfileset.partitionReferenceNum = sbi->s_partitions - 1; - (newfileset.partitionReferenceNum != 0xFFFF && - fileset->logicalBlockNum == 0xFFFFFFFF && - fileset->partitionReferenceNum == 0xFFFF); - newfileset.partitionReferenceNum--) { - lastblock = sbi->s_partmaps - [newfileset.partitionReferenceNum] - .s_partition_len; - newfileset.logicalBlockNum = 0; - - do { - bh = udf_read_ptagged(sb, &newfileset, 0, - &ident); - if (!bh) { - newfileset.logicalBlockNum++; - continue; - } - - switch (ident) { - case TAG_IDENT_SBD: - { - struct spaceBitmapDesc *sp; - sp = (struct spaceBitmapDesc *) - bh->b_data; - newfileset.logicalBlockNum += 1 + - ((le32_to_cpu(sp->numOfBytes) + - sizeof(struct spaceBitmapDesc) - - 1) >> sb->s_blocksize_bits); - brelse(bh); - break; - } - case TAG_IDENT_FSD: - *fileset = newfileset; - break; - default: - newfileset.logicalBlockNum++; - brelse(bh); - bh = NULL; - break; - } - } while (newfileset.logicalBlockNum < lastblock && - fileset->logicalBlockNum == 0xFFFFFFFF && - fileset->partitionReferenceNum == 0xFFFF); - } - } - - if ((fileset->logicalBlockNum != 0xFFFFFFFF || - fileset->partitionReferenceNum != 0xFFFF) && bh) { udf_debug("Fileset at block=%u, partition=%u\n", fileset->logicalBlockNum, fileset->partitionReferenceNum); - sbi->s_partition = fileset->partitionReferenceNum; + UDF_SB(sb)->s_partition = fileset->partitionReferenceNum; udf_load_fileset(sb, bh, root); brelse(bh); return 0; @@ -1570,10 +1510,16 @@ static void udf_load_logicalvolint(struct super_block *sb, struct kernel_extent_ */ #define PART_DESC_ALLOC_STEP 32 +struct part_desc_seq_scan_data { + struct udf_vds_record rec; + u32 partnum; +}; + struct desc_seq_scan_data { struct udf_vds_record vds[VDS_POS_LENGTH]; unsigned int size_part_descs; - struct udf_vds_record *part_descs_loc; + unsigned int num_part_descs; + struct part_desc_seq_scan_data *part_descs_loc; }; static struct udf_vds_record *handle_partition_descriptor( @@ -1582,10 +1528,14 @@ static struct udf_vds_record *handle_partition_descriptor( { struct partitionDesc *desc = (struct partitionDesc *)bh->b_data; int partnum; + int i; partnum = le16_to_cpu(desc->partitionNumber); - if (partnum >= data->size_part_descs) { - struct udf_vds_record *new_loc; + for (i = 0; i < data->num_part_descs; i++) + if (partnum == data->part_descs_loc[i].partnum) + return &(data->part_descs_loc[i].rec); + if (data->num_part_descs >= data->size_part_descs) { + struct part_desc_seq_scan_data *new_loc; unsigned int new_size = ALIGN(partnum, PART_DESC_ALLOC_STEP); new_loc = kcalloc(new_size, sizeof(*new_loc), GFP_KERNEL); @@ -1597,7 +1547,7 @@ static struct udf_vds_record *handle_partition_descriptor( data->part_descs_loc = new_loc; data->size_part_descs = new_size; } - return &(data->part_descs_loc[partnum]); + return &(data->part_descs_loc[data->num_part_descs++].rec); } @@ -1647,6 +1597,7 @@ static noinline int udf_process_sequence( memset(data.vds, 0, sizeof(struct udf_vds_record) * VDS_POS_LENGTH); data.size_part_descs = PART_DESC_ALLOC_STEP; + data.num_part_descs = 0; data.part_descs_loc = kcalloc(data.size_part_descs, sizeof(*data.part_descs_loc), GFP_KERNEL); @@ -1658,7 +1609,6 @@ static noinline int udf_process_sequence( * are in it. */ for (; (!done && block <= lastblock); block++) { - bh = udf_read_tagged(sb, block, block, &ident); if (!bh) break; @@ -1730,13 +1680,10 @@ static noinline int udf_process_sequence( } /* Now handle prevailing Partition Descriptors */ - for (i = 0; i < data.size_part_descs; i++) { - if (data.part_descs_loc[i].block) { - ret = udf_load_partdesc(sb, - data.part_descs_loc[i].block); - if (ret < 0) - return ret; - } + for (i = 0; i < data.num_part_descs; i++) { + ret = udf_load_partdesc(sb, data.part_descs_loc[i].rec.block); + if (ret < 0) + return ret; } return 0; diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h index 66d1d45fa2e1..d356f802945a 100644 --- a/include/asm-generic/io.h +++ b/include/asm-generic/io.h @@ -1026,7 +1026,8 @@ static inline void __iomem *ioremap_wt(phys_addr_t offset, size_t size) #define ioport_map ioport_map static inline void __iomem *ioport_map(unsigned long port, unsigned int nr) { - return PCI_IOBASE + (port & MMIO_UPPER_LIMIT); + port &= IO_SPACE_LIMIT; + return (port > MMIO_UPPER_LIMIT) ? NULL : PCI_IOBASE + port; } #endif diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index ca1d2cc2cdfa..18863d56273c 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -199,47 +199,57 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, #define __declare_arg_0(a0, res) \ struct arm_smccc_res *___res = res; \ - register u32 r0 asm("r0") = a0; \ + register unsigned long r0 asm("r0") = (u32)a0; \ register unsigned long r1 asm("r1"); \ register unsigned long r2 asm("r2"); \ register unsigned long r3 asm("r3") #define __declare_arg_1(a0, a1, res) \ + typeof(a1) __a1 = a1; \ struct arm_smccc_res *___res = res; \ - register u32 r0 asm("r0") = a0; \ - register typeof(a1) r1 asm("r1") = a1; \ + register unsigned long r0 asm("r0") = (u32)a0; \ + register unsigned long r1 asm("r1") = __a1; \ register unsigned long r2 asm("r2"); \ register unsigned long r3 asm("r3") #define __declare_arg_2(a0, a1, a2, res) \ + typeof(a1) __a1 = a1; \ + typeof(a2) __a2 = a2; \ struct arm_smccc_res *___res = res; \ - register u32 r0 asm("r0") = a0; \ - register typeof(a1) r1 asm("r1") = a1; \ - register typeof(a2) r2 asm("r2") = a2; \ + register unsigned long r0 asm("r0") = (u32)a0; \ + register unsigned long r1 asm("r1") = __a1; \ + register unsigned long r2 asm("r2") = __a2; \ register unsigned long r3 asm("r3") #define __declare_arg_3(a0, a1, a2, a3, res) \ + typeof(a1) __a1 = a1; \ + typeof(a2) __a2 = a2; \ + typeof(a3) __a3 = a3; \ struct arm_smccc_res *___res = res; \ - register u32 r0 asm("r0") = a0; \ - register typeof(a1) r1 asm("r1") = a1; \ - register typeof(a2) r2 asm("r2") = a2; \ - register typeof(a3) r3 asm("r3") = a3 + register unsigned long r0 asm("r0") = (u32)a0; \ + register unsigned long r1 asm("r1") = __a1; \ + register unsigned long r2 asm("r2") = __a2; \ + register unsigned long r3 asm("r3") = __a3 #define __declare_arg_4(a0, a1, a2, a3, a4, res) \ + typeof(a4) __a4 = a4; \ __declare_arg_3(a0, a1, a2, a3, res); \ - register typeof(a4) r4 asm("r4") = a4 + register unsigned long r4 asm("r4") = __a4 #define __declare_arg_5(a0, a1, a2, a3, a4, a5, res) \ + typeof(a5) __a5 = a5; \ __declare_arg_4(a0, a1, a2, a3, a4, res); \ - register typeof(a5) r5 asm("r5") = a5 + register unsigned long r5 asm("r5") = __a5 #define __declare_arg_6(a0, a1, a2, a3, a4, a5, a6, res) \ + typeof(a6) __a6 = a6; \ __declare_arg_5(a0, a1, a2, a3, a4, a5, res); \ - register typeof(a6) r6 asm("r6") = a6 + register unsigned long r6 asm("r6") = __a6 #define __declare_arg_7(a0, a1, a2, a3, a4, a5, a6, a7, res) \ + typeof(a7) __a7 = a7; \ __declare_arg_6(a0, a1, a2, a3, a4, a5, a6, res); \ - register typeof(a7) r7 asm("r7") = a7 + register unsigned long r7 asm("r7") = __a7 #define ___declare_args(count, ...) __declare_arg_ ## count(__VA_ARGS__) #define __declare_args(count, ...) ___declare_args(count, __VA_ARGS__) diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 212b3822d180..b41f7bc958ef 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -573,7 +573,7 @@ struct virtchnl_filter { enum virtchnl_flow_type flow_type; enum virtchnl_action action; u32 action_meta; - __u8 field_flags; + u8 field_flags; }; VIRTCHNL_CHECK_STRUCT_LEN(272, virtchnl_filter); diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 34aec30e06c7..6d766a19f2bb 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -56,6 +56,7 @@ struct blkcg { struct list_head all_blkcgs_node; #ifdef CONFIG_CGROUP_WRITEBACK struct list_head cgwb_list; + refcount_t cgwb_refcnt; #endif }; @@ -89,7 +90,6 @@ struct blkg_policy_data { /* the blkg and policy id this per-policy data belongs to */ struct blkcg_gq *blkg; int plid; - bool offline; }; /* @@ -387,6 +387,49 @@ static inline struct blkcg *cpd_to_blkcg(struct blkcg_policy_data *cpd) return cpd ? cpd->blkcg : NULL; } +extern void blkcg_destroy_blkgs(struct blkcg *blkcg); + +#ifdef CONFIG_CGROUP_WRITEBACK + +/** + * blkcg_cgwb_get - get a reference for blkcg->cgwb_list + * @blkcg: blkcg of interest + * + * This is used to track the number of active wb's related to a blkcg. + */ +static inline void blkcg_cgwb_get(struct blkcg *blkcg) +{ + refcount_inc(&blkcg->cgwb_refcnt); +} + +/** + * blkcg_cgwb_put - put a reference for @blkcg->cgwb_list + * @blkcg: blkcg of interest + * + * This is used to track the number of active wb's related to a blkcg. + * When this count goes to zero, all active wb has finished so the + * blkcg can continue destruction by calling blkcg_destroy_blkgs(). + * This work may occur in cgwb_release_workfn() on the cgwb_release + * workqueue. + */ +static inline void blkcg_cgwb_put(struct blkcg *blkcg) +{ + if (refcount_dec_and_test(&blkcg->cgwb_refcnt)) + blkcg_destroy_blkgs(blkcg); +} + +#else + +static inline void blkcg_cgwb_get(struct blkcg *blkcg) { } + +static inline void blkcg_cgwb_put(struct blkcg *blkcg) +{ + /* wb isn't being accounted, so trigger destruction right away */ + blkcg_destroy_blkgs(blkcg); +} + +#endif + /** * blkg_path - format cgroup path of blkg * @blkg: blkg of interest diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d6869e0e2b64..6980014357d4 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -54,7 +54,7 @@ struct blk_stat_callback; * Maximum number of blkcg policies allowed to be registered concurrently. * Defined here to simplify include dependency. */ -#define BLKCG_MAX_POLS 3 +#define BLKCG_MAX_POLS 5 typedef void (rq_end_io_fn)(struct request *, blk_status_t); diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 38b04f559ad3..b42b60a83e19 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -41,6 +41,7 @@ enum bpf_reg_liveness { }; struct bpf_reg_state { + /* Ordering of fields matters. See states_equal() */ enum bpf_reg_type type; union { /* valid when type == PTR_TO_PACKET */ @@ -59,7 +60,6 @@ struct bpf_reg_state { * came from, when one is tested for != NULL. */ u32 id; - /* Ordering of fields matters. See states_equal() */ /* For scalar types (SCALAR_VALUE), this represents our knowledge of * the actual value. * For pointer types, this represents the variable part of the offset @@ -76,15 +76,15 @@ struct bpf_reg_state { s64 smax_value; /* maximum possible (s64)value */ u64 umin_value; /* minimum possible (u64)value */ u64 umax_value; /* maximum possible (u64)value */ + /* parentage chain for liveness checking */ + struct bpf_reg_state *parent; /* Inside the callee two registers can be both PTR_TO_STACK like * R1=fp-8 and R2=fp-8, but one of them points to this function stack * while another to the caller's stack. To differentiate them 'frameno' * is used which is an index in bpf_verifier_state->frame[] array * pointing to bpf_func_state. - * This field must be second to last, for states_equal() reasons. */ u32 frameno; - /* This field must be last, for states_equal() reasons. */ enum bpf_reg_liveness live; }; @@ -107,7 +107,6 @@ struct bpf_stack_state { */ struct bpf_func_state { struct bpf_reg_state regs[MAX_BPF_REG]; - struct bpf_verifier_state *parent; /* index of call instruction that called into this func */ int callsite; /* stack frame number of this function state from pov of @@ -129,7 +128,6 @@ struct bpf_func_state { struct bpf_verifier_state { /* call stack tracking */ struct bpf_func_state *frame[MAX_CALL_FRAMES]; - struct bpf_verifier_state *parent; u32 curframe; }; diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index f8a2245b70ac..afd9596ce636 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -183,14 +183,6 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, /** * struct ethtool_ops - optional netdev operations - * @get_settings: DEPRECATED, use %get_link_ksettings/%set_link_ksettings - * API. Get various device settings including Ethernet link - * settings. The @cmd parameter is expected to have been cleared - * before get_settings is called. Returns a negative error code - * or zero. - * @set_settings: DEPRECATED, use %get_link_ksettings/%set_link_ksettings - * API. Set various device settings including Ethernet link - * settings. Returns a negative error code or zero. * @get_drvinfo: Report driver/device information. Should only set the * @driver, @version, @fw_version and @bus_info fields. If not * implemented, the @driver and @bus_info fields will be filled in @@ -297,19 +289,16 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, * a TX queue has this number, return -EINVAL. If only a RX queue or a TX * queue has this number, ignore the inapplicable fields. * Returns a negative error code or zero. - * @get_link_ksettings: When defined, takes precedence over the - * %get_settings method. Get various device settings - * including Ethernet link settings. The %cmd and - * %link_mode_masks_nwords fields should be ignored (use - * %__ETHTOOL_LINK_MODE_MASK_NBITS instead of the latter), any - * change to them will be overwritten by kernel. Returns a - * negative error code or zero. - * @set_link_ksettings: When defined, takes precedence over the - * %set_settings method. Set various device settings including - * Ethernet link settings. The %cmd and %link_mode_masks_nwords - * fields should be ignored (use %__ETHTOOL_LINK_MODE_MASK_NBITS - * instead of the latter), any change to them will be overwritten - * by kernel. Returns a negative error code or zero. + * @get_link_ksettings: Get various device settings including Ethernet link + * settings. The %cmd and %link_mode_masks_nwords fields should be + * ignored (use %__ETHTOOL_LINK_MODE_MASK_NBITS instead of the latter), + * any change to them will be overwritten by kernel. Returns a negative + * error code or zero. + * @set_link_ksettings: Set various device settings including Ethernet link + * settings. The %cmd and %link_mode_masks_nwords fields should be + * ignored (use %__ETHTOOL_LINK_MODE_MASK_NBITS instead of the latter), + * any change to them will be overwritten by kernel. Returns a negative + * error code or zero. * @get_fecparam: Get the network device Forward Error Correction parameters. * @set_fecparam: Set the network device Forward Error Correction parameters. * @get_ethtool_phy_stats: Return extended statistics about the PHY device. @@ -329,8 +318,6 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, * of the generic netdev features interface. */ struct ethtool_ops { - int (*get_settings)(struct net_device *, struct ethtool_cmd *); - int (*set_settings)(struct net_device *, struct ethtool_cmd *); void (*get_drvinfo)(struct net_device *, struct ethtool_drvinfo *); int (*get_regs_len)(struct net_device *); void (*get_regs)(struct net_device *, struct ethtool_regs *, void *); diff --git a/include/linux/fs.h b/include/linux/fs.h index 33322702c910..6c0b4a1c22ff 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1763,6 +1763,7 @@ struct file_operations { u64); int (*dedupe_file_range)(struct file *, loff_t, struct file *, loff_t, u64); + int (*fadvise)(struct file *, loff_t, loff_t, int); } __randomize_layout; struct inode_operations { @@ -3459,4 +3460,8 @@ static inline bool dir_relax_shared(struct inode *inode) extern bool path_noexec(const struct path *path); extern void inode_nohighmem(struct inode *inode); +/* mm/fadvise.c */ +extern int vfs_fadvise(struct file *file, loff_t offset, loff_t len, + int advice); + #endif /* _LINUX_FS_H */ diff --git a/include/linux/hid.h b/include/linux/hid.h index 834e6461a690..d44a78362942 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -526,6 +526,7 @@ struct hid_input { const char *name; bool registered; struct list_head reports; /* the list of reports */ + unsigned int application; /* application usage for this input */ }; enum hid_type { diff --git a/include/linux/i2c.h b/include/linux/i2c.h index b79387fd57da..65b4eaed1d96 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -855,7 +855,7 @@ static inline u8 i2c_8bit_addr_from_msg(const struct i2c_msg *msg) } u8 *i2c_get_dma_safe_msg_buf(struct i2c_msg *msg, unsigned int threshold); -void i2c_release_dma_safe_msg_buf(struct i2c_msg *msg, u8 *buf); +void i2c_put_dma_safe_msg_buf(u8 *buf, struct i2c_msg *msg, bool xferred); int i2c_handle_smbus_host_notify(struct i2c_adapter *adap, unsigned short addr); /** diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 9c03a7d5e400..c4809ad8ab46 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1460,13 +1460,16 @@ struct ieee80211_ht_operation { * STA can receive. Rate expressed in units of 1 Mbps. * If this field is 0 this value should not be used to * consider the highest RX data rate supported. - * The top 3 bits of this field are reserved. + * The top 3 bits of this field indicate the Maximum NSTS,total + * (a beamformee capability.) * @tx_mcs_map: TX MCS map 2 bits for each stream, total 8 streams * @tx_highest: Indicates highest long GI VHT PPDU data rate * STA can transmit. Rate expressed in units of 1 Mbps. * If this field is 0 this value should not be used to * consider the highest TX data rate supported. - * The top 3 bits of this field are reserved. + * The top 2 bits of this field are reserved, the + * 3rd bit from the top indiciates VHT Extended NSS BW + * Capability. */ struct ieee80211_vht_mcs_info { __le16 rx_mcs_map; @@ -1475,6 +1478,13 @@ struct ieee80211_vht_mcs_info { __le16 tx_highest; } __packed; +/* for rx_highest */ +#define IEEE80211_VHT_MAX_NSTS_TOTAL_SHIFT 13 +#define IEEE80211_VHT_MAX_NSTS_TOTAL_MASK (7 << IEEE80211_VHT_MAX_NSTS_TOTAL_SHIFT) + +/* for tx_highest */ +#define IEEE80211_VHT_EXT_NSS_BW_CAPABLE (1 << 13) + /** * enum ieee80211_vht_mcs_support - VHT MCS support definitions * @IEEE80211_VHT_MCS_SUPPORT_0_7: MCSes 0-7 are supported for the @@ -1545,11 +1555,11 @@ struct ieee80211_vht_operation { * struct ieee80211_he_cap_elem - HE capabilities element * * This structure is the "HE capabilities element" fixed fields as - * described in P802.11ax_D2.0 section 9.4.2.237.2 and 9.4.2.237.3 + * described in P802.11ax_D3.0 section 9.4.2.237.2 and 9.4.2.237.3 */ struct ieee80211_he_cap_elem { - u8 mac_cap_info[5]; - u8 phy_cap_info[9]; + u8 mac_cap_info[6]; + u8 phy_cap_info[11]; } __packed; #define IEEE80211_TX_RX_MCS_NSS_DESC_MAX_LEN 5 @@ -1650,6 +1660,7 @@ struct ieee80211_mu_edca_param_set { #define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ 0x00000004 #define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ 0x00000008 #define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK 0x0000000C +#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_SHIFT 2 #define IEEE80211_VHT_CAP_RXLDPC 0x00000010 #define IEEE80211_VHT_CAP_SHORT_GI_80 0x00000020 #define IEEE80211_VHT_CAP_SHORT_GI_160 0x00000040 @@ -1678,6 +1689,26 @@ struct ieee80211_mu_edca_param_set { #define IEEE80211_VHT_CAP_VHT_LINK_ADAPTATION_VHT_MRQ_MFB 0x0c000000 #define IEEE80211_VHT_CAP_RX_ANTENNA_PATTERN 0x10000000 #define IEEE80211_VHT_CAP_TX_ANTENNA_PATTERN 0x20000000 +#define IEEE80211_VHT_CAP_EXT_NSS_BW_SHIFT 30 +#define IEEE80211_VHT_CAP_EXT_NSS_BW_MASK 0xc0000000 + +/** + * ieee80211_get_vht_max_nss - return max NSS for a given bandwidth/MCS + * @cap: VHT capabilities of the peer + * @bw: bandwidth to use + * @mcs: MCS index to use + * @ext_nss_bw_capable: indicates whether or not the local transmitter + * (rate scaling algorithm) can deal with the new logic + * (dot11VHTExtendedNSSBWCapable) + * + * Due to the VHT Extended NSS Bandwidth Support, the maximum NSS can + * vary for a given BW/MCS. This function parses the data. + * + * Note: This function is exported by cfg80211. + */ +int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, + enum ieee80211_vht_chanwidth bw, + int mcs, bool ext_nss_bw_capable); /* 802.11ax HE MAC capabilities */ #define IEEE80211_HE_MAC_CAP0_HTC_HE 0x01 @@ -1707,15 +1738,15 @@ struct ieee80211_mu_edca_param_set { #define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_8US 0x04 #define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US 0x08 #define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_MASK 0x0c -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_1 0x00 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_2 0x10 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_3 0x20 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_4 0x30 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_5 0x40 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_6 0x50 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_7 0x60 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_8 0x70 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_MASK 0x70 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_1 0x00 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_2 0x10 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_3 0x20 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_4 0x30 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_5 0x40 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_6 0x50 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_7 0x60 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8 0x70 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_MASK 0x70 /* Link adaptation is split between byte HE_MAC_CAP1 and * HE_MAC_CAP2. It should be set only if IEEE80211_HE_MAC_CAP0_HTC_HE @@ -1729,14 +1760,13 @@ struct ieee80211_mu_edca_param_set { #define IEEE80211_HE_MAC_CAP2_LINK_ADAPTATION 0x01 #define IEEE80211_HE_MAC_CAP2_ALL_ACK 0x02 -#define IEEE80211_HE_MAC_CAP2_UL_MU_RESP_SCHED 0x04 +#define IEEE80211_HE_MAC_CAP2_TRS 0x04 #define IEEE80211_HE_MAC_CAP2_BSR 0x08 #define IEEE80211_HE_MAC_CAP2_BCAST_TWT 0x10 #define IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP 0x20 #define IEEE80211_HE_MAC_CAP2_MU_CASCADING 0x40 #define IEEE80211_HE_MAC_CAP2_ACK_EN 0x80 -#define IEEE80211_HE_MAC_CAP3_GRP_ADDR_MULTI_STA_BA_DL_MU 0x01 #define IEEE80211_HE_MAC_CAP3_OMI_CONTROL 0x02 #define IEEE80211_HE_MAC_CAP3_OFDMA_RA 0x04 @@ -1744,25 +1774,34 @@ struct ieee80211_mu_edca_param_set { * A-MDPU Length Exponent field in the HT capabilities, VHT capabilities and the * same field in the HE capabilities. */ -#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_USE_VHT 0x00 -#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_VHT_1 0x08 -#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_VHT_2 0x10 -#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_RESERVED 0x18 -#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_MASK 0x18 -#define IEEE80211_HE_MAC_CAP3_A_AMSDU_FRAG 0x20 +#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_USE_VHT 0x00 +#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_VHT_1 0x08 +#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_VHT_2 0x10 +#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_RESERVED 0x18 +#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_MASK 0x18 +#define IEEE80211_HE_MAC_CAP3_AMSDU_FRAG 0x20 #define IEEE80211_HE_MAC_CAP3_FLEX_TWT_SCHED 0x40 #define IEEE80211_HE_MAC_CAP3_RX_CTRL_FRAME_TO_MULTIBSS 0x80 #define IEEE80211_HE_MAC_CAP4_BSRP_BQRP_A_MPDU_AGG 0x01 #define IEEE80211_HE_MAC_CAP4_QTP 0x02 #define IEEE80211_HE_MAC_CAP4_BQR 0x04 -#define IEEE80211_HE_MAC_CAP4_SR_RESP 0x08 +#define IEEE80211_HE_MAC_CAP4_SRP_RESP 0x08 #define IEEE80211_HE_MAC_CAP4_NDP_FB_REP 0x10 #define IEEE80211_HE_MAC_CAP4_OPS 0x20 #define IEEE80211_HE_MAC_CAP4_AMDSU_IN_AMPDU 0x40 +/* Multi TID agg TX is split between byte #4 and #5 + * The value is a combination of B39,B40,B41 + */ +#define IEEE80211_HE_MAC_CAP4_MULTI_TID_AGG_TX_QOS_B39 0x80 + +#define IEEE80211_HE_MAC_CAP5_MULTI_TID_AGG_TX_QOS_B40 0x01 +#define IEEE80211_HE_MAC_CAP5_MULTI_TID_AGG_TX_QOS_B41 0x02 +#define IEEE80211_HE_MAC_CAP5_SUBCHAN_SELECVITE_TRANSMISSION 0x04 +#define IEEE80211_HE_MAC_CAP5_UL_2x996_TONE_RU 0x08 +#define IEEE80211_HE_MAC_CAP5_OM_CTRL_UL_MU_DATA_DIS_RX 0x10 /* 802.11ax HE PHY capabilities */ -#define IEEE80211_HE_PHY_CAP0_DUAL_BAND 0x01 #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G 0x02 #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G 0x04 #define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G 0x08 @@ -1779,10 +1818,10 @@ struct ieee80211_mu_edca_param_set { #define IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A 0x10 #define IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD 0x20 #define IEEE80211_HE_PHY_CAP1_HE_LTF_AND_GI_FOR_HE_PPDUS_0_8US 0x40 -/* Midamble RX Max NSTS is split between byte #2 and byte #3 */ -#define IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_MAX_NSTS 0x80 +/* Midamble RX/TX Max NSTS is split between byte #2 and byte #3 */ +#define IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS 0x80 -#define IEEE80211_HE_PHY_CAP2_MIDAMBLE_RX_MAX_NSTS 0x01 +#define IEEE80211_HE_PHY_CAP2_MIDAMBLE_RX_TX_MAX_NSTS 0x01 #define IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US 0x02 #define IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ 0x04 #define IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ 0x08 @@ -1883,7 +1922,19 @@ struct ieee80211_mu_edca_param_set { #define IEEE80211_HE_PHY_CAP8_20MHZ_IN_160MHZ_HE_PPDU 0x04 #define IEEE80211_HE_PHY_CAP8_80MHZ_IN_160MHZ_HE_PPDU 0x08 #define IEEE80211_HE_PHY_CAP8_HE_ER_SU_1XLTF_AND_08_US_GI 0x10 -#define IEEE80211_HE_PHY_CAP8_MIDAMBLE_RX_2X_AND_1XLTF 0x20 +#define IEEE80211_HE_PHY_CAP8_MIDAMBLE_RX_TX_2X_AND_1XLTF 0x20 +#define IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_20MHZ 0x00 +#define IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_40MHZ 0x40 +#define IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_80MHZ 0x80 +#define IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_160_OR_80P80_MHZ 0xc0 +#define IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_MASK 0xc0 + +#define IEEE80211_HE_PHY_CAP9_LONGER_THAN_16_SIGB_OFDM_SYM 0x01 +#define IEEE80211_HE_PHY_CAP9_NON_TRIGGERED_CQI_FEEDBACK 0x02 +#define IEEE80211_HE_PHY_CAP9_TX_1024_QAM_LESS_THAN_242_TONE_RU 0x04 +#define IEEE80211_HE_PHY_CAP9_RX_1024_QAM_LESS_THAN_242_TONE_RU 0x08 +#define IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_COMP_SIGB 0x10 +#define IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_NON_COMP_SIGB 0x20 /* 802.11ax HE TX/RX MCS NSS Support */ #define IEEE80211_TX_RX_MCS_NSS_SUPP_HIGHEST_MCS_POS (3) @@ -1963,8 +2014,8 @@ ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info) #define IEEE80211_HE_OPERATION_TWT_REQUIRED 0x00000200 #define IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK 0x000ffc00 #define IEEE80211_HE_OPERATION_RTS_THRESHOLD_OFFSET 10 -#define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR 0x000100000 -#define IEEE80211_HE_OPERATION_VHT_OPER_INFO 0x000200000 +#define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR 0x00100000 +#define IEEE80211_HE_OPERATION_VHT_OPER_INFO 0x00200000 #define IEEE80211_HE_OPERATION_MULTI_BSSID_AP 0x10000000 #define IEEE80211_HE_OPERATION_TX_BSSID_INDICATOR 0x20000000 #define IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED 0x40000000 diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h index 3d2996dc7d85..12e3eebf0ce6 100644 --- a/include/linux/if_tun.h +++ b/include/linux/if_tun.h @@ -16,9 +16,23 @@ #define __IF_TUN_H #include <uapi/linux/if_tun.h> +#include <uapi/linux/virtio_net.h> #define TUN_XDP_FLAG 0x1UL +#define TUN_MSG_UBUF 1 +#define TUN_MSG_PTR 2 +struct tun_msg_ctl { + unsigned short type; + unsigned short num; + void *ptr; +}; + +struct tun_xdp_hdr { + int buflen; + struct virtio_net_hdr gso; +}; + #if defined(CONFIG_TUN) || defined(CONFIG_TUN_MODULE) struct socket *tun_get_socket(struct file *); struct ptr_ring *tun_get_tx_ring(struct file *file); diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 8415bf1a9776..495e834c1367 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -274,7 +274,8 @@ struct ipv6_pinfo { */ dontfrag:1, autoflowlabel:1, - autoflowlabel_set:1; + autoflowlabel_set:1, + mc_all:1; __u8 min_hopcount; __u8 tclass; __be32 rcv_flowinfo; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 7a452716de4b..ed73b51f6697 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -362,8 +362,8 @@ struct mlx5_frag_buf { struct mlx5_frag_buf_ctrl { struct mlx5_frag_buf frag_buf; u32 sz_m1; - u32 frag_sz_m1; - u32 strides_offset; + u16 frag_sz_m1; + u16 strides_offset; u8 log_sz; u8 log_stride; u8 log_frag_strides; @@ -583,10 +583,11 @@ struct mlx5_irq_info { }; struct mlx5_fc_stats { - struct rb_root counters; - struct list_head addlist; - /* protect addlist add/splice operations */ - spinlock_t addlist_lock; + spinlock_t counters_idr_lock; /* protects counters_idr */ + struct idr counters_idr; + struct list_head counters; + struct llist_head addlist; + struct llist_head dellist; struct workqueue_struct *wq; struct delayed_work work; @@ -804,7 +805,7 @@ struct mlx5_pps { }; struct mlx5_clock { - rwlock_t lock; + seqlock_t lock; struct cyclecounter cycles; struct timecounter tc; struct hwtstamp_config hwtstamp_config; @@ -995,7 +996,7 @@ static inline u32 mlx5_base_mkey(const u32 key) } static inline void mlx5_fill_fbc_offset(u8 log_stride, u8 log_sz, - u32 strides_offset, + u16 strides_offset, struct mlx5_frag_buf_ctrl *fbc) { fbc->log_stride = log_stride; @@ -1052,7 +1053,7 @@ int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn); void mlx5_health_cleanup(struct mlx5_core_dev *dev); int mlx5_health_init(struct mlx5_core_dev *dev); void mlx5_start_health_poll(struct mlx5_core_dev *dev); -void mlx5_stop_health_poll(struct mlx5_core_dev *dev); +void mlx5_stop_health_poll(struct mlx5_core_dev *dev, bool disable_health); void mlx5_drain_health_wq(struct mlx5_core_dev *dev); void mlx5_trigger_health_work(struct mlx5_core_dev *dev); void mlx5_drain_health_recovery(struct mlx5_core_dev *dev); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index cd2bc939efd0..5ed8f6292a53 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -341,7 +341,7 @@ struct mm_struct { struct { struct vm_area_struct *mmap; /* list of VMAs */ struct rb_root mm_rb; - u32 vmacache_seqnum; /* per-thread vmacache */ + u64 vmacache_seqnum; /* per-thread vmacache */ #ifdef CONFIG_MMU unsigned long (*get_unmapped_area) (struct file *filp, unsigned long addr, unsigned long len, diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h index 5fe87687664c..d7016dcb245e 100644 --- a/include/linux/mm_types_task.h +++ b/include/linux/mm_types_task.h @@ -32,7 +32,7 @@ #define VMACACHE_MASK (VMACACHE_SIZE - 1) struct vmacache { - u32 seqnum; + u64 seqnum; struct vm_area_struct *vmas[VMACACHE_SIZE]; }; diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 1298a7daa57d..01797cb4587e 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -754,6 +754,7 @@ struct tb_service_id { * struct typec_device_id - USB Type-C alternate mode identifiers * @svid: Standard or Vendor ID * @mode: Mode index + * @driver_data: Driver specific data */ struct typec_device_id { __u16 svid; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ca5ab98053c8..1cbbf77a685f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -535,6 +535,32 @@ static inline void napi_synchronize(const struct napi_struct *n) barrier(); } +/** + * napi_if_scheduled_mark_missed - if napi is running, set the + * NAPIF_STATE_MISSED + * @n: NAPI context + * + * If napi is running, set the NAPIF_STATE_MISSED, and return true if + * NAPI is scheduled. + **/ +static inline bool napi_if_scheduled_mark_missed(struct napi_struct *n) +{ + unsigned long val, new; + + do { + val = READ_ONCE(n->state); + if (val & NAPIF_STATE_DISABLE) + return true; + + if (!(val & NAPIF_STATE_SCHED)) + return false; + + new = val | NAPIF_STATE_MISSED; + } while (cmpxchg(&n->state, val, new) != val); + + return true; +} + enum netdev_queue_state_t { __QUEUE_STATE_DRV_XOFF, __QUEUE_STATE_STACK_XOFF, @@ -1974,7 +2000,6 @@ struct net_device { struct pcpu_lstats __percpu *lstats; struct pcpu_sw_netstats __percpu *tstats; struct pcpu_dstats __percpu *dstats; - struct pcpu_vstats __percpu *vstats; }; #if IS_ENABLED(CONFIG_GARP) @@ -2317,6 +2342,7 @@ static inline struct sk_buff *call_gro_receive_sk(gro_receive_sk_t cb, struct packet_type { __be16 type; /* This is really htons(ether_type). */ + bool ignore_outgoing; struct net_device *dev; /* NULL is wildcarded here */ int (*func) (struct sk_buff *, struct net_device *, @@ -2355,6 +2381,12 @@ struct pcpu_sw_netstats { struct u64_stats_sync syncp; }; +struct pcpu_lstats { + u64 packets; + u64 bytes; + struct u64_stats_sync syncp; +}; + #define __netdev_alloc_pcpu_stats(type, gfp) \ ({ \ typeof(type) __percpu *pcpu_stats = alloc_percpu_gfp(type, gfp);\ diff --git a/include/linux/of.h b/include/linux/of.h index 4d25e4f952d9..99b0ebf49632 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -256,6 +256,9 @@ static inline unsigned long of_read_ulong(const __be32 *cell, int size) #define OF_IS_DYNAMIC(x) test_bit(OF_DYNAMIC, &x->_flags) #define OF_MARK_DYNAMIC(x) set_bit(OF_DYNAMIC, &x->_flags) +extern bool of_node_name_eq(const struct device_node *np, const char *name); +extern bool of_node_name_prefix(const struct device_node *np, const char *prefix); + static inline const char *of_node_full_name(const struct device_node *np) { return np ? np->full_name : "<no-node>"; @@ -290,6 +293,8 @@ extern struct device_node *of_get_next_child(const struct device_node *node, extern struct device_node *of_get_next_available_child( const struct device_node *node, struct device_node *prev); +extern struct device_node *of_get_compatible_child(const struct device_node *parent, + const char *compatible); extern struct device_node *of_get_child_by_name(const struct device_node *node, const char *name); @@ -561,6 +566,16 @@ static inline struct device_node *to_of_node(const struct fwnode_handle *fwnode) return NULL; } +static inline bool of_node_name_eq(const struct device_node *np, const char *name) +{ + return false; +} + +static inline bool of_node_name_prefix(const struct device_node *np, const char *prefix) +{ + return false; +} + static inline const char* of_node_full_name(const struct device_node *np) { return "<no-node>"; @@ -632,6 +647,12 @@ static inline bool of_have_populated_dt(void) return false; } +static inline struct device_node *of_get_compatible_child(const struct device_node *parent, + const char *compatible) +{ + return NULL; +} + static inline struct device_node *of_get_child_by_name( const struct device_node *node, const char *name) @@ -967,6 +988,18 @@ static inline struct device_node *of_find_matching_node( return of_find_matching_node_and_match(from, matches, NULL); } +static inline const char *of_node_get_device_type(const struct device_node *np) +{ + return of_get_property(np, "type", NULL); +} + +static inline bool of_node_is_type(const struct device_node *np, const char *type) +{ + const char *match = of_node_get_device_type(np); + + return np && match && type && !strcmp(match, type); +} + /** * of_property_count_u8_elems - Count the number of u8 elements in a property * diff --git a/include/linux/pci.h b/include/linux/pci.h index e72ca8dd6241..6925828f9f25 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1235,6 +1235,9 @@ void pci_bus_remove_resources(struct pci_bus *bus); int devm_request_pci_bus_resources(struct device *dev, struct list_head *resources); +/* Temporary until new and working PCI SBR API in place */ +int pci_bridge_secondary_bus_reset(struct pci_dev *dev); + #define pci_bus_for_each_resource(bus, res, i) \ for (i = 0; \ (res = pci_bus_resource_n(bus, i)) || i < PCI_BRIDGE_RESOURCE_NUM; \ diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 99d366cb0e9f..d157983b84cf 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -3084,4 +3084,6 @@ #define PCI_VENDOR_ID_OCZ 0x1b85 +#define PCI_VENDOR_ID_NCUBE 0x10ff + #endif /* _LINUX_PCI_IDS_H */ diff --git a/include/linux/phy.h b/include/linux/phy.h index cd6f637cbbfb..192a1fa0c73b 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1049,6 +1049,14 @@ int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd); int phy_start_interrupts(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); int phy_set_max_speed(struct phy_device *phydev, u32 max_speed); +void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode); +void phy_support_sym_pause(struct phy_device *phydev); +void phy_support_asym_pause(struct phy_device *phydev); +void phy_set_sym_pause(struct phy_device *phydev, bool rx, bool tx, + bool autoneg); +void phy_set_asym_pause(struct phy_device *phydev, bool rx, bool tx); +bool phy_validate_pause(struct phy_device *phydev, + struct ethtool_pauseparam *pp); int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, int (*run)(struct phy_device *)); diff --git a/include/linux/platform_data/ina2xx.h b/include/linux/platform_data/ina2xx.h index 9abc0ca7259b..9f0aa1b48c78 100644 --- a/include/linux/platform_data/ina2xx.h +++ b/include/linux/platform_data/ina2xx.h @@ -1,7 +1,7 @@ /* * Driver for Texas Instruments INA219, INA226 power monitor chips * - * Copyright (C) 2012 Lothar Felten <l-felten@ti.com> + * Copyright (C) 2012 Lothar Felten <lothar.felten@gmail.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 diff --git a/include/linux/qed/common_hsi.h b/include/linux/qed/common_hsi.h index 0081fa6d1268..03f59a28fefd 100644 --- a/include/linux/qed/common_hsi.h +++ b/include/linux/qed/common_hsi.h @@ -110,7 +110,7 @@ #define FW_MAJOR_VERSION 8 #define FW_MINOR_VERSION 37 -#define FW_REVISION_VERSION 2 +#define FW_REVISION_VERSION 7 #define FW_ENGINEERING_VERSION 0 /***********************/ @@ -931,12 +931,12 @@ struct db_rdma_dpm_params { #define DB_RDMA_DPM_PARAMS_WQE_SIZE_SHIFT 16 #define DB_RDMA_DPM_PARAMS_RESERVED0_MASK 0x1 #define DB_RDMA_DPM_PARAMS_RESERVED0_SHIFT 27 -#define DB_RDMA_DPM_PARAMS_COMPLETION_FLG_MASK 0x1 -#define DB_RDMA_DPM_PARAMS_COMPLETION_FLG_SHIFT 28 +#define DB_RDMA_DPM_PARAMS_ACK_REQUEST_MASK 0x1 +#define DB_RDMA_DPM_PARAMS_ACK_REQUEST_SHIFT 28 #define DB_RDMA_DPM_PARAMS_S_FLG_MASK 0x1 #define DB_RDMA_DPM_PARAMS_S_FLG_SHIFT 29 -#define DB_RDMA_DPM_PARAMS_RESERVED1_MASK 0x1 -#define DB_RDMA_DPM_PARAMS_RESERVED1_SHIFT 30 +#define DB_RDMA_DPM_PARAMS_COMPLETION_FLG_MASK 0x1 +#define DB_RDMA_DPM_PARAMS_COMPLETION_FLG_SHIFT 30 #define DB_RDMA_DPM_PARAMS_CONN_TYPE_IS_IWARP_MASK 0x1 #define DB_RDMA_DPM_PARAMS_CONN_TYPE_IS_IWARP_SHIFT 31 }; diff --git a/include/linux/qed/iscsi_common.h b/include/linux/qed/iscsi_common.h index b34c573f2b30..66aba505ec56 100644 --- a/include/linux/qed/iscsi_common.h +++ b/include/linux/qed/iscsi_common.h @@ -896,7 +896,7 @@ struct e4_ustorm_iscsi_task_ag_ctx { __le32 exp_cont_len; __le32 total_data_acked; __le32 exp_data_acked; - u8 next_tid_valid; + u8 byte2; u8 byte3; __le16 word1; __le16 next_tid; diff --git a/include/linux/quota.h b/include/linux/quota.h index ca9772c8e48b..f32dd270b8e3 100644 --- a/include/linux/quota.h +++ b/include/linux/quota.h @@ -408,13 +408,7 @@ struct qc_type_state { struct qc_state { unsigned int s_incoredqs; /* Number of dquots in core */ - /* - * Per quota type information. The array should really have - * max(MAXQUOTAS, XQM_MAXQUOTAS) entries. BUILD_BUG_ON in - * quota_getinfo() makes sure XQM_MAXQUOTAS is large enough. Once VFS - * supports project quotas, this can be changed to MAXQUOTAS - */ - struct qc_type_state s_state[XQM_MAXQUOTAS]; + struct qc_type_state s_state[MAXQUOTAS]; /* Per quota type information */ }; /* Structure for communicating via ->set_info */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 17a13e4785fc..e3a53ca4a9b5 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1339,6 +1339,17 @@ static inline void skb_zcopy_abort(struct sk_buff *skb) } } +static inline void skb_mark_not_on_list(struct sk_buff *skb) +{ + skb->next = NULL; +} + +static inline void skb_list_del_init(struct sk_buff *skb) +{ + __list_del_entry(&skb->list); + skb_mark_not_on_list(skb); +} + /** * skb_queue_empty - check if a queue is empty * @list: queue head @@ -1593,6 +1604,17 @@ static inline struct sk_buff *skb_peek(const struct sk_buff_head *list_) } /** + * __skb_peek - peek at the head of a non-empty &sk_buff_head + * @list_: list to peek at + * + * Like skb_peek(), but the caller knows that the list is not empty. + */ +static inline struct sk_buff *__skb_peek(const struct sk_buff_head *list_) +{ + return list_->next; +} + +/** * skb_peek_next - peek skb following the given one from a queue * @skb: skb to start from * @list_: list to peek at diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 5d738804e3d6..a5a3cfc3c2fa 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -258,8 +258,8 @@ extern void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot); extern int persistent_clock_is_local; extern void read_persistent_clock64(struct timespec64 *ts); -void read_persistent_clock_and_boot_offset(struct timespec64 *wall_clock, - struct timespec64 *boot_offset); +void read_persistent_wall_and_boot_offset(struct timespec64 *wall_clock, + struct timespec64 *boot_offset); extern int update_persistent_clock64(struct timespec64 now); /* diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index 7f2e16e76ac4..041f7e56a289 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -158,8 +158,10 @@ extern void syscall_unregfunc(void); * For rcuidle callers, use srcu since sched-rcu \ * doesn't work from the idle path. \ */ \ - if (rcuidle) \ + if (rcuidle) { \ idx = srcu_read_lock_notrace(&tracepoint_srcu); \ + rcu_irq_enter_irqson(); \ + } \ \ it_func_ptr = rcu_dereference_raw((tp)->funcs); \ \ @@ -171,8 +173,10 @@ extern void syscall_unregfunc(void); } while ((++it_func_ptr)->func); \ } \ \ - if (rcuidle) \ + if (rcuidle) { \ + rcu_irq_exit_irqson(); \ srcu_read_unlock_notrace(&tracepoint_srcu, idx);\ + } \ \ preempt_enable_notrace(); \ } while (0) diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 5c7f010676a7..47a3441cf4c4 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -105,7 +105,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #ifdef CONFIG_DEBUG_VM_VMACACHE VMACACHE_FIND_CALLS, VMACACHE_FIND_HITS, - VMACACHE_FULL_FLUSHES, #endif #ifdef CONFIG_SWAP SWAP_RA, diff --git a/include/linux/vmacache.h b/include/linux/vmacache.h index 3e9a963edd6a..6fce268a4588 100644 --- a/include/linux/vmacache.h +++ b/include/linux/vmacache.h @@ -10,7 +10,6 @@ static inline void vmacache_flush(struct task_struct *tsk) memset(tsk->vmacache.vmas, 0, sizeof(tsk->vmacache.vmas)); } -extern void vmacache_flush_all(struct mm_struct *mm); extern void vmacache_update(unsigned long addr, struct vm_area_struct *newvma); extern struct vm_area_struct *vmacache_find(struct mm_struct *mm, unsigned long addr); @@ -24,10 +23,6 @@ extern struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm, static inline void vmacache_invalidate(struct mm_struct *mm) { mm->vmacache_seqnum++; - - /* deal with overflows */ - if (unlikely(mm->vmacache_seqnum == 0)) - vmacache_flush_all(mm); } #endif /* __LINUX_VMACACHE_H */ diff --git a/include/net/act_api.h b/include/net/act_api.h index 1ad5b19e83a9..c6f195b3c706 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -23,13 +23,11 @@ struct tc_action { const struct tc_action_ops *ops; __u32 type; /* for backward compat(TCA_OLD_COMPAT) */ __u32 order; - struct list_head list; struct tcf_idrinfo *idrinfo; u32 tcfa_index; refcount_t tcfa_refcnt; atomic_t tcfa_bindcnt; - u32 tcfa_capab; int tcfa_action; struct tcf_t tcfa_tm; struct gnet_stats_basic_packed tcfa_bstats; @@ -44,7 +42,6 @@ struct tc_action { #define tcf_index common.tcfa_index #define tcf_refcnt common.tcfa_refcnt #define tcf_bindcnt common.tcfa_bindcnt -#define tcf_capab common.tcfa_capab #define tcf_action common.tcfa_action #define tcf_tm common.tcfa_tm #define tcf_bstats common.tcfa_bstats @@ -88,8 +85,7 @@ struct tc_action_ops { struct tcf_result *); /* called under RCU BH lock*/ int (*dump)(struct sk_buff *, struct tc_action *, int, int); void (*cleanup)(struct tc_action *); - int (*lookup)(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack); + int (*lookup)(struct net *net, struct tc_action **a, u32 index); int (*init)(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **act, int ovr, int bind, bool rtnl_held, @@ -102,7 +98,6 @@ struct tc_action_ops { size_t (*get_fill_size)(const struct tc_action *act); struct net_device *(*get_dev)(const struct tc_action *a); void (*put_dev)(struct net_device *dev); - int (*delete)(struct net *net, u32 index); }; struct tc_action_net { @@ -148,8 +143,6 @@ int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb, const struct tc_action_ops *ops, struct netlink_ext_ack *extack); int tcf_idr_search(struct tc_action_net *tn, struct tc_action **a, u32 index); -bool tcf_idr_check(struct tc_action_net *tn, u32 index, struct tc_action **a, - int bind); int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, struct tc_action **a, const struct tc_action_ops *ops, int bind, bool cpustats); @@ -158,7 +151,6 @@ void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a); void tcf_idr_cleanup(struct tc_action_net *tn, u32 index); int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index, struct tc_action **a, int bind); -int tcf_idr_delete_index(struct tc_action_net *tn, u32 index); int __tcf_idr_release(struct tc_action *a, bool bind, bool strict); static inline int tcf_idr_release(struct tc_action *a, bool bind) diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 9a850973e09a..9f3ed79c39d7 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -149,7 +149,7 @@ enum ieee80211_channel_flags { */ struct ieee80211_channel { enum nl80211_band band; - u16 center_freq; + u32 center_freq; u16 hw_value; u32 flags; int max_antenna_gain; @@ -849,6 +849,7 @@ struct cfg80211_bitrate_mask { * @beacon_rate: bitrate to be used for beacons * @ht_cap: HT capabilities (or %NULL if HT isn't enabled) * @vht_cap: VHT capabilities (or %NULL if VHT isn't enabled) + * @he_cap: HE capabilities (or %NULL if HE isn't enabled) * @ht_required: stations must support HT * @vht_required: stations must support VHT */ @@ -874,6 +875,7 @@ struct cfg80211_ap_settings { const struct ieee80211_ht_cap *ht_cap; const struct ieee80211_vht_cap *vht_cap; + const struct ieee80211_he_cap_elem *he_cap; bool ht_required, vht_required; }; @@ -4733,6 +4735,17 @@ const u8 *cfg80211_find_vendor_ie(unsigned int oui, int oui_type, const u8 *ies, int len); /** + * cfg80211_send_layer2_update - send layer 2 update frame + * + * @dev: network device + * @addr: STA MAC address + * + * Wireless drivers can use this function to update forwarding tables in bridge + * devices upon STA association. + */ +void cfg80211_send_layer2_update(struct net_device *dev, const u8 *addr); + +/** * DOC: Regulatory enforcement infrastructure * * TODO @@ -4865,8 +4878,8 @@ const char *reg_initiator_name(enum nl80211_reg_initiator initiator); * * Return: 0 on success. -ENODATA. */ -int reg_query_regdb_wmm(char *alpha2, int freq, u32 *ptr, - struct ieee80211_wmm_rule *rule); +int reg_query_regdb_wmm(char *alpha2, int freq, + struct ieee80211_reg_rule *rule); /* * callbacks for asynchronous cfg80211 methods, notification diff --git a/include/net/dsa.h b/include/net/dsa.h index 461e8a7661b7..23690c44e167 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -35,6 +35,7 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_BRCM_PREPEND, DSA_TAG_PROTO_DSA, DSA_TAG_PROTO_EDSA, + DSA_TAG_PROTO_GSWIP, DSA_TAG_PROTO_KSZ, DSA_TAG_PROTO_LAN9303, DSA_TAG_PROTO_MTK, diff --git a/include/net/genetlink.h b/include/net/genetlink.h index decf6012a401..aa2e5888f18d 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -112,7 +112,7 @@ static inline void genl_info_net_set(struct genl_info *info, struct net *net) #define GENL_SET_ERR_MSG(info, msg) NL_SET_ERR_MSG((info)->extack, msg) static inline int genl_err_attr(struct genl_info *info, int err, - struct nlattr *attr) + const struct nlattr *attr) { info->extack->bad_attr = attr; diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h index feef706e1158..8014153bdd49 100644 --- a/include/net/ieee80211_radiotap.h +++ b/include/net/ieee80211_radiotap.h @@ -75,6 +75,8 @@ enum ieee80211_radiotap_presence { IEEE80211_RADIOTAP_TIMESTAMP = 22, IEEE80211_RADIOTAP_HE = 23, IEEE80211_RADIOTAP_HE_MU = 24, + IEEE80211_RADIOTAP_ZERO_LEN_PSDU = 26, + IEEE80211_RADIOTAP_LSIG = 27, /* valid in every it_present bitmap, even vendor namespaces */ IEEE80211_RADIOTAP_RADIOTAP_NAMESPACE = 29, @@ -325,6 +327,25 @@ enum ieee80211_radiotap_he_mu_bits { IEEE80211_RADIOTAP_HE_MU_FLAGS2_CH2_CTR_26T_RU = 0x0800, }; +enum ieee80211_radiotap_lsig_data1 { + IEEE80211_RADIOTAP_LSIG_DATA1_RATE_KNOWN = 0x0001, + IEEE80211_RADIOTAP_LSIG_DATA1_LENGTH_KNOWN = 0x0002, +}; + +enum ieee80211_radiotap_lsig_data2 { + IEEE80211_RADIOTAP_LSIG_DATA2_RATE = 0x000f, + IEEE80211_RADIOTAP_LSIG_DATA2_LENGTH = 0xfff0, +}; + +struct ieee80211_radiotap_lsig { + __le16 data1, data2; +}; + +enum ieee80211_radiotap_zero_len_psdu_type { + IEEE80211_RADIOTAP_ZERO_LEN_PSDU_SOUNDING = 0, + IEEE80211_RADIOTAP_ZERO_LEN_PSDU_VENDOR = 0xff, +}; + /** * ieee80211_get_radiotap_len - get radiotap header length */ diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 3d4930528db0..f06e968f1992 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -182,7 +182,6 @@ struct rt6_info { struct in6_addr rt6i_gateway; struct inet6_dev *rt6i_idev; u32 rt6i_flags; - struct rt6key rt6i_prefsrc; struct list_head rt6i_uncached; struct uncached_list *rt6i_uncached_list; @@ -413,6 +412,25 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt, struct nl_info *info, struct netlink_ext_ack *extack); int fib6_del(struct fib6_info *rt, struct nl_info *info); +static inline +void rt6_get_prefsrc(const struct rt6_info *rt, struct in6_addr *addr) +{ + const struct fib6_info *from; + + rcu_read_lock(); + + from = rcu_dereference(rt->from); + if (from) { + *addr = from->fib6_prefsrc.addr; + } else { + struct in6_addr in6_zero = {}; + + *addr = in6_zero; + } + + rcu_read_unlock(); +} + static inline struct net_device *fib6_info_nh_dev(const struct fib6_info *f6i) { return f6i->fib6_nh.nh_dev; diff --git a/include/net/llc.h b/include/net/llc.h index 890a87318014..df282d9b4017 100644 --- a/include/net/llc.h +++ b/include/net/llc.h @@ -66,6 +66,7 @@ struct llc_sap { int sk_count; struct hlist_nulls_head sk_laddr_hash[LLC_SK_LADDR_HASH_ENTRIES]; struct hlist_head sk_dev_hash[LLC_SK_DEV_HASH_ENTRIES]; + struct rcu_head rcu; }; static inline diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 5790f55c241d..c4fadbafbf21 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -101,8 +101,9 @@ * Drivers indicate that they use this model by implementing the .wake_tx_queue * driver operation. * - * Intermediate queues (struct ieee80211_txq) are kept per-sta per-tid, with a - * single per-vif queue for multicast data frames. + * Intermediate queues (struct ieee80211_txq) are kept per-sta per-tid, with + * another per-sta for non-data/non-mgmt and bufferable management frames, and + * a single per-vif queue for multicast data frames. * * The driver is expected to initialize its private per-queue data for stations * and interfaces in the .add_interface and .sta_add ops. @@ -1140,6 +1141,11 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) * from the RX info data, so leave those zeroed when building this data) * @RX_FLAG_RADIOTAP_HE_MU: HE MU radiotap data is present * (&struct ieee80211_radiotap_he_mu) + * @RX_FLAG_RADIOTAP_LSIG: L-SIG radiotap data is present + * @RX_FLAG_NO_PSDU: use the frame only for radiotap reporting, with + * the "0-length PSDU" field included there. The value for it is + * in &struct ieee80211_rx_status. Note that if this value isn't + * known the frame shouldn't be reported. */ enum mac80211_rx_flags { RX_FLAG_MMIC_ERROR = BIT(0), @@ -1170,6 +1176,8 @@ enum mac80211_rx_flags { RX_FLAG_AMPDU_EOF_BIT_KNOWN = BIT(25), RX_FLAG_RADIOTAP_HE = BIT(26), RX_FLAG_RADIOTAP_HE_MU = BIT(27), + RX_FLAG_RADIOTAP_LSIG = BIT(28), + RX_FLAG_NO_PSDU = BIT(29), }; /** @@ -1242,6 +1250,7 @@ enum mac80211_rx_encoding { * @ampdu_reference: A-MPDU reference number, must be a different value for * each A-MPDU but the same for each subframe within one A-MPDU * @ampdu_delimiter_crc: A-MPDU delimiter CRC + * @zero_length_psdu_type: radiotap type of the 0-length PSDU */ struct ieee80211_rx_status { u64 mactime; @@ -1262,6 +1271,7 @@ struct ieee80211_rx_status { u8 chains; s8 chain_signal[IEEE80211_MAX_CHAINS]; u8 ampdu_delimiter_crc; + u8 zero_length_psdu_type; }; /** @@ -1504,6 +1514,8 @@ enum ieee80211_vif_flags { * @drv_priv: data area for driver use, will always be aligned to * sizeof(void \*). * @txq: the multicast data TX queue (if driver uses the TXQ abstraction) + * @txqs_stopped: per AC flag to indicate that intermediate TXQs are stopped, + * protected by fq->lock. */ struct ieee80211_vif { enum nl80211_iftype type; @@ -1528,6 +1540,8 @@ struct ieee80211_vif { unsigned int probe_req_reg; + bool txqs_stopped[IEEE80211_NUM_ACS]; + /* must be last */ u8 drv_priv[0] __aligned(sizeof(void *)); }; @@ -1839,7 +1853,9 @@ struct ieee80211_sta_rates { * unlimited. * @support_p2p_ps: indicates whether the STA supports P2P PS mechanism or not. * @max_rc_amsdu_len: Maximum A-MSDU size in bytes recommended by rate control. - * @txq: per-TID data TX queues (if driver uses the TXQ abstraction) + * @max_tid_amsdu_len: Maximum A-MSDU size in bytes for this TID + * @txq: per-TID data TX queues (if driver uses the TXQ abstraction); note that + * the last entry (%IEEE80211_NUM_TIDS) is used for non-data frames */ struct ieee80211_sta { u32 supp_rates[NUM_NL80211_BANDS]; @@ -1879,8 +1895,9 @@ struct ieee80211_sta { u16 max_amsdu_len; bool support_p2p_ps; u16 max_rc_amsdu_len; + u16 max_tid_amsdu_len[IEEE80211_NUM_TIDS]; - struct ieee80211_txq *txq[IEEE80211_NUM_TIDS]; + struct ieee80211_txq *txq[IEEE80211_NUM_TIDS + 1]; /* must be last */ u8 drv_priv[0] __aligned(sizeof(void *)); @@ -1914,7 +1931,8 @@ struct ieee80211_tx_control { * * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @sta: station table entry, %NULL for per-vif queue - * @tid: the TID for this queue (unused for per-vif queue) + * @tid: the TID for this queue (unused for per-vif queue), + * %IEEE80211_NUM_TIDS for non-data (if enabled) * @ac: the AC for this queue * @drv_priv: driver private area, sized by hw->txq_data_size * @@ -2127,6 +2145,19 @@ struct ieee80211_txq { * @IEEE80211_HW_DOESNT_SUPPORT_QOS_NDP: The driver (or firmware) doesn't * support QoS NDP for AP probing - that's most likely a driver bug. * + * @IEEE80211_HW_BUFF_MMPDU_TXQ: use the TXQ for bufferable MMPDUs, this of + * course requires the driver to use TXQs to start with. + * + * @IEEE80211_HW_SUPPORTS_VHT_EXT_NSS_BW: (Hardware) rate control supports VHT + * extended NSS BW (dot11VHTExtendedNSSBWCapable). This flag will be set if + * the selected rate control algorithm sets %RATE_CTRL_CAPA_VHT_EXT_NSS_BW + * but if the rate control is built-in then it must be set by the driver. + * See also the documentation for that flag. + * + * @IEEE80211_HW_STA_MMPDU_TXQ: use the extra non-TID per-station TXQ for all + * MMPDUs on station interfaces. This of course requires the driver to use + * TXQs to start with. + * * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays */ enum ieee80211_hw_flags { @@ -2172,6 +2203,9 @@ enum ieee80211_hw_flags { IEEE80211_HW_SUPPORTS_TDLS_BUFFER_STA, IEEE80211_HW_DEAUTH_NEED_MGD_TX_PREP, IEEE80211_HW_DOESNT_SUPPORT_QOS_NDP, + IEEE80211_HW_BUFF_MMPDU_TXQ, + IEEE80211_HW_SUPPORTS_VHT_EXT_NSS_BW, + IEEE80211_HW_STA_MMPDU_TXQ, /* keep last, obviously */ NUM_IEEE80211_HW_FLAGS @@ -2290,6 +2324,10 @@ enum ieee80211_hw_flags { * supported by HW. * @max_nan_de_entries: maximum number of NAN DE functions supported by the * device. + * + * @tx_sk_pacing_shift: Pacing shift to set on TCP sockets when frames from + * them are encountered. The default should typically not be changed, + * unless the driver has good reasons for needing more buffers. */ struct ieee80211_hw { struct ieee80211_conf conf; @@ -2325,6 +2363,7 @@ struct ieee80211_hw { u8 n_cipher_schemes; const struct ieee80211_cipher_scheme *cipher_schemes; u8 max_nan_de_entries; + u8 tx_sk_pacing_shift; }; static inline bool _ieee80211_hw_check(struct ieee80211_hw *hw, @@ -2506,6 +2545,19 @@ void ieee80211_free_txskb(struct ieee80211_hw *hw, struct sk_buff *skb); * The set_default_unicast_key() call updates the default WEP key index * configured to the hardware for WEP encryption type. This is required * for devices that support offload of data packets (e.g. ARP responses). + * + * Mac80211 drivers should set the @NL80211_EXT_FEATURE_CAN_REPLACE_PTK0 flag + * when they are able to replace in-use PTK keys according to to following + * requirements: + * 1) They do not hand over frames decrypted with the old key to + mac80211 once the call to set_key() with command %DISABLE_KEY has been + completed when also setting @IEEE80211_KEY_FLAG_GENERATE_IV for any key, + 2) either drop or continue to use the old key for any outgoing frames queued + at the time of the key deletion (including re-transmits), + 3) never send out a frame queued prior to the set_key() %SET_KEY command + encrypted with the new key and + 4) never send out a frame unencrypted when it should be encrypted. + Mac80211 will not queue any new frames for a deleted key to the driver. */ /** @@ -3542,6 +3594,10 @@ enum ieee80211_reconfig_type { * @del_nan_func: Remove a NAN function. The driver must call * ieee80211_nan_func_terminated() with * NL80211_NAN_FUNC_TERM_REASON_USER_REQUEST reason code upon removal. + * @can_aggregate_in_amsdu: Called in order to determine if HW supports + * aggregating two specific frames in the same A-MSDU. The relation + * between the skbs should be symmetric and transitive. Note that while + * skb is always a real frame, head may or may not be an A-MSDU. */ struct ieee80211_ops { void (*tx)(struct ieee80211_hw *hw, @@ -3824,6 +3880,9 @@ struct ieee80211_ops { void (*del_nan_func)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u8 instance_id); + bool (*can_aggregate_in_amsdu)(struct ieee80211_hw *hw, + struct sk_buff *head, + struct sk_buff *skb); }; /** @@ -5644,7 +5703,22 @@ struct ieee80211_tx_rate_control { bool bss; }; +/** + * enum rate_control_capabilities - rate control capabilities + */ +enum rate_control_capabilities { + /** + * @RATE_CTRL_CAPA_VHT_EXT_NSS_BW: + * Support for extended NSS BW support (dot11VHTExtendedNSSCapable) + * Note that this is only looked at if the minimum number of chains + * that the AP uses is < the number of TX chains the hardware has, + * otherwise the NSS difference doesn't bother us. + */ + RATE_CTRL_CAPA_VHT_EXT_NSS_BW = BIT(0), +}; + struct rate_control_ops { + unsigned long capa; const char *name; void *(*alloc)(struct ieee80211_hw *hw, struct dentry *debugfsdir); void (*free)(void *priv); diff --git a/include/net/netfilter/nf_conntrack_timeout.h b/include/net/netfilter/nf_conntrack_timeout.h index d5f62cc6c2ae..3394d75e1c80 100644 --- a/include/net/netfilter/nf_conntrack_timeout.h +++ b/include/net/netfilter/nf_conntrack_timeout.h @@ -30,7 +30,7 @@ struct nf_conn_timeout { }; static inline unsigned int * -nf_ct_timeout_data(struct nf_conn_timeout *t) +nf_ct_timeout_data(const struct nf_conn_timeout *t) { struct nf_ct_timeout *timeout; diff --git a/include/net/netlink.h b/include/net/netlink.h index 0c154f98e987..318b1ded3833 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -180,6 +180,9 @@ enum { NLA_S32, NLA_S64, NLA_BITFIELD32, + NLA_REJECT, + NLA_EXACT_LEN, + NLA_EXACT_LEN_WARN, __NLA_TYPE_MAX, }; @@ -208,9 +211,23 @@ enum { * NLA_MSECS Leaving the length field zero will verify the * given type fits, using it verifies minimum length * just like "All other" - * NLA_BITFIELD32 A 32-bit bitmap/bitselector attribute + * NLA_BITFIELD32 Unused + * NLA_REJECT Unused + * NLA_EXACT_LEN Attribute must have exactly this length, otherwise + * it is rejected. + * NLA_EXACT_LEN_WARN Attribute should have exactly this length, a warning + * is logged if it is longer, shorter is rejected. * All other Minimum length of attribute payload * + * Meaning of `validation_data' field: + * NLA_BITFIELD32 This is a 32-bit bitmap/bitselector attribute and + * validation data must point to a u32 value of valid + * flags + * NLA_REJECT This attribute is always rejected and validation data + * may point to a string to report as the error instead + * of the generic one in extended ACK. + * All other Unused + * * Example: * static const struct nla_policy my_policy[ATTR_MAX+1] = { * [ATTR_FOO] = { .type = NLA_U16 }, @@ -225,6 +242,13 @@ struct nla_policy { void *validation_data; }; +#define NLA_POLICY_EXACT_LEN(_len) { .type = NLA_EXACT_LEN, .len = _len } +#define NLA_POLICY_EXACT_LEN_WARN(_len) { .type = NLA_EXACT_LEN_WARN, \ + .len = _len } + +#define NLA_POLICY_ETH_ADDR NLA_POLICY_EXACT_LEN(ETH_ALEN) +#define NLA_POLICY_ETH_ADDR_COMPAT NLA_POLICY_EXACT_LEN_WARN(ETH_ALEN) + /** * struct nl_info - netlink source information * @nlh: Netlink message header of original request diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index ef727f71336e..75a3f3fdb359 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -298,19 +298,13 @@ static inline void tcf_exts_put_net(struct tcf_exts *exts) #endif } -static inline void tcf_exts_to_list(const struct tcf_exts *exts, - struct list_head *actions) -{ #ifdef CONFIG_NET_CLS_ACT - int i; - - for (i = 0; i < exts->nr_actions; i++) { - struct tc_action *a = exts->actions[i]; - - list_add_tail(&a->list, actions); - } +#define tcf_exts_for_each_action(i, a, exts) \ + for (i = 0; i < TCA_ACT_MAX_PRIO && ((a) = (exts)->actions[i]); i++) +#else +#define tcf_exts_for_each_action(i, a, exts) \ + for (; 0; (void)(i), (void)(a), (void)(exts)) #endif -} static inline void tcf_exts_stats_update(const struct tcf_exts *exts, @@ -361,6 +355,15 @@ static inline bool tcf_exts_has_one_action(struct tcf_exts *exts) #endif } +static inline struct tc_action *tcf_exts_first_action(struct tcf_exts *exts) +{ +#ifdef CONFIG_NET_CLS_ACT + return exts->actions[0]; +#else + return NULL; +#endif +} + /** * tcf_exts_exec - execute tc filter extensions * @skb: socket buffer diff --git a/include/net/regulatory.h b/include/net/regulatory.h index 60f8cc86a447..3469750df0f4 100644 --- a/include/net/regulatory.h +++ b/include/net/regulatory.h @@ -217,15 +217,15 @@ struct ieee80211_wmm_rule { struct ieee80211_reg_rule { struct ieee80211_freq_range freq_range; struct ieee80211_power_rule power_rule; - struct ieee80211_wmm_rule *wmm_rule; + struct ieee80211_wmm_rule wmm_rule; u32 flags; u32 dfs_cac_ms; + bool has_wmm; }; struct ieee80211_regdomain { struct rcu_head rcu_head; u32 n_reg_rules; - u32 n_wmm_rules; char alpha2[3]; enum nl80211_dfs_regions dfs_region; struct ieee80211_reg_rule reg_rules[]; diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 0bbaa5488423..cf26e5aacac4 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -165,6 +165,7 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm); int rtnl_nla_parse_ifla(struct nlattr **tb, const struct nlattr *head, int len, struct netlink_ext_ack *exterr); +struct net *rtnl_get_net_ns_capable(struct sock *sk, int netnsid); #define MODULE_ALIAS_RTNL_LINK(kind) MODULE_ALIAS("rtnl-link-" kind) diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index a6d00093f35e..d326fd553b58 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -362,7 +362,7 @@ static inline void tcf_block_offload_dec(struct tcf_block *block, u32 *flags) } static inline void -tc_cls_offload_cnt_update(struct tcf_block *block, unsigned int *cnt, +tc_cls_offload_cnt_update(struct tcf_block *block, u32 *cnt, u32 *flags, bool add) { if (add) { @@ -828,8 +828,8 @@ static inline void qdisc_skb_head_init(struct qdisc_skb_head *qh) qh->qlen = 0; } -static inline int __qdisc_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch, - struct qdisc_skb_head *qh) +static inline void __qdisc_enqueue_tail(struct sk_buff *skb, + struct qdisc_skb_head *qh) { struct sk_buff *last = qh->tail; @@ -842,14 +842,24 @@ static inline int __qdisc_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch, qh->head = skb; } qh->qlen++; - qdisc_qstats_backlog_inc(sch, skb); +} +static inline int qdisc_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch) +{ + __qdisc_enqueue_tail(skb, &sch->q); + qdisc_qstats_backlog_inc(sch, skb); return NET_XMIT_SUCCESS; } -static inline int qdisc_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch) +static inline void __qdisc_enqueue_head(struct sk_buff *skb, + struct qdisc_skb_head *qh) { - return __qdisc_enqueue_tail(skb, sch, &sch->q); + skb->next = qh->head; + + if (!qh->head) + qh->tail = skb; + qh->head = skb; + qh->qlen++; } static inline struct sk_buff *__qdisc_dequeue_head(struct qdisc_skb_head *qh) diff --git a/include/net/sock.h b/include/net/sock.h index 433f45fc2d68..38cae35f6e16 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -800,6 +800,7 @@ enum sock_flags { SOCK_SELECT_ERR_QUEUE, /* Wake select on error queue */ SOCK_RCU_FREE, /* wait rcu grace period in sk_destruct() */ SOCK_TXTIME, + SOCK_XDP, /* XDP is attached */ }; #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)) diff --git a/include/net/tls.h b/include/net/tls.h index d5c683e8bb22..9f3c4ea9ad6f 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -124,6 +124,8 @@ struct tls_sw_context_rx { struct sk_buff *recv_pkt; u8 control; bool decrypted; + atomic_t decrypt_pending; + bool async_notify; }; struct tls_record_info { @@ -171,15 +173,14 @@ struct cipher_context { char *rec_seq; }; +union tls_crypto_context { + struct tls_crypto_info info; + struct tls12_crypto_info_aes_gcm_128 aes_gcm_128; +}; + struct tls_context { - union { - struct tls_crypto_info crypto_send; - struct tls12_crypto_info_aes_gcm_128 crypto_send_aes_gcm_128; - }; - union { - struct tls_crypto_info crypto_recv; - struct tls12_crypto_info_aes_gcm_128 crypto_recv_aes_gcm_128; - }; + union tls_crypto_context crypto_send; + union tls_crypto_context crypto_recv; struct list_head list; struct net_device *netdev; @@ -367,8 +368,8 @@ static inline void tls_fill_prepend(struct tls_context *ctx, * size KTLS_DTLS_HEADER_SIZE + KTLS_DTLS_NONCE_EXPLICIT_SIZE */ buf[0] = record_type; - buf[1] = TLS_VERSION_MINOR(ctx->crypto_send.version); - buf[2] = TLS_VERSION_MAJOR(ctx->crypto_send.version); + buf[1] = TLS_VERSION_MINOR(ctx->crypto_send.info.version); + buf[2] = TLS_VERSION_MAJOR(ctx->crypto_send.info.version); /* we can use IV for nonce explicit according to spec */ buf[3] = pkt_len >> 8; buf[4] = pkt_len & 0xFF; diff --git a/include/net/vxlan.h b/include/net/vxlan.h index b99a02ae3934..7ef15179f263 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -5,7 +5,6 @@ #include <linux/if_vlan.h> #include <net/udp_tunnel.h> #include <net/dst_metadata.h> -#include <net/udp_tunnel.h> /* VXLAN protocol (RFC 7348) header: * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ diff --git a/include/net/xdp.h b/include/net/xdp.h index 76b95256c266..0f25b3675c5c 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -91,6 +91,8 @@ static inline void xdp_scrub_frame(struct xdp_frame *frame) frame->dev_rx = NULL; } +struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp); + /* Convert xdp_buff to xdp_frame */ static inline struct xdp_frame *convert_to_xdp_frame(struct xdp_buff *xdp) @@ -99,9 +101,8 @@ struct xdp_frame *convert_to_xdp_frame(struct xdp_buff *xdp) int metasize; int headroom; - /* TODO: implement clone, copy, use "native" MEM_TYPE */ if (xdp->rxq->mem.type == MEM_TYPE_ZERO_COPY) - return NULL; + return xdp_convert_zc_to_xdp_frame(xdp); /* Assure headroom is available for storing info */ headroom = xdp->data - xdp->data_hard_start; @@ -135,6 +136,7 @@ void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq); bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq); int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq, enum xdp_mem_type type, void *allocator); +void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq); /* Drivers not supporting XDP metadata can use this helper, which * rejects any room expansion for metadata as a result. diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 7161856bcf9c..932ca0dad6f3 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -16,11 +16,6 @@ struct net_device; struct xsk_queue; -struct xdp_umem_props { - u64 chunk_mask; - u64 size; -}; - struct xdp_umem_page { void *addr; dma_addr_t dma; @@ -30,7 +25,8 @@ struct xdp_umem { struct xsk_queue *fq; struct xsk_queue *cq; struct xdp_umem_page *pages; - struct xdp_umem_props props; + u64 chunk_mask; + u64 size; u32 headroom; u32 chunk_size_nohr; struct user_struct *user; @@ -79,6 +75,16 @@ void xsk_umem_discard_addr(struct xdp_umem *umem); void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries); bool xsk_umem_consume_tx(struct xdp_umem *umem, dma_addr_t *dma, u32 *len); void xsk_umem_consume_tx_done(struct xdp_umem *umem); + +static inline char *xdp_umem_get_data(struct xdp_umem *umem, u64 addr) +{ + return umem->pages[addr >> PAGE_SHIFT].addr + (addr & (PAGE_SIZE - 1)); +} + +static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr) +{ + return umem->pages[addr >> PAGE_SHIFT].dma + (addr & (PAGE_SIZE - 1)); +} #else static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) { @@ -98,6 +104,39 @@ static inline bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs) { return false; } + +static inline u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr) +{ + return NULL; +} + +static inline void xsk_umem_discard_addr(struct xdp_umem *umem) +{ +} + +static inline void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries) +{ +} + +static inline bool xsk_umem_consume_tx(struct xdp_umem *umem, dma_addr_t *dma, + u32 *len) +{ + return false; +} + +static inline void xsk_umem_consume_tx_done(struct xdp_umem *umem) +{ +} + +static inline char *xdp_umem_get_data(struct xdp_umem *umem, u64 addr) +{ + return NULL; +} + +static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr) +{ + return 0; +} #endif /* CONFIG_XDP_SOCKETS */ #endif /* _LINUX_XDP_SOCK_H */ diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index dc69391d2bba..c8f8e2455bf3 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -91,10 +91,6 @@ * %ETHTOOL_GSET to get the current values before making specific * changes and then applying them with %ETHTOOL_SSET. * - * Drivers that implement set_settings() should validate all fields - * other than @cmd that are not described as read-only or deprecated, - * and must ignore all fields described as read-only. - * * Deprecated fields should be ignored by both users and drivers. */ struct ethtool_cmd { @@ -1800,14 +1796,9 @@ enum ethtool_reset_flags { * rejected. * * Deprecated %ethtool_cmd fields transceiver, maxtxpkt and maxrxpkt - * are not available in %ethtool_link_settings. Until all drivers are - * converted to ignore them or to the new %ethtool_link_settings API, - * for both queries and changes, users should always try - * %ETHTOOL_GLINKSETTINGS first, and if it fails with -ENOTSUPP stick - * only to %ETHTOOL_GSET and %ETHTOOL_SSET consistently. If it - * succeeds, then users should stick to %ETHTOOL_GLINKSETTINGS and - * %ETHTOOL_SLINKSETTINGS (which would support drivers implementing - * either %ethtool_cmd or %ethtool_link_settings). + * are not available in %ethtool_link_settings. These fields will be + * always set to zero in %ETHTOOL_GSET reply and %ETHTOOL_SSET will + * fail if any of them is set to non-zero value. * * Users should assume that all fields not marked read-only are * writable and subject to validation by the driver. They should use diff --git a/include/uapi/linux/if_addr.h b/include/uapi/linux/if_addr.h index ebaf5701c9db..dfcf3ce0097f 100644 --- a/include/uapi/linux/if_addr.h +++ b/include/uapi/linux/if_addr.h @@ -34,6 +34,7 @@ enum { IFA_MULTICAST, IFA_FLAGS, IFA_RT_PRIORITY, /* u32, priority/metric for prefix route */ + IFA_TARGET_NETNSID, __IFA_MAX, }; diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 43391e2d1153..58faab897201 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -161,6 +161,7 @@ enum { IFLA_EVENT, IFLA_NEW_NETNSID, IFLA_IF_NETNSID, + IFLA_TARGET_NETNSID = IFLA_IF_NETNSID, /* new alias */ IFLA_CARRIER_UP_COUNT, IFLA_CARRIER_DOWN_COUNT, IFLA_NEW_IFINDEX, @@ -554,6 +555,7 @@ enum { IFLA_GENEVE_UDP_ZERO_CSUM6_TX, IFLA_GENEVE_UDP_ZERO_CSUM6_RX, IFLA_GENEVE_LABEL, + IFLA_GENEVE_TTL_INHERIT, __IFLA_GENEVE_MAX }; #define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1) diff --git a/include/uapi/linux/if_packet.h b/include/uapi/linux/if_packet.h index 67b61d91d89b..467b654bd4c7 100644 --- a/include/uapi/linux/if_packet.h +++ b/include/uapi/linux/if_packet.h @@ -57,6 +57,7 @@ struct sockaddr_ll { #define PACKET_QDISC_BYPASS 20 #define PACKET_ROLLOVER_STATS 21 #define PACKET_FANOUT_DATA 22 +#define PACKET_IGNORE_OUTGOING 23 #define PACKET_FANOUT_HASH 0 #define PACKET_FANOUT_LB 1 diff --git a/include/uapi/linux/in6.h b/include/uapi/linux/in6.h index ed291e55f024..71d82fe15b03 100644 --- a/include/uapi/linux/in6.h +++ b/include/uapi/linux/in6.h @@ -177,6 +177,7 @@ struct in6_flowlabel_req { #define IPV6_V6ONLY 26 #define IPV6_JOIN_ANYCAST 27 #define IPV6_LEAVE_ANYCAST 28 +#define IPV6_MULTICAST_ALL 29 /* IPV6_MTU_DISCOVER values */ #define IPV6_PMTUDISC_DONT 0 diff --git a/include/uapi/linux/keyctl.h b/include/uapi/linux/keyctl.h index 7b8c9e19bad1..910cc4334b21 100644 --- a/include/uapi/linux/keyctl.h +++ b/include/uapi/linux/keyctl.h @@ -65,7 +65,7 @@ /* keyctl structures */ struct keyctl_dh_params { - __s32 private; + __s32 dh_private; __s32 prime; __s32 base; }; diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h index 904db6148476..998155444e0d 100644 --- a/include/uapi/linux/neighbour.h +++ b/include/uapi/linux/neighbour.h @@ -43,6 +43,7 @@ enum { #define NTF_PROXY 0x08 /* == ATF_PUBL */ #define NTF_EXT_LEARNED 0x10 #define NTF_OFFLOADED 0x20 +#define NTF_STICKY 0x40 #define NTF_ROUTER 0x80 /* diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 7acc16f34942..cfc94178d608 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3050,8 +3050,7 @@ enum nl80211_sta_bss_param { * received from the station (u64, usec) * @NL80211_STA_INFO_PAD: attribute used for padding for 64-bit alignment * @NL80211_STA_INFO_ACK_SIGNAL: signal strength of the last ACK frame(u8, dBm) - * @NL80211_STA_INFO_DATA_ACK_SIGNAL_AVG: avg signal strength of (data) - * ACK frame (s8, dBm) + * @NL80211_STA_INFO_ACK_SIGNAL_AVG: avg signal strength of ACK frames (s8, dBm) * @__NL80211_STA_INFO_AFTER_LAST: internal * @NL80211_STA_INFO_MAX: highest possible station info attribute */ @@ -3091,13 +3090,17 @@ enum nl80211_sta_info { NL80211_STA_INFO_RX_DURATION, NL80211_STA_INFO_PAD, NL80211_STA_INFO_ACK_SIGNAL, - NL80211_STA_INFO_DATA_ACK_SIGNAL_AVG, + NL80211_STA_INFO_ACK_SIGNAL_AVG, /* keep last */ __NL80211_STA_INFO_AFTER_LAST, NL80211_STA_INFO_MAX = __NL80211_STA_INFO_AFTER_LAST - 1 }; +/* we renamed this - stay compatible */ +#define NL80211_STA_INFO_DATA_ACK_SIGNAL_AVG NL80211_STA_INFO_ACK_SIGNAL_AVG + + /** * enum nl80211_tid_stats - per TID statistics attributes * @__NL80211_TID_STATS_INVALID: attribute number 0 is reserved @@ -4338,7 +4341,7 @@ enum nl80211_txrate_gi { * enum nl80211_band - Frequency band * @NL80211_BAND_2GHZ: 2.4 GHz ISM band * @NL80211_BAND_5GHZ: around 5 GHz band (4.9 - 5.7 GHz) - * @NL80211_BAND_60GHZ: around 60 GHz band (58.32 - 64.80 GHz) + * @NL80211_BAND_60GHZ: around 60 GHz band (58.32 - 69.12 GHz) * @NUM_NL80211_BANDS: number of bands, avoid using this in userspace * since newer kernel versions may support more bands */ @@ -5213,9 +5216,8 @@ enum nl80211_feature_flags { * "radar detected" event. * @NL80211_EXT_FEATURE_CONTROL_PORT_OVER_NL80211: Driver supports sending and * receiving control port frames over nl80211 instead of the netdevice. - * @NL80211_EXT_FEATURE_DATA_ACK_SIGNAL_SUPPORT: This Driver support data ack - * rssi if firmware support, this flag is to intimate about ack rssi - * support to nl80211. + * @NL80211_EXT_FEATURE_ACK_SIGNAL_SUPPORT: This driver/device supports + * (average) ACK signal strength reporting. * @NL80211_EXT_FEATURE_TXQS: Driver supports FQ-CoDel-enabled intermediate * TXQs. * @NL80211_EXT_FEATURE_SCAN_RANDOM_SN: Driver/device supports randomizing the @@ -5224,6 +5226,11 @@ enum nl80211_feature_flags { * except for supported rates from the probe request content if requested * by the %NL80211_SCAN_FLAG_MIN_PREQ_CONTENT flag. * + * @NL80211_EXT_FEATURE_CAN_REPLACE_PTK0: Driver/device confirm that they are + * able to rekey an in-use key correctly. Userspace must not rekey PTK keys + * if this flag is not set. Ignoring this can leak clear text packets and/or + * freeze the connection. + * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@ -5255,10 +5262,13 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_HIGH_ACCURACY_SCAN, NL80211_EXT_FEATURE_DFS_OFFLOAD, NL80211_EXT_FEATURE_CONTROL_PORT_OVER_NL80211, - NL80211_EXT_FEATURE_DATA_ACK_SIGNAL_SUPPORT, + NL80211_EXT_FEATURE_ACK_SIGNAL_SUPPORT, + /* we renamed this - stay compatible */ + NL80211_EXT_FEATURE_DATA_ACK_SIGNAL_SUPPORT = NL80211_EXT_FEATURE_ACK_SIGNAL_SUPPORT, NL80211_EXT_FEATURE_TXQS, NL80211_EXT_FEATURE_SCAN_RANDOM_SN, NL80211_EXT_FEATURE_SCAN_MIN_PREQ_CONTENT, + NL80211_EXT_FEATURE_CAN_REPLACE_PTK0, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index eeb787b1c53c..f35eb72739c0 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -144,7 +144,7 @@ enum perf_event_sample_format { PERF_SAMPLE_MAX = 1U << 20, /* non-ABI */ - __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, + __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, /* non-ABI; internal use */ }; /* diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index be382fb0592d..401d0c1e612d 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -483,6 +483,8 @@ enum { TCA_FLOWER_KEY_ENC_OPTS, TCA_FLOWER_KEY_ENC_OPTS_MASK, + TCA_FLOWER_IN_HW_COUNT, + __TCA_FLOWER_MAX, }; diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 8975fd1a1421..e9b7244ac381 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -395,9 +395,9 @@ enum { struct tc_htb_xstats { __u32 lends; __u32 borrows; - __u32 giants; /* too big packets (rate will not be accurate) */ - __u32 tokens; - __u32 ctokens; + __u32 giants; /* unused since 'Make HTB scheduler work with TSO.' */ + __s32 tokens; + __s32 ctokens; }; /* HFSC section */ diff --git a/include/uapi/linux/rds.h b/include/uapi/linux/rds.h index dc520e1a4123..8b73cb603c5f 100644 --- a/include/uapi/linux/rds.h +++ b/include/uapi/linux/rds.h @@ -37,6 +37,7 @@ #include <linux/types.h> #include <linux/socket.h> /* For __kernel_sockaddr_storage. */ +#include <linux/in6.h> /* For struct in6_addr. */ #define RDS_IB_ABI_VERSION 0x301 diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h index b1e22c40c4b6..84c3de89696a 100644 --- a/include/uapi/linux/vhost.h +++ b/include/uapi/linux/vhost.h @@ -176,7 +176,7 @@ struct vhost_memory { #define VHOST_BACKEND_F_IOTLB_MSG_V2 0x1 #define VHOST_SET_BACKEND_FEATURES _IOW(VHOST_VIRTIO, 0x25, __u64) -#define VHOST_GET_BACKEND_FEATURES _IOW(VHOST_VIRTIO, 0x26, __u64) +#define VHOST_GET_BACKEND_FEATURES _IOR(VHOST_VIRTIO, 0x26, __u64) /* VHOST_NET specific defines */ diff --git a/include/xen/mem-reservation.h b/include/xen/mem-reservation.h index 80b52b4945e9..a2ab516fcd2c 100644 --- a/include/xen/mem-reservation.h +++ b/include/xen/mem-reservation.h @@ -17,11 +17,12 @@ #include <xen/page.h> +extern bool xen_scrub_pages; + static inline void xenmem_reservation_scrub_page(struct page *page) { -#ifdef CONFIG_XEN_SCRUB_PAGES - clear_highpage(page); -#endif + if (xen_scrub_pages) + clear_highpage(page); } #ifdef CONFIG_XEN_HAVE_PVMMU diff --git a/ipc/shm.c b/ipc/shm.c index b0eb3757ab89..4cd402e4cfeb 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -199,6 +199,7 @@ static inline struct shmid_kernel *shm_lock(struct ipc_namespace *ns, int id) } ipc_unlock_object(ipcp); + ipcp = ERR_PTR(-EIDRM); err: rcu_read_unlock(); /* diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 0c17aab3ce5f..f9d24121be99 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -358,6 +358,29 @@ static void array_map_seq_show_elem(struct bpf_map *map, void *key, rcu_read_unlock(); } +static void percpu_array_map_seq_show_elem(struct bpf_map *map, void *key, + struct seq_file *m) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + u32 index = *(u32 *)key; + void __percpu *pptr; + int cpu; + + rcu_read_lock(); + + seq_printf(m, "%u: {\n", *(u32 *)key); + pptr = array->pptrs[index & array->index_mask]; + for_each_possible_cpu(cpu) { + seq_printf(m, "\tcpu%d: ", cpu); + btf_type_seq_show(map->btf, map->btf_value_type_id, + per_cpu_ptr(pptr, cpu), m); + seq_puts(m, "\n"); + } + seq_puts(m, "}\n"); + + rcu_read_unlock(); +} + static int array_map_check_btf(const struct bpf_map *map, const struct btf_type *key_type, const struct btf_type *value_type) @@ -398,6 +421,7 @@ const struct bpf_map_ops percpu_array_map_ops = { .map_lookup_elem = percpu_array_map_lookup_elem, .map_update_elem = array_map_update_elem, .map_delete_elem = array_map_delete_elem, + .map_seq_show_elem = percpu_array_map_seq_show_elem, .map_check_btf = array_map_check_btf, }; diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 2590700237c1..138f0302692e 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -1844,7 +1844,7 @@ static int btf_check_all_metas(struct btf_verifier_env *env) hdr = &btf->hdr; cur = btf->nohdr_data + hdr->type_off; - end = btf->nohdr_data + hdr->type_len; + end = cur + hdr->type_len; env->log_type_id = 1; while (cur < end) { diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 04b8eda94e7d..2c1790288138 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -15,6 +15,7 @@ #include <linux/jhash.h> #include <linux/filter.h> #include <linux/rculist_nulls.h> +#include <linux/random.h> #include <uapi/linux/btf.h> #include "percpu_freelist.h" #include "bpf_lru_list.h" @@ -41,6 +42,7 @@ struct bpf_htab { atomic_t count; /* number of elements in this hashtable */ u32 n_buckets; /* number of hash buckets */ u32 elem_size; /* size of each element in bytes */ + u32 hashrnd; }; /* each htab element is struct htab_elem + key + value */ @@ -371,6 +373,7 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) if (!htab->buckets) goto free_htab; + htab->hashrnd = get_random_int(); for (i = 0; i < htab->n_buckets; i++) { INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i); raw_spin_lock_init(&htab->buckets[i].lock); @@ -402,9 +405,9 @@ free_htab: return ERR_PTR(err); } -static inline u32 htab_map_hash(const void *key, u32 key_len) +static inline u32 htab_map_hash(const void *key, u32 key_len, u32 hashrnd) { - return jhash(key, key_len, 0); + return jhash(key, key_len, hashrnd); } static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash) @@ -470,7 +473,7 @@ static void *__htab_map_lookup_elem(struct bpf_map *map, void *key) key_size = map->key_size; - hash = htab_map_hash(key, key_size); + hash = htab_map_hash(key, key_size, htab->hashrnd); head = select_bucket(htab, hash); @@ -597,7 +600,7 @@ static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key) if (!key) goto find_first_elem; - hash = htab_map_hash(key, key_size); + hash = htab_map_hash(key, key_size, htab->hashrnd); head = select_bucket(htab, hash); @@ -824,7 +827,7 @@ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, key_size = map->key_size; - hash = htab_map_hash(key, key_size); + hash = htab_map_hash(key, key_size, htab->hashrnd); b = __select_bucket(htab, hash); head = &b->head; @@ -880,7 +883,7 @@ static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value, key_size = map->key_size; - hash = htab_map_hash(key, key_size); + hash = htab_map_hash(key, key_size, htab->hashrnd); b = __select_bucket(htab, hash); head = &b->head; @@ -945,7 +948,7 @@ static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key, key_size = map->key_size; - hash = htab_map_hash(key, key_size); + hash = htab_map_hash(key, key_size, htab->hashrnd); b = __select_bucket(htab, hash); head = &b->head; @@ -998,7 +1001,7 @@ static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, key_size = map->key_size; - hash = htab_map_hash(key, key_size); + hash = htab_map_hash(key, key_size, htab->hashrnd); b = __select_bucket(htab, hash); head = &b->head; @@ -1071,7 +1074,7 @@ static int htab_map_delete_elem(struct bpf_map *map, void *key) key_size = map->key_size; - hash = htab_map_hash(key, key_size); + hash = htab_map_hash(key, key_size, htab->hashrnd); b = __select_bucket(htab, hash); head = &b->head; @@ -1103,7 +1106,7 @@ static int htab_lru_map_delete_elem(struct bpf_map *map, void *key) key_size = map->key_size; - hash = htab_map_hash(key, key_size); + hash = htab_map_hash(key, key_size, htab->hashrnd); b = __select_bucket(htab, hash); head = &b->head; @@ -1282,6 +1285,35 @@ int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value, return ret; } +static void htab_percpu_map_seq_show_elem(struct bpf_map *map, void *key, + struct seq_file *m) +{ + struct htab_elem *l; + void __percpu *pptr; + int cpu; + + rcu_read_lock(); + + l = __htab_map_lookup_elem(map, key); + if (!l) { + rcu_read_unlock(); + return; + } + + btf_type_seq_show(map->btf, map->btf_key_type_id, key, m); + seq_puts(m, ": {\n"); + pptr = htab_elem_get_ptr(l, map->key_size); + for_each_possible_cpu(cpu) { + seq_printf(m, "\tcpu%d: ", cpu); + btf_type_seq_show(map->btf, map->btf_value_type_id, + per_cpu_ptr(pptr, cpu), m); + seq_puts(m, "\n"); + } + seq_puts(m, "}\n"); + + rcu_read_unlock(); +} + const struct bpf_map_ops htab_percpu_map_ops = { .map_alloc_check = htab_map_alloc_check, .map_alloc = htab_map_alloc, @@ -1290,6 +1322,7 @@ const struct bpf_map_ops htab_percpu_map_ops = { .map_lookup_elem = htab_percpu_map_lookup_elem, .map_update_elem = htab_percpu_map_update_elem, .map_delete_elem = htab_map_delete_elem, + .map_seq_show_elem = htab_percpu_map_seq_show_elem, }; const struct bpf_map_ops htab_lru_percpu_map_ops = { @@ -1300,6 +1333,7 @@ const struct bpf_map_ops htab_lru_percpu_map_ops = { .map_lookup_elem = htab_lru_percpu_map_lookup_elem, .map_update_elem = htab_lru_percpu_map_update_elem, .map_delete_elem = htab_lru_map_delete_elem, + .map_seq_show_elem = htab_percpu_map_seq_show_elem, }; static int fd_htab_map_alloc_check(union bpf_attr *attr) diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 98e621a29e8e..488ef9663c01 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -236,7 +236,7 @@ static int bpf_tcp_init(struct sock *sk) } static void smap_release_sock(struct smap_psock *psock, struct sock *sock); -static int free_start_sg(struct sock *sk, struct sk_msg_buff *md); +static int free_start_sg(struct sock *sk, struct sk_msg_buff *md, bool charge); static void bpf_tcp_release(struct sock *sk) { @@ -248,7 +248,7 @@ static void bpf_tcp_release(struct sock *sk) goto out; if (psock->cork) { - free_start_sg(psock->sock, psock->cork); + free_start_sg(psock->sock, psock->cork, true); kfree(psock->cork); psock->cork = NULL; } @@ -330,14 +330,14 @@ static void bpf_tcp_close(struct sock *sk, long timeout) close_fun = psock->save_close; if (psock->cork) { - free_start_sg(psock->sock, psock->cork); + free_start_sg(psock->sock, psock->cork, true); kfree(psock->cork); psock->cork = NULL; } list_for_each_entry_safe(md, mtmp, &psock->ingress, list) { list_del(&md->list); - free_start_sg(psock->sock, md); + free_start_sg(psock->sock, md, true); kfree(md); } @@ -369,7 +369,7 @@ static void bpf_tcp_close(struct sock *sk, long timeout) /* If another thread deleted this object skip deletion. * The refcnt on psock may or may not be zero. */ - if (l) { + if (l && l == link) { hlist_del_rcu(&link->hash_node); smap_release_sock(psock, link->sk); free_htab_elem(htab, link); @@ -570,14 +570,16 @@ static void free_bytes_sg(struct sock *sk, int bytes, md->sg_start = i; } -static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md) +static int free_sg(struct sock *sk, int start, + struct sk_msg_buff *md, bool charge) { struct scatterlist *sg = md->sg_data; int i = start, free = 0; while (sg[i].length) { free += sg[i].length; - sk_mem_uncharge(sk, sg[i].length); + if (charge) + sk_mem_uncharge(sk, sg[i].length); if (!md->skb) put_page(sg_page(&sg[i])); sg[i].length = 0; @@ -594,9 +596,9 @@ static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md) return free; } -static int free_start_sg(struct sock *sk, struct sk_msg_buff *md) +static int free_start_sg(struct sock *sk, struct sk_msg_buff *md, bool charge) { - int free = free_sg(sk, md->sg_start, md); + int free = free_sg(sk, md->sg_start, md, charge); md->sg_start = md->sg_end; return free; @@ -604,7 +606,7 @@ static int free_start_sg(struct sock *sk, struct sk_msg_buff *md) static int free_curr_sg(struct sock *sk, struct sk_msg_buff *md) { - return free_sg(sk, md->sg_curr, md); + return free_sg(sk, md->sg_curr, md, true); } static int bpf_map_msg_verdict(int _rc, struct sk_msg_buff *md) @@ -718,7 +720,7 @@ static int bpf_tcp_ingress(struct sock *sk, int apply_bytes, list_add_tail(&r->list, &psock->ingress); sk->sk_data_ready(sk); } else { - free_start_sg(sk, r); + free_start_sg(sk, r, true); kfree(r); } @@ -752,14 +754,10 @@ static int bpf_tcp_sendmsg_do_redirect(struct sock *sk, int send, release_sock(sk); } smap_release_sock(psock, sk); - if (unlikely(err)) - goto out; - return 0; + return err; out_rcu: rcu_read_unlock(); -out: - free_bytes_sg(NULL, send, md, false); - return err; + return 0; } static inline void bpf_md_init(struct smap_psock *psock) @@ -822,7 +820,7 @@ more_data: case __SK_PASS: err = bpf_tcp_push(sk, send, m, flags, true); if (unlikely(err)) { - *copied -= free_start_sg(sk, m); + *copied -= free_start_sg(sk, m, true); break; } @@ -845,16 +843,17 @@ more_data: lock_sock(sk); if (unlikely(err < 0)) { - free_start_sg(sk, m); + int free = free_start_sg(sk, m, false); + psock->sg_size = 0; if (!cork) - *copied -= send; + *copied -= free; } else { psock->sg_size -= send; } if (cork) { - free_start_sg(sk, m); + free_start_sg(sk, m, true); psock->sg_size = 0; kfree(m); m = NULL; @@ -912,6 +911,8 @@ static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); + if (!skb_queue_empty(&sk->sk_receive_queue)) + return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); rcu_read_lock(); psock = smap_psock_sk(sk); @@ -922,9 +923,6 @@ static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, goto out; rcu_read_unlock(); - if (!skb_queue_empty(&sk->sk_receive_queue)) - return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); - lock_sock(sk); bytes_ready: while (copied != len) { @@ -1122,7 +1120,7 @@ wait_for_memory: err = sk_stream_wait_memory(sk, &timeo); if (err) { if (m && m != psock->cork) - free_start_sg(sk, m); + free_start_sg(sk, m, true); goto out_err; } } @@ -1427,12 +1425,15 @@ out: static void smap_write_space(struct sock *sk) { struct smap_psock *psock; + void (*write_space)(struct sock *sk); rcu_read_lock(); psock = smap_psock_sk(sk); if (likely(psock && test_bit(SMAP_TX_RUNNING, &psock->state))) schedule_work(&psock->tx_work); + write_space = psock->save_write_space; rcu_read_unlock(); + write_space(sk); } static void smap_stop_sock(struct smap_psock *psock, struct sock *sk) @@ -1461,10 +1462,16 @@ static void smap_destroy_psock(struct rcu_head *rcu) schedule_work(&psock->gc_work); } +static bool psock_is_smap_sk(struct sock *sk) +{ + return inet_csk(sk)->icsk_ulp_ops == &bpf_tcp_ulp_ops; +} + static void smap_release_sock(struct smap_psock *psock, struct sock *sock) { if (refcount_dec_and_test(&psock->refcnt)) { - tcp_cleanup_ulp(sock); + if (psock_is_smap_sk(sock)) + tcp_cleanup_ulp(sock); write_lock_bh(&sock->sk_callback_lock); smap_stop_sock(psock, sock); write_unlock_bh(&sock->sk_callback_lock); @@ -1578,13 +1585,13 @@ static void smap_gc_work(struct work_struct *w) bpf_prog_put(psock->bpf_tx_msg); if (psock->cork) { - free_start_sg(psock->sock, psock->cork); + free_start_sg(psock->sock, psock->cork, true); kfree(psock->cork); } list_for_each_entry_safe(md, mtmp, &psock->ingress, list) { list_del(&md->list); - free_start_sg(psock->sock, md); + free_start_sg(psock->sock, md, true); kfree(md); } @@ -1891,6 +1898,10 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map, * doesn't update user data. */ if (psock) { + if (!psock_is_smap_sk(sock)) { + err = -EBUSY; + goto out_progs; + } if (READ_ONCE(psock->bpf_parse) && parse) { err = -EBUSY; goto out_progs; @@ -2140,7 +2151,9 @@ static struct bpf_map *sock_hash_alloc(union bpf_attr *attr) return ERR_PTR(-EPERM); /* check sanity of attributes */ - if (attr->max_entries == 0 || attr->value_size != 4 || + if (attr->max_entries == 0 || + attr->key_size == 0 || + attr->value_size != 4 || attr->map_flags & ~SOCK_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); @@ -2267,8 +2280,10 @@ static struct htab_elem *alloc_sock_hash_elem(struct bpf_htab *htab, } l_new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN, htab->map.numa_node); - if (!l_new) + if (!l_new) { + atomic_dec(&htab->count); return ERR_PTR(-ENOMEM); + } memcpy(l_new->key, key, key_size); l_new->sk = sk; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 8339d81cba1d..3c9636f03bb2 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -30,7 +30,6 @@ #include <linux/cred.h> #include <linux/timekeeping.h> #include <linux/ctype.h> -#include <linux/btf.h> #include <linux/nospec.h> #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 92246117d2b0..8cd4f5306c3c 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -263,6 +263,13 @@ static const char * const reg_type_str[] = { [PTR_TO_PACKET_END] = "pkt_end", }; +static char slot_type_char[] = { + [STACK_INVALID] = '?', + [STACK_SPILL] = 'r', + [STACK_MISC] = 'm', + [STACK_ZERO] = '0', +}; + static void print_liveness(struct bpf_verifier_env *env, enum bpf_reg_liveness live) { @@ -349,15 +356,26 @@ static void print_verifier_state(struct bpf_verifier_env *env, } } for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { - if (state->stack[i].slot_type[0] == STACK_SPILL) { - verbose(env, " fp%d", - (-i - 1) * BPF_REG_SIZE); - print_liveness(env, state->stack[i].spilled_ptr.live); + char types_buf[BPF_REG_SIZE + 1]; + bool valid = false; + int j; + + for (j = 0; j < BPF_REG_SIZE; j++) { + if (state->stack[i].slot_type[j] != STACK_INVALID) + valid = true; + types_buf[j] = slot_type_char[ + state->stack[i].slot_type[j]]; + } + types_buf[BPF_REG_SIZE] = 0; + if (!valid) + continue; + verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); + print_liveness(env, state->stack[i].spilled_ptr.live); + if (state->stack[i].slot_type[0] == STACK_SPILL) verbose(env, "=%s", reg_type_str[state->stack[i].spilled_ptr.type]); - } - if (state->stack[i].slot_type[0] == STACK_ZERO) - verbose(env, " fp%d=0", (-i - 1) * BPF_REG_SIZE); + else + verbose(env, "=%s", types_buf); } verbose(env, "\n"); } @@ -380,9 +398,9 @@ static int copy_stack_state(struct bpf_func_state *dst, /* do_check() starts with zero-sized stack in struct bpf_verifier_state to * make it consume minimal amount of memory. check_stack_write() access from * the program calls into realloc_func_state() to grow the stack size. - * Note there is a non-zero 'parent' pointer inside bpf_verifier_state - * which this function copies over. It points to previous bpf_verifier_state - * which is never reallocated + * Note there is a non-zero parent pointer inside each reg of bpf_verifier_state + * which this function copies over. It points to corresponding reg in previous + * bpf_verifier_state which is never reallocated */ static int realloc_func_state(struct bpf_func_state *state, int size, bool copy_old) @@ -466,7 +484,6 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state, dst_state->frame[i] = NULL; } dst_state->curframe = src->curframe; - dst_state->parent = src->parent; for (i = 0; i <= src->curframe; i++) { dst = dst_state->frame[i]; if (!dst) { @@ -732,6 +749,7 @@ static void init_reg_state(struct bpf_verifier_env *env, for (i = 0; i < MAX_BPF_REG; i++) { mark_reg_not_init(env, regs, i); regs[i].live = REG_LIVE_NONE; + regs[i].parent = NULL; } /* frame pointer */ @@ -876,74 +894,21 @@ next: return 0; } -static -struct bpf_verifier_state *skip_callee(struct bpf_verifier_env *env, - const struct bpf_verifier_state *state, - struct bpf_verifier_state *parent, - u32 regno) -{ - struct bpf_verifier_state *tmp = NULL; - - /* 'parent' could be a state of caller and - * 'state' could be a state of callee. In such case - * parent->curframe < state->curframe - * and it's ok for r1 - r5 registers - * - * 'parent' could be a callee's state after it bpf_exit-ed. - * In such case parent->curframe > state->curframe - * and it's ok for r0 only - */ - if (parent->curframe == state->curframe || - (parent->curframe < state->curframe && - regno >= BPF_REG_1 && regno <= BPF_REG_5) || - (parent->curframe > state->curframe && - regno == BPF_REG_0)) - return parent; - - if (parent->curframe > state->curframe && - regno >= BPF_REG_6) { - /* for callee saved regs we have to skip the whole chain - * of states that belong to callee and mark as LIVE_READ - * the registers before the call - */ - tmp = parent; - while (tmp && tmp->curframe != state->curframe) { - tmp = tmp->parent; - } - if (!tmp) - goto bug; - parent = tmp; - } else { - goto bug; - } - return parent; -bug: - verbose(env, "verifier bug regno %d tmp %p\n", regno, tmp); - verbose(env, "regno %d parent frame %d current frame %d\n", - regno, parent->curframe, state->curframe); - return NULL; -} - +/* Parentage chain of this register (or stack slot) should take care of all + * issues like callee-saved registers, stack slot allocation time, etc. + */ static int mark_reg_read(struct bpf_verifier_env *env, - const struct bpf_verifier_state *state, - struct bpf_verifier_state *parent, - u32 regno) + const struct bpf_reg_state *state, + struct bpf_reg_state *parent) { bool writes = parent == state->parent; /* Observe write marks */ - if (regno == BPF_REG_FP) - /* We don't need to worry about FP liveness because it's read-only */ - return 0; - while (parent) { /* if read wasn't screened by an earlier write ... */ - if (writes && state->frame[state->curframe]->regs[regno].live & REG_LIVE_WRITTEN) + if (writes && state->live & REG_LIVE_WRITTEN) break; - parent = skip_callee(env, state, parent, regno); - if (!parent) - return -EFAULT; /* ... then we depend on parent's value */ - parent->frame[parent->curframe]->regs[regno].live |= REG_LIVE_READ; + parent->live |= REG_LIVE_READ; state = parent; parent = state->parent; writes = true; @@ -969,7 +934,10 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, verbose(env, "R%d !read_ok\n", regno); return -EACCES; } - return mark_reg_read(env, vstate, vstate->parent, regno); + /* We don't need to worry about FP liveness because it's read-only */ + if (regno != BPF_REG_FP) + return mark_reg_read(env, ®s[regno], + regs[regno].parent); } else { /* check whether register used as dest operand can be written to */ if (regno == BPF_REG_FP) { @@ -1080,8 +1048,8 @@ static int check_stack_write(struct bpf_verifier_env *env, } else { u8 type = STACK_MISC; - /* regular write of data into stack */ - state->stack[spi].spilled_ptr = (struct bpf_reg_state) {}; + /* regular write of data into stack destroys any spilled ptr */ + state->stack[spi].spilled_ptr.type = NOT_INIT; /* only mark the slot as written if all 8 bytes were written * otherwise read propagation may incorrectly stop too soon @@ -1106,61 +1074,6 @@ static int check_stack_write(struct bpf_verifier_env *env, return 0; } -/* registers of every function are unique and mark_reg_read() propagates - * the liveness in the following cases: - * - from callee into caller for R1 - R5 that were used as arguments - * - from caller into callee for R0 that used as result of the call - * - from caller to the same caller skipping states of the callee for R6 - R9, - * since R6 - R9 are callee saved by implicit function prologue and - * caller's R6 != callee's R6, so when we propagate liveness up to - * parent states we need to skip callee states for R6 - R9. - * - * stack slot marking is different, since stacks of caller and callee are - * accessible in both (since caller can pass a pointer to caller's stack to - * callee which can pass it to another function), hence mark_stack_slot_read() - * has to propagate the stack liveness to all parent states at given frame number. - * Consider code: - * f1() { - * ptr = fp - 8; - * *ptr = ctx; - * call f2 { - * .. = *ptr; - * } - * .. = *ptr; - * } - * First *ptr is reading from f1's stack and mark_stack_slot_read() has - * to mark liveness at the f1's frame and not f2's frame. - * Second *ptr is also reading from f1's stack and mark_stack_slot_read() has - * to propagate liveness to f2 states at f1's frame level and further into - * f1 states at f1's frame level until write into that stack slot - */ -static void mark_stack_slot_read(struct bpf_verifier_env *env, - const struct bpf_verifier_state *state, - struct bpf_verifier_state *parent, - int slot, int frameno) -{ - bool writes = parent == state->parent; /* Observe write marks */ - - while (parent) { - if (parent->frame[frameno]->allocated_stack <= slot * BPF_REG_SIZE) - /* since LIVE_WRITTEN mark is only done for full 8-byte - * write the read marks are conservative and parent - * state may not even have the stack allocated. In such case - * end the propagation, since the loop reached beginning - * of the function - */ - break; - /* if read wasn't screened by an earlier write ... */ - if (writes && state->frame[frameno]->stack[slot].spilled_ptr.live & REG_LIVE_WRITTEN) - break; - /* ... then we depend on parent's value */ - parent->frame[frameno]->stack[slot].spilled_ptr.live |= REG_LIVE_READ; - state = parent; - parent = state->parent; - writes = true; - } -} - static int check_stack_read(struct bpf_verifier_env *env, struct bpf_func_state *reg_state /* func where register points to */, int off, int size, int value_regno) @@ -1198,8 +1111,8 @@ static int check_stack_read(struct bpf_verifier_env *env, */ state->regs[value_regno].live |= REG_LIVE_WRITTEN; } - mark_stack_slot_read(env, vstate, vstate->parent, spi, - reg_state->frameno); + mark_reg_read(env, ®_state->stack[spi].spilled_ptr, + reg_state->stack[spi].spilled_ptr.parent); return 0; } else { int zeros = 0; @@ -1215,8 +1128,8 @@ static int check_stack_read(struct bpf_verifier_env *env, off, i, size); return -EACCES; } - mark_stack_slot_read(env, vstate, vstate->parent, spi, - reg_state->frameno); + mark_reg_read(env, ®_state->stack[spi].spilled_ptr, + reg_state->stack[spi].spilled_ptr.parent); if (value_regno >= 0) { if (zeros == size) { /* any size read into register is zero extended, @@ -1908,8 +1821,8 @@ mark: /* reading any byte out of 8-byte 'spill_slot' will cause * the whole slot to be marked as 'read' */ - mark_stack_slot_read(env, env->cur_state, env->cur_state->parent, - spi, state->frameno); + mark_reg_read(env, &state->stack[spi].spilled_ptr, + state->stack[spi].spilled_ptr.parent); } return update_stack_depth(env, state, off); } @@ -2366,11 +2279,13 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, state->curframe + 1 /* frameno within this callchain */, subprog /* subprog number within this prog */); - /* copy r1 - r5 args that callee can access */ + /* copy r1 - r5 args that callee can access. The copy includes parent + * pointers, which connects us up to the liveness chain + */ for (i = BPF_REG_1; i <= BPF_REG_5; i++) callee->regs[i] = caller->regs[i]; - /* after the call regsiters r0 - r5 were scratched */ + /* after the call registers r0 - r5 were scratched */ for (i = 0; i < CALLER_SAVED_REGS; i++) { mark_reg_not_init(env, caller->regs, caller_saved[i]); check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK); @@ -3163,7 +3078,7 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, * an arbitrary scalar. Disallow all math except * pointer subtraction */ - if (opcode == BPF_SUB){ + if (opcode == BPF_SUB && env->allow_ptr_leaks) { mark_reg_unknown(env, regs, insn->dst_reg); return 0; } @@ -4370,7 +4285,7 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, /* explored state didn't use this */ return true; - equal = memcmp(rold, rcur, offsetof(struct bpf_reg_state, frameno)) == 0; + equal = memcmp(rold, rcur, offsetof(struct bpf_reg_state, parent)) == 0; if (rold->type == PTR_TO_STACK) /* two stack pointers are equal only if they're pointing to @@ -4603,7 +4518,7 @@ static bool states_equal(struct bpf_verifier_env *env, * equivalent state (jump target or such) we didn't arrive by the straight-line * code, so read marks in the state must propagate to the parent regardless * of the state's write marks. That's what 'parent == state->parent' comparison - * in mark_reg_read() and mark_stack_slot_read() is for. + * in mark_reg_read() is for. */ static int propagate_liveness(struct bpf_verifier_env *env, const struct bpf_verifier_state *vstate, @@ -4624,7 +4539,8 @@ static int propagate_liveness(struct bpf_verifier_env *env, if (vparent->frame[vparent->curframe]->regs[i].live & REG_LIVE_READ) continue; if (vstate->frame[vstate->curframe]->regs[i].live & REG_LIVE_READ) { - err = mark_reg_read(env, vstate, vparent, i); + err = mark_reg_read(env, &vstate->frame[vstate->curframe]->regs[i], + &vparent->frame[vstate->curframe]->regs[i]); if (err) return err; } @@ -4639,7 +4555,8 @@ static int propagate_liveness(struct bpf_verifier_env *env, if (parent->stack[i].spilled_ptr.live & REG_LIVE_READ) continue; if (state->stack[i].spilled_ptr.live & REG_LIVE_READ) - mark_stack_slot_read(env, vstate, vparent, i, frame); + mark_reg_read(env, &state->stack[i].spilled_ptr, + &parent->stack[i].spilled_ptr); } } return err; @@ -4649,7 +4566,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) { struct bpf_verifier_state_list *new_sl; struct bpf_verifier_state_list *sl; - struct bpf_verifier_state *cur = env->cur_state; + struct bpf_verifier_state *cur = env->cur_state, *new; int i, j, err; sl = env->explored_states[insn_idx]; @@ -4691,16 +4608,18 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) return -ENOMEM; /* add new state to the head of linked list */ - err = copy_verifier_state(&new_sl->state, cur); + new = &new_sl->state; + err = copy_verifier_state(new, cur); if (err) { - free_verifier_state(&new_sl->state, false); + free_verifier_state(new, false); kfree(new_sl); return err; } new_sl->next = env->explored_states[insn_idx]; env->explored_states[insn_idx] = new_sl; /* connect new state to parentage chain */ - cur->parent = &new_sl->state; + for (i = 0; i < BPF_REG_FP; i++) + cur_regs(env)[i].parent = &new->frame[new->curframe]->regs[i]; /* clear write marks in current state: the writes we did are not writes * our child did, so they don't screen off its reads from us. * (There are no read marks in current state, because reads always mark @@ -4713,9 +4632,13 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) /* all stack frames are accessible from callee, clear them all */ for (j = 0; j <= cur->curframe; j++) { struct bpf_func_state *frame = cur->frame[j]; + struct bpf_func_state *newframe = new->frame[j]; - for (i = 0; i < frame->allocated_stack / BPF_REG_SIZE; i++) + for (i = 0; i < frame->allocated_stack / BPF_REG_SIZE; i++) { frame->stack[i].spilled_ptr.live = REG_LIVE_NONE; + frame->stack[i].spilled_ptr.parent = + &newframe->stack[i].spilled_ptr; + } } return 0; } @@ -4734,7 +4657,6 @@ static int do_check(struct bpf_verifier_env *env) if (!state) return -ENOMEM; state->curframe = 0; - state->parent = NULL; state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL); if (!state->frame[0]) { kfree(state); diff --git a/kernel/cpu.c b/kernel/cpu.c index ed44d7d34c2d..0097acec1c71 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -102,8 +102,6 @@ static inline void cpuhp_lock_release(bool bringup) { } * @name: Name of the step * @startup: Startup function of the step * @teardown: Teardown function of the step - * @skip_onerr: Do not invoke the functions on error rollback - * Will go away once the notifiers are gone * @cant_stop: Bringup/teardown can't be stopped at this step */ struct cpuhp_step { @@ -119,7 +117,6 @@ struct cpuhp_step { struct hlist_node *node); } teardown; struct hlist_head list; - bool skip_onerr; bool cant_stop; bool multi_instance; }; @@ -550,12 +547,8 @@ static int bringup_cpu(unsigned int cpu) static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st) { - for (st->state--; st->state > st->target; st->state--) { - struct cpuhp_step *step = cpuhp_get_step(st->state); - - if (!step->skip_onerr) - cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); - } + for (st->state--; st->state > st->target; st->state--) + cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); } static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, @@ -614,15 +607,15 @@ static void cpuhp_thread_fun(unsigned int cpu) bool bringup = st->bringup; enum cpuhp_state state; + if (WARN_ON_ONCE(!st->should_run)) + return; + /* * ACQUIRE for the cpuhp_should_run() load of ->should_run. Ensures * that if we see ->should_run we also see the rest of the state. */ smp_mb(); - if (WARN_ON_ONCE(!st->should_run)) - return; - cpuhp_lock_acquire(bringup); if (st->single) { @@ -644,12 +637,6 @@ static void cpuhp_thread_fun(unsigned int cpu) WARN_ON_ONCE(!cpuhp_is_ap_state(state)); - if (st->rollback) { - struct cpuhp_step *step = cpuhp_get_step(state); - if (step->skip_onerr) - goto next; - } - if (cpuhp_is_atomic_state(state)) { local_irq_disable(); st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last); @@ -673,7 +660,6 @@ static void cpuhp_thread_fun(unsigned int cpu) st->should_run = false; } -next: cpuhp_lock_release(bringup); if (!st->should_run) @@ -916,12 +902,8 @@ void cpuhp_report_idle_dead(void) static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st) { - for (st->state++; st->state < st->target; st->state++) { - struct cpuhp_step *step = cpuhp_get_step(st->state); - - if (!step->skip_onerr) - cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); - } + for (st->state++; st->state < st->target; st->state++) + cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); } static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, @@ -934,7 +916,8 @@ static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, ret = cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); if (ret) { st->target = prev_state; - undo_cpu_down(cpu, st); + if (st->state < prev_state) + undo_cpu_down(cpu, st); break; } } @@ -987,7 +970,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, * to do the further cleanups. */ ret = cpuhp_down_callbacks(cpu, st, target); - if (ret && st->state > CPUHP_TEARDOWN_CPU && st->state < prev_state) { + if (ret && st->state == CPUHP_TEARDOWN_CPU && st->state < prev_state) { cpuhp_reset_state(st, prev_state); __cpuhp_kick_ap(st); } diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 1c35b7b945d0..de87b0282e74 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -168,7 +168,7 @@ int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents, int dma_direct_supported(struct device *dev, u64 mask) { #ifdef CONFIG_ZONE_DMA - if (mask < DMA_BIT_MASK(ARCH_ZONE_DMA_BITS)) + if (mask < phys_to_dma(dev, DMA_BIT_MASK(ARCH_ZONE_DMA_BITS))) return 0; #else /* @@ -177,7 +177,7 @@ int dma_direct_supported(struct device *dev, u64 mask) * memory, or by providing a ZONE_DMA32. If neither is the case, the * architecture needs to use an IOMMU instead of the direct mapping. */ - if (mask < DMA_BIT_MASK(32)) + if (mask < phys_to_dma(dev, DMA_BIT_MASK(32))) return 0; #endif /* diff --git a/kernel/events/core.c b/kernel/events/core.c index 2a62b96600ad..c80549bf82c6 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2867,16 +2867,11 @@ static int perf_event_modify_breakpoint(struct perf_event *bp, _perf_event_disable(bp); err = modify_user_hw_breakpoint_check(bp, attr, true); - if (err) { - if (!bp->attr.disabled) - _perf_event_enable(bp); - return err; - } - - if (!attr->disabled) + if (!bp->attr.disabled) _perf_event_enable(bp); - return 0; + + return err; } static int perf_event_modify_attr(struct perf_event *event, @@ -5948,6 +5943,7 @@ perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size, unsigned long sp; unsigned int rem; u64 dyn_size; + mm_segment_t fs; /* * We dump: @@ -5965,7 +5961,10 @@ perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size, /* Data. */ sp = perf_user_stack_pointer(regs); + fs = get_fs(); + set_fs(USER_DS); rem = __output_copy_user(handle, (void *) sp, dump_size); + set_fs(fs); dyn_size = dump_size - rem; perf_output_skip(handle, rem); diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c index b3814fce5ecb..d6b56180827c 100644 --- a/kernel/events/hw_breakpoint.c +++ b/kernel/events/hw_breakpoint.c @@ -509,6 +509,8 @@ modify_user_hw_breakpoint_check(struct perf_event *bp, struct perf_event_attr *a */ int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *attr) { + int err; + /* * modify_user_hw_breakpoint can be invoked with IRQs disabled and hence it * will not be possible to raise IPIs that invoke __perf_event_disable. @@ -520,15 +522,12 @@ int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *att else perf_event_disable(bp); - if (!attr->disabled) { - int err = modify_user_hw_breakpoint_check(bp, attr, false); + err = modify_user_hw_breakpoint_check(bp, attr, false); - if (err) - return err; + if (!bp->attr.disabled) perf_event_enable(bp); - bp->attr.disabled = 0; - } - return 0; + + return err; } EXPORT_SYMBOL_GPL(modify_user_hw_breakpoint); diff --git a/kernel/fork.c b/kernel/fork.c index d896e9ca38b0..f0b58479534f 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -550,8 +550,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, goto out; } /* a new mm has just been created */ - arch_dup_mmap(oldmm, mm); - retval = 0; + retval = arch_dup_mmap(oldmm, mm); out: up_write(&mm->mmap_sem); flush_tlb_mm(oldmm); diff --git a/kernel/jump_label.c b/kernel/jump_label.c index 01ebdf1f9f40..2e62503bea0d 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -678,7 +678,7 @@ jump_label_module_notify(struct notifier_block *self, unsigned long val, case MODULE_STATE_COMING: ret = jump_label_add_module(mod); if (ret) { - WARN(1, "Failed to allocatote memory: jump_label may not work properly.\n"); + WARN(1, "Failed to allocate memory: jump_label may not work properly.\n"); jump_label_del_module(mod); } break; diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index e406c5fdb41e..dd13f865ad40 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -55,7 +55,6 @@ #include "lockdep_internals.h" -#include <trace/events/preemptirq.h> #define CREATE_TRACE_POINTS #include <trace/events/lock.h> diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 1a81a1257b3f..3f8a35104285 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -389,7 +389,7 @@ static bool __ww_mutex_wound(struct mutex *lock, /* * wake_up_process() paired with set_current_state() * inserts sufficient barriers to make sure @owner either sees - * it's wounded in __ww_mutex_lock_check_stamp() or has a + * it's wounded in __ww_mutex_check_kill() or has a * wakeup pending to re-read the wounded state. */ if (owner != current) @@ -946,7 +946,6 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, } debug_mutex_lock_common(lock, &waiter); - debug_mutex_add_waiter(lock, &waiter, current); lock_contended(&lock->dep_map, ip); diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c index 5b915b370d5a..0be047dbd897 100644 --- a/kernel/locking/test-ww_mutex.c +++ b/kernel/locking/test-ww_mutex.c @@ -324,7 +324,7 @@ static int __test_cycle(unsigned int nthreads) if (!cycle->result) continue; - pr_err("cylic deadlock not resolved, ret[%d/%d] = %d\n", + pr_err("cyclic deadlock not resolved, ret[%d/%d] = %d\n", n, nthreads, cycle->result); ret = -EINVAL; break; diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 924e37fb1620..9bf5404397e0 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -38,7 +38,6 @@ #include <linux/kmsg_dump.h> #include <linux/syslog.h> #include <linux/cpu.h> -#include <linux/notifier.h> #include <linux/rculist.h> #include <linux/poll.h> #include <linux/irq_work.h> @@ -352,7 +351,6 @@ static int console_msg_format = MSG_FORMAT_DEFAULT; */ enum log_flags { - LOG_NOCONS = 1, /* suppress print, do not print to console */ LOG_NEWLINE = 2, /* text ended with a newline */ LOG_PREFIX = 4, /* text started with a prefix */ LOG_CONT = 8, /* text is a fragment of a continuation line */ @@ -1882,9 +1880,6 @@ int vprintk_store(int facility, int level, if (dict) lflags |= LOG_PREFIX|LOG_NEWLINE; - if (suppress_message_printing(level)) - lflags |= LOG_NOCONS; - return log_output(facility, level, lflags, dict, dictlen, text, text_len); } @@ -2033,6 +2028,7 @@ static void call_console_drivers(const char *ext_text, size_t ext_len, const char *text, size_t len) {} static size_t msg_print_text(const struct printk_log *msg, bool syslog, char *buf, size_t size) { return 0; } +static bool suppress_message_printing(int level) { return false; } #endif /* CONFIG_PRINTK */ @@ -2369,10 +2365,11 @@ skip: break; msg = log_from_idx(console_idx); - if (msg->flags & LOG_NOCONS) { + if (suppress_message_printing(msg->level)) { /* - * Skip record if !ignore_loglevel, and - * record has level above the console loglevel. + * Skip record we have buffered and already printed + * directly to the console when we received it, and + * record that has level above the console loglevel. */ console_idx = log_next(console_idx); console_seq++; diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c index a0a74c533e4b..0913b4d385de 100644 --- a/kernel/printk/printk_safe.c +++ b/kernel/printk/printk_safe.c @@ -306,12 +306,12 @@ static __printf(1, 0) int vprintk_nmi(const char *fmt, va_list args) return printk_safe_log_store(s, fmt, args); } -void printk_nmi_enter(void) +void notrace printk_nmi_enter(void) { this_cpu_or(printk_context, PRINTK_NMI_CONTEXT_MASK); } -void printk_nmi_exit(void) +void notrace printk_nmi_exit(void) { this_cpu_and(printk_context, ~PRINTK_NMI_CONTEXT_MASK); } diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 60caf1fb94e0..6383aa6a60ca 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -89,12 +89,12 @@ struct static_key sched_feat_keys[__SCHED_FEAT_NR] = { static void sched_feat_disable(int i) { - static_key_disable(&sched_feat_keys[i]); + static_key_disable_cpuslocked(&sched_feat_keys[i]); } static void sched_feat_enable(int i) { - static_key_enable(&sched_feat_keys[i]); + static_key_enable_cpuslocked(&sched_feat_keys[i]); } #else static void sched_feat_disable(int i) { }; @@ -146,9 +146,11 @@ sched_feat_write(struct file *filp, const char __user *ubuf, /* Ensure the static_key remains in a consistent state */ inode = file_inode(filp); + cpus_read_lock(); inode_lock(inode); ret = sched_feat_set(cmp); inode_unlock(inode); + cpus_read_unlock(); if (ret < 0) return ret; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index b39fb596f6c1..f808ddf2a868 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3362,6 +3362,7 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) * attach_entity_load_avg - attach this entity to its cfs_rq load avg * @cfs_rq: cfs_rq to attach to * @se: sched_entity to attach + * @flags: migration hints * * Must call update_cfs_rq_load_avg() before this, since we rely on * cfs_rq->avg.last_update_time being current. @@ -7263,6 +7264,7 @@ static void update_blocked_averages(int cpu) { struct rq *rq = cpu_rq(cpu); struct cfs_rq *cfs_rq, *pos; + const struct sched_class *curr_class; struct rq_flags rf; bool done = true; @@ -7299,8 +7301,10 @@ static void update_blocked_averages(int cpu) if (cfs_rq_has_blocked(cfs_rq)) done = false; } - update_rt_rq_load_avg(rq_clock_task(rq), rq, 0); - update_dl_rq_load_avg(rq_clock_task(rq), rq, 0); + + curr_class = rq->curr->sched_class; + update_rt_rq_load_avg(rq_clock_task(rq), rq, curr_class == &rt_sched_class); + update_dl_rq_load_avg(rq_clock_task(rq), rq, curr_class == &dl_sched_class); update_irq_load_avg(rq, 0); /* Don't need periodic decay once load/util_avg are null */ if (others_have_blocked(rq)) @@ -7365,13 +7369,16 @@ static inline void update_blocked_averages(int cpu) { struct rq *rq = cpu_rq(cpu); struct cfs_rq *cfs_rq = &rq->cfs; + const struct sched_class *curr_class; struct rq_flags rf; rq_lock_irqsave(rq, &rf); update_rq_clock(rq); update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq); - update_rt_rq_load_avg(rq_clock_task(rq), rq, 0); - update_dl_rq_load_avg(rq_clock_task(rq), rq, 0); + + curr_class = rq->curr->sched_class; + update_rt_rq_load_avg(rq_clock_task(rq), rq, curr_class == &rt_sched_class); + update_dl_rq_load_avg(rq_clock_task(rq), rq, curr_class == &dl_sched_class); update_irq_load_avg(rq, 0); #ifdef CONFIG_NO_HZ_COMMON rq->last_blocked_load_update_tick = jiffies; @@ -7482,10 +7489,10 @@ static inline int get_sd_load_idx(struct sched_domain *sd, return load_idx; } -static unsigned long scale_rt_capacity(int cpu) +static unsigned long scale_rt_capacity(struct sched_domain *sd, int cpu) { struct rq *rq = cpu_rq(cpu); - unsigned long max = arch_scale_cpu_capacity(NULL, cpu); + unsigned long max = arch_scale_cpu_capacity(sd, cpu); unsigned long used, free; unsigned long irq; @@ -7507,7 +7514,7 @@ static unsigned long scale_rt_capacity(int cpu) static void update_cpu_capacity(struct sched_domain *sd, int cpu) { - unsigned long capacity = scale_rt_capacity(cpu); + unsigned long capacity = scale_rt_capacity(sd, cpu); struct sched_group *sdg = sd->groups; cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(sd, cpu); @@ -8269,7 +8276,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env) force_balance: /* Looks like there is an imbalance. Compute it */ calculate_imbalance(env, &sds); - return sds.busiest; + return env->imbalance ? sds.busiest : NULL; out_balanced: env->imbalance = 0; @@ -9638,7 +9645,8 @@ static inline bool vruntime_normalized(struct task_struct *p) * - A task which has been woken up by try_to_wake_up() and * waiting for actually being woken up by sched_ttwu_pending(). */ - if (!se->sum_exec_runtime || p->state == TASK_WAKING) + if (!se->sum_exec_runtime || + (p->state == TASK_WAKING && p->sched_remote_wakeup)) return true; return false; diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 56a0fed30c0a..505a41c42b96 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1295,7 +1295,7 @@ static void init_numa_topology_type(void) n = sched_max_numa_distance; - if (sched_domains_numa_levels <= 1) { + if (sched_domains_numa_levels <= 2) { sched_numa_topology_type = NUMA_DIRECT; return; } @@ -1380,9 +1380,6 @@ void sched_init_numa(void) break; } - if (!level) - return; - /* * 'level' contains the number of unique distances * diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index f74fb00d8064..0e6e97a01942 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -133,19 +133,40 @@ static void inline clocksource_watchdog_unlock(unsigned long *flags) spin_unlock_irqrestore(&watchdog_lock, *flags); } +static int clocksource_watchdog_kthread(void *data); +static void __clocksource_change_rating(struct clocksource *cs, int rating); + /* * Interval: 0.5sec Threshold: 0.0625s */ #define WATCHDOG_INTERVAL (HZ >> 1) #define WATCHDOG_THRESHOLD (NSEC_PER_SEC >> 4) +static void clocksource_watchdog_work(struct work_struct *work) +{ + /* + * We cannot directly run clocksource_watchdog_kthread() here, because + * clocksource_select() calls timekeeping_notify() which uses + * stop_machine(). One cannot use stop_machine() from a workqueue() due + * lock inversions wrt CPU hotplug. + * + * Also, we only ever run this work once or twice during the lifetime + * of the kernel, so there is no point in creating a more permanent + * kthread for this. + * + * If kthread_run fails the next watchdog scan over the + * watchdog_list will find the unstable clock again. + */ + kthread_run(clocksource_watchdog_kthread, NULL, "kwatchdog"); +} + static void __clocksource_unstable(struct clocksource *cs) { cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG); cs->flags |= CLOCK_SOURCE_UNSTABLE; /* - * If the clocksource is registered clocksource_watchdog_work() will + * If the clocksource is registered clocksource_watchdog_kthread() will * re-rate and re-select. */ if (list_empty(&cs->list)) { @@ -156,7 +177,7 @@ static void __clocksource_unstable(struct clocksource *cs) if (cs->mark_unstable) cs->mark_unstable(cs); - /* kick clocksource_watchdog_work() */ + /* kick clocksource_watchdog_kthread() */ if (finished_booting) schedule_work(&watchdog_work); } @@ -166,7 +187,7 @@ static void __clocksource_unstable(struct clocksource *cs) * @cs: clocksource to be marked unstable * * This function is called by the x86 TSC code to mark clocksources as unstable; - * it defers demotion and re-selection to a work. + * it defers demotion and re-selection to a kthread. */ void clocksource_mark_unstable(struct clocksource *cs) { @@ -391,9 +412,7 @@ static void clocksource_dequeue_watchdog(struct clocksource *cs) } } -static void __clocksource_change_rating(struct clocksource *cs, int rating); - -static int __clocksource_watchdog_work(void) +static int __clocksource_watchdog_kthread(void) { struct clocksource *cs, *tmp; unsigned long flags; @@ -418,12 +437,13 @@ static int __clocksource_watchdog_work(void) return select; } -static void clocksource_watchdog_work(struct work_struct *work) +static int clocksource_watchdog_kthread(void *data) { mutex_lock(&clocksource_mutex); - if (__clocksource_watchdog_work()) + if (__clocksource_watchdog_kthread()) clocksource_select(); mutex_unlock(&clocksource_mutex); + return 0; } static bool clocksource_is_watchdog(struct clocksource *cs) @@ -442,7 +462,7 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs) static void clocksource_select_watchdog(bool fallback) { } static inline void clocksource_dequeue_watchdog(struct clocksource *cs) { } static inline void clocksource_resume_watchdog(void) { } -static inline int __clocksource_watchdog_work(void) { return 0; } +static inline int __clocksource_watchdog_kthread(void) { return 0; } static bool clocksource_is_watchdog(struct clocksource *cs) { return false; } void clocksource_mark_unstable(struct clocksource *cs) { } @@ -810,7 +830,7 @@ static int __init clocksource_done_booting(void) /* * Run the watchdog first to eliminate unstable clock sources */ - __clocksource_watchdog_work(); + __clocksource_watchdog_kthread(); clocksource_select(); mutex_unlock(&clocksource_mutex); return 0; diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 5470dce212c0..977918d5d350 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -261,7 +261,7 @@ static void __touch_watchdog(void) * entering idle state. This should only be used for scheduler events. * Use touch_softlockup_watchdog() for everything else. */ -void touch_softlockup_watchdog_sched(void) +notrace void touch_softlockup_watchdog_sched(void) { /* * Preemption can be enabled. It doesn't matter which CPU's timestamp @@ -270,7 +270,7 @@ void touch_softlockup_watchdog_sched(void) raw_cpu_write(watchdog_touch_ts, 0); } -void touch_softlockup_watchdog(void) +notrace void touch_softlockup_watchdog(void) { touch_softlockup_watchdog_sched(); wq_watchdog_touch(raw_smp_processor_id()); diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c index 1f7020d65d0a..71381168dede 100644 --- a/kernel/watchdog_hld.c +++ b/kernel/watchdog_hld.c @@ -29,7 +29,7 @@ static struct cpumask dead_events_mask; static unsigned long hardlockup_allcpu_dumped; static atomic_t watchdog_cpus = ATOMIC_INIT(0); -void arch_touch_nmi_watchdog(void) +notrace void arch_touch_nmi_watchdog(void) { /* * Using __raw here because some code paths have diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 60e80198c3df..0280deac392e 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -5574,7 +5574,7 @@ static void wq_watchdog_timer_fn(struct timer_list *unused) mod_timer(&wq_watchdog_timer, jiffies + thresh); } -void wq_watchdog_touch(int cpu) +notrace void wq_watchdog_touch(int cpu) { if (cpu >= 0) per_cpu(wq_watchdog_touched_cpu, cpu) = jiffies; diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 613316724c6a..4966c4fbe7f7 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1277,13 +1277,13 @@ config WARN_ALL_UNSEEDED_RANDOM time. This is really bad from a security perspective, and so architecture maintainers really need to do what they can to get the CRNG seeded sooner after the system is booted. - However, since users can not do anything actionble to + However, since users cannot do anything actionable to address this, by default the kernel will issue only a single warning for the first use of unseeded randomness. Say Y here if you want to receive warnings for all uses of unseeded randomness. This will be of use primarily for - those developers interersted in improving the security of + those developers interested in improving the security of Linux kernels running on their architecture (or subarchitecture). diff --git a/lib/nlattr.c b/lib/nlattr.c index e335bcafa9e4..bb6fe5ed4ecf 100644 --- a/lib/nlattr.c +++ b/lib/nlattr.c @@ -69,7 +69,8 @@ static int validate_nla_bitfield32(const struct nlattr *nla, } static int validate_nla(const struct nlattr *nla, int maxtype, - const struct nla_policy *policy) + const struct nla_policy *policy, + const char **error_msg) { const struct nla_policy *pt; int minlen = 0, attrlen = nla_len(nla), type = nla_type(nla); @@ -81,12 +82,23 @@ static int validate_nla(const struct nlattr *nla, int maxtype, BUG_ON(pt->type > NLA_TYPE_MAX); - if (nla_attr_len[pt->type] && attrlen != nla_attr_len[pt->type]) { + if ((nla_attr_len[pt->type] && attrlen != nla_attr_len[pt->type]) || + (pt->type == NLA_EXACT_LEN_WARN && attrlen != pt->len)) { pr_warn_ratelimited("netlink: '%s': attribute type %d has an invalid length.\n", current->comm, type); } switch (pt->type) { + case NLA_EXACT_LEN: + if (attrlen != pt->len) + return -ERANGE; + break; + + case NLA_REJECT: + if (pt->validation_data && error_msg) + *error_msg = pt->validation_data; + return -EINVAL; + case NLA_FLAG: if (attrlen > 0) return -ERANGE; @@ -180,11 +192,10 @@ int nla_validate(const struct nlattr *head, int len, int maxtype, int rem; nla_for_each_attr(nla, head, len, rem) { - int err = validate_nla(nla, maxtype, policy); + int err = validate_nla(nla, maxtype, policy, NULL); if (err < 0) { - if (extack) - extack->bad_attr = nla; + NL_SET_BAD_ATTR(extack, nla); return err; } } @@ -250,11 +261,15 @@ int nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head, u16 type = nla_type(nla); if (type > 0 && type <= maxtype) { + static const char _msg[] = "Attribute failed policy validation"; + const char *msg = _msg; + if (policy) { - err = validate_nla(nla, maxtype, policy); + err = validate_nla(nla, maxtype, policy, &msg); if (err < 0) { - NL_SET_ERR_MSG_ATTR(extack, nla, - "Attribute failed policy validation"); + NL_SET_BAD_ATTR(extack, nla); + if (extack) + extack->_msg = msg; goto errout; } } diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c index c72577e472f2..a66595ba5543 100644 --- a/lib/percpu_counter.c +++ b/lib/percpu_counter.c @@ -4,7 +4,6 @@ */ #include <linux/percpu_counter.h> -#include <linux/notifier.h> #include <linux/mutex.h> #include <linux/init.h> #include <linux/cpu.h> diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 310e29b51507..30526afa8343 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -28,7 +28,6 @@ #include <linux/rhashtable.h> #include <linux/err.h> #include <linux/export.h> -#include <linux/rhashtable.h> #define HASH_DEFAULT_SIZE 64UL #define HASH_MIN_SIZE 4U diff --git a/mm/Makefile b/mm/Makefile index 8716bdabe1e6..26ef77a3883b 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -32,7 +32,7 @@ ifdef CONFIG_CROSS_MEMORY_ATTACH mmu-$(CONFIG_MMU) += process_vm_access.o endif -obj-y := filemap.o mempool.o oom_kill.o \ +obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ maccess.o page_alloc.o page-writeback.o \ readahead.o swap.o truncate.o vmscan.o shmem.o \ util.o mmzone.o vmstat.o backing-dev.o \ @@ -49,7 +49,6 @@ else obj-y += bootmem.o endif -obj-$(CONFIG_ADVISE_SYSCALLS) += fadvise.o ifdef CONFIG_MMU obj-$(CONFIG_ADVISE_SYSCALLS) += madvise.o endif diff --git a/mm/backing-dev.c b/mm/backing-dev.c index f5981e9d6ae2..8a8bb8796c6c 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -491,6 +491,7 @@ static void cgwb_release_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(work, struct bdi_writeback, release_work); + struct blkcg *blkcg = css_to_blkcg(wb->blkcg_css); mutex_lock(&wb->bdi->cgwb_release_mutex); wb_shutdown(wb); @@ -499,6 +500,9 @@ static void cgwb_release_workfn(struct work_struct *work) css_put(wb->blkcg_css); mutex_unlock(&wb->bdi->cgwb_release_mutex); + /* triggers blkg destruction if cgwb_refcnt becomes zero */ + blkcg_cgwb_put(blkcg); + fprop_local_destroy_percpu(&wb->memcg_completions); percpu_ref_exit(&wb->refcnt); wb_exit(wb); @@ -597,6 +601,7 @@ static int cgwb_create(struct backing_dev_info *bdi, list_add_tail_rcu(&wb->bdi_node, &bdi->wb_list); list_add(&wb->memcg_node, memcg_cgwb_list); list_add(&wb->blkcg_node, blkcg_cgwb_list); + blkcg_cgwb_get(blkcg); css_get(memcg_css); css_get(blkcg_css); } diff --git a/mm/debug.c b/mm/debug.c index 38c926520c97..bd10aad8539a 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -114,7 +114,7 @@ EXPORT_SYMBOL(dump_vma); void dump_mm(const struct mm_struct *mm) { - pr_emerg("mm %px mmap %px seqnum %d task_size %lu\n" + pr_emerg("mm %px mmap %px seqnum %llu task_size %lu\n" #ifdef CONFIG_MMU "get_unmapped_area %px\n" #endif @@ -142,7 +142,7 @@ void dump_mm(const struct mm_struct *mm) "tlb_flush_pending %d\n" "def_flags: %#lx(%pGv)\n", - mm, mm->mmap, mm->vmacache_seqnum, mm->task_size, + mm, mm->mmap, (long long) mm->vmacache_seqnum, mm->task_size, #ifdef CONFIG_MMU mm->get_unmapped_area, #endif diff --git a/mm/fadvise.c b/mm/fadvise.c index 2d8376e3c640..467bcd032037 100644 --- a/mm/fadvise.c +++ b/mm/fadvise.c @@ -27,9 +27,9 @@ * deactivate the pages and clear PG_Referenced. */ -int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) +static int generic_fadvise(struct file *file, loff_t offset, loff_t len, + int advice) { - struct fd f = fdget(fd); struct inode *inode; struct address_space *mapping; struct backing_dev_info *bdi; @@ -37,22 +37,14 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) pgoff_t start_index; pgoff_t end_index; unsigned long nrpages; - int ret = 0; - - if (!f.file) - return -EBADF; - inode = file_inode(f.file); - if (S_ISFIFO(inode->i_mode)) { - ret = -ESPIPE; - goto out; - } + inode = file_inode(file); + if (S_ISFIFO(inode->i_mode)) + return -ESPIPE; - mapping = f.file->f_mapping; - if (!mapping || len < 0) { - ret = -EINVAL; - goto out; - } + mapping = file->f_mapping; + if (!mapping || len < 0) + return -EINVAL; bdi = inode_to_bdi(mapping->host); @@ -67,9 +59,9 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) /* no bad return value, but ignore advice */ break; default: - ret = -EINVAL; + return -EINVAL; } - goto out; + return 0; } /* @@ -85,21 +77,21 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) switch (advice) { case POSIX_FADV_NORMAL: - f.file->f_ra.ra_pages = bdi->ra_pages; - spin_lock(&f.file->f_lock); - f.file->f_mode &= ~FMODE_RANDOM; - spin_unlock(&f.file->f_lock); + file->f_ra.ra_pages = bdi->ra_pages; + spin_lock(&file->f_lock); + file->f_mode &= ~FMODE_RANDOM; + spin_unlock(&file->f_lock); break; case POSIX_FADV_RANDOM: - spin_lock(&f.file->f_lock); - f.file->f_mode |= FMODE_RANDOM; - spin_unlock(&f.file->f_lock); + spin_lock(&file->f_lock); + file->f_mode |= FMODE_RANDOM; + spin_unlock(&file->f_lock); break; case POSIX_FADV_SEQUENTIAL: - f.file->f_ra.ra_pages = bdi->ra_pages * 2; - spin_lock(&f.file->f_lock); - f.file->f_mode &= ~FMODE_RANDOM; - spin_unlock(&f.file->f_lock); + file->f_ra.ra_pages = bdi->ra_pages * 2; + spin_lock(&file->f_lock); + file->f_mode &= ~FMODE_RANDOM; + spin_unlock(&file->f_lock); break; case POSIX_FADV_WILLNEED: /* First and last PARTIAL page! */ @@ -115,8 +107,7 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) * Ignore return value because fadvise() shall return * success even if filesystem can't retrieve a hint, */ - force_page_cache_readahead(mapping, f.file, start_index, - nrpages); + force_page_cache_readahead(mapping, file, start_index, nrpages); break; case POSIX_FADV_NOREUSE: break; @@ -183,9 +174,32 @@ int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) } break; default: - ret = -EINVAL; + return -EINVAL; } -out: + return 0; +} + +int vfs_fadvise(struct file *file, loff_t offset, loff_t len, int advice) +{ + if (file->f_op->fadvise) + return file->f_op->fadvise(file, offset, len, advice); + + return generic_fadvise(file, offset, len, advice); +} +EXPORT_SYMBOL(vfs_fadvise); + +#ifdef CONFIG_ADVISE_SYSCALLS + +int ksys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) +{ + struct fd f = fdget(fd); + int ret; + + if (!f.file) + return -EBADF; + + ret = vfs_fadvise(f.file, offset, len, advice); + fdput(f); return ret; } @@ -203,3 +217,4 @@ SYSCALL_DEFINE4(fadvise64, int, fd, loff_t, offset, size_t, len, int, advice) } #endif +#endif diff --git a/mm/huge_memory.c b/mm/huge_memory.c index c3bc7e9c9a2a..533f9b00147d 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -821,11 +821,11 @@ vm_fault_t vmf_insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr, * but we need to be consistent with PTEs and architectures that * can't support a 'special' bit. */ - BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))); + BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) && + !pfn_t_devmap(pfn)); BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) == (VM_PFNMAP|VM_MIXEDMAP)); BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags)); - BUG_ON(!pfn_t_devmap(pfn)); if (addr < vma->vm_start || addr >= vma->vm_end) return VM_FAULT_SIGBUS; diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 9a085d525bbc..17dd883198ae 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -2097,6 +2097,11 @@ static int __init kmemleak_late_init(void) kmemleak_initialized = 1; + dentry = debugfs_create_file("kmemleak", 0644, NULL, NULL, + &kmemleak_fops); + if (!dentry) + pr_warn("Failed to create the debugfs kmemleak file\n"); + if (kmemleak_error) { /* * Some error occurred and kmemleak was disabled. There is a @@ -2108,10 +2113,6 @@ static int __init kmemleak_late_init(void) return -ENOMEM; } - dentry = debugfs_create_file("kmemleak", 0644, NULL, NULL, - &kmemleak_fops); - if (!dentry) - pr_warn("Failed to create the debugfs kmemleak file\n"); mutex_lock(&scan_mutex); start_scan_thread(); mutex_unlock(&scan_mutex); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 4ead5a4817de..e79cb59552d9 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1701,8 +1701,6 @@ static enum oom_status mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int if (mem_cgroup_out_of_memory(memcg, mask, order)) return OOM_SUCCESS; - WARN(1,"Memory cgroup charge failed because of no reclaimable memory! " - "This looks like a misconfiguration or a kernel bug."); return OOM_FAILED; } diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 9eea6e809a4e..38d94b703e9d 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1333,7 +1333,8 @@ static unsigned long scan_movable_pages(unsigned long start, unsigned long end) if (__PageMovable(page)) return pfn; if (PageHuge(page)) { - if (page_huge_active(page)) + if (hugepage_migration_supported(page_hstate(page)) && + page_huge_active(page)) return pfn; else pfn = round_up(pfn + 1, diff --git a/mm/oom_kill.c b/mm/oom_kill.c index b5b25e4dcbbb..f10aa5360616 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -522,6 +522,7 @@ bool __oom_reap_task_mm(struct mm_struct *mm) tlb_gather_mmu(&tlb, mm, start, end); if (mmu_notifier_invalidate_range_start_nonblock(mm, start, end)) { + tlb_finish_mmu(&tlb, start, end); ret = false; continue; } @@ -1103,10 +1104,17 @@ bool out_of_memory(struct oom_control *oc) } select_bad_process(oc); - /* Found nothing?!?! Either we hang forever, or we panic. */ - if (!oc->chosen && !is_sysrq_oom(oc) && !is_memcg_oom(oc)) { + /* Found nothing?!?! */ + if (!oc->chosen) { dump_header(oc, NULL); - panic("Out of memory and no killable processes...\n"); + pr_warn("Out of memory and no killable processes...\n"); + /* + * If we got here due to an actual allocation at the + * system level, we cannot survive this and will enter + * an endless loop in the allocator. Bail out now. + */ + if (!is_sysrq_oom(oc) && !is_memcg_oom(oc)) + panic("System is deadlocked on memory\n"); } if (oc->chosen && oc->chosen != (void *)-1UL) oom_kill_process(oc, !is_memcg_oom(oc) ? "Out of memory" : diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 6551d3b0dc30..84ae9bf5858a 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -27,7 +27,6 @@ #include <linux/mpage.h> #include <linux/rmap.h> #include <linux/percpu.h> -#include <linux/notifier.h> #include <linux/smp.h> #include <linux/sysctl.h> #include <linux/cpu.h> diff --git a/mm/page_alloc.c b/mm/page_alloc.c index e75865d58ba7..89d2a2ab3fe6 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -32,7 +32,6 @@ #include <linux/slab.h> #include <linux/ratelimit.h> #include <linux/oom.h> -#include <linux/notifier.h> #include <linux/topology.h> #include <linux/sysctl.h> #include <linux/cpu.h> @@ -7709,6 +7708,10 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, * handle each tail page individually in migration. */ if (PageHuge(page)) { + + if (!hugepage_migration_supported(page_hstate(page))) + goto unmovable; + iter = round_up(iter + 1, 1<<compound_order(page)) - 1; continue; } diff --git a/mm/readahead.c b/mm/readahead.c index a59ea70527b9..4e630143a0ba 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -20,6 +20,7 @@ #include <linux/file.h> #include <linux/mm_inline.h> #include <linux/blk-cgroup.h> +#include <linux/fadvise.h> #include "internal.h" @@ -575,24 +576,6 @@ page_cache_async_readahead(struct address_space *mapping, } EXPORT_SYMBOL_GPL(page_cache_async_readahead); -static ssize_t -do_readahead(struct address_space *mapping, struct file *filp, - pgoff_t index, unsigned long nr) -{ - if (!mapping || !mapping->a_ops) - return -EINVAL; - - /* - * Readahead doesn't make sense for DAX inodes, but we don't want it - * to report a failure either. Instead, we just return success and - * don't do any work. - */ - if (dax_mapping(mapping)) - return 0; - - return force_page_cache_readahead(mapping, filp, index, nr); -} - ssize_t ksys_readahead(int fd, loff_t offset, size_t count) { ssize_t ret; @@ -600,16 +583,22 @@ ssize_t ksys_readahead(int fd, loff_t offset, size_t count) ret = -EBADF; f = fdget(fd); - if (f.file) { - if (f.file->f_mode & FMODE_READ) { - struct address_space *mapping = f.file->f_mapping; - pgoff_t start = offset >> PAGE_SHIFT; - pgoff_t end = (offset + count - 1) >> PAGE_SHIFT; - unsigned long len = end - start + 1; - ret = do_readahead(mapping, f.file, start, len); - } - fdput(f); - } + if (!f.file || !(f.file->f_mode & FMODE_READ)) + goto out; + + /* + * The readahead() syscall is intended to run only on files + * that can execute readahead. If readahead is not possible + * on this file, then we must return -EINVAL. + */ + ret = -EINVAL; + if (!f.file->f_mapping || !f.file->f_mapping->a_ops || + !S_ISREG(file_inode(f.file)->i_mode)) + goto out; + + ret = vfs_fadvise(f.file, offset, count, POSIX_FADV_WILLNEED); +out: + fdput(f); return ret; } diff --git a/mm/slub.c b/mm/slub.c index ce2b9e5cea77..8da34a8af53d 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -19,7 +19,6 @@ #include <linux/slab.h> #include "slab.h" #include <linux/proc_fs.h> -#include <linux/notifier.h> #include <linux/seq_file.h> #include <linux/kasan.h> #include <linux/cpu.h> diff --git a/mm/util.c b/mm/util.c index d2890a407332..9e3ebd2ef65f 100644 --- a/mm/util.c +++ b/mm/util.c @@ -435,11 +435,14 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node) EXPORT_SYMBOL(kvmalloc_node); /** - * kvfree - free memory allocated with kvmalloc - * @addr: pointer returned by kvmalloc + * kvfree() - Free memory. + * @addr: Pointer to allocated memory. * - * If the memory is allocated from vmalloc area it is freed with vfree(). - * Otherwise kfree() is used. + * kvfree frees memory allocated by any of vmalloc(), kmalloc() or kvmalloc(). + * It is slightly more efficient to use kfree() or vfree() if you are certain + * that you know which one to use. + * + * Context: Any context except NMI. */ void kvfree(const void *addr) { diff --git a/mm/vmacache.c b/mm/vmacache.c index ea517bef7dc5..cdc32a3b02fa 100644 --- a/mm/vmacache.c +++ b/mm/vmacache.c @@ -20,44 +20,6 @@ #define VMACACHE_HASH(addr) ((addr >> VMACACHE_SHIFT) & VMACACHE_MASK) /* - * Flush vma caches for threads that share a given mm. - * - * The operation is safe because the caller holds the mmap_sem - * exclusively and other threads accessing the vma cache will - * have mmap_sem held at least for read, so no extra locking - * is required to maintain the vma cache. - */ -void vmacache_flush_all(struct mm_struct *mm) -{ - struct task_struct *g, *p; - - count_vm_vmacache_event(VMACACHE_FULL_FLUSHES); - - /* - * Single threaded tasks need not iterate the entire - * list of process. We can avoid the flushing as well - * since the mm's seqnum was increased and don't have - * to worry about other threads' seqnum. Current's - * flush will occur upon the next lookup. - */ - if (atomic_read(&mm->mm_users) == 1) - return; - - rcu_read_lock(); - for_each_process_thread(g, p) { - /* - * Only flush the vmacache pointers as the - * mm seqnum is already set and curr's will - * be set upon invalidation when the next - * lookup is done. - */ - if (mm == p->mm) - vmacache_flush(p); - } - rcu_read_unlock(); -} - -/* * This task may be accessing a foreign mm via (for example) * get_user_pages()->find_vma(). The vmacache is task-local and this * task's vmacache pertains to a different mm (ie, its own). There is diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index ae91e2d40056..3a7b0773536b 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -83,6 +83,7 @@ enum { struct smp_dev { /* Secure Connections OOB data */ + bool local_oob; u8 local_pk[64]; u8 local_rand[16]; bool debug_key; @@ -599,6 +600,8 @@ int smp_generate_oob(struct hci_dev *hdev, u8 hash[16], u8 rand[16]) memcpy(rand, smp->local_rand, 16); + smp->local_oob = true; + return 0; } @@ -1785,7 +1788,7 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) * successfully received our local OOB data - therefore set the * flag to indicate that local OOB is in use. */ - if (req->oob_flag == SMP_OOB_PRESENT) + if (req->oob_flag == SMP_OOB_PRESENT && SMP_DEV(hdev)->local_oob) set_bit(SMP_FLAG_LOCAL_OOB, &smp->flags); /* SMP over BR/EDR requires special treatment */ @@ -1967,7 +1970,7 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb) * successfully received our local OOB data - therefore set the * flag to indicate that local OOB is in use. */ - if (rsp->oob_flag == SMP_OOB_PRESENT) + if (rsp->oob_flag == SMP_OOB_PRESENT && SMP_DEV(hdev)->local_oob) set_bit(SMP_FLAG_LOCAL_OOB, &smp->flags); smp->prsp[0] = SMP_CMD_PAIRING_RSP; @@ -2697,7 +2700,13 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb) * key was set/generated. */ if (test_bit(SMP_FLAG_LOCAL_OOB, &smp->flags)) { - struct smp_dev *smp_dev = chan->data; + struct l2cap_chan *hchan = hdev->smp_data; + struct smp_dev *smp_dev; + + if (!hchan || !hchan->data) + return SMP_UNSPECIFIED; + + smp_dev = hchan->data; tfm_ecdh = smp_dev->tfm_ecdh; } else { @@ -3230,6 +3239,7 @@ static struct l2cap_chan *smp_add_cid(struct hci_dev *hdev, u16 cid) return ERR_CAST(tfm_ecdh); } + smp->local_oob = false; smp->tfm_aes = tfm_aes; smp->tfm_cmac = tfm_cmac; smp->tfm_ecdh = tfm_ecdh; diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 502f66349530..a56ed7f2a3a3 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -584,7 +584,7 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, unsigned long now = jiffies; /* fastpath: update of existing entry */ - if (unlikely(source != fdb->dst)) { + if (unlikely(source != fdb->dst && !fdb->is_sticky)) { fdb->dst = source; fdb_modified = true; /* Take over HW learned entry */ @@ -656,6 +656,8 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br, ndm->ndm_flags |= NTF_OFFLOADED; if (fdb->added_by_external_learn) ndm->ndm_flags |= NTF_EXT_LEARNED; + if (fdb->is_sticky) + ndm->ndm_flags |= NTF_STICKY; if (nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->key.addr)) goto nla_put_failure; @@ -772,8 +774,10 @@ skip: /* Update (create or replace) forwarding database entry */ static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source, - const __u8 *addr, __u16 state, __u16 flags, __u16 vid) + const u8 *addr, u16 state, u16 flags, u16 vid, + u8 ndm_flags) { + u8 is_sticky = !!(ndm_flags & NTF_STICKY); struct net_bridge_fdb_entry *fdb; bool modified = false; @@ -789,6 +793,9 @@ static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source, return -EINVAL; } + if (is_sticky && (state & NUD_PERMANENT)) + return -EINVAL; + fdb = br_fdb_find(br, addr, vid); if (fdb == NULL) { if (!(flags & NLM_F_CREATE)) @@ -832,6 +839,12 @@ static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source, modified = true; } + + if (is_sticky != fdb->is_sticky) { + fdb->is_sticky = is_sticky; + modified = true; + } + fdb->added_by_user = 1; fdb->used = jiffies; @@ -865,7 +878,7 @@ static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge *br, } else { spin_lock_bh(&br->hash_lock); err = fdb_add_entry(br, p, addr, ndm->ndm_state, - nlh_flags, vid); + nlh_flags, vid, ndm->ndm_flags); spin_unlock_bh(&br->hash_lock); } diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 0363f1bdc401..3bb66508f07d 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -394,8 +394,7 @@ static int find_portno(struct net_bridge *br) struct net_bridge_port *p; unsigned long *inuse; - inuse = kcalloc(BITS_TO_LONGS(BR_MAX_PORTS), sizeof(unsigned long), - GFP_KERNEL); + inuse = bitmap_zalloc(BR_MAX_PORTS, GFP_KERNEL); if (!inuse) return -ENOMEM; @@ -404,7 +403,7 @@ static int find_portno(struct net_bridge *br) set_bit(p->port_no, inuse); } index = find_first_zero_bit(inuse, BR_MAX_PORTS); - kfree(inuse); + bitmap_free(inuse); return (index >= BR_MAX_PORTS) ? -EXFULL : index; } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 11ed2029985f..d21035a17f4c 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -181,6 +181,7 @@ struct net_bridge_fdb_entry { struct hlist_node fdb_node; unsigned char is_local:1, is_static:1, + is_sticky:1, added_by_user:1, added_by_external_learn:1, offloaded:1; diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 7df269092103..bb6ba794864f 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -877,8 +877,7 @@ int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid) return 0; } - changed = kcalloc(BITS_TO_LONGS(BR_MAX_PORTS), sizeof(unsigned long), - GFP_KERNEL); + changed = bitmap_zalloc(BR_MAX_PORTS, GFP_KERNEL); if (!changed) return -ENOMEM; @@ -925,7 +924,7 @@ int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid) br->default_pvid = pvid; out: - kfree(changed); + bitmap_free(changed); return err; err_port: diff --git a/net/caif/cfrfml.c b/net/caif/cfrfml.c index b82440e1fcb4..a931a71ef6df 100644 --- a/net/caif/cfrfml.c +++ b/net/caif/cfrfml.c @@ -264,9 +264,6 @@ static int cfrfml_transmit(struct cflayer *layr, struct cfpkt *pkt) frontpkt = rearpkt; rearpkt = NULL; - err = -ENOMEM; - if (frontpkt == NULL) - goto out; err = -EPROTO; if (cfpkt_add_head(frontpkt, head, 6) < 0) goto out; diff --git a/net/core/dev.c b/net/core/dev.c index 325fc5088370..0b2d777e5b9e 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -93,7 +93,6 @@ #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/ethtool.h> -#include <linux/notifier.h> #include <linux/skbuff.h> #include <linux/bpf.h> #include <linux/bpf_trace.h> @@ -1970,6 +1969,9 @@ void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) rcu_read_lock(); again: list_for_each_entry_rcu(ptype, ptype_list, list) { + if (ptype->ignore_outgoing) + continue; + /* Never send packets back to the socket * they originated from - MvS (miquels@drinkel.ow.org) */ @@ -3229,7 +3231,7 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *first, struct net_device *de while (skb) { struct sk_buff *next = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); rc = xmit_one(skb, dev, txq, next != NULL); if (unlikely(!dev_xmit_complete(rc))) { skb->next = next; @@ -3329,7 +3331,7 @@ struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *d for (; skb != NULL; skb = next) { next = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); /* in case skb wont be segmented, point to itself */ skb->prev = skb; @@ -5293,8 +5295,7 @@ static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index, list_for_each_entry_safe_reverse(skb, p, head, list) { if (flush_old && NAPI_GRO_CB(skb)->age == jiffies) return; - list_del(&skb->list); - skb->next = NULL; + skb_list_del_init(skb); napi_gro_complete(skb); napi->gro_hash[index].count--; } @@ -5479,8 +5480,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff ret = NAPI_GRO_CB(skb)->free ? GRO_MERGED_FREE : GRO_MERGED; if (pp) { - list_del(&pp->list); - pp->next = NULL; + skb_list_del_init(pp); napi_gro_complete(pp); napi->gro_hash[hash].count--; } diff --git a/net/core/ethtool.c b/net/core/ethtool.c index c9993c6c2fd4..9d4e56d97080 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -539,47 +539,17 @@ struct ethtool_link_usettings { } link_modes; }; -/* Internal kernel helper to query a device ethtool_link_settings. - * - * Backward compatibility note: for compatibility with legacy drivers - * that implement only the ethtool_cmd API, this has to work with both - * drivers implementing get_link_ksettings API and drivers - * implementing get_settings API. When drivers implement get_settings - * and report ethtool_cmd deprecated fields - * (transceiver/maxrxpkt/maxtxpkt), these fields are silently ignored - * because the resulting struct ethtool_link_settings does not report them. - */ +/* Internal kernel helper to query a device ethtool_link_settings. */ int __ethtool_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *link_ksettings) { - int err; - struct ethtool_cmd cmd; - ASSERT_RTNL(); - if (dev->ethtool_ops->get_link_ksettings) { - memset(link_ksettings, 0, sizeof(*link_ksettings)); - return dev->ethtool_ops->get_link_ksettings(dev, - link_ksettings); - } - - /* driver doesn't support %ethtool_link_ksettings API. revert to - * legacy %ethtool_cmd API, unless it's not supported either. - * TODO: remove when ethtool_ops::get_settings disappears internally - */ - if (!dev->ethtool_ops->get_settings) + if (!dev->ethtool_ops->get_link_ksettings) return -EOPNOTSUPP; - memset(&cmd, 0, sizeof(cmd)); - cmd.cmd = ETHTOOL_GSET; - err = dev->ethtool_ops->get_settings(dev, &cmd); - if (err < 0) - return err; - - /* we ignore deprecated fields transceiver/maxrxpkt/maxtxpkt - */ - convert_legacy_settings_to_link_ksettings(link_ksettings, &cmd); - return err; + memset(link_ksettings, 0, sizeof(*link_ksettings)); + return dev->ethtool_ops->get_link_ksettings(dev, link_ksettings); } EXPORT_SYMBOL(__ethtool_get_link_ksettings); @@ -635,16 +605,7 @@ store_link_ksettings_for_user(void __user *to, return 0; } -/* Query device for its ethtool_link_settings. - * - * Backward compatibility note: this function must fail when driver - * does not implement ethtool::get_link_ksettings, even if legacy - * ethtool_ops::get_settings is implemented. This tells new versions - * of ethtool that they should use the legacy API %ETHTOOL_GSET for - * this driver, so that they can correctly access the ethtool_cmd - * deprecated fields (transceiver/maxrxpkt/maxtxpkt), until no driver - * implements ethtool_ops::get_settings anymore. - */ +/* Query device for its ethtool_link_settings. */ static int ethtool_get_link_ksettings(struct net_device *dev, void __user *useraddr) { @@ -652,7 +613,6 @@ static int ethtool_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings link_ksettings; ASSERT_RTNL(); - if (!dev->ethtool_ops->get_link_ksettings) return -EOPNOTSUPP; @@ -699,16 +659,7 @@ static int ethtool_get_link_ksettings(struct net_device *dev, return store_link_ksettings_for_user(useraddr, &link_ksettings); } -/* Update device ethtool_link_settings. - * - * Backward compatibility note: this function must fail when driver - * does not implement ethtool::set_link_ksettings, even if legacy - * ethtool_ops::set_settings is implemented. This tells new versions - * of ethtool that they should use the legacy API %ETHTOOL_SSET for - * this driver, so that they can correctly update the ethtool_cmd - * deprecated fields (transceiver/maxrxpkt/maxtxpkt), until no driver - * implements ethtool_ops::get_settings anymore. - */ +/* Update device ethtool_link_settings. */ static int ethtool_set_link_ksettings(struct net_device *dev, void __user *useraddr) { @@ -746,51 +697,31 @@ static int ethtool_set_link_ksettings(struct net_device *dev, /* Query device for its ethtool_cmd settings. * - * Backward compatibility note: for compatibility with legacy ethtool, - * this has to work with both drivers implementing get_link_ksettings - * API and drivers implementing get_settings API. When drivers - * implement get_link_ksettings and report higher link mode bits, a - * kernel warning is logged once (with name of 1st driver/device) to - * recommend user to upgrade ethtool, but the command is successful - * (only the lower link mode bits reported back to user). + * Backward compatibility note: for compatibility with legacy ethtool, this is + * now implemented via get_link_ksettings. When driver reports higher link mode + * bits, a kernel warning is logged once (with name of 1st driver/device) to + * recommend user to upgrade ethtool, but the command is successful (only the + * lower link mode bits reported back to user). Deprecated fields from + * ethtool_cmd (transceiver/maxrxpkt/maxtxpkt) are always set to zero. */ static int ethtool_get_settings(struct net_device *dev, void __user *useraddr) { + struct ethtool_link_ksettings link_ksettings; struct ethtool_cmd cmd; + int err; ASSERT_RTNL(); + if (!dev->ethtool_ops->get_link_ksettings) + return -EOPNOTSUPP; - if (dev->ethtool_ops->get_link_ksettings) { - /* First, use link_ksettings API if it is supported */ - int err; - struct ethtool_link_ksettings link_ksettings; - - memset(&link_ksettings, 0, sizeof(link_ksettings)); - err = dev->ethtool_ops->get_link_ksettings(dev, - &link_ksettings); - if (err < 0) - return err; - convert_link_ksettings_to_legacy_settings(&cmd, - &link_ksettings); - - /* send a sensible cmd tag back to user */ - cmd.cmd = ETHTOOL_GSET; - } else { - /* driver doesn't support %ethtool_link_ksettings - * API. revert to legacy %ethtool_cmd API, unless it's - * not supported either. - */ - int err; - - if (!dev->ethtool_ops->get_settings) - return -EOPNOTSUPP; + memset(&link_ksettings, 0, sizeof(link_ksettings)); + err = dev->ethtool_ops->get_link_ksettings(dev, &link_ksettings); + if (err < 0) + return err; + convert_link_ksettings_to_legacy_settings(&cmd, &link_ksettings); - memset(&cmd, 0, sizeof(cmd)); - cmd.cmd = ETHTOOL_GSET; - err = dev->ethtool_ops->get_settings(dev, &cmd); - if (err < 0) - return err; - } + /* send a sensible cmd tag back to user */ + cmd.cmd = ETHTOOL_GSET; if (copy_to_user(useraddr, &cmd, sizeof(cmd))) return -EFAULT; @@ -800,48 +731,29 @@ static int ethtool_get_settings(struct net_device *dev, void __user *useraddr) /* Update device link settings with given ethtool_cmd. * - * Backward compatibility note: for compatibility with legacy ethtool, - * this has to work with both drivers implementing set_link_ksettings - * API and drivers implementing set_settings API. When drivers - * implement set_link_ksettings and user's request updates deprecated - * ethtool_cmd fields (transceiver/maxrxpkt/maxtxpkt), a kernel - * warning is logged once (with name of 1st driver/device) to - * recommend user to upgrade ethtool, and the request is rejected. + * Backward compatibility note: for compatibility with legacy ethtool, this is + * now always implemented via set_link_settings. When user's request updates + * deprecated ethtool_cmd fields (transceiver/maxrxpkt/maxtxpkt), a kernel + * warning is logged once (with name of 1st driver/device) to recommend user to + * upgrade ethtool, and the request is rejected. */ static int ethtool_set_settings(struct net_device *dev, void __user *useraddr) { + struct ethtool_link_ksettings link_ksettings; struct ethtool_cmd cmd; ASSERT_RTNL(); if (copy_from_user(&cmd, useraddr, sizeof(cmd))) return -EFAULT; - - /* first, try new %ethtool_link_ksettings API. */ - if (dev->ethtool_ops->set_link_ksettings) { - struct ethtool_link_ksettings link_ksettings; - - if (!convert_legacy_settings_to_link_ksettings(&link_ksettings, - &cmd)) - return -EINVAL; - - link_ksettings.base.cmd = ETHTOOL_SLINKSETTINGS; - link_ksettings.base.link_mode_masks_nwords - = __ETHTOOL_LINK_MODE_MASK_NU32; - return dev->ethtool_ops->set_link_ksettings(dev, - &link_ksettings); - } - - /* legacy %ethtool_cmd API */ - - /* TODO: return -EOPNOTSUPP when ethtool_ops::get_settings - * disappears internally - */ - - if (!dev->ethtool_ops->set_settings) + if (!dev->ethtool_ops->set_link_ksettings) return -EOPNOTSUPP; - return dev->ethtool_ops->set_settings(dev, &cmd); + if (!convert_legacy_settings_to_link_ksettings(&link_ksettings, &cmd)) + return -EINVAL; + link_ksettings.base.link_mode_masks_nwords = + __ETHTOOL_LINK_MODE_MASK_NU32; + return dev->ethtool_ops->set_link_ksettings(dev, &link_ksettings); } static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev, diff --git a/net/core/filter.c b/net/core/filter.c index c25eb36f1320..0b40f95da21b 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2282,14 +2282,21 @@ static const struct bpf_func_proto bpf_msg_cork_bytes_proto = { .arg2_type = ARG_ANYTHING, }; +#define sk_msg_iter_var(var) \ + do { \ + var++; \ + if (var == MAX_SKB_FRAGS) \ + var = 0; \ + } while (0) + BPF_CALL_4(bpf_msg_pull_data, struct sk_msg_buff *, msg, u32, start, u32, end, u64, flags) { - unsigned int len = 0, offset = 0, copy = 0; + unsigned int len = 0, offset = 0, copy = 0, poffset = 0; + int bytes = end - start, bytes_sg_total; struct scatterlist *sg = msg->sg_data; int first_sg, last_sg, i, shift; unsigned char *p, *to, *from; - int bytes = end - start; struct page *page; if (unlikely(flags || end <= start)) @@ -2299,21 +2306,22 @@ BPF_CALL_4(bpf_msg_pull_data, i = msg->sg_start; do { len = sg[i].length; - offset += len; if (start < offset + len) break; - i++; - if (i == MAX_SKB_FRAGS) - i = 0; + offset += len; + sk_msg_iter_var(i); } while (i != msg->sg_end); if (unlikely(start >= offset + len)) return -EINVAL; - if (!msg->sg_copy[i] && bytes <= len) - goto out; - first_sg = i; + /* The start may point into the sg element so we need to also + * account for the headroom. + */ + bytes_sg_total = start - offset + bytes; + if (!msg->sg_copy[i] && bytes_sg_total <= len) + goto out; /* At this point we need to linearize multiple scatterlist * elements or a single shared page. Either way we need to @@ -2327,37 +2335,33 @@ BPF_CALL_4(bpf_msg_pull_data, */ do { copy += sg[i].length; - i++; - if (i == MAX_SKB_FRAGS) - i = 0; - if (bytes < copy) + sk_msg_iter_var(i); + if (bytes_sg_total <= copy) break; } while (i != msg->sg_end); last_sg = i; - if (unlikely(copy < end - start)) + if (unlikely(bytes_sg_total > copy)) return -EINVAL; - page = alloc_pages(__GFP_NOWARN | GFP_ATOMIC, get_order(copy)); + page = alloc_pages(__GFP_NOWARN | GFP_ATOMIC | __GFP_COMP, + get_order(copy)); if (unlikely(!page)) return -ENOMEM; p = page_address(page); - offset = 0; i = first_sg; do { from = sg_virt(&sg[i]); len = sg[i].length; - to = p + offset; + to = p + poffset; memcpy(to, from, len); - offset += len; + poffset += len; sg[i].length = 0; put_page(sg_page(&sg[i])); - i++; - if (i == MAX_SKB_FRAGS) - i = 0; + sk_msg_iter_var(i); } while (i != last_sg); sg[first_sg].length = copy; @@ -2367,11 +2371,15 @@ BPF_CALL_4(bpf_msg_pull_data, * had a single entry though we can just replace it and * be done. Otherwise walk the ring and shift the entries. */ - shift = last_sg - first_sg - 1; + WARN_ON_ONCE(last_sg == first_sg); + shift = last_sg > first_sg ? + last_sg - first_sg - 1 : + MAX_SKB_FRAGS - first_sg + last_sg - 1; if (!shift) goto out; - i = first_sg + 1; + i = first_sg; + sk_msg_iter_var(i); do { int move_from; @@ -2388,15 +2396,13 @@ BPF_CALL_4(bpf_msg_pull_data, sg[move_from].page_link = 0; sg[move_from].offset = 0; - i++; - if (i == MAX_SKB_FRAGS) - i = 0; + sk_msg_iter_var(i); } while (1); msg->sg_end -= shift; if (msg->sg_end < 0) msg->sg_end += MAX_SKB_FRAGS; out: - msg->data = sg_virt(&sg[i]) + start - offset; + msg->data = sg_virt(&sg[first_sg]) + start - offset; msg->data_end = msg->data + bytes; return 0; @@ -4007,6 +4013,12 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, tp->snd_ssthresh = val; } break; + case TCP_SAVE_SYN: + if (val < 0 || val > 1) + ret = -EINVAL; + else + tp->save_syn = val; + break; default: ret = -EINVAL; } @@ -4032,21 +4044,32 @@ static const struct bpf_func_proto bpf_setsockopt_proto = { BPF_CALL_5(bpf_getsockopt, struct bpf_sock_ops_kern *, bpf_sock, int, level, int, optname, char *, optval, int, optlen) { + struct inet_connection_sock *icsk; struct sock *sk = bpf_sock->sk; + struct tcp_sock *tp; if (!sk_fullsock(sk)) goto err_clear; - #ifdef CONFIG_INET if (level == SOL_TCP && sk->sk_prot->getsockopt == tcp_getsockopt) { - if (optname == TCP_CONGESTION) { - struct inet_connection_sock *icsk = inet_csk(sk); + switch (optname) { + case TCP_CONGESTION: + icsk = inet_csk(sk); if (!icsk->icsk_ca_ops || optlen <= 1) goto err_clear; strncpy(optval, icsk->icsk_ca_ops->name, optlen); optval[optlen - 1] = 0; - } else { + break; + case TCP_SAVED_SYN: + tp = tcp_sk(sk); + + if (optlen <= 0 || !tp->saved_syn || + optlen > tp->saved_syn[0]) + goto err_clear; + memcpy(optval, tp->saved_syn + 1, optlen); + break; + default: goto err_clear; } } else if (level == SOL_IP) { @@ -7281,7 +7304,7 @@ static u32 sk_reuseport_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct sk_reuseport_md, ip_protocol): - BUILD_BUG_ON(hweight_long(SK_FL_PROTO_MASK) != BITS_PER_BYTE); + BUILD_BUG_ON(HWEIGHT32(SK_FL_PROTO_MASK) != BITS_PER_BYTE); SK_REUSEPORT_LOAD_SK_FIELD_SIZE_OFF(__sk_flags_offset, BPF_W, 0); *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_PROTO_MASK); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index aa19d86937af..91592fceeaad 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1180,6 +1180,12 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, lladdr = neigh->ha; } + /* Update confirmed timestamp for neighbour entry after we + * received ARP packet even if it doesn't change IP to MAC binding. + */ + if (new & NUD_CONNECTED) + neigh->confirmed = jiffies; + /* If entry was valid and address is not changed, do not change entry state, if new one is STALE. */ @@ -1201,15 +1207,12 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, } } - /* Update timestamps only once we know we will make a change to the + /* Update timestamp only once we know we will make a change to the * neighbour entry. Otherwise we risk to move the locktime window with * noop updates and ignore relevant ARP updates. */ - if (new != old || lladdr != neigh->ha) { - if (new & NUD_CONNECTED) - neigh->confirmed = jiffies; + if (new != old || lladdr != neigh->ha) neigh->updated = jiffies; - } if (new != old) { neigh_del_timer(neigh); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 7f6938405fa1..6ac919847ce6 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3426,7 +3426,7 @@ xmit_more: net_info_ratelimited("%s xmit error: %d\n", pkt_dev->odevname, ret); pkt_dev->errors++; - /* fallthru */ + /* fall through */ case NETDEV_TX_BUSY: /* Retry it next time */ refcount_dec(&(pkt_dev->skb->users)); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 24431e578310..80a7e18c65fb 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -324,6 +324,10 @@ void rtnl_unregister_all(int protocol) rtnl_lock(); tab = rtnl_msg_handlers[protocol]; + if (!tab) { + rtnl_unlock(); + return; + } RCU_INIT_POINTER(rtnl_msg_handlers[protocol], NULL); for (msgindex = 0; msgindex < RTM_NR_MSGTYPES; msgindex++) { link = tab[msgindex]; @@ -1012,7 +1016,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(4) /* IFLA_NEW_NETNSID */ + nla_total_size(4) /* IFLA_NEW_IFINDEX */ + nla_total_size(1) /* IFLA_PROTO_DOWN */ - + nla_total_size(4) /* IFLA_IF_NETNSID */ + + nla_total_size(4) /* IFLA_TARGET_NETNSID */ + nla_total_size(4) /* IFLA_CARRIER_UP_COUNT */ + nla_total_size(4) /* IFLA_CARRIER_DOWN_COUNT */ + nla_total_size(4) /* IFLA_MIN_MTU */ @@ -1594,7 +1598,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, ifm->ifi_flags = dev_get_flags(dev); ifm->ifi_change = change; - if (tgt_netnsid >= 0 && nla_put_s32(skb, IFLA_IF_NETNSID, tgt_netnsid)) + if (tgt_netnsid >= 0 && nla_put_s32(skb, IFLA_TARGET_NETNSID, tgt_netnsid)) goto nla_put_failure; if (nla_put_string(skb, IFLA_IFNAME, dev->name) || @@ -1733,7 +1737,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_XDP] = { .type = NLA_NESTED }, [IFLA_EVENT] = { .type = NLA_U32 }, [IFLA_GROUP] = { .type = NLA_U32 }, - [IFLA_IF_NETNSID] = { .type = NLA_S32 }, + [IFLA_TARGET_NETNSID] = { .type = NLA_S32 }, [IFLA_CARRIER_UP_COUNT] = { .type = NLA_U32 }, [IFLA_CARRIER_DOWN_COUNT] = { .type = NLA_U32 }, [IFLA_MIN_MTU] = { .type = NLA_U32 }, @@ -1841,7 +1845,15 @@ static bool link_dump_filtered(struct net_device *dev, return false; } -static struct net *get_target_net(struct sock *sk, int netnsid) +/** + * rtnl_get_net_ns_capable - Get netns if sufficiently privileged. + * @sk: netlink socket + * @netnsid: network namespace identifier + * + * Returns the network namespace identified by netnsid on success or an error + * pointer on failure. + */ +struct net *rtnl_get_net_ns_capable(struct sock *sk, int netnsid) { struct net *net; @@ -1858,6 +1870,7 @@ static struct net *get_target_net(struct sock *sk, int netnsid) } return net; } +EXPORT_SYMBOL_GPL(rtnl_get_net_ns_capable); static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) { @@ -1891,9 +1904,9 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) if (nlmsg_parse(cb->nlh, hdrlen, tb, IFLA_MAX, ifla_policy, NULL) >= 0) { - if (tb[IFLA_IF_NETNSID]) { - netnsid = nla_get_s32(tb[IFLA_IF_NETNSID]); - tgt_net = get_target_net(skb->sk, netnsid); + if (tb[IFLA_TARGET_NETNSID]) { + netnsid = nla_get_s32(tb[IFLA_TARGET_NETNSID]); + tgt_net = rtnl_get_net_ns_capable(skb->sk, netnsid); if (IS_ERR(tgt_net)) { tgt_net = net; netnsid = -1; @@ -1980,7 +1993,7 @@ EXPORT_SYMBOL(rtnl_link_get_net); * * 1. IFLA_NET_NS_PID * 2. IFLA_NET_NS_FD - * 3. IFLA_IF_NETNSID + * 3. IFLA_TARGET_NETNSID */ static struct net *rtnl_link_get_net_by_nlattr(struct net *src_net, struct nlattr *tb[]) @@ -1990,10 +2003,10 @@ static struct net *rtnl_link_get_net_by_nlattr(struct net *src_net, if (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD]) return rtnl_link_get_net(src_net, tb); - if (!tb[IFLA_IF_NETNSID]) + if (!tb[IFLA_TARGET_NETNSID]) return get_net(src_net); - net = get_net_ns_by_id(src_net, nla_get_u32(tb[IFLA_IF_NETNSID])); + net = get_net_ns_by_id(src_net, nla_get_u32(tb[IFLA_TARGET_NETNSID])); if (!net) return ERR_PTR(-EINVAL); @@ -2034,13 +2047,13 @@ static int rtnl_ensure_unique_netns(struct nlattr *tb[], return -EOPNOTSUPP; } - if (tb[IFLA_IF_NETNSID] && (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD])) + if (tb[IFLA_TARGET_NETNSID] && (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD])) goto invalid_attr; - if (tb[IFLA_NET_NS_PID] && (tb[IFLA_IF_NETNSID] || tb[IFLA_NET_NS_FD])) + if (tb[IFLA_NET_NS_PID] && (tb[IFLA_TARGET_NETNSID] || tb[IFLA_NET_NS_FD])) goto invalid_attr; - if (tb[IFLA_NET_NS_FD] && (tb[IFLA_IF_NETNSID] || tb[IFLA_NET_NS_PID])) + if (tb[IFLA_NET_NS_FD] && (tb[IFLA_TARGET_NETNSID] || tb[IFLA_NET_NS_PID])) goto invalid_attr; return 0; @@ -2316,7 +2329,7 @@ static int do_setlink(const struct sk_buff *skb, if (err < 0) return err; - if (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD] || tb[IFLA_IF_NETNSID]) { + if (tb[IFLA_NET_NS_PID] || tb[IFLA_NET_NS_FD] || tb[IFLA_TARGET_NETNSID]) { struct net *net = rtnl_link_get_net_capable(skb, dev_net(dev), tb, CAP_NET_ADMIN); if (IS_ERR(net)) { @@ -2759,9 +2772,9 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, if (tb[IFLA_IFNAME]) nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ); - if (tb[IFLA_IF_NETNSID]) { - netnsid = nla_get_s32(tb[IFLA_IF_NETNSID]); - tgt_net = get_target_net(NETLINK_CB(skb).sk, netnsid); + if (tb[IFLA_TARGET_NETNSID]) { + netnsid = nla_get_s32(tb[IFLA_TARGET_NETNSID]); + tgt_net = rtnl_get_net_ns_capable(NETLINK_CB(skb).sk, netnsid); if (IS_ERR(tgt_net)) return PTR_ERR(tgt_net); } @@ -2806,7 +2819,7 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm) } if (dev->rtnl_link_state == RTNL_LINK_INITIALIZED) { - __dev_notify_flags(dev, old_flags, 0U); + __dev_notify_flags(dev, old_flags, (old_flags ^ dev->flags)); } else { dev->rtnl_link_state = RTNL_LINK_INITIALIZED; __dev_notify_flags(dev, old_flags, ~0U); @@ -3169,9 +3182,9 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh, if (err < 0) return err; - if (tb[IFLA_IF_NETNSID]) { - netnsid = nla_get_s32(tb[IFLA_IF_NETNSID]); - tgt_net = get_target_net(NETLINK_CB(skb).sk, netnsid); + if (tb[IFLA_TARGET_NETNSID]) { + netnsid = nla_get_s32(tb[IFLA_TARGET_NETNSID]); + tgt_net = rtnl_get_net_ns_capable(NETLINK_CB(skb).sk, netnsid); if (IS_ERR(tgt_net)) return PTR_ERR(tgt_net); } @@ -3256,13 +3269,13 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) { int idx; int s_idx = cb->family; + int type = cb->nlh->nlmsg_type - RTM_BASE; if (s_idx == 0) s_idx = 1; for (idx = 1; idx <= RTNL_FAMILY_MAX; idx++) { struct rtnl_link **tab; - int type = cb->nlh->nlmsg_type-RTM_BASE; struct rtnl_link *link; rtnl_dumpit_func dumpit; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index c996c09d095f..b2c807f67aba 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -939,9 +939,6 @@ struct ubuf_info *sock_zerocopy_alloc(struct sock *sk, size_t size) WARN_ON_ONCE(!in_task()); - if (!sock_flag(sk, SOCK_ZEROCOPY)) - return NULL; - skb = sock_omalloc(sk, 0, GFP_KERNEL); if (!skb) return NULL; diff --git a/net/core/sock.c b/net/core/sock.c index 3730eb855095..8537b6ca72c5 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2332,7 +2332,7 @@ static void __release_sock(struct sock *sk) next = skb->next; prefetch(next); WARN_ON_ONCE(skb_dst_is_noref(skb)); - skb->next = NULL; + skb_mark_not_on_list(skb); sk_backlog_rcv(sk, skb); cond_resched(); diff --git a/net/core/xdp.c b/net/core/xdp.c index 89b6785cef2a..4b2b194f4f1f 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -94,11 +94,21 @@ static void __xdp_mem_allocator_rcu_free(struct rcu_head *rcu) kfree(xa); } -static void __xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq) +void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq) { struct xdp_mem_allocator *xa; int id = xdp_rxq->mem.id; + if (xdp_rxq->reg_state != REG_STATE_REGISTERED) { + WARN(1, "Missing register, driver bug"); + return; + } + + if (xdp_rxq->mem.type != MEM_TYPE_PAGE_POOL && + xdp_rxq->mem.type != MEM_TYPE_ZERO_COPY) { + return; + } + if (id == 0) return; @@ -110,6 +120,7 @@ static void __xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq) mutex_unlock(&mem_id_lock); } +EXPORT_SYMBOL_GPL(xdp_rxq_info_unreg_mem_model); void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq) { @@ -119,7 +130,7 @@ void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq) WARN(!(xdp_rxq->reg_state == REG_STATE_REGISTERED), "Driver BUG"); - __xdp_rxq_info_unreg_mem_model(xdp_rxq); + xdp_rxq_info_unreg_mem_model(xdp_rxq); xdp_rxq->reg_state = REG_STATE_UNREGISTERED; xdp_rxq->dev = NULL; @@ -398,3 +409,41 @@ void xdp_attachment_setup(struct xdp_attachment_info *info, info->flags = bpf->flags; } EXPORT_SYMBOL_GPL(xdp_attachment_setup); + +struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp) +{ + unsigned int metasize, totsize; + void *addr, *data_to_copy; + struct xdp_frame *xdpf; + struct page *page; + + /* Clone into a MEM_TYPE_PAGE_ORDER0 xdp_frame. */ + metasize = xdp_data_meta_unsupported(xdp) ? 0 : + xdp->data - xdp->data_meta; + totsize = xdp->data_end - xdp->data + metasize; + + if (sizeof(*xdpf) + totsize > PAGE_SIZE) + return NULL; + + page = dev_alloc_page(); + if (!page) + return NULL; + + addr = page_to_virt(page); + xdpf = addr; + memset(xdpf, 0, sizeof(*xdpf)); + + addr += sizeof(*xdpf); + data_to_copy = metasize ? xdp->data_meta : xdp->data; + memcpy(addr, data_to_copy, totsize); + + xdpf->data = addr + metasize; + xdpf->len = totsize - metasize; + xdpf->headroom = 0; + xdpf->metasize = metasize; + xdpf->mem.type = MEM_TYPE_PAGE_ORDER0; + + xdp_return_buff(xdp); + return xdpf; +} +EXPORT_SYMBOL_GPL(xdp_convert_zc_to_xdp_frame); diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 4183e4ba27a5..48c41918fb35 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -38,6 +38,9 @@ config NET_DSA_TAG_DSA config NET_DSA_TAG_EDSA bool +config NET_DSA_TAG_GSWIP + bool + config NET_DSA_TAG_KSZ bool diff --git a/net/dsa/Makefile b/net/dsa/Makefile index 9e4d3536f977..6e721f7a2947 100644 --- a/net/dsa/Makefile +++ b/net/dsa/Makefile @@ -9,6 +9,7 @@ dsa_core-$(CONFIG_NET_DSA_TAG_BRCM) += tag_brcm.o dsa_core-$(CONFIG_NET_DSA_TAG_BRCM_PREPEND) += tag_brcm.o dsa_core-$(CONFIG_NET_DSA_TAG_DSA) += tag_dsa.o dsa_core-$(CONFIG_NET_DSA_TAG_EDSA) += tag_edsa.o +dsa_core-$(CONFIG_NET_DSA_TAG_GSWIP) += tag_gswip.o dsa_core-$(CONFIG_NET_DSA_TAG_KSZ) += tag_ksz.o dsa_core-$(CONFIG_NET_DSA_TAG_LAN9303) += tag_lan9303.o dsa_core-$(CONFIG_NET_DSA_TAG_MTK) += tag_mtk.o diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index e63c554e0623..a69c1790bbfc 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -19,12 +19,10 @@ #include <linux/of_mdio.h> #include <linux/of_platform.h> #include <linux/of_net.h> -#include <linux/of_gpio.h> #include <linux/netdevice.h> #include <linux/sysfs.h> #include <linux/phy_fixed.h> #include <linux/ptp_classify.h> -#include <linux/gpio/consumer.h> #include <linux/etherdevice.h> #include "dsa_priv.h" @@ -54,6 +52,9 @@ const struct dsa_device_ops *dsa_device_ops[DSA_TAG_LAST] = { #ifdef CONFIG_NET_DSA_TAG_EDSA [DSA_TAG_PROTO_EDSA] = &edsa_netdev_ops, #endif +#ifdef CONFIG_NET_DSA_TAG_GSWIP + [DSA_TAG_PROTO_GSWIP] = &gswip_netdev_ops, +#endif #ifdef CONFIG_NET_DSA_TAG_KSZ [DSA_TAG_PROTO_KSZ] = &ksz_netdev_ops, #endif @@ -72,6 +73,52 @@ const struct dsa_device_ops *dsa_device_ops[DSA_TAG_LAST] = { [DSA_TAG_PROTO_NONE] = &none_ops, }; +const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops) +{ + const char *protocol_name[DSA_TAG_LAST] = { +#ifdef CONFIG_NET_DSA_TAG_BRCM + [DSA_TAG_PROTO_BRCM] = "brcm", +#endif +#ifdef CONFIG_NET_DSA_TAG_BRCM_PREPEND + [DSA_TAG_PROTO_BRCM_PREPEND] = "brcm-prepend", +#endif +#ifdef CONFIG_NET_DSA_TAG_DSA + [DSA_TAG_PROTO_DSA] = "dsa", +#endif +#ifdef CONFIG_NET_DSA_TAG_EDSA + [DSA_TAG_PROTO_EDSA] = "edsa", +#endif +#ifdef CONFIG_NET_DSA_TAG_GSWIP + [DSA_TAG_PROTO_GSWIP] = "gswip", +#endif +#ifdef CONFIG_NET_DSA_TAG_KSZ + [DSA_TAG_PROTO_KSZ] = "ksz", +#endif +#ifdef CONFIG_NET_DSA_TAG_LAN9303 + [DSA_TAG_PROTO_LAN9303] = "lan9303", +#endif +#ifdef CONFIG_NET_DSA_TAG_MTK + [DSA_TAG_PROTO_MTK] = "mtk", +#endif +#ifdef CONFIG_NET_DSA_TAG_QCA + [DSA_TAG_PROTO_QCA] = "qca", +#endif +#ifdef CONFIG_NET_DSA_TAG_TRAILER + [DSA_TAG_PROTO_TRAILER] = "trailer", +#endif + [DSA_TAG_PROTO_NONE] = "none", + }; + unsigned int i; + + BUILD_BUG_ON(ARRAY_SIZE(protocol_name) != DSA_TAG_LAST); + + for (i = 0; i < ARRAY_SIZE(dsa_device_ops); i++) + if (ops == dsa_device_ops[i]) + return protocol_name[i]; + + return protocol_name[DSA_TAG_PROTO_NONE]; +}; + const struct dsa_device_ops *dsa_resolve_tag_protocol(int tag_protocol) { const struct dsa_device_ops *ops; diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 3964c6f7a7c0..9e4fd04ab53c 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -86,6 +86,7 @@ struct dsa_slave_priv { /* dsa.c */ const struct dsa_device_ops *dsa_resolve_tag_protocol(int tag_protocol); bool dsa_schedule_work(struct work_struct *work); +const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops); /* legacy.c */ #if IS_ENABLED(CONFIG_NET_DSA_LEGACY) @@ -205,6 +206,9 @@ extern const struct dsa_device_ops dsa_netdev_ops; /* tag_edsa.c */ extern const struct dsa_device_ops edsa_netdev_ops; +/* tag_gswip.c */ +extern const struct dsa_device_ops gswip_netdev_ops; + /* tag_ksz.c */ extern const struct dsa_device_ops ksz_netdev_ops; diff --git a/net/dsa/legacy.c b/net/dsa/legacy.c index 42a7b85b84e1..8aa92b09db76 100644 --- a/net/dsa/legacy.c +++ b/net/dsa/legacy.c @@ -392,8 +392,7 @@ static void dsa_of_free_platform_data(struct dsa_platform_data *pd) } /* Drop our reference to the MDIO bus device */ - if (pd->chip[i].host_dev) - put_device(pd->chip[i].host_dev); + put_device(pd->chip[i].host_dev); } kfree(pd->chip); } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 962c4fd338ba..3f840b6eea69 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -767,7 +767,6 @@ static int dsa_slave_add_cls_matchall(struct net_device *dev, const struct tc_action *a; struct dsa_port *to_dp; int err = -EOPNOTSUPP; - LIST_HEAD(actions); if (!ds->ops->port_mirror_add) return err; @@ -775,8 +774,7 @@ static int dsa_slave_add_cls_matchall(struct net_device *dev, if (!tcf_exts_has_one_action(cls->exts)) return err; - tcf_exts_to_list(cls->exts, &actions); - a = list_first_entry(&actions, struct tc_action, list); + a = tcf_exts_first_action(cls->exts); if (is_tcf_mirred_egress_mirror(a) && protocol == htons(ETH_P_ALL)) { struct dsa_mall_mirror_tc_entry *mirror; @@ -1060,6 +1058,27 @@ static struct device_type dsa_type = { .name = "dsa", }; +static ssize_t tagging_show(struct device *d, struct device_attribute *attr, + char *buf) +{ + struct net_device *dev = to_net_dev(d); + struct dsa_port *dp = dsa_slave_to_port(dev); + + return sprintf(buf, "%s\n", + dsa_tag_protocol_to_str(dp->cpu_dp->tag_ops)); +} +static DEVICE_ATTR_RO(tagging); + +static struct attribute *dsa_slave_attrs[] = { + &dev_attr_tagging.attr, + NULL +}; + +static const struct attribute_group dsa_group = { + .name = "dsa", + .attrs = dsa_slave_attrs, +}; + static void dsa_slave_phylink_validate(struct net_device *dev, unsigned long *supported, struct phylink_link_state *state) @@ -1355,8 +1374,14 @@ int dsa_slave_create(struct dsa_port *port) goto out_phy; } + ret = sysfs_create_group(&slave_dev->dev.kobj, &dsa_group); + if (ret) + goto out_unreg; + return 0; +out_unreg: + unregister_netdev(slave_dev); out_phy: rtnl_lock(); phylink_disconnect_phy(p->dp->pl); @@ -1380,6 +1405,7 @@ void dsa_slave_destroy(struct net_device *slave_dev) rtnl_unlock(); dsa_slave_notify(slave_dev, DSA_PORT_UNREGISTER); + sysfs_remove_group(&slave_dev->dev.kobj, &dsa_group); unregister_netdev(slave_dev); phylink_destroy(dp->pl); free_percpu(p->stats64); diff --git a/net/dsa/tag_gswip.c b/net/dsa/tag_gswip.c new file mode 100644 index 000000000000..49e9b73f1be3 --- /dev/null +++ b/net/dsa/tag_gswip.c @@ -0,0 +1,109 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Intel / Lantiq GSWIP V2.0 PMAC tag support + * + * Copyright (C) 2017 - 2018 Hauke Mehrtens <hauke@hauke-m.de> + */ + +#include <linux/bitops.h> +#include <linux/etherdevice.h> +#include <linux/skbuff.h> +#include <net/dsa.h> + +#include "dsa_priv.h" + +#define GSWIP_TX_HEADER_LEN 4 + +/* special tag in TX path header */ +/* Byte 0 */ +#define GSWIP_TX_SLPID_SHIFT 0 /* source port ID */ +#define GSWIP_TX_SLPID_CPU 2 +#define GSWIP_TX_SLPID_APP1 3 +#define GSWIP_TX_SLPID_APP2 4 +#define GSWIP_TX_SLPID_APP3 5 +#define GSWIP_TX_SLPID_APP4 6 +#define GSWIP_TX_SLPID_APP5 7 + +/* Byte 1 */ +#define GSWIP_TX_CRCGEN_DIS BIT(7) +#define GSWIP_TX_DPID_SHIFT 0 /* destination group ID */ +#define GSWIP_TX_DPID_ELAN 0 +#define GSWIP_TX_DPID_EWAN 1 +#define GSWIP_TX_DPID_CPU 2 +#define GSWIP_TX_DPID_APP1 3 +#define GSWIP_TX_DPID_APP2 4 +#define GSWIP_TX_DPID_APP3 5 +#define GSWIP_TX_DPID_APP4 6 +#define GSWIP_TX_DPID_APP5 7 + +/* Byte 2 */ +#define GSWIP_TX_PORT_MAP_EN BIT(7) +#define GSWIP_TX_PORT_MAP_SEL BIT(6) +#define GSWIP_TX_LRN_DIS BIT(5) +#define GSWIP_TX_CLASS_EN BIT(4) +#define GSWIP_TX_CLASS_SHIFT 0 +#define GSWIP_TX_CLASS_MASK GENMASK(3, 0) + +/* Byte 3 */ +#define GSWIP_TX_DPID_EN BIT(0) +#define GSWIP_TX_PORT_MAP_SHIFT 1 +#define GSWIP_TX_PORT_MAP_MASK GENMASK(6, 1) + +#define GSWIP_RX_HEADER_LEN 8 + +/* special tag in RX path header */ +/* Byte 7 */ +#define GSWIP_RX_SPPID_SHIFT 4 +#define GSWIP_RX_SPPID_MASK GENMASK(6, 4) + +static struct sk_buff *gswip_tag_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + int err; + u8 *gswip_tag; + + err = skb_cow_head(skb, GSWIP_TX_HEADER_LEN); + if (err) + return NULL; + + skb_push(skb, GSWIP_TX_HEADER_LEN); + + gswip_tag = skb->data; + gswip_tag[0] = GSWIP_TX_SLPID_CPU; + gswip_tag[1] = GSWIP_TX_DPID_ELAN; + gswip_tag[2] = GSWIP_TX_PORT_MAP_EN | GSWIP_TX_PORT_MAP_SEL; + gswip_tag[3] = BIT(dp->index + GSWIP_TX_PORT_MAP_SHIFT) & GSWIP_TX_PORT_MAP_MASK; + gswip_tag[3] |= GSWIP_TX_DPID_EN; + + return skb; +} + +static struct sk_buff *gswip_tag_rcv(struct sk_buff *skb, + struct net_device *dev, + struct packet_type *pt) +{ + int port; + u8 *gswip_tag; + + if (unlikely(!pskb_may_pull(skb, GSWIP_RX_HEADER_LEN))) + return NULL; + + gswip_tag = skb->data - ETH_HLEN; + + /* Get source port information */ + port = (gswip_tag[7] & GSWIP_RX_SPPID_MASK) >> GSWIP_RX_SPPID_SHIFT; + skb->dev = dsa_master_find_slave(dev, 0, port); + if (!skb->dev) + return NULL; + + /* remove GSWIP tag */ + skb_pull_rcsum(skb, GSWIP_RX_HEADER_LEN); + + return skb; +} + +const struct dsa_device_ops gswip_netdev_ops = { + .xmit = gswip_tag_xmit, + .rcv = gswip_tag_rcv, +}; diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c index e7857a8ac86d..09ffbf5ce8fa 100644 --- a/net/ieee802154/6lowpan/reassembly.c +++ b/net/ieee802154/6lowpan/reassembly.c @@ -260,7 +260,7 @@ 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; + skb_mark_not_on_list(head); head->dev = ldev; head->tstamp = fq->q.stamp; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 20fda8fb8ffd..1fbe2f815474 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1377,6 +1377,7 @@ struct sk_buff *inet_gso_segment(struct sk_buff *skb, if (encap) skb_reset_inner_headers(skb); skb->network_header = (u8 *)iph - skb->head; + skb_reset_mac_len(skb); } while ((skb = skb->next)); out: diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 82178cc69c96..777fa3b7fb13 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1512,7 +1512,7 @@ static int cipso_v4_parsetag_loc(const struct cipso_v4_doi *doi_def, * * Description: * Parse the packet's IP header looking for a CIPSO option. Returns a pointer - * to the start of the CIPSO option on success, NULL if one if not found. + * to the start of the CIPSO option on success, NULL if one is not found. * */ unsigned char *cipso_v4_optptr(const struct sk_buff *skb) @@ -1522,10 +1522,8 @@ unsigned char *cipso_v4_optptr(const struct sk_buff *skb) int optlen; int taglen; - for (optlen = iph->ihl*4 - sizeof(struct iphdr); optlen > 0; ) { + for (optlen = iph->ihl*4 - sizeof(struct iphdr); optlen > 1; ) { switch (optptr[0]) { - case IPOPT_CIPSO: - return optptr; case IPOPT_END: return NULL; case IPOPT_NOOP: @@ -1534,6 +1532,11 @@ unsigned char *cipso_v4_optptr(const struct sk_buff *skb) default: taglen = optptr[1]; } + if (!taglen || taglen > optlen) + return NULL; + if (optptr[0] == IPOPT_CIPSO) + return optptr; + optlen -= taglen; optptr += taglen; } diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index ea4bd8a52422..44d931a3cd50 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -100,6 +100,15 @@ static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = { [IFA_CACHEINFO] = { .len = sizeof(struct ifa_cacheinfo) }, [IFA_FLAGS] = { .type = NLA_U32 }, [IFA_RT_PRIORITY] = { .type = NLA_U32 }, + [IFA_TARGET_NETNSID] = { .type = NLA_S32 }, +}; + +struct inet_fill_args { + u32 portid; + u32 seq; + int event; + unsigned int flags; + int netnsid; }; #define IN4_ADDR_HSIZE_SHIFT 8 @@ -1584,13 +1593,14 @@ static int put_cacheinfo(struct sk_buff *skb, unsigned long cstamp, } static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, - u32 portid, u32 seq, int event, unsigned int flags) + struct inet_fill_args *args) { struct ifaddrmsg *ifm; struct nlmsghdr *nlh; u32 preferred, valid; - nlh = nlmsg_put(skb, portid, seq, event, sizeof(*ifm), flags); + nlh = nlmsg_put(skb, args->portid, args->seq, args->event, sizeof(*ifm), + args->flags); if (!nlh) return -EMSGSIZE; @@ -1601,6 +1611,10 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, ifm->ifa_scope = ifa->ifa_scope; ifm->ifa_index = ifa->ifa_dev->dev->ifindex; + if (args->netnsid >= 0 && + nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) + goto nla_put_failure; + if (!(ifm->ifa_flags & IFA_F_PERMANENT)) { preferred = ifa->ifa_preferred_lft; valid = ifa->ifa_valid_lft; @@ -1647,7 +1661,16 @@ nla_put_failure: static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) { + struct inet_fill_args fillargs = { + .portid = NETLINK_CB(cb->skb).portid, + .seq = cb->nlh->nlmsg_seq, + .event = RTM_NEWADDR, + .flags = NLM_F_MULTI, + .netnsid = -1, + }; struct net *net = sock_net(skb->sk); + struct nlattr *tb[IFA_MAX+1]; + struct net *tgt_net = net; int h, s_h; int idx, s_idx; int ip_idx, s_ip_idx; @@ -1660,12 +1683,24 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) s_idx = idx = cb->args[1]; s_ip_idx = ip_idx = cb->args[2]; + if (nlmsg_parse(cb->nlh, sizeof(struct ifaddrmsg), tb, IFA_MAX, + ifa_ipv4_policy, NULL) >= 0) { + if (tb[IFA_TARGET_NETNSID]) { + fillargs.netnsid = nla_get_s32(tb[IFA_TARGET_NETNSID]); + + tgt_net = rtnl_get_net_ns_capable(skb->sk, + fillargs.netnsid); + if (IS_ERR(tgt_net)) + return PTR_ERR(tgt_net); + } + } + for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; - head = &net->dev_index_head[h]; + head = &tgt_net->dev_index_head[h]; rcu_read_lock(); - cb->seq = atomic_read(&net->ipv4.dev_addr_genid) ^ - net->dev_base_seq; + cb->seq = atomic_read(&tgt_net->ipv4.dev_addr_genid) ^ + tgt_net->dev_base_seq; hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; @@ -1679,10 +1714,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) ifa = ifa->ifa_next, ip_idx++) { if (ip_idx < s_ip_idx) continue; - if (inet_fill_ifaddr(skb, ifa, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - RTM_NEWADDR, NLM_F_MULTI) < 0) { + if (inet_fill_ifaddr(skb, ifa, &fillargs) < 0) { rcu_read_unlock(); goto done; } @@ -1698,6 +1730,8 @@ done: cb->args[0] = h; cb->args[1] = idx; cb->args[2] = ip_idx; + if (fillargs.netnsid >= 0) + put_net(tgt_net); return skb->len; } @@ -1705,8 +1739,14 @@ done: static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh, u32 portid) { + struct inet_fill_args fillargs = { + .portid = portid, + .seq = nlh ? nlh->nlmsg_seq : 0, + .event = event, + .flags = 0, + .netnsid = -1, + }; struct sk_buff *skb; - u32 seq = nlh ? nlh->nlmsg_seq : 0; int err = -ENOBUFS; struct net *net; @@ -1715,7 +1755,7 @@ static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh, if (!skb) goto errout; - err = inet_fill_ifaddr(skb, ifa, portid, seq, event, 0); + err = inet_fill_ifaddr(skb, ifa, &fillargs); if (err < 0) { /* -EMSGSIZE implies BUG in inet_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index f3c89ccf14c5..bee8db979195 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -797,8 +797,10 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_nh *nh, return -EINVAL; } dev = __dev_get_by_index(net, nh->nh_oif); - if (!dev) + if (!dev) { + NL_SET_ERR_MSG(extack, "Nexthop device required for onlink"); return -ENODEV; + } if (!(dev->flags & IFF_UP)) { NL_SET_ERR_MSG(extack, "Nexthop device is not up"); diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c index b798862b6be5..7efe740c06eb 100644 --- a/net/ipv4/gre_demux.c +++ b/net/ipv4/gre_demux.c @@ -86,13 +86,14 @@ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, options = (__be32 *)(greh + 1); if (greh->flags & GRE_CSUM) { - if (skb_checksum_simple_validate(skb)) { + if (!skb_checksum_simple_validate(skb)) { + skb_checksum_try_convert(skb, IPPROTO_GRE, 0, + null_compute_pseudo); + } else if (csum_err) { *csum_err = true; return -EINVAL; } - skb_checksum_try_convert(skb, IPPROTO_GRE, 0, - null_compute_pseudo); options++; } diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index cf75f8944b05..4da39446da2d 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -820,10 +820,9 @@ static void igmp_timer_expire(struct timer_list *t) spin_lock(&im->lock); im->tm_running = 0; - if (im->unsolicit_count) { - im->unsolicit_count--; + if (im->unsolicit_count && --im->unsolicit_count) igmp_start_timer(im, unsolicited_report_interval(in_dev)); - } + im->reporter = 1; spin_unlock(&im->lock); @@ -1308,6 +1307,8 @@ static void igmp_group_added(struct ip_mc_list *im) if (in_dev->dead) return; + + im->unsolicit_count = net->ipv4.sysctl_igmp_qrv; if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) { spin_lock_bh(&im->lock); igmp_start_timer(im, IGMP_INITIAL_REPORT_DELAY); @@ -1391,9 +1392,6 @@ static void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, unsigned int mode) { struct ip_mc_list *im; -#ifdef CONFIG_IP_MULTICAST - struct net *net = dev_net(in_dev->dev); -#endif ASSERT_RTNL(); @@ -1420,7 +1418,6 @@ static void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, spin_lock_init(&im->lock); #ifdef CONFIG_IP_MULTICAST timer_setup(&im->timer, igmp_timer_expire, 0); - im->unsolicit_count = net->ipv4.sysctl_igmp_qrv; #endif im->next_rcu = in_dev->mc_list; diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 88281fbce88c..da930b01a147 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -382,7 +382,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) */ if (end < qp->q.len || ((qp->q.flags & INET_FRAG_LAST_IN) && end != qp->q.len)) - goto err; + goto discard_qp; qp->q.flags |= INET_FRAG_LAST_IN; qp->q.len = end; } else { @@ -394,20 +394,20 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) if (end > qp->q.len) { /* Some bits beyond end -> corruption. */ if (qp->q.flags & INET_FRAG_LAST_IN) - goto err; + goto discard_qp; qp->q.len = end; } } if (end == offset) - goto err; + goto discard_qp; err = -ENOMEM; if (!pskb_pull(skb, skb_network_offset(skb) + ihl)) - goto err; + goto discard_qp; err = pskb_trim_rcsum(skb, end - offset); if (err) - goto err; + goto discard_qp; /* Note : skb->rbnode and skb->dev share the same location. */ dev = skb->dev; @@ -423,6 +423,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) * We do the same here for IPv4 (and increment an snmp counter). */ + err = -EINVAL; /* Find out where to put this fragment. */ prev_tail = qp->q.fragments_tail; if (!prev_tail) @@ -431,7 +432,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) /* This is the common case: skb goes to the end. */ /* Detect and discard overlaps. */ if (offset < prev_tail->ip_defrag_offset + prev_tail->len) - goto discard_qp; + goto overlap; if (offset == prev_tail->ip_defrag_offset + prev_tail->len) ip4_frag_append_to_last_run(&qp->q, skb); else @@ -450,7 +451,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) FRAG_CB(skb1)->frag_run_len) rbn = &parent->rb_right; else /* Found an overlap with skb1. */ - goto discard_qp; + goto overlap; } while (*rbn); /* Here we have parent properly set, and rbn pointing to * one of its NULL left/right children. Insert skb. @@ -487,16 +488,18 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) skb->_skb_refdst = 0UL; err = ip_frag_reasm(qp, skb, prev_tail, dev); skb->_skb_refdst = orefdst; + if (err) + inet_frag_kill(&qp->q); return err; } skb_dst_drop(skb); return -EINPROGRESS; +overlap: + __IP_INC_STATS(net, IPSTATS_MIB_REASM_OVERLAPS); discard_qp: inet_frag_kill(&qp->q); - err = -EINVAL; - __IP_INC_STATS(net, IPSTATS_MIB_REASM_OVERLAPS); err: kfree_skb(skb); return err; @@ -599,6 +602,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, nextp = &fp->next; fp->prev = NULL; memset(&fp->rbnode, 0, sizeof(fp->rbnode)); + fp->sk = NULL; head->data_len += fp->len; head->len += fp->len; if (head->ip_summed != fp->ip_summed) @@ -620,7 +624,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, sub_frag_mem_limit(qp->q.net, head->truesize); *nextp = NULL; - head->next = NULL; + skb_mark_not_on_list(head); head->prev = NULL; head->dev = dev; head->tstamp = qp->q.stamp; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 51a5d06085ac..c3385a84f8ff 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -178,6 +178,9 @@ static void ipgre_err(struct sk_buff *skb, u32 info, if (tpi->proto == htons(ETH_P_TEB)) itn = net_generic(net, gre_tap_net_id); + else if (tpi->proto == htons(ETH_P_ERSPAN) || + tpi->proto == htons(ETH_P_ERSPAN2)) + itn = net_generic(net, erspan_net_id); else itn = net_generic(net, ipgre_net_id); @@ -229,13 +232,10 @@ static void gre_err(struct sk_buff *skb, u32 info) const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct tnl_ptk_info tpi; - bool csum_err = false; - if (gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IP), - iph->ihl * 4) < 0) { - if (!csum_err) /* ignore csum errors. */ - return; - } + if (gre_parse_header(skb, &tpi, NULL, htons(ETH_P_IP), + iph->ihl * 4) < 0) + return; if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { ipv4_update_pmtu(skb, dev_net(skb->dev), info, @@ -328,6 +328,8 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, ip_tunnel_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); return PACKET_RCVD; } + return PACKET_REJECT; + drop: kfree_skb(skb); return PACKET_RCVD; @@ -1508,11 +1510,14 @@ nla_put_failure: static void erspan_setup(struct net_device *dev) { + struct ip_tunnel *t = netdev_priv(dev); + ether_setup(dev); dev->netdev_ops = &erspan_netdev_ops; dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; ip_tunnel_setup(dev, erspan_net_id); + t->erspan_ver = 1; } static const struct nla_policy ipgre_policy[IFLA_GRE_MAX + 1] = { diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 3196cf58f418..35a786c0aaa0 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -531,11 +531,7 @@ static void ip_sublist_rcv_finish(struct list_head *head) struct sk_buff *skb, *next; list_for_each_entry_safe(skb, next, head, list) { - list_del(&skb->list); - /* Handle ip{6}_forward case, as sch_direct_xmit have - * another kind of SKB-list usage (see validate_xmit_skb_list) - */ - skb->next = NULL; + skb_list_del_init(skb); dst_input(skb); } } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 9c4e72e9c60a..c09219e7f230 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -278,7 +278,7 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk, struct sk_buff *nskb = segs->next; int err; - segs->next = NULL; + skb_mark_not_on_list(segs); err = ip_fragment(net, sk, segs, mtu, ip_finish_output2); if (err && ret == 0) @@ -684,7 +684,7 @@ int ip_do_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, skb = frag; frag = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); } if (err == 0) { diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index d9504adc47b3..184bf2e0a1ed 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -106,6 +106,10 @@ config NF_NAT_IPV4 if NF_NAT_IPV4 +config NF_NAT_MASQUERADE_IPV4 + bool + +if NF_TABLES config NFT_CHAIN_NAT_IPV4 depends on NF_TABLES_IPV4 tristate "IPv4 nf_tables nat chain support" @@ -115,9 +119,6 @@ config NFT_CHAIN_NAT_IPV4 packet transformations such as the source, destination address and source and destination ports. -config NF_NAT_MASQUERADE_IPV4 - bool - config NFT_MASQ_IPV4 tristate "IPv4 masquerading support for nf_tables" depends on NF_TABLES_IPV4 @@ -135,6 +136,7 @@ config NFT_REDIR_IPV4 help This is the expression that provides IPv4 redirect support for nf_tables. +endif # NF_TABLES config NF_NAT_SNMP_BASIC tristate "Basic SNMP-ALG support" diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b8af2fec5ad5..67670fac7c8d 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1185,7 +1185,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) flags = msg->msg_flags; - if (flags & MSG_ZEROCOPY && size) { + if (flags & MSG_ZEROCOPY && size && sock_flag(sk, SOCK_ZEROCOPY)) { if (sk->sk_state != TCP_ESTABLISHED) { err = -EINVAL; goto out_err; @@ -2595,6 +2595,8 @@ int tcp_disconnect(struct sock *sk, int flags) tp->compressed_ack = 0; tp->bytes_sent = 0; tp->bytes_retrans = 0; + tp->duplicate_sack[0].start_seq = 0; + tp->duplicate_sack[0].end_seq = 0; tp->dsack_dups = 0; tp->reord_seen = 0; diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 13d34427ca3d..02ff2dde9609 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -95,11 +95,10 @@ struct bbr { u32 mode:3, /* current bbr_mode in state machine */ prev_ca_state:3, /* CA state on previous ACK */ packet_conservation:1, /* use packet conservation? */ - restore_cwnd:1, /* decided to revert cwnd to old value */ round_start:1, /* start of packet-timed tx->ack round? */ idle_restart:1, /* restarting after idle? */ probe_rtt_round_done:1, /* a BBR_PROBE_RTT round at 4 pkts? */ - unused:12, + unused:13, lt_is_sampling:1, /* taking long-term ("LT") samples now? */ lt_rtt_cnt:7, /* round trips in long-term interval */ lt_use_bw:1; /* use lt_bw as our bw estimate? */ @@ -175,6 +174,8 @@ static const u32 bbr_lt_bw_diff = 4000 / 8; /* If we estimate we're policed, use lt_bw for this many round trips: */ static const u32 bbr_lt_bw_max_rtts = 48; +static void bbr_check_probe_rtt_done(struct sock *sk); + /* Do we estimate that STARTUP filled the pipe? */ static bool bbr_full_bw_reached(const struct sock *sk) { @@ -309,6 +310,8 @@ static void bbr_cwnd_event(struct sock *sk, enum tcp_ca_event event) */ if (bbr->mode == BBR_PROBE_BW) bbr_set_pacing_rate(sk, bbr_bw(sk), BBR_UNIT); + else if (bbr->mode == BBR_PROBE_RTT) + bbr_check_probe_rtt_done(sk); } } @@ -396,17 +399,11 @@ static bool bbr_set_cwnd_to_recover_or_restore( cwnd = tcp_packets_in_flight(tp) + acked; } else if (prev_state >= TCP_CA_Recovery && state < TCP_CA_Recovery) { /* Exiting loss recovery; restore cwnd saved before recovery. */ - bbr->restore_cwnd = 1; + cwnd = max(cwnd, bbr->prior_cwnd); bbr->packet_conservation = 0; } bbr->prev_ca_state = state; - if (bbr->restore_cwnd) { - /* Restore cwnd after exiting loss recovery or PROBE_RTT. */ - cwnd = max(cwnd, bbr->prior_cwnd); - bbr->restore_cwnd = 0; - } - if (bbr->packet_conservation) { *new_cwnd = max(cwnd, tcp_packets_in_flight(tp) + acked); return true; /* yes, using packet conservation */ @@ -423,10 +420,10 @@ static void bbr_set_cwnd(struct sock *sk, const struct rate_sample *rs, { struct tcp_sock *tp = tcp_sk(sk); struct bbr *bbr = inet_csk_ca(sk); - u32 cwnd = 0, target_cwnd = 0; + u32 cwnd = tp->snd_cwnd, target_cwnd = 0; if (!acked) - return; + goto done; /* no packet fully ACKed; just apply caps */ if (bbr_set_cwnd_to_recover_or_restore(sk, rs, acked, &cwnd)) goto done; @@ -748,6 +745,20 @@ static void bbr_check_drain(struct sock *sk, const struct rate_sample *rs) bbr_reset_probe_bw_mode(sk); /* we estimate queue is drained */ } +static void bbr_check_probe_rtt_done(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bbr *bbr = inet_csk_ca(sk); + + if (!(bbr->probe_rtt_done_stamp && + after(tcp_jiffies32, bbr->probe_rtt_done_stamp))) + return; + + bbr->min_rtt_stamp = tcp_jiffies32; /* wait a while until PROBE_RTT */ + tp->snd_cwnd = max(tp->snd_cwnd, bbr->prior_cwnd); + bbr_reset_mode(sk); +} + /* The goal of PROBE_RTT mode is to have BBR flows cooperatively and * periodically drain the bottleneck queue, to converge to measure the true * min_rtt (unloaded propagation delay). This allows the flows to keep queues @@ -806,12 +817,8 @@ static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs) } else if (bbr->probe_rtt_done_stamp) { if (bbr->round_start) bbr->probe_rtt_round_done = 1; - if (bbr->probe_rtt_round_done && - after(tcp_jiffies32, bbr->probe_rtt_done_stamp)) { - bbr->min_rtt_stamp = tcp_jiffies32; - bbr->restore_cwnd = 1; /* snap to prior_cwnd */ - bbr_reset_mode(sk); - } + if (bbr->probe_rtt_round_done) + bbr_check_probe_rtt_done(sk); } } /* Restart after idle ends only once we process a new S/ACK for data */ @@ -862,7 +869,6 @@ static void bbr_init(struct sock *sk) bbr->has_seen_rtt = 0; bbr_init_pacing_rate_from_rtt(sk); - bbr->restore_cwnd = 0; bbr->round_start = 0; bbr->idle_restart = 0; bbr->full_bw_reached = 0; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 4c2dd9f863f7..d9034073138c 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4199,6 +4199,17 @@ static void tcp_dsack_extend(struct sock *sk, u32 seq, u32 end_seq) tcp_sack_extend(tp->duplicate_sack, seq, end_seq); } +static void tcp_rcv_spurious_retrans(struct sock *sk, const struct sk_buff *skb) +{ + /* When the ACK path fails or drops most ACKs, the sender would + * timeout and spuriously retransmit the same segment repeatedly. + * The receiver remembers and reflects via DSACKs. Leverage the + * DSACK state and change the txhash to re-route speculatively. + */ + if (TCP_SKB_CB(skb)->seq == tcp_sk(sk)->duplicate_sack[0].start_seq) + sk_rethink_txhash(sk); +} + static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); @@ -4211,6 +4222,7 @@ static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb) if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) { u32 end_seq = TCP_SKB_CB(skb)->end_seq; + tcp_rcv_spurious_retrans(sk, skb); if (after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) end_seq = tp->rcv_nxt; tcp_dsack_set(sk, TCP_SKB_CB(skb)->seq, end_seq); @@ -4755,6 +4767,7 @@ queue_and_out: } if (!after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) { + tcp_rcv_spurious_retrans(sk, skb); /* A retransmit, 2nd most common case. Force an immediate ack. */ NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOST); tcp_dsack_set(sk, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq); @@ -6367,8 +6380,8 @@ static bool tcp_syn_flood_action(const struct sock *sk, if (!queue->synflood_warned && net->ipv4.sysctl_tcp_syncookies != 2 && xchg(&queue->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); + net_info_ratelimited("%s: Possible SYN flooding on port %d. %s. Check SNMP counters.\n", + proto, ntohs(tcp_hdr(skb)->dest), msg); return want_cookie; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 9e041fa5c545..09547ef9c4c6 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2517,6 +2517,12 @@ static int __net_init tcp_sk_init(struct net *net) if (res) goto fail; sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); + + /* Please enforce IP_DF and IPID==0 for RST and + * ACK sent in SYN-RECV and TIME-WAIT state. + */ + inet_sk(sk)->pmtudisc = IP_PMTUDISC_DO; + *per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk; } @@ -2543,7 +2549,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_tw_reuse = 2; cnt = tcp_hashinfo.ehash_mask + 1; - net->ipv4.tcp_death_row.sysctl_max_tw_buckets = (cnt + 1) / 2; + net->ipv4.tcp_death_row.sysctl_max_tw_buckets = cnt / 2; net->ipv4.tcp_death_row.hashinfo = &tcp_hashinfo; net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 256); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 75ef332a7caf..12affb7864d9 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -184,8 +184,9 @@ kill: inet_twsk_deschedule_put(tw); return TCP_TW_SUCCESS; } + } else { + inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN); } - inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN); if (tmp_opt.saw_tstamp) { tcptw->tw_ts_recent = tmp_opt.rcv_tsval; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index f4e35b2ff8b8..7d69dd6fa7e8 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2124,6 +2124,28 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh, inet_compute_pseudo); } +/* wrapper for udp_queue_rcv_skb tacking care of csum conversion and + * return code conversion for ip layer consumption + */ +static int udp_unicast_rcv_skb(struct sock *sk, struct sk_buff *skb, + struct udphdr *uh) +{ + int ret; + + if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk)) + skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check, + inet_compute_pseudo); + + ret = udp_queue_rcv_skb(sk, skb); + + /* a return value > 0 means to resubmit the input, but + * it wants the return to be -protocol, or 0 + */ + if (ret > 0) + return -ret; + return 0; +} + /* * All we need to do is get the socket, and then do a checksum. */ @@ -2170,14 +2192,9 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (unlikely(sk->sk_rx_dst != dst)) udp_sk_rx_dst_set(sk, dst); - ret = udp_queue_rcv_skb(sk, skb); + ret = udp_unicast_rcv_skb(sk, skb, uh); sock_put(sk); - /* a return value > 0 means to resubmit the input, but - * it wants the return to be -protocol, or 0 - */ - if (ret > 0) - return -ret; - return 0; + return ret; } if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST)) @@ -2185,22 +2202,8 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, saddr, daddr, udptable, proto); sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable); - if (sk) { - int ret; - - if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk)) - skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check, - inet_compute_pseudo); - - ret = udp_queue_rcv_skb(sk, skb); - - /* a return value > 0 means to resubmit the input, but - * it wants the return to be -protocol, or 0 - */ - if (ret > 0) - return -ret; - return 0; - } + if (sk) + return udp_unicast_rcv_skb(sk, skb, uh); if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 2fac4ad74867..d4733160e6b7 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2398,7 +2398,7 @@ static void addrconf_add_mroute(struct net_device *dev) ipv6_addr_set(&cfg.fc_dst, htonl(0xFF000000), 0, 0, 0); - ip6_route_add(&cfg, GFP_ATOMIC, NULL); + ip6_route_add(&cfg, GFP_KERNEL, NULL); } static struct inet6_dev *addrconf_add_dev(struct net_device *dev) @@ -3062,7 +3062,7 @@ static void sit_add_v4_addrs(struct inet6_dev *idev) if (addr.s6_addr32[3]) { add_addr(idev, &addr, plen, scope); addrconf_prefix_route(&addr, plen, 0, idev->dev, 0, pflags, - GFP_ATOMIC); + GFP_KERNEL); return; } @@ -3087,7 +3087,7 @@ static void sit_add_v4_addrs(struct inet6_dev *idev) add_addr(idev, &addr, plen, flag); addrconf_prefix_route(&addr, plen, 0, idev->dev, - 0, pflags, GFP_ATOMIC); + 0, pflags, GFP_KERNEL); } } } @@ -4491,6 +4491,7 @@ static const struct nla_policy ifa_ipv6_policy[IFA_MAX+1] = { [IFA_CACHEINFO] = { .len = sizeof(struct ifa_cacheinfo) }, [IFA_FLAGS] = { .len = sizeof(u32) }, [IFA_RT_PRIORITY] = { .len = sizeof(u32) }, + [IFA_TARGET_NETNSID] = { .type = NLA_S32 }, }; static int @@ -4793,19 +4794,32 @@ static inline int inet6_ifaddr_msgsize(void) + nla_total_size(4) /* IFA_RT_PRIORITY */; } +struct inet6_fill_args { + u32 portid; + u32 seq; + int event; + unsigned int flags; + int netnsid; +}; + static int inet6_fill_ifaddr(struct sk_buff *skb, struct inet6_ifaddr *ifa, - u32 portid, u32 seq, int event, unsigned int flags) + struct inet6_fill_args *args) { struct nlmsghdr *nlh; u32 preferred, valid; - nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct ifaddrmsg), flags); + nlh = nlmsg_put(skb, args->portid, args->seq, args->event, + sizeof(struct ifaddrmsg), args->flags); if (!nlh) return -EMSGSIZE; put_ifaddrmsg(nlh, ifa->prefix_len, ifa->flags, rt_scope(ifa->scope), ifa->idev->dev->ifindex); + if (args->netnsid >= 0 && + nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) + goto error; + if (!((ifa->flags&IFA_F_PERMANENT) && (ifa->prefered_lft == INFINITY_LIFE_TIME))) { preferred = ifa->prefered_lft; @@ -4855,7 +4869,7 @@ error: } static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, - u32 portid, u32 seq, int event, u16 flags) + struct inet6_fill_args *args) { struct nlmsghdr *nlh; u8 scope = RT_SCOPE_UNIVERSE; @@ -4864,10 +4878,15 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, if (ipv6_addr_scope(&ifmca->mca_addr) & IFA_SITE) scope = RT_SCOPE_SITE; - nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct ifaddrmsg), flags); + nlh = nlmsg_put(skb, args->portid, args->seq, args->event, + sizeof(struct ifaddrmsg), args->flags); if (!nlh) return -EMSGSIZE; + if (args->netnsid >= 0 && + nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) + return -EMSGSIZE; + put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex); if (nla_put_in6_addr(skb, IFA_MULTICAST, &ifmca->mca_addr) < 0 || put_cacheinfo(skb, ifmca->mca_cstamp, ifmca->mca_tstamp, @@ -4881,7 +4900,7 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, } static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, - u32 portid, u32 seq, int event, unsigned int flags) + struct inet6_fill_args *args) { struct net_device *dev = fib6_info_nh_dev(ifaca->aca_rt); int ifindex = dev ? dev->ifindex : 1; @@ -4891,10 +4910,15 @@ static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, if (ipv6_addr_scope(&ifaca->aca_addr) & IFA_SITE) scope = RT_SCOPE_SITE; - nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct ifaddrmsg), flags); + nlh = nlmsg_put(skb, args->portid, args->seq, args->event, + sizeof(struct ifaddrmsg), args->flags); if (!nlh) return -EMSGSIZE; + if (args->netnsid >= 0 && + nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) + return -EMSGSIZE; + put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex); if (nla_put_in6_addr(skb, IFA_ANYCAST, &ifaca->aca_addr) < 0 || put_cacheinfo(skb, ifaca->aca_cstamp, ifaca->aca_tstamp, @@ -4916,8 +4940,14 @@ enum addr_type_t { /* called with rcu_read_lock() */ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb, struct netlink_callback *cb, enum addr_type_t type, - int s_ip_idx, int *p_ip_idx) + int s_ip_idx, int *p_ip_idx, int netnsid) { + struct inet6_fill_args fillargs = { + .portid = NETLINK_CB(cb->skb).portid, + .seq = cb->nlh->nlmsg_seq, + .flags = NLM_F_MULTI, + .netnsid = netnsid, + }; struct ifmcaddr6 *ifmca; struct ifacaddr6 *ifaca; int err = 1; @@ -4927,16 +4957,13 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb, switch (type) { case UNICAST_ADDR: { struct inet6_ifaddr *ifa; + fillargs.event = RTM_NEWADDR; /* unicast address incl. temp addr */ list_for_each_entry(ifa, &idev->addr_list, if_list) { if (++ip_idx < s_ip_idx) continue; - err = inet6_fill_ifaddr(skb, ifa, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - RTM_NEWADDR, - NLM_F_MULTI); + err = inet6_fill_ifaddr(skb, ifa, &fillargs); if (err < 0) break; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); @@ -4944,31 +4971,26 @@ static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb, break; } case MULTICAST_ADDR: + fillargs.event = RTM_GETMULTICAST; + /* multicast address */ for (ifmca = idev->mc_list; ifmca; ifmca = ifmca->next, ip_idx++) { if (ip_idx < s_ip_idx) continue; - err = inet6_fill_ifmcaddr(skb, ifmca, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - RTM_GETMULTICAST, - NLM_F_MULTI); + err = inet6_fill_ifmcaddr(skb, ifmca, &fillargs); if (err < 0) break; } break; case ANYCAST_ADDR: + fillargs.event = RTM_GETANYCAST; /* anycast address */ for (ifaca = idev->ac_list; ifaca; ifaca = ifaca->aca_next, ip_idx++) { if (ip_idx < s_ip_idx) continue; - err = inet6_fill_ifacaddr(skb, ifaca, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - RTM_GETANYCAST, - NLM_F_MULTI); + err = inet6_fill_ifacaddr(skb, ifaca, &fillargs); if (err < 0) break; } @@ -4985,6 +5007,9 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, enum addr_type_t type) { struct net *net = sock_net(skb->sk); + struct nlattr *tb[IFA_MAX+1]; + struct net *tgt_net = net; + int netnsid = -1; int h, s_h; int idx, ip_idx; int s_idx, s_ip_idx; @@ -4996,11 +5021,22 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, s_idx = idx = cb->args[1]; s_ip_idx = ip_idx = cb->args[2]; + if (nlmsg_parse(cb->nlh, sizeof(struct ifaddrmsg), tb, IFA_MAX, + ifa_ipv6_policy, NULL) >= 0) { + if (tb[IFA_TARGET_NETNSID]) { + netnsid = nla_get_s32(tb[IFA_TARGET_NETNSID]); + + tgt_net = rtnl_get_net_ns_capable(skb->sk, netnsid); + if (IS_ERR(tgt_net)) + return PTR_ERR(tgt_net); + } + } + rcu_read_lock(); - cb->seq = atomic_read(&net->ipv6.dev_addr_genid) ^ net->dev_base_seq; + cb->seq = atomic_read(&tgt_net->ipv6.dev_addr_genid) ^ tgt_net->dev_base_seq; for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; - head = &net->dev_index_head[h]; + head = &tgt_net->dev_index_head[h]; hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; @@ -5012,7 +5048,7 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, goto cont; if (in6_dump_addrs(idev, skb, cb, type, - s_ip_idx, &ip_idx) < 0) + s_ip_idx, &ip_idx, netnsid) < 0) goto done; cont: idx++; @@ -5023,6 +5059,8 @@ done: cb->args[0] = h; cb->args[1] = idx; cb->args[2] = ip_idx; + if (netnsid >= 0) + put_net(tgt_net); return skb->len; } @@ -5053,6 +5091,14 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); + struct inet6_fill_args fillargs = { + .portid = NETLINK_CB(in_skb).portid, + .seq = nlh->nlmsg_seq, + .event = RTM_NEWADDR, + .flags = 0, + .netnsid = -1, + }; + struct net *tgt_net = net; struct ifaddrmsg *ifm; struct nlattr *tb[IFA_MAX+1]; struct in6_addr *addr = NULL, *peer; @@ -5066,15 +5112,24 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, if (err < 0) return err; + if (tb[IFA_TARGET_NETNSID]) { + fillargs.netnsid = nla_get_s32(tb[IFA_TARGET_NETNSID]); + + tgt_net = rtnl_get_net_ns_capable(NETLINK_CB(in_skb).sk, + fillargs.netnsid); + if (IS_ERR(tgt_net)) + return PTR_ERR(tgt_net); + } + addr = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer); if (!addr) return -EINVAL; ifm = nlmsg_data(nlh); if (ifm->ifa_index) - dev = dev_get_by_index(net, ifm->ifa_index); + dev = dev_get_by_index(tgt_net, ifm->ifa_index); - ifa = ipv6_get_ifaddr(net, addr, dev, 1); + ifa = ipv6_get_ifaddr(tgt_net, addr, dev, 1); if (!ifa) { err = -EADDRNOTAVAIL; goto errout; @@ -5086,20 +5141,22 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, goto errout_ifa; } - err = inet6_fill_ifaddr(skb, ifa, NETLINK_CB(in_skb).portid, - nlh->nlmsg_seq, RTM_NEWADDR, 0); + err = inet6_fill_ifaddr(skb, ifa, &fillargs); if (err < 0) { /* -EMSGSIZE implies BUG in inet6_ifaddr_msgsize() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout_ifa; } - err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); + err = rtnl_unicast(skb, tgt_net, NETLINK_CB(in_skb).portid); errout_ifa: in6_ifa_put(ifa); errout: if (dev) dev_put(dev); + if (fillargs.netnsid >= 0) + put_net(tgt_net); + return err; } @@ -5107,13 +5164,20 @@ static void inet6_ifa_notify(int event, struct inet6_ifaddr *ifa) { struct sk_buff *skb; struct net *net = dev_net(ifa->idev->dev); + struct inet6_fill_args fillargs = { + .portid = 0, + .seq = 0, + .event = event, + .flags = 0, + .netnsid = -1, + }; int err = -ENOBUFS; skb = nlmsg_new(inet6_ifaddr_msgsize(), GFP_ATOMIC); if (!skb) goto errout; - err = inet6_fill_ifaddr(skb, ifa, 0, 0, event, 0); + err = inet6_fill_ifaddr(skb, ifa, &fillargs); if (err < 0) { /* -EMSGSIZE implies BUG in inet6_ifaddr_msgsize() */ WARN_ON(err == -EMSGSIZE); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 673bba31eb18..77ef8478234f 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -209,6 +209,7 @@ lookup_protocol: np->hop_limit = -1; np->mcast_hops = IPV6_DEFAULT_MCASTHOPS; np->mc_loop = 1; + np->mc_all = 1; np->pmtudisc = IPV6_PMTUDISC_WANT; np->repflow = net->ipv6.sysctl.flowlabel_reflect; sk->sk_ipv6only = net->ipv6.sysctl.bindv6only; @@ -938,14 +939,14 @@ static int __init inet6_init(void) err = proto_register(&pingv6_prot, 1); if (err) - goto out_unregister_ping_proto; + goto out_unregister_raw_proto; /* We MUST register RAW sockets before we create the ICMP6, * IGMP6, or NDISC control sockets. */ err = rawv6_init(); if (err) - goto out_unregister_raw_proto; + goto out_unregister_ping_proto; /* Register the family here so that the init calls below will * be able to create sockets. (?? is this dangerous ??) @@ -1113,11 +1114,11 @@ netfilter_fail: igmp_fail: ndisc_cleanup(); ndisc_fail: - ip6_mr_cleanup(); + icmpv6_cleanup(); icmp_fail: - unregister_pernet_subsys(&inet6_net_ops); + ip6_mr_cleanup(); ipmr_fail: - icmpv6_cleanup(); + unregister_pernet_subsys(&inet6_net_ops); register_pernet_fail: sock_unregister(PF_INET6); rtnl_unregister_all(PF_INET6); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index d212738e9d10..5516f55e214b 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -198,6 +198,8 @@ void fib6_info_destroy_rcu(struct rcu_head *head) } } + lwtstate_put(f6i->fib6_nh.nh_lwtstate); + if (f6i->fib6_nh.nh_dev) dev_put(f6i->fib6_nh.nh_dev); @@ -987,7 +989,10 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, fib6_clean_expires(iter); else fib6_set_expires(iter, rt->expires); - fib6_metric_set(iter, RTAX_MTU, rt->fib6_pmtu); + + if (rt->fib6_pmtu) + fib6_metric_set(iter, RTAX_MTU, + rt->fib6_pmtu); return -EEXIST; } /* If we have the same destination and the same metric, diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 18a3794b0f52..515adbdba1d2 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -427,35 +427,17 @@ static void ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct net *net = dev_net(skb->dev); - const struct gre_base_hdr *greh; const struct ipv6hdr *ipv6h; - int grehlen = sizeof(*greh); + struct tnl_ptk_info tpi; struct ip6_tnl *t; - int key_off = 0; - __be16 flags; - __be32 key; - if (!pskb_may_pull(skb, offset + grehlen)) - return; - greh = (const struct gre_base_hdr *)(skb->data + offset); - flags = greh->flags; - if (flags & (GRE_VERSION | GRE_ROUTING)) + if (gre_parse_header(skb, &tpi, NULL, htons(ETH_P_IPV6), + offset) < 0) return; - if (flags & GRE_CSUM) - grehlen += 4; - if (flags & GRE_KEY) { - key_off = grehlen + offset; - grehlen += 4; - } - if (!pskb_may_pull(skb, offset + grehlen)) - return; ipv6h = (const struct ipv6hdr *)skb->data; - greh = (const struct gre_base_hdr *)(skb->data + offset); - key = key_off ? *(__be32 *)(skb->data + key_off) : 0; - t = ip6gre_tunnel_lookup(skb->dev, &ipv6h->daddr, &ipv6h->saddr, - key, greh->protocol); + tpi.key, tpi.proto); if (!t) return; @@ -1778,6 +1760,7 @@ static void ip6gre_netlink_parms(struct nlattr *data[], if (data[IFLA_GRE_COLLECT_METADATA]) parms->collect_md = true; + parms->erspan_ver = 1; if (data[IFLA_GRE_ERSPAN_VER]) parms->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]); diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 37ff4805b20c..c7e495f12011 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -115,6 +115,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, payload_len = skb->len - nhoff - sizeof(*ipv6h); ipv6h->payload_len = htons(payload_len); skb->network_header = (u8 *)ipv6h - skb->head; + skb_reset_mac_len(skb); if (udpfrag) { int err = ip6_find_1stfragopt(skb, &prevhdr); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 16f200f06500..89e0d5118afe 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -219,12 +219,10 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, kfree_skb(skb); return -ENOBUFS; } + if (skb->sk) + skb_set_owner_w(skb2, skb->sk); consume_skb(skb); skb = skb2; - /* 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); @@ -727,7 +725,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, skb = frag; frag = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); } kfree(tmp_hdr); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 5df2a58d945c..419960b0ba16 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1188,7 +1188,15 @@ route_lookup: init_tel_txopt(&opt, encap_limit); ipv6_push_frag_opts(skb, &opt.ops, &proto); } - hop_limit = hop_limit ? : ip6_dst_hoplimit(dst); + + if (hop_limit == 0) { + if (skb->protocol == htons(ETH_P_IP)) + hop_limit = ip_hdr(skb)->ttl; + else if (skb->protocol == htons(ETH_P_IPV6)) + hop_limit = ipv6_hdr(skb)->hop_limit; + else + hop_limit = ip6_dst_hoplimit(dst); + } /* Calculate max headroom for all the headers and adjust * needed_headroom if necessary. diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 38dec9da90d3..eeaf7455d51e 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -481,7 +481,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) } mtu = dst_mtu(dst); - if (!skb->ignore_df && skb->len > mtu) { + if (skb->len > mtu) { skb_dst_update_pmtu(skb, mtu); if (skb->protocol == htons(ETH_P_IPV6)) { @@ -1094,7 +1094,8 @@ static void __net_exit vti6_destroy_tunnels(struct vti6_net *ip6n, } t = rtnl_dereference(ip6n->tnls_wc[0]); - unregister_netdevice_queue(t->dev, list); + if (t) + unregister_netdevice_queue(t->dev, list); } static int __net_init vti6_init_net(struct net *net) diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index c0cac9cc3a28..381ce38940ae 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -674,6 +674,13 @@ done: retv = ipv6_sock_ac_drop(sk, mreq.ipv6mr_ifindex, &mreq.ipv6mr_acaddr); break; } + case IPV6_MULTICAST_ALL: + if (optlen < sizeof(int)) + goto e_inval; + np->mc_all = valbool; + retv = 0; + break; + case MCAST_JOIN_GROUP: case MCAST_LEAVE_GROUP: { @@ -1266,6 +1273,10 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, val = np->mcast_oif; break; + case IPV6_MULTICAST_ALL: + val = np->mc_all; + break; + case IPV6_UNICAST_IF: val = (__force int)htonl((__u32) np->ucast_oif); break; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 4ae54aaca373..6895e1dc0b03 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -636,7 +636,7 @@ bool inet6_mc_check(struct sock *sk, const struct in6_addr *mc_addr, } if (!mc) { rcu_read_unlock(); - return true; + return np->mc_all; } read_lock(&mc->sflock); psl = mc->sflist; diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 2a14d8b65924..b8ac369f98ad 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -445,11 +445,12 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_devic else if (head->ip_summed == CHECKSUM_COMPLETE) head->csum = csum_add(head->csum, fp->csum); head->truesize += fp->truesize; + fp->sk = NULL; } sub_frag_mem_limit(fq->q.net, head->truesize); head->ignore_df = 1; - head->next = NULL; + skb_mark_not_on_list(head); head->dev = dev; head->tstamp = fq->q.stamp; ipv6_hdr(head)->payload_len = htons(payload_len); diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 5c5b4f79296e..f1b1ff30fe5b 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -388,7 +388,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, } sub_frag_mem_limit(fq->q.net, sum_truesize); - head->next = NULL; + skb_mark_not_on_list(head); head->dev = dev; head->tstamp = fq->q.stamp; ipv6_hdr(head)->payload_len = htons(payload_len); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 7208c16302f6..21a919e74fbf 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -946,8 +946,6 @@ static void ip6_rt_init_dst_reject(struct rt6_info *rt, struct fib6_info *ort) static void ip6_rt_init_dst(struct rt6_info *rt, struct fib6_info *ort) { - rt->dst.flags |= fib6_info_dst_flags(ort); - if (ort->fib6_flags & RTF_REJECT) { ip6_rt_init_dst_reject(rt, ort); return; @@ -956,7 +954,7 @@ static void ip6_rt_init_dst(struct rt6_info *rt, struct fib6_info *ort) rt->dst.error = 0; rt->dst.output = ip6_output; - if (ort->fib6_type == RTN_LOCAL) { + if (ort->fib6_type == RTN_LOCAL || ort->fib6_type == RTN_ANYCAST) { rt->dst.input = ip6_input; } else if (ipv6_addr_type(&ort->fib6_dst.addr) & IPV6_ADDR_MULTICAST) { rt->dst.input = ip6_mc_input; @@ -995,8 +993,6 @@ static void ip6_rt_copy_init(struct rt6_info *rt, struct fib6_info *ort) #ifdef CONFIG_IPV6_SUBTREES rt->rt6i_src = ort->fib6_src; #endif - rt->rt6i_prefsrc = ort->fib6_prefsrc; - rt->dst.lwtstate = lwtstate_get(ort->fib6_nh.nh_lwtstate); } static struct fib6_node* fib6_backtrack(struct fib6_node *fn, @@ -1450,11 +1446,6 @@ static int rt6_insert_exception(struct rt6_info *nrt, if (ort->fib6_src.plen) src_key = &nrt->rt6i_src.addr; #endif - - /* Update rt6i_prefsrc as it could be changed - * in rt6_remove_prefsrc() - */ - nrt->rt6i_prefsrc = ort->fib6_prefsrc; /* rt6_mtu_change() might lower mtu on ort. * Only insert this exception route if its mtu * is less than ort's mtu value. @@ -1636,25 +1627,6 @@ static void rt6_update_exception_stamp_rt(struct rt6_info *rt) rcu_read_unlock(); } -static void rt6_exceptions_remove_prefsrc(struct fib6_info *rt) -{ - struct rt6_exception_bucket *bucket; - struct rt6_exception *rt6_ex; - int i; - - bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, - lockdep_is_held(&rt6_exception_lock)); - - if (bucket) { - for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) { - hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) { - rt6_ex->rt6i->rt6i_prefsrc.plen = 0; - } - bucket++; - } - } -} - static bool rt6_mtu_change_route_allowed(struct inet6_dev *idev, struct rt6_info *rt, int mtu) { @@ -3138,8 +3110,6 @@ install_route: rt->fib6_nh.nh_dev = dev; rt->fib6_table = table; - cfg->fc_nlinfo.nl_net = dev_net(dev); - if (idev) in6_dev_put(idev); @@ -3796,8 +3766,6 @@ static int fib6_remove_prefsrc(struct fib6_info *rt, void *arg) spin_lock_bh(&rt6_exception_lock); /* remove prefsrc entry */ rt->fib6_prefsrc.plen = 0; - /* need to update cache as well */ - rt6_exceptions_remove_prefsrc(rt); spin_unlock_bh(&rt6_exception_lock); } return 0; @@ -4671,20 +4639,31 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, int iif, int type, u32 portid, u32 seq, unsigned int flags) { - struct rtmsg *rtm; + struct rt6_info *rt6 = (struct rt6_info *)dst; + struct rt6key *rt6_dst, *rt6_src; + u32 *pmetrics, table, rt6_flags; struct nlmsghdr *nlh; + struct rtmsg *rtm; long expires = 0; - u32 *pmetrics; - u32 table; nlh = nlmsg_put(skb, portid, seq, type, sizeof(*rtm), flags); if (!nlh) return -EMSGSIZE; + if (rt6) { + rt6_dst = &rt6->rt6i_dst; + rt6_src = &rt6->rt6i_src; + rt6_flags = rt6->rt6i_flags; + } else { + rt6_dst = &rt->fib6_dst; + rt6_src = &rt->fib6_src; + rt6_flags = rt->fib6_flags; + } + rtm = nlmsg_data(nlh); rtm->rtm_family = AF_INET6; - rtm->rtm_dst_len = rt->fib6_dst.plen; - rtm->rtm_src_len = rt->fib6_src.plen; + rtm->rtm_dst_len = rt6_dst->plen; + rtm->rtm_src_len = rt6_src->plen; rtm->rtm_tos = 0; if (rt->fib6_table) table = rt->fib6_table->tb6_id; @@ -4699,7 +4678,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, rtm->rtm_scope = RT_SCOPE_UNIVERSE; rtm->rtm_protocol = rt->fib6_protocol; - if (rt->fib6_flags & RTF_CACHE) + if (rt6_flags & RTF_CACHE) rtm->rtm_flags |= RTM_F_CLONED; if (dest) { @@ -4707,7 +4686,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, goto nla_put_failure; rtm->rtm_dst_len = 128; } else if (rtm->rtm_dst_len) - if (nla_put_in6_addr(skb, RTA_DST, &rt->fib6_dst.addr)) + if (nla_put_in6_addr(skb, RTA_DST, &rt6_dst->addr)) goto nla_put_failure; #ifdef CONFIG_IPV6_SUBTREES if (src) { @@ -4715,12 +4694,12 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, goto nla_put_failure; rtm->rtm_src_len = 128; } else if (rtm->rtm_src_len && - nla_put_in6_addr(skb, RTA_SRC, &rt->fib6_src.addr)) + nla_put_in6_addr(skb, RTA_SRC, &rt6_src->addr)) goto nla_put_failure; #endif if (iif) { #ifdef CONFIG_IPV6_MROUTE - if (ipv6_addr_is_multicast(&rt->fib6_dst.addr)) { + if (ipv6_addr_is_multicast(&rt6_dst->addr)) { int err = ip6mr_get_route(net, skb, rtm, portid); if (err == 0) @@ -4755,7 +4734,14 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, /* For multipath routes, walk the siblings list and add * each as a nexthop within RTA_MULTIPATH. */ - if (rt->fib6_nsiblings) { + if (rt6) { + if (rt6_flags & RTF_GATEWAY && + nla_put_in6_addr(skb, RTA_GATEWAY, &rt6->rt6i_gateway)) + goto nla_put_failure; + + if (dst->dev && nla_put_u32(skb, RTA_OIF, dst->dev->ifindex)) + goto nla_put_failure; + } else if (rt->fib6_nsiblings) { struct fib6_info *sibling, *next_sibling; struct nlattr *mp; @@ -4778,7 +4764,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, goto nla_put_failure; } - if (rt->fib6_flags & RTF_EXPIRES) { + if (rt6_flags & RTF_EXPIRES) { expires = dst ? dst->expires : rt->expires; expires -= jiffies; } @@ -4786,7 +4772,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, if (rtnl_put_cacheinfo(skb, dst, 0, expires, dst ? dst->error : 0) < 0) goto nla_put_failure; - if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt->fib6_flags))) + if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt6_flags))) goto nla_put_failure; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 83f4c77c79d8..28c4aa5078fc 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -752,6 +752,28 @@ static void udp6_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) } } +/* wrapper for udp_queue_rcv_skb tacking care of csum conversion and + * return code conversion for ip layer consumption + */ +static int udp6_unicast_rcv_skb(struct sock *sk, struct sk_buff *skb, + struct udphdr *uh) +{ + int ret; + + if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk)) + skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check, + ip6_compute_pseudo); + + ret = udpv6_queue_rcv_skb(sk, skb); + + /* a return value > 0 means to resubmit the input, but + * it wants the return to be -protocol, or 0 + */ + if (ret > 0) + return -ret; + return 0; +} + int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, int proto) { @@ -803,13 +825,14 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (unlikely(sk->sk_rx_dst != dst)) udp6_sk_rx_dst_set(sk, dst); - ret = udpv6_queue_rcv_skb(sk, skb); - sock_put(sk); + if (!uh->check && !udp_sk(sk)->no_check6_rx) { + sock_put(sk); + goto report_csum_error; + } - /* a return value > 0 means to resubmit the input */ - if (ret > 0) - return ret; - return 0; + ret = udp6_unicast_rcv_skb(sk, skb, uh); + sock_put(sk); + return ret; } /* @@ -822,30 +845,13 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, /* Unicast */ sk = __udp6_lib_lookup_skb(skb, uh->source, uh->dest, udptable); if (sk) { - int ret; - - if (!uh->check && !udp_sk(sk)->no_check6_rx) { - udp6_csum_zero_error(skb); - goto csum_error; - } - - if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk)) - skb_checksum_try_convert(skb, IPPROTO_UDP, uh->check, - ip6_compute_pseudo); - - ret = udpv6_queue_rcv_skb(sk, skb); - - /* a return value > 0 means to resubmit the input */ - if (ret > 0) - return ret; - - return 0; + if (!uh->check && !udp_sk(sk)->no_check6_rx) + goto report_csum_error; + return udp6_unicast_rcv_skb(sk, skb, uh); } - if (!uh->check) { - udp6_csum_zero_error(skb); - goto csum_error; - } + if (!uh->check) + goto report_csum_error; if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard; @@ -866,6 +872,9 @@ short_packet: ulen, skb->len, daddr, ntohs(uh->dest)); goto discard; + +report_csum_error: + udp6_csum_zero_error(skb); csum_error: __UDP6_INC_STATS(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE); discard: diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index a21d8ed0a325..e2f16a0173a9 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -351,20 +351,28 @@ static int afiucv_hs_send(struct iucv_message *imsg, struct sock *sock, memcpy(&phs_hdr->iucv_hdr, imsg, sizeof(struct iucv_message)); skb->dev = iucv->hs_dev; - if (!skb->dev) - return -ENODEV; - if (!(skb->dev->flags & IFF_UP) || !netif_carrier_ok(skb->dev)) - return -ENETDOWN; + if (!skb->dev) { + err = -ENODEV; + goto err_free; + } + if (!(skb->dev->flags & IFF_UP) || !netif_carrier_ok(skb->dev)) { + err = -ENETDOWN; + goto err_free; + } if (skb->len > skb->dev->mtu) { - if (sock->sk_type == SOCK_SEQPACKET) - return -EMSGSIZE; - else - skb_trim(skb, skb->dev->mtu); + if (sock->sk_type == SOCK_SEQPACKET) { + err = -EMSGSIZE; + goto err_free; + } + skb_trim(skb, skb->dev->mtu); } skb->protocol = cpu_to_be16(ETH_P_AF_IUCV); nskb = skb_clone(skb, GFP_ATOMIC); - if (!nskb) - return -ENOMEM; + if (!nskb) { + err = -ENOMEM; + goto err_free; + } + skb_queue_tail(&iucv->send_skb_q, nskb); err = dev_queue_xmit(skb); if (net_xmit_eval(err)) { @@ -375,6 +383,10 @@ static int afiucv_hs_send(struct iucv_message *imsg, struct sock *sock, WARN_ON(atomic_read(&iucv->msg_recv) < 0); } return net_xmit_eval(err); + +err_free: + kfree_skb(skb); + return err; } static struct sock *__iucv_get_sock_by_name(char *nm) @@ -1167,7 +1179,7 @@ static int iucv_sock_sendmsg(struct socket *sock, struct msghdr *msg, err = afiucv_hs_send(&txmsg, sk, skb, 0); if (err) { atomic_dec(&iucv->msg_sent); - goto fail; + goto out; } } else { /* Classic VM IUCV transport */ skb_queue_tail(&iucv->send_skb_q, skb); @@ -2155,8 +2167,8 @@ static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev, struct sock *sk; struct iucv_sock *iucv; struct af_iucv_trans_hdr *trans_hdr; + int err = NET_RX_SUCCESS; char nullstring[8]; - int err = 0; if (skb->len < (ETH_HLEN + sizeof(struct af_iucv_trans_hdr))) { WARN_ONCE(1, "AF_IUCV too short skb, len=%d, min=%d", @@ -2254,7 +2266,7 @@ static int afiucv_hs_rcv(struct sk_buff *skb, struct net_device *dev, err = afiucv_hs_callback_rx(sk, skb); break; default: - ; + kfree_skb(skb); } return err; diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index 8f7ef167c45a..eb502c6290c2 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -1874,7 +1874,7 @@ static void iucv_pm_complete(struct device *dev) * Returns 0 if there are still iucv pathes defined * 1 if there are no iucv pathes defined */ -int iucv_path_table_empty(void) +static int iucv_path_table_empty(void) { int i; diff --git a/net/llc/llc_core.c b/net/llc/llc_core.c index 260b3dc1b4a2..64d4bef04e73 100644 --- a/net/llc/llc_core.c +++ b/net/llc/llc_core.c @@ -127,9 +127,7 @@ void llc_sap_close(struct llc_sap *sap) list_del_rcu(&sap->node); spin_unlock_bh(&llc_sap_list_lock); - synchronize_rcu(); - - kfree(sap); + kfree_rcu(sap, rcu); } static struct packet_type llc_packet_type __read_mostly = { diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index d25da0e66da1..504627e2117f 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -158,12 +158,10 @@ static int ieee80211_change_iface(struct wiphy *wiphy, if (ret) return ret; - if (type == NL80211_IFTYPE_AP_VLAN && - params && params->use_4addr == 0) { + if (type == NL80211_IFTYPE_AP_VLAN && params->use_4addr == 0) { RCU_INIT_POINTER(sdata->u.vlan.sta, NULL); ieee80211_check_fast_rx_iface(sdata); - } else if (type == NL80211_IFTYPE_STATION && - params && params->use_4addr >= 0) { + } else if (type == NL80211_IFTYPE_STATION && params->use_4addr >= 0) { sdata->u.mgd.use_4addr = params->use_4addr; } @@ -911,6 +909,9 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, sdata->vif.bss_conf.beacon_int = params->beacon_interval; + if (params->he_cap) + sdata->vif.bss_conf.he_support = true; + mutex_lock(&local->mtx); err = ieee80211_vif_use_channel(sdata, ¶ms->chandef, IEEE80211_CHANCTX_SHARED); @@ -1092,50 +1093,6 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev) return 0; } -/* Layer 2 Update frame (802.2 Type 1 LLC XID Update response) */ -struct iapp_layer2_update { - u8 da[ETH_ALEN]; /* broadcast */ - u8 sa[ETH_ALEN]; /* STA addr */ - __be16 len; /* 6 */ - u8 dsap; /* 0 */ - u8 ssap; /* 0 */ - u8 control; - u8 xid_info[3]; -} __packed; - -static void ieee80211_send_layer2_update(struct sta_info *sta) -{ - struct iapp_layer2_update *msg; - struct sk_buff *skb; - - /* Send Level 2 Update Frame to update forwarding tables in layer 2 - * bridge devices */ - - skb = dev_alloc_skb(sizeof(*msg)); - if (!skb) - return; - msg = skb_put(skb, sizeof(*msg)); - - /* 802.2 Type 1 Logical Link Control (LLC) Exchange Identifier (XID) - * Update response frame; IEEE Std 802.2-1998, 5.4.1.2.1 */ - - eth_broadcast_addr(msg->da); - memcpy(msg->sa, sta->sta.addr, ETH_ALEN); - msg->len = htons(6); - msg->dsap = 0; - msg->ssap = 0x01; /* NULL LSAP, CR Bit: Response */ - msg->control = 0xaf; /* XID response lsb.1111F101. - * F=0 (no poll command; unsolicited frame) */ - msg->xid_info[0] = 0x81; /* XID format identifier */ - msg->xid_info[1] = 1; /* LLC types/classes: Type 1 LLC */ - msg->xid_info[2] = 0; /* XID sender's receive window size (RW) */ - - skb->dev = sta->sdata->dev; - skb->protocol = eth_type_trans(skb, sta->sdata->dev); - memset(skb->cb, 0, sizeof(skb->cb)); - netif_rx_ni(skb); -} - static int sta_apply_auth_flags(struct ieee80211_local *local, struct sta_info *sta, u32 mask, u32 set) @@ -1499,7 +1456,7 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev, } if (layer2_update) - ieee80211_send_layer2_update(sta); + cfg80211_send_layer2_update(sta->sdata->dev, sta->sta.addr); rcu_read_unlock(); @@ -1601,7 +1558,7 @@ static int ieee80211_change_station(struct wiphy *wiphy, if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) ieee80211_vif_inc_num_mcast(sta->sdata); - ieee80211_send_layer2_update(sta); + cfg80211_send_layer2_update(sta->sdata->dev, sta->sta.addr); } err = sta_apply_parameters(local, sta, params); diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index b5adf3625d16..3fe541e358f3 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -3,6 +3,7 @@ * * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH + * Copyright (C) 2018 Intel Corporation * * GPLv2 * @@ -214,6 +215,9 @@ static const char *hw_flag_names[] = { FLAG(SUPPORTS_TDLS_BUFFER_STA), FLAG(DEAUTH_NEED_MGD_TX_PREP), FLAG(DOESNT_SUPPORT_QOS_NDP), + FLAG(BUFF_MMPDU_TXQ), + FLAG(SUPPORTS_VHT_EXT_NSS_BW), + FLAG(STA_MMPDU_TXQ), #undef FLAG }; diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index 4105081dc1df..af5185a836e5 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -4,6 +4,7 @@ * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright(c) 2016 Intel Deutschland GmbH + * Copyright (C) 2018 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -140,7 +141,7 @@ static ssize_t sta_aqm_read(struct file *file, char __user *userbuf, { struct sta_info *sta = file->private_data; struct ieee80211_local *local = sta->local; - size_t bufsz = AQM_TXQ_ENTRY_LEN*(IEEE80211_NUM_TIDS+1); + size_t bufsz = AQM_TXQ_ENTRY_LEN * (IEEE80211_NUM_TIDS + 2); char *buf = kzalloc(bufsz, GFP_KERNEL), *p = buf; struct txq_info *txqi; ssize_t rv; @@ -162,7 +163,9 @@ static ssize_t sta_aqm_read(struct file *file, char __user *userbuf, bufsz+buf-p, "tid ac backlog-bytes backlog-packets new-flows drops marks overlimit collisions tx-bytes tx-packets flags\n"); - for (i = 0; i < IEEE80211_NUM_TIDS; i++) { + for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) { + if (!sta->sta.txq[i]) + continue; txqi = to_txq_info(sta->sta.txq[i]); p += scnprintf(p, bufsz+buf-p, "%d %d %u %u %u %u %u %u %u %u %u 0x%lx(%s%s%s)\n", @@ -487,12 +490,368 @@ static ssize_t sta_vht_capa_read(struct file *file, char __user *userbuf, p += scnprintf(p, sizeof(buf)+buf-p, "MCS TX highest: %d Mbps\n", le16_to_cpu(vhtc->vht_mcs.tx_highest)); +#undef PFLAG } return simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); } STA_OPS(vht_capa); +static ssize_t sta_he_capa_read(struct file *file, char __user *userbuf, + size_t count, loff_t *ppos) +{ + char *buf, *p; + size_t buf_sz = PAGE_SIZE; + struct sta_info *sta = file->private_data; + struct ieee80211_sta_he_cap *hec = &sta->sta.he_cap; + struct ieee80211_he_mcs_nss_supp *nss = &hec->he_mcs_nss_supp; + u8 ppe_size; + u8 *cap; + int i; + ssize_t ret; + + buf = kmalloc(buf_sz, GFP_KERNEL); + if (!buf) + return -ENOMEM; + p = buf; + + p += scnprintf(p, buf_sz + buf - p, "HE %ssupported\n", + hec->has_he ? "" : "not "); + if (!hec->has_he) + goto out; + + cap = hec->he_cap_elem.mac_cap_info; + p += scnprintf(p, buf_sz + buf - p, + "MAC-CAP: %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x\n", + cap[0], cap[1], cap[2], cap[3], cap[4], cap[5]); + +#define PRINT(fmt, ...) \ + p += scnprintf(p, buf_sz + buf - p, "\t\t" fmt "\n", \ + ##__VA_ARGS__) + +#define PFLAG(t, n, a, b) \ + do { \ + if (cap[n] & IEEE80211_HE_##t##_CAP##n##_##a) \ + PRINT("%s", b); \ + } while (0) + +#define PFLAG_RANGE(t, i, n, s, m, off, fmt) \ + do { \ + u8 msk = IEEE80211_HE_##t##_CAP##i##_##n##_MASK; \ + u8 idx = ((cap[i] & msk) >> (ffs(msk) - 1)) + off; \ + PRINT(fmt, (s << idx) + (m * idx)); \ + } while (0) + +#define PFLAG_RANGE_DEFAULT(t, i, n, s, m, off, fmt, a, b) \ + do { \ + if (cap[i] == IEEE80211_HE_##t ##_CAP##i##_##n##_##a) { \ + PRINT("%s", b); \ + break; \ + } \ + PFLAG_RANGE(t, i, n, s, m, off, fmt); \ + } while (0) + + PFLAG(MAC, 0, HTC_HE, "HTC-HE"); + PFLAG(MAC, 0, TWT_REQ, "TWT-REQ"); + PFLAG(MAC, 0, TWT_RES, "TWT-RES"); + PFLAG_RANGE_DEFAULT(MAC, 0, DYNAMIC_FRAG, 0, 1, 0, + "DYNAMIC-FRAG-LEVEL-%d", NOT_SUPP, "NOT-SUPP"); + PFLAG_RANGE_DEFAULT(MAC, 0, MAX_NUM_FRAG_MSDU, 1, 0, 0, + "MAX-NUM-FRAG-MSDU-%d", UNLIMITED, "UNLIMITED"); + + PFLAG_RANGE_DEFAULT(MAC, 1, MIN_FRAG_SIZE, 128, 0, -1, + "MIN-FRAG-SIZE-%d", UNLIMITED, "UNLIMITED"); + PFLAG_RANGE_DEFAULT(MAC, 1, TF_MAC_PAD_DUR, 0, 8, 0, + "TF-MAC-PAD-DUR-%dUS", MASK, "UNKNOWN"); + PFLAG_RANGE(MAC, 1, MULTI_TID_AGG_RX_QOS, 0, 1, 1, + "MULTI-TID-AGG-RX-QOS-%d"); + + if (cap[0] & IEEE80211_HE_MAC_CAP0_HTC_HE) { + switch (((cap[2] << 1) | (cap[1] >> 7)) & 0x3) { + case 0: + PRINT("LINK-ADAPTATION-NO-FEEDBACK"); + break; + case 1: + PRINT("LINK-ADAPTATION-RESERVED"); + break; + case 2: + PRINT("LINK-ADAPTATION-UNSOLICITED-FEEDBACK"); + break; + case 3: + PRINT("LINK-ADAPTATION-BOTH"); + break; + } + } + + PFLAG(MAC, 2, ALL_ACK, "ALL-ACK"); + PFLAG(MAC, 2, TRS, "TRS"); + PFLAG(MAC, 2, BSR, "BSR"); + PFLAG(MAC, 2, BCAST_TWT, "BCAST-TWT"); + PFLAG(MAC, 2, 32BIT_BA_BITMAP, "32BIT-BA-BITMAP"); + PFLAG(MAC, 2, MU_CASCADING, "MU-CASCADING"); + PFLAG(MAC, 2, ACK_EN, "ACK-EN"); + + PFLAG(MAC, 3, OMI_CONTROL, "OMI-CONTROL"); + PFLAG(MAC, 3, OFDMA_RA, "OFDMA-RA"); + + switch (cap[3] & IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_MASK) { + case IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_USE_VHT: + PRINT("MAX-AMPDU-LEN-EXP-USE-VHT"); + break; + case IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_VHT_1: + PRINT("MAX-AMPDU-LEN-EXP-VHT-1"); + break; + case IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_VHT_2: + PRINT("MAX-AMPDU-LEN-EXP-VHT-2"); + break; + case IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_RESERVED: + PRINT("MAX-AMPDU-LEN-EXP-RESERVED"); + break; + } + + PFLAG(MAC, 3, AMSDU_FRAG, "AMSDU-FRAG"); + PFLAG(MAC, 3, FLEX_TWT_SCHED, "FLEX-TWT-SCHED"); + PFLAG(MAC, 3, RX_CTRL_FRAME_TO_MULTIBSS, "RX-CTRL-FRAME-TO-MULTIBSS"); + + PFLAG(MAC, 4, BSRP_BQRP_A_MPDU_AGG, "BSRP-BQRP-A-MPDU-AGG"); + PFLAG(MAC, 4, QTP, "QTP"); + PFLAG(MAC, 4, BQR, "BQR"); + PFLAG(MAC, 4, SRP_RESP, "SRP-RESP"); + PFLAG(MAC, 4, NDP_FB_REP, "NDP-FB-REP"); + PFLAG(MAC, 4, OPS, "OPS"); + PFLAG(MAC, 4, AMDSU_IN_AMPDU, "AMSDU-IN-AMPDU"); + + PRINT("MULTI-TID-AGG-TX-QOS-%d", ((cap[5] << 1) | (cap[4] >> 7)) & 0x7); + + PFLAG(MAC, 5, SUBCHAN_SELECVITE_TRANSMISSION, + "SUBCHAN-SELECVITE-TRANSMISSION"); + PFLAG(MAC, 5, UL_2x996_TONE_RU, "UL-2x996-TONE-RU"); + PFLAG(MAC, 5, OM_CTRL_UL_MU_DATA_DIS_RX, "OM-CTRL-UL-MU-DATA-DIS-RX"); + + cap = hec->he_cap_elem.phy_cap_info; + p += scnprintf(p, buf_sz + buf - p, + "PHY CAP: %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x %#.2x\n", + cap[0], cap[1], cap[2], cap[3], cap[4], cap[5], cap[6], + cap[7], cap[8], cap[9], cap[10]); + + PFLAG(PHY, 0, CHANNEL_WIDTH_SET_40MHZ_IN_2G, + "CHANNEL-WIDTH-SET-40MHZ-IN-2G"); + PFLAG(PHY, 0, CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G, + "CHANNEL-WIDTH-SET-40MHZ-80MHZ-IN-5G"); + PFLAG(PHY, 0, CHANNEL_WIDTH_SET_160MHZ_IN_5G, + "CHANNEL-WIDTH-SET-160MHZ-IN-5G"); + PFLAG(PHY, 0, CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G, + "CHANNEL-WIDTH-SET-80PLUS80-MHZ-IN-5G"); + PFLAG(PHY, 0, CHANNEL_WIDTH_SET_RU_MAPPING_IN_2G, + "CHANNEL-WIDTH-SET-RU-MAPPING-IN-2G"); + PFLAG(PHY, 0, CHANNEL_WIDTH_SET_RU_MAPPING_IN_5G, + "CHANNEL-WIDTH-SET-RU-MAPPING-IN-5G"); + + switch (cap[1] & IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK) { + case IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_80MHZ_ONLY_SECOND_20MHZ: + PRINT("PREAMBLE-PUNC-RX-80MHZ-ONLY-SECOND-20MHZ"); + break; + case IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_80MHZ_ONLY_SECOND_40MHZ: + PRINT("PREAMBLE-PUNC-RX-80MHZ-ONLY-SECOND-40MHZ"); + break; + case IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_160MHZ_ONLY_SECOND_20MHZ: + PRINT("PREAMBLE-PUNC-RX-160MHZ-ONLY-SECOND-20MHZ"); + break; + case IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_160MHZ_ONLY_SECOND_40MHZ: + PRINT("PREAMBLE-PUNC-RX-160MHZ-ONLY-SECOND-40MHZ"); + break; + } + + PFLAG(PHY, 1, DEVICE_CLASS_A, + "IEEE80211-HE-PHY-CAP1-DEVICE-CLASS-A"); + PFLAG(PHY, 1, LDPC_CODING_IN_PAYLOAD, + "LDPC-CODING-IN-PAYLOAD"); + PFLAG(PHY, 1, HE_LTF_AND_GI_FOR_HE_PPDUS_0_8US, + "HY-CAP1-HE-LTF-AND-GI-FOR-HE-PPDUS-0-8US"); + PRINT("MIDAMBLE-RX-MAX-NSTS-%d", ((cap[2] << 1) | (cap[1] >> 7)) & 0x3); + + PFLAG(PHY, 2, NDP_4x_LTF_AND_3_2US, "NDP-4X-LTF-AND-3-2US"); + PFLAG(PHY, 2, STBC_TX_UNDER_80MHZ, "STBC-TX-UNDER-80MHZ"); + PFLAG(PHY, 2, STBC_RX_UNDER_80MHZ, "STBC-RX-UNDER-80MHZ"); + PFLAG(PHY, 2, DOPPLER_TX, "DOPPLER-TX"); + PFLAG(PHY, 2, DOPPLER_RX, "DOPPLER-RX"); + PFLAG(PHY, 2, UL_MU_FULL_MU_MIMO, "UL-MU-FULL-MU-MIMO"); + PFLAG(PHY, 2, UL_MU_PARTIAL_MU_MIMO, "UL-MU-PARTIAL-MU-MIMO"); + + switch (cap[3] & IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_MASK) { + case IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_NO_DCM: + PRINT("DCM-MAX-CONST-TX-NO-DCM"); + break; + case IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_BPSK: + PRINT("DCM-MAX-CONST-TX-BPSK"); + break; + case IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_QPSK: + PRINT("DCM-MAX-CONST-TX-QPSK"); + break; + case IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_16_QAM: + PRINT("DCM-MAX-CONST-TX-16-QAM"); + break; + } + + PFLAG(PHY, 3, DCM_MAX_TX_NSS_1, "DCM-MAX-TX-NSS-1"); + PFLAG(PHY, 3, DCM_MAX_TX_NSS_2, "DCM-MAX-TX-NSS-2"); + + switch (cap[3] & IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_MASK) { + case IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_NO_DCM: + PRINT("DCM-MAX-CONST-RX-NO-DCM"); + break; + case IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_BPSK: + PRINT("DCM-MAX-CONST-RX-BPSK"); + break; + case IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_QPSK: + PRINT("DCM-MAX-CONST-RX-QPSK"); + break; + case IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_16_QAM: + PRINT("DCM-MAX-CONST-RX-16-QAM"); + break; + } + + PFLAG(PHY, 3, DCM_MAX_RX_NSS_1, "DCM-MAX-RX-NSS-1"); + PFLAG(PHY, 3, DCM_MAX_RX_NSS_2, "DCM-MAX-RX-NSS-2"); + PFLAG(PHY, 3, RX_HE_MU_PPDU_FROM_NON_AP_STA, + "RX-HE-MU-PPDU-FROM-NON-AP-STA"); + PFLAG(PHY, 3, SU_BEAMFORMER, "SU-BEAMFORMER"); + + PFLAG(PHY, 4, SU_BEAMFORMEE, "SU-BEAMFORMEE"); + PFLAG(PHY, 4, MU_BEAMFORMER, "MU-BEAMFORMER"); + + PFLAG_RANGE(PHY, 4, BEAMFORMEE_MAX_STS_UNDER_80MHZ, 0, 1, 4, + "BEAMFORMEE-MAX-STS-UNDER-%d"); + PFLAG_RANGE(PHY, 4, BEAMFORMEE_MAX_STS_ABOVE_80MHZ, 0, 1, 4, + "BEAMFORMEE-MAX-STS-ABOVE-%d"); + + PFLAG_RANGE(PHY, 5, BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ, 0, 1, 1, + "NUM-SND-DIM-UNDER-80MHZ-%d"); + PFLAG_RANGE(PHY, 5, BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ, 0, 1, 1, + "NUM-SND-DIM-ABOVE-80MHZ-%d"); + PFLAG(PHY, 5, NG16_SU_FEEDBACK, "NG16-SU-FEEDBACK"); + PFLAG(PHY, 5, NG16_MU_FEEDBACK, "NG16-MU-FEEDBACK"); + + PFLAG(PHY, 6, CODEBOOK_SIZE_42_SU, "CODEBOOK-SIZE-42-SU"); + PFLAG(PHY, 6, CODEBOOK_SIZE_75_MU, "CODEBOOK-SIZE-75-MU"); + PFLAG(PHY, 6, TRIG_SU_BEAMFORMER_FB, "TRIG-SU-BEAMFORMER-FB"); + PFLAG(PHY, 6, TRIG_MU_BEAMFORMER_FB, "TRIG-MU-BEAMFORMER-FB"); + PFLAG(PHY, 6, TRIG_CQI_FB, "TRIG-CQI-FB"); + PFLAG(PHY, 6, PARTIAL_BW_EXT_RANGE, "PARTIAL-BW-EXT-RANGE"); + PFLAG(PHY, 6, PARTIAL_BANDWIDTH_DL_MUMIMO, + "PARTIAL-BANDWIDTH-DL-MUMIMO"); + PFLAG(PHY, 6, PPE_THRESHOLD_PRESENT, "PPE-THRESHOLD-PRESENT"); + + PFLAG(PHY, 7, SRP_BASED_SR, "SRP-BASED-SR"); + PFLAG(PHY, 7, POWER_BOOST_FACTOR_AR, "POWER-BOOST-FACTOR-AR"); + PFLAG(PHY, 7, HE_SU_MU_PPDU_4XLTF_AND_08_US_GI, + "HE-SU-MU-PPDU-4XLTF-AND-08-US-GI"); + PFLAG_RANGE(PHY, 7, MAX_NC, 0, 1, 1, "MAX-NC-%d"); + PFLAG(PHY, 7, STBC_TX_ABOVE_80MHZ, "STBC-TX-ABOVE-80MHZ"); + PFLAG(PHY, 7, STBC_RX_ABOVE_80MHZ, "STBC-RX-ABOVE-80MHZ"); + + PFLAG(PHY, 8, HE_ER_SU_PPDU_4XLTF_AND_08_US_GI, + "HE-ER-SU-PPDU-4XLTF-AND-08-US-GI"); + PFLAG(PHY, 8, 20MHZ_IN_40MHZ_HE_PPDU_IN_2G, + "20MHZ-IN-40MHZ-HE-PPDU-IN-2G"); + PFLAG(PHY, 8, 20MHZ_IN_160MHZ_HE_PPDU, "20MHZ-IN-160MHZ-HE-PPDU"); + PFLAG(PHY, 8, 80MHZ_IN_160MHZ_HE_PPDU, "80MHZ-IN-160MHZ-HE-PPDU"); + PFLAG(PHY, 8, HE_ER_SU_1XLTF_AND_08_US_GI, + "HE-ER-SU-1XLTF-AND-08-US-GI"); + PFLAG(PHY, 8, MIDAMBLE_RX_TX_2X_AND_1XLTF, + "MIDAMBLE-RX-TX-2X-AND-1XLTF"); + + switch (cap[8] & IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_MASK) { + case IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_20MHZ: + PRINT("DDCM-MAX-BW-20MHZ"); + break; + case IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_40MHZ: + PRINT("DCM-MAX-BW-40MHZ"); + break; + case IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_80MHZ: + PRINT("DCM-MAX-BW-80MHZ"); + break; + case IEEE80211_HE_PHY_CAP8_DCM_MAX_BW_160_OR_80P80_MHZ: + PRINT("DCM-MAX-BW-160-OR-80P80-MHZ"); + break; + } + + PFLAG(PHY, 9, LONGER_THAN_16_SIGB_OFDM_SYM, + "LONGER-THAN-16-SIGB-OFDM-SYM"); + PFLAG(PHY, 9, NON_TRIGGERED_CQI_FEEDBACK, + "NON-TRIGGERED-CQI-FEEDBACK"); + PFLAG(PHY, 9, TX_1024_QAM_LESS_THAN_242_TONE_RU, + "TX-1024-QAM-LESS-THAN-242-TONE-RU"); + PFLAG(PHY, 9, RX_1024_QAM_LESS_THAN_242_TONE_RU, + "RX-1024-QAM-LESS-THAN-242-TONE-RU"); + PFLAG(PHY, 9, RX_FULL_BW_SU_USING_MU_WITH_COMP_SIGB, + "RX-FULL-BW-SU-USING-MU-WITH-COMP-SIGB"); + PFLAG(PHY, 9, RX_FULL_BW_SU_USING_MU_WITH_NON_COMP_SIGB, + "RX-FULL-BW-SU-USING-MU-WITH-NON-COMP-SIGB"); + +#undef PFLAG_RANGE_DEFAULT +#undef PFLAG_RANGE +#undef PFLAG + +#define PRINT_NSS_SUPP(f, n) \ + do { \ + int i; \ + u16 v = le16_to_cpu(nss->f); \ + p += scnprintf(p, buf_sz + buf - p, n ": %#.4x\n", v); \ + for (i = 0; i < 8; i += 2) { \ + switch ((v >> i) & 0x3) { \ + case 0: \ + PRINT(n "-%d-SUPPORT-0-7", i / 2); \ + break; \ + case 1: \ + PRINT(n "-%d-SUPPORT-0-9", i / 2); \ + break; \ + case 2: \ + PRINT(n "-%d-SUPPORT-0-11", i / 2); \ + break; \ + case 3: \ + PRINT(n "-%d-NOT-SUPPORTED", i / 2); \ + break; \ + } \ + } \ + } while (0) + + PRINT_NSS_SUPP(rx_mcs_80, "RX-MCS-80"); + PRINT_NSS_SUPP(tx_mcs_80, "TX-MCS-80"); + + if (cap[0] & IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G) { + PRINT_NSS_SUPP(rx_mcs_160, "RX-MCS-160"); + PRINT_NSS_SUPP(tx_mcs_160, "TX-MCS-160"); + } + + if (cap[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G) { + PRINT_NSS_SUPP(rx_mcs_80p80, "RX-MCS-80P80"); + PRINT_NSS_SUPP(tx_mcs_80p80, "TX-MCS-80P80"); + } + +#undef PRINT_NSS_SUPP +#undef PRINT + + if (!(cap[6] & IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT)) + goto out; + + p += scnprintf(p, buf_sz + buf - p, "PPE-THRESHOLDS: %#.2x", + hec->ppe_thres[0]); + + ppe_size = ieee80211_he_ppe_size(hec->ppe_thres[0], cap); + for (i = 1; i < ppe_size; i++) { + p += scnprintf(p, buf_sz + buf - p, " %#.2x", + hec->ppe_thres[i]); + } + p += scnprintf(p, buf_sz + buf - p, "\n"); + +out: + ret = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); + kfree(buf); + return ret; +} +STA_OPS(he_capa); #define DEBUGFS_ADD(name) \ debugfs_create_file(#name, 0400, \ @@ -538,6 +897,7 @@ void ieee80211_sta_debugfs_add(struct sta_info *sta) DEBUGFS_ADD(agg_status); DEBUGFS_ADD(ht_capa); DEBUGFS_ADD(vht_capa); + DEBUGFS_ADD(he_capa); DEBUGFS_ADD_COUNTER(rx_duplicates, rx_stats.num_duplicates); DEBUGFS_ADD_COUNTER(rx_fragments, rx_stats.fragments); diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 8f6998091d26..e42c641b6190 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -1173,6 +1173,16 @@ static inline void drv_wake_tx_queue(struct ieee80211_local *local, local->ops->wake_tx_queue(&local->hw, &txq->txq); } +static inline int drv_can_aggregate_in_amsdu(struct ieee80211_local *local, + struct sk_buff *head, + struct sk_buff *skb) +{ + if (!local->ops->can_aggregate_in_amsdu) + return true; + + return local->ops->can_aggregate_in_amsdu(&local->hw, head, skb); +} + static inline int drv_start_nan(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, struct cfg80211_nan_conf *conf) diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 6449a1c2283b..0d704e8d7078 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -947,8 +947,8 @@ static void ieee80211_rx_mgmt_deauth_ibss(struct ieee80211_sub_if_data *sdata, if (len < IEEE80211_DEAUTH_FRAME_LEN) return; - ibss_dbg(sdata, "RX DeAuth SA=%pM DA=%pM BSSID=%pM (reason: %d)\n", - mgmt->sa, mgmt->da, mgmt->bssid, reason); + ibss_dbg(sdata, "RX DeAuth SA=%pM DA=%pM\n", mgmt->sa, mgmt->da); + ibss_dbg(sdata, "\tBSSID=%pM (reason: %d)\n", mgmt->bssid, reason); sta_info_destroy_addr(sdata, mgmt->sa); } @@ -966,9 +966,9 @@ static void ieee80211_rx_mgmt_auth_ibss(struct ieee80211_sub_if_data *sdata, auth_alg = le16_to_cpu(mgmt->u.auth.auth_alg); auth_transaction = le16_to_cpu(mgmt->u.auth.auth_transaction); - ibss_dbg(sdata, - "RX Auth SA=%pM DA=%pM BSSID=%pM (auth_transaction=%d)\n", - mgmt->sa, mgmt->da, mgmt->bssid, auth_transaction); + ibss_dbg(sdata, "RX Auth SA=%pM DA=%pM\n", mgmt->sa, mgmt->da); + ibss_dbg(sdata, "\tBSSID=%pM (auth_transaction=%d)\n", + mgmt->bssid, auth_transaction); if (auth_alg != WLAN_AUTH_OPEN || auth_transaction != 1) return; @@ -1070,7 +1070,9 @@ static void ieee80211_update_sta_info(struct ieee80211_sub_if_data *sdata, struct ieee80211_vht_cap cap_ie; struct ieee80211_sta_vht_cap cap = sta->sta.vht_cap; - ieee80211_chandef_vht_oper(elems->vht_operation, + ieee80211_chandef_vht_oper(&local->hw, + elems->vht_operation, + elems->ht_operation, &chandef); memcpy(&cap_ie, elems->vht_cap_elem, sizeof(cap_ie)); ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband, @@ -1175,10 +1177,10 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, rx_timestamp = drv_get_tsf(local, sdata); } - ibss_dbg(sdata, - "RX beacon SA=%pM BSSID=%pM TSF=0x%llx BCN=0x%llx diff=%lld @%lu\n", + ibss_dbg(sdata, "RX beacon SA=%pM BSSID=%pM TSF=0x%llx\n", mgmt->sa, mgmt->bssid, - (unsigned long long)rx_timestamp, + (unsigned long long)rx_timestamp); + ibss_dbg(sdata, "\tBCN=0x%llx diff=%lld @%lu\n", (unsigned long long)beacon_timestamp, (unsigned long long)(rx_timestamp - beacon_timestamp), jiffies); @@ -1537,9 +1539,9 @@ static void ieee80211_rx_mgmt_probe_req(struct ieee80211_sub_if_data *sdata, tx_last_beacon = drv_tx_last_beacon(local); - ibss_dbg(sdata, - "RX ProbeReq SA=%pM DA=%pM BSSID=%pM (tx_last_beacon=%d)\n", - mgmt->sa, mgmt->da, mgmt->bssid, tx_last_beacon); + ibss_dbg(sdata, "RX ProbeReq SA=%pM DA=%pM\n", mgmt->sa, mgmt->da); + ibss_dbg(sdata, "\tBSSID=%pM (tx_last_beacon=%d)\n", + mgmt->bssid, tx_last_beacon); if (!tx_last_beacon && is_multicast_ether_addr(mgmt->da)) return; diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 172aeae21ae9..f40a2167935f 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -818,6 +818,7 @@ enum txq_info_flags { IEEE80211_TXQ_STOP, IEEE80211_TXQ_AMPDU, IEEE80211_TXQ_NO_AMSDU, + IEEE80211_TXQ_STOP_NETIF_TX, }; /** @@ -1198,6 +1199,9 @@ struct ieee80211_local { /* number of RX chains the hardware has */ u8 rx_chains; + /* bitmap of which sbands were copied */ + u8 sband_allocated; + int tx_headroom; /* required headroom for hardware/radiotap */ /* Tasklet and skb queue to process calls from IRQ mode. All frames @@ -1226,6 +1230,7 @@ struct ieee80211_local { struct sk_buff_head pending[IEEE80211_MAX_QUEUES]; struct tasklet_struct tx_pending_tasklet; + struct tasklet_struct wake_txqs_tasklet; atomic_t agg_queue_stop[IEEE80211_MAX_QUEUES]; @@ -2038,6 +2043,7 @@ void ieee80211_txq_remove_vlan(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata); void ieee80211_fill_txq_stats(struct cfg80211_txq_stats *txqstats, struct txq_info *txqi); +void ieee80211_wake_txqs(unsigned long data); void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata, u16 transaction, u16 auth_alg, u16 status, const u8 *extra, size_t extra_len, const u8 *bssid, @@ -2106,7 +2112,9 @@ u8 *ieee80211_add_wmm_info_ie(u8 *buf, u8 qosinfo); /* channel management */ bool ieee80211_chandef_ht_oper(const struct ieee80211_ht_operation *ht_oper, struct cfg80211_chan_def *chandef); -bool ieee80211_chandef_vht_oper(const struct ieee80211_vht_operation *oper, +bool ieee80211_chandef_vht_oper(struct ieee80211_hw *hw, + const struct ieee80211_vht_operation *oper, + const struct ieee80211_ht_operation *htop, struct cfg80211_chan_def *chandef); u32 ieee80211_chandef_downgrade(struct cfg80211_chan_def *c); diff --git a/net/mac80211/key.c b/net/mac80211/key.c index c054ac85793c..4700718e010f 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -248,6 +248,7 @@ static void ieee80211_key_disable_hw_accel(struct ieee80211_key *key) (key->conf.flags & IEEE80211_KEY_FLAG_RESERVE_TAILROOM))) increment_tailroom_need_count(sdata); + key->flags &= ~KEY_FLAG_UPLOADED_TO_HARDWARE; ret = drv_set_key(key->local, DISABLE_KEY, sdata, sta ? &sta->sta : NULL, &key->conf); @@ -256,8 +257,65 @@ static void ieee80211_key_disable_hw_accel(struct ieee80211_key *key) "failed to remove key (%d, %pM) from hardware (%d)\n", key->conf.keyidx, sta ? sta->sta.addr : bcast_addr, ret); +} - key->flags &= ~KEY_FLAG_UPLOADED_TO_HARDWARE; +static int ieee80211_hw_key_replace(struct ieee80211_key *old_key, + struct ieee80211_key *new_key, + bool ptk0rekey) +{ + struct ieee80211_sub_if_data *sdata; + struct ieee80211_local *local; + struct sta_info *sta; + int ret; + + /* Aggregation sessions are OK when running on SW crypto. + * A broken remote STA may cause issues not observed with HW + * crypto, though. + */ + if (!(old_key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE)) + return 0; + + assert_key_lock(old_key->local); + sta = old_key->sta; + + /* PTK only using key ID 0 needs special handling on rekey */ + if (new_key && sta && ptk0rekey) { + local = old_key->local; + sdata = old_key->sdata; + + /* Stop TX till we are on the new key */ + old_key->flags |= KEY_FLAG_TAINTED; + ieee80211_clear_fast_xmit(sta); + + /* Aggregation sessions during rekey are complicated due to the + * reorder buffer and retransmits. Side step that by blocking + * aggregation during rekey and tear down running sessions. + */ + if (ieee80211_hw_check(&local->hw, AMPDU_AGGREGATION)) { + set_sta_flag(sta, WLAN_STA_BLOCK_BA); + ieee80211_sta_tear_down_BA_sessions(sta, + AGG_STOP_LOCAL_REQUEST); + } + + if (!wiphy_ext_feature_isset(local->hw.wiphy, + NL80211_EXT_FEATURE_CAN_REPLACE_PTK0)) { + pr_warn_ratelimited("Rekeying PTK for STA %pM but driver can't safely do that.", + sta->sta.addr); + /* Flushing the driver queues *may* help prevent + * the clear text leaks and freezes. + */ + ieee80211_flush_queues(local, sdata, false); + } + } + + ieee80211_key_disable_hw_accel(old_key); + + if (new_key) + ret = ieee80211_key_enable_hw_accel(new_key); + else + ret = 0; + + return ret; } static void __ieee80211_set_default_key(struct ieee80211_sub_if_data *sdata, @@ -316,38 +374,57 @@ void ieee80211_set_default_mgmt_key(struct ieee80211_sub_if_data *sdata, } -static void ieee80211_key_replace(struct ieee80211_sub_if_data *sdata, +static int ieee80211_key_replace(struct ieee80211_sub_if_data *sdata, struct sta_info *sta, bool pairwise, struct ieee80211_key *old, struct ieee80211_key *new) { int idx; + int ret; bool defunikey, defmultikey, defmgmtkey; /* caller must provide at least one old/new */ if (WARN_ON(!new && !old)) - return; + return 0; if (new) list_add_tail_rcu(&new->list, &sdata->key_list); WARN_ON(new && old && new->conf.keyidx != old->conf.keyidx); - if (old) + if (old) { idx = old->conf.keyidx; - else + /* TODO: proper implement and test "Extended Key ID for + * Individually Addressed Frames" from IEEE 802.11-2016. + * Till then always assume only key ID 0 is used for + * pairwise keys.*/ + ret = ieee80211_hw_key_replace(old, new, pairwise); + } else { + /* new must be provided in case old is not */ idx = new->conf.keyidx; + if (!new->local->wowlan) + ret = ieee80211_key_enable_hw_accel(new); + else + ret = 0; + } + + if (ret) + return ret; if (sta) { if (pairwise) { rcu_assign_pointer(sta->ptk[idx], new); sta->ptk_idx = idx; - ieee80211_check_fast_xmit(sta); + if (new) { + clear_sta_flag(sta, WLAN_STA_BLOCK_BA); + ieee80211_check_fast_xmit(sta); + } } else { rcu_assign_pointer(sta->gtk[idx], new); } - ieee80211_check_fast_rx(sta); + if (new) + ieee80211_check_fast_rx(sta); } else { defunikey = old && old == key_mtx_dereference(sdata->local, @@ -380,6 +457,8 @@ static void ieee80211_key_replace(struct ieee80211_sub_if_data *sdata, if (old) list_del_rcu(&old->list); + + return 0; } struct ieee80211_key * @@ -575,9 +654,6 @@ static void ieee80211_key_free_common(struct ieee80211_key *key) static void __ieee80211_key_destroy(struct ieee80211_key *key, bool delay_tailroom) { - if (key->local) - ieee80211_key_disable_hw_accel(key); - if (key->local) { struct ieee80211_sub_if_data *sdata = key->sdata; @@ -654,7 +730,6 @@ int ieee80211_key_link(struct ieee80211_key *key, struct ieee80211_sub_if_data *sdata, struct sta_info *sta) { - struct ieee80211_local *local = sdata->local; struct ieee80211_key *old_key; int idx = key->conf.keyidx; bool pairwise = key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE; @@ -691,17 +766,13 @@ int ieee80211_key_link(struct ieee80211_key *key, increment_tailroom_need_count(sdata); - ieee80211_key_replace(sdata, sta, pairwise, old_key, key); - ieee80211_key_destroy(old_key, delay_tailroom); - - ieee80211_debugfs_key_add(key); + ret = ieee80211_key_replace(sdata, sta, pairwise, old_key, key); - if (!local->wowlan) { - ret = ieee80211_key_enable_hw_accel(key); - if (ret) - ieee80211_key_free(key, delay_tailroom); + if (!ret) { + ieee80211_debugfs_key_add(key); + ieee80211_key_destroy(old_key, delay_tailroom); } else { - ret = 0; + ieee80211_key_free(key, delay_tailroom); } out: diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 4fb2709cb527..77381017bac7 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -4,6 +4,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2017 Intel Deutschland GmbH + * Copyright (C) 2018 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -256,8 +257,27 @@ static void ieee80211_restart_work(struct work_struct *work) flush_work(&local->radar_detected_work); rtnl_lock(); - list_for_each_entry(sdata, &local->interfaces, list) + list_for_each_entry(sdata, &local->interfaces, list) { + /* + * XXX: there may be more work for other vif types and even + * for station mode: a good thing would be to run most of + * the iface type's dependent _stop (ieee80211_mg_stop, + * ieee80211_ibss_stop) etc... + * For now, fix only the specific bug that was seen: race + * between csa_connection_drop_work and us. + */ + if (sdata->vif.type == NL80211_IFTYPE_STATION) { + /* + * This worker is scheduled from the iface worker that + * runs on mac80211's workqueue, so we can't be + * scheduling this worker after the cancel right here. + * The exception is ieee80211_chswitch_done. + * Then we can have a race... + */ + cancel_work_sync(&sdata->u.mgd.csa_connection_drop_work); + } flush_delayed_work(&sdata->dec_tailroom_needed_wk); + } ieee80211_scan_cancel(local); /* make sure any new ROC will consider local->in_reconfig */ @@ -471,10 +491,7 @@ static const struct ieee80211_vht_cap mac80211_vht_capa_mod_mask = { cpu_to_le32(IEEE80211_VHT_CAP_RXLDPC | IEEE80211_VHT_CAP_SHORT_GI_80 | IEEE80211_VHT_CAP_SHORT_GI_160 | - IEEE80211_VHT_CAP_RXSTBC_1 | - IEEE80211_VHT_CAP_RXSTBC_2 | - IEEE80211_VHT_CAP_RXSTBC_3 | - IEEE80211_VHT_CAP_RXSTBC_4 | + IEEE80211_VHT_CAP_RXSTBC_MASK | IEEE80211_VHT_CAP_TXSTBC | IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE | IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE | @@ -594,6 +611,18 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, local->ops = ops; local->use_chanctx = use_chanctx; + /* + * We need a bit of data queued to build aggregates properly, so + * instruct the TCP stack to allow more than a single ms of data + * to be queued in the stack. The value is a bit-shift of 1 + * second, so 8 is ~4ms of queued data. Only affects local TCP + * sockets. + * This is the default, anyhow - drivers may need to override it + * for local reasons (longer buffers, longer completion time, or + * similar). + */ + local->hw.tx_sk_pacing_shift = 8; + /* set up some defaults */ local->hw.queues = 1; local->hw.max_rates = 1; @@ -668,6 +697,10 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, tasklet_init(&local->tx_pending_tasklet, ieee80211_tx_pending, (unsigned long)local); + if (ops->wake_tx_queue) + tasklet_init(&local->wake_txqs_tasklet, ieee80211_wake_txqs, + (unsigned long)local); + tasklet_init(&local->tasklet, ieee80211_tasklet_handler, (unsigned long) local); @@ -1138,6 +1171,51 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) goto fail_rate; } + if (local->rate_ctrl) { + clear_bit(IEEE80211_HW_SUPPORTS_VHT_EXT_NSS_BW, hw->flags); + if (local->rate_ctrl->ops->capa & RATE_CTRL_CAPA_VHT_EXT_NSS_BW) + ieee80211_hw_set(hw, SUPPORTS_VHT_EXT_NSS_BW); + } + + /* + * If the VHT capabilities don't have IEEE80211_VHT_EXT_NSS_BW_CAPABLE, + * or have it when we don't, copy the sband structure and set/clear it. + * This is necessary because rate scaling algorithms could be switched + * and have different support values. + * Print a message so that in the common case the reallocation can be + * avoided. + */ + BUILD_BUG_ON(NUM_NL80211_BANDS > 8 * sizeof(local->sband_allocated)); + for (band = 0; band < NUM_NL80211_BANDS; band++) { + struct ieee80211_supported_band *sband; + bool local_cap, ie_cap; + + local_cap = ieee80211_hw_check(hw, SUPPORTS_VHT_EXT_NSS_BW); + + sband = local->hw.wiphy->bands[band]; + if (!sband || !sband->vht_cap.vht_supported) + continue; + + ie_cap = !!(sband->vht_cap.vht_mcs.tx_highest & + cpu_to_le16(IEEE80211_VHT_EXT_NSS_BW_CAPABLE)); + + if (local_cap == ie_cap) + continue; + + sband = kmemdup(sband, sizeof(*sband), GFP_KERNEL); + if (!sband) + goto fail_rate; + + wiphy_dbg(hw->wiphy, "copying sband (band %d) due to VHT EXT NSS BW flag\n", + band); + + sband->vht_cap.vht_mcs.tx_highest ^= + cpu_to_le16(IEEE80211_VHT_EXT_NSS_BW_CAPABLE); + + local->hw.wiphy->bands[band] = sband; + local->sband_allocated |= BIT(band); + } + /* add one default STA interface if supported */ if (local->hw.wiphy->interface_modes & BIT(NL80211_IFTYPE_STATION) && !ieee80211_hw_check(hw, NO_AUTO_VIF)) { @@ -1208,6 +1286,7 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw) #if IS_ENABLED(CONFIG_IPV6) unregister_inet6addr_notifier(&local->ifa6_notifier); #endif + ieee80211_txq_teardown_flows(local); rtnl_lock(); @@ -1236,7 +1315,6 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw) skb_queue_purge(&local->skb_queue); skb_queue_purge(&local->skb_queue_unreliable); skb_queue_purge(&local->skb_queue_tdls_chsw); - ieee80211_txq_teardown_flows(local); destroy_workqueue(local->workqueue); wiphy_unregister(local->hw.wiphy); @@ -1256,6 +1334,7 @@ static int ieee80211_free_ack_frame(int id, void *p, void *data) void ieee80211_free_hw(struct ieee80211_hw *hw) { struct ieee80211_local *local = hw_to_local(hw); + enum nl80211_band band; mutex_destroy(&local->iflist_mtx); mutex_destroy(&local->mtx); @@ -1271,6 +1350,12 @@ void ieee80211_free_hw(struct ieee80211_hw *hw) ieee80211_free_led_names(local); + for (band = 0; band < NUM_NL80211_BANDS; band++) { + if (!(local->sband_allocated & BIT(band))) + continue; + kfree(local->hw.wiphy->bands[band]); + } + wiphy_free(local->hw.wiphy); } EXPORT_SYMBOL(ieee80211_free_hw); diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index d51da26e9c18..8bad414c52ad 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -1,5 +1,6 @@ /* * Copyright (c) 2008, 2009 open80211s Ltd. + * Copyright (C) 2018 Intel Corporation * Authors: Luis Carlos Cobo <luisca@cozybit.com> * Javier Cardona <javier@cozybit.com> * @@ -98,7 +99,9 @@ bool mesh_matches_local(struct ieee80211_sub_if_data *sdata, cfg80211_chandef_create(&sta_chan_def, sdata->vif.bss_conf.chandef.chan, NL80211_CHAN_NO_HT); ieee80211_chandef_ht_oper(ie->ht_operation, &sta_chan_def); - ieee80211_chandef_vht_oper(ie->vht_operation, &sta_chan_def); + ieee80211_chandef_vht_oper(&sdata->local->hw, + ie->vht_operation, ie->ht_operation, + &sta_chan_def); if (!cfg80211_chandef_compatible(&sdata->vif.bss_conf.chandef, &sta_chan_def)) diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 35ad3983ae4b..daf9db3c8f24 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -572,6 +572,10 @@ static void hwmp_preq_frame_process(struct ieee80211_sub_if_data *sdata, forward = false; reply = true; target_metric = 0; + + if (SN_GT(target_sn, ifmsh->sn)) + ifmsh->sn = target_sn; + if (time_after(jiffies, ifmsh->last_sn_update + net_traversal_jiffies(sdata)) || time_before(jiffies, ifmsh->last_sn_update)) { diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 7fb9957359a3..89dac799a85f 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -220,7 +220,8 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, memcpy(&he_oper_vht_cap, he_oper->optional, 3); he_oper_vht_cap.basic_mcs_set = cpu_to_le16(0); - if (!ieee80211_chandef_vht_oper(&he_oper_vht_cap, + if (!ieee80211_chandef_vht_oper(&sdata->local->hw, + &he_oper_vht_cap, ht_oper, &vht_chandef)) { if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HE)) sdata_info(sdata, @@ -228,7 +229,8 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata, ret = IEEE80211_STA_DISABLE_HE; goto out; } - } else if (!ieee80211_chandef_vht_oper(vht_oper, &vht_chandef)) { + } else if (!ieee80211_chandef_vht_oper(&sdata->local->hw, vht_oper, + ht_oper, &vht_chandef)) { if (!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT)) sdata_info(sdata, "AP VHT information is invalid, disable VHT\n"); @@ -1073,6 +1075,10 @@ static void ieee80211_chswitch_work(struct work_struct *work) */ if (sdata->reserved_chanctx) { + struct ieee80211_supported_band *sband = NULL; + struct sta_info *mgd_sta = NULL; + enum ieee80211_sta_rx_bandwidth bw = IEEE80211_STA_RX_BW_20; + /* * with multi-vif csa driver may call ieee80211_csa_finish() * many times while waiting for other interfaces to use their @@ -1081,6 +1087,48 @@ static void ieee80211_chswitch_work(struct work_struct *work) if (sdata->reserved_ready) goto out; + if (sdata->vif.bss_conf.chandef.width != + sdata->csa_chandef.width) { + /* + * For managed interface, we need to also update the AP + * station bandwidth and align the rate scale algorithm + * on the bandwidth change. Here we only consider the + * bandwidth of the new channel definition (as channel + * switch flow does not have the full HT/VHT/HE + * information), assuming that if additional changes are + * required they would be done as part of the processing + * of the next beacon from the AP. + */ + switch (sdata->csa_chandef.width) { + case NL80211_CHAN_WIDTH_20_NOHT: + case NL80211_CHAN_WIDTH_20: + default: + bw = IEEE80211_STA_RX_BW_20; + break; + case NL80211_CHAN_WIDTH_40: + bw = IEEE80211_STA_RX_BW_40; + break; + case NL80211_CHAN_WIDTH_80: + bw = IEEE80211_STA_RX_BW_80; + break; + case NL80211_CHAN_WIDTH_80P80: + case NL80211_CHAN_WIDTH_160: + bw = IEEE80211_STA_RX_BW_160; + break; + } + + mgd_sta = sta_info_get(sdata, ifmgd->bssid); + sband = + local->hw.wiphy->bands[sdata->csa_chandef.chan->band]; + } + + if (sdata->vif.bss_conf.chandef.width > + sdata->csa_chandef.width) { + mgd_sta->sta.bandwidth = bw; + rate_control_rate_update(local, sband, mgd_sta, + IEEE80211_RC_BW_CHANGED); + } + ret = ieee80211_vif_use_reserved_context(sdata); if (ret) { sdata_info(sdata, @@ -1091,6 +1139,13 @@ static void ieee80211_chswitch_work(struct work_struct *work) goto out; } + if (sdata->vif.bss_conf.chandef.width < + sdata->csa_chandef.width) { + mgd_sta->sta.bandwidth = bw; + rate_control_rate_update(local, sband, mgd_sta, + IEEE80211_RC_BW_CHANGED); + } + goto out; } @@ -1312,6 +1367,16 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, cbss->beacon_interval)); return; drop_connection: + /* + * This is just so that the disconnect flow will know that + * we were trying to switch channel and failed. In case the + * mode is 1 (we are not allowed to Tx), we will know not to + * send a deauthentication frame. Those two fields will be + * reset when the disconnection worker runs. + */ + sdata->vif.csa_active = true; + sdata->csa_block_tx = csa_ie.mode; + ieee80211_queue_work(&local->hw, &ifmgd->csa_connection_drop_work); mutex_unlock(&local->chanctx_mtx); mutex_unlock(&local->mtx); @@ -2522,6 +2587,7 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata) struct ieee80211_local *local = sdata->local; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; u8 frame_buf[IEEE80211_DEAUTH_FRAME_LEN]; + bool tx; sdata_lock(sdata); if (!ifmgd->associated) { @@ -2529,6 +2595,8 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata) return; } + tx = !sdata->csa_block_tx; + /* AP is probably out of range (or not reachable for another reason) so * remove the bss struct for that AP. */ @@ -2536,7 +2604,7 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata) ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DEAUTH, WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY, - true, frame_buf); + tx, frame_buf); mutex_lock(&local->mtx); sdata->vif.csa_active = false; ifmgd->csa_waiting_bcn = false; @@ -2547,7 +2615,7 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata) } mutex_unlock(&local->mtx); - ieee80211_report_disconnect(sdata, frame_buf, sizeof(frame_buf), true, + ieee80211_report_disconnect(sdata, frame_buf, sizeof(frame_buf), tx, WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY); sdata_unlock(sdata); @@ -3171,19 +3239,16 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata, } if (bss_conf->he_support) { - u32 he_oper_params = - le32_to_cpu(elems.he_operation->he_oper_params); + bss_conf->bss_color = + le32_get_bits(elems.he_operation->he_oper_params, + IEEE80211_HE_OPERATION_BSS_COLOR_MASK); - bss_conf->bss_color = he_oper_params & - IEEE80211_HE_OPERATION_BSS_COLOR_MASK; bss_conf->htc_trig_based_pkt_ext = - (he_oper_params & - IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK) << - IEEE80211_HE_OPERATION_DFLT_PE_DURATION_OFFSET; + le32_get_bits(elems.he_operation->he_oper_params, + IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK); bss_conf->frame_time_rts_th = - (he_oper_params & - IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK) << - IEEE80211_HE_OPERATION_RTS_THRESHOLD_OFFSET; + le32_get_bits(elems.he_operation->he_oper_params, + IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK); bss_conf->multi_sta_back_32bit = sta->sta.he_cap.he_cap_elem.mac_cap_info[2] & diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 64742f2765c4..a0ca27aeb732 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -115,7 +115,8 @@ static inline bool should_drop_frame(struct sk_buff *skb, int present_fcs_len, if (status->flag & (RX_FLAG_FAILED_FCS_CRC | RX_FLAG_FAILED_PLCP_CRC | - RX_FLAG_ONLY_MONITOR)) + RX_FLAG_ONLY_MONITOR | + RX_FLAG_NO_PSDU)) return true; if (unlikely(skb->len < 16 + present_fcs_len + rtap_space)) @@ -189,6 +190,15 @@ ieee80211_rx_radiotap_hdrlen(struct ieee80211_local *local, BUILD_BUG_ON(sizeof(struct ieee80211_radiotap_he_mu) != 12); } + if (status->flag & RX_FLAG_NO_PSDU) + len += 1; + + if (status->flag & RX_FLAG_RADIOTAP_LSIG) { + len = ALIGN(len, 2); + len += 4; + BUILD_BUG_ON(sizeof(struct ieee80211_radiotap_lsig) != 4); + } + if (status->chains) { /* antenna and antenna signal fields */ len += 2 * hweight8(status->chains); @@ -279,6 +289,7 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, struct ieee80211_vendor_radiotap rtap = {}; struct ieee80211_radiotap_he he = {}; struct ieee80211_radiotap_he_mu he_mu = {}; + struct ieee80211_radiotap_lsig lsig = {}; if (status->flag & RX_FLAG_RADIOTAP_HE) { he = *(struct ieee80211_radiotap_he *)skb->data; @@ -291,6 +302,11 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, skb_pull(skb, sizeof(he_mu)); } + if (status->flag & RX_FLAG_RADIOTAP_LSIG) { + lsig = *(struct ieee80211_radiotap_lsig *)skb->data; + skb_pull(skb, sizeof(lsig)); + } + if (status->flag & RX_FLAG_RADIOTAP_VENDOR_DATA) { rtap = *(struct ieee80211_vendor_radiotap *)skb->data; /* rtap.len and rtap.pad are undone immediately */ @@ -549,7 +565,7 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, if (status->encoding == RX_ENC_HE && status->flag & RX_FLAG_RADIOTAP_HE) { -#define HE_PREP(f, val) cpu_to_le16(FIELD_PREP(IEEE80211_RADIOTAP_HE_##f, val)) +#define HE_PREP(f, val) le16_encode_bits(val, IEEE80211_RADIOTAP_HE_##f) if (status->enc_flags & RX_ENC_FLAG_STBC_MASK) { he.data6 |= HE_PREP(DATA6_NSTS, @@ -630,6 +646,21 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, pos += sizeof(he_mu); } + if (status->flag & RX_FLAG_NO_PSDU) { + rthdr->it_present |= + cpu_to_le32(1 << IEEE80211_RADIOTAP_ZERO_LEN_PSDU); + *pos++ = status->zero_length_psdu_type; + } + + if (status->flag & RX_FLAG_RADIOTAP_LSIG) { + /* ensure 2 byte alignment */ + while ((pos - (u8 *)rthdr) & 1) + pos++; + rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_LSIG); + memcpy(pos, &lsig, sizeof(lsig)); + pos += sizeof(lsig); + } + for_each_set_bit(chain, &chains, IEEE80211_MAX_CHAINS) { *pos++ = status->chain_signal[chain]; *pos++ = chain; @@ -1505,7 +1536,7 @@ static void sta_ps_start(struct sta_info *sta) if (!sta->sta.txq[0]) return; - for (tid = 0; tid < ARRAY_SIZE(sta->sta.txq); tid++) { + for (tid = 0; tid < IEEE80211_NUM_TIDS; tid++) { if (txq_has_queue(sta->sta.txq[tid])) set_bit(tid, &sta->txq_buffered_tids); else @@ -1728,6 +1759,7 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) */ if (!ieee80211_hw_check(&sta->local->hw, AP_LINK_PS) && !ieee80211_has_morefrags(hdr->frame_control) && + !is_multicast_ether_addr(hdr->addr1) && (ieee80211_is_mgmt(hdr->frame_control) || ieee80211_is_data(hdr->frame_control)) && !(status->rx_flags & IEEE80211_RX_DEFERRED_RELEASE) && @@ -2045,6 +2077,7 @@ ieee80211_reassemble_find(struct ieee80211_sub_if_data *sdata, idx = sdata->fragment_next; for (i = 0; i < IEEE80211_FRAGMENT_MAX; i++) { struct ieee80211_hdr *f_hdr; + struct sk_buff *f_skb; idx--; if (idx < 0) @@ -2056,7 +2089,8 @@ ieee80211_reassemble_find(struct ieee80211_sub_if_data *sdata, entry->last_frag + 1 != frag) continue; - f_hdr = (struct ieee80211_hdr *)entry->skb_list.next->data; + f_skb = __skb_peek(&entry->skb_list); + f_hdr = (struct ieee80211_hdr *) f_skb->data; /* * Check ftype and addresses are equal, else check next fragment @@ -2313,7 +2347,7 @@ __ieee80211_data_to_8023(struct ieee80211_rx_data *rx, bool *port_control) if (!sdata->u.mgd.use_4addr) return -1; - else + else if (!ether_addr_equal(hdr->addr1, sdata->vif.addr)) check_port_control = true; } diff --git a/net/mac80211/spectmgmt.c b/net/mac80211/spectmgmt.c index 029334835747..4e4902bdbef8 100644 --- a/net/mac80211/spectmgmt.c +++ b/net/mac80211/spectmgmt.c @@ -144,6 +144,7 @@ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, wide_bw_chansw_ie->new_center_freq_seg1, /* .basic_mcs_set doesn't matter */ }; + struct ieee80211_ht_operation ht_oper = {}; /* default, for the case of IEEE80211_VHT_CHANWIDTH_USE_HT, * to the previously parsed chandef @@ -151,7 +152,9 @@ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata, new_vht_chandef = csa_ie->chandef; /* ignore if parsing fails */ - if (!ieee80211_chandef_vht_oper(&vht_oper, &new_vht_chandef)) + if (!ieee80211_chandef_vht_oper(&sdata->local->hw, + &vht_oper, &ht_oper, + &new_vht_chandef)) new_vht_chandef.chan = NULL; if (sta_flags & IEEE80211_STA_DISABLE_80P80MHZ && diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index f34202242d24..fb8c2252ac0e 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -113,7 +113,12 @@ static void __cleanup_single_sta(struct sta_info *sta) if (sta->sta.txq[0]) { for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) { - struct txq_info *txqi = to_txq_info(sta->sta.txq[i]); + struct txq_info *txqi; + + if (!sta->sta.txq[i]) + continue; + + txqi = to_txq_info(sta->sta.txq[i]); spin_lock_bh(&fq->lock); ieee80211_txq_purge(local, txqi); @@ -374,6 +379,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) { struct txq_info *txq = txq_data + i * size; + /* might not do anything for the bufferable MMPDU TXQ */ ieee80211_txq_init(sdata, sta, txq, i); } } @@ -1239,13 +1245,11 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) if (!ieee80211_hw_check(&local->hw, AP_LINK_PS)) drv_sta_notify(local, sdata, STA_NOTIFY_AWAKE, &sta->sta); - if (sta->sta.txq[0]) { - for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) { - if (!txq_has_queue(sta->sta.txq[i])) - continue; + for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) { + if (!sta->sta.txq[i] || !txq_has_queue(sta->sta.txq[i])) + continue; - drv_wake_tx_queue(local, to_txq_info(sta->sta.txq[i])); - } + drv_wake_tx_queue(local, to_txq_info(sta->sta.txq[i])); } skb_queue_head_init(&pending); @@ -1683,7 +1687,8 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta, return; for (tid = 0; tid < ARRAY_SIZE(sta->sta.txq); tid++) { - if (!(driver_release_tids & BIT(tid)) || + if (!sta->sta.txq[tid] || + !(driver_release_tids & BIT(tid)) || txq_has_queue(sta->sta.txq[tid])) continue; @@ -2323,13 +2328,13 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo, sinfo->filled |= BIT_ULL(NL80211_STA_INFO_ACK_SIGNAL); } - if (ieee80211_hw_check(&sta->local->hw, REPORTS_TX_ACK_STATUS) && - !(sinfo->filled & BIT_ULL(NL80211_STA_INFO_DATA_ACK_SIGNAL_AVG))) { + if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_ACK_SIGNAL_AVG)) && + sta->status_stats.ack_signal_filled) { sinfo->avg_ack_signal = -(s8)ewma_avg_signal_read( &sta->status_stats.avg_ack_signal); sinfo->filled |= - BIT_ULL(NL80211_STA_INFO_DATA_ACK_SIGNAL_AVG); + BIT_ULL(NL80211_STA_INFO_ACK_SIGNAL_AVG); } } diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index cd332e3e1134..c42bfa1dcd2c 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1249,10 +1249,18 @@ static struct txq_info *ieee80211_get_txq(struct ieee80211_local *local, (info->control.flags & IEEE80211_TX_CTRL_PS_RESPONSE)) return NULL; - if (!ieee80211_is_data_present(hdr->frame_control)) - return NULL; - - if (sta) { + if (unlikely(!ieee80211_is_data_present(hdr->frame_control))) { + if ((!ieee80211_is_mgmt(hdr->frame_control) || + ieee80211_is_bufferable_mmpdu(hdr->frame_control) || + vif->type == NL80211_IFTYPE_STATION) && + sta && sta->uploaded) { + /* + * This will be NULL if the driver didn't set the + * opt-in hardware flag. + */ + txq = sta->sta.txq[IEEE80211_NUM_TIDS]; + } + } else if (sta) { u8 tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK; if (!sta->uploaded) @@ -1440,16 +1448,33 @@ void ieee80211_txq_init(struct ieee80211_sub_if_data *sdata, txqi->txq.vif = &sdata->vif; - if (sta) { - txqi->txq.sta = &sta->sta; - sta->sta.txq[tid] = &txqi->txq; - txqi->txq.tid = tid; - txqi->txq.ac = ieee80211_ac_from_tid(tid); - } else { + if (!sta) { sdata->vif.txq = &txqi->txq; txqi->txq.tid = 0; txqi->txq.ac = IEEE80211_AC_BE; + + return; } + + if (tid == IEEE80211_NUM_TIDS) { + if (sdata->vif.type == NL80211_IFTYPE_STATION) { + /* Drivers need to opt in to the management MPDU TXQ */ + if (!ieee80211_hw_check(&sdata->local->hw, + STA_MMPDU_TXQ)) + return; + } else if (!ieee80211_hw_check(&sdata->local->hw, + BUFF_MMPDU_TXQ)) { + /* Drivers need to opt in to the bufferable MMPDU TXQ */ + return; + } + txqi->txq.ac = IEEE80211_AC_VO; + } else { + txqi->txq.ac = ieee80211_ac_from_tid(tid); + } + + txqi->txq.sta = &sta->sta; + txqi->txq.tid = tid; + sta->sta.txq[tid] = &txqi->txq; } void ieee80211_txq_purge(struct ieee80211_local *local, @@ -2951,6 +2976,10 @@ void ieee80211_check_fast_xmit(struct sta_info *sta) if (!(build.key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE)) goto out; + /* Key is being removed */ + if (build.key->flags & KEY_FLAG_TAINTED) + goto out; + switch (build.key->conf.cipher) { case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: @@ -3078,27 +3107,18 @@ void ieee80211_clear_fast_xmit(struct sta_info *sta) } static bool ieee80211_amsdu_realloc_pad(struct ieee80211_local *local, - struct sk_buff *skb, int headroom, - int *subframe_len) + struct sk_buff *skb, int headroom) { - int amsdu_len = *subframe_len + sizeof(struct ethhdr); - int padding = (4 - amsdu_len) & 3; - - if (skb_headroom(skb) < headroom || skb_tailroom(skb) < padding) { + if (skb_headroom(skb) < headroom) { I802_DEBUG_INC(local->tx_expand_skb_head); - if (pskb_expand_head(skb, headroom, padding, GFP_ATOMIC)) { + if (pskb_expand_head(skb, headroom, 0, GFP_ATOMIC)) { wiphy_debug(local->hw.wiphy, "failed to reallocate TX buffer\n"); return false; } } - if (padding) { - *subframe_len += padding; - skb_put_zero(skb, padding); - } - return true; } @@ -3122,8 +3142,7 @@ static bool ieee80211_amsdu_prepare_head(struct ieee80211_sub_if_data *sdata, if (info->control.flags & IEEE80211_TX_CTRL_AMSDU) return true; - if (!ieee80211_amsdu_realloc_pad(local, skb, sizeof(*amsdu_hdr), - &subframe_len)) + if (!ieee80211_amsdu_realloc_pad(local, skb, sizeof(*amsdu_hdr))) return false; data = skb_push(skb, sizeof(*amsdu_hdr)); @@ -3189,7 +3208,8 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata, void *data; bool ret = false; unsigned int orig_len; - int n = 1, nfrags; + int n = 2, nfrags, pad = 0; + u16 hdrlen; if (!ieee80211_hw_check(&local->hw, TX_AMSDU)) return false; @@ -3205,6 +3225,10 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata, max_amsdu_len = min_t(int, max_amsdu_len, sta->sta.max_rc_amsdu_len); + if (sta->sta.max_tid_amsdu_len[tid]) + max_amsdu_len = min_t(int, max_amsdu_len, + sta->sta.max_tid_amsdu_len[tid]); + spin_lock_bh(&fq->lock); /* TODO: Ideally aggregation should be done on dequeue to remain @@ -3222,9 +3246,6 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata, if (skb->len + head->len > max_amsdu_len) goto out; - if (!ieee80211_amsdu_prepare_head(sdata, fast_tx, head)) - goto out; - nfrags = 1 + skb_shinfo(skb)->nr_frags; nfrags += 1 + skb_shinfo(head)->nr_frags; frag_tail = &skb_shinfo(head)->frag_list; @@ -3240,10 +3261,27 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata, if (max_frags && nfrags > max_frags) goto out; - if (!ieee80211_amsdu_realloc_pad(local, skb, sizeof(rfc1042_header) + 2, - &subframe_len)) + if (!drv_can_aggregate_in_amsdu(local, head, skb)) goto out; + if (!ieee80211_amsdu_prepare_head(sdata, fast_tx, head)) + goto out; + + /* + * Pad out the previous subframe to a multiple of 4 by adding the + * padding to the next one, that's being added. Note that head->len + * is the length of the full A-MSDU, but that works since each time + * we add a new subframe we pad out the previous one to a multiple + * of 4 and thus it no longer matters in the next round. + */ + hdrlen = fast_tx->hdr_len - sizeof(rfc1042_header); + if ((head->len - hdrlen) & 3) + pad = 4 - ((head->len - hdrlen) & 3); + + if (!ieee80211_amsdu_realloc_pad(local, skb, sizeof(rfc1042_header) + + 2 + pad)) + goto out_recalc; + ret = true; data = skb_push(skb, ETH_ALEN + 2); memmove(data, data + ETH_ALEN + 2, 2 * ETH_ALEN); @@ -3253,15 +3291,19 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata, memcpy(data, &len, 2); memcpy(data + 2, rfc1042_header, sizeof(rfc1042_header)); + memset(skb_push(skb, pad), 0, pad); + head->len += skb->len; head->data_len += skb->len; *frag_tail = skb; - flow->backlog += head->len - orig_len; - tin->backlog_bytes += head->len - orig_len; - - fq_recalc_backlog(fq, tin, flow); +out_recalc: + if (head->len != orig_len) { + flow->backlog += head->len - orig_len; + tin->backlog_bytes += head->len - orig_len; + fq_recalc_backlog(fq, tin, flow); + } out: spin_unlock_bh(&fq->lock); @@ -3466,13 +3508,19 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw, struct ieee80211_tx_info *info; struct ieee80211_tx_data tx; ieee80211_tx_result r; - struct ieee80211_vif *vif; + struct ieee80211_vif *vif = txq->vif; spin_lock_bh(&fq->lock); - if (test_bit(IEEE80211_TXQ_STOP, &txqi->flags)) + if (test_bit(IEEE80211_TXQ_STOP, &txqi->flags) || + test_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txqi->flags)) goto out; + if (vif->txqs_stopped[ieee80211_ac_from_tid(txq->tid)]) { + set_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txqi->flags); + goto out; + } + /* Make sure fragments stay together. */ skb = __skb_dequeue(&txqi->frags); if (skb) @@ -3567,6 +3615,7 @@ begin: } IEEE80211_SKB_CB(skb)->control.vif = vif; + out: spin_unlock_bh(&fq->lock); @@ -3595,13 +3644,7 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb, if (!IS_ERR_OR_NULL(sta)) { struct ieee80211_fast_tx *fast_tx; - /* We need a bit of data queued to build aggregates properly, so - * instruct the TCP stack to allow more than a single ms of data - * to be queued in the stack. The value is a bit-shift of 1 - * second, so 8 is ~4ms of queued data. Only affects local TCP - * sockets. - */ - sk_pacing_shift_update(skb->sk, 8); + sk_pacing_shift_update(skb->sk, sdata->local->hw.tx_sk_pacing_shift); fast_tx = rcu_dereference(sta->fast_tx); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 88efda7c9f8a..36a3c2ada515 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -240,6 +240,99 @@ __le16 ieee80211_ctstoself_duration(struct ieee80211_hw *hw, } EXPORT_SYMBOL(ieee80211_ctstoself_duration); +static void __ieee80211_wake_txqs(struct ieee80211_sub_if_data *sdata, int ac) +{ + struct ieee80211_local *local = sdata->local; + struct ieee80211_vif *vif = &sdata->vif; + struct fq *fq = &local->fq; + struct ps_data *ps = NULL; + struct txq_info *txqi; + struct sta_info *sta; + int i; + + spin_lock_bh(&fq->lock); + + if (sdata->vif.type == NL80211_IFTYPE_AP) + ps = &sdata->bss->ps; + + sdata->vif.txqs_stopped[ac] = false; + + list_for_each_entry_rcu(sta, &local->sta_list, list) { + if (sdata != sta->sdata) + continue; + + for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) { + struct ieee80211_txq *txq = sta->sta.txq[i]; + + txqi = to_txq_info(txq); + + if (ac != txq->ac) + continue; + + if (!test_and_clear_bit(IEEE80211_TXQ_STOP_NETIF_TX, + &txqi->flags)) + continue; + + spin_unlock_bh(&fq->lock); + drv_wake_tx_queue(local, txqi); + spin_lock_bh(&fq->lock); + } + } + + if (!vif->txq) + goto out; + + txqi = to_txq_info(vif->txq); + + if (!test_and_clear_bit(IEEE80211_TXQ_STOP_NETIF_TX, &txqi->flags) || + (ps && atomic_read(&ps->num_sta_ps)) || ac != vif->txq->ac) + goto out; + + spin_unlock_bh(&fq->lock); + + drv_wake_tx_queue(local, txqi); + return; +out: + spin_unlock_bh(&fq->lock); +} + +void ieee80211_wake_txqs(unsigned long data) +{ + struct ieee80211_local *local = (struct ieee80211_local *)data; + struct ieee80211_sub_if_data *sdata; + int n_acs = IEEE80211_NUM_ACS; + unsigned long flags; + int i; + + rcu_read_lock(); + spin_lock_irqsave(&local->queue_stop_reason_lock, flags); + + if (local->hw.queues < IEEE80211_NUM_ACS) + n_acs = 1; + + for (i = 0; i < local->hw.queues; i++) { + if (local->queue_stop_reasons[i]) + continue; + + spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); + list_for_each_entry_rcu(sdata, &local->interfaces, list) { + int ac; + + for (ac = 0; ac < n_acs; ac++) { + int ac_queue = sdata->vif.hw_queue[ac]; + + if (ac_queue == i || + sdata->vif.cab_queue == i) + __ieee80211_wake_txqs(sdata, ac); + } + } + spin_lock_irqsave(&local->queue_stop_reason_lock, flags); + } + + spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); + rcu_read_unlock(); +} + void ieee80211_propagate_queue_wake(struct ieee80211_local *local, int queue) { struct ieee80211_sub_if_data *sdata; @@ -308,6 +401,9 @@ static void __ieee80211_wake_queue(struct ieee80211_hw *hw, int queue, rcu_read_unlock(); } else tasklet_schedule(&local->tx_pending_tasklet); + + if (local->ops->wake_tx_queue) + tasklet_schedule(&local->wake_txqs_tasklet); } void ieee80211_wake_queue_by_reason(struct ieee80211_hw *hw, int queue, @@ -351,9 +447,6 @@ static void __ieee80211_stop_queue(struct ieee80211_hw *hw, int queue, if (__test_and_set_bit(reason, &local->queue_stop_reasons[queue])) return; - if (local->ops->wake_tx_queue) - return; - if (local->hw.queues < IEEE80211_NUM_ACS) n_acs = 1; @@ -366,8 +459,15 @@ static void __ieee80211_stop_queue(struct ieee80211_hw *hw, int queue, for (ac = 0; ac < n_acs; ac++) { if (sdata->vif.hw_queue[ac] == queue || - sdata->vif.cab_queue == queue) - netif_stop_subqueue(sdata->dev, ac); + sdata->vif.cab_queue == queue) { + if (!local->ops->wake_tx_queue) { + netif_stop_subqueue(sdata->dev, ac); + continue; + } + spin_lock(&local->fq.lock); + sdata->vif.txqs_stopped[ac] = true; + spin_unlock(&local->fq.lock); + } } } rcu_read_unlock(); @@ -1135,7 +1235,7 @@ void ieee80211_regulatory_limit_wmm_params(struct ieee80211_sub_if_data *sdata, { struct ieee80211_chanctx_conf *chanctx_conf; const struct ieee80211_reg_rule *rrule; - struct ieee80211_wmm_ac *wmm_ac; + const struct ieee80211_wmm_ac *wmm_ac; u16 center_freq = 0; if (sdata->vif.type != NL80211_IFTYPE_AP && @@ -1154,20 +1254,19 @@ void ieee80211_regulatory_limit_wmm_params(struct ieee80211_sub_if_data *sdata, rrule = freq_reg_info(sdata->wdev.wiphy, MHZ_TO_KHZ(center_freq)); - if (IS_ERR_OR_NULL(rrule) || !rrule->wmm_rule) { + if (IS_ERR_OR_NULL(rrule) || !rrule->has_wmm) { rcu_read_unlock(); return; } if (sdata->vif.type == NL80211_IFTYPE_AP) - wmm_ac = &rrule->wmm_rule->ap[ac]; + wmm_ac = &rrule->wmm_rule.ap[ac]; else - wmm_ac = &rrule->wmm_rule->client[ac]; + wmm_ac = &rrule->wmm_rule.client[ac]; qparam->cw_min = max_t(u16, qparam->cw_min, wmm_ac->cw_min); qparam->cw_max = max_t(u16, qparam->cw_max, wmm_ac->cw_max); qparam->aifs = max_t(u8, qparam->aifs, wmm_ac->aifsn); - qparam->txop = !qparam->txop ? wmm_ac->cot / 32 : - min_t(u16, qparam->txop, wmm_ac->cot / 32); + qparam->txop = min_t(u16, qparam->txop, wmm_ac->cot / 32); rcu_read_unlock(); } @@ -2658,49 +2757,65 @@ bool ieee80211_chandef_ht_oper(const struct ieee80211_ht_operation *ht_oper, return true; } -bool ieee80211_chandef_vht_oper(const struct ieee80211_vht_operation *oper, +bool ieee80211_chandef_vht_oper(struct ieee80211_hw *hw, + const struct ieee80211_vht_operation *oper, + const struct ieee80211_ht_operation *htop, struct cfg80211_chan_def *chandef) { struct cfg80211_chan_def new = *chandef; - int cf1, cf2; + int cf0, cf1; + int ccfs0, ccfs1, ccfs2; + int ccf0, ccf1; - if (!oper) + if (!oper || !htop) return false; - cf1 = ieee80211_channel_to_frequency(oper->center_freq_seg0_idx, - chandef->chan->band); - cf2 = ieee80211_channel_to_frequency(oper->center_freq_seg1_idx, - chandef->chan->band); + ccfs0 = oper->center_freq_seg0_idx; + ccfs1 = oper->center_freq_seg1_idx; + ccfs2 = (le16_to_cpu(htop->operation_mode) & + IEEE80211_HT_OP_MODE_CCFS2_MASK) + >> IEEE80211_HT_OP_MODE_CCFS2_SHIFT; + + /* when parsing (and we know how to) CCFS1 and CCFS2 are equivalent */ + ccf0 = ccfs0; + ccf1 = ccfs1; + if (!ccfs1 && ieee80211_hw_check(hw, SUPPORTS_VHT_EXT_NSS_BW)) + ccf1 = ccfs2; + + cf0 = ieee80211_channel_to_frequency(ccf0, chandef->chan->band); + cf1 = ieee80211_channel_to_frequency(ccf1, chandef->chan->band); switch (oper->chan_width) { case IEEE80211_VHT_CHANWIDTH_USE_HT: + /* just use HT information directly */ break; case IEEE80211_VHT_CHANWIDTH_80MHZ: new.width = NL80211_CHAN_WIDTH_80; - new.center_freq1 = cf1; + new.center_freq1 = cf0; /* If needed, adjust based on the newer interop workaround. */ - if (oper->center_freq_seg1_idx) { + if (ccf1) { unsigned int diff; - diff = abs(oper->center_freq_seg1_idx - - oper->center_freq_seg0_idx); + diff = abs(ccf1 - ccf0); if (diff == 8) { new.width = NL80211_CHAN_WIDTH_160; - new.center_freq1 = cf2; + new.center_freq1 = cf1; } else if (diff > 8) { new.width = NL80211_CHAN_WIDTH_80P80; - new.center_freq2 = cf2; + new.center_freq2 = cf1; } } break; case IEEE80211_VHT_CHANWIDTH_160MHZ: + /* deprecated encoding */ new.width = NL80211_CHAN_WIDTH_160; - new.center_freq1 = cf1; + new.center_freq1 = cf0; break; case IEEE80211_VHT_CHANWIDTH_80P80MHZ: + /* deprecated encoding */ new.width = NL80211_CHAN_WIDTH_80P80; - new.center_freq1 = cf1; - new.center_freq2 = cf2; + new.center_freq1 = cf0; + new.center_freq2 = cf1; break; default: return false; diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c index 259325cbcc31..006d82e4a397 100644 --- a/net/mac80211/vht.c +++ b/net/mac80211/vht.c @@ -3,6 +3,7 @@ * * Portions of this file * Copyright(c) 2015 - 2016 Intel Deutschland GmbH + * Copyright (C) 2018 Intel Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -231,6 +232,13 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, memcpy(&vht_cap->vht_mcs, &vht_cap_ie->supp_mcs, sizeof(struct ieee80211_vht_mcs_info)); + /* copy EXT_NSS_BW Support value or remove the capability */ + if (ieee80211_hw_check(&sdata->local->hw, SUPPORTS_VHT_EXT_NSS_BW)) + vht_cap->cap |= (cap_info & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK); + else + vht_cap->vht_mcs.tx_highest &= + ~cpu_to_le16(IEEE80211_VHT_EXT_NSS_BW_CAPABLE); + /* but also restrict MCSes */ for (i = 0; i < 8; i++) { u16 own_rx, own_tx, peer_rx, peer_tx; @@ -294,6 +302,18 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata, break; default: sta->cur_max_bandwidth = IEEE80211_STA_RX_BW_80; + + if (!(vht_cap->vht_mcs.tx_highest & + cpu_to_le16(IEEE80211_VHT_EXT_NSS_BW_CAPABLE))) + break; + + /* + * If this is non-zero, then it does support 160 MHz after all, + * in one form or the other. We don't distinguish here (or even + * above) between 160 and 80+80 yet. + */ + if (cap_info & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK) + sta->cur_max_bandwidth = IEEE80211_STA_RX_BW_160; } sta->sta.bandwidth = ieee80211_sta_cur_vht_bw(sta); diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c index 82e6edf9c5d9..32cb7751d216 100644 --- a/net/ncsi/ncsi-netlink.c +++ b/net/ncsi/ncsi-netlink.c @@ -12,7 +12,6 @@ #include <linux/if_arp.h> #include <linux/rtnetlink.h> #include <linux/etherdevice.h> -#include <linux/module.h> #include <net/genetlink.h> #include <net/ncsi.h> #include <linux/skbuff.h> @@ -100,7 +99,7 @@ static int ncsi_write_package_info(struct sk_buff *skb, bool found; int rc; - if (id > ndp->package_num) { + if (id > ndp->package_num - 1) { netdev_info(ndp->ndev.dev, "NCSI: No package with id %u\n", id); return -ENODEV; } @@ -240,7 +239,7 @@ static int ncsi_pkg_info_all_nl(struct sk_buff *skb, return 0; /* done */ hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - &ncsi_genl_family, 0, NCSI_CMD_PKG_INFO); + &ncsi_genl_family, NLM_F_MULTI, NCSI_CMD_PKG_INFO); if (!hdr) { rc = -EMSGSIZE; goto err; diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 71709c104081..f61c306de1d0 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -771,13 +771,13 @@ config NETFILTER_XT_TARGET_CHECKSUM depends on NETFILTER_ADVANCED ---help--- This option adds a `CHECKSUM' target, which can be used in the iptables mangle - table. + table to work around buggy DHCP clients in virtualized environments. - You can use this target to compute and fill in the checksum in - a packet that lacks a checksum. This is particularly useful, - if you need to work around old applications such as dhcp clients, - that do not work well with checksum offloads, but don't want to disable - checksum offload in your device. + Some old DHCP clients drop packets because they are not aware + that the checksum would normally be offloaded to hardware and + thus should be considered valid. + This target can be used to fill in the checksum using iptables + when such packets are sent via a virtual network device. To compile it as a module, choose M here. If unsure, say N. diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 9f14b0df6960..51c5d7eec0a3 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -776,9 +776,26 @@ static const struct nf_hook_ops ipv6_conntrack_ops[] = { }; #endif +static int nf_ct_tcp_fixup(struct nf_conn *ct, void *_nfproto) +{ + u8 nfproto = (unsigned long)_nfproto; + + if (nf_ct_l3num(ct) != nfproto) + return 0; + + if (nf_ct_protonum(ct) == IPPROTO_TCP && + ct->proto.tcp.state == TCP_CONNTRACK_ESTABLISHED) { + ct->proto.tcp.seen[0].td_maxwin = 0; + ct->proto.tcp.seen[1].td_maxwin = 0; + } + + return 0; +} + static int nf_ct_netns_do_get(struct net *net, u8 nfproto) { struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id); + bool fixup_needed = false; int err = 0; mutex_lock(&nf_ct_proto_mutex); @@ -798,6 +815,8 @@ static int nf_ct_netns_do_get(struct net *net, u8 nfproto) ARRAY_SIZE(ipv4_conntrack_ops)); if (err) cnet->users4 = 0; + else + fixup_needed = true; break; #if IS_ENABLED(CONFIG_IPV6) case NFPROTO_IPV6: @@ -814,6 +833,8 @@ static int nf_ct_netns_do_get(struct net *net, u8 nfproto) ARRAY_SIZE(ipv6_conntrack_ops)); if (err) cnet->users6 = 0; + else + fixup_needed = true; break; #endif default: @@ -822,6 +843,11 @@ static int nf_ct_netns_do_get(struct net *net, u8 nfproto) } out_unlock: mutex_unlock(&nf_ct_proto_mutex); + + if (fixup_needed) + nf_ct_iterate_cleanup_net(net, nf_ct_tcp_fixup, + (void *)(unsigned long)nfproto, 0, 0); + return err; } diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 8c58f96b59e7..f3f91ed2c21a 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -675,7 +675,7 @@ static int nlattr_to_dccp(struct nlattr *cda[], struct nf_conn *ct) } #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> @@ -697,6 +697,8 @@ static int dccp_timeout_nlattr_to_obj(struct nlattr *tb[], timeouts[i] = ntohl(nla_get_be32(tb[i])) * HZ; } } + + timeouts[CTA_TIMEOUT_DCCP_UNSPEC] = timeouts[CTA_TIMEOUT_DCCP_REQUEST]; return 0; } @@ -726,7 +728,7 @@ dccp_timeout_nla_policy[CTA_TIMEOUT_DCCP_MAX+1] = { [CTA_TIMEOUT_DCCP_CLOSING] = { .type = NLA_U32 }, [CTA_TIMEOUT_DCCP_TIMEWAIT] = { .type = NLA_U32 }, }; -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ #ifdef CONFIG_SYSCTL /* template, data assigned later */ @@ -827,6 +829,11 @@ static int dccp_init_net(struct net *net, u_int16_t proto) dn->dccp_timeout[CT_DCCP_CLOSEREQ] = 64 * HZ; dn->dccp_timeout[CT_DCCP_CLOSING] = 64 * HZ; dn->dccp_timeout[CT_DCCP_TIMEWAIT] = 2 * DCCP_MSL; + + /* timeouts[0] is unused, make it same as SYN_SENT so + * ->timeouts[0] contains 'new' timeout, like udp or icmp. + */ + dn->dccp_timeout[CT_DCCP_NONE] = dn->dccp_timeout[CT_DCCP_REQUEST]; } return dccp_kmemdup_sysctl_table(net, pn, dn); @@ -856,7 +863,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp4 = { .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = dccp_timeout_nlattr_to_obj, .obj_to_nlattr = dccp_timeout_obj_to_nlattr, @@ -864,7 +871,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp4 = { .obj_size = sizeof(unsigned int) * CT_DCCP_MAX, .nla_policy = dccp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = dccp_init_net, .get_net_proto = dccp_get_net_proto, }; @@ -889,7 +896,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp6 = { .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = dccp_timeout_nlattr_to_obj, .obj_to_nlattr = dccp_timeout_obj_to_nlattr, @@ -897,7 +904,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp6 = { .obj_size = sizeof(unsigned int) * CT_DCCP_MAX, .nla_policy = dccp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = dccp_init_net, .get_net_proto = dccp_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c index ac4a0b296dcd..1df3244ecd07 100644 --- a/net/netfilter/nf_conntrack_proto_generic.c +++ b/net/netfilter/nf_conntrack_proto_generic.c @@ -70,7 +70,7 @@ static bool generic_new(struct nf_conn *ct, const struct sk_buff *skb, return ret; } -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> @@ -113,7 +113,7 @@ static const struct nla_policy generic_timeout_nla_policy[CTA_TIMEOUT_GENERIC_MAX+1] = { [CTA_TIMEOUT_GENERIC_TIMEOUT] = { .type = NLA_U32 }, }; -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ #ifdef CONFIG_SYSCTL static struct ctl_table generic_sysctl_table[] = { @@ -164,7 +164,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_generic = .pkt_to_tuple = generic_pkt_to_tuple, .packet = generic_packet, .new = generic_new, -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = generic_timeout_nlattr_to_obj, .obj_to_nlattr = generic_timeout_obj_to_nlattr, @@ -172,7 +172,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_generic = .obj_size = sizeof(unsigned int), .nla_policy = generic_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = generic_init_net, .get_net_proto = generic_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index d1632252bf5b..650eb4fba2c5 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -285,7 +285,7 @@ static void gre_destroy(struct nf_conn *ct) nf_ct_gre_keymap_destroy(master); } -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> @@ -334,7 +334,7 @@ gre_timeout_nla_policy[CTA_TIMEOUT_GRE_MAX+1] = { [CTA_TIMEOUT_GRE_UNREPLIED] = { .type = NLA_U32 }, [CTA_TIMEOUT_GRE_REPLIED] = { .type = NLA_U32 }, }; -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ static int gre_init_net(struct net *net, u_int16_t proto) { @@ -367,7 +367,7 @@ static const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 = { .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = gre_timeout_nlattr_to_obj, .obj_to_nlattr = gre_timeout_obj_to_nlattr, @@ -375,7 +375,7 @@ static const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 = { .obj_size = sizeof(unsigned int) * GRE_CT_MAX, .nla_policy = gre_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .net_id = &proto_gre_net_id, .init_net = gre_init_net, }; diff --git a/net/netfilter/nf_conntrack_proto_icmp.c b/net/netfilter/nf_conntrack_proto_icmp.c index 036670b38282..43c7e1a217b9 100644 --- a/net/netfilter/nf_conntrack_proto_icmp.c +++ b/net/netfilter/nf_conntrack_proto_icmp.c @@ -273,7 +273,7 @@ static unsigned int icmp_nlattr_tuple_size(void) } #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> @@ -313,7 +313,7 @@ static const struct nla_policy icmp_timeout_nla_policy[CTA_TIMEOUT_ICMP_MAX+1] = { [CTA_TIMEOUT_ICMP_TIMEOUT] = { .type = NLA_U32 }, }; -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ #ifdef CONFIG_SYSCTL static struct ctl_table icmp_sysctl_table[] = { @@ -374,7 +374,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp = .nlattr_to_tuple = icmp_nlattr_to_tuple, .nla_policy = icmp_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = icmp_timeout_nlattr_to_obj, .obj_to_nlattr = icmp_timeout_obj_to_nlattr, @@ -382,7 +382,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp = .obj_size = sizeof(unsigned int), .nla_policy = icmp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = icmp_init_net, .get_net_proto = icmp_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_icmpv6.c b/net/netfilter/nf_conntrack_proto_icmpv6.c index bed07b998a10..97e40f77d678 100644 --- a/net/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/netfilter/nf_conntrack_proto_icmpv6.c @@ -274,7 +274,7 @@ static unsigned int icmpv6_nlattr_tuple_size(void) } #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> @@ -314,7 +314,7 @@ static const struct nla_policy icmpv6_timeout_nla_policy[CTA_TIMEOUT_ICMPV6_MAX+1] = { [CTA_TIMEOUT_ICMPV6_TIMEOUT] = { .type = NLA_U32 }, }; -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ #ifdef CONFIG_SYSCTL static struct ctl_table icmpv6_sysctl_table[] = { @@ -373,7 +373,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 = .nlattr_to_tuple = icmpv6_nlattr_to_tuple, .nla_policy = icmpv6_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = icmpv6_timeout_nlattr_to_obj, .obj_to_nlattr = icmpv6_timeout_obj_to_nlattr, @@ -381,7 +381,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 = .obj_size = sizeof(unsigned int), .nla_policy = icmpv6_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = icmpv6_init_net, .get_net_proto = icmpv6_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 8d1e085fc14a..e4d738d34cd0 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -591,7 +591,7 @@ static int nlattr_to_sctp(struct nlattr *cda[], struct nf_conn *ct) } #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> @@ -613,6 +613,8 @@ static int sctp_timeout_nlattr_to_obj(struct nlattr *tb[], timeouts[i] = ntohl(nla_get_be32(tb[i])) * HZ; } } + + timeouts[CTA_TIMEOUT_SCTP_UNSPEC] = timeouts[CTA_TIMEOUT_SCTP_CLOSED]; return 0; } @@ -644,7 +646,7 @@ sctp_timeout_nla_policy[CTA_TIMEOUT_SCTP_MAX+1] = { [CTA_TIMEOUT_SCTP_HEARTBEAT_SENT] = { .type = NLA_U32 }, [CTA_TIMEOUT_SCTP_HEARTBEAT_ACKED] = { .type = NLA_U32 }, }; -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ #ifdef CONFIG_SYSCTL @@ -743,6 +745,11 @@ static int sctp_init_net(struct net *net, u_int16_t proto) for (i = 0; i < SCTP_CONNTRACK_MAX; i++) sn->timeouts[i] = sctp_timeouts[i]; + + /* timeouts[0] is unused, init it so ->timeouts[0] contains + * 'new' timeout, like udp or icmp. + */ + sn->timeouts[0] = sctp_timeouts[SCTP_CONNTRACK_CLOSED]; } return sctp_kmemdup_sysctl_table(pn, sn); @@ -773,7 +780,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 = { .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = sctp_timeout_nlattr_to_obj, .obj_to_nlattr = sctp_timeout_obj_to_nlattr, @@ -781,7 +788,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 = { .obj_size = sizeof(unsigned int) * SCTP_CONNTRACK_MAX, .nla_policy = sctp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = sctp_init_net, .get_net_proto = sctp_get_net_proto, }; @@ -806,7 +813,8 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6 = { .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, .nla_policy = nf_ct_port_nla_policy, -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#endif +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = sctp_timeout_nlattr_to_obj, .obj_to_nlattr = sctp_timeout_obj_to_nlattr, @@ -814,8 +822,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6 = { .obj_size = sizeof(unsigned int) * SCTP_CONNTRACK_MAX, .nla_policy = sctp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ -#endif +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = sctp_init_net, .get_net_proto = sctp_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index d80d322b9d8b..b4bdf9eda7b7 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1279,7 +1279,7 @@ static unsigned int tcp_nlattr_tuple_size(void) } #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> @@ -1301,6 +1301,7 @@ static int tcp_timeout_nlattr_to_obj(struct nlattr *tb[], timeouts[TCP_CONNTRACK_SYN_SENT] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_SYN_SENT]))*HZ; } + if (tb[CTA_TIMEOUT_TCP_SYN_RECV]) { timeouts[TCP_CONNTRACK_SYN_RECV] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_SYN_RECV]))*HZ; @@ -1341,6 +1342,8 @@ static int tcp_timeout_nlattr_to_obj(struct nlattr *tb[], timeouts[TCP_CONNTRACK_UNACK] = ntohl(nla_get_be32(tb[CTA_TIMEOUT_TCP_UNACK]))*HZ; } + + timeouts[CTA_TIMEOUT_TCP_UNSPEC] = timeouts[CTA_TIMEOUT_TCP_SYN_SENT]; return 0; } @@ -1391,7 +1394,7 @@ static const struct nla_policy tcp_timeout_nla_policy[CTA_TIMEOUT_TCP_MAX+1] = { [CTA_TIMEOUT_TCP_RETRANS] = { .type = NLA_U32 }, [CTA_TIMEOUT_TCP_UNACK] = { .type = NLA_U32 }, }; -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ #ifdef CONFIG_SYSCTL static struct ctl_table tcp_sysctl_table[] = { @@ -1518,6 +1521,10 @@ static int tcp_init_net(struct net *net, u_int16_t proto) for (i = 0; i < TCP_CONNTRACK_TIMEOUT_MAX; i++) tn->timeouts[i] = tcp_timeouts[i]; + /* timeouts[0] is unused, make it same as SYN_SENT so + * ->timeouts[0] contains 'new' timeout, like udp or icmp. + */ + tn->timeouts[0] = tcp_timeouts[TCP_CONNTRACK_SYN_SENT]; tn->tcp_loose = nf_ct_tcp_loose; tn->tcp_be_liberal = nf_ct_tcp_be_liberal; tn->tcp_max_retrans = nf_ct_tcp_max_retrans; @@ -1551,7 +1558,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 = .nlattr_size = TCP_NLATTR_SIZE, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = tcp_timeout_nlattr_to_obj, .obj_to_nlattr = tcp_timeout_obj_to_nlattr, @@ -1560,7 +1567,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 = TCP_CONNTRACK_TIMEOUT_MAX, .nla_policy = tcp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = tcp_init_net, .get_net_proto = tcp_get_net_proto, }; @@ -1586,7 +1593,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6 = .nlattr_tuple_size = tcp_nlattr_tuple_size, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = tcp_timeout_nlattr_to_obj, .obj_to_nlattr = tcp_timeout_obj_to_nlattr, @@ -1595,7 +1602,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6 = TCP_CONNTRACK_TIMEOUT_MAX, .nla_policy = tcp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = tcp_init_net, .get_net_proto = tcp_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 7a1b8988a931..3065fb8ef91b 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -171,7 +171,7 @@ static int udp_error(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, return NF_ACCEPT; } -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_cttimeout.h> @@ -221,7 +221,7 @@ udp_timeout_nla_policy[CTA_TIMEOUT_UDP_MAX+1] = { [CTA_TIMEOUT_UDP_UNREPLIED] = { .type = NLA_U32 }, [CTA_TIMEOUT_UDP_REPLIED] = { .type = NLA_U32 }, }; -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ #ifdef CONFIG_SYSCTL static struct ctl_table udp_sysctl_table[] = { @@ -292,7 +292,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4 = .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = udp_timeout_nlattr_to_obj, .obj_to_nlattr = udp_timeout_obj_to_nlattr, @@ -300,7 +300,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4 = .obj_size = sizeof(unsigned int) * CTA_TIMEOUT_UDP_MAX, .nla_policy = udp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = udp_init_net, .get_net_proto = udp_get_net_proto, }; @@ -321,7 +321,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4 = .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = udp_timeout_nlattr_to_obj, .obj_to_nlattr = udp_timeout_obj_to_nlattr, @@ -329,7 +329,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4 = .obj_size = sizeof(unsigned int) * CTA_TIMEOUT_UDP_MAX, .nla_policy = udp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = udp_init_net, .get_net_proto = udp_get_net_proto, }; @@ -350,7 +350,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6 = .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = udp_timeout_nlattr_to_obj, .obj_to_nlattr = udp_timeout_obj_to_nlattr, @@ -358,7 +358,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6 = .obj_size = sizeof(unsigned int) * CTA_TIMEOUT_UDP_MAX, .nla_policy = udp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = udp_init_net, .get_net_proto = udp_get_net_proto, }; @@ -379,7 +379,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 = .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, .nla_policy = nf_ct_port_nla_policy, #endif -#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT) +#ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = udp_timeout_nlattr_to_obj, .obj_to_nlattr = udp_timeout_obj_to_nlattr, @@ -387,10 +387,9 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 = .obj_size = sizeof(unsigned int) * CTA_TIMEOUT_UDP_MAX, .nla_policy = udp_timeout_nla_policy, }, -#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */ +#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ .init_net = udp_init_net, .get_net_proto = udp_get_net_proto, }; EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_udplite6); #endif -#include <net/netfilter/nf_conntrack_timeout.h> diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 1dca5683f59f..2cfb173cd0b2 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4637,6 +4637,7 @@ static int nft_flush_set(const struct nft_ctx *ctx, } set->ndeact++; + nft_set_elem_deactivate(ctx->net, set, elem); nft_trans_elem_set(trans) = set; nft_trans_elem(trans) = *elem; list_add_tail(&trans->list, &ctx->net->nft.commit_list); diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index d46a236cdf31..a30f8ba4b89a 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -489,8 +489,8 @@ err: return err; } -static struct ctnl_timeout * -ctnl_timeout_find_get(struct net *net, const char *name) +static struct nf_ct_timeout *ctnl_timeout_find_get(struct net *net, + const char *name) { struct ctnl_timeout *timeout, *matching = NULL; @@ -509,7 +509,7 @@ ctnl_timeout_find_get(struct net *net, const char *name) break; } err: - return matching; + return matching ? &matching->timeout : NULL; } static void ctnl_timeout_put(struct nf_ct_timeout *t) diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index ea4ba551abb2..43041f087eb3 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -233,6 +233,7 @@ static void nfqnl_reinject(struct nf_queue_entry *entry, unsigned int verdict) int err; if (verdict == NF_ACCEPT || + verdict == NF_REPEAT || verdict == NF_STOP) { rcu_read_lock(); ct_hook = rcu_dereference(nf_ct_hook); @@ -764,7 +765,7 @@ __nfqnl_enqueue_packet_gso(struct net *net, struct nfqnl_instance *queue, return ret; } - skb->next = NULL; + skb_mark_not_on_list(skb); entry_seg = nf_queue_entry_dup(entry); if (entry_seg) { diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 26a8baebd072..5dd87748afa8 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -799,7 +799,7 @@ err: } struct nft_ct_timeout_obj { - struct nf_conn *tmpl; + struct nf_ct_timeout *timeout; u8 l4proto; }; @@ -809,26 +809,42 @@ static void nft_ct_timeout_obj_eval(struct nft_object *obj, { const struct nft_ct_timeout_obj *priv = nft_obj_data(obj); struct nf_conn *ct = (struct nf_conn *)skb_nfct(pkt->skb); - struct sk_buff *skb = pkt->skb; + struct nf_conn_timeout *timeout; + const unsigned int *values; + + if (priv->l4proto != pkt->tprot) + return; - if (ct || - priv->l4proto != pkt->tprot) + if (!ct || nf_ct_is_template(ct) || nf_ct_is_confirmed(ct)) return; - nf_ct_set(skb, priv->tmpl, IP_CT_NEW); + timeout = nf_ct_timeout_find(ct); + if (!timeout) { + timeout = nf_ct_timeout_ext_add(ct, priv->timeout, GFP_ATOMIC); + if (!timeout) { + regs->verdict.code = NF_DROP; + return; + } + } + + rcu_assign_pointer(timeout->timeout, priv->timeout); + + /* adjust the timeout as per 'new' state. ct is unconfirmed, + * so the current timestamp must not be added. + */ + values = nf_ct_timeout_data(timeout); + if (values) + nf_ct_refresh(ct, pkt->skb, values[0]); } static int nft_ct_timeout_obj_init(const struct nft_ctx *ctx, const struct nlattr * const tb[], struct nft_object *obj) { - const struct nf_conntrack_zone *zone = &nf_ct_zone_dflt; struct nft_ct_timeout_obj *priv = nft_obj_data(obj); const struct nf_conntrack_l4proto *l4proto; - struct nf_conn_timeout *timeout_ext; struct nf_ct_timeout *timeout; int l3num = ctx->family; - struct nf_conn *tmpl; __u8 l4num; int ret; @@ -863,28 +879,14 @@ static int nft_ct_timeout_obj_init(const struct nft_ctx *ctx, timeout->l3num = l3num; timeout->l4proto = l4proto; - tmpl = nf_ct_tmpl_alloc(ctx->net, zone, GFP_ATOMIC); - if (!tmpl) { - ret = -ENOMEM; - goto err_free_timeout; - } - - timeout_ext = nf_ct_timeout_ext_add(tmpl, timeout, GFP_ATOMIC); - if (!timeout_ext) { - ret = -ENOMEM; - goto err_free_tmpl; - } ret = nf_ct_netns_get(ctx->net, ctx->family); if (ret < 0) - goto err_free_tmpl; - - priv->tmpl = tmpl; + goto err_free_timeout; + priv->timeout = timeout; return 0; -err_free_tmpl: - nf_ct_tmpl_free(tmpl); err_free_timeout: kfree(timeout); err_proto_put: @@ -896,22 +898,19 @@ static void nft_ct_timeout_obj_destroy(const struct nft_ctx *ctx, struct nft_object *obj) { struct nft_ct_timeout_obj *priv = nft_obj_data(obj); - struct nf_conn_timeout *t = nf_ct_timeout_find(priv->tmpl); - struct nf_ct_timeout *timeout; + struct nf_ct_timeout *timeout = priv->timeout; - timeout = rcu_dereference_raw(t->timeout); nf_ct_untimeout(ctx->net, timeout); nf_ct_l4proto_put(timeout->l4proto); nf_ct_netns_put(ctx->net, ctx->family); - nf_ct_tmpl_free(priv->tmpl); + kfree(priv->timeout); } static int nft_ct_timeout_obj_dump(struct sk_buff *skb, struct nft_object *obj, bool reset) { const struct nft_ct_timeout_obj *priv = nft_obj_data(obj); - const struct nf_conn_timeout *t = nf_ct_timeout_find(priv->tmpl); - const struct nf_ct_timeout *timeout = rcu_dereference_raw(t->timeout); + const struct nf_ct_timeout *timeout = priv->timeout; struct nlattr *nest_params; int ret; diff --git a/net/netfilter/xt_CHECKSUM.c b/net/netfilter/xt_CHECKSUM.c index 9f4151ec3e06..6c7aa6a0a0d2 100644 --- a/net/netfilter/xt_CHECKSUM.c +++ b/net/netfilter/xt_CHECKSUM.c @@ -16,6 +16,9 @@ #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_CHECKSUM.h> +#include <linux/netfilter_ipv4/ip_tables.h> +#include <linux/netfilter_ipv6/ip6_tables.h> + MODULE_LICENSE("GPL"); MODULE_AUTHOR("Michael S. Tsirkin <mst@redhat.com>"); MODULE_DESCRIPTION("Xtables: checksum modification"); @@ -25,7 +28,7 @@ MODULE_ALIAS("ip6t_CHECKSUM"); static unsigned int checksum_tg(struct sk_buff *skb, const struct xt_action_param *par) { - if (skb->ip_summed == CHECKSUM_PARTIAL) + if (skb->ip_summed == CHECKSUM_PARTIAL && !skb_is_gso(skb)) skb_checksum_help(skb); return XT_CONTINUE; @@ -34,6 +37,8 @@ checksum_tg(struct sk_buff *skb, const struct xt_action_param *par) static int checksum_tg_check(const struct xt_tgchk_param *par) { const struct xt_CHECKSUM_info *einfo = par->targinfo; + const struct ip6t_ip6 *i6 = par->entryinfo; + const struct ipt_ip *i4 = par->entryinfo; if (einfo->operation & ~XT_CHECKSUM_OP_FILL) { pr_info_ratelimited("unsupported CHECKSUM operation %x\n", @@ -43,6 +48,21 @@ static int checksum_tg_check(const struct xt_tgchk_param *par) if (!einfo->operation) return -EINVAL; + switch (par->family) { + case NFPROTO_IPV4: + if (i4->proto == IPPROTO_UDP && + (i4->invflags & XT_INV_PROTO) == 0) + return 0; + break; + case NFPROTO_IPV6: + if ((i6->flags & IP6T_F_PROTO) && + i6->proto == IPPROTO_UDP && + (i6->invflags & XT_INV_PROTO) == 0) + return 0; + break; + } + + pr_warn_once("CHECKSUM should be avoided. If really needed, restrict with \"-p udp\" and only use in OUTPUT\n"); return 0; } diff --git a/net/netfilter/xt_cluster.c b/net/netfilter/xt_cluster.c index dfbdbb2fc0ed..51d0c257e7a5 100644 --- a/net/netfilter/xt_cluster.c +++ b/net/netfilter/xt_cluster.c @@ -125,6 +125,7 @@ xt_cluster_mt(const struct sk_buff *skb, struct xt_action_param *par) static int xt_cluster_mt_checkentry(const struct xt_mtchk_param *par) { struct xt_cluster_match_info *info = par->matchinfo; + int ret; if (info->total_nodes > XT_CLUSTER_NODES_MAX) { pr_info_ratelimited("you have exceeded the maximum number of cluster nodes (%u > %u)\n", @@ -135,7 +136,17 @@ static int xt_cluster_mt_checkentry(const struct xt_mtchk_param *par) pr_info_ratelimited("node mask cannot exceed total number of nodes\n"); return -EDOM; } - return 0; + + ret = nf_ct_netns_get(par->net, par->family); + if (ret < 0) + pr_info_ratelimited("cannot load conntrack support for proto=%u\n", + par->family); + return ret; +} + +static void xt_cluster_mt_destroy(const struct xt_mtdtor_param *par) +{ + nf_ct_netns_put(par->net, par->family); } static struct xt_match xt_cluster_match __read_mostly = { @@ -144,6 +155,7 @@ static struct xt_match xt_cluster_match __read_mostly = { .match = xt_cluster_mt, .checkentry = xt_cluster_mt_checkentry, .matchsize = sizeof(struct xt_cluster_match_info), + .destroy = xt_cluster_mt_destroy, .me = THIS_MODULE, }; diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 9b16402f29af..3e7d259e5d8d 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -1057,7 +1057,7 @@ static struct xt_match hashlimit_mt_reg[] __read_mostly = { static void *dl_seq_start(struct seq_file *s, loff_t *pos) __acquires(htable->lock) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); unsigned int *bucket; spin_lock_bh(&htable->lock); @@ -1074,7 +1074,7 @@ static void *dl_seq_start(struct seq_file *s, loff_t *pos) static void *dl_seq_next(struct seq_file *s, void *v, loff_t *pos) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); unsigned int *bucket = v; *pos = ++(*bucket); @@ -1088,7 +1088,7 @@ static void *dl_seq_next(struct seq_file *s, void *v, loff_t *pos) static void dl_seq_stop(struct seq_file *s, void *v) __releases(htable->lock) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); unsigned int *bucket = v; if (!IS_ERR(bucket)) @@ -1130,7 +1130,7 @@ static void dl_seq_print(struct dsthash_ent *ent, u_int8_t family, static int dl_seq_real_show_v2(struct dsthash_ent *ent, u_int8_t family, struct seq_file *s) { - struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->file)); spin_lock(&ent->lock); /* recalculate to show accurate numbers */ @@ -1145,7 +1145,7 @@ static int dl_seq_real_show_v2(struct dsthash_ent *ent, u_int8_t family, static int dl_seq_real_show_v1(struct dsthash_ent *ent, u_int8_t family, struct seq_file *s) { - struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->file)); spin_lock(&ent->lock); /* recalculate to show accurate numbers */ @@ -1160,7 +1160,7 @@ static int dl_seq_real_show_v1(struct dsthash_ent *ent, u_int8_t family, static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family, struct seq_file *s) { - struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *ht = PDE_DATA(file_inode(s->file)); spin_lock(&ent->lock); /* recalculate to show accurate numbers */ @@ -1174,7 +1174,7 @@ static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family, static int dl_seq_show_v2(struct seq_file *s, void *v) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); unsigned int *bucket = (unsigned int *)v; struct dsthash_ent *ent; @@ -1188,7 +1188,7 @@ static int dl_seq_show_v2(struct seq_file *s, void *v) static int dl_seq_show_v1(struct seq_file *s, void *v) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); unsigned int *bucket = v; struct dsthash_ent *ent; @@ -1202,7 +1202,7 @@ static int dl_seq_show_v1(struct seq_file *s, void *v) static int dl_seq_show(struct seq_file *s, void *v) { - struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->private)); + struct xt_hashlimit_htable *htable = PDE_DATA(file_inode(s->file)); unsigned int *bucket = v; struct dsthash_ent *ent; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 930d17fa906c..e3a0538ec0be 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -574,11 +574,6 @@ static int netlink_insert(struct sock *sk, u32 portid) if (nlk_sk(sk)->bound) goto err; - err = -ENOMEM; - if (BITS_PER_LONG > 32 && - unlikely(atomic_read(&table->hash.nelems) >= UINT_MAX)) - goto err; - nlk_sk(sk)->portid = portid; sock_hold(sk); @@ -993,7 +988,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, struct netlink_sock *nlk = nlk_sk(sk); struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr; int err = 0; - long unsigned int groups = nladdr->nl_groups; + unsigned long groups = nladdr->nl_groups; bool bound; if (addr_len < sizeof(struct sockaddr_nl)) @@ -1011,9 +1006,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, return err; } - if (nlk->ngroups == 0) - groups = 0; - else if (nlk->ngroups < 8*sizeof(groups)) + if (nlk->ngroups < BITS_PER_LONG) groups &= (1UL << nlk->ngroups) - 1; bound = nlk->bound; diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 56b8e7167790..35966da84769 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -254,21 +254,18 @@ static bool icmphdr_ok(struct sk_buff *skb) static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key) { + unsigned short frag_off; + unsigned int payload_ofs = 0; unsigned int nh_ofs = skb_network_offset(skb); unsigned int nh_len; - int payload_ofs; struct ipv6hdr *nh; - uint8_t nexthdr; - __be16 frag_off; - int err; + int err, nexthdr, flags = 0; err = check_header(skb, nh_ofs + sizeof(*nh)); if (unlikely(err)) return err; nh = ipv6_hdr(skb); - nexthdr = nh->nexthdr; - payload_ofs = (u8 *)(nh + 1) - skb->data; key->ip.proto = NEXTHDR_NONE; key->ip.tos = ipv6_get_dsfield(nh); @@ -277,10 +274,9 @@ static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key) key->ipv6.addr.src = nh->saddr; key->ipv6.addr.dst = nh->daddr; - payload_ofs = ipv6_skip_exthdr(skb, payload_ofs, &nexthdr, &frag_off); - - if (frag_off) { - if (frag_off & htons(~0x7)) + nexthdr = ipv6_find_hdr(skb, &payload_ofs, -1, &frag_off, &flags); + if (flags & IP6_FH_F_FRAG) { + if (frag_off) key->ip.frag = OVS_FRAG_TYPE_LATER; else key->ip.frag = OVS_FRAG_TYPE_FIRST; @@ -288,11 +284,11 @@ static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key) key->ip.frag = OVS_FRAG_TYPE_NONE; } - /* Delayed handling of error in ipv6_skip_exthdr() as it - * always sets frag_off to a valid value which may be + /* Delayed handling of error in ipv6_find_hdr() as it + * always sets flags and frag_off to a valid value which may be * used to set key->ip.frag above. */ - if (unlikely(payload_ofs < 0)) + if (unlikely(nexthdr < 0)) return -EPROTO; nh_len = payload_ofs - nh_ofs; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 5610061e7f2e..f85f67b5c1f4 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3805,6 +3805,20 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv return fanout_set_data(po, optval, optlen); } + case PACKET_IGNORE_OUTGOING: + { + int val; + + if (optlen != sizeof(val)) + return -EINVAL; + if (copy_from_user(&val, optval, sizeof(val))) + return -EFAULT; + if (val < 0 || val > 1) + return -EINVAL; + + po->prot_hook.ignore_outgoing = !!val; + return 0; + } case PACKET_TX_HAS_OFF: { unsigned int val; @@ -3928,6 +3942,9 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, ((u32)po->fanout->flags << 24)) : 0); break; + case PACKET_IGNORE_OUTGOING: + val = po->prot_hook.ignore_outgoing; + break; case PACKET_ROLLOVER_STATS: if (!po->rollover) return -EINVAL; @@ -4137,36 +4154,52 @@ static const struct vm_operations_struct packet_mmap_ops = { .close = packet_mm_close, }; -static void free_pg_vec(struct pgv *pg_vec, unsigned int len) +static void free_pg_vec(struct pgv *pg_vec, unsigned int order, + unsigned int len) { int i; for (i = 0; i < len; i++) { if (likely(pg_vec[i].buffer)) { - kvfree(pg_vec[i].buffer); + if (is_vmalloc_addr(pg_vec[i].buffer)) + vfree(pg_vec[i].buffer); + else + free_pages((unsigned long)pg_vec[i].buffer, + order); pg_vec[i].buffer = NULL; } } kfree(pg_vec); } -static char *alloc_one_pg_vec_page(unsigned long size) +static char *alloc_one_pg_vec_page(unsigned long order) { char *buffer; + gfp_t gfp_flags = GFP_KERNEL | __GFP_COMP | + __GFP_ZERO | __GFP_NOWARN | __GFP_NORETRY; - buffer = kvzalloc(size, GFP_KERNEL); + buffer = (char *) __get_free_pages(gfp_flags, order); if (buffer) return buffer; - buffer = kvzalloc(size, GFP_KERNEL | __GFP_RETRY_MAYFAIL); + /* __get_free_pages failed, fall back to vmalloc */ + buffer = vzalloc(array_size((1 << order), PAGE_SIZE)); + if (buffer) + return buffer; - return buffer; + /* vmalloc failed, lets dig into swap here */ + gfp_flags &= ~__GFP_NORETRY; + buffer = (char *) __get_free_pages(gfp_flags, order); + if (buffer) + return buffer; + + /* complete and utter failure */ + return NULL; } -static struct pgv *alloc_pg_vec(struct tpacket_req *req) +static struct pgv *alloc_pg_vec(struct tpacket_req *req, int order) { unsigned int block_nr = req->tp_block_nr; - unsigned long size = req->tp_block_size; struct pgv *pg_vec; int i; @@ -4175,7 +4208,7 @@ static struct pgv *alloc_pg_vec(struct tpacket_req *req) goto out; for (i = 0; i < block_nr; i++) { - pg_vec[i].buffer = alloc_one_pg_vec_page(size); + pg_vec[i].buffer = alloc_one_pg_vec_page(order); if (unlikely(!pg_vec[i].buffer)) goto out_free_pgvec; } @@ -4184,7 +4217,7 @@ out: return pg_vec; out_free_pgvec: - free_pg_vec(pg_vec, block_nr); + free_pg_vec(pg_vec, order, block_nr); pg_vec = NULL; goto out; } @@ -4194,9 +4227,9 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, { struct pgv *pg_vec = NULL; struct packet_sock *po = pkt_sk(sk); + int was_running, order = 0; struct packet_ring_buffer *rb; struct sk_buff_head *rb_queue; - int was_running; __be16 num; int err = -EINVAL; /* Added to avoid minimal code churn */ @@ -4258,7 +4291,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, goto out; err = -ENOMEM; - pg_vec = alloc_pg_vec(req); + order = get_order(req->tp_block_size); + pg_vec = alloc_pg_vec(req, order); if (unlikely(!pg_vec)) goto out; switch (po->tp_version) { @@ -4312,6 +4346,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, rb->frame_size = req->tp_frame_size; spin_unlock_bh(&rb_queue->lock); + swap(rb->pg_vec_order, order); swap(rb->pg_vec_len, req->tp_block_nr); rb->pg_vec_pages = req->tp_block_size/PAGE_SIZE; @@ -4337,7 +4372,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, } if (pg_vec) - free_pg_vec(pg_vec, req->tp_block_nr); + free_pg_vec(pg_vec, order, req->tp_block_nr); out: return err; } diff --git a/net/packet/internal.h b/net/packet/internal.h index 8f50036f62f0..3bb7c5fb3bff 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -64,6 +64,7 @@ struct packet_ring_buffer { unsigned int frame_size; unsigned int frame_max; + unsigned int pg_vec_order; unsigned int pg_vec_pages; unsigned int pg_vec_len; diff --git a/net/rds/Kconfig b/net/rds/Kconfig index 01b3bd6a3708..b9092111bc45 100644 --- a/net/rds/Kconfig +++ b/net/rds/Kconfig @@ -1,6 +1,6 @@ config RDS - tristate "The RDS Protocol" + tristate "The Reliable Datagram Sockets Protocol" depends on INET ---help--- The RDS (Reliable Datagram Sockets) protocol provides reliable, diff --git a/net/rds/bind.c b/net/rds/bind.c index 3ab55784b637..762d2c6788a3 100644 --- a/net/rds/bind.c +++ b/net/rds/bind.c @@ -76,11 +76,13 @@ struct rds_sock *rds_find_bound(const struct in6_addr *addr, __be16 port, struct rds_sock *rs; __rds_create_bind_key(key, addr, port, scope_id); - rs = rhashtable_lookup_fast(&bind_hash_table, key, ht_parms); + rcu_read_lock(); + rs = rhashtable_lookup(&bind_hash_table, key, ht_parms); if (rs && !sock_flag(rds_rs_to_sk(rs), SOCK_DEAD)) rds_sock_addref(rs); else rs = NULL; + rcu_read_unlock(); rdsdebug("returning rs %p for %pI6c:%u\n", rs, addr, ntohs(port)); @@ -235,6 +237,7 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out; } + sock_set_flag(sk, SOCK_RCU_FREE); ret = rds_add_bound(rs, binding_addr, &port, scope_id); if (ret) goto out; diff --git a/net/rds/ib.c b/net/rds/ib.c index c1d97640c0be..eba75c1ba359 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -341,15 +341,10 @@ static int rds6_ib_conn_info_visitor(struct rds_connection *conn, if (rds_conn_state(conn) == RDS_CONN_UP) { struct rds_ib_device *rds_ibdev; - struct rdma_dev_addr *dev_addr; ic = conn->c_transport_data; - dev_addr = &ic->i_cm_id->route.addr.dev_addr; - rdma_addr_get_sgid(dev_addr, - (union ib_gid *)&iinfo6->src_gid); - rdma_addr_get_dgid(dev_addr, - (union ib_gid *)&iinfo6->dst_gid); - + rdma_read_gids(ic->i_cm_id, (union ib_gid *)&iinfo6->src_gid, + (union ib_gid *)&iinfo6->dst_gid); rds_ibdev = ic->rds_ibdev; iinfo6->max_send_wr = ic->i_send_ring.w_nr; iinfo6->max_recv_wr = ic->i_recv_ring.w_nr; diff --git a/net/rds/rds.h b/net/rds/rds.h index c4dcf654d8fe..6bfaf05b63b2 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -278,7 +278,7 @@ struct rds_incoming { struct in6_addr i_saddr; rds_rdma_cookie_t i_rdma_cookie; - struct timeval i_rx_tstamp; + ktime_t i_rx_tstamp; u64 i_rx_lat_trace[RDS_RX_MAX_TRACES]; }; diff --git a/net/rds/recv.c b/net/rds/recv.c index 504cd6bcc54c..727639dac8a7 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -43,18 +43,14 @@ void rds_inc_init(struct rds_incoming *inc, struct rds_connection *conn, struct in6_addr *saddr) { - int i; - refcount_set(&inc->i_refcount, 1); INIT_LIST_HEAD(&inc->i_item); inc->i_conn = conn; inc->i_saddr = *saddr; inc->i_rdma_cookie = 0; - inc->i_rx_tstamp.tv_sec = 0; - inc->i_rx_tstamp.tv_usec = 0; + inc->i_rx_tstamp = ktime_set(0, 0); - for (i = 0; i < RDS_RX_MAX_TRACES; i++) - inc->i_rx_lat_trace[i] = 0; + memset(inc->i_rx_lat_trace, 0, sizeof(inc->i_rx_lat_trace)); } EXPORT_SYMBOL_GPL(rds_inc_init); @@ -67,8 +63,7 @@ void rds_inc_path_init(struct rds_incoming *inc, struct rds_conn_path *cp, inc->i_conn_path = cp; inc->i_saddr = *saddr; inc->i_rdma_cookie = 0; - inc->i_rx_tstamp.tv_sec = 0; - inc->i_rx_tstamp.tv_usec = 0; + inc->i_rx_tstamp = ktime_set(0, 0); } EXPORT_SYMBOL_GPL(rds_inc_path_init); @@ -385,7 +380,7 @@ void rds_recv_incoming(struct rds_connection *conn, struct in6_addr *saddr, be32_to_cpu(inc->i_hdr.h_len), inc->i_hdr.h_dport); if (sock_flag(sk, SOCK_RCVTSTAMP)) - do_gettimeofday(&inc->i_rx_tstamp); + inc->i_rx_tstamp = ktime_get_real(); rds_inc_addref(inc); inc->i_rx_lat_trace[RDS_MSG_RX_END] = local_clock(); list_add_tail(&inc->i_item, &rs->rs_recv_queue); @@ -552,11 +547,11 @@ static int rds_cmsg_recv(struct rds_incoming *inc, struct msghdr *msg, goto out; } - if ((inc->i_rx_tstamp.tv_sec != 0) && + if ((inc->i_rx_tstamp != 0) && sock_flag(rds_rs_to_sk(rs), SOCK_RCVTSTAMP)) { + struct timeval tv = ktime_to_timeval(inc->i_rx_tstamp); ret = put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMP, - sizeof(struct timeval), - &inc->i_rx_tstamp); + sizeof(tv), &tv); if (ret) goto out; } diff --git a/net/rds/tcp.c b/net/rds/tcp.c index 2c7b7c352d3e..b9bbcf3d6c63 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -37,7 +37,6 @@ #include <net/tcp.h> #include <net/net_namespace.h> #include <net/netns/generic.h> -#include <net/tcp.h> #include <net/addrconf.h> #include "rds.h" diff --git a/net/rfkill/core.c b/net/rfkill/core.c index 1355f5ca8d22..abca57040f37 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -510,8 +510,8 @@ void rfkill_remove_epo_lock(void) /** * rfkill_is_epo_lock_active - returns true EPO is active * - * Returns 0 (false) if there is NOT an active EPO contidion, - * and 1 (true) if there is an active EPO contition, which + * Returns 0 (false) if there is NOT an active EPO condition, + * and 1 (true) if there is an active EPO condition, which * locks all radios in one of the BLOCKED states. * * Can be called in atomic context. diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c index 00192a996be0..0f8465852254 100644 --- a/net/rfkill/rfkill-gpio.c +++ b/net/rfkill/rfkill-gpio.c @@ -20,6 +20,7 @@ #include <linux/init.h> #include <linux/kernel.h> #include <linux/module.h> +#include <linux/mod_devicetable.h> #include <linux/rfkill.h> #include <linux/platform_device.h> #include <linux/clk.h> diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index cfdc199c6351..ee8e7e1d5c0f 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -259,7 +259,7 @@ static void rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, while (list) { skb = list; list = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); rxrpc_free_skb(skb, rxrpc_skb_tx_freed); } } diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 229d63c99be2..6f118d62c731 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -300,21 +300,17 @@ int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb, } EXPORT_SYMBOL(tcf_generic_walker); -static bool __tcf_idr_check(struct tc_action_net *tn, u32 index, - struct tc_action **a, int bind) +int tcf_idr_search(struct tc_action_net *tn, struct tc_action **a, u32 index) { struct tcf_idrinfo *idrinfo = tn->idrinfo; struct tc_action *p; spin_lock(&idrinfo->lock); p = idr_find(&idrinfo->action_idr, index); - if (IS_ERR(p)) { + if (IS_ERR(p)) p = NULL; - } else if (p) { + else if (p) refcount_inc(&p->tcfa_refcnt); - if (bind) - atomic_inc(&p->tcfa_bindcnt); - } spin_unlock(&idrinfo->lock); if (p) { @@ -323,23 +319,10 @@ static bool __tcf_idr_check(struct tc_action_net *tn, u32 index, } return false; } - -int tcf_idr_search(struct tc_action_net *tn, struct tc_action **a, u32 index) -{ - return __tcf_idr_check(tn, index, a, 0); -} EXPORT_SYMBOL(tcf_idr_search); -bool tcf_idr_check(struct tc_action_net *tn, u32 index, struct tc_action **a, - int bind) -{ - return __tcf_idr_check(tn, index, a, bind); -} -EXPORT_SYMBOL(tcf_idr_check); - -int tcf_idr_delete_index(struct tc_action_net *tn, u32 index) +static int tcf_idr_delete_index(struct tcf_idrinfo *idrinfo, u32 index) { - struct tcf_idrinfo *idrinfo = tn->idrinfo; struct tc_action *p; int ret = 0; @@ -370,7 +353,6 @@ int tcf_idr_delete_index(struct tc_action_net *tn, u32 index) spin_unlock(&idrinfo->lock); return ret; } -EXPORT_SYMBOL(tcf_idr_delete_index); int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, struct tc_action **a, const struct tc_action_ops *ops, @@ -409,7 +391,6 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est, p->idrinfo = idrinfo; p->ops = ops; - INIT_LIST_HEAD(&p->list); *a = p; return 0; err3: @@ -681,19 +662,30 @@ int tcf_action_destroy(struct tc_action *actions[], int bind) return ret; } +static int tcf_action_destroy_1(struct tc_action *a, int bind) +{ + struct tc_action *actions[] = { a, NULL }; + + return tcf_action_destroy(actions, bind); +} + static int tcf_action_put(struct tc_action *p) { return __tcf_action_put(p, false); } +/* Put all actions in this array, skip those NULL's. */ static void tcf_action_put_many(struct tc_action *actions[]) { int i; - for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) { + for (i = 0; i < TCA_ACT_MAX_PRIO; i++) { struct tc_action *a = actions[i]; - const struct tc_action_ops *ops = a->ops; + const struct tc_action_ops *ops; + if (!a) + continue; + ops = a->ops; if (tcf_action_put(a)) module_put(ops->owner); } @@ -896,17 +888,16 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp, if (TC_ACT_EXT_CMP(a->tcfa_action, TC_ACT_GOTO_CHAIN)) { err = tcf_action_goto_chain_init(a, tp); if (err) { - struct tc_action *actions[] = { a, NULL }; - - tcf_action_destroy(actions, bind); + tcf_action_destroy_1(a, bind); NL_SET_ERR_MSG(extack, "Failed to init TC action chain"); return ERR_PTR(err); } } if (!tcf_action_valid(a->tcfa_action)) { - NL_SET_ERR_MSG(extack, "invalid action value, using TC_ACT_UNSPEC instead"); - a->tcfa_action = TC_ACT_UNSPEC; + tcf_action_destroy_1(a, bind); + NL_SET_ERR_MSG(extack, "Invalid control action value"); + return ERR_PTR(-EINVAL); } return a; @@ -1082,12 +1073,14 @@ static struct tc_action *tcf_action_get_1(struct net *net, struct nlattr *nla, err = -EINVAL; ops = tc_lookup_action(tb[TCA_ACT_KIND]); if (!ops) { /* could happen in batch of actions */ - NL_SET_ERR_MSG(extack, "Specified TC action not found"); + NL_SET_ERR_MSG(extack, "Specified TC action kind not found"); goto err_out; } err = -ENOENT; - if (ops->lookup(net, &a, index, extack) == 0) + if (ops->lookup(net, &a, index) == 0) { + NL_SET_ERR_MSG(extack, "TC action with specified index not found"); goto err_mod; + } module_put(ops->owner); return a; @@ -1175,41 +1168,38 @@ err_out: return err; } -static int tcf_action_delete(struct net *net, struct tc_action *actions[], - int *acts_deleted, struct netlink_ext_ack *extack) +static int tcf_action_delete(struct net *net, struct tc_action *actions[]) { - u32 act_index; - int ret, i; + int i; for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) { struct tc_action *a = actions[i]; const struct tc_action_ops *ops = a->ops; - /* Actions can be deleted concurrently so we must save their * type and id to search again after reference is released. */ - act_index = a->tcfa_index; + struct tcf_idrinfo *idrinfo = a->idrinfo; + u32 act_index = a->tcfa_index; + actions[i] = NULL; if (tcf_action_put(a)) { /* last reference, action was deleted concurrently */ module_put(ops->owner); } else { + int ret; + /* now do the delete */ - ret = ops->delete(net, act_index); - if (ret < 0) { - *acts_deleted = i + 1; + ret = tcf_idr_delete_index(idrinfo, act_index); + if (ret < 0) return ret; - } } } - *acts_deleted = i; return 0; } static int tcf_del_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[], - int *acts_deleted, u32 portid, size_t attr_size, - struct netlink_ext_ack *extack) + u32 portid, size_t attr_size, struct netlink_ext_ack *extack) { int ret; struct sk_buff *skb; @@ -1227,7 +1217,7 @@ tcf_del_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[], } /* now do the delete */ - ret = tcf_action_delete(net, actions, acts_deleted, extack); + ret = tcf_action_delete(net, actions); if (ret < 0) { NL_SET_ERR_MSG(extack, "Failed to delete TC action"); kfree_skb(skb); @@ -1249,8 +1239,7 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; struct tc_action *act; size_t attr_size = 0; - struct tc_action *actions[TCA_ACT_MAX_PRIO + 1] = {}; - int acts_deleted = 0; + struct tc_action *actions[TCA_ACT_MAX_PRIO] = {}; ret = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL, extack); if (ret < 0) @@ -1280,14 +1269,13 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, if (event == RTM_GETACTION) ret = tcf_get_notify(net, portid, n, actions, event, extack); else { /* delete */ - ret = tcf_del_notify(net, n, actions, &acts_deleted, portid, - attr_size, extack); + ret = tcf_del_notify(net, n, actions, portid, attr_size, extack); if (ret) goto err; - return ret; + return 0; } err: - tcf_action_put_many(&actions[acts_deleted]); + tcf_action_put_many(actions); return ret; } diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index d30b23e42436..c7633843e223 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -387,21 +387,13 @@ static int tcf_bpf_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_bpf_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_bpf_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, bpf_net_id); return tcf_idr_search(tn, a, index); } -static int tcf_bpf_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, bpf_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_bpf_ops __read_mostly = { .kind = "bpf", .type = TCA_ACT_BPF, @@ -412,7 +404,6 @@ static struct tc_action_ops act_bpf_ops __read_mostly = { .init = tcf_bpf_init, .walk = tcf_bpf_walker, .lookup = tcf_bpf_search, - .delete = tcf_bpf_delete, .size = sizeof(struct tcf_bpf), }; diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 54c0bf54f2ac..8475913f2070 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -143,8 +143,10 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla, return -EEXIST; } /* replacing action and zone */ + spin_lock_bh(&ci->tcf_lock); ci->tcf_action = parm->action; ci->zone = parm->zone; + spin_unlock_bh(&ci->tcf_lock); ret = 0; } @@ -156,16 +158,16 @@ static inline int tcf_connmark_dump(struct sk_buff *skb, struct tc_action *a, { unsigned char *b = skb_tail_pointer(skb); struct tcf_connmark_info *ci = to_connmark(a); - struct tc_connmark opt = { .index = ci->tcf_index, .refcnt = refcount_read(&ci->tcf_refcnt) - ref, .bindcnt = atomic_read(&ci->tcf_bindcnt) - bind, - .action = ci->tcf_action, - .zone = ci->zone, }; struct tcf_t t; + spin_lock_bh(&ci->tcf_lock); + opt.action = ci->tcf_action; + opt.zone = ci->zone; if (nla_put(skb, TCA_CONNMARK_PARMS, sizeof(opt), &opt)) goto nla_put_failure; @@ -173,9 +175,12 @@ static inline int tcf_connmark_dump(struct sk_buff *skb, struct tc_action *a, if (nla_put_64bit(skb, TCA_CONNMARK_TM, sizeof(t), &t, TCA_CONNMARK_PAD)) goto nla_put_failure; + spin_unlock_bh(&ci->tcf_lock); return skb->len; + nla_put_failure: + spin_unlock_bh(&ci->tcf_lock); nlmsg_trim(skb, b); return -1; } @@ -190,21 +195,13 @@ static int tcf_connmark_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_connmark_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_connmark_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, connmark_net_id); return tcf_idr_search(tn, a, index); } -static int tcf_connmark_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, connmark_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_connmark_ops = { .kind = "connmark", .type = TCA_ACT_CONNMARK, @@ -214,7 +211,6 @@ static struct tc_action_ops act_connmark_ops = { .init = tcf_connmark_init, .walk = tcf_connmark_walker, .lookup = tcf_connmark_search, - .delete = tcf_connmark_delete, .size = sizeof(struct tcf_connmark_info), }; diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index e698d3fe2080..3dc25b7806d7 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -646,8 +646,7 @@ static int tcf_csum_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_csum_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_csum_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, csum_net_id); @@ -659,13 +658,6 @@ static size_t tcf_csum_get_fill_size(const struct tc_action *act) return nla_total_size(sizeof(struct tc_csum)); } -static int tcf_csum_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, csum_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_csum_ops = { .kind = "csum", .type = TCA_ACT_CSUM, @@ -677,7 +669,6 @@ static struct tc_action_ops act_csum_ops = { .walk = tcf_csum_walker, .lookup = tcf_csum_search, .get_fill_size = tcf_csum_get_fill_size, - .delete = tcf_csum_delete, .size = sizeof(struct tcf_csum), }; diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index 6a3f25a8ffb3..aa44d14b43c7 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -222,8 +222,7 @@ static int tcf_gact_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_gact_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_gact_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, gact_net_id); @@ -243,13 +242,6 @@ static size_t tcf_gact_get_fill_size(const struct tc_action *act) return sz; } -static int tcf_gact_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, gact_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_gact_ops = { .kind = "gact", .type = TCA_ACT_GACT, @@ -261,7 +253,6 @@ static struct tc_action_ops act_gact_ops = { .walk = tcf_gact_walker, .lookup = tcf_gact_search, .get_fill_size = tcf_gact_get_fill_size, - .delete = tcf_gact_delete, .size = sizeof(struct tcf_gact), }; diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index d1081bdf1bdb..30b63fa23ee2 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -167,16 +167,16 @@ static struct tcf_meta_ops *find_ife_oplist(u16 metaid) { struct tcf_meta_ops *o; - read_lock_bh(&ife_mod_lock); + read_lock(&ife_mod_lock); list_for_each_entry(o, &ifeoplist, list) { if (o->metaid == metaid) { if (!try_module_get(o->owner)) o = NULL; - read_unlock_bh(&ife_mod_lock); + read_unlock(&ife_mod_lock); return o; } } - read_unlock_bh(&ife_mod_lock); + read_unlock(&ife_mod_lock); return NULL; } @@ -190,12 +190,12 @@ int register_ife_op(struct tcf_meta_ops *mops) !mops->get || !mops->alloc) return -EINVAL; - write_lock_bh(&ife_mod_lock); + write_lock(&ife_mod_lock); list_for_each_entry(m, &ifeoplist, list) { if (m->metaid == mops->metaid || (strcmp(mops->name, m->name) == 0)) { - write_unlock_bh(&ife_mod_lock); + write_unlock(&ife_mod_lock); return -EEXIST; } } @@ -204,7 +204,7 @@ int register_ife_op(struct tcf_meta_ops *mops) mops->release = ife_release_meta_gen; list_add_tail(&mops->list, &ifeoplist); - write_unlock_bh(&ife_mod_lock); + write_unlock(&ife_mod_lock); return 0; } EXPORT_SYMBOL_GPL(unregister_ife_op); @@ -214,7 +214,7 @@ int unregister_ife_op(struct tcf_meta_ops *mops) struct tcf_meta_ops *m; int err = -ENOENT; - write_lock_bh(&ife_mod_lock); + write_lock(&ife_mod_lock); list_for_each_entry(m, &ifeoplist, list) { if (m->metaid == mops->metaid) { list_del(&mops->list); @@ -222,7 +222,7 @@ int unregister_ife_op(struct tcf_meta_ops *mops) break; } } - write_unlock_bh(&ife_mod_lock); + write_unlock(&ife_mod_lock); return err; } @@ -265,11 +265,8 @@ static const char *ife_meta_id2name(u32 metaid) #endif /* called when adding new meta information - * under ife->tcf_lock for existing action */ -static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid, - void *val, int len, bool exists, - bool rtnl_held) +static int load_metaops_and_vet(u32 metaid, void *val, int len, bool rtnl_held) { struct tcf_meta_ops *ops = find_ife_oplist(metaid); int ret = 0; @@ -277,15 +274,11 @@ static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid, if (!ops) { ret = -ENOENT; #ifdef CONFIG_MODULES - if (exists) - spin_unlock_bh(&ife->tcf_lock); if (rtnl_held) rtnl_unlock(); request_module("ife-meta-%s", ife_meta_id2name(metaid)); if (rtnl_held) rtnl_lock(); - if (exists) - spin_lock_bh(&ife->tcf_lock); ops = find_ife_oplist(metaid); #endif } @@ -302,24 +295,17 @@ static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid, } /* called when adding new meta information - * under ife->tcf_lock for existing action */ -static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval, - int len, bool atomic) +static int __add_metainfo(const struct tcf_meta_ops *ops, + struct tcf_ife_info *ife, u32 metaid, void *metaval, + int len, bool atomic, bool exists) { struct tcf_meta_info *mi = NULL; - struct tcf_meta_ops *ops = find_ife_oplist(metaid); int ret = 0; - if (!ops) - return -ENOENT; - mi = kzalloc(sizeof(*mi), atomic ? GFP_ATOMIC : GFP_KERNEL); - if (!mi) { - /*put back what find_ife_oplist took */ - module_put(ops->owner); + if (!mi) return -ENOMEM; - } mi->metaid = metaid; mi->ops = ops; @@ -327,29 +313,61 @@ static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval, ret = ops->alloc(mi, metaval, atomic ? GFP_ATOMIC : GFP_KERNEL); if (ret != 0) { kfree(mi); - module_put(ops->owner); return ret; } } + if (exists) + spin_lock_bh(&ife->tcf_lock); list_add_tail(&mi->metalist, &ife->metalist); + if (exists) + spin_unlock_bh(&ife->tcf_lock); return ret; } -static int use_all_metadata(struct tcf_ife_info *ife) +static int add_metainfo_and_get_ops(const struct tcf_meta_ops *ops, + struct tcf_ife_info *ife, u32 metaid, + bool exists) +{ + int ret; + + if (!try_module_get(ops->owner)) + return -ENOENT; + ret = __add_metainfo(ops, ife, metaid, NULL, 0, true, exists); + if (ret) + module_put(ops->owner); + return ret; +} + +static int add_metainfo(struct tcf_ife_info *ife, u32 metaid, void *metaval, + int len, bool exists) +{ + const struct tcf_meta_ops *ops = find_ife_oplist(metaid); + int ret; + + if (!ops) + return -ENOENT; + ret = __add_metainfo(ops, ife, metaid, metaval, len, false, exists); + if (ret) + /*put back what find_ife_oplist took */ + module_put(ops->owner); + return ret; +} + +static int use_all_metadata(struct tcf_ife_info *ife, bool exists) { struct tcf_meta_ops *o; int rc = 0; int installed = 0; - read_lock_bh(&ife_mod_lock); + read_lock(&ife_mod_lock); list_for_each_entry(o, &ifeoplist, list) { - rc = add_metainfo(ife, o->metaid, NULL, 0, true); + rc = add_metainfo_and_get_ops(o, ife, o->metaid, exists); if (rc == 0) installed += 1; } - read_unlock_bh(&ife_mod_lock); + read_unlock(&ife_mod_lock); if (installed) return 0; @@ -396,7 +414,6 @@ static void _tcf_ife_cleanup(struct tc_action *a) struct tcf_meta_info *e, *n; list_for_each_entry_safe(e, n, &ife->metalist, metalist) { - module_put(e->ops->owner); list_del(&e->metalist); if (e->metaval) { if (e->ops->release) @@ -404,6 +421,7 @@ static void _tcf_ife_cleanup(struct tc_action *a) else kfree(e->metaval); } + module_put(e->ops->owner); kfree(e); } } @@ -422,7 +440,6 @@ static void tcf_ife_cleanup(struct tc_action *a) kfree_rcu(p, rcu); } -/* under ife->tcf_lock for existing action */ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb, bool exists, bool rtnl_held) { @@ -436,8 +453,7 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb, val = nla_data(tb[i]); len = nla_len(tb[i]); - rc = load_metaops_and_vet(ife, i, val, len, exists, - rtnl_held); + rc = load_metaops_and_vet(i, val, len, rtnl_held); if (rc != 0) return rc; @@ -540,8 +556,6 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, p->eth_type = ife_type; } - if (exists) - spin_lock_bh(&ife->tcf_lock); if (ret == ACT_P_CREATED) INIT_LIST_HEAD(&ife->metalist); @@ -551,10 +565,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, NULL, NULL); if (err) { metadata_parse_err: - if (exists) - spin_unlock_bh(&ife->tcf_lock); tcf_idr_release(*a, bind); - kfree(p); return err; } @@ -569,17 +580,16 @@ metadata_parse_err: * as we can. You better have at least one else we are * going to bail out */ - err = use_all_metadata(ife); + err = use_all_metadata(ife, exists); if (err) { - if (exists) - spin_unlock_bh(&ife->tcf_lock); tcf_idr_release(*a, bind); - kfree(p); return err; } } + if (exists) + spin_lock_bh(&ife->tcf_lock); ife->tcf_action = parm->action; /* protected by tcf_lock when modifying existing action */ rcu_swap_protected(ife->params, p, 1); @@ -845,21 +855,13 @@ static int tcf_ife_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_ife_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_ife_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, ife_net_id); return tcf_idr_search(tn, a, index); } -static int tcf_ife_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, ife_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_ife_ops = { .kind = "ife", .type = TCA_ACT_IFE, @@ -870,7 +872,6 @@ static struct tc_action_ops act_ife_ops = { .init = tcf_ife_init, .walk = tcf_ife_walker, .lookup = tcf_ife_search, - .delete = tcf_ife_delete, .size = sizeof(struct tcf_ife_info), }; diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 51f235bbeb5b..1efbfb10b1fc 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -329,21 +329,13 @@ static int tcf_ipt_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_ipt_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_ipt_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, ipt_net_id); return tcf_idr_search(tn, a, index); } -static int tcf_ipt_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, ipt_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_ipt_ops = { .kind = "ipt", .type = TCA_ACT_IPT, @@ -354,7 +346,6 @@ static struct tc_action_ops act_ipt_ops = { .init = tcf_ipt_init, .walk = tcf_ipt_walker, .lookup = tcf_ipt_search, - .delete = tcf_ipt_delete, .size = sizeof(struct tcf_ipt), }; @@ -387,21 +378,13 @@ static int tcf_xt_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_xt_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_xt_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, xt_net_id); return tcf_idr_search(tn, a, index); } -static int tcf_xt_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, xt_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_xt_ops = { .kind = "xt", .type = TCA_ACT_XT, @@ -412,7 +395,6 @@ static struct tc_action_ops act_xt_ops = { .init = tcf_xt_init, .walk = tcf_xt_walker, .lookup = tcf_xt_search, - .delete = tcf_xt_delete, .size = sizeof(struct tcf_ipt), }; diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 38fd20f10f67..a9d64bfe5a2a 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -338,8 +338,7 @@ static int tcf_mirred_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_mirred_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_mirred_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, mirred_net_id); @@ -395,13 +394,6 @@ static void tcf_mirred_put_dev(struct net_device *dev) dev_put(dev); } -static int tcf_mirred_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, mirred_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_mirred_ops = { .kind = "mirred", .type = TCA_ACT_MIRRED, @@ -416,7 +408,6 @@ static struct tc_action_ops act_mirred_ops = { .size = sizeof(struct tcf_mirred), .get_dev = tcf_mirred_get_dev, .put_dev = tcf_mirred_put_dev, - .delete = tcf_mirred_delete, }; static __net_init int mirred_init_net(struct net *net) diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 822e903bfc25..c5c1e23add77 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -256,28 +256,31 @@ static int tcf_nat_dump(struct sk_buff *skb, struct tc_action *a, unsigned char *b = skb_tail_pointer(skb); struct tcf_nat *p = to_tcf_nat(a); struct tc_nat opt = { - .old_addr = p->old_addr, - .new_addr = p->new_addr, - .mask = p->mask, - .flags = p->flags, - .index = p->tcf_index, - .action = p->tcf_action, .refcnt = refcount_read(&p->tcf_refcnt) - ref, .bindcnt = atomic_read(&p->tcf_bindcnt) - bind, }; struct tcf_t t; + spin_lock_bh(&p->tcf_lock); + opt.old_addr = p->old_addr; + opt.new_addr = p->new_addr; + opt.mask = p->mask; + opt.flags = p->flags; + opt.action = p->tcf_action; + if (nla_put(skb, TCA_NAT_PARMS, sizeof(opt), &opt)) goto nla_put_failure; tcf_tm_dump(&t, &p->tcf_tm); if (nla_put_64bit(skb, TCA_NAT_TM, sizeof(t), &t, TCA_NAT_PAD)) goto nla_put_failure; + spin_unlock_bh(&p->tcf_lock); return skb->len; nla_put_failure: + spin_unlock_bh(&p->tcf_lock); nlmsg_trim(skb, b); return -1; } @@ -292,21 +295,13 @@ static int tcf_nat_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_nat_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_nat_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, nat_net_id); return tcf_idr_search(tn, a, index); } -static int tcf_nat_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, nat_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_nat_ops = { .kind = "nat", .type = TCA_ACT_NAT, @@ -316,7 +311,6 @@ static struct tc_action_ops act_nat_ops = { .init = tcf_nat_init, .walk = tcf_nat_walker, .lookup = tcf_nat_search, - .delete = tcf_nat_delete, .size = sizeof(struct tcf_nat), }; diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 8a7a7cb94e83..da3dd0f68cc2 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -109,16 +109,18 @@ static int tcf_pedit_key_ex_dump(struct sk_buff *skb, { struct nlattr *keys_start = nla_nest_start(skb, TCA_PEDIT_KEYS_EX); + if (!keys_start) + goto nla_failure; for (; n > 0; n--) { struct nlattr *key_start; key_start = nla_nest_start(skb, TCA_PEDIT_KEY_EX); + if (!key_start) + goto nla_failure; if (nla_put_u16(skb, TCA_PEDIT_KEY_EX_HTYPE, keys_ex->htype) || - nla_put_u16(skb, TCA_PEDIT_KEY_EX_CMD, keys_ex->cmd)) { - nlmsg_trim(skb, keys_start); - return -EINVAL; - } + nla_put_u16(skb, TCA_PEDIT_KEY_EX_CMD, keys_ex->cmd)) + goto nla_failure; nla_nest_end(skb, key_start); @@ -128,6 +130,9 @@ static int tcf_pedit_key_ex_dump(struct sk_buff *skb, nla_nest_end(skb, keys_start); return 0; +nla_failure: + nla_nest_cancel(skb, keys_start); + return -EINVAL; } static int tcf_pedit_init(struct net *net, struct nlattr *nla, @@ -418,7 +423,10 @@ static int tcf_pedit_dump(struct sk_buff *skb, struct tc_action *a, opt->bindcnt = atomic_read(&p->tcf_bindcnt) - bind; if (p->tcfp_keys_ex) { - tcf_pedit_key_ex_dump(skb, p->tcfp_keys_ex, p->tcfp_nkeys); + if (tcf_pedit_key_ex_dump(skb, + p->tcfp_keys_ex, + p->tcfp_nkeys)) + goto nla_put_failure; if (nla_put(skb, TCA_PEDIT_PARMS_EX, s, opt)) goto nla_put_failure; @@ -452,21 +460,13 @@ static int tcf_pedit_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_pedit_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_pedit_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, pedit_net_id); return tcf_idr_search(tn, a, index); } -static int tcf_pedit_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, pedit_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_pedit_ops = { .kind = "pedit", .type = TCA_ACT_PEDIT, @@ -477,7 +477,6 @@ static struct tc_action_ops act_pedit_ops = { .init = tcf_pedit_init, .walk = tcf_pedit_walker, .lookup = tcf_pedit_search, - .delete = tcf_pedit_delete, .size = sizeof(struct tcf_pedit), }; diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 06f0742db593..92649d2667ed 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -22,8 +22,7 @@ #include <net/act_api.h> #include <net/netlink.h> -struct tcf_police { - struct tc_action common; +struct tcf_police_params { int tcfp_result; u32 tcfp_ewma_rate; s64 tcfp_burst; @@ -36,6 +35,12 @@ struct tcf_police { bool rate_present; struct psched_ratecfg peak; bool peak_present; + struct rcu_head rcu; +}; + +struct tcf_police { + struct tc_action common; + struct tcf_police_params __rcu *params; }; #define to_police(pc) ((struct tcf_police *)pc) @@ -84,6 +89,7 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, struct tcf_police *police; struct qdisc_rate_table *R_tab = NULL, *P_tab = NULL; struct tc_action_net *tn = net_generic(net, police_net_id); + struct tcf_police_params *new; bool exists = false; int size; @@ -110,7 +116,7 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, if (!exists) { ret = tcf_idr_create(tn, parm->index, NULL, a, - &act_police_ops, bind, false); + &act_police_ops, bind, true); if (ret) { tcf_idr_cleanup(tn, parm->index); return ret; @@ -137,7 +143,8 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, } if (est) { - err = gen_replace_estimator(&police->tcf_bstats, NULL, + err = gen_replace_estimator(&police->tcf_bstats, + police->common.cpu_bstats, &police->tcf_rate_est, &police->tcf_lock, NULL, est); @@ -150,50 +157,60 @@ static int tcf_police_init(struct net *net, struct nlattr *nla, goto failure; } - spin_lock_bh(&police->tcf_lock); + new = kzalloc(sizeof(*new), GFP_KERNEL); + if (unlikely(!new)) { + err = -ENOMEM; + goto failure; + } + /* No failure allowed after this point */ - police->tcfp_mtu = parm->mtu; - if (police->tcfp_mtu == 0) { - police->tcfp_mtu = ~0; + new->tcfp_mtu = parm->mtu; + if (!new->tcfp_mtu) { + new->tcfp_mtu = ~0; if (R_tab) - police->tcfp_mtu = 255 << R_tab->rate.cell_log; + new->tcfp_mtu = 255 << R_tab->rate.cell_log; } if (R_tab) { - police->rate_present = true; - psched_ratecfg_precompute(&police->rate, &R_tab->rate, 0); + new->rate_present = true; + psched_ratecfg_precompute(&new->rate, &R_tab->rate, 0); qdisc_put_rtab(R_tab); } else { - police->rate_present = false; + new->rate_present = false; } if (P_tab) { - police->peak_present = true; - psched_ratecfg_precompute(&police->peak, &P_tab->rate, 0); + new->peak_present = true; + psched_ratecfg_precompute(&new->peak, &P_tab->rate, 0); qdisc_put_rtab(P_tab); } else { - police->peak_present = false; + new->peak_present = false; } if (tb[TCA_POLICE_RESULT]) - police->tcfp_result = nla_get_u32(tb[TCA_POLICE_RESULT]); - police->tcfp_burst = PSCHED_TICKS2NS(parm->burst); - police->tcfp_toks = police->tcfp_burst; - if (police->peak_present) { - police->tcfp_mtu_ptoks = (s64) psched_l2t_ns(&police->peak, - police->tcfp_mtu); - police->tcfp_ptoks = police->tcfp_mtu_ptoks; + new->tcfp_result = nla_get_u32(tb[TCA_POLICE_RESULT]); + new->tcfp_burst = PSCHED_TICKS2NS(parm->burst); + new->tcfp_toks = new->tcfp_burst; + if (new->peak_present) { + new->tcfp_mtu_ptoks = (s64)psched_l2t_ns(&new->peak, + new->tcfp_mtu); + new->tcfp_ptoks = new->tcfp_mtu_ptoks; } - police->tcf_action = parm->action; if (tb[TCA_POLICE_AVRATE]) - police->tcfp_ewma_rate = nla_get_u32(tb[TCA_POLICE_AVRATE]); + new->tcfp_ewma_rate = nla_get_u32(tb[TCA_POLICE_AVRATE]); + spin_lock_bh(&police->tcf_lock); + new->tcfp_t_c = ktime_get_ns(); + police->tcf_action = parm->action; + rcu_swap_protected(police->params, + new, + lockdep_is_held(&police->tcf_lock)); spin_unlock_bh(&police->tcf_lock); - if (ret != ACT_P_CREATED) - return ret; - police->tcfp_t_c = ktime_get_ns(); - tcf_idr_insert(tn, *a); + if (new) + kfree_rcu(new, rcu); + if (ret == ACT_P_CREATED) + tcf_idr_insert(tn, *a); return ret; failure: @@ -207,64 +224,69 @@ static int tcf_police_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_police *police = to_police(a); - s64 now; - s64 toks; - s64 ptoks = 0; + struct tcf_police_params *p; + s64 now, toks, ptoks = 0; + int ret; - spin_lock(&police->tcf_lock); - - bstats_update(&police->tcf_bstats, skb); tcf_lastuse_update(&police->tcf_tm); + bstats_cpu_update(this_cpu_ptr(police->common.cpu_bstats), skb); + + ret = READ_ONCE(police->tcf_action); + p = rcu_dereference_bh(police->params); - if (police->tcfp_ewma_rate) { + if (p->tcfp_ewma_rate) { struct gnet_stats_rate_est64 sample; if (!gen_estimator_read(&police->tcf_rate_est, &sample) || - sample.bps >= police->tcfp_ewma_rate) { - police->tcf_qstats.overlimits++; - if (police->tcf_action == TC_ACT_SHOT) - police->tcf_qstats.drops++; - spin_unlock(&police->tcf_lock); - return police->tcf_action; - } + sample.bps >= p->tcfp_ewma_rate) + goto inc_overlimits; } - if (qdisc_pkt_len(skb) <= police->tcfp_mtu) { - if (!police->rate_present) { - spin_unlock(&police->tcf_lock); - return police->tcfp_result; + if (qdisc_pkt_len(skb) <= p->tcfp_mtu) { + if (!p->rate_present) { + ret = p->tcfp_result; + goto end; } now = ktime_get_ns(); - toks = min_t(s64, now - police->tcfp_t_c, - police->tcfp_burst); - if (police->peak_present) { - ptoks = toks + police->tcfp_ptoks; - if (ptoks > police->tcfp_mtu_ptoks) - ptoks = police->tcfp_mtu_ptoks; - ptoks -= (s64) psched_l2t_ns(&police->peak, - qdisc_pkt_len(skb)); + toks = min_t(s64, now - p->tcfp_t_c, p->tcfp_burst); + if (p->peak_present) { + ptoks = toks + p->tcfp_ptoks; + if (ptoks > p->tcfp_mtu_ptoks) + ptoks = p->tcfp_mtu_ptoks; + ptoks -= (s64)psched_l2t_ns(&p->peak, + qdisc_pkt_len(skb)); } - toks += police->tcfp_toks; - if (toks > police->tcfp_burst) - toks = police->tcfp_burst; - toks -= (s64) psched_l2t_ns(&police->rate, qdisc_pkt_len(skb)); + toks += p->tcfp_toks; + if (toks > p->tcfp_burst) + toks = p->tcfp_burst; + toks -= (s64)psched_l2t_ns(&p->rate, qdisc_pkt_len(skb)); if ((toks|ptoks) >= 0) { - police->tcfp_t_c = now; - police->tcfp_toks = toks; - police->tcfp_ptoks = ptoks; - if (police->tcfp_result == TC_ACT_SHOT) - police->tcf_qstats.drops++; - spin_unlock(&police->tcf_lock); - return police->tcfp_result; + p->tcfp_t_c = now; + p->tcfp_toks = toks; + p->tcfp_ptoks = ptoks; + ret = p->tcfp_result; + goto inc_drops; } } - police->tcf_qstats.overlimits++; - if (police->tcf_action == TC_ACT_SHOT) - police->tcf_qstats.drops++; - spin_unlock(&police->tcf_lock); - return police->tcf_action; +inc_overlimits: + qstats_overlimit_inc(this_cpu_ptr(police->common.cpu_qstats)); +inc_drops: + if (ret == TC_ACT_SHOT) + qstats_drop_inc(this_cpu_ptr(police->common.cpu_qstats)); +end: + return ret; +} + +static void tcf_police_cleanup(struct tc_action *a) +{ + struct tcf_police *police = to_police(a); + struct tcf_police_params *p; + + p = rcu_dereference_protected(police->params, 1); + if (p) + kfree_rcu(p, rcu); } static int tcf_police_dump(struct sk_buff *skb, struct tc_action *a, @@ -272,6 +294,7 @@ static int tcf_police_dump(struct sk_buff *skb, struct tc_action *a, { unsigned char *b = skb_tail_pointer(skb); struct tcf_police *police = to_police(a); + struct tcf_police_params *p; struct tc_police opt = { .index = police->tcf_index, .refcnt = refcount_read(&police->tcf_refcnt) - ref, @@ -281,19 +304,21 @@ static int tcf_police_dump(struct sk_buff *skb, struct tc_action *a, spin_lock_bh(&police->tcf_lock); opt.action = police->tcf_action; - opt.mtu = police->tcfp_mtu; - opt.burst = PSCHED_NS2TICKS(police->tcfp_burst); - if (police->rate_present) - psched_ratecfg_getrate(&opt.rate, &police->rate); - if (police->peak_present) - psched_ratecfg_getrate(&opt.peakrate, &police->peak); + p = rcu_dereference_protected(police->params, + lockdep_is_held(&police->tcf_lock)); + opt.mtu = p->tcfp_mtu; + opt.burst = PSCHED_NS2TICKS(p->tcfp_burst); + if (p->rate_present) + psched_ratecfg_getrate(&opt.rate, &p->rate); + if (p->peak_present) + psched_ratecfg_getrate(&opt.peakrate, &p->peak); if (nla_put(skb, TCA_POLICE_TBF, sizeof(opt), &opt)) goto nla_put_failure; - if (police->tcfp_result && - nla_put_u32(skb, TCA_POLICE_RESULT, police->tcfp_result)) + if (p->tcfp_result && + nla_put_u32(skb, TCA_POLICE_RESULT, p->tcfp_result)) goto nla_put_failure; - if (police->tcfp_ewma_rate && - nla_put_u32(skb, TCA_POLICE_AVRATE, police->tcfp_ewma_rate)) + if (p->tcfp_ewma_rate && + nla_put_u32(skb, TCA_POLICE_AVRATE, p->tcfp_ewma_rate)) goto nla_put_failure; t.install = jiffies_to_clock_t(jiffies - police->tcf_tm.install); @@ -312,21 +337,13 @@ nla_put_failure: return -1; } -static int tcf_police_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_police_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, police_net_id); return tcf_idr_search(tn, a, index); } -static int tcf_police_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, police_net_id); - - return tcf_idr_delete_index(tn, index); -} - MODULE_AUTHOR("Alexey Kuznetsov"); MODULE_DESCRIPTION("Policing actions"); MODULE_LICENSE("GPL"); @@ -340,7 +357,7 @@ static struct tc_action_ops act_police_ops = { .init = tcf_police_init, .walk = tcf_police_walker, .lookup = tcf_police_search, - .delete = tcf_police_delete, + .cleanup = tcf_police_cleanup, .size = sizeof(struct tcf_police), }; diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 207b4132d1b0..1a0c682fd734 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -69,7 +69,7 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, if (!exists) { ret = tcf_idr_create(tn, parm->index, est, a, - &act_sample_ops, bind, false); + &act_sample_ops, bind, true); if (ret) { tcf_idr_cleanup(tn, parm->index); return ret; @@ -224,21 +224,13 @@ static int tcf_sample_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_sample_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_sample_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, sample_net_id); return tcf_idr_search(tn, a, index); } -static int tcf_sample_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, sample_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_sample_ops = { .kind = "sample", .type = TCA_ACT_SAMPLE, @@ -249,7 +241,6 @@ static struct tc_action_ops act_sample_ops = { .cleanup = tcf_sample_cleanup, .walk = tcf_sample_walker, .lookup = tcf_sample_search, - .delete = tcf_sample_delete, .size = sizeof(struct tcf_sample), }; diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index e616523ba3c1..902957beceb3 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -188,21 +188,13 @@ static int tcf_simp_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_simp_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_simp_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, simp_net_id); return tcf_idr_search(tn, a, index); } -static int tcf_simp_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, simp_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_simp_ops = { .kind = "simple", .type = TCA_ACT_SIMP, @@ -213,7 +205,6 @@ static struct tc_action_ops act_simp_ops = { .init = tcf_simp_init, .walk = tcf_simp_walker, .lookup = tcf_simp_search, - .delete = tcf_simp_delete, .size = sizeof(struct tcf_defact), }; diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 926d7bc4a89d..64dba3708fce 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -99,7 +99,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, skbedit_net_id); - struct tcf_skbedit_params *params_old, *params_new; + struct tcf_skbedit_params *params_new; struct nlattr *tb[TCA_SKBEDIT_MAX + 1]; struct tc_skbedit *parm; struct tcf_skbedit *d; @@ -187,8 +187,6 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, } } - ASSERT_RTNL(); - params_new = kzalloc(sizeof(*params_new), GFP_KERNEL); if (unlikely(!params_new)) { if (ret == ACT_P_CREATED) @@ -210,11 +208,13 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla, if (flags & SKBEDIT_F_MASK) params_new->mask = *mask; + spin_lock_bh(&d->tcf_lock); d->tcf_action = parm->action; - params_old = rtnl_dereference(d->params); - rcu_assign_pointer(d->params, params_new); - if (params_old) - kfree_rcu(params_old, rcu); + rcu_swap_protected(d->params, params_new, + lockdep_is_held(&d->tcf_lock)); + spin_unlock_bh(&d->tcf_lock); + if (params_new) + kfree_rcu(params_new, rcu); if (ret == ACT_P_CREATED) tcf_idr_insert(tn, *a); @@ -231,12 +231,14 @@ static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a, .index = d->tcf_index, .refcnt = refcount_read(&d->tcf_refcnt) - ref, .bindcnt = atomic_read(&d->tcf_bindcnt) - bind, - .action = d->tcf_action, }; u64 pure_flags = 0; struct tcf_t t; - params = rtnl_dereference(d->params); + spin_lock_bh(&d->tcf_lock); + params = rcu_dereference_protected(d->params, + lockdep_is_held(&d->tcf_lock)); + opt.action = d->tcf_action; if (nla_put(skb, TCA_SKBEDIT_PARMS, sizeof(opt), &opt)) goto nla_put_failure; @@ -264,9 +266,12 @@ static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a, tcf_tm_dump(&t, &d->tcf_tm); if (nla_put_64bit(skb, TCA_SKBEDIT_TM, sizeof(t), &t, TCA_SKBEDIT_PAD)) goto nla_put_failure; + spin_unlock_bh(&d->tcf_lock); + return skb->len; nla_put_failure: + spin_unlock_bh(&d->tcf_lock); nlmsg_trim(skb, b); return -1; } @@ -291,21 +296,13 @@ static int tcf_skbedit_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_skbedit_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_skbedit_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, skbedit_net_id); return tcf_idr_search(tn, a, index); } -static int tcf_skbedit_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, skbedit_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_skbedit_ops = { .kind = "skbedit", .type = TCA_ACT_SKBEDIT, @@ -316,7 +313,6 @@ static struct tc_action_ops act_skbedit_ops = { .cleanup = tcf_skbedit_cleanup, .walk = tcf_skbedit_walker, .lookup = tcf_skbedit_search, - .delete = tcf_skbedit_delete, .size = sizeof(struct tcf_skbedit), }; diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index d6a1af0c4171..59710a183bd3 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -251,21 +251,13 @@ static int tcf_skbmod_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_skbmod_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_skbmod_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, skbmod_net_id); return tcf_idr_search(tn, a, index); } -static int tcf_skbmod_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, skbmod_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_skbmod_ops = { .kind = "skbmod", .type = TCA_ACT_SKBMOD, @@ -276,7 +268,6 @@ static struct tc_action_ops act_skbmod_ops = { .cleanup = tcf_skbmod_cleanup, .walk = tcf_skbmod_walker, .lookup = tcf_skbmod_search, - .delete = tcf_skbmod_delete, .size = sizeof(struct tcf_skbmod), }; diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 8f09cf08d8fe..4cca8f274662 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -317,7 +317,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, &metadata->u.tun_info, opts_len, extack); if (ret < 0) - goto err_out; + goto release_tun_meta; } metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX; @@ -333,23 +333,24 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, &act_tunnel_key_ops, bind, true); if (ret) { NL_SET_ERR_MSG(extack, "Cannot create TC IDR"); - goto err_out; + goto release_tun_meta; } ret = ACT_P_CREATED; } else if (!ovr) { - tcf_idr_release(*a, bind); NL_SET_ERR_MSG(extack, "TC IDR already exists"); - return -EEXIST; + ret = -EEXIST; + goto release_tun_meta; } t = to_tunnel_key(*a); params_new = kzalloc(sizeof(*params_new), GFP_KERNEL); if (unlikely(!params_new)) { - tcf_idr_release(*a, bind); NL_SET_ERR_MSG(extack, "Cannot allocate tunnel key parameters"); - return -ENOMEM; + ret = -ENOMEM; + exists = true; + goto release_tun_meta; } params_new->tcft_action = parm->t_action; params_new->tcft_enc_metadata = metadata; @@ -367,6 +368,9 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, return ret; +release_tun_meta: + dst_release(&metadata->dst); + err_out: if (exists) tcf_idr_release(*a, bind); @@ -408,8 +412,10 @@ static int tunnel_key_geneve_opts_dump(struct sk_buff *skb, nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE, opt->type) || nla_put(skb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA, - opt->length * 4, opt + 1)) + opt->length * 4, opt + 1)) { + nla_nest_cancel(skb, start); return -EMSGSIZE; + } len -= sizeof(struct geneve_opt) + opt->length * 4; src += sizeof(struct geneve_opt) + opt->length * 4; @@ -423,7 +429,7 @@ static int tunnel_key_opts_dump(struct sk_buff *skb, const struct ip_tunnel_info *info) { struct nlattr *start; - int err; + int err = -EINVAL; if (!info->options_len) return 0; @@ -435,9 +441,11 @@ static int tunnel_key_opts_dump(struct sk_buff *skb, if (info->key.tun_flags & TUNNEL_GENEVE_OPT) { err = tunnel_key_geneve_opts_dump(skb, info); if (err) - return err; + goto err_out; } else { - return -EINVAL; +err_out: + nla_nest_cancel(skb, start); + return err; } nla_nest_end(skb, start); @@ -540,21 +548,13 @@ static int tunnel_key_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tunnel_key_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tunnel_key_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); return tcf_idr_search(tn, a, index); } -static int tunnel_key_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, tunnel_key_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_tunnel_key_ops = { .kind = "tunnel_key", .type = TCA_ACT_TUNNEL_KEY, @@ -565,7 +565,6 @@ static struct tc_action_ops act_tunnel_key_ops = { .cleanup = tunnel_key_release, .walk = tunnel_key_walker, .lookup = tunnel_key_search, - .delete = tunnel_key_delete, .size = sizeof(struct tcf_tunnel_key), }; diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 209e70ad2c09..ba677d54a7af 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -288,21 +288,13 @@ static int tcf_vlan_walker(struct net *net, struct sk_buff *skb, return tcf_generic_walker(tn, skb, cb, type, ops, extack); } -static int tcf_vlan_search(struct net *net, struct tc_action **a, u32 index, - struct netlink_ext_ack *extack) +static int tcf_vlan_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, vlan_net_id); return tcf_idr_search(tn, a, index); } -static int tcf_vlan_delete(struct net *net, u32 index) -{ - struct tc_action_net *tn = net_generic(net, vlan_net_id); - - return tcf_idr_delete_index(tn, index); -} - static struct tc_action_ops act_vlan_ops = { .kind = "vlan", .type = TCA_ACT_VLAN, @@ -313,7 +305,6 @@ static struct tc_action_ops act_vlan_ops = { .cleanup = tcf_vlan_cleanup, .walk = tcf_vlan_walker, .lookup = tcf_vlan_search, - .delete = tcf_vlan_delete, .size = sizeof(struct tcf_vlan), }; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 31bd1439cf60..0a75cb2e5e7b 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1252,7 +1252,7 @@ replay: } chain = tcf_chain_get(block, chain_index, true); if (!chain) { - NL_SET_ERR_MSG(extack, "Cannot find specified filter chain"); + NL_SET_ERR_MSG(extack, "Cannot create specified filter chain"); err = -ENOMEM; goto errout; } @@ -1399,7 +1399,7 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, goto errout; } NL_SET_ERR_MSG(extack, "Cannot find specified filter chain"); - err = -EINVAL; + err = -ENOENT; goto errout; } @@ -1902,6 +1902,8 @@ replay: RTM_NEWCHAIN, false); break; case RTM_DELCHAIN: + tfilter_notify_chain(net, skb, block, q, parent, n, + chain, RTM_DELTFILTER); /* Flush the chain first as the user requested chain removal. */ tcf_chain_flush(chain); /* In case the chain was successfully deleted, put a reference diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 6fd9bdd93796..4b8dd37dd4f8 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -98,7 +98,7 @@ struct cls_fl_filter { struct list_head list; u32 handle; u32 flags; - unsigned int in_hw_count; + u32 in_hw_count; struct rcu_work rwork; struct net_device *hw_dev; }; @@ -1880,6 +1880,9 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh, if (f->flags && nla_put_u32(skb, TCA_FLOWER_FLAGS, f->flags)) goto nla_put_failure; + if (nla_put_u32(skb, TCA_FLOWER_IN_HW_COUNT, f->in_hw_count)) + goto nla_put_failure; + if (tcf_exts_dump(skb, &f->exts)) goto nla_put_failure; diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index d5d2a6dc3921..f218ccf1e2d9 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -914,6 +914,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_U32_MAX + 1]; u32 htid, flags = 0; + size_t sel_size; int err; #ifdef CONFIG_CLS_U32_PERF size_t size; @@ -1076,8 +1077,13 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, } s = nla_data(tb[TCA_U32_SEL]); + sel_size = struct_size(s, keys, s->nkeys); + if (nla_len(tb[TCA_U32_SEL]) < sel_size) { + err = -EINVAL; + goto erridr; + } - n = kzalloc(sizeof(*n) + s->nkeys*sizeof(struct tc_u32_key), GFP_KERNEL); + n = kzalloc(offsetof(typeof(*n), sel) + sel_size, GFP_KERNEL); if (n == NULL) { err = -ENOBUFS; goto erridr; @@ -1092,7 +1098,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, } #endif - memcpy(&n->sel, s, sizeof(*s) + s->nkeys*sizeof(struct tc_u32_key)); + memcpy(&n->sel, s, sel_size); RCU_INIT_POINTER(n->ht_up, ht); n->handle = handle; n->fshift = s->hmask ? ffs(ntohl(s->hmask)) - 1 : 0; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 98541c6399db..411c40344b77 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -27,7 +27,6 @@ #include <linux/kmod.h> #include <linux/list.h> #include <linux/hrtimer.h> -#include <linux/lockdep.h> #include <linux/slab.h> #include <linux/hashtable.h> @@ -1053,10 +1052,6 @@ static int qdisc_block_indexes_set(struct Qdisc *sch, struct nlattr **tca, return 0; } -/* lockdep annotation is needed for ingress; egress gets it only for name */ -static struct lock_class_key qdisc_tx_lock; -static struct lock_class_key qdisc_rx_lock; - /* Allocate and initialize new qdisc. @@ -1121,7 +1116,6 @@ static struct Qdisc *qdisc_create(struct net_device *dev, if (handle == TC_H_INGRESS) { sch->flags |= TCQ_F_INGRESS; handle = TC_H_MAKE(TC_H_INGRESS, 0); - lockdep_set_class(qdisc_lock(sch), &qdisc_rx_lock); } else { if (handle == 0) { handle = qdisc_alloc_handle(dev); @@ -1129,7 +1123,6 @@ static struct Qdisc *qdisc_create(struct net_device *dev, if (handle == 0) goto err_out3; } - lockdep_set_class(qdisc_lock(sch), &qdisc_tx_lock); if (!netif_is_multiqueue(dev)) sch->flags |= TCQ_F_ONETXQUEUE; } diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 35fc7252187c..dc539295ae65 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -64,7 +64,6 @@ #include <linux/vmalloc.h> #include <linux/reciprocal_div.h> #include <net/netlink.h> -#include <linux/version.h> #include <linux/if_vlan.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> @@ -621,15 +620,20 @@ static bool cake_ddst(int flow_mode) } static u32 cake_hash(struct cake_tin_data *q, const struct sk_buff *skb, - int flow_mode) + int flow_mode, u16 flow_override, u16 host_override) { - u32 flow_hash = 0, srchost_hash, dsthost_hash; + u32 flow_hash = 0, srchost_hash = 0, dsthost_hash = 0; u16 reduced_hash, srchost_idx, dsthost_idx; struct flow_keys keys, host_keys; if (unlikely(flow_mode == CAKE_FLOW_NONE)) return 0; + /* If both overrides are set we can skip packet dissection entirely */ + if ((flow_override || !(flow_mode & CAKE_FLOW_FLOWS)) && + (host_override || !(flow_mode & CAKE_FLOW_HOSTS))) + goto skip_hash; + skb_flow_dissect_flow_keys(skb, &keys, FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); @@ -676,6 +680,14 @@ static u32 cake_hash(struct cake_tin_data *q, const struct sk_buff *skb, if (flow_mode & CAKE_FLOW_FLOWS) flow_hash = flow_hash_from_keys(&keys); +skip_hash: + if (flow_override) + flow_hash = flow_override - 1; + if (host_override) { + dsthost_hash = host_override - 1; + srchost_hash = host_override - 1; + } + if (!(flow_mode & CAKE_FLOW_FLOWS)) { if (flow_mode & CAKE_FLOW_SRC_IP) flow_hash ^= srchost_hash; @@ -800,7 +812,7 @@ static struct sk_buff *dequeue_head(struct cake_flow *flow) if (skb) { flow->head = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); } return skb; @@ -1240,7 +1252,7 @@ found: else flow->head = elig_ack->next; - elig_ack->next = NULL; + skb_mark_not_on_list(elig_ack); return elig_ack; } @@ -1571,7 +1583,7 @@ static u32 cake_classify(struct Qdisc *sch, struct cake_tin_data **t, struct cake_sched_data *q = qdisc_priv(sch); struct tcf_proto *filter; struct tcf_result res; - u32 flow = 0; + u16 flow = 0, host = 0; int result; filter = rcu_dereference_bh(q->filter_list); @@ -1595,10 +1607,12 @@ static u32 cake_classify(struct Qdisc *sch, struct cake_tin_data **t, #endif if (TC_H_MIN(res.classid) <= CAKE_QUEUES) flow = TC_H_MIN(res.classid); + if (TC_H_MAJ(res.classid) <= (CAKE_QUEUES << 16)) + host = TC_H_MAJ(res.classid) >> 16; } hash: *t = cake_select_tin(sch, skb); - return flow ?: cake_hash(*t, skb, flow_mode) + 1; + return cake_hash(*t, skb, flow_mode, flow, host) + 1; } static void cake_reconfigure(struct Qdisc *sch); @@ -1661,7 +1675,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, while (segs) { nskb = segs->next; - segs->next = NULL; + skb_mark_not_on_list(segs); qdisc_skb_cb(segs)->pkt_len = segs->len; cobalt_set_enqueue_time(segs, now); get_cobalt_cb(segs)->adjusted_len = cake_overhead(q, diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 4808713c73b9..b27ba36a269c 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -319,7 +319,7 @@ static struct sk_buff *fq_dequeue_head(struct Qdisc *sch, struct fq_flow *flow) if (skb) { flow->head = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); flow->qlen--; qdisc_qstats_backlog_dec(sch, skb); sch->q.qlen--; diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 6c0a9d5dbf94..cd04d40c30b6 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -124,7 +124,7 @@ static inline struct sk_buff *dequeue_head(struct fq_codel_flow *flow) struct sk_buff *skb = flow->head; flow->head = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); return skb; } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 69078c82963e..a64132a5db36 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -184,7 +184,7 @@ static void try_bulk_dequeue_skb(struct Qdisc *q, skb = nskb; (*packets)++; /* GSO counts as one pkt */ } - skb->next = NULL; + skb_mark_not_on_list(skb); } /* This variant of try_bulk_dequeue_skb() makes sure @@ -210,7 +210,7 @@ static void try_bulk_dequeue_skb_slow(struct Qdisc *q, skb = nskb; } while (++cnt < 8); (*packets) += cnt; - skb->next = NULL; + skb_mark_not_on_list(skb); } /* Note that dequeue_skb can possibly return a SKB list (via skb->next). diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index c3a8388dcdf6..9d6a47697406 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -330,7 +330,7 @@ static struct sk_buff *dequeue_head(struct wdrr_bucket *bucket) struct sk_buff *skb = bucket->head; bucket->head = skb->next; - skb->next = NULL; + skb_mark_not_on_list(skb); return skb; } diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 43c4bfe625a9..18ac2d6ca294 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -132,7 +132,7 @@ struct htb_class { struct htb_class_inner { struct htb_prio clprio[TC_HTB_NUMPRIO]; } inner; - } un; + }; s64 pq_key; int prio_activity; /* for which prios are we active */ @@ -411,13 +411,13 @@ static void htb_activate_prios(struct htb_sched *q, struct htb_class *cl) int prio = ffz(~m); m &= ~(1 << prio); - if (p->un.inner.clprio[prio].feed.rb_node) + if (p->inner.clprio[prio].feed.rb_node) /* parent already has its feed in use so that * reset bit in mask as parent is already ok */ mask &= ~(1 << prio); - htb_add_to_id_tree(&p->un.inner.clprio[prio].feed, cl, prio); + htb_add_to_id_tree(&p->inner.clprio[prio].feed, cl, prio); } p->prio_activity |= mask; cl = p; @@ -447,19 +447,19 @@ static void htb_deactivate_prios(struct htb_sched *q, struct htb_class *cl) int prio = ffz(~m); m &= ~(1 << prio); - if (p->un.inner.clprio[prio].ptr == cl->node + prio) { + if (p->inner.clprio[prio].ptr == cl->node + prio) { /* we are removing child which is pointed to from * parent feed - forget the pointer but remember * classid */ - p->un.inner.clprio[prio].last_ptr_id = cl->common.classid; - p->un.inner.clprio[prio].ptr = NULL; + p->inner.clprio[prio].last_ptr_id = cl->common.classid; + p->inner.clprio[prio].ptr = NULL; } htb_safe_rb_erase(cl->node + prio, - &p->un.inner.clprio[prio].feed); + &p->inner.clprio[prio].feed); - if (!p->un.inner.clprio[prio].feed.rb_node) + if (!p->inner.clprio[prio].feed.rb_node) mask |= 1 << prio; } @@ -555,7 +555,7 @@ htb_change_class_mode(struct htb_sched *q, struct htb_class *cl, s64 *diff) */ static inline void htb_activate(struct htb_sched *q, struct htb_class *cl) { - WARN_ON(cl->level || !cl->un.leaf.q || !cl->un.leaf.q->q.qlen); + WARN_ON(cl->level || !cl->leaf.q || !cl->leaf.q->q.qlen); if (!cl->prio_activity) { cl->prio_activity = 1 << cl->prio; @@ -577,22 +577,6 @@ static inline void htb_deactivate(struct htb_sched *q, struct htb_class *cl) cl->prio_activity = 0; } -static void htb_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch, - struct qdisc_skb_head *qh) -{ - struct sk_buff *last = qh->tail; - - if (last) { - skb->next = NULL; - last->next = skb; - qh->tail = skb; - } else { - qh->tail = skb; - qh->head = skb; - } - qh->qlen++; -} - static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch, struct sk_buff **to_free) { @@ -603,7 +587,7 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (cl == HTB_DIRECT) { /* enqueue to helper queue */ if (q->direct_queue.qlen < q->direct_qlen) { - htb_enqueue_tail(skb, sch, &q->direct_queue); + __qdisc_enqueue_tail(skb, &q->direct_queue); q->direct_pkts++; } else { return qdisc_drop(skb, sch, to_free); @@ -615,7 +599,7 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch, __qdisc_drop(skb, to_free); return ret; #endif - } else if ((ret = qdisc_enqueue(skb, cl->un.leaf.q, + } else if ((ret = qdisc_enqueue(skb, cl->leaf.q, to_free)) != NET_XMIT_SUCCESS) { if (net_xmit_drop_count(ret)) { qdisc_qstats_drop(sch); @@ -823,7 +807,7 @@ static struct htb_class *htb_lookup_leaf(struct htb_prio *hprio, const int prio) cl = rb_entry(*sp->pptr, struct htb_class, node[prio]); if (!cl->level) return cl; - clp = &cl->un.inner.clprio[prio]; + clp = &cl->inner.clprio[prio]; (++sp)->root = clp->feed.rb_node; sp->pptr = &clp->ptr; sp->pid = &clp->last_ptr_id; @@ -857,7 +841,7 @@ next: * graft operation on the leaf since last dequeue; * simply deactivate and skip such class */ - if (unlikely(cl->un.leaf.q->q.qlen == 0)) { + if (unlikely(cl->leaf.q->q.qlen == 0)) { struct htb_class *next; htb_deactivate(q, cl); @@ -873,12 +857,12 @@ next: goto next; } - skb = cl->un.leaf.q->dequeue(cl->un.leaf.q); + skb = cl->leaf.q->dequeue(cl->leaf.q); if (likely(skb != NULL)) break; - qdisc_warn_nonwc("htb", cl->un.leaf.q); - htb_next_rb_node(level ? &cl->parent->un.inner.clprio[prio].ptr: + qdisc_warn_nonwc("htb", cl->leaf.q); + htb_next_rb_node(level ? &cl->parent->inner.clprio[prio].ptr: &q->hlevel[0].hprio[prio].ptr); cl = htb_lookup_leaf(hprio, prio); @@ -886,16 +870,16 @@ next: if (likely(skb != NULL)) { bstats_update(&cl->bstats, skb); - cl->un.leaf.deficit[level] -= qdisc_pkt_len(skb); - if (cl->un.leaf.deficit[level] < 0) { - cl->un.leaf.deficit[level] += cl->quantum; - htb_next_rb_node(level ? &cl->parent->un.inner.clprio[prio].ptr : + cl->leaf.deficit[level] -= qdisc_pkt_len(skb); + if (cl->leaf.deficit[level] < 0) { + cl->leaf.deficit[level] += cl->quantum; + htb_next_rb_node(level ? &cl->parent->inner.clprio[prio].ptr : &q->hlevel[0].hprio[prio].ptr); } /* this used to be after charge_class but this constelation * gives us slightly better performance */ - if (!cl->un.leaf.q->q.qlen) + if (!cl->leaf.q->q.qlen) htb_deactivate(q, cl); htb_charge_class(q, cl, level, skb); } @@ -972,10 +956,10 @@ static void htb_reset(struct Qdisc *sch) for (i = 0; i < q->clhash.hashsize; i++) { hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) { if (cl->level) - memset(&cl->un.inner, 0, sizeof(cl->un.inner)); + memset(&cl->inner, 0, sizeof(cl->inner)); else { - if (cl->un.leaf.q) - qdisc_reset(cl->un.leaf.q); + if (cl->leaf.q) + qdisc_reset(cl->leaf.q); } cl->prio_activity = 0; cl->cmode = HTB_CAN_SEND; @@ -1098,8 +1082,8 @@ static int htb_dump_class(struct Qdisc *sch, unsigned long arg, */ tcm->tcm_parent = cl->parent ? cl->parent->common.classid : TC_H_ROOT; tcm->tcm_handle = cl->common.classid; - if (!cl->level && cl->un.leaf.q) - tcm->tcm_info = cl->un.leaf.q->handle; + if (!cl->level && cl->leaf.q) + tcm->tcm_info = cl->leaf.q->handle; nest = nla_nest_start(skb, TCA_OPTIONS); if (nest == NULL) @@ -1142,9 +1126,9 @@ htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d) }; __u32 qlen = 0; - if (!cl->level && cl->un.leaf.q) { - qlen = cl->un.leaf.q->q.qlen; - qs.backlog = cl->un.leaf.q->qstats.backlog; + if (!cl->level && cl->leaf.q) { + qlen = cl->leaf.q->q.qlen; + qs.backlog = cl->leaf.q->qstats.backlog; } cl->xstats.tokens = clamp_t(s64, PSCHED_NS2TICKS(cl->tokens), INT_MIN, INT_MAX); @@ -1172,14 +1156,14 @@ static int htb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, cl->common.classid, extack)) == NULL) return -ENOBUFS; - *old = qdisc_replace(sch, new, &cl->un.leaf.q); + *old = qdisc_replace(sch, new, &cl->leaf.q); return 0; } static struct Qdisc *htb_leaf(struct Qdisc *sch, unsigned long arg) { struct htb_class *cl = (struct htb_class *)arg; - return !cl->level ? cl->un.leaf.q : NULL; + return !cl->level ? cl->leaf.q : NULL; } static void htb_qlen_notify(struct Qdisc *sch, unsigned long arg) @@ -1205,15 +1189,15 @@ static void htb_parent_to_leaf(struct htb_sched *q, struct htb_class *cl, { struct htb_class *parent = cl->parent; - WARN_ON(cl->level || !cl->un.leaf.q || cl->prio_activity); + WARN_ON(cl->level || !cl->leaf.q || cl->prio_activity); if (parent->cmode != HTB_CAN_SEND) htb_safe_rb_erase(&parent->pq_node, &q->hlevel[parent->level].wait_pq); parent->level = 0; - memset(&parent->un.inner, 0, sizeof(parent->un.inner)); - parent->un.leaf.q = new_q ? new_q : &noop_qdisc; + memset(&parent->inner, 0, sizeof(parent->inner)); + parent->leaf.q = new_q ? new_q : &noop_qdisc; parent->tokens = parent->buffer; parent->ctokens = parent->cbuffer; parent->t_c = ktime_get_ns(); @@ -1223,8 +1207,8 @@ static void htb_parent_to_leaf(struct htb_sched *q, struct htb_class *cl, static void htb_destroy_class(struct Qdisc *sch, struct htb_class *cl) { if (!cl->level) { - WARN_ON(!cl->un.leaf.q); - qdisc_destroy(cl->un.leaf.q); + WARN_ON(!cl->leaf.q); + qdisc_destroy(cl->leaf.q); } gen_kill_estimator(&cl->rate_est); tcf_block_put(cl->block); @@ -1286,11 +1270,11 @@ static int htb_delete(struct Qdisc *sch, unsigned long arg) sch_tree_lock(sch); if (!cl->level) { - unsigned int qlen = cl->un.leaf.q->q.qlen; - unsigned int backlog = cl->un.leaf.q->qstats.backlog; + unsigned int qlen = cl->leaf.q->q.qlen; + unsigned int backlog = cl->leaf.q->qstats.backlog; - qdisc_reset(cl->un.leaf.q); - qdisc_tree_reduce_backlog(cl->un.leaf.q, qlen, backlog); + qdisc_reset(cl->leaf.q); + qdisc_tree_reduce_backlog(cl->leaf.q, qlen, backlog); } /* delete from hash and active; remainder in destroy_class */ @@ -1419,13 +1403,13 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, classid, NULL); sch_tree_lock(sch); if (parent && !parent->level) { - unsigned int qlen = parent->un.leaf.q->q.qlen; - unsigned int backlog = parent->un.leaf.q->qstats.backlog; + unsigned int qlen = parent->leaf.q->q.qlen; + unsigned int backlog = parent->leaf.q->qstats.backlog; /* turn parent into inner node */ - qdisc_reset(parent->un.leaf.q); - qdisc_tree_reduce_backlog(parent->un.leaf.q, qlen, backlog); - qdisc_destroy(parent->un.leaf.q); + qdisc_reset(parent->leaf.q); + qdisc_tree_reduce_backlog(parent->leaf.q, qlen, backlog); + qdisc_destroy(parent->leaf.q); if (parent->prio_activity) htb_deactivate(q, parent); @@ -1436,10 +1420,10 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, } parent->level = (parent->parent ? parent->parent->level : TC_HTB_MAXDEPTH) - 1; - memset(&parent->un.inner, 0, sizeof(parent->un.inner)); + memset(&parent->inner, 0, sizeof(parent->inner)); } /* leaf (we) needs elementary qdisc */ - cl->un.leaf.q = new_q ? new_q : &noop_qdisc; + cl->leaf.q = new_q ? new_q : &noop_qdisc; cl->common.classid = classid; cl->parent = parent; @@ -1455,8 +1439,8 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, qdisc_class_hash_insert(&q->clhash, &cl->common); if (parent) parent->children++; - if (cl->un.leaf.q != &noop_qdisc) - qdisc_hash_add(cl->un.leaf.q, true); + if (cl->leaf.q != &noop_qdisc) + qdisc_hash_add(cl->leaf.q, true); } else { if (tca[TCA_RATE]) { err = gen_replace_estimator(&cl->bstats, NULL, @@ -1478,7 +1462,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, psched_ratecfg_precompute(&cl->ceil, &hopt->ceil, ceil64); /* it used to be a nasty bug here, we have to check that node - * is really leaf before changing cl->un.leaf ! + * is really leaf before changing cl->leaf ! */ if (!cl->level) { u64 quantum = cl->rate.rate_bytes_ps; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index ad18a2052416..506e1960ed7f 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -412,16 +412,6 @@ static struct sk_buff *netem_segment(struct sk_buff *skb, struct Qdisc *sch, return segs; } -static void netem_enqueue_skb_head(struct qdisc_skb_head *qh, struct sk_buff *skb) -{ - skb->next = qh->head; - - if (!qh->head) - qh->tail = skb; - qh->head = skb; - qh->qlen++; -} - /* * Insert one skb into qdisc. * Note: parent depends on return value to account for queue length. @@ -570,7 +560,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, cb->time_to_send = ktime_get_ns(); q->counter = 0; - netem_enqueue_skb_head(&sch->q, skb); + __qdisc_enqueue_head(skb, &sch->q); sch->qstats.requeues++; } @@ -578,7 +568,7 @@ finish_segs: if (segs) { while (segs) { skb2 = segs->next; - segs->next = NULL; + skb_mark_not_on_list(segs); qdisc_skb_cb(segs)->pkt_len = segs->len; last_len = segs->len; rc = qdisc_enqueue(segs, sch, to_free); diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 6f74a426f159..a4530e85bd02 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -162,7 +162,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch, nb = 0; while (segs) { nskb = segs->next; - segs->next = NULL; + skb_mark_not_on_list(segs); qdisc_skb_cb(segs)->pkt_len = segs->len; len += segs->len; ret = qdisc_enqueue(segs, q->qdisc, to_free); diff --git a/net/sctp/proc.c b/net/sctp/proc.c index ef5c9a82d4e8..a644292f9faf 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -215,7 +215,6 @@ static const struct seq_operations sctp_eps_ops = { struct sctp_ht_iter { struct seq_net_private p; struct rhashtable_iter hti; - int start_fail; }; static void *sctp_transport_seq_start(struct seq_file *seq, loff_t *pos) @@ -224,7 +223,6 @@ static void *sctp_transport_seq_start(struct seq_file *seq, loff_t *pos) sctp_transport_walk_start(&iter->hti); - iter->start_fail = 0; return sctp_transport_get_idx(seq_file_net(seq), &iter->hti, *pos); } @@ -232,8 +230,6 @@ static void sctp_transport_seq_stop(struct seq_file *seq, void *v) { struct sctp_ht_iter *iter = seq->private; - if (iter->start_fail) - return; sctp_transport_walk_stop(&iter->hti); } @@ -264,8 +260,6 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v) } transport = (struct sctp_transport *)v; - if (!sctp_transport_hold(transport)) - return 0; assoc = transport->asoc; epb = &assoc->base; sk = epb->sk; @@ -322,8 +316,6 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v) } transport = (struct sctp_transport *)v; - if (!sctp_transport_hold(transport)) - return 0; assoc = transport->asoc; list_for_each_entry_rcu(tsp, &assoc->peer.transport_addr_list, diff --git a/net/sctp/socket.c b/net/sctp/socket.c index e96b15a66aba..f73e9d38d5ba 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2658,20 +2658,23 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, } if (params->spp_flags & SPP_IPV6_FLOWLABEL) { - if (trans && trans->ipaddr.sa.sa_family == AF_INET6) { - trans->flowlabel = params->spp_ipv6_flowlabel & - SCTP_FLOWLABEL_VAL_MASK; - trans->flowlabel |= SCTP_FLOWLABEL_SET_MASK; - } else if (asoc) { - list_for_each_entry(trans, - &asoc->peer.transport_addr_list, - transports) { - if (trans->ipaddr.sa.sa_family != AF_INET6) - continue; + if (trans) { + if (trans->ipaddr.sa.sa_family == AF_INET6) { trans->flowlabel = params->spp_ipv6_flowlabel & SCTP_FLOWLABEL_VAL_MASK; trans->flowlabel |= SCTP_FLOWLABEL_SET_MASK; } + } else if (asoc) { + struct sctp_transport *t; + + list_for_each_entry(t, &asoc->peer.transport_addr_list, + transports) { + if (t->ipaddr.sa.sa_family != AF_INET6) + continue; + t->flowlabel = params->spp_ipv6_flowlabel & + SCTP_FLOWLABEL_VAL_MASK; + t->flowlabel |= SCTP_FLOWLABEL_SET_MASK; + } asoc->flowlabel = params->spp_ipv6_flowlabel & SCTP_FLOWLABEL_VAL_MASK; asoc->flowlabel |= SCTP_FLOWLABEL_SET_MASK; @@ -2687,12 +2690,13 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, trans->dscp = params->spp_dscp & SCTP_DSCP_VAL_MASK; trans->dscp |= SCTP_DSCP_SET_MASK; } else if (asoc) { - list_for_each_entry(trans, - &asoc->peer.transport_addr_list, + struct sctp_transport *t; + + list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) { - trans->dscp = params->spp_dscp & - SCTP_DSCP_VAL_MASK; - trans->dscp |= SCTP_DSCP_SET_MASK; + t->dscp = params->spp_dscp & + SCTP_DSCP_VAL_MASK; + t->dscp |= SCTP_DSCP_SET_MASK; } asoc->dscp = params->spp_dscp & SCTP_DSCP_VAL_MASK; asoc->dscp |= SCTP_DSCP_SET_MASK; @@ -5005,9 +5009,14 @@ struct sctp_transport *sctp_transport_get_next(struct net *net, break; } + if (!sctp_transport_hold(t)) + continue; + if (net_eq(sock_net(t->asoc->base.sk), net) && t->asoc->peer.primary_path == t) break; + + sctp_transport_put(t); } return t; @@ -5017,13 +5026,18 @@ struct sctp_transport *sctp_transport_get_idx(struct net *net, struct rhashtable_iter *iter, int pos) { - void *obj = SEQ_START_TOKEN; + struct sctp_transport *t; - while (pos && (obj = sctp_transport_get_next(net, iter)) && - !IS_ERR(obj)) - pos--; + if (!pos) + return SEQ_START_TOKEN; - return obj; + while ((t = sctp_transport_get_next(net, iter)) && !IS_ERR(t)) { + if (!--pos) + break; + sctp_transport_put(t); + } + + return t; } int sctp_for_each_endpoint(int (*cb)(struct sctp_endpoint *, void *), @@ -5082,8 +5096,6 @@ again: tsp = sctp_transport_get_idx(net, &hti, *pos + 1); for (; !IS_ERR_OR_NULL(tsp); tsp = sctp_transport_get_next(net, &hti)) { - if (!sctp_transport_hold(tsp)) - continue; ret = cb(tsp, p); if (ret) break; diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c index 0b427100b0d4..331cc734e3db 100644 --- a/net/sctp/ulpqueue.c +++ b/net/sctp/ulpqueue.c @@ -459,7 +459,7 @@ static struct sctp_ulpevent *sctp_ulpq_retrieve_reassembled(struct sctp_ulpq *ul * element in the queue, then count it towards * possible PD. */ - if (pos == ulpq->reasm.next) { + if (skb_queue_is_first(&ulpq->reasm, pos)) { pd_first = pos; pd_last = pos; pd_len = pos->len; diff --git a/net/socket.c b/net/socket.c index e6945e318f02..01f3f8f32d6f 100644 --- a/net/socket.c +++ b/net/socket.c @@ -941,7 +941,8 @@ void dlci_ioctl_set(int (*hook) (unsigned int, void __user *)) EXPORT_SYMBOL(dlci_ioctl_set); static long sock_do_ioctl(struct net *net, struct socket *sock, - unsigned int cmd, unsigned long arg) + unsigned int cmd, unsigned long arg, + unsigned int ifreq_size) { int err; void __user *argp = (void __user *)arg; @@ -967,11 +968,11 @@ static long sock_do_ioctl(struct net *net, struct socket *sock, } else { struct ifreq ifr; bool need_copyout; - if (copy_from_user(&ifr, argp, sizeof(struct ifreq))) + if (copy_from_user(&ifr, argp, ifreq_size)) return -EFAULT; err = dev_ioctl(net, cmd, &ifr, &need_copyout); if (!err && need_copyout) - if (copy_to_user(argp, &ifr, sizeof(struct ifreq))) + if (copy_to_user(argp, &ifr, ifreq_size)) return -EFAULT; } return err; @@ -1070,7 +1071,8 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) err = open_related_ns(&net->ns, get_net_ns); break; default: - err = sock_do_ioctl(net, sock, cmd, arg); + err = sock_do_ioctl(net, sock, cmd, arg, + sizeof(struct ifreq)); break; } return err; @@ -2750,7 +2752,8 @@ static int do_siocgstamp(struct net *net, struct socket *sock, int err; set_fs(KERNEL_DS); - err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv); + err = sock_do_ioctl(net, sock, cmd, (unsigned long)&ktv, + sizeof(struct compat_ifreq)); set_fs(old_fs); if (!err) err = compat_put_timeval(&ktv, up); @@ -2766,7 +2769,8 @@ static int do_siocgstampns(struct net *net, struct socket *sock, int err; set_fs(KERNEL_DS); - err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts); + err = sock_do_ioctl(net, sock, cmd, (unsigned long)&kts, + sizeof(struct compat_ifreq)); set_fs(old_fs); if (!err) err = compat_put_timespec(&kts, up); @@ -3072,7 +3076,8 @@ static int routing_ioctl(struct net *net, struct socket *sock, } set_fs(KERNEL_DS); - ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r); + ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r, + sizeof(struct compat_ifreq)); set_fs(old_fs); out: @@ -3185,7 +3190,8 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, case SIOCBONDSETHWADDR: case SIOCBONDCHANGEACTIVE: case SIOCGIFNAME: - return sock_do_ioctl(net, sock, cmd, arg); + return sock_do_ioctl(net, sock, cmd, arg, + sizeof(struct compat_ifreq)); } return -ENOIOCTLCMD; diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 9ee6cfea56dd..d8026543bf4c 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -51,12 +51,12 @@ const char tipc_bclink_name[] = "broadcast-link"; * struct tipc_bc_base - base structure for keeping broadcast send state * @link: broadcast send link structure * @inputq: data input queue; will only carry SOCK_WAKEUP messages - * @dest: array keeping number of reachable destinations per bearer + * @dests: array keeping number of reachable destinations per bearer * @primary_bearer: a bearer having links to all broadcast destinations, if any * @bcast_support: indicates if primary bearer, if any, supports broadcast * @rcast_support: indicates if all peer nodes support replicast * @rc_ratio: dest count as percentage of cluster size where send method changes - * @bc_threshold: calculated drom rc_ratio; if dests > threshold use broadcast + * @bc_threshold: calculated from rc_ratio; if dests > threshold use broadcast */ struct tipc_bc_base { struct tipc_link *link; diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 418f03d0be90..91891041e5e1 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -577,7 +577,7 @@ static int tipc_l2_rcv_msg(struct sk_buff *skb, struct net_device *dev, rcu_dereference_rtnl(orig_dev->tipc_ptr); if (likely(b && test_bit(0, &b->up) && (skb->pkt_type <= PACKET_MULTICAST))) { - skb->next = NULL; + skb_mark_not_on_list(skb); tipc_rcv(dev_net(b->pt.dev), skb, b); rcu_read_unlock(); return NET_RX_SUCCESS; diff --git a/net/tipc/diag.c b/net/tipc/diag.c index aaabb0b776dd..73137f4aeb68 100644 --- a/net/tipc/diag.c +++ b/net/tipc/diag.c @@ -84,7 +84,9 @@ static int tipc_sock_diag_handler_dump(struct sk_buff *skb, if (h->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { + .start = tipc_dump_start, .dump = tipc_diag_dump, + .done = tipc_dump_done, }; netlink_dump_start(net->diag_nlsk, skb, h, &c); return 0; diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 88f027b502f6..66d5b2c5987a 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -980,20 +980,17 @@ int tipc_nl_name_table_dump(struct sk_buff *skb, struct netlink_callback *cb) struct tipc_dest *tipc_dest_find(struct list_head *l, u32 node, u32 port) { - u64 value = (u64)node << 32 | port; struct tipc_dest *dst; list_for_each_entry(dst, l, list) { - if (dst->value != value) - continue; - return dst; + if (dst->node == node && dst->port == port) + return dst; } return NULL; } bool tipc_dest_push(struct list_head *l, u32 node, u32 port) { - u64 value = (u64)node << 32 | port; struct tipc_dest *dst; if (tipc_dest_find(l, node, port)) @@ -1002,7 +999,8 @@ bool tipc_dest_push(struct list_head *l, u32 node, u32 port) dst = kmalloc(sizeof(*dst), GFP_ATOMIC); if (unlikely(!dst)) return false; - dst->value = value; + dst->node = node; + dst->port = port; list_add(&dst->list, l); return true; } diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h index 0febba41da86..892bd750b85f 100644 --- a/net/tipc/name_table.h +++ b/net/tipc/name_table.h @@ -133,13 +133,8 @@ void tipc_nametbl_stop(struct net *net); struct tipc_dest { struct list_head list; - union { - struct { - u32 port; - u32 node; - }; - u64 value; - }; + u32 port; + u32 node; }; struct tipc_dest *tipc_dest_find(struct list_head *l, u32 node, u32 port); diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c index 6ff2254088f6..99ee419210ba 100644 --- a/net/tipc/netlink.c +++ b/net/tipc/netlink.c @@ -167,7 +167,9 @@ static const struct genl_ops tipc_genl_v2_ops[] = { }, { .cmd = TIPC_NL_SOCK_GET, + .start = tipc_dump_start, .dumpit = tipc_nl_sk_dump, + .done = tipc_dump_done, .policy = tipc_nl_policy, }, { diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index a2f76743c73a..6376467e78f8 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -185,6 +185,10 @@ static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, return -ENOMEM; buf->sk = msg->dst_sk; + if (__tipc_dump_start(&cb, msg->net)) { + kfree_skb(buf); + return -ENOMEM; + } do { int rem; @@ -216,6 +220,7 @@ static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, err = 0; err_out: + tipc_dump_done(&cb); kfree_skb(buf); if (err == -EMSGSIZE) { diff --git a/net/tipc/socket.c b/net/tipc/socket.c index c1e93c9515bc..3f03ddd0e35b 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -576,6 +576,7 @@ static int tipc_release(struct socket *sock) sk_stop_timer(sk, &sk->sk_timer); tipc_sk_remove(tsk); + sock_orphan(sk); /* Reject any messages that accumulated in backlog queue */ release_sock(sk); tipc_dest_list_purge(&tsk->cong_links); @@ -2672,6 +2673,8 @@ void tipc_sk_reinit(struct net *net) rhashtable_walk_stop(&iter); } while (tsk == ERR_PTR(-EAGAIN)); + + rhashtable_walk_exit(&iter); } static struct tipc_sock *tipc_sk_lookup(struct net *net, u32 portid) @@ -3227,45 +3230,74 @@ int tipc_nl_sk_walk(struct sk_buff *skb, struct netlink_callback *cb, struct netlink_callback *cb, struct tipc_sock *tsk)) { - struct net *net = sock_net(skb->sk); - struct tipc_net *tn = tipc_net(net); - const struct bucket_table *tbl; - u32 prev_portid = cb->args[1]; - u32 tbl_id = cb->args[0]; - struct rhash_head *pos; + struct rhashtable_iter *iter = (void *)cb->args[4]; struct tipc_sock *tsk; int err; - rcu_read_lock(); - tbl = rht_dereference_rcu((&tn->sk_rht)->tbl, &tn->sk_rht); - for (; tbl_id < tbl->size; tbl_id++) { - rht_for_each_entry_rcu(tsk, pos, tbl, tbl_id, node) { - spin_lock_bh(&tsk->sk.sk_lock.slock); - if (prev_portid && prev_portid != tsk->portid) { - spin_unlock_bh(&tsk->sk.sk_lock.slock); + rhashtable_walk_start(iter); + while ((tsk = rhashtable_walk_next(iter)) != NULL) { + if (IS_ERR(tsk)) { + err = PTR_ERR(tsk); + if (err == -EAGAIN) { + err = 0; continue; } + break; + } - err = skb_handler(skb, cb, tsk); - if (err) { - prev_portid = tsk->portid; - spin_unlock_bh(&tsk->sk.sk_lock.slock); - goto out; - } - - prev_portid = 0; - spin_unlock_bh(&tsk->sk.sk_lock.slock); + sock_hold(&tsk->sk); + rhashtable_walk_stop(iter); + lock_sock(&tsk->sk); + err = skb_handler(skb, cb, tsk); + if (err) { + release_sock(&tsk->sk); + sock_put(&tsk->sk); + goto out; } + release_sock(&tsk->sk); + rhashtable_walk_start(iter); + sock_put(&tsk->sk); } + rhashtable_walk_stop(iter); out: - rcu_read_unlock(); - cb->args[0] = tbl_id; - cb->args[1] = prev_portid; - return skb->len; } EXPORT_SYMBOL(tipc_nl_sk_walk); +int tipc_dump_start(struct netlink_callback *cb) +{ + return __tipc_dump_start(cb, sock_net(cb->skb->sk)); +} +EXPORT_SYMBOL(tipc_dump_start); + +int __tipc_dump_start(struct netlink_callback *cb, struct net *net) +{ + /* tipc_nl_name_table_dump() uses cb->args[0...3]. */ + struct rhashtable_iter *iter = (void *)cb->args[4]; + struct tipc_net *tn = tipc_net(net); + + if (!iter) { + iter = kmalloc(sizeof(*iter), GFP_KERNEL); + if (!iter) + return -ENOMEM; + + cb->args[4] = (long)iter; + } + + rhashtable_walk_enter(&tn->sk_rht, iter); + return 0; +} + +int tipc_dump_done(struct netlink_callback *cb) +{ + struct rhashtable_iter *hti = (void *)cb->args[4]; + + rhashtable_walk_exit(hti); + kfree(hti); + return 0; +} +EXPORT_SYMBOL(tipc_dump_done); + int tipc_sk_fill_sock_diag(struct sk_buff *skb, struct netlink_callback *cb, struct tipc_sock *tsk, u32 sk_filter_state, u64 (*tipc_diag_gen_cookie)(struct sock *sk)) diff --git a/net/tipc/socket.h b/net/tipc/socket.h index aff9b2ae5a1f..5e575f205afe 100644 --- a/net/tipc/socket.h +++ b/net/tipc/socket.h @@ -68,4 +68,7 @@ int tipc_nl_sk_walk(struct sk_buff *skb, struct netlink_callback *cb, int (*skb_handler)(struct sk_buff *skb, struct netlink_callback *cb, struct tipc_sock *tsk)); +int tipc_dump_start(struct netlink_callback *cb); +int __tipc_dump_start(struct netlink_callback *cb, struct net *net); +int tipc_dump_done(struct netlink_callback *cb); #endif diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index c8e34ef22c30..d8956f7daac4 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -57,16 +57,12 @@ * @idr_lock: protect the connection identifier set * @idr_in_use: amount of allocated identifier entry * @net: network namspace instance - * @rcvbuf_cache: memory cache of server receive buffer + * @awork: accept work item * @rcv_wq: receive workqueue * @send_wq: send workqueue * @max_rcvbuf_size: maximum permitted receive message length - * @tipc_conn_new: callback will be called when new connection is incoming - * @tipc_conn_release: callback will be called before releasing the connection - * @tipc_conn_recvmsg: callback will be called when message arrives + * @listener: topsrv listener socket * @name: server name - * @imp: message importance - * @type: socket type */ struct tipc_topsrv { struct idr conn_idr; @@ -90,9 +86,7 @@ struct tipc_topsrv { * @server: pointer to connected server * @sub_list: lsit to all pertaing subscriptions * @sub_lock: lock protecting the subscription list - * @outqueue_lock: control access to the outqueue * @rwork: receive work item - * @rx_action: what to do when connection socket is active * @outqueue: pointer to first outbound message in queue * @outqueue_lock: control access to the outqueue * @swork: send work item @@ -313,8 +307,8 @@ static void tipc_conn_send_work(struct work_struct *work) conn_put(con); } -/* tipc_conn_queue_evt() - interrupt level call from a subscription instance - * The queued work is launched into tipc_send_work()->tipc_send_to_sock() +/* tipc_topsrv_queue_evt() - interrupt level call from a subscription instance + * The queued work is launched into tipc_conn_send_work()->tipc_conn_send_to_sock() */ void tipc_topsrv_queue_evt(struct net *net, int conid, u32 event, struct tipc_event *evt) diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 292742e50bfa..961b07d4d41c 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -686,7 +686,7 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx) goto free_marker_record; } - crypto_info = &ctx->crypto_send; + crypto_info = &ctx->crypto_send.info; switch (crypto_info->cipher_type) { case TLS_CIPHER_AES_GCM_128: nonce_size = TLS_CIPHER_AES_GCM_128_IV_SIZE; @@ -780,7 +780,7 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx) ctx->priv_ctx_tx = offload_ctx; rc = netdev->tlsdev_ops->tls_dev_add(netdev, sk, TLS_OFFLOAD_CTX_DIR_TX, - &ctx->crypto_send, + &ctx->crypto_send.info, tcp_sk(sk)->write_seq); if (rc) goto release_netdev; @@ -862,7 +862,7 @@ int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx) goto release_ctx; rc = netdev->tlsdev_ops->tls_dev_add(netdev, sk, TLS_OFFLOAD_CTX_DIR_RX, - &ctx->crypto_recv, + &ctx->crypto_recv.info, tcp_sk(sk)->copied_seq); if (rc) { pr_err_ratelimited("%s: The netdev has refused to offload this socket\n", diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c index 6102169239d1..450a6dbc5a88 100644 --- a/net/tls/tls_device_fallback.c +++ b/net/tls/tls_device_fallback.c @@ -320,7 +320,7 @@ static struct sk_buff *tls_enc_skb(struct tls_context *tls_ctx, goto free_req; iv = buf; - memcpy(iv, tls_ctx->crypto_send_aes_gcm_128.salt, + memcpy(iv, tls_ctx->crypto_send.aes_gcm_128.salt, TLS_CIPHER_AES_GCM_128_SALT_SIZE); aad = buf + TLS_CIPHER_AES_GCM_128_SALT_SIZE + TLS_CIPHER_AES_GCM_128_IV_SIZE; diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 93c0c225ab34..523622dc74f8 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -213,9 +213,14 @@ static void tls_write_space(struct sock *sk) { struct tls_context *ctx = tls_get_ctx(sk); - /* We are already sending pages, ignore notification */ - if (ctx->in_tcp_sendpages) + /* If in_tcp_sendpages call lower protocol write space handler + * to ensure we wake up any waiting operations there. For example + * if do_tcp_sendpages where to call sk_wait_event. + */ + if (ctx->in_tcp_sendpages) { + ctx->sk_write_space(sk); return; + } if (!sk->sk_write_pending && tls_is_pending_closed_record(ctx)) { gfp_t sk_allocation = sk->sk_allocation; @@ -236,6 +241,16 @@ static void tls_write_space(struct sock *sk) ctx->sk_write_space(sk); } +static void tls_ctx_free(struct tls_context *ctx) +{ + if (!ctx) + return; + + memzero_explicit(&ctx->crypto_send, sizeof(ctx->crypto_send)); + memzero_explicit(&ctx->crypto_recv, sizeof(ctx->crypto_recv)); + kfree(ctx); +} + static void tls_sk_proto_close(struct sock *sk, long timeout) { struct tls_context *ctx = tls_get_ctx(sk); @@ -289,7 +304,7 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) #else { #endif - kfree(ctx); + tls_ctx_free(ctx); ctx = NULL; } @@ -300,7 +315,7 @@ skip_tx_cleanup: * for sk->sk_prot->unhash [tls_hw_unhash] */ if (free_ctx) - kfree(ctx); + tls_ctx_free(ctx); } static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval, @@ -325,7 +340,7 @@ static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval, } /* get user crypto info */ - crypto_info = &ctx->crypto_send; + crypto_info = &ctx->crypto_send.info; if (!TLS_CRYPTO_INFO_READY(crypto_info)) { rc = -EBUSY; @@ -412,9 +427,9 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval, } if (tx) - crypto_info = &ctx->crypto_send; + crypto_info = &ctx->crypto_send.info; else - crypto_info = &ctx->crypto_recv; + crypto_info = &ctx->crypto_recv.info; /* Currently we don't support set crypto info more than one time */ if (TLS_CRYPTO_INFO_READY(crypto_info)) { @@ -494,7 +509,7 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval, goto out; err_crypto_info: - memset(crypto_info, 0, sizeof(*crypto_info)); + memzero_explicit(crypto_info, sizeof(union tls_crypto_context)); out: return rc; } diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 52fbe727d7c1..5ff51bac8b46 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -43,12 +43,133 @@ #define MAX_IV_SIZE TLS_CIPHER_AES_GCM_128_IV_SIZE +static int __skb_nsg(struct sk_buff *skb, int offset, int len, + unsigned int recursion_level) +{ + int start = skb_headlen(skb); + int i, chunk = start - offset; + struct sk_buff *frag_iter; + int elt = 0; + + if (unlikely(recursion_level >= 24)) + return -EMSGSIZE; + + if (chunk > 0) { + if (chunk > len) + chunk = len; + elt++; + len -= chunk; + if (len == 0) + return elt; + offset += chunk; + } + + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + int end; + + WARN_ON(start > offset + len); + + end = start + skb_frag_size(&skb_shinfo(skb)->frags[i]); + chunk = end - offset; + if (chunk > 0) { + if (chunk > len) + chunk = len; + elt++; + len -= chunk; + if (len == 0) + return elt; + offset += chunk; + } + start = end; + } + + if (unlikely(skb_has_frag_list(skb))) { + skb_walk_frags(skb, frag_iter) { + int end, ret; + + WARN_ON(start > offset + len); + + end = start + frag_iter->len; + chunk = end - offset; + if (chunk > 0) { + if (chunk > len) + chunk = len; + ret = __skb_nsg(frag_iter, offset - start, chunk, + recursion_level + 1); + if (unlikely(ret < 0)) + return ret; + elt += ret; + len -= chunk; + if (len == 0) + return elt; + offset += chunk; + } + start = end; + } + } + BUG_ON(len); + return elt; +} + +/* Return the number of scatterlist elements required to completely map the + * skb, or -EMSGSIZE if the recursion depth is exceeded. + */ +static int skb_nsg(struct sk_buff *skb, int offset, int len) +{ + return __skb_nsg(skb, offset, len, 0); +} + +static void tls_decrypt_done(struct crypto_async_request *req, int err) +{ + struct aead_request *aead_req = (struct aead_request *)req; + struct scatterlist *sgout = aead_req->dst; + struct tls_sw_context_rx *ctx; + struct tls_context *tls_ctx; + struct scatterlist *sg; + struct sk_buff *skb; + unsigned int pages; + int pending; + + skb = (struct sk_buff *)req->data; + tls_ctx = tls_get_ctx(skb->sk); + ctx = tls_sw_ctx_rx(tls_ctx); + pending = atomic_dec_return(&ctx->decrypt_pending); + + /* Propagate if there was an err */ + if (err) { + ctx->async_wait.err = err; + tls_err_abort(skb->sk, err); + } + + /* After using skb->sk to propagate sk through crypto async callback + * we need to NULL it again. + */ + skb->sk = NULL; + + /* Release the skb, pages and memory allocated for crypto req */ + kfree_skb(skb); + + /* Skip the first S/G entry as it points to AAD */ + for_each_sg(sg_next(sgout), sg, UINT_MAX, pages) { + if (!sg) + break; + put_page(sg_page(sg)); + } + + kfree(aead_req); + + if (!pending && READ_ONCE(ctx->async_notify)) + complete(&ctx->async_wait.completion); +} + static int tls_do_decryption(struct sock *sk, + struct sk_buff *skb, struct scatterlist *sgin, struct scatterlist *sgout, char *iv_recv, size_t data_len, - struct aead_request *aead_req) + struct aead_request *aead_req, + bool async) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); @@ -59,10 +180,36 @@ static int tls_do_decryption(struct sock *sk, aead_request_set_crypt(aead_req, sgin, sgout, data_len + tls_ctx->rx.tag_size, (u8 *)iv_recv); - aead_request_set_callback(aead_req, CRYPTO_TFM_REQ_MAY_BACKLOG, - crypto_req_done, &ctx->async_wait); - ret = crypto_wait_req(crypto_aead_decrypt(aead_req), &ctx->async_wait); + if (async) { + /* Using skb->sk to push sk through to crypto async callback + * handler. This allows propagating errors up to the socket + * if needed. It _must_ be cleared in the async handler + * before kfree_skb is called. We _know_ skb->sk is NULL + * because it is a clone from strparser. + */ + skb->sk = sk; + aead_request_set_callback(aead_req, + CRYPTO_TFM_REQ_MAY_BACKLOG, + tls_decrypt_done, skb); + atomic_inc(&ctx->decrypt_pending); + } else { + aead_request_set_callback(aead_req, + CRYPTO_TFM_REQ_MAY_BACKLOG, + crypto_req_done, &ctx->async_wait); + } + + ret = crypto_aead_decrypt(aead_req); + if (ret == -EINPROGRESS) { + if (async) + return ret; + + ret = crypto_wait_req(ret, &ctx->async_wait); + } + + if (async) + atomic_dec(&ctx->decrypt_pending); + return ret; } @@ -125,6 +272,9 @@ static int alloc_encrypted_sg(struct sock *sk, int len) &ctx->sg_encrypted_num_elem, &ctx->sg_encrypted_size, 0); + if (rc == -ENOSPC) + ctx->sg_encrypted_num_elem = ARRAY_SIZE(ctx->sg_encrypted_data); + return rc; } @@ -138,6 +288,9 @@ static int alloc_plaintext_sg(struct sock *sk, int len) &ctx->sg_plaintext_num_elem, &ctx->sg_plaintext_size, tls_ctx->pending_open_record_frags); + if (rc == -ENOSPC) + ctx->sg_plaintext_num_elem = ARRAY_SIZE(ctx->sg_plaintext_data); + return rc; } @@ -348,7 +501,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); - int ret = 0; + int ret; int required_size; long timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); bool eor = !(msg->msg_flags & MSG_MORE); @@ -364,7 +517,8 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) lock_sock(sk); - if (tls_complete_pending_work(sk, tls_ctx, msg->msg_flags, &timeo)) + ret = tls_complete_pending_work(sk, tls_ctx, msg->msg_flags, &timeo); + if (ret) goto send_end; if (unlikely(msg->msg_controllen)) { @@ -499,7 +653,7 @@ int tls_sw_sendpage(struct sock *sk, struct page *page, { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); - int ret = 0; + int ret; long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); bool eor; size_t orig_size = size; @@ -519,7 +673,8 @@ int tls_sw_sendpage(struct sock *sk, struct page *page, sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); - if (tls_complete_pending_work(sk, tls_ctx, flags, &timeo)) + ret = tls_complete_pending_work(sk, tls_ctx, flags, &timeo); + if (ret) goto sendpage_end; /* Call the sk_stream functions to manage the sndbuf mem. */ @@ -678,12 +833,14 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb, n_sgout = iov_iter_npages(out_iov, INT_MAX) + 1; else n_sgout = sg_nents(out_sg); + n_sgin = skb_nsg(skb, rxm->offset + tls_ctx->rx.prepend_size, + rxm->full_len - tls_ctx->rx.prepend_size); } else { n_sgout = 0; *zc = false; + n_sgin = skb_cow_data(skb, 0, &unused); } - n_sgin = skb_cow_data(skb, 0, &unused); if (n_sgin < 1) return -EBADMSG; @@ -763,7 +920,10 @@ fallback_to_reg_recv: } /* Prepare and submit AEAD request */ - err = tls_do_decryption(sk, sgin, sgout, iv, data_len, aead_req); + err = tls_do_decryption(sk, skb, sgin, sgout, iv, + data_len, aead_req, *zc); + if (err == -EINPROGRESS) + return err; /* Release the pages in case iov was mapped to pages */ for (; pages > 0; pages--) @@ -788,8 +948,12 @@ static int decrypt_skb_update(struct sock *sk, struct sk_buff *skb, #endif if (!ctx->decrypted) { err = decrypt_internal(sk, skb, dest, NULL, chunk, zc); - if (err < 0) + if (err < 0) { + if (err == -EINPROGRESS) + tls_advance_record_sn(sk, &tls_ctx->rx); + return err; + } } else { *zc = false; } @@ -817,18 +981,20 @@ static bool tls_sw_advance_skb(struct sock *sk, struct sk_buff *skb, { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); - struct strp_msg *rxm = strp_msg(skb); - if (len < rxm->full_len) { - rxm->offset += len; - rxm->full_len -= len; + if (skb) { + struct strp_msg *rxm = strp_msg(skb); - return false; + if (len < rxm->full_len) { + rxm->offset += len; + rxm->full_len -= len; + return false; + } + kfree_skb(skb); } /* Finished with message */ ctx->recv_pkt = NULL; - kfree_skb(skb); __strp_unpause(&ctx->strp); return true; @@ -851,6 +1017,7 @@ int tls_sw_recvmsg(struct sock *sk, int target, err = 0; long timeo; bool is_kvec = msg->msg_iter.type & ITER_KVEC; + int num_async = 0; flags |= nonblock; @@ -863,6 +1030,7 @@ int tls_sw_recvmsg(struct sock *sk, timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); do { bool zc = false; + bool async = false; int chunk = 0; skb = tls_wait_data(sk, flags, timeo, &err); @@ -870,6 +1038,7 @@ int tls_sw_recvmsg(struct sock *sk, goto recv_end; rxm = strp_msg(skb); + if (!cmsg) { int cerr; @@ -896,26 +1065,39 @@ int tls_sw_recvmsg(struct sock *sk, err = decrypt_skb_update(sk, skb, &msg->msg_iter, &chunk, &zc); - if (err < 0) { + if (err < 0 && err != -EINPROGRESS) { tls_err_abort(sk, EBADMSG); goto recv_end; } + + if (err == -EINPROGRESS) { + async = true; + num_async++; + goto pick_next_record; + } + ctx->decrypted = true; } if (!zc) { chunk = min_t(unsigned int, rxm->full_len, len); + err = skb_copy_datagram_msg(skb, rxm->offset, msg, chunk); if (err < 0) goto recv_end; } +pick_next_record: copied += chunk; len -= chunk; if (likely(!(flags & MSG_PEEK))) { u8 control = ctx->control; + /* For async, drop current skb reference */ + if (async) + skb = NULL; + if (tls_sw_advance_skb(sk, skb, chunk)) { /* Return full control message to * userspace before trying to parse @@ -924,14 +1106,40 @@ int tls_sw_recvmsg(struct sock *sk, msg->msg_flags |= MSG_EOR; if (control != TLS_RECORD_TYPE_DATA) goto recv_end; + } else { + break; } + } else { + /* MSG_PEEK right now cannot look beyond current skb + * from strparser, meaning we cannot advance skb here + * and thus unpause strparser since we'd loose original + * one. + */ + break; } + /* If we have a new message from strparser, continue now. */ if (copied >= target && !ctx->recv_pkt) break; } while (len); recv_end: + if (num_async) { + /* Wait for all previously submitted records to be decrypted */ + smp_store_mb(ctx->async_notify, true); + if (atomic_read(&ctx->decrypt_pending)) { + err = crypto_wait_req(-EINPROGRESS, &ctx->async_wait); + if (err) { + /* one of async decrypt failed */ + tls_err_abort(sk, err); + copied = 0; + } + } else { + reinit_completion(&ctx->async_wait.completion); + } + WRITE_ONCE(ctx->async_notify, false); + } + release_sock(sk); return copied ? : err; } @@ -1049,8 +1257,8 @@ static int tls_read_size(struct strparser *strp, struct sk_buff *skb) goto read_failure; } - if (header[1] != TLS_VERSION_MINOR(tls_ctx->crypto_recv.version) || - header[2] != TLS_VERSION_MAJOR(tls_ctx->crypto_recv.version)) { + if (header[1] != TLS_VERSION_MINOR(tls_ctx->crypto_recv.info.version) || + header[2] != TLS_VERSION_MAJOR(tls_ctx->crypto_recv.info.version)) { ret = -EINVAL; goto read_failure; } @@ -1130,7 +1338,6 @@ void tls_sw_free_resources_rx(struct sock *sk) int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) { - char keyval[TLS_CIPHER_AES_GCM_128_KEY_SIZE]; struct tls_crypto_info *crypto_info; struct tls12_crypto_info_aes_gcm_128 *gcm_128_info; struct tls_sw_context_tx *sw_ctx_tx = NULL; @@ -1175,12 +1382,12 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) if (tx) { crypto_init_wait(&sw_ctx_tx->async_wait); - crypto_info = &ctx->crypto_send; + crypto_info = &ctx->crypto_send.info; cctx = &ctx->tx; aead = &sw_ctx_tx->aead_send; } else { crypto_init_wait(&sw_ctx_rx->async_wait); - crypto_info = &ctx->crypto_recv; + crypto_info = &ctx->crypto_recv.info; cctx = &ctx->rx; aead = &sw_ctx_rx->aead_recv; } @@ -1259,9 +1466,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) ctx->push_pending_record = tls_sw_push_pending_record; - memcpy(keyval, gcm_128_info->key, TLS_CIPHER_AES_GCM_128_KEY_SIZE); - - rc = crypto_aead_setkey(*aead, keyval, + rc = crypto_aead_setkey(*aead, gcm_128_info->key, TLS_CIPHER_AES_GCM_128_KEY_SIZE); if (rc) goto free_aead; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 5fb9b7dd9831..d5f9b5235cdd 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -669,13 +669,13 @@ static int nl80211_msg_put_wmm_rules(struct sk_buff *msg, goto nla_put_failure; if (nla_put_u16(msg, NL80211_WMMR_CW_MIN, - rule->wmm_rule->client[j].cw_min) || + rule->wmm_rule.client[j].cw_min) || nla_put_u16(msg, NL80211_WMMR_CW_MAX, - rule->wmm_rule->client[j].cw_max) || + rule->wmm_rule.client[j].cw_max) || nla_put_u8(msg, NL80211_WMMR_AIFSN, - rule->wmm_rule->client[j].aifsn) || - nla_put_u8(msg, NL80211_WMMR_TXOP, - rule->wmm_rule->client[j].cot)) + rule->wmm_rule.client[j].aifsn) || + nla_put_u16(msg, NL80211_WMMR_TXOP, + rule->wmm_rule.client[j].cot)) goto nla_put_failure; nla_nest_end(msg, nl_wmm_rule); @@ -766,9 +766,9 @@ static int nl80211_msg_put_channel(struct sk_buff *msg, struct wiphy *wiphy, if (large) { const struct ieee80211_reg_rule *rule = - freq_reg_info(wiphy, chan->center_freq); + freq_reg_info(wiphy, MHZ_TO_KHZ(chan->center_freq)); - if (!IS_ERR(rule) && rule->wmm_rule) { + if (!IS_ERR_OR_NULL(rule) && rule->has_wmm) { if (nl80211_msg_put_wmm_rules(msg, rule)) goto nla_put_failure; } @@ -4095,6 +4095,9 @@ static void nl80211_calculate_ap_params(struct cfg80211_ap_settings *params) cap = cfg80211_find_ie(WLAN_EID_VHT_CAPABILITY, ies, ies_len); if (cap && cap[1] >= sizeof(*params->vht_cap)) params->vht_cap = (void *)(cap + 2); + cap = cfg80211_find_ext_ie(WLAN_EID_EXT_HE_CAPABILITY, ies, ies_len); + if (cap && cap[1] >= sizeof(*params->he_cap) + 1) + params->he_cap = (void *)(cap + 3); } static bool nl80211_get_ap_channel(struct cfg80211_registered_device *rdev, @@ -4724,10 +4727,11 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid, PUT_SINFO_U64(RX_DROP_MISC, rx_dropped_misc); PUT_SINFO_U64(BEACON_RX, rx_beacon); PUT_SINFO(BEACON_SIGNAL_AVG, rx_beacon_signal_avg, u8); - PUT_SINFO(ACK_SIGNAL, ack_signal, u8); if (wiphy_ext_feature_isset(&rdev->wiphy, - NL80211_EXT_FEATURE_DATA_ACK_SIGNAL_SUPPORT)) - PUT_SINFO(DATA_ACK_SIGNAL_AVG, avg_ack_signal, s8); + NL80211_EXT_FEATURE_ACK_SIGNAL_SUPPORT)) { + PUT_SINFO(ACK_SIGNAL, ack_signal, u8); + PUT_SINFO(ACK_SIGNAL_AVG, avg_ack_signal, s8); + } #undef PUT_SINFO #undef PUT_SINFO_U64 @@ -12205,6 +12209,7 @@ static int nl80211_update_ft_ies(struct sk_buff *skb, struct genl_info *info) return -EOPNOTSUPP; if (!info->attrs[NL80211_ATTR_MDID] || + !info->attrs[NL80211_ATTR_IE] || !is_valid_ie_attr(info->attrs[NL80211_ATTR_IE])) return -EINVAL; diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 4fc66a117b7d..56be68a27bb9 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -425,36 +425,23 @@ static const struct ieee80211_regdomain * reg_copy_regd(const struct ieee80211_regdomain *src_regd) { struct ieee80211_regdomain *regd; - int size_of_regd, size_of_wmms; + int size_of_regd; unsigned int i; - struct ieee80211_wmm_rule *d_wmm, *s_wmm; size_of_regd = sizeof(struct ieee80211_regdomain) + src_regd->n_reg_rules * sizeof(struct ieee80211_reg_rule); - size_of_wmms = src_regd->n_wmm_rules * - sizeof(struct ieee80211_wmm_rule); - regd = kzalloc(size_of_regd + size_of_wmms, GFP_KERNEL); + regd = kzalloc(size_of_regd, GFP_KERNEL); if (!regd) return ERR_PTR(-ENOMEM); memcpy(regd, src_regd, sizeof(struct ieee80211_regdomain)); - d_wmm = (struct ieee80211_wmm_rule *)((u8 *)regd + size_of_regd); - s_wmm = (struct ieee80211_wmm_rule *)((u8 *)src_regd + size_of_regd); - memcpy(d_wmm, s_wmm, size_of_wmms); - - for (i = 0; i < src_regd->n_reg_rules; i++) { + for (i = 0; i < src_regd->n_reg_rules; i++) memcpy(®d->reg_rules[i], &src_regd->reg_rules[i], sizeof(struct ieee80211_reg_rule)); - if (!src_regd->reg_rules[i].wmm_rule) - continue; - regd->reg_rules[i].wmm_rule = d_wmm + - (src_regd->reg_rules[i].wmm_rule - s_wmm) / - sizeof(struct ieee80211_wmm_rule); - } return regd; } @@ -860,27 +847,44 @@ static bool valid_regdb(const u8 *data, unsigned int size) return true; } -static void set_wmm_rule(struct ieee80211_wmm_rule *rule, - struct fwdb_wmm_rule *wmm) +static void set_wmm_rule(const struct fwdb_header *db, + const struct fwdb_country *country, + const struct fwdb_rule *rule, + struct ieee80211_reg_rule *rrule) { - unsigned int i; + struct ieee80211_wmm_rule *wmm_rule = &rrule->wmm_rule; + struct fwdb_wmm_rule *wmm; + unsigned int i, wmm_ptr; + + wmm_ptr = be16_to_cpu(rule->wmm_ptr) << 2; + wmm = (void *)((u8 *)db + wmm_ptr); + + if (!valid_wmm(wmm)) { + pr_err("Invalid regulatory WMM rule %u-%u in domain %c%c\n", + be32_to_cpu(rule->start), be32_to_cpu(rule->end), + country->alpha2[0], country->alpha2[1]); + return; + } for (i = 0; i < IEEE80211_NUM_ACS; i++) { - rule->client[i].cw_min = + wmm_rule->client[i].cw_min = ecw2cw((wmm->client[i].ecw & 0xf0) >> 4); - rule->client[i].cw_max = ecw2cw(wmm->client[i].ecw & 0x0f); - rule->client[i].aifsn = wmm->client[i].aifsn; - rule->client[i].cot = 1000 * be16_to_cpu(wmm->client[i].cot); - rule->ap[i].cw_min = ecw2cw((wmm->ap[i].ecw & 0xf0) >> 4); - rule->ap[i].cw_max = ecw2cw(wmm->ap[i].ecw & 0x0f); - rule->ap[i].aifsn = wmm->ap[i].aifsn; - rule->ap[i].cot = 1000 * be16_to_cpu(wmm->ap[i].cot); + wmm_rule->client[i].cw_max = ecw2cw(wmm->client[i].ecw & 0x0f); + wmm_rule->client[i].aifsn = wmm->client[i].aifsn; + wmm_rule->client[i].cot = + 1000 * be16_to_cpu(wmm->client[i].cot); + wmm_rule->ap[i].cw_min = ecw2cw((wmm->ap[i].ecw & 0xf0) >> 4); + wmm_rule->ap[i].cw_max = ecw2cw(wmm->ap[i].ecw & 0x0f); + wmm_rule->ap[i].aifsn = wmm->ap[i].aifsn; + wmm_rule->ap[i].cot = 1000 * be16_to_cpu(wmm->ap[i].cot); } + + rrule->has_wmm = true; } static int __regdb_query_wmm(const struct fwdb_header *db, const struct fwdb_country *country, int freq, - u32 *dbptr, struct ieee80211_wmm_rule *rule) + struct ieee80211_reg_rule *rrule) { unsigned int ptr = be16_to_cpu(country->coll_ptr) << 2; struct fwdb_collection *coll = (void *)((u8 *)db + ptr); @@ -889,20 +893,14 @@ static int __regdb_query_wmm(const struct fwdb_header *db, for (i = 0; i < coll->n_rules; i++) { __be16 *rules_ptr = (void *)((u8 *)coll + ALIGN(coll->len, 2)); unsigned int rule_ptr = be16_to_cpu(rules_ptr[i]) << 2; - struct fwdb_rule *rrule = (void *)((u8 *)db + rule_ptr); - struct fwdb_wmm_rule *wmm; - unsigned int wmm_ptr; + struct fwdb_rule *rule = (void *)((u8 *)db + rule_ptr); - if (rrule->len < offsetofend(struct fwdb_rule, wmm_ptr)) + if (rule->len < offsetofend(struct fwdb_rule, wmm_ptr)) continue; - if (freq >= KHZ_TO_MHZ(be32_to_cpu(rrule->start)) && - freq <= KHZ_TO_MHZ(be32_to_cpu(rrule->end))) { - wmm_ptr = be16_to_cpu(rrule->wmm_ptr) << 2; - wmm = (void *)((u8 *)db + wmm_ptr); - set_wmm_rule(rule, wmm); - if (dbptr) - *dbptr = wmm_ptr; + if (freq >= KHZ_TO_MHZ(be32_to_cpu(rule->start)) && + freq <= KHZ_TO_MHZ(be32_to_cpu(rule->end))) { + set_wmm_rule(db, country, rule, rrule); return 0; } } @@ -910,8 +908,7 @@ static int __regdb_query_wmm(const struct fwdb_header *db, return -ENODATA; } -int reg_query_regdb_wmm(char *alpha2, int freq, u32 *dbptr, - struct ieee80211_wmm_rule *rule) +int reg_query_regdb_wmm(char *alpha2, int freq, struct ieee80211_reg_rule *rule) { const struct fwdb_header *hdr = regdb; const struct fwdb_country *country; @@ -925,8 +922,7 @@ int reg_query_regdb_wmm(char *alpha2, int freq, u32 *dbptr, country = &hdr->country[0]; while (country->coll_ptr) { if (alpha2_equal(alpha2, country->alpha2)) - return __regdb_query_wmm(regdb, country, freq, dbptr, - rule); + return __regdb_query_wmm(regdb, country, freq, rule); country++; } @@ -935,32 +931,13 @@ int reg_query_regdb_wmm(char *alpha2, int freq, u32 *dbptr, } EXPORT_SYMBOL(reg_query_regdb_wmm); -struct wmm_ptrs { - struct ieee80211_wmm_rule *rule; - u32 ptr; -}; - -static struct ieee80211_wmm_rule *find_wmm_ptr(struct wmm_ptrs *wmm_ptrs, - u32 wmm_ptr, int n_wmms) -{ - int i; - - for (i = 0; i < n_wmms; i++) { - if (wmm_ptrs[i].ptr == wmm_ptr) - return wmm_ptrs[i].rule; - } - return NULL; -} - static int regdb_query_country(const struct fwdb_header *db, const struct fwdb_country *country) { unsigned int ptr = be16_to_cpu(country->coll_ptr) << 2; struct fwdb_collection *coll = (void *)((u8 *)db + ptr); struct ieee80211_regdomain *regdom; - struct ieee80211_regdomain *tmp_rd; - unsigned int size_of_regd, i, n_wmms = 0; - struct wmm_ptrs *wmm_ptrs; + unsigned int size_of_regd, i; size_of_regd = sizeof(struct ieee80211_regdomain) + coll->n_rules * sizeof(struct ieee80211_reg_rule); @@ -969,12 +946,6 @@ static int regdb_query_country(const struct fwdb_header *db, if (!regdom) return -ENOMEM; - wmm_ptrs = kcalloc(coll->n_rules, sizeof(*wmm_ptrs), GFP_KERNEL); - if (!wmm_ptrs) { - kfree(regdom); - return -ENOMEM; - } - regdom->n_reg_rules = coll->n_rules; regdom->alpha2[0] = country->alpha2[0]; regdom->alpha2[1] = country->alpha2[1]; @@ -1011,39 +982,9 @@ static int regdb_query_country(const struct fwdb_header *db, if (rule->len >= offsetofend(struct fwdb_rule, cac_timeout)) rrule->dfs_cac_ms = 1000 * be16_to_cpu(rule->cac_timeout); - if (rule->len >= offsetofend(struct fwdb_rule, wmm_ptr)) { - u32 wmm_ptr = be16_to_cpu(rule->wmm_ptr) << 2; - struct ieee80211_wmm_rule *wmm_pos = - find_wmm_ptr(wmm_ptrs, wmm_ptr, n_wmms); - struct fwdb_wmm_rule *wmm; - struct ieee80211_wmm_rule *wmm_rule; - - if (wmm_pos) { - rrule->wmm_rule = wmm_pos; - continue; - } - wmm = (void *)((u8 *)db + wmm_ptr); - tmp_rd = krealloc(regdom, size_of_regd + (n_wmms + 1) * - sizeof(struct ieee80211_wmm_rule), - GFP_KERNEL); - - if (!tmp_rd) { - kfree(regdom); - kfree(wmm_ptrs); - return -ENOMEM; - } - regdom = tmp_rd; - - wmm_rule = (struct ieee80211_wmm_rule *) - ((u8 *)regdom + size_of_regd + n_wmms * - sizeof(struct ieee80211_wmm_rule)); - - set_wmm_rule(wmm_rule, wmm); - wmm_ptrs[n_wmms].ptr = wmm_ptr; - wmm_ptrs[n_wmms++].rule = wmm_rule; - } + if (rule->len >= offsetofend(struct fwdb_rule, wmm_ptr)) + set_wmm_rule(db, country, rule, rrule); } - kfree(wmm_ptrs); return reg_schedule_apply(regdom); } @@ -3249,13 +3190,59 @@ static void restore_regulatory_settings(bool reset_user) schedule_work(®_work); } +static bool is_wiphy_all_set_reg_flag(enum ieee80211_regulatory_flags flag) +{ + struct cfg80211_registered_device *rdev; + struct wireless_dev *wdev; + + list_for_each_entry(rdev, &cfg80211_rdev_list, list) { + list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) { + wdev_lock(wdev); + if (!(wdev->wiphy->regulatory_flags & flag)) { + wdev_unlock(wdev); + return false; + } + wdev_unlock(wdev); + } + } + + return true; +} + void regulatory_hint_disconnect(void) { + /* Restore of regulatory settings is not required when wiphy(s) + * ignore IE from connected access point but clearance of beacon hints + * is required when wiphy(s) supports beacon hints. + */ + if (is_wiphy_all_set_reg_flag(REGULATORY_COUNTRY_IE_IGNORE)) { + struct reg_beacon *reg_beacon, *btmp; + + if (is_wiphy_all_set_reg_flag(REGULATORY_DISABLE_BEACON_HINTS)) + return; + + spin_lock_bh(®_pending_beacons_lock); + list_for_each_entry_safe(reg_beacon, btmp, + ®_pending_beacons, list) { + list_del(®_beacon->list); + kfree(reg_beacon); + } + spin_unlock_bh(®_pending_beacons_lock); + + list_for_each_entry_safe(reg_beacon, btmp, + ®_beacon_list, list) { + list_del(®_beacon->list); + kfree(reg_beacon); + } + + return; + } + pr_debug("All devices are disconnected, going to restore regulatory settings\n"); restore_regulatory_settings(false); } -static bool freq_is_chan_12_13_14(u16 freq) +static bool freq_is_chan_12_13_14(u32 freq) { if (freq == ieee80211_channel_to_frequency(12, NL80211_BAND_2GHZ) || freq == ieee80211_channel_to_frequency(13, NL80211_BAND_2GHZ) || diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 7c73510b161f..5e7eec849200 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -112,7 +112,7 @@ } while (0) #define CHAN_ENTRY __field(enum nl80211_band, band) \ - __field(u16, center_freq) + __field(u32, center_freq) #define CHAN_ASSIGN(chan) \ do { \ if (chan) { \ diff --git a/net/wireless/util.c b/net/wireless/util.c index e0825a019e9f..ef14d80ca03e 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -5,17 +5,20 @@ * Copyright 2007-2009 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2017 Intel Deutschland GmbH + * Copyright (C) 2018 Intel Corporation */ #include <linux/export.h> #include <linux/bitops.h> #include <linux/etherdevice.h> #include <linux/slab.h> +#include <linux/ieee80211.h> #include <net/cfg80211.h> #include <net/ip.h> #include <net/dsfield.h> #include <linux/if_vlan.h> #include <linux/mpls.h> #include <linux/gcd.h> +#include <linux/bitfield.h> #include "core.h" #include "rdev-ops.h" @@ -88,7 +91,7 @@ int ieee80211_channel_to_frequency(int chan, enum nl80211_band band) return 5000 + chan * 5; break; case NL80211_BAND_60GHZ: - if (chan < 5) + if (chan < 7) return 56160 + chan * 2160; break; default: @@ -109,7 +112,7 @@ int ieee80211_frequency_to_channel(int freq) return (freq - 4000) / 5; else if (freq <= 45000) /* DMG band lower limit */ return (freq - 5000) / 5; - else if (freq >= 58320 && freq <= 64800) + else if (freq >= 58320 && freq <= 70200) return (freq - 56160) / 2160; else return 0; @@ -1456,7 +1459,7 @@ bool ieee80211_chandef_to_operating_class(struct cfg80211_chan_def *chandef, u8 *op_class) { u8 vht_opclass; - u16 freq = chandef->center_freq1; + u32 freq = chandef->center_freq1; if (freq >= 2412 && freq <= 2472) { if (chandef->width > NL80211_CHAN_WIDTH_40) @@ -1568,7 +1571,7 @@ bool ieee80211_chandef_to_operating_class(struct cfg80211_chan_def *chandef, } /* 56.16 GHz, channel 1..4 */ - if (freq >= 56160 + 2160 * 1 && freq <= 56160 + 2160 * 4) { + if (freq >= 56160 + 2160 * 1 && freq <= 56160 + 2160 * 6) { if (chandef->width >= NL80211_CHAN_WIDTH_40) return false; @@ -1893,3 +1896,154 @@ EXPORT_SYMBOL(rfc1042_header); const unsigned char bridge_tunnel_header[] __aligned(2) = { 0xaa, 0xaa, 0x03, 0x00, 0x00, 0xf8 }; EXPORT_SYMBOL(bridge_tunnel_header); + +/* Layer 2 Update frame (802.2 Type 1 LLC XID Update response) */ +struct iapp_layer2_update { + u8 da[ETH_ALEN]; /* broadcast */ + u8 sa[ETH_ALEN]; /* STA addr */ + __be16 len; /* 6 */ + u8 dsap; /* 0 */ + u8 ssap; /* 0 */ + u8 control; + u8 xid_info[3]; +} __packed; + +void cfg80211_send_layer2_update(struct net_device *dev, const u8 *addr) +{ + struct iapp_layer2_update *msg; + struct sk_buff *skb; + + /* Send Level 2 Update Frame to update forwarding tables in layer 2 + * bridge devices */ + + skb = dev_alloc_skb(sizeof(*msg)); + if (!skb) + return; + msg = skb_put(skb, sizeof(*msg)); + + /* 802.2 Type 1 Logical Link Control (LLC) Exchange Identifier (XID) + * Update response frame; IEEE Std 802.2-1998, 5.4.1.2.1 */ + + eth_broadcast_addr(msg->da); + ether_addr_copy(msg->sa, addr); + msg->len = htons(6); + msg->dsap = 0; + msg->ssap = 0x01; /* NULL LSAP, CR Bit: Response */ + msg->control = 0xaf; /* XID response lsb.1111F101. + * F=0 (no poll command; unsolicited frame) */ + msg->xid_info[0] = 0x81; /* XID format identifier */ + msg->xid_info[1] = 1; /* LLC types/classes: Type 1 LLC */ + msg->xid_info[2] = 0; /* XID sender's receive window size (RW) */ + + skb->dev = dev; + skb->protocol = eth_type_trans(skb, dev); + memset(skb->cb, 0, sizeof(skb->cb)); + netif_rx_ni(skb); +} +EXPORT_SYMBOL(cfg80211_send_layer2_update); + +int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, + enum ieee80211_vht_chanwidth bw, + int mcs, bool ext_nss_bw_capable) +{ + u16 map = le16_to_cpu(cap->supp_mcs.rx_mcs_map); + int max_vht_nss = 0; + int ext_nss_bw; + int supp_width; + int i, mcs_encoding; + + if (map == 0xffff) + return 0; + + if (WARN_ON(mcs > 9)) + return 0; + if (mcs <= 7) + mcs_encoding = 0; + else if (mcs == 8) + mcs_encoding = 1; + else + mcs_encoding = 2; + + /* find max_vht_nss for the given MCS */ + for (i = 7; i >= 0; i--) { + int supp = (map >> (2 * i)) & 3; + + if (supp == 3) + continue; + + if (supp >= mcs_encoding) { + max_vht_nss = i; + break; + } + } + + if (!(cap->supp_mcs.tx_mcs_map & + cpu_to_le16(IEEE80211_VHT_EXT_NSS_BW_CAPABLE))) + return max_vht_nss; + + ext_nss_bw = le32_get_bits(cap->vht_cap_info, + IEEE80211_VHT_CAP_EXT_NSS_BW_MASK); + supp_width = le32_get_bits(cap->vht_cap_info, + IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK); + + /* if not capable, treat ext_nss_bw as 0 */ + if (!ext_nss_bw_capable) + ext_nss_bw = 0; + + /* This is invalid */ + if (supp_width == 3) + return 0; + + /* This is an invalid combination so pretend nothing is supported */ + if (supp_width == 2 && (ext_nss_bw == 1 || ext_nss_bw == 2)) + return 0; + + /* + * Cover all the special cases according to IEEE 802.11-2016 + * Table 9-250. All other cases are either factor of 1 or not + * valid/supported. + */ + switch (bw) { + case IEEE80211_VHT_CHANWIDTH_USE_HT: + case IEEE80211_VHT_CHANWIDTH_80MHZ: + if ((supp_width == 1 || supp_width == 2) && + ext_nss_bw == 3) + return 2 * max_vht_nss; + break; + case IEEE80211_VHT_CHANWIDTH_160MHZ: + if (supp_width == 0 && + (ext_nss_bw == 1 || ext_nss_bw == 2)) + return DIV_ROUND_UP(max_vht_nss, 2); + if (supp_width == 0 && + ext_nss_bw == 3) + return DIV_ROUND_UP(3 * max_vht_nss, 4); + if (supp_width == 1 && + ext_nss_bw == 3) + return 2 * max_vht_nss; + break; + case IEEE80211_VHT_CHANWIDTH_80P80MHZ: + if (supp_width == 0 && + (ext_nss_bw == 1 || ext_nss_bw == 2)) + return 0; /* not possible */ + if (supp_width == 0 && + ext_nss_bw == 2) + return DIV_ROUND_UP(max_vht_nss, 2); + if (supp_width == 0 && + ext_nss_bw == 3) + return DIV_ROUND_UP(3 * max_vht_nss, 4); + if (supp_width == 1 && + ext_nss_bw == 0) + return 0; /* not possible */ + if (supp_width == 1 && + ext_nss_bw == 1) + return DIV_ROUND_UP(max_vht_nss, 2); + if (supp_width == 1 && + ext_nss_bw == 2) + return DIV_ROUND_UP(3 * max_vht_nss, 4); + break; + } + + /* not covered or invalid combination received */ + return max_vht_nss; +} +EXPORT_SYMBOL(ieee80211_get_vht_max_nss); diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index 911ca6d3cb5a..b3b632c5aeae 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -74,14 +74,12 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, return 0; if (!dev->netdev_ops->ndo_bpf || !dev->netdev_ops->ndo_xsk_async_xmit) - return force_zc ? -ENOTSUPP : 0; /* fail or fallback */ - - bpf.command = XDP_QUERY_XSK_UMEM; + return force_zc ? -EOPNOTSUPP : 0; /* fail or fallback */ rtnl_lock(); err = xdp_umem_query(dev, queue_id); if (err) { - err = err < 0 ? -ENOTSUPP : -EBUSY; + err = err < 0 ? -EOPNOTSUPP : -EBUSY; goto err_rtnl_unlock; } @@ -314,8 +312,8 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) umem->pid = get_task_pid(current, PIDTYPE_PID); umem->address = (unsigned long)addr; - umem->props.chunk_mask = ~((u64)chunk_size - 1); - umem->props.size = size; + umem->chunk_mask = ~((u64)chunk_size - 1); + umem->size = size; umem->headroom = headroom; umem->chunk_size_nohr = chunk_size - headroom; umem->npgs = size / PAGE_SIZE; diff --git a/net/xdp/xdp_umem.h b/net/xdp/xdp_umem.h index f11560334f88..c8be1ad3eb88 100644 --- a/net/xdp/xdp_umem.h +++ b/net/xdp/xdp_umem.h @@ -8,16 +8,6 @@ #include <net/xdp_sock.h> -static inline char *xdp_umem_get_data(struct xdp_umem *umem, u64 addr) -{ - return umem->pages[addr >> PAGE_SHIFT].addr + (addr & (PAGE_SIZE - 1)); -} - -static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr) -{ - return umem->pages[addr >> PAGE_SHIFT].dma + (addr & (PAGE_SIZE - 1)); -} - int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, u32 queue_id, u16 flags); bool xdp_umem_validate_queues(struct xdp_umem *umem); diff --git a/net/xdp/xdp_umem_props.h b/net/xdp/xdp_umem_props.h deleted file mode 100644 index 40eab10dfc49..000000000000 --- a/net/xdp/xdp_umem_props.h +++ /dev/null @@ -1,14 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* XDP user-space packet buffer - * Copyright(c) 2018 Intel Corporation. - */ - -#ifndef XDP_UMEM_PROPS_H_ -#define XDP_UMEM_PROPS_H_ - -struct xdp_umem_props { - u64 chunk_mask; - u64 size; -}; - -#endif /* XDP_UMEM_PROPS_H_ */ diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 4e937cd7c17d..5a432dfee4ee 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -55,20 +55,30 @@ EXPORT_SYMBOL(xsk_umem_discard_addr); static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) { - void *buffer; + void *to_buf, *from_buf; + u32 metalen; u64 addr; int err; if (!xskq_peek_addr(xs->umem->fq, &addr) || - len > xs->umem->chunk_size_nohr) { + len > xs->umem->chunk_size_nohr - XDP_PACKET_HEADROOM) { xs->rx_dropped++; return -ENOSPC; } addr += xs->umem->headroom; - buffer = xdp_umem_get_data(xs->umem, addr); - memcpy(buffer, xdp->data, len); + if (unlikely(xdp_data_meta_unsupported(xdp))) { + from_buf = xdp->data; + metalen = 0; + } else { + from_buf = xdp->data_meta; + metalen = xdp->data - xdp->data_meta; + } + + to_buf = xdp_umem_get_data(xs->umem, addr); + memcpy(to_buf, from_buf, len + metalen); + addr += metalen; err = xskq_produce_batch_desc(xs->rx, addr, len); if (!err) { xskq_discard_addr(xs->umem->fq); @@ -111,6 +121,7 @@ void xsk_flush(struct xdp_sock *xs) int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) { + u32 metalen = xdp->data - xdp->data_meta; u32 len = xdp->data_end - xdp->data; void *buffer; u64 addr; @@ -120,7 +131,7 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) return -EINVAL; if (!xskq_peek_addr(xs->umem->fq, &addr) || - len > xs->umem->chunk_size_nohr) { + len > xs->umem->chunk_size_nohr - XDP_PACKET_HEADROOM) { xs->rx_dropped++; return -ENOSPC; } @@ -128,7 +139,8 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) addr += xs->umem->headroom; buffer = xdp_umem_get_data(xs->umem, addr); - memcpy(buffer, xdp->data, len); + memcpy(buffer, xdp->data_meta, len + metalen); + addr += metalen; err = xskq_produce_batch_desc(xs->rx, addr, len); if (!err) { xskq_discard_addr(xs->umem->fq); @@ -458,8 +470,10 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) goto out_unlock; } else { /* This xsk has its own umem. */ - xskq_set_umem(xs->umem->fq, &xs->umem->props); - xskq_set_umem(xs->umem->cq, &xs->umem->props); + xskq_set_umem(xs->umem->fq, xs->umem->size, + xs->umem->chunk_mask); + xskq_set_umem(xs->umem->cq, xs->umem->size, + xs->umem->chunk_mask); err = xdp_umem_assign_dev(xs->umem, dev, qid, flags); if (err) @@ -469,8 +483,8 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) xs->dev = dev; xs->zc = xs->umem->zc; xs->queue_id = qid; - xskq_set_umem(xs->rx, &xs->umem->props); - xskq_set_umem(xs->tx, &xs->umem->props); + xskq_set_umem(xs->rx, xs->umem->size, xs->umem->chunk_mask); + xskq_set_umem(xs->tx, xs->umem->size, xs->umem->chunk_mask); xdp_add_sk_umem(xs->umem, xs); out_unlock: diff --git a/net/xdp/xsk_queue.c b/net/xdp/xsk_queue.c index 6c32e92e98fc..2dc1384d9f27 100644 --- a/net/xdp/xsk_queue.c +++ b/net/xdp/xsk_queue.c @@ -7,12 +7,13 @@ #include "xsk_queue.h" -void xskq_set_umem(struct xsk_queue *q, struct xdp_umem_props *umem_props) +void xskq_set_umem(struct xsk_queue *q, u64 size, u64 chunk_mask) { if (!q) return; - q->umem_props = *umem_props; + q->size = size; + q->chunk_mask = chunk_mask; } static u32 xskq_umem_get_ring_size(struct xsk_queue *q) diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index 8a64b150be54..82252cccb4e0 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -31,7 +31,8 @@ struct xdp_umem_ring { }; struct xsk_queue { - struct xdp_umem_props umem_props; + u64 chunk_mask; + u64 size; u32 ring_mask; u32 nentries; u32 prod_head; @@ -78,7 +79,7 @@ static inline u32 xskq_nb_free(struct xsk_queue *q, u32 producer, u32 dcnt) static inline bool xskq_is_valid_addr(struct xsk_queue *q, u64 addr) { - if (addr >= q->umem_props.size) { + if (addr >= q->size) { q->invalid_descs++; return false; } @@ -92,7 +93,7 @@ static inline u64 *xskq_validate_addr(struct xsk_queue *q, u64 *addr) struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring; unsigned int idx = q->cons_tail & q->ring_mask; - *addr = READ_ONCE(ring->desc[idx]) & q->umem_props.chunk_mask; + *addr = READ_ONCE(ring->desc[idx]) & q->chunk_mask; if (xskq_is_valid_addr(q, *addr)) return addr; @@ -173,8 +174,8 @@ static inline bool xskq_is_valid_desc(struct xsk_queue *q, struct xdp_desc *d) if (!xskq_is_valid_addr(q, d->addr)) return false; - if (((d->addr + d->len) & q->umem_props.chunk_mask) != - (d->addr & q->umem_props.chunk_mask)) { + if (((d->addr + d->len) & q->chunk_mask) != + (d->addr & q->chunk_mask)) { q->invalid_descs++; return false; } @@ -253,7 +254,7 @@ static inline bool xskq_empty_desc(struct xsk_queue *q) return xskq_nb_free(q, q->prod_tail, q->nentries) == q->nentries; } -void xskq_set_umem(struct xsk_queue *q, struct xdp_umem_props *umem_props); +void xskq_set_umem(struct xsk_queue *q, u64 size, u64 chunk_mask); struct xsk_queue *xskq_create(u32 nentries, bool umem_queue); void xskq_destroy(struct xsk_queue *q_ops); diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 5611b7521020..260fbba4f03e 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -99,7 +99,7 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur do { struct sk_buff *nskb = skb2->next; - skb2->next = NULL; + skb_mark_not_on_list(skb2); xo = xfrm_offload(skb2); xo->flags |= XFRM_DEV_RESUME; diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 45ba07ab3e4f..2d42cb0c94b8 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -189,7 +189,7 @@ static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb struct sk_buff *nskb = segs->next; int err; - segs->next = NULL; + skb_mark_not_on_list(segs); err = xfrm_output2(net, sk, segs); if (unlikely(err)) { diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index 36f9f41d094b..be0a961450bc 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -153,6 +153,7 @@ always += tcp_cong_kern.o always += tcp_iw_kern.o always += tcp_clamp_kern.o always += tcp_basertt_kern.o +always += tcp_tos_reflect_kern.o always += xdp_redirect_kern.o always += xdp_redirect_map_kern.o always += xdp_redirect_cpu_kern.o diff --git a/samples/bpf/tcp_tos_reflect_kern.c b/samples/bpf/tcp_tos_reflect_kern.c new file mode 100644 index 000000000000..d51dab19eca6 --- /dev/null +++ b/samples/bpf/tcp_tos_reflect_kern.c @@ -0,0 +1,87 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2018 Facebook + * + * BPF program to automatically reflect TOS option from received syn packet + * + * Use load_sock_ops to load this BPF program. + */ + +#include <uapi/linux/bpf.h> +#include <uapi/linux/tcp.h> +#include <uapi/linux/if_ether.h> +#include <uapi/linux/if_packet.h> +#include <uapi/linux/ip.h> +#include <uapi/linux/ipv6.h> +#include <uapi/linux/in.h> +#include <linux/socket.h> +#include "bpf_helpers.h" +#include "bpf_endian.h" + +#define DEBUG 1 + +#define bpf_printk(fmt, ...) \ +({ \ + char ____fmt[] = fmt; \ + bpf_trace_printk(____fmt, sizeof(____fmt), \ + ##__VA_ARGS__); \ +}) + +SEC("sockops") +int bpf_basertt(struct bpf_sock_ops *skops) +{ + char header[sizeof(struct ipv6hdr)]; + struct ipv6hdr *hdr6; + struct iphdr *hdr; + int hdr_size = 0; + int save_syn = 1; + int tos = 0; + int rv = 0; + int op; + + op = (int) skops->op; + +#ifdef DEBUG + bpf_printk("BPF command: %d\n", op); +#endif + switch (op) { + case BPF_SOCK_OPS_TCP_LISTEN_CB: + rv = bpf_setsockopt(skops, SOL_TCP, TCP_SAVE_SYN, + &save_syn, sizeof(save_syn)); + break; + case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: + if (skops->family == AF_INET) + hdr_size = sizeof(struct iphdr); + else + hdr_size = sizeof(struct ipv6hdr); + rv = bpf_getsockopt(skops, SOL_TCP, TCP_SAVED_SYN, + header, hdr_size); + if (!rv) { + if (skops->family == AF_INET) { + hdr = (struct iphdr *) header; + tos = hdr->tos; + if (tos != 0) + bpf_setsockopt(skops, SOL_IP, IP_TOS, + &tos, sizeof(tos)); + } else { + hdr6 = (struct ipv6hdr *) header; + tos = ((hdr6->priority) << 4 | + (hdr6->flow_lbl[0]) >> 4); + if (tos) + bpf_setsockopt(skops, SOL_IPV6, + IPV6_TCLASS, + &tos, sizeof(tos)); + } + rv = 0; + } + break; + default: + rv = -1; + } +#ifdef DEBUG + bpf_printk("Returning %d\n", rv); +#endif + skops->reply = rv; + return 1; +} +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/xdpsock_kern.c b/samples/bpf/xdpsock_kern.c index d8806c41362e..b8ccd0802b3f 100644 --- a/samples/bpf/xdpsock_kern.c +++ b/samples/bpf/xdpsock_kern.c @@ -16,7 +16,7 @@ struct bpf_map_def SEC("maps") xsks_map = { .type = BPF_MAP_TYPE_XSKMAP, .key_size = sizeof(int), .value_size = sizeof(int), - .max_entries = 4, + .max_entries = MAX_SOCKS, }; struct bpf_map_def SEC("maps") rr_map = { diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c index 4914788b6727..57ecadc58403 100644 --- a/samples/bpf/xdpsock_user.c +++ b/samples/bpf/xdpsock_user.c @@ -118,7 +118,6 @@ struct xdpsock { unsigned long prev_tx_npkts; }; -#define MAX_SOCKS 4 static int num_socks; struct xdpsock *xsks[MAX_SOCKS]; @@ -596,7 +595,7 @@ static void dump_stats(void) prev_time = now; - for (i = 0; i < num_socks; i++) { + for (i = 0; i < num_socks && xsks[i]; i++) { char *fmt = "%-15s %'-11.0f %'-11lu\n"; double rx_pps, tx_pps; @@ -649,6 +648,8 @@ static struct option long_options[] = { {"xdp-skb", no_argument, 0, 'S'}, {"xdp-native", no_argument, 0, 'N'}, {"interval", required_argument, 0, 'n'}, + {"zero-copy", no_argument, 0, 'z'}, + {"copy", no_argument, 0, 'c'}, {0, 0, 0, 0} }; @@ -667,6 +668,8 @@ static void usage(const char *prog) " -S, --xdp-skb=n Use XDP skb-mod\n" " -N, --xdp-native=n Enfore XDP native mode\n" " -n, --interval=n Specify statistics update interval (default 1 sec).\n" + " -z, --zero-copy Force zero-copy mode.\n" + " -c, --copy Force copy mode.\n" "\n"; fprintf(stderr, str, prog); exit(EXIT_FAILURE); @@ -679,7 +682,7 @@ static void parse_command_line(int argc, char **argv) opterr = 0; for (;;) { - c = getopt_long(argc, argv, "rtli:q:psSNn:", long_options, + c = getopt_long(argc, argv, "rtli:q:psSNn:cz", long_options, &option_index); if (c == -1) break; @@ -716,6 +719,12 @@ static void parse_command_line(int argc, char **argv) case 'n': opt_interval = atoi(optarg); break; + case 'z': + opt_xdp_bind_flags |= XDP_ZEROCOPY; + break; + case 'c': + opt_xdp_bind_flags |= XDP_COPY; + break; default: usage(basename(argv[0])); } diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include index c75413d05a63..ce53639a864a 100644 --- a/scripts/Kbuild.include +++ b/scripts/Kbuild.include @@ -153,10 +153,6 @@ cc-fullversion = $(shell $(CONFIG_SHELL) \ # Usage: EXTRA_CFLAGS += $(call cc-ifversion, -lt, 0402, -O1) cc-ifversion = $(shell [ $(cc-version) $(1) $(2) ] && echo $(3) || echo $(4)) -# cc-if-fullversion -# Usage: EXTRA_CFLAGS += $(call cc-if-fullversion, -lt, 040502, -O1) -cc-if-fullversion = $(shell [ $(cc-fullversion) $(1) $(2) ] && echo $(3) || echo $(4)) - # cc-ldoption # Usage: ldflags += $(call cc-ldoption, -Wl$(comma)--hash-style=both) cc-ldoption = $(call try-run,\ diff --git a/scripts/Makefile.build b/scripts/Makefile.build index 1c48572223d1..5a2d1c9578a0 100644 --- a/scripts/Makefile.build +++ b/scripts/Makefile.build @@ -246,8 +246,6 @@ objtool_args += --no-fp endif ifdef CONFIG_GCOV_KERNEL objtool_args += --no-unreachable -else -objtool_args += $(call cc-ifversion, -lt, 0405, --no-unreachable) endif ifdef CONFIG_RETPOLINE ifneq ($(RETPOLINE_CFLAGS),) diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 5219280bf7ff..161b0224d6ae 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -380,6 +380,7 @@ our $Attribute = qr{ __noclone| __deprecated| __read_mostly| + __ro_after_init| __kprobes| $InitAttribute| ____cacheline_aligned| @@ -3311,7 +3312,7 @@ sub process { # known declaration macros $sline =~ /^\+\s+$declaration_macros/ || # start of struct or union or enum - $sline =~ /^\+\s+(?:union|struct|enum|typedef)\b/ || + $sline =~ /^\+\s+(?:static\s+)?(?:const\s+)?(?:union|struct|enum|typedef)\b/ || # start or end of block or continuation of declaration $sline =~ /^\+\s+(?:$|[\{\}\.\#\"\?\:\(\[])/ || # bitfield continuation diff --git a/scripts/depmod.sh b/scripts/depmod.sh index 999d585eaa73..e083bcae343f 100755 --- a/scripts/depmod.sh +++ b/scripts/depmod.sh @@ -11,13 +11,14 @@ DEPMOD=$1 KERNELRELEASE=$2 if ! test -r System.map ; then + echo "Warning: modules_install: missing 'System.map' file. Skipping depmod." >&2 exit 0 fi if [ -z $(command -v $DEPMOD) ]; then - echo "'make modules_install' requires $DEPMOD. Please install it." >&2 + echo "Warning: 'make modules_install' requires $DEPMOD. Please install it." >&2 echo "This is probably in the kmod package." >&2 - exit 1 + exit 0 fi # older versions of depmod require the version string to start with three diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile index 4a7bd2192073..67ed9f6ccdf8 100644 --- a/scripts/kconfig/Makefile +++ b/scripts/kconfig/Makefile @@ -221,7 +221,6 @@ $(obj)/zconf.tab.o: $(obj)/zconf.lex.c # check if necessary packages are available, and configure build flags define filechk_conf_cfg - $(CONFIG_SHELL) $(srctree)/scripts/kconfig/check-pkgconfig.sh; \ $(CONFIG_SHELL) $< endef diff --git a/scripts/kconfig/check-pkgconfig.sh b/scripts/kconfig/check-pkgconfig.sh deleted file mode 100644 index 7a1c40bfb58c..000000000000 --- a/scripts/kconfig/check-pkgconfig.sh +++ /dev/null @@ -1,8 +0,0 @@ -#!/bin/sh -# SPDX-License-Identifier: GPL-2.0 -# Check for pkg-config presence - -if [ -z $(command -v pkg-config) ]; then - echo "'make *config' requires 'pkg-config'. Please install it." 1>&2 - exit 1 -fi diff --git a/scripts/kconfig/gconf-cfg.sh b/scripts/kconfig/gconf-cfg.sh index 533b3d8f8f08..480ecd8b9f41 100755 --- a/scripts/kconfig/gconf-cfg.sh +++ b/scripts/kconfig/gconf-cfg.sh @@ -3,6 +3,13 @@ PKG="gtk+-2.0 gmodule-2.0 libglade-2.0" +if [ -z "$(command -v pkg-config)" ]; then + echo >&2 "*" + echo >&2 "* 'make gconfig' requires 'pkg-config'. Please install it." + echo >&2 "*" + exit 1 +fi + if ! pkg-config --exists $PKG; then echo >&2 "*" echo >&2 "* Unable to find the GTK+ installation. Please make sure that" diff --git a/scripts/kconfig/mconf-cfg.sh b/scripts/kconfig/mconf-cfg.sh index e6f9facd0077..c812872d7f9d 100755 --- a/scripts/kconfig/mconf-cfg.sh +++ b/scripts/kconfig/mconf-cfg.sh @@ -4,20 +4,23 @@ PKG="ncursesw" PKG2="ncurses" -if pkg-config --exists $PKG; then - echo cflags=\"$(pkg-config --cflags $PKG)\" - echo libs=\"$(pkg-config --libs $PKG)\" - exit 0 -fi +if [ -n "$(command -v pkg-config)" ]; then + if pkg-config --exists $PKG; then + echo cflags=\"$(pkg-config --cflags $PKG)\" + echo libs=\"$(pkg-config --libs $PKG)\" + exit 0 + fi -if pkg-config --exists $PKG2; then - echo cflags=\"$(pkg-config --cflags $PKG2)\" - echo libs=\"$(pkg-config --libs $PKG2)\" - exit 0 + if pkg-config --exists $PKG2; then + echo cflags=\"$(pkg-config --cflags $PKG2)\" + echo libs=\"$(pkg-config --libs $PKG2)\" + exit 0 + fi fi -# Unfortunately, some distributions (e.g. openSUSE) cannot find ncurses -# by pkg-config. +# Check the default paths in case pkg-config is not installed. +# (Even if it is installed, some distributions such as openSUSE cannot +# find ncurses by pkg-config.) if [ -f /usr/include/ncursesw/ncurses.h ]; then echo cflags=\"-D_GNU_SOURCE -I/usr/include/ncursesw\" echo libs=\"-lncursesw\" diff --git a/scripts/kconfig/mconf.c b/scripts/kconfig/mconf.c index 83b5836615fb..143c05fec161 100644 --- a/scripts/kconfig/mconf.c +++ b/scripts/kconfig/mconf.c @@ -490,7 +490,6 @@ static void build_conf(struct menu *menu) switch (prop->type) { case P_MENU: child_count++; - prompt = prompt; if (single_menu_mode) { item_make("%s%*c%s", menu->data ? "-->" : "++>", diff --git a/scripts/kconfig/nconf-cfg.sh b/scripts/kconfig/nconf-cfg.sh index 42f5ac73548e..001559ef0a60 100644 --- a/scripts/kconfig/nconf-cfg.sh +++ b/scripts/kconfig/nconf-cfg.sh @@ -4,20 +4,23 @@ PKG="ncursesw menuw panelw" PKG2="ncurses menu panel" -if pkg-config --exists $PKG; then - echo cflags=\"$(pkg-config --cflags $PKG)\" - echo libs=\"$(pkg-config --libs $PKG)\" - exit 0 -fi +if [ -n "$(command -v pkg-config)" ]; then + if pkg-config --exists $PKG; then + echo cflags=\"$(pkg-config --cflags $PKG)\" + echo libs=\"$(pkg-config --libs $PKG)\" + exit 0 + fi -if pkg-config --exists $PKG2; then - echo cflags=\"$(pkg-config --cflags $PKG2)\" - echo libs=\"$(pkg-config --libs $PKG2)\" - exit 0 + if pkg-config --exists $PKG2; then + echo cflags=\"$(pkg-config --cflags $PKG2)\" + echo libs=\"$(pkg-config --libs $PKG2)\" + exit 0 + fi fi -# Unfortunately, some distributions (e.g. openSUSE) cannot find ncurses -# by pkg-config. +# Check the default paths in case pkg-config is not installed. +# (Even if it is installed, some distributions such as openSUSE cannot +# find ncurses by pkg-config.) if [ -f /usr/include/ncursesw/ncurses.h ]; then echo cflags=\"-D_GNU_SOURCE -I/usr/include/ncursesw\" echo libs=\"-lncursesw -lmenuw -lpanelw\" diff --git a/scripts/kconfig/qconf-cfg.sh b/scripts/kconfig/qconf-cfg.sh index 0862e1562536..02ccc0ae1031 100755 --- a/scripts/kconfig/qconf-cfg.sh +++ b/scripts/kconfig/qconf-cfg.sh @@ -4,6 +4,13 @@ PKG="Qt5Core Qt5Gui Qt5Widgets" PKG2="QtCore QtGui" +if [ -z "$(command -v pkg-config)" ]; then + echo >&2 "*" + echo >&2 "* 'make xconfig' requires 'pkg-config'. Please install it." + echo >&2 "*" + exit 1 +fi + if pkg-config --exists $PKG; then echo cflags=\"-std=c++11 -fPIC $(pkg-config --cflags Qt5Core Qt5Gui Qt5Widgets)\" echo libs=\"$(pkg-config --libs $PKG)\" diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl index fe06e77c15eb..f599031260d5 100755 --- a/scripts/recordmcount.pl +++ b/scripts/recordmcount.pl @@ -389,6 +389,9 @@ if ($arch eq "x86_64") { $mcount_regex = "^\\s*([0-9a-fA-F]+):\\sR_RISCV_CALL\\s_mcount\$"; $type = ".quad"; $alignment = 2; +} elsif ($arch eq "nds32") { + $mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*R_NDS32_HI20_RELA\\s+_mcount\$"; + $alignment = 2; } else { die "Arch $arch is not supported with CONFIG_FTRACE_MCOUNT_RECORD"; } diff --git a/scripts/setlocalversion b/scripts/setlocalversion index 71f39410691b..79f7dd57d571 100755 --- a/scripts/setlocalversion +++ b/scripts/setlocalversion @@ -74,7 +74,7 @@ scm_version() fi # Check for uncommitted changes - if git diff-index --name-only HEAD | grep -qv "^scripts/package"; then + if git status -uno --porcelain | grep -qv '^.. scripts/package'; then printf '%s' -dirty fi diff --git a/scripts/subarch.include b/scripts/subarch.include new file mode 100644 index 000000000000..650682821126 --- /dev/null +++ b/scripts/subarch.include @@ -0,0 +1,13 @@ +# SUBARCH tells the usermode build what the underlying arch is. That is set +# first, and if a usermode build is happening, the "ARCH=um" on the command +# line overrides the setting of ARCH below. If a native build is happening, +# then ARCH is assigned, getting whatever value it gets normally, and +# SUBARCH is subsequently ignored. + +SUBARCH := $(shell uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ \ + -e s/sun4u/sparc64/ \ + -e s/arm.*/arm/ -e s/sa110/arm/ \ + -e s/s390x/s390/ -e s/parisc64/parisc/ \ + -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \ + -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ \ + -e s/riscv.*/riscv/) diff --git a/security/Kconfig b/security/Kconfig index 27d8b2688f75..d9aa521b5206 100644 --- a/security/Kconfig +++ b/security/Kconfig @@ -57,7 +57,7 @@ config SECURITY_NETWORK config PAGE_TABLE_ISOLATION bool "Remove the kernel mapping in user mode" default y - depends on X86 && !UML + depends on (X86_64 || X86_PAE) && !UML help This feature reduces the number of hardware side channels by ensuring that the majority of kernel addresses are not mapped diff --git a/security/apparmor/secid.c b/security/apparmor/secid.c index f2f22d00db18..4ccec1bcf6f5 100644 --- a/security/apparmor/secid.c +++ b/security/apparmor/secid.c @@ -79,7 +79,6 @@ int apparmor_secid_to_secctx(u32 secid, char **secdata, u32 *seclen) struct aa_label *label = aa_secid_to_label(secid); int len; - AA_BUG(!secdata); AA_BUG(!seclen); if (!label) diff --git a/security/keys/dh.c b/security/keys/dh.c index 711e89d8c415..3b602a1e27fa 100644 --- a/security/keys/dh.c +++ b/security/keys/dh.c @@ -300,7 +300,7 @@ long __keyctl_dh_compute(struct keyctl_dh_params __user *params, } dh_inputs.g_size = dlen; - dlen = dh_data_from_key(pcopy.private, &dh_inputs.key); + dlen = dh_data_from_key(pcopy.dh_private, &dh_inputs.key); if (dlen < 0) { ret = dlen; goto out2; diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c index 69517e18ef07..08d5662039e3 100644 --- a/sound/core/rawmidi.c +++ b/sound/core/rawmidi.c @@ -129,7 +129,7 @@ static int snd_rawmidi_runtime_create(struct snd_rawmidi_substream *substream) runtime->avail = 0; else runtime->avail = runtime->buffer_size; - runtime->buffer = kvmalloc(runtime->buffer_size, GFP_KERNEL); + runtime->buffer = kvzalloc(runtime->buffer_size, GFP_KERNEL); if (!runtime->buffer) { kfree(runtime); return -ENOMEM; @@ -655,7 +655,7 @@ static int resize_runtime_buffer(struct snd_rawmidi_runtime *runtime, if (params->avail_min < 1 || params->avail_min > params->buffer_size) return -EINVAL; if (params->buffer_size != runtime->buffer_size) { - newbuf = kvmalloc(params->buffer_size, GFP_KERNEL); + newbuf = kvzalloc(params->buffer_size, GFP_KERNEL); if (!newbuf) return -ENOMEM; spin_lock_irq(&runtime->lock); diff --git a/sound/hda/ext/hdac_ext_stream.c b/sound/hda/ext/hdac_ext_stream.c index 1bd27576db98..a835558ddbc9 100644 --- a/sound/hda/ext/hdac_ext_stream.c +++ b/sound/hda/ext/hdac_ext_stream.c @@ -146,7 +146,8 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_stream_decouple); */ void snd_hdac_ext_link_stream_start(struct hdac_ext_stream *stream) { - snd_hdac_updatel(stream->pplc_addr, AZX_REG_PPLCCTL, 0, AZX_PPLCCTL_RUN); + snd_hdac_updatel(stream->pplc_addr, AZX_REG_PPLCCTL, + AZX_PPLCCTL_RUN, AZX_PPLCCTL_RUN); } EXPORT_SYMBOL_GPL(snd_hdac_ext_link_stream_start); @@ -171,7 +172,8 @@ void snd_hdac_ext_link_stream_reset(struct hdac_ext_stream *stream) snd_hdac_ext_link_stream_clear(stream); - snd_hdac_updatel(stream->pplc_addr, AZX_REG_PPLCCTL, 0, AZX_PPLCCTL_STRST); + snd_hdac_updatel(stream->pplc_addr, AZX_REG_PPLCCTL, + AZX_PPLCCTL_STRST, AZX_PPLCCTL_STRST); udelay(3); timeout = 50; do { @@ -242,7 +244,7 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_link_set_stream_id); void snd_hdac_ext_link_clear_stream_id(struct hdac_ext_link *link, int stream) { - snd_hdac_updatew(link->ml_addr, AZX_REG_ML_LOSIDV, 0, (1 << stream)); + snd_hdac_updatew(link->ml_addr, AZX_REG_ML_LOSIDV, (1 << stream), 0); } EXPORT_SYMBOL_GPL(snd_hdac_ext_link_clear_stream_id); @@ -415,7 +417,6 @@ void snd_hdac_ext_stream_spbcap_enable(struct hdac_bus *bus, bool enable, int index) { u32 mask = 0; - u32 register_mask = 0; if (!bus->spbcap) { dev_err(bus->dev, "Address of SPB capability is NULL\n"); @@ -424,12 +425,8 @@ void snd_hdac_ext_stream_spbcap_enable(struct hdac_bus *bus, mask |= (1 << index); - register_mask = readl(bus->spbcap + AZX_REG_SPB_SPBFCCTL); - - mask |= register_mask; - if (enable) - snd_hdac_updatel(bus->spbcap, AZX_REG_SPB_SPBFCCTL, 0, mask); + snd_hdac_updatel(bus->spbcap, AZX_REG_SPB_SPBFCCTL, mask, mask); else snd_hdac_updatel(bus->spbcap, AZX_REG_SPB_SPBFCCTL, mask, 0); } @@ -503,7 +500,6 @@ void snd_hdac_ext_stream_drsm_enable(struct hdac_bus *bus, bool enable, int index) { u32 mask = 0; - u32 register_mask = 0; if (!bus->drsmcap) { dev_err(bus->dev, "Address of DRSM capability is NULL\n"); @@ -512,12 +508,8 @@ void snd_hdac_ext_stream_drsm_enable(struct hdac_bus *bus, mask |= (1 << index); - register_mask = readl(bus->drsmcap + AZX_REG_SPB_SPBFCCTL); - - mask |= register_mask; - if (enable) - snd_hdac_updatel(bus->drsmcap, AZX_REG_DRSM_CTL, 0, mask); + snd_hdac_updatel(bus->drsmcap, AZX_REG_DRSM_CTL, mask, mask); else snd_hdac_updatel(bus->drsmcap, AZX_REG_DRSM_CTL, mask, 0); } diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c index 0a5085537034..26d348b47867 100644 --- a/sound/pci/hda/hda_codec.c +++ b/sound/pci/hda/hda_codec.c @@ -3935,7 +3935,8 @@ void snd_hda_bus_reset_codecs(struct hda_bus *bus) list_for_each_codec(codec, bus) { /* FIXME: maybe a better way needed for forced reset */ - cancel_delayed_work_sync(&codec->jackpoll_work); + if (current_work() != &codec->jackpoll_work.work) + cancel_delayed_work_sync(&codec->jackpoll_work); #ifdef CONFIG_PM if (hda_codec_is_power_on(codec)) { hda_call_codec_suspend(codec); diff --git a/tools/arch/arm/include/uapi/asm/kvm.h b/tools/arch/arm/include/uapi/asm/kvm.h index 16e006f708ca..4602464ebdfb 100644 --- a/tools/arch/arm/include/uapi/asm/kvm.h +++ b/tools/arch/arm/include/uapi/asm/kvm.h @@ -27,6 +27,7 @@ #define __KVM_HAVE_GUEST_DEBUG #define __KVM_HAVE_IRQ_LINE #define __KVM_HAVE_READONLY_MEM +#define __KVM_HAVE_VCPU_EVENTS #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 @@ -125,6 +126,18 @@ struct kvm_sync_regs { struct kvm_arch_memory_slot { }; +/* for KVM_GET/SET_VCPU_EVENTS */ +struct kvm_vcpu_events { + struct { + __u8 serror_pending; + __u8 serror_has_esr; + /* Align it to 8 bytes */ + __u8 pad[6]; + __u64 serror_esr; + } exception; + __u32 reserved[12]; +}; + /* If you need to interpret the index values, here is the key: */ #define KVM_REG_ARM_COPROC_MASK 0x000000000FFF0000 #define KVM_REG_ARM_COPROC_SHIFT 16 diff --git a/tools/arch/arm64/include/uapi/asm/kvm.h b/tools/arch/arm64/include/uapi/asm/kvm.h index 4e76630dd655..97c3478ee6e7 100644 --- a/tools/arch/arm64/include/uapi/asm/kvm.h +++ b/tools/arch/arm64/include/uapi/asm/kvm.h @@ -39,6 +39,7 @@ #define __KVM_HAVE_GUEST_DEBUG #define __KVM_HAVE_IRQ_LINE #define __KVM_HAVE_READONLY_MEM +#define __KVM_HAVE_VCPU_EVENTS #define KVM_COALESCED_MMIO_PAGE_OFFSET 1 @@ -154,6 +155,18 @@ struct kvm_sync_regs { struct kvm_arch_memory_slot { }; +/* for KVM_GET/SET_VCPU_EVENTS */ +struct kvm_vcpu_events { + struct { + __u8 serror_pending; + __u8 serror_has_esr; + /* Align it to 8 bytes */ + __u8 pad[6]; + __u64 serror_esr; + } exception; + __u32 reserved[12]; +}; + /* If you need to interpret the index values, here is the key: */ #define KVM_REG_ARM_COPROC_MASK 0x000000000FFF0000 #define KVM_REG_ARM_COPROC_SHIFT 16 diff --git a/tools/arch/s390/include/uapi/asm/kvm.h b/tools/arch/s390/include/uapi/asm/kvm.h index 4cdaa55fabfe..9a50f02b9894 100644 --- a/tools/arch/s390/include/uapi/asm/kvm.h +++ b/tools/arch/s390/include/uapi/asm/kvm.h @@ -4,7 +4,7 @@ /* * KVM s390 specific structures and definitions * - * Copyright IBM Corp. 2008 + * Copyright IBM Corp. 2008, 2018 * * Author(s): Carsten Otte <cotte@de.ibm.com> * Christian Borntraeger <borntraeger@de.ibm.com> @@ -225,6 +225,7 @@ struct kvm_guest_debug_arch { #define KVM_SYNC_FPRS (1UL << 8) #define KVM_SYNC_GSCB (1UL << 9) #define KVM_SYNC_BPBC (1UL << 10) +#define KVM_SYNC_ETOKEN (1UL << 11) /* length and alignment of the sdnx as a power of two */ #define SDNXC 8 #define SDNXL (1UL << SDNXC) @@ -258,6 +259,8 @@ struct kvm_sync_regs { struct { __u64 reserved1[2]; __u64 gscb[4]; + __u64 etoken; + __u64 etoken_extension; }; }; }; diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index c535c2fdea13..86299efa804a 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -378,4 +378,41 @@ struct kvm_sync_regs { #define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0) #define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1) +#define KVM_STATE_NESTED_GUEST_MODE 0x00000001 +#define KVM_STATE_NESTED_RUN_PENDING 0x00000002 + +#define KVM_STATE_NESTED_SMM_GUEST_MODE 0x00000001 +#define KVM_STATE_NESTED_SMM_VMXON 0x00000002 + +struct kvm_vmx_nested_state { + __u64 vmxon_pa; + __u64 vmcs_pa; + + struct { + __u16 flags; + } smm; +}; + +/* for KVM_CAP_NESTED_STATE */ +struct kvm_nested_state { + /* KVM_STATE_* flags */ + __u16 flags; + + /* 0 for VMX, 1 for SVM. */ + __u16 format; + + /* 128 for SVM, 128 + VMCS size for VMX. */ + __u32 size; + + union { + /* VMXON, VMCS */ + struct kvm_vmx_nested_state vmx; + + /* Pad the header to 128 bytes. */ + __u8 pad[120]; + }; + + __u8 data[0]; +}; + #endif /* _ASM_X86_KVM_H */ diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index b2ec20e562bd..9c55077ca5dd 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -68,6 +68,7 @@ static const char * const map_type_name[] = { [BPF_MAP_TYPE_DEVMAP] = "devmap", [BPF_MAP_TYPE_SOCKMAP] = "sockmap", [BPF_MAP_TYPE_CPUMAP] = "cpumap", + [BPF_MAP_TYPE_XSKMAP] = "xskmap", [BPF_MAP_TYPE_SOCKHASH] = "sockhash", [BPF_MAP_TYPE_CGROUP_STORAGE] = "cgroup_storage", }; @@ -169,9 +170,28 @@ static int do_dump_btf(const struct btf_dumper *d, if (ret) goto err_end_obj; - jsonw_name(d->jw, "value"); + if (!map_is_per_cpu(map_info->type)) { + jsonw_name(d->jw, "value"); + ret = btf_dumper_type(d, map_info->btf_value_type_id, value); + } else { + unsigned int i, n, step; - ret = btf_dumper_type(d, map_info->btf_value_type_id, value); + jsonw_name(d->jw, "values"); + jsonw_start_array(d->jw); + n = get_possible_cpus(); + step = round_up(map_info->value_size, 8); + for (i = 0; i < n; i++) { + jsonw_start_object(d->jw); + jsonw_int_field(d->jw, "cpu", i); + jsonw_name(d->jw, "value"); + ret = btf_dumper_type(d, map_info->btf_value_type_id, + value + i * step); + jsonw_end_object(d->jw); + if (ret) + break; + } + jsonw_end_array(d->jw); + } err_end_obj: /* end of key-value pair */ @@ -298,6 +318,16 @@ static void print_entry_json(struct bpf_map_info *info, unsigned char *key, jsonw_end_object(json_wtr); } jsonw_end_array(json_wtr); + if (btf) { + struct btf_dumper d = { + .btf = btf, + .jw = json_wtr, + .is_plain_text = false, + }; + + jsonw_name(json_wtr, "formatted"); + do_dump_btf(&d, info, key, value); + } } jsonw_end_object(json_wtr); diff --git a/tools/bpf/bpftool/map_perf_ring.c b/tools/bpf/bpftool/map_perf_ring.c index 1832100d1b27..6d41323be291 100644 --- a/tools/bpf/bpftool/map_perf_ring.c +++ b/tools/bpf/bpftool/map_perf_ring.c @@ -194,8 +194,10 @@ int do_event_pipe(int argc, char **argv) } while (argc) { - if (argc < 2) + if (argc < 2) { BAD_ARG(); + goto err_close_map; + } if (is_prefix(*argv, "cpu")) { char *endptr; @@ -221,6 +223,7 @@ int do_event_pipe(int argc, char **argv) NEXT_ARG(); } else { BAD_ARG(); + goto err_close_map; } do_all = false; diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c index dbf6e8bd98ba..bbb2a8ef367c 100644 --- a/tools/hv/hv_kvp_daemon.c +++ b/tools/hv/hv_kvp_daemon.c @@ -286,7 +286,7 @@ static int kvp_key_delete(int pool, const __u8 *key, int key_size) * Found a match; just move the remaining * entries up. */ - if (i == num_records) { + if (i == (num_records - 1)) { kvp_file_info[pool].num_records--; kvp_update_file(pool); return 0; diff --git a/tools/include/linux/lockdep.h b/tools/include/linux/lockdep.h index 6b0c36a58fcb..e56997288f2b 100644 --- a/tools/include/linux/lockdep.h +++ b/tools/include/linux/lockdep.h @@ -30,9 +30,12 @@ struct task_struct { struct held_lock held_locks[MAX_LOCK_DEPTH]; gfp_t lockdep_reclaim_gfp; int pid; + int state; char comm[17]; }; +#define TASK_RUNNING 0 + extern struct task_struct *__curr(void); #define current (__curr()) diff --git a/tools/include/linux/nmi.h b/tools/include/linux/nmi.h new file mode 100644 index 000000000000..e69de29bb2d1 --- /dev/null +++ b/tools/include/linux/nmi.h diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index 42990676a55e..df4bedb9b01c 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -734,9 +734,11 @@ __SYSCALL(__NR_pkey_free, sys_pkey_free) __SYSCALL(__NR_statx, sys_statx) #define __NR_io_pgetevents 292 __SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents) +#define __NR_rseq 293 +__SYSCALL(__NR_rseq, sys_rseq) #undef __NR_syscalls -#define __NR_syscalls 293 +#define __NR_syscalls 294 /* * 32 bit systems traditionally used different diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h index 9c660e1688ab..300f336633f2 100644 --- a/tools/include/uapi/drm/drm.h +++ b/tools/include/uapi/drm/drm.h @@ -687,6 +687,15 @@ struct drm_get_cap { */ #define DRM_CLIENT_CAP_ASPECT_RATIO 4 +/** + * DRM_CLIENT_CAP_WRITEBACK_CONNECTORS + * + * If set to 1, the DRM core will expose special connectors to be used for + * writing back to memory the scene setup in the commit. Depends on client + * also supporting DRM_CLIENT_CAP_ATOMIC + */ +#define DRM_CLIENT_CAP_WRITEBACK_CONNECTORS 5 + /** DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */ struct drm_set_client_cap { __u64 capability; diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index cf01b6824244..58faab897201 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -161,9 +161,12 @@ enum { IFLA_EVENT, IFLA_NEW_NETNSID, IFLA_IF_NETNSID, + IFLA_TARGET_NETNSID = IFLA_IF_NETNSID, /* new alias */ IFLA_CARRIER_UP_COUNT, IFLA_CARRIER_DOWN_COUNT, IFLA_NEW_IFINDEX, + IFLA_MIN_MTU, + IFLA_MAX_MTU, __IFLA_MAX }; @@ -334,6 +337,7 @@ enum { IFLA_BRPORT_GROUP_FWD_MASK, IFLA_BRPORT_NEIGH_SUPPRESS, IFLA_BRPORT_ISOLATED, + IFLA_BRPORT_BACKUP_PORT, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) @@ -459,6 +463,16 @@ enum { #define IFLA_MACSEC_MAX (__IFLA_MACSEC_MAX - 1) +/* XFRM section */ +enum { + IFLA_XFRM_UNSPEC, + IFLA_XFRM_LINK, + IFLA_XFRM_IF_ID, + __IFLA_XFRM_MAX +}; + +#define IFLA_XFRM_MAX (__IFLA_XFRM_MAX - 1) + enum macsec_validation_type { MACSEC_VALIDATE_DISABLED = 0, MACSEC_VALIDATE_CHECK = 1, @@ -541,6 +555,7 @@ enum { IFLA_GENEVE_UDP_ZERO_CSUM6_TX, IFLA_GENEVE_UDP_ZERO_CSUM6_RX, IFLA_GENEVE_LABEL, + IFLA_GENEVE_TTL_INHERIT, __IFLA_GENEVE_MAX }; #define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1) @@ -920,6 +935,7 @@ enum { XDP_ATTACHED_DRV, XDP_ATTACHED_SKB, XDP_ATTACHED_HW, + XDP_ATTACHED_MULTI, }; enum { @@ -928,6 +944,9 @@ enum { IFLA_XDP_ATTACHED, IFLA_XDP_FLAGS, IFLA_XDP_PROG_ID, + IFLA_XDP_DRV_PROG_ID, + IFLA_XDP_SKB_PROG_ID, + IFLA_XDP_HW_PROG_ID, __IFLA_XDP_MAX, }; diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index b6270a3b38e9..07548de5c988 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -949,6 +949,9 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_GET_MSR_FEATURES 153 #define KVM_CAP_HYPERV_EVENTFD 154 #define KVM_CAP_HYPERV_TLBFLUSH 155 +#define KVM_CAP_S390_HPAGE_1M 156 +#define KVM_CAP_NESTED_STATE 157 +#define KVM_CAP_ARM_INJECT_SERROR_ESR 158 #ifdef KVM_CAP_IRQ_ROUTING @@ -1391,6 +1394,9 @@ struct kvm_enc_region { /* Available with KVM_CAP_HYPERV_EVENTFD */ #define KVM_HYPERV_EVENTFD _IOW(KVMIO, 0xbd, struct kvm_hyperv_eventfd) +/* Available with KVM_CAP_NESTED_STATE */ +#define KVM_GET_NESTED_STATE _IOWR(KVMIO, 0xbe, struct kvm_nested_state) +#define KVM_SET_NESTED_STATE _IOW(KVMIO, 0xbf, struct kvm_nested_state) /* Secure Encrypted Virtualization command */ enum sev_cmd_id { diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index eeb787b1c53c..f35eb72739c0 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -144,7 +144,7 @@ enum perf_event_sample_format { PERF_SAMPLE_MAX = 1U << 20, /* non-ABI */ - __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, + __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, /* non-ABI; internal use */ }; /* diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h index c51f8e5cc608..84c3de89696a 100644 --- a/tools/include/uapi/linux/vhost.h +++ b/tools/include/uapi/linux/vhost.h @@ -65,6 +65,7 @@ struct vhost_iotlb_msg { }; #define VHOST_IOTLB_MSG 0x1 +#define VHOST_IOTLB_MSG_V2 0x2 struct vhost_msg { int type; @@ -74,6 +75,15 @@ struct vhost_msg { }; }; +struct vhost_msg_v2 { + __u32 type; + __u32 reserved; + union { + struct vhost_iotlb_msg iotlb; + __u8 padding[64]; + }; +}; + struct vhost_memory_region { __u64 guest_phys_addr; __u64 memory_size; /* bytes */ @@ -160,6 +170,14 @@ struct vhost_memory { #define VHOST_GET_VRING_BUSYLOOP_TIMEOUT _IOW(VHOST_VIRTIO, 0x24, \ struct vhost_vring_state) +/* Set or get vhost backend capability */ + +/* Use message type V2 */ +#define VHOST_BACKEND_F_IOTLB_MSG_V2 0x1 + +#define VHOST_SET_BACKEND_FEATURES _IOW(VHOST_VIRTIO, 0x25, __u64) +#define VHOST_GET_BACKEND_FEATURES _IOR(VHOST_VIRTIO, 0x26, __u64) + /* VHOST_NET specific defines */ /* Attach virtio net ring to a raw socket, or tap device. diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat index 56c4b3f8a01b..439b8a27488d 100755 --- a/tools/kvm/kvm_stat/kvm_stat +++ b/tools/kvm/kvm_stat/kvm_stat @@ -759,12 +759,18 @@ class DebugfsProvider(Provider): if len(vms) == 0: self.do_read = False - self.paths = filter(lambda x: "{}-".format(pid) in x, vms) + self.paths = list(filter(lambda x: "{}-".format(pid) in x, vms)) else: self.paths = [] self.do_read = True - self.reset() + + def _verify_paths(self): + """Remove invalid paths""" + for path in self.paths: + if not os.path.exists(os.path.join(PATH_DEBUGFS_KVM, path)): + self.paths.remove(path) + continue def read(self, reset=0, by_guest=0): """Returns a dict with format:'file name / field -> current value'. @@ -780,6 +786,7 @@ class DebugfsProvider(Provider): # If no debugfs filtering support is available, then don't read. if not self.do_read: return results + self._verify_paths() paths = self.paths if self._pid == 0: @@ -1096,15 +1103,16 @@ class Tui(object): pid = self.stats.pid_filter self.screen.erase() gname = self.get_gname_from_pid(pid) + self._gname = gname if gname: gname = ('({})'.format(gname[:MAX_GUEST_NAME_LEN] + '...' if len(gname) > MAX_GUEST_NAME_LEN else gname)) if pid > 0: - self.screen.addstr(0, 0, 'kvm statistics - pid {0} {1}' - .format(pid, gname), curses.A_BOLD) + self._headline = 'kvm statistics - pid {0} {1}'.format(pid, gname) else: - self.screen.addstr(0, 0, 'kvm statistics - summary', curses.A_BOLD) + self._headline = 'kvm statistics - summary' + self.screen.addstr(0, 0, self._headline, curses.A_BOLD) if self.stats.fields_filter: regex = self.stats.fields_filter if len(regex) > MAX_REGEX_LEN: @@ -1162,6 +1170,19 @@ class Tui(object): return sorted_items + if not self._is_running_guest(self.stats.pid_filter): + if self._gname: + try: # ...to identify the guest by name in case it's back + pids = self.get_pid_from_gname(self._gname) + if len(pids) == 1: + self._refresh_header(pids[0]) + self._update_pid(pids[0]) + return + except: + pass + self._display_guest_dead() + # leave final data on screen + return row = 3 self.screen.move(row, 0) self.screen.clrtobot() @@ -1184,6 +1205,7 @@ class Tui(object): # print events tavg = 0 tcur = 0 + guest_removed = False for key, values in get_sorted_events(self, stats): if row >= self.screen.getmaxyx()[0] - 1 or values == (0, 0): break @@ -1191,7 +1213,10 @@ class Tui(object): key = self.get_gname_from_pid(key) if not key: continue - cur = int(round(values.delta / sleeptime)) if values.delta else '' + cur = int(round(values.delta / sleeptime)) if values.delta else 0 + if cur < 0: + guest_removed = True + continue if key[0] != ' ': if values.delta: tcur += values.delta @@ -1204,13 +1229,21 @@ class Tui(object): values.value * 100 / float(ltotal), cur)) row += 1 if row == 3: - self.screen.addstr(4, 1, 'No matching events reported yet') + if guest_removed: + self.screen.addstr(4, 1, 'Guest removed, updating...') + else: + self.screen.addstr(4, 1, 'No matching events reported yet') if row > 4: tavg = int(round(tcur / sleeptime)) if tcur > 0 else '' self.screen.addstr(row, 1, '%-40s %10d %8s' % ('Total', total, tavg), curses.A_BOLD) self.screen.refresh() + def _display_guest_dead(self): + marker = ' Guest is DEAD ' + y = min(len(self._headline), 80 - len(marker)) + self.screen.addstr(0, y, marker, curses.A_BLINK | curses.A_STANDOUT) + def _show_msg(self, text): """Display message centered text and exit on key press""" hint = 'Press any key to continue' @@ -1219,10 +1252,10 @@ class Tui(object): (x, term_width) = self.screen.getmaxyx() row = 2 for line in text: - start = (term_width - len(line)) / 2 + start = (term_width - len(line)) // 2 self.screen.addstr(row, start, line) row += 1 - self.screen.addstr(row + 1, (term_width - len(hint)) / 2, hint, + self.screen.addstr(row + 1, (term_width - len(hint)) // 2, hint, curses.A_STANDOUT) self.screen.getkey() @@ -1319,6 +1352,12 @@ class Tui(object): msg = '"' + str(val) + '": Invalid value' self._refresh_header() + def _is_running_guest(self, pid): + """Check if pid is still a running process.""" + if not pid: + return True + return os.path.isdir(os.path.join('/proc/', str(pid))) + def _show_vm_selection_by_guest(self): """Draws guest selection mask. @@ -1346,7 +1385,7 @@ class Tui(object): if not guest or guest == '0': break if guest.isdigit(): - if not os.path.isdir(os.path.join('/proc/', guest)): + if not self._is_running_guest(guest): msg = '"' + guest + '": Not a running process' continue pid = int(guest) diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf index b3d1b12a5081..5224ade3d5af 100644 --- a/tools/perf/Makefile.perf +++ b/tools/perf/Makefile.perf @@ -777,14 +777,12 @@ endif $(call QUIET_INSTALL, libexec) \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' ifndef NO_LIBBPF - $(call QUIET_INSTALL, lib) \ - $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf' - $(call QUIET_INSTALL, include/bpf) \ - $(INSTALL) include/bpf/*.h '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf' - $(call QUIET_INSTALL, lib) \ - $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf' - $(call QUIET_INSTALL, examples/bpf) \ - $(INSTALL) examples/bpf/*.c '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf' + $(call QUIET_INSTALL, bpf-headers) \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf'; \ + $(INSTALL) include/bpf/*.h -t '$(DESTDIR_SQ)$(perf_include_instdir_SQ)/bpf' + $(call QUIET_INSTALL, bpf-examples) \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf'; \ + $(INSTALL) examples/bpf/*.c -t '$(DESTDIR_SQ)$(perf_examples_instdir_SQ)/bpf' endif $(call QUIET_INSTALL, perf-archive) \ $(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)' diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile index f013b115dc86..dbef716a1913 100644 --- a/tools/perf/arch/arm64/Makefile +++ b/tools/perf/arch/arm64/Makefile @@ -11,7 +11,8 @@ PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1 out := $(OUTPUT)arch/arm64/include/generated/asm header := $(out)/syscalls.c -sysdef := $(srctree)/tools/include/uapi/asm-generic/unistd.h +incpath := $(srctree)/tools +sysdef := $(srctree)/tools/arch/arm64/include/uapi/asm/unistd.h sysprf := $(srctree)/tools/perf/arch/arm64/entry/syscalls/ systbl := $(sysprf)/mksyscalltbl @@ -19,7 +20,7 @@ systbl := $(sysprf)/mksyscalltbl _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)') $(header): $(sysdef) $(systbl) - $(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(sysdef) > $@ + $(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(incpath) $(sysdef) > $@ clean:: $(call QUIET_CLEAN, arm64) $(RM) $(header) diff --git a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl index 52e197317d3e..2dbb8cade048 100755 --- a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl +++ b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl @@ -11,7 +11,8 @@ gcc=$1 hostcc=$2 -input=$3 +incpath=$3 +input=$4 if ! test -r $input; then echo "Could not read input file" >&2 @@ -28,7 +29,6 @@ create_table_from_c() cat <<-_EoHEADER #include <stdio.h> - #define __ARCH_WANT_RENAMEAT #include "$input" int main(int argc, char *argv[]) { @@ -42,7 +42,7 @@ create_table_from_c() printf "%s\n" " printf(\"#define SYSCALLTBL_ARM64_MAX_ID %d\\n\", __NR_$last_sc);" printf "}\n" - } | $hostcc -o $create_table_exe -x c - + } | $hostcc -I $incpath/include/uapi -o $create_table_exe -x c - $create_table_exe diff --git a/tools/perf/arch/powerpc/util/sym-handling.c b/tools/perf/arch/powerpc/util/sym-handling.c index 20e7d74d86cd..10a44e946f77 100644 --- a/tools/perf/arch/powerpc/util/sym-handling.c +++ b/tools/perf/arch/powerpc/util/sym-handling.c @@ -22,15 +22,16 @@ bool elf__needs_adjust_symbols(GElf_Ehdr ehdr) #endif -#if !defined(_CALL_ELF) || _CALL_ELF != 2 int arch__choose_best_symbol(struct symbol *syma, struct symbol *symb __maybe_unused) { char *sym = syma->name; +#if !defined(_CALL_ELF) || _CALL_ELF != 2 /* Skip over any initial dot */ if (*sym == '.') sym++; +#endif /* Avoid "SyS" kernel syscall aliases */ if (strlen(sym) >= 3 && !strncmp(sym, "SyS", 3)) @@ -41,6 +42,7 @@ int arch__choose_best_symbol(struct symbol *syma, return SYMBOL_A; } +#if !defined(_CALL_ELF) || _CALL_ELF != 2 /* Allow matching against dot variants */ int arch__compare_symbol_names(const char *namea, const char *nameb) { diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h index c1bd979b957b..613709cfbbd0 100644 --- a/tools/perf/arch/x86/include/arch-tests.h +++ b/tools/perf/arch/x86/include/arch-tests.h @@ -9,6 +9,7 @@ struct test; int test__rdpmc(struct test *test __maybe_unused, int subtest); int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest); int test__insn_x86(struct test *test __maybe_unused, int subtest); +int test__bp_modify(struct test *test, int subtest); #ifdef HAVE_DWARF_UNWIND_SUPPORT struct thread; diff --git a/tools/perf/arch/x86/tests/Build b/tools/perf/arch/x86/tests/Build index 8e2c5a38c3b9..586849ff83a0 100644 --- a/tools/perf/arch/x86/tests/Build +++ b/tools/perf/arch/x86/tests/Build @@ -5,3 +5,4 @@ libperf-y += arch-tests.o libperf-y += rdpmc.o libperf-y += perf-time-to-tsc.o libperf-$(CONFIG_AUXTRACE) += insn-x86.o +libperf-$(CONFIG_X86_64) += bp-modify.o diff --git a/tools/perf/arch/x86/tests/arch-tests.c b/tools/perf/arch/x86/tests/arch-tests.c index cc1802ff5410..d47d3f8e3c8e 100644 --- a/tools/perf/arch/x86/tests/arch-tests.c +++ b/tools/perf/arch/x86/tests/arch-tests.c @@ -24,6 +24,12 @@ struct test arch_tests[] = { .func = test__insn_x86, }, #endif +#if defined(__x86_64__) + { + .desc = "x86 bp modify", + .func = test__bp_modify, + }, +#endif { .func = NULL, }, diff --git a/tools/perf/arch/x86/tests/bp-modify.c b/tools/perf/arch/x86/tests/bp-modify.c new file mode 100644 index 000000000000..f53e4406709f --- /dev/null +++ b/tools/perf/arch/x86/tests/bp-modify.c @@ -0,0 +1,213 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/compiler.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <sys/user.h> +#include <syscall.h> +#include <unistd.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/ptrace.h> +#include <asm/ptrace.h> +#include <errno.h> +#include "debug.h" +#include "tests/tests.h" +#include "arch-tests.h" + +static noinline int bp_1(void) +{ + pr_debug("in %s\n", __func__); + return 0; +} + +static noinline int bp_2(void) +{ + pr_debug("in %s\n", __func__); + return 0; +} + +static int spawn_child(void) +{ + int child = fork(); + + if (child == 0) { + /* + * The child sets itself for as tracee and + * waits in signal for parent to trace it, + * then it calls bp_1 and quits. + */ + int err = ptrace(PTRACE_TRACEME, 0, NULL, NULL); + + if (err) { + pr_debug("failed to PTRACE_TRACEME\n"); + exit(1); + } + + raise(SIGCONT); + bp_1(); + exit(0); + } + + return child; +} + +/* + * This tests creates HW breakpoint, tries to + * change it and checks it was properly changed. + */ +static int bp_modify1(void) +{ + pid_t child; + int status; + unsigned long rip = 0, dr7 = 1; + + child = spawn_child(); + + waitpid(child, &status, 0); + if (WIFEXITED(status)) { + pr_debug("tracee exited prematurely 1\n"); + return TEST_FAIL; + } + + /* + * The parent does following steps: + * - creates a new breakpoint (id 0) for bp_2 function + * - changes that breakponit to bp_1 function + * - waits for the breakpoint to hit and checks + * it has proper rip of bp_1 function + * - detaches the child + */ + if (ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[0]), bp_2)) { + pr_debug("failed to set breakpoint, 1st time: %s\n", + strerror(errno)); + goto out; + } + + if (ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[0]), bp_1)) { + pr_debug("failed to set breakpoint, 2nd time: %s\n", + strerror(errno)); + goto out; + } + + if (ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[7]), dr7)) { + pr_debug("failed to set dr7: %s\n", strerror(errno)); + goto out; + } + + if (ptrace(PTRACE_CONT, child, NULL, NULL)) { + pr_debug("failed to PTRACE_CONT: %s\n", strerror(errno)); + goto out; + } + + waitpid(child, &status, 0); + if (WIFEXITED(status)) { + pr_debug("tracee exited prematurely 2\n"); + return TEST_FAIL; + } + + rip = ptrace(PTRACE_PEEKUSER, child, + offsetof(struct user_regs_struct, rip), NULL); + if (rip == (unsigned long) -1) { + pr_debug("failed to PTRACE_PEEKUSER: %s\n", + strerror(errno)); + goto out; + } + + pr_debug("rip %lx, bp_1 %p\n", rip, bp_1); + +out: + if (ptrace(PTRACE_DETACH, child, NULL, NULL)) { + pr_debug("failed to PTRACE_DETACH: %s", strerror(errno)); + return TEST_FAIL; + } + + return rip == (unsigned long) bp_1 ? TEST_OK : TEST_FAIL; +} + +/* + * This tests creates HW breakpoint, tries to + * change it to bogus value and checks the original + * breakpoint is hit. + */ +static int bp_modify2(void) +{ + pid_t child; + int status; + unsigned long rip = 0, dr7 = 1; + + child = spawn_child(); + + waitpid(child, &status, 0); + if (WIFEXITED(status)) { + pr_debug("tracee exited prematurely 1\n"); + return TEST_FAIL; + } + + /* + * The parent does following steps: + * - creates a new breakpoint (id 0) for bp_1 function + * - tries to change that breakpoint to (-1) address + * - waits for the breakpoint to hit and checks + * it has proper rip of bp_1 function + * - detaches the child + */ + if (ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[0]), bp_1)) { + pr_debug("failed to set breakpoint: %s\n", + strerror(errno)); + goto out; + } + + if (ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[7]), dr7)) { + pr_debug("failed to set dr7: %s\n", strerror(errno)); + goto out; + } + + if (!ptrace(PTRACE_POKEUSER, child, + offsetof(struct user, u_debugreg[0]), (unsigned long) (-1))) { + pr_debug("failed, breakpoint set to bogus address\n"); + goto out; + } + + if (ptrace(PTRACE_CONT, child, NULL, NULL)) { + pr_debug("failed to PTRACE_CONT: %s\n", strerror(errno)); + goto out; + } + + waitpid(child, &status, 0); + if (WIFEXITED(status)) { + pr_debug("tracee exited prematurely 2\n"); + return TEST_FAIL; + } + + rip = ptrace(PTRACE_PEEKUSER, child, + offsetof(struct user_regs_struct, rip), NULL); + if (rip == (unsigned long) -1) { + pr_debug("failed to PTRACE_PEEKUSER: %s\n", + strerror(errno)); + goto out; + } + + pr_debug("rip %lx, bp_1 %p\n", rip, bp_1); + +out: + if (ptrace(PTRACE_DETACH, child, NULL, NULL)) { + pr_debug("failed to PTRACE_DETACH: %s", strerror(errno)); + return TEST_FAIL; + } + + return rip == (unsigned long) bp_1 ? TEST_OK : TEST_FAIL; +} + +int test__bp_modify(struct test *test __maybe_unused, + int subtest __maybe_unused) +{ + TEST_ASSERT_VAL("modify test 1 failed\n", !bp_modify1()); + TEST_ASSERT_VAL("modify test 2 failed\n", !bp_modify2()); + + return 0; +} diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 20061cf42288..28cd6a17491b 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -246,8 +246,14 @@ find_target: indirect_call: tok = strchr(endptr, '*'); - if (tok != NULL) - ops->target.addr = strtoull(tok + 1, NULL, 16); + if (tok != NULL) { + endptr++; + + /* Indirect call can use a non-rip register and offset: callq *0x8(%rbx). + * Do not parse such instruction. */ + if (strstr(endptr, "(%r") == NULL) + ops->target.addr = strtoull(endptr, NULL, 16); + } goto find_target; } @@ -276,7 +282,19 @@ bool ins__is_call(const struct ins *ins) return ins->ops == &call_ops || ins->ops == &s390_call_ops; } -static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, struct map_symbol *ms) +/* + * Prevents from matching commas in the comment section, e.g.: + * ffff200008446e70: b.cs ffff2000084470f4 <generic_exec_single+0x314> // b.hs, b.nlast + */ +static inline const char *validate_comma(const char *c, struct ins_operands *ops) +{ + if (ops->raw_comment && c > ops->raw_comment) + return NULL; + + return c; +} + +static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms) { struct map *map = ms->map; struct symbol *sym = ms->sym; @@ -285,6 +303,10 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op }; const char *c = strchr(ops->raw, ','); u64 start, end; + + ops->raw_comment = strchr(ops->raw, arch->objdump.comment_char); + c = validate_comma(c, ops); + /* * Examples of lines to parse for the _cpp_lex_token@@Base * function: @@ -304,6 +326,7 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op ops->target.addr = strtoull(c, NULL, 16); if (!ops->target.addr) { c = strchr(c, ','); + c = validate_comma(c, ops); if (c++ != NULL) ops->target.addr = strtoull(c, NULL, 16); } @@ -361,9 +384,12 @@ static int jump__scnprintf(struct ins *ins, char *bf, size_t size, return scnprintf(bf, size, "%-6s %s", ins->name, ops->target.sym->name); c = strchr(ops->raw, ','); + c = validate_comma(c, ops); + if (c != NULL) { const char *c2 = strchr(c + 1, ','); + c2 = validate_comma(c2, ops); /* check for 3-op insn */ if (c2 != NULL) c = c2; diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 005a5fe8a8c6..5399ba2321bb 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -22,6 +22,7 @@ struct ins { struct ins_operands { char *raw; + char *raw_comment; struct { char *raw; char *name; diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index c980bbff6353..1a61628a1c12 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -251,8 +251,9 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx) { struct perf_evsel *evsel = zalloc(perf_evsel__object.size); - if (evsel != NULL) - perf_evsel__init(evsel, attr, idx); + if (!evsel) + return NULL; + perf_evsel__init(evsel, attr, idx); if (perf_evsel__is_bpf_output(evsel)) { evsel->attr.sample_type |= (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c index 36d0763311ef..6a6929f208b4 100644 --- a/tools/perf/util/map.c +++ b/tools/perf/util/map.c @@ -576,6 +576,13 @@ struct symbol *map_groups__find_symbol(struct map_groups *mg, return NULL; } +static bool map__contains_symbol(struct map *map, struct symbol *sym) +{ + u64 ip = map->unmap_ip(map, sym->start); + + return ip >= map->start && ip < map->end; +} + struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct map **mapp) { @@ -591,6 +598,10 @@ struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, if (sym == NULL) continue; + if (!map__contains_symbol(pos, sym)) { + sym = NULL; + continue; + } if (mapp != NULL) *mapp = pos; goto out; diff --git a/tools/perf/util/trace-event-info.c b/tools/perf/util/trace-event-info.c index c85d0d1a65ed..7b0ca7cbb7de 100644 --- a/tools/perf/util/trace-event-info.c +++ b/tools/perf/util/trace-event-info.c @@ -377,7 +377,7 @@ out: static int record_saved_cmdline(void) { - unsigned int size; + unsigned long long size; char *path; struct stat st; int ret, err = 0; diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c index 920b1d58a068..e76214f8d596 100644 --- a/tools/perf/util/trace-event-parse.c +++ b/tools/perf/util/trace-event-parse.c @@ -164,16 +164,15 @@ void parse_ftrace_printk(struct tep_handle *pevent, void parse_saved_cmdline(struct tep_handle *pevent, char *file, unsigned int size __maybe_unused) { - char *comm; + char comm[17]; /* Max comm length in the kernel is 16. */ char *line; char *next = NULL; int pid; line = strtok_r(file, "\n", &next); while (line) { - sscanf(line, "%d %ms", &pid, &comm); - tep_register_comm(pevent, comm, pid); - free(comm); + if (sscanf(line, "%d %16s", &pid, comm) == 2) + tep_register_comm(pevent, comm, pid); line = strtok_r(NULL, "\n", &next); } } diff --git a/tools/testing/selftests/android/Makefile b/tools/testing/selftests/android/Makefile index 72c25a3cb658..d9a725478375 100644 --- a/tools/testing/selftests/android/Makefile +++ b/tools/testing/selftests/android/Makefile @@ -6,7 +6,7 @@ TEST_PROGS := run.sh include ../lib.mk -all: +all: khdr @for DIR in $(SUBDIRS); do \ BUILD_TARGET=$(OUTPUT)/$$DIR; \ mkdir $$BUILD_TARGET -p; \ diff --git a/tools/testing/selftests/android/ion/config b/tools/testing/selftests/android/config index b4ad748a9dd9..b4ad748a9dd9 100644 --- a/tools/testing/selftests/android/ion/config +++ b/tools/testing/selftests/android/config diff --git a/tools/testing/selftests/android/ion/Makefile b/tools/testing/selftests/android/ion/Makefile index e03695287f76..88cfe88e466f 100644 --- a/tools/testing/selftests/android/ion/Makefile +++ b/tools/testing/selftests/android/ion/Makefile @@ -10,6 +10,8 @@ $(TEST_GEN_FILES): ipcsocket.c ionutils.c TEST_PROGS := ion_test.sh +KSFT_KHDR_INSTALL := 1 +top_srcdir = ../../../../.. include ../../lib.mk $(OUTPUT)/ionapp_export: ionapp_export.c ipcsocket.c ionutils.c diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c index 6b5cfeb7a9cc..f42b3396d622 100644 --- a/tools/testing/selftests/bpf/test_btf.c +++ b/tools/testing/selftests/bpf/test_btf.c @@ -4,6 +4,7 @@ #include <linux/bpf.h> #include <linux/btf.h> #include <linux/err.h> +#include <linux/kernel.h> #include <bpf/bpf.h> #include <sys/resource.h> #include <libelf.h> @@ -45,7 +46,6 @@ static int count_result(int err) return err; } -#define min(a, b) ((a) < (b) ? (a) : (b)) #define __printf(a, b) __attribute__((format(printf, a, b))) __printf(1, 2) @@ -130,6 +130,7 @@ struct btf_raw_test { bool map_create_err; bool ordered_map; bool lossless_map; + bool percpu_map; int hdr_len_delta; int type_off_delta; int str_off_delta; @@ -2157,6 +2158,7 @@ static struct btf_pprint_test_meta { const char *map_name; bool ordered_map; bool lossless_map; + bool percpu_map; } pprint_tests_meta[] = { { .descr = "BTF pretty print array", @@ -2164,6 +2166,7 @@ static struct btf_pprint_test_meta { .map_name = "pprint_test_array", .ordered_map = true, .lossless_map = true, + .percpu_map = false, }, { @@ -2172,6 +2175,7 @@ static struct btf_pprint_test_meta { .map_name = "pprint_test_hash", .ordered_map = false, .lossless_map = true, + .percpu_map = false, }, { @@ -2180,30 +2184,83 @@ static struct btf_pprint_test_meta { .map_name = "pprint_test_lru_hash", .ordered_map = false, .lossless_map = false, + .percpu_map = false, +}, + +{ + .descr = "BTF pretty print percpu array", + .map_type = BPF_MAP_TYPE_PERCPU_ARRAY, + .map_name = "pprint_test_percpu_array", + .ordered_map = true, + .lossless_map = true, + .percpu_map = true, +}, + +{ + .descr = "BTF pretty print percpu hash", + .map_type = BPF_MAP_TYPE_PERCPU_HASH, + .map_name = "pprint_test_percpu_hash", + .ordered_map = false, + .lossless_map = true, + .percpu_map = true, +}, + +{ + .descr = "BTF pretty print lru percpu hash", + .map_type = BPF_MAP_TYPE_LRU_PERCPU_HASH, + .map_name = "pprint_test_lru_percpu_hash", + .ordered_map = false, + .lossless_map = false, + .percpu_map = true, }, }; -static void set_pprint_mapv(struct pprint_mapv *v, uint32_t i) +static void set_pprint_mapv(struct pprint_mapv *v, uint32_t i, + int num_cpus, int rounded_value_size) { - v->ui32 = i; - v->si32 = -i; - v->unused_bits2a = 3; - v->bits28 = i; - v->unused_bits2b = 3; - v->ui64 = i; - v->aenum = i & 0x03; + int cpu; + + for (cpu = 0; cpu < num_cpus; cpu++) { + v->ui32 = i + cpu; + v->si32 = -i; + v->unused_bits2a = 3; + v->bits28 = i; + v->unused_bits2b = 3; + v->ui64 = i; + v->aenum = i & 0x03; + v = (void *)v + rounded_value_size; + } } +static int check_line(const char *expected_line, int nexpected_line, + int expected_line_len, const char *line) +{ + if (CHECK(nexpected_line == expected_line_len, + "expected_line is too long")) + return -1; + + if (strcmp(expected_line, line)) { + fprintf(stderr, "unexpected pprint output\n"); + fprintf(stderr, "expected: %s", expected_line); + fprintf(stderr, " read: %s", line); + return -1; + } + + return 0; +} + + static int do_test_pprint(void) { const struct btf_raw_test *test = &pprint_test_template; struct bpf_create_map_attr create_attr = {}; + bool ordered_map, lossless_map, percpu_map; + int err, ret, num_cpus, rounded_value_size; + struct pprint_mapv *mapv = NULL; unsigned int key, nr_read_elems; - bool ordered_map, lossless_map; int map_fd = -1, btf_fd = -1; - struct pprint_mapv mapv = {}; unsigned int raw_btf_size; char expected_line[255]; FILE *pin_file = NULL; @@ -2212,7 +2269,6 @@ static int do_test_pprint(void) char *line = NULL; uint8_t *raw_btf; ssize_t nread; - int err, ret; fprintf(stderr, "%s......", test->descr); raw_btf = btf_raw_create(&hdr_tmpl, test->raw_types, @@ -2261,9 +2317,18 @@ static int do_test_pprint(void) if (CHECK(err, "bpf_obj_pin(%s): errno:%d.", pin_path, errno)) goto done; + percpu_map = test->percpu_map; + num_cpus = percpu_map ? bpf_num_possible_cpus() : 1; + rounded_value_size = round_up(sizeof(struct pprint_mapv), 8); + mapv = calloc(num_cpus, rounded_value_size); + if (CHECK(!mapv, "mapv allocation failure")) { + err = -1; + goto done; + } + for (key = 0; key < test->max_entries; key++) { - set_pprint_mapv(&mapv, key); - bpf_map_update_elem(map_fd, &key, &mapv, 0); + set_pprint_mapv(mapv, key, num_cpus, rounded_value_size); + bpf_map_update_elem(map_fd, &key, mapv, 0); } pin_file = fopen(pin_path, "r"); @@ -2286,33 +2351,74 @@ static int do_test_pprint(void) ordered_map = test->ordered_map; lossless_map = test->lossless_map; do { + struct pprint_mapv *cmapv; ssize_t nexpected_line; unsigned int next_key; + int cpu; next_key = ordered_map ? nr_read_elems : atoi(line); - set_pprint_mapv(&mapv, next_key); - nexpected_line = snprintf(expected_line, sizeof(expected_line), - "%u: {%u,0,%d,0x%x,0x%x,0x%x,{%lu|[%u,%u,%u,%u,%u,%u,%u,%u]},%s}\n", - next_key, - mapv.ui32, mapv.si32, - mapv.unused_bits2a, mapv.bits28, mapv.unused_bits2b, - mapv.ui64, - mapv.ui8a[0], mapv.ui8a[1], mapv.ui8a[2], mapv.ui8a[3], - mapv.ui8a[4], mapv.ui8a[5], mapv.ui8a[6], mapv.ui8a[7], - pprint_enum_str[mapv.aenum]); - - if (CHECK(nexpected_line == sizeof(expected_line), - "expected_line is too long")) { - err = -1; - goto done; + set_pprint_mapv(mapv, next_key, num_cpus, rounded_value_size); + cmapv = mapv; + + for (cpu = 0; cpu < num_cpus; cpu++) { + if (percpu_map) { + /* for percpu map, the format looks like: + * <key>: { + * cpu0: <value_on_cpu0> + * cpu1: <value_on_cpu1> + * ... + * cpun: <value_on_cpun> + * } + * + * let us verify the line containing the key here. + */ + if (cpu == 0) { + nexpected_line = snprintf(expected_line, + sizeof(expected_line), + "%u: {\n", + next_key); + + err = check_line(expected_line, nexpected_line, + sizeof(expected_line), line); + if (err == -1) + goto done; + } + + /* read value@cpu */ + nread = getline(&line, &line_len, pin_file); + if (nread < 0) + break; + } + + nexpected_line = snprintf(expected_line, sizeof(expected_line), + "%s%u: {%u,0,%d,0x%x,0x%x,0x%x," + "{%lu|[%u,%u,%u,%u,%u,%u,%u,%u]},%s}\n", + percpu_map ? "\tcpu" : "", + percpu_map ? cpu : next_key, + cmapv->ui32, cmapv->si32, + cmapv->unused_bits2a, + cmapv->bits28, + cmapv->unused_bits2b, + cmapv->ui64, + cmapv->ui8a[0], cmapv->ui8a[1], + cmapv->ui8a[2], cmapv->ui8a[3], + cmapv->ui8a[4], cmapv->ui8a[5], + cmapv->ui8a[6], cmapv->ui8a[7], + pprint_enum_str[cmapv->aenum]); + + err = check_line(expected_line, nexpected_line, + sizeof(expected_line), line); + if (err == -1) + goto done; + + cmapv = (void *)cmapv + rounded_value_size; } - if (strcmp(expected_line, line)) { - err = -1; - fprintf(stderr, "unexpected pprint output\n"); - fprintf(stderr, "expected: %s", expected_line); - fprintf(stderr, " read: %s", line); - goto done; + if (percpu_map) { + /* skip the last bracket for the percpu map */ + nread = getline(&line, &line_len, pin_file); + if (nread < 0) + break; } nread = getline(&line, &line_len, pin_file); @@ -2334,6 +2440,8 @@ static int do_test_pprint(void) err = 0; done: + if (mapv) + free(mapv); if (!err) fprintf(stderr, "OK"); if (*btf_log_buf && (err || args.always_log)) @@ -2361,6 +2469,7 @@ static int test_pprint(void) pprint_test_template.map_name = pprint_tests_meta[i].map_name; pprint_test_template.ordered_map = pprint_tests_meta[i].ordered_map; pprint_test_template.lossless_map = pprint_tests_meta[i].lossless_map; + pprint_test_template.percpu_map = pprint_tests_meta[i].percpu_map; err |= count_result(do_test_pprint()); } diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index 0c7d9e556b47..ac7de38e5c63 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -469,8 +469,6 @@ static int sendmsg_test(struct sockmap_options *opt) fprintf(stderr, "msg_loop_rx: iov_count %i iov_buf %i cnt %i err %i\n", iov_count, iov_buf, cnt, err); - shutdown(p2, SHUT_RDWR); - shutdown(p1, SHUT_RDWR); if (s.end.tv_sec - s.start.tv_sec) { sent_Bps = sentBps(s); recvd_Bps = recvdBps(s); @@ -500,7 +498,6 @@ static int sendmsg_test(struct sockmap_options *opt) fprintf(stderr, "msg_loop_tx: iov_count %i iov_buf %i cnt %i err %i\n", iov_count, iov_buf, cnt, err); - shutdown(c1, SHUT_RDWR); if (s.end.tv_sec - s.start.tv_sec) { sent_Bps = sentBps(s); recvd_Bps = recvdBps(s); @@ -1348,9 +1345,9 @@ static int populate_progs(char *bpf_file) return 0; } -static int __test_suite(char *bpf_file) +static int __test_suite(int cg_fd, char *bpf_file) { - int cg_fd, err; + int err, cleanup = cg_fd; err = populate_progs(bpf_file); if (err < 0) { @@ -1358,22 +1355,24 @@ static int __test_suite(char *bpf_file) return err; } - if (setup_cgroup_environment()) { - fprintf(stderr, "ERROR: cgroup env failed\n"); - return -EINVAL; - } - - cg_fd = create_and_get_cgroup(CG_PATH); if (cg_fd < 0) { - fprintf(stderr, - "ERROR: (%i) open cg path failed: %s\n", - cg_fd, optarg); - return cg_fd; - } + if (setup_cgroup_environment()) { + fprintf(stderr, "ERROR: cgroup env failed\n"); + return -EINVAL; + } + + cg_fd = create_and_get_cgroup(CG_PATH); + if (cg_fd < 0) { + fprintf(stderr, + "ERROR: (%i) open cg path failed: %s\n", + cg_fd, optarg); + return cg_fd; + } - if (join_cgroup(CG_PATH)) { - fprintf(stderr, "ERROR: failed to join cgroup\n"); - return -EINVAL; + if (join_cgroup(CG_PATH)) { + fprintf(stderr, "ERROR: failed to join cgroup\n"); + return -EINVAL; + } } /* Tests basic commands and APIs with range of iov values */ @@ -1394,20 +1393,24 @@ static int __test_suite(char *bpf_file) out: printf("Summary: %i PASSED %i FAILED\n", passed, failed); - cleanup_cgroup_environment(); - close(cg_fd); + if (cleanup < 0) { + cleanup_cgroup_environment(); + close(cg_fd); + } return err; } -static int test_suite(void) +static int test_suite(int cg_fd) { int err; - err = __test_suite(BPF_SOCKMAP_FILENAME); + err = __test_suite(cg_fd, BPF_SOCKMAP_FILENAME); if (err) goto out; - err = __test_suite(BPF_SOCKHASH_FILENAME); + err = __test_suite(cg_fd, BPF_SOCKHASH_FILENAME); out: + if (cg_fd > -1) + close(cg_fd); return err; } @@ -1420,7 +1423,7 @@ int main(int argc, char **argv) int test = PING_PONG; if (argc < 2) - return test_suite(); + return test_suite(-1); while ((opt = getopt_long(argc, argv, ":dhvc:r:i:l:t:", long_options, &longindex)) != -1) { @@ -1486,6 +1489,9 @@ int main(int argc, char **argv) } } + if (argc <= 3 && cg_fd) + return test_suite(cg_fd); + if (!cg_fd) { fprintf(stderr, "%s requires cgroup option: --cgroup <path>\n", argv[0]); diff --git a/tools/testing/selftests/bpf/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/test_tcpbpf_kern.c index 4b7fd540cea9..74f73b33a7b0 100644 --- a/tools/testing/selftests/bpf/test_tcpbpf_kern.c +++ b/tools/testing/selftests/bpf/test_tcpbpf_kern.c @@ -5,6 +5,7 @@ #include <linux/if_ether.h> #include <linux/if_packet.h> #include <linux/ip.h> +#include <linux/ipv6.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/tcp.h> @@ -17,6 +18,13 @@ struct bpf_map_def SEC("maps") global_map = { .type = BPF_MAP_TYPE_ARRAY, .key_size = sizeof(__u32), .value_size = sizeof(struct tcpbpf_globals), + .max_entries = 4, +}; + +struct bpf_map_def SEC("maps") sockopt_results = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(int), .max_entries = 2, }; @@ -45,11 +53,14 @@ int _version SEC("version") = 1; SEC("sockops") int bpf_testcb(struct bpf_sock_ops *skops) { - int rv = -1; - int bad_call_rv = 0; + char header[sizeof(struct ipv6hdr) + sizeof(struct tcphdr)]; + struct tcphdr *thdr; int good_call_rv = 0; - int op; + int bad_call_rv = 0; + int save_syn = 1; + int rv = -1; int v = 0; + int op; op = (int) skops->op; @@ -82,6 +93,21 @@ int bpf_testcb(struct bpf_sock_ops *skops) v = 0xff; rv = bpf_setsockopt(skops, SOL_IPV6, IPV6_TCLASS, &v, sizeof(v)); + if (skops->family == AF_INET6) { + v = bpf_getsockopt(skops, IPPROTO_TCP, TCP_SAVED_SYN, + header, (sizeof(struct ipv6hdr) + + sizeof(struct tcphdr))); + if (!v) { + int offset = sizeof(struct ipv6hdr); + + thdr = (struct tcphdr *)(header + offset); + v = thdr->syn; + __u32 key = 1; + + bpf_map_update_elem(&sockopt_results, &key, &v, + BPF_ANY); + } + } break; case BPF_SOCK_OPS_RTO_CB: break; @@ -111,6 +137,12 @@ int bpf_testcb(struct bpf_sock_ops *skops) break; case BPF_SOCK_OPS_TCP_LISTEN_CB: bpf_sock_ops_cb_flags_set(skops, BPF_SOCK_OPS_STATE_CB_FLAG); + v = bpf_setsockopt(skops, IPPROTO_TCP, TCP_SAVE_SYN, + &save_syn, sizeof(save_syn)); + /* Update global map w/ result of setsock opt */ + __u32 key = 0; + + bpf_map_update_elem(&sockopt_results, &key, &v, BPF_ANY); break; default: rv = -1; diff --git a/tools/testing/selftests/bpf/test_tcpbpf_user.c b/tools/testing/selftests/bpf/test_tcpbpf_user.c index a275c2971376..e6eebda7d112 100644 --- a/tools/testing/selftests/bpf/test_tcpbpf_user.c +++ b/tools/testing/selftests/bpf/test_tcpbpf_user.c @@ -54,6 +54,26 @@ err: return -1; } +int verify_sockopt_result(int sock_map_fd) +{ + __u32 key = 0; + int res; + int rv; + + /* check setsockopt for SAVE_SYN */ + rv = bpf_map_lookup_elem(sock_map_fd, &key, &res); + EXPECT_EQ(0, rv, "d"); + EXPECT_EQ(0, res, "d"); + key = 1; + /* check getsockopt for SAVED_SYN */ + rv = bpf_map_lookup_elem(sock_map_fd, &key, &res); + EXPECT_EQ(0, rv, "d"); + EXPECT_EQ(1, res, "d"); + return 0; +err: + return -1; +} + static int bpf_find_map(const char *test, struct bpf_object *obj, const char *name) { @@ -70,11 +90,11 @@ static int bpf_find_map(const char *test, struct bpf_object *obj, int main(int argc, char **argv) { const char *file = "test_tcpbpf_kern.o"; + int prog_fd, map_fd, sock_map_fd; struct tcpbpf_globals g = {0}; const char *cg_path = "/foo"; int error = EXIT_FAILURE; struct bpf_object *obj; - int prog_fd, map_fd; int cg_fd = -1; __u32 key = 0; int rv; @@ -110,6 +130,10 @@ int main(int argc, char **argv) if (map_fd < 0) goto err; + sock_map_fd = bpf_find_map(__func__, obj, "sockopt_results"); + if (sock_map_fd < 0) + goto err; + rv = bpf_map_lookup_elem(map_fd, &key, &g); if (rv != 0) { printf("FAILED: bpf_map_lookup_elem returns %d\n", rv); @@ -121,6 +145,11 @@ int main(int argc, char **argv) goto err; } + if (verify_sockopt_result(sock_map_fd)) { + printf("FAILED: Wrong sockopt stats\n"); + goto err; + } + printf("PASSED!\n"); error = 0; err: diff --git a/tools/testing/selftests/cgroup/.gitignore b/tools/testing/selftests/cgroup/.gitignore index 95eb3a53c381..adacda50a4b2 100644 --- a/tools/testing/selftests/cgroup/.gitignore +++ b/tools/testing/selftests/cgroup/.gitignore @@ -1 +1,2 @@ test_memcontrol +test_core diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/cgroup_util.c index 1c5d2b2a583b..14c9fe284806 100644 --- a/tools/testing/selftests/cgroup/cgroup_util.c +++ b/tools/testing/selftests/cgroup/cgroup_util.c @@ -89,17 +89,28 @@ int cg_read(const char *cgroup, const char *control, char *buf, size_t len) int cg_read_strcmp(const char *cgroup, const char *control, const char *expected) { - size_t size = strlen(expected) + 1; + size_t size; char *buf; + int ret; + + /* Handle the case of comparing against empty string */ + if (!expected) + size = 32; + else + size = strlen(expected) + 1; buf = malloc(size); if (!buf) return -1; - if (cg_read(cgroup, control, buf, size)) + if (cg_read(cgroup, control, buf, size)) { + free(buf); return -1; + } - return strcmp(expected, buf); + ret = strcmp(expected, buf); + free(buf); + return ret; } int cg_read_strstr(const char *cgroup, const char *control, const char *needle) @@ -337,3 +348,24 @@ int is_swap_enabled(void) return cnt > 1; } + +int set_oom_adj_score(int pid, int score) +{ + char path[PATH_MAX]; + int fd, len; + + sprintf(path, "/proc/%d/oom_score_adj", pid); + + fd = open(path, O_WRONLY | O_APPEND); + if (fd < 0) + return fd; + + len = dprintf(fd, "%d", score); + if (len < 0) { + close(fd); + return len; + } + + close(fd); + return 0; +} diff --git a/tools/testing/selftests/cgroup/cgroup_util.h b/tools/testing/selftests/cgroup/cgroup_util.h index 1ff6f9f1abdc..9ac8b7958f83 100644 --- a/tools/testing/selftests/cgroup/cgroup_util.h +++ b/tools/testing/selftests/cgroup/cgroup_util.h @@ -40,3 +40,4 @@ extern int get_temp_fd(void); extern int alloc_pagecache(int fd, size_t size); extern int alloc_anon(const char *cgroup, void *arg); extern int is_swap_enabled(void); +extern int set_oom_adj_score(int pid, int score); diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c index cf0bddc9d271..28d321ba311b 100644 --- a/tools/testing/selftests/cgroup/test_memcontrol.c +++ b/tools/testing/selftests/cgroup/test_memcontrol.c @@ -2,6 +2,7 @@ #define _GNU_SOURCE #include <linux/limits.h> +#include <linux/oom.h> #include <fcntl.h> #include <stdio.h> #include <stdlib.h> @@ -202,6 +203,36 @@ static int alloc_pagecache_50M_noexit(const char *cgroup, void *arg) return 0; } +static int alloc_anon_noexit(const char *cgroup, void *arg) +{ + int ppid = getppid(); + + if (alloc_anon(cgroup, arg)) + return -1; + + while (getppid() == ppid) + sleep(1); + + return 0; +} + +/* + * Wait until processes are killed asynchronously by the OOM killer + * If we exceed a timeout, fail. + */ +static int cg_test_proc_killed(const char *cgroup) +{ + int limit; + + for (limit = 10; limit > 0; limit--) { + if (cg_read_strcmp(cgroup, "cgroup.procs", "") == 0) + return 0; + + usleep(100000); + } + return -1; +} + /* * First, this test creates the following hierarchy: * A memory.min = 50M, memory.max = 200M @@ -964,6 +995,177 @@ cleanup: return ret; } +/* + * This test disables swapping and tries to allocate anonymous memory + * up to OOM with memory.group.oom set. Then it checks that all + * processes in the leaf (but not the parent) were killed. + */ +static int test_memcg_oom_group_leaf_events(const char *root) +{ + int ret = KSFT_FAIL; + char *parent, *child; + + parent = cg_name(root, "memcg_test_0"); + child = cg_name(root, "memcg_test_0/memcg_test_1"); + + if (!parent || !child) + goto cleanup; + + if (cg_create(parent)) + goto cleanup; + + if (cg_create(child)) + goto cleanup; + + if (cg_write(parent, "cgroup.subtree_control", "+memory")) + goto cleanup; + + if (cg_write(child, "memory.max", "50M")) + goto cleanup; + + if (cg_write(child, "memory.swap.max", "0")) + goto cleanup; + + if (cg_write(child, "memory.oom.group", "1")) + goto cleanup; + + cg_run_nowait(parent, alloc_anon_noexit, (void *) MB(60)); + cg_run_nowait(child, alloc_anon_noexit, (void *) MB(1)); + cg_run_nowait(child, alloc_anon_noexit, (void *) MB(1)); + if (!cg_run(child, alloc_anon, (void *)MB(100))) + goto cleanup; + + if (cg_test_proc_killed(child)) + goto cleanup; + + if (cg_read_key_long(child, "memory.events", "oom_kill ") <= 0) + goto cleanup; + + if (cg_read_key_long(parent, "memory.events", "oom_kill ") != 0) + goto cleanup; + + ret = KSFT_PASS; + +cleanup: + if (child) + cg_destroy(child); + if (parent) + cg_destroy(parent); + free(child); + free(parent); + + return ret; +} + +/* + * This test disables swapping and tries to allocate anonymous memory + * up to OOM with memory.group.oom set. Then it checks that all + * processes in the parent and leaf were killed. + */ +static int test_memcg_oom_group_parent_events(const char *root) +{ + int ret = KSFT_FAIL; + char *parent, *child; + + parent = cg_name(root, "memcg_test_0"); + child = cg_name(root, "memcg_test_0/memcg_test_1"); + + if (!parent || !child) + goto cleanup; + + if (cg_create(parent)) + goto cleanup; + + if (cg_create(child)) + goto cleanup; + + if (cg_write(parent, "memory.max", "80M")) + goto cleanup; + + if (cg_write(parent, "memory.swap.max", "0")) + goto cleanup; + + if (cg_write(parent, "memory.oom.group", "1")) + goto cleanup; + + cg_run_nowait(parent, alloc_anon_noexit, (void *) MB(60)); + cg_run_nowait(child, alloc_anon_noexit, (void *) MB(1)); + cg_run_nowait(child, alloc_anon_noexit, (void *) MB(1)); + + if (!cg_run(child, alloc_anon, (void *)MB(100))) + goto cleanup; + + if (cg_test_proc_killed(child)) + goto cleanup; + if (cg_test_proc_killed(parent)) + goto cleanup; + + ret = KSFT_PASS; + +cleanup: + if (child) + cg_destroy(child); + if (parent) + cg_destroy(parent); + free(child); + free(parent); + + return ret; +} + +/* + * This test disables swapping and tries to allocate anonymous memory + * up to OOM with memory.group.oom set. Then it checks that all + * processes were killed except those set with OOM_SCORE_ADJ_MIN + */ +static int test_memcg_oom_group_score_events(const char *root) +{ + int ret = KSFT_FAIL; + char *memcg; + int safe_pid; + + memcg = cg_name(root, "memcg_test_0"); + + if (!memcg) + goto cleanup; + + if (cg_create(memcg)) + goto cleanup; + + if (cg_write(memcg, "memory.max", "50M")) + goto cleanup; + + if (cg_write(memcg, "memory.swap.max", "0")) + goto cleanup; + + if (cg_write(memcg, "memory.oom.group", "1")) + goto cleanup; + + safe_pid = cg_run_nowait(memcg, alloc_anon_noexit, (void *) MB(1)); + if (set_oom_adj_score(safe_pid, OOM_SCORE_ADJ_MIN)) + goto cleanup; + + cg_run_nowait(memcg, alloc_anon_noexit, (void *) MB(1)); + if (!cg_run(memcg, alloc_anon, (void *)MB(100))) + goto cleanup; + + if (cg_read_key_long(memcg, "memory.events", "oom_kill ") != 3) + goto cleanup; + + if (kill(safe_pid, SIGKILL)) + goto cleanup; + + ret = KSFT_PASS; + +cleanup: + if (memcg) + cg_destroy(memcg); + free(memcg); + + return ret; +} + + #define T(x) { x, #x } struct memcg_test { int (*fn)(const char *root); @@ -978,6 +1180,9 @@ struct memcg_test { T(test_memcg_oom_events), T(test_memcg_swap_max), T(test_memcg_sock), + T(test_memcg_oom_group_leaf_events), + T(test_memcg_oom_group_parent_events), + T(test_memcg_oom_group_score_events), }; #undef T diff --git a/tools/testing/selftests/efivarfs/config b/tools/testing/selftests/efivarfs/config new file mode 100644 index 000000000000..4e151f1005b2 --- /dev/null +++ b/tools/testing/selftests/efivarfs/config @@ -0,0 +1 @@ +CONFIG_EFIVAR_FS=y diff --git a/tools/testing/selftests/futex/functional/Makefile b/tools/testing/selftests/futex/functional/Makefile index ff8feca49746..ad1eeb14fda7 100644 --- a/tools/testing/selftests/futex/functional/Makefile +++ b/tools/testing/selftests/futex/functional/Makefile @@ -18,6 +18,7 @@ TEST_GEN_FILES := \ TEST_PROGS := run.sh +top_srcdir = ../../../../.. include ../../lib.mk $(TEST_GEN_FILES): $(HEADERS) diff --git a/tools/testing/selftests/gpio/Makefile b/tools/testing/selftests/gpio/Makefile index 1bbb47565c55..4665cdbf1a8d 100644 --- a/tools/testing/selftests/gpio/Makefile +++ b/tools/testing/selftests/gpio/Makefile @@ -21,11 +21,8 @@ endef CFLAGS += -O2 -g -std=gnu99 -Wall -I../../../../usr/include/ LDLIBS += -lmount -I/usr/include/libmount -$(BINARIES): ../../../gpio/gpio-utils.o ../../../../usr/include/linux/gpio.h +$(BINARIES):| khdr +$(BINARIES): ../../../gpio/gpio-utils.o ../../../gpio/gpio-utils.o: make ARCH=$(ARCH) CROSS_COMPILE=$(CROSS_COMPILE) -C ../../../gpio - -../../../../usr/include/linux/gpio.h: - make -C ../../../.. headers_install INSTALL_HDR_PATH=$(shell pwd)/../../../../usr/ - diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index 15e6b75fc3a5..a3edb2c8e43d 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -19,7 +19,6 @@ #define KSFT_FAIL 1 #define KSFT_XFAIL 2 #define KSFT_XPASS 3 -/* Treat skip as pass */ #define KSFT_SKIP 4 /* counters */ diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 03b0f551bedf..87d1a8488af8 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -37,9 +37,6 @@ $(LIBKVM_OBJ): $(OUTPUT)/%.o: %.c $(OUTPUT)/libkvm.a: $(LIBKVM_OBJ) $(AR) crs $@ $^ -$(LINUX_HDR_PATH): - make -C $(top_srcdir) headers_install - -all: $(STATIC_LIBS) $(LINUX_HDR_PATH) +all: $(STATIC_LIBS) $(TEST_GEN_PROGS): $(STATIC_LIBS) -$(TEST_GEN_PROGS) $(LIBKVM_OBJ): | $(LINUX_HDR_PATH) +$(STATIC_LIBS):| khdr diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk index 17ab36605a8e..0a8e75886224 100644 --- a/tools/testing/selftests/lib.mk +++ b/tools/testing/selftests/lib.mk @@ -16,8 +16,20 @@ TEST_GEN_PROGS := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS)) TEST_GEN_PROGS_EXTENDED := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS_EXTENDED)) TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES)) +top_srcdir ?= ../../../.. +include $(top_srcdir)/scripts/subarch.include +ARCH ?= $(SUBARCH) + all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) +.PHONY: khdr +khdr: + make ARCH=$(ARCH) -C $(top_srcdir) headers_install + +ifdef KSFT_KHDR_INSTALL +$(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES):| khdr +endif + .ONESHELL: define RUN_TEST_PRINT_RESULT TEST_HDR_MSG="selftests: "`basename $$PWD`:" $$BASENAME_TEST"; \ diff --git a/tools/testing/selftests/memory-hotplug/config b/tools/testing/selftests/memory-hotplug/config index 2fde30191a47..a7e8cd5bb265 100644 --- a/tools/testing/selftests/memory-hotplug/config +++ b/tools/testing/selftests/memory-hotplug/config @@ -2,3 +2,4 @@ CONFIG_MEMORY_HOTPLUG=y CONFIG_MEMORY_HOTPLUG_SPARSE=y CONFIG_NOTIFIER_ERROR_INJECTION=y CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m +CONFIG_MEMORY_HOTREMOVE=y diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 78b24cf76f40..8cf22b3c2563 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -14,3 +14,4 @@ udpgso_bench_rx udpgso_bench_tx tcp_inq tls +ip_defrag diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 9cca68e440a0..256d82d5fa87 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -5,16 +5,17 @@ CFLAGS = -Wall -Wl,--no-as-needed -O2 -g CFLAGS += -I../../../../usr/include/ TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh -TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh +TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh ip_defrag.sh TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh TEST_PROGS_EXTENDED := in_netns.sh TEST_GEN_FILES = socket TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd -TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx +TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx ip_defrag TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls +KSFT_KHDR_INSTALL := 1 include ../lib.mk $(OUTPUT)/reuseport_bpf_numa: LDFLAGS += -lnuma diff --git a/tools/testing/selftests/net/ip_defrag.c b/tools/testing/selftests/net/ip_defrag.c new file mode 100644 index 000000000000..55fdcdc78eef --- /dev/null +++ b/tools/testing/selftests/net/ip_defrag.c @@ -0,0 +1,313 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE + +#include <arpa/inet.h> +#include <errno.h> +#include <error.h> +#include <linux/in.h> +#include <netinet/ip.h> +#include <netinet/ip6.h> +#include <netinet/udp.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <time.h> +#include <unistd.h> + +static bool cfg_do_ipv4; +static bool cfg_do_ipv6; +static bool cfg_verbose; +static bool cfg_overlap; +static unsigned short cfg_port = 9000; + +const struct in_addr addr4 = { .s_addr = __constant_htonl(INADDR_LOOPBACK + 2) }; + +#define IP4_HLEN (sizeof(struct iphdr)) +#define IP6_HLEN (sizeof(struct ip6_hdr)) +#define UDP_HLEN (sizeof(struct udphdr)) + +static int msg_len; +static int max_frag_len; + +#define MSG_LEN_MAX 60000 /* Max UDP payload length. */ + +#define IP4_MF (1u << 13) /* IPv4 MF flag. */ + +static uint8_t udp_payload[MSG_LEN_MAX]; +static uint8_t ip_frame[IP_MAXPACKET]; +static uint16_t ip_id = 0xabcd; +static int msg_counter; +static int frag_counter; +static unsigned int seed; + +/* Receive a UDP packet. Validate it matches udp_payload. */ +static void recv_validate_udp(int fd_udp) +{ + ssize_t ret; + static uint8_t recv_buff[MSG_LEN_MAX]; + + ret = recv(fd_udp, recv_buff, msg_len, 0); + msg_counter++; + + if (cfg_overlap) { + if (ret != -1) + error(1, 0, "recv: expected timeout; got %d; seed = %u", + (int)ret, seed); + if (errno != ETIMEDOUT && errno != EAGAIN) + error(1, errno, "recv: expected timeout: %d; seed = %u", + errno, seed); + return; /* OK */ + } + + if (ret == -1) + error(1, errno, "recv: msg_len = %d max_frag_len = %d", + msg_len, max_frag_len); + if (ret != msg_len) + error(1, 0, "recv: wrong size: %d vs %d", (int)ret, msg_len); + if (memcmp(udp_payload, recv_buff, msg_len)) + error(1, 0, "recv: wrong data"); +} + +static uint32_t raw_checksum(uint8_t *buf, int len, uint32_t sum) +{ + int i; + + for (i = 0; i < (len & ~1U); i += 2) { + sum += (u_int16_t)ntohs(*((u_int16_t *)(buf + i))); + if (sum > 0xffff) + sum -= 0xffff; + } + + if (i < len) { + sum += buf[i] << 8; + if (sum > 0xffff) + sum -= 0xffff; + } + + return sum; +} + +static uint16_t udp_checksum(struct ip *iphdr, struct udphdr *udphdr) +{ + uint32_t sum = 0; + + sum = raw_checksum((uint8_t *)&iphdr->ip_src, 2 * sizeof(iphdr->ip_src), + IPPROTO_UDP + (uint32_t)(UDP_HLEN + msg_len)); + sum = raw_checksum((uint8_t *)udp_payload, msg_len, sum); + sum = raw_checksum((uint8_t *)udphdr, UDP_HLEN, sum); + return htons(0xffff & ~sum); +} + +static void send_fragment(int fd_raw, struct sockaddr *addr, socklen_t alen, + struct ip *iphdr, int offset) +{ + int frag_len; + int res; + + if (msg_len - offset <= max_frag_len) { + /* This is the last fragment. */ + frag_len = IP4_HLEN + msg_len - offset; + iphdr->ip_off = htons((offset + UDP_HLEN) / 8); + } else { + frag_len = IP4_HLEN + max_frag_len; + iphdr->ip_off = htons((offset + UDP_HLEN) / 8 | IP4_MF); + } + iphdr->ip_len = htons(frag_len); + memcpy(ip_frame + IP4_HLEN, udp_payload + offset, + frag_len - IP4_HLEN); + + res = sendto(fd_raw, ip_frame, frag_len, 0, addr, alen); + if (res < 0) + error(1, errno, "send_fragment"); + if (res != frag_len) + error(1, 0, "send_fragment: %d vs %d", res, frag_len); + + frag_counter++; +} + +static void send_udp_frags_v4(int fd_raw, struct sockaddr *addr, socklen_t alen) +{ + struct ip *iphdr = (struct ip *)ip_frame; + struct udphdr udphdr; + int res; + int offset; + int frag_len; + + /* Send the UDP datagram using raw IP fragments: the 0th fragment + * has the UDP header; other fragments are pieces of udp_payload + * split in chunks of frag_len size. + * + * Odd fragments (1st, 3rd, 5th, etc.) are sent out first, then + * even fragments (0th, 2nd, etc.) are sent out. + */ + memset(iphdr, 0, sizeof(*iphdr)); + iphdr->ip_hl = 5; + iphdr->ip_v = 4; + iphdr->ip_tos = 0; + iphdr->ip_id = htons(ip_id++); + iphdr->ip_ttl = 0x40; + iphdr->ip_p = IPPROTO_UDP; + iphdr->ip_src.s_addr = htonl(INADDR_LOOPBACK); + iphdr->ip_dst = addr4; + iphdr->ip_sum = 0; + + /* Odd fragments. */ + offset = 0; + while (offset < msg_len) { + send_fragment(fd_raw, addr, alen, iphdr, offset); + offset += 2 * max_frag_len; + } + + if (cfg_overlap) { + /* Send an extra random fragment. */ + offset = rand() % (UDP_HLEN + msg_len - 1); + /* sendto() returns EINVAL if offset + frag_len is too small. */ + frag_len = IP4_HLEN + UDP_HLEN + rand() % 256; + iphdr->ip_off = htons(offset / 8 | IP4_MF); + iphdr->ip_len = htons(frag_len); + res = sendto(fd_raw, ip_frame, frag_len, 0, addr, alen); + if (res < 0) + error(1, errno, "sendto overlap"); + if (res != frag_len) + error(1, 0, "sendto overlap: %d vs %d", (int)res, frag_len); + frag_counter++; + } + + /* Zeroth fragment (UDP header). */ + frag_len = IP4_HLEN + UDP_HLEN; + iphdr->ip_len = htons(frag_len); + iphdr->ip_off = htons(IP4_MF); + + udphdr.source = htons(cfg_port + 1); + udphdr.dest = htons(cfg_port); + udphdr.len = htons(UDP_HLEN + msg_len); + udphdr.check = 0; + udphdr.check = udp_checksum(iphdr, &udphdr); + + memcpy(ip_frame + IP4_HLEN, &udphdr, UDP_HLEN); + res = sendto(fd_raw, ip_frame, frag_len, 0, addr, alen); + if (res < 0) + error(1, errno, "sendto UDP header"); + if (res != frag_len) + error(1, 0, "sendto UDP header: %d vs %d", (int)res, frag_len); + frag_counter++; + + /* Even fragments. */ + offset = max_frag_len; + while (offset < msg_len) { + send_fragment(fd_raw, addr, alen, iphdr, offset); + offset += 2 * max_frag_len; + } +} + +static void run_test(struct sockaddr *addr, socklen_t alen) +{ + int fd_tx_udp, fd_tx_raw, fd_rx_udp; + struct timeval tv = { .tv_sec = 0, .tv_usec = 10 * 1000 }; + int idx; + + /* Initialize the payload. */ + for (idx = 0; idx < MSG_LEN_MAX; ++idx) + udp_payload[idx] = idx % 256; + + /* Open sockets. */ + fd_tx_udp = socket(addr->sa_family, SOCK_DGRAM, 0); + if (fd_tx_udp == -1) + error(1, errno, "socket tx_udp"); + + fd_tx_raw = socket(addr->sa_family, SOCK_RAW, IPPROTO_RAW); + if (fd_tx_raw == -1) + error(1, errno, "socket tx_raw"); + + fd_rx_udp = socket(addr->sa_family, SOCK_DGRAM, 0); + if (fd_rx_udp == -1) + error(1, errno, "socket rx_udp"); + if (bind(fd_rx_udp, addr, alen)) + error(1, errno, "bind"); + /* Fail fast. */ + if (setsockopt(fd_rx_udp, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv))) + error(1, errno, "setsockopt rcv timeout"); + + for (msg_len = 1; msg_len < MSG_LEN_MAX; msg_len += (rand() % 4096)) { + if (cfg_verbose) + printf("msg_len: %d\n", msg_len); + max_frag_len = addr->sa_family == AF_INET ? 8 : 1280; + for (; max_frag_len < 1500 && max_frag_len <= msg_len; + max_frag_len += 8) { + send_udp_frags_v4(fd_tx_raw, addr, alen); + recv_validate_udp(fd_rx_udp); + } + } + + /* Cleanup. */ + if (close(fd_tx_raw)) + error(1, errno, "close tx_raw"); + if (close(fd_tx_udp)) + error(1, errno, "close tx_udp"); + if (close(fd_rx_udp)) + error(1, errno, "close rx_udp"); + + if (cfg_verbose) + printf("processed %d messages, %d fragments\n", + msg_counter, frag_counter); + + fprintf(stderr, "PASS\n"); +} + + +static void run_test_v4(void) +{ + struct sockaddr_in addr = {0}; + + addr.sin_family = AF_INET; + addr.sin_port = htons(cfg_port); + addr.sin_addr = addr4; + + run_test((void *)&addr, sizeof(addr)); +} + +static void run_test_v6(void) +{ + fprintf(stderr, "NOT IMPL.\n"); + exit(1); +} + +static void parse_opts(int argc, char **argv) +{ + int c; + + while ((c = getopt(argc, argv, "46ov")) != -1) { + switch (c) { + case '4': + cfg_do_ipv4 = true; + break; + case '6': + cfg_do_ipv6 = true; + break; + case 'o': + cfg_overlap = true; + break; + case 'v': + cfg_verbose = true; + break; + default: + error(1, 0, "%s: parse error", argv[0]); + } + } +} + +int main(int argc, char **argv) +{ + parse_opts(argc, argv); + seed = time(NULL); + srand(seed); + + if (cfg_do_ipv4) + run_test_v4(); + if (cfg_do_ipv6) + run_test_v6(); + + return 0; +} diff --git a/tools/testing/selftests/net/ip_defrag.sh b/tools/testing/selftests/net/ip_defrag.sh new file mode 100755 index 000000000000..78743adcca9e --- /dev/null +++ b/tools/testing/selftests/net/ip_defrag.sh @@ -0,0 +1,28 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# Run a couple of IP defragmentation tests. + +set +x +set -e + +echo "ipv4 defrag" + +run_v4() { +sysctl -w net.ipv4.ipfrag_high_thresh=9000000 &> /dev/null +sysctl -w net.ipv4.ipfrag_low_thresh=7000000 &> /dev/null +./ip_defrag -4 +} +export -f run_v4 + +./in_netns.sh "run_v4" + +echo "ipv4 defrag with overlaps" +run_v4o() { +sysctl -w net.ipv4.ipfrag_high_thresh=9000000 &> /dev/null +sysctl -w net.ipv4.ipfrag_low_thresh=7000000 &> /dev/null +./ip_defrag -4o +} +export -f run_v4o + +./in_netns.sh "run_v4o" diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index f8cc38afffa2..32a194e3e07a 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -46,6 +46,9 @@ # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 +# Some systems don't have a ping6 binary anymore +which ping6 > /dev/null 2>&1 && ping6=$(which ping6) || ping6=$(which ping) + tests=" pmtu_vti6_exception vti6: PMTU exceptions pmtu_vti4_exception vti4: PMTU exceptions @@ -274,7 +277,7 @@ test_pmtu_vti6_exception() { mtu "${ns_b}" veth_b 4000 mtu "${ns_a}" vti6_a 5000 mtu "${ns_b}" vti6_b 5000 - ${ns_a} ping6 -q -i 0.1 -w 2 -s 60000 ${vti6_b_addr} > /dev/null + ${ns_a} ${ping6} -q -i 0.1 -w 2 -s 60000 ${vti6_b_addr} > /dev/null # Check that exception was created if [ "$(route_get_dst_pmtu_from_exception "${ns_a}" ${vti6_b_addr})" = "" ]; then @@ -334,7 +337,7 @@ test_pmtu_vti4_link_add_mtu() { fail=0 min=68 - max=$((65528 - 20)) + max=$((65535 - 20)) # Check invalid values first for v in $((min - 1)) $((max + 1)); do ${ns_a} ip link add vti4_a mtu ${v} type vti local ${veth4_a_addr} remote ${veth4_b_addr} key 10 2>/dev/null diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index b3ebf2646e52..11d54c36ae49 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -121,11 +121,11 @@ TEST_F(tls, send_then_sendfile) buf = (char *)malloc(st.st_size); EXPECT_EQ(send(self->fd, test_str, to_send, 0), to_send); - EXPECT_EQ(recv(self->cfd, recv_buf, to_send, 0), to_send); + EXPECT_EQ(recv(self->cfd, recv_buf, to_send, MSG_WAITALL), to_send); EXPECT_EQ(memcmp(test_str, recv_buf, to_send), 0); EXPECT_GE(sendfile(self->fd, filefd, 0, st.st_size), 0); - EXPECT_EQ(recv(self->cfd, buf, st.st_size, 0), st.st_size); + EXPECT_EQ(recv(self->cfd, buf, st.st_size, MSG_WAITALL), st.st_size); } TEST_F(tls, recv_max) @@ -160,7 +160,7 @@ TEST_F(tls, msg_more) EXPECT_EQ(send(self->fd, test_str, send_len, MSG_MORE), send_len); EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_DONTWAIT), -1); EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len); - EXPECT_EQ(recv(self->cfd, buf, send_len * 2, MSG_DONTWAIT), + EXPECT_EQ(recv(self->cfd, buf, send_len * 2, MSG_WAITALL), send_len * 2); EXPECT_EQ(memcmp(buf, test_str, send_len), 0); } @@ -180,7 +180,7 @@ TEST_F(tls, sendmsg_single) msg.msg_iov = &vec; msg.msg_iovlen = 1; EXPECT_EQ(sendmsg(self->fd, &msg, 0), send_len); - EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len); + EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_WAITALL), send_len); EXPECT_EQ(memcmp(buf, test_str, send_len), 0); } @@ -306,7 +306,7 @@ TEST_F(tls, splice_from_pipe2) EXPECT_GE(splice(p[0], NULL, self->fd, NULL, 8000, 0), 0); EXPECT_GE(write(p2[1], mem_send + 8000, 8000), 0); EXPECT_GE(splice(p2[0], NULL, self->fd, NULL, 8000, 0), 0); - EXPECT_GE(recv(self->cfd, mem_recv, send_len, 0), 0); + EXPECT_EQ(recv(self->cfd, mem_recv, send_len, MSG_WAITALL), send_len); EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0); } @@ -436,7 +436,7 @@ TEST_F(tls, multiple_send_single_recv) EXPECT_GE(send(self->fd, send_mem, send_len, 0), 0); EXPECT_GE(send(self->fd, send_mem, send_len, 0), 0); memset(recv_mem, 0, total_len); - EXPECT_EQ(recv(self->cfd, recv_mem, total_len, 0), total_len); + EXPECT_EQ(recv(self->cfd, recv_mem, total_len, MSG_WAITALL), total_len); EXPECT_EQ(memcmp(send_mem, recv_mem, send_len), 0); EXPECT_EQ(memcmp(send_mem, recv_mem + send_len, send_len), 0); @@ -502,6 +502,78 @@ TEST_F(tls, recv_peek_multiple) EXPECT_EQ(memcmp(test_str, buf, send_len), 0); } +TEST_F(tls, recv_peek_multiple_records) +{ + char const *test_str = "test_read_peek_mult_recs"; + char const *test_str_first = "test_read_peek"; + char const *test_str_second = "_mult_recs"; + int len; + char buf[64]; + + len = strlen(test_str_first); + EXPECT_EQ(send(self->fd, test_str_first, len, 0), len); + + len = strlen(test_str_second) + 1; + EXPECT_EQ(send(self->fd, test_str_second, len, 0), len); + + len = sizeof(buf); + memset(buf, 0, len); + EXPECT_NE(recv(self->cfd, buf, len, MSG_PEEK), -1); + + /* MSG_PEEK can only peek into the current record. */ + len = strlen(test_str_first) + 1; + EXPECT_EQ(memcmp(test_str_first, buf, len), 0); + + len = sizeof(buf); + memset(buf, 0, len); + EXPECT_NE(recv(self->cfd, buf, len, 0), -1); + + /* Non-MSG_PEEK will advance strparser (and therefore record) + * however. + */ + len = strlen(test_str) + 1; + EXPECT_EQ(memcmp(test_str, buf, len), 0); + + /* MSG_MORE will hold current record open, so later MSG_PEEK + * will see everything. + */ + len = strlen(test_str_first); + EXPECT_EQ(send(self->fd, test_str_first, len, MSG_MORE), len); + + len = strlen(test_str_second) + 1; + EXPECT_EQ(send(self->fd, test_str_second, len, 0), len); + + len = sizeof(buf); + memset(buf, 0, len); + EXPECT_NE(recv(self->cfd, buf, len, MSG_PEEK), -1); + + len = strlen(test_str) + 1; + EXPECT_EQ(memcmp(test_str, buf, len), 0); +} + +TEST_F(tls, recv_peek_large_buf_mult_recs) +{ + char const *test_str = "test_read_peek_mult_recs"; + char const *test_str_first = "test_read_peek"; + char const *test_str_second = "_mult_recs"; + int len; + char buf[64]; + + len = strlen(test_str_first); + EXPECT_EQ(send(self->fd, test_str_first, len, 0), len); + + len = strlen(test_str_second) + 1; + EXPECT_EQ(send(self->fd, test_str_second, len, 0), len); + + len = sizeof(buf); + memset(buf, 0, len); + EXPECT_NE(recv(self->cfd, buf, len, MSG_PEEK), -1); + + len = strlen(test_str) + 1; + EXPECT_EQ(memcmp(test_str, buf, len), 0); +} + + TEST_F(tls, pollin) { char const *test_str = "test_poll"; @@ -515,7 +587,7 @@ TEST_F(tls, pollin) EXPECT_EQ(poll(&fd, 1, 20), 1); EXPECT_EQ(fd.revents & POLLIN, 1); - EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len); + EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_WAITALL), send_len); /* Test timing out */ EXPECT_EQ(poll(&fd, 1, 20), 0); } @@ -533,7 +605,7 @@ TEST_F(tls, poll_wait) /* Set timeout to inf. secs */ EXPECT_EQ(poll(&fd, 1, -1), 1); EXPECT_EQ(fd.revents & POLLIN, 1); - EXPECT_EQ(recv(self->cfd, recv_mem, send_len, 0), send_len); + EXPECT_EQ(recv(self->cfd, recv_mem, send_len, MSG_WAITALL), send_len); } TEST_F(tls, blocking) @@ -679,7 +751,7 @@ TEST_F(tls, control_msg) EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1); vec.iov_base = buf; - EXPECT_EQ(recvmsg(self->cfd, &msg, 0), send_len); + EXPECT_EQ(recvmsg(self->cfd, &msg, MSG_WAITALL), send_len); cmsg = CMSG_FIRSTHDR(&msg); EXPECT_NE(cmsg, NULL); EXPECT_EQ(cmsg->cmsg_level, SOL_TLS); diff --git a/tools/testing/selftests/networking/timestamping/Makefile b/tools/testing/selftests/networking/timestamping/Makefile index a728040edbe1..14cfcf006936 100644 --- a/tools/testing/selftests/networking/timestamping/Makefile +++ b/tools/testing/selftests/networking/timestamping/Makefile @@ -5,6 +5,7 @@ TEST_PROGS := hwtstamp_config rxtimestamp timestamping txtimestamp all: $(TEST_PROGS) +top_srcdir = ../../../../.. include ../../lib.mk clean: diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json index f03763d81617..30f9b54bd666 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json @@ -313,6 +313,54 @@ ] }, { + "id": "6aaf", + "name": "Add police actions with conform-exceed control pass/pipe [with numeric values]", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action police rate 3mbit burst 250k conform-exceed 0/3 index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action police index 1", + "matchPattern": "action order [0-9]*: police 0x1 rate 3Mbit burst 250Kb mtu 2Kb action pass/pipe", + "matchCount": "1", + "teardown": [ + "$TC actions flush action police" + ] + }, + { + "id": "29b1", + "name": "Add police actions with conform-exceed control <invalid>/drop", + "category": [ + "actions", + "police" + ], + "setup": [ + [ + "$TC actions flush action police", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action police rate 3mbit burst 250k conform-exceed 10/drop index 1", + "expExitCode": "255", + "verifyCmd": "$TC actions ls action police", + "matchPattern": "action order [0-9]*: police 0x1 rate 3Mbit burst 250Kb mtu 2Kb action ", + "matchCount": "0", + "teardown": [ + "$TC actions flush action police" + ] + }, + { "id": "c26f", "name": "Add police action with invalid peakrate value", "category": [ diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index 9881876d2aa0..e94b7b14bcb2 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -26,10 +26,6 @@ TEST_PROGS := run_vmtests include ../lib.mk -$(OUTPUT)/userfaultfd: ../../../../usr/include/linux/kernel.h $(OUTPUT)/userfaultfd: LDLIBS += -lpthread $(OUTPUT)/mlock-random-test: LDLIBS += -lcap - -../../../../usr/include/linux/kernel.h: - make -C ../../../.. headers_install diff --git a/tools/vm/page-types.c b/tools/vm/page-types.c index 30cb0a0713ff..37908a83ddc2 100644 --- a/tools/vm/page-types.c +++ b/tools/vm/page-types.c @@ -159,12 +159,6 @@ static const char * const page_flag_names[] = { }; -static const char * const debugfs_known_mountpoints[] = { - "/sys/kernel/debug", - "/debug", - 0, -}; - /* * data structures */ diff --git a/tools/vm/slabinfo.c b/tools/vm/slabinfo.c index f82c2eaa859d..334b16db0ebb 100644 --- a/tools/vm/slabinfo.c +++ b/tools/vm/slabinfo.c @@ -30,8 +30,8 @@ struct slabinfo { int alias; int refs; int aliases, align, cache_dma, cpu_slabs, destroy_by_rcu; - int hwcache_align, object_size, objs_per_slab; - int sanity_checks, slab_size, store_user, trace; + unsigned int hwcache_align, object_size, objs_per_slab; + unsigned int sanity_checks, slab_size, store_user, trace; int order, poison, reclaim_account, red_zone; unsigned long partial, objects, slabs, objects_partial, objects_total; unsigned long alloc_fastpath, alloc_slowpath; diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c index 91aaf73b00df..ed162a6c57c5 100644 --- a/virt/kvm/arm/mmu.c +++ b/virt/kvm/arm/mmu.c @@ -1817,18 +1817,6 @@ static int kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *dat return 0; } -int kvm_unmap_hva(struct kvm *kvm, unsigned long hva) -{ - unsigned long end = hva + PAGE_SIZE; - - if (!kvm->arch.pgd) - return 0; - - trace_kvm_unmap_hva(hva); - handle_hva_to_gpa(kvm, hva, end, &kvm_unmap_hva_handler, NULL); - return 0; -} - int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end) { @@ -1860,13 +1848,20 @@ static int kvm_set_spte_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte) { unsigned long end = hva + PAGE_SIZE; + kvm_pfn_t pfn = pte_pfn(pte); pte_t stage2_pte; if (!kvm->arch.pgd) return; trace_kvm_set_spte_hva(hva); - stage2_pte = pfn_pte(pte_pfn(pte), PAGE_S2); + + /* + * We've moved a page around, probably through CoW, so let's treat it + * just like a translation fault and clean the cache to the PoC. + */ + clean_dcache_guest_page(pfn, PAGE_SIZE); + stage2_pte = pfn_pte(pfn, PAGE_S2); handle_hva_to_gpa(kvm, hva, end, &kvm_set_spte_handler, &stage2_pte); } diff --git a/virt/kvm/arm/trace.h b/virt/kvm/arm/trace.h index e53b596f483b..57b3edebbb40 100644 --- a/virt/kvm/arm/trace.h +++ b/virt/kvm/arm/trace.h @@ -134,21 +134,6 @@ TRACE_EVENT(kvm_mmio_emulate, __entry->vcpu_pc, __entry->instr, __entry->cpsr) ); -TRACE_EVENT(kvm_unmap_hva, - TP_PROTO(unsigned long hva), - TP_ARGS(hva), - - TP_STRUCT__entry( - __field( unsigned long, hva ) - ), - - TP_fast_assign( - __entry->hva = hva; - ), - - TP_printk("mmu notifier unmap hva: %#08lx", __entry->hva) -); - TRACE_EVENT(kvm_unmap_hva_range, TP_PROTO(unsigned long start, unsigned long end), TP_ARGS(start, end), |